From 07a3061e0832fe22932e0fa977581e45b9c42431 Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Sun, 3 Jul 2016 13:31:35 +0200 Subject: batman-adv: netlink: add routing_algo query BATADV_CMD_GET_ROUTING_ALGOS is used to get the list of supported routing algorithms. Signed-off-by: Matthias Schiffer Signed-off-by: Andrew Lunn [sven.eckelmann@open-mesh.com: Reduce the number of changes to BATADV_CMD_GET_ROUTING_ALGOS, fix includes] Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich Signed-off-by: Marek Lindner --- include/uapi/linux/batman_adv.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index 0fbf6fd4711b..7afce444a64e 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -73,6 +73,7 @@ enum batadv_nl_attrs { * @BATADV_CMD_GET_MESH_INFO: Query basic information about batman-adv device * @BATADV_CMD_TP_METER: Start a tp meter session * @BATADV_CMD_TP_METER_CANCEL: Cancel a tp meter session + * @BATADV_CMD_GET_ROUTING_ALGOS: Query the list of routing algorithms. * @__BATADV_CMD_AFTER_LAST: internal use * @BATADV_CMD_MAX: highest used command number */ @@ -81,6 +82,7 @@ enum batadv_nl_commands { BATADV_CMD_GET_MESH_INFO, BATADV_CMD_TP_METER, BATADV_CMD_TP_METER_CANCEL, + BATADV_CMD_GET_ROUTING_ALGOS, /* add new commands above here */ __BATADV_CMD_AFTER_LAST, BATADV_CMD_MAX = __BATADV_CMD_AFTER_LAST - 1 -- cgit v1.2.3 From b60620cf567b79da46096a0ba29b39f23b6e7f1c Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Sun, 3 Jul 2016 13:31:36 +0200 Subject: batman-adv: netlink: hardif query BATADV_CMD_GET_HARDIFS will return the list of hardifs (including index, name and MAC address) of all hardifs for a given softif. Signed-off-by: Matthias Schiffer Signed-off-by: Andrew Lunn [sven.eckelmann@open-mesh.com: Reduce the number of changes to BATADV_CMD_GET_HARDIFS, add policy for attributes] Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich Signed-off-by: Marek Lindner --- include/uapi/linux/batman_adv.h | 4 ++ net/batman-adv/netlink.c | 128 +++++++++++++++++++++++++++++++++++++++- 2 files changed, 130 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index 7afce444a64e..8abcbca14b6a 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -40,6 +40,7 @@ * @BATADV_ATTR_TPMETER_BYTES: amount of acked bytes during run * @BATADV_ATTR_TPMETER_COOKIE: session cookie to match tp_meter session * @BATADV_ATTR_PAD: attribute used for padding for 64-bit alignment + * @BATADV_ATTR_ACTIVE: Flag indicating if the hard interface is active * @__BATADV_ATTR_AFTER_LAST: internal use * @NUM_BATADV_ATTR: total number of batadv_nl_attrs available * @BATADV_ATTR_MAX: highest attribute number currently defined @@ -60,6 +61,7 @@ enum batadv_nl_attrs { BATADV_ATTR_TPMETER_BYTES, BATADV_ATTR_TPMETER_COOKIE, BATADV_ATTR_PAD, + BATADV_ATTR_ACTIVE, /* add attributes above here, update the policy in netlink.c */ __BATADV_ATTR_AFTER_LAST, NUM_BATADV_ATTR = __BATADV_ATTR_AFTER_LAST, @@ -74,6 +76,7 @@ enum batadv_nl_attrs { * @BATADV_CMD_TP_METER: Start a tp meter session * @BATADV_CMD_TP_METER_CANCEL: Cancel a tp meter session * @BATADV_CMD_GET_ROUTING_ALGOS: Query the list of routing algorithms. + * @BATADV_CMD_GET_HARDIFS: Query list of hard interfaces * @__BATADV_CMD_AFTER_LAST: internal use * @BATADV_CMD_MAX: highest used command number */ @@ -83,6 +86,7 @@ enum batadv_nl_commands { BATADV_CMD_TP_METER, BATADV_CMD_TP_METER_CANCEL, BATADV_CMD_GET_ROUTING_ALGOS, + BATADV_CMD_GET_HARDIFS, /* add new commands above here */ __BATADV_CMD_AFTER_LAST, BATADV_CMD_MAX = __BATADV_CMD_AFTER_LAST - 1 diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 19fb2657e274..3f872d6eec57 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -26,10 +26,14 @@ #include #include #include +#include +#include +#include #include #include #include #include +#include #include #include "bat_algo.h" @@ -37,8 +41,6 @@ #include "soft-interface.h" #include "tp_meter.h" -struct sk_buff; - struct genl_family batadv_netlink_family = { .id = GENL_ID_GENERATE, .hdrsize = 0, @@ -70,8 +72,24 @@ static struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = { [BATADV_ATTR_TPMETER_TEST_TIME] = { .type = NLA_U32 }, [BATADV_ATTR_TPMETER_BYTES] = { .type = NLA_U64 }, [BATADV_ATTR_TPMETER_COOKIE] = { .type = NLA_U32 }, + [BATADV_ATTR_ACTIVE] = { .type = NLA_FLAG }, }; +/** + * batadv_netlink_get_ifindex - Extract an interface index from a message + * @nlh: Message header + * @attrtype: Attribute which holds an interface index + * + * Return: interface index, or 0. + */ +static int +batadv_netlink_get_ifindex(const struct nlmsghdr *nlh, int attrtype) +{ + struct nlattr *attr = nlmsg_find_attr(nlh, GENL_HDRLEN, attrtype); + + return attr ? nla_get_u32(attr) : 0; +} + /** * batadv_netlink_mesh_info_put - fill in generic information about mesh * interface @@ -381,6 +399,106 @@ out: return ret; } +/** + * batadv_netlink_dump_hardif_entry - Dump one hard interface into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @hard_iface: Hard interface to dump + * + * Return: error code, or 0 on success + */ +static int +batadv_netlink_dump_hardif_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_hard_iface *hard_iface) +{ + struct net_device *net_dev = hard_iface->net_dev; + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, NLM_F_MULTI, + BATADV_CMD_GET_HARDIFS); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, + net_dev->ifindex) || + nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, + net_dev->name) || + nla_put(msg, BATADV_ATTR_HARD_ADDRESS, ETH_ALEN, + net_dev->dev_addr)) + goto nla_put_failure; + + if (hard_iface->if_status == BATADV_IF_ACTIVE) { + if (nla_put_flag(msg, BATADV_ATTR_ACTIVE)) + goto nla_put_failure; + } + + genlmsg_end(msg, hdr); + return 0; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +/** + * batadv_netlink_dump_hardifs - Dump all hard interface into a messages + * @msg: Netlink message to dump into + * @cb: Parameters from query + * + * Return: error code, or length of reply message on success + */ +static int +batadv_netlink_dump_hardifs(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct net *net = sock_net(cb->skb->sk); + struct net_device *soft_iface; + struct batadv_hard_iface *hard_iface; + int ifindex; + int portid = NETLINK_CB(cb->skb).portid; + int seq = cb->nlh->nlmsg_seq; + int skip = cb->args[0]; + int i = 0; + + ifindex = batadv_netlink_get_ifindex(cb->nlh, + BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return -EINVAL; + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface) + return -ENODEV; + + if (!batadv_softif_is_valid(soft_iface)) { + dev_put(soft_iface); + return -ENODEV; + } + + rcu_read_lock(); + + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->soft_iface != soft_iface) + continue; + + if (i++ < skip) + continue; + + if (batadv_netlink_dump_hardif_entry(msg, portid, seq, + hard_iface)) { + i--; + break; + } + } + + rcu_read_unlock(); + + dev_put(soft_iface); + + cb->args[0] = i; + + return msg->len; +} + static struct genl_ops batadv_netlink_ops[] = { { .cmd = BATADV_CMD_GET_MESH_INFO, @@ -406,6 +524,12 @@ static struct genl_ops batadv_netlink_ops[] = { .policy = batadv_netlink_policy, .dumpit = batadv_algo_dump, }, + { + .cmd = BATADV_CMD_GET_HARDIFS, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .dumpit = batadv_netlink_dump_hardifs, + }, }; /** -- cgit v1.2.3 From d34f05507db245bef819b684ad84f9e0f9bb003d Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Sun, 3 Jul 2016 13:31:37 +0200 Subject: batman-adv: netlink: add translation table query This adds the commands BATADV_CMD_GET_TRANSTABLE_LOCAL and BATADV_CMD_GET_TRANSTABLE_GLOBAL, which correspond to the transtable_local and transtable_global debugfs files. The batadv_tt_client_flags enum is moved to the UAPI to expose it as part of the netlink API. Signed-off-by: Matthias Schiffer Signed-off-by: Andrew Lunn [sven.eckelmann@open-mesh.com: add policy for attributes, fix includes] Signed-off-by: Sven Eckelmann [sw@simonwunderlich.de: fix VID attributes content] Signed-off-by: Simon Wunderlich Signed-off-by: Marek Lindner --- include/uapi/linux/batman_adv.h | 56 ++++++ net/batman-adv/netlink.c | 23 ++- net/batman-adv/netlink.h | 3 + net/batman-adv/packet.h | 36 ---- net/batman-adv/translation-table.c | 377 +++++++++++++++++++++++++++++++++++++ net/batman-adv/translation-table.h | 4 + 6 files changed, 462 insertions(+), 37 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index 8abcbca14b6a..1168d058cd2b 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -22,6 +22,42 @@ #define BATADV_NL_MCAST_GROUP_TPMETER "tpmeter" +/** + * enum batadv_tt_client_flags - TT client specific flags + * @BATADV_TT_CLIENT_DEL: the client has to be deleted from the table + * @BATADV_TT_CLIENT_ROAM: the client roamed to/from another node and the new + * update telling its new real location has not been received/sent yet + * @BATADV_TT_CLIENT_WIFI: this client is connected through a wifi interface. + * This information is used by the "AP Isolation" feature + * @BATADV_TT_CLIENT_ISOLA: this client is considered "isolated". This + * information is used by the Extended Isolation feature + * @BATADV_TT_CLIENT_NOPURGE: this client should never be removed from the table + * @BATADV_TT_CLIENT_NEW: this client has been added to the local table but has + * not been announced yet + * @BATADV_TT_CLIENT_PENDING: this client is marked for removal but it is kept + * in the table for one more originator interval for consistency purposes + * @BATADV_TT_CLIENT_TEMP: this global client has been detected to be part of + * the network but no nnode has already announced it + * + * Bits from 0 to 7 are called _remote flags_ because they are sent on the wire. + * Bits from 8 to 15 are called _local flags_ because they are used for local + * computations only. + * + * Bits from 4 to 7 - a subset of remote flags - are ensured to be in sync with + * the other nodes in the network. To achieve this goal these flags are included + * in the TT CRC computation. + */ +enum batadv_tt_client_flags { + BATADV_TT_CLIENT_DEL = (1 << 0), + BATADV_TT_CLIENT_ROAM = (1 << 1), + BATADV_TT_CLIENT_WIFI = (1 << 4), + BATADV_TT_CLIENT_ISOLA = (1 << 5), + BATADV_TT_CLIENT_NOPURGE = (1 << 8), + BATADV_TT_CLIENT_NEW = (1 << 9), + BATADV_TT_CLIENT_PENDING = (1 << 10), + BATADV_TT_CLIENT_TEMP = (1 << 11), +}; + /** * enum batadv_nl_attrs - batman-adv netlink attributes * @@ -41,6 +77,14 @@ * @BATADV_ATTR_TPMETER_COOKIE: session cookie to match tp_meter session * @BATADV_ATTR_PAD: attribute used for padding for 64-bit alignment * @BATADV_ATTR_ACTIVE: Flag indicating if the hard interface is active + * @BATADV_ATTR_TT_ADDRESS: Client MAC address + * @BATADV_ATTR_TT_TTVN: Translation table version + * @BATADV_ATTR_TT_LAST_TTVN: Previous translation table version + * @BATADV_ATTR_TT_CRC32: CRC32 over translation table + * @BATADV_ATTR_TT_VID: VLAN ID + * @BATADV_ATTR_TT_FLAGS: Translation table client flags + * @BATADV_ATTR_FLAG_BEST: Flags indicating entry is the best + * @BATADV_ATTR_LAST_SEEN_MSECS: Time in milliseconds since last seen * @__BATADV_ATTR_AFTER_LAST: internal use * @NUM_BATADV_ATTR: total number of batadv_nl_attrs available * @BATADV_ATTR_MAX: highest attribute number currently defined @@ -62,6 +106,14 @@ enum batadv_nl_attrs { BATADV_ATTR_TPMETER_COOKIE, BATADV_ATTR_PAD, BATADV_ATTR_ACTIVE, + BATADV_ATTR_TT_ADDRESS, + BATADV_ATTR_TT_TTVN, + BATADV_ATTR_TT_LAST_TTVN, + BATADV_ATTR_TT_CRC32, + BATADV_ATTR_TT_VID, + BATADV_ATTR_TT_FLAGS, + BATADV_ATTR_FLAG_BEST, + BATADV_ATTR_LAST_SEEN_MSECS, /* add attributes above here, update the policy in netlink.c */ __BATADV_ATTR_AFTER_LAST, NUM_BATADV_ATTR = __BATADV_ATTR_AFTER_LAST, @@ -77,6 +129,8 @@ enum batadv_nl_attrs { * @BATADV_CMD_TP_METER_CANCEL: Cancel a tp meter session * @BATADV_CMD_GET_ROUTING_ALGOS: Query the list of routing algorithms. * @BATADV_CMD_GET_HARDIFS: Query list of hard interfaces + * @BATADV_CMD_GET_TRANSTABLE_LOCAL: Query list of local translations + * @BATADV_CMD_GET_TRANSTABLE_GLOBAL Query list of global translations * @__BATADV_CMD_AFTER_LAST: internal use * @BATADV_CMD_MAX: highest used command number */ @@ -87,6 +141,8 @@ enum batadv_nl_commands { BATADV_CMD_TP_METER_CANCEL, BATADV_CMD_GET_ROUTING_ALGOS, BATADV_CMD_GET_HARDIFS, + BATADV_CMD_GET_TRANSTABLE_LOCAL, + BATADV_CMD_GET_TRANSTABLE_GLOBAL, /* add new commands above here */ __BATADV_CMD_AFTER_LAST, BATADV_CMD_MAX = __BATADV_CMD_AFTER_LAST - 1 diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 3f872d6eec57..14360ec16513 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -40,6 +40,7 @@ #include "hard-interface.h" #include "soft-interface.h" #include "tp_meter.h" +#include "translation-table.h" struct genl_family batadv_netlink_family = { .id = GENL_ID_GENERATE, @@ -73,6 +74,14 @@ static struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = { [BATADV_ATTR_TPMETER_BYTES] = { .type = NLA_U64 }, [BATADV_ATTR_TPMETER_COOKIE] = { .type = NLA_U32 }, [BATADV_ATTR_ACTIVE] = { .type = NLA_FLAG }, + [BATADV_ATTR_TT_ADDRESS] = { .len = ETH_ALEN }, + [BATADV_ATTR_TT_TTVN] = { .type = NLA_U8 }, + [BATADV_ATTR_TT_LAST_TTVN] = { .type = NLA_U8 }, + [BATADV_ATTR_TT_CRC32] = { .type = NLA_U32 }, + [BATADV_ATTR_TT_VID] = { .type = NLA_U16 }, + [BATADV_ATTR_TT_FLAGS] = { .type = NLA_U32 }, + [BATADV_ATTR_FLAG_BEST] = { .type = NLA_FLAG }, + [BATADV_ATTR_LAST_SEEN_MSECS] = { .type = NLA_U32 }, }; /** @@ -82,7 +91,7 @@ static struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = { * * Return: interface index, or 0. */ -static int +int batadv_netlink_get_ifindex(const struct nlmsghdr *nlh, int attrtype) { struct nlattr *attr = nlmsg_find_attr(nlh, GENL_HDRLEN, attrtype); @@ -530,6 +539,18 @@ static struct genl_ops batadv_netlink_ops[] = { .policy = batadv_netlink_policy, .dumpit = batadv_netlink_dump_hardifs, }, + { + .cmd = BATADV_CMD_GET_TRANSTABLE_LOCAL, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .dumpit = batadv_tt_local_dump, + }, + { + .cmd = BATADV_CMD_GET_TRANSTABLE_GLOBAL, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .dumpit = batadv_tt_global_dump, + }, }; /** diff --git a/net/batman-adv/netlink.h b/net/batman-adv/netlink.h index b399f49504df..52eb16281aba 100644 --- a/net/batman-adv/netlink.h +++ b/net/batman-adv/netlink.h @@ -23,8 +23,11 @@ #include #include +struct nlmsghdr; + void batadv_netlink_register(void); void batadv_netlink_unregister(void); +int batadv_netlink_get_ifindex(const struct nlmsghdr *nlh, int attrtype); int batadv_netlink_tpmeter_notify(struct batadv_priv *bat_priv, const u8 *dst, u8 result, u32 test_time, u64 total_bytes, diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index 6b011ff64dd8..6afc0b86950e 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -128,42 +128,6 @@ enum batadv_tt_data_flags { BATADV_TT_FULL_TABLE = BIT(4), }; -/** - * enum batadv_tt_client_flags - TT client specific flags - * @BATADV_TT_CLIENT_DEL: the client has to be deleted from the table - * @BATADV_TT_CLIENT_ROAM: the client roamed to/from another node and the new - * update telling its new real location has not been received/sent yet - * @BATADV_TT_CLIENT_WIFI: this client is connected through a wifi interface. - * This information is used by the "AP Isolation" feature - * @BATADV_TT_CLIENT_ISOLA: this client is considered "isolated". This - * information is used by the Extended Isolation feature - * @BATADV_TT_CLIENT_NOPURGE: this client should never be removed from the table - * @BATADV_TT_CLIENT_NEW: this client has been added to the local table but has - * not been announced yet - * @BATADV_TT_CLIENT_PENDING: this client is marked for removal but it is kept - * in the table for one more originator interval for consistency purposes - * @BATADV_TT_CLIENT_TEMP: this global client has been detected to be part of - * the network but no nnode has already announced it - * - * Bits from 0 to 7 are called _remote flags_ because they are sent on the wire. - * Bits from 8 to 15 are called _local flags_ because they are used for local - * computations only. - * - * Bits from 4 to 7 - a subset of remote flags - are ensured to be in sync with - * the other nodes in the network. To achieve this goal these flags are included - * in the TT CRC computation. - */ -enum batadv_tt_client_flags { - BATADV_TT_CLIENT_DEL = BIT(0), - BATADV_TT_CLIENT_ROAM = BIT(1), - BATADV_TT_CLIENT_WIFI = BIT(4), - BATADV_TT_CLIENT_ISOLA = BIT(5), - BATADV_TT_CLIENT_NOPURGE = BIT(8), - BATADV_TT_CLIENT_NEW = BIT(9), - BATADV_TT_CLIENT_PENDING = BIT(10), - BATADV_TT_CLIENT_TEMP = BIT(11), -}; - /** * enum batadv_vlan_flags - flags for the four MSB of any vlan ID field * @BATADV_VLAN_HAS_TAG: whether the field contains a valid vlan tag or not diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index af2bfef6dca8..20804078293c 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -37,20 +37,27 @@ #include #include #include +#include #include #include #include +#include #include #include #include #include #include +#include +#include +#include +#include #include "bridge_loop_avoidance.h" #include "hard-interface.h" #include "hash.h" #include "log.h" #include "multicast.h" +#include "netlink.h" #include "originator.h" #include "packet.h" #include "soft-interface.h" @@ -1108,6 +1115,164 @@ out: return 0; } +/** + * batadv_tt_local_dump_entry - Dump one TT local entry into a message + * @msg :Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @common: tt local & tt global common data + * + * Return: Error code, or 0 on success + */ +static int +batadv_tt_local_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_tt_common_entry *common) +{ + void *hdr; + struct batadv_softif_vlan *vlan; + struct batadv_tt_local_entry *local; + unsigned int last_seen_msecs; + u32 crc; + + local = container_of(common, struct batadv_tt_local_entry, common); + last_seen_msecs = jiffies_to_msecs(jiffies - local->last_seen); + + vlan = batadv_softif_vlan_get(bat_priv, common->vid); + if (!vlan) + return 0; + + crc = vlan->tt.crc; + + batadv_softif_vlan_put(vlan); + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, + NLM_F_MULTI, + BATADV_CMD_GET_TRANSTABLE_LOCAL); + if (!hdr) + return -ENOBUFS; + + if (nla_put(msg, BATADV_ATTR_TT_ADDRESS, ETH_ALEN, common->addr) || + nla_put_u32(msg, BATADV_ATTR_TT_CRC32, crc) || + nla_put_u16(msg, BATADV_ATTR_TT_VID, common->vid) || + nla_put_u32(msg, BATADV_ATTR_TT_FLAGS, common->flags)) + goto nla_put_failure; + + if (!(common->flags & BATADV_TT_CLIENT_NOPURGE) && + nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, last_seen_msecs)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +/** + * batadv_tt_local_dump_bucket - Dump one TT local bucket into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @head: Pointer to the list containing the local tt entries + * @idx_s: Number of entries to skip + * + * Return: Error code, or 0 on success + */ +static int +batadv_tt_local_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct hlist_head *head, int *idx_s) +{ + struct batadv_tt_common_entry *common; + int idx = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(common, head, hash_entry) { + if (idx++ < *idx_s) + continue; + + if (batadv_tt_local_dump_entry(msg, portid, seq, bat_priv, + common)) { + rcu_read_unlock(); + *idx_s = idx - 1; + return -EMSGSIZE; + } + } + rcu_read_unlock(); + + *idx_s = 0; + return 0; +} + +/** + * batadv_tt_local_dump - Dump TT local entries into a message + * @msg: Netlink message to dump into + * @cb: Parameters from query + * + * Return: Error code, or 0 on success + */ +int batadv_tt_local_dump(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct net *net = sock_net(cb->skb->sk); + struct net_device *soft_iface; + struct batadv_priv *bat_priv; + struct batadv_hard_iface *primary_if = NULL; + struct batadv_hashtable *hash; + struct hlist_head *head; + int ret; + int ifindex; + int bucket = cb->args[0]; + int idx = cb->args[1]; + int portid = NETLINK_CB(cb->skb).portid; + + ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return -EINVAL; + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { + ret = -ENODEV; + goto out; + } + + bat_priv = netdev_priv(soft_iface); + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { + ret = -ENOENT; + goto out; + } + + hash = bat_priv->tt.local_hash; + + while (bucket < hash->size) { + head = &hash->table[bucket]; + + if (batadv_tt_local_dump_bucket(msg, portid, cb->nlh->nlmsg_seq, + bat_priv, head, &idx)) + break; + + bucket++; + } + + ret = msg->len; + + out: + if (primary_if) + batadv_hardif_put(primary_if); + if (soft_iface) + dev_put(soft_iface); + + cb->args[0] = bucket; + cb->args[1] = idx; + + return ret; +} + static void batadv_tt_local_set_pending(struct batadv_priv *bat_priv, struct batadv_tt_local_entry *tt_local_entry, @@ -1755,6 +1920,218 @@ out: return 0; } +/** + * batadv_tt_global_dump_subentry - Dump all TT local entries into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @common: tt local & tt global common data + * @orig: Originator node announcing a non-mesh client + * @best: Is the best originator for the TT entry + * + * Return: Error code, or 0 on success + */ +static int +batadv_tt_global_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_tt_common_entry *common, + struct batadv_tt_orig_list_entry *orig, + bool best) +{ + void *hdr; + struct batadv_orig_node_vlan *vlan; + u8 last_ttvn; + u32 crc; + + vlan = batadv_orig_node_vlan_get(orig->orig_node, + common->vid); + if (!vlan) + return 0; + + crc = vlan->tt.crc; + + batadv_orig_node_vlan_put(vlan); + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, + NLM_F_MULTI, + BATADV_CMD_GET_TRANSTABLE_GLOBAL); + if (!hdr) + return -ENOBUFS; + + last_ttvn = atomic_read(&orig->orig_node->last_ttvn); + + if (nla_put(msg, BATADV_ATTR_TT_ADDRESS, ETH_ALEN, common->addr) || + nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, + orig->orig_node->orig) || + nla_put_u8(msg, BATADV_ATTR_TT_TTVN, orig->ttvn) || + nla_put_u8(msg, BATADV_ATTR_TT_LAST_TTVN, last_ttvn) || + nla_put_u32(msg, BATADV_ATTR_TT_CRC32, crc) || + nla_put_u16(msg, BATADV_ATTR_TT_VID, common->vid) || + nla_put_u32(msg, BATADV_ATTR_TT_FLAGS, common->flags)) + goto nla_put_failure; + + if (best && nla_put_flag(msg, BATADV_ATTR_FLAG_BEST)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +/** + * batadv_tt_global_dump_entry - Dump one TT global entry into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @common: tt local & tt global common data + * @sub_s: Number of entries to skip + * + * This function assumes the caller holds rcu_read_lock(). + * + * Return: Error code, or 0 on success + */ +static int +batadv_tt_global_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_tt_common_entry *common, int *sub_s) +{ + struct batadv_tt_orig_list_entry *orig_entry, *best_entry; + struct batadv_tt_global_entry *global; + struct hlist_head *head; + int sub = 0; + bool best; + + global = container_of(common, struct batadv_tt_global_entry, common); + best_entry = batadv_transtable_best_orig(bat_priv, global); + head = &global->orig_list; + + hlist_for_each_entry_rcu(orig_entry, head, list) { + if (sub++ < *sub_s) + continue; + + best = (orig_entry == best_entry); + + if (batadv_tt_global_dump_subentry(msg, portid, seq, common, + orig_entry, best)) { + *sub_s = sub - 1; + return -EMSGSIZE; + } + } + + *sub_s = 0; + return 0; +} + +/** + * batadv_tt_global_dump_bucket - Dump one TT local bucket into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @head: Pointer to the list containing the global tt entries + * @idx_s: Number of entries to skip + * @sub: Number of entries to skip + * + * Return: Error code, or 0 on success + */ +static int +batadv_tt_global_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct hlist_head *head, int *idx_s, int *sub) +{ + struct batadv_tt_common_entry *common; + int idx = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(common, head, hash_entry) { + if (idx++ < *idx_s) + continue; + + if (batadv_tt_global_dump_entry(msg, portid, seq, bat_priv, + common, sub)) { + rcu_read_unlock(); + *idx_s = idx - 1; + return -EMSGSIZE; + } + } + rcu_read_unlock(); + + *idx_s = 0; + *sub = 0; + return 0; +} + +/** + * batadv_tt_global_dump - Dump TT global entries into a message + * @msg: Netlink message to dump into + * @cb: Parameters from query + * + * Return: Error code, or length of message on success + */ +int batadv_tt_global_dump(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct net *net = sock_net(cb->skb->sk); + struct net_device *soft_iface; + struct batadv_priv *bat_priv; + struct batadv_hard_iface *primary_if = NULL; + struct batadv_hashtable *hash; + struct hlist_head *head; + int ret; + int ifindex; + int bucket = cb->args[0]; + int idx = cb->args[1]; + int sub = cb->args[2]; + int portid = NETLINK_CB(cb->skb).portid; + + ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return -EINVAL; + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { + ret = -ENODEV; + goto out; + } + + bat_priv = netdev_priv(soft_iface); + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { + ret = -ENOENT; + goto out; + } + + hash = bat_priv->tt.global_hash; + + while (bucket < hash->size) { + head = &hash->table[bucket]; + + if (batadv_tt_global_dump_bucket(msg, portid, + cb->nlh->nlmsg_seq, bat_priv, + head, &idx, &sub)) + break; + + bucket++; + } + + ret = msg->len; + + out: + if (primary_if) + batadv_hardif_put(primary_if); + if (soft_iface) + dev_put(soft_iface); + + cb->args[0] = bucket; + cb->args[1] = idx; + cb->args[2] = sub; + + return ret; +} + /** * _batadv_tt_global_del_orig_entry - remove and free an orig_entry * @tt_global_entry: the global entry to remove the orig_entry from diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 02b0f85527cc..783fdba84db2 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -22,8 +22,10 @@ #include +struct netlink_callback; struct net_device; struct seq_file; +struct sk_buff; int batadv_tt_init(struct batadv_priv *bat_priv); bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr, @@ -33,6 +35,8 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const char *message, bool roaming); int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset); int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset); +int batadv_tt_local_dump(struct sk_buff *msg, struct netlink_callback *cb); +int batadv_tt_global_dump(struct sk_buff *msg, struct netlink_callback *cb); void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, s32 match_vid, const char *message); -- cgit v1.2.3 From 85cf8c859d53f6f53c37bb7f23a41f6171427021 Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Sun, 3 Jul 2016 13:31:39 +0200 Subject: batman-adv: netlink: add originator and neighbor table queries Add BATADV_CMD_GET_ORIGINATORS and BATADV_CMD_GET_NEIGHBORS commands, using handlers bat_orig_dump and bat_neigh_dump in batadv_algo_ops. Will always return -EOPNOTSUPP for now, as no implementations exist yet. Signed-off-by: Matthias Schiffer Signed-off-by: Andrew Lunn [sven@narfation.org: Rewrite based on new algo_ops structures] Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich Signed-off-by: Marek Lindner --- include/uapi/linux/batman_adv.h | 4 + net/batman-adv/netlink.c | 13 ++++ net/batman-adv/originator.c | 160 ++++++++++++++++++++++++++++++++++++++++ net/batman-adv/originator.h | 4 + net/batman-adv/types.h | 9 +++ 5 files changed, 190 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index 1168d058cd2b..3f7a415f5e09 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -131,6 +131,8 @@ enum batadv_nl_attrs { * @BATADV_CMD_GET_HARDIFS: Query list of hard interfaces * @BATADV_CMD_GET_TRANSTABLE_LOCAL: Query list of local translations * @BATADV_CMD_GET_TRANSTABLE_GLOBAL Query list of global translations + * @BATADV_CMD_GET_ORIGINATORS: Query list of originators + * @BATADV_CMD_GET_NEIGHBORS: Query list of neighbours * @__BATADV_CMD_AFTER_LAST: internal use * @BATADV_CMD_MAX: highest used command number */ @@ -143,6 +145,8 @@ enum batadv_nl_commands { BATADV_CMD_GET_HARDIFS, BATADV_CMD_GET_TRANSTABLE_LOCAL, BATADV_CMD_GET_TRANSTABLE_GLOBAL, + BATADV_CMD_GET_ORIGINATORS, + BATADV_CMD_GET_NEIGHBORS, /* add new commands above here */ __BATADV_CMD_AFTER_LAST, BATADV_CMD_MAX = __BATADV_CMD_AFTER_LAST - 1 diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 0c0d20bb92ce..8469fc4ec5a3 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -39,6 +39,7 @@ #include "bat_algo.h" #include "hard-interface.h" +#include "originator.h" #include "soft-interface.h" #include "tp_meter.h" #include "translation-table.h" @@ -554,6 +555,18 @@ static struct genl_ops batadv_netlink_ops[] = { .policy = batadv_netlink_policy, .dumpit = batadv_tt_global_dump, }, + { + .cmd = BATADV_CMD_GET_ORIGINATORS, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .dumpit = batadv_orig_dump, + }, + { + .cmd = BATADV_CMD_GET_NEIGHBORS, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .dumpit = batadv_hardif_neigh_dump, + }, }; /** diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 3940b5d24421..95c85558c530 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -28,11 +28,15 @@ #include #include #include +#include #include #include +#include #include #include #include +#include +#include #include "bat_algo.h" #include "distributed-arp-table.h" @@ -42,8 +46,10 @@ #include "hash.h" #include "log.h" #include "multicast.h" +#include "netlink.h" #include "network-coding.h" #include "routing.h" +#include "soft-interface.h" #include "translation-table.h" /* hash class keys */ @@ -720,6 +726,83 @@ int batadv_hardif_neigh_seq_print_text(struct seq_file *seq, void *offset) return 0; } +/** + * batadv_hardif_neigh_dump - Dump to netlink the neighbor infos for a specific + * outgoing interface + * @msg: message to dump into + * @cb: parameters for the dump + * + * Return: 0 or error value + */ +int batadv_hardif_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct net *net = sock_net(cb->skb->sk); + struct net_device *soft_iface; + struct net_device *hard_iface = NULL; + struct batadv_hard_iface *hardif = BATADV_IF_DEFAULT; + struct batadv_priv *bat_priv; + struct batadv_hard_iface *primary_if = NULL; + int ret; + int ifindex, hard_ifindex; + + ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return -EINVAL; + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { + ret = -ENODEV; + goto out; + } + + bat_priv = netdev_priv(soft_iface); + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { + ret = -ENOENT; + goto out; + } + + hard_ifindex = batadv_netlink_get_ifindex(cb->nlh, + BATADV_ATTR_HARD_IFINDEX); + if (hard_ifindex) { + hard_iface = dev_get_by_index(net, hard_ifindex); + if (hard_iface) + hardif = batadv_hardif_get_by_netdev(hard_iface); + + if (!hardif) { + ret = -ENODEV; + goto out; + } + + if (hardif->soft_iface != soft_iface) { + ret = -ENOENT; + goto out; + } + } + + if (!bat_priv->algo_ops->neigh.dump) { + ret = -EOPNOTSUPP; + goto out; + } + + bat_priv->algo_ops->neigh.dump(msg, cb, bat_priv, hardif); + + ret = msg->len; + + out: + if (hardif) + batadv_hardif_put(hardif); + if (hard_iface) + dev_put(hard_iface); + if (primary_if) + batadv_hardif_put(primary_if); + if (soft_iface) + dev_put(soft_iface); + + return ret; +} + /** * batadv_orig_ifinfo_release - release orig_ifinfo from lists and queue for * free after rcu grace period @@ -1330,6 +1413,83 @@ out: return 0; } +/** + * batadv_orig_dump - Dump to netlink the originator infos for a specific + * outgoing interface + * @msg: message to dump into + * @cb: parameters for the dump + * + * Return: 0 or error value + */ +int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct net *net = sock_net(cb->skb->sk); + struct net_device *soft_iface; + struct net_device *hard_iface = NULL; + struct batadv_hard_iface *hardif = BATADV_IF_DEFAULT; + struct batadv_priv *bat_priv; + struct batadv_hard_iface *primary_if = NULL; + int ret; + int ifindex, hard_ifindex; + + ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return -EINVAL; + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { + ret = -ENODEV; + goto out; + } + + bat_priv = netdev_priv(soft_iface); + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { + ret = -ENOENT; + goto out; + } + + hard_ifindex = batadv_netlink_get_ifindex(cb->nlh, + BATADV_ATTR_HARD_IFINDEX); + if (hard_ifindex) { + hard_iface = dev_get_by_index(net, hard_ifindex); + if (hard_iface) + hardif = batadv_hardif_get_by_netdev(hard_iface); + + if (!hardif) { + ret = -ENODEV; + goto out; + } + + if (hardif->soft_iface != soft_iface) { + ret = -ENOENT; + goto out; + } + } + + if (!bat_priv->algo_ops->orig.dump) { + ret = -EOPNOTSUPP; + goto out; + } + + bat_priv->algo_ops->orig.dump(msg, cb, bat_priv, hardif); + + ret = msg->len; + + out: + if (hardif) + batadv_hardif_put(hardif); + if (hard_iface) + dev_put(hard_iface); + if (primary_if) + batadv_hardif_put(primary_if); + if (soft_iface) + dev_put(soft_iface); + + return ret; +} + int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, int max_if_num) { diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 566306bf05dc..ebc56183f358 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -31,7 +31,9 @@ #include "hash.h" +struct netlink_callback; struct seq_file; +struct sk_buff; bool batadv_compare_orig(const struct hlist_node *node, const void *data2); int batadv_originator_init(struct batadv_priv *bat_priv); @@ -61,6 +63,7 @@ batadv_neigh_ifinfo_get(struct batadv_neigh_node *neigh, struct batadv_hard_iface *if_outgoing); void batadv_neigh_ifinfo_put(struct batadv_neigh_ifinfo *neigh_ifinfo); +int batadv_hardif_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb); int batadv_hardif_neigh_seq_print_text(struct seq_file *seq, void *offset); struct batadv_orig_ifinfo * @@ -72,6 +75,7 @@ batadv_orig_ifinfo_new(struct batadv_orig_node *orig_node, void batadv_orig_ifinfo_put(struct batadv_orig_ifinfo *orig_ifinfo); int batadv_orig_seq_print_text(struct seq_file *seq, void *offset); +int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb); int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset); int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, int max_if_num); diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 72806a3c40df..968023a61598 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -28,6 +28,7 @@ #include #include #include +#include #include /* for linux/wait.h */ #include #include @@ -1418,6 +1419,7 @@ struct batadv_algo_iface_ops { * @is_similar_or_better: check if neigh1 is equally similar or better than * neigh2 for their respective outgoing interface from the metric prospective * @print: print the single hop neighbor list (optional) + * @dump: dump neighbors to a netlink socket (optional) */ struct batadv_algo_neigh_ops { void (*hardif_init)(struct batadv_hardif_neigh_node *neigh); @@ -1430,6 +1432,9 @@ struct batadv_algo_neigh_ops { struct batadv_neigh_node *neigh2, struct batadv_hard_iface *if_outgoing2); void (*print)(struct batadv_priv *priv, struct seq_file *seq); + void (*dump)(struct sk_buff *msg, struct netlink_callback *cb, + struct batadv_priv *priv, + struct batadv_hard_iface *hard_iface); }; /** @@ -1441,6 +1446,7 @@ struct batadv_algo_neigh_ops { * @del_if: ask the routing algorithm to apply the needed changes to the * orig_node due to an hard-interface being removed from the mesh (optional) * @print: print the originator table (optional) + * @dump: dump originators to a netlink socket (optional) */ struct batadv_algo_orig_ops { void (*free)(struct batadv_orig_node *orig_node); @@ -1449,6 +1455,9 @@ struct batadv_algo_orig_ops { int del_if_num); void (*print)(struct batadv_priv *priv, struct seq_file *seq, struct batadv_hard_iface *hard_iface); + void (*dump)(struct sk_buff *msg, struct netlink_callback *cb, + struct batadv_priv *priv, + struct batadv_hard_iface *hard_iface); }; /** -- cgit v1.2.3 From 024f99cb4acc14dab5e55e1ecdf6aad31269ca98 Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Sun, 3 Jul 2016 13:31:40 +0200 Subject: batman-adv: add B.A.T.M.A.N. IV bat_{orig, neigh}_dump implementations Signed-off-by: Matthias Schiffer Signed-off-by: Andrew Lunn [sven.eckelmann@open-mesh.com: Fix function parameter alignments, add policy for attributes, fix includes, fix algo_ops integration] Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich Signed-off-by: Marek Lindner --- include/uapi/linux/batman_adv.h | 4 + net/batman-adv/bat_iv_ogm.c | 366 ++++++++++++++++++++++++++++++++++++++++ net/batman-adv/netlink.c | 2 + 3 files changed, 372 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index 3f7a415f5e09..ba2359a1f464 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -85,6 +85,8 @@ enum batadv_tt_client_flags { * @BATADV_ATTR_TT_FLAGS: Translation table client flags * @BATADV_ATTR_FLAG_BEST: Flags indicating entry is the best * @BATADV_ATTR_LAST_SEEN_MSECS: Time in milliseconds since last seen + * @BATADV_ATTR_NEIGH_ADDRESS: Neighbour MAC address + * @BATADV_ATTR_TQ: TQ to neighbour * @__BATADV_ATTR_AFTER_LAST: internal use * @NUM_BATADV_ATTR: total number of batadv_nl_attrs available * @BATADV_ATTR_MAX: highest attribute number currently defined @@ -114,6 +116,8 @@ enum batadv_nl_attrs { BATADV_ATTR_TT_FLAGS, BATADV_ATTR_FLAG_BEST, BATADV_ATTR_LAST_SEEN_MSECS, + BATADV_ATTR_NEIGH_ADDRESS, + BATADV_ATTR_TQ, /* add attributes above here, update the policy in netlink.c */ __BATADV_ATTR_AFTER_LAST, NUM_BATADV_ATTR = __BATADV_ATTR_AFTER_LAST, diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index a40cdf273625..7a8c0f63e2ae 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include #include @@ -48,6 +49,9 @@ #include #include #include +#include +#include +#include #include "bat_algo.h" #include "bitarray.h" @@ -55,6 +59,7 @@ #include "hard-interface.h" #include "hash.h" #include "log.h" +#include "netlink.h" #include "network-coding.h" #include "originator.h" #include "packet.h" @@ -1947,6 +1952,235 @@ next: seq_puts(seq, "No batman nodes in range ...\n"); } +/** + * batadv_iv_ogm_neigh_get_tq_avg - Get the TQ average for a neighbour on a + * given outgoing interface. + * @neigh_node: Neighbour of interest + * @if_outgoing: Outgoing interface of interest + * @tq_avg: Pointer of where to store the TQ average + * + * Return: False if no average TQ available, otherwise true. + */ +static bool +batadv_iv_ogm_neigh_get_tq_avg(struct batadv_neigh_node *neigh_node, + struct batadv_hard_iface *if_outgoing, + u8 *tq_avg) +{ + struct batadv_neigh_ifinfo *n_ifinfo; + + n_ifinfo = batadv_neigh_ifinfo_get(neigh_node, if_outgoing); + if (!n_ifinfo) + return false; + + *tq_avg = n_ifinfo->bat_iv.tq_avg; + batadv_neigh_ifinfo_put(n_ifinfo); + + return true; +} + +/** + * batadv_iv_ogm_orig_dump_subentry - Dump an originator subentry into a + * message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @if_outgoing: Limit dump to entries with this outgoing interface + * @orig_node: Originator to dump + * @neigh_node: Single hops neighbour + * @best: Is the best originator + * + * Return: Error code, or 0 on success + */ +static int +batadv_iv_ogm_orig_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *if_outgoing, + struct batadv_orig_node *orig_node, + struct batadv_neigh_node *neigh_node, + bool best) +{ + void *hdr; + u8 tq_avg; + unsigned int last_seen_msecs; + + last_seen_msecs = jiffies_to_msecs(jiffies - orig_node->last_seen); + + if (!batadv_iv_ogm_neigh_get_tq_avg(neigh_node, if_outgoing, &tq_avg)) + return 0; + + if (if_outgoing != BATADV_IF_DEFAULT && + if_outgoing != neigh_node->if_incoming) + return 0; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, + NLM_F_MULTI, BATADV_CMD_GET_ORIGINATORS); + if (!hdr) + return -ENOBUFS; + + if (nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, + orig_node->orig) || + nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN, + neigh_node->addr) || + nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, + neigh_node->if_incoming->net_dev->ifindex) || + nla_put_u8(msg, BATADV_ATTR_TQ, tq_avg) || + nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, + last_seen_msecs)) + goto nla_put_failure; + + if (best && nla_put_flag(msg, BATADV_ATTR_FLAG_BEST)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +/** + * batadv_iv_ogm_orig_dump_entry - Dump an originator entry into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @if_outgoing: Limit dump to entries with this outgoing interface + * @orig_node: Originator to dump + * @sub_s: Number of sub entries to skip + * + * This function assumes the caller holds rcu_read_lock(). + * + * Return: Error code, or 0 on success + */ +static int +batadv_iv_ogm_orig_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *if_outgoing, + struct batadv_orig_node *orig_node, int *sub_s) +{ + struct batadv_neigh_node *neigh_node_best; + struct batadv_neigh_node *neigh_node; + int sub = 0; + bool best; + u8 tq_avg_best; + + neigh_node_best = batadv_orig_router_get(orig_node, if_outgoing); + if (!neigh_node_best) + goto out; + + if (!batadv_iv_ogm_neigh_get_tq_avg(neigh_node_best, if_outgoing, + &tq_avg_best)) + goto out; + + if (tq_avg_best == 0) + goto out; + + hlist_for_each_entry_rcu(neigh_node, &orig_node->neigh_list, list) { + if (sub++ < *sub_s) + continue; + + best = (neigh_node == neigh_node_best); + + if (batadv_iv_ogm_orig_dump_subentry(msg, portid, seq, + bat_priv, if_outgoing, + orig_node, neigh_node, + best)) { + batadv_neigh_node_put(neigh_node_best); + + *sub_s = sub - 1; + return -EMSGSIZE; + } + } + + out: + if (neigh_node_best) + batadv_neigh_node_put(neigh_node_best); + + *sub_s = 0; + return 0; +} + +/** + * batadv_iv_ogm_orig_dump_bucket - Dump an originator bucket into a + * message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @if_outgoing: Limit dump to entries with this outgoing interface + * @head: Bucket to be dumped + * @idx_s: Number of entries to be skipped + * @sub: Number of sub entries to be skipped + * + * Return: Error code, or 0 on success + */ +static int +batadv_iv_ogm_orig_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *if_outgoing, + struct hlist_head *head, int *idx_s, int *sub) +{ + struct batadv_orig_node *orig_node; + int idx = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { + if (idx++ < *idx_s) + continue; + + if (batadv_iv_ogm_orig_dump_entry(msg, portid, seq, bat_priv, + if_outgoing, orig_node, + sub)) { + rcu_read_unlock(); + *idx_s = idx - 1; + return -EMSGSIZE; + } + } + rcu_read_unlock(); + + *idx_s = 0; + *sub = 0; + return 0; +} + +/** + * batadv_iv_ogm_orig_dump - Dump the originators into a message + * @msg: Netlink message to dump into + * @cb: Control block containing additional options + * @bat_priv: The bat priv with all the soft interface information + * @if_outgoing: Limit dump to entries with this outgoing interface + */ +static void +batadv_iv_ogm_orig_dump(struct sk_buff *msg, struct netlink_callback *cb, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_hashtable *hash = bat_priv->orig_hash; + struct hlist_head *head; + int bucket = cb->args[0]; + int idx = cb->args[1]; + int sub = cb->args[2]; + int portid = NETLINK_CB(cb->skb).portid; + + while (bucket < hash->size) { + head = &hash->table[bucket]; + + if (batadv_iv_ogm_orig_dump_bucket(msg, portid, + cb->nlh->nlmsg_seq, + bat_priv, if_outgoing, head, + &idx, &sub)) + break; + + bucket++; + } + + cb->args[0] = bucket; + cb->args[1] = idx; + cb->args[2] = sub; +} + /** * batadv_iv_hardif_neigh_print - print a single hop neighbour node * @seq: neighbour table seq_file struct @@ -2043,6 +2277,136 @@ out: return ret; } +/** + * batadv_iv_ogm_neigh_dump_neigh - Dump a neighbour into a netlink message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @hardif_neigh: Neighbour to be dumped + * + * Return: Error code, or 0 on success + */ +static int +batadv_iv_ogm_neigh_dump_neigh(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_hardif_neigh_node *hardif_neigh) +{ + void *hdr; + unsigned int last_seen_msecs; + + last_seen_msecs = jiffies_to_msecs(jiffies - hardif_neigh->last_seen); + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, + NLM_F_MULTI, BATADV_CMD_GET_NEIGHBORS); + if (!hdr) + return -ENOBUFS; + + if (nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN, + hardif_neigh->addr) || + nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, + hardif_neigh->if_incoming->net_dev->ifindex) || + nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, + last_seen_msecs)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +/** + * batadv_iv_ogm_neigh_dump_hardif - Dump the neighbours of a hard interface + * into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @hard_iface: Hard interface to dump the neighbours for + * @idx_s: Number of entries to skip + * + * This function assumes the caller holds rcu_read_lock(). + * + * Return: Error code, or 0 on success + */ +static int +batadv_iv_ogm_neigh_dump_hardif(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *hard_iface, + int *idx_s) +{ + struct batadv_hardif_neigh_node *hardif_neigh; + int idx = 0; + + hlist_for_each_entry_rcu(hardif_neigh, + &hard_iface->neigh_list, list) { + if (idx++ < *idx_s) + continue; + + if (batadv_iv_ogm_neigh_dump_neigh(msg, portid, seq, + hardif_neigh)) { + *idx_s = idx - 1; + return -EMSGSIZE; + } + } + + *idx_s = 0; + return 0; +} + +/** + * batadv_iv_ogm_neigh_dump - Dump the neighbours into a message + * @msg: Netlink message to dump into + * @cb: Control block containing additional options + * @bat_priv: The bat priv with all the soft interface information + * @single_hardif: Limit dump to this hard interfaace + */ +static void +batadv_iv_ogm_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *single_hardif) +{ + struct batadv_hard_iface *hard_iface; + int i_hardif = 0; + int i_hardif_s = cb->args[0]; + int idx = cb->args[1]; + int portid = NETLINK_CB(cb->skb).portid; + + rcu_read_lock(); + if (single_hardif) { + if (i_hardif_s == 0) { + if (batadv_iv_ogm_neigh_dump_hardif(msg, portid, + cb->nlh->nlmsg_seq, + bat_priv, + single_hardif, + &idx) == 0) + i_hardif++; + } + } else { + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, + list) { + if (hard_iface->soft_iface != bat_priv->soft_iface) + continue; + + if (i_hardif++ < i_hardif_s) + continue; + + if (batadv_iv_ogm_neigh_dump_hardif(msg, portid, + cb->nlh->nlmsg_seq, + bat_priv, + hard_iface, &idx)) { + i_hardif--; + break; + } + } + } + rcu_read_unlock(); + + cb->args[0] = i_hardif; + cb->args[1] = idx; +} + /** * batadv_iv_ogm_neigh_cmp - compare the metrics of two neighbors * @neigh1: the first neighbor object of the comparison @@ -2330,9 +2694,11 @@ static struct batadv_algo_ops batadv_batman_iv __read_mostly = { .cmp = batadv_iv_ogm_neigh_cmp, .is_similar_or_better = batadv_iv_ogm_neigh_is_sob, .print = batadv_iv_neigh_print, + .dump = batadv_iv_ogm_neigh_dump, }, .orig = { .print = batadv_iv_ogm_orig_print, + .dump = batadv_iv_ogm_orig_dump, .free = batadv_iv_ogm_orig_free, .add_if = batadv_iv_ogm_orig_add_if, .del_if = batadv_iv_ogm_orig_del_if, diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 8469fc4ec5a3..0c7940cc1968 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -84,6 +84,8 @@ static struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = { [BATADV_ATTR_TT_FLAGS] = { .type = NLA_U32 }, [BATADV_ATTR_FLAG_BEST] = { .type = NLA_FLAG }, [BATADV_ATTR_LAST_SEEN_MSECS] = { .type = NLA_U32 }, + [BATADV_ATTR_NEIGH_ADDRESS] = { .len = ETH_ALEN }, + [BATADV_ATTR_TQ] = { .type = NLA_U8 }, }; /** -- cgit v1.2.3 From f02a478f518ee5690f279c8c2d3a6222143a7b20 Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Sun, 3 Jul 2016 13:31:41 +0200 Subject: batman-adv: add B.A.T.M.A.N. V bat_{orig, neigh}_dump implementations Dump the algo V originators and neighbours. Signed-off-by: Matthias Schiffer Signed-off-by: Andrew Lunn [sven@narfation.org: Fix includes, fix algo_ops integration] Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich Signed-off-by: Marek Lindner --- include/uapi/linux/batman_adv.h | 2 + net/batman-adv/bat_v.c | 340 ++++++++++++++++++++++++++++++++++++++++ net/batman-adv/netlink.c | 1 + 3 files changed, 343 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index ba2359a1f464..2e2747fb1311 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -87,6 +87,7 @@ enum batadv_tt_client_flags { * @BATADV_ATTR_LAST_SEEN_MSECS: Time in milliseconds since last seen * @BATADV_ATTR_NEIGH_ADDRESS: Neighbour MAC address * @BATADV_ATTR_TQ: TQ to neighbour + * @BATADV_ATTR_THROUGHPUT: Estimated throughput to Neighbour * @__BATADV_ATTR_AFTER_LAST: internal use * @NUM_BATADV_ATTR: total number of batadv_nl_attrs available * @BATADV_ATTR_MAX: highest attribute number currently defined @@ -118,6 +119,7 @@ enum batadv_nl_attrs { BATADV_ATTR_LAST_SEEN_MSECS, BATADV_ATTR_NEIGH_ADDRESS, BATADV_ATTR_TQ, + BATADV_ATTR_THROUGHPUT, /* add attributes above here, update the policy in netlink.c */ __BATADV_ATTR_AFTER_LAST, NUM_BATADV_ATTR = __BATADV_ATTR_AFTER_LAST, diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 1d777b171366..9dccfaf32115 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -22,17 +22,22 @@ #include #include #include +#include #include #include #include #include #include +#include #include #include #include #include #include #include +#include +#include +#include #include "bat_algo.h" #include "bat_v_elp.h" @@ -42,9 +47,12 @@ #include "hard-interface.h" #include "hash.h" #include "log.h" +#include "netlink.h" #include "originator.h" #include "packet.h" +struct sk_buff; + static void batadv_v_iface_activate(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); @@ -205,6 +213,138 @@ static void batadv_v_neigh_print(struct batadv_priv *bat_priv, seq_puts(seq, "No batman nodes in range ...\n"); } +/** + * batadv_v_neigh_dump_neigh - Dump a neighbour into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @hardif_neigh: Neighbour to dump + * + * Return: Error code, or 0 on success + */ +static int +batadv_v_neigh_dump_neigh(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_hardif_neigh_node *hardif_neigh) +{ + void *hdr; + unsigned int last_seen_msecs; + u32 throughput; + + last_seen_msecs = jiffies_to_msecs(jiffies - hardif_neigh->last_seen); + throughput = ewma_throughput_read(&hardif_neigh->bat_v.throughput); + throughput = throughput * 100; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, NLM_F_MULTI, + BATADV_CMD_GET_NEIGHBORS); + if (!hdr) + return -ENOBUFS; + + if (nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN, + hardif_neigh->addr) || + nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, + hardif_neigh->if_incoming->net_dev->ifindex) || + nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, + last_seen_msecs) || + nla_put_u32(msg, BATADV_ATTR_THROUGHPUT, throughput)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +/** + * batadv_v_neigh_dump_hardif - Dump the neighbours of a hard interface into + * a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @hard_iface: The hard interface to be dumped + * @idx_s: Entries to be skipped + * + * This function assumes the caller holds rcu_read_lock(). + * + * Return: Error code, or 0 on success + */ +static int +batadv_v_neigh_dump_hardif(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *hard_iface, + int *idx_s) +{ + struct batadv_hardif_neigh_node *hardif_neigh; + int idx = 0; + + hlist_for_each_entry_rcu(hardif_neigh, + &hard_iface->neigh_list, list) { + if (idx++ < *idx_s) + continue; + + if (batadv_v_neigh_dump_neigh(msg, portid, seq, hardif_neigh)) { + *idx_s = idx - 1; + return -EMSGSIZE; + } + } + + *idx_s = 0; + return 0; +} + +/** + * batadv_v_neigh_dump - Dump the neighbours of a hard interface into a + * message + * @msg: Netlink message to dump into + * @cb: Control block containing additional options + * @bat_priv: The bat priv with all the soft interface information + * @single_hardif: Limit dumping to this hard interface + */ +static void +batadv_v_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *single_hardif) +{ + struct batadv_hard_iface *hard_iface; + int i_hardif = 0; + int i_hardif_s = cb->args[0]; + int idx = cb->args[1]; + int portid = NETLINK_CB(cb->skb).portid; + + rcu_read_lock(); + if (single_hardif) { + if (i_hardif_s == 0) { + if (batadv_v_neigh_dump_hardif(msg, portid, + cb->nlh->nlmsg_seq, + bat_priv, single_hardif, + &idx) == 0) + i_hardif++; + } + } else { + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->soft_iface != bat_priv->soft_iface) + continue; + + if (i_hardif++ < i_hardif_s) + continue; + + if (batadv_v_neigh_dump_hardif(msg, portid, + cb->nlh->nlmsg_seq, + bat_priv, hard_iface, + &idx)) { + i_hardif--; + break; + } + } + } + rcu_read_unlock(); + + cb->args[0] = i_hardif; + cb->args[1] = idx; +} + /** * batadv_v_orig_print - print the originator table * @bat_priv: the bat priv with all the soft interface information @@ -272,6 +412,204 @@ next: seq_puts(seq, "No batman nodes in range ...\n"); } +/** + * batadv_v_orig_dump_subentry - Dump an originator subentry into a + * message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @if_outgoing: Limit dump to entries with this outgoing interface + * @orig_node: Originator to dump + * @neigh_node: Single hops neighbour + * @best: Is the best originator + * + * Return: Error code, or 0 on success + */ +static int +batadv_v_orig_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *if_outgoing, + struct batadv_orig_node *orig_node, + struct batadv_neigh_node *neigh_node, + bool best) +{ + struct batadv_neigh_ifinfo *n_ifinfo; + unsigned int last_seen_msecs; + u32 throughput; + void *hdr; + + n_ifinfo = batadv_neigh_ifinfo_get(neigh_node, if_outgoing); + if (!n_ifinfo) + return 0; + + throughput = n_ifinfo->bat_v.throughput * 100; + + batadv_neigh_ifinfo_put(n_ifinfo); + + last_seen_msecs = jiffies_to_msecs(jiffies - orig_node->last_seen); + + if (if_outgoing != BATADV_IF_DEFAULT && + if_outgoing != neigh_node->if_incoming) + return 0; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, NLM_F_MULTI, + BATADV_CMD_GET_ORIGINATORS); + if (!hdr) + return -ENOBUFS; + + if (nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, orig_node->orig) || + nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN, + neigh_node->addr) || + nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, + neigh_node->if_incoming->net_dev->ifindex) || + nla_put_u32(msg, BATADV_ATTR_THROUGHPUT, throughput) || + nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, + last_seen_msecs)) + goto nla_put_failure; + + if (best && nla_put_flag(msg, BATADV_ATTR_FLAG_BEST)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +/** + * batadv_v_orig_dump_entry - Dump an originator entry into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @if_outgoing: Limit dump to entries with this outgoing interface + * @orig_node: Originator to dump + * @sub_s: Number of sub entries to skip + * + * This function assumes the caller holds rcu_read_lock(). + * + * Return: Error code, or 0 on success + */ +static int +batadv_v_orig_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *if_outgoing, + struct batadv_orig_node *orig_node, int *sub_s) +{ + struct batadv_neigh_node *neigh_node_best; + struct batadv_neigh_node *neigh_node; + int sub = 0; + bool best; + + neigh_node_best = batadv_orig_router_get(orig_node, if_outgoing); + if (!neigh_node_best) + goto out; + + hlist_for_each_entry_rcu(neigh_node, &orig_node->neigh_list, list) { + if (sub++ < *sub_s) + continue; + + best = (neigh_node == neigh_node_best); + + if (batadv_v_orig_dump_subentry(msg, portid, seq, bat_priv, + if_outgoing, orig_node, + neigh_node, best)) { + batadv_neigh_node_put(neigh_node_best); + + *sub_s = sub - 1; + return -EMSGSIZE; + } + } + + out: + if (neigh_node_best) + batadv_neigh_node_put(neigh_node_best); + + *sub_s = 0; + return 0; +} + +/** + * batadv_v_orig_dump_bucket - Dump an originator bucket into a + * message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @if_outgoing: Limit dump to entries with this outgoing interface + * @head: Bucket to be dumped + * @idx_s: Number of entries to be skipped + * @sub: Number of sub entries to be skipped + * + * Return: Error code, or 0 on success + */ +static int +batadv_v_orig_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *if_outgoing, + struct hlist_head *head, int *idx_s, int *sub) +{ + struct batadv_orig_node *orig_node; + int idx = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { + if (idx++ < *idx_s) + continue; + + if (batadv_v_orig_dump_entry(msg, portid, seq, bat_priv, + if_outgoing, orig_node, sub)) { + rcu_read_unlock(); + *idx_s = idx - 1; + return -EMSGSIZE; + } + } + rcu_read_unlock(); + + *idx_s = 0; + *sub = 0; + return 0; +} + +/** + * batadv_v_orig_dump - Dump the originators into a message + * @msg: Netlink message to dump into + * @cb: Control block containing additional options + * @bat_priv: The bat priv with all the soft interface information + * @if_outgoing: Limit dump to entries with this outgoing interface + */ +static void +batadv_v_orig_dump(struct sk_buff *msg, struct netlink_callback *cb, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_hashtable *hash = bat_priv->orig_hash; + struct hlist_head *head; + int bucket = cb->args[0]; + int idx = cb->args[1]; + int sub = cb->args[2]; + int portid = NETLINK_CB(cb->skb).portid; + + while (bucket < hash->size) { + head = &hash->table[bucket]; + + if (batadv_v_orig_dump_bucket(msg, portid, + cb->nlh->nlmsg_seq, + bat_priv, if_outgoing, head, &idx, + &sub)) + break; + + bucket++; + } + + cb->args[0] = bucket; + cb->args[1] = idx; + cb->args[2] = sub; +} + static int batadv_v_neigh_cmp(struct batadv_neigh_node *neigh1, struct batadv_hard_iface *if_outgoing1, struct batadv_neigh_node *neigh2, @@ -573,9 +911,11 @@ static struct batadv_algo_ops batadv_batman_v __read_mostly = { .cmp = batadv_v_neigh_cmp, .is_similar_or_better = batadv_v_neigh_is_sob, .print = batadv_v_neigh_print, + .dump = batadv_v_neigh_dump, }, .orig = { .print = batadv_v_orig_print, + .dump = batadv_v_orig_dump, }, .gw = { .store_sel_class = batadv_v_store_sel_class, diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 0c7940cc1968..025f2ec2b27e 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -86,6 +86,7 @@ static struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = { [BATADV_ATTR_LAST_SEEN_MSECS] = { .type = NLA_U32 }, [BATADV_ATTR_NEIGH_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_TQ] = { .type = NLA_U8 }, + [BATADV_ATTR_THROUGHPUT] = { .type = NLA_U32 }, }; /** -- cgit v1.2.3 From d7129dafcb71adfd1a166d0477ce0f564cf410d5 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sun, 3 Jul 2016 13:31:42 +0200 Subject: batman-adv: netlink: add gateway table queries Add BATADV_CMD_GET_GATEWAYS commands, using handlers bat_gw_dump in batadv_algo_ops. Will always return -EOPNOTSUPP for now, as no implementations exist yet. Signed-off-by: Sven Eckelmann Signed-off-by: Marek Lindner Signed-off-by: Simon Wunderlich --- include/uapi/linux/batman_adv.h | 8 ++++++ net/batman-adv/gateway_client.c | 59 +++++++++++++++++++++++++++++++++++++++++ net/batman-adv/gateway_client.h | 2 ++ net/batman-adv/netlink.c | 10 +++++++ net/batman-adv/types.h | 3 +++ 5 files changed, 82 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index 2e2747fb1311..a13fc09e8192 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -88,6 +88,9 @@ enum batadv_tt_client_flags { * @BATADV_ATTR_NEIGH_ADDRESS: Neighbour MAC address * @BATADV_ATTR_TQ: TQ to neighbour * @BATADV_ATTR_THROUGHPUT: Estimated throughput to Neighbour + * @BATADV_ATTR_BANDWIDTH_UP: Reported uplink bandwidth + * @BATADV_ATTR_BANDWIDTH_DOWN: Reported downlink bandwidth + * @BATADV_ATTR_ROUTER: Gateway router MAC address * @__BATADV_ATTR_AFTER_LAST: internal use * @NUM_BATADV_ATTR: total number of batadv_nl_attrs available * @BATADV_ATTR_MAX: highest attribute number currently defined @@ -120,6 +123,9 @@ enum batadv_nl_attrs { BATADV_ATTR_NEIGH_ADDRESS, BATADV_ATTR_TQ, BATADV_ATTR_THROUGHPUT, + BATADV_ATTR_BANDWIDTH_UP, + BATADV_ATTR_BANDWIDTH_DOWN, + BATADV_ATTR_ROUTER, /* add attributes above here, update the policy in netlink.c */ __BATADV_ATTR_AFTER_LAST, NUM_BATADV_ATTR = __BATADV_ATTR_AFTER_LAST, @@ -139,6 +145,7 @@ enum batadv_nl_attrs { * @BATADV_CMD_GET_TRANSTABLE_GLOBAL Query list of global translations * @BATADV_CMD_GET_ORIGINATORS: Query list of originators * @BATADV_CMD_GET_NEIGHBORS: Query list of neighbours + * @BATADV_CMD_GET_GATEWAYS: Query list of gateways * @__BATADV_CMD_AFTER_LAST: internal use * @BATADV_CMD_MAX: highest used command number */ @@ -153,6 +160,7 @@ enum batadv_nl_commands { BATADV_CMD_GET_TRANSTABLE_GLOBAL, BATADV_CMD_GET_ORIGINATORS, BATADV_CMD_GET_NEIGHBORS, + BATADV_CMD_GET_GATEWAYS, /* add new commands above here */ __BATADV_CMD_AFTER_LAST, BATADV_CMD_MAX = __BATADV_CMD_AFTER_LAST - 1 diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index a77a17939f1e..c2928c2287b8 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -20,6 +20,7 @@ #include #include +#include #include #include #include @@ -31,6 +32,7 @@ #include #include #include +#include #include #include #include @@ -39,13 +41,17 @@ #include #include #include +#include +#include #include "gateway_common.h" #include "hard-interface.h" #include "log.h" +#include "netlink.h" #include "originator.h" #include "packet.h" #include "routing.h" +#include "soft-interface.h" #include "sysfs.h" #include "translation-table.h" @@ -500,6 +506,59 @@ int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset) return 0; } +/** + * batadv_gw_dump - Dump gateways into a message + * @msg: Netlink message to dump into + * @cb: Control block containing additional options + * + * Return: Error code, or length of message + */ +int batadv_gw_dump(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct batadv_hard_iface *primary_if = NULL; + struct net *net = sock_net(cb->skb->sk); + struct net_device *soft_iface; + struct batadv_priv *bat_priv; + int ifindex; + int ret; + + ifindex = batadv_netlink_get_ifindex(cb->nlh, + BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return -EINVAL; + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { + ret = -ENODEV; + goto out; + } + + bat_priv = netdev_priv(soft_iface); + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { + ret = -ENOENT; + goto out; + } + + if (!bat_priv->algo_ops->gw.dump) { + ret = -EOPNOTSUPP; + goto out; + } + + bat_priv->algo_ops->gw.dump(msg, cb, bat_priv); + + ret = msg->len; + +out: + if (primary_if) + batadv_hardif_put(primary_if); + if (soft_iface) + dev_put(soft_iface); + + return ret; +} + /** * batadv_gw_dhcp_recipient_get - check if a packet is a DHCP message * @skb: the packet to check diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index 6b40432aa1ed..859166d03561 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -23,6 +23,7 @@ #include struct batadv_tvlv_gateway_data; +struct netlink_callback; struct seq_file; struct sk_buff; @@ -43,6 +44,7 @@ void batadv_gw_node_put(struct batadv_gw_node *gw_node); struct batadv_gw_node * batadv_gw_get_selected_gw_node(struct batadv_priv *bat_priv); int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset); +int batadv_gw_dump(struct sk_buff *msg, struct netlink_callback *cb); bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, struct sk_buff *skb); enum batadv_dhcp_recipient batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len, diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 025f2ec2b27e..c68ccb03634d 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -38,6 +38,7 @@ #include #include "bat_algo.h" +#include "gateway_client.h" #include "hard-interface.h" #include "originator.h" #include "soft-interface.h" @@ -87,6 +88,9 @@ static struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = { [BATADV_ATTR_NEIGH_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_TQ] = { .type = NLA_U8 }, [BATADV_ATTR_THROUGHPUT] = { .type = NLA_U32 }, + [BATADV_ATTR_BANDWIDTH_UP] = { .type = NLA_U32 }, + [BATADV_ATTR_BANDWIDTH_DOWN] = { .type = NLA_U32 }, + [BATADV_ATTR_ROUTER] = { .len = ETH_ALEN }, }; /** @@ -570,6 +574,12 @@ static struct genl_ops batadv_netlink_ops[] = { .policy = batadv_netlink_policy, .dumpit = batadv_hardif_neigh_dump, }, + { + .cmd = BATADV_CMD_GET_GATEWAYS, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .dumpit = batadv_gw_dump, + }, }; /** diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 968023a61598..b5f01a36ec34 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1469,6 +1469,7 @@ struct batadv_algo_orig_ops { * @is_eligible: check if a newly discovered GW is a potential candidate for * the election as best GW (optional) * @print: print the gateway table (optional) + * @dump: dump gateways to a netlink socket (optional) */ struct batadv_algo_gw_ops { ssize_t (*store_sel_class)(struct batadv_priv *bat_priv, char *buff, @@ -1480,6 +1481,8 @@ struct batadv_algo_gw_ops { struct batadv_orig_node *curr_gw_orig, struct batadv_orig_node *orig_node); void (*print)(struct batadv_priv *bat_priv, struct seq_file *seq); + void (*dump)(struct sk_buff *msg, struct netlink_callback *cb, + struct batadv_priv *priv); }; /** -- cgit v1.2.3 From 04f3f5bf1883fbe0acba5c1fc698cf5cedebc5c5 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 3 Jul 2016 13:31:45 +0200 Subject: batman-adv: add B.A.T.M.A.N. Dump BLA claims via netlink Dump the list of bridge loop avoidance claims via the netlink socket. Signed-off-by: Andrew Lunn [sven.eckelmann@open-mesh.com: add policy for attributes, fix includes, fix soft_iface reference leak] Signed-off-by: Sven Eckelmann [sw@simonwunderlich.de: fix kerneldoc, fix error reporting] Signed-off-by: Simon Wunderlich Signed-off-by: Marek Lindner --- include/uapi/linux/batman_adv.h | 12 +++ net/batman-adv/bridge_loop_avoidance.c | 169 +++++++++++++++++++++++++++++++++ net/batman-adv/bridge_loop_avoidance.h | 10 +- net/batman-adv/netlink.c | 12 +++ 4 files changed, 202 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index a13fc09e8192..96b37ab2e840 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -91,6 +91,11 @@ enum batadv_tt_client_flags { * @BATADV_ATTR_BANDWIDTH_UP: Reported uplink bandwidth * @BATADV_ATTR_BANDWIDTH_DOWN: Reported downlink bandwidth * @BATADV_ATTR_ROUTER: Gateway router MAC address + * @BATADV_ATTR_BLA_OWN: Flag indicating own originator + * @BATADV_ATTR_BLA_ADDRESS: Bridge loop avoidance claim MAC address + * @BATADV_ATTR_BLA_VID: BLA VLAN ID + * @BATADV_ATTR_BLA_BACKBONE: BLA gateway originator MAC address + * @BATADV_ATTR_BLA_CRC: BLA CRC * @__BATADV_ATTR_AFTER_LAST: internal use * @NUM_BATADV_ATTR: total number of batadv_nl_attrs available * @BATADV_ATTR_MAX: highest attribute number currently defined @@ -126,6 +131,11 @@ enum batadv_nl_attrs { BATADV_ATTR_BANDWIDTH_UP, BATADV_ATTR_BANDWIDTH_DOWN, BATADV_ATTR_ROUTER, + BATADV_ATTR_BLA_OWN, + BATADV_ATTR_BLA_ADDRESS, + BATADV_ATTR_BLA_VID, + BATADV_ATTR_BLA_BACKBONE, + BATADV_ATTR_BLA_CRC, /* add attributes above here, update the policy in netlink.c */ __BATADV_ATTR_AFTER_LAST, NUM_BATADV_ATTR = __BATADV_ATTR_AFTER_LAST, @@ -146,6 +156,7 @@ enum batadv_nl_attrs { * @BATADV_CMD_GET_ORIGINATORS: Query list of originators * @BATADV_CMD_GET_NEIGHBORS: Query list of neighbours * @BATADV_CMD_GET_GATEWAYS: Query list of gateways + * @BATADV_CMD_GET_BLA_CLAIM: Query list of bridge loop avoidance claims * @__BATADV_CMD_AFTER_LAST: internal use * @BATADV_CMD_MAX: highest used command number */ @@ -161,6 +172,7 @@ enum batadv_nl_commands { BATADV_CMD_GET_ORIGINATORS, BATADV_CMD_GET_NEIGHBORS, BATADV_CMD_GET_GATEWAYS, + BATADV_CMD_GET_BLA_CLAIM, /* add new commands above here */ __BATADV_CMD_AFTER_LAST, BATADV_CMD_MAX = __BATADV_CMD_AFTER_LAST - 1 diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index c75ef648f0fd..aafa88f3e98d 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include #include @@ -45,12 +46,18 @@ #include #include #include +#include +#include +#include +#include #include "hard-interface.h" #include "hash.h" #include "log.h" +#include "netlink.h" #include "originator.h" #include "packet.h" +#include "soft-interface.h" #include "sysfs.h" #include "translation-table.h" @@ -2051,6 +2058,168 @@ out: return 0; } +/** + * batadv_bla_claim_dump_entry - dump one entry of the claim table + * to a netlink socket + * @msg: buffer for the message + * @portid: netlink port + * @seq: Sequence number of netlink message + * @primary_if: primary interface + * @claim: entry to dump + * + * Return: 0 or error code. + */ +static int +batadv_bla_claim_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_hard_iface *primary_if, + struct batadv_bla_claim *claim) +{ + u8 *primary_addr = primary_if->net_dev->dev_addr; + u16 backbone_crc; + bool is_own; + void *hdr; + int ret = -EINVAL; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, + NLM_F_MULTI, BATADV_CMD_GET_BLA_CLAIM); + if (!hdr) { + ret = -ENOBUFS; + goto out; + } + + is_own = batadv_compare_eth(claim->backbone_gw->orig, + primary_addr); + + spin_lock_bh(&claim->backbone_gw->crc_lock); + backbone_crc = claim->backbone_gw->crc; + spin_unlock_bh(&claim->backbone_gw->crc_lock); + + if (is_own) + if (nla_put_flag(msg, BATADV_ATTR_BLA_OWN)) { + genlmsg_cancel(msg, hdr); + goto out; + } + + if (nla_put(msg, BATADV_ATTR_BLA_ADDRESS, ETH_ALEN, claim->addr) || + nla_put_u16(msg, BATADV_ATTR_BLA_VID, claim->vid) || + nla_put(msg, BATADV_ATTR_BLA_BACKBONE, ETH_ALEN, + claim->backbone_gw->orig) || + nla_put_u16(msg, BATADV_ATTR_BLA_CRC, + backbone_crc)) { + genlmsg_cancel(msg, hdr); + goto out; + } + + genlmsg_end(msg, hdr); + ret = 0; + +out: + return ret; +} + +/** + * batadv_bla_claim_dump_bucket - dump one bucket of the claim table + * to a netlink socket + * @msg: buffer for the message + * @portid: netlink port + * @seq: Sequence number of netlink message + * @primary_if: primary interface + * @head: bucket to dump + * @idx_skip: How many entries to skip + * + * Return: always 0. + */ +static int +batadv_bla_claim_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_hard_iface *primary_if, + struct hlist_head *head, int *idx_skip) +{ + struct batadv_bla_claim *claim; + int idx = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(claim, head, hash_entry) { + if (idx++ < *idx_skip) + continue; + if (batadv_bla_claim_dump_entry(msg, portid, seq, + primary_if, claim)) { + *idx_skip = idx - 1; + goto unlock; + } + } + + *idx_skip = idx; +unlock: + rcu_read_unlock(); + return 0; +} + +/** + * batadv_bla_claim_dump - dump claim table to a netlink socket + * @msg: buffer for the message + * @cb: callback structure containing arguments + * + * Return: message length. + */ +int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct batadv_hard_iface *primary_if = NULL; + int portid = NETLINK_CB(cb->skb).portid; + struct net *net = sock_net(cb->skb->sk); + struct net_device *soft_iface; + struct batadv_hashtable *hash; + struct batadv_priv *bat_priv; + int bucket = cb->args[0]; + struct hlist_head *head; + int idx = cb->args[1]; + int ifindex; + int ret = 0; + + ifindex = batadv_netlink_get_ifindex(cb->nlh, + BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return -EINVAL; + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { + ret = -ENODEV; + goto out; + } + + bat_priv = netdev_priv(soft_iface); + hash = bat_priv->bla.claim_hash; + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { + ret = -ENOENT; + goto out; + } + + while (bucket < hash->size) { + head = &hash->table[bucket]; + + if (batadv_bla_claim_dump_bucket(msg, portid, + cb->nlh->nlmsg_seq, + primary_if, head, &idx)) + break; + bucket++; + } + + cb->args[0] = bucket; + cb->args[1] = idx; + + ret = msg->len; + +out: + if (primary_if) + batadv_hardif_put(primary_if); + + if (soft_iface) + dev_put(soft_iface); + + return ret; +} + /** * batadv_bla_backbone_table_seq_print_text - print the backbone table in a seq * file diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 0f01daeb359e..a80b9e96f28e 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -23,6 +23,7 @@ #include struct net_device; +struct netlink_callback; struct seq_file; struct sk_buff; @@ -35,6 +36,7 @@ bool batadv_bla_is_backbone_gw(struct sk_buff *skb, struct batadv_orig_node *orig_node, int hdr_size); int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset); +int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb); int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset); bool batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, u8 *orig, @@ -47,7 +49,7 @@ void batadv_bla_update_orig_address(struct batadv_priv *bat_priv, void batadv_bla_status_update(struct net_device *net_dev); int batadv_bla_init(struct batadv_priv *bat_priv); void batadv_bla_free(struct batadv_priv *bat_priv); - +int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb); #define BATADV_BLA_CRC_INIT 0 #else /* ifdef CONFIG_BATMAN_ADV_BLA */ @@ -112,6 +114,12 @@ static inline void batadv_bla_free(struct batadv_priv *bat_priv) { } +static inline int batadv_bla_claim_dump(struct sk_buff *msg, + struct netlink_callback *cb) +{ + return -EOPNOTSUPP; +} + #endif /* ifdef CONFIG_BATMAN_ADV_BLA */ #endif /* ifndef _NET_BATMAN_ADV_BLA_H_ */ diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index c68ccb03634d..b33675cbaecf 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -38,6 +38,7 @@ #include #include "bat_algo.h" +#include "bridge_loop_avoidance.h" #include "gateway_client.h" #include "hard-interface.h" #include "originator.h" @@ -91,6 +92,11 @@ static struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = { [BATADV_ATTR_BANDWIDTH_UP] = { .type = NLA_U32 }, [BATADV_ATTR_BANDWIDTH_DOWN] = { .type = NLA_U32 }, [BATADV_ATTR_ROUTER] = { .len = ETH_ALEN }, + [BATADV_ATTR_BLA_OWN] = { .type = NLA_FLAG }, + [BATADV_ATTR_BLA_ADDRESS] = { .len = ETH_ALEN }, + [BATADV_ATTR_BLA_VID] = { .type = NLA_U16 }, + [BATADV_ATTR_BLA_BACKBONE] = { .len = ETH_ALEN }, + [BATADV_ATTR_BLA_CRC] = { .type = NLA_U16 }, }; /** @@ -580,6 +586,12 @@ static struct genl_ops batadv_netlink_ops[] = { .policy = batadv_netlink_policy, .dumpit = batadv_gw_dump, }, + { + .cmd = BATADV_CMD_GET_BLA_CLAIM, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .dumpit = batadv_bla_claim_dump, + }, }; /** -- cgit v1.2.3 From ea4152e1171604f325f1a5f080190823a0edbc1f Mon Sep 17 00:00:00 2001 From: Simon Wunderlich Date: Sun, 3 Jul 2016 13:31:47 +0200 Subject: batman-adv: add backbone table netlink support Dump the list of bridge loop avoidance backbones via the netlink socket. Signed-off-by: Simon Wunderlich Signed-off-by: Sven Eckelmann Signed-off-by: Marek Lindner --- include/uapi/linux/batman_adv.h | 2 + net/batman-adv/bridge_loop_avoidance.c | 164 +++++++++++++++++++++++++++++++++ net/batman-adv/bridge_loop_avoidance.h | 7 ++ net/batman-adv/netlink.c | 7 ++ 4 files changed, 180 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index 96b37ab2e840..734fe83ab645 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -157,6 +157,7 @@ enum batadv_nl_attrs { * @BATADV_CMD_GET_NEIGHBORS: Query list of neighbours * @BATADV_CMD_GET_GATEWAYS: Query list of gateways * @BATADV_CMD_GET_BLA_CLAIM: Query list of bridge loop avoidance claims + * @BATADV_CMD_GET_BLA_BACKBONE: Query list of bridge loop avoidance backbones * @__BATADV_CMD_AFTER_LAST: internal use * @BATADV_CMD_MAX: highest used command number */ @@ -173,6 +174,7 @@ enum batadv_nl_commands { BATADV_CMD_GET_NEIGHBORS, BATADV_CMD_GET_GATEWAYS, BATADV_CMD_GET_BLA_CLAIM, + BATADV_CMD_GET_BLA_BACKBONE, /* add new commands above here */ __BATADV_CMD_AFTER_LAST, BATADV_CMD_MAX = __BATADV_CMD_AFTER_LAST - 1 diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index aafa88f3e98d..35ed1d32bab5 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -2283,3 +2283,167 @@ out: batadv_hardif_put(primary_if); return 0; } + +/** + * batadv_bla_backbone_dump_entry - dump one entry of the backbone table + * to a netlink socket + * @msg: buffer for the message + * @portid: netlink port + * @seq: Sequence number of netlink message + * @primary_if: primary interface + * @backbone_gw: entry to dump + * + * Return: 0 or error code. + */ +static int +batadv_bla_backbone_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_hard_iface *primary_if, + struct batadv_bla_backbone_gw *backbone_gw) +{ + u8 *primary_addr = primary_if->net_dev->dev_addr; + u16 backbone_crc; + bool is_own; + int msecs; + void *hdr; + int ret = -EINVAL; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, + NLM_F_MULTI, BATADV_CMD_GET_BLA_BACKBONE); + if (!hdr) { + ret = -ENOBUFS; + goto out; + } + + is_own = batadv_compare_eth(backbone_gw->orig, primary_addr); + + spin_lock_bh(&backbone_gw->crc_lock); + backbone_crc = backbone_gw->crc; + spin_unlock_bh(&backbone_gw->crc_lock); + + msecs = jiffies_to_msecs(jiffies - backbone_gw->lasttime); + + if (is_own) + if (nla_put_flag(msg, BATADV_ATTR_BLA_OWN)) { + genlmsg_cancel(msg, hdr); + goto out; + } + + if (nla_put(msg, BATADV_ATTR_BLA_BACKBONE, ETH_ALEN, + backbone_gw->orig) || + nla_put_u16(msg, BATADV_ATTR_BLA_VID, backbone_gw->vid) || + nla_put_u16(msg, BATADV_ATTR_BLA_CRC, + backbone_crc) || + nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, msecs)) { + genlmsg_cancel(msg, hdr); + goto out; + } + + genlmsg_end(msg, hdr); + ret = 0; + +out: + return ret; +} + +/** + * batadv_bla_backbone_dump_bucket - dump one bucket of the backbone table + * to a netlink socket + * @msg: buffer for the message + * @portid: netlink port + * @seq: Sequence number of netlink message + * @primary_if: primary interface + * @head: bucket to dump + * @idx_skip: How many entries to skip + * + * Return: always 0. + */ +static int +batadv_bla_backbone_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_hard_iface *primary_if, + struct hlist_head *head, int *idx_skip) +{ + struct batadv_bla_backbone_gw *backbone_gw; + int idx = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { + if (idx++ < *idx_skip) + continue; + if (batadv_bla_backbone_dump_entry(msg, portid, seq, + primary_if, backbone_gw)) { + *idx_skip = idx - 1; + goto unlock; + } + } + + *idx_skip = idx; +unlock: + rcu_read_unlock(); + return 0; +} + +/** + * batadv_bla_backbone_dump - dump backbone table to a netlink socket + * @msg: buffer for the message + * @cb: callback structure containing arguments + * + * Return: message length. + */ +int batadv_bla_backbone_dump(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct batadv_hard_iface *primary_if = NULL; + int portid = NETLINK_CB(cb->skb).portid; + struct net *net = sock_net(cb->skb->sk); + struct net_device *soft_iface; + struct batadv_hashtable *hash; + struct batadv_priv *bat_priv; + int bucket = cb->args[0]; + struct hlist_head *head; + int idx = cb->args[1]; + int ifindex; + int ret = 0; + + ifindex = batadv_netlink_get_ifindex(cb->nlh, + BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return -EINVAL; + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { + ret = -ENODEV; + goto out; + } + + bat_priv = netdev_priv(soft_iface); + hash = bat_priv->bla.backbone_hash; + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { + ret = -ENOENT; + goto out; + } + + while (bucket < hash->size) { + head = &hash->table[bucket]; + + if (batadv_bla_backbone_dump_bucket(msg, portid, + cb->nlh->nlmsg_seq, + primary_if, head, &idx)) + break; + bucket++; + } + + cb->args[0] = bucket; + cb->args[1] = idx; + + ret = msg->len; + +out: + if (primary_if) + batadv_hardif_put(primary_if); + + if (soft_iface) + dev_put(soft_iface); + + return ret; +} diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index a80b9e96f28e..1ae93e46fb98 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -39,6 +39,7 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset); int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb); int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset); +int batadv_bla_backbone_dump(struct sk_buff *msg, struct netlink_callback *cb); bool batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, u8 *orig, unsigned short vid); bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, @@ -120,6 +121,12 @@ static inline int batadv_bla_claim_dump(struct sk_buff *msg, return -EOPNOTSUPP; } +static inline int batadv_bla_backbone_dump(struct sk_buff *msg, + struct netlink_callback *cb) +{ + return -EOPNOTSUPP; +} + #endif /* ifdef CONFIG_BATMAN_ADV_BLA */ #endif /* ifndef _NET_BATMAN_ADV_BLA_H_ */ diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 464de9d05135..c3f68167591d 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -600,6 +600,13 @@ static struct genl_ops batadv_netlink_ops[] = { .policy = batadv_netlink_policy, .dumpit = batadv_bla_claim_dump, }, + { + .cmd = BATADV_CMD_GET_BLA_BACKBONE, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .dumpit = batadv_bla_backbone_dump, + }, + }; /** -- cgit v1.2.3 From ab10dccb11608b96b43b557c12a5ad867723e503 Mon Sep 17 00:00:00 2001 From: Gao Feng Date: Tue, 9 Aug 2016 12:38:24 +0800 Subject: rps: Inspect PPTP encapsulated by GRE to get flow hash The PPTP is encapsulated by GRE header with that GRE_VERSION bits must contain one. But current GRE RPS needs the GRE_VERSION must be zero. So RPS does not work for PPTP traffic. In my test environment, there are four MIPS cores, and all traffic are passed through by PPTP. As a result, only one core is 100% busy while other three cores are very idle. After this patch, the usage of four cores are balanced well. Signed-off-by: Gao Feng Reviewed-by: Philip Prindeville Signed-off-by: David S. Miller --- drivers/net/ppp/pptp.c | 36 +------------ include/net/gre.h | 10 +++- include/net/pptp.h | 40 +++++++++++++++ include/uapi/linux/if_tunnel.h | 7 ++- net/core/flow_dissector.c | 113 ++++++++++++++++++++++++++++------------- 5 files changed, 135 insertions(+), 71 deletions(-) create mode 100644 include/net/pptp.h (limited to 'include/uapi/linux') diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index ae0905ed4a32..3e68dbc0af7f 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -37,6 +37,7 @@ #include #include #include +#include #include @@ -53,41 +54,6 @@ static struct proto pptp_sk_proto __read_mostly; static const struct ppp_channel_ops pptp_chan_ops; static const struct proto_ops pptp_ops; -#define PPP_LCP_ECHOREQ 0x09 -#define PPP_LCP_ECHOREP 0x0A -#define SC_RCV_BITS (SC_RCV_B7_1|SC_RCV_B7_0|SC_RCV_ODDP|SC_RCV_EVNP) - -#define MISSING_WINDOW 20 -#define WRAPPED(curseq, lastseq)\ - ((((curseq) & 0xffffff00) == 0) &&\ - (((lastseq) & 0xffffff00) == 0xffffff00)) - -#define PPTP_GRE_PROTO 0x880B -#define PPTP_GRE_VER 0x1 - -#define PPTP_GRE_FLAG_C 0x80 -#define PPTP_GRE_FLAG_R 0x40 -#define PPTP_GRE_FLAG_K 0x20 -#define PPTP_GRE_FLAG_S 0x10 -#define PPTP_GRE_FLAG_A 0x80 - -#define PPTP_GRE_IS_C(f) ((f)&PPTP_GRE_FLAG_C) -#define PPTP_GRE_IS_R(f) ((f)&PPTP_GRE_FLAG_R) -#define PPTP_GRE_IS_K(f) ((f)&PPTP_GRE_FLAG_K) -#define PPTP_GRE_IS_S(f) ((f)&PPTP_GRE_FLAG_S) -#define PPTP_GRE_IS_A(f) ((f)&PPTP_GRE_FLAG_A) - -#define PPTP_HEADER_OVERHEAD (2+sizeof(struct pptp_gre_header)) -struct pptp_gre_header { - u8 flags; - u8 ver; - __be16 protocol; - __be16 payload_len; - __be16 call_id; - __be32 seq; - __be32 ack; -} __packed; - static struct pppox_sock *lookup_chan(u16 call_id, __be32 s_addr) { struct pppox_sock *sock; diff --git a/include/net/gre.h b/include/net/gre.h index 7a54a31d1d4c..8962e1e68449 100644 --- a/include/net/gre.h +++ b/include/net/gre.h @@ -7,7 +7,15 @@ struct gre_base_hdr { __be16 flags; __be16 protocol; -}; +} __packed; + +struct gre_full_hdr { + struct gre_base_hdr fixed_header; + __be16 csum; + __be16 reserved1; + __be32 key; + __be32 seq; +} __packed; #define GRE_HEADER_SECTION 4 #define GREPROTO_CISCO 0 diff --git a/include/net/pptp.h b/include/net/pptp.h new file mode 100644 index 000000000000..301d3e2ba1f9 --- /dev/null +++ b/include/net/pptp.h @@ -0,0 +1,40 @@ +#ifndef _NET_PPTP_H +#define _NET_PPTP_H + +#define PPP_LCP_ECHOREQ 0x09 +#define PPP_LCP_ECHOREP 0x0A +#define SC_RCV_BITS (SC_RCV_B7_1|SC_RCV_B7_0|SC_RCV_ODDP|SC_RCV_EVNP) + +#define MISSING_WINDOW 20 +#define WRAPPED(curseq, lastseq)\ + ((((curseq) & 0xffffff00) == 0) &&\ + (((lastseq) & 0xffffff00) == 0xffffff00)) + +#define PPTP_GRE_PROTO 0x880B +#define PPTP_GRE_VER 0x1 + +#define PPTP_GRE_FLAG_C 0x80 +#define PPTP_GRE_FLAG_R 0x40 +#define PPTP_GRE_FLAG_K 0x20 +#define PPTP_GRE_FLAG_S 0x10 +#define PPTP_GRE_FLAG_A 0x80 + +#define PPTP_GRE_IS_C(f) ((f)&PPTP_GRE_FLAG_C) +#define PPTP_GRE_IS_R(f) ((f)&PPTP_GRE_FLAG_R) +#define PPTP_GRE_IS_K(f) ((f)&PPTP_GRE_FLAG_K) +#define PPTP_GRE_IS_S(f) ((f)&PPTP_GRE_FLAG_S) +#define PPTP_GRE_IS_A(f) ((f)&PPTP_GRE_FLAG_A) + +#define PPTP_HEADER_OVERHEAD (2+sizeof(struct pptp_gre_header)) +struct pptp_gre_header { + u8 flags; + u8 ver; + __be16 protocol; + __be16 payload_len; + __be16 call_id; + __be32 seq; + __be32 ack; +} __packed; + + +#endif diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 1046f5515174..60dbb200de60 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -24,9 +24,14 @@ #define GRE_SEQ __cpu_to_be16(0x1000) #define GRE_STRICT __cpu_to_be16(0x0800) #define GRE_REC __cpu_to_be16(0x0700) -#define GRE_FLAGS __cpu_to_be16(0x00F8) +#define GRE_ACK __cpu_to_be16(0x0080) +#define GRE_FLAGS __cpu_to_be16(0x0078) #define GRE_VERSION __cpu_to_be16(0x0007) +#define GRE_VERSION_1 __cpu_to_be16(0x0001) +#define GRE_PROTO_PPP __cpu_to_be16(0x880b) +#define GRE_PPTP_KEY_MASK __cpu_to_be32(0xffff) + struct ip_tunnel_parm { char name[IFNAMSIZ]; int link; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 61ad43f61c5e..91028ae2fb01 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -6,6 +6,8 @@ #include #include #include +#include +#include #include #include #include @@ -338,32 +340,42 @@ mpls: ip_proto_again: switch (ip_proto) { case IPPROTO_GRE: { - struct gre_hdr { - __be16 flags; - __be16 proto; - } *hdr, _hdr; + struct gre_base_hdr *hdr, _hdr; + u16 gre_ver; + int offset = 0; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) goto out_bad; - /* - * Only look inside GRE if version zero and no - * routing - */ - if (hdr->flags & (GRE_VERSION | GRE_ROUTING)) + + /* Only look inside GRE without routing */ + if (hdr->flags & GRE_ROUTING) break; - proto = hdr->proto; - nhoff += 4; + /* Only look inside GRE for version 0 and 1 */ + gre_ver = ntohs(hdr->flags & GRE_VERSION); + if (gre_ver > 1) + break; + + proto = hdr->protocol; + if (gre_ver) { + /* Version1 must be PPTP, and check the flags */ + if (!(proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY))) + break; + } + + offset += sizeof(struct gre_base_hdr); + if (hdr->flags & GRE_CSUM) - nhoff += 4; + offset += sizeof(((struct gre_full_hdr *)0)->csum) + + sizeof(((struct gre_full_hdr *)0)->reserved1); + if (hdr->flags & GRE_KEY) { const __be32 *keyid; __be32 _keyid; - keyid = __skb_header_pointer(skb, nhoff, sizeof(_keyid), + keyid = __skb_header_pointer(skb, nhoff + offset, sizeof(_keyid), data, hlen, &_keyid); - if (!keyid) goto out_bad; @@ -372,32 +384,65 @@ ip_proto_again: key_keyid = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_GRE_KEYID, target_container); - key_keyid->keyid = *keyid; + if (gre_ver == 0) + key_keyid->keyid = *keyid; + else + key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK; } - nhoff += 4; + offset += sizeof(((struct gre_full_hdr *)0)->key); } + if (hdr->flags & GRE_SEQ) - nhoff += 4; - if (proto == htons(ETH_P_TEB)) { - const struct ethhdr *eth; - struct ethhdr _eth; - - eth = __skb_header_pointer(skb, nhoff, - sizeof(_eth), - data, hlen, &_eth); - if (!eth) + offset += sizeof(((struct pptp_gre_header *)0)->seq); + + if (gre_ver == 0) { + if (proto == htons(ETH_P_TEB)) { + const struct ethhdr *eth; + struct ethhdr _eth; + + eth = __skb_header_pointer(skb, nhoff + offset, + sizeof(_eth), + data, hlen, &_eth); + if (!eth) + goto out_bad; + proto = eth->h_proto; + offset += sizeof(*eth); + + /* Cap headers that we access via pointers at the + * end of the Ethernet header as our maximum alignment + * at that point is only 2 bytes. + */ + if (NET_IP_ALIGN) + hlen = (nhoff + offset); + } + } else { /* version 1, must be PPTP */ + u8 _ppp_hdr[PPP_HDRLEN]; + u8 *ppp_hdr; + + if (hdr->flags & GRE_ACK) + offset += sizeof(((struct pptp_gre_header *)0)->ack); + + ppp_hdr = skb_header_pointer(skb, nhoff + offset, + sizeof(_ppp_hdr), _ppp_hdr); + if (!ppp_hdr) goto out_bad; - proto = eth->h_proto; - nhoff += sizeof(*eth); - - /* Cap headers that we access via pointers at the - * end of the Ethernet header as our maximum alignment - * at that point is only 2 bytes. - */ - if (NET_IP_ALIGN) - hlen = nhoff; + + switch (PPP_PROTOCOL(ppp_hdr)) { + case PPP_IP: + proto = htons(ETH_P_IP); + break; + case PPP_IPV6: + proto = htons(ETH_P_IPV6); + break; + default: + /* Could probably catch some more like MPLS */ + break; + } + + offset += PPP_HDRLEN; } + nhoff += offset; key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) goto out_good; -- cgit v1.2.3 From cb1b69b0b15b2897daeba8674c14c85a23a3347f Mon Sep 17 00:00:00 2001 From: Laura Garcia Liebana Date: Thu, 11 Aug 2016 18:02:07 +0200 Subject: netfilter: nf_tables: add hash expression This patch adds a new hash expression, this provides jhash support but this can be extended to support for other hash functions. The modulus and seed already comes embedded into this new expression. Use case example: ... meta mark set hash ip saddr mod 10 Signed-off-by: Laura Garcia Liebana Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 20 +++++ net/netfilter/Kconfig | 6 ++ net/netfilter/Makefile | 1 + net/netfilter/nft_hash.c | 136 +++++++++++++++++++++++++++++++ 4 files changed, 163 insertions(+) create mode 100644 net/netfilter/nft_hash.c (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 01751faccaf8..6ce0a6dd0889 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -723,6 +723,26 @@ enum nft_meta_keys { NFT_META_PRANDOM, }; +/** + * enum nft_hash_attributes - nf_tables hash expression netlink attributes + * + * @NFTA_HASH_SREG: source register (NLA_U32) + * @NFTA_HASH_DREG: destination register (NLA_U32) + * @NFTA_HASH_LEN: source data length (NLA_U32) + * @NFTA_HASH_MODULUS: modulus value (NLA_U32) + * @NFTA_HASH_SEED: seed value (NLA_U32) + */ +enum nft_hash_attributes { + NFTA_HASH_UNSPEC, + NFTA_HASH_SREG, + NFTA_HASH_DREG, + NFTA_HASH_LEN, + NFTA_HASH_MODULUS, + NFTA_HASH_SEED, + __NFTA_HASH_MAX, +}; +#define NFTA_HASH_MAX (__NFTA_HASH_MAX - 1) + /** * enum nft_meta_attributes - nf_tables meta expression netlink attributes * diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index e5740e108a0b..9cfaa00c79b2 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -563,6 +563,12 @@ config NFT_COMPAT x_tables match/target extensions over the nf_tables framework. +config NFT_HASH + tristate "Netfilter nf_tables hash module" + help + This option adds the "hash" expression that you can use to perform + a hash operation on registers. + if NF_TABLES_NETDEV config NF_DUP_NETDEV diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 101fb859203c..1106ccde215c 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -92,6 +92,7 @@ obj-$(CONFIG_NFT_COUNTER) += nft_counter.o obj-$(CONFIG_NFT_LOG) += nft_log.o obj-$(CONFIG_NFT_MASQ) += nft_masq.o obj-$(CONFIG_NFT_REDIR) += nft_redir.o +obj-$(CONFIG_NFT_HASH) += nft_hash.o # nf_tables netdev obj-$(CONFIG_NFT_DUP_NETDEV) += nft_dup_netdev.o diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c new file mode 100644 index 000000000000..b82ff29b3f5f --- /dev/null +++ b/net/netfilter/nft_hash.c @@ -0,0 +1,136 @@ +/* + * Copyright (c) 2016 Laura Garcia + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct nft_hash { + enum nft_registers sreg:8; + enum nft_registers dreg:8; + u8 len; + u32 modulus; + u32 seed; +}; + +static void nft_hash_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_hash *priv = nft_expr_priv(expr); + const void *data = ®s->data[priv->sreg]; + + regs->data[priv->dreg] = + reciprocal_scale(jhash(data, priv->len, priv->seed), + priv->modulus); +} + +const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = { + [NFTA_HASH_SREG] = { .type = NLA_U32 }, + [NFTA_HASH_DREG] = { .type = NLA_U32 }, + [NFTA_HASH_LEN] = { .type = NLA_U32 }, + [NFTA_HASH_MODULUS] = { .type = NLA_U32 }, + [NFTA_HASH_SEED] = { .type = NLA_U32 }, +}; + +static int nft_hash_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_hash *priv = nft_expr_priv(expr); + u32 len; + + if (!tb[NFTA_HASH_SREG] || + !tb[NFTA_HASH_DREG] || + !tb[NFTA_HASH_LEN] || + !tb[NFTA_HASH_SEED] || + !tb[NFTA_HASH_MODULUS]) + return -EINVAL; + + priv->sreg = nft_parse_register(tb[NFTA_HASH_SREG]); + priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]); + + len = ntohl(nla_get_be32(tb[NFTA_HASH_LEN])); + if (len == 0 || len > U8_MAX) + return -ERANGE; + + priv->len = len; + + priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS])); + if (priv->modulus <= 1) + return -ERANGE; + + priv->seed = ntohl(nla_get_be32(tb[NFTA_HASH_SEED])); + + return nft_validate_register_load(priv->sreg, len) && + nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, sizeof(u32)); +} + +static int nft_hash_dump(struct sk_buff *skb, + const struct nft_expr *expr) +{ + const struct nft_hash *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_HASH_SREG, priv->sreg)) + goto nla_put_failure; + if (nft_dump_register(skb, NFTA_HASH_DREG, priv->dreg)) + goto nla_put_failure; + if (nft_dump_register(skb, NFTA_HASH_LEN, priv->len)) + goto nla_put_failure; + if (nft_dump_register(skb, NFTA_HASH_MODULUS, priv->modulus)) + goto nla_put_failure; + if (nft_dump_register(skb, NFTA_HASH_SEED, priv->seed)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static struct nft_expr_type nft_hash_type; +static const struct nft_expr_ops nft_hash_ops = { + .type = &nft_hash_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_hash)), + .eval = nft_hash_eval, + .init = nft_hash_init, + .dump = nft_hash_dump, +}; + +static struct nft_expr_type nft_hash_type __read_mostly = { + .name = "hash", + .ops = &nft_hash_ops, + .policy = nft_hash_policy, + .maxattr = NFTA_HASH_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_hash_module_init(void) +{ + return nft_register_expr(&nft_hash_type); +} + +static void __exit nft_hash_module_exit(void) +{ + nft_unregister_expr(&nft_hash_type); +} + +module_init(nft_hash_module_init); +module_exit(nft_hash_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Laura Garcia "); +MODULE_ALIAS_NFT_EXPR("hash"); -- cgit v1.2.3 From 300d8b93d73533411a98362350fe7d1795f1a044 Mon Sep 17 00:00:00 2001 From: Appana Durga Kedareswara Rao Date: Wed, 10 Aug 2016 11:20:06 +0530 Subject: net: Add mask for Control register 10Mbps speed This patch adds mask for the Control register 10Mbps speed. Reviewed-by: Florian Fainelli Signed-off-by: Kedareswara rao Appana Signed-off-by: David S. Miller --- include/uapi/linux/mii.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mii.h b/include/uapi/linux/mii.h index 237fac4bc17b..15d8510cdae0 100644 --- a/include/uapi/linux/mii.h +++ b/include/uapi/linux/mii.h @@ -48,6 +48,7 @@ #define BMCR_SPEED100 0x2000 /* Select 100Mbps */ #define BMCR_LOOPBACK 0x4000 /* TXD loopback bits */ #define BMCR_RESET 0x8000 /* Reset to default state */ +#define BMCR_SPEED10 0x0000 /* Select 10Mbps */ /* Basic mode status register. */ #define BMSR_ERCAP 0x0001 /* Ext-reg capability */ -- cgit v1.2.3 From 60d20f9195b260bdf0ac10c275ae9f6016f9c069 Mon Sep 17 00:00:00 2001 From: Sargun Dhillon Date: Fri, 12 Aug 2016 08:56:52 -0700 Subject: bpf: Add bpf_current_task_under_cgroup helper This adds a bpf helper that's similar to the skb_in_cgroup helper to check whether the probe is currently executing in the context of a specific subset of the cgroupsv2 hierarchy. It does this based on membership test for a cgroup arraymap. It is invalid to call this in an interrupt, and it'll return an error. The helper is primarily to be used in debugging activities for containers, where you may have multiple programs running in a given top-level "container". Signed-off-by: Sargun Dhillon Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Tejun Heo Acked-by: Tejun Heo Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 11 +++++++++++ kernel/bpf/arraymap.c | 2 +- kernel/bpf/verifier.c | 4 +++- kernel/trace/bpf_trace.c | 30 ++++++++++++++++++++++++++++++ 4 files changed, 45 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index da218fec6056..bea0c4e2830a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -375,6 +375,17 @@ enum bpf_func_id { */ 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_FUNC_MAX_ID, }; diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 633a650d7aeb..a2ac051c342f 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -538,7 +538,7 @@ static int __init register_perf_event_array_map(void) } late_initcall(register_perf_event_array_map); -#ifdef CONFIG_SOCK_CGROUP_DATA +#ifdef CONFIG_CGROUPS static void *cgroup_fd_array_get_ptr(struct bpf_map *map, struct file *map_file /* not used */, int fd) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 7094c69ac199..d504722ebfa4 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1053,7 +1053,8 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) goto error; break; case BPF_MAP_TYPE_CGROUP_ARRAY: - if (func_id != BPF_FUNC_skb_in_cgroup) + if (func_id != BPF_FUNC_skb_in_cgroup && + func_id != BPF_FUNC_current_task_under_cgroup) goto error; break; default: @@ -1075,6 +1076,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) if (map->map_type != BPF_MAP_TYPE_STACK_TRACE) goto error; break; + case BPF_FUNC_current_task_under_cgroup: case BPF_FUNC_skb_in_cgroup: if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY) goto error; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index b20438fdb029..6b794d6669a7 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -376,6 +376,34 @@ static const struct bpf_func_proto bpf_get_current_task_proto = { .ret_type = RET_INTEGER, }; +static u64 bpf_current_task_under_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + struct bpf_map *map = (struct bpf_map *)(long)r1; + struct bpf_array *array = container_of(map, struct bpf_array, map); + struct cgroup *cgrp; + u32 idx = (u32)r2; + + if (unlikely(in_interrupt())) + return -EINVAL; + + if (unlikely(idx >= array->map.max_entries)) + return -E2BIG; + + cgrp = READ_ONCE(array->ptrs[idx]); + if (unlikely(!cgrp)) + return -EAGAIN; + + return task_under_cgroup_hierarchy(current, cgrp); +} + +static const struct bpf_func_proto bpf_current_task_under_cgroup_proto = { + .func = bpf_current_task_under_cgroup, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id) { switch (func_id) { @@ -407,6 +435,8 @@ static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id) return &bpf_perf_event_read_proto; case BPF_FUNC_probe_write_user: return bpf_get_probe_write_proto(); + case BPF_FUNC_current_task_under_cgroup: + return &bpf_current_task_under_cgroup_proto; default: return NULL; } -- cgit v1.2.3 From 03459345bc00da70a35fa39bcfcf13d779097074 Mon Sep 17 00:00:00 2001 From: Gao Feng Date: Sat, 13 Aug 2016 00:30:48 +0800 Subject: pptp: Refactor the struct and macros of PPTP codes 1. Use struct gre_base_hdr directly in pptp_gre_header instead of duplicated members; 2. Use existing macros like GRE_KEY, GRE_SEQ, and so on instead of duplicated macros defined by PPTP; 3. Add new macros like GRE_IS_ACK/SEQ and so on instead of PPTP_GRE_IS_A/S and so on; Signed-off-by: Gao Feng Reviewed-by: Philip Prindeville Signed-off-by: David S. Miller --- drivers/net/ppp/pptp.c | 28 +++++++++++++--------------- include/net/pptp.h | 19 +------------------ include/uapi/linux/if_tunnel.h | 12 ++++++++++-- 3 files changed, 24 insertions(+), 35 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 3e68dbc0af7f..1951b1085cb8 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -206,16 +206,14 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb) skb_push(skb, header_len); hdr = (struct pptp_gre_header *)(skb->data); - hdr->flags = PPTP_GRE_FLAG_K; - hdr->ver = PPTP_GRE_VER; - hdr->protocol = htons(PPTP_GRE_PROTO); - hdr->call_id = htons(opt->dst_addr.call_id); + hdr->gre_hd.flags = GRE_KEY | GRE_VERSION_1 | GRE_SEQ; + hdr->gre_hd.protocol = GRE_PROTO_PPP; + hdr->call_id = htons(opt->dst_addr.call_id); - hdr->flags |= PPTP_GRE_FLAG_S; - hdr->seq = htonl(++opt->seq_sent); + hdr->seq = htonl(++opt->seq_sent); if (opt->ack_sent != seq_recv) { /* send ack with this message */ - hdr->ver |= PPTP_GRE_FLAG_A; + hdr->gre_hd.flags |= GRE_ACK; hdr->ack = htonl(seq_recv); opt->ack_sent = seq_recv; } @@ -278,7 +276,7 @@ static int pptp_rcv_core(struct sock *sk, struct sk_buff *skb) headersize = sizeof(*header); /* test if acknowledgement present */ - if (PPTP_GRE_IS_A(header->ver)) { + if (GRE_IS_ACK(header->gre_hd.flags)) { __u32 ack; if (!pskb_may_pull(skb, headersize)) @@ -286,7 +284,7 @@ static int pptp_rcv_core(struct sock *sk, struct sk_buff *skb) header = (struct pptp_gre_header *)(skb->data); /* ack in different place if S = 0 */ - ack = PPTP_GRE_IS_S(header->flags) ? header->ack : header->seq; + ack = GRE_IS_SEQ(header->gre_hd.flags) ? header->ack : header->seq; ack = ntohl(ack); @@ -299,7 +297,7 @@ static int pptp_rcv_core(struct sock *sk, struct sk_buff *skb) headersize -= sizeof(header->ack); } /* test if payload present */ - if (!PPTP_GRE_IS_S(header->flags)) + if (!GRE_IS_SEQ(header->gre_hd.flags)) goto drop; payload_len = ntohs(header->payload_len); @@ -360,11 +358,11 @@ static int pptp_rcv(struct sk_buff *skb) header = (struct pptp_gre_header *)skb->data; - if (ntohs(header->protocol) != PPTP_GRE_PROTO || /* PPTP-GRE protocol for PPTP */ - PPTP_GRE_IS_C(header->flags) || /* flag C should be clear */ - PPTP_GRE_IS_R(header->flags) || /* flag R should be clear */ - !PPTP_GRE_IS_K(header->flags) || /* flag K should be set */ - (header->flags&0xF) != 0) /* routing and recursion ctrl = 0 */ + if (header->gre_hd.protocol != GRE_PROTO_PPP || /* PPTP-GRE protocol for PPTP */ + GRE_IS_CSUM(header->gre_hd.flags) || /* flag CSUM should be clear */ + GRE_IS_ROUTING(header->gre_hd.flags) || /* flag ROUTING should be clear */ + !GRE_IS_KEY(header->gre_hd.flags) || /* flag KEY should be set */ + (header->gre_hd.flags & GRE_FLAGS)) /* flag Recursion Ctrl should be clear */ /* if invalid, discard this packet */ goto drop; diff --git a/include/net/pptp.h b/include/net/pptp.h index 301d3e2ba1f9..92e9f1fe2628 100644 --- a/include/net/pptp.h +++ b/include/net/pptp.h @@ -10,26 +10,9 @@ ((((curseq) & 0xffffff00) == 0) &&\ (((lastseq) & 0xffffff00) == 0xffffff00)) -#define PPTP_GRE_PROTO 0x880B -#define PPTP_GRE_VER 0x1 - -#define PPTP_GRE_FLAG_C 0x80 -#define PPTP_GRE_FLAG_R 0x40 -#define PPTP_GRE_FLAG_K 0x20 -#define PPTP_GRE_FLAG_S 0x10 -#define PPTP_GRE_FLAG_A 0x80 - -#define PPTP_GRE_IS_C(f) ((f)&PPTP_GRE_FLAG_C) -#define PPTP_GRE_IS_R(f) ((f)&PPTP_GRE_FLAG_R) -#define PPTP_GRE_IS_K(f) ((f)&PPTP_GRE_FLAG_K) -#define PPTP_GRE_IS_S(f) ((f)&PPTP_GRE_FLAG_S) -#define PPTP_GRE_IS_A(f) ((f)&PPTP_GRE_FLAG_A) - #define PPTP_HEADER_OVERHEAD (2+sizeof(struct pptp_gre_header)) struct pptp_gre_header { - u8 flags; - u8 ver; - __be16 protocol; + struct gre_base_hdr gre_hd; __be16 payload_len; __be16 call_id; __be32 seq; diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 60dbb200de60..361b9f0f20d7 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -28,8 +28,16 @@ #define GRE_FLAGS __cpu_to_be16(0x0078) #define GRE_VERSION __cpu_to_be16(0x0007) -#define GRE_VERSION_1 __cpu_to_be16(0x0001) -#define GRE_PROTO_PPP __cpu_to_be16(0x880b) +#define GRE_IS_CSUM(f) ((f) & GRE_CSUM) +#define GRE_IS_ROUTING(f) ((f) & GRE_ROUTING) +#define GRE_IS_KEY(f) ((f) & GRE_KEY) +#define GRE_IS_SEQ(f) ((f) & GRE_SEQ) +#define GRE_IS_STRICT(f) ((f) & GRE_STRICT) +#define GRE_IS_REC(f) ((f) & GRE_REC) +#define GRE_IS_ACK(f) ((f) & GRE_ACK) + +#define GRE_VERSION_1 __cpu_to_be16(0x0001) +#define GRE_PROTO_PPP __cpu_to_be16(0x880b) #define GRE_PPTP_KEY_MASK __cpu_to_be32(0xffff) struct ip_tunnel_parm { -- cgit v1.2.3 From 02486c2905a7caa50b0f508a86e03d12d8d24ac4 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 11 Aug 2016 17:36:20 -0700 Subject: libnvdimm: fix SMART Health DSM payload definition "NVDIMM DSM Interface Example" v1.2 made an incompatible change to the layout of function1 "SMART and Health Info". While the kernel does not directly consume this payload, it does define it in ndctl.h that userpace utilities consume. Reported-by: Brian Boylston Signed-off-by: Dan Williams --- include/uapi/linux/ndctl.h | 30 +++++++++++++++++------------- 1 file changed, 17 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index ba5a8c79652a..ede5c6a62164 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -21,14 +21,16 @@ struct nd_cmd_smart { } __packed; #define ND_SMART_HEALTH_VALID (1 << 0) -#define ND_SMART_TEMP_VALID (1 << 1) -#define ND_SMART_SPARES_VALID (1 << 2) -#define ND_SMART_ALARM_VALID (1 << 3) -#define ND_SMART_USED_VALID (1 << 4) -#define ND_SMART_SHUTDOWN_VALID (1 << 5) -#define ND_SMART_VENDOR_VALID (1 << 6) -#define ND_SMART_TEMP_TRIP (1 << 0) -#define ND_SMART_SPARE_TRIP (1 << 1) +#define ND_SMART_SPARES_VALID (1 << 1) +#define ND_SMART_USED_VALID (1 << 2) +#define ND_SMART_TEMP_VALID (1 << 3) +#define ND_SMART_CTEMP_VALID (1 << 4) +#define ND_SMART_ALARM_VALID (1 << 9) +#define ND_SMART_SHUTDOWN_VALID (1 << 10) +#define ND_SMART_VENDOR_VALID (1 << 11) +#define ND_SMART_SPARE_TRIP (1 << 0) +#define ND_SMART_TEMP_TRIP (1 << 1) +#define ND_SMART_CTEMP_TRIP (1 << 2) #define ND_SMART_NON_CRITICAL_HEALTH (1 << 0) #define ND_SMART_CRITICAL_HEALTH (1 << 1) #define ND_SMART_FATAL_HEALTH (1 << 2) @@ -37,14 +39,15 @@ struct nd_smart_payload { __u32 flags; __u8 reserved0[4]; __u8 health; - __u16 temperature; __u8 spares; - __u8 alarm_flags; __u8 life_used; + __u8 alarm_flags; + __u16 temperature; + __u16 ctrl_temperature; + __u8 reserved1[15]; __u8 shutdown_state; - __u8 reserved1; __u32 vendor_size; - __u8 vendor_data[108]; + __u8 vendor_data[92]; } __packed; struct nd_cmd_smart_threshold { @@ -53,7 +56,8 @@ struct nd_cmd_smart_threshold { } __packed; struct nd_smart_threshold_payload { - __u16 alarm_control; + __u8 alarm_control; + __u8 reserved0; __u16 temperature; __u8 spares; __u8 reserved[3]; -- cgit v1.2.3 From 9bb04a0c4e261187be904d05c2bcd1da0eebc20c Mon Sep 17 00:00:00 2001 From: Jonathan Yong Date: Sat, 11 Jun 2016 14:13:38 -0500 Subject: PCI: Add Precision Time Measurement (PTM) support Add Precision Time Measurement (PTM) support (see PCIe r3.1, sec 6.22). Enable PTM on PTM Root devices and switch ports. This does not enable PTM on endpoints. There currently are no PTM-capable devices on the market, but it is expected to be supported by the Intel Apollo Lake platform. [bhelgaas: complete rework] Signed-off-by: Jonathan Yong Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.h | 6 ++++ drivers/pci/pcie/Kconfig | 11 +++++++ drivers/pci/pcie/Makefile | 1 + drivers/pci/pcie/ptm.c | 70 +++++++++++++++++++++++++++++++++++++++++++ drivers/pci/probe.c | 3 ++ include/linux/pci.h | 5 ++++ include/uapi/linux/pci_regs.h | 10 ++++++- 7 files changed, 105 insertions(+), 1 deletion(-) create mode 100644 drivers/pci/pcie/ptm.c (limited to 'include/uapi/linux') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 9730c474b016..194521bfb1a3 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -332,6 +332,12 @@ static inline resource_size_t pci_resource_alignment(struct pci_dev *dev, void pci_enable_acs(struct pci_dev *dev); +#ifdef CONFIG_PCIE_PTM +void pci_ptm_init(struct pci_dev *dev); +#else +static inline void pci_ptm_init(struct pci_dev *dev) { } +#endif + struct pci_dev_reset_methods { u16 vendor; u16 device; diff --git a/drivers/pci/pcie/Kconfig b/drivers/pci/pcie/Kconfig index 7fcea75afa4c..7ce77635e5ad 100644 --- a/drivers/pci/pcie/Kconfig +++ b/drivers/pci/pcie/Kconfig @@ -92,3 +92,14 @@ config PCIE_DPC will be handled by the DPC driver. If your system doesn't have this capability or you do not want to use this feature, it is safe to answer N. + +config PCIE_PTM + bool "PCIe Precision Time Measurement support" + default n + depends on PCIEPORTBUS + help + This enables PCI Express Precision Time Measurement (PTM) + support. + + This is only useful if you have devices that support PTM, but it + is safe to enable even if you don't. diff --git a/drivers/pci/pcie/Makefile b/drivers/pci/pcie/Makefile index b24525b3dec1..36e35ea8fde7 100644 --- a/drivers/pci/pcie/Makefile +++ b/drivers/pci/pcie/Makefile @@ -16,3 +16,4 @@ obj-$(CONFIG_PCIEAER) += aer/ obj-$(CONFIG_PCIE_PME) += pme.o obj-$(CONFIG_PCIE_DPC) += pcie-dpc.o +obj-$(CONFIG_PCIE_PTM) += ptm.o diff --git a/drivers/pci/pcie/ptm.c b/drivers/pci/pcie/ptm.c new file mode 100644 index 000000000000..48eea4e65247 --- /dev/null +++ b/drivers/pci/pcie/ptm.c @@ -0,0 +1,70 @@ +/* + * PCI Express Precision Time Measurement + * Copyright (c) 2016, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include +#include +#include +#include "../pci.h" + +static void pci_ptm_info(struct pci_dev *dev) +{ + dev_info(&dev->dev, "PTM enabled%s\n", dev->ptm_root ? " (root)" : ""); +} + +void pci_ptm_init(struct pci_dev *dev) +{ + int pos; + u32 cap, ctrl; + struct pci_dev *ups; + + if (!pci_is_pcie(dev)) + return; + + pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_PTM); + if (!pos) + return; + + /* + * Enable PTM only on interior devices (root ports, switch ports, + * etc.) on the assumption that it causes no link traffic until an + * endpoint enables it. + */ + if ((pci_pcie_type(dev) == PCI_EXP_TYPE_ENDPOINT || + pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END)) + return; + + pci_read_config_dword(dev, pos + PCI_PTM_CAP, &cap); + + /* + * There's no point in enabling PTM unless it's enabled in the + * upstream device or this device can be a PTM Root itself. Per + * the spec recommendation (PCIe r3.1, sec 7.32.3), select the + * furthest upstream Time Source as the PTM Root. + */ + ups = pci_upstream_bridge(dev); + if (ups && ups->ptm_enabled) { + ctrl = PCI_PTM_CTRL_ENABLE; + } else { + if (cap & PCI_PTM_CAP_ROOT) { + ctrl = PCI_PTM_CTRL_ENABLE | PCI_PTM_CTRL_ROOT; + dev->ptm_root = 1; + } else + return; + } + + pci_write_config_dword(dev, pos + PCI_PTM_CTRL, ctrl); + dev->ptm_enabled = 1; + + pci_ptm_info(dev); +} diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 93f280df3428..e2e424472058 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1667,6 +1667,9 @@ static void pci_init_capabilities(struct pci_dev *dev) pci_enable_acs(dev); pci_cleanup_aer_error_status_regs(dev); + + /* Precision Time Measurement */ + pci_ptm_init(dev); } /* diff --git a/include/linux/pci.h b/include/linux/pci.h index 2599a980340f..96c509fa9d46 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -367,6 +367,11 @@ struct pci_dev { int rom_attr_enabled; /* has display of the rom attribute been enabled? */ struct bin_attribute *res_attr[DEVICE_COUNT_RESOURCE]; /* sysfs file for resources */ struct bin_attribute *res_attr_wc[DEVICE_COUNT_RESOURCE]; /* sysfs file for WC mapping of resources */ + +#ifdef CONFIG_PCIE_PTM + unsigned int ptm_root:1; + unsigned int ptm_enabled:1; +#endif #ifdef CONFIG_PCI_MSI const struct attribute_group **msi_irq_groups; #endif diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 404095124ae2..926fff41b417 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -671,7 +671,8 @@ #define PCI_EXT_CAP_ID_PMUX 0x1A /* Protocol Multiplexing */ #define PCI_EXT_CAP_ID_PASID 0x1B /* Process Address Space ID */ #define PCI_EXT_CAP_ID_DPC 0x1D /* Downstream Port Containment */ -#define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_DPC +#define PCI_EXT_CAP_ID_PTM 0x1F /* Precision Time Measurement */ +#define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_PTM #define PCI_EXT_CAP_DSN_SIZEOF 12 #define PCI_EXT_CAP_MCAST_ENDPOINT_SIZEOF 40 @@ -964,4 +965,11 @@ #define PCI_EXP_DPC_SOURCE_ID 10 /* DPC Source Identifier */ +/* Precision Time Measurement */ +#define PCI_PTM_CAP 0x04 /* PTM Capability */ +#define PCI_PTM_CAP_ROOT 0x00000004 /* Root capable */ +#define PCI_PTM_CTRL 0x08 /* PTM Control */ +#define PCI_PTM_CTRL_ENABLE 0x00000001 /* PTM enable */ +#define PCI_PTM_CTRL_ROOT 0x00000002 /* Root select */ + #endif /* LINUX_PCI_REGS_H */ -- cgit v1.2.3 From 0b28cb4bcb17dcb5fe0763fc3e1a94398b8f6cf6 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Sun, 7 Aug 2016 02:25:36 -0700 Subject: HID: intel-ish-hid: ISH HID client driver This driver is responsible for implementing ISH HID client, which gets HID description and report. Once it has completely gets report descriptors, it registers as a HID LL drivers. This implements necessary callbacks so that it can be used by HID sensor hub driver. Original-author: Daniel Drubin Reviewed-and-tested-by: Ooi, Joyce Tested-by: Grant Likely Tested-by: Rann Bar-On Tested-by: Atri Bhattacharya Signed-off-by: Srinivas Pandruvada Signed-off-by: Jiri Kosina --- drivers/hid/intel-ish-hid/Makefile | 4 + drivers/hid/intel-ish-hid/ishtp-hid-client.c | 978 +++++++++++++++++++++++++++ drivers/hid/intel-ish-hid/ishtp-hid.c | 246 +++++++ drivers/hid/intel-ish-hid/ishtp-hid.h | 182 +++++ include/uapi/linux/input.h | 1 + 5 files changed, 1411 insertions(+) create mode 100644 drivers/hid/intel-ish-hid/ishtp-hid-client.c create mode 100644 drivers/hid/intel-ish-hid/ishtp-hid.c create mode 100644 drivers/hid/intel-ish-hid/ishtp-hid.h (limited to 'include/uapi/linux') diff --git a/drivers/hid/intel-ish-hid/Makefile b/drivers/hid/intel-ish-hid/Makefile index ab626d8f7bb8..8c08b0b358b1 100644 --- a/drivers/hid/intel-ish-hid/Makefile +++ b/drivers/hid/intel-ish-hid/Makefile @@ -15,4 +15,8 @@ obj-$(CONFIG_INTEL_ISH_HID) += intel-ish-ipc.o intel-ish-ipc-objs := ipc/ipc.o intel-ish-ipc-objs += ipc/pci-ish.o +obj-$(CONFIG_INTEL_ISH_HID) += intel-ishtp-hid.o +intel-ishtp-hid-objs := ishtp-hid.o +intel-ishtp-hid-objs += ishtp-hid-client.o + ccflags-y += -Idrivers/hid/intel-ish-hid/ishtp diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c new file mode 100644 index 000000000000..5c643d7a07b2 --- /dev/null +++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c @@ -0,0 +1,978 @@ +/* + * ISHTP client driver for HID (ISH) + * + * Copyright (c) 2014-2016, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include +#include +#include +#include "ishtp/ishtp-dev.h" +#include "ishtp/client.h" +#include "ishtp-hid.h" + +/* Rx ring buffer pool size */ +#define HID_CL_RX_RING_SIZE 32 +#define HID_CL_TX_RING_SIZE 16 + +/** + * report_bad_packets() - Report bad packets + * @hid_ishtp_cl: Client instance to get stats + * @recv_buf: Raw received host interface message + * @cur_pos: Current position index in payload + * @payload_len: Length of payload expected + * + * Dumps error in case bad packet is received + */ +static void report_bad_packet(struct ishtp_cl *hid_ishtp_cl, void *recv_buf, + size_t cur_pos, size_t payload_len) +{ + struct hostif_msg *recv_msg = recv_buf; + struct ishtp_cl_data *client_data = hid_ishtp_cl->client_data; + + dev_err(&client_data->cl_device->dev, "[hid-ish]: BAD packet %02X\n" + "total_bad=%u cur_pos=%u\n" + "[%02X %02X %02X %02X]\n" + "payload_len=%u\n" + "multi_packet_cnt=%u\n" + "is_response=%02X\n", + recv_msg->hdr.command, client_data->bad_recv_cnt, + (unsigned int)cur_pos, + ((unsigned char *)recv_msg)[0], ((unsigned char *)recv_msg)[1], + ((unsigned char *)recv_msg)[2], ((unsigned char *)recv_msg)[3], + (unsigned int)payload_len, client_data->multi_packet_cnt, + recv_msg->hdr.command & ~CMD_MASK); +} + +/** + * process_recv() - Received and parse incoming packet + * @hid_ishtp_cl: Client instance to get stats + * @recv_buf: Raw received host interface message + * @data_len: length of the message + * + * Parse the incoming packet. If it is a response packet then it will update + * per instance flags and wake up the caller waiting to for the response. + */ +static void process_recv(struct ishtp_cl *hid_ishtp_cl, void *recv_buf, + size_t data_len) +{ + struct hostif_msg *recv_msg; + unsigned char *payload; + struct device_info *dev_info; + int i, j; + size_t payload_len, total_len, cur_pos; + int report_type; + struct report_list *reports_list; + char *reports; + size_t report_len; + struct ishtp_cl_data *client_data = hid_ishtp_cl->client_data; + int curr_hid_dev = client_data->cur_hid_dev; + + if (data_len < sizeof(struct hostif_msg_hdr)) { + dev_err(&client_data->cl_device->dev, + "[hid-ish]: error, received %u which is less than data header %u\n", + (unsigned int)data_len, + (unsigned int)sizeof(struct hostif_msg_hdr)); + ++client_data->bad_recv_cnt; + ish_hw_reset(hid_ishtp_cl->dev); + return; + } + + payload = recv_buf + sizeof(struct hostif_msg_hdr); + total_len = data_len; + cur_pos = 0; + + do { + recv_msg = (struct hostif_msg *)(recv_buf + cur_pos); + payload_len = recv_msg->hdr.size; + + /* Sanity checks */ + if (cur_pos + payload_len + sizeof(struct hostif_msg) > + total_len) { + ++client_data->bad_recv_cnt; + report_bad_packet(hid_ishtp_cl, recv_msg, cur_pos, + payload_len); + ish_hw_reset(hid_ishtp_cl->dev); + break; + } + + hid_ishtp_trace(client_data, "%s %d\n", + __func__, recv_msg->hdr.command & CMD_MASK); + + switch (recv_msg->hdr.command & CMD_MASK) { + case HOSTIF_DM_ENUM_DEVICES: + if ((!(recv_msg->hdr.command & ~CMD_MASK) || + client_data->init_done)) { + ++client_data->bad_recv_cnt; + report_bad_packet(hid_ishtp_cl, recv_msg, + cur_pos, + payload_len); + ish_hw_reset(hid_ishtp_cl->dev); + break; + } + client_data->hid_dev_count = (unsigned int)*payload; + if (!client_data->hid_devices) + client_data->hid_devices = devm_kzalloc( + &client_data->cl_device->dev, + client_data->hid_dev_count * + sizeof(struct device_info), + GFP_KERNEL); + if (!client_data->hid_devices) { + dev_err(&client_data->cl_device->dev, + "Mem alloc failed for hid device info\n"); + wake_up_interruptible(&client_data->init_wait); + break; + } + for (i = 0; i < client_data->hid_dev_count; ++i) { + if (1 + sizeof(struct device_info) * i >= + payload_len) { + dev_err(&client_data->cl_device->dev, + "[hid-ish]: [ENUM_DEVICES]: content size %lu is bigger than payload_len %u\n", + 1 + sizeof(struct device_info) + * i, + (unsigned int)payload_len); + } + + if (1 + sizeof(struct device_info) * i >= + data_len) + break; + + dev_info = (struct device_info *)(payload + 1 + + sizeof(struct device_info) * i); + if (client_data->hid_devices) + memcpy(client_data->hid_devices + i, + dev_info, + sizeof(struct device_info)); + } + + client_data->enum_devices_done = true; + wake_up_interruptible(&client_data->init_wait); + + break; + + case HOSTIF_GET_HID_DESCRIPTOR: + if ((!(recv_msg->hdr.command & ~CMD_MASK) || + client_data->init_done)) { + ++client_data->bad_recv_cnt; + report_bad_packet(hid_ishtp_cl, recv_msg, + cur_pos, + payload_len); + ish_hw_reset(hid_ishtp_cl->dev); + break; + } + if (!client_data->hid_descr[curr_hid_dev]) + client_data->hid_descr[curr_hid_dev] = + devm_kmalloc(&client_data->cl_device->dev, + payload_len, GFP_KERNEL); + if (client_data->hid_descr[curr_hid_dev]) { + memcpy(client_data->hid_descr[curr_hid_dev], + payload, payload_len); + client_data->hid_descr_size[curr_hid_dev] = + payload_len; + client_data->hid_descr_done = true; + } + wake_up_interruptible(&client_data->init_wait); + + break; + + case HOSTIF_GET_REPORT_DESCRIPTOR: + if ((!(recv_msg->hdr.command & ~CMD_MASK) || + client_data->init_done)) { + ++client_data->bad_recv_cnt; + report_bad_packet(hid_ishtp_cl, recv_msg, + cur_pos, + payload_len); + ish_hw_reset(hid_ishtp_cl->dev); + break; + } + if (!client_data->report_descr[curr_hid_dev]) + client_data->report_descr[curr_hid_dev] = + devm_kmalloc(&client_data->cl_device->dev, + payload_len, GFP_KERNEL); + if (client_data->report_descr[curr_hid_dev]) { + memcpy(client_data->report_descr[curr_hid_dev], + payload, + payload_len); + client_data->report_descr_size[curr_hid_dev] = + payload_len; + client_data->report_descr_done = true; + } + wake_up_interruptible(&client_data->init_wait); + + break; + + case HOSTIF_GET_FEATURE_REPORT: + report_type = HID_FEATURE_REPORT; + goto do_get_report; + + case HOSTIF_GET_INPUT_REPORT: + report_type = HID_INPUT_REPORT; +do_get_report: + /* Get index of device that matches this id */ + for (i = 0; i < client_data->num_hid_devices; ++i) { + if (recv_msg->hdr.device_id == + client_data->hid_devices[i].dev_id) + if (client_data->hid_sensor_hubs[i]) { + hid_input_report( + client_data->hid_sensor_hubs[ + i], + report_type, payload, + payload_len, 0); + ishtp_hid_wakeup( + client_data->hid_sensor_hubs[ + i]); + break; + } + } + break; + + case HOSTIF_SET_FEATURE_REPORT: + /* Get index of device that matches this id */ + for (i = 0; i < client_data->num_hid_devices; ++i) { + if (recv_msg->hdr.device_id == + client_data->hid_devices[i].dev_id) + if (client_data->hid_sensor_hubs[i]) { + ishtp_hid_wakeup( + client_data->hid_sensor_hubs[ + i]); + break; + } + } + break; + + case HOSTIF_PUBLISH_INPUT_REPORT: + report_type = HID_INPUT_REPORT; + for (i = 0; i < client_data->num_hid_devices; ++i) + if (recv_msg->hdr.device_id == + client_data->hid_devices[i].dev_id) + if (client_data->hid_sensor_hubs[i]) + hid_input_report( + client_data->hid_sensor_hubs[ + i], + report_type, payload, + payload_len, 0); + break; + + case HOSTIF_PUBLISH_INPUT_REPORT_LIST: + report_type = HID_INPUT_REPORT; + reports_list = (struct report_list *)payload; + reports = (char *)reports_list->reports; + + for (j = 0; j < reports_list->num_of_reports; j++) { + recv_msg = (struct hostif_msg *)(reports + + sizeof(uint16_t)); + report_len = *(uint16_t *)reports; + payload = reports + sizeof(uint16_t) + + sizeof(struct hostif_msg_hdr); + payload_len = report_len - + sizeof(struct hostif_msg_hdr); + + for (i = 0; i < client_data->num_hid_devices; + ++i) + if (recv_msg->hdr.device_id == + client_data->hid_devices[i].dev_id && + client_data->hid_sensor_hubs[i]) { + hid_input_report( + client_data->hid_sensor_hubs[ + i], + report_type, + payload, payload_len, + 0); + } + + reports += sizeof(uint16_t) + report_len; + } + break; + default: + ++client_data->bad_recv_cnt; + report_bad_packet(hid_ishtp_cl, recv_msg, cur_pos, + payload_len); + ish_hw_reset(hid_ishtp_cl->dev); + break; + + } + + if (!cur_pos && cur_pos + payload_len + + sizeof(struct hostif_msg) < total_len) + ++client_data->multi_packet_cnt; + + cur_pos += payload_len + sizeof(struct hostif_msg); + payload += payload_len + sizeof(struct hostif_msg); + + } while (cur_pos < total_len); +} + +/** + * ish_cl_event_cb() - bus driver callback for incoming message/packet + * @device: Pointer to the the ishtp client device for which this message + * is targeted + * + * Remove the packet from the list and process the message by calling + * process_recv + */ +static void ish_cl_event_cb(struct ishtp_cl_device *device) +{ + struct ishtp_cl *hid_ishtp_cl = device->driver_data; + struct ishtp_cl_rb *rb_in_proc; + size_t r_length; + unsigned long flags; + + if (!hid_ishtp_cl) + return; + + spin_lock_irqsave(&hid_ishtp_cl->in_process_spinlock, flags); + while (!list_empty(&hid_ishtp_cl->in_process_list.list)) { + rb_in_proc = list_entry( + hid_ishtp_cl->in_process_list.list.next, + struct ishtp_cl_rb, list); + list_del_init(&rb_in_proc->list); + spin_unlock_irqrestore(&hid_ishtp_cl->in_process_spinlock, + flags); + + if (!rb_in_proc->buffer.data) + return; + + r_length = rb_in_proc->buf_idx; + + /* decide what to do with received data */ + process_recv(hid_ishtp_cl, rb_in_proc->buffer.data, r_length); + + ishtp_cl_io_rb_recycle(rb_in_proc); + spin_lock_irqsave(&hid_ishtp_cl->in_process_spinlock, flags); + } + spin_unlock_irqrestore(&hid_ishtp_cl->in_process_spinlock, flags); +} + +/** + * hid_ishtp_set_feature() - send request to ISH FW to set a feature request + * @hid: hid device instance for this request + * @buf: feature buffer + * @len: Length of feature buffer + * @report_id: Report id for the feature set request + * + * This is called from hid core .request() callback. This function doesn't wait + * for response. + */ +void hid_ishtp_set_feature(struct hid_device *hid, char *buf, unsigned int len, + int report_id) +{ + struct ishtp_hid_data *hid_data = hid->driver_data; + struct ishtp_cl_data *client_data = hid_data->client_data; + struct hostif_msg *msg = (struct hostif_msg *)buf; + int rv; + int i; + + hid_ishtp_trace(client_data, "%s hid %p\n", __func__, hid); + + rv = ishtp_hid_link_ready_wait(client_data); + if (rv) { + hid_ishtp_trace(client_data, "%s hid %p link not ready\n", + __func__, hid); + return; + } + + memset(msg, 0, sizeof(struct hostif_msg)); + msg->hdr.command = HOSTIF_SET_FEATURE_REPORT; + for (i = 0; i < client_data->num_hid_devices; ++i) { + if (hid == client_data->hid_sensor_hubs[i]) { + msg->hdr.device_id = + client_data->hid_devices[i].dev_id; + break; + } + } + + if (i == client_data->num_hid_devices) + return; + + rv = ishtp_cl_send(client_data->hid_ishtp_cl, buf, len); + if (rv) + hid_ishtp_trace(client_data, "%s hid %p send failed\n", + __func__, hid); +} + +/** + * hid_ishtp_get_report() - request to get feature/input report + * @hid: hid device instance for this request + * @report_id: Report id for the get request + * @report_type: Report type for the this request + * + * This is called from hid core .request() callback. This function will send + * request to FW and return without waiting for response. + */ +void hid_ishtp_get_report(struct hid_device *hid, int report_id, + int report_type) +{ + struct ishtp_hid_data *hid_data = hid->driver_data; + struct ishtp_cl_data *client_data = hid_data->client_data; + static unsigned char buf[10]; + unsigned int len; + struct hostif_msg_to_sensor *msg = (struct hostif_msg_to_sensor *)buf; + int rv; + int i; + + hid_ishtp_trace(client_data, "%s hid %p\n", __func__, hid); + rv = ishtp_hid_link_ready_wait(client_data); + if (rv) { + hid_ishtp_trace(client_data, "%s hid %p link not ready\n", + __func__, hid); + return; + } + + len = sizeof(struct hostif_msg_to_sensor); + + memset(msg, 0, sizeof(struct hostif_msg_to_sensor)); + msg->hdr.command = (report_type == HID_FEATURE_REPORT) ? + HOSTIF_GET_FEATURE_REPORT : HOSTIF_GET_INPUT_REPORT; + for (i = 0; i < client_data->num_hid_devices; ++i) { + if (hid == client_data->hid_sensor_hubs[i]) { + msg->hdr.device_id = + client_data->hid_devices[i].dev_id; + break; + } + } + + if (i == client_data->num_hid_devices) + return; + + msg->report_id = report_id; + rv = ishtp_cl_send(client_data->hid_ishtp_cl, buf, len); + if (rv) + hid_ishtp_trace(client_data, "%s hid %p send failed\n", + __func__, hid); +} + +/** + * ishtp_hid_link_ready_wait() - Wait for link ready + * @client_data: client data instance + * + * If the transport link started suspend process, then wait, till either + * resumed or timeout + * + * Return: 0 on success, non zero on error + */ +int ishtp_hid_link_ready_wait(struct ishtp_cl_data *client_data) +{ + int rc; + + if (client_data->suspended) { + hid_ishtp_trace(client_data, "wait for link ready\n"); + rc = wait_event_interruptible_timeout( + client_data->ishtp_resume_wait, + !client_data->suspended, + 5 * HZ); + + if (rc == 0) { + hid_ishtp_trace(client_data, "link not ready\n"); + return -EIO; + } + hid_ishtp_trace(client_data, "link ready\n"); + } + + return 0; +} + +/** + * ishtp_enum_enum_devices() - Enumerate hid devices + * @hid_ishtp_cl: client instance + * + * Helper function to send request to firmware to enumerate HID devices + * + * Return: 0 on success, non zero on error + */ +static int ishtp_enum_enum_devices(struct ishtp_cl *hid_ishtp_cl) +{ + struct hostif_msg msg; + struct ishtp_cl_data *client_data = hid_ishtp_cl->client_data; + int retry_count; + int rv; + + /* Send HOSTIF_DM_ENUM_DEVICES */ + memset(&msg, 0, sizeof(struct hostif_msg)); + msg.hdr.command = HOSTIF_DM_ENUM_DEVICES; + rv = ishtp_cl_send(hid_ishtp_cl, (unsigned char *)&msg, + sizeof(struct hostif_msg)); + if (rv) + return rv; + + retry_count = 0; + while (!client_data->enum_devices_done && + retry_count < 10) { + wait_event_interruptible_timeout(client_data->init_wait, + client_data->enum_devices_done, + 3 * HZ); + ++retry_count; + if (!client_data->enum_devices_done) + /* Send HOSTIF_DM_ENUM_DEVICES */ + rv = ishtp_cl_send(hid_ishtp_cl, + (unsigned char *) &msg, + sizeof(struct hostif_msg)); + } + if (!client_data->enum_devices_done) { + dev_err(&client_data->cl_device->dev, + "[hid-ish]: timed out waiting for enum_devices\n"); + return -ETIMEDOUT; + } + if (!client_data->hid_devices) { + dev_err(&client_data->cl_device->dev, + "[hid-ish]: failed to allocate HID dev structures\n"); + return -ENOMEM; + } + + client_data->num_hid_devices = client_data->hid_dev_count; + dev_info(&hid_ishtp_cl->device->dev, + "[hid-ish]: enum_devices_done OK, num_hid_devices=%d\n", + client_data->num_hid_devices); + + return 0; +} + +/** + * ishtp_get_hid_descriptor() - Get hid descriptor + * @hid_ishtp_cl: client instance + * @index: Index into the hid_descr array + * + * Helper function to send request to firmware get HID descriptor of a device + * + * Return: 0 on success, non zero on error + */ +static int ishtp_get_hid_descriptor(struct ishtp_cl *hid_ishtp_cl, int index) +{ + struct hostif_msg msg; + struct ishtp_cl_data *client_data = hid_ishtp_cl->client_data; + int rv; + + /* Get HID descriptor */ + client_data->hid_descr_done = false; + memset(&msg, 0, sizeof(struct hostif_msg)); + msg.hdr.command = HOSTIF_GET_HID_DESCRIPTOR; + msg.hdr.device_id = client_data->hid_devices[index].dev_id; + rv = ishtp_cl_send(hid_ishtp_cl, (unsigned char *) &msg, + sizeof(struct hostif_msg)); + if (rv) + return rv; + + if (!client_data->hid_descr_done) { + wait_event_interruptible_timeout(client_data->init_wait, + client_data->hid_descr_done, + 3 * HZ); + if (!client_data->hid_descr_done) { + dev_err(&client_data->cl_device->dev, + "[hid-ish]: timed out for hid_descr_done\n"); + return -EIO; + } + + if (!client_data->hid_descr[index]) { + dev_err(&client_data->cl_device->dev, + "[hid-ish]: allocation HID desc fail\n"); + return -ENOMEM; + } + } + + return 0; +} + +/** + * ishtp_get_report_descriptor() - Get report descriptor + * @hid_ishtp_cl: client instance + * @index: Index into the hid_descr array + * + * Helper function to send request to firmware get HID report descriptor of + * a device + * + * Return: 0 on success, non zero on error + */ +static int ishtp_get_report_descriptor(struct ishtp_cl *hid_ishtp_cl, + int index) +{ + struct hostif_msg msg; + struct ishtp_cl_data *client_data = hid_ishtp_cl->client_data; + int rv; + + /* Get report descriptor */ + client_data->report_descr_done = false; + memset(&msg, 0, sizeof(struct hostif_msg)); + msg.hdr.command = HOSTIF_GET_REPORT_DESCRIPTOR; + msg.hdr.device_id = client_data->hid_devices[index].dev_id; + rv = ishtp_cl_send(hid_ishtp_cl, (unsigned char *) &msg, + sizeof(struct hostif_msg)); + if (rv) + return rv; + + if (!client_data->report_descr_done) + wait_event_interruptible_timeout(client_data->init_wait, + client_data->report_descr_done, + 3 * HZ); + if (!client_data->report_descr_done) { + dev_err(&client_data->cl_device->dev, + "[hid-ish]: timed out for report descr\n"); + return -EIO; + } + if (!client_data->report_descr[index]) { + dev_err(&client_data->cl_device->dev, + "[hid-ish]: failed to alloc report descr\n"); + return -ENOMEM; + } + + return 0; +} + +/** + * hid_ishtp_cl_init() - Init function for ISHTP client + * @hid_ishtp_cl: ISHTP client instance + * @reset: true if called for init after reset + * + * This function complete the initializtion of the client. The summary of + * processing: + * - Send request to enumerate the hid clients + * Get the HID descriptor for each enumearated device + * Get report description of each device + * Register each device wik hid core by calling ishtp_hid_probe + * + * Return: 0 on success, non zero on error + */ +static int hid_ishtp_cl_init(struct ishtp_cl *hid_ishtp_cl, int reset) +{ + struct ishtp_device *dev; + unsigned long flags; + struct ishtp_cl_data *client_data = hid_ishtp_cl->client_data; + int i; + int rv; + + dev_dbg(&client_data->cl_device->dev, "%s\n", __func__); + hid_ishtp_trace(client_data, "%s reset flag: %d\n", __func__, reset); + + rv = ishtp_cl_link(hid_ishtp_cl, ISHTP_HOST_CLIENT_ID_ANY); + if (rv) { + dev_err(&client_data->cl_device->dev, + "ishtp_cl_link failed\n"); + return -ENOMEM; + } + + client_data->init_done = 0; + + dev = hid_ishtp_cl->dev; + + /* Connect to FW client */ + hid_ishtp_cl->rx_ring_size = HID_CL_RX_RING_SIZE; + hid_ishtp_cl->tx_ring_size = HID_CL_TX_RING_SIZE; + + spin_lock_irqsave(&dev->fw_clients_lock, flags); + i = ishtp_fw_cl_by_uuid(dev, &hid_ishtp_guid); + if (i < 0) { + spin_unlock_irqrestore(&dev->fw_clients_lock, flags); + dev_err(&client_data->cl_device->dev, + "ish client uuid not found\n"); + return i; + } + hid_ishtp_cl->fw_client_id = dev->fw_clients[i].client_id; + spin_unlock_irqrestore(&dev->fw_clients_lock, flags); + hid_ishtp_cl->state = ISHTP_CL_CONNECTING; + + rv = ishtp_cl_connect(hid_ishtp_cl); + if (rv) { + dev_err(&client_data->cl_device->dev, + "client connect fail\n"); + goto err_cl_unlink; + } + + hid_ishtp_trace(client_data, "%s client connected\n", __func__); + + /* Register read callback */ + ishtp_register_event_cb(hid_ishtp_cl->device, ish_cl_event_cb); + + rv = ishtp_enum_enum_devices(hid_ishtp_cl); + if (rv) + goto err_cl_disconnect; + + hid_ishtp_trace(client_data, "%s enumerated device count %d\n", + __func__, client_data->num_hid_devices); + + for (i = 0; i < client_data->num_hid_devices; ++i) { + client_data->cur_hid_dev = i; + + rv = ishtp_get_hid_descriptor(hid_ishtp_cl, i); + if (rv) + goto err_cl_disconnect; + + rv = ishtp_get_report_descriptor(hid_ishtp_cl, i); + if (rv) + goto err_cl_disconnect; + + if (!reset) { + rv = ishtp_hid_probe(i, client_data); + if (rv) { + dev_err(&client_data->cl_device->dev, + "[hid-ish]: HID probe for #%u failed: %d\n", + i, rv); + goto err_cl_disconnect; + } + } + } /* for() on all hid devices */ + + client_data->init_done = 1; + client_data->suspended = false; + wake_up_interruptible(&client_data->ishtp_resume_wait); + hid_ishtp_trace(client_data, "%s successful init\n", __func__); + return 0; + +err_cl_disconnect: + hid_ishtp_cl->state = ISHTP_CL_DISCONNECTING; + ishtp_cl_disconnect(hid_ishtp_cl); +err_cl_unlink: + ishtp_cl_unlink(hid_ishtp_cl); + return rv; +} + +/** + * hid_ishtp_cl_deinit() - Deinit function for ISHTP client + * @hid_ishtp_cl: ISHTP client instance + * + * Unlink and free hid client + */ +static void hid_ishtp_cl_deinit(struct ishtp_cl *hid_ishtp_cl) +{ + ishtp_cl_unlink(hid_ishtp_cl); + ishtp_cl_flush_queues(hid_ishtp_cl); + + /* disband and free all Tx and Rx client-level rings */ + ishtp_cl_free(hid_ishtp_cl); +} + +static void hid_ishtp_cl_reset_handler(struct work_struct *work) +{ + struct ishtp_cl_data *client_data; + struct ishtp_cl *hid_ishtp_cl; + struct ishtp_cl_device *cl_device; + int retry; + int rv; + + client_data = container_of(work, struct ishtp_cl_data, work); + + hid_ishtp_cl = client_data->hid_ishtp_cl; + cl_device = client_data->cl_device; + + hid_ishtp_trace(client_data, "%s hid_ishtp_cl %p\n", __func__, + hid_ishtp_cl); + dev_dbg(&cl_device->dev, "%s\n", __func__); + + hid_ishtp_cl_deinit(hid_ishtp_cl); + + hid_ishtp_cl = ishtp_cl_allocate(cl_device->ishtp_dev); + if (!hid_ishtp_cl) + return; + + cl_device->driver_data = hid_ishtp_cl; + hid_ishtp_cl->client_data = client_data; + client_data->hid_ishtp_cl = hid_ishtp_cl; + + client_data->num_hid_devices = 0; + + for (retry = 0; retry < 3; ++retry) { + rv = hid_ishtp_cl_init(hid_ishtp_cl, 1); + if (!rv) + break; + dev_err(&client_data->cl_device->dev, "Retry reset init\n"); + } + if (rv) { + dev_err(&client_data->cl_device->dev, "Reset Failed\n"); + hid_ishtp_trace(client_data, "%s Failed hid_ishtp_cl %p\n", + __func__, hid_ishtp_cl); + } +} + +/** + * hid_ishtp_cl_probe() - ISHTP client driver probe + * @cl_device: ISHTP client device instance + * + * This function gets called on device create on ISHTP bus + * + * Return: 0 on success, non zero on error + */ +static int hid_ishtp_cl_probe(struct ishtp_cl_device *cl_device) +{ + struct ishtp_cl *hid_ishtp_cl; + struct ishtp_cl_data *client_data; + int rv; + + if (!cl_device) + return -ENODEV; + + if (uuid_le_cmp(hid_ishtp_guid, + cl_device->fw_client->props.protocol_name) != 0) + return -ENODEV; + + client_data = devm_kzalloc(&cl_device->dev, sizeof(*client_data), + GFP_KERNEL); + if (!client_data) + return -ENOMEM; + + hid_ishtp_cl = ishtp_cl_allocate(cl_device->ishtp_dev); + if (!hid_ishtp_cl) + return -ENOMEM; + + cl_device->driver_data = hid_ishtp_cl; + hid_ishtp_cl->client_data = client_data; + client_data->hid_ishtp_cl = hid_ishtp_cl; + client_data->cl_device = cl_device; + + init_waitqueue_head(&client_data->init_wait); + init_waitqueue_head(&client_data->ishtp_resume_wait); + + INIT_WORK(&client_data->work, hid_ishtp_cl_reset_handler); + + rv = hid_ishtp_cl_init(hid_ishtp_cl, 0); + if (rv) { + ishtp_cl_free(hid_ishtp_cl); + return rv; + } + ishtp_get_device(cl_device); + + return 0; +} + +/** + * hid_ishtp_cl_remove() - ISHTP client driver remove + * @cl_device: ISHTP client device instance + * + * This function gets called on device remove on ISHTP bus + * + * Return: 0 + */ +static int hid_ishtp_cl_remove(struct ishtp_cl_device *cl_device) +{ + struct ishtp_cl *hid_ishtp_cl = cl_device->driver_data; + struct ishtp_cl_data *client_data = hid_ishtp_cl->client_data; + + hid_ishtp_trace(client_data, "%s hid_ishtp_cl %p\n", __func__, + hid_ishtp_cl); + + dev_dbg(&cl_device->dev, "%s\n", __func__); + hid_ishtp_cl->state = ISHTP_CL_DISCONNECTING; + ishtp_cl_disconnect(hid_ishtp_cl); + ishtp_put_device(cl_device); + ishtp_hid_remove(client_data); + hid_ishtp_cl_deinit(hid_ishtp_cl); + + hid_ishtp_cl = NULL; + + client_data->num_hid_devices = 0; + + return 0; +} + +/** + * hid_ishtp_cl_reset() - ISHTP client driver reset + * @cl_device: ISHTP client device instance + * + * This function gets called on device reset on ISHTP bus + * + * Return: 0 + */ +static int hid_ishtp_cl_reset(struct ishtp_cl_device *cl_device) +{ + struct ishtp_cl *hid_ishtp_cl = cl_device->driver_data; + struct ishtp_cl_data *client_data = hid_ishtp_cl->client_data; + + hid_ishtp_trace(client_data, "%s hid_ishtp_cl %p\n", __func__, + hid_ishtp_cl); + + schedule_work(&client_data->work); + + return 0; +} + +#define to_ishtp_cl_device(d) container_of(d, struct ishtp_cl_device, dev) + +/** + * hid_ishtp_cl_suspend() - ISHTP client driver suspend + * @device: device instance + * + * This function gets called on system suspend + * + * Return: 0 + */ +static int hid_ishtp_cl_suspend(struct device *device) +{ + struct ishtp_cl_device *cl_device = to_ishtp_cl_device(device); + struct ishtp_cl *hid_ishtp_cl = cl_device->driver_data; + struct ishtp_cl_data *client_data = hid_ishtp_cl->client_data; + + hid_ishtp_trace(client_data, "%s hid_ishtp_cl %p\n", __func__, + hid_ishtp_cl); + client_data->suspended = true; + + return 0; +} + +/** + * hid_ishtp_cl_resume() - ISHTP client driver resume + * @device: device instance + * + * This function gets called on system resume + * + * Return: 0 + */ +static int hid_ishtp_cl_resume(struct device *device) +{ + struct ishtp_cl_device *cl_device = to_ishtp_cl_device(device); + struct ishtp_cl *hid_ishtp_cl = cl_device->driver_data; + struct ishtp_cl_data *client_data = hid_ishtp_cl->client_data; + + hid_ishtp_trace(client_data, "%s hid_ishtp_cl %p\n", __func__, + hid_ishtp_cl); + client_data->suspended = false; + return 0; +} + +static const struct dev_pm_ops hid_ishtp_pm_ops = { + .suspend = hid_ishtp_cl_suspend, + .resume = hid_ishtp_cl_resume, +}; + +static struct ishtp_cl_driver hid_ishtp_cl_driver = { + .name = "ish-hid", + .probe = hid_ishtp_cl_probe, + .remove = hid_ishtp_cl_remove, + .reset = hid_ishtp_cl_reset, + .driver.pm = &hid_ishtp_pm_ops, +}; + +static int __init ish_hid_init(void) +{ + int rv; + + /* Register ISHTP client device driver with ISHTP Bus */ + rv = ishtp_cl_driver_register(&hid_ishtp_cl_driver); + + return rv; + +} + +static void __exit ish_hid_exit(void) +{ + ishtp_cl_driver_unregister(&hid_ishtp_cl_driver); +} + +late_initcall(ish_hid_init); +module_exit(ish_hid_exit); + +MODULE_DESCRIPTION("ISH ISHTP HID client driver"); +/* Primary author */ +MODULE_AUTHOR("Daniel Drubin "); +/* + * Several modification for multi instance support + * suspend/resume and clean up + */ +MODULE_AUTHOR("Srinivas Pandruvada "); + +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ishtp:*"); diff --git a/drivers/hid/intel-ish-hid/ishtp-hid.c b/drivers/hid/intel-ish-hid/ishtp-hid.c new file mode 100644 index 000000000000..277983aa1d90 --- /dev/null +++ b/drivers/hid/intel-ish-hid/ishtp-hid.c @@ -0,0 +1,246 @@ +/* + * ISHTP-HID glue driver. + * + * Copyright (c) 2012-2016, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include +#include +#include "ishtp/client.h" +#include "ishtp-hid.h" + +/** + * ishtp_hid_parse() - hid-core .parse() callback + * @hid: hid device instance + * + * This function gets called during call to hid_add_device + * + * Return: 0 on success and non zero on error + */ +static int ishtp_hid_parse(struct hid_device *hid) +{ + struct ishtp_hid_data *hid_data = hid->driver_data; + struct ishtp_cl_data *client_data = hid_data->client_data; + int rv; + + rv = hid_parse_report(hid, client_data->report_descr[hid_data->index], + client_data->report_descr_size[hid_data->index]); + if (rv) + return rv; + + return 0; +} + +/* Empty callbacks with success return code */ +static int ishtp_hid_start(struct hid_device *hid) +{ + return 0; +} + +static void ishtp_hid_stop(struct hid_device *hid) +{ +} + +static int ishtp_hid_open(struct hid_device *hid) +{ + return 0; +} + +static void ishtp_hid_close(struct hid_device *hid) +{ +} + +static int ishtp_raw_request(struct hid_device *hdev, unsigned char reportnum, + __u8 *buf, size_t len, unsigned char rtype, int reqtype) +{ + return 0; +} + +/** + * ishtp_hid_request() - hid-core .request() callback + * @hid: hid device instance + * @rep: pointer to hid_report + * @reqtype: type of req. [GET|SET]_REPORT + * + * This function is used to set/get feaure/input report. + */ +static void ishtp_hid_request(struct hid_device *hid, struct hid_report *rep, + int reqtype) +{ + struct ishtp_hid_data *hid_data = hid->driver_data; + /* the specific report length, just HID part of it */ + unsigned int len = ((rep->size - 1) >> 3) + 1 + (rep->id > 0); + char *buf; + unsigned int header_size = sizeof(struct hostif_msg); + + len += header_size; + + hid_data->request_done = false; + switch (reqtype) { + case HID_REQ_GET_REPORT: + hid_ishtp_get_report(hid, rep->id, rep->type); + break; + case HID_REQ_SET_REPORT: + /* + * Spare 7 bytes for 64b accesses through + * get/put_unaligned_le64() + */ + buf = kzalloc(len + 7, GFP_KERNEL); + if (!buf) + return; + + hid_output_report(rep, buf + header_size); + hid_ishtp_set_feature(hid, buf, len, rep->id); + kfree(buf); + break; + } +} + +/** + * ishtp_wait_for_response() - hid-core .wait() callback + * @hid: hid device instance + * + * This function is used to wait after get feaure/input report. + * + * Return: 0 on success and non zero on error + */ +static int ishtp_wait_for_response(struct hid_device *hid) +{ + struct ishtp_hid_data *hid_data = hid->driver_data; + struct ishtp_cl_data *client_data = hid_data->client_data; + int rv; + + hid_ishtp_trace(client_data, "%s hid %p\n", __func__, hid); + + rv = ishtp_hid_link_ready_wait(hid_data->client_data); + if (rv) + return rv; + + if (!hid_data->request_done) + wait_event_interruptible_timeout(hid_data->hid_wait, + hid_data->request_done, 3 * HZ); + + if (!hid_data->request_done) { + hid_err(hid, + "timeout waiting for response from ISHTP device\n"); + return -ETIMEDOUT; + } + hid_ishtp_trace(client_data, "%s hid %p done\n", __func__, hid); + + hid_data->request_done = false; + + return 0; +} + +/** + * ishtp_hid_wakeup() - Wakeup caller + * @hid: hid device instance + * + * This function will wakeup caller waiting for Get/Set feature report + */ +void ishtp_hid_wakeup(struct hid_device *hid) +{ + struct ishtp_hid_data *hid_data = hid->driver_data; + + hid_data->request_done = true; + wake_up_interruptible(&hid_data->hid_wait); +} + +static struct hid_ll_driver ishtp_hid_ll_driver = { + .parse = ishtp_hid_parse, + .start = ishtp_hid_start, + .stop = ishtp_hid_stop, + .open = ishtp_hid_open, + .close = ishtp_hid_close, + .request = ishtp_hid_request, + .wait = ishtp_wait_for_response, + .raw_request = ishtp_raw_request +}; + +/** + * ishtp_hid_probe() - hid register ll driver + * @cur_hid_dev: Index of hid device calling to register + * @client_data: Client data pointer + * + * This function is used to allocate and add HID device. + * + * Return: 0 on success, non zero on error + */ +int ishtp_hid_probe(unsigned int cur_hid_dev, + struct ishtp_cl_data *client_data) +{ + int rv; + struct hid_device *hid; + struct ishtp_hid_data *hid_data; + + hid = hid_allocate_device(); + if (IS_ERR(hid)) { + rv = PTR_ERR(hid); + return -ENOMEM; + } + + hid_data = kzalloc(sizeof(*hid_data), GFP_KERNEL); + if (!hid_data) { + rv = -ENOMEM; + goto err_hid_data; + } + + hid_data->index = cur_hid_dev; + hid_data->client_data = client_data; + init_waitqueue_head(&hid_data->hid_wait); + + hid->driver_data = hid_data; + + client_data->hid_sensor_hubs[cur_hid_dev] = hid; + + hid->ll_driver = &ishtp_hid_ll_driver; + hid->bus = BUS_INTEL_ISHTP; + hid->dev.parent = &client_data->cl_device->dev; + hid->version = le16_to_cpu(ISH_HID_VERSION); + hid->vendor = le16_to_cpu(ISH_HID_VENDOR); + hid->product = le16_to_cpu(ISH_HID_PRODUCT); + snprintf(hid->name, sizeof(hid->name), "%s %04hX:%04hX", "hid-ishtp", + hid->vendor, hid->product); + + rv = hid_add_device(hid); + if (rv) + goto err_hid_device; + + hid_ishtp_trace(client_data, "%s allocated hid %p\n", __func__, hid); + + return 0; + +err_hid_device: + kfree(hid_data); +err_hid_data: + kfree(hid); + return rv; +} + +/** + * ishtp_hid_probe() - Remove registered hid device + * @client_data: client data pointer + * + * This function is used to destroy allocatd HID device. + */ +void ishtp_hid_remove(struct ishtp_cl_data *client_data) +{ + int i; + + for (i = 0; i < client_data->num_hid_devices; ++i) { + if (client_data->hid_sensor_hubs[i]) { + kfree(client_data->hid_sensor_hubs[i]->driver_data); + hid_destroy_device(client_data->hid_sensor_hubs[i]); + client_data->hid_sensor_hubs[i] = NULL; + } + } +} diff --git a/drivers/hid/intel-ish-hid/ishtp-hid.h b/drivers/hid/intel-ish-hid/ishtp-hid.h new file mode 100644 index 000000000000..f5c7eb79b7b5 --- /dev/null +++ b/drivers/hid/intel-ish-hid/ishtp-hid.h @@ -0,0 +1,182 @@ +/* + * ISHTP-HID glue driver's definitions. + * + * Copyright (c) 2014-2016, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ +#ifndef ISHTP_HID__H +#define ISHTP_HID__H + +/* The fixed ISH product and vendor id */ +#define ISH_HID_VENDOR 0x8086 +#define ISH_HID_PRODUCT 0x22D8 +#define ISH_HID_VERSION 0x0200 + +#define CMD_MASK 0x7F +#define IS_RESPONSE 0x80 + +/* Used to dump to Linux trace buffer, if enabled */ +#define hid_ishtp_trace(client, ...) \ + client->cl_device->ishtp_dev->print_log(\ + client->cl_device->ishtp_dev, __VA_ARGS__) + +/* ISH Transport protocol (ISHTP in short) GUID */ +static const uuid_le hid_ishtp_guid = UUID_LE(0x33AECD58, 0xB679, 0x4E54, + 0x9B, 0xD9, 0xA0, 0x4D, 0x34, + 0xF0, 0xC2, 0x26); + +/* ISH HID message structure */ +struct hostif_msg_hdr { + uint8_t command; /* Bit 7: is_response */ + uint8_t device_id; + uint8_t status; + uint8_t flags; + uint16_t size; +} __packed; + +struct hostif_msg { + struct hostif_msg_hdr hdr; +} __packed; + +struct hostif_msg_to_sensor { + struct hostif_msg_hdr hdr; + uint8_t report_id; +} __packed; + +struct device_info { + uint32_t dev_id; + uint8_t dev_class; + uint16_t pid; + uint16_t vid; +} __packed; + +struct ishtp_version { + uint8_t major; + uint8_t minor; + uint8_t hotfix; + uint16_t build; +} __packed; + +/* struct for ISHTP aggregated input data */ +struct report_list { + uint16_t total_size; + uint8_t num_of_reports; + uint8_t flags; + struct { + uint16_t size_of_report; + uint8_t report[1]; + } __packed reports[1]; +} __packed; + +/* HOSTIF commands */ +#define HOSTIF_HID_COMMAND_BASE 0 +#define HOSTIF_GET_HID_DESCRIPTOR 0 +#define HOSTIF_GET_REPORT_DESCRIPTOR 1 +#define HOSTIF_GET_FEATURE_REPORT 2 +#define HOSTIF_SET_FEATURE_REPORT 3 +#define HOSTIF_GET_INPUT_REPORT 4 +#define HOSTIF_PUBLISH_INPUT_REPORT 5 +#define HOSTIF_PUBLISH_INPUT_REPORT_LIST 6 +#define HOSTIF_DM_COMMAND_BASE 32 +#define HOSTIF_DM_ENUM_DEVICES 33 +#define HOSTIF_DM_ADD_DEVICE 34 + +#define MAX_HID_DEVICES 32 + +/** + * struct ishtp_cl_data - Encapsulate per ISH TP HID Client + * @enum_device_done: Enum devices response complete flag + * @hid_descr_done: HID descriptor complete flag + * @report_descr_done: Get report descriptor complete flag + * @init_done: Init process completed successfully + * @suspended: System is under suspend state or in progress + * @num_hid_devices: Number of HID devices enumerated in this client + * @cur_hid_dev: This keeps track of the device index for which + * initialization and registration with HID core + * in progress. + * @hid_devices: Store vid/pid/devid for each enumerated HID device + * @report_descr: Stores the raw report descriptors for each HID device + * @report_descr_size: Report description of size of above repo_descr[] + * @hid_sensor_hubs: Pointer to hid_device for all HID device, so that + * when clients are removed, they can be freed + * @hid_descr: Pointer to hid descriptor for each enumerated hid + * device + * @hid_descr_size: Size of each above report descriptor + * @init_wait: Wait queue to wait during initialization, where the + * client send message to ISH FW and wait for response + * @ishtp_hid_wait: The wait for get report during wait callback from hid + * core + * @bad_recv_cnt: Running count of packets received with error + * @multi_packet_cnt: Count of fragmented packet count + * + * This structure is used to store completion flags and per client data like + * like report description, number of HID devices etc. + */ +struct ishtp_cl_data { + /* completion flags */ + bool enum_devices_done; + bool hid_descr_done; + bool report_descr_done; + bool init_done; + bool suspended; + + unsigned int num_hid_devices; + unsigned int cur_hid_dev; + unsigned int hid_dev_count; + + struct device_info *hid_devices; + unsigned char *report_descr[MAX_HID_DEVICES]; + int report_descr_size[MAX_HID_DEVICES]; + struct hid_device *hid_sensor_hubs[MAX_HID_DEVICES]; + unsigned char *hid_descr[MAX_HID_DEVICES]; + int hid_descr_size[MAX_HID_DEVICES]; + + wait_queue_head_t init_wait; + wait_queue_head_t ishtp_resume_wait; + struct ishtp_cl *hid_ishtp_cl; + + /* Statistics */ + unsigned int bad_recv_cnt; + int multi_packet_cnt; + + struct work_struct work; + struct ishtp_cl_device *cl_device; +}; + +/** + * struct ishtp_hid_data - Per instance HID data + * @index: Device index in the order of enumeration + * @request_done: Get Feature/Input report complete flag + * used during get/set request from hid core + * @client_data: Link to the client instance + * @hid_wait: Completion waitq + * + * Used to tie hid hid->driver data to driver client instance + */ +struct ishtp_hid_data { + int index; + bool request_done; + struct ishtp_cl_data *client_data; + wait_queue_head_t hid_wait; +}; + +/* Interface functions between HID LL driver and ISH TP client */ +void hid_ishtp_set_feature(struct hid_device *hid, char *buf, unsigned int len, + int report_id); +void hid_ishtp_get_report(struct hid_device *hid, int report_id, + int report_type); +int ishtp_hid_probe(unsigned int cur_hid_dev, + struct ishtp_cl_data *client_data); +void ishtp_hid_remove(struct ishtp_cl_data *client_data); +int ishtp_hid_link_ready_wait(struct ishtp_cl_data *client_data); +void ishtp_hid_wakeup(struct hid_device *hid); + +#endif /* ISHTP_HID__H */ diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index c51494119817..e794f7bee22f 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -248,6 +248,7 @@ struct input_mask { #define BUS_SPI 0x1C #define BUS_RMI 0x1D #define BUS_CEC 0x1E +#define BUS_INTEL_ISHTP 0x1F /* * MT_TOOL types -- cgit v1.2.3 From eec097d43100a8195fd4f678671ecd5d986dd675 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Mon, 13 Jun 2016 11:01:51 -0500 Subject: PCI: Add pci_enable_ptm() for drivers to enable PTM on endpoints Add an pci_enable_ptm() interface so drivers can enable PTM. The PCI core enables PTM on PTM Roots and switches automatically, but we don't enable PTM on endpoints unless a driver requests it. Signed-off-by: Bjorn Helgaas --- drivers/pci/pcie/ptm.c | 45 +++++++++++++++++++++++++++++++++++++++++++ include/linux/pci.h | 7 +++++++ include/uapi/linux/pci_regs.h | 1 + 3 files changed, 53 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/pci/pcie/ptm.c b/drivers/pci/pcie/ptm.c index 48eea4e65247..a14ac94b96dc 100644 --- a/drivers/pci/pcie/ptm.c +++ b/drivers/pci/pcie/ptm.c @@ -68,3 +68,48 @@ void pci_ptm_init(struct pci_dev *dev) pci_ptm_info(dev); } + +int pci_enable_ptm(struct pci_dev *dev, u8 *granularity) +{ + int pos; + u32 cap, ctrl; + struct pci_dev *ups; + + if (!pci_is_pcie(dev)) + return -EINVAL; + + pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_PTM); + if (!pos) + return -EINVAL; + + pci_read_config_dword(dev, pos + PCI_PTM_CAP, &cap); + if (!(cap & PCI_PTM_CAP_REQ)) + return -EINVAL; + + /* + * For a PCIe Endpoint, PTM is only useful if the endpoint can + * issue PTM requests to upstream devices that have PTM enabled. + * + * For Root Complex Integrated Endpoints, there is no upstream + * device, so there must be some implementation-specific way to + * associate the endpoint with a time source. + */ + if (pci_pcie_type(dev) == PCI_EXP_TYPE_ENDPOINT) { + ups = pci_upstream_bridge(dev); + if (!ups || !ups->ptm_enabled) + return -EINVAL; + } else if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END) { + } else + return -EINVAL; + + ctrl = PCI_PTM_CTRL_ENABLE; + pci_write_config_dword(dev, pos + PCI_PTM_CTRL, ctrl); + dev->ptm_enabled = 1; + + pci_ptm_info(dev); + + if (granularity) + *granularity = 0; + return 0; +} +EXPORT_SYMBOL(pci_enable_ptm); diff --git a/include/linux/pci.h b/include/linux/pci.h index 96c509fa9d46..9e4b6d6f3c8d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1407,6 +1407,13 @@ static inline void pci_disable_ats(struct pci_dev *d) { } static inline int pci_ats_queue_depth(struct pci_dev *d) { return -ENODEV; } #endif +#ifdef CONFIG_PCIE_PTM +int pci_enable_ptm(struct pci_dev *dev, u8 *granularity); +#else +static inline int pci_enable_ptm(struct pci_dev *dev, u8 *granularity) +{ return -EINVAL; } +#endif + void pci_cfg_access_lock(struct pci_dev *dev); bool pci_cfg_access_trylock(struct pci_dev *dev); void pci_cfg_access_unlock(struct pci_dev *dev); diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 926fff41b417..72bbe1491cbf 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -967,6 +967,7 @@ /* Precision Time Measurement */ #define PCI_PTM_CAP 0x04 /* PTM Capability */ +#define PCI_PTM_CAP_REQ 0x00000001 /* Requester capable */ #define PCI_PTM_CAP_ROOT 0x00000004 /* Root capable */ #define PCI_PTM_CTRL 0x08 /* PTM Control */ #define PCI_PTM_CTRL_ENABLE 0x00000001 /* PTM enable */ -- cgit v1.2.3 From 9399ae9a6cb28ebac78216f715ace3b42f1c2132 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Wed, 17 Aug 2016 13:36:13 +0300 Subject: net_sched: flower: Add vlan support Enhance flower to support 802.1Q vlan protocol classification. Currently, the supported fields are vlan_id and vlan_priority. Example: # add a flower filter with vlan id and priority classification tc filter add dev ens4f0 protocol 802.1Q parent ffff: \ flower \ indev ens4f0 \ vlan_ethtype ipv4 \ vlan_id 100 \ vlan_prio 3 \ action vlan pop Signed-off-by: Hadar Hen Zion Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 3 ++ net/sched/cls_flower.c | 70 ++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 70 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index d1c1ccaba787..51b5b247fb5a 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -428,6 +428,9 @@ enum { TCA_FLOWER_KEY_UDP_DST, /* be16 */ TCA_FLOWER_FLAGS, + TCA_FLOWER_KEY_VLAN_ID, + TCA_FLOWER_KEY_VLAN_PRIO, + TCA_FLOWER_KEY_VLAN_ETH_TYPE, __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 0080fc073019..1e11e57e6947 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -28,6 +28,7 @@ struct fl_flow_key { struct flow_dissector_key_control control; struct flow_dissector_key_basic basic; struct flow_dissector_key_eth_addrs eth; + struct flow_dissector_key_vlan vlan; struct flow_dissector_key_addrs ipaddrs; union { struct flow_dissector_key_ipv4_addrs ipv4; @@ -293,6 +294,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_TCP_DST] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_UDP_SRC] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_UDP_DST] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_VLAN_ID] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_VLAN_PRIO] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_VLAN_ETH_TYPE] = { .type = NLA_U16 }, + }; static void fl_set_key_val(struct nlattr **tb, @@ -308,9 +313,29 @@ static void fl_set_key_val(struct nlattr **tb, memcpy(mask, nla_data(tb[mask_type]), len); } +static void fl_set_key_vlan(struct nlattr **tb, + struct flow_dissector_key_vlan *key_val, + struct flow_dissector_key_vlan *key_mask) +{ +#define VLAN_PRIORITY_MASK 0x7 + + if (tb[TCA_FLOWER_KEY_VLAN_ID]) { + key_val->vlan_id = + nla_get_u16(tb[TCA_FLOWER_KEY_VLAN_ID]) & VLAN_VID_MASK; + key_mask->vlan_id = VLAN_VID_MASK; + } + if (tb[TCA_FLOWER_KEY_VLAN_PRIO]) { + key_val->vlan_priority = + nla_get_u8(tb[TCA_FLOWER_KEY_VLAN_PRIO]) & + VLAN_PRIORITY_MASK; + key_mask->vlan_priority = VLAN_PRIORITY_MASK; + } +} + static int fl_set_key(struct net *net, struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask) { + __be16 ethertype; #ifdef CONFIG_NET_CLS_IND if (tb[TCA_FLOWER_INDEV]) { int err = tcf_change_indev(net, tb[TCA_FLOWER_INDEV]); @@ -328,9 +353,19 @@ static int fl_set_key(struct net *net, struct nlattr **tb, mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK, sizeof(key->eth.src)); - fl_set_key_val(tb, &key->basic.n_proto, TCA_FLOWER_KEY_ETH_TYPE, - &mask->basic.n_proto, TCA_FLOWER_UNSPEC, - sizeof(key->basic.n_proto)); + if (tb[TCA_FLOWER_KEY_ETH_TYPE]) + ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_ETH_TYPE]); + + if (ethertype == htons(ETH_P_8021Q)) { + fl_set_key_vlan(tb, &key->vlan, &mask->vlan); + fl_set_key_val(tb, &key->basic.n_proto, + TCA_FLOWER_KEY_VLAN_ETH_TYPE, + &mask->basic.n_proto, TCA_FLOWER_UNSPEC, + sizeof(key->basic.n_proto)); + } else { + key->basic.n_proto = ethertype; + mask->basic.n_proto = cpu_to_be16(~0); + } if (key->basic.n_proto == htons(ETH_P_IP) || key->basic.n_proto == htons(ETH_P_IPV6)) { @@ -438,6 +473,8 @@ static void fl_init_dissector(struct cls_fl_head *head, FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6); FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, FLOW_DISSECTOR_KEY_PORTS, tp); + FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FLOW_DISSECTOR_KEY_VLAN, vlan); skb_flow_dissector_init(&head->dissector, keys, cnt); } @@ -666,6 +703,29 @@ static int fl_dump_key_val(struct sk_buff *skb, return 0; } +static int fl_dump_key_vlan(struct sk_buff *skb, + struct flow_dissector_key_vlan *vlan_key, + struct flow_dissector_key_vlan *vlan_mask) +{ + int err; + + if (!memchr_inv(vlan_mask, 0, sizeof(*vlan_mask))) + return 0; + if (vlan_mask->vlan_id) { + err = nla_put_u16(skb, TCA_FLOWER_KEY_VLAN_ID, + vlan_key->vlan_id); + if (err) + return err; + } + if (vlan_mask->vlan_priority) { + err = nla_put_u8(skb, TCA_FLOWER_KEY_VLAN_PRIO, + vlan_key->vlan_priority); + if (err) + return err; + } + return 0; +} + static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { @@ -710,6 +770,10 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, &mask->basic.n_proto, TCA_FLOWER_UNSPEC, sizeof(key->basic.n_proto))) goto nla_put_failure; + + if (fl_dump_key_vlan(skb, &key->vlan, &mask->vlan)) + goto nla_put_failure; + if ((key->basic.n_proto == htons(ETH_P_IP) || key->basic.n_proto == htons(ETH_P_IPV6)) && fl_dump_key_val(skb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO, -- cgit v1.2.3 From 956af37102b515512331a03c35c958b2a1d8dd87 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Wed, 17 Aug 2016 13:36:14 +0300 Subject: net_sched: act_vlan: Add priority option The current vlan push action supports only vid and protocol options. Add priority option. Example script that adds vlan push action with vid and priority: tc filter add dev veth0 protocol ip parent ffff: \ flower \ indev veth0 \ action vlan push id 100 priority 5 Signed-off-by: Hadar Hen Zion Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/tc_act/tc_vlan.h | 1 + include/uapi/linux/tc_act/tc_vlan.h | 1 + net/sched/act_vlan.c | 13 +++++++++++-- 3 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h index e29f52e8bdf1..6b835889ea30 100644 --- a/include/net/tc_act/tc_vlan.h +++ b/include/net/tc_act/tc_vlan.h @@ -20,6 +20,7 @@ struct tcf_vlan { int tcfv_action; u16 tcfv_push_vid; __be16 tcfv_push_proto; + u8 tcfv_push_prio; }; #define to_vlan(a) ((struct tcf_vlan *)a) diff --git a/include/uapi/linux/tc_act/tc_vlan.h b/include/uapi/linux/tc_act/tc_vlan.h index 31151ff6264f..be72b6e3843b 100644 --- a/include/uapi/linux/tc_act/tc_vlan.h +++ b/include/uapi/linux/tc_act/tc_vlan.h @@ -29,6 +29,7 @@ enum { TCA_VLAN_PUSH_VLAN_ID, TCA_VLAN_PUSH_VLAN_PROTOCOL, TCA_VLAN_PAD, + TCA_VLAN_PUSH_VLAN_PRIORITY, __TCA_VLAN_MAX, }; #define TCA_VLAN_MAX (__TCA_VLAN_MAX - 1) diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 691409de3e1a..59a8d3150ae2 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -43,7 +43,8 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, goto drop; break; case TCA_VLAN_ACT_PUSH: - err = skb_vlan_push(skb, v->tcfv_push_proto, v->tcfv_push_vid); + err = skb_vlan_push(skb, v->tcfv_push_proto, v->tcfv_push_vid | + (v->tcfv_push_prio << VLAN_PRIO_SHIFT)); if (err) goto drop; break; @@ -65,6 +66,7 @@ static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = { [TCA_VLAN_PARMS] = { .len = sizeof(struct tc_vlan) }, [TCA_VLAN_PUSH_VLAN_ID] = { .type = NLA_U16 }, [TCA_VLAN_PUSH_VLAN_PROTOCOL] = { .type = NLA_U16 }, + [TCA_VLAN_PUSH_VLAN_PRIORITY] = { .type = NLA_U8 }, }; static int tcf_vlan_init(struct net *net, struct nlattr *nla, @@ -78,6 +80,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, int action; __be16 push_vid = 0; __be16 push_proto = 0; + u8 push_prio = 0; bool exists = false; int ret = 0, err; @@ -123,6 +126,9 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, } else { push_proto = htons(ETH_P_8021Q); } + + if (tb[TCA_VLAN_PUSH_VLAN_PRIORITY]) + push_prio = nla_get_u8(tb[TCA_VLAN_PUSH_VLAN_PRIORITY]); break; default: if (exists) @@ -150,6 +156,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, v->tcfv_action = action; v->tcfv_push_vid = push_vid; + v->tcfv_push_prio = push_prio; v->tcfv_push_proto = push_proto; v->tcf_action = parm->action; @@ -181,7 +188,9 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, if (v->tcfv_action == TCA_VLAN_ACT_PUSH && (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, v->tcfv_push_vid) || nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL, - v->tcfv_push_proto))) + v->tcfv_push_proto) || + (nla_put_u8(skb, TCA_VLAN_PUSH_VLAN_PRIORITY, + v->tcfv_push_prio)))) goto nla_put_failure; tcf_tm_dump(&t, &v->tcf_tm); -- cgit v1.2.3 From 61ba1a2da9693b88bf5f2bb8e7a99a29cd139122 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 17 Aug 2016 12:53:10 +0200 Subject: net: bridge: export vlan flags with the stats Use one of the vlan xstats padding fields to export the vlan flags. This is needed in order to be able to distinguish between master (bridge) and port vlan entries in user-space when dumping the bridge vlan stats. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 2 +- net/bridge/br_netlink.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index c186f64fffca..ab92bca6d448 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -140,7 +140,7 @@ struct bridge_vlan_xstats { __u64 tx_bytes; __u64 tx_packets; __u16 vid; - __u16 pad1; + __u16 flags; __u32 pad2; }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 493ab9b3d51a..872d4c0deb59 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1321,6 +1321,7 @@ static int br_fill_linkxstats(struct sk_buff *skb, continue; memset(&vxi, 0, sizeof(vxi)); vxi.vid = v->vid; + vxi.flags = v->flags; br_vlan_get_stats(v, &stats); vxi.rx_bytes = stats.rx_bytes; vxi.rx_packets = stats.rx_packets; -- cgit v1.2.3 From b34040227be7da760cc72ef3c807e0985e7f0f16 Mon Sep 17 00:00:00 2001 From: Richard Alpe Date: Thu, 18 Aug 2016 10:33:52 +0200 Subject: tipc: add peer removal functionality Add TIPC_NL_PEER_REMOVE netlink command. This command can remove an offline peer node from the internal data structures. This will be supported by the tipc user space tool in iproute2. Signed-off-by: Richard Alpe Reviewed-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- include/uapi/linux/tipc_netlink.h | 1 + net/tipc/net.h | 2 ++ net/tipc/netlink.c | 5 ++++ net/tipc/node.c | 63 +++++++++++++++++++++++++++++++++++++++ net/tipc/node.h | 1 + 5 files changed, 72 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h index 5f3f6d09fb79..bcb65ef725f6 100644 --- a/include/uapi/linux/tipc_netlink.h +++ b/include/uapi/linux/tipc_netlink.h @@ -59,6 +59,7 @@ enum { TIPC_NL_MON_SET, TIPC_NL_MON_GET, TIPC_NL_MON_PEER_GET, + TIPC_NL_PEER_REMOVE, __TIPC_NL_CMD_MAX, TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1 diff --git a/net/tipc/net.h b/net/tipc/net.h index 77a7a118911d..c7c254902873 100644 --- a/net/tipc/net.h +++ b/net/tipc/net.h @@ -39,6 +39,8 @@ #include +extern const struct nla_policy tipc_nl_net_policy[]; + int tipc_net_start(struct net *net, u32 addr); void tipc_net_stop(struct net *net); diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index a84daec0afe9..2718de667828 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -238,6 +238,11 @@ static const struct genl_ops tipc_genl_v2_ops[] = { .dumpit = tipc_nl_node_dump_monitor_peer, .policy = tipc_nl_policy, }, + { + .cmd = TIPC_NL_PEER_REMOVE, + .doit = tipc_nl_peer_rm, + .policy = tipc_nl_policy, + } }; int tipc_nlmsg_parse(const struct nlmsghdr *nlh, struct nlattr ***attr) diff --git a/net/tipc/node.c b/net/tipc/node.c index 21974191e425..7e8b75fd1a02 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1553,6 +1553,69 @@ discard: kfree_skb(skb); } +int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = sock_net(skb->sk); + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct nlattr *attrs[TIPC_NLA_NET_MAX + 1]; + struct tipc_node *peer; + u32 addr; + int err; + int i; + + /* We identify the peer by its net */ + if (!info->attrs[TIPC_NLA_NET]) + return -EINVAL; + + err = nla_parse_nested(attrs, TIPC_NLA_NET_MAX, + info->attrs[TIPC_NLA_NET], + tipc_nl_net_policy); + if (err) + return err; + + if (!attrs[TIPC_NLA_NET_ADDR]) + return -EINVAL; + + addr = nla_get_u32(attrs[TIPC_NLA_NET_ADDR]); + + if (in_own_node(net, addr)) + return -ENOTSUPP; + + spin_lock_bh(&tn->node_list_lock); + peer = tipc_node_find(net, addr); + if (!peer) { + spin_unlock_bh(&tn->node_list_lock); + return -ENXIO; + } + + tipc_node_write_lock(peer); + if (peer->state != SELF_DOWN_PEER_DOWN && + peer->state != SELF_DOWN_PEER_LEAVING) { + tipc_node_write_unlock(peer); + err = -EBUSY; + goto err_out; + } + + for (i = 0; i < MAX_BEARERS; i++) { + struct tipc_link_entry *le = &peer->links[i]; + + if (le->link) { + kfree(le->link); + le->link = NULL; + peer->link_cnt--; + } + } + tipc_node_write_unlock(peer); + tipc_node_delete(peer); + + err = 0; +err_out: + tipc_node_put(peer); + spin_unlock_bh(&tn->node_list_lock); + + return err; +} + int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb) { int err; diff --git a/net/tipc/node.h b/net/tipc/node.h index d69fdfcc0ec9..4578b34c7dca 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -77,6 +77,7 @@ int tipc_nl_node_dump_link(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_node_reset_link_stats(struct sk_buff *skb, struct genl_info *info); int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info); int tipc_nl_node_set_link(struct sk_buff *skb, struct genl_info *info); +int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info); int tipc_nl_node_set_monitor(struct sk_buff *skb, struct genl_info *info); int tipc_nl_node_get_monitor(struct sk_buff *skb, struct genl_info *info); -- cgit v1.2.3 From 5293efe62df81908f2e90c9820c7edcc8e61f5e9 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 18 Aug 2016 01:00:39 +0200 Subject: bpf: add bpf_skb_change_tail helper This work adds a bpf_skb_change_tail() helper for tc BPF programs. The basic idea is to expand or shrink the skb in a controlled manner. The eBPF program can then rewrite the rest via helpers like bpf_skb_store_bytes(), bpf_lX_csum_replace() and others rather than passing a raw buffer for writing here. bpf_skb_change_tail() is really a slow path helper and intended for replies with f.e. ICMP control messages. Concept is similar to other helpers like bpf_skb_change_proto() helper to keep the helper without protocol specifics and let the BPF program mangle the remaining parts. A flags field has been added and is reserved for now should we extend the helper in future. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/skbuff.h | 43 +++++++++++++++++++- include/uapi/linux/bpf.h | 11 ++++++ net/core/filter.c | 100 +++++++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 150 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0f665cb26b50..7047448e8129 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2295,7 +2295,7 @@ static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len) int ___pskb_trim(struct sk_buff *skb, unsigned int len); -static inline void __skb_trim(struct sk_buff *skb, unsigned int len) +static inline void __skb_set_length(struct sk_buff *skb, unsigned int len) { if (unlikely(skb_is_nonlinear(skb))) { WARN_ON(1); @@ -2305,6 +2305,11 @@ static inline void __skb_trim(struct sk_buff *skb, unsigned int len) skb_set_tail_pointer(skb, len); } +static inline void __skb_trim(struct sk_buff *skb, unsigned int len) +{ + __skb_set_length(skb, len); +} + void skb_trim(struct sk_buff *skb, unsigned int len); static inline int __pskb_trim(struct sk_buff *skb, unsigned int len) @@ -2335,6 +2340,20 @@ static inline void pskb_trim_unique(struct sk_buff *skb, unsigned int len) BUG_ON(err); } +static inline int __skb_grow(struct sk_buff *skb, unsigned int len) +{ + unsigned int diff = len - skb->len; + + if (skb_tailroom(skb) < diff) { + int ret = pskb_expand_head(skb, 0, diff - skb_tailroom(skb), + GFP_ATOMIC); + if (ret) + return ret; + } + __skb_set_length(skb, len); + return 0; +} + /** * skb_orphan - orphan a buffer * @skb: buffer to orphan @@ -2938,6 +2957,21 @@ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) return __pskb_trim(skb, len); } +static inline int __skb_trim_rcsum(struct sk_buff *skb, unsigned int len) +{ + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->ip_summed = CHECKSUM_NONE; + __skb_trim(skb, len); + return 0; +} + +static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len) +{ + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->ip_summed = CHECKSUM_NONE; + return __skb_grow(skb, len); +} + #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ skb != (struct sk_buff *)(queue); \ @@ -3726,6 +3760,13 @@ static inline bool skb_is_gso_v6(const struct sk_buff *skb) return skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6; } +static inline void skb_gso_reset(struct sk_buff *skb) +{ + skb_shinfo(skb)->gso_size = 0; + skb_shinfo(skb)->gso_segs = 0; + skb_shinfo(skb)->gso_type = 0; +} + void __skb_warn_lro_forwarding(const struct sk_buff *skb); static inline bool skb_warn_if_lro(const struct sk_buff *skb) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 866d53c33298..e4c5a1baa993 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -386,6 +386,17 @@ enum bpf_func_id { */ 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_FUNC_MAX_ID, }; diff --git a/net/core/filter.c b/net/core/filter.c index 58b5e6dd25fe..abf546d96b6b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1350,14 +1350,18 @@ struct bpf_scratchpad { static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp); +static inline int __bpf_try_make_writable(struct sk_buff *skb, + unsigned int write_len) +{ + return skb_ensure_writable(skb, write_len); +} + static inline int bpf_try_make_writable(struct sk_buff *skb, unsigned int write_len) { - int err; + int err = __bpf_try_make_writable(skb, write_len); - err = skb_ensure_writable(skb, write_len); bpf_compute_data_end(skb); - return err; } @@ -1992,6 +1996,92 @@ static const struct bpf_func_proto bpf_skb_change_type_proto = { .arg2_type = ARG_ANYTHING, }; +static u32 __bpf_skb_min_len(const struct sk_buff *skb) +{ + u32 min_len = skb_network_offset(skb); + + if (skb_transport_header_was_set(skb)) + min_len = skb_transport_offset(skb); + if (skb->ip_summed == CHECKSUM_PARTIAL) + min_len = skb_checksum_start_offset(skb) + + skb->csum_offset + sizeof(__sum16); + return min_len; +} + +static u32 __bpf_skb_max_len(const struct sk_buff *skb) +{ + return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len : + 65536; +} + +static int bpf_skb_grow_rcsum(struct sk_buff *skb, unsigned int new_len) +{ + unsigned int old_len = skb->len; + int ret; + + ret = __skb_grow_rcsum(skb, new_len); + if (!ret) + memset(skb->data + old_len, 0, new_len - old_len); + return ret; +} + +static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len) +{ + return __skb_trim_rcsum(skb, new_len); +} + +static u64 bpf_skb_change_tail(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *)(long) r1; + u32 max_len = __bpf_skb_max_len(skb); + u32 min_len = __bpf_skb_min_len(skb); + u32 new_len = (u32) r2; + int ret; + + if (unlikely(flags || new_len > max_len || new_len < min_len)) + return -EINVAL; + if (skb->encapsulation) + return -ENOTSUPP; + + /* The basic idea of this helper is that it's performing the + * needed work to either grow or trim an skb, and eBPF program + * rewrites the rest via helpers like bpf_skb_store_bytes(), + * bpf_lX_csum_replace() and others rather than passing a raw + * buffer here. This one is a slow path helper and intended + * for replies with control messages. + * + * Like in bpf_skb_change_proto(), we want to keep this rather + * minimal and without protocol specifics so that we are able + * to separate concerns as in bpf_skb_store_bytes() should only + * be the one responsible for writing buffers. + * + * It's really expected to be a slow path operation here for + * control message replies, so we're implicitly linearizing, + * uncloning and drop offloads from the skb by this. + */ + ret = __bpf_try_make_writable(skb, skb->len); + if (!ret) { + if (new_len > skb->len) + ret = bpf_skb_grow_rcsum(skb, new_len); + else if (new_len < skb->len) + ret = bpf_skb_trim_rcsum(skb, new_len); + if (!ret && skb_is_gso(skb)) + skb_gso_reset(skb); + } + + bpf_compute_data_end(skb); + return ret; +} + +static const struct bpf_func_proto bpf_skb_change_tail_proto = { + .func = bpf_skb_change_tail, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + bool bpf_helper_changes_skb_data(void *func) { if (func == bpf_skb_vlan_push) @@ -2002,6 +2092,8 @@ bool bpf_helper_changes_skb_data(void *func) return true; if (func == bpf_skb_change_proto) return true; + if (func == bpf_skb_change_tail) + return true; if (func == bpf_l3_csum_replace) return true; if (func == bpf_l4_csum_replace) @@ -2368,6 +2460,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_skb_change_proto_proto; case BPF_FUNC_skb_change_type: return &bpf_skb_change_type_proto; + case BPF_FUNC_skb_change_tail: + return &bpf_skb_change_tail_proto; case BPF_FUNC_skb_get_tunnel_key: return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: -- cgit v1.2.3 From 3d2f30a1df907e3ef4175121f0d21456630a72aa Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 18 Aug 2016 01:46:06 +0200 Subject: netfilter: nf_tables: add quota expression This patch adds the quota expression. This new stateful expression integrate easily into the dynset expression to build 'hashquota' flow tables. Arguably, we could use instead "counter bytes > 1000" instead, but this approach has several problems: 1) We only support for one single stateful expression in dynamic set definitions, and the expression above is a composite of two expressions: get counter + comparison. 2) We would need to restore the packed counter representation (that we used to have) based on seqlock to synchronize this, since per-cpu is not suitable for this. So instead of bloating the counter expression back with the seqlock representation and extending the existing set infrastructure to make it more complex for the composite described above, let's follow the more simple approach of adding a quota expression that we can plug into our existing infrastructure. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 19 +++++ net/netfilter/Kconfig | 6 ++ net/netfilter/Makefile | 1 + net/netfilter/nft_quota.c | 121 +++++++++++++++++++++++++++++++ 4 files changed, 147 insertions(+) create mode 100644 net/netfilter/nft_quota.c (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 6ce0a6dd0889..784fbf15ab3d 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -900,6 +900,25 @@ enum nft_queue_attributes { #define NFT_QUEUE_FLAG_CPU_FANOUT 0x02 /* use current CPU (no hashing) */ #define NFT_QUEUE_FLAG_MASK 0x03 +enum nft_quota_flags { + NFT_QUOTA_F_INV = (1 << 0), +}; + +/** + * enum nft_quota_attributes - nf_tables quota expression netlink attributes + * + * @NFTA_QUOTA_BYTES: quota in bytes (NLA_U16) + * @NFTA_QUOTA_FLAGS: flags (NLA_U32) + */ +enum nft_quota_attributes { + NFTA_QUOTA_UNSPEC, + NFTA_QUOTA_BYTES, + NFTA_QUOTA_FLAGS, + NFTA_QUOTA_PAD, + __NFTA_QUOTA_MAX +}; +#define NFTA_QUOTA_MAX (__NFTA_QUOTA_MAX - 1) + /** * enum nft_reject_types - nf_tables reject expression reject types * diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 9cfaa00c79b2..29a8078deafa 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -542,6 +542,12 @@ config NFT_QUEUE This is required if you intend to use the userspace queueing infrastructure (also known as NFQUEUE) from nftables. +config NFT_QUOTA + tristate "Netfilter nf_tables quota module" + help + This option adds the "quota" expression that you can use to match + enforce bytes quotas. + config NFT_REJECT default m if NETFILTER_ADVANCED=n tristate "Netfilter nf_tables reject support" diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 1106ccde215c..0fc42df19b8c 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -84,6 +84,7 @@ obj-$(CONFIG_NFT_CT) += nft_ct.o obj-$(CONFIG_NFT_LIMIT) += nft_limit.o obj-$(CONFIG_NFT_NAT) += nft_nat.o obj-$(CONFIG_NFT_QUEUE) += nft_queue.o +obj-$(CONFIG_NFT_QUOTA) += nft_quota.o obj-$(CONFIG_NFT_REJECT) += nft_reject.o obj-$(CONFIG_NFT_REJECT_INET) += nft_reject_inet.o obj-$(CONFIG_NFT_SET_RBTREE) += nft_set_rbtree.o diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c new file mode 100644 index 000000000000..6eafbf987ed9 --- /dev/null +++ b/net/netfilter/nft_quota.c @@ -0,0 +1,121 @@ +/* + * Copyright (c) 2016 Pablo Neira Ayuso + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +struct nft_quota { + u64 quota; + bool invert; + atomic64_t remain; +}; + +static inline long nft_quota(struct nft_quota *priv, + const struct nft_pktinfo *pkt) +{ + return atomic64_sub_return(pkt->skb->len, &priv->remain); +} + +static void nft_quota_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_quota *priv = nft_expr_priv(expr); + + if (nft_quota(priv, pkt) < 0 && !priv->invert) + regs->verdict.code = NFT_BREAK; +} + +static const struct nla_policy nft_quota_policy[NFTA_QUOTA_MAX + 1] = { + [NFTA_QUOTA_BYTES] = { .type = NLA_U64 }, + [NFTA_QUOTA_FLAGS] = { .type = NLA_U32 }, +}; + +static int nft_quota_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_quota *priv = nft_expr_priv(expr); + u32 flags = 0; + u64 quota; + + if (!tb[NFTA_QUOTA_BYTES]) + return -EINVAL; + + quota = be64_to_cpu(nla_get_be64(tb[NFTA_QUOTA_BYTES])); + if (quota > S64_MAX) + return -EOVERFLOW; + + if (tb[NFTA_QUOTA_FLAGS]) { + flags = ntohl(nla_get_be32(tb[NFTA_QUOTA_FLAGS])); + if (flags & ~NFT_QUOTA_F_INV) + return -EINVAL; + } + + priv->quota = quota; + priv->invert = (flags & NFT_QUOTA_F_INV) ? true : false; + atomic64_set(&priv->remain, quota); + + return 0; +} + +static int nft_quota_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_quota *priv = nft_expr_priv(expr); + u32 flags = priv->invert ? NFT_QUOTA_F_INV : 0; + + if (nla_put_be64(skb, NFTA_QUOTA_BYTES, cpu_to_be64(priv->quota), + NFTA_QUOTA_PAD) || + nla_put_be32(skb, NFTA_QUOTA_FLAGS, htonl(flags))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static struct nft_expr_type nft_quota_type; +static const struct nft_expr_ops nft_quota_ops = { + .type = &nft_quota_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_quota)), + .eval = nft_quota_eval, + .init = nft_quota_init, + .dump = nft_quota_dump, +}; + +static struct nft_expr_type nft_quota_type __read_mostly = { + .name = "quota", + .ops = &nft_quota_ops, + .policy = nft_quota_policy, + .maxattr = NFTA_QUOTA_MAX, + .flags = NFT_EXPR_STATEFUL, + .owner = THIS_MODULE, +}; + +static int __init nft_quota_module_init(void) +{ + return nft_register_expr(&nft_quota_type); +} + +static void __exit nft_quota_module_exit(void) +{ + nft_unregister_expr(&nft_quota_type); +} + +module_init(nft_quota_module_init); +module_exit(nft_quota_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso "); +MODULE_ALIAS_NFT_EXPR("quota"); -- cgit v1.2.3 From 91dbc6be0a62d3bcea98287734d593610aed507d Mon Sep 17 00:00:00 2001 From: Laura Garcia Liebana Date: Thu, 18 Aug 2016 12:13:13 +0200 Subject: netfilter: nf_tables: add number generator expression This patch adds the numgen expression that allows us to generated incremental and random numbers, this generator is bound to a upper limit that is specified by userspace. This expression is useful to distribute packets in a round-robin fashion as well as randomly. Signed-off-by: Laura Garcia Liebana Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 24 ++++ net/netfilter/Kconfig | 6 + net/netfilter/Makefile | 1 + net/netfilter/nft_numgen.c | 192 +++++++++++++++++++++++++++++++ 4 files changed, 223 insertions(+) create mode 100644 net/netfilter/nft_numgen.c (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 784fbf15ab3d..8c9d6ff70ec0 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1121,4 +1121,28 @@ enum nft_trace_types { __NFT_TRACETYPE_MAX }; #define NFT_TRACETYPE_MAX (__NFT_TRACETYPE_MAX - 1) + +/** + * enum nft_ng_attributes - nf_tables number generator expression netlink attributes + * + * @NFTA_NG_DREG: destination register (NLA_U32) + * @NFTA_NG_UNTIL: source value to increment the counter until reset (NLA_U32) + * @NFTA_NG_TYPE: operation type (NLA_U32) + */ +enum nft_ng_attributes { + NFTA_NG_UNSPEC, + NFTA_NG_DREG, + NFTA_NG_UNTIL, + NFTA_NG_TYPE, + __NFTA_NG_MAX +}; +#define NFTA_NG_MAX (__NFTA_NG_MAX - 1) + +enum nft_ng_types { + NFT_NG_INCREMENTAL, + NFT_NG_RANDOM, + __NFT_NG_MAX +}; +#define NFT_NG_MAX (__NFT_NG_MAX - 1) + #endif /* _LINUX_NF_TABLES_H */ diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 29a8078deafa..e8d56d9a4df2 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -474,6 +474,12 @@ config NFT_META This option adds the "meta" expression that you can use to match and to set packet metainformation such as the packet mark. +config NFT_NUMGEN + tristate "Netfilter nf_tables number generator module" + help + This option adds the number generator expression used to perform + incremental counting and random numbers bound to a upper limit. + config NFT_CT depends on NF_CONNTRACK tristate "Netfilter nf_tables conntrack module" diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 0fc42df19b8c..0c8581100ac6 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -80,6 +80,7 @@ obj-$(CONFIG_NF_TABLES_NETDEV) += nf_tables_netdev.o obj-$(CONFIG_NFT_COMPAT) += nft_compat.o obj-$(CONFIG_NFT_EXTHDR) += nft_exthdr.o obj-$(CONFIG_NFT_META) += nft_meta.o +obj-$(CONFIG_NFT_NUMGEN) += nft_numgen.o obj-$(CONFIG_NFT_CT) += nft_ct.o obj-$(CONFIG_NFT_LIMIT) += nft_limit.o obj-$(CONFIG_NFT_NAT) += nft_nat.o diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c new file mode 100644 index 000000000000..176e26d5bbd0 --- /dev/null +++ b/net/netfilter/nft_numgen.c @@ -0,0 +1,192 @@ +/* + * Copyright (c) 2016 Laura Garcia + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static DEFINE_PER_CPU(struct rnd_state, nft_numgen_prandom_state); + +struct nft_ng_inc { + enum nft_registers dreg:8; + u32 until; + atomic_t counter; +}; + +static void nft_ng_inc_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_ng_inc *priv = nft_expr_priv(expr); + u32 nval, oval; + + do { + oval = atomic_read(&priv->counter); + nval = (oval + 1 < priv->until) ? oval + 1 : 0; + } while (atomic_cmpxchg(&priv->counter, oval, nval) != oval); + + memcpy(®s->data[priv->dreg], &priv->counter, sizeof(u32)); +} + +static const struct nla_policy nft_ng_policy[NFTA_NG_MAX + 1] = { + [NFTA_NG_DREG] = { .type = NLA_U32 }, + [NFTA_NG_UNTIL] = { .type = NLA_U32 }, + [NFTA_NG_TYPE] = { .type = NLA_U32 }, +}; + +static int nft_ng_inc_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_ng_inc *priv = nft_expr_priv(expr); + + priv->until = ntohl(nla_get_be32(tb[NFTA_NG_UNTIL])); + if (priv->until == 0) + return -ERANGE; + + priv->dreg = nft_parse_register(tb[NFTA_NG_DREG]); + atomic_set(&priv->counter, 0); + + return nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, sizeof(u32)); +} + +static int nft_ng_dump(struct sk_buff *skb, enum nft_registers dreg, + u32 until, enum nft_ng_types type) +{ + if (nft_dump_register(skb, NFTA_NG_DREG, dreg)) + goto nla_put_failure; + if (nft_dump_register(skb, NFTA_NG_UNTIL, until)) + goto nla_put_failure; + if (nft_dump_register(skb, NFTA_NG_TYPE, type)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static int nft_ng_inc_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_ng_inc *priv = nft_expr_priv(expr); + + return nft_ng_dump(skb, priv->dreg, priv->until, NFT_NG_INCREMENTAL); +} + +struct nft_ng_random { + enum nft_registers dreg:8; + u32 until; +}; + +static void nft_ng_random_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_ng_random *priv = nft_expr_priv(expr); + struct rnd_state *state = this_cpu_ptr(&nft_numgen_prandom_state); + + regs->data[priv->dreg] = reciprocal_scale(prandom_u32_state(state), + priv->until); +} + +static int nft_ng_random_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_ng_random *priv = nft_expr_priv(expr); + + priv->until = ntohl(nla_get_be32(tb[NFTA_NG_UNTIL])); + if (priv->until == 0) + return -ERANGE; + + prandom_init_once(&nft_numgen_prandom_state); + + priv->dreg = nft_parse_register(tb[NFTA_NG_DREG]); + + return nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, sizeof(u32)); +} + +static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_ng_random *priv = nft_expr_priv(expr); + + return nft_ng_dump(skb, priv->dreg, priv->until, NFT_NG_RANDOM); +} + +static struct nft_expr_type nft_ng_type; +static const struct nft_expr_ops nft_ng_inc_ops = { + .type = &nft_ng_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_inc)), + .eval = nft_ng_inc_eval, + .init = nft_ng_inc_init, + .dump = nft_ng_inc_dump, +}; + +static const struct nft_expr_ops nft_ng_random_ops = { + .type = &nft_ng_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_random)), + .eval = nft_ng_random_eval, + .init = nft_ng_random_init, + .dump = nft_ng_random_dump, +}; + +static const struct nft_expr_ops * +nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) +{ + u32 type; + + if (!tb[NFTA_NG_DREG] || + !tb[NFTA_NG_UNTIL] || + !tb[NFTA_NG_TYPE]) + return ERR_PTR(-EINVAL); + + type = ntohl(nla_get_be32(tb[NFTA_NG_TYPE])); + + switch (type) { + case NFT_NG_INCREMENTAL: + return &nft_ng_inc_ops; + case NFT_NG_RANDOM: + return &nft_ng_random_ops; + } + + return ERR_PTR(-EINVAL); +} + +static struct nft_expr_type nft_ng_type __read_mostly = { + .name = "numgen", + .select_ops = &nft_ng_select_ops, + .policy = nft_ng_policy, + .maxattr = NFTA_NG_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_ng_module_init(void) +{ + return nft_register_expr(&nft_ng_type); +} + +static void __exit nft_ng_module_exit(void) +{ + nft_unregister_expr(&nft_ng_type); +} + +module_init(nft_ng_module_init); +module_exit(nft_ng_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Laura Garcia "); +MODULE_ALIAS_NFT_EXPR("numgen"); -- cgit v1.2.3 From 7ac5d7b1a1254ceb4be19ba93ef7a6ee4e7ac382 Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Mon, 22 Aug 2016 20:32:22 +0200 Subject: HSI: hsi_char.h: use __u32 from linux/types.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes userspace compiler errors like: linux/hsi/hsi_char.h:51:2: error: unknown type name ‘uint32_t’ Signed-off-by: Mikko Rapeli Signed-off-by: Sebastian Reichel --- include/uapi/linux/hsi/hsi_char.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/hsi/hsi_char.h b/include/uapi/linux/hsi/hsi_char.h index 76160b4f455d..c00a463d55f9 100644 --- a/include/uapi/linux/hsi/hsi_char.h +++ b/include/uapi/linux/hsi/hsi_char.h @@ -20,10 +20,11 @@ * 02110-1301 USA */ - #ifndef __HSI_CHAR_H #define __HSI_CHAR_H +#include + #define HSI_CHAR_MAGIC 'k' #define HSC_IOW(num, dtype) _IOW(HSI_CHAR_MAGIC, num, dtype) #define HSC_IOR(num, dtype) _IOR(HSI_CHAR_MAGIC, num, dtype) @@ -48,16 +49,16 @@ #define HSC_ARB_PRIO 1 struct hsc_rx_config { - uint32_t mode; - uint32_t flow; - uint32_t channels; + __u32 mode; + __u32 flow; + __u32 channels; }; struct hsc_tx_config { - uint32_t mode; - uint32_t channels; - uint32_t speed; - uint32_t arb_mode; + __u32 mode; + __u32 channels; + __u32 speed; + __u32 arb_mode; }; #endif /* __HSI_CHAR_H */ -- cgit v1.2.3 From b43f95695124baba9f7c48e247fc8fd212a984d9 Mon Sep 17 00:00:00 2001 From: Pablo Neira Date: Mon, 22 Aug 2016 11:37:36 +0200 Subject: netfilter: nf_tables: typo in trace attribute definition Should be attributes, instead of attibutes, for consistency with other definitions. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 8c9d6ff70ec0..8a63f22b365d 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1090,7 +1090,7 @@ enum nft_gen_attributes { * @NFTA_TRACE_NFPROTO: nf protocol processed (NLA_U32) * @NFTA_TRACE_POLICY: policy that decided fate of packet (NLA_U32) */ -enum nft_trace_attibutes { +enum nft_trace_attributes { NFTA_TRACE_UNSPEC, NFTA_TRACE_TABLE, NFTA_TRACE_CHAIN, -- cgit v1.2.3 From 3bc52c45bac26bf7ed1dc8d287ad1aeaed1250b6 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sun, 24 Jul 2016 21:55:45 -0700 Subject: dax: define a unified inode/address_space for device-dax mappings In support of enabling resize / truncate of device-dax instances, define a pseudo-fs to provide a unified inode/address space for vm operations. Cc: Al Viro Signed-off-by: Dan Williams --- drivers/dax/dax.c | 150 +++++++++++++++++++++++++++++++++++++++++++-- fs/char_dev.c | 1 + include/uapi/linux/magic.h | 1 + 3 files changed, 148 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c index 17715773c097..e8b9319aeadb 100644 --- a/drivers/dax/dax.c +++ b/drivers/dax/dax.c @@ -13,7 +13,9 @@ #include #include #include +#include #include +#include #include #include #include @@ -26,6 +28,9 @@ static struct class *dax_class; static DEFINE_IDA(dax_minor_ida); static int nr_dax = CONFIG_NR_DEV_DAX; module_param(nr_dax, int, S_IRUGO); +static struct vfsmount *dax_mnt; +static struct kmem_cache *dax_cache __read_mostly; +static struct super_block *dax_superblock __read_mostly; MODULE_PARM_DESC(nr_dax, "max number of device-dax instances"); /** @@ -61,6 +66,7 @@ struct dax_region { */ struct dax_dev { struct dax_region *region; + struct inode *inode; struct device dev; struct cdev cdev; bool alive; @@ -69,6 +75,117 @@ struct dax_dev { struct resource res[0]; }; +static struct inode *dax_alloc_inode(struct super_block *sb) +{ + return kmem_cache_alloc(dax_cache, GFP_KERNEL); +} + +static void dax_i_callback(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + + kmem_cache_free(dax_cache, inode); +} + +static void dax_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, dax_i_callback); +} + +static const struct super_operations dax_sops = { + .statfs = simple_statfs, + .alloc_inode = dax_alloc_inode, + .destroy_inode = dax_destroy_inode, + .drop_inode = generic_delete_inode, +}; + +static struct dentry *dax_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) +{ + return mount_pseudo(fs_type, "dax:", &dax_sops, NULL, DAXFS_MAGIC); +} + +static struct file_system_type dax_type = { + .name = "dax", + .mount = dax_mount, + .kill_sb = kill_anon_super, +}; + +static int dax_test(struct inode *inode, void *data) +{ + return inode->i_cdev == data; +} + +static int dax_set(struct inode *inode, void *data) +{ + inode->i_cdev = data; + return 0; +} + +static struct inode *dax_inode_get(struct cdev *cdev, dev_t devt) +{ + struct inode *inode; + + inode = iget5_locked(dax_superblock, hash_32(devt + DAXFS_MAGIC, 31), + dax_test, dax_set, cdev); + + if (!inode) + return NULL; + + if (inode->i_state & I_NEW) { + inode->i_mode = S_IFCHR; + inode->i_flags = S_DAX; + inode->i_rdev = devt; + mapping_set_gfp_mask(&inode->i_data, GFP_USER); + unlock_new_inode(inode); + } + return inode; +} + +static void init_once(void *inode) +{ + inode_init_once(inode); +} + +static int dax_inode_init(void) +{ + int rc; + + dax_cache = kmem_cache_create("dax_cache", sizeof(struct inode), 0, + (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| + SLAB_MEM_SPREAD|SLAB_ACCOUNT), + init_once); + if (!dax_cache) + return -ENOMEM; + + rc = register_filesystem(&dax_type); + if (rc) + goto err_register_fs; + + dax_mnt = kern_mount(&dax_type); + if (IS_ERR(dax_mnt)) { + rc = PTR_ERR(dax_mnt); + goto err_mount; + } + dax_superblock = dax_mnt->mnt_sb; + + return 0; + + err_mount: + unregister_filesystem(&dax_type); + err_register_fs: + kmem_cache_destroy(dax_cache); + + return rc; +} + +static void dax_inode_exit(void) +{ + kern_unmount(dax_mnt); + unregister_filesystem(&dax_type); + kmem_cache_destroy(dax_cache); +} + static void dax_region_free(struct kref *kref) { struct dax_region *dax_region; @@ -379,6 +496,9 @@ static int dax_open(struct inode *inode, struct file *filp) dax_dev = container_of(inode->i_cdev, struct dax_dev, cdev); dev_dbg(&dax_dev->dev, "%s\n", __func__); + inode->i_mapping = dax_dev->inode->i_mapping; + inode->i_mapping->host = dax_dev->inode; + filp->f_mapping = inode->i_mapping; filp->private_data = dax_dev; inode->i_flags = S_DAX; @@ -410,6 +530,7 @@ static void dax_dev_release(struct device *dev) ida_simple_remove(&dax_region->ida, dax_dev->id); ida_simple_remove(&dax_minor_ida, MINOR(dev->devt)); dax_region_put(dax_region); + iput(dax_dev->inode); kfree(dax_dev); } @@ -459,6 +580,12 @@ int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res, goto err_minor; } + dax_dev->inode = dax_inode_get(&dax_dev->cdev, dev_t); + if (!dax_dev->inode) { + rc = -ENOMEM; + goto err_inode; + } + /* device_initialize() so cdev can reference kobj parent */ dev_t = MKDEV(MAJOR(dax_devt), minor); dev = &dax_dev->dev; @@ -494,6 +621,8 @@ int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res, return devm_add_action_or_reset(dax_region->dev, unregister_dax_dev, dev); err_cdev: + iput(dax_dev->inode); + err_inode: ida_simple_remove(&dax_minor_ida, minor); err_minor: ida_simple_remove(&dax_region->ida, dax_dev->id); @@ -508,16 +637,28 @@ static int __init dax_init(void) { int rc; + rc = dax_inode_init(); + if (rc) + return rc; + nr_dax = max(nr_dax, 256); rc = alloc_chrdev_region(&dax_devt, 0, nr_dax, "dax"); if (rc) - return rc; + goto err_chrdev; dax_class = class_create(THIS_MODULE, "dax"); - if (IS_ERR(dax_class)) - unregister_chrdev_region(dax_devt, nr_dax); + if (IS_ERR(dax_class)) { + rc = PTR_ERR(dax_class); + goto err_class; + } - return PTR_ERR_OR_ZERO(dax_class); + return 0; + + err_class: + unregister_chrdev_region(dax_devt, nr_dax); + err_chrdev: + dax_inode_exit(); + return rc; } static void __exit dax_exit(void) @@ -525,6 +666,7 @@ static void __exit dax_exit(void) class_destroy(dax_class); unregister_chrdev_region(dax_devt, nr_dax); ida_destroy(&dax_minor_ida); + dax_inode_exit(); } MODULE_AUTHOR("Intel Corporation"); diff --git a/fs/char_dev.c b/fs/char_dev.c index 6edd825231c5..44a240c4bb65 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -406,6 +406,7 @@ void cd_forget(struct inode *inode) spin_lock(&cdev_lock); list_del_init(&inode->i_devices); inode->i_cdev = NULL; + inode->i_mapping = &inode->i_data; spin_unlock(&cdev_lock); } diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index e398beac67b8..9bd559472c92 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -65,6 +65,7 @@ #define V9FS_MAGIC 0x01021997 #define BDEVFS_MAGIC 0x62646576 +#define DAXFS_MAGIC 0x64646178 #define BINFMTFS_MAGIC 0x42494e4d #define DEVPTS_SUPER_MAGIC 0x1cd1 #define FUTEXFS_SUPER_MAGIC 0xBAD1DEA -- cgit v1.2.3 From a52e95abf772b43c9226e9a72d3c1353903ba96f Mon Sep 17 00:00:00 2001 From: Lorenzo Colitti Date: Wed, 24 Aug 2016 15:46:26 +0900 Subject: net: diag: allow socket bytecode filters to match socket marks This allows a privileged process to filter by socket mark when dumping sockets via INET_DIAG_BY_FAMILY. This is useful on systems that use mark-based routing such as Android. The ability to filter socket marks requires CAP_NET_ADMIN, which is consistent with other privileged operations allowed by the SOCK_DIAG interface such as the ability to destroy sockets and the ability to inspect BPF filters attached to packet sockets. Tested: https://android-review.googlesource.com/261350 Signed-off-by: Lorenzo Colitti Acked-by: David Ahern Signed-off-by: David S. Miller --- include/uapi/linux/inet_diag.h | 6 ++++++ net/ipv4/inet_diag.c | 36 +++++++++++++++++++++++++++++++++--- 2 files changed, 39 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index abbd1dc5d683..5581206a08ae 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -73,6 +73,7 @@ enum { INET_DIAG_BC_S_COND, INET_DIAG_BC_D_COND, INET_DIAG_BC_DEV_COND, /* u32 ifindex */ + INET_DIAG_BC_MARK_COND, }; struct inet_diag_hostcond { @@ -82,6 +83,11 @@ struct inet_diag_hostcond { __be32 addr[0]; }; +struct inet_diag_markcond { + __u32 mark; + __u32 mask; +}; + /* Base info structure. It contains socket identity (addrs/ports/cookie) * and, alas, the information shown by netstat. */ struct inet_diag_msg { diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index a89b68c6a934..abfbe492ebfe 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -45,6 +45,7 @@ struct inet_diag_entry { u16 family; u16 userlocks; u32 ifindex; + u32 mark; }; static DEFINE_MUTEX(inet_diag_table_mutex); @@ -580,6 +581,14 @@ static int inet_diag_bc_run(const struct nlattr *_bc, yes = 0; break; } + case INET_DIAG_BC_MARK_COND: { + struct inet_diag_markcond *cond; + + cond = (struct inet_diag_markcond *)(op + 1); + if ((entry->mark & cond->mask) != cond->mark) + yes = 0; + break; + } } if (yes) { @@ -624,6 +633,12 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk) entry.dport = ntohs(inet->inet_dport); entry.ifindex = sk->sk_bound_dev_if; entry.userlocks = sk_fullsock(sk) ? sk->sk_userlocks : 0; + if (sk_fullsock(sk)) + entry.mark = sk->sk_mark; + else if (sk->sk_state == TCP_NEW_SYN_RECV) + entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark; + else + entry.mark = 0; return inet_diag_bc_run(bc, &entry); } @@ -706,8 +721,17 @@ static bool valid_port_comparison(const struct inet_diag_bc_op *op, return true; } -static int inet_diag_bc_audit(const struct nlattr *attr) +static bool valid_markcond(const struct inet_diag_bc_op *op, int len, + int *min_len) { + *min_len += sizeof(struct inet_diag_markcond); + return len >= *min_len; +} + +static int inet_diag_bc_audit(const struct nlattr *attr, + const struct sk_buff *skb) +{ + bool net_admin = netlink_net_capable(skb, CAP_NET_ADMIN); const void *bytecode, *bc; int bytecode_len, len; @@ -738,6 +762,12 @@ static int inet_diag_bc_audit(const struct nlattr *attr) if (!valid_port_comparison(bc, len, &min_len)) return -EINVAL; break; + case INET_DIAG_BC_MARK_COND: + if (!net_admin) + return -EPERM; + if (!valid_markcond(bc, len, &min_len)) + return -EINVAL; + break; case INET_DIAG_BC_AUTO: case INET_DIAG_BC_JMP: case INET_DIAG_BC_NOP: @@ -1030,7 +1060,7 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) attr = nlmsg_find_attr(nlh, hdrlen, INET_DIAG_REQ_BYTECODE); - err = inet_diag_bc_audit(attr); + err = inet_diag_bc_audit(attr, skb); if (err) return err; } @@ -1061,7 +1091,7 @@ static int inet_diag_handler_cmd(struct sk_buff *skb, struct nlmsghdr *h) attr = nlmsg_find_attr(h, hdrlen, INET_DIAG_REQ_BYTECODE); - err = inet_diag_bc_audit(attr); + err = inet_diag_bc_audit(attr, skb); if (err) return err; } -- cgit v1.2.3 From 54dfce6d07b0391e23d006579bba488de4f7d6aa Mon Sep 17 00:00:00 2001 From: Felix Hädicke Date: Wed, 22 Jun 2016 01:12:07 +0200 Subject: usb: gadget: f_fs: handle control requests not directed to interface or endpoint MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduces a new FunctionFS descriptor flag named FUNCTIONFS_ALL_CTRL_RECIP. When this flag is enabled, control requests, which are not explicitly directed to an interface or endpoint, can be handled. This allows FunctionFS userspace drivers to process non-standard control requests. Signed-off-by: Felix Hädicke Signed-off-by: Felipe Balbi --- drivers/usb/gadget/function/f_fs.c | 34 ++++++++++++++++++++++++++++++---- include/uapi/linux/usb/functionfs.h | 1 + 2 files changed, 31 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 5c8429f23a89..d7acab873836 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -98,6 +98,8 @@ static int ffs_func_set_alt(struct usb_function *, unsigned, unsigned); static void ffs_func_disable(struct usb_function *); static int ffs_func_setup(struct usb_function *, const struct usb_ctrlrequest *); +static bool ffs_func_req_match(struct usb_function *, + const struct usb_ctrlrequest *); static void ffs_func_suspend(struct usb_function *); static void ffs_func_resume(struct usb_function *); @@ -2243,7 +2245,8 @@ static int __ffs_data_got_descs(struct ffs_data *ffs, FUNCTIONFS_HAS_SS_DESC | FUNCTIONFS_HAS_MS_OS_DESC | FUNCTIONFS_VIRTUAL_ADDR | - FUNCTIONFS_EVENTFD)) { + FUNCTIONFS_EVENTFD | + FUNCTIONFS_ALL_CTRL_RECIP)) { ret = -ENOSYS; goto error; } @@ -3094,8 +3097,9 @@ static int ffs_func_setup(struct usb_function *f, * handle them. All other either handled by composite or * passed to usb_configuration->setup() (if one is set). No * matter, we will handle requests directed to endpoint here - * as well (as it's straightforward) but what to do with any - * other request? + * as well (as it's straightforward). Other request recipient + * types are only handled when the user flag FUNCTIONFS_ALL_CTRL_RECIP + * is being used. */ if (ffs->state != FFS_ACTIVE) return -ENODEV; @@ -3116,7 +3120,10 @@ static int ffs_func_setup(struct usb_function *f, break; default: - return -EOPNOTSUPP; + if (func->ffs->user_flags & FUNCTIONFS_ALL_CTRL_RECIP) + ret = le16_to_cpu(creq->wIndex); + else + return -EOPNOTSUPP; } spin_lock_irqsave(&ffs->ev.waitq.lock, flags); @@ -3128,6 +3135,24 @@ static int ffs_func_setup(struct usb_function *f, return 0; } +static bool ffs_func_req_match(struct usb_function *f, + const struct usb_ctrlrequest *creq) +{ + struct ffs_function *func = ffs_func_from_usb(f); + + switch (creq->bRequestType & USB_RECIP_MASK) { + case USB_RECIP_INTERFACE: + return ffs_func_revmap_intf(func, + le16_to_cpu(creq->wIndex) >= 0); + case USB_RECIP_ENDPOINT: + return ffs_func_revmap_ep(func, + le16_to_cpu(creq->wIndex) >= 0); + default: + return (bool) (func->ffs->user_flags & + FUNCTIONFS_ALL_CTRL_RECIP); + } +} + static void ffs_func_suspend(struct usb_function *f) { ENTER(); @@ -3378,6 +3403,7 @@ static struct usb_function *ffs_alloc(struct usb_function_instance *fi) func->function.set_alt = ffs_func_set_alt; func->function.disable = ffs_func_disable; func->function.setup = ffs_func_setup; + func->function.req_match = ffs_func_req_match; func->function.suspend = ffs_func_suspend; func->function.resume = ffs_func_resume; func->function.free_func = ffs_free; diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h index 108dd7997014..93da4ca82dc7 100644 --- a/include/uapi/linux/usb/functionfs.h +++ b/include/uapi/linux/usb/functionfs.h @@ -21,6 +21,7 @@ enum functionfs_flags { FUNCTIONFS_HAS_MS_OS_DESC = 8, FUNCTIONFS_VIRTUAL_ADDR = 16, FUNCTIONFS_EVENTFD = 32, + FUNCTIONFS_ALL_CTRL_RECIP = 64, }; /* Descriptor of an non-audio endpoint */ -- cgit v1.2.3 From 4368c28ae7acb0744968e58c81be561b44aacd57 Mon Sep 17 00:00:00 2001 From: Felix Hädicke Date: Wed, 22 Jun 2016 01:12:09 +0200 Subject: usb: gadget: f_fs: handle control requests in config 0 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduces a new FunctionFS descriptor flag named FUNCTIONFS_CONFIG0_SETUP. When this flag is enabled, FunctionFS userspace drivers can process non-standard control requests in configuration 0. Signed-off-by: Felix Hädicke Signed-off-by: Felipe Balbi --- drivers/usb/gadget/function/f_fs.c | 5 +++-- include/uapi/linux/usb/functionfs.h | 1 + 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index d8f46f6233ac..998697bd80ac 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -2247,7 +2247,8 @@ static int __ffs_data_got_descs(struct ffs_data *ffs, FUNCTIONFS_HAS_MS_OS_DESC | FUNCTIONFS_VIRTUAL_ADDR | FUNCTIONFS_EVENTFD | - FUNCTIONFS_ALL_CTRL_RECIP)) { + FUNCTIONFS_ALL_CTRL_RECIP | + FUNCTIONFS_CONFIG0_SETUP)) { ret = -ENOSYS; goto error; } @@ -3142,7 +3143,7 @@ static bool ffs_func_req_match(struct usb_function *f, { struct ffs_function *func = ffs_func_from_usb(f); - if (config0) + if (config0 && !(func->ffs->user_flags & FUNCTIONFS_CONFIG0_SETUP)) return false; switch (creq->bRequestType & USB_RECIP_MASK) { diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h index 93da4ca82dc7..acc63697a0cc 100644 --- a/include/uapi/linux/usb/functionfs.h +++ b/include/uapi/linux/usb/functionfs.h @@ -22,6 +22,7 @@ enum functionfs_flags { FUNCTIONFS_VIRTUAL_ADDR = 16, FUNCTIONFS_EVENTFD = 32, FUNCTIONFS_ALL_CTRL_RECIP = 64, + FUNCTIONFS_CONFIG0_SETUP = 128, }; /* Descriptor of an non-audio endpoint */ -- cgit v1.2.3 From 8b2ec318eece89be5e33d5313a25461a55a3177a Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Sun, 12 Jun 2016 16:26:40 -0500 Subject: PCI: Add PTM clock granularity information The PTM Control register (PCIe r3.1, sec 7.32.3) contains an Effective Granularity field: This provides information relating to the expected accuracy of the PTM clock, but does not otherwise affect the PTM mechanism. Set the Effective Granularity based on the PTM Root and any intervening PTM Time Sources. This does not set Effective Granularity for Root Complex Integrated Endpoints because I don't know how to figure out clock granularity for them. The spec says: ... system software must set [Effective Granularity] to the value reported in the Local Clock Granularity field by the associated PTM Time Source. but I don't know how to identify the associated PTM Time Source. Normally it's the upstream bridge, but an integrated endpoint has no upstream bridge. Signed-off-by: Bjorn Helgaas --- drivers/pci/pcie/ptm.c | 31 +++++++++++++++++++++++++++++-- include/linux/pci.h | 1 + include/uapi/linux/pci_regs.h | 1 + 3 files changed, 31 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/pci/pcie/ptm.c b/drivers/pci/pcie/ptm.c index a14ac94b96dc..bab8ac63c4f3 100644 --- a/drivers/pci/pcie/ptm.c +++ b/drivers/pci/pcie/ptm.c @@ -19,13 +19,29 @@ static void pci_ptm_info(struct pci_dev *dev) { - dev_info(&dev->dev, "PTM enabled%s\n", dev->ptm_root ? " (root)" : ""); + char clock_desc[8]; + + switch (dev->ptm_granularity) { + case 0: + snprintf(clock_desc, sizeof(clock_desc), "unknown"); + break; + case 255: + snprintf(clock_desc, sizeof(clock_desc), ">254ns"); + break; + default: + snprintf(clock_desc, sizeof(clock_desc), "%udns", + dev->ptm_granularity); + break; + } + dev_info(&dev->dev, "PTM enabled%s, %s granularity\n", + dev->ptm_root ? " (root)" : "", clock_desc); } void pci_ptm_init(struct pci_dev *dev) { int pos; u32 cap, ctrl; + u8 local_clock; struct pci_dev *ups; if (!pci_is_pcie(dev)) @@ -45,6 +61,7 @@ void pci_ptm_init(struct pci_dev *dev) return; pci_read_config_dword(dev, pos + PCI_PTM_CAP, &cap); + local_clock = (cap & PCI_PTM_GRANULARITY_MASK) >> 8; /* * There's no point in enabling PTM unless it's enabled in the @@ -55,14 +72,20 @@ void pci_ptm_init(struct pci_dev *dev) ups = pci_upstream_bridge(dev); if (ups && ups->ptm_enabled) { ctrl = PCI_PTM_CTRL_ENABLE; + if (ups->ptm_granularity == 0) + dev->ptm_granularity = 0; + else if (ups->ptm_granularity > local_clock) + dev->ptm_granularity = ups->ptm_granularity; } else { if (cap & PCI_PTM_CAP_ROOT) { ctrl = PCI_PTM_CTRL_ENABLE | PCI_PTM_CTRL_ROOT; dev->ptm_root = 1; + dev->ptm_granularity = local_clock; } else return; } + ctrl |= dev->ptm_granularity << 8; pci_write_config_dword(dev, pos + PCI_PTM_CTRL, ctrl); dev->ptm_enabled = 1; @@ -98,18 +121,22 @@ int pci_enable_ptm(struct pci_dev *dev, u8 *granularity) ups = pci_upstream_bridge(dev); if (!ups || !ups->ptm_enabled) return -EINVAL; + + dev->ptm_granularity = ups->ptm_granularity; } else if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END) { + dev->ptm_granularity = 0; } else return -EINVAL; ctrl = PCI_PTM_CTRL_ENABLE; + ctrl |= dev->ptm_granularity << 8; pci_write_config_dword(dev, pos + PCI_PTM_CTRL, ctrl); dev->ptm_enabled = 1; pci_ptm_info(dev); if (granularity) - *granularity = 0; + *granularity = dev->ptm_granularity; return 0; } EXPORT_SYMBOL(pci_enable_ptm); diff --git a/include/linux/pci.h b/include/linux/pci.h index 9e4b6d6f3c8d..7256f33b6a15 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -371,6 +371,7 @@ struct pci_dev { #ifdef CONFIG_PCIE_PTM unsigned int ptm_root:1; unsigned int ptm_enabled:1; + u8 ptm_granularity; #endif #ifdef CONFIG_PCI_MSI const struct attribute_group **msi_irq_groups; diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 72bbe1491cbf..d812172d1d7b 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -969,6 +969,7 @@ #define PCI_PTM_CAP 0x04 /* PTM Capability */ #define PCI_PTM_CAP_REQ 0x00000001 /* Requester capable */ #define PCI_PTM_CAP_ROOT 0x00000004 /* Root capable */ +#define PCI_PTM_GRANULARITY_MASK 0x0000FF00 /* Clock granularity */ #define PCI_PTM_CTRL 0x08 /* PTM Control */ #define PCI_PTM_CTRL_ENABLE 0x00000001 /* PTM enable */ #define PCI_PTM_CTRL_ROOT 0x00000002 /* Root select */ -- cgit v1.2.3 From 72145a68e4ee116533df49af4b87aca0aacc179c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 24 Aug 2016 09:01:23 -0700 Subject: tcp: md5: add LINUX_MIB_TCPMD5FAILURE counter Adds SNMP counter for drops caused by MD5 mismatches. The current syslog might help, but a counter is more precise and helps monitoring. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/uapi/linux/snmp.h | 1 + net/ipv4/proc.c | 1 + net/ipv4/tcp_ipv4.c | 1 + net/ipv6/tcp_ipv6.c | 1 + 4 files changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 25a9ad8bcef1..e7a31f830690 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -235,6 +235,7 @@ enum LINUX_MIB_TCPSPURIOUSRTOS, /* TCPSpuriousRTOs */ LINUX_MIB_TCPMD5NOTFOUND, /* TCPMD5NotFound */ LINUX_MIB_TCPMD5UNEXPECTED, /* TCPMD5Unexpected */ + LINUX_MIB_TCPMD5FAILURE, /* TCPMD5Failure */ LINUX_MIB_SACKSHIFTED, LINUX_MIB_SACKMERGED, LINUX_MIB_SACKSHIFTFALLBACK, diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 9f665b63a927..1ed015e4bc79 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -257,6 +257,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPSpuriousRTOs", LINUX_MIB_TCPSPURIOUSRTOS), SNMP_MIB_ITEM("TCPMD5NotFound", LINUX_MIB_TCPMD5NOTFOUND), SNMP_MIB_ITEM("TCPMD5Unexpected", LINUX_MIB_TCPMD5UNEXPECTED), + SNMP_MIB_ITEM("TCPMD5Failure", LINUX_MIB_TCPMD5FAILURE), SNMP_MIB_ITEM("TCPSackShifted", LINUX_MIB_SACKSHIFTED), SNMP_MIB_ITEM("TCPSackMerged", LINUX_MIB_SACKMERGED), SNMP_MIB_ITEM("TCPSackShiftFallback", LINUX_MIB_SACKSHIFTFALLBACK), diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 436d978c6c39..ad41e8ecf796 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1169,6 +1169,7 @@ static bool tcp_v4_inbound_md5_hash(const struct sock *sk, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n", &iph->saddr, ntohs(th->source), &iph->daddr, ntohs(th->dest), diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index ac0ed7bda406..e4f55683af31 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -671,6 +671,7 @@ static bool tcp_v6_inbound_md5_hash(const struct sock *sk, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u\n", genhash ? "failed" : "mismatch", &ip6h->saddr, ntohs(th->source), -- cgit v1.2.3 From ef20cd4dd1633987bcf46ac34ace2c8af212361f Mon Sep 17 00:00:00 2001 From: Richard Alpe Date: Fri, 26 Aug 2016 10:52:53 +0200 Subject: tipc: introduce UDP replicast This patch introduces UDP replicast. A concept where we emulate multicast by sending multiple unicast messages to configured peers. The purpose of replicast is mainly to be able to use TIPC in cloud environments where IP multicast is disabled. Using replicas to unicast multicast messages is costly as we have to copy each skb and send the copies individually. Signed-off-by: Richard Alpe Reviewed-by: Jon Maloy Signed-off-by: David S. Miller --- include/uapi/linux/tipc_netlink.h | 1 + net/tipc/bearer.c | 44 ++++++++++++++ net/tipc/bearer.h | 1 + net/tipc/netlink.c | 5 ++ net/tipc/udp_media.c | 118 ++++++++++++++++++++++++++++++++++---- net/tipc/udp_media.h | 44 ++++++++++++++ 6 files changed, 201 insertions(+), 12 deletions(-) create mode 100644 net/tipc/udp_media.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h index bcb65ef725f6..b15664c36219 100644 --- a/include/uapi/linux/tipc_netlink.h +++ b/include/uapi/linux/tipc_netlink.h @@ -60,6 +60,7 @@ enum { TIPC_NL_MON_GET, TIPC_NL_MON_PEER_GET, TIPC_NL_PEER_REMOVE, + TIPC_NL_BEARER_ADD, __TIPC_NL_CMD_MAX, TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1 diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 28056fa8f77a..d7b442dd6669 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -42,6 +42,7 @@ #include "monitor.h" #include "bcast.h" #include "netlink.h" +#include "udp_media.h" #define MAX_ADDR_STR 60 @@ -897,6 +898,49 @@ int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) return 0; } +int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info) +{ + int err; + char *name; + struct tipc_bearer *b; + struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; + struct net *net = sock_net(skb->sk); + + if (!info->attrs[TIPC_NLA_BEARER]) + return -EINVAL; + + err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX, + info->attrs[TIPC_NLA_BEARER], + tipc_nl_bearer_policy); + if (err) + return err; + + if (!attrs[TIPC_NLA_BEARER_NAME]) + return -EINVAL; + name = nla_data(attrs[TIPC_NLA_BEARER_NAME]); + + rtnl_lock(); + b = tipc_bearer_find(net, name); + if (!b) { + rtnl_unlock(); + return -EINVAL; + } + +#ifdef CONFIG_TIPC_MEDIA_UDP + if (attrs[TIPC_NLA_BEARER_UDP_OPTS]) { + err = tipc_udp_nl_bearer_add(b, + attrs[TIPC_NLA_BEARER_UDP_OPTS]); + if (err) { + rtnl_unlock(); + return err; + } + } +#endif + rtnl_unlock(); + + return 0; +} + int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) { int err; diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 83a9abbfe32c..78892e2f53e3 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -181,6 +181,7 @@ int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info); +int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info); int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info); diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 2718de667828..3122f21ca979 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -160,6 +160,11 @@ static const struct genl_ops tipc_genl_v2_ops[] = { .dumpit = tipc_nl_bearer_dump, .policy = tipc_nl_policy, }, + { + .cmd = TIPC_NL_BEARER_ADD, + .doit = tipc_nl_bearer_add, + .policy = tipc_nl_policy, + }, { .cmd = TIPC_NL_BEARER_SET, .doit = tipc_nl_bearer_set, diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index b8ec1a18241e..6b938cc15daf 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -49,6 +49,7 @@ #include "core.h" #include "bearer.h" #include "netlink.h" +#include "msg.h" /* IANA assigned UDP port */ #define UDP_PORT_DEFAULT 6118 @@ -70,6 +71,13 @@ struct udp_media_addr { }; }; +/* struct udp_replicast - container for UDP remote addresses */ +struct udp_replicast { + struct udp_media_addr addr; + struct rcu_head rcu; + struct list_head list; +}; + /** * struct udp_bearer - ip/udp bearer data structure * @bearer: associated generic tipc bearer @@ -82,6 +90,7 @@ struct udp_bearer { struct socket *ubsock; u32 ifindex; struct work_struct work; + struct udp_replicast rcast; }; static int tipc_udp_is_mcast_addr(struct udp_media_addr *addr) @@ -203,29 +212,75 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb, { struct udp_media_addr *src = (struct udp_media_addr *)&b->addr.value; struct udp_media_addr *dst = (struct udp_media_addr *)&addr->value; + struct udp_replicast *rcast; struct udp_bearer *ub; int err = 0; if (skb_headroom(skb) < UDP_MIN_HEADROOM) { err = pskb_expand_head(skb, UDP_MIN_HEADROOM, 0, GFP_ATOMIC); if (err) - goto tx_error; + goto out; } skb_set_inner_protocol(skb, htons(ETH_P_TIPC)); ub = rcu_dereference_rtnl(b->media_ptr); if (!ub) { err = -ENODEV; - goto tx_error; + goto out; } - return tipc_udp_xmit(net, skb, ub, src, dst); + if (!addr->broadcast || list_empty(&ub->rcast.list)) + return tipc_udp_xmit(net, skb, ub, src, dst); -tx_error: + /* Replicast, send an skb to each configured IP address */ + list_for_each_entry_rcu(rcast, &ub->rcast.list, list) { + struct sk_buff *_skb; + + _skb = pskb_copy(skb, GFP_ATOMIC); + if (!_skb) { + err = -ENOMEM; + goto out; + } + + err = tipc_udp_xmit(net, _skb, ub, src, &rcast->addr); + if (err) { + kfree_skb(_skb); + goto out; + } + } + err = 0; +out: kfree_skb(skb); return err; } +static int tipc_udp_rcast_add(struct tipc_bearer *b, + struct udp_media_addr *addr) +{ + struct udp_replicast *rcast; + struct udp_bearer *ub; + + ub = rcu_dereference_rtnl(b->media_ptr); + if (!ub) + return -ENODEV; + + rcast = kmalloc(sizeof(*rcast), GFP_ATOMIC); + if (!rcast) + return -ENOMEM; + + memcpy(&rcast->addr, addr, sizeof(struct udp_media_addr)); + + if (ntohs(addr->proto) == ETH_P_IP) + pr_info("New replicast peer: %pI4\n", &rcast->addr.ipv4); +#if IS_ENABLED(CONFIG_IPV6) + else if (ntohs(addr->proto) == ETH_P_IPV6) + pr_info("New replicast peer: %pI6\n", &rcast->addr.ipv6); +#endif + + list_add_rcu(&rcast->list, &ub->rcast.list); + return 0; +} + /* tipc_udp_recv - read data from bearer socket */ static int tipc_udp_recv(struct sock *sk, struct sk_buff *skb) { @@ -320,6 +375,32 @@ static int tipc_parse_udp_addr(struct nlattr *nla, struct udp_media_addr *addr, return -EADDRNOTAVAIL; } +int tipc_udp_nl_bearer_add(struct tipc_bearer *b, struct nlattr *attr) +{ + int err; + struct udp_media_addr addr = {0}; + struct nlattr *opts[TIPC_NLA_UDP_MAX + 1]; + struct udp_media_addr *dst; + + if (nla_parse_nested(opts, TIPC_NLA_UDP_MAX, attr, tipc_nl_udp_policy)) + return -EINVAL; + + if (!opts[TIPC_NLA_UDP_REMOTE]) + return -EINVAL; + + err = tipc_parse_udp_addr(opts[TIPC_NLA_UDP_REMOTE], &addr, NULL); + if (err) + return err; + + dst = (struct udp_media_addr *)&b->bcast_addr.value; + if (tipc_udp_is_mcast_addr(dst)) { + pr_err("Can't add remote ip to TIPC UDP multicast bearer\n"); + return -EINVAL; + } + + return tipc_udp_rcast_add(b, &addr); +} + /** * tipc_udp_enable - callback to create a new udp bearer instance * @net: network namespace @@ -334,7 +415,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, { int err = -EINVAL; struct udp_bearer *ub; - struct udp_media_addr *remote; + struct udp_media_addr remote = {0}; struct udp_media_addr local = {0}; struct udp_port_cfg udp_conf = {0}; struct udp_tunnel_sock_cfg tuncfg = {NULL}; @@ -344,6 +425,8 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, if (!ub) return -ENOMEM; + INIT_LIST_HEAD(&ub->rcast.list); + if (!attrs[TIPC_NLA_BEARER_UDP_OPTS]) goto err; @@ -362,9 +445,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, if (err) goto err; - remote = (struct udp_media_addr *)&b->bcast_addr.value; - memset(remote, 0, sizeof(struct udp_media_addr)); - err = tipc_parse_udp_addr(opts[TIPC_NLA_UDP_REMOTE], remote, NULL); + err = tipc_parse_udp_addr(opts[TIPC_NLA_UDP_REMOTE], &remote, NULL); if (err) goto err; @@ -409,10 +490,17 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, tuncfg.encap_destroy = NULL; setup_udp_tunnel_sock(net, ub->ubsock, &tuncfg); - if (tipc_udp_is_mcast_addr(remote)) { - if (enable_mcast(ub, remote)) - goto err; - } + /** + * The bcast media address port is used for all peers and the ip + * is used if it's a multicast address. + */ + memcpy(&b->bcast_addr.value, &remote, sizeof(remote)); + if (tipc_udp_is_mcast_addr(&remote)) + err = enable_mcast(ub, &remote); + else + err = tipc_udp_rcast_add(b, &remote); + if (err) + goto err; return 0; err: @@ -424,6 +512,12 @@ err: static void cleanup_bearer(struct work_struct *work) { struct udp_bearer *ub = container_of(work, struct udp_bearer, work); + struct udp_replicast *rcast, *tmp; + + list_for_each_entry_safe(rcast, tmp, &ub->rcast.list, list) { + list_del_rcu(&rcast->list); + kfree_rcu(rcast, rcu); + } if (ub->ubsock) udp_tunnel_sock_release(ub->ubsock); diff --git a/net/tipc/udp_media.h b/net/tipc/udp_media.h new file mode 100644 index 000000000000..4dcb54880aa6 --- /dev/null +++ b/net/tipc/udp_media.h @@ -0,0 +1,44 @@ +/* + * net/tipc/udp_media.h: Include file for UDP bearer media + * + * Copyright (c) 1996-2006, 2013-2016, Ericsson AB + * Copyright (c) 2005, 2010-2011, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifdef CONFIG_TIPC_MEDIA_UDP +#ifndef _TIPC_UDP_MEDIA_H +#define _TIPC_UDP_MEDIA_H + +int tipc_udp_nl_bearer_add(struct tipc_bearer *b, struct nlattr *attr); + +#endif +#endif -- cgit v1.2.3 From fdb3accc2c15fabc2b687b2819da9167027c61b6 Mon Sep 17 00:00:00 2001 From: Richard Alpe Date: Fri, 26 Aug 2016 10:52:55 +0200 Subject: tipc: add the ability to get UDP options via netlink Add UDP bearer options to netlink bearer get message. This is used by the tipc user space tool to display UDP options. The UDP bearer information is passed using either a sockaddr_in or sockaddr_in6 structs. This means the user space receiver should intermediately store the retrieved data in a large enough struct (sockaddr_strage) before casting to the proper IP version type. Signed-off-by: Richard Alpe Reviewed-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- include/uapi/linux/tipc_netlink.h | 2 ++ net/tipc/bearer.c | 8 +++++ net/tipc/udp_media.c | 61 +++++++++++++++++++++++++++++++++++++++ net/tipc/udp_media.h | 1 + 4 files changed, 72 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h index b15664c36219..f9edd20fe9ba 100644 --- a/include/uapi/linux/tipc_netlink.h +++ b/include/uapi/linux/tipc_netlink.h @@ -61,6 +61,7 @@ enum { TIPC_NL_MON_PEER_GET, TIPC_NL_PEER_REMOVE, TIPC_NL_BEARER_ADD, + TIPC_NL_UDP_GET_REMOTEIP, __TIPC_NL_CMD_MAX, TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1 @@ -100,6 +101,7 @@ enum { TIPC_NLA_UDP_UNSPEC, TIPC_NLA_UDP_LOCAL, /* sockaddr_storage */ TIPC_NLA_UDP_REMOTE, /* sockaddr_storage */ + TIPC_NLA_UDP_MULTI_REMOTEIP, /* flag */ __TIPC_NLA_UDP_MAX, TIPC_NLA_UDP_MAX = __TIPC_NLA_UDP_MAX - 1 diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index d7b442dd6669..975dbeb60ab0 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -712,6 +712,14 @@ static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg, goto prop_msg_full; nla_nest_end(msg->skb, prop); + +#ifdef CONFIG_TIPC_MEDIA_UDP + if (bearer->media->type_id == TIPC_MEDIA_TYPE_UDP) { + if (tipc_udp_nl_add_bearer_data(msg, bearer)) + goto attr_msg_full; + } +#endif + nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 6ece3c9ccf82..a6cdd9895653 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -401,6 +401,67 @@ static int enable_mcast(struct udp_bearer *ub, struct udp_media_addr *remote) return err; } +static int __tipc_nl_add_udp_addr(struct sk_buff *skb, + struct udp_media_addr *addr, int nla_t) +{ + if (ntohs(addr->proto) == ETH_P_IP) { + struct sockaddr_in ip4; + + ip4.sin_family = AF_INET; + ip4.sin_port = addr->port; + ip4.sin_addr.s_addr = addr->ipv4.s_addr; + if (nla_put(skb, nla_t, sizeof(ip4), &ip4)) + return -EMSGSIZE; + +#if IS_ENABLED(CONFIG_IPV6) + } else if (ntohs(addr->proto) == ETH_P_IPV6) { + struct sockaddr_in6 ip6; + + ip6.sin6_family = AF_INET6; + ip6.sin6_port = addr->port; + memcpy(&ip6.sin6_addr, &addr->ipv6, sizeof(struct in6_addr)); + if (nla_put(skb, nla_t, sizeof(ip6), &ip6)) + return -EMSGSIZE; +#endif + } + + return 0; +} + +int tipc_udp_nl_add_bearer_data(struct tipc_nl_msg *msg, struct tipc_bearer *b) +{ + struct udp_media_addr *src = (struct udp_media_addr *)&b->addr.value; + struct udp_media_addr *dst; + struct udp_bearer *ub; + struct nlattr *nest; + + ub = rcu_dereference_rtnl(b->media_ptr); + if (!ub) + return -ENODEV; + + nest = nla_nest_start(msg->skb, TIPC_NLA_BEARER_UDP_OPTS); + if (!nest) + goto msg_full; + + if (__tipc_nl_add_udp_addr(msg->skb, src, TIPC_NLA_UDP_LOCAL)) + goto msg_full; + + dst = (struct udp_media_addr *)&b->bcast_addr.value; + if (__tipc_nl_add_udp_addr(msg->skb, dst, TIPC_NLA_UDP_REMOTE)) + goto msg_full; + + if (!list_empty(&ub->rcast.list)) { + if (nla_put_flag(msg->skb, TIPC_NLA_UDP_MULTI_REMOTEIP)) + goto msg_full; + } + + nla_nest_end(msg->skb, nest); + return 0; +msg_full: + nla_nest_cancel(msg->skb, nest); + return -EMSGSIZE; +} + /** * tipc_parse_udp_addr - build udp media address from netlink data * @nlattr: netlink attribute containing sockaddr storage aligned address diff --git a/net/tipc/udp_media.h b/net/tipc/udp_media.h index 4dcb54880aa6..c06326a134db 100644 --- a/net/tipc/udp_media.h +++ b/net/tipc/udp_media.h @@ -39,6 +39,7 @@ #define _TIPC_UDP_MEDIA_H int tipc_udp_nl_bearer_add(struct tipc_bearer *b, struct nlattr *attr); +int tipc_udp_nl_add_bearer_data(struct tipc_nl_msg *msg, struct tipc_bearer *b); #endif #endif -- cgit v1.2.3 From 5711a98221443aec54c4c81ee98c6ae46acccb65 Mon Sep 17 00:00:00 2001 From: Vidya Sagar Ravipati Date: Fri, 26 Aug 2016 01:25:50 -0700 Subject: net: ethtool: add support for 1000BaseX and missing 10G link modes This patch enhances ethtool link mode bitmap to include missing interface modes for 1G/10G speeds Changes: 1000baseX is the mode introduced to cover all 1G Fiber cases. All modes under 1000BaseX i.e. 1000BASE-SX, 1000BASE-LX, 1000BASE-LX10 and 1000BASE-BX10 are not explicitly defined at this moment. 10G CR,SR,LR and ER link modes are included for 10G speed.. Issue: ethtool on 1G/10G SFP port reports Base-T as this port supports 1000baseX,10G CR, SR and LR modes. root@tor-02$ ethtool swp1 Settings for swp1: Supported ports: [ FIBRE ] Supported link modes: 1000baseT/Full 10000baseT/Full Supported pause frame use: Symmetric Receive-only Supports auto-negotiation: Yes Advertised link modes: 1000baseT/Full Advertised pause frame use: No Advertised auto-negotiation: No Speed: 10000Mb/s Duplex: Full Port: FIBRE PHYAD: 0 Transceiver: external Auto-negotiation: off Current message level: 0x00000000 (0) Link detected: yes After fix: root@tor-02$ ethtool swp1 Settings for swp1: Supported ports: [ FIBRE ] Supported link modes: 1000baseX/Full 10000baseCR/Full 10000baseSR/Full 10000baseLR/Full 10000baseER/Full Supported pause frame use: Symmetric Receive-only Supports auto-negotiation: Yes Advertised link modes: 1000baseT/Full Advertised pause frame use: No Advertised auto-negotiation: No Speed: 10000Mb/s Duplex: Full Port: FIBRE PHYAD: 0 Transceiver: external Auto-negotiation: off Current message level: 0x00000000 (0) Link detected: yes Signed-off-by: Vidya Sagar Ravipati Signed-off-by: David S. Miller --- include/uapi/linux/ethtool.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index b8f38e84d93a..099a4200732c 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1362,7 +1362,14 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT = 37, ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT = 38, ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT = 39, - ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT = 40, + ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT = 40, + ETHTOOL_LINK_MODE_1000baseX_Full_BIT = 41, + ETHTOOL_LINK_MODE_10000baseCR_Full_BIT = 42, + ETHTOOL_LINK_MODE_10000baseSR_Full_BIT = 43, + ETHTOOL_LINK_MODE_10000baseLR_Full_BIT = 44, + ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT = 45, + ETHTOOL_LINK_MODE_10000baseER_Full_BIT = 46, + /* Last allowed bit for __ETHTOOL_LINK_MODE_LEGACY_MASK is bit * 31. Please do NOT define any SUPPORTED_* or ADVERTISED_* @@ -1371,7 +1378,7 @@ enum ethtool_link_mode_bit_indices { */ __ETHTOOL_LINK_MODE_LAST - = ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT, + = ETHTOOL_LINK_MODE_10000baseER_Full_BIT, }; #define __ETHTOOL_LINK_MODE_LEGACY_MASK(base_name) \ -- cgit v1.2.3 From b6cb5ac8331b6bcfe9ce38c7f7f58db6e1d6270a Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 31 Aug 2016 15:36:52 +0200 Subject: net: bridge: add per-port multicast flood flag Add a per-port flag to control the unknown multicast flood, similar to the unknown unicast flood flag and break a few long lines in the netlink flag exports. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 1 + include/uapi/linux/if_link.h | 1 + net/bridge/br_forward.c | 3 +++ net/bridge/br_if.c | 2 +- net/bridge/br_netlink.c | 12 +++++++++--- net/bridge/br_sysfs_if.c | 1 + 6 files changed, 16 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index dcb89e3515db..c6587c01d951 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -45,6 +45,7 @@ struct br_ip_list { #define BR_PROXYARP BIT(8) #define BR_LEARNING_SYNC BIT(9) #define BR_PROXYARP_WIFI BIT(10) +#define BR_MCAST_FLOOD BIT(11) #define BR_DEFAULT_AGEING_TIME (300 * HZ) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index a1b5202c5f6b..9bf3aecfe05b 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -318,6 +318,7 @@ enum { IFLA_BRPORT_FLUSH, IFLA_BRPORT_MULTICAST_ROUTER, IFLA_BRPORT_PAD, + IFLA_BRPORT_MCAST_FLOOD, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 5de854ed3340..7cb41aee4c82 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -186,6 +186,9 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb, /* Do not flood unicast traffic to ports that turn it off */ if (pkt_type == BR_PKT_UNICAST && !(p->flags & BR_FLOOD)) continue; + if (pkt_type == BR_PKT_MULTICAST && + !(p->flags & BR_MCAST_FLOOD)) + continue; /* Do not flood to ports that enable proxy ARP */ if (p->flags & BR_PROXYARP) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 1da3221845f1..ed0dd3340084 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -362,7 +362,7 @@ static struct net_bridge_port *new_nbp(struct net_bridge *br, p->path_cost = port_cost(dev); p->priority = 0x8000 >> BR_PORT_BITS; p->port_no = index; - p->flags = BR_LEARNING | BR_FLOOD; + p->flags = BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD; br_init_port(p); br_set_state(p, BR_STATE_DISABLED); br_stp_port_timer_init(p); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 190a5bc00f4a..e99037c6f7b7 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -169,10 +169,15 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u32(skb, IFLA_BRPORT_COST, p->path_cost) || nla_put_u8(skb, IFLA_BRPORT_MODE, mode) || nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(p->flags & BR_BPDU_GUARD)) || - nla_put_u8(skb, IFLA_BRPORT_PROTECT, !!(p->flags & BR_ROOT_BLOCK)) || - nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, !!(p->flags & BR_MULTICAST_FAST_LEAVE)) || + nla_put_u8(skb, IFLA_BRPORT_PROTECT, + !!(p->flags & BR_ROOT_BLOCK)) || + nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, + !!(p->flags & BR_MULTICAST_FAST_LEAVE)) || nla_put_u8(skb, IFLA_BRPORT_LEARNING, !!(p->flags & BR_LEARNING)) || - nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(p->flags & BR_FLOOD)) || + nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, + !!(p->flags & BR_FLOOD)) || + nla_put_u8(skb, IFLA_BRPORT_MCAST_FLOOD, + !!(p->flags & BR_MCAST_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(p->flags & BR_PROXYARP)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI, !!(p->flags & BR_PROXYARP_WIFI)) || @@ -630,6 +635,7 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK); br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING); br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD); + br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD); br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP); br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI); diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 1e04d4d44273..e657258e1f2c 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -171,6 +171,7 @@ BRPORT_ATTR_FLAG(learning, BR_LEARNING); BRPORT_ATTR_FLAG(unicast_flood, BR_FLOOD); BRPORT_ATTR_FLAG(proxyarp, BR_PROXYARP); BRPORT_ATTR_FLAG(proxyarp_wifi, BR_PROXYARP_WIFI); +BRPORT_ATTR_FLAG(multicast_flood, BR_MCAST_FLOOD); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf) -- cgit v1.2.3 From 0515e5999a466dfe6e1924f460da599bb6821487 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 1 Sep 2016 18:37:22 -0700 Subject: bpf: introduce BPF_PROG_TYPE_PERF_EVENT program type Introduce BPF_PROG_TYPE_PERF_EVENT programs that can be attached to HW and SW perf events (PERF_TYPE_HARDWARE and PERF_TYPE_SOFTWARE correspondingly in uapi/linux/perf_event.h) The program visible context meta structure is struct bpf_perf_event_data { struct pt_regs regs; __u64 sample_period; }; which is accessible directly from the program: int bpf_prog(struct bpf_perf_event_data *ctx) { ... ctx->sample_period ... ... ctx->regs.ip ... } The bpf verifier rewrites the accesses into kernel internal struct bpf_perf_event_data_kern which allows changing struct perf_sample_data without affecting bpf programs. New fields can be added to the end of struct bpf_perf_event_data in the future. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/perf_event.h | 5 +++ include/uapi/linux/Kbuild | 1 + include/uapi/linux/bpf.h | 1 + include/uapi/linux/bpf_perf_event.h | 18 +++++++++++ kernel/trace/bpf_trace.c | 61 +++++++++++++++++++++++++++++++++++++ 5 files changed, 86 insertions(+) create mode 100644 include/uapi/linux/bpf_perf_event.h (limited to 'include/uapi/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 2b6b43cc0dd5..97bfe62f30d7 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -788,6 +788,11 @@ struct perf_output_handle { int page; }; +struct bpf_perf_event_data_kern { + struct pt_regs *regs; + struct perf_sample_data *data; +}; + #ifdef CONFIG_CGROUP_PERF /* diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 185f8ea2702f..d0352a971ebd 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -71,6 +71,7 @@ header-y += binfmts.h header-y += blkpg.h header-y += blktrace_api.h header-y += bpf_common.h +header-y += bpf_perf_event.h header-y += bpf.h header-y += bpqether.h header-y += bsg.h diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e4c5a1baa993..f896dfac4ac0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -95,6 +95,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SCHED_ACT, BPF_PROG_TYPE_TRACEPOINT, BPF_PROG_TYPE_XDP, + BPF_PROG_TYPE_PERF_EVENT, }; #define BPF_PSEUDO_MAP_FD 1 diff --git a/include/uapi/linux/bpf_perf_event.h b/include/uapi/linux/bpf_perf_event.h new file mode 100644 index 000000000000..067427259820 --- /dev/null +++ b/include/uapi/linux/bpf_perf_event.h @@ -0,0 +1,18 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#ifndef _UAPI__LINUX_BPF_PERF_EVENT_H__ +#define _UAPI__LINUX_BPF_PERF_EVENT_H__ + +#include +#include + +struct bpf_perf_event_data { + struct pt_regs regs; + __u64 sample_period; +}; + +#endif /* _UAPI__LINUX_BPF_PERF_EVENT_H__ */ diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index ad35213b8405..d3869b03d9fe 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1,4 +1,5 @@ /* Copyright (c) 2011-2015 PLUMgrid, http://plumgrid.com + * Copyright (c) 2016 Facebook * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -8,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -552,10 +554,69 @@ static struct bpf_prog_type_list tracepoint_tl = { .type = BPF_PROG_TYPE_TRACEPOINT, }; +static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type, + enum bpf_reg_type *reg_type) +{ + if (off < 0 || off >= sizeof(struct bpf_perf_event_data)) + return false; + if (type != BPF_READ) + return false; + if (off % size != 0) + return false; + if (off == offsetof(struct bpf_perf_event_data, sample_period)) { + if (size != sizeof(u64)) + return false; + } else { + if (size != sizeof(long)) + return false; + } + return true; +} + +static u32 pe_prog_convert_ctx_access(enum bpf_access_type type, int dst_reg, + int src_reg, int ctx_off, + struct bpf_insn *insn_buf, + struct bpf_prog *prog) +{ + struct bpf_insn *insn = insn_buf; + + switch (ctx_off) { + case offsetof(struct bpf_perf_event_data, sample_period): + BUILD_BUG_ON(FIELD_SIZEOF(struct perf_sample_data, period) != sizeof(u64)); + *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct bpf_perf_event_data_kern, data)), + dst_reg, src_reg, + offsetof(struct bpf_perf_event_data_kern, data)); + *insn++ = BPF_LDX_MEM(BPF_DW, dst_reg, dst_reg, + offsetof(struct perf_sample_data, period)); + break; + default: + *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct bpf_perf_event_data_kern, regs)), + dst_reg, src_reg, + offsetof(struct bpf_perf_event_data_kern, regs)); + *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(sizeof(long)), + dst_reg, dst_reg, ctx_off); + break; + } + + return insn - insn_buf; +} + +static const struct bpf_verifier_ops perf_event_prog_ops = { + .get_func_proto = tp_prog_func_proto, + .is_valid_access = pe_prog_is_valid_access, + .convert_ctx_access = pe_prog_convert_ctx_access, +}; + +static struct bpf_prog_type_list perf_event_tl = { + .ops = &perf_event_prog_ops, + .type = BPF_PROG_TYPE_PERF_EVENT, +}; + static int __init register_kprobe_prog_ops(void) { bpf_register_prog_type(&kprobe_tl); bpf_register_prog_type(&tracepoint_tl); + bpf_register_prog_type(&perf_event_tl); return 0; } late_initcall(register_kprobe_prog_ops); -- cgit v1.2.3 From ecc6569f3503b39f45bc6b86197b5e0a8533fb72 Mon Sep 17 00:00:00 2001 From: Gao Feng Date: Thu, 25 Aug 2016 23:08:11 +0800 Subject: netfilter: gre: Use consistent GRE_* macros instead of ones defined by netfilter. There are already some GRE_* macros in kernel, so it is unnecessary to define these macros. And remove some useless macros Signed-off-by: Gao Feng Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_proto_gre.h | 22 ++-------------------- include/uapi/linux/if_tunnel.h | 1 + net/ipv4/netfilter/nf_nat_proto_gre.c | 4 ++-- net/netfilter/nf_conntrack_proto_gre.c | 4 ++-- 4 files changed, 7 insertions(+), 24 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h index df78dc2b5524..0189747f2691 100644 --- a/include/linux/netfilter/nf_conntrack_proto_gre.h +++ b/include/linux/netfilter/nf_conntrack_proto_gre.h @@ -1,29 +1,11 @@ #ifndef _CONNTRACK_PROTO_GRE_H #define _CONNTRACK_PROTO_GRE_H #include +#include +#include /* GRE PROTOCOL HEADER */ -/* GRE Version field */ -#define GRE_VERSION_1701 0x0 -#define GRE_VERSION_PPTP 0x1 - -/* GRE Protocol field */ -#define GRE_PROTOCOL_PPTP 0x880B - -/* GRE Flags */ -#define GRE_FLAG_C 0x80 -#define GRE_FLAG_R 0x40 -#define GRE_FLAG_K 0x20 -#define GRE_FLAG_S 0x10 -#define GRE_FLAG_A 0x80 - -#define GRE_IS_C(f) ((f)&GRE_FLAG_C) -#define GRE_IS_R(f) ((f)&GRE_FLAG_R) -#define GRE_IS_K(f) ((f)&GRE_FLAG_K) -#define GRE_IS_S(f) ((f)&GRE_FLAG_S) -#define GRE_IS_A(f) ((f)&GRE_FLAG_A) - /* GRE is a mess: Four different standards */ struct gre_hdr { #if defined(__LITTLE_ENDIAN_BITFIELD) diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 9865c8caedde..fb7337d6b985 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -39,6 +39,7 @@ #define GRE_IS_REC(f) ((f) & GRE_REC) #define GRE_IS_ACK(f) ((f) & GRE_ACK) +#define GRE_VERSION_0 __cpu_to_be16(0x0000) #define GRE_VERSION_1 __cpu_to_be16(0x0001) #define GRE_PROTO_PPP __cpu_to_be16(0x880b) #define GRE_PPTP_KEY_MASK __cpu_to_be32(0xffff) diff --git a/net/ipv4/netfilter/nf_nat_proto_gre.c b/net/ipv4/netfilter/nf_nat_proto_gre.c index 9414923f1e15..93198d71dbb6 100644 --- a/net/ipv4/netfilter/nf_nat_proto_gre.c +++ b/net/ipv4/netfilter/nf_nat_proto_gre.c @@ -104,11 +104,11 @@ gre_manip_pkt(struct sk_buff *skb, if (maniptype != NF_NAT_MANIP_DST) return true; switch (greh->version) { - case GRE_VERSION_1701: + case ntohs(GRE_VERSION_0): /* We do not currently NAT any GREv0 packets. * Try to behave like "nf_nat_proto_unknown" */ break; - case GRE_VERSION_PPTP: + case ntohs(GRE_VERSION_1): pr_debug("call_id -> 0x%04x\n", ntohs(tuple->dst.u.gre.key)); pgreh->call_id = tuple->dst.u.gre.key; break; diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index a96451a7af20..deb239a014e4 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -200,7 +200,7 @@ static bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, /* first only delinearize old RFC1701 GRE header */ grehdr = skb_header_pointer(skb, dataoff, sizeof(_grehdr), &_grehdr); - if (!grehdr || grehdr->version != GRE_VERSION_PPTP) { + if (!grehdr || grehdr->version != ntohs(GRE_VERSION_1)) { /* try to behave like "nf_conntrack_proto_generic" */ tuple->src.u.all = 0; tuple->dst.u.all = 0; @@ -212,7 +212,7 @@ static bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, if (!pgrehdr) return true; - if (ntohs(grehdr->protocol) != GRE_PROTOCOL_PPTP) { + if (grehdr->protocol != GRE_PROTO_PPP) { pr_debug("GRE_VERSION_PPTP but unknown proto\n"); return false; } -- cgit v1.2.3 From 0d9932b2875f568d679f2af33ce610da3903ac11 Mon Sep 17 00:00:00 2001 From: Laura Garcia Liebana Date: Fri, 2 Sep 2016 15:05:57 +0200 Subject: netfilter: nft_numgen: rename until attribute by modulus The _until_ attribute is renamed to _modulus_ as the behaviour is similar to other expresions with number limits (ex. nft_hash). Renaming is possible because there isn't a kernel release yet with these changes. Signed-off-by: Laura Garcia Liebana Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 4 ++-- net/netfilter/nft_numgen.c | 30 +++++++++++++++--------------- 2 files changed, 17 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 28ce01d79707..24161e25576d 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1126,13 +1126,13 @@ enum nft_trace_types { * enum nft_ng_attributes - nf_tables number generator expression netlink attributes * * @NFTA_NG_DREG: destination register (NLA_U32) - * @NFTA_NG_UNTIL: source value to increment the counter until reset (NLA_U32) + * @NFTA_NG_MODULUS: maximum counter value (NLA_U32) * @NFTA_NG_TYPE: operation type (NLA_U32) */ enum nft_ng_attributes { NFTA_NG_UNSPEC, NFTA_NG_DREG, - NFTA_NG_UNTIL, + NFTA_NG_MODULUS, NFTA_NG_TYPE, __NFTA_NG_MAX }; diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c index 294745ecb0fc..f51a3ede3932 100644 --- a/net/netfilter/nft_numgen.c +++ b/net/netfilter/nft_numgen.c @@ -21,7 +21,7 @@ static DEFINE_PER_CPU(struct rnd_state, nft_numgen_prandom_state); struct nft_ng_inc { enum nft_registers dreg:8; - u32 until; + u32 modulus; atomic_t counter; }; @@ -34,7 +34,7 @@ static void nft_ng_inc_eval(const struct nft_expr *expr, do { oval = atomic_read(&priv->counter); - nval = (oval + 1 < priv->until) ? oval + 1 : 0; + nval = (oval + 1 < priv->modulus) ? oval + 1 : 0; } while (atomic_cmpxchg(&priv->counter, oval, nval) != oval); memcpy(®s->data[priv->dreg], &priv->counter, sizeof(u32)); @@ -42,7 +42,7 @@ static void nft_ng_inc_eval(const struct nft_expr *expr, static const struct nla_policy nft_ng_policy[NFTA_NG_MAX + 1] = { [NFTA_NG_DREG] = { .type = NLA_U32 }, - [NFTA_NG_UNTIL] = { .type = NLA_U32 }, + [NFTA_NG_MODULUS] = { .type = NLA_U32 }, [NFTA_NG_TYPE] = { .type = NLA_U32 }, }; @@ -52,8 +52,8 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx, { struct nft_ng_inc *priv = nft_expr_priv(expr); - priv->until = ntohl(nla_get_be32(tb[NFTA_NG_UNTIL])); - if (priv->until == 0) + priv->modulus = ntohl(nla_get_be32(tb[NFTA_NG_MODULUS])); + if (priv->modulus == 0) return -ERANGE; priv->dreg = nft_parse_register(tb[NFTA_NG_DREG]); @@ -64,11 +64,11 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx, } static int nft_ng_dump(struct sk_buff *skb, enum nft_registers dreg, - u32 until, enum nft_ng_types type) + u32 modulus, enum nft_ng_types type) { if (nft_dump_register(skb, NFTA_NG_DREG, dreg)) goto nla_put_failure; - if (nla_put_be32(skb, NFTA_NG_UNTIL, htonl(until))) + if (nla_put_be32(skb, NFTA_NG_MODULUS, htonl(modulus))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_NG_TYPE, htonl(type))) goto nla_put_failure; @@ -83,12 +83,12 @@ static int nft_ng_inc_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_ng_inc *priv = nft_expr_priv(expr); - return nft_ng_dump(skb, priv->dreg, priv->until, NFT_NG_INCREMENTAL); + return nft_ng_dump(skb, priv->dreg, priv->modulus, NFT_NG_INCREMENTAL); } struct nft_ng_random { enum nft_registers dreg:8; - u32 until; + u32 modulus; }; static void nft_ng_random_eval(const struct nft_expr *expr, @@ -99,7 +99,7 @@ static void nft_ng_random_eval(const struct nft_expr *expr, struct rnd_state *state = this_cpu_ptr(&nft_numgen_prandom_state); regs->data[priv->dreg] = reciprocal_scale(prandom_u32_state(state), - priv->until); + priv->modulus); } static int nft_ng_random_init(const struct nft_ctx *ctx, @@ -108,8 +108,8 @@ static int nft_ng_random_init(const struct nft_ctx *ctx, { struct nft_ng_random *priv = nft_expr_priv(expr); - priv->until = ntohl(nla_get_be32(tb[NFTA_NG_UNTIL])); - if (priv->until == 0) + priv->modulus = ntohl(nla_get_be32(tb[NFTA_NG_MODULUS])); + if (priv->modulus == 0) return -ERANGE; prandom_init_once(&nft_numgen_prandom_state); @@ -124,7 +124,7 @@ static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_ng_random *priv = nft_expr_priv(expr); - return nft_ng_dump(skb, priv->dreg, priv->until, NFT_NG_RANDOM); + return nft_ng_dump(skb, priv->dreg, priv->modulus, NFT_NG_RANDOM); } static struct nft_expr_type nft_ng_type; @@ -149,8 +149,8 @@ nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { u32 type; - if (!tb[NFTA_NG_DREG] || - !tb[NFTA_NG_UNTIL] || + if (!tb[NFTA_NG_DREG] || + !tb[NFTA_NG_MODULUS] || !tb[NFTA_NG_TYPE]) return ERR_PTR(-EINVAL); -- cgit v1.2.3 From d545caca827b65aab557a9e9dcdcf1e5a3823c2d Mon Sep 17 00:00:00 2001 From: Lorenzo Colitti Date: Thu, 8 Sep 2016 00:42:25 +0900 Subject: net: inet: diag: expose the socket mark to privileged processes. This adds the capability for a process that has CAP_NET_ADMIN on a socket to see the socket mark in socket dumps. Commit a52e95abf772 ("net: diag: allow socket bytecode filters to match socket marks") recently gave privileged processes the ability to filter socket dumps based on mark. This patch is complementary: it ensures that the mark is also passed to userspace in the socket's netlink attributes. It is useful for tools like ss which display information about sockets. Tested: https://android-review.googlesource.com/270210 Signed-off-by: Lorenzo Colitti Signed-off-by: David S. Miller --- include/linux/inet_diag.h | 4 ++-- include/uapi/linux/inet_diag.h | 1 + net/ipv4/inet_diag.c | 49 ++++++++++++++++++++++++++++-------------- net/ipv4/udp_diag.c | 10 +++++---- net/sctp/sctp_diag.c | 20 +++++++++++------ 5 files changed, 56 insertions(+), 28 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index feb04ea20f11..65da430e260f 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -37,7 +37,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct sk_buff *skb, const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, u32 pid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh); + const struct nlmsghdr *unlh, bool net_admin); void inet_diag_dump_icsk(struct inet_hashinfo *h, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, @@ -56,7 +56,7 @@ void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk); int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, struct inet_diag_msg *r, int ext, - struct user_namespace *user_ns); + struct user_namespace *user_ns, bool net_admin); extern int inet_diag_register(const struct inet_diag_handler *handler); extern void inet_diag_unregister(const struct inet_diag_handler *handler); diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index 5581206a08ae..b5c366f87b3e 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -123,6 +123,7 @@ enum { INET_DIAG_LOCALS, INET_DIAG_PEERS, INET_DIAG_PAD, + INET_DIAG_MARK, __INET_DIAG_MAX, }; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index abfbe492ebfe..e4d16fc5bbb3 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -99,6 +99,7 @@ static size_t inet_sk_attr_size(void) + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ + nla_total_size(1) /* INET_DIAG_TOS */ + nla_total_size(1) /* INET_DIAG_TCLASS */ + + nla_total_size(4) /* INET_DIAG_MARK */ + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(sizeof(struct inet_diag_msg)) + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) @@ -109,7 +110,8 @@ static size_t inet_sk_attr_size(void) int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, struct inet_diag_msg *r, int ext, - struct user_namespace *user_ns) + struct user_namespace *user_ns, + bool net_admin) { const struct inet_sock *inet = inet_sk(sk); @@ -136,6 +138,9 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, } #endif + if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark)) + goto errout; + r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); r->idiag_inode = sock_i_ino(sk); @@ -149,7 +154,8 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct sk_buff *skb, const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, + bool net_admin) { const struct tcp_congestion_ops *ca_ops; const struct inet_diag_handler *handler; @@ -175,7 +181,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, r->idiag_timer = 0; r->idiag_retrans = 0; - if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns)) + if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns, net_admin)) goto errout; if (ext & (1 << (INET_DIAG_MEMINFO - 1))) { @@ -274,10 +280,11 @@ static int inet_csk_diag_fill(struct sock *sk, const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, + bool net_admin) { - return inet_sk_diag_fill(sk, inet_csk(sk), skb, req, - user_ns, portid, seq, nlmsg_flags, unlh); + return inet_sk_diag_fill(sk, inet_csk(sk), skb, req, user_ns, + portid, seq, nlmsg_flags, unlh, net_admin); } static int inet_twsk_diag_fill(struct sock *sk, @@ -319,8 +326,9 @@ static int inet_twsk_diag_fill(struct sock *sk, static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, bool net_admin) { + struct request_sock *reqsk = inet_reqsk(sk); struct inet_diag_msg *r; struct nlmsghdr *nlh; long tmo; @@ -334,7 +342,7 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, inet_diag_msg_common_fill(r, sk); r->idiag_state = TCP_SYN_RECV; r->idiag_timer = 1; - r->idiag_retrans = inet_reqsk(sk)->num_retrans; + r->idiag_retrans = reqsk->num_retrans; BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) != offsetof(struct sock, sk_cookie)); @@ -346,6 +354,10 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, r->idiag_uid = 0; r->idiag_inode = 0; + if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, + inet_rsk(reqsk)->ir_mark)) + return -EMSGSIZE; + nlmsg_end(skb, nlh); return 0; } @@ -354,7 +366,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, const struct inet_diag_req_v2 *r, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, bool net_admin) { if (sk->sk_state == TCP_TIME_WAIT) return inet_twsk_diag_fill(sk, skb, portid, seq, @@ -362,10 +374,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, if (sk->sk_state == TCP_NEW_SYN_RECV) return inet_req_diag_fill(sk, skb, portid, seq, - nlmsg_flags, unlh); + nlmsg_flags, unlh, net_admin); return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq, - nlmsg_flags, unlh); + nlmsg_flags, unlh, net_admin); } struct sock *inet_diag_find_one_icsk(struct net *net, @@ -435,7 +447,8 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, err = sk_diag_fill(sk, rep, req, sk_user_ns(NETLINK_CB(in_skb).sk), NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0, nlh); + nlh->nlmsg_seq, 0, nlh, + netlink_net_capable(in_skb, CAP_NET_ADMIN)); if (err < 0) { WARN_ON(err == -EMSGSIZE); nlmsg_free(rep); @@ -796,7 +809,8 @@ static int inet_csk_diag_dump(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, - const struct nlattr *bc) + const struct nlattr *bc, + bool net_admin) { if (!inet_diag_bc_sk(bc, sk)) return 0; @@ -804,7 +818,8 @@ static int inet_csk_diag_dump(struct sock *sk, return inet_csk_diag_fill(sk, skb, r, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); + cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh, + net_admin); } static void twsk_build_assert(void) @@ -840,6 +855,7 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, struct net *net = sock_net(skb->sk); int i, num, s_i, s_num; u32 idiag_states = r->idiag_states; + bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); if (idiag_states & TCPF_SYN_RECV) idiag_states |= TCPF_NEW_SYN_RECV; @@ -880,7 +896,8 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, cb->args[3] > 0) goto next_listen; - if (inet_csk_diag_dump(sk, skb, cb, r, bc) < 0) { + if (inet_csk_diag_dump(sk, skb, cb, r, + bc, net_admin) < 0) { spin_unlock_bh(&ilb->lock); goto done; } @@ -948,7 +965,7 @@ skip_listen_ht: sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->nlh); + cb->nlh, net_admin); if (res < 0) { spin_unlock_bh(lock); goto done; diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 58b79c0c0d69..9a89c10a55f0 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -20,7 +20,7 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *req, - struct nlattr *bc) + struct nlattr *bc, bool net_admin) { if (!inet_diag_bc_sk(bc, sk)) return 0; @@ -28,7 +28,7 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, return inet_sk_diag_fill(sk, NULL, skb, req, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); + cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh, net_admin); } static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, @@ -76,7 +76,8 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, err = inet_sk_diag_fill(sk, NULL, rep, req, sk_user_ns(NETLINK_CB(in_skb).sk), NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0, nlh); + nlh->nlmsg_seq, 0, nlh, + netlink_net_capable(in_skb, CAP_NET_ADMIN)); if (err < 0) { WARN_ON(err == -EMSGSIZE); kfree_skb(rep); @@ -97,6 +98,7 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, struct nlattr *bc) { + bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); struct net *net = sock_net(skb->sk); int num, s_num, slot, s_slot; @@ -132,7 +134,7 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, r->id.idiag_dport) goto next; - if (sk_diag_dump(sk, skb, cb, r, bc) < 0) { + if (sk_diag_dump(sk, skb, cb, r, bc, net_admin) < 0) { spin_unlock_bh(&hslot->lock); goto done; } diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c index f3508aa75815..807158e32f5f 100644 --- a/net/sctp/sctp_diag.c +++ b/net/sctp/sctp_diag.c @@ -106,7 +106,8 @@ static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc, const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, int portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, + bool net_admin) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct list_head *addr_list; @@ -133,7 +134,7 @@ static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc, r->idiag_retrans = 0; } - if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns)) + if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns, net_admin)) goto errout; if (ext & (1 << (INET_DIAG_SKMEMINFO - 1))) { @@ -203,6 +204,7 @@ struct sctp_comm_param { struct netlink_callback *cb; const struct inet_diag_req_v2 *r; const struct nlmsghdr *nlh; + bool net_admin; }; static size_t inet_assoc_attr_size(struct sctp_association *asoc) @@ -219,6 +221,7 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc) + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ + nla_total_size(1) /* INET_DIAG_TOS */ + nla_total_size(1) /* INET_DIAG_TCLASS */ + + nla_total_size(4) /* INET_DIAG_MARK */ + nla_total_size(addrlen * asoc->peer.transport_count) + nla_total_size(addrlen * addrcnt) + nla_total_size(sizeof(struct inet_diag_meminfo)) @@ -256,7 +259,8 @@ static int sctp_tsp_dump_one(struct sctp_transport *tsp, void *p) err = inet_sctp_diag_fill(sk, assoc, rep, req, sk_user_ns(NETLINK_CB(in_skb).sk), NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0, nlh); + nlh->nlmsg_seq, 0, nlh, + commp->net_admin); release_sock(sk); if (err < 0) { WARN_ON(err == -EMSGSIZE); @@ -310,7 +314,8 @@ static int sctp_tsp_dump(struct sctp_transport *tsp, void *p) sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - NLM_F_MULTI, cb->nlh) < 0) { + NLM_F_MULTI, cb->nlh, + commp->net_admin) < 0) { cb->args[3] = 1; err = 2; goto release; @@ -320,7 +325,8 @@ static int sctp_tsp_dump(struct sctp_transport *tsp, void *p) if (inet_sctp_diag_fill(sk, assoc, skb, r, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, 0, cb->nlh) < 0) { + cb->nlh->nlmsg_seq, 0, cb->nlh, + commp->net_admin) < 0) { err = 2; goto release; } @@ -375,7 +381,7 @@ static int sctp_ep_dump(struct sctp_endpoint *ep, void *p) sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->nlh) < 0) { + cb->nlh, commp->net_admin) < 0) { err = 2; goto out; } @@ -412,6 +418,7 @@ static int sctp_diag_dump_one(struct sk_buff *in_skb, .skb = in_skb, .r = req, .nlh = nlh, + .net_admin = netlink_net_capable(in_skb, CAP_NET_ADMIN), }; if (req->sdiag_family == AF_INET) { @@ -447,6 +454,7 @@ static void sctp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, .skb = skb, .cb = cb, .r = r, + .net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN), }; /* eps hashtable dumps -- cgit v1.2.3 From 8c146bb9d59aa2ac45222171916ece186c4b3943 Mon Sep 17 00:00:00 2001 From: Thomas F Herbert Date: Wed, 7 Sep 2016 12:56:57 -0400 Subject: openvswitch: 802.1ad uapi changes. openvswitch: Add support for 8021.AD Change the description of the VLAN tpid field. Signed-off-by: Thomas F Herbert Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 54c3b4f4aceb..59ed3992c760 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -605,13 +605,13 @@ struct ovs_action_push_mpls { * @vlan_tci: Tag control identifier (TCI) to push. The CFI bit must be set * (but it will not be set in the 802.1Q header that is pushed). * - * The @vlan_tpid value is typically %ETH_P_8021Q. The only acceptable TPID - * values are those that the kernel module also parses as 802.1Q headers, to - * prevent %OVS_ACTION_ATTR_PUSH_VLAN followed by %OVS_ACTION_ATTR_POP_VLAN - * from having surprising results. + * The @vlan_tpid value is typically %ETH_P_8021Q or %ETH_P_8021AD. + * The only acceptable TPID values are those that the kernel module also parses + * as 802.1Q or 802.1AD headers, to prevent %OVS_ACTION_ATTR_PUSH_VLAN followed + * by %OVS_ACTION_ATTR_POP_VLAN from having surprising results. */ struct ovs_action_push_vlan { - __be16 vlan_tpid; /* 802.1Q TPID. */ + __be16 vlan_tpid; /* 802.1Q or 802.1ad TPID. */ __be16 vlan_tci; /* 802.1Q TCI (VLAN ID and priority). */ }; @@ -721,9 +721,10 @@ enum ovs_nat_attr { * is copied from the value to the packet header field, rest of the bits are * left unchanged. The non-masked value bits must be passed in as zeroes. * Masking is not supported for the %OVS_KEY_ATTR_TUNNEL attribute. - * @OVS_ACTION_ATTR_PUSH_VLAN: Push a new outermost 802.1Q header onto the - * packet. - * @OVS_ACTION_ATTR_POP_VLAN: Pop the outermost 802.1Q header off the packet. + * @OVS_ACTION_ATTR_PUSH_VLAN: Push a new outermost 802.1Q or 802.1ad header + * onto the packet. + * @OVS_ACTION_ATTR_POP_VLAN: Pop the outermost 802.1Q or 802.1ad header + * from the packet. * @OVS_ACTION_ATTR_SAMPLE: Probabilitically executes actions, as specified in * the nested %OVS_SAMPLE_ATTR_* attributes. * @OVS_ACTION_ATTR_PUSH_MPLS: Push a new MPLS label stack entry onto the -- cgit v1.2.3 From 34a3d4b2d1f1b7c81af79f6f93a6cef4c3a0f54a Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Thu, 8 Sep 2016 13:55:56 -0400 Subject: xfrm: fix header file comment reference to struct xfrm_replay_state_esn Reported-by: Paul Wouters Signed-off-by: Richard Guy Briggs Signed-off-by: Steffen Klassert --- include/uapi/linux/xfrm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 143338978b48..1fc62b239f1b 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -298,7 +298,7 @@ enum xfrm_attr_type_t { XFRMA_ALG_AUTH_TRUNC, /* struct xfrm_algo_auth */ XFRMA_MARK, /* struct xfrm_mark */ XFRMA_TFCPAD, /* __u32 */ - XFRMA_REPLAY_ESN_VAL, /* struct xfrm_replay_esn */ + XFRMA_REPLAY_ESN_VAL, /* struct xfrm_replay_state_esn */ XFRMA_SA_EXTRA_FLAGS, /* __u32 */ XFRMA_PROTO, /* __u8 */ XFRMA_ADDRESS_FILTER, /* struct xfrm_address_filter */ -- cgit v1.2.3 From bc3103f1ed405de587fa43d8b0671e615505a700 Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Thu, 8 Sep 2016 16:23:47 +0300 Subject: net/sched: cls_flower: Classify packet in ip tunnels Introduce classifying by metadata extracted by the tunnel device. Outer header fields - source/dest ip and tunnel id, are extracted from the metadata when classifying. For example, the following will add a filter on the ingress Qdisc of shared vxlan device named 'vxlan0'. To forward packets with outer src ip 11.11.0.2, dst ip 11.11.0.1 and tunnel id 11. The packets will be forwarded to tap device 'vnet0' (after metadata is released): $ tc filter add dev vxlan0 protocol ip parent ffff: \ flower \ enc_src_ip 11.11.0.2 \ enc_dst_ip 11.11.0.1 \ enc_key_id 11 \ dst_ip 11.11.11.1 \ action tunnel_key release \ action mirred egress redirect dev vnet0 The action tunnel_key, will be introduced in the next patch in this series. Signed-off-by: Amir Vadai Signed-off-by: Hadar Hen Zion Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 11 +++++ net/sched/cls_flower.c | 100 ++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 110 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 51b5b247fb5a..f9c287c67eae 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -431,6 +431,17 @@ enum { TCA_FLOWER_KEY_VLAN_ID, TCA_FLOWER_KEY_VLAN_PRIO, TCA_FLOWER_KEY_VLAN_ETH_TYPE, + + TCA_FLOWER_KEY_ENC_KEY_ID, /* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_SRC, /* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,/* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_DST, /* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,/* be32 */ + TCA_FLOWER_KEY_ENC_IPV6_SRC, /* struct in6_addr */ + TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,/* struct in6_addr */ + TCA_FLOWER_KEY_ENC_IPV6_DST, /* struct in6_addr */ + TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,/* struct in6_addr */ + __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index cf9ad5b50889..b084b2aab2d7 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -23,9 +23,13 @@ #include #include +#include +#include + struct fl_flow_key { int indev_ifindex; struct flow_dissector_key_control control; + struct flow_dissector_key_control enc_control; struct flow_dissector_key_basic basic; struct flow_dissector_key_eth_addrs eth; struct flow_dissector_key_vlan vlan; @@ -35,6 +39,11 @@ struct fl_flow_key { struct flow_dissector_key_ipv6_addrs ipv6; }; struct flow_dissector_key_ports tp; + struct flow_dissector_key_keyid enc_key_id; + union { + struct flow_dissector_key_ipv4_addrs enc_ipv4; + struct flow_dissector_key_ipv6_addrs enc_ipv6; + }; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ struct fl_flow_mask_range { @@ -124,11 +133,31 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct cls_fl_filter *f; struct fl_flow_key skb_key; struct fl_flow_key skb_mkey; + struct ip_tunnel_info *info; if (!atomic_read(&head->ht.nelems)) return -1; fl_clear_masked_range(&skb_key, &head->mask); + + info = skb_tunnel_info(skb); + if (info) { + struct ip_tunnel_key *key = &info->key; + + switch (ip_tunnel_info_af(info)) { + case AF_INET: + skb_key.enc_ipv4.src = key->u.ipv4.src; + skb_key.enc_ipv4.dst = key->u.ipv4.dst; + break; + case AF_INET6: + skb_key.enc_ipv6.src = key->u.ipv6.src; + skb_key.enc_ipv6.dst = key->u.ipv6.dst; + break; + } + + skb_key.enc_key_id.keyid = tunnel_id_to_key32(key->tun_id); + } + skb_key.indev_ifindex = skb->skb_iif; /* skb_flow_dissect() does not set n_proto in case an unknown protocol, * so do it rather here. @@ -297,7 +326,15 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_VLAN_ID] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_VLAN_PRIO] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_VLAN_ETH_TYPE] = { .type = NLA_U16 }, - + [TCA_FLOWER_KEY_ENC_KEY_ID] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_ENC_IPV4_SRC] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_ENC_IPV4_DST] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_ENC_IPV4_DST_MASK] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_ENC_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, + [TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK] = { .len = sizeof(struct in6_addr) }, + [TCA_FLOWER_KEY_ENC_IPV6_DST] = { .len = sizeof(struct in6_addr) }, + [TCA_FLOWER_KEY_ENC_IPV6_DST_MASK] = { .len = sizeof(struct in6_addr) }, }; static void fl_set_key_val(struct nlattr **tb, @@ -409,6 +446,40 @@ static int fl_set_key(struct net *net, struct nlattr **tb, sizeof(key->tp.dst)); } + if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] || + tb[TCA_FLOWER_KEY_ENC_IPV4_DST]) { + key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + fl_set_key_val(tb, &key->enc_ipv4.src, + TCA_FLOWER_KEY_ENC_IPV4_SRC, + &mask->enc_ipv4.src, + TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK, + sizeof(key->enc_ipv4.src)); + fl_set_key_val(tb, &key->enc_ipv4.dst, + TCA_FLOWER_KEY_ENC_IPV4_DST, + &mask->enc_ipv4.dst, + TCA_FLOWER_KEY_ENC_IPV4_DST_MASK, + sizeof(key->enc_ipv4.dst)); + } + + if (tb[TCA_FLOWER_KEY_ENC_IPV6_SRC] || + tb[TCA_FLOWER_KEY_ENC_IPV6_DST]) { + key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + fl_set_key_val(tb, &key->enc_ipv6.src, + TCA_FLOWER_KEY_ENC_IPV6_SRC, + &mask->enc_ipv6.src, + TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK, + sizeof(key->enc_ipv6.src)); + fl_set_key_val(tb, &key->enc_ipv6.dst, + TCA_FLOWER_KEY_ENC_IPV6_DST, + &mask->enc_ipv6.dst, + TCA_FLOWER_KEY_ENC_IPV6_DST_MASK, + sizeof(key->enc_ipv6.dst)); + } + + fl_set_key_val(tb, &key->enc_key_id.keyid, TCA_FLOWER_KEY_ENC_KEY_ID, + &mask->enc_key_id.keyid, TCA_FLOWER_KEY_ENC_KEY_ID, + sizeof(key->enc_key_id.keyid)); + return 0; } @@ -821,6 +892,33 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, sizeof(key->tp.dst)))) goto nla_put_failure; + if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS && + (fl_dump_key_val(skb, &key->enc_ipv4.src, + TCA_FLOWER_KEY_ENC_IPV4_SRC, &mask->enc_ipv4.src, + TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK, + sizeof(key->enc_ipv4.src)) || + fl_dump_key_val(skb, &key->enc_ipv4.dst, + TCA_FLOWER_KEY_ENC_IPV4_DST, &mask->enc_ipv4.dst, + TCA_FLOWER_KEY_ENC_IPV4_DST_MASK, + sizeof(key->enc_ipv4.dst)))) + goto nla_put_failure; + else if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS && + (fl_dump_key_val(skb, &key->enc_ipv6.src, + TCA_FLOWER_KEY_ENC_IPV6_SRC, &mask->enc_ipv6.src, + TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK, + sizeof(key->enc_ipv6.src)) || + fl_dump_key_val(skb, &key->enc_ipv6.dst, + TCA_FLOWER_KEY_ENC_IPV6_DST, + &mask->enc_ipv6.dst, + TCA_FLOWER_KEY_ENC_IPV6_DST_MASK, + sizeof(key->enc_ipv6.dst)))) + goto nla_put_failure; + + if (fl_dump_key_val(skb, &key->enc_key_id, TCA_FLOWER_KEY_ENC_KEY_ID, + &mask->enc_key_id, TCA_FLOWER_KEY_ENC_KEY_ID, + sizeof(key->enc_key_id))) + goto nla_put_failure; + nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags); if (tcf_exts_dump(skb, &f->exts)) -- cgit v1.2.3 From d0f6dd8a914f42c6f1a3a8c08caa16559d3d9a1b Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Thu, 8 Sep 2016 16:23:48 +0300 Subject: net/sched: Introduce act_tunnel_key This action could be used before redirecting packets to a shared tunnel device, or when redirecting packets arriving from a such a device. The action will release the metadata created by the tunnel device (decap), or set the metadata with the specified values for encap operation. For example, the following flower filter will forward all ICMP packets destined to 11.11.11.2 through the shared vxlan device 'vxlan0'. Before redirecting, a metadata for the vxlan tunnel is created using the tunnel_key action and it's arguments: $ tc filter add dev net0 protocol ip parent ffff: \ flower \ ip_proto 1 \ dst_ip 11.11.11.2 \ action tunnel_key set \ src_ip 11.11.0.1 \ dst_ip 11.11.0.2 \ id 11 \ action mirred egress redirect dev vxlan0 Signed-off-by: Amir Vadai Signed-off-by: Hadar Hen Zion Reviewed-by: Shmulik Ladkani Acked-by: Jamal Hadi Salim Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tc_act/tc_tunnel_key.h | 30 +++ include/uapi/linux/tc_act/tc_tunnel_key.h | 41 ++++ net/sched/Kconfig | 11 + net/sched/Makefile | 1 + net/sched/act_tunnel_key.c | 351 ++++++++++++++++++++++++++++++ 5 files changed, 434 insertions(+) create mode 100644 include/net/tc_act/tc_tunnel_key.h create mode 100644 include/uapi/linux/tc_act/tc_tunnel_key.h create mode 100644 net/sched/act_tunnel_key.c (limited to 'include/uapi/linux') diff --git a/include/net/tc_act/tc_tunnel_key.h b/include/net/tc_act/tc_tunnel_key.h new file mode 100644 index 000000000000..253f8da6c2a6 --- /dev/null +++ b/include/net/tc_act/tc_tunnel_key.h @@ -0,0 +1,30 @@ +/* + * Copyright (c) 2016, Amir Vadai + * Copyright (c) 2016, Mellanox Technologies. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __NET_TC_TUNNEL_KEY_H +#define __NET_TC_TUNNEL_KEY_H + +#include + +struct tcf_tunnel_key_params { + struct rcu_head rcu; + int tcft_action; + int action; + struct metadata_dst *tcft_enc_metadata; +}; + +struct tcf_tunnel_key { + struct tc_action common; + struct tcf_tunnel_key_params __rcu *params; +}; + +#define to_tunnel_key(a) ((struct tcf_tunnel_key *)a) + +#endif /* __NET_TC_TUNNEL_KEY_H */ diff --git a/include/uapi/linux/tc_act/tc_tunnel_key.h b/include/uapi/linux/tc_act/tc_tunnel_key.h new file mode 100644 index 000000000000..890106ff16e6 --- /dev/null +++ b/include/uapi/linux/tc_act/tc_tunnel_key.h @@ -0,0 +1,41 @@ +/* + * Copyright (c) 2016, Amir Vadai + * Copyright (c) 2016, Mellanox Technologies. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __LINUX_TC_TUNNEL_KEY_H +#define __LINUX_TC_TUNNEL_KEY_H + +#include + +#define TCA_ACT_TUNNEL_KEY 17 + +#define TCA_TUNNEL_KEY_ACT_SET 1 +#define TCA_TUNNEL_KEY_ACT_RELEASE 2 + +struct tc_tunnel_key { + tc_gen; + int t_action; +}; + +enum { + TCA_TUNNEL_KEY_UNSPEC, + TCA_TUNNEL_KEY_TM, + TCA_TUNNEL_KEY_PARMS, + TCA_TUNNEL_KEY_ENC_IPV4_SRC, /* be32 */ + TCA_TUNNEL_KEY_ENC_IPV4_DST, /* be32 */ + TCA_TUNNEL_KEY_ENC_IPV6_SRC, /* struct in6_addr */ + TCA_TUNNEL_KEY_ENC_IPV6_DST, /* struct in6_addr */ + TCA_TUNNEL_KEY_ENC_KEY_ID, /* be64 */ + TCA_TUNNEL_KEY_PAD, + __TCA_TUNNEL_KEY_MAX, +}; + +#define TCA_TUNNEL_KEY_MAX (__TCA_TUNNEL_KEY_MAX - 1) + +#endif diff --git a/net/sched/Kconfig b/net/sched/Kconfig index ccf931b3b94c..72e3426fa48f 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -761,6 +761,17 @@ config NET_ACT_IFE To compile this code as a module, choose M here: the module will be called act_ife. +config NET_ACT_TUNNEL_KEY + tristate "IP tunnel metadata manipulation" + depends on NET_CLS_ACT + ---help--- + Say Y here to set/release ip tunnel metadata. + + If unsure, say N. + + To compile this code as a module, choose M here: the + module will be called act_tunnel_key. + config NET_IFE_SKBMARK tristate "Support to encoding decoding skb mark on IFE action" depends on NET_ACT_IFE diff --git a/net/sched/Makefile b/net/sched/Makefile index ae088a5a9d95..b9d046b9535a 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -22,6 +22,7 @@ obj-$(CONFIG_NET_ACT_CONNMARK) += act_connmark.o obj-$(CONFIG_NET_ACT_IFE) += act_ife.o obj-$(CONFIG_NET_IFE_SKBMARK) += act_meta_mark.o obj-$(CONFIG_NET_IFE_SKBPRIO) += act_meta_skbprio.o +obj-$(CONFIG_NET_ACT_TUNNEL_KEY)+= act_tunnel_key.o obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o obj-$(CONFIG_NET_SCH_CBQ) += sch_cbq.o obj-$(CONFIG_NET_SCH_HTB) += sch_htb.o diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c new file mode 100644 index 000000000000..dceff7412dc3 --- /dev/null +++ b/net/sched/act_tunnel_key.c @@ -0,0 +1,351 @@ +/* + * Copyright (c) 2016, Amir Vadai + * Copyright (c) 2016, Mellanox Technologies. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#define TUNNEL_KEY_TAB_MASK 15 + +static int tunnel_key_net_id; +static struct tc_action_ops act_tunnel_key_ops; + +static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_tunnel_key *t = to_tunnel_key(a); + struct tcf_tunnel_key_params *params; + int action; + + rcu_read_lock(); + + params = rcu_dereference(t->params); + + tcf_lastuse_update(&t->tcf_tm); + bstats_cpu_update(this_cpu_ptr(t->common.cpu_bstats), skb); + action = params->action; + + switch (params->tcft_action) { + case TCA_TUNNEL_KEY_ACT_RELEASE: + skb_dst_drop(skb); + break; + case TCA_TUNNEL_KEY_ACT_SET: + skb_dst_drop(skb); + skb_dst_set(skb, dst_clone(¶ms->tcft_enc_metadata->dst)); + break; + default: + WARN_ONCE(1, "Bad tunnel_key action %d.\n", + params->tcft_action); + break; + } + + rcu_read_unlock(); + + return action; +} + +static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { + [TCA_TUNNEL_KEY_PARMS] = { .len = sizeof(struct tc_tunnel_key) }, + [TCA_TUNNEL_KEY_ENC_IPV4_SRC] = { .type = NLA_U32 }, + [TCA_TUNNEL_KEY_ENC_IPV4_DST] = { .type = NLA_U32 }, + [TCA_TUNNEL_KEY_ENC_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, + [TCA_TUNNEL_KEY_ENC_IPV6_DST] = { .len = sizeof(struct in6_addr) }, + [TCA_TUNNEL_KEY_ENC_KEY_ID] = { .type = NLA_U32 }, +}; + +static int tunnel_key_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action **a, + int ovr, int bind) +{ + struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); + struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1]; + struct tcf_tunnel_key_params *params_old; + struct tcf_tunnel_key_params *params_new; + struct metadata_dst *metadata = NULL; + struct tc_tunnel_key *parm; + struct tcf_tunnel_key *t; + bool exists = false; + __be64 key_id; + int ret = 0; + int err; + + if (!nla) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_TUNNEL_KEY_MAX, nla, tunnel_key_policy); + if (err < 0) + return err; + + if (!tb[TCA_TUNNEL_KEY_PARMS]) + return -EINVAL; + + parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]); + exists = tcf_hash_check(tn, parm->index, a, bind); + if (exists && bind) + return 0; + + switch (parm->t_action) { + case TCA_TUNNEL_KEY_ACT_RELEASE: + break; + case TCA_TUNNEL_KEY_ACT_SET: + if (!tb[TCA_TUNNEL_KEY_ENC_KEY_ID]) { + ret = -EINVAL; + goto err_out; + } + + key_id = key32_to_tunnel_id(nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID])); + + if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] && + tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) { + __be32 saddr; + __be32 daddr; + + saddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC]); + daddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]); + + metadata = __ip_tun_set_dst(saddr, daddr, 0, 0, + TUNNEL_KEY, key_id, 0); + } else if (tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC] && + tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]) { + struct in6_addr saddr; + struct in6_addr daddr; + + saddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC]); + daddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]); + + metadata = __ipv6_tun_set_dst(&saddr, &daddr, 0, 0, 0, + TUNNEL_KEY, key_id, 0); + } + + if (!metadata) { + ret = -EINVAL; + goto err_out; + } + + metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX; + break; + default: + goto err_out; + } + + if (!exists) { + ret = tcf_hash_create(tn, parm->index, est, a, + &act_tunnel_key_ops, bind, true); + if (ret) + return ret; + + ret = ACT_P_CREATED; + } else { + tcf_hash_release(*a, bind); + if (!ovr) + return -EEXIST; + } + + t = to_tunnel_key(*a); + + ASSERT_RTNL(); + params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); + if (unlikely(!params_new)) { + if (ret == ACT_P_CREATED) + tcf_hash_release(*a, bind); + return -ENOMEM; + } + + params_old = rtnl_dereference(t->params); + + params_new->action = parm->action; + params_new->tcft_action = parm->t_action; + params_new->tcft_enc_metadata = metadata; + + rcu_assign_pointer(t->params, params_new); + + if (params_old) + kfree_rcu(params_old, rcu); + + if (ret == ACT_P_CREATED) + tcf_hash_insert(tn, *a); + + return ret; + +err_out: + if (exists) + tcf_hash_release(*a, bind); + return ret; +} + +static void tunnel_key_release(struct tc_action *a, int bind) +{ + struct tcf_tunnel_key *t = to_tunnel_key(a); + struct tcf_tunnel_key_params *params; + + rcu_read_lock(); + params = rcu_dereference(t->params); + + if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) + dst_release(¶ms->tcft_enc_metadata->dst); + + kfree_rcu(params, rcu); + + rcu_read_unlock(); +} + +static int tunnel_key_dump_addresses(struct sk_buff *skb, + const struct ip_tunnel_info *info) +{ + unsigned short family = ip_tunnel_info_af(info); + + if (family == AF_INET) { + __be32 saddr = info->key.u.ipv4.src; + __be32 daddr = info->key.u.ipv4.dst; + + if (!nla_put_in_addr(skb, TCA_TUNNEL_KEY_ENC_IPV4_SRC, saddr) && + !nla_put_in_addr(skb, TCA_TUNNEL_KEY_ENC_IPV4_DST, daddr)) + return 0; + } + + if (family == AF_INET6) { + const struct in6_addr *saddr6 = &info->key.u.ipv6.src; + const struct in6_addr *daddr6 = &info->key.u.ipv6.dst; + + if (!nla_put_in6_addr(skb, + TCA_TUNNEL_KEY_ENC_IPV6_SRC, saddr6) && + !nla_put_in6_addr(skb, + TCA_TUNNEL_KEY_ENC_IPV6_DST, daddr6)) + return 0; + } + + return -EINVAL; +} + +static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) +{ + unsigned char *b = skb_tail_pointer(skb); + struct tcf_tunnel_key *t = to_tunnel_key(a); + struct tcf_tunnel_key_params *params; + struct tc_tunnel_key opt = { + .index = t->tcf_index, + .refcnt = t->tcf_refcnt - ref, + .bindcnt = t->tcf_bindcnt - bind, + }; + struct tcf_t tm; + int ret = -1; + + rcu_read_lock(); + params = rcu_dereference(t->params); + + opt.t_action = params->tcft_action; + opt.action = params->action; + + if (nla_put(skb, TCA_TUNNEL_KEY_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + + if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) { + struct ip_tunnel_key *key = + ¶ms->tcft_enc_metadata->u.tun_info.key; + __be32 key_id = tunnel_id_to_key32(key->tun_id); + + if (nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id) || + tunnel_key_dump_addresses(skb, + ¶ms->tcft_enc_metadata->u.tun_info)) + goto nla_put_failure; + } + + tcf_tm_dump(&tm, &t->tcf_tm); + if (nla_put_64bit(skb, TCA_TUNNEL_KEY_TM, sizeof(tm), + &tm, TCA_TUNNEL_KEY_PAD)) + goto nla_put_failure; + + ret = skb->len; + goto out; + +nla_put_failure: + nlmsg_trim(skb, b); +out: + rcu_read_unlock(); + + return ret; +} + +static int tunnel_key_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + const struct tc_action_ops *ops) +{ + struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); + + return tcf_generic_walker(tn, skb, cb, type, ops); +} + +static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); + + return tcf_hash_search(tn, a, index); +} + +static struct tc_action_ops act_tunnel_key_ops = { + .kind = "tunnel_key", + .type = TCA_ACT_TUNNEL_KEY, + .owner = THIS_MODULE, + .act = tunnel_key_act, + .dump = tunnel_key_dump, + .init = tunnel_key_init, + .cleanup = tunnel_key_release, + .walk = tunnel_key_walker, + .lookup = tunnel_key_search, + .size = sizeof(struct tcf_tunnel_key), +}; + +static __net_init int tunnel_key_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); + + return tc_action_net_init(tn, &act_tunnel_key_ops, TUNNEL_KEY_TAB_MASK); +} + +static void __net_exit tunnel_key_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations tunnel_key_net_ops = { + .init = tunnel_key_init_net, + .exit = tunnel_key_exit_net, + .id = &tunnel_key_net_id, + .size = sizeof(struct tc_action_net), +}; + +static int __init tunnel_key_init_module(void) +{ + return tcf_register_action(&act_tunnel_key_ops, &tunnel_key_net_ops); +} + +static void __exit tunnel_key_cleanup_module(void) +{ + tcf_unregister_action(&act_tunnel_key_ops, &tunnel_key_net_ops); +} + +module_init(tunnel_key_init_module); +module_exit(tunnel_key_cleanup_module); + +MODULE_AUTHOR("Amir Vadai "); +MODULE_DESCRIPTION("ip tunnel manipulation actions"); +MODULE_LICENSE("GPL v2"); -- cgit v1.2.3 From 70ca767ea1b2748f45e96192400e515dddbe517c Mon Sep 17 00:00:00 2001 From: Laura Garcia Liebana Date: Tue, 6 Sep 2016 08:44:19 +0200 Subject: netfilter: nft_hash: Add hash offset value Add support to pass through an offset to the hash value. With this feature, the sysadmin is able to generate a hash with a given offset value. Example: meta mark set jhash ip saddr mod 2 seed 0xabcd offset 100 This option generates marks according to the source address from 100 to 101. Signed-off-by: Laura Garcia Liebana --- include/uapi/linux/netfilter/nf_tables.h | 2 ++ net/netfilter/nft_hash.c | 17 +++++++++++++---- 2 files changed, 15 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 24161e25576d..8c653bbd1ead 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -731,6 +731,7 @@ enum nft_meta_keys { * @NFTA_HASH_LEN: source data length (NLA_U32) * @NFTA_HASH_MODULUS: modulus value (NLA_U32) * @NFTA_HASH_SEED: seed value (NLA_U32) + * @NFTA_HASH_OFFSET: add this offset value to hash result (NLA_U32) */ enum nft_hash_attributes { NFTA_HASH_UNSPEC, @@ -739,6 +740,7 @@ enum nft_hash_attributes { NFTA_HASH_LEN, NFTA_HASH_MODULUS, NFTA_HASH_SEED, + NFTA_HASH_OFFSET, __NFTA_HASH_MAX, }; #define NFTA_HASH_MAX (__NFTA_HASH_MAX - 1) diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index 764251d31e46..bd12f7a801c2 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -23,6 +23,7 @@ struct nft_hash { u8 len; u32 modulus; u32 seed; + u32 offset; }; static void nft_hash_eval(const struct nft_expr *expr, @@ -31,10 +32,10 @@ static void nft_hash_eval(const struct nft_expr *expr, { struct nft_hash *priv = nft_expr_priv(expr); const void *data = ®s->data[priv->sreg]; + u32 h; - regs->data[priv->dreg] = - reciprocal_scale(jhash(data, priv->len, priv->seed), - priv->modulus); + h = reciprocal_scale(jhash(data, priv->len, priv->seed), priv->modulus); + regs->data[priv->dreg] = h + priv->offset; } static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = { @@ -59,6 +60,9 @@ static int nft_hash_init(const struct nft_ctx *ctx, !tb[NFTA_HASH_MODULUS]) return -EINVAL; + if (tb[NFTA_HASH_OFFSET]) + priv->offset = ntohl(nla_get_be32(tb[NFTA_HASH_OFFSET])); + priv->sreg = nft_parse_register(tb[NFTA_HASH_SREG]); priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]); @@ -72,6 +76,9 @@ static int nft_hash_init(const struct nft_ctx *ctx, if (priv->modulus <= 1) return -ERANGE; + if (priv->offset + priv->modulus - 1 < U32_MAX) + return -EOVERFLOW; + priv->seed = ntohl(nla_get_be32(tb[NFTA_HASH_SEED])); return nft_validate_register_load(priv->sreg, len) && @@ -94,7 +101,9 @@ static int nft_hash_dump(struct sk_buff *skb, goto nla_put_failure; if (nla_put_be32(skb, NFTA_HASH_SEED, htonl(priv->seed))) goto nla_put_failure; - + if (priv->offset != 0) + if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset))) + goto nla_put_failure; return 0; nla_put_failure: -- cgit v1.2.3 From dbd2be0646e3239022630c426cbceefa15714bca Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 7 Sep 2016 12:22:18 +0200 Subject: netfilter: nft_dynset: allow to invert match criteria The dynset expression matches if we can fit a new entry into the set. If there is no room for it, then it breaks the rule evaluation. This patch introduces the inversion flag so you can add rules to explicitly drop packets that don't fit into the set. For example: # nft filter input flow table xyz size 4 { ip saddr timeout 120s counter } overflow drop This is useful to provide a replacement for connlimit. For the rule above, every new entry uses the IPv4 address as key in the set, this entry gets a timeout of 120 seconds that gets refresh on every packet seen. If we get new flow and our set already contains 4 entries already, then this packet is dropped. You can already express this in positive logic, assuming default policy to drop: # nft filter input flow table xyz size 4 { ip saddr timeout 10s counter } accept Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 6 ++++++ net/netfilter/nft_dynset.c | 20 +++++++++++++++++++- 2 files changed, 25 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 8c653bbd1ead..bc0eb6a1066d 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -575,6 +575,10 @@ enum nft_dynset_ops { NFT_DYNSET_OP_UPDATE, }; +enum nft_dynset_flags { + NFT_DYNSET_F_INV = (1 << 0), +}; + /** * enum nft_dynset_attributes - dynset expression attributes * @@ -585,6 +589,7 @@ enum nft_dynset_ops { * @NFTA_DYNSET_SREG_DATA: source register of the data (NLA_U32) * @NFTA_DYNSET_TIMEOUT: timeout value for the new element (NLA_U64) * @NFTA_DYNSET_EXPR: expression (NLA_NESTED: nft_expr_attributes) + * @NFTA_DYNSET_FLAGS: flags (NLA_U32) */ enum nft_dynset_attributes { NFTA_DYNSET_UNSPEC, @@ -596,6 +601,7 @@ enum nft_dynset_attributes { NFTA_DYNSET_TIMEOUT, NFTA_DYNSET_EXPR, NFTA_DYNSET_PAD, + NFTA_DYNSET_FLAGS, __NFTA_DYNSET_MAX, }; #define NFTA_DYNSET_MAX (__NFTA_DYNSET_MAX - 1) diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 0af26699bf04..e3b83c31da2e 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -22,6 +22,7 @@ struct nft_dynset { enum nft_dynset_ops op:8; enum nft_registers sreg_key:8; enum nft_registers sreg_data:8; + bool invert; u64 timeout; struct nft_expr *expr; struct nft_set_binding binding; @@ -82,10 +83,14 @@ static void nft_dynset_eval(const struct nft_expr *expr, if (sexpr != NULL) sexpr->ops->eval(sexpr, regs, pkt); + + if (priv->invert) + regs->verdict.code = NFT_BREAK; return; } out: - regs->verdict.code = NFT_BREAK; + if (!priv->invert) + regs->verdict.code = NFT_BREAK; } static const struct nla_policy nft_dynset_policy[NFTA_DYNSET_MAX + 1] = { @@ -96,6 +101,7 @@ static const struct nla_policy nft_dynset_policy[NFTA_DYNSET_MAX + 1] = { [NFTA_DYNSET_SREG_DATA] = { .type = NLA_U32 }, [NFTA_DYNSET_TIMEOUT] = { .type = NLA_U64 }, [NFTA_DYNSET_EXPR] = { .type = NLA_NESTED }, + [NFTA_DYNSET_FLAGS] = { .type = NLA_U32 }, }; static int nft_dynset_init(const struct nft_ctx *ctx, @@ -113,6 +119,15 @@ static int nft_dynset_init(const struct nft_ctx *ctx, tb[NFTA_DYNSET_SREG_KEY] == NULL) return -EINVAL; + if (tb[NFTA_DYNSET_FLAGS]) { + u32 flags = ntohl(nla_get_be32(tb[NFTA_DYNSET_FLAGS])); + + if (flags & ~NFT_DYNSET_F_INV) + return -EINVAL; + if (flags & NFT_DYNSET_F_INV) + priv->invert = true; + } + set = nf_tables_set_lookup(ctx->table, tb[NFTA_DYNSET_SET_NAME], genmask); if (IS_ERR(set)) { @@ -220,6 +235,7 @@ static void nft_dynset_destroy(const struct nft_ctx *ctx, static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_dynset *priv = nft_expr_priv(expr); + u32 flags = priv->invert ? NFT_DYNSET_F_INV : 0; if (nft_dump_register(skb, NFTA_DYNSET_SREG_KEY, priv->sreg_key)) goto nla_put_failure; @@ -235,6 +251,8 @@ static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr) goto nla_put_failure; if (priv->expr && nft_expr_dump(skb, NFTA_DYNSET_EXPR, priv->expr)) goto nla_put_failure; + if (nla_put_be32(skb, NFTA_DYNSET_FLAGS, htonl(flags))) + goto nla_put_failure; return 0; nla_put_failure: -- cgit v1.2.3 From 8e8118f893138d4cc3d4dbf4163d7497fca54a9d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sun, 11 Sep 2016 22:55:53 +0200 Subject: netfilter: conntrack: remove packet hotpath stats These counters sit in hot path and do show up in perf, this is especially true for 'found' and 'searched' which get incremented for every packet processed. Information like searched=212030105 new=623431 found=333613 delete=623327 does not seem too helpful nowadays: - on busy systems found and searched will overflow every few hours (these are 32bit integers), other more busy ones every few days. - for debugging there are better methods, such as iptables' trace target, the conntrack log sysctls. Nowadays we also have perf tool. This removes packet path stat counters except those that are expected to be 0 (or close to 0) on a normal system, e.g. 'insert_failed' (race happened) or 'invalid' (proto tracker rejects). The insert stat is retained for the ctnetlink case. The found stat is retained for the tuple-is-taken check when NAT has to determine if it needs to pick a different source address. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_common.h | 4 ---- include/uapi/linux/netfilter/nfnetlink_conntrack.h | 8 ++++---- net/netfilter/nf_conntrack_core.c | 14 ++------------ net/netfilter/nf_conntrack_netlink.c | 6 +----- net/netfilter/nf_conntrack_standalone.c | 8 ++++---- 5 files changed, 11 insertions(+), 29 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 275505792664..1d1ef4e20512 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -4,13 +4,9 @@ #include struct ip_conntrack_stat { - unsigned int searched; unsigned int found; - unsigned int new; unsigned int invalid; unsigned int ignore; - unsigned int delete; - unsigned int delete_list; unsigned int insert; unsigned int insert_failed; unsigned int drop; diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h index 9df789709abe..6deb8867c5fc 100644 --- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h +++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h @@ -231,13 +231,13 @@ enum ctattr_secctx { enum ctattr_stats_cpu { CTA_STATS_UNSPEC, - CTA_STATS_SEARCHED, + CTA_STATS_SEARCHED, /* no longer used */ CTA_STATS_FOUND, - CTA_STATS_NEW, + CTA_STATS_NEW, /* no longer used */ CTA_STATS_INVALID, CTA_STATS_IGNORE, - CTA_STATS_DELETE, - CTA_STATS_DELETE_LIST, + CTA_STATS_DELETE, /* no longer used */ + CTA_STATS_DELETE_LIST, /* no longer used */ CTA_STATS_INSERT, CTA_STATS_INSERT_FAILED, CTA_STATS_DROP, diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index ac1db4019d5c..8d1ddb9b63ed 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -379,7 +379,6 @@ static void destroy_conntrack(struct nf_conntrack *nfct) { struct nf_conn *ct = (struct nf_conn *)nfct; - struct net *net = nf_ct_net(ct); struct nf_conntrack_l4proto *l4proto; pr_debug("destroy_conntrack(%p)\n", ct); @@ -406,7 +405,6 @@ destroy_conntrack(struct nf_conntrack *nfct) nf_ct_del_from_dying_or_unconfirmed_list(ct); - NF_CT_STAT_INC(net, delete); local_bh_enable(); if (ct->master) @@ -438,7 +436,6 @@ static void nf_ct_delete_from_lists(struct nf_conn *ct) nf_ct_add_to_dying_list(ct); - NF_CT_STAT_INC(net, delete_list); local_bh_enable(); } @@ -529,11 +526,8 @@ begin: if (nf_ct_is_dying(ct)) continue; - if (nf_ct_key_equal(h, tuple, zone, net)) { - NF_CT_STAT_INC_ATOMIC(net, found); + if (nf_ct_key_equal(h, tuple, zone, net)) return h; - } - NF_CT_STAT_INC_ATOMIC(net, searched); } /* * if the nulls value we got at the end of this lookup is @@ -798,7 +792,6 @@ __nf_conntrack_confirm(struct sk_buff *skb) */ __nf_conntrack_hash_insert(ct, hash, reply_hash); nf_conntrack_double_unlock(hash, reply_hash); - NF_CT_STAT_INC(net, insert); local_bh_enable(); help = nfct_help(ct); @@ -857,7 +850,6 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, rcu_read_unlock(); return 1; } - NF_CT_STAT_INC_ATOMIC(net, searched); } if (get_nulls_value(n) != hash) { @@ -1177,10 +1169,8 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, } spin_unlock(&nf_conntrack_expect_lock); } - if (!exp) { + if (!exp) __nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC); - NF_CT_STAT_INC(net, new); - } /* Now it is inserted into the unconfirmed list, bump refcount */ nf_conntrack_get(&ct->ct_general); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index c052b712c49f..27540455dc62 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1984,13 +1984,9 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq, nfmsg->version = NFNETLINK_V0; nfmsg->res_id = htons(cpu); - if (nla_put_be32(skb, CTA_STATS_SEARCHED, htonl(st->searched)) || - nla_put_be32(skb, CTA_STATS_FOUND, htonl(st->found)) || - nla_put_be32(skb, CTA_STATS_NEW, htonl(st->new)) || + if (nla_put_be32(skb, CTA_STATS_FOUND, htonl(st->found)) || nla_put_be32(skb, CTA_STATS_INVALID, htonl(st->invalid)) || nla_put_be32(skb, CTA_STATS_IGNORE, htonl(st->ignore)) || - nla_put_be32(skb, CTA_STATS_DELETE, htonl(st->delete)) || - nla_put_be32(skb, CTA_STATS_DELETE_LIST, htonl(st->delete_list)) || nla_put_be32(skb, CTA_STATS_INSERT, htonl(st->insert)) || nla_put_be32(skb, CTA_STATS_INSERT_FAILED, htonl(st->insert_failed)) || diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 3d9a316a3c77..7d52f8401afd 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -352,13 +352,13 @@ static int ct_cpu_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x " "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n", nr_conntracks, - st->searched, + 0, st->found, - st->new, + 0, st->invalid, st->ignore, - st->delete, - st->delete_list, + 0, + 0, st->insert, st->insert_failed, st->drop, -- cgit v1.2.3 From 86da71b57383d40993cb90baafb3735cffe5d800 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Mon, 12 Sep 2016 20:13:09 -0400 Subject: net_sched: Introduce skbmod action This action is intended to be an upgrade from a usability perspective from pedit (as well as operational debugability). Compare this: sudo tc filter add dev $ETH parent 1: protocol ip prio 10 \ u32 match ip protocol 1 0xff flowid 1:2 \ action pedit munge offset -14 u8 set 0x02 \ munge offset -13 u8 set 0x15 \ munge offset -12 u8 set 0x15 \ munge offset -11 u8 set 0x15 \ munge offset -10 u16 set 0x1515 \ pipe to: sudo tc filter add dev $ETH parent 1: protocol ip prio 10 \ u32 match ip protocol 1 0xff flowid 1:2 \ action skbmod dmac 02:15:15:15:15:15 Also try to do a MAC address swap with pedit or worse try to debug a policy with destination mac, source mac and etherype. Then make few rules out of those and you'll get my point. In the future common use cases on pedit can be migrated to this action (as an example different fields in ip v4/6, transports like tcp/udp/sctp etc). For this first cut, this allows modifying basic ethernet header. The most important ethernet use case at the moment is when redirecting or mirroring packets to a remote machine. The dst mac address needs a re-write so that it doesnt get dropped or confuse an interconnecting (learning) switch or dropped by a target machine (which looks at the dst mac). And at times when flipping back the packet a swap of the MAC addresses is needed. Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/tc_act/tc_skbmod.h | 30 ++++ include/uapi/linux/tc_act/tc_skbmod.h | 39 +++++ net/sched/Kconfig | 11 ++ net/sched/Makefile | 1 + net/sched/act_skbmod.c | 301 ++++++++++++++++++++++++++++++++++ 5 files changed, 382 insertions(+) create mode 100644 include/net/tc_act/tc_skbmod.h create mode 100644 include/uapi/linux/tc_act/tc_skbmod.h create mode 100644 net/sched/act_skbmod.c (limited to 'include/uapi/linux') diff --git a/include/net/tc_act/tc_skbmod.h b/include/net/tc_act/tc_skbmod.h new file mode 100644 index 000000000000..644a2116b47b --- /dev/null +++ b/include/net/tc_act/tc_skbmod.h @@ -0,0 +1,30 @@ +/* + * Copyright (c) 2016, Jamal Hadi Salim + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. +*/ + +#ifndef __NET_TC_SKBMOD_H +#define __NET_TC_SKBMOD_H + +#include +#include + +struct tcf_skbmod_params { + struct rcu_head rcu; + u64 flags; /*up to 64 types of operations; extend if needed */ + u8 eth_dst[ETH_ALEN]; + u16 eth_type; + u8 eth_src[ETH_ALEN]; +}; + +struct tcf_skbmod { + struct tc_action common; + struct tcf_skbmod_params __rcu *skbmod_p; +}; +#define to_skbmod(a) ((struct tcf_skbmod *)a) + +#endif /* __NET_TC_SKBMOD_H */ diff --git a/include/uapi/linux/tc_act/tc_skbmod.h b/include/uapi/linux/tc_act/tc_skbmod.h new file mode 100644 index 000000000000..10fc07da6c69 --- /dev/null +++ b/include/uapi/linux/tc_act/tc_skbmod.h @@ -0,0 +1,39 @@ +/* + * Copyright (c) 2016, Jamal Hadi Salim + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. +*/ + +#ifndef __LINUX_TC_SKBMOD_H +#define __LINUX_TC_SKBMOD_H + +#include + +#define TCA_ACT_SKBMOD 15 + +#define SKBMOD_F_DMAC 0x1 +#define SKBMOD_F_SMAC 0x2 +#define SKBMOD_F_ETYPE 0x4 +#define SKBMOD_F_SWAPMAC 0x8 + +struct tc_skbmod { + tc_gen; + __u64 flags; +}; + +enum { + TCA_SKBMOD_UNSPEC, + TCA_SKBMOD_TM, + TCA_SKBMOD_PARMS, + TCA_SKBMOD_DMAC, + TCA_SKBMOD_SMAC, + TCA_SKBMOD_ETYPE, + TCA_SKBMOD_PAD, + __TCA_SKBMOD_MAX +}; +#define TCA_SKBMOD_MAX (__TCA_SKBMOD_MAX - 1) + +#endif diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 72e3426fa48f..7795d5a3f79a 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -749,6 +749,17 @@ config NET_ACT_CONNMARK To compile this code as a module, choose M here: the module will be called act_connmark. +config NET_ACT_SKBMOD + tristate "skb data modification action" + depends on NET_CLS_ACT + ---help--- + Say Y here to allow modification of skb data + + If unsure, say N. + + To compile this code as a module, choose M here: the + module will be called act_skbmod. + config NET_ACT_IFE tristate "Inter-FE action based on IETF ForCES InterFE LFB" depends on NET_CLS_ACT diff --git a/net/sched/Makefile b/net/sched/Makefile index b9d046b9535a..148ae0d5ac2c 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_NET_ACT_CSUM) += act_csum.o obj-$(CONFIG_NET_ACT_VLAN) += act_vlan.o obj-$(CONFIG_NET_ACT_BPF) += act_bpf.o obj-$(CONFIG_NET_ACT_CONNMARK) += act_connmark.o +obj-$(CONFIG_NET_ACT_SKBMOD) += act_skbmod.o obj-$(CONFIG_NET_ACT_IFE) += act_ife.o obj-$(CONFIG_NET_IFE_SKBMARK) += act_meta_mark.o obj-$(CONFIG_NET_IFE_SKBPRIO) += act_meta_skbprio.o diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c new file mode 100644 index 000000000000..e7d96381c908 --- /dev/null +++ b/net/sched/act_skbmod.c @@ -0,0 +1,301 @@ +/* + * net/sched/act_skbmod.c skb data modifier + * + * Copyright (c) 2016 Jamal Hadi Salim + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. +*/ + +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#define SKBMOD_TAB_MASK 15 + +static int skbmod_net_id; +static struct tc_action_ops act_skbmod_ops; + +#define MAX_EDIT_LEN ETH_HLEN +static int tcf_skbmod_run(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_skbmod *d = to_skbmod(a); + int action; + struct tcf_skbmod_params *p; + u64 flags; + int err; + + tcf_lastuse_update(&d->tcf_tm); + bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb); + + /* XXX: if you are going to edit more fields beyond ethernet header + * (example when you add IP header replacement or vlan swap) + * then MAX_EDIT_LEN needs to change appropriately + */ + err = skb_ensure_writable(skb, MAX_EDIT_LEN); + if (unlikely(err)) { /* best policy is to drop on the floor */ + qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats)); + return TC_ACT_SHOT; + } + + rcu_read_lock(); + action = READ_ONCE(d->tcf_action); + if (unlikely(action == TC_ACT_SHOT)) { + qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats)); + rcu_read_unlock(); + return action; + } + + p = rcu_dereference(d->skbmod_p); + flags = p->flags; + if (flags & SKBMOD_F_DMAC) + ether_addr_copy(eth_hdr(skb)->h_dest, p->eth_dst); + if (flags & SKBMOD_F_SMAC) + ether_addr_copy(eth_hdr(skb)->h_source, p->eth_src); + if (flags & SKBMOD_F_ETYPE) + eth_hdr(skb)->h_proto = p->eth_type; + rcu_read_unlock(); + + if (flags & SKBMOD_F_SWAPMAC) { + u16 tmpaddr[ETH_ALEN / 2]; /* ether_addr_copy() requirement */ + /*XXX: I am sure we can come up with more efficient swapping*/ + ether_addr_copy((u8 *)tmpaddr, eth_hdr(skb)->h_dest); + ether_addr_copy(eth_hdr(skb)->h_dest, eth_hdr(skb)->h_source); + ether_addr_copy(eth_hdr(skb)->h_source, (u8 *)tmpaddr); + } + + return action; +} + +static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = { + [TCA_SKBMOD_PARMS] = { .len = sizeof(struct tc_skbmod) }, + [TCA_SKBMOD_DMAC] = { .len = ETH_ALEN }, + [TCA_SKBMOD_SMAC] = { .len = ETH_ALEN }, + [TCA_SKBMOD_ETYPE] = { .type = NLA_U16 }, +}; + +static int tcf_skbmod_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action **a, + int ovr, int bind) +{ + struct tc_action_net *tn = net_generic(net, skbmod_net_id); + struct nlattr *tb[TCA_SKBMOD_MAX + 1]; + struct tcf_skbmod_params *p, *p_old; + struct tc_skbmod *parm; + struct tcf_skbmod *d; + bool exists = false; + u8 *daddr = NULL; + u8 *saddr = NULL; + u16 eth_type = 0; + u32 lflags = 0; + int ret = 0, err; + + if (!nla) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_SKBMOD_MAX, nla, skbmod_policy); + if (err < 0) + return err; + + if (!tb[TCA_SKBMOD_PARMS]) + return -EINVAL; + + if (tb[TCA_SKBMOD_DMAC]) { + daddr = nla_data(tb[TCA_SKBMOD_DMAC]); + lflags |= SKBMOD_F_DMAC; + } + + if (tb[TCA_SKBMOD_SMAC]) { + saddr = nla_data(tb[TCA_SKBMOD_SMAC]); + lflags |= SKBMOD_F_SMAC; + } + + if (tb[TCA_SKBMOD_ETYPE]) { + eth_type = nla_get_u16(tb[TCA_SKBMOD_ETYPE]); + lflags |= SKBMOD_F_ETYPE; + } + + parm = nla_data(tb[TCA_SKBMOD_PARMS]); + if (parm->flags & SKBMOD_F_SWAPMAC) + lflags = SKBMOD_F_SWAPMAC; + + exists = tcf_hash_check(tn, parm->index, a, bind); + if (exists && bind) + return 0; + + if (!lflags) + return -EINVAL; + + if (!exists) { + ret = tcf_hash_create(tn, parm->index, est, a, + &act_skbmod_ops, bind, true); + if (ret) + return ret; + + ret = ACT_P_CREATED; + } else { + tcf_hash_release(*a, bind); + if (!ovr) + return -EEXIST; + } + + d = to_skbmod(*a); + + ASSERT_RTNL(); + p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL); + if (unlikely(!p)) { + if (ovr) + tcf_hash_release(*a, bind); + return -ENOMEM; + } + + p->flags = lflags; + d->tcf_action = parm->action; + + p_old = rtnl_dereference(d->skbmod_p); + + if (ovr) + spin_lock_bh(&d->tcf_lock); + + if (lflags & SKBMOD_F_DMAC) + ether_addr_copy(p->eth_dst, daddr); + if (lflags & SKBMOD_F_SMAC) + ether_addr_copy(p->eth_src, saddr); + if (lflags & SKBMOD_F_ETYPE) + p->eth_type = htons(eth_type); + + rcu_assign_pointer(d->skbmod_p, p); + if (ovr) + spin_unlock_bh(&d->tcf_lock); + + if (p_old) + kfree_rcu(p_old, rcu); + + if (ret == ACT_P_CREATED) + tcf_hash_insert(tn, *a); + return ret; +} + +static void tcf_skbmod_cleanup(struct tc_action *a, int bind) +{ + struct tcf_skbmod *d = to_skbmod(a); + struct tcf_skbmod_params *p; + + p = rcu_dereference_protected(d->skbmod_p, 1); + kfree_rcu(p, rcu); +} + +static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) +{ + struct tcf_skbmod *d = to_skbmod(a); + unsigned char *b = skb_tail_pointer(skb); + struct tcf_skbmod_params *p = rtnl_dereference(d->skbmod_p); + struct tc_skbmod opt = { + .index = d->tcf_index, + .refcnt = d->tcf_refcnt - ref, + .bindcnt = d->tcf_bindcnt - bind, + .action = d->tcf_action, + }; + struct tcf_t t; + + opt.flags = p->flags; + if (nla_put(skb, TCA_SKBMOD_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + if ((p->flags & SKBMOD_F_DMAC) && + nla_put(skb, TCA_SKBMOD_DMAC, ETH_ALEN, p->eth_dst)) + goto nla_put_failure; + if ((p->flags & SKBMOD_F_SMAC) && + nla_put(skb, TCA_SKBMOD_SMAC, ETH_ALEN, p->eth_src)) + goto nla_put_failure; + if ((p->flags & SKBMOD_F_ETYPE) && + nla_put_u16(skb, TCA_SKBMOD_ETYPE, ntohs(p->eth_type))) + goto nla_put_failure; + + tcf_tm_dump(&t, &d->tcf_tm); + if (nla_put_64bit(skb, TCA_SKBMOD_TM, sizeof(t), &t, TCA_SKBMOD_PAD)) + goto nla_put_failure; + + return skb->len; +nla_put_failure: + rcu_read_unlock(); + nlmsg_trim(skb, b); + return -1; +} + +static int tcf_skbmod_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + const struct tc_action_ops *ops) +{ + struct tc_action_net *tn = net_generic(net, skbmod_net_id); + + return tcf_generic_walker(tn, skb, cb, type, ops); +} + +static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, skbmod_net_id); + + return tcf_hash_search(tn, a, index); +} + +static struct tc_action_ops act_skbmod_ops = { + .kind = "skbmod", + .type = TCA_ACT_SKBMOD, + .owner = THIS_MODULE, + .act = tcf_skbmod_run, + .dump = tcf_skbmod_dump, + .init = tcf_skbmod_init, + .cleanup = tcf_skbmod_cleanup, + .walk = tcf_skbmod_walker, + .lookup = tcf_skbmod_search, + .size = sizeof(struct tcf_skbmod), +}; + +static __net_init int skbmod_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, skbmod_net_id); + + return tc_action_net_init(tn, &act_skbmod_ops, SKBMOD_TAB_MASK); +} + +static void __net_exit skbmod_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, skbmod_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations skbmod_net_ops = { + .init = skbmod_init_net, + .exit = skbmod_exit_net, + .id = &skbmod_net_id, + .size = sizeof(struct tc_action_net), +}; + +MODULE_AUTHOR("Jamal Hadi Salim, "); +MODULE_DESCRIPTION("SKB data mod-ing"); +MODULE_LICENSE("GPL"); + +static int __init skbmod_init_module(void) +{ + return tcf_register_action(&act_skbmod_ops, &skbmod_net_ops); +} + +static void __exit skbmod_cleanup_module(void) +{ + tcf_unregister_action(&act_skbmod_ops, &skbmod_net_ops); +} + +module_init(skbmod_init_module); +module_exit(skbmod_cleanup_module); -- cgit v1.2.3 From aa72d708373dacfa690960b336543b867784b350 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 15 Sep 2016 15:28:22 +0300 Subject: net/sched: cls_flower: Support masking for matching on tcp/udp ports Add the definitions for src/dst udp/tcp port masks and use them when setting && dumping the relevant keys. Signed-off-by: Or Gerlitz Signed-off-by: Paul Blakey Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 4 ++++ net/sched/cls_flower.c | 20 ++++++++++++-------- 2 files changed, 16 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index f9c287c67eae..60ea2a084880 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -442,6 +442,10 @@ enum { TCA_FLOWER_KEY_ENC_IPV6_DST, /* struct in6_addr */ TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,/* struct in6_addr */ + TCA_FLOWER_KEY_TCP_SRC_MASK, /* be16 */ + TCA_FLOWER_KEY_TCP_DST_MASK, /* be16 */ + TCA_FLOWER_KEY_UDP_SRC_MASK, /* be16 */ + TCA_FLOWER_KEY_UDP_DST_MASK, /* be16 */ __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index b084b2aab2d7..027523c82797 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -335,6 +335,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK] = { .len = sizeof(struct in6_addr) }, [TCA_FLOWER_KEY_ENC_IPV6_DST] = { .len = sizeof(struct in6_addr) }, [TCA_FLOWER_KEY_ENC_IPV6_DST_MASK] = { .len = sizeof(struct in6_addr) }, + [TCA_FLOWER_KEY_TCP_SRC_MASK] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_TCP_DST_MASK] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_UDP_SRC_MASK] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_UDP_DST_MASK] = { .type = NLA_U16 }, }; static void fl_set_key_val(struct nlattr **tb, @@ -432,17 +436,17 @@ static int fl_set_key(struct net *net, struct nlattr **tb, if (key->basic.ip_proto == IPPROTO_TCP) { fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC, - &mask->tp.src, TCA_FLOWER_UNSPEC, + &mask->tp.src, TCA_FLOWER_KEY_TCP_SRC_MASK, sizeof(key->tp.src)); fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_TCP_DST, - &mask->tp.dst, TCA_FLOWER_UNSPEC, + &mask->tp.dst, TCA_FLOWER_KEY_TCP_DST_MASK, sizeof(key->tp.dst)); } else if (key->basic.ip_proto == IPPROTO_UDP) { fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_UDP_SRC, - &mask->tp.src, TCA_FLOWER_UNSPEC, + &mask->tp.src, TCA_FLOWER_KEY_UDP_SRC_MASK, sizeof(key->tp.src)); fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_UDP_DST, - &mask->tp.dst, TCA_FLOWER_UNSPEC, + &mask->tp.dst, TCA_FLOWER_KEY_UDP_DST_MASK, sizeof(key->tp.dst)); } @@ -877,18 +881,18 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, if (key->basic.ip_proto == IPPROTO_TCP && (fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC, - &mask->tp.src, TCA_FLOWER_UNSPEC, + &mask->tp.src, TCA_FLOWER_KEY_TCP_SRC_MASK, sizeof(key->tp.src)) || fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_TCP_DST, - &mask->tp.dst, TCA_FLOWER_UNSPEC, + &mask->tp.dst, TCA_FLOWER_KEY_TCP_DST_MASK, sizeof(key->tp.dst)))) goto nla_put_failure; else if (key->basic.ip_proto == IPPROTO_UDP && (fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_UDP_SRC, - &mask->tp.src, TCA_FLOWER_UNSPEC, + &mask->tp.src, TCA_FLOWER_KEY_UDP_SRC_MASK, sizeof(key->tp.src)) || fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_UDP_DST, - &mask->tp.dst, TCA_FLOWER_UNSPEC, + &mask->tp.dst, TCA_FLOWER_KEY_UDP_DST_MASK, sizeof(key->tp.dst)))) goto nla_put_failure; -- cgit v1.2.3 From 37a6c1512314d2439ef7136d773d5a470e0996b9 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 15 Sep 2016 15:28:24 +0300 Subject: net/sched: cls_flower: Specify vlan attributes format in the UAPI header Specify the format (size and endianess) for the vlan attributes. Signed-off-by: Or Gerlitz Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 60ea2a084880..8915b61bbf83 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -428,9 +428,9 @@ enum { TCA_FLOWER_KEY_UDP_DST, /* be16 */ TCA_FLOWER_FLAGS, - TCA_FLOWER_KEY_VLAN_ID, - TCA_FLOWER_KEY_VLAN_PRIO, - TCA_FLOWER_KEY_VLAN_ETH_TYPE, + TCA_FLOWER_KEY_VLAN_ID, /* be16 */ + TCA_FLOWER_KEY_VLAN_PRIO, /* u8 */ + TCA_FLOWER_KEY_VLAN_ETH_TYPE, /* be16 */ TCA_FLOWER_KEY_ENC_KEY_ID, /* be32 */ TCA_FLOWER_KEY_ENC_IPV4_SRC, /* be32 */ -- cgit v1.2.3 From c568d68341be7030f5647def68851e469b21ca11 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 16 Sep 2016 12:44:20 +0200 Subject: locks: fix file locking on overlayfs This patch allows flock, posix locks, ofd locks and leases to work correctly on overlayfs. Instead of using the underlying inode for storing lock context use the overlay inode. This allows locks to be persistent across copy-up. This is done by introducing locks_inode() helper and using it instead of file_inode() to get the inode in locking code. For non-overlayfs the two are equivalent, except for an extra pointer dereference in locks_inode(). Since lock operations are in "struct file_operations" we must also make sure not to call underlying filesystem's lock operations. Introcude a super block flag MS_NOREMOTELOCK to this effect. Signed-off-by: Miklos Szeredi Acked-by: Jeff Layton Cc: "J. Bruce Fields" --- fs/locks.c | 50 +++++++++++++++++++++++++++---------------------- fs/namespace.c | 2 +- fs/open.c | 2 +- fs/overlayfs/super.c | 2 +- include/linux/fs.h | 16 ++++++++++++++-- include/uapi/linux/fs.h | 1 + 6 files changed, 46 insertions(+), 27 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/locks.c b/fs/locks.c index ee1b15f6fc13..c1656cff53ee 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -139,6 +139,11 @@ #define IS_LEASE(fl) (fl->fl_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT)) #define IS_OFDLCK(fl) (fl->fl_flags & FL_OFDLCK) +static inline bool is_remote_lock(struct file *filp) +{ + return likely(!(filp->f_path.dentry->d_sb->s_flags & MS_NOREMOTELOCK)); +} + static bool lease_breaking(struct file_lock *fl) { return fl->fl_flags & (FL_UNLOCK_PENDING | FL_DOWNGRADE_PENDING); @@ -791,7 +796,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl) { struct file_lock *cfl; struct file_lock_context *ctx; - struct inode *inode = file_inode(filp); + struct inode *inode = locks_inode(filp); ctx = smp_load_acquire(&inode->i_flctx); if (!ctx || list_empty_careful(&ctx->flc_posix)) { @@ -1192,7 +1197,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { - return posix_lock_inode(file_inode(filp), fl, conflock); + return posix_lock_inode(locks_inode(filp), fl, conflock); } EXPORT_SYMBOL(posix_lock_file); @@ -1232,7 +1237,7 @@ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) int locks_mandatory_locked(struct file *file) { int ret; - struct inode *inode = file_inode(file); + struct inode *inode = locks_inode(file); struct file_lock_context *ctx; struct file_lock *fl; @@ -1572,7 +1577,7 @@ EXPORT_SYMBOL(lease_get_mtime); int fcntl_getlease(struct file *filp) { struct file_lock *fl; - struct inode *inode = file_inode(filp); + struct inode *inode = locks_inode(filp); struct file_lock_context *ctx; int type = F_UNLCK; LIST_HEAD(dispose); @@ -1580,7 +1585,7 @@ int fcntl_getlease(struct file *filp) ctx = smp_load_acquire(&inode->i_flctx); if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&ctx->flc_lock); - time_out_leases(file_inode(filp), &dispose); + time_out_leases(inode, &dispose); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file != filp) continue; @@ -1628,7 +1633,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr { struct file_lock *fl, *my_fl = NULL, *lease; struct dentry *dentry = filp->f_path.dentry; - struct inode *inode = file_inode(filp); + struct inode *inode = dentry->d_inode; struct file_lock_context *ctx; bool is_deleg = (*flp)->fl_flags & FL_DELEG; int error; @@ -1742,7 +1747,7 @@ static int generic_delete_lease(struct file *filp, void *owner) { int error = -EAGAIN; struct file_lock *fl, *victim = NULL; - struct inode *inode = file_inode(filp); + struct inode *inode = locks_inode(filp); struct file_lock_context *ctx; LIST_HEAD(dispose); @@ -1782,7 +1787,7 @@ static int generic_delete_lease(struct file *filp, void *owner) int generic_setlease(struct file *filp, long arg, struct file_lock **flp, void **priv) { - struct inode *inode = file_inode(filp); + struct inode *inode = locks_inode(filp); int error; if ((!uid_eq(current_fsuid(), inode->i_uid)) && !capable(CAP_LEASE)) @@ -1830,7 +1835,7 @@ EXPORT_SYMBOL(generic_setlease); int vfs_setlease(struct file *filp, long arg, struct file_lock **lease, void **priv) { - if (filp->f_op->setlease) + if (filp->f_op->setlease && is_remote_lock(filp)) return filp->f_op->setlease(filp, arg, lease, priv); else return generic_setlease(filp, arg, lease, priv); @@ -1979,7 +1984,7 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) if (error) goto out_free; - if (f.file->f_op->flock) + if (f.file->f_op->flock && is_remote_lock(f.file)) error = f.file->f_op->flock(f.file, (can_sleep) ? F_SETLKW : F_SETLK, lock); @@ -2005,7 +2010,7 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) */ int vfs_test_lock(struct file *filp, struct file_lock *fl) { - if (filp->f_op->lock) + if (filp->f_op->lock && is_remote_lock(filp)) return filp->f_op->lock(filp, F_GETLK, fl); posix_test_lock(filp, fl); return 0; @@ -2129,7 +2134,7 @@ out: */ int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { - if (filp->f_op->lock) + if (filp->f_op->lock && is_remote_lock(filp)) return filp->f_op->lock(filp, cmd, fl); else return posix_lock_file(filp, fl, conf); @@ -2191,7 +2196,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, if (file_lock == NULL) return -ENOLCK; - inode = file_inode(filp); + inode = locks_inode(filp); /* * This might block, so we do it before checking the inode. @@ -2343,7 +2348,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, if (copy_from_user(&flock, l, sizeof(flock))) goto out; - inode = file_inode(filp); + inode = locks_inode(filp); /* Don't allow mandatory locks on files that may be memory mapped * and shared. @@ -2426,6 +2431,7 @@ out: void locks_remove_posix(struct file *filp, fl_owner_t owner) { int error; + struct inode *inode = locks_inode(filp); struct file_lock lock; struct file_lock_context *ctx; @@ -2434,7 +2440,7 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner) * posix_lock_file(). Another process could be setting a lock on this * file at the same time, but we wouldn't remove that lock anyway. */ - ctx = smp_load_acquire(&file_inode(filp)->i_flctx); + ctx = smp_load_acquire(&inode->i_flctx); if (!ctx || list_empty(&ctx->flc_posix)) return; @@ -2452,7 +2458,7 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner) if (lock.fl_ops && lock.fl_ops->fl_release_private) lock.fl_ops->fl_release_private(&lock); - trace_locks_remove_posix(file_inode(filp), &lock, error); + trace_locks_remove_posix(inode, &lock, error); } EXPORT_SYMBOL(locks_remove_posix); @@ -2469,12 +2475,12 @@ locks_remove_flock(struct file *filp, struct file_lock_context *flctx) .fl_type = F_UNLCK, .fl_end = OFFSET_MAX, }; - struct inode *inode = file_inode(filp); + struct inode *inode = locks_inode(filp); if (list_empty(&flctx->flc_flock)) return; - if (filp->f_op->flock) + if (filp->f_op->flock && is_remote_lock(filp)) filp->f_op->flock(filp, F_SETLKW, &fl); else flock_lock_inode(inode, &fl); @@ -2508,7 +2514,7 @@ void locks_remove_file(struct file *filp) { struct file_lock_context *ctx; - ctx = smp_load_acquire(&file_inode(filp)->i_flctx); + ctx = smp_load_acquire(&locks_inode(filp)->i_flctx); if (!ctx) return; @@ -2552,7 +2558,7 @@ EXPORT_SYMBOL(posix_unblock_lock); */ int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { - if (filp->f_op->lock) + if (filp->f_op->lock && is_remote_lock(filp)) return filp->f_op->lock(filp, F_CANCELLK, fl); return 0; } @@ -2580,7 +2586,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, fl_pid = fl->fl_pid; if (fl->fl_file != NULL) - inode = file_inode(fl->fl_file); + inode = locks_inode(fl->fl_file); seq_printf(f, "%lld:%s ", id, pfx); if (IS_POSIX(fl)) { @@ -2682,7 +2688,7 @@ static void __show_fd_locks(struct seq_file *f, void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) { - struct inode *inode = file_inode(filp); + struct inode *inode = locks_inode(filp); struct file_lock_context *ctx; int id = 0; diff --git a/fs/namespace.c b/fs/namespace.c index 7bb2cda3bfef..dcd9afe21e62 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2700,7 +2700,7 @@ long do_mount(const char *dev_name, const char __user *dir_name, flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN | MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT | - MS_STRICTATIME); + MS_STRICTATIME | MS_NOREMOTELOCK); if (flags & MS_REMOUNT) retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags, diff --git a/fs/open.c b/fs/open.c index 4fd6e256f4f4..648fb9d3e97a 100644 --- a/fs/open.c +++ b/fs/open.c @@ -726,7 +726,7 @@ static int do_dentry_open(struct file *f, if (error) goto cleanup_all; - error = break_lease(inode, f->f_flags); + error = break_lease(locks_inode(f), f->f_flags); if (error) goto cleanup_all; diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index e2a94a26767b..3d0b9dee2b76 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1320,7 +1320,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_xattr = ovl_xattr_handlers; sb->s_root = root_dentry; sb->s_fs_info = ufs; - sb->s_flags |= MS_POSIXACL; + sb->s_flags |= MS_POSIXACL | MS_NOREMOTELOCK; return 0; diff --git a/include/linux/fs.h b/include/linux/fs.h index 7db097d673a8..8ee0f011547f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1065,6 +1065,18 @@ struct file_lock_context { extern void send_sigio(struct fown_struct *fown, int fd, int band); +/* + * Return the inode to use for locking + * + * For overlayfs this should be the overlay inode, not the real inode returned + * by file_inode(). For any other fs file_inode(filp) and locks_inode(filp) are + * equal. + */ +static inline struct inode *locks_inode(const struct file *f) +{ + return f->f_path.dentry->d_inode; +} + #ifdef CONFIG_FILE_LOCKING extern int fcntl_getlk(struct file *, unsigned int, struct flock __user *); extern int fcntl_setlk(unsigned int, struct file *, unsigned int, @@ -1252,7 +1264,7 @@ static inline struct dentry *file_dentry(const struct file *file) static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) { - return locks_lock_inode_wait(file_inode(filp), fl); + return locks_lock_inode_wait(locks_inode(filp), fl); } struct fasync_struct { @@ -2155,7 +2167,7 @@ static inline int mandatory_lock(struct inode *ino) static inline int locks_verify_locked(struct file *file) { - if (mandatory_lock(file_inode(file))) + if (mandatory_lock(locks_inode(file))) return locks_mandatory_locked(file); return 0; } diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 3b00f7c8943f..2473272169f2 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -132,6 +132,7 @@ struct inodes_stat_t { #define MS_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ /* These sb flags are internal to the kernel */ +#define MS_NOREMOTELOCK (1<<27) #define MS_NOSEC (1<<28) #define MS_BORN (1<<29) #define MS_ACTIVE (1<<30) -- cgit v1.2.3 From cfc7381b3002756b1dcada32979e942aa3126e31 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 15 Sep 2016 13:00:29 -0700 Subject: ip_tunnel: add collect_md mode to IPIP tunnel Similar to gre, vxlan, geneve tunnels allow IPIP tunnels to operate in 'collect metadata' mode. bpf_skb_[gs]et_tunnel_key() helpers can make use of it right away. ovs can use it as well in the future (once appropriate ovs-vport abstractions and user apis are added). Note that just like in other tunnels we cannot cache the dst, since tunnel_info metadata can be different for every packet. Signed-off-by: Alexei Starovoitov Acked-by: Thomas Graf Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/net/ip_tunnels.h | 2 ++ include/uapi/linux/if_tunnel.h | 1 + net/ipv4/ip_tunnel.c | 76 ++++++++++++++++++++++++++++++++++++++++++ net/ipv4/ipip.c | 35 +++++++++++++++---- 4 files changed, 108 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index e598c639aa6f..59557c07904b 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -255,6 +255,8 @@ void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops); void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, const u8 protocol); +void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, + const u8 proto); int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu); diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 9865c8caedde..18d5dc13985d 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -73,6 +73,7 @@ enum { IFLA_IPTUN_ENCAP_FLAGS, IFLA_IPTUN_ENCAP_SPORT, IFLA_IPTUN_ENCAP_DPORT, + IFLA_IPTUN_COLLECT_METADATA, __IFLA_IPTUN_MAX, }; #define IFLA_IPTUN_MAX (__IFLA_IPTUN_MAX - 1) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 95649ebd2874..5719d6ba0824 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -55,6 +55,7 @@ #include #include #include +#include #if IS_ENABLED(CONFIG_IPV6) #include @@ -546,6 +547,81 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, return 0; } +void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + u32 headroom = sizeof(struct iphdr); + struct ip_tunnel_info *tun_info; + const struct ip_tunnel_key *key; + const struct iphdr *inner_iph; + struct rtable *rt; + struct flowi4 fl4; + __be16 df = 0; + u8 tos, ttl; + + tun_info = skb_tunnel_info(skb); + if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || + ip_tunnel_info_af(tun_info) != AF_INET)) + goto tx_error; + key = &tun_info->key; + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + inner_iph = (const struct iphdr *)skb_inner_network_header(skb); + tos = key->tos; + if (tos == 1) { + if (skb->protocol == htons(ETH_P_IP)) + tos = inner_iph->tos; + else if (skb->protocol == htons(ETH_P_IPV6)) + tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); + } + init_tunnel_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0, + RT_TOS(tos), tunnel->parms.link); + if (tunnel->encap.type != TUNNEL_ENCAP_NONE) + goto tx_error; + rt = ip_route_output_key(tunnel->net, &fl4); + if (IS_ERR(rt)) { + dev->stats.tx_carrier_errors++; + goto tx_error; + } + if (rt->dst.dev == dev) { + ip_rt_put(rt); + dev->stats.collisions++; + goto tx_error; + } + tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); + ttl = key->ttl; + if (ttl == 0) { + if (skb->protocol == htons(ETH_P_IP)) + ttl = inner_iph->ttl; + else if (skb->protocol == htons(ETH_P_IPV6)) + ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit; + else + ttl = ip4_dst_hoplimit(&rt->dst); + } + if (key->tun_flags & TUNNEL_DONT_FRAGMENT) + df = htons(IP_DF); + else if (skb->protocol == htons(ETH_P_IP)) + df = inner_iph->frag_off & htons(IP_DF); + headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; + if (headroom > dev->needed_headroom) + dev->needed_headroom = headroom; + + if (skb_cow_head(skb, dev->needed_headroom)) { + ip_rt_put(rt); + goto tx_dropped; + } + iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, key->tos, + key->ttl, df, !net_eq(tunnel->net, dev_net(dev))); + return; +tx_error: + dev->stats.tx_errors++; + goto kfree; +tx_dropped: + dev->stats.tx_dropped++; +kfree: + kfree_skb(skb); +} +EXPORT_SYMBOL_GPL(ip_md_tunnel_xmit); + void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, u8 protocol) { diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 4ae3f8e6c6cc..c9392589c415 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -115,6 +115,7 @@ #include #include #include +#include static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); @@ -193,6 +194,7 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) { struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); + struct metadata_dst *tun_dst = NULL; struct ip_tunnel *tunnel; const struct iphdr *iph; @@ -216,7 +218,12 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) tpi = &ipip_tpi; if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; - return ip_tunnel_rcv(tunnel, skb, tpi, NULL, log_ecn_error); + if (tunnel->collect_md) { + tun_dst = ip_tun_rx_dst(skb, 0, 0, 0); + if (!tun_dst) + return 0; + } + return ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); } return -1; @@ -270,7 +277,10 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, skb_set_inner_ipproto(skb, ipproto); - ip_tunnel_xmit(skb, dev, tiph, ipproto); + if (tunnel->collect_md) + ip_md_tunnel_xmit(skb, dev, ipproto); + else + ip_tunnel_xmit(skb, dev, tiph, ipproto); return NETDEV_TX_OK; tx_error: @@ -380,13 +390,14 @@ static int ipip_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) } static void ipip_netlink_parms(struct nlattr *data[], - struct ip_tunnel_parm *parms) + struct ip_tunnel_parm *parms, bool *collect_md) { memset(parms, 0, sizeof(*parms)); parms->iph.version = 4; parms->iph.protocol = IPPROTO_IPIP; parms->iph.ihl = 5; + *collect_md = false; if (!data) return; @@ -414,6 +425,9 @@ static void ipip_netlink_parms(struct nlattr *data[], if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC])) parms->iph.frag_off = htons(IP_DF); + + if (data[IFLA_IPTUN_COLLECT_METADATA]) + *collect_md = true; } /* This function returns true when ENCAP attributes are present in the nl msg */ @@ -453,18 +467,18 @@ static bool ipip_netlink_encap_parms(struct nlattr *data[], static int ipip_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { + struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; if (ipip_netlink_encap_parms(data, &ipencap)) { - struct ip_tunnel *t = netdev_priv(dev); int err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } - ipip_netlink_parms(data, &p); + ipip_netlink_parms(data, &p, &t->collect_md); return ip_tunnel_newlink(dev, tb, &p); } @@ -473,6 +487,7 @@ static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], { struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; + bool collect_md; if (ipip_netlink_encap_parms(data, &ipencap)) { struct ip_tunnel *t = netdev_priv(dev); @@ -482,7 +497,9 @@ static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], return err; } - ipip_netlink_parms(data, &p); + ipip_netlink_parms(data, &p, &collect_md); + if (collect_md) + return -EINVAL; if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) || (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr)) @@ -516,6 +533,8 @@ static size_t ipip_get_size(const struct net_device *dev) nla_total_size(2) + /* IFLA_IPTUN_ENCAP_DPORT */ nla_total_size(2) + + /* IFLA_IPTUN_COLLECT_METADATA */ + nla_total_size(0) + 0; } @@ -544,6 +563,9 @@ static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev) tunnel->encap.flags)) goto nla_put_failure; + if (tunnel->collect_md) + if (nla_put_flag(skb, IFLA_IPTUN_COLLECT_METADATA)) + goto nla_put_failure; return 0; nla_put_failure: @@ -562,6 +584,7 @@ static const struct nla_policy ipip_policy[IFLA_IPTUN_MAX + 1] = { [IFLA_IPTUN_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_DPORT] = { .type = NLA_U16 }, + [IFLA_IPTUN_COLLECT_METADATA] = { .type = NLA_FLAG }, }; static struct rtnl_link_ops ipip_link_ops __read_mostly = { -- cgit v1.2.3 From 69ae6ad2ff37911903a90256e216d7e7ae460002 Mon Sep 17 00:00:00 2001 From: Nogah Frankel Date: Fri, 16 Sep 2016 15:05:37 +0200 Subject: net: core: Add offload stats to if_stats_msg Add a nested attribute of offload stats to if_stats_msg named IFLA_STATS_LINK_OFFLOAD_XSTATS. Under it, add SW stats, meaning stats only per packets that went via slowpath to the cpu, named IFLA_OFFLOAD_XSTATS_CPU_HIT. Signed-off-by: Nogah Frankel Signed-off-by: Jiri Pirko Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 9 ++++ net/core/rtnetlink.c | 111 +++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 116 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 9bf3aecfe05b..2351776a724f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -826,6 +826,7 @@ enum { IFLA_STATS_LINK_64, IFLA_STATS_LINK_XSTATS, IFLA_STATS_LINK_XSTATS_SLAVE, + IFLA_STATS_LINK_OFFLOAD_XSTATS, __IFLA_STATS_MAX, }; @@ -845,6 +846,14 @@ enum { }; #define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1) +/* These are stats embedded into IFLA_STATS_LINK_OFFLOAD_XSTATS */ +enum { + IFLA_OFFLOAD_XSTATS_UNSPEC, + IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */ + __IFLA_OFFLOAD_XSTATS_MAX +}; +#define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1) + /* XDP section */ enum { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 937e459bdaa9..0dbae4244a89 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3577,6 +3577,91 @@ static bool stats_attr_valid(unsigned int mask, int attrid, int idxattr) (!idxattr || idxattr == attrid); } +#define IFLA_OFFLOAD_XSTATS_FIRST (IFLA_OFFLOAD_XSTATS_UNSPEC + 1) +static int rtnl_get_offload_stats_attr_size(int attr_id) +{ + switch (attr_id) { + case IFLA_OFFLOAD_XSTATS_CPU_HIT: + return sizeof(struct rtnl_link_stats64); + } + + return 0; +} + +static int rtnl_get_offload_stats(struct sk_buff *skb, struct net_device *dev, + int *prividx) +{ + struct nlattr *attr = NULL; + int attr_id, size; + void *attr_data; + int err; + + if (!(dev->netdev_ops && dev->netdev_ops->ndo_has_offload_stats && + dev->netdev_ops->ndo_get_offload_stats)) + return -ENODATA; + + for (attr_id = IFLA_OFFLOAD_XSTATS_FIRST; + attr_id <= IFLA_OFFLOAD_XSTATS_MAX; attr_id++) { + if (attr_id < *prividx) + continue; + + size = rtnl_get_offload_stats_attr_size(attr_id); + if (!size) + continue; + + if (!dev->netdev_ops->ndo_has_offload_stats(attr_id)) + continue; + + attr = nla_reserve_64bit(skb, attr_id, size, + IFLA_OFFLOAD_XSTATS_UNSPEC); + if (!attr) + goto nla_put_failure; + + attr_data = nla_data(attr); + memset(attr_data, 0, size); + err = dev->netdev_ops->ndo_get_offload_stats(attr_id, dev, + attr_data); + if (err) + goto get_offload_stats_failure; + } + + if (!attr) + return -ENODATA; + + *prividx = 0; + return 0; + +nla_put_failure: + err = -EMSGSIZE; +get_offload_stats_failure: + *prividx = attr_id; + return err; +} + +static int rtnl_get_offload_stats_size(const struct net_device *dev) +{ + int nla_size = 0; + int attr_id; + int size; + + if (!(dev->netdev_ops && dev->netdev_ops->ndo_has_offload_stats && + dev->netdev_ops->ndo_get_offload_stats)) + return 0; + + for (attr_id = IFLA_OFFLOAD_XSTATS_FIRST; + attr_id <= IFLA_OFFLOAD_XSTATS_MAX; attr_id++) { + if (!dev->netdev_ops->ndo_has_offload_stats(attr_id)) + continue; + size = rtnl_get_offload_stats_attr_size(attr_id); + nla_size += nla_total_size_64bit(size); + } + + if (nla_size != 0) + nla_size += nla_total_size(0); + + return nla_size; +} + static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags, unsigned int filter_mask, @@ -3586,6 +3671,7 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, struct nlmsghdr *nlh; struct nlattr *attr; int s_prividx = *prividx; + int err; ASSERT_RTNL(); @@ -3614,8 +3700,6 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, const struct rtnl_link_ops *ops = dev->rtnl_link_ops; if (ops && ops->fill_linkxstats) { - int err; - *idxattr = IFLA_STATS_LINK_XSTATS; attr = nla_nest_start(skb, IFLA_STATS_LINK_XSTATS); @@ -3639,8 +3723,6 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, if (master) ops = master->rtnl_link_ops; if (ops && ops->fill_linkxstats) { - int err; - *idxattr = IFLA_STATS_LINK_XSTATS_SLAVE; attr = nla_nest_start(skb, IFLA_STATS_LINK_XSTATS_SLAVE); @@ -3655,6 +3737,24 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, } } + if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_OFFLOAD_XSTATS, + *idxattr)) { + *idxattr = IFLA_STATS_LINK_OFFLOAD_XSTATS; + attr = nla_nest_start(skb, IFLA_STATS_LINK_OFFLOAD_XSTATS); + if (!attr) + goto nla_put_failure; + + err = rtnl_get_offload_stats(skb, dev, prividx); + if (err == -ENODATA) + nla_nest_cancel(skb, attr); + else + nla_nest_end(skb, attr); + + if (err && err != -ENODATA) + goto nla_put_failure; + *idxattr = 0; + } + nlmsg_end(skb, nlh); return 0; @@ -3708,6 +3808,9 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev, } } + if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_OFFLOAD_XSTATS, 0)) + size += rtnl_get_offload_stats_size(dev); + return size; } -- cgit v1.2.3 From 4fbae7d83c98c30efcf0a2a2ac55fbb75ef5a1a5 Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Fri, 16 Sep 2016 12:59:19 -0700 Subject: ipvlan: Introduce l3s mode In a typical IPvlan L3 setup where master is in default-ns and each slave is into different (slave) ns. In this setup egress packet processing for traffic originating from slave-ns will hit all NF_HOOKs in slave-ns as well as default-ns. However same is not true for ingress processing. All these NF_HOOKs are hit only in the slave-ns skipping them in the default-ns. IPvlan in L3 mode is restrictive and if admins want to deploy iptables rules in default-ns, this asymmetric data path makes it impossible to do so. This patch makes use of the l3_rcv() (added as part of l3mdev enhancements) to perform input route lookup on RX packets without changing the skb->dev and then uses nf_hook at NF_INET_LOCAL_IN to change the skb->dev just before handing over skb to L4. Signed-off-by: Mahesh Bandewar CC: David Ahern Reviewed-by: David Ahern Signed-off-by: David S. Miller --- Documentation/networking/ipvlan.txt | 7 ++- drivers/net/Kconfig | 1 + drivers/net/ipvlan/ipvlan.h | 6 +++ drivers/net/ipvlan/ipvlan_core.c | 94 +++++++++++++++++++++++++++++++++++++ drivers/net/ipvlan/ipvlan_main.c | 87 +++++++++++++++++++++++++++++++--- include/uapi/linux/if_link.h | 1 + 6 files changed, 188 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ipvlan.txt b/Documentation/networking/ipvlan.txt index 14422f8fcdc4..24196cef7c91 100644 --- a/Documentation/networking/ipvlan.txt +++ b/Documentation/networking/ipvlan.txt @@ -22,7 +22,7 @@ The driver can be built into the kernel (CONFIG_IPVLAN=y) or as a module There are no module parameters for this driver and it can be configured using IProute2/ip utility. - ip link add link type ipvlan mode { l2 | L3 } + ip link add link type ipvlan mode { l2 | l3 | l3s } e.g. ip link add link ipvl0 eth0 type ipvlan mode l2 @@ -48,6 +48,11 @@ master device for the L2 processing and routing from that instance will be used before packets are queued on the outbound device. In this mode the slaves will not receive nor can send multicast / broadcast traffic. +4.3 L3S mode: + This is very similar to the L3 mode except that iptables (conn-tracking) +works in this mode and hence it is L3-symmetric (L3s). This will have slightly less +performance but that shouldn't matter since you are choosing this mode over plain-L3 +mode to make conn-tracking work. 5. What to choose (macvlan vs. ipvlan)? These two devices are very similar in many regards and the specific use diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 0c5415b05ea9..8768a625350d 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -149,6 +149,7 @@ config IPVLAN tristate "IP-VLAN support" depends on INET depends on IPV6 + depends on NET_L3_MASTER_DEV ---help--- This allows one to create virtual devices off of a main interface and packets will be delivered based on the dest L3 (IPv6/IPv4 addr) diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index 695a5dc9ace3..7e0732f5ea07 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -23,11 +23,13 @@ #include #include #include +#include #include #include #include #include #include +#include #define IPVLAN_DRV "ipvlan" #define IPV_DRV_VER "0.1" @@ -124,4 +126,8 @@ struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan, const void *iaddr, bool is_v6); bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6); void ipvlan_ht_addr_del(struct ipvl_addr *addr); +struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, struct sk_buff *skb, + u16 proto); +unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state); #endif /* __IPVLAN_H */ diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index b5f9511d819e..b4e990743e1d 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -560,6 +560,7 @@ int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) case IPVLAN_MODE_L2: return ipvlan_xmit_mode_l2(skb, dev); case IPVLAN_MODE_L3: + case IPVLAN_MODE_L3S: return ipvlan_xmit_mode_l3(skb, dev); } @@ -664,6 +665,8 @@ rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb) return ipvlan_handle_mode_l2(pskb, port); case IPVLAN_MODE_L3: return ipvlan_handle_mode_l3(pskb, port); + case IPVLAN_MODE_L3S: + return RX_HANDLER_PASS; } /* Should not reach here */ @@ -672,3 +675,94 @@ rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb) kfree_skb(skb); return RX_HANDLER_CONSUMED; } + +static struct ipvl_addr *ipvlan_skb_to_addr(struct sk_buff *skb, + struct net_device *dev) +{ + struct ipvl_addr *addr = NULL; + struct ipvl_port *port; + void *lyr3h; + int addr_type; + + if (!dev || !netif_is_ipvlan_port(dev)) + goto out; + + port = ipvlan_port_get_rcu(dev); + if (!port || port->mode != IPVLAN_MODE_L3S) + goto out; + + lyr3h = ipvlan_get_L3_hdr(skb, &addr_type); + if (!lyr3h) + goto out; + + addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true); +out: + return addr; +} + +struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, struct sk_buff *skb, + u16 proto) +{ + struct ipvl_addr *addr; + struct net_device *sdev; + + addr = ipvlan_skb_to_addr(skb, dev); + if (!addr) + goto out; + + sdev = addr->master->dev; + switch (proto) { + case AF_INET: + { + int err; + struct iphdr *ip4h = ip_hdr(skb); + + err = ip_route_input_noref(skb, ip4h->daddr, ip4h->saddr, + ip4h->tos, sdev); + if (unlikely(err)) + goto out; + break; + } + case AF_INET6: + { + struct dst_entry *dst; + struct ipv6hdr *ip6h = ipv6_hdr(skb); + int flags = RT6_LOOKUP_F_HAS_SADDR; + struct flowi6 fl6 = { + .flowi6_iif = sdev->ifindex, + .daddr = ip6h->daddr, + .saddr = ip6h->saddr, + .flowlabel = ip6_flowinfo(ip6h), + .flowi6_mark = skb->mark, + .flowi6_proto = ip6h->nexthdr, + }; + + skb_dst_drop(skb); + dst = ip6_route_input_lookup(dev_net(sdev), sdev, &fl6, flags); + skb_dst_set(skb, dst); + break; + } + default: + break; + } + +out: + return skb; +} + +unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct ipvl_addr *addr; + unsigned int len; + + addr = ipvlan_skb_to_addr(skb, skb->dev); + if (!addr) + goto out; + + skb->dev = addr->master->dev; + len = skb->len + ETH_HLEN; + ipvlan_count_rx(addr->master, len, true, false); +out: + return NF_ACCEPT; +} diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 18b4e8c7f68a..f442eb366863 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -9,24 +9,87 @@ #include "ipvlan.h" +static u32 ipvl_nf_hook_refcnt = 0; + +static struct nf_hook_ops ipvl_nfops[] __read_mostly = { + { + .hook = ipvlan_nf_input, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_IN, + .priority = INT_MAX, + }, + { + .hook = ipvlan_nf_input, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = INT_MAX, + }, +}; + +static struct l3mdev_ops ipvl_l3mdev_ops __read_mostly = { + .l3mdev_l3_rcv = ipvlan_l3_rcv, +}; + static void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev) { ipvlan->dev->mtu = dev->mtu - ipvlan->mtu_adj; } -static void ipvlan_set_port_mode(struct ipvl_port *port, u16 nval) +static int ipvlan_register_nf_hook(void) +{ + int err = 0; + + if (!ipvl_nf_hook_refcnt) { + err = _nf_register_hooks(ipvl_nfops, ARRAY_SIZE(ipvl_nfops)); + if (!err) + ipvl_nf_hook_refcnt = 1; + } else { + ipvl_nf_hook_refcnt++; + } + + return err; +} + +static void ipvlan_unregister_nf_hook(void) +{ + WARN_ON(!ipvl_nf_hook_refcnt); + + ipvl_nf_hook_refcnt--; + if (!ipvl_nf_hook_refcnt) + _nf_unregister_hooks(ipvl_nfops, ARRAY_SIZE(ipvl_nfops)); +} + +static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval) { struct ipvl_dev *ipvlan; + struct net_device *mdev = port->dev; + int err = 0; + ASSERT_RTNL(); if (port->mode != nval) { + if (nval == IPVLAN_MODE_L3S) { + /* New mode is L3S */ + err = ipvlan_register_nf_hook(); + if (!err) { + mdev->l3mdev_ops = &ipvl_l3mdev_ops; + mdev->priv_flags |= IFF_L3MDEV_MASTER; + } else + return err; + } else if (port->mode == IPVLAN_MODE_L3S) { + /* Old mode was L3S */ + mdev->priv_flags &= ~IFF_L3MDEV_MASTER; + ipvlan_unregister_nf_hook(); + mdev->l3mdev_ops = NULL; + } list_for_each_entry(ipvlan, &port->ipvlans, pnode) { - if (nval == IPVLAN_MODE_L3) + if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) ipvlan->dev->flags |= IFF_NOARP; else ipvlan->dev->flags &= ~IFF_NOARP; } port->mode = nval; } + return err; } static int ipvlan_port_create(struct net_device *dev) @@ -74,6 +137,11 @@ static void ipvlan_port_destroy(struct net_device *dev) struct ipvl_port *port = ipvlan_port_get_rtnl(dev); dev->priv_flags &= ~IFF_IPVLAN_MASTER; + if (port->mode == IPVLAN_MODE_L3S) { + dev->priv_flags &= ~IFF_L3MDEV_MASTER; + ipvlan_unregister_nf_hook(); + dev->l3mdev_ops = NULL; + } netdev_rx_handler_unregister(dev); cancel_work_sync(&port->wq); __skb_queue_purge(&port->backlog); @@ -132,7 +200,8 @@ static int ipvlan_open(struct net_device *dev) struct net_device *phy_dev = ipvlan->phy_dev; struct ipvl_addr *addr; - if (ipvlan->port->mode == IPVLAN_MODE_L3) + if (ipvlan->port->mode == IPVLAN_MODE_L3 || + ipvlan->port->mode == IPVLAN_MODE_L3S) dev->flags |= IFF_NOARP; else dev->flags &= ~IFF_NOARP; @@ -372,13 +441,14 @@ static int ipvlan_nl_changelink(struct net_device *dev, { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev); + int err = 0; if (data && data[IFLA_IPVLAN_MODE]) { u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]); - ipvlan_set_port_mode(port, nmode); + err = ipvlan_set_port_mode(port, nmode); } - return 0; + return err; } static size_t ipvlan_nl_getsize(const struct net_device *dev) @@ -473,10 +543,13 @@ static int ipvlan_link_new(struct net *src_net, struct net_device *dev, unregister_netdevice(dev); return err; } + err = ipvlan_set_port_mode(port, mode); + if (err) { + unregister_netdevice(dev); + return err; + } list_add_tail_rcu(&ipvlan->pnode, &port->ipvlans); - ipvlan_set_port_mode(port, mode); - netif_stacked_transfer_operstate(phy_dev, dev); return 0; } diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 2351776a724f..7ec9e99d5491 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -464,6 +464,7 @@ enum { enum ipvlan_mode { IPVLAN_MODE_L2 = 0, IPVLAN_MODE_L3, + IPVLAN_MODE_L3S, IPVLAN_MODE_MAX }; -- cgit v1.2.3 From 408fbc22ef1efb00dd896acd00e9f7d9b641e047 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sun, 18 Sep 2016 07:31:43 -0400 Subject: net sched ife action: Introduce skb tcindex metadata encap decap Sample use case of how this is encoded: user space via tuntap (or a connected VM/Machine/container) encodes the tcindex TLV. Sample use case of decoding: IFE action decodes it and the skb->tc_index is then used to classify. So something like this for encoded ICMP packets: .. first decode then reclassify... skb->tcindex will be set sudo $TC filter add dev $ETH parent ffff: prio 2 protocol 0xbeef \ u32 match u32 0 0 flowid 1:1 \ action ife decode reclassify ...next match the decode icmp packet... sudo $TC filter add dev $ETH parent ffff: prio 4 protocol ip \ u32 match ip protocol 1 0xff flowid 1:1 \ action continue ... last classify it using the tcindex classifier and do someaction.. sudo $TC filter add dev $ETH parent ffff: prio 5 protocol ip \ handle 0x11 tcindex classid 1:1 \ action blah.. Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/uapi/linux/tc_act/tc_ife.h | 3 +- net/sched/Kconfig | 5 +++ net/sched/Makefile | 1 + net/sched/act_meta_skbtcindex.c | 79 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 87 insertions(+), 1 deletion(-) create mode 100644 net/sched/act_meta_skbtcindex.c (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tc_act/tc_ife.h b/include/uapi/linux/tc_act/tc_ife.h index 4ece02a77b9a..cd18360eca24 100644 --- a/include/uapi/linux/tc_act/tc_ife.h +++ b/include/uapi/linux/tc_act/tc_ife.h @@ -32,8 +32,9 @@ enum { #define IFE_META_HASHID 2 #define IFE_META_PRIO 3 #define IFE_META_QMAP 4 +#define IFE_META_TCINDEX 5 /*Can be overridden at runtime by module option*/ -#define __IFE_META_MAX 5 +#define __IFE_META_MAX 6 #define IFE_META_MAX (__IFE_META_MAX - 1) #endif diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 7795d5a3f79a..87956a768d1b 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -793,6 +793,11 @@ config NET_IFE_SKBPRIO depends on NET_ACT_IFE ---help--- +config NET_IFE_SKBTCINDEX + tristate "Support to encoding decoding skb tcindex on IFE action" + depends on NET_ACT_IFE + ---help--- + config NET_CLS_IND bool "Incoming device classification" depends on NET_CLS_U32 || NET_CLS_FW diff --git a/net/sched/Makefile b/net/sched/Makefile index 148ae0d5ac2c..4bdda3634e0b 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -23,6 +23,7 @@ obj-$(CONFIG_NET_ACT_SKBMOD) += act_skbmod.o obj-$(CONFIG_NET_ACT_IFE) += act_ife.o obj-$(CONFIG_NET_IFE_SKBMARK) += act_meta_mark.o obj-$(CONFIG_NET_IFE_SKBPRIO) += act_meta_skbprio.o +obj-$(CONFIG_NET_IFE_SKBTCINDEX) += act_meta_skbtcindex.o obj-$(CONFIG_NET_ACT_TUNNEL_KEY)+= act_tunnel_key.o obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o obj-$(CONFIG_NET_SCH_CBQ) += sch_cbq.o diff --git a/net/sched/act_meta_skbtcindex.c b/net/sched/act_meta_skbtcindex.c new file mode 100644 index 000000000000..3b35774ce890 --- /dev/null +++ b/net/sched/act_meta_skbtcindex.c @@ -0,0 +1,79 @@ +/* + * net/sched/act_meta_tc_index.c IFE skb->tc_index metadata module + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * copyright Jamal Hadi Salim (2016) + * +*/ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static int skbtcindex_encode(struct sk_buff *skb, void *skbdata, + struct tcf_meta_info *e) +{ + u32 ifetc_index = skb->tc_index; + + return ife_encode_meta_u16(ifetc_index, skbdata, e); +} + +static int skbtcindex_decode(struct sk_buff *skb, void *data, u16 len) +{ + u16 ifetc_index = *(u16 *)data; + + skb->tc_index = ntohs(ifetc_index); + return 0; +} + +static int skbtcindex_check(struct sk_buff *skb, struct tcf_meta_info *e) +{ + return ife_check_meta_u16(skb->tc_index, e); +} + +static struct tcf_meta_ops ife_skbtcindex_ops = { + .metaid = IFE_META_TCINDEX, + .metatype = NLA_U16, + .name = "tc_index", + .synopsis = "skb tc_index 16 bit metadata", + .check_presence = skbtcindex_check, + .encode = skbtcindex_encode, + .decode = skbtcindex_decode, + .get = ife_get_meta_u16, + .alloc = ife_alloc_meta_u16, + .release = ife_release_meta_gen, + .validate = ife_validate_meta_u16, + .owner = THIS_MODULE, +}; + +static int __init ifetc_index_init_module(void) +{ + return register_ife_op(&ife_skbtcindex_ops); +} + +static void __exit ifetc_index_cleanup_module(void) +{ + unregister_ife_op(&ife_skbtcindex_ops); +} + +module_init(ifetc_index_init_module); +module_exit(ifetc_index_cleanup_module); + +MODULE_AUTHOR("Jamal Hadi Salim(2016)"); +MODULE_DESCRIPTION("Inter-FE skb tc_index metadata module"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_IFE_META(IFE_META_SKBTCINDEX); -- cgit v1.2.3 From 823d1bc1082970fc02f8172859c789933ed84bc5 Mon Sep 17 00:00:00 2001 From: Emilio López Date: Mon, 19 Sep 2016 01:21:20 -0300 Subject: dma-buf/sync_file: fix documentation error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The ioctl name and description on the documentation block don't match the ioctl being defined. This was probably overlooked while renaming the ioctls during the sync file destaging. This patch provides a more accurate description of what the ioctl actually does. Signed-off-by: Emilio López Reviewed-by: Gustavo Padovan Signed-off-by: Sumit Semwal Link: http://patchwork.freedesktop.org/patch/msgid/20160919042120.6280-1-emilio.lopez@collabora.co.uk --- include/uapi/linux/sync_file.h | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/sync_file.h b/include/uapi/linux/sync_file.h index 413303d37b56..5b287d6970b3 100644 --- a/include/uapi/linux/sync_file.h +++ b/include/uapi/linux/sync_file.h @@ -85,15 +85,12 @@ struct sync_file_info { #define SYNC_IOC_MERGE _IOWR(SYNC_IOC_MAGIC, 3, struct sync_merge_data) /** - * DOC: SYNC_IOC_FENCE_INFO - get detailed information on a fence + * DOC: SYNC_IOC_FILE_INFO - get detailed information on a sync_file * - * Takes a struct sync_file_info_data with extra space allocated for pt_info. - * Caller should write the size of the buffer into len. On return, len is - * updated to reflect the total size of the sync_file_info_data including - * pt_info. - * - * pt_info is a buffer containing sync_pt_infos for every sync_pt in the fence. - * To iterate over the sync_pt_infos, use the sync_pt_info.len field. + * Takes a struct sync_file_info. If num_fences is 0, the field is updated + * with the actual number of fences. If num_fences is > 0, the system will + * use the pointer provided on sync_fence_info to return up to num_fences of + * struct sync_fence_info, with detailed fence information. */ #define SYNC_IOC_FILE_INFO _IOWR(SYNC_IOC_MAGIC, 4, struct sync_file_info) -- cgit v1.2.3 From 36bbef52c7eb646ed6247055a2acd3851e317857 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 20 Sep 2016 00:26:13 +0200 Subject: bpf: direct packet write and access for helpers for clsact progs This work implements direct packet access for helpers and direct packet write in a similar fashion as already available for XDP types via commits 4acf6c0b84c9 ("bpf: enable direct packet data write for xdp progs") and 6841de8b0d03 ("bpf: allow helpers access the packet directly"), and as a complementary feature to the already available direct packet read for tc (cls/act) programs. For enabling this, we need to introduce two helpers, bpf_skb_pull_data() and bpf_csum_update(). The first is generally needed for both, read and write, because they would otherwise only be limited to the current linear skb head. Usually, when the data_end test fails, programs just bail out, or, in the direct read case, use bpf_skb_load_bytes() as an alternative to overcome this limitation. If such data sits in non-linear parts, we can just pull them in once with the new helper, retest and eventually access them. At the same time, this also makes sure the skb is uncloned, which is, of course, a necessary condition for direct write. As this needs to be an invariant for the write part only, the verifier detects writes and adds a prologue that is calling bpf_skb_pull_data() to effectively unclone the skb from the very beginning in case it is indeed cloned. The heuristic makes use of a similar trick that was done in 233577a22089 ("net: filter: constify detection of pkt_type_offset"). This comes at zero cost for other programs that do not use the direct write feature. Should a program use this feature only sparsely and has read access for the most parts with, for example, drop return codes, then such write action can be delegated to a tail called program for mitigating this cost of potential uncloning to a late point in time where it would have been paid similarly with the bpf_skb_store_bytes() as well. Advantage of direct write is that the writes are inlined whereas the helper cannot make any length assumptions and thus needs to generate a call to memcpy() also for small sizes, as well as cost of helper call itself with sanity checks are avoided. Plus, when direct read is already used, we don't need to cache or perform rechecks on the data boundaries (due to verifier invalidating previous checks for helpers that change skb->data), so more complex programs using rewrites can benefit from switching to direct read plus write. For direct packet access to helpers, we save the otherwise needed copy into a temp struct sitting on stack memory when use-case allows. Both facilities are enabled via may_access_direct_pkt_data() in verifier. For now, we limit this to map helpers and csum_diff, and can successively enable other helpers where we find it makes sense. Helpers that definitely cannot be allowed for this are those part of bpf_helper_changes_skb_data() since they can change underlying data, and those that write into memory as this could happen for packet typed args when still cloned. bpf_csum_update() helper accommodates for the fact that we need to fixup checksum_complete when using direct write instead of bpf_skb_store_bytes(), meaning the programs can use available helpers like bpf_csum_diff(), and implement csum_add(), csum_sub(), csum_block_add(), csum_block_sub() equivalents in eBPF together with the new helper. A usage example will be provided for iproute2's examples/bpf/ directory. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 4 +- include/linux/skbuff.h | 14 ++++- include/uapi/linux/bpf.h | 21 ++++++++ kernel/bpf/helpers.c | 3 ++ kernel/bpf/verifier.c | 54 ++++++++++++++----- net/core/filter.c | 134 +++++++++++++++++++++++++++++++++++++++++------ 6 files changed, 196 insertions(+), 34 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9a904f63f8c1..5691fdc83819 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -96,6 +96,7 @@ enum bpf_return_type { struct bpf_func_proto { u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); bool gpl_only; + bool pkt_access; enum bpf_return_type ret_type; enum bpf_arg_type arg1_type; enum bpf_arg_type arg2_type; @@ -151,7 +152,8 @@ struct bpf_verifier_ops { */ bool (*is_valid_access)(int off, int size, enum bpf_access_type type, enum bpf_reg_type *reg_type); - + int (*gen_prologue)(struct bpf_insn *insn, bool direct_write, + const struct bpf_prog *prog); u32 (*convert_ctx_access)(enum bpf_access_type type, int dst_reg, int src_reg, int ctx_off, struct bpf_insn *insn, struct bpf_prog *prog); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4c5662f05bda..c6dab3f7457c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -676,13 +676,23 @@ struct sk_buff { */ kmemcheck_bitfield_begin(flags1); __u16 queue_mapping; + +/* if you move cloned around you also must adapt those constants */ +#ifdef __BIG_ENDIAN_BITFIELD +#define CLONED_MASK (1 << 7) +#else +#define CLONED_MASK 1 +#endif +#define CLONED_OFFSET() offsetof(struct sk_buff, __cloned_offset) + + __u8 __cloned_offset[0]; __u8 cloned:1, nohdr:1, fclone:2, peeked:1, head_frag:1, - xmit_more:1; - /* one bit hole */ + xmit_more:1, + __unused:1; /* one bit hole */ kmemcheck_bitfield_end(flags1); /* fields enclosed in headers_start/headers_end are copied diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f896dfac4ac0..e07432b9f8b8 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -398,6 +398,27 @@ enum bpf_func_id { */ 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_FUNC_MAX_ID, }; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a5b8bf8cfcfd..39918402e6e9 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -36,6 +36,7 @@ BPF_CALL_2(bpf_map_lookup_elem, struct bpf_map *, map, void *, key) const struct bpf_func_proto bpf_map_lookup_elem_proto = { .func = bpf_map_lookup_elem, .gpl_only = false, + .pkt_access = true, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_MAP_KEY, @@ -51,6 +52,7 @@ BPF_CALL_4(bpf_map_update_elem, struct bpf_map *, map, void *, key, const struct bpf_func_proto bpf_map_update_elem_proto = { .func = bpf_map_update_elem, .gpl_only = false, + .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_MAP_KEY, @@ -67,6 +69,7 @@ BPF_CALL_2(bpf_map_delete_elem, struct bpf_map *, map, void *, key) const struct bpf_func_proto bpf_map_delete_elem_proto = { .func = bpf_map_delete_elem, .gpl_only = false, + .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_MAP_KEY, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index bc138f34e38c..3a75ee3bdcd1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -196,6 +196,7 @@ struct verifier_env { u32 used_map_cnt; /* number of used maps */ u32 id_gen; /* used to generate unique reg IDs */ bool allow_ptr_leaks; + bool seen_direct_write; }; #define BPF_COMPLEXITY_LIMIT_INSNS 65536 @@ -204,6 +205,7 @@ struct verifier_env { struct bpf_call_arg_meta { struct bpf_map *map_ptr; bool raw_mode; + bool pkt_access; int regno; int access_size; }; @@ -654,10 +656,17 @@ static int check_map_access(struct verifier_env *env, u32 regno, int off, #define MAX_PACKET_OFF 0xffff -static bool may_write_pkt_data(enum bpf_prog_type type) +static bool may_access_direct_pkt_data(struct verifier_env *env, + const struct bpf_call_arg_meta *meta) { - switch (type) { + switch (env->prog->type) { + case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: + if (meta) + return meta->pkt_access; + + env->seen_direct_write = true; return true; default: return false; @@ -817,7 +826,7 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off, err = check_stack_read(state, off, size, value_regno); } } else if (state->regs[regno].type == PTR_TO_PACKET) { - if (t == BPF_WRITE && !may_write_pkt_data(env->prog->type)) { + if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL)) { verbose("cannot write into packet\n"); return -EACCES; } @@ -950,8 +959,8 @@ static int check_func_arg(struct verifier_env *env, u32 regno, return 0; } - if (type == PTR_TO_PACKET && !may_write_pkt_data(env->prog->type)) { - verbose("helper access to the packet is not allowed for clsact\n"); + if (type == PTR_TO_PACKET && !may_access_direct_pkt_data(env, meta)) { + verbose("helper access to the packet is not allowed\n"); return -EACCES; } @@ -1191,6 +1200,7 @@ static int check_call(struct verifier_env *env, int func_id) changes_data = bpf_helper_changes_skb_data(fn->func); memset(&meta, 0, sizeof(meta)); + meta.pkt_access = fn->pkt_access; /* We only support one arg being in raw mode at the moment, which * is sufficient for the helper functions we have right now. @@ -2675,18 +2685,35 @@ static void convert_pseudo_ld_imm64(struct verifier_env *env) */ static int convert_ctx_accesses(struct verifier_env *env) { - struct bpf_insn *insn = env->prog->insnsi; - int insn_cnt = env->prog->len; - struct bpf_insn insn_buf[16]; + const struct bpf_verifier_ops *ops = env->prog->aux->ops; + struct bpf_insn insn_buf[16], *insn; struct bpf_prog *new_prog; enum bpf_access_type type; - int i; + int i, insn_cnt, cnt; - if (!env->prog->aux->ops->convert_ctx_access) + if (ops->gen_prologue) { + cnt = ops->gen_prologue(insn_buf, env->seen_direct_write, + env->prog); + if (cnt >= ARRAY_SIZE(insn_buf)) { + verbose("bpf verifier is misconfigured\n"); + return -EINVAL; + } else if (cnt) { + new_prog = bpf_patch_insn_single(env->prog, 0, + insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + env->prog = new_prog; + } + } + + if (!ops->convert_ctx_access) return 0; + insn_cnt = env->prog->len; + insn = env->prog->insnsi; + for (i = 0; i < insn_cnt; i++, insn++) { - u32 insn_delta, cnt; + u32 insn_delta; if (insn->code == (BPF_LDX | BPF_MEM | BPF_W) || insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) @@ -2703,9 +2730,8 @@ static int convert_ctx_accesses(struct verifier_env *env) continue; } - cnt = env->prog->aux->ops-> - convert_ctx_access(type, insn->dst_reg, insn->src_reg, - insn->off, insn_buf, env->prog); + cnt = ops->convert_ctx_access(type, insn->dst_reg, insn->src_reg, + insn->off, insn_buf, env->prog); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { verbose("bpf verifier is misconfigured\n"); return -EINVAL; diff --git a/net/core/filter.c b/net/core/filter.c index 298b146b47e7..0920c2ac1d00 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1362,6 +1362,11 @@ static inline int bpf_try_make_writable(struct sk_buff *skb, return err; } +static int bpf_try_make_head_writable(struct sk_buff *skb) +{ + return bpf_try_make_writable(skb, skb_headlen(skb)); +} + static inline void bpf_push_mac_rcsum(struct sk_buff *skb) { if (skb_at_tc_ingress(skb)) @@ -1441,6 +1446,28 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = { .arg4_type = ARG_CONST_STACK_SIZE, }; +BPF_CALL_2(bpf_skb_pull_data, struct sk_buff *, skb, u32, len) +{ + /* Idea is the following: should the needed direct read/write + * test fail during runtime, we can pull in more data and redo + * again, since implicitly, we invalidate previous checks here. + * + * Or, since we know how much we need to make read/writeable, + * this can be done once at the program beginning for direct + * access case. By this we overcome limitations of only current + * headroom being accessible. + */ + return bpf_try_make_writable(skb, len ? : skb_headlen(skb)); +} + +static const struct bpf_func_proto bpf_skb_pull_data_proto = { + .func = bpf_skb_pull_data, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset, u64, from, u64, to, u64, flags) { @@ -1567,6 +1594,7 @@ BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size, static const struct bpf_func_proto bpf_csum_diff_proto = { .func = bpf_csum_diff, .gpl_only = false, + .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_STACK, .arg2_type = ARG_CONST_STACK_SIZE_OR_ZERO, @@ -1575,6 +1603,26 @@ static const struct bpf_func_proto bpf_csum_diff_proto = { .arg5_type = ARG_ANYTHING, }; +BPF_CALL_2(bpf_csum_update, struct sk_buff *, skb, __wsum, csum) +{ + /* The interface is to be used in combination with bpf_csum_diff() + * for direct packet writes. csum rotation for alignment as well + * as emulating csum_sub() can be done from the eBPF program. + */ + if (skb->ip_summed == CHECKSUM_COMPLETE) + return (skb->csum = csum_add(skb->csum, csum)); + + return -ENOTSUPP; +} + +static const struct bpf_func_proto bpf_csum_update_proto = { + .func = bpf_csum_update, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb) { return dev_forward_skb(dev, skb); @@ -1602,6 +1650,8 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) { struct net_device *dev; + struct sk_buff *clone; + int ret; if (unlikely(flags & ~(BPF_F_INGRESS))) return -EINVAL; @@ -1610,14 +1660,25 @@ BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) if (unlikely(!dev)) return -EINVAL; - skb = skb_clone(skb, GFP_ATOMIC); - if (unlikely(!skb)) + clone = skb_clone(skb, GFP_ATOMIC); + if (unlikely(!clone)) return -ENOMEM; - bpf_push_mac_rcsum(skb); + /* For direct write, we need to keep the invariant that the skbs + * we're dealing with need to be uncloned. Should uncloning fail + * here, we need to free the just generated clone to unclone once + * again. + */ + ret = bpf_try_make_head_writable(skb); + if (unlikely(ret)) { + kfree_skb(clone); + return -ENOMEM; + } + + bpf_push_mac_rcsum(clone); return flags & BPF_F_INGRESS ? - __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb); + __bpf_rx_skb(dev, clone) : __bpf_tx_skb(dev, clone); } static const struct bpf_func_proto bpf_clone_redirect_proto = { @@ -2063,19 +2124,14 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = { bool bpf_helper_changes_skb_data(void *func) { - if (func == bpf_skb_vlan_push) - return true; - if (func == bpf_skb_vlan_pop) - return true; - if (func == bpf_skb_store_bytes) - return true; - if (func == bpf_skb_change_proto) - return true; - if (func == bpf_skb_change_tail) - return true; - if (func == bpf_l3_csum_replace) - return true; - if (func == bpf_l4_csum_replace) + if (func == bpf_skb_vlan_push || + func == bpf_skb_vlan_pop || + func == bpf_skb_store_bytes || + func == bpf_skb_change_proto || + func == bpf_skb_change_tail || + func == bpf_skb_pull_data || + func == bpf_l3_csum_replace || + func == bpf_l4_csum_replace) return true; return false; @@ -2440,8 +2496,12 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_skb_store_bytes_proto; case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; + case BPF_FUNC_skb_pull_data: + return &bpf_skb_pull_data_proto; case BPF_FUNC_csum_diff: return &bpf_csum_diff_proto; + case BPF_FUNC_csum_update: + return &bpf_csum_update_proto; case BPF_FUNC_l3_csum_replace: return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: @@ -2533,6 +2593,45 @@ static bool sk_filter_is_valid_access(int off, int size, return __is_valid_access(off, size, type); } +static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write, + const struct bpf_prog *prog) +{ + struct bpf_insn *insn = insn_buf; + + if (!direct_write) + return 0; + + /* if (!skb->cloned) + * goto start; + * + * (Fast-path, otherwise approximation that we might be + * a clone, do the rest in helper.) + */ + *insn++ = BPF_LDX_MEM(BPF_B, BPF_REG_6, BPF_REG_1, CLONED_OFFSET()); + *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_6, CLONED_MASK); + *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 7); + + /* ret = bpf_skb_pull_data(skb, 0); */ + *insn++ = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); + *insn++ = BPF_ALU64_REG(BPF_XOR, BPF_REG_2, BPF_REG_2); + *insn++ = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_pull_data); + /* if (!ret) + * goto restore; + * return TC_ACT_SHOT; + */ + *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2); + *insn++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, TC_ACT_SHOT); + *insn++ = BPF_EXIT_INSN(); + + /* restore: */ + *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); + /* start: */ + *insn++ = prog->insnsi[0]; + + return insn - insn_buf; +} + static bool tc_cls_act_is_valid_access(int off, int size, enum bpf_access_type type, enum bpf_reg_type *reg_type) @@ -2810,6 +2909,7 @@ static const struct bpf_verifier_ops tc_cls_act_ops = { .get_func_proto = tc_cls_act_func_proto, .is_valid_access = tc_cls_act_is_valid_access, .convert_ctx_access = tc_cls_act_convert_ctx_access, + .gen_prologue = tc_cls_act_prologue, }; static const struct bpf_verifier_ops xdp_ops = { -- cgit v1.2.3 From 77879147a3481babffd7e368d977ab682545a6bd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 19 Sep 2016 23:39:11 -0400 Subject: net_sched: sch_fq: add low_rate_threshold parameter This commit adds to the fq module a low_rate_threshold parameter to insert a delay after all packets if the socket requests a pacing rate below the threshold. This helps achieve more precise control of the sending rate with low-rate paths, especially policers. The basic issue is that if a congestion control module detects a policer at a certain rate, it may want fq to be able to shape to that policed rate. That way the sender can avoid policer drops by having the packets arrive at the policer at or just under the policed rate. The default threshold of 550Kbps was chosen analytically so that for policers or links at 500Kbps or 512Kbps fq would very likely invoke this mechanism, even if the pacing rate was briefly slightly above the available bandwidth. This value was then empirically validated with two years of production testing on YouTube video servers. Signed-off-by: Van Jacobson Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Nandita Dukkipati Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 2 ++ net/sched/sch_fq.c | 22 +++++++++++++++++++--- 2 files changed, 21 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 2382eed50278..f8e39dbaa781 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -792,6 +792,8 @@ enum { TCA_FQ_ORPHAN_MASK, /* mask applied to orphaned skb hashes */ + TCA_FQ_LOW_RATE_THRESHOLD, /* per packet delay under this rate */ + __TCA_FQ_MAX }; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index dc52cc10d6ed..5dd929cc1423 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -94,6 +94,7 @@ struct fq_sched_data { u32 flow_max_rate; /* optional max rate per flow */ u32 flow_plimit; /* max packets per flow */ u32 orphan_mask; /* mask for orphaned skb */ + u32 low_rate_threshold; struct rb_root *fq_root; u8 rate_enable; u8 fq_trees_log; @@ -433,7 +434,7 @@ static struct sk_buff *fq_dequeue(struct Qdisc *sch) struct fq_flow_head *head; struct sk_buff *skb; struct fq_flow *f; - u32 rate; + u32 rate, plen; skb = fq_dequeue_head(sch, &q->internal); if (skb) @@ -482,7 +483,7 @@ begin: prefetch(&skb->end); f->credit -= qdisc_pkt_len(skb); - if (f->credit > 0 || !q->rate_enable) + if (!q->rate_enable) goto out; /* Do not pace locally generated ack packets */ @@ -493,8 +494,15 @@ begin: if (skb->sk) rate = min(skb->sk->sk_pacing_rate, rate); + if (rate <= q->low_rate_threshold) { + f->credit = 0; + plen = qdisc_pkt_len(skb); + } else { + plen = max(qdisc_pkt_len(skb), q->quantum); + if (f->credit > 0) + goto out; + } if (rate != ~0U) { - u32 plen = max(qdisc_pkt_len(skb), q->quantum); u64 len = (u64)plen * NSEC_PER_SEC; if (likely(rate)) @@ -662,6 +670,7 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = { [TCA_FQ_FLOW_MAX_RATE] = { .type = NLA_U32 }, [TCA_FQ_BUCKETS_LOG] = { .type = NLA_U32 }, [TCA_FQ_FLOW_REFILL_DELAY] = { .type = NLA_U32 }, + [TCA_FQ_LOW_RATE_THRESHOLD] = { .type = NLA_U32 }, }; static int fq_change(struct Qdisc *sch, struct nlattr *opt) @@ -716,6 +725,10 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) if (tb[TCA_FQ_FLOW_MAX_RATE]) q->flow_max_rate = nla_get_u32(tb[TCA_FQ_FLOW_MAX_RATE]); + if (tb[TCA_FQ_LOW_RATE_THRESHOLD]) + q->low_rate_threshold = + nla_get_u32(tb[TCA_FQ_LOW_RATE_THRESHOLD]); + if (tb[TCA_FQ_RATE_ENABLE]) { u32 enable = nla_get_u32(tb[TCA_FQ_RATE_ENABLE]); @@ -781,6 +794,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt) q->fq_root = NULL; q->fq_trees_log = ilog2(1024); q->orphan_mask = 1024 - 1; + q->low_rate_threshold = 550000 / 8; qdisc_watchdog_init(&q->watchdog, sch); if (opt) @@ -811,6 +825,8 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) nla_put_u32(skb, TCA_FQ_FLOW_REFILL_DELAY, jiffies_to_usecs(q->flow_refill_delay)) || nla_put_u32(skb, TCA_FQ_ORPHAN_MASK, q->orphan_mask) || + nla_put_u32(skb, TCA_FQ_LOW_RATE_THRESHOLD, + q->low_rate_threshold) || nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log)) goto nla_put_failure; -- cgit v1.2.3 From eb8329e0a04db0061f714f033b4454326ba147f4 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Mon, 19 Sep 2016 23:39:16 -0400 Subject: tcp: export data delivery rate This commit export two new fields in struct tcp_info: tcpi_delivery_rate: The most recent goodput, as measured by tcp_rate_gen(). If the socket is limited by the sending application (e.g., no data to send), it reports the highest measurement instead of the most recent. The unit is bytes per second (like other rate fields in tcp_info). tcpi_delivery_rate_app_limited: A boolean indicating if the goodput was measured when the socket's throughput was limited by the sending application. This delivery rate information can be useful for applications that want to know the current throughput the TCP connection is seeing, e.g. adaptive bitrate video streaming. It can also be very useful for debugging or troubleshooting. Signed-off-by: Van Jacobson Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Nandita Dukkipati Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/linux/tcp.h | 5 ++++- include/uapi/linux/tcp.h | 3 +++ net/ipv4/tcp.c | 11 ++++++++++- net/ipv4/tcp_rate.c | 12 +++++++++++- 4 files changed, 28 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index fdcd00ffcb66..a17ae7b85218 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -213,7 +213,8 @@ struct tcp_sock { u8 reord; /* reordering detected */ } rack; u16 advmss; /* Advertised MSS */ - u8 unused; + u8 rate_app_limited:1, /* rate_{delivered,interval_us} limited? */ + unused:7; u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ thin_dupack : 1,/* Fast retransmit on first dupack */ @@ -271,6 +272,8 @@ struct tcp_sock { u32 app_limited; /* limited until "delivered" reaches this val */ struct skb_mstamp first_tx_mstamp; /* start of window send phase */ struct skb_mstamp delivered_mstamp; /* time we reached "delivered" */ + u32 rate_delivered; /* saved rate sample: packets delivered */ + u32 rate_interval_us; /* saved rate sample: time elapsed */ u32 rcv_wnd; /* Current receiver window */ u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 482898fc433a..73ac0db487f8 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -167,6 +167,7 @@ struct tcp_info { __u8 tcpi_backoff; __u8 tcpi_options; __u8 tcpi_snd_wscale : 4, tcpi_rcv_wscale : 4; + __u8 tcpi_delivery_rate_app_limited:1; __u32 tcpi_rto; __u32 tcpi_ato; @@ -211,6 +212,8 @@ struct tcp_info { __u32 tcpi_min_rtt; __u32 tcpi_data_segs_in; /* RFC4898 tcpEStatsDataSegsIn */ __u32 tcpi_data_segs_out; /* RFC4898 tcpEStatsDataSegsOut */ + + __u64 tcpi_delivery_rate; }; /* for TCP_MD5SIG socket option */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2250f891f931..f253e5019d22 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2712,7 +2712,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) { const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */ const struct inet_connection_sock *icsk = inet_csk(sk); - u32 now = tcp_time_stamp; + u32 now = tcp_time_stamp, intv; unsigned int start; int notsent_bytes; u64 rate64; @@ -2802,6 +2802,15 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_min_rtt = tcp_min_rtt(tp); info->tcpi_data_segs_in = tp->data_segs_in; info->tcpi_data_segs_out = tp->data_segs_out; + + info->tcpi_delivery_rate_app_limited = tp->rate_app_limited ? 1 : 0; + rate = READ_ONCE(tp->rate_delivered); + intv = READ_ONCE(tp->rate_interval_us); + if (rate && intv) { + rate64 = (u64)rate * tp->mss_cache * USEC_PER_SEC; + do_div(rate64, intv); + put_unaligned(rate64, &info->tcpi_delivery_rate); + } } EXPORT_SYMBOL_GPL(tcp_get_info); diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index 52ff84be59ab..9be1581a5a08 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -149,12 +149,22 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, * for connections suffer heavy or prolonged losses. */ if (unlikely(rs->interval_us < tcp_min_rtt(tp))) { - rs->interval_us = -1; if (!rs->is_retrans) pr_debug("tcp rate: %ld %d %u %u %u\n", rs->interval_us, rs->delivered, inet_csk(sk)->icsk_ca_state, tp->rx_opt.sack_ok, tcp_min_rtt(tp)); + rs->interval_us = -1; + return; + } + + /* Record the last non-app-limited or the highest app-limited bw */ + if (!rs->is_app_limited || + ((u64)rs->delivered * tp->rate_interval_us >= + (u64)tp->rate_delivered * rs->interval_us)) { + tp->rate_delivered = rs->delivered; + tp->rate_interval_us = rs->interval_us; + tp->rate_app_limited = rs->is_app_limited; } } -- cgit v1.2.3 From 0f8782ea14974ce992618b55f0c041ef43ed0b78 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Mon, 19 Sep 2016 23:39:23 -0400 Subject: tcp_bbr: add BBR congestion control This commit implements a new TCP congestion control algorithm: BBR (Bottleneck Bandwidth and RTT). A detailed description of BBR will be published in ACM Queue, Vol. 14 No. 5, September-October 2016, as "BBR: Congestion-Based Congestion Control". BBR has significantly increased throughput and reduced latency for connections on Google's internal backbone networks and google.com and YouTube Web servers. BBR requires only changes on the sender side, not in the network or the receiver side. Thus it can be incrementally deployed on today's Internet, or in datacenters. The Internet has predominantly used loss-based congestion control (largely Reno or CUBIC) since the 1980s, relying on packet loss as the signal to slow down. While this worked well for many years, loss-based congestion control is unfortunately out-dated in today's networks. On today's Internet, loss-based congestion control causes the infamous bufferbloat problem, often causing seconds of needless queuing delay, since it fills the bloated buffers in many last-mile links. On today's high-speed long-haul links using commodity switches with shallow buffers, loss-based congestion control has abysmal throughput because it over-reacts to losses caused by transient traffic bursts. In 1981 Kleinrock and Gale showed that the optimal operating point for a network maximizes delivered bandwidth while minimizing delay and loss, not only for single connections but for the network as a whole. Finding that optimal operating point has been elusive, since any single network measurement is ambiguous: network measurements are the result of both bandwidth and propagation delay, and those two cannot be measured simultaneously. While it is impossible to disambiguate any single bandwidth or RTT measurement, a connection's behavior over time tells a clearer story. BBR uses a measurement strategy designed to resolve this ambiguity. It combines these measurements with a robust servo loop using recent control systems advances to implement a distributed congestion control algorithm that reacts to actual congestion, not packet loss or transient queue delay, and is designed to converge with high probability to a point near the optimal operating point. In a nutshell, BBR creates an explicit model of the network pipe by sequentially probing the bottleneck bandwidth and RTT. On the arrival of each ACK, BBR derives the current delivery rate of the last round trip, and feeds it through a windowed max-filter to estimate the bottleneck bandwidth. Conversely it uses a windowed min-filter to estimate the round trip propagation delay. The max-filtered bandwidth and min-filtered RTT estimates form BBR's model of the network pipe. Using its model, BBR sets control parameters to govern sending behavior. The primary control is the pacing rate: BBR applies a gain multiplier to transmit faster or slower than the observed bottleneck bandwidth. The conventional congestion window (cwnd) is now the secondary control; the cwnd is set to a small multiple of the estimated BDP (bandwidth-delay product) in order to allow full utilization and bandwidth probing while bounding the potential amount of queue at the bottleneck. When a BBR connection starts, it enters STARTUP mode and applies a high gain to perform an exponential search to quickly probe the bottleneck bandwidth (doubling its sending rate each round trip, like slow start). However, instead of continuing until it fills up the buffer (i.e. a loss), or until delay or ACK spacing reaches some threshold (like Hystart), it uses its model of the pipe to estimate when that pipe is full: it estimates the pipe is full when it notices the estimated bandwidth has stopped growing. At that point it exits STARTUP and enters DRAIN mode, where it reduces its pacing rate to drain the queue it estimates it has created. Then BBR enters steady state. In steady state, PROBE_BW mode cycles between first pacing faster to probe for more bandwidth, then pacing slower to drain any queue that created if no more bandwidth was available, and then cruising at the estimated bandwidth to utilize the pipe without creating excess queue. Occasionally, on an as-needed basis, it sends significantly slower to probe for RTT (PROBE_RTT mode). BBR has been fully deployed on Google's wide-area backbone networks and we're experimenting with BBR on Google.com and YouTube on a global scale. Replacing CUBIC with BBR has resulted in significant improvements in network latency and application (RPC, browser, and video) metrics. For more details please refer to our upcoming ACM Queue publication. Example performance results, to illustrate the difference between BBR and CUBIC: Resilience to random loss (e.g. from shallow buffers): Consider a netperf TCP_STREAM test lasting 30 secs on an emulated path with a 10Gbps bottleneck, 100ms RTT, and 1% packet loss rate. CUBIC gets 3.27 Mbps, and BBR gets 9150 Mbps (2798x higher). Low latency with the bloated buffers common in today's last-mile links: Consider a netperf TCP_STREAM test lasting 120 secs on an emulated path with a 10Mbps bottleneck, 40ms RTT, and 1000-packet bottleneck buffer. Both fully utilize the bottleneck bandwidth, but BBR achieves this with a median RTT 25x lower (43 ms instead of 1.09 secs). Our long-term goal is to improve the congestion control algorithms used on the Internet. We are hopeful that BBR can help advance the efforts toward this goal, and motivate the community to do further research. Test results, performance evaluations, feedback, and BBR-related discussions are very welcome in the public e-mail list for BBR: https://groups.google.com/forum/#!forum/bbr-dev NOTE: BBR *must* be used with the fq qdisc ("man tc-fq") with pacing enabled, since pacing is integral to the BBR design and implementation. BBR without pacing would not function properly, and may incur unnecessary high packet loss rates. Signed-off-by: Van Jacobson Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Nandita Dukkipati Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/uapi/linux/inet_diag.h | 13 + net/ipv4/Kconfig | 18 + net/ipv4/Makefile | 1 + net/ipv4/tcp_bbr.c | 896 +++++++++++++++++++++++++++++++++++++++++ 4 files changed, 928 insertions(+) create mode 100644 net/ipv4/tcp_bbr.c (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index b5c366f87b3e..509cd961068d 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -124,6 +124,7 @@ enum { INET_DIAG_PEERS, INET_DIAG_PAD, INET_DIAG_MARK, + INET_DIAG_BBRINFO, __INET_DIAG_MAX, }; @@ -157,8 +158,20 @@ struct tcp_dctcp_info { __u32 dctcp_ab_tot; }; +/* INET_DIAG_BBRINFO */ + +struct tcp_bbr_info { + /* u64 bw: max-filtered BW (app throughput) estimate in Byte per sec: */ + __u32 bbr_bw_lo; /* lower 32 bits of bw */ + __u32 bbr_bw_hi; /* upper 32 bits of bw */ + __u32 bbr_min_rtt; /* min-filtered RTT in uSec */ + __u32 bbr_pacing_gain; /* pacing gain shifted left 8 bits */ + __u32 bbr_cwnd_gain; /* cwnd gain shifted left 8 bits */ +}; + union tcp_cc_info { struct tcpvegas_info vegas; struct tcp_dctcp_info dctcp; + struct tcp_bbr_info bbr; }; #endif /* _UAPI_INET_DIAG_H_ */ diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 50d6a9b49f6c..300b06888fdf 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -640,6 +640,21 @@ config TCP_CONG_CDG D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using delay gradients." In Networking 2011. Preprint: http://goo.gl/No3vdg +config TCP_CONG_BBR + tristate "BBR TCP" + default n + ---help--- + + BBR (Bottleneck Bandwidth and RTT) TCP congestion control aims to + maximize network utilization and minimize queues. It builds an explicit + model of the the bottleneck delivery rate and path round-trip + propagation delay. It tolerates packet loss and delay unrelated to + congestion. It can operate over LAN, WAN, cellular, wifi, or cable + modem links. It can coexist with flows that use loss-based congestion + control, and can operate with shallow buffers, deep buffers, + bufferbloat, policers, or AQM schemes that do not provide a delay + signal. It requires the fq ("Fair Queue") pacing packet scheduler. + choice prompt "Default TCP congestion control" default DEFAULT_CUBIC @@ -674,6 +689,9 @@ choice config DEFAULT_CDG bool "CDG" if TCP_CONG_CDG=y + config DEFAULT_BBR + bool "BBR" if TCP_CONG_BBR=y + config DEFAULT_RENO bool "Reno" endchoice diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 9cfff1a0bf71..bc6a6c8b9bcd 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -41,6 +41,7 @@ obj-$(CONFIG_INET_DIAG) += inet_diag.o obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o +obj-$(CONFIG_TCP_CONG_BBR) += tcp_bbr.o obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o obj-$(CONFIG_TCP_CONG_CDG) += tcp_cdg.o obj-$(CONFIG_TCP_CONG_CUBIC) += tcp_cubic.o diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c new file mode 100644 index 000000000000..0ea66c2c9344 --- /dev/null +++ b/net/ipv4/tcp_bbr.c @@ -0,0 +1,896 @@ +/* Bottleneck Bandwidth and RTT (BBR) congestion control + * + * BBR congestion control computes the sending rate based on the delivery + * rate (throughput) estimated from ACKs. In a nutshell: + * + * On each ACK, update our model of the network path: + * bottleneck_bandwidth = windowed_max(delivered / elapsed, 10 round trips) + * min_rtt = windowed_min(rtt, 10 seconds) + * pacing_rate = pacing_gain * bottleneck_bandwidth + * cwnd = max(cwnd_gain * bottleneck_bandwidth * min_rtt, 4) + * + * The core algorithm does not react directly to packet losses or delays, + * although BBR may adjust the size of next send per ACK when loss is + * observed, or adjust the sending rate if it estimates there is a + * traffic policer, in order to keep the drop rate reasonable. + * + * BBR is described in detail in: + * "BBR: Congestion-Based Congestion Control", + * Neal Cardwell, Yuchung Cheng, C. Stephen Gunn, Soheil Hassas Yeganeh, + * Van Jacobson. ACM Queue, Vol. 14 No. 5, September-October 2016. + * + * There is a public e-mail list for discussing BBR development and testing: + * https://groups.google.com/forum/#!forum/bbr-dev + * + * NOTE: BBR *must* be used with the fq qdisc ("man tc-fq") with pacing enabled, + * since pacing is integral to the BBR design and implementation. + * BBR without pacing would not function properly, and may incur unnecessary + * high packet loss rates. + */ +#include +#include +#include +#include +#include +#include + +/* Scale factor for rate in pkt/uSec unit to avoid truncation in bandwidth + * estimation. The rate unit ~= (1500 bytes / 1 usec / 2^24) ~= 715 bps. + * This handles bandwidths from 0.06pps (715bps) to 256Mpps (3Tbps) in a u32. + * Since the minimum window is >=4 packets, the lower bound isn't + * an issue. The upper bound isn't an issue with existing technologies. + */ +#define BW_SCALE 24 +#define BW_UNIT (1 << BW_SCALE) + +#define BBR_SCALE 8 /* scaling factor for fractions in BBR (e.g. gains) */ +#define BBR_UNIT (1 << BBR_SCALE) + +/* BBR has the following modes for deciding how fast to send: */ +enum bbr_mode { + BBR_STARTUP, /* ramp up sending rate rapidly to fill pipe */ + BBR_DRAIN, /* drain any queue created during startup */ + BBR_PROBE_BW, /* discover, share bw: pace around estimated bw */ + BBR_PROBE_RTT, /* cut cwnd to min to probe min_rtt */ +}; + +/* BBR congestion control block */ +struct bbr { + u32 min_rtt_us; /* min RTT in min_rtt_win_sec window */ + u32 min_rtt_stamp; /* timestamp of min_rtt_us */ + u32 probe_rtt_done_stamp; /* end time for BBR_PROBE_RTT mode */ + struct minmax bw; /* Max recent delivery rate in pkts/uS << 24 */ + u32 rtt_cnt; /* count of packet-timed rounds elapsed */ + u32 next_rtt_delivered; /* scb->tx.delivered at end of round */ + struct skb_mstamp cycle_mstamp; /* time of this cycle phase start */ + u32 mode:3, /* current bbr_mode in state machine */ + prev_ca_state:3, /* CA state on previous ACK */ + packet_conservation:1, /* use packet conservation? */ + restore_cwnd:1, /* decided to revert cwnd to old value */ + round_start:1, /* start of packet-timed tx->ack round? */ + tso_segs_goal:7, /* segments we want in each skb we send */ + idle_restart:1, /* restarting after idle? */ + probe_rtt_round_done:1, /* a BBR_PROBE_RTT round at 4 pkts? */ + unused:5, + lt_is_sampling:1, /* taking long-term ("LT") samples now? */ + lt_rtt_cnt:7, /* round trips in long-term interval */ + lt_use_bw:1; /* use lt_bw as our bw estimate? */ + u32 lt_bw; /* LT est delivery rate in pkts/uS << 24 */ + u32 lt_last_delivered; /* LT intvl start: tp->delivered */ + u32 lt_last_stamp; /* LT intvl start: tp->delivered_mstamp */ + u32 lt_last_lost; /* LT intvl start: tp->lost */ + u32 pacing_gain:10, /* current gain for setting pacing rate */ + cwnd_gain:10, /* current gain for setting cwnd */ + full_bw_cnt:3, /* number of rounds without large bw gains */ + cycle_idx:3, /* current index in pacing_gain cycle array */ + unused_b:6; + u32 prior_cwnd; /* prior cwnd upon entering loss recovery */ + u32 full_bw; /* recent bw, to estimate if pipe is full */ +}; + +#define CYCLE_LEN 8 /* number of phases in a pacing gain cycle */ + +/* Window length of bw filter (in rounds): */ +static const int bbr_bw_rtts = CYCLE_LEN + 2; +/* Window length of min_rtt filter (in sec): */ +static const u32 bbr_min_rtt_win_sec = 10; +/* Minimum time (in ms) spent at bbr_cwnd_min_target in BBR_PROBE_RTT mode: */ +static const u32 bbr_probe_rtt_mode_ms = 200; +/* Skip TSO below the following bandwidth (bits/sec): */ +static const int bbr_min_tso_rate = 1200000; + +/* We use a high_gain value of 2/ln(2) because it's the smallest pacing gain + * that will allow a smoothly increasing pacing rate that will double each RTT + * and send the same number of packets per RTT that an un-paced, slow-starting + * Reno or CUBIC flow would: + */ +static const int bbr_high_gain = BBR_UNIT * 2885 / 1000 + 1; +/* The pacing gain of 1/high_gain in BBR_DRAIN is calculated to typically drain + * the queue created in BBR_STARTUP in a single round: + */ +static const int bbr_drain_gain = BBR_UNIT * 1000 / 2885; +/* The gain for deriving steady-state cwnd tolerates delayed/stretched ACKs: */ +static const int bbr_cwnd_gain = BBR_UNIT * 2; +/* The pacing_gain values for the PROBE_BW gain cycle, to discover/share bw: */ +static const int bbr_pacing_gain[] = { + BBR_UNIT * 5 / 4, /* probe for more available bw */ + BBR_UNIT * 3 / 4, /* drain queue and/or yield bw to other flows */ + BBR_UNIT, BBR_UNIT, BBR_UNIT, /* cruise at 1.0*bw to utilize pipe, */ + BBR_UNIT, BBR_UNIT, BBR_UNIT /* without creating excess queue... */ +}; +/* Randomize the starting gain cycling phase over N phases: */ +static const u32 bbr_cycle_rand = 7; + +/* Try to keep at least this many packets in flight, if things go smoothly. For + * smooth functioning, a sliding window protocol ACKing every other packet + * needs at least 4 packets in flight: + */ +static const u32 bbr_cwnd_min_target = 4; + +/* To estimate if BBR_STARTUP mode (i.e. high_gain) has filled pipe... */ +/* If bw has increased significantly (1.25x), there may be more bw available: */ +static const u32 bbr_full_bw_thresh = BBR_UNIT * 5 / 4; +/* But after 3 rounds w/o significant bw growth, estimate pipe is full: */ +static const u32 bbr_full_bw_cnt = 3; + +/* "long-term" ("LT") bandwidth estimator parameters... */ +/* The minimum number of rounds in an LT bw sampling interval: */ +static const u32 bbr_lt_intvl_min_rtts = 4; +/* If lost/delivered ratio > 20%, interval is "lossy" and we may be policed: */ +static const u32 bbr_lt_loss_thresh = 50; +/* If 2 intervals have a bw ratio <= 1/8, their bw is "consistent": */ +static const u32 bbr_lt_bw_ratio = BBR_UNIT / 8; +/* If 2 intervals have a bw diff <= 4 Kbit/sec their bw is "consistent": */ +static const u32 bbr_lt_bw_diff = 4000 / 8; +/* If we estimate we're policed, use lt_bw for this many round trips: */ +static const u32 bbr_lt_bw_max_rtts = 48; + +/* Do we estimate that STARTUP filled the pipe? */ +static bool bbr_full_bw_reached(const struct sock *sk) +{ + const struct bbr *bbr = inet_csk_ca(sk); + + return bbr->full_bw_cnt >= bbr_full_bw_cnt; +} + +/* Return the windowed max recent bandwidth sample, in pkts/uS << BW_SCALE. */ +static u32 bbr_max_bw(const struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + return minmax_get(&bbr->bw); +} + +/* Return the estimated bandwidth of the path, in pkts/uS << BW_SCALE. */ +static u32 bbr_bw(const struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + return bbr->lt_use_bw ? bbr->lt_bw : bbr_max_bw(sk); +} + +/* Return rate in bytes per second, optionally with a gain. + * The order here is chosen carefully to avoid overflow of u64. This should + * work for input rates of up to 2.9Tbit/sec and gain of 2.89x. + */ +static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain) +{ + rate *= tcp_mss_to_mtu(sk, tcp_sk(sk)->mss_cache); + rate *= gain; + rate >>= BBR_SCALE; + rate *= USEC_PER_SEC; + return rate >> BW_SCALE; +} + +/* Pace using current bw estimate and a gain factor. In order to help drive the + * network toward lower queues while maintaining high utilization and low + * latency, the average pacing rate aims to be slightly (~1%) lower than the + * estimated bandwidth. This is an important aspect of the design. In this + * implementation this slightly lower pacing rate is achieved implicitly by not + * including link-layer headers in the packet size used for the pacing rate. + */ +static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain) +{ + struct bbr *bbr = inet_csk_ca(sk); + u64 rate = bw; + + rate = bbr_rate_bytes_per_sec(sk, rate, gain); + rate = min_t(u64, rate, sk->sk_max_pacing_rate); + if (bbr->mode != BBR_STARTUP || rate > sk->sk_pacing_rate) + sk->sk_pacing_rate = rate; +} + +/* Return count of segments we want in the skbs we send, or 0 for default. */ +static u32 bbr_tso_segs_goal(struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + return bbr->tso_segs_goal; +} + +static void bbr_set_tso_segs_goal(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u32 min_segs; + + min_segs = sk->sk_pacing_rate < (bbr_min_tso_rate >> 3) ? 1 : 2; + bbr->tso_segs_goal = min(tcp_tso_autosize(sk, tp->mss_cache, min_segs), + 0x7FU); +} + +/* Save "last known good" cwnd so we can restore it after losses or PROBE_RTT */ +static void bbr_save_cwnd(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + + if (bbr->prev_ca_state < TCP_CA_Recovery && bbr->mode != BBR_PROBE_RTT) + bbr->prior_cwnd = tp->snd_cwnd; /* this cwnd is good enough */ + else /* loss recovery or BBR_PROBE_RTT have temporarily cut cwnd */ + bbr->prior_cwnd = max(bbr->prior_cwnd, tp->snd_cwnd); +} + +static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + + if (event == CA_EVENT_TX_START && tp->app_limited) { + bbr->idle_restart = 1; + /* Avoid pointless buffer overflows: pace at est. bw if we don't + * need more speed (we're restarting from idle and app-limited). + */ + if (bbr->mode == BBR_PROBE_BW) + bbr_set_pacing_rate(sk, bbr_bw(sk), BBR_UNIT); + } +} + +/* Find target cwnd. Right-size the cwnd based on min RTT and the + * estimated bottleneck bandwidth: + * + * cwnd = bw * min_rtt * gain = BDP * gain + * + * The key factor, gain, controls the amount of queue. While a small gain + * builds a smaller queue, it becomes more vulnerable to noise in RTT + * measurements (e.g., delayed ACKs or other ACK compression effects). This + * noise may cause BBR to under-estimate the rate. + * + * To achieve full performance in high-speed paths, we budget enough cwnd to + * fit full-sized skbs in-flight on both end hosts to fully utilize the path: + * - one skb in sending host Qdisc, + * - one skb in sending host TSO/GSO engine + * - one skb being received by receiver host LRO/GRO/delayed-ACK engine + * Don't worry, at low rates (bbr_min_tso_rate) this won't bloat cwnd because + * in such cases tso_segs_goal is 1. The minimum cwnd is 4 packets, + * which allows 2 outstanding 2-packet sequences, to try to keep pipe + * full even with ACK-every-other-packet delayed ACKs. + */ +static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain) +{ + struct bbr *bbr = inet_csk_ca(sk); + u32 cwnd; + u64 w; + + /* If we've never had a valid RTT sample, cap cwnd at the initial + * default. This should only happen when the connection is not using TCP + * timestamps and has retransmitted all of the SYN/SYNACK/data packets + * ACKed so far. In this case, an RTO can cut cwnd to 1, in which + * case we need to slow-start up toward something safe: TCP_INIT_CWND. + */ + if (unlikely(bbr->min_rtt_us == ~0U)) /* no valid RTT samples yet? */ + return TCP_INIT_CWND; /* be safe: cap at default initial cwnd*/ + + w = (u64)bw * bbr->min_rtt_us; + + /* Apply a gain to the given value, then remove the BW_SCALE shift. */ + cwnd = (((w * gain) >> BBR_SCALE) + BW_UNIT - 1) / BW_UNIT; + + /* Allow enough full-sized skbs in flight to utilize end systems. */ + cwnd += 3 * bbr->tso_segs_goal; + + /* Reduce delayed ACKs by rounding up cwnd to the next even number. */ + cwnd = (cwnd + 1) & ~1U; + + return cwnd; +} + +/* An optimization in BBR to reduce losses: On the first round of recovery, we + * follow the packet conservation principle: send P packets per P packets acked. + * After that, we slow-start and send at most 2*P packets per P packets acked. + * After recovery finishes, or upon undo, we restore the cwnd we had when + * recovery started (capped by the target cwnd based on estimated BDP). + * + * TODO(ycheng/ncardwell): implement a rate-based approach. + */ +static bool bbr_set_cwnd_to_recover_or_restore( + struct sock *sk, const struct rate_sample *rs, u32 acked, u32 *new_cwnd) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u8 prev_state = bbr->prev_ca_state, state = inet_csk(sk)->icsk_ca_state; + u32 cwnd = tp->snd_cwnd; + + /* An ACK for P pkts should release at most 2*P packets. We do this + * in two steps. First, here we deduct the number of lost packets. + * Then, in bbr_set_cwnd() we slow start up toward the target cwnd. + */ + if (rs->losses > 0) + cwnd = max_t(s32, cwnd - rs->losses, 1); + + if (state == TCP_CA_Recovery && prev_state != TCP_CA_Recovery) { + /* Starting 1st round of Recovery, so do packet conservation. */ + bbr->packet_conservation = 1; + bbr->next_rtt_delivered = tp->delivered; /* start round now */ + /* Cut unused cwnd from app behavior, TSQ, or TSO deferral: */ + cwnd = tcp_packets_in_flight(tp) + acked; + } else if (prev_state >= TCP_CA_Recovery && state < TCP_CA_Recovery) { + /* Exiting loss recovery; restore cwnd saved before recovery. */ + bbr->restore_cwnd = 1; + bbr->packet_conservation = 0; + } + bbr->prev_ca_state = state; + + if (bbr->restore_cwnd) { + /* Restore cwnd after exiting loss recovery or PROBE_RTT. */ + cwnd = max(cwnd, bbr->prior_cwnd); + bbr->restore_cwnd = 0; + } + + if (bbr->packet_conservation) { + *new_cwnd = max(cwnd, tcp_packets_in_flight(tp) + acked); + return true; /* yes, using packet conservation */ + } + *new_cwnd = cwnd; + return false; +} + +/* Slow-start up toward target cwnd (if bw estimate is growing, or packet loss + * has drawn us down below target), or snap down to target if we're above it. + */ +static void bbr_set_cwnd(struct sock *sk, const struct rate_sample *rs, + u32 acked, u32 bw, int gain) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u32 cwnd = 0, target_cwnd = 0; + + if (!acked) + return; + + if (bbr_set_cwnd_to_recover_or_restore(sk, rs, acked, &cwnd)) + goto done; + + /* If we're below target cwnd, slow start cwnd toward target cwnd. */ + target_cwnd = bbr_target_cwnd(sk, bw, gain); + if (bbr_full_bw_reached(sk)) /* only cut cwnd if we filled the pipe */ + cwnd = min(cwnd + acked, target_cwnd); + else if (cwnd < target_cwnd || tp->delivered < TCP_INIT_CWND) + cwnd = cwnd + acked; + cwnd = max(cwnd, bbr_cwnd_min_target); + +done: + tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp); /* apply global cap */ + if (bbr->mode == BBR_PROBE_RTT) /* drain queue, refresh min_rtt */ + tp->snd_cwnd = min(tp->snd_cwnd, bbr_cwnd_min_target); +} + +/* End cycle phase if it's time and/or we hit the phase's in-flight target. */ +static bool bbr_is_next_cycle_phase(struct sock *sk, + const struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + bool is_full_length = + skb_mstamp_us_delta(&tp->delivered_mstamp, &bbr->cycle_mstamp) > + bbr->min_rtt_us; + u32 inflight, bw; + + /* The pacing_gain of 1.0 paces at the estimated bw to try to fully + * use the pipe without increasing the queue. + */ + if (bbr->pacing_gain == BBR_UNIT) + return is_full_length; /* just use wall clock time */ + + inflight = rs->prior_in_flight; /* what was in-flight before ACK? */ + bw = bbr_max_bw(sk); + + /* A pacing_gain > 1.0 probes for bw by trying to raise inflight to at + * least pacing_gain*BDP; this may take more than min_rtt if min_rtt is + * small (e.g. on a LAN). We do not persist if packets are lost, since + * a path with small buffers may not hold that much. + */ + if (bbr->pacing_gain > BBR_UNIT) + return is_full_length && + (rs->losses || /* perhaps pacing_gain*BDP won't fit */ + inflight >= bbr_target_cwnd(sk, bw, bbr->pacing_gain)); + + /* A pacing_gain < 1.0 tries to drain extra queue we added if bw + * probing didn't find more bw. If inflight falls to match BDP then we + * estimate queue is drained; persisting would underutilize the pipe. + */ + return is_full_length || + inflight <= bbr_target_cwnd(sk, bw, BBR_UNIT); +} + +static void bbr_advance_cycle_phase(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + + bbr->cycle_idx = (bbr->cycle_idx + 1) & (CYCLE_LEN - 1); + bbr->cycle_mstamp = tp->delivered_mstamp; + bbr->pacing_gain = bbr_pacing_gain[bbr->cycle_idx]; +} + +/* Gain cycling: cycle pacing gain to converge to fair share of available bw. */ +static void bbr_update_cycle_phase(struct sock *sk, + const struct rate_sample *rs) +{ + struct bbr *bbr = inet_csk_ca(sk); + + if ((bbr->mode == BBR_PROBE_BW) && !bbr->lt_use_bw && + bbr_is_next_cycle_phase(sk, rs)) + bbr_advance_cycle_phase(sk); +} + +static void bbr_reset_startup_mode(struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + bbr->mode = BBR_STARTUP; + bbr->pacing_gain = bbr_high_gain; + bbr->cwnd_gain = bbr_high_gain; +} + +static void bbr_reset_probe_bw_mode(struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + bbr->mode = BBR_PROBE_BW; + bbr->pacing_gain = BBR_UNIT; + bbr->cwnd_gain = bbr_cwnd_gain; + bbr->cycle_idx = CYCLE_LEN - 1 - prandom_u32_max(bbr_cycle_rand); + bbr_advance_cycle_phase(sk); /* flip to next phase of gain cycle */ +} + +static void bbr_reset_mode(struct sock *sk) +{ + if (!bbr_full_bw_reached(sk)) + bbr_reset_startup_mode(sk); + else + bbr_reset_probe_bw_mode(sk); +} + +/* Start a new long-term sampling interval. */ +static void bbr_reset_lt_bw_sampling_interval(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + + bbr->lt_last_stamp = tp->delivered_mstamp.stamp_jiffies; + bbr->lt_last_delivered = tp->delivered; + bbr->lt_last_lost = tp->lost; + bbr->lt_rtt_cnt = 0; +} + +/* Completely reset long-term bandwidth sampling. */ +static void bbr_reset_lt_bw_sampling(struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + bbr->lt_bw = 0; + bbr->lt_use_bw = 0; + bbr->lt_is_sampling = false; + bbr_reset_lt_bw_sampling_interval(sk); +} + +/* Long-term bw sampling interval is done. Estimate whether we're policed. */ +static void bbr_lt_bw_interval_done(struct sock *sk, u32 bw) +{ + struct bbr *bbr = inet_csk_ca(sk); + u32 diff; + + if (bbr->lt_bw) { /* do we have bw from a previous interval? */ + /* Is new bw close to the lt_bw from the previous interval? */ + diff = abs(bw - bbr->lt_bw); + if ((diff * BBR_UNIT <= bbr_lt_bw_ratio * bbr->lt_bw) || + (bbr_rate_bytes_per_sec(sk, diff, BBR_UNIT) <= + bbr_lt_bw_diff)) { + /* All criteria are met; estimate we're policed. */ + bbr->lt_bw = (bw + bbr->lt_bw) >> 1; /* avg 2 intvls */ + bbr->lt_use_bw = 1; + bbr->pacing_gain = BBR_UNIT; /* try to avoid drops */ + bbr->lt_rtt_cnt = 0; + return; + } + } + bbr->lt_bw = bw; + bbr_reset_lt_bw_sampling_interval(sk); +} + +/* Token-bucket traffic policers are common (see "An Internet-Wide Analysis of + * Traffic Policing", SIGCOMM 2016). BBR detects token-bucket policers and + * explicitly models their policed rate, to reduce unnecessary losses. We + * estimate that we're policed if we see 2 consecutive sampling intervals with + * consistent throughput and high packet loss. If we think we're being policed, + * set lt_bw to the "long-term" average delivery rate from those 2 intervals. + */ +static void bbr_lt_bw_sampling(struct sock *sk, const struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u32 lost, delivered; + u64 bw; + s32 t; + + if (bbr->lt_use_bw) { /* already using long-term rate, lt_bw? */ + if (bbr->mode == BBR_PROBE_BW && bbr->round_start && + ++bbr->lt_rtt_cnt >= bbr_lt_bw_max_rtts) { + bbr_reset_lt_bw_sampling(sk); /* stop using lt_bw */ + bbr_reset_probe_bw_mode(sk); /* restart gain cycling */ + } + return; + } + + /* Wait for the first loss before sampling, to let the policer exhaust + * its tokens and estimate the steady-state rate allowed by the policer. + * Starting samples earlier includes bursts that over-estimate the bw. + */ + if (!bbr->lt_is_sampling) { + if (!rs->losses) + return; + bbr_reset_lt_bw_sampling_interval(sk); + bbr->lt_is_sampling = true; + } + + /* To avoid underestimates, reset sampling if we run out of data. */ + if (rs->is_app_limited) { + bbr_reset_lt_bw_sampling(sk); + return; + } + + if (bbr->round_start) + bbr->lt_rtt_cnt++; /* count round trips in this interval */ + if (bbr->lt_rtt_cnt < bbr_lt_intvl_min_rtts) + return; /* sampling interval needs to be longer */ + if (bbr->lt_rtt_cnt > 4 * bbr_lt_intvl_min_rtts) { + bbr_reset_lt_bw_sampling(sk); /* interval is too long */ + return; + } + + /* End sampling interval when a packet is lost, so we estimate the + * policer tokens were exhausted. Stopping the sampling before the + * tokens are exhausted under-estimates the policed rate. + */ + if (!rs->losses) + return; + + /* Calculate packets lost and delivered in sampling interval. */ + lost = tp->lost - bbr->lt_last_lost; + delivered = tp->delivered - bbr->lt_last_delivered; + /* Is loss rate (lost/delivered) >= lt_loss_thresh? If not, wait. */ + if (!delivered || (lost << BBR_SCALE) < bbr_lt_loss_thresh * delivered) + return; + + /* Find average delivery rate in this sampling interval. */ + t = (s32)(tp->delivered_mstamp.stamp_jiffies - bbr->lt_last_stamp); + if (t < 1) + return; /* interval is less than one jiffy, so wait */ + t = jiffies_to_usecs(t); + /* Interval long enough for jiffies_to_usecs() to return a bogus 0? */ + if (t < 1) { + bbr_reset_lt_bw_sampling(sk); /* interval too long; reset */ + return; + } + bw = (u64)delivered * BW_UNIT; + do_div(bw, t); + bbr_lt_bw_interval_done(sk, bw); +} + +/* Estimate the bandwidth based on how fast packets are delivered */ +static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u64 bw; + + bbr->round_start = 0; + if (rs->delivered < 0 || rs->interval_us <= 0) + return; /* Not a valid observation */ + + /* See if we've reached the next RTT */ + if (!before(rs->prior_delivered, bbr->next_rtt_delivered)) { + bbr->next_rtt_delivered = tp->delivered; + bbr->rtt_cnt++; + bbr->round_start = 1; + bbr->packet_conservation = 0; + } + + bbr_lt_bw_sampling(sk, rs); + + /* Divide delivered by the interval to find a (lower bound) bottleneck + * bandwidth sample. Delivered is in packets and interval_us in uS and + * ratio will be <<1 for most connections. So delivered is first scaled. + */ + bw = (u64)rs->delivered * BW_UNIT; + do_div(bw, rs->interval_us); + + /* If this sample is application-limited, it is likely to have a very + * low delivered count that represents application behavior rather than + * the available network rate. Such a sample could drag down estimated + * bw, causing needless slow-down. Thus, to continue to send at the + * last measured network rate, we filter out app-limited samples unless + * they describe the path bw at least as well as our bw model. + * + * So the goal during app-limited phase is to proceed with the best + * network rate no matter how long. We automatically leave this + * phase when app writes faster than the network can deliver :) + */ + if (!rs->is_app_limited || bw >= bbr_max_bw(sk)) { + /* Incorporate new sample into our max bw filter. */ + minmax_running_max(&bbr->bw, bbr_bw_rtts, bbr->rtt_cnt, bw); + } +} + +/* Estimate when the pipe is full, using the change in delivery rate: BBR + * estimates that STARTUP filled the pipe if the estimated bw hasn't changed by + * at least bbr_full_bw_thresh (25%) after bbr_full_bw_cnt (3) non-app-limited + * rounds. Why 3 rounds: 1: rwin autotuning grows the rwin, 2: we fill the + * higher rwin, 3: we get higher delivery rate samples. Or transient + * cross-traffic or radio noise can go away. CUBIC Hystart shares a similar + * design goal, but uses delay and inter-ACK spacing instead of bandwidth. + */ +static void bbr_check_full_bw_reached(struct sock *sk, + const struct rate_sample *rs) +{ + struct bbr *bbr = inet_csk_ca(sk); + u32 bw_thresh; + + if (bbr_full_bw_reached(sk) || !bbr->round_start || rs->is_app_limited) + return; + + bw_thresh = (u64)bbr->full_bw * bbr_full_bw_thresh >> BBR_SCALE; + if (bbr_max_bw(sk) >= bw_thresh) { + bbr->full_bw = bbr_max_bw(sk); + bbr->full_bw_cnt = 0; + return; + } + ++bbr->full_bw_cnt; +} + +/* If pipe is probably full, drain the queue and then enter steady-state. */ +static void bbr_check_drain(struct sock *sk, const struct rate_sample *rs) +{ + struct bbr *bbr = inet_csk_ca(sk); + + if (bbr->mode == BBR_STARTUP && bbr_full_bw_reached(sk)) { + bbr->mode = BBR_DRAIN; /* drain queue we created */ + bbr->pacing_gain = bbr_drain_gain; /* pace slow to drain */ + bbr->cwnd_gain = bbr_high_gain; /* maintain cwnd */ + } /* fall through to check if in-flight is already small: */ + if (bbr->mode == BBR_DRAIN && + tcp_packets_in_flight(tcp_sk(sk)) <= + bbr_target_cwnd(sk, bbr_max_bw(sk), BBR_UNIT)) + bbr_reset_probe_bw_mode(sk); /* we estimate queue is drained */ +} + +/* The goal of PROBE_RTT mode is to have BBR flows cooperatively and + * periodically drain the bottleneck queue, to converge to measure the true + * min_rtt (unloaded propagation delay). This allows the flows to keep queues + * small (reducing queuing delay and packet loss) and achieve fairness among + * BBR flows. + * + * The min_rtt filter window is 10 seconds. When the min_rtt estimate expires, + * we enter PROBE_RTT mode and cap the cwnd at bbr_cwnd_min_target=4 packets. + * After at least bbr_probe_rtt_mode_ms=200ms and at least one packet-timed + * round trip elapsed with that flight size <= 4, we leave PROBE_RTT mode and + * re-enter the previous mode. BBR uses 200ms to approximately bound the + * performance penalty of PROBE_RTT's cwnd capping to roughly 2% (200ms/10s). + * + * Note that flows need only pay 2% if they are busy sending over the last 10 + * seconds. Interactive applications (e.g., Web, RPCs, video chunks) often have + * natural silences or low-rate periods within 10 seconds where the rate is low + * enough for long enough to drain its queue in the bottleneck. We pick up + * these min RTT measurements opportunistically with our min_rtt filter. :-) + */ +static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + bool filter_expired; + + /* Track min RTT seen in the min_rtt_win_sec filter window: */ + filter_expired = after(tcp_time_stamp, + bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ); + if (rs->rtt_us >= 0 && + (rs->rtt_us <= bbr->min_rtt_us || filter_expired)) { + bbr->min_rtt_us = rs->rtt_us; + bbr->min_rtt_stamp = tcp_time_stamp; + } + + if (bbr_probe_rtt_mode_ms > 0 && filter_expired && + !bbr->idle_restart && bbr->mode != BBR_PROBE_RTT) { + bbr->mode = BBR_PROBE_RTT; /* dip, drain queue */ + bbr->pacing_gain = BBR_UNIT; + bbr->cwnd_gain = BBR_UNIT; + bbr_save_cwnd(sk); /* note cwnd so we can restore it */ + bbr->probe_rtt_done_stamp = 0; + } + + if (bbr->mode == BBR_PROBE_RTT) { + /* Ignore low rate samples during this mode. */ + tp->app_limited = + (tp->delivered + tcp_packets_in_flight(tp)) ? : 1; + /* Maintain min packets in flight for max(200 ms, 1 round). */ + if (!bbr->probe_rtt_done_stamp && + tcp_packets_in_flight(tp) <= bbr_cwnd_min_target) { + bbr->probe_rtt_done_stamp = tcp_time_stamp + + msecs_to_jiffies(bbr_probe_rtt_mode_ms); + bbr->probe_rtt_round_done = 0; + bbr->next_rtt_delivered = tp->delivered; + } else if (bbr->probe_rtt_done_stamp) { + if (bbr->round_start) + bbr->probe_rtt_round_done = 1; + if (bbr->probe_rtt_round_done && + after(tcp_time_stamp, bbr->probe_rtt_done_stamp)) { + bbr->min_rtt_stamp = tcp_time_stamp; + bbr->restore_cwnd = 1; /* snap to prior_cwnd */ + bbr_reset_mode(sk); + } + } + } + bbr->idle_restart = 0; +} + +static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) +{ + bbr_update_bw(sk, rs); + bbr_update_cycle_phase(sk, rs); + bbr_check_full_bw_reached(sk, rs); + bbr_check_drain(sk, rs); + bbr_update_min_rtt(sk, rs); +} + +static void bbr_main(struct sock *sk, const struct rate_sample *rs) +{ + struct bbr *bbr = inet_csk_ca(sk); + u32 bw; + + bbr_update_model(sk, rs); + + bw = bbr_bw(sk); + bbr_set_pacing_rate(sk, bw, bbr->pacing_gain); + bbr_set_tso_segs_goal(sk); + bbr_set_cwnd(sk, rs, rs->acked_sacked, bw, bbr->cwnd_gain); +} + +static void bbr_init(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u64 bw; + + bbr->prior_cwnd = 0; + bbr->tso_segs_goal = 0; /* default segs per skb until first ACK */ + bbr->rtt_cnt = 0; + bbr->next_rtt_delivered = 0; + bbr->prev_ca_state = TCP_CA_Open; + bbr->packet_conservation = 0; + + bbr->probe_rtt_done_stamp = 0; + bbr->probe_rtt_round_done = 0; + bbr->min_rtt_us = tcp_min_rtt(tp); + bbr->min_rtt_stamp = tcp_time_stamp; + + minmax_reset(&bbr->bw, bbr->rtt_cnt, 0); /* init max bw to 0 */ + + /* Initialize pacing rate to: high_gain * init_cwnd / RTT. */ + bw = (u64)tp->snd_cwnd * BW_UNIT; + do_div(bw, (tp->srtt_us >> 3) ? : USEC_PER_MSEC); + sk->sk_pacing_rate = 0; /* force an update of sk_pacing_rate */ + bbr_set_pacing_rate(sk, bw, bbr_high_gain); + + bbr->restore_cwnd = 0; + bbr->round_start = 0; + bbr->idle_restart = 0; + bbr->full_bw = 0; + bbr->full_bw_cnt = 0; + bbr->cycle_mstamp.v64 = 0; + bbr->cycle_idx = 0; + bbr_reset_lt_bw_sampling(sk); + bbr_reset_startup_mode(sk); +} + +static u32 bbr_sndbuf_expand(struct sock *sk) +{ + /* Provision 3 * cwnd since BBR may slow-start even during recovery. */ + return 3; +} + +/* In theory BBR does not need to undo the cwnd since it does not + * always reduce cwnd on losses (see bbr_main()). Keep it for now. + */ +static u32 bbr_undo_cwnd(struct sock *sk) +{ + return tcp_sk(sk)->snd_cwnd; +} + +/* Entering loss recovery, so save cwnd for when we exit or undo recovery. */ +static u32 bbr_ssthresh(struct sock *sk) +{ + bbr_save_cwnd(sk); + return TCP_INFINITE_SSTHRESH; /* BBR does not use ssthresh */ +} + +static size_t bbr_get_info(struct sock *sk, u32 ext, int *attr, + union tcp_cc_info *info) +{ + if (ext & (1 << (INET_DIAG_BBRINFO - 1)) || + ext & (1 << (INET_DIAG_VEGASINFO - 1))) { + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u64 bw = bbr_bw(sk); + + bw = bw * tp->mss_cache * USEC_PER_SEC >> BW_SCALE; + memset(&info->bbr, 0, sizeof(info->bbr)); + info->bbr.bbr_bw_lo = (u32)bw; + info->bbr.bbr_bw_hi = (u32)(bw >> 32); + info->bbr.bbr_min_rtt = bbr->min_rtt_us; + info->bbr.bbr_pacing_gain = bbr->pacing_gain; + info->bbr.bbr_cwnd_gain = bbr->cwnd_gain; + *attr = INET_DIAG_BBRINFO; + return sizeof(info->bbr); + } + return 0; +} + +static void bbr_set_state(struct sock *sk, u8 new_state) +{ + struct bbr *bbr = inet_csk_ca(sk); + + if (new_state == TCP_CA_Loss) { + struct rate_sample rs = { .losses = 1 }; + + bbr->prev_ca_state = TCP_CA_Loss; + bbr->full_bw = 0; + bbr->round_start = 1; /* treat RTO like end of a round */ + bbr_lt_bw_sampling(sk, &rs); + } +} + +static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = { + .flags = TCP_CONG_NON_RESTRICTED, + .name = "bbr", + .owner = THIS_MODULE, + .init = bbr_init, + .cong_control = bbr_main, + .sndbuf_expand = bbr_sndbuf_expand, + .undo_cwnd = bbr_undo_cwnd, + .cwnd_event = bbr_cwnd_event, + .ssthresh = bbr_ssthresh, + .tso_segs_goal = bbr_tso_segs_goal, + .get_info = bbr_get_info, + .set_state = bbr_set_state, +}; + +static int __init bbr_register(void) +{ + BUILD_BUG_ON(sizeof(struct bbr) > ICSK_CA_PRIV_SIZE); + return tcp_register_congestion_control(&tcp_bbr_cong_ops); +} + +static void __exit bbr_unregister(void) +{ + tcp_unregister_congestion_control(&tcp_bbr_cong_ops); +} + +module_init(bbr_register); +module_exit(bbr_unregister); + +MODULE_AUTHOR("Van Jacobson "); +MODULE_AUTHOR("Neal Cardwell "); +MODULE_AUTHOR("Yuchung Cheng "); +MODULE_AUTHOR("Soheil Hassas Yeganeh "); +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_DESCRIPTION("TCP BBR (Bottleneck Bandwidth and RTT)"); -- cgit v1.2.3 From 0d01d45f1b251448590c710baa32f722e43c62c7 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 21 Sep 2016 11:43:54 +0100 Subject: net: cls_bpf: limit hardware offload by software-only flag Add cls_bpf support for the TCA_CLS_FLAGS_SKIP_HW flag. Unlike U32 and flower cls_bpf already has some netlink flags defined. Create a new attribute to be able to use the same flag values as the above. Unlike U32 and flower reject unknown flags. Signed-off-by: Jakub Kicinski Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 1 + include/uapi/linux/pkt_cls.h | 1 + net/sched/cls_bpf.c | 22 ++++++++++++++++++++-- 3 files changed, 22 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 41e8071dff87..57af9f3032ff 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -498,6 +498,7 @@ struct tc_cls_bpf_offload { struct bpf_prog *prog; const char *name; bool exts_integrated; + u32 gen_flags; }; #endif diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 8915b61bbf83..8fd715f806a2 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -396,6 +396,7 @@ enum { TCA_BPF_FD, TCA_BPF_NAME, TCA_BPF_FLAGS, + TCA_BPF_FLAGS_GEN, __TCA_BPF_MAX, }; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 6523c5b4c0a5..ebf01f7c1470 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -27,6 +27,8 @@ MODULE_AUTHOR("Daniel Borkmann "); MODULE_DESCRIPTION("TC BPF based classifier"); #define CLS_BPF_NAME_LEN 256 +#define CLS_BPF_SUPPORTED_GEN_FLAGS \ + TCA_CLS_FLAGS_SKIP_HW struct cls_bpf_head { struct list_head plist; @@ -40,6 +42,7 @@ struct cls_bpf_prog { struct tcf_result res; bool exts_integrated; bool offloaded; + u32 gen_flags; struct tcf_exts exts; u32 handle; union { @@ -55,6 +58,7 @@ struct cls_bpf_prog { static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = { [TCA_BPF_CLASSID] = { .type = NLA_U32 }, [TCA_BPF_FLAGS] = { .type = NLA_U32 }, + [TCA_BPF_FLAGS_GEN] = { .type = NLA_U32 }, [TCA_BPF_FD] = { .type = NLA_U32 }, [TCA_BPF_NAME] = { .type = NLA_NUL_STRING, .len = CLS_BPF_NAME_LEN }, @@ -154,6 +158,7 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, bpf_offload.prog = prog->filter; bpf_offload.name = prog->bpf_name; bpf_offload.exts_integrated = prog->exts_integrated; + bpf_offload.gen_flags = prog->gen_flags; return dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &offload); @@ -167,14 +172,14 @@ static void cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, enum tc_clsbpf_command cmd; if (oldprog && oldprog->offloaded) { - if (tc_should_offload(dev, tp, 0)) { + if (tc_should_offload(dev, tp, prog->gen_flags)) { cmd = TC_CLSBPF_REPLACE; } else { obj = oldprog; cmd = TC_CLSBPF_DESTROY; } } else { - if (!tc_should_offload(dev, tp, 0)) + if (!tc_should_offload(dev, tp, prog->gen_flags)) return; cmd = TC_CLSBPF_ADD; } @@ -370,6 +375,7 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, { bool is_bpf, is_ebpf, have_exts = false; struct tcf_exts exts; + u32 gen_flags = 0; int ret; is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS]; @@ -394,8 +400,17 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT; } + if (tb[TCA_BPF_FLAGS_GEN]) { + gen_flags = nla_get_u32(tb[TCA_BPF_FLAGS_GEN]); + if (gen_flags & ~CLS_BPF_SUPPORTED_GEN_FLAGS || + !tc_flags_valid(gen_flags)) { + ret = -EINVAL; + goto errout; + } + } prog->exts_integrated = have_exts; + prog->gen_flags = gen_flags; ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : cls_bpf_prog_from_efd(tb, prog, tp); @@ -568,6 +583,9 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, bpf_flags |= TCA_BPF_FLAG_ACT_DIRECT; if (bpf_flags && nla_put_u32(skb, TCA_BPF_FLAGS, bpf_flags)) goto nla_put_failure; + if (prog->gen_flags && + nla_put_u32(skb, TCA_BPF_FLAGS_GEN, prog->gen_flags)) + goto nla_put_failure; nla_nest_end(skb, nest); -- cgit v1.2.3 From 45a497f2d149a4a8061c61518a79d59f1f3034b2 Mon Sep 17 00:00:00 2001 From: Shmulik Ladkani Date: Mon, 19 Sep 2016 19:11:10 +0300 Subject: net/sched: act_vlan: Introduce TCA_VLAN_ACT_MODIFY vlan action TCA_VLAN_ACT_MODIFY allows one to change an existing tag. It accepts same attributes as TCA_VLAN_ACT_PUSH (protocol, id, priority). If packet is vlan tagged, then the tag gets overwritten according to user specified attributes. For example, this allows user to replace a tag's vid while preserving its priority bits (as opposed to "action vlan pop pipe action vlan push"). Signed-off-by: Shmulik Ladkani Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/uapi/linux/tc_act/tc_vlan.h | 1 + net/sched/act_vlan.c | 29 ++++++++++++++++++++++++++++- 2 files changed, 29 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tc_act/tc_vlan.h b/include/uapi/linux/tc_act/tc_vlan.h index be72b6e3843b..bddb272b843f 100644 --- a/include/uapi/linux/tc_act/tc_vlan.h +++ b/include/uapi/linux/tc_act/tc_vlan.h @@ -16,6 +16,7 @@ #define TCA_VLAN_ACT_POP 1 #define TCA_VLAN_ACT_PUSH 2 +#define TCA_VLAN_ACT_MODIFY 3 struct tc_vlan { tc_gen; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 59a8d3150ae2..a95c00b119da 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -30,6 +30,7 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, struct tcf_vlan *v = to_vlan(a); int action; int err; + u16 tci; spin_lock(&v->tcf_lock); tcf_lastuse_update(&v->tcf_tm); @@ -48,6 +49,30 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, if (err) goto drop; break; + case TCA_VLAN_ACT_MODIFY: + /* No-op if no vlan tag (either hw-accel or in-payload) */ + if (!skb_vlan_tagged(skb)) + goto unlock; + /* extract existing tag (and guarantee no hw-accel tag) */ + if (skb_vlan_tag_present(skb)) { + tci = skb_vlan_tag_get(skb); + skb->vlan_tci = 0; + } else { + /* in-payload vlan tag, pop it */ + err = __skb_vlan_pop(skb, &tci); + if (err) + goto drop; + } + /* replace the vid */ + tci = (tci & ~VLAN_VID_MASK) | v->tcfv_push_vid; + /* replace prio bits, if tcfv_push_prio specified */ + if (v->tcfv_push_prio) { + tci &= ~VLAN_PRIO_MASK; + tci |= v->tcfv_push_prio << VLAN_PRIO_SHIFT; + } + /* put updated tci as hwaccel tag */ + __vlan_hwaccel_put_tag(skb, v->tcfv_push_proto, tci); + break; default: BUG(); } @@ -102,6 +127,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, case TCA_VLAN_ACT_POP: break; case TCA_VLAN_ACT_PUSH: + case TCA_VLAN_ACT_MODIFY: if (!tb[TCA_VLAN_PUSH_VLAN_ID]) { if (exists) tcf_hash_release(*a, bind); @@ -185,7 +211,8 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, if (nla_put(skb, TCA_VLAN_PARMS, sizeof(opt), &opt)) goto nla_put_failure; - if (v->tcfv_action == TCA_VLAN_ACT_PUSH && + if ((v->tcfv_action == TCA_VLAN_ACT_PUSH || + v->tcfv_action == TCA_VLAN_ACT_MODIFY) && (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, v->tcfv_push_vid) || nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL, v->tcfv_push_proto) || -- cgit v1.2.3 From 2b03bf732488a3c2e920afe22c03b82cb8477e28 Mon Sep 17 00:00:00 2001 From: Laura Garcia Liebana Date: Tue, 13 Sep 2016 13:49:53 +0200 Subject: netfilter: nft_numgen: add number generation offset Add support of an offset value for incremental counter and random. With this option the sysadmin is able to start the counter to a certain value and then apply the generated number. Example: meta mark set numgen inc mod 2 offset 100 This will generate marks with the serie 100, 101, 100, 101, ... Suggested-by: Pablo Neira Ayuso Signed-off-by: Laura Garcia Liebana Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 ++ net/netfilter/nft_numgen.c | 32 ++++++++++++++++++++++++++------ 2 files changed, 28 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index bc0eb6a1066d..bcfb892ff148 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1136,12 +1136,14 @@ enum nft_trace_types { * @NFTA_NG_DREG: destination register (NLA_U32) * @NFTA_NG_MODULUS: maximum counter value (NLA_U32) * @NFTA_NG_TYPE: operation type (NLA_U32) + * @NFTA_NG_OFFSET: offset to be added to the counter (NLA_U32) */ enum nft_ng_attributes { NFTA_NG_UNSPEC, NFTA_NG_DREG, NFTA_NG_MODULUS, NFTA_NG_TYPE, + NFTA_NG_OFFSET, __NFTA_NG_MAX }; #define NFTA_NG_MAX (__NFTA_NG_MAX - 1) diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c index f173ebec30a7..55bc5ab78d4a 100644 --- a/net/netfilter/nft_numgen.c +++ b/net/netfilter/nft_numgen.c @@ -23,6 +23,7 @@ struct nft_ng_inc { enum nft_registers dreg:8; u32 modulus; atomic_t counter; + u32 offset; }; static void nft_ng_inc_eval(const struct nft_expr *expr, @@ -37,13 +38,14 @@ static void nft_ng_inc_eval(const struct nft_expr *expr, nval = (oval + 1 < priv->modulus) ? oval + 1 : 0; } while (atomic_cmpxchg(&priv->counter, oval, nval) != oval); - regs->data[priv->dreg] = nval; + regs->data[priv->dreg] = nval + priv->offset; } static const struct nla_policy nft_ng_policy[NFTA_NG_MAX + 1] = { [NFTA_NG_DREG] = { .type = NLA_U32 }, [NFTA_NG_MODULUS] = { .type = NLA_U32 }, [NFTA_NG_TYPE] = { .type = NLA_U32 }, + [NFTA_NG_OFFSET] = { .type = NLA_U32 }, }; static int nft_ng_inc_init(const struct nft_ctx *ctx, @@ -52,10 +54,16 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx, { struct nft_ng_inc *priv = nft_expr_priv(expr); + if (tb[NFTA_NG_OFFSET]) + priv->offset = ntohl(nla_get_be32(tb[NFTA_NG_OFFSET])); + priv->modulus = ntohl(nla_get_be32(tb[NFTA_NG_MODULUS])); if (priv->modulus == 0) return -ERANGE; + if (priv->offset + priv->modulus - 1 < priv->offset) + return -EOVERFLOW; + priv->dreg = nft_parse_register(tb[NFTA_NG_DREG]); atomic_set(&priv->counter, 0); @@ -64,7 +72,7 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx, } static int nft_ng_dump(struct sk_buff *skb, enum nft_registers dreg, - u32 modulus, enum nft_ng_types type) + u32 modulus, enum nft_ng_types type, u32 offset) { if (nft_dump_register(skb, NFTA_NG_DREG, dreg)) goto nla_put_failure; @@ -72,6 +80,8 @@ static int nft_ng_dump(struct sk_buff *skb, enum nft_registers dreg, goto nla_put_failure; if (nla_put_be32(skb, NFTA_NG_TYPE, htonl(type))) goto nla_put_failure; + if (nla_put_be32(skb, NFTA_NG_OFFSET, htonl(offset))) + goto nla_put_failure; return 0; @@ -83,12 +93,14 @@ static int nft_ng_inc_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_ng_inc *priv = nft_expr_priv(expr); - return nft_ng_dump(skb, priv->dreg, priv->modulus, NFT_NG_INCREMENTAL); + return nft_ng_dump(skb, priv->dreg, priv->modulus, NFT_NG_INCREMENTAL, + priv->offset); } struct nft_ng_random { enum nft_registers dreg:8; u32 modulus; + u32 offset; }; static void nft_ng_random_eval(const struct nft_expr *expr, @@ -97,9 +109,10 @@ static void nft_ng_random_eval(const struct nft_expr *expr, { struct nft_ng_random *priv = nft_expr_priv(expr); struct rnd_state *state = this_cpu_ptr(&nft_numgen_prandom_state); + u32 val; - regs->data[priv->dreg] = reciprocal_scale(prandom_u32_state(state), - priv->modulus); + val = reciprocal_scale(prandom_u32_state(state), priv->modulus); + regs->data[priv->dreg] = val + priv->offset; } static int nft_ng_random_init(const struct nft_ctx *ctx, @@ -108,10 +121,16 @@ static int nft_ng_random_init(const struct nft_ctx *ctx, { struct nft_ng_random *priv = nft_expr_priv(expr); + if (tb[NFTA_NG_OFFSET]) + priv->offset = ntohl(nla_get_be32(tb[NFTA_NG_OFFSET])); + priv->modulus = ntohl(nla_get_be32(tb[NFTA_NG_MODULUS])); if (priv->modulus == 0) return -ERANGE; + if (priv->offset + priv->modulus - 1 < priv->offset) + return -EOVERFLOW; + prandom_init_once(&nft_numgen_prandom_state); priv->dreg = nft_parse_register(tb[NFTA_NG_DREG]); @@ -124,7 +143,8 @@ static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_ng_random *priv = nft_expr_priv(expr); - return nft_ng_dump(skb, priv->dreg, priv->modulus, NFT_NG_RANDOM); + return nft_ng_dump(skb, priv->dreg, priv->modulus, NFT_NG_RANDOM, + priv->offset); } static struct nft_expr_type nft_ng_type; -- cgit v1.2.3 From 6786741dbf99e44fb0c0ed85a37582b8a26f1c3b Mon Sep 17 00:00:00 2001 From: Andrey Vagin Date: Tue, 6 Sep 2016 00:47:14 -0700 Subject: nsfs: add ioctl to get an owning user namespace for ns file descriptor Each namespace has an owning user namespace and now there is not way to discover these relationships. Understending namespaces relationships allows to answer the question: what capability does process X have to perform operations on a resource governed by namespace Y? After a long discussion, Eric W. Biederman proposed to use ioctl-s for this purpose. The NS_GET_USERNS ioctl returns a file descriptor to an owning user namespace. It returns EPERM if a target namespace is outside of a current user namespace. v2: rename parent to relative v3: Add a missing mntput when returning -EAGAIN --EWB Acked-by: Serge Hallyn Link: https://lkml.org/lkml/2016/7/6/158 Signed-off-by: Andrei Vagin Signed-off-by: Eric W. Biederman --- fs/nsfs.c | 96 ++++++++++++++++++++++++++++++++++++++++------- include/uapi/linux/nsfs.h | 11 ++++++ 2 files changed, 94 insertions(+), 13 deletions(-) create mode 100644 include/uapi/linux/nsfs.h (limited to 'include/uapi/linux') diff --git a/fs/nsfs.c b/fs/nsfs.c index 8f20d6016e20..3887da470f7e 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -5,11 +5,16 @@ #include #include #include +#include +#include static struct vfsmount *nsfs_mnt; +static long ns_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg); static const struct file_operations ns_file_operations = { .llseek = no_llseek, + .unlocked_ioctl = ns_ioctl, }; static char *ns_dname(struct dentry *dentry, char *buffer, int buflen) @@ -44,22 +49,14 @@ static void nsfs_evict(struct inode *inode) ns->ops->put(ns); } -void *ns_get_path(struct path *path, struct task_struct *task, - const struct proc_ns_operations *ns_ops) +static void *__ns_get_path(struct path *path, struct ns_common *ns) { struct vfsmount *mnt = mntget(nsfs_mnt); struct qstr qname = { .name = "", }; struct dentry *dentry; struct inode *inode; - struct ns_common *ns; unsigned long d; -again: - ns = ns_ops->get(task); - if (!ns) { - mntput(mnt); - return ERR_PTR(-ENOENT); - } rcu_read_lock(); d = atomic_long_read(&ns->stashed); if (!d) @@ -68,7 +65,7 @@ again: if (!lockref_get_not_dead(&dentry->d_lockref)) goto slow; rcu_read_unlock(); - ns_ops->put(ns); + ns->ops->put(ns); got_it: path->mnt = mnt; path->dentry = dentry; @@ -77,7 +74,7 @@ slow: rcu_read_unlock(); inode = new_inode_pseudo(mnt->mnt_sb); if (!inode) { - ns_ops->put(ns); + ns->ops->put(ns); mntput(mnt); return ERR_PTR(-ENOMEM); } @@ -95,17 +92,90 @@ slow: return ERR_PTR(-ENOMEM); } d_instantiate(dentry, inode); - dentry->d_fsdata = (void *)ns_ops; + dentry->d_fsdata = (void *)ns->ops; d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry); if (d) { d_delete(dentry); /* make sure ->d_prune() does nothing */ dput(dentry); + mntput(mnt); cpu_relax(); - goto again; + return ERR_PTR(-EAGAIN); } goto got_it; } +void *ns_get_path(struct path *path, struct task_struct *task, + const struct proc_ns_operations *ns_ops) +{ + struct ns_common *ns; + void *ret; + +again: + ns = ns_ops->get(task); + if (!ns) + return ERR_PTR(-ENOENT); + + ret = __ns_get_path(path, ns); + if (IS_ERR(ret) && PTR_ERR(ret) == -EAGAIN) + goto again; + return ret; +} + +static int open_related_ns(struct ns_common *ns, + struct ns_common *(*get_ns)(struct ns_common *ns)) +{ + struct path path = {}; + struct file *f; + void *err; + int fd; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) + return fd; + + while (1) { + struct ns_common *relative; + + relative = get_ns(ns); + if (IS_ERR(relative)) { + put_unused_fd(fd); + return PTR_ERR(relative); + } + + err = __ns_get_path(&path, relative); + if (IS_ERR(err) && PTR_ERR(err) == -EAGAIN) + continue; + break; + } + if (IS_ERR(err)) { + put_unused_fd(fd); + return PTR_ERR(err); + } + + f = dentry_open(&path, O_RDONLY, current_cred()); + path_put(&path); + if (IS_ERR(f)) { + put_unused_fd(fd); + fd = PTR_ERR(f); + } else + fd_install(fd, f); + + return fd; +} + +static long ns_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + struct ns_common *ns = get_proc_ns(file_inode(filp)); + + switch (ioctl) { + case NS_GET_USERNS: + return open_related_ns(ns, ns_get_owner); + default: + return -ENOTTY; + } +} + int ns_get_name(char *buf, size_t size, struct task_struct *task, const struct proc_ns_operations *ns_ops) { diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h new file mode 100644 index 000000000000..5cacd5c1b5d7 --- /dev/null +++ b/include/uapi/linux/nsfs.h @@ -0,0 +1,11 @@ +#ifndef __LINUX_NSFS_H +#define __LINUX_NSFS_H + +#include + +#define NSIO 0xb7 + +/* Returns a file descriptor that refers to an owning user namespace */ +#define NS_GET_USERNS _IO(NSIO, 0x1) + +#endif /* __LINUX_NSFS_H */ -- cgit v1.2.3 From a7306ed8d94af729ecef8b6e37506a1c6fc14788 Mon Sep 17 00:00:00 2001 From: Andrey Vagin Date: Tue, 6 Sep 2016 00:47:15 -0700 Subject: nsfs: add ioctl to get a parent namespace Pid and user namepaces are hierarchical. There is no way to discover parent-child relationships. In a future we will use this interface to dump and restore nested namespaces. Acked-by: Serge Hallyn Signed-off-by: Andrei Vagin Signed-off-by: Eric W. Biederman --- fs/nsfs.c | 4 ++++ include/linux/proc_ns.h | 1 + include/uapi/linux/nsfs.h | 2 ++ kernel/pid_namespace.c | 19 +++++++++++++++++++ kernel/user_namespace.c | 1 + 5 files changed, 27 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/nsfs.c b/fs/nsfs.c index 3887da470f7e..fb7b397a1297 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -171,6 +171,10 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, switch (ioctl) { case NS_GET_USERNS: return open_related_ns(ns, ns_get_owner); + case NS_GET_PARENT: + if (!ns->ops->get_parent) + return -EINVAL; + return open_related_ns(ns, ns->ops->get_parent); default: return -ENOTTY; } diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index ca85a4348ffc..12cb8bd81d2d 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -19,6 +19,7 @@ struct proc_ns_operations { void (*put)(struct ns_common *ns); int (*install)(struct nsproxy *nsproxy, struct ns_common *ns); struct user_namespace *(*owner)(struct ns_common *ns); + struct ns_common *(*get_parent)(struct ns_common *ns); }; extern const struct proc_ns_operations netns_operations; diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index 5cacd5c1b5d7..3af617230d1b 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -7,5 +7,7 @@ /* Returns a file descriptor that refers to an owning user namespace */ #define NS_GET_USERNS _IO(NSIO, 0x1) +/* Returns a file descriptor that refers to a parent namespace */ +#define NS_GET_PARENT _IO(NSIO, 0x2) #endif /* __LINUX_NSFS_H */ diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index c02d744225e1..4fa2d56a936c 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -388,6 +388,24 @@ static int pidns_install(struct nsproxy *nsproxy, struct ns_common *ns) return 0; } +static struct ns_common *pidns_get_parent(struct ns_common *ns) +{ + struct pid_namespace *active = task_active_pid_ns(current); + struct pid_namespace *pid_ns, *p; + + /* See if the parent is in the current namespace */ + pid_ns = p = to_pid_ns(ns)->parent; + for (;;) { + if (!p) + return ERR_PTR(-EPERM); + if (p == active) + break; + p = p->parent; + } + + return &get_pid_ns(pid_ns)->ns; +} + static struct user_namespace *pidns_owner(struct ns_common *ns) { return to_pid_ns(ns)->user_ns; @@ -400,6 +418,7 @@ const struct proc_ns_operations pidns_operations = { .put = pidns_put, .install = pidns_install, .owner = pidns_owner, + .get_parent = pidns_get_parent, }; static __init int pid_namespaces_init(void) diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 0ef683a03c20..a58a219b99c6 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -1034,6 +1034,7 @@ const struct proc_ns_operations userns_operations = { .put = userns_put, .install = userns_install, .owner = userns_owner, + .get_parent = ns_get_owner, }; static __init int user_namespaces_init(void) -- cgit v1.2.3 From 8061bb54436c19fd16b7c734a69ff60bac26e3e9 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Wed, 14 Sep 2016 23:41:46 +0800 Subject: netfilter: nft_queue: add _SREG_QNUM attr to select the queue number Currently, the user can specify the queue numbers by _QUEUE_NUM and _QUEUE_TOTAL attributes, this is enough in most situations. But acctually, it is not very flexible, for example: tcp dport 80 mapped to queue0 tcp dport 81 mapped to queue1 tcp dport 82 mapped to queue2 In order to do this thing, we must add 3 nft rules, and more mapping meant more rules ... So take one register to select the queue number, then we can add one simple rule to mapping queues, maybe like this: queue num tcp dport map { 80:0, 81:1, 82:2 ... } Florian Westphal also proposed wider usage scenarios: queue num jhash ip saddr . ip daddr mod ... queue num meta cpu ... queue num meta mark ... The last point is how to load a queue number from sreg, although we can use *(u16*)®s->data[reg] to load the queue number, just like nat expr to load its l4port do. But we will cooperate with hash expr, meta cpu, meta mark expr and so on. They all store the result to u32 type, so cast it to u16 pointer and dereference it will generate wrong result in the big endian system. So just keep it simple, we treat queue number as u32 type, although u16 type is already enough. Suggested-by: Pablo Neira Ayuso Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 + net/netfilter/nft_queue.c | 102 +++++++++++++++++++++++++++---- 2 files changed, 92 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index bcfb892ff148..1cf41dd838b2 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -894,12 +894,14 @@ enum nft_log_attributes { * @NFTA_QUEUE_NUM: netlink queue to send messages to (NLA_U16) * @NFTA_QUEUE_TOTAL: number of queues to load balance packets on (NLA_U16) * @NFTA_QUEUE_FLAGS: various flags (NLA_U16) + * @NFTA_QUEUE_SREG_QNUM: source register of queue number (NLA_U32: nft_registers) */ enum nft_queue_attributes { NFTA_QUEUE_UNSPEC, NFTA_QUEUE_NUM, NFTA_QUEUE_TOTAL, NFTA_QUEUE_FLAGS, + NFTA_QUEUE_SREG_QNUM, __NFTA_QUEUE_MAX }; #define NFTA_QUEUE_MAX (__NFTA_QUEUE_MAX - 1) diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c index d16d59959ff6..393d359a1889 100644 --- a/net/netfilter/nft_queue.c +++ b/net/netfilter/nft_queue.c @@ -22,9 +22,10 @@ static u32 jhash_initval __read_mostly; struct nft_queue { - u16 queuenum; - u16 queues_total; - u16 flags; + enum nft_registers sreg_qnum:8; + u16 queuenum; + u16 queues_total; + u16 flags; }; static void nft_queue_eval(const struct nft_expr *expr, @@ -54,26 +55,39 @@ static void nft_queue_eval(const struct nft_expr *expr, regs->verdict.code = ret; } +static void nft_queue_sreg_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_queue *priv = nft_expr_priv(expr); + u32 queue, ret; + + queue = regs->data[priv->sreg_qnum]; + + ret = NF_QUEUE_NR(queue); + if (priv->flags & NFT_QUEUE_FLAG_BYPASS) + ret |= NF_VERDICT_FLAG_QUEUE_BYPASS; + + regs->verdict.code = ret; +} + static const struct nla_policy nft_queue_policy[NFTA_QUEUE_MAX + 1] = { [NFTA_QUEUE_NUM] = { .type = NLA_U16 }, [NFTA_QUEUE_TOTAL] = { .type = NLA_U16 }, [NFTA_QUEUE_FLAGS] = { .type = NLA_U16 }, + [NFTA_QUEUE_SREG_QNUM] = { .type = NLA_U32 }, }; static int nft_queue_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) + const struct nft_expr *expr, + const struct nlattr * const tb[]) { struct nft_queue *priv = nft_expr_priv(expr); u32 maxid; - if (tb[NFTA_QUEUE_NUM] == NULL) - return -EINVAL; - - init_hashrandom(&jhash_initval); priv->queuenum = ntohs(nla_get_be16(tb[NFTA_QUEUE_NUM])); - if (tb[NFTA_QUEUE_TOTAL] != NULL) + if (tb[NFTA_QUEUE_TOTAL]) priv->queues_total = ntohs(nla_get_be16(tb[NFTA_QUEUE_TOTAL])); else priv->queues_total = 1; @@ -85,11 +99,34 @@ static int nft_queue_init(const struct nft_ctx *ctx, if (maxid > U16_MAX) return -ERANGE; - if (tb[NFTA_QUEUE_FLAGS] != NULL) { + if (tb[NFTA_QUEUE_FLAGS]) { + priv->flags = ntohs(nla_get_be16(tb[NFTA_QUEUE_FLAGS])); + if (priv->flags & ~NFT_QUEUE_FLAG_MASK) + return -EINVAL; + } + return 0; +} + +static int nft_queue_sreg_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_queue *priv = nft_expr_priv(expr); + int err; + + priv->sreg_qnum = nft_parse_register(tb[NFTA_QUEUE_SREG_QNUM]); + err = nft_validate_register_load(priv->sreg_qnum, sizeof(u32)); + if (err < 0) + return err; + + if (tb[NFTA_QUEUE_FLAGS]) { priv->flags = ntohs(nla_get_be16(tb[NFTA_QUEUE_FLAGS])); if (priv->flags & ~NFT_QUEUE_FLAG_MASK) return -EINVAL; + if (priv->flags & NFT_QUEUE_FLAG_CPU_FANOUT) + return -EOPNOTSUPP; } + return 0; } @@ -108,6 +145,21 @@ nla_put_failure: return -1; } +static int +nft_queue_sreg_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_queue *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_QUEUE_SREG_QNUM, priv->sreg_qnum) || + nla_put_be16(skb, NFTA_QUEUE_FLAGS, htons(priv->flags))) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + static struct nft_expr_type nft_queue_type; static const struct nft_expr_ops nft_queue_ops = { .type = &nft_queue_type, @@ -117,9 +169,35 @@ static const struct nft_expr_ops nft_queue_ops = { .dump = nft_queue_dump, }; +static const struct nft_expr_ops nft_queue_sreg_ops = { + .type = &nft_queue_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_queue)), + .eval = nft_queue_sreg_eval, + .init = nft_queue_sreg_init, + .dump = nft_queue_sreg_dump, +}; + +static const struct nft_expr_ops * +nft_queue_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + if (tb[NFTA_QUEUE_NUM] && tb[NFTA_QUEUE_SREG_QNUM]) + return ERR_PTR(-EINVAL); + + init_hashrandom(&jhash_initval); + + if (tb[NFTA_QUEUE_NUM]) + return &nft_queue_ops; + + if (tb[NFTA_QUEUE_SREG_QNUM]) + return &nft_queue_sreg_ops; + + return ERR_PTR(-EINVAL); +} + static struct nft_expr_type nft_queue_type __read_mostly = { .name = "queue", - .ops = &nft_queue_ops, + .select_ops = &nft_queue_select_ops, .policy = nft_queue_policy, .maxattr = NFTA_QUEUE_MAX, .owner = THIS_MODULE, -- cgit v1.2.3 From fefa569a9d4bc4b7758c0fddd75bb0382c95da77 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 22 Sep 2016 08:58:55 -0700 Subject: net_sched: sch_fq: account for schedule/timers drifts It looks like the following patch can make FQ very precise, even in VM or stressed hosts. It matters at high pacing rates. We take into account the difference between the time that was programmed when last packet was sent, and current time (a drift of tens of usecs is often observed) Add an EWMA of the unthrottle latency to help diagnostics. This latency is the difference between current time and oldest packet in delayed RB-tree. This accounts for the high resolution timer latency, but can be different under stress, as fq_check_throttled() can be opportunistically be called from a dequeue() called after an enqueue() for a different flow. Tested: // Start a 10Gbit flow $ netperf --google-pacing-rate 1250000000 -H lpaa24 -l 10000 -- -K bbr & Before patch : $ sar -n DEV 10 5 | grep eth0 | grep Average Average: eth0 17106.04 756876.84 1102.75 1119049.02 0.00 0.00 0.52 After patch : $ sar -n DEV 10 5 | grep eth0 | grep Average Average: eth0 17867.00 800245.90 1151.77 1183172.12 0.00 0.00 0.52 A new iproute2 tc can output the 'unthrottle latency' : $ tc -s qd sh dev eth0 | grep latency 0 gc, 0 highprio, 32490767 throttled, 2382 ns latency Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 2 +- net/sched/sch_fq.c | 21 ++++++++++++++++++--- 2 files changed, 19 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index f8e39dbaa781..df7451d35131 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -811,7 +811,7 @@ struct tc_fq_qd_stats { __u32 flows; __u32 inactive_flows; __u32 throttled_flows; - __u32 pad; + __u32 unthrottle_latency_ns; }; /* Heavy-Hitter Filter */ diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 5dd929cc1423..18e752439f6f 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -86,6 +86,7 @@ struct fq_sched_data { struct rb_root delayed; /* for rate limited flows */ u64 time_next_delayed_flow; + unsigned long unthrottle_latency_ns; struct fq_flow internal; /* for non classified or high prio packets */ u32 quantum; @@ -408,11 +409,19 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, static void fq_check_throttled(struct fq_sched_data *q, u64 now) { + unsigned long sample; struct rb_node *p; if (q->time_next_delayed_flow > now) return; + /* Update unthrottle latency EWMA. + * This is cheap and can help diagnosing timer/latency problems. + */ + sample = (unsigned long)(now - q->time_next_delayed_flow); + q->unthrottle_latency_ns -= q->unthrottle_latency_ns >> 3; + q->unthrottle_latency_ns += sample >> 3; + q->time_next_delayed_flow = ~0ULL; while ((p = rb_first(&q->delayed)) != NULL) { struct fq_flow *f = container_of(p, struct fq_flow, rate_node); @@ -515,7 +524,12 @@ begin: len = NSEC_PER_SEC; q->stat_pkts_too_long++; } - + /* Account for schedule/timers drifts. + * f->time_next_packet was set when prior packet was sent, + * and current time (@now) can be too late by tens of us. + */ + if (f->time_next_packet) + len -= min(len/2, now - f->time_next_packet); f->time_next_packet = now + len; } out: @@ -787,6 +801,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt) q->initial_quantum = 10 * psched_mtu(qdisc_dev(sch)); q->flow_refill_delay = msecs_to_jiffies(40); q->flow_max_rate = ~0U; + q->time_next_delayed_flow = ~0ULL; q->rate_enable = 1; q->new_flows.first = NULL; q->old_flows.first = NULL; @@ -854,8 +869,8 @@ static int fq_dump_stats(struct Qdisc *sch, struct gnet_dump *d) st.flows = q->flows; st.inactive_flows = q->inactive_flows; st.throttled_flows = q->throttled_flows; - st.pad = 0; - + st.unthrottle_latency_ns = min_t(unsigned long, + q->unthrottle_latency_ns, ~0U); sch_tree_unlock(sch); return gnet_stats_copy_app(d, &st, sizeof(st)); -- cgit v1.2.3 From 7a4b28c6cc9ffac50f791b99cc7e46106436e5d8 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 23 Sep 2016 01:28:37 +0200 Subject: bpf: add helper to invalidate hash Add a small helper that complements 36bbef52c7eb ("bpf: direct packet write and access for helpers for clsact progs") for invalidating the current skb->hash after mangling on headers via direct packet write. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 7 +++++++ net/core/filter.c | 18 ++++++++++++++++++ 2 files changed, 25 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e07432b9f8b8..f09c70b97eca 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -419,6 +419,13 @@ enum bpf_func_id { */ BPF_FUNC_csum_update, + /** + * bpf_set_hash_invalid(skb) + * Invalidate current skb>hash. + * @skb: pointer to skb + */ + BPF_FUNC_set_hash_invalid, + __BPF_FUNC_MAX_ID, }; diff --git a/net/core/filter.c b/net/core/filter.c index acf84fbfb043..00351cdf7d0c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1777,6 +1777,22 @@ static const struct bpf_func_proto bpf_get_hash_recalc_proto = { .arg1_type = ARG_PTR_TO_CTX, }; +BPF_CALL_1(bpf_set_hash_invalid, struct sk_buff *, skb) +{ + /* After all direct packet write, this can be used once for + * triggering a lazy recalc on next skb_get_hash() invocation. + */ + skb_clear_hash(skb); + return 0; +} + +static const struct bpf_func_proto bpf_set_hash_invalid_proto = { + .func = bpf_set_hash_invalid, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto, u16, vlan_tci) { @@ -2534,6 +2550,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_get_route_realm_proto; case BPF_FUNC_get_hash_recalc: return &bpf_get_hash_recalc_proto; + case BPF_FUNC_set_hash_invalid: + return &bpf_set_hash_invalid_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; case BPF_FUNC_get_smp_processor_id: -- cgit v1.2.3 From 79aab093a0b5370d7fc4e99df75996f4744dc03f Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Thu, 22 Sep 2016 12:11:15 +0300 Subject: net: Update API for VF vlan protocol 802.1ad support Introduce new rtnl UAPI that exposes a list of vlans per VF, giving the ability for user-space application to specify it for the VF, as an option to support 802.1ad. We adjusted IP Link tool to support this option. For future use cases, the new UAPI supports multiple vlans. For now we limit the list size to a single vlan in kernel. Add IFLA_VF_VLAN_LIST in addition to IFLA_VF_VLAN to keep backward compatibility with older versions of IP Link tool. Add a vlan protocol parameter to the ndo_set_vf_vlan callback. We kept 802.1Q as the drivers' default vlan protocol. Suitable ip link tool command examples: Set vf vlan protocol 802.1ad: ip link set eth0 vf 1 vlan 100 proto 802.1ad Set vf to VST (802.1Q) mode: ip link set eth0 vf 1 vlan 100 proto 802.1Q Or by omitting the new parameter ip link set eth0 vf 1 vlan 100 Signed-off-by: Moshe Shemesh Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 3 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c | 9 ++- drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 6 +- drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h | 2 +- drivers/net/ethernet/emulex/benet/be_main.c | 6 +- drivers/net/ethernet/intel/fm10k/fm10k.h | 2 +- drivers/net/ethernet/intel/fm10k/fm10k_iov.c | 6 +- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 11 ++- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h | 4 +- drivers/net/ethernet/intel/igb/igb_main.c | 9 ++- drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c | 5 +- drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h | 2 +- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 6 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 6 +- drivers/net/ethernet/qlogic/qede/qede_main.c | 6 +- drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h | 2 +- .../net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c | 5 +- drivers/net/ethernet/sfc/sriov.c | 5 +- drivers/net/ethernet/sfc/sriov.h | 2 +- include/linux/if_link.h | 1 + include/linux/netdevice.h | 6 +- include/uapi/linux/if_link.h | 19 ++++- net/core/rtnetlink.c | 80 ++++++++++++++++++---- 23 files changed, 161 insertions(+), 42 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index 0e68fadecfdb..243cb9748d35 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -492,7 +492,8 @@ int __bnx2x_setup_tc(struct net_device *dev, u32 handle, __be16 proto, int bnx2x_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivi); int bnx2x_set_vf_mac(struct net_device *dev, int queue, u8 *mac); -int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos); +int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos, + __be16 vlan_proto); /* select_queue callback */ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 6c586b045d1d..3f77d0863543 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -2521,7 +2521,8 @@ void bnx2x_pf_set_vfs_vlan(struct bnx2x *bp) for_each_vf(bp, vfidx) { bulletin = BP_VF_BULLETIN(bp, vfidx); if (bulletin->valid_bitmap & (1 << VLAN_VALID)) - bnx2x_set_vf_vlan(bp->dev, vfidx, bulletin->vlan, 0); + bnx2x_set_vf_vlan(bp->dev, vfidx, bulletin->vlan, 0, + htons(ETH_P_8021Q)); } } @@ -2781,7 +2782,8 @@ static int bnx2x_set_vf_vlan_filter(struct bnx2x *bp, struct bnx2x_virtf *vf, return 0; } -int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos) +int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos, + __be16 vlan_proto) { struct pf_vf_bulletin_content *bulletin = NULL; struct bnx2x *bp = netdev_priv(dev); @@ -2796,6 +2798,9 @@ int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos) return -EINVAL; } + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + DP(BNX2X_MSG_IOV, "configuring VF %d with VLAN %d qos %d\n", vfidx, vlan, 0); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 8be718508600..ec6cd18842c3 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -174,7 +174,8 @@ int bnxt_set_vf_mac(struct net_device *dev, int vf_id, u8 *mac) return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); } -int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos) +int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos, + __be16 vlan_proto) { struct hwrm_func_cfg_input req = {0}; struct bnxt *bp = netdev_priv(dev); @@ -185,6 +186,9 @@ int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos) if (bp->hwrm_spec_code < 0x10201) return -ENOTSUPP; + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + rc = bnxt_vf_ndo_prep(bp, vf_id); if (rc) return rc; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h index 0392670ab49c..1ab72e4820af 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h @@ -12,7 +12,7 @@ int bnxt_get_vf_config(struct net_device *, int, struct ifla_vf_info *); int bnxt_set_vf_mac(struct net_device *, int, u8 *); -int bnxt_set_vf_vlan(struct net_device *, int, u16, u8); +int bnxt_set_vf_vlan(struct net_device *, int, u16, u8, __be16); int bnxt_set_vf_bw(struct net_device *, int, int, int); int bnxt_set_vf_link_state(struct net_device *, int, int); int bnxt_set_vf_spoofchk(struct net_device *, int, bool); diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 9a94840c5757..ac513e6627d1 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1895,7 +1895,8 @@ static int be_clear_vf_tvt(struct be_adapter *adapter, int vf) return 0; } -static int be_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos) +static int be_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos, + __be16 vlan_proto) { struct be_adapter *adapter = netdev_priv(netdev); struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf]; @@ -1907,6 +1908,9 @@ static int be_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos) if (vf >= adapter->num_vfs || vlan > 4095 || qos > 7) return -EINVAL; + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + if (vlan || qos) { vlan |= qos << VLAN_PRIO_SHIFT; status = be_set_vf_tvt(adapter, vf, vlan); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index 67ff01aeb11a..4d19e46f7c55 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -507,7 +507,7 @@ int fm10k_iov_configure(struct pci_dev *pdev, int num_vfs); s32 fm10k_iov_update_pvid(struct fm10k_intfc *interface, u16 glort, u16 pvid); int fm10k_ndo_set_vf_mac(struct net_device *netdev, int vf_idx, u8 *mac); int fm10k_ndo_set_vf_vlan(struct net_device *netdev, - int vf_idx, u16 vid, u8 qos); + int vf_idx, u16 vid, u8 qos, __be16 vlan_proto); int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx, int rate, int unused); int fm10k_ndo_get_vf_config(struct net_device *netdev, diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index d9dec81f6b6d..5f4dac0d36ef 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -445,7 +445,7 @@ int fm10k_ndo_set_vf_mac(struct net_device *netdev, int vf_idx, u8 *mac) } int fm10k_ndo_set_vf_vlan(struct net_device *netdev, int vf_idx, u16 vid, - u8 qos) + u8 qos, __be16 vlan_proto) { struct fm10k_intfc *interface = netdev_priv(netdev); struct fm10k_iov_data *iov_data = interface->iov_data; @@ -460,6 +460,10 @@ int fm10k_ndo_set_vf_vlan(struct net_device *netdev, int vf_idx, u16 vid, if (qos || (vid > (VLAN_VID_MASK - 1))) return -EINVAL; + /* VF VLAN Protocol part to default is unsupported */ + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + vf_info = &iov_data->vf_info[vf_idx]; /* exit if there is nothing to do */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index da3423561b3a..724d8740d4cc 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2747,11 +2747,12 @@ error_param: * @vf_id: VF identifier * @vlan_id: mac address * @qos: priority setting + * @vlan_proto: vlan protocol * * program VF vlan id and/or qos **/ -int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, - int vf_id, u16 vlan_id, u8 qos) +int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, + u16 vlan_id, u8 qos, __be16 vlan_proto) { u16 vlanprio = vlan_id | (qos << I40E_VLAN_PRIORITY_SHIFT); struct i40e_netdev_priv *np = netdev_priv(netdev); @@ -2774,6 +2775,12 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, goto error_pvid; } + if (vlan_proto != htons(ETH_P_8021Q)) { + dev_err(&pf->pdev->dev, "VF VLAN protocol is not supported\n"); + ret = -EPROTONOSUPPORT; + goto error_pvid; + } + vf = &(pf->vf[vf_id]); vsi = pf->vsi[vf->lan_vsi_idx]; if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 875174141451..4012d069939a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -129,8 +129,8 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf); /* VF configuration related iplink handlers */ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac); -int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, - int vf_id, u16 vlan_id, u8 qos); +int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, + u16 vlan_id, u8 qos, __be16 vlan_proto); int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, int max_tx_rate); int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index af75eac5fa16..a83aa13a5bf4 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -169,7 +169,7 @@ static int igb_set_vf_mac(struct igb_adapter *, int, unsigned char *); static void igb_restore_vf_multicasts(struct igb_adapter *adapter); static int igb_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac); static int igb_ndo_set_vf_vlan(struct net_device *netdev, - int vf, u16 vlan, u8 qos); + int vf, u16 vlan, u8 qos, __be16 vlan_proto); static int igb_ndo_set_vf_bw(struct net_device *, int, int, int); static int igb_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting); @@ -6222,14 +6222,17 @@ static int igb_disable_port_vlan(struct igb_adapter *adapter, int vf) return 0; } -static int igb_ndo_set_vf_vlan(struct net_device *netdev, - int vf, u16 vlan, u8 qos) +static int igb_ndo_set_vf_vlan(struct net_device *netdev, int vf, + u16 vlan, u8 qos, __be16 vlan_proto) { struct igb_adapter *adapter = netdev_priv(netdev); if ((vf >= adapter->vfs_allocated_count) || (vlan > 4095) || (qos > 7)) return -EINVAL; + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + return (vlan || qos) ? igb_enable_port_vlan(adapter, vf, vlan, qos) : igb_disable_port_vlan(adapter, vf); } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 8618599dfd6f..b18590a995db 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -1354,13 +1354,16 @@ static int ixgbe_disable_port_vlan(struct ixgbe_adapter *adapter, int vf) return err; } -int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos) +int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, + u8 qos, __be16 vlan_proto) { int err = 0; struct ixgbe_adapter *adapter = netdev_priv(netdev); if ((vf >= adapter->num_vfs) || (vlan > 4095) || (qos > 7)) return -EINVAL; + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; if (vlan || qos) { /* Check if there is already a port VLAN set, if so * we have to delete the old one first before we diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h index 47e65e2f886a..0c7977d27b71 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h @@ -43,7 +43,7 @@ void ixgbe_disable_tx_rx(struct ixgbe_adapter *adapter); void ixgbe_ping_all_vfs(struct ixgbe_adapter *adapter); int ixgbe_ndo_set_vf_mac(struct net_device *netdev, int queue, u8 *mac); int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int queue, u16 vlan, - u8 qos); + u8 qos, __be16 vlan_proto); int ixgbe_link_mbps(struct ixgbe_adapter *adapter); int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate, int max_tx_rate); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index a94f8a3f026c..132eeeafcdc4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2400,11 +2400,15 @@ static int mlx4_en_set_vf_mac(struct net_device *dev, int queue, u8 *mac) return mlx4_set_vf_mac(mdev->dev, en_priv->port, queue, mac_u64); } -static int mlx4_en_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos) +static int mlx4_en_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos, + __be16 vlan_proto) { struct mlx4_en_priv *en_priv = netdev_priv(dev); struct mlx4_en_dev *mdev = en_priv->mdev; + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + return mlx4_set_vf_vlan(mdev->dev, en_priv->port, vf, vlan, qos); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index c12792314be7..b58cfe37dead 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2917,11 +2917,15 @@ static int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac) return mlx5_eswitch_set_vport_mac(mdev->priv.eswitch, vf + 1, mac); } -static int mlx5e_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos) +static int mlx5e_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos, + __be16 vlan_proto) { struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5_core_dev *mdev = priv->mdev; + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + return mlx5_eswitch_set_vport_vlan(mdev->priv.eswitch, vf + 1, vlan, qos); } diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index cd23a2946db7..0e198fe89d1a 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -100,7 +100,8 @@ static int qede_alloc_rx_buffer(struct qede_dev *edev, static void qede_link_update(void *dev, struct qed_link_output *link); #ifdef CONFIG_QED_SRIOV -static int qede_set_vf_vlan(struct net_device *ndev, int vf, u16 vlan, u8 qos) +static int qede_set_vf_vlan(struct net_device *ndev, int vf, u16 vlan, u8 qos, + __be16 vlan_proto) { struct qede_dev *edev = netdev_priv(ndev); @@ -109,6 +110,9 @@ static int qede_set_vf_vlan(struct net_device *ndev, int vf, u16 vlan, u8 qos) return -EINVAL; } + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + DP_VERBOSE(edev, QED_MSG_IOV, "Setting Vlan 0x%04x to VF [%d]\n", vlan, vf); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h index 24061b9b92e8..5f327659efa7 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h @@ -238,7 +238,7 @@ int qlcnic_sriov_set_vf_mac(struct net_device *, int, u8 *); int qlcnic_sriov_set_vf_tx_rate(struct net_device *, int, int, int); int qlcnic_sriov_get_vf_config(struct net_device *, int , struct ifla_vf_info *); -int qlcnic_sriov_set_vf_vlan(struct net_device *, int, u16, u8); +int qlcnic_sriov_set_vf_vlan(struct net_device *, int, u16, u8, __be16); int qlcnic_sriov_set_vf_spoofchk(struct net_device *, int, bool); #else static inline void qlcnic_sriov_pf_disable(struct qlcnic_adapter *adapter) {} diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c index afd687e5e779..50eaafa3eaba 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c @@ -1915,7 +1915,7 @@ int qlcnic_sriov_set_vf_tx_rate(struct net_device *netdev, int vf, } int qlcnic_sriov_set_vf_vlan(struct net_device *netdev, int vf, - u16 vlan, u8 qos) + u16 vlan, u8 qos, __be16 vlan_proto) { struct qlcnic_adapter *adapter = netdev_priv(netdev); struct qlcnic_sriov *sriov = adapter->ahw->sriov; @@ -1928,6 +1928,9 @@ int qlcnic_sriov_set_vf_vlan(struct net_device *netdev, int vf, if (vf >= sriov->num_vfs || qos > 7) return -EINVAL; + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + if (vlan > MAX_VLAN_ID) { netdev_err(netdev, "Invalid VLAN ID, allowed range is [0 - %d]\n", diff --git a/drivers/net/ethernet/sfc/sriov.c b/drivers/net/ethernet/sfc/sriov.c index 816c44689e67..9abcf4aded30 100644 --- a/drivers/net/ethernet/sfc/sriov.c +++ b/drivers/net/ethernet/sfc/sriov.c @@ -22,7 +22,7 @@ int efx_sriov_set_vf_mac(struct net_device *net_dev, int vf_i, u8 *mac) } int efx_sriov_set_vf_vlan(struct net_device *net_dev, int vf_i, u16 vlan, - u8 qos) + u8 qos, __be16 vlan_proto) { struct efx_nic *efx = netdev_priv(net_dev); @@ -31,6 +31,9 @@ int efx_sriov_set_vf_vlan(struct net_device *net_dev, int vf_i, u16 vlan, (qos & ~(VLAN_PRIO_MASK >> VLAN_PRIO_SHIFT))) return -EINVAL; + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + return efx->type->sriov_set_vf_vlan(efx, vf_i, vlan, qos); } else { return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/sfc/sriov.h b/drivers/net/ethernet/sfc/sriov.h index 400df526586d..ba1762e7f216 100644 --- a/drivers/net/ethernet/sfc/sriov.h +++ b/drivers/net/ethernet/sfc/sriov.h @@ -16,7 +16,7 @@ int efx_sriov_set_vf_mac(struct net_device *net_dev, int vf_i, u8 *mac); int efx_sriov_set_vf_vlan(struct net_device *net_dev, int vf_i, u16 vlan, - u8 qos); + u8 qos, __be16 vlan_proto); int efx_sriov_set_vf_spoofchk(struct net_device *net_dev, int vf_i, bool spoofchk); int efx_sriov_get_vf_config(struct net_device *net_dev, int vf_i, diff --git a/include/linux/if_link.h b/include/linux/if_link.h index f923d15b432c..0b17c585b5cd 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -25,5 +25,6 @@ struct ifla_vf_info { __u32 max_tx_rate; __u32 rss_query_en; __u32 trusted; + __be16 vlan_proto; }; #endif /* _LINUX_IF_LINK_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 69f242c71865..1e8a5c734d72 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -946,7 +946,8 @@ struct netdev_xdp { * * SR-IOV management functions. * int (*ndo_set_vf_mac)(struct net_device *dev, int vf, u8* mac); - * int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan, u8 qos); + * int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan, + * u8 qos, __be16 proto); * int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate, * int max_tx_rate); * int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); @@ -1187,7 +1188,8 @@ struct net_device_ops { int (*ndo_set_vf_mac)(struct net_device *dev, int queue, u8 *mac); int (*ndo_set_vf_vlan)(struct net_device *dev, - int queue, u16 vlan, u8 qos); + int queue, u16 vlan, + u8 qos, __be16 proto); int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate, int max_tx_rate); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 7ec9e99d5491..b4fba662cd32 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -619,7 +619,7 @@ enum { enum { IFLA_VF_UNSPEC, IFLA_VF_MAC, /* Hardware queue specific attributes */ - IFLA_VF_VLAN, + IFLA_VF_VLAN, /* VLAN ID and QoS */ IFLA_VF_TX_RATE, /* Max TX Bandwidth Allocation */ IFLA_VF_SPOOFCHK, /* Spoof Checking on/off switch */ IFLA_VF_LINK_STATE, /* link state enable/disable/auto switch */ @@ -631,6 +631,7 @@ enum { IFLA_VF_TRUST, /* Trust VF */ IFLA_VF_IB_NODE_GUID, /* VF Infiniband node GUID */ IFLA_VF_IB_PORT_GUID, /* VF Infiniband port GUID */ + IFLA_VF_VLAN_LIST, /* nested list of vlans, option for QinQ */ __IFLA_VF_MAX, }; @@ -647,6 +648,22 @@ struct ifla_vf_vlan { __u32 qos; }; +enum { + IFLA_VF_VLAN_INFO_UNSPEC, + IFLA_VF_VLAN_INFO, /* VLAN ID, QoS and VLAN protocol */ + __IFLA_VF_VLAN_INFO_MAX, +}; + +#define IFLA_VF_VLAN_INFO_MAX (__IFLA_VF_VLAN_INFO_MAX - 1) +#define MAX_VLAN_LIST_LEN 1 + +struct ifla_vf_vlan_info { + __u32 vf; + __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ + __u32 qos; + __be16 vlan_proto; /* VLAN protocol either 802.1Q or 802.1ad */ +}; + struct ifla_vf_tx_rate { __u32 vf; __u32 rate; /* Max TX bandwidth in Mbps, 0 disables throttling */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 0dbae4244a89..3ac8946bf244 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -843,7 +843,10 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, size += nla_total_size(num_vfs * sizeof(struct nlattr)); size += num_vfs * (nla_total_size(sizeof(struct ifla_vf_mac)) + - nla_total_size(sizeof(struct ifla_vf_vlan)) + + nla_total_size(MAX_VLAN_LIST_LEN * + sizeof(struct nlattr)) + + nla_total_size(MAX_VLAN_LIST_LEN * + sizeof(struct ifla_vf_vlan_info)) + nla_total_size(sizeof(struct ifla_vf_spoofchk)) + nla_total_size(sizeof(struct ifla_vf_rate)) + nla_total_size(sizeof(struct ifla_vf_link_state)) + @@ -1111,14 +1114,15 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, struct nlattr *vfinfo) { struct ifla_vf_rss_query_en vf_rss_query_en; + struct nlattr *vf, *vfstats, *vfvlanlist; struct ifla_vf_link_state vf_linkstate; + struct ifla_vf_vlan_info vf_vlan_info; struct ifla_vf_spoofchk vf_spoofchk; struct ifla_vf_tx_rate vf_tx_rate; struct ifla_vf_stats vf_stats; struct ifla_vf_trust vf_trust; struct ifla_vf_vlan vf_vlan; struct ifla_vf_rate vf_rate; - struct nlattr *vf, *vfstats; struct ifla_vf_mac vf_mac; struct ifla_vf_info ivi; @@ -1135,11 +1139,14 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, * IFLA_VF_LINK_STATE_AUTO which equals zero */ ivi.linkstate = 0; + /* VLAN Protocol by default is 802.1Q */ + ivi.vlan_proto = htons(ETH_P_8021Q); if (dev->netdev_ops->ndo_get_vf_config(dev, vfs_num, &ivi)) return 0; vf_mac.vf = vf_vlan.vf = + vf_vlan_info.vf = vf_rate.vf = vf_tx_rate.vf = vf_spoofchk.vf = @@ -1150,6 +1157,9 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); vf_vlan.vlan = ivi.vlan; vf_vlan.qos = ivi.qos; + vf_vlan_info.vlan = ivi.vlan; + vf_vlan_info.qos = ivi.qos; + vf_vlan_info.vlan_proto = ivi.vlan_proto; vf_tx_rate.rate = ivi.max_tx_rate; vf_rate.min_tx_rate = ivi.min_tx_rate; vf_rate.max_tx_rate = ivi.max_tx_rate; @@ -1158,10 +1168,8 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, vf_rss_query_en.setting = ivi.rss_query_en; vf_trust.setting = ivi.trusted; vf = nla_nest_start(skb, IFLA_VF_INFO); - if (!vf) { - nla_nest_cancel(skb, vfinfo); - return -EMSGSIZE; - } + if (!vf) + goto nla_put_vfinfo_failure; if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) || nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) || nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate), @@ -1177,17 +1185,23 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, &vf_rss_query_en) || nla_put(skb, IFLA_VF_TRUST, sizeof(vf_trust), &vf_trust)) - return -EMSGSIZE; + goto nla_put_vf_failure; + vfvlanlist = nla_nest_start(skb, IFLA_VF_VLAN_LIST); + if (!vfvlanlist) + goto nla_put_vf_failure; + if (nla_put(skb, IFLA_VF_VLAN_INFO, sizeof(vf_vlan_info), + &vf_vlan_info)) { + nla_nest_cancel(skb, vfvlanlist); + goto nla_put_vf_failure; + } + nla_nest_end(skb, vfvlanlist); memset(&vf_stats, 0, sizeof(vf_stats)); if (dev->netdev_ops->ndo_get_vf_stats) dev->netdev_ops->ndo_get_vf_stats(dev, vfs_num, &vf_stats); vfstats = nla_nest_start(skb, IFLA_VF_STATS); - if (!vfstats) { - nla_nest_cancel(skb, vf); - nla_nest_cancel(skb, vfinfo); - return -EMSGSIZE; - } + if (!vfstats) + goto nla_put_vf_failure; if (nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_PACKETS, vf_stats.rx_packets, IFLA_VF_STATS_PAD) || nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_PACKETS, @@ -1199,11 +1213,19 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, nla_put_u64_64bit(skb, IFLA_VF_STATS_BROADCAST, vf_stats.broadcast, IFLA_VF_STATS_PAD) || nla_put_u64_64bit(skb, IFLA_VF_STATS_MULTICAST, - vf_stats.multicast, IFLA_VF_STATS_PAD)) - return -EMSGSIZE; + vf_stats.multicast, IFLA_VF_STATS_PAD)) { + nla_nest_cancel(skb, vfstats); + goto nla_put_vf_failure; + } nla_nest_end(skb, vfstats); nla_nest_end(skb, vf); return 0; + +nla_put_vf_failure: + nla_nest_cancel(skb, vf); +nla_put_vfinfo_failure: + nla_nest_cancel(skb, vfinfo); + return -EMSGSIZE; } static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev) @@ -1448,6 +1470,7 @@ static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { [IFLA_VF_MAC] = { .len = sizeof(struct ifla_vf_mac) }, [IFLA_VF_VLAN] = { .len = sizeof(struct ifla_vf_vlan) }, + [IFLA_VF_VLAN_LIST] = { .type = NLA_NESTED }, [IFLA_VF_TX_RATE] = { .len = sizeof(struct ifla_vf_tx_rate) }, [IFLA_VF_SPOOFCHK] = { .len = sizeof(struct ifla_vf_spoofchk) }, [IFLA_VF_RATE] = { .len = sizeof(struct ifla_vf_rate) }, @@ -1704,7 +1727,34 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) err = -EOPNOTSUPP; if (ops->ndo_set_vf_vlan) err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan, - ivv->qos); + ivv->qos, + htons(ETH_P_8021Q)); + if (err < 0) + return err; + } + + if (tb[IFLA_VF_VLAN_LIST]) { + struct ifla_vf_vlan_info *ivvl[MAX_VLAN_LIST_LEN]; + struct nlattr *attr; + int rem, len = 0; + + err = -EOPNOTSUPP; + if (!ops->ndo_set_vf_vlan) + return err; + + nla_for_each_nested(attr, tb[IFLA_VF_VLAN_LIST], rem) { + if (nla_type(attr) != IFLA_VF_VLAN_INFO || + nla_len(attr) < NLA_HDRLEN) { + return -EINVAL; + } + if (len >= MAX_VLAN_LIST_LEN) + return -EOPNOTSUPP; + ivvl[len] = nla_data(attr); + + len++; + } + err = ops->ndo_set_vf_vlan(dev, ivvl[0]->vf, ivvl[0]->vlan, + ivvl[0]->qos, ivvl[0]->vlan_proto); if (err < 0) return err; } -- cgit v1.2.3 From 11d5f15723c9f39d7c131d0149d024c17dbef676 Mon Sep 17 00:00:00 2001 From: Vishwanath Pai Date: Thu, 22 Sep 2016 12:43:44 -0400 Subject: netfilter: xt_hashlimit: Create revision 2 to support higher pps rates Create a new revision for the hashlimit iptables extension module. Rev 2 will support higher pps of upto 1 million, Version 1 supports only 10k. To support this we have to increase the size of the variables avg and burst in hashlimit_cfg to 64-bit. Create two new structs hashlimit_cfg2 and xt_hashlimit_mtinfo2 and also create newer versions of all the functions for match, checkentry and destroy. Some of the functions like hashlimit_mt, hashlimit_mt_check etc are very similar in both rev1 and rev2 with only minor changes, so I have split those functions and moved all the common code to a *_common function. Signed-off-by: Vishwanath Pai Signed-off-by: Joshua Hunt Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/xt_hashlimit.h | 23 ++ net/netfilter/xt_hashlimit.c | 330 ++++++++++++++++++++++------ 2 files changed, 285 insertions(+), 68 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/xt_hashlimit.h b/include/uapi/linux/netfilter/xt_hashlimit.h index 6db90372f09c..3efc0ca18345 100644 --- a/include/uapi/linux/netfilter/xt_hashlimit.h +++ b/include/uapi/linux/netfilter/xt_hashlimit.h @@ -6,6 +6,7 @@ /* timings are in milliseconds. */ #define XT_HASHLIMIT_SCALE 10000 +#define XT_HASHLIMIT_SCALE_v2 1000000llu /* 1/10,000 sec period => max of 10,000/sec. Min rate is then 429490 * seconds, or one packet every 59 hours. */ @@ -63,6 +64,20 @@ struct hashlimit_cfg1 { __u8 srcmask, dstmask; }; +struct hashlimit_cfg2 { + __u64 avg; /* Average secs between packets * scale */ + __u64 burst; /* Period multiplier for upper limit. */ + __u32 mode; /* bitmask of XT_HASHLIMIT_HASH_* */ + + /* user specified */ + __u32 size; /* how many buckets */ + __u32 max; /* max number of entries */ + __u32 gc_interval; /* gc interval */ + __u32 expire; /* when do entries expire? */ + + __u8 srcmask, dstmask; +}; + struct xt_hashlimit_mtinfo1 { char name[IFNAMSIZ]; struct hashlimit_cfg1 cfg; @@ -71,4 +86,12 @@ struct xt_hashlimit_mtinfo1 { struct xt_hashlimit_htable *hinfo __attribute__((aligned(8))); }; +struct xt_hashlimit_mtinfo2 { + char name[NAME_MAX]; + struct hashlimit_cfg2 cfg; + + /* Used internally by the kernel */ + struct xt_hashlimit_htable *hinfo __attribute__((aligned(8))); +}; + #endif /* _UAPI_XT_HASHLIMIT_H */ diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index e93d9e0a3f35..44a095ecc7b7 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -57,6 +57,7 @@ static inline struct hashlimit_net *hashlimit_pernet(struct net *net) /* need to declare this at the top */ static const struct file_operations dl_file_ops_v1; +static const struct file_operations dl_file_ops; /* hash table crap */ struct dsthash_dst { @@ -86,8 +87,8 @@ struct dsthash_ent { unsigned long expires; /* precalculated expiry time */ struct { unsigned long prev; /* last modification */ - u_int32_t credit; - u_int32_t credit_cap, cost; + u_int64_t credit; + u_int64_t credit_cap, cost; } rateinfo; struct rcu_head rcu; }; @@ -98,7 +99,7 @@ struct xt_hashlimit_htable { u_int8_t family; bool rnd_initialized; - struct hashlimit_cfg1 cfg; /* config */ + struct hashlimit_cfg2 cfg; /* config */ /* used internally */ spinlock_t lock; /* lock for list_head */ @@ -114,6 +115,30 @@ struct xt_hashlimit_htable { struct hlist_head hash[0]; /* hashtable itself */ }; +static int +cfg_copy(struct hashlimit_cfg2 *to, void *from, int revision) +{ + if (revision == 1) { + struct hashlimit_cfg1 *cfg = (struct hashlimit_cfg1 *)from; + + to->mode = cfg->mode; + to->avg = cfg->avg; + to->burst = cfg->burst; + to->size = cfg->size; + to->max = cfg->max; + to->gc_interval = cfg->gc_interval; + to->expire = cfg->expire; + to->srcmask = cfg->srcmask; + to->dstmask = cfg->dstmask; + } else if (revision == 2) { + memcpy(to, from, sizeof(struct hashlimit_cfg2)); + } else { + return -EINVAL; + } + + return 0; +} + static DEFINE_MUTEX(hashlimit_mutex); /* protects htables list */ static struct kmem_cache *hashlimit_cachep __read_mostly; @@ -215,16 +240,18 @@ dsthash_free(struct xt_hashlimit_htable *ht, struct dsthash_ent *ent) } static void htable_gc(struct work_struct *work); -static int htable_create_v1(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, - u_int8_t family) +static int htable_create(struct net *net, struct hashlimit_cfg2 *cfg, + const char *name, u_int8_t family, + struct xt_hashlimit_htable **out_hinfo, + int revision) { struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); struct xt_hashlimit_htable *hinfo; - unsigned int size; - unsigned int i; + unsigned int size, i; + int ret; - if (minfo->cfg.size) { - size = minfo->cfg.size; + if (cfg->size) { + size = cfg->size; } else { size = (totalram_pages << PAGE_SHIFT) / 16384 / sizeof(struct list_head); @@ -238,10 +265,14 @@ static int htable_create_v1(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, sizeof(struct list_head) * size); if (hinfo == NULL) return -ENOMEM; - minfo->hinfo = hinfo; + *out_hinfo = hinfo; /* copy match config into hashtable config */ - memcpy(&hinfo->cfg, &minfo->cfg, sizeof(hinfo->cfg)); + ret = cfg_copy(&hinfo->cfg, (void *)cfg, 2); + + if (ret) + return ret; + hinfo->cfg.size = size; if (hinfo->cfg.max == 0) hinfo->cfg.max = 8 * hinfo->cfg.size; @@ -255,17 +286,18 @@ static int htable_create_v1(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, hinfo->count = 0; hinfo->family = family; hinfo->rnd_initialized = false; - hinfo->name = kstrdup(minfo->name, GFP_KERNEL); + hinfo->name = kstrdup(name, GFP_KERNEL); if (!hinfo->name) { vfree(hinfo); return -ENOMEM; } spin_lock_init(&hinfo->lock); - hinfo->pde = proc_create_data(minfo->name, 0, + hinfo->pde = proc_create_data(name, 0, (family == NFPROTO_IPV4) ? hashlimit_net->ipt_hashlimit : hashlimit_net->ip6t_hashlimit, - &dl_file_ops_v1, hinfo); + (revision == 1) ? &dl_file_ops_v1 : &dl_file_ops, + hinfo); if (hinfo->pde == NULL) { kfree(hinfo->name); vfree(hinfo); @@ -399,6 +431,7 @@ static void htable_put(struct xt_hashlimit_htable *hinfo) CREDITS_PER_JIFFY*HZ*60*60*24 < 2^32 ie. */ #define MAX_CPJ_v1 (0xFFFFFFFF / (HZ*60*60*24)) +#define MAX_CPJ (0xFFFFFFFFFFFFFFFF / (HZ*60*60*24)) /* Repeated shift and or gives us all 1s, final shift and add 1 gives * us the power of 2 below the theoretical max, so GCC simply does a @@ -408,8 +441,11 @@ static void htable_put(struct xt_hashlimit_htable *hinfo) #define _POW2_BELOW8(x) (_POW2_BELOW4(x)|_POW2_BELOW4((x)>>4)) #define _POW2_BELOW16(x) (_POW2_BELOW8(x)|_POW2_BELOW8((x)>>8)) #define _POW2_BELOW32(x) (_POW2_BELOW16(x)|_POW2_BELOW16((x)>>16)) +#define _POW2_BELOW64(x) (_POW2_BELOW32(x)|_POW2_BELOW32((x)>>32)) #define POW2_BELOW32(x) ((_POW2_BELOW32(x)>>1) + 1) +#define POW2_BELOW64(x) ((_POW2_BELOW64(x)>>1) + 1) +#define CREDITS_PER_JIFFY POW2_BELOW64(MAX_CPJ) #define CREDITS_PER_JIFFY_v1 POW2_BELOW32(MAX_CPJ_v1) /* in byte mode, the lowest possible rate is one packet/second. @@ -425,15 +461,24 @@ static u32 xt_hashlimit_len_to_chunks(u32 len) } /* Precision saver. */ -static u32 user2credits(u32 user) +static u64 user2credits(u64 user, int revision) { - /* If multiplying would overflow... */ - if (user > 0xFFFFFFFF / (HZ*CREDITS_PER_JIFFY_v1)) - /* Divide first. */ - return (user / XT_HASHLIMIT_SCALE) *\ - HZ * CREDITS_PER_JIFFY_v1; + if (revision == 1) { + /* If multiplying would overflow... */ + if (user > 0xFFFFFFFF / (HZ*CREDITS_PER_JIFFY_v1)) + /* Divide first. */ + return (user / XT_HASHLIMIT_SCALE) *\ + HZ * CREDITS_PER_JIFFY_v1; + + return (user * HZ * CREDITS_PER_JIFFY_v1) \ + / XT_HASHLIMIT_SCALE; + } else { + if (user > 0xFFFFFFFFFFFFFFFF / (HZ*CREDITS_PER_JIFFY)) + return (user / XT_HASHLIMIT_SCALE_v2) *\ + HZ * CREDITS_PER_JIFFY; - return (user * HZ * CREDITS_PER_JIFFY_v1) / XT_HASHLIMIT_SCALE; + return (user * HZ * CREDITS_PER_JIFFY) / XT_HASHLIMIT_SCALE_v2; + } } static u32 user2credits_byte(u32 user) @@ -443,10 +488,11 @@ static u32 user2credits_byte(u32 user) return (u32) (us >> 32); } -static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, u32 mode) +static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, + u32 mode, int revision) { unsigned long delta = now - dh->rateinfo.prev; - u32 cap; + u64 cap, cpj; if (delta == 0) return; @@ -454,7 +500,7 @@ static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, u32 mode) dh->rateinfo.prev = now; if (mode & XT_HASHLIMIT_BYTES) { - u32 tmp = dh->rateinfo.credit; + u64 tmp = dh->rateinfo.credit; dh->rateinfo.credit += CREDITS_PER_JIFFY_BYTES * delta; cap = CREDITS_PER_JIFFY_BYTES * HZ; if (tmp >= dh->rateinfo.credit) {/* overflow */ @@ -462,7 +508,9 @@ static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, u32 mode) return; } } else { - dh->rateinfo.credit += delta * CREDITS_PER_JIFFY_v1; + cpj = (revision == 1) ? + CREDITS_PER_JIFFY_v1 : CREDITS_PER_JIFFY; + dh->rateinfo.credit += delta * cpj; cap = dh->rateinfo.credit_cap; } if (dh->rateinfo.credit > cap) @@ -470,7 +518,7 @@ static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, u32 mode) } static void rateinfo_init(struct dsthash_ent *dh, - struct xt_hashlimit_htable *hinfo) + struct xt_hashlimit_htable *hinfo, int revision) { dh->rateinfo.prev = jiffies; if (hinfo->cfg.mode & XT_HASHLIMIT_BYTES) { @@ -479,8 +527,8 @@ static void rateinfo_init(struct dsthash_ent *dh, dh->rateinfo.credit_cap = hinfo->cfg.burst; } else { dh->rateinfo.credit = user2credits(hinfo->cfg.avg * - hinfo->cfg.burst); - dh->rateinfo.cost = user2credits(hinfo->cfg.avg); + hinfo->cfg.burst, revision); + dh->rateinfo.cost = user2credits(hinfo->cfg.avg, revision); dh->rateinfo.credit_cap = dh->rateinfo.credit; } } @@ -604,15 +652,15 @@ static u32 hashlimit_byte_cost(unsigned int len, struct dsthash_ent *dh) } static bool -hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) +hashlimit_mt_common(const struct sk_buff *skb, struct xt_action_param *par, + struct xt_hashlimit_htable *hinfo, + const struct hashlimit_cfg2 *cfg, int revision) { - const struct xt_hashlimit_mtinfo1 *info = par->matchinfo; - struct xt_hashlimit_htable *hinfo = info->hinfo; unsigned long now = jiffies; struct dsthash_ent *dh; struct dsthash_dst dst; bool race = false; - u32 cost; + u64 cost; if (hashlimit_init_dst(hinfo, &dst, skb, par->thoff) < 0) goto hotdrop; @@ -627,18 +675,18 @@ hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) } else if (race) { /* Already got an entry, update expiration timeout */ dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire); - rateinfo_recalc(dh, now, hinfo->cfg.mode); + rateinfo_recalc(dh, now, hinfo->cfg.mode, revision); } else { dh->expires = jiffies + msecs_to_jiffies(hinfo->cfg.expire); - rateinfo_init(dh, hinfo); + rateinfo_init(dh, hinfo, revision); } } else { /* update expiration timeout */ dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire); - rateinfo_recalc(dh, now, hinfo->cfg.mode); + rateinfo_recalc(dh, now, hinfo->cfg.mode, revision); } - if (info->cfg.mode & XT_HASHLIMIT_BYTES) + if (cfg->mode & XT_HASHLIMIT_BYTES) cost = hashlimit_byte_cost(skb->len, dh); else cost = dh->rateinfo.cost; @@ -648,70 +696,126 @@ hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) dh->rateinfo.credit -= cost; spin_unlock(&dh->lock); rcu_read_unlock_bh(); - return !(info->cfg.mode & XT_HASHLIMIT_INVERT); + return !(cfg->mode & XT_HASHLIMIT_INVERT); } spin_unlock(&dh->lock); rcu_read_unlock_bh(); /* default match is underlimit - so over the limit, we need to invert */ - return info->cfg.mode & XT_HASHLIMIT_INVERT; + return cfg->mode & XT_HASHLIMIT_INVERT; hotdrop: par->hotdrop = true; return false; } -static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par) +static bool +hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_hashlimit_mtinfo1 *info = par->matchinfo; + struct xt_hashlimit_htable *hinfo = info->hinfo; + struct hashlimit_cfg2 cfg = {}; + int ret; + + ret = cfg_copy(&cfg, (void *)&info->cfg, 1); + + if (ret) + return ret; + + return hashlimit_mt_common(skb, par, hinfo, &cfg, 1); +} + +static bool +hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_hashlimit_mtinfo2 *info = par->matchinfo; + struct xt_hashlimit_htable *hinfo = info->hinfo; + + return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 2); +} + +static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, + struct xt_hashlimit_htable **hinfo, + struct hashlimit_cfg2 *cfg, + const char *name, int revision) { struct net *net = par->net; - struct xt_hashlimit_mtinfo1 *info = par->matchinfo; int ret; - if (info->cfg.gc_interval == 0 || info->cfg.expire == 0) - return -EINVAL; - if (info->name[sizeof(info->name)-1] != '\0') + if (cfg->gc_interval == 0 || cfg->expire == 0) return -EINVAL; if (par->family == NFPROTO_IPV4) { - if (info->cfg.srcmask > 32 || info->cfg.dstmask > 32) + if (cfg->srcmask > 32 || cfg->dstmask > 32) return -EINVAL; } else { - if (info->cfg.srcmask > 128 || info->cfg.dstmask > 128) + if (cfg->srcmask > 128 || cfg->dstmask > 128) return -EINVAL; } - if (info->cfg.mode & ~XT_HASHLIMIT_ALL) { + if (cfg->mode & ~XT_HASHLIMIT_ALL) { pr_info("Unknown mode mask %X, kernel too old?\n", - info->cfg.mode); + cfg->mode); return -EINVAL; } /* Check for overflow. */ - if (info->cfg.mode & XT_HASHLIMIT_BYTES) { - if (user2credits_byte(info->cfg.avg) == 0) { - pr_info("overflow, rate too high: %u\n", info->cfg.avg); + if (cfg->mode & XT_HASHLIMIT_BYTES) { + if (user2credits_byte(cfg->avg) == 0) { + pr_info("overflow, rate too high: %llu\n", cfg->avg); return -EINVAL; } - } else if (info->cfg.burst == 0 || - user2credits(info->cfg.avg * info->cfg.burst) < - user2credits(info->cfg.avg)) { - pr_info("overflow, try lower: %u/%u\n", - info->cfg.avg, info->cfg.burst); + } else if (cfg->burst == 0 || + user2credits(cfg->avg * cfg->burst, revision) < + user2credits(cfg->avg, revision)) { + pr_info("overflow, try lower: %llu/%llu\n", + cfg->avg, cfg->burst); return -ERANGE; } mutex_lock(&hashlimit_mutex); - info->hinfo = htable_find_get(net, info->name, par->family); - if (info->hinfo == NULL) { - ret = htable_create_v1(net, info, par->family); + *hinfo = htable_find_get(net, name, par->family); + if (*hinfo == NULL) { + ret = htable_create(net, cfg, name, par->family, + hinfo, revision); if (ret < 0) { mutex_unlock(&hashlimit_mutex); return ret; } } mutex_unlock(&hashlimit_mutex); + return 0; } +static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par) +{ + struct xt_hashlimit_mtinfo1 *info = par->matchinfo; + struct hashlimit_cfg2 cfg = {}; + int ret; + + if (info->name[sizeof(info->name) - 1] != '\0') + return -EINVAL; + + ret = cfg_copy(&cfg, (void *)&info->cfg, 1); + + if (ret) + return ret; + + return hashlimit_mt_check_common(par, &info->hinfo, + &cfg, info->name, 1); +} + +static int hashlimit_mt_check(const struct xt_mtchk_param *par) +{ + struct xt_hashlimit_mtinfo2 *info = par->matchinfo; + + if (info->name[sizeof(info->name) - 1] != '\0') + return -EINVAL; + + return hashlimit_mt_check_common(par, &info->hinfo, &info->cfg, + info->name, 2); +} + static void hashlimit_mt_destroy_v1(const struct xt_mtdtor_param *par) { const struct xt_hashlimit_mtinfo1 *info = par->matchinfo; @@ -719,6 +823,13 @@ static void hashlimit_mt_destroy_v1(const struct xt_mtdtor_param *par) htable_put(info->hinfo); } +static void hashlimit_mt_destroy(const struct xt_mtdtor_param *par) +{ + const struct xt_hashlimit_mtinfo2 *info = par->matchinfo; + + htable_put(info->hinfo); +} + static struct xt_match hashlimit_mt_reg[] __read_mostly = { { .name = "hashlimit", @@ -730,6 +841,16 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { .destroy = hashlimit_mt_destroy_v1, .me = THIS_MODULE, }, + { + .name = "hashlimit", + .revision = 2, + .family = NFPROTO_IPV4, + .match = hashlimit_mt, + .matchsize = sizeof(struct xt_hashlimit_mtinfo2), + .checkentry = hashlimit_mt_check, + .destroy = hashlimit_mt_destroy, + .me = THIS_MODULE, + }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "hashlimit", @@ -741,6 +862,16 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { .destroy = hashlimit_mt_destroy_v1, .me = THIS_MODULE, }, + { + .name = "hashlimit", + .revision = 2, + .family = NFPROTO_IPV6, + .match = hashlimit_mt, + .matchsize = sizeof(struct xt_hashlimit_mtinfo2), + .checkentry = hashlimit_mt_check, + .destroy = hashlimit_mt_destroy, + .me = THIS_MODULE, + }, #endif }; @@ -787,18 +918,12 @@ static void dl_seq_stop(struct seq_file *s, void *v) spin_unlock_bh(&htable->lock); } -static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, - struct seq_file *s) +static void dl_seq_print(struct dsthash_ent *ent, u_int8_t family, + struct seq_file *s) { - const struct xt_hashlimit_htable *ht = s->private; - - spin_lock(&ent->lock); - /* recalculate to show accurate numbers */ - rateinfo_recalc(ent, jiffies, ht->cfg.mode); - switch (family) { case NFPROTO_IPV4: - seq_printf(s, "%ld %pI4:%u->%pI4:%u %u %u %u\n", + seq_printf(s, "%ld %pI4:%u->%pI4:%u %llu %llu %llu\n", (long)(ent->expires - jiffies)/HZ, &ent->dst.ip.src, ntohs(ent->dst.src_port), @@ -809,7 +934,7 @@ static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, break; #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) case NFPROTO_IPV6: - seq_printf(s, "%ld %pI6:%u->%pI6:%u %u %u %u\n", + seq_printf(s, "%ld %pI6:%u->%pI6:%u %llu %llu %llu\n", (long)(ent->expires - jiffies)/HZ, &ent->dst.ip6.src, ntohs(ent->dst.src_port), @@ -822,6 +947,34 @@ static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, default: BUG(); } +} + +static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, + struct seq_file *s) +{ + const struct xt_hashlimit_htable *ht = s->private; + + spin_lock(&ent->lock); + /* recalculate to show accurate numbers */ + rateinfo_recalc(ent, jiffies, ht->cfg.mode, 1); + + dl_seq_print(ent, family, s); + + spin_unlock(&ent->lock); + return seq_has_overflowed(s); +} + +static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, + struct seq_file *s) +{ + const struct xt_hashlimit_htable *ht = s->private; + + spin_lock(&ent->lock); + /* recalculate to show accurate numbers */ + rateinfo_recalc(ent, jiffies, ht->cfg.mode, 2); + + dl_seq_print(ent, family, s); + spin_unlock(&ent->lock); return seq_has_overflowed(s); } @@ -840,6 +993,20 @@ static int dl_seq_show_v1(struct seq_file *s, void *v) return 0; } +static int dl_seq_show(struct seq_file *s, void *v) +{ + struct xt_hashlimit_htable *htable = s->private; + unsigned int *bucket = (unsigned int *)v; + struct dsthash_ent *ent; + + if (!hlist_empty(&htable->hash[*bucket])) { + hlist_for_each_entry(ent, &htable->hash[*bucket], node) + if (dl_seq_real_show(ent, htable->family, s)) + return -1; + } + return 0; +} + static const struct seq_operations dl_seq_ops_v1 = { .start = dl_seq_start, .next = dl_seq_next, @@ -847,6 +1014,13 @@ static const struct seq_operations dl_seq_ops_v1 = { .show = dl_seq_show_v1 }; +static const struct seq_operations dl_seq_ops = { + .start = dl_seq_start, + .next = dl_seq_next, + .stop = dl_seq_stop, + .show = dl_seq_show +}; + static int dl_proc_open_v1(struct inode *inode, struct file *file) { int ret = seq_open(file, &dl_seq_ops_v1); @@ -858,6 +1032,18 @@ static int dl_proc_open_v1(struct inode *inode, struct file *file) return ret; } +static int dl_proc_open(struct inode *inode, struct file *file) +{ + int ret = seq_open(file, &dl_seq_ops); + + if (!ret) { + struct seq_file *sf = file->private_data; + + sf->private = PDE_DATA(inode); + } + return ret; +} + static const struct file_operations dl_file_ops_v1 = { .owner = THIS_MODULE, .open = dl_proc_open_v1, @@ -866,6 +1052,14 @@ static const struct file_operations dl_file_ops_v1 = { .release = seq_release }; +static const struct file_operations dl_file_ops = { + .owner = THIS_MODULE, + .open = dl_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release +}; + static int __net_init hashlimit_proc_net_init(struct net *net) { struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); -- cgit v1.2.3 From 0f3cd9b3697708c86a825ae3cedabf7be6fd3e72 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 23 Sep 2016 15:23:33 +0200 Subject: netfilter: nf_tables: add range expression Inverse ranges != [a,b] are not currently possible because rules are composites of && operations, and we need to express this: data < a || data > b This patch adds a new range expression. Positive ranges can be already through two cmp expressions: cmp(sreg, data, >=) cmp(sreg, data, <=) This new range expression provides an alternative way to express this. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables_core.h | 3 + include/uapi/linux/netfilter/nf_tables.h | 29 +++++++ net/netfilter/Makefile | 3 +- net/netfilter/nf_tables_core.c | 7 +- net/netfilter/nft_range.c | 138 +++++++++++++++++++++++++++++++ 5 files changed, 178 insertions(+), 2 deletions(-) create mode 100644 net/netfilter/nft_range.c (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index a9060dd99db7..00f4f6b1b1ba 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -28,6 +28,9 @@ extern const struct nft_expr_ops nft_cmp_fast_ops; int nft_cmp_module_init(void); void nft_cmp_module_exit(void); +int nft_range_module_init(void); +void nft_range_module_exit(void); + int nft_lookup_module_init(void); void nft_lookup_module_exit(void); diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 1cf41dd838b2..c6c4477c136b 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -546,6 +546,35 @@ enum nft_cmp_attributes { }; #define NFTA_CMP_MAX (__NFTA_CMP_MAX - 1) +/** + * enum nft_range_ops - nf_tables range operator + * + * @NFT_RANGE_EQ: equal + * @NFT_RANGE_NEQ: not equal + */ +enum nft_range_ops { + NFT_RANGE_EQ, + NFT_RANGE_NEQ, +}; + +/** + * enum nft_range_attributes - nf_tables range expression netlink attributes + * + * @NFTA_RANGE_SREG: source register of data to compare (NLA_U32: nft_registers) + * @NFTA_RANGE_OP: cmp operation (NLA_U32: nft_cmp_ops) + * @NFTA_RANGE_FROM_DATA: data range from (NLA_NESTED: nft_data_attributes) + * @NFTA_RANGE_TO_DATA: data range to (NLA_NESTED: nft_data_attributes) + */ +enum nft_range_attributes { + NFTA_RANGE_UNSPEC, + NFTA_RANGE_SREG, + NFTA_RANGE_OP, + NFTA_RANGE_FROM_DATA, + NFTA_RANGE_TO_DATA, + __NFTA_RANGE_MAX +}; +#define NFTA_RANGE_MAX (__NFTA_RANGE_MAX - 1) + enum nft_lookup_flags { NFT_LOOKUP_F_INV = (1 << 0), }; diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 0c8581100ac6..c23c3c84416f 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -71,8 +71,9 @@ obj-$(CONFIG_NF_DUP_NETDEV) += nf_dup_netdev.o # nf_tables nf_tables-objs += nf_tables_core.o nf_tables_api.o nf_tables_trace.o -nf_tables-objs += nft_immediate.o nft_cmp.o nft_lookup.o nft_dynset.o +nf_tables-objs += nft_immediate.o nft_cmp.o nft_range.o nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o +nf_tables-objs += nft_lookup.o nft_dynset.o obj-$(CONFIG_NF_TABLES) += nf_tables.o obj-$(CONFIG_NF_TABLES_INET) += nf_tables_inet.o diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 67259cefef06..7c94ce0080d5 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -263,8 +263,13 @@ int __init nf_tables_core_module_init(void) if (err < 0) goto err7; - return 0; + err = nft_range_module_init(); + if (err < 0) + goto err8; + return 0; +err8: + nft_dynset_module_exit(); err7: nft_payload_module_exit(); err6: diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c new file mode 100644 index 000000000000..c6d5358482d1 --- /dev/null +++ b/net/netfilter/nft_range.c @@ -0,0 +1,138 @@ +/* + * Copyright (c) 2016 Pablo Neira Ayuso + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +struct nft_range_expr { + struct nft_data data_from; + struct nft_data data_to; + enum nft_registers sreg:8; + u8 len; + enum nft_range_ops op:8; +}; + +static void nft_range_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_range_expr *priv = nft_expr_priv(expr); + bool mismatch; + int d1, d2; + + d1 = memcmp(®s->data[priv->sreg], &priv->data_from, priv->len); + d2 = memcmp(®s->data[priv->sreg], &priv->data_to, priv->len); + switch (priv->op) { + case NFT_RANGE_EQ: + mismatch = (d1 < 0 || d2 > 0); + break; + case NFT_RANGE_NEQ: + mismatch = (d1 >= 0 && d2 <= 0); + break; + } + + if (mismatch) + regs->verdict.code = NFT_BREAK; +} + +static const struct nla_policy nft_range_policy[NFTA_RANGE_MAX + 1] = { + [NFTA_RANGE_SREG] = { .type = NLA_U32 }, + [NFTA_RANGE_OP] = { .type = NLA_U32 }, + [NFTA_RANGE_FROM_DATA] = { .type = NLA_NESTED }, + [NFTA_RANGE_TO_DATA] = { .type = NLA_NESTED }, +}; + +static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_range_expr *priv = nft_expr_priv(expr); + struct nft_data_desc desc_from, desc_to; + int err; + + err = nft_data_init(NULL, &priv->data_from, sizeof(priv->data_from), + &desc_from, tb[NFTA_RANGE_FROM_DATA]); + if (err < 0) + return err; + + err = nft_data_init(NULL, &priv->data_to, sizeof(priv->data_to), + &desc_to, tb[NFTA_RANGE_TO_DATA]); + if (err < 0) + goto err1; + + if (desc_from.len != desc_to.len) { + err = -EINVAL; + goto err2; + } + + priv->sreg = nft_parse_register(tb[NFTA_RANGE_SREG]); + err = nft_validate_register_load(priv->sreg, desc_from.len); + if (err < 0) + goto err2; + + priv->op = ntohl(nla_get_be32(tb[NFTA_RANGE_OP])); + priv->len = desc_from.len; + return 0; +err2: + nft_data_uninit(&priv->data_to, desc_to.type); +err1: + nft_data_uninit(&priv->data_from, desc_from.type); + return err; +} + +static int nft_range_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_range_expr *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_RANGE_SREG, priv->sreg)) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_RANGE_OP, htonl(priv->op))) + goto nla_put_failure; + + if (nft_data_dump(skb, NFTA_RANGE_FROM_DATA, &priv->data_from, + NFT_DATA_VALUE, priv->len) < 0 || + nft_data_dump(skb, NFTA_RANGE_TO_DATA, &priv->data_to, + NFT_DATA_VALUE, priv->len) < 0) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static struct nft_expr_type nft_range_type; +static const struct nft_expr_ops nft_range_ops = { + .type = &nft_range_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_range_expr)), + .eval = nft_range_eval, + .init = nft_range_init, + .dump = nft_range_dump, +}; + +static struct nft_expr_type nft_range_type __read_mostly = { + .name = "range", + .ops = &nft_range_ops, + .policy = nft_range_policy, + .maxattr = NFTA_RANGE_MAX, + .owner = THIS_MODULE, +}; + +int __init nft_range_module_init(void) +{ + return nft_register_expr(&nft_range_type); +} + +void nft_range_module_exit(void) +{ + nft_unregister_expr(&nft_range_type); +} -- cgit v1.2.3 From ff107d27761ff4b644c82c209e004ec9c8fbbc22 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sun, 25 Sep 2016 16:35:56 +0800 Subject: netfilter: nft_log: complete NFTA_LOG_FLAGS attr support NFTA_LOG_FLAGS attribute is already supported, but the related NF_LOG_XXX flags are not exposed to the userspace. So we cannot explicitly enable log flags to log uid, tcp sequence, ip options and so on, i.e. such rule "nft add rule filter output log uid" is not supported yet. So move NF_LOG_XXX macro definitions to the uapi/../nf_log.h. In order to keep consistent with other modules, change NF_LOG_MASK to refer to all supported log flags. On the other hand, add a new NF_LOG_DEFAULT_MASK to refer to the original default log flags. Finally, if user specify the unsupported log flags or NFTA_LOG_GROUP and NFTA_LOG_FLAGS are set at the same time, report EINVAL to the userspace. Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_log.h | 11 +++-------- include/uapi/linux/netfilter/nf_log.h | 12 ++++++++++++ net/bridge/netfilter/ebt_log.c | 2 +- net/ipv4/netfilter/ip_tables.c | 2 +- net/ipv4/netfilter/nf_log_arp.c | 2 +- net/ipv4/netfilter/nf_log_ipv4.c | 4 ++-- net/ipv6/netfilter/ip6_tables.c | 2 +- net/ipv6/netfilter/nf_log_ipv6.c | 4 ++-- net/netfilter/nf_tables_core.c | 2 +- net/netfilter/nft_log.c | 9 ++++++++- 10 files changed, 32 insertions(+), 18 deletions(-) create mode 100644 include/uapi/linux/netfilter/nf_log.h (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h index ee07dc8b0a7b..309cd267be4f 100644 --- a/include/net/netfilter/nf_log.h +++ b/include/net/netfilter/nf_log.h @@ -2,15 +2,10 @@ #define _NF_LOG_H #include +#include -/* those NF_LOG_* defines and struct nf_loginfo are legacy definitios that will - * disappear once iptables is replaced with pkttables. Please DO NOT use them - * for any new code! */ -#define NF_LOG_TCPSEQ 0x01 /* Log TCP sequence numbers */ -#define NF_LOG_TCPOPT 0x02 /* Log TCP options */ -#define NF_LOG_IPOPT 0x04 /* Log IP options */ -#define NF_LOG_UID 0x08 /* Log UID owning local socket */ -#define NF_LOG_MASK 0x0f +/* Log tcp sequence, tcp options, ip options and uid owning local socket */ +#define NF_LOG_DEFAULT_MASK 0x0f /* This flag indicates that copy_len field in nf_loginfo is set */ #define NF_LOG_F_COPY_LEN 0x1 diff --git a/include/uapi/linux/netfilter/nf_log.h b/include/uapi/linux/netfilter/nf_log.h new file mode 100644 index 000000000000..8be21e02387d --- /dev/null +++ b/include/uapi/linux/netfilter/nf_log.h @@ -0,0 +1,12 @@ +#ifndef _NETFILTER_NF_LOG_H +#define _NETFILTER_NF_LOG_H + +#define NF_LOG_TCPSEQ 0x01 /* Log TCP sequence numbers */ +#define NF_LOG_TCPOPT 0x02 /* Log TCP options */ +#define NF_LOG_IPOPT 0x04 /* Log IP options */ +#define NF_LOG_UID 0x08 /* Log UID owning local socket */ +#define NF_LOG_NFLOG 0x10 /* Unsupported, don't reuse */ +#define NF_LOG_MACDECODE 0x20 /* Decode MAC header */ +#define NF_LOG_MASK 0x2f + +#endif /* _NETFILTER_NF_LOG_H */ diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c index 152300d164ac..9a11086ba6ff 100644 --- a/net/bridge/netfilter/ebt_log.c +++ b/net/bridge/netfilter/ebt_log.c @@ -91,7 +91,7 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, if (loginfo->type == NF_LOG_TYPE_LOG) bitmask = loginfo->u.log.logflags; else - bitmask = NF_LOG_MASK; + bitmask = NF_LOG_DEFAULT_MASK; if ((bitmask & EBT_LOG_IP) && eth_hdr(skb)->h_proto == htons(ETH_P_IP)) { diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index f993545a3373..7c00ce90adb8 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -156,7 +156,7 @@ static struct nf_loginfo trace_loginfo = { .u = { .log = { .level = 4, - .logflags = NF_LOG_MASK, + .logflags = NF_LOG_DEFAULT_MASK, }, }, }; diff --git a/net/ipv4/netfilter/nf_log_arp.c b/net/ipv4/netfilter/nf_log_arp.c index 8945c2653814..b24795e2ee6d 100644 --- a/net/ipv4/netfilter/nf_log_arp.c +++ b/net/ipv4/netfilter/nf_log_arp.c @@ -30,7 +30,7 @@ static struct nf_loginfo default_loginfo = { .u = { .log = { .level = LOGLEVEL_NOTICE, - .logflags = NF_LOG_MASK, + .logflags = NF_LOG_DEFAULT_MASK, }, }, }; diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c index 20f225593a8b..5b571e1b5f15 100644 --- a/net/ipv4/netfilter/nf_log_ipv4.c +++ b/net/ipv4/netfilter/nf_log_ipv4.c @@ -29,7 +29,7 @@ static struct nf_loginfo default_loginfo = { .u = { .log = { .level = LOGLEVEL_NOTICE, - .logflags = NF_LOG_MASK, + .logflags = NF_LOG_DEFAULT_MASK, }, }, }; @@ -46,7 +46,7 @@ static void dump_ipv4_packet(struct nf_log_buf *m, if (info->type == NF_LOG_TYPE_LOG) logflags = info->u.log.logflags; else - logflags = NF_LOG_MASK; + logflags = NF_LOG_DEFAULT_MASK; ih = skb_header_pointer(skb, iphoff, sizeof(_iph), &_iph); if (ih == NULL) { diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 552fac2f390a..55aacea24396 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -190,7 +190,7 @@ static struct nf_loginfo trace_loginfo = { .u = { .log = { .level = LOGLEVEL_WARNING, - .logflags = NF_LOG_MASK, + .logflags = NF_LOG_DEFAULT_MASK, }, }, }; diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c index c1bcf699a23d..f6aee2895fee 100644 --- a/net/ipv6/netfilter/nf_log_ipv6.c +++ b/net/ipv6/netfilter/nf_log_ipv6.c @@ -30,7 +30,7 @@ static struct nf_loginfo default_loginfo = { .u = { .log = { .level = LOGLEVEL_NOTICE, - .logflags = NF_LOG_MASK, + .logflags = NF_LOG_DEFAULT_MASK, }, }, }; @@ -52,7 +52,7 @@ static void dump_ipv6_packet(struct nf_log_buf *m, if (info->type == NF_LOG_TYPE_LOG) logflags = info->u.log.logflags; else - logflags = NF_LOG_MASK; + logflags = NF_LOG_DEFAULT_MASK; ih = skb_header_pointer(skb, ip6hoff, sizeof(_ip6h), &_ip6h); if (ih == NULL) { diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 7c94ce0080d5..0dd5c695482f 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -34,7 +34,7 @@ static struct nf_loginfo trace_loginfo = { .u = { .log = { .level = LOGLEVEL_WARNING, - .logflags = NF_LOG_MASK, + .logflags = NF_LOG_DEFAULT_MASK, }, }, }; diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index 24a73bb26e94..1b01404bb33f 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -58,8 +58,11 @@ static int nft_log_init(const struct nft_ctx *ctx, if (tb[NFTA_LOG_LEVEL] != NULL && tb[NFTA_LOG_GROUP] != NULL) return -EINVAL; - if (tb[NFTA_LOG_GROUP] != NULL) + if (tb[NFTA_LOG_GROUP] != NULL) { li->type = NF_LOG_TYPE_ULOG; + if (tb[NFTA_LOG_FLAGS] != NULL) + return -EINVAL; + } nla = tb[NFTA_LOG_PREFIX]; if (nla != NULL) { @@ -87,6 +90,10 @@ static int nft_log_init(const struct nft_ctx *ctx, if (tb[NFTA_LOG_FLAGS] != NULL) { li->u.log.logflags = ntohl(nla_get_be32(tb[NFTA_LOG_FLAGS])); + if (li->u.log.logflags & ~NF_LOG_MASK) { + err = -EINVAL; + goto err1; + } } break; case NF_LOG_TYPE_ULOG: -- cgit v1.2.3 From 8564e38206de2ff005a27c8d7c2ce3869a44f0dd Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 19 Sep 2016 09:44:44 +0200 Subject: cfg80211: add checks for beacon rate, extend to mesh The previous commit added support for specifying the beacon rate for AP mode. Add features checks to this, and extend it to also support the rate configuration for mesh networks. For IBSS it's not as simple due to joining etc., so that's not yet supported. Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 +++- include/uapi/linux/nl80211.h | 17 +++++++++++++++- net/wireless/nl80211.c | 46 +++++++++++++++++++++++++++++++++----------- 3 files changed, 54 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index e0949c8bc2d1..ed37304fa09d 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -712,7 +712,7 @@ struct cfg80211_bitrate_mask { * MAC address based access control * @pbss: If set, start as a PCP instead of AP. Relevant for DMG * networks. - * @beacon_rate: masks for setting user configured beacon tx rate. + * @beacon_rate: bitrate to be used for beacons */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; @@ -1365,6 +1365,7 @@ struct mesh_config { * @beacon_interval: beacon interval to use * @mcast_rate: multicat rate for Mesh Node [6Mbps is the default for 802.11a] * @basic_rates: basic rates to use when creating the mesh + * @beacon_rate: bitrate to be used for beacons * * These parameters are fixed when the mesh is created. */ @@ -1385,6 +1386,7 @@ struct mesh_setup { u16 beacon_interval; int mcast_rate[NUM_NL80211_BANDS]; u32 basic_rates; + struct cfg80211_bitrate_mask beacon_rate; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 220694151434..ec10d1b2838f 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1343,7 +1343,13 @@ enum nl80211_commands { * enum nl80211_band value is used as the index (nla_type() of the nested * data. If a band is not included, it will be configured to allow all * rates based on negotiated supported rates information. This attribute - * is used with %NL80211_CMD_SET_TX_BITRATE_MASK. + * is used with %NL80211_CMD_SET_TX_BITRATE_MASK and with starting AP, + * and joining mesh networks (not IBSS yet). In the later case, it must + * specify just a single bitrate, which is to be used for the beacon. + * The driver must also specify support for this with the extended + * features NL80211_EXT_FEATURE_BEACON_RATE_LEGACY, + * NL80211_EXT_FEATURE_BEACON_RATE_HT and + * NL80211_EXT_FEATURE_BEACON_RATE_VHT. * * @NL80211_ATTR_FRAME_MATCH: A binary attribute which typically must contain * at least one byte, currently used with @NL80211_CMD_REGISTER_FRAME. @@ -4551,6 +4557,12 @@ enum nl80211_feature_flags { * (if available). * @NL80211_EXT_FEATURE_SET_SCAN_DWELL: This driver supports configuration of * channel dwell time. + * @NL80211_EXT_FEATURE_BEACON_RATE_LEGACY: Driver supports beacon rate + * configuration (AP/mesh), supporting a legacy (non HT/VHT) rate. + * @NL80211_EXT_FEATURE_BEACON_RATE_HT: Driver supports beacon rate + * configuration (AP/mesh) with HT rates. + * @NL80211_EXT_FEATURE_BEACON_RATE_VHT: Driver supports beacon rate + * configuration (AP/mesh) with VHT rates. * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. @@ -4562,6 +4574,9 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_SCAN_START_TIME, NL80211_EXT_FEATURE_BSS_PARENT_TSF, NL80211_EXT_FEATURE_SET_SCAN_DWELL, + NL80211_EXT_FEATURE_BEACON_RATE_LEGACY, + NL80211_EXT_FEATURE_BEACON_RATE_HT, + NL80211_EXT_FEATURE_BEACON_RATE_VHT, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index a10484da60c0..b8441e60b0f6 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3569,13 +3569,12 @@ out: return 0; } -static int validate_beacon_tx_rate(struct cfg80211_ap_settings *params) +static int validate_beacon_tx_rate(struct cfg80211_registered_device *rdev, + enum nl80211_band band, + struct cfg80211_bitrate_mask *beacon_rate) { - u32 rate, count_ht, count_vht, i; - enum nl80211_band band; - - band = params->chandef.chan->band; - rate = params->beacon_rate.control[band].legacy; + u32 count_ht, count_vht, i; + u32 rate = beacon_rate->control[band].legacy; /* Allow only one rate */ if (hweight32(rate) > 1) @@ -3583,9 +3582,9 @@ static int validate_beacon_tx_rate(struct cfg80211_ap_settings *params) count_ht = 0; for (i = 0; i < IEEE80211_HT_MCS_MASK_LEN; i++) { - if (hweight8(params->beacon_rate.control[band].ht_mcs[i]) > 1) { + if (hweight8(beacon_rate->control[band].ht_mcs[i]) > 1) { return -EINVAL; - } else if (params->beacon_rate.control[band].ht_mcs[i]) { + } else if (beacon_rate->control[band].ht_mcs[i]) { count_ht++; if (count_ht > 1) return -EINVAL; @@ -3596,9 +3595,9 @@ static int validate_beacon_tx_rate(struct cfg80211_ap_settings *params) count_vht = 0; for (i = 0; i < NL80211_VHT_NSS_MAX; i++) { - if (hweight16(params->beacon_rate.control[band].vht_mcs[i]) > 1) { + if (hweight16(beacon_rate->control[band].vht_mcs[i]) > 1) { return -EINVAL; - } else if (params->beacon_rate.control[band].vht_mcs[i]) { + } else if (beacon_rate->control[band].vht_mcs[i]) { count_vht++; if (count_vht > 1) return -EINVAL; @@ -3610,6 +3609,19 @@ static int validate_beacon_tx_rate(struct cfg80211_ap_settings *params) if ((count_ht && count_vht) || (!rate && !count_ht && !count_vht)) return -EINVAL; + if (rate && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_BEACON_RATE_LEGACY)) + return -EINVAL; + if (count_ht && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_BEACON_RATE_HT)) + return -EINVAL; + if (count_vht && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_BEACON_RATE_VHT)) + return -EINVAL; + return 0; } @@ -3847,7 +3859,8 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) if (err) return err; - err = validate_beacon_tx_rate(¶ms); + err = validate_beacon_tx_rate(rdev, params.chandef.chan->band, + ¶ms.beacon_rate); if (err) return err; } @@ -9406,6 +9419,17 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) return err; } + if (info->attrs[NL80211_ATTR_TX_RATES]) { + err = nl80211_parse_tx_bitrate_mask(info, &setup.beacon_rate); + if (err) + return err; + + err = validate_beacon_tx_rate(rdev, setup.chandef.chan->band, + &setup.beacon_rate); + if (err) + return err; + } + return cfg80211_join_mesh(rdev, dev, &setup, &cfg); } -- cgit v1.2.3 From b4c8eb0379c8d3300a54210edd2235fd1e81a8a6 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Sep 2016 16:28:26 -0400 Subject: nfs: add a new NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK constant As defined in RFC 5661, section 18.16. Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- include/uapi/linux/nfs4.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h index 2b871e0858d9..4ae62796bfde 100644 --- a/include/uapi/linux/nfs4.h +++ b/include/uapi/linux/nfs4.h @@ -39,8 +39,9 @@ #define NFS4_FH_VOL_MIGRATION 0x0004 #define NFS4_FH_VOL_RENAME 0x0008 -#define NFS4_OPEN_RESULT_CONFIRM 0x0002 -#define NFS4_OPEN_RESULT_LOCKTYPE_POSIX 0x0004 +#define NFS4_OPEN_RESULT_CONFIRM 0x0002 +#define NFS4_OPEN_RESULT_LOCKTYPE_POSIX 0x0004 +#define NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK 0x0020 #define NFS4_SHARE_ACCESS_MASK 0x000F #define NFS4_SHARE_ACCESS_READ 0x0001 -- cgit v1.2.3 From 8e5470c9839caff94fe334e67ff7e7ace587282a Mon Sep 17 00:00:00 2001 From: Thor Thayer Date: Thu, 22 Sep 2016 14:56:16 -0500 Subject: serial: 8250: Set Altera 16550 TX FIFO Threshold The Altera 16550 soft IP UART requires 2 additional registers for TX FIFO threshold support. These 2 registers enable the TX FIFO Low Watermark and set the TX FIFO Low Watermark. Set the TX FIFO threshold to the FIFO size - tx_loadsz. Signed-off-by: Thor Thayer Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_port.c | 43 +++++++++++++++++++++++++++++++++++++ include/uapi/linux/serial_reg.h | 8 +++++++ 2 files changed, 51 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 28d29fac1973..1bfb6fdbaa20 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1870,6 +1870,30 @@ static int exar_handle_irq(struct uart_port *port) return ret; } +/* + * Newer 16550 compatible parts such as the SC16C650 & Altera 16550 Soft IP + * have a programmable TX threshold that triggers the THRE interrupt in + * the IIR register. In this case, the THRE interrupt indicates the FIFO + * has space available. Load it up with tx_loadsz bytes. + */ +static int serial8250_tx_threshold_handle_irq(struct uart_port *port) +{ + unsigned long flags; + unsigned int iir = serial_port_in(port, UART_IIR); + + /* TX Threshold IRQ triggered so load up FIFO */ + if ((iir & UART_IIR_ID) == UART_IIR_THRI) { + struct uart_8250_port *up = up_to_u8250p(port); + + spin_lock_irqsave(&port->lock, flags); + serial8250_tx_chars(up); + spin_unlock_irqrestore(&port->lock, flags); + } + + iir = serial_port_in(port, UART_IIR); + return serial8250_handle_irq(port, iir); +} + static unsigned int serial8250_tx_empty(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); @@ -2159,6 +2183,25 @@ int serial8250_do_startup(struct uart_port *port) serial_port_out(port, UART_LCR, 0); } + /* + * For the Altera 16550 variants, set TX threshold trigger level. + */ + if (((port->type == PORT_ALTR_16550_F32) || + (port->type == PORT_ALTR_16550_F64) || + (port->type == PORT_ALTR_16550_F128)) && (port->fifosize > 1)) { + /* Bounds checking of TX threshold (valid 0 to fifosize-2) */ + if ((up->tx_loadsz < 2) || (up->tx_loadsz > port->fifosize)) { + pr_err("ttyS%d TX FIFO Threshold errors, skipping\n", + serial_index(port)); + } else { + serial_port_out(port, UART_ALTR_AFR, + UART_ALTR_EN_TXFIFO_LW); + serial_port_out(port, UART_ALTR_TX_LOW, + port->fifosize - up->tx_loadsz); + port->handle_irq = serial8250_tx_threshold_handle_irq; + } + } + if (port->irq) { unsigned char iir1; /* diff --git a/include/uapi/linux/serial_reg.h b/include/uapi/linux/serial_reg.h index 1e5ac4e776da..b4c04842a8c0 100644 --- a/include/uapi/linux/serial_reg.h +++ b/include/uapi/linux/serial_reg.h @@ -376,5 +376,13 @@ #define UART_EXAR_TXTRG 0x0a /* Tx FIFO trigger level write-only */ #define UART_EXAR_RXTRG 0x0b /* Rx FIFO trigger level write-only */ +/* + * These are definitions for the Altera ALTR_16550_F32/F64/F128 + * Normalized from 0x100 to 0x40 because of shift by 2 (32 bit regs). + */ +#define UART_ALTR_AFR 0x40 /* Additional Features Register */ +#define UART_ALTR_EN_TXFIFO_LW 0x01 /* Enable the TX FIFO Low Watermark */ +#define UART_ALTR_TX_LOW 0x41 /* Tx FIFO Low Watermark */ + #endif /* _LINUX_SERIAL_REG_H */ -- cgit v1.2.3 From bc8bcf3b150a29cd8d3f17a1aeb19a804ea683fa Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Tue, 27 Sep 2016 13:03:23 +0200 Subject: posix_acl: uapi header split Export the base definitions and the xattr representation of POSIX ACLs to user space. Signed-off-by: Andreas Gruenbacher Signed-off-by: Al Viro --- include/linux/posix_acl.h | 22 +------------------- include/linux/posix_acl_xattr.h | 18 +---------------- include/uapi/linux/Kbuild | 2 ++ include/uapi/linux/posix_acl.h | 39 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/posix_acl_xattr.h | 38 +++++++++++++++++++++++++++++++++++ 5 files changed, 81 insertions(+), 38 deletions(-) create mode 100644 include/uapi/linux/posix_acl.h create mode 100644 include/uapi/linux/posix_acl_xattr.h (limited to 'include/uapi/linux') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index d5d3d741f028..5433eea8e97c 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -11,27 +11,7 @@ #include #include #include - -#define ACL_UNDEFINED_ID (-1) - -/* a_type field in acl_user_posix_entry_t */ -#define ACL_TYPE_ACCESS (0x8000) -#define ACL_TYPE_DEFAULT (0x4000) - -/* e_tag entry in struct posix_acl_entry */ -#define ACL_USER_OBJ (0x01) -#define ACL_USER (0x02) -#define ACL_GROUP_OBJ (0x04) -#define ACL_GROUP (0x08) -#define ACL_MASK (0x10) -#define ACL_OTHER (0x20) - -/* permissions in the e_perm field */ -#define ACL_READ (0x04) -#define ACL_WRITE (0x02) -#define ACL_EXECUTE (0x01) -//#define ACL_ADD (0x08) -//#define ACL_DELETE (0x10) +#include struct posix_acl_entry { short e_tag; diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h index d23d36842322..8b867e3bf3aa 100644 --- a/include/linux/posix_acl_xattr.h +++ b/include/linux/posix_acl_xattr.h @@ -10,25 +10,9 @@ #define _POSIX_ACL_XATTR_H #include +#include #include -/* Supported ACL a_version fields */ -#define POSIX_ACL_XATTR_VERSION 0x0002 - -/* An undefined entry e_id value */ -#define ACL_UNDEFINED_ID (-1) - -struct posix_acl_xattr_entry { - __le16 e_tag; - __le16 e_perm; - __le32 e_id; -}; - -struct posix_acl_xattr_header { - __le32 a_version; -}; - - static inline size_t posix_acl_xattr_size(int count) { diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 185f8ea2702f..e266739168ec 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -335,6 +335,8 @@ header-y += pkt_cls.h header-y += pkt_sched.h header-y += pmu.h header-y += poll.h +header-y += posix_acl.h +header-y += posix_acl_xattr.h header-y += posix_types.h header-y += ppdev.h header-y += ppp-comp.h diff --git a/include/uapi/linux/posix_acl.h b/include/uapi/linux/posix_acl.h new file mode 100644 index 000000000000..1037cb19aa17 --- /dev/null +++ b/include/uapi/linux/posix_acl.h @@ -0,0 +1,39 @@ +/* + * Copyright (C) 2002 Andreas Gruenbacher + * Copyright (C) 2016 Red Hat, Inc. + * + * This file is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This file is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + */ + +#ifndef __UAPI_POSIX_ACL_H +#define __UAPI_POSIX_ACL_H + +#define ACL_UNDEFINED_ID (-1) + +/* a_type field in acl_user_posix_entry_t */ +#define ACL_TYPE_ACCESS (0x8000) +#define ACL_TYPE_DEFAULT (0x4000) + +/* e_tag entry in struct posix_acl_entry */ +#define ACL_USER_OBJ (0x01) +#define ACL_USER (0x02) +#define ACL_GROUP_OBJ (0x04) +#define ACL_GROUP (0x08) +#define ACL_MASK (0x10) +#define ACL_OTHER (0x20) + +/* permissions in the e_perm field */ +#define ACL_READ (0x04) +#define ACL_WRITE (0x02) +#define ACL_EXECUTE (0x01) + +#endif /* __UAPI_POSIX_ACL_H */ diff --git a/include/uapi/linux/posix_acl_xattr.h b/include/uapi/linux/posix_acl_xattr.h new file mode 100644 index 000000000000..8b579844109b --- /dev/null +++ b/include/uapi/linux/posix_acl_xattr.h @@ -0,0 +1,38 @@ +/* + * Copyright (C) 2002 Andreas Gruenbacher + * Copyright (C) 2016 Red Hat, Inc. + * + * This file is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This file is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + */ + +#ifndef __UAPI_POSIX_ACL_XATTR_H +#define __UAPI_POSIX_ACL_XATTR_H + +#include + +/* Supported ACL a_version fields */ +#define POSIX_ACL_XATTR_VERSION 0x0002 + +/* An undefined entry e_id value */ +#define ACL_UNDEFINED_ID (-1) + +struct posix_acl_xattr_entry { + __le16 e_tag; + __le16 e_perm; + __le32 e_id; +}; + +struct posix_acl_xattr_header { + __le32 a_version; +}; + +#endif /* __UAPI_POSIX_ACL_XATTR_H */ -- cgit v1.2.3 From 7ff89ac608d9e856cae6fa651553fa0709bf9c50 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Thu, 18 Aug 2016 12:05:25 -0400 Subject: audit: add exclude filter extension to feature bitmap Add to the audit feature bitmap to indicate availability of the extension of the exclude filter to include PID, UID, AUID, GID, SUBJ_*. RFE: add additional fields for use in audit filter exclude rules https://github.com/linux-audit/audit-kernel/issues/5 Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/uapi/linux/audit.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index d820aa979620..76c5e7eb1189 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -327,9 +327,11 @@ enum { #define AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT 0x00000001 #define AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME 0x00000002 #define AUDIT_FEATURE_BITMAP_EXECUTABLE_PATH 0x00000004 +#define AUDIT_FEATURE_BITMAP_EXCLUDE_EXTEND 0x00000008 #define AUDIT_FEATURE_BITMAP_ALL (AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT | \ AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME | \ - AUDIT_FEATURE_BITMAP_EXECUTABLE_PATH) + AUDIT_FEATURE_BITMAP_EXECUTABLE_PATH | \ + AUDIT_FEATURE_BITMAP_EXCLUDE_EXTEND) /* deprecated: AUDIT_VERSION_* */ #define AUDIT_VERSION_LATEST AUDIT_FEATURE_BITMAP_ALL -- cgit v1.2.3 From 54f9c4d0778b3f9ab791b1b7eb1a5d2809f02f50 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Tue, 20 Sep 2016 09:01:38 +0200 Subject: ipmi: add an Aspeed BT IPMI BMC driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds a simple device driver to expose the iBT interface on Aspeed SOCs (AST2400 and AST2500) as a character device. Such SOCs are commonly used as BMCs (BaseBoard Management Controllers) and this driver implements the BMC side of the BT interface. The BT (Block Transfer) interface is used to perform in-band IPMI communication between a host and its BMC. Entire messages are buffered before sending a notification to the other end, host or BMC, that there is data to be read. Usually, the host emits requests and the BMC responses but the specification provides a mean for the BMC to send SMS Attention (BMC-to-Host attention or System Management Software attention) messages. For this purpose, the driver introduces a specific ioctl on the device: 'BT_BMC_IOCTL_SMS_ATN' that can be used by the system running on the BMC to signal the host of such an event. The device name defaults to '/dev/ipmi-bt-host' Signed-off-by: Alistair Popple Signed-off-by: Jeremy Kerr Signed-off-by: Joel Stanley [clg: - checkpatch fixes - added a devicetree binding documentation - replace 'bt_host' by 'bt_bmc' to reflect that the driver is the BMC side of the IPMI BT interface - renamed the device to 'ipmi-bt-host' - introduced a temporary buffer to copy_{to,from}_user - used platform_get_irq() - moved the driver under drivers/char/ipmi/ but kept it as a misc device - changed the compatible cell to "aspeed,ast2400-bt-bmc" ] Signed-off-by: Cédric Le Goater Acked-by: Arnd Bergmann [clg: - checkpatch --strict fixes - removed the use of devm_iounmap, devm_kfree in cleanup paths - introduced an atomic-t to limit opens to 1 - introduced a mutex to protect write/read operations] Acked-by: Rob Herring Signed-off-by: Cédric Le Goater Signed-off-by: Corey Minyard --- Documentation/devicetree/bindings/ipmi.txt | 25 - .../bindings/ipmi/aspeed,ast2400-bt-bmc.txt | 23 + .../devicetree/bindings/ipmi/ipmi-smic.txt | 25 + drivers/Makefile | 2 +- drivers/char/ipmi/Kconfig | 7 + drivers/char/ipmi/Makefile | 1 + drivers/char/ipmi/bt-bmc.c | 510 +++++++++++++++++++++ include/uapi/linux/Kbuild | 1 + include/uapi/linux/bt-bmc.h | 18 + 9 files changed, 586 insertions(+), 26 deletions(-) delete mode 100644 Documentation/devicetree/bindings/ipmi.txt create mode 100644 Documentation/devicetree/bindings/ipmi/aspeed,ast2400-bt-bmc.txt create mode 100644 Documentation/devicetree/bindings/ipmi/ipmi-smic.txt create mode 100644 drivers/char/ipmi/bt-bmc.c create mode 100644 include/uapi/linux/bt-bmc.h (limited to 'include/uapi/linux') diff --git a/Documentation/devicetree/bindings/ipmi.txt b/Documentation/devicetree/bindings/ipmi.txt deleted file mode 100644 index d5f1a877ed3e..000000000000 --- a/Documentation/devicetree/bindings/ipmi.txt +++ /dev/null @@ -1,25 +0,0 @@ -IPMI device - -Required properties: -- compatible: should be one of ipmi-kcs, ipmi-smic, or ipmi-bt -- device_type: should be ipmi -- reg: Address and length of the register set for the device - -Optional properties: -- interrupts: The interrupt for the device. Without this the interface - is polled. -- reg-size - The size of the register. Defaults to 1 -- reg-spacing - The number of bytes between register starts. Defaults to 1 -- reg-shift - The amount to shift the registers to the right to get the data - into bit zero. - -Example: - -smic@fff3a000 { - compatible = "ipmi-smic"; - device_type = "ipmi"; - reg = <0xfff3a000 0x1000>; - interrupts = <0 24 4>; - reg-size = <4>; - reg-spacing = <4>; -}; diff --git a/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-bt-bmc.txt b/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-bt-bmc.txt new file mode 100644 index 000000000000..fbbacd958240 --- /dev/null +++ b/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-bt-bmc.txt @@ -0,0 +1,23 @@ +* Aspeed BT (Block Transfer) IPMI interface + +The Aspeed SOCs (AST2400 and AST2500) are commonly used as BMCs +(BaseBoard Management Controllers) and the BT interface can be used to +perform in-band IPMI communication with their host. + +Required properties: + +- compatible : should be "aspeed,ast2400-bt-bmc" +- reg: physical address and size of the registers + +Optional properties: + +- interrupts: interrupt generated by the BT interface. without an + interrupt, the driver will operate in poll mode. + +Example: + + ibt@1e789140 { + compatible = "aspeed,ast2400-bt-bmc"; + reg = <0x1e789140 0x18>; + interrupts = <8>; + }; diff --git a/Documentation/devicetree/bindings/ipmi/ipmi-smic.txt b/Documentation/devicetree/bindings/ipmi/ipmi-smic.txt new file mode 100644 index 000000000000..d5f1a877ed3e --- /dev/null +++ b/Documentation/devicetree/bindings/ipmi/ipmi-smic.txt @@ -0,0 +1,25 @@ +IPMI device + +Required properties: +- compatible: should be one of ipmi-kcs, ipmi-smic, or ipmi-bt +- device_type: should be ipmi +- reg: Address and length of the register set for the device + +Optional properties: +- interrupts: The interrupt for the device. Without this the interface + is polled. +- reg-size - The size of the register. Defaults to 1 +- reg-spacing - The number of bytes between register starts. Defaults to 1 +- reg-shift - The amount to shift the registers to the right to get the data + into bit zero. + +Example: + +smic@fff3a000 { + compatible = "ipmi-smic"; + device_type = "ipmi"; + reg = <0xfff3a000 0x1000>; + interrupts = <0 24 4>; + reg-size = <4>; + reg-spacing = <4>; +}; diff --git a/drivers/Makefile b/drivers/Makefile index 53abb4a5f736..5a9e7b6b7928 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -21,7 +21,7 @@ obj-y += video/ obj-y += idle/ # IPMI must come before ACPI in order to provide IPMI opregion support -obj-$(CONFIG_IPMI_HANDLER) += char/ipmi/ +obj-y += char/ipmi/ obj-$(CONFIG_ACPI) += acpi/ obj-$(CONFIG_SFI) += sfi/ diff --git a/drivers/char/ipmi/Kconfig b/drivers/char/ipmi/Kconfig index 5a9350b1069a..2c234e3e7513 100644 --- a/drivers/char/ipmi/Kconfig +++ b/drivers/char/ipmi/Kconfig @@ -76,3 +76,10 @@ config IPMI_POWEROFF the IPMI management controller is capable of this. endif # IPMI_HANDLER + +config ASPEED_BT_IPMI_BMC + tristate "BT IPMI bmc driver" + help + Provides a driver for the BT (Block Transfer) IPMI interface + found on Aspeed SOCs (AST2400 and AST2500). The driver + implements the BMC side of the BT interface. diff --git a/drivers/char/ipmi/Makefile b/drivers/char/ipmi/Makefile index f3ffde1f5f1f..0d98cd91def1 100644 --- a/drivers/char/ipmi/Makefile +++ b/drivers/char/ipmi/Makefile @@ -11,3 +11,4 @@ obj-$(CONFIG_IPMI_SSIF) += ipmi_ssif.o obj-$(CONFIG_IPMI_POWERNV) += ipmi_powernv.o obj-$(CONFIG_IPMI_WATCHDOG) += ipmi_watchdog.o obj-$(CONFIG_IPMI_POWEROFF) += ipmi_poweroff.o +obj-$(CONFIG_ASPEED_BT_IPMI_BMC) += bt-bmc.o diff --git a/drivers/char/ipmi/bt-bmc.c b/drivers/char/ipmi/bt-bmc.c new file mode 100644 index 000000000000..2e880bf0be26 --- /dev/null +++ b/drivers/char/ipmi/bt-bmc.c @@ -0,0 +1,510 @@ +/* + * Copyright (c) 2015-2016, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * This is a BMC device used to communicate to the host + */ +#define DEVICE_NAME "ipmi-bt-host" + +#define BT_IO_BASE 0xe4 +#define BT_IRQ 10 + +#define BT_CR0 0x0 +#define BT_CR0_IO_BASE 16 +#define BT_CR0_IRQ 12 +#define BT_CR0_EN_CLR_SLV_RDP 0x8 +#define BT_CR0_EN_CLR_SLV_WRP 0x4 +#define BT_CR0_ENABLE_IBT 0x1 +#define BT_CR1 0x4 +#define BT_CR1_IRQ_H2B 0x01 +#define BT_CR1_IRQ_HBUSY 0x40 +#define BT_CR2 0x8 +#define BT_CR2_IRQ_H2B 0x01 +#define BT_CR2_IRQ_HBUSY 0x40 +#define BT_CR3 0xc +#define BT_CTRL 0x10 +#define BT_CTRL_B_BUSY 0x80 +#define BT_CTRL_H_BUSY 0x40 +#define BT_CTRL_OEM0 0x20 +#define BT_CTRL_SMS_ATN 0x10 +#define BT_CTRL_B2H_ATN 0x08 +#define BT_CTRL_H2B_ATN 0x04 +#define BT_CTRL_CLR_RD_PTR 0x02 +#define BT_CTRL_CLR_WR_PTR 0x01 +#define BT_BMC2HOST 0x14 +#define BT_INTMASK 0x18 +#define BT_INTMASK_B2H_IRQEN 0x01 +#define BT_INTMASK_B2H_IRQ 0x02 +#define BT_INTMASK_BMC_HWRST 0x80 + +#define BT_BMC_BUFFER_SIZE 256 + +struct bt_bmc { + struct device dev; + struct miscdevice miscdev; + void __iomem *base; + int irq; + wait_queue_head_t queue; + struct timer_list poll_timer; + struct mutex mutex; +}; + +static atomic_t open_count = ATOMIC_INIT(0); + +static u8 bt_inb(struct bt_bmc *bt_bmc, int reg) +{ + return ioread8(bt_bmc->base + reg); +} + +static void bt_outb(struct bt_bmc *bt_bmc, u8 data, int reg) +{ + iowrite8(data, bt_bmc->base + reg); +} + +static void clr_rd_ptr(struct bt_bmc *bt_bmc) +{ + bt_outb(bt_bmc, BT_CTRL_CLR_RD_PTR, BT_CTRL); +} + +static void clr_wr_ptr(struct bt_bmc *bt_bmc) +{ + bt_outb(bt_bmc, BT_CTRL_CLR_WR_PTR, BT_CTRL); +} + +static void clr_h2b_atn(struct bt_bmc *bt_bmc) +{ + bt_outb(bt_bmc, BT_CTRL_H2B_ATN, BT_CTRL); +} + +static void set_b_busy(struct bt_bmc *bt_bmc) +{ + if (!(bt_inb(bt_bmc, BT_CTRL) & BT_CTRL_B_BUSY)) + bt_outb(bt_bmc, BT_CTRL_B_BUSY, BT_CTRL); +} + +static void clr_b_busy(struct bt_bmc *bt_bmc) +{ + if (bt_inb(bt_bmc, BT_CTRL) & BT_CTRL_B_BUSY) + bt_outb(bt_bmc, BT_CTRL_B_BUSY, BT_CTRL); +} + +static void set_b2h_atn(struct bt_bmc *bt_bmc) +{ + bt_outb(bt_bmc, BT_CTRL_B2H_ATN, BT_CTRL); +} + +static u8 bt_read(struct bt_bmc *bt_bmc) +{ + return bt_inb(bt_bmc, BT_BMC2HOST); +} + +static ssize_t bt_readn(struct bt_bmc *bt_bmc, u8 *buf, size_t n) +{ + int i; + + for (i = 0; i < n; i++) + buf[i] = bt_read(bt_bmc); + return n; +} + +static void bt_write(struct bt_bmc *bt_bmc, u8 c) +{ + bt_outb(bt_bmc, c, BT_BMC2HOST); +} + +static ssize_t bt_writen(struct bt_bmc *bt_bmc, u8 *buf, size_t n) +{ + int i; + + for (i = 0; i < n; i++) + bt_write(bt_bmc, buf[i]); + return n; +} + +static void set_sms_atn(struct bt_bmc *bt_bmc) +{ + bt_outb(bt_bmc, BT_CTRL_SMS_ATN, BT_CTRL); +} + +static struct bt_bmc *file_bt_bmc(struct file *file) +{ + return container_of(file->private_data, struct bt_bmc, miscdev); +} + +static int bt_bmc_open(struct inode *inode, struct file *file) +{ + struct bt_bmc *bt_bmc = file_bt_bmc(file); + + if (atomic_inc_return(&open_count) == 1) { + clr_b_busy(bt_bmc); + return 0; + } + + atomic_dec(&open_count); + return -EBUSY; +} + +/* + * The BT (Block Transfer) interface means that entire messages are + * buffered by the host before a notification is sent to the BMC that + * there is data to be read. The first byte is the length and the + * message data follows. The read operation just tries to capture the + * whole before returning it to userspace. + * + * BT Message format : + * + * Byte 1 Byte 2 Byte 3 Byte 4 Byte 5:N + * Length NetFn/LUN Seq Cmd Data + * + */ +static ssize_t bt_bmc_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct bt_bmc *bt_bmc = file_bt_bmc(file); + u8 len; + int len_byte = 1; + u8 kbuffer[BT_BMC_BUFFER_SIZE]; + ssize_t ret = 0; + ssize_t nread; + + if (!access_ok(VERIFY_WRITE, buf, count)) + return -EFAULT; + + WARN_ON(*ppos); + + if (wait_event_interruptible(bt_bmc->queue, + bt_inb(bt_bmc, BT_CTRL) & BT_CTRL_H2B_ATN)) + return -ERESTARTSYS; + + mutex_lock(&bt_bmc->mutex); + + if (unlikely(!(bt_inb(bt_bmc, BT_CTRL) & BT_CTRL_H2B_ATN))) { + ret = -EIO; + goto out_unlock; + } + + set_b_busy(bt_bmc); + clr_h2b_atn(bt_bmc); + clr_rd_ptr(bt_bmc); + + /* + * The BT frames start with the message length, which does not + * include the length byte. + */ + kbuffer[0] = bt_read(bt_bmc); + len = kbuffer[0]; + + /* We pass the length back to userspace as well */ + if (len + 1 > count) + len = count - 1; + + while (len) { + nread = min_t(ssize_t, len, sizeof(kbuffer) - len_byte); + + bt_readn(bt_bmc, kbuffer + len_byte, nread); + + if (copy_to_user(buf, kbuffer, nread + len_byte)) { + ret = -EFAULT; + break; + } + len -= nread; + buf += nread + len_byte; + ret += nread + len_byte; + len_byte = 0; + } + + clr_b_busy(bt_bmc); + +out_unlock: + mutex_unlock(&bt_bmc->mutex); + return ret; +} + +/* + * BT Message response format : + * + * Byte 1 Byte 2 Byte 3 Byte 4 Byte 5 Byte 6:N + * Length NetFn/LUN Seq Cmd Code Data + */ +static ssize_t bt_bmc_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct bt_bmc *bt_bmc = file_bt_bmc(file); + u8 kbuffer[BT_BMC_BUFFER_SIZE]; + ssize_t ret = 0; + ssize_t nwritten; + + /* + * send a minimum response size + */ + if (count < 5) + return -EINVAL; + + if (!access_ok(VERIFY_READ, buf, count)) + return -EFAULT; + + WARN_ON(*ppos); + + /* + * There's no interrupt for clearing bmc busy so we have to + * poll + */ + if (wait_event_interruptible(bt_bmc->queue, + !(bt_inb(bt_bmc, BT_CTRL) & + (BT_CTRL_H_BUSY | BT_CTRL_B2H_ATN)))) + return -ERESTARTSYS; + + mutex_lock(&bt_bmc->mutex); + + if (unlikely(bt_inb(bt_bmc, BT_CTRL) & + (BT_CTRL_H_BUSY | BT_CTRL_B2H_ATN))) { + ret = -EIO; + goto out_unlock; + } + + clr_wr_ptr(bt_bmc); + + while (count) { + nwritten = min_t(ssize_t, count, sizeof(kbuffer)); + if (copy_from_user(&kbuffer, buf, nwritten)) { + ret = -EFAULT; + break; + } + + bt_writen(bt_bmc, kbuffer, nwritten); + + count -= nwritten; + buf += nwritten; + ret += nwritten; + } + + set_b2h_atn(bt_bmc); + +out_unlock: + mutex_unlock(&bt_bmc->mutex); + return ret; +} + +static long bt_bmc_ioctl(struct file *file, unsigned int cmd, + unsigned long param) +{ + struct bt_bmc *bt_bmc = file_bt_bmc(file); + + switch (cmd) { + case BT_BMC_IOCTL_SMS_ATN: + set_sms_atn(bt_bmc); + return 0; + } + return -EINVAL; +} + +static int bt_bmc_release(struct inode *inode, struct file *file) +{ + struct bt_bmc *bt_bmc = file_bt_bmc(file); + + atomic_dec(&open_count); + set_b_busy(bt_bmc); + return 0; +} + +static unsigned int bt_bmc_poll(struct file *file, poll_table *wait) +{ + struct bt_bmc *bt_bmc = file_bt_bmc(file); + unsigned int mask = 0; + u8 ctrl; + + poll_wait(file, &bt_bmc->queue, wait); + + ctrl = bt_inb(bt_bmc, BT_CTRL); + + if (ctrl & BT_CTRL_H2B_ATN) + mask |= POLLIN; + + if (!(ctrl & (BT_CTRL_H_BUSY | BT_CTRL_B2H_ATN))) + mask |= POLLOUT; + + return mask; +} + +static const struct file_operations bt_bmc_fops = { + .owner = THIS_MODULE, + .open = bt_bmc_open, + .read = bt_bmc_read, + .write = bt_bmc_write, + .release = bt_bmc_release, + .poll = bt_bmc_poll, + .unlocked_ioctl = bt_bmc_ioctl, +}; + +static void poll_timer(unsigned long data) +{ + struct bt_bmc *bt_bmc = (void *)data; + + bt_bmc->poll_timer.expires += msecs_to_jiffies(500); + wake_up(&bt_bmc->queue); + add_timer(&bt_bmc->poll_timer); +} + +static irqreturn_t bt_bmc_irq(int irq, void *arg) +{ + struct bt_bmc *bt_bmc = arg; + u32 reg; + + reg = ioread32(bt_bmc->base + BT_CR2); + reg &= BT_CR2_IRQ_H2B | BT_CR2_IRQ_HBUSY; + if (!reg) + return IRQ_NONE; + + /* ack pending IRQs */ + iowrite32(reg, bt_bmc->base + BT_CR2); + + wake_up(&bt_bmc->queue); + return IRQ_HANDLED; +} + +static int bt_bmc_config_irq(struct bt_bmc *bt_bmc, + struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + u32 reg; + int rc; + + bt_bmc->irq = platform_get_irq(pdev, 0); + if (!bt_bmc->irq) + return -ENODEV; + + rc = devm_request_irq(dev, bt_bmc->irq, bt_bmc_irq, IRQF_SHARED, + DEVICE_NAME, bt_bmc); + if (rc < 0) { + dev_warn(dev, "Unable to request IRQ %d\n", bt_bmc->irq); + bt_bmc->irq = 0; + return rc; + } + + /* + * Configure IRQs on the bmc clearing the H2B and HBUSY bits; + * H2B will be asserted when the bmc has data for us; HBUSY + * will be cleared (along with B2H) when we can write the next + * message to the BT buffer + */ + reg = ioread32(bt_bmc->base + BT_CR1); + reg |= BT_CR1_IRQ_H2B | BT_CR1_IRQ_HBUSY; + iowrite32(reg, bt_bmc->base + BT_CR1); + + return 0; +} + +static int bt_bmc_probe(struct platform_device *pdev) +{ + struct bt_bmc *bt_bmc; + struct device *dev; + struct resource *res; + int rc; + + if (!pdev || !pdev->dev.of_node) + return -ENODEV; + + dev = &pdev->dev; + dev_info(dev, "Found bt bmc device\n"); + + bt_bmc = devm_kzalloc(dev, sizeof(*bt_bmc), GFP_KERNEL); + if (!bt_bmc) + return -ENOMEM; + + dev_set_drvdata(&pdev->dev, bt_bmc); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + dev_err(dev, "Unable to find resources\n"); + return -ENXIO; + } + + bt_bmc->base = devm_ioremap_resource(&pdev->dev, res); + if (!bt_bmc->base) + return -ENOMEM; + + mutex_init(&bt_bmc->mutex); + init_waitqueue_head(&bt_bmc->queue); + + bt_bmc->miscdev.minor = MISC_DYNAMIC_MINOR, + bt_bmc->miscdev.name = DEVICE_NAME, + bt_bmc->miscdev.fops = &bt_bmc_fops, + bt_bmc->miscdev.parent = dev; + rc = misc_register(&bt_bmc->miscdev); + if (rc) { + dev_err(dev, "Unable to register misc device\n"); + return rc; + } + + bt_bmc_config_irq(bt_bmc, pdev); + + if (bt_bmc->irq) { + dev_info(dev, "Using IRQ %d\n", bt_bmc->irq); + } else { + dev_info(dev, "No IRQ; using timer\n"); + setup_timer(&bt_bmc->poll_timer, poll_timer, + (unsigned long)bt_bmc); + bt_bmc->poll_timer.expires = jiffies + msecs_to_jiffies(10); + add_timer(&bt_bmc->poll_timer); + } + + iowrite32((BT_IO_BASE << BT_CR0_IO_BASE) | + (BT_IRQ << BT_CR0_IRQ) | + BT_CR0_EN_CLR_SLV_RDP | + BT_CR0_EN_CLR_SLV_WRP | + BT_CR0_ENABLE_IBT, + bt_bmc->base + BT_CR0); + + clr_b_busy(bt_bmc); + + return 0; +} + +static int bt_bmc_remove(struct platform_device *pdev) +{ + struct bt_bmc *bt_bmc = dev_get_drvdata(&pdev->dev); + + misc_deregister(&bt_bmc->miscdev); + if (!bt_bmc->irq) + del_timer_sync(&bt_bmc->poll_timer); + return 0; +} + +static const struct of_device_id bt_bmc_match[] = { + { .compatible = "aspeed,ast2400-bt-bmc" }, + { }, +}; + +static struct platform_driver bt_bmc_driver = { + .driver = { + .name = DEVICE_NAME, + .of_match_table = bt_bmc_match, + }, + .probe = bt_bmc_probe, + .remove = bt_bmc_remove, +}; + +module_platform_driver(bt_bmc_driver); + +MODULE_DEVICE_TABLE(of, bt_bmc_match); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Alistair Popple "); +MODULE_DESCRIPTION("Linux device interface to the BT interface"); diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 185f8ea2702f..17b12942c67d 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -74,6 +74,7 @@ header-y += bpf_common.h header-y += bpf.h header-y += bpqether.h header-y += bsg.h +header-y += bt-bmc.h header-y += btrfs.h header-y += can.h header-y += capability.h diff --git a/include/uapi/linux/bt-bmc.h b/include/uapi/linux/bt-bmc.h new file mode 100644 index 000000000000..d9ec766a63d0 --- /dev/null +++ b/include/uapi/linux/bt-bmc.h @@ -0,0 +1,18 @@ +/* + * Copyright (c) 2015-2016, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _UAPI_LINUX_BT_BMC_H +#define _UAPI_LINUX_BT_BMC_H + +#include + +#define __BT_BMC_IOCTL_MAGIC 0xb1 +#define BT_BMC_IOCTL_SMS_ATN _IO(__BT_BMC_IOCTL_MAGIC, 0x00) + +#endif /* _UAPI_LINUX_BT_BMC_H */ -- cgit v1.2.3 From bd11f0741fa5a2c296629898ad07759dd12b35bb Mon Sep 17 00:00:00 2001 From: Maciej Żenczykowski Date: Tue, 27 Sep 2016 23:57:58 -0700 Subject: ipv6 addrconf: implement RFC7559 router solicitation backoff MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This implements: https://tools.ietf.org/html/rfc7559 Backoff is performed according to RFC3315 section 14: https://tools.ietf.org/html/rfc3315#section-14 We allow setting /proc/sys/net/ipv6/conf/*/router_solicitations to a negative value meaning an unlimited number of retransmits, and we make this the new default (inline with the RFC). We also add a new setting: /proc/sys/net/ipv6/conf/*/router_solicitation_max_interval defaulting to 1 hour (per RFC recommendation). Signed-off-by: Maciej Żenczykowski Acked-by: Erik Kline Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + include/net/addrconf.h | 3 ++- include/net/if_inet6.h | 1 + include/uapi/linux/ipv6.h | 1 + net/ipv6/addrconf.c | 51 ++++++++++++++++++++++++++++++++++++++++------- 5 files changed, 49 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index c6dbcd84a2c7..7e9a789be5e0 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -18,6 +18,7 @@ struct ipv6_devconf { __s32 dad_transmits; __s32 rtr_solicits; __s32 rtr_solicit_interval; + __s32 rtr_solicit_max_interval; __s32 rtr_solicit_delay; __s32 force_mld_version; __s32 mldv1_unsolicited_report_interval; diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 9826d3a9464c..f2d072787947 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -1,8 +1,9 @@ #ifndef _ADDRCONF_H #define _ADDRCONF_H -#define MAX_RTR_SOLICITATIONS 3 +#define MAX_RTR_SOLICITATIONS -1 /* unlimited */ #define RTR_SOLICITATION_INTERVAL (4*HZ) +#define RTR_SOLICITATION_MAX_INTERVAL (3600*HZ) /* 1 hour */ #define MIN_VALID_LIFETIME (2*3600) /* 2 hours */ diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 1c8b6820b694..515352c6280a 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -201,6 +201,7 @@ struct inet6_dev { struct ipv6_devstat stats; struct timer_list rs_timer; + __s32 rs_interval; /* in jiffies */ __u8 rs_probes; __u8 addr_gen_mode; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 395876060f50..8c2772340c3f 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -177,6 +177,7 @@ enum { DEVCONF_DROP_UNICAST_IN_L2_MULTICAST, DEVCONF_DROP_UNSOLICITED_NA, DEVCONF_KEEP_ADDR_ON_DOWN, + DEVCONF_RTR_SOLICIT_MAX_INTERVAL, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 35d4baa55c9d..87183983724d 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -112,6 +112,27 @@ static inline u32 cstamp_delta(unsigned long cstamp) return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; } +static inline s32 rfc3315_s14_backoff_init(s32 irt) +{ + /* multiply 'initial retransmission time' by 0.9 .. 1.1 */ + u64 tmp = (900000 + prandom_u32() % 200001) * (u64)irt; + do_div(tmp, 1000000); + return (s32)tmp; +} + +static inline s32 rfc3315_s14_backoff_update(s32 rt, s32 mrt) +{ + /* multiply 'retransmission timeout' by 1.9 .. 2.1 */ + u64 tmp = (1900000 + prandom_u32() % 200001) * (u64)rt; + do_div(tmp, 1000000); + if ((s32)tmp > mrt) { + /* multiply 'maximum retransmission time' by 0.9 .. 1.1 */ + tmp = (900000 + prandom_u32() % 200001) * (u64)mrt; + do_div(tmp, 1000000); + } + return (s32)tmp; +} + #ifdef CONFIG_SYSCTL static int addrconf_sysctl_register(struct inet6_dev *idev); static void addrconf_sysctl_unregister(struct inet6_dev *idev); @@ -187,6 +208,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .dad_transmits = 1, .rtr_solicits = MAX_RTR_SOLICITATIONS, .rtr_solicit_interval = RTR_SOLICITATION_INTERVAL, + .rtr_solicit_max_interval = RTR_SOLICITATION_MAX_INTERVAL, .rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY, .use_tempaddr = 0, .temp_valid_lft = TEMP_VALID_LIFETIME, @@ -232,6 +254,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .dad_transmits = 1, .rtr_solicits = MAX_RTR_SOLICITATIONS, .rtr_solicit_interval = RTR_SOLICITATION_INTERVAL, + .rtr_solicit_max_interval = RTR_SOLICITATION_MAX_INTERVAL, .rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY, .use_tempaddr = 0, .temp_valid_lft = TEMP_VALID_LIFETIME, @@ -3687,7 +3710,7 @@ static void addrconf_rs_timer(unsigned long data) if (idev->if_flags & IF_RA_RCVD) goto out; - if (idev->rs_probes++ < idev->cnf.rtr_solicits) { + if (idev->rs_probes++ < idev->cnf.rtr_solicits || idev->cnf.rtr_solicits < 0) { write_unlock(&idev->lock); if (!ipv6_get_lladdr(dev, &lladdr, IFA_F_TENTATIVE)) ndisc_send_rs(dev, &lladdr, @@ -3696,11 +3719,13 @@ static void addrconf_rs_timer(unsigned long data) goto put; write_lock(&idev->lock); + idev->rs_interval = rfc3315_s14_backoff_update( + idev->rs_interval, idev->cnf.rtr_solicit_max_interval); /* The wait after the last probe can be shorter */ addrconf_mod_rs_timer(idev, (idev->rs_probes == idev->cnf.rtr_solicits) ? idev->cnf.rtr_solicit_delay : - idev->cnf.rtr_solicit_interval); + idev->rs_interval); } else { /* * Note: we do not support deprecated "all on-link" @@ -3949,7 +3974,7 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp) send_mld = ifp->scope == IFA_LINK && ipv6_lonely_lladdr(ifp); send_rs = send_mld && ipv6_accept_ra(ifp->idev) && - ifp->idev->cnf.rtr_solicits > 0 && + ifp->idev->cnf.rtr_solicits != 0 && (dev->flags&IFF_LOOPBACK) == 0; read_unlock_bh(&ifp->idev->lock); @@ -3971,10 +3996,11 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp) write_lock_bh(&ifp->idev->lock); spin_lock(&ifp->lock); + ifp->idev->rs_interval = rfc3315_s14_backoff_init( + ifp->idev->cnf.rtr_solicit_interval); ifp->idev->rs_probes = 1; ifp->idev->if_flags |= IF_RS_SENT; - addrconf_mod_rs_timer(ifp->idev, - ifp->idev->cnf.rtr_solicit_interval); + addrconf_mod_rs_timer(ifp->idev, ifp->idev->rs_interval); spin_unlock(&ifp->lock); write_unlock_bh(&ifp->idev->lock); } @@ -4891,6 +4917,8 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_RTR_SOLICITS] = cnf->rtr_solicits; array[DEVCONF_RTR_SOLICIT_INTERVAL] = jiffies_to_msecs(cnf->rtr_solicit_interval); + array[DEVCONF_RTR_SOLICIT_MAX_INTERVAL] = + jiffies_to_msecs(cnf->rtr_solicit_max_interval); array[DEVCONF_RTR_SOLICIT_DELAY] = jiffies_to_msecs(cnf->rtr_solicit_delay); array[DEVCONF_FORCE_MLD_VERSION] = cnf->force_mld_version; @@ -5099,7 +5127,7 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token) return -EINVAL; if (!ipv6_accept_ra(idev)) return -EINVAL; - if (idev->cnf.rtr_solicits <= 0) + if (idev->cnf.rtr_solicits == 0) return -EINVAL; write_lock_bh(&idev->lock); @@ -5128,8 +5156,10 @@ update_lft: if (update_rs) { idev->if_flags |= IF_RS_SENT; + idev->rs_interval = rfc3315_s14_backoff_init( + idev->cnf.rtr_solicit_interval); idev->rs_probes = 1; - addrconf_mod_rs_timer(idev, idev->cnf.rtr_solicit_interval); + addrconf_mod_rs_timer(idev, idev->rs_interval); } /* Well, that's kinda nasty ... */ @@ -5777,6 +5807,13 @@ static const struct ctl_table addrconf_sysctl[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, + { + .procname = "router_solicitation_max_interval", + .data = &ipv6_devconf.rtr_solicit_max_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, { .procname = "router_solicitation_delay", .data = &ipv6_devconf.rtr_solicit_delay, -- cgit v1.2.3 From cb3b7d87652aeb37cfb5295a6157a3280dae10cb Mon Sep 17 00:00:00 2001 From: Ayala Beker Date: Tue, 20 Sep 2016 17:31:13 +0300 Subject: cfg80211: add start / stop NAN commands This allows user space to start/stop NAN interface. A NAN interface is like P2P device in a few aspects: it doesn't have a netdev associated to it. Add the new interface type and prevent operations that can't be executed on NAN interface like scan. Define several attributes that may be configured by user space when starting NAN functionality (master preference and dual band operation) Signed-off-by: Andrei Otcheretianski Signed-off-by: Emmanuel Grumbach Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 21 +++++++++- include/uapi/linux/nl80211.h | 47 +++++++++++++++++++++++ net/mac80211/cfg.c | 2 + net/mac80211/chan.c | 3 ++ net/mac80211/iface.c | 4 ++ net/mac80211/offchannel.c | 1 + net/mac80211/rx.c | 3 ++ net/mac80211/util.c | 1 + net/wireless/chan.c | 2 + net/wireless/core.c | 34 +++++++++++++++++ net/wireless/core.h | 3 ++ net/wireless/mlme.c | 1 + net/wireless/nl80211.c | 91 ++++++++++++++++++++++++++++++++++++++++++-- net/wireless/rdev-ops.h | 20 ++++++++++ net/wireless/trace.h | 27 +++++++++++++ net/wireless/util.c | 6 ++- 16 files changed, 260 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 68dca3d93b85..9898e1f883e2 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2313,6 +2313,19 @@ struct cfg80211_qos_map { struct cfg80211_dscp_range up[8]; }; +/** + * struct cfg80211_nan_conf - NAN configuration + * + * This struct defines NAN configuration parameters + * + * @master_pref: master preference (1 - 255) + * @dual: dual band operation mode, see &enum nl80211_nan_dual_band_conf + */ +struct cfg80211_nan_conf { + u8 master_pref; + u8 dual; +}; + /** * struct cfg80211_ops - backend description for wireless configuration * @@ -2601,6 +2614,8 @@ struct cfg80211_qos_map { * and returning to the base channel for communication with the AP. * @tdls_cancel_channel_switch: Stop channel-switching with a TDLS peer. Both * peers must be on the base channel when the call completes. + * @start_nan: Start the NAN interface. + * @stop_nan: Stop the NAN interface. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -2866,6 +2881,9 @@ struct cfg80211_ops { void (*tdls_cancel_channel_switch)(struct wiphy *wiphy, struct net_device *dev, const u8 *addr); + int (*start_nan)(struct wiphy *wiphy, struct wireless_dev *wdev, + struct cfg80211_nan_conf *conf); + void (*stop_nan)(struct wiphy *wiphy, struct wireless_dev *wdev); }; /* @@ -3626,6 +3644,7 @@ struct cfg80211_cached_keys; * beacons, 0 when not valid * @address: The address for this device, valid only if @netdev is %NULL * @p2p_started: true if this is a P2P Device that has been started + * @nan_started: true if this is a NAN interface that has been started * @cac_started: true if DFS channel availability check has been started * @cac_start_time: timestamp (jiffies) when the dfs state was entered. * @cac_time_ms: CAC time in ms @@ -3657,7 +3676,7 @@ struct wireless_dev { struct mutex mtx; - bool use_4addr, p2p_started; + bool use_4addr, p2p_started, nan_started; u8 address[ETH_ALEN] __aligned(sizeof(u16)); diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index ec10d1b2838f..98fd3ec8598d 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -838,6 +838,16 @@ * not running. The driver indicates the status of the scan through * cfg80211_scan_done(). * + * @NL80211_CMD_START_NAN: Start NAN operation, identified by its + * %NL80211_ATTR_WDEV interface. This interface must have been previously + * created with %NL80211_CMD_NEW_INTERFACE. After it has been started, the + * NAN interface will create or join a cluster. This command must have a + * valid %NL80211_ATTR_NAN_MASTER_PREF attribute and optional + * %NL80211_ATTR_NAN_DUAL attributes. + * After this command NAN functions can be added. + * @NL80211_CMD_STOP_NAN: Stop the NAN operation, identified by + * its %NL80211_ATTR_WDEV interface. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1026,6 +1036,9 @@ enum nl80211_commands { NL80211_CMD_ABORT_SCAN, + NL80211_CMD_START_NAN, + NL80211_CMD_STOP_NAN, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -1739,6 +1752,12 @@ enum nl80211_commands { * regulatory indoor configuration would be owned by the netlink socket * that configured the indoor setting, and the indoor operation would be * cleared when the socket is closed. + * If set during NAN interface creation, the interface will be destroyed + * if the socket is closed just like any other interface. Moreover, only + * the netlink socket that created the interface will be allowed to add + * and remove functions. NAN notifications will be sent in unicast to that + * socket. Without this attribute, any socket can add functions and the + * notifications will be sent to the %NL80211_MCGRP_NAN multicast group. * * @NL80211_ATTR_TDLS_INITIATOR: flag attribute indicating the current end is * the TDLS link initiator. @@ -1873,6 +1892,14 @@ enum nl80211_commands { * @NL80211_ATTR_MESH_PEER_AID: Association ID for the mesh peer (u16). This is * used to pull the stored data for mesh peer in power save state. * + * @NL80211_ATTR_NAN_MASTER_PREF: the master preference to be used by + * %NL80211_CMD_START_NAN. Its type is u8 and it can't be 0. + * Also, values 1 and 255 are reserved for certification purposes and + * should not be used during a normal device operation. + * @NL80211_ATTR_NAN_DUAL: NAN dual band operation config (see + * &enum nl80211_nan_dual_band_conf). This attribute is used with + * %NL80211_CMD_START_NAN. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2267,6 +2294,9 @@ enum nl80211_attrs { NL80211_ATTR_MESH_PEER_AID, + NL80211_ATTR_NAN_MASTER_PREF, + NL80211_ATTR_NAN_DUAL, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -2345,6 +2375,7 @@ enum nl80211_attrs { * commands to create and destroy one * @NL80211_IF_TYPE_OCB: Outside Context of a BSS * This mode corresponds to the MIB variable dot11OCBActivated=true + * @NL80211_IFTYPE_NAN: NAN device interface type (not a netdev) * @NL80211_IFTYPE_MAX: highest interface type number currently defined * @NUM_NL80211_IFTYPES: number of defined interface types * @@ -2365,6 +2396,7 @@ enum nl80211_iftype { NL80211_IFTYPE_P2P_GO, NL80211_IFTYPE_P2P_DEVICE, NL80211_IFTYPE_OCB, + NL80211_IFTYPE_NAN, /* keep last */ NUM_NL80211_IFTYPES, @@ -4870,4 +4902,19 @@ enum nl80211_bss_select_attr { NL80211_BSS_SELECT_ATTR_MAX = __NL80211_BSS_SELECT_ATTR_AFTER_LAST - 1 }; +/** + * enum nl80211_nan_dual_band_conf - NAN dual band configuration + * + * Defines the NAN dual band mode of operation + * + * @NL80211_NAN_BAND_DEFAULT: device default mode + * @NL80211_NAN_BAND_2GHZ: 2.4GHz mode + * @NL80211_NAN_BAND_5GHZ: 5GHz mode + */ +enum nl80211_nan_dual_band_conf { + NL80211_NAN_BAND_DEFAULT = 1 << 0, + NL80211_NAN_BAND_2GHZ = 1 << 1, + NL80211_NAN_BAND_5GHZ = 1 << 2, +}; + #endif /* __LINUX_NL80211_H */ diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index e29ff5749944..a74027f887bc 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -257,6 +257,7 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_P2P_DEVICE: + case NL80211_IFTYPE_NAN: case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: case NL80211_IFTYPE_P2P_CLIENT: @@ -2036,6 +2037,7 @@ static int ieee80211_scan(struct wiphy *wiphy, !(req->flags & NL80211_SCAN_FLAG_AP))) return -EOPNOTSUPP; break; + case NL80211_IFTYPE_NAN: default: return -EOPNOTSUPP; } diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 74142d07ad31..d035801569eb 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -274,6 +274,7 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, ieee80211_get_max_required_bw(sdata)); break; case NL80211_IFTYPE_P2P_DEVICE: + case NL80211_IFTYPE_NAN: continue; case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_WDS: @@ -718,6 +719,7 @@ void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local, switch (sdata->vif.type) { case NL80211_IFTYPE_P2P_DEVICE: + case NL80211_IFTYPE_NAN: continue; case NL80211_IFTYPE_STATION: if (!sdata->u.mgd.associated) @@ -980,6 +982,7 @@ ieee80211_vif_chanctx_reservation_complete(struct ieee80211_sub_if_data *sdata) case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_P2P_DEVICE: + case NL80211_IFTYPE_NAN: case NUM_NL80211_IFTYPES: WARN_ON(1); break; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index b0abddc714ef..e694ca2baad0 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -545,6 +545,7 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_OCB: + case NL80211_IFTYPE_NAN: /* no special treatment */ break; case NL80211_IFTYPE_UNSPECIFIED: @@ -660,6 +661,7 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) break; case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_P2P_DEVICE: + case NL80211_IFTYPE_NAN: break; default: /* not reached */ @@ -948,6 +950,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, /* relies on synchronize_rcu() below */ RCU_INIT_POINTER(local->p2p_sdata, NULL); /* fall through */ + case NL80211_IFTYPE_NAN: default: cancel_work_sync(&sdata->work); /* @@ -1457,6 +1460,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, break; case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_P2P_DEVICE: + case NL80211_IFTYPE_NAN: sdata->vif.bss_conf.bssid = sdata->vif.addr; break; case NL80211_IFTYPE_UNSPECIFIED: diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index 55a9c5b94ce1..75d5c960ce67 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -838,6 +838,7 @@ int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, case NL80211_IFTYPE_P2P_DEVICE: need_offchan = true; break; + case NL80211_IFTYPE_NAN: default: return -EOPNOTSUPP; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index e796060b7c5e..c9489a86e6d6 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3586,6 +3586,9 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) ieee80211_is_probe_req(hdr->frame_control) || ieee80211_is_probe_resp(hdr->frame_control) || ieee80211_is_beacon(hdr->frame_control); + case NL80211_IFTYPE_NAN: + /* Currently no frames on NAN interface are allowed */ + return false; default: break; } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index b6865d884487..2c78541f695c 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1975,6 +1975,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_P2P_DEVICE: + case NL80211_IFTYPE_NAN: /* nothing to do */ break; case NL80211_IFTYPE_UNSPECIFIED: diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 0f506220a3bd..5497d022fada 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -372,6 +372,7 @@ int cfg80211_chandef_dfs_required(struct wiphy *wiphy, case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_P2P_DEVICE: + case NL80211_IFTYPE_NAN: break; case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: @@ -946,6 +947,7 @@ cfg80211_get_chan_state(struct wireless_dev *wdev, case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_P2P_DEVICE: + case NL80211_IFTYPE_NAN: /* these interface types don't really have a channel */ return; case NL80211_IFTYPE_UNSPECIFIED: diff --git a/net/wireless/core.c b/net/wireless/core.c index 4911cd997b9a..013987243c0b 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -225,6 +225,23 @@ void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev, } } +void cfg80211_stop_nan(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev) +{ + ASSERT_RTNL(); + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_NAN)) + return; + + if (!wdev->nan_started) + return; + + rdev_stop_nan(rdev, wdev); + wdev->nan_started = false; + + rdev->opencount--; +} + void cfg80211_shutdown_all_interfaces(struct wiphy *wiphy) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); @@ -242,6 +259,9 @@ void cfg80211_shutdown_all_interfaces(struct wiphy *wiphy) case NL80211_IFTYPE_P2P_DEVICE: cfg80211_stop_p2p_device(rdev, wdev); break; + case NL80211_IFTYPE_NAN: + cfg80211_stop_nan(rdev, wdev); + break; default: break; } @@ -537,6 +557,11 @@ static int wiphy_verify_combinations(struct wiphy *wiphy) c->limits[j].max > 1)) return -EINVAL; + /* Only a single NAN can be allowed */ + if (WARN_ON(types & BIT(NL80211_IFTYPE_NAN) && + c->limits[j].max > 1)) + return -EINVAL; + cnt += c->limits[j].max; /* * Don't advertise an unsupported type @@ -579,6 +604,10 @@ int wiphy_register(struct wiphy *wiphy) !rdev->ops->tdls_cancel_channel_switch))) return -EINVAL; + if (WARN_ON((wiphy->interface_modes & BIT(NL80211_IFTYPE_NAN)) && + (!rdev->ops->start_nan || !rdev->ops->stop_nan))) + return -EINVAL; + /* * if a wiphy has unsupported modes for regulatory channel enforcement, * opt-out of enforcement checking @@ -589,6 +618,7 @@ int wiphy_register(struct wiphy *wiphy) BIT(NL80211_IFTYPE_P2P_GO) | BIT(NL80211_IFTYPE_ADHOC) | BIT(NL80211_IFTYPE_P2P_DEVICE) | + BIT(NL80211_IFTYPE_NAN) | BIT(NL80211_IFTYPE_AP_VLAN) | BIT(NL80211_IFTYPE_MONITOR))) wiphy->regulatory_flags |= REGULATORY_IGNORE_STALE_KICKOFF; @@ -916,6 +946,9 @@ void cfg80211_unregister_wdev(struct wireless_dev *wdev) cfg80211_mlme_purge_registrations(wdev); cfg80211_stop_p2p_device(rdev, wdev); break; + case NL80211_IFTYPE_NAN: + cfg80211_stop_nan(rdev, wdev); + break; default: WARN_ON_ONCE(1); break; @@ -979,6 +1012,7 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev, /* must be handled by mac80211/driver, has no APIs */ break; case NL80211_IFTYPE_P2P_DEVICE: + case NL80211_IFTYPE_NAN: /* cannot happen, has no netdev */ break; case NL80211_IFTYPE_AP_VLAN: diff --git a/net/wireless/core.h b/net/wireless/core.h index 554f87d0f991..08d2e948c9ad 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -488,6 +488,9 @@ void cfg80211_leave(struct cfg80211_registered_device *rdev, void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); +void cfg80211_stop_nan(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev); + #define CFG80211_MAX_NUM_DIFFERENT_CHANNELS 10 #ifdef CONFIG_CFG80211_DEVELOPER_WARNINGS diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index d6abb0704db5..cbb48e26a871 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -634,6 +634,7 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, * fall through, P2P device only supports * public action frames */ + case NL80211_IFTYPE_NAN: default: err = -EOPNOTSUPP; break; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b8441e60b0f6..9e9fb37087fc 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -409,6 +409,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { .len = VHT_MUMIMO_GROUPS_DATA_LEN }, [NL80211_ATTR_MU_MIMO_FOLLOW_MAC_ADDR] = { .len = ETH_ALEN }, + [NL80211_ATTR_NAN_MASTER_PREF] = { .type = NLA_U8 }, + [NL80211_ATTR_NAN_DUAL] = { .type = NLA_U8 }, }; /* policy for the key attributes */ @@ -934,6 +936,7 @@ static int nl80211_key_allowed(struct wireless_dev *wdev) case NL80211_IFTYPE_UNSPECIFIED: case NL80211_IFTYPE_OCB: case NL80211_IFTYPE_MONITOR: + case NL80211_IFTYPE_NAN: case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_WDS: case NUM_NL80211_IFTYPES: @@ -2819,7 +2822,7 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) !(rdev->wiphy.interface_modes & (1 << type))) return -EOPNOTSUPP; - if ((type == NL80211_IFTYPE_P2P_DEVICE || + if ((type == NL80211_IFTYPE_P2P_DEVICE || type == NL80211_IFTYPE_NAN || rdev->wiphy.features & NL80211_FEATURE_MAC_ON_CREATE) && info->attrs[NL80211_ATTR_MAC]) { nla_memcpy(params.macaddr, info->attrs[NL80211_ATTR_MAC], @@ -2875,9 +2878,10 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) wdev->mesh_id_up_len); wdev_unlock(wdev); break; + case NL80211_IFTYPE_NAN: case NL80211_IFTYPE_P2P_DEVICE: /* - * P2P Device doesn't have a netdev, so doesn't go + * P2P Device and NAN do not have a netdev, so don't go * through the netdev notifier and must be added here */ mutex_init(&wdev->mtx); @@ -6434,6 +6438,9 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) wiphy = &rdev->wiphy; + if (wdev->iftype == NL80211_IFTYPE_NAN) + return -EOPNOTSUPP; + if (!rdev->ops->scan) return -EOPNOTSUPP; @@ -8977,6 +8984,7 @@ static int nl80211_register_mgmt(struct sk_buff *skb, struct genl_info *info) case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_P2P_DEVICE: break; + case NL80211_IFTYPE_NAN: default: return -EOPNOTSUPP; } @@ -9022,6 +9030,7 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) case NL80211_IFTYPE_MESH_POINT: case NL80211_IFTYPE_P2P_GO: break; + case NL80211_IFTYPE_NAN: default: return -EOPNOTSUPP; } @@ -9138,6 +9147,7 @@ static int nl80211_tx_mgmt_cancel_wait(struct sk_buff *skb, struct genl_info *in case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_P2P_DEVICE: break; + case NL80211_IFTYPE_NAN: default: return -EOPNOTSUPP; } @@ -10504,6 +10514,58 @@ static int nl80211_stop_p2p_device(struct sk_buff *skb, struct genl_info *info) return 0; } +static int nl80211_start_nan(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct wireless_dev *wdev = info->user_ptr[1]; + struct cfg80211_nan_conf conf = {}; + int err; + + if (wdev->iftype != NL80211_IFTYPE_NAN) + return -EOPNOTSUPP; + + if (wdev->nan_started) + return -EEXIST; + + if (rfkill_blocked(rdev->rfkill)) + return -ERFKILL; + + if (!info->attrs[NL80211_ATTR_NAN_MASTER_PREF]) + return -EINVAL; + + if (!info->attrs[NL80211_ATTR_NAN_DUAL]) + return -EINVAL; + + conf.master_pref = + nla_get_u8(info->attrs[NL80211_ATTR_NAN_MASTER_PREF]); + if (!conf.master_pref) + return -EINVAL; + + conf.dual = nla_get_u8(info->attrs[NL80211_ATTR_NAN_DUAL]); + + err = rdev_start_nan(rdev, wdev, &conf); + if (err) + return err; + + wdev->nan_started = true; + rdev->opencount++; + + return 0; +} + +static int nl80211_stop_nan(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct wireless_dev *wdev = info->user_ptr[1]; + + if (wdev->iftype != NL80211_IFTYPE_NAN) + return -EOPNOTSUPP; + + cfg80211_stop_nan(rdev, wdev); + + return 0; +} + static int nl80211_get_protocol_features(struct sk_buff *skb, struct genl_info *info) { @@ -11205,7 +11267,14 @@ static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, dev_hold(dev); } else if (ops->internal_flags & NL80211_FLAG_CHECK_NETDEV_UP) { - if (!wdev->p2p_started) { + if (wdev->iftype == NL80211_IFTYPE_P2P_DEVICE && + !wdev->p2p_started) { + if (rtnl) + rtnl_unlock(); + return -ENETDOWN; + } + if (wdev->iftype == NL80211_IFTYPE_NAN && + !wdev->nan_started) { if (rtnl) rtnl_unlock(); return -ENETDOWN; @@ -11838,6 +11907,22 @@ static const struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_START_NAN, + .doit = nl80211_start_nan, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_WDEV | + NL80211_FLAG_NEED_RTNL, + }, + { + .cmd = NL80211_CMD_STOP_NAN, + .doit = nl80211_stop_nan, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_WDEV_UP | + NL80211_FLAG_NEED_RTNL, + }, { .cmd = NL80211_CMD_SET_MCAST_RATE, .doit = nl80211_set_mcast_rate, diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 85ff30bee2b9..afb68a8428b9 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -887,6 +887,26 @@ static inline void rdev_stop_p2p_device(struct cfg80211_registered_device *rdev, trace_rdev_return_void(&rdev->wiphy); } +static inline int rdev_start_nan(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + struct cfg80211_nan_conf *conf) +{ + int ret; + + trace_rdev_start_nan(&rdev->wiphy, wdev, conf); + ret = rdev->ops->start_nan(&rdev->wiphy, wdev, conf); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline void rdev_stop_nan(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev) +{ + trace_rdev_stop_nan(&rdev->wiphy, wdev); + rdev->ops->stop_nan(&rdev->wiphy, wdev); + trace_rdev_return_void(&rdev->wiphy); +} + static inline int rdev_set_mac_acl(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_acl_data *params) diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 72b5255cefe2..5f3370f4c6a2 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1889,6 +1889,33 @@ DEFINE_EVENT(wiphy_wdev_evt, rdev_stop_p2p_device, TP_ARGS(wiphy, wdev) ); +TRACE_EVENT(rdev_start_nan, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, + struct cfg80211_nan_conf *conf), + TP_ARGS(wiphy, wdev, conf), + TP_STRUCT__entry( + WIPHY_ENTRY + WDEV_ENTRY + __field(u8, master_pref) + __field(u8, dual); + ), + TP_fast_assign( + WIPHY_ASSIGN; + WDEV_ASSIGN; + __entry->master_pref = conf->master_pref; + __entry->dual = conf->dual; + ), + TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT + ", master preference: %u, dual: %d", + WIPHY_PR_ARG, WDEV_PR_ARG, __entry->master_pref, + __entry->dual) +); + +DEFINE_EVENT(wiphy_wdev_evt, rdev_stop_nan, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev), + TP_ARGS(wiphy, wdev) +); + TRACE_EVENT(rdev_set_mac_acl, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, struct cfg80211_acl_data *params), diff --git a/net/wireless/util.c b/net/wireless/util.c index e02141d66b69..7a2d46b0058a 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1008,8 +1008,9 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, if (otype == NL80211_IFTYPE_AP_VLAN) return -EOPNOTSUPP; - /* cannot change into P2P device type */ - if (ntype == NL80211_IFTYPE_P2P_DEVICE) + /* cannot change into P2P device or NAN */ + if (ntype == NL80211_IFTYPE_P2P_DEVICE || + ntype == NL80211_IFTYPE_NAN) return -EOPNOTSUPP; if (!rdev->ops->change_virtual_intf || @@ -1088,6 +1089,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, /* not happening */ break; case NL80211_IFTYPE_P2P_DEVICE: + case NL80211_IFTYPE_NAN: WARN_ON(1); break; } -- cgit v1.2.3 From a442b761b24b6886f9a4e2ff5f8cb4824c96526b Mon Sep 17 00:00:00 2001 From: Ayala Beker Date: Tue, 20 Sep 2016 17:31:15 +0300 Subject: cfg80211: add add_nan_func / del_nan_func A NAN function can be either publish, subscribe or follow up. Make all the necessary verifications and just pass the request to the driver. Allow the user space application that starts NAN to forbid any other socket to add or remove functions. Signed-off-by: Andrei Otcheretianski Signed-off-by: Emmanuel Grumbach Signed-off-by: Ayala Beker Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 91 +++++++++++ include/uapi/linux/nl80211.h | 150 ++++++++++++++++++ net/wireless/core.c | 3 +- net/wireless/nl80211.c | 369 +++++++++++++++++++++++++++++++++++++++++++ net/wireless/rdev-ops.h | 21 +++ net/wireless/trace.h | 39 +++++ net/wireless/util.c | 22 +++ 7 files changed, 694 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 9898e1f883e2..2f35ccf6da83 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2326,6 +2326,73 @@ struct cfg80211_nan_conf { u8 dual; }; +/** + * struct cfg80211_nan_func_filter - a NAN function Rx / Tx filter + * + * @filter: the content of the filter + * @len: the length of the filter + */ +struct cfg80211_nan_func_filter { + const u8 *filter; + u8 len; +}; + +/** + * struct cfg80211_nan_func - a NAN function + * + * @type: &enum nl80211_nan_function_type + * @service_id: the service ID of the function + * @publish_type: &nl80211_nan_publish_type + * @close_range: if true, the range should be limited. Threshold is + * implementation specific. + * @publish_bcast: if true, the solicited publish should be broadcasted + * @subscribe_active: if true, the subscribe is active + * @followup_id: the instance ID for follow up + * @followup_reqid: the requestor instance ID for follow up + * @followup_dest: MAC address of the recipient of the follow up + * @ttl: time to live counter in DW. + * @serv_spec_info: Service Specific Info + * @serv_spec_info_len: Service Specific Info length + * @srf_include: if true, SRF is inclusive + * @srf_bf: Bloom Filter + * @srf_bf_len: Bloom Filter length + * @srf_bf_idx: Bloom Filter index + * @srf_macs: SRF MAC addresses + * @srf_num_macs: number of MAC addresses in SRF + * @rx_filters: rx filters that are matched with corresponding peer's tx_filter + * @tx_filters: filters that should be transmitted in the SDF. + * @num_rx_filters: length of &rx_filters. + * @num_tx_filters: length of &tx_filters. + * @instance_id: driver allocated id of the function. + * @cookie: unique NAN function identifier. + */ +struct cfg80211_nan_func { + enum nl80211_nan_function_type type; + u8 service_id[NL80211_NAN_FUNC_SERVICE_ID_LEN]; + u8 publish_type; + bool close_range; + bool publish_bcast; + bool subscribe_active; + u8 followup_id; + u8 followup_reqid; + struct mac_address followup_dest; + u32 ttl; + const u8 *serv_spec_info; + u8 serv_spec_info_len; + bool srf_include; + const u8 *srf_bf; + u8 srf_bf_len; + u8 srf_bf_idx; + struct mac_address *srf_macs; + int srf_num_macs; + struct cfg80211_nan_func_filter *rx_filters; + struct cfg80211_nan_func_filter *tx_filters; + u8 num_tx_filters; + u8 num_rx_filters; + u8 instance_id; + u64 cookie; +}; + /** * struct cfg80211_ops - backend description for wireless configuration * @@ -2616,6 +2683,14 @@ struct cfg80211_nan_conf { * peers must be on the base channel when the call completes. * @start_nan: Start the NAN interface. * @stop_nan: Stop the NAN interface. + * @add_nan_func: Add a NAN function. Returns negative value on failure. + * On success @nan_func ownership is transferred to the driver and + * it may access it outside of the scope of this function. The driver + * should free the @nan_func when no longer needed by calling + * cfg80211_free_nan_func(). + * On success the driver should assign an instance_id in the + * provided @nan_func. + * @del_nan_func: Delete a NAN function. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -2884,6 +2959,10 @@ struct cfg80211_ops { int (*start_nan)(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_nan_conf *conf); void (*stop_nan)(struct wiphy *wiphy, struct wireless_dev *wdev); + int (*add_nan_func)(struct wiphy *wiphy, struct wireless_dev *wdev, + struct cfg80211_nan_func *nan_func); + void (*del_nan_func)(struct wiphy *wiphy, struct wireless_dev *wdev, + u64 cookie); }; /* @@ -3335,6 +3414,8 @@ struct wiphy_iftype_ext_capab { * @bss_select_support: bitmask indicating the BSS selection criteria supported * by the driver in the .connect() callback. The bit position maps to the * attribute indices defined in &enum nl80211_bss_select_attr. + * + * @cookie_counter: unique generic cookie counter, used to identify objects. */ struct wiphy { /* assign these fields before you register the wiphy */ @@ -3464,6 +3545,8 @@ struct wiphy { u32 bss_select_support; + u64 cookie_counter; + char priv[0] __aligned(NETDEV_ALIGN); }; @@ -5584,6 +5667,14 @@ wiphy_ext_feature_isset(struct wiphy *wiphy, return (ft_byte & BIT(ftidx % 8)) != 0; } +/** + * cfg80211_free_nan_func - free NAN function + * @f: NAN function that should be freed + * + * Frees all the NAN function and all it's allocated members. + */ +void cfg80211_free_nan_func(struct cfg80211_nan_func *f); + /* ethtool helper */ void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info); diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 98fd3ec8598d..e4935d963061 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -847,6 +847,21 @@ * After this command NAN functions can be added. * @NL80211_CMD_STOP_NAN: Stop the NAN operation, identified by * its %NL80211_ATTR_WDEV interface. + * @NL80211_CMD_ADD_NAN_FUNCTION: Add a NAN function. The function is defined + * with %NL80211_ATTR_NAN_FUNC nested attribute. When called, this + * operation returns the strictly positive and unique instance id + * (%NL80211_ATTR_NAN_FUNC_INST_ID) and a cookie (%NL80211_ATTR_COOKIE) + * of the function upon success. + * Since instance ID's can be re-used, this cookie is the right + * way to identify the function. This will avoid races when a termination + * event is handled by the user space after it has already added a new + * function that got the same instance id from the kernel as the one + * which just terminated. + * This cookie may be used in NAN events even before the command + * returns, so userspace shouldn't process NAN events until it processes + * the response to this command. + * Look at %NL80211_ATTR_SOCKET_OWNER as well. + * @NL80211_CMD_DEL_NAN_FUNCTION: Delete a NAN function by cookie. * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use @@ -1038,6 +1053,8 @@ enum nl80211_commands { NL80211_CMD_START_NAN, NL80211_CMD_STOP_NAN, + NL80211_CMD_ADD_NAN_FUNCTION, + NL80211_CMD_DEL_NAN_FUNCTION, /* add new commands above here */ @@ -1899,6 +1916,9 @@ enum nl80211_commands { * @NL80211_ATTR_NAN_DUAL: NAN dual band operation config (see * &enum nl80211_nan_dual_band_conf). This attribute is used with * %NL80211_CMD_START_NAN. + * @NL80211_ATTR_NAN_FUNC: a function that can be added to NAN. See + * &enum nl80211_nan_func_attributes for description of this nested + * attribute. * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined @@ -2296,6 +2316,7 @@ enum nl80211_attrs { NL80211_ATTR_NAN_MASTER_PREF, NL80211_ATTR_NAN_DUAL, + NL80211_ATTR_NAN_FUNC, /* add attributes here, update the policy in nl80211.c */ @@ -4917,4 +4938,133 @@ enum nl80211_nan_dual_band_conf { NL80211_NAN_BAND_5GHZ = 1 << 2, }; +/** + * enum nl80211_nan_function_type - NAN function type + * + * Defines the function type of a NAN function + * + * @NL80211_NAN_FUNC_PUBLISH: function is publish + * @NL80211_NAN_FUNC_SUBSCRIBE: function is subscribe + * @NL80211_NAN_FUNC_FOLLOW_UP: function is follow-up + */ +enum nl80211_nan_function_type { + NL80211_NAN_FUNC_PUBLISH, + NL80211_NAN_FUNC_SUBSCRIBE, + NL80211_NAN_FUNC_FOLLOW_UP, + + /* keep last */ + __NL80211_NAN_FUNC_TYPE_AFTER_LAST, + NL80211_NAN_FUNC_MAX_TYPE = __NL80211_NAN_FUNC_TYPE_AFTER_LAST - 1, +}; + +/** + * enum nl80211_nan_publish_type - NAN publish tx type + * + * Defines how to send publish Service Discovery Frames + * + * @NL80211_NAN_SOLICITED_PUBLISH: publish function is solicited + * @NL80211_NAN_UNSOLICITED_PUBLISH: publish function is unsolicited + */ +enum nl80211_nan_publish_type { + NL80211_NAN_SOLICITED_PUBLISH = 1 << 0, + NL80211_NAN_UNSOLICITED_PUBLISH = 1 << 1, +}; + +#define NL80211_NAN_FUNC_SERVICE_ID_LEN 6 +#define NL80211_NAN_FUNC_SERVICE_SPEC_INFO_MAX_LEN 0xff +#define NL80211_NAN_FUNC_SRF_MAX_LEN 0xff + +/** + * enum nl80211_nan_func_attributes - NAN function attributes + * @__NL80211_NAN_FUNC_INVALID: invalid + * @NL80211_NAN_FUNC_TYPE: &enum nl80211_nan_function_type (u8). + * @NL80211_NAN_FUNC_SERVICE_ID: 6 bytes of the service ID hash as + * specified in NAN spec. This is a binary attribute. + * @NL80211_NAN_FUNC_PUBLISH_TYPE: relevant if the function's type is + * publish. Defines the transmission type for the publish Service Discovery + * Frame, see &enum nl80211_nan_publish_type. Its type is u8. + * @NL80211_NAN_FUNC_PUBLISH_BCAST: relevant if the function is a solicited + * publish. Should the solicited publish Service Discovery Frame be sent to + * the NAN Broadcast address. This is a flag. + * @NL80211_NAN_FUNC_SUBSCRIBE_ACTIVE: relevant if the function's type is + * subscribe. Is the subscribe active. This is a flag. + * @NL80211_NAN_FUNC_FOLLOW_UP_ID: relevant if the function's type is follow up. + * The instance ID for the follow up Service Discovery Frame. This is u8. + * @NL80211_NAN_FUNC_FOLLOW_UP_REQ_ID: relevant if the function's type + * is follow up. This is a u8. + * The requestor instance ID for the follow up Service Discovery Frame. + * @NL80211_NAN_FUNC_FOLLOW_UP_DEST: the MAC address of the recipient of the + * follow up Service Discovery Frame. This is a binary attribute. + * @NL80211_NAN_FUNC_CLOSE_RANGE: is this function limited for devices in a + * close range. The range itself (RSSI) is defined by the device. + * This is a flag. + * @NL80211_NAN_FUNC_TTL: strictly positive number of DWs this function should + * stay active. If not present infinite TTL is assumed. This is a u32. + * @NL80211_NAN_FUNC_SERVICE_INFO: array of bytes describing the service + * specific info. This is a binary attribute. + * @NL80211_NAN_FUNC_SRF: Service Receive Filter. This is a nested attribute. + * See &enum nl80211_nan_srf_attributes. + * @NL80211_NAN_FUNC_RX_MATCH_FILTER: Receive Matching filter. This is a nested + * attribute. It is a list of binary values. + * @NL80211_NAN_FUNC_TX_MATCH_FILTER: Transmit Matching filter. This is a + * nested attribute. It is a list of binary values. + * @NL80211_NAN_FUNC_INSTANCE_ID: The instance ID of the function. + * Its type is u8 and it cannot be 0. + * @NL80211_NAN_FUNC_TERM_REASON: NAN function termination reason. + * See &enum nl80211_nan_func_term_reason. + * + * @NUM_NL80211_NAN_FUNC_ATTR: internal + * @NL80211_NAN_FUNC_ATTR_MAX: highest NAN function attribute + */ +enum nl80211_nan_func_attributes { + __NL80211_NAN_FUNC_INVALID, + NL80211_NAN_FUNC_TYPE, + NL80211_NAN_FUNC_SERVICE_ID, + NL80211_NAN_FUNC_PUBLISH_TYPE, + NL80211_NAN_FUNC_PUBLISH_BCAST, + NL80211_NAN_FUNC_SUBSCRIBE_ACTIVE, + NL80211_NAN_FUNC_FOLLOW_UP_ID, + NL80211_NAN_FUNC_FOLLOW_UP_REQ_ID, + NL80211_NAN_FUNC_FOLLOW_UP_DEST, + NL80211_NAN_FUNC_CLOSE_RANGE, + NL80211_NAN_FUNC_TTL, + NL80211_NAN_FUNC_SERVICE_INFO, + NL80211_NAN_FUNC_SRF, + NL80211_NAN_FUNC_RX_MATCH_FILTER, + NL80211_NAN_FUNC_TX_MATCH_FILTER, + NL80211_NAN_FUNC_INSTANCE_ID, + NL80211_NAN_FUNC_TERM_REASON, + + /* keep last */ + NUM_NL80211_NAN_FUNC_ATTR, + NL80211_NAN_FUNC_ATTR_MAX = NUM_NL80211_NAN_FUNC_ATTR - 1 +}; + +/** + * enum nl80211_nan_srf_attributes - NAN Service Response filter attributes + * @__NL80211_NAN_SRF_INVALID: invalid + * @NL80211_NAN_SRF_INCLUDE: present if the include bit of the SRF set. + * This is a flag. + * @NL80211_NAN_SRF_BF: Bloom Filter. Present if and only if + * &NL80211_NAN_SRF_MAC_ADDRS isn't present. This attribute is binary. + * @NL80211_NAN_SRF_BF_IDX: index of the Bloom Filter. Mandatory if + * &NL80211_NAN_SRF_BF is present. This is a u8. + * @NL80211_NAN_SRF_MAC_ADDRS: list of MAC addresses for the SRF. Present if + * and only if &NL80211_NAN_SRF_BF isn't present. This is a nested + * attribute. Each nested attribute is a MAC address. + * @NUM_NL80211_NAN_SRF_ATTR: internal + * @NL80211_NAN_SRF_ATTR_MAX: highest NAN SRF attribute + */ +enum nl80211_nan_srf_attributes { + __NL80211_NAN_SRF_INVALID, + NL80211_NAN_SRF_INCLUDE, + NL80211_NAN_SRF_BF, + NL80211_NAN_SRF_BF_IDX, + NL80211_NAN_SRF_MAC_ADDRS, + + /* keep last */ + NUM_NL80211_NAN_SRF_ATTR, + NL80211_NAN_SRF_ATTR_MAX = NUM_NL80211_NAN_SRF_ATTR - 1, +}; + #endif /* __LINUX_NL80211_H */ diff --git a/net/wireless/core.c b/net/wireless/core.c index 013987243c0b..8201e6d7449e 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -605,7 +605,8 @@ int wiphy_register(struct wiphy *wiphy) return -EINVAL; if (WARN_ON((wiphy->interface_modes & BIT(NL80211_IFTYPE_NAN)) && - (!rdev->ops->start_nan || !rdev->ops->stop_nan))) + (!rdev->ops->start_nan || !rdev->ops->stop_nan || + !rdev->ops->add_nan_func || !rdev->ops->del_nan_func))) return -EINVAL; /* diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 9e9fb37087fc..0eca59ccd685 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -411,6 +411,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_MU_MIMO_FOLLOW_MAC_ADDR] = { .len = ETH_ALEN }, [NL80211_ATTR_NAN_MASTER_PREF] = { .type = NLA_U8 }, [NL80211_ATTR_NAN_DUAL] = { .type = NLA_U8 }, + [NL80211_ATTR_NAN_FUNC] = { .type = NLA_NESTED }, }; /* policy for the key attributes */ @@ -504,6 +505,39 @@ nl80211_bss_select_policy[NL80211_BSS_SELECT_ATTR_MAX + 1] = { }, }; +/* policy for NAN function attributes */ +static const struct nla_policy +nl80211_nan_func_policy[NL80211_NAN_FUNC_ATTR_MAX + 1] = { + [NL80211_NAN_FUNC_TYPE] = { .type = NLA_U8 }, + [NL80211_NAN_FUNC_SERVICE_ID] = { .type = NLA_BINARY, + .len = NL80211_NAN_FUNC_SERVICE_ID_LEN }, + [NL80211_NAN_FUNC_PUBLISH_TYPE] = { .type = NLA_U8 }, + [NL80211_NAN_FUNC_PUBLISH_BCAST] = { .type = NLA_FLAG }, + [NL80211_NAN_FUNC_SUBSCRIBE_ACTIVE] = { .type = NLA_FLAG }, + [NL80211_NAN_FUNC_FOLLOW_UP_ID] = { .type = NLA_U8 }, + [NL80211_NAN_FUNC_FOLLOW_UP_REQ_ID] = { .type = NLA_U8 }, + [NL80211_NAN_FUNC_FOLLOW_UP_DEST] = { .len = ETH_ALEN }, + [NL80211_NAN_FUNC_CLOSE_RANGE] = { .type = NLA_FLAG }, + [NL80211_NAN_FUNC_TTL] = { .type = NLA_U32 }, + [NL80211_NAN_FUNC_SERVICE_INFO] = { .type = NLA_BINARY, + .len = NL80211_NAN_FUNC_SERVICE_SPEC_INFO_MAX_LEN }, + [NL80211_NAN_FUNC_SRF] = { .type = NLA_NESTED }, + [NL80211_NAN_FUNC_RX_MATCH_FILTER] = { .type = NLA_NESTED }, + [NL80211_NAN_FUNC_TX_MATCH_FILTER] = { .type = NLA_NESTED }, + [NL80211_NAN_FUNC_INSTANCE_ID] = { .type = NLA_U8 }, + [NL80211_NAN_FUNC_TERM_REASON] = { .type = NLA_U8 }, +}; + +/* policy for Service Response Filter attributes */ +static const struct nla_policy +nl80211_nan_srf_policy[NL80211_NAN_SRF_ATTR_MAX + 1] = { + [NL80211_NAN_SRF_INCLUDE] = { .type = NLA_FLAG }, + [NL80211_NAN_SRF_BF] = { .type = NLA_BINARY, + .len = NL80211_NAN_FUNC_SRF_MAX_LEN }, + [NL80211_NAN_SRF_BF_IDX] = { .type = NLA_U8 }, + [NL80211_NAN_SRF_MAC_ADDRS] = { .type = NLA_NESTED }, +}; + static int nl80211_prepare_wdev_dump(struct sk_buff *skb, struct netlink_callback *cb, struct cfg80211_registered_device **rdev, @@ -10566,6 +10600,325 @@ static int nl80211_stop_nan(struct sk_buff *skb, struct genl_info *info) return 0; } +static int validate_nan_filter(struct nlattr *filter_attr) +{ + struct nlattr *attr; + int len = 0, n_entries = 0, rem; + + nla_for_each_nested(attr, filter_attr, rem) { + len += nla_len(attr); + n_entries++; + } + + if (len >= U8_MAX) + return -EINVAL; + + return n_entries; +} + +static int handle_nan_filter(struct nlattr *attr_filter, + struct cfg80211_nan_func *func, + bool tx) +{ + struct nlattr *attr; + int n_entries, rem, i; + struct cfg80211_nan_func_filter *filter; + + n_entries = validate_nan_filter(attr_filter); + if (n_entries < 0) + return n_entries; + + BUILD_BUG_ON(sizeof(*func->rx_filters) != sizeof(*func->tx_filters)); + + filter = kcalloc(n_entries, sizeof(*func->rx_filters), GFP_KERNEL); + if (!filter) + return -ENOMEM; + + i = 0; + nla_for_each_nested(attr, attr_filter, rem) { + filter[i].filter = kmemdup(nla_data(attr), nla_len(attr), + GFP_KERNEL); + filter[i].len = nla_len(attr); + i++; + } + if (tx) { + func->num_tx_filters = n_entries; + func->tx_filters = filter; + } else { + func->num_rx_filters = n_entries; + func->rx_filters = filter; + } + + return 0; +} + +static int nl80211_nan_add_func(struct sk_buff *skb, + struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct wireless_dev *wdev = info->user_ptr[1]; + struct nlattr *tb[NUM_NL80211_NAN_FUNC_ATTR], *func_attr; + struct cfg80211_nan_func *func; + struct sk_buff *msg = NULL; + void *hdr = NULL; + int err = 0; + + if (wdev->iftype != NL80211_IFTYPE_NAN) + return -EOPNOTSUPP; + + if (!wdev->nan_started) + return -ENOTCONN; + + if (!info->attrs[NL80211_ATTR_NAN_FUNC]) + return -EINVAL; + + if (wdev->owner_nlportid && + wdev->owner_nlportid != info->snd_portid) + return -ENOTCONN; + + err = nla_parse(tb, NL80211_NAN_FUNC_ATTR_MAX, + nla_data(info->attrs[NL80211_ATTR_NAN_FUNC]), + nla_len(info->attrs[NL80211_ATTR_NAN_FUNC]), + nl80211_nan_func_policy); + if (err) + return err; + + func = kzalloc(sizeof(*func), GFP_KERNEL); + if (!func) + return -ENOMEM; + + func->cookie = wdev->wiphy->cookie_counter++; + + if (!tb[NL80211_NAN_FUNC_TYPE] || + nla_get_u8(tb[NL80211_NAN_FUNC_TYPE]) > NL80211_NAN_FUNC_MAX_TYPE) { + err = -EINVAL; + goto out; + } + + + func->type = nla_get_u8(tb[NL80211_NAN_FUNC_TYPE]); + + if (!tb[NL80211_NAN_FUNC_SERVICE_ID]) { + err = -EINVAL; + goto out; + } + + memcpy(func->service_id, nla_data(tb[NL80211_NAN_FUNC_SERVICE_ID]), + sizeof(func->service_id)); + + func->close_range = + nla_get_flag(tb[NL80211_NAN_FUNC_CLOSE_RANGE]); + + if (tb[NL80211_NAN_FUNC_SERVICE_INFO]) { + func->serv_spec_info_len = + nla_len(tb[NL80211_NAN_FUNC_SERVICE_INFO]); + func->serv_spec_info = + kmemdup(nla_data(tb[NL80211_NAN_FUNC_SERVICE_INFO]), + func->serv_spec_info_len, + GFP_KERNEL); + if (!func->serv_spec_info) { + err = -ENOMEM; + goto out; + } + } + + if (tb[NL80211_NAN_FUNC_TTL]) + func->ttl = nla_get_u32(tb[NL80211_NAN_FUNC_TTL]); + + switch (func->type) { + case NL80211_NAN_FUNC_PUBLISH: + if (!tb[NL80211_NAN_FUNC_PUBLISH_TYPE]) { + err = -EINVAL; + goto out; + } + + func->publish_type = + nla_get_u8(tb[NL80211_NAN_FUNC_PUBLISH_TYPE]); + func->publish_bcast = + nla_get_flag(tb[NL80211_NAN_FUNC_PUBLISH_BCAST]); + + if ((!(func->publish_type & NL80211_NAN_SOLICITED_PUBLISH)) && + func->publish_bcast) { + err = -EINVAL; + goto out; + } + break; + case NL80211_NAN_FUNC_SUBSCRIBE: + func->subscribe_active = + nla_get_flag(tb[NL80211_NAN_FUNC_SUBSCRIBE_ACTIVE]); + break; + case NL80211_NAN_FUNC_FOLLOW_UP: + if (!tb[NL80211_NAN_FUNC_FOLLOW_UP_ID] || + !tb[NL80211_NAN_FUNC_FOLLOW_UP_REQ_ID]) { + err = -EINVAL; + goto out; + } + + func->followup_id = + nla_get_u8(tb[NL80211_NAN_FUNC_FOLLOW_UP_ID]); + func->followup_reqid = + nla_get_u8(tb[NL80211_NAN_FUNC_FOLLOW_UP_REQ_ID]); + memcpy(func->followup_dest.addr, + nla_data(tb[NL80211_NAN_FUNC_FOLLOW_UP_DEST]), + sizeof(func->followup_dest.addr)); + if (func->ttl) { + err = -EINVAL; + goto out; + } + break; + default: + err = -EINVAL; + goto out; + } + + if (tb[NL80211_NAN_FUNC_SRF]) { + struct nlattr *srf_tb[NUM_NL80211_NAN_SRF_ATTR]; + + err = nla_parse(srf_tb, NL80211_NAN_SRF_ATTR_MAX, + nla_data(tb[NL80211_NAN_FUNC_SRF]), + nla_len(tb[NL80211_NAN_FUNC_SRF]), NULL); + if (err) + goto out; + + func->srf_include = + nla_get_flag(srf_tb[NL80211_NAN_SRF_INCLUDE]); + + if (srf_tb[NL80211_NAN_SRF_BF]) { + if (srf_tb[NL80211_NAN_SRF_MAC_ADDRS] || + !srf_tb[NL80211_NAN_SRF_BF_IDX]) { + err = -EINVAL; + goto out; + } + + func->srf_bf_len = + nla_len(srf_tb[NL80211_NAN_SRF_BF]); + func->srf_bf = + kmemdup(nla_data(srf_tb[NL80211_NAN_SRF_BF]), + func->srf_bf_len, GFP_KERNEL); + if (!func->srf_bf) { + err = -ENOMEM; + goto out; + } + + func->srf_bf_idx = + nla_get_u8(srf_tb[NL80211_NAN_SRF_BF_IDX]); + } else { + struct nlattr *attr, *mac_attr = + srf_tb[NL80211_NAN_SRF_MAC_ADDRS]; + int n_entries, rem, i = 0; + + if (!mac_attr) { + err = -EINVAL; + goto out; + } + + n_entries = validate_acl_mac_addrs(mac_attr); + if (n_entries <= 0) { + err = -EINVAL; + goto out; + } + + func->srf_num_macs = n_entries; + func->srf_macs = + kzalloc(sizeof(*func->srf_macs) * n_entries, + GFP_KERNEL); + if (!func->srf_macs) { + err = -ENOMEM; + goto out; + } + + nla_for_each_nested(attr, mac_attr, rem) + memcpy(func->srf_macs[i++].addr, nla_data(attr), + sizeof(*func->srf_macs)); + } + } + + if (tb[NL80211_NAN_FUNC_TX_MATCH_FILTER]) { + err = handle_nan_filter(tb[NL80211_NAN_FUNC_TX_MATCH_FILTER], + func, true); + if (err) + goto out; + } + + if (tb[NL80211_NAN_FUNC_RX_MATCH_FILTER]) { + err = handle_nan_filter(tb[NL80211_NAN_FUNC_RX_MATCH_FILTER], + func, false); + if (err) + goto out; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) { + err = -ENOMEM; + goto out; + } + + hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0, + NL80211_CMD_ADD_NAN_FUNCTION); + /* This can't really happen - we just allocated 4KB */ + if (WARN_ON(!hdr)) { + err = -ENOMEM; + goto out; + } + + err = rdev_add_nan_func(rdev, wdev, func); +out: + if (err < 0) { + cfg80211_free_nan_func(func); + nlmsg_free(msg); + return err; + } + + /* propagate the instance id and cookie to userspace */ + if (nla_put_u64_64bit(msg, NL80211_ATTR_COOKIE, func->cookie, + NL80211_ATTR_PAD)) + goto nla_put_failure; + + func_attr = nla_nest_start(msg, NL80211_ATTR_NAN_FUNC); + if (!func_attr) + goto nla_put_failure; + + if (nla_put_u8(msg, NL80211_NAN_FUNC_INSTANCE_ID, + func->instance_id)) + goto nla_put_failure; + + nla_nest_end(msg, func_attr); + + genlmsg_end(msg, hdr); + return genlmsg_reply(msg, info); + +nla_put_failure: + nlmsg_free(msg); + return -ENOBUFS; +} + +static int nl80211_nan_del_func(struct sk_buff *skb, + struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct wireless_dev *wdev = info->user_ptr[1]; + u64 cookie; + + if (wdev->iftype != NL80211_IFTYPE_NAN) + return -EOPNOTSUPP; + + if (!wdev->nan_started) + return -ENOTCONN; + + if (!info->attrs[NL80211_ATTR_COOKIE]) + return -EINVAL; + + if (wdev->owner_nlportid && + wdev->owner_nlportid != info->snd_portid) + return -ENOTCONN; + + cookie = nla_get_u64(info->attrs[NL80211_ATTR_COOKIE]); + + rdev_del_nan_func(rdev, wdev, cookie); + + return 0; +} + static int nl80211_get_protocol_features(struct sk_buff *skb, struct genl_info *info) { @@ -11923,6 +12276,22 @@ static const struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_ADD_NAN_FUNCTION, + .doit = nl80211_nan_add_func, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_WDEV_UP | + NL80211_FLAG_NEED_RTNL, + }, + { + .cmd = NL80211_CMD_DEL_NAN_FUNCTION, + .doit = nl80211_nan_del_func, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_WDEV_UP | + NL80211_FLAG_NEED_RTNL, + }, { .cmd = NL80211_CMD_SET_MCAST_RATE, .doit = nl80211_set_mcast_rate, diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index afb68a8428b9..98c4c3bdcb11 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -907,6 +907,27 @@ static inline void rdev_stop_nan(struct cfg80211_registered_device *rdev, trace_rdev_return_void(&rdev->wiphy); } +static inline int +rdev_add_nan_func(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + struct cfg80211_nan_func *nan_func) +{ + int ret; + + trace_rdev_add_nan_func(&rdev->wiphy, wdev, nan_func); + ret = rdev->ops->add_nan_func(&rdev->wiphy, wdev, nan_func); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline void rdev_del_nan_func(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, u64 cookie) +{ + trace_rdev_del_nan_func(&rdev->wiphy, wdev, cookie); + rdev->ops->del_nan_func(&rdev->wiphy, wdev, cookie); + trace_rdev_return_void(&rdev->wiphy); +} + static inline int rdev_set_mac_acl(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_acl_data *params) diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 5f3370f4c6a2..56089843d619 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1916,6 +1916,45 @@ DEFINE_EVENT(wiphy_wdev_evt, rdev_stop_nan, TP_ARGS(wiphy, wdev) ); +TRACE_EVENT(rdev_add_nan_func, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, + const struct cfg80211_nan_func *func), + TP_ARGS(wiphy, wdev, func), + TP_STRUCT__entry( + WIPHY_ENTRY + WDEV_ENTRY + __field(u8, func_type) + __field(u64, cookie) + ), + TP_fast_assign( + WIPHY_ASSIGN; + WDEV_ASSIGN; + __entry->func_type = func->type; + __entry->cookie = func->cookie + ), + TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT ", type=%u, cookie=%llu", + WIPHY_PR_ARG, WDEV_PR_ARG, __entry->func_type, + __entry->cookie) +); + +TRACE_EVENT(rdev_del_nan_func, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, + u64 cookie), + TP_ARGS(wiphy, wdev, cookie), + TP_STRUCT__entry( + WIPHY_ENTRY + WDEV_ENTRY + __field(u64, cookie) + ), + TP_fast_assign( + WIPHY_ASSIGN; + WDEV_ASSIGN; + __entry->cookie = cookie; + ), + TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT ", cookie=%llu", + WIPHY_PR_ARG, WDEV_PR_ARG, __entry->cookie) +); + TRACE_EVENT(rdev_set_mac_acl, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, struct cfg80211_acl_data *params), diff --git a/net/wireless/util.c b/net/wireless/util.c index 7a2d46b0058a..8edce22d1b93 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1762,6 +1762,28 @@ int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr, } EXPORT_SYMBOL(cfg80211_get_station); +void cfg80211_free_nan_func(struct cfg80211_nan_func *f) +{ + int i; + + if (!f) + return; + + kfree(f->serv_spec_info); + kfree(f->srf_bf); + kfree(f->srf_macs); + for (i = 0; i < f->num_rx_filters; i++) + kfree(f->rx_filters[i].filter); + + for (i = 0; i < f->num_tx_filters; i++) + kfree(f->tx_filters[i].filter); + + kfree(f->rx_filters); + kfree(f->tx_filters); + kfree(f); +} +EXPORT_SYMBOL(cfg80211_free_nan_func); + /* See IEEE 802.1H for LLC/SNAP encapsulation/decapsulation */ /* Ethernet-II snap header (RFC1042 for most EtherTypes) */ const unsigned char rfc1042_header[] __aligned(2) = -- cgit v1.2.3 From a5a9dcf291e1e541243878eed2d73a74006fa1f1 Mon Sep 17 00:00:00 2001 From: Ayala Beker Date: Tue, 20 Sep 2016 17:31:16 +0300 Subject: cfg80211: allow the user space to change current NAN configuration Some NAN configuration paramaters may change during the operation of the NAN device. For example, a user may want to update master preference value when the device gets plugged/unplugged to the power. Add API that allows to do so. Signed-off-by: Andrei Otcheretianski Signed-off-by: Emmanuel Grumbach Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 19 +++++++++++++++++++ include/uapi/linux/nl80211.h | 11 +++++++++-- net/wireless/nl80211.c | 42 ++++++++++++++++++++++++++++++++++++++++++ net/wireless/rdev-ops.h | 17 +++++++++++++++++ net/wireless/trace.h | 24 ++++++++++++++++++++++++ 5 files changed, 111 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 2f35ccf6da83..8574a57e19ba 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2326,6 +2326,18 @@ struct cfg80211_nan_conf { u8 dual; }; +/** + * enum cfg80211_nan_conf_changes - indicates changed fields in NAN + * configuration + * + * @CFG80211_NAN_CONF_CHANGED_PREF: master preference + * @CFG80211_NAN_CONF_CHANGED_DUAL: dual band operation + */ +enum cfg80211_nan_conf_changes { + CFG80211_NAN_CONF_CHANGED_PREF = BIT(0), + CFG80211_NAN_CONF_CHANGED_DUAL = BIT(1), +}; + /** * struct cfg80211_nan_func_filter - a NAN function Rx / Tx filter * @@ -2691,6 +2703,9 @@ struct cfg80211_nan_func { * On success the driver should assign an instance_id in the * provided @nan_func. * @del_nan_func: Delete a NAN function. + * @nan_change_conf: changes NAN configuration. The changed parameters must + * be specified in @changes (using &enum cfg80211_nan_conf_changes); + * All other parameters must be ignored. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -2963,6 +2978,10 @@ struct cfg80211_ops { struct cfg80211_nan_func *nan_func); void (*del_nan_func)(struct wiphy *wiphy, struct wireless_dev *wdev, u64 cookie); + int (*nan_change_conf)(struct wiphy *wiphy, + struct wireless_dev *wdev, + struct cfg80211_nan_conf *conf, + u32 changes); }; /* diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index e4935d963061..9c9c0c352873 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -862,6 +862,10 @@ * the response to this command. * Look at %NL80211_ATTR_SOCKET_OWNER as well. * @NL80211_CMD_DEL_NAN_FUNCTION: Delete a NAN function by cookie. + * @NL80211_CMD_CHANGE_NAN_CONFIG: Change current NAN configuration. NAN + * must be operational (%NL80211_CMD_START_NAN was executed). + * It must contain at least one of the following attributes: + * %NL80211_ATTR_NAN_MASTER_PREF, %NL80211_ATTR_NAN_DUAL. * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use @@ -1055,6 +1059,7 @@ enum nl80211_commands { NL80211_CMD_STOP_NAN, NL80211_CMD_ADD_NAN_FUNCTION, NL80211_CMD_DEL_NAN_FUNCTION, + NL80211_CMD_CHANGE_NAN_CONFIG, /* add new commands above here */ @@ -1910,12 +1915,14 @@ enum nl80211_commands { * used to pull the stored data for mesh peer in power save state. * * @NL80211_ATTR_NAN_MASTER_PREF: the master preference to be used by - * %NL80211_CMD_START_NAN. Its type is u8 and it can't be 0. + * %NL80211_CMD_START_NAN and optionally with + * %NL80211_CMD_CHANGE_NAN_CONFIG. Its type is u8 and it can't be 0. * Also, values 1 and 255 are reserved for certification purposes and * should not be used during a normal device operation. * @NL80211_ATTR_NAN_DUAL: NAN dual band operation config (see * &enum nl80211_nan_dual_band_conf). This attribute is used with - * %NL80211_CMD_START_NAN. + * %NL80211_CMD_START_NAN and optionally with + * %NL80211_CMD_CHANGE_NAN_CONFIG. * @NL80211_ATTR_NAN_FUNC: a function that can be added to NAN. See * &enum nl80211_nan_func_attributes for description of this nested * attribute. diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0eca59ccd685..c0b5ae4af2d8 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -10919,6 +10919,40 @@ static int nl80211_nan_del_func(struct sk_buff *skb, return 0; } +static int nl80211_nan_change_config(struct sk_buff *skb, + struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct wireless_dev *wdev = info->user_ptr[1]; + struct cfg80211_nan_conf conf = {}; + u32 changed = 0; + + if (wdev->iftype != NL80211_IFTYPE_NAN) + return -EOPNOTSUPP; + + if (!wdev->nan_started) + return -ENOTCONN; + + if (info->attrs[NL80211_ATTR_NAN_MASTER_PREF]) { + conf.master_pref = + nla_get_u8(info->attrs[NL80211_ATTR_NAN_MASTER_PREF]); + if (conf.master_pref <= 1 || conf.master_pref == 255) + return -EINVAL; + + changed |= CFG80211_NAN_CONF_CHANGED_PREF; + } + + if (info->attrs[NL80211_ATTR_NAN_DUAL]) { + conf.dual = nla_get_u8(info->attrs[NL80211_ATTR_NAN_DUAL]); + changed |= CFG80211_NAN_CONF_CHANGED_DUAL; + } + + if (!changed) + return -EINVAL; + + return rdev_nan_change_conf(rdev, wdev, &conf, changed); +} + static int nl80211_get_protocol_features(struct sk_buff *skb, struct genl_info *info) { @@ -12292,6 +12326,14 @@ static const struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_CHANGE_NAN_CONFIG, + .doit = nl80211_nan_change_config, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_WDEV_UP | + NL80211_FLAG_NEED_RTNL, + }, { .cmd = NL80211_CMD_SET_MCAST_RATE, .doit = nl80211_set_mcast_rate, diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 98c4c3bdcb11..11cf83c8ad4f 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -928,6 +928,23 @@ static inline void rdev_del_nan_func(struct cfg80211_registered_device *rdev, trace_rdev_return_void(&rdev->wiphy); } +static inline int +rdev_nan_change_conf(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + struct cfg80211_nan_conf *conf, u32 changes) +{ + int ret; + + trace_rdev_nan_change_conf(&rdev->wiphy, wdev, conf, changes); + if (rdev->ops->nan_change_conf) + ret = rdev->ops->nan_change_conf(&rdev->wiphy, wdev, conf, + changes); + else + ret = -ENOTSUPP; + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + static inline int rdev_set_mac_acl(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_acl_data *params) diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 56089843d619..a3d0a91b1e09 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1911,6 +1911,30 @@ TRACE_EVENT(rdev_start_nan, __entry->dual) ); +TRACE_EVENT(rdev_nan_change_conf, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, + struct cfg80211_nan_conf *conf, u32 changes), + TP_ARGS(wiphy, wdev, conf, changes), + TP_STRUCT__entry( + WIPHY_ENTRY + WDEV_ENTRY + __field(u8, master_pref) + __field(u8, dual); + __field(u32, changes); + ), + TP_fast_assign( + WIPHY_ASSIGN; + WDEV_ASSIGN; + __entry->master_pref = conf->master_pref; + __entry->dual = conf->dual; + __entry->changes = changes; + ), + TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT + ", master preference: %u, dual: %d, changes: %x", + WIPHY_PR_ARG, WDEV_PR_ARG, __entry->master_pref, + __entry->dual, __entry->changes) +); + DEFINE_EVENT(wiphy_wdev_evt, rdev_stop_nan, TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev), TP_ARGS(wiphy, wdev) -- cgit v1.2.3 From 50bcd31d9992e99c231820f5276e70346cbfbc51 Mon Sep 17 00:00:00 2001 From: Ayala Beker Date: Tue, 20 Sep 2016 17:31:17 +0300 Subject: cfg80211: provide a function to report a match for NAN Provide a function the driver can call to report a match. This will send the event to the user space. If the NAN instance is tied to the owner, the notifications will be sent to the socket that started the NAN interface only. Signed-off-by: Andrei Otcheretianski Signed-off-by: Emmanuel Grumbach Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 37 ++++++++++++++++++++ include/uapi/linux/nl80211.h | 31 +++++++++++++++++ net/wireless/nl80211.c | 80 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 148 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 8574a57e19ba..5481664b5389 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5694,6 +5694,43 @@ wiphy_ext_feature_isset(struct wiphy *wiphy, */ void cfg80211_free_nan_func(struct cfg80211_nan_func *f); +/** + * struct cfg80211_nan_match_params - NAN match parameters + * @type: the type of the function that triggered a match. If it is + * %NL80211_NAN_FUNC_SUBSCRIBE it means that we replied to a subscriber. + * If it is %NL80211_NAN_FUNC_PUBLISH, it means that we got a discovery + * result. + * If it is %NL80211_NAN_FUNC_FOLLOW_UP, we received a follow up. + * @inst_id: the local instance id + * @peer_inst_id: the instance id of the peer's function + * @addr: the MAC address of the peer + * @info_len: the length of the &info + * @info: the Service Specific Info from the peer (if any) + * @cookie: unique identifier of the corresponding function + */ +struct cfg80211_nan_match_params { + enum nl80211_nan_function_type type; + u8 inst_id; + u8 peer_inst_id; + const u8 *addr; + u8 info_len; + const u8 *info; + u64 cookie; +}; + +/** + * cfg80211_nan_match - report a match for a NAN function. + * @wdev: the wireless device reporting the match + * @match: match notification parameters + * @gfp: allocation flags + * + * This function reports that the a NAN function had a match. This + * can be a subscribe that had a match or a solicited publish that + * was sent. It can also be a follow up that was received. + */ +void cfg80211_nan_match(struct wireless_dev *wdev, + struct cfg80211_nan_match_params *match, gfp_t gfp); + /* ethtool helper */ void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info); diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 9c9c0c352873..995bf802d604 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -48,6 +48,7 @@ #define NL80211_MULTICAST_GROUP_REG "regulatory" #define NL80211_MULTICAST_GROUP_MLME "mlme" #define NL80211_MULTICAST_GROUP_VENDOR "vendor" +#define NL80211_MULTICAST_GROUP_NAN "nan" #define NL80211_MULTICAST_GROUP_TESTMODE "testmode" /** @@ -866,6 +867,9 @@ * must be operational (%NL80211_CMD_START_NAN was executed). * It must contain at least one of the following attributes: * %NL80211_ATTR_NAN_MASTER_PREF, %NL80211_ATTR_NAN_DUAL. + * @NL80211_CMD_NAN_FUNC_MATCH: Notification sent when a match is reported. + * This will contain a %NL80211_ATTR_NAN_MATCH nested attribute and + * %NL80211_ATTR_COOKIE. * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use @@ -1060,6 +1064,7 @@ enum nl80211_commands { NL80211_CMD_ADD_NAN_FUNCTION, NL80211_CMD_DEL_NAN_FUNCTION, NL80211_CMD_CHANGE_NAN_CONFIG, + NL80211_CMD_NAN_MATCH, /* add new commands above here */ @@ -1926,6 +1931,8 @@ enum nl80211_commands { * @NL80211_ATTR_NAN_FUNC: a function that can be added to NAN. See * &enum nl80211_nan_func_attributes for description of this nested * attribute. + * @NL80211_ATTR_NAN_MATCH: used to report a match. This is a nested attribute. + * See &enum nl80211_nan_match_attributes. * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined @@ -2324,6 +2331,7 @@ enum nl80211_attrs { NL80211_ATTR_NAN_MASTER_PREF, NL80211_ATTR_NAN_DUAL, NL80211_ATTR_NAN_FUNC, + NL80211_ATTR_NAN_MATCH, /* add attributes here, update the policy in nl80211.c */ @@ -5074,4 +5082,27 @@ enum nl80211_nan_srf_attributes { NL80211_NAN_SRF_ATTR_MAX = NUM_NL80211_NAN_SRF_ATTR - 1, }; +/** + * enum nl80211_nan_match_attributes - NAN match attributes + * @__NL80211_NAN_MATCH_INVALID: invalid + * @NL80211_NAN_MATCH_FUNC_LOCAL: the local function that had the + * match. This is a nested attribute. + * See &enum nl80211_nan_func_attributes. + * @NL80211_NAN_MATCH_FUNC_PEER: the peer function + * that caused the match. This is a nested attribute. + * See &enum nl80211_nan_func_attributes. + * + * @NUM_NL80211_NAN_MATCH_ATTR: internal + * @NL80211_NAN_MATCH_ATTR_MAX: highest NAN match attribute + */ +enum nl80211_nan_match_attributes { + __NL80211_NAN_MATCH_INVALID, + NL80211_NAN_MATCH_FUNC_LOCAL, + NL80211_NAN_MATCH_FUNC_PEER, + + /* keep last */ + NUM_NL80211_NAN_MATCH_ATTR, + NL80211_NAN_MATCH_ATTR_MAX = NUM_NL80211_NAN_MATCH_ATTR - 1 +}; + #endif /* __LINUX_NL80211_H */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c0b5ae4af2d8..0bbd9ed28318 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -56,6 +56,7 @@ enum nl80211_multicast_groups { NL80211_MCGRP_REGULATORY, NL80211_MCGRP_MLME, NL80211_MCGRP_VENDOR, + NL80211_MCGRP_NAN, NL80211_MCGRP_TESTMODE /* keep last - ifdef! */ }; @@ -65,6 +66,7 @@ static const struct genl_multicast_group nl80211_mcgrps[] = { [NL80211_MCGRP_REGULATORY] = { .name = NL80211_MULTICAST_GROUP_REG }, [NL80211_MCGRP_MLME] = { .name = NL80211_MULTICAST_GROUP_MLME }, [NL80211_MCGRP_VENDOR] = { .name = NL80211_MULTICAST_GROUP_VENDOR }, + [NL80211_MCGRP_NAN] = { .name = NL80211_MULTICAST_GROUP_NAN }, #ifdef CONFIG_NL80211_TESTMODE [NL80211_MCGRP_TESTMODE] = { .name = NL80211_MULTICAST_GROUP_TESTMODE } #endif @@ -10953,6 +10955,84 @@ static int nl80211_nan_change_config(struct sk_buff *skb, return rdev_nan_change_conf(rdev, wdev, &conf, changed); } +void cfg80211_nan_match(struct wireless_dev *wdev, + struct cfg80211_nan_match_params *match, gfp_t gfp) +{ + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + struct nlattr *match_attr, *local_func_attr, *peer_func_attr; + struct sk_buff *msg; + void *hdr; + + if (WARN_ON(!match->inst_id || !match->peer_inst_id || !match->addr)) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_NAN_MATCH); + if (!hdr) { + nlmsg_free(msg); + return; + } + + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + (wdev->netdev && nla_put_u32(msg, NL80211_ATTR_IFINDEX, + wdev->netdev->ifindex)) || + nla_put_u64_64bit(msg, NL80211_ATTR_WDEV, wdev_id(wdev), + NL80211_ATTR_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(msg, NL80211_ATTR_COOKIE, match->cookie, + NL80211_ATTR_PAD) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, match->addr)) + goto nla_put_failure; + + match_attr = nla_nest_start(msg, NL80211_ATTR_NAN_MATCH); + if (!match_attr) + goto nla_put_failure; + + local_func_attr = nla_nest_start(msg, NL80211_NAN_MATCH_FUNC_LOCAL); + if (!local_func_attr) + goto nla_put_failure; + + if (nla_put_u8(msg, NL80211_NAN_FUNC_INSTANCE_ID, match->inst_id)) + goto nla_put_failure; + + nla_nest_end(msg, local_func_attr); + + peer_func_attr = nla_nest_start(msg, NL80211_NAN_MATCH_FUNC_PEER); + if (!peer_func_attr) + goto nla_put_failure; + + if (nla_put_u8(msg, NL80211_NAN_FUNC_TYPE, match->type) || + nla_put_u8(msg, NL80211_NAN_FUNC_INSTANCE_ID, match->peer_inst_id)) + goto nla_put_failure; + + if (match->info && match->info_len && + nla_put(msg, NL80211_NAN_FUNC_SERVICE_INFO, match->info_len, + match->info)) + goto nla_put_failure; + + nla_nest_end(msg, peer_func_attr); + nla_nest_end(msg, match_attr); + genlmsg_end(msg, hdr); + + if (!wdev->owner_nlportid) + genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), + msg, 0, NL80211_MCGRP_NAN, gfp); + else + genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, + wdev->owner_nlportid); + + return; + +nla_put_failure: + nlmsg_free(msg); +} +EXPORT_SYMBOL(cfg80211_nan_match); + static int nl80211_get_protocol_features(struct sk_buff *skb, struct genl_info *info) { -- cgit v1.2.3 From 368e5a7b4ecb71b3d347799cb9351b0dce5dec70 Mon Sep 17 00:00:00 2001 From: Ayala Beker Date: Tue, 20 Sep 2016 17:31:18 +0300 Subject: cfg80211: Provide an API to report NAN function termination Provide a function that reports NAN DE function termination. The function may be terminated due to one of the following reasons: user request, ttl expiration or failure. If the NAN instance is tied to the owner, the notification will be sent to the socket that started the NAN interface only Signed-off-by: Andrei Otcheretianski Signed-off-by: Emmanuel Grumbach Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 16 ++++++++++++ include/uapi/linux/nl80211.h | 18 +++++++++++++ net/wireless/nl80211.c | 60 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 94 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5481664b5389..fe78f02a242e 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5731,6 +5731,22 @@ struct cfg80211_nan_match_params { void cfg80211_nan_match(struct wireless_dev *wdev, struct cfg80211_nan_match_params *match, gfp_t gfp); +/** + * cfg80211_nan_func_terminated - notify about NAN function termination. + * + * @wdev: the wireless device reporting the match + * @inst_id: the local instance id + * @reason: termination reason (one of the NL80211_NAN_FUNC_TERM_REASON_*) + * @cookie: unique NAN function identifier + * @gfp: allocation flags + * + * This function reports that the a NAN function is terminated. + */ +void cfg80211_nan_func_terminated(struct wireless_dev *wdev, + u8 inst_id, + enum nl80211_nan_func_term_reason reason, + u64 cookie, gfp_t gfp); + /* ethtool helper */ void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info); diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 995bf802d604..56368e9b4622 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -863,6 +863,9 @@ * the response to this command. * Look at %NL80211_ATTR_SOCKET_OWNER as well. * @NL80211_CMD_DEL_NAN_FUNCTION: Delete a NAN function by cookie. + * This command is also used as a notification sent when a NAN function is + * terminated. This will contain a %NL80211_ATTR_NAN_FUNC_INST_ID + * and %NL80211_ATTR_COOKIE attributes. * @NL80211_CMD_CHANGE_NAN_CONFIG: Change current NAN configuration. NAN * must be operational (%NL80211_CMD_START_NAN was executed). * It must contain at least one of the following attributes: @@ -4985,6 +4988,21 @@ enum nl80211_nan_publish_type { NL80211_NAN_UNSOLICITED_PUBLISH = 1 << 1, }; +/** + * enum nl80211_nan_func_term_reason - NAN functions termination reason + * + * Defines termination reasons of a NAN function + * + * @NL80211_NAN_FUNC_TERM_REASON_USER_REQUEST: requested by user + * @NL80211_NAN_FUNC_TERM_REASON_TTL_EXPIRED: timeout + * @NL80211_NAN_FUNC_TERM_REASON_ERROR: errored + */ +enum nl80211_nan_func_term_reason { + NL80211_NAN_FUNC_TERM_REASON_USER_REQUEST, + NL80211_NAN_FUNC_TERM_REASON_TTL_EXPIRED, + NL80211_NAN_FUNC_TERM_REASON_ERROR, +}; + #define NL80211_NAN_FUNC_SERVICE_ID_LEN 6 #define NL80211_NAN_FUNC_SERVICE_SPEC_INFO_MAX_LEN 0xff #define NL80211_NAN_FUNC_SRF_MAX_LEN 0xff diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0bbd9ed28318..92eb6f0b9f3d 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -11033,6 +11033,66 @@ nla_put_failure: } EXPORT_SYMBOL(cfg80211_nan_match); +void cfg80211_nan_func_terminated(struct wireless_dev *wdev, + u8 inst_id, + enum nl80211_nan_func_term_reason reason, + u64 cookie, gfp_t gfp) +{ + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + struct sk_buff *msg; + struct nlattr *func_attr; + void *hdr; + + if (WARN_ON(!inst_id)) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_DEL_NAN_FUNCTION); + if (!hdr) { + nlmsg_free(msg); + return; + } + + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + (wdev->netdev && nla_put_u32(msg, NL80211_ATTR_IFINDEX, + wdev->netdev->ifindex)) || + nla_put_u64_64bit(msg, NL80211_ATTR_WDEV, wdev_id(wdev), + NL80211_ATTR_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(msg, NL80211_ATTR_COOKIE, cookie, + NL80211_ATTR_PAD)) + goto nla_put_failure; + + func_attr = nla_nest_start(msg, NL80211_ATTR_NAN_FUNC); + if (!func_attr) + goto nla_put_failure; + + if (nla_put_u8(msg, NL80211_NAN_FUNC_INSTANCE_ID, inst_id) || + nla_put_u8(msg, NL80211_NAN_FUNC_TERM_REASON, reason)) + goto nla_put_failure; + + nla_nest_end(msg, func_attr); + genlmsg_end(msg, hdr); + + if (!wdev->owner_nlportid) + genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), + msg, 0, NL80211_MCGRP_NAN, gfp); + else + genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, + wdev->owner_nlportid); + + return; + +nla_put_failure: + nlmsg_free(msg); +} +EXPORT_SYMBOL(cfg80211_nan_func_terminated); + static int nl80211_get_protocol_features(struct sk_buff *skb, struct genl_info *info) { -- cgit v1.2.3 From 5e940c1dd3c1f7561924954eecee956ec277a79b Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Sat, 1 Oct 2016 07:32:32 +0200 Subject: fuse: handle killpriv in userspace fs Only userspace filesystem can do the killing of suid/sgid without races. So introduce an INIT flag and negotiate support for this. Signed-off-by: Miklos Szeredi --- fs/fuse/dir.c | 44 +++++++++++++++++++++++++++----------------- fs/fuse/fuse_i.h | 3 +++ fs/fuse/inode.c | 4 +++- include/uapi/linux/fuse.h | 7 ++++++- 4 files changed, 39 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index b7a690ed6a75..7cb68b18eb3f 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1703,6 +1703,7 @@ error: static int fuse_setattr(struct dentry *entry, struct iattr *attr) { struct inode *inode = d_inode(entry); + struct fuse_conn *fc = get_fuse_conn(inode); struct file *file = (attr->ia_valid & ATTR_FILE) ? attr->ia_file : NULL; int ret; @@ -1710,27 +1711,36 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr) return -EACCES; if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) { - int kill; - attr->ia_valid &= ~(ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_MODE); + /* - * ia_mode calculation may have used stale i_mode. Refresh and - * recalculate. + * The only sane way to reliably kill suid/sgid is to do it in + * the userspace filesystem + * + * This should be done on write(), truncate() and chown(). */ - ret = fuse_do_getattr(inode, NULL, file); - if (ret) - return ret; - - attr->ia_mode = inode->i_mode; - kill = should_remove_suid(entry); - if (kill & ATTR_KILL_SUID) { - attr->ia_valid |= ATTR_MODE; - attr->ia_mode &= ~S_ISUID; - } - if (kill & ATTR_KILL_SGID) { - attr->ia_valid |= ATTR_MODE; - attr->ia_mode &= ~S_ISGID; + if (!fc->handle_killpriv) { + int kill; + + /* + * ia_mode calculation may have used stale i_mode. + * Refresh and recalculate. + */ + ret = fuse_do_getattr(inode, NULL, file); + if (ret) + return ret; + + attr->ia_mode = inode->i_mode; + kill = should_remove_suid(entry); + if (kill & ATTR_KILL_SUID) { + attr->ia_valid |= ATTR_MODE; + attr->ia_mode &= ~S_ISUID; + } + if (kill & ATTR_KILL_SGID) { + attr->ia_valid |= ATTR_MODE; + attr->ia_mode &= ~S_ISGID; + } } } if (!attr->ia_valid) diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 6db54d0bd81b..9940a648c985 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -547,6 +547,9 @@ struct fuse_conn { /** allow parallel lookups and readdir (default is serialized) */ unsigned parallel_dirops:1; + /** handle fs handles killing suid/sgid/cap on write/chown/trunc */ + unsigned handle_killpriv:1; + /* * The following bitfields are only for optimization purposes * and hence races in setting them will not cause malfunction diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 1e535f31fed0..b965934939cb 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -910,6 +910,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) fc->writeback_cache = 1; if (arg->flags & FUSE_PARALLEL_DIROPS) fc->parallel_dirops = 1; + if (arg->flags & FUSE_HANDLE_KILLPRIV) + fc->handle_killpriv = 1; if (arg->time_gran && arg->time_gran <= 1000000000) fc->sb->s_time_gran = arg->time_gran; } else { @@ -941,7 +943,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) FUSE_FLOCK_LOCKS | FUSE_HAS_IOCTL_DIR | FUSE_AUTO_INVAL_DATA | FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO | FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT | - FUSE_PARALLEL_DIROPS; + FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV; req->in.h.opcode = FUSE_INIT; req->in.numargs = 1; req->in.args[0].size = sizeof(*arg); diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 27e17363263a..14ca2f10d354 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -108,6 +108,9 @@ * * 7.25 * - add FUSE_PARALLEL_DIROPS + * + * 7.26 + * - add FUSE_HANDLE_KILLPRIV */ #ifndef _LINUX_FUSE_H @@ -143,7 +146,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 25 +#define FUSE_KERNEL_MINOR_VERSION 26 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -238,6 +241,7 @@ struct fuse_file_lock { * FUSE_WRITEBACK_CACHE: use writeback cache for buffered writes * FUSE_NO_OPEN_SUPPORT: kernel supports zero-message opens * FUSE_PARALLEL_DIROPS: allow parallel lookups and readdir + * FUSE_HANDLE_KILLPRIV: fs handles killing suid/sgid/cap on write/chown/trunc */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -258,6 +262,7 @@ struct fuse_file_lock { #define FUSE_WRITEBACK_CACHE (1 << 16) #define FUSE_NO_OPEN_SUPPORT (1 << 17) #define FUSE_PARALLEL_DIROPS (1 << 18) +#define FUSE_HANDLE_KILLPRIV (1 << 19) /** * CUSE INIT request/reply flags -- cgit v1.2.3 From 60bcc88ad185d512f5718f2f8dcccb483ea8fb73 Mon Sep 17 00:00:00 2001 From: Seth Forshee Date: Mon, 29 Aug 2016 08:46:37 -0500 Subject: fuse: Add posix ACL support Add a new INIT flag, FUSE_POSIX_ACL, for negotiating ACL support with userspace. When it is set in the INIT response, ACL support will be enabled. ACL support also implies "default_permissions". When ACL support is enabled, the kernel will cache and have responsibility for enforcing ACLs. ACL xattrs will be passed to userspace, which is responsible for updating the ACLs in the filesystem, keeping the file mode in sync, and inheritance of default ACLs when new filesystem nodes are created. Signed-off-by: Seth Forshee Signed-off-by: Miklos Szeredi --- fs/fuse/Kconfig | 1 + fs/fuse/Makefile | 2 +- fs/fuse/acl.c | 99 +++++++++++++++++++++++++++++++++++++++++++++++ fs/fuse/dir.c | 16 ++++++++ fs/fuse/fuse_i.h | 14 +++++++ fs/fuse/inode.c | 9 ++++- fs/fuse/xattr.c | 18 ++++++--- include/uapi/linux/fuse.h | 3 ++ 8 files changed, 155 insertions(+), 7 deletions(-) create mode 100644 fs/fuse/acl.c (limited to 'include/uapi/linux') diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig index 1b2f6c2c3aaf..76f09ce7e5b2 100644 --- a/fs/fuse/Kconfig +++ b/fs/fuse/Kconfig @@ -1,5 +1,6 @@ config FUSE_FS tristate "FUSE (Filesystem in Userspace) support" + select FS_POSIX_ACL help With FUSE it is possible to implement a fully functional filesystem in a userspace program. diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile index 448aa27ada00..60da84a86dab 100644 --- a/fs/fuse/Makefile +++ b/fs/fuse/Makefile @@ -5,4 +5,4 @@ obj-$(CONFIG_FUSE_FS) += fuse.o obj-$(CONFIG_CUSE) += cuse.o -fuse-objs := dev.o dir.o file.o inode.o control.o xattr.o +fuse-objs := dev.o dir.o file.o inode.o control.o xattr.o acl.o diff --git a/fs/fuse/acl.c b/fs/fuse/acl.c new file mode 100644 index 000000000000..ec85765502f1 --- /dev/null +++ b/fs/fuse/acl.c @@ -0,0 +1,99 @@ +/* + * FUSE: Filesystem in Userspace + * Copyright (C) 2016 Canonical Ltd. + * + * This program can be distributed under the terms of the GNU GPL. + * See the file COPYING. + */ + +#include "fuse_i.h" + +#include +#include + +struct posix_acl *fuse_get_acl(struct inode *inode, int type) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + int size; + const char *name; + void *value = NULL; + struct posix_acl *acl; + + if (!fc->posix_acl || fc->no_getxattr) + return NULL; + + if (type == ACL_TYPE_ACCESS) + name = XATTR_NAME_POSIX_ACL_ACCESS; + else if (type == ACL_TYPE_DEFAULT) + name = XATTR_NAME_POSIX_ACL_DEFAULT; + else + return ERR_PTR(-EOPNOTSUPP); + + value = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!value) + return ERR_PTR(-ENOMEM); + size = fuse_getxattr(inode, name, value, PAGE_SIZE); + if (size > 0) + acl = posix_acl_from_xattr(&init_user_ns, value, size); + else if ((size == 0) || (size == -ENODATA) || + (size == -EOPNOTSUPP && fc->no_getxattr)) + acl = NULL; + else if (size == -ERANGE) + acl = ERR_PTR(-E2BIG); + else + acl = ERR_PTR(size); + + kfree(value); + return acl; +} + +int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + const char *name; + int ret; + + if (!fc->posix_acl || fc->no_setxattr) + return -EOPNOTSUPP; + + if (type == ACL_TYPE_ACCESS) + name = XATTR_NAME_POSIX_ACL_ACCESS; + else if (type == ACL_TYPE_DEFAULT) + name = XATTR_NAME_POSIX_ACL_DEFAULT; + else + return -EINVAL; + + if (acl) { + /* + * Fuse userspace is responsible for updating access + * permissions in the inode, if needed. fuse_setxattr + * invalidates the inode attributes, which will force + * them to be refreshed the next time they are used, + * and it also updates i_ctime. + */ + size_t size = posix_acl_xattr_size(acl->a_count); + void *value; + + if (size > PAGE_SIZE) + return -E2BIG; + + value = kmalloc(size, GFP_KERNEL); + if (!value) + return -ENOMEM; + + ret = posix_acl_to_xattr(&init_user_ns, acl, value, size); + if (ret < 0) { + kfree(value); + return ret; + } + + ret = fuse_setxattr(inode, name, value, size, 0); + kfree(value); + } else { + ret = fuse_removexattr(inode, name); + } + forget_all_cached_acls(inode); + fuse_invalidate_attr(inode); + + return ret; +} diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 7cb68b18eb3f..3076f48d86a6 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -14,6 +14,7 @@ #include #include #include +#include static bool fuse_use_readdirplus(struct inode *dir, struct dir_context *ctx) { @@ -244,6 +245,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) if (ret || (outarg.attr.mode ^ inode->i_mode) & S_IFMT) goto invalid; + forget_all_cached_acls(inode); fuse_change_attributes(inode, &outarg.attr, entry_attr_timeout(&outarg), attr_version); @@ -918,6 +920,7 @@ int fuse_update_attributes(struct inode *inode, struct kstat *stat, if (time_before64(fi->i_time, get_jiffies_64())) { r = true; + forget_all_cached_acls(inode); err = fuse_do_getattr(inode, stat, file); } else { r = false; @@ -1065,6 +1068,7 @@ static int fuse_perm_getattr(struct inode *inode, int mask) if (mask & MAY_NOT_BLOCK) return -ECHILD; + forget_all_cached_acls(inode); return fuse_do_getattr(inode, NULL, NULL); } @@ -1234,6 +1238,7 @@ retry: fi->nlookup++; spin_unlock(&fc->lock); + forget_all_cached_acls(inode); fuse_change_attributes(inode, &o->attr, entry_attr_timeout(o), attr_version); @@ -1748,6 +1753,13 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr) ret = fuse_do_setattr(inode, attr, file); if (!ret) { + /* + * If filesystem supports acls it may have updated acl xattrs in + * the filesystem, so forget cached acls for the inode. + */ + if (fc->posix_acl) + forget_all_cached_acls(inode); + /* Directory mode changed, may need to revalidate access */ if (d_is_dir(entry) && (attr->ia_valid & ATTR_MODE)) fuse_invalidate_entry_cache(entry); @@ -1785,6 +1797,8 @@ static const struct inode_operations fuse_dir_inode_operations = { .getxattr = generic_getxattr, .listxattr = fuse_listxattr, .removexattr = generic_removexattr, + .get_acl = fuse_get_acl, + .set_acl = fuse_set_acl, }; static const struct file_operations fuse_dir_operations = { @@ -1806,6 +1820,8 @@ static const struct inode_operations fuse_common_inode_operations = { .getxattr = generic_getxattr, .listxattr = fuse_listxattr, .removexattr = generic_removexattr, + .get_acl = fuse_get_acl, + .set_acl = fuse_set_acl, }; static const struct inode_operations fuse_symlink_inode_operations = { diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 9940a648c985..e8d96ec22533 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -23,6 +23,7 @@ #include #include #include +#include /** Max number of pages that can be used in a single read request */ #define FUSE_MAX_PAGES_PER_REQ 32 @@ -627,6 +628,9 @@ struct fuse_conn { /** Is lseek not implemented by fs? */ unsigned no_lseek:1; + /** Does the filesystem support posix acls? */ + unsigned posix_acl:1; + /** The number of requests waiting for completion */ atomic_t num_waiting; @@ -971,7 +975,17 @@ void fuse_set_initialized(struct fuse_conn *fc); void fuse_unlock_inode(struct inode *inode); void fuse_lock_inode(struct inode *inode); +int fuse_setxattr(struct inode *inode, const char *name, const void *value, + size_t size, int flags); +ssize_t fuse_getxattr(struct inode *inode, const char *name, void *value, + size_t size); ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size); +int fuse_removexattr(struct inode *inode, const char *name); extern const struct xattr_handler *fuse_xattr_handlers[]; +extern const struct xattr_handler *fuse_acl_xattr_handlers[]; + +struct posix_acl; +struct posix_acl *fuse_get_acl(struct inode *inode, int type); +int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type); #endif /* _FS_FUSE_I_H */ diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index b965934939cb..16ac9d86c507 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -20,6 +20,7 @@ #include #include #include +#include MODULE_AUTHOR("Miklos Szeredi "); MODULE_DESCRIPTION("Filesystem in Userspace"); @@ -340,6 +341,7 @@ int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid, return -ENOENT; fuse_invalidate_attr(inode); + forget_all_cached_acls(inode); if (offset >= 0) { pg_start = offset >> PAGE_SHIFT; if (len <= 0) @@ -914,6 +916,11 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) fc->handle_killpriv = 1; if (arg->time_gran && arg->time_gran <= 1000000000) fc->sb->s_time_gran = arg->time_gran; + if ((arg->flags & FUSE_POSIX_ACL)) { + fc->flags |= FUSE_DEFAULT_PERMISSIONS; + fc->posix_acl = 1; + fc->sb->s_xattr = fuse_acl_xattr_handlers; + } } else { ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; @@ -943,7 +950,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) FUSE_FLOCK_LOCKS | FUSE_HAS_IOCTL_DIR | FUSE_AUTO_INVAL_DATA | FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO | FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT | - FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV; + FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL; req->in.h.opcode = FUSE_INIT; req->in.numargs = 1; req->in.args[0].size = sizeof(*arg); diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c index e22980f0a9e2..04b097f29d8a 100644 --- a/fs/fuse/xattr.c +++ b/fs/fuse/xattr.c @@ -9,9 +9,10 @@ #include "fuse_i.h" #include +#include -static int fuse_setxattr(struct inode *inode, const char *name, - const void *value, size_t size, int flags) +int fuse_setxattr(struct inode *inode, const char *name, const void *value, + size_t size, int flags) { struct fuse_conn *fc = get_fuse_conn(inode); FUSE_ARGS(args); @@ -45,8 +46,8 @@ static int fuse_setxattr(struct inode *inode, const char *name, return err; } -static ssize_t fuse_getxattr(struct inode *inode, const char *name, - void *value, size_t size) +ssize_t fuse_getxattr(struct inode *inode, const char *name, void *value, + size_t size) { struct fuse_conn *fc = get_fuse_conn(inode); FUSE_ARGS(args); @@ -147,7 +148,7 @@ ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size) return ret; } -static int fuse_removexattr(struct inode *inode, const char *name) +int fuse_removexattr(struct inode *inode, const char *name) { struct fuse_conn *fc = get_fuse_conn(inode); FUSE_ARGS(args); @@ -201,3 +202,10 @@ const struct xattr_handler *fuse_xattr_handlers[] = { &fuse_xattr_handler, NULL }; + +const struct xattr_handler *fuse_acl_xattr_handlers[] = { + &posix_acl_access_xattr_handler, + &posix_acl_default_xattr_handler, + &fuse_xattr_handler, + NULL +}; diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 14ca2f10d354..42fa977e3b14 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -111,6 +111,7 @@ * * 7.26 * - add FUSE_HANDLE_KILLPRIV + * - add FUSE_POSIX_ACL */ #ifndef _LINUX_FUSE_H @@ -242,6 +243,7 @@ struct fuse_file_lock { * FUSE_NO_OPEN_SUPPORT: kernel supports zero-message opens * FUSE_PARALLEL_DIROPS: allow parallel lookups and readdir * FUSE_HANDLE_KILLPRIV: fs handles killing suid/sgid/cap on write/chown/trunc + * FUSE_POSIX_ACL: filesystem supports posix acls */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -263,6 +265,7 @@ struct fuse_file_lock { #define FUSE_NO_OPEN_SUPPORT (1 << 17) #define FUSE_PARALLEL_DIROPS (1 << 18) #define FUSE_HANDLE_KILLPRIV (1 << 19) +#define FUSE_POSIX_ACL (1 << 20) /** * CUSE INIT request/reply flags -- cgit v1.2.3 From 1a8f324aa1f2237caef1c6633734785bbdcffeed Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Wed, 28 Sep 2016 13:59:49 -0400 Subject: iio: Implement counter channel type and info constants Quadrature encoders, such as rotary encoders and linear encoders, are devices which are capable of encoding the relative position and direction of motion of a shaft. This patch introduces several IIO constants for supporting quadrature encoder counter devices. IIO_COUNT: Current count (main data provided by the counter device) IIO_INDEX: Counter device index value Signed-off-by: William Breathitt Gray Signed-off-by: Jonathan Cameron --- Documentation/ABI/testing/sysfs-bus-iio | 18 ++++++++++++++++++ drivers/iio/industrialio-core.c | 2 ++ include/uapi/linux/iio/types.h | 2 ++ 3 files changed, 22 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index fee35c00cc4e..b8f220f978dd 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -329,6 +329,7 @@ What: /sys/bus/iio/devices/iio:deviceX/in_pressure_scale What: /sys/bus/iio/devices/iio:deviceX/in_humidityrelative_scale What: /sys/bus/iio/devices/iio:deviceX/in_velocity_sqrt(x^2+y^2+z^2)_scale What: /sys/bus/iio/devices/iio:deviceX/in_illuminance_scale +What: /sys/bus/iio/devices/iio:deviceX/in_countY_scale KernelVersion: 2.6.35 Contact: linux-iio@vger.kernel.org Description: @@ -1579,3 +1580,20 @@ Contact: linux-iio@vger.kernel.org Description: Raw (unscaled no offset etc.) electric conductivity reading that can be processed to siemens per meter. + +What: /sys/bus/iio/devices/iio:deviceX/in_countY_raw +KernelVersion: 4.9 +Contact: linux-iio@vger.kernel.org +Description: + Raw counter device counts from channel Y. For quadrature + counters, multiplication by an available [Y]_scale results in + the counts of a single quadrature signal phase from channel Y. + +What: /sys/bus/iio/devices/iio:deviceX/in_indexY_raw +KernelVersion: 4.9 +Contact: linux-iio@vger.kernel.org +Description: + Raw counter device index value from channel Y. This attribute + provides an absolute positional reference (e.g. a pulse once per + revolution) which may be used to home positional systems as + required. diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index fc340ed3dca1..649725bc15c1 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -81,6 +81,8 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_PH] = "ph", [IIO_UVINDEX] = "uvindex", [IIO_ELECTRICALCONDUCTIVITY] = "electricalconductivity", + [IIO_COUNT] = "count", + [IIO_INDEX] = "index", }; static const char * const iio_modifier_names[] = { diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index 22e5e589a274..e54d14a7f876 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -40,6 +40,8 @@ enum iio_chan_type { IIO_PH, IIO_UVINDEX, IIO_ELECTRICALCONDUCTIVITY, + IIO_COUNT, + IIO_INDEX, }; enum iio_modifier { -- cgit v1.2.3 From 0a6eab8bd4e0120d49511acbb294797d96ef9e4a Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 3 Oct 2016 09:11:13 -0700 Subject: vfs: support FS_XFLAG_COWEXTSIZE and get/set of CoW extent size hint Introduce XFLAGs for the new XFS CoW extent size hint, and actually plumb the CoW extent size hint into the fsxattr structure. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig --- include/uapi/linux/fs.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 3b00f7c8943f..cf398764b19e 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -157,7 +157,8 @@ struct fsxattr { __u32 fsx_extsize; /* extsize field value (get/set)*/ __u32 fsx_nextents; /* nextents field value (get) */ __u32 fsx_projid; /* project identifier (get/set) */ - unsigned char fsx_pad[12]; + __u32 fsx_cowextsize; /* CoW extsize field value (get/set)*/ + unsigned char fsx_pad[8]; }; /* @@ -178,6 +179,7 @@ struct fsxattr { #define FS_XFLAG_NODEFRAG 0x00002000 /* do not defragment */ #define FS_XFLAG_FILESTREAM 0x00004000 /* use filestream allocator */ #define FS_XFLAG_DAX 0x00008000 /* use DAX for IO */ +#define FS_XFLAG_COWEXTSIZE 0x00010000 /* CoW extent size allocator hint */ #define FS_XFLAG_HASATTR 0x80000000 /* no DIFLAG for this */ /* the read-only stuff doesn't really belong here, but any other place is -- cgit v1.2.3 From 71be6b4942dd64bc17728f82f787be98fd8afed7 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 3 Oct 2016 09:11:14 -0700 Subject: vfs: add a FALLOC_FL_UNSHARE mode to fallocate to unshare a range of blocks Add a new fallocate mode flag that explicitly unshares blocks on filesystems that support such features. The new flag can only be used with an allocate-mode fallocate call. Signed-off-by: Darrick J. Wong --- fs/open.c | 5 +++++ include/linux/falloc.h | 3 ++- include/uapi/linux/falloc.h | 18 ++++++++++++++++++ 3 files changed, 25 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/open.c b/fs/open.c index 4fd6e256f4f4..d58525dda28d 100644 --- a/fs/open.c +++ b/fs/open.c @@ -256,6 +256,11 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) (mode & ~FALLOC_FL_INSERT_RANGE)) return -EINVAL; + /* Unshare range should only be used with allocate mode. */ + if ((mode & FALLOC_FL_UNSHARE_RANGE) && + (mode & ~(FALLOC_FL_UNSHARE_RANGE | FALLOC_FL_KEEP_SIZE))) + return -EINVAL; + if (!(file->f_mode & FMODE_WRITE)) return -EBADF; diff --git a/include/linux/falloc.h b/include/linux/falloc.h index 996111000a8c..7494dc67c66f 100644 --- a/include/linux/falloc.h +++ b/include/linux/falloc.h @@ -25,6 +25,7 @@ struct space_resv { FALLOC_FL_PUNCH_HOLE | \ FALLOC_FL_COLLAPSE_RANGE | \ FALLOC_FL_ZERO_RANGE | \ - FALLOC_FL_INSERT_RANGE) + FALLOC_FL_INSERT_RANGE | \ + FALLOC_FL_UNSHARE_RANGE) #endif /* _FALLOC_H_ */ diff --git a/include/uapi/linux/falloc.h b/include/uapi/linux/falloc.h index 3e445a760f14..b075f601919b 100644 --- a/include/uapi/linux/falloc.h +++ b/include/uapi/linux/falloc.h @@ -58,4 +58,22 @@ */ #define FALLOC_FL_INSERT_RANGE 0x20 +/* + * FALLOC_FL_UNSHARE_RANGE is used to unshare shared blocks within the + * file size without overwriting any existing data. The purpose of this + * call is to preemptively reallocate any blocks that are subject to + * copy-on-write. + * + * Different filesystems may implement different limitations on the + * granularity of the operation. Most will limit operations to filesystem + * block size boundaries, but this boundary may be larger or smaller + * depending on the filesystem and/or the configuration of the filesystem + * or file. + * + * This flag can only be used with allocate-mode fallocate, which is + * to say that it cannot be used with the punch, zero, collapse, or + * insert range modes. + */ +#define FALLOC_FL_UNSHARE_RANGE 0x40 + #endif /* _UAPI_FALLOC_H_ */ -- cgit v1.2.3 From 6675df311db87aa2107a04ef97e19420953cbace Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Thu, 22 Sep 2016 17:24:22 -0700 Subject: Btrfs: catch invalid free space trees MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are two separate issues that can lead to corrupted free space trees. 1. The free space tree bitmaps had an endianness issue on big-endian systems which is fixed by an earlier patch in this series. 2. btrfs-progs before v4.7.3 modified filesystems without updating the free space tree. To catch both of these issues at once, we need to force the free space tree to be rebuilt. To do so, add a FREE_SPACE_TREE_VALID compat_ro bit. If the bit isn't set, we know that it was either produced by a broken big-endian kernel or may have been corrupted by btrfs-progs. This also provides us with a way to add rudimentary read-write support for the free space tree to btrfs-progs: it can just clear this bit and have the kernel rebuild the free space tree. Cc: stable@vger.kernel.org # 4.5+ Tested-by: Holger Hoffstätte Tested-by: Chandan Rajendra Signed-off-by: Omar Sandoval Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 3 ++- fs/btrfs/disk-io.c | 9 +++++++++ fs/btrfs/free-space-tree.c | 2 ++ include/uapi/linux/btrfs.h | 12 +++++++++++- 4 files changed, 24 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 33fe03551105..791e47ce9d27 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -251,7 +251,8 @@ struct btrfs_super_block { #define BTRFS_FEATURE_COMPAT_SAFE_CLEAR 0ULL #define BTRFS_FEATURE_COMPAT_RO_SUPP \ - (BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE) + (BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE | \ + BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID) #define BTRFS_FEATURE_COMPAT_RO_SAFE_SET 0ULL #define BTRFS_FEATURE_COMPAT_RO_SAFE_CLEAR 0ULL diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index c0bfc6ce5f06..3dede6d53bad 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2566,6 +2566,7 @@ int open_ctree(struct super_block *sb, int num_backups_tried = 0; int backup_index = 0; int max_active; + int clear_free_space_tree = 0; tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL); chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL); @@ -3131,6 +3132,14 @@ retry_root_backup: if (btrfs_test_opt(fs_info, CLEAR_CACHE) && btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) { + clear_free_space_tree = 1; + } else if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && + !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID)) { + btrfs_warn(fs_info, "free space tree is invalid"); + clear_free_space_tree = 1; + } + + if (clear_free_space_tree) { btrfs_info(fs_info, "clearing free space tree"); ret = btrfs_clear_free_space_tree(fs_info); if (ret) { diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index 8fd85bfbe2da..ea605ffd0e03 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -1182,6 +1182,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) } btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE); + btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID); fs_info->creating_free_space_tree = 0; ret = btrfs_commit_transaction(trans, tree_root); @@ -1250,6 +1251,7 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info) return PTR_ERR(trans); btrfs_clear_fs_compat_ro(fs_info, FREE_SPACE_TREE); + btrfs_clear_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID); fs_info->free_space_root = NULL; ret = clear_free_space_tree(trans, free_space_root); diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index ac5eacd3055b..db4c253f8011 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -239,7 +239,17 @@ struct btrfs_ioctl_fs_info_args { * Used by: * struct btrfs_ioctl_feature_flags */ -#define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE (1ULL << 0) +#define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE (1ULL << 0) +/* + * Older kernels (< 4.9) on big-endian systems produced broken free space tree + * bitmaps, and btrfs-progs also used to corrupt the free space tree (versions + * < 4.7.3). If this bit is clear, then the free space tree cannot be trusted. + * btrfs-progs can also intentionally clear this bit to ask the kernel to + * rebuild the free space tree, however this might not work on older kernels + * that do not know about this bit. If not sure, clear the cache manually on + * first mount when booting older kernel versions. + */ +#define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID (1ULL << 1) #define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF (1ULL << 0) #define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL (1ULL << 1) -- cgit v1.2.3 From 58f0f9f75c1b94dabbfc3daa333a4e68536b0a42 Mon Sep 17 00:00:00 2001 From: Emilio López Date: Tue, 27 Sep 2016 11:31:42 -0300 Subject: uapi: add missing install of sync_file.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As part of the sync framework destaging, the sync_file.h header was moved, but an entry was not added on Kbuild to install it. This patch resolves this omission so that "make headers_install" installs this header. Fixes: 460bfc41fd52 ("dma-buf/sync_file: de-stage sync_file headers") Reported-by: Michael Ellerman Reviewed-by: Gustavo Padovan Signed-off-by: Emilio López Signed-off-by: Sean Paul Link: http://patchwork.freedesktop.org/patch/msgid/20160927143142.8975-1-emilio.lopez@collabora.co.uk --- include/uapi/linux/Kbuild | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 185f8ea2702f..407ca0d7a938 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -396,6 +396,7 @@ header-y += string.h header-y += suspend_ioctls.h header-y += swab.h header-y += synclink.h +header-y += sync_file.h header-y += sysctl.h header-y += sysinfo.h header-y += target_core_user.h -- cgit v1.2.3 From f58b3c91f6786c66483fc18fd8b82a74cbf96d19 Mon Sep 17 00:00:00 2001 From: Tomohiro Kusumi Date: Tue, 11 Oct 2016 13:53:10 -0700 Subject: autofs: move inclusion of linux/limits.h to uapi linux/limits.h should be included by uapi instead of linux/auto_fs.h so as not to cause compile error in userspace. # cat << EOF > ./test1.c > #include > #include > int main(void) { > return 0; > } > EOF # gcc -Wall -g ./test1.c In file included from ./test1.c:2:0: /usr/include/linux/auto_fs.h:54:12: error: 'NAME_MAX' undeclared here (not in a function) char name[NAME_MAX+1]; ^ Link: http://lkml.kernel.org/r/20160812024856.12352.24092.stgit@pluto.themaw.net Signed-off-by: Tomohiro Kusumi Signed-off-by: Ian Kent Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/auto_fs.h | 1 - include/uapi/linux/auto_fs.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/linux/auto_fs.h b/include/linux/auto_fs.h index b4066bb89083..b8f814c95cf5 100644 --- a/include/linux/auto_fs.h +++ b/include/linux/auto_fs.h @@ -10,7 +10,6 @@ #define _LINUX_AUTO_FS_H #include -#include #include #include #endif /* _LINUX_AUTO_FS_H */ diff --git a/include/uapi/linux/auto_fs.h b/include/uapi/linux/auto_fs.h index 9175a1b4dc69..1bfc3ed8b284 100644 --- a/include/uapi/linux/auto_fs.h +++ b/include/uapi/linux/auto_fs.h @@ -12,6 +12,7 @@ #define _UAPI_LINUX_AUTO_FS_H #include +#include #ifndef __KERNEL__ #include #endif /* __KERNEL__ */ -- cgit v1.2.3 From 9b88ee0f3bb4c5b1e721bdcee93601b501d72f0a Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Tue, 11 Oct 2016 13:53:13 -0700 Subject: autofs4: move linux/auto_dev-ioctl.h to uapi/linux Since linux/auto_dev-ioctl.h wasn't included in include/linux/Kbuild it wasn't moved to uapi/linux as part of the uapi series. Link: http://lkml.kernel.org/r/20160812024901.12352.10984.stgit@pluto.themaw.net Signed-off-by: Ian Kent Cc: Tomohiro Kusumi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/auto_dev-ioctl.h | 209 +--------------------------------- include/uapi/linux/auto_dev-ioctl.h | 221 ++++++++++++++++++++++++++++++++++++ 2 files changed, 222 insertions(+), 208 deletions(-) create mode 100644 include/uapi/linux/auto_dev-ioctl.h (limited to 'include/uapi/linux') diff --git a/include/linux/auto_dev-ioctl.h b/include/linux/auto_dev-ioctl.h index bf82e3a758e5..28c15050ebe6 100644 --- a/include/linux/auto_dev-ioctl.h +++ b/include/linux/auto_dev-ioctl.h @@ -10,212 +10,5 @@ #ifndef _LINUX_AUTO_DEV_IOCTL_H #define _LINUX_AUTO_DEV_IOCTL_H -#include -#include - -#define AUTOFS_DEVICE_NAME "autofs" - -#define AUTOFS_DEV_IOCTL_VERSION_MAJOR 1 -#define AUTOFS_DEV_IOCTL_VERSION_MINOR 0 - -#define AUTOFS_DEV_IOCTL_SIZE sizeof(struct autofs_dev_ioctl) - -/* - * An ioctl interface for autofs mount point control. - */ - -struct args_protover { - __u32 version; -}; - -struct args_protosubver { - __u32 sub_version; -}; - -struct args_openmount { - __u32 devid; -}; - -struct args_ready { - __u32 token; -}; - -struct args_fail { - __u32 token; - __s32 status; -}; - -struct args_setpipefd { - __s32 pipefd; -}; - -struct args_timeout { - __u64 timeout; -}; - -struct args_requester { - __u32 uid; - __u32 gid; -}; - -struct args_expire { - __u32 how; -}; - -struct args_askumount { - __u32 may_umount; -}; - -struct args_ismountpoint { - union { - struct args_in { - __u32 type; - } in; - struct args_out { - __u32 devid; - __u32 magic; - } out; - }; -}; - -/* - * All the ioctls use this structure. - * When sending a path size must account for the total length - * of the chunk of memory otherwise is is the size of the - * structure. - */ - -struct autofs_dev_ioctl { - __u32 ver_major; - __u32 ver_minor; - __u32 size; /* total size of data passed in - * including this struct */ - __s32 ioctlfd; /* automount command fd */ - - /* Command parameters */ - - union { - struct args_protover protover; - struct args_protosubver protosubver; - struct args_openmount openmount; - struct args_ready ready; - struct args_fail fail; - struct args_setpipefd setpipefd; - struct args_timeout timeout; - struct args_requester requester; - struct args_expire expire; - struct args_askumount askumount; - struct args_ismountpoint ismountpoint; - }; - - char path[0]; -}; - -static inline void init_autofs_dev_ioctl(struct autofs_dev_ioctl *in) -{ - memset(in, 0, sizeof(struct autofs_dev_ioctl)); - in->ver_major = AUTOFS_DEV_IOCTL_VERSION_MAJOR; - in->ver_minor = AUTOFS_DEV_IOCTL_VERSION_MINOR; - in->size = sizeof(struct autofs_dev_ioctl); - in->ioctlfd = -1; -} - -/* - * If you change this make sure you make the corresponding change - * to autofs-dev-ioctl.c:lookup_ioctl() - */ -enum { - /* Get various version info */ - AUTOFS_DEV_IOCTL_VERSION_CMD = 0x71, - AUTOFS_DEV_IOCTL_PROTOVER_CMD, - AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD, - - /* Open mount ioctl fd */ - AUTOFS_DEV_IOCTL_OPENMOUNT_CMD, - - /* Close mount ioctl fd */ - AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD, - - /* Mount/expire status returns */ - AUTOFS_DEV_IOCTL_READY_CMD, - AUTOFS_DEV_IOCTL_FAIL_CMD, - - /* Activate/deactivate autofs mount */ - AUTOFS_DEV_IOCTL_SETPIPEFD_CMD, - AUTOFS_DEV_IOCTL_CATATONIC_CMD, - - /* Expiry timeout */ - AUTOFS_DEV_IOCTL_TIMEOUT_CMD, - - /* Get mount last requesting uid and gid */ - AUTOFS_DEV_IOCTL_REQUESTER_CMD, - - /* Check for eligible expire candidates */ - AUTOFS_DEV_IOCTL_EXPIRE_CMD, - - /* Request busy status */ - AUTOFS_DEV_IOCTL_ASKUMOUNT_CMD, - - /* Check if path is a mountpoint */ - AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD, -}; - -#define AUTOFS_IOCTL 0x93 - -#define AUTOFS_DEV_IOCTL_VERSION \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_VERSION_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_PROTOVER \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_PROTOVER_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_PROTOSUBVER \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_OPENMOUNT \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_OPENMOUNT_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_CLOSEMOUNT \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_READY \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_READY_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_FAIL \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_FAIL_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_SETPIPEFD \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_SETPIPEFD_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_CATATONIC \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_CATATONIC_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_TIMEOUT \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_TIMEOUT_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_REQUESTER \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_REQUESTER_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_EXPIRE \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_EXPIRE_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_ASKUMOUNT \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_ASKUMOUNT_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_ISMOUNTPOINT \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD, struct autofs_dev_ioctl) - +#include #endif /* _LINUX_AUTO_DEV_IOCTL_H */ diff --git a/include/uapi/linux/auto_dev-ioctl.h b/include/uapi/linux/auto_dev-ioctl.h new file mode 100644 index 000000000000..021ed331dd71 --- /dev/null +++ b/include/uapi/linux/auto_dev-ioctl.h @@ -0,0 +1,221 @@ +/* + * Copyright 2008 Red Hat, Inc. All rights reserved. + * Copyright 2008 Ian Kent + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + */ + +#ifndef _UAPI_LINUX_AUTO_DEV_IOCTL_H +#define _UAPI_LINUX_AUTO_DEV_IOCTL_H + +#include +#include + +#define AUTOFS_DEVICE_NAME "autofs" + +#define AUTOFS_DEV_IOCTL_VERSION_MAJOR 1 +#define AUTOFS_DEV_IOCTL_VERSION_MINOR 0 + +#define AUTOFS_DEV_IOCTL_SIZE sizeof(struct autofs_dev_ioctl) + +/* + * An ioctl interface for autofs mount point control. + */ + +struct args_protover { + __u32 version; +}; + +struct args_protosubver { + __u32 sub_version; +}; + +struct args_openmount { + __u32 devid; +}; + +struct args_ready { + __u32 token; +}; + +struct args_fail { + __u32 token; + __s32 status; +}; + +struct args_setpipefd { + __s32 pipefd; +}; + +struct args_timeout { + __u64 timeout; +}; + +struct args_requester { + __u32 uid; + __u32 gid; +}; + +struct args_expire { + __u32 how; +}; + +struct args_askumount { + __u32 may_umount; +}; + +struct args_ismountpoint { + union { + struct args_in { + __u32 type; + } in; + struct args_out { + __u32 devid; + __u32 magic; + } out; + }; +}; + +/* + * All the ioctls use this structure. + * When sending a path size must account for the total length + * of the chunk of memory otherwise is is the size of the + * structure. + */ + +struct autofs_dev_ioctl { + __u32 ver_major; + __u32 ver_minor; + __u32 size; /* total size of data passed in + * including this struct */ + __s32 ioctlfd; /* automount command fd */ + + /* Command parameters */ + + union { + struct args_protover protover; + struct args_protosubver protosubver; + struct args_openmount openmount; + struct args_ready ready; + struct args_fail fail; + struct args_setpipefd setpipefd; + struct args_timeout timeout; + struct args_requester requester; + struct args_expire expire; + struct args_askumount askumount; + struct args_ismountpoint ismountpoint; + }; + + char path[0]; +}; + +static inline void init_autofs_dev_ioctl(struct autofs_dev_ioctl *in) +{ + memset(in, 0, sizeof(struct autofs_dev_ioctl)); + in->ver_major = AUTOFS_DEV_IOCTL_VERSION_MAJOR; + in->ver_minor = AUTOFS_DEV_IOCTL_VERSION_MINOR; + in->size = sizeof(struct autofs_dev_ioctl); + in->ioctlfd = -1; +} + +/* + * If you change this make sure you make the corresponding change + * to autofs-dev-ioctl.c:lookup_ioctl() + */ +enum { + /* Get various version info */ + AUTOFS_DEV_IOCTL_VERSION_CMD = 0x71, + AUTOFS_DEV_IOCTL_PROTOVER_CMD, + AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD, + + /* Open mount ioctl fd */ + AUTOFS_DEV_IOCTL_OPENMOUNT_CMD, + + /* Close mount ioctl fd */ + AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD, + + /* Mount/expire status returns */ + AUTOFS_DEV_IOCTL_READY_CMD, + AUTOFS_DEV_IOCTL_FAIL_CMD, + + /* Activate/deactivate autofs mount */ + AUTOFS_DEV_IOCTL_SETPIPEFD_CMD, + AUTOFS_DEV_IOCTL_CATATONIC_CMD, + + /* Expiry timeout */ + AUTOFS_DEV_IOCTL_TIMEOUT_CMD, + + /* Get mount last requesting uid and gid */ + AUTOFS_DEV_IOCTL_REQUESTER_CMD, + + /* Check for eligible expire candidates */ + AUTOFS_DEV_IOCTL_EXPIRE_CMD, + + /* Request busy status */ + AUTOFS_DEV_IOCTL_ASKUMOUNT_CMD, + + /* Check if path is a mountpoint */ + AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD, +}; + +#define AUTOFS_IOCTL 0x93 + +#define AUTOFS_DEV_IOCTL_VERSION \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_VERSION_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_PROTOVER \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_PROTOVER_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_PROTOSUBVER \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_OPENMOUNT \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_OPENMOUNT_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_CLOSEMOUNT \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_READY \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_READY_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_FAIL \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_FAIL_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_SETPIPEFD \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_SETPIPEFD_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_CATATONIC \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_CATATONIC_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_TIMEOUT \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_TIMEOUT_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_REQUESTER \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_REQUESTER_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_EXPIRE \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_EXPIRE_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_ASKUMOUNT \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_ASKUMOUNT_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_ISMOUNTPOINT \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD, struct autofs_dev_ioctl) + +#endif /* _UAPI_LINUX_AUTO_DEV_IOCTL_H */ -- cgit v1.2.3 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/net/cfg80211.h | 15 +++++++++++++++ include/uapi/linux/nl80211.h | 8 ++++++-- net/wireless/core.h | 2 +- net/wireless/nl80211.c | 14 +++++++++++--- net/wireless/util.c | 43 +++++++++++++++++++++++++++++++++++++------ 5 files changed, 70 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index ea108541e1e0..5000ec758eb3 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -784,11 +784,19 @@ struct cfg80211_csa_settings { * @iftype_num: array with the number of interfaces of each interface * type. The index is the interface type as specified in &enum * nl80211_iftype. + * @beacon_int_gcd: a value specifying GCD of all beaconing interfaces, + * the GCD of a single value is considered the value itself, so for + * a single interface this should be set to that interface's beacon + * interval + * @beacon_int_different: a flag indicating whether or not all beacon + * intervals (of beaconing interfaces) are different or not. */ struct iface_combination_params { int num_different_channels; u8 radar_detect; int iftype_num[NUM_NL80211_IFTYPES]; + u32 beacon_int_gcd; + bool beacon_int_different; }; /** @@ -3100,6 +3108,12 @@ struct ieee80211_iface_limit { * only in special cases. * @radar_detect_widths: bitmap of channel widths supported for radar detection * @radar_detect_regions: bitmap of regions supported for radar detection + * @beacon_int_min_gcd: This interface combination supports different + * beacon intervals. + * = 0 - all beacon intervals for different interface must be same. + * > 0 - any beacon interval for the interface part of this combination AND + * *GCD* of all beacon intervals from beaconing interfaces of this + * combination must be greater or equal to this value. * * With this structure the driver can describe which interface * combinations it supports concurrently. @@ -3158,6 +3172,7 @@ struct ieee80211_iface_combination { bool beacon_int_infra_match; u8 radar_detect_widths; u8 radar_detect_regions; + u32 beacon_int_min_gcd; }; struct ieee80211_txrx_stypes { 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, diff --git a/net/wireless/core.h b/net/wireless/core.h index 08d2e948c9ad..21e31888cfa9 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -475,7 +475,7 @@ int ieee80211_get_ratemask(struct ieee80211_supported_band *sband, u32 *mask); int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev, - u32 beacon_int); + enum nl80211_iftype iftype, u32 beacon_int); void cfg80211_update_iface_num(struct cfg80211_registered_device *rdev, enum nl80211_iftype iftype, int num); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c510810f0b7c..903cd5a5d1ce 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1075,6 +1075,10 @@ static int nl80211_put_iface_combinations(struct wiphy *wiphy, nla_put_u32(msg, NL80211_IFACE_COMB_RADAR_DETECT_REGIONS, c->radar_detect_regions))) goto nla_put_failure; + if (c->beacon_int_min_gcd && + nla_put_u32(msg, NL80211_IFACE_COMB_BI_MIN_GCD, + c->beacon_int_min_gcd)) + goto nla_put_failure; nla_nest_end(msg, nl_combi); } @@ -3803,7 +3807,8 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) params.dtim_period = nla_get_u32(info->attrs[NL80211_ATTR_DTIM_PERIOD]); - err = cfg80211_validate_beacon_int(rdev, params.beacon_interval); + err = cfg80211_validate_beacon_int(rdev, dev->ieee80211_ptr->iftype, + params.beacon_interval); if (err) return err; @@ -8152,7 +8157,8 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) ibss.beacon_interval = nla_get_u32(info->attrs[NL80211_ATTR_BEACON_INTERVAL]); - err = cfg80211_validate_beacon_int(rdev, ibss.beacon_interval); + err = cfg80211_validate_beacon_int(rdev, NL80211_IFTYPE_ADHOC, + ibss.beacon_interval); if (err) return err; @@ -9417,7 +9423,9 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) setup.beacon_interval = nla_get_u32(info->attrs[NL80211_ATTR_BEACON_INTERVAL]); - err = cfg80211_validate_beacon_int(rdev, setup.beacon_interval); + err = cfg80211_validate_beacon_int(rdev, + NL80211_IFTYPE_MESH_POINT, + setup.beacon_interval); if (err) return err; } diff --git a/net/wireless/util.c b/net/wireless/util.c index 0d69b257793d..d2ea1f152d17 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1559,24 +1559,46 @@ bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, EXPORT_SYMBOL(ieee80211_chandef_to_operating_class); int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev, - u32 beacon_int) + enum nl80211_iftype iftype, u32 beacon_int) { struct wireless_dev *wdev; - int res = 0; + struct iface_combination_params params = { + .beacon_int_gcd = beacon_int, /* GCD(n) = n */ + }; if (beacon_int < 10 || beacon_int > 10000) return -EINVAL; + params.iftype_num[iftype] = 1; list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { if (!wdev->beacon_interval) continue; - if (wdev->beacon_interval != beacon_int) { - res = -EINVAL; - break; + + params.iftype_num[wdev->iftype]++; + } + + list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { + u32 bi_prev = wdev->beacon_interval; + + if (!wdev->beacon_interval) + continue; + + /* slight optimisation - skip identical BIs */ + if (wdev->beacon_interval == beacon_int) + continue; + + params.beacon_int_different = true; + + /* Get the GCD */ + while (bi_prev != 0) { + u32 tmp_bi = bi_prev; + + bi_prev = params.beacon_int_gcd % bi_prev; + params.beacon_int_gcd = tmp_bi; } } - return res; + return cfg80211_check_combinations(&rdev->wiphy, ¶ms); } int cfg80211_iter_combinations(struct wiphy *wiphy, @@ -1652,6 +1674,15 @@ int cfg80211_iter_combinations(struct wiphy *wiphy, if ((all_iftypes & used_iftypes) != used_iftypes) goto cont; + if (params->beacon_int_gcd) { + if (c->beacon_int_min_gcd && + params->beacon_int_gcd < c->beacon_int_min_gcd) + return -EINVAL; + if (!c->beacon_int_min_gcd && + params->beacon_int_different) + goto cont; + } + /* This combination covered all interface types and * supported the requested numbers, so we're good. */ -- 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 --- arch/m68k/emu/nfeth.c | 1 - drivers/isdn/hysdn/hysdn_net.c | 1 - drivers/media/dvb-core/dvb_net.c | 2 +- drivers/net/appletalk/ipddp.c | 1 - drivers/net/cris/eth_v10.c | 1 - drivers/net/ethernet/3com/3c509.c | 1 - drivers/net/ethernet/3com/3c515.c | 1 - drivers/net/ethernet/3com/3c574_cs.c | 1 - drivers/net/ethernet/3com/3c589_cs.c | 1 - drivers/net/ethernet/3com/3c59x.c | 2 -- drivers/net/ethernet/3com/typhoon.c | 1 - drivers/net/ethernet/8390/8390.c | 1 - drivers/net/ethernet/8390/8390p.c | 1 - drivers/net/ethernet/8390/ax88796.c | 1 - drivers/net/ethernet/8390/axnet_cs.c | 1 - drivers/net/ethernet/8390/etherh.c | 1 - drivers/net/ethernet/8390/hydra.c | 1 - drivers/net/ethernet/8390/mac8390.c | 1 - drivers/net/ethernet/8390/mcf8390.c | 1 - drivers/net/ethernet/8390/ne2k-pci.c | 1 - drivers/net/ethernet/8390/pcnet_cs.c | 1 - drivers/net/ethernet/8390/smc-ultra.c | 1 - drivers/net/ethernet/8390/wd.c | 1 - drivers/net/ethernet/8390/zorro8390.c | 1 - drivers/net/ethernet/adaptec/starfire.c | 1 - drivers/net/ethernet/adi/bfin_mac.c | 1 - drivers/net/ethernet/allwinner/sun4i-emac.c | 1 - drivers/net/ethernet/amd/a2065.c | 1 - drivers/net/ethernet/amd/am79c961a.c | 1 - drivers/net/ethernet/amd/ariadne.c | 1 - drivers/net/ethernet/amd/atarilance.c | 1 - drivers/net/ethernet/amd/au1000_eth.c | 1 - drivers/net/ethernet/amd/declance.c | 1 - drivers/net/ethernet/amd/hplance.c | 1 - drivers/net/ethernet/amd/lance.c | 1 - drivers/net/ethernet/amd/mvme147.c | 1 - drivers/net/ethernet/amd/ni65.c | 1 - drivers/net/ethernet/amd/nmclan_cs.c | 1 - drivers/net/ethernet/amd/pcnet32.c | 1 - drivers/net/ethernet/amd/sun3lance.c | 1 - drivers/net/ethernet/amd/sunlance.c | 1 - drivers/net/ethernet/apm/xgene/xgene_enet_main.c | 1 - drivers/net/ethernet/apple/bmac.c | 1 - drivers/net/ethernet/apple/mace.c | 1 - drivers/net/ethernet/apple/macmace.c | 1 - drivers/net/ethernet/aurora/nb8800.c | 1 - drivers/net/ethernet/cadence/macb.c | 1 - drivers/net/ethernet/cirrus/cs89x0.c | 1 - drivers/net/ethernet/cirrus/ep93xx_eth.c | 1 - drivers/net/ethernet/cirrus/mac89x0.c | 1 - drivers/net/ethernet/davicom/dm9000.c | 1 - drivers/net/ethernet/dec/tulip/de2104x.c | 1 - drivers/net/ethernet/dec/tulip/de4x5.c | 1 - drivers/net/ethernet/dec/tulip/dmfe.c | 1 - drivers/net/ethernet/dec/tulip/tulip_core.c | 1 - drivers/net/ethernet/dec/tulip/uli526x.c | 1 - drivers/net/ethernet/dec/tulip/winbond-840.c | 1 - drivers/net/ethernet/dec/tulip/xircom_cb.c | 1 - drivers/net/ethernet/dnet.c | 1 - drivers/net/ethernet/ec_bhf.c | 1 - drivers/net/ethernet/fealnx.c | 1 - drivers/net/ethernet/freescale/fec_main.c | 1 - drivers/net/ethernet/freescale/fec_mpc52xx.c | 1 - drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c | 1 - drivers/net/ethernet/freescale/ucc_geth.c | 1 - drivers/net/ethernet/fujitsu/fmvj18x_cs.c | 1 - drivers/net/ethernet/hisilicon/hip04_eth.c | 1 - drivers/net/ethernet/hisilicon/hisi_femac.c | 1 - drivers/net/ethernet/hp/hp100.c | 2 -- drivers/net/ethernet/i825xx/82596.c | 1 - drivers/net/ethernet/i825xx/ether1.c | 1 - drivers/net/ethernet/i825xx/lib82596.c | 1 - drivers/net/ethernet/i825xx/sun3_82586.c | 1 - drivers/net/ethernet/ibm/emac/core.c | 1 - drivers/net/ethernet/korina.c | 1 - drivers/net/ethernet/lantiq_etop.c | 18 ++++++++---------- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 1 - drivers/net/ethernet/micrel/ks8851.c | 1 - drivers/net/ethernet/micrel/ks8851_mll.c | 1 - drivers/net/ethernet/microchip/enc28j60.c | 1 - drivers/net/ethernet/moxa/moxart_ether.c | 1 - drivers/net/ethernet/natsemi/jazzsonic.c | 1 - drivers/net/ethernet/natsemi/macsonic.c | 1 - drivers/net/ethernet/natsemi/xtsonic.c | 1 - drivers/net/ethernet/netx-eth.c | 1 - drivers/net/ethernet/nuvoton/w90p910_ether.c | 1 - drivers/net/ethernet/nxp/lpc_eth.c | 1 - drivers/net/ethernet/packetengines/hamachi.c | 1 - drivers/net/ethernet/packetengines/yellowfin.c | 1 - drivers/net/ethernet/qlogic/qla3xxx.c | 1 - drivers/net/ethernet/rdc/r6040.c | 1 - drivers/net/ethernet/realtek/atp.c | 1 - drivers/net/ethernet/renesas/ravb_main.c | 1 - drivers/net/ethernet/renesas/sh_eth.c | 2 -- drivers/net/ethernet/seeq/ether3.c | 1 - drivers/net/ethernet/seeq/sgiseeq.c | 1 - drivers/net/ethernet/sgi/ioc3-eth.c | 1 - drivers/net/ethernet/sgi/meth.c | 1 - drivers/net/ethernet/silan/sc92031.c | 1 - drivers/net/ethernet/sis/sis190.c | 1 - drivers/net/ethernet/sis/sis900.c | 1 - drivers/net/ethernet/smsc/epic100.c | 1 - drivers/net/ethernet/smsc/smc911x.c | 1 - drivers/net/ethernet/smsc/smc9194.c | 1 - drivers/net/ethernet/smsc/smc91c92_cs.c | 1 - drivers/net/ethernet/smsc/smc91x.c | 1 - drivers/net/ethernet/smsc/smsc911x.c | 1 - drivers/net/ethernet/sun/sunbmac.c | 1 - drivers/net/ethernet/sun/sunhme.c | 1 - drivers/net/ethernet/sun/sunqe.c | 1 - drivers/net/ethernet/ti/cpmac.c | 1 - drivers/net/ethernet/ti/cpsw.c | 1 - drivers/net/ethernet/ti/tlan.c | 1 - drivers/net/ethernet/toshiba/tc35815.c | 1 - drivers/net/ethernet/tundra/tsi108_eth.c | 1 - drivers/net/ethernet/via/via-rhine.c | 1 - drivers/net/ethernet/wiznet/w5100.c | 1 - drivers/net/ethernet/wiznet/w5300.c | 1 - drivers/net/ethernet/xircom/xirc2ps_cs.c | 1 - drivers/net/ethernet/xscale/ixp4xx_eth.c | 1 - drivers/net/plip/plip.c | 1 - drivers/net/sb1000.c | 1 - drivers/net/usb/catc.c | 1 - drivers/net/usb/kaweth.c | 1 - drivers/net/usb/pegasus.c | 1 - drivers/net/usb/r8152.c | 3 ++- drivers/net/usb/rtl8150.c | 1 - drivers/net/wan/sbni.c | 1 - drivers/net/wireless/intersil/prism54/islpci_dev.c | 1 - drivers/net/wireless/mac80211_hwsim.c | 1 - drivers/net/wireless/marvell/libertas/main.c | 1 - drivers/net/wireless/ray_cs.c | 1 - drivers/net/wireless/wl3501_cs.c | 1 - drivers/net/wireless/zydas/zd1201.c | 1 - drivers/staging/rtl8188eu/os_dep/mon.c | 1 - drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 1 - drivers/staging/rtl8192u/r8192U_core.c | 1 - drivers/staging/slicoss/slicoss.c | 1 - include/uapi/linux/if_ether.h | 2 ++ net/atm/br2684.c | 2 -- net/bluetooth/bnep/netdev.c | 1 - net/ethernet/eth.c | 5 +++-- net/irda/irlan/irlan_eth.c | 1 - 143 files changed, 16 insertions(+), 156 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/m68k/emu/nfeth.c b/arch/m68k/emu/nfeth.c index a0985fd088d1..fc4be028c418 100644 --- a/arch/m68k/emu/nfeth.c +++ b/arch/m68k/emu/nfeth.c @@ -184,7 +184,6 @@ static const struct net_device_ops nfeth_netdev_ops = { .ndo_start_xmit = nfeth_xmit, .ndo_tx_timeout = nfeth_tx_timeout, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, }; diff --git a/drivers/isdn/hysdn/hysdn_net.c b/drivers/isdn/hysdn/hysdn_net.c index 5609deee7cd3..b93a4e9a8d34 100644 --- a/drivers/isdn/hysdn/hysdn_net.c +++ b/drivers/isdn/hysdn/hysdn_net.c @@ -232,7 +232,6 @@ static const struct net_device_ops hysdn_netdev_ops = { .ndo_open = net_open, .ndo_stop = net_close, .ndo_start_xmit = net_send_packet, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c index 9914f69a4a02..0da622f5fe69 100644 --- a/drivers/media/dvb-core/dvb_net.c +++ b/drivers/media/dvb-core/dvb_net.c @@ -1198,7 +1198,6 @@ static const struct net_device_ops dvb_netdev_ops = { .ndo_start_xmit = dvb_net_tx, .ndo_set_rx_mode = dvb_net_set_multicast_list, .ndo_set_mac_address = dvb_net_set_mac, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, }; @@ -1209,6 +1208,7 @@ static void dvb_net_setup(struct net_device *dev) dev->header_ops = &dvb_header_ops; dev->netdev_ops = &dvb_netdev_ops; dev->mtu = 4096; + dev->max_mtu = 4096; dev->flags |= IFF_NOARP; } diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c index e90c6a7333d7..31f89f1c6123 100644 --- a/drivers/net/appletalk/ipddp.c +++ b/drivers/net/appletalk/ipddp.c @@ -59,7 +59,6 @@ static int ipddp_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); static const struct net_device_ops ipddp_netdev_ops = { .ndo_start_xmit = ipddp_xmit, .ndo_do_ioctl = ipddp_ioctl, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/cris/eth_v10.c b/drivers/net/cris/eth_v10.c index 221f5f011ff9..e128826aa117 100644 --- a/drivers/net/cris/eth_v10.c +++ b/drivers/net/cris/eth_v10.c @@ -264,7 +264,6 @@ static const struct net_device_ops e100_netdev_ops = { .ndo_do_ioctl = e100_ioctl, .ndo_set_mac_address = e100_set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, .ndo_set_config = e100_set_config, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = e100_netpoll, diff --git a/drivers/net/ethernet/3com/3c509.c b/drivers/net/ethernet/3com/3c509.c index 91ada52f776b..9f9a5f440e2f 100644 --- a/drivers/net/ethernet/3com/3c509.c +++ b/drivers/net/ethernet/3com/3c509.c @@ -508,7 +508,6 @@ static const struct net_device_ops netdev_ops = { .ndo_get_stats = el3_get_stats, .ndo_set_rx_mode = set_multicast_list, .ndo_tx_timeout = el3_tx_timeout, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c index b26e038b4a0e..b9f4c463e516 100644 --- a/drivers/net/ethernet/3com/3c515.c +++ b/drivers/net/ethernet/3com/3c515.c @@ -570,7 +570,6 @@ static const struct net_device_ops netdev_ops = { .ndo_tx_timeout = corkscrew_timeout, .ndo_get_stats = corkscrew_get_stats, .ndo_set_rx_mode = set_rx_mode, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/3com/3c574_cs.c b/drivers/net/ethernet/3com/3c574_cs.c index b88afd759307..9359a37fedc0 100644 --- a/drivers/net/ethernet/3com/3c574_cs.c +++ b/drivers/net/ethernet/3com/3c574_cs.c @@ -254,7 +254,6 @@ static const struct net_device_ops el3_netdev_ops = { .ndo_get_stats = el3_get_stats, .ndo_do_ioctl = el3_ioctl, .ndo_set_rx_mode = set_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c index 71396e4b87e3..e28254a00599 100644 --- a/drivers/net/ethernet/3com/3c589_cs.c +++ b/drivers/net/ethernet/3com/3c589_cs.c @@ -188,7 +188,6 @@ static const struct net_device_ops el3_netdev_ops = { .ndo_set_config = el3_config, .ndo_get_stats = el3_get_stats, .ndo_set_rx_mode = set_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 9133e7926da5..3ecf61382269 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -1062,7 +1062,6 @@ static const struct net_device_ops boomrang_netdev_ops = { .ndo_do_ioctl = vortex_ioctl, #endif .ndo_set_rx_mode = set_rx_mode, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, #ifdef CONFIG_NET_POLL_CONTROLLER @@ -1080,7 +1079,6 @@ static const struct net_device_ops vortex_netdev_ops = { .ndo_do_ioctl = vortex_ioctl, #endif .ndo_set_rx_mode = set_rx_mode, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/3com/typhoon.c b/drivers/net/ethernet/3com/typhoon.c index 8f8418d2ac4a..506b507b4158 100644 --- a/drivers/net/ethernet/3com/typhoon.c +++ b/drivers/net/ethernet/3com/typhoon.c @@ -2255,7 +2255,6 @@ static const struct net_device_ops typhoon_netdev_ops = { .ndo_get_stats = typhoon_get_stats, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_change_mtu = eth_change_mtu, }; static int diff --git a/drivers/net/ethernet/8390/8390.c b/drivers/net/ethernet/8390/8390.c index 5db1f55abef4..a43544af257b 100644 --- a/drivers/net/ethernet/8390/8390.c +++ b/drivers/net/ethernet/8390/8390.c @@ -64,7 +64,6 @@ const struct net_device_ops ei_netdev_ops = { .ndo_set_rx_mode = ei_set_multicast_list, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_change_mtu = eth_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = ei_poll, #endif diff --git a/drivers/net/ethernet/8390/8390p.c b/drivers/net/ethernet/8390/8390p.c index e8fc2e87e840..46d2257c4430 100644 --- a/drivers/net/ethernet/8390/8390p.c +++ b/drivers/net/ethernet/8390/8390p.c @@ -69,7 +69,6 @@ const struct net_device_ops eip_netdev_ops = { .ndo_set_rx_mode = eip_set_multicast_list, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_change_mtu = eth_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = eip_poll, #endif diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c index 39ca9350d1b2..b0a3b85fc6f8 100644 --- a/drivers/net/ethernet/8390/ax88796.c +++ b/drivers/net/ethernet/8390/ax88796.c @@ -536,7 +536,6 @@ static const struct net_device_ops ax_netdev_ops = { .ndo_set_rx_mode = ax_ei_set_multicast_list, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_change_mtu = eth_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = ax_ei_poll, #endif diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c index 4ea717d68c95..1d84a0544ace 100644 --- a/drivers/net/ethernet/8390/axnet_cs.c +++ b/drivers/net/ethernet/8390/axnet_cs.c @@ -134,7 +134,6 @@ static const struct net_device_ops axnet_netdev_ops = { .ndo_tx_timeout = axnet_tx_timeout, .ndo_get_stats = get_stats, .ndo_set_rx_mode = set_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/8390/etherh.c b/drivers/net/ethernet/8390/etherh.c index d686b9cac29f..11cbf22ad201 100644 --- a/drivers/net/ethernet/8390/etherh.c +++ b/drivers/net/ethernet/8390/etherh.c @@ -654,7 +654,6 @@ static const struct net_device_ops etherh_netdev_ops = { .ndo_set_rx_mode = __ei_set_multicast_list, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_change_mtu = eth_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = __ei_poll, #endif diff --git a/drivers/net/ethernet/8390/hydra.c b/drivers/net/ethernet/8390/hydra.c index 0fe19d609c2e..8ae249195301 100644 --- a/drivers/net/ethernet/8390/hydra.c +++ b/drivers/net/ethernet/8390/hydra.c @@ -105,7 +105,6 @@ static const struct net_device_ops hydra_netdev_ops = { .ndo_set_rx_mode = __ei_set_multicast_list, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_change_mtu = eth_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = __ei_poll, #endif diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c index b9283901136e..9497f18eaba0 100644 --- a/drivers/net/ethernet/8390/mac8390.c +++ b/drivers/net/ethernet/8390/mac8390.c @@ -483,7 +483,6 @@ static const struct net_device_ops mac8390_netdev_ops = { .ndo_set_rx_mode = __ei_set_multicast_list, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_change_mtu = eth_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = __ei_poll, #endif diff --git a/drivers/net/ethernet/8390/mcf8390.c b/drivers/net/ethernet/8390/mcf8390.c index e1c055574a11..4bb967bc879e 100644 --- a/drivers/net/ethernet/8390/mcf8390.c +++ b/drivers/net/ethernet/8390/mcf8390.c @@ -308,7 +308,6 @@ static const struct net_device_ops mcf8390_netdev_ops = { .ndo_set_rx_mode = __ei_set_multicast_list, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_change_mtu = eth_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = __ei_poll, #endif diff --git a/drivers/net/ethernet/8390/ne2k-pci.c b/drivers/net/ethernet/8390/ne2k-pci.c index 57e97910c728..07355302443d 100644 --- a/drivers/net/ethernet/8390/ne2k-pci.c +++ b/drivers/net/ethernet/8390/ne2k-pci.c @@ -209,7 +209,6 @@ static const struct net_device_ops ne2k_netdev_ops = { .ndo_set_rx_mode = ei_set_multicast_list, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_change_mtu = eth_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = ei_poll, #endif diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c index 2f79d29f17f2..63079a6e20d9 100644 --- a/drivers/net/ethernet/8390/pcnet_cs.c +++ b/drivers/net/ethernet/8390/pcnet_cs.c @@ -227,7 +227,6 @@ static const struct net_device_ops pcnet_netdev_ops = { .ndo_do_ioctl = ei_ioctl, .ndo_set_rx_mode = ei_set_multicast_list, .ndo_tx_timeout = ei_tx_timeout, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/8390/smc-ultra.c b/drivers/net/ethernet/8390/smc-ultra.c index 139385dcdaa7..364b6514f65f 100644 --- a/drivers/net/ethernet/8390/smc-ultra.c +++ b/drivers/net/ethernet/8390/smc-ultra.c @@ -195,7 +195,6 @@ static const struct net_device_ops ultra_netdev_ops = { .ndo_set_rx_mode = ei_set_multicast_list, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_change_mtu = eth_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = ultra_poll, #endif diff --git a/drivers/net/ethernet/8390/wd.c b/drivers/net/ethernet/8390/wd.c index dd7d816bde52..ad019cbc698f 100644 --- a/drivers/net/ethernet/8390/wd.c +++ b/drivers/net/ethernet/8390/wd.c @@ -156,7 +156,6 @@ static const struct net_device_ops wd_netdev_ops = { .ndo_set_rx_mode = ei_set_multicast_list, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_change_mtu = eth_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = ei_poll, #endif diff --git a/drivers/net/ethernet/8390/zorro8390.c b/drivers/net/ethernet/8390/zorro8390.c index 8308728fad05..6d93956b293b 100644 --- a/drivers/net/ethernet/8390/zorro8390.c +++ b/drivers/net/ethernet/8390/zorro8390.c @@ -284,7 +284,6 @@ static const struct net_device_ops zorro8390_netdev_ops = { .ndo_set_rx_mode = __ei_set_multicast_list, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_change_mtu = eth_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = __ei_poll, #endif diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c index 8af2c88d5b33..4a9a16e25666 100644 --- a/drivers/net/ethernet/adaptec/starfire.c +++ b/drivers/net/ethernet/adaptec/starfire.c @@ -634,7 +634,6 @@ static const struct net_device_ops netdev_ops = { .ndo_get_stats = get_stats, .ndo_set_rx_mode = set_rx_mode, .ndo_do_ioctl = netdev_ioctl, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, #ifdef VLAN_SUPPORT diff --git a/drivers/net/ethernet/adi/bfin_mac.c b/drivers/net/ethernet/adi/bfin_mac.c index 00f9ee3fc3e5..88164529b52a 100644 --- a/drivers/net/ethernet/adi/bfin_mac.c +++ b/drivers/net/ethernet/adi/bfin_mac.c @@ -1571,7 +1571,6 @@ static const struct net_device_ops bfin_mac_netdev_ops = { .ndo_set_rx_mode = bfin_mac_set_multicast_list, .ndo_do_ioctl = bfin_mac_ioctl, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = bfin_mac_poll_controller, #endif diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c index 6ffdff68bfc4..af27f9dbedf2 100644 --- a/drivers/net/ethernet/allwinner/sun4i-emac.c +++ b/drivers/net/ethernet/allwinner/sun4i-emac.c @@ -773,7 +773,6 @@ static const struct net_device_ops emac_netdev_ops = { .ndo_tx_timeout = emac_timeout, .ndo_set_rx_mode = emac_set_rx_mode, .ndo_do_ioctl = emac_ioctl, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = emac_set_mac_address, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/amd/a2065.c b/drivers/net/ethernet/amd/a2065.c index a83cd1c4ce1d..ee4b94e3cda9 100644 --- a/drivers/net/ethernet/amd/a2065.c +++ b/drivers/net/ethernet/amd/a2065.c @@ -665,7 +665,6 @@ static const struct net_device_ops lance_netdev_ops = { .ndo_tx_timeout = lance_tx_timeout, .ndo_set_rx_mode = lance_set_multicast, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, }; diff --git a/drivers/net/ethernet/amd/am79c961a.c b/drivers/net/ethernet/amd/am79c961a.c index fcdf5dda448f..b11e910850f7 100644 --- a/drivers/net/ethernet/amd/am79c961a.c +++ b/drivers/net/ethernet/amd/am79c961a.c @@ -663,7 +663,6 @@ static const struct net_device_ops am79c961_netdev_ops = { .ndo_set_rx_mode = am79c961_setmulticastlist, .ndo_tx_timeout = am79c961_timeout, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = am79c961_poll_controller, diff --git a/drivers/net/ethernet/amd/ariadne.c b/drivers/net/ethernet/amd/ariadne.c index 968b7bfac8fc..5fd7b15b0574 100644 --- a/drivers/net/ethernet/amd/ariadne.c +++ b/drivers/net/ethernet/amd/ariadne.c @@ -706,7 +706,6 @@ static const struct net_device_ops ariadne_netdev_ops = { .ndo_get_stats = ariadne_get_stats, .ndo_set_rx_mode = set_multicast_list, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, }; diff --git a/drivers/net/ethernet/amd/atarilance.c b/drivers/net/ethernet/amd/atarilance.c index d2bc8e5dcd23..e53ccc3b7d8d 100644 --- a/drivers/net/ethernet/amd/atarilance.c +++ b/drivers/net/ethernet/amd/atarilance.c @@ -460,7 +460,6 @@ static const struct net_device_ops lance_netdev_ops = { .ndo_set_mac_address = lance_set_mac_address, .ndo_tx_timeout = lance_tx_timeout, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, }; static unsigned long __init lance_probe1( struct net_device *dev, diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c index df664187cd82..a3c90fe5de00 100644 --- a/drivers/net/ethernet/amd/au1000_eth.c +++ b/drivers/net/ethernet/amd/au1000_eth.c @@ -1103,7 +1103,6 @@ static const struct net_device_ops au1000_netdev_ops = { .ndo_tx_timeout = au1000_tx_timeout, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, }; static int au1000_probe(struct platform_device *pdev) diff --git a/drivers/net/ethernet/amd/declance.c b/drivers/net/ethernet/amd/declance.c index b799c7ac899b..76e5fc7adff5 100644 --- a/drivers/net/ethernet/amd/declance.c +++ b/drivers/net/ethernet/amd/declance.c @@ -1013,7 +1013,6 @@ static const struct net_device_ops lance_netdev_ops = { .ndo_start_xmit = lance_start_xmit, .ndo_tx_timeout = lance_tx_timeout, .ndo_set_rx_mode = lance_set_multicast, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, }; diff --git a/drivers/net/ethernet/amd/hplance.c b/drivers/net/ethernet/amd/hplance.c index 6c9de117ffc6..c3dbf1c8a269 100644 --- a/drivers/net/ethernet/amd/hplance.c +++ b/drivers/net/ethernet/amd/hplance.c @@ -72,7 +72,6 @@ static const struct net_device_ops hplance_netdev_ops = { .ndo_stop = hplance_close, .ndo_start_xmit = lance_start_xmit, .ndo_set_rx_mode = lance_set_multicast, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/amd/lance.c b/drivers/net/ethernet/amd/lance.c index abb1ba228b26..61a641f23149 100644 --- a/drivers/net/ethernet/amd/lance.c +++ b/drivers/net/ethernet/amd/lance.c @@ -461,7 +461,6 @@ static const struct net_device_ops lance_netdev_ops = { .ndo_get_stats = lance_get_stats, .ndo_set_rx_mode = set_multicast_list, .ndo_tx_timeout = lance_tx_timeout, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/amd/mvme147.c b/drivers/net/ethernet/amd/mvme147.c index 0660ac5846bb..0a920448522f 100644 --- a/drivers/net/ethernet/amd/mvme147.c +++ b/drivers/net/ethernet/amd/mvme147.c @@ -62,7 +62,6 @@ static const struct net_device_ops lance_netdev_ops = { .ndo_start_xmit = lance_start_xmit, .ndo_set_rx_mode = lance_set_multicast, .ndo_tx_timeout = lance_tx_timeout, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, }; diff --git a/drivers/net/ethernet/amd/ni65.c b/drivers/net/ethernet/amd/ni65.c index cda53db75f17..5985bf220a8d 100644 --- a/drivers/net/ethernet/amd/ni65.c +++ b/drivers/net/ethernet/amd/ni65.c @@ -407,7 +407,6 @@ static const struct net_device_ops ni65_netdev_ops = { .ndo_start_xmit = ni65_send_packet, .ndo_tx_timeout = ni65_timeout, .ndo_set_rx_mode = set_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c index 2807e181647b..113a3b3cc50c 100644 --- a/drivers/net/ethernet/amd/nmclan_cs.c +++ b/drivers/net/ethernet/amd/nmclan_cs.c @@ -427,7 +427,6 @@ static const struct net_device_ops mace_netdev_ops = { .ndo_set_config = mace_config, .ndo_get_stats = mace_get_stats, .ndo_set_rx_mode = set_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index c22bf52d3320..adc7ab99a2f6 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -1527,7 +1527,6 @@ static const struct net_device_ops pcnet32_netdev_ops = { .ndo_get_stats = pcnet32_get_stats, .ndo_set_rx_mode = pcnet32_set_multicast_list, .ndo_do_ioctl = pcnet32_ioctl, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/amd/sun3lance.c b/drivers/net/ethernet/amd/sun3lance.c index 3d8c6b2cdea4..12bb4f1489fc 100644 --- a/drivers/net/ethernet/amd/sun3lance.c +++ b/drivers/net/ethernet/amd/sun3lance.c @@ -299,7 +299,6 @@ static const struct net_device_ops lance_netdev_ops = { .ndo_start_xmit = lance_start_xmit, .ndo_set_rx_mode = set_multicast_list, .ndo_set_mac_address = NULL, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/amd/sunlance.c b/drivers/net/ethernet/amd/sunlance.c index 9b56b40259dc..291ca5187f12 100644 --- a/drivers/net/ethernet/amd/sunlance.c +++ b/drivers/net/ethernet/amd/sunlance.c @@ -1294,7 +1294,6 @@ static const struct net_device_ops sparc_lance_ops = { .ndo_start_xmit = lance_start_xmit, .ndo_set_rx_mode = lance_set_multicast, .ndo_tx_timeout = lance_tx_timeout, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index f75d9556152f..3fc7b0db952b 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -1252,7 +1252,6 @@ static const struct net_device_ops xgene_ndev_ops = { .ndo_start_xmit = xgene_enet_start_xmit, .ndo_tx_timeout = xgene_enet_timeout, .ndo_get_stats64 = xgene_enet_get_stats64, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = xgene_enet_set_mac_address, }; diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c index a65d7a60f116..2b2d87089987 100644 --- a/drivers/net/ethernet/apple/bmac.c +++ b/drivers/net/ethernet/apple/bmac.c @@ -1237,7 +1237,6 @@ static const struct net_device_ops bmac_netdev_ops = { .ndo_start_xmit = bmac_output, .ndo_set_rx_mode = bmac_set_multicast, .ndo_set_mac_address = bmac_set_address, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c index e58a7c73766e..96dd5300e0e5 100644 --- a/drivers/net/ethernet/apple/mace.c +++ b/drivers/net/ethernet/apple/mace.c @@ -102,7 +102,6 @@ static const struct net_device_ops mace_netdev_ops = { .ndo_start_xmit = mace_xmit_start, .ndo_set_rx_mode = mace_set_multicast, .ndo_set_mac_address = mace_set_address, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/apple/macmace.c b/drivers/net/ethernet/apple/macmace.c index 89914ca17a49..857df9c45f04 100644 --- a/drivers/net/ethernet/apple/macmace.c +++ b/drivers/net/ethernet/apple/macmace.c @@ -186,7 +186,6 @@ static const struct net_device_ops mace_netdev_ops = { .ndo_tx_timeout = mace_tx_timeout, .ndo_set_rx_mode = mace_set_multicast, .ndo_set_mac_address = mace_set_address, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index b047fd607b83..453dc0967125 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -1032,7 +1032,6 @@ static const struct net_device_ops nb8800_netdev_ops = { .ndo_set_mac_address = nb8800_set_mac_address, .ndo_set_rx_mode = nb8800_set_rx_mode, .ndo_do_ioctl = nb8800_ioctl, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index b32444a3ed79..20e72044b765 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -2793,7 +2793,6 @@ static const struct net_device_ops at91ether_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, .ndo_do_ioctl = macb_ioctl, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = at91ether_poll_controller, #endif diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c index c363b58552e9..3647b28e8de0 100644 --- a/drivers/net/ethernet/cirrus/cs89x0.c +++ b/drivers/net/ethernet/cirrus/cs89x0.c @@ -1266,7 +1266,6 @@ static const struct net_device_ops net_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = net_poll_controller, #endif - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/cirrus/ep93xx_eth.c b/drivers/net/ethernet/cirrus/ep93xx_eth.c index de9f7c97d916..9119af088821 100644 --- a/drivers/net/ethernet/cirrus/ep93xx_eth.c +++ b/drivers/net/ethernet/cirrus/ep93xx_eth.c @@ -749,7 +749,6 @@ static const struct net_device_ops ep93xx_netdev_ops = { .ndo_start_xmit = ep93xx_xmit, .ndo_do_ioctl = ep93xx_ioctl, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, }; diff --git a/drivers/net/ethernet/cirrus/mac89x0.c b/drivers/net/ethernet/cirrus/mac89x0.c index 07719676c305..b600fbbbf679 100644 --- a/drivers/net/ethernet/cirrus/mac89x0.c +++ b/drivers/net/ethernet/cirrus/mac89x0.c @@ -172,7 +172,6 @@ static const struct net_device_ops mac89x0_netdev_ops = { .ndo_set_rx_mode = set_multicast_list, .ndo_set_mac_address = set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, }; /* Probe for the CS8900 card in slot E. We won't bother looking diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index f45385f5c6e5..f1a81c52afe3 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -1382,7 +1382,6 @@ static const struct net_device_ops dm9000_netdev_ops = { .ndo_tx_timeout = dm9000_timeout, .ndo_set_rx_mode = dm9000_hash_table, .ndo_do_ioctl = dm9000_ioctl, - .ndo_change_mtu = eth_change_mtu, .ndo_set_features = dm9000_set_features, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c index cadcee645f74..90c573b8ccaf 100644 --- a/drivers/net/ethernet/dec/tulip/de2104x.c +++ b/drivers/net/ethernet/dec/tulip/de2104x.c @@ -1956,7 +1956,6 @@ static const struct net_device_ops de_netdev_ops = { .ndo_start_xmit = de_start_xmit, .ndo_get_stats = de_get_stats, .ndo_tx_timeout = de_tx_timeout, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c index 6620fc861c47..51fda3a6b13f 100644 --- a/drivers/net/ethernet/dec/tulip/de4x5.c +++ b/drivers/net/ethernet/dec/tulip/de4x5.c @@ -1085,7 +1085,6 @@ static const struct net_device_ops de4x5_netdev_ops = { .ndo_get_stats = de4x5_get_stats, .ndo_set_rx_mode = set_multicast_list, .ndo_do_ioctl = de4x5_ioctl, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address= eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/dec/tulip/dmfe.c b/drivers/net/ethernet/dec/tulip/dmfe.c index 8ed0fd8b1dda..df4994919456 100644 --- a/drivers/net/ethernet/dec/tulip/dmfe.c +++ b/drivers/net/ethernet/dec/tulip/dmfe.c @@ -352,7 +352,6 @@ static const struct net_device_ops netdev_ops = { .ndo_stop = dmfe_stop, .ndo_start_xmit = dmfe_start_xmit, .ndo_set_rx_mode = dmfe_set_filter_mode, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index bbde90bc74fe..5f1377449b8f 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -1282,7 +1282,6 @@ static const struct net_device_ops tulip_netdev_ops = { .ndo_get_stats = tulip_get_stats, .ndo_do_ioctl = private_ioctl, .ndo_set_rx_mode = set_rx_mode, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c index e750b5ddc0fb..e1c4133b8787 100644 --- a/drivers/net/ethernet/dec/tulip/uli526x.c +++ b/drivers/net/ethernet/dec/tulip/uli526x.c @@ -269,7 +269,6 @@ static const struct net_device_ops netdev_ops = { .ndo_stop = uli526x_stop, .ndo_start_xmit = uli526x_start_xmit, .ndo_set_rx_mode = uli526x_set_filter_mode, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c index 1f62b9423851..feda96d585e7 100644 --- a/drivers/net/ethernet/dec/tulip/winbond-840.c +++ b/drivers/net/ethernet/dec/tulip/winbond-840.c @@ -353,7 +353,6 @@ static const struct net_device_ops netdev_ops = { .ndo_set_rx_mode = set_rx_mode, .ndo_do_ioctl = netdev_ioctl, .ndo_tx_timeout = tx_timeout, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/dec/tulip/xircom_cb.c b/drivers/net/ethernet/dec/tulip/xircom_cb.c index 0e721cedfa67..19e4ea15b504 100644 --- a/drivers/net/ethernet/dec/tulip/xircom_cb.c +++ b/drivers/net/ethernet/dec/tulip/xircom_cb.c @@ -174,7 +174,6 @@ static const struct net_device_ops netdev_ops = { .ndo_open = xircom_open, .ndo_stop = xircom_close, .ndo_start_xmit = xircom_start_xmit, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c index c3b64cdd0dec..2a17c59f69f9 100644 --- a/drivers/net/ethernet/dnet.c +++ b/drivers/net/ethernet/dnet.c @@ -767,7 +767,6 @@ static const struct net_device_ops dnet_netdev_ops = { .ndo_do_ioctl = dnet_ioctl, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, }; static int dnet_probe(struct platform_device *pdev) diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c index f7b42483921c..57650953ff83 100644 --- a/drivers/net/ethernet/ec_bhf.c +++ b/drivers/net/ethernet/ec_bhf.c @@ -482,7 +482,6 @@ static const struct net_device_ops ec_bhf_netdev_ops = { .ndo_open = ec_bhf_open, .ndo_stop = ec_bhf_stop, .ndo_get_stats64 = ec_bhf_get_stats, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr }; diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c index c08bd763172a..6967b287b6e7 100644 --- a/drivers/net/ethernet/fealnx.c +++ b/drivers/net/ethernet/fealnx.c @@ -472,7 +472,6 @@ static const struct net_device_ops netdev_ops = { .ndo_set_rx_mode = set_rx_mode, .ndo_do_ioctl = mii_ioctl, .ndo_tx_timeout = fealnx_tx_timeout, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 48a033e64423..4ce8179aa4ff 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3055,7 +3055,6 @@ static const struct net_device_ops fec_netdev_ops = { .ndo_stop = fec_enet_close, .ndo_start_xmit = fec_enet_start_xmit, .ndo_set_rx_mode = set_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_tx_timeout = fec_timeout, .ndo_set_mac_address = fec_set_mac_address, diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c index 446ae9d60c71..aa8cf5d2a53c 100644 --- a/drivers/net/ethernet/freescale/fec_mpc52xx.c +++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c @@ -802,7 +802,6 @@ static const struct net_device_ops mpc52xx_fec_netdev_ops = { .ndo_set_mac_address = mpc52xx_fec_set_mac_address, .ndo_validate_addr = eth_validate_addr, .ndo_do_ioctl = mpc52xx_fec_ioctl, - .ndo_change_mtu = eth_change_mtu, .ndo_tx_timeout = mpc52xx_fec_tx_timeout, .ndo_get_stats = mpc52xx_fec_get_stats, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c index dc120c148d97..925d1bca6a26 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c @@ -912,7 +912,6 @@ static const struct net_device_ops fs_enet_netdev_ops = { .ndo_do_ioctl = fs_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_change_mtu = eth_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = fs_enet_netpoll, #endif diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index 186ef8f16c80..786182480a73 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -3681,7 +3681,6 @@ static const struct net_device_ops ucc_geth_netdev_ops = { .ndo_start_xmit = ucc_geth_start_xmit, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = ucc_geth_set_mac_addr, - .ndo_change_mtu = eth_change_mtu, .ndo_set_rx_mode = ucc_geth_set_multi, .ndo_tx_timeout = ucc_geth_timeout, .ndo_do_ioctl = ucc_geth_ioctl, diff --git a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c index 399cfd217288..51c4abc51bf4 100644 --- a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c +++ b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c @@ -225,7 +225,6 @@ static const struct net_device_ops fjn_netdev_ops = { .ndo_tx_timeout = fjn_tx_timeout, .ndo_set_config = fjn_config, .ndo_set_rx_mode = set_rx_mode, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index 39778892b3b3..3c99ca420f57 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -769,7 +769,6 @@ static const struct net_device_ops hip04_netdev_ops = { .ndo_set_mac_address = hip04_set_mac_address, .ndo_tx_timeout = hip04_timeout, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, }; static int hip04_alloc_ring(struct net_device *ndev, struct device *d) diff --git a/drivers/net/ethernet/hisilicon/hisi_femac.c b/drivers/net/ethernet/hisilicon/hisi_femac.c index ced185962ef8..49863068c59e 100644 --- a/drivers/net/ethernet/hisilicon/hisi_femac.c +++ b/drivers/net/ethernet/hisilicon/hisi_femac.c @@ -712,7 +712,6 @@ static const struct net_device_ops hisi_femac_netdev_ops = { .ndo_do_ioctl = hisi_femac_net_ioctl, .ndo_set_mac_address = hisi_femac_set_mac_address, .ndo_set_rx_mode = hisi_femac_net_set_rx_mode, - .ndo_change_mtu = eth_change_mtu, }; static void hisi_femac_core_reset(struct hisi_femac_priv *priv) diff --git a/drivers/net/ethernet/hp/hp100.c b/drivers/net/ethernet/hp/hp100.c index 631dbc7b4dbb..1a31bee6e728 100644 --- a/drivers/net/ethernet/hp/hp100.c +++ b/drivers/net/ethernet/hp/hp100.c @@ -427,7 +427,6 @@ static const struct net_device_ops hp100_bm_netdev_ops = { .ndo_start_xmit = hp100_start_xmit_bm, .ndo_get_stats = hp100_get_stats, .ndo_set_rx_mode = hp100_set_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; @@ -438,7 +437,6 @@ static const struct net_device_ops hp100_netdev_ops = { .ndo_start_xmit = hp100_start_xmit, .ndo_get_stats = hp100_get_stats, .ndo_set_rx_mode = hp100_set_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/i825xx/82596.c b/drivers/net/ethernet/i825xx/82596.c index ce235b776793..945883842533 100644 --- a/drivers/net/ethernet/i825xx/82596.c +++ b/drivers/net/ethernet/i825xx/82596.c @@ -1118,7 +1118,6 @@ static const struct net_device_ops i596_netdev_ops = { .ndo_start_xmit = i596_start_xmit, .ndo_set_rx_mode = set_multicast_list, .ndo_tx_timeout = i596_tx_timeout, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/i825xx/ether1.c b/drivers/net/ethernet/i825xx/ether1.c index 5d353c660068..dc983450354b 100644 --- a/drivers/net/ethernet/i825xx/ether1.c +++ b/drivers/net/ethernet/i825xx/ether1.c @@ -981,7 +981,6 @@ static const struct net_device_ops ether1_netdev_ops = { .ndo_set_rx_mode = ether1_setmulticastlist, .ndo_tx_timeout = ether1_timeout, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, }; diff --git a/drivers/net/ethernet/i825xx/lib82596.c b/drivers/net/ethernet/i825xx/lib82596.c index 3dbc53c21baa..e86773325cbe 100644 --- a/drivers/net/ethernet/i825xx/lib82596.c +++ b/drivers/net/ethernet/i825xx/lib82596.c @@ -1037,7 +1037,6 @@ static const struct net_device_ops i596_netdev_ops = { .ndo_start_xmit = i596_start_xmit, .ndo_set_rx_mode = set_multicast_list, .ndo_tx_timeout = i596_tx_timeout, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/i825xx/sun3_82586.c b/drivers/net/ethernet/i825xx/sun3_82586.c index 21c84cc9c871..8bb15a8c2a40 100644 --- a/drivers/net/ethernet/i825xx/sun3_82586.c +++ b/drivers/net/ethernet/i825xx/sun3_82586.c @@ -337,7 +337,6 @@ static const struct net_device_ops sun3_82586_netdev_ops = { .ndo_get_stats = sun3_82586_get_stats, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_change_mtu = eth_change_mtu, }; static int __init sun3_82586_probe1(struct net_device *dev,int ioaddr) diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 8f139197f1aa..5d804a544674 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -2718,7 +2718,6 @@ static const struct net_device_ops emac_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = emac_set_mac_address, .ndo_start_xmit = emac_start_xmit, - .ndo_change_mtu = eth_change_mtu, }; static const struct net_device_ops emac_gige_netdev_ops = { diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c index 1799fe1415df..cbeea915f026 100644 --- a/drivers/net/ethernet/korina.c +++ b/drivers/net/ethernet/korina.c @@ -1085,7 +1085,6 @@ static const struct net_device_ops korina_netdev_ops = { .ndo_set_rx_mode = korina_multicast_list, .ndo_tx_timeout = korina_tx_timeout, .ndo_do_ioctl = korina_ioctl, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 91e09d68b7e2..1a739d71f1c2 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -519,18 +519,16 @@ ltq_etop_tx(struct sk_buff *skb, struct net_device *dev) static int ltq_etop_change_mtu(struct net_device *dev, int new_mtu) { - int ret = eth_change_mtu(dev, new_mtu); + struct ltq_etop_priv *priv = netdev_priv(dev); + unsigned long flags; - if (!ret) { - struct ltq_etop_priv *priv = netdev_priv(dev); - unsigned long flags; + dev->mtu = new_mtu; - spin_lock_irqsave(&priv->lock, flags); - ltq_etop_w32((ETOP_PLEN_UNDER << 16) | new_mtu, - LTQ_ETOP_IGPLEN); - spin_unlock_irqrestore(&priv->lock, flags); - } - return ret; + spin_lock_irqsave(&priv->lock, flags); + ltq_etop_w32((ETOP_PLEN_UNDER << 16) | new_mtu, LTQ_ETOP_IGPLEN); + spin_unlock_irqrestore(&priv->lock, flags); + + return 0; } static int diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 4a62ffd7729d..8f80e618ae59 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -2243,7 +2243,6 @@ static const struct net_device_ops mtk_netdev_ops = { .ndo_set_mac_address = mtk_set_mac_address, .ndo_validate_addr = eth_validate_addr, .ndo_do_ioctl = mtk_do_ioctl, - .ndo_change_mtu = eth_change_mtu, .ndo_tx_timeout = mtk_tx_timeout, .ndo_get_stats64 = mtk_get_stats64, .ndo_fix_features = mtk_fix_features, diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c index 1edc973df4c4..e7e1aff40bd9 100644 --- a/drivers/net/ethernet/micrel/ks8851.c +++ b/drivers/net/ethernet/micrel/ks8851.c @@ -1063,7 +1063,6 @@ static const struct net_device_ops ks8851_netdev_ops = { .ndo_start_xmit = ks8851_start_xmit, .ndo_set_mac_address = ks8851_set_mac_address, .ndo_set_rx_mode = ks8851_set_rx_mode, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c index 2fc5cd56c0a8..db628078a4e6 100644 --- a/drivers/net/ethernet/micrel/ks8851_mll.c +++ b/drivers/net/ethernet/micrel/ks8851_mll.c @@ -1285,7 +1285,6 @@ static const struct net_device_ops ks_netdev_ops = { .ndo_start_xmit = ks_start_xmit, .ndo_set_mac_address = ks_set_mac_address, .ndo_set_rx_mode = ks_set_rx_mode, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/microchip/enc28j60.c b/drivers/net/ethernet/microchip/enc28j60.c index 0a26b11ca8f6..045b9106c0ff 100644 --- a/drivers/net/ethernet/microchip/enc28j60.c +++ b/drivers/net/ethernet/microchip/enc28j60.c @@ -1544,7 +1544,6 @@ static const struct net_device_ops enc28j60_netdev_ops = { .ndo_set_rx_mode = enc28j60_set_multicast_list, .ndo_set_mac_address = enc28j60_set_mac_address, .ndo_tx_timeout = enc28j60_tx_timeout, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index 4367dd6879a2..9774b50cff6e 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -444,7 +444,6 @@ static struct net_device_ops moxart_netdev_ops = { .ndo_set_rx_mode = moxart_mac_set_rx_mode, .ndo_set_mac_address = moxart_set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, }; static int moxart_mac_probe(struct platform_device *pdev) diff --git a/drivers/net/ethernet/natsemi/jazzsonic.c b/drivers/net/ethernet/natsemi/jazzsonic.c index acf3f11e38cc..a6caeb567c0d 100644 --- a/drivers/net/ethernet/natsemi/jazzsonic.c +++ b/drivers/net/ethernet/natsemi/jazzsonic.c @@ -110,7 +110,6 @@ static const struct net_device_ops sonic_netdev_ops = { .ndo_get_stats = sonic_get_stats, .ndo_set_rx_mode = sonic_multicast_list, .ndo_tx_timeout = sonic_tx_timeout, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, }; diff --git a/drivers/net/ethernet/natsemi/macsonic.c b/drivers/net/ethernet/natsemi/macsonic.c index d98f5b8a1c66..3ca6ae7caf55 100644 --- a/drivers/net/ethernet/natsemi/macsonic.c +++ b/drivers/net/ethernet/natsemi/macsonic.c @@ -190,7 +190,6 @@ static const struct net_device_ops macsonic_netdev_ops = { .ndo_tx_timeout = sonic_tx_timeout, .ndo_get_stats = sonic_get_stats, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, }; diff --git a/drivers/net/ethernet/natsemi/xtsonic.c b/drivers/net/ethernet/natsemi/xtsonic.c index 7007d212f3e4..9ee0f69a83c0 100644 --- a/drivers/net/ethernet/natsemi/xtsonic.c +++ b/drivers/net/ethernet/natsemi/xtsonic.c @@ -124,7 +124,6 @@ static const struct net_device_ops xtsonic_netdev_ops = { .ndo_set_rx_mode = sonic_multicast_list, .ndo_tx_timeout = sonic_tx_timeout, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, }; diff --git a/drivers/net/ethernet/netx-eth.c b/drivers/net/ethernet/netx-eth.c index adbc47f2d132..df4188cb43e0 100644 --- a/drivers/net/ethernet/netx-eth.c +++ b/drivers/net/ethernet/netx-eth.c @@ -304,7 +304,6 @@ static const struct net_device_ops netx_eth_netdev_ops = { .ndo_start_xmit = netx_eth_hard_start_xmit, .ndo_tx_timeout = netx_eth_timeout, .ndo_set_rx_mode = netx_eth_set_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, }; diff --git a/drivers/net/ethernet/nuvoton/w90p910_ether.c b/drivers/net/ethernet/nuvoton/w90p910_ether.c index 712d8bcb7d8c..119f6dca71f0 100644 --- a/drivers/net/ethernet/nuvoton/w90p910_ether.c +++ b/drivers/net/ethernet/nuvoton/w90p910_ether.c @@ -915,7 +915,6 @@ static const struct net_device_ops w90p910_ether_netdev_ops = { .ndo_set_mac_address = w90p910_set_mac_address, .ndo_do_ioctl = w90p910_ether_ioctl, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, }; static void __init get_mac_address(struct net_device *dev) diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index 8e13ec84c538..dd6b0d0f7fa5 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -1256,7 +1256,6 @@ static const struct net_device_ops lpc_netdev_ops = { .ndo_do_ioctl = lpc_eth_ioctl, .ndo_set_mac_address = lpc_set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, }; static int lpc_eth_drv_probe(struct platform_device *pdev) diff --git a/drivers/net/ethernet/packetengines/hamachi.c b/drivers/net/ethernet/packetengines/hamachi.c index 91be2f02ef1c..2d04679a923a 100644 --- a/drivers/net/ethernet/packetengines/hamachi.c +++ b/drivers/net/ethernet/packetengines/hamachi.c @@ -568,7 +568,6 @@ static const struct net_device_ops hamachi_netdev_ops = { .ndo_start_xmit = hamachi_start_xmit, .ndo_get_stats = hamachi_get_stats, .ndo_set_rx_mode = set_rx_mode, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_tx_timeout = hamachi_tx_timeout, diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c index fb1d1031b091..2a2ca5fa0c69 100644 --- a/drivers/net/ethernet/packetengines/yellowfin.c +++ b/drivers/net/ethernet/packetengines/yellowfin.c @@ -360,7 +360,6 @@ static const struct net_device_ops netdev_ops = { .ndo_stop = yellowfin_close, .ndo_start_xmit = yellowfin_start_xmit, .ndo_set_rx_mode = set_rx_mode, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_do_ioctl = netdev_ioctl, diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index b09a6b80d107..5c100ab86c00 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -3755,7 +3755,6 @@ static const struct net_device_ops ql3xxx_netdev_ops = { .ndo_open = ql3xxx_open, .ndo_start_xmit = ql3xxx_send, .ndo_stop = ql3xxx_close, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = ql3xxx_set_mac_address, .ndo_tx_timeout = ql3xxx_tx_timeout, diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c index 5ef5d728c250..4ff4e0491406 100644 --- a/drivers/net/ethernet/rdc/r6040.c +++ b/drivers/net/ethernet/rdc/r6040.c @@ -969,7 +969,6 @@ static const struct net_device_ops r6040_netdev_ops = { .ndo_start_xmit = r6040_start_xmit, .ndo_get_stats = r6040_get_stats, .ndo_set_rx_mode = r6040_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_do_ioctl = r6040_ioctl, diff --git a/drivers/net/ethernet/realtek/atp.c b/drivers/net/ethernet/realtek/atp.c index 5cb96785fb63..570ed3bd3cbf 100644 --- a/drivers/net/ethernet/realtek/atp.c +++ b/drivers/net/ethernet/realtek/atp.c @@ -245,7 +245,6 @@ static const struct net_device_ops atp_netdev_ops = { .ndo_start_xmit = atp_send_packet, .ndo_set_rx_mode = set_rx_mode, .ndo_tx_timeout = tx_timeout, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 630536bc72f9..27cfec3154c8 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1780,7 +1780,6 @@ static const struct net_device_ops ravb_netdev_ops = { .ndo_do_ioctl = ravb_do_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_change_mtu = eth_change_mtu, }; /* MDIO bus init function */ diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 05b0dc55de77..e443695c2757 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -2914,7 +2914,6 @@ static const struct net_device_ops sh_eth_netdev_ops = { .ndo_do_ioctl = sh_eth_do_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_change_mtu = eth_change_mtu, }; static const struct net_device_ops sh_eth_netdev_ops_tsu = { @@ -2929,7 +2928,6 @@ static const struct net_device_ops sh_eth_netdev_ops_tsu = { .ndo_do_ioctl = sh_eth_do_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_change_mtu = eth_change_mtu, }; #ifdef CONFIG_OF diff --git a/drivers/net/ethernet/seeq/ether3.c b/drivers/net/ethernet/seeq/ether3.c index bdac936a68bc..244c1e171017 100644 --- a/drivers/net/ethernet/seeq/ether3.c +++ b/drivers/net/ethernet/seeq/ether3.c @@ -745,7 +745,6 @@ static const struct net_device_ops ether3_netdev_ops = { .ndo_set_rx_mode = ether3_setmulticastlist, .ndo_tx_timeout = ether3_timeout, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, }; diff --git a/drivers/net/ethernet/seeq/sgiseeq.c b/drivers/net/ethernet/seeq/sgiseeq.c index c2bd5378ffda..ed34196028b8 100644 --- a/drivers/net/ethernet/seeq/sgiseeq.c +++ b/drivers/net/ethernet/seeq/sgiseeq.c @@ -714,7 +714,6 @@ static const struct net_device_ops sgiseeq_netdev_ops = { .ndo_tx_timeout = timeout, .ndo_set_rx_mode = sgiseeq_set_multicast, .ndo_set_mac_address = sgiseeq_set_mac_address, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c index 7a254da85dd7..42051ab98cf0 100644 --- a/drivers/net/ethernet/sgi/ioc3-eth.c +++ b/drivers/net/ethernet/sgi/ioc3-eth.c @@ -1225,7 +1225,6 @@ static const struct net_device_ops ioc3_netdev_ops = { .ndo_do_ioctl = ioc3_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = ioc3_set_mac_address, - .ndo_change_mtu = eth_change_mtu, }; static int ioc3_probe(struct pci_dev *pdev, const struct pci_device_id *ent) diff --git a/drivers/net/ethernet/sgi/meth.c b/drivers/net/ethernet/sgi/meth.c index aaa80f13859b..69d2d30e5ef1 100644 --- a/drivers/net/ethernet/sgi/meth.c +++ b/drivers/net/ethernet/sgi/meth.c @@ -815,7 +815,6 @@ static const struct net_device_ops meth_netdev_ops = { .ndo_start_xmit = meth_tx, .ndo_do_ioctl = meth_ioctl, .ndo_tx_timeout = meth_tx_timeout, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_set_rx_mode = meth_set_rx_mode, diff --git a/drivers/net/ethernet/silan/sc92031.c b/drivers/net/ethernet/silan/sc92031.c index 7426f8b21252..6c2e2b311c16 100644 --- a/drivers/net/ethernet/silan/sc92031.c +++ b/drivers/net/ethernet/silan/sc92031.c @@ -1386,7 +1386,6 @@ static const struct net_device_ops sc92031_netdev_ops = { .ndo_open = sc92031_open, .ndo_stop = sc92031_stop, .ndo_set_rx_mode = sc92031_set_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_tx_timeout = sc92031_tx_timeout, diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c index 27be6c869315..210e35d079dd 100644 --- a/drivers/net/ethernet/sis/sis190.c +++ b/drivers/net/ethernet/sis/sis190.c @@ -1833,7 +1833,6 @@ static const struct net_device_ops sis190_netdev_ops = { .ndo_start_xmit = sis190_start_xmit, .ndo_tx_timeout = sis190_tx_timeout, .ndo_set_rx_mode = sis190_set_rx_mode, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = sis190_mac_addr, .ndo_validate_addr = eth_validate_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index 6f85276376e8..39fca6c0b68d 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -400,7 +400,6 @@ static const struct net_device_ops sis900_netdev_ops = { .ndo_start_xmit = sis900_start_xmit, .ndo_set_config = sis900_set_config, .ndo_set_rx_mode = set_rx_mode, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_do_ioctl = mii_ioctl, diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c index 7186b89269ad..fe9760ffab51 100644 --- a/drivers/net/ethernet/smsc/epic100.c +++ b/drivers/net/ethernet/smsc/epic100.c @@ -313,7 +313,6 @@ static const struct net_device_ops epic_netdev_ops = { .ndo_get_stats = epic_get_stats, .ndo_set_rx_mode = set_rx_mode, .ndo_do_ioctl = netdev_ioctl, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c index cb49c9654f0a..4f19c6166182 100644 --- a/drivers/net/ethernet/smsc/smc911x.c +++ b/drivers/net/ethernet/smsc/smc911x.c @@ -1753,7 +1753,6 @@ static const struct net_device_ops smc911x_netdev_ops = { .ndo_start_xmit = smc911x_hard_start_xmit, .ndo_tx_timeout = smc911x_timeout, .ndo_set_rx_mode = smc911x_set_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/smsc/smc9194.c b/drivers/net/ethernet/smsc/smc9194.c index d496888b85d3..c8d84679ede7 100644 --- a/drivers/net/ethernet/smsc/smc9194.c +++ b/drivers/net/ethernet/smsc/smc9194.c @@ -809,7 +809,6 @@ static const struct net_device_ops smc_netdev_ops = { .ndo_start_xmit = smc_wait_to_send_packet, .ndo_tx_timeout = smc_timeout, .ndo_set_rx_mode = smc_set_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/smsc/smc91c92_cs.c b/drivers/net/ethernet/smsc/smc91c92_cs.c index db3c696d7002..f1c75e291e55 100644 --- a/drivers/net/ethernet/smsc/smc91c92_cs.c +++ b/drivers/net/ethernet/smsc/smc91c92_cs.c @@ -294,7 +294,6 @@ static const struct net_device_ops smc_netdev_ops = { .ndo_set_config = s9k_config, .ndo_set_rx_mode = set_rx_mode, .ndo_do_ioctl = smc_ioctl, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 73212590d04a..9b4780f87863 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -1762,7 +1762,6 @@ static const struct net_device_ops smc_netdev_ops = { .ndo_start_xmit = smc_hard_start_xmit, .ndo_tx_timeout = smc_timeout, .ndo_set_rx_mode = smc_set_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index e9b8579e6241..cdb343f0c6e0 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -2152,7 +2152,6 @@ static const struct net_device_ops smsc911x_netdev_ops = { .ndo_get_stats = smsc911x_get_stats, .ndo_set_rx_mode = smsc911x_set_multicast_list, .ndo_do_ioctl = smsc911x_do_ioctl, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = smsc911x_set_mac_address, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c index aa4f9d2d8fa9..ea89ef3b48fb 100644 --- a/drivers/net/ethernet/sun/sunbmac.c +++ b/drivers/net/ethernet/sun/sunbmac.c @@ -1064,7 +1064,6 @@ static const struct net_device_ops bigmac_ops = { .ndo_get_stats = bigmac_get_stats, .ndo_set_rx_mode = bigmac_set_multicast, .ndo_tx_timeout = bigmac_tx_timeout, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index cf4dcff051d5..ca96408058b0 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -2669,7 +2669,6 @@ static const struct net_device_ops hme_netdev_ops = { .ndo_tx_timeout = happy_meal_tx_timeout, .ndo_get_stats = happy_meal_get_stats, .ndo_set_rx_mode = happy_meal_set_multicast, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/sun/sunqe.c b/drivers/net/ethernet/sun/sunqe.c index 9b825780b3be..c5ef711f6567 100644 --- a/drivers/net/ethernet/sun/sunqe.c +++ b/drivers/net/ethernet/sun/sunqe.c @@ -823,7 +823,6 @@ static const struct net_device_ops qec_ops = { .ndo_start_xmit = qe_start_xmit, .ndo_set_rx_mode = qe_set_multicast, .ndo_tx_timeout = qe_tx_timeout, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c index fa0cfda24fd9..c56e7030c44e 100644 --- a/drivers/net/ethernet/ti/cpmac.c +++ b/drivers/net/ethernet/ti/cpmac.c @@ -1068,7 +1068,6 @@ static const struct net_device_ops cpmac_netdev_ops = { .ndo_tx_timeout = cpmac_tx_timeout, .ndo_set_rx_mode = cpmac_set_multicast_list, .ndo_do_ioctl = cpmac_ioctl, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, }; diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 6d4b8a2e0cf6..b1ddf89a19be 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1883,7 +1883,6 @@ static const struct net_device_ops cpsw_netdev_ops = { .ndo_set_mac_address = cpsw_ndo_set_mac_address, .ndo_do_ioctl = cpsw_ndo_ioctl, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, .ndo_tx_timeout = cpsw_ndo_tx_timeout, .ndo_set_rx_mode = cpsw_ndo_set_rx_mode, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c index ece0ea0f6b38..4a3eeb10d45b 100644 --- a/drivers/net/ethernet/ti/tlan.c +++ b/drivers/net/ethernet/ti/tlan.c @@ -772,7 +772,6 @@ static const struct net_device_ops tlan_netdev_ops = { .ndo_get_stats = tlan_get_stats, .ndo_set_rx_mode = tlan_set_multicast_list, .ndo_do_ioctl = tlan_ioctl, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c index 5b01b3fa9fec..3be61ed28741 100644 --- a/drivers/net/ethernet/toshiba/tc35815.c +++ b/drivers/net/ethernet/toshiba/tc35815.c @@ -747,7 +747,6 @@ static const struct net_device_ops tc35815_netdev_ops = { .ndo_tx_timeout = tc35815_tx_timeout, .ndo_do_ioctl = tc35815_ioctl, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = tc35815_poll_controller, diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c index 8fd131207ee1..f153ad729ce5 100644 --- a/drivers/net/ethernet/tundra/tsi108_eth.c +++ b/drivers/net/ethernet/tundra/tsi108_eth.c @@ -1548,7 +1548,6 @@ static const struct net_device_ops tsi108_netdev_ops = { .ndo_do_ioctl = tsi108_do_ioctl, .ndo_set_mac_address = tsi108_set_mac, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, }; static int diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index 9d14731cdcb1..ba5c54249055 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -890,7 +890,6 @@ static const struct net_device_ops rhine_netdev_ops = { .ndo_start_xmit = rhine_start_tx, .ndo_get_stats64 = rhine_get_stats64, .ndo_set_rx_mode = rhine_set_rx_mode, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_do_ioctl = netdev_ioctl, diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c index d2349a1bc6ba..e1296ef2cf66 100644 --- a/drivers/net/ethernet/wiznet/w5100.c +++ b/drivers/net/ethernet/wiznet/w5100.c @@ -1045,7 +1045,6 @@ static const struct net_device_ops w5100_netdev_ops = { .ndo_set_rx_mode = w5100_set_rx_mode, .ndo_set_mac_address = w5100_set_macaddr, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, }; static int w5100_mmio_probe(struct platform_device *pdev) diff --git a/drivers/net/ethernet/wiznet/w5300.c b/drivers/net/ethernet/wiznet/w5300.c index ca31a57dbc86..724fabd38a23 100644 --- a/drivers/net/ethernet/wiznet/w5300.c +++ b/drivers/net/ethernet/wiznet/w5300.c @@ -536,7 +536,6 @@ static const struct net_device_ops w5300_netdev_ops = { .ndo_set_rx_mode = w5300_set_rx_mode, .ndo_set_mac_address = w5300_set_macaddr, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, }; static int w5300_hw_probe(struct platform_device *pdev) diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c index ddced28e8247..3b08ec766076 100644 --- a/drivers/net/ethernet/xircom/xirc2ps_cs.c +++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c @@ -466,7 +466,6 @@ static const struct net_device_ops netdev_ops = { .ndo_set_config = do_config, .ndo_do_ioctl = do_ioctl, .ndo_set_rx_mode = set_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c index 7f127dc1b7ba..46cc33b9e926 100644 --- a/drivers/net/ethernet/xscale/ixp4xx_eth.c +++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c @@ -1379,7 +1379,6 @@ static const struct net_device_ops ixp4xx_netdev_ops = { .ndo_start_xmit = eth_xmit, .ndo_set_rx_mode = eth_set_mcast_list, .ndo_do_ioctl = eth_ioctl, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/plip/plip.c b/drivers/net/plip/plip.c index 9c4b41a4df7d..3c55ea357f35 100644 --- a/drivers/net/plip/plip.c +++ b/drivers/net/plip/plip.c @@ -270,7 +270,6 @@ static const struct net_device_ops plip_netdev_ops = { .ndo_stop = plip_close, .ndo_start_xmit = plip_tx_packet, .ndo_do_ioctl = plip_ioctl, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/sb1000.c b/drivers/net/sb1000.c index aad0b59d41e3..8b8b53259783 100644 --- a/drivers/net/sb1000.c +++ b/drivers/net/sb1000.c @@ -141,7 +141,6 @@ static const struct net_device_ops sb1000_netdev_ops = { .ndo_start_xmit = sb1000_start_xmit, .ndo_do_ioctl = sb1000_dev_ioctl, .ndo_stop = sb1000_close, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c index d9ca05d3ac8e..a1f2f6f1e614 100644 --- a/drivers/net/usb/catc.c +++ b/drivers/net/usb/catc.c @@ -761,7 +761,6 @@ static const struct net_device_ops catc_netdev_ops = { .ndo_tx_timeout = catc_tx_timeout, .ndo_set_rx_mode = catc_set_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c index 66b34ddbe216..338aed5da14d 100644 --- a/drivers/net/usb/kaweth.c +++ b/drivers/net/usb/kaweth.c @@ -982,7 +982,6 @@ static const struct net_device_ops kaweth_netdev_ops = { .ndo_tx_timeout = kaweth_tx_timeout, .ndo_set_rx_mode = kaweth_set_rx_mode, .ndo_get_stats = kaweth_netdev_stats, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index 1434e5dd5f9c..399f7ee57aea 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -1273,7 +1273,6 @@ static const struct net_device_ops pegasus_netdev_ops = { .ndo_set_rx_mode = pegasus_set_multicast, .ndo_get_stats = pegasus_netdev_stats, .ndo_tx_timeout = pegasus_tx_timeout, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 44d439f50961..2886946ca371 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -4113,7 +4113,8 @@ static int rtl8152_change_mtu(struct net_device *dev, int new_mtu) switch (tp->version) { case RTL_VER_01: case RTL_VER_02: - return eth_change_mtu(dev, new_mtu); + dev->mtu = new_mtu; + return 0; default: break; } diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 7c72bfac89d0..93a1bda1c1e5 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -847,7 +847,6 @@ static const struct net_device_ops rtl8150_netdev_ops = { .ndo_set_rx_mode = rtl8150_set_multicast, .ndo_set_mac_address = rtl8150_set_mac_address, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/wan/sbni.c b/drivers/net/wan/sbni.c index 3a421ca8a4d0..3f83be98d469 100644 --- a/drivers/net/wan/sbni.c +++ b/drivers/net/wan/sbni.c @@ -211,7 +211,6 @@ static const struct net_device_ops sbni_netdev_ops = { .ndo_start_xmit = sbni_start_xmit, .ndo_set_rx_mode = set_multicast_list, .ndo_do_ioctl = sbni_ioctl, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/wireless/intersil/prism54/islpci_dev.c b/drivers/net/wireless/intersil/prism54/islpci_dev.c index 84a42012aeae..325176d4d796 100644 --- a/drivers/net/wireless/intersil/prism54/islpci_dev.c +++ b/drivers/net/wireless/intersil/prism54/islpci_dev.c @@ -808,7 +808,6 @@ static const struct net_device_ops islpci_netdev_ops = { .ndo_start_xmit = islpci_eth_transmit, .ndo_tx_timeout = islpci_eth_tx_timeout, .ndo_set_mac_address = prism54_set_mac_address, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 431f13b4faf6..e95b79bccf9b 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -2791,7 +2791,6 @@ static void mac80211_hwsim_free(void) static const struct net_device_ops hwsim_netdev_ops = { .ndo_start_xmit = hwsim_mon_xmit, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/wireless/marvell/libertas/main.c b/drivers/net/wireless/marvell/libertas/main.c index 8541cbed786d..e3500203715c 100644 --- a/drivers/net/wireless/marvell/libertas/main.c +++ b/drivers/net/wireless/marvell/libertas/main.c @@ -945,7 +945,6 @@ static const struct net_device_ops lbs_netdev_ops = { .ndo_start_xmit = lbs_hard_start_xmit, .ndo_set_mac_address = lbs_set_mac_address, .ndo_set_rx_mode = lbs_set_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c index 0881ba8535f4..4fdc7223c894 100644 --- a/drivers/net/wireless/ray_cs.c +++ b/drivers/net/wireless/ray_cs.c @@ -272,7 +272,6 @@ static const struct net_device_ops ray_netdev_ops = { .ndo_set_config = ray_dev_config, .ndo_get_stats = ray_get_stats, .ndo_set_rx_mode = set_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/wireless/wl3501_cs.c b/drivers/net/wireless/wl3501_cs.c index 932f3f81e8cf..d9d29ab88184 100644 --- a/drivers/net/wireless/wl3501_cs.c +++ b/drivers/net/wireless/wl3501_cs.c @@ -1853,7 +1853,6 @@ static const struct net_device_ops wl3501_netdev_ops = { .ndo_stop = wl3501_close, .ndo_start_xmit = wl3501_hard_start_xmit, .ndo_tx_timeout = wl3501_tx_timeout, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/wireless/zydas/zd1201.c b/drivers/net/wireless/zydas/zd1201.c index dea049b2556f..de7ff395977a 100644 --- a/drivers/net/wireless/zydas/zd1201.c +++ b/drivers/net/wireless/zydas/zd1201.c @@ -1724,7 +1724,6 @@ static const struct net_device_ops zd1201_netdev_ops = { .ndo_tx_timeout = zd1201_tx_timeout, .ndo_set_rx_mode = zd1201_set_multicast, .ndo_set_mac_address = zd1201_set_mac_address, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/staging/rtl8188eu/os_dep/mon.c b/drivers/staging/rtl8188eu/os_dep/mon.c index d976e5e18d50..c9c9821cfc32 100644 --- a/drivers/staging/rtl8188eu/os_dep/mon.c +++ b/drivers/staging/rtl8188eu/os_dep/mon.c @@ -145,7 +145,6 @@ static netdev_tx_t mon_xmit(struct sk_buff *skb, struct net_device *dev) static const struct net_device_ops mon_netdev_ops = { .ndo_start_xmit = mon_xmit, - .ndo_change_mtu = eth_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 4c30eea45f89..5f53fbd565ef 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -2545,7 +2545,6 @@ static const struct net_device_ops rtl8192_netdev_ops = { .ndo_set_rx_mode = _rtl92e_set_multicast, .ndo_set_mac_address = _rtl92e_set_mac_adr, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, .ndo_start_xmit = rtllib_xmit, }; diff --git a/drivers/staging/rtl8192u/r8192U_core.c b/drivers/staging/rtl8192u/r8192U_core.c index 457eeb5f5239..fdb03dccb449 100644 --- a/drivers/staging/rtl8192u/r8192U_core.c +++ b/drivers/staging/rtl8192u/r8192U_core.c @@ -4930,7 +4930,6 @@ static const struct net_device_ops rtl8192_netdev_ops = { .ndo_set_rx_mode = r8192_set_multicast, .ndo_set_mac_address = r8192_set_mac_adr, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, .ndo_start_xmit = ieee80211_xmit, }; diff --git a/drivers/staging/slicoss/slicoss.c b/drivers/staging/slicoss/slicoss.c index 062307ad7fed..2802b900f8ee 100644 --- a/drivers/staging/slicoss/slicoss.c +++ b/drivers/staging/slicoss/slicoss.c @@ -2880,7 +2880,6 @@ static const struct net_device_ops slic_netdev_ops = { .ndo_get_stats = slic_get_stats, .ndo_set_rx_mode = slic_mcast_set_list, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = eth_change_mtu, }; static u32 slic_card_locate(struct adapter *adapter) 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. */ diff --git a/net/atm/br2684.c b/net/atm/br2684.c index aa0047c5c467..c7d82f4e8422 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -620,14 +620,12 @@ error: static const struct net_device_ops br2684_netdev_ops = { .ndo_start_xmit = br2684_start_xmit, .ndo_set_mac_address = br2684_mac_addr, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, }; static const struct net_device_ops br2684_netdev_ops_routed = { .ndo_start_xmit = br2684_start_xmit, .ndo_set_mac_address = br2684_mac_addr, - .ndo_change_mtu = eth_change_mtu }; static void br2684_setup(struct net_device *netdev) diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c index f4fcb4a9d5c1..0f25ddc319e2 100644 --- a/net/bluetooth/bnep/netdev.c +++ b/net/bluetooth/bnep/netdev.c @@ -211,7 +211,6 @@ static const struct net_device_ops bnep_netdev_ops = { .ndo_set_rx_mode = bnep_net_set_mc_list, .ndo_set_mac_address = bnep_net_set_mac_addr, .ndo_tx_timeout = bnep_net_timeout, - .ndo_change_mtu = eth_change_mtu, }; diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 66dff5e3d772..f983c102ebe3 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -322,8 +322,7 @@ EXPORT_SYMBOL(eth_mac_addr); */ int eth_change_mtu(struct net_device *dev, int new_mtu) { - if (new_mtu < 68 || new_mtu > ETH_DATA_LEN) - return -EINVAL; + netdev_warn(dev, "%s is deprecated\n", __func__); dev->mtu = new_mtu; return 0; } @@ -357,6 +356,8 @@ void ether_setup(struct net_device *dev) dev->type = ARPHRD_ETHER; dev->hard_header_len = ETH_HLEN; dev->mtu = ETH_DATA_LEN; + dev->min_mtu = ETH_MIN_MTU; + dev->max_mtu = ETH_DATA_LEN; dev->addr_len = ETH_ALEN; dev->tx_queue_len = 1000; /* Ethernet wants good queues */ dev->flags = IFF_BROADCAST|IFF_MULTICAST; diff --git a/net/irda/irlan/irlan_eth.c b/net/irda/irlan/irlan_eth.c index d8b7267280c3..8192eaea4ecd 100644 --- a/net/irda/irlan/irlan_eth.c +++ b/net/irda/irlan/irlan_eth.c @@ -51,7 +51,6 @@ static const struct net_device_ops irlan_eth_netdev_ops = { .ndo_stop = irlan_eth_close, .ndo_start_xmit = irlan_eth_xmit, .ndo_set_rx_mode = irlan_eth_set_multicast_list, - .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, }; -- cgit v1.2.3 From 2e0cbc4dd077aea4f1693583fd68eaed4d60464b Mon Sep 17 00:00:00 2001 From: Ram Amrani Date: Mon, 10 Oct 2016 13:15:30 +0300 Subject: qedr: Add RoCE driver framework Adds a skeletal implementation of the qed* RoCE driver - basically the ability to communicate with the qede driver and receive notifications from it regarding various init/exit events. Signed-off-by: Rajesh Borundia Signed-off-by: Ram Amrani Signed-off-by: Doug Ledford --- drivers/infiniband/Kconfig | 2 + drivers/infiniband/hw/Makefile | 1 + drivers/infiniband/hw/qedr/Kconfig | 7 + drivers/infiniband/hw/qedr/Makefile | 3 + drivers/infiniband/hw/qedr/main.c | 254 ++++++++++++++++++++++++++++++++++++ drivers/infiniband/hw/qedr/qedr.h | 61 +++++++++ drivers/net/ethernet/qlogic/Kconfig | 11 -- include/uapi/linux/pci_regs.h | 3 + 8 files changed, 331 insertions(+), 11 deletions(-) create mode 100644 drivers/infiniband/hw/qedr/Kconfig create mode 100644 drivers/infiniband/hw/qedr/Makefile create mode 100644 drivers/infiniband/hw/qedr/main.c create mode 100644 drivers/infiniband/hw/qedr/qedr.h (limited to 'include/uapi/linux') diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig index 19a418a1b631..fb3fb89640e5 100644 --- a/drivers/infiniband/Kconfig +++ b/drivers/infiniband/Kconfig @@ -89,4 +89,6 @@ source "drivers/infiniband/sw/rxe/Kconfig" source "drivers/infiniband/hw/hfi1/Kconfig" +source "drivers/infiniband/hw/qedr/Kconfig" + endif # INFINIBAND diff --git a/drivers/infiniband/hw/Makefile b/drivers/infiniband/hw/Makefile index 21fe401ff178..e7a5ed9f6f3f 100644 --- a/drivers/infiniband/hw/Makefile +++ b/drivers/infiniband/hw/Makefile @@ -10,3 +10,4 @@ obj-$(CONFIG_INFINIBAND_OCRDMA) += ocrdma/ obj-$(CONFIG_INFINIBAND_USNIC) += usnic/ obj-$(CONFIG_INFINIBAND_HFI1) += hfi1/ obj-$(CONFIG_INFINIBAND_HNS) += hns/ +obj-$(CONFIG_INFINIBAND_QEDR) += qedr/ diff --git a/drivers/infiniband/hw/qedr/Kconfig b/drivers/infiniband/hw/qedr/Kconfig new file mode 100644 index 000000000000..7c06d85568d4 --- /dev/null +++ b/drivers/infiniband/hw/qedr/Kconfig @@ -0,0 +1,7 @@ +config INFINIBAND_QEDR + tristate "QLogic RoCE driver" + depends on 64BIT && QEDE + select QED_LL2 + ---help--- + This driver provides low-level InfiniBand over Ethernet + support for QLogic QED host channel adapters (HCAs). diff --git a/drivers/infiniband/hw/qedr/Makefile b/drivers/infiniband/hw/qedr/Makefile new file mode 100644 index 000000000000..3a5b7a288281 --- /dev/null +++ b/drivers/infiniband/hw/qedr/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_INFINIBAND_QEDR) := qedr.o + +qedr-y := main.o diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c new file mode 100644 index 000000000000..7387d029a35b --- /dev/null +++ b/drivers/infiniband/hw/qedr/main.c @@ -0,0 +1,254 @@ +/* QLogic qedr NIC Driver + * Copyright (c) 2015-2016 QLogic Corporation + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and /or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ +#include +#include +#include +#include +#include +#include +#include +#include "qedr.h" + +MODULE_DESCRIPTION("QLogic 40G/100G ROCE Driver"); +MODULE_AUTHOR("QLogic Corporation"); +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_VERSION(QEDR_MODULE_VERSION); + +void qedr_ib_dispatch_event(struct qedr_dev *dev, u8 port_num, + enum ib_event_type type) +{ + struct ib_event ibev; + + ibev.device = &dev->ibdev; + ibev.element.port_num = port_num; + ibev.event = type; + + ib_dispatch_event(&ibev); +} + +static enum rdma_link_layer qedr_link_layer(struct ib_device *device, + u8 port_num) +{ + return IB_LINK_LAYER_ETHERNET; +} + +static int qedr_register_device(struct qedr_dev *dev) +{ + strlcpy(dev->ibdev.name, "qedr%d", IB_DEVICE_NAME_MAX); + + memcpy(dev->ibdev.node_desc, QEDR_NODE_DESC, sizeof(QEDR_NODE_DESC)); + dev->ibdev.owner = THIS_MODULE; + + dev->ibdev.get_link_layer = qedr_link_layer; + + return 0; +} + +/* QEDR sysfs interface */ +static ssize_t show_rev(struct device *device, struct device_attribute *attr, + char *buf) +{ + struct qedr_dev *dev = dev_get_drvdata(device); + + return scnprintf(buf, PAGE_SIZE, "0x%x\n", dev->pdev->vendor); +} + +static ssize_t show_hca_type(struct device *device, + struct device_attribute *attr, char *buf) +{ + return scnprintf(buf, PAGE_SIZE, "%s\n", "HCA_TYPE_TO_SET"); +} + +static DEVICE_ATTR(hw_rev, S_IRUGO, show_rev, NULL); +static DEVICE_ATTR(hca_type, S_IRUGO, show_hca_type, NULL); + +static struct device_attribute *qedr_attributes[] = { + &dev_attr_hw_rev, + &dev_attr_hca_type +}; + +static void qedr_remove_sysfiles(struct qedr_dev *dev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(qedr_attributes); i++) + device_remove_file(&dev->ibdev.dev, qedr_attributes[i]); +} + +static void qedr_pci_set_atomic(struct qedr_dev *dev, struct pci_dev *pdev) +{ + struct pci_dev *bridge; + u32 val; + + dev->atomic_cap = IB_ATOMIC_NONE; + + bridge = pdev->bus->self; + if (!bridge) + return; + + /* Check whether we are connected directly or via a switch */ + while (bridge && bridge->bus->parent) { + DP_DEBUG(dev, QEDR_MSG_INIT, + "Device is not connected directly to root. bridge->bus->number=%d primary=%d\n", + bridge->bus->number, bridge->bus->primary); + /* Need to check Atomic Op Routing Supported all the way to + * root complex. + */ + pcie_capability_read_dword(bridge, PCI_EXP_DEVCAP2, &val); + if (!(val & PCI_EXP_DEVCAP2_ATOMIC_ROUTE)) { + pcie_capability_clear_word(pdev, + PCI_EXP_DEVCTL2, + PCI_EXP_DEVCTL2_ATOMIC_REQ); + return; + } + bridge = bridge->bus->parent->self; + } + bridge = pdev->bus->self; + + /* according to bridge capability */ + pcie_capability_read_dword(bridge, PCI_EXP_DEVCAP2, &val); + if (val & PCI_EXP_DEVCAP2_ATOMIC_COMP64) { + pcie_capability_set_word(pdev, PCI_EXP_DEVCTL2, + PCI_EXP_DEVCTL2_ATOMIC_REQ); + dev->atomic_cap = IB_ATOMIC_GLOB; + } else { + pcie_capability_clear_word(pdev, PCI_EXP_DEVCTL2, + PCI_EXP_DEVCTL2_ATOMIC_REQ); + } +} + +static struct qedr_dev *qedr_add(struct qed_dev *cdev, struct pci_dev *pdev, + struct net_device *ndev) +{ + struct qedr_dev *dev; + int rc = 0, i; + + dev = (struct qedr_dev *)ib_alloc_device(sizeof(*dev)); + if (!dev) { + pr_err("Unable to allocate ib device\n"); + return NULL; + } + + DP_DEBUG(dev, QEDR_MSG_INIT, "qedr add device called\n"); + + dev->pdev = pdev; + dev->ndev = ndev; + dev->cdev = cdev; + + qedr_pci_set_atomic(dev, pdev); + + rc = qedr_register_device(dev); + if (rc) { + DP_ERR(dev, "Unable to allocate register device\n"); + goto init_err; + } + + for (i = 0; i < ARRAY_SIZE(qedr_attributes); i++) + if (device_create_file(&dev->ibdev.dev, qedr_attributes[i])) + goto init_err; + + DP_DEBUG(dev, QEDR_MSG_INIT, "qedr driver loaded successfully\n"); + return dev; + +init_err: + ib_dealloc_device(&dev->ibdev); + DP_ERR(dev, "qedr driver load failed rc=%d\n", rc); + + return NULL; +} + +static void qedr_remove(struct qedr_dev *dev) +{ + /* First unregister with stack to stop all the active traffic + * of the registered clients. + */ + qedr_remove_sysfiles(dev); + + ib_dealloc_device(&dev->ibdev); +} + +static int qedr_close(struct qedr_dev *dev) +{ + qedr_ib_dispatch_event(dev, 1, IB_EVENT_PORT_ERR); + + return 0; +} + +static void qedr_shutdown(struct qedr_dev *dev) +{ + qedr_close(dev); + qedr_remove(dev); +} + +/* event handling via NIC driver ensures that all the NIC specific + * initialization done before RoCE driver notifies + * event to stack. + */ +static void qedr_notify(struct qedr_dev *dev, enum qede_roce_event event) +{ + switch (event) { + case QEDE_UP: + qedr_ib_dispatch_event(dev, 1, IB_EVENT_PORT_ACTIVE); + break; + case QEDE_DOWN: + qedr_close(dev); + break; + case QEDE_CLOSE: + qedr_shutdown(dev); + break; + case QEDE_CHANGE_ADDR: + qedr_ib_dispatch_event(dev, 1, IB_EVENT_GID_CHANGE); + break; + default: + pr_err("Event not supported\n"); + } +} + +static struct qedr_driver qedr_drv = { + .name = "qedr_driver", + .add = qedr_add, + .remove = qedr_remove, + .notify = qedr_notify, +}; + +static int __init qedr_init_module(void) +{ + return qede_roce_register_driver(&qedr_drv); +} + +static void __exit qedr_exit_module(void) +{ + qede_roce_unregister_driver(&qedr_drv); +} + +module_init(qedr_init_module); +module_exit(qedr_exit_module); diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h new file mode 100644 index 000000000000..801417080f11 --- /dev/null +++ b/drivers/infiniband/hw/qedr/qedr.h @@ -0,0 +1,61 @@ +/* QLogic qedr NIC Driver + * Copyright (c) 2015-2016 QLogic Corporation + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and /or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ +#ifndef __QEDR_H__ +#define __QEDR_H__ + +#include +#include +#include +#include + +#define QEDR_MODULE_VERSION "8.10.10.0" +#define QEDR_NODE_DESC "QLogic 579xx RoCE HCA" +#define DP_NAME(dev) ((dev)->ibdev.name) + +#define DP_DEBUG(dev, module, fmt, ...) \ + pr_debug("(%s) " module ": " fmt, \ + DP_NAME(dev) ? DP_NAME(dev) : "", ## __VA_ARGS__) + +#define QEDR_MSG_INIT "INIT" + +struct qedr_dev { + struct ib_device ibdev; + struct qed_dev *cdev; + struct pci_dev *pdev; + struct net_device *ndev; + + enum ib_atomic_cap atomic_cap; + + u32 dp_module; + u8 dp_level; +}; +#endif diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig index 0df1391f9663..1e8339a67f6e 100644 --- a/drivers/net/ethernet/qlogic/Kconfig +++ b/drivers/net/ethernet/qlogic/Kconfig @@ -107,15 +107,4 @@ config QEDE ---help--- This enables the support for ... -config INFINIBAND_QEDR - tristate "QLogic qede RoCE sources [debug]" - depends on QEDE && 64BIT - select QED_LL2 - default n - ---help--- - This provides a temporary node that allows the compilation - and logical testing of the InfiniBand over Ethernet support - for QLogic QED. This would be replaced by the 'real' option - once the QEDR driver is added [+relocated]. - endif # NET_VENDOR_QLOGIC diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index d812172d1d7b..e5a2e68b2236 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -612,6 +612,8 @@ */ #define PCI_EXP_DEVCAP2 36 /* Device Capabilities 2 */ #define PCI_EXP_DEVCAP2_ARI 0x00000020 /* Alternative Routing-ID */ +#define PCI_EXP_DEVCAP2_ATOMIC_ROUTE 0x00000040 /* Atomic Op routing */ +#define PCI_EXP_DEVCAP2_ATOMIC_COMP64 0x00000100 /* Atomic 64-bit compare */ #define PCI_EXP_DEVCAP2_LTR 0x00000800 /* Latency tolerance reporting */ #define PCI_EXP_DEVCAP2_OBFF_MASK 0x000c0000 /* OBFF support mechanism */ #define PCI_EXP_DEVCAP2_OBFF_MSG 0x00040000 /* New message signaling */ @@ -619,6 +621,7 @@ #define PCI_EXP_DEVCTL2 40 /* Device Control 2 */ #define PCI_EXP_DEVCTL2_COMP_TIMEOUT 0x000f /* Completion Timeout Value */ #define PCI_EXP_DEVCTL2_ARI 0x0020 /* Alternative Routing-ID */ +#define PCI_EXP_DEVCTL2_ATOMIC_REQ 0x0040 /* Set Atomic requests */ #define PCI_EXP_DEVCTL2_IDO_REQ_EN 0x0100 /* Allow IDO for requests */ #define PCI_EXP_DEVCTL2_IDO_CMP_EN 0x0200 /* Allow IDO for completions */ #define PCI_EXP_DEVCTL2_LTR_EN 0x0400 /* Enable LTR mechanism */ -- cgit v1.2.3 From 85a624403c77c3f074931aefdfced59f61b668cb Mon Sep 17 00:00:00 2001 From: Jesse Brandeburg Date: Thu, 13 Oct 2016 16:13:55 -0700 Subject: ethtool: silence warning on bit loss Sparse was complaining when we went to prototype some code using ethtool_cmd_speed_set and SPEED_100000, which uses the upper 16 bits of __u32 speed for the first time. CHECK ... .../uapi/linux/ethtool.h:123:28: warning: cast truncates bits from constant value (186a0 becomes 86a0) The warning is actually bogus, as no bits are really lost, but we can get rid of the sparse warning with this one small change. Reported-by: Preethi Banala Signed-off-by: Jesse Brandeburg Signed-off-by: David S. Miller --- include/uapi/linux/ethtool.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 099a4200732c..8e547231c1b7 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -119,8 +119,7 @@ struct ethtool_cmd { static inline void ethtool_cmd_speed_set(struct ethtool_cmd *ep, __u32 speed) { - - ep->speed = (__u16)speed; + ep->speed = (__u16)(speed & 0xFFFF); ep->speed_hi = (__u16)(speed >> 16); } -- cgit v1.2.3 From 6a0cb1bc106fc07ce0443303bcdb7f7da5131e5c Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 18 Oct 2016 15:40:33 +0900 Subject: block: Implement support for zoned block devices Implement zoned block device zone information reporting and reset. Zone information are reported as struct blk_zone. This implementation does not differentiate between host-aware and host-managed device models and is valid for both. Two functions are provided: blkdev_report_zones for discovering the zone configuration of a zoned block device, and blkdev_reset_zones for resetting the write pointer of sequential zones. The helper function blk_queue_zone_size and bdev_zone_size are also provided for, as the name suggest, obtaining the zone size (in 512B sectors) of the zones of the device. Signed-off-by: Hannes Reinecke [Damien: * Removed the zone cache * Implement report zones operation based on earlier proposal by Shaun Tancheff ] Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Shaun Tancheff Tested-by: Shaun Tancheff Signed-off-by: Jens Axboe --- block/Kconfig | 8 ++ block/Makefile | 1 + block/blk-zoned.c | 257 ++++++++++++++++++++++++++++++++++++++++++ include/linux/blkdev.h | 31 +++++ include/uapi/linux/Kbuild | 1 + include/uapi/linux/blkzoned.h | 103 +++++++++++++++++ 6 files changed, 401 insertions(+) create mode 100644 block/blk-zoned.c create mode 100644 include/uapi/linux/blkzoned.h (limited to 'include/uapi/linux') diff --git a/block/Kconfig b/block/Kconfig index 1d4d624492fc..6b0ad08f0677 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -89,6 +89,14 @@ config BLK_DEV_INTEGRITY T10/SCSI Data Integrity Field or the T13/ATA External Path Protection. If in doubt, say N. +config BLK_DEV_ZONED + bool "Zoned block device support" + ---help--- + Block layer zoned block device support. This option enables + support for ZAC/ZBC host-managed and host-aware zoned block devices. + + Say yes here if you have a ZAC or ZBC storage device. + config BLK_DEV_THROTTLING bool "Block layer bio throttling support" depends on BLK_CGROUP=y diff --git a/block/Makefile b/block/Makefile index 36acdd7545be..934dac73fb37 100644 --- a/block/Makefile +++ b/block/Makefile @@ -23,3 +23,4 @@ obj-$(CONFIG_BLOCK_COMPAT) += compat_ioctl.o obj-$(CONFIG_BLK_CMDLINE_PARSER) += cmdline-parser.o obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o obj-$(CONFIG_BLK_MQ_PCI) += blk-mq-pci.o +obj-$(CONFIG_BLK_DEV_ZONED) += blk-zoned.o diff --git a/block/blk-zoned.c b/block/blk-zoned.c new file mode 100644 index 000000000000..1603573f9605 --- /dev/null +++ b/block/blk-zoned.c @@ -0,0 +1,257 @@ +/* + * Zoned block device handling + * + * Copyright (c) 2015, Hannes Reinecke + * Copyright (c) 2015, SUSE Linux GmbH + * + * Copyright (c) 2016, Damien Le Moal + * Copyright (c) 2016, Western Digital + */ + +#include +#include +#include +#include + +static inline sector_t blk_zone_start(struct request_queue *q, + sector_t sector) +{ + sector_t zone_mask = blk_queue_zone_size(q) - 1; + + return sector & ~zone_mask; +} + +/* + * Check that a zone report belongs to the partition. + * If yes, fix its start sector and write pointer, copy it in the + * zone information array and return true. Return false otherwise. + */ +static bool blkdev_report_zone(struct block_device *bdev, + struct blk_zone *rep, + struct blk_zone *zone) +{ + sector_t offset = get_start_sect(bdev); + + if (rep->start < offset) + return false; + + rep->start -= offset; + if (rep->start + rep->len > bdev->bd_part->nr_sects) + return false; + + if (rep->type == BLK_ZONE_TYPE_CONVENTIONAL) + rep->wp = rep->start + rep->len; + else + rep->wp -= offset; + memcpy(zone, rep, sizeof(struct blk_zone)); + + return true; +} + +/** + * blkdev_report_zones - Get zones information + * @bdev: Target block device + * @sector: Sector from which to report zones + * @zones: Array of zone structures where to return the zones information + * @nr_zones: Number of zone structures in the zone array + * @gfp_mask: Memory allocation flags (for bio_alloc) + * + * Description: + * Get zone information starting from the zone containing @sector. + * The number of zone information reported may be less than the number + * requested by @nr_zones. The number of zones actually reported is + * returned in @nr_zones. + */ +int blkdev_report_zones(struct block_device *bdev, + sector_t sector, + struct blk_zone *zones, + unsigned int *nr_zones, + gfp_t gfp_mask) +{ + struct request_queue *q = bdev_get_queue(bdev); + struct blk_zone_report_hdr *hdr; + unsigned int nrz = *nr_zones; + struct page *page; + unsigned int nr_rep; + size_t rep_bytes; + unsigned int nr_pages; + struct bio *bio; + struct bio_vec *bv; + unsigned int i, n, nz; + unsigned int ofst; + void *addr; + int ret = 0; + + if (!q) + return -ENXIO; + + if (!blk_queue_is_zoned(q)) + return -EOPNOTSUPP; + + if (!nrz) + return 0; + + if (sector > bdev->bd_part->nr_sects) { + *nr_zones = 0; + return 0; + } + + /* + * The zone report has a header. So make room for it in the + * payload. Also make sure that the report fits in a single BIO + * that will not be split down the stack. + */ + rep_bytes = sizeof(struct blk_zone_report_hdr) + + sizeof(struct blk_zone) * nrz; + rep_bytes = (rep_bytes + PAGE_SIZE - 1) & PAGE_MASK; + if (rep_bytes > (queue_max_sectors(q) << 9)) + rep_bytes = queue_max_sectors(q) << 9; + + nr_pages = min_t(unsigned int, BIO_MAX_PAGES, + rep_bytes >> PAGE_SHIFT); + nr_pages = min_t(unsigned int, nr_pages, + queue_max_segments(q)); + + bio = bio_alloc(gfp_mask, nr_pages); + if (!bio) + return -ENOMEM; + + bio->bi_bdev = bdev; + bio->bi_iter.bi_sector = blk_zone_start(q, sector); + bio_set_op_attrs(bio, REQ_OP_ZONE_REPORT, 0); + + for (i = 0; i < nr_pages; i++) { + page = alloc_page(gfp_mask); + if (!page) { + ret = -ENOMEM; + goto out; + } + if (!bio_add_page(bio, page, PAGE_SIZE, 0)) { + __free_page(page); + break; + } + } + + if (i == 0) + ret = -ENOMEM; + else + ret = submit_bio_wait(bio); + if (ret) + goto out; + + /* + * Process the report result: skip the header and go through the + * reported zones to fixup and fixup the zone information for + * partitions. At the same time, return the zone information into + * the zone array. + */ + n = 0; + nz = 0; + nr_rep = 0; + bio_for_each_segment_all(bv, bio, i) { + + if (!bv->bv_page) + break; + + addr = kmap_atomic(bv->bv_page); + + /* Get header in the first page */ + ofst = 0; + if (!nr_rep) { + hdr = (struct blk_zone_report_hdr *) addr; + nr_rep = hdr->nr_zones; + ofst = sizeof(struct blk_zone_report_hdr); + } + + /* Fixup and report zones */ + while (ofst < bv->bv_len && + n < nr_rep && nz < nrz) { + if (blkdev_report_zone(bdev, addr + ofst, &zones[nz])) + nz++; + ofst += sizeof(struct blk_zone); + n++; + } + + kunmap_atomic(addr); + + if (n >= nr_rep || nz >= nrz) + break; + + } + +out: + bio_for_each_segment_all(bv, bio, i) + __free_page(bv->bv_page); + bio_put(bio); + + if (ret == 0) + *nr_zones = nz; + + return ret; +} +EXPORT_SYMBOL_GPL(blkdev_report_zones); + +/** + * blkdev_reset_zones - Reset zones write pointer + * @bdev: Target block device + * @sector: Start sector of the first zone to reset + * @nr_sectors: Number of sectors, at least the length of one zone + * @gfp_mask: Memory allocation flags (for bio_alloc) + * + * Description: + * Reset the write pointer of the zones contained in the range + * @sector..@sector+@nr_sectors. Specifying the entire disk sector range + * is valid, but the specified range should not contain conventional zones. + */ +int blkdev_reset_zones(struct block_device *bdev, + sector_t sector, sector_t nr_sectors, + gfp_t gfp_mask) +{ + struct request_queue *q = bdev_get_queue(bdev); + sector_t zone_sectors; + sector_t end_sector = sector + nr_sectors; + struct bio *bio; + int ret; + + if (!q) + return -ENXIO; + + if (!blk_queue_is_zoned(q)) + return -EOPNOTSUPP; + + if (end_sector > bdev->bd_part->nr_sects) + /* Out of range */ + return -EINVAL; + + /* Check alignment (handle eventual smaller last zone) */ + zone_sectors = blk_queue_zone_size(q); + if (sector & (zone_sectors - 1)) + return -EINVAL; + + if ((nr_sectors & (zone_sectors - 1)) && + end_sector != bdev->bd_part->nr_sects) + return -EINVAL; + + while (sector < end_sector) { + + bio = bio_alloc(gfp_mask, 0); + bio->bi_iter.bi_sector = sector; + bio->bi_bdev = bdev; + bio_set_op_attrs(bio, REQ_OP_ZONE_RESET, 0); + + ret = submit_bio_wait(bio); + bio_put(bio); + + if (ret) + return ret; + + sector += zone_sectors; + + /* This may take a while, so be nice to others */ + cond_resched(); + + } + + return 0; +} +EXPORT_SYMBOL_GPL(blkdev_reset_zones); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f19e16bb43d1..252043f7cd2c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -24,6 +24,7 @@ #include #include #include +#include struct module; struct scsi_ioctl_command; @@ -302,6 +303,21 @@ struct queue_limits { enum blk_zoned_model zoned; }; +#ifdef CONFIG_BLK_DEV_ZONED + +struct blk_zone_report_hdr { + unsigned int nr_zones; + u8 padding[60]; +}; + +extern int blkdev_report_zones(struct block_device *bdev, + sector_t sector, struct blk_zone *zones, + unsigned int *nr_zones, gfp_t gfp_mask); +extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors, + sector_t nr_sectors, gfp_t gfp_mask); + +#endif /* CONFIG_BLK_DEV_ZONED */ + struct request_queue { /* * Together with queue_head for cacheline sharing @@ -654,6 +670,11 @@ static inline bool blk_queue_is_zoned(struct request_queue *q) } } +static inline unsigned int blk_queue_zone_size(struct request_queue *q) +{ + return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; +} + /* * We regard a request as sync, if either a read or a sync write */ @@ -1401,6 +1422,16 @@ static inline bool bdev_is_zoned(struct block_device *bdev) return false; } +static inline unsigned int bdev_zone_size(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (q) + return blk_queue_zone_size(q); + + return 0; +} + static inline int queue_dma_alignment(struct request_queue *q) { return q ? q->dma_alignment : 511; diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 6965d0909554..b2166f283da9 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -70,6 +70,7 @@ header-y += bfs_fs.h header-y += binfmts.h header-y += blkpg.h header-y += blktrace_api.h +header-y += blkzoned.h header-y += bpf_common.h header-y += bpf_perf_event.h header-y += bpf.h diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h new file mode 100644 index 000000000000..a3817214b0e0 --- /dev/null +++ b/include/uapi/linux/blkzoned.h @@ -0,0 +1,103 @@ +/* + * Zoned block devices handling. + * + * Copyright (C) 2015 Seagate Technology PLC + * + * Written by: Shaun Tancheff + * + * Modified by: Damien Le Moal + * Copyright (C) 2016 Western Digital + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ +#ifndef _UAPI_BLKZONED_H +#define _UAPI_BLKZONED_H + +#include + +/** + * enum blk_zone_type - Types of zones allowed in a zoned device. + * + * @BLK_ZONE_TYPE_CONVENTIONAL: The zone has no write pointer and can be writen + * randomly. Zone reset has no effect on the zone. + * @BLK_ZONE_TYPE_SEQWRITE_REQ: The zone must be written sequentially + * @BLK_ZONE_TYPE_SEQWRITE_PREF: The zone can be written non-sequentially + * + * Any other value not defined is reserved and must be considered as invalid. + */ +enum blk_zone_type { + BLK_ZONE_TYPE_CONVENTIONAL = 0x1, + BLK_ZONE_TYPE_SEQWRITE_REQ = 0x2, + BLK_ZONE_TYPE_SEQWRITE_PREF = 0x3, +}; + +/** + * enum blk_zone_cond - Condition [state] of a zone in a zoned device. + * + * @BLK_ZONE_COND_NOT_WP: The zone has no write pointer, it is conventional. + * @BLK_ZONE_COND_EMPTY: The zone is empty. + * @BLK_ZONE_COND_IMP_OPEN: The zone is open, but not explicitly opened. + * @BLK_ZONE_COND_EXP_OPEN: The zones was explicitly opened by an + * OPEN ZONE command. + * @BLK_ZONE_COND_CLOSED: The zone was [explicitly] closed after writing. + * @BLK_ZONE_COND_FULL: The zone is marked as full, possibly by a zone + * FINISH ZONE command. + * @BLK_ZONE_COND_READONLY: The zone is read-only. + * @BLK_ZONE_COND_OFFLINE: The zone is offline (sectors cannot be read/written). + * + * The Zone Condition state machine in the ZBC/ZAC standards maps the above + * deinitions as: + * - ZC1: Empty | BLK_ZONE_EMPTY + * - ZC2: Implicit Open | BLK_ZONE_COND_IMP_OPEN + * - ZC3: Explicit Open | BLK_ZONE_COND_EXP_OPEN + * - ZC4: Closed | BLK_ZONE_CLOSED + * - ZC5: Full | BLK_ZONE_FULL + * - ZC6: Read Only | BLK_ZONE_READONLY + * - ZC7: Offline | BLK_ZONE_OFFLINE + * + * Conditions 0x5 to 0xC are reserved by the current ZBC/ZAC spec and should + * be considered invalid. + */ +enum blk_zone_cond { + BLK_ZONE_COND_NOT_WP = 0x0, + BLK_ZONE_COND_EMPTY = 0x1, + BLK_ZONE_COND_IMP_OPEN = 0x2, + BLK_ZONE_COND_EXP_OPEN = 0x3, + BLK_ZONE_COND_CLOSED = 0x4, + BLK_ZONE_COND_READONLY = 0xD, + BLK_ZONE_COND_FULL = 0xE, + BLK_ZONE_COND_OFFLINE = 0xF, +}; + +/** + * struct blk_zone - Zone descriptor for BLKREPORTZONE ioctl. + * + * @start: Zone start in 512 B sector units + * @len: Zone length in 512 B sector units + * @wp: Zone write pointer location in 512 B sector units + * @type: see enum blk_zone_type for possible values + * @cond: see enum blk_zone_cond for possible values + * @non_seq: Flag indicating that the zone is using non-sequential resources + * (for host-aware zoned block devices only). + * @reset: Flag indicating that a zone reset is recommended. + * @reserved: Padding to 64 B to match the ZBC/ZAC defined zone descriptor size. + * + * start, len and wp use the regular 512 B sector unit, regardless of the + * device logical block size. The overall structure size is 64 B to match the + * ZBC/ZAC defined zone descriptor and allow support for future additional + * zone information. + */ +struct blk_zone { + __u64 start; /* Zone start sector */ + __u64 len; /* Zone length in number of sectors */ + __u64 wp; /* Zone write pointer position */ + __u8 type; /* Zone type */ + __u8 cond; /* Zone condition */ + __u8 non_seq; /* Non-sequential write resources active */ + __u8 reset; /* Reset write pointer recommended */ + __u8 reserved[36]; +}; + +#endif /* _UAPI_BLKZONED_H */ -- cgit v1.2.3 From 3ed05a987e0f63b21e634101e0b460d32f3581c3 Mon Sep 17 00:00:00 2001 From: Shaun Tancheff Date: Tue, 18 Oct 2016 15:40:35 +0900 Subject: blk-zoned: implement ioctls Adds the new BLKREPORTZONE and BLKRESETZONE ioctls for respectively obtaining the zone configuration of a zoned block device and resetting the write pointer of sequential zones of a zoned block device. The BLKREPORTZONE ioctl maps directly to a single call of the function blkdev_report_zones. The zone information result is passed as an array of struct blk_zone identical to the structure used internally for processing the REQ_OP_ZONE_REPORT operation. The BLKRESETZONE ioctl maps to a single call of the blkdev_reset_zones function. Signed-off-by: Shaun Tancheff Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- block/blk-zoned.c | 93 +++++++++++++++++++++++++++++++++++++++++++ block/ioctl.c | 4 ++ include/linux/blkdev.h | 21 ++++++++++ include/uapi/linux/blkzoned.h | 40 +++++++++++++++++++ include/uapi/linux/fs.h | 4 ++ 5 files changed, 162 insertions(+) (limited to 'include/uapi/linux') diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 1603573f9605..667f95d86695 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -255,3 +255,96 @@ int blkdev_reset_zones(struct block_device *bdev, return 0; } EXPORT_SYMBOL_GPL(blkdev_reset_zones); + +/** + * BLKREPORTZONE ioctl processing. + * Called from blkdev_ioctl. + */ +int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg) +{ + void __user *argp = (void __user *)arg; + struct request_queue *q; + struct blk_zone_report rep; + struct blk_zone *zones; + int ret; + + if (!argp) + return -EINVAL; + + q = bdev_get_queue(bdev); + if (!q) + return -ENXIO; + + if (!blk_queue_is_zoned(q)) + return -ENOTTY; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + if (copy_from_user(&rep, argp, sizeof(struct blk_zone_report))) + return -EFAULT; + + if (!rep.nr_zones) + return -EINVAL; + + zones = kcalloc(rep.nr_zones, sizeof(struct blk_zone), GFP_KERNEL); + if (!zones) + return -ENOMEM; + + ret = blkdev_report_zones(bdev, rep.sector, + zones, &rep.nr_zones, + GFP_KERNEL); + if (ret) + goto out; + + if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) { + ret = -EFAULT; + goto out; + } + + if (rep.nr_zones) { + if (copy_to_user(argp + sizeof(struct blk_zone_report), zones, + sizeof(struct blk_zone) * rep.nr_zones)) + ret = -EFAULT; + } + + out: + kfree(zones); + + return ret; +} + +/** + * BLKRESETZONE ioctl processing. + * Called from blkdev_ioctl. + */ +int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg) +{ + void __user *argp = (void __user *)arg; + struct request_queue *q; + struct blk_zone_range zrange; + + if (!argp) + return -EINVAL; + + q = bdev_get_queue(bdev); + if (!q) + return -ENXIO; + + if (!blk_queue_is_zoned(q)) + return -ENOTTY; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + if (!(mode & FMODE_WRITE)) + return -EBADF; + + if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range))) + return -EFAULT; + + return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors, + GFP_KERNEL); +} diff --git a/block/ioctl.c b/block/ioctl.c index 755119c3c1b9..f856963204f4 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -519,6 +519,10 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, BLKDEV_DISCARD_SECURE); case BLKZEROOUT: return blk_ioctl_zeroout(bdev, mode, arg); + case BLKREPORTZONE: + return blkdev_report_zones_ioctl(bdev, mode, cmd, arg); + case BLKRESETZONE: + return blkdev_reset_zones_ioctl(bdev, mode, cmd, arg); case HDIO_GETGEO: return blkdev_getgeo(bdev, argp); case BLKRAGET: diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 252043f7cd2c..90097dd8b8ed 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -316,6 +316,27 @@ extern int blkdev_report_zones(struct block_device *bdev, extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); +extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg); +extern int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg); + +#else /* CONFIG_BLK_DEV_ZONED */ + +static inline int blkdev_report_zones_ioctl(struct block_device *bdev, + fmode_t mode, unsigned int cmd, + unsigned long arg) +{ + return -ENOTTY; +} + +static inline int blkdev_reset_zones_ioctl(struct block_device *bdev, + fmode_t mode, unsigned int cmd, + unsigned long arg) +{ + return -ENOTTY; +} + #endif /* CONFIG_BLK_DEV_ZONED */ struct request_queue { diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h index a3817214b0e0..40d1d7bff537 100644 --- a/include/uapi/linux/blkzoned.h +++ b/include/uapi/linux/blkzoned.h @@ -16,6 +16,7 @@ #define _UAPI_BLKZONED_H #include +#include /** * enum blk_zone_type - Types of zones allowed in a zoned device. @@ -100,4 +101,43 @@ struct blk_zone { __u8 reserved[36]; }; +/** + * struct blk_zone_report - BLKREPORTZONE ioctl request/reply + * + * @sector: starting sector of report + * @nr_zones: IN maximum / OUT actual + * @reserved: padding to 16 byte alignment + * @zones: Space to hold @nr_zones @zones entries on reply. + * + * The array of at most @nr_zones must follow this structure in memory. + */ +struct blk_zone_report { + __u64 sector; + __u32 nr_zones; + __u8 reserved[4]; + struct blk_zone zones[0]; +} __packed; + +/** + * struct blk_zone_range - BLKRESETZONE ioctl request + * @sector: starting sector of the first zone to issue reset write pointer + * @nr_sectors: Total number of sectors of 1 or more zones to reset + */ +struct blk_zone_range { + __u64 sector; + __u64 nr_sectors; +}; + +/** + * Zoned block device ioctl's: + * + * @BLKREPORTZONE: Get zone information. Takes a zone report as argument. + * The zone report will start from the zone containing the + * sector specified in the report request structure. + * @BLKRESETZONE: Reset the write pointer of the zones in the specified + * sector range. The sector range must be zone aligned. + */ +#define BLKREPORTZONE _IOWR(0x12, 130, struct blk_zone_report) +#define BLKRESETZONE _IOW(0x12, 131, struct blk_zone_range) + #endif /* _UAPI_BLKZONED_H */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index acb2b6152ba0..c1d11df07b28 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -225,6 +225,10 @@ struct fsxattr { #define BLKSECDISCARD _IO(0x12,125) #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) +/* + * A jump here: 130-131 are reserved for zoned block devices + * (see uapi/linux/blkzoned.h) + */ #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ -- cgit v1.2.3 From 85dda4e5b0ee1f5b4e8cc93d39e475006bc61ccd Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 18 Oct 2016 18:59:34 +0200 Subject: rtnetlink: Add rtnexthop offload flag to compare mask The offload flag is a status flag and should not be used by FIB semantics for comparison. Fixes: 37ed9493699c ("rtnetlink: add RTNH_F_EXTERNAL flag for fib offload") Signed-off-by: Jiri Pirko Reviewed-by: Andy Gospodarek Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 262f0379d83a..5a78be518101 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -350,7 +350,7 @@ struct rtnexthop { #define RTNH_F_OFFLOAD 8 /* offloaded route */ #define RTNH_F_LINKDOWN 16 /* carrier-down on nexthop */ -#define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN) +#define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN | RTNH_F_OFFLOAD) /* Macros to handle hexthops */ -- 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 --- drivers/net/ethernet/alteon/acenic.c | 5 ++--- drivers/net/ethernet/amazon/ena/ena_netdev.c | 9 ++------- drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 5 ----- drivers/net/ethernet/amd/xgbe/xgbe-main.c | 2 ++ drivers/net/ethernet/broadcom/sb1250-mac.c | 12 ++---------- drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c | 4 ++-- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 6 ++++-- .../net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c | 6 ++---- drivers/net/ethernet/emulex/benet/be_main.c | 22 ++++------------------ drivers/net/ethernet/ibm/ibmveth.c | 6 +++--- drivers/net/ethernet/ibm/ibmvnic.c | 16 ++++------------ drivers/net/ethernet/jme.c | 12 ++++-------- drivers/net/ethernet/marvell/mv643xx_eth.c | 7 ++++--- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 3 +++ drivers/net/ethernet/mellanox/mlxsw/switchx2.c | 3 +++ drivers/net/ethernet/natsemi/ns83820.c | 11 ++--------- drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c | 12 ------------ .../net/ethernet/qlogic/netxen/netxen_nic_main.c | 7 +++++++ drivers/net/ethernet/qlogic/qlge/qlge_main.c | 7 +++++++ drivers/net/ethernet/qualcomm/emac/emac.c | 13 ++++++------- drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 7 ++++--- include/uapi/linux/if_ether.h | 1 + 22 files changed, 68 insertions(+), 108 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c index b90a26b13fdf..a5c1e290677a 100644 --- a/drivers/net/ethernet/alteon/acenic.c +++ b/drivers/net/ethernet/alteon/acenic.c @@ -474,6 +474,8 @@ static int acenic_probe_one(struct pci_dev *pdev, dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; dev->watchdog_timeo = 5*HZ; + dev->min_mtu = 0; + dev->max_mtu = ACE_JUMBO_MTU; dev->netdev_ops = &ace_netdev_ops; dev->ethtool_ops = &ace_ethtool_ops; @@ -2548,9 +2550,6 @@ static int ace_change_mtu(struct net_device *dev, int new_mtu) struct ace_private *ap = netdev_priv(dev); struct ace_regs __iomem *regs = ap->regs; - if (new_mtu > ACE_JUMBO_MTU) - return -EINVAL; - writel(new_mtu + ETH_HLEN + 4, ®s->IfMtu); dev->mtu = new_mtu; diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index bfeaec5bd7b9..2a55ab00686a 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -103,13 +103,6 @@ static int ena_change_mtu(struct net_device *dev, int new_mtu) struct ena_adapter *adapter = netdev_priv(dev); int ret; - if ((new_mtu > adapter->max_mtu) || (new_mtu < ENA_MIN_MTU)) { - netif_err(adapter, drv, dev, - "Invalid MTU setting. new_mtu: %d\n", new_mtu); - - return -EINVAL; - } - ret = ena_com_set_dev_mtu(adapter->ena_dev, new_mtu); if (!ret) { netif_dbg(adapter, drv, dev, "set MTU to %d\n", new_mtu); @@ -2755,6 +2748,8 @@ static void ena_set_conf_feat_params(struct ena_adapter *adapter, ena_set_dev_offloads(feat, netdev); adapter->max_mtu = feat->dev_attr.max_mtu; + netdev->max_mtu = adapter->max_mtu; + netdev->min_mtu = ENA_MIN_MTU; } static int ena_rss_init_default(struct ena_adapter *adapter) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 7f9216db026f..c4e668208e04 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -257,11 +257,6 @@ static int xgbe_calc_rx_buf_size(struct net_device *netdev, unsigned int mtu) { unsigned int rx_buf_size; - if (mtu > XGMAC_JUMBO_PACKET_MTU) { - netdev_alert(netdev, "MTU exceeds maximum supported value\n"); - return -EINVAL; - } - rx_buf_size = mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; rx_buf_size = clamp_val(rx_buf_size, XGBE_RX_MIN_BUF_SIZE, PAGE_SIZE); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c index 9de078819aa6..667e1209a2f5 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c @@ -738,6 +738,8 @@ static int xgbe_probe(struct platform_device *pdev) pdata->netdev_features = netdev->features; netdev->priv_flags |= IFF_UNICAST_FLT; + netdev->min_mtu = 0; + netdev->max_mtu = XGMAC_JUMBO_PACKET_MTU; /* Use default watchdog timeout */ netdev->watchdog_timeo = 0; diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c index f1b81187a201..cb312e4c89f4 100644 --- a/drivers/net/ethernet/broadcom/sb1250-mac.c +++ b/drivers/net/ethernet/broadcom/sb1250-mac.c @@ -2147,15 +2147,6 @@ static void sbmac_setmulti(struct sbmac_softc *sc) } } -static int sb1250_change_mtu(struct net_device *_dev, int new_mtu) -{ - if (new_mtu > ENET_PACKET_SIZE) - return -EINVAL; - _dev->mtu = new_mtu; - pr_info("changing the mtu to %d\n", new_mtu); - return 0; -} - static const struct net_device_ops sbmac_netdev_ops = { .ndo_open = sbmac_open, .ndo_stop = sbmac_close, @@ -2163,7 +2154,6 @@ static const struct net_device_ops sbmac_netdev_ops = { .ndo_set_rx_mode = sbmac_set_rx_mode, .ndo_tx_timeout = sbmac_tx_timeout, .ndo_do_ioctl = sbmac_mii_ioctl, - .ndo_change_mtu = sb1250_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, #ifdef CONFIG_NET_POLL_CONTROLLER @@ -2229,6 +2219,8 @@ static int sbmac_init(struct platform_device *pldev, long long base) dev->netdev_ops = &sbmac_netdev_ops; dev->watchdog_timeo = TX_TIMEOUT; + dev->max_mtu = 0; + dev->max_mtu = ENET_PACKET_SIZE; netif_napi_add(dev, &sc->napi, sbmac_poll, 16); diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 43da891fab97..092b3c16440b 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -2531,8 +2531,6 @@ static int cxgb_change_mtu(struct net_device *dev, int new_mtu) struct adapter *adapter = pi->adapter; int ret; - if (new_mtu < 81) /* accommodate SACK */ - return -EINVAL; if ((ret = t3_mac_set_mtu(&pi->mac, new_mtu))) return ret; dev->mtu = new_mtu; @@ -3295,6 +3293,8 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->netdev_ops = &cxgb_netdev_ops; netdev->ethtool_ops = &cxgb_ethtool_ops; + netdev->min_mtu = 81; + netdev->max_mtu = ETH_MAX_MTU; } pci_set_drvdata(pdev, adapter); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index f320497368f4..b0bb23f95beb 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -2502,8 +2502,6 @@ static int cxgb_change_mtu(struct net_device *dev, int new_mtu) int ret; struct port_info *pi = netdev_priv(dev); - if (new_mtu < 81 || new_mtu > MAX_MTU) /* accommodate SACK */ - return -EINVAL; ret = t4_set_rxmode(pi->adapter, pi->adapter->pf, pi->viid, new_mtu, -1, -1, -1, -1, true); if (!ret) @@ -4803,6 +4801,10 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->priv_flags |= IFF_UNICAST_FLT; + /* MTU range: 81 - 9600 */ + netdev->min_mtu = 81; + netdev->max_mtu = MAX_MTU; + netdev->netdev_ops = &cxgb4_netdev_ops; #ifdef CONFIG_CHELSIO_T4_DCB netdev->dcbnl_ops = &cxgb4_dcb_ops; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 100b2cc064a3..5d4da0e8acaa 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -1108,10 +1108,6 @@ static int cxgb4vf_change_mtu(struct net_device *dev, int new_mtu) int ret; struct port_info *pi = netdev_priv(dev); - /* accommodate SACK */ - if (new_mtu < 81) - return -EINVAL; - ret = t4vf_set_rxmode(pi->adapter, pi->viid, new_mtu, -1, -1, -1, -1, true); if (!ret) @@ -2966,6 +2962,8 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev, netdev->features |= NETIF_F_HIGHDMA; netdev->priv_flags |= IFF_UNICAST_FLT; + netdev->min_mtu = 81; + netdev->max_mtu = ETH_MAX_MTU; netdev->netdev_ops = &cxgb4vf_netdev_ops; netdev->ethtool_ops = &cxgb4vf_ethtool_ops; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index cece8a08edca..3f6152cc648c 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1406,23 +1406,6 @@ drop: return NETDEV_TX_OK; } -static int be_change_mtu(struct net_device *netdev, int new_mtu) -{ - struct be_adapter *adapter = netdev_priv(netdev); - struct device *dev = &adapter->pdev->dev; - - if (new_mtu < BE_MIN_MTU || new_mtu > BE_MAX_MTU) { - dev_info(dev, "MTU must be between %d and %d bytes\n", - BE_MIN_MTU, BE_MAX_MTU); - return -EINVAL; - } - - dev_info(dev, "MTU changed from %d to %d bytes\n", - netdev->mtu, new_mtu); - netdev->mtu = new_mtu; - return 0; -} - static inline bool be_in_all_promisc(struct be_adapter *adapter) { return (adapter->if_flags & BE_IF_FLAGS_ALL_PROMISCUOUS) == @@ -5216,7 +5199,6 @@ static const struct net_device_ops be_netdev_ops = { .ndo_start_xmit = be_xmit, .ndo_set_rx_mode = be_set_rx_mode, .ndo_set_mac_address = be_mac_addr_set, - .ndo_change_mtu = be_change_mtu, .ndo_get_stats64 = be_get_stats64, .ndo_validate_addr = eth_validate_addr, .ndo_vlan_rx_add_vid = be_vlan_add_vid, @@ -5266,6 +5248,10 @@ static void be_netdev_init(struct net_device *netdev) netdev->netdev_ops = &be_netdev_ops; netdev->ethtool_ops = &be_ethtool_ops; + + /* MTU range: 256 - 9000 */ + netdev->min_mtu = BE_MIN_MTU; + netdev->max_mtu = BE_MAX_MTU; } static void be_cleanup(struct be_adapter *adapter) diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index ebe60719e489..29c05d0d79a9 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1349,9 +1349,6 @@ static int ibmveth_change_mtu(struct net_device *dev, int new_mtu) int i, rc; int need_restart = 0; - if (new_mtu < IBMVETH_MIN_MTU) - return -EINVAL; - for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) if (new_mtu_oh <= adapter->rx_buff_pool[i].buff_size) break; @@ -1551,6 +1548,9 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id) netdev->hw_features |= NETIF_F_TSO; } + netdev->min_mtu = IBMVETH_MIN_MTU; + netdev->min_mtu = ETH_MAX_MTU; + memcpy(netdev->dev_addr, mac_addr_p, ETH_ALEN); if (firmware_has_feature(FW_FEATURE_CMO)) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index bfe17d9c022d..657206be7ba9 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -902,17 +902,6 @@ static int ibmvnic_set_mac(struct net_device *netdev, void *p) return 0; } -static int ibmvnic_change_mtu(struct net_device *netdev, int new_mtu) -{ - struct ibmvnic_adapter *adapter = netdev_priv(netdev); - - if (new_mtu > adapter->req_mtu || new_mtu < adapter->min_mtu) - return -EINVAL; - - netdev->mtu = new_mtu; - return 0; -} - static void ibmvnic_tx_timeout(struct net_device *dev) { struct ibmvnic_adapter *adapter = netdev_priv(dev); @@ -1029,7 +1018,6 @@ static const struct net_device_ops ibmvnic_netdev_ops = { .ndo_set_rx_mode = ibmvnic_set_multi, .ndo_set_mac_address = ibmvnic_set_mac, .ndo_validate_addr = eth_validate_addr, - .ndo_change_mtu = ibmvnic_change_mtu, .ndo_tx_timeout = ibmvnic_tx_timeout, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = ibmvnic_netpoll_controller, @@ -2638,10 +2626,12 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq, break; case MIN_MTU: adapter->min_mtu = be64_to_cpu(crq->query_capability.number); + netdev->min_mtu = adapter->min_mtu; netdev_dbg(netdev, "min_mtu = %lld\n", adapter->min_mtu); break; case MAX_MTU: adapter->max_mtu = be64_to_cpu(crq->query_capability.number); + netdev->max_mtu = adapter->max_mtu; netdev_dbg(netdev, "max_mtu = %lld\n", adapter->max_mtu); break; case MAX_MULTICAST_FILTERS: @@ -3654,6 +3644,8 @@ static void handle_crq_init_rsp(struct work_struct *work) goto task_failed; netdev->real_num_tx_queues = adapter->req_tx_queues; + netdev->min_mtu = adapter->min_mtu; + netdev->max_mtu = adapter->max_mtu; if (adapter->failover) { adapter->failover = false; diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index 836ebd8ee768..f9fcab54783c 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -2357,14 +2357,6 @@ jme_change_mtu(struct net_device *netdev, int new_mtu) { struct jme_adapter *jme = netdev_priv(netdev); - if (new_mtu == jme->old_mtu) - return 0; - - if (((new_mtu + ETH_HLEN) > MAX_ETHERNET_JUMBO_PACKET_SIZE) || - ((new_mtu) < IPV6_MIN_MTU)) - return -EINVAL; - - netdev->mtu = new_mtu; netdev_update_features(netdev); @@ -3063,6 +3055,10 @@ jme_init_one(struct pci_dev *pdev, if (using_dac) netdev->features |= NETIF_F_HIGHDMA; + /* MTU range: 1280 - 9202*/ + netdev->min_mtu = IPV6_MIN_MTU; + netdev->max_mtu = MAX_ETHERNET_JUMBO_PACKET_SIZE - ETH_HLEN; + SET_NETDEV_DEV(netdev, &pdev->dev); pci_set_drvdata(pdev, netdev); diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 18e6bb6e3867..68675d83bdc5 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2585,9 +2585,6 @@ static int mv643xx_eth_change_mtu(struct net_device *dev, int new_mtu) { struct mv643xx_eth_private *mp = netdev_priv(dev); - if (new_mtu < 64 || new_mtu > 9500) - return -EINVAL; - dev->mtu = new_mtu; mv643xx_eth_recalc_skb_size(mp); tx_set_rate(mp, 1000000000, 16777216); @@ -3206,6 +3203,10 @@ static int mv643xx_eth_probe(struct platform_device *pdev) dev->priv_flags |= IFF_UNICAST_FLT; dev->gso_max_segs = MV643XX_MAX_TSO_SEGS; + /* MTU range: 64 - 9500 */ + dev->min_mtu = 64; + dev->max_mtu = 9500; + SET_NETDEV_DEV(dev, &pdev->dev); if (mp->shared->win_protect) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 99805fd3d110..6d8cb22579ee 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2284,6 +2284,9 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_TC; dev->hw_features |= NETIF_F_HW_TC; + dev->min_mtu = 0; + dev->max_mtu = ETH_MAX_MTU; + /* Each packet needs to have a Tx header (metadata) on top all other * headers. */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index c0c23e2f3275..66af63d99b8b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -994,6 +994,9 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port) dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_LLTX | NETIF_F_SG | NETIF_F_VLAN_CHALLENGED; + dev->min_mtu = 0; + dev->max_mtu = ETH_MAX_MTU; + /* Each packet needs to have a Tx header (metadata) on top all other * headers. */ diff --git a/drivers/net/ethernet/natsemi/ns83820.c b/drivers/net/ethernet/natsemi/ns83820.c index 569ade6cf85c..a34631ed741d 100644 --- a/drivers/net/ethernet/natsemi/ns83820.c +++ b/drivers/net/ethernet/natsemi/ns83820.c @@ -1679,14 +1679,6 @@ static void ns83820_getmac(struct ns83820 *dev, u8 *mac) } } -static int ns83820_change_mtu(struct net_device *ndev, int new_mtu) -{ - if (new_mtu > RX_BUF_SIZE) - return -EINVAL; - ndev->mtu = new_mtu; - return 0; -} - static void ns83820_set_multicast(struct net_device *ndev) { struct ns83820 *dev = PRIV(ndev); @@ -1933,7 +1925,6 @@ static const struct net_device_ops netdev_ops = { .ndo_stop = ns83820_stop, .ndo_start_xmit = ns83820_hard_start_xmit, .ndo_get_stats = ns83820_get_stats, - .ndo_change_mtu = ns83820_change_mtu, .ndo_set_rx_mode = ns83820_set_multicast, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, @@ -2190,6 +2181,8 @@ static int ns83820_init_one(struct pci_dev *pci_dev, ndev->features |= NETIF_F_SG; ndev->features |= NETIF_F_IP_CSUM; + ndev->min_mtu = 0; + #ifdef NS83820_VLAN_ACCEL_SUPPORT /* We also support hardware vlan acceleration */ ndev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c index 2b10f1bcd151..a996801d442d 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c @@ -987,20 +987,8 @@ int netxen_send_lro_cleanup(struct netxen_adapter *adapter) int netxen_nic_change_mtu(struct net_device *netdev, int mtu) { struct netxen_adapter *adapter = netdev_priv(netdev); - int max_mtu; int rc = 0; - if (NX_IS_REVISION_P3(adapter->ahw.revision_id)) - max_mtu = P3_MAX_MTU; - else - max_mtu = P2_MAX_MTU; - - if (mtu > max_mtu) { - printk(KERN_ERR "%s: mtu > %d bytes unsupported\n", - netdev->name, max_mtu); - return -EINVAL; - } - if (adapter->set_mtu) rc = adapter->set_mtu(adapter, mtu); diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 7a0281a36c28..561fb94c7267 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -1572,6 +1572,13 @@ netxen_nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->physical_port = i; } + /* MTU range: 0 - 8000 (P2) or 9600 (P3) */ + netdev->min_mtu = 0; + if (NX_IS_REVISION_P3(adapter->ahw.revision_id)) + netdev->max_mtu = P3_MAX_MTU; + else + netdev->max_mtu = P2_MAX_MTU; + netxen_nic_clear_stats(adapter); err = netxen_setup_intr(adapter); diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index fd4a8e473f11..1409412ab39d 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -4788,6 +4788,13 @@ static int qlge_probe(struct pci_dev *pdev, ndev->ethtool_ops = &qlge_ethtool_ops; ndev->watchdog_timeo = 10 * HZ; + /* MTU range: this driver only supports 1500 or 9000, so this only + * filters out values above or below, and we'll rely on + * qlge_change_mtu to make sure only 1500 or 9000 are allowed + */ + ndev->min_mtu = ETH_DATA_LEN; + ndev->max_mtu = 9000; + err = register_netdev(ndev); if (err) { dev_err(&pdev->dev, "net device registration failed.\n"); diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 9bf3b2b82e95..e4e1925d18a4 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -239,15 +239,8 @@ static void emac_rx_mode_set(struct net_device *netdev) /* Change the Maximum Transfer Unit (MTU) */ static int emac_change_mtu(struct net_device *netdev, int new_mtu) { - unsigned int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; struct emac_adapter *adpt = netdev_priv(netdev); - if ((max_frame < EMAC_MIN_ETH_FRAME_SIZE) || - (max_frame > EMAC_MAX_ETH_FRAME_SIZE)) { - netdev_err(adpt->netdev, "error: invalid MTU setting\n"); - return -EINVAL; - } - netif_info(adpt, hw, adpt->netdev, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); @@ -679,6 +672,12 @@ static int emac_probe(struct platform_device *pdev) netdev->vlan_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6; + /* MTU range: 46 - 9194 */ + netdev->min_mtu = EMAC_MIN_ETH_FRAME_SIZE - + (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN); + netdev->max_mtu = EMAC_MAX_ETH_FRAME_SIZE - + (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN); + INIT_WORK(&adpt->work_thread, emac_work_thread); /* Initialize queues */ diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index c688d68c39aa..c9c8a3be9f1b 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1034,9 +1034,6 @@ static int axienet_change_mtu(struct net_device *ndev, int new_mtu) XAE_TRL_SIZE) > lp->rxmem) return -EINVAL; - if ((new_mtu > XAE_JUMBO_MTU) || (new_mtu < 64)) - return -EINVAL; - ndev->mtu = new_mtu; return 0; @@ -1475,6 +1472,10 @@ static int axienet_probe(struct platform_device *pdev) ndev->netdev_ops = &axienet_netdev_ops; ndev->ethtool_ops = &axienet_ethtool_ops; + /* MTU range: 64 - 9000 */ + ndev->min_mtu = 64; + ndev->max_mtu = XAE_JUMBO_MTU; + lp = netdev_priv(ndev); lp->ndev = ndev; lp->dev = &pdev->dev; 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 a8b4a1ea0cecda1089739cfda1b247d17981062d Mon Sep 17 00:00:00 2001 From: Wu-Cheng Li Date: Fri, 2 Sep 2016 09:19:57 -0300 Subject: [media] videodev2.h: add V4L2_PIX_FMT_VP9 format This adds VP9 video coding format, a successor to VP8. Signed-off-by: Wu-Cheng Li Signed-off-by: Tiffany Lin Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 94f123f3e04e..ad206de8eada 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -603,6 +603,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_VC1_ANNEX_G v4l2_fourcc('V', 'C', '1', 'G') /* SMPTE 421M Annex G compliant stream */ #define V4L2_PIX_FMT_VC1_ANNEX_L v4l2_fourcc('V', 'C', '1', 'L') /* SMPTE 421M Annex L compliant stream */ #define V4L2_PIX_FMT_VP8 v4l2_fourcc('V', 'P', '8', '0') /* VP8 */ +#define V4L2_PIX_FMT_VP9 v4l2_fourcc('V', 'P', '9', '0') /* VP9 */ /* Vendor-specific formats */ #define V4L2_PIX_FMT_CPIA1 v4l2_fourcc('C', 'P', 'I', 'A') /* cpia1 YUV */ -- cgit v1.2.3 From d4de663458bd00a579742e966c2db0d86352358b Mon Sep 17 00:00:00 2001 From: Tiffany Lin Date: Fri, 9 Sep 2016 12:48:04 -0300 Subject: [media] v4l: add Mediatek compressed video block format Add V4L2_PIX_FMT_MT21C format used on MT8173 driver. It is compressed format and need MT8173 MDP driver to transfer to other standard format. Signed-off-by: Tiffany Lin Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-ioctl.c | 1 + include/uapi/linux/videodev2.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index a4b5d360fc96..39e19b4222be 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1249,6 +1249,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_JPGL: descr = "JPEG Lite"; break; case V4L2_PIX_FMT_SE401: descr = "GSPCA SE401"; break; case V4L2_PIX_FMT_S5C_UYVY_JPG: descr = "S5C73MX interleaved UYVY/JPEG"; break; + case V4L2_PIX_FMT_MT21C: descr = "Mediatek Compressed Format"; break; default: WARN(1, "Unknown pixelformat 0x%08x\n", fmt->pixelformat); if (fmt->description[0]) diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index ad206de8eada..2da477c04479 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -635,6 +635,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_Y8I v4l2_fourcc('Y', '8', 'I', ' ') /* Greyscale 8-bit L/R interleaved */ #define V4L2_PIX_FMT_Y12I v4l2_fourcc('Y', '1', '2', 'I') /* Greyscale 12-bit L/R interleaved */ #define V4L2_PIX_FMT_Z16 v4l2_fourcc('Z', '1', '6', ' ') /* Depth data 16-bit */ +#define V4L2_PIX_FMT_MT21C v4l2_fourcc('M', 'T', '2', '1') /* Mediatek compressed block mode */ /* SDR formats - used only for Software Defined Radio devices */ #define V4L2_SDR_FMT_CU8 v4l2_fourcc('C', 'U', '0', '8') /* IQ u8 */ -- cgit v1.2.3 From 66b2ab271afc0888b87a44dc946cc68067ba0985 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Delgado Date: Thu, 18 Aug 2016 11:33:27 -0300 Subject: [media] videodev2.h Add HSV formats These formats store the color information of the image in a geometrical representation. The colors are mapped into a cylinder, where the angle is the HUE, the height is the VALUE and the distance to the center is the SATURATION. This is a very useful format for image segmentation algorithms. Signed-off-by: Ricardo Ribalda Delgado Acked-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-ioctl.c | 2 ++ include/uapi/linux/videodev2.h | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 39e19b4222be..181381d1dc77 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1200,6 +1200,8 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_TM6000: descr = "A/V + VBI Mux Packet"; break; case V4L2_PIX_FMT_CIT_YYVYUY: descr = "GSPCA CIT YYVYUY"; break; case V4L2_PIX_FMT_KONICA420: descr = "GSPCA KONICA420"; break; + case V4L2_PIX_FMT_HSV24: descr = "24-bit HSV 8-8-8"; break; + case V4L2_PIX_FMT_HSV32: descr = "32-bit XHSV 8-8-8-8"; break; case V4L2_SDR_FMT_CU8: descr = "Complex U8"; break; case V4L2_SDR_FMT_CU16LE: descr = "Complex U16LE"; break; case V4L2_SDR_FMT_CS8: descr = "Complex S8"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 2da477c04479..6b480c91778e 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -587,6 +587,10 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_SRGGB12 v4l2_fourcc('R', 'G', '1', '2') /* 12 RGRG.. GBGB.. */ #define V4L2_PIX_FMT_SBGGR16 v4l2_fourcc('B', 'Y', 'R', '2') /* 16 BGBG.. GRGR.. */ +/* HSV formats */ +#define V4L2_PIX_FMT_HSV24 v4l2_fourcc('H', 'S', 'V', '3') +#define V4L2_PIX_FMT_HSV32 v4l2_fourcc('H', 'S', 'V', '4') + /* compressed formats */ #define V4L2_PIX_FMT_MJPEG v4l2_fourcc('M', 'J', 'P', 'G') /* Motion-JPEG */ #define V4L2_PIX_FMT_JPEG v4l2_fourcc('J', 'P', 'E', 'G') /* JFIF JPEG */ -- cgit v1.2.3 From 8a0d62af93026de424d75906e3651ba653197668 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Delgado Date: Mon, 22 Aug 2016 06:28:07 -0300 Subject: [media] videodev2.h Add HSV encoding Some hardware maps the Hue between 0 and 255 instead of 0-179. Support this format with a new field hsv_enc. Signed-off-by: Ricardo Ribalda Delgado Acked-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 32 +++++++++++++++++++++++++++----- 1 file changed, 27 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 6b480c91778e..4364ce6b0aa6 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -334,6 +334,19 @@ enum v4l2_ycbcr_encoding { V4L2_YCBCR_ENC_SMPTE240M = 8, }; +/* + * enum v4l2_hsv_encoding values should not collide with the ones from + * enum v4l2_ycbcr_encoding. + */ +enum v4l2_hsv_encoding { + + /* Hue mapped to 0 - 179 */ + V4L2_HSV_ENC_180 = 128, + + /* Hue mapped to 0-255 */ + V4L2_HSV_ENC_256 = 129, +}; + /* * Determine how YCBCR_ENC_DEFAULT should map to a proper Y'CbCr encoding. * This depends on the colorspace. @@ -362,9 +375,10 @@ enum v4l2_quantization { * This depends on whether the image is RGB or not, the colorspace and the * Y'CbCr encoding. */ -#define V4L2_MAP_QUANTIZATION_DEFAULT(is_rgb, colsp, ycbcr_enc) \ - (((is_rgb) && (colsp) == V4L2_COLORSPACE_BT2020) ? V4L2_QUANTIZATION_LIM_RANGE : \ - (((is_rgb) || (ycbcr_enc) == V4L2_YCBCR_ENC_XV601 || \ +#define V4L2_MAP_QUANTIZATION_DEFAULT(is_rgb_or_hsv, colsp, ycbcr_enc) \ + (((is_rgb_or_hsv) && (colsp) == V4L2_COLORSPACE_BT2020) ? \ + V4L2_QUANTIZATION_LIM_RANGE : \ + (((is_rgb_or_hsv) || (ycbcr_enc) == V4L2_YCBCR_ENC_XV601 || \ (ycbcr_enc) == V4L2_YCBCR_ENC_XV709 || (colsp) == V4L2_COLORSPACE_JPEG) || \ (colsp) == V4L2_COLORSPACE_ADOBERGB || (colsp) == V4L2_COLORSPACE_SRGB ? \ V4L2_QUANTIZATION_FULL_RANGE : V4L2_QUANTIZATION_LIM_RANGE)) @@ -462,7 +476,12 @@ struct v4l2_pix_format { __u32 colorspace; /* enum v4l2_colorspace */ __u32 priv; /* private data, depends on pixelformat */ __u32 flags; /* format flags (V4L2_PIX_FMT_FLAG_*) */ - __u32 ycbcr_enc; /* enum v4l2_ycbcr_encoding */ + union { + /* enum v4l2_ycbcr_encoding */ + __u32 ycbcr_enc; + /* enum v4l2_hsv_encoding */ + __u32 hsv_enc; + }; __u32 quantization; /* enum v4l2_quantization */ __u32 xfer_func; /* enum v4l2_xfer_func */ }; @@ -2012,7 +2031,10 @@ struct v4l2_pix_format_mplane { struct v4l2_plane_pix_format plane_fmt[VIDEO_MAX_PLANES]; __u8 num_planes; __u8 flags; - __u8 ycbcr_enc; + union { + __u8 ycbcr_enc; + __u8 hsv_enc; + }; __u8 quantization; __u8 xfer_func; __u8 reserved[7]; -- 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/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 6 ++++++ kernel/bpf/core.c | 1 + kernel/bpf/helpers.c | 12 ++++++++++++ kernel/trace/bpf_trace.c | 2 ++ net/core/filter.c | 2 ++ 6 files changed, 24 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c201017b5730..edcd96ded8aa 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -319,6 +319,7 @@ extern const struct bpf_func_proto bpf_map_delete_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; +extern const struct bpf_func_proto bpf_get_numa_node_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; extern const struct bpf_func_proto bpf_ktime_get_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; 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, }; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index aa6d98154106..82a04143368e 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1043,6 +1043,7 @@ const struct bpf_func_proto bpf_map_delete_elem_proto __weak; const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; +const struct bpf_func_proto bpf_get_numa_node_id_proto __weak; const struct bpf_func_proto bpf_ktime_get_ns_proto __weak; const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 39918402e6e9..045cbe673356 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -92,6 +93,17 @@ const struct bpf_func_proto bpf_get_smp_processor_id_proto = { .ret_type = RET_INTEGER, }; +BPF_CALL_0(bpf_get_numa_node_id) +{ + return numa_node_id(); +} + +const struct bpf_func_proto bpf_get_numa_node_id_proto = { + .func = bpf_get_numa_node_id, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; + BPF_CALL_0(bpf_ktime_get_ns) { /* NMI safe access to clock monotonic */ diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 5dcb99281259..fa77311dadb2 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -422,6 +422,8 @@ static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id) return bpf_get_trace_printk_proto(); case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; + case BPF_FUNC_get_numa_node_id: + return &bpf_get_numa_node_id_proto; case BPF_FUNC_perf_event_read: return &bpf_perf_event_read_proto; case BPF_FUNC_probe_write_user: diff --git a/net/core/filter.c b/net/core/filter.c index 00351cdf7d0c..cd9e2ba66b0e 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2492,6 +2492,8 @@ sk_filter_func_proto(enum bpf_func_id func_id) return &bpf_get_prandom_u32_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_raw_smp_processor_id_proto; + case BPF_FUNC_get_numa_node_id: + return &bpf_get_numa_node_id_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_ktime_get_ns: -- 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/net/raw.h | 6 + include/net/rawv6.h | 7 ++ include/uapi/linux/inet_diag.h | 17 +++ net/ipv4/Kconfig | 8 ++ net/ipv4/Makefile | 1 + net/ipv4/inet_diag.c | 9 ++ net/ipv4/raw.c | 21 +++- net/ipv4/raw_diag.c | 261 +++++++++++++++++++++++++++++++++++++++++ net/ipv6/raw.c | 7 +- 9 files changed, 333 insertions(+), 4 deletions(-) create mode 100644 net/ipv4/raw_diag.c (limited to 'include/uapi/linux') diff --git a/include/net/raw.h b/include/net/raw.h index 3e789008394d..57c33dd22ec4 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -23,6 +23,12 @@ extern struct proto raw_prot; +extern struct raw_hashinfo raw_v4_hashinfo; +struct sock *__raw_v4_lookup(struct net *net, struct sock *sk, + unsigned short num, __be32 raddr, + __be32 laddr, int dif); + +int raw_abort(struct sock *sk, int err); void raw_icmp_error(struct sk_buff *, int, u32); int raw_local_deliver(struct sk_buff *, int); diff --git a/include/net/rawv6.h b/include/net/rawv6.h index 87783dea0791..cbe4e9de1894 100644 --- a/include/net/rawv6.h +++ b/include/net/rawv6.h @@ -3,6 +3,13 @@ #include +extern struct raw_hashinfo raw_v6_hashinfo; +struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, + unsigned short num, const struct in6_addr *loc_addr, + const struct in6_addr *rmt_addr, int dif); + +int raw_abort(struct sock *sk, int err); + void raw6_icmp_error(struct sk_buff *, int nexthdr, u8 type, u8 code, int inner_offset, __be32); bool raw6_local_deliver(struct sk_buff *, int); 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, diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 300b06888fdf..28e051a8e847 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -430,6 +430,14 @@ config INET_UDP_DIAG Support for UDP socket monitoring interface used by the ss tool. If unsure, say Y. +config INET_RAW_DIAG + tristate "RAW: socket monitoring interface" + depends on INET_DIAG && (IPV6 || IPV6=n) + default n + ---help--- + Support for RAW socket monitoring interface used by the ss tool. + If unsure, say Y. + config INET_DIAG_DESTROY bool "INET: allow privileged process to administratively close sockets" depends on INET_DIAG diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index bc6a6c8b9bcd..48af58a5686e 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -40,6 +40,7 @@ obj-$(CONFIG_NETFILTER) += netfilter.o netfilter/ obj-$(CONFIG_INET_DIAG) += inet_diag.o obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o +obj-$(CONFIG_INET_RAW_DIAG) += raw_diag.o obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o obj-$(CONFIG_TCP_CONG_BBR) += tcp_bbr.o obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 0a1d4a896a26..3b34024202d8 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -200,6 +200,15 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO)) goto errout; + /* + * RAW sockets might have user-defined protocols assigned, + * so report the one supplied on socket creation. + */ + if (sk->sk_type == SOCK_RAW) { + if (nla_put_u8(skb, INET_DIAG_PROTOCOL, sk->sk_protocol)) + goto errout; + } + if (!icsk) { handler->idiag_get_info(sk, r, NULL); goto out; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 90a85c955872..03618ed03532 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -89,9 +89,10 @@ struct raw_frag_vec { int hlen; }; -static struct raw_hashinfo raw_v4_hashinfo = { +struct raw_hashinfo raw_v4_hashinfo = { .lock = __RW_LOCK_UNLOCKED(raw_v4_hashinfo.lock), }; +EXPORT_SYMBOL_GPL(raw_v4_hashinfo); int raw_hash_sk(struct sock *sk) { @@ -120,7 +121,7 @@ void raw_unhash_sk(struct sock *sk) } EXPORT_SYMBOL_GPL(raw_unhash_sk); -static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk, +struct sock *__raw_v4_lookup(struct net *net, struct sock *sk, unsigned short num, __be32 raddr, __be32 laddr, int dif) { sk_for_each_from(sk) { @@ -136,6 +137,7 @@ static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk, found: return sk; } +EXPORT_SYMBOL_GPL(__raw_v4_lookup); /* * 0 - deliver @@ -912,6 +914,20 @@ static int compat_raw_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg } #endif +int raw_abort(struct sock *sk, int err) +{ + lock_sock(sk); + + sk->sk_err = err; + sk->sk_error_report(sk); + udp_disconnect(sk, 0); + + release_sock(sk); + + return 0; +} +EXPORT_SYMBOL_GPL(raw_abort); + struct proto raw_prot = { .name = "RAW", .owner = THIS_MODULE, @@ -937,6 +953,7 @@ struct proto raw_prot = { .compat_getsockopt = compat_raw_getsockopt, .compat_ioctl = compat_raw_ioctl, #endif + .diag_destroy = raw_abort, }; #ifdef CONFIG_PROC_FS diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c new file mode 100644 index 000000000000..ef3bea061b75 --- /dev/null +++ b/net/ipv4/raw_diag.c @@ -0,0 +1,261 @@ +#include + +#include +#include + +#include +#include + +#ifdef pr_fmt +# undef pr_fmt +#endif + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +static struct raw_hashinfo * +raw_get_hashinfo(const struct inet_diag_req_v2 *r) +{ + if (r->sdiag_family == AF_INET) { + return &raw_v4_hashinfo; +#if IS_ENABLED(CONFIG_IPV6) + } else if (r->sdiag_family == AF_INET6) { + return &raw_v6_hashinfo; +#endif + } else { + pr_warn_once("Unexpected inet family %d\n", + r->sdiag_family); + WARN_ON_ONCE(1); + return ERR_PTR(-EINVAL); + } +} + +/* + * Due to requirement of not breaking user API we can't simply + * rename @pad field in inet_diag_req_v2 structure, instead + * use helper to figure it out. + */ + +static struct sock *raw_lookup(struct net *net, struct sock *from, + const struct inet_diag_req_v2 *req) +{ + struct inet_diag_req_raw *r = (void *)req; + struct sock *sk = NULL; + + if (r->sdiag_family == AF_INET) + sk = __raw_v4_lookup(net, from, r->sdiag_raw_protocol, + r->id.idiag_dst[0], + r->id.idiag_src[0], + r->id.idiag_if); +#if IS_ENABLED(CONFIG_IPV6) + else + sk = __raw_v6_lookup(net, from, r->sdiag_raw_protocol, + (const struct in6_addr *)r->id.idiag_src, + (const struct in6_addr *)r->id.idiag_dst, + r->id.idiag_if); +#endif + return sk; +} + +static struct sock *raw_sock_get(struct net *net, const struct inet_diag_req_v2 *r) +{ + struct raw_hashinfo *hashinfo = raw_get_hashinfo(r); + struct sock *sk = NULL, *s; + int slot; + + if (IS_ERR(hashinfo)) + return ERR_CAST(hashinfo); + + read_lock(&hashinfo->lock); + for (slot = 0; slot < RAW_HTABLE_SIZE; slot++) { + sk_for_each(s, &hashinfo->ht[slot]) { + sk = raw_lookup(net, s, r); + if (sk) { + /* + * Grab it and keep until we fill + * diag meaage to be reported, so + * caller should call sock_put then. + * We can do that because we're keeping + * hashinfo->lock here. + */ + sock_hold(sk); + break; + } + } + } + read_unlock(&hashinfo->lock); + + return sk ? sk : ERR_PTR(-ENOENT); +} + +static int raw_diag_dump_one(struct sk_buff *in_skb, + const struct nlmsghdr *nlh, + const struct inet_diag_req_v2 *r) +{ + struct net *net = sock_net(in_skb->sk); + struct sk_buff *rep; + struct sock *sk; + int err; + + sk = raw_sock_get(net, r); + if (IS_ERR(sk)) + return PTR_ERR(sk); + + rep = nlmsg_new(sizeof(struct inet_diag_msg) + + sizeof(struct inet_diag_meminfo) + 64, + GFP_KERNEL); + if (!rep) { + sock_put(sk); + return -ENOMEM; + } + + err = inet_sk_diag_fill(sk, NULL, rep, r, + sk_user_ns(NETLINK_CB(in_skb).sk), + NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, 0, nlh, + netlink_net_capable(in_skb, CAP_NET_ADMIN)); + sock_put(sk); + + if (err < 0) { + kfree_skb(rep); + return err; + } + + err = netlink_unicast(net->diag_nlsk, rep, + NETLINK_CB(in_skb).portid, + MSG_DONTWAIT); + if (err > 0) + err = 0; + return err; +} + +static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, + struct netlink_callback *cb, + const struct inet_diag_req_v2 *r, + struct nlattr *bc, bool net_admin) +{ + if (!inet_diag_bc_sk(bc, sk)) + return 0; + + return inet_sk_diag_fill(sk, NULL, skb, r, + sk_user_ns(NETLINK_CB(cb->skb).sk), + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->nlh, net_admin); +} + +static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, + const struct inet_diag_req_v2 *r, struct nlattr *bc) +{ + bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); + struct raw_hashinfo *hashinfo = raw_get_hashinfo(r); + struct net *net = sock_net(skb->sk); + int num, s_num, slot, s_slot; + struct sock *sk = NULL; + + if (IS_ERR(hashinfo)) + return; + + s_slot = cb->args[0]; + num = s_num = cb->args[1]; + + read_lock(&hashinfo->lock); + for (slot = s_slot; slot < RAW_HTABLE_SIZE; s_num = 0, slot++) { + num = 0; + + sk_for_each(sk, &hashinfo->ht[slot]) { + struct inet_sock *inet = inet_sk(sk); + + if (!net_eq(sock_net(sk), net)) + continue; + if (num < s_num) + goto next; + if (sk->sk_family != r->sdiag_family) + goto next; + if (r->id.idiag_sport != inet->inet_sport && + r->id.idiag_sport) + goto next; + if (r->id.idiag_dport != inet->inet_dport && + r->id.idiag_dport) + goto next; + if (sk_diag_dump(sk, skb, cb, r, bc, net_admin) < 0) + goto out_unlock; +next: + num++; + } + } + +out_unlock: + read_unlock(&hashinfo->lock); + + cb->args[0] = slot; + cb->args[1] = num; +} + +static void raw_diag_get_info(struct sock *sk, struct inet_diag_msg *r, + void *info) +{ + r->idiag_rqueue = sk_rmem_alloc_get(sk); + r->idiag_wqueue = sk_wmem_alloc_get(sk); +} + +#ifdef CONFIG_INET_DIAG_DESTROY +static int raw_diag_destroy(struct sk_buff *in_skb, + const struct inet_diag_req_v2 *r) +{ + struct net *net = sock_net(in_skb->sk); + struct sock *sk; + + sk = raw_sock_get(net, r); + if (IS_ERR(sk)) + return PTR_ERR(sk); + return sock_diag_destroy(sk, ECONNABORTED); +} +#endif + +static const struct inet_diag_handler raw_diag_handler = { + .dump = raw_diag_dump, + .dump_one = raw_diag_dump_one, + .idiag_get_info = raw_diag_get_info, + .idiag_type = IPPROTO_RAW, + .idiag_info_size = 0, +#ifdef CONFIG_INET_DIAG_DESTROY + .destroy = raw_diag_destroy, +#endif +}; + +static void __always_unused __check_inet_diag_req_raw(void) +{ + /* + * Make sure the two structures are identical, + * except the @pad field. + */ +#define __offset_mismatch(m1, m2) \ + (offsetof(struct inet_diag_req_v2, m1) != \ + offsetof(struct inet_diag_req_raw, m2)) + + BUILD_BUG_ON(sizeof(struct inet_diag_req_v2) != + sizeof(struct inet_diag_req_raw)); + BUILD_BUG_ON(__offset_mismatch(sdiag_family, sdiag_family)); + BUILD_BUG_ON(__offset_mismatch(sdiag_protocol, sdiag_protocol)); + BUILD_BUG_ON(__offset_mismatch(idiag_ext, idiag_ext)); + BUILD_BUG_ON(__offset_mismatch(pad, sdiag_raw_protocol)); + BUILD_BUG_ON(__offset_mismatch(idiag_states, idiag_states)); + BUILD_BUG_ON(__offset_mismatch(id, id)); +#undef __offset_mismatch +} + +static int __init raw_diag_init(void) +{ + return inet_diag_register(&raw_diag_handler); +} + +static void __exit raw_diag_exit(void) +{ + inet_diag_unregister(&raw_diag_handler); +} + +module_init(raw_diag_init); +module_exit(raw_diag_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-255 /* AF_INET - IPPROTO_RAW */); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10-255 /* AF_INET6 - IPPROTO_RAW */); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 54404f08efcc..d7e8b955ade8 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -65,11 +65,12 @@ #define ICMPV6_HDRLEN 4 /* ICMPv6 header, RFC 4443 Section 2.1 */ -static struct raw_hashinfo raw_v6_hashinfo = { +struct raw_hashinfo raw_v6_hashinfo = { .lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock), }; +EXPORT_SYMBOL_GPL(raw_v6_hashinfo); -static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, +struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, unsigned short num, const struct in6_addr *loc_addr, const struct in6_addr *rmt_addr, int dif) { @@ -102,6 +103,7 @@ static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, found: return sk; } +EXPORT_SYMBOL_GPL(__raw_v6_lookup); /* * 0 - deliver @@ -1259,6 +1261,7 @@ struct proto rawv6_prot = { .compat_getsockopt = compat_rawv6_getsockopt, .compat_ioctl = compat_rawv6_ioctl, #endif + .diag_destroy = raw_abort, }; #ifdef CONFIG_PROC_FS -- cgit v1.2.3 From 8c27ceff3604b249a9efafbd1bd8b141b79e619d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 18 Oct 2016 10:12:27 -0200 Subject: docs: fix locations of several documents that got moved The previous patch renamed several files that are cross-referenced along the Kernel documentation. Adjust the links to point to the right places. Signed-off-by: Mauro Carvalho Chehab --- Documentation/00-INDEX | 54 +++++++++++----------- Documentation/ABI/README | 2 +- Documentation/ABI/testing/sysfs-kernel-slab | 2 +- Documentation/DocBook/kernel-hacking.tmpl | 4 +- Documentation/acpi/video_extension.txt | 2 +- Documentation/admin-guide/README.rst | 13 +++--- Documentation/admin-guide/bad-memory.rst | 2 +- Documentation/admin-guide/binfmt-misc.rst | 4 +- Documentation/admin-guide/braille-console.rst | 6 +-- Documentation/admin-guide/bug-hunting.rst | 7 +-- Documentation/admin-guide/devices.rst | 2 +- Documentation/admin-guide/kernel-parameters.rst | 6 +-- Documentation/admin-guide/oops-tracing.rst | 2 +- Documentation/admin-guide/ramoops.rst | 2 +- Documentation/admin-guide/reporting-bugs.rst | 6 +-- Documentation/admin-guide/security-bugs.rst | 2 +- Documentation/admin-guide/unicode.rst | 2 +- Documentation/arm/Booting | 2 +- Documentation/atomic_ops.txt | 2 +- Documentation/blockdev/ramdisk.txt | 2 +- Documentation/cgroup-v1/00-INDEX | 2 +- .../devicetree/bindings/rtc/maxim,ds3231.txt | 2 +- Documentation/devicetree/bindings/rtc/pcf8563.txt | 2 +- .../devicetree/bindings/submitting-patches.txt | 2 +- Documentation/filesystems/locks.txt | 2 +- Documentation/filesystems/nfs/nfsroot.txt | 4 +- Documentation/frv/booting.txt | 2 +- Documentation/hwmon/submitting-patches | 8 ++-- Documentation/isdn/README | 2 +- Documentation/ja_JP/HOWTO | 24 +++++----- Documentation/ja_JP/SubmitChecklist | 8 ++-- Documentation/ja_JP/SubmittingPatches | 18 ++++---- Documentation/ja_JP/stable_api_nonsense.txt | 4 +- Documentation/ja_JP/stable_kernel_rules.txt | 6 +-- Documentation/kernel-per-CPU-kthreads.txt | 2 +- Documentation/ko_KR/HOWTO | 30 ++++++------ Documentation/ko_KR/stable_api_nonsense.txt | 4 +- Documentation/lockup-watchdogs.txt | 4 +- Documentation/m68k/kernel-options.txt | 2 +- Documentation/media/uapi/v4l/diff-v4l.rst | 4 +- Documentation/media/v4l-drivers/bttv.rst | 4 +- Documentation/memory-hotplug.txt | 2 +- Documentation/networking/netconsole.txt | 2 +- Documentation/networking/netdev-FAQ.txt | 8 ++-- Documentation/networking/vortex.txt | 2 +- Documentation/power/00-INDEX | 2 +- Documentation/power/pci.txt | 10 ++-- Documentation/power/runtime_pm.txt | 2 +- Documentation/power/swsusp-dmcrypt.txt | 2 +- Documentation/process/4.Coding.rst | 4 +- Documentation/process/5.Posting.rst | 12 ++--- Documentation/process/8.Conclusion.rst | 6 +-- Documentation/process/adding-syscalls.rst | 2 +- Documentation/process/coding-style.rst | 2 +- Documentation/process/howto.rst | 24 +++++----- Documentation/process/management-style.rst | 2 +- Documentation/process/stable-kernel-rules.rst | 4 +- Documentation/process/submit-checklist.rst | 6 +-- Documentation/process/submitting-drivers.rst | 8 ++-- Documentation/process/submitting-patches.rst | 14 +++--- Documentation/rfkill.txt | 2 +- Documentation/scsi/scsi-parameters.txt | 2 +- Documentation/scsi/scsi_mid_low_api.txt | 2 +- Documentation/scsi/sym53c8xx_2.txt | 2 +- Documentation/sound/alsa/alsa-parameters.txt | 2 +- Documentation/sound/oss/oss-parameters.txt | 2 +- Documentation/sysctl/kernel.txt | 4 +- Documentation/virtual/kvm/review-checklist.txt | 4 +- Documentation/vm/numa | 2 +- .../watchdog/convert_drivers_to_kernel_api.txt | 2 +- Documentation/watchdog/watchdog-parameters.txt | 2 +- Documentation/x86/boot.txt | 2 +- Documentation/zh_CN/CodingStyle | 6 +-- Documentation/zh_CN/HOWTO | 30 ++++++------ Documentation/zh_CN/SecurityBugs | 6 +-- Documentation/zh_CN/SubmittingDrivers | 12 ++--- Documentation/zh_CN/SubmittingPatches | 14 +++--- Documentation/zh_CN/arm/Booting | 2 +- Documentation/zh_CN/email-clients.txt | 4 +- Documentation/zh_CN/oops-tracing.txt | 6 +-- Documentation/zh_CN/stable_api_nonsense.txt | 4 +- Documentation/zh_CN/stable_kernel_rules.txt | 6 +-- .../zh_CN/volatile-considered-harmful.txt | 4 +- MAINTAINERS | 10 ++-- arch/x86/Kconfig | 2 +- drivers/acpi/Kconfig | 2 +- drivers/ata/libata-core.c | 2 +- drivers/char/pcmcia/cm4000_cs.c | 4 +- drivers/net/can/grcan.c | 2 +- drivers/nvdimm/Kconfig | 2 +- drivers/staging/vme/devices/vme_user.c | 2 +- drivers/video/fbdev/skeletonfb.c | 8 ++-- drivers/virtio/Kconfig | 2 +- fs/Kconfig.binfmt | 4 +- fs/pstore/Kconfig | 2 +- include/linux/device.h | 2 +- include/linux/pm.h | 2 +- include/uapi/linux/major.h | 2 +- init/Kconfig | 2 +- init/main.c | 2 +- lib/Kconfig.debug | 2 +- scripts/checkpatch.pl | 6 +-- tools/testing/selftests/futex/README | 2 +- 103 files changed, 280 insertions(+), 278 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX index d07575a8499e..39caa6544d1f 100644 --- a/Documentation/00-INDEX +++ b/Documentation/00-INDEX @@ -15,11 +15,11 @@ Following translations are available on the WWW: ABI/ - info on kernel <-> userspace ABI and relative interface stability. -BUG-HUNTING +admin-guide/bug-hunting.rst - brute force method of doing binary search of patches to find bug. -Changes +process/changes.rst - list of changes that break older software packages. -CodingStyle +process/coding-style.rst - how the maintainers expect the C code in the kernel to look. DMA-API.txt - DMA API, pci_ API & extensions for non-consistent memory machines. @@ -33,7 +33,7 @@ DocBook/ - directory with DocBook templates etc. for kernel documentation. EDID/ - directory with info on customizing EDID for broken gfx/displays. -HOWTO +process/howto.rst - the process and procedures of how to do Linux kernel development. IPMI.txt - info on Linux Intelligent Platform Management Interface (IPMI) Driver. @@ -48,7 +48,7 @@ Intel-IOMMU.txt Makefile - This file does nothing. Removing it breaks make htmldocs and make distclean. -ManagementStyle +process/management-style.rst - how to (attempt to) manage kernel hackers. RCU/ - directory with info on RCU (read-copy update). @@ -56,13 +56,13 @@ SAK.txt - info on Secure Attention Keys. SM501.txt - Silicon Motion SM501 multimedia companion chip -SecurityBugs +admin-guide/security-bugs.rst - procedure for reporting security bugs found in the kernel. -SubmitChecklist +process/submit-checklist.rst - Linux kernel patch submission checklist. -SubmittingDrivers +process/submitting-drivers.rst - procedure to get a new driver source included into the kernel tree. -SubmittingPatches +process/submitting-patches.rst - procedure to get a source patch included into the kernel tree. VGA-softcursor.txt - how to change your VGA cursor from a blinking underscore. @@ -72,7 +72,7 @@ acpi/ - info on ACPI-specific hooks in the kernel. aoe/ - description of AoE (ATA over Ethernet) along with config examples. -applying-patches.txt +process/applying-patches.rst - description of various trees and how to apply their patches. arm/ - directory with info about Linux on the ARM architecture. @@ -86,7 +86,7 @@ auxdisplay/ - misc. LCD driver documentation (cfag12864b, ks0108). backlight/ - directory with info on controlling backlights in flat panel displays -bad_memory.txt +admin-guide/bad-memory.rst - how to use kernel parameters to exclude bad RAM regions. basic_profiling.txt - basic instructions for those who wants to profile Linux kernel. @@ -154,7 +154,7 @@ process/ - how to work with the mainline kernel development process. device-mapper/ - directory with info on Device Mapper. -devices.txt +admin-guide/devices.rst - plain ASCII listing of all the nodes in /dev/ with major minor #'s. devicetree/ - directory with info on device tree files used by OF/PowerPC/ARM @@ -178,7 +178,7 @@ efi-stub.txt - How to use the EFI boot stub to bypass GRUB or elilo on EFI systems. eisa.txt - info on EISA bus support. -email-clients.txt +process/email-clients.rst - info on how to use e-mail to send un-mangled (git) patches. extcon/ - directory with porting guide for Android kernel switch driver. @@ -226,9 +226,9 @@ ia64/ - directory with info about Linux on Intel 64 bit architecture. infiniband/ - directory with documents concerning Linux InfiniBand support. -init.txt +admin-guide/init.rst - what to do when the kernel can't find the 1st process to run. -initrd.txt +admin-guide/initrd.rst - how to use the RAM disk as an initial/temporary root filesystem. input/ - info on Linux input device support. @@ -248,7 +248,7 @@ isapnp.txt - info on Linux ISA Plug & Play support. isdn/ - directory with info on the Linux ISDN support, and supported cards. -java.txt +admin-guide/java.rst - info on the in-kernel binary support for Java(tm). ja_JP/ - directory with Japanese translations of various documents @@ -256,11 +256,11 @@ kbuild/ - directory with info about the kernel build process. kdump/ - directory with mini HowTo on getting the crash dump code to work. -kernel-docs.txt +process/kernel-docs.rst - listing of various WWW + books that document kernel internals. kernel-documentation.rst - how to write and format reStructuredText kernel documentation -kernel-parameters.txt +admin-guide/kernel-parameters.rst - summary listing of command line / boot prompt args for the kernel. kernel-per-CPU-kthreads.txt - List of all per-CPU kthreads and how they introduce jitter. @@ -302,7 +302,7 @@ magic-number.txt - list of magic numbers used to mark/protect kernel data structures. mailbox.txt - How to write drivers for the common mailbox framework (IPC). -md.txt +admin-guide/md.rst - info on boot arguments for the multiple devices driver. media-framework.txt - info on media framework, its data structures, functions and usage. @@ -326,7 +326,7 @@ module-signing.txt - Kernel module signing for increased security when loading modules. mtd/ - directory with info about memory technology devices (flash) -mono.txt +admin-guide/mono.rst - how to execute Mono-based .NET binaries with the help of BINFMT_MISC. namespaces/ - directory with various information about namespaces @@ -340,7 +340,7 @@ nommu-mmap.txt - documentation about no-mmu memory mapping support. numastat.txt - info on how to read Numa policy hit/miss statistics in sysfs. -oops-tracing.txt +admin-guide/oops-tracing.rst - how to decode those nasty internal kernel error dump messages. padata.txt - An introduction to the "padata" parallel execution API @@ -378,7 +378,7 @@ ptp/ - directory with info on support for IEEE 1588 PTP clocks in Linux. pwm.txt - info on the pulse width modulation driver subsystem -ramoops.txt +admin-guide/ramoops.rst - documentation of the ramoops oops/panic logging module. rapidio/ - directory with info on RapidIO packet-based fabric interconnect @@ -406,7 +406,7 @@ security/ - directory that contains security-related info serial/ - directory with info on the low level serial API. -serial-console.txt +admin-guide/serial-console.rst - how to set up Linux with a serial line console as the default. sgi-ioc4.txt - description of the SGI IOC4 PCI (multi function) device. @@ -420,9 +420,9 @@ sparse.txt - info on how to obtain and use the sparse tool for typechecking. spi/ - overview of Linux kernel Serial Peripheral Interface (SPI) support. -stable_api_nonsense.txt +process/stable-api-nonsense.rst - info on why the kernel does not have a stable in-kernel api or abi. -stable_kernel_rules.txt +process/stable-kernel-rules.rst - rules and procedures for the -stable kernel releases. static-keys.txt - info on how static keys allow debug code in hotpaths via patching @@ -444,7 +444,7 @@ trace/ - directory with info on tracing technologies within linux unaligned-memory-access.txt - info on how to avoid arch breaking unaligned memory access in code. -unicode.txt +admin-guide/unicode.rst - info on the Unicode character/font mapping used in Linux. unshare.txt - description of the Linux unshare system call. @@ -466,7 +466,7 @@ vm/ - directory with info on the Linux vm code. vme_api.txt - file relating info on the VME bus API in linux -volatile-considered-harmful.txt +process/volatile-considered-harmful.rst - Why the "volatile" type class should not be used w1/ - directory with documents regarding the 1-wire (w1) subsystem. diff --git a/Documentation/ABI/README b/Documentation/ABI/README index 1fafc4b0753b..3121029dce21 100644 --- a/Documentation/ABI/README +++ b/Documentation/ABI/README @@ -84,4 +84,4 @@ stable: - Kernel-internal symbols. Do not rely on the presence, absence, location, or type of any kernel symbol, either in System.map files or the kernel binary - itself. See Documentation/stable_api_nonsense.txt. + itself. See Documentation/process/stable-api-nonsense.rst. diff --git a/Documentation/ABI/testing/sysfs-kernel-slab b/Documentation/ABI/testing/sysfs-kernel-slab index 91bd6ca5440f..2cc0a72b64be 100644 --- a/Documentation/ABI/testing/sysfs-kernel-slab +++ b/Documentation/ABI/testing/sysfs-kernel-slab @@ -347,7 +347,7 @@ Description: because of fragmentation, SLUB will retry with the minimum order possible depending on its characteristics. When debug_guardpage_minorder=N (N > 0) parameter is specified - (see Documentation/kernel-parameters.txt), the minimum possible + (see Documentation/admin-guide/kernel-parameters.rst), the minimum possible order is used and this sysfs entry can not be used to change the order at run time. diff --git a/Documentation/DocBook/kernel-hacking.tmpl b/Documentation/DocBook/kernel-hacking.tmpl index 2a272275c81b..da5c087462b1 100644 --- a/Documentation/DocBook/kernel-hacking.tmpl +++ b/Documentation/DocBook/kernel-hacking.tmpl @@ -1208,8 +1208,8 @@ static struct block_device_operations opt_fops = { - Finally, don't forget to read Documentation/SubmittingPatches - and possibly Documentation/SubmittingDrivers. + Finally, don't forget to read Documentation/process/submitting-patches.rst + and possibly Documentation/process/submitting-drivers.rst. diff --git a/Documentation/acpi/video_extension.txt b/Documentation/acpi/video_extension.txt index 78b32ac02466..79bf6a4921be 100644 --- a/Documentation/acpi/video_extension.txt +++ b/Documentation/acpi/video_extension.txt @@ -101,6 +101,6 @@ received a notification, it will set the backlight level accordingly. This does not affect the sending of event to user space, they are always sent to user space regardless of whether or not the video module controls the backlight level directly. This behaviour can be controlled through the brightness_switch_enabled -module parameter as documented in kernel-parameters.txt. It is recommended to +module parameter as documented in admin-guide/kernel-parameters.rst. It is recommended to disable this behaviour once a GUI environment starts up and wants to have full control of the backlight level. diff --git a/Documentation/admin-guide/README.rst b/Documentation/admin-guide/README.rst index 05aad8543340..1b6dfb2b3adb 100644 --- a/Documentation/admin-guide/README.rst +++ b/Documentation/admin-guide/README.rst @@ -50,7 +50,8 @@ Documentation - There are various README files in the Documentation/ subdirectory: these typically contain kernel-specific installation notes for some drivers for example. See Documentation/00-INDEX for a list of what - is contained in each file. Please read the Changes file, as it + is contained in each file. Please read the + :ref:`Documentation/process/changes.rst ` file, as it contains information about the problems, which may result by upgrading your kernel. @@ -96,7 +97,7 @@ Installing the kernel source and 4.0.2 patches. Similarly, if you are running kernel version 4.0.2 and want to jump to 4.0.3, you must first reverse the 4.0.2 patch (that is, patch -R) **before** applying the 4.0.3 patch. You can read more on this in - :ref:`Documentation/applying-patches.txt `. + :ref:`Documentation/process/applying-patches.rst `. Alternatively, the script patch-kernel can be used to automate this process. It determines the current kernel version and applies any @@ -120,7 +121,7 @@ Software requirements Compiling and running the 4.x kernels requires up-to-date versions of various software packages. Consult - :ref:`Documentation/Changes ` for the minimum version numbers + :ref:`Documentation/process/changes.rst ` for the minimum version numbers required and how to get updates for these packages. Beware that using excessively old versions of these packages can cause indirect errors that are very difficult to track down, so don't assume that @@ -254,7 +255,7 @@ Compiling the kernel -------------------- - Make sure you have at least gcc 3.2 available. - For more information, refer to :ref:`Documentation/Changes `. + For more information, refer to :ref:`Documentation/process/changes.rst `. Please note that you can still run a.out user programs with this kernel. @@ -355,7 +356,7 @@ If something goes wrong help debugging the problem. The text above the dump is also important: it tells something about why the kernel dumped code (in the above example, it's due to a bad kernel pointer). More information - on making sense of the dump is in Documentation/oops-tracing.txt + on making sense of the dump is in Documentation/admin-guide/oops-tracing.rst - If you compiled the kernel with CONFIG_KALLSYMS you can send the dump as is, otherwise you will have to use the ``ksymoops`` program to make @@ -393,7 +394,7 @@ If something goes wrong If you for some reason cannot do the above (you have a pre-compiled kernel image or similar), telling me as much about your setup as - possible will help. Please read the :ref:`REPORTING-BUGS ` + possible will help. Please read the :ref:`admin-guide/reporting-bugs.rst ` document for details. - Alternatively, you can use gdb on a running kernel. (read-only; i.e. you diff --git a/Documentation/admin-guide/bad-memory.rst b/Documentation/admin-guide/bad-memory.rst index 017fc86430c3..a5c0e25e496f 100644 --- a/Documentation/admin-guide/bad-memory.rst +++ b/Documentation/admin-guide/bad-memory.rst @@ -33,7 +33,7 @@ memmap is already in the kernel and usable as kernel-parameter at boot-time. Its syntax is slightly strange and you may need to calculate the values by yourself! -Syntax to exclude a memory area (see kernel-parameters.txt for details):: +Syntax to exclude a memory area (see admin-guide/kernel-parameters.rst for details):: memmap=$
diff --git a/Documentation/admin-guide/binfmt-misc.rst b/Documentation/admin-guide/binfmt-misc.rst index 9c5ff8f260bf..97b0d7927078 100644 --- a/Documentation/admin-guide/binfmt-misc.rst +++ b/Documentation/admin-guide/binfmt-misc.rst @@ -124,7 +124,7 @@ A few examples (assumed you are in ``/proc/sys/fs/binfmt_misc``): echo ':DOSWin:M::MZ::/usr/local/bin/wine:' > register -For java support see Documentation/java.txt +For java support see Documentation/admin-guide/java.rst You can enable/disable binfmt_misc or one binary type by echoing 0 (to disable) @@ -140,7 +140,7 @@ Hints ----- If you want to pass special arguments to your interpreter, you can -write a wrapper script for it. See Documentation/java.txt for an +write a wrapper script for it. See Documentation/admin-guide/java.rst for an example. Your interpreter should NOT look in the PATH for the filename; the kernel diff --git a/Documentation/admin-guide/braille-console.rst b/Documentation/admin-guide/braille-console.rst index fa3702dc04ab..18e79337dcfd 100644 --- a/Documentation/admin-guide/braille-console.rst +++ b/Documentation/admin-guide/braille-console.rst @@ -3,7 +3,7 @@ Linux Braille Console To get early boot messages on a braille device (before userspace screen readers can start), you first need to compile the support for the usual serial -console (see :ref:`Documentation/serial-console.txt `), and +console (see :ref:`Documentation/admin-guide/serial-console.rst `), and for braille device (in :menuselection:`Device Drivers --> Accessibility support --> Console on braille device`). @@ -13,7 +13,7 @@ format is:: console=brl,serial_options... where ``serial_options...`` are the same as described in -:ref:`Documentation/serial-console.txt `. +:ref:`Documentation/admin-guide/serial-console.rst `. So for instance you can use ``console=brl,ttyS0`` if the braille device is connected to the first serial port, and ``console=brl,ttyS0,115200`` to override the baud rate to 115200, etc. @@ -31,7 +31,7 @@ parameter. For simplicity, only one braille console can be enabled, other uses of ``console=brl,...`` will be discarded. Also note that it does not interfere with the console selection mechanism described in -:ref:`Documentation/serial-console.txt `. +:ref:`Documentation/admin-guide/serial-console.rst `. For now, only the VisioBraille device is supported. diff --git a/Documentation/admin-guide/bug-hunting.rst b/Documentation/admin-guide/bug-hunting.rst index a8ef794aadae..d35dd9fd1af0 100644 --- a/Documentation/admin-guide/bug-hunting.rst +++ b/Documentation/admin-guide/bug-hunting.rst @@ -15,7 +15,7 @@ give up. Report as much as you have found to the relevant maintainer. See MAINTAINERS for who that is for the subsystem you have worked on. Before you submit a bug report read -:ref:`Documentation/REPORTING-BUGS `. +:ref:`Documentation/admin-guide/reporting-bugs.rst `. Devices not appearing ===================== @@ -244,5 +244,6 @@ Once you have worked out a fix please submit it upstream. After all open source is about sharing what you do and don't you want to be recognised for your genius? -Please do read :ref:`Documentation/SubmittingPatches ` -though to help your code get accepted. +Please do read +ref:`Documentation/process/submitting-patches.rst ` though +to help your code get accepted. diff --git a/Documentation/admin-guide/devices.rst b/Documentation/admin-guide/devices.rst index b29555041531..89db341fba7a 100644 --- a/Documentation/admin-guide/devices.rst +++ b/Documentation/admin-guide/devices.rst @@ -10,7 +10,7 @@ The LaTeX version of this document is no longer maintained, nor is the document that used to reside at lanana.org. This version in the mainline Linux kernel is the master document. Updates shall be sent as patches to the kernel maintainers (see the -:ref:`Documentation/SubmittingPatches ` document). +:ref:`Documentation/process/submitting-patches.rst ` document). Specifically explore the sections titled "CHAR and MISC DRIVERS", and "BLOCK LAYER" in the MAINTAINERS file to find the right maintainers to involve for character and block devices. diff --git a/Documentation/admin-guide/kernel-parameters.rst b/Documentation/admin-guide/kernel-parameters.rst index b0804273b6e3..d2f2725f032e 100644 --- a/Documentation/admin-guide/kernel-parameters.rst +++ b/Documentation/admin-guide/kernel-parameters.rst @@ -815,7 +815,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted:: bits, and "f" is flow control ("r" for RTS or omit it). Default is "9600n8". - See Documentation/serial-console.txt for more + See Documentation/admin-guide/serial-console.rst for more information. See Documentation/networking/netconsole.txt for an alternative. @@ -2239,7 +2239,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted:: mce=option [X86-64] See Documentation/x86/x86_64/boot-options.txt md= [HW] RAID subsystems devices and level - See Documentation/md.txt. + See Documentation/admin-guide/md.rst. mdacon= [MDA] Format: , @@ -3322,7 +3322,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted:: r128= [HW,DRM] raid= [HW,RAID] - See Documentation/md.txt. + See Documentation/admin-guide/md.rst. ramdisk_size= [RAM] Sizes of RAM disks in kilobytes See Documentation/blockdev/ramdisk.txt. diff --git a/Documentation/admin-guide/oops-tracing.rst b/Documentation/admin-guide/oops-tracing.rst index 3e25ea7349ee..13be8d7bcfe7 100644 --- a/Documentation/admin-guide/oops-tracing.rst +++ b/Documentation/admin-guide/oops-tracing.rst @@ -44,7 +44,7 @@ the disk is not available then you have three options : so won't help for 'early' oopses) (2) Boot with a serial console (see - :ref:`Documentation/serial-console.txt `), + :ref:`Documentation/admin-guide/serial-console.rst `), run a null modem to a second machine and capture the output there using your favourite communication program. Minicom works well. diff --git a/Documentation/admin-guide/ramoops.rst b/Documentation/admin-guide/ramoops.rst index 7eaf1e71c083..fe95c027e37c 100644 --- a/Documentation/admin-guide/ramoops.rst +++ b/Documentation/admin-guide/ramoops.rst @@ -61,7 +61,7 @@ Setting the ramoops parameters can be done in several different manners: mem=128M ramoops.mem_address=0x8000000 ramoops.ecc=1 B. Use Device Tree bindings, as described in - ``Documentation/device-tree/bindings/reserved-memory/ramoops.txt``. + ``Documentation/device-tree/bindings/reserved-memory/admin-guide/ramoops.rst``. For example:: reserved-memory { diff --git a/Documentation/admin-guide/reporting-bugs.rst b/Documentation/admin-guide/reporting-bugs.rst index 05c53ac7fa76..0c0f2698ec5a 100644 --- a/Documentation/admin-guide/reporting-bugs.rst +++ b/Documentation/admin-guide/reporting-bugs.rst @@ -61,7 +61,7 @@ files to the get_maintainer.pl script:: If it is a security bug, please copy the Security Contact listed in the MAINTAINERS file. They can help coordinate bugfix and disclosure. See -:ref:`Documentation/SecurityBugs ` for more information. +:ref:`Documentation/admin-guide/security-bugs.rst ` for more information. If you can't figure out which subsystem caused the issue, you should file a bug in kernel.org bugzilla and send email to @@ -94,7 +94,7 @@ step-by-step instructions for how a user can trigger the bug. If the failure includes an "OOPS:", take a picture of the screen, capture a netconsole trace, or type the message from your screen into the bug -report. Please read "Documentation/oops-tracing.txt" before posting your +report. Please read "Documentation/admin-guide/oops-tracing.rst" before posting your bug report. This explains what you should do with the "Oops" information to make it useful to the recipient. @@ -120,7 +120,7 @@ summary from [1.]>" for easy identification by the developers:: [4.2.] Kernel .config file: [5.] Most recent kernel version which did not have the bug: [6.] Output of Oops.. message (if applicable) with symbolic information - resolved (see Documentation/oops-tracing.txt) + resolved (see Documentation/admin-guide/oops-tracing.rst) [7.] A small shell script or example program which triggers the problem (if possible) [8.] Environment diff --git a/Documentation/admin-guide/security-bugs.rst b/Documentation/admin-guide/security-bugs.rst index df795e22d08b..4f7414cad586 100644 --- a/Documentation/admin-guide/security-bugs.rst +++ b/Documentation/admin-guide/security-bugs.rst @@ -19,7 +19,7 @@ area maintainers to understand and fix the security vulnerability. As it is with any bug, the more information provided the easier it will be to diagnose and fix. Please review the procedure outlined in -REPORTING-BUGS if you are unclear about what information is helpful. +admin-guide/reporting-bugs.rst if you are unclear about what information is helpful. Any exploit code is very helpful and will not be released without consent from the reporter unless it has already been made public. diff --git a/Documentation/admin-guide/unicode.rst b/Documentation/admin-guide/unicode.rst index 012e8e895842..4e5c3df9d55f 100644 --- a/Documentation/admin-guide/unicode.rst +++ b/Documentation/admin-guide/unicode.rst @@ -7,7 +7,7 @@ This file is maintained by H. Peter Anvin as part of the Linux Assigned Names And Numbers Authority (LANANA) project. The current version can be found at: - http://www.lanana.org/docs/unicode/unicode.txt + http://www.lanana.org/docs/unicode/admin-guide/unicode.rst Introdution ----------- diff --git a/Documentation/arm/Booting b/Documentation/arm/Booting index 83c1df2fc758..259f00af3ab3 100644 --- a/Documentation/arm/Booting +++ b/Documentation/arm/Booting @@ -51,7 +51,7 @@ As an alternative, the boot loader can pass the relevant 'console=' option to the kernel via the tagged lists specifying the port, and serial format options as described in - Documentation/kernel-parameters.txt. + Documentation/admin-guide/kernel-parameters.rst. 3. Detect the machine type diff --git a/Documentation/atomic_ops.txt b/Documentation/atomic_ops.txt index c9d1cacb4395..7281bf939779 100644 --- a/Documentation/atomic_ops.txt +++ b/Documentation/atomic_ops.txt @@ -16,7 +16,7 @@ will fail. Something like the following should suffice: typedef struct { long counter; } atomic_long_t; Historically, counter has been declared volatile. This is now discouraged. -See Documentation/volatile-considered-harmful.txt for the complete rationale. +See Documentation/process/volatile-considered-harmful.rst for the complete rationale. local_t is very similar to atomic_t. If the counter is per CPU and only updated by one CPU, local_t is probably more appropriate. Please see diff --git a/Documentation/blockdev/ramdisk.txt b/Documentation/blockdev/ramdisk.txt index fe2ef978d85a..501e12e0323e 100644 --- a/Documentation/blockdev/ramdisk.txt +++ b/Documentation/blockdev/ramdisk.txt @@ -14,7 +14,7 @@ Contents: The RAM disk driver is a way to use main system memory as a block device. It is required for initrd, an initial filesystem used if you need to load modules -in order to access the root filesystem (see Documentation/initrd.txt). It can +in order to access the root filesystem (see Documentation/admin-guide/initrd.rst). It can also be used for a temporary filesystem for crypto work, since the contents are erased on reboot. diff --git a/Documentation/cgroup-v1/00-INDEX b/Documentation/cgroup-v1/00-INDEX index 106885ad670d..13e0c85e7b35 100644 --- a/Documentation/cgroup-v1/00-INDEX +++ b/Documentation/cgroup-v1/00-INDEX @@ -8,7 +8,7 @@ cpuacct.txt - CPU Accounting Controller; account CPU usage for groups of tasks. cpusets.txt - documents the cpusets feature; assign CPUs and Mem to a set of tasks. -devices.txt +admin-guide/devices.rst - Device Whitelist Controller; description, interface and security. freezer-subsystem.txt - checkpointing; rationale to not use signals, interface. diff --git a/Documentation/devicetree/bindings/rtc/maxim,ds3231.txt b/Documentation/devicetree/bindings/rtc/maxim,ds3231.txt index ddef330d2709..1ad4c1c2b3b3 100644 --- a/Documentation/devicetree/bindings/rtc/maxim,ds3231.txt +++ b/Documentation/devicetree/bindings/rtc/maxim,ds3231.txt @@ -1,7 +1,7 @@ * Maxim DS3231 Real Time Clock Required properties: -see: Documentation/devicetree/bindings/i2c/trivial-devices.txt +see: Documentation/devicetree/bindings/i2c/trivial-admin-guide/devices.rst Optional property: - #clock-cells: Should be 1. diff --git a/Documentation/devicetree/bindings/rtc/pcf8563.txt b/Documentation/devicetree/bindings/rtc/pcf8563.txt index 72f6d2c9665e..086c998c5561 100644 --- a/Documentation/devicetree/bindings/rtc/pcf8563.txt +++ b/Documentation/devicetree/bindings/rtc/pcf8563.txt @@ -3,7 +3,7 @@ Philips PCF8563/Epson RTC8564 Real Time Clock Required properties: -see: Documentation/devicetree/bindings/i2c/trivial-devices.txt +see: Documentation/devicetree/bindings/i2c/trivial-admin-guide/devices.rst Optional property: - #clock-cells: Should be 0. diff --git a/Documentation/devicetree/bindings/submitting-patches.txt b/Documentation/devicetree/bindings/submitting-patches.txt index 7d44eae7ab0b..274058c583dd 100644 --- a/Documentation/devicetree/bindings/submitting-patches.txt +++ b/Documentation/devicetree/bindings/submitting-patches.txt @@ -3,7 +3,7 @@ I. For patch submitters - 0) Normal patch submission rules from Documentation/SubmittingPatches + 0) Normal patch submission rules from Documentation/process/submitting-patches.rst applies. 1) The Documentation/ portion of the patch should be a separate patch. diff --git a/Documentation/filesystems/locks.txt b/Documentation/filesystems/locks.txt index 2cf81082581d..5368690f412e 100644 --- a/Documentation/filesystems/locks.txt +++ b/Documentation/filesystems/locks.txt @@ -19,7 +19,7 @@ forever. This should not cause problems for anybody, since everybody using a 2.1.x kernel should have updated their C library to a suitable version -anyway (see the file "Documentation/Changes".) +anyway (see the file "Documentation/process/changes.rst".) 1.2 Allow Mixed Locks Again --------------------------- diff --git a/Documentation/filesystems/nfs/nfsroot.txt b/Documentation/filesystems/nfs/nfsroot.txt index 0b2883b17d4c..5efae00f6c7f 100644 --- a/Documentation/filesystems/nfs/nfsroot.txt +++ b/Documentation/filesystems/nfs/nfsroot.txt @@ -11,7 +11,7 @@ Updated 2006 by Horms In order to use a diskless system, such as an X-terminal or printer server for example, it is necessary for the root filesystem to be present on a non-disk device. This may be an initramfs (see Documentation/filesystems/ -ramfs-rootfs-initramfs.txt), a ramdisk (see Documentation/initrd.txt) or a +ramfs-rootfs-initramfs.txt), a ramdisk (see Documentation/admin-guide/initrd.rst) or a filesystem mounted via NFS. The following text describes on how to use NFS for the root filesystem. For the rest of this text 'client' means the diskless system, and 'server' means the NFS server. @@ -284,7 +284,7 @@ They depend on various facilities being available: "kernel ". The nfsroot parameters are passed to the kernel by adding them to the "append" line. It is common to use serial console in conjunction with pxeliunx, - see Documentation/serial-console.txt for more information. + see Documentation/admin-guide/serial-console.rst for more information. For more information on isolinux, including how to create bootdisks for prebuilt kernels, see http://syslinux.zytor.com/ diff --git a/Documentation/frv/booting.txt b/Documentation/frv/booting.txt index 9bdf4b46e741..cd9dc1dfb144 100644 --- a/Documentation/frv/booting.txt +++ b/Documentation/frv/booting.txt @@ -119,7 +119,7 @@ separated by spaces: 253:0 Device with major 253 and minor 0 Authoritative information can be found in - "Documentation/kernel-parameters.txt". + "Documentation/admin-guide/kernel-parameters.rst". (*) rw diff --git a/Documentation/hwmon/submitting-patches b/Documentation/hwmon/submitting-patches index 57f60307accc..f88221b46153 100644 --- a/Documentation/hwmon/submitting-patches +++ b/Documentation/hwmon/submitting-patches @@ -10,10 +10,10 @@ increase the chances of your change being accepted. ---------- * It should be unnecessary to mention, but please read and follow - Documentation/SubmitChecklist - Documentation/SubmittingDrivers - Documentation/SubmittingPatches - Documentation/CodingStyle + Documentation/process/submit-checklist.rst + Documentation/process/submitting-drivers.rst + Documentation/process/submitting-patches.rst + Documentation/process/coding-style.rst * Please run your patch through 'checkpatch --strict'. There should be no errors, no warnings, and few if any check messages. If there are any diff --git a/Documentation/isdn/README b/Documentation/isdn/README index cfb1884342ee..32d4e80c2c03 100644 --- a/Documentation/isdn/README +++ b/Documentation/isdn/README @@ -332,7 +332,7 @@ README for the ISDN-subsystem 4. Device-inodes The major and minor numbers and their names are described in - Documentation/devices.txt. The major numbers are: + Documentation/admin-guide/devices.rst. The major numbers are: 43 for the ISDN-tty's. 44 for the ISDN-callout-tty's. diff --git a/Documentation/ja_JP/HOWTO b/Documentation/ja_JP/HOWTO index 581c14bdd7be..b03fc8047f03 100644 --- a/Documentation/ja_JP/HOWTO +++ b/Documentation/ja_JP/HOWTO @@ -127,15 +127,15 @@ linux-api@ver.kernel.org に送ることを勧めます。 小限のレベルで必要な数々のソフトウェアパッケージの一覧を示してい ます。 - Documentation/CodingStyle + Documentation/process/coding-style.rst これは Linux カーネルのコーディングスタイルと背景にある理由を記述 しています。全ての新しいコードはこのドキュメントにあるガイドライン に従っていることを期待されています。大部分のメンテナはこれらのルー ルに従っているものだけを受け付け、多くの人は正しいスタイルのコード だけをレビューします。 - Documentation/SubmittingPatches - Documentation/SubmittingDrivers + Documentation/process/submitting-patches.rst + Documentation/process/submitting-drivers.rst これらのファイルには、どうやってうまくパッチを作って投稿するかに ついて非常に詳しく書かれており、以下を含みます(これだけに限らない けれども) @@ -153,7 +153,7 @@ linux-api@ver.kernel.org に送ることを勧めます。 "Linux kernel patch submission format" http://linux.yyz.us/patch-format.html - Documentation/stable_api_nonsense.txt + Documentation/process/stable-api-nonsense.rst このファイルはカーネルの中に不変のAPIを持たないことにした意識的な 決断の背景にある理由について書かれています。以下のようなことを含 んでいます- @@ -164,29 +164,29 @@ linux-api@ver.kernel.org に送ることを勧めます。 このドキュメントは Linux 開発の思想を理解するのに非常に重要です。 そして、他のOSでの開発者が Linux に移る時にとても重要です。 - Documentation/SecurityBugs + Documentation/admin-guide/security-bugs.rst もし Linux カーネルでセキュリティ問題を発見したように思ったら、こ のドキュメントのステップに従ってカーネル開発者に連絡し、問題解決を 支援してください。 - Documentation/ManagementStyle + Documentation/process/management-style.rst このドキュメントは Linux カーネルのメンテナ達がどう行動するか、 彼らの手法の背景にある共有されている精神について記述しています。こ れはカーネル開発の初心者なら（もしくは、単に興味があるだけの人でも） 重要です。なぜならこのドキュメントは、カーネルメンテナ達の独特な 行動についての多くの誤解や混乱を解消するからです。 - Documentation/stable_kernel_rules.txt + Documentation/process/stable-kernel-rules.rst このファイルはどのように stable カーネルのリリースが行われるかのルー ルが記述されています。そしてこれらのリリースの中のどこかで変更を取 り入れてもらいたい場合に何をすれば良いかが示されています。 - Documentation/kernel-docs.txt + Documentation/process/kernel-docs.rst 　　カーネル開発に付随する外部ドキュメントのリストです。もしあなたが 探しているものがカーネル内のドキュメントでみつからなかった場合、 このリストをあたってみてください。 - Documentation/applying-patches.txt + Documentation/process/applying-patches.rst パッチとはなにか、パッチをどうやって様々なカーネルの開発ブランチに 適用するのかについて正確に記述した良い入門書です。 @@ -314,7 +314,7 @@ Andrew Morton が Linux-kernel メーリングリストにカーネルリリー た問題がなければもう少し長くなることもあります。セキュリティ関連の問題 の場合はこれに対してだいたいの場合、すぐにリリースがされます。 -カーネルツリーに入っている、Documentation/stable_kernel_rules.txt ファ +カーネルツリーに入っている、Documentation/process/stable-kernel-rules.rst ファ イルにはどのような種類の変更が -stable ツリーに受け入れ可能か、またリ リースプロセスがどう動くかが記述されています。 @@ -372,7 +372,7 @@ bugzilla.kernel.org は Linux カーネル開発者がカーネルのバグを 場所です。ユーザは見つけたバグの全てをこのツールで報告すべきです。 どう kernel bugzilla を使うかの詳細は、以下を参照してください- http://bugzilla.kernel.org/page.cgi?id=faq.html -メインカーネルソースディレクトリにあるファイル REPORTING-BUGS はカーネ +メインカーネルソースディレクトリにあるファイル admin-guide/reporting-bugs.rst はカーネ ルバグらしいものについてどうレポートするかの良いテンプレートであり、問 題の追跡を助けるためにカーネル開発者にとってどんな情報が必要なのかの詳 細が書かれています。 @@ -438,7 +438,7 @@ MAINTAINERS ファイルにリストがありますので参照してくださ メールの先頭でなく、各引用行の間にあなたの言いたいことを追加するべきで す。 -もしパッチをメールに付ける場合は、Documentation/SubmittingPatches に提 +もしパッチをメールに付ける場合は、Documentation/process/submitting-patches.rst に提 示されているように、それは プレーンな可読テキストにすることを忘れない ようにしましょう。カーネル開発者は 添付や圧縮したパッチを扱いたがりま せん- diff --git a/Documentation/ja_JP/SubmitChecklist b/Documentation/ja_JP/SubmitChecklist index cb5507b1ac81..60c7c35ac517 100644 --- a/Documentation/ja_JP/SubmitChecklist +++ b/Documentation/ja_JP/SubmitChecklist @@ -1,5 +1,5 @@ NOTE: -This is a version of Documentation/SubmitChecklist into Japanese. +This is a version of Documentation/process/submit-checklist.rst into Japanese. This document is maintained by Takenori Nagano and the JF Project team . If you find any difference between this document and the original file @@ -14,7 +14,7 @@ to update the original English file first. Last Updated: 2008/07/14 ================================== これは、 -linux-2.6.26/Documentation/SubmitChecklist の和訳です。 +linux-2.6.26/Documentation/process/submit-checklist.rst の和訳です。 翻訳団体： JF プロジェクト < http://www.linux.or.jp/JF/ > 翻訳日： 2008/07/14 @@ -27,7 +27,7 @@ Linux カーネルパッチ投稿者向けチェックリスト ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 本書では、パッチをより素早く取り込んでもらいたい開発者が実践すべき基本的な事柄 -をいくつか紹介します。ここにある全ての事柄は、Documentation/SubmittingPatches +をいくつか紹介します。ここにある全ての事柄は、Documentation/process/submitting-patches.rst などのLinuxカーネルパッチ投稿に際しての心得を補足するものです。 1: 妥当なCONFIGオプションや変更されたCONFIGオプション、つまり =y, =m, =n @@ -84,7 +84,7 @@ Linux カーネルパッチ投稿者向けチェックリスト 必ずドキュメントを追加してください。 17: 新しいブートパラメータを追加した場合には、 - 必ずDocumentation/kernel-parameters.txt に説明を追加してください。 + 必ずDocumentation/admin-guide/kernel-parameters.rst に説明を追加してください。 18: 新しくmoduleにパラメータを追加した場合には、MODULE_PARM_DESC()を 利用して必ずその説明を記述してください。 diff --git a/Documentation/ja_JP/SubmittingPatches b/Documentation/ja_JP/SubmittingPatches index 5d6ae639bfa0..02139656463e 100644 --- a/Documentation/ja_JP/SubmittingPatches +++ b/Documentation/ja_JP/SubmittingPatches @@ -1,5 +1,5 @@ NOTE: -This is a version of Documentation/SubmittingPatches into Japanese. +This is a version of Documentation/process/submitting-patches.rst into Japanese. This document is maintained by Keiichi KII and the JF Project team . If you find any difference between this document and the original file @@ -15,7 +15,7 @@ Last Updated: 2011/06/09 ================================== これは、 -linux-2.6.39/Documentation/SubmittingPatches の和訳 +linux-2.6.39/Documentation/process/submitting-patches.rst の和訳 です。 翻訳団体： JF プロジェクト < http://www.linux.or.jp/JF/ > 翻訳日： 2011/06/09 @@ -34,9 +34,9 @@ Linux カーネルに変更を加えたいと思っている個人又は会社 おじけづかせることもあります。この文章はあなたの変更を大いに受け入れ てもらえやすくする提案を集めたものです。 -コードを投稿する前に、Documentation/SubmitChecklist の項目リストに目 +コードを投稿する前に、Documentation/process/submit-checklist.rst の項目リストに目 を通してチェックしてください。もしあなたがドライバーを投稿しようとし -ているなら、Documentation/SubmittingDrivers にも目を通してください。 +ているなら、Documentation/process/submitting-drivers.rst にも目を通してください。 -------------------------------------------- セクション1 パッチの作り方と送り方 @@ -148,7 +148,7 @@ http://savannah.nongnu.org/projects/quilt 4) パッチのスタイルチェック あなたのパッチが基本的な( Linux カーネルの)コーディングスタイルに違反し -ていないかをチェックして下さい。その詳細を Documentation/CodingStyle で +ていないかをチェックして下さい。その詳細を Documentation/process/coding-style.rst で 見つけることができます。コーディングスタイルの違反はレビューする人の 時間を無駄にするだけなので、恐らくあなたのパッチは読まれることすらなく 拒否されるでしょう。 @@ -246,7 +246,7 @@ MIME 形式の添付ファイルは Linus に手間を取らせることにな あれば、誰かが MIME 形式のパッチを再送するよう求めるかもしれません。 余計な変更を加えずにあなたのパッチを送信するための電子メールクライアントの設定 -のヒントについては Documentation/email-clients.txt を参照してください。 +のヒントについては Documentation/process/email-clients.rst を参照してください。 8) 電子メールのサイズ @@ -609,7 +609,7 @@ diffstat の結果を生成するために「 git diff -M --stat --summary 」 し例外を適用するには、本当に妥当な理由が不可欠です。あなたは恐らくこの セクションを Linus のコンピュータ・サイエンス101と呼ぶでしょう。 -1) Documentation/CodingStyleを参照 +1) Documentation/process/coding-style.rstを参照 言うまでもなく、あなたのコードがこのコーディングスタイルからあまりに も逸脱していると、レビューやコメントなしに受け取ってもらえないかもし @@ -704,8 +704,8 @@ Greg Kroah-Hartman, "How to piss off a kernel subsystem maintainer". NO!!!! No more huge patch bombs to linux-kernel@vger.kernel.org people! -Kernel Documentation/CodingStyle: - +Kernel Documentation/process/coding-style.rst: + Linus Torvalds's mail on the canonical patch format: diff --git a/Documentation/ja_JP/stable_api_nonsense.txt b/Documentation/ja_JP/stable_api_nonsense.txt index 7653b5cbfed2..a3b40a4bdcfd 100644 --- a/Documentation/ja_JP/stable_api_nonsense.txt +++ b/Documentation/ja_JP/stable_api_nonsense.txt @@ -1,5 +1,5 @@ NOTE: -This is a version of Documentation/stable_api_nonsense.txt into Japanese. +This is a version of Documentation/process/stable-api-nonsense.rst into Japanese. This document is maintained by IKEDA, Munehiro and the JF Project team . If you find any difference between this document and the original file @@ -14,7 +14,7 @@ to update the original English file first. Last Updated: 2007/07/18 ================================== これは、 -linux-2.6.22-rc4/Documentation/stable_api_nonsense.txt の和訳 +linux-2.6.22-rc4/Documentation/process/stable-api-nonsense.rst の和訳 です。 翻訳団体： JF プロジェクト < http://www.linux.or.jp/JF/ > 翻訳日 ： 2007/06/11 diff --git a/Documentation/ja_JP/stable_kernel_rules.txt b/Documentation/ja_JP/stable_kernel_rules.txt index 9dbda9b5d21e..f9249aecba64 100644 --- a/Documentation/ja_JP/stable_kernel_rules.txt +++ b/Documentation/ja_JP/stable_kernel_rules.txt @@ -1,5 +1,5 @@ NOTE: -This is Japanese translated version of "Documentation/stable_kernel_rules.txt". +This is Japanese translated version of "Documentation/process/stable-kernel-rules.rst". This one is maintained by Tsugikazu Shibata and JF Project team . If you find difference with original file or problem in translation, @@ -12,7 +12,7 @@ file at first. ================================== これは、 -linux-2.6.29/Documentation/stable_kernel_rules.txt +linux-2.6.29/Documentation/process/stable-kernel-rules.rst の和訳です。 翻訳団体： JF プロジェクト < http://www.linux.or.jp/JF/ > @@ -43,7 +43,7 @@ linux-2.6.29/Documentation/stable_kernel_rules.txt "理論的には競合状態になる"ようなものは不可。 - いかなる些細な修正も含めることはできない。(スペルの修正、空白のクリー ンアップなど) - - Documentation/SubmittingPatches の規則に従ったものでなければならない。 + - Documentation/process/submitting-patches.rst の規則に従ったものでなければならない。 - パッチ自体か同等の修正が Linus のツリーに既に存在しなければならない。 　 Linus のツリーでのコミットID を -stable へのパッチ投稿の際に引用す ること。 diff --git a/Documentation/kernel-per-CPU-kthreads.txt b/Documentation/kernel-per-CPU-kthreads.txt index bbc3a8b8cff4..df31e30b6a02 100644 --- a/Documentation/kernel-per-CPU-kthreads.txt +++ b/Documentation/kernel-per-CPU-kthreads.txt @@ -264,7 +264,7 @@ To reduce its OS jitter, do at least one of the following: kthreads from being created in the first place. 2. Boot with "nosoftlockup=0", which will also prevent these kthreads from being created. Other related watchdog and softlockup boot - parameters may be found in Documentation/kernel-parameters.txt + parameters may be found in Documentation/admin-guide/kernel-parameters.rst and Documentation/watchdog/watchdog-parameters.txt. 3. Echo a zero to /proc/sys/kernel/watchdog to disable the watchdog timer. diff --git a/Documentation/ko_KR/HOWTO b/Documentation/ko_KR/HOWTO index 9a3e65924d54..025252731af5 100644 --- a/Documentation/ko_KR/HOWTO +++ b/Documentation/ko_KR/HOWTO @@ -1,5 +1,5 @@ NOTE: -This is a version of Documentation/HOWTO translated into korean +This is a version of Documentation/process/howto.rst translated into korean This document is maintained by Minchan Kim If you find any difference between this document and the original file or a problem with the translation, please contact the maintainer of this file. @@ -11,7 +11,7 @@ try to update the original English file first. ================================== 이 문서는 -Documentation/HOWTO +Documentation/process/howto.rst 의 한글 번역입니다. 역자： 김민찬 @@ -98,18 +98,18 @@ mtk.manpages@gmail.com의 메인테이너에게 보낼 것을 권장한다. 빌드하기 위해 필요한 것을 설명한다. 커널에 입문하는 사람들은 여기서 시작해야 한다. - Documentation/Changes + Documentation/process/changes.rst 이 파일은 커널을 성공적으로 빌드하고 실행시키기 위해 필요한 다양한 소프트웨어 패키지들의 최소 버젼을 나열한다. - Documentation/CodingStyle + Documentation/process/coding-style.rst 이 문서는 리눅스 커널 코딩 스타일과 그렇게 한 몇몇 이유를 설명한다. 모든 새로운 코드는 이 문서에 가이드라인들을 따라야 한다. 대부분의 메인테이너들은 이 규칙을 따르는 패치들만을 받아들일 것이고 많은 사람들이 그 패치가 올바른 스타일일 경우만 코드를 검토할 것이다. - Documentation/SubmittingPatches - Documentation/SubmittingDrivers + Documentation/process/submitting-patches.rst + Documentation/process/submitting-drivers.rst 이 파일들은 성공적으로 패치를 만들고 보내는 법을 다음의 내용들로 굉장히 상세히 설명하고 있다(그러나 다음으로 한정되진 않는다). - Email 내용들 @@ -126,7 +126,7 @@ mtk.manpages@gmail.com의 메인테이너에게 보낼 것을 권장한다. "Linux kernel patch submission format" http://linux.yyz.us/patch-format.html - Documentation/stable_api_nonsense.txt + Documentation/process/stable-api-nonsense.rst 이 문서는 의도적으로 커널이 불변하는 API를 갖지 않도록 결정한 이유를 설명하며 다음과 같은 것들을 포함한다. - 서브시스템 shim-layer(호환성을 위해?) @@ -136,12 +136,12 @@ mtk.manpages@gmail.com의 메인테이너에게 보낼 것을 권장한다. 리눅스로 전향하는 사람들에게는 매우 중요하다. - Documentation/SecurityBugs + Documentation/admin-guide/security-bugs.rst 여러분들이 리눅스 커널의 보안 문제를 발견했다고 생각한다면 이 문서에 나온 단계에 따라서 커널 개발자들에게 알리고 그 문제를 해결할 수 있도록 도와 달라. - Documentation/ManagementStyle + Documentation/process/management-style.rst 이 문서는 리눅스 커널 메인테이너들이 그들의 방법론에 녹아 있는 정신을 어떻게 공유하고 운영하는지를 설명한다. 이것은 커널 개발에 입문하는 모든 사람들(또는 커널 개발에 작은 호기심이라도 있는 사람들)이 @@ -149,17 +149,17 @@ mtk.manpages@gmail.com의 메인테이너에게 보낼 것을 권장한다. 독특한 행동에 관하여 흔히 있는 오해들과 혼란들을 해소하고 있기 때문이다. - Documentation/stable_kernel_rules.txt + Documentation/process/stable-kernel-rules.rst 이 문서는 안정적인 커널 배포가 이루어지는 규칙을 설명하고 있으며 여러분들이 이러한 배포들 중 하나에 변경을 하길 원한다면 무엇을 해야 하는지를 설명한다. - Documentation/kernel-docs.txt + Documentation/process/kernel-docs.rst 커널 개발에 관계된 외부 문서의 리스트이다. 커널 내의 포함된 문서들 중에 여러분이 찾고 싶은 문서를 발견하지 못할 경우 이 리스트를 살펴보라. - Documentation/applying-patches.txt + Documentation/process/applying-patches.rst 패치가 무엇이며 그것을 커널의 다른 개발 브랜치들에 어떻게 적용하는지에 관하여 자세히 설명하고 있는 좋은 입문서이다. @@ -276,7 +276,7 @@ Andrew Morton의 글이 있다. 4.x.y는 "stable" 팀에 의해 관리되며 거의 매번 격주로 배포된다. -커널 트리 문서들 내에 Documentation/stable_kernel_rules.txt 파일은 어떤 +커널 트리 문서들 내에 Documentation/process/stable-kernel-rules.rst 파일은 어떤 종류의 변경들이 -stable 트리로 들어왔는지와 배포 프로세스가 어떻게 진행되는지를 설명한다. @@ -328,7 +328,7 @@ bugzilla.kernel.org는 리눅스 커널 개발자들이 커널의 버그를 추 kernel bugzilla를 사용하는 자세한 방법은 다음을 참조하라. http://test.kernel.org/bugzilla/faq.html -메인 커널 소스 디렉토리에 있는 REPORTING-BUGS 파일은 커널 버그라고 생각되는 +메인 커널 소스 디렉토리에 있는 admin-guide/reporting-bugs.rst 파일은 커널 버그라고 생각되는 것을 보고하는 방법에 관한 좋은 템플릿이며 문제를 추적하기 위해서 커널 개발자들이 필요로 하는 정보가 무엇들인지를 상세히 설명하고 있다. @@ -391,7 +391,7 @@ bugme-janitor 메일링 리스트(bugzilla에 모든 변화들이 여기서 메 "John 커널해커는 작성했다...."를 유지하며 여러분들의 의견을 그 메일의 윗부분에 작성하지 말고 각 인용한 단락들 사이에 넣어라. -여러분들이 패치들을 메일에 넣는다면 그것들은 Documentation/SubmittingPatches에 +여러분들이 패치들을 메일에 넣는다면 그것들은 Documentation/process/submitting-patches.rst에 나와있는데로 명백히(plain) 읽을 수 있는 텍스트여야 한다. 커널 개발자들은 첨부파일이나 압축된 패치들을 원하지 않는다. 그들은 여러분들의 패치의 각 라인 단위로 코멘트를 하길 원하며 압축하거나 첨부하지 않고 보내는 것이 diff --git a/Documentation/ko_KR/stable_api_nonsense.txt b/Documentation/ko_KR/stable_api_nonsense.txt index 3ba10b11d556..4d93af1efd61 100644 --- a/Documentation/ko_KR/stable_api_nonsense.txt +++ b/Documentation/ko_KR/stable_api_nonsense.txt @@ -1,5 +1,5 @@ NOTE: -This is a version of Documentation/stable_api_nonsense.txt translated +This is a version of Documentation/process/stable-api-nonsense.rst translated into korean This document is maintained by Minchan Kim If you find any difference between this document and the original file or @@ -12,7 +12,7 @@ try to update the original English file first. ================================== 이 문서는 -Documentation/stable_api_nonsense.txt +Documentation/process/stable-api-nonsense.rst 의 한글 번역입니다. 역자： 김민찬 diff --git a/Documentation/lockup-watchdogs.txt b/Documentation/lockup-watchdogs.txt index 4a6e33e1af61..c8b8378513d6 100644 --- a/Documentation/lockup-watchdogs.txt +++ b/Documentation/lockup-watchdogs.txt @@ -11,7 +11,7 @@ details), without giving other tasks a chance to run. The current stack trace is displayed upon detection and, by default, the system will stay locked up. Alternatively, the kernel can be configured to panic; a sysctl, "kernel.softlockup_panic", a kernel parameter, -"softlockup_panic" (see "Documentation/kernel-parameters.txt" for +"softlockup_panic" (see "Documentation/admin-guide/kernel-parameters.rst" for details), and a compile option, "BOOTPARAM_SOFTLOCKUP_PANIC", are provided for this. @@ -23,7 +23,7 @@ upon detection and the system will stay locked up unless the default behavior is changed, which can be done through a sysctl, 'hardlockup_panic', a compile time knob, "BOOTPARAM_HARDLOCKUP_PANIC", and a kernel parameter, "nmi_watchdog" -(see "Documentation/kernel-parameters.txt" for details). +(see "Documentation/admin-guide/kernel-parameters.rst" for details). The panic option can be used in combination with panic_timeout (this timeout is set through the confusingly named "kernel.panic" sysctl), diff --git a/Documentation/m68k/kernel-options.txt b/Documentation/m68k/kernel-options.txt index eaf32a1fd0b1..79d21246c75a 100644 --- a/Documentation/m68k/kernel-options.txt +++ b/Documentation/m68k/kernel-options.txt @@ -139,7 +139,7 @@ follows: PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF/PARTNROFF=-2 Authoritative information can be found in -"Documentation/kernel-parameters.txt". +"Documentation/admin-guide/kernel-parameters.rst". 2.2) ro, rw diff --git a/Documentation/media/uapi/v4l/diff-v4l.rst b/Documentation/media/uapi/v4l/diff-v4l.rst index 76b2ecab8657..8209eeb63dd2 100644 --- a/Documentation/media/uapi/v4l/diff-v4l.rst +++ b/Documentation/media/uapi/v4l/diff-v4l.rst @@ -648,12 +648,12 @@ microcode programming. A new interface for MPEG compression and playback devices is documented in :ref:`extended-controls`. .. [#f1] - According to Documentation/devices.txt these should be symbolic links + According to Documentation/admin-guide/devices.rst these should be symbolic links to ``/dev/video0``. Note the original bttv interface is not compatible with V4L or V4L2. .. [#f2] - According to ``Documentation/devices.txt`` a symbolic link to + According to ``Documentation/admin-guide/devices.rst`` a symbolic link to ``/dev/radio0``. .. [#f3] diff --git a/Documentation/media/v4l-drivers/bttv.rst b/Documentation/media/v4l-drivers/bttv.rst index 7abc1c9a261b..bc63b12efafd 100644 --- a/Documentation/media/v4l-drivers/bttv.rst +++ b/Documentation/media/v4l-drivers/bttv.rst @@ -304,10 +304,10 @@ bug. It is very helpful if you can tell where exactly it broke With a hard freeze you probably doesn't find anything in the logfiles. The only way to capture any kernel messages is to hook up a serial console and let some terminal application log the messages. /me uses -screen. See Documentation/serial-console.txt for details on setting +screen. See Documentation/admin-guide/serial-console.rst for details on setting up a serial console. -Read Documentation/oops-tracing.txt to learn how to get any useful +Read Documentation/admin-guide/oops-tracing.rst to learn how to get any useful information out of a register+stack dump printed by the kernel on protection faults (so-called "kernel oops"). diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt index 0d7cb955aa01..5de846d3ecc0 100644 --- a/Documentation/memory-hotplug.txt +++ b/Documentation/memory-hotplug.txt @@ -324,7 +324,7 @@ guarantee that the memory block contains only migratable pages. Now, a boot option for making a memory block which consists of migratable pages is supported. By specifying "kernelcore=" or "movablecore=" boot option, you can create ZONE_MOVABLE...a zone which is just used for movable pages. -(See also Documentation/kernel-parameters.txt) +(See also Documentation/admin-guide/kernel-parameters.rst) Assume the system has "TOTAL" amount of memory at boot time, this boot option creates ZONE_MOVABLE as following. diff --git a/Documentation/networking/netconsole.txt b/Documentation/networking/netconsole.txt index 30409a36e95d..296ea00fd3eb 100644 --- a/Documentation/networking/netconsole.txt +++ b/Documentation/networking/netconsole.txt @@ -200,7 +200,7 @@ priority messages to the console. You can change this at runtime using: or by specifying "debug" on the kernel command line at boot, to send all kernel messages to the console. A specific value for this parameter can also be set using the "loglevel" kernel boot option. See the -dmesg(8) man page and Documentation/kernel-parameters.txt for details. +dmesg(8) man page and Documentation/admin-guide/kernel-parameters.rst for details. Netconsole was designed to be as instantaneous as possible, to enable the logging of even the most critical kernel bugs. It works diff --git a/Documentation/networking/netdev-FAQ.txt b/Documentation/networking/netdev-FAQ.txt index 0fe1c6e0dbcd..cdebc5c8705f 100644 --- a/Documentation/networking/netdev-FAQ.txt +++ b/Documentation/networking/netdev-FAQ.txt @@ -136,14 +136,14 @@ A: Normally Greg Kroah-Hartman collects stable commits himself, but Q: I see a network patch and I think it should be backported to stable. Should I request it via "stable@vger.kernel.org" like the references in - the kernel's Documentation/stable_kernel_rules.txt file say? + the kernel's Documentation/process/stable-kernel-rules.rst file say? A: No, not for networking. Check the stable queues as per above 1st to see if it is already queued. If not, then send a mail to netdev, listing the upstream commit ID and why you think it should be a stable candidate. Before you jump to go do the above, do note that the normal stable rules - in Documentation/stable_kernel_rules.txt still apply. So you need to + in Documentation/process/stable-kernel-rules.rst still apply. So you need to explicitly indicate why it is a critical fix and exactly what users are impacted. In addition, you need to convince yourself that you _really_ think it has been overlooked, vs. having been considered and rejected. @@ -165,7 +165,7 @@ A: No. See above answer. In short, if you think it really belongs in If you think there is some valid information relating to it being in stable that does _not_ belong in the commit log, then use the three - dash marker line as described in Documentation/SubmittingPatches to + dash marker line as described in Documentation/process/submitting-patches.rst to temporarily embed that information into the patch that you send. Q: Someone said that the comment style and coding convention is different @@ -220,5 +220,5 @@ A: Attention to detail. Re-read your own work as if you were the If it is your first patch, mail it to yourself so you can test apply it to an unpatched tree to confirm infrastructure didn't mangle it. - Finally, go back and read Documentation/SubmittingPatches to be + Finally, go back and read Documentation/process/submitting-patches.rst to be sure you are not repeating some common mistake documented there. diff --git a/Documentation/networking/vortex.txt b/Documentation/networking/vortex.txt index 97282da82b75..ad3dead052a4 100644 --- a/Documentation/networking/vortex.txt +++ b/Documentation/networking/vortex.txt @@ -364,7 +364,7 @@ steps you should take: - The contents of your report will vary a lot depending upon the problem. If it's a kernel crash then you should refer to the - REPORTING-BUGS file. + admin-guide/reporting-bugs.rst file. But for most problems it is useful to provide the following: diff --git a/Documentation/power/00-INDEX b/Documentation/power/00-INDEX index ad04cc8097ed..7cb6085839f3 100644 --- a/Documentation/power/00-INDEX +++ b/Documentation/power/00-INDEX @@ -6,7 +6,7 @@ basic-pm-debugging.txt - Debugging suspend and resume charger-manager.txt - Battery charger management. -devices.txt +admin-guide/devices.rst - How drivers interact with system-wide power management drivers-testing.txt - Testing suspend and resume support in device drivers diff --git a/Documentation/power/pci.txt b/Documentation/power/pci.txt index 44558882aa60..85c746cbab2c 100644 --- a/Documentation/power/pci.txt +++ b/Documentation/power/pci.txt @@ -8,7 +8,7 @@ management. Based on previous work by Patrick Mochel This document only covers the aspects of power management specific to PCI devices. For general description of the kernel's interfaces related to device -power management refer to Documentation/power/devices.txt and +power management refer to Documentation/power/admin-guide/devices.rst and Documentation/power/runtime_pm.txt. --------------------------------------------------------------------------- @@ -417,7 +417,7 @@ pm->runtime_idle() callback. 2.4. System-Wide Power Transitions ---------------------------------- There are a few different types of system-wide power transitions, described in -Documentation/power/devices.txt. Each of them requires devices to be handled +Documentation/power/admin-guide/devices.rst. Each of them requires devices to be handled in a specific way and the PM core executes subsystem-level power management callbacks for this purpose. They are executed in phases such that each phase involves executing the same subsystem-level callback for every device belonging @@ -623,7 +623,7 @@ System restore requires a hibernation image to be loaded into memory and the pre-hibernation memory contents to be restored before the pre-hibernation system activity can be resumed. -As described in Documentation/power/devices.txt, the hibernation image is loaded +As described in Documentation/power/admin-guide/devices.rst, the hibernation image is loaded into memory by a fresh instance of the kernel, called the boot kernel, which in turn is loaded and run by a boot loader in the usual way. After the boot kernel has loaded the image, it needs to replace its own code and data with the code @@ -677,7 +677,7 @@ controlling the runtime power management of their devices. At the time of this writing there are two ways to define power management callbacks for a PCI device driver, the recommended one, based on using a -dev_pm_ops structure described in Documentation/power/devices.txt, and the +dev_pm_ops structure described in Documentation/power/admin-guide/devices.rst, and the "legacy" one, in which the .suspend(), .suspend_late(), .resume_early(), and .resume() callbacks from struct pci_driver are used. The legacy approach, however, doesn't allow one to define runtime power management callbacks and is @@ -1046,5 +1046,5 @@ PCI Local Bus Specification, Rev. 3.0 PCI Bus Power Management Interface Specification, Rev. 1.2 Advanced Configuration and Power Interface (ACPI) Specification, Rev. 3.0b PCI Express Base Specification, Rev. 2.0 -Documentation/power/devices.txt +Documentation/power/admin-guide/devices.rst Documentation/power/runtime_pm.txt diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt index 1fd1fbe9ce95..4870980e967e 100644 --- a/Documentation/power/runtime_pm.txt +++ b/Documentation/power/runtime_pm.txt @@ -674,7 +674,7 @@ left in runtime suspend. If that happens, the PM core will not execute any system suspend and resume callbacks for all of those devices, except for the complete callback, which is then entirely responsible for handling the device as appropriate. This only applies to system suspend transitions that are not -related to hibernation (see Documentation/power/devices.txt for more +related to hibernation (see Documentation/power/admin-guide/devices.rst for more information). The PM core does its best to reduce the probability of race conditions between diff --git a/Documentation/power/swsusp-dmcrypt.txt b/Documentation/power/swsusp-dmcrypt.txt index 59931b46ff7e..b802fbfd95ef 100644 --- a/Documentation/power/swsusp-dmcrypt.txt +++ b/Documentation/power/swsusp-dmcrypt.txt @@ -8,7 +8,7 @@ Some prerequisites: You know how dm-crypt works. If not, visit the following web page: http://www.saout.de/misc/dm-crypt/ You have read Documentation/power/swsusp.txt and understand it. -You did read Documentation/initrd.txt and know how an initrd works. +You did read Documentation/admin-guide/initrd.rst and know how an initrd works. You know how to create or how to modify an initrd. Now your system is properly set up, your disk is encrypted except for diff --git a/Documentation/process/4.Coding.rst b/Documentation/process/4.Coding.rst index 9d5cef996f7f..983d628c1112 100644 --- a/Documentation/process/4.Coding.rst +++ b/Documentation/process/4.Coding.rst @@ -22,7 +22,7 @@ Coding style ************ The kernel has long had a standard coding style, described in -Documentation/CodingStyle. For much of that time, the policies described +Documentation/process/coding-style.rst. For much of that time, the policies described in that file were taken as being, at most, advisory. As a result, there is a substantial amount of code in the kernel which does not meet the coding style guidelines. The presence of that code leads to two independent @@ -343,7 +343,7 @@ user-space developers to know what they are working with. See Documentation/ABI/README for a description of how this documentation should be formatted and what information needs to be provided. -The file Documentation/kernel-parameters.txt describes all of the kernel's +The file Documentation/admin-guide/kernel-parameters.rst describes all of the kernel's boot-time parameters. Any patch which adds new parameters should add the appropriate entries to this file. diff --git a/Documentation/process/5.Posting.rst b/Documentation/process/5.Posting.rst index b511ddf7e82a..1b7728b19ea7 100644 --- a/Documentation/process/5.Posting.rst +++ b/Documentation/process/5.Posting.rst @@ -9,8 +9,8 @@ kernel. Unsurprisingly, the kernel development community has evolved a set of conventions and procedures which are used in the posting of patches; following them will make life much easier for everybody involved. This document will attempt to cover these expectations in reasonable detail; -more information can also be found in the files SubmittingPatches, -SubmittingDrivers, and SubmitChecklist in the kernel documentation +more information can also be found in the files process/submitting-patches.rst, +process/submitting-drivers.rst, and process/submit-checklist.rst in the kernel documentation directory. @@ -198,7 +198,7 @@ pass it to diff with the "-X" option. The tags mentioned above are used to describe how various developers have been associated with the development of this patch. They are described in -detail in the SubmittingPatches document; what follows here is a brief +detail in the process/submitting-patches.rst document; what follows here is a brief summary. Each of these lines has the format: :: @@ -210,7 +210,7 @@ The tags in common use are: - Signed-off-by: this is a developer's certification that he or she has the right to submit the patch for inclusion into the kernel. It is an agreement to the Developer's Certificate of Origin, the full text of - which can be found in Documentation/SubmittingPatches. Code without a + which can be found in Documentation/process/submitting-patches.rst. Code without a proper signoff cannot be merged into the mainline. - Acked-by: indicates an agreement by another developer (often a @@ -221,7 +221,7 @@ The tags in common use are: it to work. - Reviewed-by: the named developer has reviewed the patch for correctness; - see the reviewer's statement in Documentation/SubmittingPatches for more + see the reviewer's statement in Documentation/process/submitting-patches.rst for more detail. - Reported-by: names a user who reported a problem which is fixed by this @@ -248,7 +248,7 @@ take care of: be examined in any detail. If there is any doubt at all, mail the patch to yourself and convince yourself that it shows up intact. - Documentation/email-clients.txt has some helpful hints on making + Documentation/process/email-clients.rst has some helpful hints on making specific mail clients work for sending patches. - Are you sure your patch is free of silly mistakes? You should always diff --git a/Documentation/process/8.Conclusion.rst b/Documentation/process/8.Conclusion.rst index 23ec7cbc2d2b..1c7f54cd0261 100644 --- a/Documentation/process/8.Conclusion.rst +++ b/Documentation/process/8.Conclusion.rst @@ -5,9 +5,9 @@ For more information There are numerous sources of information on Linux kernel development and related topics. First among those will always be the Documentation -directory found in the kernel source distribution. The top-level HOWTO -file is an important starting point; SubmittingPatches and -SubmittingDrivers are also something which all kernel developers should +directory found in the kernel source distribution. The top-level process/howto.rst +file is an important starting point; process/submitting-patches.rst and +process/submitting-drivers.rst are also something which all kernel developers should read. Many internal kernel APIs are documented using the kerneldoc mechanism; "make htmldocs" or "make pdfdocs" can be used to generate those documents in HTML or PDF format (though the version of TeX shipped by some diff --git a/Documentation/process/adding-syscalls.rst b/Documentation/process/adding-syscalls.rst index f5b5b1aa51b3..8cc25a06f353 100644 --- a/Documentation/process/adding-syscalls.rst +++ b/Documentation/process/adding-syscalls.rst @@ -3,7 +3,7 @@ Adding a New System Call This document describes what's involved in adding a new system call to the Linux kernel, over and above the normal submission advice in -:ref:`Documentation/SubmittingPatches `. +:ref:`Documentation/process/submitting-patches.rst `. System Call Alternatives diff --git a/Documentation/process/coding-style.rst b/Documentation/process/coding-style.rst index 9c61c039ccd9..968808bec407 100644 --- a/Documentation/process/coding-style.rst +++ b/Documentation/process/coding-style.rst @@ -1058,5 +1058,5 @@ gcc internals and indent, all available from http://www.gnu.org/manual/ WG14 is the international standardization working group for the programming language C, URL: http://www.open-std.org/JTC1/SC22/WG14/ -Kernel CodingStyle, by greg@kroah.com at OLS 2002: +Kernel process/coding-style.rst, by greg@kroah.com at OLS 2002: http://www.kroah.com/linux/talks/ols_2002_kernel_codingstyle_talk/html/ diff --git a/Documentation/process/howto.rst b/Documentation/process/howto.rst index 5f042349f987..3f66a1980726 100644 --- a/Documentation/process/howto.rst +++ b/Documentation/process/howto.rst @@ -90,19 +90,19 @@ required reading: what is necessary to do to configure and build the kernel. People who are new to the kernel should start here. - :ref:`Documentation/Changes ` + :ref:`Documentation/process/changes.rst ` This file gives a list of the minimum levels of various software packages that are necessary to build and run the kernel successfully. - :ref:`Documentation/CodingStyle ` + :ref:`Documentation/process/coding-style.rst ` This describes the Linux kernel coding style, and some of the rationale behind it. All new code is expected to follow the guidelines in this document. Most maintainers will only accept patches if these rules are followed, and many people will only review code if it is in the proper style. - :ref:`Documentation/SubmittingPatches ` and :ref:`Documentation/SubmittingDrivers ` + :ref:`Documentation/process/submitting-patches.rst ` and :ref:`Documentation/process/submitting-drivers.rst ` These files describe in explicit detail how to successfully create and send a patch, including (but not limited to): @@ -122,7 +122,7 @@ required reading: "Linux kernel patch submission format" http://linux.yyz.us/patch-format.html - :ref:`Documentation/stable_api_nonsense.txt ` + :ref:`Documentation/process/stable-api-nonsense.rst ` This file describes the rationale behind the conscious decision to not have a stable API within the kernel, including things like: @@ -135,29 +135,29 @@ required reading: philosophy and is very important for people moving to Linux from development on other Operating Systems. - :ref:`Documentation/SecurityBugs ` + :ref:`Documentation/admin-guide/security-bugs.rst ` If you feel you have found a security problem in the Linux kernel, please follow the steps in this document to help notify the kernel developers, and help solve the issue. - :ref:`Documentation/ManagementStyle ` + :ref:`Documentation/process/management-style.rst ` This document describes how Linux kernel maintainers operate and the shared ethos behind their methodologies. This is important reading for anyone new to kernel development (or anyone simply curious about it), as it resolves a lot of common misconceptions and confusion about the unique behavior of kernel maintainers. - :ref:`Documentation/stable_kernel_rules.txt ` + :ref:`Documentation/process/stable-kernel-rules.rst ` This file describes the rules on how the stable kernel releases happen, and what to do if you want to get a change into one of these releases. - :ref:`Documentation/kernel-docs.txt ` + :ref:`Documentation/process/kernel-docs.rst ` A list of external documentation that pertains to kernel development. Please consult this list if you do not find what you are looking for within the in-kernel documentation. - :ref:`Documentation/applying-patches.txt ` + :ref:`Documentation/process/applying-patches.rst ` A good introduction describing exactly what a patch is and how to apply it to the different development branches of the kernel. @@ -307,7 +307,7 @@ two weeks, but it can be longer if there are no pressing problems. A security-related problem, instead, can cause a release to happen almost instantly. -The file Documentation/stable_kernel_rules.txt in the kernel tree +The file Documentation/process/stable-kernel-rules.rst in the kernel tree documents what kinds of changes are acceptable for the -stable tree, and how the release process works. @@ -366,7 +366,7 @@ tool. For details on how to use the kernel bugzilla, please see: https://bugzilla.kernel.org/page.cgi?id=faq.html -The file REPORTING-BUGS in the main kernel source directory has a good +The file admin-guide/reporting-bugs.rst in the main kernel source directory has a good template for how to report a possible kernel bug, and details what kind of information is needed by the kernel developers to help track down the problem. @@ -440,7 +440,7 @@ add your statements between the individual quoted sections instead of writing at the top of the mail. If you add patches to your mail, make sure they are plain readable text -as stated in Documentation/SubmittingPatches. +as stated in Documentation/process/submitting-patches.rst. Kernel developers don't want to deal with attachments or compressed patches; they may want to comment on individual lines of your patch, which works only that way. Make sure you diff --git a/Documentation/process/management-style.rst b/Documentation/process/management-style.rst index dea2e66c9a10..45595fd8a66b 100644 --- a/Documentation/process/management-style.rst +++ b/Documentation/process/management-style.rst @@ -5,7 +5,7 @@ Linux kernel management style This is a short document describing the preferred (or made up, depending on who you ask) management style for the linux kernel. It's meant to -mirror the CodingStyle document to some degree, and mainly written to +mirror the process/coding-style.rst document to some degree, and mainly written to avoid answering [#f1]_ the same (or similar) questions over and over again. Management style is very personal and much harder to quantify than diff --git a/Documentation/process/stable-kernel-rules.rst b/Documentation/process/stable-kernel-rules.rst index 4d82e31b7958..11ec2d93a5e0 100644 --- a/Documentation/process/stable-kernel-rules.rst +++ b/Documentation/process/stable-kernel-rules.rst @@ -27,7 +27,7 @@ Rules on what kind of patches are accepted, and which ones are not, into the - It cannot contain any "trivial" fixes in it (spelling changes, whitespace cleanups, etc). - It must follow the - :ref:`Documentation/SubmittingPatches ` + :ref:`Documentation/process/submitting-patches.rst ` rules. - It or an equivalent fix must already exist in Linus' tree (upstream). @@ -40,7 +40,7 @@ Procedure for submitting patches to the -stable tree Documentation/networking/netdev-FAQ.txt - Security patches should not be handled (solely) by the -stable review process but should follow the procedures in - :ref:`Documentation/SecurityBugs `. + :ref:`Documentation/admin-guide/security-bugs.rst `. For all other submissions, choose one of the following procedures ----------------------------------------------------------------- diff --git a/Documentation/process/submit-checklist.rst b/Documentation/process/submit-checklist.rst index 894289b22b15..a0d9d34bfb6d 100644 --- a/Documentation/process/submit-checklist.rst +++ b/Documentation/process/submit-checklist.rst @@ -7,7 +7,7 @@ Here are some basic things that developers should do if they want to see their kernel patch submissions accepted more quickly. These are all above and beyond the documentation that is provided in -:ref:`Documentation/SubmittingPatches ` +:ref:`Documentation/process/submitting-patches.rst ` and elsewhere regarding submitting Linux kernel patches. @@ -31,7 +31,7 @@ and elsewhere regarding submitting Linux kernel patches. tends to use ``unsigned long`` for 64-bit quantities. 5) Check your patch for general style as detailed in - :ref:`Documentation/CodingStyle `. + :ref:`Documentation/process/coding-style.rst `. Check for trivial violations with the patch style checker prior to submission (``scripts/checkpatch.pl``). You should be able to justify all violations that remain in @@ -78,7 +78,7 @@ and elsewhere regarding submitting Linux kernel patches. 16) All new ``/proc`` entries are documented under ``Documentation/`` 17) All new kernel boot parameters are documented in - ``Documentation/kernel-parameters.txt``. + ``Documentation/admin-guide/kernel-parameters.rst``. 18) All new module parameters are documented with ``MODULE_PARM_DESC()`` diff --git a/Documentation/process/submitting-drivers.rst b/Documentation/process/submitting-drivers.rst index 252b77a23fad..0939d018c289 100644 --- a/Documentation/process/submitting-drivers.rst +++ b/Documentation/process/submitting-drivers.rst @@ -8,7 +8,7 @@ various kernel trees. Note that if you are interested in video card drivers you should probably talk to XFree86 (http://www.xfree86.org/) and/or X.Org (http://x.org/) instead. -Also read the Documentation/SubmittingPatches document. +Also read the Documentation/process/submitting-patches.rst document. Allocating Device Numbers @@ -19,7 +19,7 @@ by the Linux assigned name and number authority (currently this is Torben Mathiasen). The site is http://www.lanana.org/. This also deals with allocating numbers for devices that are not going to be submitted to the mainstream kernel. -See Documentation/devices.txt for more information on this. +See Documentation/admin-guide/devices.rst for more information on this. If you don't use assigned numbers then when your device is submitted it will be given an assigned number even if that is different from values you may @@ -73,7 +73,7 @@ Interfaces: Code: Please use the Linux style of code formatting as documented - in :ref:`Documentation/CodingStyle `. + in :ref:`Documentation/process/coding-style.rst `. If you have sections of code that need to be in other formats, for example because they are shared with a windows driver kit and you want to @@ -109,7 +109,7 @@ PM support: anything. For the driver testing instructions see Documentation/power/drivers-testing.txt and for a relatively complete overview of the power management issues related to - drivers see Documentation/power/devices.txt . + drivers see Documentation/power/admin-guide/devices.rst . Control: In general if there is active maintenance of a driver by diff --git a/Documentation/process/submitting-patches.rst b/Documentation/process/submitting-patches.rst index 4cc20b2c6df3..b4cf8f375184 100644 --- a/Documentation/process/submitting-patches.rst +++ b/Documentation/process/submitting-patches.rst @@ -11,10 +11,10 @@ can greatly increase the chances of your change being accepted. This document contains a large number of suggestions in a relatively terse format. For detailed information on how the kernel development process works, see :ref:`Documentation/process `. -Also, read :ref:`Documentation/SubmitChecklist ` +Also, read :ref:`Documentation/process/submit-checklist.rst ` for a list of items to check before submitting code. If you are submitting a driver, also read -:ref:`Documentation/SubmittingDrivers `; +:ref:`Documentation/process/submitting-drivers.rst `; for device tree binding patches, read Documentation/devicetree/bindings/submitting-patches.txt. @@ -238,7 +238,7 @@ then only post say 15 or so at a time and wait for review and integration. Check your patch for basic style violations, details of which can be found in -:ref:`Documentation/CodingStyle `. +:ref:`Documentation/process/coding-style.rst `. Failure to do so simply wastes the reviewers time and will get your patch rejected, probably without even being read. @@ -305,7 +305,7 @@ toward the stable maintainers by putting a line like this:: into the sign-off area of your patch (note, NOT an email recipient). You should also read -:ref:`Documentation/stable_kernel_rules.txt ` +:ref:`Documentation/process/stable-kernel-rules.rst ` in addition to this file. Note, however, that some subsystem maintainers want to come to their own @@ -363,7 +363,7 @@ decreasing the likelihood of your MIME-attached change being accepted. Exception: If your mailer is mangling patches then someone may ask you to re-send them using MIME. -See :ref:`Documentation/email-clients.txt ` +See :ref:`Documentation/process/email-clients.rst ` for hints about configuring your e-mail client so that it sends your patches untouched. @@ -828,8 +828,8 @@ Greg Kroah-Hartman, "How to piss off a kernel subsystem maintainer". NO!!!! No more huge patch bombs to linux-kernel@vger.kernel.org people! -Kernel Documentation/CodingStyle: - :ref:`Documentation/CodingStyle ` +Kernel Documentation/process/coding-style.rst: + :ref:`Documentation/process/coding-style.rst ` Linus Torvalds's mail on the canonical patch format: diff --git a/Documentation/rfkill.txt b/Documentation/rfkill.txt index 1f0c27049340..8c174063b3f0 100644 --- a/Documentation/rfkill.txt +++ b/Documentation/rfkill.txt @@ -26,7 +26,7 @@ whether they can be changed or not: the system software. The rfkill subsystem has two parameters, rfkill.default_state and -rfkill.master_switch_mode, which are documented in kernel-parameters.txt. +rfkill.master_switch_mode, which are documented in admin-guide/kernel-parameters.rst. 2. Implementation details diff --git a/Documentation/scsi/scsi-parameters.txt b/Documentation/scsi/scsi-parameters.txt index 8e66dafa41e1..8477655c0e46 100644 --- a/Documentation/scsi/scsi-parameters.txt +++ b/Documentation/scsi/scsi-parameters.txt @@ -1,7 +1,7 @@ SCSI Kernel Parameters ~~~~~~~~~~~~~~~~~~~~~~ -See Documentation/kernel-parameters.txt for general information on +See Documentation/admin-guide/kernel-parameters.rst for general information on specifying module parameters. This document may not be entirely up to date and comprehensive. The command diff --git a/Documentation/scsi/scsi_mid_low_api.txt b/Documentation/scsi/scsi_mid_low_api.txt index 255075157511..6338400eed73 100644 --- a/Documentation/scsi/scsi_mid_low_api.txt +++ b/Documentation/scsi/scsi_mid_low_api.txt @@ -336,7 +336,7 @@ in parallel by these functions. Conventions =========== First, Linus Torvalds's thoughts on C coding style can be found in the -Documentation/CodingStyle file. +Documentation/process/coding-style.rst file. Next, there is a movement to "outlaw" typedefs introducing synonyms for struct tags. Both can be still found in the SCSI subsystem, but diff --git a/Documentation/scsi/sym53c8xx_2.txt b/Documentation/scsi/sym53c8xx_2.txt index 6af8f7a7770f..d28186553fb0 100644 --- a/Documentation/scsi/sym53c8xx_2.txt +++ b/Documentation/scsi/sym53c8xx_2.txt @@ -427,7 +427,7 @@ Synchronous transfers frequency (default answer: 80) 10.1 Syntax Setup commands can be passed to the driver either at boot time or as -parameters to modprobe, as described in Documentation/kernel-parameters.txt +parameters to modprobe, as described in Documentation/admin-guide/kernel-parameters.rst Example of boot setup command under lilo prompt: diff --git a/Documentation/sound/alsa/alsa-parameters.txt b/Documentation/sound/alsa/alsa-parameters.txt index 0fa40679b080..72eced86f035 100644 --- a/Documentation/sound/alsa/alsa-parameters.txt +++ b/Documentation/sound/alsa/alsa-parameters.txt @@ -1,7 +1,7 @@ ALSA Kernel Parameters ~~~~~~~~~~~~~~~~~~~~~~ -See Documentation/kernel-parameters.txt for general information on +See Documentation/admin-guide/kernel-parameters.rst for general information on specifying module parameters. This document may not be entirely up to date and comprehensive. The command diff --git a/Documentation/sound/oss/oss-parameters.txt b/Documentation/sound/oss/oss-parameters.txt index 3ab391e7c295..cc675f25eee4 100644 --- a/Documentation/sound/oss/oss-parameters.txt +++ b/Documentation/sound/oss/oss-parameters.txt @@ -1,7 +1,7 @@ OSS Kernel Parameters ~~~~~~~~~~~~~~~~~~~~~ -See Documentation/kernel-parameters.txt for general information on +See Documentation/admin-guide/kernel-parameters.rst for general information on specifying module parameters. This document may not be entirely up to date and comprehensive. The command diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index ffab8b5caa60..6bb78f872929 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -71,7 +71,7 @@ show up in /proc/sys/kernel: - printk_ratelimit_burst - pty ==> Documentation/filesystems/devpts.txt - randomize_va_space -- real-root-dev ==> Documentation/initrd.txt +- real-root-dev ==> Documentation/admin-guide/initrd.rst - reboot-cmd [ SPARC only ] - rtsig-max - rtsig-nr @@ -453,7 +453,7 @@ in a KVM virtual machine. This default can be overridden by adding nmi_watchdog=1 -to the guest kernel command line (see Documentation/kernel-parameters.txt). +to the guest kernel command line (see Documentation/admin-guide/kernel-parameters.rst). ============================================================== diff --git a/Documentation/virtual/kvm/review-checklist.txt b/Documentation/virtual/kvm/review-checklist.txt index a850986ed684..a83b27635fdd 100644 --- a/Documentation/virtual/kvm/review-checklist.txt +++ b/Documentation/virtual/kvm/review-checklist.txt @@ -1,8 +1,8 @@ Review checklist for kvm patches ================================ -1. The patch must follow Documentation/CodingStyle and - Documentation/SubmittingPatches. +1. The patch must follow Documentation/process/coding-style.rst and + Documentation/process/submitting-patches.rst. 2. Patches should be against kvm.git master branch. diff --git a/Documentation/vm/numa b/Documentation/vm/numa index e0b58c0e6b49..a08f71647714 100644 --- a/Documentation/vm/numa +++ b/Documentation/vm/numa @@ -82,7 +82,7 @@ such as DMA or DMA32, represent relatively scarce resources. Linux chooses a default zonelist order based on the sizes of the various zone types relative to the total memory of the node and the total memory of the system. The default zonelist order may be overridden using the numa_zonelist_order kernel -boot parameter or sysctl. [see Documentation/kernel-parameters.txt and +boot parameter or sysctl. [see Documentation/admin-guide/kernel-parameters.rst and Documentation/sysctl/vm.txt] By default, Linux will attempt to satisfy memory allocation requests from the diff --git a/Documentation/watchdog/convert_drivers_to_kernel_api.txt b/Documentation/watchdog/convert_drivers_to_kernel_api.txt index 271b8850dde7..9fffb2958d13 100644 --- a/Documentation/watchdog/convert_drivers_to_kernel_api.txt +++ b/Documentation/watchdog/convert_drivers_to_kernel_api.txt @@ -213,6 +213,6 @@ The entry for the driver now needs to select WATCHDOG_CORE: Create a patch and send it to upstream -------------------------------------- -Make sure you understood Documentation/SubmittingPatches and send your patch to +Make sure you understood Documentation/process/submitting-patches.rst and send your patch to linux-watchdog@vger.kernel.org. We are looking forward to it :) diff --git a/Documentation/watchdog/watchdog-parameters.txt b/Documentation/watchdog/watchdog-parameters.txt index a8d364227a77..e21850e270a0 100644 --- a/Documentation/watchdog/watchdog-parameters.txt +++ b/Documentation/watchdog/watchdog-parameters.txt @@ -4,7 +4,7 @@ be listed here unless the driver has its own driver-specific information file. -See Documentation/kernel-parameters.txt for information on +See Documentation/admin-guide/kernel-parameters.rst for information on providing kernel parameters for builtin drivers versus loadable modules. diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt index 9da6f3512249..5e9b826b5f62 100644 --- a/Documentation/x86/boot.txt +++ b/Documentation/x86/boot.txt @@ -921,7 +921,7 @@ They should normally not be deleted from the kernel command line even though not all of them are actually meaningful to the kernel. Boot loader authors who need additional command line options for the boot loader itself should get them registered in -Documentation/kernel-parameters.txt to make sure they will not +Documentation/admin-guide/kernel-parameters.rst to make sure they will not conflict with actual kernel options now or in the future. vga= diff --git a/Documentation/zh_CN/CodingStyle b/Documentation/zh_CN/CodingStyle index 12717791baac..b02738042799 100644 --- a/Documentation/zh_CN/CodingStyle +++ b/Documentation/zh_CN/CodingStyle @@ -1,4 +1,4 @@ -Chinese translated version of Documentation/CodingStyle +Chinese translated version of Documentation/process/coding-style.rst If you have any comment or update to the content, please post to LKML directly. However, if you have problem communicating in English you can also ask the @@ -7,7 +7,7 @@ translation is outdated or there is problem with translation. Chinese maintainer: Zhang Le --------------------------------------------------------------------- -Documentation/CodingStyle的中文翻译 +Documentation/process/coding-style.rst的中文翻译 如果想评论或更新本文的内容，请直接发信到LKML。如果你使用英文交流有困难的话，也可 以向中文版维护者求助。如果本翻译更新不及时或者翻译存在问题，请联系中文版维护者。 @@ -809,5 +809,5 @@ GNU 手册 - 遵循 K&R 标准和此文本 - cpp, gcc, gcc internals and indent, WG14是C语言的国际标准化工作组，URL: http://www.open-std.org/JTC1/SC22/WG14/ -Kernel CodingStyle，作者 greg@kroah.com 发表于OLS 2002： +Kernel process/coding-style.rst，作者 greg@kroah.com 发表于OLS 2002： http://www.kroah.com/linux/talks/ols_2002_kernel_codingstyle_talk/html/ diff --git a/Documentation/zh_CN/HOWTO b/Documentation/zh_CN/HOWTO index f0613b92e0be..11be075ba5fa 100644 --- a/Documentation/zh_CN/HOWTO +++ b/Documentation/zh_CN/HOWTO @@ -1,4 +1,4 @@ -Chinese translated version of Documentation/HOWTO +Chinese translated version of Documentation/process/howto.rst If you have any comment or update to the content, please contact the original document maintainer directly. However, if you have a problem @@ -9,7 +9,7 @@ or if there is a problem with the translation. Maintainer: Greg Kroah-Hartman Chinese maintainer: Li Yang --------------------------------------------------------------------- -Documentation/HOWTO 的中文翻译 +Documentation/process/howto.rst 的中文翻译 如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文 交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻 @@ -93,16 +93,16 @@ Linux内核代码中包含有大量的文档。这些文档对于学习如何与 文件简要介绍了Linux内核的背景，并且描述了如何配置和编译内核。内核的 新用户应该从这里开始。 - Documentation/Changes + Documentation/process/changes.rst 文件给出了用来编译和使用内核所需要的最小软件包列表。 - Documentation/CodingStyle + Documentation/process/coding-style.rst 描述Linux内核的代码风格和理由。所有新代码需要遵守这篇文档中定义的规 范。大多数维护者只会接收符合规定的补丁，很多人也只会帮忙检查符合风格 的代码。 - Documentation/SubmittingPatches - Documentation/SubmittingDrivers + Documentation/process/submitting-patches.rst + Documentation/process/submitting-drivers.rst 这两份文档明确描述如何创建和发送补丁，其中包括（但不仅限于)： - 邮件内容 - 邮件格式 @@ -116,7 +116,7 @@ Linux内核代码中包含有大量的文档。这些文档对于学习如何与 "Linux kernel patch submission format" http://linux.yyz.us/patch-format.html - Documentation/stable_api_nonsense.txt + Documentation/process/stable-api-nonsense.rst 论证内核为什么特意不包括稳定的内核内部API，也就是说不包括像这样的特 性： - 子系统中间层（为了兼容性？） @@ -125,23 +125,23 @@ Linux内核代码中包含有大量的文档。这些文档对于学习如何与 这篇文档对于理解Linux的开发哲学至关重要。对于将开发平台从其他操作系 统转移到Linux的人来说也很重要。 - Documentation/SecurityBugs + Documentation/admin-guide/security-bugs.rst 如果你认为自己发现了Linux内核的安全性问题，请根据这篇文档中的步骤来 提醒其他内核开发者并帮助解决这个问题。 - Documentation/ManagementStyle + Documentation/process/management-style.rst 描述内核维护者的工作方法及其共有特点。这对于刚刚接触内核开发（或者对 它感到好奇）的人来说很重要，因为它解释了很多对于内核维护者独特行为的 普遍误解与迷惑。 - Documentation/stable_kernel_rules.txt + Documentation/process/stable-kernel-rules.rst 解释了稳定版内核发布的规则，以及如何将改动放入这些版本的步骤。 - Documentation/kernel-docs.txt + Documentation/process/kernel-docs.rst 有助于内核开发的外部文档列表。如果你在内核自带的文档中没有找到你想找 的内容，可以查看这些文档。 - Documentation/applying-patches.txt + Documentation/process/applying-patches.rst 关于补丁是什么以及如何将它打在不同内核开发分支上的好介绍 内核还拥有大量从代码自动生成的文档。它包含内核内部API的全面介绍以及如何 @@ -238,7 +238,7 @@ kernel.org网站的pub/linux/kernel/v2.6/目录下找到它。它的开发遵循 2.6.x.y版本由“稳定版”小组（邮件地址）维护，一般隔周发 布新版本。 -内核源码中的Documentation/stable_kernel_rules.txt文件具体描述了可被稳定 +内核源码中的Documentation/process/stable-kernel-rules.rst文件具体描述了可被稳定 版内核接受的修改类型以及发布的流程。 @@ -329,7 +329,7 @@ bugzilla.kernel.org是Linux内核开发者们用来跟踪内核Bug的网站。 户在这个工具中报告找到的所有bug。如何使用内核bugzilla的细节请访问： http://test.kernel.org/bugzilla/faq.html -内核源码主目录中的REPORTING-BUGS文件里有一个很好的模板。它指导用户如何报 +内核源码主目录中的admin-guide/reporting-bugs.rst文件里有一个很好的模板。它指导用户如何报 告可能的内核bug以及需要提供哪些信息来帮助内核开发者们找到问题的根源。 @@ -380,7 +380,7 @@ MAINTAINERS文件中可以找到不同话题对应的邮件列表。 这几行。将你的评论加在被引用的段落之间而不要放在邮件的顶部。 如果你在邮件中附带补丁，请确认它们是可以直接阅读的纯文本（如 -Documentation/SubmittingPatches文档中所述）。内核开发者们不希望遇到附件 +Documentation/process/submitting-patches.rst文档中所述）。内核开发者们不希望遇到附件 或者被压缩了的补丁。只有这样才能保证他们可以直接评论你的每行代码。请确保 你使用的邮件发送程序不会修改空格和制表符。一个防范性的测试方法是先将邮件 发送给自己，然后自己尝试是否可以顺利地打上收到的补丁。如果测试不成功，请 diff --git a/Documentation/zh_CN/SecurityBugs b/Documentation/zh_CN/SecurityBugs index d21eb07fe943..2d0fffd122ce 100644 --- a/Documentation/zh_CN/SecurityBugs +++ b/Documentation/zh_CN/SecurityBugs @@ -1,4 +1,4 @@ -Chinese translated version of Documentation/SecurityBugs +Chinese translated version of Documentation/admin-guide/security-bugs.rst If you have any comment or update to the content, please contact the original document maintainer directly. However, if you have a problem @@ -8,7 +8,7 @@ or if there is a problem with the translation. Chinese maintainer: Harry Wei --------------------------------------------------------------------- -Documentation/SecurityBugs 的中文翻译 +Documentation/admin-guide/security-bugs.rst 的中文翻译 如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文 交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻 @@ -31,7 +31,7 @@ linux内核安全团队可以通过email来联系。这是 一组独立的安全工作人员，可以帮助改善漏洞报告并且公布和取消一个修复。安 全团队有可能会从部分的维护者那里引进额外的帮助来了解并且修复安全漏洞。 当遇到任何漏洞，所能提供的信息越多就越能诊断和修复。如果你不清楚什么 -是有帮助的信息，那就请重温一下REPORTING-BUGS文件中的概述过程。任 +是有帮助的信息，那就请重温一下admin-guide/reporting-bugs.rst文件中的概述过程。任 何攻击性的代码都是非常有用的，未经报告者的同意不会被取消，除非它已经 被公布于众。 diff --git a/Documentation/zh_CN/SubmittingDrivers b/Documentation/zh_CN/SubmittingDrivers index d313f5d8448d..929385e4b194 100644 --- a/Documentation/zh_CN/SubmittingDrivers +++ b/Documentation/zh_CN/SubmittingDrivers @@ -1,4 +1,4 @@ -Chinese translated version of Documentation/SubmittingDrivers +Chinese translated version of Documentation/process/submitting-drivers.rst If you have any comment or update to the content, please contact the original document maintainer directly. However, if you have a problem @@ -8,7 +8,7 @@ or if there is a problem with the translation. Chinese maintainer: Li Yang --------------------------------------------------------------------- -Documentation/SubmittingDrivers 的中文翻译 +Documentation/process/submitting-drivers.rst 的中文翻译 如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文 交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻 @@ -30,7 +30,7 @@ Documentation/SubmittingDrivers 的中文翻译 兴趣的是显卡驱动程序，你也许应该访问 XFree86 项目(http://www.xfree86.org/) 和／或 X.org 项目 (http://x.org)。 -另请参阅 Documentation/SubmittingPatches 文档。 +另请参阅 Documentation/process/submitting-patches.rst 文档。 分配设备号 @@ -39,7 +39,7 @@ Documentation/SubmittingDrivers 的中文翻译 块设备和字符设备的主设备号与从设备号是由 Linux 命名编号分配权威 LANANA（ 现在是 Torben Mathiasen）负责分配。申请的网址是 http://www.lanana.org/。 即使不准备提交到主流内核的设备驱动也需要在这里分配设备号。有关详细信息， -请参阅 Documentation/devices.txt。 +请参阅 Documentation/admin-guide/devices.rst。 如果你使用的不是已经分配的设备号，那么当你提交设备驱动的时候，它将会被强 制分配一个新的设备号，即便这个设备号和你之前发给客户的截然不同。 @@ -81,7 +81,7 @@ Linux 2.6: 如果你需要一个 Linux 和 NT 的通用驱动接口，那么请在用 户空间实现它。 -代码： 请使用 Documentation/CodingStyle 中所描述的 Linux 代码风 +代码： 请使用 Documentation/process/coding-style.rst 中所描述的 Linux 代码风 格。如果你的某些代码段（例如那些与 Windows 驱动程序包共 享的代码段）需要使用其他格式，而你却只希望维护一份代码， 那么请将它们很好地区分出来，并且注明原因。 @@ -107,7 +107,7 @@ Linux 2.6: 程序测试的指导，请参阅 Documentation/power/drivers-testing.txt。有关驱动程序电 源管理问题相对全面的概述，请参阅 - Documentation/power/devices.txt。 + Documentation/power/admin-guide/devices.rst。 管理： 如果一个驱动程序的作者还在进行有效的维护，那么通常除了那 些明显正确且不需要任何检查的补丁以外，其他所有的补丁都会 diff --git a/Documentation/zh_CN/SubmittingPatches b/Documentation/zh_CN/SubmittingPatches index 1d3a10f8746b..e9098da8f1a4 100644 --- a/Documentation/zh_CN/SubmittingPatches +++ b/Documentation/zh_CN/SubmittingPatches @@ -1,4 +1,4 @@ -Chinese translated version of Documentation/SubmittingPatches +Chinese translated version of Documentation/process/submitting-patches.rst If you have any comment or update to the content, please contact the original document maintainer directly. However, if you have a problem @@ -8,7 +8,7 @@ or if there is a problem with the translation. Chinese maintainer: TripleX Chung --------------------------------------------------------------------- -Documentation/SubmittingPatches 的中文翻译 +Documentation/process/submitting-patches.rst 的中文翻译 如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文 交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻 @@ -30,9 +30,9 @@ Documentation/SubmittingPatches 的中文翻译 对于想要将改动提交到 Linux 内核的个人或者公司来说，如果不熟悉“规矩”， 提交的流程会让人畏惧。本文档收集了一系列建议，这些建议可以大大的提高你 的改动被接受的机会。 -阅读 Documentation/SubmitChecklist 来获得在提交代码前需要检查的项目的列 +阅读 Documentation/process/submit-checklist.rst 来获得在提交代码前需要检查的项目的列 表。如果你在提交一个驱动程序，那么同时阅读一下 -Documentation/SubmittingDrivers 。 +Documentation/process/submitting-drivers.rst 。 -------------------------- @@ -338,7 +338,7 @@ e-mail 标题中的“一句话概述”扼要的描述 e-mail 中的补丁。 本节包含很多和提交到内核的代码有关的通常的"规则"。事情永远有例外...但是 你必须真的有好的理由这样做。你可以把本节叫做Linus的计算机科学入门课。 -1) 读 Document/CodingStyle +1) 读 Document/process/coding-style.rst Nuff 说过，如果你的代码和这个偏离太多，那么它有可能会被拒绝，没有更多的 审查，没有更多的评价。 @@ -404,8 +404,8 @@ Greg Kroah-Hartman, "How to piss off a kernel subsystem maintainer". NO!!!! No more huge patch bombs to linux-kernel@vger.kernel.org people! -Kernel Documentation/CodingStyle: - +Kernel Documentation/process/coding-style.rst: + Linus Torvalds's mail on the canonical patch format: diff --git a/Documentation/zh_CN/arm/Booting b/Documentation/zh_CN/arm/Booting index 6158a64df80c..1fe866f8218f 100644 --- a/Documentation/zh_CN/arm/Booting +++ b/Documentation/zh_CN/arm/Booting @@ -68,7 +68,7 @@ RAM，或可能使用对这个设备已知的 RAM 信息，还可能使用任何 作为替代方案，引导加载程序也可以通过标签列表传递相关的'console=' 选项给内核以指定某个串口，而串口数据格式的选项在以下文档中描述： - Documentation/kernel-parameters.txt。 + Documentation/admin-guide/kernel-parameters.rst。 3、检测机器类型 diff --git a/Documentation/zh_CN/email-clients.txt b/Documentation/zh_CN/email-clients.txt index b9a1a3e6c78d..ec31d97e8d0e 100644 --- a/Documentation/zh_CN/email-clients.txt +++ b/Documentation/zh_CN/email-clients.txt @@ -1,4 +1,4 @@ -Chinese translated version of Documentation/email-clients.txt +Chinese translated version of Documentation/process/email-clients.rst If you have any comment or update to the content, please contact the original document maintainer directly. However, if you have a problem @@ -8,7 +8,7 @@ or if there is a problem with the translation. Chinese maintainer: Harry Wei --------------------------------------------------------------------- -Documentation/email-clients.txt 的中文翻译 +Documentation/process/email-clients.rst 的中文翻译 如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文 交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻 diff --git a/Documentation/zh_CN/oops-tracing.txt b/Documentation/zh_CN/oops-tracing.txt index 9312608ffb8d..41ab53cc0e83 100644 --- a/Documentation/zh_CN/oops-tracing.txt +++ b/Documentation/zh_CN/oops-tracing.txt @@ -1,4 +1,4 @@ -Chinese translated version of Documentation/oops-tracing.txt +Chinese translated version of Documentation/admin-guide/oops-tracing.rst If you have any comment or update to the content, please contact the original document maintainer directly. However, if you have a problem @@ -8,7 +8,7 @@ or if there is a problem with the translation. Chinese maintainer: Dave Young --------------------------------------------------------------------- -Documentation/oops-tracing.txt 的中文翻译 +Documentation/admin-guide/oops-tracing.rst 的中文翻译 如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文 交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻 @@ -50,7 +50,7 @@ cat /proc/kmsg > file， 然而你必须介入中止传输， kmsg是一个“ 息滚动到了终端的上面，你会发现以高分辩率启动（比如，vga=791）会让你读到更多的文 本。（注意：这需要vesafb，所以对‘早期’的oops没有帮助） -（2）用串口终端启动（请参看Documentation/serial-console.txt），运行一个null +（2）用串口终端启动（请参看Documentation/admin-guide/serial-console.rst），运行一个null modem到另一台机器并用你喜欢的通讯工具获取输出。Minicom工作地很好。 （3）使用Kdump（请参看Documentation/kdump/kdump.txt）， diff --git a/Documentation/zh_CN/stable_api_nonsense.txt b/Documentation/zh_CN/stable_api_nonsense.txt index c26a27d1ee7d..a2b27fab382c 100644 --- a/Documentation/zh_CN/stable_api_nonsense.txt +++ b/Documentation/zh_CN/stable_api_nonsense.txt @@ -1,4 +1,4 @@ -Chinese translated version of Documentation/stable_api_nonsense.txt +Chinese translated version of Documentation/process/stable-api-nonsense.rst If you have any comment or update to the content, please contact the original document maintainer directly. However, if you have problem @@ -9,7 +9,7 @@ is problem with translation. Maintainer: Greg Kroah-Hartman Chinese maintainer: TripleX Chung --------------------------------------------------------------------- -Documentation/stable_api_nonsense.txt 的中文翻译 +Documentation/process/stable-api-nonsense.rst 的中文翻译 如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文 交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻 diff --git a/Documentation/zh_CN/stable_kernel_rules.txt b/Documentation/zh_CN/stable_kernel_rules.txt index 26ea5ed7cd9c..db4ba5a0c39a 100644 --- a/Documentation/zh_CN/stable_kernel_rules.txt +++ b/Documentation/zh_CN/stable_kernel_rules.txt @@ -1,4 +1,4 @@ -Chinese translated version of Documentation/stable_kernel_rules.txt +Chinese translated version of Documentation/process/stable-kernel-rules.rst If you have any comment or update to the content, please contact the original document maintainer directly. However, if you have a problem @@ -8,7 +8,7 @@ or if there is a problem with the translation. Chinese maintainer: TripleX Chung --------------------------------------------------------------------- -Documentation/stable_kernel_rules.txt 的中文翻译 +Documentation/process/stable-kernel-rules.rst 的中文翻译 如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文 交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻 @@ -38,7 +38,7 @@ Documentation/stable_kernel_rules.txt 的中文翻译 - 没有“理论上的竞争条件”，除非能给出竞争条件如何被利用的解释。 - 不能存在任何的“琐碎的”修正（拼写修正，去掉多余空格之类的）。 - 必须被相关子系统的维护者接受。 - - 必须遵循Documentation/SubmittingPatches里的规则。 + - 必须遵循Documentation/process/submitting-patches.rst里的规则。 向稳定版代码树提交补丁的过程： diff --git a/Documentation/zh_CN/volatile-considered-harmful.txt b/Documentation/zh_CN/volatile-considered-harmful.txt index ba8149d2233a..475125967197 100644 --- a/Documentation/zh_CN/volatile-considered-harmful.txt +++ b/Documentation/zh_CN/volatile-considered-harmful.txt @@ -1,4 +1,4 @@ -Chinese translated version of Documentation/volatile-considered-harmful.txt +Chinese translated version of Documentation/process/volatile-considered-harmful.rst If you have any comment or update to the content, please contact the original document maintainer directly. However, if you have a problem @@ -9,7 +9,7 @@ or if there is a problem with the translation. Maintainer: Jonathan Corbet Chinese maintainer: Bryan Wu --------------------------------------------------------------------- -Documentation/volatile-considered-harmful.txt 的中文翻译 +Documentation/process/volatile-considered-harmful.rst 的中文翻译 如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文 交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻 diff --git a/MAINTAINERS b/MAINTAINERS index de0451df542f..69820b75b2e0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -35,13 +35,13 @@ trivial patch so apply some common sense. PLEASE check your patch with the automated style checker (scripts/checkpatch.pl) to catch trivial style violations. - See Documentation/CodingStyle for guidance here. + See Documentation/process/coding-style.rst for guidance here. PLEASE CC: the maintainers and mailing lists that are generated by scripts/get_maintainer.pl. The results returned by the script will be best if you have git installed and are making your changes in a branch derived from Linus' latest git tree. - See Documentation/SubmittingPatches for details. + See Documentation/process/submitting-patches.rst for details. PLEASE try to include any credit lines you want added with the patch. It avoids people being missed off by mistake and makes @@ -54,7 +54,7 @@ trivial patch so apply some common sense. of the Linux Foundation certificate of contribution and should include a Signed-off-by: line. The current version of this "Developer's Certificate of Origin" (DCO) is listed in the file - Documentation/SubmittingPatches. + Documentation/process/submitting-patches.rst. 6. Make sure you have the right to send any changes you make. If you do changes at work you may find your employer owns the patch @@ -2924,7 +2924,7 @@ CAPELLA MICROSYSTEMS LIGHT SENSOR DRIVER M: Kevin Tsai S: Maintained F: drivers/iio/light/cm* -F: Documentation/devicetree/bindings/i2c/trivial-devices.txt +F: Documentation/devicetree/bindings/i2c/trivial-admin-guide/devices.rst CAVIUM I2C DRIVER M: Jan Glauber @@ -11438,7 +11438,7 @@ STABLE BRANCH M: Greg Kroah-Hartman L: stable@vger.kernel.org S: Supported -F: Documentation/stable_kernel_rules.txt +F: Documentation/process/stable-kernel-rules.rst STAGING SUBSYSTEM M: Greg Kroah-Hartman diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index bada636d1065..19d237b0737d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1525,7 +1525,7 @@ config X86_CHECK_BIOS_CORRUPTION line. By default it scans the low 64k of memory every 60 seconds; see the memory_corruption_check_size and memory_corruption_check_period parameters in - Documentation/kernel-parameters.txt to adjust this. + Documentation/admin-guide/kernel-parameters.rst to adjust this. When enabled with the default parameters, this option has almost no overhead, as it reserves a relatively small amount diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 535e7828445a..c5f9cbe0ae21 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -342,7 +342,7 @@ config ACPI_DEBUG Use the acpi.debug_layer and acpi.debug_level kernel command-line parameters documented in Documentation/acpi/debug.txt and - Documentation/kernel-parameters.txt to control the type and + Documentation/admin-guide/kernel-parameters.rst to control the type and amount of debug output. config ACPI_PCI_SLOT diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 223a770f78f3..59ce0dd50701 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -129,7 +129,7 @@ static int ata_force_tbl_size; static char ata_force_param_buf[PAGE_SIZE] __initdata; /* param_buf is thrown away after initialization, disallow read */ module_param_string(force, ata_force_param_buf, sizeof(ata_force_param_buf), 0); -MODULE_PARM_DESC(force, "Force ATA configurations including cable type, link speed and transfer mode (see Documentation/kernel-parameters.txt for details)"); +MODULE_PARM_DESC(force, "Force ATA configurations including cable type, link speed and transfer mode (see Documentation/admin-guide/kernel-parameters.rst for details)"); static int atapi_enabled = 1; module_param(atapi_enabled, int, 0444); diff --git a/drivers/char/pcmcia/cm4000_cs.c b/drivers/char/pcmcia/cm4000_cs.c index c115217c79ae..e051fc8aa7d7 100644 --- a/drivers/char/pcmcia/cm4000_cs.c +++ b/drivers/char/pcmcia/cm4000_cs.c @@ -14,7 +14,7 @@ * (C) 2000,2001,2002,2003,2004 Omnikey AG * * (C) 2005-2006 Harald Welte - * - Adhere to Kernel CodingStyle + * - Adhere to Kernel process/coding-style.rst * - Port to 2.6.13 "new" style PCMCIA * - Check for copy_{from,to}_user return values * - Use nonseekable_open() @@ -151,7 +151,7 @@ static struct pcmcia_device *dev_table[CM4000_MAX_DEV]; static struct class *cmm_class; /* This table doesn't use spaces after the comma between fields and thus - * violates CodingStyle. However, I don't really think wrapping it around will + * violates process/coding-style.rst. However, I don't really think wrapping it around will * make it any clearer to read -HW */ static unsigned char fi_di_table[10][14] = { /*FI 00 01 02 03 04 05 06 07 08 09 10 11 12 13 */ diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c index db9538d4b358..a7be12d9a139 100644 --- a/drivers/net/can/grcan.c +++ b/drivers/net/can/grcan.c @@ -15,7 +15,7 @@ * See "Documentation/ABI/testing/sysfs-class-net-grcan" for information on the * sysfs interface. * - * See "Documentation/kernel-parameters.txt" for information on the module + * See "Documentation/admin-guide/kernel-parameters.rst" for information on the module * parameters. * * This program is free software; you can redistribute it and/or modify it diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig index 8b2b740d6679..b20ce7da1ee4 100644 --- a/drivers/nvdimm/Kconfig +++ b/drivers/nvdimm/Kconfig @@ -28,7 +28,7 @@ config BLK_DEV_PMEM non-standard OEM-specific E820 memory type (type-12, see CONFIG_X86_PMEM_LEGACY), or it is manually specified by the 'memmap=nn[KMG]!ss[KMG]' kernel command line (see - Documentation/kernel-parameters.txt). This driver converts + Documentation/admin-guide/kernel-parameters.rst). This driver converts these persistent memory ranges into block devices that are capable of DAX (direct-access) file system mappings. See Documentation/nvdimm/nvdimm.txt for more details. diff --git a/drivers/staging/vme/devices/vme_user.c b/drivers/staging/vme/devices/vme_user.c index 5dd430f8f921..d84dffb894f4 100644 --- a/drivers/staging/vme/devices/vme_user.c +++ b/drivers/staging/vme/devices/vme_user.c @@ -47,7 +47,7 @@ static const char driver_name[] = "vme_user"; static int bus[VME_USER_BUS_MAX]; static unsigned int bus_num; -/* Currently Documentation/devices.txt defines the following for VME: +/* Currently Documentation/admin-guide/devices.rst defines the following for VME: * * 221 char VME bus * 0 = /dev/bus/vme/m0 First master image diff --git a/drivers/video/fbdev/skeletonfb.c b/drivers/video/fbdev/skeletonfb.c index f948baa16d82..e219a0a22077 100644 --- a/drivers/video/fbdev/skeletonfb.c +++ b/drivers/video/fbdev/skeletonfb.c @@ -836,7 +836,7 @@ static void xxxfb_remove(struct pci_dev *dev) * @dev: PCI device * @msg: the suspend event code. * - * See Documentation/power/devices.txt for more information + * See Documentation/power/admin-guide/devices.rst for more information */ static int xxxfb_suspend(struct pci_dev *dev, pm_message_t msg) { @@ -851,7 +851,7 @@ static int xxxfb_suspend(struct pci_dev *dev, pm_message_t msg) * xxxfb_resume - Optional but recommended function. Resume the device. * @dev: PCI device * - * See Documentation/power/devices.txt for more information + * See Documentation/power/admin-guide/devices.rst for more information */ static int xxxfb_resume(struct pci_dev *dev) { @@ -915,7 +915,7 @@ static void __exit xxxfb_exit(void) * @dev: platform device * @msg: the suspend event code. * - * See Documentation/power/devices.txt for more information + * See Documentation/power/admin-guide/devices.rst for more information */ static int xxxfb_suspend(struct platform_device *dev, pm_message_t msg) { @@ -930,7 +930,7 @@ static int xxxfb_suspend(struct platform_device *dev, pm_message_t msg) * xxxfb_resume - Optional but recommended function. Resume the device. * @dev: platform device * - * See Documentation/power/devices.txt for more information + * See Documentation/power/admin-guide/devices.rst for more information */ static int xxxfb_resume(struct platform_dev *dev) { diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index 77590320d44c..623f72334fa5 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -75,7 +75,7 @@ config VIRTIO_MMIO_CMDLINE_DEVICES Allow virtio-mmio devices instantiation via the kernel command line or module parameters. Be aware that using incorrect parameters (base address in particular) can crash your system - you have been warned. - See Documentation/kernel-parameters.txt for details. + See Documentation/admin-guide/kernel-parameters.rst for details. If unsure, say 'N'. diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 4c09d93d9569..b2f82cf6bf86 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -170,8 +170,8 @@ config BINFMT_MISC You can do other nice things, too. Read the file to learn how to use this - feature, for information about how - to include Java support. and for + feature, for information about how + to include Java support. and for information about how to include Mono-based .NET support. To use binfmt_misc, you will need to mount it: diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig index be40813eff52..b42e5bd6d8ff 100644 --- a/fs/pstore/Kconfig +++ b/fs/pstore/Kconfig @@ -86,4 +86,4 @@ config PSTORE_RAM Note that for historical reasons, the module will be named "ramoops.ko". - For more information, see Documentation/ramoops.txt. + For more information, see Documentation/admin-guide/ramoops.rst. diff --git a/include/linux/device.h b/include/linux/device.h index bc41e87a969b..36d3a9867da9 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -733,7 +733,7 @@ struct device_dma_parameters { * minimizes board-specific #ifdefs in drivers. * @driver_data: Private pointer for driver specific info. * @power: For device power management. - * See Documentation/power/devices.txt for details. + * See Documentation/power/admin-guide/devices.rst for details. * @pm_domain: Provide callbacks that are executed during system suspend, * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. diff --git a/include/linux/pm.h b/include/linux/pm.h index 06eb353182ab..efa67b2dfee9 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -258,7 +258,7 @@ typedef struct pm_message { * example, if it detects that a child was unplugged while the system was * asleep). * - * Refer to Documentation/power/devices.txt for more information about the role + * Refer to Documentation/power/admin-guide/devices.rst for more information about the role * of the above callbacks in the system suspend process. * * There also are callbacks related to runtime power management of devices. diff --git a/include/uapi/linux/major.h b/include/uapi/linux/major.h index 620252e69b44..19e195bee990 100644 --- a/include/uapi/linux/major.h +++ b/include/uapi/linux/major.h @@ -3,7 +3,7 @@ /* * This file has definitions for major device numbers. - * For the device number assignments, see Documentation/devices.txt. + * For the device number assignments, see Documentation/admin-guide/devices.rst. */ #define UNNAMED_MAJOR 0 diff --git a/init/Kconfig b/init/Kconfig index 34407f15e6d3..172f80ea0d58 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1306,7 +1306,7 @@ config BLK_DEV_INITRD boot loader (loadlin or lilo) and that is mounted as root before the normal boot procedure. It is typically used to load modules needed to mount the "real" root file system, - etc. See for details. + etc. See for details. If RAM disk support (BLK_DEV_RAM) is also included, this also enables initial RAM disk (initrd) support and adds diff --git a/init/main.c b/init/main.c index 2858be732f6d..691eb9351a83 100644 --- a/init/main.c +++ b/init/main.c @@ -980,7 +980,7 @@ static int __ref kernel_init(void *unused) return 0; panic("No working init found. Try passing init= option to kernel. " - "See Linux Documentation/init.txt for guidance."); + "See Linux Documentation/admin-guide/init.rst for guidance."); } static noinline void __init kernel_init_freeable(void) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 33bc56cf60d7..d2df3a93284b 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -13,7 +13,7 @@ config PRINTK_TIME be included, not that the timestamp is recorded. The behavior is also controlled by the kernel command line - parameter printk.time=1. See Documentation/kernel-parameters.txt + parameter printk.time=1. See Documentation/admin-guide/kernel-parameters.rst config MESSAGE_LOGLEVEL_DEFAULT int "Default message log level (1-7)" diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index a8368d1c4348..d0c729ccec20 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -2187,7 +2187,7 @@ sub process { if ($rawline=~/^\+\+\+\s+(\S+)/) { $setup_docs = 0; - if ($1 =~ m@Documentation/kernel-parameters.txt$@) { + if ($1 =~ m@Documentation/admin-guide/kernel-parameters.rst$@) { $setup_docs = 1; } #next; @@ -5102,7 +5102,7 @@ sub process { my $asm_volatile = qr{\b(__asm__|asm)\s+(__volatile__|volatile)\b}; if ($line =~ /\bvolatile\b/ && $line !~ /$asm_volatile/) { WARN("VOLATILE", - "Use of volatile is usually wrong: see Documentation/volatile-considered-harmful.txt\n" . $herecurr); + "Use of volatile is usually wrong: see Documentation/process/volatile-considered-harmful.rst\n" . $herecurr); } # Check for user-visible strings broken across lines, which breaks the ability @@ -5817,7 +5817,7 @@ sub process { if (!grep(/$name/, @setup_docs)) { CHK("UNDOCUMENTED_SETUP", - "__setup appears un-documented -- check Documentation/kernel-parameters.txt\n" . $herecurr); + "__setup appears un-documented -- check Documentation/admin-guide/kernel-parameters.rst\n" . $herecurr); } } diff --git a/tools/testing/selftests/futex/README b/tools/testing/selftests/futex/README index 0558bb9ce0a6..f3926c33ed4c 100644 --- a/tools/testing/selftests/futex/README +++ b/tools/testing/selftests/futex/README @@ -59,4 +59,4 @@ o FIXME: decide on a sane test naming scheme. Currently the tests are named Coding Style ------------ o The Futex Test project adheres to the coding standards set forth by Linux - kernel as defined in the Linux source Documentation/CodingStyle. + kernel as defined in the Linux source Documentation/process/coding-style.rst. -- cgit v1.2.3 From 2ebda74fd6c9d3fc3b9f0234fc519795e23025a5 Mon Sep 17 00:00:00 2001 From: Giovanni Cabiddu Date: Fri, 21 Oct 2016 13:19:47 +0100 Subject: crypto: acomp - add asynchronous compression api Add acomp, an asynchronous compression api that uses scatterlist buffers. Signed-off-by: Giovanni Cabiddu Signed-off-by: Herbert Xu --- crypto/Kconfig | 10 ++ crypto/Makefile | 2 + crypto/acompress.c | 118 +++++++++++++++ crypto/crypto_user.c | 19 +++ include/crypto/acompress.h | 281 ++++++++++++++++++++++++++++++++++++ include/crypto/internal/acompress.h | 66 +++++++++ include/linux/crypto.h | 1 + include/uapi/linux/cryptouser.h | 5 + 8 files changed, 502 insertions(+) create mode 100644 crypto/acompress.c create mode 100644 include/crypto/acompress.h create mode 100644 include/crypto/internal/acompress.h (limited to 'include/uapi/linux') diff --git a/crypto/Kconfig b/crypto/Kconfig index fd288053b1c5..9950c47c9d27 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -102,6 +102,15 @@ config CRYPTO_KPP select CRYPTO_ALGAPI select CRYPTO_KPP2 +config CRYPTO_ACOMP2 + tristate + select CRYPTO_ALGAPI2 + +config CRYPTO_ACOMP + tristate + select CRYPTO_ALGAPI + select CRYPTO_ACOMP2 + config CRYPTO_RSA tristate "RSA algorithm" select CRYPTO_AKCIPHER @@ -138,6 +147,7 @@ config CRYPTO_MANAGER2 select CRYPTO_BLKCIPHER2 select CRYPTO_AKCIPHER2 select CRYPTO_KPP2 + select CRYPTO_ACOMP2 config CRYPTO_USER tristate "Userspace cryptographic algorithm configuration" diff --git a/crypto/Makefile b/crypto/Makefile index 99cc64ac70ef..0933dc6bd24c 100644 --- a/crypto/Makefile +++ b/crypto/Makefile @@ -50,6 +50,8 @@ rsa_generic-y += rsa_helper.o rsa_generic-y += rsa-pkcs1pad.o obj-$(CONFIG_CRYPTO_RSA) += rsa_generic.o +obj-$(CONFIG_CRYPTO_ACOMP2) += acompress.o + cryptomgr-y := algboss.o testmgr.o obj-$(CONFIG_CRYPTO_MANAGER2) += cryptomgr.o diff --git a/crypto/acompress.c b/crypto/acompress.c new file mode 100644 index 000000000000..4977279476d3 --- /dev/null +++ b/crypto/acompress.c @@ -0,0 +1,118 @@ +/* + * Asynchronous Compression operations + * + * Copyright (c) 2016, Intel Corporation + * Authors: Weigang Li + * Giovanni Cabiddu + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" + +#ifdef CONFIG_NET +static int crypto_acomp_report(struct sk_buff *skb, struct crypto_alg *alg) +{ + struct crypto_report_acomp racomp; + + strncpy(racomp.type, "acomp", sizeof(racomp.type)); + + if (nla_put(skb, CRYPTOCFGA_REPORT_ACOMP, + sizeof(struct crypto_report_acomp), &racomp)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} +#else +static int crypto_acomp_report(struct sk_buff *skb, struct crypto_alg *alg) +{ + return -ENOSYS; +} +#endif + +static void crypto_acomp_show(struct seq_file *m, struct crypto_alg *alg) + __attribute__ ((unused)); + +static void crypto_acomp_show(struct seq_file *m, struct crypto_alg *alg) +{ + seq_puts(m, "type : acomp\n"); +} + +static void crypto_acomp_exit_tfm(struct crypto_tfm *tfm) +{ + struct crypto_acomp *acomp = __crypto_acomp_tfm(tfm); + struct acomp_alg *alg = crypto_acomp_alg(acomp); + + alg->exit(acomp); +} + +static int crypto_acomp_init_tfm(struct crypto_tfm *tfm) +{ + struct crypto_acomp *acomp = __crypto_acomp_tfm(tfm); + struct acomp_alg *alg = crypto_acomp_alg(acomp); + + if (alg->exit) + acomp->base.exit = crypto_acomp_exit_tfm; + + if (alg->init) + return alg->init(acomp); + + return 0; +} + +static const struct crypto_type crypto_acomp_type = { + .extsize = crypto_alg_extsize, + .init_tfm = crypto_acomp_init_tfm, +#ifdef CONFIG_PROC_FS + .show = crypto_acomp_show, +#endif + .report = crypto_acomp_report, + .maskclear = ~CRYPTO_ALG_TYPE_MASK, + .maskset = CRYPTO_ALG_TYPE_MASK, + .type = CRYPTO_ALG_TYPE_ACOMPRESS, + .tfmsize = offsetof(struct crypto_acomp, base), +}; + +struct crypto_acomp *crypto_alloc_acomp(const char *alg_name, u32 type, + u32 mask) +{ + return crypto_alloc_tfm(alg_name, &crypto_acomp_type, type, mask); +} +EXPORT_SYMBOL_GPL(crypto_alloc_acomp); + +int crypto_register_acomp(struct acomp_alg *alg) +{ + struct crypto_alg *base = &alg->base; + + base->cra_type = &crypto_acomp_type; + base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK; + base->cra_flags |= CRYPTO_ALG_TYPE_ACOMPRESS; + + return crypto_register_alg(base); +} +EXPORT_SYMBOL_GPL(crypto_register_acomp); + +int crypto_unregister_acomp(struct acomp_alg *alg) +{ + return crypto_unregister_alg(&alg->base); +} +EXPORT_SYMBOL_GPL(crypto_unregister_acomp); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Asynchronous compression type"); diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c index 1c5705481c69..a90404a0c5ff 100644 --- a/crypto/crypto_user.c +++ b/crypto/crypto_user.c @@ -112,6 +112,21 @@ nla_put_failure: return -EMSGSIZE; } +static int crypto_report_acomp(struct sk_buff *skb, struct crypto_alg *alg) +{ + struct crypto_report_acomp racomp; + + strncpy(racomp.type, "acomp", sizeof(racomp.type)); + + if (nla_put(skb, CRYPTOCFGA_REPORT_ACOMP, + sizeof(struct crypto_report_acomp), &racomp)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + static int crypto_report_akcipher(struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_akcipher rakcipher; @@ -186,7 +201,11 @@ static int crypto_report_one(struct crypto_alg *alg, goto nla_put_failure; break; + case CRYPTO_ALG_TYPE_ACOMPRESS: + if (crypto_report_acomp(skb, alg)) + goto nla_put_failure; + break; case CRYPTO_ALG_TYPE_AKCIPHER: if (crypto_report_akcipher(skb, alg)) goto nla_put_failure; diff --git a/include/crypto/acompress.h b/include/crypto/acompress.h new file mode 100644 index 000000000000..14c70d887160 --- /dev/null +++ b/include/crypto/acompress.h @@ -0,0 +1,281 @@ +/* + * Asynchronous Compression operations + * + * Copyright (c) 2016, Intel Corporation + * Authors: Weigang Li + * Giovanni Cabiddu + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ +#ifndef _CRYPTO_ACOMP_H +#define _CRYPTO_ACOMP_H +#include + +#define CRYPTO_ACOMP_ALLOC_OUTPUT 0x00000001 + +/** + * struct acomp_req - asynchronous (de)compression request + * + * @base: Common attributes for asynchronous crypto requests + * @src: Source Data + * @dst: Destination data + * @slen: Size of the input buffer + * @dlen: Size of the output buffer and number of bytes produced + * @flags: Internal flags + * @__ctx: Start of private context data + */ +struct acomp_req { + struct crypto_async_request base; + struct scatterlist *src; + struct scatterlist *dst; + unsigned int slen; + unsigned int dlen; + u32 flags; + void *__ctx[] CRYPTO_MINALIGN_ATTR; +}; + +/** + * struct crypto_acomp - user-instantiated objects which encapsulate + * algorithms and core processing logic + * + * @base: Common crypto API algorithm data structure + */ +struct crypto_acomp { + struct crypto_tfm base; +}; + +/** + * struct acomp_alg - asynchronous compression algorithm + * + * @compress: Function performs a compress operation + * @decompress: Function performs a de-compress operation + * @dst_free: Frees destination buffer if allocated inside the algorithm + * @init: Initialize the cryptographic transformation object. + * This function is used to initialize the cryptographic + * transformation object. This function is called only once at + * the instantiation time, right after the transformation context + * was allocated. In case the cryptographic hardware has some + * special requirements which need to be handled by software, this + * function shall check for the precise requirement of the + * transformation and put any software fallbacks in place. + * @exit: Deinitialize the cryptographic transformation object. This is a + * counterpart to @init, used to remove various changes set in + * @init. + * + * @reqsize: Context size for (de)compression requests + * @base: Common crypto API algorithm data structure + */ +struct acomp_alg { + int (*compress)(struct acomp_req *req); + int (*decompress)(struct acomp_req *req); + void (*dst_free)(struct scatterlist *dst); + int (*init)(struct crypto_acomp *tfm); + void (*exit)(struct crypto_acomp *tfm); + unsigned int reqsize; + struct crypto_alg base; +}; + +/** + * DOC: Asynchronous Compression API + * + * The Asynchronous Compression API is used with the algorithms of type + * CRYPTO_ALG_TYPE_ACOMPRESS (listed as type "acomp" in /proc/crypto) + */ + +/** + * crypto_alloc_acomp() -- allocate ACOMPRESS tfm handle + * @alg_name: is the cra_name / name or cra_driver_name / driver name of the + * compression algorithm e.g. "deflate" + * @type: specifies the type of the algorithm + * @mask: specifies the mask for the algorithm + * + * Allocate a handle for a compression algorithm. The returned struct + * crypto_acomp is the handle that is required for any subsequent + * API invocation for the compression operations. + * + * Return: allocated handle in case of success; IS_ERR() is true in case + * of an error, PTR_ERR() returns the error code. + */ +struct crypto_acomp *crypto_alloc_acomp(const char *alg_name, u32 type, + u32 mask); + +static inline struct crypto_tfm *crypto_acomp_tfm(struct crypto_acomp *tfm) +{ + return &tfm->base; +} + +static inline struct acomp_alg *__crypto_acomp_alg(struct crypto_alg *alg) +{ + return container_of(alg, struct acomp_alg, base); +} + +static inline struct crypto_acomp *__crypto_acomp_tfm(struct crypto_tfm *tfm) +{ + return container_of(tfm, struct crypto_acomp, base); +} + +static inline struct acomp_alg *crypto_acomp_alg(struct crypto_acomp *tfm) +{ + return __crypto_acomp_alg(crypto_acomp_tfm(tfm)->__crt_alg); +} + +static inline unsigned int crypto_acomp_reqsize(struct crypto_acomp *tfm) +{ + return crypto_acomp_alg(tfm)->reqsize; +} + +static inline void acomp_request_set_tfm(struct acomp_req *req, + struct crypto_acomp *tfm) +{ + req->base.tfm = crypto_acomp_tfm(tfm); +} + +static inline struct crypto_acomp *crypto_acomp_reqtfm(struct acomp_req *req) +{ + return __crypto_acomp_tfm(req->base.tfm); +} + +/** + * crypto_free_acomp() -- free ACOMPRESS tfm handle + * + * @tfm: ACOMPRESS tfm handle allocated with crypto_alloc_acomp() + */ +static inline void crypto_free_acomp(struct crypto_acomp *tfm) +{ + crypto_destroy_tfm(tfm, crypto_acomp_tfm(tfm)); +} + +static inline int crypto_has_acomp(const char *alg_name, u32 type, u32 mask) +{ + type &= ~CRYPTO_ALG_TYPE_MASK; + type |= CRYPTO_ALG_TYPE_ACOMPRESS; + mask |= CRYPTO_ALG_TYPE_MASK; + + return crypto_has_alg(alg_name, type, mask); +} + +/** + * acomp_request_alloc() -- allocates asynchronous (de)compression request + * + * @tfm: ACOMPRESS tfm handle allocated with crypto_alloc_acomp() + * + * Return: allocated handle in case of success or NULL in case of an error + */ +static inline struct acomp_req *acomp_request_alloc(struct crypto_acomp *tfm) +{ + struct acomp_req *req; + + req = kzalloc(sizeof(*req) + crypto_acomp_reqsize(tfm), GFP_KERNEL); + if (likely(req)) + acomp_request_set_tfm(req, tfm); + + return req; +} + +/** + * acomp_request_free() -- zeroize and free asynchronous (de)compression + * request as well as the output buffer if allocated + * inside the algorithm + * + * @req: request to free + */ +static inline void acomp_request_free(struct acomp_req *req) +{ + struct crypto_acomp *tfm = crypto_acomp_reqtfm(req); + struct acomp_alg *alg = crypto_acomp_alg(tfm); + + if (req->flags & CRYPTO_ACOMP_ALLOC_OUTPUT) { + alg->dst_free(req->dst); + req->dst = NULL; + } + kzfree(req); +} + +/** + * acomp_request_set_callback() -- Sets an asynchronous callback + * + * Callback will be called when an asynchronous operation on a given + * request is finished. + * + * @req: request that the callback will be set for + * @flgs: specify for instance if the operation may backlog + * @cmlp: callback which will be called + * @data: private data used by the caller + */ +static inline void acomp_request_set_callback(struct acomp_req *req, + u32 flgs, + crypto_completion_t cmpl, + void *data) +{ + req->base.complete = cmpl; + req->base.data = data; + req->base.flags = flgs; +} + +/** + * acomp_request_set_params() -- Sets request parameters + * + * Sets parameters required by an acomp operation + * + * @req: asynchronous compress request + * @src: pointer to input buffer scatterlist + * @dst: pointer to output buffer scatterlist. If this is NULL, the + * acomp layer will allocate the output memory + * @slen: size of the input buffer + * @dlen: size of the output buffer. If dst is NULL, this can be used by + * the user to specify the maximum amount of memory to allocate + */ +static inline void acomp_request_set_params(struct acomp_req *req, + struct scatterlist *src, + struct scatterlist *dst, + unsigned int slen, + unsigned int dlen) +{ + req->src = src; + req->dst = dst; + req->slen = slen; + req->dlen = dlen; + + if (!req->dst) + req->flags |= CRYPTO_ACOMP_ALLOC_OUTPUT; +} + +/** + * crypto_acomp_compress() -- Invoke asynchronous compress operation + * + * Function invokes the asynchronous compress operation + * + * @req: asynchronous compress request + * + * Return: zero on success; error code in case of error + */ +static inline int crypto_acomp_compress(struct acomp_req *req) +{ + struct crypto_acomp *tfm = crypto_acomp_reqtfm(req); + struct acomp_alg *alg = crypto_acomp_alg(tfm); + + return alg->compress(req); +} + +/** + * crypto_acomp_decompress() -- Invoke asynchronous decompress operation + * + * Function invokes the asynchronous decompress operation + * + * @req: asynchronous compress request + * + * Return: zero on success; error code in case of error + */ +static inline int crypto_acomp_decompress(struct acomp_req *req) +{ + struct crypto_acomp *tfm = crypto_acomp_reqtfm(req); + struct acomp_alg *alg = crypto_acomp_alg(tfm); + + return alg->decompress(req); +} + +#endif diff --git a/include/crypto/internal/acompress.h b/include/crypto/internal/acompress.h new file mode 100644 index 000000000000..a9a9000d1aea --- /dev/null +++ b/include/crypto/internal/acompress.h @@ -0,0 +1,66 @@ +/* + * Asynchronous Compression operations + * + * Copyright (c) 2016, Intel Corporation + * Authors: Weigang Li + * Giovanni Cabiddu + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ +#ifndef _CRYPTO_ACOMP_INT_H +#define _CRYPTO_ACOMP_INT_H +#include + +/* + * Transform internal helpers. + */ +static inline void *acomp_request_ctx(struct acomp_req *req) +{ + return req->__ctx; +} + +static inline void *acomp_tfm_ctx(struct crypto_acomp *tfm) +{ + return tfm->base.__crt_ctx; +} + +static inline void acomp_request_complete(struct acomp_req *req, + int err) +{ + req->base.complete(&req->base, err); +} + +static inline const char *acomp_alg_name(struct crypto_acomp *tfm) +{ + return crypto_acomp_tfm(tfm)->__crt_alg->cra_name; +} + +/** + * crypto_register_acomp() -- Register asynchronous compression algorithm + * + * Function registers an implementation of an asynchronous + * compression algorithm + * + * @alg: algorithm definition + * + * Return: zero on success; error code in case of error + */ +int crypto_register_acomp(struct acomp_alg *alg); + +/** + * crypto_unregister_acomp() -- Unregister asynchronous compression algorithm + * + * Function unregisters an implementation of an asynchronous + * compression algorithm + * + * @alg: algorithm definition + * + * Return: zero on success; error code in case of error + */ +int crypto_unregister_acomp(struct acomp_alg *alg); + +#endif diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 7cee5551625b..dc57a0505505 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -50,6 +50,7 @@ #define CRYPTO_ALG_TYPE_SKCIPHER 0x00000005 #define CRYPTO_ALG_TYPE_GIVCIPHER 0x00000006 #define CRYPTO_ALG_TYPE_KPP 0x00000008 +#define CRYPTO_ALG_TYPE_ACOMPRESS 0x0000000a #define CRYPTO_ALG_TYPE_RNG 0x0000000c #define CRYPTO_ALG_TYPE_AKCIPHER 0x0000000d #define CRYPTO_ALG_TYPE_DIGEST 0x0000000e diff --git a/include/uapi/linux/cryptouser.h b/include/uapi/linux/cryptouser.h index 79b5ded2001a..11d21fce14d6 100644 --- a/include/uapi/linux/cryptouser.h +++ b/include/uapi/linux/cryptouser.h @@ -46,6 +46,7 @@ enum crypto_attr_type_t { CRYPTOCFGA_REPORT_CIPHER, /* struct crypto_report_cipher */ CRYPTOCFGA_REPORT_AKCIPHER, /* struct crypto_report_akcipher */ CRYPTOCFGA_REPORT_KPP, /* struct crypto_report_kpp */ + CRYPTOCFGA_REPORT_ACOMP, /* struct crypto_report_acomp */ __CRYPTOCFGA_MAX #define CRYPTOCFGA_MAX (__CRYPTOCFGA_MAX - 1) @@ -112,5 +113,9 @@ struct crypto_report_kpp { char type[CRYPTO_MAX_NAME]; }; +struct crypto_report_acomp { + char type[CRYPTO_MAX_NAME]; +}; + #define CRYPTO_REPORT_MAXSIZE (sizeof(struct crypto_user_alg) + \ sizeof(struct crypto_report_blkcipher)) -- 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/net/cfg80211.h | 12 +++++++----- include/uapi/linux/nl80211.h | 15 ++++++++++++--- net/mac80211/mlme.c | 12 ++++++------ net/wireless/core.h | 2 +- net/wireless/mlme.c | 6 +++--- net/wireless/nl80211.c | 18 +++++++++--------- 6 files changed, 38 insertions(+), 27 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index d1ffbc3a8e55..dffc265a4fd6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1785,9 +1785,11 @@ const u8 *ieee80211_bss_get_ie(struct cfg80211_bss *bss, u8 ie); * @key_len: length of WEP key for shared key authentication * @key_idx: index of WEP key for shared key authentication * @key: WEP key for shared key authentication - * @sae_data: Non-IE data to use with SAE or %NULL. This starts with - * Authentication transaction sequence number field. - * @sae_data_len: Length of sae_data buffer in octets + * @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. + * @auth_data_len: Length of auth_data buffer in octets */ struct cfg80211_auth_request { struct cfg80211_bss *bss; @@ -1796,8 +1798,8 @@ struct cfg80211_auth_request { enum nl80211_auth_type auth_type; const u8 *key; u8 key_len, key_idx; - const u8 *sae_data; - size_t sae_data_len; + const u8 *auth_data; + size_t auth_data_len; }; /** 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 diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index c8d3a9b02fb6..32fd29581d4d 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4483,20 +4483,20 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, return -EOPNOTSUPP; } - auth_data = kzalloc(sizeof(*auth_data) + req->sae_data_len + + auth_data = kzalloc(sizeof(*auth_data) + req->auth_data_len + req->ie_len, GFP_KERNEL); if (!auth_data) return -ENOMEM; auth_data->bss = req->bss; - if (req->sae_data_len >= 4) { - __le16 *pos = (__le16 *) req->sae_data; + if (req->auth_data_len >= 4) { + __le16 *pos = (__le16 *) req->auth_data; auth_data->sae_trans = le16_to_cpu(pos[0]); auth_data->sae_status = le16_to_cpu(pos[1]); - memcpy(auth_data->data, req->sae_data + 4, - req->sae_data_len - 4); - auth_data->data_len += req->sae_data_len - 4; + memcpy(auth_data->data, req->auth_data + 4, + req->auth_data_len - 4); + auth_data->data_len += req->auth_data_len - 4; } if (req->ie && req->ie_len) { diff --git a/net/wireless/core.h b/net/wireless/core.h index 21e31888cfa9..fb2fcd5581fe 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -345,7 +345,7 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, const u8 *ssid, int ssid_len, const u8 *ie, int ie_len, const u8 *key, int key_len, int key_idx, - const u8 *sae_data, int sae_data_len); + const u8 *auth_data, int auth_data_len); int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, struct net_device *dev, struct ieee80211_channel *chan, diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index cbb48e26a871..bd1f7a159d6a 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -204,14 +204,14 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, const u8 *ssid, int ssid_len, const u8 *ie, int ie_len, const u8 *key, int key_len, int key_idx, - const u8 *sae_data, int sae_data_len) + const u8 *auth_data, int auth_data_len) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_auth_request req = { .ie = ie, .ie_len = ie_len, - .sae_data = sae_data, - .sae_data_len = sae_data_len, + .auth_data = auth_data, + .auth_data_len = auth_data_len, .auth_type = auth_type, .key = key, .key_len = key_len, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 7e746c90156e..704851142eed 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -357,7 +357,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_BG_SCAN_PERIOD] = { .type = NLA_U16 }, [NL80211_ATTR_WDEV] = { .type = NLA_U64 }, [NL80211_ATTR_USER_REG_HINT_TYPE] = { .type = NLA_U32 }, - [NL80211_ATTR_SAE_DATA] = { .type = NLA_BINARY, }, + [NL80211_ATTR_AUTH_DATA] = { .type = NLA_BINARY, }, [NL80211_ATTR_VHT_CAPABILITY] = { .len = NL80211_VHT_CAPABILITY_LEN }, [NL80211_ATTR_SCAN_FLAGS] = { .type = NLA_U32 }, [NL80211_ATTR_P2P_CTWINDOW] = { .type = NLA_U8 }, @@ -7729,8 +7729,8 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct ieee80211_channel *chan; - const u8 *bssid, *ssid, *ie = NULL, *sae_data = NULL; - int err, ssid_len, ie_len = 0, sae_data_len = 0; + const u8 *bssid, *ssid, *ie = NULL, *auth_data = NULL; + int err, ssid_len, ie_len = 0, auth_data_len = 0; enum nl80211_auth_type auth_type; struct key_parse key; bool local_state_change; @@ -7811,16 +7811,16 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) return -EINVAL; if (auth_type == NL80211_AUTHTYPE_SAE && - !info->attrs[NL80211_ATTR_SAE_DATA]) + !info->attrs[NL80211_ATTR_AUTH_DATA]) return -EINVAL; - if (info->attrs[NL80211_ATTR_SAE_DATA]) { + if (info->attrs[NL80211_ATTR_AUTH_DATA]) { if (auth_type != NL80211_AUTHTYPE_SAE) return -EINVAL; - sae_data = nla_data(info->attrs[NL80211_ATTR_SAE_DATA]); - sae_data_len = nla_len(info->attrs[NL80211_ATTR_SAE_DATA]); + auth_data = nla_data(info->attrs[NL80211_ATTR_AUTH_DATA]); + auth_data_len = nla_len(info->attrs[NL80211_ATTR_AUTH_DATA]); /* need to include at least Auth Transaction and Status Code */ - if (sae_data_len < 4) + if (auth_data_len < 4) return -EINVAL; } @@ -7837,7 +7837,7 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) err = cfg80211_mlme_auth(rdev, dev, chan, auth_type, bssid, ssid, ssid_len, ie, ie_len, key.p.key, key.p.key_len, key.idx, - sae_data, sae_data_len); + auth_data, auth_data_len); wdev_unlock(dev->ieee80211_ptr); return err; } -- 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/linux/ieee80211.h | 3 +++ include/uapi/linux/nl80211.h | 6 ++++++ net/wireless/nl80211.c | 21 +++++++++++++++++++-- 3 files changed, 28 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index d428adf51446..793a0174ba29 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1576,6 +1576,9 @@ struct ieee80211_vht_operation { #define WLAN_AUTH_SHARED_KEY 1 #define WLAN_AUTH_FT 2 #define WLAN_AUTH_SAE 3 +#define WLAN_AUTH_FILS_SK 4 +#define WLAN_AUTH_FILS_SK_PFS 5 +#define WLAN_AUTH_FILS_PK 6 #define WLAN_AUTH_LEAP 128 #define WLAN_AUTH_CHALLENGE_LEN 128 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, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 704851142eed..ff798620e929 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3778,12 +3778,23 @@ static bool nl80211_valid_auth_type(struct cfg80211_registered_device *rdev, if (!(rdev->wiphy.features & NL80211_FEATURE_SAE) && auth_type == NL80211_AUTHTYPE_SAE) return false; + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_FILS_STA) && + (auth_type == NL80211_AUTHTYPE_FILS_SK || + auth_type == NL80211_AUTHTYPE_FILS_SK_PFS || + auth_type == NL80211_AUTHTYPE_FILS_PK)) + return false; return true; case NL80211_CMD_CONNECT: case NL80211_CMD_START_AP: /* SAE not supported yet */ if (auth_type == NL80211_AUTHTYPE_SAE) return false; + /* FILS not supported yet */ + if (auth_type == NL80211_AUTHTYPE_FILS_SK || + auth_type == NL80211_AUTHTYPE_FILS_SK_PFS || + auth_type == NL80211_AUTHTYPE_FILS_PK) + return false; return true; default: return false; @@ -7810,12 +7821,18 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) if (!nl80211_valid_auth_type(rdev, auth_type, NL80211_CMD_AUTHENTICATE)) return -EINVAL; - if (auth_type == NL80211_AUTHTYPE_SAE && + if ((auth_type == NL80211_AUTHTYPE_SAE || + auth_type == NL80211_AUTHTYPE_FILS_SK || + auth_type == NL80211_AUTHTYPE_FILS_SK_PFS || + auth_type == NL80211_AUTHTYPE_FILS_PK) && !info->attrs[NL80211_ATTR_AUTH_DATA]) return -EINVAL; if (info->attrs[NL80211_ATTR_AUTH_DATA]) { - if (auth_type != NL80211_AUTHTYPE_SAE) + if (auth_type != NL80211_AUTHTYPE_SAE && + auth_type != NL80211_AUTHTYPE_FILS_SK && + auth_type != NL80211_AUTHTYPE_FILS_SK_PFS && + auth_type != NL80211_AUTHTYPE_FILS_PK) return -EINVAL; auth_data = nla_data(info->attrs[NL80211_ATTR_AUTH_DATA]); auth_data_len = nla_len(info->attrs[NL80211_ATTR_AUTH_DATA]); -- 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/linux/ieee80211.h | 3 +++ include/net/cfg80211.h | 9 +++++++++ include/uapi/linux/nl80211.h | 8 ++++++++ net/wireless/nl80211.c | 12 ++++++++++++ 4 files changed, 32 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 793a0174ba29..fe849329511a 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2096,6 +2096,9 @@ enum ieee80211_key_len { #define IEEE80211_GCMP_MIC_LEN 16 #define IEEE80211_GCMP_PN_LEN 6 +#define FILS_NONCE_LEN 16 +#define FILS_MAX_KEK_LEN 64 + /* Public action codes */ enum ieee80211_pub_actioncode { WLAN_PUB_ACTION_EXT_CHANSW_ANN = 4, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 8ca2e9f354f7..738b4d8a4666 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1840,6 +1840,12 @@ enum cfg80211_assoc_req_flags { * @ht_capa_mask: The bits of ht_capa which are to be used. * @vht_capa: VHT capability override * @vht_capa_mask: VHT capability mask indicating which fields to use + * @fils_kek: FILS KEK for protecting (Re)Association Request/Response frame or + * %NULL if FILS is not used. + * @fils_kek_len: Length of fils_kek in octets + * @fils_nonces: FILS nonces (part of AAD) for protecting (Re)Association + * Request/Response frame or %NULL if FILS is not used. This field starts + * with 16 octets of STA Nonce followed by 16 octets of AP Nonce. */ struct cfg80211_assoc_request { struct cfg80211_bss *bss; @@ -1851,6 +1857,9 @@ struct cfg80211_assoc_request { struct ieee80211_ht_cap ht_capa; struct ieee80211_ht_cap ht_capa_mask; struct ieee80211_vht_cap vht_capa, vht_capa_mask; + const u8 *fils_kek; + size_t fils_kek_len; + const u8 *fils_nonces; }; /** 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, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index ff798620e929..667d5f719c22 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -414,6 +414,9 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_NAN_MASTER_PREF] = { .type = NLA_U8 }, [NL80211_ATTR_NAN_DUAL] = { .type = NLA_U8 }, [NL80211_ATTR_NAN_FUNC] = { .type = NLA_NESTED }, + [NL80211_ATTR_FILS_KEK] = { .type = NLA_BINARY, + .len = FILS_MAX_KEK_LEN }, + [NL80211_ATTR_FILS_NONCES] = { .len = 2 * FILS_NONCE_LEN }, }; /* policy for the key attributes */ @@ -8033,6 +8036,15 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) req.flags |= ASSOC_REQ_USE_RRM; } + if (info->attrs[NL80211_ATTR_FILS_KEK]) { + req.fils_kek = nla_data(info->attrs[NL80211_ATTR_FILS_KEK]); + req.fils_kek_len = nla_len(info->attrs[NL80211_ATTR_FILS_KEK]); + if (!info->attrs[NL80211_ATTR_FILS_NONCES]) + return -EINVAL; + req.fils_nonces = + nla_data(info->attrs[NL80211_ATTR_FILS_NONCES]); + } + err = nl80211_crypto_settings(rdev, info, &req.crypto, 1); if (!err) { wdev_lock(dev->ieee80211_ptr); -- 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/net/cfg80211.h | 6 ++++++ include/uapi/linux/nl80211.h | 21 +++++++++++++++++++++ net/wireless/nl80211.c | 35 +++++++++++++++++++++++++++++++++++ net/wireless/rdev-ops.h | 12 ++++++++++++ net/wireless/trace.h | 19 +++++++++++++++++++ 5 files changed, 93 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 738b4d8a4666..41ae3f500957 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2742,6 +2742,8 @@ struct cfg80211_nan_func { * @nan_change_conf: changes NAN configuration. The changed parameters must * be specified in @changes (using &enum cfg80211_nan_conf_changes); * All other parameters must be ignored. + * + * @set_multicast_to_unicast: configure multicast to unicast conversion for BSS */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -3018,6 +3020,10 @@ struct cfg80211_ops { struct wireless_dev *wdev, struct cfg80211_nan_conf *conf, u32 changes); + + int (*set_multicast_to_unicast)(struct wiphy *wiphy, + struct net_device *dev, + const bool enabled); }; /* 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, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 667d5f719c22..0c9d00c9cef1 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -417,6 +417,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_FILS_KEK] = { .type = NLA_BINARY, .len = FILS_MAX_KEK_LEN }, [NL80211_ATTR_FILS_NONCES] = { .len = 2 * FILS_NONCE_LEN }, + [NL80211_ATTR_MULTICAST_TO_UNICAST_ENABLED] = { .type = NLA_FLAG, }, }; /* policy for the key attributes */ @@ -1659,6 +1660,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, if (rdev->wiphy.features & NL80211_FEATURE_SUPPORTS_WMM_ADMISSION) CMD(add_tx_ts, ADD_TX_TS); + CMD(set_multicast_to_unicast, SET_MULTICAST_TO_UNICAST); } #undef CMD @@ -11766,6 +11768,31 @@ static int nl80211_tdls_cancel_channel_switch(struct sk_buff *skb, return 0; } +static int nl80211_set_multicast_to_unicast(struct sk_buff *skb, + struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; + const struct nlattr *nla; + bool enabled; + + if (netif_running(dev)) + return -EBUSY; + + if (!rdev->ops->set_multicast_to_unicast) + return -EOPNOTSUPP; + + if (wdev->iftype != NL80211_IFTYPE_AP && + wdev->iftype != NL80211_IFTYPE_P2P_GO) + return -EOPNOTSUPP; + + nla = info->attrs[NL80211_ATTR_MULTICAST_TO_UNICAST_ENABLED]; + enabled = nla_get_flag(nla); + + return rdev_set_multicast_to_unicast(rdev, dev, enabled); +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -12625,6 +12652,14 @@ static const struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_SET_MULTICAST_TO_UNICAST, + .doit = nl80211_set_multicast_to_unicast, + .policy = nl80211_policy, + .flags = GENL_UNS_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, + }, }; /* notification functions */ diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 11cf83c8ad4f..e9ecf23e7942 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -562,6 +562,18 @@ static inline int rdev_set_wds_peer(struct cfg80211_registered_device *rdev, return ret; } +static inline int +rdev_set_multicast_to_unicast(struct cfg80211_registered_device *rdev, + struct net_device *dev, + const bool enabled) +{ + int ret; + trace_rdev_set_multicast_to_unicast(&rdev->wiphy, dev, enabled); + ret = rdev->ops->set_multicast_to_unicast(&rdev->wiphy, dev, enabled); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + static inline void rdev_rfkill_poll(struct cfg80211_registered_device *rdev) { trace_rdev_rfkill_poll(&rdev->wiphy); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index a3d0a91b1e09..25f8318b3e0b 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -3030,6 +3030,25 @@ DEFINE_EVENT(wiphy_wdev_evt, rdev_abort_scan, TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev), TP_ARGS(wiphy, wdev) ); + +TRACE_EVENT(rdev_set_multicast_to_unicast, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + const bool enabled), + TP_ARGS(wiphy, netdev, enabled), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(bool, enabled) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->enabled = enabled; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", unicast: %s", + WIPHY_PR_ARG, NETDEV_PR_ARG, + BOOL_TO_STR(__entry->enabled)) +); #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH -- 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/net/cfg80211.h | 24 ++++++++++++++++++++++++ include/uapi/linux/nl80211.h | 8 ++++++++ net/wireless/nl80211.c | 40 ++++++++++++++++++++++++++++++++++++++++ net/wireless/rdev-ops.h | 12 ++++++++++++ net/wireless/trace.h | 18 ++++++++++++++++++ 5 files changed, 102 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 41ae3f500957..c575583b50fb 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2050,6 +2050,18 @@ struct cfg80211_connect_params { const u8 *prev_bssid; }; +/** + * enum cfg80211_connect_params_changed - Connection parameters being updated + * + * This enum provides information of all connect parameters that + * have to be updated as part of update_connect_params() call. + * + * @UPDATE_ASSOC_IES: Indicates whether association request IEs are updated + */ +enum cfg80211_connect_params_changed { + UPDATE_ASSOC_IES = BIT(0), +}; + /** * enum wiphy_params_flags - set_wiphy_params bitfield values * @WIPHY_PARAM_RETRY_SHORT: wiphy->retry_short has changed @@ -2571,6 +2583,14 @@ struct cfg80211_nan_func { * cases, the result of roaming is indicated with a call to * cfg80211_roamed() or cfg80211_roamed_bss(). * (invoked with the wireless_dev mutex held) + * @update_connect_params: Update the connect parameters while connected to a + * BSS. The updated parameters can be used by driver/firmware for + * subsequent BSS selection (roaming) decisions and to form the + * Authentication/(Re)Association Request frames. This call does not + * request an immediate disassociation or reassociation with the current + * BSS, i.e., this impacts only subsequent (re)associations. The bits in + * changed are defined in &enum cfg80211_connect_params_changed. + * (invoked with the wireless_dev mutex held) * @disconnect: Disconnect from the BSS/ESS or stop connection attempts if * connection is in progress. Once done, call cfg80211_disconnected() in * case connection was already established (invoked with the @@ -2858,6 +2878,10 @@ struct cfg80211_ops { int (*connect)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_connect_params *sme); + int (*update_connect_params)(struct wiphy *wiphy, + struct net_device *dev, + struct cfg80211_connect_params *sme, + u32 changed); int (*disconnect)(struct wiphy *wiphy, struct net_device *dev, u16 reason_code); 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 */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0c9d00c9cef1..bb30fa1969f9 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1661,6 +1661,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, NL80211_FEATURE_SUPPORTS_WMM_ADMISSION) CMD(add_tx_ts, ADD_TX_TS); CMD(set_multicast_to_unicast, SET_MULTICAST_TO_UNICAST); + CMD(update_connect_params, UPDATE_CONNECT_PARAMS); } #undef CMD @@ -8779,6 +8780,37 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) return err; } +static int nl80211_update_connect_params(struct sk_buff *skb, + struct genl_info *info) +{ + struct cfg80211_connect_params connect = {}; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; + u32 changed = 0; + int ret; + + if (!rdev->ops->update_connect_params) + return -EOPNOTSUPP; + + if (info->attrs[NL80211_ATTR_IE]) { + if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) + return -EINVAL; + connect.ie = nla_data(info->attrs[NL80211_ATTR_IE]); + connect.ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); + changed |= UPDATE_ASSOC_IES; + } + + wdev_lock(dev->ieee80211_ptr); + if (!wdev->current_bss) + ret = -ENOLINK; + else + ret = rdev_update_connect_params(rdev, dev, &connect, changed); + wdev_unlock(dev->ieee80211_ptr); + + return ret; +} + static int nl80211_disconnect(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -12231,6 +12263,14 @@ static const struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_UPDATE_CONNECT_PARAMS, + .doit = nl80211_update_connect_params, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, + }, { .cmd = NL80211_CMD_DISCONNECT, .doit = nl80211_disconnect, diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index e9ecf23e7942..2f425075ada8 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -490,6 +490,18 @@ static inline int rdev_connect(struct cfg80211_registered_device *rdev, return ret; } +static inline int +rdev_update_connect_params(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_connect_params *sme, u32 changed) +{ + int ret; + trace_rdev_update_connect_params(&rdev->wiphy, dev, sme, changed); + ret = rdev->ops->update_connect_params(&rdev->wiphy, dev, sme, changed); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + static inline int rdev_disconnect(struct cfg80211_registered_device *rdev, struct net_device *dev, u16 reason_code) { diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 25f8318b3e0b..ea1b47e04fa4 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1281,6 +1281,24 @@ TRACE_EVENT(rdev_connect, __entry->wpa_versions, __entry->flags, MAC_PR_ARG(prev_bssid)) ); +TRACE_EVENT(rdev_update_connect_params, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_connect_params *sme, u32 changed), + TP_ARGS(wiphy, netdev, sme, changed), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(u32, changed) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->changed = changed; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", parameters changed: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->changed) +); + TRACE_EVENT(rdev_set_cqm_rssi_config, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, s32 rssi_thold, -- 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/net/tc_act/tc_skbedit.h | 1 + include/uapi/linux/tc_act/tc_skbedit.h | 2 ++ net/sched/act_skbedit.c | 21 ++++++++++++++++++--- 3 files changed, 21 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index 5767e9dbcf92..19cd3d345804 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -27,6 +27,7 @@ struct tcf_skbedit { u32 flags; u32 priority; u32 mark; + u32 mask; u16 queue_mapping; u16 ptype; }; 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) diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index a133dcb82132..024f3a3afeff 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -46,8 +46,10 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a, if (d->flags & SKBEDIT_F_QUEUE_MAPPING && skb->dev->real_num_tx_queues > d->queue_mapping) skb_set_queue_mapping(skb, d->queue_mapping); - if (d->flags & SKBEDIT_F_MARK) - skb->mark = d->mark; + if (d->flags & SKBEDIT_F_MARK) { + skb->mark &= ~d->mask; + skb->mark |= d->mark & d->mask; + } if (d->flags & SKBEDIT_F_PTYPE) skb->pkt_type = d->ptype; @@ -61,6 +63,7 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { [TCA_SKBEDIT_QUEUE_MAPPING] = { .len = sizeof(u16) }, [TCA_SKBEDIT_MARK] = { .len = sizeof(u32) }, [TCA_SKBEDIT_PTYPE] = { .len = sizeof(u16) }, + [TCA_SKBEDIT_MASK] = { .len = sizeof(u32) }, }; static int tcf_skbedit_init(struct net *net, struct nlattr *nla, @@ -71,7 +74,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; struct tc_skbedit *parm; struct tcf_skbedit *d; - u32 flags = 0, *priority = NULL, *mark = NULL; + u32 flags = 0, *priority = NULL, *mark = NULL, *mask = NULL; u16 *queue_mapping = NULL, *ptype = NULL; bool exists = false; int ret = 0, err; @@ -108,6 +111,11 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, mark = nla_data(tb[TCA_SKBEDIT_MARK]); } + if (tb[TCA_SKBEDIT_MASK] != NULL) { + flags |= SKBEDIT_F_MASK; + mask = nla_data(tb[TCA_SKBEDIT_MASK]); + } + parm = nla_data(tb[TCA_SKBEDIT_PARMS]); exists = tcf_hash_check(tn, parm->index, a, bind); @@ -145,6 +153,10 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, d->mark = *mark; if (flags & SKBEDIT_F_PTYPE) d->ptype = *ptype; + /* default behaviour is to use all the bits */ + d->mask = 0xffffffff; + if (flags & SKBEDIT_F_MASK) + d->mask = *mask; d->tcf_action = parm->action; @@ -182,6 +194,9 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, if ((d->flags & SKBEDIT_F_PTYPE) && nla_put_u16(skb, TCA_SKBEDIT_PTYPE, d->ptype)) goto nla_put_failure; + if ((d->flags & SKBEDIT_F_MASK) && + nla_put_u32(skb, TCA_SKBEDIT_MASK, d->mask)) + goto nla_put_failure; tcf_tm_dump(&t, &d->tcf_tm); if (nla_put_64bit(skb, TCA_SKBEDIT_TM, sizeof(t), &t, TCA_SKBEDIT_PAD)) -- 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 --- drivers/acpi/event.c | 1 - drivers/net/gtp.c | 1 - drivers/net/macsec.c | 1 - drivers/net/team/team.c | 1 - drivers/net/wireless/mac80211_hwsim.c | 1 - drivers/scsi/pmcraid.c | 6 ------ drivers/target/target_core_user.c | 1 - drivers/thermal/thermal_core.c | 1 - fs/dlm/netlink.c | 1 - fs/quota/netlink.c | 7 ------- include/linux/genl_magic_func.h | 1 - include/net/genetlink.h | 7 ++----- include/uapi/linux/genetlink.h | 1 - kernel/taskstats.c | 1 - net/batman-adv/netlink.c | 1 - net/core/devlink.c | 1 - net/core/drop_monitor.c | 1 - net/hsr/hsr_netlink.c | 1 - net/ieee802154/netlink.c | 1 - net/ieee802154/nl802154.c | 1 - net/ipv4/fou.c | 1 - net/ipv4/tcp_metrics.c | 1 - net/ipv6/ila/ila_xlat.c | 1 - net/irda/irnetlink.c | 1 - net/l2tp/l2tp_netlink.c | 1 - net/netfilter/ipvs/ip_vs_ctl.c | 1 - net/netlabel/netlabel_calipso.c | 1 - net/netlabel/netlabel_cipso_v4.c | 1 - net/netlabel/netlabel_mgmt.c | 1 - net/netlabel/netlabel_unlabeled.c | 1 - net/netlink/genetlink.c | 37 +++++++++++++++++++++-------------- net/nfc/netlink.c | 1 - net/openvswitch/datapath.c | 4 ---- net/tipc/netlink.c | 1 - net/tipc/netlink_compat.c | 1 - net/wimax/stack.c | 1 - net/wireless/nl80211.c | 1 - 37 files changed, 24 insertions(+), 69 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c index e24ea4e796e4..8dfca3d53131 100644 --- a/drivers/acpi/event.c +++ b/drivers/acpi/event.c @@ -83,7 +83,6 @@ static const struct genl_multicast_group acpi_event_mcgrps[] = { }; static struct genl_family acpi_event_genl_family = { - .id = GENL_ID_GENERATE, .name = ACPI_GENL_FAMILY_NAME, .version = ACPI_GENL_VERSION, .maxattr = ACPI_GENL_ATTR_MAX, diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 97e0cbca0a08..f66737ba1299 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1095,7 +1095,6 @@ static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info) } static struct genl_family gtp_genl_family = { - .id = GENL_ID_GENERATE, .name = "gtp", .version = 0, .hdrsize = 0, diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 1a134cb2d52c..a5309b81a786 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1422,7 +1422,6 @@ static void clear_tx_sa(struct macsec_tx_sa *tx_sa) } static struct genl_family macsec_fam = { - .id = GENL_ID_GENERATE, .name = MACSEC_GENL_NAME, .hdrsize = 0, .version = MACSEC_GENL_VERSION, diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index a380649bf6b5..0b50205764ff 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2151,7 +2151,6 @@ static struct rtnl_link_ops team_link_ops __read_mostly = { ***********************************/ static struct genl_family team_nl_family = { - .id = GENL_ID_GENERATE, .name = TEAM_GENL_NAME, .version = TEAM_GENL_VERSION, .maxattr = TEAM_ATTR_MAX, diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index e95b79bccf9b..54b6cd62676e 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -589,7 +589,6 @@ struct hwsim_radiotap_ack_hdr { /* MAC80211_HWSIM netlinf family */ static struct genl_family hwsim_genl_family = { - .id = GENL_ID_GENERATE, .hdrsize = 0, .name = "MAC80211_HWSIM", .version = 1, diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index 68a5c347fae9..cc50eb87b28a 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -1369,12 +1369,6 @@ static struct genl_multicast_group pmcraid_mcgrps[] = { }; static struct genl_family pmcraid_event_family = { - /* - * Due to prior multicast group abuse (the code having assumed that - * the family ID can be used as a multicast group ID) we need to - * statically allocate a family (and thus group) ID. - */ - .id = GENL_ID_PMCRAID, .name = "pmcraid", .version = 1, .maxattr = PMCRAID_AEN_ATTR_MAX, diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 62bf4fe5704a..313a0ef3cda7 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -148,7 +148,6 @@ static const struct genl_multicast_group tcmu_mcgrps[] = { /* Our generic netlink family */ static struct genl_family tcmu_genl_family = { - .id = GENL_ID_GENERATE, .hdrsize = 0, .name = "TCM-USER", .version = 1, diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 226b0b4aced6..68d7503f6417 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -2164,7 +2164,6 @@ static const struct genl_multicast_group thermal_event_mcgrps[] = { }; static struct genl_family thermal_event_genl_family = { - .id = GENL_ID_GENERATE, .name = THERMAL_GENL_FAMILY_NAME, .version = THERMAL_GENL_VERSION, .maxattr = THERMAL_GENL_ATTR_MAX, diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c index 1e6e227134d7..00d226956264 100644 --- a/fs/dlm/netlink.c +++ b/fs/dlm/netlink.c @@ -17,7 +17,6 @@ static uint32_t dlm_nl_seqnum; static uint32_t listener_nlportid; static struct genl_family family = { - .id = GENL_ID_GENERATE, .name = DLM_GENL_NAME, .version = DLM_GENL_VERSION, }; diff --git a/fs/quota/netlink.c b/fs/quota/netlink.c index 8b252673d454..3965a5cdfaa2 100644 --- a/fs/quota/netlink.c +++ b/fs/quota/netlink.c @@ -13,13 +13,6 @@ static const struct genl_multicast_group quota_mcgrps[] = { /* Netlink family structure for quota */ static struct genl_family quota_genl_family = { - /* - * Needed due to multicast group ID abuse - old code assumed - * the family ID was also a valid multicast group ID (which - * isn't true) and userspace might thus rely on it. Assign a - * static ID for this group to make dealing with that easier. - */ - .id = GENL_ID_VFS_DQUOT, .hdrsize = 0, .name = "VFS_DQUOT", .version = 1, diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h index 667c31101b8b..7c070c1fe457 100644 --- a/include/linux/genl_magic_func.h +++ b/include/linux/genl_magic_func.h @@ -260,7 +260,6 @@ static struct genl_ops ZZZ_genl_ops[] __read_mostly = { */ #define ZZZ_genl_family CONCAT_(GENL_MAGIC_FAMILY, _genl_family) static struct genl_family ZZZ_genl_family __read_mostly = { - .id = GENL_ID_GENERATE, .name = __stringify(GENL_MAGIC_FAMILY), .version = GENL_MAGIC_VERSION, #ifdef GENL_MAGIC_FAMILY_HDRSZ diff --git a/include/net/genetlink.h b/include/net/genetlink.h index ef9defb3f5bc..43a5c3975a2f 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -20,7 +20,7 @@ struct genl_info; /** * struct genl_family - generic netlink family - * @id: protocol family idenfitier + * @id: protocol family identifier (private) * @hdrsize: length of user specific header in bytes * @name: name of family * @version: protocol version @@ -48,7 +48,7 @@ struct genl_info; * @n_ops: number of operations supported by this family (private) */ struct genl_family { - unsigned int id; + unsigned int id; /* private */ unsigned int hdrsize; char name[GENL_NAMSIZ]; unsigned int version; @@ -149,9 +149,6 @@ static inline int genl_register_family(struct genl_family *family) * Registers the specified family and operations from the specified table. * Only one family may be registered with the same family name or identifier. * - * The family id may equal GENL_ID_GENERATE causing an unique id to - * be automatically generated and assigned. - * * Either a doit or dumpit callback must be specified for every registered * operation or the function will fail. Only one operation structure per * command identifier may be registered. 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) diff --git a/kernel/taskstats.c b/kernel/taskstats.c index b3f05ee20d18..d7a1a9461a10 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -42,7 +42,6 @@ static int family_registered; struct kmem_cache *taskstats_cache; static struct genl_family family = { - .id = GENL_ID_GENERATE, .name = TASKSTATS_GENL_NAME, .version = TASKSTATS_GENL_VERSION, .maxattr = TASKSTATS_CMD_ATTR_MAX, diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 64cb6acbe0a6..a03b0ed7e8dd 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -49,7 +49,6 @@ #include "translation-table.h" struct genl_family batadv_netlink_family = { - .id = GENL_ID_GENERATE, .hdrsize = 0, .name = BATADV_NL_NAME, .version = 1, diff --git a/net/core/devlink.c b/net/core/devlink.c index d2fd736de6a2..3008d9c33875 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -342,7 +342,6 @@ static void devlink_nl_post_doit(const struct genl_ops *ops, } static struct genl_family devlink_nl_family = { - .id = GENL_ID_GENERATE, .name = DEVLINK_GENL_NAME, .version = DEVLINK_GENL_VERSION, .maxattr = DEVLINK_ATTR_MAX, diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 72cfb0c61125..a5320dfcd978 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -60,7 +60,6 @@ struct dm_hw_stat_delta { }; static struct genl_family net_drop_monitor_family = { - .id = GENL_ID_GENERATE, .hdrsize = 0, .name = "NET_DM", .version = 2, diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index d4d1617f43a8..2ad039492bee 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -132,7 +132,6 @@ static const struct nla_policy hsr_genl_policy[HSR_A_MAX + 1] = { }; static struct genl_family hsr_genl_family = { - .id = GENL_ID_GENERATE, .hdrsize = 0, .name = "HSR", .version = 1, diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c index c8133c07ceee..19144158b696 100644 --- a/net/ieee802154/netlink.c +++ b/net/ieee802154/netlink.c @@ -29,7 +29,6 @@ static unsigned int ieee802154_seq_num; static DEFINE_SPINLOCK(ieee802154_seq_lock); struct genl_family nl802154_family = { - .id = GENL_ID_GENERATE, .hdrsize = 0, .name = IEEE802154_NL_NAME, .version = 1, diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index 21aabadccd0e..182299858f1d 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -34,7 +34,6 @@ static void nl802154_post_doit(const struct genl_ops *ops, struct sk_buff *skb, /* the netlink family */ static struct genl_family nl802154_fam = { - .id = GENL_ID_GENERATE, /* don't bother with a hardcoded ID */ .name = NL802154_GENL_NAME, /* have users key off the name instead */ .hdrsize = 0, /* no private header */ .version = 1, /* no particular meaning now */ diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index cf50f7e2b012..e3fc527c5d37 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -623,7 +623,6 @@ static int fou_destroy(struct net *net, struct fou_cfg *cfg) } static struct genl_family fou_nl_family = { - .id = GENL_ID_GENERATE, .hdrsize = 0, .name = FOU_GENL_NAME, .version = FOU_GENL_VERSION, diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index bf1f3b2b29d1..3da305127b32 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -743,7 +743,6 @@ void tcp_fastopen_cache_set(struct sock *sk, u16 mss, } static struct genl_family tcp_metrics_nl_family = { - .id = GENL_ID_GENERATE, .hdrsize = 0, .name = TCP_METRICS_GENL_NAME, .version = TCP_METRICS_GENL_VERSION, diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index e604013dd814..0d57e27d1cdd 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -119,7 +119,6 @@ static const struct rhashtable_params rht_params = { }; static struct genl_family ila_nl_family = { - .id = GENL_ID_GENERATE, .hdrsize = 0, .name = ILA_GENL_NAME, .version = ILA_GENL_VERSION, diff --git a/net/irda/irnetlink.c b/net/irda/irnetlink.c index e15c40e86660..f23b81aa91fe 100644 --- a/net/irda/irnetlink.c +++ b/net/irda/irnetlink.c @@ -25,7 +25,6 @@ static struct genl_family irda_nl_family = { - .id = GENL_ID_GENERATE, .name = IRDA_NL_NAME, .hdrsize = 0, .version = IRDA_NL_VERSION, diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index bf3117771822..4fbf1f41ac52 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -32,7 +32,6 @@ static struct genl_family l2tp_nl_family = { - .id = GENL_ID_GENERATE, .name = L2TP_GENL_NAME, .version = L2TP_GENL_VERSION, .hdrsize = 0, diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index c3c809b2e712..ceed66cdd03e 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2841,7 +2841,6 @@ static struct nf_sockopt_ops ip_vs_sockopts = { /* IPVS genetlink family */ static struct genl_family ip_vs_genl_family = { - .id = GENL_ID_GENERATE, .hdrsize = 0, .name = IPVS_GENL_NAME, .version = IPVS_GENL_VERSION, diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c index 2ec93c5e77bb..152e503b8c5d 100644 --- a/net/netlabel/netlabel_calipso.c +++ b/net/netlabel/netlabel_calipso.c @@ -61,7 +61,6 @@ struct netlbl_domhsh_walk_arg { /* NetLabel Generic NETLINK CALIPSO family */ static struct genl_family netlbl_calipso_gnl_family = { - .id = GENL_ID_GENERATE, .hdrsize = 0, .name = NETLBL_NLTYPE_CALIPSO_NAME, .version = NETLBL_PROTO_VERSION, diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index 7fd1104ba900..755b284e7ad4 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -60,7 +60,6 @@ struct netlbl_domhsh_walk_arg { /* NetLabel Generic NETLINK CIPSOv4 family */ static struct genl_family netlbl_cipsov4_gnl_family = { - .id = GENL_ID_GENERATE, .hdrsize = 0, .name = NETLBL_NLTYPE_CIPSOV4_NAME, .version = NETLBL_PROTO_VERSION, diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index f85d0e07af2d..3b00f2368fcd 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -61,7 +61,6 @@ struct netlbl_domhsh_walk_arg { /* NetLabel Generic NETLINK CIPSOv4 family */ static struct genl_family netlbl_mgmt_gnl_family = { - .id = GENL_ID_GENERATE, .hdrsize = 0, .name = NETLBL_NLTYPE_MGMT_NAME, .version = NETLBL_PROTO_VERSION, diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 4528cff9138b..c2ea8d1f653a 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -124,7 +124,6 @@ static u8 netlabel_unlabel_acceptflg; /* NetLabel Generic NETLINK unlabeled family */ static struct genl_family netlbl_unlabel_gnl_family = { - .id = GENL_ID_GENERATE, .hdrsize = 0, .name = NETLBL_NLTYPE_UNLABELED_NAME, .version = NETLBL_PROTO_VERSION, diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 01291b7a27bb..f19ec969edee 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -349,8 +349,6 @@ static int genl_validate_ops(const struct genl_family *family) * * Registers the specified family after validating it first. Only one * family may be registered with the same family name or identifier. - * The family id may equal GENL_ID_GENERATE causing an unique id to - * be automatically generated and assigned. * * The family's ops array must already be assigned, you can use the * genl_register_family_with_ops() helper function. @@ -359,13 +357,7 @@ static int genl_validate_ops(const struct genl_family *family) */ int __genl_register_family(struct genl_family *family) { - int err = -EINVAL, i; - - if (family->id && family->id < GENL_MIN_ID) - goto errout; - - if (family->id > GENL_MAX_ID) - goto errout; + int err, i; err = genl_validate_ops(family); if (err) @@ -378,8 +370,27 @@ int __genl_register_family(struct genl_family *family) goto errout_locked; } - if (family->id == GENL_ID_GENERATE) { - u16 newid = genl_generate_id(); + if (family == &genl_ctrl) { + family->id = GENL_ID_CTRL; + } else { + u16 newid; + + /* this should be left zero in the struct */ + WARN_ON(family->id); + + /* + * Sadly, a few cases need to be special-cased + * due to them having previously abused the API + * and having used their family ID also as their + * multicast group ID, so we use reserved IDs + * for both to be sure we can do that mapping. + */ + if (strcmp(family->name, "pmcraid") == 0) + newid = GENL_ID_PMCRAID; + else if (strcmp(family->name, "VFS_DQUOT") == 0) + newid = GENL_ID_VFS_DQUOT; + else + newid = genl_generate_id(); if (!newid) { err = -ENOMEM; @@ -387,9 +398,6 @@ int __genl_register_family(struct genl_family *family) } family->id = newid; - } else if (genl_family_find_byid(family->id)) { - err = -EEXIST; - goto errout_locked; } if (family->maxattr && !family->parallel_ops) { @@ -419,7 +427,6 @@ int __genl_register_family(struct genl_family *family) errout_locked: genl_unlock_all(); -errout: return err; } EXPORT_SYMBOL(__genl_register_family); diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 79786bf62b88..c230403e066c 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -39,7 +39,6 @@ static const struct genl_multicast_group nfc_genl_mcgrps[] = { }; static struct genl_family nfc_genl_family = { - .id = GENL_ID_GENERATE, .hdrsize = 0, .name = NFC_GENL_NAME, .version = NFC_GENL_VERSION, diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 194435aa1165..f9fef7dfba15 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -671,7 +671,6 @@ static const struct genl_ops dp_packet_genl_ops[] = { }; static struct genl_family dp_packet_genl_family = { - .id = GENL_ID_GENERATE, .hdrsize = sizeof(struct ovs_header), .name = OVS_PACKET_FAMILY, .version = OVS_PACKET_VERSION, @@ -1436,7 +1435,6 @@ static const struct genl_ops dp_flow_genl_ops[] = { }; static struct genl_family dp_flow_genl_family = { - .id = GENL_ID_GENERATE, .hdrsize = sizeof(struct ovs_header), .name = OVS_FLOW_FAMILY, .version = OVS_FLOW_VERSION, @@ -1822,7 +1820,6 @@ static const struct genl_ops dp_datapath_genl_ops[] = { }; static struct genl_family dp_datapath_genl_family = { - .id = GENL_ID_GENERATE, .hdrsize = sizeof(struct ovs_header), .name = OVS_DATAPATH_FAMILY, .version = OVS_DATAPATH_VERSION, @@ -2244,7 +2241,6 @@ static const struct genl_ops dp_vport_genl_ops[] = { }; struct genl_family dp_vport_genl_family = { - .id = GENL_ID_GENERATE, .hdrsize = sizeof(struct ovs_header), .name = OVS_VPORT_FAMILY, .version = OVS_VPORT_VERSION, diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 4b94f3cfe3af..383b8fedabc7 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -136,7 +136,6 @@ const struct nla_policy tipc_nl_udp_policy[TIPC_NLA_UDP_MAX + 1] = { * so we have a separate genl handling for the new API. */ struct genl_family tipc_genl_family = { - .id = GENL_ID_GENERATE, .name = TIPC_GENL_V2_NAME, .version = TIPC_GENL_V2_VERSION, .hdrsize = 0, diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 1fd464764765..f04428e4c8e5 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -1216,7 +1216,6 @@ send: } static struct genl_family tipc_genl_compat_family = { - .id = GENL_ID_GENERATE, .name = TIPC_GENL_NAME, .version = TIPC_GENL_VERSION, .hdrsize = TIPC_GENL_HDRLEN, diff --git a/net/wimax/stack.c b/net/wimax/stack.c index 3f816e2971ee..8ac83a41585f 100644 --- a/net/wimax/stack.c +++ b/net/wimax/stack.c @@ -573,7 +573,6 @@ size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL); struct genl_family wimax_gnl_family = { - .id = GENL_ID_GENERATE, .name = "WiMAX", .version = WIMAX_GNL_VERSION, .hdrsize = 0, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 7d8cb3330c86..714beafe05e0 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -39,7 +39,6 @@ static void nl80211_post_doit(const struct genl_ops *ops, struct sk_buff *skb, /* the netlink family */ static struct genl_family nl80211_fam = { - .id = GENL_ID_GENERATE, /* don't bother with a hardcoded ID */ .name = NL80211_GENL_NAME, /* have users key off the name instead */ .hdrsize = 0, /* no private header */ .version = 1, /* no particular meaning now */ -- 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/net/genetlink.h | 31 +++-- include/uapi/linux/genetlink.h | 2 + net/netlink/genetlink.c | 271 ++++++++++++++++------------------------- 3 files changed, 123 insertions(+), 181 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 2298b50cee34..3ec87bacc0f5 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -40,7 +40,6 @@ struct genl_info; * generic netlink family is removed while there are still open * sockets. * @attrbuf: buffer to store parsed attributes (private) - * @family_list: family list (private) * @mcgrps: multicast groups used by this family * @n_mcgrps: number of multicast groups * @mcgrp_offset: starting number of multicast group IDs in this family @@ -70,11 +69,10 @@ struct genl_family { unsigned int n_ops; unsigned int n_mcgrps; unsigned int mcgrp_offset; /* private */ - struct list_head family_list; /* private */ struct module *module; }; -struct nlattr **genl_family_attrbuf(struct genl_family *family); +struct nlattr **genl_family_attrbuf(const struct genl_family *family); /** * struct genl_info - receiving information @@ -134,12 +132,12 @@ struct genl_ops { }; int genl_register_family(struct genl_family *family); -int genl_unregister_family(struct genl_family *family); -void genl_notify(struct genl_family *family, struct sk_buff *skb, +int genl_unregister_family(const struct genl_family *family); +void genl_notify(const struct genl_family *family, struct sk_buff *skb, struct genl_info *info, u32 group, gfp_t flags); void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, - struct genl_family *family, int flags, u8 cmd); + const struct genl_family *family, int flags, u8 cmd); /** * genlmsg_nlhdr - Obtain netlink header from user specified header @@ -148,8 +146,8 @@ void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, * * Returns pointer to netlink header. */ -static inline struct nlmsghdr *genlmsg_nlhdr(void *user_hdr, - struct genl_family *family) +static inline struct nlmsghdr * +genlmsg_nlhdr(void *user_hdr, const struct genl_family *family) { return (struct nlmsghdr *)((char *)user_hdr - family->hdrsize - @@ -185,7 +183,7 @@ static inline int genlmsg_parse(const struct nlmsghdr *nlh, */ static inline void genl_dump_check_consistent(struct netlink_callback *cb, void *user_hdr, - struct genl_family *family) + const struct genl_family *family) { nl_dump_check_consistent(cb, genlmsg_nlhdr(user_hdr, family)); } @@ -202,7 +200,7 @@ static inline void genl_dump_check_consistent(struct netlink_callback *cb, */ static inline void *genlmsg_put_reply(struct sk_buff *skb, struct genl_info *info, - struct genl_family *family, + const struct genl_family *family, int flags, u8 cmd) { return genlmsg_put(skb, info->snd_portid, info->snd_seq, family, @@ -239,7 +237,7 @@ static inline void genlmsg_cancel(struct sk_buff *skb, void *hdr) * @group: offset of multicast group in groups array * @flags: allocation flags */ -static inline int genlmsg_multicast_netns(struct genl_family *family, +static inline int genlmsg_multicast_netns(const struct genl_family *family, struct net *net, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { @@ -257,7 +255,7 @@ static inline int genlmsg_multicast_netns(struct genl_family *family, * @group: offset of multicast group in groups array * @flags: allocation flags */ -static inline int genlmsg_multicast(struct genl_family *family, +static inline int genlmsg_multicast(const struct genl_family *family, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { @@ -275,7 +273,7 @@ static inline int genlmsg_multicast(struct genl_family *family, * * This function must hold the RTNL or rcu_read_lock(). */ -int genlmsg_multicast_allns(struct genl_family *family, +int genlmsg_multicast_allns(const struct genl_family *family, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags); @@ -359,8 +357,9 @@ static inline struct sk_buff *genlmsg_new(size_t payload, gfp_t flags) * This function returns the number of broadcast listeners that have set the * NETLINK_RECV_NO_ENOBUFS socket option. */ -static inline int genl_set_err(struct genl_family *family, struct net *net, - u32 portid, u32 group, int code) +static inline int genl_set_err(const struct genl_family *family, + struct net *net, u32 portid, + u32 group, int code) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; @@ -368,7 +367,7 @@ static inline int genl_set_err(struct genl_family *family, struct net *net, return netlink_set_err(net->genl_sock, portid, group, code); } -static inline int genl_has_listeners(struct genl_family *family, +static inline int genl_has_listeners(const struct genl_family *family, struct net *net, unsigned int group) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) 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 diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index ca582ee4ae05..85659921e7b2 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -58,10 +59,8 @@ static void genl_unlock_all(void) up_write(&cb_lock); } -#define GENL_FAM_TAB_SIZE 16 -#define GENL_FAM_TAB_MASK (GENL_FAM_TAB_SIZE - 1) +static DEFINE_IDR(genl_fam_idr); -static struct list_head family_ht[GENL_FAM_TAB_SIZE]; /* * Bitmap of multicast groups that are currently in use. * @@ -86,45 +85,29 @@ static unsigned long mc_group_start = 0x3 | BIT(GENL_ID_CTRL) | static unsigned long *mc_groups = &mc_group_start; static unsigned long mc_groups_longs = 1; -static int genl_ctrl_event(int event, struct genl_family *family, +static int genl_ctrl_event(int event, const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id); -static inline unsigned int genl_family_hash(unsigned int id) +static const struct genl_family *genl_family_find_byid(unsigned int id) { - return id & GENL_FAM_TAB_MASK; + return idr_find(&genl_fam_idr, id); } -static inline struct list_head *genl_family_chain(unsigned int id) +static const struct genl_family *genl_family_find_byname(char *name) { - return &family_ht[genl_family_hash(id)]; -} - -static struct genl_family *genl_family_find_byid(unsigned int id) -{ - struct genl_family *f; + const struct genl_family *family; + unsigned int id; - list_for_each_entry(f, genl_family_chain(id), family_list) - if (f->id == id) - return f; + idr_for_each_entry(&genl_fam_idr, family, id) + if (strcmp(family->name, name) == 0) + return family; return NULL; } -static struct genl_family *genl_family_find_byname(char *name) -{ - struct genl_family *f; - int i; - - for (i = 0; i < GENL_FAM_TAB_SIZE; i++) - list_for_each_entry(f, genl_family_chain(i), family_list) - if (strcmp(f->name, name) == 0) - return f; - - return NULL; -} - -static const struct genl_ops *genl_get_cmd(u8 cmd, struct genl_family *family) +static const struct genl_ops *genl_get_cmd(u8 cmd, + const struct genl_family *family) { int i; @@ -135,26 +118,6 @@ static const struct genl_ops *genl_get_cmd(u8 cmd, struct genl_family *family) return NULL; } -/* Of course we are going to have problems once we hit - * 2^16 alive types, but that can only happen by year 2K -*/ -static u16 genl_generate_id(void) -{ - static u16 id_gen_idx = GENL_MIN_ID; - int i; - - for (i = 0; i <= GENL_MAX_ID - GENL_MIN_ID; i++) { - if (id_gen_idx != GENL_ID_VFS_DQUOT && - id_gen_idx != GENL_ID_PMCRAID && - !genl_family_find_byid(id_gen_idx)) - return id_gen_idx; - if (++id_gen_idx > GENL_MAX_ID) - id_gen_idx = GENL_MIN_ID; - } - - return 0; -} - static int genl_allocate_reserve_groups(int n_groups, int *first_id) { unsigned long *new_groups; @@ -295,7 +258,7 @@ static int genl_validate_assign_mc_groups(struct genl_family *family) return err; } -static void genl_unregister_mc_groups(struct genl_family *family) +static void genl_unregister_mc_groups(const struct genl_family *family) { struct net *net; int i; @@ -358,6 +321,7 @@ static int genl_validate_ops(const struct genl_family *family) int genl_register_family(struct genl_family *family) { int err, i; + int start = GENL_START_ALLOC, end = GENL_MAX_ID; err = genl_validate_ops(family); if (err) @@ -370,34 +334,20 @@ int genl_register_family(struct genl_family *family) goto errout_locked; } + /* + * Sadly, a few cases need to be special-cased + * due to them having previously abused the API + * and having used their family ID also as their + * multicast group ID, so we use reserved IDs + * for both to be sure we can do that mapping. + */ if (family == &genl_ctrl) { - family->id = GENL_ID_CTRL; - } else { - u16 newid; - - /* this should be left zero in the struct */ - WARN_ON(family->id); - - /* - * Sadly, a few cases need to be special-cased - * due to them having previously abused the API - * and having used their family ID also as their - * multicast group ID, so we use reserved IDs - * for both to be sure we can do that mapping. - */ - if (strcmp(family->name, "pmcraid") == 0) - newid = GENL_ID_PMCRAID; - else if (strcmp(family->name, "VFS_DQUOT") == 0) - newid = GENL_ID_VFS_DQUOT; - else - newid = genl_generate_id(); - - if (!newid) { - err = -ENOMEM; - goto errout_locked; - } - - family->id = newid; + /* and this needs to be special for initial family lookups */ + start = end = GENL_ID_CTRL; + } else if (strcmp(family->name, "pmcraid") == 0) { + start = end = GENL_ID_PMCRAID; + } else if (strcmp(family->name, "VFS_DQUOT") == 0) { + start = end = GENL_ID_VFS_DQUOT; } if (family->maxattr && !family->parallel_ops) { @@ -410,11 +360,15 @@ int genl_register_family(struct genl_family *family) } else family->attrbuf = NULL; + family->id = idr_alloc(&genl_fam_idr, family, + start, end + 1, GFP_KERNEL); + if (!family->id) + goto errout_locked; + err = genl_validate_assign_mc_groups(family); if (err) - goto errout_locked; + goto errout_remove; - list_add_tail(&family->family_list, genl_family_chain(family->id)); genl_unlock_all(); /* send all events */ @@ -425,6 +379,8 @@ int genl_register_family(struct genl_family *family) return 0; +errout_remove: + idr_remove(&genl_fam_idr, family->id); errout_locked: genl_unlock_all(); return err; @@ -439,32 +395,29 @@ EXPORT_SYMBOL(genl_register_family); * * Returns 0 on success or a negative error code. */ -int genl_unregister_family(struct genl_family *family) +int genl_unregister_family(const struct genl_family *family) { - struct genl_family *rc; - genl_lock_all(); - list_for_each_entry(rc, genl_family_chain(family->id), family_list) { - if (family->id != rc->id || strcmp(rc->name, family->name)) - continue; + if (genl_family_find_byid(family->id)) { + genl_unlock_all(); + return -ENOENT; + } - genl_unregister_mc_groups(family); + genl_unregister_mc_groups(family); - list_del(&rc->family_list); - up_write(&cb_lock); - wait_event(genl_sk_destructing_waitq, - atomic_read(&genl_sk_destructing_cnt) == 0); - genl_unlock(); + idr_remove(&genl_fam_idr, family->id); - kfree(family->attrbuf); - genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0); - return 0; - } + up_write(&cb_lock); + wait_event(genl_sk_destructing_waitq, + atomic_read(&genl_sk_destructing_cnt) == 0); + genl_unlock(); - genl_unlock_all(); + kfree(family->attrbuf); - return -ENOENT; + genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0); + + return 0; } EXPORT_SYMBOL(genl_unregister_family); @@ -480,7 +433,7 @@ EXPORT_SYMBOL(genl_unregister_family); * Returns pointer to user specific header */ void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, - struct genl_family *family, int flags, u8 cmd) + const struct genl_family *family, int flags, u8 cmd) { struct nlmsghdr *nlh; struct genlmsghdr *hdr; @@ -539,7 +492,7 @@ static int genl_lock_done(struct netlink_callback *cb) return rc; } -static int genl_family_rcv_msg(struct genl_family *family, +static int genl_family_rcv_msg(const struct genl_family *family, struct sk_buff *skb, struct nlmsghdr *nlh) { @@ -651,7 +604,7 @@ out: static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { - struct genl_family *family; + const struct genl_family *family; int err; family = genl_family_find_byid(nlh->nlmsg_type); @@ -682,7 +635,7 @@ static void genl_rcv(struct sk_buff *skb) static struct genl_family genl_ctrl; -static int ctrl_fill_info(struct genl_family *family, u32 portid, u32 seq, +static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { void *hdr; @@ -769,7 +722,7 @@ nla_put_failure: return -EMSGSIZE; } -static int ctrl_fill_mcgrp_info(struct genl_family *family, +static int ctrl_fill_mcgrp_info(const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) @@ -812,37 +765,30 @@ nla_put_failure: static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) { - - int i, n = 0; + int n = 0; struct genl_family *rt; struct net *net = sock_net(skb->sk); - int chains_to_skip = cb->args[0]; - int fams_to_skip = cb->args[1]; - - for (i = chains_to_skip; i < GENL_FAM_TAB_SIZE; i++) { - n = 0; - list_for_each_entry(rt, genl_family_chain(i), family_list) { - if (!rt->netnsok && !net_eq(net, &init_net)) - continue; - if (++n < fams_to_skip) - continue; - if (ctrl_fill_info(rt, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - skb, CTRL_CMD_NEWFAMILY) < 0) - goto errout; - } + int fams_to_skip = cb->args[0]; + unsigned int id; - fams_to_skip = 0; - } + idr_for_each_entry(&genl_fam_idr, rt, id) { + if (!rt->netnsok && !net_eq(net, &init_net)) + continue; + + if (n++ < fams_to_skip) + continue; -errout: - cb->args[0] = i; - cb->args[1] = n; + if (ctrl_fill_info(rt, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + skb, CTRL_CMD_NEWFAMILY) < 0) + break; + } + cb->args[0] = n; return skb->len; } -static struct sk_buff *ctrl_build_family_msg(struct genl_family *family, +static struct sk_buff *ctrl_build_family_msg(const struct genl_family *family, u32 portid, int seq, u8 cmd) { struct sk_buff *skb; @@ -862,7 +808,7 @@ static struct sk_buff *ctrl_build_family_msg(struct genl_family *family, } static struct sk_buff * -ctrl_build_mcgrp_msg(struct genl_family *family, +ctrl_build_mcgrp_msg(const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id, u32 portid, int seq, u8 cmd) { @@ -892,7 +838,7 @@ static const struct nla_policy ctrl_policy[CTRL_ATTR_MAX+1] = { static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; - struct genl_family *res = NULL; + const struct genl_family *res = NULL; int err = -EINVAL; if (info->attrs[CTRL_ATTR_FAMILY_ID]) { @@ -936,7 +882,7 @@ static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info) return genlmsg_reply(msg, info); } -static int genl_ctrl_event(int event, struct genl_family *family, +static int genl_ctrl_event(int event, const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id) { @@ -1005,25 +951,24 @@ static struct genl_family genl_ctrl = { static int genl_bind(struct net *net, int group) { - int i, err = -ENOENT; + struct genl_family *f; + int err = -ENOENT; + unsigned int id; down_read(&cb_lock); - for (i = 0; i < GENL_FAM_TAB_SIZE; i++) { - struct genl_family *f; - - list_for_each_entry(f, genl_family_chain(i), family_list) { - if (group >= f->mcgrp_offset && - group < f->mcgrp_offset + f->n_mcgrps) { - int fam_grp = group - f->mcgrp_offset; - - if (!f->netnsok && net != &init_net) - err = -ENOENT; - else if (f->mcast_bind) - err = f->mcast_bind(net, fam_grp); - else - err = 0; - break; - } + + idr_for_each_entry(&genl_fam_idr, f, id) { + if (group >= f->mcgrp_offset && + group < f->mcgrp_offset + f->n_mcgrps) { + int fam_grp = group - f->mcgrp_offset; + + if (!f->netnsok && net != &init_net) + err = -ENOENT; + else if (f->mcast_bind) + err = f->mcast_bind(net, fam_grp); + else + err = 0; + break; } } up_read(&cb_lock); @@ -1033,21 +978,19 @@ static int genl_bind(struct net *net, int group) static void genl_unbind(struct net *net, int group) { - int i; + struct genl_family *f; + unsigned int id; down_read(&cb_lock); - for (i = 0; i < GENL_FAM_TAB_SIZE; i++) { - struct genl_family *f; - list_for_each_entry(f, genl_family_chain(i), family_list) { - if (group >= f->mcgrp_offset && - group < f->mcgrp_offset + f->n_mcgrps) { - int fam_grp = group - f->mcgrp_offset; + idr_for_each_entry(&genl_fam_idr, f, id) { + if (group >= f->mcgrp_offset && + group < f->mcgrp_offset + f->n_mcgrps) { + int fam_grp = group - f->mcgrp_offset; - if (f->mcast_unbind) - f->mcast_unbind(net, fam_grp); - break; - } + if (f->mcast_unbind) + f->mcast_unbind(net, fam_grp); + break; } } up_read(&cb_lock); @@ -1087,10 +1030,7 @@ static struct pernet_operations genl_pernet_ops = { static int __init genl_init(void) { - int i, err; - - for (i = 0; i < GENL_FAM_TAB_SIZE; i++) - INIT_LIST_HEAD(&family_ht[i]); + int err; err = genl_register_family(&genl_ctrl); if (err < 0) @@ -1118,7 +1058,7 @@ subsys_initcall(genl_init); * You cannot use this function with a family that has parallel_ops * and you can only use it within (pre/post) doit/dumpit callbacks. */ -struct nlattr **genl_family_attrbuf(struct genl_family *family) +struct nlattr **genl_family_attrbuf(const struct genl_family *family) { if (!WARN_ON(family->parallel_ops)) lockdep_assert_held(&genl_mutex); @@ -1156,8 +1096,9 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group, return err; } -int genlmsg_multicast_allns(struct genl_family *family, struct sk_buff *skb, - u32 portid, unsigned int group, gfp_t flags) +int genlmsg_multicast_allns(const struct genl_family *family, + struct sk_buff *skb, u32 portid, + unsigned int group, gfp_t flags) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; @@ -1166,7 +1107,7 @@ int genlmsg_multicast_allns(struct genl_family *family, struct sk_buff *skb, } EXPORT_SYMBOL(genlmsg_multicast_allns); -void genl_notify(struct genl_family *family, struct sk_buff *skb, +void genl_notify(const struct genl_family *family, struct sk_buff *skb, struct genl_info *info, u32 group, gfp_t flags) { struct net *net = genl_info_net(info); -- 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 ++++++++++++++++++++++++----------------------- kernel/bpf/verifier.c | 35 ++- 2 files changed, 316 insertions(+), 293 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. */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 846d7ceaf202..900257578934 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -19,6 +19,7 @@ #include #include #include +#include /* bpf_check() is a static code analyzer that walks eBPF program * instruction by instruction and updates register/stack state. @@ -190,6 +191,22 @@ static const char * const reg_type_str[] = { [PTR_TO_PACKET_END] = "pkt_end", }; +#define __BPF_FUNC_STR_FN(x) [BPF_FUNC_ ## x] = __stringify(bpf_ ## x) +static const char * const func_id_str[] = { + __BPF_FUNC_MAPPER(__BPF_FUNC_STR_FN) +}; +#undef __BPF_FUNC_STR_FN + +static const char *func_id_name(int id) +{ + BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID); + + if (id >= 0 && id < __BPF_FUNC_MAX_ID && func_id_str[id]) + return func_id_str[id]; + else + return "unknown"; +} + static void print_verifier_state(struct bpf_verifier_state *state) { struct bpf_reg_state *reg; @@ -354,7 +371,8 @@ static void print_bpf_insn(struct bpf_insn *insn) u8 opcode = BPF_OP(insn->code); if (opcode == BPF_CALL) { - verbose("(%02x) call %d\n", insn->code, insn->imm); + verbose("(%02x) call %s#%d\n", insn->code, + func_id_name(insn->imm), insn->imm); } else if (insn->code == (BPF_JMP | BPF_JA)) { verbose("(%02x) goto pc%+d\n", insn->code, insn->off); @@ -1114,8 +1132,8 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) return 0; error: - verbose("cannot pass map_type %d into func %d\n", - map->map_type, func_id); + verbose("cannot pass map_type %d into func %s#%d\n", + map->map_type, func_id_name(func_id), func_id); return -EINVAL; } @@ -1172,7 +1190,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id) /* find function prototype */ if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) { - verbose("invalid func %d\n", func_id); + verbose("invalid func %s#%d\n", func_id_name(func_id), func_id); return -EINVAL; } @@ -1180,7 +1198,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id) fn = env->prog->aux->ops->get_func_proto(func_id); if (!fn) { - verbose("unknown func %d\n", func_id); + verbose("unknown func %s#%d\n", func_id_name(func_id), func_id); return -EINVAL; } @@ -1200,7 +1218,8 @@ static int check_call(struct bpf_verifier_env *env, int func_id) */ err = check_raw_mode(fn); if (err) { - verbose("kernel subsystem misconfigured func %d\n", func_id); + verbose("kernel subsystem misconfigured func %s#%d\n", + func_id_name(func_id), func_id); return err; } @@ -1256,8 +1275,8 @@ static int check_call(struct bpf_verifier_env *env, int func_id) regs[BPF_REG_0].map_ptr = meta.map_ptr; regs[BPF_REG_0].id = ++env->id_gen; } else { - verbose("unknown return type %d of func %d\n", - fn->ret_type, func_id); + verbose("unknown return type %d of func %s#%d\n", + fn->ret_type, func_id_name(func_id), func_id); return -EINVAL; } -- cgit v1.2.3 From 5ff193fbde20df5d80fec367cea3e7856c057320 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Fri, 28 Oct 2016 15:04:42 -0700 Subject: x86/intel_rdt: Add basic resctrl filesystem support Use kernfs as basis for our user interface filesystem. This patch supports mount/umount, and one mount parameter "cdp" to enable code/data prioritization (though all we do at this point is ensure that the system can support CDP). The file system is not populated yet in this patch. [ tglx: Fixed up a few nits and added cdp handling in case of error ] Signed-off-by: Fenghua Yu Cc: "Ravi V Shankar" Cc: "Tony Luck" Cc: "Shaohua Li" Cc: "Sai Prakhya" Cc: "Peter Zijlstra" Cc: "Stephane Eranian" Cc: "Dave Hansen" Cc: "David Carrillo-Cisneros" Cc: "Nilay Vaish" Cc: "Vikas Shivappa" Cc: "Ingo Molnar" Cc: "Borislav Petkov" Cc: "H. Peter Anvin" Link: http://lkml.kernel.org/r/1477692289-37412-4-git-send-email-fenghua.yu@intel.com Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/intel_rdt.h | 26 +++ arch/x86/kernel/cpu/Makefile | 2 +- arch/x86/kernel/cpu/intel_rdt.c | 8 +- arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 271 +++++++++++++++++++++++++++++++ include/uapi/linux/magic.h | 1 + 5 files changed, 306 insertions(+), 2 deletions(-) create mode 100644 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c (limited to 'include/uapi/linux') diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h index c0d0a6e6448c..09d00e6f7ad6 100644 --- a/arch/x86/include/asm/intel_rdt.h +++ b/arch/x86/include/asm/intel_rdt.h @@ -1,9 +1,31 @@ #ifndef _ASM_X86_INTEL_RDT_H #define _ASM_X86_INTEL_RDT_H +#include + +#define IA32_L3_QOS_CFG 0xc81 #define IA32_L3_CBM_BASE 0xc90 #define IA32_L2_CBM_BASE 0xd10 +#define L3_QOS_CDP_ENABLE 0x01ULL + +/** + * struct rdtgroup - store rdtgroup's data in resctrl file system. + * @kn: kernfs node + * @rdtgroup_list: linked list for all rdtgroups + * @closid: closid for this rdtgroup + */ +struct rdtgroup { + struct kernfs_node *kn; + struct list_head rdtgroup_list; + int closid; +}; + +/* List of all resource groups */ +extern struct list_head rdt_all_groups; + +int __init rdtgroup_init(void); + /** * struct rdt_resource - attributes of an RDT resource * @enabled: Is this feature enabled on this machine @@ -68,6 +90,10 @@ struct msr_param { extern struct mutex rdtgroup_mutex; extern struct rdt_resource rdt_resources_all[]; +extern struct rdtgroup rdtgroup_default; +DECLARE_STATIC_KEY_FALSE(rdt_enable_key); + +int __init rdtgroup_init(void); enum { RDT_RESOURCE_L3, diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index cf4bfd030c0c..b4334e86c1a9 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -34,7 +34,7 @@ obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o -obj-$(CONFIG_INTEL_RDT_A) += intel_rdt.o +obj-$(CONFIG_INTEL_RDT_A) += intel_rdt.o intel_rdt_rdtgroup.o obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 3d4b397a1181..9d95414f7117 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -361,7 +361,7 @@ static int intel_rdt_offline_cpu(unsigned int cpu) static int __init intel_rdt_late_init(void) { struct rdt_resource *r; - int state; + int state, ret; if (!get_rdt_resources()) return -ENODEV; @@ -372,6 +372,12 @@ static int __init intel_rdt_late_init(void) if (state < 0) return state; + ret = rdtgroup_init(); + if (ret) { + cpuhp_remove_state(state); + return ret; + } + for_each_capable_rdt_resource(r) pr_info("Intel RDT %s allocation detected\n", r->name); diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c new file mode 100644 index 000000000000..106e4ce8f7e0 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -0,0 +1,271 @@ +/* + * User interface for Resource Alloction in Resource Director Technology(RDT) + * + * Copyright (C) 2016 Intel Corporation + * + * Author: Fenghua Yu + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * More information about RDT be found in the Intel (R) x86 Architecture + * Software Developer Manual. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include + +#include + +#include + +DEFINE_STATIC_KEY_FALSE(rdt_enable_key); +struct kernfs_root *rdt_root; +struct rdtgroup rdtgroup_default; +LIST_HEAD(rdt_all_groups); + +static void l3_qos_cfg_update(void *arg) +{ + bool *enable = arg; + + wrmsrl(IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL); +} + +static int set_l3_qos_cfg(struct rdt_resource *r, bool enable) +{ + cpumask_var_t cpu_mask; + struct rdt_domain *d; + int cpu; + + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) + return -ENOMEM; + + list_for_each_entry(d, &r->domains, list) { + /* Pick one CPU from each domain instance to update MSR */ + cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); + } + cpu = get_cpu(); + /* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */ + if (cpumask_test_cpu(cpu, cpu_mask)) + l3_qos_cfg_update(&enable); + /* Update QOS_CFG MSR on all other cpus in cpu_mask. */ + smp_call_function_many(cpu_mask, l3_qos_cfg_update, &enable, 1); + put_cpu(); + + free_cpumask_var(cpu_mask); + + return 0; +} + +static int cdp_enable(void) +{ + struct rdt_resource *r_l3data = &rdt_resources_all[RDT_RESOURCE_L3DATA]; + struct rdt_resource *r_l3code = &rdt_resources_all[RDT_RESOURCE_L3CODE]; + struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3]; + int ret; + + if (!r_l3->capable || !r_l3data->capable || !r_l3code->capable) + return -EINVAL; + + ret = set_l3_qos_cfg(r_l3, true); + if (!ret) { + r_l3->enabled = false; + r_l3data->enabled = true; + r_l3code->enabled = true; + } + return ret; +} + +static void cdp_disable(void) +{ + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; + + r->enabled = r->capable; + + if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled) { + rdt_resources_all[RDT_RESOURCE_L3DATA].enabled = false; + rdt_resources_all[RDT_RESOURCE_L3CODE].enabled = false; + set_l3_qos_cfg(r, false); + } +} + +static int parse_rdtgroupfs_options(char *data) +{ + char *token, *o = data; + int ret = 0; + + while ((token = strsep(&o, ",")) != NULL) { + if (!*token) + return -EINVAL; + + if (!strcmp(token, "cdp")) + ret = cdp_enable(); + } + + return ret; +} + +static struct dentry *rdt_mount(struct file_system_type *fs_type, + int flags, const char *unused_dev_name, + void *data) +{ + struct dentry *dentry; + int ret; + + mutex_lock(&rdtgroup_mutex); + /* + * resctrl file system can only be mounted once. + */ + if (static_branch_unlikely(&rdt_enable_key)) { + dentry = ERR_PTR(-EBUSY); + goto out; + } + + ret = parse_rdtgroupfs_options(data); + if (ret) { + dentry = ERR_PTR(ret); + goto out_cdp; + } + + dentry = kernfs_mount(fs_type, flags, rdt_root, + RDTGROUP_SUPER_MAGIC, NULL); + if (IS_ERR(dentry)) + goto out_cdp; + + static_branch_enable(&rdt_enable_key); + goto out; + +out_cdp: + cdp_disable(); +out: + mutex_unlock(&rdtgroup_mutex); + + return dentry; +} + +static int reset_all_cbms(struct rdt_resource *r) +{ + struct msr_param msr_param; + cpumask_var_t cpu_mask; + struct rdt_domain *d; + int i, cpu; + + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) + return -ENOMEM; + + msr_param.res = r; + msr_param.low = 0; + msr_param.high = r->num_closid; + + /* + * Disable resource control for this resource by setting all + * CBMs in all domains to the maximum mask value. Pick one CPU + * from each domain to update the MSRs below. + */ + list_for_each_entry(d, &r->domains, list) { + cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); + + for (i = 0; i < r->num_closid; i++) + d->cbm[i] = r->max_cbm; + } + cpu = get_cpu(); + /* Update CBM on this cpu if it's in cpu_mask. */ + if (cpumask_test_cpu(cpu, cpu_mask)) + rdt_cbm_update(&msr_param); + /* Update CBM on all other cpus in cpu_mask. */ + smp_call_function_many(cpu_mask, rdt_cbm_update, &msr_param, 1); + put_cpu(); + + free_cpumask_var(cpu_mask); + + return 0; +} + +static void rdt_kill_sb(struct super_block *sb) +{ + struct rdt_resource *r; + + mutex_lock(&rdtgroup_mutex); + + /*Put everything back to default values. */ + for_each_enabled_rdt_resource(r) + reset_all_cbms(r); + cdp_disable(); + static_branch_disable(&rdt_enable_key); + kernfs_kill_sb(sb); + mutex_unlock(&rdtgroup_mutex); +} + +static struct file_system_type rdt_fs_type = { + .name = "resctrl", + .mount = rdt_mount, + .kill_sb = rdt_kill_sb, +}; + +static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = { +}; + +static int __init rdtgroup_setup_root(void) +{ + rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops, + KERNFS_ROOT_CREATE_DEACTIVATED, + &rdtgroup_default); + if (IS_ERR(rdt_root)) + return PTR_ERR(rdt_root); + + mutex_lock(&rdtgroup_mutex); + + rdtgroup_default.closid = 0; + list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups); + + rdtgroup_default.kn = rdt_root->kn; + kernfs_activate(rdtgroup_default.kn); + + mutex_unlock(&rdtgroup_mutex); + + return 0; +} + +/* + * rdtgroup_init - rdtgroup initialization + * + * Setup resctrl file system including set up root, create mount point, + * register rdtgroup filesystem, and initialize files under root directory. + * + * Return: 0 on success or -errno + */ +int __init rdtgroup_init(void) +{ + int ret = 0; + + ret = rdtgroup_setup_root(); + if (ret) + return ret; + + ret = sysfs_create_mount_point(fs_kobj, "resctrl"); + if (ret) + goto cleanup_root; + + ret = register_filesystem(&rdt_fs_type); + if (ret) + goto cleanup_mountpoint; + + return 0; + +cleanup_mountpoint: + sysfs_remove_mount_point(fs_kobj, "resctrl"); +cleanup_root: + kernfs_destroy_root(rdt_root); + + return ret; +} diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 9bd559472c92..e230af2e6855 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -57,6 +57,7 @@ #define CGROUP_SUPER_MAGIC 0x27e0eb #define CGROUP2_SUPER_MAGIC 0x63677270 +#define RDTGROUP_SUPER_MAGIC 0x7655821 #define STACK_END_MAGIC 0x57AC6E9D -- cgit v1.2.3 From 541b6fe63023f3059cf85d47ff2767a3e42a8e44 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Mon, 26 Sep 2016 10:51:18 +0300 Subject: usb: add helper to extract bits 12:11 of wMaxPacketSize According to USB Specification 2.0 table 9-4, wMaxPacketSize is a bitfield. Endpoint's maxpacket is laid out in bits 10:0. For high-speed, high-bandwidth isochronous endpoints, bits 12:11 contain a multiplier to tell us how many transactions we want to try per uframe. This means that if we want an isochronous endpoint to issue 3 transfers of 1024 bytes per uframe, wMaxPacketSize should contain the value: 1024 | (2 << 11) or 5120 (0x1400). In order to make Host and Peripheral controller drivers' life easier, we're adding a helper which returns bits 12:11. Note that no care is made WRT to checking endpoint type and gadget's speed. That's left for drivers to handle. Signed-off-by: Felipe Balbi --- include/uapi/linux/usb/ch9.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index a8acc24765fe..7628dff5fac3 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -423,6 +423,11 @@ struct usb_endpoint_descriptor { #define USB_ENDPOINT_XFER_INT 3 #define USB_ENDPOINT_MAX_ADJUSTABLE 0x80 +#define USB_EP_MAXP_MULT_SHIFT 11 +#define USB_EP_MAXP_MULT_MASK (3 << USB_EP_MAXP_MULT_SHIFT) +#define USB_EP_MAXP_MULT(m) \ + (((m) & USB_EP_MAXP_MULT_MASK) >> USB_EP_MAXP_MULT_SHIFT) + /* The USB 3.0 spec redefines bits 5:4 of bmAttributes as interrupt ep type. */ #define USB_ENDPOINT_INTRTYPE 0x30 #define USB_ENDPOINT_INTR_PERIODIC (0 << 4) @@ -630,6 +635,20 @@ static inline int usb_endpoint_maxp(const struct usb_endpoint_descriptor *epd) return __le16_to_cpu(epd->wMaxPacketSize); } +/** + * usb_endpoint_maxp_mult - get endpoint's transactional opportunities + * @epd: endpoint to be checked + * + * Return @epd's wMaxPacketSize[12:11] + 1 + */ +static inline int +usb_endpoint_maxp_mult(const struct usb_endpoint_descriptor *epd) +{ + int maxp = __le16_to_cpu(epd->wMaxPacketSize); + + return USB_EP_MAXP_MULT(maxp) + 1; +} + static inline int usb_endpoint_interrupt_type( const struct usb_endpoint_descriptor *epd) { -- 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 --- fs/nsfs.c | 2 +- include/linux/proc_fs.h | 4 ++++ include/uapi/linux/sockios.h | 1 + net/socket.c | 13 +++++++++++++ 4 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/nsfs.c b/fs/nsfs.c index 8718af895eab..8c9fb29c6673 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -118,7 +118,7 @@ again: return ret; } -static int open_related_ns(struct ns_common *ns, +int open_related_ns(struct ns_common *ns, struct ns_common *(*get_ns)(struct ns_common *ns)) { struct path path = {}; diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index b97bf2ef996e..368c7ad06ae5 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -82,4 +82,8 @@ static inline struct proc_dir_entry *proc_net_mkdir( return proc_mkdir_data(name, 0, parent, net); } +struct ns_common; +int open_related_ns(struct ns_common *ns, + struct ns_common *(*get_ns)(struct ns_common *ns)); + #endif /* _LINUX_PROC_FS_H */ 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 */ diff --git a/net/socket.c b/net/socket.c index 5a9bf5ee2464..970a7ea3fc4a 100644 --- a/net/socket.c +++ b/net/socket.c @@ -877,6 +877,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, * what to do with it - that's up to the protocol still. */ +static struct ns_common *get_net_ns(struct ns_common *ns) +{ + return &get_net(container_of(ns, struct net, ns))->ns; +} + static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { struct socket *sock; @@ -945,6 +950,13 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) err = dlci_ioctl_hook(cmd, argp); mutex_unlock(&dlci_ioctl_mutex); break; + case SIOCGSKNS: + err = -EPERM; + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + break; + + err = open_related_ns(&net->ns, get_net_ns); + break; default: err = sock_do_ioctl(net, sock, cmd, arg); break; @@ -3093,6 +3105,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCSIFVLAN: case SIOCADDDLCI: case SIOCDELDLCI: + case SIOCGSKNS: return sock_ioctl(file, cmd, arg); case SIOCGIFFLAGS: -- 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 --- drivers/net/tun.c | 2 +- include/uapi/linux/sockios.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 9142db847ee1..1588469844e7 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1985,7 +1985,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, int le; int ret; - if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == 0x89) { + if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == SOCK_IOC_TYPE) { if (copy_from_user(&ifr, argp, ifreq_len)) return -EFAULT; } else { 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/net/netfilter/nft_fib.h | 31 ++++ include/uapi/linux/netfilter/nf_tables.h | 36 ++++ net/ipv4/netfilter/Kconfig | 8 + net/ipv4/netfilter/Makefile | 1 + net/ipv4/netfilter/nft_fib_ipv4.c | 238 ++++++++++++++++++++++++++ net/ipv6/netfilter/Kconfig | 8 + net/ipv6/netfilter/Makefile | 1 + net/ipv6/netfilter/nft_fib_ipv6.c | 275 +++++++++++++++++++++++++++++++ net/netfilter/Kconfig | 13 ++ net/netfilter/Makefile | 2 + net/netfilter/nft_fib.c | 159 ++++++++++++++++++ net/netfilter/nft_fib_inet.c | 82 +++++++++ 12 files changed, 854 insertions(+) create mode 100644 include/net/netfilter/nft_fib.h create mode 100644 net/ipv4/netfilter/nft_fib_ipv4.c create mode 100644 net/ipv6/netfilter/nft_fib_ipv6.c create mode 100644 net/netfilter/nft_fib.c create mode 100644 net/netfilter/nft_fib_inet.c (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h new file mode 100644 index 000000000000..cbedda077db2 --- /dev/null +++ b/include/net/netfilter/nft_fib.h @@ -0,0 +1,31 @@ +#ifndef _NFT_FIB_H_ +#define _NFT_FIB_H_ + +struct nft_fib { + enum nft_registers dreg:8; + u8 result; + u32 flags; +}; + +extern const struct nla_policy nft_fib_policy[]; + +int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr); +int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nlattr * const tb[]); +int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nft_data **data); + + +void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt); +void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt); + +void nft_fib6_eval_type(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt); +void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt); + +void nft_fib_store_result(void *reg, enum nft_fib_result r, + const struct nft_pktinfo *pkt, int index); +#endif 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 * diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index d613309e3e5d..f80bb8f457c8 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -54,6 +54,14 @@ config NFT_DUP_IPV4 help This module enables IPv4 packet duplication support for nf_tables. +config NFT_FIB_IPV4 + select NFT_FIB + tristate "nf_tables fib / ip route lookup support" + help + This module enables IPv4 FIB lookups, e.g. for reverse path filtering. + It also allows query of the FIB for the route type, e.g. local, unicast, + multicast or blackhole. + endif # NF_TABLES_IPV4 config NF_TABLES_ARP diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 853328f8fd05..59d7786ddce1 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -34,6 +34,7 @@ obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o +obj-$(CONFIG_NFT_FIB_IPV4) += nft_fib_ipv4.o obj-$(CONFIG_NFT_MASQ_IPV4) += nft_masq_ipv4.o obj-$(CONFIG_NFT_REDIR_IPV4) += nft_redir_ipv4.o obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c new file mode 100644 index 000000000000..db91fd42db67 --- /dev/null +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -0,0 +1,238 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +/* don't try to find route from mcast/bcast/zeronet */ +static __be32 get_saddr(__be32 addr) +{ + if (ipv4_is_multicast(addr) || ipv4_is_lbcast(addr) || + ipv4_is_zeronet(addr)) + return 0; + return addr; +} + +static bool fib4_is_local(const struct sk_buff *skb) +{ + const struct rtable *rt = skb_rtable(skb); + + return rt && (rt->rt_flags & RTCF_LOCAL); +} + +#define DSCP_BITS 0xfc + +void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_fib *priv = nft_expr_priv(expr); + u32 *dst = ®s->data[priv->dreg]; + const struct net_device *dev = NULL; + const struct iphdr *iph; + __be32 addr; + + if (priv->flags & NFTA_FIB_F_IIF) + dev = pkt->in; + else if (priv->flags & NFTA_FIB_F_OIF) + dev = pkt->out; + + iph = ip_hdr(pkt->skb); + if (priv->flags & NFTA_FIB_F_DADDR) + addr = iph->daddr; + else + addr = iph->saddr; + + *dst = inet_dev_addr_type(pkt->net, dev, addr); +} +EXPORT_SYMBOL_GPL(nft_fib4_eval_type); + +static int get_ifindex(const struct net_device *dev) +{ + return dev ? dev->ifindex : 0; +} + +void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_fib *priv = nft_expr_priv(expr); + u32 *dest = ®s->data[priv->dreg]; + const struct iphdr *iph; + struct fib_result res; + struct flowi4 fl4 = { + .flowi4_scope = RT_SCOPE_UNIVERSE, + .flowi4_iif = LOOPBACK_IFINDEX, + }; + const struct net_device *oif; + struct net_device *found; +#ifdef CONFIG_IP_ROUTE_MULTIPATH + int i; +#endif + + /* + * Do not set flowi4_oif, it restricts results (for example, asking + * for oif 3 will get RTN_UNICAST result even if the daddr exits + * on another interface. + * + * Search results for the desired outinterface instead. + */ + if (priv->flags & NFTA_FIB_F_OIF) + oif = pkt->out; + else if (priv->flags & NFTA_FIB_F_IIF) + oif = pkt->in; + else + oif = NULL; + + if (pkt->hook == NF_INET_PRE_ROUTING && fib4_is_local(pkt->skb)) { + nft_fib_store_result(dest, priv->result, pkt, LOOPBACK_IFINDEX); + return; + } + + iph = ip_hdr(pkt->skb); + if (ipv4_is_multicast(iph->daddr) && + ipv4_is_zeronet(iph->saddr) && + ipv4_is_local_multicast(iph->daddr)) { + nft_fib_store_result(dest, priv->result, pkt, + get_ifindex(pkt->skb->dev)); + return; + } + + if (priv->flags & NFTA_FIB_F_MARK) + fl4.flowi4_mark = pkt->skb->mark; + + fl4.flowi4_tos = iph->tos & DSCP_BITS; + + if (priv->flags & NFTA_FIB_F_DADDR) { + fl4.daddr = iph->daddr; + fl4.saddr = get_saddr(iph->saddr); + } else { + fl4.daddr = iph->saddr; + fl4.saddr = get_saddr(iph->daddr); + } + + if (fib_lookup(pkt->net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE)) + return; + + switch (res.type) { + case RTN_UNICAST: + break; + case RTN_LOCAL: /* should not appear here, see fib4_is_local() above */ + return; + default: + break; + } + + if (!oif) { + found = FIB_RES_DEV(res); + goto ok; + } + +#ifdef CONFIG_IP_ROUTE_MULTIPATH + for (i = 0; i < res.fi->fib_nhs; i++) { + struct fib_nh *nh = &res.fi->fib_nh[i]; + + if (nh->nh_dev == oif) { + found = nh->nh_dev; + goto ok; + } + } + return; +#else + found = FIB_RES_DEV(res); + if (found != oif) + return; +#endif +ok: + switch (priv->result) { + case NFT_FIB_RESULT_OIF: + *dest = found->ifindex; + break; + case NFT_FIB_RESULT_OIFNAME: + strncpy((char *)dest, found->name, IFNAMSIZ); + break; + default: + WARN_ON_ONCE(1); + break; + } +} +EXPORT_SYMBOL_GPL(nft_fib4_eval); + +static struct nft_expr_type nft_fib4_type; + +static const struct nft_expr_ops nft_fib4_type_ops = { + .type = &nft_fib4_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)), + .eval = nft_fib4_eval_type, + .init = nft_fib_init, + .dump = nft_fib_dump, + .validate = nft_fib_validate, +}; + +static const struct nft_expr_ops nft_fib4_ops = { + .type = &nft_fib4_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)), + .eval = nft_fib4_eval, + .init = nft_fib_init, + .dump = nft_fib_dump, + .validate = nft_fib_validate, +}; + +static const struct nft_expr_ops * +nft_fib4_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + enum nft_fib_result result; + + if (!tb[NFTA_FIB_RESULT]) + return ERR_PTR(-EINVAL); + + result = htonl(nla_get_be32(tb[NFTA_FIB_RESULT])); + + switch (result) { + case NFT_FIB_RESULT_OIF: + return &nft_fib4_ops; + case NFT_FIB_RESULT_OIFNAME: + return &nft_fib4_ops; + case NFT_FIB_RESULT_ADDRTYPE: + return &nft_fib4_type_ops; + default: + return ERR_PTR(-EOPNOTSUPP); + } +} + +static struct nft_expr_type nft_fib4_type __read_mostly = { + .name = "fib", + .select_ops = &nft_fib4_select_ops, + .policy = nft_fib_policy, + .maxattr = NFTA_FIB_MAX, + .family = NFPROTO_IPV4, + .owner = THIS_MODULE, +}; + +static int __init nft_fib4_module_init(void) +{ + return nft_register_expr(&nft_fib4_type); +} + +static void __exit nft_fib4_module_exit(void) +{ + nft_unregister_expr(&nft_fib4_type); +} + +module_init(nft_fib4_module_init); +module_exit(nft_fib4_module_exit); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Florian Westphal "); +MODULE_ALIAS_NFT_AF_EXPR(2, "fib"); diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index e10a04c9cdc7..144f1de33836 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -54,6 +54,14 @@ config NFT_DUP_IPV6 help This module enables IPv6 packet duplication support for nf_tables. +config NFT_FIB_IPV6 + tristate "nf_tables fib / ipv6 route lookup support" + select NFT_FIB + help + This module enables IPv6 FIB lookups, e.g. for reverse path filtering. + It also allows query of the FIB for the route type, e.g. local, unicast, + multicast or blackhole. + endif # NF_TABLES_IPV6 endif # NF_TABLES diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index b4f7d0b4e2af..7984f3071f05 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -40,6 +40,7 @@ obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o obj-$(CONFIG_NFT_MASQ_IPV6) += nft_masq_ipv6.o obj-$(CONFIG_NFT_REDIR_IPV6) += nft_redir_ipv6.o obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o +obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o # matches obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c new file mode 100644 index 000000000000..ff1f1b6b4a4a --- /dev/null +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -0,0 +1,275 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +static bool fib6_is_local(const struct sk_buff *skb) +{ + const struct rt6_info *rt = (const void *)skb_dst(skb); + + return rt && (rt->rt6i_flags & RTF_LOCAL); +} + +static int get_ifindex(const struct net_device *dev) +{ + return dev ? dev->ifindex : 0; +} + +static int nft_fib6_flowi_init(struct flowi6 *fl6, const struct nft_fib *priv, + const struct nft_pktinfo *pkt, + const struct net_device *dev) +{ + const struct ipv6hdr *iph = ipv6_hdr(pkt->skb); + int lookup_flags = 0; + + if (priv->flags & NFTA_FIB_F_DADDR) { + fl6->daddr = iph->daddr; + fl6->saddr = iph->saddr; + } else { + fl6->daddr = iph->saddr; + fl6->saddr = iph->daddr; + } + + if (ipv6_addr_type(&fl6->daddr) & IPV6_ADDR_LINKLOCAL) { + lookup_flags |= RT6_LOOKUP_F_IFACE; + fl6->flowi6_oif = get_ifindex(dev ? dev : pkt->skb->dev); + } + + if (ipv6_addr_type(&fl6->saddr) & IPV6_ADDR_UNICAST) + lookup_flags |= RT6_LOOKUP_F_HAS_SADDR; + + if (priv->flags & NFTA_FIB_F_MARK) + fl6->flowi6_mark = pkt->skb->mark; + + fl6->flowlabel = (*(__be32 *)iph) & IPV6_FLOWINFO_MASK; + + return lookup_flags; +} + +static u32 __nft_fib6_eval_type(const struct nft_fib *priv, + const struct nft_pktinfo *pkt) +{ + const struct net_device *dev = NULL; + const struct nf_ipv6_ops *v6ops; + const struct nf_afinfo *afinfo; + int route_err, addrtype; + struct rt6_info *rt; + struct flowi6 fl6 = { + .flowi6_iif = LOOPBACK_IFINDEX, + .flowi6_proto = pkt->tprot, + }; + u32 ret = 0; + + afinfo = nf_get_afinfo(NFPROTO_IPV6); + if (!afinfo) + return RTN_UNREACHABLE; + + if (priv->flags & NFTA_FIB_F_IIF) + dev = pkt->in; + else if (priv->flags & NFTA_FIB_F_OIF) + dev = pkt->out; + + nft_fib6_flowi_init(&fl6, priv, pkt, dev); + + v6ops = nf_get_ipv6_ops(); + if (dev && v6ops && v6ops->chk_addr(pkt->net, &fl6.daddr, dev, true)) + ret = RTN_LOCAL; + + route_err = afinfo->route(pkt->net, (struct dst_entry **)&rt, + flowi6_to_flowi(&fl6), false); + if (route_err) + goto err; + + if (rt->rt6i_flags & RTF_REJECT) { + route_err = rt->dst.error; + dst_release(&rt->dst); + goto err; + } + + if (ipv6_anycast_destination((struct dst_entry *)rt, &fl6.daddr)) + ret = RTN_ANYCAST; + else if (!dev && rt->rt6i_flags & RTF_LOCAL) + ret = RTN_LOCAL; + + dst_release(&rt->dst); + + if (ret) + return ret; + + addrtype = ipv6_addr_type(&fl6.daddr); + + if (addrtype & IPV6_ADDR_MULTICAST) + return RTN_MULTICAST; + if (addrtype & IPV6_ADDR_UNICAST) + return RTN_UNICAST; + + return RTN_UNSPEC; + err: + switch (route_err) { + case -EINVAL: + return RTN_BLACKHOLE; + case -EACCES: + return RTN_PROHIBIT; + case -EAGAIN: + return RTN_THROW; + default: + break; + } + + return RTN_UNREACHABLE; +} + +void nft_fib6_eval_type(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_fib *priv = nft_expr_priv(expr); + u32 *dest = ®s->data[priv->dreg]; + + *dest = __nft_fib6_eval_type(priv, pkt); +} +EXPORT_SYMBOL_GPL(nft_fib6_eval_type); + +void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_fib *priv = nft_expr_priv(expr); + const struct net_device *oif = NULL; + u32 *dest = ®s->data[priv->dreg]; + struct flowi6 fl6 = { + .flowi6_iif = LOOPBACK_IFINDEX, + .flowi6_proto = pkt->tprot, + }; + struct rt6_info *rt; + int lookup_flags; + + if (priv->flags & NFTA_FIB_F_IIF) + oif = pkt->in; + else if (priv->flags & NFTA_FIB_F_OIF) + oif = pkt->out; + + lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif); + + if (pkt->hook == NF_INET_PRE_ROUTING && fib6_is_local(pkt->skb)) { + nft_fib_store_result(dest, priv->result, pkt, LOOPBACK_IFINDEX); + return; + } + + *dest = 0; + again: + rt = (void *)ip6_route_lookup(pkt->net, &fl6, lookup_flags); + if (rt->dst.error) + goto put_rt_err; + + /* Should not see RTF_LOCAL here */ + if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL)) + goto put_rt_err; + + if (oif && oif != rt->rt6i_idev->dev) { + /* multipath route? Try again with F_IFACE */ + if ((lookup_flags & RT6_LOOKUP_F_IFACE) == 0) { + lookup_flags |= RT6_LOOKUP_F_IFACE; + fl6.flowi6_oif = oif->ifindex; + ip6_rt_put(rt); + goto again; + } + } + + switch (priv->result) { + case NFT_FIB_RESULT_OIF: + *dest = rt->rt6i_idev->dev->ifindex; + break; + case NFT_FIB_RESULT_OIFNAME: + strncpy((char *)dest, rt->rt6i_idev->dev->name, IFNAMSIZ); + break; + default: + WARN_ON_ONCE(1); + break; + } + + put_rt_err: + ip6_rt_put(rt); +} +EXPORT_SYMBOL_GPL(nft_fib6_eval); + +static struct nft_expr_type nft_fib6_type; + +static const struct nft_expr_ops nft_fib6_type_ops = { + .type = &nft_fib6_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)), + .eval = nft_fib6_eval_type, + .init = nft_fib_init, + .dump = nft_fib_dump, + .validate = nft_fib_validate, +}; + +static const struct nft_expr_ops nft_fib6_ops = { + .type = &nft_fib6_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)), + .eval = nft_fib6_eval, + .init = nft_fib_init, + .dump = nft_fib_dump, + .validate = nft_fib_validate, +}; + +static const struct nft_expr_ops * +nft_fib6_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + enum nft_fib_result result; + + if (!tb[NFTA_FIB_RESULT]) + return ERR_PTR(-EINVAL); + + result = htonl(nla_get_be32(tb[NFTA_FIB_RESULT])); + + switch (result) { + case NFT_FIB_RESULT_OIF: + return &nft_fib6_ops; + case NFT_FIB_RESULT_OIFNAME: + return &nft_fib6_ops; + case NFT_FIB_RESULT_ADDRTYPE: + return &nft_fib6_type_ops; + default: + return ERR_PTR(-EOPNOTSUPP); + } +} + +static struct nft_expr_type nft_fib6_type __read_mostly = { + .name = "fib", + .select_ops = &nft_fib6_select_ops, + .policy = nft_fib_policy, + .maxattr = NFTA_FIB_MAX, + .family = NFPROTO_IPV6, + .owner = THIS_MODULE, +}; + +static int __init nft_fib6_module_init(void) +{ + return nft_register_expr(&nft_fib6_type); +} + +static void __exit nft_fib6_module_exit(void) +{ + nft_unregister_expr(&nft_fib6_type); +} +module_init(nft_fib6_module_init); +module_exit(nft_fib6_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Florian Westphal "); +MODULE_ALIAS_NFT_AF_EXPR(10, "fib"); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index e8d56d9a4df2..9bcf899ce16e 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -581,6 +581,19 @@ config NFT_HASH This option adds the "hash" expression that you can use to perform a hash operation on registers. +config NFT_FIB + tristate + +config NFT_FIB_INET + depends on NF_TABLES_INET + depends on NFT_FIB_IPV4 + depends on NFT_FIB_IPV6 + tristate "Netfilter nf_tables fib inet support" + help + This option allows using the FIB expression from the inet table. + The lookup will be delegated to the IPv4 or IPv6 FIB depending + on the protocol of the packet. + if NF_TABLES_NETDEV config NF_DUP_NETDEV diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index c23c3c84416f..8faa36c0686d 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -96,6 +96,8 @@ obj-$(CONFIG_NFT_LOG) += nft_log.o obj-$(CONFIG_NFT_MASQ) += nft_masq.o obj-$(CONFIG_NFT_REDIR) += nft_redir.o obj-$(CONFIG_NFT_HASH) += nft_hash.o +obj-$(CONFIG_NFT_FIB) += nft_fib.o +obj-$(CONFIG_NFT_FIB_INET) += nft_fib_inet.o # nf_tables netdev obj-$(CONFIG_NFT_DUP_NETDEV) += nft_dup_netdev.o diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c new file mode 100644 index 000000000000..4944a8b7f7a7 --- /dev/null +++ b/net/netfilter/nft_fib.c @@ -0,0 +1,159 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Generic part shared by ipv4 and ipv6 backends. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +const struct nla_policy nft_fib_policy[NFTA_FIB_MAX + 1] = { + [NFTA_FIB_DREG] = { .type = NLA_U32 }, + [NFTA_FIB_RESULT] = { .type = NLA_U32 }, + [NFTA_FIB_FLAGS] = { .type = NLA_U32 }, +}; +EXPORT_SYMBOL(nft_fib_policy); + +#define NFTA_FIB_F_ALL (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR | \ + NFTA_FIB_F_MARK | NFTA_FIB_F_IIF | NFTA_FIB_F_OIF) + +int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nft_data **data) +{ + const struct nft_fib *priv = nft_expr_priv(expr); + unsigned int hooks; + + switch (priv->result) { + case NFT_FIB_RESULT_OIF: /* fallthrough */ + case NFT_FIB_RESULT_OIFNAME: + hooks = (1 << NF_INET_PRE_ROUTING); + break; + case NFT_FIB_RESULT_ADDRTYPE: + if (priv->flags & NFTA_FIB_F_IIF) + hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD); + else if (priv->flags & NFTA_FIB_F_OIF) + hooks = (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_FORWARD); + else + hooks = (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_POST_ROUTING); + + break; + default: + return -EINVAL; + } + + return nft_chain_validate_hooks(ctx->chain, hooks); +} +EXPORT_SYMBOL_GPL(nft_fib_validate); + +int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_fib *priv = nft_expr_priv(expr); + unsigned int len; + int err; + + if (!tb[NFTA_FIB_DREG] || !tb[NFTA_FIB_RESULT] || !tb[NFTA_FIB_FLAGS]) + return -EINVAL; + + priv->flags = ntohl(nla_get_be32(tb[NFTA_FIB_FLAGS])); + + if (priv->flags == 0 || (priv->flags & ~NFTA_FIB_F_ALL)) + return -EINVAL; + + if ((priv->flags & (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR)) == + (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR)) + return -EINVAL; + if ((priv->flags & (NFTA_FIB_F_IIF | NFTA_FIB_F_OIF)) == + (NFTA_FIB_F_IIF | NFTA_FIB_F_OIF)) + return -EINVAL; + if ((priv->flags & (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR)) == 0) + return -EINVAL; + + priv->result = htonl(nla_get_be32(tb[NFTA_FIB_RESULT])); + priv->dreg = nft_parse_register(tb[NFTA_FIB_DREG]); + + switch (priv->result) { + case NFT_FIB_RESULT_OIF: + if (priv->flags & NFTA_FIB_F_OIF) + return -EINVAL; + len = sizeof(int); + break; + case NFT_FIB_RESULT_OIFNAME: + if (priv->flags & NFTA_FIB_F_OIF) + return -EINVAL; + len = IFNAMSIZ; + break; + case NFT_FIB_RESULT_ADDRTYPE: + len = sizeof(u32); + break; + default: + return -EINVAL; + } + + err = nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, len); + if (err < 0) + return err; + + return nft_fib_validate(ctx, expr, NULL); +} +EXPORT_SYMBOL_GPL(nft_fib_init); + +int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_fib *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_FIB_DREG, priv->dreg)) + return -1; + + if (nla_put_be32(skb, NFTA_FIB_RESULT, htonl(priv->result))) + return -1; + + if (nla_put_be32(skb, NFTA_FIB_FLAGS, htonl(priv->flags))) + return -1; + + return 0; +} +EXPORT_SYMBOL_GPL(nft_fib_dump); + +void nft_fib_store_result(void *reg, enum nft_fib_result r, + const struct nft_pktinfo *pkt, int index) +{ + struct net_device *dev; + u32 *dreg = reg; + + switch (r) { + case NFT_FIB_RESULT_OIF: + *dreg = index; + break; + case NFT_FIB_RESULT_OIFNAME: + dev = dev_get_by_index_rcu(pkt->net, index); + strncpy(reg, dev ? dev->name : "", IFNAMSIZ); + break; + default: + WARN_ON_ONCE(1); + *dreg = 0; + break; + } +} +EXPORT_SYMBOL_GPL(nft_fib_store_result); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Florian Westphal "); diff --git a/net/netfilter/nft_fib_inet.c b/net/netfilter/nft_fib_inet.c new file mode 100644 index 000000000000..fe8943b572b7 --- /dev/null +++ b/net/netfilter/nft_fib_inet.c @@ -0,0 +1,82 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +static void nft_fib_inet_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_fib *priv = nft_expr_priv(expr); + + switch (pkt->pf) { + case NFPROTO_IPV4: + switch (priv->result) { + case NFT_FIB_RESULT_OIF: + case NFT_FIB_RESULT_OIFNAME: + return nft_fib4_eval(expr, regs, pkt); + case NFT_FIB_RESULT_ADDRTYPE: + return nft_fib4_eval_type(expr, regs, pkt); + } + break; + case NFPROTO_IPV6: + switch (priv->result) { + case NFT_FIB_RESULT_OIF: + case NFT_FIB_RESULT_OIFNAME: + return nft_fib6_eval(expr, regs, pkt); + case NFT_FIB_RESULT_ADDRTYPE: + return nft_fib6_eval_type(expr, regs, pkt); + } + break; + } + + regs->verdict.code = NF_DROP; +} + +static struct nft_expr_type nft_fib_inet_type; +static const struct nft_expr_ops nft_fib_inet_ops = { + .type = &nft_fib_inet_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)), + .eval = nft_fib_inet_eval, + .init = nft_fib_init, + .dump = nft_fib_dump, + .validate = nft_fib_validate, +}; + +static struct nft_expr_type nft_fib_inet_type __read_mostly = { + .family = NFPROTO_INET, + .name = "fib", + .ops = &nft_fib_inet_ops, + .policy = nft_fib_policy, + .maxattr = NFTA_FIB_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_fib_inet_module_init(void) +{ + return nft_register_expr(&nft_fib_inet_type); +} + +static void __exit nft_fib_inet_module_exit(void) +{ + nft_unregister_expr(&nft_fib_inet_type); +} + +module_init(nft_fib_inet_module_init); +module_exit(nft_fib_inet_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Florian Westphal "); +MODULE_ALIAS_NFT_AF_EXPR(1, "fib"); -- 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 ++++++ net/netfilter/Kconfig | 6 ++ net/netfilter/Makefile | 1 + net/netfilter/nft_rt.c | 153 +++++++++++++++++++++++++++++++ 4 files changed, 187 insertions(+) create mode 100644 net/netfilter/nft_rt.c (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 * diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index ed00ec114ea2..44410d30d461 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -478,6 +478,12 @@ config NFT_META This option adds the "meta" expression that you can use to match and to set packet metainformation such as the packet mark. +config NFT_RT + tristate "Netfilter nf_tables routing module" + help + This option adds the "rt" expression that you can use to match + packet routing information such as the packet nexthop. + config NFT_NUMGEN tristate "Netfilter nf_tables number generator module" help diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 8edd791743fe..5bbf767672ec 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -84,6 +84,7 @@ obj-$(CONFIG_NF_TABLES_NETDEV) += nf_tables_netdev.o obj-$(CONFIG_NFT_COMPAT) += nft_compat.o obj-$(CONFIG_NFT_EXTHDR) += nft_exthdr.o obj-$(CONFIG_NFT_META) += nft_meta.o +obj-$(CONFIG_NFT_RT) += nft_rt.o obj-$(CONFIG_NFT_NUMGEN) += nft_numgen.o obj-$(CONFIG_NFT_CT) += nft_ct.o obj-$(CONFIG_NFT_LIMIT) += nft_limit.o diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c new file mode 100644 index 000000000000..9e5ec1f67020 --- /dev/null +++ b/net/netfilter/nft_rt.c @@ -0,0 +1,153 @@ +/* + * Copyright (c) 2016 Anders K. Pedersen + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct nft_rt { + enum nft_rt_keys key:8; + enum nft_registers dreg:8; +}; + +void nft_rt_get_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_rt *priv = nft_expr_priv(expr); + const struct sk_buff *skb = pkt->skb; + u32 *dest = ®s->data[priv->dreg]; + const struct dst_entry *dst; + + dst = skb_dst(skb); + if (!dst) + goto err; + + switch (priv->key) { +#ifdef CONFIG_IP_ROUTE_CLASSID + case NFT_RT_CLASSID: + *dest = dst->tclassid; + break; +#endif + case NFT_RT_NEXTHOP4: + if (pkt->pf != NFPROTO_IPV4) + goto err; + + *dest = rt_nexthop((const struct rtable *)dst, + ip_hdr(skb)->daddr); + break; + case NFT_RT_NEXTHOP6: + if (pkt->pf != NFPROTO_IPV6) + goto err; + + memcpy(dest, rt6_nexthop((struct rt6_info *)dst, + &ipv6_hdr(skb)->daddr), + sizeof(struct in6_addr)); + break; + default: + WARN_ON(1); + goto err; + } + return; + +err: + regs->verdict.code = NFT_BREAK; +} + +const struct nla_policy nft_rt_policy[NFTA_RT_MAX + 1] = { + [NFTA_RT_DREG] = { .type = NLA_U32 }, + [NFTA_RT_KEY] = { .type = NLA_U32 }, +}; + +int nft_rt_get_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_rt *priv = nft_expr_priv(expr); + unsigned int len; + + if (tb[NFTA_RT_KEY] == NULL || + tb[NFTA_RT_DREG] == NULL) + return -EINVAL; + + priv->key = ntohl(nla_get_be32(tb[NFTA_RT_KEY])); + switch (priv->key) { +#ifdef CONFIG_IP_ROUTE_CLASSID + case NFT_RT_CLASSID: +#endif + case NFT_RT_NEXTHOP4: + len = sizeof(u32); + break; + case NFT_RT_NEXTHOP6: + len = sizeof(struct in6_addr); + break; + default: + return -EOPNOTSUPP; + } + + priv->dreg = nft_parse_register(tb[NFTA_RT_DREG]); + return nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, len); +} + +int nft_rt_get_dump(struct sk_buff *skb, + const struct nft_expr *expr) +{ + const struct nft_rt *priv = nft_expr_priv(expr); + + if (nla_put_be32(skb, NFTA_RT_KEY, htonl(priv->key))) + goto nla_put_failure; + if (nft_dump_register(skb, NFTA_RT_DREG, priv->dreg)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static struct nft_expr_type nft_rt_type; +static const struct nft_expr_ops nft_rt_get_ops = { + .type = &nft_rt_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_rt)), + .eval = nft_rt_get_eval, + .init = nft_rt_get_init, + .dump = nft_rt_get_dump, +}; + +static struct nft_expr_type nft_rt_type __read_mostly = { + .name = "rt", + .ops = &nft_rt_get_ops, + .policy = nft_rt_policy, + .maxattr = NFTA_RT_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_rt_module_init(void) +{ + return nft_register_expr(&nft_rt_type); +} + +static void __exit nft_rt_module_exit(void) +{ + nft_unregister_expr(&nft_rt_type); +} + +module_init(nft_rt_module_init); +module_exit(nft_rt_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Anders K. Pedersen "); +MODULE_ALIAS_NFT_EXPR("rt"); -- cgit v1.2.3 From abb621844f6a0c93bbc934f9a096752c4c1c5722 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Wed, 28 Sep 2016 13:42:17 +0300 Subject: usb: ch9: make usb_endpoint_maxp() return only packet size Now that we have a helper to gather periodic endpoints' multiplier bits from wMaxPacketSize and every driver is using it, we can safely make sure that usb_endpoint_maxp() returns only bits 10:0 of wMaxPacketSize which is where the actual packet size lies. Signed-off-by: Felipe Balbi --- include/uapi/linux/usb/ch9.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index 7628dff5fac3..2c5d7c4a69e3 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -423,6 +423,7 @@ struct usb_endpoint_descriptor { #define USB_ENDPOINT_XFER_INT 3 #define USB_ENDPOINT_MAX_ADJUSTABLE 0x80 +#define USB_ENDPOINT_MAXP_MASK 0x07ff #define USB_EP_MAXP_MULT_SHIFT 11 #define USB_EP_MAXP_MULT_MASK (3 << USB_EP_MAXP_MULT_SHIFT) #define USB_EP_MAXP_MULT(m) \ @@ -628,11 +629,11 @@ static inline int usb_endpoint_is_isoc_out( * usb_endpoint_maxp - get endpoint's max packet size * @epd: endpoint to be checked * - * Returns @epd's max packet + * Returns @epd's max packet bits [10:0] */ static inline int usb_endpoint_maxp(const struct usb_endpoint_descriptor *epd) { - return __le16_to_cpu(epd->wMaxPacketSize); + return __le16_to_cpu(epd->wMaxPacketSize) & USB_ENDPOINT_MAXP_MASK; } /** -- 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 +- net/bridge/br_netfilter_hooks.c | 6 ++++-- net/netfilter/core.c | 2 +- 3 files changed, 6 insertions(+), 4 deletions(-) (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 diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index d0d66faebe90..7e3645fa6339 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -845,8 +845,10 @@ static unsigned int ip_sabotage_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - if (skb->nf_bridge && !skb->nf_bridge->in_prerouting) - return NF_STOP; + if (skb->nf_bridge && !skb->nf_bridge->in_prerouting) { + state->okfn(state->net, state->sk, skb); + return NF_STOLEN; + } return NF_ACCEPT; } diff --git a/net/netfilter/core.c b/net/netfilter/core.c index cb0232c11bc8..14f97b624f98 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -333,7 +333,7 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state) entry = rcu_dereference(state->hook_entries); next_hook: verdict = nf_iterate(skb, state, &entry); - if (verdict == NF_ACCEPT || verdict == NF_STOP) { + if (verdict == NF_ACCEPT) { ret = 1; } else if ((verdict & NF_VERDICT_MASK) == NF_DROP) { kfree_skb(skb); -- 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/net/inet_sock.h | 1 + include/uapi/linux/in.h | 1 + net/ipv4/ip_sockglue.c | 26 ++++++++++++++++++++++++++ 3 files changed, 28 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 236a81034fef..c9cff977a7fb 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -228,6 +228,7 @@ struct inet_sock { #define IP_CMSG_PASSSEC BIT(5) #define IP_CMSG_ORIGDSTADDR BIT(6) #define IP_CMSG_CHECKSUM BIT(7) +#define IP_CMSG_RECVFRAGSIZE BIT(8) /** * sk_to_full_sk - Access to a full socket 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 */ diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index b8a2d63d1fb8..ecbaae200131 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -97,6 +97,17 @@ static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb) put_cmsg(msg, SOL_IP, IP_RETOPTS, opt->optlen, opt->__data); } +static void ip_cmsg_recv_fragsize(struct msghdr *msg, struct sk_buff *skb) +{ + int val; + + if (IPCB(skb)->frag_max_size == 0) + return; + + val = IPCB(skb)->frag_max_size; + put_cmsg(msg, SOL_IP, IP_RECVFRAGSIZE, sizeof(val), &val); +} + static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb, int tlen, int offset) { @@ -218,6 +229,9 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, if (flags & IP_CMSG_CHECKSUM) ip_cmsg_recv_checksum(msg, skb, tlen, offset); + + if (flags & IP_CMSG_RECVFRAGSIZE) + ip_cmsg_recv_fragsize(msg, skb); } EXPORT_SYMBOL(ip_cmsg_recv_offset); @@ -614,6 +628,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, case IP_MULTICAST_LOOP: case IP_RECVORIGDSTADDR: case IP_CHECKSUM: + case IP_RECVFRAGSIZE: if (optlen >= sizeof(int)) { if (get_user(val, (int __user *) optval)) return -EFAULT; @@ -726,6 +741,14 @@ static int do_ip_setsockopt(struct sock *sk, int level, } } break; + case IP_RECVFRAGSIZE: + if (sk->sk_type != SOCK_RAW && sk->sk_type != SOCK_DGRAM) + goto e_inval; + if (val) + inet->cmsg_flags |= IP_CMSG_RECVFRAGSIZE; + else + inet->cmsg_flags &= ~IP_CMSG_RECVFRAGSIZE; + break; case IP_TOS: /* This sets both TOS and Precedence */ if (sk->sk_type == SOCK_STREAM) { val &= ~INET_ECN_MASK; @@ -1357,6 +1380,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_CHECKSUM: val = (inet->cmsg_flags & IP_CMSG_CHECKSUM) != 0; break; + case IP_RECVFRAGSIZE: + val = (inet->cmsg_flags & IP_CMSG_RECVFRAGSIZE) != 0; + break; case IP_TOS: val = inet->tos; break; -- 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/linux/ipv6.h | 5 +++-- include/uapi/linux/in6.h | 1 + net/ipv6/datagram.c | 5 +++++ net/ipv6/ipv6_sockglue.c | 8 ++++++++ 4 files changed, 17 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index ca1ad9ebbc92..1afb6e8d35c3 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -229,8 +229,9 @@ struct ipv6_pinfo { rxflow:1, rxtclass:1, rxpmtu:1, - rxorigdstaddr:1; - /* 2 bits hole */ + rxorigdstaddr:1, + recvfragsize:1; + /* 1 bits hole */ } bits; __u16 all; } rxopt; 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: diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 37874e2f30ed..620c79a0130a 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -715,6 +715,11 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, put_cmsg(msg, SOL_IPV6, IPV6_ORIGDSTADDR, sizeof(sin6), &sin6); } } + if (np->rxopt.bits.recvfragsize && opt->frag_max_size) { + int val = opt->frag_max_size; + + put_cmsg(msg, SOL_IPV6, IPV6_RECVFRAGSIZE, sizeof(val), &val); + } } void ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 636ec56f5f50..6c126780fcf2 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -868,6 +868,10 @@ pref_skip_coa: np->autoflowlabel = valbool; retv = 0; break; + case IPV6_RECVFRAGSIZE: + np->rxopt.bits.recvfragsize = valbool; + retv = 0; + break; } release_sock(sk); @@ -1310,6 +1314,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = np->autoflowlabel; break; + case IPV6_RECVFRAGSIZE: + val = np->rxopt.bits.recvfragsize; + break; + default: return -ENOPROTOOPT; } -- 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 Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 5 +++++ net/sched/cls_flower.c | 19 +++++++++++++++++++ 2 files changed, 24 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 8fd715f806a2..eb94781757ee 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -447,6 +447,11 @@ enum { TCA_FLOWER_KEY_TCP_DST_MASK, /* be16 */ TCA_FLOWER_KEY_UDP_SRC_MASK, /* be16 */ TCA_FLOWER_KEY_UDP_DST_MASK, /* be16 */ + TCA_FLOWER_KEY_SCTP_SRC_MASK, /* be16 */ + TCA_FLOWER_KEY_SCTP_DST_MASK, /* be16 */ + + TCA_FLOWER_KEY_SCTP_SRC, /* be16 */ + TCA_FLOWER_KEY_SCTP_DST, /* be16 */ __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index a8fb1ca03b3e..db4cd882a989 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -344,6 +344,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_TCP_DST_MASK] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_UDP_SRC_MASK] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_UDP_DST_MASK] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_SCTP_SRC_MASK] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_SCTP_DST_MASK] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_SCTP_SRC] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_SCTP_DST] = { .type = NLA_U16 }, }; static void fl_set_key_val(struct nlattr **tb, @@ -453,6 +457,13 @@ static int fl_set_key(struct net *net, struct nlattr **tb, fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_UDP_DST, &mask->tp.dst, TCA_FLOWER_KEY_UDP_DST_MASK, sizeof(key->tp.dst)); + } else if (key->basic.ip_proto == IPPROTO_SCTP) { + fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_SCTP_SRC, + &mask->tp.src, TCA_FLOWER_KEY_SCTP_SRC_MASK, + sizeof(key->tp.src)); + fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_SCTP_DST, + &mask->tp.dst, TCA_FLOWER_KEY_SCTP_DST_MASK, + sizeof(key->tp.dst)); } if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] || @@ -897,6 +908,14 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, &mask->tp.dst, TCA_FLOWER_KEY_UDP_DST_MASK, sizeof(key->tp.dst)))) goto nla_put_failure; + else if (key->basic.ip_proto == IPPROTO_SCTP && + (fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_SCTP_SRC, + &mask->tp.src, TCA_FLOWER_KEY_SCTP_SRC_MASK, + sizeof(key->tp.src)) || + fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_SCTP_DST, + &mask->tp.dst, TCA_FLOWER_KEY_SCTP_DST_MASK, + sizeof(key->tp.dst)))) + goto nla_put_failure; if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS && (fl_dump_key_val(skb, &key->enc_ipv4.src, -- cgit v1.2.3 From 622ec2c9d52405973c9f1ca5116eb1c393adfc7d Mon Sep 17 00:00:00 2001 From: Lorenzo Colitti Date: Fri, 4 Nov 2016 02:23:42 +0900 Subject: net: core: add UID to flows, rules, and routes - Define a new FIB rule attributes, FRA_UID_RANGE, to describe a range of UIDs. - Define a RTA_UID attribute for per-UID route lookups and dumps. - Support passing these attributes to and from userspace via rtnetlink. The value INVALID_UID indicates no UID was specified. - Add a UID field to the flow structures. Signed-off-by: Lorenzo Colitti Signed-off-by: David S. Miller --- include/net/fib_rules.h | 9 ++++- include/net/flow.h | 5 +++ include/uapi/linux/fib_rules.h | 6 ++++ include/uapi/linux/rtnetlink.h | 1 + net/core/fib_rules.c | 74 ++++++++++++++++++++++++++++++++++++++++-- net/ipv4/fib_frontend.c | 1 + net/ipv4/route.c | 11 +++++++ net/ipv6/route.c | 7 ++++ 8 files changed, 111 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 456e4a6006ab..8dbfdf728cd8 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -8,6 +8,11 @@ #include #include +struct fib_kuid_range { + kuid_t start; + kuid_t end; +}; + struct fib_rule { struct list_head list; int iifindex; @@ -30,6 +35,7 @@ struct fib_rule { int suppress_prefixlen; char iifname[IFNAMSIZ]; char oifname[IFNAMSIZ]; + struct fib_kuid_range uid_range; struct rcu_head rcu; }; @@ -92,7 +98,8 @@ struct fib_rules_ops { [FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \ [FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \ [FRA_GOTO] = { .type = NLA_U32 }, \ - [FRA_L3MDEV] = { .type = NLA_U8 } + [FRA_L3MDEV] = { .type = NLA_U8 }, \ + [FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) } static inline void fib_rule_get(struct fib_rule *rule) { diff --git a/include/net/flow.h b/include/net/flow.h index 035aa7716967..51373f3a5e31 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -11,6 +11,7 @@ #include #include #include +#include /* * ifindex generation is per-net namespace, and loopback is @@ -37,6 +38,7 @@ struct flowi_common { #define FLOWI_FLAG_SKIP_NH_OIF 0x04 __u32 flowic_secid; struct flowi_tunnel flowic_tun_key; + kuid_t flowic_uid; }; union flowi_uli { @@ -74,6 +76,7 @@ struct flowi4 { #define flowi4_flags __fl_common.flowic_flags #define flowi4_secid __fl_common.flowic_secid #define flowi4_tun_key __fl_common.flowic_tun_key +#define flowi4_uid __fl_common.flowic_uid /* (saddr,daddr) must be grouped, same order as in IP header */ __be32 saddr; @@ -131,6 +134,7 @@ struct flowi6 { #define flowi6_flags __fl_common.flowic_flags #define flowi6_secid __fl_common.flowic_secid #define flowi6_tun_key __fl_common.flowic_tun_key +#define flowi6_uid __fl_common.flowic_uid struct in6_addr daddr; struct in6_addr saddr; /* Note: flowi6_tos is encoded in flowlabel, too. */ @@ -176,6 +180,7 @@ struct flowi { #define flowi_flags u.__fl_common.flowic_flags #define flowi_secid u.__fl_common.flowic_secid #define flowi_tun_key u.__fl_common.flowic_tun_key +#define flowi_uid u.__fl_common.flowic_uid } __attribute__((__aligned__(BITS_PER_LONG/8))); static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4) diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h index 14404b3ebb89..bbf02a63a011 100644 --- a/include/uapi/linux/fib_rules.h +++ b/include/uapi/linux/fib_rules.h @@ -29,6 +29,11 @@ struct fib_rule_hdr { __u32 flags; }; +struct fib_rule_uid_range { + __u32 start; + __u32 end; +}; + enum { FRA_UNSPEC, FRA_DST, /* destination address */ @@ -51,6 +56,7 @@ enum { FRA_OIFNAME, FRA_PAD, FRA_L3MDEV, /* iif or oif is l3mdev goto its table */ + FRA_UID_RANGE, /* UID range */ __FRA_MAX }; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 5a78be518101..e14377f2ec27 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -318,6 +318,7 @@ enum rtattr_type_t { RTA_ENCAP, RTA_EXPIRES, RTA_PAD, + RTA_UID, __RTA_MAX }; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index be4629c344a6..5de436a73be2 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -18,6 +18,11 @@ #include #include +static const struct fib_kuid_range fib_kuid_range_unset = { + KUIDT_INIT(0), + KUIDT_INIT(~0), +}; + int fib_default_rule_add(struct fib_rules_ops *ops, u32 pref, u32 table, u32 flags) { @@ -33,6 +38,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops, r->table = table; r->flags = flags; r->fr_net = ops->fro_net; + r->uid_range = fib_kuid_range_unset; r->suppress_prefixlen = -1; r->suppress_ifgroup = -1; @@ -172,6 +178,34 @@ void fib_rules_unregister(struct fib_rules_ops *ops) } EXPORT_SYMBOL_GPL(fib_rules_unregister); +static int uid_range_set(struct fib_kuid_range *range) +{ + return uid_valid(range->start) && uid_valid(range->end); +} + +static struct fib_kuid_range nla_get_kuid_range(struct nlattr **tb) +{ + struct fib_rule_uid_range *in; + struct fib_kuid_range out; + + in = (struct fib_rule_uid_range *)nla_data(tb[FRA_UID_RANGE]); + + out.start = make_kuid(current_user_ns(), in->start); + out.end = make_kuid(current_user_ns(), in->end); + + return out; +} + +static int nla_put_uid_range(struct sk_buff *skb, struct fib_kuid_range *range) +{ + struct fib_rule_uid_range out = { + from_kuid_munged(current_user_ns(), range->start), + from_kuid_munged(current_user_ns(), range->end) + }; + + return nla_put(skb, FRA_UID_RANGE, sizeof(out), &out); +} + static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, struct flowi *fl, int flags, struct fib_lookup_arg *arg) @@ -193,6 +227,10 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, if (rule->l3mdev && !l3mdev_fib_rule_match(rule->fr_net, fl, arg)) goto out; + if (uid_lt(fl->flowi_uid, rule->uid_range.start) || + uid_gt(fl->flowi_uid, rule->uid_range.end)) + goto out; + ret = ops->match(rule, fl, flags); out: return (rule->flags & FIB_RULE_INVERT) ? !ret : ret; @@ -429,6 +467,21 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh) if (rule->l3mdev && rule->table) goto errout_free; + if (tb[FRA_UID_RANGE]) { + if (current_user_ns() != net->user_ns) { + err = -EPERM; + goto errout_free; + } + + rule->uid_range = nla_get_kuid_range(tb); + + if (!uid_range_set(&rule->uid_range) || + !uid_lte(rule->uid_range.start, rule->uid_range.end)) + goto errout_free; + } else { + rule->uid_range = fib_kuid_range_unset; + } + if ((nlh->nlmsg_flags & NLM_F_EXCL) && rule_exists(ops, frh, tb, rule)) { err = -EEXIST; @@ -497,6 +550,7 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh) struct fib_rules_ops *ops = NULL; struct fib_rule *rule, *tmp; struct nlattr *tb[FRA_MAX+1]; + struct fib_kuid_range range; int err = -EINVAL; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) @@ -516,6 +570,14 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh) if (err < 0) goto errout; + if (tb[FRA_UID_RANGE]) { + range = nla_get_kuid_range(tb); + if (!uid_range_set(&range)) + goto errout; + } else { + range = fib_kuid_range_unset; + } + list_for_each_entry(rule, &ops->rules_list, list) { if (frh->action && (frh->action != rule->action)) continue; @@ -552,6 +614,11 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh) (rule->l3mdev != nla_get_u8(tb[FRA_L3MDEV]))) continue; + if (uid_range_set(&range) && + (!uid_eq(rule->uid_range.start, range.start) || + !uid_eq(rule->uid_range.end, range.end))) + continue; + if (!ops->compare(rule, frh, tb)) continue; @@ -619,7 +686,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */ + nla_total_size(4) /* FRA_FWMARK */ + nla_total_size(4) /* FRA_FWMASK */ - + nla_total_size_64bit(8); /* FRA_TUN_ID */ + + nla_total_size_64bit(8) /* FRA_TUN_ID */ + + nla_total_size(sizeof(struct fib_kuid_range)); if (ops->nlmsg_payload) payload += ops->nlmsg_payload(rule); @@ -679,7 +747,9 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, (rule->tun_id && nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)) || (rule->l3mdev && - nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev))) + nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)) || + (uid_range_set(&rule->uid_range) && + nla_put_uid_range(skb, &rule->uid_range))) goto nla_put_failure; if (rule->suppress_ifgroup != -1) { diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index c3b80478226e..d93eea8e2409 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -610,6 +610,7 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { [RTA_FLOW] = { .type = NLA_U32 }, [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, [RTA_ENCAP] = { .type = NLA_NESTED }, + [RTA_UID] = { .type = NLA_U32 }, }; static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 4392db83d540..92e59a638d3b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2504,6 +2504,11 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark)) goto nla_put_failure; + if (!uid_eq(fl4->flowi4_uid, INVALID_UID) && + nla_put_u32(skb, RTA_UID, + from_kuid_munged(current_user_ns(), fl4->flowi4_uid))) + goto nla_put_failure; + error = rt->dst.error; if (rt_is_input_route(rt)) { @@ -2556,6 +2561,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) int mark; struct sk_buff *skb; u32 table_id = RT_TABLE_MAIN; + kuid_t uid; err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy); if (err < 0) @@ -2583,6 +2589,10 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0; iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0; mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0; + if (tb[RTA_UID]) + uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID])); + else + uid = (iif ? INVALID_UID : current_uid()); memset(&fl4, 0, sizeof(fl4)); fl4.daddr = dst; @@ -2590,6 +2600,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) fl4.flowi4_tos = rtm->rtm_tos; fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; fl4.flowi4_mark = mark; + fl4.flowi4_uid = uid; if (iif) { struct net_device *dev; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 947ed1ded026..fdb9c87137bd 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2797,6 +2797,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, [RTA_ENCAP] = { .type = NLA_NESTED }, [RTA_EXPIRES] = { .type = NLA_U32 }, + [RTA_UID] = { .type = NLA_U32 }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -3371,6 +3372,12 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) if (tb[RTA_MARK]) fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]); + if (tb[RTA_UID]) + fl6.flowi6_uid = make_kuid(current_user_ns(), + nla_get_u32(tb[RTA_UID])); + else + fl6.flowi6_uid = iif ? INVALID_UID : current_uid(); + if (iif) { struct net_device *dev; int flags = 0; -- cgit v1.2.3 From f4d997fd613001e612543339e0275c037f94ffe9 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Mon, 7 Nov 2016 15:14:39 +0200 Subject: net/sched: cls_flower: Add UDP port to tunnel parameters The current IP tunneling classification supports only IP addresses and key. Enhance UDP based IP tunneling classification parameters by adding UDP src and dst port. Signed-off-by: Hadar Hen Zion Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/net/flow_dissector.h | 1 + include/uapi/linux/pkt_cls.h | 5 +++++ net/sched/cls_flower.c | 29 ++++++++++++++++++++++++++++- 3 files changed, 34 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 4e7cf38a7750..c4f31666afd2 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -132,6 +132,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, /* struct flow_dissector_key_ipv4_addrs */ FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */ FLOW_DISSECTOR_KEY_ENC_CONTROL, /* struct flow_dissector_key_control */ + FLOW_DISSECTOR_KEY_ENC_PORTS, /* struct flow_dissector_key_ports */ FLOW_DISSECTOR_KEY_MAX, }; diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index eb94781757ee..86786d45ee66 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -452,6 +452,11 @@ enum { TCA_FLOWER_KEY_SCTP_SRC, /* be16 */ TCA_FLOWER_KEY_SCTP_DST, /* be16 */ + + TCA_FLOWER_KEY_ENC_UDP_SRC_PORT, /* be16 */ + TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK, /* be16 */ + TCA_FLOWER_KEY_ENC_UDP_DST_PORT, /* be16 */ + TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, /* be16 */ __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 6369b74c8f5b..e8dd09af0d0c 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -43,6 +43,7 @@ struct fl_flow_key { struct flow_dissector_key_ipv4_addrs enc_ipv4; struct flow_dissector_key_ipv6_addrs enc_ipv6; }; + struct flow_dissector_key_ports enc_tp; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ struct fl_flow_mask_range { @@ -155,6 +156,8 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, } skb_key.enc_key_id.keyid = tunnel_id_to_key32(key->tun_id); + skb_key.enc_tp.src = key->tp_src; + skb_key.enc_tp.dst = key->tp_dst; } skb_key.indev_ifindex = skb->skb_iif; @@ -348,6 +351,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_SCTP_DST_MASK] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_SCTP_SRC] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_SCTP_DST] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_ENC_UDP_SRC_PORT] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_ENC_UDP_DST_PORT] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK] = { .type = NLA_U16 }, }; static void fl_set_key_val(struct nlattr **tb, @@ -500,6 +507,14 @@ static int fl_set_key(struct net *net, struct nlattr **tb, &mask->enc_key_id.keyid, TCA_FLOWER_UNSPEC, sizeof(key->enc_key_id.keyid)); + fl_set_key_val(tb, &key->enc_tp.src, TCA_FLOWER_KEY_ENC_UDP_SRC_PORT, + &mask->enc_tp.src, TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK, + sizeof(key->enc_tp.src)); + + fl_set_key_val(tb, &key->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT, + &mask->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, + sizeof(key->enc_tp.dst)); + return 0; } @@ -577,6 +592,8 @@ static void fl_init_dissector(struct cls_fl_head *head, FL_KEY_IS_MASKED(&mask->key, enc_ipv6)) FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_ENC_CONTROL, enc_control); + FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp); skb_flow_dissector_init(&head->dissector, keys, cnt); } @@ -951,7 +968,17 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, if (fl_dump_key_val(skb, &key->enc_key_id, TCA_FLOWER_KEY_ENC_KEY_ID, &mask->enc_key_id, TCA_FLOWER_UNSPEC, - sizeof(key->enc_key_id))) + sizeof(key->enc_key_id)) || + fl_dump_key_val(skb, &key->enc_tp.src, + TCA_FLOWER_KEY_ENC_UDP_SRC_PORT, + &mask->enc_tp.src, + TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK, + sizeof(key->enc_tp.src)) || + fl_dump_key_val(skb, &key->enc_tp.dst, + TCA_FLOWER_KEY_ENC_UDP_DST_PORT, + &mask->enc_tp.dst, + TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, + sizeof(key->enc_tp.dst))) goto nla_put_failure; nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags); -- cgit v1.2.3 From 75bfbca01e48d2d62e8321609ae32aaf6c6fab0e Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Mon, 7 Nov 2016 15:14:41 +0200 Subject: net/sched: act_tunnel_key: Add UDP dst port option The current tunnel set action supports only IP addresses and key options. Add UDP dst port option. Signed-off-by: Hadar Hen Zion Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/uapi/linux/tc_act/tc_tunnel_key.h | 1 + net/sched/act_tunnel_key.c | 14 +++++++++++--- 2 files changed, 12 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tc_act/tc_tunnel_key.h b/include/uapi/linux/tc_act/tc_tunnel_key.h index 890106ff16e6..84ea55e1076b 100644 --- a/include/uapi/linux/tc_act/tc_tunnel_key.h +++ b/include/uapi/linux/tc_act/tc_tunnel_key.h @@ -33,6 +33,7 @@ enum { TCA_TUNNEL_KEY_ENC_IPV6_DST, /* struct in6_addr */ TCA_TUNNEL_KEY_ENC_KEY_ID, /* be64 */ TCA_TUNNEL_KEY_PAD, + TCA_TUNNEL_KEY_ENC_DST_PORT, /* be16 */ __TCA_TUNNEL_KEY_MAX, }; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index bd2f63e9cf5c..edc720f11687 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -66,6 +66,7 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, [TCA_TUNNEL_KEY_ENC_IPV6_DST] = { .len = sizeof(struct in6_addr) }, [TCA_TUNNEL_KEY_ENC_KEY_ID] = { .type = NLA_U32 }, + [TCA_TUNNEL_KEY_ENC_DST_PORT] = {.type = NLA_U16}, }; static int tunnel_key_init(struct net *net, struct nlattr *nla, @@ -80,6 +81,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, struct tc_tunnel_key *parm; struct tcf_tunnel_key *t; bool exists = false; + __be16 dst_port = 0; __be64 key_id; int ret = 0; int err; @@ -110,6 +112,9 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, key_id = key32_to_tunnel_id(nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID])); + if (tb[TCA_TUNNEL_KEY_ENC_DST_PORT]) + dst_port = nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_DST_PORT]); + if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] && tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) { __be32 saddr; @@ -119,7 +124,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, daddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]); metadata = __ip_tun_set_dst(saddr, daddr, 0, 0, - 0, TUNNEL_KEY, key_id, 0); + dst_port, TUNNEL_KEY, + key_id, 0); } else if (tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC] && tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]) { struct in6_addr saddr; @@ -129,7 +135,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, daddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]); metadata = __ipv6_tun_set_dst(&saddr, &daddr, 0, 0, 0, - 0, TUNNEL_KEY, key_id, 0); + dst_port, TUNNEL_KEY, + key_id, 0); } if (!metadata) { @@ -257,7 +264,8 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, if (nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id) || tunnel_key_dump_addresses(skb, - ¶ms->tcft_enc_metadata->u.tun_info)) + ¶ms->tcft_enc_metadata->u.tun_info) || + nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, key->tp_dst)) goto nla_put_failure; } -- cgit v1.2.3 From 3f11ec045fecf2c0fb21f08f68ebc9237bd1d03c Mon Sep 17 00:00:00 2001 From: Asbjørn Sloth Tønnesen Date: Mon, 7 Nov 2016 20:39:24 +0000 Subject: net: l2tp: change L2TP_ATTR_UDP_ZERO_CSUM6_{RX, TX} attribute types The attributes L2TP_ATTR_UDP_ZERO_CSUM6_RX and L2TP_ATTR_UDP_ZERO_CSUM6_TX are used as flags, but is defined as a u8 in a comment. This patch redocuments them as flags. Adding nla_policy entries would break API, so not doing that. CC: Tom Herbert Signed-off-by: Asbjoern Sloth Toennesen Signed-off-by: David S. Miller --- include/uapi/linux/l2tp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h index 4bd27d0270a2..5daa48e2571e 100644 --- a/include/uapi/linux/l2tp.h +++ b/include/uapi/linux/l2tp.h @@ -124,8 +124,8 @@ enum { L2TP_ATTR_STATS, /* nested */ L2TP_ATTR_IP6_SADDR, /* struct in6_addr */ L2TP_ATTR_IP6_DADDR, /* struct in6_addr */ - L2TP_ATTR_UDP_ZERO_CSUM6_TX, /* u8 */ - L2TP_ATTR_UDP_ZERO_CSUM6_RX, /* u8 */ + L2TP_ATTR_UDP_ZERO_CSUM6_TX, /* flag */ + L2TP_ATTR_UDP_ZERO_CSUM6_RX, /* flag */ L2TP_ATTR_PAD, __L2TP_ATTR_MAX, }; -- cgit v1.2.3 From 1ababeba4a21f3dba3da3523c670b207fb2feb62 Mon Sep 17 00:00:00 2001 From: David Lebrun Date: Tue, 8 Nov 2016 14:57:39 +0100 Subject: ipv6: implement dataplane support for rthdr type 4 (Segment Routing Header) Implement minimal support for processing of SR-enabled packets as described in https://tools.ietf.org/html/draft-ietf-6man-segment-routing-header-02. This patch implements the following operations: - Intermediate segment endpoint: incrementation of active segment and rerouting. - Egress for SR-encapsulated packets: decapsulation of outer IPv6 header + SRH and routing of inner packet. - Cleanup flag support for SR-inlined packets: removal of SRH if we are the penultimate segment endpoint. A per-interface sysctl seg6_enabled is provided, to accept/deny SR-enabled packets. Default is deny. This patch does not provide support for HMAC-signed packets. Signed-off-by: David Lebrun Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + include/linux/seg6.h | 6 ++ include/net/seg6.h | 36 ++++++++++ include/uapi/linux/ipv6.h | 2 + include/uapi/linux/seg6.h | 54 ++++++++++++++ net/ipv6/addrconf.c | 10 +++ net/ipv6/exthdrs.c | 175 ++++++++++++++++++++++++++++++++++++++++++++++ 7 files changed, 284 insertions(+) create mode 100644 include/linux/seg6.h create mode 100644 include/net/seg6.h create mode 100644 include/uapi/linux/seg6.h (limited to 'include/uapi/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 1afb6e8d35c3..68d3f71f0abf 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -64,6 +64,7 @@ struct ipv6_devconf { } stable_secret; __s32 use_oif_addrs_only; __s32 keep_addr_on_down; + __s32 seg6_enabled; struct ctl_table_header *sysctl_header; }; diff --git a/include/linux/seg6.h b/include/linux/seg6.h new file mode 100644 index 000000000000..7a66d2b4c5a6 --- /dev/null +++ b/include/linux/seg6.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_SEG6_H +#define _LINUX_SEG6_H + +#include + +#endif diff --git a/include/net/seg6.h b/include/net/seg6.h new file mode 100644 index 000000000000..4dd52a7e95f1 --- /dev/null +++ b/include/net/seg6.h @@ -0,0 +1,36 @@ +/* + * SR-IPv6 implementation + * + * Author: + * David Lebrun + * + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _NET_SEG6_H +#define _NET_SEG6_H + +static inline void update_csum_diff4(struct sk_buff *skb, __be32 from, + __be32 to) +{ + __be32 diff[] = { ~from, to }; + + skb->csum = ~csum_partial((char *)diff, sizeof(diff), ~skb->csum); +} + +static inline void update_csum_diff16(struct sk_buff *skb, __be32 *from, + __be32 *to) +{ + __be32 diff[] = { + ~from[0], ~from[1], ~from[2], ~from[3], + to[0], to[1], to[2], to[3], + }; + + skb->csum = ~csum_partial((char *)diff, sizeof(diff), ~skb->csum); +} + +#endif diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 8c2772340c3f..7ff1d654e333 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -39,6 +39,7 @@ struct in6_ifreq { #define IPV6_SRCRT_STRICT 0x01 /* Deprecated; will be removed */ #define IPV6_SRCRT_TYPE_0 0 /* Deprecated; will be removed */ #define IPV6_SRCRT_TYPE_2 2 /* IPv6 type 2 Routing Header */ +#define IPV6_SRCRT_TYPE_4 4 /* Segment Routing with IPv6 */ /* * routing header @@ -178,6 +179,7 @@ enum { DEVCONF_DROP_UNSOLICITED_NA, DEVCONF_KEEP_ADDR_ON_DOWN, DEVCONF_RTR_SOLICIT_MAX_INTERVAL, + DEVCONF_SEG6_ENABLED, DEVCONF_MAX }; diff --git a/include/uapi/linux/seg6.h b/include/uapi/linux/seg6.h new file mode 100644 index 000000000000..c396a8052f73 --- /dev/null +++ b/include/uapi/linux/seg6.h @@ -0,0 +1,54 @@ +/* + * SR-IPv6 implementation + * + * Author: + * David Lebrun + * + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _UAPI_LINUX_SEG6_H +#define _UAPI_LINUX_SEG6_H + +/* + * SRH + */ +struct ipv6_sr_hdr { + __u8 nexthdr; + __u8 hdrlen; + __u8 type; + __u8 segments_left; + __u8 first_segment; + __u8 flag_1; + __u8 flag_2; + __u8 reserved; + + struct in6_addr segments[0]; +}; + +#define SR6_FLAG1_CLEANUP (1 << 7) +#define SR6_FLAG1_PROTECTED (1 << 6) +#define SR6_FLAG1_OAM (1 << 5) +#define SR6_FLAG1_ALERT (1 << 4) +#define SR6_FLAG1_HMAC (1 << 3) + +#define SR6_TLV_INGRESS 1 +#define SR6_TLV_EGRESS 2 +#define SR6_TLV_OPAQUE 3 +#define SR6_TLV_PADDING 4 +#define SR6_TLV_HMAC 5 + +#define sr_has_cleanup(srh) ((srh)->flag_1 & SR6_FLAG1_CLEANUP) +#define sr_has_hmac(srh) ((srh)->flag_1 & SR6_FLAG1_HMAC) + +struct sr6_tlv { + __u8 type; + __u8 len; + __u8 data[0]; +}; + +#endif diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 060dd9922018..2ac6cb460af0 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -238,6 +238,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, .keep_addr_on_down = 0, + .seg6_enabled = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -284,6 +285,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, .keep_addr_on_down = 0, + .seg6_enabled = 0, }; /* Check if a valid qdisc is available */ @@ -4944,6 +4946,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = cnf->drop_unicast_in_l2_multicast; array[DEVCONF_DROP_UNSOLICITED_NA] = cnf->drop_unsolicited_na; array[DEVCONF_KEEP_ADDR_ON_DOWN] = cnf->keep_addr_on_down; + array[DEVCONF_SEG6_ENABLED] = cnf->seg6_enabled; } static inline size_t inet6_ifla6_size(void) @@ -6035,6 +6038,13 @@ static const struct ctl_table addrconf_sysctl[] = { .proc_handler = proc_dointvec, }, + { + .procname = "seg6_enabled", + .data = &ipv6_devconf.seg6_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { /* sentinel */ } diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 139ceb68bd37..b8ba3961ff8a 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -47,6 +47,8 @@ #if IS_ENABLED(CONFIG_IPV6_MIP6) #include #endif +#include +#include #include @@ -286,6 +288,175 @@ static int ipv6_destopt_rcv(struct sk_buff *skb) return -1; } +static void seg6_update_csum(struct sk_buff *skb) +{ + struct ipv6_sr_hdr *hdr; + struct in6_addr *addr; + __be32 from, to; + + /* srh is at transport offset and seg_left is already decremented + * but daddr is not yet updated with next segment + */ + + hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb); + addr = hdr->segments + hdr->segments_left; + + hdr->segments_left++; + from = *(__be32 *)hdr; + + hdr->segments_left--; + to = *(__be32 *)hdr; + + /* update skb csum with diff resulting from seg_left decrement */ + + update_csum_diff4(skb, from, to); + + /* compute csum diff between current and next segment and update */ + + update_csum_diff16(skb, (__be32 *)(&ipv6_hdr(skb)->daddr), + (__be32 *)addr); +} + +static int ipv6_srh_rcv(struct sk_buff *skb) +{ + struct inet6_skb_parm *opt = IP6CB(skb); + struct net *net = dev_net(skb->dev); + struct ipv6_sr_hdr *hdr; + struct inet6_dev *idev; + struct in6_addr *addr; + bool cleanup = false; + int accept_seg6; + + hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb); + + idev = __in6_dev_get(skb->dev); + + accept_seg6 = net->ipv6.devconf_all->seg6_enabled; + if (accept_seg6 > idev->cnf.seg6_enabled) + accept_seg6 = idev->cnf.seg6_enabled; + + if (!accept_seg6) { + kfree_skb(skb); + return -1; + } + +looped_back: + if (hdr->segments_left > 0) { + if (hdr->nexthdr != NEXTHDR_IPV6 && hdr->segments_left == 1 && + sr_has_cleanup(hdr)) + cleanup = true; + } else { + if (hdr->nexthdr == NEXTHDR_IPV6) { + int offset = (hdr->hdrlen + 1) << 3; + + skb_postpull_rcsum(skb, skb_network_header(skb), + skb_network_header_len(skb)); + + if (!pskb_pull(skb, offset)) { + kfree_skb(skb); + return -1; + } + skb_postpull_rcsum(skb, skb_transport_header(skb), + offset); + + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + skb->encapsulation = 0; + + __skb_tunnel_rx(skb, skb->dev, net); + + netif_rx(skb); + return -1; + } + + opt->srcrt = skb_network_header_len(skb); + opt->lastopt = opt->srcrt; + skb->transport_header += (hdr->hdrlen + 1) << 3; + opt->nhoff = (&hdr->nexthdr) - skb_network_header(skb); + + return 1; + } + + if (hdr->segments_left >= (hdr->hdrlen >> 1)) { + __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INHDRERRORS); + icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, + ((&hdr->segments_left) - + skb_network_header(skb))); + kfree_skb(skb); + return -1; + } + + if (skb_cloned(skb)) { + if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) { + __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_OUTDISCARDS); + kfree_skb(skb); + return -1; + } + } + + hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb); + + hdr->segments_left--; + addr = hdr->segments + hdr->segments_left; + + skb_push(skb, sizeof(struct ipv6hdr)); + + if (skb->ip_summed == CHECKSUM_COMPLETE) + seg6_update_csum(skb); + + ipv6_hdr(skb)->daddr = *addr; + + if (cleanup) { + int srhlen = (hdr->hdrlen + 1) << 3; + int nh = hdr->nexthdr; + + skb_pull_rcsum(skb, sizeof(struct ipv6hdr) + srhlen); + memmove(skb_network_header(skb) + srhlen, + skb_network_header(skb), + (unsigned char *)hdr - skb_network_header(skb)); + skb->network_header += srhlen; + ipv6_hdr(skb)->nexthdr = nh; + ipv6_hdr(skb)->payload_len = htons(skb->len - + sizeof(struct ipv6hdr)); + skb_push_rcsum(skb, sizeof(struct ipv6hdr)); + } + + skb_dst_drop(skb); + + ip6_route_input(skb); + + if (skb_dst(skb)->error) { + dst_input(skb); + return -1; + } + + if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) { + if (ipv6_hdr(skb)->hop_limit <= 1) { + __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INHDRERRORS); + icmpv6_send(skb, ICMPV6_TIME_EXCEED, + ICMPV6_EXC_HOPLIMIT, 0); + kfree_skb(skb); + return -1; + } + ipv6_hdr(skb)->hop_limit--; + + /* be sure that srh is still present before reinjecting */ + if (!cleanup) { + skb_pull(skb, sizeof(struct ipv6hdr)); + goto looped_back; + } + skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); + } + + dst_input(skb); + + return -1; +} + /******************************** Routing header. ********************************/ @@ -326,6 +497,10 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb) return -1; } + /* segment routing */ + if (hdr->type == IPV6_SRCRT_TYPE_4) + return ipv6_srh_rcv(skb); + looped_back: if (hdr->segments_left == 0) { switch (hdr->type) { -- cgit v1.2.3 From 915d7e5e5930b4f01d0971d93b9b25ed17d221aa Mon Sep 17 00:00:00 2001 From: David Lebrun Date: Tue, 8 Nov 2016 14:57:40 +0100 Subject: ipv6: sr: add code base for control plane support of SR-IPv6 This patch adds the necessary hooks and structures to provide support for SR-IPv6 control plane, essentially the Generic Netlink commands that will be used for userspace control over the Segment Routing kernel structures. The genetlink commands provide control over two different structures: tunnel source and HMAC data. The tunnel source is the source address that will be used by default when encapsulating packets into an outer IPv6 header + SRH. If the tunnel source is set to :: then an address of the outgoing interface will be selected as the source. The HMAC commands currently just return ENOTSUPP and will be implemented in a future patch. Signed-off-by: David Lebrun Signed-off-by: David S. Miller --- include/linux/seg6_genl.h | 6 ++ include/net/netns/ipv6.h | 1 + include/net/seg6.h | 16 +++ include/uapi/linux/seg6_genl.h | 32 ++++++ net/ipv6/Makefile | 2 +- net/ipv6/af_inet6.c | 9 +- net/ipv6/seg6.c | 214 +++++++++++++++++++++++++++++++++++++++++ 7 files changed, 278 insertions(+), 2 deletions(-) create mode 100644 include/linux/seg6_genl.h create mode 100644 include/uapi/linux/seg6_genl.h create mode 100644 net/ipv6/seg6.c (limited to 'include/uapi/linux') diff --git a/include/linux/seg6_genl.h b/include/linux/seg6_genl.h new file mode 100644 index 000000000000..d6c3fb4f3734 --- /dev/null +++ b/include/linux/seg6_genl.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_SEG6_GENL_H +#define _LINUX_SEG6_GENL_H + +#include + +#endif diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 10d0848f5b8a..de7745e2edcc 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -85,6 +85,7 @@ struct netns_ipv6 { #endif atomic_t dev_addr_genid; atomic_t fib6_sernum; + struct seg6_pernet_data *seg6_data; }; #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) diff --git a/include/net/seg6.h b/include/net/seg6.h index 4dd52a7e95f1..7c7b8ed39661 100644 --- a/include/net/seg6.h +++ b/include/net/seg6.h @@ -14,6 +14,9 @@ #ifndef _NET_SEG6_H #define _NET_SEG6_H +#include +#include + static inline void update_csum_diff4(struct sk_buff *skb, __be32 from, __be32 to) { @@ -33,4 +36,17 @@ static inline void update_csum_diff16(struct sk_buff *skb, __be32 *from, skb->csum = ~csum_partial((char *)diff, sizeof(diff), ~skb->csum); } +struct seg6_pernet_data { + struct mutex lock; + struct in6_addr __rcu *tun_src; +}; + +static inline struct seg6_pernet_data *seg6_pernet(struct net *net) +{ + return net->ipv6.seg6_data; +} + +extern int seg6_init(void); +extern void seg6_exit(void); + #endif diff --git a/include/uapi/linux/seg6_genl.h b/include/uapi/linux/seg6_genl.h new file mode 100644 index 000000000000..fcf1c60d7df3 --- /dev/null +++ b/include/uapi/linux/seg6_genl.h @@ -0,0 +1,32 @@ +#ifndef _UAPI_LINUX_SEG6_GENL_H +#define _UAPI_LINUX_SEG6_GENL_H + +#define SEG6_GENL_NAME "SEG6" +#define SEG6_GENL_VERSION 0x1 + +enum { + SEG6_ATTR_UNSPEC, + SEG6_ATTR_DST, + SEG6_ATTR_DSTLEN, + SEG6_ATTR_HMACKEYID, + SEG6_ATTR_SECRET, + SEG6_ATTR_SECRETLEN, + SEG6_ATTR_ALGID, + SEG6_ATTR_HMACINFO, + __SEG6_ATTR_MAX, +}; + +#define SEG6_ATTR_MAX (__SEG6_ATTR_MAX - 1) + +enum { + SEG6_CMD_UNSPEC, + SEG6_CMD_SETHMAC, + SEG6_CMD_DUMPHMAC, + SEG6_CMD_SET_TUNSRC, + SEG6_CMD_GET_TUNSRC, + __SEG6_CMD_MAX, +}; + +#define SEG6_CMD_MAX (__SEG6_CMD_MAX - 1) + +#endif diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index c174ccb340a1..c92010d62afc 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -9,7 +9,7 @@ ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \ route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \ raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \ exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o \ - udp_offload.o + udp_offload.o seg6.o ipv6-offload := ip6_offload.o tcpv6_offload.o exthdrs_offload.o diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index c86911b63f8a..d424f3a3737a 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -61,6 +61,7 @@ #include #endif #include +#include #include #include @@ -991,6 +992,10 @@ static int __init inet6_init(void) if (err) goto calipso_fail; + err = seg6_init(); + if (err) + goto seg6_fail; + #ifdef CONFIG_SYSCTL err = ipv6_sysctl_register(); if (err) @@ -1001,8 +1006,10 @@ out: #ifdef CONFIG_SYSCTL sysctl_fail: - calipso_exit(); + seg6_exit(); #endif +seg6_fail: + calipso_exit(); calipso_fail: pingv6_exit(); pingv6_fail: diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c new file mode 100644 index 000000000000..e246b0ba12ac --- /dev/null +++ b/net/ipv6/seg6.c @@ -0,0 +1,214 @@ +/* + * SR-IPv6 implementation + * + * Author: + * David Lebrun + * + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include + +#include +#include + +#include +#include +#include +#include + +static struct genl_family seg6_genl_family; + +static const struct nla_policy seg6_genl_policy[SEG6_ATTR_MAX + 1] = { + [SEG6_ATTR_DST] = { .type = NLA_BINARY, + .len = sizeof(struct in6_addr) }, + [SEG6_ATTR_DSTLEN] = { .type = NLA_S32, }, + [SEG6_ATTR_HMACKEYID] = { .type = NLA_U32, }, + [SEG6_ATTR_SECRET] = { .type = NLA_BINARY, }, + [SEG6_ATTR_SECRETLEN] = { .type = NLA_U8, }, + [SEG6_ATTR_ALGID] = { .type = NLA_U8, }, + [SEG6_ATTR_HMACINFO] = { .type = NLA_NESTED, }, +}; + +static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info) +{ + return -ENOTSUPP; +} + +static int seg6_genl_set_tunsrc(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct in6_addr *val, *t_old, *t_new; + struct seg6_pernet_data *sdata; + + sdata = seg6_pernet(net); + + if (!info->attrs[SEG6_ATTR_DST]) + return -EINVAL; + + val = nla_data(info->attrs[SEG6_ATTR_DST]); + t_new = kmemdup(val, sizeof(*val), GFP_KERNEL); + + mutex_lock(&sdata->lock); + + t_old = sdata->tun_src; + rcu_assign_pointer(sdata->tun_src, t_new); + + mutex_unlock(&sdata->lock); + + synchronize_net(); + kfree(t_old); + + return 0; +} + +static int seg6_genl_get_tunsrc(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct in6_addr *tun_src; + struct sk_buff *msg; + void *hdr; + + msg = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, + &seg6_genl_family, 0, SEG6_CMD_GET_TUNSRC); + if (!hdr) + goto free_msg; + + rcu_read_lock(); + tun_src = rcu_dereference(seg6_pernet(net)->tun_src); + + if (nla_put(msg, SEG6_ATTR_DST, sizeof(struct in6_addr), tun_src)) + goto nla_put_failure; + + rcu_read_unlock(); + + genlmsg_end(msg, hdr); + genlmsg_reply(msg, info); + + return 0; + +nla_put_failure: + rcu_read_unlock(); + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return -ENOMEM; +} + +static int seg6_genl_dumphmac(struct sk_buff *skb, struct netlink_callback *cb) +{ + return -ENOTSUPP; +} + +static int __net_init seg6_net_init(struct net *net) +{ + struct seg6_pernet_data *sdata; + + sdata = kzalloc(sizeof(*sdata), GFP_KERNEL); + if (!sdata) + return -ENOMEM; + + mutex_init(&sdata->lock); + + sdata->tun_src = kzalloc(sizeof(*sdata->tun_src), GFP_KERNEL); + if (!sdata->tun_src) { + kfree(sdata); + return -ENOMEM; + } + + net->ipv6.seg6_data = sdata; + + return 0; +} + +static void __net_exit seg6_net_exit(struct net *net) +{ + struct seg6_pernet_data *sdata = seg6_pernet(net); + + kfree(sdata->tun_src); + kfree(sdata); +} + +static struct pernet_operations ip6_segments_ops = { + .init = seg6_net_init, + .exit = seg6_net_exit, +}; + +static const struct genl_ops seg6_genl_ops[] = { + { + .cmd = SEG6_CMD_SETHMAC, + .doit = seg6_genl_sethmac, + .policy = seg6_genl_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = SEG6_CMD_DUMPHMAC, + .dumpit = seg6_genl_dumphmac, + .policy = seg6_genl_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = SEG6_CMD_SET_TUNSRC, + .doit = seg6_genl_set_tunsrc, + .policy = seg6_genl_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = SEG6_CMD_GET_TUNSRC, + .doit = seg6_genl_get_tunsrc, + .policy = seg6_genl_policy, + .flags = GENL_ADMIN_PERM, + }, +}; + +static struct genl_family seg6_genl_family __ro_after_init = { + .hdrsize = 0, + .name = SEG6_GENL_NAME, + .version = SEG6_GENL_VERSION, + .maxattr = SEG6_ATTR_MAX, + .netnsok = true, + .parallel_ops = true, + .ops = seg6_genl_ops, + .n_ops = ARRAY_SIZE(seg6_genl_ops), + .module = THIS_MODULE, +}; + +int __init seg6_init(void) +{ + int err = -ENOMEM; + + err = genl_register_family(&seg6_genl_family); + if (err) + goto out; + + err = register_pernet_subsys(&ip6_segments_ops); + if (err) + goto out_unregister_genl; + + pr_info("Segment Routing with IPv6\n"); + +out: + return err; +out_unregister_genl: + genl_unregister_family(&seg6_genl_family); + goto out; +} + +void seg6_exit(void) +{ + unregister_pernet_subsys(&ip6_segments_ops); + genl_unregister_family(&seg6_genl_family); +} -- cgit v1.2.3 From 6c8702c60b88651072460f3f4026c7dfe2521d12 Mon Sep 17 00:00:00 2001 From: David Lebrun Date: Tue, 8 Nov 2016 14:57:41 +0100 Subject: ipv6: sr: add support for SRH encapsulation and injection with lwtunnels This patch creates a new type of interfaceless lightweight tunnel (SEG6), enabling the encapsulation and injection of SRH within locally emitted packets and forwarded packets. >From a configuration viewpoint, a seg6 tunnel would be configured as follows: ip -6 ro ad fc00::1/128 encap seg6 mode encap segs fc42::1,fc42::2,fc42::3 dev eth0 Any packet whose destination address is fc00::1 would thus be encapsulated within an outer IPv6 header containing the SRH with three segments, and would actually be routed to the first segment of the list. If `mode inline' was specified instead of `mode encap', then the SRH would be directly inserted after the IPv6 header without outer encapsulation. The inline mode is only available if CONFIG_IPV6_SEG6_INLINE is enabled. This feature was made configurable because direct header insertion may break several mechanisms such as PMTUD or IPSec AH. Signed-off-by: David Lebrun Signed-off-by: David S. Miller --- include/linux/seg6_iptunnel.h | 6 + include/net/seg6.h | 6 + include/uapi/linux/lwtunnel.h | 1 + include/uapi/linux/seg6_iptunnel.h | 44 ++++ net/core/lwtunnel.c | 2 + net/ipv6/Kconfig | 12 ++ net/ipv6/Makefile | 2 +- net/ipv6/seg6.c | 44 ++++ net/ipv6/seg6_iptunnel.c | 410 +++++++++++++++++++++++++++++++++++++ 9 files changed, 526 insertions(+), 1 deletion(-) create mode 100644 include/linux/seg6_iptunnel.h create mode 100644 include/uapi/linux/seg6_iptunnel.h create mode 100644 net/ipv6/seg6_iptunnel.c (limited to 'include/uapi/linux') diff --git a/include/linux/seg6_iptunnel.h b/include/linux/seg6_iptunnel.h new file mode 100644 index 000000000000..5377cf6a5a02 --- /dev/null +++ b/include/linux/seg6_iptunnel.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_SEG6_IPTUNNEL_H +#define _LINUX_SEG6_IPTUNNEL_H + +#include + +#endif diff --git a/include/net/seg6.h b/include/net/seg6.h index 7c7b8ed39661..ff5da0ce83e9 100644 --- a/include/net/seg6.h +++ b/include/net/seg6.h @@ -16,6 +16,8 @@ #include #include +#include +#include static inline void update_csum_diff4(struct sk_buff *skb, __be32 from, __be32 to) @@ -48,5 +50,9 @@ static inline struct seg6_pernet_data *seg6_pernet(struct net *net) extern int seg6_init(void); extern void seg6_exit(void); +extern int seg6_iptunnel_init(void); +extern void seg6_iptunnel_exit(void); + +extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len); #endif diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h index a478fe80e203..453cc6215bfd 100644 --- a/include/uapi/linux/lwtunnel.h +++ b/include/uapi/linux/lwtunnel.h @@ -9,6 +9,7 @@ enum lwtunnel_encap_types { LWTUNNEL_ENCAP_IP, LWTUNNEL_ENCAP_ILA, LWTUNNEL_ENCAP_IP6, + LWTUNNEL_ENCAP_SEG6, __LWTUNNEL_ENCAP_MAX, }; diff --git a/include/uapi/linux/seg6_iptunnel.h b/include/uapi/linux/seg6_iptunnel.h new file mode 100644 index 000000000000..0f7dbd280a9c --- /dev/null +++ b/include/uapi/linux/seg6_iptunnel.h @@ -0,0 +1,44 @@ +/* + * SR-IPv6 implementation + * + * Author: + * David Lebrun + * + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _UAPI_LINUX_SEG6_IPTUNNEL_H +#define _UAPI_LINUX_SEG6_IPTUNNEL_H + +enum { + SEG6_IPTUNNEL_UNSPEC, + SEG6_IPTUNNEL_SRH, + __SEG6_IPTUNNEL_MAX, +}; +#define SEG6_IPTUNNEL_MAX (__SEG6_IPTUNNEL_MAX - 1) + +struct seg6_iptunnel_encap { + int mode; + struct ipv6_sr_hdr srh[0]; +}; + +#define SEG6_IPTUN_ENCAP_SIZE(x) ((sizeof(*x)) + (((x)->srh->hdrlen + 1) << 3)) + +enum { + SEG6_IPTUN_MODE_INLINE, + SEG6_IPTUN_MODE_ENCAP, +}; + +static inline size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo) +{ + int encap = (tuninfo->mode == SEG6_IPTUN_MODE_ENCAP); + + return ((tuninfo->srh->hdrlen + 1) << 3) + + (encap * sizeof(struct ipv6hdr)); +} + +#endif diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 88fd64250b02..03976e939818 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -39,6 +39,8 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type) return "MPLS"; case LWTUNNEL_ENCAP_ILA: return "ILA"; + case LWTUNNEL_ENCAP_SEG6: + return "SEG6"; case LWTUNNEL_ENCAP_IP6: case LWTUNNEL_ENCAP_IP: case LWTUNNEL_ENCAP_NONE: diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 2343e4f2e0bf..1123a001d729 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -289,4 +289,16 @@ config IPV6_PIMSM_V2 Support for IPv6 PIM multicast routing protocol PIM-SMv2. If unsure, say N. +config IPV6_SEG6_INLINE + bool "IPv6: direct Segment Routing Header insertion " + depends on IPV6 + ---help--- + Support for direct insertion of the Segment Routing Header, + also known as inline mode. Be aware that direct insertion of + extension headers (as opposed to encapsulation) may break + multiple mechanisms such as PMTUD or IPSec AH. Use this feature + only if you know exactly what you are doing. + + If unsure, say N. + endif # IPV6 diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index c92010d62afc..59ee92fb3689 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -9,7 +9,7 @@ ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \ route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \ raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \ exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o \ - udp_offload.o seg6.o + udp_offload.o seg6.o seg6_iptunnel.o ipv6-offload := ip6_offload.o tcpv6_offload.o exthdrs_offload.o diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index e246b0ba12ac..9c78053e67e0 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -26,6 +26,43 @@ #include #include +bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len) +{ + int trailing; + unsigned int tlv_offset; + + if (srh->type != IPV6_SRCRT_TYPE_4) + return false; + + if (((srh->hdrlen + 1) << 3) != len) + return false; + + if (srh->segments_left != srh->first_segment) + return false; + + tlv_offset = sizeof(*srh) + ((srh->first_segment + 1) << 4); + + trailing = len - tlv_offset; + if (trailing < 0) + return false; + + while (trailing) { + struct sr6_tlv *tlv; + unsigned int tlv_len; + + tlv = (struct sr6_tlv *)((unsigned char *)srh + tlv_offset); + tlv_len = sizeof(*tlv) + tlv->len; + + trailing -= tlv_len; + if (trailing < 0) + return false; + + tlv_offset += tlv_len; + } + + return true; +} + static struct genl_family seg6_genl_family; static const struct nla_policy seg6_genl_policy[SEG6_ATTR_MAX + 1] = { @@ -198,10 +235,16 @@ int __init seg6_init(void) if (err) goto out_unregister_genl; + err = seg6_iptunnel_init(); + if (err) + goto out_unregister_pernet; + pr_info("Segment Routing with IPv6\n"); out: return err; +out_unregister_pernet: + unregister_pernet_subsys(&ip6_segments_ops); out_unregister_genl: genl_unregister_family(&seg6_genl_family); goto out; @@ -209,6 +252,7 @@ out_unregister_genl: void seg6_exit(void) { + seg6_iptunnel_exit(); unregister_pernet_subsys(&ip6_segments_ops); genl_unregister_family(&seg6_genl_family); } diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c new file mode 100644 index 000000000000..39762b2fa7a2 --- /dev/null +++ b/net/ipv6/seg6_iptunnel.c @@ -0,0 +1,410 @@ +/* + * SR-IPv6 implementation + * + * Author: + * David Lebrun + * + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#ifdef CONFIG_DST_CACHE +#include +#endif + +struct seg6_lwt { +#ifdef CONFIG_DST_CACHE + struct dst_cache cache; +#endif + struct seg6_iptunnel_encap tuninfo[0]; +}; + +static inline struct seg6_lwt *seg6_lwt_lwtunnel(struct lwtunnel_state *lwt) +{ + return (struct seg6_lwt *)lwt->data; +} + +static inline struct seg6_iptunnel_encap * +seg6_encap_lwtunnel(struct lwtunnel_state *lwt) +{ + return seg6_lwt_lwtunnel(lwt)->tuninfo; +} + +static const struct nla_policy seg6_iptunnel_policy[SEG6_IPTUNNEL_MAX + 1] = { + [SEG6_IPTUNNEL_SRH] = { .type = NLA_BINARY }, +}; + +int nla_put_srh(struct sk_buff *skb, int attrtype, + struct seg6_iptunnel_encap *tuninfo) +{ + struct seg6_iptunnel_encap *data; + struct nlattr *nla; + int len; + + len = SEG6_IPTUN_ENCAP_SIZE(tuninfo); + + nla = nla_reserve(skb, attrtype, len); + if (!nla) + return -EMSGSIZE; + + data = nla_data(nla); + memcpy(data, tuninfo, len); + + return 0; +} + +static void set_tun_src(struct net *net, struct net_device *dev, + struct in6_addr *daddr, struct in6_addr *saddr) +{ + struct seg6_pernet_data *sdata = seg6_pernet(net); + struct in6_addr *tun_src; + + rcu_read_lock(); + + tun_src = rcu_dereference(sdata->tun_src); + + if (!ipv6_addr_any(tun_src)) { + memcpy(saddr, tun_src, sizeof(struct in6_addr)); + } else { + ipv6_dev_get_saddr(net, dev, daddr, IPV6_PREFER_SRC_PUBLIC, + saddr); + } + + rcu_read_unlock(); +} + +/* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */ +static int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) +{ + struct net *net = dev_net(skb_dst(skb)->dev); + struct ipv6hdr *hdr, *inner_hdr; + struct ipv6_sr_hdr *isrh; + int hdrlen, tot_len, err; + + hdrlen = (osrh->hdrlen + 1) << 3; + tot_len = hdrlen + sizeof(*hdr); + + err = pskb_expand_head(skb, tot_len, 0, GFP_ATOMIC); + if (unlikely(err)) + return err; + + inner_hdr = ipv6_hdr(skb); + + skb_push(skb, tot_len); + skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + hdr = ipv6_hdr(skb); + + /* inherit tc, flowlabel and hlim + * hlim will be decremented in ip6_forward() afterwards and + * decapsulation will overwrite inner hlim with outer hlim + */ + ip6_flow_hdr(hdr, ip6_tclass(ip6_flowinfo(inner_hdr)), + ip6_flowlabel(inner_hdr)); + hdr->hop_limit = inner_hdr->hop_limit; + hdr->nexthdr = NEXTHDR_ROUTING; + + isrh = (void *)hdr + sizeof(*hdr); + memcpy(isrh, osrh, hdrlen); + + isrh->nexthdr = NEXTHDR_IPV6; + + hdr->daddr = isrh->segments[isrh->first_segment]; + set_tun_src(net, skb->dev, &hdr->daddr, &hdr->saddr); + + skb_postpush_rcsum(skb, hdr, tot_len); + + return 0; +} + +/* insert an SRH within an IPv6 packet, just after the IPv6 header */ +#ifdef CONFIG_IPV6_SEG6_INLINE +static int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) +{ + struct ipv6hdr *hdr, *oldhdr; + struct ipv6_sr_hdr *isrh; + int hdrlen, err; + + hdrlen = (osrh->hdrlen + 1) << 3; + + err = pskb_expand_head(skb, hdrlen, 0, GFP_ATOMIC); + if (unlikely(err)) + return err; + + oldhdr = ipv6_hdr(skb); + + skb_pull(skb, sizeof(struct ipv6hdr)); + skb_postpull_rcsum(skb, skb_network_header(skb), + sizeof(struct ipv6hdr)); + + skb_push(skb, sizeof(struct ipv6hdr) + hdrlen); + skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + + hdr = ipv6_hdr(skb); + + memmove(hdr, oldhdr, sizeof(*hdr)); + + isrh = (void *)hdr + sizeof(*hdr); + memcpy(isrh, osrh, hdrlen); + + isrh->nexthdr = hdr->nexthdr; + hdr->nexthdr = NEXTHDR_ROUTING; + + isrh->segments[0] = hdr->daddr; + hdr->daddr = isrh->segments[isrh->first_segment]; + + skb_postpush_rcsum(skb, hdr, sizeof(struct ipv6hdr) + hdrlen); + + return 0; +} +#endif + +static int seg6_do_srh(struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct seg6_iptunnel_encap *tinfo; + int err = 0; + + tinfo = seg6_encap_lwtunnel(dst->lwtstate); + + if (likely(!skb->encapsulation)) { + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + } + + switch (tinfo->mode) { +#ifdef CONFIG_IPV6_SEG6_INLINE + case SEG6_IPTUN_MODE_INLINE: + err = seg6_do_srh_inline(skb, tinfo->srh); + skb_reset_inner_headers(skb); + break; +#endif + case SEG6_IPTUN_MODE_ENCAP: + err = seg6_do_srh_encap(skb, tinfo->srh); + break; + } + + if (err) + return err; + + ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); + skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + + skb_set_inner_protocol(skb, skb->protocol); + + return 0; +} + +int seg6_input(struct sk_buff *skb) +{ + int err; + + err = seg6_do_srh(skb); + if (unlikely(err)) { + kfree_skb(skb); + return err; + } + + skb_dst_drop(skb); + ip6_route_input(skb); + + return dst_input(skb); +} + +int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + struct dst_entry *orig_dst = skb_dst(skb); + struct dst_entry *dst = NULL; + struct seg6_lwt *slwt; + int err = -EINVAL; + + err = seg6_do_srh(skb); + if (unlikely(err)) + goto drop; + + slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); + +#ifdef CONFIG_DST_CACHE + dst = dst_cache_get(&slwt->cache); +#endif + + if (unlikely(!dst)) { + struct ipv6hdr *hdr = ipv6_hdr(skb); + struct flowi6 fl6; + + fl6.daddr = hdr->daddr; + fl6.saddr = hdr->saddr; + fl6.flowlabel = ip6_flowinfo(hdr); + fl6.flowi6_mark = skb->mark; + fl6.flowi6_proto = hdr->nexthdr; + + dst = ip6_route_output(net, NULL, &fl6); + if (dst->error) { + err = dst->error; + dst_release(dst); + goto drop; + } + +#ifdef CONFIG_DST_CACHE + dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr); +#endif + } + + skb_dst_drop(skb); + skb_dst_set(skb, dst); + + return dst_output(net, sk, skb); +drop: + kfree_skb(skb); + return err; +} + +static int seg6_build_state(struct net_device *dev, struct nlattr *nla, + unsigned int family, const void *cfg, + struct lwtunnel_state **ts) +{ + struct nlattr *tb[SEG6_IPTUNNEL_MAX + 1]; + struct seg6_iptunnel_encap *tuninfo; + struct lwtunnel_state *newts; + int tuninfo_len, min_size; + struct seg6_lwt *slwt; + int err; + + err = nla_parse_nested(tb, SEG6_IPTUNNEL_MAX, nla, + seg6_iptunnel_policy); + + if (err < 0) + return err; + + if (!tb[SEG6_IPTUNNEL_SRH]) + return -EINVAL; + + tuninfo = nla_data(tb[SEG6_IPTUNNEL_SRH]); + tuninfo_len = nla_len(tb[SEG6_IPTUNNEL_SRH]); + + /* tuninfo must contain at least the iptunnel encap structure, + * the SRH and one segment + */ + min_size = sizeof(*tuninfo) + sizeof(struct ipv6_sr_hdr) + + sizeof(struct in6_addr); + if (tuninfo_len < min_size) + return -EINVAL; + + switch (tuninfo->mode) { +#ifdef CONFIG_IPV6_SEG6_INLINE + case SEG6_IPTUN_MODE_INLINE: + break; +#endif + case SEG6_IPTUN_MODE_ENCAP: + break; + default: + return -EINVAL; + } + + /* verify that SRH is consistent */ + if (!seg6_validate_srh(tuninfo->srh, tuninfo_len - sizeof(*tuninfo))) + return -EINVAL; + + newts = lwtunnel_state_alloc(tuninfo_len + sizeof(*slwt)); + if (!newts) + return -ENOMEM; + + slwt = seg6_lwt_lwtunnel(newts); + +#ifdef CONFIG_DST_CACHE + err = dst_cache_init(&slwt->cache, GFP_KERNEL); + if (err) { + kfree(newts); + return err; + } +#endif + + memcpy(&slwt->tuninfo, tuninfo, tuninfo_len); + + newts->type = LWTUNNEL_ENCAP_SEG6; + newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT | + LWTUNNEL_STATE_INPUT_REDIRECT; + newts->headroom = seg6_lwt_headroom(tuninfo); + + *ts = newts; + + return 0; +} + +#ifdef CONFIG_DST_CACHE +static void seg6_destroy_state(struct lwtunnel_state *lwt) +{ + dst_cache_destroy(&seg6_lwt_lwtunnel(lwt)->cache); +} +#endif + +static int seg6_fill_encap_info(struct sk_buff *skb, + struct lwtunnel_state *lwtstate) +{ + struct seg6_iptunnel_encap *tuninfo = seg6_encap_lwtunnel(lwtstate); + + if (nla_put_srh(skb, SEG6_IPTUNNEL_SRH, tuninfo)) + return -EMSGSIZE; + + return 0; +} + +static int seg6_encap_nlsize(struct lwtunnel_state *lwtstate) +{ + struct seg6_iptunnel_encap *tuninfo = seg6_encap_lwtunnel(lwtstate); + + return nla_total_size(SEG6_IPTUN_ENCAP_SIZE(tuninfo)); +} + +static int seg6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) +{ + struct seg6_iptunnel_encap *a_hdr = seg6_encap_lwtunnel(a); + struct seg6_iptunnel_encap *b_hdr = seg6_encap_lwtunnel(b); + int len = SEG6_IPTUN_ENCAP_SIZE(a_hdr); + + if (len != SEG6_IPTUN_ENCAP_SIZE(b_hdr)) + return 1; + + return memcmp(a_hdr, b_hdr, len); +} + +static const struct lwtunnel_encap_ops seg6_iptun_ops = { + .build_state = seg6_build_state, +#ifdef CONFIG_DST_CACHE + .destroy_state = seg6_destroy_state, +#endif + .output = seg6_output, + .input = seg6_input, + .fill_encap = seg6_fill_encap_info, + .get_encap_size = seg6_encap_nlsize, + .cmp_encap = seg6_encap_cmp, +}; + +int __init seg6_iptunnel_init(void) +{ + return lwtunnel_encap_add_ops(&seg6_iptun_ops, LWTUNNEL_ENCAP_SEG6); +} + +void seg6_iptunnel_exit(void) +{ + lwtunnel_encap_del_ops(&seg6_iptun_ops, LWTUNNEL_ENCAP_SEG6); +} -- cgit v1.2.3 From bf355b8d2c30a289232042cacc1cfaea4923936c Mon Sep 17 00:00:00 2001 From: David Lebrun Date: Tue, 8 Nov 2016 14:57:42 +0100 Subject: ipv6: sr: add core files for SR HMAC support This patch adds the necessary functions to compute and check the HMAC signature of an SR-enabled packet. Two HMAC algorithms are supported: hmac(sha1) and hmac(sha256). In order to avoid dynamic memory allocation for each HMAC computation, a per-cpu ring buffer is allocated for this purpose. A new per-interface sysctl called seg6_require_hmac is added, allowing a user-defined policy for processing HMAC-signed SR-enabled packets. A value of -1 means that the HMAC field will always be ignored. A value of 0 means that if an HMAC field is present, its validity will be enforced (the packet is dropped is the signature is incorrect). Finally, a value of 1 means that any SR-enabled packet that does not contain an HMAC signature or whose signature is incorrect will be dropped. Signed-off-by: David Lebrun Signed-off-by: David S. Miller --- include/linux/ipv6.h | 3 + include/linux/seg6_hmac.h | 6 + include/net/seg6.h | 4 + include/net/seg6_hmac.h | 62 ++++++ include/uapi/linux/ipv6.h | 1 + include/uapi/linux/seg6_hmac.h | 21 ++ net/ipv6/Kconfig | 12 + net/ipv6/Makefile | 1 + net/ipv6/addrconf.c | 18 ++ net/ipv6/seg6_hmac.c | 484 +++++++++++++++++++++++++++++++++++++++++ 10 files changed, 612 insertions(+) create mode 100644 include/linux/seg6_hmac.h create mode 100644 include/net/seg6_hmac.h create mode 100644 include/uapi/linux/seg6_hmac.h create mode 100644 net/ipv6/seg6_hmac.c (limited to 'include/uapi/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 68d3f71f0abf..93756585521f 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -65,6 +65,9 @@ struct ipv6_devconf { __s32 use_oif_addrs_only; __s32 keep_addr_on_down; __s32 seg6_enabled; +#ifdef CONFIG_IPV6_SEG6_HMAC + __s32 seg6_require_hmac; +#endif struct ctl_table_header *sysctl_header; }; diff --git a/include/linux/seg6_hmac.h b/include/linux/seg6_hmac.h new file mode 100644 index 000000000000..da437ebdc6cd --- /dev/null +++ b/include/linux/seg6_hmac.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_SEG6_HMAC_H +#define _LINUX_SEG6_HMAC_H + +#include + +#endif diff --git a/include/net/seg6.h b/include/net/seg6.h index ff5da0ce83e9..4e0357517d79 100644 --- a/include/net/seg6.h +++ b/include/net/seg6.h @@ -18,6 +18,7 @@ #include #include #include +#include static inline void update_csum_diff4(struct sk_buff *skb, __be32 from, __be32 to) @@ -41,6 +42,9 @@ static inline void update_csum_diff16(struct sk_buff *skb, __be32 *from, struct seg6_pernet_data { struct mutex lock; struct in6_addr __rcu *tun_src; +#ifdef CONFIG_IPV6_SEG6_HMAC + struct rhashtable hmac_infos; +#endif }; static inline struct seg6_pernet_data *seg6_pernet(struct net *net) diff --git a/include/net/seg6_hmac.h b/include/net/seg6_hmac.h new file mode 100644 index 000000000000..69c3a106056b --- /dev/null +++ b/include/net/seg6_hmac.h @@ -0,0 +1,62 @@ +/* + * SR-IPv6 implementation + * + * Author: + * David Lebrun + * + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _NET_SEG6_HMAC_H +#define _NET_SEG6_HMAC_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define SEG6_HMAC_MAX_DIGESTSIZE 160 +#define SEG6_HMAC_RING_SIZE 256 + +struct seg6_hmac_info { + struct rhash_head node; + struct rcu_head rcu; + + u32 hmackeyid; + char secret[SEG6_HMAC_SECRET_LEN]; + u8 slen; + u8 alg_id; +}; + +struct seg6_hmac_algo { + u8 alg_id; + char name[64]; + struct crypto_shash * __percpu *tfms; + struct shash_desc * __percpu *shashs; +}; + +extern int seg6_hmac_compute(struct seg6_hmac_info *hinfo, + struct ipv6_sr_hdr *hdr, struct in6_addr *saddr, + u8 *output); +extern struct seg6_hmac_info *seg6_hmac_info_lookup(struct net *net, u32 key); +extern int seg6_hmac_info_add(struct net *net, u32 key, + struct seg6_hmac_info *hinfo); +extern int seg6_hmac_info_del(struct net *net, u32 key); +extern int seg6_push_hmac(struct net *net, struct in6_addr *saddr, + struct ipv6_sr_hdr *srh); +extern bool seg6_hmac_validate_skb(struct sk_buff *skb); +extern int seg6_hmac_init(void); +extern void seg6_hmac_exit(void); +extern int seg6_hmac_net_init(struct net *net); +extern void seg6_hmac_net_exit(struct net *net); + +#endif diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 7ff1d654e333..53561be1ac21 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -180,6 +180,7 @@ enum { DEVCONF_KEEP_ADDR_ON_DOWN, DEVCONF_RTR_SOLICIT_MAX_INTERVAL, DEVCONF_SEG6_ENABLED, + DEVCONF_SEG6_REQUIRE_HMAC, DEVCONF_MAX }; diff --git a/include/uapi/linux/seg6_hmac.h b/include/uapi/linux/seg6_hmac.h new file mode 100644 index 000000000000..b652dfd51bc5 --- /dev/null +++ b/include/uapi/linux/seg6_hmac.h @@ -0,0 +1,21 @@ +#ifndef _UAPI_LINUX_SEG6_HMAC_H +#define _UAPI_LINUX_SEG6_HMAC_H + +#include + +#define SEG6_HMAC_SECRET_LEN 64 +#define SEG6_HMAC_FIELD_LEN 32 + +struct sr6_tlv_hmac { + struct sr6_tlv tlvhdr; + __u16 reserved; + __be32 hmackeyid; + __u8 hmac[SEG6_HMAC_FIELD_LEN]; +}; + +enum { + SEG6_HMAC_ALGO_SHA1 = 1, + SEG6_HMAC_ALGO_SHA256 = 2, +}; + +#endif diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 1123a001d729..0f00811a785f 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -301,4 +301,16 @@ config IPV6_SEG6_INLINE If unsure, say N. +config IPV6_SEG6_HMAC + bool "IPv6: Segment Routing HMAC support" + depends on IPV6 + select CRYPTO_HMAC + select CRYPTO_SHA1 + select CRYPTO_SHA256 + ---help--- + Support for HMAC signature generation and verification + of SR-enabled packets. + + If unsure, say N. + endif # IPV6 diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 59ee92fb3689..129cad2ba960 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -44,6 +44,7 @@ obj-$(CONFIG_IPV6_SIT) += sit.o obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o obj-$(CONFIG_IPV6_GRE) += ip6_gre.o obj-$(CONFIG_IPV6_FOU) += fou6.o +obj-$(CONFIG_IPV6_SEG6_HMAC) += seg6_hmac.o obj-y += addrconf_core.o exthdrs_core.o ip6_checksum.o ip6_icmp.o obj-$(CONFIG_INET) += output_core.o protocol.o $(ipv6-offload) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2ac6cb460af0..86219c0a0104 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -239,6 +239,9 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .ignore_routes_with_linkdown = 0, .keep_addr_on_down = 0, .seg6_enabled = 0, +#ifdef CONFIG_IPV6_SEG6_HMAC + .seg6_require_hmac = 0, +#endif }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -286,6 +289,9 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .ignore_routes_with_linkdown = 0, .keep_addr_on_down = 0, .seg6_enabled = 0, +#ifdef CONFIG_IPV6_SEG6_HMAC + .seg6_require_hmac = 0, +#endif }; /* Check if a valid qdisc is available */ @@ -4947,6 +4953,9 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_DROP_UNSOLICITED_NA] = cnf->drop_unsolicited_na; array[DEVCONF_KEEP_ADDR_ON_DOWN] = cnf->keep_addr_on_down; array[DEVCONF_SEG6_ENABLED] = cnf->seg6_enabled; +#ifdef CONFIG_IPV6_SEG6_HMAC + array[DEVCONF_SEG6_REQUIRE_HMAC] = cnf->seg6_require_hmac; +#endif } static inline size_t inet6_ifla6_size(void) @@ -6045,6 +6054,15 @@ static const struct ctl_table addrconf_sysctl[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#ifdef CONFIG_IPV6_SEG6_HMAC + { + .procname = "seg6_require_hmac", + .data = &ipv6_devconf.seg6_require_hmac, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif { /* sentinel */ } diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c new file mode 100644 index 000000000000..ef1c8a46e7ac --- /dev/null +++ b/net/ipv6/seg6_hmac.c @@ -0,0 +1,484 @@ +/* + * SR-IPv6 implementation -- HMAC functions + * + * Author: + * David Lebrun + * + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +static char * __percpu *hmac_ring; + +static int seg6_hmac_cmpfn(struct rhashtable_compare_arg *arg, const void *obj) +{ + const struct seg6_hmac_info *hinfo = obj; + + return (hinfo->hmackeyid != *(__u32 *)arg->key); +} + +static inline void seg6_hinfo_release(struct seg6_hmac_info *hinfo) +{ + kfree_rcu(hinfo, rcu); +} + +static void seg6_free_hi(void *ptr, void *arg) +{ + struct seg6_hmac_info *hinfo = (struct seg6_hmac_info *)ptr; + + if (hinfo) + seg6_hinfo_release(hinfo); +} + +static const struct rhashtable_params rht_params = { + .head_offset = offsetof(struct seg6_hmac_info, node), + .key_offset = offsetof(struct seg6_hmac_info, hmackeyid), + .key_len = sizeof(u32), + .automatic_shrinking = true, + .obj_cmpfn = seg6_hmac_cmpfn, +}; + +static struct seg6_hmac_algo hmac_algos[] = { + { + .alg_id = SEG6_HMAC_ALGO_SHA1, + .name = "hmac(sha1)", + }, + { + .alg_id = SEG6_HMAC_ALGO_SHA256, + .name = "hmac(sha256)", + }, +}; + +static struct sr6_tlv_hmac *seg6_get_tlv_hmac(struct ipv6_sr_hdr *srh) +{ + struct sr6_tlv_hmac *tlv; + + if (srh->hdrlen < (srh->first_segment + 1) * 2 + 5) + return NULL; + + if (!sr_has_hmac(srh)) + return NULL; + + tlv = (struct sr6_tlv_hmac *) + ((char *)srh + ((srh->hdrlen + 1) << 3) - 40); + + if (tlv->tlvhdr.type != SR6_TLV_HMAC || tlv->tlvhdr.len != 38) + return NULL; + + return tlv; +} + +static struct seg6_hmac_algo *__hmac_get_algo(u8 alg_id) +{ + struct seg6_hmac_algo *algo; + int i, alg_count; + + alg_count = sizeof(hmac_algos) / sizeof(struct seg6_hmac_algo); + for (i = 0; i < alg_count; i++) { + algo = &hmac_algos[i]; + if (algo->alg_id == alg_id) + return algo; + } + + return NULL; +} + +static int __do_hmac(struct seg6_hmac_info *hinfo, const char *text, u8 psize, + u8 *output, int outlen) +{ + struct seg6_hmac_algo *algo; + struct crypto_shash *tfm; + struct shash_desc *shash; + int ret, dgsize; + + algo = __hmac_get_algo(hinfo->alg_id); + if (!algo) + return -ENOENT; + + tfm = *this_cpu_ptr(algo->tfms); + + dgsize = crypto_shash_digestsize(tfm); + if (dgsize > outlen) { + pr_debug("sr-ipv6: __do_hmac: digest size too big (%d / %d)\n", + dgsize, outlen); + return -ENOMEM; + } + + ret = crypto_shash_setkey(tfm, hinfo->secret, hinfo->slen); + if (ret < 0) { + pr_debug("sr-ipv6: crypto_shash_setkey failed: err %d\n", ret); + goto failed; + } + + shash = *this_cpu_ptr(algo->shashs); + shash->tfm = tfm; + + ret = crypto_shash_digest(shash, text, psize, output); + if (ret < 0) { + pr_debug("sr-ipv6: crypto_shash_digest failed: err %d\n", ret); + goto failed; + } + + return dgsize; + +failed: + return ret; +} + +int seg6_hmac_compute(struct seg6_hmac_info *hinfo, struct ipv6_sr_hdr *hdr, + struct in6_addr *saddr, u8 *output) +{ + __be32 hmackeyid = cpu_to_be32(hinfo->hmackeyid); + u8 tmp_out[SEG6_HMAC_MAX_DIGESTSIZE]; + int plen, i, dgsize, wrsize; + char *ring, *off; + + /* a 160-byte buffer for digest output allows to store highest known + * hash function (RadioGatun) with up to 1216 bits + */ + + /* saddr(16) + first_seg(1) + cleanup(1) + keyid(4) + seglist(16n) */ + plen = 16 + 1 + 1 + 4 + (hdr->first_segment + 1) * 16; + + /* this limit allows for 14 segments */ + if (plen >= SEG6_HMAC_RING_SIZE) + return -EMSGSIZE; + + /* Let's build the HMAC text on the ring buffer. The text is composed + * as follows, in order: + * + * 1. Source IPv6 address (128 bits) + * 2. first_segment value (8 bits) + * 3. cleanup flag (8 bits: highest bit is cleanup value, others are 0) + * 4. HMAC Key ID (32 bits) + * 5. All segments in the segments list (n * 128 bits) + */ + + local_bh_disable(); + ring = *this_cpu_ptr(hmac_ring); + off = ring; + + /* source address */ + memcpy(off, saddr, 16); + off += 16; + + /* first_segment value */ + *off++ = hdr->first_segment; + + /* cleanup flag */ + *off++ = !!(sr_has_cleanup(hdr)) << 7; + + /* HMAC Key ID */ + memcpy(off, &hmackeyid, 4); + off += 4; + + /* all segments in the list */ + for (i = 0; i < hdr->first_segment + 1; i++) { + memcpy(off, hdr->segments + i, 16); + off += 16; + } + + dgsize = __do_hmac(hinfo, ring, plen, tmp_out, + SEG6_HMAC_MAX_DIGESTSIZE); + local_bh_enable(); + + if (dgsize < 0) + return dgsize; + + wrsize = SEG6_HMAC_FIELD_LEN; + if (wrsize > dgsize) + wrsize = dgsize; + + memset(output, 0, SEG6_HMAC_FIELD_LEN); + memcpy(output, tmp_out, wrsize); + + return 0; +} +EXPORT_SYMBOL(seg6_hmac_compute); + +/* checks if an incoming SR-enabled packet's HMAC status matches + * the incoming policy. + * + * called with rcu_read_lock() + */ +bool seg6_hmac_validate_skb(struct sk_buff *skb) +{ + u8 hmac_output[SEG6_HMAC_FIELD_LEN]; + struct net *net = dev_net(skb->dev); + struct seg6_hmac_info *hinfo; + struct sr6_tlv_hmac *tlv; + struct ipv6_sr_hdr *srh; + struct inet6_dev *idev; + + idev = __in6_dev_get(skb->dev); + + srh = (struct ipv6_sr_hdr *)skb_transport_header(skb); + + tlv = seg6_get_tlv_hmac(srh); + + /* mandatory check but no tlv */ + if (idev->cnf.seg6_require_hmac > 0 && !tlv) + return false; + + /* no check */ + if (idev->cnf.seg6_require_hmac < 0) + return true; + + /* check only if present */ + if (idev->cnf.seg6_require_hmac == 0 && !tlv) + return true; + + /* now, seg6_require_hmac >= 0 && tlv */ + + hinfo = seg6_hmac_info_lookup(net, be32_to_cpu(tlv->hmackeyid)); + if (!hinfo) + return false; + + if (seg6_hmac_compute(hinfo, srh, &ipv6_hdr(skb)->saddr, hmac_output)) + return false; + + if (memcmp(hmac_output, tlv->hmac, SEG6_HMAC_FIELD_LEN) != 0) + return false; + + return true; +} +EXPORT_SYMBOL(seg6_hmac_validate_skb); + +/* called with rcu_read_lock() */ +struct seg6_hmac_info *seg6_hmac_info_lookup(struct net *net, u32 key) +{ + struct seg6_pernet_data *sdata = seg6_pernet(net); + struct seg6_hmac_info *hinfo; + + hinfo = rhashtable_lookup_fast(&sdata->hmac_infos, &key, rht_params); + + return hinfo; +} +EXPORT_SYMBOL(seg6_hmac_info_lookup); + +int seg6_hmac_info_add(struct net *net, u32 key, struct seg6_hmac_info *hinfo) +{ + struct seg6_pernet_data *sdata = seg6_pernet(net); + int err; + + err = rhashtable_lookup_insert_fast(&sdata->hmac_infos, &hinfo->node, + rht_params); + + return err; +} +EXPORT_SYMBOL(seg6_hmac_info_add); + +int seg6_hmac_info_del(struct net *net, u32 key) +{ + struct seg6_pernet_data *sdata = seg6_pernet(net); + struct seg6_hmac_info *hinfo; + int err = -ENOENT; + + hinfo = rhashtable_lookup_fast(&sdata->hmac_infos, &key, rht_params); + if (!hinfo) + goto out; + + err = rhashtable_remove_fast(&sdata->hmac_infos, &hinfo->node, + rht_params); + if (err) + goto out; + + seg6_hinfo_release(hinfo); + +out: + return err; +} +EXPORT_SYMBOL(seg6_hmac_info_del); + +int seg6_push_hmac(struct net *net, struct in6_addr *saddr, + struct ipv6_sr_hdr *srh) +{ + struct seg6_hmac_info *hinfo; + struct sr6_tlv_hmac *tlv; + int err = -ENOENT; + + tlv = seg6_get_tlv_hmac(srh); + if (!tlv) + return -EINVAL; + + rcu_read_lock(); + + hinfo = seg6_hmac_info_lookup(net, be32_to_cpu(tlv->hmackeyid)); + if (!hinfo) + goto out; + + memset(tlv->hmac, 0, SEG6_HMAC_FIELD_LEN); + err = seg6_hmac_compute(hinfo, srh, saddr, tlv->hmac); + +out: + rcu_read_unlock(); + return err; +} +EXPORT_SYMBOL(seg6_push_hmac); + +static int seg6_hmac_init_ring(void) +{ + int i; + + hmac_ring = alloc_percpu(char *); + + if (!hmac_ring) + return -ENOMEM; + + for_each_possible_cpu(i) { + char *ring = kzalloc(SEG6_HMAC_RING_SIZE, GFP_KERNEL); + + if (!ring) + return -ENOMEM; + + *per_cpu_ptr(hmac_ring, i) = ring; + } + + return 0; +} + +static int seg6_hmac_init_algo(void) +{ + struct seg6_hmac_algo *algo; + struct crypto_shash *tfm; + struct shash_desc *shash; + int i, alg_count, cpu; + + alg_count = sizeof(hmac_algos) / sizeof(struct seg6_hmac_algo); + + for (i = 0; i < alg_count; i++) { + struct crypto_shash **p_tfm; + int shsize; + + algo = &hmac_algos[i]; + algo->tfms = alloc_percpu(struct crypto_shash *); + if (!algo->tfms) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + tfm = crypto_alloc_shash(algo->name, 0, GFP_KERNEL); + if (IS_ERR(tfm)) + return PTR_ERR(tfm); + p_tfm = per_cpu_ptr(algo->tfms, cpu); + *p_tfm = tfm; + } + + p_tfm = this_cpu_ptr(algo->tfms); + tfm = *p_tfm; + + shsize = sizeof(*shash) + crypto_shash_descsize(tfm); + + algo->shashs = alloc_percpu(struct shash_desc *); + if (!algo->shashs) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + shash = kzalloc(shsize, GFP_KERNEL); + if (!shash) + return -ENOMEM; + *per_cpu_ptr(algo->shashs, cpu) = shash; + } + } + + return 0; +} + +int __init seg6_hmac_init(void) +{ + int ret; + + ret = seg6_hmac_init_ring(); + if (ret < 0) + goto out; + + ret = seg6_hmac_init_algo(); + +out: + return ret; +} +EXPORT_SYMBOL(seg6_hmac_init); + +int __net_init seg6_hmac_net_init(struct net *net) +{ + struct seg6_pernet_data *sdata = seg6_pernet(net); + + rhashtable_init(&sdata->hmac_infos, &rht_params); + + return 0; +} +EXPORT_SYMBOL(seg6_hmac_net_init); + +void seg6_hmac_exit(void) +{ + struct seg6_hmac_algo *algo = NULL; + int i, alg_count, cpu; + + for_each_possible_cpu(i) { + char *ring = *per_cpu_ptr(hmac_ring, i); + + kfree(ring); + } + free_percpu(hmac_ring); + + alg_count = sizeof(hmac_algos) / sizeof(struct seg6_hmac_algo); + for (i = 0; i < alg_count; i++) { + algo = &hmac_algos[i]; + for_each_possible_cpu(cpu) { + struct crypto_shash *tfm; + struct shash_desc *shash; + + shash = *per_cpu_ptr(algo->shashs, cpu); + kfree(shash); + tfm = *per_cpu_ptr(algo->tfms, cpu); + crypto_free_shash(tfm); + } + free_percpu(algo->tfms); + free_percpu(algo->shashs); + } +} +EXPORT_SYMBOL(seg6_hmac_exit); + +void __net_exit seg6_hmac_net_exit(struct net *net) +{ + struct seg6_pernet_data *sdata = seg6_pernet(net); + + rhashtable_free_and_destroy(&sdata->hmac_infos, seg6_free_hi, NULL); +} +EXPORT_SYMBOL(seg6_hmac_net_exit); -- cgit v1.2.3 From 91820da6ae85904d95ed53bf3a83f9ec44a6b80a Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Thu, 10 Nov 2016 16:28:23 +0100 Subject: openvswitch: add Ethernet push and pop actions It's not allowed to push Ethernet header in front of another Ethernet header. It's not allowed to pop Ethernet header if there's a vlan tag. This preserves the invariant that L3 packet never has a vlan tag. Based on previous versions by Lorand Jakab and Simon Horman. Signed-off-by: Lorand Jakab Signed-off-by: Simon Horman Signed-off-by: Jiri Benc Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 15 ++++++++++++ net/openvswitch/actions.c | 49 ++++++++++++++++++++++++++++++++++++++++ net/openvswitch/flow_netlink.c | 18 +++++++++++++++ 3 files changed, 82 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 59ed3992c760..375d812fea36 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -705,6 +705,15 @@ enum ovs_nat_attr { #define OVS_NAT_ATTR_MAX (__OVS_NAT_ATTR_MAX - 1) +/* + * struct ovs_action_push_eth - %OVS_ACTION_ATTR_PUSH_ETH action argument. + * @addresses: Source and destination MAC addresses. + * @eth_type: Ethernet type + */ +struct ovs_action_push_eth { + struct ovs_key_ethernet addresses; +}; + /** * enum ovs_action_attr - Action types. * @@ -738,6 +747,10 @@ enum ovs_nat_attr { * is no MPLS label stack, as determined by ethertype, no action is taken. * @OVS_ACTION_ATTR_CT: Track the connection. Populate the conntrack-related * entries in the flow key. + * @OVS_ACTION_ATTR_PUSH_ETH: Push a new outermost Ethernet header onto the + * packet. + * @OVS_ACTION_ATTR_POP_ETH: Pop the outermost Ethernet header off the + * packet. * * Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all * fields within a header are modifiable, e.g. the IPv4 protocol and fragment @@ -765,6 +778,8 @@ enum ovs_action_attr { * bits. */ OVS_ACTION_ATTR_CT, /* Nested OVS_CT_ATTR_* . */ OVS_ACTION_ATTR_TRUNC, /* u32 struct ovs_action_trunc. */ + OVS_ACTION_ATTR_PUSH_ETH, /* struct ovs_action_push_eth. */ + OVS_ACTION_ATTR_POP_ETH, /* No argument. */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 064cbcb7b0c5..514f7bcf7c63 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -317,6 +317,47 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key, return 0; } +/* pop_eth does not support VLAN packets as this action is never called + * for them. + */ +static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key) +{ + skb_pull_rcsum(skb, ETH_HLEN); + skb_reset_mac_header(skb); + skb_reset_mac_len(skb); + + /* safe right before invalidate_flow_key */ + key->mac_proto = MAC_PROTO_NONE; + invalidate_flow_key(key); + return 0; +} + +static int push_eth(struct sk_buff *skb, struct sw_flow_key *key, + const struct ovs_action_push_eth *ethh) +{ + struct ethhdr *hdr; + + /* Add the new Ethernet header */ + if (skb_cow_head(skb, ETH_HLEN) < 0) + return -ENOMEM; + + skb_push(skb, ETH_HLEN); + skb_reset_mac_header(skb); + skb_reset_mac_len(skb); + + hdr = eth_hdr(skb); + ether_addr_copy(hdr->h_source, ethh->addresses.eth_src); + ether_addr_copy(hdr->h_dest, ethh->addresses.eth_dst); + hdr->h_proto = skb->protocol; + + skb_postpush_rcsum(skb, hdr, ETH_HLEN); + + /* safe right before invalidate_flow_key */ + key->mac_proto = MAC_PROTO_ETHERNET; + invalidate_flow_key(key); + return 0; +} + static void update_ip_l4_checksum(struct sk_buff *skb, struct iphdr *nh, __be32 addr, __be32 new_addr) { @@ -1200,6 +1241,14 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, if (err) return err == -EINPROGRESS ? 0 : err; break; + + case OVS_ACTION_ATTR_PUSH_ETH: + err = push_eth(skb, key, nla_data(a)); + break; + + case OVS_ACTION_ATTR_POP_ETH: + err = pop_eth(skb, key); + break; } if (unlikely(err)) { diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index c3d0cc4321c3..d19044f2b1f4 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2383,6 +2383,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash), [OVS_ACTION_ATTR_CT] = (u32)-1, [OVS_ACTION_ATTR_TRUNC] = sizeof(struct ovs_action_trunc), + [OVS_ACTION_ATTR_PUSH_ETH] = sizeof(struct ovs_action_push_eth), + [OVS_ACTION_ATTR_POP_ETH] = 0, }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -2517,6 +2519,22 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, skip_copy = true; break; + case OVS_ACTION_ATTR_PUSH_ETH: + /* Disallow pushing an Ethernet header if one + * is already present */ + if (mac_proto != MAC_PROTO_NONE) + return -EINVAL; + mac_proto = MAC_PROTO_NONE; + break; + + case OVS_ACTION_ATTR_POP_ETH: + if (mac_proto != MAC_PROTO_ETHERNET) + return -EINVAL; + if (vlan_tci & htons(VLAN_TAG_PRESENT)) + return -EINVAL; + mac_proto = MAC_PROTO_ETHERNET; + break; + default: OVS_NLERR(log, "Unknown Action type %d", type); return -EINVAL; -- cgit v1.2.3 From 10b217681ddec4fa3ddb375bb188fec504523da4 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Thu, 10 Nov 2016 13:21:42 +0200 Subject: net: bpqether.h: remove if_ether.h guard __LINUX_IF_ETHER_H is not defined anywhere, and if_ether.h can keep itself from double inclusion, though it uses a single underscore prefix. Signed-off-by: Baruch Siach Signed-off-by: David S. Miller --- include/uapi/linux/bpqether.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpqether.h b/include/uapi/linux/bpqether.h index a6c35e1a89ad..05865edaefda 100644 --- a/include/uapi/linux/bpqether.h +++ b/include/uapi/linux/bpqether.h @@ -5,9 +5,7 @@ * Defines for the BPQETHER pseudo device driver */ -#ifndef __LINUX_IF_ETHER_H #include -#endif #define SIOCSBPQETHOPT (SIOCDEVPRIVATE+0) /* reserved */ #define SIOCSBPQETHADDR (SIOCDEVPRIVATE+1) -- cgit v1.2.3 From 7b5b74efcca00f15c2aec1dc7175bfe34b6ec643 Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Thu, 10 Nov 2016 19:08:39 -0500 Subject: Revert "include/uapi/linux/atm_zatm.h: include linux/time.h" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit cf00713a655d ("include/uapi/linux/atm_zatm.h: include linux/time.h"). This attempted to fix userspace breakage that no longer existed when the patch was merged. Almost one year earlier, commit 70ba07b675b5 ("atm: remove 'struct zatm_t_hist'") deleted the struct in question. After this patch was merged, we now have to deal with people being unable to include this header in conjunction with standard C library headers like stdlib.h (which linux-atm does). Example breakage: x86_64-pc-linux-gnu-gcc -DHAVE_CONFIG_H -I. -I../.. -I./../q2931 -I./../saal \ -I. -DCPPFLAGS_TEST -I../../src/include -O2 -march=native -pipe -g \ -frecord-gcc-switches -freport-bug -Wimplicit-function-declaration \ -Wnonnull -Wstrict-aliasing -Wparentheses -Warray-bounds \ -Wfree-nonheap-object -Wreturn-local-addr -fno-strict-aliasing -Wall \ -Wshadow -Wpointer-arith -Wwrite-strings -Wstrict-prototypes -c zntune.c In file included from /usr/include/linux/atm_zatm.h:17:0, from zntune.c:17: /usr/include/linux/time.h:9:8: error: redefinition of ‘struct timespec’ struct timespec { ^ In file included from /usr/include/sys/select.h:43:0, from /usr/include/sys/types.h:219, from /usr/include/stdlib.h:314, from zntune.c:9: /usr/include/time.h:120:8: note: originally defined here struct timespec ^ Signed-off-by: Mike Frysinger Acked-by: Mikko Rapeli Signed-off-by: David S. Miller --- include/uapi/linux/atm_zatm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/atm_zatm.h b/include/uapi/linux/atm_zatm.h index 5cd4d4d2dd1d..9c9c6ad55f14 100644 --- a/include/uapi/linux/atm_zatm.h +++ b/include/uapi/linux/atm_zatm.h @@ -14,7 +14,6 @@ #include #include -#include #define ZATM_GETPOOL _IOW('a',ATMIOC_SARPRV+1,struct atmif_sioc) /* get pool statistics */ -- cgit v1.2.3 From 29ba732acbeece1e34c68483d1ec1f3720fa1bb3 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 11 Nov 2016 10:55:09 -0800 Subject: bpf: Add BPF_MAP_TYPE_LRU_HASH Provide a LRU version of the existing BPF_MAP_TYPE_HASH. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 8 ++ kernel/bpf/hashtab.c | 266 ++++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 260 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e2f38e0091b6..ed8c6799fb14 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -85,6 +85,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PERCPU_ARRAY, BPF_MAP_TYPE_STACK_TRACE, BPF_MAP_TYPE_CGROUP_ARRAY, + BPF_MAP_TYPE_LRU_HASH, }; enum bpf_prog_type { @@ -106,6 +107,13 @@ enum bpf_prog_type { #define BPF_EXIST 2 /* update existing element */ #define BPF_F_NO_PREALLOC (1U << 0) +/* Instead of having one common LRU list in the + * BPF_MAP_TYPE_LRU_HASH map, use a percpu LRU list + * which can scale and perform better. + * Note, the LRU nodes (including free nodes) cannot be moved + * across different LRU lists. + */ +#define BPF_F_NO_COMMON_LRU (1U << 1) union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index b478d80f9771..4a9e71a7c41f 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -15,6 +15,7 @@ #include #include #include "percpu_freelist.h" +#include "bpf_lru_list.h" struct bucket { struct hlist_head head; @@ -25,7 +26,10 @@ struct bpf_htab { struct bpf_map map; struct bucket *buckets; void *elems; - struct pcpu_freelist freelist; + union { + struct pcpu_freelist freelist; + struct bpf_lru lru; + }; void __percpu *extra_elems; atomic_t count; /* number of elements in this hashtable */ u32 n_buckets; /* number of hash buckets */ @@ -48,11 +52,19 @@ struct htab_elem { union { struct rcu_head rcu; enum extra_elem_state state; + struct bpf_lru_node lru_node; }; u32 hash; char key[0] __aligned(8); }; +static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node); + +static bool htab_is_lru(const struct bpf_htab *htab) +{ + return htab->map.map_type == BPF_MAP_TYPE_LRU_HASH; +} + static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size, void __percpu *pptr) { @@ -87,7 +99,22 @@ free_elems: vfree(htab->elems); } -static int prealloc_elems_and_freelist(struct bpf_htab *htab) +static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key, + u32 hash) +{ + struct bpf_lru_node *node = bpf_lru_pop_free(&htab->lru, hash); + struct htab_elem *l; + + if (node) { + l = container_of(node, struct htab_elem, lru_node); + memcpy(l->key, key, htab->map.key_size); + return l; + } + + return NULL; +} + +static int prealloc_init(struct bpf_htab *htab) { int err = -ENOMEM, i; @@ -110,12 +137,27 @@ static int prealloc_elems_and_freelist(struct bpf_htab *htab) } skip_percpu_elems: - err = pcpu_freelist_init(&htab->freelist); + if (htab_is_lru(htab)) + err = bpf_lru_init(&htab->lru, + htab->map.map_flags & BPF_F_NO_COMMON_LRU, + offsetof(struct htab_elem, hash) - + offsetof(struct htab_elem, lru_node), + htab_lru_map_delete_node, + htab); + else + err = pcpu_freelist_init(&htab->freelist); + if (err) goto free_elems; - pcpu_freelist_populate(&htab->freelist, htab->elems, htab->elem_size, - htab->map.max_entries); + if (htab_is_lru(htab)) + bpf_lru_populate(&htab->lru, htab->elems, + offsetof(struct htab_elem, lru_node), + htab->elem_size, htab->map.max_entries); + else + pcpu_freelist_populate(&htab->freelist, htab->elems, + htab->elem_size, htab->map.max_entries); + return 0; free_elems: @@ -123,6 +165,16 @@ free_elems: return err; } +static void prealloc_destroy(struct bpf_htab *htab) +{ + htab_free_elems(htab); + + if (htab_is_lru(htab)) + bpf_lru_destroy(&htab->lru); + else + pcpu_freelist_destroy(&htab->freelist); +} + static int alloc_extra_elems(struct bpf_htab *htab) { void __percpu *pptr; @@ -144,14 +196,34 @@ static int alloc_extra_elems(struct bpf_htab *htab) static struct bpf_map *htab_map_alloc(union bpf_attr *attr) { bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_HASH; + bool lru = attr->map_type == BPF_MAP_TYPE_LRU_HASH; + /* percpu_lru means each cpu has its own LRU list. + * it is different from BPF_MAP_TYPE_PERCPU_HASH where + * the map's value itself is percpu. percpu_lru has + * nothing to do with the map's value. + */ + bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU); + bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC); struct bpf_htab *htab; int err, i; u64 cost; - if (attr->map_flags & ~BPF_F_NO_PREALLOC) + if (lru && !capable(CAP_SYS_ADMIN)) + /* LRU implementation is much complicated than other + * maps. Hence, limit to CAP_SYS_ADMIN for now. + */ + return ERR_PTR(-EPERM); + + if (attr->map_flags & ~(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU)) /* reserved bits should not be used */ return ERR_PTR(-EINVAL); + if (!lru && percpu_lru) + return ERR_PTR(-EINVAL); + + if (lru && !prealloc) + return ERR_PTR(-ENOTSUPP); + htab = kzalloc(sizeof(*htab), GFP_USER); if (!htab) return ERR_PTR(-ENOMEM); @@ -171,6 +243,18 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) htab->map.value_size == 0) goto free_htab; + if (percpu_lru) { + /* ensure each CPU's lru list has >=1 elements. + * since we are at it, make each lru list has the same + * number of elements. + */ + htab->map.max_entries = roundup(attr->max_entries, + num_possible_cpus()); + if (htab->map.max_entries < attr->max_entries) + htab->map.max_entries = rounddown(attr->max_entries, + num_possible_cpus()); + } + /* hash table size must be power of 2 */ htab->n_buckets = roundup_pow_of_two(htab->map.max_entries); @@ -241,14 +325,17 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) raw_spin_lock_init(&htab->buckets[i].lock); } - if (!percpu) { + if (!percpu && !lru) { + /* lru itself can remove the least used element, so + * there is no need for an extra elem during map_update. + */ err = alloc_extra_elems(htab); if (err) goto free_buckets; } - if (!(attr->map_flags & BPF_F_NO_PREALLOC)) { - err = prealloc_elems_and_freelist(htab); + if (prealloc) { + err = prealloc_init(htab); if (err) goto free_extra_elems; } @@ -323,6 +410,46 @@ static void *htab_map_lookup_elem(struct bpf_map *map, void *key) return NULL; } +static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct htab_elem *l = __htab_map_lookup_elem(map, key); + + if (l) { + bpf_lru_node_set_ref(&l->lru_node); + return l->key + round_up(map->key_size, 8); + } + + return NULL; +} + +/* It is called from the bpf_lru_list when the LRU needs to delete + * older elements from the htab. + */ +static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) +{ + struct bpf_htab *htab = (struct bpf_htab *)arg; + struct htab_elem *l, *tgt_l; + struct hlist_head *head; + unsigned long flags; + struct bucket *b; + + tgt_l = container_of(node, struct htab_elem, lru_node); + b = __select_bucket(htab, tgt_l->hash); + head = &b->head; + + raw_spin_lock_irqsave(&b->lock, flags); + + hlist_for_each_entry_rcu(l, head, hash_node) + if (l == tgt_l) { + hlist_del_rcu(&l->hash_node); + break; + } + + raw_spin_unlock_irqrestore(&b->lock, flags); + + return l == tgt_l; +} + /* Called from syscall */ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { @@ -579,6 +706,70 @@ err: return ret; } +static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct htab_elem *l_new, *l_old = NULL; + struct hlist_head *head; + unsigned long flags; + struct bucket *b; + u32 key_size, hash; + int ret; + + if (unlikely(map_flags > BPF_EXIST)) + /* unknown flags */ + return -EINVAL; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + key_size = map->key_size; + + hash = htab_map_hash(key, key_size); + + b = __select_bucket(htab, hash); + head = &b->head; + + /* For LRU, we need to alloc before taking bucket's + * spinlock because getting free nodes from LRU may need + * to remove older elements from htab and this removal + * operation will need a bucket lock. + */ + l_new = prealloc_lru_pop(htab, key, hash); + if (!l_new) + return -ENOMEM; + memcpy(l_new->key + round_up(map->key_size, 8), value, map->value_size); + + /* bpf_map_update_elem() can be called in_irq() */ + raw_spin_lock_irqsave(&b->lock, flags); + + l_old = lookup_elem_raw(head, hash, key, key_size); + + ret = check_flags(htab, l_old, map_flags); + if (ret) + goto err; + + /* add new element to the head of the list, so that + * concurrent search will find it before old elem + */ + hlist_add_head_rcu(&l_new->hash_node, head); + if (l_old) { + bpf_lru_node_set_ref(&l_new->lru_node); + hlist_del_rcu(&l_old->hash_node); + } + ret = 0; + +err: + raw_spin_unlock_irqrestore(&b->lock, flags); + + if (ret) + bpf_lru_push_free(&htab->lru, &l_new->lru_node); + else if (l_old) + bpf_lru_push_free(&htab->lru, &l_old->lru_node); + + return ret; +} + static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags, bool onallcpus) @@ -671,6 +862,39 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) return ret; } +static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct hlist_head *head; + struct bucket *b; + struct htab_elem *l; + unsigned long flags; + u32 hash, key_size; + int ret = -ENOENT; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + key_size = map->key_size; + + hash = htab_map_hash(key, key_size); + b = __select_bucket(htab, hash); + head = &b->head; + + raw_spin_lock_irqsave(&b->lock, flags); + + l = lookup_elem_raw(head, hash, key, key_size); + + if (l) { + hlist_del_rcu(&l->hash_node); + ret = 0; + } + + raw_spin_unlock_irqrestore(&b->lock, flags); + if (l) + bpf_lru_push_free(&htab->lru, &l->lru_node); + return ret; +} + static void delete_all_elements(struct bpf_htab *htab) { int i; @@ -703,12 +927,11 @@ static void htab_map_free(struct bpf_map *map) * not have executed. Wait for them. */ rcu_barrier(); - if (htab->map.map_flags & BPF_F_NO_PREALLOC) { + if (htab->map.map_flags & BPF_F_NO_PREALLOC) delete_all_elements(htab); - } else { - htab_free_elems(htab); - pcpu_freelist_destroy(&htab->freelist); - } + else + prealloc_destroy(htab); + free_percpu(htab->extra_elems); kvfree(htab->buckets); kfree(htab); @@ -728,6 +951,20 @@ static struct bpf_map_type_list htab_type __read_mostly = { .type = BPF_MAP_TYPE_HASH, }; +static const struct bpf_map_ops htab_lru_ops = { + .map_alloc = htab_map_alloc, + .map_free = htab_map_free, + .map_get_next_key = htab_map_get_next_key, + .map_lookup_elem = htab_lru_map_lookup_elem, + .map_update_elem = htab_lru_map_update_elem, + .map_delete_elem = htab_lru_map_delete_elem, +}; + +static struct bpf_map_type_list htab_lru_type __read_mostly = { + .ops = &htab_lru_ops, + .type = BPF_MAP_TYPE_LRU_HASH, +}; + /* Called from eBPF program */ static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key) { @@ -798,6 +1035,7 @@ static int __init register_htab_map(void) { bpf_register_map_type(&htab_type); bpf_register_map_type(&htab_percpu_type); + bpf_register_map_type(&htab_lru_type); return 0; } late_initcall(register_htab_map); -- cgit v1.2.3 From 8f8449384ec364ba2a654f11f94e754e4ff719e0 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 11 Nov 2016 10:55:10 -0800 Subject: bpf: Add BPF_MAP_TYPE_LRU_PERCPU_HASH Provide a LRU version of the existing BPF_MAP_TYPE_PERCPU_HASH Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 3 +- kernel/bpf/hashtab.c | 129 ++++++++++++++++++++++++++++++++++++++++++++--- kernel/bpf/syscall.c | 8 ++- 3 files changed, 131 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ed8c6799fb14..7d9b2832c280 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -86,6 +86,7 @@ enum bpf_map_type { BPF_MAP_TYPE_STACK_TRACE, BPF_MAP_TYPE_CGROUP_ARRAY, BPF_MAP_TYPE_LRU_HASH, + BPF_MAP_TYPE_LRU_PERCPU_HASH, }; enum bpf_prog_type { @@ -108,7 +109,7 @@ enum bpf_prog_type { #define BPF_F_NO_PREALLOC (1U << 0) /* Instead of having one common LRU list in the - * BPF_MAP_TYPE_LRU_HASH map, use a percpu LRU list + * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list * which can scale and perform better. * Note, the LRU nodes (including free nodes) cannot be moved * across different LRU lists. diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 4a9e71a7c41f..34debc1a9641 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -62,7 +62,14 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node); static bool htab_is_lru(const struct bpf_htab *htab) { - return htab->map.map_type == BPF_MAP_TYPE_LRU_HASH; + return htab->map.map_type == BPF_MAP_TYPE_LRU_HASH || + htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH; +} + +static bool htab_is_percpu(const struct bpf_htab *htab) +{ + return htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH || + htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH; } static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size, @@ -85,7 +92,7 @@ static void htab_free_elems(struct bpf_htab *htab) { int i; - if (htab->map.map_type != BPF_MAP_TYPE_PERCPU_HASH) + if (!htab_is_percpu(htab)) goto free_elems; for (i = 0; i < htab->map.max_entries; i++) { @@ -122,7 +129,7 @@ static int prealloc_init(struct bpf_htab *htab) if (!htab->elems) return -ENOMEM; - if (htab->map.map_type != BPF_MAP_TYPE_PERCPU_HASH) + if (!htab_is_percpu(htab)) goto skip_percpu_elems; for (i = 0; i < htab->map.max_entries; i++) { @@ -195,8 +202,10 @@ static int alloc_extra_elems(struct bpf_htab *htab) /* Called from syscall */ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) { - bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_HASH; - bool lru = attr->map_type == BPF_MAP_TYPE_LRU_HASH; + bool percpu = (attr->map_type == BPF_MAP_TYPE_PERCPU_HASH || + attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH); + bool lru = (attr->map_type == BPF_MAP_TYPE_LRU_HASH || + attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH); /* percpu_lru means each cpu has its own LRU list. * it is different from BPF_MAP_TYPE_PERCPU_HASH where * the map's value itself is percpu. percpu_lru has @@ -823,12 +832,84 @@ err: return ret; } +static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags, + bool onallcpus) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct htab_elem *l_new = NULL, *l_old; + struct hlist_head *head; + unsigned long flags; + struct bucket *b; + u32 key_size, hash; + int ret; + + if (unlikely(map_flags > BPF_EXIST)) + /* unknown flags */ + return -EINVAL; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + key_size = map->key_size; + + hash = htab_map_hash(key, key_size); + + b = __select_bucket(htab, hash); + head = &b->head; + + /* For LRU, we need to alloc before taking bucket's + * spinlock because LRU's elem alloc may need + * to remove older elem from htab and this removal + * operation will need a bucket lock. + */ + if (map_flags != BPF_EXIST) { + l_new = prealloc_lru_pop(htab, key, hash); + if (!l_new) + return -ENOMEM; + } + + /* bpf_map_update_elem() can be called in_irq() */ + raw_spin_lock_irqsave(&b->lock, flags); + + l_old = lookup_elem_raw(head, hash, key, key_size); + + ret = check_flags(htab, l_old, map_flags); + if (ret) + goto err; + + if (l_old) { + bpf_lru_node_set_ref(&l_old->lru_node); + + /* per-cpu hash map can update value in-place */ + pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size), + value, onallcpus); + } else { + pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size), + value, onallcpus); + hlist_add_head_rcu(&l_new->hash_node, head); + l_new = NULL; + } + ret = 0; +err: + raw_spin_unlock_irqrestore(&b->lock, flags); + if (l_new) + bpf_lru_push_free(&htab->lru, &l_new->lru_node); + return ret; +} + static int htab_percpu_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return __htab_percpu_map_update_elem(map, key, value, map_flags, false); } +static int htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) +{ + return __htab_lru_percpu_map_update_elem(map, key, value, map_flags, + false); +} + /* Called from syscall or from eBPF program */ static int htab_map_delete_elem(struct bpf_map *map, void *key) { @@ -976,8 +1057,21 @@ static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key) return NULL; } +static void *htab_lru_percpu_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct htab_elem *l = __htab_map_lookup_elem(map, key); + + if (l) { + bpf_lru_node_set_ref(&l->lru_node); + return this_cpu_ptr(htab_elem_get_ptr(l, map->key_size)); + } + + return NULL; +} + int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value) { + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l; void __percpu *pptr; int ret = -ENOENT; @@ -993,6 +1087,8 @@ int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value) l = __htab_map_lookup_elem(map, key); if (!l) goto out; + if (htab_is_lru(htab)) + bpf_lru_node_set_ref(&l->lru_node); pptr = htab_elem_get_ptr(l, map->key_size); for_each_possible_cpu(cpu) { bpf_long_memcpy(value + off, @@ -1008,10 +1104,16 @@ out: int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, u64 map_flags) { + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); int ret; rcu_read_lock(); - ret = __htab_percpu_map_update_elem(map, key, value, map_flags, true); + if (htab_is_lru(htab)) + ret = __htab_lru_percpu_map_update_elem(map, key, value, + map_flags, true); + else + ret = __htab_percpu_map_update_elem(map, key, value, map_flags, + true); rcu_read_unlock(); return ret; @@ -1031,11 +1133,26 @@ static struct bpf_map_type_list htab_percpu_type __read_mostly = { .type = BPF_MAP_TYPE_PERCPU_HASH, }; +static const struct bpf_map_ops htab_lru_percpu_ops = { + .map_alloc = htab_map_alloc, + .map_free = htab_map_free, + .map_get_next_key = htab_map_get_next_key, + .map_lookup_elem = htab_lru_percpu_map_lookup_elem, + .map_update_elem = htab_lru_percpu_map_update_elem, + .map_delete_elem = htab_lru_map_delete_elem, +}; + +static struct bpf_map_type_list htab_lru_percpu_type __read_mostly = { + .ops = &htab_lru_percpu_ops, + .type = BPF_MAP_TYPE_LRU_PERCPU_HASH, +}; + static int __init register_htab_map(void) { bpf_register_map_type(&htab_type); bpf_register_map_type(&htab_percpu_type); bpf_register_map_type(&htab_lru_type); + bpf_register_map_type(&htab_lru_percpu_type); return 0; } late_initcall(register_htab_map); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 233e3ac836a6..ce1b7de7d72c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -292,6 +292,7 @@ static int map_lookup_elem(union bpf_attr *attr) goto free_key; if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) value_size = round_up(map->value_size, 8) * num_possible_cpus(); else @@ -302,7 +303,8 @@ static int map_lookup_elem(union bpf_attr *attr) if (!value) goto free_key; - if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) { + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); @@ -366,6 +368,7 @@ static int map_update_elem(union bpf_attr *attr) goto free_key; if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) value_size = round_up(map->value_size, 8) * num_possible_cpus(); else @@ -385,7 +388,8 @@ static int map_update_elem(union bpf_attr *attr) */ preempt_disable(); __this_cpu_inc(bpf_prog_active); - if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) { + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_update(map, key, value, attr->flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_update(map, key, value, attr->flags); -- cgit v1.2.3 From 8fbe91e7918af8adfad45828ae8acfc2f01cb6a5 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 16 Sep 2016 07:47:08 -0300 Subject: [media] videodev2.h: checkpatch cleanup Format comments according to what checkpatch wants. No other changes. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 50 +++++++++++++++++++++++++----------------- 1 file changed, 30 insertions(+), 20 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 4364ce6b0aa6..7d3e2e9673af 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1303,33 +1303,43 @@ struct v4l2_bt_timings { /* Flags */ -/* CVT/GTF specific: timing uses reduced blanking (CVT) or the 'Secondary - GTF' curve (GTF). In both cases the horizontal and/or vertical blanking - intervals are reduced, allowing a higher resolution over the same - bandwidth. This is a read-only flag. */ +/* + * CVT/GTF specific: timing uses reduced blanking (CVT) or the 'Secondary + * GTF' curve (GTF). In both cases the horizontal and/or vertical blanking + * intervals are reduced, allowing a higher resolution over the same + * bandwidth. This is a read-only flag. + */ #define V4L2_DV_FL_REDUCED_BLANKING (1 << 0) -/* CEA-861 specific: set for CEA-861 formats with a framerate of a multiple - of six. These formats can be optionally played at 1 / 1.001 speed. - This is a read-only flag. */ +/* + * CEA-861 specific: set for CEA-861 formats with a framerate of a multiple + * of six. These formats can be optionally played at 1 / 1.001 speed. + * This is a read-only flag. + */ #define V4L2_DV_FL_CAN_REDUCE_FPS (1 << 1) -/* CEA-861 specific: only valid for video transmitters, the flag is cleared - by receivers. - If the framerate of the format is a multiple of six, then the pixelclock - used to set up the transmitter is divided by 1.001 to make it compatible - with 60 Hz based standards such as NTSC and PAL-M that use a framerate of - 29.97 Hz. Otherwise this flag is cleared. If the transmitter can't generate - such frequencies, then the flag will also be cleared. */ +/* + * CEA-861 specific: only valid for video transmitters, the flag is cleared + * by receivers. + * If the framerate of the format is a multiple of six, then the pixelclock + * used to set up the transmitter is divided by 1.001 to make it compatible + * with 60 Hz based standards such as NTSC and PAL-M that use a framerate of + * 29.97 Hz. Otherwise this flag is cleared. If the transmitter can't generate + * such frequencies, then the flag will also be cleared. + */ #define V4L2_DV_FL_REDUCED_FPS (1 << 2) -/* Specific to interlaced formats: if set, then field 1 is really one half-line - longer and field 2 is really one half-line shorter, so each field has - exactly the same number of half-lines. Whether half-lines can be detected - or used depends on the hardware. */ +/* + * Specific to interlaced formats: if set, then field 1 is really one half-line + * longer and field 2 is really one half-line shorter, so each field has + * exactly the same number of half-lines. Whether half-lines can be detected + * or used depends on the hardware. + */ #define V4L2_DV_FL_HALF_LINE (1 << 3) -/* If set, then this is a Consumer Electronics (CE) video format. Such formats +/* + * If set, then this is a Consumer Electronics (CE) video format. Such formats * differ from other formats (commonly called IT formats) in that if RGB * encoding is used then by default the RGB values use limited range (i.e. * use the range 16-235) as opposed to 0-255. All formats defined in CEA-861 - * except for the 640x480 format are CE formats. */ + * except for the 640x480 format are CE formats. + */ #define V4L2_DV_FL_IS_CE_VIDEO (1 << 4) /* Some formats like SMPTE-125M have an interlaced signal with a odd * total height. For these formats, if this flag is set, the first -- cgit v1.2.3 From 4f100ff65955c1076f90b4b7be92c4f86d70adff Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 14 Jul 2016 07:58:35 -0300 Subject: [media] videodev2.h: add VICs and picture aspect ratio Add picture aspect ratio information, the CEA-861 VIC (Video Identification Code) and the HDMI VIC to struct v4l2_bt_timings. The picture aspect was chosen rather than the pixel aspect since 1) the CEA-861 standard uses picture aspect, and 2) pixel aspect ratio can become tricky when dealing with pixel repeat timings. While we don't support those yet at the moment, this might become necessary. And in that case using picture aspect ratio makes more sense. And converting picture aspect ratio to pixel aspect ratio is easy enough. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 7d3e2e9673af..d3f613e2c54a 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1254,6 +1254,9 @@ struct v4l2_standard { * (aka field 2) of interlaced field formats * @standards: Standards the timing belongs to * @flags: Flags + * @picture_aspect: The picture aspect ratio (hor/vert). + * @cea861_vic: VIC code as per the CEA-861 standard. + * @hdmi_vic: VIC code as per the HDMI standard. * @reserved: Reserved fields, must be zeroed. * * A note regarding vertical interlaced timings: height refers to the total @@ -1283,7 +1286,10 @@ struct v4l2_bt_timings { __u32 il_vbackporch; __u32 standards; __u32 flags; - __u32 reserved[14]; + struct v4l2_fract picture_aspect; + __u8 cea861_vic; + __u8 hdmi_vic; + __u8 reserved[46]; } __attribute__ ((packed)); /* Interlaced or progressive format */ @@ -1345,7 +1351,24 @@ struct v4l2_bt_timings { * total height. For these formats, if this flag is set, the first * field has the extra line. If not, it is the second field. */ -#define V4L2_DV_FL_FIRST_FIELD_EXTRA_LINE (1 << 5) +#define V4L2_DV_FL_FIRST_FIELD_EXTRA_LINE (1 << 5) +/* + * If set, then the picture_aspect field is valid. Otherwise assume that the + * pixels are square, so the picture aspect ratio is the same as the width to + * height ratio. + */ +#define V4L2_DV_FL_HAS_PICTURE_ASPECT (1 << 6) +/* + * If set, then the cea861_vic field is valid and contains the Video + * Identification Code as per the CEA-861 standard. + */ +#define V4L2_DV_FL_HAS_CEA861_VIC (1 << 7) +/* + * If set, then the hdmi_vic field is valid and contains the Video + * Identification Code as per the HDMI standard (HDMI Vendor Specific + * InfoFrame). + */ +#define V4L2_DV_FL_HAS_HDMI_VIC (1 << 8) /* A few useful defines to calculate the total blanking and frame sizes */ #define V4L2_DV_BT_BLANKING_WIDTH(bt) \ -- cgit v1.2.3 From cf0381205dec0ab10b0a17ac016c593cc7a0077f Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 14 Jul 2016 07:59:01 -0300 Subject: [media] v4l2-dv-timings: add VICs and picture aspect ratio Add the CEA-861 VIC, the HDMI VIC and the picture aspect ratio information where applicable. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/v4l2-dv-timings.h | 97 +++++++++++++++++++++++------------- 1 file changed, 63 insertions(+), 34 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/v4l2-dv-timings.h b/include/uapi/linux/v4l2-dv-timings.h index f31957166337..da2955154381 100644 --- a/include/uapi/linux/v4l2-dv-timings.h +++ b/include/uapi/linux/v4l2-dv-timings.h @@ -1,7 +1,7 @@ /* * V4L2 DV timings header. * - * Copyright (C) 2012 Hans Verkuil + * Copyright (C) 2012-2016 Hans Verkuil * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -11,11 +11,6 @@ * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA - * 02110-1301 USA */ #ifndef _V4L2_DV_TIMINGS_H @@ -33,13 +28,14 @@ .bt = { _width , ## args } #endif -/* CEA-861-E timings (i.e. standard HDTV timings) */ +/* CEA-861-F timings (i.e. standard HDTV timings) */ #define V4L2_DV_BT_CEA_640X480P59_94 { \ .type = V4L2_DV_BT_656_1120, \ V4L2_INIT_BT_TIMINGS(640, 480, 0, 0, \ 25175000, 16, 96, 48, 10, 2, 33, 0, 0, 0, \ - V4L2_DV_BT_STD_DMT | V4L2_DV_BT_STD_CEA861, 0) \ + V4L2_DV_BT_STD_DMT | V4L2_DV_BT_STD_CEA861, \ + V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 1) \ } /* Note: these are the nominal timings, for HDMI links this format is typically @@ -49,14 +45,18 @@ V4L2_INIT_BT_TIMINGS(720, 480, 1, 0, \ 13500000, 19, 62, 57, 4, 3, 15, 4, 3, 16, \ V4L2_DV_BT_STD_CEA861, \ - V4L2_DV_FL_HALF_LINE | V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_FL_HALF_LINE | V4L2_DV_FL_IS_CE_VIDEO | \ + V4L2_DV_FL_HAS_PICTURE_ASPECT | V4L2_DV_FL_HAS_CEA861_VIC, \ + { 4, 3 }, 6) \ } #define V4L2_DV_BT_CEA_720X480P59_94 { \ .type = V4L2_DV_BT_656_1120, \ V4L2_INIT_BT_TIMINGS(720, 480, 0, 0, \ 27000000, 16, 62, 60, 9, 6, 30, 0, 0, 0, \ - V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_BT_STD_CEA861, \ + V4L2_DV_FL_IS_CE_VIDEO | V4L2_DV_FL_HAS_PICTURE_ASPECT | \ + V4L2_DV_FL_HAS_CEA861_VIC, { 4, 3 }, 2) \ } /* Note: these are the nominal timings, for HDMI links this format is typically @@ -66,14 +66,18 @@ V4L2_INIT_BT_TIMINGS(720, 576, 1, 0, \ 13500000, 12, 63, 69, 2, 3, 19, 2, 3, 20, \ V4L2_DV_BT_STD_CEA861, \ - V4L2_DV_FL_HALF_LINE | V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_FL_HALF_LINE | V4L2_DV_FL_IS_CE_VIDEO | \ + V4L2_DV_FL_HAS_PICTURE_ASPECT | V4L2_DV_FL_HAS_CEA861_VIC, \ + { 4, 3 }, 21) \ } #define V4L2_DV_BT_CEA_720X576P50 { \ .type = V4L2_DV_BT_656_1120, \ V4L2_INIT_BT_TIMINGS(720, 576, 0, 0, \ 27000000, 12, 64, 68, 5, 5, 39, 0, 0, 0, \ - V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_BT_STD_CEA861, \ + V4L2_DV_FL_IS_CE_VIDEO | V4L2_DV_FL_HAS_PICTURE_ASPECT | \ + V4L2_DV_FL_HAS_CEA861_VIC, { 4, 3 }, 17) \ } #define V4L2_DV_BT_CEA_1280X720P24 { \ @@ -82,7 +86,7 @@ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 59400000, 1760, 40, 220, 5, 5, 20, 0, 0, 0, \ V4L2_DV_BT_STD_DMT | V4L2_DV_BT_STD_CEA861, \ - V4L2_DV_FL_CAN_REDUCE_FPS) \ + V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 60) \ } #define V4L2_DV_BT_CEA_1280X720P25 { \ @@ -90,7 +94,8 @@ V4L2_INIT_BT_TIMINGS(1280, 720, 0, \ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 74250000, 2420, 40, 220, 5, 5, 20, 0, 0, 0, \ - V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_BT_STD_CEA861, \ + V4L2_DV_FL_IS_CE_VIDEO | V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 61) \ } #define V4L2_DV_BT_CEA_1280X720P30 { \ @@ -99,7 +104,8 @@ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 74250000, 1760, 40, 220, 5, 5, 20, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ - V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO | \ + V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 62) \ } #define V4L2_DV_BT_CEA_1280X720P50 { \ @@ -107,7 +113,8 @@ V4L2_INIT_BT_TIMINGS(1280, 720, 0, \ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 74250000, 440, 40, 220, 5, 5, 20, 0, 0, 0, \ - V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_BT_STD_CEA861, \ + V4L2_DV_FL_IS_CE_VIDEO | V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 19) \ } #define V4L2_DV_BT_CEA_1280X720P60 { \ @@ -116,7 +123,8 @@ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 74250000, 110, 40, 220, 5, 5, 20, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ - V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO | \ + V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 4) \ } #define V4L2_DV_BT_CEA_1920X1080P24 { \ @@ -125,7 +133,8 @@ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 74250000, 638, 44, 148, 4, 5, 36, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ - V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO | \ + V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 32) \ } #define V4L2_DV_BT_CEA_1920X1080P25 { \ @@ -133,7 +142,8 @@ V4L2_INIT_BT_TIMINGS(1920, 1080, 0, \ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 74250000, 528, 44, 148, 4, 5, 36, 0, 0, 0, \ - V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_BT_STD_CEA861, \ + V4L2_DV_FL_IS_CE_VIDEO | V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 33) \ } #define V4L2_DV_BT_CEA_1920X1080P30 { \ @@ -142,7 +152,8 @@ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 74250000, 88, 44, 148, 4, 5, 36, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ - V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO | \ + V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 34) \ } #define V4L2_DV_BT_CEA_1920X1080I50 { \ @@ -151,7 +162,8 @@ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 74250000, 528, 44, 148, 2, 5, 15, 2, 5, 16, \ V4L2_DV_BT_STD_CEA861, \ - V4L2_DV_FL_HALF_LINE | V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_FL_HALF_LINE | V4L2_DV_FL_IS_CE_VIDEO | \ + V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 20) \ } #define V4L2_DV_BT_CEA_1920X1080P50 { \ @@ -159,7 +171,8 @@ V4L2_INIT_BT_TIMINGS(1920, 1080, 0, \ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 148500000, 528, 44, 148, 4, 5, 36, 0, 0, 0, \ - V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_BT_STD_CEA861, \ + V4L2_DV_FL_IS_CE_VIDEO | V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 31) \ } #define V4L2_DV_BT_CEA_1920X1080I60 { \ @@ -169,7 +182,8 @@ 74250000, 88, 44, 148, 2, 5, 15, 2, 5, 16, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | \ - V4L2_DV_FL_HALF_LINE | V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_FL_HALF_LINE | V4L2_DV_FL_IS_CE_VIDEO | \ + V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 5) \ } #define V4L2_DV_BT_CEA_1920X1080P60 { \ @@ -178,7 +192,8 @@ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 148500000, 88, 44, 148, 4, 5, 36, 0, 0, 0, \ V4L2_DV_BT_STD_DMT | V4L2_DV_BT_STD_CEA861, \ - V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO | \ + V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 16) \ } #define V4L2_DV_BT_CEA_3840X2160P24 { \ @@ -187,7 +202,9 @@ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 1276, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ - V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO | \ + V4L2_DV_FL_HAS_CEA861_VIC | V4L2_DV_FL_HAS_HDMI_VIC, \ + { 0, 0 }, 93, 3) \ } #define V4L2_DV_BT_CEA_3840X2160P25 { \ @@ -195,7 +212,9 @@ V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 1056, 88, 296, 8, 10, 72, 0, 0, 0, \ - V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_BT_STD_CEA861, \ + V4L2_DV_FL_IS_CE_VIDEO | V4L2_DV_FL_HAS_CEA861_VIC | \ + V4L2_DV_FL_HAS_HDMI_VIC, { 0, 0 }, 94, 2) \ } #define V4L2_DV_BT_CEA_3840X2160P30 { \ @@ -204,7 +223,9 @@ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 176, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ - V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO | \ + V4L2_DV_FL_HAS_CEA861_VIC | V4L2_DV_FL_HAS_HDMI_VIC, \ + { 0, 0 }, 95, 1) \ } #define V4L2_DV_BT_CEA_3840X2160P50 { \ @@ -212,7 +233,8 @@ V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 594000000, 1056, 88, 296, 8, 10, 72, 0, 0, 0, \ - V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_BT_STD_CEA861, \ + V4L2_DV_FL_IS_CE_VIDEO | V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 96) \ } #define V4L2_DV_BT_CEA_3840X2160P60 { \ @@ -221,7 +243,8 @@ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 594000000, 176, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ - V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO | \ + V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 97) \ } #define V4L2_DV_BT_CEA_4096X2160P24 { \ @@ -230,7 +253,9 @@ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 1020, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ - V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO | \ + V4L2_DV_FL_HAS_CEA861_VIC | V4L2_DV_FL_HAS_HDMI_VIC, \ + { 0, 0 }, 98, 4) \ } #define V4L2_DV_BT_CEA_4096X2160P25 { \ @@ -238,7 +263,8 @@ V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 968, 88, 128, 8, 10, 72, 0, 0, 0, \ - V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_BT_STD_CEA861, \ + V4L2_DV_FL_IS_CE_VIDEO | V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 99) \ } #define V4L2_DV_BT_CEA_4096X2160P30 { \ @@ -247,7 +273,8 @@ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 88, 88, 128, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ - V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO | \ + V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 100) \ } #define V4L2_DV_BT_CEA_4096X2160P50 { \ @@ -255,7 +282,8 @@ V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 594000000, 968, 88, 128, 8, 10, 72, 0, 0, 0, \ - V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_BT_STD_CEA861, \ + V4L2_DV_FL_IS_CE_VIDEO | V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 101) \ } #define V4L2_DV_BT_CEA_4096X2160P60 { \ @@ -264,7 +292,8 @@ V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 594000000, 88, 88, 128, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ - V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ + V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO | \ + V4L2_DV_FL_HAS_CEA861_VIC, { 0, 0 }, 102) \ } -- cgit v1.2.3 From 0dbacebede1e4e44bf500f94d692fad05eb2c293 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 2 Nov 2016 08:25:28 -0200 Subject: [media] cec: move the CEC framework out of staging and to media The last open issues have been addressed, so it is time to move this out of staging and into the mainline and to move the public cec headers to include/uapi/linux. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/Makefile | 2 +- drivers/media/Kconfig | 16 + drivers/media/Makefile | 4 + drivers/media/cec/Makefile | 5 + drivers/media/cec/cec-adap.c | 1856 ++++++++++++++++++++++++++++ drivers/media/cec/cec-api.c | 588 +++++++++ drivers/media/cec/cec-core.c | 411 +++++++ drivers/media/cec/cec-priv.h | 56 + drivers/media/i2c/Kconfig | 6 +- drivers/media/platform/vivid/Kconfig | 2 +- drivers/staging/media/Kconfig | 2 - drivers/staging/media/Makefile | 1 - drivers/staging/media/cec/Kconfig | 12 - drivers/staging/media/cec/Makefile | 5 - drivers/staging/media/cec/TODO | 9 - drivers/staging/media/cec/cec-adap.c | 1856 ---------------------------- drivers/staging/media/cec/cec-api.c | 588 --------- drivers/staging/media/cec/cec-core.c | 411 ------- drivers/staging/media/cec/cec-priv.h | 56 - drivers/staging/media/pulse8-cec/Kconfig | 2 +- drivers/staging/media/s5p-cec/Kconfig | 2 +- drivers/staging/media/st-cec/Kconfig | 2 +- include/linux/cec-funcs.h | 1971 ------------------------------ include/linux/cec.h | 1071 ---------------- include/media/cec.h | 2 +- include/uapi/linux/Kbuild | 2 + include/uapi/linux/cec-funcs.h | 1965 +++++++++++++++++++++++++++++ include/uapi/linux/cec.h | 1065 ++++++++++++++++ 28 files changed, 5977 insertions(+), 5991 deletions(-) create mode 100644 drivers/media/cec/Makefile create mode 100644 drivers/media/cec/cec-adap.c create mode 100644 drivers/media/cec/cec-api.c create mode 100644 drivers/media/cec/cec-core.c create mode 100644 drivers/media/cec/cec-priv.h delete mode 100644 drivers/staging/media/cec/Kconfig delete mode 100644 drivers/staging/media/cec/Makefile delete mode 100644 drivers/staging/media/cec/TODO delete mode 100644 drivers/staging/media/cec/cec-adap.c delete mode 100644 drivers/staging/media/cec/cec-api.c delete mode 100644 drivers/staging/media/cec/cec-core.c delete mode 100644 drivers/staging/media/cec/cec-priv.h delete mode 100644 include/linux/cec-funcs.h delete mode 100644 include/linux/cec.h create mode 100644 include/uapi/linux/cec-funcs.h create mode 100644 include/uapi/linux/cec.h (limited to 'include/uapi/linux') diff --git a/Documentation/media/Makefile b/Documentation/media/Makefile index a7fb35291f6c..61afa052c501 100644 --- a/Documentation/media/Makefile +++ b/Documentation/media/Makefile @@ -51,7 +51,7 @@ $(BUILDDIR)/videodev2.h.rst: ${UAPI}/videodev2.h ${PARSER} $(SRC_DIR)/videodev2. $(BUILDDIR)/media.h.rst: ${UAPI}/media.h ${PARSER} $(SRC_DIR)/media.h.rst.exceptions @$($(quiet)gen_rst) -$(BUILDDIR)/cec.h.rst: ${KAPI}/cec.h ${PARSER} $(SRC_DIR)/cec.h.rst.exceptions +$(BUILDDIR)/cec.h.rst: ${UAPI}/cec.h ${PARSER} $(SRC_DIR)/cec.h.rst.exceptions @$($(quiet)gen_rst) $(BUILDDIR)/lirc.h.rst: ${UAPI}/lirc.h ${PARSER} $(SRC_DIR)/lirc.h.rst.exceptions diff --git a/drivers/media/Kconfig b/drivers/media/Kconfig index 7b8540291217..bc643cbf813e 100644 --- a/drivers/media/Kconfig +++ b/drivers/media/Kconfig @@ -80,6 +80,22 @@ config MEDIA_RC_SUPPORT Say Y when you have a TV or an IR device. +config MEDIA_CEC_SUPPORT + bool "HDMI CEC support" + select MEDIA_CEC_EDID + ---help--- + Enable support for HDMI CEC (Consumer Electronics Control), + which is an optional HDMI feature. + + Say Y when you have an HDMI receiver, transmitter or a USB CEC + adapter that supports HDMI CEC. + +config MEDIA_CEC_DEBUG + bool "HDMI CEC debugfs interface" + depends on MEDIA_CEC_SUPPORT && DEBUG_FS + ---help--- + Turns on the DebugFS interface for CEC devices. + config MEDIA_CEC_EDID bool diff --git a/drivers/media/Makefile b/drivers/media/Makefile index 0deaa93efdee..d87ccb8eeabe 100644 --- a/drivers/media/Makefile +++ b/drivers/media/Makefile @@ -6,6 +6,10 @@ ifeq ($(CONFIG_MEDIA_CEC_EDID),y) obj-$(CONFIG_MEDIA_SUPPORT) += cec-edid.o endif +ifeq ($(CONFIG_MEDIA_CEC_SUPPORT),y) + obj-$(CONFIG_MEDIA_SUPPORT) += cec/ +endif + media-objs := media-device.o media-devnode.o media-entity.o # diff --git a/drivers/media/cec/Makefile b/drivers/media/cec/Makefile new file mode 100644 index 000000000000..d6686337275f --- /dev/null +++ b/drivers/media/cec/Makefile @@ -0,0 +1,5 @@ +cec-objs := cec-core.o cec-adap.o cec-api.o + +ifeq ($(CONFIG_MEDIA_CEC_SUPPORT),y) + obj-$(CONFIG_MEDIA_SUPPORT) += cec.o +endif diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c new file mode 100644 index 000000000000..054cd06e2247 --- /dev/null +++ b/drivers/media/cec/cec-adap.c @@ -0,0 +1,1856 @@ +/* + * cec-adap.c - HDMI Consumer Electronics Control framework - CEC adapter + * + * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. + * + * This program is free software; you may redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "cec-priv.h" + +static int cec_report_features(struct cec_adapter *adap, unsigned int la_idx); +static int cec_report_phys_addr(struct cec_adapter *adap, unsigned int la_idx); + +/* + * 400 ms is the time it takes for one 16 byte message to be + * transferred and 5 is the maximum number of retries. Add + * another 100 ms as a margin. So if the transmit doesn't + * finish before that time something is really wrong and we + * have to time out. + * + * This is a sign that something it really wrong and a warning + * will be issued. + */ +#define CEC_XFER_TIMEOUT_MS (5 * 400 + 100) + +#define call_op(adap, op, arg...) \ + (adap->ops->op ? adap->ops->op(adap, ## arg) : 0) + +#define call_void_op(adap, op, arg...) \ + do { \ + if (adap->ops->op) \ + adap->ops->op(adap, ## arg); \ + } while (0) + +static int cec_log_addr2idx(const struct cec_adapter *adap, u8 log_addr) +{ + int i; + + for (i = 0; i < adap->log_addrs.num_log_addrs; i++) + if (adap->log_addrs.log_addr[i] == log_addr) + return i; + return -1; +} + +static unsigned int cec_log_addr2dev(const struct cec_adapter *adap, u8 log_addr) +{ + int i = cec_log_addr2idx(adap, log_addr); + + return adap->log_addrs.primary_device_type[i < 0 ? 0 : i]; +} + +/* + * Queue a new event for this filehandle. If ts == 0, then set it + * to the current time. + * + * The two events that are currently defined do not need to keep track + * of intermediate events, so no actual queue of events is needed, + * instead just store the latest state and the total number of lost + * messages. + * + * Should new events be added in the future that require intermediate + * results to be queued as well, then a proper queue data structure is + * required. But until then, just keep it simple. + */ +void cec_queue_event_fh(struct cec_fh *fh, + const struct cec_event *new_ev, u64 ts) +{ + struct cec_event *ev = &fh->events[new_ev->event - 1]; + + if (ts == 0) + ts = ktime_get_ns(); + + mutex_lock(&fh->lock); + if (new_ev->event == CEC_EVENT_LOST_MSGS && + fh->pending_events & (1 << new_ev->event)) { + /* + * If there is already a lost_msgs event, then just + * update the lost_msgs count. This effectively + * merges the old and new events into one. + */ + ev->lost_msgs.lost_msgs += new_ev->lost_msgs.lost_msgs; + goto unlock; + } + + /* + * Intermediate states are not interesting, so just + * overwrite any older event. + */ + *ev = *new_ev; + ev->ts = ts; + fh->pending_events |= 1 << new_ev->event; + +unlock: + mutex_unlock(&fh->lock); + wake_up_interruptible(&fh->wait); +} + +/* Queue a new event for all open filehandles. */ +static void cec_queue_event(struct cec_adapter *adap, + const struct cec_event *ev) +{ + u64 ts = ktime_get_ns(); + struct cec_fh *fh; + + mutex_lock(&adap->devnode.lock); + list_for_each_entry(fh, &adap->devnode.fhs, list) + cec_queue_event_fh(fh, ev, ts); + mutex_unlock(&adap->devnode.lock); +} + +/* + * Queue a new message for this filehandle. If there is no more room + * in the queue, then send the LOST_MSGS event instead. + */ +static void cec_queue_msg_fh(struct cec_fh *fh, const struct cec_msg *msg) +{ + static const struct cec_event ev_lost_msg = { + .ts = 0, + .event = CEC_EVENT_LOST_MSGS, + .flags = 0, + { + .lost_msgs.lost_msgs = 1, + }, + }; + struct cec_msg_entry *entry; + + mutex_lock(&fh->lock); + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + goto lost_msgs; + + entry->msg = *msg; + /* Add new msg at the end of the queue */ + list_add_tail(&entry->list, &fh->msgs); + + /* + * if the queue now has more than CEC_MAX_MSG_RX_QUEUE_SZ + * messages, drop the oldest one and send a lost message event. + */ + if (fh->queued_msgs == CEC_MAX_MSG_RX_QUEUE_SZ) { + list_del(&entry->list); + goto lost_msgs; + } + fh->queued_msgs++; + mutex_unlock(&fh->lock); + wake_up_interruptible(&fh->wait); + return; + +lost_msgs: + mutex_unlock(&fh->lock); + cec_queue_event_fh(fh, &ev_lost_msg, 0); +} + +/* + * Queue the message for those filehandles that are in monitor mode. + * If valid_la is true (this message is for us or was sent by us), + * then pass it on to any monitoring filehandle. If this message + * isn't for us or from us, then only give it to filehandles that + * are in MONITOR_ALL mode. + * + * This can only happen if the CEC_CAP_MONITOR_ALL capability is + * set and the CEC adapter was placed in 'monitor all' mode. + */ +static void cec_queue_msg_monitor(struct cec_adapter *adap, + const struct cec_msg *msg, + bool valid_la) +{ + struct cec_fh *fh; + u32 monitor_mode = valid_la ? CEC_MODE_MONITOR : + CEC_MODE_MONITOR_ALL; + + mutex_lock(&adap->devnode.lock); + list_for_each_entry(fh, &adap->devnode.fhs, list) { + if (fh->mode_follower >= monitor_mode) + cec_queue_msg_fh(fh, msg); + } + mutex_unlock(&adap->devnode.lock); +} + +/* + * Queue the message for follower filehandles. + */ +static void cec_queue_msg_followers(struct cec_adapter *adap, + const struct cec_msg *msg) +{ + struct cec_fh *fh; + + mutex_lock(&adap->devnode.lock); + list_for_each_entry(fh, &adap->devnode.fhs, list) { + if (fh->mode_follower == CEC_MODE_FOLLOWER) + cec_queue_msg_fh(fh, msg); + } + mutex_unlock(&adap->devnode.lock); +} + +/* Notify userspace of an adapter state change. */ +static void cec_post_state_event(struct cec_adapter *adap) +{ + struct cec_event ev = { + .event = CEC_EVENT_STATE_CHANGE, + }; + + ev.state_change.phys_addr = adap->phys_addr; + ev.state_change.log_addr_mask = adap->log_addrs.log_addr_mask; + cec_queue_event(adap, &ev); +} + +/* + * A CEC transmit (and a possible wait for reply) completed. + * If this was in blocking mode, then complete it, otherwise + * queue the message for userspace to dequeue later. + * + * This function is called with adap->lock held. + */ +static void cec_data_completed(struct cec_data *data) +{ + /* + * Delete this transmit from the filehandle's xfer_list since + * we're done with it. + * + * Note that if the filehandle is closed before this transmit + * finished, then the release() function will set data->fh to NULL. + * Without that we would be referring to a closed filehandle. + */ + if (data->fh) + list_del(&data->xfer_list); + + if (data->blocking) { + /* + * Someone is blocking so mark the message as completed + * and call complete. + */ + data->completed = true; + complete(&data->c); + } else { + /* + * No blocking, so just queue the message if needed and + * free the memory. + */ + if (data->fh) + cec_queue_msg_fh(data->fh, &data->msg); + kfree(data); + } +} + +/* + * A pending CEC transmit needs to be cancelled, either because the CEC + * adapter is disabled or the transmit takes an impossibly long time to + * finish. + * + * This function is called with adap->lock held. + */ +static void cec_data_cancel(struct cec_data *data) +{ + /* + * It's either the current transmit, or it is a pending + * transmit. Take the appropriate action to clear it. + */ + if (data->adap->transmitting == data) { + data->adap->transmitting = NULL; + } else { + list_del_init(&data->list); + if (!(data->msg.tx_status & CEC_TX_STATUS_OK)) + data->adap->transmit_queue_sz--; + } + + /* Mark it as an error */ + data->msg.tx_ts = ktime_get_ns(); + data->msg.tx_status = CEC_TX_STATUS_ERROR | + CEC_TX_STATUS_MAX_RETRIES; + data->attempts = 0; + data->msg.tx_error_cnt = 1; + /* Queue transmitted message for monitoring purposes */ + cec_queue_msg_monitor(data->adap, &data->msg, 1); + + cec_data_completed(data); +} + +/* + * Main CEC state machine + * + * Wait until the thread should be stopped, or we are not transmitting and + * a new transmit message is queued up, in which case we start transmitting + * that message. When the adapter finished transmitting the message it will + * call cec_transmit_done(). + * + * If the adapter is disabled, then remove all queued messages instead. + * + * If the current transmit times out, then cancel that transmit. + */ +int cec_thread_func(void *_adap) +{ + struct cec_adapter *adap = _adap; + + for (;;) { + unsigned int signal_free_time; + struct cec_data *data; + bool timeout = false; + u8 attempts; + + if (adap->transmitting) { + int err; + + /* + * We are transmitting a message, so add a timeout + * to prevent the state machine to get stuck waiting + * for this message to finalize and add a check to + * see if the adapter is disabled in which case the + * transmit should be canceled. + */ + err = wait_event_interruptible_timeout(adap->kthread_waitq, + kthread_should_stop() || + (!adap->is_configured && !adap->is_configuring) || + (!adap->transmitting && + !list_empty(&adap->transmit_queue)), + msecs_to_jiffies(CEC_XFER_TIMEOUT_MS)); + timeout = err == 0; + } else { + /* Otherwise we just wait for something to happen. */ + wait_event_interruptible(adap->kthread_waitq, + kthread_should_stop() || + (!adap->transmitting && + !list_empty(&adap->transmit_queue))); + } + + mutex_lock(&adap->lock); + + if ((!adap->is_configured && !adap->is_configuring) || + kthread_should_stop()) { + /* + * If the adapter is disabled, or we're asked to stop, + * then cancel any pending transmits. + */ + while (!list_empty(&adap->transmit_queue)) { + data = list_first_entry(&adap->transmit_queue, + struct cec_data, list); + cec_data_cancel(data); + } + if (adap->transmitting) + cec_data_cancel(adap->transmitting); + + /* + * Cancel the pending timeout work. We have to unlock + * the mutex when flushing the work since + * cec_wait_timeout() will take it. This is OK since + * no new entries can be added to wait_queue as long + * as adap->transmitting is NULL, which it is due to + * the cec_data_cancel() above. + */ + while (!list_empty(&adap->wait_queue)) { + data = list_first_entry(&adap->wait_queue, + struct cec_data, list); + + if (!cancel_delayed_work(&data->work)) { + mutex_unlock(&adap->lock); + flush_scheduled_work(); + mutex_lock(&adap->lock); + } + cec_data_cancel(data); + } + goto unlock; + } + + if (adap->transmitting && timeout) { + /* + * If we timeout, then log that. This really shouldn't + * happen and is an indication of a faulty CEC adapter + * driver, or the CEC bus is in some weird state. + */ + dprintk(0, "message %*ph timed out!\n", + adap->transmitting->msg.len, + adap->transmitting->msg.msg); + /* Just give up on this. */ + cec_data_cancel(adap->transmitting); + goto unlock; + } + + /* + * If we are still transmitting, or there is nothing new to + * transmit, then just continue waiting. + */ + if (adap->transmitting || list_empty(&adap->transmit_queue)) + goto unlock; + + /* Get a new message to transmit */ + data = list_first_entry(&adap->transmit_queue, + struct cec_data, list); + list_del_init(&data->list); + adap->transmit_queue_sz--; + /* Make this the current transmitting message */ + adap->transmitting = data; + + /* + * Suggested number of attempts as per the CEC 2.0 spec: + * 4 attempts is the default, except for 'secondary poll + * messages', i.e. poll messages not sent during the adapter + * configuration phase when it allocates logical addresses. + */ + if (data->msg.len == 1 && adap->is_configured) + attempts = 2; + else + attempts = 4; + + /* Set the suggested signal free time */ + if (data->attempts) { + /* should be >= 3 data bit periods for a retry */ + signal_free_time = CEC_SIGNAL_FREE_TIME_RETRY; + } else if (data->new_initiator) { + /* should be >= 5 data bit periods for new initiator */ + signal_free_time = CEC_SIGNAL_FREE_TIME_NEW_INITIATOR; + } else { + /* + * should be >= 7 data bit periods for sending another + * frame immediately after another. + */ + signal_free_time = CEC_SIGNAL_FREE_TIME_NEXT_XFER; + } + if (data->attempts == 0) + data->attempts = attempts; + + /* Tell the adapter to transmit, cancel on error */ + if (adap->ops->adap_transmit(adap, data->attempts, + signal_free_time, &data->msg)) + cec_data_cancel(data); + +unlock: + mutex_unlock(&adap->lock); + + if (kthread_should_stop()) + break; + } + return 0; +} + +/* + * Called by the CEC adapter if a transmit finished. + */ +void cec_transmit_done(struct cec_adapter *adap, u8 status, u8 arb_lost_cnt, + u8 nack_cnt, u8 low_drive_cnt, u8 error_cnt) +{ + struct cec_data *data; + struct cec_msg *msg; + u64 ts = ktime_get_ns(); + + dprintk(2, "cec_transmit_done %02x\n", status); + mutex_lock(&adap->lock); + data = adap->transmitting; + if (!data) { + /* + * This can happen if a transmit was issued and the cable is + * unplugged while the transmit is ongoing. Ignore this + * transmit in that case. + */ + dprintk(1, "cec_transmit_done without an ongoing transmit!\n"); + goto unlock; + } + + msg = &data->msg; + + /* Drivers must fill in the status! */ + WARN_ON(status == 0); + msg->tx_ts = ts; + msg->tx_status |= status; + msg->tx_arb_lost_cnt += arb_lost_cnt; + msg->tx_nack_cnt += nack_cnt; + msg->tx_low_drive_cnt += low_drive_cnt; + msg->tx_error_cnt += error_cnt; + + /* Mark that we're done with this transmit */ + adap->transmitting = NULL; + + /* + * If there are still retry attempts left and there was an error and + * the hardware didn't signal that it retried itself (by setting + * CEC_TX_STATUS_MAX_RETRIES), then we will retry ourselves. + */ + if (data->attempts > 1 && + !(status & (CEC_TX_STATUS_MAX_RETRIES | CEC_TX_STATUS_OK))) { + /* Retry this message */ + data->attempts--; + /* Add the message in front of the transmit queue */ + list_add(&data->list, &adap->transmit_queue); + adap->transmit_queue_sz++; + goto wake_thread; + } + + data->attempts = 0; + + /* Always set CEC_TX_STATUS_MAX_RETRIES on error */ + if (!(status & CEC_TX_STATUS_OK)) + msg->tx_status |= CEC_TX_STATUS_MAX_RETRIES; + + /* Queue transmitted message for monitoring purposes */ + cec_queue_msg_monitor(adap, msg, 1); + + if ((status & CEC_TX_STATUS_OK) && adap->is_configured && + msg->timeout) { + /* + * Queue the message into the wait queue if we want to wait + * for a reply. + */ + list_add_tail(&data->list, &adap->wait_queue); + schedule_delayed_work(&data->work, + msecs_to_jiffies(msg->timeout)); + } else { + /* Otherwise we're done */ + cec_data_completed(data); + } + +wake_thread: + /* + * Wake up the main thread to see if another message is ready + * for transmitting or to retry the current message. + */ + wake_up_interruptible(&adap->kthread_waitq); +unlock: + mutex_unlock(&adap->lock); +} +EXPORT_SYMBOL_GPL(cec_transmit_done); + +/* + * Called when waiting for a reply times out. + */ +static void cec_wait_timeout(struct work_struct *work) +{ + struct cec_data *data = container_of(work, struct cec_data, work.work); + struct cec_adapter *adap = data->adap; + + mutex_lock(&adap->lock); + /* + * Sanity check in case the timeout and the arrival of the message + * happened at the same time. + */ + if (list_empty(&data->list)) + goto unlock; + + /* Mark the message as timed out */ + list_del_init(&data->list); + data->msg.rx_ts = ktime_get_ns(); + data->msg.rx_status = CEC_RX_STATUS_TIMEOUT; + cec_data_completed(data); +unlock: + mutex_unlock(&adap->lock); +} + +/* + * Transmit a message. The fh argument may be NULL if the transmit is not + * associated with a specific filehandle. + * + * This function is called with adap->lock held. + */ +int cec_transmit_msg_fh(struct cec_adapter *adap, struct cec_msg *msg, + struct cec_fh *fh, bool block) +{ + struct cec_data *data; + u8 last_initiator = 0xff; + unsigned int timeout; + int res = 0; + + msg->rx_ts = 0; + msg->tx_ts = 0; + msg->rx_status = 0; + msg->tx_status = 0; + msg->tx_arb_lost_cnt = 0; + msg->tx_nack_cnt = 0; + msg->tx_low_drive_cnt = 0; + msg->tx_error_cnt = 0; + msg->sequence = ++adap->sequence; + if (!msg->sequence) + msg->sequence = ++adap->sequence; + + if (msg->reply && msg->timeout == 0) { + /* Make sure the timeout isn't 0. */ + msg->timeout = 1000; + } + + /* Sanity checks */ + if (msg->len == 0 || msg->len > CEC_MAX_MSG_SIZE) { + dprintk(1, "cec_transmit_msg: invalid length %d\n", msg->len); + return -EINVAL; + } + if (msg->timeout && msg->len == 1) { + dprintk(1, "cec_transmit_msg: can't reply for poll msg\n"); + return -EINVAL; + } + memset(msg->msg + msg->len, 0, sizeof(msg->msg) - msg->len); + if (msg->len == 1) { + if (cec_msg_initiator(msg) != 0xf || + cec_msg_destination(msg) == 0xf) { + dprintk(1, "cec_transmit_msg: invalid poll message\n"); + return -EINVAL; + } + if (cec_has_log_addr(adap, cec_msg_destination(msg))) { + /* + * If the destination is a logical address our adapter + * has already claimed, then just NACK this. + * It depends on the hardware what it will do with a + * POLL to itself (some OK this), so it is just as + * easy to handle it here so the behavior will be + * consistent. + */ + msg->tx_ts = ktime_get_ns(); + msg->tx_status = CEC_TX_STATUS_NACK | + CEC_TX_STATUS_MAX_RETRIES; + msg->tx_nack_cnt = 1; + return 0; + } + } + if (msg->len > 1 && !cec_msg_is_broadcast(msg) && + cec_has_log_addr(adap, cec_msg_destination(msg))) { + dprintk(1, "cec_transmit_msg: destination is the adapter itself\n"); + return -EINVAL; + } + if (cec_msg_initiator(msg) != 0xf && + !cec_has_log_addr(adap, cec_msg_initiator(msg))) { + dprintk(1, "cec_transmit_msg: initiator has unknown logical address %d\n", + cec_msg_initiator(msg)); + return -EINVAL; + } + if (!adap->is_configured && !adap->is_configuring) + return -ENONET; + + if (adap->transmit_queue_sz >= CEC_MAX_MSG_TX_QUEUE_SZ) + return -EBUSY; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + if (msg->len > 1 && msg->msg[1] == CEC_MSG_CDC_MESSAGE) { + msg->msg[2] = adap->phys_addr >> 8; + msg->msg[3] = adap->phys_addr & 0xff; + } + + if (msg->timeout) + dprintk(2, "cec_transmit_msg: %*ph (wait for 0x%02x%s)\n", + msg->len, msg->msg, msg->reply, !block ? ", nb" : ""); + else + dprintk(2, "cec_transmit_msg: %*ph%s\n", + msg->len, msg->msg, !block ? " (nb)" : ""); + + data->msg = *msg; + data->fh = fh; + data->adap = adap; + data->blocking = block; + + /* + * Determine if this message follows a message from the same + * initiator. Needed to determine the free signal time later on. + */ + if (msg->len > 1) { + if (!(list_empty(&adap->transmit_queue))) { + const struct cec_data *last; + + last = list_last_entry(&adap->transmit_queue, + const struct cec_data, list); + last_initiator = cec_msg_initiator(&last->msg); + } else if (adap->transmitting) { + last_initiator = + cec_msg_initiator(&adap->transmitting->msg); + } + } + data->new_initiator = last_initiator != cec_msg_initiator(msg); + init_completion(&data->c); + INIT_DELAYED_WORK(&data->work, cec_wait_timeout); + + if (fh) + list_add_tail(&data->xfer_list, &fh->xfer_list); + list_add_tail(&data->list, &adap->transmit_queue); + adap->transmit_queue_sz++; + if (!adap->transmitting) + wake_up_interruptible(&adap->kthread_waitq); + + /* All done if we don't need to block waiting for completion */ + if (!block) + return 0; + + /* + * If we don't get a completion before this time something is really + * wrong and we time out. + */ + timeout = CEC_XFER_TIMEOUT_MS; + /* Add the requested timeout if we have to wait for a reply as well */ + if (msg->timeout) + timeout += msg->timeout; + + /* + * Release the lock and wait, retake the lock afterwards. + */ + mutex_unlock(&adap->lock); + res = wait_for_completion_killable_timeout(&data->c, + msecs_to_jiffies(timeout)); + mutex_lock(&adap->lock); + + if (data->completed) { + /* The transmit completed (possibly with an error) */ + *msg = data->msg; + kfree(data); + return 0; + } + /* + * The wait for completion timed out or was interrupted, so mark this + * as non-blocking and disconnect from the filehandle since it is + * still 'in flight'. When it finally completes it will just drop the + * result silently. + */ + data->blocking = false; + if (data->fh) + list_del(&data->xfer_list); + data->fh = NULL; + + if (res == 0) { /* timed out */ + /* Check if the reply or the transmit failed */ + if (msg->timeout && (msg->tx_status & CEC_TX_STATUS_OK)) + msg->rx_status = CEC_RX_STATUS_TIMEOUT; + else + msg->tx_status = CEC_TX_STATUS_MAX_RETRIES; + } + return res > 0 ? 0 : res; +} + +/* Helper function to be used by drivers and this framework. */ +int cec_transmit_msg(struct cec_adapter *adap, struct cec_msg *msg, + bool block) +{ + int ret; + + mutex_lock(&adap->lock); + ret = cec_transmit_msg_fh(adap, msg, NULL, block); + mutex_unlock(&adap->lock); + return ret; +} +EXPORT_SYMBOL_GPL(cec_transmit_msg); + +/* + * I don't like forward references but without this the low-level + * cec_received_msg() function would come after a bunch of high-level + * CEC protocol handling functions. That was very confusing. + */ +static int cec_receive_notify(struct cec_adapter *adap, struct cec_msg *msg, + bool is_reply); + +#define DIRECTED 0x80 +#define BCAST1_4 0x40 +#define BCAST2_0 0x20 /* broadcast only allowed for >= 2.0 */ +#define BCAST (BCAST1_4 | BCAST2_0) +#define BOTH (BCAST | DIRECTED) + +/* + * Specify minimum length and whether the message is directed, broadcast + * or both. Messages that do not match the criteria are ignored as per + * the CEC specification. + */ +static const u8 cec_msg_size[256] = { + [CEC_MSG_ACTIVE_SOURCE] = 4 | BCAST, + [CEC_MSG_IMAGE_VIEW_ON] = 2 | DIRECTED, + [CEC_MSG_TEXT_VIEW_ON] = 2 | DIRECTED, + [CEC_MSG_INACTIVE_SOURCE] = 4 | DIRECTED, + [CEC_MSG_REQUEST_ACTIVE_SOURCE] = 2 | BCAST, + [CEC_MSG_ROUTING_CHANGE] = 6 | BCAST, + [CEC_MSG_ROUTING_INFORMATION] = 4 | BCAST, + [CEC_MSG_SET_STREAM_PATH] = 4 | BCAST, + [CEC_MSG_STANDBY] = 2 | BOTH, + [CEC_MSG_RECORD_OFF] = 2 | DIRECTED, + [CEC_MSG_RECORD_ON] = 3 | DIRECTED, + [CEC_MSG_RECORD_STATUS] = 3 | DIRECTED, + [CEC_MSG_RECORD_TV_SCREEN] = 2 | DIRECTED, + [CEC_MSG_CLEAR_ANALOGUE_TIMER] = 13 | DIRECTED, + [CEC_MSG_CLEAR_DIGITAL_TIMER] = 16 | DIRECTED, + [CEC_MSG_CLEAR_EXT_TIMER] = 13 | DIRECTED, + [CEC_MSG_SET_ANALOGUE_TIMER] = 13 | DIRECTED, + [CEC_MSG_SET_DIGITAL_TIMER] = 16 | DIRECTED, + [CEC_MSG_SET_EXT_TIMER] = 13 | DIRECTED, + [CEC_MSG_SET_TIMER_PROGRAM_TITLE] = 2 | DIRECTED, + [CEC_MSG_TIMER_CLEARED_STATUS] = 3 | DIRECTED, + [CEC_MSG_TIMER_STATUS] = 3 | DIRECTED, + [CEC_MSG_CEC_VERSION] = 3 | DIRECTED, + [CEC_MSG_GET_CEC_VERSION] = 2 | DIRECTED, + [CEC_MSG_GIVE_PHYSICAL_ADDR] = 2 | DIRECTED, + [CEC_MSG_GET_MENU_LANGUAGE] = 2 | DIRECTED, + [CEC_MSG_REPORT_PHYSICAL_ADDR] = 5 | BCAST, + [CEC_MSG_SET_MENU_LANGUAGE] = 5 | BCAST, + [CEC_MSG_REPORT_FEATURES] = 6 | BCAST, + [CEC_MSG_GIVE_FEATURES] = 2 | DIRECTED, + [CEC_MSG_DECK_CONTROL] = 3 | DIRECTED, + [CEC_MSG_DECK_STATUS] = 3 | DIRECTED, + [CEC_MSG_GIVE_DECK_STATUS] = 3 | DIRECTED, + [CEC_MSG_PLAY] = 3 | DIRECTED, + [CEC_MSG_GIVE_TUNER_DEVICE_STATUS] = 3 | DIRECTED, + [CEC_MSG_SELECT_ANALOGUE_SERVICE] = 6 | DIRECTED, + [CEC_MSG_SELECT_DIGITAL_SERVICE] = 9 | DIRECTED, + [CEC_MSG_TUNER_DEVICE_STATUS] = 7 | DIRECTED, + [CEC_MSG_TUNER_STEP_DECREMENT] = 2 | DIRECTED, + [CEC_MSG_TUNER_STEP_INCREMENT] = 2 | DIRECTED, + [CEC_MSG_DEVICE_VENDOR_ID] = 5 | BCAST, + [CEC_MSG_GIVE_DEVICE_VENDOR_ID] = 2 | DIRECTED, + [CEC_MSG_VENDOR_COMMAND] = 2 | DIRECTED, + [CEC_MSG_VENDOR_COMMAND_WITH_ID] = 5 | BOTH, + [CEC_MSG_VENDOR_REMOTE_BUTTON_DOWN] = 2 | BOTH, + [CEC_MSG_VENDOR_REMOTE_BUTTON_UP] = 2 | BOTH, + [CEC_MSG_SET_OSD_STRING] = 3 | DIRECTED, + [CEC_MSG_GIVE_OSD_NAME] = 2 | DIRECTED, + [CEC_MSG_SET_OSD_NAME] = 2 | DIRECTED, + [CEC_MSG_MENU_REQUEST] = 3 | DIRECTED, + [CEC_MSG_MENU_STATUS] = 3 | DIRECTED, + [CEC_MSG_USER_CONTROL_PRESSED] = 3 | DIRECTED, + [CEC_MSG_USER_CONTROL_RELEASED] = 2 | DIRECTED, + [CEC_MSG_GIVE_DEVICE_POWER_STATUS] = 2 | DIRECTED, + [CEC_MSG_REPORT_POWER_STATUS] = 3 | DIRECTED | BCAST2_0, + [CEC_MSG_FEATURE_ABORT] = 4 | DIRECTED, + [CEC_MSG_ABORT] = 2 | DIRECTED, + [CEC_MSG_GIVE_AUDIO_STATUS] = 2 | DIRECTED, + [CEC_MSG_GIVE_SYSTEM_AUDIO_MODE_STATUS] = 2 | DIRECTED, + [CEC_MSG_REPORT_AUDIO_STATUS] = 3 | DIRECTED, + [CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR] = 2 | DIRECTED, + [CEC_MSG_REQUEST_SHORT_AUDIO_DESCRIPTOR] = 2 | DIRECTED, + [CEC_MSG_SET_SYSTEM_AUDIO_MODE] = 3 | BOTH, + [CEC_MSG_SYSTEM_AUDIO_MODE_REQUEST] = 2 | DIRECTED, + [CEC_MSG_SYSTEM_AUDIO_MODE_STATUS] = 3 | DIRECTED, + [CEC_MSG_SET_AUDIO_RATE] = 3 | DIRECTED, + [CEC_MSG_INITIATE_ARC] = 2 | DIRECTED, + [CEC_MSG_REPORT_ARC_INITIATED] = 2 | DIRECTED, + [CEC_MSG_REPORT_ARC_TERMINATED] = 2 | DIRECTED, + [CEC_MSG_REQUEST_ARC_INITIATION] = 2 | DIRECTED, + [CEC_MSG_REQUEST_ARC_TERMINATION] = 2 | DIRECTED, + [CEC_MSG_TERMINATE_ARC] = 2 | DIRECTED, + [CEC_MSG_REQUEST_CURRENT_LATENCY] = 4 | BCAST, + [CEC_MSG_REPORT_CURRENT_LATENCY] = 7 | BCAST, + [CEC_MSG_CDC_MESSAGE] = 2 | BCAST, +}; + +/* Called by the CEC adapter if a message is received */ +void cec_received_msg(struct cec_adapter *adap, struct cec_msg *msg) +{ + struct cec_data *data; + u8 msg_init = cec_msg_initiator(msg); + u8 msg_dest = cec_msg_destination(msg); + u8 cmd = msg->msg[1]; + bool is_reply = false; + bool valid_la = true; + u8 min_len = 0; + + if (WARN_ON(!msg->len || msg->len > CEC_MAX_MSG_SIZE)) + return; + + msg->rx_ts = ktime_get_ns(); + msg->rx_status = CEC_RX_STATUS_OK; + msg->sequence = msg->reply = msg->timeout = 0; + msg->tx_status = 0; + msg->tx_ts = 0; + msg->flags = 0; + memset(msg->msg + msg->len, 0, sizeof(msg->msg) - msg->len); + + mutex_lock(&adap->lock); + dprintk(2, "cec_received_msg: %*ph\n", msg->len, msg->msg); + + /* Check if this message was for us (directed or broadcast). */ + if (!cec_msg_is_broadcast(msg)) + valid_la = cec_has_log_addr(adap, msg_dest); + + /* + * Check if the length is not too short or if the message is a + * broadcast message where a directed message was expected or + * vice versa. If so, then the message has to be ignored (according + * to section CEC 7.3 and CEC 12.2). + */ + if (valid_la && msg->len > 1 && cec_msg_size[cmd]) { + u8 dir_fl = cec_msg_size[cmd] & BOTH; + + min_len = cec_msg_size[cmd] & 0x1f; + if (msg->len < min_len) + valid_la = false; + else if (!cec_msg_is_broadcast(msg) && !(dir_fl & DIRECTED)) + valid_la = false; + else if (cec_msg_is_broadcast(msg) && !(dir_fl & BCAST1_4)) + valid_la = false; + else if (cec_msg_is_broadcast(msg) && + adap->log_addrs.cec_version >= CEC_OP_CEC_VERSION_2_0 && + !(dir_fl & BCAST2_0)) + valid_la = false; + } + if (valid_la && min_len) { + /* These messages have special length requirements */ + switch (cmd) { + case CEC_MSG_TIMER_STATUS: + if (msg->msg[2] & 0x10) { + switch (msg->msg[2] & 0xf) { + case CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE: + case CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE: + if (msg->len < 5) + valid_la = false; + break; + } + } else if ((msg->msg[2] & 0xf) == CEC_OP_PROG_ERROR_DUPLICATE) { + if (msg->len < 5) + valid_la = false; + } + break; + case CEC_MSG_RECORD_ON: + switch (msg->msg[2]) { + case CEC_OP_RECORD_SRC_OWN: + break; + case CEC_OP_RECORD_SRC_DIGITAL: + if (msg->len < 10) + valid_la = false; + break; + case CEC_OP_RECORD_SRC_ANALOG: + if (msg->len < 7) + valid_la = false; + break; + case CEC_OP_RECORD_SRC_EXT_PLUG: + if (msg->len < 4) + valid_la = false; + break; + case CEC_OP_RECORD_SRC_EXT_PHYS_ADDR: + if (msg->len < 5) + valid_la = false; + break; + } + break; + } + } + + /* It's a valid message and not a poll or CDC message */ + if (valid_la && msg->len > 1 && cmd != CEC_MSG_CDC_MESSAGE) { + bool abort = cmd == CEC_MSG_FEATURE_ABORT; + + /* The aborted command is in msg[2] */ + if (abort) + cmd = msg->msg[2]; + + /* + * Walk over all transmitted messages that are waiting for a + * reply. + */ + list_for_each_entry(data, &adap->wait_queue, list) { + struct cec_msg *dst = &data->msg; + + /* + * The *only* CEC message that has two possible replies + * is CEC_MSG_INITIATE_ARC. + * In this case allow either of the two replies. + */ + if (!abort && dst->msg[1] == CEC_MSG_INITIATE_ARC && + (cmd == CEC_MSG_REPORT_ARC_INITIATED || + cmd == CEC_MSG_REPORT_ARC_TERMINATED) && + (dst->reply == CEC_MSG_REPORT_ARC_INITIATED || + dst->reply == CEC_MSG_REPORT_ARC_TERMINATED)) + dst->reply = cmd; + + /* Does the command match? */ + if ((abort && cmd != dst->msg[1]) || + (!abort && cmd != dst->reply)) + continue; + + /* Does the addressing match? */ + if (msg_init != cec_msg_destination(dst) && + !cec_msg_is_broadcast(dst)) + continue; + + /* We got a reply */ + memcpy(dst->msg, msg->msg, msg->len); + dst->len = msg->len; + dst->rx_ts = msg->rx_ts; + dst->rx_status = msg->rx_status; + if (abort) + dst->rx_status |= CEC_RX_STATUS_FEATURE_ABORT; + msg->flags = dst->flags; + /* Remove it from the wait_queue */ + list_del_init(&data->list); + + /* Cancel the pending timeout work */ + if (!cancel_delayed_work(&data->work)) { + mutex_unlock(&adap->lock); + flush_scheduled_work(); + mutex_lock(&adap->lock); + } + /* + * Mark this as a reply, provided someone is still + * waiting for the answer. + */ + if (data->fh) + is_reply = true; + cec_data_completed(data); + break; + } + } + mutex_unlock(&adap->lock); + + /* Pass the message on to any monitoring filehandles */ + cec_queue_msg_monitor(adap, msg, valid_la); + + /* We're done if it is not for us or a poll message */ + if (!valid_la || msg->len <= 1) + return; + + if (adap->log_addrs.log_addr_mask == 0) + return; + + /* + * Process the message on the protocol level. If is_reply is true, + * then cec_receive_notify() won't pass on the reply to the listener(s) + * since that was already done by cec_data_completed() above. + */ + cec_receive_notify(adap, msg, is_reply); +} +EXPORT_SYMBOL_GPL(cec_received_msg); + +/* Logical Address Handling */ + +/* + * Attempt to claim a specific logical address. + * + * This function is called with adap->lock held. + */ +static int cec_config_log_addr(struct cec_adapter *adap, + unsigned int idx, + unsigned int log_addr) +{ + struct cec_log_addrs *las = &adap->log_addrs; + struct cec_msg msg = { }; + int err; + + if (cec_has_log_addr(adap, log_addr)) + return 0; + + /* Send poll message */ + msg.len = 1; + msg.msg[0] = 0xf0 | log_addr; + err = cec_transmit_msg_fh(adap, &msg, NULL, true); + + /* + * While trying to poll the physical address was reset + * and the adapter was unconfigured, so bail out. + */ + if (!adap->is_configuring) + return -EINTR; + + if (err) + return err; + + if (msg.tx_status & CEC_TX_STATUS_OK) + return 0; + + /* + * Message not acknowledged, so this logical + * address is free to use. + */ + err = adap->ops->adap_log_addr(adap, log_addr); + if (err) + return err; + + las->log_addr[idx] = log_addr; + las->log_addr_mask |= 1 << log_addr; + adap->phys_addrs[log_addr] = adap->phys_addr; + + dprintk(2, "claimed addr %d (%d)\n", log_addr, + las->primary_device_type[idx]); + return 1; +} + +/* + * Unconfigure the adapter: clear all logical addresses and send + * the state changed event. + * + * This function is called with adap->lock held. + */ +static void cec_adap_unconfigure(struct cec_adapter *adap) +{ + WARN_ON(adap->ops->adap_log_addr(adap, CEC_LOG_ADDR_INVALID)); + adap->log_addrs.log_addr_mask = 0; + adap->is_configuring = false; + adap->is_configured = false; + memset(adap->phys_addrs, 0xff, sizeof(adap->phys_addrs)); + wake_up_interruptible(&adap->kthread_waitq); + cec_post_state_event(adap); +} + +/* + * Attempt to claim the required logical addresses. + */ +static int cec_config_thread_func(void *arg) +{ + /* The various LAs for each type of device */ + static const u8 tv_log_addrs[] = { + CEC_LOG_ADDR_TV, CEC_LOG_ADDR_SPECIFIC, + CEC_LOG_ADDR_INVALID + }; + static const u8 record_log_addrs[] = { + CEC_LOG_ADDR_RECORD_1, CEC_LOG_ADDR_RECORD_2, + CEC_LOG_ADDR_RECORD_3, + CEC_LOG_ADDR_BACKUP_1, CEC_LOG_ADDR_BACKUP_2, + CEC_LOG_ADDR_INVALID + }; + static const u8 tuner_log_addrs[] = { + CEC_LOG_ADDR_TUNER_1, CEC_LOG_ADDR_TUNER_2, + CEC_LOG_ADDR_TUNER_3, CEC_LOG_ADDR_TUNER_4, + CEC_LOG_ADDR_BACKUP_1, CEC_LOG_ADDR_BACKUP_2, + CEC_LOG_ADDR_INVALID + }; + static const u8 playback_log_addrs[] = { + CEC_LOG_ADDR_PLAYBACK_1, CEC_LOG_ADDR_PLAYBACK_2, + CEC_LOG_ADDR_PLAYBACK_3, + CEC_LOG_ADDR_BACKUP_1, CEC_LOG_ADDR_BACKUP_2, + CEC_LOG_ADDR_INVALID + }; + static const u8 audiosystem_log_addrs[] = { + CEC_LOG_ADDR_AUDIOSYSTEM, + CEC_LOG_ADDR_INVALID + }; + static const u8 specific_use_log_addrs[] = { + CEC_LOG_ADDR_SPECIFIC, + CEC_LOG_ADDR_BACKUP_1, CEC_LOG_ADDR_BACKUP_2, + CEC_LOG_ADDR_INVALID + }; + static const u8 *type2addrs[6] = { + [CEC_LOG_ADDR_TYPE_TV] = tv_log_addrs, + [CEC_LOG_ADDR_TYPE_RECORD] = record_log_addrs, + [CEC_LOG_ADDR_TYPE_TUNER] = tuner_log_addrs, + [CEC_LOG_ADDR_TYPE_PLAYBACK] = playback_log_addrs, + [CEC_LOG_ADDR_TYPE_AUDIOSYSTEM] = audiosystem_log_addrs, + [CEC_LOG_ADDR_TYPE_SPECIFIC] = specific_use_log_addrs, + }; + static const u16 type2mask[] = { + [CEC_LOG_ADDR_TYPE_TV] = CEC_LOG_ADDR_MASK_TV, + [CEC_LOG_ADDR_TYPE_RECORD] = CEC_LOG_ADDR_MASK_RECORD, + [CEC_LOG_ADDR_TYPE_TUNER] = CEC_LOG_ADDR_MASK_TUNER, + [CEC_LOG_ADDR_TYPE_PLAYBACK] = CEC_LOG_ADDR_MASK_PLAYBACK, + [CEC_LOG_ADDR_TYPE_AUDIOSYSTEM] = CEC_LOG_ADDR_MASK_AUDIOSYSTEM, + [CEC_LOG_ADDR_TYPE_SPECIFIC] = CEC_LOG_ADDR_MASK_SPECIFIC, + }; + struct cec_adapter *adap = arg; + struct cec_log_addrs *las = &adap->log_addrs; + int err; + int i, j; + + mutex_lock(&adap->lock); + dprintk(1, "physical address: %x.%x.%x.%x, claim %d logical addresses\n", + cec_phys_addr_exp(adap->phys_addr), las->num_log_addrs); + las->log_addr_mask = 0; + + if (las->log_addr_type[0] == CEC_LOG_ADDR_TYPE_UNREGISTERED) + goto configured; + + for (i = 0; i < las->num_log_addrs; i++) { + unsigned int type = las->log_addr_type[i]; + const u8 *la_list; + u8 last_la; + + /* + * The TV functionality can only map to physical address 0. + * For any other address, try the Specific functionality + * instead as per the spec. + */ + if (adap->phys_addr && type == CEC_LOG_ADDR_TYPE_TV) + type = CEC_LOG_ADDR_TYPE_SPECIFIC; + + la_list = type2addrs[type]; + last_la = las->log_addr[i]; + las->log_addr[i] = CEC_LOG_ADDR_INVALID; + if (last_la == CEC_LOG_ADDR_INVALID || + last_la == CEC_LOG_ADDR_UNREGISTERED || + !(last_la & type2mask[type])) + last_la = la_list[0]; + + err = cec_config_log_addr(adap, i, last_la); + if (err > 0) /* Reused last LA */ + continue; + + if (err < 0) + goto unconfigure; + + for (j = 0; la_list[j] != CEC_LOG_ADDR_INVALID; j++) { + /* Tried this one already, skip it */ + if (la_list[j] == last_la) + continue; + /* The backup addresses are CEC 2.0 specific */ + if ((la_list[j] == CEC_LOG_ADDR_BACKUP_1 || + la_list[j] == CEC_LOG_ADDR_BACKUP_2) && + las->cec_version < CEC_OP_CEC_VERSION_2_0) + continue; + + err = cec_config_log_addr(adap, i, la_list[j]); + if (err == 0) /* LA is in use */ + continue; + if (err < 0) + goto unconfigure; + /* Done, claimed an LA */ + break; + } + + if (la_list[j] == CEC_LOG_ADDR_INVALID) + dprintk(1, "could not claim LA %d\n", i); + } + + if (adap->log_addrs.log_addr_mask == 0 && + !(las->flags & CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK)) + goto unconfigure; + +configured: + if (adap->log_addrs.log_addr_mask == 0) { + /* Fall back to unregistered */ + las->log_addr[0] = CEC_LOG_ADDR_UNREGISTERED; + las->log_addr_mask = 1 << las->log_addr[0]; + for (i = 1; i < las->num_log_addrs; i++) + las->log_addr[i] = CEC_LOG_ADDR_INVALID; + } + adap->is_configured = true; + adap->is_configuring = false; + cec_post_state_event(adap); + mutex_unlock(&adap->lock); + + for (i = 0; i < las->num_log_addrs; i++) { + if (las->log_addr[i] == CEC_LOG_ADDR_INVALID || + (las->flags & CEC_LOG_ADDRS_FL_CDC_ONLY)) + continue; + + /* + * Report Features must come first according + * to CEC 2.0 + */ + if (las->log_addr[i] != CEC_LOG_ADDR_UNREGISTERED) + cec_report_features(adap, i); + cec_report_phys_addr(adap, i); + } + for (i = las->num_log_addrs; i < CEC_MAX_LOG_ADDRS; i++) + las->log_addr[i] = CEC_LOG_ADDR_INVALID; + mutex_lock(&adap->lock); + adap->kthread_config = NULL; + mutex_unlock(&adap->lock); + complete(&adap->config_completion); + return 0; + +unconfigure: + for (i = 0; i < las->num_log_addrs; i++) + las->log_addr[i] = CEC_LOG_ADDR_INVALID; + cec_adap_unconfigure(adap); + adap->kthread_config = NULL; + mutex_unlock(&adap->lock); + complete(&adap->config_completion); + return 0; +} + +/* + * Called from either __cec_s_phys_addr or __cec_s_log_addrs to claim the + * logical addresses. + * + * This function is called with adap->lock held. + */ +static void cec_claim_log_addrs(struct cec_adapter *adap, bool block) +{ + if (WARN_ON(adap->is_configuring || adap->is_configured)) + return; + + init_completion(&adap->config_completion); + + /* Ready to kick off the thread */ + adap->is_configuring = true; + adap->kthread_config = kthread_run(cec_config_thread_func, adap, + "ceccfg-%s", adap->name); + if (IS_ERR(adap->kthread_config)) { + adap->kthread_config = NULL; + } else if (block) { + mutex_unlock(&adap->lock); + wait_for_completion(&adap->config_completion); + mutex_lock(&adap->lock); + } +} + +/* Set a new physical address and send an event notifying userspace of this. + * + * This function is called with adap->lock held. + */ +void __cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr, bool block) +{ + if (phys_addr == adap->phys_addr || adap->devnode.unregistered) + return; + + if (phys_addr == CEC_PHYS_ADDR_INVALID || + adap->phys_addr != CEC_PHYS_ADDR_INVALID) { + adap->phys_addr = CEC_PHYS_ADDR_INVALID; + cec_post_state_event(adap); + cec_adap_unconfigure(adap); + /* Disabling monitor all mode should always succeed */ + if (adap->monitor_all_cnt) + WARN_ON(call_op(adap, adap_monitor_all_enable, false)); + WARN_ON(adap->ops->adap_enable(adap, false)); + if (phys_addr == CEC_PHYS_ADDR_INVALID) + return; + } + + if (adap->ops->adap_enable(adap, true)) + return; + + if (adap->monitor_all_cnt && + call_op(adap, adap_monitor_all_enable, true)) { + WARN_ON(adap->ops->adap_enable(adap, false)); + return; + } + adap->phys_addr = phys_addr; + cec_post_state_event(adap); + if (adap->log_addrs.num_log_addrs) + cec_claim_log_addrs(adap, block); +} + +void cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr, bool block) +{ + if (IS_ERR_OR_NULL(adap)) + return; + + mutex_lock(&adap->lock); + __cec_s_phys_addr(adap, phys_addr, block); + mutex_unlock(&adap->lock); +} +EXPORT_SYMBOL_GPL(cec_s_phys_addr); + +/* + * Called from either the ioctl or a driver to set the logical addresses. + * + * This function is called with adap->lock held. + */ +int __cec_s_log_addrs(struct cec_adapter *adap, + struct cec_log_addrs *log_addrs, bool block) +{ + u16 type_mask = 0; + int i; + + if (adap->devnode.unregistered) + return -ENODEV; + + if (!log_addrs || log_addrs->num_log_addrs == 0) { + adap->log_addrs.num_log_addrs = 0; + cec_adap_unconfigure(adap); + return 0; + } + + if (log_addrs->flags & CEC_LOG_ADDRS_FL_CDC_ONLY) { + /* + * Sanitize log_addrs fields if a CDC-Only device is + * requested. + */ + log_addrs->num_log_addrs = 1; + log_addrs->osd_name[0] = '\0'; + log_addrs->vendor_id = CEC_VENDOR_ID_NONE; + log_addrs->log_addr_type[0] = CEC_LOG_ADDR_TYPE_UNREGISTERED; + /* + * This is just an internal convention since a CDC-Only device + * doesn't have to be a switch. But switches already use + * unregistered, so it makes some kind of sense to pick this + * as the primary device. Since a CDC-Only device never sends + * any 'normal' CEC messages this primary device type is never + * sent over the CEC bus. + */ + log_addrs->primary_device_type[0] = CEC_OP_PRIM_DEVTYPE_SWITCH; + log_addrs->all_device_types[0] = 0; + log_addrs->features[0][0] = 0; + log_addrs->features[0][1] = 0; + } + + /* Ensure the osd name is 0-terminated */ + log_addrs->osd_name[sizeof(log_addrs->osd_name) - 1] = '\0'; + + /* Sanity checks */ + if (log_addrs->num_log_addrs > adap->available_log_addrs) { + dprintk(1, "num_log_addrs > %d\n", adap->available_log_addrs); + return -EINVAL; + } + + /* + * Vendor ID is a 24 bit number, so check if the value is + * within the correct range. + */ + if (log_addrs->vendor_id != CEC_VENDOR_ID_NONE && + (log_addrs->vendor_id & 0xff000000) != 0) + return -EINVAL; + + if (log_addrs->cec_version != CEC_OP_CEC_VERSION_1_4 && + log_addrs->cec_version != CEC_OP_CEC_VERSION_2_0) + return -EINVAL; + + if (log_addrs->num_log_addrs > 1) + for (i = 0; i < log_addrs->num_log_addrs; i++) + if (log_addrs->log_addr_type[i] == + CEC_LOG_ADDR_TYPE_UNREGISTERED) { + dprintk(1, "num_log_addrs > 1 can't be combined with unregistered LA\n"); + return -EINVAL; + } + + for (i = 0; i < log_addrs->num_log_addrs; i++) { + const u8 feature_sz = ARRAY_SIZE(log_addrs->features[0]); + u8 *features = log_addrs->features[i]; + bool op_is_dev_features = false; + + log_addrs->log_addr[i] = CEC_LOG_ADDR_INVALID; + if (type_mask & (1 << log_addrs->log_addr_type[i])) { + dprintk(1, "duplicate logical address type\n"); + return -EINVAL; + } + type_mask |= 1 << log_addrs->log_addr_type[i]; + if ((type_mask & (1 << CEC_LOG_ADDR_TYPE_RECORD)) && + (type_mask & (1 << CEC_LOG_ADDR_TYPE_PLAYBACK))) { + /* Record already contains the playback functionality */ + dprintk(1, "invalid record + playback combination\n"); + return -EINVAL; + } + if (log_addrs->primary_device_type[i] > + CEC_OP_PRIM_DEVTYPE_PROCESSOR) { + dprintk(1, "unknown primary device type\n"); + return -EINVAL; + } + if (log_addrs->primary_device_type[i] == 2) { + dprintk(1, "invalid primary device type\n"); + return -EINVAL; + } + if (log_addrs->log_addr_type[i] > CEC_LOG_ADDR_TYPE_UNREGISTERED) { + dprintk(1, "unknown logical address type\n"); + return -EINVAL; + } + for (i = 0; i < feature_sz; i++) { + if ((features[i] & 0x80) == 0) { + if (op_is_dev_features) + break; + op_is_dev_features = true; + } + } + if (!op_is_dev_features || i == feature_sz) { + dprintk(1, "malformed features\n"); + return -EINVAL; + } + /* Zero unused part of the feature array */ + memset(features + i + 1, 0, feature_sz - i - 1); + } + + if (log_addrs->cec_version >= CEC_OP_CEC_VERSION_2_0) { + if (log_addrs->num_log_addrs > 2) { + dprintk(1, "CEC 2.0 allows no more than 2 logical addresses\n"); + return -EINVAL; + } + if (log_addrs->num_log_addrs == 2) { + if (!(type_mask & ((1 << CEC_LOG_ADDR_TYPE_AUDIOSYSTEM) | + (1 << CEC_LOG_ADDR_TYPE_TV)))) { + dprintk(1, "Two LAs is only allowed for audiosystem and TV\n"); + return -EINVAL; + } + if (!(type_mask & ((1 << CEC_LOG_ADDR_TYPE_PLAYBACK) | + (1 << CEC_LOG_ADDR_TYPE_RECORD)))) { + dprintk(1, "An audiosystem/TV can only be combined with record or playback\n"); + return -EINVAL; + } + } + } + + /* Zero unused LAs */ + for (i = log_addrs->num_log_addrs; i < CEC_MAX_LOG_ADDRS; i++) { + log_addrs->primary_device_type[i] = 0; + log_addrs->log_addr_type[i] = 0; + log_addrs->all_device_types[i] = 0; + memset(log_addrs->features[i], 0, + sizeof(log_addrs->features[i])); + } + + log_addrs->log_addr_mask = adap->log_addrs.log_addr_mask; + adap->log_addrs = *log_addrs; + if (adap->phys_addr != CEC_PHYS_ADDR_INVALID) + cec_claim_log_addrs(adap, block); + return 0; +} + +int cec_s_log_addrs(struct cec_adapter *adap, + struct cec_log_addrs *log_addrs, bool block) +{ + int err; + + mutex_lock(&adap->lock); + err = __cec_s_log_addrs(adap, log_addrs, block); + mutex_unlock(&adap->lock); + return err; +} +EXPORT_SYMBOL_GPL(cec_s_log_addrs); + +/* High-level core CEC message handling */ + +/* Transmit the Report Features message */ +static int cec_report_features(struct cec_adapter *adap, unsigned int la_idx) +{ + struct cec_msg msg = { }; + const struct cec_log_addrs *las = &adap->log_addrs; + const u8 *features = las->features[la_idx]; + bool op_is_dev_features = false; + unsigned int idx; + + /* This is 2.0 and up only */ + if (adap->log_addrs.cec_version < CEC_OP_CEC_VERSION_2_0) + return 0; + + /* Report Features */ + msg.msg[0] = (las->log_addr[la_idx] << 4) | 0x0f; + msg.len = 4; + msg.msg[1] = CEC_MSG_REPORT_FEATURES; + msg.msg[2] = adap->log_addrs.cec_version; + msg.msg[3] = las->all_device_types[la_idx]; + + /* Write RC Profiles first, then Device Features */ + for (idx = 0; idx < ARRAY_SIZE(las->features[0]); idx++) { + msg.msg[msg.len++] = features[idx]; + if ((features[idx] & CEC_OP_FEAT_EXT) == 0) { + if (op_is_dev_features) + break; + op_is_dev_features = true; + } + } + return cec_transmit_msg(adap, &msg, false); +} + +/* Transmit the Report Physical Address message */ +static int cec_report_phys_addr(struct cec_adapter *adap, unsigned int la_idx) +{ + const struct cec_log_addrs *las = &adap->log_addrs; + struct cec_msg msg = { }; + + /* Report Physical Address */ + msg.msg[0] = (las->log_addr[la_idx] << 4) | 0x0f; + cec_msg_report_physical_addr(&msg, adap->phys_addr, + las->primary_device_type[la_idx]); + dprintk(2, "config: la %d pa %x.%x.%x.%x\n", + las->log_addr[la_idx], + cec_phys_addr_exp(adap->phys_addr)); + return cec_transmit_msg(adap, &msg, false); +} + +/* Transmit the Feature Abort message */ +static int cec_feature_abort_reason(struct cec_adapter *adap, + struct cec_msg *msg, u8 reason) +{ + struct cec_msg tx_msg = { }; + + /* + * Don't reply with CEC_MSG_FEATURE_ABORT to a CEC_MSG_FEATURE_ABORT + * message! + */ + if (msg->msg[1] == CEC_MSG_FEATURE_ABORT) + return 0; + cec_msg_set_reply_to(&tx_msg, msg); + cec_msg_feature_abort(&tx_msg, msg->msg[1], reason); + return cec_transmit_msg(adap, &tx_msg, false); +} + +static int cec_feature_abort(struct cec_adapter *adap, struct cec_msg *msg) +{ + return cec_feature_abort_reason(adap, msg, + CEC_OP_ABORT_UNRECOGNIZED_OP); +} + +static int cec_feature_refused(struct cec_adapter *adap, struct cec_msg *msg) +{ + return cec_feature_abort_reason(adap, msg, + CEC_OP_ABORT_REFUSED); +} + +/* + * Called when a CEC message is received. This function will do any + * necessary core processing. The is_reply bool is true if this message + * is a reply to an earlier transmit. + * + * The message is either a broadcast message or a valid directed message. + */ +static int cec_receive_notify(struct cec_adapter *adap, struct cec_msg *msg, + bool is_reply) +{ + bool is_broadcast = cec_msg_is_broadcast(msg); + u8 dest_laddr = cec_msg_destination(msg); + u8 init_laddr = cec_msg_initiator(msg); + u8 devtype = cec_log_addr2dev(adap, dest_laddr); + int la_idx = cec_log_addr2idx(adap, dest_laddr); + bool from_unregistered = init_laddr == 0xf; + struct cec_msg tx_cec_msg = { }; + + dprintk(1, "cec_receive_notify: %*ph\n", msg->len, msg->msg); + + /* If this is a CDC-Only device, then ignore any non-CDC messages */ + if (cec_is_cdc_only(&adap->log_addrs) && + msg->msg[1] != CEC_MSG_CDC_MESSAGE) + return 0; + + if (adap->ops->received) { + /* Allow drivers to process the message first */ + if (adap->ops->received(adap, msg) != -ENOMSG) + return 0; + } + + /* + * REPORT_PHYSICAL_ADDR, CEC_MSG_USER_CONTROL_PRESSED and + * CEC_MSG_USER_CONTROL_RELEASED messages always have to be + * handled by the CEC core, even if the passthrough mode is on. + * The others are just ignored if passthrough mode is on. + */ + switch (msg->msg[1]) { + case CEC_MSG_GET_CEC_VERSION: + case CEC_MSG_GIVE_DEVICE_VENDOR_ID: + case CEC_MSG_ABORT: + case CEC_MSG_GIVE_DEVICE_POWER_STATUS: + case CEC_MSG_GIVE_PHYSICAL_ADDR: + case CEC_MSG_GIVE_OSD_NAME: + case CEC_MSG_GIVE_FEATURES: + /* + * Skip processing these messages if the passthrough mode + * is on. + */ + if (adap->passthrough) + goto skip_processing; + /* Ignore if addressing is wrong */ + if (is_broadcast || from_unregistered) + return 0; + break; + + case CEC_MSG_USER_CONTROL_PRESSED: + case CEC_MSG_USER_CONTROL_RELEASED: + /* Wrong addressing mode: don't process */ + if (is_broadcast || from_unregistered) + goto skip_processing; + break; + + case CEC_MSG_REPORT_PHYSICAL_ADDR: + /* + * This message is always processed, regardless of the + * passthrough setting. + * + * Exception: don't process if wrong addressing mode. + */ + if (!is_broadcast) + goto skip_processing; + break; + + default: + break; + } + + cec_msg_set_reply_to(&tx_cec_msg, msg); + + switch (msg->msg[1]) { + /* The following messages are processed but still passed through */ + case CEC_MSG_REPORT_PHYSICAL_ADDR: { + u16 pa = (msg->msg[2] << 8) | msg->msg[3]; + + if (!from_unregistered) + adap->phys_addrs[init_laddr] = pa; + dprintk(1, "Reported physical address %x.%x.%x.%x for logical address %d\n", + cec_phys_addr_exp(pa), init_laddr); + break; + } + + case CEC_MSG_USER_CONTROL_PRESSED: + if (!(adap->capabilities & CEC_CAP_RC) || + !(adap->log_addrs.flags & CEC_LOG_ADDRS_FL_ALLOW_RC_PASSTHRU)) + break; + +#if IS_REACHABLE(CONFIG_RC_CORE) + switch (msg->msg[2]) { + /* + * Play function, this message can have variable length + * depending on the specific play function that is used. + */ + case 0x60: + if (msg->len == 2) + rc_keydown(adap->rc, RC_TYPE_CEC, + msg->msg[2], 0); + else + rc_keydown(adap->rc, RC_TYPE_CEC, + msg->msg[2] << 8 | msg->msg[3], 0); + break; + /* + * Other function messages that are not handled. + * Currently the RC framework does not allow to supply an + * additional parameter to a keypress. These "keys" contain + * other information such as channel number, an input number + * etc. + * For the time being these messages are not processed by the + * framework and are simply forwarded to the user space. + */ + case 0x56: case 0x57: + case 0x67: case 0x68: case 0x69: case 0x6a: + break; + default: + rc_keydown(adap->rc, RC_TYPE_CEC, msg->msg[2], 0); + break; + } +#endif + break; + + case CEC_MSG_USER_CONTROL_RELEASED: + if (!(adap->capabilities & CEC_CAP_RC) || + !(adap->log_addrs.flags & CEC_LOG_ADDRS_FL_ALLOW_RC_PASSTHRU)) + break; +#if IS_REACHABLE(CONFIG_RC_CORE) + rc_keyup(adap->rc); +#endif + break; + + /* + * The remaining messages are only processed if the passthrough mode + * is off. + */ + case CEC_MSG_GET_CEC_VERSION: + cec_msg_cec_version(&tx_cec_msg, adap->log_addrs.cec_version); + return cec_transmit_msg(adap, &tx_cec_msg, false); + + case CEC_MSG_GIVE_PHYSICAL_ADDR: + /* Do nothing for CEC switches using addr 15 */ + if (devtype == CEC_OP_PRIM_DEVTYPE_SWITCH && dest_laddr == 15) + return 0; + cec_msg_report_physical_addr(&tx_cec_msg, adap->phys_addr, devtype); + return cec_transmit_msg(adap, &tx_cec_msg, false); + + case CEC_MSG_GIVE_DEVICE_VENDOR_ID: + if (adap->log_addrs.vendor_id == CEC_VENDOR_ID_NONE) + return cec_feature_abort(adap, msg); + cec_msg_device_vendor_id(&tx_cec_msg, adap->log_addrs.vendor_id); + return cec_transmit_msg(adap, &tx_cec_msg, false); + + case CEC_MSG_ABORT: + /* Do nothing for CEC switches */ + if (devtype == CEC_OP_PRIM_DEVTYPE_SWITCH) + return 0; + return cec_feature_refused(adap, msg); + + case CEC_MSG_GIVE_OSD_NAME: { + if (adap->log_addrs.osd_name[0] == 0) + return cec_feature_abort(adap, msg); + cec_msg_set_osd_name(&tx_cec_msg, adap->log_addrs.osd_name); + return cec_transmit_msg(adap, &tx_cec_msg, false); + } + + case CEC_MSG_GIVE_FEATURES: + if (adap->log_addrs.cec_version >= CEC_OP_CEC_VERSION_2_0) + return cec_report_features(adap, la_idx); + return 0; + + default: + /* + * Unprocessed messages are aborted if userspace isn't doing + * any processing either. + */ + if (!is_broadcast && !is_reply && !adap->follower_cnt && + !adap->cec_follower && msg->msg[1] != CEC_MSG_FEATURE_ABORT) + return cec_feature_abort(adap, msg); + break; + } + +skip_processing: + /* If this was a reply, then we're done, unless otherwise specified */ + if (is_reply && !(msg->flags & CEC_MSG_FL_REPLY_TO_FOLLOWERS)) + return 0; + + /* + * Send to the exclusive follower if there is one, otherwise send + * to all followers. + */ + if (adap->cec_follower) + cec_queue_msg_fh(adap->cec_follower, msg); + else + cec_queue_msg_followers(adap, msg); + return 0; +} + +/* + * Helper functions to keep track of the 'monitor all' use count. + * + * These functions are called with adap->lock held. + */ +int cec_monitor_all_cnt_inc(struct cec_adapter *adap) +{ + int ret = 0; + + if (adap->monitor_all_cnt == 0) + ret = call_op(adap, adap_monitor_all_enable, 1); + if (ret == 0) + adap->monitor_all_cnt++; + return ret; +} + +void cec_monitor_all_cnt_dec(struct cec_adapter *adap) +{ + adap->monitor_all_cnt--; + if (adap->monitor_all_cnt == 0) + WARN_ON(call_op(adap, adap_monitor_all_enable, 0)); +} + +#ifdef CONFIG_MEDIA_CEC_DEBUG +/* + * Log the current state of the CEC adapter. + * Very useful for debugging. + */ +int cec_adap_status(struct seq_file *file, void *priv) +{ + struct cec_adapter *adap = dev_get_drvdata(file->private); + struct cec_data *data; + + mutex_lock(&adap->lock); + seq_printf(file, "configured: %d\n", adap->is_configured); + seq_printf(file, "configuring: %d\n", adap->is_configuring); + seq_printf(file, "phys_addr: %x.%x.%x.%x\n", + cec_phys_addr_exp(adap->phys_addr)); + seq_printf(file, "number of LAs: %d\n", adap->log_addrs.num_log_addrs); + seq_printf(file, "LA mask: 0x%04x\n", adap->log_addrs.log_addr_mask); + if (adap->cec_follower) + seq_printf(file, "has CEC follower%s\n", + adap->passthrough ? " (in passthrough mode)" : ""); + if (adap->cec_initiator) + seq_puts(file, "has CEC initiator\n"); + if (adap->monitor_all_cnt) + seq_printf(file, "file handles in Monitor All mode: %u\n", + adap->monitor_all_cnt); + data = adap->transmitting; + if (data) + seq_printf(file, "transmitting message: %*ph (reply: %02x, timeout: %ums)\n", + data->msg.len, data->msg.msg, data->msg.reply, + data->msg.timeout); + seq_printf(file, "pending transmits: %u\n", adap->transmit_queue_sz); + list_for_each_entry(data, &adap->transmit_queue, list) { + seq_printf(file, "queued tx message: %*ph (reply: %02x, timeout: %ums)\n", + data->msg.len, data->msg.msg, data->msg.reply, + data->msg.timeout); + } + list_for_each_entry(data, &adap->wait_queue, list) { + seq_printf(file, "message waiting for reply: %*ph (reply: %02x, timeout: %ums)\n", + data->msg.len, data->msg.msg, data->msg.reply, + data->msg.timeout); + } + + call_void_op(adap, adap_status, file); + mutex_unlock(&adap->lock); + return 0; +} +#endif diff --git a/drivers/media/cec/cec-api.c b/drivers/media/cec/cec-api.c new file mode 100644 index 000000000000..d4bc4ee2c6e5 --- /dev/null +++ b/drivers/media/cec/cec-api.c @@ -0,0 +1,588 @@ +/* + * cec-api.c - HDMI Consumer Electronics Control framework - API + * + * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. + * + * This program is free software; you may redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "cec-priv.h" + +static inline struct cec_devnode *cec_devnode_data(struct file *filp) +{ + struct cec_fh *fh = filp->private_data; + + return &fh->adap->devnode; +} + +/* CEC file operations */ + +static unsigned int cec_poll(struct file *filp, + struct poll_table_struct *poll) +{ + struct cec_devnode *devnode = cec_devnode_data(filp); + struct cec_fh *fh = filp->private_data; + struct cec_adapter *adap = fh->adap; + unsigned int res = 0; + + if (!devnode->registered) + return POLLERR | POLLHUP; + mutex_lock(&adap->lock); + if (adap->is_configured && + adap->transmit_queue_sz < CEC_MAX_MSG_TX_QUEUE_SZ) + res |= POLLOUT | POLLWRNORM; + if (fh->queued_msgs) + res |= POLLIN | POLLRDNORM; + if (fh->pending_events) + res |= POLLPRI; + poll_wait(filp, &fh->wait, poll); + mutex_unlock(&adap->lock); + return res; +} + +static bool cec_is_busy(const struct cec_adapter *adap, + const struct cec_fh *fh) +{ + bool valid_initiator = adap->cec_initiator && adap->cec_initiator == fh; + bool valid_follower = adap->cec_follower && adap->cec_follower == fh; + + /* + * Exclusive initiators and followers can always access the CEC adapter + */ + if (valid_initiator || valid_follower) + return false; + /* + * All others can only access the CEC adapter if there is no + * exclusive initiator and they are in INITIATOR mode. + */ + return adap->cec_initiator || + fh->mode_initiator == CEC_MODE_NO_INITIATOR; +} + +static long cec_adap_g_caps(struct cec_adapter *adap, + struct cec_caps __user *parg) +{ + struct cec_caps caps = {}; + + strlcpy(caps.driver, adap->devnode.parent->driver->name, + sizeof(caps.driver)); + strlcpy(caps.name, adap->name, sizeof(caps.name)); + caps.available_log_addrs = adap->available_log_addrs; + caps.capabilities = adap->capabilities; + caps.version = LINUX_VERSION_CODE; + if (copy_to_user(parg, &caps, sizeof(caps))) + return -EFAULT; + return 0; +} + +static long cec_adap_g_phys_addr(struct cec_adapter *adap, + __u16 __user *parg) +{ + u16 phys_addr; + + mutex_lock(&adap->lock); + phys_addr = adap->phys_addr; + mutex_unlock(&adap->lock); + if (copy_to_user(parg, &phys_addr, sizeof(phys_addr))) + return -EFAULT; + return 0; +} + +static long cec_adap_s_phys_addr(struct cec_adapter *adap, struct cec_fh *fh, + bool block, __u16 __user *parg) +{ + u16 phys_addr; + long err; + + if (!(adap->capabilities & CEC_CAP_PHYS_ADDR)) + return -ENOTTY; + if (copy_from_user(&phys_addr, parg, sizeof(phys_addr))) + return -EFAULT; + + err = cec_phys_addr_validate(phys_addr, NULL, NULL); + if (err) + return err; + mutex_lock(&adap->lock); + if (cec_is_busy(adap, fh)) + err = -EBUSY; + else + __cec_s_phys_addr(adap, phys_addr, block); + mutex_unlock(&adap->lock); + return err; +} + +static long cec_adap_g_log_addrs(struct cec_adapter *adap, + struct cec_log_addrs __user *parg) +{ + struct cec_log_addrs log_addrs; + + mutex_lock(&adap->lock); + log_addrs = adap->log_addrs; + if (!adap->is_configured) + memset(log_addrs.log_addr, CEC_LOG_ADDR_INVALID, + sizeof(log_addrs.log_addr)); + mutex_unlock(&adap->lock); + + if (copy_to_user(parg, &log_addrs, sizeof(log_addrs))) + return -EFAULT; + return 0; +} + +static long cec_adap_s_log_addrs(struct cec_adapter *adap, struct cec_fh *fh, + bool block, struct cec_log_addrs __user *parg) +{ + struct cec_log_addrs log_addrs; + long err = -EBUSY; + + if (!(adap->capabilities & CEC_CAP_LOG_ADDRS)) + return -ENOTTY; + if (copy_from_user(&log_addrs, parg, sizeof(log_addrs))) + return -EFAULT; + log_addrs.flags &= CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK | + CEC_LOG_ADDRS_FL_ALLOW_RC_PASSTHRU | + CEC_LOG_ADDRS_FL_CDC_ONLY; + mutex_lock(&adap->lock); + if (!adap->is_configuring && + (!log_addrs.num_log_addrs || !adap->is_configured) && + !cec_is_busy(adap, fh)) { + err = __cec_s_log_addrs(adap, &log_addrs, block); + if (!err) + log_addrs = adap->log_addrs; + } + mutex_unlock(&adap->lock); + if (err) + return err; + if (copy_to_user(parg, &log_addrs, sizeof(log_addrs))) + return -EFAULT; + return 0; +} + +static long cec_transmit(struct cec_adapter *adap, struct cec_fh *fh, + bool block, struct cec_msg __user *parg) +{ + struct cec_msg msg = {}; + long err = 0; + + if (!(adap->capabilities & CEC_CAP_TRANSMIT)) + return -ENOTTY; + if (copy_from_user(&msg, parg, sizeof(msg))) + return -EFAULT; + + /* A CDC-Only device can only send CDC messages */ + if ((adap->log_addrs.flags & CEC_LOG_ADDRS_FL_CDC_ONLY) && + (msg.len == 1 || msg.msg[1] != CEC_MSG_CDC_MESSAGE)) + return -EINVAL; + + msg.flags &= CEC_MSG_FL_REPLY_TO_FOLLOWERS; + mutex_lock(&adap->lock); + if (!adap->is_configured) + err = -ENONET; + else if (cec_is_busy(adap, fh)) + err = -EBUSY; + else + err = cec_transmit_msg_fh(adap, &msg, fh, block); + mutex_unlock(&adap->lock); + if (err) + return err; + if (copy_to_user(parg, &msg, sizeof(msg))) + return -EFAULT; + return 0; +} + +/* Called by CEC_RECEIVE: wait for a message to arrive */ +static int cec_receive_msg(struct cec_fh *fh, struct cec_msg *msg, bool block) +{ + u32 timeout = msg->timeout; + int res; + + do { + mutex_lock(&fh->lock); + /* Are there received messages queued up? */ + if (fh->queued_msgs) { + /* Yes, return the first one */ + struct cec_msg_entry *entry = + list_first_entry(&fh->msgs, + struct cec_msg_entry, list); + + list_del(&entry->list); + *msg = entry->msg; + kfree(entry); + fh->queued_msgs--; + mutex_unlock(&fh->lock); + /* restore original timeout value */ + msg->timeout = timeout; + return 0; + } + + /* No, return EAGAIN in non-blocking mode or wait */ + mutex_unlock(&fh->lock); + + /* Return when in non-blocking mode */ + if (!block) + return -EAGAIN; + + if (msg->timeout) { + /* The user specified a timeout */ + res = wait_event_interruptible_timeout(fh->wait, + fh->queued_msgs, + msecs_to_jiffies(msg->timeout)); + if (res == 0) + res = -ETIMEDOUT; + else if (res > 0) + res = 0; + } else { + /* Wait indefinitely */ + res = wait_event_interruptible(fh->wait, + fh->queued_msgs); + } + /* Exit on error, otherwise loop to get the new message */ + } while (!res); + return res; +} + +static long cec_receive(struct cec_adapter *adap, struct cec_fh *fh, + bool block, struct cec_msg __user *parg) +{ + struct cec_msg msg = {}; + long err = 0; + + if (copy_from_user(&msg, parg, sizeof(msg))) + return -EFAULT; + mutex_lock(&adap->lock); + if (!adap->is_configured && fh->mode_follower < CEC_MODE_MONITOR) + err = -ENONET; + mutex_unlock(&adap->lock); + if (err) + return err; + + err = cec_receive_msg(fh, &msg, block); + if (err) + return err; + if (copy_to_user(parg, &msg, sizeof(msg))) + return -EFAULT; + return 0; +} + +static long cec_dqevent(struct cec_adapter *adap, struct cec_fh *fh, + bool block, struct cec_event __user *parg) +{ + struct cec_event *ev = NULL; + u64 ts = ~0ULL; + unsigned int i; + long err = 0; + + mutex_lock(&fh->lock); + while (!fh->pending_events && block) { + mutex_unlock(&fh->lock); + err = wait_event_interruptible(fh->wait, fh->pending_events); + if (err) + return err; + mutex_lock(&fh->lock); + } + + /* Find the oldest event */ + for (i = 0; i < CEC_NUM_EVENTS; i++) { + if (fh->pending_events & (1 << (i + 1)) && + fh->events[i].ts <= ts) { + ev = &fh->events[i]; + ts = ev->ts; + } + } + if (!ev) { + err = -EAGAIN; + goto unlock; + } + + if (copy_to_user(parg, ev, sizeof(*ev))) { + err = -EFAULT; + goto unlock; + } + + fh->pending_events &= ~(1 << ev->event); + +unlock: + mutex_unlock(&fh->lock); + return err; +} + +static long cec_g_mode(struct cec_adapter *adap, struct cec_fh *fh, + u32 __user *parg) +{ + u32 mode = fh->mode_initiator | fh->mode_follower; + + if (copy_to_user(parg, &mode, sizeof(mode))) + return -EFAULT; + return 0; +} + +static long cec_s_mode(struct cec_adapter *adap, struct cec_fh *fh, + u32 __user *parg) +{ + u32 mode; + u8 mode_initiator; + u8 mode_follower; + long err = 0; + + if (copy_from_user(&mode, parg, sizeof(mode))) + return -EFAULT; + if (mode & ~(CEC_MODE_INITIATOR_MSK | CEC_MODE_FOLLOWER_MSK)) + return -EINVAL; + + mode_initiator = mode & CEC_MODE_INITIATOR_MSK; + mode_follower = mode & CEC_MODE_FOLLOWER_MSK; + + if (mode_initiator > CEC_MODE_EXCL_INITIATOR || + mode_follower > CEC_MODE_MONITOR_ALL) + return -EINVAL; + + if (mode_follower == CEC_MODE_MONITOR_ALL && + !(adap->capabilities & CEC_CAP_MONITOR_ALL)) + return -EINVAL; + + /* Follower modes should always be able to send CEC messages */ + if ((mode_initiator == CEC_MODE_NO_INITIATOR || + !(adap->capabilities & CEC_CAP_TRANSMIT)) && + mode_follower >= CEC_MODE_FOLLOWER && + mode_follower <= CEC_MODE_EXCL_FOLLOWER_PASSTHRU) + return -EINVAL; + + /* Monitor modes require CEC_MODE_NO_INITIATOR */ + if (mode_initiator && mode_follower >= CEC_MODE_MONITOR) + return -EINVAL; + + /* Monitor modes require CAP_NET_ADMIN */ + if (mode_follower >= CEC_MODE_MONITOR && !capable(CAP_NET_ADMIN)) + return -EPERM; + + mutex_lock(&adap->lock); + /* + * You can't become exclusive follower if someone else already + * has that job. + */ + if ((mode_follower == CEC_MODE_EXCL_FOLLOWER || + mode_follower == CEC_MODE_EXCL_FOLLOWER_PASSTHRU) && + adap->cec_follower && adap->cec_follower != fh) + err = -EBUSY; + /* + * You can't become exclusive initiator if someone else already + * has that job. + */ + if (mode_initiator == CEC_MODE_EXCL_INITIATOR && + adap->cec_initiator && adap->cec_initiator != fh) + err = -EBUSY; + + if (!err) { + bool old_mon_all = fh->mode_follower == CEC_MODE_MONITOR_ALL; + bool new_mon_all = mode_follower == CEC_MODE_MONITOR_ALL; + + if (old_mon_all != new_mon_all) { + if (new_mon_all) + err = cec_monitor_all_cnt_inc(adap); + else + cec_monitor_all_cnt_dec(adap); + } + } + + if (err) { + mutex_unlock(&adap->lock); + return err; + } + + if (fh->mode_follower == CEC_MODE_FOLLOWER) + adap->follower_cnt--; + if (mode_follower == CEC_MODE_FOLLOWER) + adap->follower_cnt++; + if (mode_follower == CEC_MODE_EXCL_FOLLOWER || + mode_follower == CEC_MODE_EXCL_FOLLOWER_PASSTHRU) { + adap->passthrough = + mode_follower == CEC_MODE_EXCL_FOLLOWER_PASSTHRU; + adap->cec_follower = fh; + } else if (adap->cec_follower == fh) { + adap->passthrough = false; + adap->cec_follower = NULL; + } + if (mode_initiator == CEC_MODE_EXCL_INITIATOR) + adap->cec_initiator = fh; + else if (adap->cec_initiator == fh) + adap->cec_initiator = NULL; + fh->mode_initiator = mode_initiator; + fh->mode_follower = mode_follower; + mutex_unlock(&adap->lock); + return 0; +} + +static long cec_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) +{ + struct cec_devnode *devnode = cec_devnode_data(filp); + struct cec_fh *fh = filp->private_data; + struct cec_adapter *adap = fh->adap; + bool block = !(filp->f_flags & O_NONBLOCK); + void __user *parg = (void __user *)arg; + + if (!devnode->registered) + return -ENODEV; + + switch (cmd) { + case CEC_ADAP_G_CAPS: + return cec_adap_g_caps(adap, parg); + + case CEC_ADAP_G_PHYS_ADDR: + return cec_adap_g_phys_addr(adap, parg); + + case CEC_ADAP_S_PHYS_ADDR: + return cec_adap_s_phys_addr(adap, fh, block, parg); + + case CEC_ADAP_G_LOG_ADDRS: + return cec_adap_g_log_addrs(adap, parg); + + case CEC_ADAP_S_LOG_ADDRS: + return cec_adap_s_log_addrs(adap, fh, block, parg); + + case CEC_TRANSMIT: + return cec_transmit(adap, fh, block, parg); + + case CEC_RECEIVE: + return cec_receive(adap, fh, block, parg); + + case CEC_DQEVENT: + return cec_dqevent(adap, fh, block, parg); + + case CEC_G_MODE: + return cec_g_mode(adap, fh, parg); + + case CEC_S_MODE: + return cec_s_mode(adap, fh, parg); + + default: + return -ENOTTY; + } +} + +static int cec_open(struct inode *inode, struct file *filp) +{ + struct cec_devnode *devnode = + container_of(inode->i_cdev, struct cec_devnode, cdev); + struct cec_adapter *adap = to_cec_adapter(devnode); + struct cec_fh *fh = kzalloc(sizeof(*fh), GFP_KERNEL); + /* + * Initial events that are automatically sent when the cec device is + * opened. + */ + struct cec_event ev_state = { + .event = CEC_EVENT_STATE_CHANGE, + .flags = CEC_EVENT_FL_INITIAL_STATE, + }; + int err; + + if (!fh) + return -ENOMEM; + + INIT_LIST_HEAD(&fh->msgs); + INIT_LIST_HEAD(&fh->xfer_list); + mutex_init(&fh->lock); + init_waitqueue_head(&fh->wait); + + fh->mode_initiator = CEC_MODE_INITIATOR; + fh->adap = adap; + + err = cec_get_device(devnode); + if (err) { + kfree(fh); + return err; + } + + filp->private_data = fh; + + mutex_lock(&devnode->lock); + /* Queue up initial state events */ + ev_state.state_change.phys_addr = adap->phys_addr; + ev_state.state_change.log_addr_mask = adap->log_addrs.log_addr_mask; + cec_queue_event_fh(fh, &ev_state, 0); + + list_add(&fh->list, &devnode->fhs); + mutex_unlock(&devnode->lock); + + return 0; +} + +/* Override for the release function */ +static int cec_release(struct inode *inode, struct file *filp) +{ + struct cec_devnode *devnode = cec_devnode_data(filp); + struct cec_adapter *adap = to_cec_adapter(devnode); + struct cec_fh *fh = filp->private_data; + + mutex_lock(&adap->lock); + if (adap->cec_initiator == fh) + adap->cec_initiator = NULL; + if (adap->cec_follower == fh) { + adap->cec_follower = NULL; + adap->passthrough = false; + } + if (fh->mode_follower == CEC_MODE_FOLLOWER) + adap->follower_cnt--; + if (fh->mode_follower == CEC_MODE_MONITOR_ALL) + cec_monitor_all_cnt_dec(adap); + mutex_unlock(&adap->lock); + + mutex_lock(&devnode->lock); + list_del(&fh->list); + mutex_unlock(&devnode->lock); + + /* Unhook pending transmits from this filehandle. */ + mutex_lock(&adap->lock); + while (!list_empty(&fh->xfer_list)) { + struct cec_data *data = + list_first_entry(&fh->xfer_list, struct cec_data, xfer_list); + + data->blocking = false; + data->fh = NULL; + list_del(&data->xfer_list); + } + mutex_unlock(&adap->lock); + while (!list_empty(&fh->msgs)) { + struct cec_msg_entry *entry = + list_first_entry(&fh->msgs, struct cec_msg_entry, list); + + list_del(&entry->list); + kfree(entry); + } + kfree(fh); + + cec_put_device(devnode); + filp->private_data = NULL; + return 0; +} + +const struct file_operations cec_devnode_fops = { + .owner = THIS_MODULE, + .open = cec_open, + .unlocked_ioctl = cec_ioctl, + .release = cec_release, + .poll = cec_poll, + .llseek = no_llseek, +}; diff --git a/drivers/media/cec/cec-core.c b/drivers/media/cec/cec-core.c new file mode 100644 index 000000000000..b0137e247dc9 --- /dev/null +++ b/drivers/media/cec/cec-core.c @@ -0,0 +1,411 @@ +/* + * cec-core.c - HDMI Consumer Electronics Control framework - Core + * + * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. + * + * This program is free software; you may redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "cec-priv.h" + +#define CEC_NUM_DEVICES 256 +#define CEC_NAME "cec" + +int cec_debug; +module_param_named(debug, cec_debug, int, 0644); +MODULE_PARM_DESC(debug, "debug level (0-2)"); + +static dev_t cec_dev_t; + +/* Active devices */ +static DEFINE_MUTEX(cec_devnode_lock); +static DECLARE_BITMAP(cec_devnode_nums, CEC_NUM_DEVICES); + +static struct dentry *top_cec_dir; + +/* dev to cec_devnode */ +#define to_cec_devnode(cd) container_of(cd, struct cec_devnode, dev) + +int cec_get_device(struct cec_devnode *devnode) +{ + /* + * Check if the cec device is available. This needs to be done with + * the devnode->lock held to prevent an open/unregister race: + * without the lock, the device could be unregistered and freed between + * the devnode->registered check and get_device() calls, leading to + * a crash. + */ + mutex_lock(&devnode->lock); + /* + * return ENXIO if the cec device has been removed + * already or if it is not registered anymore. + */ + if (!devnode->registered) { + mutex_unlock(&devnode->lock); + return -ENXIO; + } + /* and increase the device refcount */ + get_device(&devnode->dev); + mutex_unlock(&devnode->lock); + return 0; +} + +void cec_put_device(struct cec_devnode *devnode) +{ + put_device(&devnode->dev); +} + +/* Called when the last user of the cec device exits. */ +static void cec_devnode_release(struct device *cd) +{ + struct cec_devnode *devnode = to_cec_devnode(cd); + + mutex_lock(&cec_devnode_lock); + /* Mark device node number as free */ + clear_bit(devnode->minor, cec_devnode_nums); + mutex_unlock(&cec_devnode_lock); + + cec_delete_adapter(to_cec_adapter(devnode)); +} + +static struct bus_type cec_bus_type = { + .name = CEC_NAME, +}; + +/* + * Register a cec device node + * + * The registration code assigns minor numbers and registers the new device node + * with the kernel. An error is returned if no free minor number can be found, + * or if the registration of the device node fails. + * + * Zero is returned on success. + * + * Note that if the cec_devnode_register call fails, the release() callback of + * the cec_devnode structure is *not* called, so the caller is responsible for + * freeing any data. + */ +static int __must_check cec_devnode_register(struct cec_devnode *devnode, + struct module *owner) +{ + int minor; + int ret; + + /* Initialization */ + INIT_LIST_HEAD(&devnode->fhs); + mutex_init(&devnode->lock); + + /* Part 1: Find a free minor number */ + mutex_lock(&cec_devnode_lock); + minor = find_next_zero_bit(cec_devnode_nums, CEC_NUM_DEVICES, 0); + if (minor == CEC_NUM_DEVICES) { + mutex_unlock(&cec_devnode_lock); + pr_err("could not get a free minor\n"); + return -ENFILE; + } + + set_bit(minor, cec_devnode_nums); + mutex_unlock(&cec_devnode_lock); + + devnode->minor = minor; + devnode->dev.bus = &cec_bus_type; + devnode->dev.devt = MKDEV(MAJOR(cec_dev_t), minor); + devnode->dev.release = cec_devnode_release; + devnode->dev.parent = devnode->parent; + dev_set_name(&devnode->dev, "cec%d", devnode->minor); + device_initialize(&devnode->dev); + + /* Part 2: Initialize and register the character device */ + cdev_init(&devnode->cdev, &cec_devnode_fops); + devnode->cdev.kobj.parent = &devnode->dev.kobj; + devnode->cdev.owner = owner; + + ret = cdev_add(&devnode->cdev, devnode->dev.devt, 1); + if (ret < 0) { + pr_err("%s: cdev_add failed\n", __func__); + goto clr_bit; + } + + ret = device_add(&devnode->dev); + if (ret) + goto cdev_del; + + devnode->registered = true; + return 0; + +cdev_del: + cdev_del(&devnode->cdev); +clr_bit: + mutex_lock(&cec_devnode_lock); + clear_bit(devnode->minor, cec_devnode_nums); + mutex_unlock(&cec_devnode_lock); + return ret; +} + +/* + * Unregister a cec device node + * + * This unregisters the passed device. Future open calls will be met with + * errors. + * + * This function can safely be called if the device node has never been + * registered or has already been unregistered. + */ +static void cec_devnode_unregister(struct cec_devnode *devnode) +{ + struct cec_fh *fh; + + mutex_lock(&devnode->lock); + + /* Check if devnode was never registered or already unregistered */ + if (!devnode->registered || devnode->unregistered) { + mutex_unlock(&devnode->lock); + return; + } + + list_for_each_entry(fh, &devnode->fhs, list) + wake_up_interruptible(&fh->wait); + + devnode->registered = false; + devnode->unregistered = true; + mutex_unlock(&devnode->lock); + + device_del(&devnode->dev); + cdev_del(&devnode->cdev); + put_device(&devnode->dev); +} + +struct cec_adapter *cec_allocate_adapter(const struct cec_adap_ops *ops, + void *priv, const char *name, u32 caps, + u8 available_las, struct device *parent) +{ + struct cec_adapter *adap; + int res; + + if (WARN_ON(!parent)) + return ERR_PTR(-EINVAL); + if (WARN_ON(!caps)) + return ERR_PTR(-EINVAL); + if (WARN_ON(!ops)) + return ERR_PTR(-EINVAL); + if (WARN_ON(!available_las || available_las > CEC_MAX_LOG_ADDRS)) + return ERR_PTR(-EINVAL); + adap = kzalloc(sizeof(*adap), GFP_KERNEL); + if (!adap) + return ERR_PTR(-ENOMEM); + adap->owner = parent->driver->owner; + adap->devnode.parent = parent; + strlcpy(adap->name, name, sizeof(adap->name)); + adap->phys_addr = CEC_PHYS_ADDR_INVALID; + adap->log_addrs.cec_version = CEC_OP_CEC_VERSION_2_0; + adap->log_addrs.vendor_id = CEC_VENDOR_ID_NONE; + adap->capabilities = caps; + adap->available_log_addrs = available_las; + adap->sequence = 0; + adap->ops = ops; + adap->priv = priv; + memset(adap->phys_addrs, 0xff, sizeof(adap->phys_addrs)); + mutex_init(&adap->lock); + INIT_LIST_HEAD(&adap->transmit_queue); + INIT_LIST_HEAD(&adap->wait_queue); + init_waitqueue_head(&adap->kthread_waitq); + + adap->kthread = kthread_run(cec_thread_func, adap, "cec-%s", name); + if (IS_ERR(adap->kthread)) { + pr_err("cec-%s: kernel_thread() failed\n", name); + res = PTR_ERR(adap->kthread); + kfree(adap); + return ERR_PTR(res); + } + + if (!(caps & CEC_CAP_RC)) + return adap; + +#if IS_REACHABLE(CONFIG_RC_CORE) + /* Prepare the RC input device */ + adap->rc = rc_allocate_device(); + if (!adap->rc) { + pr_err("cec-%s: failed to allocate memory for rc_dev\n", + name); + kthread_stop(adap->kthread); + kfree(adap); + return ERR_PTR(-ENOMEM); + } + + snprintf(adap->input_name, sizeof(adap->input_name), + "RC for %s", name); + snprintf(adap->input_phys, sizeof(adap->input_phys), + "%s/input0", name); + + adap->rc->input_name = adap->input_name; + adap->rc->input_phys = adap->input_phys; + adap->rc->input_id.bustype = BUS_CEC; + adap->rc->input_id.vendor = 0; + adap->rc->input_id.product = 0; + adap->rc->input_id.version = 1; + adap->rc->dev.parent = parent; + adap->rc->driver_type = RC_DRIVER_SCANCODE; + adap->rc->driver_name = CEC_NAME; + adap->rc->allowed_protocols = RC_BIT_CEC; + adap->rc->priv = adap; + adap->rc->map_name = RC_MAP_CEC; + adap->rc->timeout = MS_TO_NS(100); +#else + adap->capabilities &= ~CEC_CAP_RC; +#endif + return adap; +} +EXPORT_SYMBOL_GPL(cec_allocate_adapter); + +int cec_register_adapter(struct cec_adapter *adap) +{ + int res; + + if (IS_ERR_OR_NULL(adap)) + return 0; + +#if IS_REACHABLE(CONFIG_RC_CORE) + if (adap->capabilities & CEC_CAP_RC) { + res = rc_register_device(adap->rc); + + if (res) { + pr_err("cec-%s: failed to prepare input device\n", + adap->name); + rc_free_device(adap->rc); + adap->rc = NULL; + return res; + } + } +#endif + + res = cec_devnode_register(&adap->devnode, adap->owner); + if (res) { +#if IS_REACHABLE(CONFIG_RC_CORE) + /* Note: rc_unregister also calls rc_free */ + rc_unregister_device(adap->rc); + adap->rc = NULL; +#endif + return res; + } + + dev_set_drvdata(&adap->devnode.dev, adap); +#ifdef CONFIG_MEDIA_CEC_DEBUG + if (!top_cec_dir) + return 0; + + adap->cec_dir = debugfs_create_dir(dev_name(&adap->devnode.dev), top_cec_dir); + if (IS_ERR_OR_NULL(adap->cec_dir)) { + pr_warn("cec-%s: Failed to create debugfs dir\n", adap->name); + return 0; + } + adap->status_file = debugfs_create_devm_seqfile(&adap->devnode.dev, + "status", adap->cec_dir, cec_adap_status); + if (IS_ERR_OR_NULL(adap->status_file)) { + pr_warn("cec-%s: Failed to create status file\n", adap->name); + debugfs_remove_recursive(adap->cec_dir); + adap->cec_dir = NULL; + } +#endif + return 0; +} +EXPORT_SYMBOL_GPL(cec_register_adapter); + +void cec_unregister_adapter(struct cec_adapter *adap) +{ + if (IS_ERR_OR_NULL(adap)) + return; + +#if IS_REACHABLE(CONFIG_RC_CORE) + /* Note: rc_unregister also calls rc_free */ + rc_unregister_device(adap->rc); + adap->rc = NULL; +#endif + debugfs_remove_recursive(adap->cec_dir); + cec_devnode_unregister(&adap->devnode); +} +EXPORT_SYMBOL_GPL(cec_unregister_adapter); + +void cec_delete_adapter(struct cec_adapter *adap) +{ + if (IS_ERR_OR_NULL(adap)) + return; + mutex_lock(&adap->lock); + __cec_s_phys_addr(adap, CEC_PHYS_ADDR_INVALID, false); + mutex_unlock(&adap->lock); + kthread_stop(adap->kthread); + if (adap->kthread_config) + kthread_stop(adap->kthread_config); +#if IS_REACHABLE(CONFIG_RC_CORE) + rc_free_device(adap->rc); +#endif + kfree(adap); +} +EXPORT_SYMBOL_GPL(cec_delete_adapter); + +/* + * Initialise cec for linux + */ +static int __init cec_devnode_init(void) +{ + int ret; + + pr_info("Linux cec interface: v0.10\n"); + ret = alloc_chrdev_region(&cec_dev_t, 0, CEC_NUM_DEVICES, + CEC_NAME); + if (ret < 0) { + pr_warn("cec: unable to allocate major\n"); + return ret; + } + +#ifdef CONFIG_MEDIA_CEC_DEBUG + top_cec_dir = debugfs_create_dir("cec", NULL); + if (IS_ERR_OR_NULL(top_cec_dir)) { + pr_warn("cec: Failed to create debugfs cec dir\n"); + top_cec_dir = NULL; + } +#endif + + ret = bus_register(&cec_bus_type); + if (ret < 0) { + unregister_chrdev_region(cec_dev_t, CEC_NUM_DEVICES); + pr_warn("cec: bus_register failed\n"); + return -EIO; + } + + return 0; +} + +static void __exit cec_devnode_exit(void) +{ + debugfs_remove_recursive(top_cec_dir); + bus_unregister(&cec_bus_type); + unregister_chrdev_region(cec_dev_t, CEC_NUM_DEVICES); +} + +subsys_initcall(cec_devnode_init); +module_exit(cec_devnode_exit) + +MODULE_AUTHOR("Hans Verkuil "); +MODULE_DESCRIPTION("Device node registration for cec drivers"); +MODULE_LICENSE("GPL"); diff --git a/drivers/media/cec/cec-priv.h b/drivers/media/cec/cec-priv.h new file mode 100644 index 000000000000..70767a7900f2 --- /dev/null +++ b/drivers/media/cec/cec-priv.h @@ -0,0 +1,56 @@ +/* + * cec-priv.h - HDMI Consumer Electronics Control internal header + * + * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. + * + * This program is free software; you may redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef _CEC_PRIV_H +#define _CEC_PRIV_H + +#include +#include + +#define dprintk(lvl, fmt, arg...) \ + do { \ + if (lvl <= cec_debug) \ + pr_info("cec-%s: " fmt, adap->name, ## arg); \ + } while (0) + +/* devnode to cec_adapter */ +#define to_cec_adapter(node) container_of(node, struct cec_adapter, devnode) + +/* cec-core.c */ +extern int cec_debug; +int cec_get_device(struct cec_devnode *devnode); +void cec_put_device(struct cec_devnode *devnode); + +/* cec-adap.c */ +int cec_monitor_all_cnt_inc(struct cec_adapter *adap); +void cec_monitor_all_cnt_dec(struct cec_adapter *adap); +int cec_adap_status(struct seq_file *file, void *priv); +int cec_thread_func(void *_adap); +void __cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr, bool block); +int __cec_s_log_addrs(struct cec_adapter *adap, + struct cec_log_addrs *log_addrs, bool block); +int cec_transmit_msg_fh(struct cec_adapter *adap, struct cec_msg *msg, + struct cec_fh *fh, bool block); +void cec_queue_event_fh(struct cec_fh *fh, + const struct cec_event *new_ev, u64 ts); + +/* cec-api.c */ +extern const struct file_operations cec_devnode_fops; + +#endif diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig index 2669b4bad910..b31fa6fae009 100644 --- a/drivers/media/i2c/Kconfig +++ b/drivers/media/i2c/Kconfig @@ -221,7 +221,7 @@ config VIDEO_ADV7604 config VIDEO_ADV7604_CEC bool "Enable Analog Devices ADV7604 CEC support" - depends on VIDEO_ADV7604 && MEDIA_CEC + depends on VIDEO_ADV7604 && MEDIA_CEC_SUPPORT ---help--- When selected the adv7604 will support the optional HDMI CEC feature. @@ -242,7 +242,7 @@ config VIDEO_ADV7842 config VIDEO_ADV7842_CEC bool "Enable Analog Devices ADV7842 CEC support" - depends on VIDEO_ADV7842 && MEDIA_CEC + depends on VIDEO_ADV7842 && MEDIA_CEC_SUPPORT ---help--- When selected the adv7842 will support the optional HDMI CEC feature. @@ -481,7 +481,7 @@ config VIDEO_ADV7511 config VIDEO_ADV7511_CEC bool "Enable Analog Devices ADV7511 CEC support" - depends on VIDEO_ADV7511 && MEDIA_CEC + depends on VIDEO_ADV7511 && MEDIA_CEC_SUPPORT ---help--- When selected the adv7511 will support the optional HDMI CEC feature. diff --git a/drivers/media/platform/vivid/Kconfig b/drivers/media/platform/vivid/Kconfig index 8e6918c5c87c..db0dd19d227a 100644 --- a/drivers/media/platform/vivid/Kconfig +++ b/drivers/media/platform/vivid/Kconfig @@ -25,7 +25,7 @@ config VIDEO_VIVID config VIDEO_VIVID_CEC bool "Enable CEC emulation support" - depends on VIDEO_VIVID && MEDIA_CEC + depends on VIDEO_VIVID && MEDIA_CEC_SUPPORT ---help--- When selected the vivid module will emulate the optional HDMI CEC feature. diff --git a/drivers/staging/media/Kconfig b/drivers/staging/media/Kconfig index 6620d96ee44d..0abe5ffb4934 100644 --- a/drivers/staging/media/Kconfig +++ b/drivers/staging/media/Kconfig @@ -21,8 +21,6 @@ if STAGING_MEDIA && MEDIA_SUPPORT # Please keep them in alphabetic order source "drivers/staging/media/bcm2048/Kconfig" -source "drivers/staging/media/cec/Kconfig" - source "drivers/staging/media/cxd2099/Kconfig" source "drivers/staging/media/davinci_vpfe/Kconfig" diff --git a/drivers/staging/media/Makefile b/drivers/staging/media/Makefile index 906257e94dda..246299eff80d 100644 --- a/drivers/staging/media/Makefile +++ b/drivers/staging/media/Makefile @@ -1,5 +1,4 @@ obj-$(CONFIG_I2C_BCM2048) += bcm2048/ -obj-$(CONFIG_MEDIA_CEC) += cec/ obj-$(CONFIG_VIDEO_SAMSUNG_S5P_CEC) += s5p-cec/ obj-$(CONFIG_DVB_CXD2099) += cxd2099/ obj-$(CONFIG_LIRC_STAGING) += lirc/ diff --git a/drivers/staging/media/cec/Kconfig b/drivers/staging/media/cec/Kconfig deleted file mode 100644 index 6e12d41b1f86..000000000000 --- a/drivers/staging/media/cec/Kconfig +++ /dev/null @@ -1,12 +0,0 @@ -config MEDIA_CEC - bool "CEC API (EXPERIMENTAL)" - depends on MEDIA_SUPPORT - select MEDIA_CEC_EDID - ---help--- - Enable the CEC API. - -config MEDIA_CEC_DEBUG - bool "CEC debugfs interface (EXPERIMENTAL)" - depends on MEDIA_CEC && DEBUG_FS - ---help--- - Turns on the DebugFS interface for CEC devices. diff --git a/drivers/staging/media/cec/Makefile b/drivers/staging/media/cec/Makefile deleted file mode 100644 index bd7f3c593468..000000000000 --- a/drivers/staging/media/cec/Makefile +++ /dev/null @@ -1,5 +0,0 @@ -cec-objs := cec-core.o cec-adap.o cec-api.o - -ifeq ($(CONFIG_MEDIA_CEC),y) - obj-$(CONFIG_MEDIA_SUPPORT) += cec.o -endif diff --git a/drivers/staging/media/cec/TODO b/drivers/staging/media/cec/TODO deleted file mode 100644 index 504d35c7ae95..000000000000 --- a/drivers/staging/media/cec/TODO +++ /dev/null @@ -1,9 +0,0 @@ -TODOs: - -- Once this is out of staging this should no longer be a separate - config option, instead it should be selected by drivers that want it. -- Revisit the IS_REACHABLE(RC_CORE): perhaps the RC_CORE support should - be enabled through a separate config option in drivers/media/Kconfig - or rc/Kconfig? - -Hans Verkuil diff --git a/drivers/staging/media/cec/cec-adap.c b/drivers/staging/media/cec/cec-adap.c deleted file mode 100644 index 054cd06e2247..000000000000 --- a/drivers/staging/media/cec/cec-adap.c +++ /dev/null @@ -1,1856 +0,0 @@ -/* - * cec-adap.c - HDMI Consumer Electronics Control framework - CEC adapter - * - * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. - * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "cec-priv.h" - -static int cec_report_features(struct cec_adapter *adap, unsigned int la_idx); -static int cec_report_phys_addr(struct cec_adapter *adap, unsigned int la_idx); - -/* - * 400 ms is the time it takes for one 16 byte message to be - * transferred and 5 is the maximum number of retries. Add - * another 100 ms as a margin. So if the transmit doesn't - * finish before that time something is really wrong and we - * have to time out. - * - * This is a sign that something it really wrong and a warning - * will be issued. - */ -#define CEC_XFER_TIMEOUT_MS (5 * 400 + 100) - -#define call_op(adap, op, arg...) \ - (adap->ops->op ? adap->ops->op(adap, ## arg) : 0) - -#define call_void_op(adap, op, arg...) \ - do { \ - if (adap->ops->op) \ - adap->ops->op(adap, ## arg); \ - } while (0) - -static int cec_log_addr2idx(const struct cec_adapter *adap, u8 log_addr) -{ - int i; - - for (i = 0; i < adap->log_addrs.num_log_addrs; i++) - if (adap->log_addrs.log_addr[i] == log_addr) - return i; - return -1; -} - -static unsigned int cec_log_addr2dev(const struct cec_adapter *adap, u8 log_addr) -{ - int i = cec_log_addr2idx(adap, log_addr); - - return adap->log_addrs.primary_device_type[i < 0 ? 0 : i]; -} - -/* - * Queue a new event for this filehandle. If ts == 0, then set it - * to the current time. - * - * The two events that are currently defined do not need to keep track - * of intermediate events, so no actual queue of events is needed, - * instead just store the latest state and the total number of lost - * messages. - * - * Should new events be added in the future that require intermediate - * results to be queued as well, then a proper queue data structure is - * required. But until then, just keep it simple. - */ -void cec_queue_event_fh(struct cec_fh *fh, - const struct cec_event *new_ev, u64 ts) -{ - struct cec_event *ev = &fh->events[new_ev->event - 1]; - - if (ts == 0) - ts = ktime_get_ns(); - - mutex_lock(&fh->lock); - if (new_ev->event == CEC_EVENT_LOST_MSGS && - fh->pending_events & (1 << new_ev->event)) { - /* - * If there is already a lost_msgs event, then just - * update the lost_msgs count. This effectively - * merges the old and new events into one. - */ - ev->lost_msgs.lost_msgs += new_ev->lost_msgs.lost_msgs; - goto unlock; - } - - /* - * Intermediate states are not interesting, so just - * overwrite any older event. - */ - *ev = *new_ev; - ev->ts = ts; - fh->pending_events |= 1 << new_ev->event; - -unlock: - mutex_unlock(&fh->lock); - wake_up_interruptible(&fh->wait); -} - -/* Queue a new event for all open filehandles. */ -static void cec_queue_event(struct cec_adapter *adap, - const struct cec_event *ev) -{ - u64 ts = ktime_get_ns(); - struct cec_fh *fh; - - mutex_lock(&adap->devnode.lock); - list_for_each_entry(fh, &adap->devnode.fhs, list) - cec_queue_event_fh(fh, ev, ts); - mutex_unlock(&adap->devnode.lock); -} - -/* - * Queue a new message for this filehandle. If there is no more room - * in the queue, then send the LOST_MSGS event instead. - */ -static void cec_queue_msg_fh(struct cec_fh *fh, const struct cec_msg *msg) -{ - static const struct cec_event ev_lost_msg = { - .ts = 0, - .event = CEC_EVENT_LOST_MSGS, - .flags = 0, - { - .lost_msgs.lost_msgs = 1, - }, - }; - struct cec_msg_entry *entry; - - mutex_lock(&fh->lock); - entry = kmalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) - goto lost_msgs; - - entry->msg = *msg; - /* Add new msg at the end of the queue */ - list_add_tail(&entry->list, &fh->msgs); - - /* - * if the queue now has more than CEC_MAX_MSG_RX_QUEUE_SZ - * messages, drop the oldest one and send a lost message event. - */ - if (fh->queued_msgs == CEC_MAX_MSG_RX_QUEUE_SZ) { - list_del(&entry->list); - goto lost_msgs; - } - fh->queued_msgs++; - mutex_unlock(&fh->lock); - wake_up_interruptible(&fh->wait); - return; - -lost_msgs: - mutex_unlock(&fh->lock); - cec_queue_event_fh(fh, &ev_lost_msg, 0); -} - -/* - * Queue the message for those filehandles that are in monitor mode. - * If valid_la is true (this message is for us or was sent by us), - * then pass it on to any monitoring filehandle. If this message - * isn't for us or from us, then only give it to filehandles that - * are in MONITOR_ALL mode. - * - * This can only happen if the CEC_CAP_MONITOR_ALL capability is - * set and the CEC adapter was placed in 'monitor all' mode. - */ -static void cec_queue_msg_monitor(struct cec_adapter *adap, - const struct cec_msg *msg, - bool valid_la) -{ - struct cec_fh *fh; - u32 monitor_mode = valid_la ? CEC_MODE_MONITOR : - CEC_MODE_MONITOR_ALL; - - mutex_lock(&adap->devnode.lock); - list_for_each_entry(fh, &adap->devnode.fhs, list) { - if (fh->mode_follower >= monitor_mode) - cec_queue_msg_fh(fh, msg); - } - mutex_unlock(&adap->devnode.lock); -} - -/* - * Queue the message for follower filehandles. - */ -static void cec_queue_msg_followers(struct cec_adapter *adap, - const struct cec_msg *msg) -{ - struct cec_fh *fh; - - mutex_lock(&adap->devnode.lock); - list_for_each_entry(fh, &adap->devnode.fhs, list) { - if (fh->mode_follower == CEC_MODE_FOLLOWER) - cec_queue_msg_fh(fh, msg); - } - mutex_unlock(&adap->devnode.lock); -} - -/* Notify userspace of an adapter state change. */ -static void cec_post_state_event(struct cec_adapter *adap) -{ - struct cec_event ev = { - .event = CEC_EVENT_STATE_CHANGE, - }; - - ev.state_change.phys_addr = adap->phys_addr; - ev.state_change.log_addr_mask = adap->log_addrs.log_addr_mask; - cec_queue_event(adap, &ev); -} - -/* - * A CEC transmit (and a possible wait for reply) completed. - * If this was in blocking mode, then complete it, otherwise - * queue the message for userspace to dequeue later. - * - * This function is called with adap->lock held. - */ -static void cec_data_completed(struct cec_data *data) -{ - /* - * Delete this transmit from the filehandle's xfer_list since - * we're done with it. - * - * Note that if the filehandle is closed before this transmit - * finished, then the release() function will set data->fh to NULL. - * Without that we would be referring to a closed filehandle. - */ - if (data->fh) - list_del(&data->xfer_list); - - if (data->blocking) { - /* - * Someone is blocking so mark the message as completed - * and call complete. - */ - data->completed = true; - complete(&data->c); - } else { - /* - * No blocking, so just queue the message if needed and - * free the memory. - */ - if (data->fh) - cec_queue_msg_fh(data->fh, &data->msg); - kfree(data); - } -} - -/* - * A pending CEC transmit needs to be cancelled, either because the CEC - * adapter is disabled or the transmit takes an impossibly long time to - * finish. - * - * This function is called with adap->lock held. - */ -static void cec_data_cancel(struct cec_data *data) -{ - /* - * It's either the current transmit, or it is a pending - * transmit. Take the appropriate action to clear it. - */ - if (data->adap->transmitting == data) { - data->adap->transmitting = NULL; - } else { - list_del_init(&data->list); - if (!(data->msg.tx_status & CEC_TX_STATUS_OK)) - data->adap->transmit_queue_sz--; - } - - /* Mark it as an error */ - data->msg.tx_ts = ktime_get_ns(); - data->msg.tx_status = CEC_TX_STATUS_ERROR | - CEC_TX_STATUS_MAX_RETRIES; - data->attempts = 0; - data->msg.tx_error_cnt = 1; - /* Queue transmitted message for monitoring purposes */ - cec_queue_msg_monitor(data->adap, &data->msg, 1); - - cec_data_completed(data); -} - -/* - * Main CEC state machine - * - * Wait until the thread should be stopped, or we are not transmitting and - * a new transmit message is queued up, in which case we start transmitting - * that message. When the adapter finished transmitting the message it will - * call cec_transmit_done(). - * - * If the adapter is disabled, then remove all queued messages instead. - * - * If the current transmit times out, then cancel that transmit. - */ -int cec_thread_func(void *_adap) -{ - struct cec_adapter *adap = _adap; - - for (;;) { - unsigned int signal_free_time; - struct cec_data *data; - bool timeout = false; - u8 attempts; - - if (adap->transmitting) { - int err; - - /* - * We are transmitting a message, so add a timeout - * to prevent the state machine to get stuck waiting - * for this message to finalize and add a check to - * see if the adapter is disabled in which case the - * transmit should be canceled. - */ - err = wait_event_interruptible_timeout(adap->kthread_waitq, - kthread_should_stop() || - (!adap->is_configured && !adap->is_configuring) || - (!adap->transmitting && - !list_empty(&adap->transmit_queue)), - msecs_to_jiffies(CEC_XFER_TIMEOUT_MS)); - timeout = err == 0; - } else { - /* Otherwise we just wait for something to happen. */ - wait_event_interruptible(adap->kthread_waitq, - kthread_should_stop() || - (!adap->transmitting && - !list_empty(&adap->transmit_queue))); - } - - mutex_lock(&adap->lock); - - if ((!adap->is_configured && !adap->is_configuring) || - kthread_should_stop()) { - /* - * If the adapter is disabled, or we're asked to stop, - * then cancel any pending transmits. - */ - while (!list_empty(&adap->transmit_queue)) { - data = list_first_entry(&adap->transmit_queue, - struct cec_data, list); - cec_data_cancel(data); - } - if (adap->transmitting) - cec_data_cancel(adap->transmitting); - - /* - * Cancel the pending timeout work. We have to unlock - * the mutex when flushing the work since - * cec_wait_timeout() will take it. This is OK since - * no new entries can be added to wait_queue as long - * as adap->transmitting is NULL, which it is due to - * the cec_data_cancel() above. - */ - while (!list_empty(&adap->wait_queue)) { - data = list_first_entry(&adap->wait_queue, - struct cec_data, list); - - if (!cancel_delayed_work(&data->work)) { - mutex_unlock(&adap->lock); - flush_scheduled_work(); - mutex_lock(&adap->lock); - } - cec_data_cancel(data); - } - goto unlock; - } - - if (adap->transmitting && timeout) { - /* - * If we timeout, then log that. This really shouldn't - * happen and is an indication of a faulty CEC adapter - * driver, or the CEC bus is in some weird state. - */ - dprintk(0, "message %*ph timed out!\n", - adap->transmitting->msg.len, - adap->transmitting->msg.msg); - /* Just give up on this. */ - cec_data_cancel(adap->transmitting); - goto unlock; - } - - /* - * If we are still transmitting, or there is nothing new to - * transmit, then just continue waiting. - */ - if (adap->transmitting || list_empty(&adap->transmit_queue)) - goto unlock; - - /* Get a new message to transmit */ - data = list_first_entry(&adap->transmit_queue, - struct cec_data, list); - list_del_init(&data->list); - adap->transmit_queue_sz--; - /* Make this the current transmitting message */ - adap->transmitting = data; - - /* - * Suggested number of attempts as per the CEC 2.0 spec: - * 4 attempts is the default, except for 'secondary poll - * messages', i.e. poll messages not sent during the adapter - * configuration phase when it allocates logical addresses. - */ - if (data->msg.len == 1 && adap->is_configured) - attempts = 2; - else - attempts = 4; - - /* Set the suggested signal free time */ - if (data->attempts) { - /* should be >= 3 data bit periods for a retry */ - signal_free_time = CEC_SIGNAL_FREE_TIME_RETRY; - } else if (data->new_initiator) { - /* should be >= 5 data bit periods for new initiator */ - signal_free_time = CEC_SIGNAL_FREE_TIME_NEW_INITIATOR; - } else { - /* - * should be >= 7 data bit periods for sending another - * frame immediately after another. - */ - signal_free_time = CEC_SIGNAL_FREE_TIME_NEXT_XFER; - } - if (data->attempts == 0) - data->attempts = attempts; - - /* Tell the adapter to transmit, cancel on error */ - if (adap->ops->adap_transmit(adap, data->attempts, - signal_free_time, &data->msg)) - cec_data_cancel(data); - -unlock: - mutex_unlock(&adap->lock); - - if (kthread_should_stop()) - break; - } - return 0; -} - -/* - * Called by the CEC adapter if a transmit finished. - */ -void cec_transmit_done(struct cec_adapter *adap, u8 status, u8 arb_lost_cnt, - u8 nack_cnt, u8 low_drive_cnt, u8 error_cnt) -{ - struct cec_data *data; - struct cec_msg *msg; - u64 ts = ktime_get_ns(); - - dprintk(2, "cec_transmit_done %02x\n", status); - mutex_lock(&adap->lock); - data = adap->transmitting; - if (!data) { - /* - * This can happen if a transmit was issued and the cable is - * unplugged while the transmit is ongoing. Ignore this - * transmit in that case. - */ - dprintk(1, "cec_transmit_done without an ongoing transmit!\n"); - goto unlock; - } - - msg = &data->msg; - - /* Drivers must fill in the status! */ - WARN_ON(status == 0); - msg->tx_ts = ts; - msg->tx_status |= status; - msg->tx_arb_lost_cnt += arb_lost_cnt; - msg->tx_nack_cnt += nack_cnt; - msg->tx_low_drive_cnt += low_drive_cnt; - msg->tx_error_cnt += error_cnt; - - /* Mark that we're done with this transmit */ - adap->transmitting = NULL; - - /* - * If there are still retry attempts left and there was an error and - * the hardware didn't signal that it retried itself (by setting - * CEC_TX_STATUS_MAX_RETRIES), then we will retry ourselves. - */ - if (data->attempts > 1 && - !(status & (CEC_TX_STATUS_MAX_RETRIES | CEC_TX_STATUS_OK))) { - /* Retry this message */ - data->attempts--; - /* Add the message in front of the transmit queue */ - list_add(&data->list, &adap->transmit_queue); - adap->transmit_queue_sz++; - goto wake_thread; - } - - data->attempts = 0; - - /* Always set CEC_TX_STATUS_MAX_RETRIES on error */ - if (!(status & CEC_TX_STATUS_OK)) - msg->tx_status |= CEC_TX_STATUS_MAX_RETRIES; - - /* Queue transmitted message for monitoring purposes */ - cec_queue_msg_monitor(adap, msg, 1); - - if ((status & CEC_TX_STATUS_OK) && adap->is_configured && - msg->timeout) { - /* - * Queue the message into the wait queue if we want to wait - * for a reply. - */ - list_add_tail(&data->list, &adap->wait_queue); - schedule_delayed_work(&data->work, - msecs_to_jiffies(msg->timeout)); - } else { - /* Otherwise we're done */ - cec_data_completed(data); - } - -wake_thread: - /* - * Wake up the main thread to see if another message is ready - * for transmitting or to retry the current message. - */ - wake_up_interruptible(&adap->kthread_waitq); -unlock: - mutex_unlock(&adap->lock); -} -EXPORT_SYMBOL_GPL(cec_transmit_done); - -/* - * Called when waiting for a reply times out. - */ -static void cec_wait_timeout(struct work_struct *work) -{ - struct cec_data *data = container_of(work, struct cec_data, work.work); - struct cec_adapter *adap = data->adap; - - mutex_lock(&adap->lock); - /* - * Sanity check in case the timeout and the arrival of the message - * happened at the same time. - */ - if (list_empty(&data->list)) - goto unlock; - - /* Mark the message as timed out */ - list_del_init(&data->list); - data->msg.rx_ts = ktime_get_ns(); - data->msg.rx_status = CEC_RX_STATUS_TIMEOUT; - cec_data_completed(data); -unlock: - mutex_unlock(&adap->lock); -} - -/* - * Transmit a message. The fh argument may be NULL if the transmit is not - * associated with a specific filehandle. - * - * This function is called with adap->lock held. - */ -int cec_transmit_msg_fh(struct cec_adapter *adap, struct cec_msg *msg, - struct cec_fh *fh, bool block) -{ - struct cec_data *data; - u8 last_initiator = 0xff; - unsigned int timeout; - int res = 0; - - msg->rx_ts = 0; - msg->tx_ts = 0; - msg->rx_status = 0; - msg->tx_status = 0; - msg->tx_arb_lost_cnt = 0; - msg->tx_nack_cnt = 0; - msg->tx_low_drive_cnt = 0; - msg->tx_error_cnt = 0; - msg->sequence = ++adap->sequence; - if (!msg->sequence) - msg->sequence = ++adap->sequence; - - if (msg->reply && msg->timeout == 0) { - /* Make sure the timeout isn't 0. */ - msg->timeout = 1000; - } - - /* Sanity checks */ - if (msg->len == 0 || msg->len > CEC_MAX_MSG_SIZE) { - dprintk(1, "cec_transmit_msg: invalid length %d\n", msg->len); - return -EINVAL; - } - if (msg->timeout && msg->len == 1) { - dprintk(1, "cec_transmit_msg: can't reply for poll msg\n"); - return -EINVAL; - } - memset(msg->msg + msg->len, 0, sizeof(msg->msg) - msg->len); - if (msg->len == 1) { - if (cec_msg_initiator(msg) != 0xf || - cec_msg_destination(msg) == 0xf) { - dprintk(1, "cec_transmit_msg: invalid poll message\n"); - return -EINVAL; - } - if (cec_has_log_addr(adap, cec_msg_destination(msg))) { - /* - * If the destination is a logical address our adapter - * has already claimed, then just NACK this. - * It depends on the hardware what it will do with a - * POLL to itself (some OK this), so it is just as - * easy to handle it here so the behavior will be - * consistent. - */ - msg->tx_ts = ktime_get_ns(); - msg->tx_status = CEC_TX_STATUS_NACK | - CEC_TX_STATUS_MAX_RETRIES; - msg->tx_nack_cnt = 1; - return 0; - } - } - if (msg->len > 1 && !cec_msg_is_broadcast(msg) && - cec_has_log_addr(adap, cec_msg_destination(msg))) { - dprintk(1, "cec_transmit_msg: destination is the adapter itself\n"); - return -EINVAL; - } - if (cec_msg_initiator(msg) != 0xf && - !cec_has_log_addr(adap, cec_msg_initiator(msg))) { - dprintk(1, "cec_transmit_msg: initiator has unknown logical address %d\n", - cec_msg_initiator(msg)); - return -EINVAL; - } - if (!adap->is_configured && !adap->is_configuring) - return -ENONET; - - if (adap->transmit_queue_sz >= CEC_MAX_MSG_TX_QUEUE_SZ) - return -EBUSY; - - data = kzalloc(sizeof(*data), GFP_KERNEL); - if (!data) - return -ENOMEM; - - if (msg->len > 1 && msg->msg[1] == CEC_MSG_CDC_MESSAGE) { - msg->msg[2] = adap->phys_addr >> 8; - msg->msg[3] = adap->phys_addr & 0xff; - } - - if (msg->timeout) - dprintk(2, "cec_transmit_msg: %*ph (wait for 0x%02x%s)\n", - msg->len, msg->msg, msg->reply, !block ? ", nb" : ""); - else - dprintk(2, "cec_transmit_msg: %*ph%s\n", - msg->len, msg->msg, !block ? " (nb)" : ""); - - data->msg = *msg; - data->fh = fh; - data->adap = adap; - data->blocking = block; - - /* - * Determine if this message follows a message from the same - * initiator. Needed to determine the free signal time later on. - */ - if (msg->len > 1) { - if (!(list_empty(&adap->transmit_queue))) { - const struct cec_data *last; - - last = list_last_entry(&adap->transmit_queue, - const struct cec_data, list); - last_initiator = cec_msg_initiator(&last->msg); - } else if (adap->transmitting) { - last_initiator = - cec_msg_initiator(&adap->transmitting->msg); - } - } - data->new_initiator = last_initiator != cec_msg_initiator(msg); - init_completion(&data->c); - INIT_DELAYED_WORK(&data->work, cec_wait_timeout); - - if (fh) - list_add_tail(&data->xfer_list, &fh->xfer_list); - list_add_tail(&data->list, &adap->transmit_queue); - adap->transmit_queue_sz++; - if (!adap->transmitting) - wake_up_interruptible(&adap->kthread_waitq); - - /* All done if we don't need to block waiting for completion */ - if (!block) - return 0; - - /* - * If we don't get a completion before this time something is really - * wrong and we time out. - */ - timeout = CEC_XFER_TIMEOUT_MS; - /* Add the requested timeout if we have to wait for a reply as well */ - if (msg->timeout) - timeout += msg->timeout; - - /* - * Release the lock and wait, retake the lock afterwards. - */ - mutex_unlock(&adap->lock); - res = wait_for_completion_killable_timeout(&data->c, - msecs_to_jiffies(timeout)); - mutex_lock(&adap->lock); - - if (data->completed) { - /* The transmit completed (possibly with an error) */ - *msg = data->msg; - kfree(data); - return 0; - } - /* - * The wait for completion timed out or was interrupted, so mark this - * as non-blocking and disconnect from the filehandle since it is - * still 'in flight'. When it finally completes it will just drop the - * result silently. - */ - data->blocking = false; - if (data->fh) - list_del(&data->xfer_list); - data->fh = NULL; - - if (res == 0) { /* timed out */ - /* Check if the reply or the transmit failed */ - if (msg->timeout && (msg->tx_status & CEC_TX_STATUS_OK)) - msg->rx_status = CEC_RX_STATUS_TIMEOUT; - else - msg->tx_status = CEC_TX_STATUS_MAX_RETRIES; - } - return res > 0 ? 0 : res; -} - -/* Helper function to be used by drivers and this framework. */ -int cec_transmit_msg(struct cec_adapter *adap, struct cec_msg *msg, - bool block) -{ - int ret; - - mutex_lock(&adap->lock); - ret = cec_transmit_msg_fh(adap, msg, NULL, block); - mutex_unlock(&adap->lock); - return ret; -} -EXPORT_SYMBOL_GPL(cec_transmit_msg); - -/* - * I don't like forward references but without this the low-level - * cec_received_msg() function would come after a bunch of high-level - * CEC protocol handling functions. That was very confusing. - */ -static int cec_receive_notify(struct cec_adapter *adap, struct cec_msg *msg, - bool is_reply); - -#define DIRECTED 0x80 -#define BCAST1_4 0x40 -#define BCAST2_0 0x20 /* broadcast only allowed for >= 2.0 */ -#define BCAST (BCAST1_4 | BCAST2_0) -#define BOTH (BCAST | DIRECTED) - -/* - * Specify minimum length and whether the message is directed, broadcast - * or both. Messages that do not match the criteria are ignored as per - * the CEC specification. - */ -static const u8 cec_msg_size[256] = { - [CEC_MSG_ACTIVE_SOURCE] = 4 | BCAST, - [CEC_MSG_IMAGE_VIEW_ON] = 2 | DIRECTED, - [CEC_MSG_TEXT_VIEW_ON] = 2 | DIRECTED, - [CEC_MSG_INACTIVE_SOURCE] = 4 | DIRECTED, - [CEC_MSG_REQUEST_ACTIVE_SOURCE] = 2 | BCAST, - [CEC_MSG_ROUTING_CHANGE] = 6 | BCAST, - [CEC_MSG_ROUTING_INFORMATION] = 4 | BCAST, - [CEC_MSG_SET_STREAM_PATH] = 4 | BCAST, - [CEC_MSG_STANDBY] = 2 | BOTH, - [CEC_MSG_RECORD_OFF] = 2 | DIRECTED, - [CEC_MSG_RECORD_ON] = 3 | DIRECTED, - [CEC_MSG_RECORD_STATUS] = 3 | DIRECTED, - [CEC_MSG_RECORD_TV_SCREEN] = 2 | DIRECTED, - [CEC_MSG_CLEAR_ANALOGUE_TIMER] = 13 | DIRECTED, - [CEC_MSG_CLEAR_DIGITAL_TIMER] = 16 | DIRECTED, - [CEC_MSG_CLEAR_EXT_TIMER] = 13 | DIRECTED, - [CEC_MSG_SET_ANALOGUE_TIMER] = 13 | DIRECTED, - [CEC_MSG_SET_DIGITAL_TIMER] = 16 | DIRECTED, - [CEC_MSG_SET_EXT_TIMER] = 13 | DIRECTED, - [CEC_MSG_SET_TIMER_PROGRAM_TITLE] = 2 | DIRECTED, - [CEC_MSG_TIMER_CLEARED_STATUS] = 3 | DIRECTED, - [CEC_MSG_TIMER_STATUS] = 3 | DIRECTED, - [CEC_MSG_CEC_VERSION] = 3 | DIRECTED, - [CEC_MSG_GET_CEC_VERSION] = 2 | DIRECTED, - [CEC_MSG_GIVE_PHYSICAL_ADDR] = 2 | DIRECTED, - [CEC_MSG_GET_MENU_LANGUAGE] = 2 | DIRECTED, - [CEC_MSG_REPORT_PHYSICAL_ADDR] = 5 | BCAST, - [CEC_MSG_SET_MENU_LANGUAGE] = 5 | BCAST, - [CEC_MSG_REPORT_FEATURES] = 6 | BCAST, - [CEC_MSG_GIVE_FEATURES] = 2 | DIRECTED, - [CEC_MSG_DECK_CONTROL] = 3 | DIRECTED, - [CEC_MSG_DECK_STATUS] = 3 | DIRECTED, - [CEC_MSG_GIVE_DECK_STATUS] = 3 | DIRECTED, - [CEC_MSG_PLAY] = 3 | DIRECTED, - [CEC_MSG_GIVE_TUNER_DEVICE_STATUS] = 3 | DIRECTED, - [CEC_MSG_SELECT_ANALOGUE_SERVICE] = 6 | DIRECTED, - [CEC_MSG_SELECT_DIGITAL_SERVICE] = 9 | DIRECTED, - [CEC_MSG_TUNER_DEVICE_STATUS] = 7 | DIRECTED, - [CEC_MSG_TUNER_STEP_DECREMENT] = 2 | DIRECTED, - [CEC_MSG_TUNER_STEP_INCREMENT] = 2 | DIRECTED, - [CEC_MSG_DEVICE_VENDOR_ID] = 5 | BCAST, - [CEC_MSG_GIVE_DEVICE_VENDOR_ID] = 2 | DIRECTED, - [CEC_MSG_VENDOR_COMMAND] = 2 | DIRECTED, - [CEC_MSG_VENDOR_COMMAND_WITH_ID] = 5 | BOTH, - [CEC_MSG_VENDOR_REMOTE_BUTTON_DOWN] = 2 | BOTH, - [CEC_MSG_VENDOR_REMOTE_BUTTON_UP] = 2 | BOTH, - [CEC_MSG_SET_OSD_STRING] = 3 | DIRECTED, - [CEC_MSG_GIVE_OSD_NAME] = 2 | DIRECTED, - [CEC_MSG_SET_OSD_NAME] = 2 | DIRECTED, - [CEC_MSG_MENU_REQUEST] = 3 | DIRECTED, - [CEC_MSG_MENU_STATUS] = 3 | DIRECTED, - [CEC_MSG_USER_CONTROL_PRESSED] = 3 | DIRECTED, - [CEC_MSG_USER_CONTROL_RELEASED] = 2 | DIRECTED, - [CEC_MSG_GIVE_DEVICE_POWER_STATUS] = 2 | DIRECTED, - [CEC_MSG_REPORT_POWER_STATUS] = 3 | DIRECTED | BCAST2_0, - [CEC_MSG_FEATURE_ABORT] = 4 | DIRECTED, - [CEC_MSG_ABORT] = 2 | DIRECTED, - [CEC_MSG_GIVE_AUDIO_STATUS] = 2 | DIRECTED, - [CEC_MSG_GIVE_SYSTEM_AUDIO_MODE_STATUS] = 2 | DIRECTED, - [CEC_MSG_REPORT_AUDIO_STATUS] = 3 | DIRECTED, - [CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR] = 2 | DIRECTED, - [CEC_MSG_REQUEST_SHORT_AUDIO_DESCRIPTOR] = 2 | DIRECTED, - [CEC_MSG_SET_SYSTEM_AUDIO_MODE] = 3 | BOTH, - [CEC_MSG_SYSTEM_AUDIO_MODE_REQUEST] = 2 | DIRECTED, - [CEC_MSG_SYSTEM_AUDIO_MODE_STATUS] = 3 | DIRECTED, - [CEC_MSG_SET_AUDIO_RATE] = 3 | DIRECTED, - [CEC_MSG_INITIATE_ARC] = 2 | DIRECTED, - [CEC_MSG_REPORT_ARC_INITIATED] = 2 | DIRECTED, - [CEC_MSG_REPORT_ARC_TERMINATED] = 2 | DIRECTED, - [CEC_MSG_REQUEST_ARC_INITIATION] = 2 | DIRECTED, - [CEC_MSG_REQUEST_ARC_TERMINATION] = 2 | DIRECTED, - [CEC_MSG_TERMINATE_ARC] = 2 | DIRECTED, - [CEC_MSG_REQUEST_CURRENT_LATENCY] = 4 | BCAST, - [CEC_MSG_REPORT_CURRENT_LATENCY] = 7 | BCAST, - [CEC_MSG_CDC_MESSAGE] = 2 | BCAST, -}; - -/* Called by the CEC adapter if a message is received */ -void cec_received_msg(struct cec_adapter *adap, struct cec_msg *msg) -{ - struct cec_data *data; - u8 msg_init = cec_msg_initiator(msg); - u8 msg_dest = cec_msg_destination(msg); - u8 cmd = msg->msg[1]; - bool is_reply = false; - bool valid_la = true; - u8 min_len = 0; - - if (WARN_ON(!msg->len || msg->len > CEC_MAX_MSG_SIZE)) - return; - - msg->rx_ts = ktime_get_ns(); - msg->rx_status = CEC_RX_STATUS_OK; - msg->sequence = msg->reply = msg->timeout = 0; - msg->tx_status = 0; - msg->tx_ts = 0; - msg->flags = 0; - memset(msg->msg + msg->len, 0, sizeof(msg->msg) - msg->len); - - mutex_lock(&adap->lock); - dprintk(2, "cec_received_msg: %*ph\n", msg->len, msg->msg); - - /* Check if this message was for us (directed or broadcast). */ - if (!cec_msg_is_broadcast(msg)) - valid_la = cec_has_log_addr(adap, msg_dest); - - /* - * Check if the length is not too short or if the message is a - * broadcast message where a directed message was expected or - * vice versa. If so, then the message has to be ignored (according - * to section CEC 7.3 and CEC 12.2). - */ - if (valid_la && msg->len > 1 && cec_msg_size[cmd]) { - u8 dir_fl = cec_msg_size[cmd] & BOTH; - - min_len = cec_msg_size[cmd] & 0x1f; - if (msg->len < min_len) - valid_la = false; - else if (!cec_msg_is_broadcast(msg) && !(dir_fl & DIRECTED)) - valid_la = false; - else if (cec_msg_is_broadcast(msg) && !(dir_fl & BCAST1_4)) - valid_la = false; - else if (cec_msg_is_broadcast(msg) && - adap->log_addrs.cec_version >= CEC_OP_CEC_VERSION_2_0 && - !(dir_fl & BCAST2_0)) - valid_la = false; - } - if (valid_la && min_len) { - /* These messages have special length requirements */ - switch (cmd) { - case CEC_MSG_TIMER_STATUS: - if (msg->msg[2] & 0x10) { - switch (msg->msg[2] & 0xf) { - case CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE: - case CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE: - if (msg->len < 5) - valid_la = false; - break; - } - } else if ((msg->msg[2] & 0xf) == CEC_OP_PROG_ERROR_DUPLICATE) { - if (msg->len < 5) - valid_la = false; - } - break; - case CEC_MSG_RECORD_ON: - switch (msg->msg[2]) { - case CEC_OP_RECORD_SRC_OWN: - break; - case CEC_OP_RECORD_SRC_DIGITAL: - if (msg->len < 10) - valid_la = false; - break; - case CEC_OP_RECORD_SRC_ANALOG: - if (msg->len < 7) - valid_la = false; - break; - case CEC_OP_RECORD_SRC_EXT_PLUG: - if (msg->len < 4) - valid_la = false; - break; - case CEC_OP_RECORD_SRC_EXT_PHYS_ADDR: - if (msg->len < 5) - valid_la = false; - break; - } - break; - } - } - - /* It's a valid message and not a poll or CDC message */ - if (valid_la && msg->len > 1 && cmd != CEC_MSG_CDC_MESSAGE) { - bool abort = cmd == CEC_MSG_FEATURE_ABORT; - - /* The aborted command is in msg[2] */ - if (abort) - cmd = msg->msg[2]; - - /* - * Walk over all transmitted messages that are waiting for a - * reply. - */ - list_for_each_entry(data, &adap->wait_queue, list) { - struct cec_msg *dst = &data->msg; - - /* - * The *only* CEC message that has two possible replies - * is CEC_MSG_INITIATE_ARC. - * In this case allow either of the two replies. - */ - if (!abort && dst->msg[1] == CEC_MSG_INITIATE_ARC && - (cmd == CEC_MSG_REPORT_ARC_INITIATED || - cmd == CEC_MSG_REPORT_ARC_TERMINATED) && - (dst->reply == CEC_MSG_REPORT_ARC_INITIATED || - dst->reply == CEC_MSG_REPORT_ARC_TERMINATED)) - dst->reply = cmd; - - /* Does the command match? */ - if ((abort && cmd != dst->msg[1]) || - (!abort && cmd != dst->reply)) - continue; - - /* Does the addressing match? */ - if (msg_init != cec_msg_destination(dst) && - !cec_msg_is_broadcast(dst)) - continue; - - /* We got a reply */ - memcpy(dst->msg, msg->msg, msg->len); - dst->len = msg->len; - dst->rx_ts = msg->rx_ts; - dst->rx_status = msg->rx_status; - if (abort) - dst->rx_status |= CEC_RX_STATUS_FEATURE_ABORT; - msg->flags = dst->flags; - /* Remove it from the wait_queue */ - list_del_init(&data->list); - - /* Cancel the pending timeout work */ - if (!cancel_delayed_work(&data->work)) { - mutex_unlock(&adap->lock); - flush_scheduled_work(); - mutex_lock(&adap->lock); - } - /* - * Mark this as a reply, provided someone is still - * waiting for the answer. - */ - if (data->fh) - is_reply = true; - cec_data_completed(data); - break; - } - } - mutex_unlock(&adap->lock); - - /* Pass the message on to any monitoring filehandles */ - cec_queue_msg_monitor(adap, msg, valid_la); - - /* We're done if it is not for us or a poll message */ - if (!valid_la || msg->len <= 1) - return; - - if (adap->log_addrs.log_addr_mask == 0) - return; - - /* - * Process the message on the protocol level. If is_reply is true, - * then cec_receive_notify() won't pass on the reply to the listener(s) - * since that was already done by cec_data_completed() above. - */ - cec_receive_notify(adap, msg, is_reply); -} -EXPORT_SYMBOL_GPL(cec_received_msg); - -/* Logical Address Handling */ - -/* - * Attempt to claim a specific logical address. - * - * This function is called with adap->lock held. - */ -static int cec_config_log_addr(struct cec_adapter *adap, - unsigned int idx, - unsigned int log_addr) -{ - struct cec_log_addrs *las = &adap->log_addrs; - struct cec_msg msg = { }; - int err; - - if (cec_has_log_addr(adap, log_addr)) - return 0; - - /* Send poll message */ - msg.len = 1; - msg.msg[0] = 0xf0 | log_addr; - err = cec_transmit_msg_fh(adap, &msg, NULL, true); - - /* - * While trying to poll the physical address was reset - * and the adapter was unconfigured, so bail out. - */ - if (!adap->is_configuring) - return -EINTR; - - if (err) - return err; - - if (msg.tx_status & CEC_TX_STATUS_OK) - return 0; - - /* - * Message not acknowledged, so this logical - * address is free to use. - */ - err = adap->ops->adap_log_addr(adap, log_addr); - if (err) - return err; - - las->log_addr[idx] = log_addr; - las->log_addr_mask |= 1 << log_addr; - adap->phys_addrs[log_addr] = adap->phys_addr; - - dprintk(2, "claimed addr %d (%d)\n", log_addr, - las->primary_device_type[idx]); - return 1; -} - -/* - * Unconfigure the adapter: clear all logical addresses and send - * the state changed event. - * - * This function is called with adap->lock held. - */ -static void cec_adap_unconfigure(struct cec_adapter *adap) -{ - WARN_ON(adap->ops->adap_log_addr(adap, CEC_LOG_ADDR_INVALID)); - adap->log_addrs.log_addr_mask = 0; - adap->is_configuring = false; - adap->is_configured = false; - memset(adap->phys_addrs, 0xff, sizeof(adap->phys_addrs)); - wake_up_interruptible(&adap->kthread_waitq); - cec_post_state_event(adap); -} - -/* - * Attempt to claim the required logical addresses. - */ -static int cec_config_thread_func(void *arg) -{ - /* The various LAs for each type of device */ - static const u8 tv_log_addrs[] = { - CEC_LOG_ADDR_TV, CEC_LOG_ADDR_SPECIFIC, - CEC_LOG_ADDR_INVALID - }; - static const u8 record_log_addrs[] = { - CEC_LOG_ADDR_RECORD_1, CEC_LOG_ADDR_RECORD_2, - CEC_LOG_ADDR_RECORD_3, - CEC_LOG_ADDR_BACKUP_1, CEC_LOG_ADDR_BACKUP_2, - CEC_LOG_ADDR_INVALID - }; - static const u8 tuner_log_addrs[] = { - CEC_LOG_ADDR_TUNER_1, CEC_LOG_ADDR_TUNER_2, - CEC_LOG_ADDR_TUNER_3, CEC_LOG_ADDR_TUNER_4, - CEC_LOG_ADDR_BACKUP_1, CEC_LOG_ADDR_BACKUP_2, - CEC_LOG_ADDR_INVALID - }; - static const u8 playback_log_addrs[] = { - CEC_LOG_ADDR_PLAYBACK_1, CEC_LOG_ADDR_PLAYBACK_2, - CEC_LOG_ADDR_PLAYBACK_3, - CEC_LOG_ADDR_BACKUP_1, CEC_LOG_ADDR_BACKUP_2, - CEC_LOG_ADDR_INVALID - }; - static const u8 audiosystem_log_addrs[] = { - CEC_LOG_ADDR_AUDIOSYSTEM, - CEC_LOG_ADDR_INVALID - }; - static const u8 specific_use_log_addrs[] = { - CEC_LOG_ADDR_SPECIFIC, - CEC_LOG_ADDR_BACKUP_1, CEC_LOG_ADDR_BACKUP_2, - CEC_LOG_ADDR_INVALID - }; - static const u8 *type2addrs[6] = { - [CEC_LOG_ADDR_TYPE_TV] = tv_log_addrs, - [CEC_LOG_ADDR_TYPE_RECORD] = record_log_addrs, - [CEC_LOG_ADDR_TYPE_TUNER] = tuner_log_addrs, - [CEC_LOG_ADDR_TYPE_PLAYBACK] = playback_log_addrs, - [CEC_LOG_ADDR_TYPE_AUDIOSYSTEM] = audiosystem_log_addrs, - [CEC_LOG_ADDR_TYPE_SPECIFIC] = specific_use_log_addrs, - }; - static const u16 type2mask[] = { - [CEC_LOG_ADDR_TYPE_TV] = CEC_LOG_ADDR_MASK_TV, - [CEC_LOG_ADDR_TYPE_RECORD] = CEC_LOG_ADDR_MASK_RECORD, - [CEC_LOG_ADDR_TYPE_TUNER] = CEC_LOG_ADDR_MASK_TUNER, - [CEC_LOG_ADDR_TYPE_PLAYBACK] = CEC_LOG_ADDR_MASK_PLAYBACK, - [CEC_LOG_ADDR_TYPE_AUDIOSYSTEM] = CEC_LOG_ADDR_MASK_AUDIOSYSTEM, - [CEC_LOG_ADDR_TYPE_SPECIFIC] = CEC_LOG_ADDR_MASK_SPECIFIC, - }; - struct cec_adapter *adap = arg; - struct cec_log_addrs *las = &adap->log_addrs; - int err; - int i, j; - - mutex_lock(&adap->lock); - dprintk(1, "physical address: %x.%x.%x.%x, claim %d logical addresses\n", - cec_phys_addr_exp(adap->phys_addr), las->num_log_addrs); - las->log_addr_mask = 0; - - if (las->log_addr_type[0] == CEC_LOG_ADDR_TYPE_UNREGISTERED) - goto configured; - - for (i = 0; i < las->num_log_addrs; i++) { - unsigned int type = las->log_addr_type[i]; - const u8 *la_list; - u8 last_la; - - /* - * The TV functionality can only map to physical address 0. - * For any other address, try the Specific functionality - * instead as per the spec. - */ - if (adap->phys_addr && type == CEC_LOG_ADDR_TYPE_TV) - type = CEC_LOG_ADDR_TYPE_SPECIFIC; - - la_list = type2addrs[type]; - last_la = las->log_addr[i]; - las->log_addr[i] = CEC_LOG_ADDR_INVALID; - if (last_la == CEC_LOG_ADDR_INVALID || - last_la == CEC_LOG_ADDR_UNREGISTERED || - !(last_la & type2mask[type])) - last_la = la_list[0]; - - err = cec_config_log_addr(adap, i, last_la); - if (err > 0) /* Reused last LA */ - continue; - - if (err < 0) - goto unconfigure; - - for (j = 0; la_list[j] != CEC_LOG_ADDR_INVALID; j++) { - /* Tried this one already, skip it */ - if (la_list[j] == last_la) - continue; - /* The backup addresses are CEC 2.0 specific */ - if ((la_list[j] == CEC_LOG_ADDR_BACKUP_1 || - la_list[j] == CEC_LOG_ADDR_BACKUP_2) && - las->cec_version < CEC_OP_CEC_VERSION_2_0) - continue; - - err = cec_config_log_addr(adap, i, la_list[j]); - if (err == 0) /* LA is in use */ - continue; - if (err < 0) - goto unconfigure; - /* Done, claimed an LA */ - break; - } - - if (la_list[j] == CEC_LOG_ADDR_INVALID) - dprintk(1, "could not claim LA %d\n", i); - } - - if (adap->log_addrs.log_addr_mask == 0 && - !(las->flags & CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK)) - goto unconfigure; - -configured: - if (adap->log_addrs.log_addr_mask == 0) { - /* Fall back to unregistered */ - las->log_addr[0] = CEC_LOG_ADDR_UNREGISTERED; - las->log_addr_mask = 1 << las->log_addr[0]; - for (i = 1; i < las->num_log_addrs; i++) - las->log_addr[i] = CEC_LOG_ADDR_INVALID; - } - adap->is_configured = true; - adap->is_configuring = false; - cec_post_state_event(adap); - mutex_unlock(&adap->lock); - - for (i = 0; i < las->num_log_addrs; i++) { - if (las->log_addr[i] == CEC_LOG_ADDR_INVALID || - (las->flags & CEC_LOG_ADDRS_FL_CDC_ONLY)) - continue; - - /* - * Report Features must come first according - * to CEC 2.0 - */ - if (las->log_addr[i] != CEC_LOG_ADDR_UNREGISTERED) - cec_report_features(adap, i); - cec_report_phys_addr(adap, i); - } - for (i = las->num_log_addrs; i < CEC_MAX_LOG_ADDRS; i++) - las->log_addr[i] = CEC_LOG_ADDR_INVALID; - mutex_lock(&adap->lock); - adap->kthread_config = NULL; - mutex_unlock(&adap->lock); - complete(&adap->config_completion); - return 0; - -unconfigure: - for (i = 0; i < las->num_log_addrs; i++) - las->log_addr[i] = CEC_LOG_ADDR_INVALID; - cec_adap_unconfigure(adap); - adap->kthread_config = NULL; - mutex_unlock(&adap->lock); - complete(&adap->config_completion); - return 0; -} - -/* - * Called from either __cec_s_phys_addr or __cec_s_log_addrs to claim the - * logical addresses. - * - * This function is called with adap->lock held. - */ -static void cec_claim_log_addrs(struct cec_adapter *adap, bool block) -{ - if (WARN_ON(adap->is_configuring || adap->is_configured)) - return; - - init_completion(&adap->config_completion); - - /* Ready to kick off the thread */ - adap->is_configuring = true; - adap->kthread_config = kthread_run(cec_config_thread_func, adap, - "ceccfg-%s", adap->name); - if (IS_ERR(adap->kthread_config)) { - adap->kthread_config = NULL; - } else if (block) { - mutex_unlock(&adap->lock); - wait_for_completion(&adap->config_completion); - mutex_lock(&adap->lock); - } -} - -/* Set a new physical address and send an event notifying userspace of this. - * - * This function is called with adap->lock held. - */ -void __cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr, bool block) -{ - if (phys_addr == adap->phys_addr || adap->devnode.unregistered) - return; - - if (phys_addr == CEC_PHYS_ADDR_INVALID || - adap->phys_addr != CEC_PHYS_ADDR_INVALID) { - adap->phys_addr = CEC_PHYS_ADDR_INVALID; - cec_post_state_event(adap); - cec_adap_unconfigure(adap); - /* Disabling monitor all mode should always succeed */ - if (adap->monitor_all_cnt) - WARN_ON(call_op(adap, adap_monitor_all_enable, false)); - WARN_ON(adap->ops->adap_enable(adap, false)); - if (phys_addr == CEC_PHYS_ADDR_INVALID) - return; - } - - if (adap->ops->adap_enable(adap, true)) - return; - - if (adap->monitor_all_cnt && - call_op(adap, adap_monitor_all_enable, true)) { - WARN_ON(adap->ops->adap_enable(adap, false)); - return; - } - adap->phys_addr = phys_addr; - cec_post_state_event(adap); - if (adap->log_addrs.num_log_addrs) - cec_claim_log_addrs(adap, block); -} - -void cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr, bool block) -{ - if (IS_ERR_OR_NULL(adap)) - return; - - mutex_lock(&adap->lock); - __cec_s_phys_addr(adap, phys_addr, block); - mutex_unlock(&adap->lock); -} -EXPORT_SYMBOL_GPL(cec_s_phys_addr); - -/* - * Called from either the ioctl or a driver to set the logical addresses. - * - * This function is called with adap->lock held. - */ -int __cec_s_log_addrs(struct cec_adapter *adap, - struct cec_log_addrs *log_addrs, bool block) -{ - u16 type_mask = 0; - int i; - - if (adap->devnode.unregistered) - return -ENODEV; - - if (!log_addrs || log_addrs->num_log_addrs == 0) { - adap->log_addrs.num_log_addrs = 0; - cec_adap_unconfigure(adap); - return 0; - } - - if (log_addrs->flags & CEC_LOG_ADDRS_FL_CDC_ONLY) { - /* - * Sanitize log_addrs fields if a CDC-Only device is - * requested. - */ - log_addrs->num_log_addrs = 1; - log_addrs->osd_name[0] = '\0'; - log_addrs->vendor_id = CEC_VENDOR_ID_NONE; - log_addrs->log_addr_type[0] = CEC_LOG_ADDR_TYPE_UNREGISTERED; - /* - * This is just an internal convention since a CDC-Only device - * doesn't have to be a switch. But switches already use - * unregistered, so it makes some kind of sense to pick this - * as the primary device. Since a CDC-Only device never sends - * any 'normal' CEC messages this primary device type is never - * sent over the CEC bus. - */ - log_addrs->primary_device_type[0] = CEC_OP_PRIM_DEVTYPE_SWITCH; - log_addrs->all_device_types[0] = 0; - log_addrs->features[0][0] = 0; - log_addrs->features[0][1] = 0; - } - - /* Ensure the osd name is 0-terminated */ - log_addrs->osd_name[sizeof(log_addrs->osd_name) - 1] = '\0'; - - /* Sanity checks */ - if (log_addrs->num_log_addrs > adap->available_log_addrs) { - dprintk(1, "num_log_addrs > %d\n", adap->available_log_addrs); - return -EINVAL; - } - - /* - * Vendor ID is a 24 bit number, so check if the value is - * within the correct range. - */ - if (log_addrs->vendor_id != CEC_VENDOR_ID_NONE && - (log_addrs->vendor_id & 0xff000000) != 0) - return -EINVAL; - - if (log_addrs->cec_version != CEC_OP_CEC_VERSION_1_4 && - log_addrs->cec_version != CEC_OP_CEC_VERSION_2_0) - return -EINVAL; - - if (log_addrs->num_log_addrs > 1) - for (i = 0; i < log_addrs->num_log_addrs; i++) - if (log_addrs->log_addr_type[i] == - CEC_LOG_ADDR_TYPE_UNREGISTERED) { - dprintk(1, "num_log_addrs > 1 can't be combined with unregistered LA\n"); - return -EINVAL; - } - - for (i = 0; i < log_addrs->num_log_addrs; i++) { - const u8 feature_sz = ARRAY_SIZE(log_addrs->features[0]); - u8 *features = log_addrs->features[i]; - bool op_is_dev_features = false; - - log_addrs->log_addr[i] = CEC_LOG_ADDR_INVALID; - if (type_mask & (1 << log_addrs->log_addr_type[i])) { - dprintk(1, "duplicate logical address type\n"); - return -EINVAL; - } - type_mask |= 1 << log_addrs->log_addr_type[i]; - if ((type_mask & (1 << CEC_LOG_ADDR_TYPE_RECORD)) && - (type_mask & (1 << CEC_LOG_ADDR_TYPE_PLAYBACK))) { - /* Record already contains the playback functionality */ - dprintk(1, "invalid record + playback combination\n"); - return -EINVAL; - } - if (log_addrs->primary_device_type[i] > - CEC_OP_PRIM_DEVTYPE_PROCESSOR) { - dprintk(1, "unknown primary device type\n"); - return -EINVAL; - } - if (log_addrs->primary_device_type[i] == 2) { - dprintk(1, "invalid primary device type\n"); - return -EINVAL; - } - if (log_addrs->log_addr_type[i] > CEC_LOG_ADDR_TYPE_UNREGISTERED) { - dprintk(1, "unknown logical address type\n"); - return -EINVAL; - } - for (i = 0; i < feature_sz; i++) { - if ((features[i] & 0x80) == 0) { - if (op_is_dev_features) - break; - op_is_dev_features = true; - } - } - if (!op_is_dev_features || i == feature_sz) { - dprintk(1, "malformed features\n"); - return -EINVAL; - } - /* Zero unused part of the feature array */ - memset(features + i + 1, 0, feature_sz - i - 1); - } - - if (log_addrs->cec_version >= CEC_OP_CEC_VERSION_2_0) { - if (log_addrs->num_log_addrs > 2) { - dprintk(1, "CEC 2.0 allows no more than 2 logical addresses\n"); - return -EINVAL; - } - if (log_addrs->num_log_addrs == 2) { - if (!(type_mask & ((1 << CEC_LOG_ADDR_TYPE_AUDIOSYSTEM) | - (1 << CEC_LOG_ADDR_TYPE_TV)))) { - dprintk(1, "Two LAs is only allowed for audiosystem and TV\n"); - return -EINVAL; - } - if (!(type_mask & ((1 << CEC_LOG_ADDR_TYPE_PLAYBACK) | - (1 << CEC_LOG_ADDR_TYPE_RECORD)))) { - dprintk(1, "An audiosystem/TV can only be combined with record or playback\n"); - return -EINVAL; - } - } - } - - /* Zero unused LAs */ - for (i = log_addrs->num_log_addrs; i < CEC_MAX_LOG_ADDRS; i++) { - log_addrs->primary_device_type[i] = 0; - log_addrs->log_addr_type[i] = 0; - log_addrs->all_device_types[i] = 0; - memset(log_addrs->features[i], 0, - sizeof(log_addrs->features[i])); - } - - log_addrs->log_addr_mask = adap->log_addrs.log_addr_mask; - adap->log_addrs = *log_addrs; - if (adap->phys_addr != CEC_PHYS_ADDR_INVALID) - cec_claim_log_addrs(adap, block); - return 0; -} - -int cec_s_log_addrs(struct cec_adapter *adap, - struct cec_log_addrs *log_addrs, bool block) -{ - int err; - - mutex_lock(&adap->lock); - err = __cec_s_log_addrs(adap, log_addrs, block); - mutex_unlock(&adap->lock); - return err; -} -EXPORT_SYMBOL_GPL(cec_s_log_addrs); - -/* High-level core CEC message handling */ - -/* Transmit the Report Features message */ -static int cec_report_features(struct cec_adapter *adap, unsigned int la_idx) -{ - struct cec_msg msg = { }; - const struct cec_log_addrs *las = &adap->log_addrs; - const u8 *features = las->features[la_idx]; - bool op_is_dev_features = false; - unsigned int idx; - - /* This is 2.0 and up only */ - if (adap->log_addrs.cec_version < CEC_OP_CEC_VERSION_2_0) - return 0; - - /* Report Features */ - msg.msg[0] = (las->log_addr[la_idx] << 4) | 0x0f; - msg.len = 4; - msg.msg[1] = CEC_MSG_REPORT_FEATURES; - msg.msg[2] = adap->log_addrs.cec_version; - msg.msg[3] = las->all_device_types[la_idx]; - - /* Write RC Profiles first, then Device Features */ - for (idx = 0; idx < ARRAY_SIZE(las->features[0]); idx++) { - msg.msg[msg.len++] = features[idx]; - if ((features[idx] & CEC_OP_FEAT_EXT) == 0) { - if (op_is_dev_features) - break; - op_is_dev_features = true; - } - } - return cec_transmit_msg(adap, &msg, false); -} - -/* Transmit the Report Physical Address message */ -static int cec_report_phys_addr(struct cec_adapter *adap, unsigned int la_idx) -{ - const struct cec_log_addrs *las = &adap->log_addrs; - struct cec_msg msg = { }; - - /* Report Physical Address */ - msg.msg[0] = (las->log_addr[la_idx] << 4) | 0x0f; - cec_msg_report_physical_addr(&msg, adap->phys_addr, - las->primary_device_type[la_idx]); - dprintk(2, "config: la %d pa %x.%x.%x.%x\n", - las->log_addr[la_idx], - cec_phys_addr_exp(adap->phys_addr)); - return cec_transmit_msg(adap, &msg, false); -} - -/* Transmit the Feature Abort message */ -static int cec_feature_abort_reason(struct cec_adapter *adap, - struct cec_msg *msg, u8 reason) -{ - struct cec_msg tx_msg = { }; - - /* - * Don't reply with CEC_MSG_FEATURE_ABORT to a CEC_MSG_FEATURE_ABORT - * message! - */ - if (msg->msg[1] == CEC_MSG_FEATURE_ABORT) - return 0; - cec_msg_set_reply_to(&tx_msg, msg); - cec_msg_feature_abort(&tx_msg, msg->msg[1], reason); - return cec_transmit_msg(adap, &tx_msg, false); -} - -static int cec_feature_abort(struct cec_adapter *adap, struct cec_msg *msg) -{ - return cec_feature_abort_reason(adap, msg, - CEC_OP_ABORT_UNRECOGNIZED_OP); -} - -static int cec_feature_refused(struct cec_adapter *adap, struct cec_msg *msg) -{ - return cec_feature_abort_reason(adap, msg, - CEC_OP_ABORT_REFUSED); -} - -/* - * Called when a CEC message is received. This function will do any - * necessary core processing. The is_reply bool is true if this message - * is a reply to an earlier transmit. - * - * The message is either a broadcast message or a valid directed message. - */ -static int cec_receive_notify(struct cec_adapter *adap, struct cec_msg *msg, - bool is_reply) -{ - bool is_broadcast = cec_msg_is_broadcast(msg); - u8 dest_laddr = cec_msg_destination(msg); - u8 init_laddr = cec_msg_initiator(msg); - u8 devtype = cec_log_addr2dev(adap, dest_laddr); - int la_idx = cec_log_addr2idx(adap, dest_laddr); - bool from_unregistered = init_laddr == 0xf; - struct cec_msg tx_cec_msg = { }; - - dprintk(1, "cec_receive_notify: %*ph\n", msg->len, msg->msg); - - /* If this is a CDC-Only device, then ignore any non-CDC messages */ - if (cec_is_cdc_only(&adap->log_addrs) && - msg->msg[1] != CEC_MSG_CDC_MESSAGE) - return 0; - - if (adap->ops->received) { - /* Allow drivers to process the message first */ - if (adap->ops->received(adap, msg) != -ENOMSG) - return 0; - } - - /* - * REPORT_PHYSICAL_ADDR, CEC_MSG_USER_CONTROL_PRESSED and - * CEC_MSG_USER_CONTROL_RELEASED messages always have to be - * handled by the CEC core, even if the passthrough mode is on. - * The others are just ignored if passthrough mode is on. - */ - switch (msg->msg[1]) { - case CEC_MSG_GET_CEC_VERSION: - case CEC_MSG_GIVE_DEVICE_VENDOR_ID: - case CEC_MSG_ABORT: - case CEC_MSG_GIVE_DEVICE_POWER_STATUS: - case CEC_MSG_GIVE_PHYSICAL_ADDR: - case CEC_MSG_GIVE_OSD_NAME: - case CEC_MSG_GIVE_FEATURES: - /* - * Skip processing these messages if the passthrough mode - * is on. - */ - if (adap->passthrough) - goto skip_processing; - /* Ignore if addressing is wrong */ - if (is_broadcast || from_unregistered) - return 0; - break; - - case CEC_MSG_USER_CONTROL_PRESSED: - case CEC_MSG_USER_CONTROL_RELEASED: - /* Wrong addressing mode: don't process */ - if (is_broadcast || from_unregistered) - goto skip_processing; - break; - - case CEC_MSG_REPORT_PHYSICAL_ADDR: - /* - * This message is always processed, regardless of the - * passthrough setting. - * - * Exception: don't process if wrong addressing mode. - */ - if (!is_broadcast) - goto skip_processing; - break; - - default: - break; - } - - cec_msg_set_reply_to(&tx_cec_msg, msg); - - switch (msg->msg[1]) { - /* The following messages are processed but still passed through */ - case CEC_MSG_REPORT_PHYSICAL_ADDR: { - u16 pa = (msg->msg[2] << 8) | msg->msg[3]; - - if (!from_unregistered) - adap->phys_addrs[init_laddr] = pa; - dprintk(1, "Reported physical address %x.%x.%x.%x for logical address %d\n", - cec_phys_addr_exp(pa), init_laddr); - break; - } - - case CEC_MSG_USER_CONTROL_PRESSED: - if (!(adap->capabilities & CEC_CAP_RC) || - !(adap->log_addrs.flags & CEC_LOG_ADDRS_FL_ALLOW_RC_PASSTHRU)) - break; - -#if IS_REACHABLE(CONFIG_RC_CORE) - switch (msg->msg[2]) { - /* - * Play function, this message can have variable length - * depending on the specific play function that is used. - */ - case 0x60: - if (msg->len == 2) - rc_keydown(adap->rc, RC_TYPE_CEC, - msg->msg[2], 0); - else - rc_keydown(adap->rc, RC_TYPE_CEC, - msg->msg[2] << 8 | msg->msg[3], 0); - break; - /* - * Other function messages that are not handled. - * Currently the RC framework does not allow to supply an - * additional parameter to a keypress. These "keys" contain - * other information such as channel number, an input number - * etc. - * For the time being these messages are not processed by the - * framework and are simply forwarded to the user space. - */ - case 0x56: case 0x57: - case 0x67: case 0x68: case 0x69: case 0x6a: - break; - default: - rc_keydown(adap->rc, RC_TYPE_CEC, msg->msg[2], 0); - break; - } -#endif - break; - - case CEC_MSG_USER_CONTROL_RELEASED: - if (!(adap->capabilities & CEC_CAP_RC) || - !(adap->log_addrs.flags & CEC_LOG_ADDRS_FL_ALLOW_RC_PASSTHRU)) - break; -#if IS_REACHABLE(CONFIG_RC_CORE) - rc_keyup(adap->rc); -#endif - break; - - /* - * The remaining messages are only processed if the passthrough mode - * is off. - */ - case CEC_MSG_GET_CEC_VERSION: - cec_msg_cec_version(&tx_cec_msg, adap->log_addrs.cec_version); - return cec_transmit_msg(adap, &tx_cec_msg, false); - - case CEC_MSG_GIVE_PHYSICAL_ADDR: - /* Do nothing for CEC switches using addr 15 */ - if (devtype == CEC_OP_PRIM_DEVTYPE_SWITCH && dest_laddr == 15) - return 0; - cec_msg_report_physical_addr(&tx_cec_msg, adap->phys_addr, devtype); - return cec_transmit_msg(adap, &tx_cec_msg, false); - - case CEC_MSG_GIVE_DEVICE_VENDOR_ID: - if (adap->log_addrs.vendor_id == CEC_VENDOR_ID_NONE) - return cec_feature_abort(adap, msg); - cec_msg_device_vendor_id(&tx_cec_msg, adap->log_addrs.vendor_id); - return cec_transmit_msg(adap, &tx_cec_msg, false); - - case CEC_MSG_ABORT: - /* Do nothing for CEC switches */ - if (devtype == CEC_OP_PRIM_DEVTYPE_SWITCH) - return 0; - return cec_feature_refused(adap, msg); - - case CEC_MSG_GIVE_OSD_NAME: { - if (adap->log_addrs.osd_name[0] == 0) - return cec_feature_abort(adap, msg); - cec_msg_set_osd_name(&tx_cec_msg, adap->log_addrs.osd_name); - return cec_transmit_msg(adap, &tx_cec_msg, false); - } - - case CEC_MSG_GIVE_FEATURES: - if (adap->log_addrs.cec_version >= CEC_OP_CEC_VERSION_2_0) - return cec_report_features(adap, la_idx); - return 0; - - default: - /* - * Unprocessed messages are aborted if userspace isn't doing - * any processing either. - */ - if (!is_broadcast && !is_reply && !adap->follower_cnt && - !adap->cec_follower && msg->msg[1] != CEC_MSG_FEATURE_ABORT) - return cec_feature_abort(adap, msg); - break; - } - -skip_processing: - /* If this was a reply, then we're done, unless otherwise specified */ - if (is_reply && !(msg->flags & CEC_MSG_FL_REPLY_TO_FOLLOWERS)) - return 0; - - /* - * Send to the exclusive follower if there is one, otherwise send - * to all followers. - */ - if (adap->cec_follower) - cec_queue_msg_fh(adap->cec_follower, msg); - else - cec_queue_msg_followers(adap, msg); - return 0; -} - -/* - * Helper functions to keep track of the 'monitor all' use count. - * - * These functions are called with adap->lock held. - */ -int cec_monitor_all_cnt_inc(struct cec_adapter *adap) -{ - int ret = 0; - - if (adap->monitor_all_cnt == 0) - ret = call_op(adap, adap_monitor_all_enable, 1); - if (ret == 0) - adap->monitor_all_cnt++; - return ret; -} - -void cec_monitor_all_cnt_dec(struct cec_adapter *adap) -{ - adap->monitor_all_cnt--; - if (adap->monitor_all_cnt == 0) - WARN_ON(call_op(adap, adap_monitor_all_enable, 0)); -} - -#ifdef CONFIG_MEDIA_CEC_DEBUG -/* - * Log the current state of the CEC adapter. - * Very useful for debugging. - */ -int cec_adap_status(struct seq_file *file, void *priv) -{ - struct cec_adapter *adap = dev_get_drvdata(file->private); - struct cec_data *data; - - mutex_lock(&adap->lock); - seq_printf(file, "configured: %d\n", adap->is_configured); - seq_printf(file, "configuring: %d\n", adap->is_configuring); - seq_printf(file, "phys_addr: %x.%x.%x.%x\n", - cec_phys_addr_exp(adap->phys_addr)); - seq_printf(file, "number of LAs: %d\n", adap->log_addrs.num_log_addrs); - seq_printf(file, "LA mask: 0x%04x\n", adap->log_addrs.log_addr_mask); - if (adap->cec_follower) - seq_printf(file, "has CEC follower%s\n", - adap->passthrough ? " (in passthrough mode)" : ""); - if (adap->cec_initiator) - seq_puts(file, "has CEC initiator\n"); - if (adap->monitor_all_cnt) - seq_printf(file, "file handles in Monitor All mode: %u\n", - adap->monitor_all_cnt); - data = adap->transmitting; - if (data) - seq_printf(file, "transmitting message: %*ph (reply: %02x, timeout: %ums)\n", - data->msg.len, data->msg.msg, data->msg.reply, - data->msg.timeout); - seq_printf(file, "pending transmits: %u\n", adap->transmit_queue_sz); - list_for_each_entry(data, &adap->transmit_queue, list) { - seq_printf(file, "queued tx message: %*ph (reply: %02x, timeout: %ums)\n", - data->msg.len, data->msg.msg, data->msg.reply, - data->msg.timeout); - } - list_for_each_entry(data, &adap->wait_queue, list) { - seq_printf(file, "message waiting for reply: %*ph (reply: %02x, timeout: %ums)\n", - data->msg.len, data->msg.msg, data->msg.reply, - data->msg.timeout); - } - - call_void_op(adap, adap_status, file); - mutex_unlock(&adap->lock); - return 0; -} -#endif diff --git a/drivers/staging/media/cec/cec-api.c b/drivers/staging/media/cec/cec-api.c deleted file mode 100644 index d4bc4ee2c6e5..000000000000 --- a/drivers/staging/media/cec/cec-api.c +++ /dev/null @@ -1,588 +0,0 @@ -/* - * cec-api.c - HDMI Consumer Electronics Control framework - API - * - * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. - * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "cec-priv.h" - -static inline struct cec_devnode *cec_devnode_data(struct file *filp) -{ - struct cec_fh *fh = filp->private_data; - - return &fh->adap->devnode; -} - -/* CEC file operations */ - -static unsigned int cec_poll(struct file *filp, - struct poll_table_struct *poll) -{ - struct cec_devnode *devnode = cec_devnode_data(filp); - struct cec_fh *fh = filp->private_data; - struct cec_adapter *adap = fh->adap; - unsigned int res = 0; - - if (!devnode->registered) - return POLLERR | POLLHUP; - mutex_lock(&adap->lock); - if (adap->is_configured && - adap->transmit_queue_sz < CEC_MAX_MSG_TX_QUEUE_SZ) - res |= POLLOUT | POLLWRNORM; - if (fh->queued_msgs) - res |= POLLIN | POLLRDNORM; - if (fh->pending_events) - res |= POLLPRI; - poll_wait(filp, &fh->wait, poll); - mutex_unlock(&adap->lock); - return res; -} - -static bool cec_is_busy(const struct cec_adapter *adap, - const struct cec_fh *fh) -{ - bool valid_initiator = adap->cec_initiator && adap->cec_initiator == fh; - bool valid_follower = adap->cec_follower && adap->cec_follower == fh; - - /* - * Exclusive initiators and followers can always access the CEC adapter - */ - if (valid_initiator || valid_follower) - return false; - /* - * All others can only access the CEC adapter if there is no - * exclusive initiator and they are in INITIATOR mode. - */ - return adap->cec_initiator || - fh->mode_initiator == CEC_MODE_NO_INITIATOR; -} - -static long cec_adap_g_caps(struct cec_adapter *adap, - struct cec_caps __user *parg) -{ - struct cec_caps caps = {}; - - strlcpy(caps.driver, adap->devnode.parent->driver->name, - sizeof(caps.driver)); - strlcpy(caps.name, adap->name, sizeof(caps.name)); - caps.available_log_addrs = adap->available_log_addrs; - caps.capabilities = adap->capabilities; - caps.version = LINUX_VERSION_CODE; - if (copy_to_user(parg, &caps, sizeof(caps))) - return -EFAULT; - return 0; -} - -static long cec_adap_g_phys_addr(struct cec_adapter *adap, - __u16 __user *parg) -{ - u16 phys_addr; - - mutex_lock(&adap->lock); - phys_addr = adap->phys_addr; - mutex_unlock(&adap->lock); - if (copy_to_user(parg, &phys_addr, sizeof(phys_addr))) - return -EFAULT; - return 0; -} - -static long cec_adap_s_phys_addr(struct cec_adapter *adap, struct cec_fh *fh, - bool block, __u16 __user *parg) -{ - u16 phys_addr; - long err; - - if (!(adap->capabilities & CEC_CAP_PHYS_ADDR)) - return -ENOTTY; - if (copy_from_user(&phys_addr, parg, sizeof(phys_addr))) - return -EFAULT; - - err = cec_phys_addr_validate(phys_addr, NULL, NULL); - if (err) - return err; - mutex_lock(&adap->lock); - if (cec_is_busy(adap, fh)) - err = -EBUSY; - else - __cec_s_phys_addr(adap, phys_addr, block); - mutex_unlock(&adap->lock); - return err; -} - -static long cec_adap_g_log_addrs(struct cec_adapter *adap, - struct cec_log_addrs __user *parg) -{ - struct cec_log_addrs log_addrs; - - mutex_lock(&adap->lock); - log_addrs = adap->log_addrs; - if (!adap->is_configured) - memset(log_addrs.log_addr, CEC_LOG_ADDR_INVALID, - sizeof(log_addrs.log_addr)); - mutex_unlock(&adap->lock); - - if (copy_to_user(parg, &log_addrs, sizeof(log_addrs))) - return -EFAULT; - return 0; -} - -static long cec_adap_s_log_addrs(struct cec_adapter *adap, struct cec_fh *fh, - bool block, struct cec_log_addrs __user *parg) -{ - struct cec_log_addrs log_addrs; - long err = -EBUSY; - - if (!(adap->capabilities & CEC_CAP_LOG_ADDRS)) - return -ENOTTY; - if (copy_from_user(&log_addrs, parg, sizeof(log_addrs))) - return -EFAULT; - log_addrs.flags &= CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK | - CEC_LOG_ADDRS_FL_ALLOW_RC_PASSTHRU | - CEC_LOG_ADDRS_FL_CDC_ONLY; - mutex_lock(&adap->lock); - if (!adap->is_configuring && - (!log_addrs.num_log_addrs || !adap->is_configured) && - !cec_is_busy(adap, fh)) { - err = __cec_s_log_addrs(adap, &log_addrs, block); - if (!err) - log_addrs = adap->log_addrs; - } - mutex_unlock(&adap->lock); - if (err) - return err; - if (copy_to_user(parg, &log_addrs, sizeof(log_addrs))) - return -EFAULT; - return 0; -} - -static long cec_transmit(struct cec_adapter *adap, struct cec_fh *fh, - bool block, struct cec_msg __user *parg) -{ - struct cec_msg msg = {}; - long err = 0; - - if (!(adap->capabilities & CEC_CAP_TRANSMIT)) - return -ENOTTY; - if (copy_from_user(&msg, parg, sizeof(msg))) - return -EFAULT; - - /* A CDC-Only device can only send CDC messages */ - if ((adap->log_addrs.flags & CEC_LOG_ADDRS_FL_CDC_ONLY) && - (msg.len == 1 || msg.msg[1] != CEC_MSG_CDC_MESSAGE)) - return -EINVAL; - - msg.flags &= CEC_MSG_FL_REPLY_TO_FOLLOWERS; - mutex_lock(&adap->lock); - if (!adap->is_configured) - err = -ENONET; - else if (cec_is_busy(adap, fh)) - err = -EBUSY; - else - err = cec_transmit_msg_fh(adap, &msg, fh, block); - mutex_unlock(&adap->lock); - if (err) - return err; - if (copy_to_user(parg, &msg, sizeof(msg))) - return -EFAULT; - return 0; -} - -/* Called by CEC_RECEIVE: wait for a message to arrive */ -static int cec_receive_msg(struct cec_fh *fh, struct cec_msg *msg, bool block) -{ - u32 timeout = msg->timeout; - int res; - - do { - mutex_lock(&fh->lock); - /* Are there received messages queued up? */ - if (fh->queued_msgs) { - /* Yes, return the first one */ - struct cec_msg_entry *entry = - list_first_entry(&fh->msgs, - struct cec_msg_entry, list); - - list_del(&entry->list); - *msg = entry->msg; - kfree(entry); - fh->queued_msgs--; - mutex_unlock(&fh->lock); - /* restore original timeout value */ - msg->timeout = timeout; - return 0; - } - - /* No, return EAGAIN in non-blocking mode or wait */ - mutex_unlock(&fh->lock); - - /* Return when in non-blocking mode */ - if (!block) - return -EAGAIN; - - if (msg->timeout) { - /* The user specified a timeout */ - res = wait_event_interruptible_timeout(fh->wait, - fh->queued_msgs, - msecs_to_jiffies(msg->timeout)); - if (res == 0) - res = -ETIMEDOUT; - else if (res > 0) - res = 0; - } else { - /* Wait indefinitely */ - res = wait_event_interruptible(fh->wait, - fh->queued_msgs); - } - /* Exit on error, otherwise loop to get the new message */ - } while (!res); - return res; -} - -static long cec_receive(struct cec_adapter *adap, struct cec_fh *fh, - bool block, struct cec_msg __user *parg) -{ - struct cec_msg msg = {}; - long err = 0; - - if (copy_from_user(&msg, parg, sizeof(msg))) - return -EFAULT; - mutex_lock(&adap->lock); - if (!adap->is_configured && fh->mode_follower < CEC_MODE_MONITOR) - err = -ENONET; - mutex_unlock(&adap->lock); - if (err) - return err; - - err = cec_receive_msg(fh, &msg, block); - if (err) - return err; - if (copy_to_user(parg, &msg, sizeof(msg))) - return -EFAULT; - return 0; -} - -static long cec_dqevent(struct cec_adapter *adap, struct cec_fh *fh, - bool block, struct cec_event __user *parg) -{ - struct cec_event *ev = NULL; - u64 ts = ~0ULL; - unsigned int i; - long err = 0; - - mutex_lock(&fh->lock); - while (!fh->pending_events && block) { - mutex_unlock(&fh->lock); - err = wait_event_interruptible(fh->wait, fh->pending_events); - if (err) - return err; - mutex_lock(&fh->lock); - } - - /* Find the oldest event */ - for (i = 0; i < CEC_NUM_EVENTS; i++) { - if (fh->pending_events & (1 << (i + 1)) && - fh->events[i].ts <= ts) { - ev = &fh->events[i]; - ts = ev->ts; - } - } - if (!ev) { - err = -EAGAIN; - goto unlock; - } - - if (copy_to_user(parg, ev, sizeof(*ev))) { - err = -EFAULT; - goto unlock; - } - - fh->pending_events &= ~(1 << ev->event); - -unlock: - mutex_unlock(&fh->lock); - return err; -} - -static long cec_g_mode(struct cec_adapter *adap, struct cec_fh *fh, - u32 __user *parg) -{ - u32 mode = fh->mode_initiator | fh->mode_follower; - - if (copy_to_user(parg, &mode, sizeof(mode))) - return -EFAULT; - return 0; -} - -static long cec_s_mode(struct cec_adapter *adap, struct cec_fh *fh, - u32 __user *parg) -{ - u32 mode; - u8 mode_initiator; - u8 mode_follower; - long err = 0; - - if (copy_from_user(&mode, parg, sizeof(mode))) - return -EFAULT; - if (mode & ~(CEC_MODE_INITIATOR_MSK | CEC_MODE_FOLLOWER_MSK)) - return -EINVAL; - - mode_initiator = mode & CEC_MODE_INITIATOR_MSK; - mode_follower = mode & CEC_MODE_FOLLOWER_MSK; - - if (mode_initiator > CEC_MODE_EXCL_INITIATOR || - mode_follower > CEC_MODE_MONITOR_ALL) - return -EINVAL; - - if (mode_follower == CEC_MODE_MONITOR_ALL && - !(adap->capabilities & CEC_CAP_MONITOR_ALL)) - return -EINVAL; - - /* Follower modes should always be able to send CEC messages */ - if ((mode_initiator == CEC_MODE_NO_INITIATOR || - !(adap->capabilities & CEC_CAP_TRANSMIT)) && - mode_follower >= CEC_MODE_FOLLOWER && - mode_follower <= CEC_MODE_EXCL_FOLLOWER_PASSTHRU) - return -EINVAL; - - /* Monitor modes require CEC_MODE_NO_INITIATOR */ - if (mode_initiator && mode_follower >= CEC_MODE_MONITOR) - return -EINVAL; - - /* Monitor modes require CAP_NET_ADMIN */ - if (mode_follower >= CEC_MODE_MONITOR && !capable(CAP_NET_ADMIN)) - return -EPERM; - - mutex_lock(&adap->lock); - /* - * You can't become exclusive follower if someone else already - * has that job. - */ - if ((mode_follower == CEC_MODE_EXCL_FOLLOWER || - mode_follower == CEC_MODE_EXCL_FOLLOWER_PASSTHRU) && - adap->cec_follower && adap->cec_follower != fh) - err = -EBUSY; - /* - * You can't become exclusive initiator if someone else already - * has that job. - */ - if (mode_initiator == CEC_MODE_EXCL_INITIATOR && - adap->cec_initiator && adap->cec_initiator != fh) - err = -EBUSY; - - if (!err) { - bool old_mon_all = fh->mode_follower == CEC_MODE_MONITOR_ALL; - bool new_mon_all = mode_follower == CEC_MODE_MONITOR_ALL; - - if (old_mon_all != new_mon_all) { - if (new_mon_all) - err = cec_monitor_all_cnt_inc(adap); - else - cec_monitor_all_cnt_dec(adap); - } - } - - if (err) { - mutex_unlock(&adap->lock); - return err; - } - - if (fh->mode_follower == CEC_MODE_FOLLOWER) - adap->follower_cnt--; - if (mode_follower == CEC_MODE_FOLLOWER) - adap->follower_cnt++; - if (mode_follower == CEC_MODE_EXCL_FOLLOWER || - mode_follower == CEC_MODE_EXCL_FOLLOWER_PASSTHRU) { - adap->passthrough = - mode_follower == CEC_MODE_EXCL_FOLLOWER_PASSTHRU; - adap->cec_follower = fh; - } else if (adap->cec_follower == fh) { - adap->passthrough = false; - adap->cec_follower = NULL; - } - if (mode_initiator == CEC_MODE_EXCL_INITIATOR) - adap->cec_initiator = fh; - else if (adap->cec_initiator == fh) - adap->cec_initiator = NULL; - fh->mode_initiator = mode_initiator; - fh->mode_follower = mode_follower; - mutex_unlock(&adap->lock); - return 0; -} - -static long cec_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) -{ - struct cec_devnode *devnode = cec_devnode_data(filp); - struct cec_fh *fh = filp->private_data; - struct cec_adapter *adap = fh->adap; - bool block = !(filp->f_flags & O_NONBLOCK); - void __user *parg = (void __user *)arg; - - if (!devnode->registered) - return -ENODEV; - - switch (cmd) { - case CEC_ADAP_G_CAPS: - return cec_adap_g_caps(adap, parg); - - case CEC_ADAP_G_PHYS_ADDR: - return cec_adap_g_phys_addr(adap, parg); - - case CEC_ADAP_S_PHYS_ADDR: - return cec_adap_s_phys_addr(adap, fh, block, parg); - - case CEC_ADAP_G_LOG_ADDRS: - return cec_adap_g_log_addrs(adap, parg); - - case CEC_ADAP_S_LOG_ADDRS: - return cec_adap_s_log_addrs(adap, fh, block, parg); - - case CEC_TRANSMIT: - return cec_transmit(adap, fh, block, parg); - - case CEC_RECEIVE: - return cec_receive(adap, fh, block, parg); - - case CEC_DQEVENT: - return cec_dqevent(adap, fh, block, parg); - - case CEC_G_MODE: - return cec_g_mode(adap, fh, parg); - - case CEC_S_MODE: - return cec_s_mode(adap, fh, parg); - - default: - return -ENOTTY; - } -} - -static int cec_open(struct inode *inode, struct file *filp) -{ - struct cec_devnode *devnode = - container_of(inode->i_cdev, struct cec_devnode, cdev); - struct cec_adapter *adap = to_cec_adapter(devnode); - struct cec_fh *fh = kzalloc(sizeof(*fh), GFP_KERNEL); - /* - * Initial events that are automatically sent when the cec device is - * opened. - */ - struct cec_event ev_state = { - .event = CEC_EVENT_STATE_CHANGE, - .flags = CEC_EVENT_FL_INITIAL_STATE, - }; - int err; - - if (!fh) - return -ENOMEM; - - INIT_LIST_HEAD(&fh->msgs); - INIT_LIST_HEAD(&fh->xfer_list); - mutex_init(&fh->lock); - init_waitqueue_head(&fh->wait); - - fh->mode_initiator = CEC_MODE_INITIATOR; - fh->adap = adap; - - err = cec_get_device(devnode); - if (err) { - kfree(fh); - return err; - } - - filp->private_data = fh; - - mutex_lock(&devnode->lock); - /* Queue up initial state events */ - ev_state.state_change.phys_addr = adap->phys_addr; - ev_state.state_change.log_addr_mask = adap->log_addrs.log_addr_mask; - cec_queue_event_fh(fh, &ev_state, 0); - - list_add(&fh->list, &devnode->fhs); - mutex_unlock(&devnode->lock); - - return 0; -} - -/* Override for the release function */ -static int cec_release(struct inode *inode, struct file *filp) -{ - struct cec_devnode *devnode = cec_devnode_data(filp); - struct cec_adapter *adap = to_cec_adapter(devnode); - struct cec_fh *fh = filp->private_data; - - mutex_lock(&adap->lock); - if (adap->cec_initiator == fh) - adap->cec_initiator = NULL; - if (adap->cec_follower == fh) { - adap->cec_follower = NULL; - adap->passthrough = false; - } - if (fh->mode_follower == CEC_MODE_FOLLOWER) - adap->follower_cnt--; - if (fh->mode_follower == CEC_MODE_MONITOR_ALL) - cec_monitor_all_cnt_dec(adap); - mutex_unlock(&adap->lock); - - mutex_lock(&devnode->lock); - list_del(&fh->list); - mutex_unlock(&devnode->lock); - - /* Unhook pending transmits from this filehandle. */ - mutex_lock(&adap->lock); - while (!list_empty(&fh->xfer_list)) { - struct cec_data *data = - list_first_entry(&fh->xfer_list, struct cec_data, xfer_list); - - data->blocking = false; - data->fh = NULL; - list_del(&data->xfer_list); - } - mutex_unlock(&adap->lock); - while (!list_empty(&fh->msgs)) { - struct cec_msg_entry *entry = - list_first_entry(&fh->msgs, struct cec_msg_entry, list); - - list_del(&entry->list); - kfree(entry); - } - kfree(fh); - - cec_put_device(devnode); - filp->private_data = NULL; - return 0; -} - -const struct file_operations cec_devnode_fops = { - .owner = THIS_MODULE, - .open = cec_open, - .unlocked_ioctl = cec_ioctl, - .release = cec_release, - .poll = cec_poll, - .llseek = no_llseek, -}; diff --git a/drivers/staging/media/cec/cec-core.c b/drivers/staging/media/cec/cec-core.c deleted file mode 100644 index b0137e247dc9..000000000000 --- a/drivers/staging/media/cec/cec-core.c +++ /dev/null @@ -1,411 +0,0 @@ -/* - * cec-core.c - HDMI Consumer Electronics Control framework - Core - * - * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. - * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "cec-priv.h" - -#define CEC_NUM_DEVICES 256 -#define CEC_NAME "cec" - -int cec_debug; -module_param_named(debug, cec_debug, int, 0644); -MODULE_PARM_DESC(debug, "debug level (0-2)"); - -static dev_t cec_dev_t; - -/* Active devices */ -static DEFINE_MUTEX(cec_devnode_lock); -static DECLARE_BITMAP(cec_devnode_nums, CEC_NUM_DEVICES); - -static struct dentry *top_cec_dir; - -/* dev to cec_devnode */ -#define to_cec_devnode(cd) container_of(cd, struct cec_devnode, dev) - -int cec_get_device(struct cec_devnode *devnode) -{ - /* - * Check if the cec device is available. This needs to be done with - * the devnode->lock held to prevent an open/unregister race: - * without the lock, the device could be unregistered and freed between - * the devnode->registered check and get_device() calls, leading to - * a crash. - */ - mutex_lock(&devnode->lock); - /* - * return ENXIO if the cec device has been removed - * already or if it is not registered anymore. - */ - if (!devnode->registered) { - mutex_unlock(&devnode->lock); - return -ENXIO; - } - /* and increase the device refcount */ - get_device(&devnode->dev); - mutex_unlock(&devnode->lock); - return 0; -} - -void cec_put_device(struct cec_devnode *devnode) -{ - put_device(&devnode->dev); -} - -/* Called when the last user of the cec device exits. */ -static void cec_devnode_release(struct device *cd) -{ - struct cec_devnode *devnode = to_cec_devnode(cd); - - mutex_lock(&cec_devnode_lock); - /* Mark device node number as free */ - clear_bit(devnode->minor, cec_devnode_nums); - mutex_unlock(&cec_devnode_lock); - - cec_delete_adapter(to_cec_adapter(devnode)); -} - -static struct bus_type cec_bus_type = { - .name = CEC_NAME, -}; - -/* - * Register a cec device node - * - * The registration code assigns minor numbers and registers the new device node - * with the kernel. An error is returned if no free minor number can be found, - * or if the registration of the device node fails. - * - * Zero is returned on success. - * - * Note that if the cec_devnode_register call fails, the release() callback of - * the cec_devnode structure is *not* called, so the caller is responsible for - * freeing any data. - */ -static int __must_check cec_devnode_register(struct cec_devnode *devnode, - struct module *owner) -{ - int minor; - int ret; - - /* Initialization */ - INIT_LIST_HEAD(&devnode->fhs); - mutex_init(&devnode->lock); - - /* Part 1: Find a free minor number */ - mutex_lock(&cec_devnode_lock); - minor = find_next_zero_bit(cec_devnode_nums, CEC_NUM_DEVICES, 0); - if (minor == CEC_NUM_DEVICES) { - mutex_unlock(&cec_devnode_lock); - pr_err("could not get a free minor\n"); - return -ENFILE; - } - - set_bit(minor, cec_devnode_nums); - mutex_unlock(&cec_devnode_lock); - - devnode->minor = minor; - devnode->dev.bus = &cec_bus_type; - devnode->dev.devt = MKDEV(MAJOR(cec_dev_t), minor); - devnode->dev.release = cec_devnode_release; - devnode->dev.parent = devnode->parent; - dev_set_name(&devnode->dev, "cec%d", devnode->minor); - device_initialize(&devnode->dev); - - /* Part 2: Initialize and register the character device */ - cdev_init(&devnode->cdev, &cec_devnode_fops); - devnode->cdev.kobj.parent = &devnode->dev.kobj; - devnode->cdev.owner = owner; - - ret = cdev_add(&devnode->cdev, devnode->dev.devt, 1); - if (ret < 0) { - pr_err("%s: cdev_add failed\n", __func__); - goto clr_bit; - } - - ret = device_add(&devnode->dev); - if (ret) - goto cdev_del; - - devnode->registered = true; - return 0; - -cdev_del: - cdev_del(&devnode->cdev); -clr_bit: - mutex_lock(&cec_devnode_lock); - clear_bit(devnode->minor, cec_devnode_nums); - mutex_unlock(&cec_devnode_lock); - return ret; -} - -/* - * Unregister a cec device node - * - * This unregisters the passed device. Future open calls will be met with - * errors. - * - * This function can safely be called if the device node has never been - * registered or has already been unregistered. - */ -static void cec_devnode_unregister(struct cec_devnode *devnode) -{ - struct cec_fh *fh; - - mutex_lock(&devnode->lock); - - /* Check if devnode was never registered or already unregistered */ - if (!devnode->registered || devnode->unregistered) { - mutex_unlock(&devnode->lock); - return; - } - - list_for_each_entry(fh, &devnode->fhs, list) - wake_up_interruptible(&fh->wait); - - devnode->registered = false; - devnode->unregistered = true; - mutex_unlock(&devnode->lock); - - device_del(&devnode->dev); - cdev_del(&devnode->cdev); - put_device(&devnode->dev); -} - -struct cec_adapter *cec_allocate_adapter(const struct cec_adap_ops *ops, - void *priv, const char *name, u32 caps, - u8 available_las, struct device *parent) -{ - struct cec_adapter *adap; - int res; - - if (WARN_ON(!parent)) - return ERR_PTR(-EINVAL); - if (WARN_ON(!caps)) - return ERR_PTR(-EINVAL); - if (WARN_ON(!ops)) - return ERR_PTR(-EINVAL); - if (WARN_ON(!available_las || available_las > CEC_MAX_LOG_ADDRS)) - return ERR_PTR(-EINVAL); - adap = kzalloc(sizeof(*adap), GFP_KERNEL); - if (!adap) - return ERR_PTR(-ENOMEM); - adap->owner = parent->driver->owner; - adap->devnode.parent = parent; - strlcpy(adap->name, name, sizeof(adap->name)); - adap->phys_addr = CEC_PHYS_ADDR_INVALID; - adap->log_addrs.cec_version = CEC_OP_CEC_VERSION_2_0; - adap->log_addrs.vendor_id = CEC_VENDOR_ID_NONE; - adap->capabilities = caps; - adap->available_log_addrs = available_las; - adap->sequence = 0; - adap->ops = ops; - adap->priv = priv; - memset(adap->phys_addrs, 0xff, sizeof(adap->phys_addrs)); - mutex_init(&adap->lock); - INIT_LIST_HEAD(&adap->transmit_queue); - INIT_LIST_HEAD(&adap->wait_queue); - init_waitqueue_head(&adap->kthread_waitq); - - adap->kthread = kthread_run(cec_thread_func, adap, "cec-%s", name); - if (IS_ERR(adap->kthread)) { - pr_err("cec-%s: kernel_thread() failed\n", name); - res = PTR_ERR(adap->kthread); - kfree(adap); - return ERR_PTR(res); - } - - if (!(caps & CEC_CAP_RC)) - return adap; - -#if IS_REACHABLE(CONFIG_RC_CORE) - /* Prepare the RC input device */ - adap->rc = rc_allocate_device(); - if (!adap->rc) { - pr_err("cec-%s: failed to allocate memory for rc_dev\n", - name); - kthread_stop(adap->kthread); - kfree(adap); - return ERR_PTR(-ENOMEM); - } - - snprintf(adap->input_name, sizeof(adap->input_name), - "RC for %s", name); - snprintf(adap->input_phys, sizeof(adap->input_phys), - "%s/input0", name); - - adap->rc->input_name = adap->input_name; - adap->rc->input_phys = adap->input_phys; - adap->rc->input_id.bustype = BUS_CEC; - adap->rc->input_id.vendor = 0; - adap->rc->input_id.product = 0; - adap->rc->input_id.version = 1; - adap->rc->dev.parent = parent; - adap->rc->driver_type = RC_DRIVER_SCANCODE; - adap->rc->driver_name = CEC_NAME; - adap->rc->allowed_protocols = RC_BIT_CEC; - adap->rc->priv = adap; - adap->rc->map_name = RC_MAP_CEC; - adap->rc->timeout = MS_TO_NS(100); -#else - adap->capabilities &= ~CEC_CAP_RC; -#endif - return adap; -} -EXPORT_SYMBOL_GPL(cec_allocate_adapter); - -int cec_register_adapter(struct cec_adapter *adap) -{ - int res; - - if (IS_ERR_OR_NULL(adap)) - return 0; - -#if IS_REACHABLE(CONFIG_RC_CORE) - if (adap->capabilities & CEC_CAP_RC) { - res = rc_register_device(adap->rc); - - if (res) { - pr_err("cec-%s: failed to prepare input device\n", - adap->name); - rc_free_device(adap->rc); - adap->rc = NULL; - return res; - } - } -#endif - - res = cec_devnode_register(&adap->devnode, adap->owner); - if (res) { -#if IS_REACHABLE(CONFIG_RC_CORE) - /* Note: rc_unregister also calls rc_free */ - rc_unregister_device(adap->rc); - adap->rc = NULL; -#endif - return res; - } - - dev_set_drvdata(&adap->devnode.dev, adap); -#ifdef CONFIG_MEDIA_CEC_DEBUG - if (!top_cec_dir) - return 0; - - adap->cec_dir = debugfs_create_dir(dev_name(&adap->devnode.dev), top_cec_dir); - if (IS_ERR_OR_NULL(adap->cec_dir)) { - pr_warn("cec-%s: Failed to create debugfs dir\n", adap->name); - return 0; - } - adap->status_file = debugfs_create_devm_seqfile(&adap->devnode.dev, - "status", adap->cec_dir, cec_adap_status); - if (IS_ERR_OR_NULL(adap->status_file)) { - pr_warn("cec-%s: Failed to create status file\n", adap->name); - debugfs_remove_recursive(adap->cec_dir); - adap->cec_dir = NULL; - } -#endif - return 0; -} -EXPORT_SYMBOL_GPL(cec_register_adapter); - -void cec_unregister_adapter(struct cec_adapter *adap) -{ - if (IS_ERR_OR_NULL(adap)) - return; - -#if IS_REACHABLE(CONFIG_RC_CORE) - /* Note: rc_unregister also calls rc_free */ - rc_unregister_device(adap->rc); - adap->rc = NULL; -#endif - debugfs_remove_recursive(adap->cec_dir); - cec_devnode_unregister(&adap->devnode); -} -EXPORT_SYMBOL_GPL(cec_unregister_adapter); - -void cec_delete_adapter(struct cec_adapter *adap) -{ - if (IS_ERR_OR_NULL(adap)) - return; - mutex_lock(&adap->lock); - __cec_s_phys_addr(adap, CEC_PHYS_ADDR_INVALID, false); - mutex_unlock(&adap->lock); - kthread_stop(adap->kthread); - if (adap->kthread_config) - kthread_stop(adap->kthread_config); -#if IS_REACHABLE(CONFIG_RC_CORE) - rc_free_device(adap->rc); -#endif - kfree(adap); -} -EXPORT_SYMBOL_GPL(cec_delete_adapter); - -/* - * Initialise cec for linux - */ -static int __init cec_devnode_init(void) -{ - int ret; - - pr_info("Linux cec interface: v0.10\n"); - ret = alloc_chrdev_region(&cec_dev_t, 0, CEC_NUM_DEVICES, - CEC_NAME); - if (ret < 0) { - pr_warn("cec: unable to allocate major\n"); - return ret; - } - -#ifdef CONFIG_MEDIA_CEC_DEBUG - top_cec_dir = debugfs_create_dir("cec", NULL); - if (IS_ERR_OR_NULL(top_cec_dir)) { - pr_warn("cec: Failed to create debugfs cec dir\n"); - top_cec_dir = NULL; - } -#endif - - ret = bus_register(&cec_bus_type); - if (ret < 0) { - unregister_chrdev_region(cec_dev_t, CEC_NUM_DEVICES); - pr_warn("cec: bus_register failed\n"); - return -EIO; - } - - return 0; -} - -static void __exit cec_devnode_exit(void) -{ - debugfs_remove_recursive(top_cec_dir); - bus_unregister(&cec_bus_type); - unregister_chrdev_region(cec_dev_t, CEC_NUM_DEVICES); -} - -subsys_initcall(cec_devnode_init); -module_exit(cec_devnode_exit) - -MODULE_AUTHOR("Hans Verkuil "); -MODULE_DESCRIPTION("Device node registration for cec drivers"); -MODULE_LICENSE("GPL"); diff --git a/drivers/staging/media/cec/cec-priv.h b/drivers/staging/media/cec/cec-priv.h deleted file mode 100644 index 70767a7900f2..000000000000 --- a/drivers/staging/media/cec/cec-priv.h +++ /dev/null @@ -1,56 +0,0 @@ -/* - * cec-priv.h - HDMI Consumer Electronics Control internal header - * - * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. - * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -#ifndef _CEC_PRIV_H -#define _CEC_PRIV_H - -#include -#include - -#define dprintk(lvl, fmt, arg...) \ - do { \ - if (lvl <= cec_debug) \ - pr_info("cec-%s: " fmt, adap->name, ## arg); \ - } while (0) - -/* devnode to cec_adapter */ -#define to_cec_adapter(node) container_of(node, struct cec_adapter, devnode) - -/* cec-core.c */ -extern int cec_debug; -int cec_get_device(struct cec_devnode *devnode); -void cec_put_device(struct cec_devnode *devnode); - -/* cec-adap.c */ -int cec_monitor_all_cnt_inc(struct cec_adapter *adap); -void cec_monitor_all_cnt_dec(struct cec_adapter *adap); -int cec_adap_status(struct seq_file *file, void *priv); -int cec_thread_func(void *_adap); -void __cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr, bool block); -int __cec_s_log_addrs(struct cec_adapter *adap, - struct cec_log_addrs *log_addrs, bool block); -int cec_transmit_msg_fh(struct cec_adapter *adap, struct cec_msg *msg, - struct cec_fh *fh, bool block); -void cec_queue_event_fh(struct cec_fh *fh, - const struct cec_event *new_ev, u64 ts); - -/* cec-api.c */ -extern const struct file_operations cec_devnode_fops; - -#endif diff --git a/drivers/staging/media/pulse8-cec/Kconfig b/drivers/staging/media/pulse8-cec/Kconfig index c6aa2d1c9df0..6ffc407de62f 100644 --- a/drivers/staging/media/pulse8-cec/Kconfig +++ b/drivers/staging/media/pulse8-cec/Kconfig @@ -1,6 +1,6 @@ config USB_PULSE8_CEC tristate "Pulse Eight HDMI CEC" - depends on USB_ACM && MEDIA_CEC + depends on USB_ACM && MEDIA_CEC_SUPPORT select SERIO select SERIO_SERPORT ---help--- diff --git a/drivers/staging/media/s5p-cec/Kconfig b/drivers/staging/media/s5p-cec/Kconfig index 0315fd7ad0f1..ddfd955da0d4 100644 --- a/drivers/staging/media/s5p-cec/Kconfig +++ b/drivers/staging/media/s5p-cec/Kconfig @@ -1,6 +1,6 @@ config VIDEO_SAMSUNG_S5P_CEC tristate "Samsung S5P CEC driver" - depends on VIDEO_DEV && MEDIA_CEC && (PLAT_S5P || ARCH_EXYNOS || COMPILE_TEST) + depends on VIDEO_DEV && MEDIA_CEC_SUPPORT && (PLAT_S5P || ARCH_EXYNOS || COMPILE_TEST) ---help--- This is a driver for Samsung S5P HDMI CEC interface. It uses the generic CEC framework interface. diff --git a/drivers/staging/media/st-cec/Kconfig b/drivers/staging/media/st-cec/Kconfig index 784d2c600aca..c04283db58d6 100644 --- a/drivers/staging/media/st-cec/Kconfig +++ b/drivers/staging/media/st-cec/Kconfig @@ -1,6 +1,6 @@ config VIDEO_STI_HDMI_CEC tristate "STMicroelectronics STiH4xx HDMI CEC driver" - depends on VIDEO_DEV && MEDIA_CEC && (ARCH_STI || COMPILE_TEST) + depends on VIDEO_DEV && MEDIA_CEC_SUPPORT && (ARCH_STI || COMPILE_TEST) ---help--- This is a driver for STIH4xx HDMI CEC interface. It uses the generic CEC framework interface. diff --git a/include/linux/cec-funcs.h b/include/linux/cec-funcs.h deleted file mode 100644 index 138bbf721e70..000000000000 --- a/include/linux/cec-funcs.h +++ /dev/null @@ -1,1971 +0,0 @@ -/* - * cec - HDMI Consumer Electronics Control message functions - * - * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. - * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * Alternatively you can redistribute this file under the terms of the - * BSD license as stated below: - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * 3. The names of its contributors may not be used to endorse or promote - * products derived from this software without specific prior written - * permission. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -/* - * Note: this framework is still in staging and it is likely the API - * will change before it goes out of staging. - * - * Once it is moved out of staging this header will move to uapi. - */ -#ifndef _CEC_UAPI_FUNCS_H -#define _CEC_UAPI_FUNCS_H - -#include - -/* One Touch Play Feature */ -static inline void cec_msg_active_source(struct cec_msg *msg, __u16 phys_addr) -{ - msg->len = 4; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_ACTIVE_SOURCE; - msg->msg[2] = phys_addr >> 8; - msg->msg[3] = phys_addr & 0xff; -} - -static inline void cec_ops_active_source(const struct cec_msg *msg, - __u16 *phys_addr) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; -} - -static inline void cec_msg_image_view_on(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_IMAGE_VIEW_ON; -} - -static inline void cec_msg_text_view_on(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_TEXT_VIEW_ON; -} - - -/* Routing Control Feature */ -static inline void cec_msg_inactive_source(struct cec_msg *msg, - __u16 phys_addr) -{ - msg->len = 4; - msg->msg[1] = CEC_MSG_INACTIVE_SOURCE; - msg->msg[2] = phys_addr >> 8; - msg->msg[3] = phys_addr & 0xff; -} - -static inline void cec_ops_inactive_source(const struct cec_msg *msg, - __u16 *phys_addr) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; -} - -static inline void cec_msg_request_active_source(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_REQUEST_ACTIVE_SOURCE; - msg->reply = reply ? CEC_MSG_ACTIVE_SOURCE : 0; -} - -static inline void cec_msg_routing_information(struct cec_msg *msg, - __u16 phys_addr) -{ - msg->len = 4; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_ROUTING_INFORMATION; - msg->msg[2] = phys_addr >> 8; - msg->msg[3] = phys_addr & 0xff; -} - -static inline void cec_ops_routing_information(const struct cec_msg *msg, - __u16 *phys_addr) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; -} - -static inline void cec_msg_routing_change(struct cec_msg *msg, - bool reply, - __u16 orig_phys_addr, - __u16 new_phys_addr) -{ - msg->len = 6; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_ROUTING_CHANGE; - msg->msg[2] = orig_phys_addr >> 8; - msg->msg[3] = orig_phys_addr & 0xff; - msg->msg[4] = new_phys_addr >> 8; - msg->msg[5] = new_phys_addr & 0xff; - msg->reply = reply ? CEC_MSG_ROUTING_INFORMATION : 0; -} - -static inline void cec_ops_routing_change(const struct cec_msg *msg, - __u16 *orig_phys_addr, - __u16 *new_phys_addr) -{ - *orig_phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *new_phys_addr = (msg->msg[4] << 8) | msg->msg[5]; -} - -static inline void cec_msg_set_stream_path(struct cec_msg *msg, __u16 phys_addr) -{ - msg->len = 4; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_SET_STREAM_PATH; - msg->msg[2] = phys_addr >> 8; - msg->msg[3] = phys_addr & 0xff; -} - -static inline void cec_ops_set_stream_path(const struct cec_msg *msg, - __u16 *phys_addr) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; -} - - -/* Standby Feature */ -static inline void cec_msg_standby(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_STANDBY; -} - - -/* One Touch Record Feature */ -static inline void cec_msg_record_off(struct cec_msg *msg, bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_RECORD_OFF; - msg->reply = reply ? CEC_MSG_RECORD_STATUS : 0; -} - -struct cec_op_arib_data { - __u16 transport_id; - __u16 service_id; - __u16 orig_network_id; -}; - -struct cec_op_atsc_data { - __u16 transport_id; - __u16 program_number; -}; - -struct cec_op_dvb_data { - __u16 transport_id; - __u16 service_id; - __u16 orig_network_id; -}; - -struct cec_op_channel_data { - __u8 channel_number_fmt; - __u16 major; - __u16 minor; -}; - -struct cec_op_digital_service_id { - __u8 service_id_method; - __u8 dig_bcast_system; - union { - struct cec_op_arib_data arib; - struct cec_op_atsc_data atsc; - struct cec_op_dvb_data dvb; - struct cec_op_channel_data channel; - }; -}; - -struct cec_op_record_src { - __u8 type; - union { - struct cec_op_digital_service_id digital; - struct { - __u8 ana_bcast_type; - __u16 ana_freq; - __u8 bcast_system; - } analog; - struct { - __u8 plug; - } ext_plug; - struct { - __u16 phys_addr; - } ext_phys_addr; - }; -}; - -static inline void cec_set_digital_service_id(__u8 *msg, - const struct cec_op_digital_service_id *digital) -{ - *msg++ = (digital->service_id_method << 7) | digital->dig_bcast_system; - if (digital->service_id_method == CEC_OP_SERVICE_ID_METHOD_BY_CHANNEL) { - *msg++ = (digital->channel.channel_number_fmt << 2) | - (digital->channel.major >> 8); - *msg++ = digital->channel.major & 0xff; - *msg++ = digital->channel.minor >> 8; - *msg++ = digital->channel.minor & 0xff; - *msg++ = 0; - *msg++ = 0; - return; - } - switch (digital->dig_bcast_system) { - case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_GEN: - case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_CABLE: - case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_SAT: - case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_T: - *msg++ = digital->atsc.transport_id >> 8; - *msg++ = digital->atsc.transport_id & 0xff; - *msg++ = digital->atsc.program_number >> 8; - *msg++ = digital->atsc.program_number & 0xff; - *msg++ = 0; - *msg++ = 0; - break; - default: - *msg++ = digital->dvb.transport_id >> 8; - *msg++ = digital->dvb.transport_id & 0xff; - *msg++ = digital->dvb.service_id >> 8; - *msg++ = digital->dvb.service_id & 0xff; - *msg++ = digital->dvb.orig_network_id >> 8; - *msg++ = digital->dvb.orig_network_id & 0xff; - break; - } -} - -static inline void cec_get_digital_service_id(const __u8 *msg, - struct cec_op_digital_service_id *digital) -{ - digital->service_id_method = msg[0] >> 7; - digital->dig_bcast_system = msg[0] & 0x7f; - if (digital->service_id_method == CEC_OP_SERVICE_ID_METHOD_BY_CHANNEL) { - digital->channel.channel_number_fmt = msg[1] >> 2; - digital->channel.major = ((msg[1] & 3) << 6) | msg[2]; - digital->channel.minor = (msg[3] << 8) | msg[4]; - return; - } - digital->dvb.transport_id = (msg[1] << 8) | msg[2]; - digital->dvb.service_id = (msg[3] << 8) | msg[4]; - digital->dvb.orig_network_id = (msg[5] << 8) | msg[6]; -} - -static inline void cec_msg_record_on_own(struct cec_msg *msg) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_RECORD_ON; - msg->msg[2] = CEC_OP_RECORD_SRC_OWN; -} - -static inline void cec_msg_record_on_digital(struct cec_msg *msg, - const struct cec_op_digital_service_id *digital) -{ - msg->len = 10; - msg->msg[1] = CEC_MSG_RECORD_ON; - msg->msg[2] = CEC_OP_RECORD_SRC_DIGITAL; - cec_set_digital_service_id(msg->msg + 3, digital); -} - -static inline void cec_msg_record_on_analog(struct cec_msg *msg, - __u8 ana_bcast_type, - __u16 ana_freq, - __u8 bcast_system) -{ - msg->len = 7; - msg->msg[1] = CEC_MSG_RECORD_ON; - msg->msg[2] = CEC_OP_RECORD_SRC_ANALOG; - msg->msg[3] = ana_bcast_type; - msg->msg[4] = ana_freq >> 8; - msg->msg[5] = ana_freq & 0xff; - msg->msg[6] = bcast_system; -} - -static inline void cec_msg_record_on_plug(struct cec_msg *msg, - __u8 plug) -{ - msg->len = 4; - msg->msg[1] = CEC_MSG_RECORD_ON; - msg->msg[2] = CEC_OP_RECORD_SRC_EXT_PLUG; - msg->msg[3] = plug; -} - -static inline void cec_msg_record_on_phys_addr(struct cec_msg *msg, - __u16 phys_addr) -{ - msg->len = 5; - msg->msg[1] = CEC_MSG_RECORD_ON; - msg->msg[2] = CEC_OP_RECORD_SRC_EXT_PHYS_ADDR; - msg->msg[3] = phys_addr >> 8; - msg->msg[4] = phys_addr & 0xff; -} - -static inline void cec_msg_record_on(struct cec_msg *msg, - bool reply, - const struct cec_op_record_src *rec_src) -{ - switch (rec_src->type) { - case CEC_OP_RECORD_SRC_OWN: - cec_msg_record_on_own(msg); - break; - case CEC_OP_RECORD_SRC_DIGITAL: - cec_msg_record_on_digital(msg, &rec_src->digital); - break; - case CEC_OP_RECORD_SRC_ANALOG: - cec_msg_record_on_analog(msg, - rec_src->analog.ana_bcast_type, - rec_src->analog.ana_freq, - rec_src->analog.bcast_system); - break; - case CEC_OP_RECORD_SRC_EXT_PLUG: - cec_msg_record_on_plug(msg, rec_src->ext_plug.plug); - break; - case CEC_OP_RECORD_SRC_EXT_PHYS_ADDR: - cec_msg_record_on_phys_addr(msg, - rec_src->ext_phys_addr.phys_addr); - break; - } - msg->reply = reply ? CEC_MSG_RECORD_STATUS : 0; -} - -static inline void cec_ops_record_on(const struct cec_msg *msg, - struct cec_op_record_src *rec_src) -{ - rec_src->type = msg->msg[2]; - switch (rec_src->type) { - case CEC_OP_RECORD_SRC_OWN: - break; - case CEC_OP_RECORD_SRC_DIGITAL: - cec_get_digital_service_id(msg->msg + 3, &rec_src->digital); - break; - case CEC_OP_RECORD_SRC_ANALOG: - rec_src->analog.ana_bcast_type = msg->msg[3]; - rec_src->analog.ana_freq = - (msg->msg[4] << 8) | msg->msg[5]; - rec_src->analog.bcast_system = msg->msg[6]; - break; - case CEC_OP_RECORD_SRC_EXT_PLUG: - rec_src->ext_plug.plug = msg->msg[3]; - break; - case CEC_OP_RECORD_SRC_EXT_PHYS_ADDR: - rec_src->ext_phys_addr.phys_addr = - (msg->msg[3] << 8) | msg->msg[4]; - break; - } -} - -static inline void cec_msg_record_status(struct cec_msg *msg, __u8 rec_status) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_RECORD_STATUS; - msg->msg[2] = rec_status; -} - -static inline void cec_ops_record_status(const struct cec_msg *msg, - __u8 *rec_status) -{ - *rec_status = msg->msg[2]; -} - -static inline void cec_msg_record_tv_screen(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_RECORD_TV_SCREEN; - msg->reply = reply ? CEC_MSG_RECORD_ON : 0; -} - - -/* Timer Programming Feature */ -static inline void cec_msg_timer_status(struct cec_msg *msg, - __u8 timer_overlap_warning, - __u8 media_info, - __u8 prog_info, - __u8 prog_error, - __u8 duration_hr, - __u8 duration_min) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_TIMER_STATUS; - msg->msg[2] = (timer_overlap_warning << 7) | - (media_info << 5) | - (prog_info ? 0x10 : 0) | - (prog_info ? prog_info : prog_error); - if (prog_info == CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE || - prog_info == CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE || - prog_error == CEC_OP_PROG_ERROR_DUPLICATE) { - msg->len += 2; - msg->msg[3] = ((duration_hr / 10) << 4) | (duration_hr % 10); - msg->msg[4] = ((duration_min / 10) << 4) | (duration_min % 10); - } -} - -static inline void cec_ops_timer_status(const struct cec_msg *msg, - __u8 *timer_overlap_warning, - __u8 *media_info, - __u8 *prog_info, - __u8 *prog_error, - __u8 *duration_hr, - __u8 *duration_min) -{ - *timer_overlap_warning = msg->msg[2] >> 7; - *media_info = (msg->msg[2] >> 5) & 3; - if (msg->msg[2] & 0x10) { - *prog_info = msg->msg[2] & 0xf; - *prog_error = 0; - } else { - *prog_info = 0; - *prog_error = msg->msg[2] & 0xf; - } - if (*prog_info == CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE || - *prog_info == CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE || - *prog_error == CEC_OP_PROG_ERROR_DUPLICATE) { - *duration_hr = (msg->msg[3] >> 4) * 10 + (msg->msg[3] & 0xf); - *duration_min = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); - } else { - *duration_hr = *duration_min = 0; - } -} - -static inline void cec_msg_timer_cleared_status(struct cec_msg *msg, - __u8 timer_cleared_status) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_TIMER_CLEARED_STATUS; - msg->msg[2] = timer_cleared_status; -} - -static inline void cec_ops_timer_cleared_status(const struct cec_msg *msg, - __u8 *timer_cleared_status) -{ - *timer_cleared_status = msg->msg[2]; -} - -static inline void cec_msg_clear_analogue_timer(struct cec_msg *msg, - bool reply, - __u8 day, - __u8 month, - __u8 start_hr, - __u8 start_min, - __u8 duration_hr, - __u8 duration_min, - __u8 recording_seq, - __u8 ana_bcast_type, - __u16 ana_freq, - __u8 bcast_system) -{ - msg->len = 13; - msg->msg[1] = CEC_MSG_CLEAR_ANALOGUE_TIMER; - msg->msg[2] = day; - msg->msg[3] = month; - /* Hours and minutes are in BCD format */ - msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); - msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); - msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); - msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); - msg->msg[8] = recording_seq; - msg->msg[9] = ana_bcast_type; - msg->msg[10] = ana_freq >> 8; - msg->msg[11] = ana_freq & 0xff; - msg->msg[12] = bcast_system; - msg->reply = reply ? CEC_MSG_TIMER_CLEARED_STATUS : 0; -} - -static inline void cec_ops_clear_analogue_timer(const struct cec_msg *msg, - __u8 *day, - __u8 *month, - __u8 *start_hr, - __u8 *start_min, - __u8 *duration_hr, - __u8 *duration_min, - __u8 *recording_seq, - __u8 *ana_bcast_type, - __u16 *ana_freq, - __u8 *bcast_system) -{ - *day = msg->msg[2]; - *month = msg->msg[3]; - /* Hours and minutes are in BCD format */ - *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); - *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); - *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); - *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); - *recording_seq = msg->msg[8]; - *ana_bcast_type = msg->msg[9]; - *ana_freq = (msg->msg[10] << 8) | msg->msg[11]; - *bcast_system = msg->msg[12]; -} - -static inline void cec_msg_clear_digital_timer(struct cec_msg *msg, - bool reply, - __u8 day, - __u8 month, - __u8 start_hr, - __u8 start_min, - __u8 duration_hr, - __u8 duration_min, - __u8 recording_seq, - const struct cec_op_digital_service_id *digital) -{ - msg->len = 16; - msg->reply = reply ? CEC_MSG_TIMER_CLEARED_STATUS : 0; - msg->msg[1] = CEC_MSG_CLEAR_DIGITAL_TIMER; - msg->msg[2] = day; - msg->msg[3] = month; - /* Hours and minutes are in BCD format */ - msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); - msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); - msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); - msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); - msg->msg[8] = recording_seq; - cec_set_digital_service_id(msg->msg + 9, digital); -} - -static inline void cec_ops_clear_digital_timer(const struct cec_msg *msg, - __u8 *day, - __u8 *month, - __u8 *start_hr, - __u8 *start_min, - __u8 *duration_hr, - __u8 *duration_min, - __u8 *recording_seq, - struct cec_op_digital_service_id *digital) -{ - *day = msg->msg[2]; - *month = msg->msg[3]; - /* Hours and minutes are in BCD format */ - *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); - *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); - *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); - *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); - *recording_seq = msg->msg[8]; - cec_get_digital_service_id(msg->msg + 9, digital); -} - -static inline void cec_msg_clear_ext_timer(struct cec_msg *msg, - bool reply, - __u8 day, - __u8 month, - __u8 start_hr, - __u8 start_min, - __u8 duration_hr, - __u8 duration_min, - __u8 recording_seq, - __u8 ext_src_spec, - __u8 plug, - __u16 phys_addr) -{ - msg->len = 13; - msg->msg[1] = CEC_MSG_CLEAR_EXT_TIMER; - msg->msg[2] = day; - msg->msg[3] = month; - /* Hours and minutes are in BCD format */ - msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); - msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); - msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); - msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); - msg->msg[8] = recording_seq; - msg->msg[9] = ext_src_spec; - msg->msg[10] = plug; - msg->msg[11] = phys_addr >> 8; - msg->msg[12] = phys_addr & 0xff; - msg->reply = reply ? CEC_MSG_TIMER_CLEARED_STATUS : 0; -} - -static inline void cec_ops_clear_ext_timer(const struct cec_msg *msg, - __u8 *day, - __u8 *month, - __u8 *start_hr, - __u8 *start_min, - __u8 *duration_hr, - __u8 *duration_min, - __u8 *recording_seq, - __u8 *ext_src_spec, - __u8 *plug, - __u16 *phys_addr) -{ - *day = msg->msg[2]; - *month = msg->msg[3]; - /* Hours and minutes are in BCD format */ - *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); - *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); - *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); - *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); - *recording_seq = msg->msg[8]; - *ext_src_spec = msg->msg[9]; - *plug = msg->msg[10]; - *phys_addr = (msg->msg[11] << 8) | msg->msg[12]; -} - -static inline void cec_msg_set_analogue_timer(struct cec_msg *msg, - bool reply, - __u8 day, - __u8 month, - __u8 start_hr, - __u8 start_min, - __u8 duration_hr, - __u8 duration_min, - __u8 recording_seq, - __u8 ana_bcast_type, - __u16 ana_freq, - __u8 bcast_system) -{ - msg->len = 13; - msg->msg[1] = CEC_MSG_SET_ANALOGUE_TIMER; - msg->msg[2] = day; - msg->msg[3] = month; - /* Hours and minutes are in BCD format */ - msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); - msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); - msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); - msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); - msg->msg[8] = recording_seq; - msg->msg[9] = ana_bcast_type; - msg->msg[10] = ana_freq >> 8; - msg->msg[11] = ana_freq & 0xff; - msg->msg[12] = bcast_system; - msg->reply = reply ? CEC_MSG_TIMER_STATUS : 0; -} - -static inline void cec_ops_set_analogue_timer(const struct cec_msg *msg, - __u8 *day, - __u8 *month, - __u8 *start_hr, - __u8 *start_min, - __u8 *duration_hr, - __u8 *duration_min, - __u8 *recording_seq, - __u8 *ana_bcast_type, - __u16 *ana_freq, - __u8 *bcast_system) -{ - *day = msg->msg[2]; - *month = msg->msg[3]; - /* Hours and minutes are in BCD format */ - *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); - *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); - *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); - *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); - *recording_seq = msg->msg[8]; - *ana_bcast_type = msg->msg[9]; - *ana_freq = (msg->msg[10] << 8) | msg->msg[11]; - *bcast_system = msg->msg[12]; -} - -static inline void cec_msg_set_digital_timer(struct cec_msg *msg, - bool reply, - __u8 day, - __u8 month, - __u8 start_hr, - __u8 start_min, - __u8 duration_hr, - __u8 duration_min, - __u8 recording_seq, - const struct cec_op_digital_service_id *digital) -{ - msg->len = 16; - msg->reply = reply ? CEC_MSG_TIMER_STATUS : 0; - msg->msg[1] = CEC_MSG_SET_DIGITAL_TIMER; - msg->msg[2] = day; - msg->msg[3] = month; - /* Hours and minutes are in BCD format */ - msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); - msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); - msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); - msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); - msg->msg[8] = recording_seq; - cec_set_digital_service_id(msg->msg + 9, digital); -} - -static inline void cec_ops_set_digital_timer(const struct cec_msg *msg, - __u8 *day, - __u8 *month, - __u8 *start_hr, - __u8 *start_min, - __u8 *duration_hr, - __u8 *duration_min, - __u8 *recording_seq, - struct cec_op_digital_service_id *digital) -{ - *day = msg->msg[2]; - *month = msg->msg[3]; - /* Hours and minutes are in BCD format */ - *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); - *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); - *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); - *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); - *recording_seq = msg->msg[8]; - cec_get_digital_service_id(msg->msg + 9, digital); -} - -static inline void cec_msg_set_ext_timer(struct cec_msg *msg, - bool reply, - __u8 day, - __u8 month, - __u8 start_hr, - __u8 start_min, - __u8 duration_hr, - __u8 duration_min, - __u8 recording_seq, - __u8 ext_src_spec, - __u8 plug, - __u16 phys_addr) -{ - msg->len = 13; - msg->msg[1] = CEC_MSG_SET_EXT_TIMER; - msg->msg[2] = day; - msg->msg[3] = month; - /* Hours and minutes are in BCD format */ - msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); - msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); - msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); - msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); - msg->msg[8] = recording_seq; - msg->msg[9] = ext_src_spec; - msg->msg[10] = plug; - msg->msg[11] = phys_addr >> 8; - msg->msg[12] = phys_addr & 0xff; - msg->reply = reply ? CEC_MSG_TIMER_STATUS : 0; -} - -static inline void cec_ops_set_ext_timer(const struct cec_msg *msg, - __u8 *day, - __u8 *month, - __u8 *start_hr, - __u8 *start_min, - __u8 *duration_hr, - __u8 *duration_min, - __u8 *recording_seq, - __u8 *ext_src_spec, - __u8 *plug, - __u16 *phys_addr) -{ - *day = msg->msg[2]; - *month = msg->msg[3]; - /* Hours and minutes are in BCD format */ - *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); - *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); - *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); - *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); - *recording_seq = msg->msg[8]; - *ext_src_spec = msg->msg[9]; - *plug = msg->msg[10]; - *phys_addr = (msg->msg[11] << 8) | msg->msg[12]; -} - -static inline void cec_msg_set_timer_program_title(struct cec_msg *msg, - const char *prog_title) -{ - unsigned int len = strlen(prog_title); - - if (len > 14) - len = 14; - msg->len = 2 + len; - msg->msg[1] = CEC_MSG_SET_TIMER_PROGRAM_TITLE; - memcpy(msg->msg + 2, prog_title, len); -} - -static inline void cec_ops_set_timer_program_title(const struct cec_msg *msg, - char *prog_title) -{ - unsigned int len = msg->len > 2 ? msg->len - 2 : 0; - - if (len > 14) - len = 14; - memcpy(prog_title, msg->msg + 2, len); - prog_title[len] = '\0'; -} - -/* System Information Feature */ -static inline void cec_msg_cec_version(struct cec_msg *msg, __u8 cec_version) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_CEC_VERSION; - msg->msg[2] = cec_version; -} - -static inline void cec_ops_cec_version(const struct cec_msg *msg, - __u8 *cec_version) -{ - *cec_version = msg->msg[2]; -} - -static inline void cec_msg_get_cec_version(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_GET_CEC_VERSION; - msg->reply = reply ? CEC_MSG_CEC_VERSION : 0; -} - -static inline void cec_msg_report_physical_addr(struct cec_msg *msg, - __u16 phys_addr, __u8 prim_devtype) -{ - msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_REPORT_PHYSICAL_ADDR; - msg->msg[2] = phys_addr >> 8; - msg->msg[3] = phys_addr & 0xff; - msg->msg[4] = prim_devtype; -} - -static inline void cec_ops_report_physical_addr(const struct cec_msg *msg, - __u16 *phys_addr, __u8 *prim_devtype) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *prim_devtype = msg->msg[4]; -} - -static inline void cec_msg_give_physical_addr(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_GIVE_PHYSICAL_ADDR; - msg->reply = reply ? CEC_MSG_REPORT_PHYSICAL_ADDR : 0; -} - -static inline void cec_msg_set_menu_language(struct cec_msg *msg, - const char *language) -{ - msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_SET_MENU_LANGUAGE; - memcpy(msg->msg + 2, language, 3); -} - -static inline void cec_ops_set_menu_language(const struct cec_msg *msg, - char *language) -{ - memcpy(language, msg->msg + 2, 3); - language[3] = '\0'; -} - -static inline void cec_msg_get_menu_language(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_GET_MENU_LANGUAGE; - msg->reply = reply ? CEC_MSG_SET_MENU_LANGUAGE : 0; -} - -/* - * Assumes a single RC Profile byte and a single Device Features byte, - * i.e. no extended features are supported by this helper function. - * - * As of CEC 2.0 no extended features are defined, should those be added - * in the future, then this function needs to be adapted or a new function - * should be added. - */ -static inline void cec_msg_report_features(struct cec_msg *msg, - __u8 cec_version, __u8 all_device_types, - __u8 rc_profile, __u8 dev_features) -{ - msg->len = 6; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_REPORT_FEATURES; - msg->msg[2] = cec_version; - msg->msg[3] = all_device_types; - msg->msg[4] = rc_profile; - msg->msg[5] = dev_features; -} - -static inline void cec_ops_report_features(const struct cec_msg *msg, - __u8 *cec_version, __u8 *all_device_types, - const __u8 **rc_profile, const __u8 **dev_features) -{ - const __u8 *p = &msg->msg[4]; - - *cec_version = msg->msg[2]; - *all_device_types = msg->msg[3]; - *rc_profile = p; - while (p < &msg->msg[14] && (*p & CEC_OP_FEAT_EXT)) - p++; - if (!(*p & CEC_OP_FEAT_EXT)) { - *dev_features = p + 1; - while (p < &msg->msg[15] && (*p & CEC_OP_FEAT_EXT)) - p++; - } - if (*p & CEC_OP_FEAT_EXT) - *rc_profile = *dev_features = NULL; -} - -static inline void cec_msg_give_features(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_GIVE_FEATURES; - msg->reply = reply ? CEC_MSG_REPORT_FEATURES : 0; -} - -/* Deck Control Feature */ -static inline void cec_msg_deck_control(struct cec_msg *msg, - __u8 deck_control_mode) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_DECK_CONTROL; - msg->msg[2] = deck_control_mode; -} - -static inline void cec_ops_deck_control(const struct cec_msg *msg, - __u8 *deck_control_mode) -{ - *deck_control_mode = msg->msg[2]; -} - -static inline void cec_msg_deck_status(struct cec_msg *msg, - __u8 deck_info) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_DECK_STATUS; - msg->msg[2] = deck_info; -} - -static inline void cec_ops_deck_status(const struct cec_msg *msg, - __u8 *deck_info) -{ - *deck_info = msg->msg[2]; -} - -static inline void cec_msg_give_deck_status(struct cec_msg *msg, - bool reply, - __u8 status_req) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_GIVE_DECK_STATUS; - msg->msg[2] = status_req; - msg->reply = reply ? CEC_MSG_DECK_STATUS : 0; -} - -static inline void cec_ops_give_deck_status(const struct cec_msg *msg, - __u8 *status_req) -{ - *status_req = msg->msg[2]; -} - -static inline void cec_msg_play(struct cec_msg *msg, - __u8 play_mode) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_PLAY; - msg->msg[2] = play_mode; -} - -static inline void cec_ops_play(const struct cec_msg *msg, - __u8 *play_mode) -{ - *play_mode = msg->msg[2]; -} - - -/* Tuner Control Feature */ -struct cec_op_tuner_device_info { - __u8 rec_flag; - __u8 tuner_display_info; - bool is_analog; - union { - struct cec_op_digital_service_id digital; - struct { - __u8 ana_bcast_type; - __u16 ana_freq; - __u8 bcast_system; - } analog; - }; -}; - -static inline void cec_msg_tuner_device_status_analog(struct cec_msg *msg, - __u8 rec_flag, - __u8 tuner_display_info, - __u8 ana_bcast_type, - __u16 ana_freq, - __u8 bcast_system) -{ - msg->len = 7; - msg->msg[1] = CEC_MSG_TUNER_DEVICE_STATUS; - msg->msg[2] = (rec_flag << 7) | tuner_display_info; - msg->msg[3] = ana_bcast_type; - msg->msg[4] = ana_freq >> 8; - msg->msg[5] = ana_freq & 0xff; - msg->msg[6] = bcast_system; -} - -static inline void cec_msg_tuner_device_status_digital(struct cec_msg *msg, - __u8 rec_flag, __u8 tuner_display_info, - const struct cec_op_digital_service_id *digital) -{ - msg->len = 10; - msg->msg[1] = CEC_MSG_TUNER_DEVICE_STATUS; - msg->msg[2] = (rec_flag << 7) | tuner_display_info; - cec_set_digital_service_id(msg->msg + 3, digital); -} - -static inline void cec_msg_tuner_device_status(struct cec_msg *msg, - const struct cec_op_tuner_device_info *tuner_dev_info) -{ - if (tuner_dev_info->is_analog) - cec_msg_tuner_device_status_analog(msg, - tuner_dev_info->rec_flag, - tuner_dev_info->tuner_display_info, - tuner_dev_info->analog.ana_bcast_type, - tuner_dev_info->analog.ana_freq, - tuner_dev_info->analog.bcast_system); - else - cec_msg_tuner_device_status_digital(msg, - tuner_dev_info->rec_flag, - tuner_dev_info->tuner_display_info, - &tuner_dev_info->digital); -} - -static inline void cec_ops_tuner_device_status(const struct cec_msg *msg, - struct cec_op_tuner_device_info *tuner_dev_info) -{ - tuner_dev_info->is_analog = msg->len < 10; - tuner_dev_info->rec_flag = msg->msg[2] >> 7; - tuner_dev_info->tuner_display_info = msg->msg[2] & 0x7f; - if (tuner_dev_info->is_analog) { - tuner_dev_info->analog.ana_bcast_type = msg->msg[3]; - tuner_dev_info->analog.ana_freq = (msg->msg[4] << 8) | msg->msg[5]; - tuner_dev_info->analog.bcast_system = msg->msg[6]; - return; - } - cec_get_digital_service_id(msg->msg + 3, &tuner_dev_info->digital); -} - -static inline void cec_msg_give_tuner_device_status(struct cec_msg *msg, - bool reply, - __u8 status_req) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_GIVE_TUNER_DEVICE_STATUS; - msg->msg[2] = status_req; - msg->reply = reply ? CEC_MSG_TUNER_DEVICE_STATUS : 0; -} - -static inline void cec_ops_give_tuner_device_status(const struct cec_msg *msg, - __u8 *status_req) -{ - *status_req = msg->msg[2]; -} - -static inline void cec_msg_select_analogue_service(struct cec_msg *msg, - __u8 ana_bcast_type, - __u16 ana_freq, - __u8 bcast_system) -{ - msg->len = 6; - msg->msg[1] = CEC_MSG_SELECT_ANALOGUE_SERVICE; - msg->msg[2] = ana_bcast_type; - msg->msg[3] = ana_freq >> 8; - msg->msg[4] = ana_freq & 0xff; - msg->msg[5] = bcast_system; -} - -static inline void cec_ops_select_analogue_service(const struct cec_msg *msg, - __u8 *ana_bcast_type, - __u16 *ana_freq, - __u8 *bcast_system) -{ - *ana_bcast_type = msg->msg[2]; - *ana_freq = (msg->msg[3] << 8) | msg->msg[4]; - *bcast_system = msg->msg[5]; -} - -static inline void cec_msg_select_digital_service(struct cec_msg *msg, - const struct cec_op_digital_service_id *digital) -{ - msg->len = 9; - msg->msg[1] = CEC_MSG_SELECT_DIGITAL_SERVICE; - cec_set_digital_service_id(msg->msg + 2, digital); -} - -static inline void cec_ops_select_digital_service(const struct cec_msg *msg, - struct cec_op_digital_service_id *digital) -{ - cec_get_digital_service_id(msg->msg + 2, digital); -} - -static inline void cec_msg_tuner_step_decrement(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_TUNER_STEP_DECREMENT; -} - -static inline void cec_msg_tuner_step_increment(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_TUNER_STEP_INCREMENT; -} - - -/* Vendor Specific Commands Feature */ -static inline void cec_msg_device_vendor_id(struct cec_msg *msg, __u32 vendor_id) -{ - msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_DEVICE_VENDOR_ID; - msg->msg[2] = vendor_id >> 16; - msg->msg[3] = (vendor_id >> 8) & 0xff; - msg->msg[4] = vendor_id & 0xff; -} - -static inline void cec_ops_device_vendor_id(const struct cec_msg *msg, - __u32 *vendor_id) -{ - *vendor_id = (msg->msg[2] << 16) | (msg->msg[3] << 8) | msg->msg[4]; -} - -static inline void cec_msg_give_device_vendor_id(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_GIVE_DEVICE_VENDOR_ID; - msg->reply = reply ? CEC_MSG_DEVICE_VENDOR_ID : 0; -} - -static inline void cec_msg_vendor_command(struct cec_msg *msg, - __u8 size, const __u8 *vendor_cmd) -{ - if (size > 14) - size = 14; - msg->len = 2 + size; - msg->msg[1] = CEC_MSG_VENDOR_COMMAND; - memcpy(msg->msg + 2, vendor_cmd, size); -} - -static inline void cec_ops_vendor_command(const struct cec_msg *msg, - __u8 *size, - const __u8 **vendor_cmd) -{ - *size = msg->len - 2; - - if (*size > 14) - *size = 14; - *vendor_cmd = msg->msg + 2; -} - -static inline void cec_msg_vendor_command_with_id(struct cec_msg *msg, - __u32 vendor_id, __u8 size, - const __u8 *vendor_cmd) -{ - if (size > 11) - size = 11; - msg->len = 5 + size; - msg->msg[1] = CEC_MSG_VENDOR_COMMAND_WITH_ID; - msg->msg[2] = vendor_id >> 16; - msg->msg[3] = (vendor_id >> 8) & 0xff; - msg->msg[4] = vendor_id & 0xff; - memcpy(msg->msg + 5, vendor_cmd, size); -} - -static inline void cec_ops_vendor_command_with_id(const struct cec_msg *msg, - __u32 *vendor_id, __u8 *size, - const __u8 **vendor_cmd) -{ - *size = msg->len - 5; - - if (*size > 11) - *size = 11; - *vendor_id = (msg->msg[2] << 16) | (msg->msg[3] << 8) | msg->msg[4]; - *vendor_cmd = msg->msg + 5; -} - -static inline void cec_msg_vendor_remote_button_down(struct cec_msg *msg, - __u8 size, - const __u8 *rc_code) -{ - if (size > 14) - size = 14; - msg->len = 2 + size; - msg->msg[1] = CEC_MSG_VENDOR_REMOTE_BUTTON_DOWN; - memcpy(msg->msg + 2, rc_code, size); -} - -static inline void cec_ops_vendor_remote_button_down(const struct cec_msg *msg, - __u8 *size, - const __u8 **rc_code) -{ - *size = msg->len - 2; - - if (*size > 14) - *size = 14; - *rc_code = msg->msg + 2; -} - -static inline void cec_msg_vendor_remote_button_up(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_VENDOR_REMOTE_BUTTON_UP; -} - - -/* OSD Display Feature */ -static inline void cec_msg_set_osd_string(struct cec_msg *msg, - __u8 disp_ctl, - const char *osd) -{ - unsigned int len = strlen(osd); - - if (len > 13) - len = 13; - msg->len = 3 + len; - msg->msg[1] = CEC_MSG_SET_OSD_STRING; - msg->msg[2] = disp_ctl; - memcpy(msg->msg + 3, osd, len); -} - -static inline void cec_ops_set_osd_string(const struct cec_msg *msg, - __u8 *disp_ctl, - char *osd) -{ - unsigned int len = msg->len > 3 ? msg->len - 3 : 0; - - *disp_ctl = msg->msg[2]; - if (len > 13) - len = 13; - memcpy(osd, msg->msg + 3, len); - osd[len] = '\0'; -} - - -/* Device OSD Transfer Feature */ -static inline void cec_msg_set_osd_name(struct cec_msg *msg, const char *name) -{ - unsigned int len = strlen(name); - - if (len > 14) - len = 14; - msg->len = 2 + len; - msg->msg[1] = CEC_MSG_SET_OSD_NAME; - memcpy(msg->msg + 2, name, len); -} - -static inline void cec_ops_set_osd_name(const struct cec_msg *msg, - char *name) -{ - unsigned int len = msg->len > 2 ? msg->len - 2 : 0; - - if (len > 14) - len = 14; - memcpy(name, msg->msg + 2, len); - name[len] = '\0'; -} - -static inline void cec_msg_give_osd_name(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_GIVE_OSD_NAME; - msg->reply = reply ? CEC_MSG_SET_OSD_NAME : 0; -} - - -/* Device Menu Control Feature */ -static inline void cec_msg_menu_status(struct cec_msg *msg, - __u8 menu_state) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_MENU_STATUS; - msg->msg[2] = menu_state; -} - -static inline void cec_ops_menu_status(const struct cec_msg *msg, - __u8 *menu_state) -{ - *menu_state = msg->msg[2]; -} - -static inline void cec_msg_menu_request(struct cec_msg *msg, - bool reply, - __u8 menu_req) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_MENU_REQUEST; - msg->msg[2] = menu_req; - msg->reply = reply ? CEC_MSG_MENU_STATUS : 0; -} - -static inline void cec_ops_menu_request(const struct cec_msg *msg, - __u8 *menu_req) -{ - *menu_req = msg->msg[2]; -} - -struct cec_op_ui_command { - __u8 ui_cmd; - bool has_opt_arg; - union { - struct cec_op_channel_data channel_identifier; - __u8 ui_broadcast_type; - __u8 ui_sound_presentation_control; - __u8 play_mode; - __u8 ui_function_media; - __u8 ui_function_select_av_input; - __u8 ui_function_select_audio_input; - }; -}; - -static inline void cec_msg_user_control_pressed(struct cec_msg *msg, - const struct cec_op_ui_command *ui_cmd) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_USER_CONTROL_PRESSED; - msg->msg[2] = ui_cmd->ui_cmd; - if (!ui_cmd->has_opt_arg) - return; - switch (ui_cmd->ui_cmd) { - case 0x56: - case 0x57: - case 0x60: - case 0x68: - case 0x69: - case 0x6a: - /* The optional operand is one byte for all these ui commands */ - msg->len++; - msg->msg[3] = ui_cmd->play_mode; - break; - case 0x67: - msg->len += 4; - msg->msg[3] = (ui_cmd->channel_identifier.channel_number_fmt << 2) | - (ui_cmd->channel_identifier.major >> 8); - msg->msg[4] = ui_cmd->channel_identifier.major & 0xff; - msg->msg[5] = ui_cmd->channel_identifier.minor >> 8; - msg->msg[6] = ui_cmd->channel_identifier.minor & 0xff; - break; - } -} - -static inline void cec_ops_user_control_pressed(const struct cec_msg *msg, - struct cec_op_ui_command *ui_cmd) -{ - ui_cmd->ui_cmd = msg->msg[2]; - ui_cmd->has_opt_arg = false; - if (msg->len == 3) - return; - switch (ui_cmd->ui_cmd) { - case 0x56: - case 0x57: - case 0x60: - case 0x68: - case 0x69: - case 0x6a: - /* The optional operand is one byte for all these ui commands */ - ui_cmd->play_mode = msg->msg[3]; - ui_cmd->has_opt_arg = true; - break; - case 0x67: - if (msg->len < 7) - break; - ui_cmd->has_opt_arg = true; - ui_cmd->channel_identifier.channel_number_fmt = msg->msg[3] >> 2; - ui_cmd->channel_identifier.major = ((msg->msg[3] & 3) << 6) | msg->msg[4]; - ui_cmd->channel_identifier.minor = (msg->msg[5] << 8) | msg->msg[6]; - break; - } -} - -static inline void cec_msg_user_control_released(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_USER_CONTROL_RELEASED; -} - -/* Remote Control Passthrough Feature */ - -/* Power Status Feature */ -static inline void cec_msg_report_power_status(struct cec_msg *msg, - __u8 pwr_state) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_REPORT_POWER_STATUS; - msg->msg[2] = pwr_state; -} - -static inline void cec_ops_report_power_status(const struct cec_msg *msg, - __u8 *pwr_state) -{ - *pwr_state = msg->msg[2]; -} - -static inline void cec_msg_give_device_power_status(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_GIVE_DEVICE_POWER_STATUS; - msg->reply = reply ? CEC_MSG_REPORT_POWER_STATUS : 0; -} - -/* General Protocol Messages */ -static inline void cec_msg_feature_abort(struct cec_msg *msg, - __u8 abort_msg, __u8 reason) -{ - msg->len = 4; - msg->msg[1] = CEC_MSG_FEATURE_ABORT; - msg->msg[2] = abort_msg; - msg->msg[3] = reason; -} - -static inline void cec_ops_feature_abort(const struct cec_msg *msg, - __u8 *abort_msg, __u8 *reason) -{ - *abort_msg = msg->msg[2]; - *reason = msg->msg[3]; -} - -/* This changes the current message into a feature abort message */ -static inline void cec_msg_reply_feature_abort(struct cec_msg *msg, __u8 reason) -{ - cec_msg_set_reply_to(msg, msg); - msg->len = 4; - msg->msg[2] = msg->msg[1]; - msg->msg[3] = reason; - msg->msg[1] = CEC_MSG_FEATURE_ABORT; -} - -static inline void cec_msg_abort(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_ABORT; -} - - -/* System Audio Control Feature */ -static inline void cec_msg_report_audio_status(struct cec_msg *msg, - __u8 aud_mute_status, - __u8 aud_vol_status) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_REPORT_AUDIO_STATUS; - msg->msg[2] = (aud_mute_status << 7) | (aud_vol_status & 0x7f); -} - -static inline void cec_ops_report_audio_status(const struct cec_msg *msg, - __u8 *aud_mute_status, - __u8 *aud_vol_status) -{ - *aud_mute_status = msg->msg[2] >> 7; - *aud_vol_status = msg->msg[2] & 0x7f; -} - -static inline void cec_msg_give_audio_status(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_GIVE_AUDIO_STATUS; - msg->reply = reply ? CEC_MSG_REPORT_AUDIO_STATUS : 0; -} - -static inline void cec_msg_set_system_audio_mode(struct cec_msg *msg, - __u8 sys_aud_status) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_SET_SYSTEM_AUDIO_MODE; - msg->msg[2] = sys_aud_status; -} - -static inline void cec_ops_set_system_audio_mode(const struct cec_msg *msg, - __u8 *sys_aud_status) -{ - *sys_aud_status = msg->msg[2]; -} - -static inline void cec_msg_system_audio_mode_request(struct cec_msg *msg, - bool reply, - __u16 phys_addr) -{ - msg->len = phys_addr == 0xffff ? 2 : 4; - msg->msg[1] = CEC_MSG_SYSTEM_AUDIO_MODE_REQUEST; - msg->msg[2] = phys_addr >> 8; - msg->msg[3] = phys_addr & 0xff; - msg->reply = reply ? CEC_MSG_SET_SYSTEM_AUDIO_MODE : 0; - -} - -static inline void cec_ops_system_audio_mode_request(const struct cec_msg *msg, - __u16 *phys_addr) -{ - if (msg->len < 4) - *phys_addr = 0xffff; - else - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; -} - -static inline void cec_msg_system_audio_mode_status(struct cec_msg *msg, - __u8 sys_aud_status) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_SYSTEM_AUDIO_MODE_STATUS; - msg->msg[2] = sys_aud_status; -} - -static inline void cec_ops_system_audio_mode_status(const struct cec_msg *msg, - __u8 *sys_aud_status) -{ - *sys_aud_status = msg->msg[2]; -} - -static inline void cec_msg_give_system_audio_mode_status(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_GIVE_SYSTEM_AUDIO_MODE_STATUS; - msg->reply = reply ? CEC_MSG_SYSTEM_AUDIO_MODE_STATUS : 0; -} - -static inline void cec_msg_report_short_audio_descriptor(struct cec_msg *msg, - __u8 num_descriptors, - const __u32 *descriptors) -{ - unsigned int i; - - if (num_descriptors > 4) - num_descriptors = 4; - msg->len = 2 + num_descriptors * 3; - msg->msg[1] = CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR; - for (i = 0; i < num_descriptors; i++) { - msg->msg[2 + i * 3] = (descriptors[i] >> 16) & 0xff; - msg->msg[3 + i * 3] = (descriptors[i] >> 8) & 0xff; - msg->msg[4 + i * 3] = descriptors[i] & 0xff; - } -} - -static inline void cec_ops_report_short_audio_descriptor(const struct cec_msg *msg, - __u8 *num_descriptors, - __u32 *descriptors) -{ - unsigned int i; - - *num_descriptors = (msg->len - 2) / 3; - if (*num_descriptors > 4) - *num_descriptors = 4; - for (i = 0; i < *num_descriptors; i++) - descriptors[i] = (msg->msg[2 + i * 3] << 16) | - (msg->msg[3 + i * 3] << 8) | - msg->msg[4 + i * 3]; -} - -static inline void cec_msg_request_short_audio_descriptor(struct cec_msg *msg, - bool reply, - __u8 num_descriptors, - const __u8 *audio_format_id, - const __u8 *audio_format_code) -{ - unsigned int i; - - if (num_descriptors > 4) - num_descriptors = 4; - msg->len = 2 + num_descriptors; - msg->msg[1] = CEC_MSG_REQUEST_SHORT_AUDIO_DESCRIPTOR; - msg->reply = reply ? CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR : 0; - for (i = 0; i < num_descriptors; i++) - msg->msg[2 + i] = (audio_format_id[i] << 6) | - (audio_format_code[i] & 0x3f); -} - -static inline void cec_ops_request_short_audio_descriptor(const struct cec_msg *msg, - __u8 *num_descriptors, - __u8 *audio_format_id, - __u8 *audio_format_code) -{ - unsigned int i; - - *num_descriptors = msg->len - 2; - if (*num_descriptors > 4) - *num_descriptors = 4; - for (i = 0; i < *num_descriptors; i++) { - audio_format_id[i] = msg->msg[2 + i] >> 6; - audio_format_code[i] = msg->msg[2 + i] & 0x3f; - } -} - - -/* Audio Rate Control Feature */ -static inline void cec_msg_set_audio_rate(struct cec_msg *msg, - __u8 audio_rate) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_SET_AUDIO_RATE; - msg->msg[2] = audio_rate; -} - -static inline void cec_ops_set_audio_rate(const struct cec_msg *msg, - __u8 *audio_rate) -{ - *audio_rate = msg->msg[2]; -} - - -/* Audio Return Channel Control Feature */ -static inline void cec_msg_report_arc_initiated(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_REPORT_ARC_INITIATED; -} - -static inline void cec_msg_initiate_arc(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_INITIATE_ARC; - msg->reply = reply ? CEC_MSG_REPORT_ARC_INITIATED : 0; -} - -static inline void cec_msg_request_arc_initiation(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_REQUEST_ARC_INITIATION; - msg->reply = reply ? CEC_MSG_INITIATE_ARC : 0; -} - -static inline void cec_msg_report_arc_terminated(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_REPORT_ARC_TERMINATED; -} - -static inline void cec_msg_terminate_arc(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_TERMINATE_ARC; - msg->reply = reply ? CEC_MSG_REPORT_ARC_TERMINATED : 0; -} - -static inline void cec_msg_request_arc_termination(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_REQUEST_ARC_TERMINATION; - msg->reply = reply ? CEC_MSG_TERMINATE_ARC : 0; -} - - -/* Dynamic Audio Lipsync Feature */ -/* Only for CEC 2.0 and up */ -static inline void cec_msg_report_current_latency(struct cec_msg *msg, - __u16 phys_addr, - __u8 video_latency, - __u8 low_latency_mode, - __u8 audio_out_compensated, - __u8 audio_out_delay) -{ - msg->len = 7; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_REPORT_CURRENT_LATENCY; - msg->msg[2] = phys_addr >> 8; - msg->msg[3] = phys_addr & 0xff; - msg->msg[4] = video_latency; - msg->msg[5] = (low_latency_mode << 2) | audio_out_compensated; - msg->msg[6] = audio_out_delay; -} - -static inline void cec_ops_report_current_latency(const struct cec_msg *msg, - __u16 *phys_addr, - __u8 *video_latency, - __u8 *low_latency_mode, - __u8 *audio_out_compensated, - __u8 *audio_out_delay) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *video_latency = msg->msg[4]; - *low_latency_mode = (msg->msg[5] >> 2) & 1; - *audio_out_compensated = msg->msg[5] & 3; - *audio_out_delay = msg->msg[6]; -} - -static inline void cec_msg_request_current_latency(struct cec_msg *msg, - bool reply, - __u16 phys_addr) -{ - msg->len = 4; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_REQUEST_CURRENT_LATENCY; - msg->msg[2] = phys_addr >> 8; - msg->msg[3] = phys_addr & 0xff; - msg->reply = reply ? CEC_MSG_REPORT_CURRENT_LATENCY : 0; -} - -static inline void cec_ops_request_current_latency(const struct cec_msg *msg, - __u16 *phys_addr) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; -} - - -/* Capability Discovery and Control Feature */ -static inline void cec_msg_cdc_hec_inquire_state(struct cec_msg *msg, - __u16 phys_addr1, - __u16 phys_addr2) -{ - msg->len = 9; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_CDC_MESSAGE; - /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ - msg->msg[4] = CEC_MSG_CDC_HEC_INQUIRE_STATE; - msg->msg[5] = phys_addr1 >> 8; - msg->msg[6] = phys_addr1 & 0xff; - msg->msg[7] = phys_addr2 >> 8; - msg->msg[8] = phys_addr2 & 0xff; -} - -static inline void cec_ops_cdc_hec_inquire_state(const struct cec_msg *msg, - __u16 *phys_addr, - __u16 *phys_addr1, - __u16 *phys_addr2) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *phys_addr1 = (msg->msg[5] << 8) | msg->msg[6]; - *phys_addr2 = (msg->msg[7] << 8) | msg->msg[8]; -} - -static inline void cec_msg_cdc_hec_report_state(struct cec_msg *msg, - __u16 target_phys_addr, - __u8 hec_func_state, - __u8 host_func_state, - __u8 enc_func_state, - __u8 cdc_errcode, - __u8 has_field, - __u16 hec_field) -{ - msg->len = has_field ? 10 : 8; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_CDC_MESSAGE; - /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ - msg->msg[4] = CEC_MSG_CDC_HEC_REPORT_STATE; - msg->msg[5] = target_phys_addr >> 8; - msg->msg[6] = target_phys_addr & 0xff; - msg->msg[7] = (hec_func_state << 6) | - (host_func_state << 4) | - (enc_func_state << 2) | - cdc_errcode; - if (has_field) { - msg->msg[8] = hec_field >> 8; - msg->msg[9] = hec_field & 0xff; - } -} - -static inline void cec_ops_cdc_hec_report_state(const struct cec_msg *msg, - __u16 *phys_addr, - __u16 *target_phys_addr, - __u8 *hec_func_state, - __u8 *host_func_state, - __u8 *enc_func_state, - __u8 *cdc_errcode, - __u8 *has_field, - __u16 *hec_field) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *target_phys_addr = (msg->msg[5] << 8) | msg->msg[6]; - *hec_func_state = msg->msg[7] >> 6; - *host_func_state = (msg->msg[7] >> 4) & 3; - *enc_func_state = (msg->msg[7] >> 4) & 3; - *cdc_errcode = msg->msg[7] & 3; - *has_field = msg->len >= 10; - *hec_field = *has_field ? ((msg->msg[8] << 8) | msg->msg[9]) : 0; -} - -static inline void cec_msg_cdc_hec_set_state(struct cec_msg *msg, - __u16 phys_addr1, - __u16 phys_addr2, - __u8 hec_set_state, - __u16 phys_addr3, - __u16 phys_addr4, - __u16 phys_addr5) -{ - msg->len = 10; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_CDC_MESSAGE; - /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ - msg->msg[4] = CEC_MSG_CDC_HEC_INQUIRE_STATE; - msg->msg[5] = phys_addr1 >> 8; - msg->msg[6] = phys_addr1 & 0xff; - msg->msg[7] = phys_addr2 >> 8; - msg->msg[8] = phys_addr2 & 0xff; - msg->msg[9] = hec_set_state; - if (phys_addr3 != CEC_PHYS_ADDR_INVALID) { - msg->msg[msg->len++] = phys_addr3 >> 8; - msg->msg[msg->len++] = phys_addr3 & 0xff; - if (phys_addr4 != CEC_PHYS_ADDR_INVALID) { - msg->msg[msg->len++] = phys_addr4 >> 8; - msg->msg[msg->len++] = phys_addr4 & 0xff; - if (phys_addr5 != CEC_PHYS_ADDR_INVALID) { - msg->msg[msg->len++] = phys_addr5 >> 8; - msg->msg[msg->len++] = phys_addr5 & 0xff; - } - } - } -} - -static inline void cec_ops_cdc_hec_set_state(const struct cec_msg *msg, - __u16 *phys_addr, - __u16 *phys_addr1, - __u16 *phys_addr2, - __u8 *hec_set_state, - __u16 *phys_addr3, - __u16 *phys_addr4, - __u16 *phys_addr5) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *phys_addr1 = (msg->msg[5] << 8) | msg->msg[6]; - *phys_addr2 = (msg->msg[7] << 8) | msg->msg[8]; - *hec_set_state = msg->msg[9]; - *phys_addr3 = *phys_addr4 = *phys_addr5 = CEC_PHYS_ADDR_INVALID; - if (msg->len >= 12) - *phys_addr3 = (msg->msg[10] << 8) | msg->msg[11]; - if (msg->len >= 14) - *phys_addr4 = (msg->msg[12] << 8) | msg->msg[13]; - if (msg->len >= 16) - *phys_addr5 = (msg->msg[14] << 8) | msg->msg[15]; -} - -static inline void cec_msg_cdc_hec_set_state_adjacent(struct cec_msg *msg, - __u16 phys_addr1, - __u8 hec_set_state) -{ - msg->len = 8; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_CDC_MESSAGE; - /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ - msg->msg[4] = CEC_MSG_CDC_HEC_SET_STATE_ADJACENT; - msg->msg[5] = phys_addr1 >> 8; - msg->msg[6] = phys_addr1 & 0xff; - msg->msg[7] = hec_set_state; -} - -static inline void cec_ops_cdc_hec_set_state_adjacent(const struct cec_msg *msg, - __u16 *phys_addr, - __u16 *phys_addr1, - __u8 *hec_set_state) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *phys_addr1 = (msg->msg[5] << 8) | msg->msg[6]; - *hec_set_state = msg->msg[7]; -} - -static inline void cec_msg_cdc_hec_request_deactivation(struct cec_msg *msg, - __u16 phys_addr1, - __u16 phys_addr2, - __u16 phys_addr3) -{ - msg->len = 11; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_CDC_MESSAGE; - /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ - msg->msg[4] = CEC_MSG_CDC_HEC_REQUEST_DEACTIVATION; - msg->msg[5] = phys_addr1 >> 8; - msg->msg[6] = phys_addr1 & 0xff; - msg->msg[7] = phys_addr2 >> 8; - msg->msg[8] = phys_addr2 & 0xff; - msg->msg[9] = phys_addr3 >> 8; - msg->msg[10] = phys_addr3 & 0xff; -} - -static inline void cec_ops_cdc_hec_request_deactivation(const struct cec_msg *msg, - __u16 *phys_addr, - __u16 *phys_addr1, - __u16 *phys_addr2, - __u16 *phys_addr3) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *phys_addr1 = (msg->msg[5] << 8) | msg->msg[6]; - *phys_addr2 = (msg->msg[7] << 8) | msg->msg[8]; - *phys_addr3 = (msg->msg[9] << 8) | msg->msg[10]; -} - -static inline void cec_msg_cdc_hec_notify_alive(struct cec_msg *msg) -{ - msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_CDC_MESSAGE; - /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ - msg->msg[4] = CEC_MSG_CDC_HEC_NOTIFY_ALIVE; -} - -static inline void cec_ops_cdc_hec_notify_alive(const struct cec_msg *msg, - __u16 *phys_addr) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; -} - -static inline void cec_msg_cdc_hec_discover(struct cec_msg *msg) -{ - msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_CDC_MESSAGE; - /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ - msg->msg[4] = CEC_MSG_CDC_HEC_DISCOVER; -} - -static inline void cec_ops_cdc_hec_discover(const struct cec_msg *msg, - __u16 *phys_addr) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; -} - -static inline void cec_msg_cdc_hpd_set_state(struct cec_msg *msg, - __u8 input_port, - __u8 hpd_state) -{ - msg->len = 6; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_CDC_MESSAGE; - /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ - msg->msg[4] = CEC_MSG_CDC_HPD_SET_STATE; - msg->msg[5] = (input_port << 4) | hpd_state; -} - -static inline void cec_ops_cdc_hpd_set_state(const struct cec_msg *msg, - __u16 *phys_addr, - __u8 *input_port, - __u8 *hpd_state) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *input_port = msg->msg[5] >> 4; - *hpd_state = msg->msg[5] & 0xf; -} - -static inline void cec_msg_cdc_hpd_report_state(struct cec_msg *msg, - __u8 hpd_state, - __u8 hpd_error) -{ - msg->len = 6; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_CDC_MESSAGE; - /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ - msg->msg[4] = CEC_MSG_CDC_HPD_REPORT_STATE; - msg->msg[5] = (hpd_state << 4) | hpd_error; -} - -static inline void cec_ops_cdc_hpd_report_state(const struct cec_msg *msg, - __u16 *phys_addr, - __u8 *hpd_state, - __u8 *hpd_error) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *hpd_state = msg->msg[5] >> 4; - *hpd_error = msg->msg[5] & 0xf; -} - -#endif diff --git a/include/linux/cec.h b/include/linux/cec.h deleted file mode 100644 index 9c87711c0e1c..000000000000 --- a/include/linux/cec.h +++ /dev/null @@ -1,1071 +0,0 @@ -/* - * cec - HDMI Consumer Electronics Control public header - * - * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. - * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * Alternatively you can redistribute this file under the terms of the - * BSD license as stated below: - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * 3. The names of its contributors may not be used to endorse or promote - * products derived from this software without specific prior written - * permission. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -/* - * Note: this framework is still in staging and it is likely the API - * will change before it goes out of staging. - * - * Once it is moved out of staging this header will move to uapi. - */ -#ifndef _CEC_UAPI_H -#define _CEC_UAPI_H - -#include - -#define CEC_MAX_MSG_SIZE 16 - -/** - * struct cec_msg - CEC message structure. - * @tx_ts: Timestamp in nanoseconds using CLOCK_MONOTONIC. Set by the - * driver when the message transmission has finished. - * @rx_ts: Timestamp in nanoseconds using CLOCK_MONOTONIC. Set by the - * driver when the message was received. - * @len: Length in bytes of the message. - * @timeout: The timeout (in ms) that is used to timeout CEC_RECEIVE. - * Set to 0 if you want to wait forever. This timeout can also be - * used with CEC_TRANSMIT as the timeout for waiting for a reply. - * If 0, then it will use a 1 second timeout instead of waiting - * forever as is done with CEC_RECEIVE. - * @sequence: The framework assigns a sequence number to messages that are - * sent. This can be used to track replies to previously sent - * messages. - * @flags: Set to 0. - * @msg: The message payload. - * @reply: This field is ignored with CEC_RECEIVE and is only used by - * CEC_TRANSMIT. If non-zero, then wait for a reply with this - * opcode. Set to CEC_MSG_FEATURE_ABORT if you want to wait for - * a possible ABORT reply. If there was an error when sending the - * msg or FeatureAbort was returned, then reply is set to 0. - * If reply is non-zero upon return, then len/msg are set to - * the received message. - * If reply is zero upon return and status has the - * CEC_TX_STATUS_FEATURE_ABORT bit set, then len/msg are set to - * the received feature abort message. - * If reply is zero upon return and status has the - * CEC_TX_STATUS_MAX_RETRIES bit set, then no reply was seen at - * all. If reply is non-zero for CEC_TRANSMIT and the message is a - * broadcast, then -EINVAL is returned. - * if reply is non-zero, then timeout is set to 1000 (the required - * maximum response time). - * @rx_status: The message receive status bits. Set by the driver. - * @tx_status: The message transmit status bits. Set by the driver. - * @tx_arb_lost_cnt: The number of 'Arbitration Lost' events. Set by the driver. - * @tx_nack_cnt: The number of 'Not Acknowledged' events. Set by the driver. - * @tx_low_drive_cnt: The number of 'Low Drive Detected' events. Set by the - * driver. - * @tx_error_cnt: The number of 'Error' events. Set by the driver. - */ -struct cec_msg { - __u64 tx_ts; - __u64 rx_ts; - __u32 len; - __u32 timeout; - __u32 sequence; - __u32 flags; - __u8 msg[CEC_MAX_MSG_SIZE]; - __u8 reply; - __u8 rx_status; - __u8 tx_status; - __u8 tx_arb_lost_cnt; - __u8 tx_nack_cnt; - __u8 tx_low_drive_cnt; - __u8 tx_error_cnt; -}; - -/** - * cec_msg_initiator - return the initiator's logical address. - * @msg: the message structure - */ -static inline __u8 cec_msg_initiator(const struct cec_msg *msg) -{ - return msg->msg[0] >> 4; -} - -/** - * cec_msg_destination - return the destination's logical address. - * @msg: the message structure - */ -static inline __u8 cec_msg_destination(const struct cec_msg *msg) -{ - return msg->msg[0] & 0xf; -} - -/** - * cec_msg_opcode - return the opcode of the message, -1 for poll - * @msg: the message structure - */ -static inline int cec_msg_opcode(const struct cec_msg *msg) -{ - return msg->len > 1 ? msg->msg[1] : -1; -} - -/** - * cec_msg_is_broadcast - return true if this is a broadcast message. - * @msg: the message structure - */ -static inline bool cec_msg_is_broadcast(const struct cec_msg *msg) -{ - return (msg->msg[0] & 0xf) == 0xf; -} - -/** - * cec_msg_init - initialize the message structure. - * @msg: the message structure - * @initiator: the logical address of the initiator - * @destination:the logical address of the destination (0xf for broadcast) - * - * The whole structure is zeroed, the len field is set to 1 (i.e. a poll - * message) and the initiator and destination are filled in. - */ -static inline void cec_msg_init(struct cec_msg *msg, - __u8 initiator, __u8 destination) -{ - memset(msg, 0, sizeof(*msg)); - msg->msg[0] = (initiator << 4) | destination; - msg->len = 1; -} - -/** - * cec_msg_set_reply_to - fill in destination/initiator in a reply message. - * @msg: the message structure for the reply - * @orig: the original message structure - * - * Set the msg destination to the orig initiator and the msg initiator to the - * orig destination. Note that msg and orig may be the same pointer, in which - * case the change is done in place. - */ -static inline void cec_msg_set_reply_to(struct cec_msg *msg, - struct cec_msg *orig) -{ - /* The destination becomes the initiator and vice versa */ - msg->msg[0] = (cec_msg_destination(orig) << 4) | - cec_msg_initiator(orig); - msg->reply = msg->timeout = 0; -} - -/* cec_msg flags field */ -#define CEC_MSG_FL_REPLY_TO_FOLLOWERS (1 << 0) - -/* cec_msg tx/rx_status field */ -#define CEC_TX_STATUS_OK (1 << 0) -#define CEC_TX_STATUS_ARB_LOST (1 << 1) -#define CEC_TX_STATUS_NACK (1 << 2) -#define CEC_TX_STATUS_LOW_DRIVE (1 << 3) -#define CEC_TX_STATUS_ERROR (1 << 4) -#define CEC_TX_STATUS_MAX_RETRIES (1 << 5) - -#define CEC_RX_STATUS_OK (1 << 0) -#define CEC_RX_STATUS_TIMEOUT (1 << 1) -#define CEC_RX_STATUS_FEATURE_ABORT (1 << 2) - -static inline bool cec_msg_status_is_ok(const struct cec_msg *msg) -{ - if (msg->tx_status && !(msg->tx_status & CEC_TX_STATUS_OK)) - return false; - if (msg->rx_status && !(msg->rx_status & CEC_RX_STATUS_OK)) - return false; - if (!msg->tx_status && !msg->rx_status) - return false; - return !(msg->rx_status & CEC_RX_STATUS_FEATURE_ABORT); -} - -#define CEC_LOG_ADDR_INVALID 0xff -#define CEC_PHYS_ADDR_INVALID 0xffff - -/* - * The maximum number of logical addresses one device can be assigned to. - * The CEC 2.0 spec allows for only 2 logical addresses at the moment. The - * Analog Devices CEC hardware supports 3. So let's go wild and go for 4. - */ -#define CEC_MAX_LOG_ADDRS 4 - -/* The logical addresses defined by CEC 2.0 */ -#define CEC_LOG_ADDR_TV 0 -#define CEC_LOG_ADDR_RECORD_1 1 -#define CEC_LOG_ADDR_RECORD_2 2 -#define CEC_LOG_ADDR_TUNER_1 3 -#define CEC_LOG_ADDR_PLAYBACK_1 4 -#define CEC_LOG_ADDR_AUDIOSYSTEM 5 -#define CEC_LOG_ADDR_TUNER_2 6 -#define CEC_LOG_ADDR_TUNER_3 7 -#define CEC_LOG_ADDR_PLAYBACK_2 8 -#define CEC_LOG_ADDR_RECORD_3 9 -#define CEC_LOG_ADDR_TUNER_4 10 -#define CEC_LOG_ADDR_PLAYBACK_3 11 -#define CEC_LOG_ADDR_BACKUP_1 12 -#define CEC_LOG_ADDR_BACKUP_2 13 -#define CEC_LOG_ADDR_SPECIFIC 14 -#define CEC_LOG_ADDR_UNREGISTERED 15 /* as initiator address */ -#define CEC_LOG_ADDR_BROADCAST 15 /* ad destination address */ - -/* The logical address types that the CEC device wants to claim */ -#define CEC_LOG_ADDR_TYPE_TV 0 -#define CEC_LOG_ADDR_TYPE_RECORD 1 -#define CEC_LOG_ADDR_TYPE_TUNER 2 -#define CEC_LOG_ADDR_TYPE_PLAYBACK 3 -#define CEC_LOG_ADDR_TYPE_AUDIOSYSTEM 4 -#define CEC_LOG_ADDR_TYPE_SPECIFIC 5 -#define CEC_LOG_ADDR_TYPE_UNREGISTERED 6 -/* - * Switches should use UNREGISTERED. - * Processors should use SPECIFIC. - */ - -#define CEC_LOG_ADDR_MASK_TV (1 << CEC_LOG_ADDR_TV) -#define CEC_LOG_ADDR_MASK_RECORD ((1 << CEC_LOG_ADDR_RECORD_1) | \ - (1 << CEC_LOG_ADDR_RECORD_2) | \ - (1 << CEC_LOG_ADDR_RECORD_3)) -#define CEC_LOG_ADDR_MASK_TUNER ((1 << CEC_LOG_ADDR_TUNER_1) | \ - (1 << CEC_LOG_ADDR_TUNER_2) | \ - (1 << CEC_LOG_ADDR_TUNER_3) | \ - (1 << CEC_LOG_ADDR_TUNER_4)) -#define CEC_LOG_ADDR_MASK_PLAYBACK ((1 << CEC_LOG_ADDR_PLAYBACK_1) | \ - (1 << CEC_LOG_ADDR_PLAYBACK_2) | \ - (1 << CEC_LOG_ADDR_PLAYBACK_3)) -#define CEC_LOG_ADDR_MASK_AUDIOSYSTEM (1 << CEC_LOG_ADDR_AUDIOSYSTEM) -#define CEC_LOG_ADDR_MASK_BACKUP ((1 << CEC_LOG_ADDR_BACKUP_1) | \ - (1 << CEC_LOG_ADDR_BACKUP_2)) -#define CEC_LOG_ADDR_MASK_SPECIFIC (1 << CEC_LOG_ADDR_SPECIFIC) -#define CEC_LOG_ADDR_MASK_UNREGISTERED (1 << CEC_LOG_ADDR_UNREGISTERED) - -static inline bool cec_has_tv(__u16 log_addr_mask) -{ - return log_addr_mask & CEC_LOG_ADDR_MASK_TV; -} - -static inline bool cec_has_record(__u16 log_addr_mask) -{ - return log_addr_mask & CEC_LOG_ADDR_MASK_RECORD; -} - -static inline bool cec_has_tuner(__u16 log_addr_mask) -{ - return log_addr_mask & CEC_LOG_ADDR_MASK_TUNER; -} - -static inline bool cec_has_playback(__u16 log_addr_mask) -{ - return log_addr_mask & CEC_LOG_ADDR_MASK_PLAYBACK; -} - -static inline bool cec_has_audiosystem(__u16 log_addr_mask) -{ - return log_addr_mask & CEC_LOG_ADDR_MASK_AUDIOSYSTEM; -} - -static inline bool cec_has_backup(__u16 log_addr_mask) -{ - return log_addr_mask & CEC_LOG_ADDR_MASK_BACKUP; -} - -static inline bool cec_has_specific(__u16 log_addr_mask) -{ - return log_addr_mask & CEC_LOG_ADDR_MASK_SPECIFIC; -} - -static inline bool cec_is_unregistered(__u16 log_addr_mask) -{ - return log_addr_mask & CEC_LOG_ADDR_MASK_UNREGISTERED; -} - -static inline bool cec_is_unconfigured(__u16 log_addr_mask) -{ - return log_addr_mask == 0; -} - -/* - * Use this if there is no vendor ID (CEC_G_VENDOR_ID) or if the vendor ID - * should be disabled (CEC_S_VENDOR_ID) - */ -#define CEC_VENDOR_ID_NONE 0xffffffff - -/* The message handling modes */ -/* Modes for initiator */ -#define CEC_MODE_NO_INITIATOR (0x0 << 0) -#define CEC_MODE_INITIATOR (0x1 << 0) -#define CEC_MODE_EXCL_INITIATOR (0x2 << 0) -#define CEC_MODE_INITIATOR_MSK 0x0f - -/* Modes for follower */ -#define CEC_MODE_NO_FOLLOWER (0x0 << 4) -#define CEC_MODE_FOLLOWER (0x1 << 4) -#define CEC_MODE_EXCL_FOLLOWER (0x2 << 4) -#define CEC_MODE_EXCL_FOLLOWER_PASSTHRU (0x3 << 4) -#define CEC_MODE_MONITOR (0xe << 4) -#define CEC_MODE_MONITOR_ALL (0xf << 4) -#define CEC_MODE_FOLLOWER_MSK 0xf0 - -/* Userspace has to configure the physical address */ -#define CEC_CAP_PHYS_ADDR (1 << 0) -/* Userspace has to configure the logical addresses */ -#define CEC_CAP_LOG_ADDRS (1 << 1) -/* Userspace can transmit messages (and thus become follower as well) */ -#define CEC_CAP_TRANSMIT (1 << 2) -/* - * Passthrough all messages instead of processing them. - */ -#define CEC_CAP_PASSTHROUGH (1 << 3) -/* Supports remote control */ -#define CEC_CAP_RC (1 << 4) -/* Hardware can monitor all messages, not just directed and broadcast. */ -#define CEC_CAP_MONITOR_ALL (1 << 5) - -/** - * struct cec_caps - CEC capabilities structure. - * @driver: name of the CEC device driver. - * @name: name of the CEC device. @driver + @name must be unique. - * @available_log_addrs: number of available logical addresses. - * @capabilities: capabilities of the CEC adapter. - * @version: version of the CEC adapter framework. - */ -struct cec_caps { - char driver[32]; - char name[32]; - __u32 available_log_addrs; - __u32 capabilities; - __u32 version; -}; - -/** - * struct cec_log_addrs - CEC logical addresses structure. - * @log_addr: the claimed logical addresses. Set by the driver. - * @log_addr_mask: current logical address mask. Set by the driver. - * @cec_version: the CEC version that the adapter should implement. Set by the - * caller. - * @num_log_addrs: how many logical addresses should be claimed. Set by the - * caller. - * @vendor_id: the vendor ID of the device. Set by the caller. - * @flags: flags. - * @osd_name: the OSD name of the device. Set by the caller. - * @primary_device_type: the primary device type for each logical address. - * Set by the caller. - * @log_addr_type: the logical address types. Set by the caller. - * @all_device_types: CEC 2.0: all device types represented by the logical - * address. Set by the caller. - * @features: CEC 2.0: The logical address features. Set by the caller. - */ -struct cec_log_addrs { - __u8 log_addr[CEC_MAX_LOG_ADDRS]; - __u16 log_addr_mask; - __u8 cec_version; - __u8 num_log_addrs; - __u32 vendor_id; - __u32 flags; - char osd_name[15]; - __u8 primary_device_type[CEC_MAX_LOG_ADDRS]; - __u8 log_addr_type[CEC_MAX_LOG_ADDRS]; - - /* CEC 2.0 */ - __u8 all_device_types[CEC_MAX_LOG_ADDRS]; - __u8 features[CEC_MAX_LOG_ADDRS][12]; -}; - -/* Allow a fallback to unregistered */ -#define CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK (1 << 0) -/* Passthrough RC messages to the input subsystem */ -#define CEC_LOG_ADDRS_FL_ALLOW_RC_PASSTHRU (1 << 1) -/* CDC-Only device: supports only CDC messages */ -#define CEC_LOG_ADDRS_FL_CDC_ONLY (1 << 2) - -/* Events */ - -/* Event that occurs when the adapter state changes */ -#define CEC_EVENT_STATE_CHANGE 1 -/* - * This event is sent when messages are lost because the application - * didn't empty the message queue in time - */ -#define CEC_EVENT_LOST_MSGS 2 - -#define CEC_EVENT_FL_INITIAL_STATE (1 << 0) - -/** - * struct cec_event_state_change - used when the CEC adapter changes state. - * @phys_addr: the current physical address - * @log_addr_mask: the current logical address mask - */ -struct cec_event_state_change { - __u16 phys_addr; - __u16 log_addr_mask; -}; - -/** - * struct cec_event_lost_msgs - tells you how many messages were lost due. - * @lost_msgs: how many messages were lost. - */ -struct cec_event_lost_msgs { - __u32 lost_msgs; -}; - -/** - * struct cec_event - CEC event structure - * @ts: the timestamp of when the event was sent. - * @event: the event. - * array. - * @state_change: the event payload for CEC_EVENT_STATE_CHANGE. - * @lost_msgs: the event payload for CEC_EVENT_LOST_MSGS. - * @raw: array to pad the union. - */ -struct cec_event { - __u64 ts; - __u32 event; - __u32 flags; - union { - struct cec_event_state_change state_change; - struct cec_event_lost_msgs lost_msgs; - __u32 raw[16]; - }; -}; - -/* ioctls */ - -/* Adapter capabilities */ -#define CEC_ADAP_G_CAPS _IOWR('a', 0, struct cec_caps) - -/* - * phys_addr is either 0 (if this is the CEC root device) - * or a valid physical address obtained from the sink's EDID - * as read by this CEC device (if this is a source device) - * or a physical address obtained and modified from a sink - * EDID and used for a sink CEC device. - * If nothing is connected, then phys_addr is 0xffff. - * See HDMI 1.4b, section 8.7 (Physical Address). - * - * The CEC_ADAP_S_PHYS_ADDR ioctl may not be available if that is handled - * internally. - */ -#define CEC_ADAP_G_PHYS_ADDR _IOR('a', 1, __u16) -#define CEC_ADAP_S_PHYS_ADDR _IOW('a', 2, __u16) - -/* - * Configure the CEC adapter. It sets the device type and which - * logical types it will try to claim. It will return which - * logical addresses it could actually claim. - * An error is returned if the adapter is disabled or if there - * is no physical address assigned. - */ - -#define CEC_ADAP_G_LOG_ADDRS _IOR('a', 3, struct cec_log_addrs) -#define CEC_ADAP_S_LOG_ADDRS _IOWR('a', 4, struct cec_log_addrs) - -/* Transmit/receive a CEC command */ -#define CEC_TRANSMIT _IOWR('a', 5, struct cec_msg) -#define CEC_RECEIVE _IOWR('a', 6, struct cec_msg) - -/* Dequeue CEC events */ -#define CEC_DQEVENT _IOWR('a', 7, struct cec_event) - -/* - * Get and set the message handling mode for this filehandle. - */ -#define CEC_G_MODE _IOR('a', 8, __u32) -#define CEC_S_MODE _IOW('a', 9, __u32) - -/* - * The remainder of this header defines all CEC messages and operands. - * The format matters since it the cec-ctl utility parses it to generate - * code for implementing all these messages. - * - * Comments ending with 'Feature' group messages for each feature. - * If messages are part of multiple features, then the "Has also" - * comment is used to list the previously defined messages that are - * supported by the feature. - * - * Before operands are defined a comment is added that gives the - * name of the operand and in brackets the variable name of the - * corresponding argument in the cec-funcs.h function. - */ - -/* Messages */ - -/* One Touch Play Feature */ -#define CEC_MSG_ACTIVE_SOURCE 0x82 -#define CEC_MSG_IMAGE_VIEW_ON 0x04 -#define CEC_MSG_TEXT_VIEW_ON 0x0d - - -/* Routing Control Feature */ - -/* - * Has also: - * CEC_MSG_ACTIVE_SOURCE - */ - -#define CEC_MSG_INACTIVE_SOURCE 0x9d -#define CEC_MSG_REQUEST_ACTIVE_SOURCE 0x85 -#define CEC_MSG_ROUTING_CHANGE 0x80 -#define CEC_MSG_ROUTING_INFORMATION 0x81 -#define CEC_MSG_SET_STREAM_PATH 0x86 - - -/* Standby Feature */ -#define CEC_MSG_STANDBY 0x36 - - -/* One Touch Record Feature */ -#define CEC_MSG_RECORD_OFF 0x0b -#define CEC_MSG_RECORD_ON 0x09 -/* Record Source Type Operand (rec_src_type) */ -#define CEC_OP_RECORD_SRC_OWN 1 -#define CEC_OP_RECORD_SRC_DIGITAL 2 -#define CEC_OP_RECORD_SRC_ANALOG 3 -#define CEC_OP_RECORD_SRC_EXT_PLUG 4 -#define CEC_OP_RECORD_SRC_EXT_PHYS_ADDR 5 -/* Service Identification Method Operand (service_id_method) */ -#define CEC_OP_SERVICE_ID_METHOD_BY_DIG_ID 0 -#define CEC_OP_SERVICE_ID_METHOD_BY_CHANNEL 1 -/* Digital Service Broadcast System Operand (dig_bcast_system) */ -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_GEN 0x00 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_GEN 0x01 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_GEN 0x02 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_BS 0x08 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_CS 0x09 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_T 0x0a -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_CABLE 0x10 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_SAT 0x11 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_T 0x12 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_C 0x18 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_S 0x19 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_S2 0x1a -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_T 0x1b -/* Analogue Broadcast Type Operand (ana_bcast_type) */ -#define CEC_OP_ANA_BCAST_TYPE_CABLE 0 -#define CEC_OP_ANA_BCAST_TYPE_SATELLITE 1 -#define CEC_OP_ANA_BCAST_TYPE_TERRESTRIAL 2 -/* Broadcast System Operand (bcast_system) */ -#define CEC_OP_BCAST_SYSTEM_PAL_BG 0x00 -#define CEC_OP_BCAST_SYSTEM_SECAM_LQ 0x01 /* SECAM L' */ -#define CEC_OP_BCAST_SYSTEM_PAL_M 0x02 -#define CEC_OP_BCAST_SYSTEM_NTSC_M 0x03 -#define CEC_OP_BCAST_SYSTEM_PAL_I 0x04 -#define CEC_OP_BCAST_SYSTEM_SECAM_DK 0x05 -#define CEC_OP_BCAST_SYSTEM_SECAM_BG 0x06 -#define CEC_OP_BCAST_SYSTEM_SECAM_L 0x07 -#define CEC_OP_BCAST_SYSTEM_PAL_DK 0x08 -#define CEC_OP_BCAST_SYSTEM_OTHER 0x1f -/* Channel Number Format Operand (channel_number_fmt) */ -#define CEC_OP_CHANNEL_NUMBER_FMT_1_PART 0x01 -#define CEC_OP_CHANNEL_NUMBER_FMT_2_PART 0x02 - -#define CEC_MSG_RECORD_STATUS 0x0a -/* Record Status Operand (rec_status) */ -#define CEC_OP_RECORD_STATUS_CUR_SRC 0x01 -#define CEC_OP_RECORD_STATUS_DIG_SERVICE 0x02 -#define CEC_OP_RECORD_STATUS_ANA_SERVICE 0x03 -#define CEC_OP_RECORD_STATUS_EXT_INPUT 0x04 -#define CEC_OP_RECORD_STATUS_NO_DIG_SERVICE 0x05 -#define CEC_OP_RECORD_STATUS_NO_ANA_SERVICE 0x06 -#define CEC_OP_RECORD_STATUS_NO_SERVICE 0x07 -#define CEC_OP_RECORD_STATUS_INVALID_EXT_PLUG 0x09 -#define CEC_OP_RECORD_STATUS_INVALID_EXT_PHYS_ADDR 0x0a -#define CEC_OP_RECORD_STATUS_UNSUP_CA 0x0b -#define CEC_OP_RECORD_STATUS_NO_CA_ENTITLEMENTS 0x0c -#define CEC_OP_RECORD_STATUS_CANT_COPY_SRC 0x0d -#define CEC_OP_RECORD_STATUS_NO_MORE_COPIES 0x0e -#define CEC_OP_RECORD_STATUS_NO_MEDIA 0x10 -#define CEC_OP_RECORD_STATUS_PLAYING 0x11 -#define CEC_OP_RECORD_STATUS_ALREADY_RECORDING 0x12 -#define CEC_OP_RECORD_STATUS_MEDIA_PROT 0x13 -#define CEC_OP_RECORD_STATUS_NO_SIGNAL 0x14 -#define CEC_OP_RECORD_STATUS_MEDIA_PROBLEM 0x15 -#define CEC_OP_RECORD_STATUS_NO_SPACE 0x16 -#define CEC_OP_RECORD_STATUS_PARENTAL_LOCK 0x17 -#define CEC_OP_RECORD_STATUS_TERMINATED_OK 0x1a -#define CEC_OP_RECORD_STATUS_ALREADY_TERM 0x1b -#define CEC_OP_RECORD_STATUS_OTHER 0x1f - -#define CEC_MSG_RECORD_TV_SCREEN 0x0f - - -/* Timer Programming Feature */ -#define CEC_MSG_CLEAR_ANALOGUE_TIMER 0x33 -/* Recording Sequence Operand (recording_seq) */ -#define CEC_OP_REC_SEQ_SUNDAY 0x01 -#define CEC_OP_REC_SEQ_MONDAY 0x02 -#define CEC_OP_REC_SEQ_TUESDAY 0x04 -#define CEC_OP_REC_SEQ_WEDNESDAY 0x08 -#define CEC_OP_REC_SEQ_THURSDAY 0x10 -#define CEC_OP_REC_SEQ_FRIDAY 0x20 -#define CEC_OP_REC_SEQ_SATERDAY 0x40 -#define CEC_OP_REC_SEQ_ONCE_ONLY 0x00 - -#define CEC_MSG_CLEAR_DIGITAL_TIMER 0x99 - -#define CEC_MSG_CLEAR_EXT_TIMER 0xa1 -/* External Source Specifier Operand (ext_src_spec) */ -#define CEC_OP_EXT_SRC_PLUG 0x04 -#define CEC_OP_EXT_SRC_PHYS_ADDR 0x05 - -#define CEC_MSG_SET_ANALOGUE_TIMER 0x34 -#define CEC_MSG_SET_DIGITAL_TIMER 0x97 -#define CEC_MSG_SET_EXT_TIMER 0xa2 - -#define CEC_MSG_SET_TIMER_PROGRAM_TITLE 0x67 -#define CEC_MSG_TIMER_CLEARED_STATUS 0x43 -/* Timer Cleared Status Data Operand (timer_cleared_status) */ -#define CEC_OP_TIMER_CLR_STAT_RECORDING 0x00 -#define CEC_OP_TIMER_CLR_STAT_NO_MATCHING 0x01 -#define CEC_OP_TIMER_CLR_STAT_NO_INFO 0x02 -#define CEC_OP_TIMER_CLR_STAT_CLEARED 0x80 - -#define CEC_MSG_TIMER_STATUS 0x35 -/* Timer Overlap Warning Operand (timer_overlap_warning) */ -#define CEC_OP_TIMER_OVERLAP_WARNING_NO_OVERLAP 0 -#define CEC_OP_TIMER_OVERLAP_WARNING_OVERLAP 1 -/* Media Info Operand (media_info) */ -#define CEC_OP_MEDIA_INFO_UNPROT_MEDIA 0 -#define CEC_OP_MEDIA_INFO_PROT_MEDIA 1 -#define CEC_OP_MEDIA_INFO_NO_MEDIA 2 -/* Programmed Indicator Operand (prog_indicator) */ -#define CEC_OP_PROG_IND_NOT_PROGRAMMED 0 -#define CEC_OP_PROG_IND_PROGRAMMED 1 -/* Programmed Info Operand (prog_info) */ -#define CEC_OP_PROG_INFO_ENOUGH_SPACE 0x08 -#define CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE 0x09 -#define CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE 0x0b -#define CEC_OP_PROG_INFO_NONE_AVAILABLE 0x0a -/* Not Programmed Error Info Operand (prog_error) */ -#define CEC_OP_PROG_ERROR_NO_FREE_TIMER 0x01 -#define CEC_OP_PROG_ERROR_DATE_OUT_OF_RANGE 0x02 -#define CEC_OP_PROG_ERROR_REC_SEQ_ERROR 0x03 -#define CEC_OP_PROG_ERROR_INV_EXT_PLUG 0x04 -#define CEC_OP_PROG_ERROR_INV_EXT_PHYS_ADDR 0x05 -#define CEC_OP_PROG_ERROR_CA_UNSUPP 0x06 -#define CEC_OP_PROG_ERROR_INSUF_CA_ENTITLEMENTS 0x07 -#define CEC_OP_PROG_ERROR_RESOLUTION_UNSUPP 0x08 -#define CEC_OP_PROG_ERROR_PARENTAL_LOCK 0x09 -#define CEC_OP_PROG_ERROR_CLOCK_FAILURE 0x0a -#define CEC_OP_PROG_ERROR_DUPLICATE 0x0e - - -/* System Information Feature */ -#define CEC_MSG_CEC_VERSION 0x9e -/* CEC Version Operand (cec_version) */ -#define CEC_OP_CEC_VERSION_1_3A 4 -#define CEC_OP_CEC_VERSION_1_4 5 -#define CEC_OP_CEC_VERSION_2_0 6 - -#define CEC_MSG_GET_CEC_VERSION 0x9f -#define CEC_MSG_GIVE_PHYSICAL_ADDR 0x83 -#define CEC_MSG_GET_MENU_LANGUAGE 0x91 -#define CEC_MSG_REPORT_PHYSICAL_ADDR 0x84 -/* Primary Device Type Operand (prim_devtype) */ -#define CEC_OP_PRIM_DEVTYPE_TV 0 -#define CEC_OP_PRIM_DEVTYPE_RECORD 1 -#define CEC_OP_PRIM_DEVTYPE_TUNER 3 -#define CEC_OP_PRIM_DEVTYPE_PLAYBACK 4 -#define CEC_OP_PRIM_DEVTYPE_AUDIOSYSTEM 5 -#define CEC_OP_PRIM_DEVTYPE_SWITCH 6 -#define CEC_OP_PRIM_DEVTYPE_PROCESSOR 7 - -#define CEC_MSG_SET_MENU_LANGUAGE 0x32 -#define CEC_MSG_REPORT_FEATURES 0xa6 /* HDMI 2.0 */ -/* All Device Types Operand (all_device_types) */ -#define CEC_OP_ALL_DEVTYPE_TV 0x80 -#define CEC_OP_ALL_DEVTYPE_RECORD 0x40 -#define CEC_OP_ALL_DEVTYPE_TUNER 0x20 -#define CEC_OP_ALL_DEVTYPE_PLAYBACK 0x10 -#define CEC_OP_ALL_DEVTYPE_AUDIOSYSTEM 0x08 -#define CEC_OP_ALL_DEVTYPE_SWITCH 0x04 -/* - * And if you wondering what happened to PROCESSOR devices: those should - * be mapped to a SWITCH. - */ - -/* Valid for RC Profile and Device Feature operands */ -#define CEC_OP_FEAT_EXT 0x80 /* Extension bit */ -/* RC Profile Operand (rc_profile) */ -#define CEC_OP_FEAT_RC_TV_PROFILE_NONE 0x00 -#define CEC_OP_FEAT_RC_TV_PROFILE_1 0x02 -#define CEC_OP_FEAT_RC_TV_PROFILE_2 0x06 -#define CEC_OP_FEAT_RC_TV_PROFILE_3 0x0a -#define CEC_OP_FEAT_RC_TV_PROFILE_4 0x0e -#define CEC_OP_FEAT_RC_SRC_HAS_DEV_ROOT_MENU 0x50 -#define CEC_OP_FEAT_RC_SRC_HAS_DEV_SETUP_MENU 0x48 -#define CEC_OP_FEAT_RC_SRC_HAS_CONTENTS_MENU 0x44 -#define CEC_OP_FEAT_RC_SRC_HAS_MEDIA_TOP_MENU 0x42 -#define CEC_OP_FEAT_RC_SRC_HAS_MEDIA_CONTEXT_MENU 0x41 -/* Device Feature Operand (dev_features) */ -#define CEC_OP_FEAT_DEV_HAS_RECORD_TV_SCREEN 0x40 -#define CEC_OP_FEAT_DEV_HAS_SET_OSD_STRING 0x20 -#define CEC_OP_FEAT_DEV_HAS_DECK_CONTROL 0x10 -#define CEC_OP_FEAT_DEV_HAS_SET_AUDIO_RATE 0x08 -#define CEC_OP_FEAT_DEV_SINK_HAS_ARC_TX 0x04 -#define CEC_OP_FEAT_DEV_SOURCE_HAS_ARC_RX 0x02 - -#define CEC_MSG_GIVE_FEATURES 0xa5 /* HDMI 2.0 */ - - -/* Deck Control Feature */ -#define CEC_MSG_DECK_CONTROL 0x42 -/* Deck Control Mode Operand (deck_control_mode) */ -#define CEC_OP_DECK_CTL_MODE_SKIP_FWD 1 -#define CEC_OP_DECK_CTL_MODE_SKIP_REV 2 -#define CEC_OP_DECK_CTL_MODE_STOP 3 -#define CEC_OP_DECK_CTL_MODE_EJECT 4 - -#define CEC_MSG_DECK_STATUS 0x1b -/* Deck Info Operand (deck_info) */ -#define CEC_OP_DECK_INFO_PLAY 0x11 -#define CEC_OP_DECK_INFO_RECORD 0x12 -#define CEC_OP_DECK_INFO_PLAY_REV 0x13 -#define CEC_OP_DECK_INFO_STILL 0x14 -#define CEC_OP_DECK_INFO_SLOW 0x15 -#define CEC_OP_DECK_INFO_SLOW_REV 0x16 -#define CEC_OP_DECK_INFO_FAST_FWD 0x17 -#define CEC_OP_DECK_INFO_FAST_REV 0x18 -#define CEC_OP_DECK_INFO_NO_MEDIA 0x19 -#define CEC_OP_DECK_INFO_STOP 0x1a -#define CEC_OP_DECK_INFO_SKIP_FWD 0x1b -#define CEC_OP_DECK_INFO_SKIP_REV 0x1c -#define CEC_OP_DECK_INFO_INDEX_SEARCH_FWD 0x1d -#define CEC_OP_DECK_INFO_INDEX_SEARCH_REV 0x1e -#define CEC_OP_DECK_INFO_OTHER 0x1f - -#define CEC_MSG_GIVE_DECK_STATUS 0x1a -/* Status Request Operand (status_req) */ -#define CEC_OP_STATUS_REQ_ON 1 -#define CEC_OP_STATUS_REQ_OFF 2 -#define CEC_OP_STATUS_REQ_ONCE 3 - -#define CEC_MSG_PLAY 0x41 -/* Play Mode Operand (play_mode) */ -#define CEC_OP_PLAY_MODE_PLAY_FWD 0x24 -#define CEC_OP_PLAY_MODE_PLAY_REV 0x20 -#define CEC_OP_PLAY_MODE_PLAY_STILL 0x25 -#define CEC_OP_PLAY_MODE_PLAY_FAST_FWD_MIN 0x05 -#define CEC_OP_PLAY_MODE_PLAY_FAST_FWD_MED 0x06 -#define CEC_OP_PLAY_MODE_PLAY_FAST_FWD_MAX 0x07 -#define CEC_OP_PLAY_MODE_PLAY_FAST_REV_MIN 0x09 -#define CEC_OP_PLAY_MODE_PLAY_FAST_REV_MED 0x0a -#define CEC_OP_PLAY_MODE_PLAY_FAST_REV_MAX 0x0b -#define CEC_OP_PLAY_MODE_PLAY_SLOW_FWD_MIN 0x15 -#define CEC_OP_PLAY_MODE_PLAY_SLOW_FWD_MED 0x16 -#define CEC_OP_PLAY_MODE_PLAY_SLOW_FWD_MAX 0x17 -#define CEC_OP_PLAY_MODE_PLAY_SLOW_REV_MIN 0x19 -#define CEC_OP_PLAY_MODE_PLAY_SLOW_REV_MED 0x1a -#define CEC_OP_PLAY_MODE_PLAY_SLOW_REV_MAX 0x1b - - -/* Tuner Control Feature */ -#define CEC_MSG_GIVE_TUNER_DEVICE_STATUS 0x08 -#define CEC_MSG_SELECT_ANALOGUE_SERVICE 0x92 -#define CEC_MSG_SELECT_DIGITAL_SERVICE 0x93 -#define CEC_MSG_TUNER_DEVICE_STATUS 0x07 -/* Recording Flag Operand (rec_flag) */ -#define CEC_OP_REC_FLAG_USED 0 -#define CEC_OP_REC_FLAG_NOT_USED 1 -/* Tuner Display Info Operand (tuner_display_info) */ -#define CEC_OP_TUNER_DISPLAY_INFO_DIGITAL 0 -#define CEC_OP_TUNER_DISPLAY_INFO_NONE 1 -#define CEC_OP_TUNER_DISPLAY_INFO_ANALOGUE 2 - -#define CEC_MSG_TUNER_STEP_DECREMENT 0x06 -#define CEC_MSG_TUNER_STEP_INCREMENT 0x05 - - -/* Vendor Specific Commands Feature */ - -/* - * Has also: - * CEC_MSG_CEC_VERSION - * CEC_MSG_GET_CEC_VERSION - */ -#define CEC_MSG_DEVICE_VENDOR_ID 0x87 -#define CEC_MSG_GIVE_DEVICE_VENDOR_ID 0x8c -#define CEC_MSG_VENDOR_COMMAND 0x89 -#define CEC_MSG_VENDOR_COMMAND_WITH_ID 0xa0 -#define CEC_MSG_VENDOR_REMOTE_BUTTON_DOWN 0x8a -#define CEC_MSG_VENDOR_REMOTE_BUTTON_UP 0x8b - - -/* OSD Display Feature */ -#define CEC_MSG_SET_OSD_STRING 0x64 -/* Display Control Operand (disp_ctl) */ -#define CEC_OP_DISP_CTL_DEFAULT 0x00 -#define CEC_OP_DISP_CTL_UNTIL_CLEARED 0x40 -#define CEC_OP_DISP_CTL_CLEAR 0x80 - - -/* Device OSD Transfer Feature */ -#define CEC_MSG_GIVE_OSD_NAME 0x46 -#define CEC_MSG_SET_OSD_NAME 0x47 - - -/* Device Menu Control Feature */ -#define CEC_MSG_MENU_REQUEST 0x8d -/* Menu Request Type Operand (menu_req) */ -#define CEC_OP_MENU_REQUEST_ACTIVATE 0x00 -#define CEC_OP_MENU_REQUEST_DEACTIVATE 0x01 -#define CEC_OP_MENU_REQUEST_QUERY 0x02 - -#define CEC_MSG_MENU_STATUS 0x8e -/* Menu State Operand (menu_state) */ -#define CEC_OP_MENU_STATE_ACTIVATED 0x00 -#define CEC_OP_MENU_STATE_DEACTIVATED 0x01 - -#define CEC_MSG_USER_CONTROL_PRESSED 0x44 -/* UI Broadcast Type Operand (ui_bcast_type) */ -#define CEC_OP_UI_BCAST_TYPE_TOGGLE_ALL 0x00 -#define CEC_OP_UI_BCAST_TYPE_TOGGLE_DIG_ANA 0x01 -#define CEC_OP_UI_BCAST_TYPE_ANALOGUE 0x10 -#define CEC_OP_UI_BCAST_TYPE_ANALOGUE_T 0x20 -#define CEC_OP_UI_BCAST_TYPE_ANALOGUE_CABLE 0x30 -#define CEC_OP_UI_BCAST_TYPE_ANALOGUE_SAT 0x40 -#define CEC_OP_UI_BCAST_TYPE_DIGITAL 0x50 -#define CEC_OP_UI_BCAST_TYPE_DIGITAL_T 0x60 -#define CEC_OP_UI_BCAST_TYPE_DIGITAL_CABLE 0x70 -#define CEC_OP_UI_BCAST_TYPE_DIGITAL_SAT 0x80 -#define CEC_OP_UI_BCAST_TYPE_DIGITAL_COM_SAT 0x90 -#define CEC_OP_UI_BCAST_TYPE_DIGITAL_COM_SAT2 0x91 -#define CEC_OP_UI_BCAST_TYPE_IP 0xa0 -/* UI Sound Presentation Control Operand (ui_snd_pres_ctl) */ -#define CEC_OP_UI_SND_PRES_CTL_DUAL_MONO 0x10 -#define CEC_OP_UI_SND_PRES_CTL_KARAOKE 0x20 -#define CEC_OP_UI_SND_PRES_CTL_DOWNMIX 0x80 -#define CEC_OP_UI_SND_PRES_CTL_REVERB 0x90 -#define CEC_OP_UI_SND_PRES_CTL_EQUALIZER 0xa0 -#define CEC_OP_UI_SND_PRES_CTL_BASS_UP 0xb1 -#define CEC_OP_UI_SND_PRES_CTL_BASS_NEUTRAL 0xb2 -#define CEC_OP_UI_SND_PRES_CTL_BASS_DOWN 0xb3 -#define CEC_OP_UI_SND_PRES_CTL_TREBLE_UP 0xc1 -#define CEC_OP_UI_SND_PRES_CTL_TREBLE_NEUTRAL 0xc2 -#define CEC_OP_UI_SND_PRES_CTL_TREBLE_DOWN 0xc3 - -#define CEC_MSG_USER_CONTROL_RELEASED 0x45 - - -/* Remote Control Passthrough Feature */ - -/* - * Has also: - * CEC_MSG_USER_CONTROL_PRESSED - * CEC_MSG_USER_CONTROL_RELEASED - */ - - -/* Power Status Feature */ -#define CEC_MSG_GIVE_DEVICE_POWER_STATUS 0x8f -#define CEC_MSG_REPORT_POWER_STATUS 0x90 -/* Power Status Operand (pwr_state) */ -#define CEC_OP_POWER_STATUS_ON 0 -#define CEC_OP_POWER_STATUS_STANDBY 1 -#define CEC_OP_POWER_STATUS_TO_ON 2 -#define CEC_OP_POWER_STATUS_TO_STANDBY 3 - - -/* General Protocol Messages */ -#define CEC_MSG_FEATURE_ABORT 0x00 -/* Abort Reason Operand (reason) */ -#define CEC_OP_ABORT_UNRECOGNIZED_OP 0 -#define CEC_OP_ABORT_INCORRECT_MODE 1 -#define CEC_OP_ABORT_NO_SOURCE 2 -#define CEC_OP_ABORT_INVALID_OP 3 -#define CEC_OP_ABORT_REFUSED 4 -#define CEC_OP_ABORT_UNDETERMINED 5 - -#define CEC_MSG_ABORT 0xff - - -/* System Audio Control Feature */ - -/* - * Has also: - * CEC_MSG_USER_CONTROL_PRESSED - * CEC_MSG_USER_CONTROL_RELEASED - */ -#define CEC_MSG_GIVE_AUDIO_STATUS 0x71 -#define CEC_MSG_GIVE_SYSTEM_AUDIO_MODE_STATUS 0x7d -#define CEC_MSG_REPORT_AUDIO_STATUS 0x7a -/* Audio Mute Status Operand (aud_mute_status) */ -#define CEC_OP_AUD_MUTE_STATUS_OFF 0 -#define CEC_OP_AUD_MUTE_STATUS_ON 1 - -#define CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR 0xa3 -#define CEC_MSG_REQUEST_SHORT_AUDIO_DESCRIPTOR 0xa4 -#define CEC_MSG_SET_SYSTEM_AUDIO_MODE 0x72 -/* System Audio Status Operand (sys_aud_status) */ -#define CEC_OP_SYS_AUD_STATUS_OFF 0 -#define CEC_OP_SYS_AUD_STATUS_ON 1 - -#define CEC_MSG_SYSTEM_AUDIO_MODE_REQUEST 0x70 -#define CEC_MSG_SYSTEM_AUDIO_MODE_STATUS 0x7e -/* Audio Format ID Operand (audio_format_id) */ -#define CEC_OP_AUD_FMT_ID_CEA861 0 -#define CEC_OP_AUD_FMT_ID_CEA861_CXT 1 - - -/* Audio Rate Control Feature */ -#define CEC_MSG_SET_AUDIO_RATE 0x9a -/* Audio Rate Operand (audio_rate) */ -#define CEC_OP_AUD_RATE_OFF 0 -#define CEC_OP_AUD_RATE_WIDE_STD 1 -#define CEC_OP_AUD_RATE_WIDE_FAST 2 -#define CEC_OP_AUD_RATE_WIDE_SLOW 3 -#define CEC_OP_AUD_RATE_NARROW_STD 4 -#define CEC_OP_AUD_RATE_NARROW_FAST 5 -#define CEC_OP_AUD_RATE_NARROW_SLOW 6 - - -/* Audio Return Channel Control Feature */ -#define CEC_MSG_INITIATE_ARC 0xc0 -#define CEC_MSG_REPORT_ARC_INITIATED 0xc1 -#define CEC_MSG_REPORT_ARC_TERMINATED 0xc2 -#define CEC_MSG_REQUEST_ARC_INITIATION 0xc3 -#define CEC_MSG_REQUEST_ARC_TERMINATION 0xc4 -#define CEC_MSG_TERMINATE_ARC 0xc5 - - -/* Dynamic Audio Lipsync Feature */ -/* Only for CEC 2.0 and up */ -#define CEC_MSG_REQUEST_CURRENT_LATENCY 0xa7 -#define CEC_MSG_REPORT_CURRENT_LATENCY 0xa8 -/* Low Latency Mode Operand (low_latency_mode) */ -#define CEC_OP_LOW_LATENCY_MODE_OFF 0 -#define CEC_OP_LOW_LATENCY_MODE_ON 1 -/* Audio Output Compensated Operand (audio_out_compensated) */ -#define CEC_OP_AUD_OUT_COMPENSATED_NA 0 -#define CEC_OP_AUD_OUT_COMPENSATED_DELAY 1 -#define CEC_OP_AUD_OUT_COMPENSATED_NO_DELAY 2 -#define CEC_OP_AUD_OUT_COMPENSATED_PARTIAL_DELAY 3 - - -/* Capability Discovery and Control Feature */ -#define CEC_MSG_CDC_MESSAGE 0xf8 -/* Ethernet-over-HDMI: nobody ever does this... */ -#define CEC_MSG_CDC_HEC_INQUIRE_STATE 0x00 -#define CEC_MSG_CDC_HEC_REPORT_STATE 0x01 -/* HEC Functionality State Operand (hec_func_state) */ -#define CEC_OP_HEC_FUNC_STATE_NOT_SUPPORTED 0 -#define CEC_OP_HEC_FUNC_STATE_INACTIVE 1 -#define CEC_OP_HEC_FUNC_STATE_ACTIVE 2 -#define CEC_OP_HEC_FUNC_STATE_ACTIVATION_FIELD 3 -/* Host Functionality State Operand (host_func_state) */ -#define CEC_OP_HOST_FUNC_STATE_NOT_SUPPORTED 0 -#define CEC_OP_HOST_FUNC_STATE_INACTIVE 1 -#define CEC_OP_HOST_FUNC_STATE_ACTIVE 2 -/* ENC Functionality State Operand (enc_func_state) */ -#define CEC_OP_ENC_FUNC_STATE_EXT_CON_NOT_SUPPORTED 0 -#define CEC_OP_ENC_FUNC_STATE_EXT_CON_INACTIVE 1 -#define CEC_OP_ENC_FUNC_STATE_EXT_CON_ACTIVE 2 -/* CDC Error Code Operand (cdc_errcode) */ -#define CEC_OP_CDC_ERROR_CODE_NONE 0 -#define CEC_OP_CDC_ERROR_CODE_CAP_UNSUPPORTED 1 -#define CEC_OP_CDC_ERROR_CODE_WRONG_STATE 2 -#define CEC_OP_CDC_ERROR_CODE_OTHER 3 -/* HEC Support Operand (hec_support) */ -#define CEC_OP_HEC_SUPPORT_NO 0 -#define CEC_OP_HEC_SUPPORT_YES 1 -/* HEC Activation Operand (hec_activation) */ -#define CEC_OP_HEC_ACTIVATION_ON 0 -#define CEC_OP_HEC_ACTIVATION_OFF 1 - -#define CEC_MSG_CDC_HEC_SET_STATE_ADJACENT 0x02 -#define CEC_MSG_CDC_HEC_SET_STATE 0x03 -/* HEC Set State Operand (hec_set_state) */ -#define CEC_OP_HEC_SET_STATE_DEACTIVATE 0 -#define CEC_OP_HEC_SET_STATE_ACTIVATE 1 - -#define CEC_MSG_CDC_HEC_REQUEST_DEACTIVATION 0x04 -#define CEC_MSG_CDC_HEC_NOTIFY_ALIVE 0x05 -#define CEC_MSG_CDC_HEC_DISCOVER 0x06 -/* Hotplug Detect messages */ -#define CEC_MSG_CDC_HPD_SET_STATE 0x10 -/* HPD State Operand (hpd_state) */ -#define CEC_OP_HPD_STATE_CP_EDID_DISABLE 0 -#define CEC_OP_HPD_STATE_CP_EDID_ENABLE 1 -#define CEC_OP_HPD_STATE_CP_EDID_DISABLE_ENABLE 2 -#define CEC_OP_HPD_STATE_EDID_DISABLE 3 -#define CEC_OP_HPD_STATE_EDID_ENABLE 4 -#define CEC_OP_HPD_STATE_EDID_DISABLE_ENABLE 5 -#define CEC_MSG_CDC_HPD_REPORT_STATE 0x11 -/* HPD Error Code Operand (hpd_error) */ -#define CEC_OP_HPD_ERROR_NONE 0 -#define CEC_OP_HPD_ERROR_INITIATOR_NOT_CAPABLE 1 -#define CEC_OP_HPD_ERROR_INITIATOR_WRONG_STATE 2 -#define CEC_OP_HPD_ERROR_OTHER 3 -#define CEC_OP_HPD_ERROR_NONE_NO_VIDEO 4 - -/* End of Messages */ - -/* Helper functions to identify the 'special' CEC devices */ - -static inline bool cec_is_2nd_tv(const struct cec_log_addrs *las) -{ - /* - * It is a second TV if the logical address is 14 or 15 and the - * primary device type is a TV. - */ - return las->num_log_addrs && - las->log_addr[0] >= CEC_LOG_ADDR_SPECIFIC && - las->primary_device_type[0] == CEC_OP_PRIM_DEVTYPE_TV; -} - -static inline bool cec_is_processor(const struct cec_log_addrs *las) -{ - /* - * It is a processor if the logical address is 12-15 and the - * primary device type is a Processor. - */ - return las->num_log_addrs && - las->log_addr[0] >= CEC_LOG_ADDR_BACKUP_1 && - las->primary_device_type[0] == CEC_OP_PRIM_DEVTYPE_PROCESSOR; -} - -static inline bool cec_is_switch(const struct cec_log_addrs *las) -{ - /* - * It is a switch if the logical address is 15 and the - * primary device type is a Switch and the CDC-Only flag is not set. - */ - return las->num_log_addrs == 1 && - las->log_addr[0] == CEC_LOG_ADDR_UNREGISTERED && - las->primary_device_type[0] == CEC_OP_PRIM_DEVTYPE_SWITCH && - !(las->flags & CEC_LOG_ADDRS_FL_CDC_ONLY); -} - -static inline bool cec_is_cdc_only(const struct cec_log_addrs *las) -{ - /* - * It is a CDC-only device if the logical address is 15 and the - * primary device type is a Switch and the CDC-Only flag is set. - */ - return las->num_log_addrs == 1 && - las->log_addr[0] == CEC_LOG_ADDR_UNREGISTERED && - las->primary_device_type[0] == CEC_OP_PRIM_DEVTYPE_SWITCH && - (las->flags & CEC_LOG_ADDRS_FL_CDC_ONLY); -} - -#endif diff --git a/include/media/cec.h b/include/media/cec.h index fdb5d600e4bb..717eaf552f3d 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -196,7 +196,7 @@ static inline bool cec_is_sink(const struct cec_adapter *adap) return adap->phys_addr == 0; } -#if IS_ENABLED(CONFIG_MEDIA_CEC) +#if IS_ENABLED(CONFIG_MEDIA_CEC_SUPPORT) struct cec_adapter *cec_allocate_adapter(const struct cec_adap_ops *ops, void *priv, const char *name, u32 caps, u8 available_las, struct device *parent); diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 6965d0909554..c49c448cff92 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -82,6 +82,8 @@ header-y += capi.h header-y += cciss_defs.h header-y += cciss_ioctl.h header-y += cdrom.h +header-y += cec.h +header-y += cec-funcs.h header-y += cgroupstats.h header-y += chio.h header-y += cm4000_cs.h diff --git a/include/uapi/linux/cec-funcs.h b/include/uapi/linux/cec-funcs.h new file mode 100644 index 000000000000..1a1de2169f48 --- /dev/null +++ b/include/uapi/linux/cec-funcs.h @@ -0,0 +1,1965 @@ +/* + * cec - HDMI Consumer Electronics Control message functions + * + * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. + * + * This program is free software; you may redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * Alternatively you can redistribute this file under the terms of the + * BSD license as stated below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * 3. The names of its contributors may not be used to endorse or promote + * products derived from this software without specific prior written + * permission. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef _CEC_UAPI_FUNCS_H +#define _CEC_UAPI_FUNCS_H + +#include + +/* One Touch Play Feature */ +static inline void cec_msg_active_source(struct cec_msg *msg, __u16 phys_addr) +{ + msg->len = 4; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_ACTIVE_SOURCE; + msg->msg[2] = phys_addr >> 8; + msg->msg[3] = phys_addr & 0xff; +} + +static inline void cec_ops_active_source(const struct cec_msg *msg, + __u16 *phys_addr) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; +} + +static inline void cec_msg_image_view_on(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_IMAGE_VIEW_ON; +} + +static inline void cec_msg_text_view_on(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_TEXT_VIEW_ON; +} + + +/* Routing Control Feature */ +static inline void cec_msg_inactive_source(struct cec_msg *msg, + __u16 phys_addr) +{ + msg->len = 4; + msg->msg[1] = CEC_MSG_INACTIVE_SOURCE; + msg->msg[2] = phys_addr >> 8; + msg->msg[3] = phys_addr & 0xff; +} + +static inline void cec_ops_inactive_source(const struct cec_msg *msg, + __u16 *phys_addr) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; +} + +static inline void cec_msg_request_active_source(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_REQUEST_ACTIVE_SOURCE; + msg->reply = reply ? CEC_MSG_ACTIVE_SOURCE : 0; +} + +static inline void cec_msg_routing_information(struct cec_msg *msg, + __u16 phys_addr) +{ + msg->len = 4; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_ROUTING_INFORMATION; + msg->msg[2] = phys_addr >> 8; + msg->msg[3] = phys_addr & 0xff; +} + +static inline void cec_ops_routing_information(const struct cec_msg *msg, + __u16 *phys_addr) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; +} + +static inline void cec_msg_routing_change(struct cec_msg *msg, + bool reply, + __u16 orig_phys_addr, + __u16 new_phys_addr) +{ + msg->len = 6; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_ROUTING_CHANGE; + msg->msg[2] = orig_phys_addr >> 8; + msg->msg[3] = orig_phys_addr & 0xff; + msg->msg[4] = new_phys_addr >> 8; + msg->msg[5] = new_phys_addr & 0xff; + msg->reply = reply ? CEC_MSG_ROUTING_INFORMATION : 0; +} + +static inline void cec_ops_routing_change(const struct cec_msg *msg, + __u16 *orig_phys_addr, + __u16 *new_phys_addr) +{ + *orig_phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *new_phys_addr = (msg->msg[4] << 8) | msg->msg[5]; +} + +static inline void cec_msg_set_stream_path(struct cec_msg *msg, __u16 phys_addr) +{ + msg->len = 4; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_SET_STREAM_PATH; + msg->msg[2] = phys_addr >> 8; + msg->msg[3] = phys_addr & 0xff; +} + +static inline void cec_ops_set_stream_path(const struct cec_msg *msg, + __u16 *phys_addr) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; +} + + +/* Standby Feature */ +static inline void cec_msg_standby(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_STANDBY; +} + + +/* One Touch Record Feature */ +static inline void cec_msg_record_off(struct cec_msg *msg, bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_RECORD_OFF; + msg->reply = reply ? CEC_MSG_RECORD_STATUS : 0; +} + +struct cec_op_arib_data { + __u16 transport_id; + __u16 service_id; + __u16 orig_network_id; +}; + +struct cec_op_atsc_data { + __u16 transport_id; + __u16 program_number; +}; + +struct cec_op_dvb_data { + __u16 transport_id; + __u16 service_id; + __u16 orig_network_id; +}; + +struct cec_op_channel_data { + __u8 channel_number_fmt; + __u16 major; + __u16 minor; +}; + +struct cec_op_digital_service_id { + __u8 service_id_method; + __u8 dig_bcast_system; + union { + struct cec_op_arib_data arib; + struct cec_op_atsc_data atsc; + struct cec_op_dvb_data dvb; + struct cec_op_channel_data channel; + }; +}; + +struct cec_op_record_src { + __u8 type; + union { + struct cec_op_digital_service_id digital; + struct { + __u8 ana_bcast_type; + __u16 ana_freq; + __u8 bcast_system; + } analog; + struct { + __u8 plug; + } ext_plug; + struct { + __u16 phys_addr; + } ext_phys_addr; + }; +}; + +static inline void cec_set_digital_service_id(__u8 *msg, + const struct cec_op_digital_service_id *digital) +{ + *msg++ = (digital->service_id_method << 7) | digital->dig_bcast_system; + if (digital->service_id_method == CEC_OP_SERVICE_ID_METHOD_BY_CHANNEL) { + *msg++ = (digital->channel.channel_number_fmt << 2) | + (digital->channel.major >> 8); + *msg++ = digital->channel.major & 0xff; + *msg++ = digital->channel.minor >> 8; + *msg++ = digital->channel.minor & 0xff; + *msg++ = 0; + *msg++ = 0; + return; + } + switch (digital->dig_bcast_system) { + case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_GEN: + case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_CABLE: + case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_SAT: + case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_T: + *msg++ = digital->atsc.transport_id >> 8; + *msg++ = digital->atsc.transport_id & 0xff; + *msg++ = digital->atsc.program_number >> 8; + *msg++ = digital->atsc.program_number & 0xff; + *msg++ = 0; + *msg++ = 0; + break; + default: + *msg++ = digital->dvb.transport_id >> 8; + *msg++ = digital->dvb.transport_id & 0xff; + *msg++ = digital->dvb.service_id >> 8; + *msg++ = digital->dvb.service_id & 0xff; + *msg++ = digital->dvb.orig_network_id >> 8; + *msg++ = digital->dvb.orig_network_id & 0xff; + break; + } +} + +static inline void cec_get_digital_service_id(const __u8 *msg, + struct cec_op_digital_service_id *digital) +{ + digital->service_id_method = msg[0] >> 7; + digital->dig_bcast_system = msg[0] & 0x7f; + if (digital->service_id_method == CEC_OP_SERVICE_ID_METHOD_BY_CHANNEL) { + digital->channel.channel_number_fmt = msg[1] >> 2; + digital->channel.major = ((msg[1] & 3) << 6) | msg[2]; + digital->channel.minor = (msg[3] << 8) | msg[4]; + return; + } + digital->dvb.transport_id = (msg[1] << 8) | msg[2]; + digital->dvb.service_id = (msg[3] << 8) | msg[4]; + digital->dvb.orig_network_id = (msg[5] << 8) | msg[6]; +} + +static inline void cec_msg_record_on_own(struct cec_msg *msg) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_RECORD_ON; + msg->msg[2] = CEC_OP_RECORD_SRC_OWN; +} + +static inline void cec_msg_record_on_digital(struct cec_msg *msg, + const struct cec_op_digital_service_id *digital) +{ + msg->len = 10; + msg->msg[1] = CEC_MSG_RECORD_ON; + msg->msg[2] = CEC_OP_RECORD_SRC_DIGITAL; + cec_set_digital_service_id(msg->msg + 3, digital); +} + +static inline void cec_msg_record_on_analog(struct cec_msg *msg, + __u8 ana_bcast_type, + __u16 ana_freq, + __u8 bcast_system) +{ + msg->len = 7; + msg->msg[1] = CEC_MSG_RECORD_ON; + msg->msg[2] = CEC_OP_RECORD_SRC_ANALOG; + msg->msg[3] = ana_bcast_type; + msg->msg[4] = ana_freq >> 8; + msg->msg[5] = ana_freq & 0xff; + msg->msg[6] = bcast_system; +} + +static inline void cec_msg_record_on_plug(struct cec_msg *msg, + __u8 plug) +{ + msg->len = 4; + msg->msg[1] = CEC_MSG_RECORD_ON; + msg->msg[2] = CEC_OP_RECORD_SRC_EXT_PLUG; + msg->msg[3] = plug; +} + +static inline void cec_msg_record_on_phys_addr(struct cec_msg *msg, + __u16 phys_addr) +{ + msg->len = 5; + msg->msg[1] = CEC_MSG_RECORD_ON; + msg->msg[2] = CEC_OP_RECORD_SRC_EXT_PHYS_ADDR; + msg->msg[3] = phys_addr >> 8; + msg->msg[4] = phys_addr & 0xff; +} + +static inline void cec_msg_record_on(struct cec_msg *msg, + bool reply, + const struct cec_op_record_src *rec_src) +{ + switch (rec_src->type) { + case CEC_OP_RECORD_SRC_OWN: + cec_msg_record_on_own(msg); + break; + case CEC_OP_RECORD_SRC_DIGITAL: + cec_msg_record_on_digital(msg, &rec_src->digital); + break; + case CEC_OP_RECORD_SRC_ANALOG: + cec_msg_record_on_analog(msg, + rec_src->analog.ana_bcast_type, + rec_src->analog.ana_freq, + rec_src->analog.bcast_system); + break; + case CEC_OP_RECORD_SRC_EXT_PLUG: + cec_msg_record_on_plug(msg, rec_src->ext_plug.plug); + break; + case CEC_OP_RECORD_SRC_EXT_PHYS_ADDR: + cec_msg_record_on_phys_addr(msg, + rec_src->ext_phys_addr.phys_addr); + break; + } + msg->reply = reply ? CEC_MSG_RECORD_STATUS : 0; +} + +static inline void cec_ops_record_on(const struct cec_msg *msg, + struct cec_op_record_src *rec_src) +{ + rec_src->type = msg->msg[2]; + switch (rec_src->type) { + case CEC_OP_RECORD_SRC_OWN: + break; + case CEC_OP_RECORD_SRC_DIGITAL: + cec_get_digital_service_id(msg->msg + 3, &rec_src->digital); + break; + case CEC_OP_RECORD_SRC_ANALOG: + rec_src->analog.ana_bcast_type = msg->msg[3]; + rec_src->analog.ana_freq = + (msg->msg[4] << 8) | msg->msg[5]; + rec_src->analog.bcast_system = msg->msg[6]; + break; + case CEC_OP_RECORD_SRC_EXT_PLUG: + rec_src->ext_plug.plug = msg->msg[3]; + break; + case CEC_OP_RECORD_SRC_EXT_PHYS_ADDR: + rec_src->ext_phys_addr.phys_addr = + (msg->msg[3] << 8) | msg->msg[4]; + break; + } +} + +static inline void cec_msg_record_status(struct cec_msg *msg, __u8 rec_status) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_RECORD_STATUS; + msg->msg[2] = rec_status; +} + +static inline void cec_ops_record_status(const struct cec_msg *msg, + __u8 *rec_status) +{ + *rec_status = msg->msg[2]; +} + +static inline void cec_msg_record_tv_screen(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_RECORD_TV_SCREEN; + msg->reply = reply ? CEC_MSG_RECORD_ON : 0; +} + + +/* Timer Programming Feature */ +static inline void cec_msg_timer_status(struct cec_msg *msg, + __u8 timer_overlap_warning, + __u8 media_info, + __u8 prog_info, + __u8 prog_error, + __u8 duration_hr, + __u8 duration_min) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_TIMER_STATUS; + msg->msg[2] = (timer_overlap_warning << 7) | + (media_info << 5) | + (prog_info ? 0x10 : 0) | + (prog_info ? prog_info : prog_error); + if (prog_info == CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE || + prog_info == CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE || + prog_error == CEC_OP_PROG_ERROR_DUPLICATE) { + msg->len += 2; + msg->msg[3] = ((duration_hr / 10) << 4) | (duration_hr % 10); + msg->msg[4] = ((duration_min / 10) << 4) | (duration_min % 10); + } +} + +static inline void cec_ops_timer_status(const struct cec_msg *msg, + __u8 *timer_overlap_warning, + __u8 *media_info, + __u8 *prog_info, + __u8 *prog_error, + __u8 *duration_hr, + __u8 *duration_min) +{ + *timer_overlap_warning = msg->msg[2] >> 7; + *media_info = (msg->msg[2] >> 5) & 3; + if (msg->msg[2] & 0x10) { + *prog_info = msg->msg[2] & 0xf; + *prog_error = 0; + } else { + *prog_info = 0; + *prog_error = msg->msg[2] & 0xf; + } + if (*prog_info == CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE || + *prog_info == CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE || + *prog_error == CEC_OP_PROG_ERROR_DUPLICATE) { + *duration_hr = (msg->msg[3] >> 4) * 10 + (msg->msg[3] & 0xf); + *duration_min = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); + } else { + *duration_hr = *duration_min = 0; + } +} + +static inline void cec_msg_timer_cleared_status(struct cec_msg *msg, + __u8 timer_cleared_status) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_TIMER_CLEARED_STATUS; + msg->msg[2] = timer_cleared_status; +} + +static inline void cec_ops_timer_cleared_status(const struct cec_msg *msg, + __u8 *timer_cleared_status) +{ + *timer_cleared_status = msg->msg[2]; +} + +static inline void cec_msg_clear_analogue_timer(struct cec_msg *msg, + bool reply, + __u8 day, + __u8 month, + __u8 start_hr, + __u8 start_min, + __u8 duration_hr, + __u8 duration_min, + __u8 recording_seq, + __u8 ana_bcast_type, + __u16 ana_freq, + __u8 bcast_system) +{ + msg->len = 13; + msg->msg[1] = CEC_MSG_CLEAR_ANALOGUE_TIMER; + msg->msg[2] = day; + msg->msg[3] = month; + /* Hours and minutes are in BCD format */ + msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); + msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); + msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); + msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); + msg->msg[8] = recording_seq; + msg->msg[9] = ana_bcast_type; + msg->msg[10] = ana_freq >> 8; + msg->msg[11] = ana_freq & 0xff; + msg->msg[12] = bcast_system; + msg->reply = reply ? CEC_MSG_TIMER_CLEARED_STATUS : 0; +} + +static inline void cec_ops_clear_analogue_timer(const struct cec_msg *msg, + __u8 *day, + __u8 *month, + __u8 *start_hr, + __u8 *start_min, + __u8 *duration_hr, + __u8 *duration_min, + __u8 *recording_seq, + __u8 *ana_bcast_type, + __u16 *ana_freq, + __u8 *bcast_system) +{ + *day = msg->msg[2]; + *month = msg->msg[3]; + /* Hours and minutes are in BCD format */ + *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); + *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); + *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); + *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); + *recording_seq = msg->msg[8]; + *ana_bcast_type = msg->msg[9]; + *ana_freq = (msg->msg[10] << 8) | msg->msg[11]; + *bcast_system = msg->msg[12]; +} + +static inline void cec_msg_clear_digital_timer(struct cec_msg *msg, + bool reply, + __u8 day, + __u8 month, + __u8 start_hr, + __u8 start_min, + __u8 duration_hr, + __u8 duration_min, + __u8 recording_seq, + const struct cec_op_digital_service_id *digital) +{ + msg->len = 16; + msg->reply = reply ? CEC_MSG_TIMER_CLEARED_STATUS : 0; + msg->msg[1] = CEC_MSG_CLEAR_DIGITAL_TIMER; + msg->msg[2] = day; + msg->msg[3] = month; + /* Hours and minutes are in BCD format */ + msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); + msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); + msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); + msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); + msg->msg[8] = recording_seq; + cec_set_digital_service_id(msg->msg + 9, digital); +} + +static inline void cec_ops_clear_digital_timer(const struct cec_msg *msg, + __u8 *day, + __u8 *month, + __u8 *start_hr, + __u8 *start_min, + __u8 *duration_hr, + __u8 *duration_min, + __u8 *recording_seq, + struct cec_op_digital_service_id *digital) +{ + *day = msg->msg[2]; + *month = msg->msg[3]; + /* Hours and minutes are in BCD format */ + *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); + *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); + *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); + *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); + *recording_seq = msg->msg[8]; + cec_get_digital_service_id(msg->msg + 9, digital); +} + +static inline void cec_msg_clear_ext_timer(struct cec_msg *msg, + bool reply, + __u8 day, + __u8 month, + __u8 start_hr, + __u8 start_min, + __u8 duration_hr, + __u8 duration_min, + __u8 recording_seq, + __u8 ext_src_spec, + __u8 plug, + __u16 phys_addr) +{ + msg->len = 13; + msg->msg[1] = CEC_MSG_CLEAR_EXT_TIMER; + msg->msg[2] = day; + msg->msg[3] = month; + /* Hours and minutes are in BCD format */ + msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); + msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); + msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); + msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); + msg->msg[8] = recording_seq; + msg->msg[9] = ext_src_spec; + msg->msg[10] = plug; + msg->msg[11] = phys_addr >> 8; + msg->msg[12] = phys_addr & 0xff; + msg->reply = reply ? CEC_MSG_TIMER_CLEARED_STATUS : 0; +} + +static inline void cec_ops_clear_ext_timer(const struct cec_msg *msg, + __u8 *day, + __u8 *month, + __u8 *start_hr, + __u8 *start_min, + __u8 *duration_hr, + __u8 *duration_min, + __u8 *recording_seq, + __u8 *ext_src_spec, + __u8 *plug, + __u16 *phys_addr) +{ + *day = msg->msg[2]; + *month = msg->msg[3]; + /* Hours and minutes are in BCD format */ + *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); + *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); + *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); + *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); + *recording_seq = msg->msg[8]; + *ext_src_spec = msg->msg[9]; + *plug = msg->msg[10]; + *phys_addr = (msg->msg[11] << 8) | msg->msg[12]; +} + +static inline void cec_msg_set_analogue_timer(struct cec_msg *msg, + bool reply, + __u8 day, + __u8 month, + __u8 start_hr, + __u8 start_min, + __u8 duration_hr, + __u8 duration_min, + __u8 recording_seq, + __u8 ana_bcast_type, + __u16 ana_freq, + __u8 bcast_system) +{ + msg->len = 13; + msg->msg[1] = CEC_MSG_SET_ANALOGUE_TIMER; + msg->msg[2] = day; + msg->msg[3] = month; + /* Hours and minutes are in BCD format */ + msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); + msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); + msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); + msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); + msg->msg[8] = recording_seq; + msg->msg[9] = ana_bcast_type; + msg->msg[10] = ana_freq >> 8; + msg->msg[11] = ana_freq & 0xff; + msg->msg[12] = bcast_system; + msg->reply = reply ? CEC_MSG_TIMER_STATUS : 0; +} + +static inline void cec_ops_set_analogue_timer(const struct cec_msg *msg, + __u8 *day, + __u8 *month, + __u8 *start_hr, + __u8 *start_min, + __u8 *duration_hr, + __u8 *duration_min, + __u8 *recording_seq, + __u8 *ana_bcast_type, + __u16 *ana_freq, + __u8 *bcast_system) +{ + *day = msg->msg[2]; + *month = msg->msg[3]; + /* Hours and minutes are in BCD format */ + *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); + *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); + *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); + *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); + *recording_seq = msg->msg[8]; + *ana_bcast_type = msg->msg[9]; + *ana_freq = (msg->msg[10] << 8) | msg->msg[11]; + *bcast_system = msg->msg[12]; +} + +static inline void cec_msg_set_digital_timer(struct cec_msg *msg, + bool reply, + __u8 day, + __u8 month, + __u8 start_hr, + __u8 start_min, + __u8 duration_hr, + __u8 duration_min, + __u8 recording_seq, + const struct cec_op_digital_service_id *digital) +{ + msg->len = 16; + msg->reply = reply ? CEC_MSG_TIMER_STATUS : 0; + msg->msg[1] = CEC_MSG_SET_DIGITAL_TIMER; + msg->msg[2] = day; + msg->msg[3] = month; + /* Hours and minutes are in BCD format */ + msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); + msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); + msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); + msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); + msg->msg[8] = recording_seq; + cec_set_digital_service_id(msg->msg + 9, digital); +} + +static inline void cec_ops_set_digital_timer(const struct cec_msg *msg, + __u8 *day, + __u8 *month, + __u8 *start_hr, + __u8 *start_min, + __u8 *duration_hr, + __u8 *duration_min, + __u8 *recording_seq, + struct cec_op_digital_service_id *digital) +{ + *day = msg->msg[2]; + *month = msg->msg[3]; + /* Hours and minutes are in BCD format */ + *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); + *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); + *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); + *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); + *recording_seq = msg->msg[8]; + cec_get_digital_service_id(msg->msg + 9, digital); +} + +static inline void cec_msg_set_ext_timer(struct cec_msg *msg, + bool reply, + __u8 day, + __u8 month, + __u8 start_hr, + __u8 start_min, + __u8 duration_hr, + __u8 duration_min, + __u8 recording_seq, + __u8 ext_src_spec, + __u8 plug, + __u16 phys_addr) +{ + msg->len = 13; + msg->msg[1] = CEC_MSG_SET_EXT_TIMER; + msg->msg[2] = day; + msg->msg[3] = month; + /* Hours and minutes are in BCD format */ + msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); + msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); + msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); + msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); + msg->msg[8] = recording_seq; + msg->msg[9] = ext_src_spec; + msg->msg[10] = plug; + msg->msg[11] = phys_addr >> 8; + msg->msg[12] = phys_addr & 0xff; + msg->reply = reply ? CEC_MSG_TIMER_STATUS : 0; +} + +static inline void cec_ops_set_ext_timer(const struct cec_msg *msg, + __u8 *day, + __u8 *month, + __u8 *start_hr, + __u8 *start_min, + __u8 *duration_hr, + __u8 *duration_min, + __u8 *recording_seq, + __u8 *ext_src_spec, + __u8 *plug, + __u16 *phys_addr) +{ + *day = msg->msg[2]; + *month = msg->msg[3]; + /* Hours and minutes are in BCD format */ + *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); + *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); + *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); + *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); + *recording_seq = msg->msg[8]; + *ext_src_spec = msg->msg[9]; + *plug = msg->msg[10]; + *phys_addr = (msg->msg[11] << 8) | msg->msg[12]; +} + +static inline void cec_msg_set_timer_program_title(struct cec_msg *msg, + const char *prog_title) +{ + unsigned int len = strlen(prog_title); + + if (len > 14) + len = 14; + msg->len = 2 + len; + msg->msg[1] = CEC_MSG_SET_TIMER_PROGRAM_TITLE; + memcpy(msg->msg + 2, prog_title, len); +} + +static inline void cec_ops_set_timer_program_title(const struct cec_msg *msg, + char *prog_title) +{ + unsigned int len = msg->len > 2 ? msg->len - 2 : 0; + + if (len > 14) + len = 14; + memcpy(prog_title, msg->msg + 2, len); + prog_title[len] = '\0'; +} + +/* System Information Feature */ +static inline void cec_msg_cec_version(struct cec_msg *msg, __u8 cec_version) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_CEC_VERSION; + msg->msg[2] = cec_version; +} + +static inline void cec_ops_cec_version(const struct cec_msg *msg, + __u8 *cec_version) +{ + *cec_version = msg->msg[2]; +} + +static inline void cec_msg_get_cec_version(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_GET_CEC_VERSION; + msg->reply = reply ? CEC_MSG_CEC_VERSION : 0; +} + +static inline void cec_msg_report_physical_addr(struct cec_msg *msg, + __u16 phys_addr, __u8 prim_devtype) +{ + msg->len = 5; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_REPORT_PHYSICAL_ADDR; + msg->msg[2] = phys_addr >> 8; + msg->msg[3] = phys_addr & 0xff; + msg->msg[4] = prim_devtype; +} + +static inline void cec_ops_report_physical_addr(const struct cec_msg *msg, + __u16 *phys_addr, __u8 *prim_devtype) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *prim_devtype = msg->msg[4]; +} + +static inline void cec_msg_give_physical_addr(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_GIVE_PHYSICAL_ADDR; + msg->reply = reply ? CEC_MSG_REPORT_PHYSICAL_ADDR : 0; +} + +static inline void cec_msg_set_menu_language(struct cec_msg *msg, + const char *language) +{ + msg->len = 5; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_SET_MENU_LANGUAGE; + memcpy(msg->msg + 2, language, 3); +} + +static inline void cec_ops_set_menu_language(const struct cec_msg *msg, + char *language) +{ + memcpy(language, msg->msg + 2, 3); + language[3] = '\0'; +} + +static inline void cec_msg_get_menu_language(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_GET_MENU_LANGUAGE; + msg->reply = reply ? CEC_MSG_SET_MENU_LANGUAGE : 0; +} + +/* + * Assumes a single RC Profile byte and a single Device Features byte, + * i.e. no extended features are supported by this helper function. + * + * As of CEC 2.0 no extended features are defined, should those be added + * in the future, then this function needs to be adapted or a new function + * should be added. + */ +static inline void cec_msg_report_features(struct cec_msg *msg, + __u8 cec_version, __u8 all_device_types, + __u8 rc_profile, __u8 dev_features) +{ + msg->len = 6; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_REPORT_FEATURES; + msg->msg[2] = cec_version; + msg->msg[3] = all_device_types; + msg->msg[4] = rc_profile; + msg->msg[5] = dev_features; +} + +static inline void cec_ops_report_features(const struct cec_msg *msg, + __u8 *cec_version, __u8 *all_device_types, + const __u8 **rc_profile, const __u8 **dev_features) +{ + const __u8 *p = &msg->msg[4]; + + *cec_version = msg->msg[2]; + *all_device_types = msg->msg[3]; + *rc_profile = p; + while (p < &msg->msg[14] && (*p & CEC_OP_FEAT_EXT)) + p++; + if (!(*p & CEC_OP_FEAT_EXT)) { + *dev_features = p + 1; + while (p < &msg->msg[15] && (*p & CEC_OP_FEAT_EXT)) + p++; + } + if (*p & CEC_OP_FEAT_EXT) + *rc_profile = *dev_features = NULL; +} + +static inline void cec_msg_give_features(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_GIVE_FEATURES; + msg->reply = reply ? CEC_MSG_REPORT_FEATURES : 0; +} + +/* Deck Control Feature */ +static inline void cec_msg_deck_control(struct cec_msg *msg, + __u8 deck_control_mode) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_DECK_CONTROL; + msg->msg[2] = deck_control_mode; +} + +static inline void cec_ops_deck_control(const struct cec_msg *msg, + __u8 *deck_control_mode) +{ + *deck_control_mode = msg->msg[2]; +} + +static inline void cec_msg_deck_status(struct cec_msg *msg, + __u8 deck_info) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_DECK_STATUS; + msg->msg[2] = deck_info; +} + +static inline void cec_ops_deck_status(const struct cec_msg *msg, + __u8 *deck_info) +{ + *deck_info = msg->msg[2]; +} + +static inline void cec_msg_give_deck_status(struct cec_msg *msg, + bool reply, + __u8 status_req) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_GIVE_DECK_STATUS; + msg->msg[2] = status_req; + msg->reply = reply ? CEC_MSG_DECK_STATUS : 0; +} + +static inline void cec_ops_give_deck_status(const struct cec_msg *msg, + __u8 *status_req) +{ + *status_req = msg->msg[2]; +} + +static inline void cec_msg_play(struct cec_msg *msg, + __u8 play_mode) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_PLAY; + msg->msg[2] = play_mode; +} + +static inline void cec_ops_play(const struct cec_msg *msg, + __u8 *play_mode) +{ + *play_mode = msg->msg[2]; +} + + +/* Tuner Control Feature */ +struct cec_op_tuner_device_info { + __u8 rec_flag; + __u8 tuner_display_info; + bool is_analog; + union { + struct cec_op_digital_service_id digital; + struct { + __u8 ana_bcast_type; + __u16 ana_freq; + __u8 bcast_system; + } analog; + }; +}; + +static inline void cec_msg_tuner_device_status_analog(struct cec_msg *msg, + __u8 rec_flag, + __u8 tuner_display_info, + __u8 ana_bcast_type, + __u16 ana_freq, + __u8 bcast_system) +{ + msg->len = 7; + msg->msg[1] = CEC_MSG_TUNER_DEVICE_STATUS; + msg->msg[2] = (rec_flag << 7) | tuner_display_info; + msg->msg[3] = ana_bcast_type; + msg->msg[4] = ana_freq >> 8; + msg->msg[5] = ana_freq & 0xff; + msg->msg[6] = bcast_system; +} + +static inline void cec_msg_tuner_device_status_digital(struct cec_msg *msg, + __u8 rec_flag, __u8 tuner_display_info, + const struct cec_op_digital_service_id *digital) +{ + msg->len = 10; + msg->msg[1] = CEC_MSG_TUNER_DEVICE_STATUS; + msg->msg[2] = (rec_flag << 7) | tuner_display_info; + cec_set_digital_service_id(msg->msg + 3, digital); +} + +static inline void cec_msg_tuner_device_status(struct cec_msg *msg, + const struct cec_op_tuner_device_info *tuner_dev_info) +{ + if (tuner_dev_info->is_analog) + cec_msg_tuner_device_status_analog(msg, + tuner_dev_info->rec_flag, + tuner_dev_info->tuner_display_info, + tuner_dev_info->analog.ana_bcast_type, + tuner_dev_info->analog.ana_freq, + tuner_dev_info->analog.bcast_system); + else + cec_msg_tuner_device_status_digital(msg, + tuner_dev_info->rec_flag, + tuner_dev_info->tuner_display_info, + &tuner_dev_info->digital); +} + +static inline void cec_ops_tuner_device_status(const struct cec_msg *msg, + struct cec_op_tuner_device_info *tuner_dev_info) +{ + tuner_dev_info->is_analog = msg->len < 10; + tuner_dev_info->rec_flag = msg->msg[2] >> 7; + tuner_dev_info->tuner_display_info = msg->msg[2] & 0x7f; + if (tuner_dev_info->is_analog) { + tuner_dev_info->analog.ana_bcast_type = msg->msg[3]; + tuner_dev_info->analog.ana_freq = (msg->msg[4] << 8) | msg->msg[5]; + tuner_dev_info->analog.bcast_system = msg->msg[6]; + return; + } + cec_get_digital_service_id(msg->msg + 3, &tuner_dev_info->digital); +} + +static inline void cec_msg_give_tuner_device_status(struct cec_msg *msg, + bool reply, + __u8 status_req) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_GIVE_TUNER_DEVICE_STATUS; + msg->msg[2] = status_req; + msg->reply = reply ? CEC_MSG_TUNER_DEVICE_STATUS : 0; +} + +static inline void cec_ops_give_tuner_device_status(const struct cec_msg *msg, + __u8 *status_req) +{ + *status_req = msg->msg[2]; +} + +static inline void cec_msg_select_analogue_service(struct cec_msg *msg, + __u8 ana_bcast_type, + __u16 ana_freq, + __u8 bcast_system) +{ + msg->len = 6; + msg->msg[1] = CEC_MSG_SELECT_ANALOGUE_SERVICE; + msg->msg[2] = ana_bcast_type; + msg->msg[3] = ana_freq >> 8; + msg->msg[4] = ana_freq & 0xff; + msg->msg[5] = bcast_system; +} + +static inline void cec_ops_select_analogue_service(const struct cec_msg *msg, + __u8 *ana_bcast_type, + __u16 *ana_freq, + __u8 *bcast_system) +{ + *ana_bcast_type = msg->msg[2]; + *ana_freq = (msg->msg[3] << 8) | msg->msg[4]; + *bcast_system = msg->msg[5]; +} + +static inline void cec_msg_select_digital_service(struct cec_msg *msg, + const struct cec_op_digital_service_id *digital) +{ + msg->len = 9; + msg->msg[1] = CEC_MSG_SELECT_DIGITAL_SERVICE; + cec_set_digital_service_id(msg->msg + 2, digital); +} + +static inline void cec_ops_select_digital_service(const struct cec_msg *msg, + struct cec_op_digital_service_id *digital) +{ + cec_get_digital_service_id(msg->msg + 2, digital); +} + +static inline void cec_msg_tuner_step_decrement(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_TUNER_STEP_DECREMENT; +} + +static inline void cec_msg_tuner_step_increment(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_TUNER_STEP_INCREMENT; +} + + +/* Vendor Specific Commands Feature */ +static inline void cec_msg_device_vendor_id(struct cec_msg *msg, __u32 vendor_id) +{ + msg->len = 5; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_DEVICE_VENDOR_ID; + msg->msg[2] = vendor_id >> 16; + msg->msg[3] = (vendor_id >> 8) & 0xff; + msg->msg[4] = vendor_id & 0xff; +} + +static inline void cec_ops_device_vendor_id(const struct cec_msg *msg, + __u32 *vendor_id) +{ + *vendor_id = (msg->msg[2] << 16) | (msg->msg[3] << 8) | msg->msg[4]; +} + +static inline void cec_msg_give_device_vendor_id(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_GIVE_DEVICE_VENDOR_ID; + msg->reply = reply ? CEC_MSG_DEVICE_VENDOR_ID : 0; +} + +static inline void cec_msg_vendor_command(struct cec_msg *msg, + __u8 size, const __u8 *vendor_cmd) +{ + if (size > 14) + size = 14; + msg->len = 2 + size; + msg->msg[1] = CEC_MSG_VENDOR_COMMAND; + memcpy(msg->msg + 2, vendor_cmd, size); +} + +static inline void cec_ops_vendor_command(const struct cec_msg *msg, + __u8 *size, + const __u8 **vendor_cmd) +{ + *size = msg->len - 2; + + if (*size > 14) + *size = 14; + *vendor_cmd = msg->msg + 2; +} + +static inline void cec_msg_vendor_command_with_id(struct cec_msg *msg, + __u32 vendor_id, __u8 size, + const __u8 *vendor_cmd) +{ + if (size > 11) + size = 11; + msg->len = 5 + size; + msg->msg[1] = CEC_MSG_VENDOR_COMMAND_WITH_ID; + msg->msg[2] = vendor_id >> 16; + msg->msg[3] = (vendor_id >> 8) & 0xff; + msg->msg[4] = vendor_id & 0xff; + memcpy(msg->msg + 5, vendor_cmd, size); +} + +static inline void cec_ops_vendor_command_with_id(const struct cec_msg *msg, + __u32 *vendor_id, __u8 *size, + const __u8 **vendor_cmd) +{ + *size = msg->len - 5; + + if (*size > 11) + *size = 11; + *vendor_id = (msg->msg[2] << 16) | (msg->msg[3] << 8) | msg->msg[4]; + *vendor_cmd = msg->msg + 5; +} + +static inline void cec_msg_vendor_remote_button_down(struct cec_msg *msg, + __u8 size, + const __u8 *rc_code) +{ + if (size > 14) + size = 14; + msg->len = 2 + size; + msg->msg[1] = CEC_MSG_VENDOR_REMOTE_BUTTON_DOWN; + memcpy(msg->msg + 2, rc_code, size); +} + +static inline void cec_ops_vendor_remote_button_down(const struct cec_msg *msg, + __u8 *size, + const __u8 **rc_code) +{ + *size = msg->len - 2; + + if (*size > 14) + *size = 14; + *rc_code = msg->msg + 2; +} + +static inline void cec_msg_vendor_remote_button_up(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_VENDOR_REMOTE_BUTTON_UP; +} + + +/* OSD Display Feature */ +static inline void cec_msg_set_osd_string(struct cec_msg *msg, + __u8 disp_ctl, + const char *osd) +{ + unsigned int len = strlen(osd); + + if (len > 13) + len = 13; + msg->len = 3 + len; + msg->msg[1] = CEC_MSG_SET_OSD_STRING; + msg->msg[2] = disp_ctl; + memcpy(msg->msg + 3, osd, len); +} + +static inline void cec_ops_set_osd_string(const struct cec_msg *msg, + __u8 *disp_ctl, + char *osd) +{ + unsigned int len = msg->len > 3 ? msg->len - 3 : 0; + + *disp_ctl = msg->msg[2]; + if (len > 13) + len = 13; + memcpy(osd, msg->msg + 3, len); + osd[len] = '\0'; +} + + +/* Device OSD Transfer Feature */ +static inline void cec_msg_set_osd_name(struct cec_msg *msg, const char *name) +{ + unsigned int len = strlen(name); + + if (len > 14) + len = 14; + msg->len = 2 + len; + msg->msg[1] = CEC_MSG_SET_OSD_NAME; + memcpy(msg->msg + 2, name, len); +} + +static inline void cec_ops_set_osd_name(const struct cec_msg *msg, + char *name) +{ + unsigned int len = msg->len > 2 ? msg->len - 2 : 0; + + if (len > 14) + len = 14; + memcpy(name, msg->msg + 2, len); + name[len] = '\0'; +} + +static inline void cec_msg_give_osd_name(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_GIVE_OSD_NAME; + msg->reply = reply ? CEC_MSG_SET_OSD_NAME : 0; +} + + +/* Device Menu Control Feature */ +static inline void cec_msg_menu_status(struct cec_msg *msg, + __u8 menu_state) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_MENU_STATUS; + msg->msg[2] = menu_state; +} + +static inline void cec_ops_menu_status(const struct cec_msg *msg, + __u8 *menu_state) +{ + *menu_state = msg->msg[2]; +} + +static inline void cec_msg_menu_request(struct cec_msg *msg, + bool reply, + __u8 menu_req) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_MENU_REQUEST; + msg->msg[2] = menu_req; + msg->reply = reply ? CEC_MSG_MENU_STATUS : 0; +} + +static inline void cec_ops_menu_request(const struct cec_msg *msg, + __u8 *menu_req) +{ + *menu_req = msg->msg[2]; +} + +struct cec_op_ui_command { + __u8 ui_cmd; + bool has_opt_arg; + union { + struct cec_op_channel_data channel_identifier; + __u8 ui_broadcast_type; + __u8 ui_sound_presentation_control; + __u8 play_mode; + __u8 ui_function_media; + __u8 ui_function_select_av_input; + __u8 ui_function_select_audio_input; + }; +}; + +static inline void cec_msg_user_control_pressed(struct cec_msg *msg, + const struct cec_op_ui_command *ui_cmd) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_USER_CONTROL_PRESSED; + msg->msg[2] = ui_cmd->ui_cmd; + if (!ui_cmd->has_opt_arg) + return; + switch (ui_cmd->ui_cmd) { + case 0x56: + case 0x57: + case 0x60: + case 0x68: + case 0x69: + case 0x6a: + /* The optional operand is one byte for all these ui commands */ + msg->len++; + msg->msg[3] = ui_cmd->play_mode; + break; + case 0x67: + msg->len += 4; + msg->msg[3] = (ui_cmd->channel_identifier.channel_number_fmt << 2) | + (ui_cmd->channel_identifier.major >> 8); + msg->msg[4] = ui_cmd->channel_identifier.major & 0xff; + msg->msg[5] = ui_cmd->channel_identifier.minor >> 8; + msg->msg[6] = ui_cmd->channel_identifier.minor & 0xff; + break; + } +} + +static inline void cec_ops_user_control_pressed(const struct cec_msg *msg, + struct cec_op_ui_command *ui_cmd) +{ + ui_cmd->ui_cmd = msg->msg[2]; + ui_cmd->has_opt_arg = false; + if (msg->len == 3) + return; + switch (ui_cmd->ui_cmd) { + case 0x56: + case 0x57: + case 0x60: + case 0x68: + case 0x69: + case 0x6a: + /* The optional operand is one byte for all these ui commands */ + ui_cmd->play_mode = msg->msg[3]; + ui_cmd->has_opt_arg = true; + break; + case 0x67: + if (msg->len < 7) + break; + ui_cmd->has_opt_arg = true; + ui_cmd->channel_identifier.channel_number_fmt = msg->msg[3] >> 2; + ui_cmd->channel_identifier.major = ((msg->msg[3] & 3) << 6) | msg->msg[4]; + ui_cmd->channel_identifier.minor = (msg->msg[5] << 8) | msg->msg[6]; + break; + } +} + +static inline void cec_msg_user_control_released(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_USER_CONTROL_RELEASED; +} + +/* Remote Control Passthrough Feature */ + +/* Power Status Feature */ +static inline void cec_msg_report_power_status(struct cec_msg *msg, + __u8 pwr_state) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_REPORT_POWER_STATUS; + msg->msg[2] = pwr_state; +} + +static inline void cec_ops_report_power_status(const struct cec_msg *msg, + __u8 *pwr_state) +{ + *pwr_state = msg->msg[2]; +} + +static inline void cec_msg_give_device_power_status(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_GIVE_DEVICE_POWER_STATUS; + msg->reply = reply ? CEC_MSG_REPORT_POWER_STATUS : 0; +} + +/* General Protocol Messages */ +static inline void cec_msg_feature_abort(struct cec_msg *msg, + __u8 abort_msg, __u8 reason) +{ + msg->len = 4; + msg->msg[1] = CEC_MSG_FEATURE_ABORT; + msg->msg[2] = abort_msg; + msg->msg[3] = reason; +} + +static inline void cec_ops_feature_abort(const struct cec_msg *msg, + __u8 *abort_msg, __u8 *reason) +{ + *abort_msg = msg->msg[2]; + *reason = msg->msg[3]; +} + +/* This changes the current message into a feature abort message */ +static inline void cec_msg_reply_feature_abort(struct cec_msg *msg, __u8 reason) +{ + cec_msg_set_reply_to(msg, msg); + msg->len = 4; + msg->msg[2] = msg->msg[1]; + msg->msg[3] = reason; + msg->msg[1] = CEC_MSG_FEATURE_ABORT; +} + +static inline void cec_msg_abort(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_ABORT; +} + + +/* System Audio Control Feature */ +static inline void cec_msg_report_audio_status(struct cec_msg *msg, + __u8 aud_mute_status, + __u8 aud_vol_status) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_REPORT_AUDIO_STATUS; + msg->msg[2] = (aud_mute_status << 7) | (aud_vol_status & 0x7f); +} + +static inline void cec_ops_report_audio_status(const struct cec_msg *msg, + __u8 *aud_mute_status, + __u8 *aud_vol_status) +{ + *aud_mute_status = msg->msg[2] >> 7; + *aud_vol_status = msg->msg[2] & 0x7f; +} + +static inline void cec_msg_give_audio_status(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_GIVE_AUDIO_STATUS; + msg->reply = reply ? CEC_MSG_REPORT_AUDIO_STATUS : 0; +} + +static inline void cec_msg_set_system_audio_mode(struct cec_msg *msg, + __u8 sys_aud_status) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_SET_SYSTEM_AUDIO_MODE; + msg->msg[2] = sys_aud_status; +} + +static inline void cec_ops_set_system_audio_mode(const struct cec_msg *msg, + __u8 *sys_aud_status) +{ + *sys_aud_status = msg->msg[2]; +} + +static inline void cec_msg_system_audio_mode_request(struct cec_msg *msg, + bool reply, + __u16 phys_addr) +{ + msg->len = phys_addr == 0xffff ? 2 : 4; + msg->msg[1] = CEC_MSG_SYSTEM_AUDIO_MODE_REQUEST; + msg->msg[2] = phys_addr >> 8; + msg->msg[3] = phys_addr & 0xff; + msg->reply = reply ? CEC_MSG_SET_SYSTEM_AUDIO_MODE : 0; + +} + +static inline void cec_ops_system_audio_mode_request(const struct cec_msg *msg, + __u16 *phys_addr) +{ + if (msg->len < 4) + *phys_addr = 0xffff; + else + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; +} + +static inline void cec_msg_system_audio_mode_status(struct cec_msg *msg, + __u8 sys_aud_status) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_SYSTEM_AUDIO_MODE_STATUS; + msg->msg[2] = sys_aud_status; +} + +static inline void cec_ops_system_audio_mode_status(const struct cec_msg *msg, + __u8 *sys_aud_status) +{ + *sys_aud_status = msg->msg[2]; +} + +static inline void cec_msg_give_system_audio_mode_status(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_GIVE_SYSTEM_AUDIO_MODE_STATUS; + msg->reply = reply ? CEC_MSG_SYSTEM_AUDIO_MODE_STATUS : 0; +} + +static inline void cec_msg_report_short_audio_descriptor(struct cec_msg *msg, + __u8 num_descriptors, + const __u32 *descriptors) +{ + unsigned int i; + + if (num_descriptors > 4) + num_descriptors = 4; + msg->len = 2 + num_descriptors * 3; + msg->msg[1] = CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR; + for (i = 0; i < num_descriptors; i++) { + msg->msg[2 + i * 3] = (descriptors[i] >> 16) & 0xff; + msg->msg[3 + i * 3] = (descriptors[i] >> 8) & 0xff; + msg->msg[4 + i * 3] = descriptors[i] & 0xff; + } +} + +static inline void cec_ops_report_short_audio_descriptor(const struct cec_msg *msg, + __u8 *num_descriptors, + __u32 *descriptors) +{ + unsigned int i; + + *num_descriptors = (msg->len - 2) / 3; + if (*num_descriptors > 4) + *num_descriptors = 4; + for (i = 0; i < *num_descriptors; i++) + descriptors[i] = (msg->msg[2 + i * 3] << 16) | + (msg->msg[3 + i * 3] << 8) | + msg->msg[4 + i * 3]; +} + +static inline void cec_msg_request_short_audio_descriptor(struct cec_msg *msg, + bool reply, + __u8 num_descriptors, + const __u8 *audio_format_id, + const __u8 *audio_format_code) +{ + unsigned int i; + + if (num_descriptors > 4) + num_descriptors = 4; + msg->len = 2 + num_descriptors; + msg->msg[1] = CEC_MSG_REQUEST_SHORT_AUDIO_DESCRIPTOR; + msg->reply = reply ? CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR : 0; + for (i = 0; i < num_descriptors; i++) + msg->msg[2 + i] = (audio_format_id[i] << 6) | + (audio_format_code[i] & 0x3f); +} + +static inline void cec_ops_request_short_audio_descriptor(const struct cec_msg *msg, + __u8 *num_descriptors, + __u8 *audio_format_id, + __u8 *audio_format_code) +{ + unsigned int i; + + *num_descriptors = msg->len - 2; + if (*num_descriptors > 4) + *num_descriptors = 4; + for (i = 0; i < *num_descriptors; i++) { + audio_format_id[i] = msg->msg[2 + i] >> 6; + audio_format_code[i] = msg->msg[2 + i] & 0x3f; + } +} + + +/* Audio Rate Control Feature */ +static inline void cec_msg_set_audio_rate(struct cec_msg *msg, + __u8 audio_rate) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_SET_AUDIO_RATE; + msg->msg[2] = audio_rate; +} + +static inline void cec_ops_set_audio_rate(const struct cec_msg *msg, + __u8 *audio_rate) +{ + *audio_rate = msg->msg[2]; +} + + +/* Audio Return Channel Control Feature */ +static inline void cec_msg_report_arc_initiated(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_REPORT_ARC_INITIATED; +} + +static inline void cec_msg_initiate_arc(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_INITIATE_ARC; + msg->reply = reply ? CEC_MSG_REPORT_ARC_INITIATED : 0; +} + +static inline void cec_msg_request_arc_initiation(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_REQUEST_ARC_INITIATION; + msg->reply = reply ? CEC_MSG_INITIATE_ARC : 0; +} + +static inline void cec_msg_report_arc_terminated(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_REPORT_ARC_TERMINATED; +} + +static inline void cec_msg_terminate_arc(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_TERMINATE_ARC; + msg->reply = reply ? CEC_MSG_REPORT_ARC_TERMINATED : 0; +} + +static inline void cec_msg_request_arc_termination(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_REQUEST_ARC_TERMINATION; + msg->reply = reply ? CEC_MSG_TERMINATE_ARC : 0; +} + + +/* Dynamic Audio Lipsync Feature */ +/* Only for CEC 2.0 and up */ +static inline void cec_msg_report_current_latency(struct cec_msg *msg, + __u16 phys_addr, + __u8 video_latency, + __u8 low_latency_mode, + __u8 audio_out_compensated, + __u8 audio_out_delay) +{ + msg->len = 7; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_REPORT_CURRENT_LATENCY; + msg->msg[2] = phys_addr >> 8; + msg->msg[3] = phys_addr & 0xff; + msg->msg[4] = video_latency; + msg->msg[5] = (low_latency_mode << 2) | audio_out_compensated; + msg->msg[6] = audio_out_delay; +} + +static inline void cec_ops_report_current_latency(const struct cec_msg *msg, + __u16 *phys_addr, + __u8 *video_latency, + __u8 *low_latency_mode, + __u8 *audio_out_compensated, + __u8 *audio_out_delay) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *video_latency = msg->msg[4]; + *low_latency_mode = (msg->msg[5] >> 2) & 1; + *audio_out_compensated = msg->msg[5] & 3; + *audio_out_delay = msg->msg[6]; +} + +static inline void cec_msg_request_current_latency(struct cec_msg *msg, + bool reply, + __u16 phys_addr) +{ + msg->len = 4; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_REQUEST_CURRENT_LATENCY; + msg->msg[2] = phys_addr >> 8; + msg->msg[3] = phys_addr & 0xff; + msg->reply = reply ? CEC_MSG_REPORT_CURRENT_LATENCY : 0; +} + +static inline void cec_ops_request_current_latency(const struct cec_msg *msg, + __u16 *phys_addr) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; +} + + +/* Capability Discovery and Control Feature */ +static inline void cec_msg_cdc_hec_inquire_state(struct cec_msg *msg, + __u16 phys_addr1, + __u16 phys_addr2) +{ + msg->len = 9; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_CDC_MESSAGE; + /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ + msg->msg[4] = CEC_MSG_CDC_HEC_INQUIRE_STATE; + msg->msg[5] = phys_addr1 >> 8; + msg->msg[6] = phys_addr1 & 0xff; + msg->msg[7] = phys_addr2 >> 8; + msg->msg[8] = phys_addr2 & 0xff; +} + +static inline void cec_ops_cdc_hec_inquire_state(const struct cec_msg *msg, + __u16 *phys_addr, + __u16 *phys_addr1, + __u16 *phys_addr2) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *phys_addr1 = (msg->msg[5] << 8) | msg->msg[6]; + *phys_addr2 = (msg->msg[7] << 8) | msg->msg[8]; +} + +static inline void cec_msg_cdc_hec_report_state(struct cec_msg *msg, + __u16 target_phys_addr, + __u8 hec_func_state, + __u8 host_func_state, + __u8 enc_func_state, + __u8 cdc_errcode, + __u8 has_field, + __u16 hec_field) +{ + msg->len = has_field ? 10 : 8; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_CDC_MESSAGE; + /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ + msg->msg[4] = CEC_MSG_CDC_HEC_REPORT_STATE; + msg->msg[5] = target_phys_addr >> 8; + msg->msg[6] = target_phys_addr & 0xff; + msg->msg[7] = (hec_func_state << 6) | + (host_func_state << 4) | + (enc_func_state << 2) | + cdc_errcode; + if (has_field) { + msg->msg[8] = hec_field >> 8; + msg->msg[9] = hec_field & 0xff; + } +} + +static inline void cec_ops_cdc_hec_report_state(const struct cec_msg *msg, + __u16 *phys_addr, + __u16 *target_phys_addr, + __u8 *hec_func_state, + __u8 *host_func_state, + __u8 *enc_func_state, + __u8 *cdc_errcode, + __u8 *has_field, + __u16 *hec_field) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *target_phys_addr = (msg->msg[5] << 8) | msg->msg[6]; + *hec_func_state = msg->msg[7] >> 6; + *host_func_state = (msg->msg[7] >> 4) & 3; + *enc_func_state = (msg->msg[7] >> 4) & 3; + *cdc_errcode = msg->msg[7] & 3; + *has_field = msg->len >= 10; + *hec_field = *has_field ? ((msg->msg[8] << 8) | msg->msg[9]) : 0; +} + +static inline void cec_msg_cdc_hec_set_state(struct cec_msg *msg, + __u16 phys_addr1, + __u16 phys_addr2, + __u8 hec_set_state, + __u16 phys_addr3, + __u16 phys_addr4, + __u16 phys_addr5) +{ + msg->len = 10; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_CDC_MESSAGE; + /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ + msg->msg[4] = CEC_MSG_CDC_HEC_INQUIRE_STATE; + msg->msg[5] = phys_addr1 >> 8; + msg->msg[6] = phys_addr1 & 0xff; + msg->msg[7] = phys_addr2 >> 8; + msg->msg[8] = phys_addr2 & 0xff; + msg->msg[9] = hec_set_state; + if (phys_addr3 != CEC_PHYS_ADDR_INVALID) { + msg->msg[msg->len++] = phys_addr3 >> 8; + msg->msg[msg->len++] = phys_addr3 & 0xff; + if (phys_addr4 != CEC_PHYS_ADDR_INVALID) { + msg->msg[msg->len++] = phys_addr4 >> 8; + msg->msg[msg->len++] = phys_addr4 & 0xff; + if (phys_addr5 != CEC_PHYS_ADDR_INVALID) { + msg->msg[msg->len++] = phys_addr5 >> 8; + msg->msg[msg->len++] = phys_addr5 & 0xff; + } + } + } +} + +static inline void cec_ops_cdc_hec_set_state(const struct cec_msg *msg, + __u16 *phys_addr, + __u16 *phys_addr1, + __u16 *phys_addr2, + __u8 *hec_set_state, + __u16 *phys_addr3, + __u16 *phys_addr4, + __u16 *phys_addr5) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *phys_addr1 = (msg->msg[5] << 8) | msg->msg[6]; + *phys_addr2 = (msg->msg[7] << 8) | msg->msg[8]; + *hec_set_state = msg->msg[9]; + *phys_addr3 = *phys_addr4 = *phys_addr5 = CEC_PHYS_ADDR_INVALID; + if (msg->len >= 12) + *phys_addr3 = (msg->msg[10] << 8) | msg->msg[11]; + if (msg->len >= 14) + *phys_addr4 = (msg->msg[12] << 8) | msg->msg[13]; + if (msg->len >= 16) + *phys_addr5 = (msg->msg[14] << 8) | msg->msg[15]; +} + +static inline void cec_msg_cdc_hec_set_state_adjacent(struct cec_msg *msg, + __u16 phys_addr1, + __u8 hec_set_state) +{ + msg->len = 8; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_CDC_MESSAGE; + /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ + msg->msg[4] = CEC_MSG_CDC_HEC_SET_STATE_ADJACENT; + msg->msg[5] = phys_addr1 >> 8; + msg->msg[6] = phys_addr1 & 0xff; + msg->msg[7] = hec_set_state; +} + +static inline void cec_ops_cdc_hec_set_state_adjacent(const struct cec_msg *msg, + __u16 *phys_addr, + __u16 *phys_addr1, + __u8 *hec_set_state) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *phys_addr1 = (msg->msg[5] << 8) | msg->msg[6]; + *hec_set_state = msg->msg[7]; +} + +static inline void cec_msg_cdc_hec_request_deactivation(struct cec_msg *msg, + __u16 phys_addr1, + __u16 phys_addr2, + __u16 phys_addr3) +{ + msg->len = 11; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_CDC_MESSAGE; + /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ + msg->msg[4] = CEC_MSG_CDC_HEC_REQUEST_DEACTIVATION; + msg->msg[5] = phys_addr1 >> 8; + msg->msg[6] = phys_addr1 & 0xff; + msg->msg[7] = phys_addr2 >> 8; + msg->msg[8] = phys_addr2 & 0xff; + msg->msg[9] = phys_addr3 >> 8; + msg->msg[10] = phys_addr3 & 0xff; +} + +static inline void cec_ops_cdc_hec_request_deactivation(const struct cec_msg *msg, + __u16 *phys_addr, + __u16 *phys_addr1, + __u16 *phys_addr2, + __u16 *phys_addr3) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *phys_addr1 = (msg->msg[5] << 8) | msg->msg[6]; + *phys_addr2 = (msg->msg[7] << 8) | msg->msg[8]; + *phys_addr3 = (msg->msg[9] << 8) | msg->msg[10]; +} + +static inline void cec_msg_cdc_hec_notify_alive(struct cec_msg *msg) +{ + msg->len = 5; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_CDC_MESSAGE; + /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ + msg->msg[4] = CEC_MSG_CDC_HEC_NOTIFY_ALIVE; +} + +static inline void cec_ops_cdc_hec_notify_alive(const struct cec_msg *msg, + __u16 *phys_addr) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; +} + +static inline void cec_msg_cdc_hec_discover(struct cec_msg *msg) +{ + msg->len = 5; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_CDC_MESSAGE; + /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ + msg->msg[4] = CEC_MSG_CDC_HEC_DISCOVER; +} + +static inline void cec_ops_cdc_hec_discover(const struct cec_msg *msg, + __u16 *phys_addr) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; +} + +static inline void cec_msg_cdc_hpd_set_state(struct cec_msg *msg, + __u8 input_port, + __u8 hpd_state) +{ + msg->len = 6; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_CDC_MESSAGE; + /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ + msg->msg[4] = CEC_MSG_CDC_HPD_SET_STATE; + msg->msg[5] = (input_port << 4) | hpd_state; +} + +static inline void cec_ops_cdc_hpd_set_state(const struct cec_msg *msg, + __u16 *phys_addr, + __u8 *input_port, + __u8 *hpd_state) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *input_port = msg->msg[5] >> 4; + *hpd_state = msg->msg[5] & 0xf; +} + +static inline void cec_msg_cdc_hpd_report_state(struct cec_msg *msg, + __u8 hpd_state, + __u8 hpd_error) +{ + msg->len = 6; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_CDC_MESSAGE; + /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ + msg->msg[4] = CEC_MSG_CDC_HPD_REPORT_STATE; + msg->msg[5] = (hpd_state << 4) | hpd_error; +} + +static inline void cec_ops_cdc_hpd_report_state(const struct cec_msg *msg, + __u16 *phys_addr, + __u8 *hpd_state, + __u8 *hpd_error) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *hpd_state = msg->msg[5] >> 4; + *hpd_error = msg->msg[5] & 0xf; +} + +#endif diff --git a/include/uapi/linux/cec.h b/include/uapi/linux/cec.h new file mode 100644 index 000000000000..f4ec0af67707 --- /dev/null +++ b/include/uapi/linux/cec.h @@ -0,0 +1,1065 @@ +/* + * cec - HDMI Consumer Electronics Control public header + * + * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. + * + * This program is free software; you may redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * Alternatively you can redistribute this file under the terms of the + * BSD license as stated below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * 3. The names of its contributors may not be used to endorse or promote + * products derived from this software without specific prior written + * permission. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef _CEC_UAPI_H +#define _CEC_UAPI_H + +#include + +#define CEC_MAX_MSG_SIZE 16 + +/** + * struct cec_msg - CEC message structure. + * @tx_ts: Timestamp in nanoseconds using CLOCK_MONOTONIC. Set by the + * driver when the message transmission has finished. + * @rx_ts: Timestamp in nanoseconds using CLOCK_MONOTONIC. Set by the + * driver when the message was received. + * @len: Length in bytes of the message. + * @timeout: The timeout (in ms) that is used to timeout CEC_RECEIVE. + * Set to 0 if you want to wait forever. This timeout can also be + * used with CEC_TRANSMIT as the timeout for waiting for a reply. + * If 0, then it will use a 1 second timeout instead of waiting + * forever as is done with CEC_RECEIVE. + * @sequence: The framework assigns a sequence number to messages that are + * sent. This can be used to track replies to previously sent + * messages. + * @flags: Set to 0. + * @msg: The message payload. + * @reply: This field is ignored with CEC_RECEIVE and is only used by + * CEC_TRANSMIT. If non-zero, then wait for a reply with this + * opcode. Set to CEC_MSG_FEATURE_ABORT if you want to wait for + * a possible ABORT reply. If there was an error when sending the + * msg or FeatureAbort was returned, then reply is set to 0. + * If reply is non-zero upon return, then len/msg are set to + * the received message. + * If reply is zero upon return and status has the + * CEC_TX_STATUS_FEATURE_ABORT bit set, then len/msg are set to + * the received feature abort message. + * If reply is zero upon return and status has the + * CEC_TX_STATUS_MAX_RETRIES bit set, then no reply was seen at + * all. If reply is non-zero for CEC_TRANSMIT and the message is a + * broadcast, then -EINVAL is returned. + * if reply is non-zero, then timeout is set to 1000 (the required + * maximum response time). + * @rx_status: The message receive status bits. Set by the driver. + * @tx_status: The message transmit status bits. Set by the driver. + * @tx_arb_lost_cnt: The number of 'Arbitration Lost' events. Set by the driver. + * @tx_nack_cnt: The number of 'Not Acknowledged' events. Set by the driver. + * @tx_low_drive_cnt: The number of 'Low Drive Detected' events. Set by the + * driver. + * @tx_error_cnt: The number of 'Error' events. Set by the driver. + */ +struct cec_msg { + __u64 tx_ts; + __u64 rx_ts; + __u32 len; + __u32 timeout; + __u32 sequence; + __u32 flags; + __u8 msg[CEC_MAX_MSG_SIZE]; + __u8 reply; + __u8 rx_status; + __u8 tx_status; + __u8 tx_arb_lost_cnt; + __u8 tx_nack_cnt; + __u8 tx_low_drive_cnt; + __u8 tx_error_cnt; +}; + +/** + * cec_msg_initiator - return the initiator's logical address. + * @msg: the message structure + */ +static inline __u8 cec_msg_initiator(const struct cec_msg *msg) +{ + return msg->msg[0] >> 4; +} + +/** + * cec_msg_destination - return the destination's logical address. + * @msg: the message structure + */ +static inline __u8 cec_msg_destination(const struct cec_msg *msg) +{ + return msg->msg[0] & 0xf; +} + +/** + * cec_msg_opcode - return the opcode of the message, -1 for poll + * @msg: the message structure + */ +static inline int cec_msg_opcode(const struct cec_msg *msg) +{ + return msg->len > 1 ? msg->msg[1] : -1; +} + +/** + * cec_msg_is_broadcast - return true if this is a broadcast message. + * @msg: the message structure + */ +static inline bool cec_msg_is_broadcast(const struct cec_msg *msg) +{ + return (msg->msg[0] & 0xf) == 0xf; +} + +/** + * cec_msg_init - initialize the message structure. + * @msg: the message structure + * @initiator: the logical address of the initiator + * @destination:the logical address of the destination (0xf for broadcast) + * + * The whole structure is zeroed, the len field is set to 1 (i.e. a poll + * message) and the initiator and destination are filled in. + */ +static inline void cec_msg_init(struct cec_msg *msg, + __u8 initiator, __u8 destination) +{ + memset(msg, 0, sizeof(*msg)); + msg->msg[0] = (initiator << 4) | destination; + msg->len = 1; +} + +/** + * cec_msg_set_reply_to - fill in destination/initiator in a reply message. + * @msg: the message structure for the reply + * @orig: the original message structure + * + * Set the msg destination to the orig initiator and the msg initiator to the + * orig destination. Note that msg and orig may be the same pointer, in which + * case the change is done in place. + */ +static inline void cec_msg_set_reply_to(struct cec_msg *msg, + struct cec_msg *orig) +{ + /* The destination becomes the initiator and vice versa */ + msg->msg[0] = (cec_msg_destination(orig) << 4) | + cec_msg_initiator(orig); + msg->reply = msg->timeout = 0; +} + +/* cec_msg flags field */ +#define CEC_MSG_FL_REPLY_TO_FOLLOWERS (1 << 0) + +/* cec_msg tx/rx_status field */ +#define CEC_TX_STATUS_OK (1 << 0) +#define CEC_TX_STATUS_ARB_LOST (1 << 1) +#define CEC_TX_STATUS_NACK (1 << 2) +#define CEC_TX_STATUS_LOW_DRIVE (1 << 3) +#define CEC_TX_STATUS_ERROR (1 << 4) +#define CEC_TX_STATUS_MAX_RETRIES (1 << 5) + +#define CEC_RX_STATUS_OK (1 << 0) +#define CEC_RX_STATUS_TIMEOUT (1 << 1) +#define CEC_RX_STATUS_FEATURE_ABORT (1 << 2) + +static inline bool cec_msg_status_is_ok(const struct cec_msg *msg) +{ + if (msg->tx_status && !(msg->tx_status & CEC_TX_STATUS_OK)) + return false; + if (msg->rx_status && !(msg->rx_status & CEC_RX_STATUS_OK)) + return false; + if (!msg->tx_status && !msg->rx_status) + return false; + return !(msg->rx_status & CEC_RX_STATUS_FEATURE_ABORT); +} + +#define CEC_LOG_ADDR_INVALID 0xff +#define CEC_PHYS_ADDR_INVALID 0xffff + +/* + * The maximum number of logical addresses one device can be assigned to. + * The CEC 2.0 spec allows for only 2 logical addresses at the moment. The + * Analog Devices CEC hardware supports 3. So let's go wild and go for 4. + */ +#define CEC_MAX_LOG_ADDRS 4 + +/* The logical addresses defined by CEC 2.0 */ +#define CEC_LOG_ADDR_TV 0 +#define CEC_LOG_ADDR_RECORD_1 1 +#define CEC_LOG_ADDR_RECORD_2 2 +#define CEC_LOG_ADDR_TUNER_1 3 +#define CEC_LOG_ADDR_PLAYBACK_1 4 +#define CEC_LOG_ADDR_AUDIOSYSTEM 5 +#define CEC_LOG_ADDR_TUNER_2 6 +#define CEC_LOG_ADDR_TUNER_3 7 +#define CEC_LOG_ADDR_PLAYBACK_2 8 +#define CEC_LOG_ADDR_RECORD_3 9 +#define CEC_LOG_ADDR_TUNER_4 10 +#define CEC_LOG_ADDR_PLAYBACK_3 11 +#define CEC_LOG_ADDR_BACKUP_1 12 +#define CEC_LOG_ADDR_BACKUP_2 13 +#define CEC_LOG_ADDR_SPECIFIC 14 +#define CEC_LOG_ADDR_UNREGISTERED 15 /* as initiator address */ +#define CEC_LOG_ADDR_BROADCAST 15 /* ad destination address */ + +/* The logical address types that the CEC device wants to claim */ +#define CEC_LOG_ADDR_TYPE_TV 0 +#define CEC_LOG_ADDR_TYPE_RECORD 1 +#define CEC_LOG_ADDR_TYPE_TUNER 2 +#define CEC_LOG_ADDR_TYPE_PLAYBACK 3 +#define CEC_LOG_ADDR_TYPE_AUDIOSYSTEM 4 +#define CEC_LOG_ADDR_TYPE_SPECIFIC 5 +#define CEC_LOG_ADDR_TYPE_UNREGISTERED 6 +/* + * Switches should use UNREGISTERED. + * Processors should use SPECIFIC. + */ + +#define CEC_LOG_ADDR_MASK_TV (1 << CEC_LOG_ADDR_TV) +#define CEC_LOG_ADDR_MASK_RECORD ((1 << CEC_LOG_ADDR_RECORD_1) | \ + (1 << CEC_LOG_ADDR_RECORD_2) | \ + (1 << CEC_LOG_ADDR_RECORD_3)) +#define CEC_LOG_ADDR_MASK_TUNER ((1 << CEC_LOG_ADDR_TUNER_1) | \ + (1 << CEC_LOG_ADDR_TUNER_2) | \ + (1 << CEC_LOG_ADDR_TUNER_3) | \ + (1 << CEC_LOG_ADDR_TUNER_4)) +#define CEC_LOG_ADDR_MASK_PLAYBACK ((1 << CEC_LOG_ADDR_PLAYBACK_1) | \ + (1 << CEC_LOG_ADDR_PLAYBACK_2) | \ + (1 << CEC_LOG_ADDR_PLAYBACK_3)) +#define CEC_LOG_ADDR_MASK_AUDIOSYSTEM (1 << CEC_LOG_ADDR_AUDIOSYSTEM) +#define CEC_LOG_ADDR_MASK_BACKUP ((1 << CEC_LOG_ADDR_BACKUP_1) | \ + (1 << CEC_LOG_ADDR_BACKUP_2)) +#define CEC_LOG_ADDR_MASK_SPECIFIC (1 << CEC_LOG_ADDR_SPECIFIC) +#define CEC_LOG_ADDR_MASK_UNREGISTERED (1 << CEC_LOG_ADDR_UNREGISTERED) + +static inline bool cec_has_tv(__u16 log_addr_mask) +{ + return log_addr_mask & CEC_LOG_ADDR_MASK_TV; +} + +static inline bool cec_has_record(__u16 log_addr_mask) +{ + return log_addr_mask & CEC_LOG_ADDR_MASK_RECORD; +} + +static inline bool cec_has_tuner(__u16 log_addr_mask) +{ + return log_addr_mask & CEC_LOG_ADDR_MASK_TUNER; +} + +static inline bool cec_has_playback(__u16 log_addr_mask) +{ + return log_addr_mask & CEC_LOG_ADDR_MASK_PLAYBACK; +} + +static inline bool cec_has_audiosystem(__u16 log_addr_mask) +{ + return log_addr_mask & CEC_LOG_ADDR_MASK_AUDIOSYSTEM; +} + +static inline bool cec_has_backup(__u16 log_addr_mask) +{ + return log_addr_mask & CEC_LOG_ADDR_MASK_BACKUP; +} + +static inline bool cec_has_specific(__u16 log_addr_mask) +{ + return log_addr_mask & CEC_LOG_ADDR_MASK_SPECIFIC; +} + +static inline bool cec_is_unregistered(__u16 log_addr_mask) +{ + return log_addr_mask & CEC_LOG_ADDR_MASK_UNREGISTERED; +} + +static inline bool cec_is_unconfigured(__u16 log_addr_mask) +{ + return log_addr_mask == 0; +} + +/* + * Use this if there is no vendor ID (CEC_G_VENDOR_ID) or if the vendor ID + * should be disabled (CEC_S_VENDOR_ID) + */ +#define CEC_VENDOR_ID_NONE 0xffffffff + +/* The message handling modes */ +/* Modes for initiator */ +#define CEC_MODE_NO_INITIATOR (0x0 << 0) +#define CEC_MODE_INITIATOR (0x1 << 0) +#define CEC_MODE_EXCL_INITIATOR (0x2 << 0) +#define CEC_MODE_INITIATOR_MSK 0x0f + +/* Modes for follower */ +#define CEC_MODE_NO_FOLLOWER (0x0 << 4) +#define CEC_MODE_FOLLOWER (0x1 << 4) +#define CEC_MODE_EXCL_FOLLOWER (0x2 << 4) +#define CEC_MODE_EXCL_FOLLOWER_PASSTHRU (0x3 << 4) +#define CEC_MODE_MONITOR (0xe << 4) +#define CEC_MODE_MONITOR_ALL (0xf << 4) +#define CEC_MODE_FOLLOWER_MSK 0xf0 + +/* Userspace has to configure the physical address */ +#define CEC_CAP_PHYS_ADDR (1 << 0) +/* Userspace has to configure the logical addresses */ +#define CEC_CAP_LOG_ADDRS (1 << 1) +/* Userspace can transmit messages (and thus become follower as well) */ +#define CEC_CAP_TRANSMIT (1 << 2) +/* + * Passthrough all messages instead of processing them. + */ +#define CEC_CAP_PASSTHROUGH (1 << 3) +/* Supports remote control */ +#define CEC_CAP_RC (1 << 4) +/* Hardware can monitor all messages, not just directed and broadcast. */ +#define CEC_CAP_MONITOR_ALL (1 << 5) + +/** + * struct cec_caps - CEC capabilities structure. + * @driver: name of the CEC device driver. + * @name: name of the CEC device. @driver + @name must be unique. + * @available_log_addrs: number of available logical addresses. + * @capabilities: capabilities of the CEC adapter. + * @version: version of the CEC adapter framework. + */ +struct cec_caps { + char driver[32]; + char name[32]; + __u32 available_log_addrs; + __u32 capabilities; + __u32 version; +}; + +/** + * struct cec_log_addrs - CEC logical addresses structure. + * @log_addr: the claimed logical addresses. Set by the driver. + * @log_addr_mask: current logical address mask. Set by the driver. + * @cec_version: the CEC version that the adapter should implement. Set by the + * caller. + * @num_log_addrs: how many logical addresses should be claimed. Set by the + * caller. + * @vendor_id: the vendor ID of the device. Set by the caller. + * @flags: flags. + * @osd_name: the OSD name of the device. Set by the caller. + * @primary_device_type: the primary device type for each logical address. + * Set by the caller. + * @log_addr_type: the logical address types. Set by the caller. + * @all_device_types: CEC 2.0: all device types represented by the logical + * address. Set by the caller. + * @features: CEC 2.0: The logical address features. Set by the caller. + */ +struct cec_log_addrs { + __u8 log_addr[CEC_MAX_LOG_ADDRS]; + __u16 log_addr_mask; + __u8 cec_version; + __u8 num_log_addrs; + __u32 vendor_id; + __u32 flags; + char osd_name[15]; + __u8 primary_device_type[CEC_MAX_LOG_ADDRS]; + __u8 log_addr_type[CEC_MAX_LOG_ADDRS]; + + /* CEC 2.0 */ + __u8 all_device_types[CEC_MAX_LOG_ADDRS]; + __u8 features[CEC_MAX_LOG_ADDRS][12]; +}; + +/* Allow a fallback to unregistered */ +#define CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK (1 << 0) +/* Passthrough RC messages to the input subsystem */ +#define CEC_LOG_ADDRS_FL_ALLOW_RC_PASSTHRU (1 << 1) +/* CDC-Only device: supports only CDC messages */ +#define CEC_LOG_ADDRS_FL_CDC_ONLY (1 << 2) + +/* Events */ + +/* Event that occurs when the adapter state changes */ +#define CEC_EVENT_STATE_CHANGE 1 +/* + * This event is sent when messages are lost because the application + * didn't empty the message queue in time + */ +#define CEC_EVENT_LOST_MSGS 2 + +#define CEC_EVENT_FL_INITIAL_STATE (1 << 0) + +/** + * struct cec_event_state_change - used when the CEC adapter changes state. + * @phys_addr: the current physical address + * @log_addr_mask: the current logical address mask + */ +struct cec_event_state_change { + __u16 phys_addr; + __u16 log_addr_mask; +}; + +/** + * struct cec_event_lost_msgs - tells you how many messages were lost due. + * @lost_msgs: how many messages were lost. + */ +struct cec_event_lost_msgs { + __u32 lost_msgs; +}; + +/** + * struct cec_event - CEC event structure + * @ts: the timestamp of when the event was sent. + * @event: the event. + * array. + * @state_change: the event payload for CEC_EVENT_STATE_CHANGE. + * @lost_msgs: the event payload for CEC_EVENT_LOST_MSGS. + * @raw: array to pad the union. + */ +struct cec_event { + __u64 ts; + __u32 event; + __u32 flags; + union { + struct cec_event_state_change state_change; + struct cec_event_lost_msgs lost_msgs; + __u32 raw[16]; + }; +}; + +/* ioctls */ + +/* Adapter capabilities */ +#define CEC_ADAP_G_CAPS _IOWR('a', 0, struct cec_caps) + +/* + * phys_addr is either 0 (if this is the CEC root device) + * or a valid physical address obtained from the sink's EDID + * as read by this CEC device (if this is a source device) + * or a physical address obtained and modified from a sink + * EDID and used for a sink CEC device. + * If nothing is connected, then phys_addr is 0xffff. + * See HDMI 1.4b, section 8.7 (Physical Address). + * + * The CEC_ADAP_S_PHYS_ADDR ioctl may not be available if that is handled + * internally. + */ +#define CEC_ADAP_G_PHYS_ADDR _IOR('a', 1, __u16) +#define CEC_ADAP_S_PHYS_ADDR _IOW('a', 2, __u16) + +/* + * Configure the CEC adapter. It sets the device type and which + * logical types it will try to claim. It will return which + * logical addresses it could actually claim. + * An error is returned if the adapter is disabled or if there + * is no physical address assigned. + */ + +#define CEC_ADAP_G_LOG_ADDRS _IOR('a', 3, struct cec_log_addrs) +#define CEC_ADAP_S_LOG_ADDRS _IOWR('a', 4, struct cec_log_addrs) + +/* Transmit/receive a CEC command */ +#define CEC_TRANSMIT _IOWR('a', 5, struct cec_msg) +#define CEC_RECEIVE _IOWR('a', 6, struct cec_msg) + +/* Dequeue CEC events */ +#define CEC_DQEVENT _IOWR('a', 7, struct cec_event) + +/* + * Get and set the message handling mode for this filehandle. + */ +#define CEC_G_MODE _IOR('a', 8, __u32) +#define CEC_S_MODE _IOW('a', 9, __u32) + +/* + * The remainder of this header defines all CEC messages and operands. + * The format matters since it the cec-ctl utility parses it to generate + * code for implementing all these messages. + * + * Comments ending with 'Feature' group messages for each feature. + * If messages are part of multiple features, then the "Has also" + * comment is used to list the previously defined messages that are + * supported by the feature. + * + * Before operands are defined a comment is added that gives the + * name of the operand and in brackets the variable name of the + * corresponding argument in the cec-funcs.h function. + */ + +/* Messages */ + +/* One Touch Play Feature */ +#define CEC_MSG_ACTIVE_SOURCE 0x82 +#define CEC_MSG_IMAGE_VIEW_ON 0x04 +#define CEC_MSG_TEXT_VIEW_ON 0x0d + + +/* Routing Control Feature */ + +/* + * Has also: + * CEC_MSG_ACTIVE_SOURCE + */ + +#define CEC_MSG_INACTIVE_SOURCE 0x9d +#define CEC_MSG_REQUEST_ACTIVE_SOURCE 0x85 +#define CEC_MSG_ROUTING_CHANGE 0x80 +#define CEC_MSG_ROUTING_INFORMATION 0x81 +#define CEC_MSG_SET_STREAM_PATH 0x86 + + +/* Standby Feature */ +#define CEC_MSG_STANDBY 0x36 + + +/* One Touch Record Feature */ +#define CEC_MSG_RECORD_OFF 0x0b +#define CEC_MSG_RECORD_ON 0x09 +/* Record Source Type Operand (rec_src_type) */ +#define CEC_OP_RECORD_SRC_OWN 1 +#define CEC_OP_RECORD_SRC_DIGITAL 2 +#define CEC_OP_RECORD_SRC_ANALOG 3 +#define CEC_OP_RECORD_SRC_EXT_PLUG 4 +#define CEC_OP_RECORD_SRC_EXT_PHYS_ADDR 5 +/* Service Identification Method Operand (service_id_method) */ +#define CEC_OP_SERVICE_ID_METHOD_BY_DIG_ID 0 +#define CEC_OP_SERVICE_ID_METHOD_BY_CHANNEL 1 +/* Digital Service Broadcast System Operand (dig_bcast_system) */ +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_GEN 0x00 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_GEN 0x01 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_GEN 0x02 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_BS 0x08 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_CS 0x09 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_T 0x0a +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_CABLE 0x10 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_SAT 0x11 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_T 0x12 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_C 0x18 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_S 0x19 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_S2 0x1a +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_T 0x1b +/* Analogue Broadcast Type Operand (ana_bcast_type) */ +#define CEC_OP_ANA_BCAST_TYPE_CABLE 0 +#define CEC_OP_ANA_BCAST_TYPE_SATELLITE 1 +#define CEC_OP_ANA_BCAST_TYPE_TERRESTRIAL 2 +/* Broadcast System Operand (bcast_system) */ +#define CEC_OP_BCAST_SYSTEM_PAL_BG 0x00 +#define CEC_OP_BCAST_SYSTEM_SECAM_LQ 0x01 /* SECAM L' */ +#define CEC_OP_BCAST_SYSTEM_PAL_M 0x02 +#define CEC_OP_BCAST_SYSTEM_NTSC_M 0x03 +#define CEC_OP_BCAST_SYSTEM_PAL_I 0x04 +#define CEC_OP_BCAST_SYSTEM_SECAM_DK 0x05 +#define CEC_OP_BCAST_SYSTEM_SECAM_BG 0x06 +#define CEC_OP_BCAST_SYSTEM_SECAM_L 0x07 +#define CEC_OP_BCAST_SYSTEM_PAL_DK 0x08 +#define CEC_OP_BCAST_SYSTEM_OTHER 0x1f +/* Channel Number Format Operand (channel_number_fmt) */ +#define CEC_OP_CHANNEL_NUMBER_FMT_1_PART 0x01 +#define CEC_OP_CHANNEL_NUMBER_FMT_2_PART 0x02 + +#define CEC_MSG_RECORD_STATUS 0x0a +/* Record Status Operand (rec_status) */ +#define CEC_OP_RECORD_STATUS_CUR_SRC 0x01 +#define CEC_OP_RECORD_STATUS_DIG_SERVICE 0x02 +#define CEC_OP_RECORD_STATUS_ANA_SERVICE 0x03 +#define CEC_OP_RECORD_STATUS_EXT_INPUT 0x04 +#define CEC_OP_RECORD_STATUS_NO_DIG_SERVICE 0x05 +#define CEC_OP_RECORD_STATUS_NO_ANA_SERVICE 0x06 +#define CEC_OP_RECORD_STATUS_NO_SERVICE 0x07 +#define CEC_OP_RECORD_STATUS_INVALID_EXT_PLUG 0x09 +#define CEC_OP_RECORD_STATUS_INVALID_EXT_PHYS_ADDR 0x0a +#define CEC_OP_RECORD_STATUS_UNSUP_CA 0x0b +#define CEC_OP_RECORD_STATUS_NO_CA_ENTITLEMENTS 0x0c +#define CEC_OP_RECORD_STATUS_CANT_COPY_SRC 0x0d +#define CEC_OP_RECORD_STATUS_NO_MORE_COPIES 0x0e +#define CEC_OP_RECORD_STATUS_NO_MEDIA 0x10 +#define CEC_OP_RECORD_STATUS_PLAYING 0x11 +#define CEC_OP_RECORD_STATUS_ALREADY_RECORDING 0x12 +#define CEC_OP_RECORD_STATUS_MEDIA_PROT 0x13 +#define CEC_OP_RECORD_STATUS_NO_SIGNAL 0x14 +#define CEC_OP_RECORD_STATUS_MEDIA_PROBLEM 0x15 +#define CEC_OP_RECORD_STATUS_NO_SPACE 0x16 +#define CEC_OP_RECORD_STATUS_PARENTAL_LOCK 0x17 +#define CEC_OP_RECORD_STATUS_TERMINATED_OK 0x1a +#define CEC_OP_RECORD_STATUS_ALREADY_TERM 0x1b +#define CEC_OP_RECORD_STATUS_OTHER 0x1f + +#define CEC_MSG_RECORD_TV_SCREEN 0x0f + + +/* Timer Programming Feature */ +#define CEC_MSG_CLEAR_ANALOGUE_TIMER 0x33 +/* Recording Sequence Operand (recording_seq) */ +#define CEC_OP_REC_SEQ_SUNDAY 0x01 +#define CEC_OP_REC_SEQ_MONDAY 0x02 +#define CEC_OP_REC_SEQ_TUESDAY 0x04 +#define CEC_OP_REC_SEQ_WEDNESDAY 0x08 +#define CEC_OP_REC_SEQ_THURSDAY 0x10 +#define CEC_OP_REC_SEQ_FRIDAY 0x20 +#define CEC_OP_REC_SEQ_SATERDAY 0x40 +#define CEC_OP_REC_SEQ_ONCE_ONLY 0x00 + +#define CEC_MSG_CLEAR_DIGITAL_TIMER 0x99 + +#define CEC_MSG_CLEAR_EXT_TIMER 0xa1 +/* External Source Specifier Operand (ext_src_spec) */ +#define CEC_OP_EXT_SRC_PLUG 0x04 +#define CEC_OP_EXT_SRC_PHYS_ADDR 0x05 + +#define CEC_MSG_SET_ANALOGUE_TIMER 0x34 +#define CEC_MSG_SET_DIGITAL_TIMER 0x97 +#define CEC_MSG_SET_EXT_TIMER 0xa2 + +#define CEC_MSG_SET_TIMER_PROGRAM_TITLE 0x67 +#define CEC_MSG_TIMER_CLEARED_STATUS 0x43 +/* Timer Cleared Status Data Operand (timer_cleared_status) */ +#define CEC_OP_TIMER_CLR_STAT_RECORDING 0x00 +#define CEC_OP_TIMER_CLR_STAT_NO_MATCHING 0x01 +#define CEC_OP_TIMER_CLR_STAT_NO_INFO 0x02 +#define CEC_OP_TIMER_CLR_STAT_CLEARED 0x80 + +#define CEC_MSG_TIMER_STATUS 0x35 +/* Timer Overlap Warning Operand (timer_overlap_warning) */ +#define CEC_OP_TIMER_OVERLAP_WARNING_NO_OVERLAP 0 +#define CEC_OP_TIMER_OVERLAP_WARNING_OVERLAP 1 +/* Media Info Operand (media_info) */ +#define CEC_OP_MEDIA_INFO_UNPROT_MEDIA 0 +#define CEC_OP_MEDIA_INFO_PROT_MEDIA 1 +#define CEC_OP_MEDIA_INFO_NO_MEDIA 2 +/* Programmed Indicator Operand (prog_indicator) */ +#define CEC_OP_PROG_IND_NOT_PROGRAMMED 0 +#define CEC_OP_PROG_IND_PROGRAMMED 1 +/* Programmed Info Operand (prog_info) */ +#define CEC_OP_PROG_INFO_ENOUGH_SPACE 0x08 +#define CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE 0x09 +#define CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE 0x0b +#define CEC_OP_PROG_INFO_NONE_AVAILABLE 0x0a +/* Not Programmed Error Info Operand (prog_error) */ +#define CEC_OP_PROG_ERROR_NO_FREE_TIMER 0x01 +#define CEC_OP_PROG_ERROR_DATE_OUT_OF_RANGE 0x02 +#define CEC_OP_PROG_ERROR_REC_SEQ_ERROR 0x03 +#define CEC_OP_PROG_ERROR_INV_EXT_PLUG 0x04 +#define CEC_OP_PROG_ERROR_INV_EXT_PHYS_ADDR 0x05 +#define CEC_OP_PROG_ERROR_CA_UNSUPP 0x06 +#define CEC_OP_PROG_ERROR_INSUF_CA_ENTITLEMENTS 0x07 +#define CEC_OP_PROG_ERROR_RESOLUTION_UNSUPP 0x08 +#define CEC_OP_PROG_ERROR_PARENTAL_LOCK 0x09 +#define CEC_OP_PROG_ERROR_CLOCK_FAILURE 0x0a +#define CEC_OP_PROG_ERROR_DUPLICATE 0x0e + + +/* System Information Feature */ +#define CEC_MSG_CEC_VERSION 0x9e +/* CEC Version Operand (cec_version) */ +#define CEC_OP_CEC_VERSION_1_3A 4 +#define CEC_OP_CEC_VERSION_1_4 5 +#define CEC_OP_CEC_VERSION_2_0 6 + +#define CEC_MSG_GET_CEC_VERSION 0x9f +#define CEC_MSG_GIVE_PHYSICAL_ADDR 0x83 +#define CEC_MSG_GET_MENU_LANGUAGE 0x91 +#define CEC_MSG_REPORT_PHYSICAL_ADDR 0x84 +/* Primary Device Type Operand (prim_devtype) */ +#define CEC_OP_PRIM_DEVTYPE_TV 0 +#define CEC_OP_PRIM_DEVTYPE_RECORD 1 +#define CEC_OP_PRIM_DEVTYPE_TUNER 3 +#define CEC_OP_PRIM_DEVTYPE_PLAYBACK 4 +#define CEC_OP_PRIM_DEVTYPE_AUDIOSYSTEM 5 +#define CEC_OP_PRIM_DEVTYPE_SWITCH 6 +#define CEC_OP_PRIM_DEVTYPE_PROCESSOR 7 + +#define CEC_MSG_SET_MENU_LANGUAGE 0x32 +#define CEC_MSG_REPORT_FEATURES 0xa6 /* HDMI 2.0 */ +/* All Device Types Operand (all_device_types) */ +#define CEC_OP_ALL_DEVTYPE_TV 0x80 +#define CEC_OP_ALL_DEVTYPE_RECORD 0x40 +#define CEC_OP_ALL_DEVTYPE_TUNER 0x20 +#define CEC_OP_ALL_DEVTYPE_PLAYBACK 0x10 +#define CEC_OP_ALL_DEVTYPE_AUDIOSYSTEM 0x08 +#define CEC_OP_ALL_DEVTYPE_SWITCH 0x04 +/* + * And if you wondering what happened to PROCESSOR devices: those should + * be mapped to a SWITCH. + */ + +/* Valid for RC Profile and Device Feature operands */ +#define CEC_OP_FEAT_EXT 0x80 /* Extension bit */ +/* RC Profile Operand (rc_profile) */ +#define CEC_OP_FEAT_RC_TV_PROFILE_NONE 0x00 +#define CEC_OP_FEAT_RC_TV_PROFILE_1 0x02 +#define CEC_OP_FEAT_RC_TV_PROFILE_2 0x06 +#define CEC_OP_FEAT_RC_TV_PROFILE_3 0x0a +#define CEC_OP_FEAT_RC_TV_PROFILE_4 0x0e +#define CEC_OP_FEAT_RC_SRC_HAS_DEV_ROOT_MENU 0x50 +#define CEC_OP_FEAT_RC_SRC_HAS_DEV_SETUP_MENU 0x48 +#define CEC_OP_FEAT_RC_SRC_HAS_CONTENTS_MENU 0x44 +#define CEC_OP_FEAT_RC_SRC_HAS_MEDIA_TOP_MENU 0x42 +#define CEC_OP_FEAT_RC_SRC_HAS_MEDIA_CONTEXT_MENU 0x41 +/* Device Feature Operand (dev_features) */ +#define CEC_OP_FEAT_DEV_HAS_RECORD_TV_SCREEN 0x40 +#define CEC_OP_FEAT_DEV_HAS_SET_OSD_STRING 0x20 +#define CEC_OP_FEAT_DEV_HAS_DECK_CONTROL 0x10 +#define CEC_OP_FEAT_DEV_HAS_SET_AUDIO_RATE 0x08 +#define CEC_OP_FEAT_DEV_SINK_HAS_ARC_TX 0x04 +#define CEC_OP_FEAT_DEV_SOURCE_HAS_ARC_RX 0x02 + +#define CEC_MSG_GIVE_FEATURES 0xa5 /* HDMI 2.0 */ + + +/* Deck Control Feature */ +#define CEC_MSG_DECK_CONTROL 0x42 +/* Deck Control Mode Operand (deck_control_mode) */ +#define CEC_OP_DECK_CTL_MODE_SKIP_FWD 1 +#define CEC_OP_DECK_CTL_MODE_SKIP_REV 2 +#define CEC_OP_DECK_CTL_MODE_STOP 3 +#define CEC_OP_DECK_CTL_MODE_EJECT 4 + +#define CEC_MSG_DECK_STATUS 0x1b +/* Deck Info Operand (deck_info) */ +#define CEC_OP_DECK_INFO_PLAY 0x11 +#define CEC_OP_DECK_INFO_RECORD 0x12 +#define CEC_OP_DECK_INFO_PLAY_REV 0x13 +#define CEC_OP_DECK_INFO_STILL 0x14 +#define CEC_OP_DECK_INFO_SLOW 0x15 +#define CEC_OP_DECK_INFO_SLOW_REV 0x16 +#define CEC_OP_DECK_INFO_FAST_FWD 0x17 +#define CEC_OP_DECK_INFO_FAST_REV 0x18 +#define CEC_OP_DECK_INFO_NO_MEDIA 0x19 +#define CEC_OP_DECK_INFO_STOP 0x1a +#define CEC_OP_DECK_INFO_SKIP_FWD 0x1b +#define CEC_OP_DECK_INFO_SKIP_REV 0x1c +#define CEC_OP_DECK_INFO_INDEX_SEARCH_FWD 0x1d +#define CEC_OP_DECK_INFO_INDEX_SEARCH_REV 0x1e +#define CEC_OP_DECK_INFO_OTHER 0x1f + +#define CEC_MSG_GIVE_DECK_STATUS 0x1a +/* Status Request Operand (status_req) */ +#define CEC_OP_STATUS_REQ_ON 1 +#define CEC_OP_STATUS_REQ_OFF 2 +#define CEC_OP_STATUS_REQ_ONCE 3 + +#define CEC_MSG_PLAY 0x41 +/* Play Mode Operand (play_mode) */ +#define CEC_OP_PLAY_MODE_PLAY_FWD 0x24 +#define CEC_OP_PLAY_MODE_PLAY_REV 0x20 +#define CEC_OP_PLAY_MODE_PLAY_STILL 0x25 +#define CEC_OP_PLAY_MODE_PLAY_FAST_FWD_MIN 0x05 +#define CEC_OP_PLAY_MODE_PLAY_FAST_FWD_MED 0x06 +#define CEC_OP_PLAY_MODE_PLAY_FAST_FWD_MAX 0x07 +#define CEC_OP_PLAY_MODE_PLAY_FAST_REV_MIN 0x09 +#define CEC_OP_PLAY_MODE_PLAY_FAST_REV_MED 0x0a +#define CEC_OP_PLAY_MODE_PLAY_FAST_REV_MAX 0x0b +#define CEC_OP_PLAY_MODE_PLAY_SLOW_FWD_MIN 0x15 +#define CEC_OP_PLAY_MODE_PLAY_SLOW_FWD_MED 0x16 +#define CEC_OP_PLAY_MODE_PLAY_SLOW_FWD_MAX 0x17 +#define CEC_OP_PLAY_MODE_PLAY_SLOW_REV_MIN 0x19 +#define CEC_OP_PLAY_MODE_PLAY_SLOW_REV_MED 0x1a +#define CEC_OP_PLAY_MODE_PLAY_SLOW_REV_MAX 0x1b + + +/* Tuner Control Feature */ +#define CEC_MSG_GIVE_TUNER_DEVICE_STATUS 0x08 +#define CEC_MSG_SELECT_ANALOGUE_SERVICE 0x92 +#define CEC_MSG_SELECT_DIGITAL_SERVICE 0x93 +#define CEC_MSG_TUNER_DEVICE_STATUS 0x07 +/* Recording Flag Operand (rec_flag) */ +#define CEC_OP_REC_FLAG_USED 0 +#define CEC_OP_REC_FLAG_NOT_USED 1 +/* Tuner Display Info Operand (tuner_display_info) */ +#define CEC_OP_TUNER_DISPLAY_INFO_DIGITAL 0 +#define CEC_OP_TUNER_DISPLAY_INFO_NONE 1 +#define CEC_OP_TUNER_DISPLAY_INFO_ANALOGUE 2 + +#define CEC_MSG_TUNER_STEP_DECREMENT 0x06 +#define CEC_MSG_TUNER_STEP_INCREMENT 0x05 + + +/* Vendor Specific Commands Feature */ + +/* + * Has also: + * CEC_MSG_CEC_VERSION + * CEC_MSG_GET_CEC_VERSION + */ +#define CEC_MSG_DEVICE_VENDOR_ID 0x87 +#define CEC_MSG_GIVE_DEVICE_VENDOR_ID 0x8c +#define CEC_MSG_VENDOR_COMMAND 0x89 +#define CEC_MSG_VENDOR_COMMAND_WITH_ID 0xa0 +#define CEC_MSG_VENDOR_REMOTE_BUTTON_DOWN 0x8a +#define CEC_MSG_VENDOR_REMOTE_BUTTON_UP 0x8b + + +/* OSD Display Feature */ +#define CEC_MSG_SET_OSD_STRING 0x64 +/* Display Control Operand (disp_ctl) */ +#define CEC_OP_DISP_CTL_DEFAULT 0x00 +#define CEC_OP_DISP_CTL_UNTIL_CLEARED 0x40 +#define CEC_OP_DISP_CTL_CLEAR 0x80 + + +/* Device OSD Transfer Feature */ +#define CEC_MSG_GIVE_OSD_NAME 0x46 +#define CEC_MSG_SET_OSD_NAME 0x47 + + +/* Device Menu Control Feature */ +#define CEC_MSG_MENU_REQUEST 0x8d +/* Menu Request Type Operand (menu_req) */ +#define CEC_OP_MENU_REQUEST_ACTIVATE 0x00 +#define CEC_OP_MENU_REQUEST_DEACTIVATE 0x01 +#define CEC_OP_MENU_REQUEST_QUERY 0x02 + +#define CEC_MSG_MENU_STATUS 0x8e +/* Menu State Operand (menu_state) */ +#define CEC_OP_MENU_STATE_ACTIVATED 0x00 +#define CEC_OP_MENU_STATE_DEACTIVATED 0x01 + +#define CEC_MSG_USER_CONTROL_PRESSED 0x44 +/* UI Broadcast Type Operand (ui_bcast_type) */ +#define CEC_OP_UI_BCAST_TYPE_TOGGLE_ALL 0x00 +#define CEC_OP_UI_BCAST_TYPE_TOGGLE_DIG_ANA 0x01 +#define CEC_OP_UI_BCAST_TYPE_ANALOGUE 0x10 +#define CEC_OP_UI_BCAST_TYPE_ANALOGUE_T 0x20 +#define CEC_OP_UI_BCAST_TYPE_ANALOGUE_CABLE 0x30 +#define CEC_OP_UI_BCAST_TYPE_ANALOGUE_SAT 0x40 +#define CEC_OP_UI_BCAST_TYPE_DIGITAL 0x50 +#define CEC_OP_UI_BCAST_TYPE_DIGITAL_T 0x60 +#define CEC_OP_UI_BCAST_TYPE_DIGITAL_CABLE 0x70 +#define CEC_OP_UI_BCAST_TYPE_DIGITAL_SAT 0x80 +#define CEC_OP_UI_BCAST_TYPE_DIGITAL_COM_SAT 0x90 +#define CEC_OP_UI_BCAST_TYPE_DIGITAL_COM_SAT2 0x91 +#define CEC_OP_UI_BCAST_TYPE_IP 0xa0 +/* UI Sound Presentation Control Operand (ui_snd_pres_ctl) */ +#define CEC_OP_UI_SND_PRES_CTL_DUAL_MONO 0x10 +#define CEC_OP_UI_SND_PRES_CTL_KARAOKE 0x20 +#define CEC_OP_UI_SND_PRES_CTL_DOWNMIX 0x80 +#define CEC_OP_UI_SND_PRES_CTL_REVERB 0x90 +#define CEC_OP_UI_SND_PRES_CTL_EQUALIZER 0xa0 +#define CEC_OP_UI_SND_PRES_CTL_BASS_UP 0xb1 +#define CEC_OP_UI_SND_PRES_CTL_BASS_NEUTRAL 0xb2 +#define CEC_OP_UI_SND_PRES_CTL_BASS_DOWN 0xb3 +#define CEC_OP_UI_SND_PRES_CTL_TREBLE_UP 0xc1 +#define CEC_OP_UI_SND_PRES_CTL_TREBLE_NEUTRAL 0xc2 +#define CEC_OP_UI_SND_PRES_CTL_TREBLE_DOWN 0xc3 + +#define CEC_MSG_USER_CONTROL_RELEASED 0x45 + + +/* Remote Control Passthrough Feature */ + +/* + * Has also: + * CEC_MSG_USER_CONTROL_PRESSED + * CEC_MSG_USER_CONTROL_RELEASED + */ + + +/* Power Status Feature */ +#define CEC_MSG_GIVE_DEVICE_POWER_STATUS 0x8f +#define CEC_MSG_REPORT_POWER_STATUS 0x90 +/* Power Status Operand (pwr_state) */ +#define CEC_OP_POWER_STATUS_ON 0 +#define CEC_OP_POWER_STATUS_STANDBY 1 +#define CEC_OP_POWER_STATUS_TO_ON 2 +#define CEC_OP_POWER_STATUS_TO_STANDBY 3 + + +/* General Protocol Messages */ +#define CEC_MSG_FEATURE_ABORT 0x00 +/* Abort Reason Operand (reason) */ +#define CEC_OP_ABORT_UNRECOGNIZED_OP 0 +#define CEC_OP_ABORT_INCORRECT_MODE 1 +#define CEC_OP_ABORT_NO_SOURCE 2 +#define CEC_OP_ABORT_INVALID_OP 3 +#define CEC_OP_ABORT_REFUSED 4 +#define CEC_OP_ABORT_UNDETERMINED 5 + +#define CEC_MSG_ABORT 0xff + + +/* System Audio Control Feature */ + +/* + * Has also: + * CEC_MSG_USER_CONTROL_PRESSED + * CEC_MSG_USER_CONTROL_RELEASED + */ +#define CEC_MSG_GIVE_AUDIO_STATUS 0x71 +#define CEC_MSG_GIVE_SYSTEM_AUDIO_MODE_STATUS 0x7d +#define CEC_MSG_REPORT_AUDIO_STATUS 0x7a +/* Audio Mute Status Operand (aud_mute_status) */ +#define CEC_OP_AUD_MUTE_STATUS_OFF 0 +#define CEC_OP_AUD_MUTE_STATUS_ON 1 + +#define CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR 0xa3 +#define CEC_MSG_REQUEST_SHORT_AUDIO_DESCRIPTOR 0xa4 +#define CEC_MSG_SET_SYSTEM_AUDIO_MODE 0x72 +/* System Audio Status Operand (sys_aud_status) */ +#define CEC_OP_SYS_AUD_STATUS_OFF 0 +#define CEC_OP_SYS_AUD_STATUS_ON 1 + +#define CEC_MSG_SYSTEM_AUDIO_MODE_REQUEST 0x70 +#define CEC_MSG_SYSTEM_AUDIO_MODE_STATUS 0x7e +/* Audio Format ID Operand (audio_format_id) */ +#define CEC_OP_AUD_FMT_ID_CEA861 0 +#define CEC_OP_AUD_FMT_ID_CEA861_CXT 1 + + +/* Audio Rate Control Feature */ +#define CEC_MSG_SET_AUDIO_RATE 0x9a +/* Audio Rate Operand (audio_rate) */ +#define CEC_OP_AUD_RATE_OFF 0 +#define CEC_OP_AUD_RATE_WIDE_STD 1 +#define CEC_OP_AUD_RATE_WIDE_FAST 2 +#define CEC_OP_AUD_RATE_WIDE_SLOW 3 +#define CEC_OP_AUD_RATE_NARROW_STD 4 +#define CEC_OP_AUD_RATE_NARROW_FAST 5 +#define CEC_OP_AUD_RATE_NARROW_SLOW 6 + + +/* Audio Return Channel Control Feature */ +#define CEC_MSG_INITIATE_ARC 0xc0 +#define CEC_MSG_REPORT_ARC_INITIATED 0xc1 +#define CEC_MSG_REPORT_ARC_TERMINATED 0xc2 +#define CEC_MSG_REQUEST_ARC_INITIATION 0xc3 +#define CEC_MSG_REQUEST_ARC_TERMINATION 0xc4 +#define CEC_MSG_TERMINATE_ARC 0xc5 + + +/* Dynamic Audio Lipsync Feature */ +/* Only for CEC 2.0 and up */ +#define CEC_MSG_REQUEST_CURRENT_LATENCY 0xa7 +#define CEC_MSG_REPORT_CURRENT_LATENCY 0xa8 +/* Low Latency Mode Operand (low_latency_mode) */ +#define CEC_OP_LOW_LATENCY_MODE_OFF 0 +#define CEC_OP_LOW_LATENCY_MODE_ON 1 +/* Audio Output Compensated Operand (audio_out_compensated) */ +#define CEC_OP_AUD_OUT_COMPENSATED_NA 0 +#define CEC_OP_AUD_OUT_COMPENSATED_DELAY 1 +#define CEC_OP_AUD_OUT_COMPENSATED_NO_DELAY 2 +#define CEC_OP_AUD_OUT_COMPENSATED_PARTIAL_DELAY 3 + + +/* Capability Discovery and Control Feature */ +#define CEC_MSG_CDC_MESSAGE 0xf8 +/* Ethernet-over-HDMI: nobody ever does this... */ +#define CEC_MSG_CDC_HEC_INQUIRE_STATE 0x00 +#define CEC_MSG_CDC_HEC_REPORT_STATE 0x01 +/* HEC Functionality State Operand (hec_func_state) */ +#define CEC_OP_HEC_FUNC_STATE_NOT_SUPPORTED 0 +#define CEC_OP_HEC_FUNC_STATE_INACTIVE 1 +#define CEC_OP_HEC_FUNC_STATE_ACTIVE 2 +#define CEC_OP_HEC_FUNC_STATE_ACTIVATION_FIELD 3 +/* Host Functionality State Operand (host_func_state) */ +#define CEC_OP_HOST_FUNC_STATE_NOT_SUPPORTED 0 +#define CEC_OP_HOST_FUNC_STATE_INACTIVE 1 +#define CEC_OP_HOST_FUNC_STATE_ACTIVE 2 +/* ENC Functionality State Operand (enc_func_state) */ +#define CEC_OP_ENC_FUNC_STATE_EXT_CON_NOT_SUPPORTED 0 +#define CEC_OP_ENC_FUNC_STATE_EXT_CON_INACTIVE 1 +#define CEC_OP_ENC_FUNC_STATE_EXT_CON_ACTIVE 2 +/* CDC Error Code Operand (cdc_errcode) */ +#define CEC_OP_CDC_ERROR_CODE_NONE 0 +#define CEC_OP_CDC_ERROR_CODE_CAP_UNSUPPORTED 1 +#define CEC_OP_CDC_ERROR_CODE_WRONG_STATE 2 +#define CEC_OP_CDC_ERROR_CODE_OTHER 3 +/* HEC Support Operand (hec_support) */ +#define CEC_OP_HEC_SUPPORT_NO 0 +#define CEC_OP_HEC_SUPPORT_YES 1 +/* HEC Activation Operand (hec_activation) */ +#define CEC_OP_HEC_ACTIVATION_ON 0 +#define CEC_OP_HEC_ACTIVATION_OFF 1 + +#define CEC_MSG_CDC_HEC_SET_STATE_ADJACENT 0x02 +#define CEC_MSG_CDC_HEC_SET_STATE 0x03 +/* HEC Set State Operand (hec_set_state) */ +#define CEC_OP_HEC_SET_STATE_DEACTIVATE 0 +#define CEC_OP_HEC_SET_STATE_ACTIVATE 1 + +#define CEC_MSG_CDC_HEC_REQUEST_DEACTIVATION 0x04 +#define CEC_MSG_CDC_HEC_NOTIFY_ALIVE 0x05 +#define CEC_MSG_CDC_HEC_DISCOVER 0x06 +/* Hotplug Detect messages */ +#define CEC_MSG_CDC_HPD_SET_STATE 0x10 +/* HPD State Operand (hpd_state) */ +#define CEC_OP_HPD_STATE_CP_EDID_DISABLE 0 +#define CEC_OP_HPD_STATE_CP_EDID_ENABLE 1 +#define CEC_OP_HPD_STATE_CP_EDID_DISABLE_ENABLE 2 +#define CEC_OP_HPD_STATE_EDID_DISABLE 3 +#define CEC_OP_HPD_STATE_EDID_ENABLE 4 +#define CEC_OP_HPD_STATE_EDID_DISABLE_ENABLE 5 +#define CEC_MSG_CDC_HPD_REPORT_STATE 0x11 +/* HPD Error Code Operand (hpd_error) */ +#define CEC_OP_HPD_ERROR_NONE 0 +#define CEC_OP_HPD_ERROR_INITIATOR_NOT_CAPABLE 1 +#define CEC_OP_HPD_ERROR_INITIATOR_WRONG_STATE 2 +#define CEC_OP_HPD_ERROR_OTHER 3 +#define CEC_OP_HPD_ERROR_NONE_NO_VIDEO 4 + +/* End of Messages */ + +/* Helper functions to identify the 'special' CEC devices */ + +static inline bool cec_is_2nd_tv(const struct cec_log_addrs *las) +{ + /* + * It is a second TV if the logical address is 14 or 15 and the + * primary device type is a TV. + */ + return las->num_log_addrs && + las->log_addr[0] >= CEC_LOG_ADDR_SPECIFIC && + las->primary_device_type[0] == CEC_OP_PRIM_DEVTYPE_TV; +} + +static inline bool cec_is_processor(const struct cec_log_addrs *las) +{ + /* + * It is a processor if the logical address is 12-15 and the + * primary device type is a Processor. + */ + return las->num_log_addrs && + las->log_addr[0] >= CEC_LOG_ADDR_BACKUP_1 && + las->primary_device_type[0] == CEC_OP_PRIM_DEVTYPE_PROCESSOR; +} + +static inline bool cec_is_switch(const struct cec_log_addrs *las) +{ + /* + * It is a switch if the logical address is 15 and the + * primary device type is a Switch and the CDC-Only flag is not set. + */ + return las->num_log_addrs == 1 && + las->log_addr[0] == CEC_LOG_ADDR_UNREGISTERED && + las->primary_device_type[0] == CEC_OP_PRIM_DEVTYPE_SWITCH && + !(las->flags & CEC_LOG_ADDRS_FL_CDC_ONLY); +} + +static inline bool cec_is_cdc_only(const struct cec_log_addrs *las) +{ + /* + * It is a CDC-only device if the logical address is 15 and the + * primary device type is a Switch and the CDC-Only flag is set. + */ + return las->num_log_addrs == 1 && + las->log_addr[0] == CEC_LOG_ADDR_UNREGISTERED && + las->primary_device_type[0] == CEC_OP_PRIM_DEVTYPE_SWITCH && + (las->flags & CEC_LOG_ADDRS_FL_CDC_ONLY); +} + +#endif -- cgit v1.2.3 From 3145c754aca8182b4cfe301b3cfe6dc8f2cb499c Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 4 Nov 2016 08:23:27 -0200 Subject: [media] cec.h/cec-funcs.h: don't use bool in public headers Replace bool by int or __u8 (when used in a struct). Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/cec-funcs.h | 70 +++++++++++++++++++++--------------------- include/uapi/linux/cec.h | 37 +++++++++++----------- 2 files changed, 54 insertions(+), 53 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/cec-funcs.h b/include/uapi/linux/cec-funcs.h index 1a1de2169f48..3cbc327801d6 100644 --- a/include/uapi/linux/cec-funcs.h +++ b/include/uapi/linux/cec-funcs.h @@ -84,7 +84,7 @@ static inline void cec_ops_inactive_source(const struct cec_msg *msg, } static inline void cec_msg_request_active_source(struct cec_msg *msg, - bool reply) + int reply) { msg->len = 2; msg->msg[0] |= 0xf; /* broadcast */ @@ -109,7 +109,7 @@ static inline void cec_ops_routing_information(const struct cec_msg *msg, } static inline void cec_msg_routing_change(struct cec_msg *msg, - bool reply, + int reply, __u16 orig_phys_addr, __u16 new_phys_addr) { @@ -156,7 +156,7 @@ static inline void cec_msg_standby(struct cec_msg *msg) /* One Touch Record Feature */ -static inline void cec_msg_record_off(struct cec_msg *msg, bool reply) +static inline void cec_msg_record_off(struct cec_msg *msg, int reply) { msg->len = 2; msg->msg[1] = CEC_MSG_RECORD_OFF; @@ -318,7 +318,7 @@ static inline void cec_msg_record_on_phys_addr(struct cec_msg *msg, } static inline void cec_msg_record_on(struct cec_msg *msg, - bool reply, + int reply, const struct cec_op_record_src *rec_src) { switch (rec_src->type) { @@ -385,7 +385,7 @@ static inline void cec_ops_record_status(const struct cec_msg *msg, } static inline void cec_msg_record_tv_screen(struct cec_msg *msg, - bool reply) + int reply) { msg->len = 2; msg->msg[1] = CEC_MSG_RECORD_TV_SCREEN; @@ -459,7 +459,7 @@ static inline void cec_ops_timer_cleared_status(const struct cec_msg *msg, } static inline void cec_msg_clear_analogue_timer(struct cec_msg *msg, - bool reply, + int reply, __u8 day, __u8 month, __u8 start_hr, @@ -514,7 +514,7 @@ static inline void cec_ops_clear_analogue_timer(const struct cec_msg *msg, } static inline void cec_msg_clear_digital_timer(struct cec_msg *msg, - bool reply, + int reply, __u8 day, __u8 month, __u8 start_hr, @@ -560,7 +560,7 @@ static inline void cec_ops_clear_digital_timer(const struct cec_msg *msg, } static inline void cec_msg_clear_ext_timer(struct cec_msg *msg, - bool reply, + int reply, __u8 day, __u8 month, __u8 start_hr, @@ -615,7 +615,7 @@ static inline void cec_ops_clear_ext_timer(const struct cec_msg *msg, } static inline void cec_msg_set_analogue_timer(struct cec_msg *msg, - bool reply, + int reply, __u8 day, __u8 month, __u8 start_hr, @@ -670,7 +670,7 @@ static inline void cec_ops_set_analogue_timer(const struct cec_msg *msg, } static inline void cec_msg_set_digital_timer(struct cec_msg *msg, - bool reply, + int reply, __u8 day, __u8 month, __u8 start_hr, @@ -716,7 +716,7 @@ static inline void cec_ops_set_digital_timer(const struct cec_msg *msg, } static inline void cec_msg_set_ext_timer(struct cec_msg *msg, - bool reply, + int reply, __u8 day, __u8 month, __u8 start_hr, @@ -808,7 +808,7 @@ static inline void cec_ops_cec_version(const struct cec_msg *msg, } static inline void cec_msg_get_cec_version(struct cec_msg *msg, - bool reply) + int reply) { msg->len = 2; msg->msg[1] = CEC_MSG_GET_CEC_VERSION; @@ -834,7 +834,7 @@ static inline void cec_ops_report_physical_addr(const struct cec_msg *msg, } static inline void cec_msg_give_physical_addr(struct cec_msg *msg, - bool reply) + int reply) { msg->len = 2; msg->msg[1] = CEC_MSG_GIVE_PHYSICAL_ADDR; @@ -858,7 +858,7 @@ static inline void cec_ops_set_menu_language(const struct cec_msg *msg, } static inline void cec_msg_get_menu_language(struct cec_msg *msg, - bool reply) + int reply) { msg->len = 2; msg->msg[1] = CEC_MSG_GET_MENU_LANGUAGE; @@ -907,7 +907,7 @@ static inline void cec_ops_report_features(const struct cec_msg *msg, } static inline void cec_msg_give_features(struct cec_msg *msg, - bool reply) + int reply) { msg->len = 2; msg->msg[1] = CEC_MSG_GIVE_FEATURES; @@ -944,7 +944,7 @@ static inline void cec_ops_deck_status(const struct cec_msg *msg, } static inline void cec_msg_give_deck_status(struct cec_msg *msg, - bool reply, + int reply, __u8 status_req) { msg->len = 3; @@ -978,7 +978,7 @@ static inline void cec_ops_play(const struct cec_msg *msg, struct cec_op_tuner_device_info { __u8 rec_flag; __u8 tuner_display_info; - bool is_analog; + __u8 is_analog; union { struct cec_op_digital_service_id digital; struct { @@ -1048,7 +1048,7 @@ static inline void cec_ops_tuner_device_status(const struct cec_msg *msg, } static inline void cec_msg_give_tuner_device_status(struct cec_msg *msg, - bool reply, + int reply, __u8 status_req) { msg->len = 3; @@ -1131,7 +1131,7 @@ static inline void cec_ops_device_vendor_id(const struct cec_msg *msg, } static inline void cec_msg_give_device_vendor_id(struct cec_msg *msg, - bool reply) + int reply) { msg->len = 2; msg->msg[1] = CEC_MSG_GIVE_DEVICE_VENDOR_ID; @@ -1267,7 +1267,7 @@ static inline void cec_ops_set_osd_name(const struct cec_msg *msg, } static inline void cec_msg_give_osd_name(struct cec_msg *msg, - bool reply) + int reply) { msg->len = 2; msg->msg[1] = CEC_MSG_GIVE_OSD_NAME; @@ -1291,7 +1291,7 @@ static inline void cec_ops_menu_status(const struct cec_msg *msg, } static inline void cec_msg_menu_request(struct cec_msg *msg, - bool reply, + int reply, __u8 menu_req) { msg->len = 3; @@ -1308,7 +1308,7 @@ static inline void cec_ops_menu_request(const struct cec_msg *msg, struct cec_op_ui_command { __u8 ui_cmd; - bool has_opt_arg; + __u8 has_opt_arg; union { struct cec_op_channel_data channel_identifier; __u8 ui_broadcast_type; @@ -1354,7 +1354,7 @@ static inline void cec_ops_user_control_pressed(const struct cec_msg *msg, struct cec_op_ui_command *ui_cmd) { ui_cmd->ui_cmd = msg->msg[2]; - ui_cmd->has_opt_arg = false; + ui_cmd->has_opt_arg = 0; if (msg->len == 3) return; switch (ui_cmd->ui_cmd) { @@ -1366,12 +1366,12 @@ static inline void cec_ops_user_control_pressed(const struct cec_msg *msg, case 0x6a: /* The optional operand is one byte for all these ui commands */ ui_cmd->play_mode = msg->msg[3]; - ui_cmd->has_opt_arg = true; + ui_cmd->has_opt_arg = 1; break; case 0x67: if (msg->len < 7) break; - ui_cmd->has_opt_arg = true; + ui_cmd->has_opt_arg = 1; ui_cmd->channel_identifier.channel_number_fmt = msg->msg[3] >> 2; ui_cmd->channel_identifier.major = ((msg->msg[3] & 3) << 6) | msg->msg[4]; ui_cmd->channel_identifier.minor = (msg->msg[5] << 8) | msg->msg[6]; @@ -1403,7 +1403,7 @@ static inline void cec_ops_report_power_status(const struct cec_msg *msg, } static inline void cec_msg_give_device_power_status(struct cec_msg *msg, - bool reply) + int reply) { msg->len = 2; msg->msg[1] = CEC_MSG_GIVE_DEVICE_POWER_STATUS; @@ -1463,7 +1463,7 @@ static inline void cec_ops_report_audio_status(const struct cec_msg *msg, } static inline void cec_msg_give_audio_status(struct cec_msg *msg, - bool reply) + int reply) { msg->len = 2; msg->msg[1] = CEC_MSG_GIVE_AUDIO_STATUS; @@ -1485,7 +1485,7 @@ static inline void cec_ops_set_system_audio_mode(const struct cec_msg *msg, } static inline void cec_msg_system_audio_mode_request(struct cec_msg *msg, - bool reply, + int reply, __u16 phys_addr) { msg->len = phys_addr == 0xffff ? 2 : 4; @@ -1520,7 +1520,7 @@ static inline void cec_ops_system_audio_mode_status(const struct cec_msg *msg, } static inline void cec_msg_give_system_audio_mode_status(struct cec_msg *msg, - bool reply) + int reply) { msg->len = 2; msg->msg[1] = CEC_MSG_GIVE_SYSTEM_AUDIO_MODE_STATUS; @@ -1560,7 +1560,7 @@ static inline void cec_ops_report_short_audio_descriptor(const struct cec_msg *m } static inline void cec_msg_request_short_audio_descriptor(struct cec_msg *msg, - bool reply, + int reply, __u8 num_descriptors, const __u8 *audio_format_id, const __u8 *audio_format_code) @@ -1618,7 +1618,7 @@ static inline void cec_msg_report_arc_initiated(struct cec_msg *msg) } static inline void cec_msg_initiate_arc(struct cec_msg *msg, - bool reply) + int reply) { msg->len = 2; msg->msg[1] = CEC_MSG_INITIATE_ARC; @@ -1626,7 +1626,7 @@ static inline void cec_msg_initiate_arc(struct cec_msg *msg, } static inline void cec_msg_request_arc_initiation(struct cec_msg *msg, - bool reply) + int reply) { msg->len = 2; msg->msg[1] = CEC_MSG_REQUEST_ARC_INITIATION; @@ -1640,7 +1640,7 @@ static inline void cec_msg_report_arc_terminated(struct cec_msg *msg) } static inline void cec_msg_terminate_arc(struct cec_msg *msg, - bool reply) + int reply) { msg->len = 2; msg->msg[1] = CEC_MSG_TERMINATE_ARC; @@ -1648,7 +1648,7 @@ static inline void cec_msg_terminate_arc(struct cec_msg *msg, } static inline void cec_msg_request_arc_termination(struct cec_msg *msg, - bool reply) + int reply) { msg->len = 2; msg->msg[1] = CEC_MSG_REQUEST_ARC_TERMINATION; @@ -1690,7 +1690,7 @@ static inline void cec_ops_report_current_latency(const struct cec_msg *msg, } static inline void cec_msg_request_current_latency(struct cec_msg *msg, - bool reply, + int reply, __u16 phys_addr) { msg->len = 4; diff --git a/include/uapi/linux/cec.h b/include/uapi/linux/cec.h index f4ec0af67707..14b6f24b189e 100644 --- a/include/uapi/linux/cec.h +++ b/include/uapi/linux/cec.h @@ -37,6 +37,7 @@ #define _CEC_UAPI_H #include +#include #define CEC_MAX_MSG_SIZE 16 @@ -129,7 +130,7 @@ static inline int cec_msg_opcode(const struct cec_msg *msg) * cec_msg_is_broadcast - return true if this is a broadcast message. * @msg: the message structure */ -static inline bool cec_msg_is_broadcast(const struct cec_msg *msg) +static inline int cec_msg_is_broadcast(const struct cec_msg *msg) { return (msg->msg[0] & 0xf) == 0xf; } @@ -184,14 +185,14 @@ static inline void cec_msg_set_reply_to(struct cec_msg *msg, #define CEC_RX_STATUS_TIMEOUT (1 << 1) #define CEC_RX_STATUS_FEATURE_ABORT (1 << 2) -static inline bool cec_msg_status_is_ok(const struct cec_msg *msg) +static inline int cec_msg_status_is_ok(const struct cec_msg *msg) { if (msg->tx_status && !(msg->tx_status & CEC_TX_STATUS_OK)) - return false; + return 0; if (msg->rx_status && !(msg->rx_status & CEC_RX_STATUS_OK)) - return false; + return 0; if (!msg->tx_status && !msg->rx_status) - return false; + return 0; return !(msg->rx_status & CEC_RX_STATUS_FEATURE_ABORT); } @@ -254,47 +255,47 @@ static inline bool cec_msg_status_is_ok(const struct cec_msg *msg) #define CEC_LOG_ADDR_MASK_SPECIFIC (1 << CEC_LOG_ADDR_SPECIFIC) #define CEC_LOG_ADDR_MASK_UNREGISTERED (1 << CEC_LOG_ADDR_UNREGISTERED) -static inline bool cec_has_tv(__u16 log_addr_mask) +static inline int cec_has_tv(__u16 log_addr_mask) { return log_addr_mask & CEC_LOG_ADDR_MASK_TV; } -static inline bool cec_has_record(__u16 log_addr_mask) +static inline int cec_has_record(__u16 log_addr_mask) { return log_addr_mask & CEC_LOG_ADDR_MASK_RECORD; } -static inline bool cec_has_tuner(__u16 log_addr_mask) +static inline int cec_has_tuner(__u16 log_addr_mask) { return log_addr_mask & CEC_LOG_ADDR_MASK_TUNER; } -static inline bool cec_has_playback(__u16 log_addr_mask) +static inline int cec_has_playback(__u16 log_addr_mask) { return log_addr_mask & CEC_LOG_ADDR_MASK_PLAYBACK; } -static inline bool cec_has_audiosystem(__u16 log_addr_mask) +static inline int cec_has_audiosystem(__u16 log_addr_mask) { return log_addr_mask & CEC_LOG_ADDR_MASK_AUDIOSYSTEM; } -static inline bool cec_has_backup(__u16 log_addr_mask) +static inline int cec_has_backup(__u16 log_addr_mask) { return log_addr_mask & CEC_LOG_ADDR_MASK_BACKUP; } -static inline bool cec_has_specific(__u16 log_addr_mask) +static inline int cec_has_specific(__u16 log_addr_mask) { return log_addr_mask & CEC_LOG_ADDR_MASK_SPECIFIC; } -static inline bool cec_is_unregistered(__u16 log_addr_mask) +static inline int cec_is_unregistered(__u16 log_addr_mask) { return log_addr_mask & CEC_LOG_ADDR_MASK_UNREGISTERED; } -static inline bool cec_is_unconfigured(__u16 log_addr_mask) +static inline int cec_is_unconfigured(__u16 log_addr_mask) { return log_addr_mask == 0; } @@ -1016,7 +1017,7 @@ struct cec_event { /* Helper functions to identify the 'special' CEC devices */ -static inline bool cec_is_2nd_tv(const struct cec_log_addrs *las) +static inline int cec_is_2nd_tv(const struct cec_log_addrs *las) { /* * It is a second TV if the logical address is 14 or 15 and the @@ -1027,7 +1028,7 @@ static inline bool cec_is_2nd_tv(const struct cec_log_addrs *las) las->primary_device_type[0] == CEC_OP_PRIM_DEVTYPE_TV; } -static inline bool cec_is_processor(const struct cec_log_addrs *las) +static inline int cec_is_processor(const struct cec_log_addrs *las) { /* * It is a processor if the logical address is 12-15 and the @@ -1038,7 +1039,7 @@ static inline bool cec_is_processor(const struct cec_log_addrs *las) las->primary_device_type[0] == CEC_OP_PRIM_DEVTYPE_PROCESSOR; } -static inline bool cec_is_switch(const struct cec_log_addrs *las) +static inline int cec_is_switch(const struct cec_log_addrs *las) { /* * It is a switch if the logical address is 15 and the @@ -1050,7 +1051,7 @@ static inline bool cec_is_switch(const struct cec_log_addrs *las) !(las->flags & CEC_LOG_ADDRS_FL_CDC_ONLY); } -static inline bool cec_is_cdc_only(const struct cec_log_addrs *las) +static inline int cec_is_cdc_only(const struct cec_log_addrs *las) { /* * It is a CDC-only device if the logical address is 15 and the -- cgit v1.2.3 From 446e412597217e937d33296e77eeba7379ab3008 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 4 Aug 2016 13:14:02 -0300 Subject: [media] v4l: ctrls: Add deinterlacing mode control The menu control selects the operation mode of a video deinterlacer. The menu entries are driver specific. Signed-off-by: Laurent Pinchart Reviewed-by: Kieran Bingham Acked-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/v4l/extended-controls.rst | 4 ++++ Documentation/media/v4l-drivers/index.rst | 2 ++ drivers/media/v4l2-core/v4l2-ctrls.c | 2 ++ include/uapi/linux/v4l2-controls.h | 1 + 4 files changed, 9 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/media/uapi/v4l/extended-controls.rst b/Documentation/media/uapi/v4l/extended-controls.rst index 7725c33d8b69..40071ea5d90e 100644 --- a/Documentation/media/uapi/v4l/extended-controls.rst +++ b/Documentation/media/uapi/v4l/extended-controls.rst @@ -3017,6 +3017,10 @@ Image Process Control IDs test pattern images. These hardware specific test patterns can be used to test if a device is working properly. +``V4L2_CID_DEINTERLACING_MODE (menu)`` + The video deinterlacing mode (such as Bob, Weave, ...). The menu items are + driver specific and are documented in :ref:`v4l-drivers`. + .. _dv-controls: diff --git a/Documentation/media/v4l-drivers/index.rst b/Documentation/media/v4l-drivers/index.rst index aac566f88833..acde3ed7860f 100644 --- a/Documentation/media/v4l-drivers/index.rst +++ b/Documentation/media/v4l-drivers/index.rst @@ -2,6 +2,8 @@ .. include:: +.. _v4l-drivers: + ################################################ Video4Linux (V4L) driver-specific documentation ################################################ diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index adc2147fcff7..47001e25fd9e 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -885,6 +885,7 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_LINK_FREQ: return "Link Frequency"; case V4L2_CID_PIXEL_RATE: return "Pixel Rate"; case V4L2_CID_TEST_PATTERN: return "Test Pattern"; + case V4L2_CID_DEINTERLACING_MODE: return "Deinterlacing Mode"; /* DV controls */ /* Keep the order of the 'case's the same as in v4l2-controls.h! */ @@ -1058,6 +1059,7 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, case V4L2_CID_DV_RX_RGB_RANGE: case V4L2_CID_DV_RX_IT_CONTENT_TYPE: case V4L2_CID_TEST_PATTERN: + case V4L2_CID_DEINTERLACING_MODE: case V4L2_CID_TUNE_DEEMPHASIS: case V4L2_CID_MPEG_VIDEO_VPX_GOLDEN_FRAME_SEL: case V4L2_CID_DETECT_MD_MODE: diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index b6a357a5f053..0d2e1e01fbd5 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -892,6 +892,7 @@ enum v4l2_jpeg_chroma_subsampling { #define V4L2_CID_LINK_FREQ (V4L2_CID_IMAGE_PROC_CLASS_BASE + 1) #define V4L2_CID_PIXEL_RATE (V4L2_CID_IMAGE_PROC_CLASS_BASE + 2) #define V4L2_CID_TEST_PATTERN (V4L2_CID_IMAGE_PROC_CLASS_BASE + 3) +#define V4L2_CID_DEINTERLACING_MODE (V4L2_CID_IMAGE_PROC_CLASS_BASE + 4) /* DV-class control IDs defined by V4L2 */ -- cgit v1.2.3 From 2818c6e91980d966d015a9f763ab24b41e6a7c3d Mon Sep 17 00:00:00 2001 From: Kirti Wankhede Date: Thu, 17 Nov 2016 02:16:30 +0530 Subject: vfio: Define device_api strings Defined device API strings. Vendor driver using mediated device framework should use corresponding string for device_api attribute. Signed-off-by: Kirti Wankhede Signed-off-by: Neo Jia Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 255a2113f53c..519eff362c1c 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -203,6 +203,16 @@ struct vfio_device_info { }; #define VFIO_DEVICE_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 7) +/* + * Vendor driver using Mediated device framework should provide device_api + * attribute in supported type attribute groups. Device API string should be one + * of the following corresponding to device flags in vfio_device_info structure. + */ + +#define VFIO_DEVICE_API_PCI_STRING "vfio-pci" +#define VFIO_DEVICE_API_PLATFORM_STRING "vfio-platform" +#define VFIO_DEVICE_API_AMBA_STRING "vfio-amba" + /** * VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8, * struct vfio_region_info) -- cgit v1.2.3 From 0d27f4e437e448c4ff440a31567b9729d1634d66 Mon Sep 17 00:00:00 2001 From: Raju Lakkaraju Date: Thu, 17 Nov 2016 13:07:20 +0100 Subject: ethtool: (uapi) Add ETHTOOL_PHY_GTUNABLE and ETHTOOL_PHY_STUNABLE Defines a generic API to get/set phy tunables. The API is using the existing ethtool_tunable/tunable_type_id types which is already being used for mac level tunables. Signed-off-by: Raju Lakkaraju Reviewed-by: Andrew Lunn Signed-off-by: Allan W. Nielsen Signed-off-by: David S. Miller --- include/uapi/linux/ethtool.h | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 8e547231c1b7..42f696f139ec 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -248,6 +248,16 @@ struct ethtool_tunable { void *data[0]; }; +enum phy_tunable_id { + ETHTOOL_PHY_ID_UNSPEC, + + /* + * Add your fresh new phy tunable attribute above and remember to update + * phy_tunable_strings[] in net/core/ethtool.c + */ + __ETHTOOL_PHY_TUNABLE_COUNT, +}; + /** * struct ethtool_regs - hardware register dump * @cmd: Command number = %ETHTOOL_GREGS @@ -548,6 +558,7 @@ struct ethtool_pauseparam { * @ETH_SS_FEATURES: Device feature names * @ETH_SS_RSS_HASH_FUNCS: RSS hush function names * @ETH_SS_PHY_STATS: Statistic names, for use with %ETHTOOL_GPHYSTATS + * @ETH_SS_PHY_TUNABLES: PHY tunable names */ enum ethtool_stringset { ETH_SS_TEST = 0, @@ -558,6 +569,7 @@ enum ethtool_stringset { ETH_SS_RSS_HASH_FUNCS, ETH_SS_TUNABLES, ETH_SS_PHY_STATS, + ETH_SS_PHY_TUNABLES, }; /** @@ -1313,7 +1325,8 @@ struct ethtool_per_queue_op { #define ETHTOOL_GLINKSETTINGS 0x0000004c /* Get ethtool_link_settings */ #define ETHTOOL_SLINKSETTINGS 0x0000004d /* Set ethtool_link_settings */ - +#define ETHTOOL_PHY_GTUNABLE 0x0000004e /* Get PHY tunable configuration */ +#define ETHTOOL_PHY_STUNABLE 0x0000004f /* Set PHY tunable configuration */ /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET -- cgit v1.2.3 From 607c7029146790201e90b58c4235ddff0304d6e0 Mon Sep 17 00:00:00 2001 From: Raju Lakkaraju Date: Thu, 17 Nov 2016 13:07:22 +0100 Subject: ethtool: (uapi) Add ETHTOOL_PHY_DOWNSHIFT to PHY tunables For operation in cabling environments that are incompatible with 1000BASE-T, PHY device may provide an automatic link speed downshift operation. When enabled, the device automatically changes its 1000BASE-T auto-negotiation to the next slower speed after a configured number of failed attempts at 1000BASE-T. This feature is useful in setting up in networks using older cable installations that include only pairs A and B, and not pairs C and D. Signed-off-by: Raju Lakkaraju Signed-off-by: Allan W. Nielsen Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/uapi/linux/ethtool.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 42f696f139ec..f0db7788f887 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -248,9 +248,12 @@ struct ethtool_tunable { void *data[0]; }; +#define DOWNSHIFT_DEV_DEFAULT_COUNT 0xff +#define DOWNSHIFT_DEV_DISABLE 0 + enum phy_tunable_id { ETHTOOL_PHY_ID_UNSPEC, - + ETHTOOL_PHY_DOWNSHIFT, /* * Add your fresh new phy tunable attribute above and remember to update * phy_tunable_strings[] in net/core/ethtool.c -- cgit v1.2.3 From 651be3cb085341a21847e47c694c249c3e1e4e5b Mon Sep 17 00:00:00 2001 From: Pratyush Anand Date: Mon, 14 Nov 2016 19:32:42 +0530 Subject: hw_breakpoint: Allow watchpoint of length 3,5,6 and 7 We only support breakpoint/watchpoint of length 1, 2, 4 and 8. If we can support other length as well, then user may watch more data with less number of watchpoints (provided hardware supports it). For example: if we have to watch only 4th, 5th and 6th byte from a 64 bit aligned address, we will have to use two slots to implement it currently. One slot will watch a half word at offset 4 and other a byte at offset 6. If we can have a watchpoint of length 3 then we can watch it with single slot as well. ARM64 hardware does support such functionality, therefore adding these new definitions in generic layer. Signed-off-by: Pratyush Anand Signed-off-by: Will Deacon --- include/uapi/linux/hw_breakpoint.h | 4 ++++ tools/include/uapi/linux/hw_breakpoint.h | 4 ++++ 2 files changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/hw_breakpoint.h b/include/uapi/linux/hw_breakpoint.h index b04000a2296a..2b65efd19a46 100644 --- a/include/uapi/linux/hw_breakpoint.h +++ b/include/uapi/linux/hw_breakpoint.h @@ -4,7 +4,11 @@ enum { HW_BREAKPOINT_LEN_1 = 1, HW_BREAKPOINT_LEN_2 = 2, + HW_BREAKPOINT_LEN_3 = 3, HW_BREAKPOINT_LEN_4 = 4, + HW_BREAKPOINT_LEN_5 = 5, + HW_BREAKPOINT_LEN_6 = 6, + HW_BREAKPOINT_LEN_7 = 7, HW_BREAKPOINT_LEN_8 = 8, }; diff --git a/tools/include/uapi/linux/hw_breakpoint.h b/tools/include/uapi/linux/hw_breakpoint.h index b04000a2296a..2b65efd19a46 100644 --- a/tools/include/uapi/linux/hw_breakpoint.h +++ b/tools/include/uapi/linux/hw_breakpoint.h @@ -4,7 +4,11 @@ enum { HW_BREAKPOINT_LEN_1 = 1, HW_BREAKPOINT_LEN_2 = 2, + HW_BREAKPOINT_LEN_3 = 3, HW_BREAKPOINT_LEN_4 = 4, + HW_BREAKPOINT_LEN_5 = 5, + HW_BREAKPOINT_LEN_6 = 6, + HW_BREAKPOINT_LEN_7 = 7, HW_BREAKPOINT_LEN_8 = 8, }; -- cgit v1.2.3 From e3fd9a93a12a1020067a676e826877623cee8e2b Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 9 Nov 2016 17:48:15 +0100 Subject: kvm: kvmclock: let KVM_GET_CLOCK return whether the master clock is in use MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Userspace can read the exact value of kvmclock by reading the TSC and fetching the timekeeping parameters out of guest memory. This however is brittle and not necessary anymore with KVM 4.11. Provide a mechanism that lets userspace know if the new KVM_GET_CLOCK semantics are in effect, and---since we are at it---if the clock is stable across all VCPUs. Cc: Radim Krčmář Cc: Marcelo Tosatti Signed-off-by: Paolo Bonzini Signed-off-by: Radim Krčmář --- Documentation/virtual/kvm/api.txt | 11 +++++++++++ arch/x86/kvm/x86.c | 10 +++++++--- include/uapi/linux/kvm.h | 7 +++++++ 3 files changed, 25 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 739db9ab16b2..6bbceb9a3a19 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -777,6 +777,17 @@ Gets the current timestamp of kvmclock as seen by the current guest. In conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios such as migration. +When KVM_CAP_ADJUST_CLOCK is passed to KVM_CHECK_EXTENSION, it returns the +set of bits that KVM can return in struct kvm_clock_data's flag member. + +The only flag defined now is KVM_CLOCK_TSC_STABLE. If set, the returned +value is the exact kvmclock value seen by all VCPUs at the instant +when KVM_GET_CLOCK was called. If clear, the returned value is simply +CLOCK_MONOTONIC plus a constant offset; the offset can be modified +with KVM_SET_CLOCK. KVM will try to make all VCPUs follow this clock, +but the exact value read by each VCPU could differ, because the host +TSC is not stable. + struct kvm_clock_data { __u64 clock; /* kvmclock current value */ __u32 flags; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2f27af4f312a..3320804bb2ac 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2610,7 +2610,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_PIT_STATE2: case KVM_CAP_SET_IDENTITY_MAP_ADDR: case KVM_CAP_XEN_HVM: - case KVM_CAP_ADJUST_CLOCK: case KVM_CAP_VCPU_EVENTS: case KVM_CAP_HYPERV: case KVM_CAP_HYPERV_VAPIC: @@ -2637,6 +2636,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) #endif r = 1; break; + case KVM_CAP_ADJUST_CLOCK: + r = KVM_CLOCK_TSC_STABLE; + break; case KVM_CAP_X86_SMM: /* SMBASE is usually relocated above 1M on modern chipsets, * and SMM handlers might indeed rely on 4G segment limits, @@ -4117,9 +4119,11 @@ long kvm_arch_vm_ioctl(struct file *filp, struct kvm_clock_data user_ns; u64 now_ns; - now_ns = get_kvmclock_ns(kvm); + local_irq_disable(); + now_ns = __get_kvmclock_ns(kvm); user_ns.clock = now_ns; - user_ns.flags = 0; + user_ns.flags = kvm->arch.use_master_clock ? KVM_CLOCK_TSC_STABLE : 0; + local_irq_enable(); memset(&user_ns.pad, 0, sizeof(user_ns.pad)); r = -EFAULT; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 300ef255d1e0..4ee67cb99143 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -972,12 +972,19 @@ struct kvm_irqfd { __u8 pad[16]; }; +/* For KVM_CAP_ADJUST_CLOCK */ + +/* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags. */ +#define KVM_CLOCK_TSC_STABLE 2 + struct kvm_clock_data { __u64 clock; __u32 flags; __u32 pad[9]; }; +/* For KVM_CAP_SW_TLB */ + #define KVM_MMU_FSL_BOOKE_NOHV 0 #define KVM_MMU_FSL_BOOKE_HV 1 -- cgit v1.2.3 From 209e2367917317d51732473627ac38e730340b45 Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Sun, 28 Aug 2016 08:42:37 +0200 Subject: uapi dm-log-userspace.h: use __u32, __s32, __u64 and __s64 from linux/types.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes userspace compilation errors like: linux/dm-log-userspace.h:416:2: error: unknown type name ‘uint64_t’ Signed-off-by: Mikko Rapeli Reviewed-by: Bart Van Assche Signed-off-by: Mike Snitzer --- include/uapi/linux/dm-log-userspace.h | 53 ++++++++++++++++++----------------- 1 file changed, 27 insertions(+), 26 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/dm-log-userspace.h b/include/uapi/linux/dm-log-userspace.h index 0fa0d9ef06a5..05e91e14c501 100644 --- a/include/uapi/linux/dm-log-userspace.h +++ b/include/uapi/linux/dm-log-userspace.h @@ -7,6 +7,7 @@ #ifndef __DM_LOG_USERSPACE_H__ #define __DM_LOG_USERSPACE_H__ +#include #include /* For DM_UUID_LEN */ /* @@ -147,12 +148,12 @@ /* * DM_ULOG_GET_REGION_SIZE corresponds to (found in dm-dirty-log.h): - * uint32_t (*get_region_size)(struct dm_dirty_log *log); + * __u32 (*get_region_size)(struct dm_dirty_log *log); * * Payload-to-userspace: * None. * Payload-to-kernel: - * uint64_t - contains the region size + * __u64 - contains the region size * * The region size is something that was determined at constructor time. * It is returned in the payload area and 'data_size' is set to @@ -168,11 +169,11 @@ * int (*is_clean)(struct dm_dirty_log *log, region_t region); * * Payload-to-userspace: - * uint64_t - the region to get clean status on + * __u64 - the region to get clean status on * Payload-to-kernel: - * int64_t - 1 if clean, 0 otherwise + * __s64 - 1 if clean, 0 otherwise * - * Payload is sizeof(uint64_t) and contains the region for which the clean + * Payload is sizeof(__u64) and contains the region for which the clean * status is being made. * * When the request has been processed, user-space must return the @@ -187,9 +188,9 @@ * int can_block); * * Payload-to-userspace: - * uint64_t - the region to get sync status on + * __u64 - the region to get sync status on * Payload-to-kernel: - * int64_t - 1 if in-sync, 0 otherwise + * __s64 - 1 if in-sync, 0 otherwise * * Exactly the same as 'is_clean' above, except this time asking "has the * region been recovered?" vs. "is the region not being modified?" @@ -203,7 +204,7 @@ * Payload-to-userspace: * If the 'integrated_flush' directive is present in the constructor * table, the payload is as same as DM_ULOG_MARK_REGION: - * uint64_t [] - region(s) to mark + * __u64 [] - region(s) to mark * else * None * Payload-to-kernel: @@ -225,13 +226,13 @@ * void (*mark_region)(struct dm_dirty_log *log, region_t region); * * Payload-to-userspace: - * uint64_t [] - region(s) to mark + * __u64 [] - region(s) to mark * Payload-to-kernel: * None. * * Incoming payload contains the one or more regions to mark dirty. * The number of regions contained in the payload can be determined from - * 'data_size/sizeof(uint64_t)'. + * 'data_size/sizeof(__u64)'. * * When the request has been processed, user-space must return the * dm_ulog_request to the kernel - setting the 'error' field and clearing @@ -244,13 +245,13 @@ * void (*clear_region)(struct dm_dirty_log *log, region_t region); * * Payload-to-userspace: - * uint64_t [] - region(s) to clear + * __u64 [] - region(s) to clear * Payload-to-kernel: * None. * * Incoming payload contains the one or more regions to mark clean. * The number of regions contained in the payload can be determined from - * 'data_size/sizeof(uint64_t)'. + * 'data_size/sizeof(__u64)'. * * When the request has been processed, user-space must return the * dm_ulog_request to the kernel - setting the 'error' field and clearing @@ -266,8 +267,8 @@ * None. * Payload-to-kernel: * { - * int64_t i; -- 1 if recovery necessary, 0 otherwise - * uint64_t r; -- The region to recover if i=1 + * __s64 i; -- 1 if recovery necessary, 0 otherwise + * __u64 r; -- The region to recover if i=1 * } * 'data_size' should be set appropriately. * @@ -283,8 +284,8 @@ * * Payload-to-userspace: * { - * uint64_t - region to set sync state on - * int64_t - 0 if not-in-sync, 1 if in-sync + * __u64 - region to set sync state on + * __s64 - 0 if not-in-sync, 1 if in-sync * } * Payload-to-kernel: * None. @@ -302,7 +303,7 @@ * Payload-to-userspace: * None. * Payload-to-kernel: - * uint64_t - the number of in-sync regions + * __u64 - the number of in-sync regions * * No incoming payload. Kernel-bound payload contains the number of * regions that are in-sync (in a size_t). @@ -350,11 +351,11 @@ * int (*is_remote_recovering)(struct dm_dirty_log *log, region_t region); * * Payload-to-userspace: - * uint64_t - region to determine recovery status on + * __u64 - region to determine recovery status on * Payload-to-kernel: * { - * int64_t is_recovering; -- 0 if no, 1 if yes - * uint64_t in_sync_hint; -- lowest region still needing resync + * __s64 is_recovering; -- 0 if no, 1 if yes + * __u64 in_sync_hint; -- lowest region still needing resync * } * * When the request has been processed, user-space must return the @@ -413,16 +414,16 @@ struct dm_ulog_request { * differentiate between logs that are being swapped and have the * same 'uuid'. (Think "live" and "inactive" device-mapper tables.) */ - uint64_t luid; + __u64 luid; char uuid[DM_UUID_LEN]; char padding[3]; /* Padding because DM_UUID_LEN = 129 */ - uint32_t version; /* See DM_ULOG_REQUEST_VERSION */ - int32_t error; /* Used to report back processing errors */ + __u32 version; /* See DM_ULOG_REQUEST_VERSION */ + __s32 error; /* Used to report back processing errors */ - uint32_t seq; /* Sequence number for request */ - uint32_t request_type; /* DM_ULOG_* defined above */ - uint32_t data_size; /* How much data (not including this struct) */ + __u32 seq; /* Sequence number for request */ + __u32 request_type; /* DM_ULOG_* defined above */ + __u32 data_size; /* How much data (not including this struct) */ char data[0]; }; -- cgit v1.2.3 From 5e9235853d652a295d5f56cb8652950b6b5bf56b Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Mon, 21 Nov 2016 13:03:24 +0100 Subject: bridge: mcast: add IGMPv3 query support This patch adds basic support for IGMPv3 queries, the default is IGMPv2 as before. A new multicast option - multicast_igmp_version, adds the ability to change it between 2 and 3 via netlink and sysfs. The option struct member is in a 4 byte hole in net_bridge. There also a few minor style adjustments in br_multicast_new_group and br_multicast_add_group. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_multicast.c | 79 ++++++++++++++++++++++++++++++++++---------- net/bridge/br_netlink.c | 15 ++++++++- net/bridge/br_private.h | 3 ++ net/bridge/br_sysfs_br.c | 18 ++++++++++ 5 files changed, 98 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index b4fba662cd32..325d2601150d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -275,6 +275,7 @@ enum { IFLA_BR_PAD, IFLA_BR_VLAN_STATS_ENABLED, IFLA_BR_MCAST_STATS_ENABLED, + IFLA_BR_MCAST_IGMP_VERSION, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 073d54afa056..66192c11aa45 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -365,13 +365,18 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, __be32 group, u8 *igmp_type) { + struct igmpv3_query *ihv3; + size_t igmp_hdr_size; struct sk_buff *skb; struct igmphdr *ih; struct ethhdr *eth; struct iphdr *iph; + igmp_hdr_size = sizeof(*ih); + if (br->multicast_igmp_version == 3) + igmp_hdr_size = sizeof(*ihv3); skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*iph) + - sizeof(*ih) + 4); + igmp_hdr_size + 4); if (!skb) goto out; @@ -396,7 +401,7 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, iph->version = 4; iph->ihl = 6; iph->tos = 0xc0; - iph->tot_len = htons(sizeof(*iph) + sizeof(*ih) + 4); + iph->tot_len = htons(sizeof(*iph) + igmp_hdr_size + 4); iph->id = 0; iph->frag_off = htons(IP_DF); iph->ttl = 1; @@ -412,17 +417,37 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, skb_put(skb, 24); skb_set_transport_header(skb, skb->len); - ih = igmp_hdr(skb); *igmp_type = IGMP_HOST_MEMBERSHIP_QUERY; - ih->type = IGMP_HOST_MEMBERSHIP_QUERY; - ih->code = (group ? br->multicast_last_member_interval : - br->multicast_query_response_interval) / - (HZ / IGMP_TIMER_SCALE); - ih->group = group; - ih->csum = 0; - ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr)); - skb_put(skb, sizeof(*ih)); + switch (br->multicast_igmp_version) { + case 2: + ih = igmp_hdr(skb); + ih->type = IGMP_HOST_MEMBERSHIP_QUERY; + ih->code = (group ? br->multicast_last_member_interval : + br->multicast_query_response_interval) / + (HZ / IGMP_TIMER_SCALE); + ih->group = group; + ih->csum = 0; + ih->csum = ip_compute_csum((void *)ih, sizeof(*ih)); + break; + case 3: + ihv3 = igmpv3_query_hdr(skb); + ihv3->type = IGMP_HOST_MEMBERSHIP_QUERY; + ihv3->code = (group ? br->multicast_last_member_interval : + br->multicast_query_response_interval) / + (HZ / IGMP_TIMER_SCALE); + ihv3->group = group; + ihv3->qqic = br->multicast_query_interval / HZ; + ihv3->nsrcs = 0; + ihv3->resv = 0; + ihv3->suppress = 0; + ihv3->qrv = 2; + ihv3->csum = 0; + ihv3->csum = ip_compute_csum((void *)ihv3, sizeof(*ihv3)); + break; + } + + skb_put(skb, igmp_hdr_size); __skb_pull(skb, sizeof(*eth)); out: @@ -608,7 +633,8 @@ err: } struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br, - struct net_bridge_port *port, struct br_ip *group) + struct net_bridge_port *p, + struct br_ip *group) { struct net_bridge_mdb_htable *mdb; struct net_bridge_mdb_entry *mp; @@ -624,7 +650,7 @@ struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br, } hash = br_ip_hash(mdb, group); - mp = br_multicast_get_group(br, port, group, hash); + mp = br_multicast_get_group(br, p, group, hash); switch (PTR_ERR(mp)) { case 0: break; @@ -681,9 +707,9 @@ static int br_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, struct br_ip *group) { - struct net_bridge_mdb_entry *mp; - struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; + struct net_bridge_port_group *p; + struct net_bridge_mdb_entry *mp; unsigned long now = jiffies; int err; @@ -861,9 +887,9 @@ static void br_multicast_send_query(struct net_bridge *br, struct net_bridge_port *port, struct bridge_mcast_own_query *own_query) { - unsigned long time; - struct br_ip br_group; struct bridge_mcast_other_query *other_query = NULL; + struct br_ip br_group; + unsigned long time; if (!netif_running(br->dev) || br->multicast_disabled || !br->multicast_querier) @@ -1816,6 +1842,7 @@ void br_multicast_init(struct net_bridge *br) br->hash_elasticity = 4; br->hash_max = 512; + br->multicast_igmp_version = 2; br->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; br->multicast_querier = 0; br->multicast_query_use_ifaddr = 0; @@ -2132,6 +2159,24 @@ unlock: return err; } +int br_multicast_set_igmp_version(struct net_bridge *br, unsigned long val) +{ + /* Currently we support only version 2 and 3 */ + switch (val) { + case 2: + case 3: + break; + default: + return -EINVAL; + } + + spin_lock_bh(&br->multicast_lock); + br->multicast_igmp_version = val; + spin_unlock_bh(&br->multicast_lock); + + return 0; +} + /** * br_multicast_list_adjacent - Returns snooped multicast addresses * @dev: The bridge port adjacent to which to retrieve addresses diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index e99037c6f7b7..10b9b80f778f 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -858,6 +858,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_VLAN_DEFAULT_PVID] = { .type = NLA_U16 }, [IFLA_BR_VLAN_STATS_ENABLED] = { .type = NLA_U8 }, [IFLA_BR_MCAST_STATS_ENABLED] = { .type = NLA_U8 }, + [IFLA_BR_MCAST_IGMP_VERSION] = { .type = NLA_U8 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -1069,6 +1070,15 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], mcast_stats = nla_get_u8(data[IFLA_BR_MCAST_STATS_ENABLED]); br->multicast_stats_enabled = !!mcast_stats; } + + if (data[IFLA_BR_MCAST_IGMP_VERSION]) { + __u8 igmp_version; + + igmp_version = nla_get_u8(data[IFLA_BR_MCAST_IGMP_VERSION]); + err = br_multicast_set_igmp_version(br, igmp_version); + if (err) + return err; + } #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (data[IFLA_BR_NF_CALL_IPTABLES]) { @@ -1135,6 +1145,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_RESPONSE_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_STARTUP_QUERY_INTVL */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_IGMP_VERSION */ #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IPTABLES */ @@ -1210,7 +1221,9 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u32(skb, IFLA_BR_MCAST_LAST_MEMBER_CNT, br->multicast_last_member_count) || nla_put_u32(skb, IFLA_BR_MCAST_STARTUP_QUERY_CNT, - br->multicast_startup_query_count)) + br->multicast_startup_query_count) || + nla_put_u8(skb, IFLA_BR_MCAST_IGMP_VERSION, + br->multicast_igmp_version)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_last_member_interval); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 1b63177e0ccd..3d207d92d899 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -333,6 +333,8 @@ struct net_bridge u32 multicast_last_member_count; u32 multicast_startup_query_count; + u8 multicast_igmp_version; + unsigned long multicast_last_member_interval; unsigned long multicast_membership_interval; unsigned long multicast_querier_interval; @@ -582,6 +584,7 @@ int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val); int br_multicast_toggle(struct net_bridge *br, unsigned long val); int br_multicast_set_querier(struct net_bridge *br, unsigned long val); int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val); +int br_multicast_set_igmp_version(struct net_bridge *br, unsigned long val); struct net_bridge_mdb_entry * br_mdb_ip_get(struct net_bridge_mdb_htable *mdb, struct br_ip *dst); struct net_bridge_mdb_entry * diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index e120307c6e36..f00d1690658c 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -440,6 +440,23 @@ static ssize_t hash_max_store(struct device *d, struct device_attribute *attr, } static DEVICE_ATTR_RW(hash_max); +static ssize_t multicast_igmp_version_show(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + + return sprintf(buf, "%u\n", br->multicast_igmp_version); +} + +static ssize_t multicast_igmp_version_store(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, br_multicast_set_igmp_version); +} +static DEVICE_ATTR_RW(multicast_igmp_version); + static ssize_t multicast_last_member_count_show(struct device *d, struct device_attribute *attr, char *buf) @@ -809,6 +826,7 @@ static struct attribute *bridge_attrs[] = { &dev_attr_multicast_query_response_interval.attr, &dev_attr_multicast_startup_query_interval.attr, &dev_attr_multicast_stats_enabled.attr, + &dev_attr_multicast_igmp_version.attr, #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) &dev_attr_nf_call_iptables.attr, -- cgit v1.2.3 From aa2ae3e71c74cc00ec22f133dc900b3817415785 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Mon, 21 Nov 2016 13:03:25 +0100 Subject: bridge: mcast: add MLDv2 querier support This patch adds basic support for MLDv2 queries, the default is MLDv1 as before. A new multicast option - multicast_mld_version, adds the ability to change it between 1 and 2 via netlink and sysfs. The MLD option is disabled if CONFIG_IPV6 is disabled. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_multicast.c | 89 +++++++++++++++++++++++++++++++++----------- net/bridge/br_netlink.c | 19 +++++++++- net/bridge/br_private.h | 4 ++ net/bridge/br_sysfs_br.c | 22 +++++++++++ 5 files changed, 113 insertions(+), 22 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 325d2601150d..92b2d4928bf1 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -276,6 +276,7 @@ enum { IFLA_BR_VLAN_STATS_ENABLED, IFLA_BR_MCAST_STATS_ENABLED, IFLA_BR_MCAST_IGMP_VERSION, + IFLA_BR_MCAST_MLD_VERSION, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 66192c11aa45..b30e77e8427c 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -459,15 +459,20 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, const struct in6_addr *grp, u8 *igmp_type) { - struct sk_buff *skb; + struct mld2_query *mld2q; + unsigned long interval; struct ipv6hdr *ip6h; struct mld_msg *mldq; + size_t mld_hdr_size; + struct sk_buff *skb; struct ethhdr *eth; u8 *hopopt; - unsigned long interval; + mld_hdr_size = sizeof(*mldq); + if (br->multicast_mld_version == 2) + mld_hdr_size = sizeof(*mld2q); skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*ip6h) + - 8 + sizeof(*mldq)); + 8 + mld_hdr_size); if (!skb) goto out; @@ -486,7 +491,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, ip6h = ipv6_hdr(skb); *(__force __be32 *)ip6h = htonl(0x60000000); - ip6h->payload_len = htons(8 + sizeof(*mldq)); + ip6h->payload_len = htons(8 + mld_hdr_size); ip6h->nexthdr = IPPROTO_HOPOPTS; ip6h->hop_limit = 1; ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1)); @@ -514,26 +519,47 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, /* ICMPv6 */ skb_set_transport_header(skb, skb->len); - mldq = (struct mld_msg *) icmp6_hdr(skb); - interval = ipv6_addr_any(grp) ? br->multicast_query_response_interval : br->multicast_last_member_interval; - *igmp_type = ICMPV6_MGM_QUERY; - mldq->mld_type = ICMPV6_MGM_QUERY; - mldq->mld_code = 0; - mldq->mld_cksum = 0; - mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval)); - mldq->mld_reserved = 0; - mldq->mld_mca = *grp; - - /* checksum */ - mldq->mld_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, - sizeof(*mldq), IPPROTO_ICMPV6, - csum_partial(mldq, - sizeof(*mldq), 0)); - skb_put(skb, sizeof(*mldq)); + switch (br->multicast_mld_version) { + case 1: + mldq = (struct mld_msg *)icmp6_hdr(skb); + mldq->mld_type = ICMPV6_MGM_QUERY; + mldq->mld_code = 0; + mldq->mld_cksum = 0; + mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval)); + mldq->mld_reserved = 0; + mldq->mld_mca = *grp; + mldq->mld_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, + sizeof(*mldq), IPPROTO_ICMPV6, + csum_partial(mldq, + sizeof(*mldq), + 0)); + break; + case 2: + mld2q = (struct mld2_query *)icmp6_hdr(skb); + mld2q->mld2q_mrc = ntohs((u16)jiffies_to_msecs(interval)); + mld2q->mld2q_type = ICMPV6_MGM_QUERY; + mld2q->mld2q_code = 0; + mld2q->mld2q_cksum = 0; + mld2q->mld2q_resv1 = 0; + mld2q->mld2q_resv2 = 0; + mld2q->mld2q_suppress = 0; + mld2q->mld2q_qrv = 2; + mld2q->mld2q_nsrcs = 0; + mld2q->mld2q_qqic = br->multicast_query_interval / HZ; + mld2q->mld2q_mca = *grp; + mld2q->mld2q_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, + sizeof(*mld2q), + IPPROTO_ICMPV6, + csum_partial(mld2q, + sizeof(*mld2q), + 0)); + break; + } + skb_put(skb, mld_hdr_size); __skb_pull(skb, sizeof(*eth)); @@ -1842,7 +1868,6 @@ void br_multicast_init(struct net_bridge *br) br->hash_elasticity = 4; br->hash_max = 512; - br->multicast_igmp_version = 2; br->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; br->multicast_querier = 0; br->multicast_query_use_ifaddr = 0; @@ -1858,7 +1883,9 @@ void br_multicast_init(struct net_bridge *br) br->ip4_other_query.delay_time = 0; br->ip4_querier.port = NULL; + br->multicast_igmp_version = 2; #if IS_ENABLED(CONFIG_IPV6) + br->multicast_mld_version = 1; br->ip6_other_query.delay_time = 0; br->ip6_querier.port = NULL; #endif @@ -2177,6 +2204,26 @@ int br_multicast_set_igmp_version(struct net_bridge *br, unsigned long val) return 0; } +#if IS_ENABLED(CONFIG_IPV6) +int br_multicast_set_mld_version(struct net_bridge *br, unsigned long val) +{ + /* Currently we support version 1 and 2 */ + switch (val) { + case 1: + case 2: + break; + default: + return -EINVAL; + } + + spin_lock_bh(&br->multicast_lock); + br->multicast_mld_version = val; + spin_unlock_bh(&br->multicast_lock); + + return 0; +} +#endif + /** * br_multicast_list_adjacent - Returns snooped multicast addresses * @dev: The bridge port adjacent to which to retrieve addresses diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 10b9b80f778f..71c7453268c1 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -859,6 +859,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_VLAN_STATS_ENABLED] = { .type = NLA_U8 }, [IFLA_BR_MCAST_STATS_ENABLED] = { .type = NLA_U8 }, [IFLA_BR_MCAST_IGMP_VERSION] = { .type = NLA_U8 }, + [IFLA_BR_MCAST_MLD_VERSION] = { .type = NLA_U8 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -1079,6 +1080,17 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (err) return err; } + +#if IS_ENABLED(CONFIG_IPV6) + if (data[IFLA_BR_MCAST_MLD_VERSION]) { + __u8 mld_version; + + mld_version = nla_get_u8(data[IFLA_BR_MCAST_MLD_VERSION]); + err = br_multicast_set_mld_version(br, mld_version); + if (err) + return err; + } +#endif #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (data[IFLA_BR_NF_CALL_IPTABLES]) { @@ -1146,6 +1158,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_RESPONSE_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_STARTUP_QUERY_INTVL */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_IGMP_VERSION */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_MLD_VERSION */ #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IPTABLES */ @@ -1225,7 +1238,11 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u8(skb, IFLA_BR_MCAST_IGMP_VERSION, br->multicast_igmp_version)) return -EMSGSIZE; - +#if IS_ENABLED(CONFIG_IPV6) + if (nla_put_u8(skb, IFLA_BR_MCAST_MLD_VERSION, + br->multicast_mld_version)) + return -EMSGSIZE; +#endif clockval = jiffies_to_clock_t(br->multicast_last_member_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_LAST_MEMBER_INTVL, clockval, IFLA_BR_PAD)) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 3d207d92d899..26aec2366bc3 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -355,6 +355,7 @@ struct net_bridge struct bridge_mcast_other_query ip6_other_query; struct bridge_mcast_own_query ip6_own_query; struct bridge_mcast_querier ip6_querier; + u8 multicast_mld_version; #endif /* IS_ENABLED(CONFIG_IPV6) */ #endif @@ -585,6 +586,9 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val); int br_multicast_set_querier(struct net_bridge *br, unsigned long val); int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val); int br_multicast_set_igmp_version(struct net_bridge *br, unsigned long val); +#if IS_ENABLED(CONFIG_IPV6) +int br_multicast_set_mld_version(struct net_bridge *br, unsigned long val); +#endif struct net_bridge_mdb_entry * br_mdb_ip_get(struct net_bridge_mdb_htable *mdb, struct br_ip *dst); struct net_bridge_mdb_entry * diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index f00d1690658c..c9d2e0abfb89 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -659,6 +659,25 @@ static ssize_t multicast_stats_enabled_store(struct device *d, return store_bridge_parm(d, buf, len, set_stats_enabled); } static DEVICE_ATTR_RW(multicast_stats_enabled); + +#if IS_ENABLED(CONFIG_IPV6) +static ssize_t multicast_mld_version_show(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + + return sprintf(buf, "%u\n", br->multicast_mld_version); +} + +static ssize_t multicast_mld_version_store(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, br_multicast_set_mld_version); +} +static DEVICE_ATTR_RW(multicast_mld_version); +#endif #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) static ssize_t nf_call_iptables_show( @@ -827,6 +846,9 @@ static struct attribute *bridge_attrs[] = { &dev_attr_multicast_startup_query_interval.attr, &dev_attr_multicast_stats_enabled.attr, &dev_attr_multicast_igmp_version.attr, +#if IS_ENABLED(CONFIG_IPV6) + &dev_attr_multicast_mld_version.attr, +#endif #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) &dev_attr_nf_call_iptables.attr, -- cgit v1.2.3 From e381322b0190c1253d347de3f28b5c37756fb651 Mon Sep 17 00:00:00 2001 From: David Lechner Date: Fri, 16 Sep 2016 14:16:48 -0500 Subject: leds: Introduce userspace LED class driver This driver creates a userspace leds driver similar to uinput. New LEDs are created by opening /dev/uleds and writing a uleds_user_dev struct. A new LED class device is registered with the name given in the struct. Reading will return a single byte that is the current brightness. The poll() syscall is also supported. It will be triggered whenever the brightness changes. Closing the file handle to /dev/uleds will remove the leds class device. Signed-off-by: David Lechner Signed-off-by: Jacek Anaszewski --- Documentation/leds/uleds.txt | 36 +++++++ drivers/leds/Kconfig | 8 ++ drivers/leds/Makefile | 3 + drivers/leds/uleds.c | 235 +++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/Kbuild | 1 + include/uapi/linux/uleds.h | 24 +++++ 6 files changed, 307 insertions(+) create mode 100644 Documentation/leds/uleds.txt create mode 100644 drivers/leds/uleds.c create mode 100644 include/uapi/linux/uleds.h (limited to 'include/uapi/linux') diff --git a/Documentation/leds/uleds.txt b/Documentation/leds/uleds.txt new file mode 100644 index 000000000000..13e375a580f9 --- /dev/null +++ b/Documentation/leds/uleds.txt @@ -0,0 +1,36 @@ +Userspace LEDs +============== + +The uleds driver supports userspace LEDs. This can be useful for testing +triggers and can also be used to implement virtual LEDs. + + +Usage +===== + +When the driver is loaded, a character device is created at /dev/uleds. To +create a new LED class device, open /dev/uleds and write a uleds_user_dev +structure to it (found in kernel public header file linux/uleds.h). + + #define LED_MAX_NAME_SIZE 64 + + struct uleds_user_dev { + char name[LED_MAX_NAME_SIZE]; + }; + +A new LED class device will be created with the name given. The name can be +any valid sysfs device node name, but consider using the LED class naming +convention of "devicename:color:function". + +The current brightness is found by reading a single byte from the character +device. Values are unsigned: 0 to 255. Reading will block until the brightness +changes. The device node can also be polled to notify when the brightness value +changes. + +The LED class device will be removed when the open file handle to /dev/uleds +is closed. + +Multiple LED class devices are created by opening additional file handles to +/dev/uleds. + +See tools/leds/uledmon.c for an example userspace program. diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index 7a628c6516f6..5fd3f4ca0c3c 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -659,6 +659,14 @@ config LEDS_MLXCPLD This option enabled support for the LEDs on the Mellanox boards. Say Y to enabled these. +config LEDS_USER + tristate "Userspace LED support" + depends on LEDS_CLASS + help + This option enables support for userspace LEDs. Say 'y' to enable this + support in kernel. To compile this driver as a module, choose 'm' here: + the module will be called uleds. + comment "LED Triggers" source "drivers/leds/trigger/Kconfig" diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile index 3965070190f5..d5331ff5b563 100644 --- a/drivers/leds/Makefile +++ b/drivers/leds/Makefile @@ -75,5 +75,8 @@ obj-$(CONFIG_LEDS_MLXCPLD) += leds-mlxcpld.o # LED SPI Drivers obj-$(CONFIG_LEDS_DAC124S085) += leds-dac124s085.o +# LED Userspace Drivers +obj-$(CONFIG_LEDS_USER) += uleds.o + # LED Triggers obj-$(CONFIG_LEDS_TRIGGERS) += trigger/ diff --git a/drivers/leds/uleds.c b/drivers/leds/uleds.c new file mode 100644 index 000000000000..5e9e8a1fdefb --- /dev/null +++ b/drivers/leds/uleds.c @@ -0,0 +1,235 @@ +/* + * Userspace driver for the LED subsystem + * + * Copyright (C) 2016 David Lechner + * + * Based on uinput.c: Aristeu Sergio Rozanski Filho + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#define ULEDS_NAME "uleds" + +enum uleds_state { + ULEDS_STATE_UNKNOWN, + ULEDS_STATE_REGISTERED, +}; + +struct uleds_device { + struct uleds_user_dev user_dev; + struct led_classdev led_cdev; + struct mutex mutex; + enum uleds_state state; + wait_queue_head_t waitq; + int brightness; + bool new_data; +}; + +static struct miscdevice uleds_misc; + +static void uleds_brightness_set(struct led_classdev *led_cdev, + enum led_brightness brightness) +{ + struct uleds_device *udev = container_of(led_cdev, struct uleds_device, + led_cdev); + + if (udev->brightness != brightness) { + udev->brightness = brightness; + udev->new_data = true; + wake_up_interruptible(&udev->waitq); + } +} + +static int uleds_open(struct inode *inode, struct file *file) +{ + struct uleds_device *udev; + + udev = kzalloc(sizeof(*udev), GFP_KERNEL); + if (!udev) + return -ENOMEM; + + udev->led_cdev.name = udev->user_dev.name; + udev->led_cdev.brightness_set = uleds_brightness_set; + + mutex_init(&udev->mutex); + init_waitqueue_head(&udev->waitq); + udev->state = ULEDS_STATE_UNKNOWN; + + file->private_data = udev; + nonseekable_open(inode, file); + + return 0; +} + +static ssize_t uleds_write(struct file *file, const char __user *buffer, + size_t count, loff_t *ppos) +{ + struct uleds_device *udev = file->private_data; + const char *name; + int ret; + + if (count == 0) + return 0; + + ret = mutex_lock_interruptible(&udev->mutex); + if (ret) + return ret; + + if (udev->state == ULEDS_STATE_REGISTERED) { + ret = -EBUSY; + goto out; + } + + if (count != sizeof(struct uleds_user_dev)) { + ret = -EINVAL; + goto out; + } + + if (copy_from_user(&udev->user_dev, buffer, + sizeof(struct uleds_user_dev))) { + ret = -EFAULT; + goto out; + } + + name = udev->user_dev.name; + if (!name[0] || !strcmp(name, ".") || !strcmp(name, "..") || + strchr(name, '/')) { + ret = -EINVAL; + goto out; + } + + if (udev->user_dev.max_brightness <= 0) { + ret = -EINVAL; + goto out; + } + udev->led_cdev.max_brightness = udev->user_dev.max_brightness; + + ret = devm_led_classdev_register(uleds_misc.this_device, + &udev->led_cdev); + if (ret < 0) + goto out; + + udev->new_data = true; + udev->state = ULEDS_STATE_REGISTERED; + ret = count; + +out: + mutex_unlock(&udev->mutex); + + return ret; +} + +static ssize_t uleds_read(struct file *file, char __user *buffer, size_t count, + loff_t *ppos) +{ + struct uleds_device *udev = file->private_data; + ssize_t retval; + + if (count < sizeof(udev->brightness)) + return 0; + + do { + retval = mutex_lock_interruptible(&udev->mutex); + if (retval) + return retval; + + if (udev->state != ULEDS_STATE_REGISTERED) { + retval = -ENODEV; + } else if (!udev->new_data && (file->f_flags & O_NONBLOCK)) { + retval = -EAGAIN; + } else if (udev->new_data) { + retval = copy_to_user(buffer, &udev->brightness, + sizeof(udev->brightness)); + udev->new_data = false; + retval = sizeof(udev->brightness); + } + + mutex_unlock(&udev->mutex); + + if (retval) + break; + + if (!(file->f_flags & O_NONBLOCK)) + retval = wait_event_interruptible(udev->waitq, + udev->new_data || + udev->state != ULEDS_STATE_REGISTERED); + } while (retval == 0); + + return retval; +} + +static unsigned int uleds_poll(struct file *file, poll_table *wait) +{ + struct uleds_device *udev = file->private_data; + + poll_wait(file, &udev->waitq, wait); + + if (udev->new_data) + return POLLIN | POLLRDNORM; + + return 0; +} + +static int uleds_release(struct inode *inode, struct file *file) +{ + struct uleds_device *udev = file->private_data; + + if (udev->state == ULEDS_STATE_REGISTERED) { + udev->state = ULEDS_STATE_UNKNOWN; + devm_led_classdev_unregister(uleds_misc.this_device, + &udev->led_cdev); + } + kfree(udev); + + return 0; +} + +static const struct file_operations uleds_fops = { + .owner = THIS_MODULE, + .open = uleds_open, + .release = uleds_release, + .read = uleds_read, + .write = uleds_write, + .poll = uleds_poll, + .llseek = no_llseek, +}; + +static struct miscdevice uleds_misc = { + .fops = &uleds_fops, + .minor = MISC_DYNAMIC_MINOR, + .name = ULEDS_NAME, +}; + +static int __init uleds_init(void) +{ + return misc_register(&uleds_misc); +} +module_init(uleds_init); + +static void __exit uleds_exit(void) +{ + misc_deregister(&uleds_misc); +} +module_exit(uleds_exit); + +MODULE_AUTHOR("David Lechner "); +MODULE_DESCRIPTION("Userspace driver for the LED subsystem"); +MODULE_LICENSE("GPL"); diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 6965d0909554..f196c539021e 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -425,6 +425,7 @@ header-y += udp.h header-y += uhid.h header-y += uinput.h header-y += uio.h +header-y += uleds.h header-y += ultrasound.h header-y += un.h header-y += unistd.h diff --git a/include/uapi/linux/uleds.h b/include/uapi/linux/uleds.h new file mode 100644 index 000000000000..95186578c46e --- /dev/null +++ b/include/uapi/linux/uleds.h @@ -0,0 +1,24 @@ +/* + * Userspace driver support for the LED subsystem + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ +#ifndef _UAPI__ULEDS_H_ +#define _UAPI__ULEDS_H_ + +#define LED_MAX_NAME_SIZE 64 + +struct uleds_user_dev { + char name[LED_MAX_NAME_SIZE]; + int max_brightness; +}; + +#endif /* _UAPI__ULEDS_H_ */ -- cgit v1.2.3 From 688834e6ae6b21e3d98b5cf2586aa4a9b515c3a0 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 18 Nov 2016 16:16:11 +1100 Subject: md/failfast: add failfast flag for md to be used by some personalities. This patch just adds a 'failfast' per-device flag which can be stored in v0.90 or v1.x metadata. The flag is not used yet but the intent is that it can be used for mirrored (raid1/raid10) arrays where low latency is more important than keeping all devices on-line. Setting the flag for a device effectively gives permission for that device to be marked as Faulty and excluded from the array on the first error. The underlying driver will be directed not to retry requests that result in failures. There is a proviso that the device must not be marked faulty if that would cause the array as a whole to fail, it may only be marked Faulty if the array remains functional, but is degraded. Failures on read requests will cause the device to be marked as Faulty immediately so that further reads will avoid that device. No attempt will be made to correct read errors by over-writing with the correct data. It is expected that if transient errors, such as cable unplug, are possible, then something in user-space will revalidate failed devices and re-add them when they appear to be working again. Signed-off-by: NeilBrown Signed-off-by: Shaohua Li --- drivers/md/md.c | 27 +++++++++++++++++++++++++++ drivers/md/md.h | 6 ++++++ include/uapi/linux/raid/md_p.h | 7 ++++++- 3 files changed, 39 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/md/md.c b/drivers/md/md.c index d3cef771e422..2cf0e89cc56c 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1164,6 +1164,8 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev) } if (desc->state & (1<flags); + if (desc->state & (1<flags); } else /* MULTIPATH are always insync */ set_bit(In_sync, &rdev->flags); return 0; @@ -1289,6 +1291,8 @@ static void super_90_sync(struct mddev *mddev, struct md_rdev *rdev) } if (test_bit(WriteMostly, &rdev2->flags)) d->state |= (1<flags)) + d->state |= (1<raid_disks ; i++) { @@ -1673,6 +1677,8 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) } if (sb->devflags & WriteMostly1) set_bit(WriteMostly, &rdev->flags); + if (sb->devflags & FailFast1) + set_bit(FailFast, &rdev->flags); if (le32_to_cpu(sb->feature_map) & MD_FEATURE_REPLACEMENT) set_bit(Replacement, &rdev->flags); } else /* MULTIPATH are always insync */ @@ -1711,6 +1717,10 @@ static void super_1_sync(struct mddev *mddev, struct md_rdev *rdev) sb->chunksize = cpu_to_le32(mddev->chunk_sectors); sb->level = cpu_to_le32(mddev->level); sb->layout = cpu_to_le32(mddev->layout); + if (test_bit(FailFast, &rdev->flags)) + sb->devflags |= FailFast1; + else + sb->devflags &= ~FailFast1; if (test_bit(WriteMostly, &rdev->flags)) sb->devflags |= WriteMostly1; @@ -2557,6 +2567,8 @@ state_show(struct md_rdev *rdev, char *page) len += sprintf(page+len, "replacement%s", sep); if (test_bit(ExternalBbl, &flags)) len += sprintf(page+len, "external_bbl%s", sep); + if (test_bit(FailFast, &flags)) + len += sprintf(page+len, "failfast%s", sep); if (len) len -= strlen(sep); @@ -2579,6 +2591,7 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) * so that it gets rebuilt based on bitmap * write_error - sets WriteErrorSeen * -write_error - clears WriteErrorSeen + * {,-}failfast - set/clear FailFast */ int err = -EINVAL; if (cmd_match(buf, "faulty") && rdev->mddev->pers) { @@ -2637,6 +2650,12 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) } else if (cmd_match(buf, "insync") && rdev->raid_disk == -1) { set_bit(In_sync, &rdev->flags); err = 0; + } else if (cmd_match(buf, "failfast")) { + set_bit(FailFast, &rdev->flags); + err = 0; + } else if (cmd_match(buf, "-failfast")) { + clear_bit(FailFast, &rdev->flags); + err = 0; } else if (cmd_match(buf, "-insync") && rdev->raid_disk >= 0 && !test_bit(Journal, &rdev->flags)) { if (rdev->mddev->pers == NULL) { @@ -5942,6 +5961,8 @@ static int get_disk_info(struct mddev *mddev, void __user * arg) info.state |= (1<flags)) info.state |= (1<flags)) + info.state |= (1<flags); else clear_bit(WriteMostly, &rdev->flags); + if (info->state & (1<flags); + else + clear_bit(FailFast, &rdev->flags); if (info->state & (1<state & (1<flags); + if (info->state & (1<flags); if (!mddev->persistent) { pr_debug("md: nonpersistent superblock ...\n"); diff --git a/drivers/md/md.h b/drivers/md/md.h index af6b33c30d2d..bc6712ef8c81 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -171,6 +171,12 @@ enum flag_bits { ExternalBbl, /* External metadata provides bad * block management for a disk */ + FailFast, /* Minimal retries should be attempted on + * this device, so use REQ_FAILFAST_DEV. + * Also don't try to repair failed reads. + * It is expects that no bad block log + * is present. + */ }; static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors, diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h index c3e654c6d518..9930f3e9040f 100644 --- a/include/uapi/linux/raid/md_p.h +++ b/include/uapi/linux/raid/md_p.h @@ -84,6 +84,10 @@ #define MD_DISK_CANDIDATE 5 /* disk is added as spare (local) until confirmed * For clustered enviroments only. */ +#define MD_DISK_FAILFAST 10 /* Send REQ_FAILFAST if there are multiple + * devices available - and don't try to + * correct read errors. + */ #define MD_DISK_WRITEMOSTLY 9 /* disk is "write-mostly" is RAID1 config. * read requests will only be sent here in @@ -265,8 +269,9 @@ struct mdp_superblock_1 { __le32 dev_number; /* permanent identifier of this device - not role in raid */ __le32 cnt_corrected_read; /* number of read errors that were corrected by re-writing */ __u8 device_uuid[16]; /* user-space setable, ignored by kernel */ - __u8 devflags; /* per-device flags. Only one defined...*/ + __u8 devflags; /* per-device flags. Only two defined...*/ #define WriteMostly1 1 /* mask for writemostly flag in above */ +#define FailFast1 2 /* Should avoid retries and fixups and just fail */ /* Bad block log. If there are any bad blocks the feature flag is set. * If offset and size are non-zero, that space is reserved and available */ -- cgit v1.2.3 From 9561a7ade0c205bc2ee035a2ac880478dcc1a024 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 22 Nov 2016 14:04:40 -0500 Subject: nbd: add multi-connection support NBD can become contended on its single connection. We have to serialize all writes and we can only process one read response at a time. Fix this by allowing userspace to provide multiple connections to a single nbd device. This coupled with block-mq drastically increases performance in multi-process cases. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Jens Axboe --- drivers/block/nbd.c | 382 +++++++++++++++++++++++++++++------------------ include/uapi/linux/nbd.h | 9 +- 2 files changed, 243 insertions(+), 148 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 807d24a2f1de..e683e2241cbd 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -41,26 +41,34 @@ #include +struct nbd_sock { + struct socket *sock; + struct mutex tx_lock; +}; + #define NBD_TIMEDOUT 0 #define NBD_DISCONNECT_REQUESTED 1 +#define NBD_DISCONNECTED 2 +#define NBD_RUNNING 3 struct nbd_device { u32 flags; unsigned long runtime_flags; - struct socket * sock; /* If == NULL, device is not ready, yet */ + struct nbd_sock **socks; int magic; struct blk_mq_tag_set tag_set; - struct mutex tx_lock; + struct mutex config_lock; struct gendisk *disk; + int num_connections; + atomic_t recv_threads; + wait_queue_head_t recv_wq; int blksize; loff_t bytesize; - /* protects initialization and shutdown of the socket */ - spinlock_t sock_lock; struct task_struct *task_recv; - struct task_struct *task_send; + struct task_struct *task_setup; #if IS_ENABLED(CONFIG_DEBUG_FS) struct dentry *dbg_dir; @@ -69,7 +77,7 @@ struct nbd_device { struct nbd_cmd { struct nbd_device *nbd; - struct list_head list; + struct completion send_complete; }; #if IS_ENABLED(CONFIG_DEBUG_FS) @@ -159,22 +167,20 @@ static void nbd_end_request(struct nbd_cmd *cmd) */ static void sock_shutdown(struct nbd_device *nbd) { - struct socket *sock; - - spin_lock(&nbd->sock_lock); + int i; - if (!nbd->sock) { - spin_unlock_irq(&nbd->sock_lock); + if (nbd->num_connections == 0) + return; + if (test_and_set_bit(NBD_DISCONNECTED, &nbd->runtime_flags)) return; - } - - sock = nbd->sock; - dev_warn(disk_to_dev(nbd->disk), "shutting down socket\n"); - nbd->sock = NULL; - spin_unlock(&nbd->sock_lock); - kernel_sock_shutdown(sock, SHUT_RDWR); - sockfd_put(sock); + for (i = 0; i < nbd->num_connections; i++) { + struct nbd_sock *nsock = nbd->socks[i]; + mutex_lock(&nsock->tx_lock); + kernel_sock_shutdown(nsock->sock, SHUT_RDWR); + mutex_unlock(&nsock->tx_lock); + } + dev_warn(disk_to_dev(nbd->disk), "shutting down sockets\n"); } static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, @@ -182,35 +188,31 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); struct nbd_device *nbd = cmd->nbd; - struct socket *sock = NULL; - - spin_lock(&nbd->sock_lock); + dev_err(nbd_to_dev(nbd), "Connection timed out, shutting down connection\n"); set_bit(NBD_TIMEDOUT, &nbd->runtime_flags); - - if (nbd->sock) { - sock = nbd->sock; - get_file(sock->file); - } - - spin_unlock(&nbd->sock_lock); - if (sock) { - kernel_sock_shutdown(sock, SHUT_RDWR); - sockfd_put(sock); - } - req->errors++; - dev_err(nbd_to_dev(nbd), "Connection timed out, shutting down connection\n"); + + /* + * If our disconnect packet times out then we're already holding the + * config_lock and could deadlock here, so just set an error and return, + * we'll handle shutting everything down later. + */ + if (req->cmd_type == REQ_TYPE_DRV_PRIV) + return BLK_EH_HANDLED; + mutex_lock(&nbd->config_lock); + sock_shutdown(nbd); + mutex_unlock(&nbd->config_lock); return BLK_EH_HANDLED; } /* * Send or receive packet. */ -static int sock_xmit(struct nbd_device *nbd, int send, void *buf, int size, - int msg_flags) +static int sock_xmit(struct nbd_device *nbd, int index, int send, void *buf, + int size, int msg_flags) { - struct socket *sock = nbd->sock; + struct socket *sock = nbd->socks[index]->sock; int result; struct msghdr msg; struct kvec iov; @@ -254,19 +256,19 @@ static int sock_xmit(struct nbd_device *nbd, int send, void *buf, int size, return result; } -static inline int sock_send_bvec(struct nbd_device *nbd, struct bio_vec *bvec, - int flags) +static inline int sock_send_bvec(struct nbd_device *nbd, int index, + struct bio_vec *bvec, int flags) { int result; void *kaddr = kmap(bvec->bv_page); - result = sock_xmit(nbd, 1, kaddr + bvec->bv_offset, + result = sock_xmit(nbd, index, 1, kaddr + bvec->bv_offset, bvec->bv_len, flags); kunmap(bvec->bv_page); return result; } /* always call with the tx_lock held */ -static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd) +static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) { struct request *req = blk_mq_rq_from_pdu(cmd); int result, flags; @@ -274,10 +276,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd) unsigned long size = blk_rq_bytes(req); struct bio *bio; u32 type; + u32 tag = blk_mq_unique_tag(req); - if (req->cmd_type == REQ_TYPE_DRV_PRIV) - type = NBD_CMD_DISC; - else if (req_op(req) == REQ_OP_DISCARD) + if (req_op(req) == REQ_OP_DISCARD) type = NBD_CMD_TRIM; else if (req_op(req) == REQ_OP_FLUSH) type = NBD_CMD_FLUSH; @@ -289,16 +290,16 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd) memset(&request, 0, sizeof(request)); request.magic = htonl(NBD_REQUEST_MAGIC); request.type = htonl(type); - if (type != NBD_CMD_FLUSH && type != NBD_CMD_DISC) { + if (type != NBD_CMD_FLUSH) { request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9); request.len = htonl(size); } - memcpy(request.handle, &req->tag, sizeof(req->tag)); + memcpy(request.handle, &tag, sizeof(tag)); dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n", cmd, nbdcmd_to_ascii(type), (unsigned long long)blk_rq_pos(req) << 9, blk_rq_bytes(req)); - result = sock_xmit(nbd, 1, &request, sizeof(request), + result = sock_xmit(nbd, index, 1, &request, sizeof(request), (type == NBD_CMD_WRITE) ? MSG_MORE : 0); if (result <= 0) { dev_err(disk_to_dev(nbd->disk), @@ -323,7 +324,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd) flags = MSG_MORE; dev_dbg(nbd_to_dev(nbd), "request %p: sending %d bytes data\n", cmd, bvec.bv_len); - result = sock_send_bvec(nbd, &bvec, flags); + result = sock_send_bvec(nbd, index, &bvec, flags); if (result <= 0) { dev_err(disk_to_dev(nbd->disk), "Send data failed (result %d)\n", @@ -344,31 +345,34 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd) return 0; } -static inline int sock_recv_bvec(struct nbd_device *nbd, struct bio_vec *bvec) +static inline int sock_recv_bvec(struct nbd_device *nbd, int index, + struct bio_vec *bvec) { int result; void *kaddr = kmap(bvec->bv_page); - result = sock_xmit(nbd, 0, kaddr + bvec->bv_offset, bvec->bv_len, - MSG_WAITALL); + result = sock_xmit(nbd, index, 0, kaddr + bvec->bv_offset, + bvec->bv_len, MSG_WAITALL); kunmap(bvec->bv_page); return result; } /* NULL returned = something went wrong, inform userspace */ -static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd) +static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) { int result; struct nbd_reply reply; struct nbd_cmd *cmd; struct request *req = NULL; u16 hwq; - int tag; + u32 tag; reply.magic = 0; - result = sock_xmit(nbd, 0, &reply, sizeof(reply), MSG_WAITALL); + result = sock_xmit(nbd, index, 0, &reply, sizeof(reply), MSG_WAITALL); if (result <= 0) { - dev_err(disk_to_dev(nbd->disk), - "Receive control failed (result %d)\n", result); + if (!test_bit(NBD_DISCONNECTED, &nbd->runtime_flags) && + !test_bit(NBD_DISCONNECT_REQUESTED, &nbd->runtime_flags)) + dev_err(disk_to_dev(nbd->disk), + "Receive control failed (result %d)\n", result); return ERR_PTR(result); } @@ -378,7 +382,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd) return ERR_PTR(-EPROTO); } - memcpy(&tag, reply.handle, sizeof(int)); + memcpy(&tag, reply.handle, sizeof(u32)); hwq = blk_mq_unique_tag_to_hwq(tag); if (hwq < nbd->tag_set.nr_hw_queues) @@ -390,7 +394,6 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd) return ERR_PTR(-ENOENT); } cmd = blk_mq_rq_to_pdu(req); - if (ntohl(reply.error)) { dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n", ntohl(reply.error)); @@ -404,7 +407,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd) struct bio_vec bvec; rq_for_each_segment(bvec, req, iter) { - result = sock_recv_bvec(nbd, &bvec); + result = sock_recv_bvec(nbd, index, &bvec); if (result <= 0) { dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n", result); @@ -414,6 +417,9 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd) dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n", cmd, bvec.bv_len); } + } else { + /* See the comment in nbd_queue_rq. */ + wait_for_completion(&cmd->send_complete); } return cmd; } @@ -432,25 +438,24 @@ static struct device_attribute pid_attr = { .show = pid_show, }; -static int nbd_thread_recv(struct nbd_device *nbd, struct block_device *bdev) +struct recv_thread_args { + struct work_struct work; + struct nbd_device *nbd; + int index; +}; + +static void recv_work(struct work_struct *work) { + struct recv_thread_args *args = container_of(work, + struct recv_thread_args, + work); + struct nbd_device *nbd = args->nbd; struct nbd_cmd *cmd; - int ret; + int ret = 0; BUG_ON(nbd->magic != NBD_MAGIC); - - sk_set_memalloc(nbd->sock->sk); - - ret = device_create_file(disk_to_dev(nbd->disk), &pid_attr); - if (ret) { - dev_err(disk_to_dev(nbd->disk), "device_create_file failed!\n"); - return ret; - } - - nbd_size_update(nbd, bdev); - while (1) { - cmd = nbd_read_stat(nbd); + cmd = nbd_read_stat(nbd, args->index); if (IS_ERR(cmd)) { ret = PTR_ERR(cmd); break; @@ -459,10 +464,14 @@ static int nbd_thread_recv(struct nbd_device *nbd, struct block_device *bdev) nbd_end_request(cmd); } - nbd_size_clear(nbd, bdev); - - device_remove_file(disk_to_dev(nbd->disk), &pid_attr); - return ret; + /* + * We got an error, shut everybody down if this wasn't the result of a + * disconnect request. + */ + if (ret && !test_bit(NBD_DISCONNECT_REQUESTED, &nbd->runtime_flags)) + sock_shutdown(nbd); + atomic_dec(&nbd->recv_threads); + wake_up(&nbd->recv_wq); } static void nbd_clear_req(struct request *req, void *data, bool reserved) @@ -480,26 +489,35 @@ static void nbd_clear_que(struct nbd_device *nbd) { BUG_ON(nbd->magic != NBD_MAGIC); - /* - * Because we have set nbd->sock to NULL under the tx_lock, all - * modifications to the list must have completed by now. - */ - BUG_ON(nbd->sock); - blk_mq_tagset_busy_iter(&nbd->tag_set, nbd_clear_req, NULL); dev_dbg(disk_to_dev(nbd->disk), "queue cleared\n"); } -static void nbd_handle_cmd(struct nbd_cmd *cmd) +static void nbd_handle_cmd(struct nbd_cmd *cmd, int index) { struct request *req = blk_mq_rq_from_pdu(cmd); struct nbd_device *nbd = cmd->nbd; + struct nbd_sock *nsock; + + if (index >= nbd->num_connections) { + dev_err(disk_to_dev(nbd->disk), + "Attempted send on invalid socket\n"); + goto error_out; + } + + if (test_bit(NBD_DISCONNECTED, &nbd->runtime_flags)) { + dev_err(disk_to_dev(nbd->disk), + "Attempted send on closed socket\n"); + goto error_out; + } - if (req->cmd_type != REQ_TYPE_FS) + if (req->cmd_type != REQ_TYPE_FS && + req->cmd_type != REQ_TYPE_DRV_PRIV) goto error_out; - if (rq_data_dir(req) == WRITE && + if (req->cmd_type == REQ_TYPE_FS && + rq_data_dir(req) == WRITE && (nbd->flags & NBD_FLAG_READ_ONLY)) { dev_err(disk_to_dev(nbd->disk), "Write on read-only\n"); @@ -508,23 +526,22 @@ static void nbd_handle_cmd(struct nbd_cmd *cmd) req->errors = 0; - mutex_lock(&nbd->tx_lock); - nbd->task_send = current; - if (unlikely(!nbd->sock)) { - mutex_unlock(&nbd->tx_lock); + nsock = nbd->socks[index]; + mutex_lock(&nsock->tx_lock); + if (unlikely(!nsock->sock)) { + mutex_unlock(&nsock->tx_lock); dev_err(disk_to_dev(nbd->disk), "Attempted send on closed socket\n"); goto error_out; } - if (nbd_send_cmd(nbd, cmd) != 0) { + if (nbd_send_cmd(nbd, cmd, index) != 0) { dev_err(disk_to_dev(nbd->disk), "Request send failed\n"); req->errors++; nbd_end_request(cmd); } - nbd->task_send = NULL; - mutex_unlock(&nbd->tx_lock); + mutex_unlock(&nsock->tx_lock); return; @@ -538,39 +555,70 @@ static int nbd_queue_rq(struct blk_mq_hw_ctx *hctx, { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(bd->rq); + /* + * Since we look at the bio's to send the request over the network we + * need to make sure the completion work doesn't mark this request done + * before we are done doing our send. This keeps us from dereferencing + * freed data if we have particularly fast completions (ie we get the + * completion before we exit sock_xmit on the last bvec) or in the case + * that the server is misbehaving (or there was an error) before we're + * done sending everything over the wire. + */ + init_completion(&cmd->send_complete); blk_mq_start_request(bd->rq); - nbd_handle_cmd(cmd); + nbd_handle_cmd(cmd, hctx->queue_num); + complete(&cmd->send_complete); + return BLK_MQ_RQ_QUEUE_OK; } -static int nbd_set_socket(struct nbd_device *nbd, struct socket *sock) +static int nbd_add_socket(struct nbd_device *nbd, struct socket *sock) { - int ret = 0; - - spin_lock_irq(&nbd->sock_lock); + struct nbd_sock **socks; + struct nbd_sock *nsock; - if (nbd->sock) { - ret = -EBUSY; - goto out; + if (!nbd->task_setup) + nbd->task_setup = current; + if (nbd->task_setup != current) { + dev_err(disk_to_dev(nbd->disk), + "Device being setup by another task"); + return -EINVAL; } - nbd->sock = sock; + socks = krealloc(nbd->socks, (nbd->num_connections + 1) * + sizeof(struct nbd_sock *), GFP_KERNEL); + if (!socks) + return -ENOMEM; + nsock = kzalloc(sizeof(struct nbd_sock), GFP_KERNEL); + if (!nsock) + return -ENOMEM; -out: - spin_unlock_irq(&nbd->sock_lock); + nbd->socks = socks; - return ret; + mutex_init(&nsock->tx_lock); + nsock->sock = sock; + socks[nbd->num_connections++] = nsock; + + return 0; } /* Reset all properties of an NBD device */ static void nbd_reset(struct nbd_device *nbd) { + int i; + + for (i = 0; i < nbd->num_connections; i++) + kfree(nbd->socks[i]); + kfree(nbd->socks); + nbd->socks = NULL; nbd->runtime_flags = 0; nbd->blksize = 1024; nbd->bytesize = 0; set_capacity(nbd->disk, 0); nbd->flags = 0; nbd->tag_set.timeout = 0; + nbd->num_connections = 0; + nbd->task_setup = NULL; queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue); } @@ -596,48 +644,67 @@ static void nbd_parse_flags(struct nbd_device *nbd, struct block_device *bdev) blk_queue_write_cache(nbd->disk->queue, false, false); } +static void send_disconnects(struct nbd_device *nbd) +{ + struct nbd_request request = {}; + int i, ret; + + request.magic = htonl(NBD_REQUEST_MAGIC); + request.type = htonl(NBD_CMD_DISC); + + for (i = 0; i < nbd->num_connections; i++) { + ret = sock_xmit(nbd, i, 1, &request, sizeof(request), 0); + if (ret <= 0) + dev_err(disk_to_dev(nbd->disk), + "Send disconnect failed %d\n", ret); + } +} + static int nbd_dev_dbg_init(struct nbd_device *nbd); static void nbd_dev_dbg_close(struct nbd_device *nbd); -/* Must be called with tx_lock held */ - +/* Must be called with config_lock held */ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, unsigned int cmd, unsigned long arg) { switch (cmd) { case NBD_DISCONNECT: { - struct request *sreq; - dev_info(disk_to_dev(nbd->disk), "NBD_DISCONNECT\n"); - if (!nbd->sock) + if (!nbd->socks) return -EINVAL; - sreq = blk_mq_alloc_request(bdev_get_queue(bdev), WRITE, 0); - if (!sreq) - return -ENOMEM; - - mutex_unlock(&nbd->tx_lock); + mutex_unlock(&nbd->config_lock); fsync_bdev(bdev); - mutex_lock(&nbd->tx_lock); - sreq->cmd_type = REQ_TYPE_DRV_PRIV; + mutex_lock(&nbd->config_lock); /* Check again after getting mutex back. */ - if (!nbd->sock) { - blk_mq_free_request(sreq); + if (!nbd->socks) return -EINVAL; - } - set_bit(NBD_DISCONNECT_REQUESTED, &nbd->runtime_flags); - - nbd_send_cmd(nbd, blk_mq_rq_to_pdu(sreq)); - blk_mq_free_request(sreq); + if (!test_and_set_bit(NBD_DISCONNECT_REQUESTED, + &nbd->runtime_flags)) + send_disconnects(nbd); return 0; } - + case NBD_CLEAR_SOCK: sock_shutdown(nbd); nbd_clear_que(nbd); kill_bdev(bdev); + nbd_bdev_reset(bdev); + /* + * We want to give the run thread a chance to wait for everybody + * to clean up and then do it's own cleanup. + */ + if (!test_bit(NBD_RUNNING, &nbd->runtime_flags)) { + int i; + + for (i = 0; i < nbd->num_connections; i++) + kfree(nbd->socks[i]); + kfree(nbd->socks); + nbd->socks = NULL; + nbd->num_connections = 0; + } return 0; case NBD_SET_SOCK: { @@ -647,7 +714,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, if (!sock) return err; - err = nbd_set_socket(nbd, sock); + err = nbd_add_socket(nbd, sock); if (!err && max_part) bdev->bd_invalidated = 1; @@ -676,26 +743,58 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, return 0; case NBD_DO_IT: { - int error; + struct recv_thread_args *args; + int num_connections = nbd->num_connections; + int error, i; if (nbd->task_recv) return -EBUSY; - if (!nbd->sock) + if (!nbd->socks) return -EINVAL; + if (num_connections > 1 && + !(nbd->flags & NBD_FLAG_CAN_MULTI_CONN)) { + dev_err(disk_to_dev(nbd->disk), "server does not support multiple connections per device.\n"); + goto out_err; + } - /* We have to claim the device under the lock */ + set_bit(NBD_RUNNING, &nbd->runtime_flags); + blk_mq_update_nr_hw_queues(&nbd->tag_set, nbd->num_connections); + args = kcalloc(num_connections, sizeof(*args), GFP_KERNEL); + if (!args) + goto out_err; nbd->task_recv = current; - mutex_unlock(&nbd->tx_lock); + mutex_unlock(&nbd->config_lock); nbd_parse_flags(nbd, bdev); + error = device_create_file(disk_to_dev(nbd->disk), &pid_attr); + if (error) { + dev_err(disk_to_dev(nbd->disk), "device_create_file failed!\n"); + goto out_recv; + } + + nbd_size_update(nbd, bdev); + nbd_dev_dbg_init(nbd); - error = nbd_thread_recv(nbd, bdev); + for (i = 0; i < num_connections; i++) { + sk_set_memalloc(nbd->socks[i]->sock->sk); + atomic_inc(&nbd->recv_threads); + INIT_WORK(&args[i].work, recv_work); + args[i].nbd = nbd; + args[i].index = i; + queue_work(system_long_wq, &args[i].work); + } + wait_event_interruptible(nbd->recv_wq, + atomic_read(&nbd->recv_threads) == 0); + for (i = 0; i < num_connections; i++) + flush_work(&args[i].work); nbd_dev_dbg_close(nbd); - - mutex_lock(&nbd->tx_lock); + nbd_size_clear(nbd, bdev); + device_remove_file(disk_to_dev(nbd->disk), &pid_attr); +out_recv: + mutex_lock(&nbd->config_lock); nbd->task_recv = NULL; - +out_err: sock_shutdown(nbd); nbd_clear_que(nbd); kill_bdev(bdev); @@ -708,7 +807,6 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, error = -ETIMEDOUT; nbd_reset(nbd); - return error; } @@ -740,9 +838,9 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode, BUG_ON(nbd->magic != NBD_MAGIC); - mutex_lock(&nbd->tx_lock); + mutex_lock(&nbd->config_lock); error = __nbd_ioctl(bdev, nbd, cmd, arg); - mutex_unlock(&nbd->tx_lock); + mutex_unlock(&nbd->config_lock); return error; } @@ -762,8 +860,6 @@ static int nbd_dbg_tasks_show(struct seq_file *s, void *unused) if (nbd->task_recv) seq_printf(s, "recv: %d\n", task_pid_nr(nbd->task_recv)); - if (nbd->task_send) - seq_printf(s, "send: %d\n", task_pid_nr(nbd->task_send)); return 0; } @@ -887,9 +983,7 @@ static int nbd_init_request(void *data, struct request *rq, unsigned int numa_node) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(rq); - cmd->nbd = data; - INIT_LIST_HEAD(&cmd->list); return 0; } @@ -999,13 +1093,13 @@ static int __init nbd_init(void) for (i = 0; i < nbds_max; i++) { struct gendisk *disk = nbd_dev[i].disk; nbd_dev[i].magic = NBD_MAGIC; - spin_lock_init(&nbd_dev[i].sock_lock); - mutex_init(&nbd_dev[i].tx_lock); + mutex_init(&nbd_dev[i].config_lock); disk->major = NBD_MAJOR; disk->first_minor = i << part_shift; disk->fops = &nbd_fops; disk->private_data = &nbd_dev[i]; sprintf(disk->disk_name, "nbd%d", i); + init_waitqueue_head(&nbd_dev[i].recv_wq); nbd_reset(&nbd_dev[i]); add_disk(disk); } diff --git a/include/uapi/linux/nbd.h b/include/uapi/linux/nbd.h index e08e413d5f71..f063cff178c5 100644 --- a/include/uapi/linux/nbd.h +++ b/include/uapi/linux/nbd.h @@ -38,11 +38,12 @@ enum { }; /* values for flags field */ -#define NBD_FLAG_HAS_FLAGS (1 << 0) /* nbd-server supports flags */ -#define NBD_FLAG_READ_ONLY (1 << 1) /* device is read-only */ -#define NBD_FLAG_SEND_FLUSH (1 << 2) /* can flush writeback cache */ +#define NBD_FLAG_HAS_FLAGS (1 << 0) /* nbd-server supports flags */ +#define NBD_FLAG_READ_ONLY (1 << 1) /* device is read-only */ +#define NBD_FLAG_SEND_FLUSH (1 << 2) /* can flush writeback cache */ /* there is a gap here to match userspace */ -#define NBD_FLAG_SEND_TRIM (1 << 5) /* send trim/discard */ +#define NBD_FLAG_SEND_TRIM (1 << 5) /* send trim/discard */ +#define NBD_FLAG_CAN_MULTI_CONN (1 << 7) /* Server supports multiple connections per export. */ /* userspace doesn't need the nbd_device structure */ -- cgit v1.2.3 From 63db89eaf0b9bf856c5e079ed5eab5c3f13165c8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 22 Nov 2016 13:09:50 -0700 Subject: nbd: move multi-connection bit to unused value Bit #7 is already used, move to bit #8 which is the first unused one. Fixes: 9561a7ade0c2 ("nbd: add multi-connection support") Signed-off-by: Jens Axboe --- include/uapi/linux/nbd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nbd.h b/include/uapi/linux/nbd.h index f063cff178c5..c91c642ea900 100644 --- a/include/uapi/linux/nbd.h +++ b/include/uapi/linux/nbd.h @@ -43,7 +43,7 @@ enum { #define NBD_FLAG_SEND_FLUSH (1 << 2) /* can flush writeback cache */ /* there is a gap here to match userspace */ #define NBD_FLAG_SEND_TRIM (1 << 5) /* send trim/discard */ -#define NBD_FLAG_CAN_MULTI_CONN (1 << 7) /* Server supports multiple connections per export. */ +#define NBD_FLAG_CAN_MULTI_CONN (1 << 8) /* Server supports multiple connections per export. */ /* userspace doesn't need the nbd_device structure */ -- cgit v1.2.3 From b9a4b13c770a84599dc706b78cd70ad5761fc30b Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Mon, 27 Jun 2016 10:46:16 -0300 Subject: [media] v4l: Add 16-bit raw bayer pixel formats The formats added by this patch are: V4L2_PIX_FMT_SBGGR16 V4L2_PIX_FMT_SGBRG16 V4L2_PIX_FMT_SGRBG16 V4L2_PIX_FMT_SRGGB16 already existed before the patch. Rework the documentation to match that of the other sample depths. Also align the description of V4L2_PIX_FMT_SRGGB16 to match with other similar formats. Signed-off-by: Sakari Ailus Acked-by: Lad, Prabhakar Signed-off-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/v4l/pixfmt-rgb.rst | 2 +- Documentation/media/uapi/v4l/pixfmt-sbggr16.rst | 62 ---------------------- Documentation/media/uapi/v4l/pixfmt-srggb16.rst | 69 +++++++++++++++++++++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 5 +- include/uapi/linux/videodev2.h | 3 ++ 5 files changed, 77 insertions(+), 64 deletions(-) delete mode 100644 Documentation/media/uapi/v4l/pixfmt-sbggr16.rst create mode 100644 Documentation/media/uapi/v4l/pixfmt-srggb16.rst (limited to 'include/uapi/linux') diff --git a/Documentation/media/uapi/v4l/pixfmt-rgb.rst b/Documentation/media/uapi/v4l/pixfmt-rgb.rst index 9cc980882e80..b0f35136021e 100644 --- a/Documentation/media/uapi/v4l/pixfmt-rgb.rst +++ b/Documentation/media/uapi/v4l/pixfmt-rgb.rst @@ -12,9 +12,9 @@ RGB Formats pixfmt-packed-rgb pixfmt-srggb8 - pixfmt-sbggr16 pixfmt-srggb10 pixfmt-srggb10p pixfmt-srggb10alaw8 pixfmt-srggb10dpcm8 pixfmt-srggb12 + pixfmt-srggb16 diff --git a/Documentation/media/uapi/v4l/pixfmt-sbggr16.rst b/Documentation/media/uapi/v4l/pixfmt-sbggr16.rst deleted file mode 100644 index 6f7f327db85c..000000000000 --- a/Documentation/media/uapi/v4l/pixfmt-sbggr16.rst +++ /dev/null @@ -1,62 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. _V4L2-PIX-FMT-SBGGR16: - -***************************** -V4L2_PIX_FMT_SBGGR16 ('BYR2') -***************************** - -Bayer RGB format - - -Description -=========== - -This format is similar to -:ref:`V4L2_PIX_FMT_SBGGR8 `, except each pixel -has a depth of 16 bits. The least significant byte is stored at lower -memory addresses (little-endian). - -**Byte Order.** -Each cell is one byte. - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - * - start + 0: - - B\ :sub:`00low` - - B\ :sub:`00high` - - G\ :sub:`01low` - - G\ :sub:`01high` - - B\ :sub:`02low` - - B\ :sub:`02high` - - G\ :sub:`03low` - - G\ :sub:`03high` - * - start + 8: - - G\ :sub:`10low` - - G\ :sub:`10high` - - R\ :sub:`11low` - - R\ :sub:`11high` - - G\ :sub:`12low` - - G\ :sub:`12high` - - R\ :sub:`13low` - - R\ :sub:`13high` - * - start + 16: - - B\ :sub:`20low` - - B\ :sub:`20high` - - G\ :sub:`21low` - - G\ :sub:`21high` - - B\ :sub:`22low` - - B\ :sub:`22high` - - G\ :sub:`23low` - - G\ :sub:`23high` - * - start + 24: - - G\ :sub:`30low` - - G\ :sub:`30high` - - R\ :sub:`31low` - - R\ :sub:`31high` - - G\ :sub:`32low` - - G\ :sub:`32high` - - R\ :sub:`33low` - - R\ :sub:`33high` diff --git a/Documentation/media/uapi/v4l/pixfmt-srggb16.rst b/Documentation/media/uapi/v4l/pixfmt-srggb16.rst new file mode 100644 index 000000000000..06facc9cd539 --- /dev/null +++ b/Documentation/media/uapi/v4l/pixfmt-srggb16.rst @@ -0,0 +1,69 @@ +.. -*- coding: utf-8; mode: rst -*- + +.. _V4L2-PIX-FMT-SRGGB16: +.. _v4l2-pix-fmt-sbggr16: +.. _v4l2-pix-fmt-sgbrg16: +.. _v4l2-pix-fmt-sgrbg16: + + +*************************************************************************************************************************** +V4L2_PIX_FMT_SRGGB16 ('RG16'), V4L2_PIX_FMT_SGRBG16 ('GR16'), V4L2_PIX_FMT_SGBRG16 ('GB16'), V4L2_PIX_FMT_SBGGR16 ('BYR2'), +*************************************************************************************************************************** + + +16-bit Bayer formats + + +Description +=========== + +These four pixel formats are raw sRGB / Bayer formats with 16 bits per +sample. Each sample is stored in a 16-bit word. Each n-pixel row contains +n/2 green samples and n/2 blue or red samples, with alternating red and blue +rows. Bytes are stored in memory in little endian order. They are +conventionally described as GRGR... BGBG..., RGRG... GBGB..., etc. Below is +an example of one of these formats: + +**Byte Order.** +Each cell is one byte. + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + + * - start + 0: + - B\ :sub:`00low` + - B\ :sub:`00high` + - G\ :sub:`01low` + - G\ :sub:`01high` + - B\ :sub:`02low` + - B\ :sub:`02high` + - G\ :sub:`03low` + - G\ :sub:`03high` + * - start + 8: + - G\ :sub:`10low` + - G\ :sub:`10high` + - R\ :sub:`11low` + - R\ :sub:`11high` + - G\ :sub:`12low` + - G\ :sub:`12high` + - R\ :sub:`13low` + - R\ :sub:`13high` + * - start + 16: + - B\ :sub:`20low` + - B\ :sub:`20high` + - G\ :sub:`21low` + - G\ :sub:`21high` + - B\ :sub:`22low` + - B\ :sub:`22high` + - G\ :sub:`23low` + - G\ :sub:`23high` + * - start + 24: + - G\ :sub:`30low` + - G\ :sub:`30high` + - R\ :sub:`31low` + - R\ :sub:`31high` + - G\ :sub:`32low` + - G\ :sub:`32high` + - R\ :sub:`33low` + - R\ :sub:`33high` diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 181381d1dc77..61d2d65318c5 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1191,7 +1191,10 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_SGBRG10DPCM8: descr = "8-bit Bayer GBGB/RGRG (DPCM)"; break; case V4L2_PIX_FMT_SGRBG10DPCM8: descr = "8-bit Bayer GRGR/BGBG (DPCM)"; break; case V4L2_PIX_FMT_SRGGB10DPCM8: descr = "8-bit Bayer RGRG/GBGB (DPCM)"; break; - case V4L2_PIX_FMT_SBGGR16: descr = "16-bit Bayer BGBG/GRGR (Exp.)"; break; + case V4L2_PIX_FMT_SBGGR16: descr = "16-bit Bayer BGBG/GRGR"; break; + case V4L2_PIX_FMT_SGBRG16: descr = "16-bit Bayer GBGB/RGRG"; break; + case V4L2_PIX_FMT_SGRBG16: descr = "16-bit Bayer GRGR/BGBG"; break; + case V4L2_PIX_FMT_SRGGB16: descr = "16-bit Bayer RGRG/GBGB"; break; case V4L2_PIX_FMT_SN9C20X_I420: descr = "GSPCA SN9C20X I420"; break; case V4L2_PIX_FMT_SPCA501: descr = "GSPCA SPCA501"; break; case V4L2_PIX_FMT_SPCA505: descr = "GSPCA SPCA505"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index d3f613e2c54a..46e8a2e369f9 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -605,6 +605,9 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_SGRBG12 v4l2_fourcc('B', 'A', '1', '2') /* 12 GRGR.. BGBG.. */ #define V4L2_PIX_FMT_SRGGB12 v4l2_fourcc('R', 'G', '1', '2') /* 12 RGRG.. GBGB.. */ #define V4L2_PIX_FMT_SBGGR16 v4l2_fourcc('B', 'Y', 'R', '2') /* 16 BGBG.. GRGR.. */ +#define V4L2_PIX_FMT_SGBRG16 v4l2_fourcc('G', 'B', '1', '6') /* 16 GBGB.. RGRG.. */ +#define V4L2_PIX_FMT_SGRBG16 v4l2_fourcc('G', 'R', '1', '6') /* 16 GRGR.. BGBG.. */ +#define V4L2_PIX_FMT_SRGGB16 v4l2_fourcc('R', 'G', '1', '6') /* 16 RGRG.. GBGB.. */ /* HSV formats */ #define V4L2_PIX_FMT_HSV24 v4l2_fourcc('H', 'S', 'V', '3') -- cgit v1.2.3 From a91d5df2b44a0c9b171ac47a48e02e762c8224e9 Mon Sep 17 00:00:00 2001 From: David Gibson Date: Wed, 23 Nov 2016 16:14:06 +1100 Subject: KVM: PPC: Move KVM_PPC_PVINFO_FLAGS_EV_IDLE definition next to its structure The KVM_PPC_PVINFO_FLAGS_EV_IDLE macro defines a bit for use in the flags field of struct kvm_ppc_pvinfo. However, changes since that was introduced have moved it away from that structure definition, which is confusing. Move it back next to the structure it belongs with. Signed-off-by: David Gibson Signed-off-by: Paul Mackerras --- include/uapi/linux/kvm.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 300ef255d1e0..e9f5ceffd741 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -651,6 +651,9 @@ struct kvm_enable_cap { }; /* for KVM_PPC_GET_PVINFO */ + +#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) + struct kvm_ppc_pvinfo { /* out */ __u32 flags; @@ -682,8 +685,6 @@ struct kvm_ppc_smmu_info { struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; }; -#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) - #define KVMIO 0xAE /* machine type bits, to be used as argument to KVM_CREATE_VM */ -- cgit v1.2.3 From 59bfde01fab0c4550778cd53e8d266f1dfddf7b7 Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Tue, 22 Nov 2016 23:09:57 +0200 Subject: devlink: Add E-Switch inline mode control Some HWs need the VF driver to put part of the packet headers on the TX descriptor so the e-switch can do proper matching and steering. The supported modes: none, link, network, transport. Signed-off-by: Roi Dayan Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/net/devlink.h | 2 ++ include/uapi/linux/devlink.h | 8 +++++ net/core/devlink.c | 70 ++++++++++++++++++++++++++++++++------------ 3 files changed, 61 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/devlink.h b/include/net/devlink.h index 211bd3c37028..d29e5fc82582 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -92,6 +92,8 @@ struct devlink_ops { int (*eswitch_mode_get)(struct devlink *devlink, u16 *p_mode); int (*eswitch_mode_set)(struct devlink *devlink, u16 mode); + int (*eswitch_inline_mode_get)(struct devlink *devlink, u8 *p_inline_mode); + int (*eswitch_inline_mode_set)(struct devlink *devlink, u8 inline_mode); }; static inline void *devlink_priv(struct devlink *devlink) diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 915bfa74458c..9014c33d4e77 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -102,6 +102,13 @@ enum devlink_eswitch_mode { DEVLINK_ESWITCH_MODE_SWITCHDEV, }; +enum devlink_eswitch_inline_mode { + DEVLINK_ESWITCH_INLINE_MODE_NONE, + DEVLINK_ESWITCH_INLINE_MODE_LINK, + DEVLINK_ESWITCH_INLINE_MODE_NETWORK, + DEVLINK_ESWITCH_INLINE_MODE_TRANSPORT, +}; + enum devlink_attr { /* don't change the order or add anything between, this is ABI! */ DEVLINK_ATTR_UNSPEC, @@ -133,6 +140,7 @@ enum devlink_attr { DEVLINK_ATTR_SB_OCC_CUR, /* u32 */ DEVLINK_ATTR_SB_OCC_MAX, /* u32 */ DEVLINK_ATTR_ESWITCH_MODE, /* u16 */ + DEVLINK_ATTR_ESWITCH_INLINE_MODE, /* u8 */ /* add new attributes above here, update the policy in devlink.c */ diff --git a/net/core/devlink.c b/net/core/devlink.c index c14f8b661db9..2b5bf9efa720 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1394,26 +1394,45 @@ static int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb, static int devlink_eswitch_fill(struct sk_buff *msg, struct devlink *devlink, enum devlink_command cmd, u32 portid, - u32 seq, int flags, u16 mode) + u32 seq, int flags) { + const struct devlink_ops *ops = devlink->ops; void *hdr; + int err = 0; + u16 mode; + u8 inline_mode; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; + err = devlink_nl_put_handle(msg, devlink); + if (err) + goto out; - if (nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode)) - goto nla_put_failure; + err = ops->eswitch_mode_get(devlink, &mode); + if (err) + goto out; + err = nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode); + if (err) + goto out; + + if (ops->eswitch_inline_mode_get) { + err = ops->eswitch_inline_mode_get(devlink, &inline_mode); + if (err) + goto out; + err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_INLINE_MODE, + inline_mode); + if (err) + goto out; + } genlmsg_end(msg, hdr); return 0; -nla_put_failure: +out: genlmsg_cancel(msg, hdr); - return -EMSGSIZE; + return err; } static int devlink_nl_cmd_eswitch_mode_get_doit(struct sk_buff *skb, @@ -1422,22 +1441,17 @@ static int devlink_nl_cmd_eswitch_mode_get_doit(struct sk_buff *skb, struct devlink *devlink = info->user_ptr[0]; const struct devlink_ops *ops = devlink->ops; struct sk_buff *msg; - u16 mode; int err; if (!ops || !ops->eswitch_mode_get) return -EOPNOTSUPP; - err = ops->eswitch_mode_get(devlink, &mode); - if (err) - return err; - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_MODE_GET, - info->snd_portid, info->snd_seq, 0, mode); + info->snd_portid, info->snd_seq, 0); if (err) { nlmsg_free(msg); @@ -1453,15 +1467,32 @@ static int devlink_nl_cmd_eswitch_mode_set_doit(struct sk_buff *skb, struct devlink *devlink = info->user_ptr[0]; const struct devlink_ops *ops = devlink->ops; u16 mode; + u8 inline_mode; + int err = 0; - if (!info->attrs[DEVLINK_ATTR_ESWITCH_MODE]) - return -EINVAL; + if (!ops) + return -EOPNOTSUPP; - mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]); + if (info->attrs[DEVLINK_ATTR_ESWITCH_MODE]) { + if (!ops->eswitch_mode_set) + return -EOPNOTSUPP; + mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]); + err = ops->eswitch_mode_set(devlink, mode); + if (err) + return err; + } - if (ops && ops->eswitch_mode_set) - return ops->eswitch_mode_set(devlink, mode); - return -EOPNOTSUPP; + if (info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]) { + if (!ops->eswitch_inline_mode_set) + return -EOPNOTSUPP; + inline_mode = nla_get_u8( + info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]); + err = ops->eswitch_inline_mode_set(devlink, inline_mode); + if (err) + return err; + } + + return 0; } static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { @@ -1478,6 +1509,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 }, [DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 }, [DEVLINK_ATTR_ESWITCH_MODE] = { .type = NLA_U16 }, + [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 }, }; static const struct genl_ops devlink_nl_ops[] = { -- cgit v1.2.3 From 0e33661de493db325435d565a4a722120ae4cbf3 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Wed, 23 Nov 2016 16:52:25 +0100 Subject: bpf: add new prog type for cgroup socket filtering This program type is similar to BPF_PROG_TYPE_SOCKET_FILTER, except that it does not allow BPF_LD_[ABS|IND] instructions and hooks up the bpf_skb_load_bytes() helper. Programs of this type will be attached to cgroups for network filtering and accounting. Signed-off-by: Daniel Mack Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 9 +++++++++ net/core/filter.c | 23 +++++++++++++++++++++++ 2 files changed, 32 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7d9b2832c280..5ae679fac993 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -98,8 +98,17 @@ enum bpf_prog_type { BPF_PROG_TYPE_TRACEPOINT, BPF_PROG_TYPE_XDP, BPF_PROG_TYPE_PERF_EVENT, + BPF_PROG_TYPE_CGROUP_SKB, }; +enum bpf_attach_type { + BPF_CGROUP_INET_INGRESS, + BPF_CGROUP_INET_EGRESS, + __MAX_BPF_ATTACH_TYPE +}; + +#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE + #define BPF_PSEUDO_MAP_FD 1 /* flags for BPF_MAP_UPDATE_ELEM command */ diff --git a/net/core/filter.c b/net/core/filter.c index dece94fef005..2de302d68038 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2630,6 +2630,17 @@ xdp_func_proto(enum bpf_func_id func_id) } } +static const struct bpf_func_proto * +cg_skb_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_skb_load_bytes: + return &bpf_skb_load_bytes_proto; + default: + return sk_filter_func_proto(func_id); + } +} + static bool __is_valid_access(int off, int size, enum bpf_access_type type) { if (off < 0 || off >= sizeof(struct __sk_buff)) @@ -2992,6 +3003,12 @@ static const struct bpf_verifier_ops xdp_ops = { .convert_ctx_access = xdp_convert_ctx_access, }; +static const struct bpf_verifier_ops cg_skb_ops = { + .get_func_proto = cg_skb_func_proto, + .is_valid_access = sk_filter_is_valid_access, + .convert_ctx_access = sk_filter_convert_ctx_access, +}; + static struct bpf_prog_type_list sk_filter_type __read_mostly = { .ops = &sk_filter_ops, .type = BPF_PROG_TYPE_SOCKET_FILTER, @@ -3012,12 +3029,18 @@ static struct bpf_prog_type_list xdp_type __read_mostly = { .type = BPF_PROG_TYPE_XDP, }; +static struct bpf_prog_type_list cg_skb_type __read_mostly = { + .ops = &cg_skb_ops, + .type = BPF_PROG_TYPE_CGROUP_SKB, +}; + static int __init register_sk_filter_ops(void) { bpf_register_prog_type(&sk_filter_type); bpf_register_prog_type(&sched_cls_type); bpf_register_prog_type(&sched_act_type); bpf_register_prog_type(&xdp_type); + bpf_register_prog_type(&cg_skb_type); return 0; } -- cgit v1.2.3 From f4324551489e8781d838f941b7aee4208e52e8bf Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Wed, 23 Nov 2016 16:52:27 +0100 Subject: bpf: add BPF_PROG_ATTACH and BPF_PROG_DETACH commands Extend the bpf(2) syscall by two new commands, BPF_PROG_ATTACH and BPF_PROG_DETACH which allow attaching and detaching eBPF programs to a target. On the API level, the target could be anything that has an fd in userspace, hence the name of the field in union bpf_attr is called 'target_fd'. When called with BPF_ATTACH_TYPE_CGROUP_INET_{E,IN}GRESS, the target is expected to be a valid file descriptor of a cgroup v2 directory which has the bpf controller enabled. These are the only use-cases implemented by this patch at this point, but more can be added. If a program of the given type already exists in the given cgroup, the program is swapped automically, so userspace does not have to drop an existing program first before installing a new one, which would otherwise leave a gap in which no program is attached. For more information on the propagation logic to subcgroups, please refer to the bpf cgroup controller implementation. The API is guarded by CAP_NET_ADMIN. Signed-off-by: Daniel Mack Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 8 +++++ kernel/bpf/syscall.c | 81 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 89 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 5ae679fac993..1370a9d1456f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -73,6 +73,8 @@ enum bpf_cmd { BPF_PROG_LOAD, BPF_OBJ_PIN, BPF_OBJ_GET, + BPF_PROG_ATTACH, + BPF_PROG_DETACH, }; enum bpf_map_type { @@ -159,6 +161,12 @@ union bpf_attr { __aligned_u64 pathname; __u32 bpf_fd; }; + + struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ + __u32 target_fd; /* container object to attach to */ + __u32 attach_bpf_fd; /* eBPF program to attach */ + __u32 attach_type; + }; } __attribute__((aligned(8))); /* BPF helper function descriptions: diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index eb15498b8d55..1090d16a31c1 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -835,6 +835,77 @@ static int bpf_obj_get(const union bpf_attr *attr) return bpf_obj_get_user(u64_to_user_ptr(attr->pathname)); } +#ifdef CONFIG_CGROUP_BPF + +#define BPF_PROG_ATTACH_LAST_FIELD attach_type + +static int bpf_prog_attach(const union bpf_attr *attr) +{ + struct bpf_prog *prog; + struct cgroup *cgrp; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (CHECK_ATTR(BPF_PROG_ATTACH)) + return -EINVAL; + + switch (attr->attach_type) { + case BPF_CGROUP_INET_INGRESS: + case BPF_CGROUP_INET_EGRESS: + prog = bpf_prog_get_type(attr->attach_bpf_fd, + BPF_PROG_TYPE_CGROUP_SKB); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + cgrp = cgroup_get_from_fd(attr->target_fd); + if (IS_ERR(cgrp)) { + bpf_prog_put(prog); + return PTR_ERR(cgrp); + } + + cgroup_bpf_update(cgrp, prog, attr->attach_type); + cgroup_put(cgrp); + break; + + default: + return -EINVAL; + } + + return 0; +} + +#define BPF_PROG_DETACH_LAST_FIELD attach_type + +static int bpf_prog_detach(const union bpf_attr *attr) +{ + struct cgroup *cgrp; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (CHECK_ATTR(BPF_PROG_DETACH)) + return -EINVAL; + + switch (attr->attach_type) { + case BPF_CGROUP_INET_INGRESS: + case BPF_CGROUP_INET_EGRESS: + cgrp = cgroup_get_from_fd(attr->target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + + cgroup_bpf_update(cgrp, NULL, attr->attach_type); + cgroup_put(cgrp); + break; + + default: + return -EINVAL; + } + + return 0; +} +#endif /* CONFIG_CGROUP_BPF */ + SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr = {}; @@ -901,6 +972,16 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_OBJ_GET: err = bpf_obj_get(&attr); break; + +#ifdef CONFIG_CGROUP_BPF + case BPF_PROG_ATTACH: + err = bpf_prog_attach(&attr); + break; + case BPF_PROG_DETACH: + err = bpf_prog_detach(&attr); + break; +#endif + default: err = -EINVAL; break; -- cgit v1.2.3 From 7ea7861c8c2462af932410c54542cb279683eaf8 Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Thu, 3 Nov 2016 17:57:50 -0600 Subject: tpm, tpm_vtpm_proxy: add kdoc comments for VTPM_PROXY_IOC_NEW_DEV Added kdoc comments for VTPM_PROXY_IOC_NEW_DEV so that these can be imported to the kernel documentation written with rst markup and generated with Sphinx. Signed-off-by: Jarkko Sakkinen Reviewed-by: Stefan Berger --- drivers/char/tpm/tpm_vtpm_proxy.c | 72 +++++++++++++++++++++++++-------------- include/uapi/linux/vtpm_proxy.h | 23 ++++++++++--- 2 files changed, 65 insertions(+), 30 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/char/tpm/tpm_vtpm_proxy.c b/drivers/char/tpm/tpm_vtpm_proxy.c index 9a940332c157..3d6f6ca81def 100644 --- a/drivers/char/tpm/tpm_vtpm_proxy.c +++ b/drivers/char/tpm/tpm_vtpm_proxy.c @@ -1,5 +1,6 @@ /* * Copyright (C) 2015, 2016 IBM Corporation + * Copyright (C) 2016 Intel Corporation * * Author: Stefan Berger * @@ -524,6 +525,50 @@ static void vtpm_proxy_delete_device(struct proxy_dev *proxy_dev) * Code related to the control device /dev/vtpmx */ +/** + * vtpmx_ioc_new_dev - handler for the %VTPM_PROXY_IOC_NEW_DEV ioctl + * @file: /dev/vtpmx + * @ioctl: the ioctl number + * @arg: pointer to the struct vtpmx_proxy_new_dev + * + * Creates an anonymous file that is used by the process acting as a TPM to + * communicate with the client processes. The function will also add a new TPM + * device through which data is proxied to this TPM acting process. The caller + * will be provided with a file descriptor to communicate with the clients and + * major and minor numbers for the TPM device. + */ +static long vtpmx_ioc_new_dev(struct file *file, unsigned int ioctl, + unsigned long arg) +{ + void __user *argp = (void __user *)arg; + struct vtpm_proxy_new_dev __user *vtpm_new_dev_p; + struct vtpm_proxy_new_dev vtpm_new_dev; + struct file *vtpm_file; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + vtpm_new_dev_p = argp; + + if (copy_from_user(&vtpm_new_dev, vtpm_new_dev_p, + sizeof(vtpm_new_dev))) + return -EFAULT; + + vtpm_file = vtpm_proxy_create_device(&vtpm_new_dev); + if (IS_ERR(vtpm_file)) + return PTR_ERR(vtpm_file); + + if (copy_to_user(vtpm_new_dev_p, &vtpm_new_dev, + sizeof(vtpm_new_dev))) { + put_unused_fd(vtpm_new_dev.fd); + fput(vtpm_file); + return -EFAULT; + } + + fd_install(vtpm_new_dev.fd, vtpm_file); + return 0; +} + /* * vtpmx_fops_ioctl: ioctl on /dev/vtpmx * @@ -531,34 +576,11 @@ static void vtpm_proxy_delete_device(struct proxy_dev *proxy_dev) * Returns 0 on success, a negative error code otherwise. */ static long vtpmx_fops_ioctl(struct file *f, unsigned int ioctl, - unsigned long arg) + unsigned long arg) { - void __user *argp = (void __user *)arg; - struct vtpm_proxy_new_dev __user *vtpm_new_dev_p; - struct vtpm_proxy_new_dev vtpm_new_dev; - struct file *file; - switch (ioctl) { case VTPM_PROXY_IOC_NEW_DEV: - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - vtpm_new_dev_p = argp; - if (copy_from_user(&vtpm_new_dev, vtpm_new_dev_p, - sizeof(vtpm_new_dev))) - return -EFAULT; - file = vtpm_proxy_create_device(&vtpm_new_dev); - if (IS_ERR(file)) - return PTR_ERR(file); - if (copy_to_user(vtpm_new_dev_p, &vtpm_new_dev, - sizeof(vtpm_new_dev))) { - put_unused_fd(vtpm_new_dev.fd); - fput(file); - return -EFAULT; - } - - fd_install(vtpm_new_dev.fd, file); - return 0; - + return vtpmx_ioc_new_dev(f, ioctl, arg); default: return -ENOIOCTLCMD; } diff --git a/include/uapi/linux/vtpm_proxy.h b/include/uapi/linux/vtpm_proxy.h index 41e8e2252a30..a69e991eb080 100644 --- a/include/uapi/linux/vtpm_proxy.h +++ b/include/uapi/linux/vtpm_proxy.h @@ -1,6 +1,7 @@ /* * Definitions for the VTPM proxy driver * Copyright (c) 2015, 2016, IBM Corporation + * Copyright (C) 2016 Intel Corporation * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -18,8 +19,23 @@ #include #include -/* ioctls */ +/** + * enum vtpm_proxy_flags - flags for the proxy TPM + * @VTPM_PROXY_FLAG_TPM2: the proxy TPM uses TPM 2.0 protocol + */ +enum vtpm_proxy_flags { + VTPM_PROXY_FLAG_TPM2 = 1, +}; +/** + * struct vtpm_proxy_new_dev - parameter structure for the + * %VTPM_PROXY_IOC_NEW_DEV ioctl + * @flags: flags for the proxy TPM + * @tpm_num: index of the TPM device + * @fd: the file descriptor used by the proxy TPM + * @major: the major number of the TPM device + * @minor: the minor number of the TPM device + */ struct vtpm_proxy_new_dev { __u32 flags; /* input */ __u32 tpm_num; /* output */ @@ -28,9 +44,6 @@ struct vtpm_proxy_new_dev { __u32 minor; /* output */ }; -/* above flags */ -#define VTPM_PROXY_FLAG_TPM2 1 /* emulator is TPM 2 */ - -#define VTPM_PROXY_IOC_NEW_DEV _IOWR(0xa1, 0x00, struct vtpm_proxy_new_dev) +#define VTPM_PROXY_IOC_NEW_DEV _IOWR(0xa1, 0x00, struct vtpm_proxy_new_dev) #endif /* _UAPI_LINUX_VTPM_PROXY_H */ -- cgit v1.2.3 From faa1fa54fd25a59a6c4b731ac652a2b7cd21ace8 Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Sun, 27 Nov 2016 12:14:49 +0200 Subject: net/sched: Export tc_tunnel_key so its UAPI accessible Export tc_tunnel_key so it can be used from user space. Signed-off-by: Roi Dayan Reviewed-by: Amir Vadai Signed-off-by: David S. Miller --- include/uapi/linux/tc_act/Kbuild | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tc_act/Kbuild b/include/uapi/linux/tc_act/Kbuild index e3969bd939e4..9611c7b6c18f 100644 --- a/include/uapi/linux/tc_act/Kbuild +++ b/include/uapi/linux/tc_act/Kbuild @@ -11,3 +11,4 @@ header-y += tc_vlan.h header-y += tc_bpf.h header-y += tc_connmark.h header-y += tc_ife.h +header-y += tc_tunnel_key.h -- cgit v1.2.3 From 417b1bf8367edb7e68bd9f3275c104871aeca530 Mon Sep 17 00:00:00 2001 From: Jeonghan Kim Date: Wed, 19 Oct 2016 19:48:02 +0900 Subject: mmc: block: Change MMC_IOC_MAX_BYTES It is used for limitation of buffer size during IOCTL such as FFU. However, eMMC FW size is bigger than (512L*256). (For instance, currently, Samsung eMMC FW size is over 300KB.) So, it needs to increase to execute FFU. Signed-off-by: Jeonghan Kim Acked-by: Jaehoon Chung Signed-off-by: Ulf Hansson --- include/uapi/linux/mmc/ioctl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mmc/ioctl.h b/include/uapi/linux/mmc/ioctl.h index 7e385b83b9d8..700a55156eee 100644 --- a/include/uapi/linux/mmc/ioctl.h +++ b/include/uapi/linux/mmc/ioctl.h @@ -69,6 +69,6 @@ struct mmc_ioc_multi_cmd { * is enforced per ioctl call. For larger data transfers, use the normal * block device operations. */ -#define MMC_IOC_MAX_BYTES (512L * 256) +#define MMC_IOC_MAX_BYTES (512L * 1024) #define MMC_IOC_MAX_CMDS 255 #endif /* LINUX_MMC_IOCTL_H */ -- cgit v1.2.3 From 8fae47705685fcaa75a1fe4c8c3e18300a702979 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Sun, 20 Nov 2016 16:47:55 -0500 Subject: audit: add support for session ID user filter Define AUDIT_SESSIONID in the uapi and add support for specifying user filters based on the session ID. Also add the new session ID filter to the feature bitmap so userspace knows it is available. https://github.com/linux-audit/audit-kernel/issues/4 RFE: add a session ID filter to the kernel's user filter Signed-off-by: Richard Guy Briggs [PM: combine multiple patches from Richard into this one] Signed-off-by: Paul Moore --- include/uapi/linux/audit.h | 5 ++++- kernel/auditfilter.c | 2 ++ kernel/auditsc.c | 5 +++++ 3 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 82e8aa59446b..c8dc97bc2c1b 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -254,6 +254,7 @@ #define AUDIT_OBJ_LEV_LOW 22 #define AUDIT_OBJ_LEV_HIGH 23 #define AUDIT_LOGINUID_SET 24 +#define AUDIT_SESSIONID 25 /* Session ID */ /* These are ONLY useful when checking * at syscall exit time (AUDIT_AT_EXIT). */ @@ -329,9 +330,11 @@ enum { #define AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT 0x00000001 #define AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME 0x00000002 #define AUDIT_FEATURE_BITMAP_EXECUTABLE_PATH 0x00000004 +#define AUDIT_FEATURE_BITMAP_SESSIONID_FILTER 0x00000010 #define AUDIT_FEATURE_BITMAP_ALL (AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT | \ AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME | \ - AUDIT_FEATURE_BITMAP_EXECUTABLE_PATH) + AUDIT_FEATURE_BITMAP_EXECUTABLE_PATH | \ + AUDIT_FEATURE_BITMAP_SESSIONID_FILTER) /* deprecated: AUDIT_VERSION_* */ #define AUDIT_VERSION_LATEST AUDIT_FEATURE_BITMAP_ALL diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 632e90d1005f..880519d6cf2a 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -363,6 +363,7 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) case AUDIT_EXIT: case AUDIT_SUCCESS: case AUDIT_INODE: + case AUDIT_SESSIONID: /* bit ops are only useful on syscall args */ if (f->op == Audit_bitmask || f->op == Audit_bittest) return -EINVAL; @@ -476,6 +477,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, if (!gid_valid(f->gid)) goto exit_free; break; + case AUDIT_SESSIONID: case AUDIT_ARCH: entry->rule.arch_f = f; break; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index d161b17ce8ce..f78cb1b3fa74 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -446,6 +446,7 @@ static int audit_filter_rules(struct task_struct *tsk, const struct cred *cred; int i, need_sid = 1; u32 sid; + unsigned int sessionid; cred = rcu_dereference_check(tsk->cred, tsk == current || task_creation); @@ -508,6 +509,10 @@ static int audit_filter_rules(struct task_struct *tsk, case AUDIT_FSGID: result = audit_gid_comparator(cred->fsgid, f->op, f->gid); break; + case AUDIT_SESSIONID: + sessionid = audit_get_sessionid(current); + result = audit_comparator(sessionid, f->op, f->val); + break; case AUDIT_PERS: result = audit_comparator(tsk->personality, f->op, f->val); break; -- cgit v1.2.3 From efd90174167530c67a54273fd5d8369c87f9bd32 Mon Sep 17 00:00:00 2001 From: Francis Yan Date: Sun, 27 Nov 2016 23:07:17 -0800 Subject: tcp: export sender limits chronographs to TCP_INFO This patch exports all the sender chronograph measurements collected in the previous patches to TCP_INFO interface. Note that busy time exported includes all the other sending limits (rwnd-limited, sndbuf-limited). Internally the time unit is jiffy but externally the measurements are in microseconds for future extensions. Signed-off-by: Francis Yan Signed-off-by: Yuchung Cheng Signed-off-by: Soheil Hassas Yeganeh Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/uapi/linux/tcp.h | 4 ++++ net/ipv4/tcp.c | 20 ++++++++++++++++++++ 2 files changed, 24 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 73ac0db487f8..2863b661d6e1 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -214,6 +214,10 @@ struct tcp_info { __u32 tcpi_data_segs_out; /* RFC4898 tcpEStatsDataSegsOut */ __u64 tcpi_delivery_rate; + + __u64 tcpi_busy_time; /* Time (usec) busy sending data */ + __u64 tcpi_rwnd_limited; /* Time (usec) limited by receive window */ + __u64 tcpi_sndbuf_limited; /* Time (usec) limited by send buffer */ }; /* for TCP_MD5SIG socket option */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 259ffb50e429..cdde20f49999 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2708,6 +2708,25 @@ int compat_tcp_setsockopt(struct sock *sk, int level, int optname, EXPORT_SYMBOL(compat_tcp_setsockopt); #endif +static void tcp_get_info_chrono_stats(const struct tcp_sock *tp, + struct tcp_info *info) +{ + u64 stats[__TCP_CHRONO_MAX], total = 0; + enum tcp_chrono i; + + for (i = TCP_CHRONO_BUSY; i < __TCP_CHRONO_MAX; ++i) { + stats[i] = tp->chrono_stat[i - 1]; + if (i == tp->chrono_type) + stats[i] += tcp_time_stamp - tp->chrono_start; + stats[i] *= USEC_PER_SEC / HZ; + total += stats[i]; + } + + info->tcpi_busy_time = total; + info->tcpi_rwnd_limited = stats[TCP_CHRONO_RWND_LIMITED]; + info->tcpi_sndbuf_limited = stats[TCP_CHRONO_SNDBUF_LIMITED]; +} + /* Return information about state of tcp endpoint in API format. */ void tcp_get_info(struct sock *sk, struct tcp_info *info) { @@ -2800,6 +2819,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_bytes_acked = tp->bytes_acked; info->tcpi_bytes_received = tp->bytes_received; info->tcpi_notsent_bytes = max_t(int, 0, tp->write_seq - tp->snd_nxt); + tcp_get_info_chrono_stats(tp, info); unlock_sock_fast(sk, slow); -- cgit v1.2.3 From 1c885808e45601b2b6f68b30ac1d999e10b6f606 Mon Sep 17 00:00:00 2001 From: Francis Yan Date: Sun, 27 Nov 2016 23:07:18 -0800 Subject: tcp: SOF_TIMESTAMPING_OPT_STATS option for SO_TIMESTAMPING This patch exports the sender chronograph stats via the socket SO_TIMESTAMPING channel. Currently we can instrument how long a particular application unit of data was queued in TCP by tracking SOF_TIMESTAMPING_TX_SOFTWARE and SOF_TIMESTAMPING_TX_SCHED. Having these sender chronograph stats exported simultaneously along with these timestamps allow further breaking down the various sender limitation. For example, a video server can tell if a particular chunk of video on a connection takes a long time to deliver because TCP was experiencing small receive window. It is not possible to tell before this patch without packet traces. To prepare these stats, the user needs to set SOF_TIMESTAMPING_OPT_STATS and SOF_TIMESTAMPING_OPT_TSONLY flags while requesting other SOF_TIMESTAMPING TX timestamps. When the timestamps are available in the error queue, the stats are returned in a separate control message of type SCM_TIMESTAMPING_OPT_STATS, in a list of TLVs (struct nlattr) of types: TCP_NLA_BUSY_TIME, TCP_NLA_RWND_LIMITED, TCP_NLA_SNDBUF_LIMITED. Unit is microsecond. Signed-off-by: Francis Yan Signed-off-by: Yuchung Cheng Signed-off-by: Soheil Hassas Yeganeh Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- Documentation/networking/timestamping.txt | 10 ++++++++++ arch/alpha/include/uapi/asm/socket.h | 2 ++ arch/frv/include/uapi/asm/socket.h | 2 ++ arch/ia64/include/uapi/asm/socket.h | 2 ++ arch/m32r/include/uapi/asm/socket.h | 2 ++ arch/mips/include/uapi/asm/socket.h | 2 ++ arch/mn10300/include/uapi/asm/socket.h | 2 ++ arch/parisc/include/uapi/asm/socket.h | 2 ++ arch/powerpc/include/uapi/asm/socket.h | 2 ++ arch/s390/include/uapi/asm/socket.h | 2 ++ arch/sparc/include/uapi/asm/socket.h | 2 ++ arch/xtensa/include/uapi/asm/socket.h | 2 ++ include/linux/tcp.h | 2 ++ include/uapi/asm-generic/socket.h | 2 ++ include/uapi/linux/net_tstamp.h | 3 ++- include/uapi/linux/tcp.h | 8 ++++++++ net/core/skbuff.c | 14 +++++++++++--- net/core/sock.c | 7 +++++++ net/ipv4/tcp.c | 20 ++++++++++++++++++++ net/socket.c | 7 ++++++- 20 files changed, 90 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt index 671cccf0dcd2..96f50694a748 100644 --- a/Documentation/networking/timestamping.txt +++ b/Documentation/networking/timestamping.txt @@ -182,6 +182,16 @@ SOF_TIMESTAMPING_OPT_TSONLY: the timestamp even if sysctl net.core.tstamp_allow_data is 0. This option disables SOF_TIMESTAMPING_OPT_CMSG. +SOF_TIMESTAMPING_OPT_STATS: + + Optional stats that are obtained along with the transmit timestamps. + It must be used together with SOF_TIMESTAMPING_OPT_TSONLY. When the + transmit timestamp is available, the stats are available in a + separate control message of type SCM_TIMESTAMPING_OPT_STATS, as a + list of TLVs (struct nlattr) of types. These stats allow the + application to associate various transport layer stats with + the transmit timestamps, such as how long a certain block of + data was limited by peer's receiver window. New applications are encouraged to pass SOF_TIMESTAMPING_OPT_ID to disambiguate timestamps and SOF_TIMESTAMPING_OPT_TSONLY to operate diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 9e46d6e656d9..afc901b7a6f6 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -97,4 +97,6 @@ #define SO_CNX_ADVICE 53 +#define SCM_TIMESTAMPING_OPT_STATS 54 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h index afbc98f02d27..81e03530ed39 100644 --- a/arch/frv/include/uapi/asm/socket.h +++ b/arch/frv/include/uapi/asm/socket.h @@ -90,5 +90,7 @@ #define SO_CNX_ADVICE 53 +#define SCM_TIMESTAMPING_OPT_STATS 54 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h index 0018fad9039f..57feb0c1f7d7 100644 --- a/arch/ia64/include/uapi/asm/socket.h +++ b/arch/ia64/include/uapi/asm/socket.h @@ -99,4 +99,6 @@ #define SO_CNX_ADVICE 53 +#define SCM_TIMESTAMPING_OPT_STATS 54 + #endif /* _ASM_IA64_SOCKET_H */ diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h index 5fe42fc7b6c5..5853f8e92c20 100644 --- a/arch/m32r/include/uapi/asm/socket.h +++ b/arch/m32r/include/uapi/asm/socket.h @@ -90,4 +90,6 @@ #define SO_CNX_ADVICE 53 +#define SCM_TIMESTAMPING_OPT_STATS 54 + #endif /* _ASM_M32R_SOCKET_H */ diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 2027240aafbb..566ecdcb5b4b 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -108,4 +108,6 @@ #define SO_CNX_ADVICE 53 +#define SCM_TIMESTAMPING_OPT_STATS 54 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h index 5129f23a9ee1..0e12527c4b0e 100644 --- a/arch/mn10300/include/uapi/asm/socket.h +++ b/arch/mn10300/include/uapi/asm/socket.h @@ -90,4 +90,6 @@ #define SO_CNX_ADVICE 53 +#define SCM_TIMESTAMPING_OPT_STATS 54 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 9c935d717df9..7a109b73ddf7 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -89,4 +89,6 @@ #define SO_CNX_ADVICE 0x402E +#define SCM_TIMESTAMPING_OPT_STATS 0x402F + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h index 1672e3398270..44583a52f882 100644 --- a/arch/powerpc/include/uapi/asm/socket.h +++ b/arch/powerpc/include/uapi/asm/socket.h @@ -97,4 +97,6 @@ #define SO_CNX_ADVICE 53 +#define SCM_TIMESTAMPING_OPT_STATS 54 + #endif /* _ASM_POWERPC_SOCKET_H */ diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index 41b51c2f4f1b..b24a64cbfeb1 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -96,4 +96,6 @@ #define SO_CNX_ADVICE 53 +#define SCM_TIMESTAMPING_OPT_STATS 54 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 31aede3af088..a25dc32f5d6a 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -86,6 +86,8 @@ #define SO_CNX_ADVICE 0x0037 +#define SCM_TIMESTAMPING_OPT_STATS 0x0038 + /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 0x5001 #define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002 diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h index 81435d995e11..9fdbe1fe0473 100644 --- a/arch/xtensa/include/uapi/asm/socket.h +++ b/arch/xtensa/include/uapi/asm/socket.h @@ -101,4 +101,6 @@ #define SO_CNX_ADVICE 53 +#define SCM_TIMESTAMPING_OPT_STATS 54 + #endif /* _XTENSA_SOCKET_H */ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index d5d3bd814338..00e0ee8f001f 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -428,4 +428,6 @@ static inline void tcp_saved_syn_free(struct tcp_sock *tp) tp->saved_syn = NULL; } +struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk); + #endif /* _LINUX_TCP_H */ diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 67d632f1743d..2c748ddad5f8 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -92,4 +92,6 @@ #define SO_CNX_ADVICE 53 +#define SCM_TIMESTAMPING_OPT_STATS 54 + #endif /* __ASM_GENERIC_SOCKET_H */ diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index 264e515de16f..464dcca5ed68 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -25,8 +25,9 @@ enum { SOF_TIMESTAMPING_TX_ACK = (1<<9), SOF_TIMESTAMPING_OPT_CMSG = (1<<10), SOF_TIMESTAMPING_OPT_TSONLY = (1<<11), + SOF_TIMESTAMPING_OPT_STATS = (1<<12), - SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_TSONLY, + SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_STATS, SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) | SOF_TIMESTAMPING_LAST }; diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 2863b661d6e1..c53de2691cec 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -220,6 +220,14 @@ struct tcp_info { __u64 tcpi_sndbuf_limited; /* Time (usec) limited by send buffer */ }; +/* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */ +enum { + TCP_NLA_PAD, + TCP_NLA_BUSY, /* Time (usec) busy sending data */ + TCP_NLA_RWND_LIMITED, /* Time (usec) limited by receive window */ + TCP_NLA_SNDBUF_LIMITED, /* Time (usec) limited by send buffer */ +}; + /* for TCP_MD5SIG socket option */ #define TCP_MD5SIG_MAXKEYLEN 80 diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d1d1a5a5ad24..ea6fa954c7a0 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3839,10 +3839,18 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, if (!skb_may_tx_timestamp(sk, tsonly)) return; - if (tsonly) - skb = alloc_skb(0, GFP_ATOMIC); - else + if (tsonly) { +#ifdef CONFIG_INET + if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) && + sk->sk_protocol == IPPROTO_TCP && + sk->sk_type == SOCK_STREAM) + skb = tcp_get_timestamping_opt_stats(sk); + else +#endif + skb = alloc_skb(0, GFP_ATOMIC); + } else { skb = skb_clone(orig_skb, GFP_ATOMIC); + } if (!skb) return; diff --git a/net/core/sock.c b/net/core/sock.c index 14e6145be33b..d8c7f8c877ca 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -854,6 +854,13 @@ set_rcvbuf: sk->sk_tskey = 0; } } + + if (val & SOF_TIMESTAMPING_OPT_STATS && + !(val & SOF_TIMESTAMPING_OPT_TSONLY)) { + ret = -EINVAL; + break; + } + sk->sk_tsflags = val; if (val & SOF_TIMESTAMPING_RX_SOFTWARE) sock_enable_timestamp(sk, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index cdde20f49999..1149b48700a1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2841,6 +2841,26 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) } EXPORT_SYMBOL_GPL(tcp_get_info); +struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *stats; + struct tcp_info info; + + stats = alloc_skb(3 * nla_total_size_64bit(sizeof(u64)), GFP_ATOMIC); + if (!stats) + return NULL; + + tcp_get_info_chrono_stats(tp, &info); + nla_put_u64_64bit(stats, TCP_NLA_BUSY, + info.tcpi_busy_time, TCP_NLA_PAD); + nla_put_u64_64bit(stats, TCP_NLA_RWND_LIMITED, + info.tcpi_rwnd_limited, TCP_NLA_PAD); + nla_put_u64_64bit(stats, TCP_NLA_SNDBUF_LIMITED, + info.tcpi_sndbuf_limited, TCP_NLA_PAD); + return stats; +} + static int do_tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { diff --git a/net/socket.c b/net/socket.c index e2584c51aa1f..e6318943ad07 100644 --- a/net/socket.c +++ b/net/socket.c @@ -693,9 +693,14 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && ktime_to_timespec_cond(shhwtstamps->hwtstamp, tss.ts + 2)) empty = 0; - if (!empty) + if (!empty) { put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING, sizeof(tss), &tss); + + if (skb->len && (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS)) + put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_OPT_STATS, + skb->len, skb->data); + } } EXPORT_SYMBOL_GPL(__sock_recv_timestamp); -- cgit v1.2.3 From 85de8576a0b14aecc99136cfbf90e367fa2142cb Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 28 Nov 2016 23:16:54 +0100 Subject: bpf, xdp: allow to pass flags to dev_change_xdp_fd Add an IFLA_XDP_FLAGS attribute that can be passed for setting up XDP along with IFLA_XDP_FD, which eventually allows user space to implement typical add/replace/delete logic for programs. Right now, calling into dev_change_xdp_fd() will always replace previous programs. When passed XDP_FLAGS_UPDATE_IF_NOEXIST, we can handle this more graceful when requested by returning -EBUSY in case we try to attach a new program, but we find that another one is already attached. This will be used by upcoming front-end for iproute2 as well. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- include/uapi/linux/if_link.h | 4 ++++ net/core/dev.c | 20 ++++++++++++++++++-- net/core/rtnetlink.c | 14 +++++++++++++- 4 files changed, 36 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4ffcd874cc20..3755317cc6a9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3253,7 +3253,7 @@ int dev_get_phys_port_id(struct net_device *dev, int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len); int dev_change_proto_down(struct net_device *dev, bool proto_down); -int dev_change_xdp_fd(struct net_device *dev, int fd); +int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 92b2d4928bf1..6b13e591abc9 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -876,10 +876,14 @@ enum { /* XDP section */ +#define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0) +#define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST) + enum { IFLA_XDP_UNSPEC, IFLA_XDP_FD, IFLA_XDP_ATTACHED, + IFLA_XDP_FLAGS, __IFLA_XDP_MAX, }; diff --git a/net/core/dev.c b/net/core/dev.c index 048b46b7c92a..bffb5253e778 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6692,26 +6692,42 @@ EXPORT_SYMBOL(dev_change_proto_down); * dev_change_xdp_fd - set or clear a bpf program for a device rx path * @dev: device * @fd: new program fd or negative value to clear + * @flags: xdp-related flags * * Set or clear a bpf program for a device */ -int dev_change_xdp_fd(struct net_device *dev, int fd) +int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags) { const struct net_device_ops *ops = dev->netdev_ops; struct bpf_prog *prog = NULL; - struct netdev_xdp xdp = {}; + struct netdev_xdp xdp; int err; + ASSERT_RTNL(); + if (!ops->ndo_xdp) return -EOPNOTSUPP; if (fd >= 0) { + if (flags & XDP_FLAGS_UPDATE_IF_NOEXIST) { + memset(&xdp, 0, sizeof(xdp)); + xdp.command = XDP_QUERY_PROG; + + err = ops->ndo_xdp(dev, &xdp); + if (err < 0) + return err; + if (xdp.prog_attached) + return -EBUSY; + } + prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP); if (IS_ERR(prog)) return PTR_ERR(prog); } + memset(&xdp, 0, sizeof(xdp)); xdp.command = XDP_SETUP_PROG; xdp.prog = prog; + err = ops->ndo_xdp(dev, &xdp); if (err < 0 && prog) bpf_prog_put(prog); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 4e60525ea586..bd85570e6e4b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1505,6 +1505,7 @@ static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { static const struct nla_policy ifla_xdp_policy[IFLA_XDP_MAX + 1] = { [IFLA_XDP_FD] = { .type = NLA_S32 }, [IFLA_XDP_ATTACHED] = { .type = NLA_U8 }, + [IFLA_XDP_FLAGS] = { .type = NLA_U32 }, }; static const struct rtnl_link_ops *linkinfo_to_kind_ops(const struct nlattr *nla) @@ -2164,6 +2165,7 @@ static int do_setlink(const struct sk_buff *skb, if (tb[IFLA_XDP]) { struct nlattr *xdp[IFLA_XDP_MAX + 1]; + u32 xdp_flags = 0; err = nla_parse_nested(xdp, IFLA_XDP_MAX, tb[IFLA_XDP], ifla_xdp_policy); @@ -2174,9 +2176,19 @@ static int do_setlink(const struct sk_buff *skb, err = -EINVAL; goto errout; } + + if (xdp[IFLA_XDP_FLAGS]) { + xdp_flags = nla_get_u32(xdp[IFLA_XDP_FLAGS]); + if (xdp_flags & ~XDP_FLAGS_MASK) { + err = -EINVAL; + goto errout; + } + } + if (xdp[IFLA_XDP_FD]) { err = dev_change_xdp_fd(dev, - nla_get_s32(xdp[IFLA_XDP_FD])); + nla_get_s32(xdp[IFLA_XDP_FD]), + xdp_flags); if (err) goto errout; status |= DO_SETLINK_NOTIFY; -- cgit v1.2.3 From 3a0af8fd61f90920f6fa04e4f1e9a6a73c1b4fd2 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Wed, 30 Nov 2016 17:10:10 +0100 Subject: bpf: BPF for lightweight tunnel infrastructure Registers new BPF program types which correspond to the LWT hooks: - BPF_PROG_TYPE_LWT_IN => dst_input() - BPF_PROG_TYPE_LWT_OUT => dst_output() - BPF_PROG_TYPE_LWT_XMIT => lwtunnel_xmit() The separate program types are required to differentiate between the capabilities each LWT hook allows: * Programs attached to dst_input() or dst_output() are restricted and may only read the data of an skb. This prevent modification and possible invalidation of already validated packet headers on receive and the construction of illegal headers while the IP headers are still being assembled. * Programs attached to lwtunnel_xmit() are allowed to modify packet content as well as prepending an L2 header via a newly introduced helper bpf_skb_change_head(). This is safe as lwtunnel_xmit() is invoked after the IP header has been assembled completely. All BPF programs receive an skb with L3 headers attached and may return one of the following error codes: BPF_OK - Continue routing as per nexthop BPF_DROP - Drop skb and return EPERM BPF_REDIRECT - Redirect skb to device as per redirect() helper. (Only valid in lwtunnel_xmit() context) The return codes are binary compatible with their TC_ACT_ relatives to ease compatibility. Signed-off-by: Thomas Graf Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/filter.h | 2 +- include/uapi/linux/bpf.h | 32 +++- include/uapi/linux/lwtunnel.h | 23 +++ kernel/bpf/verifier.c | 14 +- net/Kconfig | 8 + net/core/Makefile | 1 + net/core/filter.c | 173 ++++++++++++++++++ net/core/lwt_bpf.c | 396 ++++++++++++++++++++++++++++++++++++++++++ net/core/lwtunnel.c | 2 + 9 files changed, 646 insertions(+), 5 deletions(-) create mode 100644 net/core/lwt_bpf.c (limited to 'include/uapi/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 7f246a281435..7ba644626553 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -438,7 +438,7 @@ struct xdp_buff { }; /* compute the linear packet data range [data, data_end) which - * will be accessed by cls_bpf and act_bpf programs + * will be accessed by cls_bpf, act_bpf and lwt programs */ static inline void bpf_compute_data_end(struct sk_buff *skb) { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1370a9d1456f..22ac82792687 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -101,6 +101,9 @@ enum bpf_prog_type { BPF_PROG_TYPE_XDP, BPF_PROG_TYPE_PERF_EVENT, BPF_PROG_TYPE_CGROUP_SKB, + BPF_PROG_TYPE_LWT_IN, + BPF_PROG_TYPE_LWT_OUT, + BPF_PROG_TYPE_LWT_XMIT, }; enum bpf_attach_type { @@ -409,6 +412,16 @@ union bpf_attr { * * int bpf_get_numa_node_id() * Return: Id of current NUMA node. + * + * int bpf_skb_change_head() + * Grows headroom of skb and adjusts MAC header offset accordingly. + * Will extends/reallocae as required automatically. + * May change skb data pointer and will thus invalidate any check + * performed for direct packet access. + * @skb: pointer to skb + * @len: length of header to be pushed in front + * @flags: Flags (unused for now) + * Return: 0 on success or negative error */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -453,7 +466,8 @@ union bpf_attr { FN(skb_pull_data), \ FN(csum_update), \ FN(set_hash_invalid), \ - FN(get_numa_node_id), + FN(get_numa_node_id), \ + FN(skb_change_head), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -537,6 +551,22 @@ struct bpf_tunnel_key { __u32 tunnel_label; }; +/* Generic BPF return codes which all BPF program types may support. + * The values are binary compatible with their TC_ACT_* counter-part to + * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT + * programs. + * + * XDP is handled seprately, see XDP_*. + */ +enum bpf_ret_code { + BPF_OK = 0, + /* 1 reserved */ + BPF_DROP = 2, + /* 3-6 reserved */ + BPF_REDIRECT = 7, + /* >127 are reserved for prog type specific return codes */ +}; + /* User return codes for XDP prog type. * A valid XDP program must return one of these defined values. All other * return codes are reserved for future use. Unknown return codes will result diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h index 453cc6215bfd..92724cba1eba 100644 --- a/include/uapi/linux/lwtunnel.h +++ b/include/uapi/linux/lwtunnel.h @@ -10,6 +10,7 @@ enum lwtunnel_encap_types { LWTUNNEL_ENCAP_ILA, LWTUNNEL_ENCAP_IP6, LWTUNNEL_ENCAP_SEG6, + LWTUNNEL_ENCAP_BPF, __LWTUNNEL_ENCAP_MAX, }; @@ -43,4 +44,26 @@ enum lwtunnel_ip6_t { #define LWTUNNEL_IP6_MAX (__LWTUNNEL_IP6_MAX - 1) +enum { + LWT_BPF_PROG_UNSPEC, + LWT_BPF_PROG_FD, + LWT_BPF_PROG_NAME, + __LWT_BPF_PROG_MAX, +}; + +#define LWT_BPF_PROG_MAX (__LWT_BPF_PROG_MAX - 1) + +enum { + LWT_BPF_UNSPEC, + LWT_BPF_IN, + LWT_BPF_OUT, + LWT_BPF_XMIT, + LWT_BPF_XMIT_HEADROOM, + __LWT_BPF_MAX, +}; + +#define LWT_BPF_MAX (__LWT_BPF_MAX - 1) + +#define LWT_BPF_MAX_HEADROOM 256 + #endif /* _UAPI_LWTUNNEL_H_ */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 8740c5fa02fc..8135cb1077ee 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -633,12 +633,19 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, int off, #define MAX_PACKET_OFF 0xffff static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, - const struct bpf_call_arg_meta *meta) + const struct bpf_call_arg_meta *meta, + enum bpf_access_type t) { switch (env->prog->type) { + case BPF_PROG_TYPE_LWT_IN: + case BPF_PROG_TYPE_LWT_OUT: + /* dst_input() and dst_output() can't write for now */ + if (t == BPF_WRITE) + return false; case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: + case BPF_PROG_TYPE_LWT_XMIT: if (meta) return meta->pkt_access; @@ -837,7 +844,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off, err = check_stack_read(state, off, size, value_regno); } } else if (state->regs[regno].type == PTR_TO_PACKET) { - if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL)) { + if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) { verbose("cannot write into packet\n"); return -EACCES; } @@ -970,7 +977,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, return 0; } - if (type == PTR_TO_PACKET && !may_access_direct_pkt_data(env, meta)) { + if (type == PTR_TO_PACKET && + !may_access_direct_pkt_data(env, meta, BPF_READ)) { verbose("helper access to the packet is not allowed\n"); return -EACCES; } diff --git a/net/Kconfig b/net/Kconfig index 7b6cd340b72b..a1005007224c 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -402,6 +402,14 @@ config LWTUNNEL weight tunnel endpoint. Tunnel encapsulation parameters are stored with light weight tunnel state associated with fib routes. +config LWTUNNEL_BPF + bool "Execute BPF program as route nexthop action" + depends on LWTUNNEL + default y if LWTUNNEL=y + ---help--- + Allows to run BPF programs as a nexthop action following a route + lookup for incoming and outgoing packets. + config DST_CACHE bool default n diff --git a/net/core/Makefile b/net/core/Makefile index d6508c2ddca5..f6761b6e3b29 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -24,6 +24,7 @@ obj-$(CONFIG_NET_PTP_CLASSIFY) += ptp_classifier.o obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o obj-$(CONFIG_LWTUNNEL) += lwtunnel.o +obj-$(CONFIG_LWTUNNEL_BPF) += lwt_bpf.o obj-$(CONFIG_DST_CACHE) += dst_cache.o obj-$(CONFIG_HWBM) += hwbm.o obj-$(CONFIG_NET_DEVLINK) += devlink.o diff --git a/net/core/filter.c b/net/core/filter.c index 698a262b8ebb..1c4d0faf22c8 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1689,6 +1689,12 @@ static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev, static int __bpf_redirect_common(struct sk_buff *skb, struct net_device *dev, u32 flags) { + /* Verify that a link layer header is carried */ + if (unlikely(skb->mac_header >= skb->network_header)) { + kfree_skb(skb); + return -ERANGE; + } + bpf_push_mac_rcsum(skb); return flags & BPF_F_INGRESS ? __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb); @@ -2188,12 +2194,53 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, + u64, flags) +{ + u32 max_len = __bpf_skb_max_len(skb); + u32 new_len = skb->len + head_room; + int ret; + + if (unlikely(flags || (!skb_is_gso(skb) && new_len > max_len) || + new_len < skb->len)) + return -EINVAL; + + ret = skb_cow(skb, head_room); + if (likely(!ret)) { + /* Idea for this helper is that we currently only + * allow to expand on mac header. This means that + * skb->protocol network header, etc, stay as is. + * Compared to bpf_skb_change_tail(), we're more + * flexible due to not needing to linearize or + * reset GSO. Intention for this helper is to be + * used by an L3 skb that needs to push mac header + * for redirection into L2 device. + */ + __skb_push(skb, head_room); + memset(skb->data, 0, head_room); + skb_reset_mac_header(skb); + } + + bpf_compute_data_end(skb); + return 0; +} + +static const struct bpf_func_proto bpf_skb_change_head_proto = { + .func = bpf_skb_change_head, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + bool bpf_helper_changes_skb_data(void *func) { if (func == bpf_skb_vlan_push || func == bpf_skb_vlan_pop || func == bpf_skb_store_bytes || func == bpf_skb_change_proto || + func == bpf_skb_change_head || func == bpf_skb_change_tail || func == bpf_skb_pull_data || func == bpf_l3_csum_replace || @@ -2639,6 +2686,68 @@ cg_skb_func_proto(enum bpf_func_id func_id) } } +static const struct bpf_func_proto * +lwt_inout_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_skb_load_bytes: + return &bpf_skb_load_bytes_proto; + case BPF_FUNC_skb_pull_data: + return &bpf_skb_pull_data_proto; + case BPF_FUNC_csum_diff: + return &bpf_csum_diff_proto; + case BPF_FUNC_get_cgroup_classid: + return &bpf_get_cgroup_classid_proto; + case BPF_FUNC_get_route_realm: + return &bpf_get_route_realm_proto; + case BPF_FUNC_get_hash_recalc: + return &bpf_get_hash_recalc_proto; + case BPF_FUNC_perf_event_output: + return &bpf_skb_event_output_proto; + case BPF_FUNC_get_smp_processor_id: + return &bpf_get_smp_processor_id_proto; + case BPF_FUNC_skb_under_cgroup: + return &bpf_skb_under_cgroup_proto; + default: + return sk_filter_func_proto(func_id); + } +} + +static const struct bpf_func_proto * +lwt_xmit_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_skb_get_tunnel_key: + return &bpf_skb_get_tunnel_key_proto; + case BPF_FUNC_skb_set_tunnel_key: + return bpf_get_skb_set_tunnel_proto(func_id); + case BPF_FUNC_skb_get_tunnel_opt: + return &bpf_skb_get_tunnel_opt_proto; + case BPF_FUNC_skb_set_tunnel_opt: + return bpf_get_skb_set_tunnel_proto(func_id); + case BPF_FUNC_redirect: + return &bpf_redirect_proto; + case BPF_FUNC_clone_redirect: + return &bpf_clone_redirect_proto; + case BPF_FUNC_skb_change_tail: + return &bpf_skb_change_tail_proto; + case BPF_FUNC_skb_change_head: + return &bpf_skb_change_head_proto; + case BPF_FUNC_skb_store_bytes: + return &bpf_skb_store_bytes_proto; + case BPF_FUNC_csum_update: + return &bpf_csum_update_proto; + case BPF_FUNC_l3_csum_replace: + return &bpf_l3_csum_replace_proto; + case BPF_FUNC_l4_csum_replace: + return &bpf_l4_csum_replace_proto; + case BPF_FUNC_set_hash_invalid: + return &bpf_set_hash_invalid_proto; + default: + return lwt_inout_func_proto(func_id); + } +} + static bool __is_valid_access(int off, int size, enum bpf_access_type type) { if (off < 0 || off >= sizeof(struct __sk_buff)) @@ -2676,6 +2785,39 @@ static bool sk_filter_is_valid_access(int off, int size, return __is_valid_access(off, size, type); } +static bool lwt_is_valid_access(int off, int size, + enum bpf_access_type type, + enum bpf_reg_type *reg_type) +{ + switch (off) { + case offsetof(struct __sk_buff, tc_classid): + return false; + } + + if (type == BPF_WRITE) { + switch (off) { + case offsetof(struct __sk_buff, mark): + case offsetof(struct __sk_buff, priority): + case offsetof(struct __sk_buff, cb[0]) ... + offsetof(struct __sk_buff, cb[4]): + break; + default: + return false; + } + } + + switch (off) { + case offsetof(struct __sk_buff, data): + *reg_type = PTR_TO_PACKET; + break; + case offsetof(struct __sk_buff, data_end): + *reg_type = PTR_TO_PACKET_END; + break; + } + + return __is_valid_access(off, size, type); +} + static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { @@ -3007,6 +3149,19 @@ static const struct bpf_verifier_ops cg_skb_ops = { .convert_ctx_access = sk_filter_convert_ctx_access, }; +static const struct bpf_verifier_ops lwt_inout_ops = { + .get_func_proto = lwt_inout_func_proto, + .is_valid_access = lwt_is_valid_access, + .convert_ctx_access = sk_filter_convert_ctx_access, +}; + +static const struct bpf_verifier_ops lwt_xmit_ops = { + .get_func_proto = lwt_xmit_func_proto, + .is_valid_access = lwt_is_valid_access, + .convert_ctx_access = sk_filter_convert_ctx_access, + .gen_prologue = tc_cls_act_prologue, +}; + static struct bpf_prog_type_list sk_filter_type __read_mostly = { .ops = &sk_filter_ops, .type = BPF_PROG_TYPE_SOCKET_FILTER, @@ -3032,6 +3187,21 @@ static struct bpf_prog_type_list cg_skb_type __read_mostly = { .type = BPF_PROG_TYPE_CGROUP_SKB, }; +static struct bpf_prog_type_list lwt_in_type __read_mostly = { + .ops = &lwt_inout_ops, + .type = BPF_PROG_TYPE_LWT_IN, +}; + +static struct bpf_prog_type_list lwt_out_type __read_mostly = { + .ops = &lwt_inout_ops, + .type = BPF_PROG_TYPE_LWT_OUT, +}; + +static struct bpf_prog_type_list lwt_xmit_type __read_mostly = { + .ops = &lwt_xmit_ops, + .type = BPF_PROG_TYPE_LWT_XMIT, +}; + static int __init register_sk_filter_ops(void) { bpf_register_prog_type(&sk_filter_type); @@ -3039,6 +3209,9 @@ static int __init register_sk_filter_ops(void) bpf_register_prog_type(&sched_act_type); bpf_register_prog_type(&xdp_type); bpf_register_prog_type(&cg_skb_type); + bpf_register_prog_type(&lwt_in_type); + bpf_register_prog_type(&lwt_out_type); + bpf_register_prog_type(&lwt_xmit_type); return 0; } diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c new file mode 100644 index 000000000000..71bb3e2eca08 --- /dev/null +++ b/net/core/lwt_bpf.c @@ -0,0 +1,396 @@ +/* Copyright (c) 2016 Thomas Graf + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#include +#include +#include +#include +#include +#include + +struct bpf_lwt_prog { + struct bpf_prog *prog; + char *name; +}; + +struct bpf_lwt { + struct bpf_lwt_prog in; + struct bpf_lwt_prog out; + struct bpf_lwt_prog xmit; + int family; +}; + +#define MAX_PROG_NAME 256 + +static inline struct bpf_lwt *bpf_lwt_lwtunnel(struct lwtunnel_state *lwt) +{ + return (struct bpf_lwt *)lwt->data; +} + +#define NO_REDIRECT false +#define CAN_REDIRECT true + +static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, + struct dst_entry *dst, bool can_redirect) +{ + int ret; + + /* Preempt disable is needed to protect per-cpu redirect_info between + * BPF prog and skb_do_redirect(). The call_rcu in bpf_prog_put() and + * access to maps strictly require a rcu_read_lock() for protection, + * mixing with BH RCU lock doesn't work. + */ + preempt_disable(); + rcu_read_lock(); + bpf_compute_data_end(skb); + ret = bpf_prog_run_save_cb(lwt->prog, skb); + rcu_read_unlock(); + + switch (ret) { + case BPF_OK: + break; + + case BPF_REDIRECT: + if (unlikely(!can_redirect)) { + pr_warn_once("Illegal redirect return code in prog %s\n", + lwt->name ? : ""); + ret = BPF_OK; + } else { + ret = skb_do_redirect(skb); + if (ret == 0) + ret = BPF_REDIRECT; + } + break; + + case BPF_DROP: + kfree_skb(skb); + ret = -EPERM; + break; + + default: + pr_warn_once("bpf-lwt: Illegal return value %u, expect packet loss\n", ret); + kfree_skb(skb); + ret = -EINVAL; + break; + } + + preempt_enable(); + + return ret; +} + +static int bpf_input(struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct bpf_lwt *bpf; + int ret; + + bpf = bpf_lwt_lwtunnel(dst->lwtstate); + if (bpf->in.prog) { + ret = run_lwt_bpf(skb, &bpf->in, dst, NO_REDIRECT); + if (ret < 0) + return ret; + } + + if (unlikely(!dst->lwtstate->orig_input)) { + pr_warn_once("orig_input not set on dst for prog %s\n", + bpf->out.name); + kfree_skb(skb); + return -EINVAL; + } + + return dst->lwtstate->orig_input(skb); +} + +static int bpf_output(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct bpf_lwt *bpf; + int ret; + + bpf = bpf_lwt_lwtunnel(dst->lwtstate); + if (bpf->out.prog) { + ret = run_lwt_bpf(skb, &bpf->out, dst, NO_REDIRECT); + if (ret < 0) + return ret; + } + + if (unlikely(!dst->lwtstate->orig_output)) { + pr_warn_once("orig_output not set on dst for prog %s\n", + bpf->out.name); + kfree_skb(skb); + return -EINVAL; + } + + return dst->lwtstate->orig_output(net, sk, skb); +} + +static int xmit_check_hhlen(struct sk_buff *skb) +{ + int hh_len = skb_dst(skb)->dev->hard_header_len; + + if (skb_headroom(skb) < hh_len) { + int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb)); + + if (pskb_expand_head(skb, nhead, 0, GFP_ATOMIC)) + return -ENOMEM; + } + + return 0; +} + +static int bpf_xmit(struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct bpf_lwt *bpf; + + bpf = bpf_lwt_lwtunnel(dst->lwtstate); + if (bpf->xmit.prog) { + int ret; + + ret = run_lwt_bpf(skb, &bpf->xmit, dst, CAN_REDIRECT); + switch (ret) { + case BPF_OK: + /* If the header was expanded, headroom might be too + * small for L2 header to come, expand as needed. + */ + ret = xmit_check_hhlen(skb); + if (unlikely(ret)) + return ret; + + return LWTUNNEL_XMIT_CONTINUE; + case BPF_REDIRECT: + return LWTUNNEL_XMIT_DONE; + default: + return ret; + } + } + + return LWTUNNEL_XMIT_CONTINUE; +} + +static void bpf_lwt_prog_destroy(struct bpf_lwt_prog *prog) +{ + if (prog->prog) + bpf_prog_put(prog->prog); + + kfree(prog->name); +} + +static void bpf_destroy_state(struct lwtunnel_state *lwt) +{ + struct bpf_lwt *bpf = bpf_lwt_lwtunnel(lwt); + + bpf_lwt_prog_destroy(&bpf->in); + bpf_lwt_prog_destroy(&bpf->out); + bpf_lwt_prog_destroy(&bpf->xmit); +} + +static const struct nla_policy bpf_prog_policy[LWT_BPF_PROG_MAX + 1] = { + [LWT_BPF_PROG_FD] = { .type = NLA_U32, }, + [LWT_BPF_PROG_NAME] = { .type = NLA_NUL_STRING, + .len = MAX_PROG_NAME }, +}; + +static int bpf_parse_prog(struct nlattr *attr, struct bpf_lwt_prog *prog, + enum bpf_prog_type type) +{ + struct nlattr *tb[LWT_BPF_PROG_MAX + 1]; + struct bpf_prog *p; + int ret; + u32 fd; + + ret = nla_parse_nested(tb, LWT_BPF_PROG_MAX, attr, bpf_prog_policy); + if (ret < 0) + return ret; + + if (!tb[LWT_BPF_PROG_FD] || !tb[LWT_BPF_PROG_NAME]) + return -EINVAL; + + prog->name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_KERNEL); + if (!prog->name) + return -ENOMEM; + + fd = nla_get_u32(tb[LWT_BPF_PROG_FD]); + p = bpf_prog_get_type(fd, type); + if (IS_ERR(p)) + return PTR_ERR(p); + + prog->prog = p; + + return 0; +} + +static const struct nla_policy bpf_nl_policy[LWT_BPF_MAX + 1] = { + [LWT_BPF_IN] = { .type = NLA_NESTED, }, + [LWT_BPF_OUT] = { .type = NLA_NESTED, }, + [LWT_BPF_XMIT] = { .type = NLA_NESTED, }, + [LWT_BPF_XMIT_HEADROOM] = { .type = NLA_U32 }, +}; + +static int bpf_build_state(struct net_device *dev, struct nlattr *nla, + unsigned int family, const void *cfg, + struct lwtunnel_state **ts) +{ + struct nlattr *tb[LWT_BPF_MAX + 1]; + struct lwtunnel_state *newts; + struct bpf_lwt *bpf; + int ret; + + if (family != AF_INET && family != AF_INET6) + return -EAFNOSUPPORT; + + ret = nla_parse_nested(tb, LWT_BPF_MAX, nla, bpf_nl_policy); + if (ret < 0) + return ret; + + if (!tb[LWT_BPF_IN] && !tb[LWT_BPF_OUT] && !tb[LWT_BPF_XMIT]) + return -EINVAL; + + newts = lwtunnel_state_alloc(sizeof(*bpf)); + if (!newts) + return -ENOMEM; + + newts->type = LWTUNNEL_ENCAP_BPF; + bpf = bpf_lwt_lwtunnel(newts); + + if (tb[LWT_BPF_IN]) { + newts->flags |= LWTUNNEL_STATE_INPUT_REDIRECT; + ret = bpf_parse_prog(tb[LWT_BPF_IN], &bpf->in, + BPF_PROG_TYPE_LWT_IN); + if (ret < 0) + goto errout; + } + + if (tb[LWT_BPF_OUT]) { + newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT; + ret = bpf_parse_prog(tb[LWT_BPF_OUT], &bpf->out, + BPF_PROG_TYPE_LWT_OUT); + if (ret < 0) + goto errout; + } + + if (tb[LWT_BPF_XMIT]) { + newts->flags |= LWTUNNEL_STATE_XMIT_REDIRECT; + ret = bpf_parse_prog(tb[LWT_BPF_XMIT], &bpf->xmit, + BPF_PROG_TYPE_LWT_XMIT); + if (ret < 0) + goto errout; + } + + if (tb[LWT_BPF_XMIT_HEADROOM]) { + u32 headroom = nla_get_u32(tb[LWT_BPF_XMIT_HEADROOM]); + + if (headroom > LWT_BPF_MAX_HEADROOM) { + ret = -ERANGE; + goto errout; + } + + newts->headroom = headroom; + } + + bpf->family = family; + *ts = newts; + + return 0; + +errout: + bpf_destroy_state(newts); + kfree(newts); + return ret; +} + +static int bpf_fill_lwt_prog(struct sk_buff *skb, int attr, + struct bpf_lwt_prog *prog) +{ + struct nlattr *nest; + + if (!prog->prog) + return 0; + + nest = nla_nest_start(skb, attr); + if (!nest) + return -EMSGSIZE; + + if (prog->name && + nla_put_string(skb, LWT_BPF_PROG_NAME, prog->name)) + return -EMSGSIZE; + + return nla_nest_end(skb, nest); +} + +static int bpf_fill_encap_info(struct sk_buff *skb, struct lwtunnel_state *lwt) +{ + struct bpf_lwt *bpf = bpf_lwt_lwtunnel(lwt); + + if (bpf_fill_lwt_prog(skb, LWT_BPF_IN, &bpf->in) < 0 || + bpf_fill_lwt_prog(skb, LWT_BPF_OUT, &bpf->out) < 0 || + bpf_fill_lwt_prog(skb, LWT_BPF_XMIT, &bpf->xmit) < 0) + return -EMSGSIZE; + + return 0; +} + +static int bpf_encap_nlsize(struct lwtunnel_state *lwtstate) +{ + int nest_len = nla_total_size(sizeof(struct nlattr)) + + nla_total_size(MAX_PROG_NAME) + /* LWT_BPF_PROG_NAME */ + 0; + + return nest_len + /* LWT_BPF_IN */ + nest_len + /* LWT_BPF_OUT */ + nest_len + /* LWT_BPF_XMIT */ + 0; +} + +int bpf_lwt_prog_cmp(struct bpf_lwt_prog *a, struct bpf_lwt_prog *b) +{ + /* FIXME: + * The LWT state is currently rebuilt for delete requests which + * results in a new bpf_prog instance. Comparing names for now. + */ + if (!a->name && !b->name) + return 0; + + if (!a->name || !b->name) + return 1; + + return strcmp(a->name, b->name); +} + +static int bpf_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) +{ + struct bpf_lwt *a_bpf = bpf_lwt_lwtunnel(a); + struct bpf_lwt *b_bpf = bpf_lwt_lwtunnel(b); + + return bpf_lwt_prog_cmp(&a_bpf->in, &b_bpf->in) || + bpf_lwt_prog_cmp(&a_bpf->out, &b_bpf->out) || + bpf_lwt_prog_cmp(&a_bpf->xmit, &b_bpf->xmit); +} + +static const struct lwtunnel_encap_ops bpf_encap_ops = { + .build_state = bpf_build_state, + .destroy_state = bpf_destroy_state, + .input = bpf_input, + .output = bpf_output, + .xmit = bpf_xmit, + .fill_encap = bpf_fill_encap_info, + .get_encap_size = bpf_encap_nlsize, + .cmp_encap = bpf_encap_cmp, +}; + +static int __init bpf_lwt_init(void) +{ + return lwtunnel_encap_add_ops(&bpf_encap_ops, LWTUNNEL_ENCAP_BPF); +} + +subsys_initcall(bpf_lwt_init) diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 03976e939818..a5d4e866ce88 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -41,6 +41,8 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type) return "ILA"; case LWTUNNEL_ENCAP_SEG6: return "SEG6"; + case LWTUNNEL_ENCAP_BPF: + return "BPF"; case LWTUNNEL_ENCAP_IP6: case LWTUNNEL_ENCAP_IP: case LWTUNNEL_ENCAP_NONE: -- cgit v1.2.3 From 61023658760032e97869b07d54be9681d2529e77 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 1 Dec 2016 08:48:04 -0800 Subject: bpf: Add new cgroup attach type to enable sock modifications Add new cgroup based program type, BPF_PROG_TYPE_CGROUP_SOCK. Similar to BPF_PROG_TYPE_CGROUP_SKB programs can be attached to a cgroup and run any time a process in the cgroup opens an AF_INET or AF_INET6 socket. Currently only sk_bound_dev_if is exported to userspace for modification by a bpf program. This allows a cgroup to be configured such that AF_INET{6} sockets opened by processes are automatically bound to a specific device. In turn, this enables the running of programs that do not support SO_BINDTODEVICE in a specific VRF context / L3 domain. Signed-off-by: David Ahern Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf-cgroup.h | 14 +++++++++++ include/uapi/linux/bpf.h | 6 +++++ kernel/bpf/cgroup.c | 33 ++++++++++++++++++++++++ kernel/bpf/syscall.c | 5 +++- net/core/filter.c | 62 ++++++++++++++++++++++++++++++++++++++++++++++ net/ipv4/af_inet.c | 12 ++++++++- net/ipv6/af_inet6.c | 8 ++++++ 7 files changed, 138 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index af2ca8b432c0..7b6e5d168c95 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -40,6 +40,9 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, enum bpf_attach_type type); +int __cgroup_bpf_run_filter_sk(struct sock *sk, + enum bpf_attach_type type); + /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ @@ -63,6 +66,16 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, __ret; \ }) +#define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled && sk) { \ + __ret = __cgroup_bpf_run_filter_sk(sk, \ + BPF_CGROUP_INET_SOCK_CREATE); \ + } \ + __ret; \ +}) + #else struct cgroup_bpf {}; @@ -72,6 +85,7 @@ static inline void cgroup_bpf_inherit(struct cgroup *cgrp, #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) #endif /* CONFIG_CGROUP_BPF */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 22ac82792687..bfe5e31a1288 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -101,6 +101,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_XDP, BPF_PROG_TYPE_PERF_EVENT, BPF_PROG_TYPE_CGROUP_SKB, + BPF_PROG_TYPE_CGROUP_SOCK, BPF_PROG_TYPE_LWT_IN, BPF_PROG_TYPE_LWT_OUT, BPF_PROG_TYPE_LWT_XMIT, @@ -109,6 +110,7 @@ enum bpf_prog_type { enum bpf_attach_type { BPF_CGROUP_INET_INGRESS, BPF_CGROUP_INET_EGRESS, + BPF_CGROUP_INET_SOCK_CREATE, __MAX_BPF_ATTACH_TYPE }; @@ -567,6 +569,10 @@ enum bpf_ret_code { /* >127 are reserved for prog type specific return codes */ }; +struct bpf_sock { + __u32 bound_dev_if; +}; + /* User return codes for XDP prog type. * A valid XDP program must return one of these defined values. All other * return codes are reserved for future use. Unknown return codes will result diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 8fe55ffd109d..a515f7b007c6 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -165,3 +165,36 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, return ret; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb); + +/** + * __cgroup_bpf_run_filter_sk() - Run a program on a sock + * @sk: sock structure to manipulate + * @type: The type of program to be exectuted + * + * socket is passed is expected to be of type INET or INET6. + * + * The program type passed in via @type must be suitable for sock + * filtering. No further check is performed to assert that. + * + * This function will return %-EPERM if any if an attached program was found + * and if it returned != 1 during execution. In all other cases, 0 is returned. + */ +int __cgroup_bpf_run_filter_sk(struct sock *sk, + enum bpf_attach_type type) +{ + struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + struct bpf_prog *prog; + int ret = 0; + + + rcu_read_lock(); + + prog = rcu_dereference(cgrp->bpf.effective[type]); + if (prog) + ret = BPF_PROG_RUN(prog, sk) == 1 ? 0 : -EPERM; + + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5518a6839ab1..85af86c496cd 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -869,7 +869,9 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_CGROUP_INET_EGRESS: ptype = BPF_PROG_TYPE_CGROUP_SKB; break; - + case BPF_CGROUP_INET_SOCK_CREATE: + ptype = BPF_PROG_TYPE_CGROUP_SOCK; + break; default: return -EINVAL; } @@ -905,6 +907,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) switch (attr->attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: + case BPF_CGROUP_INET_SOCK_CREATE: cgrp = cgroup_get_from_fd(attr->target_fd); if (IS_ERR(cgrp)) return PTR_ERR(cgrp); diff --git a/net/core/filter.c b/net/core/filter.c index 1c4d0faf22c8..0ab252e462aa 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2818,6 +2818,32 @@ static bool lwt_is_valid_access(int off, int size, return __is_valid_access(off, size, type); } +static bool sock_filter_is_valid_access(int off, int size, + enum bpf_access_type type, + enum bpf_reg_type *reg_type) +{ + if (type == BPF_WRITE) { + switch (off) { + case offsetof(struct bpf_sock, bound_dev_if): + break; + default: + return false; + } + } + + if (off < 0 || off + size > sizeof(struct bpf_sock)) + return false; + + /* The verifier guarantees that size > 0. */ + if (off % size != 0) + return false; + + if (size != sizeof(__u32)) + return false; + + return true; +} + static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { @@ -3076,6 +3102,30 @@ static u32 sk_filter_convert_ctx_access(enum bpf_access_type type, int dst_reg, return insn - insn_buf; } +static u32 sock_filter_convert_ctx_access(enum bpf_access_type type, + int dst_reg, int src_reg, + int ctx_off, + struct bpf_insn *insn_buf, + struct bpf_prog *prog) +{ + struct bpf_insn *insn = insn_buf; + + switch (ctx_off) { + case offsetof(struct bpf_sock, bound_dev_if): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_bound_dev_if) != 4); + + if (type == BPF_WRITE) + *insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sock, sk_bound_dev_if)); + else + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sock, sk_bound_dev_if)); + break; + } + + return insn - insn_buf; +} + static u32 tc_cls_act_convert_ctx_access(enum bpf_access_type type, int dst_reg, int src_reg, int ctx_off, struct bpf_insn *insn_buf, @@ -3162,6 +3212,12 @@ static const struct bpf_verifier_ops lwt_xmit_ops = { .gen_prologue = tc_cls_act_prologue, }; +static const struct bpf_verifier_ops cg_sock_ops = { + .get_func_proto = sk_filter_func_proto, + .is_valid_access = sock_filter_is_valid_access, + .convert_ctx_access = sock_filter_convert_ctx_access, +}; + static struct bpf_prog_type_list sk_filter_type __read_mostly = { .ops = &sk_filter_ops, .type = BPF_PROG_TYPE_SOCKET_FILTER, @@ -3202,6 +3258,11 @@ static struct bpf_prog_type_list lwt_xmit_type __read_mostly = { .type = BPF_PROG_TYPE_LWT_XMIT, }; +static struct bpf_prog_type_list cg_sock_type __read_mostly = { + .ops = &cg_sock_ops, + .type = BPF_PROG_TYPE_CGROUP_SOCK +}; + static int __init register_sk_filter_ops(void) { bpf_register_prog_type(&sk_filter_type); @@ -3209,6 +3270,7 @@ static int __init register_sk_filter_ops(void) bpf_register_prog_type(&sched_act_type); bpf_register_prog_type(&xdp_type); bpf_register_prog_type(&cg_skb_type); + bpf_register_prog_type(&cg_sock_type); bpf_register_prog_type(&lwt_in_type); bpf_register_prog_type(&lwt_out_type); bpf_register_prog_type(&lwt_xmit_type); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 5ddf5cda07f4..24d2550492ee 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -374,8 +374,18 @@ lookup_protocol: if (sk->sk_prot->init) { err = sk->sk_prot->init(sk); - if (err) + if (err) { + sk_common_release(sk); + goto out; + } + } + + if (!kern) { + err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk); + if (err) { sk_common_release(sk); + goto out; + } } out: return err; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index d424f3a3737a..237e654ba717 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -258,6 +258,14 @@ lookup_protocol: goto out; } } + + if (!kern) { + err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk); + if (err) { + sk_common_release(sk); + goto out; + } + } out: return err; out_rcu_unlock: -- cgit v1.2.3 From aa4c1037a30f4e88f444e83d42c2befbe0d5caf5 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 1 Dec 2016 08:48:06 -0800 Subject: bpf: Add support for reading socket family, type, protocol Add socket family, type and protocol to bpf_sock allowing bpf programs read-only access. Add __sk_flags_offset[0] to struct sock before the bitfield to programmtically determine the offset of the unsigned int containing protocol and type. Signed-off-by: David Ahern Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/net/sock.h | 15 +++++++++++++++ include/uapi/linux/bpf.h | 3 +++ net/core/filter.c | 21 +++++++++++++++++++++ 3 files changed, 39 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/sock.h b/include/net/sock.h index 442cbb118a07..69afda6bea15 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -389,6 +389,21 @@ struct sock { * Because of non atomicity rules, all * changes are protected by socket lock. */ + unsigned int __sk_flags_offset[0]; +#ifdef __BIG_ENDIAN_BITFIELD +#define SK_FL_PROTO_SHIFT 16 +#define SK_FL_PROTO_MASK 0x00ff0000 + +#define SK_FL_TYPE_SHIFT 0 +#define SK_FL_TYPE_MASK 0x0000ffff +#else +#define SK_FL_PROTO_SHIFT 8 +#define SK_FL_PROTO_MASK 0x0000ff00 + +#define SK_FL_TYPE_SHIFT 16 +#define SK_FL_TYPE_MASK 0xffff0000 +#endif + kmemcheck_bitfield_begin(flags); unsigned int sk_padding : 2, sk_no_check_tx : 1, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bfe5e31a1288..6123d9b8e828 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -571,6 +571,9 @@ enum bpf_ret_code { struct bpf_sock { __u32 bound_dev_if; + __u32 family; + __u32 type; + __u32 protocol; }; /* User return codes for XDP prog type. diff --git a/net/core/filter.c b/net/core/filter.c index 0ab252e462aa..56b43587d200 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3121,6 +3121,27 @@ static u32 sock_filter_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, offsetof(struct sock, sk_bound_dev_if)); break; + + case offsetof(struct bpf_sock, family): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_family) != 2); + + *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, + offsetof(struct sock, sk_family)); + break; + + case offsetof(struct bpf_sock, type): + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sock, __sk_flags_offset)); + *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, SK_FL_TYPE_MASK); + *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, SK_FL_TYPE_SHIFT); + break; + + case offsetof(struct bpf_sock, protocol): + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sock, __sk_flags_offset)); + *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, SK_FL_PROTO_MASK); + *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, SK_FL_PROTO_SHIFT); + break; } return insn - insn_buf; -- cgit v1.2.3 From adc176c5472214971d77c1a61c83db9b01e9cdc7 Mon Sep 17 00:00:00 2001 From: Erik Nordmark Date: Fri, 2 Dec 2016 14:00:08 -0800 Subject: ipv6 addrconf: Implemented enhanced DAD (RFC7527) Implemented RFC7527 Enhanced DAD. IPv6 duplicate address detection can fail if there is some temporary loopback of Ethernet frames. RFC7527 solves this by including a random nonce in the NS messages used for DAD, and if an NS is received with the same nonce it is assumed to be a looped back DAD probe and is ignored. RFC7527 is enabled by default. Can be disabled by setting both of conf/{all,interface}/enhanced_dad to zero. Signed-off-by: Erik Nordmark Signed-off-by: Bob Gilligan Reviewed-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 9 +++++++++ include/linux/ipv6.h | 1 + include/net/if_inet6.h | 1 + include/net/ndisc.h | 5 ++++- include/uapi/linux/ipv6.h | 1 + net/ipv6/addrconf.c | 22 +++++++++++++++++++++- net/ipv6/ndisc.c | 29 ++++++++++++++++++++++++++--- net/ipv6/route.c | 2 +- 8 files changed, 64 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 5ca567fa6b8c..7dd65c9cf707 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1734,6 +1734,15 @@ drop_unsolicited_na - BOOLEAN By default this is turned off. +enhanced_dad - BOOLEAN + Include a nonce option in the IPv6 neighbor solicitation messages used for + duplicate address detection per RFC7527. A received DAD NS will only signal + a duplicate address if the nonce is different. This avoids any false + detection of duplicates due to loopback of the NS messages that we send. + The nonce option will be sent on an interface unless both of + conf/{all,interface}/enhanced_dad are set to FALSE. + Default: TRUE + icmp/*: ratelimit - INTEGER Limit the maximal rates for sending ICMPv6 packets. diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 3f95233b2733..671d014e6429 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -68,6 +68,7 @@ struct ipv6_devconf { #ifdef CONFIG_IPV6_SEG6_HMAC __s32 seg6_require_hmac; #endif + __u32 enhanced_dad; struct ctl_table_header *sysctl_header; }; diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index b0576cb2ab25..0fa4c324b713 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -55,6 +55,7 @@ struct inet6_ifaddr { __u8 stable_privacy_retry; __u16 scope; + __u64 dad_nonce; unsigned long cstamp; /* created timestamp */ unsigned long tstamp; /* updated timestamp */ diff --git a/include/net/ndisc.h b/include/net/ndisc.h index be1fe2283254..d562a2fe4860 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -31,6 +31,7 @@ enum { ND_OPT_PREFIX_INFO = 3, /* RFC2461 */ ND_OPT_REDIRECT_HDR = 4, /* RFC2461 */ ND_OPT_MTU = 5, /* RFC2461 */ + ND_OPT_NONCE = 14, /* RFC7527 */ __ND_OPT_ARRAY_MAX, ND_OPT_ROUTE_INFO = 24, /* RFC4191 */ ND_OPT_RDNSS = 25, /* RFC5006 */ @@ -121,6 +122,7 @@ struct ndisc_options { #define nd_opts_pi_end nd_opt_array[__ND_OPT_PREFIX_INFO_END] #define nd_opts_rh nd_opt_array[ND_OPT_REDIRECT_HDR] #define nd_opts_mtu nd_opt_array[ND_OPT_MTU] +#define nd_opts_nonce nd_opt_array[ND_OPT_NONCE] #define nd_802154_opts_src_lladdr nd_802154_opt_array[ND_OPT_SOURCE_LL_ADDR] #define nd_802154_opts_tgt_lladdr nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR] @@ -398,7 +400,8 @@ void ndisc_cleanup(void); int ndisc_rcv(struct sk_buff *skb); void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, - const struct in6_addr *daddr, const struct in6_addr *saddr); + const struct in6_addr *daddr, const struct in6_addr *saddr, + u64 nonce); void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr); diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 53561be1ac21..eaf65dc82e22 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -181,6 +181,7 @@ enum { DEVCONF_RTR_SOLICIT_MAX_INTERVAL, DEVCONF_SEG6_ENABLED, DEVCONF_SEG6_REQUIRE_HMAC, + DEVCONF_ENHANCED_DAD, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 4c387dc338e3..c1e124bc8e1e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -242,6 +242,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { #ifdef CONFIG_IPV6_SEG6_HMAC .seg6_require_hmac = 0, #endif + .enhanced_dad = 1, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -292,6 +293,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { #ifdef CONFIG_IPV6_SEG6_HMAC .seg6_require_hmac = 0, #endif + .enhanced_dad = 1, }; /* Check if a valid qdisc is available */ @@ -3735,12 +3737,21 @@ static void addrconf_dad_kick(struct inet6_ifaddr *ifp) { unsigned long rand_num; struct inet6_dev *idev = ifp->idev; + u64 nonce; if (ifp->flags & IFA_F_OPTIMISTIC) rand_num = 0; else rand_num = prandom_u32() % (idev->cnf.rtr_solicit_delay ? : 1); + nonce = 0; + if (idev->cnf.enhanced_dad || + dev_net(idev->dev)->ipv6.devconf_all->enhanced_dad) { + do + get_random_bytes(&nonce, 6); + while (nonce == 0); + } + ifp->dad_nonce = nonce; ifp->dad_probes = idev->cnf.dad_transmits; addrconf_mod_dad_work(ifp, rand_num); } @@ -3918,7 +3929,8 @@ static void addrconf_dad_work(struct work_struct *w) /* send a neighbour solicitation for our addr */ addrconf_addr_solict_mult(&ifp->addr, &mcaddr); - ndisc_send_ns(ifp->idev->dev, &ifp->addr, &mcaddr, &in6addr_any); + ndisc_send_ns(ifp->idev->dev, &ifp->addr, &mcaddr, &in6addr_any, + ifp->dad_nonce); out: in6_ifa_put(ifp); rtnl_unlock(); @@ -4962,6 +4974,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, #ifdef CONFIG_IPV6_SEG6_HMAC array[DEVCONF_SEG6_REQUIRE_HMAC] = cnf->seg6_require_hmac; #endif + array[DEVCONF_ENHANCED_DAD] = cnf->enhanced_dad; } static inline size_t inet6_ifla6_size(void) @@ -6069,6 +6082,13 @@ static const struct ctl_table addrconf_sysctl[] = { .proc_handler = proc_dointvec, }, #endif + { + .procname = "enhanced_dad", + .data = &ipv6_devconf.enhanced_dad, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { /* sentinel */ } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index d8e671457d10..7ebac630d3c6 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -233,6 +233,7 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev, case ND_OPT_SOURCE_LL_ADDR: case ND_OPT_TARGET_LL_ADDR: case ND_OPT_MTU: + case ND_OPT_NONCE: case ND_OPT_REDIRECT_HDR: if (ndopts->nd_opt_array[nd_opt->nd_opt_type]) { ND_PRINTK(2, warn, @@ -568,7 +569,8 @@ static void ndisc_send_unsol_na(struct net_device *dev) } void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, - const struct in6_addr *daddr, const struct in6_addr *saddr) + const struct in6_addr *daddr, const struct in6_addr *saddr, + u64 nonce) { struct sk_buff *skb; struct in6_addr addr_buf; @@ -588,6 +590,8 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, if (inc_opt) optlen += ndisc_opt_addr_space(dev, NDISC_NEIGHBOUR_SOLICITATION); + if (nonce != 0) + optlen += 8; skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) @@ -605,6 +609,13 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, dev->dev_addr, NDISC_NEIGHBOUR_SOLICITATION); + if (nonce != 0) { + u8 *opt = skb_put(skb, 8); + + opt[0] = ND_OPT_NONCE; + opt[1] = 8 >> 3; + memcpy(opt + 2, &nonce, 6); + } ndisc_send_skb(skb, daddr, saddr); } @@ -693,12 +704,12 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) "%s: trying to ucast probe in NUD_INVALID: %pI6\n", __func__, target); } - ndisc_send_ns(dev, target, target, saddr); + ndisc_send_ns(dev, target, target, saddr, 0); } else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) { neigh_app_ns(neigh); } else { addrconf_addr_solict_mult(target, &mcaddr); - ndisc_send_ns(dev, target, &mcaddr, saddr); + ndisc_send_ns(dev, target, &mcaddr, saddr, 0); } } @@ -742,6 +753,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) int dad = ipv6_addr_any(saddr); bool inc; int is_router = -1; + u64 nonce = 0; if (skb->len < sizeof(struct nd_msg)) { ND_PRINTK(2, warn, "NS: packet too short\n"); @@ -786,6 +798,8 @@ static void ndisc_recv_ns(struct sk_buff *skb) return; } } + if (ndopts.nd_opts_nonce) + memcpy(&nonce, (u8 *)(ndopts.nd_opts_nonce + 1), 6); inc = ipv6_addr_is_multicast(daddr); @@ -794,6 +808,15 @@ static void ndisc_recv_ns(struct sk_buff *skb) have_ifp: if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) { if (dad) { + if (nonce != 0 && ifp->dad_nonce == nonce) { + u8 *np = (u8 *)&nonce; + /* Matching nonce if looped back */ + ND_PRINTK(2, notice, + "%s: IPv6 DAD loopback for address %pI6c nonce %pM ignored\n", + ifp->idev->dev->name, + &ifp->addr, np); + goto out; + } /* * We are colliding with another node * who is doing DAD diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b317bb135ed4..aac7818e2e0f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -527,7 +527,7 @@ static void rt6_probe_deferred(struct work_struct *w) container_of(w, struct __rt6_probe_work, work); addrconf_addr_solict_mult(&work->target, &mcaddr); - ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL); + ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, 0); dev_put(work->dev); kfree(work); } -- cgit v1.2.3 From 3fefeb88d002850e591339fed291eb6a795d9f21 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Tue, 15 Nov 2016 15:08:24 +0100 Subject: netfilter: nf_conntrack_tuple_common.h: fix #include To allow usage of enum ip_conntrack_dir in include/net/netns/conntrack.h, this patch encloses #include in a #ifndef __KERNEL__ directive, so that compiler errors caused by unwanted inclusion of include/linux/netfilter.h are avoided. In addition, #include line has been added to resolve correctly CTINFO2DIR macro. Signed-off-by: Davide Caratti Acked-by: Mikko Rapeli Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_conntrack_tuple_common.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_conntrack_tuple_common.h b/include/uapi/linux/netfilter/nf_conntrack_tuple_common.h index a9c3834abdd4..526b42496b78 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_tuple_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_tuple_common.h @@ -2,7 +2,10 @@ #define _NF_CONNTRACK_TUPLE_COMMON_H #include +#ifndef __KERNEL__ #include +#endif +#include /* IP_CT_IS_REPLY */ enum ip_conntrack_dir { IP_CT_DIR_ORIGINAL, -- cgit v1.2.3 From 7bd509e311f408f7a5132fcdde2069af65fa05ae Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 4 Dec 2016 23:19:41 +0100 Subject: bpf: add prog_digest and expose it via fdinfo/netlink When loading a BPF program via bpf(2), calculate the digest over the program's instruction stream and store it in struct bpf_prog's digest member. This is done at a point in time before any instructions are rewritten by the verifier. Any unstable map file descriptor number part of the imm field will be zeroed for the hash. fdinfo example output for progs: # cat /proc/1590/fdinfo/5 pos: 0 flags: 02000002 mnt_id: 11 prog_type: 1 prog_jited: 1 prog_digest: b27e8b06da22707513aa97363dfb11c7c3675d28 memlock: 4096 When programs are pinned and retrieved by an ELF loader, the loader can check the program's digest through fdinfo and compare it against one that was generated over the ELF file's program section to see if the program needs to be reloaded. Furthermore, this can also be exposed through other means such as netlink in case of a tc cls/act dump (or xdp in future), but also through tracepoints or other facilities to identify the program. Other than that, the digest can also serve as a base name for the work in progress kallsyms support of programs. The digest doesn't depend/select the crypto layer, since we need to keep dependencies to a minimum. iproute2 will get support for this facility. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/linux/filter.h | 7 +++- include/uapi/linux/pkt_cls.h | 1 + include/uapi/linux/tc_act/tc_bpf.h | 1 + kernel/bpf/core.c | 65 ++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 24 +++++++++++++- kernel/bpf/verifier.c | 2 ++ net/sched/act_bpf.c | 9 ++++++ net/sched/cls_bpf.c | 8 +++++ 9 files changed, 116 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 69d0a7f12a3b..8796ff03f472 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -216,6 +216,7 @@ u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5); u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); +void bpf_prog_calc_digest(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); diff --git a/include/linux/filter.h b/include/linux/filter.h index 97338134398f..f078d2b1cff6 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -14,6 +14,7 @@ #include #include #include +#include #include @@ -56,6 +57,9 @@ struct bpf_prog_aux; /* BPF program can access up to 512 bytes of stack space. */ #define MAX_BPF_STACK 512 +/* Maximum BPF program size in bytes. */ +#define MAX_BPF_SIZE (BPF_MAXINSNS * sizeof(struct bpf_insn)) + /* Helper macros for filter block array initializers. */ /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ @@ -404,8 +408,9 @@ struct bpf_prog { cb_access:1, /* Is control block accessed? */ dst_needed:1; /* Do we need dst entry? */ kmemcheck_bitfield_end(meta); - u32 len; /* Number of filter blocks */ enum bpf_prog_type type; /* Type of BPF program */ + u32 len; /* Number of filter blocks */ + u32 digest[SHA_DIGEST_WORDS]; /* Program digest */ struct bpf_prog_aux *aux; /* Auxiliary fields */ struct sock_fprog_kern *orig_prog; /* Original BPF program */ unsigned int (*bpf_func)(const void *ctx, diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 86786d45ee66..1adc0b654996 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -397,6 +397,7 @@ enum { TCA_BPF_NAME, TCA_BPF_FLAGS, TCA_BPF_FLAGS_GEN, + TCA_BPF_DIGEST, __TCA_BPF_MAX, }; diff --git a/include/uapi/linux/tc_act/tc_bpf.h b/include/uapi/linux/tc_act/tc_bpf.h index 063d9d465119..a6b88a6f7f71 100644 --- a/include/uapi/linux/tc_act/tc_bpf.h +++ b/include/uapi/linux/tc_act/tc_bpf.h @@ -27,6 +27,7 @@ enum { TCA_ACT_BPF_FD, TCA_ACT_BPF_NAME, TCA_ACT_BPF_PAD, + TCA_ACT_BPF_DIGEST, __TCA_ACT_BPF_MAX, }; #define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 82a04143368e..bdcc9f4ba767 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -136,6 +136,71 @@ void __bpf_prog_free(struct bpf_prog *fp) vfree(fp); } +#define SHA_BPF_RAW_SIZE \ + round_up(MAX_BPF_SIZE + sizeof(__be64) + 1, SHA_MESSAGE_BYTES) + +/* Called under verifier mutex. */ +void bpf_prog_calc_digest(struct bpf_prog *fp) +{ + const u32 bits_offset = SHA_MESSAGE_BYTES - sizeof(__be64); + static u32 ws[SHA_WORKSPACE_WORDS]; + static u8 raw[SHA_BPF_RAW_SIZE]; + struct bpf_insn *dst = (void *)raw; + u32 i, bsize, psize, blocks; + bool was_ld_map; + u8 *todo = raw; + __be32 *result; + __be64 *bits; + + sha_init(fp->digest); + memset(ws, 0, sizeof(ws)); + + /* We need to take out the map fd for the digest calculation + * since they are unstable from user space side. + */ + for (i = 0, was_ld_map = false; i < fp->len; i++) { + dst[i] = fp->insnsi[i]; + if (!was_ld_map && + dst[i].code == (BPF_LD | BPF_IMM | BPF_DW) && + dst[i].src_reg == BPF_PSEUDO_MAP_FD) { + was_ld_map = true; + dst[i].imm = 0; + } else if (was_ld_map && + dst[i].code == 0 && + dst[i].dst_reg == 0 && + dst[i].src_reg == 0 && + dst[i].off == 0) { + was_ld_map = false; + dst[i].imm = 0; + } else { + was_ld_map = false; + } + } + + psize = fp->len * sizeof(struct bpf_insn); + memset(&raw[psize], 0, sizeof(raw) - psize); + raw[psize++] = 0x80; + + bsize = round_up(psize, SHA_MESSAGE_BYTES); + blocks = bsize / SHA_MESSAGE_BYTES; + if (bsize - psize >= sizeof(__be64)) { + bits = (__be64 *)(todo + bsize - sizeof(__be64)); + } else { + bits = (__be64 *)(todo + bsize + bits_offset); + blocks++; + } + *bits = cpu_to_be64((psize - 1) << 3); + + while (blocks--) { + sha_transform(fp->digest, todo, ws); + todo += SHA_MESSAGE_BYTES; + } + + result = (__force __be32 *)fp->digest; + for (i = 0; i < SHA_DIGEST_WORDS; i++) + result[i] = cpu_to_be32(fp->digest[i]); +} + static bool bpf_is_jmp_and_has_target(const struct bpf_insn *insn) { return BPF_CLASS(insn->code) == BPF_JMP && diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 85af86c496cd..c0d2b423ce93 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -662,8 +662,30 @@ static int bpf_prog_release(struct inode *inode, struct file *filp) return 0; } +#ifdef CONFIG_PROC_FS +static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) +{ + const struct bpf_prog *prog = filp->private_data; + char prog_digest[sizeof(prog->digest) * 2 + 1] = { }; + + bin2hex(prog_digest, prog->digest, sizeof(prog->digest)); + seq_printf(m, + "prog_type:\t%u\n" + "prog_jited:\t%u\n" + "prog_digest:\t%s\n" + "memlock:\t%llu\n", + prog->type, + prog->jited, + prog_digest, + prog->pages * 1ULL << PAGE_SHIFT); +} +#endif + static const struct file_operations bpf_prog_fops = { - .release = bpf_prog_release, +#ifdef CONFIG_PROC_FS + .show_fdinfo = bpf_prog_show_fdinfo, +#endif + .release = bpf_prog_release, }; int bpf_prog_new_fd(struct bpf_prog *prog) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 38d05da84a49..cb37339ca0da 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3176,6 +3176,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) log_level = 0; } + bpf_prog_calc_digest(env->prog); + ret = replace_map_fd_with_map_ptr(env); if (ret < 0) goto skip_full_check; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 84c1d2da4f8b..1c60317f0121 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -117,10 +117,19 @@ static int tcf_bpf_dump_bpf_info(const struct tcf_bpf *prog, static int tcf_bpf_dump_ebpf_info(const struct tcf_bpf *prog, struct sk_buff *skb) { + struct nlattr *nla; + if (prog->bpf_name && nla_put_string(skb, TCA_ACT_BPF_NAME, prog->bpf_name)) return -EMSGSIZE; + nla = nla_reserve(skb, TCA_ACT_BPF_DIGEST, + sizeof(prog->filter->digest)); + if (nla == NULL) + return -EMSGSIZE; + + memcpy(nla_data(nla), prog->filter->digest, nla_len(nla)); + return 0; } diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index f70e03d2d2c8..adc776048d1a 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -549,10 +549,18 @@ static int cls_bpf_dump_bpf_info(const struct cls_bpf_prog *prog, static int cls_bpf_dump_ebpf_info(const struct cls_bpf_prog *prog, struct sk_buff *skb) { + struct nlattr *nla; + if (prog->bpf_name && nla_put_string(skb, TCA_BPF_NAME, prog->bpf_name)) return -EMSGSIZE; + nla = nla_reserve(skb, TCA_BPF_DIGEST, sizeof(prog->filter->digest)); + if (nla == NULL) + return -EMSGSIZE; + + memcpy(nla_data(nla), prog->filter->digest, nla_len(nla)); + return 0; } -- cgit v1.2.3 From ad558858295726cb876b78d1c39d471372f1901a Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Fri, 2 Dec 2016 14:53:59 -0800 Subject: uapi: export tc_skbmod.h Fixes commit 735cffe5d800 ("net_sched: Introduce skbmod action") Not used by iproute2 but maybe in future. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/uapi/linux/tc_act/Kbuild | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tc_act/Kbuild b/include/uapi/linux/tc_act/Kbuild index 9611c7b6c18f..e3db7403296f 100644 --- a/include/uapi/linux/tc_act/Kbuild +++ b/include/uapi/linux/tc_act/Kbuild @@ -12,3 +12,4 @@ header-y += tc_bpf.h header-y += tc_connmark.h header-y += tc_ife.h header-y += tc_tunnel_key.h +header-y += tc_skbmod.h -- cgit v1.2.3 From ffe3bb85c19e1dbf96cc13aad823ae0a8855d066 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Fri, 2 Dec 2016 14:54:00 -0800 Subject: uapi: export nf_log.h File is in uapi directory but not being copied on make install_headers Fixes commit 4ec9c8fbbc22 ("netfilter: nft_log: complete NFTA_LOG_FLAGS attr support"). Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/uapi/linux/netfilter/Kbuild | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/Kbuild b/include/uapi/linux/netfilter/Kbuild index cd26d7a0fd07..03f194aeadc5 100644 --- a/include/uapi/linux/netfilter/Kbuild +++ b/include/uapi/linux/netfilter/Kbuild @@ -5,6 +5,7 @@ header-y += nf_conntrack_ftp.h header-y += nf_conntrack_sctp.h header-y += nf_conntrack_tcp.h header-y += nf_conntrack_tuple_common.h +header-y += nf_log.h header-y += nf_tables.h header-y += nf_tables_compat.h header-y += nf_nat.h -- cgit v1.2.3 From efc45154828ae4e49c6b46f59882bfef32697d44 Mon Sep 17 00:00:00 2001 From: Jonas Gorski Date: Sat, 3 Dec 2016 17:31:45 +0100 Subject: uapi glibc compat: fix outer guard of net device flags enum Fix a wrong condition preventing the higher net device flags IFF_LOWER_UP etc to be defined if net/if.h is included before linux/if.h. The comment makes it clear the intention was to allow partial definition with either parts. This fixes compilation of userspace programs trying to use IFF_LOWER_UP, IFF_DORMANT or IFF_ECHO. Fixes: 4a91cb61bb99 ("uapi glibc compat: fix compile errors when glibc net/if.h included before linux/if.h") Signed-off-by: Jonas Gorski Reviewed-by: Mikko Rapeli Signed-off-by: David S. Miller --- include/uapi/linux/if.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h index e601c8c3bdc7..1158a043342a 100644 --- a/include/uapi/linux/if.h +++ b/include/uapi/linux/if.h @@ -31,7 +31,7 @@ #include /* For glibc compatibility. An empty enum does not compile. */ -#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 && \ +#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 || \ __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0 /** * enum net_device_flags - &struct net_device flags @@ -99,7 +99,7 @@ enum net_device_flags { IFF_ECHO = 1<<18, /* volatile */ #endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO */ }; -#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 && __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0 */ +#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 || __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0 */ /* for compatibility with glibc net/if.h */ #if __UAPI_DEF_IF_NET_DEVICE_FLAGS -- cgit v1.2.3 From 1814096980bbe546c4384b7b064126cbe7d40d30 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 24 Nov 2016 12:04:55 +0100 Subject: netfilter: nft_payload: layer 4 checksum adjustment for pseudoheader fields This patch adds a new flag that signals the kernel to update layer 4 checksum if the packet field belongs to the layer 4 pseudoheader. This implicitly provides stateless NAT 1:1 that is useful under very specific usecases. Since rules mangling layer 3 fields that are part of the pseudoheader may potentially convey any layer 4 packet, we have to deal with the layer 4 checksum adjustment using protocol specific code. This patch adds support for TCP, UDP and ICMPv6, since they include the pseudoheader in the layer 4 checksum calculation. ICMP doesn't, so we can skip it. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables_core.h | 1 + include/uapi/linux/netfilter/nf_tables.h | 6 ++ net/netfilter/nft_payload.c | 107 +++++++++++++++++++++++++++++-- 3 files changed, 109 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 862373d4ea9d..8f690effec37 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -45,6 +45,7 @@ struct nft_payload_set { enum nft_registers sreg:8; u8 csum_type; u8 csum_offset; + u8 csum_flags; }; extern const struct nft_expr_ops nft_payload_fast_ops; diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 14e5f619167e..f030e59aa2ec 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -659,6 +659,10 @@ enum nft_payload_csum_types { NFT_PAYLOAD_CSUM_INET, }; +enum nft_payload_csum_flags { + NFT_PAYLOAD_L4CSUM_PSEUDOHDR = (1 << 0), +}; + /** * enum nft_payload_attributes - nf_tables payload expression netlink attributes * @@ -669,6 +673,7 @@ enum nft_payload_csum_types { * @NFTA_PAYLOAD_SREG: source register to load data from (NLA_U32: nft_registers) * @NFTA_PAYLOAD_CSUM_TYPE: checksum type (NLA_U32) * @NFTA_PAYLOAD_CSUM_OFFSET: checksum offset relative to base (NLA_U32) + * @NFTA_PAYLOAD_CSUM_FLAGS: checksum flags (NLA_U32) */ enum nft_payload_attributes { NFTA_PAYLOAD_UNSPEC, @@ -679,6 +684,7 @@ enum nft_payload_attributes { NFTA_PAYLOAD_SREG, NFTA_PAYLOAD_CSUM_TYPE, NFTA_PAYLOAD_CSUM_OFFSET, + NFTA_PAYLOAD_CSUM_FLAGS, __NFTA_PAYLOAD_MAX }; #define NFTA_PAYLOAD_MAX (__NFTA_PAYLOAD_MAX - 1) diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 98fb5d7b8087..36d2b1096546 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -1,5 +1,6 @@ /* * Copyright (c) 2008-2009 Patrick McHardy + * Copyright (c) 2016 Pablo Neira Ayuso * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -17,6 +18,10 @@ #include #include #include +/* For layer 4 checksum field offset. */ +#include +#include +#include /* add vlan header into the user buffer for if tag was removed by offloads */ static bool @@ -164,6 +169,87 @@ const struct nft_expr_ops nft_payload_fast_ops = { .dump = nft_payload_dump, }; +static inline void nft_csum_replace(__sum16 *sum, __wsum fsum, __wsum tsum) +{ + *sum = csum_fold(csum_add(csum_sub(~csum_unfold(*sum), fsum), tsum)); + if (*sum == 0) + *sum = CSUM_MANGLED_0; +} + +static bool nft_payload_udp_checksum(struct sk_buff *skb, unsigned int thoff) +{ + struct udphdr *uh, _uh; + + uh = skb_header_pointer(skb, thoff, sizeof(_uh), &_uh); + if (!uh) + return false; + + return uh->check; +} + +static int nft_payload_l4csum_offset(const struct nft_pktinfo *pkt, + struct sk_buff *skb, + unsigned int *l4csum_offset) +{ + switch (pkt->tprot) { + case IPPROTO_TCP: + *l4csum_offset = offsetof(struct tcphdr, check); + break; + case IPPROTO_UDP: + if (!nft_payload_udp_checksum(skb, pkt->xt.thoff)) + return -1; + /* Fall through. */ + case IPPROTO_UDPLITE: + *l4csum_offset = offsetof(struct udphdr, check); + break; + case IPPROTO_ICMPV6: + *l4csum_offset = offsetof(struct icmp6hdr, icmp6_cksum); + break; + default: + return -1; + } + + *l4csum_offset += pkt->xt.thoff; + return 0; +} + +static int nft_payload_l4csum_update(const struct nft_pktinfo *pkt, + struct sk_buff *skb, + __wsum fsum, __wsum tsum) +{ + int l4csum_offset; + __sum16 sum; + + /* If we cannot determine layer 4 checksum offset or this packet doesn't + * require layer 4 checksum recalculation, skip this packet. + */ + if (nft_payload_l4csum_offset(pkt, skb, &l4csum_offset) < 0) + return 0; + + if (skb_copy_bits(skb, l4csum_offset, &sum, sizeof(sum)) < 0) + return -1; + + /* Checksum mangling for an arbitrary amount of bytes, based on + * inet_proto_csum_replace*() functions. + */ + if (skb->ip_summed != CHECKSUM_PARTIAL) { + nft_csum_replace(&sum, fsum, tsum); + if (skb->ip_summed == CHECKSUM_COMPLETE) { + skb->csum = ~csum_add(csum_sub(~(skb->csum), fsum), + tsum); + } + } else { + sum = ~csum_fold(csum_add(csum_sub(csum_unfold(sum), fsum), + tsum)); + } + + if (!skb_make_writable(skb, l4csum_offset + sizeof(sum)) || + skb_store_bits(skb, l4csum_offset, &sum, sizeof(sum)) < 0) + return -1; + + return 0; +} + static void nft_payload_set_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -204,14 +290,15 @@ static void nft_payload_set_eval(const struct nft_expr *expr, fsum = skb_checksum(skb, offset, priv->len, 0); tsum = csum_partial(src, priv->len, 0); - sum = csum_fold(csum_add(csum_sub(~csum_unfold(sum), fsum), - tsum)); - if (sum == 0) - sum = CSUM_MANGLED_0; + nft_csum_replace(&sum, fsum, tsum); if (!skb_make_writable(skb, csum_offset + sizeof(sum)) || skb_store_bits(skb, csum_offset, &sum, sizeof(sum)) < 0) goto err; + + if (priv->csum_flags && + nft_payload_l4csum_update(pkt, skb, fsum, tsum) < 0) + goto err; } if (!skb_make_writable(skb, max(offset + priv->len, 0)) || @@ -240,6 +327,15 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, if (tb[NFTA_PAYLOAD_CSUM_OFFSET]) priv->csum_offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_OFFSET])); + if (tb[NFTA_PAYLOAD_CSUM_FLAGS]) { + u32 flags; + + flags = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_FLAGS])); + if (flags & ~NFT_PAYLOAD_L4CSUM_PSEUDOHDR) + return -EINVAL; + + priv->csum_flags = flags; + } switch (priv->csum_type) { case NFT_PAYLOAD_CSUM_NONE: @@ -262,7 +358,8 @@ static int nft_payload_set_dump(struct sk_buff *skb, const struct nft_expr *expr nla_put_be32(skb, NFTA_PAYLOAD_LEN, htonl(priv->len)) || nla_put_be32(skb, NFTA_PAYLOAD_CSUM_TYPE, htonl(priv->csum_type)) || nla_put_be32(skb, NFTA_PAYLOAD_CSUM_OFFSET, - htonl(priv->csum_offset))) + htonl(priv->csum_offset)) || + nla_put_be32(skb, NFTA_PAYLOAD_CSUM_FLAGS, htonl(priv->csum_flags))) goto nla_put_failure; return 0; -- cgit v1.2.3 From e50092404c1bc7aaeb0a0f4077fa6f07b073a20f Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 28 Nov 2016 00:04:32 +0100 Subject: netfilter: nf_tables: add stateful objects This patch augments nf_tables to support stateful objects. This new infrastructure allows you to create, dump and delete stateful objects, that are identified by a user-defined name. This patch adds the generic infrastructure, follow up patches add support for two stateful objects: counters and quotas. This patch provides a native infrastructure for nf_tables to replace nfacct, the extended accounting infrastructure for iptables. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 79 +++++ include/uapi/linux/netfilter/nf_tables.h | 29 ++ net/netfilter/nf_tables_api.c | 516 +++++++++++++++++++++++++++++++ 3 files changed, 624 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 32970cba184a..903cd618f50e 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -875,6 +875,7 @@ unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv); * @list: used internally * @chains: chains in the table * @sets: sets in the table + * @objects: stateful objects in the table * @hgenerator: handle generator state * @use: number of chain references to this table * @flags: table flag (see enum nft_table_flags) @@ -885,6 +886,7 @@ struct nft_table { struct list_head list; struct list_head chains; struct list_head sets; + struct list_head objects; u64 hgenerator; u32 use; u16 flags:14, @@ -934,6 +936,73 @@ void nft_unregister_expr(struct nft_expr_type *); int nft_verdict_dump(struct sk_buff *skb, int type, const struct nft_verdict *v); +/** + * struct nft_object - nf_tables stateful object + * + * @list: table stateful object list node + * @type: pointer to object type + * @data: pointer to object data + * @name: name of this stateful object + * @genmask: generation mask + * @use: number of references to this stateful object + * @data: object data, layout depends on type + */ +struct nft_object { + struct list_head list; + char name[NFT_OBJ_MAXNAMELEN]; + u32 genmask:2, + use:30; + /* runtime data below here */ + const struct nft_object_type *type ____cacheline_aligned; + unsigned char data[] + __attribute__((aligned(__alignof__(u64)))); +}; + +static inline void *nft_obj_data(const struct nft_object *obj) +{ + return (void *)obj->data; +} + +#define nft_expr_obj(expr) *((struct nft_object **)nft_expr_priv(expr)) + +struct nft_object *nf_tables_obj_lookup(const struct nft_table *table, + const struct nlattr *nla, u32 objtype, + u8 genmask); + +/** + * struct nft_object_type - stateful object type + * + * @eval: stateful object evaluation function + * @list: list node in list of object types + * @type: stateful object numeric type + * @size: stateful object size + * @owner: module owner + * @maxattr: maximum netlink attribute + * @policy: netlink attribute policy + * @init: initialize object from netlink attributes + * @destroy: release existing stateful object + * @dump: netlink dump stateful object + */ +struct nft_object_type { + void (*eval)(struct nft_object *obj, + struct nft_regs *regs, + const struct nft_pktinfo *pkt); + struct list_head list; + u32 type; + unsigned int size; + unsigned int maxattr; + struct module *owner; + const struct nla_policy *policy; + int (*init)(const struct nlattr * const tb[], + struct nft_object *obj); + void (*destroy)(struct nft_object *obj); + int (*dump)(struct sk_buff *skb, + const struct nft_object *obj); +}; + +int nft_register_obj(struct nft_object_type *obj_type); +void nft_unregister_obj(struct nft_object_type *obj_type); + /** * struct nft_traceinfo - nft tracing information and state * @@ -981,6 +1050,9 @@ void nft_trace_notify(struct nft_traceinfo *info); #define MODULE_ALIAS_NFT_SET() \ MODULE_ALIAS("nft-set") +#define MODULE_ALIAS_NFT_OBJ(type) \ + MODULE_ALIAS("nft-obj-" __stringify(type)) + /* * The gencursor defines two generations, the currently active and the * next one. Objects contain a bitmask of 2 bits specifying the generations @@ -1157,4 +1229,11 @@ struct nft_trans_elem { #define nft_trans_elem(trans) \ (((struct nft_trans_elem *)trans->data)->elem) +struct nft_trans_obj { + struct nft_object *obj; +}; + +#define nft_trans_obj(trans) \ + (((struct nft_trans_obj *)trans->data)->obj) + #endif /* _NET_NF_TABLES_H */ diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index f030e59aa2ec..18e30dbc8c3f 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -4,6 +4,7 @@ #define NFT_TABLE_MAXNAMELEN 32 #define NFT_CHAIN_MAXNAMELEN 32 #define NFT_SET_MAXNAMELEN 32 +#define NFT_OBJ_MAXNAMELEN 32 #define NFT_USERDATA_MAXLEN 256 /** @@ -85,6 +86,9 @@ enum nft_verdicts { * @NFT_MSG_NEWGEN: announce a new generation, only for events (enum nft_gen_attributes) * @NFT_MSG_GETGEN: get the rule-set generation (enum nft_gen_attributes) * @NFT_MSG_TRACE: trace event (enum nft_trace_attributes) + * @NFT_MSG_NEWOBJ: create a stateful object (enum nft_obj_attributes) + * @NFT_MSG_GETOBJ: get a stateful object (enum nft_obj_attributes) + * @NFT_MSG_DELOBJ: delete a stateful object (enum nft_obj_attributes) */ enum nf_tables_msg_types { NFT_MSG_NEWTABLE, @@ -105,6 +109,9 @@ enum nf_tables_msg_types { NFT_MSG_NEWGEN, NFT_MSG_GETGEN, NFT_MSG_TRACE, + NFT_MSG_NEWOBJ, + NFT_MSG_GETOBJ, + NFT_MSG_DELOBJ, NFT_MSG_MAX, }; @@ -1178,6 +1185,28 @@ enum nft_fib_flags { NFTA_FIB_F_OIF = 1 << 4, /* restrict to oif */ }; +#define NFT_OBJECT_UNSPEC 0 + +/** + * enum nft_object_attributes - nf_tables stateful object netlink attributes + * + * @NFTA_OBJ_TABLE: name of the table containing the expression (NLA_STRING) + * @NFTA_OBJ_NAME: name of this expression type (NLA_STRING) + * @NFTA_OBJ_TYPE: stateful object type (NLA_U32) + * @NFTA_OBJ_DATA: stateful object data (NLA_NESTED) + * @NFTA_OBJ_USE: number of references to this expression (NLA_U32) + */ +enum nft_object_attributes { + NFTA_OBJ_UNSPEC, + NFTA_OBJ_TABLE, + NFTA_OBJ_NAME, + NFTA_OBJ_TYPE, + NFTA_OBJ_DATA, + NFTA_OBJ_USE, + __NFTA_OBJ_MAX +}; +#define NFTA_OBJ_MAX (__NFTA_OBJ_MAX - 1) + /** * enum nft_trace_attributes - nf_tables trace netlink attributes * diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e5194f6f906c..2ae717c5dcb8 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -22,6 +22,7 @@ #include static LIST_HEAD(nf_tables_expressions); +static LIST_HEAD(nf_tables_objects); /** * nft_register_afinfo - register nf_tables address family info @@ -304,6 +305,38 @@ static int nft_delset(struct nft_ctx *ctx, struct nft_set *set) return err; } +static int nft_trans_obj_add(struct nft_ctx *ctx, int msg_type, + struct nft_object *obj) +{ + struct nft_trans *trans; + + trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_obj)); + if (trans == NULL) + return -ENOMEM; + + if (msg_type == NFT_MSG_NEWOBJ) + nft_activate_next(ctx->net, obj); + + nft_trans_obj(trans) = obj; + list_add_tail(&trans->list, &ctx->net->nft.commit_list); + + return 0; +} + +static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj) +{ + int err; + + err = nft_trans_obj_add(ctx, NFT_MSG_DELOBJ, obj); + if (err < 0) + return err; + + nft_deactivate_next(ctx->net, obj); + ctx->table->use--; + + return err; +} + /* * Tables */ @@ -688,6 +721,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, nla_strlcpy(table->name, name, NFT_TABLE_MAXNAMELEN); INIT_LIST_HEAD(&table->chains); INIT_LIST_HEAD(&table->sets); + INIT_LIST_HEAD(&table->objects); table->flags = flags; nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla); @@ -709,6 +743,7 @@ static int nft_flush_table(struct nft_ctx *ctx) { int err; struct nft_chain *chain, *nc; + struct nft_object *obj, *ne; struct nft_set *set, *ns; list_for_each_entry(chain, &ctx->table->chains, list) { @@ -735,6 +770,12 @@ static int nft_flush_table(struct nft_ctx *ctx) goto out; } + list_for_each_entry_safe(obj, ne, &ctx->table->objects, list) { + err = nft_delobj(ctx, obj); + if (err < 0) + goto out; + } + list_for_each_entry_safe(chain, nc, &ctx->table->chains, list) { if (!nft_is_active_next(ctx->net, chain)) continue; @@ -3838,6 +3879,434 @@ struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set, } EXPORT_SYMBOL_GPL(nft_set_gc_batch_alloc); +/* + * Stateful objects + */ + +/** + * nft_register_obj- register nf_tables stateful object type + * @obj: object type + * + * Registers the object type for use with nf_tables. Returns zero on + * success or a negative errno code otherwise. + */ +int nft_register_obj(struct nft_object_type *obj_type) +{ + if (obj_type->type == NFT_OBJECT_UNSPEC) + return -EINVAL; + + nfnl_lock(NFNL_SUBSYS_NFTABLES); + list_add_rcu(&obj_type->list, &nf_tables_objects); + nfnl_unlock(NFNL_SUBSYS_NFTABLES); + return 0; +} +EXPORT_SYMBOL_GPL(nft_register_obj); + +/** + * nft_unregister_obj - unregister nf_tables object type + * @obj: object type + * + * Unregisters the object type for use with nf_tables. + */ +void nft_unregister_obj(struct nft_object_type *obj_type) +{ + nfnl_lock(NFNL_SUBSYS_NFTABLES); + list_del_rcu(&obj_type->list); + nfnl_unlock(NFNL_SUBSYS_NFTABLES); +} +EXPORT_SYMBOL_GPL(nft_unregister_obj); + +struct nft_object *nf_tables_obj_lookup(const struct nft_table *table, + const struct nlattr *nla, + u32 objtype, u8 genmask) +{ + struct nft_object *obj; + + list_for_each_entry(obj, &table->objects, list) { + if (!nla_strcmp(nla, obj->name) && + objtype == obj->type->type && + nft_active_genmask(obj, genmask)) + return obj; + } + return ERR_PTR(-ENOENT); +} +EXPORT_SYMBOL_GPL(nf_tables_obj_lookup); + +static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = { + [NFTA_OBJ_TABLE] = { .type = NLA_STRING }, + [NFTA_OBJ_NAME] = { .type = NLA_STRING }, + [NFTA_OBJ_TYPE] = { .type = NLA_U32 }, + [NFTA_OBJ_DATA] = { .type = NLA_NESTED }, +}; + +static struct nft_object *nft_obj_init(const struct nft_object_type *type, + const struct nlattr *attr) +{ + struct nlattr *tb[type->maxattr + 1]; + struct nft_object *obj; + int err; + + if (attr) { + err = nla_parse_nested(tb, type->maxattr, attr, type->policy); + if (err < 0) + goto err1; + } else { + memset(tb, 0, sizeof(tb[0]) * (type->maxattr + 1)); + } + + err = -ENOMEM; + obj = kzalloc(sizeof(struct nft_object) + type->size, GFP_KERNEL); + if (obj == NULL) + goto err1; + + err = type->init((const struct nlattr * const *)tb, obj); + if (err < 0) + goto err2; + + obj->type = type; + return obj; +err2: + kfree(obj); +err1: + return ERR_PTR(err); +} + +static int nft_object_dump(struct sk_buff *skb, unsigned int attr, + const struct nft_object *obj) +{ + struct nlattr *nest; + + nest = nla_nest_start(skb, attr); + if (!nest) + goto nla_put_failure; + if (obj->type->dump(skb, obj) < 0) + goto nla_put_failure; + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + return -1; +} + +static const struct nft_object_type *__nft_obj_type_get(u32 objtype) +{ + const struct nft_object_type *type; + + list_for_each_entry(type, &nf_tables_objects, list) { + if (objtype == type->type) + return type; + } + return NULL; +} + +static const struct nft_object_type *nft_obj_type_get(u32 objtype) +{ + const struct nft_object_type *type; + + type = __nft_obj_type_get(objtype); + if (type != NULL && try_module_get(type->owner)) + return type; + +#ifdef CONFIG_MODULES + if (type == NULL) { + nfnl_unlock(NFNL_SUBSYS_NFTABLES); + request_module("nft-obj-%u", objtype); + nfnl_lock(NFNL_SUBSYS_NFTABLES); + if (__nft_obj_type_get(objtype)) + return ERR_PTR(-EAGAIN); + } +#endif + return ERR_PTR(-ENOENT); +} + +static int nf_tables_newobj(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, + const struct nlattr * const nla[]) +{ + const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + const struct nft_object_type *type; + u8 genmask = nft_genmask_next(net); + int family = nfmsg->nfgen_family; + struct nft_af_info *afi; + struct nft_table *table; + struct nft_object *obj; + struct nft_ctx ctx; + u32 objtype; + int err; + + if (!nla[NFTA_OBJ_TYPE] || + !nla[NFTA_OBJ_NAME] || + !nla[NFTA_OBJ_DATA]) + return -EINVAL; + + afi = nf_tables_afinfo_lookup(net, family, true); + if (IS_ERR(afi)) + return PTR_ERR(afi); + + table = nf_tables_table_lookup(afi, nla[NFTA_OBJ_TABLE], genmask); + if (IS_ERR(table)) + return PTR_ERR(table); + + objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); + obj = nf_tables_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask); + if (IS_ERR(obj)) { + err = PTR_ERR(obj); + if (err != -ENOENT) + return err; + + obj = NULL; + } + + if (obj != NULL) { + if (nlh->nlmsg_flags & NLM_F_EXCL) + return -EEXIST; + + return 0; + } + + nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla); + + type = nft_obj_type_get(objtype); + if (IS_ERR(type)) + return PTR_ERR(type); + + obj = nft_obj_init(type, nla[NFTA_OBJ_DATA]); + if (IS_ERR(obj)) { + err = PTR_ERR(obj); + goto err1; + } + nla_strlcpy(obj->name, nla[NFTA_OBJ_NAME], NFT_OBJ_MAXNAMELEN); + + err = nft_trans_obj_add(&ctx, NFT_MSG_NEWOBJ, obj); + if (err < 0) + goto err2; + + list_add_tail_rcu(&obj->list, &table->objects); + table->use++; + return 0; +err2: + if (obj->type->destroy) + obj->type->destroy(obj); + kfree(obj); +err1: + module_put(type->owner); + return err; +} + +static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net, + u32 portid, u32 seq, int event, u32 flags, + int family, const struct nft_table *table, + const struct nft_object *obj) +{ + struct nfgenmsg *nfmsg; + struct nlmsghdr *nlh; + + event |= NFNL_SUBSYS_NFTABLES << 8; + nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags); + if (nlh == NULL) + goto nla_put_failure; + + nfmsg = nlmsg_data(nlh); + nfmsg->nfgen_family = family; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = htons(net->nft.base_seq & 0xffff); + + if (nla_put_string(skb, NFTA_OBJ_TABLE, table->name) || + nla_put_string(skb, NFTA_OBJ_NAME, obj->name) || + nla_put_be32(skb, NFTA_OBJ_TYPE, htonl(obj->type->type)) || + nla_put_be32(skb, NFTA_OBJ_USE, htonl(obj->use)) || + nft_object_dump(skb, NFTA_OBJ_DATA, obj)) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + return 0; + +nla_put_failure: + nlmsg_trim(skb, nlh); + return -1; +} + +static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) +{ + const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); + const struct nft_af_info *afi; + const struct nft_table *table; + const struct nft_object *obj; + unsigned int idx = 0, s_idx = cb->args[0]; + struct net *net = sock_net(skb->sk); + int family = nfmsg->nfgen_family; + + rcu_read_lock(); + cb->seq = net->nft.base_seq; + + list_for_each_entry_rcu(afi, &net->nft.af_info, list) { + if (family != NFPROTO_UNSPEC && family != afi->family) + continue; + + list_for_each_entry_rcu(table, &afi->tables, list) { + list_for_each_entry_rcu(obj, &table->objects, list) { + if (!nft_is_active(net, obj)) + goto cont; + if (idx < s_idx) + goto cont; + if (idx > s_idx) + memset(&cb->args[1], 0, + sizeof(cb->args) - sizeof(cb->args[0])); + if (nf_tables_fill_obj_info(skb, net, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NFT_MSG_NEWOBJ, + NLM_F_MULTI | NLM_F_APPEND, + afi->family, table, obj) < 0) + goto done; + + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); +cont: + idx++; + } + } + } +done: + rcu_read_unlock(); + + cb->args[0] = idx; + return skb->len; +} + +static int nf_tables_getobj(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, + const struct nlattr * const nla[]) +{ + const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + u8 genmask = nft_genmask_cur(net); + int family = nfmsg->nfgen_family; + const struct nft_af_info *afi; + const struct nft_table *table; + struct nft_object *obj; + struct sk_buff *skb2; + u32 objtype; + int err; + + if (nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .dump = nf_tables_dump_obj, + }; + return netlink_dump_start(nlsk, skb, nlh, &c); + } + + if (!nla[NFTA_OBJ_NAME] || + !nla[NFTA_OBJ_TYPE]) + return -EINVAL; + + afi = nf_tables_afinfo_lookup(net, family, false); + if (IS_ERR(afi)) + return PTR_ERR(afi); + + table = nf_tables_table_lookup(afi, nla[NFTA_OBJ_TABLE], genmask); + if (IS_ERR(table)) + return PTR_ERR(table); + + objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); + obj = nf_tables_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask); + if (IS_ERR(obj)) + return PTR_ERR(obj); + + skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb2) + return -ENOMEM; + + err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid, + nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, + family, table, obj); + if (err < 0) + goto err; + + return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); +err: + kfree_skb(skb2); + return err; + + return 0; +} + +static void nft_obj_destroy(struct nft_object *obj) +{ + if (obj->type->destroy) + obj->type->destroy(obj); + + module_put(obj->type->owner); + kfree(obj); +} + +static int nf_tables_delobj(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, + const struct nlattr * const nla[]) +{ + const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + u8 genmask = nft_genmask_next(net); + int family = nfmsg->nfgen_family; + struct nft_af_info *afi; + struct nft_table *table; + struct nft_object *obj; + struct nft_ctx ctx; + u32 objtype; + + if (!nla[NFTA_OBJ_TYPE] || + !nla[NFTA_OBJ_NAME]) + return -EINVAL; + + afi = nf_tables_afinfo_lookup(net, family, true); + if (IS_ERR(afi)) + return PTR_ERR(afi); + + table = nf_tables_table_lookup(afi, nla[NFTA_OBJ_TABLE], genmask); + if (IS_ERR(table)) + return PTR_ERR(table); + + objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); + obj = nf_tables_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask); + if (IS_ERR(obj)) + return PTR_ERR(obj); + if (obj->use > 0) + return -EBUSY; + + nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla); + + return nft_delobj(&ctx, obj); +} + +static int nf_tables_obj_notify(const struct nft_ctx *ctx, + struct nft_object *obj, int event) +{ + struct sk_buff *skb; + int err; + + if (!ctx->report && + !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) + return 0; + + err = -ENOBUFS; + skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (skb == NULL) + goto err; + + err = nf_tables_fill_obj_info(skb, ctx->net, ctx->portid, ctx->seq, + event, 0, ctx->afi->family, ctx->table, + obj); + if (err < 0) { + kfree_skb(skb); + goto err; + } + + err = nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES, + ctx->report, GFP_KERNEL); +err: + if (err < 0) { + nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, + err); + } + return err; +} + static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq) { @@ -3998,6 +4467,21 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { [NFT_MSG_GETGEN] = { .call = nf_tables_getgen, }, + [NFT_MSG_NEWOBJ] = { + .call_batch = nf_tables_newobj, + .attr_count = NFTA_OBJ_MAX, + .policy = nft_obj_policy, + }, + [NFT_MSG_GETOBJ] = { + .call = nf_tables_getobj, + .attr_count = NFTA_OBJ_MAX, + .policy = nft_obj_policy, + }, + [NFT_MSG_DELOBJ] = { + .call_batch = nf_tables_delobj, + .attr_count = NFTA_OBJ_MAX, + .policy = nft_obj_policy, + }, }; static void nft_chain_commit_update(struct nft_trans *trans) @@ -4040,6 +4524,9 @@ static void nf_tables_commit_release(struct nft_trans *trans) nft_set_elem_destroy(nft_trans_elem_set(trans), nft_trans_elem(trans).priv, true); break; + case NFT_MSG_DELOBJ: + nft_obj_destroy(nft_trans_obj(trans)); + break; } kfree(trans); } @@ -4147,6 +4634,17 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) atomic_dec(&te->set->nelems); te->set->ndeact--; break; + case NFT_MSG_NEWOBJ: + nft_clear(net, nft_trans_obj(trans)); + nf_tables_obj_notify(&trans->ctx, nft_trans_obj(trans), + NFT_MSG_NEWOBJ); + nft_trans_destroy(trans); + break; + case NFT_MSG_DELOBJ: + list_del_rcu(&nft_trans_obj(trans)->list); + nf_tables_obj_notify(&trans->ctx, nft_trans_obj(trans), + NFT_MSG_DELOBJ); + break; } } @@ -4181,6 +4679,9 @@ static void nf_tables_abort_release(struct nft_trans *trans) nft_set_elem_destroy(nft_trans_elem_set(trans), nft_trans_elem(trans).priv, true); break; + case NFT_MSG_NEWOBJ: + nft_obj_destroy(nft_trans_obj(trans)); + break; } kfree(trans); } @@ -4259,6 +4760,15 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb) te->set->ops->activate(net, te->set, &te->elem); te->set->ndeact--; + nft_trans_destroy(trans); + break; + case NFT_MSG_NEWOBJ: + trans->ctx.table->use--; + list_del_rcu(&nft_trans_obj(trans)->list); + break; + case NFT_MSG_DELOBJ: + trans->ctx.table->use++; + nft_clear(trans->ctx.net, nft_trans_obj(trans)); nft_trans_destroy(trans); break; } @@ -4807,6 +5317,7 @@ static void __nft_release_afinfo(struct net *net, struct nft_af_info *afi) { struct nft_table *table, *nt; struct nft_chain *chain, *nc; + struct nft_object *obj, *ne; struct nft_rule *rule, *nr; struct nft_set *set, *ns; struct nft_ctx ctx = { @@ -4833,6 +5344,11 @@ static void __nft_release_afinfo(struct net *net, struct nft_af_info *afi) table->use--; nft_set_destroy(set); } + list_for_each_entry_safe(obj, ne, &table->objects, list) { + list_del(&obj->list); + table->use--; + nft_obj_destroy(obj); + } list_for_each_entry_safe(chain, nc, &table->chains, list) { list_del(&chain->list); table->use--; -- cgit v1.2.3 From b1ce0ced101ee134c5d0bbb378b2c3cadc617f20 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 28 Nov 2016 00:04:36 +0100 Subject: netfilter: nft_counter: add stateful object type Register a new percpu counter stateful object type into the stateful object infrastructure. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 1 + net/netfilter/nft_counter.c | 140 +++++++++++++++++++++++++------ 2 files changed, 114 insertions(+), 27 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 18e30dbc8c3f..e352ef65d753 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1186,6 +1186,7 @@ enum nft_fib_flags { }; #define NFT_OBJECT_UNSPEC 0 +#define NFT_OBJECT_COUNTER 1 /** * enum nft_object_attributes - nf_tables stateful object netlink attributes diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 77db8358ab14..6f3dd429f865 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -31,11 +31,10 @@ struct nft_counter_percpu_priv { struct nft_counter_percpu __percpu *counter; }; -static void nft_counter_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +static inline void nft_counter_do_eval(struct nft_counter_percpu_priv *priv, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { - struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); struct nft_counter_percpu *this_cpu; local_bh_disable(); @@ -47,6 +46,60 @@ static void nft_counter_eval(const struct nft_expr *expr, local_bh_enable(); } +static inline void nft_counter_obj_eval(struct nft_object *obj, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_counter_percpu_priv *priv = nft_obj_data(obj); + + nft_counter_do_eval(priv, regs, pkt); +} + +static int nft_counter_do_init(const struct nlattr * const tb[], + struct nft_counter_percpu_priv *priv) +{ + struct nft_counter_percpu __percpu *cpu_stats; + struct nft_counter_percpu *this_cpu; + + cpu_stats = netdev_alloc_pcpu_stats(struct nft_counter_percpu); + if (cpu_stats == NULL) + return -ENOMEM; + + preempt_disable(); + this_cpu = this_cpu_ptr(cpu_stats); + if (tb[NFTA_COUNTER_PACKETS]) { + this_cpu->counter.packets = + be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS])); + } + if (tb[NFTA_COUNTER_BYTES]) { + this_cpu->counter.bytes = + be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES])); + } + preempt_enable(); + priv->counter = cpu_stats; + return 0; +} + +static int nft_counter_obj_init(const struct nlattr * const tb[], + struct nft_object *obj) +{ + struct nft_counter_percpu_priv *priv = nft_obj_data(obj); + + return nft_counter_do_init(tb, priv); +} + +static void nft_counter_do_destroy(struct nft_counter_percpu_priv *priv) +{ + free_percpu(priv->counter); +} + +static void nft_counter_obj_destroy(struct nft_object *obj) +{ + struct nft_counter_percpu_priv *priv = nft_obj_data(obj); + + nft_counter_do_destroy(priv); +} + static void nft_counter_fetch(const struct nft_counter_percpu __percpu *counter, struct nft_counter *total) { @@ -69,9 +122,9 @@ static void nft_counter_fetch(const struct nft_counter_percpu __percpu *counter, } } -static int nft_counter_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_counter_do_dump(struct sk_buff *skb, + const struct nft_counter_percpu_priv *priv) { - struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); struct nft_counter total; nft_counter_fetch(priv->counter, &total); @@ -87,36 +140,54 @@ nla_put_failure: return -1; } +static int nft_counter_obj_dump(struct sk_buff *skb, + const struct nft_object *obj) +{ + const struct nft_counter_percpu_priv *priv = nft_obj_data(obj); + + return nft_counter_do_dump(skb, priv); +} + static const struct nla_policy nft_counter_policy[NFTA_COUNTER_MAX + 1] = { [NFTA_COUNTER_PACKETS] = { .type = NLA_U64 }, [NFTA_COUNTER_BYTES] = { .type = NLA_U64 }, }; +static struct nft_object_type nft_counter_obj __read_mostly = { + .type = NFT_OBJECT_COUNTER, + .size = sizeof(struct nft_counter_percpu_priv), + .maxattr = NFTA_COUNTER_MAX, + .policy = nft_counter_policy, + .eval = nft_counter_obj_eval, + .init = nft_counter_obj_init, + .destroy = nft_counter_obj_destroy, + .dump = nft_counter_obj_dump, + .owner = THIS_MODULE, +}; + +static void nft_counter_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); + + nft_counter_do_eval(priv, regs, pkt); +} + +static int nft_counter_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); + + return nft_counter_do_dump(skb, priv); +} + static int nft_counter_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); - struct nft_counter_percpu __percpu *cpu_stats; - struct nft_counter_percpu *this_cpu; - cpu_stats = netdev_alloc_pcpu_stats(struct nft_counter_percpu); - if (cpu_stats == NULL) - return -ENOMEM; - - preempt_disable(); - this_cpu = this_cpu_ptr(cpu_stats); - if (tb[NFTA_COUNTER_PACKETS]) { - this_cpu->counter.packets = - be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS])); - } - if (tb[NFTA_COUNTER_BYTES]) { - this_cpu->counter.bytes = - be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES])); - } - preempt_enable(); - priv->counter = cpu_stats; - return 0; + return nft_counter_do_init(tb, priv); } static void nft_counter_destroy(const struct nft_ctx *ctx, @@ -124,7 +195,7 @@ static void nft_counter_destroy(const struct nft_ctx *ctx, { struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); - free_percpu(priv->counter); + nft_counter_do_destroy(priv); } static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src) @@ -174,12 +245,26 @@ static struct nft_expr_type nft_counter_type __read_mostly = { static int __init nft_counter_module_init(void) { - return nft_register_expr(&nft_counter_type); + int err; + + err = nft_register_obj(&nft_counter_obj); + if (err < 0) + return err; + + err = nft_register_expr(&nft_counter_type); + if (err < 0) + goto err1; + + return 0; +err1: + nft_unregister_obj(&nft_counter_obj); + return err; } static void __exit nft_counter_module_exit(void) { nft_unregister_expr(&nft_counter_type); + nft_unregister_obj(&nft_counter_obj); } module_init(nft_counter_module_init); @@ -188,3 +273,4 @@ module_exit(nft_counter_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy "); MODULE_ALIAS_NFT_EXPR("counter"); +MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_COUNTER); -- cgit v1.2.3 From 173705d9a2df1490478bf0d39f1b517bd489c8fa Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 28 Nov 2016 00:04:43 +0100 Subject: netfilter: nft_quota: add stateful object type Register a new quota stateful object type into the new stateful object infrastructure. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 1 + net/netfilter/nft_quota.c | 96 +++++++++++++++++++++++++++----- 2 files changed, 84 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index e352ef65d753..ad0577ba5d2a 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1187,6 +1187,7 @@ enum nft_fib_flags { #define NFT_OBJECT_UNSPEC 0 #define NFT_OBJECT_COUNTER 1 +#define NFT_OBJECT_QUOTA 2 /** * enum nft_object_attributes - nf_tables stateful object netlink attributes diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index c00104c07095..09ce72b1d6bf 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -27,12 +27,10 @@ static inline bool nft_overquota(struct nft_quota *priv, return atomic64_sub_return(pkt->skb->len, &priv->remain) < 0; } -static void nft_quota_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +static inline void nft_quota_do_eval(struct nft_quota *priv, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { - struct nft_quota *priv = nft_expr_priv(expr); - if (nft_overquota(priv, pkt) ^ priv->invert) regs->verdict.code = NFT_BREAK; } @@ -42,11 +40,18 @@ static const struct nla_policy nft_quota_policy[NFTA_QUOTA_MAX + 1] = { [NFTA_QUOTA_FLAGS] = { .type = NLA_U32 }, }; -static int nft_quota_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) +static void nft_quota_obj_eval(struct nft_object *obj, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_quota *priv = nft_obj_data(obj); + + nft_quota_do_eval(priv, regs, pkt); +} + +static int nft_quota_do_init(const struct nlattr * const tb[], + struct nft_quota *priv) { - struct nft_quota *priv = nft_expr_priv(expr); u32 flags = 0; u64 quota; @@ -70,9 +75,16 @@ static int nft_quota_init(const struct nft_ctx *ctx, return 0; } -static int nft_quota_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_quota_obj_init(const struct nlattr * const tb[], + struct nft_object *obj) +{ + struct nft_quota *priv = nft_obj_data(obj); + + return nft_quota_do_init(tb, priv); +} + +static int nft_quota_do_dump(struct sk_buff *skb, const struct nft_quota *priv) { - const struct nft_quota *priv = nft_expr_priv(expr); u32 flags = priv->invert ? NFT_QUOTA_F_INV : 0; if (nla_put_be64(skb, NFTA_QUOTA_BYTES, cpu_to_be64(priv->quota), @@ -85,6 +97,49 @@ nla_put_failure: return -1; } +static int nft_quota_obj_dump(struct sk_buff *skb, const struct nft_object *obj) +{ + struct nft_quota *priv = nft_obj_data(obj); + + return nft_quota_do_dump(skb, priv); +} + +static struct nft_object_type nft_quota_obj __read_mostly = { + .type = NFT_OBJECT_QUOTA, + .size = sizeof(struct nft_quota), + .maxattr = NFTA_QUOTA_MAX, + .policy = nft_quota_policy, + .init = nft_quota_obj_init, + .eval = nft_quota_obj_eval, + .dump = nft_quota_obj_dump, + .owner = THIS_MODULE, +}; + +static void nft_quota_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_quota *priv = nft_expr_priv(expr); + + nft_quota_do_eval(priv, regs, pkt); +} + +static int nft_quota_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_quota *priv = nft_expr_priv(expr); + + return nft_quota_do_init(tb, priv); +} + +static int nft_quota_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_quota *priv = nft_expr_priv(expr); + + return nft_quota_do_dump(skb, priv); +} + static struct nft_expr_type nft_quota_type; static const struct nft_expr_ops nft_quota_ops = { .type = &nft_quota_type, @@ -105,12 +160,26 @@ static struct nft_expr_type nft_quota_type __read_mostly = { static int __init nft_quota_module_init(void) { - return nft_register_expr(&nft_quota_type); + int err; + + err = nft_register_obj(&nft_quota_obj); + if (err < 0) + return err; + + err = nft_register_expr(&nft_quota_type); + if (err < 0) + goto err1; + + return 0; +err1: + nft_unregister_obj(&nft_quota_obj); + return err; } static void __exit nft_quota_module_exit(void) { - nft_unregister_expr(&nft_quota_type); + nft_unregister_expr(&nft_quota_type); + nft_unregister_obj(&nft_quota_obj); } module_init(nft_quota_module_init); @@ -119,3 +188,4 @@ module_exit(nft_quota_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso "); MODULE_ALIAS_NFT_EXPR("quota"); +MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_QUOTA); -- cgit v1.2.3 From c97d22e68bfedfacb9e752dee536c69916ae0933 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 28 Nov 2016 00:05:38 +0100 Subject: netfilter: nf_tables: add stateful object reference expression This new expression allows us to refer to existing stateful objects from rules. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 14 ++++ net/netfilter/Kconfig | 6 ++ net/netfilter/Makefile | 1 + net/netfilter/nft_objref.c | 112 +++++++++++++++++++++++++++++++ 4 files changed, 133 insertions(+) create mode 100644 net/netfilter/nft_objref.c (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index ad0577ba5d2a..1043ce4250c5 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1137,6 +1137,20 @@ enum nft_fwd_attributes { }; #define NFTA_FWD_MAX (__NFTA_FWD_MAX - 1) +/** + * enum nft_objref_attributes - nf_tables stateful object expression netlink attributes + * + * @NFTA_OBJREF_IMM_TYPE: object type for immediate reference (NLA_U32: nft_register) + * @NFTA_OBJREF_IMM_NAME: object name for immediate reference (NLA_STRING) + */ +enum nft_objref_attributes { + NFTA_OBJREF_UNSPEC, + NFTA_OBJREF_IMM_TYPE, + NFTA_OBJREF_IMM_NAME, + __NFTA_OBJREF_MAX +}; +#define NFTA_OBJREF_MAX (__NFTA_OBJREF_MAX - 1) + /** * enum nft_gen_attributes - nf_tables ruleset generation attributes * diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index def4be06cda6..63729b489c2c 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -551,6 +551,12 @@ config NFT_NAT This option adds the "nat" expression that you can use to perform typical Network Address Translation (NAT) packet transformations. +config NFT_OBJREF + tristate "Netfilter nf_tables stateful object reference module" + help + This option adds the "objref" expression that allows you to refer to + stateful objects, such as counters and quotas. + config NFT_QUEUE depends on NETFILTER_NETLINK_QUEUE tristate "Netfilter nf_tables queue module" diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index e4c8c1d7aaed..ca30d1960f1d 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -88,6 +88,7 @@ obj-$(CONFIG_NFT_NUMGEN) += nft_numgen.o obj-$(CONFIG_NFT_CT) += nft_ct.o obj-$(CONFIG_NFT_LIMIT) += nft_limit.o obj-$(CONFIG_NFT_NAT) += nft_nat.o +obj-$(CONFIG_NFT_OBJREF) += nft_objref.o obj-$(CONFIG_NFT_QUEUE) += nft_queue.o obj-$(CONFIG_NFT_QUOTA) += nft_quota.o obj-$(CONFIG_NFT_REJECT) += nft_reject.o diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c new file mode 100644 index 000000000000..23820f796aad --- /dev/null +++ b/net/netfilter/nft_objref.c @@ -0,0 +1,112 @@ +/* + * Copyright (c) 2012-2016 Pablo Neira Ayuso + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include + +#define nft_objref_priv(expr) *((struct nft_object **)nft_expr_priv(expr)) + +static void nft_objref_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_object *obj = nft_objref_priv(expr); + + obj->type->eval(obj, regs, pkt); +} + +static int nft_objref_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_object *obj = nft_objref_priv(expr); + u8 genmask = nft_genmask_next(ctx->net); + u32 objtype; + + if (!tb[NFTA_OBJREF_IMM_NAME] || + !tb[NFTA_OBJREF_IMM_TYPE]) + return -EINVAL; + + objtype = ntohl(nla_get_be32(tb[NFTA_OBJREF_IMM_TYPE])); + obj = nf_tables_obj_lookup(ctx->table, tb[NFTA_OBJREF_IMM_NAME], objtype, + genmask); + if (IS_ERR(obj)) + return -ENOENT; + + nft_objref_priv(expr) = obj; + obj->use++; + + return 0; +} + +static int nft_objref_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_object *obj = nft_objref_priv(expr); + + if (nla_put_string(skb, NFTA_OBJREF_IMM_NAME, obj->name) || + nla_put_be32(skb, NFTA_OBJREF_IMM_TYPE, htonl(obj->type->type))) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static void nft_objref_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + struct nft_object *obj = nft_objref_priv(expr); + + obj->use--; +} + +static struct nft_expr_type nft_objref_type; +static const struct nft_expr_ops nft_objref_ops = { + .type = &nft_objref_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_object *)), + .eval = nft_objref_eval, + .init = nft_objref_init, + .destroy = nft_objref_destroy, + .dump = nft_objref_dump, +}; + +static const struct nla_policy nft_objref_policy[NFTA_OBJREF_MAX + 1] = { + [NFTA_OBJREF_IMM_NAME] = { .type = NLA_STRING }, + [NFTA_OBJREF_IMM_TYPE] = { .type = NLA_U32 }, +}; + +static struct nft_expr_type nft_objref_type __read_mostly = { + .name = "objref", + .ops = &nft_objref_ops, + .policy = nft_objref_policy, + .maxattr = NFTA_OBJREF_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_objref_module_init(void) +{ + return nft_register_expr(&nft_objref_type); +} + +static void __exit nft_objref_module_exit(void) +{ + nft_unregister_expr(&nft_objref_type); +} + +module_init(nft_objref_module_init); +module_exit(nft_objref_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso "); +MODULE_ALIAS_NFT_EXPR("objref"); -- cgit v1.2.3 From 332b05ca7a438f857c61a3c21a88489a21532364 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 5 Dec 2016 11:44:23 +0100 Subject: can: raw: raw_setsockopt: limit number of can_filter that can be set This patch adds a check to limit the number of can_filters that can be set via setsockopt on CAN_RAW sockets. Otherwise allocations > MAX_ORDER are not prevented resulting in a warning. Reference: https://lkml.org/lkml/2016/12/2/230 Reported-by: Andrey Konovalov Tested-by: Andrey Konovalov Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can.h | 1 + net/can/raw.c | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h index 9692cda5f8fc..c48d93a28d1a 100644 --- a/include/uapi/linux/can.h +++ b/include/uapi/linux/can.h @@ -196,5 +196,6 @@ struct can_filter { }; #define CAN_INV_FILTER 0x20000000U /* to be set in can_filter.can_id */ +#define CAN_RAW_FILTER_MAX 512 /* maximum number of can_filter set via setsockopt() */ #endif /* !_UAPI_CAN_H */ diff --git a/net/can/raw.c b/net/can/raw.c index 972c187d40ab..b075f028d7e2 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -499,6 +499,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, if (optlen % sizeof(struct can_filter) != 0) return -EINVAL; + if (optlen > CAN_RAW_FILTER_MAX * sizeof(struct can_filter)) + return -EINVAL; + count = optlen / sizeof(struct can_filter); if (count > 1) { -- cgit v1.2.3 From 795595f68d6c787028345804bb06f5a633af24a2 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 28 Nov 2016 00:05:52 +0100 Subject: netfilter: nft_quota: dump consumed quota Add a new attribute NFTA_QUOTA_CONSUMED that displays the amount of quota that has been already consumed. This allows us to restore the internal state of the quota object between reboots as well as to monitor how wasted it is. This patch changes the logic to account for the consumed bytes, instead of the bytes that remain to be consumed. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 ++ net/netfilter/nft_quota.c | 21 ++++++++++++++++----- 2 files changed, 18 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 1043ce4250c5..3d47582caa80 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -988,12 +988,14 @@ enum nft_quota_flags { * * @NFTA_QUOTA_BYTES: quota in bytes (NLA_U16) * @NFTA_QUOTA_FLAGS: flags (NLA_U32) + * @NFTA_QUOTA_CONSUMED: quota already consumed in bytes (NLA_U64) */ enum nft_quota_attributes { NFTA_QUOTA_UNSPEC, NFTA_QUOTA_BYTES, NFTA_QUOTA_FLAGS, NFTA_QUOTA_PAD, + NFTA_QUOTA_CONSUMED, __NFTA_QUOTA_MAX }; #define NFTA_QUOTA_MAX (__NFTA_QUOTA_MAX - 1) diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index 09ce72b1d6bf..0d344209803a 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -18,20 +18,20 @@ struct nft_quota { u64 quota; bool invert; - atomic64_t remain; + atomic64_t consumed; }; static inline bool nft_overquota(struct nft_quota *priv, - const struct nft_pktinfo *pkt) + const struct sk_buff *skb) { - return atomic64_sub_return(pkt->skb->len, &priv->remain) < 0; + return atomic64_add_return(skb->len, &priv->consumed) >= priv->quota; } static inline void nft_quota_do_eval(struct nft_quota *priv, struct nft_regs *regs, const struct nft_pktinfo *pkt) { - if (nft_overquota(priv, pkt) ^ priv->invert) + if (nft_overquota(priv, pkt->skb) ^ priv->invert) regs->verdict.code = NFT_BREAK; } @@ -70,7 +70,7 @@ static int nft_quota_do_init(const struct nlattr * const tb[], priv->quota = quota; priv->invert = (flags & NFT_QUOTA_F_INV) ? true : false; - atomic64_set(&priv->remain, quota); + atomic64_set(&priv->consumed, 0); return 0; } @@ -86,9 +86,20 @@ static int nft_quota_obj_init(const struct nlattr * const tb[], static int nft_quota_do_dump(struct sk_buff *skb, const struct nft_quota *priv) { u32 flags = priv->invert ? NFT_QUOTA_F_INV : 0; + u64 consumed; + + consumed = atomic64_read(&priv->consumed); + /* Since we inconditionally increment consumed quota for each packet + * that we see, don't go over the quota boundary in what we send to + * userspace. + */ + if (consumed > priv->quota) + consumed = priv->quota; if (nla_put_be64(skb, NFTA_QUOTA_BYTES, cpu_to_be64(priv->quota), NFTA_QUOTA_PAD) || + nla_put_be64(skb, NFTA_QUOTA_CONSUMED, cpu_to_be64(consumed), + NFTA_QUOTA_PAD) || nla_put_be32(skb, NFTA_QUOTA_FLAGS, htonl(flags))) goto nla_put_failure; return 0; -- cgit v1.2.3 From 43da04a593d8b2626f1cf4b56efe9402f6b53652 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 28 Nov 2016 00:05:44 +0100 Subject: netfilter: nf_tables: atomic dump and reset for stateful objects This patch adds a new NFT_MSG_GETOBJ_RESET command perform an atomic dump-and-reset of the stateful object. This also comes with add support for atomic dump and reset for counter and quota objects. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 3 +- include/uapi/linux/netfilter/nf_tables.h | 2 ++ net/netfilter/nf_tables_api.c | 29 ++++++++++++----- net/netfilter/nft_counter.c | 56 +++++++++++++++++++++++++++----- net/netfilter/nft_quota.c | 18 ++++++---- 5 files changed, 85 insertions(+), 23 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 903cd618f50e..6f7d6a1dc09c 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -997,7 +997,8 @@ struct nft_object_type { struct nft_object *obj); void (*destroy)(struct nft_object *obj); int (*dump)(struct sk_buff *skb, - const struct nft_object *obj); + struct nft_object *obj, + bool reset); }; int nft_register_obj(struct nft_object_type *obj_type); diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 3d47582caa80..399eac1eee91 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -89,6 +89,7 @@ enum nft_verdicts { * @NFT_MSG_NEWOBJ: create a stateful object (enum nft_obj_attributes) * @NFT_MSG_GETOBJ: get a stateful object (enum nft_obj_attributes) * @NFT_MSG_DELOBJ: delete a stateful object (enum nft_obj_attributes) + * @NFT_MSG_GETOBJ_RESET: get and reset a stateful object (enum nft_obj_attributes) */ enum nf_tables_msg_types { NFT_MSG_NEWTABLE, @@ -112,6 +113,7 @@ enum nf_tables_msg_types { NFT_MSG_NEWOBJ, NFT_MSG_GETOBJ, NFT_MSG_DELOBJ, + NFT_MSG_GETOBJ_RESET, NFT_MSG_MAX, }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 2ae717c5dcb8..bfc015af366a 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3972,14 +3972,14 @@ err1: } static int nft_object_dump(struct sk_buff *skb, unsigned int attr, - const struct nft_object *obj) + struct nft_object *obj, bool reset) { struct nlattr *nest; nest = nla_nest_start(skb, attr); if (!nest) goto nla_put_failure; - if (obj->type->dump(skb, obj) < 0) + if (obj->type->dump(skb, obj, reset) < 0) goto nla_put_failure; nla_nest_end(skb, nest); return 0; @@ -4096,7 +4096,7 @@ err1: static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, int event, u32 flags, int family, const struct nft_table *table, - const struct nft_object *obj) + struct nft_object *obj, bool reset) { struct nfgenmsg *nfmsg; struct nlmsghdr *nlh; @@ -4115,7 +4115,7 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net, nla_put_string(skb, NFTA_OBJ_NAME, obj->name) || nla_put_be32(skb, NFTA_OBJ_TYPE, htonl(obj->type->type)) || nla_put_be32(skb, NFTA_OBJ_USE, htonl(obj->use)) || - nft_object_dump(skb, NFTA_OBJ_DATA, obj)) + nft_object_dump(skb, NFTA_OBJ_DATA, obj, reset)) goto nla_put_failure; nlmsg_end(skb, nlh); @@ -4131,10 +4131,14 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); const struct nft_af_info *afi; const struct nft_table *table; - const struct nft_object *obj; unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct nft_object *obj; + bool reset = false; + + if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) + reset = true; rcu_read_lock(); cb->seq = net->nft.base_seq; @@ -4156,7 +4160,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) cb->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, NLM_F_MULTI | NLM_F_APPEND, - afi->family, table, obj) < 0) + afi->family, table, obj, reset) < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -4183,6 +4187,7 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, const struct nft_table *table; struct nft_object *obj; struct sk_buff *skb2; + bool reset = false; u32 objtype; int err; @@ -4214,9 +4219,12 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, if (!skb2) return -ENOMEM; + if (NFNL_MSG_TYPE(nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) + reset = true; + err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid, nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, - family, table, obj); + family, table, obj, reset); if (err < 0) goto err; @@ -4291,7 +4299,7 @@ static int nf_tables_obj_notify(const struct nft_ctx *ctx, err = nf_tables_fill_obj_info(skb, ctx->net, ctx->portid, ctx->seq, event, 0, ctx->afi->family, ctx->table, - obj); + obj, false); if (err < 0) { kfree_skb(skb); goto err; @@ -4482,6 +4490,11 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, + [NFT_MSG_GETOBJ_RESET] = { + .call = nf_tables_getobj, + .attr_count = NFTA_OBJ_MAX, + .policy = nft_obj_policy, + }, }; static void nft_chain_commit_update(struct nft_trans *trans) diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 6f3dd429f865..f6a02c5071c2 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -100,10 +100,10 @@ static void nft_counter_obj_destroy(struct nft_object *obj) nft_counter_do_destroy(priv); } -static void nft_counter_fetch(const struct nft_counter_percpu __percpu *counter, +static void nft_counter_fetch(struct nft_counter_percpu __percpu *counter, struct nft_counter *total) { - const struct nft_counter_percpu *cpu_stats; + struct nft_counter_percpu *cpu_stats; u64 bytes, packets; unsigned int seq; int cpu; @@ -122,12 +122,52 @@ static void nft_counter_fetch(const struct nft_counter_percpu __percpu *counter, } } +static u64 __nft_counter_reset(u64 *counter) +{ + u64 ret, old; + + do { + old = *counter; + ret = cmpxchg64(counter, old, 0); + } while (ret != old); + + return ret; +} + +static void nft_counter_reset(struct nft_counter_percpu __percpu *counter, + struct nft_counter *total) +{ + struct nft_counter_percpu *cpu_stats; + u64 bytes, packets; + unsigned int seq; + int cpu; + + memset(total, 0, sizeof(*total)); + for_each_possible_cpu(cpu) { + bytes = packets = 0; + + cpu_stats = per_cpu_ptr(counter, cpu); + do { + seq = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + packets += __nft_counter_reset(&cpu_stats->counter.packets); + bytes += __nft_counter_reset(&cpu_stats->counter.bytes); + } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, seq)); + + total->packets += packets; + total->bytes += bytes; + } +} + static int nft_counter_do_dump(struct sk_buff *skb, - const struct nft_counter_percpu_priv *priv) + const struct nft_counter_percpu_priv *priv, + bool reset) { struct nft_counter total; - nft_counter_fetch(priv->counter, &total); + if (reset) + nft_counter_reset(priv->counter, &total); + else + nft_counter_fetch(priv->counter, &total); if (nla_put_be64(skb, NFTA_COUNTER_BYTES, cpu_to_be64(total.bytes), NFTA_COUNTER_PAD) || @@ -141,11 +181,11 @@ nla_put_failure: } static int nft_counter_obj_dump(struct sk_buff *skb, - const struct nft_object *obj) + struct nft_object *obj, bool reset) { - const struct nft_counter_percpu_priv *priv = nft_obj_data(obj); + struct nft_counter_percpu_priv *priv = nft_obj_data(obj); - return nft_counter_do_dump(skb, priv); + return nft_counter_do_dump(skb, priv, reset); } static const struct nla_policy nft_counter_policy[NFTA_COUNTER_MAX + 1] = { @@ -178,7 +218,7 @@ static int nft_counter_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); - return nft_counter_do_dump(skb, priv); + return nft_counter_do_dump(skb, priv, false); } static int nft_counter_init(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index 0d344209803a..5d25f57497cb 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -83,12 +83,17 @@ static int nft_quota_obj_init(const struct nlattr * const tb[], return nft_quota_do_init(tb, priv); } -static int nft_quota_do_dump(struct sk_buff *skb, const struct nft_quota *priv) +static int nft_quota_do_dump(struct sk_buff *skb, struct nft_quota *priv, + bool reset) { u32 flags = priv->invert ? NFT_QUOTA_F_INV : 0; u64 consumed; - consumed = atomic64_read(&priv->consumed); + if (reset) + consumed = atomic64_xchg(&priv->consumed, 0); + else + consumed = atomic64_read(&priv->consumed); + /* Since we inconditionally increment consumed quota for each packet * that we see, don't go over the quota boundary in what we send to * userspace. @@ -108,11 +113,12 @@ nla_put_failure: return -1; } -static int nft_quota_obj_dump(struct sk_buff *skb, const struct nft_object *obj) +static int nft_quota_obj_dump(struct sk_buff *skb, struct nft_object *obj, + bool reset) { struct nft_quota *priv = nft_obj_data(obj); - return nft_quota_do_dump(skb, priv); + return nft_quota_do_dump(skb, priv, reset); } static struct nft_object_type nft_quota_obj __read_mostly = { @@ -146,9 +152,9 @@ static int nft_quota_init(const struct nft_ctx *ctx, static int nft_quota_dump(struct sk_buff *skb, const struct nft_expr *expr) { - const struct nft_quota *priv = nft_expr_priv(expr); + struct nft_quota *priv = nft_expr_priv(expr); - return nft_quota_do_dump(skb, priv); + return nft_quota_do_dump(skb, priv, false); } static struct nft_expr_type nft_quota_type; -- cgit v1.2.3 From 1896531710abcd9a961a17d0c5c6a9f537d479b6 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 28 Nov 2016 00:05:56 +0100 Subject: netfilter: nft_quota: add depleted flag for objects Notify on depleted quota objects. The NFT_QUOTA_F_DEPLETED flag indicates we have reached overquota. Add pointer to table from nft_object, so we can use it when sending the depletion notification to userspace. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 ++ include/uapi/linux/netfilter/nf_tables.h | 1 + net/netfilter/nf_tables_api.c | 1 + net/netfilter/nft_quota.c | 36 +++++++++++++++++++++++++------- 4 files changed, 32 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 339e374c28b5..ce6fb6e83b32 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -940,6 +940,7 @@ int nft_verdict_dump(struct sk_buff *skb, int type, * struct nft_object - nf_tables stateful object * * @list: table stateful object list node + * @table: table this object belongs to * @type: pointer to object type * @data: pointer to object data * @name: name of this stateful object @@ -950,6 +951,7 @@ int nft_verdict_dump(struct sk_buff *skb, int type, struct nft_object { struct list_head list; char name[NFT_OBJ_MAXNAMELEN]; + struct nft_table *table; u32 genmask:2, use:30; /* runtime data below here */ diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 399eac1eee91..4864caca1e8e 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -983,6 +983,7 @@ enum nft_queue_attributes { enum nft_quota_flags { NFT_QUOTA_F_INV = (1 << 0), + NFT_QUOTA_F_DEPLETED = (1 << 1), }; /** diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 9d2ed3f520ef..c5419701ca79 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4075,6 +4075,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, err = PTR_ERR(obj); goto err1; } + obj->table = table; nla_strlcpy(obj->name, nla[NFTA_OBJ_NAME], NFT_OBJ_MAXNAMELEN); err = nft_trans_obj_add(&ctx, NFT_MSG_NEWOBJ, obj); diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index 5d25f57497cb..7f27ebdce7ab 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -17,7 +17,7 @@ struct nft_quota { u64 quota; - bool invert; + unsigned long flags; atomic64_t consumed; }; @@ -27,11 +27,16 @@ static inline bool nft_overquota(struct nft_quota *priv, return atomic64_add_return(skb->len, &priv->consumed) >= priv->quota; } +static inline bool nft_quota_invert(struct nft_quota *priv) +{ + return priv->flags & NFT_QUOTA_F_INV; +} + static inline void nft_quota_do_eval(struct nft_quota *priv, struct nft_regs *regs, const struct nft_pktinfo *pkt) { - if (nft_overquota(priv, pkt->skb) ^ priv->invert) + if (nft_overquota(priv, pkt->skb) ^ nft_quota_invert(priv)) regs->verdict.code = NFT_BREAK; } @@ -40,19 +45,29 @@ static const struct nla_policy nft_quota_policy[NFTA_QUOTA_MAX + 1] = { [NFTA_QUOTA_FLAGS] = { .type = NLA_U32 }, }; +#define NFT_QUOTA_DEPLETED_BIT 1 /* From NFT_QUOTA_F_DEPLETED. */ + static void nft_quota_obj_eval(struct nft_object *obj, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_quota *priv = nft_obj_data(obj); + bool overquota; - nft_quota_do_eval(priv, regs, pkt); + overquota = nft_overquota(priv, pkt->skb); + if (overquota ^ nft_quota_invert(priv)) + regs->verdict.code = NFT_BREAK; + + if (overquota && + !test_and_set_bit(NFT_QUOTA_DEPLETED_BIT, &priv->flags)) + nft_obj_notify(nft_net(pkt), obj->table, obj, 0, 0, + NFT_MSG_NEWOBJ, nft_pf(pkt), 0, GFP_ATOMIC); } static int nft_quota_do_init(const struct nlattr * const tb[], struct nft_quota *priv) { - u32 flags = 0; + unsigned long flags = 0; u64 quota; if (!tb[NFTA_QUOTA_BYTES]) @@ -66,10 +81,12 @@ static int nft_quota_do_init(const struct nlattr * const tb[], flags = ntohl(nla_get_be32(tb[NFTA_QUOTA_FLAGS])); if (flags & ~NFT_QUOTA_F_INV) return -EINVAL; + if (flags & NFT_QUOTA_F_DEPLETED) + return -EOPNOTSUPP; } priv->quota = quota; - priv->invert = (flags & NFT_QUOTA_F_INV) ? true : false; + priv->flags = flags; atomic64_set(&priv->consumed, 0); return 0; @@ -86,13 +103,16 @@ static int nft_quota_obj_init(const struct nlattr * const tb[], static int nft_quota_do_dump(struct sk_buff *skb, struct nft_quota *priv, bool reset) { - u32 flags = priv->invert ? NFT_QUOTA_F_INV : 0; + u32 flags = priv->flags; u64 consumed; - if (reset) + if (reset) { consumed = atomic64_xchg(&priv->consumed, 0); - else + if (test_and_clear_bit(NFT_QUOTA_DEPLETED_BIT, &priv->flags)) + flags |= NFT_QUOTA_F_DEPLETED; + } else { consumed = atomic64_read(&priv->consumed); + } /* Since we inconditionally increment consumed quota for each packet * that we see, don't go over the quota boundary in what we send to -- cgit v1.2.3 From 8aeff920dcc9b3f8cf43042a76428582634d9208 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 28 Nov 2016 00:06:00 +0100 Subject: netfilter: nf_tables: add stateful object reference to set elements This patch allows you to refer to stateful objects from set elements. This provides the infrastructure to create maps where the right hand side of the mapping is a stateful object. This allows us to build dictionaries of stateful objects, that you can use to perform fast lookups using any arbitrary key combination. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 9 ++++ include/uapi/linux/netfilter/nf_tables.h | 8 ++++ net/netfilter/nf_tables_api.c | 72 +++++++++++++++++++++++++++----- 3 files changed, 79 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index ce6fb6e83b32..85f0f03f1e87 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -326,6 +326,7 @@ void nft_unregister_set(struct nft_set_ops *ops); * @name: name of the set * @ktype: key type (numeric type defined by userspace, not used in the kernel) * @dtype: data type (verdict or numeric type defined by userspace) + * @objtype: object type (see NFT_OBJECT_* definitions) * @size: maximum set size * @nelems: number of elements * @ndeact: number of deactivated elements queued for removal @@ -347,6 +348,7 @@ struct nft_set { char name[NFT_SET_MAXNAMELEN]; u32 ktype; u32 dtype; + u32 objtype; u32 size; atomic_t nelems; u32 ndeact; @@ -416,6 +418,7 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, * @NFT_SET_EXT_EXPIRATION: element expiration time * @NFT_SET_EXT_USERDATA: user data associated with the element * @NFT_SET_EXT_EXPR: expression assiociated with the element + * @NFT_SET_EXT_OBJREF: stateful object reference associated with element * @NFT_SET_EXT_NUM: number of extension types */ enum nft_set_extensions { @@ -426,6 +429,7 @@ enum nft_set_extensions { NFT_SET_EXT_EXPIRATION, NFT_SET_EXT_USERDATA, NFT_SET_EXT_EXPR, + NFT_SET_EXT_OBJREF, NFT_SET_EXT_NUM }; @@ -554,6 +558,11 @@ static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set, return elem + set->ops->elemsize; } +static inline struct nft_object **nft_set_ext_obj(const struct nft_set_ext *ext) +{ + return nft_set_ext(ext, NFT_SET_EXT_OBJREF); +} + void *nft_set_elem_init(const struct nft_set *set, const struct nft_set_ext_tmpl *tmpl, const u32 *key, const u32 *data, diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 4864caca1e8e..a6b52dbff08c 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -255,6 +255,7 @@ enum nft_rule_compat_attributes { * @NFT_SET_MAP: set is used as a dictionary * @NFT_SET_TIMEOUT: set uses timeouts * @NFT_SET_EVAL: set contains expressions for evaluation + * @NFT_SET_OBJECT: set contains stateful objects */ enum nft_set_flags { NFT_SET_ANONYMOUS = 0x1, @@ -263,6 +264,7 @@ enum nft_set_flags { NFT_SET_MAP = 0x8, NFT_SET_TIMEOUT = 0x10, NFT_SET_EVAL = 0x20, + NFT_SET_OBJECT = 0x40, }; /** @@ -304,6 +306,7 @@ enum nft_set_desc_attributes { * @NFTA_SET_TIMEOUT: default timeout value (NLA_U64) * @NFTA_SET_GC_INTERVAL: garbage collection interval (NLA_U32) * @NFTA_SET_USERDATA: user data (NLA_BINARY) + * @NFTA_SET_OBJ_TYPE: stateful object type (NLA_U32: NFT_OBJECT_*) */ enum nft_set_attributes { NFTA_SET_UNSPEC, @@ -321,6 +324,7 @@ enum nft_set_attributes { NFTA_SET_GC_INTERVAL, NFTA_SET_USERDATA, NFTA_SET_PAD, + NFTA_SET_OBJ_TYPE, __NFTA_SET_MAX }; #define NFTA_SET_MAX (__NFTA_SET_MAX - 1) @@ -344,6 +348,7 @@ enum nft_set_elem_flags { * @NFTA_SET_ELEM_EXPIRATION: expiration time (NLA_U64) * @NFTA_SET_ELEM_USERDATA: user data (NLA_BINARY) * @NFTA_SET_ELEM_EXPR: expression (NLA_NESTED: nft_expr_attributes) + * @NFTA_SET_ELEM_OBJREF: stateful object reference (NLA_STRING) */ enum nft_set_elem_attributes { NFTA_SET_ELEM_UNSPEC, @@ -355,6 +360,7 @@ enum nft_set_elem_attributes { NFTA_SET_ELEM_USERDATA, NFTA_SET_ELEM_EXPR, NFTA_SET_ELEM_PAD, + NFTA_SET_ELEM_OBJREF, __NFTA_SET_ELEM_MAX }; #define NFTA_SET_ELEM_MAX (__NFTA_SET_ELEM_MAX - 1) @@ -1207,6 +1213,8 @@ enum nft_fib_flags { #define NFT_OBJECT_UNSPEC 0 #define NFT_OBJECT_COUNTER 1 #define NFT_OBJECT_QUOTA 2 +#define __NFT_OBJECT_MAX 3 +#define NFT_OBJECT_MAX (__NFT_OBJECT_MAX - 1) /** * enum nft_object_attributes - nf_tables stateful object netlink attributes diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c5419701ca79..8228714c42d5 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2452,6 +2452,7 @@ static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = { [NFTA_SET_GC_INTERVAL] = { .type = NLA_U32 }, [NFTA_SET_USERDATA] = { .type = NLA_BINARY, .len = NFT_USERDATA_MAXLEN }, + [NFTA_SET_OBJ_TYPE] = { .type = NLA_U32 }, }; static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = { @@ -2609,6 +2610,9 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, if (nla_put_be32(skb, NFTA_SET_DATA_LEN, htonl(set->dlen))) goto nla_put_failure; } + if (set->flags & NFT_SET_OBJECT && + nla_put_be32(skb, NFTA_SET_OBJ_TYPE, htonl(set->objtype))) + goto nla_put_failure; if (set->timeout && nla_put_be64(skb, NFTA_SET_TIMEOUT, @@ -2838,7 +2842,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, unsigned int size; bool create; u64 timeout; - u32 ktype, dtype, flags, policy, gc_int; + u32 ktype, dtype, flags, policy, gc_int, objtype; struct nft_set_desc desc; unsigned char *udata; u16 udlen; @@ -2868,11 +2872,12 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, flags = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS])); if (flags & ~(NFT_SET_ANONYMOUS | NFT_SET_CONSTANT | NFT_SET_INTERVAL | NFT_SET_TIMEOUT | - NFT_SET_MAP | NFT_SET_EVAL)) + NFT_SET_MAP | NFT_SET_EVAL | + NFT_SET_OBJECT)) return -EINVAL; - /* Only one of both operations is supported */ - if ((flags & (NFT_SET_MAP | NFT_SET_EVAL)) == - (NFT_SET_MAP | NFT_SET_EVAL)) + /* Only one of these operations is supported */ + if ((flags & (NFT_SET_MAP | NFT_SET_EVAL | NFT_SET_OBJECT)) == + (NFT_SET_MAP | NFT_SET_EVAL | NFT_SET_OBJECT)) return -EOPNOTSUPP; } @@ -2897,6 +2902,19 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, } else if (flags & NFT_SET_MAP) return -EINVAL; + if (nla[NFTA_SET_OBJ_TYPE] != NULL) { + if (!(flags & NFT_SET_OBJECT)) + return -EINVAL; + + objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE])); + if (objtype == NFT_OBJECT_UNSPEC || + objtype > NFT_OBJECT_MAX) + return -EINVAL; + } else if (flags & NFT_SET_OBJECT) + return -EINVAL; + else + objtype = NFT_OBJECT_UNSPEC; + timeout = 0; if (nla[NFTA_SET_TIMEOUT] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) @@ -2984,6 +3002,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, set->ktype = ktype; set->klen = desc.klen; set->dtype = dtype; + set->objtype = objtype; set->dlen = desc.dlen; set->flags = flags; set->size = desc.size; @@ -3126,6 +3145,10 @@ const struct nft_set_ext_type nft_set_ext_types[] = { [NFT_SET_EXT_EXPR] = { .align = __alignof__(struct nft_expr), }, + [NFT_SET_EXT_OBJREF] = { + .len = sizeof(struct nft_object *), + .align = __alignof__(struct nft_object *), + }, [NFT_SET_EXT_FLAGS] = { .len = sizeof(u8), .align = __alignof__(u8), @@ -3214,6 +3237,11 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, nft_set_ext_expr(ext)) < 0) goto nla_put_failure; + if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) && + nla_put_string(skb, NFTA_SET_ELEM_OBJREF, + (*nft_set_ext_obj(ext))->name) < 0) + goto nla_put_failure; + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && nla_put_be32(skb, NFTA_SET_ELEM_FLAGS, htonl(*nft_set_ext_flags(ext)))) @@ -3508,7 +3536,8 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, nft_data_uninit(nft_set_ext_data(ext), set->dtype); if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) nf_tables_expr_destroy(NULL, nft_set_ext_expr(ext)); - + if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) + (*nft_set_ext_obj(ext))->use--; kfree(elem); } EXPORT_SYMBOL_GPL(nft_set_elem_destroy); @@ -3533,11 +3562,13 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr, u32 nlmsg_flags) { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; + u8 genmask = nft_genmask_next(ctx->net); struct nft_data_desc d1, d2; struct nft_set_ext_tmpl tmpl; struct nft_set_ext *ext, *ext2; struct nft_set_elem elem; struct nft_set_binding *binding; + struct nft_object *obj = NULL; struct nft_userdata *udata; struct nft_data data; enum nft_registers dreg; @@ -3600,6 +3631,20 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT); } + if (nla[NFTA_SET_ELEM_OBJREF] != NULL) { + if (!(set->flags & NFT_SET_OBJECT)) { + err = -EINVAL; + goto err2; + } + obj = nf_tables_obj_lookup(ctx->table, nla[NFTA_SET_ELEM_OBJREF], + set->objtype, genmask); + if (IS_ERR(obj)) { + err = PTR_ERR(obj); + goto err2; + } + nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF); + } + if (nla[NFTA_SET_ELEM_DATA] != NULL) { err = nft_data_init(ctx, &data, sizeof(data), &d2, nla[NFTA_SET_ELEM_DATA]); @@ -3658,6 +3703,10 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, udata->len = ulen - 1; nla_memcpy(&udata->data, nla[NFTA_SET_ELEM_USERDATA], ulen); } + if (obj) { + *nft_set_ext_obj(ext) = obj; + obj->use++; + } trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set); if (trans == NULL) @@ -3667,10 +3716,13 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = set->ops->insert(ctx->net, set, &elem, &ext2); if (err) { if (err == -EEXIST) { - if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && - nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) && - memcmp(nft_set_ext_data(ext), - nft_set_ext_data(ext2), set->dlen) != 0) + if ((nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && + nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) && + memcmp(nft_set_ext_data(ext), + nft_set_ext_data(ext2), set->dlen) != 0) || + (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) && + nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF) && + *nft_set_ext_obj(ext) != *nft_set_ext_obj(ext2))) err = -EBUSY; else if (!(nlmsg_flags & NLM_F_EXCL)) err = 0; -- cgit v1.2.3 From 63aea29060025fd2732680aa48a6b97687b93af8 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 28 Nov 2016 00:06:03 +0100 Subject: netfilter: nft_objref: support for stateful object maps This patch allows us to refer to stateful object dictionaries, the source register indicates the key data to be used to look up for the corresponding state object. We can refer to these maps through names or, alternatively, the map transaction id. This allows us to refer to both anonymous and named maps. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 6 ++ net/netfilter/nf_tables_api.c | 4 ++ net/netfilter/nft_objref.c | 116 ++++++++++++++++++++++++++++++- 3 files changed, 125 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index a6b52dbff08c..881d49e94569 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1153,11 +1153,17 @@ enum nft_fwd_attributes { * * @NFTA_OBJREF_IMM_TYPE: object type for immediate reference (NLA_U32: nft_register) * @NFTA_OBJREF_IMM_NAME: object name for immediate reference (NLA_STRING) + * @NFTA_OBJREF_SET_SREG: source register of the data to look for (NLA_U32: nft_registers) + * @NFTA_OBJREF_SET_NAME: name of the set where to look for (NLA_STRING) + * @NFTA_OBJREF_SET_ID: id of the set where to look for in this transaction (NLA_U32) */ enum nft_objref_attributes { NFTA_OBJREF_UNSPEC, NFTA_OBJREF_IMM_TYPE, NFTA_OBJREF_IMM_NAME, + NFTA_OBJREF_SET_SREG, + NFTA_OBJREF_SET_NAME, + NFTA_OBJREF_SET_ID, __NFTA_OBJREF_MAX }; #define NFTA_OBJREF_MAX (__NFTA_OBJREF_MAX - 1) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 8228714c42d5..b4db5bf4c135 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2504,6 +2504,7 @@ struct nft_set *nf_tables_set_lookup(const struct nft_table *table, } return ERR_PTR(-ENOENT); } +EXPORT_SYMBOL_GPL(nf_tables_set_lookup); struct nft_set *nf_tables_set_lookup_byid(const struct net *net, const struct nlattr *nla, @@ -2522,6 +2523,7 @@ struct nft_set *nf_tables_set_lookup_byid(const struct net *net, } return ERR_PTR(-ENOENT); } +EXPORT_SYMBOL_GPL(nf_tables_set_lookup_byid); static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set, const char *name) @@ -3124,6 +3126,7 @@ bind: list_add_tail_rcu(&binding->list, &set->bindings); return 0; } +EXPORT_SYMBOL_GPL(nf_tables_bind_set); void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding) @@ -3134,6 +3137,7 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, nft_is_active(ctx->net, set)) nf_tables_set_destroy(ctx, set); } +EXPORT_SYMBOL_GPL(nf_tables_unbind_set); const struct nft_set_ext_type nft_set_ext_types[] = { [NFT_SET_EXT_KEY] = { diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 23820f796aad..415a65ba2b85 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -81,14 +81,128 @@ static const struct nft_expr_ops nft_objref_ops = { .dump = nft_objref_dump, }; +struct nft_objref_map { + struct nft_set *set; + enum nft_registers sreg:8; + struct nft_set_binding binding; +}; + +static void nft_objref_map_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_objref_map *priv = nft_expr_priv(expr); + const struct nft_set *set = priv->set; + const struct nft_set_ext *ext; + struct nft_object *obj; + bool found; + + found = set->ops->lookup(nft_net(pkt), set, ®s->data[priv->sreg], + &ext); + if (!found) { + regs->verdict.code = NFT_BREAK; + return; + } + obj = *nft_set_ext_obj(ext); + obj->type->eval(obj, regs, pkt); +} + +static int nft_objref_map_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_objref_map *priv = nft_expr_priv(expr); + u8 genmask = nft_genmask_next(ctx->net); + struct nft_set *set; + int err; + + set = nf_tables_set_lookup(ctx->table, tb[NFTA_OBJREF_SET_NAME], genmask); + if (IS_ERR(set)) { + if (tb[NFTA_OBJREF_SET_ID]) { + set = nf_tables_set_lookup_byid(ctx->net, + tb[NFTA_OBJREF_SET_ID], + genmask); + } + if (IS_ERR(set)) + return PTR_ERR(set); + } + + if (!(set->flags & NFT_SET_OBJECT)) + return -EINVAL; + + priv->sreg = nft_parse_register(tb[NFTA_OBJREF_SET_SREG]); + err = nft_validate_register_load(priv->sreg, set->klen); + if (err < 0) + return err; + + priv->binding.flags = set->flags & NFT_SET_OBJECT; + + err = nf_tables_bind_set(ctx, set, &priv->binding); + if (err < 0) + return err; + + priv->set = set; + return 0; +} + +static int nft_objref_map_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_objref_map *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_OBJREF_SET_SREG, priv->sreg) || + nla_put_string(skb, NFTA_OBJREF_SET_NAME, priv->set->name)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static void nft_objref_map_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + struct nft_objref_map *priv = nft_expr_priv(expr); + + nf_tables_unbind_set(ctx, priv->set, &priv->binding); +} + +static struct nft_expr_type nft_objref_type; +static const struct nft_expr_ops nft_objref_map_ops = { + .type = &nft_objref_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_objref_map)), + .eval = nft_objref_map_eval, + .init = nft_objref_map_init, + .destroy = nft_objref_map_destroy, + .dump = nft_objref_map_dump, +}; + +static const struct nft_expr_ops * +nft_objref_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + if (tb[NFTA_OBJREF_SET_SREG] && + (tb[NFTA_OBJREF_SET_NAME] || + tb[NFTA_OBJREF_SET_ID])) + return &nft_objref_map_ops; + else if (tb[NFTA_OBJREF_IMM_NAME] && + tb[NFTA_OBJREF_IMM_TYPE]) + return &nft_objref_ops; + + return ERR_PTR(-EOPNOTSUPP); +} + static const struct nla_policy nft_objref_policy[NFTA_OBJREF_MAX + 1] = { [NFTA_OBJREF_IMM_NAME] = { .type = NLA_STRING }, [NFTA_OBJREF_IMM_TYPE] = { .type = NLA_U32 }, + [NFTA_OBJREF_SET_SREG] = { .type = NLA_U32 }, + [NFTA_OBJREF_SET_NAME] = { .type = NLA_STRING }, + [NFTA_OBJREF_SET_ID] = { .type = NLA_U32 }, }; static struct nft_expr_type nft_objref_type __read_mostly = { .name = "objref", - .ops = &nft_objref_ops, + .select_ops = nft_objref_select_ops, .policy = nft_objref_policy, .maxattr = NFTA_OBJREF_MAX, .owner = THIS_MODULE, -- cgit v1.2.3 From 2c16d60332643e90d4fa244f4a706c454b8c7569 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 6 Dec 2016 16:25:02 -0500 Subject: netfilter: xt_bpf: support ebpf Add support for attaching an eBPF object by file descriptor. The iptables binary can be called with a path to an elf object or a pinned bpf object. Also pass the mode and path to the kernel to be able to return it later for iptables dump and save. Signed-off-by: Willem de Bruijn Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/xt_bpf.h | 21 ++++++++ net/netfilter/xt_bpf.c | 96 +++++++++++++++++++++++++++++------ 2 files changed, 101 insertions(+), 16 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 1fad2c27ac32..b97725af2ac0 100644 --- a/include/uapi/linux/netfilter/xt_bpf.h +++ b/include/uapi/linux/netfilter/xt_bpf.h @@ -2,9 +2,11 @@ #define _XT_BPF_H #include +#include #include #define XT_BPF_MAX_NUM_INSTR 64 +#define XT_BPF_PATH_MAX (XT_BPF_MAX_NUM_INSTR * sizeof(struct sock_filter)) struct bpf_prog; @@ -16,4 +18,23 @@ struct xt_bpf_info { struct bpf_prog *filter __attribute__((aligned(8))); }; +enum xt_bpf_modes { + XT_BPF_MODE_BYTECODE, + XT_BPF_MODE_FD_PINNED, + XT_BPF_MODE_FD_ELF, +}; + +struct xt_bpf_info_v1 { + __u16 mode; + __u16 bpf_program_num_elem; + __s32 fd; + union { + struct sock_filter bpf_program[XT_BPF_MAX_NUM_INSTR]; + char path[XT_BPF_PATH_MAX]; + }; + + /* only used in the kernel */ + struct bpf_prog *filter __attribute__((aligned(8))); +}; + #endif /*_XT_BPF_H */ diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index dffee9d47ec4..2dedaa23ab0a 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -20,15 +21,15 @@ MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_bpf"); MODULE_ALIAS("ip6t_bpf"); -static int bpf_mt_check(const struct xt_mtchk_param *par) +static int __bpf_mt_check_bytecode(struct sock_filter *insns, __u16 len, + struct bpf_prog **ret) { - struct xt_bpf_info *info = par->matchinfo; struct sock_fprog_kern program; - program.len = info->bpf_program_num_elem; - program.filter = info->bpf_program; + program.len = len; + program.filter = insns; - if (bpf_prog_create(&info->filter, &program)) { + if (bpf_prog_create(ret, &program)) { pr_info("bpf: check failed: parse error\n"); return -EINVAL; } @@ -36,6 +37,42 @@ static int bpf_mt_check(const struct xt_mtchk_param *par) return 0; } +static int __bpf_mt_check_fd(int fd, struct bpf_prog **ret) +{ + struct bpf_prog *prog; + + prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + *ret = prog; + return 0; +} + +static int bpf_mt_check(const struct xt_mtchk_param *par) +{ + struct xt_bpf_info *info = par->matchinfo; + + return __bpf_mt_check_bytecode(info->bpf_program, + info->bpf_program_num_elem, + &info->filter); +} + +static int bpf_mt_check_v1(const struct xt_mtchk_param *par) +{ + struct xt_bpf_info_v1 *info = par->matchinfo; + + if (info->mode == XT_BPF_MODE_BYTECODE) + return __bpf_mt_check_bytecode(info->bpf_program, + info->bpf_program_num_elem, + &info->filter); + else if (info->mode == XT_BPF_MODE_FD_PINNED || + info->mode == XT_BPF_MODE_FD_ELF) + return __bpf_mt_check_fd(info->fd, &info->filter); + else + return -EINVAL; +} + static bool bpf_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_bpf_info *info = par->matchinfo; @@ -43,31 +80,58 @@ static bool bpf_mt(const struct sk_buff *skb, struct xt_action_param *par) return BPF_PROG_RUN(info->filter, skb); } +static bool bpf_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_bpf_info_v1 *info = par->matchinfo; + + return !!bpf_prog_run_save_cb(info->filter, (struct sk_buff *) skb); +} + static void bpf_mt_destroy(const struct xt_mtdtor_param *par) { const struct xt_bpf_info *info = par->matchinfo; + + bpf_prog_destroy(info->filter); +} + +static void bpf_mt_destroy_v1(const struct xt_mtdtor_param *par) +{ + const struct xt_bpf_info_v1 *info = par->matchinfo; + bpf_prog_destroy(info->filter); } -static struct xt_match bpf_mt_reg __read_mostly = { - .name = "bpf", - .revision = 0, - .family = NFPROTO_UNSPEC, - .checkentry = bpf_mt_check, - .match = bpf_mt, - .destroy = bpf_mt_destroy, - .matchsize = sizeof(struct xt_bpf_info), - .me = THIS_MODULE, +static struct xt_match bpf_mt_reg[] __read_mostly = { + { + .name = "bpf", + .revision = 0, + .family = NFPROTO_UNSPEC, + .checkentry = bpf_mt_check, + .match = bpf_mt, + .destroy = bpf_mt_destroy, + .matchsize = sizeof(struct xt_bpf_info), + .me = THIS_MODULE, + }, + { + .name = "bpf", + .revision = 1, + .family = NFPROTO_UNSPEC, + .checkentry = bpf_mt_check_v1, + .match = bpf_mt_v1, + .destroy = bpf_mt_destroy_v1, + .matchsize = sizeof(struct xt_bpf_info_v1), + .me = THIS_MODULE, + }, }; static int __init bpf_mt_init(void) { - return xt_register_match(&bpf_mt_reg); + return xt_register_matches(bpf_mt_reg, ARRAY_SIZE(bpf_mt_reg)); } static void __exit bpf_mt_exit(void) { - xt_unregister_match(&bpf_mt_reg); + xt_unregister_matches(bpf_mt_reg, ARRAY_SIZE(bpf_mt_reg)); } module_init(bpf_mt_init); -- cgit v1.2.3 From faa3ffce78298b2b782297765cffd05f52fed9d4 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Wed, 7 Dec 2016 14:03:10 +0200 Subject: net/sched: cls_flower: Add support for matching on flags Add UAPI to provide set of flags for matching, where the flags provided from user-space are mapped to flow-dissector flags. The 1st flag allows to match on whether the packet is an IP fragment and corresponds to the FLOW_DIS_IS_FRAGMENT flag. Signed-off-by: Or Gerlitz Reviewed-by: Paul Blakey Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 7 ++++ net/sched/cls_flower.c | 76 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 83 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 1adc0b654996..0ad9f0bce043 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -458,11 +458,18 @@ enum { TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK, /* be16 */ TCA_FLOWER_KEY_ENC_UDP_DST_PORT, /* be16 */ TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, /* be16 */ + + TCA_FLOWER_KEY_FLAGS, /* be32 */ + TCA_FLOWER_KEY_FLAGS_MASK, /* be32 */ __TCA_FLOWER_MAX, }; #define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1) +enum { + TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0), +}; + /* Match-all classifier */ enum { diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 29a9e6d9f274..6c7e1f5052c9 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -386,6 +386,8 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_ENC_UDP_DST_PORT] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_FLAGS] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_FLAGS_MASK] = { .type = NLA_U32 }, }; static void fl_set_key_val(struct nlattr **tb, @@ -420,6 +422,39 @@ static void fl_set_key_vlan(struct nlattr **tb, } } +static void fl_set_key_flag(u32 flower_key, u32 flower_mask, + u32 *dissector_key, u32 *dissector_mask, + u32 flower_flag_bit, u32 dissector_flag_bit) +{ + if (flower_mask & flower_flag_bit) { + *dissector_mask |= dissector_flag_bit; + if (flower_key & flower_flag_bit) + *dissector_key |= dissector_flag_bit; + } +} + +static void fl_set_key_flags(struct nlattr **tb, + u32 *flags_key, u32 *flags_mask) +{ + u32 key, mask; + + if (!tb[TCA_FLOWER_KEY_FLAGS]) + return; + + key = be32_to_cpu(nla_get_u32(tb[TCA_FLOWER_KEY_FLAGS])); + + if (!tb[TCA_FLOWER_KEY_FLAGS_MASK]) + mask = ~0; + else + mask = be32_to_cpu(nla_get_u32(tb[TCA_FLOWER_KEY_FLAGS_MASK])); + + *flags_key = 0; + *flags_mask = 0; + + fl_set_key_flag(key, mask, flags_key, flags_mask, + TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT, FLOW_DIS_IS_FRAGMENT); +} + static int fl_set_key(struct net *net, struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask) { @@ -546,6 +581,8 @@ static int fl_set_key(struct net *net, struct nlattr **tb, &mask->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, sizeof(key->enc_tp.dst)); + fl_set_key_flags(tb, &key->control.flags, &mask->control.flags); + return 0; } @@ -880,6 +917,42 @@ static int fl_dump_key_vlan(struct sk_buff *skb, return 0; } +static void fl_get_key_flag(u32 dissector_key, u32 dissector_mask, + u32 *flower_key, u32 *flower_mask, + u32 flower_flag_bit, u32 dissector_flag_bit) +{ + if (dissector_mask & dissector_flag_bit) { + *flower_mask |= flower_flag_bit; + if (dissector_key & dissector_flag_bit) + *flower_key |= flower_flag_bit; + } +} + +static int fl_dump_key_flags(struct sk_buff *skb, u32 flags_key, u32 flags_mask) +{ + u32 key, mask; + __be32 _key, _mask; + int err; + + if (!memchr_inv(&flags_mask, 0, sizeof(flags_mask))) + return 0; + + key = 0; + mask = 0; + + fl_get_key_flag(flags_key, flags_mask, &key, &mask, + TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT, FLOW_DIS_IS_FRAGMENT); + + _key = cpu_to_be32(key); + _mask = cpu_to_be32(mask); + + err = nla_put(skb, TCA_FLOWER_KEY_FLAGS, 4, &_key); + if (err) + return err; + + return nla_put(skb, TCA_FLOWER_KEY_FLAGS_MASK, 4, &_mask); +} + static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { @@ -1015,6 +1088,9 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, sizeof(key->enc_tp.dst))) goto nla_put_failure; + if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags)) + goto nla_put_failure; + nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags); if (tcf_exts_dump(skb, &f->exts)) -- cgit v1.2.3 From 7b684884fbfab33251115fa5054fb821c34b93be Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 7 Dec 2016 13:48:28 +0100 Subject: net/sched: cls_flower: Support matching on ICMP type and code Support matching on ICMP type and code. Example usage: tc qdisc add dev eth0 ingress tc filter add dev eth0 protocol ip parent ffff: flower \ indev eth0 ip_proto icmp type 8 code 0 action drop tc filter add dev eth0 protocol ipv6 parent ffff: flower \ indev eth0 ip_proto icmpv6 type 128 code 0 action drop Signed-off-by: Simon Horman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 10 +++++++++ net/sched/cls_flower.c | 53 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 63 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 0ad9f0bce043..cb4bcdc58543 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -461,6 +461,16 @@ enum { TCA_FLOWER_KEY_FLAGS, /* be32 */ TCA_FLOWER_KEY_FLAGS_MASK, /* be32 */ + + TCA_FLOWER_KEY_ICMPV4_CODE, /* u8 */ + TCA_FLOWER_KEY_ICMPV4_CODE_MASK,/* u8 */ + TCA_FLOWER_KEY_ICMPV4_TYPE, /* u8 */ + TCA_FLOWER_KEY_ICMPV4_TYPE_MASK,/* u8 */ + TCA_FLOWER_KEY_ICMPV6_CODE, /* u8 */ + TCA_FLOWER_KEY_ICMPV6_CODE_MASK,/* u8 */ + TCA_FLOWER_KEY_ICMPV6_TYPE, /* u8 */ + TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,/* u8 */ + __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 6c7e1f5052c9..e040c5140f61 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -39,6 +39,7 @@ struct fl_flow_key { struct flow_dissector_key_ipv6_addrs ipv6; }; struct flow_dissector_key_ports tp; + struct flow_dissector_key_icmp icmp; struct flow_dissector_key_keyid enc_key_id; union { struct flow_dissector_key_ipv4_addrs enc_ipv4; @@ -388,6 +389,14 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_FLAGS] = { .type = NLA_U32 }, [TCA_FLOWER_KEY_FLAGS_MASK] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_ICMPV4_TYPE] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ICMPV4_TYPE_MASK] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ICMPV4_CODE] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ICMPV4_CODE_MASK] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ICMPV6_TYPE] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ICMPV6_TYPE_MASK] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ICMPV6_CODE] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ICMPV6_CODE_MASK] = { .type = NLA_U8 }, }; static void fl_set_key_val(struct nlattr **tb, @@ -537,6 +546,26 @@ static int fl_set_key(struct net *net, struct nlattr **tb, fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_SCTP_DST, &mask->tp.dst, TCA_FLOWER_KEY_SCTP_DST_MASK, sizeof(key->tp.dst)); + } else if (key->basic.n_proto == htons(ETH_P_IP) && + key->basic.ip_proto == IPPROTO_ICMP) { + fl_set_key_val(tb, &key->icmp.type, TCA_FLOWER_KEY_ICMPV4_TYPE, + &mask->icmp.type, + TCA_FLOWER_KEY_ICMPV4_TYPE_MASK, + sizeof(key->icmp.type)); + fl_set_key_val(tb, &key->icmp.code, TCA_FLOWER_KEY_ICMPV4_CODE, + &mask->icmp.code, + TCA_FLOWER_KEY_ICMPV4_CODE_MASK, + sizeof(key->icmp.code)); + } else if (key->basic.n_proto == htons(ETH_P_IPV6) && + key->basic.ip_proto == IPPROTO_ICMPV6) { + fl_set_key_val(tb, &key->icmp.type, TCA_FLOWER_KEY_ICMPV6_TYPE, + &mask->icmp.type, + TCA_FLOWER_KEY_ICMPV6_TYPE_MASK, + sizeof(key->icmp.type)); + fl_set_key_val(tb, &key->icmp.code, TCA_FLOWER_KEY_ICMPV4_CODE, + &mask->icmp.code, + TCA_FLOWER_KEY_ICMPV4_CODE_MASK, + sizeof(key->icmp.code)); } if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] || @@ -648,6 +677,8 @@ static void fl_init_dissector(struct cls_fl_head *head, FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6); FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, FLOW_DISSECTOR_KEY_PORTS, tp); + FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FLOW_DISSECTOR_KEY_ICMP, icmp); FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, FLOW_DISSECTOR_KEY_VLAN, vlan); FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, @@ -1050,6 +1081,28 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, &mask->tp.dst, TCA_FLOWER_KEY_SCTP_DST_MASK, sizeof(key->tp.dst)))) goto nla_put_failure; + else if (key->basic.n_proto == htons(ETH_P_IP) && + key->basic.ip_proto == IPPROTO_ICMP && + (fl_dump_key_val(skb, &key->icmp.type, + TCA_FLOWER_KEY_ICMPV4_TYPE, &mask->icmp.type, + TCA_FLOWER_KEY_ICMPV4_TYPE_MASK, + sizeof(key->icmp.type)) || + fl_dump_key_val(skb, &key->icmp.code, + TCA_FLOWER_KEY_ICMPV4_CODE, &mask->icmp.code, + TCA_FLOWER_KEY_ICMPV4_CODE_MASK, + sizeof(key->icmp.code)))) + goto nla_put_failure; + else if (key->basic.n_proto == htons(ETH_P_IPV6) && + key->basic.ip_proto == IPPROTO_ICMPV6 && + (fl_dump_key_val(skb, &key->icmp.type, + TCA_FLOWER_KEY_ICMPV6_TYPE, &mask->icmp.type, + TCA_FLOWER_KEY_ICMPV6_TYPE_MASK, + sizeof(key->icmp.type)) || + fl_dump_key_val(skb, &key->icmp.code, + TCA_FLOWER_KEY_ICMPV6_CODE, &mask->icmp.code, + TCA_FLOWER_KEY_ICMPV6_CODE_MASK, + sizeof(key->icmp.code)))) + goto nla_put_failure; if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS && (fl_dump_key_val(skb, &key->enc_ipv4.src, -- cgit v1.2.3 From 17bedab2723145d17b14084430743549e6943d03 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 7 Dec 2016 15:53:11 -0800 Subject: bpf: xdp: Allow head adjustment in XDP prog This patch allows XDP prog to extend/remove the packet data at the head (like adding or removing header). It is done by adding a new XDP helper bpf_xdp_adjust_head(). It also renames bpf_helper_changes_skb_data() to bpf_helper_changes_pkt_data() to better reflect that XDP prog does not work on skb. This patch adds one "xdp_adjust_head" bit to bpf_prog for the XDP-capable driver to check if the XDP prog requires bpf_xdp_adjust_head() support. The driver can then decide to error out during XDP_SETUP_PROG. Signed-off-by: Martin KaFai Lau Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: John Fastabend Signed-off-by: David S. Miller --- arch/powerpc/net/bpf_jit_comp64.c | 4 ++-- arch/s390/net/bpf_jit_comp.c | 2 +- arch/x86/net/bpf_jit_comp.c | 2 +- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 5 ++++ drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 5 ++++ .../net/ethernet/netronome/nfp/nfp_net_common.c | 4 ++++ drivers/net/ethernet/qlogic/qede/qede_main.c | 5 ++++ include/linux/filter.h | 6 +++-- include/uapi/linux/bpf.h | 11 ++++++++- kernel/bpf/core.c | 2 +- kernel/bpf/syscall.c | 2 ++ kernel/bpf/verifier.c | 2 +- net/core/filter.c | 28 ++++++++++++++++++++-- 13 files changed, 67 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 0fe98a567125..73a5cf18fd84 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -766,7 +766,7 @@ emit_clear: func = (u8 *) __bpf_call_base + imm; /* Save skb pointer if we need to re-cache skb data */ - if (bpf_helper_changes_skb_data(func)) + if (bpf_helper_changes_pkt_data(func)) PPC_BPF_STL(3, 1, bpf_jit_stack_local(ctx)); bpf_jit_emit_func_call(image, ctx, (u64)func); @@ -775,7 +775,7 @@ emit_clear: PPC_MR(b2p[BPF_REG_0], 3); /* refresh skb cache */ - if (bpf_helper_changes_skb_data(func)) { + if (bpf_helper_changes_pkt_data(func)) { /* reload skb pointer to r3 */ PPC_BPF_LL(3, 1, bpf_jit_stack_local(ctx)); bpf_jit_emit_skb_loads(image, ctx); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index bee281f3163d..167b31b186c1 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -981,7 +981,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i EMIT2(0x0d00, REG_14, REG_W1); /* lgr %b0,%r2: load return value into %b0 */ EMIT4(0xb9040000, BPF_REG_0, REG_2); - if (bpf_helper_changes_skb_data((void *)func)) { + if (bpf_helper_changes_pkt_data((void *)func)) { jit->seen |= SEEN_SKB_CHANGE; /* lg %b1,ST_OFF_SKBP(%r15) */ EMIT6_DISP_LH(0xe3000000, 0x0004, BPF_REG_1, REG_0, diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index fe04a04dab8e..e76d1af60f7a 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -853,7 +853,7 @@ xadd: if (is_imm8(insn->off)) func = (u8 *) __bpf_call_base + imm32; jmp_offset = func - (image + addrs[i]); if (seen_ld_abs) { - reload_skb_data = bpf_helper_changes_skb_data(func); + reload_skb_data = bpf_helper_changes_pkt_data(func); if (reload_skb_data) { EMIT1(0x57); /* push %rdi */ jmp_offset += 22; /* pop, mov, sub, mov */ diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 49a81f1fc1d6..f441eda63bec 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2686,6 +2686,11 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog) int err; int i; + if (prog && prog->xdp_adjust_head) { + en_err(priv, "Does not support bpf_xdp_adjust_head()\n"); + return -EOPNOTSUPP; + } + xdp_ring_num = prog ? priv->rx_ring_num : 0; /* No need to reconfigure buffers when simply swapping the diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 07020276fe73..cbfa38fc72c0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3183,6 +3183,11 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) bool reset, was_opened; int i; + if (prog && prog->xdp_adjust_head) { + netdev_err(netdev, "Does not support bpf_xdp_adjust_head()\n"); + return -EOPNOTSUPP; + } + mutex_lock(&priv->state_lock); if ((netdev->features & NETIF_F_LRO) && prog) { diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 00d9a03be31d..e8d448109e03 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -2946,6 +2946,10 @@ static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog) }; int err; + if (prog && prog->xdp_adjust_head) { + nn_err(nn, "Does not support bpf_xdp_adjust_head()\n"); + return -EOPNOTSUPP; + } if (!prog && !nn->xdp_prog) return 0; if (prog && nn->xdp_prog) { diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index cf1dd1436d93..aecdd1c5c0ea 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -2507,6 +2507,11 @@ static int qede_xdp_set(struct qede_dev *edev, struct bpf_prog *prog) { struct qede_reload_args args; + if (prog && prog->xdp_adjust_head) { + DP_ERR(edev, "Does not support bpf_xdp_adjust_head()\n"); + return -EOPNOTSUPP; + } + /* If we're called, there was already a bpf reference increment */ args.func = &qede_xdp_reload_func; args.u.new_prog = prog; diff --git a/include/linux/filter.h b/include/linux/filter.h index f078d2b1cff6..6a1658308612 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -406,7 +406,8 @@ struct bpf_prog { u16 jited:1, /* Is our filter JIT'ed? */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ - dst_needed:1; /* Do we need dst entry? */ + dst_needed:1, /* Do we need dst entry? */ + xdp_adjust_head:1; /* Adjusting pkt head? */ kmemcheck_bitfield_end(meta); enum bpf_prog_type type; /* Type of BPF program */ u32 len; /* Number of filter blocks */ @@ -440,6 +441,7 @@ struct bpf_skb_data_end { struct xdp_buff { void *data; void *data_end; + void *data_hard_start; }; /* compute the linear packet data range [data, data_end) which @@ -595,7 +597,7 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); -bool bpf_helper_changes_skb_data(void *func); +bool bpf_helper_changes_pkt_data(void *func); struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6123d9b8e828..0eb0e87dbe9f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -424,6 +424,12 @@ union bpf_attr { * @len: length of header to be pushed in front * @flags: Flags (unused for now) * Return: 0 on success or negative error + * + * int bpf_xdp_adjust_head(xdp_md, delta) + * Adjust the xdp_md.data by delta + * @xdp_md: pointer to xdp_md + * @delta: An positive/negative integer to be added to xdp_md.data + * Return: 0 on success or negative on error */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -469,7 +475,8 @@ union bpf_attr { FN(csum_update), \ FN(set_hash_invalid), \ FN(get_numa_node_id), \ - FN(skb_change_head), + FN(skb_change_head), \ + FN(xdp_adjust_head), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -576,6 +583,8 @@ struct bpf_sock { __u32 protocol; }; +#define XDP_PACKET_HEADROOM 256 + /* User return codes for XDP prog type. * A valid XDP program must return one of these defined values. All other * return codes are reserved for future use. Unknown return codes will result diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index bdcc9f4ba767..83e0d153b0b4 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1143,7 +1143,7 @@ struct bpf_prog * __weak bpf_int_jit_compile(struct bpf_prog *prog) return prog; } -bool __weak bpf_helper_changes_skb_data(void *func) +bool __weak bpf_helper_changes_pkt_data(void *func) { return false; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 88f609f1c0c3..4819ec9d95f6 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -579,6 +579,8 @@ static void fixup_bpf_calls(struct bpf_prog *prog) prog->dst_needed = 1; if (insn->imm == BPF_FUNC_get_prandom_u32) bpf_user_rnd_init_once(); + if (insn->imm == BPF_FUNC_xdp_adjust_head) + prog->xdp_adjust_head = 1; if (insn->imm == BPF_FUNC_tail_call) { /* mark bpf_tail_call as different opcode * to avoid conditional branch in diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5b14f85f45c6..d28f9a3380a9 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1216,7 +1216,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id) return -EINVAL; } - changes_data = bpf_helper_changes_skb_data(fn->func); + changes_data = bpf_helper_changes_pkt_data(fn->func); memset(&meta, 0, sizeof(meta)); meta.pkt_access = fn->pkt_access; diff --git a/net/core/filter.c b/net/core/filter.c index b751202e12f8..b1461708a977 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2234,7 +2234,28 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = { .arg3_type = ARG_ANYTHING, }; -bool bpf_helper_changes_skb_data(void *func) +BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset) +{ + void *data = xdp->data + offset; + + if (unlikely(data < xdp->data_hard_start || + data > xdp->data_end - ETH_HLEN)) + return -EINVAL; + + xdp->data = data; + + return 0; +} + +static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { + .func = bpf_xdp_adjust_head, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + +bool bpf_helper_changes_pkt_data(void *func) { if (func == bpf_skb_vlan_push || func == bpf_skb_vlan_pop || @@ -2244,7 +2265,8 @@ bool bpf_helper_changes_skb_data(void *func) func == bpf_skb_change_tail || func == bpf_skb_pull_data || func == bpf_l3_csum_replace || - func == bpf_l4_csum_replace) + func == bpf_l4_csum_replace || + func == bpf_xdp_adjust_head) return true; return false; @@ -2670,6 +2692,8 @@ xdp_func_proto(enum bpf_func_id func_id) return &bpf_xdp_event_output_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; + case BPF_FUNC_xdp_adjust_head: + return &bpf_xdp_adjust_head_proto; default: return sk_filter_func_proto(func_id); } -- cgit v1.2.3 From 2fa436b3a2a7009c11a3bc03fe0ff4c26e80fd87 Mon Sep 17 00:00:00 2001 From: Vamsi Krishna Date: Fri, 2 Dec 2016 23:59:08 +0200 Subject: nl80211: Use different attrs for BSSID and random MAC addr in scan req NL80211_ATTR_MAC was used to set both the specific BSSID to be scanned and the random MAC address to be used when privacy is enabled. When both the features are enabled, both the BSSID and the local MAC address were getting same value causing Probe Request frames to go with unintended DA. Hence, this has been fixed by using a different NL80211_ATTR_BSSID attribute to set the specific BSSID (which was the more recent addition in cfg80211) for a scan. Backwards compatibility with old userspace software is maintained to some extent by allowing NL80211_ATTR_MAC to be used to set the specific BSSID when scanning without enabling random MAC address use. Scanning with random source MAC address was introduced by commit ad2b26abc157 ("cfg80211: allow drivers to support random MAC addresses for scan") and the issue was introduced with the addition of the second user for the same attribute in commit 818965d39177 ("cfg80211: Allow a scan request for a specific BSSID"). Fixes: 818965d39177 ("cfg80211: Allow a scan request for a specific BSSID") Signed-off-by: Vamsi Krishna Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 7 ++++++- net/wireless/nl80211.c | 16 +++++++++++++++- 2 files changed, 21 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 259c9c77fdc1..6b76e3b0c18e 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -323,7 +323,7 @@ * @NL80211_CMD_GET_SCAN: get scan results * @NL80211_CMD_TRIGGER_SCAN: trigger a new scan with the given parameters * %NL80211_ATTR_TX_NO_CCK_RATE is used to decide whether to send the - * probe requests at CCK rate or not. %NL80211_ATTR_MAC can be used to + * probe requests at CCK rate or not. %NL80211_ATTR_BSSID can be used to * specify a BSSID to scan for; if not included, the wildcard BSSID will * be used. * @NL80211_CMD_NEW_SCAN_RESULTS: scan notification (as a reply to @@ -1977,6 +1977,9 @@ enum nl80211_commands { * @NL80211_ATTR_MULTICAST_TO_UNICAST_ENABLED: Indicates whether or not multicast * packets should be send out as unicast to all stations (flag attribute). * + * @NL80211_ATTR_BSSID: The BSSID of the AP. Note that %NL80211_ATTR_MAC is also + * used in various commands/events for specifying the BSSID. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2381,6 +2384,8 @@ enum nl80211_attrs { NL80211_ATTR_MULTICAST_TO_UNICAST_ENABLED, + NL80211_ATTR_BSSID, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 765bd41b1623..3df85a751a85 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -404,6 +404,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { .len = FILS_MAX_KEK_LEN }, [NL80211_ATTR_FILS_NONCES] = { .len = 2 * FILS_NONCE_LEN }, [NL80211_ATTR_MULTICAST_TO_UNICAST_ENABLED] = { .type = NLA_FLAG, }, + [NL80211_ATTR_BSSID] = { .len = ETH_ALEN }, }; /* policy for the key attributes */ @@ -6703,7 +6704,20 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) request->no_cck = nla_get_flag(info->attrs[NL80211_ATTR_TX_NO_CCK_RATE]); - if (info->attrs[NL80211_ATTR_MAC]) + /* Initial implementation used NL80211_ATTR_MAC to set the specific + * BSSID to scan for. This was problematic because that same attribute + * was already used for another purpose (local random MAC address). The + * NL80211_ATTR_BSSID attribute was added to fix this. For backwards + * compatibility with older userspace components, also use the + * NL80211_ATTR_MAC value here if it can be determined to be used for + * the specific BSSID use case instead of the random MAC address + * (NL80211_ATTR_SCAN_FLAGS is used to enable random MAC address use). + */ + if (info->attrs[NL80211_ATTR_BSSID]) + memcpy(request->bssid, + nla_data(info->attrs[NL80211_ATTR_BSSID]), ETH_ALEN); + else if (!(request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) && + info->attrs[NL80211_ATTR_MAC]) memcpy(request->bssid, nla_data(info->attrs[NL80211_ATTR_MAC]), ETH_ALEN); else -- cgit v1.2.3 From 41c43fbee68f4f9a2a9675d83bca91c77862d7f0 Mon Sep 17 00:00:00 2001 From: Asbjørn Sloth Tønnesen Date: Sun, 11 Dec 2016 00:18:57 +0000 Subject: net: l2tp: export debug flags to UAPI Move the L2TP_MSG_* definitions to UAPI, as it is part of the netlink API. Signed-off-by: Asbjoern Sloth Toennesen Signed-off-by: David S. Miller --- include/uapi/linux/l2tp.h | 17 ++++++++++++++++- net/l2tp/l2tp_core.h | 10 ---------- 2 files changed, 16 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h index 5daa48e2571e..85ddb74fcd1c 100644 --- a/include/uapi/linux/l2tp.h +++ b/include/uapi/linux/l2tp.h @@ -108,7 +108,7 @@ enum { L2TP_ATTR_VLAN_ID, /* u16 */ L2TP_ATTR_COOKIE, /* 0, 4 or 8 bytes */ L2TP_ATTR_PEER_COOKIE, /* 0, 4 or 8 bytes */ - L2TP_ATTR_DEBUG, /* u32 */ + L2TP_ATTR_DEBUG, /* u32, enum l2tp_debug_flags */ L2TP_ATTR_RECV_SEQ, /* u8 */ L2TP_ATTR_SEND_SEQ, /* u8 */ L2TP_ATTR_LNS_MODE, /* u8 */ @@ -175,6 +175,21 @@ enum l2tp_seqmode { L2TP_SEQ_ALL = 2, }; +/** + * enum l2tp_debug_flags - debug message categories for L2TP tunnels/sessions + * + * @L2TP_MSG_DEBUG: verbose debug (if compiled in) + * @L2TP_MSG_CONTROL: userspace - kernel interface + * @L2TP_MSG_SEQ: sequence numbers + * @L2TP_MSG_DATA: data packets + */ +enum l2tp_debug_flags { + L2TP_MSG_DEBUG = (1 << 0), + L2TP_MSG_CONTROL = (1 << 1), + L2TP_MSG_SEQ = (1 << 2), + L2TP_MSG_DATA = (1 << 3), +}; + /* * NETLINK_GENERIC related info */ diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 2599af6378e4..8f560f7140a0 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -23,16 +23,6 @@ #define L2TP_HASH_BITS_2 8 #define L2TP_HASH_SIZE_2 (1 << L2TP_HASH_BITS_2) -/* Debug message categories for the DEBUG socket option */ -enum { - L2TP_MSG_DEBUG = (1 << 0), /* verbose debug (if - * compiled in) */ - L2TP_MSG_CONTROL = (1 << 1), /* userspace - kernel - * interface */ - L2TP_MSG_SEQ = (1 << 2), /* sequence numbers */ - L2TP_MSG_DATA = (1 << 3), /* data packets */ -}; - struct sk_buff; struct l2tp_stats { -- cgit v1.2.3 From 47c3e7783be4e142b861d34b5c2e223330b05d8a Mon Sep 17 00:00:00 2001 From: Asbjørn Sloth Tønnesen Date: Sun, 11 Dec 2016 00:18:58 +0000 Subject: net: l2tp: deprecate PPPOL2TP_MSG_* in favour of L2TP_MSG_* PPPOL2TP_MSG_* and L2TP_MSG_* are duplicates, and are being used interchangeably in the kernel, so let's standardize on L2TP_MSG_* internally, and keep PPPOL2TP_MSG_* defined in UAPI for compatibility. Signed-off-by: Asbjoern Sloth Toennesen Signed-off-by: David S. Miller --- Documentation/networking/l2tp.txt | 8 ++++---- include/uapi/linux/if_pppol2tp.h | 13 ++++++------- 2 files changed, 10 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/l2tp.txt b/Documentation/networking/l2tp.txt index 4650a00ed012..9bc271cdc9a8 100644 --- a/Documentation/networking/l2tp.txt +++ b/Documentation/networking/l2tp.txt @@ -177,10 +177,10 @@ setsockopt on the PPPoX socket to set a debug mask. The following debug mask bits are available: -PPPOL2TP_MSG_DEBUG verbose debug (if compiled in) -PPPOL2TP_MSG_CONTROL userspace - kernel interface -PPPOL2TP_MSG_SEQ sequence numbers handling -PPPOL2TP_MSG_DATA data packets +L2TP_MSG_DEBUG verbose debug (if compiled in) +L2TP_MSG_CONTROL userspace - kernel interface +L2TP_MSG_SEQ sequence numbers handling +L2TP_MSG_DATA data packets If enabled, files under a l2tp debugfs directory can be used to dump kernel state about L2TP tunnels and sessions. To access it, the diff --git a/include/uapi/linux/if_pppol2tp.h b/include/uapi/linux/if_pppol2tp.h index 4bd1f55d6377..6418c4d10241 100644 --- a/include/uapi/linux/if_pppol2tp.h +++ b/include/uapi/linux/if_pppol2tp.h @@ -18,6 +18,7 @@ #include #include #include +#include /* Structure used to connect() the socket to a particular tunnel UDP * socket over IPv4. @@ -90,14 +91,12 @@ enum { PPPOL2TP_SO_REORDERTO = 5, }; -/* Debug message categories for the DEBUG socket option */ +/* Debug message categories for the DEBUG socket option (deprecated) */ enum { - PPPOL2TP_MSG_DEBUG = (1 << 0), /* verbose debug (if - * compiled in) */ - PPPOL2TP_MSG_CONTROL = (1 << 1), /* userspace - kernel - * interface */ - PPPOL2TP_MSG_SEQ = (1 << 2), /* sequence numbers */ - PPPOL2TP_MSG_DATA = (1 << 3), /* data packets */ + PPPOL2TP_MSG_DEBUG = L2TP_MSG_DEBUG, + PPPOL2TP_MSG_CONTROL = L2TP_MSG_CONTROL, + PPPOL2TP_MSG_SEQ = L2TP_MSG_SEQ, + PPPOL2TP_MSG_DATA = L2TP_MSG_DATA, }; -- cgit v1.2.3 From 41d5319af3368127b55f6587f1c747dd6a7b9b04 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 26 Nov 2016 22:18:59 -0500 Subject: fscrypt: move the policy flags and encryption mode definitions to uapi header These constants are part of the UAPI, so they belong in include/uapi/linux/fs.h instead of include/linux/fscrypto.h Signed-off-by: Theodore Ts'o Reviewed-by: Eric Biggers --- include/linux/fscrypto.h | 14 -------------- include/uapi/linux/fs.h | 14 ++++++++++++++ 2 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index 71e8a20711ec..42ef82d60790 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -18,20 +18,6 @@ #include #include -#define FS_POLICY_FLAGS_PAD_4 0x00 -#define FS_POLICY_FLAGS_PAD_8 0x01 -#define FS_POLICY_FLAGS_PAD_16 0x02 -#define FS_POLICY_FLAGS_PAD_32 0x03 -#define FS_POLICY_FLAGS_PAD_MASK 0x03 -#define FS_POLICY_FLAGS_VALID 0x03 - -/* Encryption algorithms */ -#define FS_ENCRYPTION_MODE_INVALID 0 -#define FS_ENCRYPTION_MODE_AES_256_XTS 1 -#define FS_ENCRYPTION_MODE_AES_256_GCM 2 -#define FS_ENCRYPTION_MODE_AES_256_CBC 3 -#define FS_ENCRYPTION_MODE_AES_256_CTS 4 - #define FS_CRYPTO_BLOCK_SIZE 16 struct fscrypt_info; diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index acb2b6152ba0..0496d37abe28 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -254,6 +254,20 @@ struct fsxattr { /* Policy provided via an ioctl on the topmost directory */ #define FS_KEY_DESCRIPTOR_SIZE 8 +#define FS_POLICY_FLAGS_PAD_4 0x00 +#define FS_POLICY_FLAGS_PAD_8 0x01 +#define FS_POLICY_FLAGS_PAD_16 0x02 +#define FS_POLICY_FLAGS_PAD_32 0x03 +#define FS_POLICY_FLAGS_PAD_MASK 0x03 +#define FS_POLICY_FLAGS_VALID 0x03 + +/* Encryption algorithms */ +#define FS_ENCRYPTION_MODE_INVALID 0 +#define FS_ENCRYPTION_MODE_AES_256_XTS 1 +#define FS_ENCRYPTION_MODE_AES_256_GCM 2 +#define FS_ENCRYPTION_MODE_AES_256_CBC 3 +#define FS_ENCRYPTION_MODE_AES_256_CTS 4 + struct fscrypt_policy { __u8 version; __u8 contents_encryption_mode; -- cgit v1.2.3 From cc10385b6fde3e5d3a3edaabf10a4e211ee8fe72 Mon Sep 17 00:00:00 2001 From: Wang Sheng-Hui Date: Thu, 22 Sep 2016 09:05:46 +0800 Subject: PCI: Move config space size macros to pci_regs.h Move PCI configuration space size macros (PCI_CFG_SPACE_SIZE and PCI_CFG_SPACE_EXP_SIZE) from drivers/pci/pci.h to include/uapi/linux/pci_regs.h so they can be used by more drivers and eliminate duplicate definitions. [bhelgaas: Expand comment to include PCI-X details] Signed-off-by: Wang Sheng-Hui Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.h | 3 --- drivers/vfio/pci/vfio_pci_config.c | 2 -- include/uapi/linux/pci_regs.h | 8 ++++++++ 3 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 451856210e18..9cbcf1dd740b 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -1,9 +1,6 @@ #ifndef DRIVERS_PCI_H #define DRIVERS_PCI_H -#define PCI_CFG_SPACE_SIZE 256 -#define PCI_CFG_SPACE_EXP_SIZE 4096 - #define PCI_FIND_CAP_TTL 48 extern const unsigned char pcie_link_speed[]; diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index 65d4a3015542..871af74fc4ce 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -31,8 +31,6 @@ #include "vfio_pci_private.h" -#define PCI_CFG_SPACE_SIZE 256 - /* Fake capability ID for standard config space */ #define PCI_CAP_ID_BASIC 0 diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index e5a2e68b2236..174d1147081b 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -22,6 +22,14 @@ #ifndef LINUX_PCI_REGS_H #define LINUX_PCI_REGS_H +/* + * Conventional PCI and PCI-X Mode 1 devices have 256 bytes of + * configuration space. PCI-X Mode 2 and PCIe devices have 4096 bytes of + * configuration space. + */ +#define PCI_CFG_SPACE_SIZE 256 +#define PCI_CFG_SPACE_EXP_SIZE 4096 + /* * Under PCI, each device has 256 bytes of configuration address space, * of which the first 64 bytes are standardized as follows: -- cgit v1.2.3 From dbaf0624ffa57ae6e7d87a823185ccd9a7852d3c Mon Sep 17 00:00:00 2001 From: Gonglei Date: Thu, 15 Dec 2016 10:03:16 +0800 Subject: crypto: add virtio-crypto driver This patch introduces virtio-crypto driver for Linux Kernel. The virtio crypto device is a virtual cryptography device as well as a kind of virtual hardware accelerator for virtual machines. The encryption anddecryption requests are placed in the data queue and are ultimately handled by thebackend crypto accelerators. The second queue is the control queue used to create or destroy sessions for symmetric algorithms and will control some advanced features in the future. The virtio crypto device provides the following cryptoservices: CIPHER, MAC, HASH, and AEAD. For more information about virtio-crypto device, please see: http://qemu-project.org/Features/VirtioCrypto CC: Michael S. Tsirkin CC: Cornelia Huck CC: Stefan Hajnoczi CC: Herbert Xu CC: Halil Pasic CC: David S. Miller CC: Zeng Xin Signed-off-by: Gonglei Signed-off-by: Michael S. Tsirkin --- MAINTAINERS | 9 + drivers/crypto/Kconfig | 2 + drivers/crypto/Makefile | 1 + drivers/crypto/virtio/Kconfig | 10 + drivers/crypto/virtio/Makefile | 5 + drivers/crypto/virtio/virtio_crypto_algs.c | 540 +++++++++++++++++++++++++++ drivers/crypto/virtio/virtio_crypto_common.h | 128 +++++++ drivers/crypto/virtio/virtio_crypto_core.c | 476 +++++++++++++++++++++++ drivers/crypto/virtio/virtio_crypto_mgr.c | 264 +++++++++++++ include/uapi/linux/Kbuild | 1 + include/uapi/linux/virtio_crypto.h | 450 ++++++++++++++++++++++ include/uapi/linux/virtio_ids.h | 1 + 12 files changed, 1887 insertions(+) create mode 100644 drivers/crypto/virtio/Kconfig create mode 100644 drivers/crypto/virtio/Makefile create mode 100644 drivers/crypto/virtio/virtio_crypto_algs.c create mode 100644 drivers/crypto/virtio/virtio_crypto_common.h create mode 100644 drivers/crypto/virtio/virtio_crypto_core.c create mode 100644 drivers/crypto/virtio/virtio_crypto_mgr.c create mode 100644 include/uapi/linux/virtio_crypto.h (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 59c9895d73d5..650ad4f6b608 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12988,6 +12988,7 @@ F: drivers/net/virtio_net.c F: drivers/block/virtio_blk.c F: include/linux/virtio_*.h F: include/uapi/linux/virtio_*.h +F: drivers/crypto/virtio/ VIRTIO DRIVERS FOR S390 M: Christian Borntraeger @@ -13024,6 +13025,14 @@ S: Maintained F: drivers/virtio/virtio_input.c F: include/uapi/linux/virtio_input.h +VIRTIO CRYPTO DRIVER +M: Gonglei +L: virtualization@lists.linux-foundation.org +L: linux-crypto@vger.kernel.org +S: Maintained +F: drivers/crypto/virtio/ +F: include/uapi/linux/virtio_crypto.h + VIA RHINE NETWORK DRIVER S: Orphan F: drivers/net/ethernet/via/via-rhine.c diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index 4d2b81f2b223..79564785ae30 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -555,4 +555,6 @@ config CRYPTO_DEV_ROCKCHIP source "drivers/crypto/chelsio/Kconfig" +source "drivers/crypto/virtio/Kconfig" + endif # CRYPTO_HW diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile index ad7250fa1348..bc53cb833a06 100644 --- a/drivers/crypto/Makefile +++ b/drivers/crypto/Makefile @@ -32,3 +32,4 @@ obj-$(CONFIG_CRYPTO_DEV_VMX) += vmx/ obj-$(CONFIG_CRYPTO_DEV_SUN4I_SS) += sunxi-ss/ obj-$(CONFIG_CRYPTO_DEV_ROCKCHIP) += rockchip/ obj-$(CONFIG_CRYPTO_DEV_CHELSIO) += chelsio/ +obj-$(CONFIG_CRYPTO_DEV_VIRTIO) += virtio/ diff --git a/drivers/crypto/virtio/Kconfig b/drivers/crypto/virtio/Kconfig new file mode 100644 index 000000000000..d80f73366ae2 --- /dev/null +++ b/drivers/crypto/virtio/Kconfig @@ -0,0 +1,10 @@ +config CRYPTO_DEV_VIRTIO + tristate "VirtIO crypto driver" + depends on VIRTIO + select CRYPTO_AEAD + select CRYPTO_AUTHENC + select CRYPTO_BLKCIPHER + default m + help + This driver provides support for virtio crypto device. If you + choose 'M' here, this module will be called virtio_crypto. diff --git a/drivers/crypto/virtio/Makefile b/drivers/crypto/virtio/Makefile new file mode 100644 index 000000000000..dd342c947ff9 --- /dev/null +++ b/drivers/crypto/virtio/Makefile @@ -0,0 +1,5 @@ +obj-$(CONFIG_CRYPTO_DEV_VIRTIO) += virtio_crypto.o +virtio_crypto-objs := \ + virtio_crypto_algs.o \ + virtio_crypto_mgr.o \ + virtio_crypto_core.o diff --git a/drivers/crypto/virtio/virtio_crypto_algs.c b/drivers/crypto/virtio/virtio_crypto_algs.c new file mode 100644 index 000000000000..c2374df9abae --- /dev/null +++ b/drivers/crypto/virtio/virtio_crypto_algs.c @@ -0,0 +1,540 @@ + /* Algorithms supported by virtio crypto device + * + * Authors: Gonglei + * + * Copyright 2016 HUAWEI TECHNOLOGIES CO., LTD. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + */ + +#include +#include +#include +#include +#include + +#include +#include "virtio_crypto_common.h" + +/* + * The algs_lock protects the below global virtio_crypto_active_devs + * and crypto algorithms registion. + */ +static DEFINE_MUTEX(algs_lock); +static unsigned int virtio_crypto_active_devs; + +static u64 virtio_crypto_alg_sg_nents_length(struct scatterlist *sg) +{ + u64 total = 0; + + for (total = 0; sg; sg = sg_next(sg)) + total += sg->length; + + return total; +} + +static int +virtio_crypto_alg_validate_key(int key_len, uint32_t *alg) +{ + switch (key_len) { + case AES_KEYSIZE_128: + case AES_KEYSIZE_192: + case AES_KEYSIZE_256: + *alg = VIRTIO_CRYPTO_CIPHER_AES_CBC; + break; + default: + pr_err("virtio_crypto: Unsupported key length: %d\n", + key_len); + return -EINVAL; + } + return 0; +} + +static int virtio_crypto_alg_ablkcipher_init_session( + struct virtio_crypto_ablkcipher_ctx *ctx, + uint32_t alg, const uint8_t *key, + unsigned int keylen, + int encrypt) +{ + struct scatterlist outhdr, key_sg, inhdr, *sgs[3]; + unsigned int tmp; + struct virtio_crypto *vcrypto = ctx->vcrypto; + int op = encrypt ? VIRTIO_CRYPTO_OP_ENCRYPT : VIRTIO_CRYPTO_OP_DECRYPT; + int err; + unsigned int num_out = 0, num_in = 0; + + /* + * Avoid to do DMA from the stack, switch to using + * dynamically-allocated for the key + */ + uint8_t *cipher_key = kmalloc(keylen, GFP_ATOMIC); + + if (!cipher_key) + return -ENOMEM; + + memcpy(cipher_key, key, keylen); + + spin_lock(&vcrypto->ctrl_lock); + /* Pad ctrl header */ + vcrypto->ctrl.header.opcode = + cpu_to_le32(VIRTIO_CRYPTO_CIPHER_CREATE_SESSION); + vcrypto->ctrl.header.algo = cpu_to_le32(alg); + /* Set the default dataqueue id to 0 */ + vcrypto->ctrl.header.queue_id = 0; + + vcrypto->input.status = cpu_to_le32(VIRTIO_CRYPTO_ERR); + /* Pad cipher's parameters */ + vcrypto->ctrl.u.sym_create_session.op_type = + cpu_to_le32(VIRTIO_CRYPTO_SYM_OP_CIPHER); + vcrypto->ctrl.u.sym_create_session.u.cipher.para.algo = + vcrypto->ctrl.header.algo; + vcrypto->ctrl.u.sym_create_session.u.cipher.para.keylen = + cpu_to_le32(keylen); + vcrypto->ctrl.u.sym_create_session.u.cipher.para.op = + cpu_to_le32(op); + + sg_init_one(&outhdr, &vcrypto->ctrl, sizeof(vcrypto->ctrl)); + sgs[num_out++] = &outhdr; + + /* Set key */ + sg_init_one(&key_sg, cipher_key, keylen); + sgs[num_out++] = &key_sg; + + /* Return status and session id back */ + sg_init_one(&inhdr, &vcrypto->input, sizeof(vcrypto->input)); + sgs[num_out + num_in++] = &inhdr; + + err = virtqueue_add_sgs(vcrypto->ctrl_vq, sgs, num_out, + num_in, vcrypto, GFP_ATOMIC); + if (err < 0) { + spin_unlock(&vcrypto->ctrl_lock); + kzfree(cipher_key); + return err; + } + virtqueue_kick(vcrypto->ctrl_vq); + + /* + * Trapping into the hypervisor, so the request should be + * handled immediately. + */ + while (!virtqueue_get_buf(vcrypto->ctrl_vq, &tmp) && + !virtqueue_is_broken(vcrypto->ctrl_vq)) + cpu_relax(); + + if (le32_to_cpu(vcrypto->input.status) != VIRTIO_CRYPTO_OK) { + spin_unlock(&vcrypto->ctrl_lock); + pr_err("virtio_crypto: Create session failed status: %u\n", + le32_to_cpu(vcrypto->input.status)); + kzfree(cipher_key); + return -EINVAL; + } + + if (encrypt) + ctx->enc_sess_info.session_id = + le64_to_cpu(vcrypto->input.session_id); + else + ctx->dec_sess_info.session_id = + le64_to_cpu(vcrypto->input.session_id); + + spin_unlock(&vcrypto->ctrl_lock); + + kzfree(cipher_key); + return 0; +} + +static int virtio_crypto_alg_ablkcipher_close_session( + struct virtio_crypto_ablkcipher_ctx *ctx, + int encrypt) +{ + struct scatterlist outhdr, status_sg, *sgs[2]; + unsigned int tmp; + struct virtio_crypto_destroy_session_req *destroy_session; + struct virtio_crypto *vcrypto = ctx->vcrypto; + int err; + unsigned int num_out = 0, num_in = 0; + + spin_lock(&vcrypto->ctrl_lock); + vcrypto->ctrl_status.status = VIRTIO_CRYPTO_ERR; + /* Pad ctrl header */ + vcrypto->ctrl.header.opcode = + cpu_to_le32(VIRTIO_CRYPTO_CIPHER_DESTROY_SESSION); + /* Set the default virtqueue id to 0 */ + vcrypto->ctrl.header.queue_id = 0; + + destroy_session = &vcrypto->ctrl.u.destroy_session; + + if (encrypt) + destroy_session->session_id = + cpu_to_le64(ctx->enc_sess_info.session_id); + else + destroy_session->session_id = + cpu_to_le64(ctx->dec_sess_info.session_id); + + sg_init_one(&outhdr, &vcrypto->ctrl, sizeof(vcrypto->ctrl)); + sgs[num_out++] = &outhdr; + + /* Return status and session id back */ + sg_init_one(&status_sg, &vcrypto->ctrl_status.status, + sizeof(vcrypto->ctrl_status.status)); + sgs[num_out + num_in++] = &status_sg; + + err = virtqueue_add_sgs(vcrypto->ctrl_vq, sgs, num_out, + num_in, vcrypto, GFP_ATOMIC); + if (err < 0) { + spin_unlock(&vcrypto->ctrl_lock); + return err; + } + virtqueue_kick(vcrypto->ctrl_vq); + + while (!virtqueue_get_buf(vcrypto->ctrl_vq, &tmp) && + !virtqueue_is_broken(vcrypto->ctrl_vq)) + cpu_relax(); + + if (vcrypto->ctrl_status.status != VIRTIO_CRYPTO_OK) { + spin_unlock(&vcrypto->ctrl_lock); + pr_err("virtio_crypto: Close session failed status: %u, session_id: 0x%llx\n", + vcrypto->ctrl_status.status, + destroy_session->session_id); + + return -EINVAL; + } + spin_unlock(&vcrypto->ctrl_lock); + + return 0; +} + +static int virtio_crypto_alg_ablkcipher_init_sessions( + struct virtio_crypto_ablkcipher_ctx *ctx, + const uint8_t *key, unsigned int keylen) +{ + uint32_t alg; + int ret; + struct virtio_crypto *vcrypto = ctx->vcrypto; + + if (keylen > vcrypto->max_cipher_key_len) { + pr_err("virtio_crypto: the key is too long\n"); + goto bad_key; + } + + if (virtio_crypto_alg_validate_key(keylen, &alg)) + goto bad_key; + + /* Create encryption session */ + ret = virtio_crypto_alg_ablkcipher_init_session(ctx, + alg, key, keylen, 1); + if (ret) + return ret; + /* Create decryption session */ + ret = virtio_crypto_alg_ablkcipher_init_session(ctx, + alg, key, keylen, 0); + if (ret) { + virtio_crypto_alg_ablkcipher_close_session(ctx, 1); + return ret; + } + return 0; + +bad_key: + crypto_tfm_set_flags(ctx->tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); + return -EINVAL; +} + +/* Note: kernel crypto API realization */ +static int virtio_crypto_ablkcipher_setkey(struct crypto_ablkcipher *tfm, + const uint8_t *key, + unsigned int keylen) +{ + struct virtio_crypto_ablkcipher_ctx *ctx = crypto_ablkcipher_ctx(tfm); + int ret; + + if (!ctx->vcrypto) { + /* New key */ + int node = virtio_crypto_get_current_node(); + struct virtio_crypto *vcrypto = + virtcrypto_get_dev_node(node); + if (!vcrypto) { + pr_err("virtio_crypto: Could not find a virtio device in the system"); + return -ENODEV; + } + + ctx->vcrypto = vcrypto; + } else { + /* Rekeying, we should close the created sessions previously */ + virtio_crypto_alg_ablkcipher_close_session(ctx, 1); + virtio_crypto_alg_ablkcipher_close_session(ctx, 0); + } + + ret = virtio_crypto_alg_ablkcipher_init_sessions(ctx, key, keylen); + if (ret) { + virtcrypto_dev_put(ctx->vcrypto); + ctx->vcrypto = NULL; + + return ret; + } + + return 0; +} + +static int +__virtio_crypto_ablkcipher_do_req(struct virtio_crypto_request *vc_req, + struct ablkcipher_request *req, + struct data_queue *data_vq, + __u8 op) +{ + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req); + unsigned int ivsize = crypto_ablkcipher_ivsize(tfm); + struct virtio_crypto_ablkcipher_ctx *ctx = vc_req->ablkcipher_ctx; + struct virtio_crypto *vcrypto = ctx->vcrypto; + struct virtio_crypto_op_data_req *req_data; + int src_nents, dst_nents; + int err; + unsigned long flags; + struct scatterlist outhdr, iv_sg, status_sg, **sgs; + int i; + u64 dst_len; + unsigned int num_out = 0, num_in = 0; + int sg_total; + uint8_t *iv; + + src_nents = sg_nents_for_len(req->src, req->nbytes); + dst_nents = sg_nents(req->dst); + + pr_debug("virtio_crypto: Number of sgs (src_nents: %d, dst_nents: %d)\n", + src_nents, dst_nents); + + /* Why 3? outhdr + iv + inhdr */ + sg_total = src_nents + dst_nents + 3; + sgs = kzalloc_node(sg_total * sizeof(*sgs), GFP_ATOMIC, + dev_to_node(&vcrypto->vdev->dev)); + if (!sgs) + return -ENOMEM; + + req_data = kzalloc_node(sizeof(*req_data), GFP_ATOMIC, + dev_to_node(&vcrypto->vdev->dev)); + if (!req_data) { + kfree(sgs); + return -ENOMEM; + } + + vc_req->req_data = req_data; + vc_req->type = VIRTIO_CRYPTO_SYM_OP_CIPHER; + /* Head of operation */ + if (op) { + req_data->header.session_id = + cpu_to_le64(ctx->enc_sess_info.session_id); + req_data->header.opcode = + cpu_to_le32(VIRTIO_CRYPTO_CIPHER_ENCRYPT); + } else { + req_data->header.session_id = + cpu_to_le64(ctx->dec_sess_info.session_id); + req_data->header.opcode = + cpu_to_le32(VIRTIO_CRYPTO_CIPHER_DECRYPT); + } + req_data->u.sym_req.op_type = cpu_to_le32(VIRTIO_CRYPTO_SYM_OP_CIPHER); + req_data->u.sym_req.u.cipher.para.iv_len = cpu_to_le32(ivsize); + req_data->u.sym_req.u.cipher.para.src_data_len = + cpu_to_le32(req->nbytes); + + dst_len = virtio_crypto_alg_sg_nents_length(req->dst); + if (unlikely(dst_len > U32_MAX)) { + pr_err("virtio_crypto: The dst_len is beyond U32_MAX\n"); + err = -EINVAL; + goto free; + } + + pr_debug("virtio_crypto: src_len: %u, dst_len: %llu\n", + req->nbytes, dst_len); + + if (unlikely(req->nbytes + dst_len + ivsize + + sizeof(vc_req->status) > vcrypto->max_size)) { + pr_err("virtio_crypto: The length is too big\n"); + err = -EINVAL; + goto free; + } + + req_data->u.sym_req.u.cipher.para.dst_data_len = + cpu_to_le32((uint32_t)dst_len); + + /* Outhdr */ + sg_init_one(&outhdr, req_data, sizeof(*req_data)); + sgs[num_out++] = &outhdr; + + /* IV */ + + /* + * Avoid to do DMA from the stack, switch to using + * dynamically-allocated for the IV + */ + iv = kzalloc_node(ivsize, GFP_ATOMIC, + dev_to_node(&vcrypto->vdev->dev)); + if (!iv) { + err = -ENOMEM; + goto free; + } + memcpy(iv, req->info, ivsize); + sg_init_one(&iv_sg, iv, ivsize); + sgs[num_out++] = &iv_sg; + vc_req->iv = iv; + + /* Source data */ + for (i = 0; i < src_nents; i++) + sgs[num_out++] = &req->src[i]; + + /* Destination data */ + for (i = 0; i < dst_nents; i++) + sgs[num_out + num_in++] = &req->dst[i]; + + /* Status */ + sg_init_one(&status_sg, &vc_req->status, sizeof(vc_req->status)); + sgs[num_out + num_in++] = &status_sg; + + vc_req->sgs = sgs; + + spin_lock_irqsave(&data_vq->lock, flags); + err = virtqueue_add_sgs(data_vq->vq, sgs, num_out, + num_in, vc_req, GFP_ATOMIC); + virtqueue_kick(data_vq->vq); + spin_unlock_irqrestore(&data_vq->lock, flags); + if (unlikely(err < 0)) + goto free_iv; + + return 0; + +free_iv: + kzfree(iv); +free: + kzfree(req_data); + kfree(sgs); + return err; +} + +static int virtio_crypto_ablkcipher_encrypt(struct ablkcipher_request *req) +{ + struct crypto_ablkcipher *atfm = crypto_ablkcipher_reqtfm(req); + struct virtio_crypto_ablkcipher_ctx *ctx = crypto_ablkcipher_ctx(atfm); + struct virtio_crypto_request *vc_req = ablkcipher_request_ctx(req); + struct virtio_crypto *vcrypto = ctx->vcrypto; + int ret; + /* Use the first data virtqueue as default */ + struct data_queue *data_vq = &vcrypto->data_vq[0]; + + vc_req->ablkcipher_ctx = ctx; + vc_req->ablkcipher_req = req; + ret = __virtio_crypto_ablkcipher_do_req(vc_req, req, data_vq, 1); + if (ret < 0) { + pr_err("virtio_crypto: Encryption failed!\n"); + return ret; + } + + return -EINPROGRESS; +} + +static int virtio_crypto_ablkcipher_decrypt(struct ablkcipher_request *req) +{ + struct crypto_ablkcipher *atfm = crypto_ablkcipher_reqtfm(req); + struct virtio_crypto_ablkcipher_ctx *ctx = crypto_ablkcipher_ctx(atfm); + struct virtio_crypto_request *vc_req = ablkcipher_request_ctx(req); + struct virtio_crypto *vcrypto = ctx->vcrypto; + int ret; + /* Use the first data virtqueue as default */ + struct data_queue *data_vq = &vcrypto->data_vq[0]; + + vc_req->ablkcipher_ctx = ctx; + vc_req->ablkcipher_req = req; + + ret = __virtio_crypto_ablkcipher_do_req(vc_req, req, data_vq, 0); + if (ret < 0) { + pr_err("virtio_crypto: Decryption failed!\n"); + return ret; + } + + return -EINPROGRESS; +} + +static int virtio_crypto_ablkcipher_init(struct crypto_tfm *tfm) +{ + struct virtio_crypto_ablkcipher_ctx *ctx = crypto_tfm_ctx(tfm); + + tfm->crt_ablkcipher.reqsize = sizeof(struct virtio_crypto_request); + ctx->tfm = tfm; + + return 0; +} + +static void virtio_crypto_ablkcipher_exit(struct crypto_tfm *tfm) +{ + struct virtio_crypto_ablkcipher_ctx *ctx = crypto_tfm_ctx(tfm); + + if (!ctx->vcrypto) + return; + + virtio_crypto_alg_ablkcipher_close_session(ctx, 1); + virtio_crypto_alg_ablkcipher_close_session(ctx, 0); + virtcrypto_dev_put(ctx->vcrypto); + ctx->vcrypto = NULL; +} + +static struct crypto_alg virtio_crypto_algs[] = { { + .cra_name = "cbc(aes)", + .cra_driver_name = "virtio_crypto_aes_cbc", + .cra_priority = 501, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct virtio_crypto_ablkcipher_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_type = &crypto_ablkcipher_type, + .cra_init = virtio_crypto_ablkcipher_init, + .cra_exit = virtio_crypto_ablkcipher_exit, + .cra_u = { + .ablkcipher = { + .setkey = virtio_crypto_ablkcipher_setkey, + .decrypt = virtio_crypto_ablkcipher_decrypt, + .encrypt = virtio_crypto_ablkcipher_encrypt, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + }, + }, +} }; + +int virtio_crypto_algs_register(void) +{ + int ret = 0; + + mutex_lock(&algs_lock); + if (++virtio_crypto_active_devs != 1) + goto unlock; + + ret = crypto_register_algs(virtio_crypto_algs, + ARRAY_SIZE(virtio_crypto_algs)); + if (ret) + virtio_crypto_active_devs--; + +unlock: + mutex_unlock(&algs_lock); + return ret; +} + +void virtio_crypto_algs_unregister(void) +{ + mutex_lock(&algs_lock); + if (--virtio_crypto_active_devs != 0) + goto unlock; + + crypto_unregister_algs(virtio_crypto_algs, + ARRAY_SIZE(virtio_crypto_algs)); + +unlock: + mutex_unlock(&algs_lock); +} diff --git a/drivers/crypto/virtio/virtio_crypto_common.h b/drivers/crypto/virtio/virtio_crypto_common.h new file mode 100644 index 000000000000..3d6566b02876 --- /dev/null +++ b/drivers/crypto/virtio/virtio_crypto_common.h @@ -0,0 +1,128 @@ +/* Common header for Virtio crypto device. + * + * Copyright 2016 HUAWEI TECHNOLOGIES CO., LTD. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + */ + +#ifndef _VIRTIO_CRYPTO_COMMON_H +#define _VIRTIO_CRYPTO_COMMON_H + +#include +#include +#include +#include +#include +#include + + +/* Internal representation of a data virtqueue */ +struct data_queue { + /* Virtqueue associated with this send _queue */ + struct virtqueue *vq; + + /* To protect the vq operations for the dataq */ + spinlock_t lock; + + /* Name of the tx queue: dataq.$index */ + char name[32]; +}; + +struct virtio_crypto { + struct virtio_device *vdev; + struct virtqueue *ctrl_vq; + struct data_queue *data_vq; + + /* To protect the vq operations for the controlq */ + spinlock_t ctrl_lock; + + /* Maximum of data queues supported by the device */ + u32 max_data_queues; + + /* Number of queue currently used by the driver */ + u32 curr_queue; + + /* Maximum length of cipher key */ + u32 max_cipher_key_len; + /* Maximum length of authenticated key */ + u32 max_auth_key_len; + /* Maximum size of per request */ + u64 max_size; + + /* Control VQ buffers: protected by the ctrl_lock */ + struct virtio_crypto_op_ctrl_req ctrl; + struct virtio_crypto_session_input input; + struct virtio_crypto_inhdr ctrl_status; + + unsigned long status; + atomic_t ref_count; + struct list_head list; + struct module *owner; + uint8_t dev_id; + + /* Does the affinity hint is set for virtqueues? */ + bool affinity_hint_set; +}; + +struct virtio_crypto_sym_session_info { + /* Backend session id, which come from the host side */ + __u64 session_id; +}; + +struct virtio_crypto_ablkcipher_ctx { + struct virtio_crypto *vcrypto; + struct crypto_tfm *tfm; + + struct virtio_crypto_sym_session_info enc_sess_info; + struct virtio_crypto_sym_session_info dec_sess_info; +}; + +struct virtio_crypto_request { + /* Cipher or aead */ + uint32_t type; + uint8_t status; + struct virtio_crypto_ablkcipher_ctx *ablkcipher_ctx; + struct ablkcipher_request *ablkcipher_req; + struct virtio_crypto_op_data_req *req_data; + struct scatterlist **sgs; + uint8_t *iv; +}; + +int virtcrypto_devmgr_add_dev(struct virtio_crypto *vcrypto_dev); +struct list_head *virtcrypto_devmgr_get_head(void); +void virtcrypto_devmgr_rm_dev(struct virtio_crypto *vcrypto_dev); +struct virtio_crypto *virtcrypto_devmgr_get_first(void); +int virtcrypto_dev_in_use(struct virtio_crypto *vcrypto_dev); +int virtcrypto_dev_get(struct virtio_crypto *vcrypto_dev); +void virtcrypto_dev_put(struct virtio_crypto *vcrypto_dev); +int virtcrypto_dev_started(struct virtio_crypto *vcrypto_dev); +struct virtio_crypto *virtcrypto_get_dev_node(int node); +int virtcrypto_dev_start(struct virtio_crypto *vcrypto); +void virtcrypto_dev_stop(struct virtio_crypto *vcrypto); + +static inline int virtio_crypto_get_current_node(void) +{ + int cpu, node; + + cpu = get_cpu(); + node = topology_physical_package_id(cpu); + put_cpu(); + + return node; +} + +int virtio_crypto_algs_register(void); +void virtio_crypto_algs_unregister(void); + +#endif /* _VIRTIO_CRYPTO_COMMON_H */ diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c new file mode 100644 index 000000000000..fe70ec823b27 --- /dev/null +++ b/drivers/crypto/virtio/virtio_crypto_core.c @@ -0,0 +1,476 @@ + /* Driver for Virtio crypto device. + * + * Copyright 2016 HUAWEI TECHNOLOGIES CO., LTD. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + */ + +#include +#include +#include +#include + +#include +#include "virtio_crypto_common.h" + + +static void +virtcrypto_clear_request(struct virtio_crypto_request *vc_req) +{ + if (vc_req) { + kzfree(vc_req->iv); + kzfree(vc_req->req_data); + kfree(vc_req->sgs); + } +} + +static void virtcrypto_dataq_callback(struct virtqueue *vq) +{ + struct virtio_crypto *vcrypto = vq->vdev->priv; + struct virtio_crypto_request *vc_req; + unsigned long flags; + unsigned int len; + struct ablkcipher_request *ablk_req; + int error; + unsigned int qid = vq->index; + + spin_lock_irqsave(&vcrypto->data_vq[qid].lock, flags); + do { + virtqueue_disable_cb(vq); + while ((vc_req = virtqueue_get_buf(vq, &len)) != NULL) { + if (vc_req->type == VIRTIO_CRYPTO_SYM_OP_CIPHER) { + switch (vc_req->status) { + case VIRTIO_CRYPTO_OK: + error = 0; + break; + case VIRTIO_CRYPTO_INVSESS: + case VIRTIO_CRYPTO_ERR: + error = -EINVAL; + break; + case VIRTIO_CRYPTO_BADMSG: + error = -EBADMSG; + break; + default: + error = -EIO; + break; + } + ablk_req = vc_req->ablkcipher_req; + virtcrypto_clear_request(vc_req); + + spin_unlock_irqrestore( + &vcrypto->data_vq[qid].lock, flags); + /* Finish the encrypt or decrypt process */ + ablk_req->base.complete(&ablk_req->base, error); + spin_lock_irqsave( + &vcrypto->data_vq[qid].lock, flags); + } + } + } while (!virtqueue_enable_cb(vq)); + spin_unlock_irqrestore(&vcrypto->data_vq[qid].lock, flags); +} + +static int virtcrypto_find_vqs(struct virtio_crypto *vi) +{ + vq_callback_t **callbacks; + struct virtqueue **vqs; + int ret = -ENOMEM; + int i, total_vqs; + const char **names; + + /* + * We expect 1 data virtqueue, followed by + * possible N-1 data queues used in multiqueue mode, + * followed by control vq. + */ + total_vqs = vi->max_data_queues + 1; + + /* Allocate space for find_vqs parameters */ + vqs = kcalloc(total_vqs, sizeof(*vqs), GFP_KERNEL); + if (!vqs) + goto err_vq; + callbacks = kcalloc(total_vqs, sizeof(*callbacks), GFP_KERNEL); + if (!callbacks) + goto err_callback; + names = kcalloc(total_vqs, sizeof(*names), GFP_KERNEL); + if (!names) + goto err_names; + + /* Parameters for control virtqueue */ + callbacks[total_vqs - 1] = NULL; + names[total_vqs - 1] = "controlq"; + + /* Allocate/initialize parameters for data virtqueues */ + for (i = 0; i < vi->max_data_queues; i++) { + callbacks[i] = virtcrypto_dataq_callback; + snprintf(vi->data_vq[i].name, sizeof(vi->data_vq[i].name), + "dataq.%d", i); + names[i] = vi->data_vq[i].name; + } + + ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks, + names); + if (ret) + goto err_find; + + vi->ctrl_vq = vqs[total_vqs - 1]; + + for (i = 0; i < vi->max_data_queues; i++) { + spin_lock_init(&vi->data_vq[i].lock); + vi->data_vq[i].vq = vqs[i]; + } + + kfree(names); + kfree(callbacks); + kfree(vqs); + + return 0; + +err_find: + kfree(names); +err_names: + kfree(callbacks); +err_callback: + kfree(vqs); +err_vq: + return ret; +} + +static int virtcrypto_alloc_queues(struct virtio_crypto *vi) +{ + vi->data_vq = kcalloc(vi->max_data_queues, sizeof(*vi->data_vq), + GFP_KERNEL); + if (!vi->data_vq) + return -ENOMEM; + + return 0; +} + +static void virtcrypto_clean_affinity(struct virtio_crypto *vi, long hcpu) +{ + int i; + + if (vi->affinity_hint_set) { + for (i = 0; i < vi->max_data_queues; i++) + virtqueue_set_affinity(vi->data_vq[i].vq, -1); + + vi->affinity_hint_set = false; + } +} + +static void virtcrypto_set_affinity(struct virtio_crypto *vcrypto) +{ + int i = 0; + int cpu; + + /* + * In single queue mode, we don't set the cpu affinity. + */ + if (vcrypto->curr_queue == 1 || vcrypto->max_data_queues == 1) { + virtcrypto_clean_affinity(vcrypto, -1); + return; + } + + /* + * In multiqueue mode, we let the queue to be private to one cpu + * by setting the affinity hint to eliminate the contention. + * + * TODO: adds cpu hotplug support by register cpu notifier. + * + */ + for_each_online_cpu(cpu) { + virtqueue_set_affinity(vcrypto->data_vq[i].vq, cpu); + if (++i >= vcrypto->max_data_queues) + break; + } + + vcrypto->affinity_hint_set = true; +} + +static void virtcrypto_free_queues(struct virtio_crypto *vi) +{ + kfree(vi->data_vq); +} + +static int virtcrypto_init_vqs(struct virtio_crypto *vi) +{ + int ret; + + /* Allocate send & receive queues */ + ret = virtcrypto_alloc_queues(vi); + if (ret) + goto err; + + ret = virtcrypto_find_vqs(vi); + if (ret) + goto err_free; + + get_online_cpus(); + virtcrypto_set_affinity(vi); + put_online_cpus(); + + return 0; + +err_free: + virtcrypto_free_queues(vi); +err: + return ret; +} + +static int virtcrypto_update_status(struct virtio_crypto *vcrypto) +{ + u32 status; + int err; + + virtio_cread(vcrypto->vdev, + struct virtio_crypto_config, status, &status); + + /* + * Unknown status bits would be a host error and the driver + * should consider the device to be broken. + */ + if (status & (~VIRTIO_CRYPTO_S_HW_READY)) { + dev_warn(&vcrypto->vdev->dev, + "Unknown status bits: 0x%x\n", status); + + virtio_break_device(vcrypto->vdev); + return -EPERM; + } + + if (vcrypto->status == status) + return 0; + + vcrypto->status = status; + + if (vcrypto->status & VIRTIO_CRYPTO_S_HW_READY) { + err = virtcrypto_dev_start(vcrypto); + if (err) { + dev_err(&vcrypto->vdev->dev, + "Failed to start virtio crypto device.\n"); + + return -EPERM; + } + dev_info(&vcrypto->vdev->dev, "Accelerator is ready\n"); + } else { + virtcrypto_dev_stop(vcrypto); + dev_info(&vcrypto->vdev->dev, "Accelerator is not ready\n"); + } + + return 0; +} + +static void virtcrypto_del_vqs(struct virtio_crypto *vcrypto) +{ + struct virtio_device *vdev = vcrypto->vdev; + + virtcrypto_clean_affinity(vcrypto, -1); + + vdev->config->del_vqs(vdev); + + virtcrypto_free_queues(vcrypto); +} + +static int virtcrypto_probe(struct virtio_device *vdev) +{ + int err = -EFAULT; + struct virtio_crypto *vcrypto; + u32 max_data_queues = 0, max_cipher_key_len = 0; + u32 max_auth_key_len = 0; + u64 max_size = 0; + + if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) + return -ENODEV; + + if (!vdev->config->get) { + dev_err(&vdev->dev, "%s failure: config access disabled\n", + __func__); + return -EINVAL; + } + + if (num_possible_nodes() > 1 && dev_to_node(&vdev->dev) < 0) { + /* + * If the accelerator is connected to a node with no memory + * there is no point in using the accelerator since the remote + * memory transaction will be very slow. + */ + dev_err(&vdev->dev, "Invalid NUMA configuration.\n"); + return -EINVAL; + } + + vcrypto = kzalloc_node(sizeof(*vcrypto), GFP_KERNEL, + dev_to_node(&vdev->dev)); + if (!vcrypto) + return -ENOMEM; + + virtio_cread(vdev, struct virtio_crypto_config, + max_dataqueues, &max_data_queues); + if (max_data_queues < 1) + max_data_queues = 1; + + virtio_cread(vdev, struct virtio_crypto_config, + max_cipher_key_len, &max_cipher_key_len); + virtio_cread(vdev, struct virtio_crypto_config, + max_auth_key_len, &max_auth_key_len); + virtio_cread(vdev, struct virtio_crypto_config, + max_size, &max_size); + + /* Add virtio crypto device to global table */ + err = virtcrypto_devmgr_add_dev(vcrypto); + if (err) { + dev_err(&vdev->dev, "Failed to add new virtio crypto device.\n"); + goto free; + } + vcrypto->owner = THIS_MODULE; + vcrypto = vdev->priv = vcrypto; + vcrypto->vdev = vdev; + + spin_lock_init(&vcrypto->ctrl_lock); + + /* Use single data queue as default */ + vcrypto->curr_queue = 1; + vcrypto->max_data_queues = max_data_queues; + vcrypto->max_cipher_key_len = max_cipher_key_len; + vcrypto->max_auth_key_len = max_auth_key_len; + vcrypto->max_size = max_size; + + dev_info(&vdev->dev, + "max_queues: %u, max_cipher_key_len: %u, max_auth_key_len: %u, max_size 0x%llx\n", + vcrypto->max_data_queues, + vcrypto->max_cipher_key_len, + vcrypto->max_auth_key_len, + vcrypto->max_size); + + err = virtcrypto_init_vqs(vcrypto); + if (err) { + dev_err(&vdev->dev, "Failed to initialize vqs.\n"); + goto free_dev; + } + virtio_device_ready(vdev); + + err = virtcrypto_update_status(vcrypto); + if (err) + goto free_vqs; + + return 0; + +free_vqs: + vcrypto->vdev->config->reset(vdev); + virtcrypto_del_vqs(vcrypto); +free_dev: + virtcrypto_devmgr_rm_dev(vcrypto); +free: + kfree(vcrypto); + return err; +} + +static void virtcrypto_free_unused_reqs(struct virtio_crypto *vcrypto) +{ + struct virtio_crypto_request *vc_req; + int i; + struct virtqueue *vq; + + for (i = 0; i < vcrypto->max_data_queues; i++) { + vq = vcrypto->data_vq[i].vq; + while ((vc_req = virtqueue_detach_unused_buf(vq)) != NULL) { + kfree(vc_req->req_data); + kfree(vc_req->sgs); + } + } +} + +static void virtcrypto_remove(struct virtio_device *vdev) +{ + struct virtio_crypto *vcrypto = vdev->priv; + + dev_info(&vdev->dev, "Start virtcrypto_remove.\n"); + + if (virtcrypto_dev_started(vcrypto)) + virtcrypto_dev_stop(vcrypto); + vdev->config->reset(vdev); + virtcrypto_free_unused_reqs(vcrypto); + virtcrypto_del_vqs(vcrypto); + virtcrypto_devmgr_rm_dev(vcrypto); + kfree(vcrypto); +} + +static void virtcrypto_config_changed(struct virtio_device *vdev) +{ + struct virtio_crypto *vcrypto = vdev->priv; + + virtcrypto_update_status(vcrypto); +} + +#ifdef CONFIG_PM_SLEEP +static int virtcrypto_freeze(struct virtio_device *vdev) +{ + struct virtio_crypto *vcrypto = vdev->priv; + + vdev->config->reset(vdev); + virtcrypto_free_unused_reqs(vcrypto); + if (virtcrypto_dev_started(vcrypto)) + virtcrypto_dev_stop(vcrypto); + + virtcrypto_del_vqs(vcrypto); + return 0; +} + +static int virtcrypto_restore(struct virtio_device *vdev) +{ + struct virtio_crypto *vcrypto = vdev->priv; + int err; + + err = virtcrypto_init_vqs(vcrypto); + if (err) + return err; + + virtio_device_ready(vdev); + err = virtcrypto_dev_start(vcrypto); + if (err) { + dev_err(&vdev->dev, "Failed to start virtio crypto device.\n"); + return -EFAULT; + } + + return 0; +} +#endif + +static unsigned int features[] = { + /* none */ +}; + +static struct virtio_device_id id_table[] = { + { VIRTIO_ID_CRYPTO, VIRTIO_DEV_ANY_ID }, + { 0 }, +}; + +static struct virtio_driver virtio_crypto_driver = { + .driver.name = KBUILD_MODNAME, + .driver.owner = THIS_MODULE, + .feature_table = features, + .feature_table_size = ARRAY_SIZE(features), + .id_table = id_table, + .probe = virtcrypto_probe, + .remove = virtcrypto_remove, + .config_changed = virtcrypto_config_changed, +#ifdef CONFIG_PM_SLEEP + .freeze = virtcrypto_freeze, + .restore = virtcrypto_restore, +#endif +}; + +module_virtio_driver(virtio_crypto_driver); + +MODULE_DEVICE_TABLE(virtio, id_table); +MODULE_DESCRIPTION("virtio crypto device driver"); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Gonglei "); diff --git a/drivers/crypto/virtio/virtio_crypto_mgr.c b/drivers/crypto/virtio/virtio_crypto_mgr.c new file mode 100644 index 000000000000..a69ff71de2c4 --- /dev/null +++ b/drivers/crypto/virtio/virtio_crypto_mgr.c @@ -0,0 +1,264 @@ + /* Management for virtio crypto devices (refer to adf_dev_mgr.c) + * + * Copyright 2016 HUAWEI TECHNOLOGIES CO., LTD. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + */ + +#include +#include +#include + +#include +#include "virtio_crypto_common.h" + +static LIST_HEAD(virtio_crypto_table); +static uint32_t num_devices; + +/* The table_lock protects the above global list and num_devices */ +static DEFINE_MUTEX(table_lock); + +#define VIRTIO_CRYPTO_MAX_DEVICES 32 + + +/* + * virtcrypto_devmgr_add_dev() - Add vcrypto_dev to the acceleration + * framework. + * @vcrypto_dev: Pointer to virtio crypto device. + * + * Function adds virtio crypto device to the global list. + * To be used by virtio crypto device specific drivers. + * + * Return: 0 on success, error code othewise. + */ +int virtcrypto_devmgr_add_dev(struct virtio_crypto *vcrypto_dev) +{ + struct list_head *itr; + + mutex_lock(&table_lock); + if (num_devices == VIRTIO_CRYPTO_MAX_DEVICES) { + pr_info("virtio_crypto: only support up to %d devices\n", + VIRTIO_CRYPTO_MAX_DEVICES); + mutex_unlock(&table_lock); + return -EFAULT; + } + + list_for_each(itr, &virtio_crypto_table) { + struct virtio_crypto *ptr = + list_entry(itr, struct virtio_crypto, list); + + if (ptr == vcrypto_dev) { + mutex_unlock(&table_lock); + return -EEXIST; + } + } + atomic_set(&vcrypto_dev->ref_count, 0); + list_add_tail(&vcrypto_dev->list, &virtio_crypto_table); + vcrypto_dev->dev_id = num_devices++; + mutex_unlock(&table_lock); + return 0; +} + +struct list_head *virtcrypto_devmgr_get_head(void) +{ + return &virtio_crypto_table; +} + +/* + * virtcrypto_devmgr_rm_dev() - Remove vcrypto_dev from the acceleration + * framework. + * @vcrypto_dev: Pointer to virtio crypto device. + * + * Function removes virtio crypto device from the acceleration framework. + * To be used by virtio crypto device specific drivers. + * + * Return: void + */ +void virtcrypto_devmgr_rm_dev(struct virtio_crypto *vcrypto_dev) +{ + mutex_lock(&table_lock); + list_del(&vcrypto_dev->list); + num_devices--; + mutex_unlock(&table_lock); +} + +/* + * virtcrypto_devmgr_get_first() + * + * Function returns the first virtio crypto device from the acceleration + * framework. + * + * To be used by virtio crypto device specific drivers. + * + * Return: pointer to vcrypto_dev or NULL if not found. + */ +struct virtio_crypto *virtcrypto_devmgr_get_first(void) +{ + struct virtio_crypto *dev = NULL; + + mutex_lock(&table_lock); + if (!list_empty(&virtio_crypto_table)) + dev = list_first_entry(&virtio_crypto_table, + struct virtio_crypto, + list); + mutex_unlock(&table_lock); + return dev; +} + +/* + * virtcrypto_dev_in_use() - Check whether vcrypto_dev is currently in use + * @vcrypto_dev: Pointer to virtio crypto device. + * + * To be used by virtio crypto device specific drivers. + * + * Return: 1 when device is in use, 0 otherwise. + */ +int virtcrypto_dev_in_use(struct virtio_crypto *vcrypto_dev) +{ + return atomic_read(&vcrypto_dev->ref_count) != 0; +} + +/* + * virtcrypto_dev_get() - Increment vcrypto_dev reference count + * @vcrypto_dev: Pointer to virtio crypto device. + * + * Increment the vcrypto_dev refcount and if this is the first time + * incrementing it during this period the vcrypto_dev is in use, + * increment the module refcount too. + * To be used by virtio crypto device specific drivers. + * + * Return: 0 when successful, EFAULT when fail to bump module refcount + */ +int virtcrypto_dev_get(struct virtio_crypto *vcrypto_dev) +{ + if (atomic_add_return(1, &vcrypto_dev->ref_count) == 1) + if (!try_module_get(vcrypto_dev->owner)) + return -EFAULT; + return 0; +} + +/* + * virtcrypto_dev_put() - Decrement vcrypto_dev reference count + * @vcrypto_dev: Pointer to virtio crypto device. + * + * Decrement the vcrypto_dev refcount and if this is the last time + * decrementing it during this period the vcrypto_dev is in use, + * decrement the module refcount too. + * To be used by virtio crypto device specific drivers. + * + * Return: void + */ +void virtcrypto_dev_put(struct virtio_crypto *vcrypto_dev) +{ + if (atomic_sub_return(1, &vcrypto_dev->ref_count) == 0) + module_put(vcrypto_dev->owner); +} + +/* + * virtcrypto_dev_started() - Check whether device has started + * @vcrypto_dev: Pointer to virtio crypto device. + * + * To be used by virtio crypto device specific drivers. + * + * Return: 1 when the device has started, 0 otherwise + */ +int virtcrypto_dev_started(struct virtio_crypto *vcrypto_dev) +{ + return (vcrypto_dev->status & VIRTIO_CRYPTO_S_HW_READY); +} + +/* + * virtcrypto_get_dev_node() - Get vcrypto_dev on the node. + * @node: Node id the driver works. + * + * Function returns the virtio crypto device used fewest on the node. + * + * To be used by virtio crypto device specific drivers. + * + * Return: pointer to vcrypto_dev or NULL if not found. + */ +struct virtio_crypto *virtcrypto_get_dev_node(int node) +{ + struct virtio_crypto *vcrypto_dev = NULL, *tmp_dev; + unsigned long best = ~0; + unsigned long ctr; + + mutex_lock(&table_lock); + list_for_each_entry(tmp_dev, virtcrypto_devmgr_get_head(), list) { + + if ((node == dev_to_node(&tmp_dev->vdev->dev) || + dev_to_node(&tmp_dev->vdev->dev) < 0) && + virtcrypto_dev_started(tmp_dev)) { + ctr = atomic_read(&tmp_dev->ref_count); + if (best > ctr) { + vcrypto_dev = tmp_dev; + best = ctr; + } + } + } + + if (!vcrypto_dev) { + pr_info("virtio_crypto: Could not find a device on node %d\n", + node); + /* Get any started device */ + list_for_each_entry(tmp_dev, + virtcrypto_devmgr_get_head(), list) { + if (virtcrypto_dev_started(tmp_dev)) { + vcrypto_dev = tmp_dev; + break; + } + } + } + mutex_unlock(&table_lock); + if (!vcrypto_dev) + return NULL; + + virtcrypto_dev_get(vcrypto_dev); + return vcrypto_dev; +} + +/* + * virtcrypto_dev_start() - Start virtio crypto device + * @vcrypto: Pointer to virtio crypto device. + * + * Function notifies all the registered services that the virtio crypto device + * is ready to be used. + * To be used by virtio crypto device specific drivers. + * + * Return: 0 on success, EFAULT when fail to register algorithms + */ +int virtcrypto_dev_start(struct virtio_crypto *vcrypto) +{ + if (virtio_crypto_algs_register()) { + pr_err("virtio_crypto: Failed to register crypto algs\n"); + return -EFAULT; + } + + return 0; +} + +/* + * virtcrypto_dev_stop() - Stop virtio crypto device + * @vcrypto: Pointer to virtio crypto device. + * + * Function notifies all the registered services that the virtio crypto device + * is ready to be used. + * To be used by virtio crypto device specific drivers. + * + * Return: void + */ +void virtcrypto_dev_stop(struct virtio_crypto *vcrypto) +{ + virtio_crypto_algs_unregister(); +} diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index bc2ef9fef7c8..a26c5c76ab62 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -462,6 +462,7 @@ header-y += virtio_rng.h header-y += virtio_scsi.h header-y += virtio_types.h header-y += virtio_vsock.h +header-y += virtio_crypto.h header-y += vm_sockets.h header-y += vt.h header-y += vtpm_proxy.h diff --git a/include/uapi/linux/virtio_crypto.h b/include/uapi/linux/virtio_crypto.h new file mode 100644 index 000000000000..50cdc8aebfcf --- /dev/null +++ b/include/uapi/linux/virtio_crypto.h @@ -0,0 +1,450 @@ +#ifndef _VIRTIO_CRYPTO_H +#define _VIRTIO_CRYPTO_H +/* This header is BSD licensed so anyone can use the definitions to implement + * compatible drivers/servers. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of IBM nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL IBM OR + * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF + * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, + * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT + * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ +#include +#include +#include +#include + + +#define VIRTIO_CRYPTO_SERVICE_CIPHER 0 +#define VIRTIO_CRYPTO_SERVICE_HASH 1 +#define VIRTIO_CRYPTO_SERVICE_MAC 2 +#define VIRTIO_CRYPTO_SERVICE_AEAD 3 + +#define VIRTIO_CRYPTO_OPCODE(service, op) (((service) << 8) | (op)) + +struct virtio_crypto_ctrl_header { +#define VIRTIO_CRYPTO_CIPHER_CREATE_SESSION \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_CIPHER, 0x02) +#define VIRTIO_CRYPTO_CIPHER_DESTROY_SESSION \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_CIPHER, 0x03) +#define VIRTIO_CRYPTO_HASH_CREATE_SESSION \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_HASH, 0x02) +#define VIRTIO_CRYPTO_HASH_DESTROY_SESSION \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_HASH, 0x03) +#define VIRTIO_CRYPTO_MAC_CREATE_SESSION \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_MAC, 0x02) +#define VIRTIO_CRYPTO_MAC_DESTROY_SESSION \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_MAC, 0x03) +#define VIRTIO_CRYPTO_AEAD_CREATE_SESSION \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AEAD, 0x02) +#define VIRTIO_CRYPTO_AEAD_DESTROY_SESSION \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AEAD, 0x03) + __le32 opcode; + __le32 algo; + __le32 flag; + /* data virtqueue id */ + __le32 queue_id; +}; + +struct virtio_crypto_cipher_session_para { +#define VIRTIO_CRYPTO_NO_CIPHER 0 +#define VIRTIO_CRYPTO_CIPHER_ARC4 1 +#define VIRTIO_CRYPTO_CIPHER_AES_ECB 2 +#define VIRTIO_CRYPTO_CIPHER_AES_CBC 3 +#define VIRTIO_CRYPTO_CIPHER_AES_CTR 4 +#define VIRTIO_CRYPTO_CIPHER_DES_ECB 5 +#define VIRTIO_CRYPTO_CIPHER_DES_CBC 6 +#define VIRTIO_CRYPTO_CIPHER_3DES_ECB 7 +#define VIRTIO_CRYPTO_CIPHER_3DES_CBC 8 +#define VIRTIO_CRYPTO_CIPHER_3DES_CTR 9 +#define VIRTIO_CRYPTO_CIPHER_KASUMI_F8 10 +#define VIRTIO_CRYPTO_CIPHER_SNOW3G_UEA2 11 +#define VIRTIO_CRYPTO_CIPHER_AES_F8 12 +#define VIRTIO_CRYPTO_CIPHER_AES_XTS 13 +#define VIRTIO_CRYPTO_CIPHER_ZUC_EEA3 14 + __le32 algo; + /* length of key */ + __le32 keylen; + +#define VIRTIO_CRYPTO_OP_ENCRYPT 1 +#define VIRTIO_CRYPTO_OP_DECRYPT 2 + /* encrypt or decrypt */ + __le32 op; + __le32 padding; +}; + +struct virtio_crypto_session_input { + /* Device-writable part */ + __le64 session_id; + __le32 status; + __le32 padding; +}; + +struct virtio_crypto_cipher_session_req { + struct virtio_crypto_cipher_session_para para; + __u8 padding[32]; +}; + +struct virtio_crypto_hash_session_para { +#define VIRTIO_CRYPTO_NO_HASH 0 +#define VIRTIO_CRYPTO_HASH_MD5 1 +#define VIRTIO_CRYPTO_HASH_SHA1 2 +#define VIRTIO_CRYPTO_HASH_SHA_224 3 +#define VIRTIO_CRYPTO_HASH_SHA_256 4 +#define VIRTIO_CRYPTO_HASH_SHA_384 5 +#define VIRTIO_CRYPTO_HASH_SHA_512 6 +#define VIRTIO_CRYPTO_HASH_SHA3_224 7 +#define VIRTIO_CRYPTO_HASH_SHA3_256 8 +#define VIRTIO_CRYPTO_HASH_SHA3_384 9 +#define VIRTIO_CRYPTO_HASH_SHA3_512 10 +#define VIRTIO_CRYPTO_HASH_SHA3_SHAKE128 11 +#define VIRTIO_CRYPTO_HASH_SHA3_SHAKE256 12 + __le32 algo; + /* hash result length */ + __le32 hash_result_len; + __u8 padding[8]; +}; + +struct virtio_crypto_hash_create_session_req { + struct virtio_crypto_hash_session_para para; + __u8 padding[40]; +}; + +struct virtio_crypto_mac_session_para { +#define VIRTIO_CRYPTO_NO_MAC 0 +#define VIRTIO_CRYPTO_MAC_HMAC_MD5 1 +#define VIRTIO_CRYPTO_MAC_HMAC_SHA1 2 +#define VIRTIO_CRYPTO_MAC_HMAC_SHA_224 3 +#define VIRTIO_CRYPTO_MAC_HMAC_SHA_256 4 +#define VIRTIO_CRYPTO_MAC_HMAC_SHA_384 5 +#define VIRTIO_CRYPTO_MAC_HMAC_SHA_512 6 +#define VIRTIO_CRYPTO_MAC_CMAC_3DES 25 +#define VIRTIO_CRYPTO_MAC_CMAC_AES 26 +#define VIRTIO_CRYPTO_MAC_KASUMI_F9 27 +#define VIRTIO_CRYPTO_MAC_SNOW3G_UIA2 28 +#define VIRTIO_CRYPTO_MAC_GMAC_AES 41 +#define VIRTIO_CRYPTO_MAC_GMAC_TWOFISH 42 +#define VIRTIO_CRYPTO_MAC_CBCMAC_AES 49 +#define VIRTIO_CRYPTO_MAC_CBCMAC_KASUMI_F9 50 +#define VIRTIO_CRYPTO_MAC_XCBC_AES 53 + __le32 algo; + /* hash result length */ + __le32 hash_result_len; + /* length of authenticated key */ + __le32 auth_key_len; + __le32 padding; +}; + +struct virtio_crypto_mac_create_session_req { + struct virtio_crypto_mac_session_para para; + __u8 padding[40]; +}; + +struct virtio_crypto_aead_session_para { +#define VIRTIO_CRYPTO_NO_AEAD 0 +#define VIRTIO_CRYPTO_AEAD_GCM 1 +#define VIRTIO_CRYPTO_AEAD_CCM 2 +#define VIRTIO_CRYPTO_AEAD_CHACHA20_POLY1305 3 + __le32 algo; + /* length of key */ + __le32 key_len; + /* hash result length */ + __le32 hash_result_len; + /* length of the additional authenticated data (AAD) in bytes */ + __le32 aad_len; + /* encrypt or decrypt, See above VIRTIO_CRYPTO_OP_* */ + __le32 op; + __le32 padding; +}; + +struct virtio_crypto_aead_create_session_req { + struct virtio_crypto_aead_session_para para; + __u8 padding[32]; +}; + +struct virtio_crypto_alg_chain_session_para { +#define VIRTIO_CRYPTO_SYM_ALG_CHAIN_ORDER_HASH_THEN_CIPHER 1 +#define VIRTIO_CRYPTO_SYM_ALG_CHAIN_ORDER_CIPHER_THEN_HASH 2 + __le32 alg_chain_order; +/* Plain hash */ +#define VIRTIO_CRYPTO_SYM_HASH_MODE_PLAIN 1 +/* Authenticated hash (mac) */ +#define VIRTIO_CRYPTO_SYM_HASH_MODE_AUTH 2 +/* Nested hash */ +#define VIRTIO_CRYPTO_SYM_HASH_MODE_NESTED 3 + __le32 hash_mode; + struct virtio_crypto_cipher_session_para cipher_param; + union { + struct virtio_crypto_hash_session_para hash_param; + struct virtio_crypto_mac_session_para mac_param; + __u8 padding[16]; + } u; + /* length of the additional authenticated data (AAD) in bytes */ + __le32 aad_len; + __le32 padding; +}; + +struct virtio_crypto_alg_chain_session_req { + struct virtio_crypto_alg_chain_session_para para; +}; + +struct virtio_crypto_sym_create_session_req { + union { + struct virtio_crypto_cipher_session_req cipher; + struct virtio_crypto_alg_chain_session_req chain; + __u8 padding[48]; + } u; + + /* Device-readable part */ + +/* No operation */ +#define VIRTIO_CRYPTO_SYM_OP_NONE 0 +/* Cipher only operation on the data */ +#define VIRTIO_CRYPTO_SYM_OP_CIPHER 1 +/* + * Chain any cipher with any hash or mac operation. The order + * depends on the value of alg_chain_order param + */ +#define VIRTIO_CRYPTO_SYM_OP_ALGORITHM_CHAINING 2 + __le32 op_type; + __le32 padding; +}; + +struct virtio_crypto_destroy_session_req { + /* Device-readable part */ + __le64 session_id; + __u8 padding[48]; +}; + +/* The request of the control virtqueue's packet */ +struct virtio_crypto_op_ctrl_req { + struct virtio_crypto_ctrl_header header; + + union { + struct virtio_crypto_sym_create_session_req + sym_create_session; + struct virtio_crypto_hash_create_session_req + hash_create_session; + struct virtio_crypto_mac_create_session_req + mac_create_session; + struct virtio_crypto_aead_create_session_req + aead_create_session; + struct virtio_crypto_destroy_session_req + destroy_session; + __u8 padding[56]; + } u; +}; + +struct virtio_crypto_op_header { +#define VIRTIO_CRYPTO_CIPHER_ENCRYPT \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_CIPHER, 0x00) +#define VIRTIO_CRYPTO_CIPHER_DECRYPT \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_CIPHER, 0x01) +#define VIRTIO_CRYPTO_HASH \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_HASH, 0x00) +#define VIRTIO_CRYPTO_MAC \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_MAC, 0x00) +#define VIRTIO_CRYPTO_AEAD_ENCRYPT \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AEAD, 0x00) +#define VIRTIO_CRYPTO_AEAD_DECRYPT \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AEAD, 0x01) + __le32 opcode; + /* algo should be service-specific algorithms */ + __le32 algo; + /* session_id should be service-specific algorithms */ + __le64 session_id; + /* control flag to control the request */ + __le32 flag; + __le32 padding; +}; + +struct virtio_crypto_cipher_para { + /* + * Byte Length of valid IV/Counter + * + * For block ciphers in CBC or F8 mode, or for Kasumi in F8 mode, or for + * SNOW3G in UEA2 mode, this is the length of the IV (which + * must be the same as the block length of the cipher). + * For block ciphers in CTR mode, this is the length of the counter + * (which must be the same as the block length of the cipher). + * For AES-XTS, this is the 128bit tweak, i, from IEEE Std 1619-2007. + * + * The IV/Counter will be updated after every partial cryptographic + * operation. + */ + __le32 iv_len; + /* length of source data */ + __le32 src_data_len; + /* length of dst data */ + __le32 dst_data_len; + __le32 padding; +}; + +struct virtio_crypto_hash_para { + /* length of source data */ + __le32 src_data_len; + /* hash result length */ + __le32 hash_result_len; +}; + +struct virtio_crypto_mac_para { + struct virtio_crypto_hash_para hash; +}; + +struct virtio_crypto_aead_para { + /* + * Byte Length of valid IV data pointed to by the below iv_addr + * parameter. + * + * For GCM mode, this is either 12 (for 96-bit IVs) or 16, in which + * case iv_addr points to J0. + * For CCM mode, this is the length of the nonce, which can be in the + * range 7 to 13 inclusive. + */ + __le32 iv_len; + /* length of additional auth data */ + __le32 aad_len; + /* length of source data */ + __le32 src_data_len; + /* length of dst data */ + __le32 dst_data_len; +}; + +struct virtio_crypto_cipher_data_req { + /* Device-readable part */ + struct virtio_crypto_cipher_para para; + __u8 padding[24]; +}; + +struct virtio_crypto_hash_data_req { + /* Device-readable part */ + struct virtio_crypto_hash_para para; + __u8 padding[40]; +}; + +struct virtio_crypto_mac_data_req { + /* Device-readable part */ + struct virtio_crypto_mac_para para; + __u8 padding[40]; +}; + +struct virtio_crypto_alg_chain_data_para { + __le32 iv_len; + /* Length of source data */ + __le32 src_data_len; + /* Length of destination data */ + __le32 dst_data_len; + /* Starting point for cipher processing in source data */ + __le32 cipher_start_src_offset; + /* Length of the source data that the cipher will be computed on */ + __le32 len_to_cipher; + /* Starting point for hash processing in source data */ + __le32 hash_start_src_offset; + /* Length of the source data that the hash will be computed on */ + __le32 len_to_hash; + /* Length of the additional auth data */ + __le32 aad_len; + /* Length of the hash result */ + __le32 hash_result_len; + __le32 reserved; +}; + +struct virtio_crypto_alg_chain_data_req { + /* Device-readable part */ + struct virtio_crypto_alg_chain_data_para para; +}; + +struct virtio_crypto_sym_data_req { + union { + struct virtio_crypto_cipher_data_req cipher; + struct virtio_crypto_alg_chain_data_req chain; + __u8 padding[40]; + } u; + + /* See above VIRTIO_CRYPTO_SYM_OP_* */ + __le32 op_type; + __le32 padding; +}; + +struct virtio_crypto_aead_data_req { + /* Device-readable part */ + struct virtio_crypto_aead_para para; + __u8 padding[32]; +}; + +/* The request of the data virtqueue's packet */ +struct virtio_crypto_op_data_req { + struct virtio_crypto_op_header header; + + union { + struct virtio_crypto_sym_data_req sym_req; + struct virtio_crypto_hash_data_req hash_req; + struct virtio_crypto_mac_data_req mac_req; + struct virtio_crypto_aead_data_req aead_req; + __u8 padding[48]; + } u; +}; + +#define VIRTIO_CRYPTO_OK 0 +#define VIRTIO_CRYPTO_ERR 1 +#define VIRTIO_CRYPTO_BADMSG 2 +#define VIRTIO_CRYPTO_NOTSUPP 3 +#define VIRTIO_CRYPTO_INVSESS 4 /* Invalid session id */ + +/* The accelerator hardware is ready */ +#define VIRTIO_CRYPTO_S_HW_READY (1 << 0) + +struct virtio_crypto_config { + /* See VIRTIO_CRYPTO_OP_* above */ + __u32 status; + + /* + * Maximum number of data queue + */ + __u32 max_dataqueues; + + /* + * Specifies the services mask which the device support, + * see VIRTIO_CRYPTO_SERVICE_* above + */ + __u32 crypto_services; + + /* Detailed algorithms mask */ + __u32 cipher_algo_l; + __u32 cipher_algo_h; + __u32 hash_algo; + __u32 mac_algo_l; + __u32 mac_algo_h; + __u32 aead_algo; + /* Maximum length of cipher key */ + __u32 max_cipher_key_len; + /* Maximum length of authenticated key */ + __u32 max_auth_key_len; + __u32 reserve; + /* Maximum size of each crypto request's content */ + __u64 max_size; +}; + +struct virtio_crypto_inhdr { + /* See VIRTIO_CRYPTO_* above */ + __u8 status; +}; +#endif diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index 3228d582234a..6d5c3b2d4f4d 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -42,5 +42,6 @@ #define VIRTIO_ID_GPU 16 /* virtio GPU */ #define VIRTIO_ID_INPUT 18 /* virtio input */ #define VIRTIO_ID_VSOCK 19 /* virtio vsock transport */ +#define VIRTIO_ID_CRYPTO 20 /* virtio crypto */ #endif /* _LINUX_VIRTIO_IDS_H */ -- cgit v1.2.3 From 8d390464bf22a47252eb976efae2f462c5c884e5 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 18 Nov 2016 15:58:39 +0800 Subject: vhost: remove unused feature bit Signed-off-by: Jason Wang Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vhost.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 56b7ab584cc0..60180c0b5dc6 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -172,8 +172,6 @@ struct vhost_memory { #define VHOST_F_LOG_ALL 26 /* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */ #define VHOST_NET_F_VIRTIO_NET_HDR 27 -/* Vhost have device IOTLB */ -#define VHOST_F_DEVICE_IOTLB 63 /* VHOST_SCSI specific definitions */ -- cgit v1.2.3 From 05de97003c773e7881e4df3f767b81a6508107f2 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 8 Dec 2016 04:19:29 +0200 Subject: linux/types.h: enable endian checks for all sparse builds By now, linux is mostly endian-clean. Enabling endian-ness checks for everyone produces about 200 new sparse warnings for me - less than 10% over the 2000 sparse warnings already there. Not a big deal, OTOH enabling this helps people notice they are introducing new bugs. So let's just drop __CHECK_ENDIAN__. Follow-up patches can drop distinction between __bitwise and __bitwise__. Cc: Linus Torvalds Suggested-by: Christoph Hellwig Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/types.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/types.h b/include/uapi/linux/types.h index acf0979b790a..41e5914f0a8e 100644 --- a/include/uapi/linux/types.h +++ b/include/uapi/linux/types.h @@ -23,11 +23,7 @@ #else #define __bitwise__ #endif -#ifdef __CHECK_ENDIAN__ #define __bitwise __bitwise__ -#else -#define __bitwise -#endif typedef __u16 __bitwise __le16; typedef __u16 __bitwise __be16; -- cgit v1.2.3 From 9efeccacd3a486128d3add611dd4cefb5b60a58c Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Sun, 11 Dec 2016 06:34:53 +0200 Subject: linux: drop __bitwise__ everywhere __bitwise__ used to mean "yes, please enable sparse checks unconditionally", but now that we dropped __CHECK_ENDIAN__ __bitwise is exactly the same. There aren't many users, replace it by __bitwise everywhere. Signed-off-by: Michael S. Tsirkin Acked-by: Greg Kroah-Hartman Acked-by: Stefan Schmidt Acked-by: Krzysztof Kozlowski Akced-by: Lee Duncan --- arch/arm/plat-samsung/include/plat/gpio-cfg.h | 2 +- drivers/md/dm-cache-block-types.h | 6 +++--- drivers/net/ethernet/sun/sunhme.h | 2 +- drivers/net/wireless/intel/iwlwifi/iwl-fw-file.h | 4 ++-- include/linux/mmzone.h | 2 +- include/linux/serial_core.h | 4 ++-- include/linux/types.h | 4 ++-- include/scsi/iscsi_proto.h | 2 +- include/target/target_core_base.h | 2 +- include/uapi/linux/virtio_types.h | 6 +++--- net/ieee802154/6lowpan/6lowpan_i.h | 2 +- net/mac80211/ieee80211_i.h | 4 ++-- 12 files changed, 20 insertions(+), 20 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/arm/plat-samsung/include/plat/gpio-cfg.h b/arch/arm/plat-samsung/include/plat/gpio-cfg.h index 21391faab068..e55d1f597db8 100644 --- a/arch/arm/plat-samsung/include/plat/gpio-cfg.h +++ b/arch/arm/plat-samsung/include/plat/gpio-cfg.h @@ -26,7 +26,7 @@ #include -typedef unsigned int __bitwise__ samsung_gpio_pull_t; +typedef unsigned int __bitwise samsung_gpio_pull_t; /* forward declaration if gpio-core.h hasn't been included */ struct samsung_gpio_chip; diff --git a/drivers/md/dm-cache-block-types.h b/drivers/md/dm-cache-block-types.h index bed4ad4e1b7c..389c9e8ac785 100644 --- a/drivers/md/dm-cache-block-types.h +++ b/drivers/md/dm-cache-block-types.h @@ -17,9 +17,9 @@ * discard bitset. */ -typedef dm_block_t __bitwise__ dm_oblock_t; -typedef uint32_t __bitwise__ dm_cblock_t; -typedef dm_block_t __bitwise__ dm_dblock_t; +typedef dm_block_t __bitwise dm_oblock_t; +typedef uint32_t __bitwise dm_cblock_t; +typedef dm_block_t __bitwise dm_dblock_t; static inline dm_oblock_t to_oblock(dm_block_t b) { diff --git a/drivers/net/ethernet/sun/sunhme.h b/drivers/net/ethernet/sun/sunhme.h index f4307654e4ae..4a8d5b18dfd5 100644 --- a/drivers/net/ethernet/sun/sunhme.h +++ b/drivers/net/ethernet/sun/sunhme.h @@ -302,7 +302,7 @@ * Always write the address first before setting the ownership * bits to avoid races with the hardware scanning the ring. */ -typedef u32 __bitwise__ hme32; +typedef u32 __bitwise hme32; struct happy_meal_rxd { hme32 rx_flags; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-fw-file.h b/drivers/net/wireless/intel/iwlwifi/iwl-fw-file.h index 1ad0ec180d5d..84813b550ef1 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-fw-file.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-fw-file.h @@ -228,7 +228,7 @@ enum iwl_ucode_tlv_flag { IWL_UCODE_TLV_FLAGS_BCAST_FILTERING = BIT(29), }; -typedef unsigned int __bitwise__ iwl_ucode_tlv_api_t; +typedef unsigned int __bitwise iwl_ucode_tlv_api_t; /** * enum iwl_ucode_tlv_api - ucode api @@ -258,7 +258,7 @@ enum iwl_ucode_tlv_api { #endif }; -typedef unsigned int __bitwise__ iwl_ucode_tlv_capa_t; +typedef unsigned int __bitwise iwl_ucode_tlv_capa_t; /** * enum iwl_ucode_tlv_capa - ucode capabilities diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0f088f3a2fed..36d9896fbc1e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -246,7 +246,7 @@ struct lruvec { #define ISOLATE_UNEVICTABLE ((__force isolate_mode_t)0x8) /* LRU Isolation modes. */ -typedef unsigned __bitwise__ isolate_mode_t; +typedef unsigned __bitwise isolate_mode_t; enum zone_watermarks { WMARK_MIN, diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 5d494888a612..5def8e830fb0 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -111,8 +111,8 @@ struct uart_icount { __u32 buf_overrun; }; -typedef unsigned int __bitwise__ upf_t; -typedef unsigned int __bitwise__ upstat_t; +typedef unsigned int __bitwise upf_t; +typedef unsigned int __bitwise upstat_t; struct uart_port { spinlock_t lock; /* port lock */ diff --git a/include/linux/types.h b/include/linux/types.h index baf718324f4a..d501ad3ba247 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -154,8 +154,8 @@ typedef u64 dma_addr_t; typedef u32 dma_addr_t; #endif -typedef unsigned __bitwise__ gfp_t; -typedef unsigned __bitwise__ fmode_t; +typedef unsigned __bitwise gfp_t; +typedef unsigned __bitwise fmode_t; #ifdef CONFIG_PHYS_ADDR_T_64BIT typedef u64 phys_addr_t; diff --git a/include/scsi/iscsi_proto.h b/include/scsi/iscsi_proto.h index c1260d80ef30..df156f1d50b2 100644 --- a/include/scsi/iscsi_proto.h +++ b/include/scsi/iscsi_proto.h @@ -74,7 +74,7 @@ static inline int iscsi_sna_gte(u32 n1, u32 n2) #define zero_data(p) {p[0]=0;p[1]=0;p[2]=0;} /* initiator tags; opaque for target */ -typedef uint32_t __bitwise__ itt_t; +typedef uint32_t __bitwise itt_t; /* below makes sense only for initiator that created this tag */ #define build_itt(itt, age) ((__force itt_t)\ ((itt) | ((age) << ISCSI_AGE_SHIFT))) diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index c2119008990a..00558287936d 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -149,7 +149,7 @@ enum se_cmd_flags_table { * Used by transport_send_check_condition_and_sense() * to signal which ASC/ASCQ sense payload should be built. */ -typedef unsigned __bitwise__ sense_reason_t; +typedef unsigned __bitwise sense_reason_t; enum tcm_sense_reason_table { #define R(x) (__force sense_reason_t )(x) diff --git a/include/uapi/linux/virtio_types.h b/include/uapi/linux/virtio_types.h index e845e8c4cbee..55c3b738722c 100644 --- a/include/uapi/linux/virtio_types.h +++ b/include/uapi/linux/virtio_types.h @@ -39,8 +39,8 @@ * - __le{16,32,64} for standard-compliant virtio devices */ -typedef __u16 __bitwise__ __virtio16; -typedef __u32 __bitwise__ __virtio32; -typedef __u64 __bitwise__ __virtio64; +typedef __u16 __bitwise __virtio16; +typedef __u32 __bitwise __virtio32; +typedef __u64 __bitwise __virtio64; #endif /* _UAPI_LINUX_VIRTIO_TYPES_H */ diff --git a/net/ieee802154/6lowpan/6lowpan_i.h b/net/ieee802154/6lowpan/6lowpan_i.h index 5ac778962e4e..ac7c96b73ad5 100644 --- a/net/ieee802154/6lowpan/6lowpan_i.h +++ b/net/ieee802154/6lowpan/6lowpan_i.h @@ -7,7 +7,7 @@ #include #include -typedef unsigned __bitwise__ lowpan_rx_result; +typedef unsigned __bitwise lowpan_rx_result; #define RX_CONTINUE ((__force lowpan_rx_result) 0u) #define RX_DROP_UNUSABLE ((__force lowpan_rx_result) 1u) #define RX_DROP ((__force lowpan_rx_result) 2u) diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index d37a577f63a1..b2069fbd60f9 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -159,7 +159,7 @@ enum ieee80211_bss_valid_data_flags { IEEE80211_BSS_VALID_ERP = BIT(3) }; -typedef unsigned __bitwise__ ieee80211_tx_result; +typedef unsigned __bitwise ieee80211_tx_result; #define TX_CONTINUE ((__force ieee80211_tx_result) 0u) #define TX_DROP ((__force ieee80211_tx_result) 1u) #define TX_QUEUED ((__force ieee80211_tx_result) 2u) @@ -180,7 +180,7 @@ struct ieee80211_tx_data { }; -typedef unsigned __bitwise__ ieee80211_rx_result; +typedef unsigned __bitwise ieee80211_rx_result; #define RX_CONTINUE ((__force ieee80211_rx_result) 0u) #define RX_DROP_UNUSABLE ((__force ieee80211_rx_result) 1u) #define RX_DROP_MONITOR ((__force ieee80211_rx_result) 2u) -- cgit v1.2.3 From 96a420d2d37cc019d0fbb95c9f0e965fa1080e1f Mon Sep 17 00:00:00 2001 From: Vincent Pelletier Date: Thu, 15 Dec 2016 12:47:41 +0000 Subject: usb: gadget: f_fs: Document eventfd effect on descriptor format. When FUNCTIONFS_EVENTFD flag is set, __ffs_data_got_descs reads a 32bits, little-endian value right after the fixed structure header, and passes it to eventfd_ctx_fdget. Document this. Also, rephrase a comment to be affirmative about the role of string descriptor at index 0. Ref: USB 2.0 spec paragraph "9.6.7 String", and also checked to still be current in USB 3.0 spec paragraph "9.6.9 String". Signed-off-by: Vincent Pelletier Signed-off-by: Felipe Balbi --- drivers/usb/gadget/function/f_fs.c | 4 ++-- include/uapi/linux/usb/functionfs.h | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index aab3fc1dbb94..818f4997c1ac 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -2091,8 +2091,8 @@ static int __ffs_data_do_entity(enum ffs_entity_type type, case FFS_STRING: /* - * Strings are indexed from 1 (0 is magic ;) reserved - * for languages list or some such) + * Strings are indexed from 1 (0 is reserved + * for languages list) */ if (*valuep > helper->ffs->strings_count) helper->ffs->strings_count = *valuep; diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h index acc63697a0cc..b2a31a55a612 100644 --- a/include/uapi/linux/usb/functionfs.h +++ b/include/uapi/linux/usb/functionfs.h @@ -93,6 +93,7 @@ struct usb_ext_prop_desc { * | 0 | magic | LE32 | FUNCTIONFS_DESCRIPTORS_MAGIC_V2 | * | 4 | length | LE32 | length of the whole data chunk | * | 8 | flags | LE32 | combination of functionfs_flags | + * | | eventfd | LE32 | eventfd file descriptor | * | | fs_count | LE32 | number of full-speed descriptors | * | | hs_count | LE32 | number of high-speed descriptors | * | | ss_count | LE32 | number of super-speed descriptors | -- cgit v1.2.3 From 575b1967e10a1f3038266244d2c7a3ca6b99fed8 Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Tue, 10 Jan 2017 16:58:30 -0800 Subject: timerfd: export defines to userspace Since userspace is expected to call timerfd syscalls directly with these flags/ioctls, make sure we export them so they don't have to duplicate the values themselves. Link: http://lkml.kernel.org/r/20161219064052.7196-1-vapier@gentoo.org Signed-off-by: Mike Frysinger Acked-by: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/timerfd.h | 20 +------------------- include/uapi/linux/Kbuild | 1 + include/uapi/linux/timerfd.h | 36 ++++++++++++++++++++++++++++++++++++ 3 files changed, 38 insertions(+), 19 deletions(-) create mode 100644 include/uapi/linux/timerfd.h (limited to 'include/uapi/linux') diff --git a/include/linux/timerfd.h b/include/linux/timerfd.h index bd36ce431e32..bab0b1ad0613 100644 --- a/include/linux/timerfd.h +++ b/include/linux/timerfd.h @@ -8,23 +8,7 @@ #ifndef _LINUX_TIMERFD_H #define _LINUX_TIMERFD_H -/* For O_CLOEXEC and O_NONBLOCK */ -#include - -/* For _IO helpers */ -#include - -/* - * CAREFUL: Check include/asm-generic/fcntl.h when defining - * new flags, since they might collide with O_* ones. We want - * to re-use O_* flags that couldn't possibly have a meaning - * from eventfd, in order to leave a free define-space for - * shared O_* flags. - */ -#define TFD_TIMER_ABSTIME (1 << 0) -#define TFD_TIMER_CANCEL_ON_SET (1 << 1) -#define TFD_CLOEXEC O_CLOEXEC -#define TFD_NONBLOCK O_NONBLOCK +#include #define TFD_SHARED_FCNTL_FLAGS (TFD_CLOEXEC | TFD_NONBLOCK) /* Flags for timerfd_create. */ @@ -32,6 +16,4 @@ /* Flags for timerfd_settime. */ #define TFD_SETTIME_FLAGS (TFD_TIMER_ABSTIME | TFD_TIMER_CANCEL_ON_SET) -#define TFD_IOC_SET_TICKS _IOW('T', 0, u64) - #endif /* _LINUX_TIMERFD_H */ diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index a8b93e685239..f330ba4547cf 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -414,6 +414,7 @@ header-y += telephony.h header-y += termios.h header-y += thermal.h header-y += time.h +header-y += timerfd.h header-y += times.h header-y += timex.h header-y += tiocl.h diff --git a/include/uapi/linux/timerfd.h b/include/uapi/linux/timerfd.h new file mode 100644 index 000000000000..6fcfaa8da173 --- /dev/null +++ b/include/uapi/linux/timerfd.h @@ -0,0 +1,36 @@ +/* + * include/linux/timerfd.h + * + * Copyright (C) 2007 Davide Libenzi + * + */ + +#ifndef _UAPI_LINUX_TIMERFD_H +#define _UAPI_LINUX_TIMERFD_H + +#include + +/* For O_CLOEXEC and O_NONBLOCK */ +#include + +/* For _IO helpers */ +#include + +/* + * CAREFUL: Check include/asm-generic/fcntl.h when defining + * new flags, since they might collide with O_* ones. We want + * to re-use O_* flags that couldn't possibly have a meaning + * from eventfd, in order to leave a free define-space for + * shared O_* flags. + * + * Also make sure to update the masks in include/linux/timerfd.h + * when adding new flags. + */ +#define TFD_TIMER_ABSTIME (1 << 0) +#define TFD_TIMER_CANCEL_ON_SET (1 << 1) +#define TFD_CLOEXEC O_CLOEXEC +#define TFD_NONBLOCK O_NONBLOCK + +#define TFD_IOC_SET_TICKS _IOW('T', 0, __u64) + +#endif /* _UAPI_LINUX_TIMERFD_H */ -- cgit v1.2.3 From 06f7c88c107fb469f4f1344142e80df5175c6836 Mon Sep 17 00:00:00 2001 From: Beni Lev Date: Tue, 19 Jul 2016 19:28:56 +0300 Subject: cfg80211: consider VHT opmode on station update Currently, this attribute is only fetched on station addition, but not on station change. Since this info is only present in the assoc request, with full station state support in the driver it cannot be present when the station is added. Thus, add support for changing the VHT opmode on station update if done before (or while) the station is marked as associated. After this, ignore it, since it used to be ignored. Signed-off-by: Beni Lev Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 4 +++- net/wireless/nl80211.c | 15 +++++++++++++++ 2 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 6b76e3b0c18e..bea982af9cfb 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1772,7 +1772,9 @@ enum nl80211_commands { * * @NL80211_ATTR_OPMODE_NOTIF: Operating mode field from Operating Mode * Notification Element based on association request when used with - * %NL80211_CMD_NEW_STATION; u8 attribute. + * %NL80211_CMD_NEW_STATION or %NL80211_CMD_SET_STATION (only when + * %NL80211_FEATURE_FULL_AP_CLIENT_STATE is supported, or with TDLS); + * u8 attribute. * * @NL80211_ATTR_VENDOR_ID: The vendor ID, either a 24-bit OUI or, if * %NL80211_VENDOR_ID_IS_LINUX is set, a special Linux ID (not used yet) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index ef5eff93a8b8..5c1b267e22be 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4615,6 +4615,15 @@ int cfg80211_check_station_change(struct wiphy *wiphy, break; } + /* + * Older kernel versions ignored this attribute entirely, so don't + * reject attempts to update it but mark it as unused instead so the + * driver won't look at the data. + */ + if (statype != CFG80211_STA_AP_CLIENT_UNASSOC && + statype != CFG80211_STA_TDLS_PEER_SETUP) + params->opmode_notif_used = false; + return 0; } EXPORT_SYMBOL(cfg80211_check_station_change); @@ -4854,6 +4863,12 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) params.local_pm = pm; } + if (info->attrs[NL80211_ATTR_OPMODE_NOTIF]) { + params.opmode_notif_used = true; + params.opmode_notif = + nla_get_u8(info->attrs[NL80211_ATTR_OPMODE_NOTIF]); + } + /* Include parameters for TDLS peer (will check later) */ err = nl80211_set_station_tdls(info, ¶ms); if (err) -- cgit v1.2.3 From f1f7714ea51c56b7163fb1a5acf39c6a204dd758 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 13 Jan 2017 23:38:15 +0100 Subject: bpf: rework prog_digest into prog_tag Commit 7bd509e311f4 ("bpf: add prog_digest and expose it via fdinfo/netlink") was recently discussed, partially due to admittedly suboptimal name of "prog_digest" in combination with sha1 hash usage, thus inevitably and rightfully concerns about its security in terms of collision resistance were raised with regards to use-cases. The intended use cases are for debugging resp. introspection only for providing a stable "tag" over the instruction sequence that both kernel and user space can calculate independently. It's not usable at all for making a security relevant decision. So collisions where two different instruction sequences generate the same tag can happen, but ideally at a rather low rate. The "tag" will be dumped in hex and is short enough to introspect in tracepoints or kallsyms output along with other data such as stack trace, etc. Thus, this patch performs a rename into prog_tag and truncates the tag to a short output (64 bits) to make it obvious it's not collision-free. Should in future a hash or facility be needed with a security relevant focus, then we can think about requirements, constraints, etc that would fit to that situation. For now, rework the exposed parts for the current use cases as long as nothing has been released yet. Tested on x86_64 and s390x. Fixes: 7bd509e311f4 ("bpf: add prog_digest and expose it via fdinfo/netlink") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Cc: Andy Lutomirski Signed-off-by: David S. Miller --- include/linux/bpf.h | 2 +- include/linux/filter.h | 6 ++++-- include/uapi/linux/pkt_cls.h | 2 +- include/uapi/linux/tc_act/tc_bpf.h | 2 +- kernel/bpf/core.c | 14 ++++++++------ kernel/bpf/syscall.c | 8 ++++---- kernel/bpf/verifier.c | 2 +- net/sched/act_bpf.c | 5 ++--- net/sched/cls_bpf.c | 4 ++-- 9 files changed, 24 insertions(+), 21 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f74ae68086dc..05cf951df3fe 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -216,7 +216,7 @@ u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5); u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); -int bpf_prog_calc_digest(struct bpf_prog *fp); +int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); diff --git a/include/linux/filter.h b/include/linux/filter.h index a0934e6c9bab..e4eb2546339a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -57,6 +57,8 @@ struct bpf_prog_aux; /* BPF program can access up to 512 bytes of stack space. */ #define MAX_BPF_STACK 512 +#define BPF_TAG_SIZE 8 + /* Helper macros for filter block array initializers. */ /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ @@ -408,7 +410,7 @@ struct bpf_prog { kmemcheck_bitfield_end(meta); enum bpf_prog_type type; /* Type of BPF program */ u32 len; /* Number of filter blocks */ - u32 digest[SHA_DIGEST_WORDS]; /* Program digest */ + u8 tag[BPF_TAG_SIZE]; struct bpf_prog_aux *aux; /* Auxiliary fields */ struct sock_fprog_kern *orig_prog; /* Original BPF program */ unsigned int (*bpf_func)(const void *ctx, @@ -519,7 +521,7 @@ static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog) return prog->len * sizeof(struct bpf_insn); } -static inline u32 bpf_prog_digest_scratch_size(const struct bpf_prog *prog) +static inline u32 bpf_prog_tag_scratch_size(const struct bpf_prog *prog) { return round_up(bpf_prog_insn_size(prog) + sizeof(__be64) + 1, SHA_MESSAGE_BYTES); diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index cb4bcdc58543..a4dcd88ec271 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -397,7 +397,7 @@ enum { TCA_BPF_NAME, TCA_BPF_FLAGS, TCA_BPF_FLAGS_GEN, - TCA_BPF_DIGEST, + TCA_BPF_TAG, __TCA_BPF_MAX, }; diff --git a/include/uapi/linux/tc_act/tc_bpf.h b/include/uapi/linux/tc_act/tc_bpf.h index a6b88a6f7f71..975b50dc8d1d 100644 --- a/include/uapi/linux/tc_act/tc_bpf.h +++ b/include/uapi/linux/tc_act/tc_bpf.h @@ -27,7 +27,7 @@ enum { TCA_ACT_BPF_FD, TCA_ACT_BPF_NAME, TCA_ACT_BPF_PAD, - TCA_ACT_BPF_DIGEST, + TCA_ACT_BPF_TAG, __TCA_ACT_BPF_MAX, }; #define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 1eb4f1303756..503d4211988a 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -146,10 +146,11 @@ void __bpf_prog_free(struct bpf_prog *fp) vfree(fp); } -int bpf_prog_calc_digest(struct bpf_prog *fp) +int bpf_prog_calc_tag(struct bpf_prog *fp) { const u32 bits_offset = SHA_MESSAGE_BYTES - sizeof(__be64); - u32 raw_size = bpf_prog_digest_scratch_size(fp); + u32 raw_size = bpf_prog_tag_scratch_size(fp); + u32 digest[SHA_DIGEST_WORDS]; u32 ws[SHA_WORKSPACE_WORDS]; u32 i, bsize, psize, blocks; struct bpf_insn *dst; @@ -162,7 +163,7 @@ int bpf_prog_calc_digest(struct bpf_prog *fp) if (!raw) return -ENOMEM; - sha_init(fp->digest); + sha_init(digest); memset(ws, 0, sizeof(ws)); /* We need to take out the map fd for the digest calculation @@ -204,13 +205,14 @@ int bpf_prog_calc_digest(struct bpf_prog *fp) *bits = cpu_to_be64((psize - 1) << 3); while (blocks--) { - sha_transform(fp->digest, todo, ws); + sha_transform(digest, todo, ws); todo += SHA_MESSAGE_BYTES; } - result = (__force __be32 *)fp->digest; + result = (__force __be32 *)digest; for (i = 0; i < SHA_DIGEST_WORDS; i++) - result[i] = cpu_to_be32(fp->digest[i]); + result[i] = cpu_to_be32(digest[i]); + memcpy(fp->tag, result, sizeof(fp->tag)); vfree(raw); return 0; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index e89acea22ecf..1d6b29e4e2c3 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -688,17 +688,17 @@ static int bpf_prog_release(struct inode *inode, struct file *filp) static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_prog *prog = filp->private_data; - char prog_digest[sizeof(prog->digest) * 2 + 1] = { }; + char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; - bin2hex(prog_digest, prog->digest, sizeof(prog->digest)); + bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); seq_printf(m, "prog_type:\t%u\n" "prog_jited:\t%u\n" - "prog_digest:\t%s\n" + "prog_tag:\t%s\n" "memlock:\t%llu\n", prog->type, prog->jited, - prog_digest, + prog_tag, prog->pages * 1ULL << PAGE_SHIFT); } #endif diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 83ed2f8f6f22..cdc43b899f28 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2936,7 +2936,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) int insn_cnt = env->prog->len; int i, j, err; - err = bpf_prog_calc_digest(env->prog); + err = bpf_prog_calc_tag(env->prog); if (err) return err; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 1c60317f0121..520baa41cba3 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -123,12 +123,11 @@ static int tcf_bpf_dump_ebpf_info(const struct tcf_bpf *prog, nla_put_string(skb, TCA_ACT_BPF_NAME, prog->bpf_name)) return -EMSGSIZE; - nla = nla_reserve(skb, TCA_ACT_BPF_DIGEST, - sizeof(prog->filter->digest)); + nla = nla_reserve(skb, TCA_ACT_BPF_TAG, sizeof(prog->filter->tag)); if (nla == NULL) return -EMSGSIZE; - memcpy(nla_data(nla), prog->filter->digest, nla_len(nla)); + memcpy(nla_data(nla), prog->filter->tag, nla_len(nla)); return 0; } diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index adc776048d1a..d9c97018317d 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -555,11 +555,11 @@ static int cls_bpf_dump_ebpf_info(const struct cls_bpf_prog *prog, nla_put_string(skb, TCA_BPF_NAME, prog->bpf_name)) return -EMSGSIZE; - nla = nla_reserve(skb, TCA_BPF_DIGEST, sizeof(prog->filter->digest)); + nla = nla_reserve(skb, TCA_BPF_TAG, sizeof(prog->filter->tag)); if (nla == NULL) return -EMSGSIZE; - memcpy(nla_data(nla), prog->filter->digest, nla_len(nla)); + memcpy(nla_data(nla), prog->filter->tag, nla_len(nla)); return 0; } -- cgit v1.2.3