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 --- net/core/sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/sock.c b/net/core/sock.c index 51fcfbc041a..b67d868649c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -911,7 +911,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) if (newsk != NULL) { struct sk_filter *filter; - memcpy(newsk, sk, sk->sk_prot->obj_size); + sock_copy(newsk, sk); /* SANITY */ sk_node_init(&newsk->sk_node); -- cgit v1.2.3-70-g09d2 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 +++++++++++++++++---- include/net/flow.h | 4 +- net/core/flow.c | 7 +- net/xfrm/xfrm_policy.c | 28 +++--- net/xfrm/xfrm_state.c | 12 ++- security/dummy.c | 23 ++++- security/selinux/hooks.c | 7 +- security/selinux/include/xfrm.h | 23 +++-- security/selinux/xfrm.c | 199 +++++++++++++++++++++++++++++++++------- 9 files changed, 329 insertions(+), 80 deletions(-) (limited to 'net/core') diff --git a/include/linux/security.h b/include/linux/security.h index 4d7fb59996b..2c4921d79d1 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 diff --git a/include/net/flow.h b/include/net/flow.h index 1cee5a83433..21d988b2058 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -86,10 +86,10 @@ struct flowi { #define FLOW_DIR_FWD 2 struct sock; -typedef void (*flow_resolve_t)(struct flowi *key, u32 sk_sid, u16 family, u8 dir, +typedef void (*flow_resolve_t)(struct flowi *key, u16 family, u8 dir, void **objp, atomic_t **obj_refp); -extern void *flow_cache_lookup(struct flowi *key, u32 sk_sid, u16 family, u8 dir, +extern void *flow_cache_lookup(struct flowi *key, u16 family, u8 dir, flow_resolve_t resolver); extern void flow_cache_flush(void); extern atomic_t flow_cache_genid; diff --git a/net/core/flow.c b/net/core/flow.c index 2191af5f26a..645241165e6 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -32,7 +32,6 @@ struct flow_cache_entry { u8 dir; struct flowi key; u32 genid; - u32 sk_sid; void *object; atomic_t *object_ref; }; @@ -165,7 +164,7 @@ static int flow_key_compare(struct flowi *key1, struct flowi *key2) return 0; } -void *flow_cache_lookup(struct flowi *key, u32 sk_sid, u16 family, u8 dir, +void *flow_cache_lookup(struct flowi *key, u16 family, u8 dir, flow_resolve_t resolver) { struct flow_cache_entry *fle, **head; @@ -189,7 +188,6 @@ void *flow_cache_lookup(struct flowi *key, u32 sk_sid, u16 family, u8 dir, for (fle = *head; fle; fle = fle->next) { if (fle->family == family && fle->dir == dir && - fle->sk_sid == sk_sid && flow_key_compare(key, &fle->key) == 0) { if (fle->genid == atomic_read(&flow_cache_genid)) { void *ret = fle->object; @@ -214,7 +212,6 @@ void *flow_cache_lookup(struct flowi *key, u32 sk_sid, u16 family, u8 dir, *head = fle; fle->family = family; fle->dir = dir; - fle->sk_sid = sk_sid; memcpy(&fle->key, key, sizeof(*key)); fle->object = NULL; flow_count(cpu)++; @@ -226,7 +223,7 @@ nocache: void *obj; atomic_t *obj_ref; - resolver(key, sk_sid, family, dir, &obj, &obj_ref); + resolver(key, family, dir, &obj, &obj_ref); if (fle) { fle->genid = atomic_read(&flow_cache_genid); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 3da67ca2c3c..79405daadc5 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -597,7 +597,7 @@ EXPORT_SYMBOL(xfrm_policy_walk); /* Find policy to apply to this flow. */ -static void xfrm_policy_lookup(struct flowi *fl, u32 sk_sid, u16 family, u8 dir, +static void xfrm_policy_lookup(struct flowi *fl, u16 family, u8 dir, void **objp, atomic_t **obj_refp) { struct xfrm_policy *pol; @@ -613,7 +613,7 @@ static void xfrm_policy_lookup(struct flowi *fl, u32 sk_sid, u16 family, u8 dir, match = xfrm_selector_match(sel, fl, family); if (match) { - if (!security_xfrm_policy_lookup(pol, sk_sid, dir)) { + if (!security_xfrm_policy_lookup(pol, fl->secid, dir)) { xfrm_pol_hold(pol); break; } @@ -641,7 +641,7 @@ static inline int policy_to_flow_dir(int dir) }; } -static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, struct flowi *fl, u32 sk_sid) +static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, struct flowi *fl) { struct xfrm_policy *pol; @@ -652,7 +652,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, struc int err = 0; if (match) - err = security_xfrm_policy_lookup(pol, sk_sid, policy_to_flow_dir(dir)); + err = security_xfrm_policy_lookup(pol, fl->secid, policy_to_flow_dir(dir)); if (match && !err) xfrm_pol_hold(pol); @@ -862,19 +862,20 @@ int xfrm_lookup(struct dst_entry **dst_p, struct flowi *fl, u32 genid; u16 family; u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT); - u32 sk_sid = security_sk_sid(sk, fl, dir); + + fl->secid = security_sk_sid(sk, fl, dir); restart: genid = atomic_read(&flow_cache_genid); policy = NULL; if (sk && sk->sk_policy[1]) - policy = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, sk_sid); + policy = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl); if (!policy) { /* To accelerate a bit... */ if ((dst_orig->flags & DST_NOXFRM) || !xfrm_policy_list[XFRM_POLICY_OUT]) return 0; - policy = flow_cache_lookup(fl, sk_sid, dst_orig->ops->family, + policy = flow_cache_lookup(fl, dst_orig->ops->family, dir, xfrm_policy_lookup); } @@ -1032,13 +1033,15 @@ int xfrm_decode_session(struct sk_buff *skb, struct flowi *fl, unsigned short family) { struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); + int err; if (unlikely(afinfo == NULL)) return -EAFNOSUPPORT; afinfo->decode_session(skb, fl); + err = security_xfrm_decode_session(skb, fl); xfrm_policy_put_afinfo(afinfo); - return 0; + return err; } EXPORT_SYMBOL(xfrm_decode_session); @@ -1058,14 +1061,11 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, struct xfrm_policy *pol; struct flowi fl; u8 fl_dir = policy_to_flow_dir(dir); - u32 sk_sid; if (xfrm_decode_session(skb, &fl, family) < 0) return 0; nf_nat_decode_session(skb, &fl, family); - sk_sid = security_sk_sid(sk, &fl, fl_dir); - /* First, check used SA against their selectors. */ if (skb->sp) { int i; @@ -1079,10 +1079,10 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, pol = NULL; if (sk && sk->sk_policy[dir]) - pol = xfrm_sk_policy_lookup(sk, dir, &fl, sk_sid); + pol = xfrm_sk_policy_lookup(sk, dir, &fl); if (!pol) - pol = flow_cache_lookup(&fl, sk_sid, family, fl_dir, + pol = flow_cache_lookup(&fl, family, fl_dir, xfrm_policy_lookup); if (!pol) @@ -1298,6 +1298,8 @@ int xfrm_bundle_ok(struct xfrm_dst *first, struct flowi *fl, int family) if (fl && !xfrm_selector_match(&dst->xfrm->sel, fl, family)) return 0; + if (fl && !security_xfrm_flow_state_match(fl, dst->xfrm)) + return 0; if (dst->xfrm->km.state != XFRM_STATE_VALID) return 0; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 0021aad5db4..be02bd981d1 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -367,7 +367,7 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, */ if (x->km.state == XFRM_STATE_VALID) { if (!xfrm_selector_match(&x->sel, fl, family) || - !xfrm_sec_ctx_match(pol->security, x->security)) + !security_xfrm_state_pol_flow_match(x, pol, fl)) continue; if (!best || best->km.dying > x->km.dying || @@ -379,7 +379,7 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, } else if (x->km.state == XFRM_STATE_ERROR || x->km.state == XFRM_STATE_EXPIRED) { if (xfrm_selector_match(&x->sel, fl, family) && - xfrm_sec_ctx_match(pol->security, x->security)) + security_xfrm_state_pol_flow_match(x, pol, fl)) error = -ESRCH; } } @@ -403,6 +403,14 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, * to current session. */ xfrm_init_tempsel(x, fl, tmpl, daddr, saddr, family); + error = security_xfrm_state_alloc_acquire(x, pol->security, fl->secid); + if (error) { + x->km.state = XFRM_STATE_DEAD; + xfrm_state_put(x); + x = NULL; + goto out; + } + if (km_query(x, tmpl, pol) == 0) { x->km.state = XFRM_STATE_ACQ; list_add_tail(&x->bydst, xfrm_state_bydst+h); diff --git a/security/dummy.c b/security/dummy.c index bd3bc5faa9a..c1f10654871 100644 --- a/security/dummy.c +++ b/security/dummy.c @@ -835,7 +835,8 @@ static int dummy_xfrm_policy_delete_security(struct xfrm_policy *xp) return 0; } -static int dummy_xfrm_state_alloc_security(struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx) +static int dummy_xfrm_state_alloc_security(struct xfrm_state *x, + struct xfrm_user_sec_ctx *sec_ctx, struct xfrm_sec_ctx *pol, u32 secid) { return 0; } @@ -853,6 +854,23 @@ static int dummy_xfrm_policy_lookup(struct xfrm_policy *xp, u32 sk_sid, u8 dir) { return 0; } + +static int dummy_xfrm_state_pol_flow_match(struct xfrm_state *x, + struct xfrm_policy *xp, struct flowi *fl) +{ + return 1; +} + +static int dummy_xfrm_flow_state_match(struct flowi *fl, struct xfrm_state *xfrm) +{ + return 1; +} + +static int dummy_xfrm_decode_session(struct sk_buff *skb, struct flowi *fl) +{ + return 0; +} + #endif /* CONFIG_SECURITY_NETWORK_XFRM */ static int dummy_register_security (const char *name, struct security_operations *ops) { @@ -1076,6 +1094,9 @@ void security_fixup_ops (struct security_operations *ops) set_to_dummy_if_null(ops, xfrm_state_free_security); set_to_dummy_if_null(ops, xfrm_state_delete_security); set_to_dummy_if_null(ops, xfrm_policy_lookup); + set_to_dummy_if_null(ops, xfrm_state_pol_flow_match); + set_to_dummy_if_null(ops, xfrm_flow_state_match); + set_to_dummy_if_null(ops, xfrm_decode_session); #endif /* CONFIG_SECURITY_NETWORK_XFRM */ #ifdef CONFIG_KEYS set_to_dummy_if_null(ops, key_alloc); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index d67abf77584..5c189da07bc 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3468,7 +3468,7 @@ static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) if (err) goto out; - err = selinux_xfrm_sock_rcv_skb(sock_sid, skb); + err = selinux_xfrm_sock_rcv_skb(sock_sid, skb, &ad); out: return err; } @@ -3720,7 +3720,7 @@ static unsigned int selinux_ip_postroute_last(unsigned int hooknum, if (err) goto out; - err = selinux_xfrm_postroute_last(isec->sid, skb); + err = selinux_xfrm_postroute_last(isec->sid, skb, &ad); out: return err ? NF_DROP : NF_ACCEPT; } @@ -4633,6 +4633,9 @@ static struct security_operations selinux_ops = { .xfrm_state_free_security = selinux_xfrm_state_free, .xfrm_state_delete_security = selinux_xfrm_state_delete, .xfrm_policy_lookup = selinux_xfrm_policy_lookup, + .xfrm_state_pol_flow_match = selinux_xfrm_state_pol_flow_match, + .xfrm_flow_state_match = selinux_xfrm_flow_state_match, + .xfrm_decode_session = selinux_xfrm_decode_session, #endif #ifdef CONFIG_KEYS diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h index c96498a10eb..f51a3e84bd9 100644 --- a/security/selinux/include/xfrm.h +++ b/security/selinux/include/xfrm.h @@ -2,6 +2,7 @@ * SELinux support for the XFRM LSM hooks * * Author : Trent Jaeger, + * Updated : Venkat Yekkirala, */ #ifndef _SELINUX_XFRM_H_ #define _SELINUX_XFRM_H_ @@ -10,10 +11,16 @@ int selinux_xfrm_policy_alloc(struct xfrm_policy *xp, struct xfrm_user_sec_ctx * int selinux_xfrm_policy_clone(struct xfrm_policy *old, struct xfrm_policy *new); void selinux_xfrm_policy_free(struct xfrm_policy *xp); int selinux_xfrm_policy_delete(struct xfrm_policy *xp); -int selinux_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx); +int selinux_xfrm_state_alloc(struct xfrm_state *x, + struct xfrm_user_sec_ctx *sec_ctx, struct xfrm_sec_ctx *pol, u32 secid); void selinux_xfrm_state_free(struct xfrm_state *x); int selinux_xfrm_state_delete(struct xfrm_state *x); -int selinux_xfrm_policy_lookup(struct xfrm_policy *xp, u32 sk_sid, u8 dir); +int selinux_xfrm_policy_lookup(struct xfrm_policy *xp, u32 fl_secid, u8 dir); +int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x, + struct xfrm_policy *xp, struct flowi *fl); +int selinux_xfrm_flow_state_match(struct flowi *fl, struct xfrm_state *xfrm); +int selinux_xfrm_decode_session(struct sk_buff *skb, struct flowi *fl); + /* * Extract the security blob from the sock (it's actually on the socket) @@ -39,17 +46,21 @@ static inline u32 selinux_no_sk_sid(struct flowi *fl) } #ifdef CONFIG_SECURITY_NETWORK_XFRM -int selinux_xfrm_sock_rcv_skb(u32 sid, struct sk_buff *skb); -int selinux_xfrm_postroute_last(u32 isec_sid, struct sk_buff *skb); +int selinux_xfrm_sock_rcv_skb(u32 sid, struct sk_buff *skb, + struct avc_audit_data *ad); +int selinux_xfrm_postroute_last(u32 isec_sid, struct sk_buff *skb, + struct avc_audit_data *ad); u32 selinux_socket_getpeer_stream(struct sock *sk); u32 selinux_socket_getpeer_dgram(struct sk_buff *skb); #else -static inline int selinux_xfrm_sock_rcv_skb(u32 isec_sid, struct sk_buff *skb) +static inline int selinux_xfrm_sock_rcv_skb(u32 isec_sid, struct sk_buff *skb, + struct avc_audit_data *ad) { return 0; } -static inline int selinux_xfrm_postroute_last(u32 isec_sid, struct sk_buff *skb) +static inline int selinux_xfrm_postroute_last(u32 isec_sid, struct sk_buff *skb, + struct avc_audit_data *ad) { return 0; } diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c index 6c985ced810..a502b0540e3 100644 --- a/security/selinux/xfrm.c +++ b/security/selinux/xfrm.c @@ -6,7 +6,12 @@ * Authors: Serge Hallyn * Trent Jaeger * + * Updated: Venkat Yekkirala + * + * Granular IPSec Associations for use in MLS environments. + * * Copyright (C) 2005 International Business Machines Corporation + * Copyright (C) 2006 Trusted Computer Solutions, Inc. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2, @@ -67,10 +72,10 @@ static inline int selinux_authorizable_xfrm(struct xfrm_state *x) } /* - * LSM hook implementation that authorizes that a socket can be used - * with the corresponding xfrm_sec_ctx and direction. + * LSM hook implementation that authorizes that a flow can use + * a xfrm policy rule. */ -int selinux_xfrm_policy_lookup(struct xfrm_policy *xp, u32 sk_sid, u8 dir) +int selinux_xfrm_policy_lookup(struct xfrm_policy *xp, u32 fl_secid, u8 dir) { int rc = 0; u32 sel_sid = SECINITSID_UNLABELED; @@ -84,27 +89,129 @@ int selinux_xfrm_policy_lookup(struct xfrm_policy *xp, u32 sk_sid, u8 dir) sel_sid = ctx->ctx_sid; } - rc = avc_has_perm(sk_sid, sel_sid, SECCLASS_ASSOCIATION, - ((dir == FLOW_DIR_IN) ? ASSOCIATION__RECVFROM : - ((dir == FLOW_DIR_OUT) ? ASSOCIATION__SENDTO : - (ASSOCIATION__SENDTO | ASSOCIATION__RECVFROM))), + rc = avc_has_perm(fl_secid, sel_sid, SECCLASS_ASSOCIATION, + ASSOCIATION__POLMATCH, NULL); return rc; } +/* + * LSM hook implementation that authorizes that a state matches + * the given policy, flow combo. + */ + +int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *xp, + struct flowi *fl) +{ + u32 state_sid; + u32 pol_sid; + int err; + + if (x->security) + state_sid = x->security->ctx_sid; + else + state_sid = SECINITSID_UNLABELED; + + if (xp->security) + pol_sid = xp->security->ctx_sid; + else + pol_sid = SECINITSID_UNLABELED; + + err = avc_has_perm(state_sid, pol_sid, SECCLASS_ASSOCIATION, + ASSOCIATION__POLMATCH, + NULL); + + if (err) + return 0; + + return selinux_xfrm_flow_state_match(fl, x); +} + +/* + * LSM hook implementation that authorizes that a particular outgoing flow + * can use a given security association. + */ + +int selinux_xfrm_flow_state_match(struct flowi *fl, struct xfrm_state *xfrm) +{ + int rc = 0; + u32 sel_sid = SECINITSID_UNLABELED; + struct xfrm_sec_ctx *ctx; + + /* Context sid is either set to label or ANY_ASSOC */ + if ((ctx = xfrm->security)) { + if (!selinux_authorizable_ctx(ctx)) + return 0; + + sel_sid = ctx->ctx_sid; + } + + rc = avc_has_perm(fl->secid, sel_sid, SECCLASS_ASSOCIATION, + ASSOCIATION__SENDTO, + NULL)? 0:1; + + return rc; +} + +/* + * LSM hook implementation that determines the sid for the session. + */ + +int selinux_xfrm_decode_session(struct sk_buff *skb, struct flowi *fl) +{ + struct sec_path *sp; + + fl->secid = SECSID_NULL; + + if (skb == NULL) + return 0; + + sp = skb->sp; + if (sp) { + int i, sid_set = 0; + + for (i = sp->len-1; i >= 0; i--) { + struct xfrm_state *x = sp->xvec[i]; + if (selinux_authorizable_xfrm(x)) { + struct xfrm_sec_ctx *ctx = x->security; + + if (!sid_set) { + fl->secid = ctx->ctx_sid; + sid_set = 1; + } + else if (fl->secid != ctx->ctx_sid) + return -EINVAL; + } + } + } + + return 0; +} + /* * Security blob allocation for xfrm_policy and xfrm_state * CTX does not have a meaningful value on input */ -static int selinux_xfrm_sec_ctx_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *uctx) +static int selinux_xfrm_sec_ctx_alloc(struct xfrm_sec_ctx **ctxp, + struct xfrm_user_sec_ctx *uctx, struct xfrm_sec_ctx *pol, u32 sid) { int rc = 0; struct task_security_struct *tsec = current->security; - struct xfrm_sec_ctx *ctx; + struct xfrm_sec_ctx *ctx = NULL; + char *ctx_str = NULL; + u32 str_len; + u32 ctx_sid; + + BUG_ON(uctx && pol); + + if (pol) + goto from_policy; BUG_ON(!uctx); - BUG_ON(uctx->ctx_doi != XFRM_SC_ALG_SELINUX); + + if (uctx->ctx_doi != XFRM_SC_ALG_SELINUX) + return -EINVAL; if (uctx->ctx_len >= PAGE_SIZE) return -ENOMEM; @@ -141,9 +248,41 @@ static int selinux_xfrm_sec_ctx_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_us return rc; +from_policy: + BUG_ON(!pol); + rc = security_sid_mls_copy(pol->ctx_sid, sid, &ctx_sid); + if (rc) + goto out; + + rc = security_sid_to_context(ctx_sid, &ctx_str, &str_len); + if (rc) + goto out; + + *ctxp = ctx = kmalloc(sizeof(*ctx) + + str_len, + GFP_ATOMIC); + + if (!ctx) { + rc = -ENOMEM; + goto out; + } + + + ctx->ctx_doi = XFRM_SC_DOI_LSM; + ctx->ctx_alg = XFRM_SC_ALG_SELINUX; + ctx->ctx_sid = ctx_sid; + ctx->ctx_len = str_len; + memcpy(ctx->ctx_str, + ctx_str, + str_len); + + goto out2; + out: *ctxp = NULL; kfree(ctx); +out2: + kfree(ctx_str); return rc; } @@ -157,7 +296,7 @@ int selinux_xfrm_policy_alloc(struct xfrm_policy *xp, struct xfrm_user_sec_ctx * BUG_ON(!xp); - err = selinux_xfrm_sec_ctx_alloc(&xp->security, uctx); + err = selinux_xfrm_sec_ctx_alloc(&xp->security, uctx, NULL, 0); return err; } @@ -217,13 +356,14 @@ int selinux_xfrm_policy_delete(struct xfrm_policy *xp) * LSM hook implementation that allocs and transfers sec_ctx spec to * xfrm_state. */ -int selinux_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *uctx) +int selinux_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *uctx, + struct xfrm_sec_ctx *pol, u32 secid) { int err; BUG_ON(!x); - err = selinux_xfrm_sec_ctx_alloc(&x->security, uctx); + err = selinux_xfrm_sec_ctx_alloc(&x->security, uctx, pol, secid); return err; } @@ -329,38 +469,30 @@ int selinux_xfrm_state_delete(struct xfrm_state *x) * we need to check for unlabelled access since this may not have * gone thru the IPSec process. */ -int selinux_xfrm_sock_rcv_skb(u32 isec_sid, struct sk_buff *skb) +int selinux_xfrm_sock_rcv_skb(u32 isec_sid, struct sk_buff *skb, + struct avc_audit_data *ad) { int i, rc = 0; struct sec_path *sp; + u32 sel_sid = SECINITSID_UNLABELED; sp = skb->sp; if (sp) { - /* - * __xfrm_policy_check does not approve unless xfrm_policy_ok - * says that spi's match for policy and the socket. - * - * Only need to verify the existence of an authorizable sp. - */ for (i = 0; i < sp->len; i++) { struct xfrm_state *x = sp->xvec[i]; - if (x && selinux_authorizable_xfrm(x)) - goto accept; + if (x && selinux_authorizable_xfrm(x)) { + struct xfrm_sec_ctx *ctx = x->security; + sel_sid = ctx->ctx_sid; + break; + } } } - /* check SELinux sock for unlabelled access */ - rc = avc_has_perm(isec_sid, SECINITSID_UNLABELED, SECCLASS_ASSOCIATION, - ASSOCIATION__RECVFROM, NULL); - if (rc) - goto drop; - -accept: - return 0; + rc = avc_has_perm(isec_sid, sel_sid, SECCLASS_ASSOCIATION, + ASSOCIATION__RECVFROM, ad); -drop: return rc; } @@ -371,7 +503,8 @@ drop: * If we do have a authorizable security association, then it has already been * checked in xfrm_policy_lookup hook. */ -int selinux_xfrm_postroute_last(u32 isec_sid, struct sk_buff *skb) +int selinux_xfrm_postroute_last(u32 isec_sid, struct sk_buff *skb, + struct avc_audit_data *ad) { struct dst_entry *dst; int rc = 0; @@ -391,7 +524,7 @@ int selinux_xfrm_postroute_last(u32 isec_sid, struct sk_buff *skb) } rc = avc_has_perm(isec_sid, SECINITSID_UNLABELED, SECCLASS_ASSOCIATION, - ASSOCIATION__SENDTO, NULL); + ASSOCIATION__SENDTO, ad); out: return rc; } -- cgit v1.2.3-70-g09d2 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 +++++++ include/net/fib_rules.h | 90 ++++++++++ net/Kconfig | 3 + net/core/Makefile | 1 + net/core/fib_rules.c | 416 ++++++++++++++++++++++++++++++++++++++++++++++ net/core/rtnetlink.c | 9 +- 6 files changed, 577 insertions(+), 2 deletions(-) create mode 100644 include/linux/fib_rules.h create mode 100644 include/net/fib_rules.h create mode 100644 net/core/fib_rules.c (limited to 'net/core') diff --git a/include/linux/fib_rules.h b/include/linux/fib_rules.h new file mode 100644 index 00000000000..5e503f0ca6e --- /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 diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h new file mode 100644 index 00000000000..61375d9e53f --- /dev/null +++ b/include/net/fib_rules.h @@ -0,0 +1,90 @@ +#ifndef __NET_FIB_RULES_H +#define __NET_FIB_RULES_H + +#include +#include +#include +#include +#include + +struct fib_rule +{ + struct list_head list; + atomic_t refcnt; + int ifindex; + char ifname[IFNAMSIZ]; + u32 pref; + u32 flags; + u32 table; + u8 action; + struct rcu_head rcu; +}; + +struct fib_lookup_arg +{ + void *lookup_ptr; + void *result; + struct fib_rule *rule; +}; + +struct fib_rules_ops +{ + int family; + struct list_head list; + int rule_size; + + int (*action)(struct fib_rule *, + struct flowi *, int, + struct fib_lookup_arg *); + int (*match)(struct fib_rule *, + struct flowi *, int); + int (*configure)(struct fib_rule *, + struct sk_buff *, + struct nlmsghdr *, + struct fib_rule_hdr *, + struct nlattr **); + int (*compare)(struct fib_rule *, + struct fib_rule_hdr *, + struct nlattr **); + int (*fill)(struct fib_rule *, struct sk_buff *, + struct nlmsghdr *, + struct fib_rule_hdr *); + u32 (*default_pref)(void); + + int nlgroup; + struct nla_policy *policy; + struct list_head *rules_list; + struct module *owner; +}; + +static inline void fib_rule_get(struct fib_rule *rule) +{ + atomic_inc(&rule->refcnt); +} + +static inline void fib_rule_put_rcu(struct rcu_head *head) +{ + struct fib_rule *rule = container_of(head, struct fib_rule, rcu); + kfree(rule); +} + +static inline void fib_rule_put(struct fib_rule *rule) +{ + if (atomic_dec_and_test(&rule->refcnt)) + call_rcu(&rule->rcu, fib_rule_put_rcu); +} + +extern int fib_rules_register(struct fib_rules_ops *); +extern int fib_rules_unregister(struct fib_rules_ops *); + +extern int fib_rules_lookup(struct fib_rules_ops *, + struct flowi *, int flags, + struct fib_lookup_arg *); + +extern int fib_nl_newrule(struct sk_buff *, + struct nlmsghdr *, void *); +extern int fib_nl_delrule(struct sk_buff *, + struct nlmsghdr *, void *); +extern int fib_rules_dump(struct sk_buff *, + struct netlink_callback *, int); +#endif diff --git a/net/Kconfig b/net/Kconfig index eb855b7fa64..6528a935622 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -251,6 +251,9 @@ config WIRELESS_EXT source "net/netlabel/Kconfig" +config FIB_RULES + bool + endif # if NET endmenu # Networking diff --git a/net/core/Makefile b/net/core/Makefile index 2645ba428d4..119568077da 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -17,3 +17,4 @@ obj-$(CONFIG_NET_PKTGEN) += pktgen.o obj-$(CONFIG_WIRELESS_EXT) += wireless.o obj-$(CONFIG_NETPOLL) += netpoll.o obj-$(CONFIG_NET_DMA) += user_dma.o +obj-$(CONFIG_FIB_RULES) += fib_rules.o diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c new file mode 100644 index 00000000000..6cdad24038e --- /dev/null +++ b/net/core/fib_rules.c @@ -0,0 +1,416 @@ +/* + * net/core/fib_rules.c Generic Routing Rules + * + * 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, version 2. + * + * Authors: Thomas Graf + */ + +#include +#include +#include +#include +#include + +static LIST_HEAD(rules_ops); +static DEFINE_SPINLOCK(rules_mod_lock); + +static void notify_rule_change(int event, struct fib_rule *rule, + struct fib_rules_ops *ops); + +static struct fib_rules_ops *lookup_rules_ops(int family) +{ + struct fib_rules_ops *ops; + + rcu_read_lock(); + list_for_each_entry_rcu(ops, &rules_ops, list) { + if (ops->family == family) { + if (!try_module_get(ops->owner)) + ops = NULL; + rcu_read_unlock(); + return ops; + } + } + rcu_read_unlock(); + + return NULL; +} + +static void rules_ops_put(struct fib_rules_ops *ops) +{ + if (ops) + module_put(ops->owner); +} + +int fib_rules_register(struct fib_rules_ops *ops) +{ + int err = -EEXIST; + struct fib_rules_ops *o; + + if (ops->rule_size < sizeof(struct fib_rule)) + return -EINVAL; + + if (ops->match == NULL || ops->configure == NULL || + ops->compare == NULL || ops->fill == NULL || + ops->action == NULL) + return -EINVAL; + + spin_lock(&rules_mod_lock); + list_for_each_entry(o, &rules_ops, list) + if (ops->family == o->family) + goto errout; + + list_add_tail_rcu(&ops->list, &rules_ops); + err = 0; +errout: + spin_unlock(&rules_mod_lock); + + return err; +} + +EXPORT_SYMBOL_GPL(fib_rules_register); + +static void cleanup_ops(struct fib_rules_ops *ops) +{ + struct fib_rule *rule, *tmp; + + list_for_each_entry_safe(rule, tmp, ops->rules_list, list) { + list_del_rcu(&rule->list); + fib_rule_put(rule); + } +} + +int fib_rules_unregister(struct fib_rules_ops *ops) +{ + int err = 0; + struct fib_rules_ops *o; + + spin_lock(&rules_mod_lock); + list_for_each_entry(o, &rules_ops, list) { + if (o == ops) { + list_del_rcu(&o->list); + cleanup_ops(ops); + goto out; + } + } + + err = -ENOENT; +out: + spin_unlock(&rules_mod_lock); + + synchronize_rcu(); + + return err; +} + +EXPORT_SYMBOL_GPL(fib_rules_unregister); + +int fib_rules_lookup(struct fib_rules_ops *ops, struct flowi *fl, + int flags, struct fib_lookup_arg *arg) +{ + struct fib_rule *rule; + int err; + + rcu_read_lock(); + + list_for_each_entry_rcu(rule, ops->rules_list, list) { + if (rule->ifindex && (rule->ifindex != fl->iif)) + continue; + + if (!ops->match(rule, fl, flags)) + continue; + + err = ops->action(rule, fl, flags, arg); + if (err != -EAGAIN) { + fib_rule_get(rule); + arg->rule = rule; + goto out; + } + } + + err = -ENETUNREACH; +out: + rcu_read_unlock(); + + return err; +} + +EXPORT_SYMBOL_GPL(fib_rules_lookup); + +int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +{ + struct fib_rule_hdr *frh = nlmsg_data(nlh); + struct fib_rules_ops *ops = NULL; + struct fib_rule *rule, *r, *last = NULL; + struct nlattr *tb[FRA_MAX+1]; + int err = -EINVAL; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) + goto errout; + + ops = lookup_rules_ops(frh->family); + if (ops == NULL) { + err = EAFNOSUPPORT; + goto errout; + } + + err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy); + if (err < 0) + goto errout; + + if (tb[FRA_IFNAME] && nla_len(tb[FRA_IFNAME]) > IFNAMSIZ) + goto errout; + + rule = kzalloc(ops->rule_size, GFP_KERNEL); + if (rule == NULL) { + err = -ENOMEM; + goto errout; + } + + if (tb[FRA_PRIORITY]) + rule->pref = nla_get_u32(tb[FRA_PRIORITY]); + + if (tb[FRA_IFNAME]) { + struct net_device *dev; + + rule->ifindex = -1; + if (nla_strlcpy(rule->ifname, tb[FRA_IFNAME], + IFNAMSIZ) >= IFNAMSIZ) + goto errout_free; + + dev = __dev_get_by_name(rule->ifname); + if (dev) + rule->ifindex = dev->ifindex; + } + + rule->action = frh->action; + rule->flags = frh->flags; + rule->table = frh->table; + + if (!rule->pref && ops->default_pref) + rule->pref = ops->default_pref(); + + err = ops->configure(rule, skb, nlh, frh, tb); + if (err < 0) + goto errout_free; + + list_for_each_entry(r, ops->rules_list, list) { + if (r->pref > rule->pref) + break; + last = r; + } + + fib_rule_get(rule); + + if (last) + list_add_rcu(&rule->list, &last->list); + else + list_add_rcu(&rule->list, ops->rules_list); + + notify_rule_change(RTM_NEWRULE, rule, ops); + rules_ops_put(ops); + return 0; + +errout_free: + kfree(rule); +errout: + rules_ops_put(ops); + return err; +} + +int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +{ + struct fib_rule_hdr *frh = nlmsg_data(nlh); + struct fib_rules_ops *ops = NULL; + struct fib_rule *rule; + struct nlattr *tb[FRA_MAX+1]; + int err = -EINVAL; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) + goto errout; + + ops = lookup_rules_ops(frh->family); + if (ops == NULL) { + err = EAFNOSUPPORT; + goto errout; + } + + err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy); + if (err < 0) + goto errout; + + list_for_each_entry(rule, ops->rules_list, list) { + if (frh->action && (frh->action != rule->action)) + continue; + + if (frh->table && (frh->table != rule->table)) + continue; + + if (tb[FRA_PRIORITY] && + (rule->pref != nla_get_u32(tb[FRA_PRIORITY]))) + continue; + + if (tb[FRA_IFNAME] && + nla_strcmp(tb[FRA_IFNAME], rule->ifname)) + continue; + + if (!ops->compare(rule, frh, tb)) + continue; + + if (rule->flags & FIB_RULE_PERMANENT) { + err = -EPERM; + goto errout; + } + + list_del_rcu(&rule->list); + synchronize_rcu(); + notify_rule_change(RTM_DELRULE, rule, ops); + fib_rule_put(rule); + rules_ops_put(ops); + return 0; + } + + err = -ENOENT; +errout: + rules_ops_put(ops); + return err; +} + +static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, + u32 pid, u32 seq, int type, int flags, + struct fib_rules_ops *ops) +{ + struct nlmsghdr *nlh; + struct fib_rule_hdr *frh; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*frh), flags); + if (nlh == NULL) + return -1; + + frh = nlmsg_data(nlh); + frh->table = rule->table; + frh->res1 = 0; + frh->res2 = 0; + frh->action = rule->action; + frh->flags = rule->flags; + + if (rule->ifname[0]) + NLA_PUT_STRING(skb, FRA_IFNAME, rule->ifname); + + if (rule->pref) + NLA_PUT_U32(skb, FRA_PRIORITY, rule->pref); + + if (ops->fill(rule, skb, nlh, frh) < 0) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + return nlmsg_cancel(skb, nlh); +} + +int fib_rules_dump(struct sk_buff *skb, struct netlink_callback *cb, int family) +{ + int idx = 0; + struct fib_rule *rule; + struct fib_rules_ops *ops; + + ops = lookup_rules_ops(family); + if (ops == NULL) + return -EAFNOSUPPORT; + + rcu_read_lock(); + list_for_each_entry(rule, ops->rules_list, list) { + if (idx < cb->args[0]) + goto skip; + + if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, RTM_NEWRULE, + NLM_F_MULTI, ops) < 0) + break; +skip: + idx++; + } + rcu_read_unlock(); + cb->args[0] = idx; + rules_ops_put(ops); + + return skb->len; +} + +EXPORT_SYMBOL_GPL(fib_rules_dump); + +static void notify_rule_change(int event, struct fib_rule *rule, + struct fib_rules_ops *ops) +{ + int size = nlmsg_total_size(sizeof(struct fib_rule_hdr) + 128); + struct sk_buff *skb = alloc_skb(size, GFP_KERNEL); + + if (skb == NULL) + netlink_set_err(rtnl, 0, ops->nlgroup, ENOBUFS); + else if (fib_nl_fill_rule(skb, rule, 0, 0, event, 0, ops) < 0) { + kfree_skb(skb); + netlink_set_err(rtnl, 0, ops->nlgroup, EINVAL); + } else + netlink_broadcast(rtnl, skb, 0, ops->nlgroup, GFP_KERNEL); +} + +static void attach_rules(struct list_head *rules, struct net_device *dev) +{ + struct fib_rule *rule; + + list_for_each_entry(rule, rules, list) { + if (rule->ifindex == -1 && + strcmp(dev->name, rule->ifname) == 0) + rule->ifindex = dev->ifindex; + } +} + +static void detach_rules(struct list_head *rules, struct net_device *dev) +{ + struct fib_rule *rule; + + list_for_each_entry(rule, rules, list) + if (rule->ifindex == dev->ifindex) + rule->ifindex = -1; +} + + +static int fib_rules_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct net_device *dev = ptr; + struct fib_rules_ops *ops; + + ASSERT_RTNL(); + rcu_read_lock(); + + switch (event) { + case NETDEV_REGISTER: + list_for_each_entry(ops, &rules_ops, list) + attach_rules(ops->rules_list, dev); + break; + + case NETDEV_UNREGISTER: + list_for_each_entry(ops, &rules_ops, list) + detach_rules(ops->rules_list, dev); + break; + } + + rcu_read_unlock(); + + return NOTIFY_DONE; +} + +static struct notifier_block fib_rules_notifier = { + .notifier_call = fib_rules_event, +}; + +static int __init fib_rules_init(void) +{ + return register_netdevice_notifier(&fib_rules_notifier); +} + +subsys_initcall(fib_rules_init); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 30cc1ba6ed5..aa7cff2257b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -49,6 +49,7 @@ #include #include #include +#include #include #ifdef CONFIG_NET_WIRELESS_RTNETLINK #include @@ -103,7 +104,7 @@ static const int rtm_min[RTM_NR_FAMILIES] = [RTM_FAM(RTM_NEWADDR)] = NLMSG_LENGTH(sizeof(struct ifaddrmsg)), [RTM_FAM(RTM_NEWROUTE)] = NLMSG_LENGTH(sizeof(struct rtmsg)), [RTM_FAM(RTM_NEWNEIGH)] = NLMSG_LENGTH(sizeof(struct ndmsg)), - [RTM_FAM(RTM_NEWRULE)] = NLMSG_LENGTH(sizeof(struct rtmsg)), + [RTM_FAM(RTM_NEWRULE)] = NLMSG_LENGTH(sizeof(struct fib_rule_hdr)), [RTM_FAM(RTM_NEWQDISC)] = NLMSG_LENGTH(sizeof(struct tcmsg)), [RTM_FAM(RTM_NEWTCLASS)] = NLMSG_LENGTH(sizeof(struct tcmsg)), [RTM_FAM(RTM_NEWTFILTER)] = NLMSG_LENGTH(sizeof(struct tcmsg)), @@ -120,7 +121,7 @@ static const int rta_max[RTM_NR_FAMILIES] = [RTM_FAM(RTM_NEWADDR)] = IFA_MAX, [RTM_FAM(RTM_NEWROUTE)] = RTA_MAX, [RTM_FAM(RTM_NEWNEIGH)] = NDA_MAX, - [RTM_FAM(RTM_NEWRULE)] = RTA_MAX, + [RTM_FAM(RTM_NEWRULE)] = FRA_MAX, [RTM_FAM(RTM_NEWQDISC)] = TCA_MAX, [RTM_FAM(RTM_NEWTCLASS)] = TCA_MAX, [RTM_FAM(RTM_NEWTFILTER)] = TCA_MAX, @@ -757,6 +758,10 @@ static struct rtnetlink_link link_rtnetlink_table[RTM_NR_MSGTYPES] = [RTM_NEWNEIGH - RTM_BASE] = { .doit = neigh_add }, [RTM_DELNEIGH - RTM_BASE] = { .doit = neigh_delete }, [RTM_GETNEIGH - RTM_BASE] = { .dumpit = neigh_dump_info }, +#ifdef CONFIG_FIB_RULES + [RTM_NEWRULE - RTM_BASE] = { .doit = fib_nl_newrule }, + [RTM_DELRULE - RTM_BASE] = { .doit = fib_nl_delrule }, +#endif [RTM_GETRULE - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, [RTM_GETNEIGHTBL - RTM_BASE] = { .dumpit = neightbl_dump_info }, [RTM_SETNEIGHTBL - RTM_BASE] = { .doit = neightbl_set }, -- cgit v1.2.3-70-g09d2 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 ----------------------------------------------- net/core/rtnetlink.c | 1 + net/decnet/dn_dev.c | 1 + net/ipv4/devinet.c | 1 + net/ipv4/fib_frontend.c | 1 + net/ipv6/addrconf.c | 1 + net/ipv6/ndisc.c | 1 + 8 files changed, 59 insertions(+), 56 deletions(-) create mode 100644 include/linux/if_addr.h (limited to 'net/core') diff --git a/include/linux/if_addr.h b/include/linux/if_addr.h new file mode 100644 index 00000000000..e1590454db5 --- /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 bf353538ae9..890c4d4038b 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. diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index aa7cff2257b..35712031e2c 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 476455fbdb0..632c5a90b58 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 80bf5b2ea2e..398e7b9ca66 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index fe4a53d4d10..a83f1aa8034 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ed766eebc02..c2a4db843e5 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -48,6 +48,7 @@ #include #include #include +#include #include #include #include diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 67cfc3813c3..5743e8bffef 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -62,6 +62,7 @@ #include #endif +#include #include #include #include -- cgit v1.2.3-70-g09d2 From da5e0494c542dddc56a1f1edfd30310ea30f41ff Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Thu, 10 Aug 2006 21:17:37 -0700 Subject: [NET]: Convert link modification to new netlink api Transforms do_setlink() into rtnl_setlink() using the new netlink api. A warning message printed to the console is added in the event that a change request fails while part of the change request has been comitted already. The ioctl() based nature of net devices makes it almost impossible to move on to atomic netlink operations without obsoleting some of the functionality. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 191 +++++++++++++++++++++++++++------------------------ 1 file changed, 100 insertions(+), 91 deletions(-) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 35712031e2c..2adc966d981 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -336,52 +336,69 @@ static int rtnetlink_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *c return skb->len; } -static int do_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static struct nla_policy ifla_policy[IFLA_MAX+1] __read_mostly = { + [IFLA_IFNAME] = { .type = NLA_STRING }, + [IFLA_MAP] = { .minlen = sizeof(struct rtnl_link_ifmap) }, + [IFLA_MTU] = { .type = NLA_U32 }, + [IFLA_TXQLEN] = { .type = NLA_U32 }, + [IFLA_WEIGHT] = { .type = NLA_U32 }, + [IFLA_OPERSTATE] = { .type = NLA_U8 }, + [IFLA_LINKMODE] = { .type = NLA_U8 }, +}; + +static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct ifinfomsg *ifm = NLMSG_DATA(nlh); - struct rtattr **ida = arg; + struct ifinfomsg *ifm; struct net_device *dev; - int err, send_addr_notify = 0; + int err, send_addr_notify = 0, modified = 0; + struct nlattr *tb[IFLA_MAX+1]; + char ifname[IFNAMSIZ]; + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); + if (err < 0) + goto errout; + + if (tb[IFLA_IFNAME] && + nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ) >= IFNAMSIZ) + return -EINVAL; + + err = -EINVAL; + ifm = nlmsg_data(nlh); if (ifm->ifi_index >= 0) dev = dev_get_by_index(ifm->ifi_index); - else if (ida[IFLA_IFNAME - 1]) { - char ifname[IFNAMSIZ]; - - if (rtattr_strlcpy(ifname, ida[IFLA_IFNAME - 1], - IFNAMSIZ) >= IFNAMSIZ) - return -EINVAL; + else if (tb[IFLA_IFNAME]) dev = dev_get_by_name(ifname); - } else - return -EINVAL; + else + goto errout; - if (!dev) - return -ENODEV; + if (dev == NULL) { + err = -ENODEV; + goto errout; + } - err = -EINVAL; + if (tb[IFLA_ADDRESS] && + nla_len(tb[IFLA_ADDRESS]) < dev->addr_len) + goto errout_dev; - if (ifm->ifi_flags) - dev_change_flags(dev, ifm->ifi_flags); + if (tb[IFLA_BROADCAST] && + nla_len(tb[IFLA_BROADCAST]) < dev->addr_len) + goto errout_dev; - if (ida[IFLA_MAP - 1]) { + if (tb[IFLA_MAP]) { struct rtnl_link_ifmap *u_map; struct ifmap k_map; if (!dev->set_config) { err = -EOPNOTSUPP; - goto out; + goto errout_dev; } if (!netif_device_present(dev)) { err = -ENODEV; - goto out; + goto errout_dev; } - - if (ida[IFLA_MAP - 1]->rta_len != RTA_LENGTH(sizeof(*u_map))) - goto out; - - u_map = RTA_DATA(ida[IFLA_MAP - 1]); + u_map = nla_data(tb[IFLA_MAP]); k_map.mem_start = (unsigned long) u_map->mem_start; k_map.mem_end = (unsigned long) u_map->mem_end; k_map.base_addr = (unsigned short) u_map->base_addr; @@ -390,119 +407,111 @@ static int do_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) k_map.port = (unsigned char) u_map->port; err = dev->set_config(dev, &k_map); + if (err < 0) + goto errout_dev; - if (err) - goto out; + modified = 1; } - if (ida[IFLA_ADDRESS - 1]) { + if (tb[IFLA_ADDRESS]) { struct sockaddr *sa; int len; if (!dev->set_mac_address) { err = -EOPNOTSUPP; - goto out; + goto errout_dev; } + if (!netif_device_present(dev)) { err = -ENODEV; - goto out; + goto errout_dev; } - if (ida[IFLA_ADDRESS - 1]->rta_len != RTA_LENGTH(dev->addr_len)) - goto out; len = sizeof(sa_family_t) + dev->addr_len; sa = kmalloc(len, GFP_KERNEL); if (!sa) { err = -ENOMEM; - goto out; + goto errout_dev; } sa->sa_family = dev->type; - memcpy(sa->sa_data, RTA_DATA(ida[IFLA_ADDRESS - 1]), + memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]), dev->addr_len); err = dev->set_mac_address(dev, sa); kfree(sa); if (err) - goto out; + goto errout_dev; send_addr_notify = 1; + modified = 1; } - if (ida[IFLA_BROADCAST - 1]) { - if (ida[IFLA_BROADCAST - 1]->rta_len != RTA_LENGTH(dev->addr_len)) - goto out; - memcpy(dev->broadcast, RTA_DATA(ida[IFLA_BROADCAST - 1]), - dev->addr_len); - send_addr_notify = 1; + if (tb[IFLA_MTU]) { + err = dev_set_mtu(dev, nla_get_u32(tb[IFLA_MTU])); + if (err < 0) + goto errout_dev; + modified = 1; } - if (ida[IFLA_MTU - 1]) { - if (ida[IFLA_MTU - 1]->rta_len != RTA_LENGTH(sizeof(u32))) - goto out; - err = dev_set_mtu(dev, *((u32 *) RTA_DATA(ida[IFLA_MTU - 1]))); - - if (err) - goto out; - + /* + * Interface selected by interface index but interface + * name provided implies that a name change has been + * requested. + */ + if (ifm->ifi_index >= 0 && ifname[0]) { + err = dev_change_name(dev, ifname); + if (err < 0) + goto errout_dev; + modified = 1; } - if (ida[IFLA_TXQLEN - 1]) { - if (ida[IFLA_TXQLEN - 1]->rta_len != RTA_LENGTH(sizeof(u32))) - goto out; +#ifdef CONFIG_NET_WIRELESS_RTNETLINK + if (tb[IFLA_WIRELESS]) { + /* Call Wireless Extensions. + * Various stuff checked in there... */ + err = wireless_rtnetlink_set(dev, nla_data(tb[IFLA_WIRELESS]), + nla_len(tb[IFLA_WIRELESS])); + if (err < 0) + goto errout_dev; + } +#endif /* CONFIG_NET_WIRELESS_RTNETLINK */ - dev->tx_queue_len = *((u32 *) RTA_DATA(ida[IFLA_TXQLEN - 1])); + if (tb[IFLA_BROADCAST]) { + nla_memcpy(dev->broadcast, tb[IFLA_BROADCAST], dev->addr_len); + send_addr_notify = 1; } - if (ida[IFLA_WEIGHT - 1]) { - if (ida[IFLA_WEIGHT - 1]->rta_len != RTA_LENGTH(sizeof(u32))) - goto out; - dev->weight = *((u32 *) RTA_DATA(ida[IFLA_WEIGHT - 1])); - } + if (ifm->ifi_flags) + dev_change_flags(dev, ifm->ifi_flags); - if (ida[IFLA_OPERSTATE - 1]) { - if (ida[IFLA_OPERSTATE - 1]->rta_len != RTA_LENGTH(sizeof(u8))) - goto out; + if (tb[IFLA_TXQLEN]) + dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]); - set_operstate(dev, *((u8 *) RTA_DATA(ida[IFLA_OPERSTATE - 1]))); - } + if (tb[IFLA_WEIGHT]) + dev->weight = nla_get_u32(tb[IFLA_WEIGHT]); - if (ida[IFLA_LINKMODE - 1]) { - if (ida[IFLA_LINKMODE - 1]->rta_len != RTA_LENGTH(sizeof(u8))) - goto out; + if (tb[IFLA_OPERSTATE]) + set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE])); + if (tb[IFLA_LINKMODE]) { write_lock_bh(&dev_base_lock); - dev->link_mode = *((u8 *) RTA_DATA(ida[IFLA_LINKMODE - 1])); + dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]); write_unlock_bh(&dev_base_lock); } - if (ifm->ifi_index >= 0 && ida[IFLA_IFNAME - 1]) { - char ifname[IFNAMSIZ]; - - if (rtattr_strlcpy(ifname, ida[IFLA_IFNAME - 1], - IFNAMSIZ) >= IFNAMSIZ) - goto out; - err = dev_change_name(dev, ifname); - if (err) - goto out; - } - -#ifdef CONFIG_NET_WIRELESS_RTNETLINK - if (ida[IFLA_WIRELESS - 1]) { - - /* Call Wireless Extensions. - * Various stuff checked in there... */ - err = wireless_rtnetlink_set(dev, RTA_DATA(ida[IFLA_WIRELESS - 1]), ida[IFLA_WIRELESS - 1]->rta_len); - if (err) - goto out; - } -#endif /* CONFIG_NET_WIRELESS_RTNETLINK */ - err = 0; -out: +errout_dev: + if (err < 0 && modified && net_ratelimit()) + printk(KERN_WARNING "A link change request failed with " + "some changes comitted already. Interface %s may " + "have been left with an inconsistent configuration, " + "please check.\n", dev->name); + if (send_addr_notify) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); dev_put(dev); +errout: return err; } @@ -753,7 +762,7 @@ static struct rtnetlink_link link_rtnetlink_table[RTM_NR_MSGTYPES] = .doit = do_getlink, #endif /* CONFIG_NET_WIRELESS_RTNETLINK */ .dumpit = rtnetlink_dump_ifinfo }, - [RTM_SETLINK - RTM_BASE] = { .doit = do_setlink }, + [RTM_SETLINK - RTM_BASE] = { .doit = rtnl_setlink }, [RTM_GETADDR - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, [RTM_GETROUTE - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, [RTM_NEWNEIGH - RTM_BASE] = { .doit = neigh_add }, -- cgit v1.2.3-70-g09d2 From b60c5115f4abf0b961a18682889798dcfbe6a801 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 4 Aug 2006 23:05:34 -0700 Subject: [NET]: Convert link dumping to new netlink api Transforms netlink code to dump link tables to use the new netlink api. Makes rtnl_getlink() available regardless of the availability of the wireless extensions. Adding copy_rtnl_link_stats() avoids the structural dependency of struct rtnl_link_stats on struct net_device_stats and thus avoids troubles later on. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 281 +++++++++++++++++++++++++-------------------------- 1 file changed, 137 insertions(+), 144 deletions(-) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2adc966d981..93ba04fb844 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -218,41 +218,73 @@ static void set_operstate(struct net_device *dev, unsigned char transition) } } -static int rtnetlink_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, - int type, u32 pid, u32 seq, u32 change, - unsigned int flags) +static void copy_rtnl_link_stats(struct rtnl_link_stats *a, + struct net_device_stats *b) { - struct ifinfomsg *r; - struct nlmsghdr *nlh; - unsigned char *b = skb->tail; - - nlh = NLMSG_NEW(skb, pid, seq, type, sizeof(*r), flags); - r = NLMSG_DATA(nlh); - r->ifi_family = AF_UNSPEC; - r->__ifi_pad = 0; - r->ifi_type = dev->type; - r->ifi_index = dev->ifindex; - r->ifi_flags = dev_get_flags(dev); - r->ifi_change = change; + a->rx_packets = b->rx_packets; + a->tx_packets = b->tx_packets; + a->rx_bytes = b->rx_bytes; + a->tx_bytes = b->tx_bytes; + a->rx_errors = b->rx_errors; + a->tx_errors = b->tx_errors; + a->rx_dropped = b->rx_dropped; + a->tx_dropped = b->tx_dropped; + + a->multicast = b->multicast; + a->collisions = b->collisions; + + a->rx_length_errors = b->rx_length_errors; + a->rx_over_errors = b->rx_over_errors; + a->rx_crc_errors = b->rx_crc_errors; + a->rx_frame_errors = b->rx_frame_errors; + a->rx_fifo_errors = b->rx_fifo_errors; + a->rx_missed_errors = b->rx_missed_errors; + + a->tx_aborted_errors = b->tx_aborted_errors; + a->tx_carrier_errors = b->tx_carrier_errors; + a->tx_fifo_errors = b->tx_fifo_errors; + a->tx_heartbeat_errors = b->tx_heartbeat_errors; + a->tx_window_errors = b->tx_window_errors; + + a->rx_compressed = b->rx_compressed; + a->tx_compressed = b->tx_compressed; +}; - RTA_PUT(skb, IFLA_IFNAME, strlen(dev->name)+1, dev->name); +static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, + void *iwbuf, int iwbuflen, int type, u32 pid, + u32 seq, u32 change, unsigned int flags) +{ + struct ifinfomsg *ifm; + struct nlmsghdr *nlh; - if (1) { - u32 txqlen = dev->tx_queue_len; - RTA_PUT(skb, IFLA_TXQLEN, sizeof(txqlen), &txqlen); - } + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); + if (nlh == NULL) + return -ENOBUFS; - if (1) { - u32 weight = dev->weight; - RTA_PUT(skb, IFLA_WEIGHT, sizeof(weight), &weight); - } + ifm = nlmsg_data(nlh); + ifm->ifi_family = AF_UNSPEC; + ifm->__ifi_pad = 0; + ifm->ifi_type = dev->type; + ifm->ifi_index = dev->ifindex; + ifm->ifi_flags = dev_get_flags(dev); + ifm->ifi_change = change; + + NLA_PUT_STRING(skb, IFLA_IFNAME, dev->name); + NLA_PUT_U32(skb, IFLA_TXQLEN, dev->tx_queue_len); + NLA_PUT_U32(skb, IFLA_WEIGHT, dev->weight); + NLA_PUT_U8(skb, IFLA_OPERSTATE, + netif_running(dev) ? dev->operstate : IF_OPER_DOWN); + NLA_PUT_U8(skb, IFLA_LINKMODE, dev->link_mode); + NLA_PUT_U32(skb, IFLA_MTU, dev->mtu); + + if (dev->ifindex != dev->iflink) + NLA_PUT_U32(skb, IFLA_LINK, dev->iflink); + + if (dev->master) + NLA_PUT_U32(skb, IFLA_MASTER, dev->master->ifindex); - if (1) { - u8 operstate = netif_running(dev)?dev->operstate:IF_OPER_DOWN; - u8 link_mode = dev->link_mode; - RTA_PUT(skb, IFLA_OPERSTATE, sizeof(operstate), &operstate); - RTA_PUT(skb, IFLA_LINKMODE, sizeof(link_mode), &link_mode); - } + if (dev->qdisc_sleeping) + NLA_PUT_STRING(skb, IFLA_QDISC, dev->qdisc_sleeping->ops->id); if (1) { struct rtnl_link_ifmap map = { @@ -263,58 +295,38 @@ static int rtnetlink_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, .dma = dev->dma, .port = dev->if_port, }; - RTA_PUT(skb, IFLA_MAP, sizeof(map), &map); + NLA_PUT(skb, IFLA_MAP, sizeof(map), &map); } if (dev->addr_len) { - RTA_PUT(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr); - RTA_PUT(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast); - } - - if (1) { - u32 mtu = dev->mtu; - RTA_PUT(skb, IFLA_MTU, sizeof(mtu), &mtu); - } - - if (dev->ifindex != dev->iflink) { - u32 iflink = dev->iflink; - RTA_PUT(skb, IFLA_LINK, sizeof(iflink), &iflink); - } - - if (dev->qdisc_sleeping) - RTA_PUT(skb, IFLA_QDISC, - strlen(dev->qdisc_sleeping->ops->id) + 1, - dev->qdisc_sleeping->ops->id); - - if (dev->master) { - u32 master = dev->master->ifindex; - RTA_PUT(skb, IFLA_MASTER, sizeof(master), &master); + NLA_PUT(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr); + NLA_PUT(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast); } if (dev->get_stats) { - unsigned long *stats = (unsigned long*)dev->get_stats(dev); + struct net_device_stats *stats = dev->get_stats(dev); if (stats) { - struct rtattr *a; - __u32 *s; - int i; - int n = sizeof(struct rtnl_link_stats)/4; - - a = __RTA_PUT(skb, IFLA_STATS, n*4); - s = RTA_DATA(a); - for (i=0; inlmsg_len = skb->tail - b; - return skb->len; -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; + if (iwbuf) + NLA_PUT(skb, IFLA_WIRELESS, iwbuflen, iwbuf); + + return nlmsg_end(skb, nlh); + +nla_put_failure: + return nlmsg_cancel(skb, nlh); } -static int rtnetlink_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) +static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { int idx; int s_idx = cb->args[0]; @@ -324,10 +336,9 @@ static int rtnetlink_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *c for (dev=dev_base, idx=0; dev; dev = dev->next, idx++) { if (idx < s_idx) continue; - if (rtnetlink_fill_ifinfo(skb, dev, RTM_NEWLINK, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, 0, - NLM_F_MULTI) <= 0) + if (rtnl_fill_ifinfo(skb, dev, NULL, 0, RTM_NEWLINK, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, 0, NLM_F_MULTI) <= 0) break; } read_unlock(&dev_base_lock); @@ -515,84 +526,69 @@ errout: return err; } -#ifdef CONFIG_NET_WIRELESS_RTNETLINK -static int do_getlink(struct sk_buff *in_skb, struct nlmsghdr* in_nlh, void *arg) +static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { - struct ifinfomsg *ifm = NLMSG_DATA(in_nlh); - struct rtattr **ida = arg; - struct net_device *dev; - struct ifinfomsg *r; - struct nlmsghdr *nlh; - int err = -ENOBUFS; - struct sk_buff *skb; - unsigned char *b; - char *iw_buf = NULL; + struct ifinfomsg *ifm; + struct nlattr *tb[IFLA_MAX+1]; + struct net_device *dev = NULL; + struct sk_buff *nskb; + char *iw_buf = NULL, *iw = NULL; int iw_buf_len = 0; + int err, payload; - if (ifm->ifi_index >= 0) + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); + if (err < 0) + goto errout; + + ifm = nlmsg_data(nlh); + if (ifm->ifi_index >= 0) { dev = dev_get_by_index(ifm->ifi_index); - else + if (dev == NULL) + return -ENODEV; + } else return -EINVAL; - if (!dev) - return -ENODEV; -#ifdef CONFIG_NET_WIRELESS_RTNETLINK - if (ida[IFLA_WIRELESS - 1]) { +#ifdef CONFIG_NET_WIRELESS_RTNETLINK + if (tb[IFLA_WIRELESS]) { /* Call Wireless Extensions. We need to know the size before * we can alloc. Various stuff checked in there... */ - err = wireless_rtnetlink_get(dev, RTA_DATA(ida[IFLA_WIRELESS - 1]), ida[IFLA_WIRELESS - 1]->rta_len, &iw_buf, &iw_buf_len); - if (err) - goto out; + err = wireless_rtnetlink_get(dev, nla_data(tb[IFLA_WIRELESS]), + nla_len(tb[IFLA_WIRELESS]), + &iw_buf, &iw_buf_len); + if (err < 0) + goto errout; + + iw += IW_EV_POINT_OFF; } #endif /* CONFIG_NET_WIRELESS_RTNETLINK */ - /* Create a skb big enough to include all the data. - * Some requests are way bigger than 4k... Jean II */ - skb = alloc_skb((NLMSG_LENGTH(sizeof(*r))) + (RTA_SPACE(iw_buf_len)), - GFP_KERNEL); - if (!skb) - goto out; - b = skb->tail; - - /* Put in the message the usual good stuff */ - nlh = NLMSG_PUT(skb, NETLINK_CB(in_skb).pid, in_nlh->nlmsg_seq, - RTM_NEWLINK, sizeof(*r)); - r = NLMSG_DATA(nlh); - r->ifi_family = AF_UNSPEC; - r->__ifi_pad = 0; - r->ifi_type = dev->type; - r->ifi_index = dev->ifindex; - r->ifi_flags = dev->flags; - r->ifi_change = 0; - - /* Put the wireless payload if it exist */ - if(iw_buf != NULL) - RTA_PUT(skb, IFLA_WIRELESS, iw_buf_len, - iw_buf + IW_EV_POINT_OFF); - - nlh->nlmsg_len = skb->tail - b; - - /* Needed ? */ - NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid; - - err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); + payload = NLMSG_ALIGN(sizeof(struct ifinfomsg) + + nla_total_size(iw_buf_len)); + nskb = nlmsg_new(nlmsg_total_size(payload), GFP_KERNEL); + if (nskb == NULL) { + err = -ENOBUFS; + goto errout; + } + + err = rtnl_fill_ifinfo(nskb, dev, iw, iw_buf_len, RTM_NEWLINK, + NETLINK_CB(skb).pid, nlh->nlmsg_seq, 0, 0); + if (err <= 0) { + kfree_skb(skb); + goto errout; + } + + err = netlink_unicast(rtnl, skb, NETLINK_CB(skb).pid, MSG_DONTWAIT); if (err > 0) err = 0; -out: - if(iw_buf != NULL) - kfree(iw_buf); +errout: + kfree(iw_buf); dev_put(dev); - return err; -rtattr_failure: -nlmsg_failure: - kfree_skb(skb); - goto out; + return err; } -#endif /* CONFIG_NET_WIRELESS_RTNETLINK */ -static int rtnetlink_dump_all(struct sk_buff *skb, struct netlink_callback *cb) +static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) { int idx; int s_idx = cb->family; @@ -623,11 +619,11 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change) sizeof(struct rtnl_link_ifmap) + sizeof(struct rtnl_link_stats) + 128); - skb = alloc_skb(size, GFP_KERNEL); + skb = nlmsg_new(size, GFP_KERNEL); if (!skb) return; - if (rtnetlink_fill_ifinfo(skb, dev, type, 0, 0, change, 0) < 0) { + if (rtnl_fill_ifinfo(skb, dev, NULL, 0, type, 0, 0, change, 0) < 0) { kfree_skb(skb); return; } @@ -757,14 +753,11 @@ static void rtnetlink_rcv(struct sock *sk, int len) static struct rtnetlink_link link_rtnetlink_table[RTM_NR_MSGTYPES] = { - [RTM_GETLINK - RTM_BASE] = { -#ifdef CONFIG_NET_WIRELESS_RTNETLINK - .doit = do_getlink, -#endif /* CONFIG_NET_WIRELESS_RTNETLINK */ - .dumpit = rtnetlink_dump_ifinfo }, + [RTM_GETLINK - RTM_BASE] = { .doit = rtnl_getlink, + .dumpit = rtnl_dump_ifinfo }, [RTM_SETLINK - RTM_BASE] = { .doit = rtnl_setlink }, - [RTM_GETADDR - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, - [RTM_GETROUTE - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, + [RTM_GETADDR - RTM_BASE] = { .dumpit = rtnl_dump_all }, + [RTM_GETROUTE - RTM_BASE] = { .dumpit = rtnl_dump_all }, [RTM_NEWNEIGH - RTM_BASE] = { .doit = neigh_add }, [RTM_DELNEIGH - RTM_BASE] = { .doit = neigh_delete }, [RTM_GETNEIGH - RTM_BASE] = { .dumpit = neigh_dump_info }, @@ -772,7 +765,7 @@ static struct rtnetlink_link link_rtnetlink_table[RTM_NR_MSGTYPES] = [RTM_NEWRULE - RTM_BASE] = { .doit = fib_nl_newrule }, [RTM_DELRULE - RTM_BASE] = { .doit = fib_nl_delrule }, #endif - [RTM_GETRULE - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, + [RTM_GETRULE - RTM_BASE] = { .dumpit = rtnl_dump_all }, [RTM_GETNEIGHTBL - RTM_BASE] = { .dumpit = neightbl_dump_info }, [RTM_SETNEIGHTBL - RTM_BASE] = { .doit = neightbl_set }, }; -- cgit v1.2.3-70-g09d2 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 --- drivers/atm/he.c | 2 +- drivers/net/3c59x.c | 2 +- drivers/net/8139cp.c | 6 +++--- drivers/net/acenic.c | 8 ++++---- drivers/net/bnx2.c | 2 +- drivers/net/cassini.c | 4 ++-- drivers/net/chelsio/sge.c | 10 +++++----- drivers/net/dl2k.c | 2 +- drivers/net/e1000/e1000_main.c | 8 ++++---- drivers/net/forcedeth.c | 3 ++- drivers/net/gianfar.c | 2 +- drivers/net/hamachi.c | 2 +- drivers/net/ibm_emac/ibm_emac_core.c | 2 +- drivers/net/ioc3-eth.c | 2 +- drivers/net/ixgb/ixgb_main.c | 2 +- drivers/net/mv643xx_eth.c | 2 +- drivers/net/myri10ge/myri10ge.c | 8 ++++---- drivers/net/ns83820.c | 2 +- drivers/net/r8169.c | 2 +- drivers/net/s2io.c | 2 +- drivers/net/sk98lin/skge.c | 6 +++--- drivers/net/skge.c | 4 ++-- drivers/net/sky2.c | 6 +++--- drivers/net/starfire.c | 6 +++--- drivers/net/sungem.c | 4 ++-- drivers/net/sunhme.c | 6 +++--- drivers/net/tg3.c | 6 +++--- drivers/net/typhoon.c | 2 +- drivers/net/via-rhine.c | 2 +- drivers/net/via-velocity.c | 2 +- include/linux/netdevice.h | 4 ++-- include/linux/skbuff.h | 17 +++++++++-------- net/core/datagram.c | 4 ++-- net/core/dev.c | 12 ++++++------ net/core/netpoll.c | 2 +- net/core/skbuff.c | 14 +++++++------- net/ipv4/icmp.c | 2 +- net/ipv4/igmp.c | 2 +- net/ipv4/ip_fragment.c | 2 +- net/ipv4/ip_gre.c | 4 ++-- net/ipv4/ip_output.c | 6 +++--- net/ipv4/ipvs/ip_vs_proto_tcp.c | 8 ++++---- net/ipv4/ipvs/ip_vs_proto_udp.c | 8 ++++---- net/ipv4/netfilter.c | 2 +- net/ipv4/netfilter/ip_conntrack_proto_tcp.c | 3 +-- net/ipv4/netfilter/ip_conntrack_proto_udp.c | 3 +-- net/ipv4/netfilter/ip_nat_standalone.c | 5 +++-- net/ipv4/netfilter/ip_queue.c | 6 +++--- net/ipv4/netfilter/ipt_ECN.c | 9 +++++---- net/ipv4/netfilter/ipt_TCPMSS.c | 5 +++-- net/ipv4/tcp.c | 8 ++++---- net/ipv4/tcp_ipv4.c | 6 +++--- net/ipv4/tcp_output.c | 18 ++++++++---------- net/ipv4/udp.c | 6 +++--- net/ipv4/xfrm4_output.c | 4 ++-- net/ipv6/exthdrs.c | 2 +- net/ipv6/icmp.c | 2 +- net/ipv6/ip6_output.c | 2 +- net/ipv6/netfilter.c | 2 +- net/ipv6/netfilter/ip6_queue.c | 6 +++--- net/ipv6/netfilter/nf_conntrack_reasm.c | 6 +++--- net/ipv6/raw.c | 2 +- net/ipv6/reassembly.c | 6 +++--- net/ipv6/tcp_ipv6.c | 6 +++--- net/ipv6/udp.c | 2 +- net/ipv6/xfrm6_output.c | 4 ++-- net/netfilter/nf_conntrack_proto_tcp.c | 3 +-- net/netfilter/nf_conntrack_proto_udp.c | 3 +-- net/netfilter/nfnetlink_queue.c | 6 +++--- net/packet/af_packet.c | 2 +- net/sched/sch_netem.c | 4 ++-- net/sunrpc/socklib.c | 2 +- 72 files changed, 168 insertions(+), 169 deletions(-) (limited to 'net/core') diff --git a/drivers/atm/he.c b/drivers/atm/he.c index ffcb9fd31c3..41e052fecd7 100644 --- a/drivers/atm/he.c +++ b/drivers/atm/he.c @@ -1912,7 +1912,7 @@ he_service_rbrq(struct he_dev *he_dev, int group) skb->tail = skb->data + skb->len; #ifdef USE_CHECKSUM_HW if (vcc->vpi == 0 && vcc->vci >= ATM_NOT_RSV_VCI) { - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_COMPLETE; skb->csum = TCP_CKSUM(skb->data, he_vcc->pdu_len); } diff --git a/drivers/net/3c59x.c b/drivers/net/3c59x.c index 80e8ca013e4..29dede2eaa8 100644 --- a/drivers/net/3c59x.c +++ b/drivers/net/3c59x.c @@ -2077,7 +2077,7 @@ boomerang_start_xmit(struct sk_buff *skb, struct net_device *dev) vp->tx_ring[entry].next = 0; #if DO_ZEROCOPY - if (skb->ip_summed != CHECKSUM_HW) + if (skb->ip_summed != CHECKSUM_PARTIAL) vp->tx_ring[entry].status = cpu_to_le32(skb->len | TxIntrUploaded); else vp->tx_ring[entry].status = cpu_to_le32(skb->len | TxIntrUploaded | AddTCPChksum | AddUDPChksum); diff --git a/drivers/net/8139cp.c b/drivers/net/8139cp.c index 1428bb7715a..a48b211c489 100644 --- a/drivers/net/8139cp.c +++ b/drivers/net/8139cp.c @@ -813,7 +813,7 @@ static int cp_start_xmit (struct sk_buff *skb, struct net_device *dev) if (mss) flags |= LargeSend | ((mss & MSSMask) << MSSShift); - else if (skb->ip_summed == CHECKSUM_HW) { + else if (skb->ip_summed == CHECKSUM_PARTIAL) { const struct iphdr *ip = skb->nh.iph; if (ip->protocol == IPPROTO_TCP) flags |= IPCS | TCPCS; @@ -867,7 +867,7 @@ static int cp_start_xmit (struct sk_buff *skb, struct net_device *dev) if (mss) ctrl |= LargeSend | ((mss & MSSMask) << MSSShift); - else if (skb->ip_summed == CHECKSUM_HW) { + else if (skb->ip_summed == CHECKSUM_PARTIAL) { if (ip->protocol == IPPROTO_TCP) ctrl |= IPCS | TCPCS; else if (ip->protocol == IPPROTO_UDP) @@ -898,7 +898,7 @@ static int cp_start_xmit (struct sk_buff *skb, struct net_device *dev) txd->addr = cpu_to_le64(first_mapping); wmb(); - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { if (ip->protocol == IPPROTO_TCP) txd->opts1 = cpu_to_le32(first_eor | first_len | FirstFrag | DescOwn | diff --git a/drivers/net/acenic.c b/drivers/net/acenic.c index 1c01e9b3d07..826548644d7 100644 --- a/drivers/net/acenic.c +++ b/drivers/net/acenic.c @@ -2040,7 +2040,7 @@ static void ace_rx_int(struct net_device *dev, u32 rxretprd, u32 rxretcsm) */ if (bd_flags & BD_FLG_TCP_UDP_SUM) { skb->csum = htons(csum); - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_COMPLETE; } else { skb->ip_summed = CHECKSUM_NONE; } @@ -2511,7 +2511,7 @@ restart: mapping = ace_map_tx_skb(ap, skb, skb, idx); flagsize = (skb->len << 16) | (BD_FLG_END); - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_PARTIAL) flagsize |= BD_FLG_TCP_UDP_SUM; #if ACENIC_DO_VLAN if (vlan_tx_tag_present(skb)) { @@ -2534,7 +2534,7 @@ restart: mapping = ace_map_tx_skb(ap, skb, NULL, idx); flagsize = (skb_headlen(skb) << 16); - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_PARTIAL) flagsize |= BD_FLG_TCP_UDP_SUM; #if ACENIC_DO_VLAN if (vlan_tx_tag_present(skb)) { @@ -2560,7 +2560,7 @@ restart: PCI_DMA_TODEVICE); flagsize = (frag->size << 16); - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_PARTIAL) flagsize |= BD_FLG_TCP_UDP_SUM; idx = (idx + 1) % ACE_TX_RING_ENTRIES(ap); diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c index 652eb05a6c2..7857b463012 100644 --- a/drivers/net/bnx2.c +++ b/drivers/net/bnx2.c @@ -4423,7 +4423,7 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev) ring_prod = TX_RING_IDX(prod); vlan_tag_flags = 0; - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { vlan_tag_flags |= TX_BD_FLAGS_TCP_UDP_CKSUM; } diff --git a/drivers/net/cassini.c b/drivers/net/cassini.c index a31544ccb3c..558fdb8ad2d 100644 --- a/drivers/net/cassini.c +++ b/drivers/net/cassini.c @@ -2167,7 +2167,7 @@ end_copy_pkt: cas_page_unmap(addr); } skb->csum = ntohs(i ^ 0xffff); - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_COMPLETE; skb->protocol = eth_type_trans(skb, cp->dev); return len; } @@ -2821,7 +2821,7 @@ static inline int cas_xmit_tx_ringN(struct cas *cp, int ring, } ctrl = 0; - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { u64 csum_start_off, csum_stuff_off; csum_start_off = (u64) (skb->h.raw - skb->data); diff --git a/drivers/net/chelsio/sge.c b/drivers/net/chelsio/sge.c index 61b3754f50f..ddd0bdb498f 100644 --- a/drivers/net/chelsio/sge.c +++ b/drivers/net/chelsio/sge.c @@ -1470,9 +1470,9 @@ int t1_start_xmit(struct sk_buff *skb, struct net_device *dev) } if (!(adapter->flags & UDP_CSUM_CAPABLE) && - skb->ip_summed == CHECKSUM_HW && + skb->ip_summed == CHECKSUM_PARTIAL && skb->nh.iph->protocol == IPPROTO_UDP) - if (unlikely(skb_checksum_help(skb, 0))) { + if (unlikely(skb_checksum_help(skb))) { dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -1495,11 +1495,11 @@ int t1_start_xmit(struct sk_buff *skb, struct net_device *dev) cpl = (struct cpl_tx_pkt *)__skb_push(skb, sizeof(*cpl)); cpl->opcode = CPL_TX_PKT; cpl->ip_csum_dis = 1; /* SW calculates IP csum */ - cpl->l4_csum_dis = skb->ip_summed == CHECKSUM_HW ? 0 : 1; + cpl->l4_csum_dis = skb->ip_summed == CHECKSUM_PARTIAL ? 0 : 1; /* the length field isn't used so don't bother setting it */ - st->tx_cso += (skb->ip_summed == CHECKSUM_HW); - sge->stats.tx_do_cksum += (skb->ip_summed == CHECKSUM_HW); + st->tx_cso += (skb->ip_summed == CHECKSUM_PARTIAL); + sge->stats.tx_do_cksum += (skb->ip_summed == CHECKSUM_PARTIAL); sge->stats.tx_reg_pkts++; } cpl->iff = dev->if_port; diff --git a/drivers/net/dl2k.c b/drivers/net/dl2k.c index 402961e68c8..b74e6765476 100644 --- a/drivers/net/dl2k.c +++ b/drivers/net/dl2k.c @@ -611,7 +611,7 @@ start_xmit (struct sk_buff *skb, struct net_device *dev) txdesc = &np->tx_ring[entry]; #if 0 - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { txdesc->status |= cpu_to_le64 (TCPChecksumEnable | UDPChecksumEnable | IPChecksumEnable); diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c index 98ef9f85482..2ab9f96f5da 100644 --- a/drivers/net/e1000/e1000_main.c +++ b/drivers/net/e1000/e1000_main.c @@ -2600,7 +2600,7 @@ e1000_tx_csum(struct e1000_adapter *adapter, struct e1000_tx_ring *tx_ring, unsigned int i; uint8_t css; - if (likely(skb->ip_summed == CHECKSUM_HW)) { + if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { css = skb->h.raw - skb->data; i = tx_ring->next_to_use; @@ -2927,11 +2927,11 @@ e1000_xmit_frame(struct sk_buff *skb, struct net_device *netdev) } /* reserve a descriptor for the offload context */ - if ((mss) || (skb->ip_summed == CHECKSUM_HW)) + if ((mss) || (skb->ip_summed == CHECKSUM_PARTIAL)) count++; count++; #else - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_PARTIAL) count++; #endif @@ -3608,7 +3608,7 @@ e1000_rx_checksum(struct e1000_adapter *adapter, */ csum = ntohl(csum ^ 0xFFFF); skb->csum = csum; - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_COMPLETE; } adapter->hw_csum_good++; } diff --git a/drivers/net/forcedeth.c b/drivers/net/forcedeth.c index 11b8f1b43dd..32cacf115f7 100644 --- a/drivers/net/forcedeth.c +++ b/drivers/net/forcedeth.c @@ -1503,7 +1503,8 @@ static int nv_start_xmit(struct sk_buff *skb, struct net_device *dev) tx_flags_extra = NV_TX2_TSO | (skb_shinfo(skb)->gso_size << NV_TX2_TSO_SHIFT); else #endif - tx_flags_extra = (skb->ip_summed == CHECKSUM_HW ? (NV_TX2_CHECKSUM_L3|NV_TX2_CHECKSUM_L4) : 0); + tx_flags_extra = skb->ip_summed == CHECKSUM_PARTIAL ? + NV_TX2_CHECKSUM_L3 | NV_TX2_CHECKSUM_L4 : 0; /* vlan tag */ if (np->vlangrp && vlan_tx_tag_present(skb)) { diff --git a/drivers/net/gianfar.c b/drivers/net/gianfar.c index ebbbd6ca620..ba960913c03 100644 --- a/drivers/net/gianfar.c +++ b/drivers/net/gianfar.c @@ -947,7 +947,7 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev) /* Set up checksumming */ if (likely((dev->features & NETIF_F_IP_CSUM) - && (CHECKSUM_HW == skb->ip_summed))) { + && (CHECKSUM_PARTIAL == skb->ip_summed))) { fcb = gfar_add_fcb(skb, txbdp); status |= TXBD_TOE; gfar_tx_checksum(skb, fcb); diff --git a/drivers/net/hamachi.c b/drivers/net/hamachi.c index 409c6aab041..763373ae966 100644 --- a/drivers/net/hamachi.c +++ b/drivers/net/hamachi.c @@ -1648,7 +1648,7 @@ static int hamachi_rx(struct net_device *dev) * could do the pseudo myself and return * CHECKSUM_UNNECESSARY */ - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_COMPLETE; } } } diff --git a/drivers/net/ibm_emac/ibm_emac_core.c b/drivers/net/ibm_emac/ibm_emac_core.c index 82468e2dc79..57e214d85e9 100644 --- a/drivers/net/ibm_emac/ibm_emac_core.c +++ b/drivers/net/ibm_emac/ibm_emac_core.c @@ -1036,7 +1036,7 @@ static inline u16 emac_tx_csum(struct ocp_enet_private *dev, struct sk_buff *skb) { #if defined(CONFIG_IBM_EMAC_TAH) - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { ++dev->stats.tx_packets_csum; return EMAC_TX_CTRL_TAH_CSUM; } diff --git a/drivers/net/ioc3-eth.c b/drivers/net/ioc3-eth.c index 68d8af7df08..65f897ddb92 100644 --- a/drivers/net/ioc3-eth.c +++ b/drivers/net/ioc3-eth.c @@ -1387,7 +1387,7 @@ static int ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev) * MAC header which should not be summed and the TCP/UDP pseudo headers * manually. */ - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { int proto = ntohs(skb->nh.iph->protocol); unsigned int csoff; struct iphdr *ih = skb->nh.iph; diff --git a/drivers/net/ixgb/ixgb_main.c b/drivers/net/ixgb/ixgb_main.c index 7bbd447289b..9405b44f321 100644 --- a/drivers/net/ixgb/ixgb_main.c +++ b/drivers/net/ixgb/ixgb_main.c @@ -1232,7 +1232,7 @@ ixgb_tx_csum(struct ixgb_adapter *adapter, struct sk_buff *skb) unsigned int i; uint8_t css, cso; - if(likely(skb->ip_summed == CHECKSUM_HW)) { + if(likely(skb->ip_summed == CHECKSUM_PARTIAL)) { css = skb->h.raw - skb->data; cso = (skb->h.raw + skb->csum) - skb->data; diff --git a/drivers/net/mv643xx_eth.c b/drivers/net/mv643xx_eth.c index eeab1df5bef..38df58fdb35 100644 --- a/drivers/net/mv643xx_eth.c +++ b/drivers/net/mv643xx_eth.c @@ -1147,7 +1147,7 @@ static void eth_tx_submit_descs_for_skb(struct mv643xx_private *mp, desc->byte_cnt = length; desc->buf_ptr = dma_map_single(NULL, skb->data, length, DMA_TO_DEVICE); - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { BUG_ON(skb->protocol != ETH_P_IP); cmd_sts |= ETH_GEN_TCP_UDP_CHECKSUM | diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c index 9bdd43ab357..9f16681d0e7 100644 --- a/drivers/net/myri10ge/myri10ge.c +++ b/drivers/net/myri10ge/myri10ge.c @@ -930,7 +930,7 @@ static inline void myri10ge_vlan_ip_csum(struct sk_buff *skb, u16 hw_csum) (vh->h_vlan_encapsulated_proto == htons(ETH_P_IP) || vh->h_vlan_encapsulated_proto == htons(ETH_P_IPV6))) { skb->csum = hw_csum; - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_COMPLETE; } } @@ -973,7 +973,7 @@ myri10ge_rx_done(struct myri10ge_priv *mgp, struct myri10ge_rx_buf *rx, if ((skb->protocol == ntohs(ETH_P_IP)) || (skb->protocol == ntohs(ETH_P_IPV6))) { skb->csum = ntohs((u16) csum); - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_COMPLETE; } else myri10ge_vlan_ip_csum(skb, ntohs((u16) csum)); } @@ -1897,13 +1897,13 @@ again: pseudo_hdr_offset = 0; odd_flag = 0; flags = (MXGEFW_FLAGS_NO_TSO | MXGEFW_FLAGS_FIRST); - if (likely(skb->ip_summed == CHECKSUM_HW)) { + if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { cksum_offset = (skb->h.raw - skb->data); pseudo_hdr_offset = (skb->h.raw + skb->csum) - skb->data; /* If the headers are excessively large, then we must * fall back to a software checksum */ if (unlikely(cksum_offset > 255 || pseudo_hdr_offset > 127)) { - if (skb_checksum_help(skb, 0)) + if (skb_checksum_help(skb)) goto drop; cksum_offset = 0; pseudo_hdr_offset = 0; diff --git a/drivers/net/ns83820.c b/drivers/net/ns83820.c index 0e76859c90a..5143f5dbb2e 100644 --- a/drivers/net/ns83820.c +++ b/drivers/net/ns83820.c @@ -1153,7 +1153,7 @@ again: if (!nr_frags) frag = NULL; extsts = 0; - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { extsts |= EXTSTS_IPPKT; if (IPPROTO_TCP == skb->nh.iph->protocol) extsts |= EXTSTS_TCPPKT; diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c index 4c2f575faad..d9b960aa9b0 100644 --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -2169,7 +2169,7 @@ static inline u32 rtl8169_tso_csum(struct sk_buff *skb, struct net_device *dev) if (mss) return LargeSend | ((mss & MSSMask) << MSSShift); } - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { const struct iphdr *ip = skb->nh.iph; if (ip->protocol == IPPROTO_TCP) diff --git a/drivers/net/s2io.c b/drivers/net/s2io.c index e72e0e09906..5b3713f622d 100644 --- a/drivers/net/s2io.c +++ b/drivers/net/s2io.c @@ -3893,7 +3893,7 @@ static int s2io_xmit(struct sk_buff *skb, struct net_device *dev) txdp->Control_1 |= TXD_TCP_LSO_MSS(s2io_tcp_mss(skb)); } #endif - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { txdp->Control_2 |= (TXD_TX_CKO_IPV4_EN | TXD_TX_CKO_TCP_EN | TXD_TX_CKO_UDP_EN); diff --git a/drivers/net/sk98lin/skge.c b/drivers/net/sk98lin/skge.c index ee62845d3ac..eb3b35180c2 100644 --- a/drivers/net/sk98lin/skge.c +++ b/drivers/net/sk98lin/skge.c @@ -1559,7 +1559,7 @@ struct sk_buff *pMessage) /* pointer to send-message */ pTxd->VDataHigh = (SK_U32) (PhysAddr >> 32); pTxd->pMBuf = pMessage; - if (pMessage->ip_summed == CHECKSUM_HW) { + if (pMessage->ip_summed == CHECKSUM_PARTIAL) { u16 hdrlen = pMessage->h.raw - pMessage->data; u16 offset = hdrlen + pMessage->csum; @@ -1678,7 +1678,7 @@ struct sk_buff *pMessage) /* pointer to send-message */ /* ** Does the HW need to evaluate checksum for TCP or UDP packets? */ - if (pMessage->ip_summed == CHECKSUM_HW) { + if (pMessage->ip_summed == CHECKSUM_PARTIAL) { u16 hdrlen = pMessage->h.raw - pMessage->data; u16 offset = hdrlen + pMessage->csum; @@ -2158,7 +2158,7 @@ rx_start: #ifdef USE_SK_RX_CHECKSUM pMsg->csum = pRxd->TcpSums & 0xffff; - pMsg->ip_summed = CHECKSUM_HW; + pMsg->ip_summed = CHECKSUM_COMPLETE; #else pMsg->ip_summed = CHECKSUM_NONE; #endif diff --git a/drivers/net/skge.c b/drivers/net/skge.c index ad878dfddef..b3d6fa3d6df 100644 --- a/drivers/net/skge.c +++ b/drivers/net/skge.c @@ -2338,7 +2338,7 @@ static int skge_xmit_frame(struct sk_buff *skb, struct net_device *dev) td->dma_lo = map; td->dma_hi = map >> 32; - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { int offset = skb->h.raw - skb->data; /* This seems backwards, but it is what the sk98lin @@ -2642,7 +2642,7 @@ static inline struct sk_buff *skge_rx_get(struct skge_port *skge, skb->dev = skge->netdev; if (skge->rx_csum) { skb->csum = csum; - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_COMPLETE; } skb->protocol = eth_type_trans(skb, skge->netdev); diff --git a/drivers/net/sky2.c b/drivers/net/sky2.c index 933e87f1cc6..8e92566b587 100644 --- a/drivers/net/sky2.c +++ b/drivers/net/sky2.c @@ -1163,7 +1163,7 @@ static unsigned tx_le_req(const struct sk_buff *skb) if (skb_is_gso(skb)) ++count; - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_PARTIAL) ++count; return count; @@ -1272,7 +1272,7 @@ static int sky2_xmit_frame(struct sk_buff *skb, struct net_device *dev) #endif /* Handle TCP checksum offload */ - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { u16 hdr = skb->h.raw - skb->data; u16 offset = hdr + skb->csum; @@ -2000,7 +2000,7 @@ static int sky2_status_intr(struct sky2_hw *hw, int to_do) #endif case OP_RXCHKS: skb = sky2->rx_ring[sky2->rx_next].skb; - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_COMPLETE; skb->csum = le16_to_cpu(status); break; diff --git a/drivers/net/starfire.c b/drivers/net/starfire.c index c0a62b00ffc..2607aa51d8e 100644 --- a/drivers/net/starfire.c +++ b/drivers/net/starfire.c @@ -1230,7 +1230,7 @@ static int start_tx(struct sk_buff *skb, struct net_device *dev) } #if defined(ZEROCOPY) && defined(HAS_BROKEN_FIRMWARE) - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { if (skb_padto(skb, (skb->len + PADDING_MASK) & ~PADDING_MASK)) return NETDEV_TX_OK; } @@ -1252,7 +1252,7 @@ static int start_tx(struct sk_buff *skb, struct net_device *dev) status |= TxDescIntr; np->reap_tx = 0; } - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { status |= TxCalTCP; np->stats.tx_compressed++; } @@ -1499,7 +1499,7 @@ static int __netdev_rx(struct net_device *dev, int *quota) * Until then, the printk stays. :-) -Ion */ else if (le16_to_cpu(desc->status2) & 0x0040) { - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_COMPLETE; skb->csum = le16_to_cpu(desc->csum); printk(KERN_DEBUG "%s: checksum_hw, status2 = %#x\n", dev->name, le16_to_cpu(desc->status2)); } diff --git a/drivers/net/sungem.c b/drivers/net/sungem.c index d7b1d1882ca..b388651b783 100644 --- a/drivers/net/sungem.c +++ b/drivers/net/sungem.c @@ -855,7 +855,7 @@ static int gem_rx(struct gem *gp, int work_to_do) } skb->csum = ntohs((status & RXDCTRL_TCPCSUM) ^ 0xffff); - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_COMPLETE; skb->protocol = eth_type_trans(skb, gp->dev); netif_receive_skb(skb); @@ -1026,7 +1026,7 @@ static int gem_start_xmit(struct sk_buff *skb, struct net_device *dev) unsigned long flags; ctrl = 0; - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { u64 csum_start_off, csum_stuff_off; csum_start_off = (u64) (skb->h.raw - skb->data); diff --git a/drivers/net/sunhme.c b/drivers/net/sunhme.c index c6f5bc3c042..17981da2273 100644 --- a/drivers/net/sunhme.c +++ b/drivers/net/sunhme.c @@ -1207,7 +1207,7 @@ static void happy_meal_transceiver_check(struct happy_meal *hp, void __iomem *tr * flags, thus: * * skb->csum = rxd->rx_flags & 0xffff; - * skb->ip_summed = CHECKSUM_HW; + * skb->ip_summed = CHECKSUM_COMPLETE; * * before sending off the skb to the protocols, and we are good as gold. */ @@ -2074,7 +2074,7 @@ static void happy_meal_rx(struct happy_meal *hp, struct net_device *dev) /* This card is _fucking_ hot... */ skb->csum = ntohs(csum ^ 0xffff); - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_COMPLETE; RXD(("len=%d csum=%4x]", len, csum)); skb->protocol = eth_type_trans(skb, dev); @@ -2268,7 +2268,7 @@ static int happy_meal_start_xmit(struct sk_buff *skb, struct net_device *dev) u32 tx_flags; tx_flags = TXFLAG_OWN; - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { u32 csum_start_off, csum_stuff_off; csum_start_off = (u32) (skb->h.raw - skb->data); diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index eafabb253f0..6f5d3a38c58 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -3851,11 +3851,11 @@ static int tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) skb->h.th->check = 0; } - else if (skb->ip_summed == CHECKSUM_HW) + else if (skb->ip_summed == CHECKSUM_PARTIAL) base_flags |= TXD_FLAG_TCPUDP_CSUM; #else mss = 0; - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_PARTIAL) base_flags |= TXD_FLAG_TCPUDP_CSUM; #endif #if TG3_VLAN_TAG_USED @@ -3981,7 +3981,7 @@ static int tg3_start_xmit_dma_bug(struct sk_buff *skb, struct net_device *dev) entry = tp->tx_prod; base_flags = 0; - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_PARTIAL) base_flags |= TXD_FLAG_TCPUDP_CSUM; #if TG3_TSO_SUPPORT != 0 mss = 0; diff --git a/drivers/net/typhoon.c b/drivers/net/typhoon.c index 4103c37172f..c6e601dc6bb 100644 --- a/drivers/net/typhoon.c +++ b/drivers/net/typhoon.c @@ -830,7 +830,7 @@ typhoon_start_tx(struct sk_buff *skb, struct net_device *dev) first_txd->addrHi = (u64)((unsigned long) skb) >> 32; first_txd->processFlags = 0; - if(skb->ip_summed == CHECKSUM_HW) { + if(skb->ip_summed == CHECKSUM_PARTIAL) { /* The 3XP will figure out if this is UDP/TCP */ first_txd->processFlags |= TYPHOON_TX_PF_TCP_CHKSUM; first_txd->processFlags |= TYPHOON_TX_PF_UDP_CHKSUM; diff --git a/drivers/net/via-rhine.c b/drivers/net/via-rhine.c index ae971080e2e..66547159bfd 100644 --- a/drivers/net/via-rhine.c +++ b/drivers/net/via-rhine.c @@ -1230,7 +1230,7 @@ static int rhine_start_tx(struct sk_buff *skb, struct net_device *dev) rp->tx_skbuff[entry] = skb; if ((rp->quirks & rqRhineI) && - (((unsigned long)skb->data & 3) || skb_shinfo(skb)->nr_frags != 0 || skb->ip_summed == CHECKSUM_HW)) { + (((unsigned long)skb->data & 3) || skb_shinfo(skb)->nr_frags != 0 || skb->ip_summed == CHECKSUM_PARTIAL)) { /* Must use alignment buffer. */ if (skb->len > PKT_BUF_SZ) { /* packet too long, drop it */ diff --git a/drivers/net/via-velocity.c b/drivers/net/via-velocity.c index aa9cd92f46b..f1e0c746a38 100644 --- a/drivers/net/via-velocity.c +++ b/drivers/net/via-velocity.c @@ -2002,7 +2002,7 @@ static int velocity_xmit(struct sk_buff *skb, struct net_device *dev) * Handle hardware checksum */ if ((vptr->flags & VELOCITY_FLAGS_TX_CSUM) - && (skb->ip_summed == CHECKSUM_HW)) { + && (skb->ip_summed == CHECKSUM_PARTIAL)) { struct iphdr *ip = skb->nh.iph; if (ip->protocol == IPPROTO_TCP) td_ptr->tdesc1.TCR |= TCR0_TCPCK; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 50a4719512e..4f2c2b6beb5 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 755e9cddac4..85577a4ffa6 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); } diff --git a/net/core/datagram.c b/net/core/datagram.c index aecddcc3040..f558c61aecc 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -417,7 +417,7 @@ unsigned int __skb_checksum_complete(struct sk_buff *skb) sum = (u16)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum)); if (likely(!sum)) { - if (unlikely(skb->ip_summed == CHECKSUM_HW)) + if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) netdev_rx_csum_fault(skb->dev); skb->ip_summed = CHECKSUM_UNNECESSARY; } @@ -462,7 +462,7 @@ int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, goto fault; if ((unsigned short)csum_fold(csum)) goto csum_error; - if (unlikely(skb->ip_summed == CHECKSUM_HW)) + if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) netdev_rx_csum_fault(skb->dev); iov->iov_len -= chunk; iov->iov_base += chunk; diff --git a/net/core/dev.c b/net/core/dev.c index d4a1ec3bded..fc82f6f6e1c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1166,12 +1166,12 @@ EXPORT_SYMBOL(netif_device_attach); * Invalidate hardware checksum when packet is to be mangled, and * complete checksum manually on outgoing path. */ -int skb_checksum_help(struct sk_buff *skb, int inward) +int skb_checksum_help(struct sk_buff *skb) { unsigned int csum; int ret = 0, offset = skb->h.raw - skb->data; - if (inward) + if (skb->ip_summed == CHECKSUM_COMPLETE) goto out_set_summed; if (unlikely(skb_shinfo(skb)->gso_size)) { @@ -1223,7 +1223,7 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) skb->mac_len = skb->nh.raw - skb->data; __skb_pull(skb, skb->mac_len); - if (unlikely(skb->ip_summed != CHECKSUM_HW)) { + if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { if (skb_header_cloned(skb) && (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) return ERR_PTR(err); @@ -1232,7 +1232,7 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) rcu_read_lock(); list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & 15], list) { if (ptype->type == type && !ptype->dev && ptype->gso_segment) { - if (unlikely(skb->ip_summed != CHECKSUM_HW)) { + if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { err = ptype->gso_send_check(skb); segs = ERR_PTR(err); if (err || skb_gso_ok(skb, features)) @@ -1444,11 +1444,11 @@ int dev_queue_xmit(struct sk_buff *skb) /* If packet is not checksummed and device does not support * checksumming for this protocol, complete checksumming here. */ - if (skb->ip_summed == CHECKSUM_HW && + if (skb->ip_summed == CHECKSUM_PARTIAL && (!(dev->features & NETIF_F_GEN_CSUM) && (!(dev->features & NETIF_F_IP_CSUM) || skb->protocol != htons(ETH_P_IP)))) - if (skb_checksum_help(skb, 0)) + if (skb_checksum_help(skb)) goto out_kfree_skb; gso: diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 471da451cd4..ead5920c26d 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -110,7 +110,7 @@ static int checksum_udp(struct sk_buff *skb, struct udphdr *uh, psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0); - if (skb->ip_summed == CHECKSUM_HW && + if (skb->ip_summed == CHECKSUM_COMPLETE && !(u16)csum_fold(csum_add(psum, skb->csum))) return 0; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c54f3664bce..8a476f1956e 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1397,7 +1397,7 @@ void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) unsigned int csum; long csstart; - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_PARTIAL) csstart = skb->h.raw - skb->data; else csstart = skb_headlen(skb); @@ -1411,7 +1411,7 @@ void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) csum = skb_copy_and_csum_bits(skb, csstart, to + csstart, skb->len - csstart, 0); - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { long csstuff = csstart + skb->csum; *((unsigned short *)(to + csstuff)) = csum_fold(csum); @@ -1898,10 +1898,10 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, * @len: length of data pulled * * This function performs an skb_pull on the packet and updates - * update the CHECKSUM_HW checksum. It should be used on receive - * path processing instead of skb_pull unless you know that the - * checksum difference is zero (e.g., a valid IP header) or you - * are setting ip_summed to CHECKSUM_NONE. + * update the CHECKSUM_COMPLETE checksum. It should be used on + * receive path processing instead of skb_pull unless you know + * that the checksum difference is zero (e.g., a valid IP header) + * or you are setting ip_summed to CHECKSUM_NONE. */ unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len) { @@ -1994,7 +1994,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) frag = skb_shinfo(nskb)->frags; k = 0; - nskb->ip_summed = CHECKSUM_HW; + nskb->ip_summed = CHECKSUM_PARTIAL; nskb->csum = skb->csum; memcpy(skb_put(nskb, hsize), skb->data + offset, hsize); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 6ad797c1416..6d223e5c674 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -930,7 +930,7 @@ int icmp_rcv(struct sk_buff *skb) ICMP_INC_STATS_BH(ICMP_MIB_INMSGS); switch (skb->ip_summed) { - case CHECKSUM_HW: + case CHECKSUM_COMPLETE: if (!(u16)csum_fold(skb->csum)) break; /* fall through */ diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 8e8117c19e4..7003e763d97 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -931,7 +931,7 @@ int igmp_rcv(struct sk_buff *skb) goto drop; switch (skb->ip_summed) { - case CHECKSUM_HW: + case CHECKSUM_COMPLETE: if (!(u16)csum_fold(skb->csum)) break; /* fall through */ diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index b84b53a4752..8d7f107c2ee 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -665,7 +665,7 @@ static struct sk_buff *ip_frag_reasm(struct ipq *qp, struct net_device *dev) head->len += fp->len; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_HW) + else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; atomic_sub(fp->truesize, &ip_frag_mem); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 0f9b3a31997..e66f6ff2e19 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -576,7 +576,7 @@ static int ipgre_rcv(struct sk_buff *skb) if (flags&GRE_CSUM) { switch (skb->ip_summed) { - case CHECKSUM_HW: + case CHECKSUM_COMPLETE: csum = (u16)csum_fold(skb->csum); if (!csum) break; @@ -584,7 +584,7 @@ static int ipgre_rcv(struct sk_buff *skb) case CHECKSUM_NONE: skb->csum = 0; csum = __skb_checksum_complete(skb); - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_COMPLETE; } offset += 4; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 308bdeac345..1b9b6742ef7 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -680,7 +680,7 @@ ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk { struct iovec *iov = from; - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { if (memcpy_fromiovecend(to, iov, offset, len) < 0) return -EFAULT; } else { @@ -736,7 +736,7 @@ static inline int ip_ufo_append_data(struct sock *sk, /* initialize protocol header pointer */ skb->h.raw = skb->data + fragheaderlen; - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; sk->sk_sndmsg_off = 0; } @@ -844,7 +844,7 @@ int ip_append_data(struct sock *sk, length + fragheaderlen <= mtu && rt->u.dst.dev->features & NETIF_F_ALL_CSUM && !exthdrlen) - csummode = CHECKSUM_HW; + csummode = CHECKSUM_PARTIAL; inet->cork.length += length; if (((length > mtu) && (sk->sk_protocol == IPPROTO_UDP)) && diff --git a/net/ipv4/ipvs/ip_vs_proto_tcp.c b/net/ipv4/ipvs/ip_vs_proto_tcp.c index bc28b1160a3..820e8318d10 100644 --- a/net/ipv4/ipvs/ip_vs_proto_tcp.c +++ b/net/ipv4/ipvs/ip_vs_proto_tcp.c @@ -151,7 +151,7 @@ tcp_snat_handler(struct sk_buff **pskb, /* Only port and addr are changed, do fast csum update */ tcp_fast_csum_update(tcph, cp->daddr, cp->vaddr, cp->dport, cp->vport); - if ((*pskb)->ip_summed == CHECKSUM_HW) + if ((*pskb)->ip_summed == CHECKSUM_COMPLETE) (*pskb)->ip_summed = CHECKSUM_NONE; } else { /* full checksum calculation */ @@ -204,7 +204,7 @@ tcp_dnat_handler(struct sk_buff **pskb, /* Only port and addr are changed, do fast csum update */ tcp_fast_csum_update(tcph, cp->vaddr, cp->daddr, cp->vport, cp->dport); - if ((*pskb)->ip_summed == CHECKSUM_HW) + if ((*pskb)->ip_summed == CHECKSUM_COMPLETE) (*pskb)->ip_summed = CHECKSUM_NONE; } else { /* full checksum calculation */ @@ -229,7 +229,7 @@ tcp_csum_check(struct sk_buff *skb, struct ip_vs_protocol *pp) switch (skb->ip_summed) { case CHECKSUM_NONE: skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0); - case CHECKSUM_HW: + case CHECKSUM_COMPLETE: if (csum_tcpudp_magic(skb->nh.iph->saddr, skb->nh.iph->daddr, skb->len - tcphoff, skb->nh.iph->protocol, skb->csum)) { @@ -239,7 +239,7 @@ tcp_csum_check(struct sk_buff *skb, struct ip_vs_protocol *pp) } break; default: - /* CHECKSUM_UNNECESSARY */ + /* No need to checksum. */ break; } diff --git a/net/ipv4/ipvs/ip_vs_proto_udp.c b/net/ipv4/ipvs/ip_vs_proto_udp.c index 89d9175d8f2..90c8166c0ec 100644 --- a/net/ipv4/ipvs/ip_vs_proto_udp.c +++ b/net/ipv4/ipvs/ip_vs_proto_udp.c @@ -161,7 +161,7 @@ udp_snat_handler(struct sk_buff **pskb, /* Only port and addr are changed, do fast csum update */ udp_fast_csum_update(udph, cp->daddr, cp->vaddr, cp->dport, cp->vport); - if ((*pskb)->ip_summed == CHECKSUM_HW) + if ((*pskb)->ip_summed == CHECKSUM_COMPLETE) (*pskb)->ip_summed = CHECKSUM_NONE; } else { /* full checksum calculation */ @@ -216,7 +216,7 @@ udp_dnat_handler(struct sk_buff **pskb, /* Only port and addr are changed, do fast csum update */ udp_fast_csum_update(udph, cp->vaddr, cp->daddr, cp->vport, cp->dport); - if ((*pskb)->ip_summed == CHECKSUM_HW) + if ((*pskb)->ip_summed == CHECKSUM_COMPLETE) (*pskb)->ip_summed = CHECKSUM_NONE; } else { /* full checksum calculation */ @@ -250,7 +250,7 @@ udp_csum_check(struct sk_buff *skb, struct ip_vs_protocol *pp) case CHECKSUM_NONE: skb->csum = skb_checksum(skb, udphoff, skb->len - udphoff, 0); - case CHECKSUM_HW: + case CHECKSUM_COMPLETE: if (csum_tcpudp_magic(skb->nh.iph->saddr, skb->nh.iph->daddr, skb->len - udphoff, @@ -262,7 +262,7 @@ udp_csum_check(struct sk_buff *skb, struct ip_vs_protocol *pp) } break; default: - /* CHECKSUM_UNNECESSARY */ + /* No need to checksum. */ break; } } diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 6a9e34b794b..f88347de21a 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -168,7 +168,7 @@ unsigned int nf_ip_checksum(struct sk_buff *skb, unsigned int hook, unsigned int csum = 0; switch (skb->ip_summed) { - case CHECKSUM_HW: + case CHECKSUM_COMPLETE: if (hook != NF_IP_PRE_ROUTING && hook != NF_IP_LOCAL_IN) break; if ((protocol == 0 && !(u16)csum_fold(skb->csum)) || diff --git a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c index fb920e76ec1..9de81ff645d 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c @@ -865,8 +865,7 @@ static int tcp_error(struct sk_buff *skb, /* Checksum invalid? Ignore. * We skip checking packets on the outgoing path - * because the semantic of CHECKSUM_HW is different there - * and moreover root might send raw packets. + * because it is assumed to be correct. */ /* FIXME: Source route IP option packets --RR */ if (ip_conntrack_checksum && hooknum == NF_IP_PRE_ROUTING && diff --git a/net/ipv4/netfilter/ip_conntrack_proto_udp.c b/net/ipv4/netfilter/ip_conntrack_proto_udp.c index 9b2c16b4d2f..e58e52f1455 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_udp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_udp.c @@ -117,8 +117,7 @@ static int udp_error(struct sk_buff *skb, enum ip_conntrack_info *ctinfo, /* Checksum invalid? Ignore. * We skip checking packets on the outgoing path - * because the semantic of CHECKSUM_HW is different there - * and moreover root might send raw packets. + * because the checksum is assumed to be correct. * FIXME: Source route IP option packets --RR */ if (ip_conntrack_checksum && hooknum == NF_IP_PRE_ROUTING && nf_ip_checksum(skb, hooknum, iph->ihl * 4, IPPROTO_UDP)) { diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c index 17de077a790..f4f00c816d8 100644 --- a/net/ipv4/netfilter/ip_nat_standalone.c +++ b/net/ipv4/netfilter/ip_nat_standalone.c @@ -111,8 +111,9 @@ ip_nat_fn(unsigned int hooknum, & htons(IP_MF|IP_OFFSET))); /* If we had a hardware checksum before, it's now invalid */ - if ((*pskb)->ip_summed == CHECKSUM_HW) - if (skb_checksum_help(*pskb, (out == NULL))) + if ((*pskb)->ip_summed == CHECKSUM_PARTIAL || + (*pskb)->ip_summed == CHECKSUM_COMPLETE) + if (skb_checksum_help(*pskb)) return NF_DROP; ct = ip_conntrack_get(*pskb, &ctinfo); diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index 198ac36db86..276a964ee6c 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -208,9 +208,9 @@ ipq_build_packet_message(struct ipq_queue_entry *entry, int *errp) break; case IPQ_COPY_PACKET: - if (entry->skb->ip_summed == CHECKSUM_HW && - (*errp = skb_checksum_help(entry->skb, - entry->info->outdev == NULL))) { + if ((entry->skb->ip_summed == CHECKSUM_PARTIAL || + entry->skb->ip_summed == CHECKSUM_COMPLETE) && + (*errp = skb_checksum_help(entry->skb))) { read_unlock_bh(&queue_lock); return NULL; } diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index 4adf5c9d34f..4ec43f98fe4 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -49,7 +49,7 @@ set_ect_ip(struct sk_buff **pskb, const struct ipt_ECN_info *einfo) /* Return 0 if there was an error. */ static inline int -set_ect_tcp(struct sk_buff **pskb, const struct ipt_ECN_info *einfo, int inward) +set_ect_tcp(struct sk_buff **pskb, const struct ipt_ECN_info *einfo) { struct tcphdr _tcph, *tcph; u_int16_t diffs[2]; @@ -70,8 +70,9 @@ set_ect_tcp(struct sk_buff **pskb, const struct ipt_ECN_info *einfo, int inward) return 0; tcph = (void *)(*pskb)->nh.iph + (*pskb)->nh.iph->ihl*4; - if ((*pskb)->ip_summed == CHECKSUM_HW && - skb_checksum_help(*pskb, inward)) + if (((*pskb)->ip_summed == CHECKSUM_PARTIAL || + (*pskb)->ip_summed == CHECKSUM_COMPLETE) && + skb_checksum_help(*pskb)) return 0; diffs[0] = ((u_int16_t *)tcph)[6]; @@ -106,7 +107,7 @@ target(struct sk_buff **pskb, if (einfo->operation & (IPT_ECN_OP_SET_ECE | IPT_ECN_OP_SET_CWR) && (*pskb)->nh.iph->protocol == IPPROTO_TCP) - if (!set_ect_tcp(pskb, einfo, (out == NULL))) + if (!set_ect_tcp(pskb, einfo)) return NF_DROP; return IPT_CONTINUE; diff --git a/net/ipv4/netfilter/ipt_TCPMSS.c b/net/ipv4/netfilter/ipt_TCPMSS.c index ef2fe5b3f0d..c998dc0fcd1 100644 --- a/net/ipv4/netfilter/ipt_TCPMSS.c +++ b/net/ipv4/netfilter/ipt_TCPMSS.c @@ -62,8 +62,9 @@ ipt_tcpmss_target(struct sk_buff **pskb, if (!skb_make_writable(pskb, (*pskb)->len)) return NF_DROP; - if ((*pskb)->ip_summed == CHECKSUM_HW && - skb_checksum_help(*pskb, out == NULL)) + if (((*pskb)->ip_summed == CHECKSUM_PARTIAL || + (*pskb)->ip_summed == CHECKSUM_COMPLETE) && + skb_checksum_help(*pskb)) return NF_DROP; iph = (*pskb)->nh.iph; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 934396bb137..b0124e69ab3 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -568,7 +568,7 @@ new_segment: skb->truesize += copy; sk->sk_wmem_queued += copy; sk->sk_forward_alloc -= copy; - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_PARTIAL; tp->write_seq += copy; TCP_SKB_CB(skb)->end_seq += copy; skb_shinfo(skb)->gso_segs = 0; @@ -723,7 +723,7 @@ new_segment: * Check whether we can use HW checksum. */ if (sk->sk_route_caps & NETIF_F_ALL_CSUM) - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_PARTIAL; skb_entail(sk, tp, skb); copy = size_goal; @@ -2205,7 +2205,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features) th->fin = th->psh = 0; th->check = ~csum_fold(th->check + delta); - if (skb->ip_summed != CHECKSUM_HW) + if (skb->ip_summed != CHECKSUM_PARTIAL) th->check = csum_fold(csum_partial(skb->h.raw, thlen, skb->csum)); @@ -2219,7 +2219,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features) delta = htonl(oldlen + (skb->tail - skb->h.raw) + skb->data_len); th->check = ~csum_fold(th->check + delta); - if (skb->ip_summed != CHECKSUM_HW) + if (skb->ip_summed != CHECKSUM_PARTIAL) th->check = csum_fold(csum_partial(skb->h.raw, thlen, skb->csum)); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 43f6740244f..b2aa512a30e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -484,7 +484,7 @@ void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb) struct inet_sock *inet = inet_sk(sk); struct tcphdr *th = skb->h.th; - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { th->check = ~tcp_v4_check(th, len, inet->saddr, inet->daddr, 0); skb->csum = offsetof(struct tcphdr, check); } else { @@ -509,7 +509,7 @@ int tcp_v4_gso_send_check(struct sk_buff *skb) th->check = 0; th->check = ~tcp_v4_check(th, skb->len, iph->saddr, iph->daddr, 0); skb->csum = offsetof(struct tcphdr, check); - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_PARTIAL; return 0; } @@ -973,7 +973,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) static int tcp_v4_checksum_init(struct sk_buff *skb) { - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_COMPLETE) { if (!tcp_v4_check(skb->h.th, skb->len, skb->nh.iph->saddr, skb->nh.iph->daddr, skb->csum)) { skb->ip_summed = CHECKSUM_UNNECESSARY; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b4f3ffe1b3b..9252a50c4b4 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -577,7 +577,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked; TCP_SKB_CB(skb)->sacked &= ~TCPCB_AT_TAIL; - if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_HW) { + if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_PARTIAL) { /* Copy and checksum data tail into the new buffer. */ buff->csum = csum_partial_copy_nocheck(skb->data + len, skb_put(buff, nsize), nsize, 0); @@ -586,7 +586,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss skb->csum = csum_block_sub(skb->csum, buff->csum, len); } else { - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_PARTIAL; skb_split(skb, buff, len); } @@ -689,7 +689,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) __pskb_trim_head(skb, len - skb_headlen(skb)); TCP_SKB_CB(skb)->seq += len; - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_PARTIAL; skb->truesize -= len; sk->sk_wmem_queued -= len; @@ -1062,7 +1062,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, /* This packet was never sent out yet, so no SACK bits. */ TCP_SKB_CB(buff)->sacked = 0; - buff->ip_summed = skb->ip_summed = CHECKSUM_HW; + buff->ip_summed = skb->ip_summed = CHECKSUM_PARTIAL; skb_split(skb, buff, len); /* Fix up tso_factor for both original and new SKB. */ @@ -1206,8 +1206,7 @@ static int tcp_mtu_probe(struct sock *sk) TCP_SKB_CB(nskb)->flags = TCPCB_FLAG_ACK; TCP_SKB_CB(nskb)->sacked = 0; nskb->csum = 0; - if (skb->ip_summed == CHECKSUM_HW) - nskb->ip_summed = CHECKSUM_HW; + nskb->ip_summed = skb->ip_summed; len = 0; while (len < probe_size) { @@ -1231,7 +1230,7 @@ static int tcp_mtu_probe(struct sock *sk) ~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH); if (!skb_shinfo(skb)->nr_frags) { skb_pull(skb, copy); - if (skb->ip_summed != CHECKSUM_HW) + if (skb->ip_summed != CHECKSUM_PARTIAL) skb->csum = csum_partial(skb->data, skb->len, 0); } else { __pskb_trim_head(skb, copy); @@ -1572,10 +1571,9 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *skb, int m memcpy(skb_put(skb, next_skb_size), next_skb->data, next_skb_size); - if (next_skb->ip_summed == CHECKSUM_HW) - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = next_skb->ip_summed; - if (skb->ip_summed != CHECKSUM_HW) + if (skb->ip_summed != CHECKSUM_PARTIAL) skb->csum = csum_block_add(skb->csum, next_skb->csum, skb_size); /* Update sequence range on original skb. */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index a4d005eccc7..87152510980 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -429,7 +429,7 @@ static int udp_push_pending_frames(struct sock *sk, struct udp_sock *up) /* * Only one fragment on the socket. */ - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { skb->csum = offsetof(struct udphdr, check); uh->check = ~csum_tcpudp_magic(fl->fl4_src, fl->fl4_dst, up->len, IPPROTO_UDP, 0); @@ -448,7 +448,7 @@ static int udp_push_pending_frames(struct sock *sk, struct udp_sock *up) * fragments on the socket so that all csums of sk_buffs * should be together. */ - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { int offset = (unsigned char *)uh - skb->data; skb->csum = skb_checksum(skb, offset, skb->len - offset, 0); @@ -1088,7 +1088,7 @@ static void udp_checksum_init(struct sk_buff *skb, struct udphdr *uh, { if (uh->check == 0) { skb->ip_summed = CHECKSUM_UNNECESSARY; - } else if (skb->ip_summed == CHECKSUM_HW) { + } else if (skb->ip_summed == CHECKSUM_COMPLETE) { if (!udp_check(uh, ulen, saddr, daddr, skb->csum)) skb->ip_summed = CHECKSUM_UNNECESSARY; } diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index d16f863cf68..4a96a9e3ef3 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -48,8 +48,8 @@ static int xfrm4_output_one(struct sk_buff *skb) struct xfrm_state *x = dst->xfrm; int err; - if (skb->ip_summed == CHECKSUM_HW) { - err = skb_checksum_help(skb, 0); + if (skb->ip_summed == CHECKSUM_PARTIAL) { + err = skb_checksum_help(skb); if (err) goto error_nolock; } diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 86dac106873..05afa6b1912 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -294,7 +294,7 @@ looped_back: hdr = (struct ipv6_rt_hdr *) skb2->h.raw; } - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; i = n - --hdr->segments_left; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index dbfce089e91..10305510767 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -606,7 +606,7 @@ static int icmpv6_rcv(struct sk_buff **pskb) /* Perform checksum. */ switch (skb->ip_summed) { - case CHECKSUM_HW: + case CHECKSUM_COMPLETE: if (!csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6, skb->csum)) break; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 4fb47a25291..65514f21c18 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -866,7 +866,7 @@ static inline int ip6_ufo_append_data(struct sock *sk, /* initialize protocol header pointer */ skb->h.raw = skb->data + fragheaderlen; - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; sk->sk_sndmsg_off = 0; } diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 395a417ba95..580b1aba672 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -87,7 +87,7 @@ unsigned int nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, unsigned int csum = 0; switch (skb->ip_summed) { - case CHECKSUM_HW: + case CHECKSUM_COMPLETE: if (hook != NF_IP6_PRE_ROUTING && hook != NF_IP6_LOCAL_IN) break; if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index 968a14be0d0..c01c126224e 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -206,9 +206,9 @@ ipq_build_packet_message(struct ipq_queue_entry *entry, int *errp) break; case IPQ_COPY_PACKET: - if (entry->skb->ip_summed == CHECKSUM_HW && - (*errp = skb_checksum_help(entry->skb, - entry->info->outdev == NULL))) { + if ((entry->skb->ip_summed == CHECKSUM_PARTIAL || + entry->skb->ip_summed == CHECKSUM_COMPLETE) && + (*errp = skb_checksum_help(entry->skb))) { read_unlock_bh(&queue_lock); return NULL; } diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 00d5583807f..7a4e4c2e319 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -408,7 +408,7 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb, return -1; } - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_sub(skb->csum, csum_partial(skb->nh.raw, (u8*)(fhdr + 1) - skb->nh.raw, @@ -640,7 +640,7 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev) head->len += fp->len; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_HW) + else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; atomic_sub(fp->truesize, &nf_ct_frag6_mem); @@ -652,7 +652,7 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev) head->nh.ipv6h->payload_len = htons(payload_len); /* Yes, and fold redundant checksum back. 8) */ - if (head->ip_summed == CHECKSUM_HW) + if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_partial(head->nh.raw, head->h.raw-head->nh.raw, head->csum); fq->fragments = NULL; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index d5040e17229..d4af1cb5e19 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -334,7 +334,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) if (!rp->checksum) skb->ip_summed = CHECKSUM_UNNECESSARY; - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_COMPLETE) { skb_postpull_rcsum(skb, skb->nh.raw, skb->h.raw - skb->nh.raw); if (!csum_ipv6_magic(&skb->nh.ipv6h->saddr, diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 4e299c69e1c..a8623d2b087 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -433,7 +433,7 @@ static void ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, return; } - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_sub(skb->csum, csum_partial(skb->nh.raw, (u8*)(fhdr+1)-skb->nh.raw, 0)); @@ -647,7 +647,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff **skb_in, head->len += fp->len; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_HW) + else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; atomic_sub(fp->truesize, &ip6_frag_mem); @@ -662,7 +662,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff **skb_in, *skb_in = head; /* Yes, and fold redundant checksum back. 8) */ - if (head->ip_summed == CHECKSUM_HW) + if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_partial(head->nh.raw, head->h.raw-head->nh.raw, head->csum); IP6_INC_STATS_BH(IPSTATS_MIB_REASMOKS); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 302786a11cd..7f1b660493b 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -545,7 +545,7 @@ static void tcp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb) struct ipv6_pinfo *np = inet6_sk(sk); struct tcphdr *th = skb->h.th; - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { th->check = ~csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP, 0); skb->csum = offsetof(struct tcphdr, check); } else { @@ -570,7 +570,7 @@ static int tcp_v6_gso_send_check(struct sk_buff *skb) th->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len, IPPROTO_TCP, 0); skb->csum = offsetof(struct tcphdr, check); - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_PARTIAL; return 0; } @@ -1033,7 +1033,7 @@ out: static int tcp_v6_checksum_init(struct sk_buff *skb) { - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_COMPLETE) { if (!tcp_v6_check(skb->h.th,skb->len,&skb->nh.ipv6h->saddr, &skb->nh.ipv6h->daddr,skb->csum)) { skb->ip_summed = CHECKSUM_UNNECESSARY; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 82c7c9cde2a..780b89f6dfc 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -475,7 +475,7 @@ static int udpv6_rcv(struct sk_buff **pskb) uh = skb->h.uh; } - if (skb->ip_summed == CHECKSUM_HW && + if (skb->ip_summed == CHECKSUM_COMPLETE && !csum_ipv6_magic(saddr, daddr, ulen, IPPROTO_UDP, skb->csum)) skb->ip_summed = CHECKSUM_UNNECESSARY; diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index c8c8b44a0f5..6d111743e50 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -41,8 +41,8 @@ static int xfrm6_output_one(struct sk_buff *skb) struct xfrm_state *x = dst->xfrm; int err; - if (skb->ip_summed == CHECKSUM_HW) { - err = skb_checksum_help(skb, 0); + if (skb->ip_summed == CHECKSUM_PARTIAL) { + err = skb_checksum_help(skb); if (err) goto error_nolock; } diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index af8adcba23a..308d2abd7ee 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -823,8 +823,7 @@ static int tcp_error(struct sk_buff *skb, /* Checksum invalid? Ignore. * We skip checking packets on the outgoing path - * because the semantic of CHECKSUM_HW is different there - * and moreover root might send raw packets. + * because the checksum is assumed to be correct. */ /* FIXME: Source route IP option packets --RR */ if (nf_conntrack_checksum && diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index ae07ebe3ab3..d36e03139e8 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -131,8 +131,7 @@ static int udp_error(struct sk_buff *skb, unsigned int dataoff, /* Checksum invalid? Ignore. * We skip checking packets on the outgoing path - * because the semantic of CHECKSUM_HW is different there - * and moreover root might send raw packets. + * because the checksum is assumed to be correct. * FIXME: Source route IP option packets --RR */ if (nf_conntrack_checksum && ((pf == PF_INET && hooknum == NF_IP_PRE_ROUTING) || diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 49ef41e34c4..eddfbe4441a 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -377,9 +377,9 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, break; case NFQNL_COPY_PACKET: - if (entskb->ip_summed == CHECKSUM_HW && - (*errp = skb_checksum_help(entskb, - outdev == NULL))) { + if ((entskb->ip_summed == CHECKSUM_PARTIAL || + entskb->ip_summed == CHECKSUM_COMPLETE) && + (*errp = skb_checksum_help(entskb))) { spin_unlock_bh(&queue->lock); return NULL; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 4172a523591..300215bdbf4 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -586,7 +586,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe else if (skb->pkt_type == PACKET_OUTGOING) { /* Special case: outgoing packets have ll header at head */ skb_pull(skb, skb->nh.raw - skb->data); - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_PARTIAL) status |= TP_STATUS_CSUMNOTREADY; } } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index a08ec4c7c55..45939bafbdf 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -192,8 +192,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) */ if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) { if (!(skb = skb_unshare(skb, GFP_ATOMIC)) - || (skb->ip_summed == CHECKSUM_HW - && skb_checksum_help(skb, 0))) { + || (skb->ip_summed == CHECKSUM_PARTIAL + && skb_checksum_help(skb))) { sch->qstats.drops++; return NET_XMIT_DROP; } diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c index eb330d4f66d..6f17527b9e6 100644 --- a/net/sunrpc/socklib.c +++ b/net/sunrpc/socklib.c @@ -168,7 +168,7 @@ int csum_partial_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb) return -1; if ((unsigned short)csum_fold(desc.csum)) return -1; - if (unlikely(skb->ip_summed == CHECKSUM_HW)) + if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) netdev_rx_csum_fault(skb->dev); return 0; no_checksum: -- cgit v1.2.3-70-g09d2 From a14a49d2b7b9290e87751f21f503f1954267d4c4 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Mon, 7 Aug 2006 17:53:08 -0700 Subject: [NEIGH]: Convert neighbour deletion to new netlink api Fixes: Return ENOENT if the neighbour is not found (was EINVAL) Return EAFNOSUPPORT if no table matches the specified address family. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/core/neighbour.c | 53 +++++++++++++++++++++++++++++++++------------------- 1 file changed, 34 insertions(+), 19 deletions(-) (limited to 'net/core') diff --git a/net/core/neighbour.c b/net/core/neighbour.c index fe2113f54e2..39c07cc66ee 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include @@ -1440,48 +1441,62 @@ int neigh_table_clear(struct neigh_table *tbl) int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct ndmsg *ndm = NLMSG_DATA(nlh); - struct rtattr **nda = arg; + struct ndmsg *ndm; + struct nlattr *dst_attr; struct neigh_table *tbl; struct net_device *dev = NULL; - int err = -ENODEV; + int err = -EINVAL; - if (ndm->ndm_ifindex && - (dev = dev_get_by_index(ndm->ndm_ifindex)) == NULL) + if (nlmsg_len(nlh) < sizeof(*ndm)) + goto out; + + dst_attr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_DST); + if (dst_attr == NULL) goto out; + ndm = nlmsg_data(nlh); + if (ndm->ndm_ifindex) { + dev = dev_get_by_index(ndm->ndm_ifindex); + if (dev == NULL) { + err = -ENODEV; + goto out; + } + } + read_lock(&neigh_tbl_lock); for (tbl = neigh_tables; tbl; tbl = tbl->next) { - struct rtattr *dst_attr = nda[NDA_DST - 1]; - struct neighbour *n; + struct neighbour *neigh; if (tbl->family != ndm->ndm_family) continue; read_unlock(&neigh_tbl_lock); - err = -EINVAL; - if (!dst_attr || RTA_PAYLOAD(dst_attr) < tbl->key_len) + if (nla_len(dst_attr) < tbl->key_len) goto out_dev_put; if (ndm->ndm_flags & NTF_PROXY) { - err = pneigh_delete(tbl, RTA_DATA(dst_attr), dev); + err = pneigh_delete(tbl, nla_data(dst_attr), dev); goto out_dev_put; } - if (!dev) - goto out; + if (dev == NULL) + goto out_dev_put; - n = neigh_lookup(tbl, RTA_DATA(dst_attr), dev); - if (n) { - err = neigh_update(n, NULL, NUD_FAILED, - NEIGH_UPDATE_F_OVERRIDE| - NEIGH_UPDATE_F_ADMIN); - neigh_release(n); + neigh = neigh_lookup(tbl, nla_data(dst_attr), dev); + if (neigh == NULL) { + err = -ENOENT; + goto out_dev_put; } + + err = neigh_update(neigh, NULL, NUD_FAILED, + NEIGH_UPDATE_F_OVERRIDE | + NEIGH_UPDATE_F_ADMIN); + neigh_release(neigh); goto out_dev_put; } read_unlock(&neigh_tbl_lock); - err = -EADDRNOTAVAIL; + err = -EAFNOSUPPORT; + out_dev_put: if (dev) dev_put(dev); -- cgit v1.2.3-70-g09d2 From 5208debd0f1da07bbb350f8b0b142775d4f002ea Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Mon, 7 Aug 2006 17:55:40 -0700 Subject: [NEIGH]: Convert neighbour addition to new netlink api Fixes: Return EAFNOSUPPORT if no table matches the specified address family. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/core/neighbour.c | 90 +++++++++++++++++++++++++++++----------------------- 1 file changed, 51 insertions(+), 39 deletions(-) (limited to 'net/core') diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 39c07cc66ee..6036f43c1fd 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1506,76 +1506,88 @@ out: int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct ndmsg *ndm = NLMSG_DATA(nlh); - struct rtattr **nda = arg; + struct ndmsg *ndm; + struct nlattr *tb[NDA_MAX+1]; struct neigh_table *tbl; struct net_device *dev = NULL; - int err = -ENODEV; + int err; + + err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); + if (err < 0) + goto out; - if (ndm->ndm_ifindex && - (dev = dev_get_by_index(ndm->ndm_ifindex)) == NULL) + err = -EINVAL; + if (tb[NDA_DST] == NULL) goto out; + ndm = nlmsg_data(nlh); + if (ndm->ndm_ifindex) { + dev = dev_get_by_index(ndm->ndm_ifindex); + if (dev == NULL) { + err = -ENODEV; + goto out; + } + + if (tb[NDA_LLADDR] && nla_len(tb[NDA_LLADDR]) < dev->addr_len) + goto out_dev_put; + } + read_lock(&neigh_tbl_lock); for (tbl = neigh_tables; tbl; tbl = tbl->next) { - struct rtattr *lladdr_attr = nda[NDA_LLADDR - 1]; - struct rtattr *dst_attr = nda[NDA_DST - 1]; - int override = 1; - struct neighbour *n; + int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE; + struct neighbour *neigh; + void *dst, *lladdr; if (tbl->family != ndm->ndm_family) continue; read_unlock(&neigh_tbl_lock); - err = -EINVAL; - if (!dst_attr || RTA_PAYLOAD(dst_attr) < tbl->key_len) + if (nla_len(tb[NDA_DST]) < tbl->key_len) goto out_dev_put; + dst = nla_data(tb[NDA_DST]); + lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL; if (ndm->ndm_flags & NTF_PROXY) { - err = -ENOBUFS; - if (pneigh_lookup(tbl, RTA_DATA(dst_attr), dev, 1)) - err = 0; + err = 0; + if (pneigh_lookup(tbl, dst, dev, 1) == NULL) + err = -ENOBUFS; goto out_dev_put; } - err = -EINVAL; - if (!dev) - goto out; - if (lladdr_attr && RTA_PAYLOAD(lladdr_attr) < dev->addr_len) + if (dev == NULL) goto out_dev_put; + + neigh = neigh_lookup(tbl, dst, dev); + if (neigh == NULL) { + if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { + err = -ENOENT; + goto out_dev_put; + } - n = neigh_lookup(tbl, RTA_DATA(dst_attr), dev); - if (n) { - if (nlh->nlmsg_flags & NLM_F_EXCL) { - err = -EEXIST; - neigh_release(n); + neigh = __neigh_lookup_errno(tbl, dst, dev); + if (IS_ERR(neigh)) { + err = PTR_ERR(neigh); goto out_dev_put; } - - override = nlh->nlmsg_flags & NLM_F_REPLACE; - } else if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { - err = -ENOENT; - goto out_dev_put; } else { - n = __neigh_lookup_errno(tbl, RTA_DATA(dst_attr), dev); - if (IS_ERR(n)) { - err = PTR_ERR(n); + if (nlh->nlmsg_flags & NLM_F_EXCL) { + err = -EEXIST; + neigh_release(neigh); goto out_dev_put; } - } - err = neigh_update(n, - lladdr_attr ? RTA_DATA(lladdr_attr) : NULL, - ndm->ndm_state, - (override ? NEIGH_UPDATE_F_OVERRIDE : 0) | - NEIGH_UPDATE_F_ADMIN); + if (!(nlh->nlmsg_flags & NLM_F_REPLACE)) + flags &= ~NEIGH_UPDATE_F_OVERRIDE; + } - neigh_release(n); + err = neigh_update(neigh, lladdr, ndm->ndm_state, flags); + neigh_release(neigh); goto out_dev_put; } read_unlock(&neigh_tbl_lock); - err = -EADDRNOTAVAIL; + err = -EAFNOSUPPORT; + out_dev_put: if (dev) dev_put(dev); -- cgit v1.2.3-70-g09d2 From 8b8aec508302d4e63fd88f47894805115277f70f Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Mon, 7 Aug 2006 17:56:37 -0700 Subject: [NEIGH]: Convert neighbour dumping to new netlink api Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/core/neighbour.c | 106 +++++++++++++++++++++++++-------------------------- 1 file changed, 51 insertions(+), 55 deletions(-) (limited to 'net/core') diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 6036f43c1fd..5490afd23b8 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1901,48 +1901,49 @@ out: return skb->len; } -static int neigh_fill_info(struct sk_buff *skb, struct neighbour *n, - u32 pid, u32 seq, int event, unsigned int flags) +static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, + u32 pid, u32 seq, int type, unsigned int flags) { unsigned long now = jiffies; - unsigned char *b = skb->tail; struct nda_cacheinfo ci; - int locked = 0; - u32 probes; - struct nlmsghdr *nlh = NLMSG_NEW(skb, pid, seq, event, - sizeof(struct ndmsg), flags); - struct ndmsg *ndm = NLMSG_DATA(nlh); + struct nlmsghdr *nlh; + struct ndmsg *ndm; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), flags); + if (nlh == NULL) + return -ENOBUFS; - ndm->ndm_family = n->ops->family; + ndm = nlmsg_data(nlh); + ndm->ndm_family = neigh->ops->family; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; - ndm->ndm_flags = n->flags; - ndm->ndm_type = n->type; - ndm->ndm_ifindex = n->dev->ifindex; - RTA_PUT(skb, NDA_DST, n->tbl->key_len, n->primary_key); - read_lock_bh(&n->lock); - locked = 1; - ndm->ndm_state = n->nud_state; - if (n->nud_state & NUD_VALID) - RTA_PUT(skb, NDA_LLADDR, n->dev->addr_len, n->ha); - ci.ndm_used = now - n->used; - ci.ndm_confirmed = now - n->confirmed; - ci.ndm_updated = now - n->updated; - ci.ndm_refcnt = atomic_read(&n->refcnt) - 1; - probes = atomic_read(&n->probes); - read_unlock_bh(&n->lock); - locked = 0; - RTA_PUT(skb, NDA_CACHEINFO, sizeof(ci), &ci); - RTA_PUT(skb, NDA_PROBES, sizeof(probes), &probes); - nlh->nlmsg_len = skb->tail - b; - return skb->len; + ndm->ndm_flags = neigh->flags; + ndm->ndm_type = neigh->type; + ndm->ndm_ifindex = neigh->dev->ifindex; -nlmsg_failure: -rtattr_failure: - if (locked) - read_unlock_bh(&n->lock); - skb_trim(skb, b - skb->data); - return -1; + NLA_PUT(skb, NDA_DST, neigh->tbl->key_len, neigh->primary_key); + + read_lock_bh(&neigh->lock); + ndm->ndm_state = neigh->nud_state; + if ((neigh->nud_state & NUD_VALID) && + nla_put(skb, NDA_LLADDR, neigh->dev->addr_len, neigh->ha) < 0) { + read_unlock_bh(&neigh->lock); + goto nla_put_failure; + } + + ci.ndm_used = now - neigh->used; + ci.ndm_confirmed = now - neigh->confirmed; + ci.ndm_updated = now - neigh->updated; + ci.ndm_refcnt = atomic_read(&neigh->refcnt) - 1; + read_unlock_bh(&neigh->lock); + + NLA_PUT_U32(skb, NDA_PROBES, atomic_read(&neigh->probes)); + NLA_PUT(skb, NDA_CACHEINFO, sizeof(ci), &ci); + + return nlmsg_end(skb, nlh); + +nla_put_failure: + return nlmsg_cancel(skb, nlh); } @@ -1986,7 +1987,7 @@ int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) int t, family, s_t; read_lock(&neigh_tbl_lock); - family = ((struct rtgenmsg *)NLMSG_DATA(cb->nlh))->rtgen_family; + family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family; s_t = cb->args[0]; for (tbl = neigh_tables, t = 0; tbl; tbl = tbl->next, t++) { @@ -2367,39 +2368,34 @@ static struct file_operations neigh_stat_seq_fops = { #ifdef CONFIG_ARPD void neigh_app_ns(struct neighbour *n) { - struct nlmsghdr *nlh; - int size = NLMSG_SPACE(sizeof(struct ndmsg) + 256); - struct sk_buff *skb = alloc_skb(size, GFP_ATOMIC); + struct sk_buff *skb; - if (!skb) + skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); + if (skb == NULL) return; - if (neigh_fill_info(skb, n, 0, 0, RTM_GETNEIGH, 0) < 0) { + if (neigh_fill_info(skb, n, 0, 0, RTM_GETNEIGH, NLM_F_REQUEST) <= 0) kfree_skb(skb); - return; + else { + NETLINK_CB(skb).dst_group = RTNLGRP_NEIGH; + netlink_broadcast(rtnl, skb, 0, RTNLGRP_NEIGH, GFP_ATOMIC); } - nlh = (struct nlmsghdr *)skb->data; - nlh->nlmsg_flags = NLM_F_REQUEST; - NETLINK_CB(skb).dst_group = RTNLGRP_NEIGH; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_NEIGH, GFP_ATOMIC); } static void neigh_app_notify(struct neighbour *n) { - struct nlmsghdr *nlh; - int size = NLMSG_SPACE(sizeof(struct ndmsg) + 256); - struct sk_buff *skb = alloc_skb(size, GFP_ATOMIC); + struct sk_buff *skb; - if (!skb) + skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); + if (skb == NULL) return; - if (neigh_fill_info(skb, n, 0, 0, RTM_NEWNEIGH, 0) < 0) { + if (neigh_fill_info(skb, n, 0, 0, RTM_NEWNEIGH, 0) <= 0) kfree_skb(skb); - return; + else { + NETLINK_CB(skb).dst_group = RTNLGRP_NEIGH; + netlink_broadcast(rtnl, skb, 0, RTNLGRP_NEIGH, GFP_ATOMIC); } - nlh = (struct nlmsghdr *)skb->data; - NETLINK_CB(skb).dst_group = RTNLGRP_NEIGH; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_NEIGH, GFP_ATOMIC); } #endif /* CONFIG_ARPD */ -- cgit v1.2.3-70-g09d2 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 --------------------------------------------- include/net/neighbour.h | 39 ++-------------------------- net/core/rtnetlink.c | 2 -- 4 files changed, 67 insertions(+), 102 deletions(-) create mode 100644 include/linux/neighbour.h (limited to 'net/core') diff --git a/include/linux/neighbour.h b/include/linux/neighbour.h new file mode 100644 index 00000000000..8e8293d86fb --- /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 84f3eb426da..9750f0214c2 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. * diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 4901ee44687..74c4b6ff8a5 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -1,6 +1,8 @@ #ifndef _NET_NEIGHBOUR_H #define _NET_NEIGHBOUR_H +#include + /* * Generic neighbour manipulation * @@ -14,40 +16,6 @@ * - Add neighbour cache statistics like rtstat */ -/* The following flags & states are exported to user space, - so that they should be moved to include/linux/ directory. - */ - -/* - * 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. - */ - -#ifdef __KERNEL__ - #include #include #include @@ -374,6 +342,3 @@ struct neighbour_cb { #define NEIGH_CB(skb) ((struct neighbour_cb *)(skb)->cb) #endif -#endif - - diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 93ba04fb844..78ccbd4c4e3 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -104,7 +104,6 @@ static const int rtm_min[RTM_NR_FAMILIES] = [RTM_FAM(RTM_NEWLINK)] = NLMSG_LENGTH(sizeof(struct ifinfomsg)), [RTM_FAM(RTM_NEWADDR)] = NLMSG_LENGTH(sizeof(struct ifaddrmsg)), [RTM_FAM(RTM_NEWROUTE)] = NLMSG_LENGTH(sizeof(struct rtmsg)), - [RTM_FAM(RTM_NEWNEIGH)] = NLMSG_LENGTH(sizeof(struct ndmsg)), [RTM_FAM(RTM_NEWRULE)] = NLMSG_LENGTH(sizeof(struct fib_rule_hdr)), [RTM_FAM(RTM_NEWQDISC)] = NLMSG_LENGTH(sizeof(struct tcmsg)), [RTM_FAM(RTM_NEWTCLASS)] = NLMSG_LENGTH(sizeof(struct tcmsg)), @@ -121,7 +120,6 @@ static const int rta_max[RTM_NR_FAMILIES] = [RTM_FAM(RTM_NEWLINK)] = IFLA_MAX, [RTM_FAM(RTM_NEWADDR)] = IFA_MAX, [RTM_FAM(RTM_NEWROUTE)] = RTA_MAX, - [RTM_FAM(RTM_NEWNEIGH)] = NDA_MAX, [RTM_FAM(RTM_NEWRULE)] = FRA_MAX, [RTM_FAM(RTM_NEWQDISC)] = TCA_MAX, [RTM_FAM(RTM_NEWTCLASS)] = TCA_MAX, -- cgit v1.2.3-70-g09d2 From 6b3f8674bccbb2e784d01e44373fb730af6cb149 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Mon, 7 Aug 2006 17:58:53 -0700 Subject: [NEIGH]: Convert neighbour table modification to new netlink api Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/core/neighbour.c | 172 +++++++++++++++++++++++++++++++-------------------- 1 file changed, 104 insertions(+), 68 deletions(-) (limited to 'net/core') diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 5490afd23b8..5a0b8f48a09 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1754,28 +1754,61 @@ static inline struct neigh_parms *lookup_neigh_params(struct neigh_table *tbl, return NULL; } +static struct nla_policy nl_neightbl_policy[NDTA_MAX+1] __read_mostly = { + [NDTA_NAME] = { .type = NLA_STRING }, + [NDTA_THRESH1] = { .type = NLA_U32 }, + [NDTA_THRESH2] = { .type = NLA_U32 }, + [NDTA_THRESH3] = { .type = NLA_U32 }, + [NDTA_GC_INTERVAL] = { .type = NLA_U64 }, + [NDTA_PARMS] = { .type = NLA_NESTED }, +}; + +static struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] __read_mostly = { + [NDTPA_IFINDEX] = { .type = NLA_U32 }, + [NDTPA_QUEUE_LEN] = { .type = NLA_U32 }, + [NDTPA_PROXY_QLEN] = { .type = NLA_U32 }, + [NDTPA_APP_PROBES] = { .type = NLA_U32 }, + [NDTPA_UCAST_PROBES] = { .type = NLA_U32 }, + [NDTPA_MCAST_PROBES] = { .type = NLA_U32 }, + [NDTPA_BASE_REACHABLE_TIME] = { .type = NLA_U64 }, + [NDTPA_GC_STALETIME] = { .type = NLA_U64 }, + [NDTPA_DELAY_PROBE_TIME] = { .type = NLA_U64 }, + [NDTPA_RETRANS_TIME] = { .type = NLA_U64 }, + [NDTPA_ANYCAST_DELAY] = { .type = NLA_U64 }, + [NDTPA_PROXY_DELAY] = { .type = NLA_U64 }, + [NDTPA_LOCKTIME] = { .type = NLA_U64 }, +}; + int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct neigh_table *tbl; - struct ndtmsg *ndtmsg = NLMSG_DATA(nlh); - struct rtattr **tb = arg; - int err = -EINVAL; + struct ndtmsg *ndtmsg; + struct nlattr *tb[NDTA_MAX+1]; + int err; - if (!tb[NDTA_NAME - 1] || !RTA_PAYLOAD(tb[NDTA_NAME - 1])) - return -EINVAL; + err = nlmsg_parse(nlh, sizeof(*ndtmsg), tb, NDTA_MAX, + nl_neightbl_policy); + if (err < 0) + goto errout; + + if (tb[NDTA_NAME] == NULL) { + err = -EINVAL; + goto errout; + } + ndtmsg = nlmsg_data(nlh); read_lock(&neigh_tbl_lock); for (tbl = neigh_tables; tbl; tbl = tbl->next) { if (ndtmsg->ndtm_family && tbl->family != ndtmsg->ndtm_family) continue; - if (!rtattr_strcmp(tb[NDTA_NAME - 1], tbl->id)) + if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0) break; } if (tbl == NULL) { err = -ENOENT; - goto errout; + goto errout_locked; } /* @@ -1784,86 +1817,89 @@ int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) */ write_lock_bh(&tbl->lock); - if (tb[NDTA_THRESH1 - 1]) - tbl->gc_thresh1 = RTA_GET_U32(tb[NDTA_THRESH1 - 1]); - - if (tb[NDTA_THRESH2 - 1]) - tbl->gc_thresh2 = RTA_GET_U32(tb[NDTA_THRESH2 - 1]); - - if (tb[NDTA_THRESH3 - 1]) - tbl->gc_thresh3 = RTA_GET_U32(tb[NDTA_THRESH3 - 1]); - - if (tb[NDTA_GC_INTERVAL - 1]) - tbl->gc_interval = RTA_GET_MSECS(tb[NDTA_GC_INTERVAL - 1]); - - if (tb[NDTA_PARMS - 1]) { - struct rtattr *tbp[NDTPA_MAX]; + if (tb[NDTA_PARMS]) { + struct nlattr *tbp[NDTPA_MAX+1]; struct neigh_parms *p; - u32 ifindex = 0; + int i, ifindex = 0; - if (rtattr_parse_nested(tbp, NDTPA_MAX, tb[NDTA_PARMS - 1]) < 0) - goto rtattr_failure; + err = nla_parse_nested(tbp, NDTPA_MAX, tb[NDTA_PARMS], + nl_ntbl_parm_policy); + if (err < 0) + goto errout_tbl_lock; - if (tbp[NDTPA_IFINDEX - 1]) - ifindex = RTA_GET_U32(tbp[NDTPA_IFINDEX - 1]); + if (tbp[NDTPA_IFINDEX]) + ifindex = nla_get_u32(tbp[NDTPA_IFINDEX]); p = lookup_neigh_params(tbl, ifindex); if (p == NULL) { err = -ENOENT; - goto rtattr_failure; + goto errout_tbl_lock; } - - if (tbp[NDTPA_QUEUE_LEN - 1]) - p->queue_len = RTA_GET_U32(tbp[NDTPA_QUEUE_LEN - 1]); - - if (tbp[NDTPA_PROXY_QLEN - 1]) - p->proxy_qlen = RTA_GET_U32(tbp[NDTPA_PROXY_QLEN - 1]); - - if (tbp[NDTPA_APP_PROBES - 1]) - p->app_probes = RTA_GET_U32(tbp[NDTPA_APP_PROBES - 1]); - - if (tbp[NDTPA_UCAST_PROBES - 1]) - p->ucast_probes = - RTA_GET_U32(tbp[NDTPA_UCAST_PROBES - 1]); - if (tbp[NDTPA_MCAST_PROBES - 1]) - p->mcast_probes = - RTA_GET_U32(tbp[NDTPA_MCAST_PROBES - 1]); - - if (tbp[NDTPA_BASE_REACHABLE_TIME - 1]) - p->base_reachable_time = - RTA_GET_MSECS(tbp[NDTPA_BASE_REACHABLE_TIME - 1]); - - if (tbp[NDTPA_GC_STALETIME - 1]) - p->gc_staletime = - RTA_GET_MSECS(tbp[NDTPA_GC_STALETIME - 1]); + for (i = 1; i <= NDTPA_MAX; i++) { + if (tbp[i] == NULL) + continue; - if (tbp[NDTPA_DELAY_PROBE_TIME - 1]) - p->delay_probe_time = - RTA_GET_MSECS(tbp[NDTPA_DELAY_PROBE_TIME - 1]); + switch (i) { + case NDTPA_QUEUE_LEN: + p->queue_len = nla_get_u32(tbp[i]); + break; + case NDTPA_PROXY_QLEN: + p->proxy_qlen = nla_get_u32(tbp[i]); + break; + case NDTPA_APP_PROBES: + p->app_probes = nla_get_u32(tbp[i]); + break; + case NDTPA_UCAST_PROBES: + p->ucast_probes = nla_get_u32(tbp[i]); + break; + case NDTPA_MCAST_PROBES: + p->mcast_probes = nla_get_u32(tbp[i]); + break; + case NDTPA_BASE_REACHABLE_TIME: + p->base_reachable_time = nla_get_msecs(tbp[i]); + break; + case NDTPA_GC_STALETIME: + p->gc_staletime = nla_get_msecs(tbp[i]); + break; + case NDTPA_DELAY_PROBE_TIME: + p->delay_probe_time = nla_get_msecs(tbp[i]); + break; + case NDTPA_RETRANS_TIME: + p->retrans_time = nla_get_msecs(tbp[i]); + break; + case NDTPA_ANYCAST_DELAY: + p->anycast_delay = nla_get_msecs(tbp[i]); + break; + case NDTPA_PROXY_DELAY: + p->proxy_delay = nla_get_msecs(tbp[i]); + break; + case NDTPA_LOCKTIME: + p->locktime = nla_get_msecs(tbp[i]); + break; + } + } + } - if (tbp[NDTPA_RETRANS_TIME - 1]) - p->retrans_time = - RTA_GET_MSECS(tbp[NDTPA_RETRANS_TIME - 1]); + if (tb[NDTA_THRESH1]) + tbl->gc_thresh1 = nla_get_u32(tb[NDTA_THRESH1]); - if (tbp[NDTPA_ANYCAST_DELAY - 1]) - p->anycast_delay = - RTA_GET_MSECS(tbp[NDTPA_ANYCAST_DELAY - 1]); + if (tb[NDTA_THRESH2]) + tbl->gc_thresh2 = nla_get_u32(tb[NDTA_THRESH2]); - if (tbp[NDTPA_PROXY_DELAY - 1]) - p->proxy_delay = - RTA_GET_MSECS(tbp[NDTPA_PROXY_DELAY - 1]); + if (tb[NDTA_THRESH3]) + tbl->gc_thresh3 = nla_get_u32(tb[NDTA_THRESH3]); - if (tbp[NDTPA_LOCKTIME - 1]) - p->locktime = RTA_GET_MSECS(tbp[NDTPA_LOCKTIME - 1]); - } + if (tb[NDTA_GC_INTERVAL]) + tbl->gc_interval = nla_get_msecs(tb[NDTA_GC_INTERVAL]); err = 0; -rtattr_failure: +errout_tbl_lock: write_unlock_bh(&tbl->lock); -errout: +errout_locked: read_unlock(&neigh_tbl_lock); +errout: return err; } -- cgit v1.2.3-70-g09d2 From ca860fb39b4aa1479e2fea67435a2c1eac9ce789 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Mon, 7 Aug 2006 18:00:18 -0700 Subject: [NEIGH]: Convert neighbour table dumping to new netlink api Also fixes skipping of already dumped neighbours. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/core/neighbour.c | 141 +++++++++++++++++++++++++++------------------------ 1 file changed, 74 insertions(+), 67 deletions(-) (limited to 'net/core') diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 5a0b8f48a09..2f4e06a1345 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1597,56 +1597,59 @@ out: static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) { - struct rtattr *nest = NULL; - - nest = RTA_NEST(skb, NDTA_PARMS); + struct nlattr *nest; + + nest = nla_nest_start(skb, NDTA_PARMS); + if (nest == NULL) + return -ENOBUFS; if (parms->dev) - RTA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex); - - RTA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)); - RTA_PUT_U32(skb, NDTPA_QUEUE_LEN, parms->queue_len); - RTA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen); - RTA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes); - RTA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes); - RTA_PUT_U32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes); - RTA_PUT_MSECS(skb, NDTPA_REACHABLE_TIME, parms->reachable_time); - RTA_PUT_MSECS(skb, NDTPA_BASE_REACHABLE_TIME, + NLA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex); + + NLA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)); + NLA_PUT_U32(skb, NDTPA_QUEUE_LEN, parms->queue_len); + NLA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen); + NLA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes); + NLA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes); + NLA_PUT_U32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes); + NLA_PUT_MSECS(skb, NDTPA_REACHABLE_TIME, parms->reachable_time); + NLA_PUT_MSECS(skb, NDTPA_BASE_REACHABLE_TIME, parms->base_reachable_time); - RTA_PUT_MSECS(skb, NDTPA_GC_STALETIME, parms->gc_staletime); - RTA_PUT_MSECS(skb, NDTPA_DELAY_PROBE_TIME, parms->delay_probe_time); - RTA_PUT_MSECS(skb, NDTPA_RETRANS_TIME, parms->retrans_time); - RTA_PUT_MSECS(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay); - RTA_PUT_MSECS(skb, NDTPA_PROXY_DELAY, parms->proxy_delay); - RTA_PUT_MSECS(skb, NDTPA_LOCKTIME, parms->locktime); + NLA_PUT_MSECS(skb, NDTPA_GC_STALETIME, parms->gc_staletime); + NLA_PUT_MSECS(skb, NDTPA_DELAY_PROBE_TIME, parms->delay_probe_time); + NLA_PUT_MSECS(skb, NDTPA_RETRANS_TIME, parms->retrans_time); + NLA_PUT_MSECS(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay); + NLA_PUT_MSECS(skb, NDTPA_PROXY_DELAY, parms->proxy_delay); + NLA_PUT_MSECS(skb, NDTPA_LOCKTIME, parms->locktime); - return RTA_NEST_END(skb, nest); + return nla_nest_end(skb, nest); -rtattr_failure: - return RTA_NEST_CANCEL(skb, nest); +nla_put_failure: + return nla_nest_cancel(skb, nest); } -static int neightbl_fill_info(struct neigh_table *tbl, struct sk_buff *skb, - struct netlink_callback *cb) +static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, + u32 pid, u32 seq, int type, int flags) { struct nlmsghdr *nlh; struct ndtmsg *ndtmsg; - nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWNEIGHTBL, sizeof(struct ndtmsg), - NLM_F_MULTI); + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndtmsg), flags); + if (nlh == NULL) + return -ENOBUFS; - ndtmsg = NLMSG_DATA(nlh); + ndtmsg = nlmsg_data(nlh); read_lock_bh(&tbl->lock); ndtmsg->ndtm_family = tbl->family; ndtmsg->ndtm_pad1 = 0; ndtmsg->ndtm_pad2 = 0; - RTA_PUT_STRING(skb, NDTA_NAME, tbl->id); - RTA_PUT_MSECS(skb, NDTA_GC_INTERVAL, tbl->gc_interval); - RTA_PUT_U32(skb, NDTA_THRESH1, tbl->gc_thresh1); - RTA_PUT_U32(skb, NDTA_THRESH2, tbl->gc_thresh2); - RTA_PUT_U32(skb, NDTA_THRESH3, tbl->gc_thresh3); + NLA_PUT_STRING(skb, NDTA_NAME, tbl->id); + NLA_PUT_MSECS(skb, NDTA_GC_INTERVAL, tbl->gc_interval); + NLA_PUT_U32(skb, NDTA_THRESH1, tbl->gc_thresh1); + NLA_PUT_U32(skb, NDTA_THRESH2, tbl->gc_thresh2); + NLA_PUT_U32(skb, NDTA_THRESH3, tbl->gc_thresh3); { unsigned long now = jiffies; @@ -1665,7 +1668,7 @@ static int neightbl_fill_info(struct neigh_table *tbl, struct sk_buff *skb, .ndtc_proxy_qlen = tbl->proxy_queue.qlen, }; - RTA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc); + NLA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc); } { @@ -1690,55 +1693,50 @@ static int neightbl_fill_info(struct neigh_table *tbl, struct sk_buff *skb, ndst.ndts_forced_gc_runs += st->forced_gc_runs; } - RTA_PUT(skb, NDTA_STATS, sizeof(ndst), &ndst); + NLA_PUT(skb, NDTA_STATS, sizeof(ndst), &ndst); } BUG_ON(tbl->parms.dev); if (neightbl_fill_parms(skb, &tbl->parms) < 0) - goto rtattr_failure; + goto nla_put_failure; read_unlock_bh(&tbl->lock); - return NLMSG_END(skb, nlh); + return nlmsg_end(skb, nlh); -rtattr_failure: +nla_put_failure: read_unlock_bh(&tbl->lock); - return NLMSG_CANCEL(skb, nlh); - -nlmsg_failure: - return -1; + return nlmsg_cancel(skb, nlh); } -static int neightbl_fill_param_info(struct neigh_table *tbl, +static int neightbl_fill_param_info(struct sk_buff *skb, + struct neigh_table *tbl, struct neigh_parms *parms, - struct sk_buff *skb, - struct netlink_callback *cb) + u32 pid, u32 seq, int type, + unsigned int flags) { struct ndtmsg *ndtmsg; struct nlmsghdr *nlh; - nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWNEIGHTBL, sizeof(struct ndtmsg), - NLM_F_MULTI); + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndtmsg), flags); + if (nlh == NULL) + return -ENOBUFS; - ndtmsg = NLMSG_DATA(nlh); + ndtmsg = nlmsg_data(nlh); read_lock_bh(&tbl->lock); ndtmsg->ndtm_family = tbl->family; ndtmsg->ndtm_pad1 = 0; ndtmsg->ndtm_pad2 = 0; - RTA_PUT_STRING(skb, NDTA_NAME, tbl->id); - if (neightbl_fill_parms(skb, parms) < 0) - goto rtattr_failure; + if (nla_put_string(skb, NDTA_NAME, tbl->id) < 0 || + neightbl_fill_parms(skb, parms) < 0) + goto errout; read_unlock_bh(&tbl->lock); - return NLMSG_END(skb, nlh); - -rtattr_failure: + return nlmsg_end(skb, nlh); +errout: read_unlock_bh(&tbl->lock); - return NLMSG_CANCEL(skb, nlh); - -nlmsg_failure: - return -1; + return nlmsg_cancel(skb, nlh); } static inline struct neigh_parms *lookup_neigh_params(struct neigh_table *tbl, @@ -1905,34 +1903,43 @@ errout: int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) { - int idx, family; - int s_idx = cb->args[0]; + int family, tidx, nidx = 0; + int tbl_skip = cb->args[0]; + int neigh_skip = cb->args[1]; struct neigh_table *tbl; - family = ((struct rtgenmsg *)NLMSG_DATA(cb->nlh))->rtgen_family; + family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family; read_lock(&neigh_tbl_lock); - for (tbl = neigh_tables, idx = 0; tbl; tbl = tbl->next) { + for (tbl = neigh_tables, tidx = 0; tbl; tbl = tbl->next, tidx++) { struct neigh_parms *p; - if (idx < s_idx || (family && tbl->family != family)) + if (tidx < tbl_skip || (family && tbl->family != family)) continue; - if (neightbl_fill_info(tbl, skb, cb) <= 0) + if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, RTM_NEWNEIGHTBL, + NLM_F_MULTI) <= 0) break; - for (++idx, p = tbl->parms.next; p; p = p->next, idx++) { - if (idx < s_idx) + for (nidx = 0, p = tbl->parms.next; p; p = p->next, nidx++) { + if (nidx < neigh_skip) continue; - if (neightbl_fill_param_info(tbl, p, skb, cb) <= 0) + if (neightbl_fill_param_info(skb, tbl, p, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGHTBL, + NLM_F_MULTI) <= 0) goto out; } + neigh_skip = 0; } out: read_unlock(&neigh_tbl_lock); - cb->args[0] = idx; + cb->args[0] = tidx; + cb->args[1] = nidx; return skb->len; } -- cgit v1.2.3-70-g09d2 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 ---------------------------------------------- net/core/rtnetlink.c | 2 - 3 files changed, 94 insertions(+), 103 deletions(-) (limited to 'net/core') diff --git a/include/linux/neighbour.h b/include/linux/neighbour.h index 8e8293d86fb..bd3bbf668cd 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 9750f0214c2..784a1a29490 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. ****/ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 78ccbd4c4e3..a1b783a6afc 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -112,7 +112,6 @@ static const int rtm_min[RTM_NR_FAMILIES] = [RTM_FAM(RTM_NEWPREFIX)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), [RTM_FAM(RTM_GETMULTICAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), [RTM_FAM(RTM_GETANYCAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), - [RTM_FAM(RTM_NEWNEIGHTBL)] = NLMSG_LENGTH(sizeof(struct ndtmsg)), }; static const int rta_max[RTM_NR_FAMILIES] = @@ -125,7 +124,6 @@ static const int rta_max[RTM_NR_FAMILIES] = [RTM_FAM(RTM_NEWTCLASS)] = TCA_MAX, [RTM_FAM(RTM_NEWTFILTER)] = TCA_MAX, [RTM_FAM(RTM_NEWACTION)] = TCAA_MAX, - [RTM_FAM(RTM_NEWNEIGHTBL)] = NDTA_MAX, }; void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data) -- cgit v1.2.3-70-g09d2 From bf0d52492d82ad70684e17c8a46942c13d0e140e Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Fri, 22 Sep 2006 14:00:29 -0700 Subject: [NET]: Remove unnecessary config.h includes from net/ config.h is automatically included by kbuild these days. Signed-off-by: Dave Jones Signed-off-by: David S. Miller --- net/atm/atm_sysfs.c | 1 - net/core/dev_mcast.c | 3 +-- net/core/wireless.c | 1 - net/ipv4/af_inet.c | 1 - net/ipv4/ipconfig.c | 1 - net/ipv4/netfilter/ip_conntrack_sip.c | 1 - net/ipv4/raw.c | 3 +-- net/ipv4/tcp_lp.c | 1 - net/ipv4/tcp_veno.c | 1 - 9 files changed, 2 insertions(+), 11 deletions(-) (limited to 'net/core') diff --git a/net/atm/atm_sysfs.c b/net/atm/atm_sysfs.c index 5df4b9a068b..c0a4ae28fcf 100644 --- a/net/atm/atm_sysfs.c +++ b/net/atm/atm_sysfs.c @@ -1,6 +1,5 @@ /* ATM driver model support. */ -#include #include #include #include diff --git a/net/core/dev_mcast.c b/net/core/dev_mcast.c index c57d887da2e..b22648d04d3 100644 --- a/net/core/dev_mcast.c +++ b/net/core/dev_mcast.c @@ -21,8 +21,7 @@ * 2 of the License, or (at your option) any later version. */ -#include -#include +#include #include #include #include diff --git a/net/core/wireless.c b/net/core/wireless.c index de0bde4b51d..348b9da73cc 100644 --- a/net/core/wireless.c +++ b/net/core/wireless.c @@ -72,7 +72,6 @@ /***************************** INCLUDES *****************************/ -#include /* Not needed ??? */ #include #include /* off_t */ #include /* struct ifreq, dev_get_by_name() */ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index fc40da3b6d3..36c38bffb47 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -67,7 +67,6 @@ * 2 of the License, or (at your option) any later version. */ -#include #include #include #include diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index cb8a92f18ef..1fbb38415b1 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -31,7 +31,6 @@ * -- Josef Siemes , Aug 2002 */ -#include #include #include #include diff --git a/net/ipv4/netfilter/ip_conntrack_sip.c b/net/ipv4/netfilter/ip_conntrack_sip.c index 4f222d6be00..2893e9c7485 100644 --- a/net/ipv4/netfilter/ip_conntrack_sip.c +++ b/net/ipv4/netfilter/ip_conntrack_sip.c @@ -8,7 +8,6 @@ * published by the Free Software Foundation. */ -#include #include #include #include diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index fe44cb50a1c..0e935b4c874 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -38,8 +38,7 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ - -#include + #include #include #include diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index 48f28d617ce..649ebaed1df 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -35,7 +35,6 @@ * Version: $Id: tcp_lp.c,v 1.24 2006/09/05 20:22:53 hswong3i Exp $ */ -#include #include #include diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index 11b42a7135c..5b2fe6d2aba 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -9,7 +9,6 @@ * See http://www.ntu.edu.sg/home5/ZHOU0022/papers/CPFu03a.pdf */ -#include #include #include #include -- cgit v1.2.3-70-g09d2 From 9e762a4a89b302cb3b26a1f9bb33eff459eaeca9 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 10 Aug 2006 23:09:48 -0700 Subject: [NET]: Introduce RTA_TABLE/FRA_TABLE attributes Introduce RTA_TABLE route attribute and FRA_TABLE routing rule attribute to hold 32 bit routing table IDs. Usespace compatibility is provided by continuing to accept and send the rtm_table field, but because of its limited size it can only carry the low 8 bits of the table ID. This implies that if larger IDs are used, _all_ userspace programs using them need to use RTA_TABLE. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/fib_rules.h | 4 ++++ include/linux/rtnetlink.h | 8 ++++++++ include/net/fib_rules.h | 7 +++++++ net/core/fib_rules.c | 5 +++-- net/decnet/dn_fib.c | 7 ++++--- net/decnet/dn_route.c | 1 + net/decnet/dn_table.c | 1 + net/ipv4/fib_frontend.c | 7 ++++--- net/ipv4/fib_rules.c | 1 + net/ipv4/fib_semantics.c | 1 + net/ipv4/route.c | 1 + net/ipv6/fib6_rules.c | 1 + net/ipv6/route.c | 13 +++++++++---- 13 files changed, 45 insertions(+), 12 deletions(-) (limited to 'net/core') diff --git a/include/linux/fib_rules.h b/include/linux/fib_rules.h index 5e503f0ca6e..19a82b6c1c1 100644 --- a/include/linux/fib_rules.h +++ b/include/linux/fib_rules.h @@ -36,6 +36,10 @@ enum FRA_UNUSED5, FRA_FWMARK, /* netfilter mark (IPv4) */ FRA_FLOW, /* flow/class id */ + FRA_UNUSED6, + FRA_UNUSED7, + FRA_UNUSED8, + FRA_TABLE, /* Extended table id */ __FRA_MAX }; diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 0aaffa2ae66..ea422a539a0 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -264,6 +264,7 @@ enum rtattr_type_t RTA_CACHEINFO, RTA_SESSION, RTA_MP_ALGO, + RTA_TABLE, __RTA_MAX }; @@ -717,6 +718,13 @@ extern void __rtnl_unlock(void); } \ } while(0) +static inline u32 rtm_get_table(struct rtattr **rta, u8 table) +{ + return RTA_GET_U32(rta[RTA_TABLE-1]); +rtattr_failure: + return table; +} + #endif /* __KERNEL__ */ diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 61375d9e53f..8e2f473d3e8 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -74,6 +74,13 @@ static inline void fib_rule_put(struct fib_rule *rule) call_rcu(&rule->rcu, fib_rule_put_rcu); } +static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla) +{ + if (nla[FRA_TABLE]) + return nla_get_u32(nla[FRA_TABLE]); + return frh->table; +} + extern int fib_rules_register(struct fib_rules_ops *); extern int fib_rules_unregister(struct fib_rules_ops *); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 6cdad24038e..873b04d5df8 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -187,7 +187,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) rule->action = frh->action; rule->flags = frh->flags; - rule->table = frh->table; + rule->table = frh_get_table(frh, tb); if (!rule->pref && ops->default_pref) rule->pref = ops->default_pref(); @@ -245,7 +245,7 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (frh->action && (frh->action != rule->action)) continue; - if (frh->table && (frh->table != rule->table)) + if (frh->table && (frh_get_table(frh, tb) != rule->table)) continue; if (tb[FRA_PRIORITY] && @@ -291,6 +291,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh = nlmsg_data(nlh); frh->table = rule->table; + NLA_PUT_U32(skb, FRA_TABLE, rule->table); frh->res1 = 0; frh->res2 = 0; frh->action = rule->action; diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 7b3bf5c3d72..fb596373daa 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -491,7 +491,8 @@ static int dn_fib_check_attr(struct rtmsg *r, struct rtattr **rta) if (attr) { if (RTA_PAYLOAD(attr) < 4 && RTA_PAYLOAD(attr) != 2) return -EINVAL; - if (i != RTA_MULTIPATH && i != RTA_METRICS) + if (i != RTA_MULTIPATH && i != RTA_METRICS && + i != RTA_TABLE) rta[i-1] = (struct rtattr *)RTA_DATA(attr); } } @@ -508,7 +509,7 @@ int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (dn_fib_check_attr(r, rta)) return -EINVAL; - tb = dn_fib_get_table(r->rtm_table, 0); + tb = dn_fib_get_table(rtm_get_table(rta, r->rtm_table), 0); if (tb) return tb->delete(tb, r, (struct dn_kern_rta *)rta, nlh, &NETLINK_CB(skb)); @@ -524,7 +525,7 @@ int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (dn_fib_check_attr(r, rta)) return -EINVAL; - tb = dn_fib_get_table(r->rtm_table, 1); + tb = dn_fib_get_table(rtm_get_table(rta, r->rtm_table), 1); if (tb) return tb->insert(tb, r, (struct dn_kern_rta *)rta, nlh, &NETLINK_CB(skb)); diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 5e6f4616ca1..4c963213fba 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1486,6 +1486,7 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, r->rtm_src_len = 0; r->rtm_tos = 0; r->rtm_table = RT_TABLE_MAIN; + RTA_PUT_U32(skb, RTA_TABLE, RT_TABLE_MAIN); r->rtm_type = rt->rt_type; r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; r->rtm_scope = RT_SCOPE_UNIVERSE; diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index 1601ee5406a..eca7c1e10c8 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -278,6 +278,7 @@ static int dn_fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, rtm->rtm_src_len = 0; rtm->rtm_tos = 0; rtm->rtm_table = tb_id; + RTA_PUT_U32(skb, RTA_TABLE, tb_id); rtm->rtm_flags = fi->fib_flags; rtm->rtm_scope = scope; rtm->rtm_type = type; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 06f4b23f6f5..2696ede52de 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -294,7 +294,8 @@ static int inet_check_attr(struct rtmsg *r, struct rtattr **rta) if (attr) { if (RTA_PAYLOAD(attr) < 4) return -EINVAL; - if (i != RTA_MULTIPATH && i != RTA_METRICS) + if (i != RTA_MULTIPATH && i != RTA_METRICS && + i != RTA_TABLE) *rta = (struct rtattr*)RTA_DATA(attr); } } @@ -310,7 +311,7 @@ int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (inet_check_attr(r, rta)) return -EINVAL; - tb = fib_get_table(r->rtm_table); + tb = fib_get_table(rtm_get_table(rta, r->rtm_table)); if (tb) return tb->tb_delete(tb, r, (struct kern_rta*)rta, nlh, &NETLINK_CB(skb)); return -ESRCH; @@ -325,7 +326,7 @@ int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (inet_check_attr(r, rta)) return -EINVAL; - tb = fib_new_table(r->rtm_table); + tb = fib_new_table(rtm_get_table(rta, r->rtm_table)); if (tb) return tb->tb_insert(tb, r, (struct kern_rta*)rta, nlh, &NETLINK_CB(skb)); return -ENOBUFS; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 58fb91b00fd..0330b9cc4b5 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -184,6 +184,7 @@ static struct nla_policy fib4_rule_policy[FRA_MAX+1] __read_mostly = { [FRA_DST] = { .type = NLA_U32 }, [FRA_FWMARK] = { .type = NLA_U32 }, [FRA_FLOW] = { .type = NLA_U32 }, + [FRA_TABLE] = { .type = NLA_U32 }, }; static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index c7a112b5a18..ab753df20a3 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -953,6 +953,7 @@ fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, rtm->rtm_src_len = 0; rtm->rtm_tos = tos; rtm->rtm_table = tb_id; + RTA_PUT_U32(skb, RTA_TABLE, tb_id); rtm->rtm_type = type; rtm->rtm_flags = fi->fib_flags; rtm->rtm_scope = scope; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index b873cbcdd0b..12128b82c9d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2652,6 +2652,7 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, r->rtm_src_len = 0; r->rtm_tos = rt->fl.fl4_tos; r->rtm_table = RT_TABLE_MAIN; + RTA_PUT_U32(skb, RTA_TABLE, RT_TABLE_MAIN); r->rtm_type = rt->rt_type; r->rtm_scope = RT_SCOPE_UNIVERSE; r->rtm_protocol = RTPROT_UNSPEC; diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 22a2fdb0983..2c4fbc855e6 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -129,6 +129,7 @@ static struct nla_policy fib6_rule_policy[RTA_MAX+1] __read_mostly = { [FRA_PRIORITY] = { .type = NLA_U32 }, [FRA_SRC] = { .minlen = sizeof(struct in6_addr) }, [FRA_DST] = { .minlen = sizeof(struct in6_addr) }, + [FRA_TABLE] = { .type = NLA_U32 }, }; static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e08d84063c1..843c5509fce 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1859,7 +1859,8 @@ int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (inet6_rtm_to_rtmsg(r, arg, &rtmsg)) return -EINVAL; - return ip6_route_del(&rtmsg, nlh, arg, &NETLINK_CB(skb), r->rtm_table); + return ip6_route_del(&rtmsg, nlh, arg, &NETLINK_CB(skb), + rtm_get_table(arg, r->rtm_table)); } int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) @@ -1869,7 +1870,8 @@ int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (inet6_rtm_to_rtmsg(r, arg, &rtmsg)) return -EINVAL; - return ip6_route_add(&rtmsg, nlh, arg, &NETLINK_CB(skb), r->rtm_table); + return ip6_route_add(&rtmsg, nlh, arg, &NETLINK_CB(skb), + rtm_get_table(arg, r->rtm_table)); } struct rt6_rtnl_dump_arg @@ -1887,6 +1889,7 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, struct nlmsghdr *nlh; unsigned char *b = skb->tail; struct rta_cacheinfo ci; + u32 table; if (prefix) { /* user wants prefix routes only */ if (!(rt->rt6i_flags & RTF_PREFIX_RT)) { @@ -1902,9 +1905,11 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, rtm->rtm_src_len = rt->rt6i_src.plen; rtm->rtm_tos = 0; if (rt->rt6i_table) - rtm->rtm_table = rt->rt6i_table->tb6_id; + table = rt->rt6i_table->tb6_id; else - rtm->rtm_table = RT6_TABLE_UNSPEC; + table = RT6_TABLE_UNSPEC; + rtm->rtm_table = table; + RTA_PUT_U32(skb, RTA_TABLE, table); if (rt->rt6i_flags&RTF_REJECT) rtm->rtm_type = RTN_UNREACHABLE; else if (rt->rt6i_dev && (rt->rt6i_dev->flags&IFF_LOOPBACK)) -- cgit v1.2.3-70-g09d2 From b6fe17d6cc5d570b72f8e4da351b593c5a680355 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Tue, 29 Aug 2006 17:06:13 -0700 Subject: [NET] netdev: Check name length Some improvements to robust name interface. These API's are safe now by convention, but it is worth providing some safety checks against future bugs. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/core/dev.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index fc82f6f6e1c..14de297d024 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -640,6 +640,8 @@ int dev_valid_name(const char *name) { if (*name == '\0') return 0; + if (strlen(name) >= IFNAMSIZ) + return 0; if (!strcmp(name, ".") || !strcmp(name, "..")) return 0; @@ -3191,13 +3193,15 @@ struct net_device *alloc_netdev(int sizeof_priv, const char *name, struct net_device *dev; int alloc_size; + BUG_ON(strlen(name) >= sizeof(dev->name)); + /* ensure 32-byte alignment of both the device and private area */ alloc_size = (sizeof(*dev) + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST; alloc_size += sizeof_priv + NETDEV_ALIGN_CONST; p = kzalloc(alloc_size, GFP_KERNEL); if (!p) { - printk(KERN_ERR "alloc_dev: Unable to allocate device.\n"); + printk(KERN_ERR "alloc_netdev: Unable to allocate device.\n"); return NULL; } -- cgit v1.2.3-70-g09d2 From 2942e90050569525628a9f34e0daaa9b661b49cc Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 15 Aug 2006 00:30:25 -0700 Subject: [RTNETLINK]: Use rtnl_unicast() for rtnetlink unicasts Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 1 + net/core/rtnetlink.c | 10 +++++++--- net/decnet/dn_route.c | 4 +--- net/ipv4/ipmr.c | 7 ++++--- net/ipv4/route.c | 7 +++---- net/ipv6/addrconf.c | 4 +--- net/ipv6/route.c | 4 +--- net/sched/act_api.c | 7 ++----- 8 files changed, 20 insertions(+), 24 deletions(-) (limited to 'net/core') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 7e4aa48680a..0e4f478e2cb 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -584,6 +584,7 @@ struct rtnetlink_link extern struct rtnetlink_link * rtnetlink_links[NPROTO]; 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 rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics); extern void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a1b783a6afc..e02fa6a33f4 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -166,6 +166,11 @@ int rtnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, int echo) return err; } +int rtnl_unicast(struct sk_buff *skb, u32 pid) +{ + return nlmsg_unicast(rtnl, skb, pid); +} + int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) { struct rtattr *mx = (struct rtattr*)skb->tail; @@ -574,9 +579,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) goto errout; } - err = netlink_unicast(rtnl, skb, NETLINK_CB(skb).pid, MSG_DONTWAIT); - if (err > 0) - err = 0; + err = rtnl_unicast(skb, NETLINK_CB(skb).pid); errout: kfree(iw_buf); dev_put(dev); @@ -825,3 +828,4 @@ EXPORT_SYMBOL(rtnl); EXPORT_SYMBOL(rtnl_lock); EXPORT_SYMBOL(rtnl_trylock); EXPORT_SYMBOL(rtnl_unlock); +EXPORT_SYMBOL(rtnl_unicast); diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 4c963213fba..c5daf3557c1 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1611,9 +1611,7 @@ int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void *arg) goto out_free; } - err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); - - return err; + return rtnl_unicast(skb, NETLINK_CB(in_skb).pid); out_free: kfree_skb(skb); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 85893eef6b1..98f0aa0d421 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -312,7 +312,8 @@ static void ipmr_destroy_unres(struct mfc_cache *c) e = NLMSG_DATA(nlh); e->error = -ETIMEDOUT; memset(&e->msg, 0, sizeof(e->msg)); - netlink_unicast(rtnl, skb, NETLINK_CB(skb).dst_pid, MSG_DONTWAIT); + + rtnl_unicast(skb, NETLINK_CB(skb).pid); } else kfree_skb(skb); } @@ -512,7 +513,6 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c) while((skb=__skb_dequeue(&uc->mfc_un.unres.unresolved))) { if (skb->nh.iph->version == 0) { - int err; struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr)); if (ipmr_fill_mroute(skb, c, NLMSG_DATA(nlh)) > 0) { @@ -525,7 +525,8 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c) e->error = -EMSGSIZE; memset(&e->msg, 0, sizeof(e->msg)); } - err = netlink_unicast(rtnl, skb, NETLINK_CB(skb).dst_pid, MSG_DONTWAIT); + + rtnl_unicast(skb, NETLINK_CB(skb).pid); } else ip_mr_forward(skb, c, 0); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 12128b82c9d..b8f6cadc5b3 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2809,10 +2809,9 @@ int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) goto out_free; } - err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); - if (err > 0) - err = 0; -out: return err; + err = rtnl_unicast(skb, NETLINK_CB(in_skb).pid); +out: + return err; out_free: kfree_skb(skb); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 9ba1e811ba5..4f991a2234d 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3268,9 +3268,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, goto out_free; } - err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); - if (err > 0) - err = 0; + err = rtnl_unicast(skb, NETLINK_CB(in_skb).pid); out: in6_ifa_put(ifa); return err; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 9ce28277f47..024c8e26c2e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2044,9 +2044,7 @@ int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) goto out_free; } - err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); - if (err > 0) - err = 0; + err = rtnl_unicast(skb, NETLINK_CB(in_skb).pid); out: return err; out_free: diff --git a/net/sched/act_api.c b/net/sched/act_api.c index a2587b52e53..6990747d6d5 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -459,7 +459,6 @@ static int act_get_notify(u32 pid, struct nlmsghdr *n, struct tc_action *a, int event) { struct sk_buff *skb; - int err = 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) @@ -468,10 +467,8 @@ act_get_notify(u32 pid, struct nlmsghdr *n, struct tc_action *a, int event) kfree_skb(skb); return -EINVAL; } - err = netlink_unicast(rtnl, skb, pid, MSG_DONTWAIT); - if (err > 0) - err = 0; - return err; + + return rtnl_unicast(skb, pid); } static struct tc_action * -- cgit v1.2.3-70-g09d2 From 97676b6b5538b3e059d33b8338e7d5cc41c5f1f1 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 15 Aug 2006 00:31:41 -0700 Subject: [RTNETLINK]: Add rtnetlink notification interface Adds rtnl_notify() to send rtnetlink notification messages and rtnl_set_sk_err() to report notification errors as socket errors in order to indicate the need of a resync due to loss of events. nlmsg_report() is added to properly document the meaning of NLM_F_ECHO. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 3 +++ include/net/netlink.h | 17 +++++++++++++++++ net/core/rtnetlink.c | 18 ++++++++++++++++++ 3 files changed, 38 insertions(+) (limited to 'net/core') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 0e4f478e2cb..ecbe0349060 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -585,6 +585,9 @@ struct rtnetlink_link extern struct rtnetlink_link * rtnetlink_links[NPROTO]; 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, + struct nlmsghdr *nlh, gfp_t flags); +extern void rtnl_set_sk_err(u32 group, int error); extern int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics); extern void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data); diff --git a/include/net/netlink.h b/include/net/netlink.h index b154b81d9a7..bf593eb59e1 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -65,6 +65,9 @@ * nlmsg_validate() validate netlink message incl. attrs * nlmsg_for_each_attr() loop over all attributes * + * Misc: + * nlmsg_report() report back to application? + * * ------------------------------------------------------------------------ * Attributes Interface * ------------------------------------------------------------------------ @@ -194,6 +197,9 @@ extern void netlink_run_queue(struct sock *sk, unsigned int *qlen, struct nlmsghdr *, int *)); extern void netlink_queue_skip(struct nlmsghdr *nlh, struct sk_buff *skb); +extern int nlmsg_notify(struct sock *sk, struct sk_buff *skb, + u32 pid, unsigned int group, int report, + gfp_t flags); extern int nla_validate(struct nlattr *head, int len, int maxtype, struct nla_policy *policy); @@ -375,6 +381,17 @@ static inline int nlmsg_validate(struct nlmsghdr *nlh, int hdrlen, int maxtype, nlmsg_attrlen(nlh, hdrlen), maxtype, policy); } +/** + * nlmsg_report - need to report back to application? + * @nlh: netlink message header + * + * Returns 1 if a report back to the application is requested. + */ +static inline int nlmsg_report(struct nlmsghdr *nlh) +{ + return !!(nlh->nlmsg_flags & NLM_F_ECHO); +} + /** * nlmsg_for_each_attr - iterate over a stream of attributes * @pos: loop counter, set to current attribute diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e02fa6a33f4..2b1af17e638 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -171,6 +171,22 @@ int rtnl_unicast(struct sk_buff *skb, u32 pid) return nlmsg_unicast(rtnl, skb, pid); } +int rtnl_notify(struct sk_buff *skb, u32 pid, u32 group, + struct nlmsghdr *nlh, gfp_t flags) +{ + int report = 0; + + if (nlh) + report = nlmsg_report(nlh); + + return nlmsg_notify(rtnl, skb, pid, group, report, flags); +} + +void rtnl_set_sk_err(u32 group, int error) +{ + netlink_set_err(rtnl, 0, group, error); +} + int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) { struct rtattr *mx = (struct rtattr*)skb->tail; @@ -829,3 +845,5 @@ EXPORT_SYMBOL(rtnl_lock); EXPORT_SYMBOL(rtnl_trylock); EXPORT_SYMBOL(rtnl_unlock); EXPORT_SYMBOL(rtnl_unicast); +EXPORT_SYMBOL(rtnl_notify); +EXPORT_SYMBOL(rtnl_set_sk_err); -- cgit v1.2.3-70-g09d2 From c17084d21c18497b506bd28b82d964bc9e6c424b Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 15 Aug 2006 00:32:48 -0700 Subject: [NET] fib_rules: Convert fib rule notification to use rtnl_notify() Adds support for NLM_F_ECHO to simplify the process of identifying inserted rules with an auto generated priority. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/core/fib_rules.c | 32 +++++++++++++++++++++----------- 1 file changed, 21 insertions(+), 11 deletions(-) (limited to 'net/core') diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 873b04d5df8..7b2e9bb1a60 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -18,7 +18,8 @@ static LIST_HEAD(rules_ops); static DEFINE_SPINLOCK(rules_mod_lock); static void notify_rule_change(int event, struct fib_rule *rule, - struct fib_rules_ops *ops); + struct fib_rules_ops *ops, struct nlmsghdr *nlh, + u32 pid); static struct fib_rules_ops *lookup_rules_ops(int family) { @@ -209,7 +210,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) else list_add_rcu(&rule->list, ops->rules_list); - notify_rule_change(RTM_NEWRULE, rule, ops); + notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).pid); rules_ops_put(ops); return 0; @@ -266,7 +267,8 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) list_del_rcu(&rule->list); synchronize_rcu(); - notify_rule_change(RTM_DELRULE, rule, ops); + notify_rule_change(RTM_DELRULE, rule, ops, nlh, + NETLINK_CB(skb).pid); fib_rule_put(rule); rules_ops_put(ops); return 0; @@ -344,18 +346,26 @@ skip: EXPORT_SYMBOL_GPL(fib_rules_dump); static void notify_rule_change(int event, struct fib_rule *rule, - struct fib_rules_ops *ops) + struct fib_rules_ops *ops, struct nlmsghdr *nlh, + u32 pid) { - int size = nlmsg_total_size(sizeof(struct fib_rule_hdr) + 128); - struct sk_buff *skb = alloc_skb(size, GFP_KERNEL); + struct sk_buff *skb; + int err = -ENOBUFS; + skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (skb == NULL) - netlink_set_err(rtnl, 0, ops->nlgroup, ENOBUFS); - else if (fib_nl_fill_rule(skb, rule, 0, 0, event, 0, ops) < 0) { + goto errout; + + err = fib_nl_fill_rule(skb, rule, pid, nlh->nlmsg_seq, event, 0, ops); + if (err < 0) { kfree_skb(skb); - netlink_set_err(rtnl, 0, ops->nlgroup, EINVAL); - } else - netlink_broadcast(rtnl, skb, 0, ops->nlgroup, GFP_KERNEL); + goto errout; + } + + err = rtnl_notify(skb, pid, ops->nlgroup, nlh, GFP_KERNEL); +errout: + if (err < 0) + rtnl_set_sk_err(ops->nlgroup, err); } static void attach_rules(struct list_head *rules, struct net_device *dev) -- cgit v1.2.3-70-g09d2 From b8673311804ca29680dd584bd08352001fcbe2f8 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 15 Aug 2006 00:33:14 -0700 Subject: [NEIGH]: Convert neighbour notifications ot use rtnl_notify() Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/core/neighbour.c | 35 +++++++++++++++++------------------ 1 file changed, 17 insertions(+), 18 deletions(-) (limited to 'net/core') diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 2f4e06a1345..23ae5e5426d 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2409,36 +2409,35 @@ static struct file_operations neigh_stat_seq_fops = { #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_ARPD -void neigh_app_ns(struct neighbour *n) +static void __neigh_notify(struct neighbour *n, int type, int flags) { struct sk_buff *skb; + int err = -ENOBUFS; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); if (skb == NULL) - return; + goto errout; - if (neigh_fill_info(skb, n, 0, 0, RTM_GETNEIGH, NLM_F_REQUEST) <= 0) + err = neigh_fill_info(skb, n, 0, 0, type, flags); + if (err < 0) { kfree_skb(skb); - else { - NETLINK_CB(skb).dst_group = RTNLGRP_NEIGH; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_NEIGH, GFP_ATOMIC); + goto errout; } + + err = rtnl_notify(skb, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); +errout: + if (err < 0) + rtnl_set_sk_err(RTNLGRP_NEIGH, err); } -static void neigh_app_notify(struct neighbour *n) +void neigh_app_ns(struct neighbour *n) { - struct sk_buff *skb; - - skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); - if (skb == NULL) - return; + __neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST); +} - if (neigh_fill_info(skb, n, 0, 0, RTM_NEWNEIGH, 0) <= 0) - kfree_skb(skb); - else { - NETLINK_CB(skb).dst_group = RTNLGRP_NEIGH; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_NEIGH, GFP_ATOMIC); - } +static void neigh_app_notify(struct neighbour *n) +{ + __neigh_notify(n, RTM_NEWNEIGH, 0); } #endif /* CONFIG_ARPD */ -- cgit v1.2.3-70-g09d2 From bd5785ba3ac1c89aa4c351ceb2acd96686424d8c Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 15 Aug 2006 00:36:49 -0700 Subject: [WIRELESS]: Convert notifications to use rtnl_notify() Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/core/wireless.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/wireless.c b/net/core/wireless.c index 348b9da73cc..3168fca312f 100644 --- a/net/core/wireless.c +++ b/net/core/wireless.c @@ -85,6 +85,7 @@ #include /* Pretty obvious */ #include /* New driver API */ +#include #include /* copy_to_user() */ @@ -1849,7 +1850,7 @@ static void wireless_nlevent_process(unsigned long data) struct sk_buff *skb; while ((skb = skb_dequeue(&wireless_nlevent_queue))) - netlink_broadcast(rtnl, skb, 0, RTNLGRP_LINK, GFP_ATOMIC); + rtnl_notify(skb, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); } static DECLARE_TASKLET(wireless_nlevent_tasklet, wireless_nlevent_process, 0); -- cgit v1.2.3-70-g09d2 From 0ec6d3f467faeec5dd3b617959eb90e9d520113d Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 15 Aug 2006 00:37:09 -0700 Subject: [NET] link: Convert notifications to use rtnl_notify() Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2b1af17e638..f5300b5dd0f 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -630,20 +630,22 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change) { struct sk_buff *skb; - int size = NLMSG_SPACE(sizeof(struct ifinfomsg) + - sizeof(struct rtnl_link_ifmap) + - sizeof(struct rtnl_link_stats) + 128); + int err = -ENOBUFS; - skb = nlmsg_new(size, GFP_KERNEL); - if (!skb) - return; + skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (skb == NULL) + goto errout; - if (rtnl_fill_ifinfo(skb, dev, NULL, 0, type, 0, 0, change, 0) < 0) { + err = rtnl_fill_ifinfo(skb, dev, NULL, 0, type, 0, 0, change, 0); + if (err < 0) { kfree_skb(skb); - return; + goto errout; } - NETLINK_CB(skb).dst_group = RTNLGRP_LINK; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_LINK, GFP_KERNEL); + + err = rtnl_notify(skb, 0, RTNLGRP_LINK, NULL, GFP_KERNEL); +errout: + if (err < 0) + rtnl_set_sk_err(RTNLGRP_LINK, err); } /* Protected by RTNL sempahore. */ -- cgit v1.2.3-70-g09d2 From 56fc85ac961e2c20dcb5ef07e2628b3f93de2e49 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 15 Aug 2006 00:37:29 -0700 Subject: [RTNETLINK]: Unexport rtnl socket Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 2 -- net/core/rtnetlink.c | 4 +--- 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'net/core') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index ecbe0349060..9c92dc8b9a0 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -574,8 +574,6 @@ extern int rtattr_parse(struct rtattr *tb[], int maxattr, struct rtattr *rta, in #define rtattr_parse_nested(tb, max, rta) \ rtattr_parse((tb), (max), RTA_DATA((rta)), RTA_PAYLOAD((rta))) -extern struct sock *rtnl; - struct rtnetlink_link { int (*doit)(struct sk_buff *, struct nlmsghdr*, void *attr); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index f5300b5dd0f..dfc58269240 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -58,6 +58,7 @@ #endif /* CONFIG_NET_WIRELESS_RTNETLINK */ static DEFINE_MUTEX(rtnl_mutex); +static struct sock *rtnl; void rtnl_lock(void) { @@ -95,8 +96,6 @@ int rtattr_parse(struct rtattr *tb[], int maxattr, struct rtattr *rta, int len) return 0; } -struct sock *rtnl; - struct rtnetlink_link * rtnetlink_links[NPROTO]; static const int rtm_min[RTM_NR_FAMILIES] = @@ -842,7 +841,6 @@ EXPORT_SYMBOL(rtattr_strlcpy); EXPORT_SYMBOL(rtattr_parse); EXPORT_SYMBOL(rtnetlink_links); EXPORT_SYMBOL(rtnetlink_put_metrics); -EXPORT_SYMBOL(rtnl); EXPORT_SYMBOL(rtnl_lock); EXPORT_SYMBOL(rtnl_trylock); EXPORT_SYMBOL(rtnl_unlock); -- cgit v1.2.3-70-g09d2 From ab32ea5d8a760e7dd4339634e95d7be24ee5b842 Mon Sep 17 00:00:00 2001 From: Brian Haley Date: Fri, 22 Sep 2006 14:15:41 -0700 Subject: [NET/IPV4/IPV6]: Change some sysctl variables to __read_mostly Change net/core, ipv4 and ipv6 sysctl variables to __read_mostly. Couldn't actually measure any performance increase while testing (.3% I consider noise), but seems like the right thing to do. Signed-off-by: Brian Haley Signed-off-by: David S. Miller --- net/core/neighbour.c | 2 +- net/core/sock.c | 10 +++++----- net/ipv4/af_inet.c | 4 ++-- net/ipv4/icmp.c | 12 ++++++------ net/ipv4/igmp.c | 4 ++-- net/ipv4/ip_fragment.c | 10 +++++----- net/ipv4/ip_output.c | 2 +- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_input.c | 36 ++++++++++++++++++------------------ net/ipv4/tcp_ipv4.c | 4 ++-- net/ipv4/tcp_minisocks.c | 4 ++-- net/ipv4/tcp_output.c | 12 ++++++------ net/ipv4/tcp_timer.c | 16 ++++++++-------- net/ipv6/addrconf.c | 6 +++--- net/ipv6/af_inet6.c | 2 +- net/ipv6/icmp.c | 2 +- net/ipv6/mcast.c | 2 +- net/ipv6/reassembly.c | 8 ++++---- 18 files changed, 69 insertions(+), 69 deletions(-) (limited to 'net/core') diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 23ae5e5426d..c7e653ff5ed 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2451,7 +2451,7 @@ static struct neigh_sysctl_table { ctl_table neigh_neigh_dir[2]; ctl_table neigh_proto_dir[2]; ctl_table neigh_root_dir[2]; -} neigh_sysctl_template = { +} neigh_sysctl_template __read_mostly = { .neigh_vars = { { .ctl_name = NET_NEIGH_MCAST_SOLICIT, diff --git a/net/core/sock.c b/net/core/sock.c index b67d868649c..cfaf09039b0 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -187,13 +187,13 @@ static struct lock_class_key af_callback_keys[AF_MAX]; #define SK_RMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) /* Run time adjustable parameters. */ -__u32 sysctl_wmem_max = SK_WMEM_MAX; -__u32 sysctl_rmem_max = SK_RMEM_MAX; -__u32 sysctl_wmem_default = SK_WMEM_MAX; -__u32 sysctl_rmem_default = SK_RMEM_MAX; +__u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX; +__u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; +__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; +__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; /* Maximal space eaten by iovec or ancilliary data plus some space */ -int sysctl_optmem_max = sizeof(unsigned long)*(2*UIO_MAXIOV + 512); +int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) { diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 36c38bffb47..f2e8927f459 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -391,7 +391,7 @@ int inet_release(struct socket *sock) } /* It is off by default, see below. */ -int sysctl_ip_nonlocal_bind; +int sysctl_ip_nonlocal_bind __read_mostly; int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { @@ -987,7 +987,7 @@ void inet_unregister_protosw(struct inet_protosw *p) * Shall we try to damage output packets if routing dev changes? */ -int sysctl_ip_dynaddr; +int sysctl_ip_dynaddr __read_mostly; static int inet_sk_reselect_saddr(struct sock *sk) { diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 6d223e5c674..c2ad07e48ab 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -187,11 +187,11 @@ struct icmp_err icmp_err_convert[] = { }; /* Control parameters for ECHO replies. */ -int sysctl_icmp_echo_ignore_all; -int sysctl_icmp_echo_ignore_broadcasts = 1; +int sysctl_icmp_echo_ignore_all __read_mostly; +int sysctl_icmp_echo_ignore_broadcasts __read_mostly = 1; /* Control parameter - ignore bogus broadcast responses? */ -int sysctl_icmp_ignore_bogus_error_responses = 1; +int sysctl_icmp_ignore_bogus_error_responses __read_mostly = 1; /* * Configurable global rate limit. @@ -205,9 +205,9 @@ int sysctl_icmp_ignore_bogus_error_responses = 1; * time exceeded (11), parameter problem (12) */ -int sysctl_icmp_ratelimit = 1 * HZ; -int sysctl_icmp_ratemask = 0x1818; -int sysctl_icmp_errors_use_inbound_ifaddr; +int sysctl_icmp_ratelimit __read_mostly = 1 * HZ; +int sysctl_icmp_ratemask __read_mostly = 0x1818; +int sysctl_icmp_errors_use_inbound_ifaddr __read_mostly; /* * ICMP control array. This specifies what to do with each ICMP. diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 7003e763d97..58be8227b0c 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1397,8 +1397,8 @@ static struct in_device * ip_mc_find_dev(struct ip_mreqn *imr) /* * Join a socket to a group */ -int sysctl_igmp_max_memberships = IP_MAX_MEMBERSHIPS; -int sysctl_igmp_max_msf = IP_MAX_MSF; +int sysctl_igmp_max_memberships __read_mostly = IP_MAX_MEMBERSHIPS; +int sysctl_igmp_max_msf __read_mostly = IP_MAX_MSF; static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 8d7f107c2ee..165d72859dd 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -54,15 +54,15 @@ * even the most extreme cases without allowing an attacker to measurably * harm machine performance. */ -int sysctl_ipfrag_high_thresh = 256*1024; -int sysctl_ipfrag_low_thresh = 192*1024; +int sysctl_ipfrag_high_thresh __read_mostly = 256*1024; +int sysctl_ipfrag_low_thresh __read_mostly = 192*1024; -int sysctl_ipfrag_max_dist = 64; +int sysctl_ipfrag_max_dist __read_mostly = 64; /* Important NOTE! Fragment queue must be destroyed before MSL expires. * RFC791 is wrong proposing to prolongate timer each fragment arrival by TTL. */ -int sysctl_ipfrag_time = IP_FRAG_TIME; +int sysctl_ipfrag_time __read_mostly = IP_FRAG_TIME; struct ipfrag_skb_cb { @@ -130,7 +130,7 @@ static unsigned int ipqhashfn(u16 id, u32 saddr, u32 daddr, u8 prot) } static struct timer_list ipfrag_secret_timer; -int sysctl_ipfrag_secret_interval = 10 * 60 * HZ; +int sysctl_ipfrag_secret_interval __read_mostly = 10 * 60 * HZ; static void ipfrag_secret_rebuild(unsigned long dummy) { diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 1b9b6742ef7..81b2795a4c2 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -83,7 +83,7 @@ #include #include -int sysctl_ip_default_ttl = IPDEFTTL; +int sysctl_ip_default_ttl __read_mostly = IPDEFTTL; /* Generate a checksum for an outgoing IP datagram. */ __inline__ void ip_send_check(struct iphdr *iph) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b0124e69ab3..e570db4d33c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -268,7 +268,7 @@ #include #include -int sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT; +int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; DEFINE_SNMP_STAT(struct tcp_mib, tcp_statistics) __read_mostly; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 159fa3f1ba6..caf3c41dcc8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -72,24 +72,24 @@ #include #include -int sysctl_tcp_timestamps = 1; -int sysctl_tcp_window_scaling = 1; -int sysctl_tcp_sack = 1; -int sysctl_tcp_fack = 1; -int sysctl_tcp_reordering = TCP_FASTRETRANS_THRESH; -int sysctl_tcp_ecn; -int sysctl_tcp_dsack = 1; -int sysctl_tcp_app_win = 31; -int sysctl_tcp_adv_win_scale = 2; - -int sysctl_tcp_stdurg; -int sysctl_tcp_rfc1337; -int sysctl_tcp_max_orphans = NR_FILE; -int sysctl_tcp_frto; -int sysctl_tcp_nometrics_save; - -int sysctl_tcp_moderate_rcvbuf = 1; -int sysctl_tcp_abc; +int sysctl_tcp_timestamps __read_mostly = 1; +int sysctl_tcp_window_scaling __read_mostly = 1; +int sysctl_tcp_sack __read_mostly = 1; +int sysctl_tcp_fack __read_mostly = 1; +int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH; +int sysctl_tcp_ecn __read_mostly; +int sysctl_tcp_dsack __read_mostly = 1; +int sysctl_tcp_app_win __read_mostly = 31; +int sysctl_tcp_adv_win_scale __read_mostly = 2; + +int sysctl_tcp_stdurg __read_mostly; +int sysctl_tcp_rfc1337 __read_mostly; +int sysctl_tcp_max_orphans __read_mostly = NR_FILE; +int sysctl_tcp_frto __read_mostly; +int sysctl_tcp_nometrics_save __read_mostly; + +int sysctl_tcp_moderate_rcvbuf __read_mostly = 1; +int sysctl_tcp_abc __read_mostly; #define FLAG_DATA 0x01 /* Incoming frame contained data. */ #define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 2973dee0a48..23b46e36b14 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -78,8 +78,8 @@ #include #include -int sysctl_tcp_tw_reuse; -int sysctl_tcp_low_latency; +int sysctl_tcp_tw_reuse __read_mostly; +int sysctl_tcp_low_latency __read_mostly; /* Check TCP sequence numbers in ICMP packets. */ #define ICMP_MIN_LENGTH 8 diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 624e2b2c7f5..0163d982690 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -34,8 +34,8 @@ #define SYNC_INIT 1 #endif -int sysctl_tcp_syncookies = SYNC_INIT; -int sysctl_tcp_abort_on_overflow; +int sysctl_tcp_syncookies __read_mostly = SYNC_INIT; +int sysctl_tcp_abort_on_overflow __read_mostly; struct inet_timewait_death_row tcp_death_row = { .sysctl_max_tw_buckets = NR_FILE * 2, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 9252a50c4b4..061edfae0c2 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -43,24 +43,24 @@ #include /* People can turn this off for buggy TCP's found in printers etc. */ -int sysctl_tcp_retrans_collapse = 1; +int sysctl_tcp_retrans_collapse __read_mostly = 1; /* People can turn this on to work with those rare, broken TCPs that * interpret the window field as a signed quantity. */ -int sysctl_tcp_workaround_signed_windows = 0; +int sysctl_tcp_workaround_signed_windows __read_mostly = 0; /* This limits the percentage of the congestion window which we * will allow a single TSO frame to consume. Building TSO frames * which are too large can cause TCP streams to be bursty. */ -int sysctl_tcp_tso_win_divisor = 3; +int sysctl_tcp_tso_win_divisor __read_mostly = 3; -int sysctl_tcp_mtu_probing = 0; -int sysctl_tcp_base_mss = 512; +int sysctl_tcp_mtu_probing __read_mostly = 0; +int sysctl_tcp_base_mss __read_mostly = 512; /* By default, RFC2861 behavior. */ -int sysctl_tcp_slow_start_after_idle = 1; +int sysctl_tcp_slow_start_after_idle __read_mostly = 1; static void update_send_head(struct sock *sk, struct tcp_sock *tp, struct sk_buff *skb) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 7c1bde3cd6c..fb09ade5897 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -23,14 +23,14 @@ #include #include -int sysctl_tcp_syn_retries = TCP_SYN_RETRIES; -int sysctl_tcp_synack_retries = TCP_SYNACK_RETRIES; -int sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME; -int sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES; -int sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL; -int sysctl_tcp_retries1 = TCP_RETR1; -int sysctl_tcp_retries2 = TCP_RETR2; -int sysctl_tcp_orphan_retries; +int sysctl_tcp_syn_retries __read_mostly = TCP_SYN_RETRIES; +int sysctl_tcp_synack_retries __read_mostly = TCP_SYNACK_RETRIES; +int sysctl_tcp_keepalive_time __read_mostly = TCP_KEEPALIVE_TIME; +int sysctl_tcp_keepalive_probes __read_mostly = TCP_KEEPALIVE_PROBES; +int sysctl_tcp_keepalive_intvl __read_mostly = TCP_KEEPALIVE_INTVL; +int sysctl_tcp_retries1 __read_mostly = TCP_RETR1; +int sysctl_tcp_retries2 __read_mostly = TCP_RETR2; +int sysctl_tcp_orphan_retries __read_mostly; static void tcp_write_timer(unsigned long); static void tcp_delack_timer(unsigned long); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 4af741ef8d6..f1ede900488 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -146,7 +146,7 @@ static int ipv6_chk_same_addr(const struct in6_addr *addr, struct net_device *de static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); -struct ipv6_devconf ipv6_devconf = { +struct ipv6_devconf ipv6_devconf __read_mostly = { .forwarding = 0, .hop_limit = IPV6_DEFAULT_HOPLIMIT, .mtu6 = IPV6_MIN_MTU, @@ -177,7 +177,7 @@ struct ipv6_devconf ipv6_devconf = { #endif }; -static struct ipv6_devconf ipv6_devconf_dflt = { +static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .forwarding = 0, .hop_limit = IPV6_DEFAULT_HOPLIMIT, .mtu6 = IPV6_MIN_MTU, @@ -3665,7 +3665,7 @@ static struct addrconf_sysctl_table ctl_table addrconf_conf_dir[2]; ctl_table addrconf_proto_dir[2]; ctl_table addrconf_root_dir[2]; -} addrconf_sysctl = { +} addrconf_sysctl __read_mostly = { .sysctl_header = NULL, .addrconf_vars = { { diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 82a1b1a328d..2ff600cfe3a 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -67,7 +67,7 @@ MODULE_AUTHOR("Cast of dozens"); MODULE_DESCRIPTION("IPv6 protocol stack for Linux"); MODULE_LICENSE("GPL"); -int sysctl_ipv6_bindv6only; +int sysctl_ipv6_bindv6only __read_mostly; /* The inetsw table contains everything that inet_create needs to * build a new socket. diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 10305510767..e3a8e27af95 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -151,7 +151,7 @@ static int is_ineligible(struct sk_buff *skb) return 0; } -static int sysctl_icmpv6_time = 1*HZ; +static int sysctl_icmpv6_time __read_mostly = 1*HZ; /* * Check the ICMP output rate limit diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 639eb20c9f1..3b114e3fa2f 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -171,7 +171,7 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, #define IPV6_MLD_MAX_MSF 64 -int sysctl_mld_max_msf = IPV6_MLD_MAX_MSF; +int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF; /* * socket join on multicast group diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index a8623d2b087..f39bbedd132 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -53,10 +53,10 @@ #include #include -int sysctl_ip6frag_high_thresh = 256*1024; -int sysctl_ip6frag_low_thresh = 192*1024; +int sysctl_ip6frag_high_thresh __read_mostly = 256*1024; +int sysctl_ip6frag_low_thresh __read_mostly = 192*1024; -int sysctl_ip6frag_time = IPV6_FRAG_TIMEOUT; +int sysctl_ip6frag_time __read_mostly = IPV6_FRAG_TIMEOUT; struct ip6frag_skb_cb { @@ -152,7 +152,7 @@ static unsigned int ip6qhashfn(u32 id, struct in6_addr *saddr, } static struct timer_list ip6_frag_secret_timer; -int sysctl_ip6frag_secret_interval = 10 * 60 * HZ; +int sysctl_ip6frag_secret_interval __read_mostly = 10 * 60 * HZ; static void ip6_frag_secret_rebuild(unsigned long dummy) { -- cgit v1.2.3-70-g09d2 From e92b43a3455d3e817c13481bb3ea3cd29d0a47f4 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Thu, 17 Aug 2006 18:17:37 -0700 Subject: [NET] neighbour: reduce exports There are several symbols only used by rtnetlink and since it can not be a module, there is no reason to export them. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/core/neighbour.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'net/core') diff --git a/net/core/neighbour.c b/net/core/neighbour.c index c7e653ff5ed..c0a27407f44 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -889,7 +889,7 @@ out_unlock_bh: return rc; } -static __inline__ void neigh_update_hhs(struct neighbour *neigh) +static void neigh_update_hhs(struct neighbour *neigh) { struct hh_cache *hh; void (*update)(struct hh_cache*, struct net_device*, unsigned char *) = @@ -2724,7 +2724,6 @@ void neigh_sysctl_unregister(struct neigh_parms *p) #endif /* CONFIG_SYSCTL */ EXPORT_SYMBOL(__neigh_event_send); -EXPORT_SYMBOL(neigh_add); EXPORT_SYMBOL(neigh_changeaddr); EXPORT_SYMBOL(neigh_compat_output); EXPORT_SYMBOL(neigh_connected_output); @@ -2744,11 +2743,8 @@ EXPORT_SYMBOL(neigh_table_clear); EXPORT_SYMBOL(neigh_table_init); EXPORT_SYMBOL(neigh_table_init_no_netlink); EXPORT_SYMBOL(neigh_update); -EXPORT_SYMBOL(neigh_update_hhs); EXPORT_SYMBOL(pneigh_enqueue); EXPORT_SYMBOL(pneigh_lookup); -EXPORT_SYMBOL(neightbl_dump_info); -EXPORT_SYMBOL(neightbl_set); #ifdef CONFIG_ARPD EXPORT_SYMBOL(neigh_app_ns); -- cgit v1.2.3-70-g09d2 From 2d7202bfdd28687073f5efef8d2f51bbab0af867 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 22 Aug 2006 00:01:27 -0700 Subject: [IPv6] route: Convert FIB6 dumping to use new netlink api Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 31 ++++++++++++++++++------------- net/ipv6/route.c | 52 ++++++++++++++++++++++++++++------------------------ 2 files changed, 46 insertions(+), 37 deletions(-) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index dfc58269240..eeff0b23e94 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -188,22 +188,27 @@ void rtnl_set_sk_err(u32 group, int error) int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) { - struct rtattr *mx = (struct rtattr*)skb->tail; - int i; + struct nlattr *mx; + int i, valid = 0; + + mx = nla_nest_start(skb, RTA_METRICS); + if (mx == NULL) + return -ENOBUFS; - RTA_PUT(skb, RTA_METRICS, 0, NULL); - for (i=0; irta_len = skb->tail - (u8*)mx; - if (mx->rta_len == RTA_LENGTH(0)) - skb_trim(skb, (u8*)mx - skb->data); - return 0; -rtattr_failure: - skb_trim(skb, (u8*)mx - skb->data); - return -1; + if (!valid) + goto nla_put_failure; + + return nla_nest_end(skb, mx); + +nla_put_failure: + return nla_nest_cancel(skb, mx); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7bcffa6ddba..f0a66de8433 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1936,8 +1936,7 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, int prefix, unsigned int flags) { struct rtmsg *rtm; - struct nlmsghdr *nlh; - unsigned char *b = skb->tail; + struct nlmsghdr *nlh; struct rta_cacheinfo ci; u32 table; @@ -1948,8 +1947,11 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, } } - nlh = NLMSG_NEW(skb, pid, seq, type, sizeof(*rtm), flags); - rtm = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtm), flags); + if (nlh == NULL) + return -ENOBUFS; + + rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET6; rtm->rtm_dst_len = rt->rt6i_dst.plen; rtm->rtm_src_len = rt->rt6i_src.plen; @@ -1959,7 +1961,7 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, else table = RT6_TABLE_UNSPEC; rtm->rtm_table = table; - RTA_PUT_U32(skb, RTA_TABLE, table); + NLA_PUT_U32(skb, RTA_TABLE, table); if (rt->rt6i_flags&RTF_REJECT) rtm->rtm_type = RTN_UNREACHABLE; else if (rt->rt6i_dev && (rt->rt6i_dev->flags&IFF_LOOPBACK)) @@ -1980,31 +1982,35 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, rtm->rtm_flags |= RTM_F_CLONED; if (dst) { - RTA_PUT(skb, RTA_DST, 16, dst); + NLA_PUT(skb, RTA_DST, 16, dst); rtm->rtm_dst_len = 128; } else if (rtm->rtm_dst_len) - RTA_PUT(skb, RTA_DST, 16, &rt->rt6i_dst.addr); + NLA_PUT(skb, RTA_DST, 16, &rt->rt6i_dst.addr); #ifdef CONFIG_IPV6_SUBTREES if (src) { - RTA_PUT(skb, RTA_SRC, 16, src); + NLA_PUT(skb, RTA_SRC, 16, src); rtm->rtm_src_len = 128; } else if (rtm->rtm_src_len) - RTA_PUT(skb, RTA_SRC, 16, &rt->rt6i_src.addr); + NLA_PUT(skb, RTA_SRC, 16, &rt->rt6i_src.addr); #endif if (iif) - RTA_PUT(skb, RTA_IIF, 4, &iif); + NLA_PUT_U32(skb, RTA_IIF, iif); else if (dst) { struct in6_addr saddr_buf; if (ipv6_get_saddr(&rt->u.dst, dst, &saddr_buf) == 0) - RTA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); + NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); } + if (rtnetlink_put_metrics(skb, rt->u.dst.metrics) < 0) - goto rtattr_failure; + goto nla_put_failure; + if (rt->u.dst.neighbour) - RTA_PUT(skb, RTA_GATEWAY, 16, &rt->u.dst.neighbour->primary_key); + NLA_PUT(skb, RTA_GATEWAY, 16, &rt->u.dst.neighbour->primary_key); + if (rt->u.dst.dev) - RTA_PUT(skb, RTA_OIF, sizeof(int), &rt->rt6i_dev->ifindex); - RTA_PUT(skb, RTA_PRIORITY, 4, &rt->rt6i_metric); + NLA_PUT_U32(skb, RTA_OIF, rt->rt6i_dev->ifindex); + + NLA_PUT_U32(skb, RTA_PRIORITY, rt->rt6i_metric); ci.rta_lastuse = jiffies_to_clock_t(jiffies - rt->u.dst.lastuse); if (rt->rt6i_expires) ci.rta_expires = jiffies_to_clock_t(rt->rt6i_expires - jiffies); @@ -2016,14 +2022,12 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, ci.rta_id = 0; ci.rta_ts = 0; ci.rta_tsage = 0; - RTA_PUT(skb, RTA_CACHEINFO, sizeof(ci), &ci); - nlh->nlmsg_len = skb->tail - b; - return skb->len; + NLA_PUT(skb, RTA_CACHEINFO, sizeof(ci), &ci); + + return nlmsg_end(skb, nlh); -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; +nla_put_failure: + return nlmsg_cancel(skb, nlh); } int rt6_dump_route(struct rt6_info *rt, void *p_arg) @@ -2031,8 +2035,8 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg) struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg; int prefix; - if (arg->cb->nlh->nlmsg_len >= NLMSG_LENGTH(sizeof(struct rtmsg))) { - struct rtmsg *rtm = NLMSG_DATA(arg->cb->nlh); + if (nlmsg_len(arg->cb->nlh) >= sizeof(struct rtmsg)) { + struct rtmsg *rtm = nlmsg_data(arg->cb->nlh); prefix = (rtm->rtm_flags & RTM_F_PREFIX) != 0; } else prefix = 0; -- cgit v1.2.3-70-g09d2 From a57d27fc7107ddcc655ba2812cfebfce3163fd62 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 22 Aug 2006 22:20:14 -0700 Subject: [RTNETLINK]: Don't return error on no-metrics. Instead just cancel the nested attribute and return 0. Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index eeff0b23e94..8f225499e32 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -202,8 +202,10 @@ int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) } } - if (!valid) - goto nla_put_failure; + if (!valid) { + nla_nest_cancel(skb, mx); + return 0; + } return nla_nest_end(skb, mx); -- cgit v1.2.3-70-g09d2 From 1aaec67f9335a17856dfacdd3e5cc6f4c18faeec Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Sun, 25 Jun 2006 23:54:55 +0900 Subject: [NET]: Add common helper functions to convert IPv6/IPv4 address string to network address structure. These helpers can be used in netfilter, cifs etc. Signed-off-by: YOSHIFUJI Hideaki --- include/linux/inet.h | 2 + net/core/utils.c | 215 +++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 217 insertions(+) (limited to 'net/core') diff --git a/include/linux/inet.h b/include/linux/inet.h index 6c5587af118..b7c6da7d6d3 100644 --- a/include/linux/inet.h +++ b/include/linux/inet.h @@ -46,5 +46,7 @@ #include extern __be32 in_aton(const char *str); +extern int in4_pton(const char *src, int srclen, u8 *dst, char delim, const char **end); +extern int in6_pton(const char *src, int srclen, u8 *dst, char delim, const char **end); #endif #endif /* _LINUX_INET_H */ diff --git a/net/core/utils.c b/net/core/utils.c index e31c90e0559..5a06e8a72c1 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -4,6 +4,7 @@ * Authors: * net_random Alan Cox * net_ratelimit Andy Kleen + * in{4,6}_pton YOSHIFUJI Hideaki, Copyright (C)2006 USAGI/WIDE Project * * Created by Alexey Kuznetsov * @@ -191,3 +192,217 @@ __be32 in_aton(const char *str) } EXPORT_SYMBOL(in_aton); + +#define IN6PTON_XDIGIT 0x00010000 +#define IN6PTON_DIGIT 0x00020000 +#define IN6PTON_COLON_MASK 0x00700000 +#define IN6PTON_COLON_1 0x00100000 /* single : requested */ +#define IN6PTON_COLON_2 0x00200000 /* second : requested */ +#define IN6PTON_COLON_1_2 0x00400000 /* :: requested */ +#define IN6PTON_DOT 0x00800000 /* . */ +#define IN6PTON_DELIM 0x10000000 +#define IN6PTON_NULL 0x20000000 /* first/tail */ +#define IN6PTON_UNKNOWN 0x40000000 + +static inline int digit2bin(char c, char delim) +{ + if (c == delim || c == '\0') + return IN6PTON_DELIM; + if (c == '.') + return IN6PTON_DOT; + if (c >= '0' && c <= '9') + return (IN6PTON_DIGIT | (c - '0')); + return IN6PTON_UNKNOWN; +} + +static inline int xdigit2bin(char c, char delim) +{ + if (c == delim || c == '\0') + return IN6PTON_DELIM; + if (c == ':') + return IN6PTON_COLON_MASK; + if (c == '.') + return IN6PTON_DOT; + if (c >= '0' && c <= '9') + return (IN6PTON_XDIGIT | IN6PTON_DIGIT| (c - '0')); + if (c >= 'a' && c <= 'f') + return (IN6PTON_XDIGIT | (c - 'a' + 10)); + if (c >= 'A' && c <= 'F') + return (IN6PTON_XDIGIT | (c - 'A' + 10)); + return IN6PTON_UNKNOWN; +} + +int in4_pton(const char *src, int srclen, + u8 *dst, + char delim, const char **end) +{ + const char *s; + u8 *d; + u8 dbuf[4]; + int ret = 0; + int i; + int w = 0; + + if (srclen < 0) + srclen = strlen(src); + s = src; + d = dbuf; + i = 0; + while(1) { + int c; + c = xdigit2bin(srclen > 0 ? *s : '\0', delim); + if (!(c & (IN6PTON_DIGIT | IN6PTON_DOT | IN6PTON_DELIM))) { + goto out; + } + if (c & (IN6PTON_DOT | IN6PTON_DELIM)) { + if (w == 0) + goto out; + *d++ = w & 0xff; + w = 0; + i++; + if (c & IN6PTON_DELIM) { + if (i != 4) + goto out; + break; + } + goto cont; + } + w = (w * 10) + c; + if ((w & 0xffff) > 255) { + goto out; + } +cont: + if (i >= 4) + goto out; + s++; + srclen--; + } + ret = 1; + memcpy(dst, dbuf, sizeof(dbuf)); +out: + if (end) + *end = s; + return ret; +} + +EXPORT_SYMBOL(in4_pton); + +int in6_pton(const char *src, int srclen, + u8 *dst, + char delim, const char **end) +{ + const char *s, *tok = NULL; + u8 *d, *dc = NULL; + u8 dbuf[16]; + int ret = 0; + int i; + int state = IN6PTON_COLON_1_2 | IN6PTON_XDIGIT | IN6PTON_NULL; + int w = 0; + + memset(dbuf, 0, sizeof(dbuf)); + + s = src; + d = dbuf; + if (srclen < 0) + srclen = strlen(src); + + printf("srclen=%d\n", srclen); + + while (1) { + int c; + + c = xdigit2bin(srclen > 0 ? *s : '\0', delim); + if (!(c & state)) + goto out; + if (c & (IN6PTON_DELIM | IN6PTON_COLON_MASK)) { + /* process one 16-bit word */ + if (!(state & IN6PTON_NULL)) { + *d++ = (w >> 8) & 0xff; + *d++ = w & 0xff; + } + w = 0; + if (c & IN6PTON_DELIM) { + /* We've processed last word */ + break; + } + /* + * COLON_1 => XDIGIT + * COLON_2 => XDIGIT|DELIM + * COLON_1_2 => COLON_2 + */ + switch (state & IN6PTON_COLON_MASK) { + case IN6PTON_COLON_2: + dc = d; + state = IN6PTON_XDIGIT | IN6PTON_DELIM; + if (dc - dbuf >= sizeof(dbuf)) + state |= IN6PTON_NULL; + break; + case IN6PTON_COLON_1|IN6PTON_COLON_1_2: + state = IN6PTON_XDIGIT | IN6PTON_COLON_2; + break; + case IN6PTON_COLON_1: + state = IN6PTON_XDIGIT; + break; + case IN6PTON_COLON_1_2: + state = IN6PTON_COLON_2; + break; + default: + state = 0; + } + tok = s + 1; + goto cont; + } + + if (c & IN6PTON_DOT) { + ret = in4_pton(tok ? tok : s, srclen + (int)(s - tok), d, delim, &s); + if (ret > 0) { + d += 4; + break; + } + goto out; + } + + w = (w << 4) | (0xff & c); + state = IN6PTON_COLON_1 | IN6PTON_DELIM; + if (!(w & 0xf000)) { + state |= IN6PTON_XDIGIT; + } + if (!dc && d + 2 < dbuf + sizeof(dbuf)) { + state |= IN6PTON_COLON_1_2; + state &= ~IN6PTON_DELIM; + } + if (d + 2 >= dbuf + sizeof(dbuf)) { + state &= ~(IN6PTON_COLON_1|IN6PTON_COLON_1_2); + } +cont: + if ((dc && d + 4 < dbuf + sizeof(dbuf)) || + d + 4 == dbuf + sizeof(dbuf)) { + state |= IN6PTON_DOT; + } + if (d >= dbuf + sizeof(dbuf)) { + state &= ~(IN6PTON_XDIGIT|IN6PTON_COLON_MASK); + } + s++; + srclen--; + } + + i = 15; d--; + + if (dc) { + while(d >= dc) + dst[i--] = *d--; + while(i >= dc - dbuf) + dst[i--] = 0; + while(i >= 0) + dst[i--] = *d--; + } else + memcpy(dst, dbuf, sizeof(dbuf)); + + ret = 1; +out: + if (end) + *end = s; + return ret; +} + +EXPORT_SYMBOL(in6_pton); -- cgit v1.2.3-70-g09d2 From d4f3e9b735c72823aab597bfa4860d184658a609 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 25 Aug 2006 00:27:09 -0700 Subject: [NET] in6_pton: Kill errant printf statement. Signed-off-by: David S. Miller --- net/core/utils.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'net/core') diff --git a/net/core/utils.c b/net/core/utils.c index 5a06e8a72c1..2682490777d 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -306,8 +306,6 @@ int in6_pton(const char *src, int srclen, if (srclen < 0) srclen = strlen(src); - printf("srclen=%d\n", srclen); - while (1) { int c; -- cgit v1.2.3-70-g09d2 From e5d679f33900c71d1a76ba07c5b04055abd34480 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sat, 26 Aug 2006 19:25:52 -0700 Subject: [NET]: Use SLAB_PANIC Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- net/core/flow.c | 6 +----- net/core/neighbour.c | 12 ++++-------- net/core/skbuff.c | 9 ++------- net/decnet/dn_route.c | 11 +++-------- net/ipv4/inetpeer.c | 5 +---- net/ipv4/ipmr.c | 5 +---- net/ipv4/route.c | 10 +++------- net/ipv4/tcp.c | 4 +--- net/ipv6/ip6_fib.c | 4 +--- net/ipv6/route.c | 10 +++------- net/xfrm/xfrm_input.c | 4 +--- net/xfrm/xfrm_policy.c | 4 +--- 12 files changed, 22 insertions(+), 62 deletions(-) (limited to 'net/core') diff --git a/net/core/flow.c b/net/core/flow.c index 645241165e6..f23e7e38654 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -343,12 +343,8 @@ static int __init flow_cache_init(void) flow_cachep = kmem_cache_create("flow_cache", sizeof(struct flow_cache_entry), - 0, SLAB_HWCACHE_ALIGN, + 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - - if (!flow_cachep) - panic("NET: failed to allocate flow cache slab\n"); - flow_hash_shift = 10; flow_lwm = 2 * flow_hash_size; flow_hwm = 4 * flow_hash_size; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index c0a27407f44..a45bd2124d6 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1339,14 +1339,10 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl) neigh_rand_reach_time(tbl->parms.base_reachable_time); if (!tbl->kmem_cachep) - tbl->kmem_cachep = kmem_cache_create(tbl->id, - tbl->entry_size, - 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); - - if (!tbl->kmem_cachep) - panic("cannot create neighbour cache"); - + tbl->kmem_cachep = + kmem_cache_create(tbl->id, tbl->entry_size, 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, + NULL, NULL); tbl->stats = alloc_percpu(struct neigh_statistics); if (!tbl->stats) panic("cannot create neighbour cache statistics"); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8a476f1956e..c448c7f6fde 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2046,19 +2046,14 @@ void __init skb_init(void) skbuff_head_cache = kmem_cache_create("skbuff_head_cache", sizeof(struct sk_buff), 0, - SLAB_HWCACHE_ALIGN, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - if (!skbuff_head_cache) - panic("cannot create skbuff cache"); - skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", (2*sizeof(struct sk_buff)) + sizeof(atomic_t), 0, - SLAB_HWCACHE_ALIGN, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - if (!skbuff_fclone_cache) - panic("cannot create skbuff cache"); } EXPORT_SYMBOL(___pskb_trim); diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index c5daf3557c1..dd0761e3d28 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1781,14 +1781,9 @@ void __init dn_route_init(void) { int i, goal, order; - dn_dst_ops.kmem_cachep = kmem_cache_create("dn_dst_cache", - sizeof(struct dn_route), - 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); - - if (!dn_dst_ops.kmem_cachep) - panic("DECnet: Failed to allocate dn_dst_cache\n"); - + dn_dst_ops.kmem_cachep = + kmem_cache_create("dn_dst_cache", sizeof(struct dn_route), 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); init_timer(&dn_route_timer); dn_route_timer.function = dn_dst_check_expire; dn_route_timer.expires = jiffies + decnet_dst_gc_interval * HZ; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 03ff62ebcfe..a675602ef29 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -126,12 +126,9 @@ void __init inet_initpeers(void) peer_cachep = kmem_cache_create("inet_peer_cache", sizeof(struct inet_peer), - 0, SLAB_HWCACHE_ALIGN, + 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - if (!peer_cachep) - panic("cannot create inet_peer_cache"); - /* All the timers, started at system startup tend to synchronize. Perturb it a bit. */ diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 98f0aa0d421..ba49588da24 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1900,11 +1900,8 @@ void __init ip_mr_init(void) { mrt_cachep = kmem_cache_create("ip_mrt_cache", sizeof(struct mfc_cache), - 0, SLAB_HWCACHE_ALIGN, + 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - if (!mrt_cachep) - panic("cannot allocate ip_mrt_cache"); - init_timer(&ipmr_expire_timer); ipmr_expire_timer.function=ipmr_expire_process; register_netdevice_notifier(&ip_mr_notifier); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a4d4cb85a16..20ffe8e88c0 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3147,13 +3147,9 @@ int __init ip_rt_init(void) } #endif - ipv4_dst_ops.kmem_cachep = kmem_cache_create("ip_dst_cache", - sizeof(struct rtable), - 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); - - if (!ipv4_dst_ops.kmem_cachep) - panic("IP: failed to allocate ip_dst_cache\n"); + ipv4_dst_ops.kmem_cachep = + kmem_cache_create("ip_dst_cache", sizeof(struct rtable), 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); rt_hash_table = (struct rt_hash_bucket *) alloc_large_system_hash("IP route cache", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e570db4d33c..29e3d606db7 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2254,9 +2254,7 @@ void __init tcp_init(void) tcp_hashinfo.bind_bucket_cachep = kmem_cache_create("tcp_bind_bucket", sizeof(struct inet_bind_bucket), 0, - SLAB_HWCACHE_ALIGN, NULL, NULL); - if (!tcp_hashinfo.bind_bucket_cachep) - panic("tcp_init: Cannot alloc tcp_bind_bucket cache."); + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); /* Size and allocate the main established and bind bucket * hash tables. diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index fbca60950b1..8fcae7a6510 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1472,10 +1472,8 @@ void __init fib6_init(void) { fib6_node_kmem = kmem_cache_create("fib6_nodes", sizeof(struct fib6_node), - 0, SLAB_HWCACHE_ALIGN, + 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - if (!fib6_node_kmem) - panic("cannot create fib6_nodes cache"); fib6_tables_init(); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d83844d9499..ba1b3d11865 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2419,13 +2419,9 @@ void __init ip6_route_init(void) { struct proc_dir_entry *p; - ip6_dst_ops.kmem_cachep = kmem_cache_create("ip6_dst_cache", - sizeof(struct rt6_info), - 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); - if (!ip6_dst_ops.kmem_cachep) - panic("cannot create ip6_dst_cache"); - + ip6_dst_ops.kmem_cachep = + kmem_cache_create("ip6_dst_cache", sizeof(struct rt6_info), 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); fib6_init(); #ifdef CONFIG_PROC_FS p = proc_net_create("ipv6_route", 0, rt6_proc_info); diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 891a6090cc0..dfc90bb1cf1 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -82,8 +82,6 @@ void __init xfrm_input_init(void) { secpath_cachep = kmem_cache_create("secpath_cache", sizeof(struct sec_path), - 0, SLAB_HWCACHE_ALIGN, + 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - if (!secpath_cachep) - panic("XFRM: failed to allocate secpath_cache\n"); } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 1cf3209cdf4..7db1c48537f 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1985,10 +1985,8 @@ static void __init xfrm_policy_init(void) xfrm_dst_cache = kmem_cache_create("xfrm_dst_cache", sizeof(struct xfrm_dst), - 0, SLAB_HWCACHE_ALIGN, + 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - if (!xfrm_dst_cache) - panic("XFRM: failed to allocate xfrm_dst_cache\n"); hmask = 8 - 1; sz = (hmask+1) * sizeof(struct hlist_head); -- cgit v1.2.3-70-g09d2 From 5176f91ea83f1a59eba4dba88634a4729d51d1ac Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Sat, 26 Aug 2006 20:13:18 -0700 Subject: [NETLINK]: Make use of NLA_STRING/NLA_NUL_STRING attribute validation Converts existing NLA_STRING attributes to use the new validation features, saving a couple of temporary buffers. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/core/fib_rules.c | 8 +------- net/core/rtnetlink.c | 9 ++++----- net/decnet/dn_rules.c | 2 +- net/ipv4/devinet.c | 2 +- net/ipv4/fib_frontend.c | 2 +- net/ipv4/fib_rules.c | 2 +- net/ipv6/fib6_rules.c | 6 +++--- net/ipv6/route.c | 2 +- net/netlink/genetlink.c | 10 ++++------ 9 files changed, 17 insertions(+), 26 deletions(-) (limited to 'net/core') diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 7b2e9bb1a60..a99d87d82b7 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -161,9 +161,6 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (err < 0) goto errout; - if (tb[FRA_IFNAME] && nla_len(tb[FRA_IFNAME]) > IFNAMSIZ) - goto errout; - rule = kzalloc(ops->rule_size, GFP_KERNEL); if (rule == NULL) { err = -ENOMEM; @@ -177,10 +174,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) struct net_device *dev; rule->ifindex = -1; - if (nla_strlcpy(rule->ifname, tb[FRA_IFNAME], - IFNAMSIZ) >= IFNAMSIZ) - goto errout_free; - + nla_strlcpy(rule->ifname, tb[FRA_IFNAME], IFNAMSIZ); dev = __dev_get_by_name(rule->ifname); if (dev) rule->ifindex = dev->ifindex; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 8f225499e32..0ebcf8488e9 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -371,8 +371,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) } static struct nla_policy ifla_policy[IFLA_MAX+1] __read_mostly = { - [IFLA_IFNAME] = { .type = NLA_STRING }, - [IFLA_MAP] = { .minlen = sizeof(struct rtnl_link_ifmap) }, + [IFLA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ-1 }, + [IFLA_MAP] = { .len = sizeof(struct rtnl_link_ifmap) }, [IFLA_MTU] = { .type = NLA_U32 }, [IFLA_TXQLEN] = { .type = NLA_U32 }, [IFLA_WEIGHT] = { .type = NLA_U32 }, @@ -392,9 +392,8 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (err < 0) goto errout; - if (tb[IFLA_IFNAME] && - nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ) >= IFNAMSIZ) - return -EINVAL; + if (tb[IFLA_IFNAME]) + nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); err = -EINVAL; ifm = nlmsg_data(nlh); diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index 63ad63dfd25..3e0c882c90b 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -112,7 +112,7 @@ errout: } static struct nla_policy dn_fib_rule_policy[FRA_MAX+1] __read_mostly = { - [FRA_IFNAME] = { .type = NLA_STRING }, + [FRA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [FRA_PRIORITY] = { .type = NLA_U32 }, [FRA_SRC] = { .type = NLA_U16 }, [FRA_DST] = { .type = NLA_U16 }, diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 0487677729c..8e8d1f17d77 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -85,7 +85,7 @@ static struct nla_policy ifa_ipv4_policy[IFA_MAX+1] __read_mostly = { [IFA_ADDRESS] = { .type = NLA_U32 }, [IFA_BROADCAST] = { .type = NLA_U32 }, [IFA_ANYCAST] = { .type = NLA_U32 }, - [IFA_LABEL] = { .type = NLA_STRING }, + [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, }; static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index d0abeab16e6..cfb527c060e 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -462,7 +462,7 @@ struct nla_policy rtm_ipv4_policy[RTA_MAX+1] __read_mostly = { [RTA_PRIORITY] = { .type = NLA_U32 }, [RTA_PREFSRC] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, - [RTA_MULTIPATH] = { .minlen = sizeof(struct rtnexthop) }, + [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_PROTOINFO] = { .type = NLA_U32 }, [RTA_FLOW] = { .type = NLA_U32 }, [RTA_MP_ALGO] = { .type = NLA_U32 }, diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 280f424ca9c..52b2adae4f2 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -179,7 +179,7 @@ static struct fib_table *fib_empty_table(void) } static struct nla_policy fib4_rule_policy[FRA_MAX+1] __read_mostly = { - [FRA_IFNAME] = { .type = NLA_STRING }, + [FRA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [FRA_PRIORITY] = { .type = NLA_U32 }, [FRA_SRC] = { .type = NLA_U32 }, [FRA_DST] = { .type = NLA_U32 }, diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 2fbc71d9018..34f5bfaddfc 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -137,10 +137,10 @@ static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) } static struct nla_policy fib6_rule_policy[FRA_MAX+1] __read_mostly = { - [FRA_IFNAME] = { .type = NLA_STRING }, + [FRA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [FRA_PRIORITY] = { .type = NLA_U32 }, - [FRA_SRC] = { .minlen = sizeof(struct in6_addr) }, - [FRA_DST] = { .minlen = sizeof(struct in6_addr) }, + [FRA_SRC] = { .len = sizeof(struct in6_addr) }, + [FRA_DST] = { .len = sizeof(struct in6_addr) }, [FRA_FWMARK] = { .type = NLA_U32 }, [FRA_FWMASK] = { .type = NLA_U32 }, [FRA_TABLE] = { .type = NLA_U32 }, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index ba1b3d11865..75f4bb9611c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1865,7 +1865,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned mtu) } static struct nla_policy rtm_ipv6_policy[RTA_MAX+1] __read_mostly = { - [RTA_GATEWAY] = { .minlen = sizeof(struct in6_addr) }, + [RTA_GATEWAY] = { .len = sizeof(struct in6_addr) }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index d32599116c5..3ac942cdb67 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -455,7 +455,8 @@ static struct sk_buff *ctrl_build_msg(struct genl_family *family, u32 pid, static struct nla_policy ctrl_policy[CTRL_ATTR_MAX+1] __read_mostly = { [CTRL_ATTR_FAMILY_ID] = { .type = NLA_U16 }, - [CTRL_ATTR_FAMILY_NAME] = { .type = NLA_STRING }, + [CTRL_ATTR_FAMILY_NAME] = { .type = NLA_NUL_STRING, + .len = GENL_NAMSIZ - 1 }, }; static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info) @@ -470,12 +471,9 @@ static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info) } if (info->attrs[CTRL_ATTR_FAMILY_NAME]) { - char name[GENL_NAMSIZ]; - - if (nla_strlcpy(name, info->attrs[CTRL_ATTR_FAMILY_NAME], - GENL_NAMSIZ) >= GENL_NAMSIZ) - goto errout; + char *name; + name = nla_data(info->attrs[CTRL_ATTR_FAMILY_NAME]); res = genl_family_find_byname(name); } -- cgit v1.2.3-70-g09d2 From 3015d5d4e5b15eddea272a697e83391100581932 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Thu, 31 Aug 2006 15:04:30 -0700 Subject: [RTNETLINK]: Fix typo causing wrong skb to be freed A typo introduced by myself which leads to freeing the skb containing the netlink message when it should free the newly allocated skb for the reply. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 0ebcf8488e9..63b882ac288 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -596,7 +596,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) err = rtnl_fill_ifinfo(nskb, dev, iw, iw_buf_len, RTM_NEWLINK, NETLINK_CB(skb).pid, nlh->nlmsg_seq, 0, 0); if (err <= 0) { - kfree_skb(skb); + kfree_skb(nskb); goto errout; } -- cgit v1.2.3-70-g09d2 From fda9ef5d679b07c9d9097aaf6ef7f069d794a8f9 Mon Sep 17 00:00:00 2001 From: Dmitry Mishin Date: Thu, 31 Aug 2006 15:28:39 -0700 Subject: [NET]: Fix sk->sk_filter field access Function sk_filter() is called from tcp_v{4,6}_rcv() functions with arg needlock = 0, while socket is not locked at that moment. In order to avoid this and similar issues in the future, use rcu for sk->sk_filter field read protection. Signed-off-by: Dmitry Mishin Signed-off-by: Alexey Kuznetsov Signed-off-by: Kirill Korotaev --- include/linux/filter.h | 13 +++++++------ include/net/sock.h | 34 +++++++++++++++++----------------- net/core/filter.c | 8 ++++---- net/core/sock.c | 22 +++++++++------------- net/dccp/ipv6.c | 2 +- net/decnet/dn_nsp_in.c | 2 +- net/ipv4/tcp_ipv4.c | 2 +- net/ipv6/tcp_ipv6.c | 4 ++-- net/packet/af_packet.c | 43 ++++++++++++++++++------------------------- net/sctp/input.c | 2 +- 10 files changed, 61 insertions(+), 71 deletions(-) (limited to 'net/core') diff --git a/include/linux/filter.h b/include/linux/filter.h index c6cb8f09508..91b2e3b9251 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -25,10 +25,10 @@ struct sock_filter /* Filter block */ { - __u16 code; /* Actual filter code */ - __u8 jt; /* Jump true */ - __u8 jf; /* Jump false */ - __u32 k; /* Generic multiuse field */ + __u16 code; /* Actual filter code */ + __u8 jt; /* Jump true */ + __u8 jf; /* Jump false */ + __u32 k; /* Generic multiuse field */ }; struct sock_fprog /* Required for SO_ATTACH_FILTER. */ @@ -41,8 +41,9 @@ struct sock_fprog /* Required for SO_ATTACH_FILTER. */ struct sk_filter { atomic_t refcnt; - unsigned int len; /* Number of filter blocks */ - struct sock_filter insns[0]; + unsigned int len; /* Number of filter blocks */ + struct rcu_head rcu; + struct sock_filter insns[0]; }; static inline unsigned int sk_filter_len(struct sk_filter *fp) diff --git a/include/net/sock.h b/include/net/sock.h index 337ebec84c7..edd4d73ce7f 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -862,30 +862,24 @@ extern void sock_init_data(struct socket *sock, struct sock *sk); * */ -static inline int sk_filter(struct sock *sk, struct sk_buff *skb, int needlock) +static inline int sk_filter(struct sock *sk, struct sk_buff *skb) { int err; + struct sk_filter *filter; err = security_sock_rcv_skb(sk, skb); if (err) return err; - if (sk->sk_filter) { - struct sk_filter *filter; - - if (needlock) - bh_lock_sock(sk); - - filter = sk->sk_filter; - if (filter) { - unsigned int pkt_len = sk_run_filter(skb, filter->insns, - filter->len); - err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; - } - - if (needlock) - bh_unlock_sock(sk); + rcu_read_lock_bh(); + filter = sk->sk_filter; + if (filter) { + unsigned int pkt_len = sk_run_filter(skb, filter->insns, + filter->len); + err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; } + rcu_read_unlock_bh(); + return err; } @@ -897,6 +891,12 @@ static inline int sk_filter(struct sock *sk, struct sk_buff *skb, int needlock) * Remove a filter from a socket and release its resources. */ +static inline void sk_filter_rcu_free(struct rcu_head *rcu) +{ + struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); + kfree(fp); +} + static inline void sk_filter_release(struct sock *sk, struct sk_filter *fp) { unsigned int size = sk_filter_len(fp); @@ -904,7 +904,7 @@ static inline void sk_filter_release(struct sock *sk, struct sk_filter *fp) atomic_sub(size, &sk->sk_omem_alloc); if (atomic_dec_and_test(&fp->refcnt)) - kfree(fp); + call_rcu_bh(&fp->rcu, sk_filter_rcu_free); } static inline void sk_filter_charge(struct sock *sk, struct sk_filter *fp) diff --git a/net/core/filter.c b/net/core/filter.c index 5b4486a60cf..6732782a5a4 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -422,10 +422,10 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) if (!err) { struct sk_filter *old_fp; - spin_lock_bh(&sk->sk_lock.slock); - old_fp = sk->sk_filter; - sk->sk_filter = fp; - spin_unlock_bh(&sk->sk_lock.slock); + rcu_read_lock_bh(); + old_fp = rcu_dereference(sk->sk_filter); + rcu_assign_pointer(sk->sk_filter, fp); + rcu_read_unlock_bh(); fp = old_fp; } diff --git a/net/core/sock.c b/net/core/sock.c index cfaf09039b0..b77e155cbe6 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -247,11 +247,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) goto out; } - /* It would be deadlock, if sock_queue_rcv_skb is used - with socket lock! We assume that users of this - function are lock free. - */ - err = sk_filter(sk, skb, 1); + err = sk_filter(sk, skb); if (err) goto out; @@ -278,7 +274,7 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb) { int rc = NET_RX_SUCCESS; - if (sk_filter(sk, skb, 0)) + if (sk_filter(sk, skb)) goto discard_and_relse; skb->dev = NULL; @@ -606,15 +602,15 @@ set_rcvbuf: break; case SO_DETACH_FILTER: - spin_lock_bh(&sk->sk_lock.slock); - filter = sk->sk_filter; + rcu_read_lock_bh(); + filter = rcu_dereference(sk->sk_filter); if (filter) { - sk->sk_filter = NULL; - spin_unlock_bh(&sk->sk_lock.slock); + rcu_assign_pointer(sk->sk_filter, NULL); sk_filter_release(sk, filter); + rcu_read_unlock_bh(); break; } - spin_unlock_bh(&sk->sk_lock.slock); + rcu_read_unlock_bh(); ret = -ENONET; break; @@ -884,10 +880,10 @@ void sk_free(struct sock *sk) if (sk->sk_destruct) sk->sk_destruct(sk); - filter = sk->sk_filter; + filter = rcu_dereference(sk->sk_filter); if (filter) { sk_filter_release(sk, filter); - sk->sk_filter = NULL; + rcu_assign_pointer(sk->sk_filter, NULL); } sock_disable_timestamp(sk); diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index f9c5e12d703..7a47399cf31 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -970,7 +970,7 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (skb->protocol == htons(ETH_P_IP)) return dccp_v4_do_rcv(sk, skb); - if (sk_filter(sk, skb, 0)) + if (sk_filter(sk, skb)) goto discard; /* diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c index 86f7f3b28e7..72ecc6e62ec 100644 --- a/net/decnet/dn_nsp_in.c +++ b/net/decnet/dn_nsp_in.c @@ -586,7 +586,7 @@ static __inline__ int dn_queue_skb(struct sock *sk, struct sk_buff *skb, int sig goto out; } - err = sk_filter(sk, skb, 0); + err = sk_filter(sk, skb); if (err) goto out; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 23b46e36b14..39b17985608 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1104,7 +1104,7 @@ process: goto discard_and_relse; nf_reset(skb); - if (sk_filter(sk, skb, 0)) + if (sk_filter(sk, skb)) goto discard_and_relse; skb->dev = NULL; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2b18918f301..2546fc9f0a7 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1075,7 +1075,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_do_rcv(sk, skb); - if (sk_filter(sk, skb, 0)) + if (sk_filter(sk, skb)) goto discard; /* @@ -1232,7 +1232,7 @@ process: if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; - if (sk_filter(sk, skb, 0)) + if (sk_filter(sk, skb)) goto discard_and_relse; skb->dev = NULL; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 300215bdbf4..f4ccb90e673 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -427,21 +427,24 @@ out_unlock: } #endif -static inline unsigned run_filter(struct sk_buff *skb, struct sock *sk, unsigned res) +static inline int run_filter(struct sk_buff *skb, struct sock *sk, + unsigned *snaplen) { struct sk_filter *filter; + int err = 0; - bh_lock_sock(sk); - filter = sk->sk_filter; - /* - * Our caller already checked that filter != NULL but we need to - * verify that under bh_lock_sock() to be safe - */ - if (likely(filter != NULL)) - res = sk_run_filter(skb, filter->insns, filter->len); - bh_unlock_sock(sk); + rcu_read_lock_bh(); + filter = rcu_dereference(sk->sk_filter); + if (filter != NULL) { + err = sk_run_filter(skb, filter->insns, filter->len); + if (!err) + err = -EPERM; + else if (*snaplen > err) + *snaplen = err; + } + rcu_read_unlock_bh(); - return res; + return err; } /* @@ -491,13 +494,8 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet snaplen = skb->len; - if (sk->sk_filter) { - unsigned res = run_filter(skb, sk, snaplen); - if (res == 0) - goto drop_n_restore; - if (snaplen > res) - snaplen = res; - } + if (run_filter(skb, sk, &snaplen) < 0) + goto drop_n_restore; if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= (unsigned)sk->sk_rcvbuf) @@ -593,13 +591,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe snaplen = skb->len; - if (sk->sk_filter) { - unsigned res = run_filter(skb, sk, snaplen); - if (res == 0) - goto drop_n_restore; - if (snaplen > res) - snaplen = res; - } + if (run_filter(skb, sk, &snaplen) < 0) + goto drop_n_restore; if (sk->sk_type == SOCK_DGRAM) { macoff = netoff = TPACKET_ALIGN(TPACKET_HDRLEN) + 16; diff --git a/net/sctp/input.c b/net/sctp/input.c index 8a34d95602c..03f65de75d8 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -228,7 +228,7 @@ int sctp_rcv(struct sk_buff *skb) goto discard_release; nf_reset(skb); - if (sk_filter(sk, skb, 1)) + if (sk_filter(sk, skb)) goto discard_release; /* Create an SCTP packet structure. */ -- cgit v1.2.3-70-g09d2 From 78e5b8916e7db119850f57ce8548fbb9767078fc Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 13 Sep 2006 20:35:36 -0700 Subject: [RTNETLINK]: Fix netdevice name corruption When changing a device by ifindex without including a IFLA_IFNAME attribute, the ifname variable contains random garbage and is used to change the device name. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 63b882ac288..d8e25e08cb7 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -394,6 +394,8 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); + else + ifname[0] = '\0'; err = -EINVAL; ifm = nlmsg_data(nlh); -- cgit v1.2.3-70-g09d2 From 62dd93181aaa1d5a501a9cebcb254f44b8a48af7 Mon Sep 17 00:00:00 2001 From: Ville Nuorvala Date: Fri, 22 Sep 2006 14:43:19 -0700 Subject: [IPV6] NDISC: Set per-entry is_router flag in Proxy NA. We have sent NA with router flag from the node-wide forwarding configuration. This is not appropriate for proxy NA, and it should be set according to each proxy entry's configuration. This is used by Mobile IPv6 home agent to support physical home link in acting as a proxy router for mobile node which is not a router, for example. Based on MIPL2 kernel patch. Signed-off-by: Ville Nuorvala Signed-off-by: Masahide NAKAMURA Signed-off-by: YOSHIFUJI Hideaki --- include/net/neighbour.h | 1 + net/core/neighbour.c | 11 ++++++++--- net/ipv6/ndisc.c | 14 +++++++++++--- 3 files changed, 20 insertions(+), 6 deletions(-) (limited to 'net/core') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index bd187daffdb..c8aacbd2e33 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -126,6 +126,7 @@ struct pneigh_entry { struct pneigh_entry *next; struct net_device *dev; + u8 flags; u8 key[0]; }; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index a45bd2124d6..b6c69e1463e 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1544,9 +1544,14 @@ int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL; if (ndm->ndm_flags & NTF_PROXY) { - err = 0; - if (pneigh_lookup(tbl, dst, dev, 1) == NULL) - err = -ENOBUFS; + struct pneigh_entry *pn; + + err = -ENOBUFS; + pn = pneigh_lookup(tbl, dst, dev, 1); + if (pn) { + pn->flags = ndm->ndm_flags; + err = 0; + } goto out_dev_put; } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 0e0d6ce6902..ddf038636f0 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -736,8 +736,10 @@ static void ndisc_recv_ns(struct sk_buff *skb) struct inet6_ifaddr *ifp; struct inet6_dev *idev = NULL; struct neighbour *neigh; + struct pneigh_entry *pneigh = NULL; int dad = ipv6_addr_any(saddr); int inc; + int is_router; if (ipv6_addr_is_multicast(&msg->target)) { ND_PRINTK2(KERN_WARNING @@ -822,7 +824,8 @@ static void ndisc_recv_ns(struct sk_buff *skb) if (ipv6_chk_acast_addr(dev, &msg->target) || (idev->cnf.forwarding && - pneigh_lookup(&nd_tbl, &msg->target, dev, 0))) { + (pneigh = pneigh_lookup(&nd_tbl, + &msg->target, dev, 0)) != NULL)) { if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && inc != 0 && @@ -843,12 +846,17 @@ static void ndisc_recv_ns(struct sk_buff *skb) goto out; } + if (pneigh) + is_router = pneigh->flags & NTF_ROUTER; + else + is_router = idev->cnf.forwarding; + if (dad) { struct in6_addr maddr; ipv6_addr_all_nodes(&maddr); ndisc_send_na(dev, NULL, &maddr, &msg->target, - idev->cnf.forwarding, 0, (ifp != NULL), 1); + is_router, 0, (ifp != NULL), 1); goto out; } @@ -869,7 +877,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) NEIGH_UPDATE_F_OVERRIDE); if (neigh || !dev->hard_header) { ndisc_send_na(dev, neigh, saddr, &msg->target, - idev->cnf.forwarding, + is_router, 1, (ifp != NULL && inc), inc); if (neigh) neigh_release(neigh); -- cgit v1.2.3-70-g09d2 From 8814c4b533817df825485ff32ce6ac406c3a54d1 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Fri, 22 Sep 2006 14:44:24 -0700 Subject: [IPV6] ADDRCONF: Convert addrconf_lock to RCU. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/net/addrconf.h | 10 ++++------ include/net/if_inet6.h | 1 + net/core/pktgen.c | 4 ++-- net/ipv6/addrconf.c | 46 ++++++++++++++++++++++++---------------------- net/ipv6/anycast.c | 4 ++-- net/ipv6/ipv6_syms.c | 1 - net/sctp/ipv6.c | 6 +++--- 7 files changed, 36 insertions(+), 36 deletions(-) (limited to 'net/core') diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 5fc8627435e..aa2ed8f0a9d 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -133,20 +133,18 @@ extern int unregister_inet6addr_notifier(struct notifier_block *nb); static inline struct inet6_dev * __in6_dev_get(struct net_device *dev) { - return (struct inet6_dev *)dev->ip6_ptr; + return rcu_dereference(dev->ip6_ptr); } -extern rwlock_t addrconf_lock; - static inline struct inet6_dev * in6_dev_get(struct net_device *dev) { struct inet6_dev *idev = NULL; - read_lock(&addrconf_lock); - idev = dev->ip6_ptr; + rcu_read_lock(); + idev = __in6_dev_get(dev); if (idev) atomic_inc(&idev->refcnt); - read_unlock(&addrconf_lock); + rcu_read_unlock(); return idev; } diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index e459e1a0ae4..34489c13c11 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -189,6 +189,7 @@ struct inet6_dev struct ipv6_devconf cnf; struct ipv6_devstat stats; unsigned long tstamp; /* ipv6InterfaceTable update timestamp */ + struct rcu_head rcu; }; extern struct ipv6_devconf ipv6_devconf; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 6a7320b39ed..72145d4a260 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -1786,7 +1786,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) * use ipv6_get_lladdr if/when it's get exported */ - read_lock(&addrconf_lock); + rcu_read_lock(); if ((idev = __in6_dev_get(pkt_dev->odev)) != NULL) { struct inet6_ifaddr *ifp; @@ -1805,7 +1805,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) } read_unlock_bh(&idev->lock); } - read_unlock(&addrconf_lock); + rcu_read_unlock(); if (err) printk("pktgen: ERROR: IPv6 link address not availble.\n"); } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 825a291d5aa..c09ebb7bb98 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -119,9 +119,6 @@ static int ipv6_count_addresses(struct inet6_dev *idev); static struct inet6_ifaddr *inet6_addr_lst[IN6_ADDR_HSIZE]; static DEFINE_RWLOCK(addrconf_hash_lock); -/* Protects inet6 devices */ -DEFINE_RWLOCK(addrconf_lock); - static void addrconf_verify(unsigned long); static DEFINE_TIMER(addr_chk_timer, addrconf_verify, 0, 0); @@ -318,6 +315,12 @@ static void addrconf_mod_timer(struct inet6_ifaddr *ifp, /* Nobody refers to this device, we may destroy it. */ +static void in6_dev_finish_destroy_rcu(struct rcu_head *head) +{ + struct inet6_dev *idev = container_of(head, struct inet6_dev, rcu); + kfree(idev); +} + void in6_dev_finish_destroy(struct inet6_dev *idev) { struct net_device *dev = idev->dev; @@ -332,7 +335,7 @@ void in6_dev_finish_destroy(struct inet6_dev *idev) return; } snmp6_free_dev(idev); - kfree(idev); + call_rcu(&idev->rcu, in6_dev_finish_destroy_rcu); } static struct inet6_dev * ipv6_add_dev(struct net_device *dev) @@ -408,9 +411,8 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) if (netif_carrier_ok(dev)) ndev->if_flags |= IF_READY; - write_lock_bh(&addrconf_lock); - dev->ip6_ptr = ndev; - write_unlock_bh(&addrconf_lock); + /* protected by rtnl_lock */ + rcu_assign_pointer(dev->ip6_ptr, ndev); ipv6_mc_init_dev(ndev); ndev->tstamp = jiffies; @@ -474,7 +476,7 @@ static void addrconf_forward_change(void) read_lock(&dev_base_lock); for (dev=dev_base; dev; dev=dev->next) { - read_lock(&addrconf_lock); + rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.forwarding) ^ (!ipv6_devconf.forwarding); @@ -482,7 +484,7 @@ static void addrconf_forward_change(void) if (changed) dev_forward_change(idev); } - read_unlock(&addrconf_lock); + rcu_read_unlock(); } read_unlock(&dev_base_lock); } @@ -543,7 +545,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, int hash; int err = 0; - read_lock_bh(&addrconf_lock); + rcu_read_lock_bh(); if (idev->dead) { err = -ENODEV; /*XXX*/ goto out2; @@ -612,7 +614,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, in6_ifa_hold(ifa); write_unlock(&idev->lock); out2: - read_unlock_bh(&addrconf_lock); + rcu_read_unlock_bh(); if (likely(err == 0)) atomic_notifier_call_chain(&inet6addr_chain, NETDEV_UP, ifa); @@ -915,7 +917,7 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev, memset(&hiscore, 0, sizeof(hiscore)); read_lock(&dev_base_lock); - read_lock(&addrconf_lock); + rcu_read_lock(); for (dev = dev_base; dev; dev=dev->next) { struct inet6_dev *idev; @@ -1127,7 +1129,7 @@ record_it: } read_unlock_bh(&idev->lock); } - read_unlock(&addrconf_lock); + rcu_read_unlock(); read_unlock(&dev_base_lock); if (!ifa_result) @@ -1151,7 +1153,7 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr) struct inet6_dev *idev; int err = -EADDRNOTAVAIL; - read_lock(&addrconf_lock); + rcu_read_lock(); if ((idev = __in6_dev_get(dev)) != NULL) { struct inet6_ifaddr *ifp; @@ -1165,7 +1167,7 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr) } read_unlock_bh(&idev->lock); } - read_unlock(&addrconf_lock); + rcu_read_unlock(); return err; } @@ -1466,7 +1468,7 @@ static void ipv6_regen_rndid(unsigned long data) struct inet6_dev *idev = (struct inet6_dev *) data; unsigned long expires; - read_lock_bh(&addrconf_lock); + rcu_read_lock_bh(); write_lock_bh(&idev->lock); if (idev->dead) @@ -1490,7 +1492,7 @@ static void ipv6_regen_rndid(unsigned long data) out: write_unlock_bh(&idev->lock); - read_unlock_bh(&addrconf_lock); + rcu_read_unlock_bh(); in6_dev_put(idev); } @@ -2342,10 +2344,10 @@ static int addrconf_ifdown(struct net_device *dev, int how) Do not dev_put! */ if (how == 1) { - write_lock_bh(&addrconf_lock); - dev->ip6_ptr = NULL; idev->dead = 1; - write_unlock_bh(&addrconf_lock); + + /* protected by rtnl_lock */ + rcu_assign_pointer(dev->ip6_ptr, NULL); /* Step 1.5: remove snmp6 entry */ snmp6_unregister_dev(idev); @@ -3573,10 +3575,10 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) { - read_lock_bh(&addrconf_lock); + rcu_read_lock_bh(); if (likely(ifp->idev->dead == 0)) __ipv6_ifa_notify(event, ifp); - read_unlock_bh(&addrconf_lock); + rcu_read_unlock_bh(); } #ifdef CONFIG_SYSCTL diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index b80fc502ca0..a9604764e01 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -56,7 +56,7 @@ ip6_onlink(struct in6_addr *addr, struct net_device *dev) int onlink; onlink = 0; - read_lock(&addrconf_lock); + rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { read_lock_bh(&idev->lock); @@ -68,7 +68,7 @@ ip6_onlink(struct in6_addr *addr, struct net_device *dev) } read_unlock_bh(&idev->lock); } - read_unlock(&addrconf_lock); + rcu_read_unlock(); return onlink; } diff --git a/net/ipv6/ipv6_syms.c b/net/ipv6/ipv6_syms.c index 7b7b90d9c3d..0e8e0676a03 100644 --- a/net/ipv6/ipv6_syms.c +++ b/net/ipv6/ipv6_syms.c @@ -14,7 +14,6 @@ EXPORT_SYMBOL(ndisc_mc_map); EXPORT_SYMBOL(register_inet6addr_notifier); EXPORT_SYMBOL(unregister_inet6addr_notifier); EXPORT_SYMBOL(ip6_route_output); -EXPORT_SYMBOL(addrconf_lock); EXPORT_SYMBOL(ipv6_setsockopt); EXPORT_SYMBOL(ipv6_getsockopt); EXPORT_SYMBOL(inet6_register_protosw); diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index fd87e3ceb56..249e5033c1a 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -321,9 +321,9 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist, struct inet6_ifaddr *ifp; struct sctp_sockaddr_entry *addr; - read_lock(&addrconf_lock); + rcu_read_lock(); if ((in6_dev = __in6_dev_get(dev)) == NULL) { - read_unlock(&addrconf_lock); + rcu_read_unlock(); return; } @@ -342,7 +342,7 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist, } read_unlock(&in6_dev->lock); - read_unlock(&addrconf_lock); + rcu_read_unlock(); } /* Initialize a sockaddr_storage from in incoming skb. */ -- cgit v1.2.3-70-g09d2