From e06e7c615877026544ad7f8b309d1a3706410383 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 10 Jun 2007 17:22:39 -0700 Subject: [IPV4]: The scheduled removal of multipath cached routing support. With help from Chris Wedgwood. Signed-off-by: David S. Miller --- include/linux/Kbuild | 1 - include/linux/ip_mp_alg.h | 22 ---------------------- include/linux/rtnetlink.h | 2 +- 3 files changed, 1 insertion(+), 24 deletions(-) delete mode 100644 include/linux/ip_mp_alg.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index afae306b177..d9445168276 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -91,7 +91,6 @@ header-y += in6.h header-y += in_route.h header-y += ioctl.h header-y += ipmi_msgdefs.h -header-y += ip_mp_alg.h header-y += ipsec.h header-y += ipx.h header-y += irda.h diff --git a/include/linux/ip_mp_alg.h b/include/linux/ip_mp_alg.h deleted file mode 100644 index e234e2008f5..00000000000 --- a/include/linux/ip_mp_alg.h +++ /dev/null @@ -1,22 +0,0 @@ -/* ip_mp_alg.h: IPV4 multipath algorithm support, user-visible values. - * - * Copyright (C) 2004, 2005 Einar Lueck - * Copyright (C) 2005 David S. Miller - */ - -#ifndef _LINUX_IP_MP_ALG_H -#define _LINUX_IP_MP_ALG_H - -enum ip_mp_alg { - IP_MP_ALG_NONE, - IP_MP_ALG_RR, - IP_MP_ALG_DRR, - IP_MP_ALG_RANDOM, - IP_MP_ALG_WRANDOM, - __IP_MP_ALG_MAX -}; - -#define IP_MP_ALG_MAX (__IP_MP_ALG_MAX - 1) - -#endif /* _LINUX_IP_MP_ALG_H */ - diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 1fae30af91f..61278584853 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -261,7 +261,7 @@ enum rtattr_type_t RTA_FLOW, RTA_CACHEINFO, RTA_SESSION, - RTA_MP_ALGO, + RTA_MP_ALGO, /* no longer used */ RTA_TABLE, __RTA_MAX }; -- cgit v1.2.3 From 8c7b7faaa630fef7f68d8728cee1cce398cc9697 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 10 Jul 2007 22:08:12 -0700 Subject: [NET]: Kill eth_copy_and_sum(). It hasn't "summed" anything in over 7 years, and it's just a straight mempcy ala skb_copy_to_linear_data() so just get rid of it. Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 071c67abed8..f48eb89efd0 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -40,12 +40,6 @@ extern int eth_header_cache(struct neighbour *neigh, struct hh_cache *hh); extern struct net_device *alloc_etherdev(int sizeof_priv); -static inline void eth_copy_and_sum (struct sk_buff *dest, - const unsigned char *src, - int len, int base) -{ - memcpy (dest->data, src, len); -} /** * is_zero_ether_addr - Determine if give Ethernet address is all zeros. -- cgit v1.2.3 From 6472ce6096bf27d85a1f2580964a36f290bd60a9 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 13 Jun 2007 12:03:21 -0700 Subject: [NET]: Mark struct net_device * argument to netdev_priv const Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3a70f553b28..94cc77cd3aa 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -546,7 +546,7 @@ struct net_device #define NETDEV_ALIGN 32 #define NETDEV_ALIGN_CONST (NETDEV_ALIGN - 1) -static inline void *netdev_priv(struct net_device *dev) +static inline void *netdev_priv(const struct net_device *dev) { return (char *)dev + ((sizeof(struct net_device) + NETDEV_ALIGN_CONST) -- cgit v1.2.3 From 38f7b870d4a6a5d3ec21557e849620cb7d032965 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 13 Jun 2007 12:03:51 -0700 Subject: [RTNETLINK]: Link creation API Add rtnetlink API for creating, changing and deleting software devices. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_link.h | 13 +++++++++++++ include/linux/netdevice.h | 3 +++ 2 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 604c2434f71..3144babd235 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -76,6 +76,8 @@ enum #define IFLA_WEIGHT IFLA_WEIGHT IFLA_OPERSTATE, IFLA_LINKMODE, + IFLA_LINKINFO, +#define IFLA_LINKINFO IFLA_LINKINFO __IFLA_MAX }; @@ -140,4 +142,15 @@ struct ifla_cacheinfo __u32 retrans_time; }; +enum +{ + IFLA_INFO_UNSPEC, + IFLA_INFO_KIND, + IFLA_INFO_DATA, + IFLA_INFO_XSTATS, + __IFLA_INFO_MAX, +}; + +#define IFLA_INFO_MAX (__IFLA_INFO_MAX - 1) + #endif /* _LINUX_IF_LINK_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 94cc77cd3aa..e7913ee5581 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -540,6 +540,9 @@ struct net_device struct device dev; /* space for optional statistics and wireless sysfs groups */ struct attribute_group *sysfs_groups[3]; + + /* rtnetlink link ops */ + const struct rtnl_link_ops *rtnl_link_ops; }; #define to_net_dev(d) container_of(d, struct net_device, dev) -- cgit v1.2.3 From 734423cf38021966a5d3bd5f5c6aaecaf32fb4ac Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 13 Jun 2007 12:07:07 -0700 Subject: [VLAN]: Use 32 bit value for skb->priority mapping skb->priority has only 32 bits and even VLAN uses 32 bit values in its API. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 81e9bc93569..aeddb49193f 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -99,7 +99,7 @@ static inline void vlan_group_set_device(struct vlan_group *vg, int vlan_id, } struct vlan_priority_tci_mapping { - unsigned long priority; + u32 priority; unsigned short vlan_qos; /* This should be shifted when first set, so we only do it * at provisioning time. * ((skb->priority << 13) & 0xE000) @@ -112,7 +112,7 @@ struct vlan_dev_info { /** This will be the mapping that correlates skb->priority to * 3 bits of VLAN QOS tags... */ - unsigned long ingress_priority_map[8]; + u32 ingress_priority_map[8]; struct vlan_priority_tci_mapping *egress_priority_map[16]; /* hash table */ unsigned short vlan_id; /* The VLAN Identifier for this interface. */ -- cgit v1.2.3 From b020cb488586f982f40eb257a32e92a4de710d65 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 13 Jun 2007 12:07:22 -0700 Subject: [VLAN]: Keep track of number of QoS mappings Keep track of the number of configured ingress/egress QoS mappings to avoid iteration while calculating the netlink attribute size. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index aeddb49193f..b46d4225f74 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -112,7 +112,10 @@ struct vlan_dev_info { /** This will be the mapping that correlates skb->priority to * 3 bits of VLAN QOS tags... */ + unsigned int nr_ingress_mappings; u32 ingress_priority_map[8]; + + unsigned int nr_egress_mappings; struct vlan_priority_tci_mapping *egress_priority_map[16]; /* hash table */ unsigned short vlan_id; /* The VLAN Identifier for this interface. */ -- cgit v1.2.3 From a4bf3af4ac46802436d352ef409cee4fe80445b3 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 13 Jun 2007 12:07:37 -0700 Subject: [VLAN]: Introduce symbolic constants for flag values Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index b46d4225f74..c7912876a21 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -398,6 +398,10 @@ enum vlan_ioctl_cmds { GET_VLAN_VID_CMD /* Get the VID of this VLAN (specified by name) */ }; +enum vlan_flags { + VLAN_FLAG_REORDER_HDR = 0x1, +}; + enum vlan_name_types { VLAN_NAME_TYPE_PLUS_VID, /* Name will look like: vlan0005 */ VLAN_NAME_TYPE_RAW_PLUS_VID, /* name will look like: eth1.0005 */ -- cgit v1.2.3 From 07b5b17e157b7018d0ca40ca0d1581a23096fb45 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 13 Jun 2007 12:07:54 -0700 Subject: [VLAN]: Use rtnl_link API Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_link.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 3144babd235..422084d18ce 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -153,4 +153,38 @@ enum #define IFLA_INFO_MAX (__IFLA_INFO_MAX - 1) +/* VLAN section */ + +enum +{ + IFLA_VLAN_UNSPEC, + IFLA_VLAN_ID, + IFLA_VLAN_FLAGS, + IFLA_VLAN_EGRESS_QOS, + IFLA_VLAN_INGRESS_QOS, + __IFLA_VLAN_MAX, +}; + +#define IFLA_VLAN_MAX (__IFLA_VLAN_MAX - 1) + +struct ifla_vlan_flags { + __u32 flags; + __u32 mask; +}; + +enum +{ + IFLA_VLAN_QOS_UNSPEC, + IFLA_VLAN_QOS_MAPPING, + __IFLA_VLAN_QOS_MAX +}; + +#define IFLA_VLAN_QOS_MAX (__IFLA_VLAN_QOS_MAX - 1) + +struct ifla_vlan_qos_mapping +{ + __u32 from; + __u32 to; +}; + #endif /* _LINUX_IF_LINK_H */ -- cgit v1.2.3 From f1c91da44728fba24927e44056a56e507c11cf7b Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Sat, 16 Jun 2007 12:38:51 -0300 Subject: [KTIME]: Introduce ktime_us_delta This provides a reusable time difference function which returns the difference in microseconds, as often used in the DCCP code. Commiter note: renamed ktime_delta to ktime_us_delta and put it in ktime.h. Signed-off-by: Gerrit Renker Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/ktime.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 2b139f66027..923665958f9 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -279,6 +279,11 @@ static inline s64 ktime_to_us(const ktime_t kt) return (s64) tv.tv_sec * USEC_PER_SEC + tv.tv_usec; } +static inline s64 ktime_us_delta(const ktime_t later, const ktime_t earlier) +{ + return ktime_to_us(ktime_sub(later, earlier)); +} + /* * The resolution of the clocks. The resolution value is returned in * the clock_getres() system call to give application programmers an -- cgit v1.2.3 From 1e180f726a58089d15637b5495fecbad8c50c833 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 16 Jun 2007 12:39:38 -0300 Subject: [KTIME]: Introduce ktime_add_us Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/ktime.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 923665958f9..dae7143644f 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -284,6 +284,11 @@ static inline s64 ktime_us_delta(const ktime_t later, const ktime_t earlier) return ktime_to_us(ktime_sub(later, earlier)); } +static inline ktime_t ktime_add_us(const ktime_t kt, const u64 usec) +{ + return ktime_add_ns(kt, usec * 1000); +} + /* * The resolution of the clocks. The resolution value is returned in * the clock_getres() system call to give application programmers an -- cgit v1.2.3 From 334a8132d9950f769f390f0f35c233d099688e7a Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 25 Jun 2007 04:35:20 -0700 Subject: [SKBUFF]: Keep track of writable header len of headerless clones Currently NAT (and others) that want to modify cloned skbs copy them, even if in the vast majority of cases its not necessary because the skb is a clone made by TCP and the portion NAT wants to modify is actually writable because TCP release the header reference before cloning. The problem is that there is no clean way for NAT to find out how long the writable header area is, so this patch introduces skb->hdr_len to hold this length. When a headerless skb is cloned skb->hdr_len is set to the current headroom, for regular clones it is copied from the original. A new function skb_clone_writable(skb, len) returns whether the skb is writable up to len bytes from skb->data. To avoid enlarging the skb the mac_len field is reduced to 16 bit and the new hdr_len field is put in the remaining 16 bit. I've done a few rough benchmarks of NAT (not with this exact patch, but a very similar one). As expected it saves huge amounts of system time in case of sendfile, bringing it down to basically the same amount as without NAT, with sendmsg it only helps on loopback, probably because of the large MTU. Transmit a 1GB file using sendfile/sendmsg over eth0/lo with and without NAT: - sendfile eth0, no NAT: sys 0m0.388s - sendfile eth0, NAT: sys 0m1.835s - sendfile eth0: NAT + path: sys 0m0.370s (~ -80%) - sendfile lo, no NAT: sys 0m0.258s - sendfile lo, NAT: sys 0m2.609s - sendfile lo, NAT + patch: sys 0m0.260s (~ -90%) - sendmsg eth0, no NAT: sys 0m2.508s - sendmsg eth0, NAT: sys 0m2.539s - sendmsg eth0, NAT + patch: sys 0m2.445s (no change) - sendmsg lo, no NAT: sys 0m2.151s - sendmsg lo, NAT: sys 0m3.557s - sendmsg lo, NAT + patch: sys 0m2.159s (~ -40%) I expect other users can see a similar performance improvement, packet mangling iptables targets, ipip and ip_gre come to mind .. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/skbuff.h | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6f0b2f7d001..881fe80f01d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -147,8 +147,8 @@ struct skb_shared_info { /* We divide dataref into two halves. The higher 16 bits hold references * to the payload part of skb->data. The lower 16 bits hold references to - * the entire skb->data. It is up to the users of the skb to agree on - * where the payload starts. + * the entire skb->data. A clone of a headerless skb holds the length of + * the header in skb->hdr_len. * * All users must obey the rule that the skb->data reference count must be * greater than or equal to the payload reference count. @@ -206,6 +206,7 @@ typedef unsigned char *sk_buff_data_t; * @len: Length of actual data * @data_len: Data length * @mac_len: Length of link layer header + * @hdr_len: writable header length of cloned skb * @csum: Checksum (must include start/offset pair) * @csum_start: Offset from skb->head where checksumming should start * @csum_offset: Offset from csum_start where checksum should be stored @@ -260,8 +261,9 @@ struct sk_buff { char cb[48]; unsigned int len, - data_len, - mac_len; + data_len; + __u16 mac_len, + hdr_len; union { __wsum csum; struct { @@ -1321,6 +1323,20 @@ static inline struct sk_buff *netdev_alloc_skb(struct net_device *dev, return __netdev_alloc_skb(dev, length, GFP_ATOMIC); } +/** + * skb_clone_writable - is the header of a clone writable + * @skb: buffer to check + * @len: length up to which to write + * + * Returns true if modifying the header part of the cloned buffer + * does not requires the data to be copied. + */ +static inline int skb_clone_writable(struct sk_buff *skb, int len) +{ + return !skb_header_cloned(skb) && + skb_headroom(skb) + len <= skb->hdr_len; +} + /** * skb_cow - copy header of skb when it is required * @skb: buffer to cow -- cgit v1.2.3 From afdc3238ec948531205f5c5f77d2de7bae519c71 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 25 Jun 2007 14:30:16 -0700 Subject: [RTNETLINK]: Add nested compat attribute Add a nested compat attribute type that can be used to convert attributes that contain a structure to nested attributes in a backwards compatible way. The attribute looks like this: struct { [ compat contents ] struct rtattr { .rta_len = total size, .rta_type = type, } rta; struct old_structure struct; [ nested top-level attribute ] struct rtattr { .rta_len = nest size, .rta_type = type, } nest_attr; [ optional 0 .. n nested attributes ] struct rtattr { .rta_len = private attribute len, .rta_type = private attribute typ, } nested_attr; struct nested_data data; }; Since both userspace and kernel deal correctly with attributes that are larger than expected old versions will just parse the compat part and ignore the rest. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 61278584853..6731e7f4cc0 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -570,6 +570,8 @@ static __inline__ int rtattr_strcmp(const struct rtattr *rta, const char *str) } extern int rtattr_parse(struct rtattr *tb[], int maxattr, struct rtattr *rta, int len); +extern int rtattr_parse_nested_compat(struct rtattr *tb[], int maxattr, + struct rtattr *rta, void **data, int len); #define rtattr_parse_nested(tb, max, rta) \ rtattr_parse((tb), (max), RTA_DATA((rta)), RTA_PAYLOAD((rta))) @@ -638,6 +640,18 @@ extern void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const voi ({ (start)->rta_len = skb_tail_pointer(skb) - (unsigned char *)(start); \ (skb)->len; }) +#define RTA_NEST_COMPAT(skb, type, attrlen, data) \ +({ struct rtattr *__start = (struct rtattr *)skb_tail_pointer(skb); \ + RTA_PUT(skb, type, attrlen, data); \ + RTA_NEST(skb, type); \ + __start; }) + +#define RTA_NEST_COMPAT_END(skb, start) \ +({ struct rtattr *__nest = (void *)(start) + NLMSG_ALIGN((start)->rta_len); \ + (start)->rta_len = skb_tail_pointer(skb) - (unsigned char *)(start); \ + RTA_NEST_END(skb, __nest); \ + (skb)->len; }) + #define RTA_NEST_CANCEL(skb, start) \ ({ if (start) \ skb_trim(skb, (unsigned char *) (start) - (skb)->data); \ -- cgit v1.2.3 From 2371baa4bdab3268b32009926f75e7a5d3a41506 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 26 Jun 2007 03:23:44 -0700 Subject: [RTNETLINK]: Fix rtnetlink compat attribute patch Sent the wrong patch previously. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 6731e7f4cc0..c91476ce314 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -570,12 +570,16 @@ static __inline__ int rtattr_strcmp(const struct rtattr *rta, const char *str) } extern int rtattr_parse(struct rtattr *tb[], int maxattr, struct rtattr *rta, int len); -extern int rtattr_parse_nested_compat(struct rtattr *tb[], int maxattr, - struct rtattr *rta, void **data, int len); +extern int __rtattr_parse_nested_compat(struct rtattr *tb[], int maxattr, + struct rtattr *rta, int len); #define rtattr_parse_nested(tb, max, rta) \ rtattr_parse((tb), (max), RTA_DATA((rta)), RTA_PAYLOAD((rta))) +#define rtattr_parse_nested_compat(tb, max, rta, data, len) \ +({ data = RTA_PAYLOAD(rta) >= len ? RTA_DATA(rta) : NULL; \ + __rtattr_parse_nested_compat(tb, max, rta, len); }) + extern int rtnetlink_send(struct sk_buff *skb, u32 pid, u32 group, int echo); extern int rtnl_unicast(struct sk_buff *skb, u32 pid); extern int rtnl_notify(struct sk_buff *skb, u32 pid, u32 group, -- cgit v1.2.3 From 59fbb3a61e02deaeaa4fb50792217921f3002d64 Mon Sep 17 00:00:00 2001 From: Masahide NAKAMURA Date: Tue, 26 Jun 2007 23:56:32 -0700 Subject: [IPV6] MIP6: Loadable module support for MIPv6. This patch makes MIPv6 loadable module named "mip6". Here is a modprobe.conf(5) example to load it automatically when user application uses XFRM state for MIPv6: alias xfrm-type-10-43 mip6 alias xfrm-type-10-60 mip6 Some MIPv6 feature is not included by this modular, however, it should not be affected to other features like either IPsec or IPv6 with and without the patch. We may discuss XFRM, MH (RAW socket) and ancillary data/sockopt separately for future work. Loadable features: * MH receiving check (to send ICMP error back) * RO header parsing and building (i.e. RH2 and HAO in DSTOPTS) * XFRM policy/state database handling for RO These are NOT covered as loadable: * Home Address flags and its rule on source address selection * XFRM sub policy (depends on its own kernel option) * XFRM functions to receive RO as IPv6 extension header * MH sending/receiving through raw socket if user application opens it (since raw socket allows to do so) * RH2 sending as ancillary data * RH2 operation with setsockopt(2) Signed-off-by: Masahide NAKAMURA Signed-off-by: David S. Miller --- include/linux/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 648bd1f0912..213b63be3c8 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -247,7 +247,7 @@ struct inet6_skb_parm { __u16 lastopt; __u32 nhoff; __u16 flags; -#ifdef CONFIG_IPV6_MIP6 +#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) __u16 dsthao; #endif -- cgit v1.2.3 From d212f87b068c9d72065ef579d85b5ee6b8b59381 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Wed, 27 Jun 2007 00:47:37 -0700 Subject: [NET]: IPV6 checksum offloading in network devices The existing model for checksum offload does not correctly handle devices that can offload IPV4 and IPV6 only. The NETIF_F_HW_CSUM flag implies device can do any arbitrary protocol. This patch: * adds NETIF_F_IPV6_CSUM for those devices * fixes bnx2 and tg3 devices that need it * add NETIF_F_IPV6_CSUM to ipv6 output (incl GSO) * fixes assumptions about NETIF_F_ALL_CSUM in nat * adjusts bridge union of checksumming computation Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e7913ee5581..7a8f22fb4ee 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -314,9 +314,10 @@ struct net_device /* Net device features */ unsigned long features; #define NETIF_F_SG 1 /* Scatter/gather IO. */ -#define NETIF_F_IP_CSUM 2 /* Can checksum only TCP/UDP over IPv4. */ +#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. */ #define NETIF_F_HW_CSUM 8 /* Can checksum all the packets. */ +#define NETIF_F_IPV6_CSUM 16 /* Can checksum TCP/UDP over IPV6 */ #define NETIF_F_HIGHDMA 32 /* Can DMA to high memory. */ #define NETIF_F_FRAGLIST 64 /* Scatter/gather IO. */ #define NETIF_F_HW_VLAN_TX 128 /* Transmit VLAN hw acceleration */ @@ -338,8 +339,11 @@ struct net_device /* List of features with software fallbacks. */ #define NETIF_F_GSO_SOFTWARE (NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6) + #define NETIF_F_GEN_CSUM (NETIF_F_NO_CSUM | NETIF_F_HW_CSUM) -#define NETIF_F_ALL_CSUM (NETIF_F_IP_CSUM | NETIF_F_GEN_CSUM) +#define NETIF_F_V4_CSUM (NETIF_F_GEN_CSUM | NETIF_F_IP_CSUM) +#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) struct net_device *next_sched; -- cgit v1.2.3 From bf742482d7a647c5c6f03f78eb35a862e159ecf5 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 27 Jun 2007 01:26:19 -0700 Subject: [NET]: dev: introduce generic net_device address lists Introduce struct dev_addr_list and list maintenance functions based on dev_mc_list and the related functions. This will be used by follow-up patches for both multicast and secondary unicast addresses. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netdevice.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7a8f22fb4ee..aa389c77aa3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -177,6 +177,14 @@ struct netif_rx_stats DECLARE_PER_CPU(struct netif_rx_stats, netdev_rx_stat); +struct dev_addr_list +{ + struct dev_addr_list *next; + u8 da_addr[MAX_ADDR_LEN]; + u8 da_addrlen; + int da_users; + int da_gusers; +}; /* * We tag multicasts with these structures. @@ -1008,6 +1016,9 @@ extern void dev_mc_upload(struct net_device *dev); extern int dev_mc_delete(struct net_device *dev, void *addr, int alen, int all); extern int dev_mc_add(struct net_device *dev, void *addr, int alen, int newonly); extern void dev_mc_discard(struct net_device *dev); +extern int __dev_addr_delete(struct dev_addr_list **list, void *addr, int alen, int all); +extern int __dev_addr_add(struct dev_addr_list **list, void *addr, int alen, int newonly); +extern void __dev_addr_discard(struct dev_addr_list **list); extern void dev_set_promiscuity(struct net_device *dev, int inc); extern void dev_set_allmulti(struct net_device *dev, int inc); extern void netdev_state_change(struct net_device *dev); -- cgit v1.2.3 From 3fba5a8b1e3df2384b90493538161e83cf15dd5f Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 27 Jun 2007 01:26:58 -0700 Subject: [NET]: dev_mcast: switch to generic net_device address lists Use generic net_device address lists for multicast list handling. Some defines are used to keep drivers working. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netdevice.h | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index aa389c77aa3..9e114e77e54 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -189,15 +189,12 @@ struct dev_addr_list /* * We tag multicasts with these structures. */ - -struct dev_mc_list -{ - struct dev_mc_list *next; - __u8 dmi_addr[MAX_ADDR_LEN]; - unsigned char dmi_addrlen; - int dmi_users; - int dmi_gusers; -}; + +#define dev_mc_list dev_addr_list +#define dmi_addr da_addr +#define dmi_addrlen da_addrlen +#define dmi_users da_users +#define dmi_gusers da_gusers struct hh_cache { @@ -400,7 +397,7 @@ struct net_device unsigned char addr_len; /* hardware address length */ unsigned short dev_id; /* for shared network cards */ - struct dev_mc_list *mc_list; /* Multicast mac addresses */ + struct dev_addr_list *mc_list; /* Multicast mac addresses */ int mc_count; /* Number of installed mcasts */ int promiscuity; int allmulti; -- cgit v1.2.3 From 4417da668c0021903464f92db278ddae348e0299 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 27 Jun 2007 01:28:10 -0700 Subject: [NET]: dev: secondary unicast address support Add support for configuring secondary unicast addresses on network devices. To support this devices capable of filtering multiple unicast addresses need to change their set_multicast_list function to configure unicast filters as well and assign it to dev->set_rx_mode instead of dev->set_multicast_list. Other devices are put into promiscous mode when secondary unicast addresses are present. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netdevice.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9e114e77e54..2c0cc19edfb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -397,6 +397,9 @@ struct net_device unsigned char addr_len; /* hardware address length */ unsigned short dev_id; /* for shared network cards */ + struct dev_addr_list *uc_list; /* Secondary unicast mac addresses */ + int uc_count; /* Number of installed ucasts */ + int uc_promisc; struct dev_addr_list *mc_list; /* Multicast mac addresses */ int mc_count; /* Number of installed mcasts */ int promiscuity; @@ -502,6 +505,8 @@ struct net_device void *saddr, unsigned len); int (*rebuild_header)(struct sk_buff *skb); +#define HAVE_SET_RX_MODE + void (*set_rx_mode)(struct net_device *dev); #define HAVE_MULTICAST void (*set_multicast_list)(struct net_device *dev); #define HAVE_SET_MAC_ADDR @@ -1008,8 +1013,11 @@ extern struct net_device *alloc_netdev(int sizeof_priv, const char *name, void (*setup)(struct net_device *)); extern int register_netdev(struct net_device *dev); extern void unregister_netdev(struct net_device *dev); -/* Functions used for multicast support */ -extern void dev_mc_upload(struct net_device *dev); +/* Functions used for secondary unicast and multicast support */ +extern void dev_set_rx_mode(struct net_device *dev); +extern void __dev_set_rx_mode(struct net_device *dev); +extern int dev_unicast_delete(struct net_device *dev, void *addr, int alen); +extern int dev_unicast_add(struct net_device *dev, void *addr, int alen); extern int dev_mc_delete(struct net_device *dev, void *addr, int alen, int all); extern int dev_mc_add(struct net_device *dev, void *addr, int alen, int newonly); extern void dev_mc_discard(struct net_device *dev); -- cgit v1.2.3 From 342f0234c71b40da785dd6a7ce1dd481ecbfdb81 Mon Sep 17 00:00:00 2001 From: James Chapman Date: Wed, 27 Jun 2007 15:37:46 -0700 Subject: [UDP]: Introduce UDP encapsulation type for L2TP This patch adds a new UDP_ENCAP_L2TPINUDP encapsulation type for UDP sockets. When a UDP socket's encap_type is UDP_ENCAP_L2TPINUDP, the skb is delivered to a function pointed to by the udp_sock's encap_rcv funcptr. If the skb isn't wanted by L2TP, it returns >0, which causes it to be passed through to UDP. Include padding to put the new encap_rcv field on a 4-byte boundary. Previously, the only user of UDP encap sockets was ESP, so when CONFIG_XFRM was not defined, some of the encap code was compiled out. This patch changes that. As a result, udp_encap_rcv() will now do a little more work when CONFIG_XFRM is not defined. Signed-off-by: James Chapman Signed-off-by: David S. Miller --- include/linux/udp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index 6de445c31a6..8ec703f462d 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -42,6 +42,7 @@ static inline struct udphdr *udp_hdr(const struct sk_buff *skb) /* UDP encapsulation types */ #define UDP_ENCAP_ESPINUDP_NON_IKE 1 /* draft-ietf-ipsec-nat-t-ike-00/01 */ #define UDP_ENCAP_ESPINUDP 2 /* draft-ietf-ipsec-udp-encaps-06 */ +#define UDP_ENCAP_L2TPINUDP 3 /* rfc2661 */ #ifdef __KERNEL__ #include @@ -70,6 +71,11 @@ struct udp_sock { #define UDPLITE_SEND_CC 0x2 /* set via udplite setsockopt */ #define UDPLITE_RECV_CC 0x4 /* set via udplite setsocktopt */ __u8 pcflag; /* marks socket as UDP-Lite if > 0 */ + __u8 unused[3]; + /* + * For encapsulation sockets. + */ + int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); }; static inline struct udp_sock *udp_sk(const struct sock *sk) -- cgit v1.2.3 From cf14a4d06742d59ecb2d837a3f53bb24d1ff9acb Mon Sep 17 00:00:00 2001 From: James Chapman Date: Wed, 27 Jun 2007 15:43:43 -0700 Subject: [L2TP]: Changes to existing ppp and socket kernel headers for L2TP Add struct sockaddr_pppol2tp to carry L2TP-specific address information for the PPPoX (PPPoL2TP) socket. Unfortunately we can't use the union inside struct sockaddr_pppox because the L2TP-specific data is larger than the current size of the union and we must preserve the size of struct sockaddr_pppox for binary compatibility. Also add a PPPIOCGL2TPSTATS ioctl to allow userspace to obtain L2TP counters and state from the kernel. Add new if_pppol2tp.h header. [ Modified to use aligned_u64 in statistics structure -DaveM ] Signed-off-by: James Chapman Signed-off-by: David S. Miller --- include/linux/Kbuild | 1 + include/linux/if_ppp.h | 16 +++++++++++ include/linux/if_pppol2tp.h | 69 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/if_pppox.h | 16 +++++++++-- include/linux/socket.h | 1 + 5 files changed, 101 insertions(+), 2 deletions(-) create mode 100644 include/linux/if_pppol2tp.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index d9445168276..127d2d192b5 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -225,6 +225,7 @@ unifdef-y += if_fddi.h unifdef-y += if_frad.h unifdef-y += if_ltalk.h unifdef-y += if_link.h +unifdef-y += if_pppol2tp.h unifdef-y += if_pppox.h unifdef-y += if_shaper.h unifdef-y += if_tr.h diff --git a/include/linux/if_ppp.h b/include/linux/if_ppp.h index 768372f07ca..0f2f70d4e48 100644 --- a/include/linux/if_ppp.h +++ b/include/linux/if_ppp.h @@ -110,6 +110,21 @@ struct ifpppcstatsreq { struct ppp_comp_stats stats; }; +/* For PPPIOCGL2TPSTATS */ +struct pppol2tp_ioc_stats { + __u16 tunnel_id; /* redundant */ + __u16 session_id; /* if zero, get tunnel stats */ + __u32 using_ipsec:1; /* valid only for session_id == 0 */ + aligned_u64 tx_packets; + aligned_u64 tx_bytes; + aligned_u64 tx_errors; + aligned_u64 rx_packets; + aligned_u64 rx_bytes; + aligned_u64 rx_seq_discards; + aligned_u64 rx_oos_packets; + aligned_u64 rx_errors; +}; + #define ifr__name b.ifr_ifrn.ifrn_name #define stats_ptr b.ifr_ifru.ifru_data @@ -146,6 +161,7 @@ struct ifpppcstatsreq { #define PPPIOCDISCONN _IO('t', 57) /* disconnect channel */ #define PPPIOCATTCHAN _IOW('t', 56, int) /* attach to ppp channel */ #define PPPIOCGCHAN _IOR('t', 55, int) /* get ppp channel number */ +#define PPPIOCGL2TPSTATS _IOR('t', 54, struct pppol2tp_ioc_stats) #define SIOCGPPPSTATS (SIOCDEVPRIVATE + 0) #define SIOCGPPPVER (SIOCDEVPRIVATE + 1) /* NEVER change this!! */ diff --git a/include/linux/if_pppol2tp.h b/include/linux/if_pppol2tp.h new file mode 100644 index 00000000000..516203b6fde --- /dev/null +++ b/include/linux/if_pppol2tp.h @@ -0,0 +1,69 @@ +/*************************************************************************** + * Linux PPP over L2TP (PPPoL2TP) Socket Implementation (RFC 2661) + * + * This file supplies definitions required by the PPP over L2TP driver + * (pppol2tp.c). All version information wrt this file is located in pppol2tp.c + * + * License: + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#ifndef __LINUX_IF_PPPOL2TP_H +#define __LINUX_IF_PPPOL2TP_H + +#include + +#ifdef __KERNEL__ +#include +#endif + +/* Structure used to connect() the socket to a particular tunnel UDP + * socket. + */ +struct pppol2tp_addr +{ + pid_t pid; /* pid that owns the fd. + * 0 => current */ + int fd; /* FD of UDP socket to use */ + + struct sockaddr_in addr; /* IP address and port to send to */ + + __be16 s_tunnel, s_session; /* For matching incoming packets */ + __be16 d_tunnel, d_session; /* For sending outgoing packets */ +}; + +/* Socket options: + * DEBUG - bitmask of debug message categories + * SENDSEQ - 0 => don't send packets with sequence numbers + * 1 => send packets with sequence numbers + * RECVSEQ - 0 => receive packet sequence numbers are optional + * 1 => drop receive packets without sequence numbers + * LNSMODE - 0 => act as LAC. + * 1 => act as LNS. + * REORDERTO - reorder timeout (in millisecs). If 0, don't try to reorder. + */ +enum { + PPPOL2TP_SO_DEBUG = 1, + PPPOL2TP_SO_RECVSEQ = 2, + PPPOL2TP_SO_SENDSEQ = 3, + PPPOL2TP_SO_LNSMODE = 4, + PPPOL2TP_SO_REORDERTO = 5, +}; + +/* Debug message categories for the DEBUG socket option */ +enum { + PPPOL2TP_MSG_DEBUG = (1 << 0), /* verbose debug (if + * compiled in) */ + PPPOL2TP_MSG_CONTROL = (1 << 1), /* userspace - kernel + * interface */ + PPPOL2TP_MSG_SEQ = (1 << 2), /* sequence numbers */ + PPPOL2TP_MSG_DATA = (1 << 3), /* data packets */ +}; + + + +#endif diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h index 6f987be60fe..25652545ba6 100644 --- a/include/linux/if_pppox.h +++ b/include/linux/if_pppox.h @@ -27,6 +27,7 @@ #include #include #endif /* __KERNEL__ */ +#include /* For user-space programs to pick up these definitions * which they wouldn't get otherwise without defining __KERNEL__ @@ -50,8 +51,9 @@ struct pppoe_addr{ * Protocols supported by AF_PPPOX */ #define PX_PROTO_OE 0 /* Currently just PPPoE */ -#define PX_MAX_PROTO 1 - +#define PX_PROTO_OL2TP 1 /* Now L2TP also */ +#define PX_MAX_PROTO 2 + struct sockaddr_pppox { sa_family_t sa_family; /* address family, AF_PPPOX */ unsigned int sa_protocol; /* protocol identifier */ @@ -60,6 +62,16 @@ struct sockaddr_pppox { }sa_addr; }__attribute__ ((packed)); +/* The use of the above union isn't viable because the size of this + * struct must stay fixed over time -- applications use sizeof(struct + * sockaddr_pppox) to fill it. We use a protocol specific sockaddr + * type instead. + */ +struct sockaddr_pppol2tp { + sa_family_t sa_family; /* address family, AF_PPPOX */ + unsigned int sa_protocol; /* protocol identifier */ + struct pppol2tp_addr pppol2tp; +}__attribute__ ((packed)); /********************************************************************* * diff --git a/include/linux/socket.h b/include/linux/socket.h index 6e7c9483a6a..fe195c97a89 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -287,6 +287,7 @@ struct ucred { #define SOL_NETLINK 270 #define SOL_TIPC 271 #define SOL_RXRPC 272 +#define SOL_PPPOL2TP 273 /* IPX options */ #define IPX_TYPE 1 -- cgit v1.2.3 From f25f4e44808f0f6c9875d94ef1c41ef86c288eb2 Mon Sep 17 00:00:00 2001 From: Peter P Waskiewicz Jr Date: Fri, 6 Jul 2007 13:36:20 -0700 Subject: [CORE] Stack changes to add multiqueue hardware support API Add the multiqueue hardware device support API to the core network stack. Allow drivers to allocate multiple queues and manage them at the netdev level if they choose to do so. Added a new field to sk_buff, namely queue_mapping, for drivers to know which tx_ring to select based on OS classification of the flow. Signed-off-by: Peter P Waskiewicz Jr Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 3 +- include/linux/netdevice.h | 80 ++++++++++++++++++++++++++++++++++++++++++--- include/linux/skbuff.h | 25 ++++++++++++-- 3 files changed, 99 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index f48eb89efd0..6cdb97365e4 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -39,7 +39,8 @@ extern void eth_header_cache_update(struct hh_cache *hh, struct net_device *dev extern int eth_header_cache(struct neighbour *neigh, struct hh_cache *hh); -extern struct net_device *alloc_etherdev(int sizeof_priv); +extern struct net_device *alloc_etherdev_mq(int sizeof_priv, unsigned int queue_count); +#define alloc_etherdev(sizeof_priv) alloc_etherdev_mq(sizeof_priv, 1) /** * is_zero_ether_addr - Determine if give Ethernet address is all zeros. diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2c0cc19edfb..9817821729c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -108,6 +108,14 @@ struct wireless_dev; #define MAX_HEADER (LL_MAX_HEADER + 48) #endif +struct net_device_subqueue +{ + /* Give a control state for each queue. This struct may contain + * per-queue locks in the future. + */ + unsigned long state; +}; + /* * Network device statistics. Akin to the 2.0 ether stats but * with byte counters. @@ -331,6 +339,7 @@ struct net_device #define NETIF_F_VLAN_CHALLENGED 1024 /* Device cannot handle VLAN packets */ #define NETIF_F_GSO 2048 /* Enable software GSO. */ #define NETIF_F_LLTX 4096 /* LockLess TX */ +#define NETIF_F_MULTI_QUEUE 16384 /* Has multiple TX/RX queues */ /* Segmentation offload features */ #define NETIF_F_GSO_SHIFT 16 @@ -557,6 +566,10 @@ struct net_device /* rtnetlink link ops */ const struct rtnl_link_ops *rtnl_link_ops; + + /* The TX queue control structures */ + unsigned int egress_subqueue_count; + struct net_device_subqueue egress_subqueue[0]; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -565,9 +578,7 @@ struct net_device static inline void *netdev_priv(const struct net_device *dev) { - return (char *)dev + ((sizeof(struct net_device) - + NETDEV_ALIGN_CONST) - & ~NETDEV_ALIGN_CONST); + return dev->priv; } #define SET_MODULE_OWNER(dev) do { } while (0) @@ -719,6 +730,62 @@ static inline int netif_running(const struct net_device *dev) return test_bit(__LINK_STATE_START, &dev->state); } +/* + * Routines to manage the subqueues on a device. We only need start + * stop, and a check if it's stopped. All other device management is + * done at the overall netdevice level. + * Also test the device if we're multiqueue. + */ +static inline void netif_start_subqueue(struct net_device *dev, u16 queue_index) +{ +#ifdef CONFIG_NETDEVICES_MULTIQUEUE + clear_bit(__LINK_STATE_XOFF, &dev->egress_subqueue[queue_index].state); +#endif +} + +static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index) +{ +#ifdef CONFIG_NETDEVICES_MULTIQUEUE +#ifdef CONFIG_NETPOLL_TRAP + if (netpoll_trap()) + return; +#endif + set_bit(__LINK_STATE_XOFF, &dev->egress_subqueue[queue_index].state); +#endif +} + +static inline int netif_subqueue_stopped(const struct net_device *dev, + u16 queue_index) +{ +#ifdef CONFIG_NETDEVICES_MULTIQUEUE + return test_bit(__LINK_STATE_XOFF, + &dev->egress_subqueue[queue_index].state); +#else + return 0; +#endif +} + +static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) +{ +#ifdef CONFIG_NETDEVICES_MULTIQUEUE +#ifdef CONFIG_NETPOLL_TRAP + if (netpoll_trap()) + return; +#endif + if (test_and_clear_bit(__LINK_STATE_XOFF, + &dev->egress_subqueue[queue_index].state)) + __netif_schedule(dev); +#endif +} + +static inline int netif_is_multiqueue(const struct net_device *dev) +{ +#ifdef CONFIG_NETDEVICES_MULTIQUEUE + return (!!(NETIF_F_MULTI_QUEUE & dev->features)); +#else + return 0; +#endif +} /* Use this variant when it is known for sure that it * is executing from interrupt context. @@ -1009,8 +1076,11 @@ static inline void netif_tx_disable(struct net_device *dev) extern void ether_setup(struct net_device *dev); /* Support for loadable net-drivers */ -extern struct net_device *alloc_netdev(int sizeof_priv, const char *name, - void (*setup)(struct net_device *)); +extern struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, + void (*setup)(struct net_device *), + unsigned int queue_count); +#define alloc_netdev(sizeof_priv, name, setup) \ + alloc_netdev_mq(sizeof_priv, name, setup, 1) extern int register_netdev(struct net_device *dev); extern void unregister_netdev(struct net_device *dev); /* Functions used for secondary unicast and multicast support */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 881fe80f01d..2d6a14f5f2f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -196,7 +196,6 @@ typedef unsigned char *sk_buff_data_t; * @sk: Socket we are owned by * @tstamp: Time we arrived * @dev: Device we arrived on/are leaving by - * @iif: ifindex of device we arrived on * @transport_header: Transport layer header * @network_header: Network layer header * @mac_header: Link layer header @@ -231,6 +230,8 @@ typedef unsigned char *sk_buff_data_t; * @nfctinfo: Relationship of this skb to the connection * @nfct_reasm: netfilter conntrack re-assembly pointer * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c + * @iif: ifindex of device we arrived on + * @queue_mapping: Queue mapping for multiqueue devices * @tc_index: Traffic control index * @tc_verd: traffic control verdict * @dma_cookie: a cookie to one of several possible DMA operations @@ -246,8 +247,6 @@ struct sk_buff { struct sock *sk; ktime_t tstamp; struct net_device *dev; - int iif; - /* 4 byte hole on 64 bit*/ struct dst_entry *dst; struct sec_path *sp; @@ -290,12 +289,18 @@ struct sk_buff { #ifdef CONFIG_BRIDGE_NETFILTER struct nf_bridge_info *nf_bridge; #endif + + int iif; + __u16 queue_mapping; + #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ #ifdef CONFIG_NET_CLS_ACT __u16 tc_verd; /* traffic control verdict */ #endif #endif + /* 2 byte hole */ + #ifdef CONFIG_NET_DMA dma_cookie_t dma_cookie; #endif @@ -1725,6 +1730,20 @@ static inline void skb_init_secmark(struct sk_buff *skb) { } #endif +static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping) +{ +#ifdef CONFIG_NETDEVICES_MULTIQUEUE + skb->queue_mapping = queue_mapping; +#endif +} + +static inline void skb_copy_queue_mapping(struct sk_buff *to, const struct sk_buff *from) +{ +#ifdef CONFIG_NETDEVICES_MULTIQUEUE + to->queue_mapping = from->queue_mapping; +#endif +} + static inline int skb_is_gso(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_size; -- cgit v1.2.3 From d62733c8e437fdb58325617c4b3331769ba82d70 Mon Sep 17 00:00:00 2001 From: Peter P Waskiewicz Jr Date: Thu, 28 Jun 2007 21:04:31 -0700 Subject: [SCHED]: Qdisc changes and sch_rr added for multiqueue Add the new sch_rr qdisc for multiqueue network device support. Allow sch_prio and sch_rr to be compiled with or without multiqueue hardware support. sch_rr is part of sch_prio, and is referenced from MODULE_ALIAS. This was done since sch_prio and sch_rr only differ in their dequeue routine. Signed-off-by: Peter P Waskiewicz Jr Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/pkt_sched.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h index d10f3533850..268c51599eb 100644 --- a/include/linux/pkt_sched.h +++ b/include/linux/pkt_sched.h @@ -101,6 +101,15 @@ struct tc_prio_qopt __u8 priomap[TC_PRIO_MAX+1]; /* Map: logical priority -> PRIO band */ }; +enum +{ + TCA_PRIO_UNSPEC, + TCA_PRIO_MQ, + __TCA_PRIO_MAX +}; + +#define TCA_PRIO_MAX (__TCA_PRIO_MAX - 1) + /* TBF section */ struct tc_tbf_qopt -- cgit v1.2.3 From 61cbc2fca6335be52788773b21efdc52a2750924 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sat, 30 Jun 2007 13:35:52 -0700 Subject: [NET]: Fix secondary unicast/multicast address count maintenance When a reference to an existing address is increased or decreased without hitting zero, the address count is incorrectly adjusted. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9817821729c..8590d685d93 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1091,8 +1091,8 @@ extern int dev_unicast_add(struct net_device *dev, void *addr, int alen); extern int dev_mc_delete(struct net_device *dev, void *addr, int alen, int all); extern int dev_mc_add(struct net_device *dev, void *addr, int alen, int newonly); extern void dev_mc_discard(struct net_device *dev); -extern int __dev_addr_delete(struct dev_addr_list **list, void *addr, int alen, int all); -extern int __dev_addr_add(struct dev_addr_list **list, void *addr, int alen, int newonly); +extern int __dev_addr_delete(struct dev_addr_list **list, int *count, void *addr, int alen, int all); +extern int __dev_addr_add(struct dev_addr_list **list, int *count, void *addr, int alen, int newonly); extern void __dev_addr_discard(struct dev_addr_list **list); extern void dev_set_promiscuity(struct net_device *dev, int inc); extern void dev_set_allmulti(struct net_device *dev, int inc); -- cgit v1.2.3 From 8c644623fe7e41f59fe97cdf666cba3cb7ced7d8 Mon Sep 17 00:00:00 2001 From: Guido Guenther Date: Mon, 2 Jul 2007 22:50:25 -0700 Subject: [NET]: Allow group ownership of TUN/TAP devices. Introduce a new syscall TUNSETGROUP for group ownership setting of tap devices. The user now is allowed to send packages if either his euid or his egid matches the one specified via tunctl (via -u or -g respecitvely). If both, gid and uid, are set via tunctl, both have to match. Signed-off-by: Guido Guenther Signed-off-by: Jeff Dike Signed-off-by: David S. Miller --- include/linux/if_tun.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 88aef7b86ef..42eb6945b93 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -36,6 +36,7 @@ struct tun_struct { unsigned long flags; int attached; uid_t owner; + gid_t group; wait_queue_head_t read_wait; struct sk_buff_head readq; @@ -78,6 +79,7 @@ struct tun_struct { #define TUNSETPERSIST _IOW('T', 203, int) #define TUNSETOWNER _IOW('T', 204, int) #define TUNSETLINK _IOW('T', 205, int) +#define TUNSETGROUP _IOW('T', 206, int) /* TUNSETIFF ifr flags */ #define IFF_TUN 0x0001 -- cgit v1.2.3 From 89da1ecf5483e6aa29b456a15ad6d05a6797c5a5 Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Mon, 2 Jul 2007 22:54:18 -0700 Subject: [IrDA]: Netlink layer. First IrDA configuration netlink layer implementation. Currently, we only support the set/get mode commands. Signed-off-by: Samuel Ortiz Signed-off-by: David S. Miller --- include/linux/irda.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irda.h b/include/linux/irda.h index 945ba311087..35911bd4dbe 100644 --- a/include/linux/irda.h +++ b/include/linux/irda.h @@ -216,6 +216,33 @@ struct if_irda_req { #define ifr_dtr ifr_ifru.ifru_line.dtr #define ifr_rts ifr_ifru.ifru_line.rts + +/* IrDA netlink definitions */ +#define IRDA_NL_NAME "irda" +#define IRDA_NL_VERSION 1 + +enum irda_nl_commands { + IRDA_NL_CMD_UNSPEC, + IRDA_NL_CMD_SET_MODE, + IRDA_NL_CMD_GET_MODE, + + __IRDA_NL_CMD_AFTER_LAST +}; +#define IRDA_NL_CMD_MAX (__IRDA_NL_CMD_AFTER_LAST - 1) + +enum nl80211_attrs { + IRDA_NL_ATTR_UNSPEC, + IRDA_NL_ATTR_IFNAME, + IRDA_NL_ATTR_MODE, + + __IRDA_NL_ATTR_AFTER_LAST +}; +#define IRDA_NL_ATTR_MAX (__IRDA_NL_ATTR_AFTER_LAST - 1) + +/* IrDA modes */ +#define IRDA_MODE_PRIMARY 0x1 +#define IRDA_MODE_SECONDARY 0x2 + #endif /* KERNEL_IRDA_H */ -- cgit v1.2.3 From 411725280bd0058ebb83c0e32133b7a94902c3a6 Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Mon, 2 Jul 2007 22:55:31 -0700 Subject: [IrDA]: Monitor mode. Through the IrDA netlink set mode command, we switch to IrDA monitor mode, where one IrLAP instance receives all the packets on the media, without ever responding to them. Signed-off-by: Samuel Ortiz Signed-off-by: David S. Miller --- include/linux/irda.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irda.h b/include/linux/irda.h index 35911bd4dbe..8e3735714c1 100644 --- a/include/linux/irda.h +++ b/include/linux/irda.h @@ -242,6 +242,7 @@ enum nl80211_attrs { /* IrDA modes */ #define IRDA_MODE_PRIMARY 0x1 #define IRDA_MODE_SECONDARY 0x2 +#define IRDA_MODE_MONITOR 0x4 #endif /* KERNEL_IRDA_H */ -- cgit v1.2.3 From 7bfe24611671ec76b44281e582b38535e21f01a9 Mon Sep 17 00:00:00 2001 From: Yasuyuki Kozakai Date: Sat, 7 Jul 2007 22:14:23 -0700 Subject: [NETFILTER]: ip6_tables: fix explanation of valid upper protocol number This explains the allowed upper protocol numbers. IP6T_F_NOPROTO was introduced to use 0 as Hop-by-Hop option header, not wildcard. But that seemed to be forgotten. 0 has been used as wildcard since 2002-08-23. Signed-off-by: Yasuyuki Kozakai Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv6/ip6_tables.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 4686f8342cb..9a720f05888 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -44,8 +44,14 @@ struct ip6t_ip6 { char iniface[IFNAMSIZ], outiface[IFNAMSIZ]; unsigned char iniface_mask[IFNAMSIZ], outiface_mask[IFNAMSIZ]; - /* ARGH, HopByHop uses 0, so can't do 0 = ANY, - instead IP6T_F_NOPROTO must be set */ + /* Upper protocol number + * - The allowed value is 0 (any) or protocol number of last parsable + * header, which is 50 (ESP), 59 (No Next Header), 135 (MH), or + * the non IPv6 extension headers. + * - The protocol numbers of IPv6 extension headers except of ESP and + * MH do not match any packets. + * - You also need to set IP6T_FLAGS_PROTO to "flags" to check protocol. + */ u_int16_t proto; /* TOS to match iff flags & IP6T_F_TOS */ u_int8_t tos; -- cgit v1.2.3 From cff533ac12494fa002e2c46acc94d670e5f636a2 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Sat, 7 Jul 2007 22:15:12 -0700 Subject: [NETFILTER]: x_tables: switch hotdrop to bool Switch the "hotdrop" variables to boolean Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 7e733a6ba4f..b8577d18d10 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -148,7 +148,7 @@ struct xt_match const void *matchinfo, int offset, unsigned int protoff, - int *hotdrop); + bool *hotdrop); /* Called when user tries to insert an entry of this type. */ /* Should return true or false. */ -- cgit v1.2.3 From 1d93a9cbad608f6398ba6c5b588c504ccd35a2ca Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Sat, 7 Jul 2007 22:15:35 -0700 Subject: [NETFILTER]: x_tables: switch xt_match->match to bool Switch the return type of match functions to boolean Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index b8577d18d10..304fce356a4 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -141,14 +141,14 @@ struct xt_match /* Arguments changed since 2.6.9, as this must now handle non-linear skb, using skb_header_pointer and skb_ip_make_writable. */ - int (*match)(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct xt_match *match, - const void *matchinfo, - int offset, - unsigned int protoff, - bool *hotdrop); + bool (*match)(const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct xt_match *match, + const void *matchinfo, + int offset, + unsigned int protoff, + bool *hotdrop); /* Called when user tries to insert an entry of this type. */ /* Should return true or false. */ -- cgit v1.2.3 From ccb79bdce71f2c04cfa9bfcbaf4d37e2f963d684 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Sat, 7 Jul 2007 22:16:00 -0700 Subject: [NETFILTER]: x_tables: switch xt_match->checkentry to bool Switch the return type of match functions to boolean Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 304fce356a4..5130dd60a2f 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -152,11 +152,11 @@ struct xt_match /* Called when user tries to insert an entry of this type. */ /* Should return true or false. */ - int (*checkentry)(const char *tablename, - const void *ip, - const struct xt_match *match, - void *matchinfo, - unsigned int hook_mask); + bool (*checkentry)(const char *tablename, + const void *ip, + const struct xt_match *match, + void *matchinfo, + unsigned int hook_mask); /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_match *match, void *matchinfo); -- cgit v1.2.3 From e1931b784a8de324abf310fa3b5e3f25d3988233 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Sat, 7 Jul 2007 22:16:26 -0700 Subject: [NETFILTER]: x_tables: switch xt_target->checkentry to bool Switch the return type of target checkentry functions to boolean. Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 5130dd60a2f..64f425a855b 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -202,11 +202,11 @@ struct xt_target hook_mask is a bitmask of hooks from which it can be called. */ /* Should return true or false. */ - int (*checkentry)(const char *tablename, - const void *entry, - const struct xt_target *target, - void *targinfo, - unsigned int hook_mask); + bool (*checkentry)(const char *tablename, + const void *entry, + const struct xt_target *target, + void *targinfo, + unsigned int hook_mask); /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_target *target, void *targinfo); -- cgit v1.2.3 From 1b50b8a371e90a5e110f466e4ac02cf6b5f681de Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Sat, 7 Jul 2007 22:20:36 -0700 Subject: [NETFILTER]: Add u32 match Along comes... xt_u32, a revamped ipt_u32 from POM-NG, Plus: * 2007-06-02: added ipv6 support * 2007-06-05: uses kmalloc for the big buffer * 2007-06-05: added inversion * 2007-06-20: use skb_copy_bits() and get rid of the big buffer and lock (suggested by Pablo Neira Ayuso) Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/xt_u32.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) create mode 100644 include/linux/netfilter/xt_u32.h (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_u32.h b/include/linux/netfilter/xt_u32.h new file mode 100644 index 00000000000..9947f56cdbd --- /dev/null +++ b/include/linux/netfilter/xt_u32.h @@ -0,0 +1,40 @@ +#ifndef _XT_U32_H +#define _XT_U32_H 1 + +enum xt_u32_ops { + XT_U32_AND, + XT_U32_LEFTSH, + XT_U32_RIGHTSH, + XT_U32_AT, +}; + +struct xt_u32_location_element { + u_int32_t number; + u_int8_t nextop; +}; + +struct xt_u32_value_element { + u_int32_t min; + u_int32_t max; +}; + +/* + * Any way to allow for an arbitrary number of elements? + * For now, I settle with a limit of 10 each. + */ +#define XT_U32_MAXSIZE 10 + +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; +}; + +struct xt_u32 { + struct xt_u32_test tests[XT_U32_MAXSIZE+1]; + u_int8_t ntests; + u_int8_t invert; +}; + +#endif /* _XT_U32_H */ -- cgit v1.2.3 From ba9dda3ab5a865542e69dfe01edb2436857c9420 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Sat, 7 Jul 2007 22:21:23 -0700 Subject: [NETFILTER]: x_tables: add TRACE target The TRACE target can be used to follow IP and IPv6 packets through the ruleset. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick NcHardy Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2d6a14f5f2f..625d73b07ab 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -227,6 +227,7 @@ typedef unsigned char *sk_buff_data_t; * @mark: Generic packet mark * @nfct: Associated connection, if any * @ipvs_property: skbuff is owned by ipvs + * @nf_trace: netfilter packet trace flag * @nfctinfo: Relationship of this skb to the connection * @nfct_reasm: netfilter conntrack re-assembly pointer * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c @@ -278,7 +279,8 @@ struct sk_buff { nfctinfo:3; __u8 pkt_type:3, fclone:2, - ipvs_property:1; + ipvs_property:1, + nf_trace:1; __be16 protocol; void (*destructor)(struct sk_buff *skb); -- cgit v1.2.3 From d3c3f4243e135b3d8c41d98be0cb2f54a4141abf Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sat, 7 Jul 2007 22:38:30 -0700 Subject: [NETFILTER]: ipt_CLUSTERIP: add compat code Adjust structure size and don't expect pointers passed in from userspace to be valid. Also replace an enum in an ABI structure by a fixed size type. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ipt_CLUSTERIP.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h b/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h index d9bceedfb3d..daf50be22c9 100644 --- a/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h +++ b/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h @@ -18,13 +18,13 @@ struct clusterip_config; struct ipt_clusterip_tgt_info { u_int32_t 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]; - enum clusterip_hashmode hash_mode; + u_int32_t hash_mode; u_int32_t hash_initval; struct clusterip_config *config; -- cgit v1.2.3 From 0d53778e81ac7af266dac8a20cc328328c327112 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sat, 7 Jul 2007 22:39:38 -0700 Subject: [NETFILTER]: Convert DEBUGP to pr_debug Convert DEBUGP to pr_debug and fix lots of non-compiling debug statements. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nf_conntrack_pptp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h index 9d8144a488c..c93061f3314 100644 --- a/include/linux/netfilter/nf_conntrack_pptp.h +++ b/include/linux/netfilter/nf_conntrack_pptp.h @@ -4,6 +4,8 @@ #include +extern const char *pptp_msg_name[]; + /* state of the control session */ enum pptp_ctrlsess_state { PPTP_SESSION_NONE, /* no session present */ -- cgit v1.2.3 From ce7663d84a87bb4e1743f62950bf7dceed723a13 Mon Sep 17 00:00:00 2001 From: Yasuyuki Kozakai Date: Sat, 7 Jul 2007 22:40:08 -0700 Subject: [NETFILTER]: nfnetlink_queue: don't unregister handler of other subsystem The queue handlers registered by ip[6]_queue.ko at initialization should not be unregistered according to requests from userland program using nfnetlink_queue. If we allow that, there is no way to register the handlers of built-in ip[6]_queue again. Signed-off-by: Yasuyuki Kozakai Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 10b5c627570..0eed0b7ab2d 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -275,7 +275,8 @@ struct nf_queue_handler { }; extern int nf_register_queue_handler(int pf, struct nf_queue_handler *qh); -extern int nf_unregister_queue_handler(int pf); +extern int nf_unregister_queue_handler(int pf, + struct nf_queue_handler *qh); extern void nf_unregister_queue_handlers(struct nf_queue_handler *qh); extern void nf_reinject(struct sk_buff *skb, struct nf_info *info, -- cgit v1.2.3 From c6c6e3e05c0b4349824efcdd36650e7be9d5c7c3 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 10 Jul 2007 22:41:55 -0700 Subject: [NET]: Update comments for skb checksums Rusty (whose comments we should all study and emulate :) pointed out that our comments for skb checksums are no longer up-to-date. So here is a patch to 1) add the case of partial checksums on input; 2) update partial checksum case to mention csum_start/csum_offset; 3) mention the new IPv6 feature bit. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/skbuff.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 625d73b07ab..9391e4a4c34 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -65,13 +65,20 @@ * is able to produce some skb->csum, it MUST use COMPLETE, * not UNNECESSARY. * + * PARTIAL: identical to the case for output below. This may occur + * on a packet received directly from another Linux OS, e.g., + * a virtualised Linux kernel on the same host. The packet can + * be treated in the same way as UNNECESSARY except that on + * output (i.e., forwarding) the checksum must be filled in + * by the OS or the hardware. + * * B. Checksumming on output. * * NONE: skb is checksummed by protocol or csum is not required. * * PARTIAL: device is required to csum packet as seen by hard_start_xmit - * from skb->transport_header to the end and to record the checksum - * at skb->transport_header + skb->csum. + * from skb->csum_start to the end and to record the checksum + * at skb->csum_start + skb->csum_offset. * * Device must show its capabilities in dev->features, set * at device setup time. @@ -82,6 +89,7 @@ * TCP/UDP over IPv4. Sigh. Vendors like this * way by an unknown reason. Though, see comment above * about CHECKSUM_UNNECESSARY. 8) + * NETIF_F_IPV6_CSUM about as dumb as the last one but does IPv6 instead. * * Any questions? No questions, good. --ANK */ -- cgit v1.2.3 From bb4dbf9e61d0801927e7df2569bb3dd8287ea301 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Tue, 10 Jul 2007 22:55:49 -0700 Subject: [IPV6]: Do not send RH0 anymore. Based on . Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/ipv6.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 213b63be3c8..cb3118cf277 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -27,8 +27,8 @@ struct in6_ifreq { int ifr6_ifindex; }; -#define IPV6_SRCRT_STRICT 0x01 /* this hop must be a neighbor */ -#define IPV6_SRCRT_TYPE_0 0 /* IPv6 type 0 Routing Header */ +#define IPV6_SRCRT_STRICT 0x01 /* Deprecated; will be removed */ +#define IPV6_SRCRT_TYPE_0 0 /* Deprecated; will be removed */ #define IPV6_SRCRT_TYPE_2 2 /* IPv6 type 2 Routing Header */ /* -- cgit v1.2.3 From 4c752098f529f41abfc985426a3eca0f2cb96676 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Wed, 23 May 2007 13:28:48 +0900 Subject: [IPV6]: Make IPV6_{RECV,2292}RTHDR boolean options. Because reversing RH0 is no longer supported by deprecation of RH0, let's make IPV6_{RECV,2292}RTHDR boolean options. Boolean are more appropriate from standard POV. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/ipv6.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index cb3118cf277..97983dc9df1 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -299,8 +299,8 @@ struct ipv6_pinfo { /* pktoption flags */ union { struct { - __u16 srcrt:2, - osrcrt:2, + __u16 srcrt:1, + osrcrt:1, rxinfo:1, rxoinfo:1, rxhlim:1, -- cgit v1.2.3 From 29578624e354f56143d92510fff33a8b2aaa2c03 Mon Sep 17 00:00:00 2001 From: Olaf Kirch Date: Wed, 11 Jul 2007 19:32:02 -0700 Subject: [NET]: Fix races in net_rx_action vs netpoll. Keep netpoll/poll_napi from messing with the poll_list. Only net_rx_action is allowed to manipulate the list. Signed-off-by: Olaf Kirch Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8590d685d93..79cc3dab4be 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -261,6 +261,8 @@ enum netdev_state_t __LINK_STATE_LINKWATCH_PENDING, __LINK_STATE_DORMANT, __LINK_STATE_QDISC_RUNNING, + /* Set by the netpoll NAPI code */ + __LINK_STATE_POLL_LIST_FROZEN, }; @@ -1014,6 +1016,14 @@ static inline void netif_rx_complete(struct net_device *dev) { unsigned long flags; +#ifdef CONFIG_NETPOLL + /* Prevent race with netpoll - yes, this is a kludge. + * But at least it doesn't penalize the non-netpoll + * code path. */ + if (test_bit(__LINK_STATE_POLL_LIST_FROZEN, &dev->state)) + return; +#endif + local_irq_save(flags); __netif_rx_complete(dev); local_irq_restore(flags); -- cgit v1.2.3 From 8c979c26a0f093c13290320edda799d8335e50ae Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 11 Jul 2007 19:45:24 -0700 Subject: [VLAN]: Fix MAC address handling The VLAN MAC address handling is broken in multiple ways. When the address differs when setting it, the real device is put in promiscous mode twice, but never taken out again. Additionally it doesn't resync when the real device's address is changed and needlessly puts it in promiscous mode when the vlan device is still down. Fix by moving address handling to vlan_dev_open/vlan_dev_stop and properly deal with address changes in the device notifier. Also switch to dev_unicast_add (which needs the exact same handling). Since the set_mac_address handler is identical to the generic ethernet one with these changes, kill it and use ether_setup(). Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index c7912876a21..61a57dc2ac9 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -135,6 +135,7 @@ struct vlan_dev_info { int old_allmulti; /* similar to above. */ int old_promiscuity; /* similar to above. */ struct net_device *real_dev; /* the underlying device/interface */ + unsigned char real_dev_addr[ETH_ALEN]; struct proc_dir_entry *dent; /* Holds the proc data */ unsigned long cnt_inc_headroom_on_tx; /* How many times did we have to grow the skb on TX. */ unsigned long cnt_encap_on_xmit; /* How many times did we have to encapsulate the skb on TX. */ -- cgit v1.2.3 From db3d99c090e0cdb34b1274767e062bfddbb384bc Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 11 Jul 2007 19:46:26 -0700 Subject: [NET_SCHED]: ematch: module autoloading Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/pkt_cls.h | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pkt_cls.h b/include/linux/pkt_cls.h index c3f01b3085a..30b8571e6b3 100644 --- a/include/linux/pkt_cls.h +++ b/include/linux/pkt_cls.h @@ -403,16 +403,13 @@ enum * 1..32767 Reserved for ematches inside kernel tree * 32768..65535 Free to use, not reliable */ -enum -{ - TCF_EM_CONTAINER, - TCF_EM_CMP, - TCF_EM_NBYTE, - TCF_EM_U32, - TCF_EM_META, - TCF_EM_TEXT, - __TCF_EM_MAX -}; +#define TCF_EM_CONTAINER 0 +#define TCF_EM_CMP 1 +#define TCF_EM_NBYTE 2 +#define TCF_EM_U32 3 +#define TCF_EM_META 4 +#define TCF_EM_TEXT 5 +#define TCF_EM_MAX 5 enum { -- cgit v1.2.3