* [net-next-2.6 PATCH 3/7] xfrm: SA lookups with mark
From: jamal @ 2010-02-14 15:18 UTC (permalink / raw)
To: timo.teras, kaber, herbert, davem; +Cc: netdev, Jamal Hadi Salim
In-Reply-To: <1266160732-946-3-git-send-email-hadi@cyberus.ca>
From: Jamal Hadi Salim <hadi@cyberus.ca>
Allow mark to be added to the SA lookup
Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca>
---
net/xfrm/xfrm_state.c | 12 ++++++++++++
1 files changed, 12 insertions(+), 0 deletions(-)
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index fcf0d9f..151c6d6 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -678,6 +678,8 @@ static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark, xfrm_ad
xfrm_addr_cmp(&x->id.daddr, daddr, family))
continue;
+ if ((mark & x->mark.m) != x->mark.v)
+ continue;
xfrm_state_hold(x);
return x;
}
@@ -698,6 +700,8 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark,
xfrm_addr_cmp(&x->props.saddr, saddr, family))
continue;
+ if ((mark & x->mark.m) != x->mark.v)
+ continue;
xfrm_state_hold(x);
return x;
}
@@ -790,6 +794,7 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr,
hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) {
if (x->props.family == family &&
x->props.reqid == tmpl->reqid &&
+ (mark & x->mark.m) == x->mark.v &&
!(x->props.flags & XFRM_STATE_WILDRECV) &&
xfrm_state_addr_check(x, daddr, saddr, family) &&
tmpl->mode == x->props.mode &&
@@ -805,6 +810,7 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr,
hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h_wildcard, bydst) {
if (x->props.family == family &&
x->props.reqid == tmpl->reqid &&
+ (mark & x->mark.m) == x->mark.v &&
!(x->props.flags & XFRM_STATE_WILDRECV) &&
xfrm_state_addr_check(x, daddr, saddr, family) &&
tmpl->mode == x->props.mode &&
@@ -888,6 +894,7 @@ xfrm_stateonly_find(struct net *net, u32 mark,
hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) {
if (x->props.family == family &&
x->props.reqid == reqid &&
+ (mark & x->mark.m) == x->mark.v &&
!(x->props.flags & XFRM_STATE_WILDRECV) &&
xfrm_state_addr_check(x, daddr, saddr, family) &&
mode == x->props.mode &&
@@ -950,11 +957,13 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew)
struct xfrm_state *x;
struct hlist_node *entry;
unsigned int h;
+ u32 mark = xnew->mark.v & xnew->mark.m;
h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family);
hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) {
if (x->props.family == family &&
x->props.reqid == reqid &&
+ (mark & x->mark.m) == x->mark.v &&
!xfrm_addr_cmp(&x->id.daddr, &xnew->id.daddr, family) &&
!xfrm_addr_cmp(&x->props.saddr, &xnew->props.saddr, family))
x->genid = xfrm_state_genid;
@@ -976,6 +985,7 @@ static struct xfrm_state *__find_acq_core(struct net *net, struct xfrm_kmark *m,
unsigned int h = xfrm_dst_hash(net, daddr, saddr, reqid, family);
struct hlist_node *entry;
struct xfrm_state *x;
+ u32 mark = m->v & m->m;
hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) {
if (x->props.reqid != reqid ||
@@ -984,6 +994,7 @@ static struct xfrm_state *__find_acq_core(struct net *net, struct xfrm_kmark *m,
x->km.state != XFRM_STATE_ACQ ||
x->id.spi != 0 ||
x->id.proto != proto ||
+ (mark & x->mark.m) != x->mark.v ||
xfrm_addr_cmp(&x->id.daddr, daddr, family) ||
xfrm_addr_cmp(&x->props.saddr, saddr, family))
continue;
@@ -1444,6 +1455,7 @@ static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 s
hlist_for_each_entry(x, entry, net->xfrm.state_bydst+i, bydst) {
if (x->km.seq == seq &&
+ (mark & x->mark.m) == x->mark.v &&
x->km.state == XFRM_STATE_ACQ) {
xfrm_state_hold(x);
return x;
--
1.6.0.4
^ permalink raw reply related
* [net-next-2.6 PATCH 2/7] xfrm: SA lookups signature with mark
From: jamal @ 2010-02-14 15:18 UTC (permalink / raw)
To: timo.teras, kaber, herbert, davem; +Cc: netdev, Jamal Hadi Salim
In-Reply-To: <1266160732-946-2-git-send-email-hadi@cyberus.ca>
From: Jamal Hadi Salim <hadi@cyberus.ca>
pass mark to all SA lookups to prepare them for when we add code
to have them search.
Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca>
---
include/net/xfrm.h | 23 +++++++++++++-----
net/core/pktgen.c | 3 +-
net/ipv4/ah4.c | 2 +-
net/ipv4/esp4.c | 2 +-
net/ipv4/ipcomp.c | 6 +++-
net/ipv6/ah6.c | 2 +-
net/ipv6/esp6.c | 2 +-
net/ipv6/ipcomp6.c | 6 +++-
net/ipv6/xfrm6_input.c | 2 +-
net/key/af_key.c | 14 ++++++-----
net/xfrm/xfrm_input.c | 2 +-
net/xfrm/xfrm_state.c | 58 ++++++++++++++++++++++++++++-------------------
net/xfrm/xfrm_user.c | 17 ++++++++-----
13 files changed, 84 insertions(+), 55 deletions(-)
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 904527f..96b6953 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1325,7 +1325,7 @@ extern struct xfrm_state *xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t
struct flowi *fl, struct xfrm_tmpl *tmpl,
struct xfrm_policy *pol, int *err,
unsigned short family);
-extern struct xfrm_state * xfrm_stateonly_find(struct net *net,
+extern struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark,
xfrm_address_t *daddr,
xfrm_address_t *saddr,
unsigned short family,
@@ -1334,8 +1334,14 @@ extern int xfrm_state_check_expire(struct xfrm_state *x);
extern void xfrm_state_insert(struct xfrm_state *x);
extern int xfrm_state_add(struct xfrm_state *x);
extern int xfrm_state_update(struct xfrm_state *x);
-extern struct xfrm_state *xfrm_state_lookup(struct net *net, xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family);
-extern struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto, unsigned short family);
+extern struct xfrm_state *xfrm_state_lookup(struct net *net, u32 mark,
+ xfrm_address_t *daddr, __be32 spi,
+ u8 proto, unsigned short family);
+extern struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, u32 mark,
+ xfrm_address_t *daddr,
+ xfrm_address_t *saddr,
+ u8 proto,
+ unsigned short family);
#ifdef CONFIG_XFRM_SUB_POLICY
extern int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src,
int n, unsigned short family);
@@ -1372,7 +1378,8 @@ struct xfrmk_spdinfo {
u32 spdhmcnt;
};
-extern struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 seq);
+extern struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark,
+ u32 seq);
extern int xfrm_state_delete(struct xfrm_state *x);
extern int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info);
extern void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si);
@@ -1457,9 +1464,11 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u8, int dir, u32 id, int d
int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info);
u32 xfrm_get_acqseq(void);
extern int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi);
-struct xfrm_state * xfrm_find_acq(struct net *net, u8 mode, u32 reqid, u8 proto,
- xfrm_address_t *daddr, xfrm_address_t *saddr,
- int create, unsigned short family);
+struct xfrm_state *xfrm_find_acq(struct net *net, struct xfrm_kmark *mark,
+ u8 mode, u32 reqid, u8 proto,
+ xfrm_address_t *daddr,
+ xfrm_address_t *saddr, int create,
+ unsigned short family);
extern int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol);
extern int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *xdst,
struct flowi *fl, int family, int strict);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 2e692af..4392381 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2188,12 +2188,13 @@ static inline int f_pick(struct pktgen_dev *pkt_dev)
/* If there was already an IPSEC SA, we keep it as is, else
* we go look for it ...
*/
+#define DUMMY_MARK 0
static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow)
{
struct xfrm_state *x = pkt_dev->flows[flow].x;
if (!x) {
/*slow path: we dont already have xfrm_state*/
- x = xfrm_stateonly_find(&init_net,
+ x = xfrm_stateonly_find(&init_net, DUMMY_MARK,
(xfrm_address_t *)&pkt_dev->cur_daddr,
(xfrm_address_t *)&pkt_dev->cur_saddr,
AF_INET,
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 7ed3e4a..987b47d 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -393,7 +393,7 @@ static void ah4_err(struct sk_buff *skb, u32 info)
icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
return;
- x = xfrm_state_lookup(net, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET);
+ x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET);
if (!x)
return;
printk(KERN_DEBUG "pmtu discovery on SA AH/%08x/%08x\n",
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 1948895..14ca1f1 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -422,7 +422,7 @@ static void esp4_err(struct sk_buff *skb, u32 info)
icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
return;
- x = xfrm_state_lookup(net, (xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET);
+ x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET);
if (!x)
return;
NETDEBUG(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%08x\n",
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index b55a0c3..b192e2f 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -36,7 +36,7 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info)
return;
spi = htonl(ntohs(ipch->cpi));
- x = xfrm_state_lookup(net, (xfrm_address_t *)&iph->daddr,
+ x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr,
spi, IPPROTO_COMP, AF_INET);
if (!x)
return;
@@ -63,6 +63,7 @@ static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x)
t->props.mode = x->props.mode;
t->props.saddr.a4 = x->props.saddr.a4;
t->props.flags = x->props.flags;
+ memcpy(&t->mark, &x->mark, sizeof(t->mark));
if (xfrm_init_state(t))
goto error;
@@ -87,8 +88,9 @@ static int ipcomp_tunnel_attach(struct xfrm_state *x)
struct net *net = xs_net(x);
int err = 0;
struct xfrm_state *t;
+ u32 mark = x->mark.v & x->mark.m;
- t = xfrm_state_lookup(net, (xfrm_address_t *)&x->id.daddr.a4,
+ t = xfrm_state_lookup(net, mark, (xfrm_address_t *)&x->id.daddr.a4,
x->props.saddr.a4, IPPROTO_IPIP, AF_INET);
if (!t) {
t = ipcomp_tunnel_create(x);
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index c2f300c..5ac8902 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -614,7 +614,7 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
type != ICMPV6_PKT_TOOBIG)
return;
- x = xfrm_state_lookup(net, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6);
+ x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6);
if (!x)
return;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 668a46b..ee9b93b 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -365,7 +365,7 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
type != ICMPV6_PKT_TOOBIG)
return;
- x = xfrm_state_lookup(net, (xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6);
+ x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6);
if (!x)
return;
printk(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%pI6\n",
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index a9fbb15..26f4ab9 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -64,7 +64,7 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
return;
spi = htonl(ntohs(ipcomph->cpi));
- x = xfrm_state_lookup(net, (xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET6);
+ x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET6);
if (!x)
return;
@@ -92,6 +92,7 @@ static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x)
t->props.family = AF_INET6;
t->props.mode = x->props.mode;
memcpy(t->props.saddr.a6, x->props.saddr.a6, sizeof(struct in6_addr));
+ memcpy(&t->mark, &x->mark, sizeof(t->mark));
if (xfrm_init_state(t))
goto error;
@@ -114,10 +115,11 @@ static int ipcomp6_tunnel_attach(struct xfrm_state *x)
int err = 0;
struct xfrm_state *t = NULL;
__be32 spi;
+ u32 mark = x->mark.m & x->mark.v;
spi = xfrm6_tunnel_spi_lookup(net, (xfrm_address_t *)&x->props.saddr);
if (spi)
- t = xfrm_state_lookup(net, (xfrm_address_t *)&x->id.daddr,
+ t = xfrm_state_lookup(net, mark, (xfrm_address_t *)&x->id.daddr,
spi, IPPROTO_IPV6, AF_INET6);
if (!t) {
t = ipcomp6_tunnel_create(x);
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 9084582..2bc98ed 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -101,7 +101,7 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
break;
}
- x = xfrm_state_lookup_byaddr(net, dst, src, proto, AF_INET6);
+ x = xfrm_state_lookup_byaddr(net, skb->mark, dst, src, proto, AF_INET6);
if (!x)
continue;
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 79d2c0f..4d652c8 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -45,6 +45,8 @@ static DECLARE_WAIT_QUEUE_HEAD(pfkey_table_wait);
static DEFINE_RWLOCK(pfkey_table_lock);
static atomic_t pfkey_table_users = ATOMIC_INIT(0);
+#define DUMMY_MARK 0
+static struct xfrm_kmark dummy_mark = {0, 0};
struct pfkey_sock {
/* struct sock must be the first member of struct pfkey_sock */
struct sock sk;
@@ -691,7 +693,7 @@ static struct xfrm_state *pfkey_xfrm_state_lookup(struct net *net, struct sadb_
if (!xaddr)
return NULL;
- return xfrm_state_lookup(net, xaddr, sa->sadb_sa_spi, proto, family);
+ return xfrm_state_lookup(net, DUMMY_MARK, xaddr, sa->sadb_sa_spi, proto, family);
}
#define PFKEY_ALIGN8(a) (1 + (((a) - 1) | (8 - 1)))
@@ -1360,7 +1362,7 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h
}
if (hdr->sadb_msg_seq) {
- x = xfrm_find_acq_byseq(net, hdr->sadb_msg_seq);
+ x = xfrm_find_acq_byseq(net, DUMMY_MARK, hdr->sadb_msg_seq);
if (x && xfrm_addr_cmp(&x->id.daddr, xdaddr, family)) {
xfrm_state_put(x);
x = NULL;
@@ -1368,7 +1370,7 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h
}
if (!x)
- x = xfrm_find_acq(net, mode, reqid, proto, xdaddr, xsaddr, 1, family);
+ x = xfrm_find_acq(net, &dummy_mark, mode, reqid, proto, xdaddr, xsaddr, 1, family);
if (x == NULL)
return -ENOENT;
@@ -1417,7 +1419,7 @@ static int pfkey_acquire(struct sock *sk, struct sk_buff *skb, struct sadb_msg *
if (hdr->sadb_msg_seq == 0 || hdr->sadb_msg_errno == 0)
return 0;
- x = xfrm_find_acq_byseq(net, hdr->sadb_msg_seq);
+ x = xfrm_find_acq_byseq(net, DUMMY_MARK, hdr->sadb_msg_seq);
if (x == NULL)
return 0;
@@ -2594,8 +2596,8 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h
return -EINVAL;
delete = (hdr->sadb_msg_type == SADB_X_SPDDELETE2);
- xp = xfrm_policy_byid(net, XFRM_POLICY_TYPE_MAIN, dir,
- pol->sadb_x_policy_id, delete, &err);
+ xp = xfrm_policy_byid(net, XFRM_POLICY_TYPE_MAIN,
+ dir, pol->sadb_x_policy_id, delete, &err);
if (xp == NULL)
return -ENOENT;
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index e0009c1..45f1c98 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -152,7 +152,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
goto drop;
}
- x = xfrm_state_lookup(net, daddr, spi, nexthdr, family);
+ x = xfrm_state_lookup(net, skb->mark, daddr, spi, nexthdr, family);
if (x == NULL) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES);
xfrm_audit_state_notfound(skb, family, spi, seq);
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index b36cc34..fcf0d9f 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -665,7 +665,7 @@ xfrm_init_tempsel(struct xfrm_state *x, struct flowi *fl,
return 0;
}
-static struct xfrm_state *__xfrm_state_lookup(struct net *net, xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family)
+static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark, xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family)
{
unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family);
struct xfrm_state *x;
@@ -685,7 +685,7 @@ static struct xfrm_state *__xfrm_state_lookup(struct net *net, xfrm_address_t *d
return NULL;
}
-static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto, unsigned short family)
+static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark, xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto, unsigned short family)
{
unsigned int h = xfrm_src_hash(net, daddr, saddr, family);
struct xfrm_state *x;
@@ -709,12 +709,14 @@ static inline struct xfrm_state *
__xfrm_state_locate(struct xfrm_state *x, int use_spi, int family)
{
struct net *net = xs_net(x);
+ u32 mark = x->mark.v & x->mark.m;
if (use_spi)
- return __xfrm_state_lookup(net, &x->id.daddr, x->id.spi,
- x->id.proto, family);
+ return __xfrm_state_lookup(net, mark, &x->id.daddr,
+ x->id.spi, x->id.proto, family);
else
- return __xfrm_state_lookup_byaddr(net, &x->id.daddr,
+ return __xfrm_state_lookup_byaddr(net, mark,
+ &x->id.daddr,
&x->props.saddr,
x->id.proto, family);
}
@@ -779,6 +781,7 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr,
int acquire_in_progress = 0;
int error = 0;
struct xfrm_state *best = NULL;
+ u32 mark = pol->mark.v & pol->mark.m;
to_put = NULL;
@@ -815,7 +818,7 @@ found:
x = best;
if (!x && !error && !acquire_in_progress) {
if (tmpl->id.spi &&
- (x0 = __xfrm_state_lookup(net, daddr, tmpl->id.spi,
+ (x0 = __xfrm_state_lookup(net, mark, daddr, tmpl->id.spi,
tmpl->id.proto, family)) != NULL) {
to_put = x0;
error = -EEXIST;
@@ -829,6 +832,7 @@ found:
/* Initialize temporary selector matching only
* to current session. */
xfrm_init_tempsel(x, fl, tmpl, daddr, saddr, family);
+ memcpy(&x->mark, &pol->mark, sizeof(x->mark));
error = security_xfrm_state_alloc_acquire(x, pol->security, fl->secid);
if (error) {
@@ -871,7 +875,7 @@ out:
}
struct xfrm_state *
-xfrm_stateonly_find(struct net *net,
+xfrm_stateonly_find(struct net *net, u32 mark,
xfrm_address_t *daddr, xfrm_address_t *saddr,
unsigned short family, u8 mode, u8 proto, u32 reqid)
{
@@ -967,7 +971,7 @@ void xfrm_state_insert(struct xfrm_state *x)
EXPORT_SYMBOL(xfrm_state_insert);
/* xfrm_state_lock is held */
-static struct xfrm_state *__find_acq_core(struct net *net, unsigned short family, u8 mode, u32 reqid, u8 proto, xfrm_address_t *daddr, xfrm_address_t *saddr, int create)
+static struct xfrm_state *__find_acq_core(struct net *net, struct xfrm_kmark *m, unsigned short family, u8 mode, u32 reqid, u8 proto, xfrm_address_t *daddr, xfrm_address_t *saddr, int create)
{
unsigned int h = xfrm_dst_hash(net, daddr, saddr, reqid, family);
struct hlist_node *entry;
@@ -1022,6 +1026,8 @@ static struct xfrm_state *__find_acq_core(struct net *net, unsigned short family
x->props.family = family;
x->props.mode = mode;
x->props.reqid = reqid;
+ x->mark.v = m->v;
+ x->mark.m = m->m;
x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
xfrm_state_hold(x);
tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL);
@@ -1038,7 +1044,7 @@ static struct xfrm_state *__find_acq_core(struct net *net, unsigned short family
return x;
}
-static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 seq);
+static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq);
int xfrm_state_add(struct xfrm_state *x)
{
@@ -1046,6 +1052,7 @@ int xfrm_state_add(struct xfrm_state *x)
struct xfrm_state *x1, *to_put;
int family;
int err;
+ u32 mark = x->mark.v & x->mark.m;
int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY);
family = x->props.family;
@@ -1063,7 +1070,7 @@ int xfrm_state_add(struct xfrm_state *x)
}
if (use_spi && x->km.seq) {
- x1 = __xfrm_find_acq_byseq(net, x->km.seq);
+ x1 = __xfrm_find_acq_byseq(net, mark, x->km.seq);
if (x1 && ((x1->id.proto != x->id.proto) ||
xfrm_addr_cmp(&x1->id.daddr, &x->id.daddr, family))) {
to_put = x1;
@@ -1072,8 +1079,8 @@ int xfrm_state_add(struct xfrm_state *x)
}
if (use_spi && !x1)
- x1 = __find_acq_core(net, family, x->props.mode, x->props.reqid,
- x->id.proto,
+ x1 = __find_acq_core(net, &x->mark, family, x->props.mode,
+ x->props.reqid, x->id.proto,
&x->id.daddr, &x->props.saddr, 0);
__xfrm_state_bump_genids(x);
@@ -1147,6 +1154,8 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp)
goto error;
}
+ memcpy(&x->mark, &orig->mark, sizeof(x->mark));
+
err = xfrm_init_state(x);
if (err)
goto error;
@@ -1344,41 +1353,41 @@ int xfrm_state_check_expire(struct xfrm_state *x)
EXPORT_SYMBOL(xfrm_state_check_expire);
struct xfrm_state *
-xfrm_state_lookup(struct net *net, xfrm_address_t *daddr, __be32 spi, u8 proto,
- unsigned short family)
+xfrm_state_lookup(struct net *net, u32 mark, xfrm_address_t *daddr, __be32 spi,
+ u8 proto, unsigned short family)
{
struct xfrm_state *x;
spin_lock_bh(&xfrm_state_lock);
- x = __xfrm_state_lookup(net, daddr, spi, proto, family);
+ x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family);
spin_unlock_bh(&xfrm_state_lock);
return x;
}
EXPORT_SYMBOL(xfrm_state_lookup);
struct xfrm_state *
-xfrm_state_lookup_byaddr(struct net *net,
+xfrm_state_lookup_byaddr(struct net *net, u32 mark,
xfrm_address_t *daddr, xfrm_address_t *saddr,
u8 proto, unsigned short family)
{
struct xfrm_state *x;
spin_lock_bh(&xfrm_state_lock);
- x = __xfrm_state_lookup_byaddr(net, daddr, saddr, proto, family);
+ x = __xfrm_state_lookup_byaddr(net, mark, daddr, saddr, proto, family);
spin_unlock_bh(&xfrm_state_lock);
return x;
}
EXPORT_SYMBOL(xfrm_state_lookup_byaddr);
struct xfrm_state *
-xfrm_find_acq(struct net *net, u8 mode, u32 reqid, u8 proto,
+xfrm_find_acq(struct net *net, struct xfrm_kmark *mark, u8 mode, u32 reqid, u8 proto,
xfrm_address_t *daddr, xfrm_address_t *saddr,
int create, unsigned short family)
{
struct xfrm_state *x;
spin_lock_bh(&xfrm_state_lock);
- x = __find_acq_core(net, family, mode, reqid, proto, daddr, saddr, create);
+ x = __find_acq_core(net, mark, family, mode, reqid, proto, daddr, saddr, create);
spin_unlock_bh(&xfrm_state_lock);
return x;
@@ -1425,7 +1434,7 @@ EXPORT_SYMBOL(xfrm_state_sort);
/* Silly enough, but I'm lazy to build resolution list */
-static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 seq)
+static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq)
{
int i;
@@ -1444,12 +1453,12 @@ static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 seq)
return NULL;
}
-struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 seq)
+struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq)
{
struct xfrm_state *x;
spin_lock_bh(&xfrm_state_lock);
- x = __xfrm_find_acq_byseq(net, seq);
+ x = __xfrm_find_acq_byseq(net, mark, seq);
spin_unlock_bh(&xfrm_state_lock);
return x;
}
@@ -1476,6 +1485,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
int err = -ENOENT;
__be32 minspi = htonl(low);
__be32 maxspi = htonl(high);
+ u32 mark = x->mark.v & x->mark.m;
spin_lock_bh(&x->lock);
if (x->km.state == XFRM_STATE_DEAD)
@@ -1488,7 +1498,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
err = -ENOENT;
if (minspi == maxspi) {
- x0 = xfrm_state_lookup(net, &x->id.daddr, minspi, x->id.proto, x->props.family);
+ x0 = xfrm_state_lookup(net, mark, &x->id.daddr, minspi, x->id.proto, x->props.family);
if (x0) {
xfrm_state_put(x0);
goto unlock;
@@ -1498,7 +1508,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
u32 spi = 0;
for (h=0; h<high-low+1; h++) {
spi = low + net_random()%(high-low+1);
- x0 = xfrm_state_lookup(net, &x->id.daddr, htonl(spi), x->id.proto, x->props.family);
+ x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family);
if (x0 == NULL) {
x->id.spi = htonl(spi);
break;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 943c871..a2c9823 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -31,6 +31,9 @@
#include <linux/in6.h>
#endif
+#define DUMMY_MARK 0
+static struct xfrm_kmark dummy_mark = {0, 0};
+
static inline int aead_len(struct xfrm_algo_aead *alg)
{
return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
@@ -530,7 +533,7 @@ static struct xfrm_state *xfrm_user_state_lookup(struct net *net,
if (xfrm_id_proto_match(p->proto, IPSEC_PROTO_ANY)) {
err = -ESRCH;
- x = xfrm_state_lookup(net, &p->daddr, p->spi, p->proto, p->family);
+ x = xfrm_state_lookup(net, DUMMY_MARK, &p->daddr, p->spi, p->proto, p->family);
} else {
xfrm_address_t *saddr = NULL;
@@ -541,7 +544,7 @@ static struct xfrm_state *xfrm_user_state_lookup(struct net *net,
}
err = -ESRCH;
- x = xfrm_state_lookup_byaddr(net, &p->daddr, saddr,
+ x = xfrm_state_lookup_byaddr(net, DUMMY_MARK, &p->daddr, saddr,
p->proto, p->family);
}
@@ -958,7 +961,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
x = NULL;
if (p->info.seq) {
- x = xfrm_find_acq_byseq(net, p->info.seq);
+ x = xfrm_find_acq_byseq(net, DUMMY_MARK, p->info.seq);
if (x && xfrm_addr_cmp(&x->id.daddr, daddr, family)) {
xfrm_state_put(x);
x = NULL;
@@ -966,7 +969,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
}
if (!x)
- x = xfrm_find_acq(net, p->info.mode, p->info.reqid,
+ x = xfrm_find_acq(net, &dummy_mark, p->info.mode, p->info.reqid,
p->info.id.proto, daddr,
&p->info.saddr, 1,
family);
@@ -1595,7 +1598,7 @@ static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh,
if (r_skb == NULL)
return -ENOMEM;
- x = xfrm_state_lookup(net, &id->daddr, id->spi, id->proto, id->family);
+ x = xfrm_state_lookup(net, DUMMY_MARK, &id->daddr, id->spi, id->proto, id->family);
if (x == NULL) {
kfree_skb(r_skb);
return -ESRCH;
@@ -1637,7 +1640,7 @@ static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh,
if (!(nlh->nlmsg_flags&NLM_F_REPLACE))
return err;
- x = xfrm_state_lookup(net, &p->sa_id.daddr, p->sa_id.spi, p->sa_id.proto, p->sa_id.family);
+ x = xfrm_state_lookup(net, DUMMY_MARK, &p->sa_id.daddr, p->sa_id.spi, p->sa_id.proto, p->sa_id.family);
if (x == NULL)
return -ESRCH;
@@ -1760,7 +1763,7 @@ static int xfrm_add_sa_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
struct xfrm_user_expire *ue = nlmsg_data(nlh);
struct xfrm_usersa_info *p = &ue->state;
- x = xfrm_state_lookup(net, &p->id.daddr, p->id.spi, p->id.proto, p->family);
+ x = xfrm_state_lookup(net, DUMMY_MARK, &p->id.daddr, p->id.spi, p->id.proto, p->family);
err = -ENOENT;
if (x == NULL)
--
1.6.0.4
^ permalink raw reply related
* [net-next-2.6 PATCH 1/7] xfrm: introduce basic mark infrastructure
From: jamal @ 2010-02-14 15:18 UTC (permalink / raw)
To: timo.teras, kaber, herbert, davem; +Cc: netdev, Jamal Hadi Salim
In-Reply-To: <1266160732-946-1-git-send-email-hadi@cyberus.ca>
From: Jamal Hadi Salim <hadi@cyberus.ca>
Add basic structuring and accessors for xfrm mark
Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca>
---
include/linux/xfrm.h | 12 +++++++++---
include/net/xfrm.h | 28 ++++++++++++++++++++++++++++
2 files changed, 37 insertions(+), 3 deletions(-)
diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h
index 29e04be..887c533 100644
--- a/include/linux/xfrm.h
+++ b/include/linux/xfrm.h
@@ -267,8 +267,8 @@ enum xfrm_attr_type_t {
XFRMA_ALG_COMP, /* struct xfrm_algo */
XFRMA_ENCAP, /* struct xfrm_algo + struct xfrm_encap_tmpl */
XFRMA_TMPL, /* 1 or more struct xfrm_user_tmpl */
- XFRMA_SA,
- XFRMA_POLICY,
+ XFRMA_SA, /* struct xfrm_usersa_info */
+ XFRMA_POLICY, /*struct xfrm_userpolicy_info */
XFRMA_SEC_CTX, /* struct xfrm_sec_ctx */
XFRMA_LTIME_VAL,
XFRMA_REPLAY_VAL,
@@ -276,17 +276,23 @@ enum xfrm_attr_type_t {
XFRMA_ETIMER_THRESH,
XFRMA_SRCADDR, /* xfrm_address_t */
XFRMA_COADDR, /* xfrm_address_t */
- XFRMA_LASTUSED,
+ XFRMA_LASTUSED, /* unsigned long */
XFRMA_POLICY_TYPE, /* struct xfrm_userpolicy_type */
XFRMA_MIGRATE,
XFRMA_ALG_AEAD, /* struct xfrm_algo_aead */
XFRMA_KMADDRESS, /* struct xfrm_user_kmaddress */
XFRMA_ALG_AUTH_TRUNC, /* struct xfrm_algo_auth */
+ XFRMA_MARK, /* u32 */
__XFRMA_MAX
#define XFRMA_MAX (__XFRMA_MAX - 1)
};
+struct xfrm_umark {
+ __u32 v; /* value */
+ __u32 m; /* mask */
+};
+
enum xfrm_sadattr_type_t {
XFRMA_SAD_UNSPEC,
XFRMA_SAD_CNT,
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 0beb413..904527f 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -123,6 +123,11 @@ struct xfrm_state_walk {
u32 seq;
};
+struct xfrm_kmark {
+ u32 v; /* value */
+ u32 m; /* mask */
+};
+
/* Full description of state of transformer. */
struct xfrm_state {
#ifdef CONFIG_NET_NS
@@ -140,6 +145,7 @@ struct xfrm_state {
struct xfrm_id id;
struct xfrm_selector sel;
+ struct xfrm_kmark mark;
u32 genid;
@@ -456,6 +462,7 @@ struct xfrm_tmpl {
#define XFRM_MAX_DEPTH 6
+
struct xfrm_policy_walk_entry {
struct list_head all;
u8 dead;
@@ -481,6 +488,7 @@ struct xfrm_policy {
u32 priority;
u32 index;
+ struct xfrm_kmark mark;
struct xfrm_selector selector;
struct xfrm_lifetime_cfg lft;
struct xfrm_lifetime_cur curlft;
@@ -1570,4 +1578,24 @@ static inline struct xfrm_state *xfrm_input_state(struct sk_buff *skb)
}
#endif
+static inline int xfrm_mark_get(struct nlattr **attrs, struct xfrm_kmark *m)
+{
+ if (attrs[XFRMA_MARK])
+ memcpy(m, nla_data(attrs[XFRMA_MARK]), sizeof(m));
+ else
+ m->v = m->m = 0;
+
+ return m->v & m->m;
+}
+
+static inline int xfrm_mark_put(struct sk_buff *skb, struct xfrm_kmark *m)
+{
+ if (m->m & m->v)
+ NLA_PUT(skb, XFRMA_MARK, sizeof(struct xfrm_kmark), m);
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
#endif /* _NET_XFRM_H */
--
1.6.0.4
^ permalink raw reply related
* [net-next-2.6 PATCH 0/7] xfrm by MARK
From: jamal @ 2010-02-14 15:18 UTC (permalink / raw)
To: timo.teras, kaber, herbert, davem; +Cc: netdev, Jamal Hadi Salim
In-Reply-To: <xfrm-mark-net-next>
From: Jamal Hadi Salim <hadi@cyberus.ca>
This patchset implements manipulation of ipsec tables with the
"mark" tag. You can config the SAD and SPD from user space
with a specified mark.
Example:
---
#ip xfrm state add src 192.168.2.100 dst 192.168.1.10 proto esp spi 0x00000301 mode tunnel mark 7 auth md5 0x96358c90783bbfa3d7b196ceabe0536b enc des3_ede 0xf6ddb555acfd9d77b03ea3843f2653255afe8eb5573965df
#ip xfrm state get mark 7 src 192.168.2.100 dst 192.168.1.10 proto esp spi 0x00000301
src 192.168.2.100 dst 192.168.1.10
proto esp spi 0x00000301 reqid 0 mode tunnel
replay-window 0
mark 7/0xffffffff
auth hmac(md5) 0x96358c90783bbfa3d7b196ceabe0536b
enc cbc(des3_ede) 0xf6ddb555acfd9d77b03ea3843f2653255afe8eb5573965df
sel src 0.0.0.0/0 dst 0.0.0.0/0
#
#
#ip xfrm policy add src 172.16.2.0/24 dst 172.16.1.0/24 \
dir fwd ptype main \
tmpl src 192.168.2.100 dst 192.168.1.100 \
proto esp mode tunnel mark 7 mask 0xffffffff
#
#ip xfrm policy ls
src 172.16.2.0/24 dst 172.16.1.0/24
dir fwd priority 0 ptype main
mark 7/0xffffffff
tmpl src 192.168.2.100 dst 192.168.1.100
proto esp reqid 0 mode tunnel
-----
A mark-configured SAD/SPD entry will use the mark as part of the
lookup key (both in data and control path).
Example:
---
# ip xfrm pol get src 172.16.2.0/24 dst 172.16.1.0/24 dir fwd
RTNETLINK answers: No such file or directory
# ip xfrm pol get src 172.16.2.0/24 dst 172.16.1.0/24 dir fwd mark 7
src 172.16.2.0/24 dst 172.16.1.0/24
dir fwd priority 0 ptype main
mark 7/0xffffffff
tmpl src 192.168.2.100 dst 192.168.1.100
proto esp reqid 0 mode tunnel
---
I could probably have broken down the last two patches into more
than one, but it was easier to do it this way. If there is strong
feeling to do that let me know.
Oh, and this is an attempt to use git-send-mail - so i would appreciate
any feedback on what i can do better next time..
Jamal Hadi Salim (7):
xfrm: introduce basic mark infrastructure
xfrm: SA lookups signature with mark
xfrm: SA lookups with mark
xfrm: SP lookups signature with mark
xfrm: SP lookups with mark
xfrm: Allow user space config of SAD mark
xfrm: Allow user space manipulation of SPD mark
include/linux/xfrm.h | 12 ++++-
include/net/xfrm.h | 56 +++++++++++++++++++++++----
net/core/pktgen.c | 3 +-
net/ipv4/ah4.c | 2 +-
net/ipv4/esp4.c | 2 +-
net/ipv4/ipcomp.c | 6 ++-
net/ipv6/ah6.c | 2 +-
net/ipv6/esp6.c | 2 +-
net/ipv6/ipcomp6.c | 6 ++-
net/ipv6/xfrm6_input.c | 2 +-
net/key/af_key.c | 16 ++++---
net/xfrm/xfrm_input.c | 2 +-
net/xfrm/xfrm_policy.c | 20 +++++++--
net/xfrm/xfrm_state.c | 70 +++++++++++++++++++++++------------
net/xfrm/xfrm_user.c | 96 ++++++++++++++++++++++++++++++++++++++++--------
15 files changed, 222 insertions(+), 75 deletions(-)
^ permalink raw reply
* [PATCH] ipcomp: double free at ipcomp_destroy()
From: Alexey Dobriyan @ 2010-02-14 14:44 UTC (permalink / raw)
To: davem; +Cc: netdev, herbert
Consider using ipcomp with tunnel mode:
pfkey_add -> xfrm_state_init -> x->type->init_state() == ipcomp4_init_state
1. If ipcomp_tunnel_attach() fails, xfrm_state private data (x->data) are freed
first time (synchronously), but stale pointer is left.
2. xfrm_state_init() failed, all right, we're going to do error unwind
but this time asynchronously and we're going to double free x->data
asynchronously.
Fix by clearing x->data pointer, so second time it'll be fine.
Note, second time can happen in quite arbitrary time, double free
messages were seen in completely irrelevant functions, e. g.
INFO: Allocated in icmp_sk_init
INFO: Freed in icmp_sk_exit
[<ffffffff810b5ceb>] kfree+0xab/0x140
[<ffffffff810719ae>] free_sect_attrs (!)
[<ffffffff81072353>] free_module
The only common thing was kmalloc-16 cache.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
---
net/xfrm/xfrm_ipcomp.c | 1 +
1 file changed, 1 insertion(+)
--- a/net/xfrm/xfrm_ipcomp.c
+++ b/net/xfrm/xfrm_ipcomp.c
@@ -332,6 +332,7 @@ void ipcomp_destroy(struct xfrm_state *x)
ipcomp_free_data(ipcd);
mutex_unlock(&ipcomp_resource_mutex);
kfree(ipcd);
+ x->data = NULL;
}
EXPORT_SYMBOL_GPL(ipcomp_destroy);
^ permalink raw reply
* [PATCH 3/5] net: Fix first line of kernel-doc for a few functions
From: Ben Hutchings @ 2010-02-14 14:19 UTC (permalink / raw)
To: David Miller; +Cc: netdev, LKML
In-Reply-To: <1266157055.10567.13.camel@localhost>
The function name must be followed by a space, hypen, space, and a
short description.
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
include/linux/skbuff.h | 4 ++--
include/net/sock.h | 2 +-
net/sunrpc/rpc_pipe.c | 2 +-
3 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ae836fd..ba0f8e3 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -738,7 +738,7 @@ static inline struct sk_buff *skb_unshare(struct sk_buff *skb,
}
/**
- * skb_peek
+ * skb_peek - peek at the head of an &sk_buff_head
* @list_: list to peek at
*
* Peek an &sk_buff. Unlike most other operations you _MUST_
@@ -759,7 +759,7 @@ static inline struct sk_buff *skb_peek(struct sk_buff_head *list_)
}
/**
- * skb_peek_tail
+ * skb_peek_tail - peek at the tail of an &sk_buff_head
* @list_: list to peek at
*
* Peek an &sk_buff. Unlike most other operations you _MUST_
diff --git a/include/net/sock.h b/include/net/sock.h
index c8d4000..580d51f 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1049,7 +1049,7 @@ extern void sk_common_release(struct sock *sk);
extern void sock_init_data(struct socket *sock, struct sock *sk);
/**
- * sk_filter_release: Release a socket filter
+ * sk_filter_release - release a socket filter
* @fp: filter to remove
*
* Remove a filter from a socket and release its resources.
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 9ac493f..8d63f8f 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -78,7 +78,7 @@ rpc_timeout_upcall_queue(struct work_struct *work)
}
/**
- * rpc_queue_upcall
+ * rpc_queue_upcall - queue an upcall message to userspace
* @inode: inode of upcall pipe on which to queue given message
* @msg: message to queue
*
--
1.6.6.2
^ permalink raw reply related
* WILL EXECUTION!
From: MALCOLM SHERIGHAM ESQ @ 2010-02-14 13:08 UTC (permalink / raw)
I wish to notify you that late Sheikh Mahmoud Alzammar made you a
beneficiary in his WILL. He left the sum of Three Million, and twenty-five
thousand British Pounds (£3, 025, 000) to you in the Codicil and last
testament to his WILL. According to him, this money is to support your
humanitarian/ medical help/ orphanage activities and to help the poor and
the needy in our society. Please respond for further correspondence
through my email: malcolm.sherigham@rocketmail.com call line: +44 701 113 2469
I await your prompt response.
Yours in Service,
Malcolm Sherigham Esq.
^ permalink raw reply
* Re: [PATCH 2/2] net/macvtap: add vhost support
From: Michael S. Tsirkin @ 2010-02-14 13:27 UTC (permalink / raw)
To: Arnd Bergmann
Cc: netdev, linux-kernel, Ed Swierk, Patrick McHardy,
Sridhar Samudrala, qemu-devel
In-Reply-To: <201002131135.08477.arnd@arndb.de>
On Sat, Feb 13, 2010 at 11:35:08AM +0100, Arnd Bergmann wrote:
> This adds support for passing a macvtap file descriptor into
> vhost-net, much like we already do for tun/tap.
>
> Most of the new code is taken from the respective patch
> in the tun driver and may get consolidated in the future.
>
> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
> ---
> drivers/net/macvtap.c | 98 ++++++++++++++++++++++++++++++++++---------
> drivers/vhost/net.c | 8 +++-
> include/linux/if_macvlan.h | 13 ++++++
> 3 files changed, 96 insertions(+), 23 deletions(-)
>
> diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
> index 7050997..e354501 100644
> --- a/drivers/net/macvtap.c
> +++ b/drivers/net/macvtap.c
> @@ -58,6 +58,8 @@ static unsigned int macvtap_major;
> static struct class *macvtap_class;
> static struct cdev macvtap_cdev;
>
> +static const struct proto_ops macvtap_socket_ops;
> +
> /*
> * RCU usage:
> * The macvtap_queue and the macvlan_dev are loosely coupled, the
> @@ -176,7 +178,7 @@ static int macvtap_forward(struct net_device *dev, struct sk_buff *skb)
> return -ENOLINK;
>
> skb_queue_tail(&q->sk.sk_receive_queue, skb);
> - wake_up(q->sk.sk_sleep);
> + wake_up_interruptible_poll(q->sk.sk_sleep, POLLIN | POLLRDNORM | POLLRDBAND);
> return 0;
> }
>
> @@ -242,7 +244,7 @@ static void macvtap_sock_write_space(struct sock *sk)
> return;
>
> if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
> - wake_up_interruptible_sync(sk->sk_sleep);
> + wake_up_interruptible_poll(sk->sk_sleep, POLLOUT | POLLWRNORM | POLLWRBAND);
> }
>
> static int macvtap_open(struct inode *inode, struct file *file)
> @@ -270,6 +272,8 @@ static int macvtap_open(struct inode *inode, struct file *file)
> init_waitqueue_head(&q->sock.wait);
> q->sock.type = SOCK_RAW;
> q->sock.state = SS_CONNECTED;
> + q->sock.file = file;
> + q->sock.ops = &macvtap_socket_ops;
> sock_init_data(&q->sock, &q->sk);
> q->sk.sk_write_space = macvtap_sock_write_space;
>
> @@ -387,32 +391,20 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
>
> rcu_read_lock_bh();
> vlan = rcu_dereference(q->vlan);
> - macvlan_count_rx(vlan, len, ret == 0, 0);
> + if (vlan)
> + macvlan_count_rx(vlan, len, ret == 0, 0);
> rcu_read_unlock_bh();
>
> return ret ? ret : len;
> }
>
> -static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv,
> - unsigned long count, loff_t pos)
> +static ssize_t macvtap_do_read(struct macvtap_queue *q, struct kiocb *iocb,
> + const struct iovec *iv, unsigned long len,
> + int noblock)
> {
> - struct file *file = iocb->ki_filp;
> - struct macvtap_queue *q = file->private_data;
> -
> DECLARE_WAITQUEUE(wait, current);
> struct sk_buff *skb;
> - ssize_t len, ret = 0;
> -
> - if (!q) {
> - ret = -ENOLINK;
> - goto out;
> - }
> -
> - len = iov_length(iv, count);
> - if (len < 0) {
> - ret = -EINVAL;
> - goto out;
> - }
> + ssize_t ret = 0;
>
> add_wait_queue(q->sk.sk_sleep, &wait);
> while (len) {
> @@ -421,7 +413,7 @@ static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv,
> /* Read frames from the queue */
> skb = skb_dequeue(&q->sk.sk_receive_queue);
> if (!skb) {
> - if (file->f_flags & O_NONBLOCK) {
> + if (noblock) {
> ret = -EAGAIN;
> break;
> }
> @@ -440,7 +432,24 @@ static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv,
>
> current->state = TASK_RUNNING;
> remove_wait_queue(q->sk.sk_sleep, &wait);
> + return ret;
> +}
> +
> +static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv,
> + unsigned long count, loff_t pos)
> +{
> + struct file *file = iocb->ki_filp;
> + struct macvtap_queue *q = file->private_data;
> + ssize_t len, ret = 0;
>
> + len = iov_length(iv, count);
> + if (len < 0) {
> + ret = -EINVAL;
> + goto out;
> + }
> +
> + ret = macvtap_do_read(q, iocb, iv, len, file->f_flags & O_NONBLOCK);
> + ret = min_t(ssize_t, ret, len); /* XXX copied from tun.c. Why? */
> out:
> return ret;
> }
> @@ -538,6 +547,53 @@ static const struct file_operations macvtap_fops = {
> #endif
> };
>
> +static int macvtap_sendmsg(struct kiocb *iocb, struct socket *sock,
> + struct msghdr *m, size_t total_len)
> +{
> + struct macvtap_queue *q = container_of(sock, struct macvtap_queue, sock);
> + return macvtap_get_user(q, m->msg_iov, total_len,
> + m->msg_flags & MSG_DONTWAIT);
> +}
> +
> +static int macvtap_recvmsg(struct kiocb *iocb, struct socket *sock,
> + struct msghdr *m, size_t total_len,
> + int flags)
> +{
> + struct macvtap_queue *q = container_of(sock, struct macvtap_queue, sock);
> + int ret;
> + if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
> + return -EINVAL;
> + ret = macvtap_do_read(q, iocb, m->msg_iov, total_len,
> + flags & MSG_DONTWAIT);
> + if (ret > total_len) {
> + m->msg_flags |= MSG_TRUNC;
> + ret = flags & MSG_TRUNC ? ret : total_len;
> + }
> + return ret;
> +}
> +
> +/* Ops structure to mimic raw sockets with tun */
> +static const struct proto_ops macvtap_socket_ops = {
> + .sendmsg = macvtap_sendmsg,
> + .recvmsg = macvtap_recvmsg,
> +};
> +
> +/* Get an underlying socket object from tun file. Returns error unless file is
> + * attached to a device. The returned object works like a packet socket, it
> + * can be used for sock_sendmsg/sock_recvmsg. The caller is responsible for
> + * holding a reference to the file for as long as the socket is in use. */
> +struct socket *macvtap_get_socket(struct file *file)
> +{
> + struct macvtap_queue *q;
> + if (file->f_op != &macvtap_fops)
> + return ERR_PTR(-EINVAL);
> + q = file->private_data;
> + if (!q)
> + return ERR_PTR(-EBADFD);
> + return &q->sock;
> +}
> +EXPORT_SYMBOL_GPL(macvtap_get_socket);
> +
> static int macvtap_init(void)
> {
> int err;
> diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> index 4c89283..91a324c 100644
> --- a/drivers/vhost/net.c
> +++ b/drivers/vhost/net.c
> @@ -22,6 +22,7 @@
> #include <linux/if_packet.h>
> #include <linux/if_arp.h>
> #include <linux/if_tun.h>
> +#include <linux/if_macvlan.h>
>
> #include <net/sock.h>
>
> @@ -452,13 +453,16 @@ err:
> return ERR_PTR(r);
> }
>
> -static struct socket *get_tun_socket(int fd)
> +static struct socket *get_tap_socket(int fd)
> {
> struct file *file = fget(fd);
> struct socket *sock;
> if (!file)
> return ERR_PTR(-EBADF);
> sock = tun_get_socket(file);
> + if (!IS_ERR(sock))
> + return sock;
> + sock = macvtap_get_socket(file);
> if (IS_ERR(sock))
> fput(file);
> return sock;
> @@ -473,7 +477,7 @@ static struct socket *get_socket(int fd)
> sock = get_raw_socket(fd);
> if (!IS_ERR(sock))
> return sock;
> - sock = get_tun_socket(fd);
> + sock = get_tap_socket(fd);
> if (!IS_ERR(sock))
> return sock;
> return ERR_PTR(-ENOTSOCK);
This will also need a dependency on macvtap in Kconfig.
See how it's done for tun.
> diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
> index 51f1512..7d7f1e3 100644
> --- a/include/linux/if_macvlan.h
> +++ b/include/linux/if_macvlan.h
> @@ -7,6 +7,19 @@
> #include <linux/netlink.h>
> #include <net/netlink.h>
>
> +#if defined(CONFIG_MACVTAP) || defined(CONFIG_MACVTAP_MODULE)
> +struct socket *macvtap_get_socket(struct file *);
> +#else
> +#include <linux/err.h>
> +#include <linux/errno.h>
> +struct file;
> +struct socket;
> +static inline struct socket *macvtap_get_socket(struct file *f)
> +{
> + return ERR_PTR(-EINVAL);
> +}
> +#endif /* CONFIG_MACVTAP */
> +
> struct macvlan_port;
> struct macvtap_queue;
>
> --
> 1.6.3.3
>
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [net-next-2.6 PATCH 2/2] net neigh: Decouple per interface neighbour table controls from binary sysctls
From: Eric W. Biederman @ 2010-02-14 13:27 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <m1fx54kkyo.fsf@fess.ebiederm.org>
Stop computing the number of neighbour table settings we have by
counting the number of binary sysctls. This behaviour was silly
and meant that we could not add another neighbour table setting
without also adding another binary sysctl.
Don't pass the binary sysctl path for neighour table entries
into neigh_sysctl_register. These parameters are no longer
used and so are just dead code.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
include/linux/sysctl.h | 1 -
include/net/neighbour.h | 1 -
net/core/neighbour.c | 7 ++++---
net/ipv4/arp.c | 3 +--
net/ipv4/devinet.c | 3 +--
net/ipv6/addrconf.c | 3 +--
net/ipv6/ndisc.c | 3 +--
7 files changed, 8 insertions(+), 13 deletions(-)
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 7c74e91..f66014c 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -596,7 +596,6 @@ enum {
NET_NEIGH_GC_THRESH3=16,
NET_NEIGH_RETRANS_TIME_MS=17,
NET_NEIGH_REACHABLE_TIME_MS=18,
- __NET_NEIGH_MAX
};
/* /proc/sys/net/dccp */
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index b017320..7834f47 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -251,7 +251,6 @@ extern void neigh_seq_stop(struct seq_file *, void *);
extern int neigh_sysctl_register(struct net_device *dev,
struct neigh_parms *p,
- int p_id, int pdev_id,
char *p_name,
proc_handler *proc_handler);
extern void neigh_sysctl_unregister(struct neigh_parms *p);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index f2efd72..d102f6d 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2556,9 +2556,11 @@ EXPORT_SYMBOL(neigh_app_ns);
#ifdef CONFIG_SYSCTL
+#define NEIGH_VARS_MAX 19
+
static struct neigh_sysctl_table {
struct ctl_table_header *sysctl_header;
- struct ctl_table neigh_vars[__NET_NEIGH_MAX];
+ struct ctl_table neigh_vars[NEIGH_VARS_MAX];
char *dev_name;
} neigh_sysctl_template __read_mostly = {
.neigh_vars = {
@@ -2675,8 +2677,7 @@ static struct neigh_sysctl_table {
};
int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
- int p_id, int pdev_id, char *p_name,
- proc_handler *handler)
+ char *p_name, proc_handler *handler)
{
struct neigh_sysctl_table *t;
const char *dev_name_source = NULL;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 1940b4d..c4dd135 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1284,8 +1284,7 @@ void __init arp_init(void)
dev_add_pack(&arp_packet_type);
arp_proc_init();
#ifdef CONFIG_SYSCTL
- neigh_sysctl_register(NULL, &arp_tbl.parms, NET_IPV4,
- NET_IPV4_NEIGH, "ipv4", NULL);
+ neigh_sysctl_register(NULL, &arp_tbl.parms, "ipv4", NULL);
#endif
register_netdevice_notifier(&arp_netdev_notifier);
}
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index b1eddee..014982b 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1487,8 +1487,7 @@ static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf)
static void devinet_sysctl_register(struct in_device *idev)
{
- neigh_sysctl_register(idev->dev, idev->arp_parms, NET_IPV4,
- NET_IPV4_NEIGH, "ipv4", NULL);
+ neigh_sysctl_register(idev->dev, idev->arp_parms, "ipv4", NULL);
__devinet_sysctl_register(dev_net(idev->dev), idev->dev->name,
&idev->cnf);
}
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 764ad37..c79cbff 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4416,8 +4416,7 @@ static void __addrconf_sysctl_unregister(struct ipv6_devconf *p)
static void addrconf_sysctl_register(struct inet6_dev *idev)
{
- neigh_sysctl_register(idev->dev, idev->nd_parms, NET_IPV6,
- NET_IPV6_NEIGH, "ipv6",
+ neigh_sysctl_register(idev->dev, idev->nd_parms, "ipv6",
&ndisc_ifinfo_sysctl_change);
__addrconf_sysctl_register(dev_net(idev->dev), idev->dev->name,
idev, &idev->cnf);
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 2dfec6b..8bcc4b7 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1820,8 +1820,7 @@ int __init ndisc_init(void)
neigh_table_init(&nd_tbl);
#ifdef CONFIG_SYSCTL
- err = neigh_sysctl_register(NULL, &nd_tbl.parms, NET_IPV6,
- NET_IPV6_NEIGH, "ipv6",
+ err = neigh_sysctl_register(NULL, &nd_tbl.parms, "ipv6",
&ndisc_ifinfo_sysctl_change);
if (err)
goto out_unregister_pernet;
--
1.6.5.2.143.g8cc62
^ permalink raw reply related
* [net-next-2.6 PATCH 1/2] net ipv4: Decouple ipv4 interface parameters from binary sysctl numbers
From: Eric W. Biederman @ 2010-02-14 13:25 UTC (permalink / raw)
To: David Miller; +Cc: netdev
Stop using the binary sysctl enumeartion in sysctl.h as an index into
a per interface array. This leads to unnecessary binary sysctl number
allocation, and a fragility in data structure and implementation
because of unnecessary coupling.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
include/linux/inetdevice.h | 42 ++++++++++++++++++++++++++++++++++++------
include/linux/sysctl.h | 4 ----
net/ipv4/devinet.c | 26 +++++++++++++-------------
3 files changed, 49 insertions(+), 23 deletions(-)
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index cf25780..2be1a1a 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -10,10 +10,40 @@
#include <linux/timer.h>
#include <linux/sysctl.h>
+enum
+{
+ IPV4_DEVCONF_FORWARDING=1,
+ IPV4_DEVCONF_MC_FORWARDING,
+ IPV4_DEVCONF_PROXY_ARP,
+ IPV4_DEVCONF_ACCEPT_REDIRECTS,
+ IPV4_DEVCONF_SECURE_REDIRECTS,
+ IPV4_DEVCONF_SEND_REDIRECTS,
+ IPV4_DEVCONF_SHARED_MEDIA,
+ IPV4_DEVCONF_RP_FILTER,
+ IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE,
+ IPV4_DEVCONF_BOOTP_RELAY,
+ IPV4_DEVCONF_LOG_MARTIANS,
+ IPV4_DEVCONF_TAG,
+ IPV4_DEVCONF_ARPFILTER,
+ IPV4_DEVCONF_MEDIUM_ID,
+ IPV4_DEVCONF_NOXFRM,
+ IPV4_DEVCONF_NOPOLICY,
+ IPV4_DEVCONF_FORCE_IGMP_VERSION,
+ IPV4_DEVCONF_ARP_ANNOUNCE,
+ IPV4_DEVCONF_ARP_IGNORE,
+ IPV4_DEVCONF_PROMOTE_SECONDARIES,
+ IPV4_DEVCONF_ARP_ACCEPT,
+ IPV4_DEVCONF_ARP_NOTIFY,
+ IPV4_DEVCONF_ACCEPT_LOCAL,
+ IPV4_DEVCONF_SRC_VMARK,
+ IPV4_DEVCONF_PROXY_ARP_PVLAN,
+ __IPV4_DEVCONF_MAX
+};
+
struct ipv4_devconf {
void *sysctl;
- int data[__NET_IPV4_CONF_MAX - 1];
- DECLARE_BITMAP(state, __NET_IPV4_CONF_MAX - 1);
+ int data[__IPV4_DEVCONF_MAX - 1];
+ DECLARE_BITMAP(state, __IPV4_DEVCONF_MAX - 1);
};
struct in_device {
@@ -40,7 +70,7 @@ struct in_device {
struct rcu_head rcu_head;
};
-#define IPV4_DEVCONF(cnf, attr) ((cnf).data[NET_IPV4_CONF_ ## attr - 1])
+#define IPV4_DEVCONF(cnf, attr) ((cnf).data[IPV4_DEVCONF_ ## attr - 1])
#define IPV4_DEVCONF_ALL(net, attr) \
IPV4_DEVCONF((*(net)->ipv4.devconf_all), attr)
@@ -60,13 +90,13 @@ static inline void ipv4_devconf_set(struct in_device *in_dev, int index,
static inline void ipv4_devconf_setall(struct in_device *in_dev)
{
- bitmap_fill(in_dev->cnf.state, __NET_IPV4_CONF_MAX - 1);
+ bitmap_fill(in_dev->cnf.state, __IPV4_DEVCONF_MAX - 1);
}
#define IN_DEV_CONF_GET(in_dev, attr) \
- ipv4_devconf_get((in_dev), NET_IPV4_CONF_ ## attr)
+ ipv4_devconf_get((in_dev), IPV4_DEVCONF_ ## attr)
#define IN_DEV_CONF_SET(in_dev, attr, val) \
- ipv4_devconf_set((in_dev), NET_IPV4_CONF_ ## attr, (val))
+ ipv4_devconf_set((in_dev), IPV4_DEVCONF_ ## attr, (val))
#define IN_DEV_ANDCONF(in_dev, attr) \
(IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr) && \
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 9f236cd..7c74e91 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -481,10 +481,6 @@ enum
NET_IPV4_CONF_PROMOTE_SECONDARIES=20,
NET_IPV4_CONF_ARP_ACCEPT=21,
NET_IPV4_CONF_ARP_NOTIFY=22,
- NET_IPV4_CONF_ACCEPT_LOCAL=23,
- NET_IPV4_CONF_SRC_VMARK=24,
- NET_IPV4_CONF_PROXY_ARP_PVLAN=25,
- __NET_IPV4_CONF_MAX
};
/* /proc/sys/net/ipv4/netfilter */
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index cd71a39..b1eddee 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -64,20 +64,20 @@
static struct ipv4_devconf ipv4_devconf = {
.data = {
- [NET_IPV4_CONF_ACCEPT_REDIRECTS - 1] = 1,
- [NET_IPV4_CONF_SEND_REDIRECTS - 1] = 1,
- [NET_IPV4_CONF_SECURE_REDIRECTS - 1] = 1,
- [NET_IPV4_CONF_SHARED_MEDIA - 1] = 1,
+ [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1,
+ [IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1,
+ [IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1,
+ [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1,
},
};
static struct ipv4_devconf ipv4_devconf_dflt = {
.data = {
- [NET_IPV4_CONF_ACCEPT_REDIRECTS - 1] = 1,
- [NET_IPV4_CONF_SEND_REDIRECTS - 1] = 1,
- [NET_IPV4_CONF_SECURE_REDIRECTS - 1] = 1,
- [NET_IPV4_CONF_SHARED_MEDIA - 1] = 1,
- [NET_IPV4_CONF_ACCEPT_SOURCE_ROUTE - 1] = 1,
+ [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1,
+ [IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1,
+ [IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1,
+ [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1,
+ [IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE - 1] = 1,
},
};
@@ -1360,7 +1360,7 @@ int ipv4_doint_and_flush(ctl_table *ctl, int write,
{ \
.procname = name, \
.data = ipv4_devconf.data + \
- NET_IPV4_CONF_ ## attr - 1, \
+ IPV4_DEVCONF_ ## attr - 1, \
.maxlen = sizeof(int), \
.mode = mval, \
.proc_handler = proc, \
@@ -1381,7 +1381,7 @@ int ipv4_doint_and_flush(ctl_table *ctl, int write,
static struct devinet_sysctl_table {
struct ctl_table_header *sysctl_header;
- struct ctl_table devinet_vars[__NET_IPV4_CONF_MAX];
+ struct ctl_table devinet_vars[__IPV4_DEVCONF_MAX];
char *dev_name;
} devinet_sysctl = {
.devinet_vars = {
@@ -1503,7 +1503,7 @@ static struct ctl_table ctl_forward_entry[] = {
{
.procname = "ip_forward",
.data = &ipv4_devconf.data[
- NET_IPV4_CONF_FORWARDING - 1],
+ IPV4_DEVCONF_FORWARDING - 1],
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = devinet_sysctl_forward,
@@ -1547,7 +1547,7 @@ static __net_init int devinet_init_net(struct net *net)
if (tbl == NULL)
goto err_alloc_ctl;
- tbl[0].data = &all->data[NET_IPV4_CONF_FORWARDING - 1];
+ tbl[0].data = &all->data[IPV4_DEVCONF_FORWARDING - 1];
tbl[0].extra1 = all;
tbl[0].extra2 = net;
#endif
--
1.6.5.2.143.g8cc62
^ permalink raw reply related
* [PATCH 2/2] X25: Dont let x25_bind use addresses containing characters
From: Andrew Hendry @ 2010-02-14 12:00 UTC (permalink / raw)
To: netdev, linux-kernel
Addresses should be all digits.
Stops x25_bind using addresses containing characters.
Signed-off-by: Andrew Hendry <andrew.hendry@gmail.com>
---
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 6c7104e..8cc7583 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -55,6 +55,7 @@
#include <linux/notifier.h>
#include <linux/init.h>
#include <linux/compat.h>
+#include <linux/ctype.h>
#include <net/x25.h>
#include <net/compat.h>
@@ -648,7 +649,7 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
struct sock *sk = sock->sk;
struct sockaddr_x25 *addr = (struct sockaddr_x25 *)uaddr;
- int rc = 0;
+ int len, i, rc = 0;
lock_kernel();
if (!sock_flag(sk, SOCK_ZAPPED) ||
@@ -658,6 +659,14 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
goto out;
}
+ len = strlen(addr->sx25_addr.x25_addr);
+ for (i = 0; i < len; i++) {
+ if (!isdigit(addr->sx25_addr.x25_addr[i])) {
+ rc = -EINVAL;
+ goto out;
+ }
+ }
+
x25_sk(sk)->source_addr = addr->sx25_addr;
x25_insert_socket(sk);
sock_reset_flag(sk, SOCK_ZAPPED);
--
1.6.3.3
^ permalink raw reply related
* [PATCH 1/2] X25: Fix x25_create errors for bad protocol and ENOBUFS
From: Andrew Hendry @ 2010-02-14 12:00 UTC (permalink / raw)
To: netdev, linux-kernel
alloc_socket failures should return -ENOBUFS
a bad protocol should return -EINVAL
Signed-off-by: Andrew Hendry <andrew.hendry@gmail.com>
---
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index e3219e4..6c7104e 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -512,15 +512,20 @@ static int x25_create(struct net *net, struct socket *sock, int protocol,
{
struct sock *sk;
struct x25_sock *x25;
- int rc = -ESOCKTNOSUPPORT;
+ int rc = -EAFNOSUPPORT;
if (!net_eq(net, &init_net))
- return -EAFNOSUPPORT;
+ goto out;
+
+ rc = -ESOCKTNOSUPPORT;
+ if (sock->type != SOCK_SEQPACKET)
+ goto out;
- if (sock->type != SOCK_SEQPACKET || protocol)
+ rc = -EINVAL;
+ if (protocol)
goto out;
- rc = -ENOMEM;
+ rc = -ENOBUFS;
if ((sk = x25_alloc_socket(net)) == NULL)
goto out;
--
1.6.3.3
^ permalink raw reply related
* includes build break - was Re: [net-next-2.6 PATCH v5 0/3] Introduce n-tuple ethtool support
From: Oliver Hartkopp @ 2010-02-14 11:56 UTC (permalink / raw)
To: David Miller, peter.p.waskiewicz.jr; +Cc: jeffrey.t.kirsher, netdev, gospo
In-Reply-To: <20100210.195445.190157100.davem@davemloft.net>
David Miller wrote:
> From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
> Date: Wed, 10 Feb 2010 18:07:18 -0800
>
>> One more round of fixes, based on feedback from Patrick McHardy
>>
>> 1) Change the list count to an unsigned value
>> 2) Fix a memory leak
>> 3) Removed an unnecessary list traversal in the ethtool core
>> 4) Moved all list destruction to a helper function, allowing the driver
>> to control when it clears the list (aside from when free_netdev() kills
>> the cached list).
>
> All applied, thanks.
>
Hi Peter,
compiling the latest net-next-2.6 i got this problem:
CHECK include/linux (358 files)
/home/hartko/net-next-2.6/usr/include/linux/ethtool.h:17: included file 'linux/rculist.h' is not exported
Which has been introduced by
http://git.kernel.org/?p=linux/kernel/git/davem/net-next-2.6.git;a=commitdiff;h=15682bc488d4af8c9bb998844a94281025e0a333
("ethtool: Introduce n-tuple filter programming support")
The patch below fixes the issue.
Signed-off-by: Oliver Hartkopp <oliver@hartkopp.net>
---
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index a3cac53..83a9a53 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -14,7 +14,9 @@
#define _LINUX_ETHTOOL_H
#include <linux/types.h>
+#ifdef __KERNEL__
#include <linux/rculist.h>
+#endif
/* This should work for both 32 and 64 bit userland. */
struct ethtool_cmd {
^ permalink raw reply related
* [PATCH 2/2] tun: socket filter support
From: Michael S. Tsirkin @ 2010-02-14 11:01 UTC (permalink / raw)
Cc: David S. Miller, Herbert Xu, Michael S. Tsirkin, Paul Moore,
David Woodhouse, Sridhar Samudrala, netdev, linux-kernel
In-Reply-To: <cover.1266144917.git.mst@redhat.com>
This patch adds Linux Socket Filter support to
tun driver.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
drivers/net/tun.c | 26 ++++++++++++++++++++++++++
include/linux/if_tun.h | 3 +++
2 files changed, 29 insertions(+), 0 deletions(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 5adb3d1..ce1efa4 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -61,6 +61,7 @@
#include <linux/crc32.h>
#include <linux/nsproxy.h>
#include <linux/virtio_net.h>
+#include <linux/rcupdate.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
@@ -366,6 +367,10 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
if (!check_filter(&tun->txflt, skb))
goto drop;
+ if (tun->socket.sk->sk_filter &&
+ sk_filter(tun->socket.sk, skb))
+ goto drop;
+
if (skb_queue_len(&tun->socket.sk->sk_receive_queue) >= dev->tx_queue_len) {
if (!(tun->flags & TUN_ONE_QUEUE)) {
/* Normal queueing mode. */
@@ -1162,6 +1167,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
struct tun_file *tfile = file->private_data;
struct tun_struct *tun;
void __user* argp = (void __user*)arg;
+ struct sock_fprog fprog;
struct ifreq ifr;
int sndbuf;
int ret;
@@ -1309,6 +1315,26 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
tun->socket.sk->sk_sndbuf = sndbuf;
break;
+ case TUNATTACHFILTER:
+ /* Can be set only for TAPs */
+ ret = -EINVAL;
+ if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+ break;
+ ret = -EFAULT;
+ if (copy_from_user(&fprog, argp, sizeof(fprog)))
+ break;
+
+ ret = sk_attach_filter(&fprog, tun->socket.sk);
+ break;
+
+ case TUNDETACHFILTER:
+ /* Can be set only for TAPs */
+ ret = -EINVAL;
+ if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+ break;
+ ret = sk_detach_filter(tun->socket.sk);
+ break;
+
default:
ret = -EINVAL;
break;
diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h
index 404abe0..1350a24 100644
--- a/include/linux/if_tun.h
+++ b/include/linux/if_tun.h
@@ -18,6 +18,7 @@
#include <linux/types.h>
#include <linux/if_ether.h>
+#include <linux/filter.h>
/* Read queue size */
#define TUN_READQ_SIZE 500
@@ -48,6 +49,8 @@
#define TUNGETIFF _IOR('T', 210, unsigned int)
#define TUNGETSNDBUF _IOR('T', 211, int)
#define TUNSETSNDBUF _IOW('T', 212, int)
+#define TUNATTACHFILTER _IOW('T', 213, struct sock_fprog)
+#define TUNDETACHFILTER _IOW('T', 214, struct sock_fprog)
/* TUNSETIFF ifr flags */
#define IFF_TUN 0x0001
--
1.6.6.144.g5c3af
^ permalink raw reply related
* [PATCH 1/2] net: export attach/detach filter routines
From: Michael S. Tsirkin @ 2010-02-14 11:01 UTC (permalink / raw)
Cc: David S. Miller, Herbert Xu, Michael S. Tsirkin, Paul Moore,
David Woodhouse, Sridhar Samudrala, netdev, linux-kernel
In-Reply-To: <cover.1266144917.git.mst@redhat.com>
Export sk_attach_filter/sk_detach_filter routines,
so that tun module can use them.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
net/core/filter.c | 2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/net/core/filter.c b/net/core/filter.c
index 4e0712a..08e40f3 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -530,6 +530,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
sk_filter_delayed_uncharge(sk, old_fp);
return 0;
}
+EXPORT_SYMBOL_GPL(sk_attach_filter);
int sk_detach_filter(struct sock *sk)
{
@@ -546,3 +547,4 @@ int sk_detach_filter(struct sock *sk)
rcu_read_unlock_bh();
return ret;
}
+EXPORT_SYMBOL_GPL(sk_detach_filter);
--
1.6.6.144.g5c3af
^ permalink raw reply related
* [PATCH 0/2] tun: linux socket filter support
From: Michael S. Tsirkin @ 2010-02-14 11:00 UTC (permalink / raw)
To: David S. Miller, Herbert Xu, Michael S. Tsirkin, Paul Moore,
David Woodhouse <David.Woodh
tun module already support RX filtering, however,
this is limited to filtering by mac address.
For virtio host, we also need filtering by vlan.
Rather than adding this directly, it seems cleaner
to add generic socket filter support.
Michael S. Tsirkin (2):
net: export attach/detach filter routines
tun: socket filter support
drivers/net/tun.c | 26 ++++++++++++++++++++++++++
include/linux/if_tun.h | 3 +++
net/core/filter.c | 2 ++
3 files changed, 31 insertions(+), 0 deletions(-)
^ permalink raw reply
* linux-2..6.33-rc7 and b43
From: Thomas Backlund @ 2010-02-14 9:53 UTC (permalink / raw)
Cc: linux-wireless, netdev
Hi,
(please cc me on replies)
We have a user that tried out b43, but got this in the logs:
--- cut ---
65858:Feb 9 22:05:16 elmo kernel: b43-phy2 ERROR: This device does not
support DMA on your system. Please use PIO instead. 65859:Feb 9
22:05:16 elmo kernel: b43-phy2 ERROR: CONFIG_B43_FORCE_PIO must
be set in your kernel configuration.
65860:Feb 9 22:05:16 elmo kernel: b43-phy2 debug: Adding Interface type 2
65861:Feb 9 22:05:16 elmo kernel: b43-phy2 ERROR: Fatal DMA error:
0x00000400, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000
65862:Feb 9 22:05:16 elmo kernel: b43-phy2 ERROR: This device does not
support DMA on your system. Please use PIO instead.
65863:Feb 9 22:05:16 elmo kernel: b43-phy2 ERROR: CONFIG_B43_FORCE_PIO
must be set in your kernel configuration.
--- cut ---
But reading the Kconfig help, it states:
--- cut ---
config B43_FORCE_PIO
bool "Force usage of PIO instead of DMA"
depends on B43 && B43_DEBUG
---help---
This will disable DMA and always enable PIO instead.
Say N!
This is only for debugging the PIO engine code. You do
_NOT_ want to enable this.
--- cut ---
So,
wich one is it ?
Do I belive the dmesg output, or the Kconfig ?
Note,
the b43 works for the user if he enable the CONFIG_B43_FORCE_PIO.
But I'm thinking of this problem from a distro point of view.
Will it break for others if I enable it ?
--
Thomas
^ permalink raw reply
* Re: smsc911x suspend/resume
From: mike @ 2010-02-14 9:01 UTC (permalink / raw)
To: Steve.Glendinning
Cc: netdev, linux-arm-kernel-bounces, LAKML, Daniel Mack,
Ian.Saturley
In-Reply-To: <OFB9598254.A94CFB16-ON802576C5.004BB8B6-802576C7.00655296@smsc.com>
On Thu, Feb 11, 2010 at 06:26:32PM +0000, Steve.Glendinning@smsc.com wrote:
> > Hmm, be careful about switching off power supplies that aren't supposed
> > to be switched off while others are still powered. You can easily
> > destroy hardware with that. Depending on how things are wired up
> > internally, voltages can leak from one unit block to the other. Maybe
> > Steve can can give a statement from official SMSC source about whether
> > it is safe to switch off VDD33A in this case.
>
> I've checked with the chip architects, no power planes should be
> externally
> switched off in any suspend mode.
The question if they *can* be switched off. With the hardware I have,
most of 3.3V supplies are enabled/disabled with the same control. So, to
have maximal power saving in the system, I just pull this control to
disable 3.3V supplies, VDD33A among them. If smsc9220 can tolerate
switching VDD33A during suspend, I can send a patch that allows proper
wake-up with such conditions.
> Steve
^ permalink raw reply
* Re: [PATCH tip/core/rcu 05/13] net: add checking to rcu_dereference() primitives
From: Eric Dumazet @ 2010-02-14 8:50 UTC (permalink / raw)
To: Michał Mirosław
Cc: Paul E. McKenney, linux-kernel, mingo, laijs, dipankar, akpm,
mathieu.desnoyers, josh, dvhltc, niv, tglx, peterz, rostedt,
Valdis.Kletnieks, dhowells, David Miller, netdev
In-Reply-To: <e2d7436a1002140034h74617164p1a5dc90df3587095@mail.gmail.com>
Le dimanche 14 février 2010 à 09:34 +0100, Michał Mirosław a écrit :
> 2010/2/12 Eric Dumazet <eric.dumazet@gmail.com>:
> > Le jeudi 11 février 2010 à 16:00 -0800, Paul E. McKenney a écrit :
> [...]
> >> @@ -1654,12 +1654,12 @@ static struct dn_route *dn_rt_cache_get_first(struct seq_file *seq)
> >>
> >> for(s->bucket = dn_rt_hash_mask; s->bucket >= 0; --s->bucket) {
> >> rcu_read_lock_bh();
> >> - rt = dn_rt_hash_table[s->bucket].chain;
> >> + rt = rcu_dereference_bh(dn_rt_hash_table[s->bucket].chain);
> >> if (rt)
> >> break;
> >> rcu_read_unlock_bh();
> >> }
> >> - return rcu_dereference(rt);
> >> + return rt;
> >> }
>
> Isn't there a bug? Looks like data pointed to by rt should be
> protected by RCU, but the rcu_read_lock is withdrawn before access.
>
Not really a bug, since we exit from dn_rt_cache_get_first() with
rcu_read_lock_bh()
We call the unlock only if NULL is returned, and rcu_dereference(NULL)
can be done in any context.
Paul had to move the rcu_dereference() so that no lockdep warning
triggers for rcu_dereference(NULL), its more a cleanup than a bug fix.
^ permalink raw reply
* Re: [PATCH tip/core/rcu 05/13] net: add checking to rcu_dereference() primitives
From: Michał Mirosław @ 2010-02-14 8:34 UTC (permalink / raw)
To: Eric Dumazet
Cc: Paul E. McKenney, linux-kernel, mingo, laijs, dipankar, akpm,
mathieu.desnoyers, josh, dvhltc, niv, tglx, peterz, rostedt,
Valdis.Kletnieks, dhowells, David Miller, netdev
In-Reply-To: <1265948152.2891.25.camel@edumazet-laptop>
2010/2/12 Eric Dumazet <eric.dumazet@gmail.com>:
> Le jeudi 11 février 2010 à 16:00 -0800, Paul E. McKenney a écrit :
[...]
>> @@ -1654,12 +1654,12 @@ static struct dn_route *dn_rt_cache_get_first(struct seq_file *seq)
>>
>> for(s->bucket = dn_rt_hash_mask; s->bucket >= 0; --s->bucket) {
>> rcu_read_lock_bh();
>> - rt = dn_rt_hash_table[s->bucket].chain;
>> + rt = rcu_dereference_bh(dn_rt_hash_table[s->bucket].chain);
>> if (rt)
>> break;
>> rcu_read_unlock_bh();
>> }
>> - return rcu_dereference(rt);
>> + return rt;
>> }
Isn't there a bug? Looks like data pointed to by rt should be
protected by RCU, but the rcu_read_lock is withdrawn before access.
Best Regards,
Michał Mirosław
^ permalink raw reply
* Re: [PATCH tip/core/rcu 05/13] net: add checking to rcu_dereference() primitives
From: Ingo Molnar @ 2010-02-14 8:23 UTC (permalink / raw)
To: Eric Dumazet
Cc: Paul E. McKenney, linux-kernel, laijs, dipankar, akpm,
mathieu.desnoyers, josh, dvhltc, niv, tglx, peterz, rostedt,
Valdis.Kletnieks, dhowells, David Miller, netdev
In-Reply-To: <1265948152.2891.25.camel@edumazet-laptop>
* Eric Dumazet <eric.dumazet@gmail.com> wrote:
> Le jeudi 11 f??vrier 2010 ?? 16:00 -0800, Paul E. McKenney a ??crit :
> > Update rcu_dereference() primitives to use new lockdep-based checking.
> > The rcu_dereference() in __in6_dev_get() may be protected either by
> > rcu_read_lock() or RTNL, per Eric Dumazet. The rcu_dereference()
> > in __sk_free() is protected by the fact that it is never reached if an
> > update could change it. Check for this by using rcu_dereference_check()
> > to verify that the struct sock's ->sk_wmem_alloc counter is zero.
> >
> > Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
>
> CC to netdev and David Miller, network maintainer.
>
> Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
>
> Thanks Paul, great work !
Dave, does this look good to you too? Cannot pick up the rest of the patchset
without these checks/annotations into the RCU tree as there's too many
warnings triggering in the networking code. So it's an all-or-nothing
patchset in that regard.
Thanks,
Ingo
^ permalink raw reply
* [PATCH v6 7/7] TCPCT part 2g: parse cookie pair and 64-bit timestamp
From: William Allen Simpson @ 2010-02-14 7:02 UTC (permalink / raw)
To: Linux Kernel Developers, Linux Kernel Network Developers
Cc: Andrew Morton, David Miller
In-Reply-To: <4B7791CF.9030201@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 784 bytes --]
Every bit is sacred. Use as few bits as possible in tcp_options_received.
Group related timestamp flag bits for cache line memory efficiency.
Fix #define spacing for TCP options.
Define and parse 64-bit timestamp extended option (and minor cleanup).
However, only 32-bits are used at this time (permitted by specification).
Parse cookie pair extended option (previously defined).
Handle header extension.
Requires:
net: tcp_header_len_th and tcp_option_len_th
TCPCT part 2f: cleanup tcp_parse_options
Signed-off-by: William.Allen.Simpson@gmail.com
---
include/linux/tcp.h | 12 ++++-
include/net/tcp.h | 45 +++++++++---------
net/ipv4/tcp_input.c | 123 +++++++++++++++++++++++++++++++++++++++++++++----
3 files changed, 146 insertions(+), 34 deletions(-)
[-- Attachment #2: TCPCT+2g6+2.6.33-rc8.patch --]
[-- Type: text/plain, Size: 9899 bytes --]
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 2987ee8..05fa9b2 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -247,7 +247,7 @@ struct tcp_options_received {
u32 ts_recent; /* Time stamp to echo next */
u32 rcv_tsval; /* Time stamp value */
u32 rcv_tsecr; /* Time stamp echo reply */
- u16 saw_tstamp : 1, /* Saw TIMESTAMP on last packet */
+ u16 tstamp64_ok:1, /* Verified with cookie pair */
tstamp_ok : 1, /* TIMESTAMP seen on SYN packet */
dsack : 1, /* D-SACK is scheduled */
wscale_ok : 1, /* Wscale seen on SYN packet */
@@ -260,13 +260,21 @@ struct tcp_options_received {
u8 num_sacks; /* Number of SACK blocks */
u16 user_mss; /* mss requested by user in ioctl */
u16 mss_clamp; /* Maximal mss, negotiated at connection setup */
+
+ /* When the options are extended beyond the standard 40 bytes,
+ * this holds the additional data offset (up to 1,020 bytes).
+ */
+ u8 extended; /* in 32-bit words */
+ u8 saw_tstamp64:1, /* 64-bit TIMESTAMP seen on last packet */
+ saw_tstamp:1, /* TIMESTAMP seen on last packet */
+ __unused:6;
};
static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
{
+ rx_opt->tstamp64_ok = 0;
rx_opt->tstamp_ok = rx_opt->sack_ok = 0;
rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
- rx_opt->cookie_plus = 0;
}
/* This is the max number of SACKS that we'll generate and process. It's safe
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 420e872..4b560d2 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -156,9 +156,8 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
/*
* TCP option
*/
-
-#define TCPOPT_NOP 1 /* Padding */
#define TCPOPT_EOL 0 /* End of options */
+#define TCPOPT_NOP 1 /* Padding */
#define TCPOPT_MSS 2 /* Segment size negotiating */
#define TCPOPT_WINDOW 3 /* Window scaling */
#define TCPOPT_SACK_PERM 4 /* SACK Permitted */
@@ -166,30 +165,32 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
#define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */
#define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */
#define TCPOPT_COOKIE 253 /* Cookie extension (experimental) */
-
-/*
- * TCP option lengths
- */
-
-#define TCPOLEN_MSS 4
-#define TCPOLEN_WINDOW 3
-#define TCPOLEN_SACK_PERM 2
-#define TCPOLEN_TIMESTAMP 10
-#define TCPOLEN_MD5SIG 18
-#define TCPOLEN_COOKIE_BASE 2 /* Cookie-less header extension */
-#define TCPOLEN_COOKIE_PAIR 3 /* Cookie pair header extension */
-#define TCPOLEN_COOKIE_MIN (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MIN)
-#define TCPOLEN_COOKIE_MAX (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MAX)
-
-/* But this is what stacks really send out. */
-#define TCPOLEN_TSTAMP_ALIGNED 12
+#define TCPOPT_TSTAMP64 254 /* 64-bit extension (experimental) */
+
+/* TCP option lengths (same order as above) */
+#define TCPOLEN_MSS 4
+#define TCPOLEN_WINDOW 3
+#define TCPOLEN_SACK_PERM 2
+#define TCPOLEN_SACK_BASE 2
+#define TCPOLEN_SACK_PERBLOCK 8
+#define TCPOLEN_TIMESTAMP 10
+#define TCPOLEN_MD5SIG 18
+#define TCPOLEN_COOKIE_BASE 2 /* Cookie-less header extension */
+#define TCPOLEN_COOKIE_PAIR 4 /* Cookie pair header extension */
+#define TCPOLEN_COOKIE_MIN (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MIN)
+#define TCPOLEN_COOKIE_MAX (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MAX)
+#define TCPOLEN_TSTAMP64 3
+
+/* TCP options 32-bit aligned (same order as above) */
+#define TCPOLEN_MSS_ALIGNED 4
#define TCPOLEN_WSCALE_ALIGNED 4
#define TCPOLEN_SACKPERM_ALIGNED 4
-#define TCPOLEN_SACK_BASE 2
#define TCPOLEN_SACK_BASE_ALIGNED 4
-#define TCPOLEN_SACK_PERBLOCK 8
+#define TCPOLEN_TSTAMP_ALIGNED 12
#define TCPOLEN_MD5SIG_ALIGNED 20
-#define TCPOLEN_MSS_ALIGNED 4
+
+/* TCP option extensions (same order as above) */
+#define TCPOEXT_TSTAMP64 16
/* Flags in tp->nonagle */
#define TCP_NAGLE_OFF 1 /* Nagle's algo is disabled */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2a9ef6b..dcad45b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3725,17 +3725,27 @@ old_ack:
/* Look for tcp options. Normally only called on SYN and SYNACK packets.
* But, this can also be called on packets in the established flow when
* the fast version below fails.
+ *
+ * Returns:
+ * 0 on success
+ * - on failure
*/
int tcp_parse_options(struct sk_buff *skb, const struct tcphdr *th,
struct tcp_options_received *opt_rx, u8 **hvpp, int estab)
{
+ __be32 *xdp = (__be32 *)th + th->doff;
unsigned char *ptr = (unsigned char *)(th + 1);
+ int remaining = skb_headlen(skb) - tcp_header_len_th(th);
int length = tcp_option_len_th(th);
+ int extend = 0;
bool syn = th->syn;
opt_rx->cookie_plus = 0;
+ opt_rx->extended = 0;
+ opt_rx->saw_tstamp64 = 0; /* false */
opt_rx->saw_tstamp = 0; /* false */
+repeat:
while (length > 0) {
int opsize;
int opcode = *ptr++;
@@ -3833,26 +3843,104 @@ int tcp_parse_options(struct sk_buff *skb, const struct tcphdr *th,
/* not yet implemented */
break;
case TCPOLEN_COOKIE_PAIR: {
- /* not yet implemented */
+ int words = ptr[1] & 0xf;
+
+ if (!syn &&
+ *ptr >= words &&
+ words >= (TCP_COOKIE_MIN / 4) &&
+ words <= (TCP_COOKIE_MAX / 4) &&
+ opt_rx->extended == 0) {
+ int bytes = words * 4;
+
+ opt_rx->extended = *ptr;
+ extend = *ptr * 4;
+
+ /* Adjust end_seq, set in
+ * tcp_v[4,6]_rcv()
+ */
+ TCP_SKB_CB(skb)->end_seq -= extend;
+ remaining -= extend;
+
+ if (unlikely(remaining < 0)) {
+ /* missing data!!! */
+ return remaining;
+ }
+ extend -= bytes;
+
+ opt_rx->cookie_plus = bytes
+ + TCPOLEN_COOKIE_BASE;
+ *hvpp = (u8 *)xdp;
+ xdp += words;
+ }
break;
}
case TCPOLEN_COOKIE_MIN+0:
case TCPOLEN_COOKIE_MIN+2:
case TCPOLEN_COOKIE_MIN+4:
case TCPOLEN_COOKIE_MIN+6:
- case TCPOLEN_COOKIE_MAX:
/* 16-bit multiple */
if (syn) {
opt_rx->cookie_plus = opsize;
*hvpp = ptr;
}
break;
+ case TCPOLEN_COOKIE_MAX+0:
+ /* either cookie or cookie pair */
+ if (syn || opt_rx->saw_tstamp64) {
+ opt_rx->cookie_plus = opsize;
+ *hvpp = ptr;
+ }
+ break;
+ case TCPOLEN_COOKIE_MAX+4:
+ case TCPOLEN_COOKIE_MAX+8:
+ case TCPOLEN_COOKIE_MAX+12:
+ case TCPOLEN_COOKIE_MAX+TCP_COOKIE_MAX:
+ /* 32-bit multiple (pair) */
+ if (opt_rx->saw_tstamp64) {
+ opt_rx->cookie_plus = opsize;
+ *hvpp = ptr;
+ }
+ break;
default:
/* ignore option */
break;
};
break;
+ case TCPOPT_TSTAMP64:
+ if (opsize == TCPOLEN_TSTAMP64) {
+ if (!syn &&
+ *ptr >= (TCPOEXT_TSTAMP64 / 4) &&
+ !opt_rx->saw_tstamp &&
+ opt_rx->extended == 0) {
+ opt_rx->extended = *ptr;
+ extend = *ptr * 4;
+
+ /* Adjust end_seq, set in
+ * tcp_v[4,6]_rcv()
+ */
+ TCP_SKB_CB(skb)->end_seq -= extend;
+ remaining -= extend;
+
+ if (unlikely(remaining < 0)) {
+ /* missing data!!! */
+ return remaining;
+ }
+ extend -= TCPOEXT_TSTAMP64;
+
+ /* 64-bits not yet implemented */
+ xdp++;
+ opt_rx->rcv_tsval = ntohl(*xdp);
+ xdp += 2;
+ opt_rx->rcv_tsecr = ntohl(*xdp);
+ xdp++;
+
+ opt_rx->saw_tstamp64 = 1; /* true */
+ opt_rx->saw_tstamp = 1; /* true */
+ }
+ }
+ break;
+
default:
/* skip unrecognized options */
break;
@@ -3861,6 +3949,13 @@ int tcp_parse_options(struct sk_buff *skb, const struct tcphdr *th,
ptr += opsize - 2;
length -= opsize;
}
+
+ if (unlikely(extend > 0)) {
+ ptr = (unsigned char *)xdp;
+ length = extend;
+ extend = 0;
+ goto repeat;
+ }
return 0;
}
@@ -3887,6 +3982,11 @@ static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, struct tcphdr *th)
/* Fast parse options. This hopes to only see timestamps.
* If it is wrong it falls back on tcp_parse_options().
+ *
+ * Returns:
+ * 1 on success, fast
+ * 0 on success, slow
+ * - on failure
*/
static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th,
struct tcp_sock *tp, u8 **hvpp)
@@ -3896,11 +3996,14 @@ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th,
*/
if (th->doff == (sizeof(*th) / 4)) {
tp->rx_opt.saw_tstamp = 0;
+ tp->rx_opt.extended = 0;
return 0;
- } else if (tp->rx_opt.tstamp_ok &&
- th->doff == ((sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) / 4)) {
- if (tcp_parse_aligned_timestamp(tp, th))
- return 1;
+ }
+ if (th->doff == ((sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) / 4) &&
+ tp->rx_opt.tstamp_ok &&
+ tcp_parse_aligned_timestamp(tp, th)) {
+ tp->rx_opt.extended = 0;
+ return 1;
}
return tcp_parse_options(skb, th, &tp->rx_opt, hvpp, 1);
}
@@ -3911,8 +4014,8 @@ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th,
*/
u8 *tcp_parse_md5sig_option(struct tcphdr *th)
{
- int length = (th->doff << 2) - sizeof (*th);
u8 *ptr = (u8*)(th + 1);
+ int length = tcp_option_len_th(th);
/* If the TCP option is too short, we can short cut */
if (length < TCPOLEN_MD5SIG)
@@ -4377,7 +4480,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq)
goto drop;
- __skb_pull(skb, th->doff * 4);
+ __skb_pull(skb, (th->doff + tp->rx_opt.extended) * 4);
TCP_ECN_accept_cwr(tp, skb);
@@ -5038,8 +5141,8 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, struct tcphdr *th)
/* Do we wait for any urgent data? - normally not... */
if (tp->urg_data == TCP_URG_NOTYET) {
- u32 ptr = tp->urg_seq - ntohl(th->seq) + (th->doff * 4) -
- th->syn;
+ u32 ptr = ((th->doff + tp->rx_opt.extended) * 4)
+ + tp->urg_seq - ntohl(th->seq) - th->syn;
/* Is the urgent pointer pointing into this packet? */
if (ptr < skb->len) {
--
1.6.3.3
^ permalink raw reply related
* [PATCH v4 6/7] TCPCT part 2f: cleanup tcp_parse_options
From: William Allen Simpson @ 2010-02-14 6:41 UTC (permalink / raw)
To: Linux Kernel Developers, Linux Kernel Network Developers
Cc: Andrew Morton, David Miller
In-Reply-To: <4B7791CF.9030201@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 757 bytes --]
Split switch, shift cases to the left, fix most lines beyond column 80.
Prepare (future) error return.
Repair net/ipv4/tcp_ipv4.c errors with goto targets, overlooked by
David Miller in commit bb5b7c11263dbbe78253cd05945a6bf8f55add8e
Requires:
TCPCT part 1g: Responder Cookie => Initiator
net: tcp_header_len_th and tcp_option_len_th
Signed-off-by: William.Allen.Simpson@gmail.com
---
include/net/tcp.h | 3 +-
net/ipv4/syncookies.c | 9 ++-
net/ipv4/tcp_input.c | 223 ++++++++++++++++++++++++++--------------------
net/ipv4/tcp_ipv4.c | 10 ++-
net/ipv4/tcp_minisocks.c | 14 ++-
net/ipv6/syncookies.c | 9 ++-
net/ipv6/tcp_ipv6.c | 6 +-
7 files changed, 163 insertions(+), 111 deletions(-)
[-- Attachment #2: TCPCT+2f4+2.6.33-rc8.patch --]
[-- Type: text/plain, Size: 14087 bytes --]
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6b0d7e9..420e872 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -403,7 +403,8 @@ extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk,
size_t len, int nonblock,
int flags, int *addr_len);
-extern void tcp_parse_options(struct sk_buff *skb,
+extern int tcp_parse_options(struct sk_buff *skb,
+ const struct tcphdr *th,
struct tcp_options_received *opt_rx,
u8 **hvpp,
int estab);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 66fd80e..d1f45ad 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -255,15 +255,16 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
{
struct tcp_options_received tcp_opt;
u8 *hash_location;
+ struct rtable *rt;
+ struct request_sock *req;
struct inet_request_sock *ireq;
struct tcp_request_sock *treq;
struct tcp_sock *tp = tcp_sk(sk);
const struct tcphdr *th = tcp_hdr(skb);
__u32 cookie = ntohl(th->ack_seq) - 1;
struct sock *ret = sk;
- struct request_sock *req;
int mss;
- struct rtable *rt;
+ int parsed;
__u8 rcv_wscale;
if (!sysctl_tcp_syncookies || !th->ack)
@@ -279,7 +280,9 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
/* check for timestamp cookie support */
memset(&tcp_opt, 0, sizeof(tcp_opt));
- tcp_parse_options(skb, &tcp_opt, &hash_location, 0);
+ parsed = tcp_parse_options(skb, th, &tcp_opt, &hash_location, 0);
+ if (parsed < 0)
+ goto out;
if (tcp_opt.saw_tstamp)
cookie_check_timestamp(&tcp_opt);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 165040e..2a9ef6b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3726,122 +3726,149 @@ old_ack:
* But, this can also be called on packets in the established flow when
* the fast version below fails.
*/
-void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
- u8 **hvpp, int estab)
+int tcp_parse_options(struct sk_buff *skb, const struct tcphdr *th,
+ struct tcp_options_received *opt_rx, u8 **hvpp, int estab)
{
- unsigned char *ptr;
- struct tcphdr *th = tcp_hdr(skb);
- int length = (th->doff * 4) - sizeof(struct tcphdr);
+ unsigned char *ptr = (unsigned char *)(th + 1);
+ int length = tcp_option_len_th(th);
+ bool syn = th->syn;
- ptr = (unsigned char *)(th + 1);
- opt_rx->saw_tstamp = 0;
+ opt_rx->cookie_plus = 0;
+ opt_rx->saw_tstamp = 0; /* false */
while (length > 0) {
- int opcode = *ptr++;
int opsize;
+ int opcode = *ptr++;
switch (opcode) {
case TCPOPT_EOL:
- return;
+ length = 0;
+ continue;
case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */
length--;
continue;
default:
- opsize = *ptr++;
- if (opsize < 2) /* "silly options" */
- return;
- if (opsize > length)
- return; /* don't parse partial options */
- switch (opcode) {
- case TCPOPT_MSS:
- if (opsize == TCPOLEN_MSS && th->syn && !estab) {
- u16 in_mss = get_unaligned_be16(ptr);
- if (in_mss) {
- if (opt_rx->user_mss &&
- opt_rx->user_mss < in_mss)
- in_mss = opt_rx->user_mss;
- opt_rx->mss_clamp = in_mss;
- }
- }
- break;
- case TCPOPT_WINDOW:
- if (opsize == TCPOLEN_WINDOW && th->syn &&
- !estab && sysctl_tcp_window_scaling) {
- __u8 snd_wscale = *(__u8 *)ptr;
- opt_rx->wscale_ok = 1;
- if (snd_wscale > 14) {
- if (net_ratelimit())
- printk(KERN_INFO "tcp_parse_options: Illegal window "
- "scaling value %d >14 received.\n",
- snd_wscale);
- snd_wscale = 14;
- }
- opt_rx->snd_wscale = snd_wscale;
- }
- break;
- case TCPOPT_TIMESTAMP:
- if ((opsize == TCPOLEN_TIMESTAMP) &&
- ((estab && opt_rx->tstamp_ok) ||
- (!estab && sysctl_tcp_timestamps))) {
- opt_rx->saw_tstamp = 1;
- opt_rx->rcv_tsval = get_unaligned_be32(ptr);
- opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4);
- }
- break;
- case TCPOPT_SACK_PERM:
- if (opsize == TCPOLEN_SACK_PERM && th->syn &&
- !estab && sysctl_tcp_sack) {
- opt_rx->sack_ok = 1;
- tcp_sack_reset(opt_rx);
+ /* fallthru */
+ break;
+ };
+
+ opsize = *ptr++;
+ if (opsize < 2 || opsize > length) {
+ /* don't parse partial options */
+ break;
+ }
+
+ switch (opcode) {
+ case TCPOPT_MSS:
+ if (opsize == TCPOLEN_MSS && syn && !estab) {
+ u16 in_mss = get_unaligned_be16(ptr);
+ if (in_mss) {
+ if (opt_rx->user_mss &&
+ opt_rx->user_mss < in_mss)
+ in_mss = opt_rx->user_mss;
+ opt_rx->mss_clamp = in_mss;
}
- break;
+ }
+ break;
- case TCPOPT_SACK:
- if ((opsize >= (TCPOLEN_SACK_BASE + TCPOLEN_SACK_PERBLOCK)) &&
- !((opsize - TCPOLEN_SACK_BASE) % TCPOLEN_SACK_PERBLOCK) &&
- opt_rx->sack_ok) {
- TCP_SKB_CB(skb)->sacked = (ptr - 2) - (unsigned char *)th;
+ case TCPOPT_WINDOW:
+ if (opsize == TCPOLEN_WINDOW && syn &&
+ !estab && sysctl_tcp_window_scaling) {
+ __u8 snd_wscale = *(__u8 *)ptr;
+ opt_rx->wscale_ok = 1;
+ if (snd_wscale > 14) {
+ if (net_ratelimit())
+ printk(KERN_INFO
+ "tcp_parse_options: "
+ "window scaling value "
+ "%d > 14 received.\n",
+ snd_wscale);
+ snd_wscale = 14;
}
- break;
+ opt_rx->snd_wscale = snd_wscale;
+ }
+ break;
+
+ case TCPOPT_SACK_PERM:
+ if (opsize == TCPOLEN_SACK_PERM && syn &&
+ !estab && sysctl_tcp_sack) {
+ opt_rx->sack_ok = 1;
+ tcp_sack_reset(opt_rx);
+ }
+ break;
+
+ case TCPOPT_SACK:
+ if ((opsize >= (TCPOLEN_SACK_BASE + TCPOLEN_SACK_PERBLOCK)) &&
+ !((opsize - TCPOLEN_SACK_BASE) % TCPOLEN_SACK_PERBLOCK) &&
+ opt_rx->sack_ok) {
+ TCP_SKB_CB(skb)->sacked = (ptr - 2)
+ - (unsigned char *)th;
+ }
+ break;
+
+ case TCPOPT_TIMESTAMP:
+ if ((opsize == TCPOLEN_TIMESTAMP) &&
+ ((estab && opt_rx->tstamp_ok) ||
+ (!estab && sysctl_tcp_timestamps))) {
+ opt_rx->saw_tstamp = 1;
+ opt_rx->rcv_tsval = get_unaligned_be32(ptr);
+ opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4);
+ }
+ break;
#ifdef CONFIG_TCP_MD5SIG
- case TCPOPT_MD5SIG:
- /*
- * The MD5 Hash has already been
- * checked (see tcp_v{4,6}_do_rcv()).
- */
- break;
+ case TCPOPT_MD5SIG:
+ /*
+ * The MD5 Hash has already been
+ * checked (see tcp_v{4,6}_do_rcv()).
+ */
+ break;
#endif
- case TCPOPT_COOKIE:
- /* This option is variable length.
- */
- switch (opsize) {
- case TCPOLEN_COOKIE_BASE:
- /* not yet implemented */
- break;
- case TCPOLEN_COOKIE_PAIR:
- /* not yet implemented */
- break;
- case TCPOLEN_COOKIE_MIN+0:
- case TCPOLEN_COOKIE_MIN+2:
- case TCPOLEN_COOKIE_MIN+4:
- case TCPOLEN_COOKIE_MIN+6:
- case TCPOLEN_COOKIE_MAX:
- /* 16-bit multiple */
+ case TCPOPT_COOKIE:
+ if (opt_rx->cookie_plus != 0) {
+ /* discard duplicate */
+ break;
+ }
+ switch (opsize) {
+ case TCPOLEN_COOKIE_BASE:
+ /* not yet implemented */
+ break;
+ case TCPOLEN_COOKIE_PAIR: {
+ /* not yet implemented */
+ break;
+ }
+ case TCPOLEN_COOKIE_MIN+0:
+ case TCPOLEN_COOKIE_MIN+2:
+ case TCPOLEN_COOKIE_MIN+4:
+ case TCPOLEN_COOKIE_MIN+6:
+ case TCPOLEN_COOKIE_MAX:
+ /* 16-bit multiple */
+ if (syn) {
opt_rx->cookie_plus = opsize;
*hvpp = ptr;
- default:
- /* ignore option */
- break;
- };
+ }
+ break;
+ default:
+ /* ignore option */
break;
};
+ break;
- ptr += opsize-2;
- length -= opsize;
- }
+ default:
+ /* skip unrecognized options */
+ break;
+ };
+
+ ptr += opsize - 2;
+ length -= opsize;
}
+ return 0;
}
+/*
+ * Returns:
+ * 1 on success
+ * 0 on failure
+ */
static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, struct tcphdr *th)
{
__be32 *ptr = (__be32 *)(th + 1);
@@ -3875,8 +3902,7 @@ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th,
if (tcp_parse_aligned_timestamp(tp, th))
return 1;
}
- tcp_parse_options(skb, &tp->rx_opt, hvpp, 1);
- return 1;
+ return tcp_parse_options(skb, th, &tp->rx_opt, hvpp, 1);
}
#ifdef CONFIG_TCP_MD5SIG
@@ -5127,10 +5153,13 @@ static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
{
u8 *hash_location;
struct tcp_sock *tp = tcp_sk(sk);
+ int parsed = tcp_fast_parse_options(skb, th, tp, &hash_location);
+
+ if (parsed < 0)
+ goto discard;
/* RFC1323: H1. Apply PAWS check first. */
- if (tcp_fast_parse_options(skb, th, tp, &hash_location) &&
- tp->rx_opt.saw_tstamp &&
+ if (tp->rx_opt.saw_tstamp &&
tcp_paws_discard(sk, skb)) {
if (!th->rst) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
@@ -5410,8 +5439,10 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
struct tcp_cookie_values *cvp = tp->cookie_values;
int saved_clamp = tp->rx_opt.mss_clamp;
int queued = 0;
+ int parsed = tcp_parse_options(skb, th, &tp->rx_opt, &hash_location, 0);
- tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0);
+ if (parsed < 0)
+ goto discard;
if (th->ack) {
/* rfc793:
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f999e06..3f0813f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1215,6 +1215,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
struct tcp_extend_values tmp_ext;
struct tcp_options_received tmp_opt;
+ int parsed;
u8 *hash_location;
struct request_sock *req;
struct inet_request_sock *ireq;
@@ -1265,7 +1266,10 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_clear_options(&tmp_opt);
tmp_opt.mss_clamp = TCP_MSS_DEFAULT;
tmp_opt.user_mss = tp->rx_opt.user_mss;
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
+ parsed = tcp_parse_options(skb, tcp_hdr(skb), &tmp_opt, &hash_location,
+ 0);
+ if (parsed < 0)
+ goto drop_and_free;
if (tmp_opt.cookie_plus > 0 &&
tmp_opt.saw_tstamp &&
@@ -1278,7 +1282,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
int l = tmp_opt.cookie_plus - TCPOLEN_COOKIE_BASE;
if (tcp_cookie_generator(&tmp_ext.cookie_bakery[0]) != 0)
- goto drop_and_release;
+ goto drop_and_free;
/* Secret recipe starts with IP addresses */
*mess++ ^= daddr;
@@ -1299,7 +1303,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
tmp_ext.cookie_out_never = 1; /* true */
tmp_ext.cookie_plus = 0;
} else {
- goto drop_and_release;
+ goto drop_and_free;
}
tmp_ext.cookie_in_always = tp->rx_opt.cookie_in_always;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 37b7536..0d42635 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -97,9 +97,12 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
+ int parsed = tcp_parse_options(skb, th, &tmp_opt,
+ &hash_location, 0);
- if (tmp_opt.saw_tstamp) {
+ if (parsed < 0) {
+ paws_reject = 1; /* true */
+ } else if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = tcptw->tw_ts_recent;
tmp_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
paws_reject = tcp_paws_reject(&tmp_opt, th->rst);
@@ -528,9 +531,12 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(struct tcphdr)>>2)) {
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
+ int parsed = tcp_parse_options(skb, th, &tmp_opt,
+ &hash_location, 0);
- if (tmp_opt.saw_tstamp) {
+ if (parsed < 0) {
+ paws_reject = 1; /* true */
+ } else if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = req->ts_recent;
/* We do not store true stamp, but it is not required,
* it can be estimated (approximately)
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 7208a06..a0905b4 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -161,6 +161,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
{
struct tcp_options_received tcp_opt;
u8 *hash_location;
+ struct dst_entry *dst;
+ struct request_sock *req;
struct inet_request_sock *ireq;
struct inet6_request_sock *ireq6;
struct tcp_request_sock *treq;
@@ -169,9 +171,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
const struct tcphdr *th = tcp_hdr(skb);
__u32 cookie = ntohl(th->ack_seq) - 1;
struct sock *ret = sk;
- struct request_sock *req;
int mss;
- struct dst_entry *dst;
+ int parsed;
__u8 rcv_wscale;
if (!sysctl_tcp_syncookies || !th->ack)
@@ -187,7 +188,9 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
/* check for timestamp cookie support */
memset(&tcp_opt, 0, sizeof(tcp_opt));
- tcp_parse_options(skb, &tcp_opt, &hash_location, 0);
+ parsed = tcp_parse_options(skb, th, &tcp_opt, &hash_location, 0);
+ if (parsed < 0)
+ goto out;
if (tcp_opt.saw_tstamp)
cookie_check_timestamp(&tcp_opt);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 3d08a4d..e15e4f6 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1164,6 +1164,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
{
struct tcp_extend_values tmp_ext;
struct tcp_options_received tmp_opt;
+ int parsed;
u8 *hash_location;
struct request_sock *req;
struct inet6_request_sock *treq;
@@ -1207,7 +1208,10 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_clear_options(&tmp_opt);
tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
tmp_opt.user_mss = tp->rx_opt.user_mss;
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
+ parsed = tcp_parse_options(skb, tcp_hdr(skb), &tmp_opt, &hash_location,
+ 0);
+ if (parsed < 0)
+ goto drop_and_free;
if (tmp_opt.cookie_plus > 0 &&
tmp_opt.saw_tstamp &&
--
1.6.3.3
^ permalink raw reply related
* [PATCH v3 5/7] TCPCT part 2e: accept SYNACK data
From: William Allen Simpson @ 2010-02-14 6:26 UTC (permalink / raw)
To: Linux Kernel Developers, Linux Kernel Network Developers
Cc: Andrew Morton, David Miller
In-Reply-To: <4B7791CF.9030201@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 709 bytes --]
When accompanied by cookie option, Initiator (client) queues incoming
SYNACK transaction data.
This is a straightforward re-implementation of an earlier (year-old)
patch that no longer applies cleanly, with permission of the original
author (Adam Langley). The patch was previously reviewed:
http://thread.gmane.org/gmane.linux.network/102586
This function will also be used in subsequent patches that implement
additional features.
Requires:
TCPCT part 1g: Responder Cookie => Initiator
net: tcp_header_len_th and tcp_option_len_th
Signed-off-by: William.Allen.Simpson@gmail.com
---
net/ipv4/tcp_input.c | 26 +++++++++++++++++++++++++-
1 files changed, 25 insertions(+), 1 deletions(-)
[-- Attachment #2: TCPCT+2e3+2.6.33-rc8.patch --]
[-- Type: text/plain, Size: 2057 bytes --]
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8e0f6ae..165040e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5395,6 +5395,12 @@ discard:
return 0;
}
+/*
+ * Returns:
+ * +1 on reset,
+ * 0 success and/or SYNACK data,
+ * -1 on discard.
+ */
static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
struct tcphdr *th)
{
@@ -5403,6 +5409,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_cookie_values *cvp = tp->cookie_values;
int saved_clamp = tp->rx_opt.mss_clamp;
+ int queued = 0;
tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0);
@@ -5509,6 +5516,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
- TCPOLEN_COOKIE_BASE;
int cookie_pair_size = cookie_size
+ cvp->cookie_desired;
+ int tcp_header_len = tcp_header_len_th(th);
/* A cookie extension option was sent and returned.
* Note that each incoming SYNACK replaces the
@@ -5524,6 +5532,19 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
hash_location, cookie_size);
cvp->cookie_pair_size = cookie_pair_size;
}
+
+ queued = skb->len - tcp_header_len;
+ if (queued > 0) {
+ /* Queue incoming transaction data. */
+ __skb_pull(skb, tcp_header_len);
+ __skb_queue_tail(&sk->sk_receive_queue, skb);
+ skb_set_owner_r(skb, sk);
+ sk->sk_data_ready(sk, 0);
+ cvp->s_data_in = 1; /* true */
+ tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+ tp->rcv_wup = TCP_SKB_CB(skb)->end_seq;
+ tp->copied_seq = TCP_SKB_CB(skb)->seq + 1;
+ }
}
smp_mb();
@@ -5577,11 +5598,14 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
TCP_DELACK_MAX, TCP_RTO_MAX);
discard:
- __kfree_skb(skb);
+ if (queued <= 0)
+ __kfree_skb(skb);
return 0;
} else {
tcp_send_ack(sk);
}
+ if (queued > 0)
+ return 0;
return -1;
}
--
1.6.3.3
^ permalink raw reply related
* [PATCH v4 4/7] tcp: input header length, prediction, and timestamp bugs
From: William Allen Simpson @ 2010-02-14 6:21 UTC (permalink / raw)
To: Linux Kernel Developers, Linux Kernel Network Developers
Cc: Andrew Morton, David Miller, Andi Kleen
In-Reply-To: <4B7791CF.9030201@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 1871 bytes --]
Fix incorrect header prediction flags documentation.
Relieve register pressure in (the i386) fast path by accessing skb->len
directly, instead of carrying a rarely used len parameter.
Eliminate unused len parameters in two other functions.
Don't use output calculated tp->tcp_header_len for input decisions.
While the output header is usually the same as the input (same options
in both directions), that's a poor assumption. In particular, Sack will
be different. Newer options are not guaranteed.
Moreover, in the fast path, that only saved a shift or two. The other
efficiencies in this patch more than make up the difference.
Instead, use tp->rx_opt.tstamp_ok to accurately predict header length.
Likewise, use tp->rx_opt.tstamp_ok for received MSS calculations.
Don't use "sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED" to guess that
the timestamp is present. This may have been OK in the days with fewer
possible options, but various combinations of newer options may yield
the same header length. (This bug is in 3 places.)
Instead, use tp->rx_opt.saw_tstamp to determine a timestamp is present.
There's no need to test buffer length against header length, already
checked by tcp_v[4,6]_rcv(). Straighten code for minor efficiency gain.
Stand-alone patch, originally developed for TCPCT.
Requires:
net: tcp_header_len_th and tcp_option_len_th
tcp: harmonize tcp_vx_rcv header length assumptions
Signed-off-by: William.Allen.Simpson@gmail.com
CC: Andi Kleen <andi@firstfloor.org>
---
include/linux/tcp.h | 6 ++-
include/net/tcp.h | 15 +++++--
net/ipv4/tcp_input.c | 94 ++++++++++++++++++----------------------------
net/ipv4/tcp_ipv4.c | 4 +-
net/ipv4/tcp_minisocks.c | 3 +-
net/ipv4/tcp_probe.c | 2 +-
net/ipv6/tcp_ipv6.c | 4 +-
7 files changed, 58 insertions(+), 70 deletions(-)
[-- Attachment #2: len_th+2d4+2.6.33-rc8.patch --]
[-- Type: text/plain, Size: 9932 bytes --]
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 74728f7..2987ee8 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -301,7 +301,11 @@ struct tcp_sock {
/*
* Header prediction flags
- * 0x5?10 << 16 + snd_wnd in net byte order
+ * S << 28 + TCP_FLAG_ACK + snd_wnd, in net byte order
+ * (PSH flag is ignored)
+ * S is 5 (no options), or 8 (timestamp aligned)
+ * otherwise, 0 to turn it off -- for instance, when there are
+ * holes in receive space.
*/
__be32 pred_flags;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 34f5cc2..6b0d7e9 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -310,13 +310,11 @@ extern int tcp_ioctl(struct sock *sk,
extern int tcp_rcv_state_process(struct sock *sk,
struct sk_buff *skb,
- struct tcphdr *th,
- unsigned len);
+ struct tcphdr *th);
extern int tcp_rcv_established(struct sock *sk,
struct sk_buff *skb,
- struct tcphdr *th,
- unsigned len);
+ struct tcphdr *th);
extern void tcp_rcv_space_adjust(struct sock *sk);
@@ -533,9 +531,16 @@ static inline u32 __tcp_set_rto(const struct tcp_sock *tp)
return (tp->srtt >> 3) + tp->rttvar;
}
+static inline u16 __tcp_fast_path_header_length(const struct tcp_sock *tp)
+{
+ return tp->rx_opt.tstamp_ok
+ ? sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED
+ : sizeof(struct tcphdr);
+}
+
static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
{
- tp->pred_flags = htonl((tp->tcp_header_len << 26) |
+ tp->pred_flags = htonl((__tcp_fast_path_header_length(tp) << (28 - 2)) |
ntohl(TCP_FLAG_ACK) |
snd_wnd);
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 28e0296..8e0f6ae 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -152,7 +152,7 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
* tcp header plus fixed timestamp option length.
* Resulting "len" is MSS free of SACK jitter.
*/
- len -= tcp_sk(sk)->tcp_header_len;
+ len -= __tcp_fast_path_header_length(tcp_sk(sk));
icsk->icsk_ack.last_seg_size = len;
if (len == lss) {
icsk->icsk_ack.rcv_mss = len;
@@ -5206,7 +5206,7 @@ discard:
* tcp_data_queue when everything is OK.
*/
int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
- struct tcphdr *th, unsigned len)
+ struct tcphdr *th)
{
struct tcp_sock *tp = tcp_sk(sk);
int res;
@@ -5225,31 +5225,15 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
* extra cost of the net_bh soft interrupt processing...
* We do checksum and copy also but from device to kernel.
*/
-
- tp->rx_opt.saw_tstamp = 0;
-
- /* pred_flags is 0xS?10 << 16 + snd_wnd
- * if header_prediction is to be made
- * 'S' will always be tp->tcp_header_len >> 2
- * '?' will be 0 for the fast path, otherwise pred_flags is 0 to
- * turn it off (when there are holes in the receive
- * space for instance)
- * PSH flag is ignored.
- */
-
if ((tcp_flag_word(th) & TCP_HP_BITS) == tp->pred_flags &&
TCP_SKB_CB(skb)->seq == tp->rcv_nxt &&
!after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) {
- int tcp_header_len = tp->tcp_header_len;
-
- /* Timestamp header prediction: tcp_header_len
- * is automatically equal to th->doff*4 due to pred_flags
- * match.
- */
+ int tcp_header_len = tcp_header_len_th(th);
- /* Check timestamp */
- if (tcp_header_len == sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) {
- /* No? Slow path! */
+ /* Timestamp header prediction */
+ if (tcp_header_len != sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) {
+ tp->rx_opt.saw_tstamp = 0; /* false */
+ } else {
if (!tcp_parse_aligned_timestamp(tp, th))
goto slow_path;
@@ -5264,35 +5248,12 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
*/
}
- if (len <= tcp_header_len) {
- /* Bulk data transfer: sender */
- if (len == tcp_header_len) {
- /* Predicted packet is in window by definition.
- * seq == rcv_nxt and rcv_wup <= rcv_nxt.
- * Hence, check seq<=rcv_wup reduces to:
- */
- if (tcp_header_len ==
- (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) &&
- tp->rcv_nxt == tp->rcv_wup)
- tcp_store_ts_recent(tp);
-
- /* We know that such packets are checksummed
- * on entry.
- */
- tcp_ack(sk, skb, 0);
- __kfree_skb(skb);
- tcp_data_snd_check(sk);
- return 0;
- } else { /* Header too small */
- TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
- goto discard;
- }
- } else {
+ if (tcp_header_len < skb->len) {
int eaten = 0;
int copied_early = 0;
if (tp->copied_seq == tp->rcv_nxt &&
- len - tcp_header_len <= tp->ucopy.len) {
+ skb->len - tcp_header_len <= tp->ucopy.len) {
#ifdef CONFIG_NET_DMA
if (tcp_dma_try_early_copy(sk, skb, tcp_header_len)) {
copied_early = 1;
@@ -5311,9 +5272,7 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
* seq == rcv_nxt and rcv_wup <= rcv_nxt.
* Hence, check seq<=rcv_wup reduces to:
*/
- if (tcp_header_len ==
- (sizeof(struct tcphdr) +
- TCPOLEN_TSTAMP_ALIGNED) &&
+ if (tp->rx_opt.saw_tstamp &&
tp->rcv_nxt == tp->rcv_wup)
tcp_store_ts_recent(tp);
@@ -5334,8 +5293,7 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
* seq == rcv_nxt and rcv_wup <= rcv_nxt.
* Hence, check seq<=rcv_wup reduces to:
*/
- if (tcp_header_len ==
- (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) &&
+ if (tp->rx_opt.saw_tstamp &&
tp->rcv_nxt == tp->rcv_wup)
tcp_store_ts_recent(tp);
@@ -5376,11 +5334,33 @@ no_ack:
else
sk->sk_data_ready(sk, 0);
return 0;
+ } else {
+ /* Bulk data transfer: sender
+ *
+ * tcp_header_len > skb->len never happens,
+ * already checked by tcp_v[4,6]_rcv()
+ *
+ * Predicted packet is in window by definition.
+ * seq == rcv_nxt and rcv_wup <= rcv_nxt.
+ * Hence, check seq<=rcv_wup reduces to:
+ */
+ if (tp->rx_opt.saw_tstamp &&
+ tp->rcv_nxt == tp->rcv_wup)
+ tcp_store_ts_recent(tp);
+
+ /* We know that such packets are checksummed
+ * on entry.
+ */
+ tcp_ack(sk, skb, 0);
+ __kfree_skb(skb);
+ tcp_data_snd_check(sk);
+ return 0;
}
}
slow_path:
- if (len < (th->doff << 2) || tcp_checksum_complete_user(sk, skb))
+ /* Assumes header and options unchanged since checksum_init() */
+ if (tcp_checksum_complete_user(sk, skb))
goto csum_error;
/*
@@ -5416,7 +5396,7 @@ discard:
}
static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
- struct tcphdr *th, unsigned len)
+ struct tcphdr *th)
{
u8 *hash_location;
struct inet_connection_sock *icsk = inet_csk(sk);
@@ -5693,7 +5673,7 @@ reset_and_undo:
*/
int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
- struct tcphdr *th, unsigned len)
+ struct tcphdr *th)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
@@ -5740,7 +5720,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
goto discard;
case TCP_SYN_SENT:
- queued = tcp_rcv_synsent_state_process(sk, skb, th, len);
+ queued = tcp_rcv_synsent_state_process(sk, skb, th);
if (queued >= 0)
return queued;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 0a76e41..f999e06 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1551,7 +1551,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
TCP_CHECK_TIMER(sk);
- if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) {
+ if (tcp_rcv_established(sk, skb, tcp_hdr(skb))) {
rsk = sk;
goto reset;
}
@@ -1578,7 +1578,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
}
TCP_CHECK_TIMER(sk);
- if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) {
+ if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb))) {
rsk = sk;
goto reset;
}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index f206ee5..37b7536 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -718,8 +718,7 @@ int tcp_child_process(struct sock *parent, struct sock *child,
int state = child->sk_state;
if (!sock_owned_by_user(child)) {
- ret = tcp_rcv_state_process(child, skb, tcp_hdr(skb),
- skb->len);
+ ret = tcp_rcv_state_process(child, skb, tcp_hdr(skb));
/* Wakeup parent, send SIGIO */
if (state == TCP_SYN_RECV && child->sk_state != state)
parent->sk_data_ready(parent, 0);
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index 9bc805d..de2a32e 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -88,7 +88,7 @@ static inline int tcp_probe_avail(void)
* Note: arguments must match tcp_rcv_established()!
*/
static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
- struct tcphdr *th, unsigned len)
+ struct tcphdr *th)
{
const struct tcp_sock *tp = tcp_sk(sk);
const struct inet_sock *inet = inet_sk(sk);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b76939a..3d08a4d 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1586,7 +1586,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
TCP_CHECK_TIMER(sk);
- if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len))
+ if (tcp_rcv_established(sk, skb, tcp_hdr(skb)))
goto reset;
TCP_CHECK_TIMER(sk);
if (opt_skb)
@@ -1618,7 +1618,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
}
TCP_CHECK_TIMER(sk);
- if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len))
+ if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb)))
goto reset;
TCP_CHECK_TIMER(sk);
if (opt_skb)
--
1.6.3.3
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox