diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2011-03-16 16:29:25 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2011-03-16 16:29:25 -0700 |
commit | 7a6362800cb7d1d618a697a650c7aaed3eb39320 (patch) | |
tree | 087f9bc6c13ef1fad4b392c5cf9325cd28fa8523 /include | |
parent | 6445ced8670f37cfc2c5e24a9de9b413dbfc788d (diff) | |
parent | ceda86a108671294052cbf51660097b6534672f5 (diff) | |
download | op-kernel-dev-7a6362800cb7d1d618a697a650c7aaed3eb39320.zip op-kernel-dev-7a6362800cb7d1d618a697a650c7aaed3eb39320.tar.gz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6: (1480 commits)
bonding: enable netpoll without checking link status
xfrm: Refcount destination entry on xfrm_lookup
net: introduce rx_handler results and logic around that
bonding: get rid of IFF_SLAVE_INACTIVE netdev->priv_flag
bonding: wrap slave state work
net: get rid of multiple bond-related netdevice->priv_flags
bonding: register slave pointer for rx_handler
be2net: Bump up the version number
be2net: Copyright notice change. Update to Emulex instead of ServerEngines
e1000e: fix kconfig for crc32 dependency
netfilter ebtables: fix xt_AUDIT to work with ebtables
xen network backend driver
bonding: Improve syslog message at device creation time
bonding: Call netif_carrier_off after register_netdevice
bonding: Incorrect TX queue offset
net_sched: fix ip_tos2prio
xfrm: fix __xfrm_route_forward()
be2net: Fix UDP packet detected status in RX compl
Phonet: fix aligned-mode pipe socket buffer header reserve
netxen: support for GbE port settings
...
Fix up conflicts in drivers/staging/brcm80211/brcmsmac/wl_mac80211.c
with the staging updates.
Diffstat (limited to 'include')
139 files changed, 5016 insertions, 831 deletions
diff --git a/include/linux/audit.h b/include/linux/audit.h index 359df04..9d339eb 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -103,6 +103,8 @@ #define AUDIT_BPRM_FCAPS 1321 /* Information about fcaps increasing perms */ #define AUDIT_CAPSET 1322 /* Record showing argument to sys_capset */ #define AUDIT_MMAP 1323 /* Record showing descriptor and flags in mmap */ +#define AUDIT_NETFILTER_PKT 1324 /* Packets traversing netfilter chains */ +#define AUDIT_NETFILTER_CFG 1325 /* Netfilter chain modifications */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h new file mode 100644 index 0000000..473771a --- /dev/null +++ b/include/linux/cpu_rmap.h @@ -0,0 +1,73 @@ +/* + * cpu_rmap.c: CPU affinity reverse-map support + * Copyright 2011 Solarflare Communications Inc. + * + * 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, incorporated herein by reference. + */ + +#include <linux/cpumask.h> +#include <linux/gfp.h> +#include <linux/slab.h> + +/** + * struct cpu_rmap - CPU affinity reverse-map + * @size: Number of objects to be reverse-mapped + * @used: Number of objects added + * @obj: Pointer to array of object pointers + * @near: For each CPU, the index and distance to the nearest object, + * based on affinity masks + */ +struct cpu_rmap { + u16 size, used; + void **obj; + struct { + u16 index; + u16 dist; + } near[0]; +}; +#define CPU_RMAP_DIST_INF 0xffff + +extern struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags); + +/** + * free_cpu_rmap - free CPU affinity reverse-map + * @rmap: Reverse-map allocated with alloc_cpu_rmap(), or %NULL + */ +static inline void free_cpu_rmap(struct cpu_rmap *rmap) +{ + kfree(rmap); +} + +extern int cpu_rmap_add(struct cpu_rmap *rmap, void *obj); +extern int cpu_rmap_update(struct cpu_rmap *rmap, u16 index, + const struct cpumask *affinity); + +static inline u16 cpu_rmap_lookup_index(struct cpu_rmap *rmap, unsigned int cpu) +{ + return rmap->near[cpu].index; +} + +static inline void *cpu_rmap_lookup_obj(struct cpu_rmap *rmap, unsigned int cpu) +{ + return rmap->obj[rmap->near[cpu].index]; +} + +#ifdef CONFIG_GENERIC_HARDIRQS + +/** + * alloc_irq_cpu_rmap - allocate CPU affinity reverse-map for IRQs + * @size: Number of objects to be mapped + * + * Must be called in process context. + */ +static inline struct cpu_rmap *alloc_irq_cpu_rmap(unsigned int size) +{ + return alloc_cpu_rmap(size, GFP_KERNEL); +} +extern void free_irq_cpu_rmap(struct cpu_rmap *rmap); + +extern int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq); + +#endif diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h index 66900e3..c522800 100644 --- a/include/linux/dcbnl.h +++ b/include/linux/dcbnl.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2008, Intel Corporation. + * Copyright (c) 2008-2011, 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, @@ -25,9 +25,14 @@ /* IEEE 802.1Qaz std supported values */ #define IEEE_8021QAZ_MAX_TCS 8 +#define IEEE_8021QAZ_TSA_STRICT 0 +#define IEEE_8021QAZ_TSA_CB_SHAPER 1 +#define IEEE_8021QAZ_TSA_ETS 2 +#define IEEE_8021QAZ_TSA_VENDOR 255 + /* This structure contains the IEEE 802.1Qaz ETS managed object * - * @willing: willing bit in ETS configuratin TLV + * @willing: willing bit in ETS configuration TLV * @ets_cap: indicates supported capacity of ets feature * @cbs: credit based shaper ets algorithm supported * @tc_tx_bw: tc tx bandwidth indexed by traffic class @@ -82,6 +87,50 @@ struct ieee_pfc { __u64 indications[IEEE_8021QAZ_MAX_TCS]; }; +/* CEE DCBX std supported values */ +#define CEE_DCBX_MAX_PGS 8 +#define CEE_DCBX_MAX_PRIO 8 + +/** + * struct cee_pg - CEE Priority-Group managed object + * + * @willing: willing bit in the PG tlv + * @error: error bit in the PG tlv + * @pg_en: enable bit of the PG feature + * @tcs_supported: number of traffic classes supported + * @pg_bw: bandwidth percentage for each priority group + * @prio_pg: priority to PG mapping indexed by priority + */ +struct cee_pg { + __u8 willing; + __u8 error; + __u8 pg_en; + __u8 tcs_supported; + __u8 pg_bw[CEE_DCBX_MAX_PGS]; + __u8 prio_pg[CEE_DCBX_MAX_PGS]; +}; + +/** + * struct cee_pfc - CEE PFC managed object + * + * @willing: willing bit in the PFC tlv + * @error: error bit in the PFC tlv + * @pfc_en: bitmap indicating pfc enabled traffic classes + * @tcs_supported: number of traffic classes supported + */ +struct cee_pfc { + __u8 willing; + __u8 error; + __u8 pfc_en; + __u8 tcs_supported; +}; + +/* IEEE 802.1Qaz std supported values */ +#define IEEE_8021QAZ_APP_SEL_ETHERTYPE 1 +#define IEEE_8021QAZ_APP_SEL_STREAM 2 +#define IEEE_8021QAZ_APP_SEL_DGRAM 3 +#define IEEE_8021QAZ_APP_SEL_ANY 4 + /* This structure contains the IEEE 802.1Qaz APP managed object. This * object is also used for the CEE std as well. There is no difference * between the objects. @@ -105,6 +154,20 @@ struct dcb_app { __u16 protocol; }; +/** + * struct dcb_peer_app_info - APP feature information sent by the peer + * + * @willing: willing bit in the peer APP tlv + * @error: error bit in the peer APP tlv + * + * In addition to this information the full peer APP tlv also contains + * a table of 'app_count' APP objects defined above. + */ +struct dcb_peer_app_info { + __u8 willing; + __u8 error; +}; + struct dcbmsg { __u8 dcb_family; __u8 cmd; @@ -139,6 +202,7 @@ struct dcbmsg { * @DCB_CMD_SDCBX: set DCBX engine configuration * @DCB_CMD_GFEATCFG: get DCBX features flags * @DCB_CMD_SFEATCFG: set DCBX features negotiation flags + * @DCB_CMD_CEE_GET: get CEE aggregated configuration */ enum dcbnl_commands { DCB_CMD_UNDEFINED, @@ -181,6 +245,8 @@ enum dcbnl_commands { DCB_CMD_GFEATCFG, DCB_CMD_SFEATCFG, + DCB_CMD_CEE_GET, + __DCB_CMD_ENUM_MAX, DCB_CMD_MAX = __DCB_CMD_ENUM_MAX - 1, }; @@ -203,6 +269,7 @@ enum dcbnl_commands { * @DCB_ATTR_IEEE: IEEE 802.1Qaz supported attributes (NLA_NESTED) * @DCB_ATTR_DCBX: DCBX engine configuration in the device (NLA_U8) * @DCB_ATTR_FEATCFG: DCBX features flags (NLA_NESTED) + * @DCB_ATTR_CEE: CEE std supported attributes (NLA_NESTED) */ enum dcbnl_attrs { DCB_ATTR_UNDEFINED, @@ -226,15 +293,32 @@ enum dcbnl_attrs { DCB_ATTR_DCBX, DCB_ATTR_FEATCFG, + /* CEE nested attributes */ + DCB_ATTR_CEE, + __DCB_ATTR_ENUM_MAX, DCB_ATTR_MAX = __DCB_ATTR_ENUM_MAX - 1, }; +/** + * enum ieee_attrs - IEEE 802.1Qaz get/set attributes + * + * @DCB_ATTR_IEEE_UNSPEC: unspecified + * @DCB_ATTR_IEEE_ETS: negotiated ETS configuration + * @DCB_ATTR_IEEE_PFC: negotiated PFC configuration + * @DCB_ATTR_IEEE_APP_TABLE: negotiated APP configuration + * @DCB_ATTR_IEEE_PEER_ETS: peer ETS configuration - get only + * @DCB_ATTR_IEEE_PEER_PFC: peer PFC configuration - get only + * @DCB_ATTR_IEEE_PEER_APP: peer APP tlv - get only + */ enum ieee_attrs { DCB_ATTR_IEEE_UNSPEC, DCB_ATTR_IEEE_ETS, DCB_ATTR_IEEE_PFC, DCB_ATTR_IEEE_APP_TABLE, + DCB_ATTR_IEEE_PEER_ETS, + DCB_ATTR_IEEE_PEER_PFC, + DCB_ATTR_IEEE_PEER_APP, __DCB_ATTR_IEEE_MAX }; #define DCB_ATTR_IEEE_MAX (__DCB_ATTR_IEEE_MAX - 1) @@ -247,6 +331,31 @@ enum ieee_attrs_app { #define DCB_ATTR_IEEE_APP_MAX (__DCB_ATTR_IEEE_APP_MAX - 1) /** + * enum cee_attrs - CEE DCBX get attributes + * + * @DCB_ATTR_CEE_UNSPEC: unspecified + * @DCB_ATTR_CEE_PEER_PG: peer PG configuration - get only + * @DCB_ATTR_CEE_PEER_PFC: peer PFC configuration - get only + * @DCB_ATTR_CEE_PEER_APP: peer APP tlv - get only + */ +enum cee_attrs { + DCB_ATTR_CEE_UNSPEC, + DCB_ATTR_CEE_PEER_PG, + DCB_ATTR_CEE_PEER_PFC, + DCB_ATTR_CEE_PEER_APP_TABLE, + __DCB_ATTR_CEE_MAX +}; +#define DCB_ATTR_CEE_MAX (__DCB_ATTR_CEE_MAX - 1) + +enum peer_app_attr { + DCB_ATTR_CEE_PEER_APP_UNSPEC, + DCB_ATTR_CEE_PEER_APP_INFO, + DCB_ATTR_CEE_PEER_APP, + __DCB_ATTR_CEE_PEER_APP_MAX +}; +#define DCB_ATTR_CEE_PEER_APP_MAX (__DCB_ATTR_CEE_PEER_APP_MAX - 1) + +/** * enum dcbnl_pfc_attrs - DCB Priority Flow Control user priority nested attrs * * @DCB_PFC_UP_ATTR_UNDEFINED: unspecified attribute to catch errors diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 010e2d8..d638e85 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -279,8 +279,6 @@ enum dccp_state { DCCP_MAX_STATES }; -#define DCCP_STATE_MASK 0x1f - enum { DCCPF_OPEN = TCPF_ESTABLISHED, DCCPF_REQUESTING = TCPF_SYN_SENT, diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 1908929..aac3e2e 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -251,6 +251,7 @@ enum ethtool_stringset { ETH_SS_STATS, ETH_SS_PRIV_FLAGS, ETH_SS_NTUPLE_FILTERS, + ETH_SS_FEATURES, }; /* for passing string sets for data tagging */ @@ -523,6 +524,92 @@ struct ethtool_flash { char data[ETHTOOL_FLASH_MAX_FILENAME]; }; +/* for returning and changing feature sets */ + +/** + * struct ethtool_get_features_block - block with state of 32 features + * @available: mask of changeable features + * @requested: mask of features requested to be enabled if possible + * @active: mask of currently enabled features + * @never_changed: mask of features not changeable for any device + */ +struct ethtool_get_features_block { + __u32 available; + __u32 requested; + __u32 active; + __u32 never_changed; +}; + +/** + * struct ethtool_gfeatures - command to get state of device's features + * @cmd: command number = %ETHTOOL_GFEATURES + * @size: in: number of elements in the features[] array; + * out: number of elements in features[] needed to hold all features + * @features: state of features + */ +struct ethtool_gfeatures { + __u32 cmd; + __u32 size; + struct ethtool_get_features_block features[0]; +}; + +/** + * struct ethtool_set_features_block - block with request for 32 features + * @valid: mask of features to be changed + * @requested: values of features to be changed + */ +struct ethtool_set_features_block { + __u32 valid; + __u32 requested; +}; + +/** + * struct ethtool_sfeatures - command to request change in device's features + * @cmd: command number = %ETHTOOL_SFEATURES + * @size: array size of the features[] array + * @features: feature change masks + */ +struct ethtool_sfeatures { + __u32 cmd; + __u32 size; + struct ethtool_set_features_block features[0]; +}; + +/* + * %ETHTOOL_SFEATURES changes features present in features[].valid to the + * values of corresponding bits in features[].requested. Bits in .requested + * not set in .valid or not changeable are ignored. + * + * Returns %EINVAL when .valid contains undefined or never-changable bits + * or size is not equal to required number of features words (32-bit blocks). + * Returns >= 0 if request was completed; bits set in the value mean: + * %ETHTOOL_F_UNSUPPORTED - there were bits set in .valid that are not + * changeable (not present in %ETHTOOL_GFEATURES' features[].available) + * those bits were ignored. + * %ETHTOOL_F_WISH - some or all changes requested were recorded but the + * resulting state of bits masked by .valid is not equal to .requested. + * Probably there are other device-specific constraints on some features + * in the set. When %ETHTOOL_F_UNSUPPORTED is set, .valid is considered + * here as though ignored bits were cleared. + * %ETHTOOL_F_COMPAT - some or all changes requested were made by calling + * compatibility functions. Requested offload state cannot be properly + * managed by kernel. + * + * Meaning of bits in the masks are obtained by %ETHTOOL_GSSET_INFO (number of + * bits in the arrays - always multiple of 32) and %ETHTOOL_GSTRINGS commands + * for ETH_SS_FEATURES string set. First entry in the table corresponds to least + * significant bit in features[0] fields. Empty strings mark undefined features. + */ +enum ethtool_sfeatures_retval_bits { + ETHTOOL_F_UNSUPPORTED__BIT, + ETHTOOL_F_WISH__BIT, + ETHTOOL_F_COMPAT__BIT, +}; + +#define ETHTOOL_F_UNSUPPORTED (1 << ETHTOOL_F_UNSUPPORTED__BIT) +#define ETHTOOL_F_WISH (1 << ETHTOOL_F_WISH__BIT) +#define ETHTOOL_F_COMPAT (1 << ETHTOOL_F_COMPAT__BIT) + #ifdef __KERNEL__ #include <linux/rculist.h> @@ -543,7 +630,6 @@ struct net_device; /* Some generic methods drivers may use in their ethtool_ops */ u32 ethtool_op_get_link(struct net_device *dev); -u32 ethtool_op_get_rx_csum(struct net_device *dev); u32 ethtool_op_get_tx_csum(struct net_device *dev); int ethtool_op_set_tx_csum(struct net_device *dev, u32 data); int ethtool_op_set_tx_hw_csum(struct net_device *dev, u32 data); @@ -744,6 +830,9 @@ struct ethtool_ops { #define ETHTOOL_GRXFHINDIR 0x00000038 /* Get RX flow hash indir'n table */ #define ETHTOOL_SRXFHINDIR 0x00000039 /* Set RX flow hash indir'n table */ +#define ETHTOOL_GFEATURES 0x0000003a /* Get device offload settings */ +#define ETHTOOL_SFEATURES 0x0000003b /* Change device offload settings */ + /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET #define SPARC_ETH_SSET ETHTOOL_SSET diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 4c4c74e..ba45e6b 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -183,10 +183,10 @@ extern void icmpv6_cleanup(void); extern void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos); -struct flowi; +struct flowi6; struct in6_addr; extern void icmpv6_flow_init(struct sock *sk, - struct flowi *fl, + struct flowi6 *fl6, u8 type, const struct in6_addr *saddr, const struct in6_addr *daddr, diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 294169e..2d1c611 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1325,6 +1325,9 @@ enum { /* Although the spec says 8 I'm seeing 6 in practice */ #define IEEE80211_COUNTRY_IE_MIN_LEN 6 +/* The Country String field of the element shall be 3 octets in length */ +#define IEEE80211_COUNTRY_STRING_LEN 3 + /* * For regulatory extension stuff see IEEE 802.11-2007 * Annex I (page 1141) and Annex J (page 1147). Also diff --git a/include/linux/if.h b/include/linux/if.h index 1239599..3bc63e6 100644 --- a/include/linux/if.h +++ b/include/linux/if.h @@ -71,11 +71,10 @@ * release skb->dst */ #define IFF_DONT_BRIDGE 0x800 /* disallow bridging this ether dev */ -#define IFF_IN_NETPOLL 0x1000 /* whether we are processing netpoll */ -#define IFF_DISABLE_NETPOLL 0x2000 /* disable netpoll at run-time */ -#define IFF_MACVLAN_PORT 0x4000 /* device used as macvlan port */ -#define IFF_BRIDGE_PORT 0x8000 /* device used as bridge port */ -#define IFF_OVS_DATAPATH 0x10000 /* device used as Open vSwitch +#define IFF_DISABLE_NETPOLL 0x1000 /* disable netpoll at run-time */ +#define IFF_MACVLAN_PORT 0x2000 /* device used as macvlan port */ +#define IFF_BRIDGE_PORT 0x4000 /* device used as bridge port */ +#define IFF_OVS_DATAPATH 0x8000 /* device used as Open vSwitch * datapath port */ #define IF_GET_IFACE 0x0001 /* for querying only */ diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 6485d2a..f4a2e6b 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -135,6 +135,7 @@ enum { IFLA_VF_PORTS, IFLA_PORT_SELF, IFLA_AF_SPEC, + IFLA_GROUP, /* Group the device belongs to */ __IFLA_MAX }; diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 74cfcff..82de336 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -217,7 +217,7 @@ struct ip_mc_list { #define IGMPV3_QQIC(value) IGMPV3_EXP(0x80, 4, 3, value) #define IGMPV3_MRC(value) IGMPV3_EXP(0x80, 4, 3, value) -extern int ip_check_mc(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u16 proto); +extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u16 proto); extern int igmp_rcv(struct sk_buff *); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index ae8fdc5..5f81466 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -144,6 +144,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) #define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY) struct in_ifaddr { + struct hlist_node hash; struct in_ifaddr *ifa_next; struct in_device *ifa_dev; struct rcu_head rcu_head; diff --git a/include/linux/ip_vs.h b/include/linux/ip_vs.h index 5f43a3b..4deb383 100644 --- a/include/linux/ip_vs.h +++ b/include/linux/ip_vs.h @@ -89,6 +89,14 @@ #define IP_VS_CONN_F_TEMPLATE 0x1000 /* template, not connection */ #define IP_VS_CONN_F_ONE_PACKET 0x2000 /* forward only one packet */ +#define IP_VS_CONN_F_BACKUP_MASK (IP_VS_CONN_F_FWD_MASK | \ + IP_VS_CONN_F_NOOUTPUT | \ + IP_VS_CONN_F_INACTIVE | \ + IP_VS_CONN_F_SEQ_MASK | \ + IP_VS_CONN_F_NO_CPORT | \ + IP_VS_CONN_F_TEMPLATE \ + ) + /* Flags that are not sent to backup server start from bit 16 */ #define IP_VS_CONN_F_NFCT (1 << 16) /* use netfilter conntrack */ diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h new file mode 100644 index 0000000..dd8da34 --- /dev/null +++ b/include/linux/micrel_phy.h @@ -0,0 +1,16 @@ +#ifndef _MICREL_PHY_H +#define _MICREL_PHY_H + +#define MICREL_PHY_ID_MASK 0x00fffff0 + +#define PHY_ID_KSZ9021 0x00221611 +#define PHY_ID_KS8737 0x00221720 +#define PHY_ID_KS8041 0x00221510 +#define PHY_ID_KS8051 0x00221550 +/* both for ks8001 Rev. A/B, and for ks8721 Rev 3. */ +#define PHY_ID_KS8001 0x0022161A + +/* struct phy_device dev_flags definitions */ +#define MICREL_PHY_50MHZ_CLK 0x00000001 + +#endif /* _MICREL_PHY_H */ diff --git a/include/linux/net.h b/include/linux/net.h index 16faa13..94de83c 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -118,6 +118,7 @@ enum sock_shutdown_cmd { }; struct socket_wq { + /* Note: wait MUST be first field of socket_wq */ wait_queue_head_t wait; struct fasync_struct *fasync_list; struct rcu_head rcu; @@ -142,7 +143,7 @@ struct socket { unsigned long flags; - struct socket_wq *wq; + struct socket_wq __rcu *wq; struct file *file; struct sock *sk; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 71caf7a..5eeb2cd 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -138,6 +138,9 @@ static inline bool dev_xmit_complete(int rc) #define MAX_ADDR_LEN 32 /* Largest hardware address length */ +/* Initial net device group. All devices belong to group 0 by default. */ +#define INIT_NETDEV_GROUP 0 + #ifdef __KERNEL__ /* * Compute the worst case header length according to the protocols @@ -387,7 +390,55 @@ enum gro_result { }; typedef enum gro_result gro_result_t; -typedef struct sk_buff *rx_handler_func_t(struct sk_buff *skb); +/* + * enum rx_handler_result - Possible return values for rx_handlers. + * @RX_HANDLER_CONSUMED: skb was consumed by rx_handler, do not process it + * further. + * @RX_HANDLER_ANOTHER: Do another round in receive path. This is indicated in + * case skb->dev was changed by rx_handler. + * @RX_HANDLER_EXACT: Force exact delivery, no wildcard. + * @RX_HANDLER_PASS: Do nothing, passe the skb as if no rx_handler was called. + * + * rx_handlers are functions called from inside __netif_receive_skb(), to do + * special processing of the skb, prior to delivery to protocol handlers. + * + * Currently, a net_device can only have a single rx_handler registered. Trying + * to register a second rx_handler will return -EBUSY. + * + * To register a rx_handler on a net_device, use netdev_rx_handler_register(). + * To unregister a rx_handler on a net_device, use + * netdev_rx_handler_unregister(). + * + * Upon return, rx_handler is expected to tell __netif_receive_skb() what to + * do with the skb. + * + * If the rx_handler consumed to skb in some way, it should return + * RX_HANDLER_CONSUMED. This is appropriate when the rx_handler arranged for + * the skb to be delivered in some other ways. + * + * If the rx_handler changed skb->dev, to divert the skb to another + * net_device, it should return RX_HANDLER_ANOTHER. The rx_handler for the + * new device will be called if it exists. + * + * If the rx_handler consider the skb should be ignored, it should return + * RX_HANDLER_EXACT. The skb will only be delivered to protocol handlers that + * are registred on exact device (ptype->dev == skb->dev). + * + * If the rx_handler didn't changed skb->dev, but want the skb to be normally + * delivered, it should return RX_HANDLER_PASS. + * + * A device without a registered rx_handler will behave as if rx_handler + * returned RX_HANDLER_PASS. + */ + +enum rx_handler_result { + RX_HANDLER_CONSUMED, + RX_HANDLER_ANOTHER, + RX_HANDLER_EXACT, + RX_HANDLER_PASS, +}; +typedef enum rx_handler_result rx_handler_result_t; +typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb); extern void __napi_schedule(struct napi_struct *n); @@ -551,14 +602,16 @@ struct rps_map { #define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + (_num * sizeof(u16))) /* - * The rps_dev_flow structure contains the mapping of a flow to a CPU and the - * tail pointer for that CPU's input queue at the time of last enqueue. + * The rps_dev_flow structure contains the mapping of a flow to a CPU, the + * tail pointer for that CPU's input queue at the time of last enqueue, and + * a hardware filter index. */ struct rps_dev_flow { u16 cpu; - u16 fill; + u16 filter; unsigned int last_qtail; }; +#define RPS_NO_FILTER 0xffff /* * The rps_dev_flow_table structure contains a table of flow mappings. @@ -608,6 +661,11 @@ static inline void rps_reset_sock_flow(struct rps_sock_flow_table *table, extern struct rps_sock_flow_table __rcu *rps_sock_flow_table; +#ifdef CONFIG_RFS_ACCEL +extern bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, + u32 flow_id, u16 filter_id); +#endif + /* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { struct rps_map __rcu *rps_map; @@ -643,6 +701,14 @@ struct xps_dev_maps { (nr_cpu_ids * sizeof(struct xps_map *))) #endif /* CONFIG_XPS */ +#define TC_MAX_QUEUE 16 +#define TC_BITMASK 15 +/* HW offloaded queuing disciplines txq count and offset maps */ +struct netdev_tc_txq { + u16 count; + u16 offset; +}; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -753,6 +819,74 @@ struct xps_dev_maps { * int (*ndo_set_vf_port)(struct net_device *dev, int vf, * struct nlattr *port[]); * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); + * int (*ndo_setup_tc)(struct net_device *dev, u8 tc) + * Called to setup 'tc' number of traffic classes in the net device. This + * is always called from the stack with the rtnl lock held and netif tx + * queues stopped. This allows the netdevice to perform queue management + * safely. + * + * Fiber Channel over Ethernet (FCoE) offload functions. + * int (*ndo_fcoe_enable)(struct net_device *dev); + * Called when the FCoE protocol stack wants to start using LLD for FCoE + * so the underlying device can perform whatever needed configuration or + * initialization to support acceleration of FCoE traffic. + * + * int (*ndo_fcoe_disable)(struct net_device *dev); + * Called when the FCoE protocol stack wants to stop using LLD for FCoE + * so the underlying device can perform whatever needed clean-ups to + * stop supporting acceleration of FCoE traffic. + * + * int (*ndo_fcoe_ddp_setup)(struct net_device *dev, u16 xid, + * struct scatterlist *sgl, unsigned int sgc); + * Called when the FCoE Initiator wants to initialize an I/O that + * is a possible candidate for Direct Data Placement (DDP). The LLD can + * perform necessary setup and returns 1 to indicate the device is set up + * successfully to perform DDP on this I/O, otherwise this returns 0. + * + * int (*ndo_fcoe_ddp_done)(struct net_device *dev, u16 xid); + * Called when the FCoE Initiator/Target is done with the DDPed I/O as + * indicated by the FC exchange id 'xid', so the underlying device can + * clean up and reuse resources for later DDP requests. + * + * int (*ndo_fcoe_ddp_target)(struct net_device *dev, u16 xid, + * struct scatterlist *sgl, unsigned int sgc); + * Called when the FCoE Target wants to initialize an I/O that + * is a possible candidate for Direct Data Placement (DDP). The LLD can + * perform necessary setup and returns 1 to indicate the device is set up + * successfully to perform DDP on this I/O, otherwise this returns 0. + * + * int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type); + * Called when the underlying device wants to override default World Wide + * Name (WWN) generation mechanism in FCoE protocol stack to pass its own + * World Wide Port Name (WWPN) or World Wide Node Name (WWNN) to the FCoE + * protocol stack to use. + * + * RFS acceleration. + * int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb, + * u16 rxq_index, u32 flow_id); + * Set hardware filter for RFS. rxq_index is the target queue index; + * flow_id is a flow ID to be passed to rps_may_expire_flow() later. + * Return the filter ID on success, or a negative error code. + * + * Slave management functions (for bridge, bonding, etc). User should + * call netdev_set_master() to set dev->master properly. + * int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev); + * Called to make another netdev an underling. + * + * int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); + * Called to release previously enslaved netdev. + * + * Feature/offload setting functions. + * u32 (*ndo_fix_features)(struct net_device *dev, u32 features); + * Adjusts the requested feature flags according to device-specific + * constraints, and returns the resulting flags. Must not modify + * the device state. + * + * int (*ndo_set_features)(struct net_device *dev, u32 features); + * Called to update device configuration to new features. Passed + * feature set might be less than what was returned by ndo_fix_features()). + * Must return >0 or -errno if it changed dev->features itself. + * */ #define HAVE_NET_DEVICE_OPS struct net_device_ops { @@ -811,6 +945,7 @@ struct net_device_ops { struct nlattr *port[]); int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); + int (*ndo_setup_tc)(struct net_device *dev, u8 tc); #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); @@ -820,11 +955,29 @@ struct net_device_ops { unsigned int sgc); int (*ndo_fcoe_ddp_done)(struct net_device *dev, u16 xid); + int (*ndo_fcoe_ddp_target)(struct net_device *dev, + u16 xid, + struct scatterlist *sgl, + unsigned int sgc); #define NETDEV_FCOE_WWNN 0 #define NETDEV_FCOE_WWPN 1 int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type); #endif +#ifdef CONFIG_RFS_ACCEL + int (*ndo_rx_flow_steer)(struct net_device *dev, + const struct sk_buff *skb, + u16 rxq_index, + u32 flow_id); +#endif + int (*ndo_add_slave)(struct net_device *dev, + struct net_device *slave_dev); + int (*ndo_del_slave)(struct net_device *dev, + struct net_device *slave_dev); + u32 (*ndo_fix_features)(struct net_device *dev, + u32 features); + int (*ndo_set_features)(struct net_device *dev, + u32 features); }; /* @@ -876,8 +1029,18 @@ struct net_device { struct list_head napi_list; struct list_head unreg_list; - /* Net device features */ - unsigned long features; + /* currently active device features */ + u32 features; + /* user-changeable features */ + u32 hw_features; + /* user-requested features */ + u32 wanted_features; + /* VLAN feature mask */ + u32 vlan_features; + + /* Net device feature bits; if you change something, + * also update netdev_features_strings[] in ethtool.c */ + #define NETIF_F_SG 1 /* Scatter/gather IO. */ #define NETIF_F_IP_CSUM 2 /* Can checksum TCP/UDP over IPv4. */ #define NETIF_F_NO_CSUM 4 /* Does not require checksum. F.e. loopack. */ @@ -902,6 +1065,7 @@ struct net_device { #define NETIF_F_FCOE_MTU (1 << 26) /* Supports max FCoE MTU, 2158 bytes*/ #define NETIF_F_NTUPLE (1 << 27) /* N-tuple filters supported */ #define NETIF_F_RXHASH (1 << 28) /* Receive hashing offload */ +#define NETIF_F_RXCSUM (1 << 29) /* Receive checksumming offload */ /* Segmentation offload features */ #define NETIF_F_GSO_SHIFT 16 @@ -913,6 +1077,12 @@ struct net_device { #define NETIF_F_TSO6 (SKB_GSO_TCPV6 << NETIF_F_GSO_SHIFT) #define NETIF_F_FSO (SKB_GSO_FCOE << NETIF_F_GSO_SHIFT) + /* Features valid for ethtool to change */ + /* = all defined minus driver/device-class-related */ +#define NETIF_F_NEVER_CHANGE (NETIF_F_HIGHDMA | NETIF_F_VLAN_CHALLENGED | \ + NETIF_F_LLTX | NETIF_F_NETNS_LOCAL) +#define NETIF_F_ETHTOOL_BITS (0x3f3fffff & ~NETIF_F_NEVER_CHANGE) + /* List of features with software fallbacks. */ #define NETIF_F_GSO_SOFTWARE (NETIF_F_TSO | NETIF_F_TSO_ECN | \ NETIF_F_TSO6 | NETIF_F_UFO) @@ -923,6 +1093,12 @@ struct net_device { #define NETIF_F_V6_CSUM (NETIF_F_GEN_CSUM | NETIF_F_IPV6_CSUM) #define NETIF_F_ALL_CSUM (NETIF_F_V4_CSUM | NETIF_F_V6_CSUM) +#define NETIF_F_ALL_TSO (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN) + +#define NETIF_F_ALL_TX_OFFLOADS (NETIF_F_ALL_CSUM | NETIF_F_SG | \ + NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \ + NETIF_F_SCTP_CSUM | NETIF_F_FCOE_CRC) + /* * If one device supports one of these features, then enable them * for all in netdev_increment_features. @@ -931,6 +1107,9 @@ struct net_device { NETIF_F_SG | NETIF_F_HIGHDMA | \ NETIF_F_FRAGLIST) + /* changeable features with no special hardware requirements */ +#define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO) + /* Interface index. Unique device identifier */ int ifindex; int iflink; @@ -1039,6 +1218,13 @@ struct net_device { /* Number of RX queues currently active in device */ unsigned int real_num_rx_queues; + +#ifdef CONFIG_RFS_ACCEL + /* CPU reverse-mapping for RX completion interrupts, indexed + * by RX queue number. Assigned by driver. This must only be + * set if the ndo_rx_flow_steer operation is defined. */ + struct cpu_rmap *rx_cpu_rmap; +#endif #endif rx_handler_func_t __rcu *rx_handler; @@ -1132,9 +1318,6 @@ struct net_device { /* rtnetlink link ops */ const struct rtnl_link_ops *rtnl_link_ops; - /* VLAN feature mask */ - unsigned long vlan_features; - /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SIZE 65536 unsigned int gso_max_size; @@ -1143,6 +1326,9 @@ struct net_device { /* Data Center Bridging netlink ops */ const struct dcbnl_rtnl_ops *dcbnl_ops; #endif + u8 num_tc; + struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; + u8 prio_tc_map[TC_BITMASK + 1]; #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) /* max exchange id for FCoE LRO by ddp */ @@ -1153,12 +1339,66 @@ struct net_device { /* phy device may attach itself for hardware timestamping */ struct phy_device *phydev; + + /* group the device belongs to */ + int group; }; #define to_net_dev(d) container_of(d, struct net_device, dev) #define NETDEV_ALIGN 32 static inline +int netdev_get_prio_tc_map(const struct net_device *dev, u32 prio) +{ + return dev->prio_tc_map[prio & TC_BITMASK]; +} + +static inline +int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc) +{ + if (tc >= dev->num_tc) + return -EINVAL; + + dev->prio_tc_map[prio & TC_BITMASK] = tc & TC_BITMASK; + return 0; +} + +static inline +void netdev_reset_tc(struct net_device *dev) +{ + dev->num_tc = 0; + memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq)); + memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map)); +} + +static inline +int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset) +{ + if (tc >= dev->num_tc) + return -EINVAL; + + dev->tc_to_txq[tc].count = count; + dev->tc_to_txq[tc].offset = offset; + return 0; +} + +static inline +int netdev_set_num_tc(struct net_device *dev, u8 num_tc) +{ + if (num_tc > TC_MAX_QUEUE) + return -EINVAL; + + dev->num_tc = num_tc; + return 0; +} + +static inline +int netdev_get_num_tc(struct net_device *dev) +{ + return dev->num_tc; +} + +static inline struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev, unsigned int index) { @@ -1300,7 +1540,7 @@ struct packet_type { struct packet_type *, struct net_device *); struct sk_buff *(*gso_segment)(struct sk_buff *skb, - int features); + u32 features); int (*gso_send_check)(struct sk_buff *skb); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); @@ -1345,7 +1585,7 @@ static inline struct net_device *next_net_device_rcu(struct net_device *dev) struct net *net; net = dev_net(dev); - lh = rcu_dereference(dev->dev_list.next); + lh = rcu_dereference(list_next_rcu(&dev->dev_list)); return lh == &net->dev_base_head ? NULL : net_device_entry(lh); } @@ -1355,6 +1595,13 @@ static inline struct net_device *first_net_device(struct net *net) net_device_entry(net->dev_base_head.next); } +static inline struct net_device *first_net_device_rcu(struct net *net) +{ + struct list_head *lh = rcu_dereference(list_next_rcu(&net->dev_base_head)); + + return lh == &net->dev_base_head ? NULL : net_device_entry(lh); +} + extern int netdev_boot_setup_check(struct net_device *dev); extern unsigned long netdev_boot_base(const char *prefix, int unit); extern struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, @@ -1606,8 +1853,7 @@ static inline void netif_tx_wake_all_queues(struct net_device *dev) static inline void netif_tx_stop_queue(struct netdev_queue *dev_queue) { if (WARN_ON(!dev_queue)) { - printk(KERN_INFO "netif_stop_queue() cannot be called before " - "register_netdev()"); + pr_info("netif_stop_queue() cannot be called before register_netdev()\n"); return; } set_bit(__QUEUE_STATE_XOFF, &dev_queue->state); @@ -1844,6 +2090,7 @@ extern int dev_set_alias(struct net_device *, const char *, size_t); extern int dev_change_net_namespace(struct net_device *, struct net *, const char *); extern int dev_set_mtu(struct net_device *, int); +extern void dev_set_group(struct net_device *, int); extern int dev_set_mac_address(struct net_device *, struct sockaddr *); extern int dev_hard_start_xmit(struct sk_buff *skb, @@ -2267,8 +2514,10 @@ extern int netdev_max_backlog; extern int netdev_tstamp_prequeue; extern int weight_p; extern int netdev_set_master(struct net_device *dev, struct net_device *master); +extern int netdev_set_bond_master(struct net_device *dev, + struct net_device *master); extern int skb_checksum_help(struct sk_buff *skb); -extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features); +extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, u32 features); #ifdef CONFIG_BUG extern void netdev_rx_csum_fault(struct net_device *dev); #else @@ -2295,22 +2544,26 @@ extern char *netdev_drivername(const struct net_device *dev, char *buffer, int l extern void linkwatch_run_queue(void); -unsigned long netdev_increment_features(unsigned long all, unsigned long one, - unsigned long mask); -unsigned long netdev_fix_features(unsigned long features, const char *name); +static inline u32 netdev_get_wanted_features(struct net_device *dev) +{ + return (dev->features & ~dev->hw_features) | dev->wanted_features; +} +u32 netdev_increment_features(u32 all, u32 one, u32 mask); +u32 netdev_fix_features(struct net_device *dev, u32 features); +void netdev_update_features(struct net_device *dev); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); -int netif_skb_features(struct sk_buff *skb); +u32 netif_skb_features(struct sk_buff *skb); -static inline int net_gso_ok(int features, int gso_type) +static inline int net_gso_ok(u32 features, int gso_type) { int feature = gso_type << NETIF_F_GSO_SHIFT; return (features & feature) == feature; } -static inline int skb_gso_ok(struct sk_buff *skb, int features) +static inline int skb_gso_ok(struct sk_buff *skb, u32 features) { return net_gso_ok(features, skb_shinfo(skb)->gso_type) && (!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST)); @@ -2328,15 +2581,9 @@ static inline void netif_set_gso_max_size(struct net_device *dev, dev->gso_max_size = size; } -extern int __skb_bond_should_drop(struct sk_buff *skb, - struct net_device *master); - -static inline int skb_bond_should_drop(struct sk_buff *skb, - struct net_device *master) +static inline int netif_is_bond_slave(struct net_device *dev) { - if (master) - return __skb_bond_should_drop(skb, master); - return 0; + return dev->flags & IFF_SLAVE && dev->priv_flags & IFF_BONDING; } extern struct pernet_operations __net_initdata loopback_net_ops; @@ -2351,6 +2598,8 @@ static inline int dev_ethtool_get_settings(struct net_device *dev, static inline u32 dev_ethtool_get_rx_csum(struct net_device *dev) { + if (dev->hw_features & NETIF_F_RXCSUM) + return !!(dev->features & NETIF_F_RXCSUM); if (!dev->ethtool_ops || !dev->ethtool_ops->get_rx_csum) return 0; return dev->ethtool_ops->get_rx_csum(dev); diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 1893837..eeec00a 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -24,16 +24,20 @@ #define NF_MAX_VERDICT NF_STOP /* we overload the higher bits for encoding auxiliary data such as the queue - * number. Not nice, but better than additional function arguments. */ -#define NF_VERDICT_MASK 0x0000ffff -#define NF_VERDICT_BITS 16 + * number or errno values. Not nice, but better than additional function + * arguments. */ +#define NF_VERDICT_MASK 0x000000ff + +/* extra verdict flags have mask 0x0000ff00 */ +#define NF_VERDICT_FLAG_QUEUE_BYPASS 0x00008000 +/* queue number (NF_QUEUE) or errno (NF_DROP) */ #define NF_VERDICT_QMASK 0xffff0000 #define NF_VERDICT_QBITS 16 -#define NF_QUEUE_NR(x) ((((x) << NF_VERDICT_BITS) & NF_VERDICT_QMASK) | NF_QUEUE) +#define NF_QUEUE_NR(x) ((((x) << 16) & NF_VERDICT_QMASK) | NF_QUEUE) -#define NF_DROP_ERR(x) (((-x) << NF_VERDICT_BITS) | NF_DROP) +#define NF_DROP_ERR(x) (((-x) << 16) | NF_DROP) /* only for userspace compatibility */ #ifndef __KERNEL__ @@ -41,6 +45,9 @@ <= 0x2000 is used for protocol-flags. */ #define NFC_UNKNOWN 0x4000 #define NFC_ALTERED 0x8000 + +/* NF_VERDICT_BITS should be 8 now, but userspace might break if this changes */ +#define NF_VERDICT_BITS 16 #endif enum nf_inet_hooks { @@ -72,6 +79,10 @@ union nf_inet_addr { #ifdef __KERNEL__ #ifdef CONFIG_NETFILTER +static inline int NF_DROP_GETERR(int verdict) +{ + return -(verdict >> NF_VERDICT_QBITS); +} static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1, const union nf_inet_addr *a2) @@ -267,7 +278,7 @@ struct nf_afinfo { int route_key_size; }; -extern const struct nf_afinfo *nf_afinfo[NFPROTO_NUMPROTO]; +extern const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO]; static inline const struct nf_afinfo *nf_get_afinfo(unsigned short family) { return rcu_dereference(nf_afinfo[family]); @@ -357,9 +368,9 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #endif /*CONFIG_NETFILTER*/ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) -extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *); +extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu; extern void nf_ct_attach(struct sk_buff *, struct sk_buff *); -extern void (*nf_ct_destroy)(struct nf_conntrack *); +extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu; #else static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} #endif diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index 9d40eff..a1b410c 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -1,3 +1,5 @@ +header-y += ipset/ + header-y += nf_conntrack_common.h header-y += nf_conntrack_ftp.h header-y += nf_conntrack_sctp.h @@ -9,6 +11,7 @@ header-y += nfnetlink_conntrack.h header-y += nfnetlink_log.h header-y += nfnetlink_queue.h header-y += x_tables.h +header-y += xt_AUDIT.h header-y += xt_CHECKSUM.h header-y += xt_CLASSIFY.h header-y += xt_CONNMARK.h @@ -26,6 +29,7 @@ header-y += xt_TCPMSS.h header-y += xt_TCPOPTSTRIP.h header-y += xt_TEE.h header-y += xt_TPROXY.h +header-y += xt_addrtype.h header-y += xt_cluster.h header-y += xt_comment.h header-y += xt_connbytes.h @@ -34,6 +38,7 @@ header-y += xt_connmark.h header-y += xt_conntrack.h header-y += xt_cpu.h header-y += xt_dccp.h +header-y += xt_devgroup.h header-y += xt_dscp.h header-y += xt_esp.h header-y += xt_hashlimit.h @@ -54,7 +59,9 @@ header-y += xt_quota.h header-y += xt_rateest.h header-y += xt_realm.h header-y += xt_recent.h +header-y += xt_set.h header-y += xt_sctp.h +header-y += xt_socket.h header-y += xt_state.h header-y += xt_statistic.h header-y += xt_string.h diff --git a/include/linux/netfilter/ipset/Kbuild b/include/linux/netfilter/ipset/Kbuild new file mode 100644 index 0000000..601fe71 --- /dev/null +++ b/include/linux/netfilter/ipset/Kbuild @@ -0,0 +1,4 @@ +header-y += ip_set.h +header-y += ip_set_bitmap.h +header-y += ip_set_hash.h +header-y += ip_set_list.h diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h new file mode 100644 index 0000000..ec333d8 --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set.h @@ -0,0 +1,452 @@ +#ifndef _IP_SET_H +#define _IP_SET_H + +/* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu> + * Patrick Schaaf <bof@bof.de> + * Martin Josefsson <gandalf@wlug.westbo.se> + * Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * 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. + */ + +/* The protocol version */ +#define IPSET_PROTOCOL 6 + +/* The max length of strings including NUL: set and type identifiers */ +#define IPSET_MAXNAMELEN 32 + +/* Message types and commands */ +enum ipset_cmd { + IPSET_CMD_NONE, + IPSET_CMD_PROTOCOL, /* 1: Return protocol version */ + IPSET_CMD_CREATE, /* 2: Create a new (empty) set */ + IPSET_CMD_DESTROY, /* 3: Destroy a (empty) set */ + IPSET_CMD_FLUSH, /* 4: Remove all elements from a set */ + IPSET_CMD_RENAME, /* 5: Rename a set */ + IPSET_CMD_SWAP, /* 6: Swap two sets */ + IPSET_CMD_LIST, /* 7: List sets */ + IPSET_CMD_SAVE, /* 8: Save sets */ + IPSET_CMD_ADD, /* 9: Add an element to a set */ + IPSET_CMD_DEL, /* 10: Delete an element from a set */ + IPSET_CMD_TEST, /* 11: Test an element in a set */ + IPSET_CMD_HEADER, /* 12: Get set header data only */ + IPSET_CMD_TYPE, /* 13: Get set type */ + IPSET_MSG_MAX, /* Netlink message commands */ + + /* Commands in userspace: */ + IPSET_CMD_RESTORE = IPSET_MSG_MAX, /* 14: Enter restore mode */ + IPSET_CMD_HELP, /* 15: Get help */ + IPSET_CMD_VERSION, /* 16: Get program version */ + IPSET_CMD_QUIT, /* 17: Quit from interactive mode */ + + IPSET_CMD_MAX, + + IPSET_CMD_COMMIT = IPSET_CMD_MAX, /* 18: Commit buffered commands */ +}; + +/* Attributes at command level */ +enum { + IPSET_ATTR_UNSPEC, + IPSET_ATTR_PROTOCOL, /* 1: Protocol version */ + IPSET_ATTR_SETNAME, /* 2: Name of the set */ + IPSET_ATTR_TYPENAME, /* 3: Typename */ + IPSET_ATTR_SETNAME2 = IPSET_ATTR_TYPENAME, /* Setname at rename/swap */ + IPSET_ATTR_REVISION, /* 4: Settype revision */ + IPSET_ATTR_FAMILY, /* 5: Settype family */ + IPSET_ATTR_FLAGS, /* 6: Flags at command level */ + IPSET_ATTR_DATA, /* 7: Nested attributes */ + IPSET_ATTR_ADT, /* 8: Multiple data containers */ + IPSET_ATTR_LINENO, /* 9: Restore lineno */ + IPSET_ATTR_PROTOCOL_MIN, /* 10: Minimal supported version number */ + IPSET_ATTR_REVISION_MIN = IPSET_ATTR_PROTOCOL_MIN, /* type rev min */ + __IPSET_ATTR_CMD_MAX, +}; +#define IPSET_ATTR_CMD_MAX (__IPSET_ATTR_CMD_MAX - 1) + +/* CADT specific attributes */ +enum { + IPSET_ATTR_IP = IPSET_ATTR_UNSPEC + 1, + IPSET_ATTR_IP_FROM = IPSET_ATTR_IP, + IPSET_ATTR_IP_TO, /* 2 */ + IPSET_ATTR_CIDR, /* 3 */ + IPSET_ATTR_PORT, /* 4 */ + IPSET_ATTR_PORT_FROM = IPSET_ATTR_PORT, + IPSET_ATTR_PORT_TO, /* 5 */ + IPSET_ATTR_TIMEOUT, /* 6 */ + IPSET_ATTR_PROTO, /* 7 */ + IPSET_ATTR_CADT_FLAGS, /* 8 */ + IPSET_ATTR_CADT_LINENO = IPSET_ATTR_LINENO, /* 9 */ + /* Reserve empty slots */ + IPSET_ATTR_CADT_MAX = 16, + /* Create-only specific attributes */ + IPSET_ATTR_GC, + IPSET_ATTR_HASHSIZE, + IPSET_ATTR_MAXELEM, + IPSET_ATTR_NETMASK, + IPSET_ATTR_PROBES, + IPSET_ATTR_RESIZE, + IPSET_ATTR_SIZE, + /* Kernel-only */ + IPSET_ATTR_ELEMENTS, + IPSET_ATTR_REFERENCES, + IPSET_ATTR_MEMSIZE, + + __IPSET_ATTR_CREATE_MAX, +}; +#define IPSET_ATTR_CREATE_MAX (__IPSET_ATTR_CREATE_MAX - 1) + +/* ADT specific attributes */ +enum { + IPSET_ATTR_ETHER = IPSET_ATTR_CADT_MAX + 1, + IPSET_ATTR_NAME, + IPSET_ATTR_NAMEREF, + IPSET_ATTR_IP2, + IPSET_ATTR_CIDR2, + __IPSET_ATTR_ADT_MAX, +}; +#define IPSET_ATTR_ADT_MAX (__IPSET_ATTR_ADT_MAX - 1) + +/* IP specific attributes */ +enum { + IPSET_ATTR_IPADDR_IPV4 = IPSET_ATTR_UNSPEC + 1, + IPSET_ATTR_IPADDR_IPV6, + __IPSET_ATTR_IPADDR_MAX, +}; +#define IPSET_ATTR_IPADDR_MAX (__IPSET_ATTR_IPADDR_MAX - 1) + +/* Error codes */ +enum ipset_errno { + IPSET_ERR_PRIVATE = 4096, + IPSET_ERR_PROTOCOL, + IPSET_ERR_FIND_TYPE, + IPSET_ERR_MAX_SETS, + IPSET_ERR_BUSY, + IPSET_ERR_EXIST_SETNAME2, + IPSET_ERR_TYPE_MISMATCH, + IPSET_ERR_EXIST, + IPSET_ERR_INVALID_CIDR, + IPSET_ERR_INVALID_NETMASK, + IPSET_ERR_INVALID_FAMILY, + IPSET_ERR_TIMEOUT, + IPSET_ERR_REFERENCED, + IPSET_ERR_IPADDR_IPV4, + IPSET_ERR_IPADDR_IPV6, + + /* Type specific error codes */ + IPSET_ERR_TYPE_SPECIFIC = 4352, +}; + +/* Flags at command level */ +enum ipset_cmd_flags { + IPSET_FLAG_BIT_EXIST = 0, + IPSET_FLAG_EXIST = (1 << IPSET_FLAG_BIT_EXIST), +}; + +/* Flags at CADT attribute level */ +enum ipset_cadt_flags { + IPSET_FLAG_BIT_BEFORE = 0, + IPSET_FLAG_BEFORE = (1 << IPSET_FLAG_BIT_BEFORE), +}; + +/* Commands with settype-specific attributes */ +enum ipset_adt { + IPSET_ADD, + IPSET_DEL, + IPSET_TEST, + IPSET_ADT_MAX, + IPSET_CREATE = IPSET_ADT_MAX, + IPSET_CADT_MAX, +}; + +#ifdef __KERNEL__ +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/vmalloc.h> +#include <net/netlink.h> + +/* Sets are identified by an index in kernel space. Tweak with ip_set_id_t + * and IPSET_INVALID_ID if you want to increase the max number of sets. + */ +typedef u16 ip_set_id_t; + +#define IPSET_INVALID_ID 65535 + +enum ip_set_dim { + IPSET_DIM_ZERO = 0, + IPSET_DIM_ONE, + IPSET_DIM_TWO, + IPSET_DIM_THREE, + /* Max dimension in elements. + * If changed, new revision of iptables match/target is required. + */ + IPSET_DIM_MAX = 6, +}; + +/* Option flags for kernel operations */ +enum ip_set_kopt { + IPSET_INV_MATCH = (1 << IPSET_DIM_ZERO), + IPSET_DIM_ONE_SRC = (1 << IPSET_DIM_ONE), + IPSET_DIM_TWO_SRC = (1 << IPSET_DIM_TWO), + IPSET_DIM_THREE_SRC = (1 << IPSET_DIM_THREE), +}; + +/* Set features */ +enum ip_set_feature { + IPSET_TYPE_IP_FLAG = 0, + IPSET_TYPE_IP = (1 << IPSET_TYPE_IP_FLAG), + IPSET_TYPE_PORT_FLAG = 1, + IPSET_TYPE_PORT = (1 << IPSET_TYPE_PORT_FLAG), + IPSET_TYPE_MAC_FLAG = 2, + IPSET_TYPE_MAC = (1 << IPSET_TYPE_MAC_FLAG), + IPSET_TYPE_IP2_FLAG = 3, + IPSET_TYPE_IP2 = (1 << IPSET_TYPE_IP2_FLAG), + IPSET_TYPE_NAME_FLAG = 4, + IPSET_TYPE_NAME = (1 << IPSET_TYPE_NAME_FLAG), + /* Strictly speaking not a feature, but a flag for dumping: + * this settype must be dumped last */ + IPSET_DUMP_LAST_FLAG = 7, + IPSET_DUMP_LAST = (1 << IPSET_DUMP_LAST_FLAG), +}; + +struct ip_set; + +typedef int (*ipset_adtfn)(struct ip_set *set, void *value, u32 timeout); + +/* Set type, variant-specific part */ +struct ip_set_type_variant { + /* Kernelspace: test/add/del entries + * returns negative error code, + * zero for no match/success to add/delete + * positive for matching element */ + int (*kadt)(struct ip_set *set, const struct sk_buff * skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags); + + /* Userspace: test/add/del entries + * returns negative error code, + * zero for no match/success to add/delete + * positive for matching element */ + int (*uadt)(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags); + + /* Low level add/del/test functions */ + ipset_adtfn adt[IPSET_ADT_MAX]; + + /* When adding entries and set is full, try to resize the set */ + int (*resize)(struct ip_set *set, bool retried); + /* Destroy the set */ + void (*destroy)(struct ip_set *set); + /* Flush the elements */ + void (*flush)(struct ip_set *set); + /* Expire entries before listing */ + void (*expire)(struct ip_set *set); + /* List set header data */ + int (*head)(struct ip_set *set, struct sk_buff *skb); + /* List elements */ + int (*list)(const struct ip_set *set, struct sk_buff *skb, + struct netlink_callback *cb); + + /* Return true if "b" set is the same as "a" + * according to the create set parameters */ + bool (*same_set)(const struct ip_set *a, const struct ip_set *b); +}; + +/* The core set type structure */ +struct ip_set_type { + struct list_head list; + + /* Typename */ + char name[IPSET_MAXNAMELEN]; + /* Protocol version */ + u8 protocol; + /* Set features to control swapping */ + u8 features; + /* Set type dimension */ + u8 dimension; + /* Supported family: may be AF_UNSPEC for both AF_INET/AF_INET6 */ + u8 family; + /* Type revision */ + u8 revision; + + /* Create set */ + int (*create)(struct ip_set *set, struct nlattr *tb[], u32 flags); + + /* Attribute policies */ + const struct nla_policy create_policy[IPSET_ATTR_CREATE_MAX + 1]; + const struct nla_policy adt_policy[IPSET_ATTR_ADT_MAX + 1]; + + /* Set this to THIS_MODULE if you are a module, otherwise NULL */ + struct module *me; +}; + +/* register and unregister set type */ +extern int ip_set_type_register(struct ip_set_type *set_type); +extern void ip_set_type_unregister(struct ip_set_type *set_type); + +/* A generic IP set */ +struct ip_set { + /* The name of the set */ + char name[IPSET_MAXNAMELEN]; + /* Lock protecting the set data */ + rwlock_t lock; + /* References to the set */ + atomic_t ref; + /* The core set type */ + struct ip_set_type *type; + /* The type variant doing the real job */ + const struct ip_set_type_variant *variant; + /* The actual INET family of the set */ + u8 family; + /* The type specific data */ + void *data; +}; + +/* register and unregister set references */ +extern ip_set_id_t ip_set_get_byname(const char *name, struct ip_set **set); +extern void ip_set_put_byindex(ip_set_id_t index); +extern const char * ip_set_name_byindex(ip_set_id_t index); +extern ip_set_id_t ip_set_nfnl_get(const char *name); +extern ip_set_id_t ip_set_nfnl_get_byindex(ip_set_id_t index); +extern void ip_set_nfnl_put(ip_set_id_t index); + +/* API for iptables set match, and SET target */ +extern int ip_set_add(ip_set_id_t id, const struct sk_buff *skb, + u8 family, u8 dim, u8 flags); +extern int ip_set_del(ip_set_id_t id, const struct sk_buff *skb, + u8 family, u8 dim, u8 flags); +extern int ip_set_test(ip_set_id_t id, const struct sk_buff *skb, + u8 family, u8 dim, u8 flags); + +/* Utility functions */ +extern void * ip_set_alloc(size_t size); +extern void ip_set_free(void *members); +extern int ip_set_get_ipaddr4(struct nlattr *nla, __be32 *ipaddr); +extern int ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr); + +static inline int +ip_set_get_hostipaddr4(struct nlattr *nla, u32 *ipaddr) +{ + __be32 ip; + int ret = ip_set_get_ipaddr4(nla, &ip); + + if (ret) + return ret; + *ipaddr = ntohl(ip); + return 0; +} + +/* Ignore IPSET_ERR_EXIST errors if asked to do so? */ +static inline bool +ip_set_eexist(int ret, u32 flags) +{ + return ret == -IPSET_ERR_EXIST && (flags & IPSET_FLAG_EXIST); +} + +/* Check the NLA_F_NET_BYTEORDER flag */ +static inline bool +ip_set_attr_netorder(struct nlattr *tb[], int type) +{ + return tb[type] && (tb[type]->nla_type & NLA_F_NET_BYTEORDER); +} + +static inline bool +ip_set_optattr_netorder(struct nlattr *tb[], int type) +{ + return !tb[type] || (tb[type]->nla_type & NLA_F_NET_BYTEORDER); +} + +/* Useful converters */ +static inline u32 +ip_set_get_h32(const struct nlattr *attr) +{ + return ntohl(nla_get_be32(attr)); +} + +static inline u16 +ip_set_get_h16(const struct nlattr *attr) +{ + return ntohs(nla_get_be16(attr)); +} + +#define ipset_nest_start(skb, attr) nla_nest_start(skb, attr | NLA_F_NESTED) +#define ipset_nest_end(skb, start) nla_nest_end(skb, start) + +#define NLA_PUT_IPADDR4(skb, type, ipaddr) \ +do { \ + struct nlattr *__nested = ipset_nest_start(skb, type); \ + \ + if (!__nested) \ + goto nla_put_failure; \ + NLA_PUT_NET32(skb, IPSET_ATTR_IPADDR_IPV4, ipaddr); \ + ipset_nest_end(skb, __nested); \ +} while (0) + +#define NLA_PUT_IPADDR6(skb, type, ipaddrptr) \ +do { \ + struct nlattr *__nested = ipset_nest_start(skb, type); \ + \ + if (!__nested) \ + goto nla_put_failure; \ + NLA_PUT(skb, IPSET_ATTR_IPADDR_IPV6, \ + sizeof(struct in6_addr), ipaddrptr); \ + ipset_nest_end(skb, __nested); \ +} while (0) + +/* Get address from skbuff */ +static inline __be32 +ip4addr(const struct sk_buff *skb, bool src) +{ + return src ? ip_hdr(skb)->saddr : ip_hdr(skb)->daddr; +} + +static inline void +ip4addrptr(const struct sk_buff *skb, bool src, __be32 *addr) +{ + *addr = src ? ip_hdr(skb)->saddr : ip_hdr(skb)->daddr; +} + +static inline void +ip6addrptr(const struct sk_buff *skb, bool src, struct in6_addr *addr) +{ + memcpy(addr, src ? &ipv6_hdr(skb)->saddr : &ipv6_hdr(skb)->daddr, + sizeof(*addr)); +} + +/* Calculate the bytes required to store the inclusive range of a-b */ +static inline int +bitmap_bytes(u32 a, u32 b) +{ + return 4 * ((((b - a + 8) / 8) + 3) / 4); +} + +/* Interface to iptables/ip6tables */ + +#define SO_IP_SET 83 + +union ip_set_name_index { + char name[IPSET_MAXNAMELEN]; + ip_set_id_t index; +}; + +#define IP_SET_OP_GET_BYNAME 0x00000006 /* Get set index by name */ +struct ip_set_req_get_set { + unsigned op; + unsigned version; + union ip_set_name_index set; +}; + +#define IP_SET_OP_GET_BYINDEX 0x00000007 /* Get set name by index */ +/* Uses ip_set_req_get_set */ + +#define IP_SET_OP_VERSION 0x00000100 /* Ask kernel version */ +struct ip_set_req_version { + unsigned op; + unsigned version; +}; + +#endif /* __KERNEL__ */ + +#endif /*_IP_SET_H */ diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h new file mode 100644 index 0000000..ec9d9be --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -0,0 +1,1074 @@ +#ifndef _IP_SET_AHASH_H +#define _IP_SET_AHASH_H + +#include <linux/rcupdate.h> +#include <linux/jhash.h> +#include <linux/netfilter/ipset/ip_set_timeout.h> + +/* Hashing which uses arrays to resolve clashing. The hash table is resized + * (doubled) when searching becomes too long. + * Internally jhash is used with the assumption that the size of the + * stored data is a multiple of sizeof(u32). If storage supports timeout, + * the timeout field must be the last one in the data structure - that field + * is ignored when computing the hash key. + * + * Readers and resizing + * + * Resizing can be triggered by userspace command only, and those + * are serialized by the nfnl mutex. During resizing the set is + * read-locked, so the only possible concurrent operations are + * the kernel side readers. Those must be protected by proper RCU locking. + */ + +/* Number of elements to store in an initial array block */ +#define AHASH_INIT_SIZE 4 +/* Max number of elements to store in an array block */ +#define AHASH_MAX_SIZE (3*4) + +/* A hash bucket */ +struct hbucket { + void *value; /* the array of the values */ + u8 size; /* size of the array */ + u8 pos; /* position of the first free entry */ +}; + +/* The hash table: the table size stored here in order to make resizing easy */ +struct htable { + u8 htable_bits; /* size of hash table == 2^htable_bits */ + struct hbucket bucket[0]; /* hashtable buckets */ +}; + +#define hbucket(h, i) &((h)->bucket[i]) + +/* Book-keeping of the prefixes added to the set */ +struct ip_set_hash_nets { + u8 cidr; /* the different cidr values in the set */ + u32 nets; /* number of elements per cidr */ +}; + +/* The generic ip_set hash structure */ +struct ip_set_hash { + struct htable *table; /* the hash table */ + u32 maxelem; /* max elements in the hash */ + u32 elements; /* current element (vs timeout) */ + u32 initval; /* random jhash init value */ + u32 timeout; /* timeout value, if enabled */ + struct timer_list gc; /* garbage collection when timeout enabled */ +#ifdef IP_SET_HASH_WITH_NETMASK + u8 netmask; /* netmask value for subnets to store */ +#endif +#ifdef IP_SET_HASH_WITH_NETS + struct ip_set_hash_nets nets[0]; /* book-keeping of prefixes */ +#endif +}; + +/* Compute htable_bits from the user input parameter hashsize */ +static u8 +htable_bits(u32 hashsize) +{ + /* Assume that hashsize == 2^htable_bits */ + u8 bits = fls(hashsize - 1); + if (jhash_size(bits) != hashsize) + /* Round up to the first 2^n value */ + bits = fls(hashsize); + + return bits; +} + +#ifdef IP_SET_HASH_WITH_NETS + +#define SET_HOST_MASK(family) (family == AF_INET ? 32 : 128) + +/* Network cidr size book keeping when the hash stores different + * sized networks */ +static void +add_cidr(struct ip_set_hash *h, u8 cidr, u8 host_mask) +{ + u8 i; + + ++h->nets[cidr-1].nets; + + pr_debug("add_cidr added %u: %u\n", cidr, h->nets[cidr-1].nets); + + if (h->nets[cidr-1].nets > 1) + return; + + /* New cidr size */ + for (i = 0; i < host_mask && h->nets[i].cidr; i++) { + /* Add in increasing prefix order, so larger cidr first */ + if (h->nets[i].cidr < cidr) + swap(h->nets[i].cidr, cidr); + } + if (i < host_mask) + h->nets[i].cidr = cidr; +} + +static void +del_cidr(struct ip_set_hash *h, u8 cidr, u8 host_mask) +{ + u8 i; + + --h->nets[cidr-1].nets; + + pr_debug("del_cidr deleted %u: %u\n", cidr, h->nets[cidr-1].nets); + + if (h->nets[cidr-1].nets != 0) + return; + + /* All entries with this cidr size deleted, so cleanup h->cidr[] */ + for (i = 0; i < host_mask - 1 && h->nets[i].cidr; i++) { + if (h->nets[i].cidr == cidr) + h->nets[i].cidr = cidr = h->nets[i+1].cidr; + } + h->nets[i - 1].cidr = 0; +} +#endif + +/* Destroy the hashtable part of the set */ +static void +ahash_destroy(struct htable *t) +{ + struct hbucket *n; + u32 i; + + for (i = 0; i < jhash_size(t->htable_bits); i++) { + n = hbucket(t, i); + if (n->size) + /* FIXME: use slab cache */ + kfree(n->value); + } + + ip_set_free(t); +} + +/* Calculate the actual memory size of the set data */ +static size_t +ahash_memsize(const struct ip_set_hash *h, size_t dsize, u8 host_mask) +{ + u32 i; + struct htable *t = h->table; + size_t memsize = sizeof(*h) + + sizeof(*t) +#ifdef IP_SET_HASH_WITH_NETS + + sizeof(struct ip_set_hash_nets) * host_mask +#endif + + jhash_size(t->htable_bits) * sizeof(struct hbucket); + + for (i = 0; i < jhash_size(t->htable_bits); i++) + memsize += t->bucket[i].size * dsize; + + return memsize; +} + +/* Flush a hash type of set: destroy all elements */ +static void +ip_set_hash_flush(struct ip_set *set) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + struct hbucket *n; + u32 i; + + for (i = 0; i < jhash_size(t->htable_bits); i++) { + n = hbucket(t, i); + if (n->size) { + n->size = n->pos = 0; + /* FIXME: use slab cache */ + kfree(n->value); + } + } +#ifdef IP_SET_HASH_WITH_NETS + memset(h->nets, 0, sizeof(struct ip_set_hash_nets) + * SET_HOST_MASK(set->family)); +#endif + h->elements = 0; +} + +/* Destroy a hash type of set */ +static void +ip_set_hash_destroy(struct ip_set *set) +{ + struct ip_set_hash *h = set->data; + + if (with_timeout(h->timeout)) + del_timer_sync(&h->gc); + + ahash_destroy(h->table); + kfree(h); + + set->data = NULL; +} + +#define HKEY(data, initval, htable_bits) \ +(jhash2((u32 *)(data), sizeof(struct type_pf_elem)/sizeof(u32), initval) \ + & jhash_mask(htable_bits)) + +#endif /* _IP_SET_AHASH_H */ + +#define CONCAT(a, b, c) a##b##c +#define TOKEN(a, b, c) CONCAT(a, b, c) + +/* Type/family dependent function prototypes */ + +#define type_pf_data_equal TOKEN(TYPE, PF, _data_equal) +#define type_pf_data_isnull TOKEN(TYPE, PF, _data_isnull) +#define type_pf_data_copy TOKEN(TYPE, PF, _data_copy) +#define type_pf_data_zero_out TOKEN(TYPE, PF, _data_zero_out) +#define type_pf_data_netmask TOKEN(TYPE, PF, _data_netmask) +#define type_pf_data_list TOKEN(TYPE, PF, _data_list) +#define type_pf_data_tlist TOKEN(TYPE, PF, _data_tlist) + +#define type_pf_elem TOKEN(TYPE, PF, _elem) +#define type_pf_telem TOKEN(TYPE, PF, _telem) +#define type_pf_data_timeout TOKEN(TYPE, PF, _data_timeout) +#define type_pf_data_expired TOKEN(TYPE, PF, _data_expired) +#define type_pf_data_timeout_set TOKEN(TYPE, PF, _data_timeout_set) + +#define type_pf_elem_add TOKEN(TYPE, PF, _elem_add) +#define type_pf_add TOKEN(TYPE, PF, _add) +#define type_pf_del TOKEN(TYPE, PF, _del) +#define type_pf_test_cidrs TOKEN(TYPE, PF, _test_cidrs) +#define type_pf_test TOKEN(TYPE, PF, _test) + +#define type_pf_elem_tadd TOKEN(TYPE, PF, _elem_tadd) +#define type_pf_del_telem TOKEN(TYPE, PF, _ahash_del_telem) +#define type_pf_expire TOKEN(TYPE, PF, _expire) +#define type_pf_tadd TOKEN(TYPE, PF, _tadd) +#define type_pf_tdel TOKEN(TYPE, PF, _tdel) +#define type_pf_ttest_cidrs TOKEN(TYPE, PF, _ahash_ttest_cidrs) +#define type_pf_ttest TOKEN(TYPE, PF, _ahash_ttest) + +#define type_pf_resize TOKEN(TYPE, PF, _resize) +#define type_pf_tresize TOKEN(TYPE, PF, _tresize) +#define type_pf_flush ip_set_hash_flush +#define type_pf_destroy ip_set_hash_destroy +#define type_pf_head TOKEN(TYPE, PF, _head) +#define type_pf_list TOKEN(TYPE, PF, _list) +#define type_pf_tlist TOKEN(TYPE, PF, _tlist) +#define type_pf_same_set TOKEN(TYPE, PF, _same_set) +#define type_pf_kadt TOKEN(TYPE, PF, _kadt) +#define type_pf_uadt TOKEN(TYPE, PF, _uadt) +#define type_pf_gc TOKEN(TYPE, PF, _gc) +#define type_pf_gc_init TOKEN(TYPE, PF, _gc_init) +#define type_pf_variant TOKEN(TYPE, PF, _variant) +#define type_pf_tvariant TOKEN(TYPE, PF, _tvariant) + +/* Flavour without timeout */ + +/* Get the ith element from the array block n */ +#define ahash_data(n, i) \ + ((struct type_pf_elem *)((n)->value) + (i)) + +/* Add an element to the hash table when resizing the set: + * we spare the maintenance of the internal counters. */ +static int +type_pf_elem_add(struct hbucket *n, const struct type_pf_elem *value) +{ + if (n->pos >= n->size) { + void *tmp; + + if (n->size >= AHASH_MAX_SIZE) + /* Trigger rehashing */ + return -EAGAIN; + + tmp = kzalloc((n->size + AHASH_INIT_SIZE) + * sizeof(struct type_pf_elem), + GFP_ATOMIC); + if (!tmp) + return -ENOMEM; + if (n->size) { + memcpy(tmp, n->value, + sizeof(struct type_pf_elem) * n->size); + kfree(n->value); + } + n->value = tmp; + n->size += AHASH_INIT_SIZE; + } + type_pf_data_copy(ahash_data(n, n->pos++), value); + return 0; +} + +/* Resize a hash: create a new hash table with doubling the hashsize + * and inserting the elements to it. Repeat until we succeed or + * fail due to memory pressures. */ +static int +type_pf_resize(struct ip_set *set, bool retried) +{ + struct ip_set_hash *h = set->data; + struct htable *t, *orig = h->table; + u8 htable_bits = orig->htable_bits; + const struct type_pf_elem *data; + struct hbucket *n, *m; + u32 i, j; + int ret; + +retry: + ret = 0; + htable_bits++; + pr_debug("attempt to resize set %s from %u to %u, t %p\n", + set->name, orig->htable_bits, htable_bits, orig); + if (!htable_bits) + /* In case we have plenty of memory :-) */ + return -IPSET_ERR_HASH_FULL; + t = ip_set_alloc(sizeof(*t) + + jhash_size(htable_bits) * sizeof(struct hbucket)); + if (!t) + return -ENOMEM; + t->htable_bits = htable_bits; + + read_lock_bh(&set->lock); + for (i = 0; i < jhash_size(orig->htable_bits); i++) { + n = hbucket(orig, i); + for (j = 0; j < n->pos; j++) { + data = ahash_data(n, j); + m = hbucket(t, HKEY(data, h->initval, htable_bits)); + ret = type_pf_elem_add(m, data); + if (ret < 0) { + read_unlock_bh(&set->lock); + ahash_destroy(t); + if (ret == -EAGAIN) + goto retry; + return ret; + } + } + } + + rcu_assign_pointer(h->table, t); + read_unlock_bh(&set->lock); + + /* Give time to other readers of the set */ + synchronize_rcu_bh(); + + pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name, + orig->htable_bits, orig, t->htable_bits, t); + ahash_destroy(orig); + + return 0; +} + +/* Add an element to a hash and update the internal counters when succeeded, + * otherwise report the proper error code. */ +static int +type_pf_add(struct ip_set *set, void *value, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t; + const struct type_pf_elem *d = value; + struct hbucket *n; + int i, ret = 0; + u32 key; + + if (h->elements >= h->maxelem) + return -IPSET_ERR_HASH_FULL; + + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); + key = HKEY(value, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) + if (type_pf_data_equal(ahash_data(n, i), d)) { + ret = -IPSET_ERR_EXIST; + goto out; + } + + ret = type_pf_elem_add(n, value); + if (ret != 0) + goto out; + +#ifdef IP_SET_HASH_WITH_NETS + add_cidr(h, d->cidr, HOST_MASK); +#endif + h->elements++; +out: + rcu_read_unlock_bh(); + return ret; +} + +/* Delete an element from the hash: swap it with the last element + * and free up space if possible. + */ +static int +type_pf_del(struct ip_set *set, void *value, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + const struct type_pf_elem *d = value; + struct hbucket *n; + int i; + struct type_pf_elem *data; + u32 key; + + key = HKEY(value, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_data(n, i); + if (!type_pf_data_equal(data, d)) + continue; + if (i != n->pos - 1) + /* Not last one */ + type_pf_data_copy(data, ahash_data(n, n->pos - 1)); + + n->pos--; + h->elements--; +#ifdef IP_SET_HASH_WITH_NETS + del_cidr(h, d->cidr, HOST_MASK); +#endif + if (n->pos + AHASH_INIT_SIZE < n->size) { + void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) + * sizeof(struct type_pf_elem), + GFP_ATOMIC); + if (!tmp) + return 0; + n->size -= AHASH_INIT_SIZE; + memcpy(tmp, n->value, + n->size * sizeof(struct type_pf_elem)); + kfree(n->value); + n->value = tmp; + } + return 0; + } + + return -IPSET_ERR_EXIST; +} + +#ifdef IP_SET_HASH_WITH_NETS + +/* Special test function which takes into account the different network + * sizes added to the set */ +static int +type_pf_test_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + struct hbucket *n; + const struct type_pf_elem *data; + int i, j = 0; + u32 key; + u8 host_mask = SET_HOST_MASK(set->family); + + pr_debug("test by nets\n"); + for (; j < host_mask && h->nets[j].cidr; j++) { + type_pf_data_netmask(d, h->nets[j].cidr); + key = HKEY(d, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_data(n, i); + if (type_pf_data_equal(data, d)) + return 1; + } + } + return 0; +} +#endif + +/* Test whether the element is added to the set */ +static int +type_pf_test(struct ip_set *set, void *value, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + struct type_pf_elem *d = value; + struct hbucket *n; + const struct type_pf_elem *data; + int i; + u32 key; + +#ifdef IP_SET_HASH_WITH_NETS + /* If we test an IP address and not a network address, + * try all possible network sizes */ + if (d->cidr == SET_HOST_MASK(set->family)) + return type_pf_test_cidrs(set, d, timeout); +#endif + + key = HKEY(d, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_data(n, i); + if (type_pf_data_equal(data, d)) + return 1; + } + return 0; +} + +/* Reply a HEADER request: fill out the header part of the set */ +static int +type_pf_head(struct ip_set *set, struct sk_buff *skb) +{ + const struct ip_set_hash *h = set->data; + struct nlattr *nested; + size_t memsize; + + read_lock_bh(&set->lock); + memsize = ahash_memsize(h, with_timeout(h->timeout) + ? sizeof(struct type_pf_telem) + : sizeof(struct type_pf_elem), + set->family == AF_INET ? 32 : 128); + read_unlock_bh(&set->lock); + + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) + goto nla_put_failure; + NLA_PUT_NET32(skb, IPSET_ATTR_HASHSIZE, + htonl(jhash_size(h->table->htable_bits))); + NLA_PUT_NET32(skb, IPSET_ATTR_MAXELEM, htonl(h->maxelem)); +#ifdef IP_SET_HASH_WITH_NETMASK + if (h->netmask != HOST_MASK) + NLA_PUT_U8(skb, IPSET_ATTR_NETMASK, h->netmask); +#endif + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, + htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)); + if (with_timeout(h->timeout)) + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(h->timeout)); + ipset_nest_end(skb, nested); + + return 0; +nla_put_failure: + return -EMSGSIZE; +} + +/* Reply a LIST/SAVE request: dump the elements of the specified set */ +static int +type_pf_list(const struct ip_set *set, + struct sk_buff *skb, struct netlink_callback *cb) +{ + const struct ip_set_hash *h = set->data; + const struct htable *t = h->table; + struct nlattr *atd, *nested; + const struct hbucket *n; + const struct type_pf_elem *data; + u32 first = cb->args[2]; + /* We assume that one hash bucket fills into one page */ + void *incomplete; + int i; + + atd = ipset_nest_start(skb, IPSET_ATTR_ADT); + if (!atd) + return -EMSGSIZE; + pr_debug("list hash set %s\n", set->name); + for (; cb->args[2] < jhash_size(t->htable_bits); cb->args[2]++) { + incomplete = skb_tail_pointer(skb); + n = hbucket(t, cb->args[2]); + pr_debug("cb->args[2]: %lu, t %p n %p\n", cb->args[2], t, n); + for (i = 0; i < n->pos; i++) { + data = ahash_data(n, i); + pr_debug("list hash %lu hbucket %p i %u, data %p\n", + cb->args[2], n, i, data); + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) { + if (cb->args[2] == first) { + nla_nest_cancel(skb, atd); + return -EMSGSIZE; + } else + goto nla_put_failure; + } + if (type_pf_data_list(skb, data)) + goto nla_put_failure; + ipset_nest_end(skb, nested); + } + } + ipset_nest_end(skb, atd); + /* Set listing finished */ + cb->args[2] = 0; + + return 0; + +nla_put_failure: + nlmsg_trim(skb, incomplete); + ipset_nest_end(skb, atd); + if (unlikely(first == cb->args[2])) { + pr_warning("Can't list set %s: one bucket does not fit into " + "a message. Please report it!\n", set->name); + cb->args[2] = 0; + return -EMSGSIZE; + } + return 0; +} + +static int +type_pf_kadt(struct ip_set *set, const struct sk_buff * skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags); +static int +type_pf_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags); + +static const struct ip_set_type_variant type_pf_variant = { + .kadt = type_pf_kadt, + .uadt = type_pf_uadt, + .adt = { + [IPSET_ADD] = type_pf_add, + [IPSET_DEL] = type_pf_del, + [IPSET_TEST] = type_pf_test, + }, + .destroy = type_pf_destroy, + .flush = type_pf_flush, + .head = type_pf_head, + .list = type_pf_list, + .resize = type_pf_resize, + .same_set = type_pf_same_set, +}; + +/* Flavour with timeout support */ + +#define ahash_tdata(n, i) \ + (struct type_pf_elem *)((struct type_pf_telem *)((n)->value) + (i)) + +static inline u32 +type_pf_data_timeout(const struct type_pf_elem *data) +{ + const struct type_pf_telem *tdata = + (const struct type_pf_telem *) data; + + return tdata->timeout; +} + +static inline bool +type_pf_data_expired(const struct type_pf_elem *data) +{ + const struct type_pf_telem *tdata = + (const struct type_pf_telem *) data; + + return ip_set_timeout_expired(tdata->timeout); +} + +static inline void +type_pf_data_timeout_set(struct type_pf_elem *data, u32 timeout) +{ + struct type_pf_telem *tdata = (struct type_pf_telem *) data; + + tdata->timeout = ip_set_timeout_set(timeout); +} + +static int +type_pf_elem_tadd(struct hbucket *n, const struct type_pf_elem *value, + u32 timeout) +{ + struct type_pf_elem *data; + + if (n->pos >= n->size) { + void *tmp; + + if (n->size >= AHASH_MAX_SIZE) + /* Trigger rehashing */ + return -EAGAIN; + + tmp = kzalloc((n->size + AHASH_INIT_SIZE) + * sizeof(struct type_pf_telem), + GFP_ATOMIC); + if (!tmp) + return -ENOMEM; + if (n->size) { + memcpy(tmp, n->value, + sizeof(struct type_pf_telem) * n->size); + kfree(n->value); + } + n->value = tmp; + n->size += AHASH_INIT_SIZE; + } + data = ahash_tdata(n, n->pos++); + type_pf_data_copy(data, value); + type_pf_data_timeout_set(data, timeout); + return 0; +} + +/* Delete expired elements from the hashtable */ +static void +type_pf_expire(struct ip_set_hash *h) +{ + struct htable *t = h->table; + struct hbucket *n; + struct type_pf_elem *data; + u32 i; + int j; + + for (i = 0; i < jhash_size(t->htable_bits); i++) { + n = hbucket(t, i); + for (j = 0; j < n->pos; j++) { + data = ahash_tdata(n, j); + if (type_pf_data_expired(data)) { + pr_debug("expired %u/%u\n", i, j); +#ifdef IP_SET_HASH_WITH_NETS + del_cidr(h, data->cidr, HOST_MASK); +#endif + if (j != n->pos - 1) + /* Not last one */ + type_pf_data_copy(data, + ahash_tdata(n, n->pos - 1)); + n->pos--; + h->elements--; + } + } + if (n->pos + AHASH_INIT_SIZE < n->size) { + void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) + * sizeof(struct type_pf_telem), + GFP_ATOMIC); + if (!tmp) + /* Still try to delete expired elements */ + continue; + n->size -= AHASH_INIT_SIZE; + memcpy(tmp, n->value, + n->size * sizeof(struct type_pf_telem)); + kfree(n->value); + n->value = tmp; + } + } +} + +static int +type_pf_tresize(struct ip_set *set, bool retried) +{ + struct ip_set_hash *h = set->data; + struct htable *t, *orig = h->table; + u8 htable_bits = orig->htable_bits; + const struct type_pf_elem *data; + struct hbucket *n, *m; + u32 i, j; + int ret; + + /* Try to cleanup once */ + if (!retried) { + i = h->elements; + write_lock_bh(&set->lock); + type_pf_expire(set->data); + write_unlock_bh(&set->lock); + if (h->elements < i) + return 0; + } + +retry: + ret = 0; + htable_bits++; + if (!htable_bits) + /* In case we have plenty of memory :-) */ + return -IPSET_ERR_HASH_FULL; + t = ip_set_alloc(sizeof(*t) + + jhash_size(htable_bits) * sizeof(struct hbucket)); + if (!t) + return -ENOMEM; + t->htable_bits = htable_bits; + + read_lock_bh(&set->lock); + for (i = 0; i < jhash_size(orig->htable_bits); i++) { + n = hbucket(orig, i); + for (j = 0; j < n->pos; j++) { + data = ahash_tdata(n, j); + m = hbucket(t, HKEY(data, h->initval, htable_bits)); + ret = type_pf_elem_tadd(m, data, + type_pf_data_timeout(data)); + if (ret < 0) { + read_unlock_bh(&set->lock); + ahash_destroy(t); + if (ret == -EAGAIN) + goto retry; + return ret; + } + } + } + + rcu_assign_pointer(h->table, t); + read_unlock_bh(&set->lock); + + /* Give time to other readers of the set */ + synchronize_rcu_bh(); + + ahash_destroy(orig); + + return 0; +} + +static int +type_pf_tadd(struct ip_set *set, void *value, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + const struct type_pf_elem *d = value; + struct hbucket *n; + struct type_pf_elem *data; + int ret = 0, i, j = AHASH_MAX_SIZE + 1; + u32 key; + + if (h->elements >= h->maxelem) + /* FIXME: when set is full, we slow down here */ + type_pf_expire(h); + if (h->elements >= h->maxelem) + return -IPSET_ERR_HASH_FULL; + + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); + key = HKEY(d, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_tdata(n, i); + if (type_pf_data_equal(data, d)) { + if (type_pf_data_expired(data)) + j = i; + else { + ret = -IPSET_ERR_EXIST; + goto out; + } + } else if (j == AHASH_MAX_SIZE + 1 && + type_pf_data_expired(data)) + j = i; + } + if (j != AHASH_MAX_SIZE + 1) { + data = ahash_tdata(n, j); +#ifdef IP_SET_HASH_WITH_NETS + del_cidr(h, data->cidr, HOST_MASK); + add_cidr(h, d->cidr, HOST_MASK); +#endif + type_pf_data_copy(data, d); + type_pf_data_timeout_set(data, timeout); + goto out; + } + ret = type_pf_elem_tadd(n, d, timeout); + if (ret != 0) + goto out; + +#ifdef IP_SET_HASH_WITH_NETS + add_cidr(h, d->cidr, HOST_MASK); +#endif + h->elements++; +out: + rcu_read_unlock_bh(); + return ret; +} + +static int +type_pf_tdel(struct ip_set *set, void *value, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + const struct type_pf_elem *d = value; + struct hbucket *n; + int i, ret = 0; + struct type_pf_elem *data; + u32 key; + + key = HKEY(value, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_tdata(n, i); + if (!type_pf_data_equal(data, d)) + continue; + if (type_pf_data_expired(data)) + ret = -IPSET_ERR_EXIST; + if (i != n->pos - 1) + /* Not last one */ + type_pf_data_copy(data, ahash_tdata(n, n->pos - 1)); + + n->pos--; + h->elements--; +#ifdef IP_SET_HASH_WITH_NETS + del_cidr(h, d->cidr, HOST_MASK); +#endif + if (n->pos + AHASH_INIT_SIZE < n->size) { + void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) + * sizeof(struct type_pf_telem), + GFP_ATOMIC); + if (!tmp) + return 0; + n->size -= AHASH_INIT_SIZE; + memcpy(tmp, n->value, + n->size * sizeof(struct type_pf_telem)); + kfree(n->value); + n->value = tmp; + } + return 0; + } + + return -IPSET_ERR_EXIST; +} + +#ifdef IP_SET_HASH_WITH_NETS +static int +type_pf_ttest_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + struct type_pf_elem *data; + struct hbucket *n; + int i, j = 0; + u32 key; + u8 host_mask = SET_HOST_MASK(set->family); + + for (; j < host_mask && h->nets[j].cidr; j++) { + type_pf_data_netmask(d, h->nets[j].cidr); + key = HKEY(d, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_tdata(n, i); + if (type_pf_data_equal(data, d)) + return !type_pf_data_expired(data); + } + } + return 0; +} +#endif + +static int +type_pf_ttest(struct ip_set *set, void *value, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + struct type_pf_elem *data, *d = value; + struct hbucket *n; + int i; + u32 key; + +#ifdef IP_SET_HASH_WITH_NETS + if (d->cidr == SET_HOST_MASK(set->family)) + return type_pf_ttest_cidrs(set, d, timeout); +#endif + key = HKEY(d, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_tdata(n, i); + if (type_pf_data_equal(data, d)) + return !type_pf_data_expired(data); + } + return 0; +} + +static int +type_pf_tlist(const struct ip_set *set, + struct sk_buff *skb, struct netlink_callback *cb) +{ + const struct ip_set_hash *h = set->data; + const struct htable *t = h->table; + struct nlattr *atd, *nested; + const struct hbucket *n; + const struct type_pf_elem *data; + u32 first = cb->args[2]; + /* We assume that one hash bucket fills into one page */ + void *incomplete; + int i; + + atd = ipset_nest_start(skb, IPSET_ATTR_ADT); + if (!atd) + return -EMSGSIZE; + for (; cb->args[2] < jhash_size(t->htable_bits); cb->args[2]++) { + incomplete = skb_tail_pointer(skb); + n = hbucket(t, cb->args[2]); + for (i = 0; i < n->pos; i++) { + data = ahash_tdata(n, i); + pr_debug("list %p %u\n", n, i); + if (type_pf_data_expired(data)) + continue; + pr_debug("do list %p %u\n", n, i); + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) { + if (cb->args[2] == first) { + nla_nest_cancel(skb, atd); + return -EMSGSIZE; + } else + goto nla_put_failure; + } + if (type_pf_data_tlist(skb, data)) + goto nla_put_failure; + ipset_nest_end(skb, nested); + } + } + ipset_nest_end(skb, atd); + /* Set listing finished */ + cb->args[2] = 0; + + return 0; + +nla_put_failure: + nlmsg_trim(skb, incomplete); + ipset_nest_end(skb, atd); + if (unlikely(first == cb->args[2])) { + pr_warning("Can't list set %s: one bucket does not fit into " + "a message. Please report it!\n", set->name); + cb->args[2] = 0; + return -EMSGSIZE; + } + return 0; +} + +static const struct ip_set_type_variant type_pf_tvariant = { + .kadt = type_pf_kadt, + .uadt = type_pf_uadt, + .adt = { + [IPSET_ADD] = type_pf_tadd, + [IPSET_DEL] = type_pf_tdel, + [IPSET_TEST] = type_pf_ttest, + }, + .destroy = type_pf_destroy, + .flush = type_pf_flush, + .head = type_pf_head, + .list = type_pf_tlist, + .resize = type_pf_tresize, + .same_set = type_pf_same_set, +}; + +static void +type_pf_gc(unsigned long ul_set) +{ + struct ip_set *set = (struct ip_set *) ul_set; + struct ip_set_hash *h = set->data; + + pr_debug("called\n"); + write_lock_bh(&set->lock); + type_pf_expire(h); + write_unlock_bh(&set->lock); + + h->gc.expires = jiffies + IPSET_GC_PERIOD(h->timeout) * HZ; + add_timer(&h->gc); +} + +static void +type_pf_gc_init(struct ip_set *set) +{ + struct ip_set_hash *h = set->data; + + init_timer(&h->gc); + h->gc.data = (unsigned long) set; + h->gc.function = type_pf_gc; + h->gc.expires = jiffies + IPSET_GC_PERIOD(h->timeout) * HZ; + add_timer(&h->gc); + pr_debug("gc initialized, run in every %u\n", + IPSET_GC_PERIOD(h->timeout)); +} + +#undef type_pf_data_equal +#undef type_pf_data_isnull +#undef type_pf_data_copy +#undef type_pf_data_zero_out +#undef type_pf_data_list +#undef type_pf_data_tlist + +#undef type_pf_elem +#undef type_pf_telem +#undef type_pf_data_timeout +#undef type_pf_data_expired +#undef type_pf_data_netmask +#undef type_pf_data_timeout_set + +#undef type_pf_elem_add +#undef type_pf_add +#undef type_pf_del +#undef type_pf_test_cidrs +#undef type_pf_test + +#undef type_pf_elem_tadd +#undef type_pf_expire +#undef type_pf_tadd +#undef type_pf_tdel +#undef type_pf_ttest_cidrs +#undef type_pf_ttest + +#undef type_pf_resize +#undef type_pf_tresize +#undef type_pf_flush +#undef type_pf_destroy +#undef type_pf_head +#undef type_pf_list +#undef type_pf_tlist +#undef type_pf_same_set +#undef type_pf_kadt +#undef type_pf_uadt +#undef type_pf_gc +#undef type_pf_gc_init +#undef type_pf_variant +#undef type_pf_tvariant diff --git a/include/linux/netfilter/ipset/ip_set_bitmap.h b/include/linux/netfilter/ipset/ip_set_bitmap.h new file mode 100644 index 0000000..61a9e87 --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_bitmap.h @@ -0,0 +1,31 @@ +#ifndef __IP_SET_BITMAP_H +#define __IP_SET_BITMAP_H + +/* Bitmap type specific error codes */ +enum { + /* The element is out of the range of the set */ + IPSET_ERR_BITMAP_RANGE = IPSET_ERR_TYPE_SPECIFIC, + /* The range exceeds the size limit of the set type */ + IPSET_ERR_BITMAP_RANGE_SIZE, +}; + +#ifdef __KERNEL__ +#define IPSET_BITMAP_MAX_RANGE 0x0000FFFF + +/* Common functions */ + +static inline u32 +range_to_mask(u32 from, u32 to, u8 *bits) +{ + u32 mask = 0xFFFFFFFE; + + *bits = 32; + while (--(*bits) > 0 && mask && (to & mask) != from) + mask <<= 1; + + return mask; +} + +#endif /* __KERNEL__ */ + +#endif /* __IP_SET_BITMAP_H */ diff --git a/include/linux/netfilter/ipset/ip_set_getport.h b/include/linux/netfilter/ipset/ip_set_getport.h new file mode 100644 index 0000000..3882a81 --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_getport.h @@ -0,0 +1,21 @@ +#ifndef _IP_SET_GETPORT_H +#define _IP_SET_GETPORT_H + +extern bool ip_set_get_ip4_port(const struct sk_buff *skb, bool src, + __be16 *port, u8 *proto); + +#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) +extern bool ip_set_get_ip6_port(const struct sk_buff *skb, bool src, + __be16 *port, u8 *proto); +#else +static inline bool ip_set_get_ip6_port(const struct sk_buff *skb, bool src, + __be16 *port, u8 *proto) +{ + return false; +} +#endif + +extern bool ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src, + __be16 *port); + +#endif /*_IP_SET_GETPORT_H*/ diff --git a/include/linux/netfilter/ipset/ip_set_hash.h b/include/linux/netfilter/ipset/ip_set_hash.h new file mode 100644 index 0000000..b86f15c --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_hash.h @@ -0,0 +1,26 @@ +#ifndef __IP_SET_HASH_H +#define __IP_SET_HASH_H + +/* Hash type specific error codes */ +enum { + /* Hash is full */ + IPSET_ERR_HASH_FULL = IPSET_ERR_TYPE_SPECIFIC, + /* Null-valued element */ + IPSET_ERR_HASH_ELEM, + /* Invalid protocol */ + IPSET_ERR_INVALID_PROTO, + /* Protocol missing but must be specified */ + IPSET_ERR_MISSING_PROTO, +}; + +#ifdef __KERNEL__ + +#define IPSET_DEFAULT_HASHSIZE 1024 +#define IPSET_MIMINAL_HASHSIZE 64 +#define IPSET_DEFAULT_MAXELEM 65536 +#define IPSET_DEFAULT_PROBES 4 +#define IPSET_DEFAULT_RESIZE 100 + +#endif /* __KERNEL__ */ + +#endif /* __IP_SET_HASH_H */ diff --git a/include/linux/netfilter/ipset/ip_set_list.h b/include/linux/netfilter/ipset/ip_set_list.h new file mode 100644 index 0000000..40a63f3 --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_list.h @@ -0,0 +1,27 @@ +#ifndef __IP_SET_LIST_H +#define __IP_SET_LIST_H + +/* List type specific error codes */ +enum { + /* Set name to be added/deleted/tested does not exist. */ + IPSET_ERR_NAME = IPSET_ERR_TYPE_SPECIFIC, + /* list:set type is not permitted to add */ + IPSET_ERR_LOOP, + /* Missing reference set */ + IPSET_ERR_BEFORE, + /* Reference set does not exist */ + IPSET_ERR_NAMEREF, + /* Set is full */ + IPSET_ERR_LIST_FULL, + /* Reference set is not added to the set */ + IPSET_ERR_REF_EXIST, +}; + +#ifdef __KERNEL__ + +#define IP_SET_LIST_DEFAULT_SIZE 8 +#define IP_SET_LIST_MIN_SIZE 4 + +#endif /* __KERNEL__ */ + +#endif /* __IP_SET_LIST_H */ diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h new file mode 100644 index 0000000..9f30c5f --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_timeout.h @@ -0,0 +1,127 @@ +#ifndef _IP_SET_TIMEOUT_H +#define _IP_SET_TIMEOUT_H + +/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * 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. + */ + +#ifdef __KERNEL__ + +/* How often should the gc be run by default */ +#define IPSET_GC_TIME (3 * 60) + +/* Timeout period depending on the timeout value of the given set */ +#define IPSET_GC_PERIOD(timeout) \ + ((timeout/3) ? min_t(u32, (timeout)/3, IPSET_GC_TIME) : 1) + +/* Set is defined without timeout support: timeout value may be 0 */ +#define IPSET_NO_TIMEOUT UINT_MAX + +#define with_timeout(timeout) ((timeout) != IPSET_NO_TIMEOUT) + +static inline unsigned int +ip_set_timeout_uget(struct nlattr *tb) +{ + unsigned int timeout = ip_set_get_h32(tb); + + /* Userspace supplied TIMEOUT parameter: adjust crazy size */ + return timeout == IPSET_NO_TIMEOUT ? IPSET_NO_TIMEOUT - 1 : timeout; +} + +#ifdef IP_SET_BITMAP_TIMEOUT + +/* Bitmap specific timeout constants and macros for the entries */ + +/* Bitmap entry is unset */ +#define IPSET_ELEM_UNSET 0 +/* Bitmap entry is set with no timeout value */ +#define IPSET_ELEM_PERMANENT (UINT_MAX/2) + +static inline bool +ip_set_timeout_test(unsigned long timeout) +{ + return timeout != IPSET_ELEM_UNSET && + (timeout == IPSET_ELEM_PERMANENT || + time_after(timeout, jiffies)); +} + +static inline bool +ip_set_timeout_expired(unsigned long timeout) +{ + return timeout != IPSET_ELEM_UNSET && + timeout != IPSET_ELEM_PERMANENT && + time_before(timeout, jiffies); +} + +static inline unsigned long +ip_set_timeout_set(u32 timeout) +{ + unsigned long t; + + if (!timeout) + return IPSET_ELEM_PERMANENT; + + t = timeout * HZ + jiffies; + if (t == IPSET_ELEM_UNSET || t == IPSET_ELEM_PERMANENT) + /* Bingo! */ + t++; + + return t; +} + +static inline u32 +ip_set_timeout_get(unsigned long timeout) +{ + return timeout == IPSET_ELEM_PERMANENT ? 0 : (timeout - jiffies)/HZ; +} + +#else + +/* Hash specific timeout constants and macros for the entries */ + +/* Hash entry is set with no timeout value */ +#define IPSET_ELEM_PERMANENT 0 + +static inline bool +ip_set_timeout_test(unsigned long timeout) +{ + return timeout == IPSET_ELEM_PERMANENT || + time_after(timeout, jiffies); +} + +static inline bool +ip_set_timeout_expired(unsigned long timeout) +{ + return timeout != IPSET_ELEM_PERMANENT && + time_before(timeout, jiffies); +} + +static inline unsigned long +ip_set_timeout_set(u32 timeout) +{ + unsigned long t; + + if (!timeout) + return IPSET_ELEM_PERMANENT; + + t = timeout * HZ + jiffies; + if (t == IPSET_ELEM_PERMANENT) + /* Bingo! :-) */ + t++; + + return t; +} + +static inline u32 +ip_set_timeout_get(unsigned long timeout) +{ + return timeout == IPSET_ELEM_PERMANENT ? 0 : (timeout - jiffies)/HZ; +} +#endif /* ! IP_SET_BITMAP_TIMEOUT */ + +#endif /* __KERNEL__ */ + +#endif /* _IP_SET_TIMEOUT_H */ diff --git a/include/linux/netfilter/ipset/pfxlen.h b/include/linux/netfilter/ipset/pfxlen.h new file mode 100644 index 0000000..0e1fb50 --- /dev/null +++ b/include/linux/netfilter/ipset/pfxlen.h @@ -0,0 +1,35 @@ +#ifndef _PFXLEN_H +#define _PFXLEN_H + +#include <asm/byteorder.h> +#include <linux/netfilter.h> + +/* Prefixlen maps, by Jan Engelhardt */ +extern const union nf_inet_addr ip_set_netmask_map[]; +extern const union nf_inet_addr ip_set_hostmask_map[]; + +static inline __be32 +ip_set_netmask(u8 pfxlen) +{ + return ip_set_netmask_map[pfxlen].ip; +} + +static inline const __be32 * +ip_set_netmask6(u8 pfxlen) +{ + return &ip_set_netmask_map[pfxlen].ip6[0]; +} + +static inline u32 +ip_set_hostmask(u8 pfxlen) +{ + return (__force u32) ip_set_hostmask_map[pfxlen].ip; +} + +static inline const __be32 * +ip_set_hostmask6(u8 pfxlen) +{ + return &ip_set_hostmask_map[pfxlen].ip6[0]; +} + +#endif /*_PFXLEN_H */ diff --git a/include/linux/netfilter/nf_conntrack_snmp.h b/include/linux/netfilter/nf_conntrack_snmp.h new file mode 100644 index 0000000..064bc63 --- /dev/null +++ b/include/linux/netfilter/nf_conntrack_snmp.h @@ -0,0 +1,9 @@ +#ifndef _NF_CONNTRACK_SNMP_H +#define _NF_CONNTRACK_SNMP_H + +extern int (*nf_nat_snmp_hook)(struct sk_buff *skb, + unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo); + +#endif /* _NF_CONNTRACK_SNMP_H */ diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 361d6b5..2b11fc1 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -47,7 +47,8 @@ struct nfgenmsg { #define NFNL_SUBSYS_QUEUE 3 #define NFNL_SUBSYS_ULOG 4 #define NFNL_SUBSYS_OSF 5 -#define NFNL_SUBSYS_COUNT 6 +#define NFNL_SUBSYS_IPSET 6 +#define NFNL_SUBSYS_COUNT 7 #ifdef __KERNEL__ diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index 19711e3..debf1ae 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -42,6 +42,7 @@ enum ctattr_type { CTA_SECMARK, /* obsolete */ CTA_ZONE, CTA_SECCTX, + CTA_TIMESTAMP, __CTA_MAX }; #define CTA_MAX (__CTA_MAX - 1) @@ -127,6 +128,14 @@ enum ctattr_counters { }; #define CTA_COUNTERS_MAX (__CTA_COUNTERS_MAX - 1) +enum ctattr_tstamp { + CTA_TIMESTAMP_UNSPEC, + CTA_TIMESTAMP_START, + CTA_TIMESTAMP_STOP, + __CTA_TIMESTAMP_MAX +}; +#define CTA_TIMESTAMP_MAX (__CTA_TIMESTAMP_MAX - 1) + enum ctattr_nat { CTA_NAT_UNSPEC, CTA_NAT_MINIP, diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 6712e71..3721952 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -611,8 +611,9 @@ struct _compat_xt_align { extern void xt_compat_lock(u_int8_t af); extern void xt_compat_unlock(u_int8_t af); -extern int xt_compat_add_offset(u_int8_t af, unsigned int offset, short delta); +extern int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta); extern void xt_compat_flush_offsets(u_int8_t af); +extern void xt_compat_init_offsets(u_int8_t af, unsigned int number); extern int xt_compat_calc_jump(u_int8_t af, unsigned int offset); extern int xt_compat_match_offset(const struct xt_match *match); diff --git a/include/linux/netfilter/xt_AUDIT.h b/include/linux/netfilter/xt_AUDIT.h new file mode 100644 index 0000000..38751d2 --- /dev/null +++ b/include/linux/netfilter/xt_AUDIT.h @@ -0,0 +1,30 @@ +/* + * Header file for iptables xt_AUDIT target + * + * (C) 2010-2011 Thomas Graf <tgraf@redhat.com> + * (C) 2010-2011 Red Hat, Inc. + * + * 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. + */ + +#ifndef _XT_AUDIT_TARGET_H +#define _XT_AUDIT_TARGET_H + +#include <linux/types.h> + +enum { + XT_AUDIT_TYPE_ACCEPT = 0, + XT_AUDIT_TYPE_DROP, + XT_AUDIT_TYPE_REJECT, + __XT_AUDIT_TYPE_MAX, +}; + +#define XT_AUDIT_TYPE_MAX (__XT_AUDIT_TYPE_MAX - 1) + +struct xt_audit_info { + __u8 type; /* XT_AUDIT_TYPE_* */ +}; + +#endif /* _XT_AUDIT_TARGET_H */ diff --git a/include/linux/netfilter/xt_CT.h b/include/linux/netfilter/xt_CT.h index 1b56410..b56e768 100644 --- a/include/linux/netfilter/xt_CT.h +++ b/include/linux/netfilter/xt_CT.h @@ -1,14 +1,16 @@ #ifndef _XT_CT_H #define _XT_CT_H +#include <linux/types.h> + #define XT_CT_NOTRACK 0x1 struct xt_ct_target_info { - u_int16_t flags; - u_int16_t zone; - u_int32_t ct_events; - u_int32_t exp_events; - char helper[16]; + __u16 flags; + __u16 zone; + __u32 ct_events; + __u32 exp_events; + char helper[16]; /* Used internally by the kernel */ struct nf_conn *ct __attribute__((aligned(8))); diff --git a/include/linux/netfilter/xt_NFQUEUE.h b/include/linux/netfilter/xt_NFQUEUE.h index 2584f4a..9eafdbb 100644 --- a/include/linux/netfilter/xt_NFQUEUE.h +++ b/include/linux/netfilter/xt_NFQUEUE.h @@ -20,4 +20,10 @@ struct xt_NFQ_info_v1 { __u16 queues_total; }; +struct xt_NFQ_info_v2 { + __u16 queuenum; + __u16 queues_total; + __u16 bypass; +}; + #endif /* _XT_NFQ_TARGET_H */ diff --git a/include/linux/netfilter/xt_TCPOPTSTRIP.h b/include/linux/netfilter/xt_TCPOPTSTRIP.h index 2db5432..7157318 100644 --- a/include/linux/netfilter/xt_TCPOPTSTRIP.h +++ b/include/linux/netfilter/xt_TCPOPTSTRIP.h @@ -1,13 +1,15 @@ #ifndef _XT_TCPOPTSTRIP_H #define _XT_TCPOPTSTRIP_H +#include <linux/types.h> + #define tcpoptstrip_set_bit(bmap, idx) \ (bmap[(idx) >> 5] |= 1U << (idx & 31)) #define tcpoptstrip_test_bit(bmap, idx) \ (((1U << (idx & 31)) & bmap[(idx) >> 5]) != 0) struct xt_tcpoptstrip_target_info { - u_int32_t strip_bmap[8]; + __u32 strip_bmap[8]; }; #endif /* _XT_TCPOPTSTRIP_H */ diff --git a/include/linux/netfilter/xt_TPROXY.h b/include/linux/netfilter/xt_TPROXY.h index 3f3d693..902043c 100644 --- a/include/linux/netfilter/xt_TPROXY.h +++ b/include/linux/netfilter/xt_TPROXY.h @@ -1,19 +1,21 @@ #ifndef _XT_TPROXY_H #define _XT_TPROXY_H +#include <linux/types.h> + /* TPROXY target is capable of marking the packet to perform * redirection. We can get rid of that whenever we get support for * mutliple targets in the same rule. */ struct xt_tproxy_target_info { - u_int32_t mark_mask; - u_int32_t mark_value; + __u32 mark_mask; + __u32 mark_value; __be32 laddr; __be16 lport; }; struct xt_tproxy_target_info_v1 { - u_int32_t mark_mask; - u_int32_t mark_value; + __u32 mark_mask; + __u32 mark_value; union nf_inet_addr laddr; __be16 lport; }; diff --git a/include/linux/netfilter/xt_addrtype.h b/include/linux/netfilter/xt_addrtype.h new file mode 100644 index 0000000..b156baa --- /dev/null +++ b/include/linux/netfilter/xt_addrtype.h @@ -0,0 +1,44 @@ +#ifndef _XT_ADDRTYPE_H +#define _XT_ADDRTYPE_H + +#include <linux/types.h> + +enum { + XT_ADDRTYPE_INVERT_SOURCE = 0x0001, + XT_ADDRTYPE_INVERT_DEST = 0x0002, + XT_ADDRTYPE_LIMIT_IFACE_IN = 0x0004, + XT_ADDRTYPE_LIMIT_IFACE_OUT = 0x0008, +}; + + +/* rtn_type enum values from rtnetlink.h, but shifted */ +enum { + XT_ADDRTYPE_UNSPEC = 1 << 0, + XT_ADDRTYPE_UNICAST = 1 << 1, /* 1 << RTN_UNICAST */ + XT_ADDRTYPE_LOCAL = 1 << 2, /* 1 << RTN_LOCAL, etc */ + XT_ADDRTYPE_BROADCAST = 1 << 3, + XT_ADDRTYPE_ANYCAST = 1 << 4, + XT_ADDRTYPE_MULTICAST = 1 << 5, + XT_ADDRTYPE_BLACKHOLE = 1 << 6, + XT_ADDRTYPE_UNREACHABLE = 1 << 7, + XT_ADDRTYPE_PROHIBIT = 1 << 8, + XT_ADDRTYPE_THROW = 1 << 9, + XT_ADDRTYPE_NAT = 1 << 10, + XT_ADDRTYPE_XRESOLVE = 1 << 11, +}; + +struct xt_addrtype_info_v1 { + __u16 source; /* source-type mask */ + __u16 dest; /* dest-type mask */ + __u32 flags; +}; + +/* revision 0 */ +struct xt_addrtype_info { + __u16 source; /* source-type mask */ + __u16 dest; /* dest-type mask */ + __u32 invert_source; + __u32 invert_dest; +}; + +#endif diff --git a/include/linux/netfilter/xt_cluster.h b/include/linux/netfilter/xt_cluster.h index 8866826..9b883c8 100644 --- a/include/linux/netfilter/xt_cluster.h +++ b/include/linux/netfilter/xt_cluster.h @@ -1,15 +1,17 @@ #ifndef _XT_CLUSTER_MATCH_H #define _XT_CLUSTER_MATCH_H +#include <linux/types.h> + enum xt_cluster_flags { XT_CLUSTER_F_INV = (1 << 0) }; struct xt_cluster_match_info { - u_int32_t total_nodes; - u_int32_t node_mask; - u_int32_t hash_seed; - u_int32_t flags; + __u32 total_nodes; + __u32 node_mask; + __u32 hash_seed; + __u32 flags; }; #define XT_CLUSTER_NODES_MAX 32 diff --git a/include/linux/netfilter/xt_comment.h b/include/linux/netfilter/xt_comment.h index eacfedc..0ea5e79 100644 --- a/include/linux/netfilter/xt_comment.h +++ b/include/linux/netfilter/xt_comment.h @@ -4,7 +4,7 @@ #define XT_MAX_COMMENT_LEN 256 struct xt_comment_info { - unsigned char comment[XT_MAX_COMMENT_LEN]; + char comment[XT_MAX_COMMENT_LEN]; }; #endif /* XT_COMMENT_H */ diff --git a/include/linux/netfilter/xt_connlimit.h b/include/linux/netfilter/xt_connlimit.h index 7e3284b..0ca66e9 100644 --- a/include/linux/netfilter/xt_connlimit.h +++ b/include/linux/netfilter/xt_connlimit.h @@ -1,8 +1,15 @@ #ifndef _XT_CONNLIMIT_H #define _XT_CONNLIMIT_H +#include <linux/types.h> + struct xt_connlimit_data; +enum { + XT_CONNLIMIT_INVERT = 1 << 0, + XT_CONNLIMIT_DADDR = 1 << 1, +}; + struct xt_connlimit_info { union { union nf_inet_addr mask; @@ -13,7 +20,14 @@ struct xt_connlimit_info { }; #endif }; - unsigned int limit, inverse; + unsigned int limit; + union { + /* revision 0 */ + unsigned int inverse; + + /* revision 1 */ + __u32 flags; + }; /* Used internally by the kernel */ struct xt_connlimit_data *data __attribute__((aligned(8))); diff --git a/include/linux/netfilter/xt_conntrack.h b/include/linux/netfilter/xt_conntrack.h index 54f47a2..74b904d 100644 --- a/include/linux/netfilter/xt_conntrack.h +++ b/include/linux/netfilter/xt_conntrack.h @@ -58,4 +58,19 @@ struct xt_conntrack_mtinfo2 { __u16 state_mask, status_mask; }; +struct xt_conntrack_mtinfo3 { + union nf_inet_addr origsrc_addr, origsrc_mask; + union nf_inet_addr origdst_addr, origdst_mask; + union nf_inet_addr replsrc_addr, replsrc_mask; + union nf_inet_addr repldst_addr, repldst_mask; + __u32 expires_min, expires_max; + __u16 l4proto; + __u16 origsrc_port, origdst_port; + __u16 replsrc_port, repldst_port; + __u16 match_flags, invert_flags; + __u16 state_mask, status_mask; + __u16 origsrc_port_high, origdst_port_high; + __u16 replsrc_port_high, repldst_port_high; +}; + #endif /*_XT_CONNTRACK_H*/ diff --git a/include/linux/netfilter/xt_devgroup.h b/include/linux/netfilter/xt_devgroup.h new file mode 100644 index 0000000..1babde0 --- /dev/null +++ b/include/linux/netfilter/xt_devgroup.h @@ -0,0 +1,21 @@ +#ifndef _XT_DEVGROUP_H +#define _XT_DEVGROUP_H + +#include <linux/types.h> + +enum xt_devgroup_flags { + XT_DEVGROUP_MATCH_SRC = 0x1, + XT_DEVGROUP_INVERT_SRC = 0x2, + XT_DEVGROUP_MATCH_DST = 0x4, + XT_DEVGROUP_INVERT_DST = 0x8, +}; + +struct xt_devgroup_info { + __u32 flags; + __u32 src_group; + __u32 src_mask; + __u32 dst_group; + __u32 dst_mask; +}; + +#endif /* _XT_DEVGROUP_H */ diff --git a/include/linux/netfilter/xt_quota.h b/include/linux/netfilter/xt_quota.h index b0d28c6..ca6e03e 100644 --- a/include/linux/netfilter/xt_quota.h +++ b/include/linux/netfilter/xt_quota.h @@ -1,6 +1,8 @@ #ifndef _XT_QUOTA_H #define _XT_QUOTA_H +#include <linux/types.h> + enum xt_quota_flags { XT_QUOTA_INVERT = 0x1, }; @@ -9,9 +11,9 @@ enum xt_quota_flags { struct xt_quota_priv; struct xt_quota_info { - u_int32_t flags; - u_int32_t pad; - aligned_u64 quota; + __u32 flags; + __u32 pad; + aligned_u64 quota; /* Used internally by the kernel */ struct xt_quota_priv *master; diff --git a/include/linux/netfilter/xt_set.h b/include/linux/netfilter/xt_set.h new file mode 100644 index 0000000..081f1de --- /dev/null +++ b/include/linux/netfilter/xt_set.h @@ -0,0 +1,56 @@ +#ifndef _XT_SET_H +#define _XT_SET_H + +#include <linux/types.h> +#include <linux/netfilter/ipset/ip_set.h> + +/* Revision 0 interface: backward compatible with netfilter/iptables */ + +/* + * Option flags for kernel operations (xt_set_info_v0) + */ +#define IPSET_SRC 0x01 /* Source match/add */ +#define IPSET_DST 0x02 /* Destination match/add */ +#define IPSET_MATCH_INV 0x04 /* Inverse matching */ + +struct xt_set_info_v0 { + ip_set_id_t index; + union { + __u32 flags[IPSET_DIM_MAX + 1]; + struct { + __u32 __flags[IPSET_DIM_MAX]; + __u8 dim; + __u8 flags; + } compat; + } u; +}; + +/* match and target infos */ +struct xt_set_info_match_v0 { + struct xt_set_info_v0 match_set; +}; + +struct xt_set_info_target_v0 { + struct xt_set_info_v0 add_set; + struct xt_set_info_v0 del_set; +}; + +/* Revision 1: current interface to netfilter/iptables */ + +struct xt_set_info { + ip_set_id_t index; + __u8 dim; + __u8 flags; +}; + +/* match and target infos */ +struct xt_set_info_match { + struct xt_set_info match_set; +}; + +struct xt_set_info_target { + struct xt_set_info add_set; + struct xt_set_info del_set; +}; + +#endif /*_XT_SET_H*/ diff --git a/include/linux/netfilter/xt_socket.h b/include/linux/netfilter/xt_socket.h index 6f475b8..26d7217 100644 --- a/include/linux/netfilter/xt_socket.h +++ b/include/linux/netfilter/xt_socket.h @@ -1,6 +1,8 @@ #ifndef _XT_SOCKET_H #define _XT_SOCKET_H +#include <linux/types.h> + enum { XT_SOCKET_TRANSPARENT = 1 << 0, }; diff --git a/include/linux/netfilter/xt_time.h b/include/linux/netfilter/xt_time.h index 14b6df4..7c37fac 100644 --- a/include/linux/netfilter/xt_time.h +++ b/include/linux/netfilter/xt_time.h @@ -1,14 +1,16 @@ #ifndef _XT_TIME_H #define _XT_TIME_H 1 +#include <linux/types.h> + struct xt_time_info { - u_int32_t date_start; - u_int32_t date_stop; - u_int32_t daytime_start; - u_int32_t daytime_stop; - u_int32_t monthdays_match; - u_int8_t weekdays_match; - u_int8_t flags; + __u32 date_start; + __u32 date_stop; + __u32 daytime_start; + __u32 daytime_stop; + __u32 monthdays_match; + __u8 weekdays_match; + __u8 flags; }; enum { diff --git a/include/linux/netfilter/xt_u32.h b/include/linux/netfilter/xt_u32.h index 9947f56..04d1bfe 100644 --- a/include/linux/netfilter/xt_u32.h +++ b/include/linux/netfilter/xt_u32.h @@ -1,6 +1,8 @@ #ifndef _XT_U32_H #define _XT_U32_H 1 +#include <linux/types.h> + enum xt_u32_ops { XT_U32_AND, XT_U32_LEFTSH, @@ -9,13 +11,13 @@ enum xt_u32_ops { }; struct xt_u32_location_element { - u_int32_t number; - u_int8_t nextop; + __u32 number; + __u8 nextop; }; struct xt_u32_value_element { - u_int32_t min; - u_int32_t max; + __u32 min; + __u32 max; }; /* @@ -27,14 +29,14 @@ struct xt_u32_value_element { struct xt_u32_test { struct xt_u32_location_element location[XT_U32_MAXSIZE+1]; struct xt_u32_value_element value[XT_U32_MAXSIZE+1]; - u_int8_t nnums; - u_int8_t nvalues; + __u8 nnums; + __u8 nvalues; }; struct xt_u32 { struct xt_u32_test tests[XT_U32_MAXSIZE+1]; - u_int8_t ntests; - u_int8_t invert; + __u8 ntests; + __u8 invert; }; #endif /* _XT_U32_H */ diff --git a/include/linux/netfilter_bridge/ebt_802_3.h b/include/linux/netfilter_bridge/ebt_802_3.h index c73ef0b..be5be15 100644 --- a/include/linux/netfilter_bridge/ebt_802_3.h +++ b/include/linux/netfilter_bridge/ebt_802_3.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_802_3_H #define __LINUX_BRIDGE_EBT_802_3_H +#include <linux/types.h> + #define EBT_802_3_SAP 0x01 #define EBT_802_3_TYPE 0x02 @@ -24,24 +26,24 @@ /* ui has one byte ctrl, ni has two */ struct hdr_ui { - uint8_t dsap; - uint8_t ssap; - uint8_t ctrl; - uint8_t orig[3]; + __u8 dsap; + __u8 ssap; + __u8 ctrl; + __u8 orig[3]; __be16 type; }; struct hdr_ni { - uint8_t dsap; - uint8_t ssap; + __u8 dsap; + __u8 ssap; __be16 ctrl; - uint8_t orig[3]; + __u8 orig[3]; __be16 type; }; struct ebt_802_3_hdr { - uint8_t daddr[6]; - uint8_t saddr[6]; + __u8 daddr[6]; + __u8 saddr[6]; __be16 len; union { struct hdr_ui ui; @@ -59,10 +61,10 @@ static inline struct ebt_802_3_hdr *ebt_802_3_hdr(const struct sk_buff *skb) #endif struct ebt_802_3_info { - uint8_t sap; + __u8 sap; __be16 type; - uint8_t bitmask; - uint8_t invflags; + __u8 bitmask; + __u8 invflags; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_among.h b/include/linux/netfilter_bridge/ebt_among.h index 0009558..bd4e3ad 100644 --- a/include/linux/netfilter_bridge/ebt_among.h +++ b/include/linux/netfilter_bridge/ebt_among.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_AMONG_H #define __LINUX_BRIDGE_EBT_AMONG_H +#include <linux/types.h> + #define EBT_AMONG_DST 0x01 #define EBT_AMONG_SRC 0x02 @@ -30,7 +32,7 @@ */ struct ebt_mac_wormhash_tuple { - uint32_t cmp[2]; + __u32 cmp[2]; __be32 ip; }; diff --git a/include/linux/netfilter_bridge/ebt_arp.h b/include/linux/netfilter_bridge/ebt_arp.h index cbf4843..522f3e4 100644 --- a/include/linux/netfilter_bridge/ebt_arp.h +++ b/include/linux/netfilter_bridge/ebt_arp.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_ARP_H #define __LINUX_BRIDGE_EBT_ARP_H +#include <linux/types.h> + #define EBT_ARP_OPCODE 0x01 #define EBT_ARP_HTYPE 0x02 #define EBT_ARP_PTYPE 0x04 @@ -27,8 +29,8 @@ struct ebt_arp_info unsigned char smmsk[ETH_ALEN]; unsigned char dmaddr[ETH_ALEN]; unsigned char dmmsk[ETH_ALEN]; - uint8_t bitmask; - uint8_t invflags; + __u8 bitmask; + __u8 invflags; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_ip.h b/include/linux/netfilter_bridge/ebt_ip.h index 6a708fb..c4bbc41 100644 --- a/include/linux/netfilter_bridge/ebt_ip.h +++ b/include/linux/netfilter_bridge/ebt_ip.h @@ -15,6 +15,8 @@ #ifndef __LINUX_BRIDGE_EBT_IP_H #define __LINUX_BRIDGE_EBT_IP_H +#include <linux/types.h> + #define EBT_IP_SOURCE 0x01 #define EBT_IP_DEST 0x02 #define EBT_IP_TOS 0x04 @@ -31,12 +33,12 @@ struct ebt_ip_info { __be32 daddr; __be32 smsk; __be32 dmsk; - uint8_t tos; - uint8_t protocol; - uint8_t bitmask; - uint8_t invflags; - uint16_t sport[2]; - uint16_t dport[2]; + __u8 tos; + __u8 protocol; + __u8 bitmask; + __u8 invflags; + __u16 sport[2]; + __u16 dport[2]; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_ip6.h b/include/linux/netfilter_bridge/ebt_ip6.h index e5de987..42b8896 100644 --- a/include/linux/netfilter_bridge/ebt_ip6.h +++ b/include/linux/netfilter_bridge/ebt_ip6.h @@ -12,14 +12,19 @@ #ifndef __LINUX_BRIDGE_EBT_IP6_H #define __LINUX_BRIDGE_EBT_IP6_H +#include <linux/types.h> + #define EBT_IP6_SOURCE 0x01 #define EBT_IP6_DEST 0x02 #define EBT_IP6_TCLASS 0x04 #define EBT_IP6_PROTO 0x08 #define EBT_IP6_SPORT 0x10 #define EBT_IP6_DPORT 0x20 +#define EBT_IP6_ICMP6 0x40 + #define EBT_IP6_MASK (EBT_IP6_SOURCE | EBT_IP6_DEST | EBT_IP6_TCLASS |\ - EBT_IP6_PROTO | EBT_IP6_SPORT | EBT_IP6_DPORT) + EBT_IP6_PROTO | EBT_IP6_SPORT | EBT_IP6_DPORT | \ + EBT_IP6_ICMP6) #define EBT_IP6_MATCH "ip6" /* the same values are used for the invflags */ @@ -28,12 +33,18 @@ struct ebt_ip6_info { struct in6_addr daddr; struct in6_addr smsk; struct in6_addr dmsk; - uint8_t tclass; - uint8_t protocol; - uint8_t bitmask; - uint8_t invflags; - uint16_t sport[2]; - uint16_t dport[2]; + __u8 tclass; + __u8 protocol; + __u8 bitmask; + __u8 invflags; + union { + __u16 sport[2]; + __u8 icmpv6_type[2]; + }; + union { + __u16 dport[2]; + __u8 icmpv6_code[2]; + }; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_limit.h b/include/linux/netfilter_bridge/ebt_limit.h index 4bf76b7..66d80b3 100644 --- a/include/linux/netfilter_bridge/ebt_limit.h +++ b/include/linux/netfilter_bridge/ebt_limit.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_LIMIT_H #define __LINUX_BRIDGE_EBT_LIMIT_H +#include <linux/types.h> + #define EBT_LIMIT_MATCH "limit" /* timings are in milliseconds. */ @@ -10,13 +12,13 @@ seconds, or one every 59 hours. */ struct ebt_limit_info { - u_int32_t avg; /* Average secs between packets * scale */ - u_int32_t burst; /* Period multiplier for upper limit. */ + __u32 avg; /* Average secs between packets * scale */ + __u32 burst; /* Period multiplier for upper limit. */ /* Used internally by the kernel */ unsigned long prev; - u_int32_t credit; - u_int32_t credit_cap, cost; + __u32 credit; + __u32 credit_cap, cost; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_log.h b/include/linux/netfilter_bridge/ebt_log.h index cc2cdfb..7e7f1d1 100644 --- a/include/linux/netfilter_bridge/ebt_log.h +++ b/include/linux/netfilter_bridge/ebt_log.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_LOG_H #define __LINUX_BRIDGE_EBT_LOG_H +#include <linux/types.h> + #define EBT_LOG_IP 0x01 /* if the frame is made by ip, log the ip information */ #define EBT_LOG_ARP 0x02 #define EBT_LOG_NFLOG 0x04 @@ -10,9 +12,9 @@ #define EBT_LOG_WATCHER "log" struct ebt_log_info { - uint8_t loglevel; - uint8_t prefix[EBT_LOG_PREFIX_SIZE]; - uint32_t bitmask; + __u8 loglevel; + __u8 prefix[EBT_LOG_PREFIX_SIZE]; + __u32 bitmask; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_mark_m.h b/include/linux/netfilter_bridge/ebt_mark_m.h index 9ceb10e..410f9e5 100644 --- a/include/linux/netfilter_bridge/ebt_mark_m.h +++ b/include/linux/netfilter_bridge/ebt_mark_m.h @@ -1,13 +1,15 @@ #ifndef __LINUX_BRIDGE_EBT_MARK_M_H #define __LINUX_BRIDGE_EBT_MARK_M_H +#include <linux/types.h> + #define EBT_MARK_AND 0x01 #define EBT_MARK_OR 0x02 #define EBT_MARK_MASK (EBT_MARK_AND | EBT_MARK_OR) struct ebt_mark_m_info { unsigned long mark, mask; - uint8_t invert; - uint8_t bitmask; + __u8 invert; + __u8 bitmask; }; #define EBT_MARK_MATCH "mark_m" diff --git a/include/linux/netfilter_bridge/ebt_nflog.h b/include/linux/netfilter_bridge/ebt_nflog.h index 0528178..df829fc 100644 --- a/include/linux/netfilter_bridge/ebt_nflog.h +++ b/include/linux/netfilter_bridge/ebt_nflog.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_NFLOG_H #define __LINUX_BRIDGE_EBT_NFLOG_H +#include <linux/types.h> + #define EBT_NFLOG_MASK 0x0 #define EBT_NFLOG_PREFIX_SIZE 64 @@ -10,11 +12,11 @@ #define EBT_NFLOG_DEFAULT_THRESHOLD 1 struct ebt_nflog_info { - u_int32_t len; - u_int16_t group; - u_int16_t threshold; - u_int16_t flags; - u_int16_t pad; + __u32 len; + __u16 group; + __u16 threshold; + __u16 flags; + __u16 pad; char prefix[EBT_NFLOG_PREFIX_SIZE]; }; diff --git a/include/linux/netfilter_bridge/ebt_pkttype.h b/include/linux/netfilter_bridge/ebt_pkttype.h index 51a7998..c241bad 100644 --- a/include/linux/netfilter_bridge/ebt_pkttype.h +++ b/include/linux/netfilter_bridge/ebt_pkttype.h @@ -1,9 +1,11 @@ #ifndef __LINUX_BRIDGE_EBT_PKTTYPE_H #define __LINUX_BRIDGE_EBT_PKTTYPE_H +#include <linux/types.h> + struct ebt_pkttype_info { - uint8_t pkt_type; - uint8_t invert; + __u8 pkt_type; + __u8 invert; }; #define EBT_PKTTYPE_MATCH "pkttype" diff --git a/include/linux/netfilter_bridge/ebt_stp.h b/include/linux/netfilter_bridge/ebt_stp.h index e503a0a..1025b9f 100644 --- a/include/linux/netfilter_bridge/ebt_stp.h +++ b/include/linux/netfilter_bridge/ebt_stp.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_STP_H #define __LINUX_BRIDGE_EBT_STP_H +#include <linux/types.h> + #define EBT_STP_TYPE 0x0001 #define EBT_STP_FLAGS 0x0002 @@ -21,24 +23,24 @@ #define EBT_STP_MATCH "stp" struct ebt_stp_config_info { - uint8_t flags; - uint16_t root_priol, root_priou; + __u8 flags; + __u16 root_priol, root_priou; char root_addr[6], root_addrmsk[6]; - uint32_t root_costl, root_costu; - uint16_t sender_priol, sender_priou; + __u32 root_costl, root_costu; + __u16 sender_priol, sender_priou; char sender_addr[6], sender_addrmsk[6]; - uint16_t portl, portu; - uint16_t msg_agel, msg_ageu; - uint16_t max_agel, max_ageu; - uint16_t hello_timel, hello_timeu; - uint16_t forward_delayl, forward_delayu; + __u16 portl, portu; + __u16 msg_agel, msg_ageu; + __u16 max_agel, max_ageu; + __u16 hello_timel, hello_timeu; + __u16 forward_delayl, forward_delayu; }; struct ebt_stp_info { - uint8_t type; + __u8 type; struct ebt_stp_config_info config; - uint16_t bitmask; - uint16_t invflags; + __u16 bitmask; + __u16 invflags; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_ulog.h b/include/linux/netfilter_bridge/ebt_ulog.h index b677e26..89a6bec 100644 --- a/include/linux/netfilter_bridge/ebt_ulog.h +++ b/include/linux/netfilter_bridge/ebt_ulog.h @@ -1,6 +1,8 @@ #ifndef _EBT_ULOG_H #define _EBT_ULOG_H +#include <linux/types.h> + #define EBT_ULOG_DEFAULT_NLGROUP 0 #define EBT_ULOG_DEFAULT_QTHRESHOLD 1 #define EBT_ULOG_MAXNLGROUPS 32 /* hardcoded netlink max */ @@ -10,7 +12,7 @@ #define EBT_ULOG_VERSION 1 struct ebt_ulog_info { - uint32_t nlgroup; + __u32 nlgroup; unsigned int cprange; unsigned int qthreshold; char prefix[EBT_ULOG_PREFIX_LEN]; diff --git a/include/linux/netfilter_bridge/ebt_vlan.h b/include/linux/netfilter_bridge/ebt_vlan.h index 1d98be4..967d1d5 100644 --- a/include/linux/netfilter_bridge/ebt_vlan.h +++ b/include/linux/netfilter_bridge/ebt_vlan.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_VLAN_H #define __LINUX_BRIDGE_EBT_VLAN_H +#include <linux/types.h> + #define EBT_VLAN_ID 0x01 #define EBT_VLAN_PRIO 0x02 #define EBT_VLAN_ENCAP 0x04 @@ -8,12 +10,12 @@ #define EBT_VLAN_MATCH "vlan" struct ebt_vlan_info { - uint16_t id; /* VLAN ID {1-4095} */ - uint8_t prio; /* VLAN User Priority {0-7} */ + __u16 id; /* VLAN ID {1-4095} */ + __u8 prio; /* VLAN User Priority {0-7} */ __be16 encap; /* VLAN Encapsulated frame code {0-65535} */ - uint8_t bitmask; /* Args bitmask bit 1=1 - ID arg, + __u8 bitmask; /* Args bitmask bit 1=1 - ID arg, bit 2=1 User-Priority arg, bit 3=1 encap*/ - uint8_t invflags; /* Inverse bitmask bit 1=1 - inversed ID arg, + __u8 invflags; /* Inverse bitmask bit 1=1 - inversed ID arg, bit 2=1 - inversed Pirority arg */ }; diff --git a/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h b/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h index e5a3687..c6a204c 100644 --- a/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h +++ b/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h @@ -1,6 +1,8 @@ #ifndef _IPT_CLUSTERIP_H_target #define _IPT_CLUSTERIP_H_target +#include <linux/types.h> + enum clusterip_hashmode { CLUSTERIP_HASHMODE_SIP = 0, CLUSTERIP_HASHMODE_SIP_SPT, @@ -17,15 +19,15 @@ struct clusterip_config; struct ipt_clusterip_tgt_info { - u_int32_t flags; + __u32 flags; /* only relevant for new ones */ - u_int8_t clustermac[6]; - u_int16_t num_total_nodes; - u_int16_t num_local_nodes; - u_int16_t local_nodes[CLUSTERIP_MAX_NODES]; - u_int32_t hash_mode; - u_int32_t hash_initval; + __u8 clustermac[6]; + __u16 num_total_nodes; + __u16 num_local_nodes; + __u16 local_nodes[CLUSTERIP_MAX_NODES]; + __u32 hash_mode; + __u32 hash_initval; /* Used internally by the kernel */ struct clusterip_config *config; diff --git a/include/linux/netfilter_ipv4/ipt_ECN.h b/include/linux/netfilter_ipv4/ipt_ECN.h index 7ca4591..bb88d53 100644 --- a/include/linux/netfilter_ipv4/ipt_ECN.h +++ b/include/linux/netfilter_ipv4/ipt_ECN.h @@ -8,6 +8,8 @@ */ #ifndef _IPT_ECN_TARGET_H #define _IPT_ECN_TARGET_H + +#include <linux/types.h> #include <linux/netfilter/xt_DSCP.h> #define IPT_ECN_IP_MASK (~XT_DSCP_MASK) @@ -19,11 +21,11 @@ #define IPT_ECN_OP_MASK 0xce struct ipt_ECN_info { - u_int8_t operation; /* bitset of operations */ - u_int8_t ip_ect; /* ECT codepoint of IPv4 header, pre-shifted */ + __u8 operation; /* bitset of operations */ + __u8 ip_ect; /* ECT codepoint of IPv4 header, pre-shifted */ union { struct { - u_int8_t ece:1, cwr:1; /* TCP ECT bits */ + __u8 ece:1, cwr:1; /* TCP ECT bits */ } tcp; } proto; }; diff --git a/include/linux/netfilter_ipv4/ipt_SAME.h b/include/linux/netfilter_ipv4/ipt_SAME.h index 2529660..5bca782 100644 --- a/include/linux/netfilter_ipv4/ipt_SAME.h +++ b/include/linux/netfilter_ipv4/ipt_SAME.h @@ -1,15 +1,17 @@ #ifndef _IPT_SAME_H #define _IPT_SAME_H +#include <linux/types.h> + #define IPT_SAME_MAX_RANGE 10 #define IPT_SAME_NODST 0x01 struct ipt_same_info { unsigned char info; - u_int32_t rangesize; - u_int32_t ipnum; - u_int32_t *iparray; + __u32 rangesize; + __u32 ipnum; + __u32 *iparray; /* hangs off end. */ struct nf_nat_range range[IPT_SAME_MAX_RANGE]; diff --git a/include/linux/netfilter_ipv4/ipt_TTL.h b/include/linux/netfilter_ipv4/ipt_TTL.h index ee6611e..f6ac169 100644 --- a/include/linux/netfilter_ipv4/ipt_TTL.h +++ b/include/linux/netfilter_ipv4/ipt_TTL.h @@ -4,6 +4,8 @@ #ifndef _IPT_TTL_H #define _IPT_TTL_H +#include <linux/types.h> + enum { IPT_TTL_SET = 0, IPT_TTL_INC, @@ -13,8 +15,8 @@ enum { #define IPT_TTL_MAXMODE IPT_TTL_DEC struct ipt_TTL_info { - u_int8_t mode; - u_int8_t ttl; + __u8 mode; + __u8 ttl; }; diff --git a/include/linux/netfilter_ipv4/ipt_addrtype.h b/include/linux/netfilter_ipv4/ipt_addrtype.h index 446de6a..0da4223 100644 --- a/include/linux/netfilter_ipv4/ipt_addrtype.h +++ b/include/linux/netfilter_ipv4/ipt_addrtype.h @@ -1,6 +1,8 @@ #ifndef _IPT_ADDRTYPE_H #define _IPT_ADDRTYPE_H +#include <linux/types.h> + enum { IPT_ADDRTYPE_INVERT_SOURCE = 0x0001, IPT_ADDRTYPE_INVERT_DEST = 0x0002, @@ -9,17 +11,17 @@ enum { }; struct ipt_addrtype_info_v1 { - u_int16_t source; /* source-type mask */ - u_int16_t dest; /* dest-type mask */ - u_int32_t flags; + __u16 source; /* source-type mask */ + __u16 dest; /* dest-type mask */ + __u32 flags; }; /* revision 0 */ struct ipt_addrtype_info { - u_int16_t source; /* source-type mask */ - u_int16_t dest; /* dest-type mask */ - u_int32_t invert_source; - u_int32_t invert_dest; + __u16 source; /* source-type mask */ + __u16 dest; /* dest-type mask */ + __u32 invert_source; + __u32 invert_dest; }; #endif diff --git a/include/linux/netfilter_ipv4/ipt_ah.h b/include/linux/netfilter_ipv4/ipt_ah.h index 2e555b4..4e02bb0 100644 --- a/include/linux/netfilter_ipv4/ipt_ah.h +++ b/include/linux/netfilter_ipv4/ipt_ah.h @@ -1,9 +1,11 @@ #ifndef _IPT_AH_H #define _IPT_AH_H +#include <linux/types.h> + struct ipt_ah { - u_int32_t spis[2]; /* Security Parameter Index */ - u_int8_t invflags; /* Inverse flags */ + __u32 spis[2]; /* Security Parameter Index */ + __u8 invflags; /* Inverse flags */ }; diff --git a/include/linux/netfilter_ipv4/ipt_ecn.h b/include/linux/netfilter_ipv4/ipt_ecn.h index 9945baa..eabf95f 100644 --- a/include/linux/netfilter_ipv4/ipt_ecn.h +++ b/include/linux/netfilter_ipv4/ipt_ecn.h @@ -8,6 +8,8 @@ */ #ifndef _IPT_ECN_H #define _IPT_ECN_H + +#include <linux/types.h> #include <linux/netfilter/xt_dscp.h> #define IPT_ECN_IP_MASK (~XT_DSCP_MASK) @@ -20,12 +22,12 @@ /* match info */ struct ipt_ecn_info { - u_int8_t operation; - u_int8_t invert; - u_int8_t ip_ect; + __u8 operation; + __u8 invert; + __u8 ip_ect; union { struct { - u_int8_t ect; + __u8 ect; } tcp; } proto; }; diff --git a/include/linux/netfilter_ipv4/ipt_ttl.h b/include/linux/netfilter_ipv4/ipt_ttl.h index ee24fd8..37bee44 100644 --- a/include/linux/netfilter_ipv4/ipt_ttl.h +++ b/include/linux/netfilter_ipv4/ipt_ttl.h @@ -4,6 +4,8 @@ #ifndef _IPT_TTL_H #define _IPT_TTL_H +#include <linux/types.h> + enum { IPT_TTL_EQ = 0, /* equals */ IPT_TTL_NE, /* not equals */ @@ -13,8 +15,8 @@ enum { struct ipt_ttl_info { - u_int8_t mode; - u_int8_t ttl; + __u8 mode; + __u8 ttl; }; diff --git a/include/linux/netfilter_ipv6/ip6t_HL.h b/include/linux/netfilter_ipv6/ip6t_HL.h index afb7813..ebd8ead 100644 --- a/include/linux/netfilter_ipv6/ip6t_HL.h +++ b/include/linux/netfilter_ipv6/ip6t_HL.h @@ -5,6 +5,8 @@ #ifndef _IP6T_HL_H #define _IP6T_HL_H +#include <linux/types.h> + enum { IP6T_HL_SET = 0, IP6T_HL_INC, @@ -14,8 +16,8 @@ enum { #define IP6T_HL_MAXMODE IP6T_HL_DEC struct ip6t_HL_info { - u_int8_t mode; - u_int8_t hop_limit; + __u8 mode; + __u8 hop_limit; }; diff --git a/include/linux/netfilter_ipv6/ip6t_REJECT.h b/include/linux/netfilter_ipv6/ip6t_REJECT.h index 6be6504..205ed62 100644 --- a/include/linux/netfilter_ipv6/ip6t_REJECT.h +++ b/include/linux/netfilter_ipv6/ip6t_REJECT.h @@ -1,6 +1,8 @@ #ifndef _IP6T_REJECT_H #define _IP6T_REJECT_H +#include <linux/types.h> + enum ip6t_reject_with { IP6T_ICMP6_NO_ROUTE, IP6T_ICMP6_ADM_PROHIBITED, @@ -12,7 +14,7 @@ enum ip6t_reject_with { }; struct ip6t_reject_info { - u_int32_t with; /* reject type */ + __u32 with; /* reject type */ }; #endif /*_IP6T_REJECT_H*/ diff --git a/include/linux/netfilter_ipv6/ip6t_ah.h b/include/linux/netfilter_ipv6/ip6t_ah.h index 17a745c..5da2b65 100644 --- a/include/linux/netfilter_ipv6/ip6t_ah.h +++ b/include/linux/netfilter_ipv6/ip6t_ah.h @@ -1,11 +1,13 @@ #ifndef _IP6T_AH_H #define _IP6T_AH_H +#include <linux/types.h> + struct ip6t_ah { - u_int32_t spis[2]; /* Security Parameter Index */ - u_int32_t hdrlen; /* Header Length */ - u_int8_t hdrres; /* Test of the Reserved Filed */ - u_int8_t invflags; /* Inverse flags */ + __u32 spis[2]; /* Security Parameter Index */ + __u32 hdrlen; /* Header Length */ + __u8 hdrres; /* Test of the Reserved Filed */ + __u8 invflags; /* Inverse flags */ }; #define IP6T_AH_SPI 0x01 diff --git a/include/linux/netfilter_ipv6/ip6t_frag.h b/include/linux/netfilter_ipv6/ip6t_frag.h index 3724d08..b47f61b 100644 --- a/include/linux/netfilter_ipv6/ip6t_frag.h +++ b/include/linux/netfilter_ipv6/ip6t_frag.h @@ -1,11 +1,13 @@ #ifndef _IP6T_FRAG_H #define _IP6T_FRAG_H +#include <linux/types.h> + struct ip6t_frag { - u_int32_t ids[2]; /* Security Parameter Index */ - u_int32_t hdrlen; /* Header Length */ - u_int8_t flags; /* */ - u_int8_t invflags; /* Inverse flags */ + __u32 ids[2]; /* Security Parameter Index */ + __u32 hdrlen; /* Header Length */ + __u8 flags; /* */ + __u8 invflags; /* Inverse flags */ }; #define IP6T_FRAG_IDS 0x01 diff --git a/include/linux/netfilter_ipv6/ip6t_hl.h b/include/linux/netfilter_ipv6/ip6t_hl.h index 5ef91b8..6e76dbc 100644 --- a/include/linux/netfilter_ipv6/ip6t_hl.h +++ b/include/linux/netfilter_ipv6/ip6t_hl.h @@ -5,6 +5,8 @@ #ifndef _IP6T_HL_H #define _IP6T_HL_H +#include <linux/types.h> + enum { IP6T_HL_EQ = 0, /* equals */ IP6T_HL_NE, /* not equals */ @@ -14,8 +16,8 @@ enum { struct ip6t_hl_info { - u_int8_t mode; - u_int8_t hop_limit; + __u8 mode; + __u8 hop_limit; }; diff --git a/include/linux/netfilter_ipv6/ip6t_ipv6header.h b/include/linux/netfilter_ipv6/ip6t_ipv6header.h index 01dfd44..efae3a2 100644 --- a/include/linux/netfilter_ipv6/ip6t_ipv6header.h +++ b/include/linux/netfilter_ipv6/ip6t_ipv6header.h @@ -8,10 +8,12 @@ on whether they contain certain headers */ #ifndef __IPV6HEADER_H #define __IPV6HEADER_H +#include <linux/types.h> + struct ip6t_ipv6header_info { - u_int8_t matchflags; - u_int8_t invflags; - u_int8_t modeflag; + __u8 matchflags; + __u8 invflags; + __u8 modeflag; }; #define MASK_HOPOPTS 128 diff --git a/include/linux/netfilter_ipv6/ip6t_mh.h b/include/linux/netfilter_ipv6/ip6t_mh.h index 18549bc..a7729a5 100644 --- a/include/linux/netfilter_ipv6/ip6t_mh.h +++ b/include/linux/netfilter_ipv6/ip6t_mh.h @@ -1,10 +1,12 @@ #ifndef _IP6T_MH_H #define _IP6T_MH_H +#include <linux/types.h> + /* MH matching stuff */ struct ip6t_mh { - u_int8_t types[2]; /* MH type range */ - u_int8_t invflags; /* Inverse flags */ + __u8 types[2]; /* MH type range */ + __u8 invflags; /* Inverse flags */ }; /* Values for "invflags" field in struct ip6t_mh. */ diff --git a/include/linux/netfilter_ipv6/ip6t_opts.h b/include/linux/netfilter_ipv6/ip6t_opts.h index 62d89bc..17d419a 100644 --- a/include/linux/netfilter_ipv6/ip6t_opts.h +++ b/include/linux/netfilter_ipv6/ip6t_opts.h @@ -1,14 +1,16 @@ #ifndef _IP6T_OPTS_H #define _IP6T_OPTS_H +#include <linux/types.h> + #define IP6T_OPTS_OPTSNR 16 struct ip6t_opts { - u_int32_t hdrlen; /* Header Length */ - u_int8_t flags; /* */ - u_int8_t invflags; /* Inverse flags */ - u_int16_t opts[IP6T_OPTS_OPTSNR]; /* opts */ - u_int8_t optsnr; /* Nr of OPts */ + __u32 hdrlen; /* Header Length */ + __u8 flags; /* */ + __u8 invflags; /* Inverse flags */ + __u16 opts[IP6T_OPTS_OPTSNR]; /* opts */ + __u8 optsnr; /* Nr of OPts */ }; #define IP6T_OPTS_LEN 0x01 diff --git a/include/linux/netfilter_ipv6/ip6t_rt.h b/include/linux/netfilter_ipv6/ip6t_rt.h index ab91bfd..7605a5f 100644 --- a/include/linux/netfilter_ipv6/ip6t_rt.h +++ b/include/linux/netfilter_ipv6/ip6t_rt.h @@ -1,18 +1,19 @@ #ifndef _IP6T_RT_H #define _IP6T_RT_H +#include <linux/types.h> /*#include <linux/in6.h>*/ #define IP6T_RT_HOPS 16 struct ip6t_rt { - u_int32_t rt_type; /* Routing Type */ - u_int32_t segsleft[2]; /* Segments Left */ - u_int32_t hdrlen; /* Header Length */ - u_int8_t flags; /* */ - u_int8_t invflags; /* Inverse flags */ + __u32 rt_type; /* Routing Type */ + __u32 segsleft[2]; /* Segments Left */ + __u32 hdrlen; /* Header Length */ + __u8 flags; /* */ + __u8 invflags; /* Inverse flags */ struct in6_addr addrs[IP6T_RT_HOPS]; /* Hops */ - u_int8_t addrnr; /* Nr of Addresses */ + __u8 addrnr; /* Nr of Addresses */ }; #define IP6T_RT_TYP 0x01 diff --git a/include/linux/netlink.h b/include/linux/netlink.h index e2b9e63..4c4ac3f 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -160,10 +160,6 @@ struct netlink_skb_parms { struct ucred creds; /* Skb credentials */ __u32 pid; __u32 dst_group; - kernel_cap_t eff_cap; - __u32 loginuid; /* Login (audit) uid */ - __u32 sessionid; /* Session id (audit) */ - __u32 sid; /* SELinux security id */ }; #define NETLINK_CB(skb) (*(struct netlink_skb_parms*)&((skb)->cb)) diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 821ffb9..3002218 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1243,6 +1243,8 @@ enum nl80211_rate_info { * @NL80211_STA_INFO_LLID: the station's mesh LLID * @NL80211_STA_INFO_PLID: the station's mesh PLID * @NL80211_STA_INFO_PLINK_STATE: peer link state for the station + * @NL80211_STA_INFO_RX_BITRATE: last unicast data frame rx rate, nested + * attribute, like NL80211_STA_INFO_TX_BITRATE. * @__NL80211_STA_INFO_AFTER_LAST: internal * @NL80211_STA_INFO_MAX: highest possible station info attribute */ @@ -1261,6 +1263,7 @@ enum nl80211_sta_info { NL80211_STA_INFO_TX_RETRIES, NL80211_STA_INFO_TX_FAILED, NL80211_STA_INFO_SIGNAL_AVG, + NL80211_STA_INFO_RX_BITRATE, /* keep last */ __NL80211_STA_INFO_AFTER_LAST, diff --git a/include/linux/pci.h b/include/linux/pci.h index 559d028..ff5bccb8 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1479,6 +1479,7 @@ void pci_request_acs(void); #define PCI_VPD_RO_KEYWORD_PARTNO "PN" #define PCI_VPD_RO_KEYWORD_MFR_ID "MN" #define PCI_VPD_RO_KEYWORD_VENDOR0 "V0" +#define PCI_VPD_RO_KEYWORD_CHKSUM "RV" /** * pci_vpd_lrdt_size - Extracts the Large Resource Data Type length diff --git a/include/linux/phonet.h b/include/linux/phonet.h index 26c8df7..6fb1384 100644 --- a/include/linux/phonet.h +++ b/include/linux/phonet.h @@ -36,9 +36,7 @@ /* Socket options for SOL_PNPIPE level */ #define PNPIPE_ENCAP 1 #define PNPIPE_IFINDEX 2 -#define PNPIPE_PIPE_HANDLE 3 -#define PNPIPE_ENABLE 4 -/* unused slot */ +#define PNPIPE_HANDLE 3 #define PNADDR_ANY 0 #define PNADDR_BROADCAST 0xFC diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h index 2cfa4bc..b1032a3 100644 --- a/include/linux/pkt_sched.h +++ b/include/linux/pkt_sched.h @@ -247,6 +247,35 @@ struct tc_gred_sopt { __u16 pad1; }; +/* CHOKe section */ + +enum { + TCA_CHOKE_UNSPEC, + TCA_CHOKE_PARMS, + TCA_CHOKE_STAB, + __TCA_CHOKE_MAX, +}; + +#define TCA_CHOKE_MAX (__TCA_CHOKE_MAX - 1) + +struct tc_choke_qopt { + __u32 limit; /* Hard queue length (packets) */ + __u32 qth_min; /* Min average threshold (packets) */ + __u32 qth_max; /* Max average threshold (packets) */ + unsigned char Wlog; /* log(W) */ + unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */ + unsigned char Scell_log; /* cell size for idle damping */ + unsigned char flags; /* see RED flags */ +}; + +struct tc_choke_xstats { + __u32 early; /* Early drops */ + __u32 pdrop; /* Drops due to queue limits */ + __u32 other; /* Drops due to drop() calls */ + __u32 marked; /* Marked packets */ + __u32 matched; /* Drops due to flow match */ +}; + /* HTB section */ #define TC_HTB_NUMPRIO 8 #define TC_HTB_MAXDEPTH 8 @@ -435,6 +464,7 @@ enum { TCA_NETEM_DELAY_DIST, TCA_NETEM_REORDER, TCA_NETEM_CORRUPT, + TCA_NETEM_LOSS, __TCA_NETEM_MAX, }; @@ -465,7 +495,33 @@ struct tc_netem_corrupt { __u32 correlation; }; +enum { + NETEM_LOSS_UNSPEC, + NETEM_LOSS_GI, /* General Intuitive - 4 state model */ + NETEM_LOSS_GE, /* Gilbert Elliot models */ + __NETEM_LOSS_MAX +}; +#define NETEM_LOSS_MAX (__NETEM_LOSS_MAX - 1) + +/* State transition probablities for 4 state model */ +struct tc_netem_gimodel { + __u32 p13; + __u32 p31; + __u32 p32; + __u32 p14; + __u32 p23; +}; + +/* Gilbert-Elliot models */ +struct tc_netem_gemodel { + __u32 p; + __u32 r; + __u32 h; + __u32 k1; +}; + #define NETEM_DIST_SCALE 8192 +#define NETEM_DIST_MAX 16384 /* DRR */ @@ -481,4 +537,55 @@ struct tc_drr_stats { __u32 deficit; }; +/* MQPRIO */ +#define TC_QOPT_BITMASK 15 +#define TC_QOPT_MAX_QUEUE 16 + +struct tc_mqprio_qopt { + __u8 num_tc; + __u8 prio_tc_map[TC_QOPT_BITMASK + 1]; + __u8 hw; + __u16 count[TC_QOPT_MAX_QUEUE]; + __u16 offset[TC_QOPT_MAX_QUEUE]; +}; + +/* SFB */ + +enum { + TCA_SFB_UNSPEC, + TCA_SFB_PARMS, + __TCA_SFB_MAX, +}; + +#define TCA_SFB_MAX (__TCA_SFB_MAX - 1) + +/* + * Note: increment, decrement are Q0.16 fixed-point values. + */ +struct tc_sfb_qopt { + __u32 rehash_interval; /* delay between hash move, in ms */ + __u32 warmup_time; /* double buffering warmup time in ms (warmup_time < rehash_interval) */ + __u32 max; /* max len of qlen_min */ + __u32 bin_size; /* maximum queue length per bin */ + __u32 increment; /* probability increment, (d1 in Blue) */ + __u32 decrement; /* probability decrement, (d2 in Blue) */ + __u32 limit; /* max SFB queue length */ + __u32 penalty_rate; /* inelastic flows are rate limited to 'rate' pps */ + __u32 penalty_burst; +}; + +struct tc_sfb_xstats { + __u32 earlydrop; + __u32 penaltydrop; + __u32 bucketdrop; + __u32 queuedrop; + __u32 childdrop; /* drops in child qdisc */ + __u32 marked; + __u32 maxqlen; + __u32 maxprob; + __u32 avgprob; +}; + +#define SFB_MAX_PROB 0xFFFF + #endif diff --git a/include/linux/security.h b/include/linux/security.h index 83d9227..56cac52 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1626,7 +1626,7 @@ struct security_operations { int (*xfrm_policy_lookup) (struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir); int (*xfrm_state_pol_flow_match) (struct xfrm_state *x, struct xfrm_policy *xp, - struct flowi *fl); + const struct flowi *fl); int (*xfrm_decode_session) (struct sk_buff *skb, u32 *secid, int ckall); #endif /* CONFIG_SECURITY_NETWORK_XFRM */ @@ -2767,7 +2767,8 @@ int security_xfrm_state_delete(struct xfrm_state *x); void security_xfrm_state_free(struct xfrm_state *x); int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir); int security_xfrm_state_pol_flow_match(struct xfrm_state *x, - struct xfrm_policy *xp, struct flowi *fl); + struct xfrm_policy *xp, + const struct flowi *fl); int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid); void security_skb_classify_flow(struct sk_buff *skb, struct flowi *fl); @@ -2819,7 +2820,7 @@ static inline int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_s } static inline int security_xfrm_state_pol_flow_match(struct xfrm_state *x, - struct xfrm_policy *xp, struct flowi *fl) + struct xfrm_policy *xp, const struct flowi *fl) { return 1; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bf221d6..24cfa62 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -388,10 +388,7 @@ struct sk_buff { kmemcheck_bitfield_begin(flags2); __u16 queue_mapping:16; #ifdef CONFIG_IPV6_NDISC_NODETYPE - __u8 ndisc_nodetype:2, - deliver_no_wcard:1; -#else - __u8 deliver_no_wcard:1; + __u8 ndisc_nodetype:2; #endif __u8 ooo_okay:1; kmemcheck_bitfield_end(flags2); @@ -1801,6 +1798,15 @@ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) prefetch(skb->prev), (skb != (struct sk_buff *)(queue)); \ skb = skb->prev) +#define skb_queue_reverse_walk_safe(queue, skb, tmp) \ + for (skb = (queue)->prev, tmp = skb->prev; \ + skb != (struct sk_buff *)(queue); \ + skb = tmp, tmp = skb->prev) + +#define skb_queue_reverse_walk_from_safe(queue, skb, tmp) \ + for (tmp = skb->prev; \ + skb != (struct sk_buff *)(queue); \ + skb = tmp, tmp = skb->prev) static inline bool skb_has_frag_list(const struct sk_buff *skb) { @@ -1868,7 +1874,7 @@ extern void skb_split(struct sk_buff *skb, extern int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); -extern struct sk_buff *skb_segment(struct sk_buff *skb, int features); +extern struct sk_buff *skb_segment(struct sk_buff *skb, u32 features); static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) diff --git a/include/linux/sockios.h b/include/linux/sockios.h index 241f179..7997a50 100644 --- a/include/linux/sockios.h +++ b/include/linux/sockios.h @@ -22,7 +22,7 @@ /* Linux-specific socket ioctls */ #define SIOCINQ FIONREAD -#define SIOCOUTQ TIOCOUTQ +#define SIOCOUTQ TIOCOUTQ /* output queue size (not sent + not acked) */ /* Routing table calls. */ #define SIOCADDRT 0x890B /* add routing table entry */ @@ -83,6 +83,8 @@ #define SIOCWANDEV 0x894A /* get/set netdev parameters */ +#define SIOCOUTQNSD 0x894B /* output queue size (not sent only) */ + /* ARP cache control calls. */ /* 0x8950 - 0x8952 * obsolete calls, don't re-use */ #define SIOCDARP 0x8953 /* delete ARP table entry */ diff --git a/include/linux/ssb/ssb_regs.h b/include/linux/ssb/ssb_regs.h index 489f7b6..402955a 100644 --- a/include/linux/ssb/ssb_regs.h +++ b/include/linux/ssb/ssb_regs.h @@ -85,6 +85,8 @@ #define SSB_IMSTATE_AP_RSV 0x00000030 /* Reserved */ #define SSB_IMSTATE_IBE 0x00020000 /* In Band Error */ #define SSB_IMSTATE_TO 0x00040000 /* Timeout */ +#define SSB_IMSTATE_BUSY 0x01800000 /* Busy (Backplane rev >= 2.3 only) */ +#define SSB_IMSTATE_REJECT 0x02000000 /* Reject (Backplane rev >= 2.3 only) */ #define SSB_INTVEC 0x0F94 /* SB Interrupt Mask */ #define SSB_INTVEC_PCI 0x00000001 /* Enable interrupts for PCI */ #define SSB_INTVEC_ENET0 0x00000002 /* Enable interrupts for enet 0 */ @@ -97,7 +99,6 @@ #define SSB_TMSLOW_RESET 0x00000001 /* Reset */ #define SSB_TMSLOW_REJECT_22 0x00000002 /* Reject (Backplane rev 2.2) */ #define SSB_TMSLOW_REJECT_23 0x00000004 /* Reject (Backplane rev 2.3) */ -#define SSB_TMSLOW_PHYCLK 0x00000010 /* MAC PHY Clock Control Enable */ #define SSB_TMSLOW_CLOCK 0x00010000 /* Clock Enable */ #define SSB_TMSLOW_FGC 0x00020000 /* Force Gated Clocks On */ #define SSB_TMSLOW_PE 0x40000000 /* Power Management Enable */ @@ -268,6 +269,8 @@ /* SPROM Revision 4 */ #define SSB_SPROM4_BFLLO 0x0044 /* Boardflags (low 16 bits) */ #define SSB_SPROM4_BFLHI 0x0046 /* Board Flags Hi */ +#define SSB_SPROM4_BFL2LO 0x0048 /* Board flags 2 (low 16 bits) */ +#define SSB_SPROM4_BFL2HI 0x004A /* Board flags 2 Hi */ #define SSB_SPROM4_IL0MAC 0x004C /* 6 byte MAC address for a/b/g/n */ #define SSB_SPROM4_CCODE 0x0052 /* Country Code (2 bytes) */ #define SSB_SPROM4_GPIOA 0x0056 /* Gen. Purpose IO # 0 and 1 */ @@ -358,6 +361,8 @@ #define SSB_SPROM5_CCODE 0x0044 /* Country Code (2 bytes) */ #define SSB_SPROM5_BFLLO 0x004A /* Boardflags (low 16 bits) */ #define SSB_SPROM5_BFLHI 0x004C /* Board Flags Hi */ +#define SSB_SPROM5_BFL2LO 0x004E /* Board flags 2 (low 16 bits) */ +#define SSB_SPROM5_BFL2HI 0x0050 /* Board flags 2 Hi */ #define SSB_SPROM5_IL0MAC 0x0052 /* 6 byte MAC address for a/b/g/n */ #define SSB_SPROM5_GPIOA 0x0076 /* Gen. Purpose IO # 0 and 1 */ #define SSB_SPROM5_GPIOA_P0 0x00FF /* Pin 0 */ diff --git a/include/linux/tipc.h b/include/linux/tipc.h index 1eefa3f..a5b994a 100644 --- a/include/linux/tipc.h +++ b/include/linux/tipc.h @@ -2,7 +2,7 @@ * include/linux/tipc.h: Include file for TIPC socket interface * * Copyright (c) 2003-2006, Ericsson AB - * Copyright (c) 2005, Wind River Systems + * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -130,12 +130,6 @@ static inline unsigned int tipc_node(__u32 addr) #define TIPC_SUB_PORTS 0x01 /* filter for port availability */ #define TIPC_SUB_SERVICE 0x02 /* filter for service availability */ #define TIPC_SUB_CANCEL 0x04 /* cancel a subscription */ -#if 0 -/* The following filter options are not currently implemented */ -#define TIPC_SUB_NO_BIND_EVTS 0x04 /* filter out "publish" events */ -#define TIPC_SUB_NO_UNBIND_EVTS 0x08 /* filter out "withdraw" events */ -#define TIPC_SUB_SINGLE_EVT 0x10 /* expire after first event */ -#endif #define TIPC_WAIT_FOREVER (~0) /* timeout for permanent subscription */ diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h index 7d42460a..0db2395 100644 --- a/include/linux/tipc_config.h +++ b/include/linux/tipc_config.h @@ -2,7 +2,7 @@ * include/linux/tipc_config.h: Include file for TIPC configuration interface * * Copyright (c) 2003-2006, Ericsson AB - * Copyright (c) 2005-2007, Wind River Systems + * Copyright (c) 2005-2007, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -76,13 +76,6 @@ #define TIPC_CMD_SHOW_LINK_STATS 0x000B /* tx link_name, rx ultra_string */ #define TIPC_CMD_SHOW_STATS 0x000F /* tx unsigned, rx ultra_string */ -#if 0 -#define TIPC_CMD_SHOW_PORT_STATS 0x0008 /* tx port_ref, rx ultra_string */ -#define TIPC_CMD_RESET_PORT_STATS 0x0009 /* tx port_ref, rx none */ -#define TIPC_CMD_GET_ROUTES 0x000A /* tx ?, rx ? */ -#define TIPC_CMD_GET_LINK_PEER 0x000D /* tx link_name, rx ? */ -#endif - /* * Protected commands: * May only be issued by "network administration capable" process. @@ -96,7 +89,7 @@ #define TIPC_CMD_GET_MAX_SUBSCR 0x4006 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_ZONES 0x4007 /* obsoleted */ #define TIPC_CMD_GET_MAX_CLUSTERS 0x4008 /* obsoleted */ -#define TIPC_CMD_GET_MAX_NODES 0x4009 /* tx none, rx unsigned */ +#define TIPC_CMD_GET_MAX_NODES 0x4009 /* obsoleted */ #define TIPC_CMD_GET_MAX_SLAVES 0x400A /* obsoleted */ #define TIPC_CMD_GET_NETID 0x400B /* tx none, rx unsigned */ @@ -109,13 +102,6 @@ #define TIPC_CMD_DUMP_LOG 0x410B /* tx none, rx ultra_string */ #define TIPC_CMD_RESET_LINK_STATS 0x410C /* tx link_name, rx none */ -#if 0 -#define TIPC_CMD_CREATE_LINK 0x4103 /* tx link_create, rx none */ -#define TIPC_CMD_REMOVE_LINK 0x4104 /* tx link_name, rx none */ -#define TIPC_CMD_BLOCK_LINK 0x4105 /* tx link_name, rx none */ -#define TIPC_CMD_UNBLOCK_LINK 0x4106 /* tx link_name, rx none */ -#endif - /* * Private commands: * May only be issued by "network administration capable" process. @@ -123,16 +109,13 @@ */ #define TIPC_CMD_SET_NODE_ADDR 0x8001 /* tx net_addr, rx none */ -#if 0 -#define TIPC_CMD_SET_ZONE_MASTER 0x8002 /* tx none, rx none */ -#endif #define TIPC_CMD_SET_REMOTE_MNG 0x8003 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_PORTS 0x8004 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_PUBL 0x8005 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_SUBSCR 0x8006 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_ZONES 0x8007 /* obsoleted */ #define TIPC_CMD_SET_MAX_CLUSTERS 0x8008 /* obsoleted */ -#define TIPC_CMD_SET_MAX_NODES 0x8009 /* tx unsigned, rx none */ +#define TIPC_CMD_SET_MAX_NODES 0x8009 /* obsoleted */ #define TIPC_CMD_SET_MAX_SLAVES 0x800A /* obsoleted */ #define TIPC_CMD_SET_NETID 0x800B /* tx unsigned, rx none */ @@ -193,6 +176,10 @@ #define TIPC_DEF_LINK_TOL 1500 #define TIPC_MAX_LINK_TOL 30000 +#if (TIPC_MIN_LINK_TOL < 16) +#error "TIPC_MIN_LINK_TOL is too small (abort limit may be NaN)" +#endif + /* * Link window limits (min, default, max), in packets */ @@ -215,7 +202,7 @@ struct tipc_link_info { struct tipc_bearer_config { __be32 priority; /* Range [1,31]. Override per link */ - __be32 detect_scope; + __be32 disc_domain; /* <Z.C.N> describing desired nodes */ char name[TIPC_MAX_BEARER_NAME]; }; @@ -247,15 +234,6 @@ struct tipc_name_table_query { #define TIPC_CFG_NOT_SUPPORTED "\x84" /* request is not supported by TIPC */ #define TIPC_CFG_INVALID_VALUE "\x85" /* request has invalid argument value */ -#if 0 -/* prototypes TLV structures for proposed commands */ -struct tipc_link_create { - __u32 domain; - struct tipc_media_addr peer_addr; - char bearer_name[TIPC_MAX_BEARER_NAME]; -}; -#endif - /* * A TLV consists of a descriptor, followed by the TLV value. * TLV descriptor fields are stored in network byte order; diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index 930fdd2..22e61fd 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -84,6 +84,16 @@ struct xfrm_replay_state { __u32 bitmap; }; +struct xfrm_replay_state_esn { + unsigned int bmp_len; + __u32 oseq; + __u32 seq; + __u32 oseq_hi; + __u32 seq_hi; + __u32 replay_window; + __u32 bmp[0]; +}; + struct xfrm_algo { char alg_name[64]; unsigned int alg_key_len; /* in bits */ @@ -284,6 +294,7 @@ 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_MAX #define XFRMA_MAX (__XFRMA_MAX - 1) @@ -350,6 +361,8 @@ struct xfrm_usersa_info { #define XFRM_STATE_WILDRECV 8 #define XFRM_STATE_ICMP 16 #define XFRM_STATE_AF_UNSPEC 32 +#define XFRM_STATE_ALIGN4 64 +#define XFRM_STATE_ESN 128 }; struct xfrm_usersa_id { diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 0c5e725..4375043 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -64,6 +64,11 @@ struct bt_security { #define BT_DEFER_SETUP 7 +#define BT_FLUSHABLE 8 + +#define BT_FLUSHABLE_OFF 0 +#define BT_FLUSHABLE_ON 1 + #define BT_INFO(fmt, arg...) printk(KERN_INFO "Bluetooth: " fmt "\n" , ## arg) #define BT_ERR(fmt, arg...) printk(KERN_ERR "%s: " fmt "\n" , __func__ , ## arg) #define BT_DBG(fmt, arg...) pr_debug("%s: " fmt "\n" , __func__ , ## arg) @@ -200,4 +205,32 @@ extern void bt_sysfs_cleanup(void); extern struct dentry *bt_debugfs; +#ifdef CONFIG_BT_L2CAP +int l2cap_init(void); +void l2cap_exit(void); +#else +static inline int l2cap_init(void) +{ + return 0; +} + +static inline void l2cap_exit(void) +{ +} +#endif + +#ifdef CONFIG_BT_SCO +int sco_init(void); +void sco_exit(void); +#else +static inline int sco_init(void) +{ + return 0; +} + +static inline void sco_exit(void) +{ +} +#endif + #endif /* __BLUETOOTH_H */ diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 29a7a8c..ec6acf2 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -76,6 +76,14 @@ enum { HCI_INQUIRY, HCI_RAW, + + HCI_SETUP, + HCI_AUTO_OFF, + HCI_MGMT, + HCI_PAIRABLE, + HCI_SERVICE_CACHE, + HCI_LINK_KEYS, + HCI_DEBUG_KEYS, }; /* HCI ioctl defines */ @@ -111,6 +119,7 @@ enum { #define HCI_PAIRING_TIMEOUT (60000) /* 60 seconds */ #define HCI_IDLE_TIMEOUT (6000) /* 6 seconds */ #define HCI_INIT_TIMEOUT (10000) /* 10 seconds */ +#define HCI_CMD_TIMEOUT (1000) /* 1 seconds */ /* HCI data types */ #define HCI_COMMAND_PKT 0x01 @@ -150,6 +159,7 @@ enum { #define EDR_ESCO_MASK (ESCO_2EV3 | ESCO_3EV3 | ESCO_2EV5 | ESCO_3EV5) /* ACL flags */ +#define ACL_START_NO_FLUSH 0x00 #define ACL_CONT 0x01 #define ACL_START 0x02 #define ACL_ACTIVE_BCAST 0x04 @@ -159,6 +169,8 @@ enum { #define SCO_LINK 0x00 #define ACL_LINK 0x01 #define ESCO_LINK 0x02 +/* Low Energy links do not have defined link type. Use invented one */ +#define LE_LINK 0x80 /* LMP features */ #define LMP_3SLOT 0x01 @@ -183,17 +195,25 @@ enum { #define LMP_PSCHEME 0x02 #define LMP_PCONTROL 0x04 +#define LMP_RSSI_INQ 0x40 #define LMP_ESCO 0x80 #define LMP_EV4 0x01 #define LMP_EV5 0x02 +#define LMP_LE 0x40 #define LMP_SNIFF_SUBR 0x02 +#define LMP_PAUSE_ENC 0x04 #define LMP_EDR_ESCO_2M 0x20 #define LMP_EDR_ESCO_3M 0x40 #define LMP_EDR_3S_ESCO 0x80 +#define LMP_EXT_INQ 0x01 #define LMP_SIMPLE_PAIR 0x08 +#define LMP_NO_FLUSH 0x40 + +#define LMP_LSTO 0x01 +#define LMP_INQ_TX_PWR 0x02 /* Connection modes */ #define HCI_CM_ACTIVE 0x0000 @@ -225,6 +245,8 @@ enum { #define HCI_AT_GENERAL_BONDING_MITM 0x05 /* ----- HCI Commands ---- */ +#define HCI_OP_NOP 0x0000 + #define HCI_OP_INQUIRY 0x0401 struct hci_cp_inquiry { __u8 lap[3]; @@ -292,11 +314,19 @@ struct hci_cp_pin_code_reply { __u8 pin_len; __u8 pin_code[16]; } __packed; +struct hci_rp_pin_code_reply { + __u8 status; + bdaddr_t bdaddr; +} __packed; #define HCI_OP_PIN_CODE_NEG_REPLY 0x040e struct hci_cp_pin_code_neg_reply { bdaddr_t bdaddr; } __packed; +struct hci_rp_pin_code_neg_reply { + __u8 status; + bdaddr_t bdaddr; +} __packed; #define HCI_OP_CHANGE_CONN_PTYPE 0x040f struct hci_cp_change_conn_ptype { @@ -377,6 +407,31 @@ struct hci_cp_reject_sync_conn_req { __u8 reason; } __packed; +#define HCI_OP_IO_CAPABILITY_REPLY 0x042b +struct hci_cp_io_capability_reply { + bdaddr_t bdaddr; + __u8 capability; + __u8 oob_data; + __u8 authentication; +} __packed; + +#define HCI_OP_USER_CONFIRM_REPLY 0x042c +struct hci_cp_user_confirm_reply { + bdaddr_t bdaddr; +} __packed; +struct hci_rp_user_confirm_reply { + __u8 status; + bdaddr_t bdaddr; +} __packed; + +#define HCI_OP_USER_CONFIRM_NEG_REPLY 0x042d + +#define HCI_OP_IO_CAPABILITY_NEG_REPLY 0x0434 +struct hci_cp_io_capability_neg_reply { + bdaddr_t bdaddr; + __u8 reason; +} __packed; + #define HCI_OP_SNIFF_MODE 0x0803 struct hci_cp_sniff_mode { __le16 handle; @@ -474,6 +529,12 @@ struct hci_cp_set_event_flt { #define HCI_CONN_SETUP_AUTO_OFF 0x01 #define HCI_CONN_SETUP_AUTO_ON 0x02 +#define HCI_OP_DELETE_STORED_LINK_KEY 0x0c12 +struct hci_cp_delete_stored_link_key { + bdaddr_t bdaddr; + __u8 delete_all; +} __packed; + #define HCI_OP_WRITE_LOCAL_NAME 0x0c13 struct hci_cp_write_local_name { __u8 name[248]; @@ -537,6 +598,8 @@ struct hci_cp_host_buffer_size { __le16 sco_max_pkt; } __packed; +#define HCI_OP_WRITE_INQUIRY_MODE 0x0c45 + #define HCI_OP_READ_SSP_MODE 0x0c55 struct hci_rp_read_ssp_mode { __u8 status; @@ -548,6 +611,8 @@ struct hci_cp_write_ssp_mode { __u8 mode; } __packed; +#define HCI_OP_READ_INQ_RSP_TX_POWER 0x0c58 + #define HCI_OP_READ_LOCAL_VERSION 0x1001 struct hci_rp_read_local_version { __u8 status; @@ -593,6 +658,47 @@ struct hci_rp_read_bd_addr { bdaddr_t bdaddr; } __packed; +#define HCI_OP_LE_SET_EVENT_MASK 0x2001 +struct hci_cp_le_set_event_mask { + __u8 mask[8]; +} __packed; + +#define HCI_OP_LE_READ_BUFFER_SIZE 0x2002 +struct hci_rp_le_read_buffer_size { + __u8 status; + __le16 le_mtu; + __u8 le_max_pkt; +} __packed; + +#define HCI_OP_LE_CREATE_CONN 0x200d +struct hci_cp_le_create_conn { + __le16 scan_interval; + __le16 scan_window; + __u8 filter_policy; + __u8 peer_addr_type; + bdaddr_t peer_addr; + __u8 own_address_type; + __le16 conn_interval_min; + __le16 conn_interval_max; + __le16 conn_latency; + __le16 supervision_timeout; + __le16 min_ce_len; + __le16 max_ce_len; +} __packed; + +#define HCI_OP_LE_CREATE_CONN_CANCEL 0x200e + +#define HCI_OP_LE_CONN_UPDATE 0x2013 +struct hci_cp_le_conn_update { + __le16 handle; + __le16 conn_interval_min; + __le16 conn_interval_max; + __le16 conn_latency; + __le16 supervision_timeout; + __le16 min_ce_len; + __le16 max_ce_len; +} __packed; + /* ---- HCI Events ---- */ #define HCI_EV_INQUIRY_COMPLETE 0x01 @@ -833,6 +939,20 @@ struct hci_ev_io_capa_request { bdaddr_t bdaddr; } __packed; +#define HCI_EV_IO_CAPA_REPLY 0x32 +struct hci_ev_io_capa_reply { + bdaddr_t bdaddr; + __u8 capability; + __u8 oob_data; + __u8 authentication; +} __packed; + +#define HCI_EV_USER_CONFIRM_REQUEST 0x33 +struct hci_ev_user_confirm_req { + bdaddr_t bdaddr; + __le32 passkey; +} __packed; + #define HCI_EV_SIMPLE_PAIR_COMPLETE 0x36 struct hci_ev_simple_pair_complete { __u8 status; @@ -845,6 +965,25 @@ struct hci_ev_remote_host_features { __u8 features[8]; } __packed; +#define HCI_EV_LE_META 0x3e +struct hci_ev_le_meta { + __u8 subevent; +} __packed; + +/* Low energy meta events */ +#define HCI_EV_LE_CONN_COMPLETE 0x01 +struct hci_ev_le_conn_complete { + __u8 status; + __le16 handle; + __u8 role; + __u8 bdaddr_type; + bdaddr_t bdaddr; + __le16 interval; + __le16 latency; + __le16 supervision_timeout; + __u8 clk_accurancy; +} __packed; + /* Internal events generated by Bluetooth stack */ #define HCI_EV_STACK_INTERNAL 0xfd struct hci_ev_stack_internal { diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index d2cf884..441dadb 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -60,12 +60,28 @@ struct hci_conn_hash { spinlock_t lock; unsigned int acl_num; unsigned int sco_num; + unsigned int le_num; }; struct bdaddr_list { struct list_head list; bdaddr_t bdaddr; }; + +struct bt_uuid { + struct list_head list; + u8 uuid[16]; + u8 svc_hint; +}; + +struct link_key { + struct list_head list; + bdaddr_t bdaddr; + u8 type; + u8 val[16]; + u8 pin_len; +}; + #define NUM_REASSEMBLY 4 struct hci_dev { struct list_head list; @@ -80,13 +96,18 @@ struct hci_dev { bdaddr_t bdaddr; __u8 dev_name[248]; __u8 dev_class[3]; + __u8 major_class; + __u8 minor_class; __u8 features[8]; __u8 commands[64]; __u8 ssp_mode; __u8 hci_ver; __u16 hci_rev; + __u8 lmp_ver; __u16 manufacturer; + __le16 lmp_subver; __u16 voice_setting; + __u8 io_capability; __u16 pkt_type; __u16 esco_type; @@ -102,18 +123,26 @@ struct hci_dev { atomic_t cmd_cnt; unsigned int acl_cnt; unsigned int sco_cnt; + unsigned int le_cnt; unsigned int acl_mtu; unsigned int sco_mtu; + unsigned int le_mtu; unsigned int acl_pkts; unsigned int sco_pkts; + unsigned int le_pkts; - unsigned long cmd_last_tx; unsigned long acl_last_tx; unsigned long sco_last_tx; + unsigned long le_last_tx; struct workqueue_struct *workqueue; + struct work_struct power_on; + struct work_struct power_off; + struct timer_list off_timer; + + struct timer_list cmd_timer; struct tasklet_struct cmd_task; struct tasklet_struct rx_task; struct tasklet_struct tx_task; @@ -129,12 +158,17 @@ struct hci_dev { wait_queue_head_t req_wait_q; __u32 req_status; __u32 req_result; - __u16 req_last_cmd; + + __u16 init_last_cmd; struct inquiry_cache inq_cache; struct hci_conn_hash conn_hash; struct list_head blacklist; + struct list_head uuids; + + struct list_head link_keys; + struct hci_dev_stats stat; struct sk_buff_head driver_init; @@ -165,31 +199,37 @@ struct hci_dev { struct hci_conn { struct list_head list; - atomic_t refcnt; - spinlock_t lock; - - bdaddr_t dst; - __u16 handle; - __u16 state; - __u8 mode; - __u8 type; - __u8 out; - __u8 attempt; - __u8 dev_class[3]; - __u8 features[8]; - __u8 ssp_mode; - __u16 interval; - __u16 pkt_type; - __u16 link_policy; - __u32 link_mode; - __u8 auth_type; - __u8 sec_level; - __u8 pending_sec_level; - __u8 power_save; - __u16 disc_timeout; - unsigned long pend; - - unsigned int sent; + atomic_t refcnt; + spinlock_t lock; + + bdaddr_t dst; + __u16 handle; + __u16 state; + __u8 mode; + __u8 type; + __u8 out; + __u8 attempt; + __u8 dev_class[3]; + __u8 features[8]; + __u8 ssp_mode; + __u16 interval; + __u16 pkt_type; + __u16 link_policy; + __u32 link_mode; + __u8 auth_type; + __u8 sec_level; + __u8 pending_sec_level; + __u8 pin_length; + __u8 io_capability; + __u8 power_save; + __u16 disc_timeout; + unsigned long pend; + + __u8 remote_cap; + __u8 remote_oob; + __u8 remote_auth; + + unsigned int sent; struct sk_buff_head data_q; @@ -208,6 +248,10 @@ struct hci_conn { void *priv; struct hci_conn *link; + + void (*connect_cfm_cb) (struct hci_conn *conn, u8 status); + void (*security_cfm_cb) (struct hci_conn *conn, u8 status); + void (*disconn_cfm_cb) (struct hci_conn *conn, u8 reason); }; extern struct hci_proto *hci_proto[]; @@ -274,24 +318,40 @@ static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c) { struct hci_conn_hash *h = &hdev->conn_hash; list_add(&c->list, &h->list); - if (c->type == ACL_LINK) + switch (c->type) { + case ACL_LINK: h->acl_num++; - else + break; + case LE_LINK: + h->le_num++; + break; + case SCO_LINK: + case ESCO_LINK: h->sco_num++; + break; + } } static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c) { struct hci_conn_hash *h = &hdev->conn_hash; list_del(&c->list); - if (c->type == ACL_LINK) + switch (c->type) { + case ACL_LINK: h->acl_num--; - else + break; + case LE_LINK: + h->le_num--; + break; + case SCO_LINK: + case ESCO_LINK: h->sco_num--; + break; + } } static inline struct hci_conn *hci_conn_hash_lookup_handle(struct hci_dev *hdev, - __u16 handle) + __u16 handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct list_head *p; @@ -306,7 +366,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_handle(struct hci_dev *hdev, } static inline struct hci_conn *hci_conn_hash_lookup_ba(struct hci_dev *hdev, - __u8 type, bdaddr_t *ba) + __u8 type, bdaddr_t *ba) { struct hci_conn_hash *h = &hdev->conn_hash; struct list_head *p; @@ -321,7 +381,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_ba(struct hci_dev *hdev, } static inline struct hci_conn *hci_conn_hash_lookup_state(struct hci_dev *hdev, - __u8 type, __u16 state) + __u8 type, __u16 state) { struct hci_conn_hash *h = &hdev->conn_hash; struct list_head *p; @@ -437,6 +497,16 @@ int hci_inquiry(void __user *arg); struct bdaddr_list *hci_blacklist_lookup(struct hci_dev *hdev, bdaddr_t *bdaddr); int hci_blacklist_clear(struct hci_dev *hdev); +int hci_uuids_clear(struct hci_dev *hdev); + +int hci_link_keys_clear(struct hci_dev *hdev); +struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr); +int hci_add_link_key(struct hci_dev *hdev, int new_key, bdaddr_t *bdaddr, + u8 *key, u8 type, u8 pin_len); +int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr); + +void hci_del_off_timer(struct hci_dev *hdev); + void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb); int hci_recv_frame(struct sk_buff *skb); @@ -458,6 +528,8 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define lmp_sniffsubr_capable(dev) ((dev)->features[5] & LMP_SNIFF_SUBR) #define lmp_esco_capable(dev) ((dev)->features[3] & LMP_ESCO) #define lmp_ssp_capable(dev) ((dev)->features[6] & LMP_SIMPLE_PAIR) +#define lmp_no_flush_capable(dev) ((dev)->features[6] & LMP_NO_FLUSH) +#define lmp_le_capable(dev) ((dev)->features[4] & LMP_LE) /* ----- HCI protocols ----- */ struct hci_proto { @@ -503,6 +575,9 @@ static inline void hci_proto_connect_cfm(struct hci_conn *conn, __u8 status) hp = hci_proto[HCI_PROTO_SCO]; if (hp && hp->connect_cfm) hp->connect_cfm(conn, status); + + if (conn->connect_cfm_cb) + conn->connect_cfm_cb(conn, status); } static inline int hci_proto_disconn_ind(struct hci_conn *conn) @@ -532,6 +607,9 @@ static inline void hci_proto_disconn_cfm(struct hci_conn *conn, __u8 reason) hp = hci_proto[HCI_PROTO_SCO]; if (hp && hp->disconn_cfm) hp->disconn_cfm(conn, reason); + + if (conn->disconn_cfm_cb) + conn->disconn_cfm_cb(conn, reason); } static inline void hci_proto_auth_cfm(struct hci_conn *conn, __u8 status) @@ -551,6 +629,9 @@ static inline void hci_proto_auth_cfm(struct hci_conn *conn, __u8 status) hp = hci_proto[HCI_PROTO_SCO]; if (hp && hp->security_cfm) hp->security_cfm(conn, status, encrypt); + + if (conn->security_cfm_cb) + conn->security_cfm_cb(conn, status); } static inline void hci_proto_encrypt_cfm(struct hci_conn *conn, __u8 status, __u8 encrypt) @@ -564,6 +645,9 @@ static inline void hci_proto_encrypt_cfm(struct hci_conn *conn, __u8 status, __u hp = hci_proto[HCI_PROTO_SCO]; if (hp && hp->security_cfm) hp->security_cfm(conn, status, encrypt); + + if (conn->security_cfm_cb) + conn->security_cfm_cb(conn, status); } int hci_register_proto(struct hci_proto *hproto); @@ -660,12 +744,29 @@ void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode); void hci_si_event(struct hci_dev *hdev, int type, int dlen, void *data); /* ----- HCI Sockets ----- */ -void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb); +void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb, + struct sock *skip_sk); /* Management interface */ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t len); int mgmt_index_added(u16 index); int mgmt_index_removed(u16 index); +int mgmt_powered(u16 index, u8 powered); +int mgmt_discoverable(u16 index, u8 discoverable); +int mgmt_connectable(u16 index, u8 connectable); +int mgmt_new_key(u16 index, struct link_key *key, u8 old_key_type); +int mgmt_connected(u16 index, bdaddr_t *bdaddr); +int mgmt_disconnected(u16 index, bdaddr_t *bdaddr); +int mgmt_disconnect_failed(u16 index); +int mgmt_connect_failed(u16 index, bdaddr_t *bdaddr, u8 status); +int mgmt_pin_code_request(u16 index, bdaddr_t *bdaddr); +int mgmt_pin_code_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status); +int mgmt_pin_code_neg_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status); +int mgmt_user_confirm_request(u16 index, bdaddr_t *bdaddr, __le32 value); +int mgmt_user_confirm_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status); +int mgmt_user_confirm_neg_reply_complete(u16 index, bdaddr_t *bdaddr, + u8 status); +int mgmt_auth_failed(u16 index, bdaddr_t *bdaddr, u8 status); /* HCI info for socket */ #define hci_pi(sk) ((struct hci_pinfo *) sk) @@ -697,4 +798,6 @@ struct hci_sec_filter { void hci_req_complete(struct hci_dev *hdev, __u16 cmd, int result); +void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, + u16 latency, u16 to_multiplier); #endif /* __HCI_CORE_H */ diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 7ad25ca..4f4bff1 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -38,6 +38,7 @@ #define L2CAP_DEFAULT_MAX_PDU_SIZE 1009 /* Sized for 3-DH5 packet */ #define L2CAP_DEFAULT_ACK_TO 200 #define L2CAP_LOCAL_BUSY_TRIES 12 +#define L2CAP_LE_DEFAULT_MTU 23 #define L2CAP_CONN_TIMEOUT (40000) /* 40 seconds */ #define L2CAP_INFO_TIMEOUT (4000) /* 4 seconds */ @@ -88,6 +89,8 @@ struct l2cap_conninfo { #define L2CAP_ECHO_RSP 0x09 #define L2CAP_INFO_REQ 0x0a #define L2CAP_INFO_RSP 0x0b +#define L2CAP_CONN_PARAM_UPDATE_REQ 0x12 +#define L2CAP_CONN_PARAM_UPDATE_RSP 0x13 /* L2CAP feature mask */ #define L2CAP_FEAT_FLOWCTL 0x00000001 @@ -160,6 +163,9 @@ struct l2cap_conn_rsp { /* channel indentifier */ #define L2CAP_CID_SIGNALING 0x0001 #define L2CAP_CID_CONN_LESS 0x0002 +#define L2CAP_CID_LE_DATA 0x0004 +#define L2CAP_CID_LE_SIGNALING 0x0005 +#define L2CAP_CID_SMP 0x0006 #define L2CAP_CID_DYN_START 0x0040 #define L2CAP_CID_DYN_END 0xffff @@ -255,6 +261,21 @@ struct l2cap_info_rsp { #define L2CAP_IR_SUCCESS 0x0000 #define L2CAP_IR_NOTSUPP 0x0001 +struct l2cap_conn_param_update_req { + __le16 min; + __le16 max; + __le16 latency; + __le16 to_multiplier; +} __packed; + +struct l2cap_conn_param_update_rsp { + __le16 result; +} __packed; + +/* Connection Parameters result */ +#define L2CAP_CONN_PARAM_ACCEPTED 0x0000 +#define L2CAP_CONN_PARAM_REJECTED 0x0001 + /* ----- L2CAP connections ----- */ struct l2cap_chan_list { struct sock *head; @@ -327,6 +348,7 @@ struct l2cap_pinfo { __u8 sec_level; __u8 role_switch; __u8 force_reliable; + __u8 flushable; __u8 conf_req[64]; __u8 conf_len; @@ -423,6 +445,35 @@ static inline int l2cap_tx_window_full(struct sock *sk) #define __is_sframe(ctrl) ((ctrl) & L2CAP_CTRL_FRAME_TYPE) #define __is_sar_start(ctrl) (((ctrl) & L2CAP_CTRL_SAR) == L2CAP_SDU_START) -void l2cap_load(void); +extern int disable_ertm; +extern const struct proto_ops l2cap_sock_ops; +extern struct bt_sock_list l2cap_sk_list; + +int l2cap_init_sockets(void); +void l2cap_cleanup_sockets(void); + +u8 l2cap_get_ident(struct l2cap_conn *conn); +void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, void *data); +int l2cap_build_conf_req(struct sock *sk, void *data); +int __l2cap_wait_ack(struct sock *sk); + +struct sk_buff *l2cap_create_connless_pdu(struct sock *sk, struct msghdr *msg, size_t len); +struct sk_buff *l2cap_create_basic_pdu(struct sock *sk, struct msghdr *msg, size_t len); +struct sk_buff *l2cap_create_iframe_pdu(struct sock *sk, struct msghdr *msg, size_t len, u16 control, u16 sdulen); +int l2cap_sar_segment_sdu(struct sock *sk, struct msghdr *msg, size_t len); +void l2cap_do_send(struct sock *sk, struct sk_buff *skb); +void l2cap_streaming_send(struct sock *sk); +int l2cap_ertm_send(struct sock *sk); + +void l2cap_sock_set_timer(struct sock *sk, long timeout); +void l2cap_sock_clear_timer(struct sock *sk); +void __l2cap_sock_close(struct sock *sk, int reason); +void l2cap_sock_kill(struct sock *sk); +void l2cap_sock_init(struct sock *sk, struct sock *parent); +struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, + int proto, gfp_t prio); +void l2cap_send_disconn_req(struct l2cap_conn *conn, struct sock *sk, int err); +void l2cap_chan_del(struct sock *sk, int err); +int l2cap_do_connect(struct sock *sk); #endif /* __L2CAP_H */ diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index ca29c13..5fabfa8 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -21,11 +21,13 @@ SOFTWARE IS DISCLAIMED. */ +#define MGMT_INDEX_NONE 0xFFFF + struct mgmt_hdr { __le16 opcode; + __le16 index; __le16 len; } __packed; -#define MGMT_HDR_SIZE 4 #define MGMT_OP_READ_VERSION 0x0001 struct mgmt_rp_read_version { @@ -40,13 +42,10 @@ struct mgmt_rp_read_index_list { } __packed; #define MGMT_OP_READ_INFO 0x0004 -struct mgmt_cp_read_info { - __le16 index; -} __packed; struct mgmt_rp_read_info { - __le16 index; __u8 type; __u8 powered; + __u8 connectable; __u8 discoverable; __u8 pairable; __u8 sec_mode; @@ -58,6 +57,116 @@ struct mgmt_rp_read_info { __u16 hci_rev; } __packed; +struct mgmt_mode { + __u8 val; +} __packed; + +#define MGMT_OP_SET_POWERED 0x0005 + +#define MGMT_OP_SET_DISCOVERABLE 0x0006 + +#define MGMT_OP_SET_CONNECTABLE 0x0007 + +#define MGMT_OP_SET_PAIRABLE 0x0008 + +#define MGMT_OP_ADD_UUID 0x0009 +struct mgmt_cp_add_uuid { + __u8 uuid[16]; + __u8 svc_hint; +} __packed; + +#define MGMT_OP_REMOVE_UUID 0x000A +struct mgmt_cp_remove_uuid { + __u8 uuid[16]; +} __packed; + +#define MGMT_OP_SET_DEV_CLASS 0x000B +struct mgmt_cp_set_dev_class { + __u8 major; + __u8 minor; +} __packed; + +#define MGMT_OP_SET_SERVICE_CACHE 0x000C +struct mgmt_cp_set_service_cache { + __u8 enable; +} __packed; + +struct mgmt_key_info { + bdaddr_t bdaddr; + u8 type; + u8 val[16]; + u8 pin_len; +} __packed; + +#define MGMT_OP_LOAD_KEYS 0x000D +struct mgmt_cp_load_keys { + __u8 debug_keys; + __le16 key_count; + struct mgmt_key_info keys[0]; +} __packed; + +#define MGMT_OP_REMOVE_KEY 0x000E +struct mgmt_cp_remove_key { + bdaddr_t bdaddr; + __u8 disconnect; +} __packed; + +#define MGMT_OP_DISCONNECT 0x000F +struct mgmt_cp_disconnect { + bdaddr_t bdaddr; +} __packed; +struct mgmt_rp_disconnect { + bdaddr_t bdaddr; +} __packed; + +#define MGMT_OP_GET_CONNECTIONS 0x0010 +struct mgmt_rp_get_connections { + __le16 conn_count; + bdaddr_t conn[0]; +} __packed; + +#define MGMT_OP_PIN_CODE_REPLY 0x0011 +struct mgmt_cp_pin_code_reply { + bdaddr_t bdaddr; + __u8 pin_len; + __u8 pin_code[16]; +} __packed; +struct mgmt_rp_pin_code_reply { + bdaddr_t bdaddr; + uint8_t status; +} __packed; + +#define MGMT_OP_PIN_CODE_NEG_REPLY 0x0012 +struct mgmt_cp_pin_code_neg_reply { + bdaddr_t bdaddr; +} __packed; + +#define MGMT_OP_SET_IO_CAPABILITY 0x0013 +struct mgmt_cp_set_io_capability { + __u8 io_capability; +} __packed; + +#define MGMT_OP_PAIR_DEVICE 0x0014 +struct mgmt_cp_pair_device { + bdaddr_t bdaddr; + __u8 io_cap; +} __packed; +struct mgmt_rp_pair_device { + bdaddr_t bdaddr; + __u8 status; +} __packed; + +#define MGMT_OP_USER_CONFIRM_REPLY 0x0015 +struct mgmt_cp_user_confirm_reply { + bdaddr_t bdaddr; +} __packed; +struct mgmt_rp_user_confirm_reply { + bdaddr_t bdaddr; + __u8 status; +} __packed; + +#define MGMT_OP_USER_CONFIRM_NEG_REPLY 0x0016 + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; @@ -72,16 +181,56 @@ struct mgmt_ev_cmd_status { #define MGMT_EV_CONTROLLER_ERROR 0x0003 struct mgmt_ev_controller_error { - __le16 index; __u8 error_code; } __packed; #define MGMT_EV_INDEX_ADDED 0x0004 -struct mgmt_ev_index_added { - __le16 index; -} __packed; #define MGMT_EV_INDEX_REMOVED 0x0005 -struct mgmt_ev_index_removed { - __le16 index; + +#define MGMT_EV_POWERED 0x0006 + +#define MGMT_EV_DISCOVERABLE 0x0007 + +#define MGMT_EV_CONNECTABLE 0x0008 + +#define MGMT_EV_PAIRABLE 0x0009 + +#define MGMT_EV_NEW_KEY 0x000A +struct mgmt_ev_new_key { + struct mgmt_key_info key; + __u8 old_key_type; +} __packed; + +#define MGMT_EV_CONNECTED 0x000B +struct mgmt_ev_connected { + bdaddr_t bdaddr; +} __packed; + +#define MGMT_EV_DISCONNECTED 0x000C +struct mgmt_ev_disconnected { + bdaddr_t bdaddr; +} __packed; + +#define MGMT_EV_CONNECT_FAILED 0x000D +struct mgmt_ev_connect_failed { + bdaddr_t bdaddr; + __u8 status; +} __packed; + +#define MGMT_EV_PIN_CODE_REQUEST 0x000E +struct mgmt_ev_pin_code_request { + bdaddr_t bdaddr; +} __packed; + +#define MGMT_EV_USER_CONFIRM_REQUEST 0x000F +struct mgmt_ev_user_confirm_request { + bdaddr_t bdaddr; + __le32 value; +} __packed; + +#define MGMT_EV_AUTH_FAILED 0x0010 +struct mgmt_ev_auth_failed { + bdaddr_t bdaddr; + __u8 status; } __packed; diff --git a/include/net/bluetooth/smp.h b/include/net/bluetooth/smp.h new file mode 100644 index 0000000..8f2edbf --- /dev/null +++ b/include/net/bluetooth/smp.h @@ -0,0 +1,76 @@ +#ifndef __SMP_H +#define __SMP_H + +struct smp_command_hdr { + __u8 code; +} __packed; + +#define SMP_CMD_PAIRING_REQ 0x01 +#define SMP_CMD_PAIRING_RSP 0x02 +struct smp_cmd_pairing { + __u8 io_capability; + __u8 oob_flag; + __u8 auth_req; + __u8 max_key_size; + __u8 init_key_dist; + __u8 resp_key_dist; +} __packed; + +#define SMP_CMD_PAIRING_CONFIRM 0x03 +struct smp_cmd_pairing_confirm { + __u8 confirm_val[16]; +} __packed; + +#define SMP_CMD_PAIRING_RANDOM 0x04 +struct smp_cmd_pairing_random { + __u8 rand_val[16]; +} __packed; + +#define SMP_CMD_PAIRING_FAIL 0x05 +struct smp_cmd_pairing_fail { + __u8 reason; +} __packed; + +#define SMP_CMD_ENCRYPT_INFO 0x06 +struct smp_cmd_encrypt_info { + __u8 ltk[16]; +} __packed; + +#define SMP_CMD_MASTER_IDENT 0x07 +struct smp_cmd_master_ident { + __u16 ediv; + __u8 rand[8]; +} __packed; + +#define SMP_CMD_IDENT_INFO 0x08 +struct smp_cmd_ident_info { + __u8 irk[16]; +} __packed; + +#define SMP_CMD_IDENT_ADDR_INFO 0x09 +struct smp_cmd_ident_addr_info { + __u8 addr_type; + bdaddr_t bdaddr; +} __packed; + +#define SMP_CMD_SIGN_INFO 0x0a +struct smp_cmd_sign_info { + __u8 csrk[16]; +} __packed; + +#define SMP_CMD_SECURITY_REQ 0x0b +struct smp_cmd_security_req { + __u8 auth_req; +} __packed; + +#define SMP_PASSKEY_ENTRY_FAILED 0x01 +#define SMP_OOB_NOT_AVAIL 0x02 +#define SMP_AUTH_REQUIREMENTS 0x03 +#define SMP_CONFIRM_FAILED 0x04 +#define SMP_PAIRING_NOTSUPP 0x05 +#define SMP_ENC_KEY_SIZE 0x06 +#define SMP_CMD_NOTSUPP 0x07 +#define SMP_UNSPECIFIED 0x08 +#define SMP_REPEATED_ATTEMPTS 0x09 + +#endif /* __SMP_H */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 1322695..60f7876 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -413,7 +413,7 @@ struct station_parameters { * @STATION_INFO_PLID: @plid filled * @STATION_INFO_PLINK_STATE: @plink_state filled * @STATION_INFO_SIGNAL: @signal filled - * @STATION_INFO_TX_BITRATE: @tx_bitrate fields are filled + * @STATION_INFO_TX_BITRATE: @txrate fields are filled * (tx_bitrate, tx_bitrate_flags and tx_bitrate_mcs) * @STATION_INFO_RX_PACKETS: @rx_packets filled * @STATION_INFO_TX_PACKETS: @tx_packets filled @@ -421,6 +421,7 @@ struct station_parameters { * @STATION_INFO_TX_FAILED: @tx_failed filled * @STATION_INFO_RX_DROP_MISC: @rx_dropped_misc filled * @STATION_INFO_SIGNAL_AVG: @signal_avg filled + * @STATION_INFO_RX_BITRATE: @rxrate fields are filled */ enum station_info_flags { STATION_INFO_INACTIVE_TIME = 1<<0, @@ -437,6 +438,7 @@ enum station_info_flags { STATION_INFO_TX_FAILED = 1<<11, STATION_INFO_RX_DROP_MISC = 1<<12, STATION_INFO_SIGNAL_AVG = 1<<13, + STATION_INFO_RX_BITRATE = 1<<14, }; /** @@ -506,6 +508,7 @@ struct station_info { s8 signal; s8 signal_avg; struct rate_info txrate; + struct rate_info rxrate; u32 rx_packets; u32 tx_packets; u32 tx_retries; @@ -1194,6 +1197,10 @@ struct cfg80211_pmksa { * (also see nl80211.h @NL80211_ATTR_WIPHY_ANTENNA_TX). * * @get_antenna: Get current antenna configuration from device (tx_ant, rx_ant). + * + * @set_ringparam: Set tx and rx ring sizes. + * + * @get_ringparam: Get tx and rx ring current and maximum sizes. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy); @@ -1361,6 +1368,10 @@ struct cfg80211_ops { int (*set_antenna)(struct wiphy *wiphy, u32 tx_ant, u32 rx_ant); int (*get_antenna)(struct wiphy *wiphy, u32 *tx_ant, u32 *rx_ant); + + int (*set_ringparam)(struct wiphy *wiphy, u32 tx, u32 rx); + void (*get_ringparam)(struct wiphy *wiphy, + u32 *tx, u32 *tx_max, u32 *rx, u32 *rx_max); }; /* @@ -1790,8 +1801,9 @@ static inline void *wdev_priv(struct wireless_dev *wdev) /** * ieee80211_channel_to_frequency - convert channel number to frequency * @chan: channel number + * @band: band, necessary due to channel number overlap */ -extern int ieee80211_channel_to_frequency(int chan); +extern int ieee80211_channel_to_frequency(int chan, enum ieee80211_band band); /** * ieee80211_frequency_to_channel - convert frequency to channel number diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h index a8e7852..e5983c9 100644 --- a/include/net/dcbnl.h +++ b/include/net/dcbnl.h @@ -43,6 +43,8 @@ struct dcbnl_rtnl_ops { int (*ieee_setpfc) (struct net_device *, struct ieee_pfc *); int (*ieee_getapp) (struct net_device *, struct dcb_app *); int (*ieee_setapp) (struct net_device *, struct dcb_app *); + int (*ieee_peer_getets) (struct net_device *, struct ieee_ets *); + int (*ieee_peer_getpfc) (struct net_device *, struct ieee_pfc *); /* CEE std */ u8 (*getstate)(struct net_device *); @@ -77,7 +79,14 @@ struct dcbnl_rtnl_ops { u8 (*getdcbx)(struct net_device *); u8 (*setdcbx)(struct net_device *, u8); + /* peer apps */ + int (*peer_getappinfo)(struct net_device *, struct dcb_peer_app_info *, + u16 *); + int (*peer_getapptable)(struct net_device *, struct dcb_app *); + /* CEE peer */ + int (*cee_peer_getpg) (struct net_device *, struct cee_pg *); + int (*cee_peer_getpfc) (struct net_device *, struct cee_pfc *); }; #endif /* __NET_DCBNL_H__ */ diff --git a/include/net/dn.h b/include/net/dn.h index a514a3c..298521e 100644 --- a/include/net/dn.h +++ b/include/net/dn.h @@ -192,10 +192,10 @@ static inline void dn_dn2eth(unsigned char *ethaddr, __le16 addr) ethaddr[5] = (__u8)(a >> 8); } -static inline void dn_sk_ports_copy(struct flowi *fl, struct dn_scp *scp) +static inline void dn_sk_ports_copy(struct flowidn *fld, struct dn_scp *scp) { - fl->uli_u.dnports.sport = scp->addrloc; - fl->uli_u.dnports.dport = scp->addrrem; + fld->fld_sport = scp->addrloc; + fld->fld_dport = scp->addrrem; } extern unsigned dn_mss_from_pmtu(struct net_device *dev, int mtu); diff --git a/include/net/dn_fib.h b/include/net/dn_fib.h index bbcde32..782ef7c 100644 --- a/include/net/dn_fib.h +++ b/include/net/dn_fib.h @@ -98,7 +98,7 @@ struct dn_fib_table { int (*delete)(struct dn_fib_table *t, struct rtmsg *r, struct dn_kern_rta *rta, struct nlmsghdr *n, struct netlink_skb_parms *req); - int (*lookup)(struct dn_fib_table *t, const struct flowi *fl, + int (*lookup)(struct dn_fib_table *t, const struct flowidn *fld, struct dn_fib_res *res); int (*flush)(struct dn_fib_table *t); int (*dump)(struct dn_fib_table *t, struct sk_buff *skb, struct netlink_callback *cb); @@ -119,12 +119,12 @@ extern struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r, struct dn_kern_rta *rta, const struct nlmsghdr *nlh, int *errp); extern int dn_fib_semantic_match(int type, struct dn_fib_info *fi, - const struct flowi *fl, + const struct flowidn *fld, struct dn_fib_res *res); extern void dn_fib_release_info(struct dn_fib_info *fi); extern __le16 dn_fib_get_attr16(struct rtattr *attr, int attrlen, int type); extern void dn_fib_flush(void); -extern void dn_fib_select_multipath(const struct flowi *fl, +extern void dn_fib_select_multipath(const struct flowidn *fld, struct dn_fib_res *res); /* @@ -141,7 +141,7 @@ extern void dn_fib_table_cleanup(void); extern void dn_fib_rules_init(void); extern void dn_fib_rules_cleanup(void); extern unsigned dnet_addr_type(__le16 addr); -extern int dn_fib_lookup(struct flowi *fl, struct dn_fib_res *res); +extern int dn_fib_lookup(struct flowidn *fld, struct dn_fib_res *res); extern int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb); diff --git a/include/net/dn_route.h b/include/net/dn_route.h index 9b185df..81712cf 100644 --- a/include/net/dn_route.h +++ b/include/net/dn_route.h @@ -16,7 +16,7 @@ *******************************************************************************/ extern struct sk_buff *dn_alloc_skb(struct sock *sk, int size, gfp_t pri); -extern int dn_route_output_sock(struct dst_entry **pprt, struct flowi *, struct sock *sk, int flags); +extern int dn_route_output_sock(struct dst_entry **pprt, struct flowidn *, struct sock *sk, int flags); extern int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb); extern void dn_rt_cache_flush(int delay); @@ -67,7 +67,7 @@ extern void dn_rt_cache_flush(int delay); struct dn_route { struct dst_entry dst; - struct flowi fl; + struct flowidn fld; __le16 rt_saddr; __le16 rt_daddr; @@ -82,12 +82,12 @@ struct dn_route { static inline bool dn_is_input_route(struct dn_route *rt) { - return rt->fl.iif != 0; + return rt->fld.flowidn_iif != 0; } static inline bool dn_is_output_route(struct dn_route *rt) { - return rt->fl.iif == 0; + return rt->fld.flowidn_iif == 0; } extern void dn_route_init(void); diff --git a/include/net/dst.h b/include/net/dst.h index 93b0310..2a46cba 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -40,24 +40,10 @@ struct dst_entry { struct rcu_head rcu_head; struct dst_entry *child; struct net_device *dev; - short error; - short obsolete; - int flags; -#define DST_HOST 0x0001 -#define DST_NOXFRM 0x0002 -#define DST_NOPOLICY 0x0004 -#define DST_NOHASH 0x0008 -#define DST_NOCACHE 0x0010 + struct dst_ops *ops; + unsigned long _metrics; unsigned long expires; - - unsigned short header_len; /* more space at head required */ - unsigned short trailer_len; /* space to reserve at tail */ - - unsigned int rate_tokens; - unsigned long rate_last; /* rate limiting for ICMP */ - struct dst_entry *path; - struct neighbour *neighbour; struct hh_cache *hh; #ifdef CONFIG_XFRM @@ -68,17 +54,16 @@ struct dst_entry { int (*input)(struct sk_buff*); int (*output)(struct sk_buff*); - struct dst_ops *ops; - - u32 _metrics[RTAX_MAX]; - -#ifdef CONFIG_NET_CLS_ROUTE + short error; + short obsolete; + unsigned short header_len; /* more space at head required */ + unsigned short trailer_len; /* space to reserve at tail */ +#ifdef CONFIG_IP_ROUTE_CLASSID __u32 tclassid; #else __u32 __pad2; #endif - /* * Align __refcnt to a 64 bytes alignment * (L1_CACHE_SIZE would be too much) @@ -93,6 +78,12 @@ struct dst_entry { atomic_t __refcnt; /* client references */ int __use; unsigned long lastuse; + int flags; +#define DST_HOST 0x0001 +#define DST_NOXFRM 0x0002 +#define DST_NOPOLICY 0x0004 +#define DST_NOHASH 0x0008 +#define DST_NOCACHE 0x0010 union { struct dst_entry *next; struct rtable __rcu *rt_next; @@ -103,10 +94,70 @@ struct dst_entry { #ifdef __KERNEL__ +extern u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); +extern const u32 dst_default_metrics[RTAX_MAX]; + +#define DST_METRICS_READ_ONLY 0x1UL +#define __DST_METRICS_PTR(Y) \ + ((u32 *)((Y) & ~DST_METRICS_READ_ONLY)) +#define DST_METRICS_PTR(X) __DST_METRICS_PTR((X)->_metrics) + +static inline bool dst_metrics_read_only(const struct dst_entry *dst) +{ + return dst->_metrics & DST_METRICS_READ_ONLY; +} + +extern void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old); + +static inline void dst_destroy_metrics_generic(struct dst_entry *dst) +{ + unsigned long val = dst->_metrics; + if (!(val & DST_METRICS_READ_ONLY)) + __dst_destroy_metrics_generic(dst, val); +} + +static inline u32 *dst_metrics_write_ptr(struct dst_entry *dst) +{ + unsigned long p = dst->_metrics; + + if (p & DST_METRICS_READ_ONLY) + return dst->ops->cow_metrics(dst, p); + return __DST_METRICS_PTR(p); +} + +/* This may only be invoked before the entry has reached global + * visibility. + */ +static inline void dst_init_metrics(struct dst_entry *dst, + const u32 *src_metrics, + bool read_only) +{ + dst->_metrics = ((unsigned long) src_metrics) | + (read_only ? DST_METRICS_READ_ONLY : 0); +} + +static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src) +{ + u32 *dst_metrics = dst_metrics_write_ptr(dest); + + if (dst_metrics) { + u32 *src_metrics = DST_METRICS_PTR(src); + + memcpy(dst_metrics, src_metrics, RTAX_MAX * sizeof(u32)); + } +} + +static inline u32 *dst_metrics_ptr(struct dst_entry *dst) +{ + return DST_METRICS_PTR(dst); +} + static inline u32 dst_metric_raw(const struct dst_entry *dst, const int metric) { - return dst->_metrics[metric-1]; + u32 *p = DST_METRICS_PTR(dst); + + return p[metric-1]; } static inline u32 @@ -131,22 +182,10 @@ dst_metric_advmss(const struct dst_entry *dst) static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val) { - dst->_metrics[metric-1] = val; -} + u32 *p = dst_metrics_write_ptr(dst); -static inline void dst_import_metrics(struct dst_entry *dst, const u32 *src_metrics) -{ - memcpy(dst->_metrics, src_metrics, RTAX_MAX * sizeof(u32)); -} - -static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src) -{ - dst_import_metrics(dest, src->_metrics); -} - -static inline u32 *dst_metrics_ptr(struct dst_entry *dst) -{ - return dst->_metrics; + if (p) + p[metric-1] = val; } static inline u32 @@ -181,8 +220,6 @@ static inline u32 dst_allfrag(const struct dst_entry *dst) { int ret = dst_feature(dst, RTAX_FEATURE_ALLFRAG); - /* Yes, _exactly_. This is paranoia. */ - barrier(); return ret; } @@ -315,7 +352,7 @@ static inline struct dst_entry *skb_dst_pop(struct sk_buff *skb) } extern int dst_discard(struct sk_buff *skb); -extern void * dst_alloc(struct dst_ops * ops); +extern void *dst_alloc(struct dst_ops * ops, int initial_ref); extern void __dst_free(struct dst_entry * dst); extern struct dst_entry *dst_destroy(struct dst_entry * dst); @@ -384,27 +421,22 @@ extern void dst_init(void); /* Flags for xfrm_lookup flags argument. */ enum { - XFRM_LOOKUP_WAIT = 1 << 0, - XFRM_LOOKUP_ICMP = 1 << 1, + XFRM_LOOKUP_ICMP = 1 << 0, }; struct flowi; #ifndef CONFIG_XFRM -static inline int xfrm_lookup(struct net *net, struct dst_entry **dst_p, - struct flowi *fl, struct sock *sk, int flags) +static inline struct dst_entry *xfrm_lookup(struct net *net, + struct dst_entry *dst_orig, + const struct flowi *fl, struct sock *sk, + int flags) { - return 0; + return dst_orig; } -static inline int __xfrm_lookup(struct net *net, struct dst_entry **dst_p, - struct flowi *fl, struct sock *sk, int flags) -{ - return 0; -} #else -extern int xfrm_lookup(struct net *net, struct dst_entry **dst_p, - struct flowi *fl, struct sock *sk, int flags); -extern int __xfrm_lookup(struct net *net, struct dst_entry **dst_p, - struct flowi *fl, struct sock *sk, int flags); +extern struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, + const struct flowi *fl, struct sock *sk, + int flags); #endif #endif diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 21a320b..dc07463 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -18,6 +18,7 @@ struct dst_ops { struct dst_entry * (*check)(struct dst_entry *, __u32 cookie); unsigned int (*default_advmss)(const struct dst_entry *); unsigned int (*default_mtu)(const struct dst_entry *); + u32 * (*cow_metrics)(struct dst_entry *, unsigned long); void (*destroy)(struct dst_entry *); void (*ifdown)(struct dst_entry *, struct net_device *dev, int how); diff --git a/include/net/flow.h b/include/net/flow.h index 240b7f3..7fe5a0f 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -10,78 +10,136 @@ #include <linux/in6.h> #include <asm/atomic.h> -struct flowi { - int oif; - int iif; - __u32 mark; +struct flowi_common { + int flowic_oif; + int flowic_iif; + __u32 flowic_mark; + __u8 flowic_tos; + __u8 flowic_scope; + __u8 flowic_proto; + __u8 flowic_flags; +#define FLOWI_FLAG_ANYSRC 0x01 +#define FLOWI_FLAG_PRECOW_METRICS 0x02 +#define FLOWI_FLAG_CAN_SLEEP 0x04 + __u32 flowic_secid; +}; +union flowi_uli { + struct { + __be16 sport; + __be16 dport; + } ports; + + struct { + __u8 type; + __u8 code; + } icmpt; + + struct { + __le16 sport; + __le16 dport; + } dnports; + + __be32 spi; + __be32 gre_key; + + struct { + __u8 type; + } mht; +}; + +struct flowi4 { + struct flowi_common __fl_common; +#define flowi4_oif __fl_common.flowic_oif +#define flowi4_iif __fl_common.flowic_iif +#define flowi4_mark __fl_common.flowic_mark +#define flowi4_tos __fl_common.flowic_tos +#define flowi4_scope __fl_common.flowic_scope +#define flowi4_proto __fl_common.flowic_proto +#define flowi4_flags __fl_common.flowic_flags +#define flowi4_secid __fl_common.flowic_secid + __be32 daddr; + __be32 saddr; + union flowi_uli uli; +#define fl4_sport uli.ports.sport +#define fl4_dport uli.ports.dport +#define fl4_icmp_type uli.icmpt.type +#define fl4_icmp_code uli.icmpt.code +#define fl4_ipsec_spi uli.spi +#define fl4_mh_type uli.mht.type +#define fl4_gre_key uli.gre_key +}; + +struct flowi6 { + struct flowi_common __fl_common; +#define flowi6_oif __fl_common.flowic_oif +#define flowi6_iif __fl_common.flowic_iif +#define flowi6_mark __fl_common.flowic_mark +#define flowi6_tos __fl_common.flowic_tos +#define flowi6_scope __fl_common.flowic_scope +#define flowi6_proto __fl_common.flowic_proto +#define flowi6_flags __fl_common.flowic_flags +#define flowi6_secid __fl_common.flowic_secid + struct in6_addr daddr; + struct in6_addr saddr; + __be32 flowlabel; + union flowi_uli uli; +#define fl6_sport uli.ports.sport +#define fl6_dport uli.ports.dport +#define fl6_icmp_type uli.icmpt.type +#define fl6_icmp_code uli.icmpt.code +#define fl6_ipsec_spi uli.spi +#define fl6_mh_type uli.mht.type +#define fl6_gre_key uli.gre_key +}; + +struct flowidn { + struct flowi_common __fl_common; +#define flowidn_oif __fl_common.flowic_oif +#define flowidn_iif __fl_common.flowic_iif +#define flowidn_mark __fl_common.flowic_mark +#define flowidn_scope __fl_common.flowic_scope +#define flowidn_proto __fl_common.flowic_proto +#define flowidn_flags __fl_common.flowic_flags + __le16 daddr; + __le16 saddr; + union flowi_uli uli; +#define fld_sport uli.ports.sport +#define fld_dport uli.ports.dport +}; + +struct flowi { union { - struct { - __be32 daddr; - __be32 saddr; - __u8 tos; - __u8 scope; - } ip4_u; - - struct { - struct in6_addr daddr; - struct in6_addr saddr; - __be32 flowlabel; - } ip6_u; - - struct { - __le16 daddr; - __le16 saddr; - __u8 scope; - } dn_u; - } nl_u; -#define fld_dst nl_u.dn_u.daddr -#define fld_src nl_u.dn_u.saddr -#define fld_scope nl_u.dn_u.scope -#define fl6_dst nl_u.ip6_u.daddr -#define fl6_src nl_u.ip6_u.saddr -#define fl6_flowlabel nl_u.ip6_u.flowlabel -#define fl4_dst nl_u.ip4_u.daddr -#define fl4_src nl_u.ip4_u.saddr -#define fl4_tos nl_u.ip4_u.tos -#define fl4_scope nl_u.ip4_u.scope - - __u8 proto; - __u8 flags; -#define FLOWI_FLAG_ANYSRC 0x01 - union { - struct { - __be16 sport; - __be16 dport; - } ports; - - struct { - __u8 type; - __u8 code; - } icmpt; - - struct { - __le16 sport; - __le16 dport; - } dnports; - - __be32 spi; - __be32 gre_key; - - struct { - __u8 type; - } mht; - } uli_u; -#define fl_ip_sport uli_u.ports.sport -#define fl_ip_dport uli_u.ports.dport -#define fl_icmp_type uli_u.icmpt.type -#define fl_icmp_code uli_u.icmpt.code -#define fl_ipsec_spi uli_u.spi -#define fl_mh_type uli_u.mht.type -#define fl_gre_key uli_u.gre_key - __u32 secid; /* used by xfrm; see secid.txt */ + struct flowi_common __fl_common; + struct flowi4 ip4; + struct flowi6 ip6; + struct flowidn dn; + } u; +#define flowi_oif u.__fl_common.flowic_oif +#define flowi_iif u.__fl_common.flowic_iif +#define flowi_mark u.__fl_common.flowic_mark +#define flowi_tos u.__fl_common.flowic_tos +#define flowi_scope u.__fl_common.flowic_scope +#define flowi_proto u.__fl_common.flowic_proto +#define flowi_flags u.__fl_common.flowic_flags +#define flowi_secid u.__fl_common.flowic_secid } __attribute__((__aligned__(BITS_PER_LONG/8))); +static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4) +{ + return container_of(fl4, struct flowi, u.ip4); +} + +static inline struct flowi *flowi6_to_flowi(struct flowi6 *fl6) +{ + return container_of(fl6, struct flowi, u.ip6); +} + +static inline struct flowi *flowidn_to_flowi(struct flowidn *fldn) +{ + return container_of(fldn, struct flowi, u.dn); +} + #define FLOW_DIR_IN 0 #define FLOW_DIR_OUT 1 #define FLOW_DIR_FWD 2 @@ -101,20 +159,14 @@ struct flow_cache_ops { }; typedef struct flow_cache_object *(*flow_resolve_t)( - struct net *net, struct flowi *key, u16 family, + struct net *net, const struct flowi *key, u16 family, u8 dir, struct flow_cache_object *oldobj, void *ctx); extern struct flow_cache_object *flow_cache_lookup( - struct net *net, struct flowi *key, u16 family, + struct net *net, const struct flowi *key, u16 family, u8 dir, flow_resolve_t resolver, void *ctx); extern void flow_cache_flush(void); extern atomic_t flow_cache_genid; -static inline int flow_cache_uli_match(struct flowi *fl1, struct flowi *fl2) -{ - return (fl1->proto == fl2->proto && - !memcmp(&fl1->uli_u, &fl2->uli_u, sizeof(fl1->uli_u))); -} - #endif diff --git a/include/net/icmp.h b/include/net/icmp.h index 6e991e0..f0698b9 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -45,7 +45,4 @@ extern int icmp_ioctl(struct sock *sk, int cmd, unsigned long arg); extern int icmp_init(void); extern void icmp_out_count(struct net *net, unsigned char type); -/* Move into dst.h ? */ -extern int xrlim_allow(struct dst_entry *dst, int timeout); - #endif /* _ICMP_H */ diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index af49f8a..b0be5fb 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -178,6 +178,11 @@ struct ieee80211_radiotap_header { * * Number of unicast retries a transmitted frame used. * + * IEEE80211_RADIOTAP_MCS u8, u8, u8 unitless + * + * Contains a bitmap of known fields/flags, the flags, and + * the MCS index. + * */ enum ieee80211_radiotap_type { IEEE80211_RADIOTAP_TSFT = 0, @@ -199,6 +204,8 @@ enum ieee80211_radiotap_type { IEEE80211_RADIOTAP_RTS_RETRIES = 16, IEEE80211_RADIOTAP_DATA_RETRIES = 17, + IEEE80211_RADIOTAP_MCS = 19, + /* valid in every it_present bitmap, even vendor namespaces */ IEEE80211_RADIOTAP_RADIOTAP_NAMESPACE = 29, IEEE80211_RADIOTAP_VENDOR_NAMESPACE = 30, @@ -245,6 +252,24 @@ enum ieee80211_radiotap_type { #define IEEE80211_RADIOTAP_F_TX_CTS 0x0002 /* used cts 'protection' */ #define IEEE80211_RADIOTAP_F_TX_RTS 0x0004 /* used rts/cts handshake */ + +/* For IEEE80211_RADIOTAP_MCS */ +#define IEEE80211_RADIOTAP_MCS_HAVE_BW 0x01 +#define IEEE80211_RADIOTAP_MCS_HAVE_MCS 0x02 +#define IEEE80211_RADIOTAP_MCS_HAVE_GI 0x04 +#define IEEE80211_RADIOTAP_MCS_HAVE_FMT 0x08 +#define IEEE80211_RADIOTAP_MCS_HAVE_FEC 0x10 + +#define IEEE80211_RADIOTAP_MCS_BW_MASK 0x03 +#define IEEE80211_RADIOTAP_MCS_BW_20 0 +#define IEEE80211_RADIOTAP_MCS_BW_40 1 +#define IEEE80211_RADIOTAP_MCS_BW_20L 2 +#define IEEE80211_RADIOTAP_MCS_BW_20U 3 +#define IEEE80211_RADIOTAP_MCS_SGI 0x04 +#define IEEE80211_RADIOTAP_MCS_FMT_GF 0x08 +#define IEEE80211_RADIOTAP_MCS_FEC_LDPC 0x10 + + /* Ugly macro to convert literal channel numbers into their mhz equivalents * There are certianly some conditions that will break this (like feeding it '30') * but they shouldn't arise since nothing talks on channel 30. */ diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 8181498..7a37369 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -86,6 +86,19 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) return (struct inet_request_sock *)sk; } +struct inet_cork { + unsigned int flags; + unsigned int fragsize; + struct ip_options *opt; + struct dst_entry *dst; + int length; /* Total length of all frames */ + __be32 addr; + struct flowi fl; + struct page *page; + u32 off; + u8 tx_flags; +}; + struct ip_mc_socklist; struct ipv6_pinfo; struct rtable; @@ -143,15 +156,7 @@ struct inet_sock { int mc_index; __be32 mc_addr; struct ip_mc_socklist __rcu *mc_list; - struct { - unsigned int flags; - unsigned int fragsize; - struct ip_options *opt; - struct dst_entry *dst; - int length; /* Total length of all frames */ - __be32 addr; - struct flowi fl; - } cork; + struct inet_cork cork; }; #define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */ @@ -219,7 +224,13 @@ static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops static inline __u8 inet_sk_flowi_flags(const struct sock *sk) { - return inet_sk(sk)->transparent ? FLOWI_FLAG_ANYSRC : 0; + __u8 flags = 0; + + if (inet_sk(sk)->transparent) + flags |= FLOWI_FLAG_ANYSRC; + if (sk->sk_protocol == IPPROTO_TCP) + flags |= FLOWI_FLAG_PRECOW_METRICS; + return flags; } #endif /* _INET_SOCK_H */ diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 599d96e..e6dd8da6 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -11,15 +11,20 @@ #include <linux/init.h> #include <linux/jiffies.h> #include <linux/spinlock.h> +#include <linux/rtnetlink.h> #include <net/ipv6.h> #include <asm/atomic.h> -struct inetpeer_addr { +struct inetpeer_addr_base { union { - __be32 a4; - __be32 a6[4]; + __be32 a4; + __be32 a6[4]; }; - __u16 family; +}; + +struct inetpeer_addr { + struct inetpeer_addr_base addr; + __u16 family; }; struct inet_peer { @@ -33,15 +38,22 @@ struct inet_peer { atomic_t refcnt; /* * Once inet_peer is queued for deletion (refcnt == -1), following fields - * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp - * We can share memory with rcu_head to keep inet_peer small + * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp, metrics + * We can share memory with rcu_head to help keep inet_peer small. */ union { struct { - atomic_t rid; /* Frag reception counter */ - atomic_t ip_id_count; /* IP ID for the next packet */ - __u32 tcp_ts; - __u32 tcp_ts_stamp; + atomic_t rid; /* Frag reception counter */ + atomic_t ip_id_count; /* IP ID for the next packet */ + __u32 tcp_ts; + __u32 tcp_ts_stamp; + u32 metrics[RTAX_MAX]; + u32 rate_tokens; /* rate limiting for ICMP */ + unsigned long rate_last; + unsigned long pmtu_expires; + u32 pmtu_orig; + u32 pmtu_learned; + struct inetpeer_addr_base redirect_learned; }; struct rcu_head rcu; }; @@ -49,6 +61,13 @@ struct inet_peer { void inet_initpeers(void) __init; +#define INETPEER_METRICS_NEW (~(u32) 0) + +static inline bool inet_metrics_new(const struct inet_peer *p) +{ + return p->metrics[RTAX_LOCK-1] == INETPEER_METRICS_NEW; +} + /* can be called with or without local BH being disabled */ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create); @@ -56,7 +75,7 @@ static inline struct inet_peer *inet_getpeer_v4(__be32 v4daddr, int create) { struct inetpeer_addr daddr; - daddr.a4 = v4daddr; + daddr.addr.a4 = v4daddr; daddr.family = AF_INET; return inet_getpeer(&daddr, create); } @@ -65,13 +84,14 @@ static inline struct inet_peer *inet_getpeer_v6(struct in6_addr *v6daddr, int cr { struct inetpeer_addr daddr; - ipv6_addr_copy((struct in6_addr *)daddr.a6, v6daddr); + ipv6_addr_copy((struct in6_addr *)daddr.addr.a6, v6daddr); daddr.family = AF_INET6; return inet_getpeer(&daddr, create); } /* can be called from BH context or outside */ extern void inet_putpeer(struct inet_peer *p); +extern bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout); /* * temporary check to make sure we dont access rid, ip_id_count, tcp_ts, diff --git a/include/net/ip.h b/include/net/ip.h index 67fac78..a4f6311 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -116,8 +116,24 @@ extern int ip_append_data(struct sock *sk, extern int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb); extern ssize_t ip_append_page(struct sock *sk, struct page *page, int offset, size_t size, int flags); +extern struct sk_buff *__ip_make_skb(struct sock *sk, + struct sk_buff_head *queue, + struct inet_cork *cork); +extern int ip_send_skb(struct sk_buff *skb); extern int ip_push_pending_frames(struct sock *sk); extern void ip_flush_pending_frames(struct sock *sk); +extern struct sk_buff *ip_make_skb(struct sock *sk, + int getfrag(void *from, char *to, int offset, int len, + int odd, struct sk_buff *skb), + void *from, int length, int transhdrlen, + struct ipcm_cookie *ipc, + struct rtable **rtp, + unsigned int flags); + +static inline struct sk_buff *ip_finish_skb(struct sock *sk) +{ + return __ip_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork); +} /* datagram.c */ extern int ip4_datagram_connect(struct sock *sk, diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 708ff7c..bc3cde0 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -108,6 +108,7 @@ struct rt6_info { u32 rt6i_flags; struct rt6key rt6i_src; u32 rt6i_metric; + u32 rt6i_peer_genid; struct inet6_dev *rt6i_idev; struct inet_peer *rt6i_peer; @@ -182,7 +183,7 @@ struct fib6_table { typedef struct rt6_info *(*pol_lookup_t)(struct net *, struct fib6_table *, - struct flowi *, int); + struct flowi6 *, int); /* * exported functions @@ -191,7 +192,7 @@ typedef struct rt6_info *(*pol_lookup_t)(struct net *, extern struct fib6_table *fib6_get_table(struct net *net, u32 id); extern struct fib6_table *fib6_new_table(struct net *net, u32 id); extern struct dst_entry *fib6_rule_lookup(struct net *net, - struct flowi *fl, int flags, + struct flowi6 *fl6, int flags, pol_lookup_t lookup); extern struct fib6_node *fib6_lookup(struct fib6_node *root, diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 8552f0a..642a80b 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -71,7 +71,7 @@ extern void ip6_route_input(struct sk_buff *skb); extern struct dst_entry * ip6_route_output(struct net *net, struct sock *sk, - struct flowi *fl); + struct flowi6 *fl6); extern int ip6_route_init(void); extern void ip6_route_cleanup(void); diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 07bdb5e..a1a8580 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -51,15 +51,17 @@ struct fib_nh { struct fib_info *nh_parent; unsigned nh_flags; unsigned char nh_scope; + unsigned char nh_cfg_scope; #ifdef CONFIG_IP_ROUTE_MULTIPATH int nh_weight; int nh_power; #endif -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID __u32 nh_tclassid; #endif int nh_oif; __be32 nh_gw; + __be32 nh_saddr; }; /* @@ -77,7 +79,7 @@ struct fib_info { int fib_protocol; __be32 fib_prefsrc; u32 fib_priority; - u32 fib_metrics[RTAX_MAX]; + u32 *fib_metrics; #define fib_mtu fib_metrics[RTAX_MTU-1] #define fib_window fib_metrics[RTAX_WINDOW-1] #define fib_rtt fib_metrics[RTAX_RTT-1] @@ -96,12 +98,15 @@ struct fib_info { struct fib_rule; #endif +struct fib_table; struct fib_result { unsigned char prefixlen; unsigned char nh_sel; unsigned char type; unsigned char scope; struct fib_info *fi; + struct fib_table *table; + struct list_head *fa_head; #ifdef CONFIG_IP_MULTIPLE_TABLES struct fib_rule *r; #endif @@ -136,11 +141,13 @@ struct fib_result_nl { #endif /* CONFIG_IP_ROUTE_MULTIPATH */ -#define FIB_RES_PREFSRC(res) ((res).fi->fib_prefsrc ? : __fib_res_prefsrc(&res)) +#define FIB_RES_SADDR(res) (FIB_RES_NH(res).nh_saddr) #define FIB_RES_GW(res) (FIB_RES_NH(res).nh_gw) #define FIB_RES_DEV(res) (FIB_RES_NH(res).nh_dev) #define FIB_RES_OIF(res) (FIB_RES_NH(res).nh_oif) +#define FIB_RES_PREFSRC(res) ((res).fi->fib_prefsrc ? : FIB_RES_SADDR(res)) + struct fib_table { struct hlist_node tb_hlist; u32 tb_id; @@ -148,16 +155,13 @@ struct fib_table { unsigned char tb_data[0]; }; -extern int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, +extern int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags); extern int fib_table_insert(struct fib_table *, struct fib_config *); extern int fib_table_delete(struct fib_table *, struct fib_config *); extern int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb); extern int fib_table_flush(struct fib_table *table); -extern void fib_table_select_default(struct fib_table *table, - const struct flowi *flp, - struct fib_result *res); extern void fib_free_table(struct fib_table *tb); @@ -182,7 +186,7 @@ static inline struct fib_table *fib_new_table(struct net *net, u32 id) return fib_get_table(net, id); } -static inline int fib_lookup(struct net *net, const struct flowi *flp, +static inline int fib_lookup(struct net *net, const struct flowi4 *flp, struct fib_result *res) { struct fib_table *table; @@ -201,11 +205,11 @@ static inline int fib_lookup(struct net *net, const struct flowi *flp, extern int __net_init fib4_rules_init(struct net *net); extern void __net_exit fib4_rules_exit(struct net *net); -#ifdef CONFIG_NET_CLS_ROUTE -extern u32 fib_rules_tclass(struct fib_result *res); +#ifdef CONFIG_IP_ROUTE_CLASSID +extern u32 fib_rules_tclass(const struct fib_result *res); #endif -extern int fib_lookup(struct net *n, struct flowi *flp, struct fib_result *res); +extern int fib_lookup(struct net *n, struct flowi4 *flp, struct fib_result *res); extern struct fib_table *fib_new_table(struct net *net, u32 id); extern struct fib_table *fib_get_table(struct net *net, u32 id); @@ -218,24 +222,23 @@ extern void ip_fib_init(void); extern int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, __be32 *spec_dst, u32 *itag, u32 mark); -extern void fib_select_default(struct net *net, const struct flowi *flp, - struct fib_result *res); +extern void fib_select_default(struct fib_result *res); /* Exported by fib_semantics.c */ extern int ip_fib_check_default(__be32 gw, struct net_device *dev); extern int fib_sync_down_dev(struct net_device *dev, int force); extern int fib_sync_down_addr(struct net *net, __be32 local); +extern void fib_update_nh_saddrs(struct net_device *dev); extern int fib_sync_up(struct net_device *dev); -extern __be32 __fib_res_prefsrc(struct fib_result *res); -extern void fib_select_multipath(const struct flowi *flp, struct fib_result *res); +extern void fib_select_multipath(struct fib_result *res); -/* Exported by fib_{hash|trie}.c */ -extern void fib_hash_init(void); -extern struct fib_table *fib_hash_table(u32 id); +/* Exported by fib_trie.c */ +extern void fib_trie_init(void); +extern struct fib_table *fib_trie_table(u32 id); -static inline void fib_combine_itag(u32 *itag, struct fib_result *res) +static inline void fib_combine_itag(u32 *itag, const struct fib_result *res) { -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID #ifdef CONFIG_IP_MULTIPLE_TABLES u32 rtag; #endif diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index b7bbd6c..272f593 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -28,6 +28,80 @@ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) #include <net/netfilter/nf_conntrack.h> #endif +#include <net/net_namespace.h> /* Netw namespace */ + +/* + * Generic access of ipvs struct + */ +static inline struct netns_ipvs *net_ipvs(struct net* net) +{ + return net->ipvs; +} +/* + * Get net ptr from skb in traffic cases + * use skb_sknet when call is from userland (ioctl or netlink) + */ +static inline struct net *skb_net(const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_NS +#ifdef CONFIG_IP_VS_DEBUG + /* + * This is used for debug only. + * Start with the most likely hit + * End with BUG + */ + if (likely(skb->dev && skb->dev->nd_net)) + return dev_net(skb->dev); + if (skb_dst(skb)->dev) + return dev_net(skb_dst(skb)->dev); + WARN(skb->sk, "Maybe skb_sknet should be used in %s() at line:%d\n", + __func__, __LINE__); + if (likely(skb->sk && skb->sk->sk_net)) + return sock_net(skb->sk); + pr_err("There is no net ptr to find in the skb in %s() line:%d\n", + __func__, __LINE__); + BUG(); +#else + return dev_net(skb->dev ? : skb_dst(skb)->dev); +#endif +#else + return &init_net; +#endif +} + +static inline struct net *skb_sknet(const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_NS +#ifdef CONFIG_IP_VS_DEBUG + /* Start with the most likely hit */ + if (likely(skb->sk && skb->sk->sk_net)) + return sock_net(skb->sk); + WARN(skb->dev, "Maybe skb_net should be used instead in %s() line:%d\n", + __func__, __LINE__); + if (likely(skb->dev && skb->dev->nd_net)) + return dev_net(skb->dev); + pr_err("There is no net ptr to find in the skb in %s() line:%d\n", + __func__, __LINE__); + BUG(); +#else + return sock_net(skb->sk); +#endif +#else + return &init_net; +#endif +} +/* + * This one needed for single_open_net since net is stored directly in + * private not as a struct i.e. seq_file_net cant be used. + */ +static inline struct net *seq_file_single_net(struct seq_file *seq) +{ +#ifdef CONFIG_NET_NS + return (struct net *)seq->private; +#else + return &init_net; +#endif +} /* Connections' size value needed by ip_vs_ctl.c */ extern int ip_vs_conn_tab_size; @@ -258,6 +332,23 @@ struct ip_vs_seq { before last resized pkt */ }; +/* + * counters per cpu + */ +struct ip_vs_counters { + __u32 conns; /* connections scheduled */ + __u32 inpkts; /* incoming packets */ + __u32 outpkts; /* outgoing packets */ + __u64 inbytes; /* incoming bytes */ + __u64 outbytes; /* outgoing bytes */ +}; +/* + * Stats per cpu + */ +struct ip_vs_cpu_stats { + struct ip_vs_counters ustats; + struct u64_stats_sync syncp; +}; /* * IPVS statistics objects @@ -279,10 +370,11 @@ struct ip_vs_estimator { }; struct ip_vs_stats { - struct ip_vs_stats_user ustats; /* statistics */ + struct ip_vs_stats_user ustats; /* statistics */ struct ip_vs_estimator est; /* estimator */ - - spinlock_t lock; /* spin lock */ + struct ip_vs_cpu_stats *cpustats; /* per cpu counters */ + spinlock_t lock; /* spin lock */ + struct ip_vs_stats_user ustats0; /* reset values */ }; struct dst_entry; @@ -290,6 +382,7 @@ struct iphdr; struct ip_vs_conn; struct ip_vs_app; struct sk_buff; +struct ip_vs_proto_data; struct ip_vs_protocol { struct ip_vs_protocol *next; @@ -297,21 +390,22 @@ struct ip_vs_protocol { u16 protocol; u16 num_states; int dont_defrag; - atomic_t appcnt; /* counter of proto app incs */ - int *timeout_table; /* protocol timeout table */ void (*init)(struct ip_vs_protocol *pp); void (*exit)(struct ip_vs_protocol *pp); + void (*init_netns)(struct net *net, struct ip_vs_proto_data *pd); + + void (*exit_netns)(struct net *net, struct ip_vs_proto_data *pd); + int (*conn_schedule)(int af, struct sk_buff *skb, - struct ip_vs_protocol *pp, + struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp); struct ip_vs_conn * (*conn_in_get)(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -319,7 +413,6 @@ struct ip_vs_protocol { struct ip_vs_conn * (*conn_out_get)(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -337,11 +430,11 @@ struct ip_vs_protocol { int (*state_transition)(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_protocol *pp); + struct ip_vs_proto_data *pd); - int (*register_app)(struct ip_vs_app *inc); + int (*register_app)(struct net *net, struct ip_vs_app *inc); - void (*unregister_app)(struct ip_vs_app *inc); + void (*unregister_app)(struct net *net, struct ip_vs_app *inc); int (*app_conn_bind)(struct ip_vs_conn *cp); @@ -350,14 +443,26 @@ struct ip_vs_protocol { int offset, const char *msg); - void (*timeout_change)(struct ip_vs_protocol *pp, int flags); + void (*timeout_change)(struct ip_vs_proto_data *pd, int flags); +}; - int (*set_state_timeout)(struct ip_vs_protocol *pp, char *sname, int to); +/* + * protocol data per netns + */ +struct ip_vs_proto_data { + struct ip_vs_proto_data *next; + struct ip_vs_protocol *pp; + int *timeout_table; /* protocol timeout table */ + atomic_t appcnt; /* counter of proto app incs. */ + struct tcp_states_t *tcp_state_table; }; -extern struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto); +extern struct ip_vs_protocol *ip_vs_proto_get(unsigned short proto); +extern struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net, + unsigned short proto); struct ip_vs_conn_param { + struct net *net; const union nf_inet_addr *caddr; const union nf_inet_addr *vaddr; __be16 cport; @@ -374,17 +479,20 @@ struct ip_vs_conn_param { * IP_VS structure allocated for each dynamically scheduled connection */ struct ip_vs_conn { - struct list_head c_list; /* hashed list heads */ - + struct hlist_node c_list; /* hashed list heads */ +#ifdef CONFIG_NET_NS + struct net *net; /* Name space */ +#endif /* Protocol, addresses and port numbers */ - u16 af; /* address family */ - union nf_inet_addr caddr; /* client address */ - union nf_inet_addr vaddr; /* virtual address */ - union nf_inet_addr daddr; /* destination address */ - volatile __u32 flags; /* status flags */ - __be16 cport; - __be16 vport; - __be16 dport; + u16 af; /* address family */ + __be16 cport; + __be16 vport; + __be16 dport; + __u32 fwmark; /* Fire wall mark from skb */ + union nf_inet_addr caddr; /* client address */ + union nf_inet_addr vaddr; /* virtual address */ + union nf_inet_addr daddr; /* destination address */ + volatile __u32 flags; /* status flags */ __u16 protocol; /* Which protocol (TCP/UDP) */ /* counter and timer */ @@ -422,10 +530,38 @@ struct ip_vs_conn { struct ip_vs_seq in_seq; /* incoming seq. struct */ struct ip_vs_seq out_seq; /* outgoing seq. struct */ + const struct ip_vs_pe *pe; char *pe_data; __u8 pe_data_len; }; +/* + * To save some memory in conn table when name space is disabled. + */ +static inline struct net *ip_vs_conn_net(const struct ip_vs_conn *cp) +{ +#ifdef CONFIG_NET_NS + return cp->net; +#else + return &init_net; +#endif +} +static inline void ip_vs_conn_net_set(struct ip_vs_conn *cp, struct net *net) +{ +#ifdef CONFIG_NET_NS + cp->net = net; +#endif +} + +static inline int ip_vs_conn_net_eq(const struct ip_vs_conn *cp, + struct net *net) +{ +#ifdef CONFIG_NET_NS + return cp->net == net; +#else + return 1; +#endif +} /* * Extended internal versions of struct ip_vs_service_user and @@ -485,6 +621,7 @@ struct ip_vs_service { unsigned flags; /* service status flags */ unsigned timeout; /* persistent timeout in ticks */ __be32 netmask; /* grouping granularity */ + struct net *net; struct list_head destinations; /* real server d-linked list */ __u32 num_dests; /* number of servers */ @@ -510,8 +647,8 @@ struct ip_vs_dest { struct list_head d_list; /* for table with all the dests */ u16 af; /* address family */ - union nf_inet_addr addr; /* IP address of the server */ __be16 port; /* port number of the server */ + union nf_inet_addr addr; /* IP address of the server */ volatile unsigned flags; /* dest status flags */ atomic_t conn_flags; /* flags to copy to conn */ atomic_t weight; /* server weight */ @@ -538,8 +675,8 @@ struct ip_vs_dest { /* for virtual service */ struct ip_vs_service *svc; /* service it belongs to */ __u16 protocol; /* which protocol (TCP/UDP) */ - union nf_inet_addr vaddr; /* virtual IP address */ __be16 vport; /* virtual port number */ + union nf_inet_addr vaddr; /* virtual IP address */ __u32 vfwmark; /* firewall mark of service */ }; @@ -651,6 +788,171 @@ struct ip_vs_app { void (*timeout_change)(struct ip_vs_app *app, int flags); }; +/* IPVS in network namespace */ +struct netns_ipvs { + int gen; /* Generation */ + /* + * Hash table: for real service lookups + */ + #define IP_VS_RTAB_BITS 4 + #define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS) + #define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1) + + struct list_head rs_table[IP_VS_RTAB_SIZE]; + /* ip_vs_app */ + struct list_head app_list; + struct mutex app_mutex; + struct lock_class_key app_key; /* mutex debuging */ + + /* ip_vs_proto */ + #define IP_VS_PROTO_TAB_SIZE 32 /* must be power of 2 */ + struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE]; + /* ip_vs_proto_tcp */ +#ifdef CONFIG_IP_VS_PROTO_TCP + #define TCP_APP_TAB_BITS 4 + #define TCP_APP_TAB_SIZE (1 << TCP_APP_TAB_BITS) + #define TCP_APP_TAB_MASK (TCP_APP_TAB_SIZE - 1) + struct list_head tcp_apps[TCP_APP_TAB_SIZE]; + spinlock_t tcp_app_lock; +#endif + /* ip_vs_proto_udp */ +#ifdef CONFIG_IP_VS_PROTO_UDP + #define UDP_APP_TAB_BITS 4 + #define UDP_APP_TAB_SIZE (1 << UDP_APP_TAB_BITS) + #define UDP_APP_TAB_MASK (UDP_APP_TAB_SIZE - 1) + struct list_head udp_apps[UDP_APP_TAB_SIZE]; + spinlock_t udp_app_lock; +#endif + /* ip_vs_proto_sctp */ +#ifdef CONFIG_IP_VS_PROTO_SCTP + #define SCTP_APP_TAB_BITS 4 + #define SCTP_APP_TAB_SIZE (1 << SCTP_APP_TAB_BITS) + #define SCTP_APP_TAB_MASK (SCTP_APP_TAB_SIZE - 1) + /* Hash table for SCTP application incarnations */ + struct list_head sctp_apps[SCTP_APP_TAB_SIZE]; + spinlock_t sctp_app_lock; +#endif + /* ip_vs_conn */ + atomic_t conn_count; /* connection counter */ + + /* ip_vs_ctl */ + struct ip_vs_stats tot_stats; /* Statistics & est. */ + + int num_services; /* no of virtual services */ + + rwlock_t rs_lock; /* real services table */ + /* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */ + struct lock_class_key ctl_key; /* ctl_mutex debuging */ + /* Trash for destinations */ + struct list_head dest_trash; + /* Service counters */ + atomic_t ftpsvc_counter; + atomic_t nullsvc_counter; + +#ifdef CONFIG_SYSCTL + /* 1/rate drop and drop-entry variables */ + struct delayed_work defense_work; /* Work handler */ + int drop_rate; + int drop_counter; + atomic_t dropentry; + /* locks in ctl.c */ + spinlock_t dropentry_lock; /* drop entry handling */ + spinlock_t droppacket_lock; /* drop packet handling */ + spinlock_t securetcp_lock; /* state and timeout tables */ + + /* sys-ctl struct */ + struct ctl_table_header *sysctl_hdr; + struct ctl_table *sysctl_tbl; +#endif + + /* sysctl variables */ + int sysctl_amemthresh; + int sysctl_am_droprate; + int sysctl_drop_entry; + int sysctl_drop_packet; + int sysctl_secure_tcp; +#ifdef CONFIG_IP_VS_NFCT + int sysctl_conntrack; +#endif + int sysctl_snat_reroute; + int sysctl_sync_ver; + int sysctl_cache_bypass; + int sysctl_expire_nodest_conn; + int sysctl_expire_quiescent_template; + int sysctl_sync_threshold[2]; + int sysctl_nat_icmp_send; + + /* ip_vs_lblc */ + int sysctl_lblc_expiration; + struct ctl_table_header *lblc_ctl_header; + struct ctl_table *lblc_ctl_table; + /* ip_vs_lblcr */ + int sysctl_lblcr_expiration; + struct ctl_table_header *lblcr_ctl_header; + struct ctl_table *lblcr_ctl_table; + /* ip_vs_est */ + struct list_head est_list; /* estimator list */ + spinlock_t est_lock; + struct timer_list est_timer; /* Estimation timer */ + /* ip_vs_sync */ + struct list_head sync_queue; + spinlock_t sync_lock; + struct ip_vs_sync_buff *sync_buff; + spinlock_t sync_buff_lock; + struct sockaddr_in sync_mcast_addr; + struct task_struct *master_thread; + struct task_struct *backup_thread; + int send_mesg_maxlen; + int recv_mesg_maxlen; + volatile int sync_state; + volatile int master_syncid; + volatile int backup_syncid; + /* multicast interface name */ + char master_mcast_ifn[IP_VS_IFNAME_MAXLEN]; + char backup_mcast_ifn[IP_VS_IFNAME_MAXLEN]; + /* net name space ptr */ + struct net *net; /* Needed by timer routines */ +}; + +#define DEFAULT_SYNC_THRESHOLD 3 +#define DEFAULT_SYNC_PERIOD 50 +#define DEFAULT_SYNC_VER 1 + +#ifdef CONFIG_SYSCTL + +static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_sync_threshold[0]; +} + +static inline int sysctl_sync_period(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_sync_threshold[1]; +} + +static inline int sysctl_sync_ver(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_sync_ver; +} + +#else + +static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) +{ + return DEFAULT_SYNC_THRESHOLD; +} + +static inline int sysctl_sync_period(struct netns_ipvs *ipvs) +{ + return DEFAULT_SYNC_PERIOD; +} + +static inline int sysctl_sync_ver(struct netns_ipvs *ipvs) +{ + return DEFAULT_SYNC_VER; +} + +#endif /* * IPVS core functions @@ -674,13 +976,14 @@ enum { IP_VS_DIR_LAST, }; -static inline void ip_vs_conn_fill_param(int af, int protocol, +static inline void ip_vs_conn_fill_param(struct net *net, int af, int protocol, const union nf_inet_addr *caddr, __be16 cport, const union nf_inet_addr *vaddr, __be16 vport, struct ip_vs_conn_param *p) { + p->net = net; p->af = af; p->protocol = protocol; p->caddr = caddr; @@ -695,7 +998,6 @@ struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p); struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p); struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -703,7 +1005,6 @@ struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p); struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -719,14 +1020,14 @@ extern void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport); struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p, const union nf_inet_addr *daddr, __be16 dport, unsigned flags, - struct ip_vs_dest *dest); + struct ip_vs_dest *dest, __u32 fwmark); extern void ip_vs_conn_expire_now(struct ip_vs_conn *cp); extern const char * ip_vs_state_name(__u16 proto, int state); -extern void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp); +extern void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp); extern int ip_vs_check_template(struct ip_vs_conn *ct); -extern void ip_vs_random_dropentry(void); +extern void ip_vs_random_dropentry(struct net *net); extern int ip_vs_conn_init(void); extern void ip_vs_conn_cleanup(void); @@ -796,12 +1097,12 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) * (from ip_vs_app.c) */ #define IP_VS_APP_MAX_PORTS 8 -extern int register_ip_vs_app(struct ip_vs_app *app); -extern void unregister_ip_vs_app(struct ip_vs_app *app); +extern int register_ip_vs_app(struct net *net, struct ip_vs_app *app); +extern void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app); extern int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp); extern void ip_vs_unbind_app(struct ip_vs_conn *cp); -extern int -register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port); +extern int register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, + __u16 proto, __u16 port); extern int ip_vs_app_inc_get(struct ip_vs_app *inc); extern void ip_vs_app_inc_put(struct ip_vs_app *inc); @@ -814,15 +1115,27 @@ void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe); void ip_vs_unbind_pe(struct ip_vs_service *svc); int register_ip_vs_pe(struct ip_vs_pe *pe); int unregister_ip_vs_pe(struct ip_vs_pe *pe); -extern struct ip_vs_pe *ip_vs_pe_get(const char *name); -extern void ip_vs_pe_put(struct ip_vs_pe *pe); +struct ip_vs_pe *ip_vs_pe_getbyname(const char *name); +struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name); + +static inline void ip_vs_pe_get(const struct ip_vs_pe *pe) +{ + if (pe && pe->module) + __module_get(pe->module); +} + +static inline void ip_vs_pe_put(const struct ip_vs_pe *pe) +{ + if (pe && pe->module) + module_put(pe->module); +} /* * IPVS protocol functions (from ip_vs_proto.c) */ extern int ip_vs_protocol_init(void); extern void ip_vs_protocol_cleanup(void); -extern void ip_vs_protocol_timeout_change(int flags); +extern void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags); extern int *ip_vs_create_timeout_table(int *table, int size); extern int ip_vs_set_state_timeout(int *table, int num, const char *const *names, @@ -852,26 +1165,23 @@ extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name); extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler); extern struct ip_vs_conn * ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, - struct ip_vs_protocol *pp, int *ignored); + struct ip_vs_proto_data *pd, int *ignored); extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, - struct ip_vs_protocol *pp); + struct ip_vs_proto_data *pd); + +extern void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg); /* * IPVS control data and functions (from ip_vs_ctl.c) */ -extern int sysctl_ip_vs_cache_bypass; -extern int sysctl_ip_vs_expire_nodest_conn; -extern int sysctl_ip_vs_expire_quiescent_template; -extern int sysctl_ip_vs_sync_threshold[2]; -extern int sysctl_ip_vs_nat_icmp_send; -extern int sysctl_ip_vs_conntrack; -extern int sysctl_ip_vs_snat_reroute; extern struct ip_vs_stats ip_vs_stats; extern const struct ctl_path net_vs_ctl_path[]; +extern int sysctl_ip_vs_sync_ver; +extern void ip_vs_sync_switch_mode(struct net *net, int mode); extern struct ip_vs_service * -ip_vs_service_get(int af, __u32 fwmark, __u16 protocol, +ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport); static inline void ip_vs_service_put(struct ip_vs_service *svc) @@ -880,7 +1190,7 @@ static inline void ip_vs_service_put(struct ip_vs_service *svc) } extern struct ip_vs_dest * -ip_vs_lookup_real_service(int af, __u16 protocol, +ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport); extern int ip_vs_use_count_inc(void); @@ -888,8 +1198,9 @@ extern void ip_vs_use_count_dec(void); extern int ip_vs_control_init(void); extern void ip_vs_control_cleanup(void); extern struct ip_vs_dest * -ip_vs_find_dest(int af, const union nf_inet_addr *daddr, __be16 dport, - const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol); +ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr, + __be16 dport, const union nf_inet_addr *vaddr, __be16 vport, + __u16 protocol, __u32 fwmark); extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp); @@ -897,14 +1208,12 @@ extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp); * IPVS sync daemon data and function prototypes * (from ip_vs_sync.c) */ -extern volatile int ip_vs_sync_state; -extern volatile int ip_vs_master_syncid; -extern volatile int ip_vs_backup_syncid; -extern char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN]; -extern char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN]; -extern int start_sync_thread(int state, char *mcast_ifn, __u8 syncid); -extern int stop_sync_thread(int state); -extern void ip_vs_sync_conn(struct ip_vs_conn *cp); +extern int start_sync_thread(struct net *net, int state, char *mcast_ifn, + __u8 syncid); +extern int stop_sync_thread(struct net *net, int state); +extern void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp); +extern int ip_vs_sync_init(void); +extern void ip_vs_sync_cleanup(void); /* @@ -912,9 +1221,11 @@ extern void ip_vs_sync_conn(struct ip_vs_conn *cp); */ extern int ip_vs_estimator_init(void); extern void ip_vs_estimator_cleanup(void); -extern void ip_vs_new_estimator(struct ip_vs_stats *stats); -extern void ip_vs_kill_estimator(struct ip_vs_stats *stats); +extern void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats); +extern void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats); extern void ip_vs_zero_estimator(struct ip_vs_stats *stats); +extern void ip_vs_read_estimator(struct ip_vs_stats_user *dst, + struct ip_vs_stats *stats); /* * Various IPVS packet transmitters (from ip_vs_xmit.c) @@ -947,21 +1258,25 @@ extern int ip_vs_icmp_xmit_v6 int offset); #endif +#ifdef CONFIG_SYSCTL /* * This is a simple mechanism to ignore packets when * we are loaded. Just set ip_vs_drop_rate to 'n' and * we start to drop 1/rate of the packets */ -extern int ip_vs_drop_rate; -extern int ip_vs_drop_counter; -static __inline__ int ip_vs_todrop(void) +static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { - if (!ip_vs_drop_rate) return 0; - if (--ip_vs_drop_counter > 0) return 0; - ip_vs_drop_counter = ip_vs_drop_rate; + if (!ipvs->drop_rate) + return 0; + if (--ipvs->drop_counter > 0) + return 0; + ipvs->drop_counter = ipvs->drop_rate; return 1; } +#else +static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { return 0; } +#endif /* * ip_vs_fwd_tag returns the forwarding tag of the connection @@ -1031,7 +1346,7 @@ static inline void ip_vs_notrack(struct sk_buff *skb) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) enum ip_conntrack_info ctinfo; - struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo); + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); if (!ct || !nf_ct_is_untracked(ct)) { nf_reset(skb); @@ -1047,9 +1362,13 @@ static inline void ip_vs_notrack(struct sk_buff *skb) * Netfilter connection tracking * (from ip_vs_nfct.c) */ -static inline int ip_vs_conntrack_enabled(void) +static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs) { - return sysctl_ip_vs_conntrack; +#ifdef CONFIG_SYSCTL + return ipvs->sysctl_conntrack; +#else + return 0; +#endif } extern void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, @@ -1062,7 +1381,7 @@ extern void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp); #else -static inline int ip_vs_conntrack_enabled(void) +static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs) { return 0; } @@ -1084,6 +1403,20 @@ static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp) /* CONFIG_IP_VS_NFCT */ #endif +static inline unsigned int +ip_vs_dest_conn_overhead(struct ip_vs_dest *dest) +{ + /* + * We think the overhead of processing active connections is 256 + * times higher than that of inactive connections in average. (This + * 256 times might not be accurate, we will change it later) We + * use the following formula to estimate the overhead now: + * dest->activeconns*256 + dest->inactconns + */ + return (atomic_read(&dest->activeconns) << 8) + + atomic_read(&dest->inactconns); +} + #endif /* __KERNEL__ */ #endif /* _NET_IP_VS_H */ diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 96e50e0..34200f9 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -492,7 +492,7 @@ extern int ip6_rcv_finish(struct sk_buff *skb); */ extern int ip6_xmit(struct sock *sk, struct sk_buff *skb, - struct flowi *fl, + struct flowi6 *fl6, struct ipv6_txoptions *opt); extern int ip6_nd_hdr(struct sock *sk, @@ -512,7 +512,7 @@ extern int ip6_append_data(struct sock *sk, int hlimit, int tclass, struct ipv6_txoptions *opt, - struct flowi *fl, + struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags, int dontfrag); @@ -523,13 +523,17 @@ extern void ip6_flush_pending_frames(struct sock *sk); extern int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, - struct flowi *fl); -extern int ip6_dst_blackhole(struct sock *sk, - struct dst_entry **dst, - struct flowi *fl); -extern int ip6_sk_dst_lookup(struct sock *sk, - struct dst_entry **dst, - struct flowi *fl); + struct flowi6 *fl6); +extern struct dst_entry * ip6_dst_lookup_flow(struct sock *sk, + struct flowi6 *fl6, + const struct in6_addr *final_dst, + bool can_sleep); +extern struct dst_entry * ip6_sk_dst_lookup_flow(struct sock *sk, + struct flowi6 *fl6, + const struct in6_addr *final_dst, + bool can_sleep); +extern struct dst_entry * ip6_blackhole_route(struct net *net, + struct dst_entry *orig_dst); /* * skb processing functions @@ -562,7 +566,7 @@ extern int ipv6_ext_hdr(u8 nexthdr); extern int ipv6_find_tlv(struct sk_buff *skb, int offset, int type); -extern struct in6_addr *fl6_update_dst(struct flowi *fl, +extern struct in6_addr *fl6_update_dst(struct flowi6 *fl6, const struct ipv6_txoptions *opt, struct in6_addr *orig); @@ -596,8 +600,8 @@ extern int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len); extern int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len); extern void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); -extern void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info); -extern void ipv6_local_rxpmtu(struct sock *sk, struct flowi *fl, u32 mtu); +extern void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info); +extern void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu); extern int inet6_release(struct socket *sock); extern int inet6_bind(struct socket *sock, struct sockaddr *uaddr, diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 62c0ce2..8650e7b 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -341,6 +341,9 @@ struct ieee80211_bss_conf { * the off-channel channel when a remain-on-channel offload is done * in hardware -- normal packets still flow and are expected to be * handled properly by the device. + * @IEEE80211_TX_INTFL_TKIP_MIC_FAILURE: Marks this packet to be used for TKIP + * testing. It will be sent out with incorrect Michael MIC key to allow + * TKIP countermeasures to be tested. * * Note: If you have to add new flags to the enumeration, then don't * forget to update %IEEE80211_TX_TEMPORARY_FLAGS when necessary. @@ -370,6 +373,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTL_LDPC = BIT(22), IEEE80211_TX_CTL_STBC = BIT(23) | BIT(24), IEEE80211_TX_CTL_TX_OFFCHAN = BIT(25), + IEEE80211_TX_INTFL_TKIP_MIC_FAILURE = BIT(26), }; #define IEEE80211_TX_CTL_STBC_SHIFT 23 @@ -595,9 +599,10 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * the frame. * @RX_FLAG_FAILED_PLCP_CRC: Set this flag if the PCLP check failed on * the frame. - * @RX_FLAG_TSFT: The timestamp passed in the RX status (@mactime field) - * is valid. This is useful in monitor mode and necessary for beacon frames - * to enable IBSS merging. + * @RX_FLAG_MACTIME_MPDU: The timestamp passed in the RX status (@mactime + * field) is valid and contains the time the first symbol of the MPDU + * was received. This is useful in monitor mode and for proper IBSS + * merging. * @RX_FLAG_SHORTPRE: Short preamble was used for this frame * @RX_FLAG_HT: HT MCS was used and rate_idx is MCS index * @RX_FLAG_40MHZ: HT40 (40 MHz) was used @@ -610,7 +615,7 @@ enum mac80211_rx_flags { RX_FLAG_IV_STRIPPED = 1<<4, RX_FLAG_FAILED_FCS_CRC = 1<<5, RX_FLAG_FAILED_PLCP_CRC = 1<<6, - RX_FLAG_TSFT = 1<<7, + RX_FLAG_MACTIME_MPDU = 1<<7, RX_FLAG_SHORTPRE = 1<<8, RX_FLAG_HT = 1<<9, RX_FLAG_40MHZ = 1<<10, @@ -1069,6 +1074,13 @@ enum ieee80211_tkip_key_type { * to decrypt group addressed frames, then IBSS RSN support is still * possible but software crypto will be used. Advertise the wiphy flag * only in that case. + * + * @IEEE80211_HW_AP_LINK_PS: When operating in AP mode the device + * autonomously manages the PS status of connected stations. When + * this flag is set mac80211 will not trigger PS mode for connected + * stations based on the PM bit of incoming frames. + * Use ieee80211_start_ps()/ieee8021_end_ps() to manually configure + * the PS mode of connected stations. */ enum ieee80211_hw_flags { IEEE80211_HW_HAS_RATE_CONTROL = 1<<0, @@ -1093,6 +1105,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_CONNECTION_MONITOR = 1<<19, IEEE80211_HW_SUPPORTS_CQM_RSSI = 1<<20, IEEE80211_HW_SUPPORTS_PER_STA_GTK = 1<<21, + IEEE80211_HW_AP_LINK_PS = 1<<22, }; /** @@ -1147,6 +1160,17 @@ enum ieee80211_hw_flags { * @napi_weight: weight used for NAPI polling. You must specify an * appropriate value here if a napi_poll operation is provided * by your driver. + + * @max_rx_aggregation_subframes: maximum buffer size (number of + * sub-frames) to be used for A-MPDU block ack receiver + * aggregation. + * This is only relevant if the device has restrictions on the + * number of subframes, if it relies on mac80211 to do reordering + * it shouldn't be set. + * + * @max_tx_aggregation_subframes: maximum number of subframes in an + * aggregate an HT driver will transmit, used by the peer as a + * hint to size its reorder buffer. */ struct ieee80211_hw { struct ieee80211_conf conf; @@ -1165,6 +1189,8 @@ struct ieee80211_hw { u8 max_rates; u8 max_report_rates; u8 max_rate_tries; + u8 max_rx_aggregation_subframes; + u8 max_tx_aggregation_subframes; }; /** @@ -1688,7 +1714,9 @@ enum ieee80211_ampdu_mlme_action { * station, AP, IBSS/WDS/mesh peer etc. This callback can sleep. * * @sta_notify: Notifies low level driver about power state transition of an - * associated station, AP, IBSS/WDS/mesh peer etc. Must be atomic. + * associated station, AP, IBSS/WDS/mesh peer etc. For a VIF operating + * in AP mode, this callback will not be called when the flag + * %IEEE80211_HW_AP_LINK_PS is set. Must be atomic. * * @conf_tx: Configure TX queue parameters (EDCF (aifs, cw_min, cw_max), * bursting) for a hardware TX queue. @@ -1723,6 +1751,10 @@ enum ieee80211_ampdu_mlme_action { * ieee80211_ampdu_mlme_action. Starting sequence number (@ssn) * is the first frame we expect to perform the action on. Notice * that TX/RX_STOP can pass NULL for this parameter. + * The @buf_size parameter is only valid when the action is set to + * %IEEE80211_AMPDU_TX_OPERATIONAL and indicates the peer's reorder + * buffer size (number of subframes) for this session -- aggregates + * containing more subframes than this may not be transmitted to the peer. * Returns a negative error code on failure. * The callback can sleep. * @@ -1767,9 +1799,18 @@ enum ieee80211_ampdu_mlme_action { * ieee80211_remain_on_channel_expired(). This callback may sleep. * @cancel_remain_on_channel: Requests that an ongoing off-channel period is * aborted before it expires. This callback may sleep. + * @offchannel_tx: Transmit frame on another channel, wait for a response + * and return. Reliable TX status must be reported for the frame. If the + * return value is 1, then the @remain_on_channel will be used with a + * regular transmission (if supported.) + * @offchannel_tx_cancel_wait: cancel wait associated with offchannel TX + * + * @set_ringparam: Set tx and rx ring sizes. + * + * @get_ringparam: Get tx and rx ring current and maximum sizes. */ struct ieee80211_ops { - int (*tx)(struct ieee80211_hw *hw, struct sk_buff *skb); + void (*tx)(struct ieee80211_hw *hw, struct sk_buff *skb); int (*start)(struct ieee80211_hw *hw); void (*stop)(struct ieee80211_hw *hw); int (*add_interface)(struct ieee80211_hw *hw, @@ -1825,7 +1866,8 @@ struct ieee80211_ops { int (*ampdu_action)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn); + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size); int (*get_survey)(struct ieee80211_hw *hw, int idx, struct survey_info *survey); void (*rfkill_poll)(struct ieee80211_hw *hw); @@ -1845,6 +1887,14 @@ struct ieee80211_ops { enum nl80211_channel_type channel_type, int duration); int (*cancel_remain_on_channel)(struct ieee80211_hw *hw); + int (*offchannel_tx)(struct ieee80211_hw *hw, struct sk_buff *skb, + struct ieee80211_channel *chan, + enum nl80211_channel_type channel_type, + unsigned int wait); + int (*offchannel_tx_cancel_wait)(struct ieee80211_hw *hw); + int (*set_ringparam)(struct ieee80211_hw *hw, u32 tx, u32 rx); + void (*get_ringparam)(struct ieee80211_hw *hw, + u32 *tx, u32 *tx_max, u32 *rx, u32 *rx_max); }; /** @@ -2113,6 +2163,48 @@ static inline void ieee80211_rx_ni(struct ieee80211_hw *hw, local_bh_enable(); } +/** + * ieee80211_sta_ps_transition - PS transition for connected sta + * + * When operating in AP mode with the %IEEE80211_HW_AP_LINK_PS + * flag set, use this function to inform mac80211 about a connected station + * entering/leaving PS mode. + * + * This function may not be called in IRQ context or with softirqs enabled. + * + * Calls to this function for a single hardware must be synchronized against + * each other. + * + * The function returns -EINVAL when the requested PS mode is already set. + * + * @sta: currently connected sta + * @start: start or stop PS + */ +int ieee80211_sta_ps_transition(struct ieee80211_sta *sta, bool start); + +/** + * ieee80211_sta_ps_transition_ni - PS transition for connected sta + * (in process context) + * + * Like ieee80211_sta_ps_transition() but can be called in process context + * (internally disables bottom halves). Concurrent call restriction still + * applies. + * + * @sta: currently connected sta + * @start: start or stop PS + */ +static inline int ieee80211_sta_ps_transition_ni(struct ieee80211_sta *sta, + bool start) +{ + int ret; + + local_bh_disable(); + ret = ieee80211_sta_ps_transition(sta, start); + local_bh_enable(); + + return ret; +} + /* * The TX headroom reserved by mac80211 for its own tx_status functions. * This is enough for the radiotap header. diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 1bf812b..3ae4919 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -27,6 +27,7 @@ struct sock; struct ctl_table_header; struct net_generic; struct sock; +struct netns_ipvs; #define NETDEV_HASHBITS 8 @@ -94,6 +95,7 @@ struct net { #ifdef CONFIG_XFRM struct netns_xfrm xfrm; #endif + struct netns_ipvs *ipvs; }; diff --git a/include/net/netevent.h b/include/net/netevent.h index e82b7ba..22b239c 100644 --- a/include/net/netevent.h +++ b/include/net/netevent.h @@ -21,7 +21,6 @@ struct netevent_redirect { enum netevent_notif_type { NETEVENT_NEIGH_UPDATE = 1, /* arg is struct neighbour ptr */ - NETEVENT_PMTU_UPDATE, /* arg is struct dst_entry ptr */ NETEVENT_REDIRECT, /* arg is struct netevent_redirect ptr */ }; diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index d85cff1..d0d1337 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -50,11 +50,24 @@ union nf_conntrack_expect_proto { /* per conntrack: application helper private data */ union nf_conntrack_help { /* insert conntrack helper private data (master) here */ +#if defined(CONFIG_NF_CONNTRACK_FTP) || defined(CONFIG_NF_CONNTRACK_FTP_MODULE) struct nf_ct_ftp_master ct_ftp_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_PPTP) || \ + defined(CONFIG_NF_CONNTRACK_PPTP_MODULE) struct nf_ct_pptp_master ct_pptp_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_H323) || \ + defined(CONFIG_NF_CONNTRACK_H323_MODULE) struct nf_ct_h323_master ct_h323_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_SANE) || \ + defined(CONFIG_NF_CONNTRACK_SANE_MODULE) struct nf_ct_sane_master ct_sane_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_SIP) || defined(CONFIG_NF_CONNTRACK_SIP_MODULE) struct nf_ct_sip_master ct_sip_info; +#endif }; #include <linux/types.h> @@ -116,14 +129,14 @@ struct nf_conn { u_int32_t secmark; #endif - /* Storage reserved for other modules: */ - union nf_conntrack_proto proto; - /* 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; }; static inline struct nf_conn * @@ -189,9 +202,9 @@ extern void nf_ct_l3proto_module_put(unsigned short l3proto); * Allocate a hashtable of hlist_head (if nulls == 0), * or hlist_nulls_head (if nulls == 1) */ -extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int nulls); +extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls); -extern void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size); +extern void nf_ct_free_hashtable(void *hash, unsigned int size); extern struct nf_conntrack_tuple_hash * __nf_conntrack_find(struct net *net, u16 zone, diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 349cefe..4283508 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -23,12 +23,17 @@ struct nf_conntrack_ecache { static inline struct nf_conntrack_ecache * nf_ct_ecache_find(const struct nf_conn *ct) { +#ifdef CONFIG_NF_CONNTRACK_EVENTS return nf_ct_ext_find(ct, NF_CT_EXT_ECACHE); +#else + return NULL; +#endif } static inline struct nf_conntrack_ecache * nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) { +#ifdef CONFIG_NF_CONNTRACK_EVENTS struct net *net = nf_ct_net(ct); struct nf_conntrack_ecache *e; @@ -45,6 +50,9 @@ nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) e->expmask = expmask; } return e; +#else + return NULL; +#endif }; #ifdef CONFIG_NF_CONNTRACK_EVENTS @@ -59,7 +67,7 @@ struct nf_ct_event_notifier { int (*fcn)(unsigned int events, struct nf_ct_event *item); }; -extern struct nf_ct_event_notifier *nf_conntrack_event_cb; +extern struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb; extern int nf_conntrack_register_notifier(struct nf_ct_event_notifier *nb); extern void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *nb); @@ -156,7 +164,7 @@ struct nf_exp_event_notifier { int (*fcn)(unsigned int events, struct nf_exp_event *item); }; -extern struct nf_exp_event_notifier *nf_expect_event_cb; +extern struct nf_exp_event_notifier __rcu *nf_expect_event_cb; extern int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *nb); extern void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *nb); diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 0772d29..2dcf317 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -7,10 +7,19 @@ enum nf_ct_ext_id { NF_CT_EXT_HELPER, +#if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE) NF_CT_EXT_NAT, +#endif NF_CT_EXT_ACCT, +#ifdef CONFIG_NF_CONNTRACK_EVENTS NF_CT_EXT_ECACHE, +#endif +#ifdef CONFIG_NF_CONNTRACK_ZONES NF_CT_EXT_ZONE, +#endif +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + NF_CT_EXT_TSTAMP, +#endif NF_CT_EXT_NUM, }; @@ -19,6 +28,7 @@ enum nf_ct_ext_id { #define NF_CT_EXT_ACCT_TYPE struct nf_conn_counter #define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache #define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone +#define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp /* Extensions: optional stuff which isn't permanently in struct. */ struct nf_ct_ext { diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 32c305d..f1c1311 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -63,4 +63,10 @@ static inline struct nf_conn_help *nfct_help(const struct nf_conn *ct) extern int nf_conntrack_helper_init(void); extern void nf_conntrack_helper_fini(void); +extern int nf_conntrack_broadcast_help(struct sk_buff *skb, + unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int timeout); + #endif /*_NF_CONNTRACK_HELPER_H*/ diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h index a754761..e8010f4 100644 --- a/include/net/netfilter/nf_conntrack_l3proto.h +++ b/include/net/netfilter/nf_conntrack_l3proto.h @@ -73,7 +73,7 @@ struct nf_conntrack_l3proto { struct module *me; }; -extern struct nf_conntrack_l3proto *nf_ct_l3protos[AF_MAX]; +extern struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[AF_MAX]; /* Protocol registration. */ extern int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto); diff --git a/include/net/netfilter/nf_conntrack_timestamp.h b/include/net/netfilter/nf_conntrack_timestamp.h new file mode 100644 index 0000000..fc9c82b --- /dev/null +++ b/include/net/netfilter/nf_conntrack_timestamp.h @@ -0,0 +1,65 @@ +#ifndef _NF_CONNTRACK_TSTAMP_H +#define _NF_CONNTRACK_TSTAMP_H + +#include <net/net_namespace.h> +#include <linux/netfilter/nf_conntrack_common.h> +#include <linux/netfilter/nf_conntrack_tuple_common.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_extend.h> + +struct nf_conn_tstamp { + u_int64_t start; + u_int64_t stop; +}; + +static inline +struct nf_conn_tstamp *nf_conn_tstamp_find(const struct nf_conn *ct) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + return nf_ct_ext_find(ct, NF_CT_EXT_TSTAMP); +#else + return NULL; +#endif +} + +static inline +struct nf_conn_tstamp *nf_ct_tstamp_ext_add(struct nf_conn *ct, gfp_t gfp) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + struct net *net = nf_ct_net(ct); + + if (!net->ct.sysctl_tstamp) + return NULL; + + return nf_ct_ext_add(ct, NF_CT_EXT_TSTAMP, gfp); +#else + return NULL; +#endif +}; + +static inline bool nf_ct_tstamp_enabled(struct net *net) +{ + return net->ct.sysctl_tstamp != 0; +} + +static inline void nf_ct_set_tstamp(struct net *net, bool enable) +{ + net->ct.sysctl_tstamp = enable; +} + +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP +extern int nf_conntrack_tstamp_init(struct net *net); +extern void nf_conntrack_tstamp_fini(struct net *net); +#else +static inline int nf_conntrack_tstamp_init(struct net *net) +{ + return 0; +} + +static inline void nf_conntrack_tstamp_fini(struct net *net) +{ + return; +} +#endif /* CONFIG_NF_CONNTRACK_TIMESTAMP */ + +#endif /* _NF_CONNTRACK_TSTAMP_H */ diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index f5f09f03..aff80b1 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -56,7 +56,9 @@ struct nf_nat_multi_range_compat { /* per conntrack: nat application helper private data */ union nf_conntrack_nat_help { /* insert nat helper private data here */ +#if defined(CONFIG_NF_NAT_PPTP) || defined(CONFIG_NF_NAT_PPTP_MODULE) struct nf_nat_pptp nat_pptp_info; +#endif }; struct nf_conn; @@ -84,7 +86,11 @@ extern int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, static inline struct nf_conn_nat *nfct_nat(const struct nf_conn *ct) { +#if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE) return nf_ct_ext_find(ct, NF_CT_EXT_NAT); +#else + return NULL; +#endif } #else /* !__KERNEL__: iptables wants this to compile. */ diff --git a/include/net/netfilter/nf_nat_core.h b/include/net/netfilter/nf_nat_core.h index 33602ab..3dc7b98 100644 --- a/include/net/netfilter/nf_nat_core.h +++ b/include/net/netfilter/nf_nat_core.h @@ -21,9 +21,9 @@ static inline int nf_nat_initialized(struct nf_conn *ct, enum nf_nat_manip_type manip) { if (manip == IP_NAT_MANIP_SRC) - return test_bit(IPS_SRC_NAT_DONE_BIT, &ct->status); + return ct->status & IPS_SRC_NAT_DONE; else - return test_bit(IPS_DST_NAT_DONE_BIT, &ct->status); + return ct->status & IPS_DST_NAT_DONE; } struct nlattr; diff --git a/include/net/netlink.h b/include/net/netlink.h index 373f1a9..8a3906a 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -856,18 +856,27 @@ static inline int nla_put_msecs(struct sk_buff *skb, int attrtype, #define NLA_PUT_BE16(skb, attrtype, value) \ NLA_PUT_TYPE(skb, __be16, attrtype, value) +#define NLA_PUT_NET16(skb, attrtype, value) \ + NLA_PUT_BE16(skb, attrtype | NLA_F_NET_BYTEORDER, value) + #define NLA_PUT_U32(skb, attrtype, value) \ NLA_PUT_TYPE(skb, u32, attrtype, value) #define NLA_PUT_BE32(skb, attrtype, value) \ NLA_PUT_TYPE(skb, __be32, attrtype, value) +#define NLA_PUT_NET32(skb, attrtype, value) \ + NLA_PUT_BE32(skb, attrtype | NLA_F_NET_BYTEORDER, value) + #define NLA_PUT_U64(skb, attrtype, value) \ NLA_PUT_TYPE(skb, u64, attrtype, value) #define NLA_PUT_BE64(skb, attrtype, value) \ NLA_PUT_TYPE(skb, __be64, attrtype, value) +#define NLA_PUT_NET64(skb, attrtype, value) \ + NLA_PUT_BE64(skb, attrtype | NLA_F_NET_BYTEORDER, value) + #define NLA_PUT_STRING(skb, attrtype, value) \ NLA_PUT(skb, attrtype, strlen(value) + 1, value) diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index d4958d4..341eb08 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -21,15 +21,15 @@ struct netns_ct { int sysctl_events; unsigned int sysctl_events_retry_timeout; int sysctl_acct; + int sysctl_tstamp; int sysctl_checksum; unsigned int sysctl_log_invalid; /* Log invalid packets */ #ifdef CONFIG_SYSCTL struct ctl_table_header *sysctl_header; struct ctl_table_header *acct_sysctl_header; + struct ctl_table_header *tstamp_sysctl_header; struct ctl_table_header *event_sysctl_header; #endif - int hash_vmalloc; - int expect_vmalloc; char *slabname; }; #endif diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index d68c3f1..e2e2ef5 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -43,7 +43,6 @@ struct netns_ipv4 { struct xt_table *nat_table; struct hlist_head *nat_bysource; unsigned int nat_htable_size; - int nat_vmalloced; #endif int sysctl_icmp_echo_ignore_all; diff --git a/include/net/phonet/pep.h b/include/net/phonet/pep.h index b60b28c..b669fe6d 100644 --- a/include/net/phonet/pep.h +++ b/include/net/phonet/pep.h @@ -28,7 +28,6 @@ struct pep_sock { /* XXX: union-ify listening vs connected stuff ? */ /* Listening socket stuff: */ - struct hlist_head ackq; struct hlist_head hlist; /* Connected socket stuff: */ @@ -45,10 +44,6 @@ struct pep_sock { u8 tx_fc; /* TX flow control */ u8 init_enable; /* auto-enable at creation */ u8 aligned; -#ifdef CONFIG_PHONET_PIPECTRLR - u8 pipe_state; - struct sockaddr_pn remote_pep; -#endif }; static inline struct pep_sock *pep_sk(struct sock *sk) @@ -158,6 +153,7 @@ enum { PN_LEGACY_FLOW_CONTROL, PN_ONE_CREDIT_FLOW_CONTROL, PN_MULTI_CREDIT_FLOW_CONTROL, + PN_MAX_FLOW_CONTROL, }; #define pn_flow_safe(fc) ((fc) >> 1) @@ -169,21 +165,4 @@ enum { PEP_IND_READY, }; -#ifdef CONFIG_PHONET_PIPECTRLR -#define PNS_PEP_CONNECT_UTID 0x02 -#define PNS_PIPE_CREATED_IND_UTID 0x04 -#define PNS_PIPE_ENABLE_UTID 0x0A -#define PNS_PIPE_ENABLED_IND_UTID 0x0C -#define PNS_PIPE_DISABLE_UTID 0x0F -#define PNS_PIPE_DISABLED_IND_UTID 0x11 -#define PNS_PEP_DISCONNECT_UTID 0x06 - -/* Used for tracking state of a pipe */ -enum { - PIPE_IDLE, - PIPE_DISABLED, - PIPE_ENABLED, -}; -#endif /* CONFIG_PHONET_PIPECTRLR */ - #endif diff --git a/include/net/phonet/phonet.h b/include/net/phonet/phonet.h index 5395e09..68e5097 100644 --- a/include/net/phonet/phonet.h +++ b/include/net/phonet/phonet.h @@ -36,6 +36,7 @@ struct pn_sock { struct sock sk; u16 sobject; + u16 dobject; u8 resource; }; diff --git a/include/net/protocol.h b/include/net/protocol.h index dc07495..6f7eb80 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -38,7 +38,7 @@ struct net_protocol { void (*err_handler)(struct sk_buff *skb, u32 info); int (*gso_send_check)(struct sk_buff *skb); struct sk_buff *(*gso_segment)(struct sk_buff *skb, - int features); + u32 features); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb); @@ -57,7 +57,7 @@ struct inet6_protocol { int (*gso_send_check)(struct sk_buff *skb); struct sk_buff *(*gso_segment)(struct sk_buff *skb, - int features); + u32 features); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb); diff --git a/include/net/route.h b/include/net/route.h index 93e10c4..30d6cae 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -49,36 +49,43 @@ struct fib_nh; struct inet_peer; +struct fib_info; struct rtable { struct dst_entry dst; - /* Cache lookup keys */ - struct flowi fl; + /* Lookup key. */ + __be32 rt_key_dst; + __be32 rt_key_src; int rt_genid; unsigned rt_flags; __u16 rt_type; + __u8 rt_tos; __be32 rt_dst; /* Path destination */ __be32 rt_src; /* Path source */ int rt_iif; + int rt_oif; + __u32 rt_mark; /* Info on neighbour */ __be32 rt_gateway; /* Miscellaneous cached information */ __be32 rt_spec_dst; /* RFC1122 specific destination */ + u32 rt_peer_genid; struct inet_peer *peer; /* long-living peer info */ + struct fib_info *fi; /* for client ref to shared metrics */ }; static inline bool rt_is_input_route(struct rtable *rt) { - return rt->fl.iif != 0; + return rt->rt_iif != 0; } static inline bool rt_is_output_route(struct rtable *rt) { - return rt->fl.iif == 0; + return rt->rt_iif == 0; } struct ip_rt_acct { @@ -115,9 +122,63 @@ extern void ip_rt_redirect(__be32 old_gw, __be32 dst, __be32 new_gw, __be32 src, struct net_device *dev); extern void rt_cache_flush(struct net *net, int how); extern void rt_cache_flush_batch(struct net *net); -extern int __ip_route_output_key(struct net *, struct rtable **, const struct flowi *flp); -extern int ip_route_output_key(struct net *, struct rtable **, struct flowi *flp); -extern int ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk, int flags); +extern struct rtable *__ip_route_output_key(struct net *, const struct flowi4 *flp); +extern struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp, + struct sock *sk); +extern struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig); + +static inline struct rtable *ip_route_output_key(struct net *net, struct flowi4 *flp) +{ + return ip_route_output_flow(net, flp, NULL); +} + +static inline struct rtable *ip_route_output(struct net *net, __be32 daddr, + __be32 saddr, u8 tos, int oif) +{ + struct flowi4 fl4 = { + .flowi4_oif = oif, + .daddr = daddr, + .saddr = saddr, + .flowi4_tos = tos, + }; + return ip_route_output_key(net, &fl4); +} + +static inline struct rtable *ip_route_output_ports(struct net *net, struct sock *sk, + __be32 daddr, __be32 saddr, + __be16 dport, __be16 sport, + __u8 proto, __u8 tos, int oif) +{ + struct flowi4 fl4 = { + .flowi4_oif = oif, + .flowi4_flags = sk ? inet_sk_flowi_flags(sk) : 0, + .flowi4_mark = sk ? sk->sk_mark : 0, + .daddr = daddr, + .saddr = saddr, + .flowi4_tos = tos, + .flowi4_proto = proto, + .fl4_dport = dport, + .fl4_sport = sport, + }; + if (sk) + security_sk_classify_flow(sk, flowi4_to_flowi(&fl4)); + return ip_route_output_flow(net, &fl4, sk); +} + +static inline struct rtable *ip_route_output_gre(struct net *net, + __be32 daddr, __be32 saddr, + __be32 gre_key, __u8 tos, int oif) +{ + struct flowi4 fl4 = { + .flowi4_oif = oif, + .daddr = daddr, + .saddr = saddr, + .flowi4_tos = tos, + .flowi4_proto = IPPROTO_GRE, + .fl4_gre_key = gre_key, + }; + return ip_route_output_key(net, &fl4); +} extern int ip_route_input_common(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin, bool noref); @@ -162,57 +223,68 @@ static inline char rt_tos2priority(u8 tos) return ip_tos2prio[IPTOS_TOS(tos)>>1]; } -static inline int ip_route_connect(struct rtable **rp, __be32 dst, - __be32 src, u32 tos, int oif, u8 protocol, - __be16 sport, __be16 dport, struct sock *sk, - int flags) +static inline struct rtable *ip_route_connect(__be32 dst, __be32 src, u32 tos, + int oif, u8 protocol, + __be16 sport, __be16 dport, + struct sock *sk, bool can_sleep) { - struct flowi fl = { .oif = oif, - .mark = sk->sk_mark, - .fl4_dst = dst, - .fl4_src = src, - .fl4_tos = tos, - .proto = protocol, - .fl_ip_sport = sport, - .fl_ip_dport = dport }; - int err; + struct flowi4 fl4 = { + .flowi4_oif = oif, + .flowi4_mark = sk->sk_mark, + .daddr = dst, + .saddr = src, + .flowi4_tos = tos, + .flowi4_proto = protocol, + .fl4_sport = sport, + .fl4_dport = dport, + }; struct net *net = sock_net(sk); + struct rtable *rt; if (inet_sk(sk)->transparent) - fl.flags |= FLOWI_FLAG_ANYSRC; + fl4.flowi4_flags |= FLOWI_FLAG_ANYSRC; + if (protocol == IPPROTO_TCP) + fl4.flowi4_flags |= FLOWI_FLAG_PRECOW_METRICS; + if (can_sleep) + fl4.flowi4_flags |= FLOWI_FLAG_CAN_SLEEP; if (!dst || !src) { - err = __ip_route_output_key(net, rp, &fl); - if (err) - return err; - fl.fl4_dst = (*rp)->rt_dst; - fl.fl4_src = (*rp)->rt_src; - ip_rt_put(*rp); - *rp = NULL; + rt = __ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) + return rt; + fl4.daddr = rt->rt_dst; + fl4.saddr = rt->rt_src; + ip_rt_put(rt); } - security_sk_classify_flow(sk, &fl); - return ip_route_output_flow(net, rp, &fl, sk, flags); + security_sk_classify_flow(sk, flowi4_to_flowi(&fl4)); + return ip_route_output_flow(net, &fl4, sk); } -static inline int ip_route_newports(struct rtable **rp, u8 protocol, - __be16 sport, __be16 dport, struct sock *sk) +static inline struct rtable *ip_route_newports(struct rtable *rt, + u8 protocol, __be16 orig_sport, + __be16 orig_dport, __be16 sport, + __be16 dport, struct sock *sk) { - if (sport != (*rp)->fl.fl_ip_sport || - dport != (*rp)->fl.fl_ip_dport) { - struct flowi fl; - - memcpy(&fl, &(*rp)->fl, sizeof(fl)); - fl.fl_ip_sport = sport; - fl.fl_ip_dport = dport; - fl.proto = protocol; + if (sport != orig_sport || dport != orig_dport) { + struct flowi4 fl4 = { + .flowi4_oif = rt->rt_oif, + .flowi4_mark = rt->rt_mark, + .daddr = rt->rt_key_dst, + .saddr = rt->rt_key_src, + .flowi4_tos = rt->rt_tos, + .flowi4_proto = protocol, + .fl4_sport = sport, + .fl4_dport = dport + }; if (inet_sk(sk)->transparent) - fl.flags |= FLOWI_FLAG_ANYSRC; - ip_rt_put(*rp); - *rp = NULL; - security_sk_classify_flow(sk, &fl); - return ip_route_output_flow(sock_net(sk), rp, &fl, sk, 0); + fl4.flowi4_flags |= FLOWI_FLAG_ANYSRC; + if (protocol == IPPROTO_TCP) + fl4.flowi4_flags |= FLOWI_FLAG_PRECOW_METRICS; + ip_rt_put(rt); + security_sk_classify_flow(sk, flowi4_to_flowi(&fl4)); + return ip_route_output_flow(sock_net(sk), &fl4, sk); } - return 0; + return rt; } extern void rt_bind_peer(struct rtable *rt, int create); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 04f8556..a9505b6 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -31,10 +31,12 @@ enum qdisc_state_t { * following bits are only changed while qdisc lock is held */ enum qdisc___state_t { - __QDISC___STATE_RUNNING, + __QDISC___STATE_RUNNING = 1, + __QDISC___STATE_THROTTLED = 2, }; struct qdisc_size_table { + struct rcu_head rcu; struct list_head list; struct tc_sizespec szopts; int refcnt; @@ -46,14 +48,13 @@ struct Qdisc { struct sk_buff * (*dequeue)(struct Qdisc *dev); unsigned flags; #define TCQ_F_BUILTIN 1 -#define TCQ_F_THROTTLED 2 -#define TCQ_F_INGRESS 4 -#define TCQ_F_CAN_BYPASS 8 -#define TCQ_F_MQROOT 16 +#define TCQ_F_INGRESS 2 +#define TCQ_F_CAN_BYPASS 4 +#define TCQ_F_MQROOT 8 #define TCQ_F_WARN_NONWC (1 << 16) int padded; struct Qdisc_ops *ops; - struct qdisc_size_table *stab; + struct qdisc_size_table __rcu *stab; struct list_head list; u32 handle; u32 parent; @@ -78,25 +79,44 @@ struct Qdisc { unsigned long state; struct sk_buff_head q; struct gnet_stats_basic_packed bstats; - unsigned long __state; + unsigned int __state; struct gnet_stats_queue qstats; struct rcu_head rcu_head; spinlock_t busylock; + u32 limit; }; -static inline bool qdisc_is_running(struct Qdisc *qdisc) +static inline bool qdisc_is_running(const struct Qdisc *qdisc) { - return test_bit(__QDISC___STATE_RUNNING, &qdisc->__state); + return (qdisc->__state & __QDISC___STATE_RUNNING) ? true : false; } static inline bool qdisc_run_begin(struct Qdisc *qdisc) { - return !__test_and_set_bit(__QDISC___STATE_RUNNING, &qdisc->__state); + if (qdisc_is_running(qdisc)) + return false; + qdisc->__state |= __QDISC___STATE_RUNNING; + return true; } static inline void qdisc_run_end(struct Qdisc *qdisc) { - __clear_bit(__QDISC___STATE_RUNNING, &qdisc->__state); + qdisc->__state &= ~__QDISC___STATE_RUNNING; +} + +static inline bool qdisc_is_throttled(const struct Qdisc *qdisc) +{ + return (qdisc->__state & __QDISC___STATE_THROTTLED) ? true : false; +} + +static inline void qdisc_throttled(struct Qdisc *qdisc) +{ + qdisc->__state |= __QDISC___STATE_THROTTLED; +} + +static inline void qdisc_unthrottled(struct Qdisc *qdisc) +{ + qdisc->__state &= ~__QDISC___STATE_THROTTLED; } struct Qdisc_class_ops { @@ -331,8 +351,8 @@ extern struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, struct Qdisc_ops *ops); extern struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, struct Qdisc_ops *ops, u32 parentid); -extern void qdisc_calculate_pkt_len(struct sk_buff *skb, - struct qdisc_size_table *stab); +extern void __qdisc_calculate_pkt_len(struct sk_buff *skb, + const struct qdisc_size_table *stab); extern void tcf_destroy(struct tcf_proto *tp); extern void tcf_destroy_chain(struct tcf_proto **fl); @@ -411,12 +431,20 @@ enum net_xmit_qdisc_t { #define net_xmit_drop_count(e) (1) #endif -static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch) +static inline void qdisc_calculate_pkt_len(struct sk_buff *skb, + const struct Qdisc *sch) { #ifdef CONFIG_NET_SCHED - if (sch->stab) - qdisc_calculate_pkt_len(skb, sch->stab); + struct qdisc_size_table *stab = rcu_dereference_bh(sch->stab); + + if (stab) + __qdisc_calculate_pkt_len(skb, stab); #endif +} + +static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch) +{ + qdisc_calculate_pkt_len(skb, sch); return sch->enqueue(skb, sch); } diff --git a/include/net/sock.h b/include/net/sock.h index bc1cf7d8..da0534d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -281,7 +281,7 @@ struct sock { int sk_rcvbuf; struct sk_filter __rcu *sk_filter; - struct socket_wq *sk_wq; + struct socket_wq __rcu *sk_wq; #ifdef CONFIG_NET_DMA struct sk_buff_head sk_async_wait_queue; @@ -1191,7 +1191,7 @@ extern void sk_filter_release_rcu(struct rcu_head *rcu); static inline void sk_filter_release(struct sk_filter *fp) { if (atomic_dec_and_test(&fp->refcnt)) - call_rcu_bh(&fp->rcu, sk_filter_release_rcu); + call_rcu(&fp->rcu, sk_filter_release_rcu); } static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) @@ -1266,7 +1266,8 @@ static inline void sk_set_socket(struct sock *sk, struct socket *sock) static inline wait_queue_head_t *sk_sleep(struct sock *sk) { - return &sk->sk_wq->wait; + BUILD_BUG_ON(offsetof(struct socket_wq, wait) != 0); + return &rcu_dereference_raw(sk->sk_wq)->wait; } /* Detach socket from process context. * Announce socket dead, detach it from wait queue and inode. @@ -1287,7 +1288,7 @@ static inline void sock_orphan(struct sock *sk) static inline void sock_graft(struct sock *sk, struct socket *parent) { write_lock_bh(&sk->sk_callback_lock); - rcu_assign_pointer(sk->sk_wq, parent->wq); + sk->sk_wq = parent->wq; parent->sk = sk; sk_set_socket(sk, parent); security_sock_graft(sk, parent); diff --git a/include/net/tcp.h b/include/net/tcp.h index 38509f0..cda30ea 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -196,6 +196,9 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); /* TCP thin-stream limits */ #define TCP_THIN_LINEAR_RETRIES 6 /* After 6 linear retries, do exp. backoff */ +/* TCP initial congestion window as per draft-hkchu-tcpm-initcwnd-01 */ +#define TCP_INIT_CWND 10 + extern struct inet_timewait_death_row tcp_death_row; /* sysctl variables for tcp */ @@ -799,15 +802,6 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk) /* Use define here intentionally to get WARN_ON location shown at the caller */ #define tcp_verify_left_out(tp) WARN_ON(tcp_left_out(tp) > tp->packets_out) -/* - * Convert RFC 3390 larger initial window into an equivalent number of packets. - * This is based on the numbers specified in RFC 5681, 3.1. - */ -static inline u32 rfc3390_bytes_to_packets(const u32 smss) -{ - return smss <= 1095 ? 4 : (smss > 2190 ? 2 : 3); -} - extern void tcp_enter_cwr(struct sock *sk, const int set_ssthresh); extern __u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst); @@ -1074,8 +1068,6 @@ static inline int tcp_paws_reject(const struct tcp_options_received *rx_opt, return 1; } -#define TCP_CHECK_TIMER(sk) do { } while (0) - static inline void tcp_mib_init(struct net *net) { /* See RFC 2012 */ @@ -1404,7 +1396,7 @@ extern struct request_sock_ops tcp6_request_sock_ops; extern void tcp_v4_destroy_sock(struct sock *sk); extern int tcp_v4_gso_send_check(struct sk_buff *skb); -extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features); +extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features); extern struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb); extern struct sk_buff **tcp4_gro_receive(struct sk_buff **head, diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h index 42a0eb6..eeb077d 100644 --- a/include/net/transp_v6.h +++ b/include/net/transp_v6.h @@ -14,7 +14,7 @@ extern struct proto udpv6_prot; extern struct proto udplitev6_prot; extern struct proto tcpv6_prot; -struct flowi; +struct flowi6; /* extention headers */ extern int ipv6_exthdrs_init(void); @@ -42,7 +42,7 @@ extern int datagram_recv_ctl(struct sock *sk, extern int datagram_send_ctl(struct net *net, struct msghdr *msg, - struct flowi *fl, + struct flowi6 *fl6, struct ipv6_txoptions *opt, int *hlimit, int *tclass, int *dontfrag); diff --git a/include/net/udp.h b/include/net/udp.h index bb967dd..67ea6fc 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -144,6 +144,17 @@ static inline __wsum udp_csum_outgoing(struct sock *sk, struct sk_buff *skb) return csum; } +static inline __wsum udp_csum(struct sk_buff *skb) +{ + __wsum csum = csum_partial(skb_transport_header(skb), + sizeof(struct udphdr), skb->csum); + + for (skb = skb_shinfo(skb)->frag_list; skb; skb = skb->next) { + csum = csum_add(csum, skb->csum); + } + return csum; +} + /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */ static inline void udp_lib_hash(struct sock *sk) { @@ -245,5 +256,5 @@ extern void udp4_proc_exit(void); extern void udp_init(void); extern int udp4_ufo_send_check(struct sk_buff *skb); -extern struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, int features); +extern struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, u32 features); #endif /* _UDP_H */ diff --git a/include/net/udplite.h b/include/net/udplite.h index afdffe6..673a024 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -115,6 +115,18 @@ static inline __wsum udplite_csum_outgoing(struct sock *sk, struct sk_buff *skb) return csum; } +static inline __wsum udplite_csum(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + int cscov = udplite_sender_cscov(udp_sk(sk), udp_hdr(skb)); + const int off = skb_transport_offset(skb); + const int len = skb->len - off; + + skb->ip_summed = CHECKSUM_NONE; /* no HW support for checksumming */ + + return skb_checksum(skb, off, min(cscov, len), 0); +} + extern void udplite4_register(void); extern int udplite_get_port(struct sock *sk, unsigned short snum, int (*scmp)(const struct sock *, const struct sock *)); diff --git a/include/net/xfrm.h b/include/net/xfrm.h index b9f385d..42a8c32 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -36,6 +36,7 @@ #define XFRM_PROTO_ROUTING IPPROTO_ROUTING #define XFRM_PROTO_DSTOPTS IPPROTO_DSTOPTS +#define XFRM_ALIGN4(len) (((len) + 3) & ~3) #define XFRM_ALIGN8(len) (((len) + 7) & ~7) #define MODULE_ALIAS_XFRM_MODE(family, encap) \ MODULE_ALIAS("xfrm-mode-" __stringify(family) "-" __stringify(encap)) @@ -185,9 +186,14 @@ struct xfrm_state { /* State for replay detection */ struct xfrm_replay_state replay; + struct xfrm_replay_state_esn *replay_esn; /* Replay detection state at the time we sent the last notification */ struct xfrm_replay_state preplay; + struct xfrm_replay_state_esn *preplay_esn; + + /* The functions for replay detection. */ + struct xfrm_replay *repl; /* internal flag that only holds state for delayed aevent at the * moment @@ -258,6 +264,15 @@ struct km_event { struct net *net; }; +struct xfrm_replay { + void (*advance)(struct xfrm_state *x, __be32 net_seq); + int (*check)(struct xfrm_state *x, + struct sk_buff *skb, + __be32 net_seq); + void (*notify)(struct xfrm_state *x, int event); + int (*overflow)(struct xfrm_state *x, struct sk_buff *skb); +}; + struct net_device; struct xfrm_type; struct xfrm_dst; @@ -266,25 +281,26 @@ struct xfrm_policy_afinfo { struct dst_ops *dst_ops; void (*garbage_collect)(struct net *net); struct dst_entry *(*dst_lookup)(struct net *net, int tos, - xfrm_address_t *saddr, - xfrm_address_t *daddr); + const xfrm_address_t *saddr, + const xfrm_address_t *daddr); int (*get_saddr)(struct net *net, xfrm_address_t *saddr, xfrm_address_t *daddr); void (*decode_session)(struct sk_buff *skb, struct flowi *fl, int reverse); - int (*get_tos)(struct flowi *fl); + int (*get_tos)(const struct flowi *fl); int (*init_path)(struct xfrm_dst *path, struct dst_entry *dst, int nfheader_len); int (*fill_dst)(struct xfrm_dst *xdst, struct net_device *dev, - struct flowi *fl); + const struct flowi *fl); + struct dst_entry *(*blackhole_route)(struct net *net, struct dst_entry *orig); }; extern int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo); extern int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo); -extern void km_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c); -extern void km_state_notify(struct xfrm_state *x, struct km_event *c); +extern void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c); +extern void km_state_notify(struct xfrm_state *x, const struct km_event *c); struct xfrm_tmpl; extern int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); @@ -299,9 +315,12 @@ struct xfrm_state_afinfo { const struct xfrm_type *type_map[IPPROTO_MAX]; struct xfrm_mode *mode_map[XFRM_MODE_MAX]; int (*init_flags)(struct xfrm_state *x); - void (*init_tempsel)(struct xfrm_selector *sel, struct flowi *fl); - void (*init_temprop)(struct xfrm_state *x, struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr); + void (*init_tempsel)(struct xfrm_selector *sel, + const struct flowi *fl); + void (*init_temprop)(struct xfrm_state *x, + const struct xfrm_tmpl *tmpl, + const xfrm_address_t *daddr, + const xfrm_address_t *saddr); int (*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n); int (*state_sort)(struct xfrm_state **dst, struct xfrm_state **src, int n); int (*output)(struct sk_buff *skb); @@ -332,7 +351,8 @@ struct xfrm_type { void (*destructor)(struct xfrm_state *); int (*input)(struct xfrm_state *, struct sk_buff *skb); int (*output)(struct xfrm_state *, struct sk_buff *pskb); - int (*reject)(struct xfrm_state *, struct sk_buff *, struct flowi *); + int (*reject)(struct xfrm_state *, struct sk_buff *, + const struct flowi *); int (*hdr_offset)(struct xfrm_state *, struct sk_buff *, u8 **); /* Estimate maximal size of result of transformation of a dgram */ u32 (*get_mtu)(struct xfrm_state *, int size); @@ -501,7 +521,7 @@ struct xfrm_policy { struct xfrm_tmpl xfrm_vec[XFRM_MAX_DEPTH]; }; -static inline struct net *xp_net(struct xfrm_policy *xp) +static inline struct net *xp_net(const struct xfrm_policy *xp) { return read_pnet(&xp->xp_net); } @@ -545,13 +565,17 @@ struct xfrm_migrate { struct xfrm_mgr { struct list_head list; char *id; - int (*notify)(struct xfrm_state *x, struct km_event *c); + int (*notify)(struct xfrm_state *x, const struct km_event *c); int (*acquire)(struct xfrm_state *x, struct xfrm_tmpl *, struct xfrm_policy *xp, int dir); struct xfrm_policy *(*compile_policy)(struct sock *sk, int opt, u8 *data, int len, int *dir); int (*new_mapping)(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport); - int (*notify_policy)(struct xfrm_policy *x, int dir, struct km_event *c); + int (*notify_policy)(struct xfrm_policy *x, int dir, const struct km_event *c); int (*report)(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr); - int (*migrate)(struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_bundles, struct xfrm_kmaddress *k); + int (*migrate)(const struct xfrm_selector *sel, + u8 dir, u8 type, + const struct xfrm_migrate *m, + int num_bundles, + const struct xfrm_kmaddress *k); }; extern int xfrm_register_km(struct xfrm_mgr *km); @@ -570,8 +594,14 @@ struct xfrm_skb_cb { /* Sequence number for replay protection. */ union { - u64 output; - __be32 input; + struct { + __u32 low; + __u32 hi; + } output; + struct { + __be32 low; + __be32 hi; + } input; } seq; }; @@ -675,6 +705,8 @@ extern void xfrm_audit_state_delete(struct xfrm_state *x, int result, u32 auid, u32 ses, u32 secid); extern void xfrm_audit_state_replay_overflow(struct xfrm_state *x, struct sk_buff *skb); +extern void xfrm_audit_state_replay(struct xfrm_state *x, + struct sk_buff *skb, __be32 net_seq); extern void xfrm_audit_state_notfound_simple(struct sk_buff *skb, u16 family); extern void xfrm_audit_state_notfound(struct sk_buff *skb, u16 family, __be32 net_spi, __be32 net_seq); @@ -707,6 +739,11 @@ static inline void xfrm_audit_state_replay_overflow(struct xfrm_state *x, { } +static inline void xfrm_audit_state_replay(struct xfrm_state *x, + struct sk_buff *skb, __be32 net_seq) +{ +} + static inline void xfrm_audit_state_notfound_simple(struct sk_buff *skb, u16 family) { @@ -762,10 +799,11 @@ static inline void xfrm_state_hold(struct xfrm_state *x) atomic_inc(&x->refcnt); } -static __inline__ int addr_match(void *token1, void *token2, int prefixlen) +static inline bool addr_match(const void *token1, const void *token2, + int prefixlen) { - __be32 *a1 = token1; - __be32 *a2 = token2; + const __be32 *a1 = token1; + const __be32 *a2 = token2; int pdw; int pbi; @@ -774,7 +812,7 @@ static __inline__ int addr_match(void *token1, void *token2, int prefixlen) if (pdw) if (memcmp(a1, a2, pdw << 2)) - return 0; + return false; if (pbi) { __be32 mask; @@ -782,32 +820,32 @@ static __inline__ int addr_match(void *token1, void *token2, int prefixlen) mask = htonl((0xffffffff) << (32 - pbi)); if ((a1[pdw] ^ a2[pdw]) & mask) - return 0; + return false; } - return 1; + return true; } static __inline__ -__be16 xfrm_flowi_sport(struct flowi *fl) +__be16 xfrm_flowi_sport(const struct flowi *fl, const union flowi_uli *uli) { __be16 port; - switch(fl->proto) { + switch(fl->flowi_proto) { case IPPROTO_TCP: case IPPROTO_UDP: case IPPROTO_UDPLITE: case IPPROTO_SCTP: - port = fl->fl_ip_sport; + port = uli->ports.sport; break; case IPPROTO_ICMP: case IPPROTO_ICMPV6: - port = htons(fl->fl_icmp_type); + port = htons(uli->icmpt.type); break; case IPPROTO_MH: - port = htons(fl->fl_mh_type); + port = htons(uli->mht.type); break; case IPPROTO_GRE: - port = htons(ntohl(fl->fl_gre_key) >> 16); + port = htons(ntohl(uli->gre_key) >> 16); break; default: port = 0; /*XXX*/ @@ -816,22 +854,22 @@ __be16 xfrm_flowi_sport(struct flowi *fl) } static __inline__ -__be16 xfrm_flowi_dport(struct flowi *fl) +__be16 xfrm_flowi_dport(const struct flowi *fl, const union flowi_uli *uli) { __be16 port; - switch(fl->proto) { + switch(fl->flowi_proto) { case IPPROTO_TCP: case IPPROTO_UDP: case IPPROTO_UDPLITE: case IPPROTO_SCTP: - port = fl->fl_ip_dport; + port = uli->ports.dport; break; case IPPROTO_ICMP: case IPPROTO_ICMPV6: - port = htons(fl->fl_icmp_code); + port = htons(uli->icmpt.code); break; case IPPROTO_GRE: - port = htons(ntohl(fl->fl_gre_key) & 0xffff); + port = htons(ntohl(uli->gre_key) & 0xffff); break; default: port = 0; /*XXX*/ @@ -839,7 +877,8 @@ __be16 xfrm_flowi_dport(struct flowi *fl) return port; } -extern int xfrm_selector_match(struct xfrm_selector *sel, struct flowi *fl, +extern int xfrm_selector_match(const struct xfrm_selector *sel, + const struct flowi *fl, unsigned short family); #ifdef CONFIG_SECURITY_NETWORK_XFRM @@ -947,7 +986,7 @@ secpath_reset(struct sk_buff *skb) } static inline int -xfrm_addr_any(xfrm_address_t *addr, unsigned short family) +xfrm_addr_any(const xfrm_address_t *addr, unsigned short family) { switch (family) { case AF_INET: @@ -959,21 +998,21 @@ xfrm_addr_any(xfrm_address_t *addr, unsigned short family) } static inline int -__xfrm4_state_addr_cmp(struct xfrm_tmpl *tmpl, struct xfrm_state *x) +__xfrm4_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x) { return (tmpl->saddr.a4 && tmpl->saddr.a4 != x->props.saddr.a4); } static inline int -__xfrm6_state_addr_cmp(struct xfrm_tmpl *tmpl, struct xfrm_state *x) +__xfrm6_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x) { return (!ipv6_addr_any((struct in6_addr*)&tmpl->saddr) && ipv6_addr_cmp((struct in6_addr *)&tmpl->saddr, (struct in6_addr*)&x->props.saddr)); } static inline int -xfrm_state_addr_cmp(struct xfrm_tmpl *tmpl, struct xfrm_state *x, unsigned short family) +xfrm_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, unsigned short family) { switch (family) { case AF_INET: @@ -1126,49 +1165,49 @@ static inline int xfrm6_policy_check_reverse(struct sock *sk, int dir, #endif static __inline__ -xfrm_address_t *xfrm_flowi_daddr(struct flowi *fl, unsigned short family) +xfrm_address_t *xfrm_flowi_daddr(const struct flowi *fl, unsigned short family) { switch (family){ case AF_INET: - return (xfrm_address_t *)&fl->fl4_dst; + return (xfrm_address_t *)&fl->u.ip4.daddr; case AF_INET6: - return (xfrm_address_t *)&fl->fl6_dst; + return (xfrm_address_t *)&fl->u.ip6.daddr; } return NULL; } static __inline__ -xfrm_address_t *xfrm_flowi_saddr(struct flowi *fl, unsigned short family) +xfrm_address_t *xfrm_flowi_saddr(const struct flowi *fl, unsigned short family) { switch (family){ case AF_INET: - return (xfrm_address_t *)&fl->fl4_src; + return (xfrm_address_t *)&fl->u.ip4.saddr; case AF_INET6: - return (xfrm_address_t *)&fl->fl6_src; + return (xfrm_address_t *)&fl->u.ip6.saddr; } return NULL; } static __inline__ -void xfrm_flowi_addr_get(struct flowi *fl, +void xfrm_flowi_addr_get(const struct flowi *fl, xfrm_address_t *saddr, xfrm_address_t *daddr, unsigned short family) { switch(family) { case AF_INET: - memcpy(&saddr->a4, &fl->fl4_src, sizeof(saddr->a4)); - memcpy(&daddr->a4, &fl->fl4_dst, sizeof(daddr->a4)); + memcpy(&saddr->a4, &fl->u.ip4.saddr, sizeof(saddr->a4)); + memcpy(&daddr->a4, &fl->u.ip4.daddr, sizeof(daddr->a4)); break; case AF_INET6: - ipv6_addr_copy((struct in6_addr *)&saddr->a6, &fl->fl6_src); - ipv6_addr_copy((struct in6_addr *)&daddr->a6, &fl->fl6_dst); + ipv6_addr_copy((struct in6_addr *)&saddr->a6, &fl->u.ip6.saddr); + ipv6_addr_copy((struct in6_addr *)&daddr->a6, &fl->u.ip6.daddr); break; } } static __inline__ int -__xfrm4_state_addr_check(struct xfrm_state *x, - xfrm_address_t *daddr, xfrm_address_t *saddr) +__xfrm4_state_addr_check(const struct xfrm_state *x, + const xfrm_address_t *daddr, const xfrm_address_t *saddr) { if (daddr->a4 == x->id.daddr.a4 && (saddr->a4 == x->props.saddr.a4 || !saddr->a4 || !x->props.saddr.a4)) @@ -1177,8 +1216,8 @@ __xfrm4_state_addr_check(struct xfrm_state *x, } static __inline__ int -__xfrm6_state_addr_check(struct xfrm_state *x, - xfrm_address_t *daddr, xfrm_address_t *saddr) +__xfrm6_state_addr_check(const struct xfrm_state *x, + const xfrm_address_t *daddr, const xfrm_address_t *saddr) { if (!ipv6_addr_cmp((struct in6_addr *)daddr, (struct in6_addr *)&x->id.daddr) && (!ipv6_addr_cmp((struct in6_addr *)saddr, (struct in6_addr *)&x->props.saddr)|| @@ -1189,8 +1228,8 @@ __xfrm6_state_addr_check(struct xfrm_state *x, } static __inline__ int -xfrm_state_addr_check(struct xfrm_state *x, - xfrm_address_t *daddr, xfrm_address_t *saddr, +xfrm_state_addr_check(const struct xfrm_state *x, + const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family) { switch (family) { @@ -1203,23 +1242,23 @@ xfrm_state_addr_check(struct xfrm_state *x, } static __inline__ int -xfrm_state_addr_flow_check(struct xfrm_state *x, struct flowi *fl, +xfrm_state_addr_flow_check(const struct xfrm_state *x, const struct flowi *fl, unsigned short family) { switch (family) { case AF_INET: return __xfrm4_state_addr_check(x, - (xfrm_address_t *)&fl->fl4_dst, - (xfrm_address_t *)&fl->fl4_src); + (const xfrm_address_t *)&fl->u.ip4.daddr, + (const xfrm_address_t *)&fl->u.ip4.saddr); case AF_INET6: return __xfrm6_state_addr_check(x, - (xfrm_address_t *)&fl->fl6_dst, - (xfrm_address_t *)&fl->fl6_src); + (const xfrm_address_t *)&fl->u.ip6.daddr, + (const xfrm_address_t *)&fl->u.ip6.saddr); } return 0; } -static inline int xfrm_state_kern(struct xfrm_state *x) +static inline int xfrm_state_kern(const struct xfrm_state *x) { return atomic_read(&x->tunnel_users); } @@ -1323,8 +1362,10 @@ extern int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, int (*func)(struct xfrm_state *, int, void*), void *); extern void xfrm_state_walk_done(struct xfrm_state_walk *walk); extern struct xfrm_state *xfrm_state_alloc(struct net *net); -extern struct xfrm_state *xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, - struct flowi *fl, struct xfrm_tmpl *tmpl, +extern struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr, + const xfrm_address_t *saddr, + const struct flowi *fl, + struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, unsigned short family); extern struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, @@ -1337,11 +1378,11 @@ extern void xfrm_state_insert(struct xfrm_state *x); extern int xfrm_state_add(struct xfrm_state *x); extern int xfrm_state_update(struct xfrm_state *x); extern struct xfrm_state *xfrm_state_lookup(struct net *net, u32 mark, - xfrm_address_t *daddr, __be32 spi, + const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family); extern struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, u32 mark, - xfrm_address_t *daddr, - xfrm_address_t *saddr, + const xfrm_address_t *daddr, + const xfrm_address_t *saddr, u8 proto, unsigned short family); #ifdef CONFIG_XFRM_SUB_POLICY @@ -1386,10 +1427,8 @@ extern int xfrm_state_delete(struct xfrm_state *x); extern int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info); extern void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); extern void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); -extern int xfrm_replay_check(struct xfrm_state *x, - struct sk_buff *skb, __be32 seq); -extern void xfrm_replay_advance(struct xfrm_state *x, __be32 seq); -extern void xfrm_replay_notify(struct xfrm_state *x, int event); +extern u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq); +extern int xfrm_init_replay(struct xfrm_state *x); extern int xfrm_state_mtu(struct xfrm_state *x, int mtu); extern int xfrm_init_state(struct xfrm_state *x); extern int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb); @@ -1468,19 +1507,19 @@ u32 xfrm_get_acqseq(void); extern int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi); struct xfrm_state *xfrm_find_acq(struct net *net, struct xfrm_mark *mark, u8 mode, u32 reqid, u8 proto, - xfrm_address_t *daddr, - xfrm_address_t *saddr, int create, + const xfrm_address_t *daddr, + const xfrm_address_t *saddr, int create, unsigned short family); extern int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol); #ifdef CONFIG_XFRM_MIGRATE -extern int km_migrate(struct xfrm_selector *sel, u8 dir, u8 type, - struct xfrm_migrate *m, int num_bundles, - struct xfrm_kmaddress *k); +extern int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, + const struct xfrm_migrate *m, int num_bundles, + const struct xfrm_kmaddress *k); extern struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m); extern struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x, struct xfrm_migrate *m); -extern int xfrm_migrate(struct xfrm_selector *sel, u8 dir, u8 type, +extern int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_bundles, struct xfrm_kmaddress *k); #endif @@ -1500,10 +1539,10 @@ extern struct xfrm_algo_desc *xfrm_ealg_get_byidx(unsigned int idx); extern struct xfrm_algo_desc *xfrm_aalg_get_byid(int alg_id); extern struct xfrm_algo_desc *xfrm_ealg_get_byid(int alg_id); extern struct xfrm_algo_desc *xfrm_calg_get_byid(int alg_id); -extern struct xfrm_algo_desc *xfrm_aalg_get_byname(char *name, int probe); -extern struct xfrm_algo_desc *xfrm_ealg_get_byname(char *name, int probe); -extern struct xfrm_algo_desc *xfrm_calg_get_byname(char *name, int probe); -extern struct xfrm_algo_desc *xfrm_aead_get_byname(char *name, int icv_len, +extern struct xfrm_algo_desc *xfrm_aalg_get_byname(const char *name, int probe); +extern struct xfrm_algo_desc *xfrm_ealg_get_byname(const char *name, int probe); +extern struct xfrm_algo_desc *xfrm_calg_get_byname(const char *name, int probe); +extern struct xfrm_algo_desc *xfrm_aead_get_byname(const char *name, int icv_len, int probe); struct hash_desc; @@ -1511,7 +1550,8 @@ struct scatterlist; typedef int (icv_update_fn_t)(struct hash_desc *, struct scatterlist *, unsigned int); -static inline int xfrm_addr_cmp(xfrm_address_t *a, xfrm_address_t *b, +static inline int xfrm_addr_cmp(const xfrm_address_t *a, + const xfrm_address_t *b, int family) { switch (family) { @@ -1544,16 +1584,21 @@ static inline int xfrm_aevent_is_on(struct net *net) } #endif -static inline int xfrm_alg_len(struct xfrm_algo *alg) +static inline int xfrm_alg_len(const struct xfrm_algo *alg) { return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); } -static inline int xfrm_alg_auth_len(struct xfrm_algo_auth *alg) +static inline int xfrm_alg_auth_len(const struct xfrm_algo_auth *alg) { return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); } +static inline int xfrm_replay_state_esn_len(struct xfrm_replay_state_esn *replay_esn) +{ + return sizeof(*replay_esn) + replay_esn->bmp_len * sizeof(__u32); +} + #ifdef CONFIG_XFRM_MIGRATE static inline struct xfrm_algo *xfrm_algo_clone(struct xfrm_algo *orig) { @@ -1597,7 +1642,7 @@ static inline int xfrm_mark_get(struct nlattr **attrs, struct xfrm_mark *m) return m->v & m->m; } -static inline int xfrm_mark_put(struct sk_buff *skb, struct xfrm_mark *m) +static inline int xfrm_mark_put(struct sk_buff *skb, const struct xfrm_mark *m) { if (m->m | m->v) NLA_PUT(skb, XFRMA_MARK, sizeof(struct xfrm_mark), m); diff --git a/include/xen/events.h b/include/xen/events.h index 962da2c..d3b9010 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -23,6 +23,12 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi, unsigned long irqflags, const char *devname, void *dev_id); +int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain, + unsigned int remote_port, + irq_handler_t handler, + unsigned long irqflags, + const char *devname, + void *dev_id); /* * Common unbind function for all event sources. Takes IRQ to unbind from. diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h index 518481c..cb94668 100644 --- a/include/xen/interface/io/netif.h +++ b/include/xen/interface/io/netif.h @@ -22,50 +22,50 @@ /* * This is the 'wire' format for packets: - * Request 1: netif_tx_request -- NETTXF_* (any flags) - * [Request 2: netif_tx_extra] (only if request 1 has NETTXF_extra_info) - * [Request 3: netif_tx_extra] (only if request 2 has XEN_NETIF_EXTRA_MORE) - * Request 4: netif_tx_request -- NETTXF_more_data - * Request 5: netif_tx_request -- NETTXF_more_data + * Request 1: xen_netif_tx_request -- XEN_NETTXF_* (any flags) + * [Request 2: xen_netif_extra_info] (only if request 1 has XEN_NETTXF_extra_info) + * [Request 3: xen_netif_extra_info] (only if request 2 has XEN_NETIF_EXTRA_MORE) + * Request 4: xen_netif_tx_request -- XEN_NETTXF_more_data + * Request 5: xen_netif_tx_request -- XEN_NETTXF_more_data * ... - * Request N: netif_tx_request -- 0 + * Request N: xen_netif_tx_request -- 0 */ /* Protocol checksum field is blank in the packet (hardware offload)? */ -#define _NETTXF_csum_blank (0) -#define NETTXF_csum_blank (1U<<_NETTXF_csum_blank) +#define _XEN_NETTXF_csum_blank (0) +#define XEN_NETTXF_csum_blank (1U<<_XEN_NETTXF_csum_blank) /* Packet data has been validated against protocol checksum. */ -#define _NETTXF_data_validated (1) -#define NETTXF_data_validated (1U<<_NETTXF_data_validated) +#define _XEN_NETTXF_data_validated (1) +#define XEN_NETTXF_data_validated (1U<<_XEN_NETTXF_data_validated) /* Packet continues in the next request descriptor. */ -#define _NETTXF_more_data (2) -#define NETTXF_more_data (1U<<_NETTXF_more_data) +#define _XEN_NETTXF_more_data (2) +#define XEN_NETTXF_more_data (1U<<_XEN_NETTXF_more_data) /* Packet to be followed by extra descriptor(s). */ -#define _NETTXF_extra_info (3) -#define NETTXF_extra_info (1U<<_NETTXF_extra_info) +#define _XEN_NETTXF_extra_info (3) +#define XEN_NETTXF_extra_info (1U<<_XEN_NETTXF_extra_info) struct xen_netif_tx_request { grant_ref_t gref; /* Reference to buffer page */ uint16_t offset; /* Offset within buffer page */ - uint16_t flags; /* NETTXF_* */ + uint16_t flags; /* XEN_NETTXF_* */ uint16_t id; /* Echoed in response message. */ uint16_t size; /* Packet size in bytes. */ }; -/* Types of netif_extra_info descriptors. */ -#define XEN_NETIF_EXTRA_TYPE_NONE (0) /* Never used - invalid */ -#define XEN_NETIF_EXTRA_TYPE_GSO (1) /* u.gso */ -#define XEN_NETIF_EXTRA_TYPE_MAX (2) +/* Types of xen_netif_extra_info descriptors. */ +#define XEN_NETIF_EXTRA_TYPE_NONE (0) /* Never used - invalid */ +#define XEN_NETIF_EXTRA_TYPE_GSO (1) /* u.gso */ +#define XEN_NETIF_EXTRA_TYPE_MAX (2) -/* netif_extra_info flags. */ -#define _XEN_NETIF_EXTRA_FLAG_MORE (0) -#define XEN_NETIF_EXTRA_FLAG_MORE (1U<<_XEN_NETIF_EXTRA_FLAG_MORE) +/* xen_netif_extra_info flags. */ +#define _XEN_NETIF_EXTRA_FLAG_MORE (0) +#define XEN_NETIF_EXTRA_FLAG_MORE (1U<<_XEN_NETIF_EXTRA_FLAG_MORE) /* GSO types - only TCPv4 currently supported. */ -#define XEN_NETIF_GSO_TYPE_TCPV4 (1) +#define XEN_NETIF_GSO_TYPE_TCPV4 (1) /* * This structure needs to fit within both netif_tx_request and @@ -107,7 +107,7 @@ struct xen_netif_extra_info { struct xen_netif_tx_response { uint16_t id; - int16_t status; /* NETIF_RSP_* */ + int16_t status; /* XEN_NETIF_RSP_* */ }; struct xen_netif_rx_request { @@ -116,25 +116,29 @@ struct xen_netif_rx_request { }; /* Packet data has been validated against protocol checksum. */ -#define _NETRXF_data_validated (0) -#define NETRXF_data_validated (1U<<_NETRXF_data_validated) +#define _XEN_NETRXF_data_validated (0) +#define XEN_NETRXF_data_validated (1U<<_XEN_NETRXF_data_validated) /* Protocol checksum field is blank in the packet (hardware offload)? */ -#define _NETRXF_csum_blank (1) -#define NETRXF_csum_blank (1U<<_NETRXF_csum_blank) +#define _XEN_NETRXF_csum_blank (1) +#define XEN_NETRXF_csum_blank (1U<<_XEN_NETRXF_csum_blank) /* Packet continues in the next request descriptor. */ -#define _NETRXF_more_data (2) -#define NETRXF_more_data (1U<<_NETRXF_more_data) +#define _XEN_NETRXF_more_data (2) +#define XEN_NETRXF_more_data (1U<<_XEN_NETRXF_more_data) /* Packet to be followed by extra descriptor(s). */ -#define _NETRXF_extra_info (3) -#define NETRXF_extra_info (1U<<_NETRXF_extra_info) +#define _XEN_NETRXF_extra_info (3) +#define XEN_NETRXF_extra_info (1U<<_XEN_NETRXF_extra_info) + +/* GSO Prefix descriptor. */ +#define _XEN_NETRXF_gso_prefix (4) +#define XEN_NETRXF_gso_prefix (1U<<_XEN_NETRXF_gso_prefix) struct xen_netif_rx_response { uint16_t id; uint16_t offset; /* Offset in page of start of received packet */ - uint16_t flags; /* NETRXF_* */ + uint16_t flags; /* XEN_NETRXF_* */ int16_t status; /* -ve: BLKIF_RSP_* ; +ve: Rx'ed pkt size. */ }; @@ -149,10 +153,10 @@ DEFINE_RING_TYPES(xen_netif_rx, struct xen_netif_rx_request, struct xen_netif_rx_response); -#define NETIF_RSP_DROPPED -2 -#define NETIF_RSP_ERROR -1 -#define NETIF_RSP_OKAY 0 -/* No response: used for auxiliary requests (e.g., netif_tx_extra). */ -#define NETIF_RSP_NULL 1 +#define XEN_NETIF_RSP_DROPPED -2 +#define XEN_NETIF_RSP_ERROR -1 +#define XEN_NETIF_RSP_OKAY 0 +/* No response: used for auxiliary requests (e.g., xen_netif_extra_info). */ +#define XEN_NETIF_RSP_NULL 1 #endif |