diff options
Diffstat (limited to 'include/net')
42 files changed, 1715 insertions, 100 deletions
diff --git a/include/net/9p/transport.h b/include/net/9p/transport.h index d9fa68f26c41..2a25dec30211 100644 --- a/include/net/9p/transport.h +++ b/include/net/9p/transport.h @@ -34,7 +34,6 @@ * @list: used to maintain a list of currently available transports * @name: the human-readable name of the transport * @maxsize: transport provided maximum packet size - * @pref: Preferences of this transport * @def: set if this transport should be considered the default * @create: member function to create a new connection on this transport * @close: member function to discard a connection on this transport diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 428277869400..0d87674fb775 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -103,14 +103,14 @@ struct vsock_transport { int (*dgram_dequeue)(struct kiocb *kiocb, struct vsock_sock *vsk, struct msghdr *msg, size_t len, int flags); int (*dgram_enqueue)(struct vsock_sock *, struct sockaddr_vm *, - struct iovec *, size_t len); + struct msghdr *, size_t len); bool (*dgram_allow)(u32 cid, u32 port); /* STREAM. */ /* TODO: stream_bind() */ - ssize_t (*stream_dequeue)(struct vsock_sock *, struct iovec *, + ssize_t (*stream_dequeue)(struct vsock_sock *, struct msghdr *, size_t len, int flags); - ssize_t (*stream_enqueue)(struct vsock_sock *, struct iovec *, + ssize_t (*stream_enqueue)(struct vsock_sock *, struct msghdr *, size_t len); s64 (*stream_has_data)(struct vsock_sock *); s64 (*stream_has_space)(struct vsock_sock *); diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h new file mode 100644 index 000000000000..e01d903633ef --- /dev/null +++ b/include/net/bond_3ad.h @@ -0,0 +1,283 @@ +/* + * Copyright(c) 1999 - 2004 Intel Corporation. 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. + * + * 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, write to the Free Software Foundation, Inc., 59 + * Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * The full GNU General Public License is included in this distribution in the + * file called LICENSE. + * + */ + +#ifndef _NET_BOND_3AD_H +#define _NET_BOND_3AD_H + +#include <asm/byteorder.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/if_ether.h> + +/* General definitions */ +#define PKT_TYPE_LACPDU cpu_to_be16(ETH_P_SLOW) +#define AD_TIMER_INTERVAL 100 /*msec*/ + +#define MULTICAST_LACPDU_ADDR {0x01, 0x80, 0xC2, 0x00, 0x00, 0x02} + +#define AD_LACP_SLOW 0 +#define AD_LACP_FAST 1 + +typedef struct mac_addr { + u8 mac_addr_value[ETH_ALEN]; +} __packed mac_addr_t; + +enum { + BOND_AD_STABLE = 0, + BOND_AD_BANDWIDTH = 1, + BOND_AD_COUNT = 2, +}; + +/* rx machine states(43.4.11 in the 802.3ad standard) */ +typedef enum { + AD_RX_DUMMY, + AD_RX_INITIALIZE, /* rx Machine */ + AD_RX_PORT_DISABLED, /* rx Machine */ + AD_RX_LACP_DISABLED, /* rx Machine */ + AD_RX_EXPIRED, /* rx Machine */ + AD_RX_DEFAULTED, /* rx Machine */ + AD_RX_CURRENT /* rx Machine */ +} rx_states_t; + +/* periodic machine states(43.4.12 in the 802.3ad standard) */ +typedef enum { + AD_PERIODIC_DUMMY, + AD_NO_PERIODIC, /* periodic machine */ + AD_FAST_PERIODIC, /* periodic machine */ + AD_SLOW_PERIODIC, /* periodic machine */ + AD_PERIODIC_TX /* periodic machine */ +} periodic_states_t; + +/* mux machine states(43.4.13 in the 802.3ad standard) */ +typedef enum { + AD_MUX_DUMMY, + AD_MUX_DETACHED, /* mux machine */ + AD_MUX_WAITING, /* mux machine */ + AD_MUX_ATTACHED, /* mux machine */ + AD_MUX_COLLECTING_DISTRIBUTING /* mux machine */ +} mux_states_t; + +/* tx machine states(43.4.15 in the 802.3ad standard) */ +typedef enum { + AD_TX_DUMMY, + AD_TRANSMIT /* tx Machine */ +} tx_states_t; + +/* rx indication types */ +typedef enum { + AD_TYPE_LACPDU = 1, /* type lacpdu */ + AD_TYPE_MARKER /* type marker */ +} pdu_type_t; + +/* rx marker indication types */ +typedef enum { + AD_MARKER_INFORMATION_SUBTYPE = 1, /* marker imformation subtype */ + AD_MARKER_RESPONSE_SUBTYPE /* marker response subtype */ +} bond_marker_subtype_t; + +/* timers types(43.4.9 in the 802.3ad standard) */ +typedef enum { + AD_CURRENT_WHILE_TIMER, + AD_ACTOR_CHURN_TIMER, + AD_PERIODIC_TIMER, + AD_PARTNER_CHURN_TIMER, + AD_WAIT_WHILE_TIMER +} ad_timers_t; + +#pragma pack(1) + +/* Link Aggregation Control Protocol(LACP) data unit structure(43.4.2.2 in the 802.3ad standard) */ +typedef struct lacpdu { + u8 subtype; /* = LACP(= 0x01) */ + u8 version_number; + u8 tlv_type_actor_info; /* = actor information(type/length/value) */ + u8 actor_information_length; /* = 20 */ + __be16 actor_system_priority; + struct mac_addr actor_system; + __be16 actor_key; + __be16 actor_port_priority; + __be16 actor_port; + u8 actor_state; + u8 reserved_3_1[3]; /* = 0 */ + u8 tlv_type_partner_info; /* = partner information */ + u8 partner_information_length; /* = 20 */ + __be16 partner_system_priority; + struct mac_addr partner_system; + __be16 partner_key; + __be16 partner_port_priority; + __be16 partner_port; + u8 partner_state; + u8 reserved_3_2[3]; /* = 0 */ + u8 tlv_type_collector_info; /* = collector information */ + u8 collector_information_length;/* = 16 */ + __be16 collector_max_delay; + u8 reserved_12[12]; + u8 tlv_type_terminator; /* = terminator */ + u8 terminator_length; /* = 0 */ + u8 reserved_50[50]; /* = 0 */ +} __packed lacpdu_t; + +typedef struct lacpdu_header { + struct ethhdr hdr; + struct lacpdu lacpdu; +} __packed lacpdu_header_t; + +/* Marker Protocol Data Unit(PDU) structure(43.5.3.2 in the 802.3ad standard) */ +typedef struct bond_marker { + u8 subtype; /* = 0x02 (marker PDU) */ + u8 version_number; /* = 0x01 */ + u8 tlv_type; /* = 0x01 (marker information) */ + /* = 0x02 (marker response information) */ + u8 marker_length; /* = 0x16 */ + u16 requester_port; /* The number assigned to the port by the requester */ + struct mac_addr requester_system; /* The requester's system id */ + u32 requester_transaction_id; /* The transaction id allocated by the requester, */ + u16 pad; /* = 0 */ + u8 tlv_type_terminator; /* = 0x00 */ + u8 terminator_length; /* = 0x00 */ + u8 reserved_90[90]; /* = 0 */ +} __packed bond_marker_t; + +typedef struct bond_marker_header { + struct ethhdr hdr; + struct bond_marker marker; +} __packed bond_marker_header_t; + +#pragma pack() + +struct slave; +struct bonding; +struct ad_info; +struct port; + +#ifdef __ia64__ +#pragma pack(8) +#endif + +/* aggregator structure(43.4.5 in the 802.3ad standard) */ +typedef struct aggregator { + struct mac_addr aggregator_mac_address; + u16 aggregator_identifier; + bool is_individual; + u16 actor_admin_aggregator_key; + u16 actor_oper_aggregator_key; + struct mac_addr partner_system; + u16 partner_system_priority; + u16 partner_oper_aggregator_key; + u16 receive_state; /* BOOLEAN */ + u16 transmit_state; /* BOOLEAN */ + struct port *lag_ports; + /* ****** PRIVATE PARAMETERS ****** */ + struct slave *slave; /* pointer to the bond slave that this aggregator belongs to */ + u16 is_active; /* BOOLEAN. Indicates if this aggregator is active */ + u16 num_of_ports; +} aggregator_t; + +struct port_params { + struct mac_addr system; + u16 system_priority; + u16 key; + u16 port_number; + u16 port_priority; + u16 port_state; +}; + +/* port structure(43.4.6 in the 802.3ad standard) */ +typedef struct port { + u16 actor_port_number; + u16 actor_port_priority; + struct mac_addr actor_system; /* This parameter is added here although it is not specified in the standard, just for simplification */ + u16 actor_system_priority; /* This parameter is added here although it is not specified in the standard, just for simplification */ + u16 actor_port_aggregator_identifier; + bool ntt; + u16 actor_admin_port_key; + u16 actor_oper_port_key; + u8 actor_admin_port_state; + u8 actor_oper_port_state; + + struct port_params partner_admin; + struct port_params partner_oper; + + bool is_enabled; + + /* ****** PRIVATE PARAMETERS ****** */ + u16 sm_vars; /* all state machines variables for this port */ + rx_states_t sm_rx_state; /* state machine rx state */ + u16 sm_rx_timer_counter; /* state machine rx timer counter */ + periodic_states_t sm_periodic_state; /* state machine periodic state */ + u16 sm_periodic_timer_counter; /* state machine periodic timer counter */ + mux_states_t sm_mux_state; /* state machine mux state */ + u16 sm_mux_timer_counter; /* state machine mux timer counter */ + tx_states_t sm_tx_state; /* state machine tx state */ + u16 sm_tx_timer_counter; /* state machine tx timer counter(allways on - enter to transmit state 3 time per second) */ + struct slave *slave; /* pointer to the bond slave that this port belongs to */ + struct aggregator *aggregator; /* pointer to an aggregator that this port related to */ + struct port *next_port_in_aggregator; /* Next port on the linked list of the parent aggregator */ + u32 transaction_id; /* continuous number for identification of Marker PDU's; */ + struct lacpdu lacpdu; /* the lacpdu that will be sent for this port */ +} port_t; + +/* system structure */ +struct ad_system { + u16 sys_priority; + struct mac_addr sys_mac_addr; +}; + +#ifdef __ia64__ +#pragma pack() +#endif + +/* ========== AD Exported structures to the main bonding code ========== */ +#define BOND_AD_INFO(bond) ((bond)->ad_info) +#define SLAVE_AD_INFO(slave) ((slave)->ad_info) + +struct ad_bond_info { + struct ad_system system; /* 802.3ad system structure */ + u32 agg_select_timer; /* Timer to select aggregator after all adapter's hand shakes */ + u16 aggregator_identifier; +}; + +struct ad_slave_info { + struct aggregator aggregator; /* 802.3ad aggregator structure */ + struct port port; /* 802.3ad port structure */ + u16 id; +}; + +/* ========== AD Exported functions to the main bonding code ========== */ +void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution); +void bond_3ad_bind_slave(struct slave *slave); +void bond_3ad_unbind_slave(struct slave *slave); +void bond_3ad_state_machine_handler(struct work_struct *); +void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout); +void bond_3ad_adapter_speed_changed(struct slave *slave); +void bond_3ad_adapter_duplex_changed(struct slave *slave); +void bond_3ad_handle_link_change(struct slave *slave, char link); +int bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info); +int __bond_3ad_get_active_agg_info(struct bonding *bond, + struct ad_info *ad_info); +int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev); +int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, + struct slave *slave); +int bond_3ad_set_carrier(struct bonding *bond); +void bond_3ad_update_lacp_rate(struct bonding *bond); +#endif /* _NET_BOND_3AD_H */ + diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h new file mode 100644 index 000000000000..313a8d3b3069 --- /dev/null +++ b/include/net/bond_alb.h @@ -0,0 +1,181 @@ +/* + * Copyright(c) 1999 - 2004 Intel Corporation. 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. + * + * 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 <http://www.gnu.org/licenses/>. + * + * The full GNU General Public License is included in this distribution in the + * file called LICENSE. + * + */ + +#ifndef _NET_BOND_ALB_H +#define _NET_BOND_ALB_H + +#include <linux/if_ether.h> + +struct bonding; +struct slave; + +#define BOND_ALB_INFO(bond) ((bond)->alb_info) +#define SLAVE_TLB_INFO(slave) ((slave)->tlb_info) + +#define ALB_TIMER_TICKS_PER_SEC 10 /* should be a divisor of HZ */ +#define BOND_TLB_REBALANCE_INTERVAL 10 /* In seconds, periodic re-balancing. + * Used for division - never set + * to zero !!! + */ +#define BOND_ALB_DEFAULT_LP_INTERVAL 1 +#define BOND_ALB_LP_INTERVAL(bond) (bond->params.lp_interval) /* In seconds, periodic send of + * learning packets to the switch + */ + +#define BOND_TLB_REBALANCE_TICKS (BOND_TLB_REBALANCE_INTERVAL \ + * ALB_TIMER_TICKS_PER_SEC) + +#define BOND_ALB_LP_TICKS(bond) (BOND_ALB_LP_INTERVAL(bond) \ + * ALB_TIMER_TICKS_PER_SEC) + +#define TLB_HASH_TABLE_SIZE 256 /* The size of the clients hash table. + * Note that this value MUST NOT be smaller + * because the key hash table is BYTE wide ! + */ + + +#define TLB_NULL_INDEX 0xffffffff + +/* rlb defs */ +#define RLB_HASH_TABLE_SIZE 256 +#define RLB_NULL_INDEX 0xffffffff +#define RLB_UPDATE_DELAY (2*ALB_TIMER_TICKS_PER_SEC) /* 2 seconds */ +#define RLB_ARP_BURST_SIZE 2 +#define RLB_UPDATE_RETRY 3 /* 3-ticks - must be smaller than the rlb + * rebalance interval (5 min). + */ +/* RLB_PROMISC_TIMEOUT = 10 sec equals the time that the current slave is + * promiscuous after failover + */ +#define RLB_PROMISC_TIMEOUT (10*ALB_TIMER_TICKS_PER_SEC) + + +struct tlb_client_info { + struct slave *tx_slave; /* A pointer to slave used for transmiting + * packets to a Client that the Hash function + * gave this entry index. + */ + u32 tx_bytes; /* Each Client accumulates the BytesTx that + * were transmitted to it, and after each + * CallBack the LoadHistory is divided + * by the balance interval + */ + u32 load_history; /* This field contains the amount of Bytes + * that were transmitted to this client by + * the server on the previous balance + * interval in Bps. + */ + u32 next; /* The next Hash table entry index, assigned + * to use the same adapter for transmit. + */ + u32 prev; /* The previous Hash table entry index, + * assigned to use the same + */ +}; + +/* ------------------------------------------------------------------------- + * struct rlb_client_info contains all info related to a specific rx client + * connection. This is the Clients Hash Table entry struct. + * Note that this is not a proper hash table; if a new client's IP address + * hash collides with an existing client entry, the old entry is replaced. + * + * There is a linked list (linked by the used_next and used_prev members) + * linking all the used entries of the hash table. This allows updating + * all the clients without walking over all the unused elements of the table. + * + * There are also linked lists of entries with identical hash(ip_src). These + * allow cleaning up the table from ip_src<->mac_src associations that have + * become outdated and would cause sending out invalid ARP updates to the + * network. These are linked by the (src_next and src_prev members). + * ------------------------------------------------------------------------- + */ +struct rlb_client_info { + __be32 ip_src; /* the server IP address */ + __be32 ip_dst; /* the client IP address */ + u8 mac_src[ETH_ALEN]; /* the server MAC address */ + u8 mac_dst[ETH_ALEN]; /* the client MAC address */ + + /* list of used hash table entries, starting at rx_hashtbl_used_head */ + u32 used_next; + u32 used_prev; + + /* ip_src based hashing */ + u32 src_next; /* next entry with same hash(ip_src) */ + u32 src_prev; /* prev entry with same hash(ip_src) */ + u32 src_first; /* first entry with hash(ip_src) == this entry's index */ + + u8 assigned; /* checking whether this entry is assigned */ + u8 ntt; /* flag - need to transmit client info */ + struct slave *slave; /* the slave assigned to this client */ + unsigned short vlan_id; /* VLAN tag associated with IP address */ +}; + +struct tlb_slave_info { + u32 head; /* Index to the head of the bi-directional clients + * hash table entries list. The entries in the list + * are the entries that were assigned to use this + * slave for transmit. + */ + u32 load; /* Each slave sums the loadHistory of all clients + * assigned to it + */ +}; + +struct alb_bond_info { + struct tlb_client_info *tx_hashtbl; /* Dynamically allocated */ + u32 unbalanced_load; + int tx_rebalance_counter; + int lp_counter; + /* -------- rlb parameters -------- */ + int rlb_enabled; + struct rlb_client_info *rx_hashtbl; /* Receive hash table */ + u32 rx_hashtbl_used_head; + u8 rx_ntt; /* flag - need to transmit + * to all rx clients + */ + struct slave *rx_slave;/* last slave to xmit from */ + u8 primary_is_promisc; /* boolean */ + u32 rlb_promisc_timeout_counter;/* counts primary + * promiscuity time + */ + u32 rlb_update_delay_counter; + u32 rlb_update_retry_counter;/* counter of retries + * of client update + */ + u8 rlb_rebalance; /* flag - indicates that the + * rx traffic should be + * rebalanced + */ +}; + +int bond_alb_initialize(struct bonding *bond, int rlb_enabled); +void bond_alb_deinitialize(struct bonding *bond); +int bond_alb_init_slave(struct bonding *bond, struct slave *slave); +void bond_alb_deinit_slave(struct bonding *bond, struct slave *slave); +void bond_alb_handle_link_change(struct bonding *bond, struct slave *slave, char link); +void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave); +int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev); +int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev); +void bond_alb_monitor(struct work_struct *); +int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr); +void bond_alb_clear_vlan(struct bonding *bond, unsigned short vlan_id); +#endif /* _NET_BOND_ALB_H */ + diff --git a/include/net/bond_options.h b/include/net/bond_options.h new file mode 100644 index 000000000000..ea6546d2c946 --- /dev/null +++ b/include/net/bond_options.h @@ -0,0 +1,130 @@ +/* + * drivers/net/bond/bond_options.h - bonding options + * Copyright (c) 2013 Nikolay Aleksandrov <nikolay@redhat.com> + * + * 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_BOND_OPTIONS_H +#define _NET_BOND_OPTIONS_H + +#define BOND_OPT_MAX_NAMELEN 32 +#define BOND_OPT_VALID(opt) ((opt) < BOND_OPT_LAST) +#define BOND_MODE_ALL_EX(x) (~(x)) + +/* Option flags: + * BOND_OPTFLAG_NOSLAVES - check if the bond device is empty before setting + * BOND_OPTFLAG_IFDOWN - check if the bond device is down before setting + * BOND_OPTFLAG_RAWVAL - the option parses the value itself + */ +enum { + BOND_OPTFLAG_NOSLAVES = BIT(0), + BOND_OPTFLAG_IFDOWN = BIT(1), + BOND_OPTFLAG_RAWVAL = BIT(2) +}; + +/* Value type flags: + * BOND_VALFLAG_DEFAULT - mark the value as default + * BOND_VALFLAG_(MIN|MAX) - mark the value as min/max + */ +enum { + BOND_VALFLAG_DEFAULT = BIT(0), + BOND_VALFLAG_MIN = BIT(1), + BOND_VALFLAG_MAX = BIT(2) +}; + +/* Option IDs, their bit positions correspond to their IDs */ +enum { + BOND_OPT_MODE, + BOND_OPT_PACKETS_PER_SLAVE, + BOND_OPT_XMIT_HASH, + BOND_OPT_ARP_VALIDATE, + BOND_OPT_ARP_ALL_TARGETS, + BOND_OPT_FAIL_OVER_MAC, + BOND_OPT_ARP_INTERVAL, + BOND_OPT_ARP_TARGETS, + BOND_OPT_DOWNDELAY, + BOND_OPT_UPDELAY, + BOND_OPT_LACP_RATE, + BOND_OPT_MINLINKS, + BOND_OPT_AD_SELECT, + BOND_OPT_NUM_PEER_NOTIF, + BOND_OPT_MIIMON, + BOND_OPT_PRIMARY, + BOND_OPT_PRIMARY_RESELECT, + BOND_OPT_USE_CARRIER, + BOND_OPT_ACTIVE_SLAVE, + BOND_OPT_QUEUE_ID, + BOND_OPT_ALL_SLAVES_ACTIVE, + BOND_OPT_RESEND_IGMP, + BOND_OPT_LP_INTERVAL, + BOND_OPT_SLAVES, + BOND_OPT_TLB_DYNAMIC_LB, + BOND_OPT_LAST +}; + +/* This structure is used for storing option values and for passing option + * values when changing an option. The logic when used as an arg is as follows: + * - if string != NULL -> parse it, if the opt is RAW type then return it, else + * return the parse result + * - if string == NULL -> parse value + */ +struct bond_opt_value { + char *string; + u64 value; + u32 flags; +}; + +struct bonding; + +struct bond_option { + int id; + const char *name; + const char *desc; + u32 flags; + + /* unsuppmodes is used to denote modes in which the option isn't + * supported. + */ + unsigned long unsuppmodes; + /* supported values which this option can have, can be a subset of + * BOND_OPTVAL_RANGE's value range + */ + const struct bond_opt_value *values; + + int (*set)(struct bonding *bond, const struct bond_opt_value *val); +}; + +int __bond_opt_set(struct bonding *bond, unsigned int option, + struct bond_opt_value *val); +int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf); + +const struct bond_opt_value *bond_opt_parse(const struct bond_option *opt, + struct bond_opt_value *val); +const struct bond_option *bond_opt_get(unsigned int option); +const struct bond_option *bond_opt_get_by_name(const char *name); +const struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val); + +/* This helper is used to initialize a bond_opt_value structure for parameter + * passing. There should be either a valid string or value, but not both. + * When value is ULLONG_MAX then string will be used. + */ +static inline void __bond_opt_init(struct bond_opt_value *optval, + char *string, u64 value) +{ + memset(optval, 0, sizeof(*optval)); + optval->value = ULLONG_MAX; + if (value == ULLONG_MAX) + optval->string = string; + else + optval->value = value; +} +#define bond_opt_initval(optval, value) __bond_opt_init(optval, NULL, value) +#define bond_opt_initstr(optval, str) __bond_opt_init(optval, str, ULLONG_MAX) + +void bond_option_arp_ip_targets_clear(struct bonding *bond); + +#endif /* _NET_BOND_OPTIONS_H */ diff --git a/include/net/bonding.h b/include/net/bonding.h new file mode 100644 index 000000000000..983a94b86b95 --- /dev/null +++ b/include/net/bonding.h @@ -0,0 +1,654 @@ +/* + * Bond several ethernet interfaces into a Cisco, running 'Etherchannel'. + * + * Portions are (c) Copyright 1995 Simon "Guru Aleph-Null" Janes + * NCM: Network and Communications Management, Inc. + * + * BUT, I'm the one who modified it for ethernet, so: + * (c) Copyright 1999, Thomas Davis, tadavis@lbl.gov + * + * This software may be used and distributed according to the terms + * of the GNU Public License, incorporated herein by reference. + * + */ + +#ifndef _NET_BONDING_H +#define _NET_BONDING_H + +#include <linux/timer.h> +#include <linux/proc_fs.h> +#include <linux/if_bonding.h> +#include <linux/cpumask.h> +#include <linux/in6.h> +#include <linux/netpoll.h> +#include <linux/inetdevice.h> +#include <linux/etherdevice.h> +#include <linux/reciprocal_div.h> +#include <linux/if_link.h> + +#include <net/bond_3ad.h> +#include <net/bond_alb.h> +#include <net/bond_options.h> + +#define DRV_VERSION "3.7.1" +#define DRV_RELDATE "April 27, 2011" +#define DRV_NAME "bonding" +#define DRV_DESCRIPTION "Ethernet Channel Bonding Driver" + +#define bond_version DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n" + +#define BOND_MAX_ARP_TARGETS 16 + +#define BOND_DEFAULT_MIIMON 100 + +/* + * Less bad way to call ioctl from within the kernel; this needs to be + * done some other way to get the call out of interrupt context. + * Needs "ioctl" variable to be supplied by calling context. + */ +#define IOCTL(dev, arg, cmd) ({ \ + int res = 0; \ + mm_segment_t fs = get_fs(); \ + set_fs(get_ds()); \ + res = ioctl(dev, arg, cmd); \ + set_fs(fs); \ + res; }) + +#define BOND_MODE(bond) ((bond)->params.mode) + +/* slave list primitives */ +#define bond_slave_list(bond) (&(bond)->dev->adj_list.lower) + +#define bond_has_slaves(bond) !list_empty(bond_slave_list(bond)) + +/* IMPORTANT: bond_first/last_slave can return NULL in case of an empty list */ +#define bond_first_slave(bond) \ + (bond_has_slaves(bond) ? \ + netdev_adjacent_get_private(bond_slave_list(bond)->next) : \ + NULL) +#define bond_last_slave(bond) \ + (bond_has_slaves(bond) ? \ + netdev_adjacent_get_private(bond_slave_list(bond)->prev) : \ + NULL) + +/* Caller must have rcu_read_lock */ +#define bond_first_slave_rcu(bond) \ + netdev_lower_get_first_private_rcu(bond->dev) + +#define bond_is_first_slave(bond, pos) (pos == bond_first_slave(bond)) +#define bond_is_last_slave(bond, pos) (pos == bond_last_slave(bond)) + +/** + * bond_for_each_slave - iterate over all slaves + * @bond: the bond holding this list + * @pos: current slave + * @iter: list_head * iterator + * + * Caller must hold RTNL + */ +#define bond_for_each_slave(bond, pos, iter) \ + netdev_for_each_lower_private((bond)->dev, pos, iter) + +/* Caller must have rcu_read_lock */ +#define bond_for_each_slave_rcu(bond, pos, iter) \ + netdev_for_each_lower_private_rcu((bond)->dev, pos, iter) + +#ifdef CONFIG_NET_POLL_CONTROLLER +extern atomic_t netpoll_block_tx; + +static inline void block_netpoll_tx(void) +{ + atomic_inc(&netpoll_block_tx); +} + +static inline void unblock_netpoll_tx(void) +{ + atomic_dec(&netpoll_block_tx); +} + +static inline int is_netpoll_tx_blocked(struct net_device *dev) +{ + if (unlikely(netpoll_tx_running(dev))) + return atomic_read(&netpoll_block_tx); + return 0; +} +#else +#define block_netpoll_tx() +#define unblock_netpoll_tx() +#define is_netpoll_tx_blocked(dev) (0) +#endif + +struct bond_params { + int mode; + int xmit_policy; + int miimon; + u8 num_peer_notif; + int arp_interval; + int arp_validate; + int arp_all_targets; + int use_carrier; + int fail_over_mac; + int updelay; + int downdelay; + int lacp_fast; + unsigned int min_links; + int ad_select; + char primary[IFNAMSIZ]; + int primary_reselect; + __be32 arp_targets[BOND_MAX_ARP_TARGETS]; + int tx_queues; + int all_slaves_active; + int resend_igmp; + int lp_interval; + int packets_per_slave; + int tlb_dynamic_lb; + struct reciprocal_value reciprocal_packets_per_slave; +}; + +struct bond_parm_tbl { + char *modename; + int mode; +}; + +struct slave { + struct net_device *dev; /* first - useful for panic debug */ + struct bonding *bond; /* our master */ + int delay; + /* all three in jiffies */ + unsigned long last_link_up; + unsigned long last_rx; + unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS]; + s8 link; /* one of BOND_LINK_XXXX */ + s8 new_link; + u8 backup:1, /* indicates backup slave. Value corresponds with + BOND_STATE_ACTIVE and BOND_STATE_BACKUP */ + inactive:1, /* indicates inactive slave */ + should_notify:1; /* indicateds whether the state changed */ + u8 duplex; + u32 original_mtu; + u32 link_failure_count; + u32 speed; + u16 queue_id; + u8 perm_hwaddr[ETH_ALEN]; + struct ad_slave_info *ad_info; + struct tlb_slave_info tlb_info; +#ifdef CONFIG_NET_POLL_CONTROLLER + struct netpoll *np; +#endif + struct kobject kobj; + struct rtnl_link_stats64 slave_stats; +}; + +struct bond_up_slave { + unsigned int count; + struct rcu_head rcu; + struct slave *arr[0]; +}; + +/* + * Link pseudo-state only used internally by monitors + */ +#define BOND_LINK_NOCHANGE -1 + +/* + * Here are the locking policies for the two bonding locks: + * Get rcu_read_lock when reading or RTNL when writing slave list. + */ +struct bonding { + struct net_device *dev; /* first - useful for panic debug */ + struct slave __rcu *curr_active_slave; + struct slave __rcu *current_arp_slave; + struct slave __rcu *primary_slave; + struct bond_up_slave __rcu *slave_arr; /* Array of usable slaves */ + bool force_primary; + s32 slave_cnt; /* never change this value outside the attach/detach wrappers */ + int (*recv_probe)(const struct sk_buff *, struct bonding *, + struct slave *); + /* mode_lock is used for mode-specific locking needs, currently used by: + * 3ad mode (4) - protect against running bond_3ad_unbind_slave() and + * bond_3ad_state_machine_handler() concurrently and also + * the access to the state machine shared variables. + * TLB mode (5) - to sync the use and modifications of its hash table + * ALB mode (6) - to sync the use and modifications of its hash table + */ + spinlock_t mode_lock; + u8 send_peer_notif; + u8 igmp_retrans; +#ifdef CONFIG_PROC_FS + struct proc_dir_entry *proc_entry; + char proc_file_name[IFNAMSIZ]; +#endif /* CONFIG_PROC_FS */ + struct list_head bond_list; + u32 rr_tx_counter; + struct ad_bond_info ad_info; + struct alb_bond_info alb_info; + struct bond_params params; + struct workqueue_struct *wq; + struct delayed_work mii_work; + struct delayed_work arp_work; + struct delayed_work alb_work; + struct delayed_work ad_work; + struct delayed_work mcast_work; + struct delayed_work slave_arr_work; +#ifdef CONFIG_DEBUG_FS + /* debugging support via debugfs */ + struct dentry *debug_dir; +#endif /* CONFIG_DEBUG_FS */ + struct rtnl_link_stats64 bond_stats; +}; + +#define bond_slave_get_rcu(dev) \ + ((struct slave *) rcu_dereference(dev->rx_handler_data)) + +#define bond_slave_get_rtnl(dev) \ + ((struct slave *) rtnl_dereference(dev->rx_handler_data)) + +struct bond_vlan_tag { + __be16 vlan_proto; + unsigned short vlan_id; +}; + +/** + * Returns NULL if the net_device does not belong to any of the bond's slaves + * + * Caller must hold bond lock for read + */ +static inline struct slave *bond_get_slave_by_dev(struct bonding *bond, + struct net_device *slave_dev) +{ + return netdev_lower_dev_get_private(bond->dev, slave_dev); +} + +static inline struct bonding *bond_get_bond_by_slave(struct slave *slave) +{ + return slave->bond; +} + +static inline bool bond_should_override_tx_queue(struct bonding *bond) +{ + return BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP || + BOND_MODE(bond) == BOND_MODE_ROUNDROBIN; +} + +static inline bool bond_is_lb(const struct bonding *bond) +{ + return BOND_MODE(bond) == BOND_MODE_TLB || + BOND_MODE(bond) == BOND_MODE_ALB; +} + +static inline bool bond_is_nondyn_tlb(const struct bonding *bond) +{ + return (BOND_MODE(bond) == BOND_MODE_TLB) && + (bond->params.tlb_dynamic_lb == 0); +} + +static inline bool bond_mode_uses_xmit_hash(const struct bonding *bond) +{ + return (BOND_MODE(bond) == BOND_MODE_8023AD || + BOND_MODE(bond) == BOND_MODE_XOR || + bond_is_nondyn_tlb(bond)); +} + +static inline bool bond_mode_uses_arp(int mode) +{ + return mode != BOND_MODE_8023AD && mode != BOND_MODE_TLB && + mode != BOND_MODE_ALB; +} + +static inline bool bond_mode_uses_primary(int mode) +{ + return mode == BOND_MODE_ACTIVEBACKUP || mode == BOND_MODE_TLB || + mode == BOND_MODE_ALB; +} + +static inline bool bond_uses_primary(struct bonding *bond) +{ + return bond_mode_uses_primary(BOND_MODE(bond)); +} + +static inline bool bond_slave_is_up(struct slave *slave) +{ + return netif_running(slave->dev) && netif_carrier_ok(slave->dev); +} + +static inline void bond_set_active_slave(struct slave *slave) +{ + if (slave->backup) { + slave->backup = 0; + rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC); + } +} + +static inline void bond_set_backup_slave(struct slave *slave) +{ + if (!slave->backup) { + slave->backup = 1; + rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC); + } +} + +static inline void bond_set_slave_state(struct slave *slave, + int slave_state, bool notify) +{ + if (slave->backup == slave_state) + return; + + slave->backup = slave_state; + if (notify) { + rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC); + slave->should_notify = 0; + } else { + if (slave->should_notify) + slave->should_notify = 0; + else + slave->should_notify = 1; + } +} + +static inline void bond_slave_state_change(struct bonding *bond) +{ + struct list_head *iter; + struct slave *tmp; + + bond_for_each_slave(bond, tmp, iter) { + if (tmp->link == BOND_LINK_UP) + bond_set_active_slave(tmp); + else if (tmp->link == BOND_LINK_DOWN) + bond_set_backup_slave(tmp); + } +} + +static inline void bond_slave_state_notify(struct bonding *bond) +{ + struct list_head *iter; + struct slave *tmp; + + bond_for_each_slave(bond, tmp, iter) { + if (tmp->should_notify) { + rtmsg_ifinfo(RTM_NEWLINK, tmp->dev, 0, GFP_ATOMIC); + tmp->should_notify = 0; + } + } +} + +static inline int bond_slave_state(struct slave *slave) +{ + return slave->backup; +} + +static inline bool bond_is_active_slave(struct slave *slave) +{ + return !bond_slave_state(slave); +} + +static inline bool bond_slave_can_tx(struct slave *slave) +{ + return bond_slave_is_up(slave) && slave->link == BOND_LINK_UP && + bond_is_active_slave(slave); +} + +#define BOND_PRI_RESELECT_ALWAYS 0 +#define BOND_PRI_RESELECT_BETTER 1 +#define BOND_PRI_RESELECT_FAILURE 2 + +#define BOND_FOM_NONE 0 +#define BOND_FOM_ACTIVE 1 +#define BOND_FOM_FOLLOW 2 + +#define BOND_ARP_TARGETS_ANY 0 +#define BOND_ARP_TARGETS_ALL 1 + +#define BOND_ARP_VALIDATE_NONE 0 +#define BOND_ARP_VALIDATE_ACTIVE (1 << BOND_STATE_ACTIVE) +#define BOND_ARP_VALIDATE_BACKUP (1 << BOND_STATE_BACKUP) +#define BOND_ARP_VALIDATE_ALL (BOND_ARP_VALIDATE_ACTIVE | \ + BOND_ARP_VALIDATE_BACKUP) +#define BOND_ARP_FILTER (BOND_ARP_VALIDATE_ALL + 1) +#define BOND_ARP_FILTER_ACTIVE (BOND_ARP_VALIDATE_ACTIVE | \ + BOND_ARP_FILTER) +#define BOND_ARP_FILTER_BACKUP (BOND_ARP_VALIDATE_BACKUP | \ + BOND_ARP_FILTER) + +#define BOND_SLAVE_NOTIFY_NOW true +#define BOND_SLAVE_NOTIFY_LATER false + +static inline int slave_do_arp_validate(struct bonding *bond, + struct slave *slave) +{ + return bond->params.arp_validate & (1 << bond_slave_state(slave)); +} + +static inline int slave_do_arp_validate_only(struct bonding *bond) +{ + return bond->params.arp_validate & BOND_ARP_FILTER; +} + +static inline int bond_is_ip_target_ok(__be32 addr) +{ + return !ipv4_is_lbcast(addr) && !ipv4_is_zeronet(addr); +} + +/* Get the oldest arp which we've received on this slave for bond's + * arp_targets. + */ +static inline unsigned long slave_oldest_target_arp_rx(struct bonding *bond, + struct slave *slave) +{ + int i = 1; + unsigned long ret = slave->target_last_arp_rx[0]; + + for (; (i < BOND_MAX_ARP_TARGETS) && bond->params.arp_targets[i]; i++) + if (time_before(slave->target_last_arp_rx[i], ret)) + ret = slave->target_last_arp_rx[i]; + + return ret; +} + +static inline unsigned long slave_last_rx(struct bonding *bond, + struct slave *slave) +{ + if (bond->params.arp_all_targets == BOND_ARP_TARGETS_ALL) + return slave_oldest_target_arp_rx(bond, slave); + + return slave->last_rx; +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +static inline void bond_netpoll_send_skb(const struct slave *slave, + struct sk_buff *skb) +{ + struct netpoll *np = slave->np; + + if (np) + netpoll_send_skb(np, skb); +} +#else +static inline void bond_netpoll_send_skb(const struct slave *slave, + struct sk_buff *skb) +{ +} +#endif + +static inline void bond_set_slave_inactive_flags(struct slave *slave, + bool notify) +{ + if (!bond_is_lb(slave->bond)) + bond_set_slave_state(slave, BOND_STATE_BACKUP, notify); + if (!slave->bond->params.all_slaves_active) + slave->inactive = 1; +} + +static inline void bond_set_slave_active_flags(struct slave *slave, + bool notify) +{ + bond_set_slave_state(slave, BOND_STATE_ACTIVE, notify); + slave->inactive = 0; +} + +static inline bool bond_is_slave_inactive(struct slave *slave) +{ + return slave->inactive; +} + +static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local) +{ + struct in_device *in_dev; + __be32 addr = 0; + + rcu_read_lock(); + in_dev = __in_dev_get_rcu(dev); + + if (in_dev) + addr = inet_confirm_addr(dev_net(dev), in_dev, dst, local, + RT_SCOPE_HOST); + rcu_read_unlock(); + return addr; +} + +struct bond_net { + struct net *net; /* Associated network namespace */ + struct list_head dev_list; +#ifdef CONFIG_PROC_FS + struct proc_dir_entry *proc_dir; +#endif + struct class_attribute class_attr_bonding_masters; +}; + +int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); +void bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev); +int bond_create(struct net *net, const char *name); +int bond_create_sysfs(struct bond_net *net); +void bond_destroy_sysfs(struct bond_net *net); +void bond_prepare_sysfs_group(struct bonding *bond); +int bond_sysfs_slave_add(struct slave *slave); +void bond_sysfs_slave_del(struct slave *slave); +int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev); +int bond_release(struct net_device *bond_dev, struct net_device *slave_dev); +u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb); +void bond_select_active_slave(struct bonding *bond); +void bond_change_active_slave(struct bonding *bond, struct slave *new_active); +void bond_create_debugfs(void); +void bond_destroy_debugfs(void); +void bond_debug_register(struct bonding *bond); +void bond_debug_unregister(struct bonding *bond); +void bond_debug_reregister(struct bonding *bond); +const char *bond_mode_name(int mode); +void bond_setup(struct net_device *bond_dev); +unsigned int bond_get_num_tx_queues(void); +int bond_netlink_init(void); +void bond_netlink_fini(void); +struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond); +const char *bond_slave_link_status(s8 link); +struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev, + struct net_device *end_dev, + int level); +int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave); +void bond_slave_arr_work_rearm(struct bonding *bond, unsigned long delay); + +#ifdef CONFIG_PROC_FS +void bond_create_proc_entry(struct bonding *bond); +void bond_remove_proc_entry(struct bonding *bond); +void bond_create_proc_dir(struct bond_net *bn); +void bond_destroy_proc_dir(struct bond_net *bn); +#else +static inline void bond_create_proc_entry(struct bonding *bond) +{ +} + +static inline void bond_remove_proc_entry(struct bonding *bond) +{ +} + +static inline void bond_create_proc_dir(struct bond_net *bn) +{ +} + +static inline void bond_destroy_proc_dir(struct bond_net *bn) +{ +} +#endif + +static inline struct slave *bond_slave_has_mac(struct bonding *bond, + const u8 *mac) +{ + struct list_head *iter; + struct slave *tmp; + + bond_for_each_slave(bond, tmp, iter) + if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) + return tmp; + + return NULL; +} + +/* Caller must hold rcu_read_lock() for read */ +static inline struct slave *bond_slave_has_mac_rcu(struct bonding *bond, + const u8 *mac) +{ + struct list_head *iter; + struct slave *tmp; + + bond_for_each_slave_rcu(bond, tmp, iter) + if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) + return tmp; + + return NULL; +} + +/* Caller must hold rcu_read_lock() for read */ +static inline bool bond_slave_has_mac_rx(struct bonding *bond, const u8 *mac) +{ + struct list_head *iter; + struct slave *tmp; + struct netdev_hw_addr *ha; + + bond_for_each_slave_rcu(bond, tmp, iter) + if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) + return true; + + if (netdev_uc_empty(bond->dev)) + return false; + + netdev_for_each_uc_addr(ha, bond->dev) + if (ether_addr_equal_64bits(mac, ha->addr)) + return true; + + return false; +} + +/* Check if the ip is present in arp ip list, or first free slot if ip == 0 + * Returns -1 if not found, index if found + */ +static inline int bond_get_targets_ip(__be32 *targets, __be32 ip) +{ + int i; + + for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) + if (targets[i] == ip) + return i; + else if (targets[i] == 0) + break; + + return -1; +} + +/* exported from bond_main.c */ +extern int bond_net_id; +extern const struct bond_parm_tbl bond_lacp_tbl[]; +extern const struct bond_parm_tbl xmit_hashtype_tbl[]; +extern const struct bond_parm_tbl arp_validate_tbl[]; +extern const struct bond_parm_tbl arp_all_targets_tbl[]; +extern const struct bond_parm_tbl fail_over_mac_tbl[]; +extern const struct bond_parm_tbl pri_reselect_tbl[]; +extern struct bond_parm_tbl ad_select_tbl[]; + +/* exported from bond_netlink.c */ +extern struct rtnl_link_ops bond_link_ops; + +static inline void bond_tx_drop(struct net_device *dev, struct sk_buff *skb) +{ + atomic_long_inc(&dev->tx_dropped); + dev_kfree_skb_any(skb); +} + +#endif /* _NET_BONDING_H */ diff --git a/include/net/checksum.h b/include/net/checksum.h index 6465bae80a4f..e339a9513e29 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -151,4 +151,20 @@ static inline void inet_proto_csum_replace2(__sum16 *sum, struct sk_buff *skb, (__force __be32)to, pseudohdr); } +static inline __wsum remcsum_adjust(void *ptr, __wsum csum, + int start, int offset) +{ + __sum16 *psum = (__sum16 *)(ptr + offset); + __wsum delta; + + /* Subtract out checksum up to start */ + csum = csum_sub(csum, csum_partial(ptr, start, 0)); + + /* Set derived checksum in packet */ + delta = csum_sub(csum_fold(csum), *psum); + *psum = csum_fold(csum); + + return delta; +} + #endif diff --git a/include/net/compat.h b/include/net/compat.h index 3b603b199c01..42a9c8431177 100644 --- a/include/net/compat.h +++ b/include/net/compat.h @@ -40,9 +40,8 @@ int compat_sock_get_timestampns(struct sock *, struct timespec __user *); #define compat_mmsghdr mmsghdr #endif /* defined(CONFIG_COMPAT) */ -int get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *); -int verify_compat_iovec(struct msghdr *, struct iovec *, - struct sockaddr_storage *, int); +ssize_t get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *, + struct sockaddr __user **, struct iovec **); asmlinkage long compat_sys_sendmsg(int, struct compat_msghdr __user *, unsigned int); asmlinkage long compat_sys_sendmmsg(int, struct compat_mmsghdr __user *, diff --git a/include/net/dsa.h b/include/net/dsa.h index b76559293535..ed3c34bbb67a 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -38,6 +38,9 @@ struct dsa_chip_data { struct device *host_dev; int sw_addr; + /* set to size of eeprom if supported by the switch */ + int eeprom_len; + /* Device tree node pointer for this specific switch chip * used during switch setup in case additional properties * and resources needs to be used @@ -139,6 +142,14 @@ struct dsa_switch { */ struct device *master_dev; +#ifdef CONFIG_NET_DSA_HWMON + /* + * Hardware monitoring information + */ + char hwmon_name[IFNAMSIZ + 8]; + struct device *hwmon_dev; +#endif + /* * Slave mii_bus and devices for the individual ports. */ @@ -242,6 +253,28 @@ struct dsa_switch_driver { struct ethtool_eee *e); int (*get_eee)(struct dsa_switch *ds, int port, struct ethtool_eee *e); + +#ifdef CONFIG_NET_DSA_HWMON + /* Hardware monitoring */ + int (*get_temp)(struct dsa_switch *ds, int *temp); + int (*get_temp_limit)(struct dsa_switch *ds, int *temp); + int (*set_temp_limit)(struct dsa_switch *ds, int temp); + int (*get_temp_alarm)(struct dsa_switch *ds, bool *alarm); +#endif + + /* EEPROM access */ + int (*get_eeprom_len)(struct dsa_switch *ds); + int (*get_eeprom)(struct dsa_switch *ds, + struct ethtool_eeprom *eeprom, u8 *data); + int (*set_eeprom)(struct dsa_switch *ds, + struct ethtool_eeprom *eeprom, u8 *data); + + /* + * Register access. + */ + int (*get_regs_len)(struct dsa_switch *ds, int port); + void (*get_regs)(struct dsa_switch *ds, int port, + struct ethtool_regs *regs, void *p); }; void register_switch_driver(struct dsa_switch_driver *type); diff --git a/include/net/fou.h b/include/net/fou.h new file mode 100644 index 000000000000..19b8a0c62a98 --- /dev/null +++ b/include/net/fou.h @@ -0,0 +1,19 @@ +#ifndef __NET_FOU_H +#define __NET_FOU_H + +#include <linux/skbuff.h> + +#include <net/flow.h> +#include <net/gue.h> +#include <net/ip_tunnels.h> +#include <net/udp.h> + +size_t fou_encap_hlen(struct ip_tunnel_encap *e); +static size_t gue_encap_hlen(struct ip_tunnel_encap *e); + +int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, + u8 *protocol, struct flowi4 *fl4); +int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, + u8 *protocol, struct flowi4 *fl4); + +#endif diff --git a/include/net/gue.h b/include/net/gue.h index b6c332788084..3f28ec7f1c7f 100644 --- a/include/net/gue.h +++ b/include/net/gue.h @@ -1,23 +1,116 @@ #ifndef __NET_GUE_H #define __NET_GUE_H +/* Definitions for the GUE header, standard and private flags, lengths + * of optional fields are below. + * + * Diagram of GUE header: + * + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * |Ver|C| Hlen | Proto/ctype | Standard flags |P| + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | | + * ~ Fields (optional) ~ + * | | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Private flags (optional, P bit is set) | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | | + * ~ Private fields (optional) ~ + * | | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * C bit indicates contol message when set, data message when unset. + * For a control message, proto/ctype is interpreted as a type of + * control message. For data messages, proto/ctype is the IP protocol + * of the next header. + * + * P bit indicates private flags field is present. The private flags + * may refer to options placed after this field. + */ + struct guehdr { union { struct { #if defined(__LITTLE_ENDIAN_BITFIELD) - __u8 hlen:4, - version:4; + __u8 hlen:5, + control:1, + version:2; #elif defined (__BIG_ENDIAN_BITFIELD) - __u8 version:4, - hlen:4; + __u8 version:2, + control:1, + hlen:5; #else #error "Please fix <asm/byteorder.h>" #endif - __u8 next_hdr; + __u8 proto_ctype; __u16 flags; }; __u32 word; }; }; +/* Standard flags in GUE header */ + +#define GUE_FLAG_PRIV htons(1<<0) /* Private flags are in options */ +#define GUE_LEN_PRIV 4 + +#define GUE_FLAGS_ALL (GUE_FLAG_PRIV) + +/* Private flags in the private option extension */ + +#define GUE_PFLAG_REMCSUM htonl(1 << 31) +#define GUE_PLEN_REMCSUM 4 + +#define GUE_PFLAGS_ALL (GUE_PFLAG_REMCSUM) + +/* Functions to compute options length corresponding to flags. + * If we ever have a lot of flags this can be potentially be + * converted to a more optimized algorithm (table lookup + * for instance). + */ +static inline size_t guehdr_flags_len(__be16 flags) +{ + return ((flags & GUE_FLAG_PRIV) ? GUE_LEN_PRIV : 0); +} + +static inline size_t guehdr_priv_flags_len(__be32 flags) +{ + return 0; +} + +/* Validate standard and private flags. Returns non-zero (meaning invalid) + * if there is an unknown standard or private flags, or the options length for + * the flags exceeds the options length specific in hlen of the GUE header. + */ +static inline int validate_gue_flags(struct guehdr *guehdr, + size_t optlen) +{ + size_t len; + __be32 flags = guehdr->flags; + + if (flags & ~GUE_FLAGS_ALL) + return 1; + + len = guehdr_flags_len(flags); + if (len > optlen) + return 1; + + if (flags & GUE_FLAG_PRIV) { + /* Private flags are last four bytes accounted in + * guehdr_flags_len + */ + flags = *(__be32 *)((void *)&guehdr[1] + len - GUE_LEN_PRIV); + + if (flags & ~GUE_PFLAGS_ALL) + return 1; + + len += guehdr_priv_flags_len(flags); + if (len > optlen) + return 1; + } + + return 0; +} + #endif diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index d1d272843b3b..9201afe083fa 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -99,4 +99,14 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *daddr, const __be16 dport, const int dif); #endif /* IS_ENABLED(CONFIG_IPV6) */ + +#define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif) \ + (((__sk)->sk_portpair == (__ports)) && \ + ((__sk)->sk_family == AF_INET6) && \ + ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr)) && \ + ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr)) && \ + (!(__sk)->sk_bound_dev_if || \ + ((__sk)->sk_bound_dev_if == (__dif))) && \ + net_eq(sock_net(__sk), (__net))) + #endif /* _INET6_HASHTABLES_H */ diff --git a/include/net/inet_common.h b/include/net/inet_common.h index fe7994c48b75..b2828a06a5a6 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -37,6 +37,8 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int inet_ctl_sock_create(struct sock **sk, unsigned short family, unsigned short type, unsigned char protocol, struct net *net); +int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, + int *addr_len); static inline void inet_ctl_sock_destroy(struct sock *sk) { diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index a5593dab6af7..9326c41c2d7f 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -65,7 +65,8 @@ void ip6_tnl_dst_reset(struct ip6_tnl *t); void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst); int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr); -int ip6_tnl_xmit_ctl(struct ip6_tnl *t); +int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, + const struct in6_addr *raddr); __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw); __u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr); diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 5bc6edeb7143..25a59eb388a6 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -117,6 +117,22 @@ struct ip_tunnel_net { struct hlist_head tunnels[IP_TNL_HASH_SIZE]; }; +struct ip_tunnel_encap_ops { + size_t (*encap_hlen)(struct ip_tunnel_encap *e); + int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e, + u8 *protocol, struct flowi4 *fl4); +}; + +#define MAX_IPTUN_ENCAP_OPS 8 + +extern const struct ip_tunnel_encap_ops __rcu * + iptun_encaps[MAX_IPTUN_ENCAP_OPS]; + +int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *op, + unsigned int num); +int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op, + unsigned int num); + #ifdef CONFIG_INET int ip_tunnel_init(struct net_device *dev); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 97f472012438..4292929392b0 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -671,6 +671,8 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr)); } +void ipv6_proxy_select_ident(struct sk_buff *skb); + int ip6_dst_hoplimit(struct dst_entry *dst); static inline int ip6_sk_dst_hoplimit(struct ipv6_pinfo *np, struct flowi6 *fl6, diff --git a/include/net/ipx.h b/include/net/ipx.h index 0143180fecc9..e5cff6811b30 100644 --- a/include/net/ipx.h +++ b/include/net/ipx.h @@ -42,6 +42,9 @@ struct ipxhdr { struct ipx_address ipx_source __packed; }; +/* From af_ipx.c */ +extern int sysctl_ipx_pprop_broadcasting; + static __inline__ struct ipxhdr *ipx_hdr(struct sk_buff *skb) { return (struct ipxhdr *)skb_transport_header(skb); @@ -147,7 +150,7 @@ int ipxrtr_add_route(__be32 network, struct ipx_interface *intrfc, unsigned char *node); void ipxrtr_del_routes(struct ipx_interface *intrfc); int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx, - struct iovec *iov, size_t len, int noblock); + struct msghdr *msg, size_t len, int noblock); int ipxrtr_route_skb(struct sk_buff *skb); struct ipx_route *ipxrtr_lookup(__be32 net); int ipxrtr_ioctl(unsigned int cmd, void __user *arg); diff --git a/include/net/irda/irda.h b/include/net/irda/irda.h index a059465101ff..92c8fb575213 100644 --- a/include/net/irda/irda.h +++ b/include/net/irda/irda.h @@ -55,16 +55,6 @@ typedef __u32 magic_t; #endif #ifdef CONFIG_IRDA_DEBUG - -extern unsigned int irda_debug; - -/* use 0 for production, 1 for verification, >2 for debug */ -#define IRDA_DEBUG_LEVEL 0 - -#define IRDA_DEBUG(n, args...) \ -do { if (irda_debug >= (n)) \ - printk(KERN_DEBUG args); \ -} while (0) #define IRDA_ASSERT(expr, func) \ do { if(!(expr)) { \ printk( "Assertion failed! %s:%s:%d %s\n", \ @@ -72,15 +62,10 @@ do { if(!(expr)) { \ func } } while (0) #define IRDA_ASSERT_LABEL(label) label #else -#define IRDA_DEBUG(n, args...) do { } while (0) #define IRDA_ASSERT(expr, func) do { (void)(expr); } while (0) #define IRDA_ASSERT_LABEL(label) #endif /* CONFIG_IRDA_DEBUG */ -#define IRDA_WARNING(args...) do { if (net_ratelimit()) printk(KERN_WARNING args); } while (0) -#define IRDA_MESSAGE(args...) do { if (net_ratelimit()) printk(KERN_INFO args); } while (0) -#define IRDA_ERROR(args...) do { if (net_ratelimit()) printk(KERN_ERR args); } while (0) - /* * Magic numbers used by Linux-IrDA. Random numbers which must be unique to * give the best protection diff --git a/include/net/irda/irlap.h b/include/net/irda/irlap.h index fb4b76d5d7f1..6f23e820618c 100644 --- a/include/net/irda/irlap.h +++ b/include/net/irda/irlap.h @@ -303,7 +303,7 @@ static inline void irlap_next_state(struct irlap_cb *self, IRLAP_STATE state) if (!self || self->magic != LAP_MAGIC) return; - IRDA_DEBUG(4, "next LAP state = %s\n", irlap_state[state]); + pr_debug("next LAP state = %s\n", irlap_state[state]); */ self->state = state; } diff --git a/include/net/mpls.h b/include/net/mpls.h new file mode 100644 index 000000000000..5b3b5addfb08 --- /dev/null +++ b/include/net/mpls.h @@ -0,0 +1,39 @@ +/* + * Copyright (c) 2014 Nicira, Inc. + * + * 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. + */ + +#ifndef _NET_MPLS_H +#define _NET_MPLS_H 1 + +#include <linux/if_ether.h> +#include <linux/netdevice.h> + +#define MPLS_HLEN 4 + +static inline bool eth_p_mpls(__be16 eth_type) +{ + return eth_type == htons(ETH_P_MPLS_UC) || + eth_type == htons(ETH_P_MPLS_MC); +} + +/* + * For non-MPLS skbs this will correspond to the network header. + * For MPLS skbs it will be before the network_header as the MPLS + * label stack lies between the end of the mac header and the network + * header. That is, for MPLS skbs the end of the mac header + * is the top of the MPLS label stack. + */ +static inline unsigned char *skb_mpls_header(struct sk_buff *skb) +{ + return skb_mac_header(skb) + skb->mac_len; +} +#endif diff --git a/include/net/neighbour.h b/include/net/neighbour.h index f60558d0254c..eb070b3674a1 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -69,7 +69,7 @@ struct neigh_parms { struct net *net; #endif struct net_device *dev; - struct neigh_parms *next; + struct list_head list; int (*neigh_setup)(struct neighbour *); void (*neigh_cleanup)(struct neighbour *); struct neigh_table *tbl; @@ -203,6 +203,7 @@ struct neigh_table { void (*proxy_redo)(struct sk_buff *skb); char *id; struct neigh_parms parms; + struct list_head parms_list; int gc_interval; int gc_thresh1; int gc_thresh2; @@ -219,6 +220,13 @@ struct neigh_table { struct pneigh_entry **phash_buckets; }; +enum { + NEIGH_ARP_TABLE = 0, + NEIGH_ND_TABLE = 1, + NEIGH_DN_TABLE = 2, + NEIGH_NR_TABLES, +}; + static inline int neigh_parms_family(struct neigh_parms *p) { return p->tbl->family; @@ -239,8 +247,8 @@ static inline void *neighbour_priv(const struct neighbour *n) #define NEIGH_UPDATE_F_ISROUTER 0x40000000 #define NEIGH_UPDATE_F_ADMIN 0x80000000 -void neigh_table_init(struct neigh_table *tbl); -int neigh_table_clear(struct neigh_table *tbl); +void neigh_table_init(int index, struct neigh_table *tbl); +int neigh_table_clear(int index, struct neigh_table *tbl); struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, struct net_device *dev); struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, diff --git a/include/net/netfilter/ipv4/nf_reject.h b/include/net/netfilter/ipv4/nf_reject.h index e8427193c777..03e928a55229 100644 --- a/include/net/netfilter/ipv4/nf_reject.h +++ b/include/net/netfilter/ipv4/nf_reject.h @@ -1,6 +1,8 @@ #ifndef _IPV4_NF_REJECT_H #define _IPV4_NF_REJECT_H +#include <linux/skbuff.h> +#include <net/ip.h> #include <net/icmp.h> static inline void nf_send_unreach(struct sk_buff *skb_in, int code) @@ -10,4 +12,12 @@ static inline void nf_send_unreach(struct sk_buff *skb_in, int code) void nf_send_reset(struct sk_buff *oldskb, int hook); +const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, + struct tcphdr *_oth, int hook); +struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb, + const struct sk_buff *oldskb, + __be16 protocol, int ttl); +void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, + const struct tcphdr *oth); + #endif /* _IPV4_NF_REJECT_H */ diff --git a/include/net/netfilter/ipv6/nf_reject.h b/include/net/netfilter/ipv6/nf_reject.h index 48e18810a9be..23216d48abf9 100644 --- a/include/net/netfilter/ipv6/nf_reject.h +++ b/include/net/netfilter/ipv6/nf_reject.h @@ -15,4 +15,14 @@ nf_send_unreach6(struct net *net, struct sk_buff *skb_in, unsigned char code, void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook); +const struct tcphdr *nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb, + struct tcphdr *otcph, + unsigned int *otcplen, int hook); +struct ipv6hdr *nf_reject_ip6hdr_put(struct sk_buff *nskb, + const struct sk_buff *oldskb, + __be16 protocol, int hoplimit); +void nf_reject_ip6_tcphdr_put(struct sk_buff *nskb, + const struct sk_buff *oldskb, + const struct tcphdr *oth, unsigned int otcplen); + #endif /* _IPV6_NF_REJECT_H */ diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index c8a7db605e03..f0daed2b54d1 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -92,12 +92,18 @@ struct nf_conn { /* Have we seen traffic both ways yet? (bitset) */ unsigned long status; - /* If we were expected by an expectation, this will be it */ - struct nf_conn *master; - /* Timer function; drops refcnt when it goes off. */ struct timer_list timeout; +#ifdef CONFIG_NET_NS + struct net *ct_net; +#endif + /* all members below initialized via memset */ + u8 __nfct_init_offset[0]; + + /* If we were expected by an expectation, this will be it */ + struct nf_conn *master; + #if defined(CONFIG_NF_CONNTRACK_MARK) u_int32_t mark; #endif @@ -108,9 +114,6 @@ struct nf_conn { /* Extensions */ struct nf_ct_ext *ext; -#ifdef CONFIG_NET_NS - struct net *ct_net; -#endif /* Storage reserved for other modules, must be the last member */ union nf_conntrack_proto proto; diff --git a/include/net/netfilter/nf_nat_redirect.h b/include/net/netfilter/nf_nat_redirect.h new file mode 100644 index 000000000000..73b729543309 --- /dev/null +++ b/include/net/netfilter/nf_nat_redirect.h @@ -0,0 +1,12 @@ +#ifndef _NF_NAT_REDIRECT_H_ +#define _NF_NAT_REDIRECT_H_ + +unsigned int +nf_nat_redirect_ipv4(struct sk_buff *skb, + const struct nf_nat_ipv4_multi_range_compat *mr, + unsigned int hooknum); +unsigned int +nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range *range, + unsigned int hooknum); + +#endif /* _NF_NAT_REDIRECT_H_ */ diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 3d7292392fac..3ae969e3acf0 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -396,14 +396,12 @@ struct nft_rule { /** * struct nft_trans - nf_tables object update in transaction * - * @rcu_head: rcu head to defer release of transaction data * @list: used internally * @msg_type: message type * @ctx: transaction context * @data: internal information related to the transaction */ struct nft_trans { - struct rcu_head rcu_head; struct list_head list; int msg_type; struct nft_ctx ctx; @@ -530,6 +528,9 @@ enum nft_chain_type { NFT_CHAIN_T_MAX }; +int nft_chain_validate_dependency(const struct nft_chain *chain, + enum nft_chain_type type); + struct nft_stats { u64 bytes; u64 pkts; diff --git a/include/net/netfilter/nf_tables_bridge.h b/include/net/netfilter/nf_tables_bridge.h new file mode 100644 index 000000000000..511fb79f6dad --- /dev/null +++ b/include/net/netfilter/nf_tables_bridge.h @@ -0,0 +1,7 @@ +#ifndef _NET_NF_TABLES_BRIDGE_H +#define _NET_NF_TABLES_BRIDGE_H + +int nft_bridge_iphdr_validate(struct sk_buff *skb); +int nft_bridge_ip6hdr_validate(struct sk_buff *skb); + +#endif /* _NET_NF_TABLES_BRIDGE_H */ diff --git a/include/net/netfilter/nft_masq.h b/include/net/netfilter/nft_masq.h index c72729f954f4..e2a518b60e19 100644 --- a/include/net/netfilter/nft_masq.h +++ b/include/net/netfilter/nft_masq.h @@ -13,4 +13,7 @@ int nft_masq_init(const struct nft_ctx *ctx, int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr); +int nft_masq_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nft_data **data); + #endif /* _NFT_MASQ_H_ */ diff --git a/include/net/netfilter/nft_redir.h b/include/net/netfilter/nft_redir.h new file mode 100644 index 000000000000..a2d67546afab --- /dev/null +++ b/include/net/netfilter/nft_redir.h @@ -0,0 +1,21 @@ +#ifndef _NFT_REDIR_H_ +#define _NFT_REDIR_H_ + +struct nft_redir { + enum nft_registers sreg_proto_min:8; + enum nft_registers sreg_proto_max:8; + u16 flags; +}; + +extern const struct nla_policy nft_redir_policy[]; + +int nft_redir_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]); + +int nft_redir_dump(struct sk_buff *skb, const struct nft_expr *expr); + +int nft_redir_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nft_data **data); + +#endif /* _NFT_REDIR_H_ */ diff --git a/include/net/netlink.h b/include/net/netlink.h index 7b903e1bdbbb..64158353ecb2 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -1185,4 +1185,14 @@ static inline int nla_validate_nested(const struct nlattr *start, int maxtype, #define nla_for_each_nested(pos, nla, rem) \ nla_for_each_attr(pos, nla_data(nla), nla_len(nla), rem) +/** + * nla_is_last - Test if attribute is last in stream + * @nla: attribute to test + * @rem: bytes remaining in stream + */ +static inline bool nla_is_last(const struct nlattr *nla, int rem) +{ + return nla->nla_len == rem; +} + #endif diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 9da798256f0e..730d82ad6ee5 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -50,8 +50,8 @@ struct netns_xfrm { struct list_head policy_all; struct hlist_head *policy_byidx; unsigned int policy_idx_hmask; - struct hlist_head policy_inexact[XFRM_POLICY_MAX * 2]; - struct xfrm_policy_hash policy_bydst[XFRM_POLICY_MAX * 2]; + struct hlist_head policy_inexact[XFRM_POLICY_MAX]; + struct xfrm_policy_hash policy_bydst[XFRM_POLICY_MAX]; unsigned int policy_count[XFRM_POLICY_MAX * 2]; struct work_struct policy_hash_work; struct xfrm_policy_hthresh policy_hthresh; diff --git a/include/net/ping.h b/include/net/ping.h index 026479b61a2d..f074060bc5de 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -82,7 +82,7 @@ int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len); int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); -void ping_rcv(struct sk_buff *skb); +bool ping_rcv(struct sk_buff *skb); #ifdef CONFIG_PROC_FS struct ping_seq_afinfo { diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index d17ed6fb2f70..3d282cbb66bf 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -219,7 +219,6 @@ struct tcf_proto_ops { void (*destroy)(struct tcf_proto*); unsigned long (*get)(struct tcf_proto*, u32 handle); - void (*put)(struct tcf_proto*, unsigned long); int (*change)(struct net *net, struct sk_buff *, struct tcf_proto*, unsigned long, u32 handle, struct nlattr **, diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 72a31db47ded..487ef34bbd63 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -219,7 +219,7 @@ struct sctp_chunk *sctp_make_abort_no_data(const struct sctp_association *, const struct sctp_chunk *, __u32 tsn); struct sctp_chunk *sctp_make_abort_user(const struct sctp_association *, - const struct msghdr *, size_t msg_len); + struct msghdr *, size_t msg_len); struct sctp_chunk *sctp_make_abort_violation(const struct sctp_association *, const struct sctp_chunk *, const __u8 *, diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 4ff3f67be62c..2bb2fcf5b11f 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -531,7 +531,7 @@ struct sctp_datamsg { struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *, struct sctp_sndrcvinfo *, - struct msghdr *, int len); + struct iov_iter *); void sctp_datamsg_free(struct sctp_datamsg *); void sctp_datamsg_put(struct sctp_datamsg *); void sctp_chunk_fail(struct sctp_chunk *, int error); @@ -647,8 +647,8 @@ struct sctp_chunk { void sctp_chunk_hold(struct sctp_chunk *); void sctp_chunk_put(struct sctp_chunk *); -int sctp_user_addto_chunk(struct sctp_chunk *chunk, int off, int len, - struct iovec *data); +int sctp_user_addto_chunk(struct sctp_chunk *chunk, int len, + struct iov_iter *from); void sctp_chunk_free(struct sctp_chunk *); void *sctp_addto_chunk(struct sctp_chunk *, int len, const void *data); struct sctp_chunk *sctp_chunkify(struct sk_buff *, @@ -1116,7 +1116,6 @@ int sctp_raw_to_bind_addrs(struct sctp_bind_addr *bp, __u8 *raw, int len, sctp_scope_t sctp_scope(const union sctp_addr *); int sctp_in_scope(struct net *net, const union sctp_addr *addr, const sctp_scope_t scope); int sctp_is_any(struct sock *sk, const union sctp_addr *addr); -int sctp_addr_is_valid(const union sctp_addr *addr); int sctp_is_ep_boundall(struct sock *sk); diff --git a/include/net/sock.h b/include/net/sock.h index 7db3db112baa..df9b89bce8ff 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -273,6 +273,7 @@ struct cg_proto; * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting * @sk_rxhash: flow hash received from netif layer + * @sk_incoming_cpu: record cpu processing incoming packets * @sk_txhash: computed flow hash for use on transmit * @sk_filter: socket filtering instructions * @sk_protinfo: private area, net family specific, when not using slab @@ -350,6 +351,12 @@ struct sock { #ifdef CONFIG_RPS __u32 sk_rxhash; #endif + u16 sk_incoming_cpu; + /* 16bit hole + * Warned : sk_incoming_cpu can be set from softirq, + * Do not use this hole without fully understanding possible issues. + */ + __u32 sk_txhash; #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sk_napi_id; @@ -833,6 +840,11 @@ static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) return sk->sk_backlog_rcv(sk, skb); } +static inline void sk_incoming_cpu_update(struct sock *sk) +{ + sk->sk_incoming_cpu = raw_smp_processor_id(); +} + static inline void sock_rps_record_flow_hash(__u32 hash) { #ifdef CONFIG_RPS @@ -1872,29 +1884,6 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, char __user *from, return 0; } -static inline int skb_copy_to_page(struct sock *sk, char __user *from, - struct sk_buff *skb, struct page *page, - int off, int copy) -{ - if (skb->ip_summed == CHECKSUM_NONE) { - int err = 0; - __wsum csum = csum_and_copy_from_user(from, - page_address(page) + off, - copy, 0, &err); - if (err) - return err; - skb->csum = csum_block_add(skb->csum, csum, skb->len); - } else if (copy_from_user(page_address(page) + off, from, copy)) - return -EFAULT; - - skb->len += copy; - skb->data_len += copy; - skb->truesize += copy; - sk->sk_wmem_queued += copy; - sk_mem_charge(sk, copy); - return 0; -} - /** * sk_wmem_alloc_get - returns write allocations * @sk: socket @@ -2276,16 +2265,6 @@ bool sk_ns_capable(const struct sock *sk, bool sk_capable(const struct sock *sk, int cap); bool sk_net_capable(const struct sock *sk, int cap); -/* - * Enable debug/info messages - */ -extern int net_msg_warn; -#define NETDEBUG(fmt, args...) \ - do { if (net_msg_warn) printk(fmt,##args); } while (0) - -#define LIMIT_NETDEBUG(fmt, args...) \ - do { if (net_msg_warn && net_ratelimit()) printk(fmt,##args); } while(0) - extern __u32 sysctl_wmem_max; extern __u32 sysctl_rmem_max; diff --git a/include/net/switchdev.h b/include/net/switchdev.h new file mode 100644 index 000000000000..8a6d1641fd9b --- /dev/null +++ b/include/net/switchdev.h @@ -0,0 +1,37 @@ +/* + * include/net/switchdev.h - Switch device API + * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us> + * + * 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_SWITCHDEV_H_ +#define _LINUX_SWITCHDEV_H_ + +#include <linux/netdevice.h> + +#ifdef CONFIG_NET_SWITCHDEV + +int netdev_switch_parent_id_get(struct net_device *dev, + struct netdev_phys_item_id *psid); +int netdev_switch_port_stp_update(struct net_device *dev, u8 state); + +#else + +static inline int netdev_switch_parent_id_get(struct net_device *dev, + struct netdev_phys_item_id *psid) +{ + return -EOPNOTSUPP; +} + +static inline int netdev_switch_port_stp_update(struct net_device *dev, + u8 state) +{ + return -EOPNOTSUPP; +} + +#endif + +#endif /* _LINUX_SWITCHDEV_H_ */ diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h new file mode 100644 index 000000000000..93b70ade1ff3 --- /dev/null +++ b/include/net/tc_act/tc_vlan.h @@ -0,0 +1,27 @@ +/* + * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us> + * + * 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_VLAN_H +#define __NET_TC_VLAN_H + +#include <net/act_api.h> + +#define VLAN_F_POP 0x1 +#define VLAN_F_PUSH 0x2 + +struct tcf_vlan { + struct tcf_common common; + int tcfv_action; + u16 tcfv_push_vid; + __be16 tcfv_push_proto; +}; +#define to_vlan(a) \ + container_of(a->priv, struct tcf_vlan, common) + +#endif /* __NET_TC_VLAN_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 4062b4f0d121..f50f29faf76f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -55,9 +55,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_HEADER (128 + MAX_HEADER) #define MAX_TCP_OPTION_SPACE 40 -/* +/* * Never offer a window over 32767 without using window scaling. Some - * poor stacks do signed 16bit maths! + * poor stacks do signed 16bit maths! */ #define MAX_TCP_WINDOW 32767U @@ -70,9 +70,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); /* After receiving this amount of duplicate ACKs fast retransmit starts. */ #define TCP_FASTRETRANS_THRESH 3 -/* Maximal reordering. */ -#define TCP_MAX_REORDERING 127 - /* Maximal number of ACKs sent quickly to accelerate slow-start. */ #define TCP_MAX_QUICKACKS 16U @@ -167,7 +164,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); /* * TCP option */ - + #define TCPOPT_NOP 1 /* Padding */ #define TCPOPT_EOL 0 /* End of options */ #define TCPOPT_MSS 2 /* Segment size negotiating */ @@ -252,6 +249,7 @@ extern int sysctl_tcp_abort_on_overflow; extern int sysctl_tcp_max_orphans; extern int sysctl_tcp_fack; extern int sysctl_tcp_reordering; +extern int sysctl_tcp_max_reordering; extern int sysctl_tcp_dsack; extern long sysctl_tcp_mem[3]; extern int sysctl_tcp_wmem[3]; @@ -492,17 +490,16 @@ u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v4_init_sequence(struct sock *sk, const struct sk_buff *skb, __u16 *mss); -#endif - __u32 cookie_init_timestamp(struct request_sock *req); -bool cookie_check_timestamp(struct tcp_options_received *opt, struct net *net, - bool *ecn_ok); +bool cookie_timestamp_decode(struct tcp_options_received *opt); +bool cookie_ecn_ok(const struct tcp_options_received *opt, + const struct net *net, const struct dst_entry *dst); /* From net/ipv6/syncookies.c */ int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th, u32 cookie); struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb); -#ifdef CONFIG_SYN_COOKIES + u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb, @@ -1104,16 +1101,16 @@ static inline int tcp_win_from_space(int space) space - (space>>sysctl_tcp_adv_win_scale); } -/* Note: caller must be prepared to deal with negative returns */ +/* Note: caller must be prepared to deal with negative returns */ static inline int tcp_space(const struct sock *sk) { return tcp_win_from_space(sk->sk_rcvbuf - atomic_read(&sk->sk_rmem_alloc)); -} +} static inline int tcp_full_space(const struct sock *sk) { - return tcp_win_from_space(sk->sk_rcvbuf); + return tcp_win_from_space(sk->sk_rcvbuf); } static inline void tcp_openreq_init(struct request_sock *req, diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index a47790bcaa38..2a50a70ef587 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -100,6 +100,15 @@ static inline struct sk_buff *udp_tunnel_handle_offloads(struct sk_buff *skb, return iptunnel_handle_offloads(skb, udp_csum, type); } +static inline void udp_tunnel_gro_complete(struct sk_buff *skb, int nhoff) +{ + struct udphdr *uh; + + uh = (struct udphdr *)(skb->data + nhoff - sizeof(struct udphdr)); + skb_shinfo(skb)->gso_type |= uh->check ? + SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; +} + static inline void udp_tunnel_encap_enable(struct socket *sock) { #if IS_ENABLED(CONFIG_IPV6) diff --git a/include/net/udplite.h b/include/net/udplite.h index 2caadabcd07b..9a28a5179400 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -40,7 +40,7 @@ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh) * checksum. UDP-Lite (like IPv6) mandates checksums, hence packets * with a zero checksum field are illegal. */ if (uh->check == 0) { - LIMIT_NETDEBUG(KERN_DEBUG "UDPLite: zeroed checksum field\n"); + net_dbg_ratelimited("UDPLite: zeroed checksum field\n"); return 1; } @@ -52,8 +52,8 @@ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh) /* * Coverage length violates RFC 3828: log and discard silently. */ - LIMIT_NETDEBUG(KERN_DEBUG "UDPLite: bad csum coverage %d/%d\n", - cscov, skb->len); + net_dbg_ratelimited("UDPLite: bad csum coverage %d/%d\n", + cscov, skb->len); return 1; } else if (cscov < skb->len) { diff --git a/include/net/vxlan.h b/include/net/vxlan.h index d5f59f3fc35d..57cccd0052e5 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -8,6 +8,12 @@ #define VNI_HASH_BITS 10 #define VNI_HASH_SIZE (1<<VNI_HASH_BITS) +/* VXLAN protocol header */ +struct vxlanhdr { + __be32 vx_flags; + __be32 vx_vni; +}; + struct vxlan_sock; typedef void (vxlan_rcv_t)(struct vxlan_sock *vh, struct sk_buff *skb, __be32 key); @@ -45,6 +51,18 @@ int vxlan_xmit_skb(struct vxlan_sock *vs, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, __be32 vni, bool xnet); +static inline bool vxlan_gso_check(struct sk_buff *skb) +{ + if ((skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL) && + (skb->inner_protocol_type != ENCAP_TYPE_ETHER || + skb->inner_protocol != htons(ETH_P_TEB) || + (skb_inner_mac_header(skb) - skb_transport_header(skb) != + sizeof(struct udphdr) + sizeof(struct vxlanhdr)))) + return false; + + return true; +} + /* IP header + UDP + VXLAN + Ethernet header */ #define VXLAN_HEADROOM (20 + 8 + 8 + 14) /* IPv6 header + UDP + VXLAN + Ethernet header */ |