From 892c141e62982272b9c738b5520ad0e5e1ad7b42 Mon Sep 17 00:00:00 2001 From: Venkat Yekkirala Date: Fri, 4 Aug 2006 23:08:56 -0700 Subject: [MLSXFRM]: Add security sid to sock This adds security for IP sockets at the sock level. Security at the sock level is needed to enforce the SELinux security policy for security associations even when a sock is orphaned (such as in the TCP LAST_ACK state). This will also be used to enforce SELinux controls over data arriving at or leaving a child socket while it's still waiting to be accepted. Signed-off-by: Venkat Yekkirala Signed-off-by: David S. Miller --- include/linux/security.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 6bc2aad494ff..4d7fb59996b0 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -812,6 +812,8 @@ struct swap_info_struct; * which is used to copy security attributes between local stream sockets. * @sk_free_security: * Deallocate security structure. + * @sk_clone_security: + * Clone/copy security structure. * @sk_getsid: * Retrieve the LSM-specific sid for the sock to enable caching of network * authorizations. @@ -1332,6 +1334,7 @@ struct security_operations { int (*socket_getpeersec_dgram) (struct socket *sock, struct sk_buff *skb, u32 *secid); int (*sk_alloc_security) (struct sock *sk, int family, gfp_t priority); void (*sk_free_security) (struct sock *sk); + void (*sk_clone_security) (const struct sock *sk, struct sock *newsk); unsigned int (*sk_getsid) (struct sock *sk, struct flowi *fl, u8 dir); #endif /* CONFIG_SECURITY_NETWORK */ @@ -2885,6 +2888,11 @@ static inline void security_sk_free(struct sock *sk) return security_ops->sk_free_security(sk); } +static inline void security_sk_clone(const struct sock *sk, struct sock *newsk) +{ + return security_ops->sk_clone_security(sk, newsk); +} + static inline unsigned int security_sk_sid(struct sock *sk, struct flowi *fl, u8 dir) { return security_ops->sk_getsid(sk, fl, dir); @@ -3011,6 +3019,10 @@ static inline void security_sk_free(struct sock *sk) { } +static inline void security_sk_clone(const struct sock *sk, struct sock *newsk) +{ +} + static inline unsigned int security_sk_sid(struct sock *sk, struct flowi *fl, u8 dir) { return 0; -- cgit v1.2.3 From e0d1caa7b0d5f02e4f34aa09c695d04251310c6c Mon Sep 17 00:00:00 2001 From: Venkat Yekkirala Date: Mon, 24 Jul 2006 23:29:07 -0700 Subject: [MLSXFRM]: Flow based matching of xfrm policy and state This implements a seemless mechanism for xfrm policy selection and state matching based on the flow sid. This also includes the necessary SELinux enforcement pieces. Signed-off-by: Venkat Yekkirala Signed-off-by: David S. Miller --- include/linux/security.h | 106 ++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 90 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 4d7fb59996b0..2c4921d79d19 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -31,6 +31,7 @@ #include #include #include +#include struct ctl_table; @@ -825,9 +826,8 @@ struct swap_info_struct; * used by the XFRM system. * @sec_ctx contains the security context information being provided by * the user-level policy update program (e.g., setkey). - * Allocate a security structure to the xp->security field. - * The security field is initialized to NULL when the xfrm_policy is - * allocated. + * Allocate a security structure to the xp->security field; the security + * field is initialized to NULL when the xfrm_policy is allocated. * Return 0 if operation was successful (memory to allocate, legal context) * @xfrm_policy_clone_security: * @old contains an existing xfrm_policy in the SPD. @@ -846,9 +846,14 @@ struct swap_info_struct; * Database by the XFRM system. * @sec_ctx contains the security context information being provided by * the user-level SA generation program (e.g., setkey or racoon). - * Allocate a security structure to the x->security field. The - * security field is initialized to NULL when the xfrm_state is - * allocated. + * @polsec contains the security context information associated with a xfrm + * policy rule from which to take the base context. polsec must be NULL + * when sec_ctx is specified. + * @secid contains the secid from which to take the mls portion of the context. + * Allocate a security structure to the x->security field; the security + * field is initialized to NULL when the xfrm_state is allocated. Set the + * context to correspond to either sec_ctx or polsec, with the mls portion + * taken from secid in the latter case. * Return 0 if operation was successful (memory to allocate, legal context). * @xfrm_state_free_security: * @x contains the xfrm_state. @@ -859,13 +864,26 @@ struct swap_info_struct; * @xfrm_policy_lookup: * @xp contains the xfrm_policy for which the access control is being * checked. - * @sk_sid contains the sock security label that is used to authorize + * @fl_secid contains the flow security label that is used to authorize * access to the policy xp. * @dir contains the direction of the flow (input or output). - * Check permission when a sock selects a xfrm_policy for processing + * Check permission when a flow selects a xfrm_policy for processing * XFRMs on a packet. The hook is called when selecting either a * per-socket policy or a generic xfrm policy. * Return 0 if permission is granted. + * @xfrm_state_pol_flow_match: + * @x contains the state to match. + * @xp contains the policy to check for a match. + * @fl contains the flow to check for a match. + * Return 1 if there is a match. + * @xfrm_flow_state_match: + * @fl contains the flow key to match. + * @xfrm points to the xfrm_state to match. + * Return 1 if there is a match. + * @xfrm_decode_session: + * @skb points to skb to decode. + * @fl points to the flow key to set. + * Return 0 if successful decoding. * * Security hooks affecting all Key Management operations * @@ -1343,10 +1361,16 @@ struct security_operations { int (*xfrm_policy_clone_security) (struct xfrm_policy *old, struct xfrm_policy *new); void (*xfrm_policy_free_security) (struct xfrm_policy *xp); int (*xfrm_policy_delete_security) (struct xfrm_policy *xp); - int (*xfrm_state_alloc_security) (struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx); + int (*xfrm_state_alloc_security) (struct xfrm_state *x, + struct xfrm_user_sec_ctx *sec_ctx, struct xfrm_sec_ctx *polsec, + u32 secid); void (*xfrm_state_free_security) (struct xfrm_state *x); int (*xfrm_state_delete_security) (struct xfrm_state *x); - int (*xfrm_policy_lookup)(struct xfrm_policy *xp, u32 sk_sid, u8 dir); + int (*xfrm_policy_lookup)(struct xfrm_policy *xp, u32 fl_secid, u8 dir); + int (*xfrm_state_pol_flow_match)(struct xfrm_state *x, + struct xfrm_policy *xp, struct flowi *fl); + int (*xfrm_flow_state_match)(struct flowi *fl, struct xfrm_state *xfrm); + int (*xfrm_decode_session)(struct sk_buff *skb, struct flowi *fl); #endif /* CONFIG_SECURITY_NETWORK_XFRM */ /* key management security hooks */ @@ -3050,9 +3074,18 @@ static inline int security_xfrm_policy_delete(struct xfrm_policy *xp) return security_ops->xfrm_policy_delete_security(xp); } -static inline int security_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx) +static inline int security_xfrm_state_alloc(struct xfrm_state *x, + struct xfrm_user_sec_ctx *sec_ctx) +{ + return security_ops->xfrm_state_alloc_security(x, sec_ctx, NULL, 0); +} + +static inline int security_xfrm_state_alloc_acquire(struct xfrm_state *x, + struct xfrm_sec_ctx *polsec, u32 secid) { - return security_ops->xfrm_state_alloc_security(x, sec_ctx); + if (!polsec) + return 0; + return security_ops->xfrm_state_alloc_security(x, NULL, polsec, secid); } static inline int security_xfrm_state_delete(struct xfrm_state *x) @@ -3065,9 +3098,25 @@ static inline void security_xfrm_state_free(struct xfrm_state *x) security_ops->xfrm_state_free_security(x); } -static inline int security_xfrm_policy_lookup(struct xfrm_policy *xp, u32 sk_sid, u8 dir) +static inline int security_xfrm_policy_lookup(struct xfrm_policy *xp, u32 fl_secid, u8 dir) +{ + return security_ops->xfrm_policy_lookup(xp, fl_secid, dir); +} + +static inline int security_xfrm_state_pol_flow_match(struct xfrm_state *x, + struct xfrm_policy *xp, struct flowi *fl) +{ + return security_ops->xfrm_state_pol_flow_match(x, xp, fl); +} + +static inline int security_xfrm_flow_state_match(struct flowi *fl, struct xfrm_state *xfrm) +{ + return security_ops->xfrm_flow_state_match(fl, xfrm); +} + +static inline int security_xfrm_decode_session(struct sk_buff *skb, struct flowi *fl) { - return security_ops->xfrm_policy_lookup(xp, sk_sid, dir); + return security_ops->xfrm_decode_session(skb, fl); } #else /* CONFIG_SECURITY_NETWORK_XFRM */ static inline int security_xfrm_policy_alloc(struct xfrm_policy *xp, struct xfrm_user_sec_ctx *sec_ctx) @@ -3089,7 +3138,14 @@ static inline int security_xfrm_policy_delete(struct xfrm_policy *xp) return 0; } -static inline int security_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx) +static inline int security_xfrm_state_alloc(struct xfrm_state *x, + struct xfrm_user_sec_ctx *sec_ctx) +{ + return 0; +} + +static inline int security_xfrm_state_alloc_acquire(struct xfrm_state *x, + struct xfrm_sec_ctx *polsec, u32 secid) { return 0; } @@ -3103,10 +3159,28 @@ static inline int security_xfrm_state_delete(struct xfrm_state *x) return 0; } -static inline int security_xfrm_policy_lookup(struct xfrm_policy *xp, u32 sk_sid, u8 dir) +static inline int security_xfrm_policy_lookup(struct xfrm_policy *xp, u32 fl_secid, u8 dir) { return 0; } + +static inline int security_xfrm_state_pol_flow_match(struct xfrm_state *x, + struct xfrm_policy *xp, struct flowi *fl) +{ + return 1; +} + +static inline int security_xfrm_flow_state_match(struct flowi *fl, + struct xfrm_state *xfrm) +{ + return 1; +} + +static inline int security_xfrm_decode_session(struct sk_buff *skb, struct flowi *fl) +{ + return 0; +} + #endif /* CONFIG_SECURITY_NETWORK_XFRM */ #ifdef CONFIG_KEYS -- cgit v1.2.3 From beb8d13bed80f8388f1a9a107d07ddd342e627e8 Mon Sep 17 00:00:00 2001 From: Venkat Yekkirala Date: Fri, 4 Aug 2006 23:12:42 -0700 Subject: [MLSXFRM]: Add flow labeling This labels the flows that could utilize IPSec xfrms at the points the flows are defined so that IPSec policy and SAs at the right label can be used. The following protos are currently not handled, but they should continue to be able to use single-labeled IPSec like they currently do. ipmr ip_gre ipip igmp sit sctp ip6_tunnel (IPv6 over IPv6 tunnel device) decnet Signed-off-by: Venkat Yekkirala Signed-off-by: David S. Miller --- include/linux/security.h | 38 +++++++++++++++++++++++++------------- 1 file changed, 25 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 2c4921d79d19..f3909d189fe0 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -32,6 +32,7 @@ #include #include #include +#include struct ctl_table; @@ -815,8 +816,8 @@ struct swap_info_struct; * Deallocate security structure. * @sk_clone_security: * Clone/copy security structure. - * @sk_getsid: - * Retrieve the LSM-specific sid for the sock to enable caching of network + * @sk_getsecid: + * Retrieve the LSM-specific secid for the sock to enable caching of network * authorizations. * * Security hooks for XFRM operations. @@ -882,8 +883,9 @@ struct swap_info_struct; * Return 1 if there is a match. * @xfrm_decode_session: * @skb points to skb to decode. - * @fl points to the flow key to set. - * Return 0 if successful decoding. + * @secid points to the flow key secid to set. + * @ckall says if all xfrms used should be checked for same secid. + * Return 0 if ckall is zero or all xfrms used have the same secid. * * Security hooks affecting all Key Management operations * @@ -1353,7 +1355,7 @@ struct security_operations { int (*sk_alloc_security) (struct sock *sk, int family, gfp_t priority); void (*sk_free_security) (struct sock *sk); void (*sk_clone_security) (const struct sock *sk, struct sock *newsk); - unsigned int (*sk_getsid) (struct sock *sk, struct flowi *fl, u8 dir); + void (*sk_getsecid) (struct sock *sk, u32 *secid); #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM @@ -1370,7 +1372,7 @@ struct security_operations { int (*xfrm_state_pol_flow_match)(struct xfrm_state *x, struct xfrm_policy *xp, struct flowi *fl); int (*xfrm_flow_state_match)(struct flowi *fl, struct xfrm_state *xfrm); - int (*xfrm_decode_session)(struct sk_buff *skb, struct flowi *fl); + int (*xfrm_decode_session)(struct sk_buff *skb, u32 *secid, int ckall); #endif /* CONFIG_SECURITY_NETWORK_XFRM */ /* key management security hooks */ @@ -2917,9 +2919,9 @@ static inline void security_sk_clone(const struct sock *sk, struct sock *newsk) return security_ops->sk_clone_security(sk, newsk); } -static inline unsigned int security_sk_sid(struct sock *sk, struct flowi *fl, u8 dir) +static inline void security_sk_classify_flow(struct sock *sk, struct flowi *fl) { - return security_ops->sk_getsid(sk, fl, dir); + security_ops->sk_getsecid(sk, &fl->secid); } #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct socket * sock, @@ -3047,9 +3049,8 @@ static inline void security_sk_clone(const struct sock *sk, struct sock *newsk) { } -static inline unsigned int security_sk_sid(struct sock *sk, struct flowi *fl, u8 dir) +static inline void security_sk_classify_flow(struct sock *sk, struct flowi *fl) { - return 0; } #endif /* CONFIG_SECURITY_NETWORK */ @@ -3114,9 +3115,16 @@ static inline int security_xfrm_flow_state_match(struct flowi *fl, struct xfrm_s return security_ops->xfrm_flow_state_match(fl, xfrm); } -static inline int security_xfrm_decode_session(struct sk_buff *skb, struct flowi *fl) +static inline int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid) +{ + return security_ops->xfrm_decode_session(skb, secid, 1); +} + +static inline void security_skb_classify_flow(struct sk_buff *skb, struct flowi *fl) { - return security_ops->xfrm_decode_session(skb, fl); + int rc = security_ops->xfrm_decode_session(skb, &fl->secid, 0); + + BUG_ON(rc); } #else /* CONFIG_SECURITY_NETWORK_XFRM */ static inline int security_xfrm_policy_alloc(struct xfrm_policy *xp, struct xfrm_user_sec_ctx *sec_ctx) @@ -3176,11 +3184,15 @@ static inline int security_xfrm_flow_state_match(struct flowi *fl, return 1; } -static inline int security_xfrm_decode_session(struct sk_buff *skb, struct flowi *fl) +static inline int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid) { return 0; } +static inline void security_skb_classify_flow(struct sk_buff *skb, struct flowi *fl) +{ +} + #endif /* CONFIG_SECURITY_NETWORK_XFRM */ #ifdef CONFIG_KEYS -- cgit v1.2.3 From cb969f072b6d67770b559617f14e767f47e77ece Mon Sep 17 00:00:00 2001 From: Venkat Yekkirala Date: Mon, 24 Jul 2006 23:32:20 -0700 Subject: [MLSXFRM]: Default labeling of socket specific IPSec policies This defaults the label of socket-specific IPSec policies to be the same as the socket they are set on. Signed-off-by: Venkat Yekkirala Signed-off-by: David S. Miller --- include/linux/security.h | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index f3909d189fe0..8e3dc6c51a6d 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -827,8 +827,10 @@ struct swap_info_struct; * used by the XFRM system. * @sec_ctx contains the security context information being provided by * the user-level policy update program (e.g., setkey). + * @sk refers to the sock from which to derive the security context. * Allocate a security structure to the xp->security field; the security - * field is initialized to NULL when the xfrm_policy is allocated. + * field is initialized to NULL when the xfrm_policy is allocated. Only + * one of sec_ctx or sock can be specified. * Return 0 if operation was successful (memory to allocate, legal context) * @xfrm_policy_clone_security: * @old contains an existing xfrm_policy in the SPD. @@ -1359,7 +1361,8 @@ struct security_operations { #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM - int (*xfrm_policy_alloc_security) (struct xfrm_policy *xp, struct xfrm_user_sec_ctx *sec_ctx); + int (*xfrm_policy_alloc_security) (struct xfrm_policy *xp, + struct xfrm_user_sec_ctx *sec_ctx, struct sock *sk); int (*xfrm_policy_clone_security) (struct xfrm_policy *old, struct xfrm_policy *new); void (*xfrm_policy_free_security) (struct xfrm_policy *xp); int (*xfrm_policy_delete_security) (struct xfrm_policy *xp); @@ -3057,7 +3060,12 @@ static inline void security_sk_classify_flow(struct sock *sk, struct flowi *fl) #ifdef CONFIG_SECURITY_NETWORK_XFRM static inline int security_xfrm_policy_alloc(struct xfrm_policy *xp, struct xfrm_user_sec_ctx *sec_ctx) { - return security_ops->xfrm_policy_alloc_security(xp, sec_ctx); + return security_ops->xfrm_policy_alloc_security(xp, sec_ctx, NULL); +} + +static inline int security_xfrm_sock_policy_alloc(struct xfrm_policy *xp, struct sock *sk) +{ + return security_ops->xfrm_policy_alloc_security(xp, NULL, sk); } static inline int security_xfrm_policy_clone(struct xfrm_policy *old, struct xfrm_policy *new) @@ -3132,6 +3140,11 @@ static inline int security_xfrm_policy_alloc(struct xfrm_policy *xp, struct xfrm return 0; } +static inline int security_xfrm_sock_policy_alloc(struct xfrm_policy *xp, struct sock *sk) +{ + return 0; +} + static inline int security_xfrm_policy_clone(struct xfrm_policy *old, struct xfrm_policy *new) { return 0; -- cgit v1.2.3 From 4237c75c0a35535d7f9f2bfeeb4b4df1e068a0bf Mon Sep 17 00:00:00 2001 From: Venkat Yekkirala Date: Mon, 24 Jul 2006 23:32:50 -0700 Subject: [MLSXFRM]: Auto-labeling of child sockets This automatically labels the TCP, Unix stream, and dccp child sockets as well as openreqs to be at the same MLS level as the peer. This will result in the selection of appropriately labeled IPSec Security Associations. This also uses the sock's sid (as opposed to the isec sid) in SELinux enforcement of secmark in rcv_skb and postroute_last hooks. Signed-off-by: Venkat Yekkirala Signed-off-by: David S. Miller --- include/linux/security.h | 55 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 8e3dc6c51a6d..bb4c80fdfe7a 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -90,6 +90,7 @@ extern int cap_netlink_recv(struct sk_buff *skb, int cap); struct nfsctl_arg; struct sched_param; struct swap_info_struct; +struct request_sock; /* bprm_apply_creds unsafe reasons */ #define LSM_UNSAFE_SHARE 1 @@ -819,6 +820,14 @@ struct swap_info_struct; * @sk_getsecid: * Retrieve the LSM-specific secid for the sock to enable caching of network * authorizations. + * @sock_graft: + * Sets the socket's isec sid to the sock's sid. + * @inet_conn_request: + * Sets the openreq's sid to socket's sid with MLS portion taken from peer sid. + * @inet_csk_clone: + * Sets the new child socket's sid to the openreq sid. + * @req_classify_flow: + * Sets the flow's sid to the openreq sid. * * Security hooks for XFRM operations. * @@ -1358,6 +1367,11 @@ struct security_operations { void (*sk_free_security) (struct sock *sk); void (*sk_clone_security) (const struct sock *sk, struct sock *newsk); void (*sk_getsecid) (struct sock *sk, u32 *secid); + void (*sock_graft)(struct sock* sk, struct socket *parent); + int (*inet_conn_request)(struct sock *sk, struct sk_buff *skb, + struct request_sock *req); + void (*inet_csk_clone)(struct sock *newsk, const struct request_sock *req); + void (*req_classify_flow)(const struct request_sock *req, struct flowi *fl); #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM @@ -2926,6 +2940,28 @@ static inline void security_sk_classify_flow(struct sock *sk, struct flowi *fl) { security_ops->sk_getsecid(sk, &fl->secid); } + +static inline void security_req_classify_flow(const struct request_sock *req, struct flowi *fl) +{ + security_ops->req_classify_flow(req, fl); +} + +static inline void security_sock_graft(struct sock* sk, struct socket *parent) +{ + security_ops->sock_graft(sk, parent); +} + +static inline int security_inet_conn_request(struct sock *sk, + struct sk_buff *skb, struct request_sock *req) +{ + return security_ops->inet_conn_request(sk, skb, req); +} + +static inline void security_inet_csk_clone(struct sock *newsk, + const struct request_sock *req) +{ + security_ops->inet_csk_clone(newsk, req); +} #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct socket * sock, struct socket * other, @@ -3055,6 +3091,25 @@ static inline void security_sk_clone(const struct sock *sk, struct sock *newsk) static inline void security_sk_classify_flow(struct sock *sk, struct flowi *fl) { } + +static inline void security_req_classify_flow(const struct request_sock *req, struct flowi *fl) +{ +} + +static inline void security_sock_graft(struct sock* sk, struct socket *parent) +{ +} + +static inline int security_inet_conn_request(struct sock *sk, + struct sk_buff *skb, struct request_sock *req) +{ + return 0; +} + +static inline void security_inet_csk_clone(struct sock *newsk, + const struct request_sock *req) +{ +} #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM -- cgit v1.2.3 From 11a03f78fbf15a866ba3bf6359a75cdfd1ced703 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Thu, 3 Aug 2006 16:46:20 -0700 Subject: [NetLabel]: core network changes Changes to the core network stack to support the NetLabel subsystem. This includes changes to the IPv4 option handling to support CIPSO labels. Signed-off-by: Paul Moore Signed-off-by: David S. Miller --- include/linux/ip.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ip.h b/include/linux/ip.h index 4b55cf1df732..2f4600146f83 100644 --- a/include/linux/ip.h +++ b/include/linux/ip.h @@ -57,6 +57,7 @@ #define IPOPT_SEC (2 |IPOPT_CONTROL|IPOPT_COPY) #define IPOPT_LSRR (3 |IPOPT_CONTROL|IPOPT_COPY) #define IPOPT_TIMESTAMP (4 |IPOPT_MEASUREMENT) +#define IPOPT_CIPSO (6 |IPOPT_CONTROL|IPOPT_COPY) #define IPOPT_RR (7 |IPOPT_CONTROL) #define IPOPT_SID (8 |IPOPT_CONTROL|IPOPT_COPY) #define IPOPT_SSRR (9 |IPOPT_CONTROL|IPOPT_COPY) -- cgit v1.2.3 From 446fda4f26822b2d42ab3396aafcedf38a9ff2b6 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Thu, 3 Aug 2006 16:48:06 -0700 Subject: [NetLabel]: CIPSOv4 engine Add support for the Commercial IP Security Option (CIPSO) to the IPv4 network stack. CIPSO has become a de-facto standard for trusted/labeled networking amongst existing Trusted Operating Systems such as Trusted Solaris, HP-UX CMW, etc. This implementation is designed to be used with the NetLabel subsystem to provide explicit packet labeling to LSM developers. The CIPSO/IPv4 packet labeling works by the LSM calling a NetLabel API function which attaches a CIPSO label (IPv4 option) to a given socket; this in turn attaches the CIPSO label to every packet leaving the socket without any extra processing on the outbound side. On the inbound side the individual packet's sk_buff is examined through a call to a NetLabel API function to determine if a CIPSO/IPv4 label is present and if so the security attributes of the CIPSO label are returned to the caller of the NetLabel API function. Signed-off-by: Paul Moore Signed-off-by: David S. Miller --- include/linux/sysctl.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index e4b1a4d4dcf3..af61d9235409 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -411,6 +411,10 @@ enum NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS=115, NET_TCP_DMA_COPYBREAK=116, NET_TCP_SLOW_START_AFTER_IDLE=117, + NET_CIPSOV4_CACHE_ENABLE=118, + NET_CIPSOV4_CACHE_BUCKET_SIZE=119, + NET_CIPSOV4_RBM_OPTFMT=120, + NET_CIPSOV4_RBM_STRICTVALID=121, }; enum { -- cgit v1.2.3 From 7420ed23a4f77480b5b7b3245e5da30dd24b7575 Mon Sep 17 00:00:00 2001 From: Venkat Yekkirala Date: Fri, 4 Aug 2006 23:17:57 -0700 Subject: [NetLabel]: SELinux support Add NetLabel support to the SELinux LSM and modify the socket_post_create() LSM hook to return an error code. The most significant part of this patch is the addition of NetLabel hooks into the following SELinux LSM hooks: * selinux_file_permission() * selinux_socket_sendmsg() * selinux_socket_post_create() * selinux_socket_sock_rcv_skb() * selinux_socket_getpeersec_stream() * selinux_socket_getpeersec_dgram() * selinux_sock_graft() * selinux_inet_conn_request() The basic reasoning behind this patch is that outgoing packets are "NetLabel'd" by labeling their socket and the NetLabel security attributes are checked via the additional hook in selinux_socket_sock_rcv_skb(). NetLabel itself is only a labeling mechanism, similar to filesystem extended attributes, it is up to the SELinux enforcement mechanism to perform the actual access checks. In addition to the changes outlined above this patch also includes some changes to the extended bitmap (ebitmap) and multi-level security (mls) code to import and export SELinux TE/MLS attributes into and out of NetLabel. Signed-off-by: Paul Moore Signed-off-by: David S. Miller --- include/linux/security.h | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index bb4c80fdfe7a..9f56fb8a4a6c 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1341,8 +1341,8 @@ struct security_operations { int (*unix_may_send) (struct socket * sock, struct socket * other); int (*socket_create) (int family, int type, int protocol, int kern); - void (*socket_post_create) (struct socket * sock, int family, - int type, int protocol, int kern); + int (*socket_post_create) (struct socket * sock, int family, + int type, int protocol, int kern); int (*socket_bind) (struct socket * sock, struct sockaddr * address, int addrlen); int (*socket_connect) (struct socket * sock, @@ -2824,13 +2824,13 @@ static inline int security_socket_create (int family, int type, return security_ops->socket_create(family, type, protocol, kern); } -static inline void security_socket_post_create(struct socket * sock, - int family, - int type, - int protocol, int kern) +static inline int security_socket_post_create(struct socket * sock, + int family, + int type, + int protocol, int kern) { - security_ops->socket_post_create(sock, family, type, - protocol, kern); + return security_ops->socket_post_create(sock, family, type, + protocol, kern); } static inline int security_socket_bind(struct socket * sock, @@ -2982,11 +2982,12 @@ static inline int security_socket_create (int family, int type, return 0; } -static inline void security_socket_post_create(struct socket * sock, - int family, - int type, - int protocol, int kern) +static inline int security_socket_post_create(struct socket * sock, + int family, + int type, + int protocol, int kern) { + return 0; } static inline int security_socket_bind(struct socket * sock, -- cgit v1.2.3 From 14c0b97ddfc2944982d078b8e33b088840068976 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 4 Aug 2006 03:38:38 -0700 Subject: [NET]: Protocol Independant Policy Routing Rules Framework Derived from net/ipv/fib_rules.c Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/fib_rules.h | 60 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 60 insertions(+) create mode 100644 include/linux/fib_rules.h (limited to 'include/linux') diff --git a/include/linux/fib_rules.h b/include/linux/fib_rules.h new file mode 100644 index 000000000000..5e503f0ca6e4 --- /dev/null +++ b/include/linux/fib_rules.h @@ -0,0 +1,60 @@ +#ifndef __LINUX_FIB_RULES_H +#define __LINUX_FIB_RULES_H + +#include +#include + +/* rule is permanent, and cannot be deleted */ +#define FIB_RULE_PERMANENT 1 + +struct fib_rule_hdr +{ + __u8 family; + __u8 dst_len; + __u8 src_len; + __u8 tos; + + __u8 table; + __u8 res1; /* reserved */ + __u8 res2; /* reserved */ + __u8 action; + + __u32 flags; +}; + +enum +{ + FRA_UNSPEC, + FRA_DST, /* destination address */ + FRA_SRC, /* source address */ + FRA_IFNAME, /* interface name */ + FRA_UNUSED1, + FRA_UNUSED2, + FRA_PRIORITY, /* priority/preference */ + FRA_UNUSED3, + FRA_UNUSED4, + FRA_UNUSED5, + FRA_FWMARK, /* netfilter mark (IPv4) */ + FRA_FLOW, /* flow/class id */ + __FRA_MAX +}; + +#define FRA_MAX (__FRA_MAX - 1) + +enum +{ + FR_ACT_UNSPEC, + FR_ACT_TO_TBL, /* Pass to fixed table */ + FR_ACT_RES1, + FR_ACT_RES2, + FR_ACT_RES3, + FR_ACT_RES4, + FR_ACT_BLACKHOLE, /* Drop without notification */ + FR_ACT_UNREACHABLE, /* Drop with ENETUNREACH */ + FR_ACT_PROHIBIT, /* Drop with EACCES */ + __FR_ACT_MAX, +}; + +#define FR_ACT_MAX (__FR_ACT_MAX - 1) + +#endif -- cgit v1.2.3 From 101367c2f8c464ea96643192673aa18d88e6336d Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 4 Aug 2006 03:39:02 -0700 Subject: [IPV6]: Policy Routing Rules Adds support for policy routing rules including a new local table for routes with a local destination. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index facd9ee37b76..bf353538ae93 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -889,6 +889,8 @@ enum rtnetlink_groups { RTNLGRP_NOP4, RTNLGRP_IPV6_PREFIX, #define RTNLGRP_IPV6_PREFIX RTNLGRP_IPV6_PREFIX + RTNLGRP_IPV6_RULE, +#define RTNLGRP_IPV6_RULE RTNLGRP_IPV6_RULE __RTNLGRP_MAX }; #define RTNLGRP_MAX (__RTNLGRP_MAX - 1) -- cgit v1.2.3 From 1823730fbc89fadde72a7bb3b7bdf03cc7b8835c Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 4 Aug 2006 23:04:54 -0700 Subject: [IPv4]: Move interface address bits to linux/if_addr.h Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/if_addr.h | 53 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/rtnetlink.h | 56 ----------------------------------------------- 2 files changed, 53 insertions(+), 56 deletions(-) create mode 100644 include/linux/if_addr.h (limited to 'include/linux') diff --git a/include/linux/if_addr.h b/include/linux/if_addr.h new file mode 100644 index 000000000000..e1590454db59 --- /dev/null +++ b/include/linux/if_addr.h @@ -0,0 +1,53 @@ +#ifndef __LINUX_IF_ADDR_H +#define __LINUX_IF_ADDR_H + +#include + +struct ifaddrmsg +{ + __u8 ifa_family; + __u8 ifa_prefixlen; /* The prefix length */ + __u8 ifa_flags; /* Flags */ + __u8 ifa_scope; /* Address scope */ + __u32 ifa_index; /* Link index */ +}; + +/* + * Important comment: + * IFA_ADDRESS is prefix address, rather than local interface address. + * It makes no difference for normally configured broadcast interfaces, + * but for point-to-point IFA_ADDRESS is DESTINATION address, + * local address is supplied in IFA_LOCAL attribute. + */ +enum +{ + IFA_UNSPEC, + IFA_ADDRESS, + IFA_LOCAL, + IFA_LABEL, + IFA_BROADCAST, + IFA_ANYCAST, + IFA_CACHEINFO, + IFA_MULTICAST, + __IFA_MAX, +}; + +#define IFA_MAX (__IFA_MAX - 1) + +/* ifa_flags */ +#define IFA_F_SECONDARY 0x01 +#define IFA_F_TEMPORARY IFA_F_SECONDARY + +#define IFA_F_DEPRECATED 0x20 +#define IFA_F_TENTATIVE 0x40 +#define IFA_F_PERMANENT 0x80 + +struct ifa_cacheinfo +{ + __u32 ifa_prefered; + __u32 ifa_valid; + __u32 cstamp; /* created timestamp, hundredths of seconds */ + __u32 tstamp; /* updated timestamp, hundredths of seconds */ +}; + +#endif diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index bf353538ae93..890c4d4038b6 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -384,62 +384,6 @@ struct rta_session }; -/********************************************************* - * Interface address. - ****/ - -struct ifaddrmsg -{ - unsigned char ifa_family; - unsigned char ifa_prefixlen; /* The prefix length */ - unsigned char ifa_flags; /* Flags */ - unsigned char ifa_scope; /* See above */ - int ifa_index; /* Link index */ -}; - -enum -{ - IFA_UNSPEC, - IFA_ADDRESS, - IFA_LOCAL, - IFA_LABEL, - IFA_BROADCAST, - IFA_ANYCAST, - IFA_CACHEINFO, - IFA_MULTICAST, - __IFA_MAX -}; - -#define IFA_MAX (__IFA_MAX - 1) - -/* ifa_flags */ - -#define IFA_F_SECONDARY 0x01 -#define IFA_F_TEMPORARY IFA_F_SECONDARY - -#define IFA_F_DEPRECATED 0x20 -#define IFA_F_TENTATIVE 0x40 -#define IFA_F_PERMANENT 0x80 - -struct ifa_cacheinfo -{ - __u32 ifa_prefered; - __u32 ifa_valid; - __u32 cstamp; /* created timestamp, hundredths of seconds */ - __u32 tstamp; /* updated timestamp, hundredths of seconds */ -}; - - -#define IFA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifaddrmsg)))) -#define IFA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifaddrmsg)) - -/* - Important comment: - IFA_ADDRESS is prefix address, rather than local interface address. - It makes no difference for normally configured broadcast interfaces, - but for point-to-point IFA_ADDRESS is DESTINATION address, - local address is supplied in IFA_LOCAL attribute. - */ /************************************************************** * Neighbour discovery. -- cgit v1.2.3 From 0844565fb8a9418f5a860aa480c1aef70319c9a2 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 4 Aug 2006 23:05:56 -0700 Subject: [NET]: Move netlink interface bits to linux/if.h Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/if.h | 129 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/rtnetlink.h | 133 +--------------------------------------------- 2 files changed, 130 insertions(+), 132 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if.h b/include/linux/if.h index 374e20ad8b0d..cd080d765324 100644 --- a/include/linux/if.h +++ b/include/linux/if.h @@ -212,5 +212,134 @@ struct ifconf #define ifc_buf ifc_ifcu.ifcu_buf /* buffer address */ #define ifc_req ifc_ifcu.ifcu_req /* array of structures */ +/* The struct should be in sync with struct net_device_stats */ +struct rtnl_link_stats +{ + __u32 rx_packets; /* total packets received */ + __u32 tx_packets; /* total packets transmitted */ + __u32 rx_bytes; /* total bytes received */ + __u32 tx_bytes; /* total bytes transmitted */ + __u32 rx_errors; /* bad packets received */ + __u32 tx_errors; /* packet transmit problems */ + __u32 rx_dropped; /* no space in linux buffers */ + __u32 tx_dropped; /* no space available in linux */ + __u32 multicast; /* multicast packets received */ + __u32 collisions; + + /* detailed rx_errors: */ + __u32 rx_length_errors; + __u32 rx_over_errors; /* receiver ring buff overflow */ + __u32 rx_crc_errors; /* recved pkt with crc error */ + __u32 rx_frame_errors; /* recv'd frame alignment error */ + __u32 rx_fifo_errors; /* recv'r fifo overrun */ + __u32 rx_missed_errors; /* receiver missed packet */ + + /* detailed tx_errors */ + __u32 tx_aborted_errors; + __u32 tx_carrier_errors; + __u32 tx_fifo_errors; + __u32 tx_heartbeat_errors; + __u32 tx_window_errors; + + /* for cslip etc */ + __u32 rx_compressed; + __u32 tx_compressed; +}; + +/* The struct should be in sync with struct ifmap */ +struct rtnl_link_ifmap +{ + __u64 mem_start; + __u64 mem_end; + __u64 base_addr; + __u16 irq; + __u8 dma; + __u8 port; +}; + +enum +{ + IFLA_UNSPEC, + IFLA_ADDRESS, + IFLA_BROADCAST, + IFLA_IFNAME, + IFLA_MTU, + IFLA_LINK, + IFLA_QDISC, + IFLA_STATS, + IFLA_COST, +#define IFLA_COST IFLA_COST + IFLA_PRIORITY, +#define IFLA_PRIORITY IFLA_PRIORITY + IFLA_MASTER, +#define IFLA_MASTER IFLA_MASTER + IFLA_WIRELESS, /* Wireless Extension event - see wireless.h */ +#define IFLA_WIRELESS IFLA_WIRELESS + IFLA_PROTINFO, /* Protocol specific information for a link */ +#define IFLA_PROTINFO IFLA_PROTINFO + IFLA_TXQLEN, +#define IFLA_TXQLEN IFLA_TXQLEN + IFLA_MAP, +#define IFLA_MAP IFLA_MAP + IFLA_WEIGHT, +#define IFLA_WEIGHT IFLA_WEIGHT + IFLA_OPERSTATE, + IFLA_LINKMODE, + __IFLA_MAX +}; + + +#define IFLA_MAX (__IFLA_MAX - 1) + +/* ifi_flags. + + IFF_* flags. + + The only change is: + IFF_LOOPBACK, IFF_BROADCAST and IFF_POINTOPOINT are + more not changeable by user. They describe link media + characteristics and set by device driver. + + Comments: + - Combination IFF_BROADCAST|IFF_POINTOPOINT is invalid + - If neither of these three flags are set; + the interface is NBMA. + + - IFF_MULTICAST does not mean anything special: + multicasts can be used on all not-NBMA links. + IFF_MULTICAST means that this media uses special encapsulation + for multicast frames. Apparently, all IFF_POINTOPOINT and + IFF_BROADCAST devices are able to use multicasts too. + */ + +/* IFLA_LINK. + For usual devices it is equal ifi_index. + If it is a "virtual interface" (f.e. tunnel), ifi_link + can point to real physical interface (f.e. for bandwidth calculations), + or maybe 0, what means, that real media is unknown (usual + for IPIP tunnels, when route to endpoint is allowed to change) + */ + +/* Subtype attributes for IFLA_PROTINFO */ +enum +{ + IFLA_INET6_UNSPEC, + IFLA_INET6_FLAGS, /* link flags */ + IFLA_INET6_CONF, /* sysctl parameters */ + IFLA_INET6_STATS, /* statistics */ + IFLA_INET6_MCAST, /* MC things. What of them? */ + IFLA_INET6_CACHEINFO, /* time values and max reasm size */ + __IFLA_INET6_MAX +}; + +#define IFLA_INET6_MAX (__IFLA_INET6_MAX - 1) + +struct ifla_cacheinfo +{ + __u32 max_reasm_len; + __u32 tstamp; /* ipv6InterfaceTable updated timestamp */ + __u32 reachable_time; + __u32 retrans_time; +}; #endif /* _LINUX_IF_H */ diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 890c4d4038b6..84f3eb426da2 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -2,6 +2,7 @@ #define __LINUX_RTNETLINK_H #include +#include /**** * Routing/neighbour discovery messages. @@ -607,138 +608,6 @@ struct prefix_cacheinfo __u32 valid_time; }; -/* The struct should be in sync with struct net_device_stats */ -struct rtnl_link_stats -{ - __u32 rx_packets; /* total packets received */ - __u32 tx_packets; /* total packets transmitted */ - __u32 rx_bytes; /* total bytes received */ - __u32 tx_bytes; /* total bytes transmitted */ - __u32 rx_errors; /* bad packets received */ - __u32 tx_errors; /* packet transmit problems */ - __u32 rx_dropped; /* no space in linux buffers */ - __u32 tx_dropped; /* no space available in linux */ - __u32 multicast; /* multicast packets received */ - __u32 collisions; - - /* detailed rx_errors: */ - __u32 rx_length_errors; - __u32 rx_over_errors; /* receiver ring buff overflow */ - __u32 rx_crc_errors; /* recved pkt with crc error */ - __u32 rx_frame_errors; /* recv'd frame alignment error */ - __u32 rx_fifo_errors; /* recv'r fifo overrun */ - __u32 rx_missed_errors; /* receiver missed packet */ - - /* detailed tx_errors */ - __u32 tx_aborted_errors; - __u32 tx_carrier_errors; - __u32 tx_fifo_errors; - __u32 tx_heartbeat_errors; - __u32 tx_window_errors; - - /* for cslip etc */ - __u32 rx_compressed; - __u32 tx_compressed; -}; - -/* The struct should be in sync with struct ifmap */ -struct rtnl_link_ifmap -{ - __u64 mem_start; - __u64 mem_end; - __u64 base_addr; - __u16 irq; - __u8 dma; - __u8 port; -}; - -enum -{ - IFLA_UNSPEC, - IFLA_ADDRESS, - IFLA_BROADCAST, - IFLA_IFNAME, - IFLA_MTU, - IFLA_LINK, - IFLA_QDISC, - IFLA_STATS, - IFLA_COST, -#define IFLA_COST IFLA_COST - IFLA_PRIORITY, -#define IFLA_PRIORITY IFLA_PRIORITY - IFLA_MASTER, -#define IFLA_MASTER IFLA_MASTER - IFLA_WIRELESS, /* Wireless Extension event - see wireless.h */ -#define IFLA_WIRELESS IFLA_WIRELESS - IFLA_PROTINFO, /* Protocol specific information for a link */ -#define IFLA_PROTINFO IFLA_PROTINFO - IFLA_TXQLEN, -#define IFLA_TXQLEN IFLA_TXQLEN - IFLA_MAP, -#define IFLA_MAP IFLA_MAP - IFLA_WEIGHT, -#define IFLA_WEIGHT IFLA_WEIGHT - IFLA_OPERSTATE, - IFLA_LINKMODE, - __IFLA_MAX -}; - - -#define IFLA_MAX (__IFLA_MAX - 1) - -#define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg)))) -#define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg)) - -/* ifi_flags. - - IFF_* flags. - - The only change is: - IFF_LOOPBACK, IFF_BROADCAST and IFF_POINTOPOINT are - more not changeable by user. They describe link media - characteristics and set by device driver. - - Comments: - - Combination IFF_BROADCAST|IFF_POINTOPOINT is invalid - - If neither of these three flags are set; - the interface is NBMA. - - - IFF_MULTICAST does not mean anything special: - multicasts can be used on all not-NBMA links. - IFF_MULTICAST means that this media uses special encapsulation - for multicast frames. Apparently, all IFF_POINTOPOINT and - IFF_BROADCAST devices are able to use multicasts too. - */ - -/* IFLA_LINK. - For usual devices it is equal ifi_index. - If it is a "virtual interface" (f.e. tunnel), ifi_link - can point to real physical interface (f.e. for bandwidth calculations), - or maybe 0, what means, that real media is unknown (usual - for IPIP tunnels, when route to endpoint is allowed to change) - */ - -/* Subtype attributes for IFLA_PROTINFO */ -enum -{ - IFLA_INET6_UNSPEC, - IFLA_INET6_FLAGS, /* link flags */ - IFLA_INET6_CONF, /* sysctl parameters */ - IFLA_INET6_STATS, /* statistics */ - IFLA_INET6_MCAST, /* MC things. What of them? */ - IFLA_INET6_CACHEINFO, /* time values and max reasm size */ - __IFLA_INET6_MAX -}; - -#define IFLA_INET6_MAX (__IFLA_INET6_MAX - 1) - -struct ifla_cacheinfo -{ - __u32 max_reasm_len; - __u32 tstamp; /* ipv6InterfaceTable updated timestamp */ - __u32 reachable_time; - __u32 retrans_time; -}; /***************************************************************** * Traffic control messages. -- cgit v1.2.3 From 84fa7933a33f806bbbaae6775e87459b1ec584c0 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 29 Aug 2006 16:44:56 -0700 Subject: [NET]: Replace CHECKSUM_HW by CHECKSUM_PARTIAL/CHECKSUM_COMPLETE Replace CHECKSUM_HW by CHECKSUM_PARTIAL (for outgoing packets, whose checksum still needs to be completed) and CHECKSUM_COMPLETE (for incoming packets, device supplied full checksum). Patch originally from Herbert Xu, updated by myself for 2.6.18-rc3. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- include/linux/skbuff.h | 17 +++++++++-------- 2 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 50a4719512ed..4f2c2b6beb5e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -976,7 +976,7 @@ extern void dev_mcast_init(void); extern int netdev_max_backlog; extern int weight_p; extern int netdev_set_master(struct net_device *dev, struct net_device *master); -extern int skb_checksum_help(struct sk_buff *skb, int inward); +extern int skb_checksum_help(struct sk_buff *skb); extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features); #ifdef CONFIG_BUG extern void netdev_rx_csum_fault(struct net_device *dev); @@ -1012,7 +1012,7 @@ static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb) { return skb_is_gso(skb) && (!skb_gso_ok(skb, dev->features) || - unlikely(skb->ip_summed != CHECKSUM_HW)); + unlikely(skb->ip_summed != CHECKSUM_PARTIAL)); } /* On bonding slaves other than the currently active slave, suppress diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 755e9cddac47..85577a4ffa61 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -34,8 +34,9 @@ #define HAVE_ALIGNABLE_SKB /* Ditto 8) */ #define CHECKSUM_NONE 0 -#define CHECKSUM_HW 1 +#define CHECKSUM_PARTIAL 1 #define CHECKSUM_UNNECESSARY 2 +#define CHECKSUM_COMPLETE 3 #define SKB_DATA_ALIGN(X) (((X) + (SMP_CACHE_BYTES - 1)) & \ ~(SMP_CACHE_BYTES - 1)) @@ -56,17 +57,17 @@ * Apparently with secret goal to sell you new device, when you * will add new protocol to your host. F.e. IPv6. 8) * - * HW: the most generic way. Device supplied checksum of _all_ + * COMPLETE: the most generic way. Device supplied checksum of _all_ * the packet as seen by netif_rx in skb->csum. * NOTE: Even if device supports only some protocols, but - * is able to produce some skb->csum, it MUST use HW, + * is able to produce some skb->csum, it MUST use COMPLETE, * not UNNECESSARY. * * B. Checksumming on output. * * NONE: skb is checksummed by protocol or csum is not required. * - * HW: device is required to csum packet as seen by hard_start_xmit + * PARTIAL: device is required to csum packet as seen by hard_start_xmit * from skb->h.raw to the end and to record the checksum * at skb->h.raw+skb->csum. * @@ -1261,14 +1262,14 @@ static inline int skb_linearize_cow(struct sk_buff *skb) * @len: length of data pulled * * After doing a pull on a received packet, you need to call this to - * update the CHECKSUM_HW checksum, or set ip_summed to CHECKSUM_NONE - * so that it can be recomputed from scratch. + * update the CHECKSUM_COMPLETE checksum, or set ip_summed to + * CHECKSUM_NONE so that it can be recomputed from scratch. */ static inline void skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0)); } @@ -1287,7 +1288,7 @@ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) { if (likely(len >= skb->len)) return 0; - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; return __pskb_trim(skb, len); } -- cgit v1.2.3 From 4cf411de49c65140b3c259748629b561c0d3340f Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sat, 5 Aug 2006 00:58:33 -0700 Subject: [NETFILTER]: Get rid of HW checksum invalidation Update hardware checksums incrementally to avoid breaking GSO. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 6 ++++++ include/linux/netfilter_ipv4/ip_nat.h | 4 ---- include/linux/netfilter_ipv4/ip_nat_core.h | 8 ++++---- 3 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 10168e26a846..b7e67d1d4382 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -282,6 +282,12 @@ extern void nf_invalidate_cache(int pf); Returns true or false. */ extern int skb_make_writable(struct sk_buff **pskb, unsigned int writable_len); +extern u_int16_t nf_csum_update(u_int32_t oldval, u_int32_t newval, + u_int32_t csum); +extern u_int16_t nf_proto_csum_update(struct sk_buff *skb, + u_int32_t oldval, u_int32_t newval, + u_int16_t csum, int pseudohdr); + struct nf_afinfo { unsigned short family; unsigned int (*checksum)(struct sk_buff *skb, unsigned int hook, diff --git a/include/linux/netfilter_ipv4/ip_nat.h b/include/linux/netfilter_ipv4/ip_nat.h index e9f5ed1d9f68..98f8407e4cb5 100644 --- a/include/linux/netfilter_ipv4/ip_nat.h +++ b/include/linux/netfilter_ipv4/ip_nat.h @@ -72,10 +72,6 @@ extern unsigned int ip_nat_setup_info(struct ip_conntrack *conntrack, extern int ip_nat_used_tuple(const struct ip_conntrack_tuple *tuple, const struct ip_conntrack *ignored_conntrack); -/* Calculate relative checksum. */ -extern u_int16_t ip_nat_cheat_check(u_int32_t oldvalinv, - u_int32_t newval, - u_int16_t oldcheck); #else /* !__KERNEL__: iptables wants this to compile. */ #define ip_nat_multi_range ip_nat_multi_range_compat #endif /*__KERNEL__*/ diff --git a/include/linux/netfilter_ipv4/ip_nat_core.h b/include/linux/netfilter_ipv4/ip_nat_core.h index 30db23f06b03..60566f9fd7b3 100644 --- a/include/linux/netfilter_ipv4/ip_nat_core.h +++ b/include/linux/netfilter_ipv4/ip_nat_core.h @@ -11,8 +11,8 @@ extern unsigned int ip_nat_packet(struct ip_conntrack *ct, unsigned int hooknum, struct sk_buff **pskb); -extern int ip_nat_icmp_reply_translation(struct sk_buff **pskb, - struct ip_conntrack *ct, - enum ip_nat_manip_type manip, - enum ip_conntrack_dir dir); +extern int ip_nat_icmp_reply_translation(struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned int hooknum, + struct sk_buff **pskb); #endif /* _IP_NAT_CORE_H */ -- cgit v1.2.3 From 9067c722cf6930adf1df2d169de9094dd90b0c33 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Mon, 7 Aug 2006 17:57:44 -0700 Subject: [NEIGH]: Move netlink neighbour bits to linux/neighbour.h Moves netlink neighbour bits to linux/neighbour.h. Also moves bits to be exported to userspace from net/neighbour.h to linux/neighbour.h and removes __KERNEL__ guards, userspace is not supposed to be using it. rtnetlink_rcv_msg() is not longer required to parse attributes for the neighbour layer, remove dependency on obsolete and buggy rta_buf. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/neighbour.h | 65 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/rtnetlink.h | 63 --------------------------------------------- 2 files changed, 65 insertions(+), 63 deletions(-) create mode 100644 include/linux/neighbour.h (limited to 'include/linux') diff --git a/include/linux/neighbour.h b/include/linux/neighbour.h new file mode 100644 index 000000000000..8e8293d86fbb --- /dev/null +++ b/include/linux/neighbour.h @@ -0,0 +1,65 @@ +#ifndef __LINUX_NEIGHBOUR_H +#define __LINUX_NEIGHBOUR_H + +#include + +struct ndmsg +{ + __u8 ndm_family; + __u8 ndm_pad1; + __u16 ndm_pad2; + __s32 ndm_ifindex; + __u16 ndm_state; + __u8 ndm_flags; + __u8 ndm_type; +}; + +enum +{ + NDA_UNSPEC, + NDA_DST, + NDA_LLADDR, + NDA_CACHEINFO, + NDA_PROBES, + __NDA_MAX +}; + +#define NDA_MAX (__NDA_MAX - 1) + +/* + * Neighbor Cache Entry Flags + */ + +#define NTF_PROXY 0x08 /* == ATF_PUBL */ +#define NTF_ROUTER 0x80 + +/* + * Neighbor Cache Entry States. + */ + +#define NUD_INCOMPLETE 0x01 +#define NUD_REACHABLE 0x02 +#define NUD_STALE 0x04 +#define NUD_DELAY 0x08 +#define NUD_PROBE 0x10 +#define NUD_FAILED 0x20 + +/* Dummy states */ +#define NUD_NOARP 0x40 +#define NUD_PERMANENT 0x80 +#define NUD_NONE 0x00 + +/* NUD_NOARP & NUD_PERMANENT are pseudostates, they never change + and make no address resolution or NUD. + NUD_PERMANENT is also cannot be deleted by garbage collectors. + */ + +struct nda_cacheinfo +{ + __u32 ndm_confirmed; + __u32 ndm_used; + __u32 ndm_updated; + __u32 ndm_refcnt; +}; + +#endif diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 84f3eb426da2..9750f0214c22 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -386,69 +386,6 @@ struct rta_session -/************************************************************** - * Neighbour discovery. - ****/ - -struct ndmsg -{ - unsigned char ndm_family; - unsigned char ndm_pad1; - unsigned short ndm_pad2; - int ndm_ifindex; /* Link index */ - __u16 ndm_state; - __u8 ndm_flags; - __u8 ndm_type; -}; - -enum -{ - NDA_UNSPEC, - NDA_DST, - NDA_LLADDR, - NDA_CACHEINFO, - NDA_PROBES, - __NDA_MAX -}; - -#define NDA_MAX (__NDA_MAX - 1) - -#define NDA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ndmsg)))) -#define NDA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ndmsg)) - -/* - * Neighbor Cache Entry Flags - */ - -#define NTF_PROXY 0x08 /* == ATF_PUBL */ -#define NTF_ROUTER 0x80 - -/* - * Neighbor Cache Entry States. - */ - -#define NUD_INCOMPLETE 0x01 -#define NUD_REACHABLE 0x02 -#define NUD_STALE 0x04 -#define NUD_DELAY 0x08 -#define NUD_PROBE 0x10 -#define NUD_FAILED 0x20 - -/* Dummy states */ -#define NUD_NOARP 0x40 -#define NUD_PERMANENT 0x80 -#define NUD_NONE 0x00 - - -struct nda_cacheinfo -{ - __u32 ndm_confirmed; - __u32 ndm_used; - __u32 ndm_updated; - __u32 ndm_refcnt; -}; - - /***************************************************************** * Neighbour tables specific messages. * -- cgit v1.2.3 From b63bbc5006a0a62fabc81c4f77e95f16ff16f340 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Mon, 7 Aug 2006 18:00:57 -0700 Subject: [NEIGH]: Move netlink neighbour table bits to linux/neighbour.h rtnetlink_rcv_msg() is not longer required to parse attributes for the neighbour tables layer, remove dependency on obsolete and buggy rta_buf. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/neighbour.h | 94 ++++++++++++++++++++++++++++++++++++++++++ include/linux/rtnetlink.h | 101 ---------------------------------------------- 2 files changed, 94 insertions(+), 101 deletions(-) (limited to 'include/linux') diff --git a/include/linux/neighbour.h b/include/linux/neighbour.h index 8e8293d86fbb..bd3bbf668cdb 100644 --- a/include/linux/neighbour.h +++ b/include/linux/neighbour.h @@ -62,4 +62,98 @@ struct nda_cacheinfo __u32 ndm_refcnt; }; +/***************************************************************** + * Neighbour tables specific messages. + * + * To retrieve the neighbour tables send RTM_GETNEIGHTBL with the + * NLM_F_DUMP flag set. Every neighbour table configuration is + * spread over multiple messages to avoid running into message + * size limits on systems with many interfaces. The first message + * in the sequence transports all not device specific data such as + * statistics, configuration, and the default parameter set. + * This message is followed by 0..n messages carrying device + * specific parameter sets. + * Although the ordering should be sufficient, NDTA_NAME can be + * used to identify sequences. The initial message can be identified + * by checking for NDTA_CONFIG. The device specific messages do + * not contain this TLV but have NDTPA_IFINDEX set to the + * corresponding interface index. + * + * To change neighbour table attributes, send RTM_SETNEIGHTBL + * with NDTA_NAME set. Changeable attribute include NDTA_THRESH[1-3], + * NDTA_GC_INTERVAL, and all TLVs in NDTA_PARMS unless marked + * otherwise. Device specific parameter sets can be changed by + * setting NDTPA_IFINDEX to the interface index of the corresponding + * device. + ****/ + +struct ndt_stats +{ + __u64 ndts_allocs; + __u64 ndts_destroys; + __u64 ndts_hash_grows; + __u64 ndts_res_failed; + __u64 ndts_lookups; + __u64 ndts_hits; + __u64 ndts_rcv_probes_mcast; + __u64 ndts_rcv_probes_ucast; + __u64 ndts_periodic_gc_runs; + __u64 ndts_forced_gc_runs; +}; + +enum { + NDTPA_UNSPEC, + NDTPA_IFINDEX, /* u32, unchangeable */ + NDTPA_REFCNT, /* u32, read-only */ + NDTPA_REACHABLE_TIME, /* u64, read-only, msecs */ + NDTPA_BASE_REACHABLE_TIME, /* u64, msecs */ + NDTPA_RETRANS_TIME, /* u64, msecs */ + NDTPA_GC_STALETIME, /* u64, msecs */ + NDTPA_DELAY_PROBE_TIME, /* u64, msecs */ + NDTPA_QUEUE_LEN, /* u32 */ + NDTPA_APP_PROBES, /* u32 */ + NDTPA_UCAST_PROBES, /* u32 */ + NDTPA_MCAST_PROBES, /* u32 */ + NDTPA_ANYCAST_DELAY, /* u64, msecs */ + NDTPA_PROXY_DELAY, /* u64, msecs */ + NDTPA_PROXY_QLEN, /* u32 */ + NDTPA_LOCKTIME, /* u64, msecs */ + __NDTPA_MAX +}; +#define NDTPA_MAX (__NDTPA_MAX - 1) + +struct ndtmsg +{ + __u8 ndtm_family; + __u8 ndtm_pad1; + __u16 ndtm_pad2; +}; + +struct ndt_config +{ + __u16 ndtc_key_len; + __u16 ndtc_entry_size; + __u32 ndtc_entries; + __u32 ndtc_last_flush; /* delta to now in msecs */ + __u32 ndtc_last_rand; /* delta to now in msecs */ + __u32 ndtc_hash_rnd; + __u32 ndtc_hash_mask; + __u32 ndtc_hash_chain_gc; + __u32 ndtc_proxy_qlen; +}; + +enum { + NDTA_UNSPEC, + NDTA_NAME, /* char *, unchangeable */ + NDTA_THRESH1, /* u32 */ + NDTA_THRESH2, /* u32 */ + NDTA_THRESH3, /* u32 */ + NDTA_CONFIG, /* struct ndt_config, read-only */ + NDTA_PARMS, /* nested TLV NDTPA_* */ + NDTA_STATS, /* struct ndt_stats, read-only */ + NDTA_GC_INTERVAL, /* u64, msecs */ + __NDTA_MAX +}; +#define NDTA_MAX (__NDTA_MAX - 1) + #endif diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 9750f0214c22..784a1a29490e 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -384,107 +384,6 @@ struct rta_session } u; }; - - -/***************************************************************** - * Neighbour tables specific messages. - * - * To retrieve the neighbour tables send RTM_GETNEIGHTBL with the - * NLM_F_DUMP flag set. Every neighbour table configuration is - * spread over multiple messages to avoid running into message - * size limits on systems with many interfaces. The first message - * in the sequence transports all not device specific data such as - * statistics, configuration, and the default parameter set. - * This message is followed by 0..n messages carrying device - * specific parameter sets. - * Although the ordering should be sufficient, NDTA_NAME can be - * used to identify sequences. The initial message can be identified - * by checking for NDTA_CONFIG. The device specific messages do - * not contain this TLV but have NDTPA_IFINDEX set to the - * corresponding interface index. - * - * To change neighbour table attributes, send RTM_SETNEIGHTBL - * with NDTA_NAME set. Changeable attribute include NDTA_THRESH[1-3], - * NDTA_GC_INTERVAL, and all TLVs in NDTA_PARMS unless marked - * otherwise. Device specific parameter sets can be changed by - * setting NDTPA_IFINDEX to the interface index of the corresponding - * device. - ****/ - -struct ndt_stats -{ - __u64 ndts_allocs; - __u64 ndts_destroys; - __u64 ndts_hash_grows; - __u64 ndts_res_failed; - __u64 ndts_lookups; - __u64 ndts_hits; - __u64 ndts_rcv_probes_mcast; - __u64 ndts_rcv_probes_ucast; - __u64 ndts_periodic_gc_runs; - __u64 ndts_forced_gc_runs; -}; - -enum { - NDTPA_UNSPEC, - NDTPA_IFINDEX, /* u32, unchangeable */ - NDTPA_REFCNT, /* u32, read-only */ - NDTPA_REACHABLE_TIME, /* u64, read-only, msecs */ - NDTPA_BASE_REACHABLE_TIME, /* u64, msecs */ - NDTPA_RETRANS_TIME, /* u64, msecs */ - NDTPA_GC_STALETIME, /* u64, msecs */ - NDTPA_DELAY_PROBE_TIME, /* u64, msecs */ - NDTPA_QUEUE_LEN, /* u32 */ - NDTPA_APP_PROBES, /* u32 */ - NDTPA_UCAST_PROBES, /* u32 */ - NDTPA_MCAST_PROBES, /* u32 */ - NDTPA_ANYCAST_DELAY, /* u64, msecs */ - NDTPA_PROXY_DELAY, /* u64, msecs */ - NDTPA_PROXY_QLEN, /* u32 */ - NDTPA_LOCKTIME, /* u64, msecs */ - __NDTPA_MAX -}; -#define NDTPA_MAX (__NDTPA_MAX - 1) - -struct ndtmsg -{ - __u8 ndtm_family; - __u8 ndtm_pad1; - __u16 ndtm_pad2; -}; - -struct ndt_config -{ - __u16 ndtc_key_len; - __u16 ndtc_entry_size; - __u32 ndtc_entries; - __u32 ndtc_last_flush; /* delta to now in msecs */ - __u32 ndtc_last_rand; /* delta to now in msecs */ - __u32 ndtc_hash_rnd; - __u32 ndtc_hash_mask; - __u32 ndtc_hash_chain_gc; - __u32 ndtc_proxy_qlen; -}; - -enum { - NDTA_UNSPEC, - NDTA_NAME, /* char *, unchangeable */ - NDTA_THRESH1, /* u32 */ - NDTA_THRESH2, /* u32 */ - NDTA_THRESH3, /* u32 */ - NDTA_CONFIG, /* struct ndt_config, read-only */ - NDTA_PARMS, /* nested TLV NDTPA_* */ - NDTA_STATS, /* struct ndt_stats, read-only */ - NDTA_GC_INTERVAL, /* u64, msecs */ - __NDTA_MAX -}; -#define NDTA_MAX (__NDTA_MAX - 1) - -#define NDTA_RTA(r) ((struct rtattr*)(((char*)(r)) + \ - NLMSG_ALIGN(sizeof(struct ndtmsg)))) -#define NDTA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ndtmsg)) - - /**** * General form of address family dependent message. ****/ -- cgit v1.2.3 From ac5a488ef252ed673cb067843e411f8cc43f7ab9 Mon Sep 17 00:00:00 2001 From: Sridhar Samudrala Date: Mon, 7 Aug 2006 20:57:31 -0700 Subject: [NET]: Round out in-kernel sockets API This patch implements wrapper functions that provide a convenient way to access the sockets API for in-kernel users like sunrpc, cifs & ocfs2 etc and any future users. Signed-off-by: Sridhar Samudrala Acked-by: James Morris Signed-off-by: David S. Miller --- include/linux/net.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index b20c53c74413..19da2c08d7b6 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -208,6 +208,25 @@ extern int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len, int flags); +extern int kernel_bind(struct socket *sock, struct sockaddr *addr, + int addrlen); +extern int kernel_listen(struct socket *sock, int backlog); +extern int kernel_accept(struct socket *sock, struct socket **newsock, + int flags); +extern int kernel_connect(struct socket *sock, struct sockaddr *addr, + int addrlen, int flags); +extern int kernel_getsockname(struct socket *sock, struct sockaddr *addr, + int *addrlen); +extern int kernel_getpeername(struct socket *sock, struct sockaddr *addr, + int *addrlen); +extern int kernel_getsockopt(struct socket *sock, int level, int optname, + char *optval, int *optlen); +extern int kernel_setsockopt(struct socket *sock, int level, int optname, + char *optval, int optlen); +extern int kernel_sendpage(struct socket *sock, struct page *page, int offset, + size_t size, int flags); +extern int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg); + #ifndef CONFIG_SMP #define SOCKOPS_WRAPPED(name) name #define SOCKOPS_WRAP(name, fam) -- cgit v1.2.3 From a8731cbf61c8768ea129780b70dc7dfc6795aad4 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Wed, 9 Aug 2006 15:56:46 -0700 Subject: [DECNET]: Covert rules to use generic code This patch converts the DECnet rules code to use the generic rules system created by Thomas Graf . Signed-off-by: Steven Whitehouse Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 784a1a29490e..0aaffa2ae666 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -534,7 +534,8 @@ enum rtnetlink_groups { RTNLGRP_NOP2, RTNLGRP_DECnet_ROUTE, #define RTNLGRP_DECnet_ROUTE RTNLGRP_DECnet_ROUTE - RTNLGRP_NOP3, + RTNLGRP_DECnet_RULE, +#define RTNLGRP_DECnet_RULE RTNLGRP_DECnet_RULE RTNLGRP_NOP4, RTNLGRP_IPV6_PREFIX, #define RTNLGRP_IPV6_PREFIX RTNLGRP_IPV6_PREFIX -- cgit v1.2.3 From 757dbb494be3309fe41ce4c62f8057d8b41d8897 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Wed, 9