* [PATCH 09/19] netfilter: rework user-space expectation helper support
From: pablo @ 2011-12-25 1:57 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1324778255-2830-1-git-send-email-pablo@netfilter.org>
From: Pablo Neira Ayuso <pablo@netfilter.org>
This partially reworks bc01befdcf3e40979eb518085a075cbf0aacede0
which added userspace expectation support.
This patch removes the nf_ct_userspace_expect_list since now we
force to use the new iptables CT target feature to add the helper
extension for conntracks that have attached expectations from
userspace.
A new version of the proof-of-concept code to implement userspace
helpers from userspace is available at:
http://people.netfilter.org/pablo/userspace-conntrack-helpers/nf-ftp-helper-POC.tar.bz2
This patch also modifies the CT target to allow to set the
conntrack's userspace helper status flags. This flag is used
to tell the conntrack system to explicitly allocate the helper
extension.
This helper extension is useful to link the userspace expectations
with the master conntrack that is being tracked from one userspace
helper.
This feature fixes a problem in the current approach of the
userspace helper support. Basically, if the master conntrack that
has got a userspace expectation vanishes, the expectations point to
one invalid memory address. Thus, triggering an oops in the
expectation deletion event path.
I decided not to add a new revision of the CT target because
I only needed to add a new flag for it. I'll document in this
issue in the iptables manpage. I have also changed the return
value from EINVAL to EOPNOTSUPP if one flag not supported is
specified. Thus, in the future adding new features that only
require a new flag can be added without a new revision.
There is no official code using this in userspace (apart from
the proof-of-concept) that uses this infrastructure but there
will be some by beginning 2012.
Reported-by: Sam Roberts <vieuxtech@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/linux/netfilter/nf_conntrack_common.h | 4 ++
include/linux/netfilter/xt_CT.h | 3 +-
include/net/netfilter/nf_conntrack_expect.h | 1 -
net/netfilter/nf_conntrack_expect.c | 63 ++++++++----------------
net/netfilter/nf_conntrack_helper.c | 12 +++++
net/netfilter/nf_conntrack_netlink.c | 5 ++-
net/netfilter/xt_CT.c | 8 ++-
7 files changed, 48 insertions(+), 48 deletions(-)
diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h
index 0d3dd66..9e3a283 100644
--- a/include/linux/netfilter/nf_conntrack_common.h
+++ b/include/linux/netfilter/nf_conntrack_common.h
@@ -83,6 +83,10 @@ enum ip_conntrack_status {
/* Conntrack is a fake untracked entry */
IPS_UNTRACKED_BIT = 12,
IPS_UNTRACKED = (1 << IPS_UNTRACKED_BIT),
+
+ /* Conntrack has a userspace helper. */
+ IPS_USERSPACE_HELPER_BIT = 13,
+ IPS_USERSPACE_HELPER = (1 << IPS_USERSPACE_HELPER_BIT),
};
/* Connection tracking event types */
diff --git a/include/linux/netfilter/xt_CT.h b/include/linux/netfilter/xt_CT.h
index b56e768..6390f09 100644
--- a/include/linux/netfilter/xt_CT.h
+++ b/include/linux/netfilter/xt_CT.h
@@ -3,7 +3,8 @@
#include <linux/types.h>
-#define XT_CT_NOTRACK 0x1
+#define XT_CT_NOTRACK 0x1
+#define XT_CT_USERSPACE_HELPER 0x2
struct xt_ct_target_info {
__u16 flags;
diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index 0f8a8c5..4619caa 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -91,7 +91,6 @@ static inline void nf_ct_unlink_expect(struct nf_conntrack_expect *exp)
void nf_ct_remove_expectations(struct nf_conn *ct);
void nf_ct_unexpect_related(struct nf_conntrack_expect *exp);
-void nf_ct_remove_userspace_expectations(void);
/* Allocate space for an expectation: this is mandatory before calling
nf_ct_expect_related. You will have to call put afterwards. */
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 340c80d..bebb167 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -38,8 +38,6 @@ unsigned int nf_ct_expect_max __read_mostly;
static struct kmem_cache *nf_ct_expect_cachep __read_mostly;
-static HLIST_HEAD(nf_ct_userspace_expect_list);
-
/* nf_conntrack_expect helper functions */
void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
u32 pid, int report)
@@ -47,14 +45,14 @@ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
struct nf_conn_help *master_help = nfct_help(exp->master);
struct net *net = nf_ct_exp_net(exp);
+ NF_CT_ASSERT(master_help);
NF_CT_ASSERT(!timer_pending(&exp->timeout));
hlist_del_rcu(&exp->hnode);
net->ct.expect_count--;
hlist_del(&exp->lnode);
- if (!(exp->flags & NF_CT_EXPECT_USERSPACE))
- master_help->expecting[exp->class]--;
+ master_help->expecting[exp->class]--;
nf_ct_expect_event_report(IPEXP_DESTROY, exp, pid, report);
nf_ct_expect_put(exp);
@@ -314,37 +312,34 @@ void nf_ct_expect_put(struct nf_conntrack_expect *exp)
}
EXPORT_SYMBOL_GPL(nf_ct_expect_put);
-static void nf_ct_expect_insert(struct nf_conntrack_expect *exp)
+static int nf_ct_expect_insert(struct nf_conntrack_expect *exp)
{
struct nf_conn_help *master_help = nfct_help(exp->master);
+ struct nf_conntrack_helper *helper;
struct net *net = nf_ct_exp_net(exp);
- const struct nf_conntrack_expect_policy *p;
unsigned int h = nf_ct_expect_dst_hash(&exp->tuple);
/* two references : one for hash insert, one for the timer */
atomic_add(2, &exp->use);
- if (master_help) {
- hlist_add_head(&exp->lnode, &master_help->expectations);
- master_help->expecting[exp->class]++;
- } else if (exp->flags & NF_CT_EXPECT_USERSPACE)
- hlist_add_head(&exp->lnode, &nf_ct_userspace_expect_list);
+ hlist_add_head(&exp->lnode, &master_help->expectations);
+ master_help->expecting[exp->class]++;
hlist_add_head_rcu(&exp->hnode, &net->ct.expect_hash[h]);
net->ct.expect_count++;
setup_timer(&exp->timeout, nf_ct_expectation_timed_out,
(unsigned long)exp);
- if (master_help) {
- p = &rcu_dereference_protected(
- master_help->helper,
- lockdep_is_held(&nf_conntrack_lock)
- )->expect_policy[exp->class];
- exp->timeout.expires = jiffies + p->timeout * HZ;
+ helper = rcu_dereference_protected(master_help->helper,
+ lockdep_is_held(&nf_conntrack_lock));
+ if (helper) {
+ exp->timeout.expires = jiffies +
+ helper->expect_policy[exp->class].timeout * HZ;
}
add_timer(&exp->timeout);
NF_CT_STAT_INC(net, expect_create);
+ return 0;
}
/* Race with expectations being used means we could have none to find; OK. */
@@ -389,14 +384,13 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
struct nf_conntrack_expect *i;
struct nf_conn *master = expect->master;
struct nf_conn_help *master_help = nfct_help(master);
+ struct nf_conntrack_helper *helper;
struct net *net = nf_ct_exp_net(expect);
struct hlist_node *n;
unsigned int h;
int ret = 1;
- /* Don't allow expectations created from kernel-space with no helper */
- if (!(expect->flags & NF_CT_EXPECT_USERSPACE) &&
- (!master_help || (master_help && !master_help->helper))) {
+ if (!master_help) {
ret = -ESHUTDOWN;
goto out;
}
@@ -414,11 +408,10 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
}
}
/* Will be over limit? */
- if (master_help) {
- p = &rcu_dereference_protected(
- master_help->helper,
- lockdep_is_held(&nf_conntrack_lock)
- )->expect_policy[expect->class];
+ helper = rcu_dereference_protected(master_help->helper,
+ lockdep_is_held(&nf_conntrack_lock));
+ if (helper) {
+ p = &helper->expect_policy[expect->class];
if (p->max_expected &&
master_help->expecting[expect->class] >= p->max_expected) {
evict_oldest_expect(master, expect);
@@ -450,8 +443,9 @@ int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
if (ret <= 0)
goto out;
- ret = 0;
- nf_ct_expect_insert(expect);
+ ret = nf_ct_expect_insert(expect);
+ if (ret < 0)
+ goto out;
spin_unlock_bh(&nf_conntrack_lock);
nf_ct_expect_event_report(IPEXP_NEW, expect, pid, report);
return ret;
@@ -461,21 +455,6 @@ out:
}
EXPORT_SYMBOL_GPL(nf_ct_expect_related_report);
-void nf_ct_remove_userspace_expectations(void)
-{
- struct nf_conntrack_expect *exp;
- struct hlist_node *n, *next;
-
- hlist_for_each_entry_safe(exp, n, next,
- &nf_ct_userspace_expect_list, lnode) {
- if (del_timer(&exp->timeout)) {
- nf_ct_unlink_expect(exp);
- nf_ct_expect_put(exp);
- }
- }
-}
-EXPORT_SYMBOL_GPL(nf_ct_remove_userspace_expectations);
-
#ifdef CONFIG_PROC_FS
struct ct_expect_iter_state {
struct seq_net_private p;
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 93c4bdb..c9e0de0 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -121,6 +121,18 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl,
int ret = 0;
if (tmpl != NULL) {
+ /* we've got a userspace helper. */
+ if (tmpl->status & IPS_USERSPACE_HELPER) {
+ help = nf_ct_helper_ext_add(ct, flags);
+ if (help == NULL) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ rcu_assign_pointer(help->helper, NULL);
+ __set_bit(IPS_USERSPACE_HELPER_BIT, &ct->status);
+ ret = 0;
+ goto out;
+ }
help = nfct_help(tmpl);
if (help != NULL)
helper = help->helper;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 636617c..7395480 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2040,6 +2040,10 @@ ctnetlink_create_expect(struct net *net, u16 zone,
}
help = nfct_help(ct);
if (!help) {
+ err = -EOPNOTSUPP;
+ goto out;
+ }
+ if (test_bit(IPS_USERSPACE_HELPER_BIT, &ct->status)) {
if (!cda[CTA_EXPECT_TIMEOUT]) {
err = -EINVAL;
goto out;
@@ -2264,7 +2268,6 @@ static void __exit ctnetlink_exit(void)
{
pr_info("ctnetlink: unregistering from nfnetlink.\n");
- nf_ct_remove_userspace_expectations();
unregister_pernet_subsys(&ctnetlink_net_ops);
nfnetlink_subsys_unregister(&ctnl_exp_subsys);
nfnetlink_subsys_unregister(&ctnl_subsys);
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 0221d10..8e87123 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -62,8 +62,8 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par)
int ret = 0;
u8 proto;
- if (info->flags & ~XT_CT_NOTRACK)
- return -EINVAL;
+ if (info->flags & ~(XT_CT_NOTRACK | XT_CT_USERSPACE_HELPER))
+ return -EOPNOTSUPP;
if (info->flags & XT_CT_NOTRACK) {
ct = nf_ct_untracked_get();
@@ -92,7 +92,9 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par)
GFP_KERNEL))
goto err3;
- if (info->helper[0]) {
+ if (info->flags & XT_CT_USERSPACE_HELPER) {
+ __set_bit(IPS_USERSPACE_HELPER_BIT, &ct->status);
+ } else if (info->helper[0]) {
ret = -ENOENT;
proto = xt_ct_find_proto(par);
if (!proto) {
--
1.7.2.5
^ permalink raw reply related
* [PATCH 05/19] IPVS: Modify the SH scheduler to use weights
From: pablo @ 2011-12-25 1:57 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1324778255-2830-1-git-send-email-pablo@netfilter.org>
From: Michael Maxim <mike@okcupid.com>
Modify the algorithm to build the source hashing hash table to add
extra slots for destinations with higher weight. This has the effect
of allowing an IPVS SH user to give more connections to hosts that
have been configured to have a higher weight.
The reason for the Kconfig change is because the size of the hash table
becomes more relevant/important if you decide to use the weights in the
manner this patch lets you. It would be conceivable that someone might
need to increase the size of that table to accommodate their
configuration, so it will be handy to be able to do that through the
regular configuration system instead of editing the source.
Signed-off-by: Michael Maxim <mike@okcupid.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/ipvs/Kconfig | 15 +++++++++++++++
net/netfilter/ipvs/ip_vs_sh.c | 18 +++++++++++++++++-
2 files changed, 32 insertions(+), 1 deletions(-)
diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index 70bd1d0..af4c0b8 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -232,6 +232,21 @@ config IP_VS_NQ
If you want to compile it in kernel, say Y. To compile it as a
module, choose M here. If unsure, say N.
+comment 'IPVS SH scheduler'
+
+config IP_VS_SH_TAB_BITS
+ int "IPVS source hashing table size (the Nth power of 2)"
+ range 4 20
+ default 8
+ ---help---
+ The source hashing scheduler maps source IPs to destinations
+ stored in a hash table. This table is tiled by each destination
+ until all slots in the table are filled. When using weights to
+ allow destinations to receive more connections, the table is
+ tiled an amount proportional to the weights specified. The table
+ needs to be large enough to effectively fit all the destinations
+ multiplied by their respective weights.
+
comment 'IPVS application helper'
config IP_VS_FTP
diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
index 33815f4..069e8d4 100644
--- a/net/netfilter/ipvs/ip_vs_sh.c
+++ b/net/netfilter/ipvs/ip_vs_sh.c
@@ -30,6 +30,11 @@
* server is dead or overloaded, the load balancer can bypass the cache
* server and send requests to the original server directly.
*
+ * The weight destination attribute can be used to control the
+ * distribution of connections to the destinations in servernode. The
+ * greater the weight, the more connections the destination
+ * will receive.
+ *
*/
#define KMSG_COMPONENT "IPVS"
@@ -99,9 +104,11 @@ ip_vs_sh_assign(struct ip_vs_sh_bucket *tbl, struct ip_vs_service *svc)
struct ip_vs_sh_bucket *b;
struct list_head *p;
struct ip_vs_dest *dest;
+ int d_count;
b = tbl;
p = &svc->destinations;
+ d_count = 0;
for (i=0; i<IP_VS_SH_TAB_SIZE; i++) {
if (list_empty(p)) {
b->dest = NULL;
@@ -113,7 +120,16 @@ ip_vs_sh_assign(struct ip_vs_sh_bucket *tbl, struct ip_vs_service *svc)
atomic_inc(&dest->refcnt);
b->dest = dest;
- p = p->next;
+ IP_VS_DBG_BUF(6, "assigned i: %d dest: %s weight: %d\n",
+ i, IP_VS_DBG_ADDR(svc->af, &dest->addr),
+ atomic_read(&dest->weight));
+
+ /* Don't move to next dest until filling weight */
+ if (++d_count >= atomic_read(&dest->weight)) {
+ p = p->next;
+ d_count = 0;
+ }
+
}
b++;
}
--
1.7.2.5
^ permalink raw reply related
* [PATCH 12/19] netfilter: nf_nat: add missing nla_policy entry for CTA_NAT_PROTO attribute
From: pablo @ 2011-12-25 1:57 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1324778255-2830-1-git-send-email-pablo@netfilter.org>
From: Patrick McHardy <kaber@trash.net>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/ipv4/netfilter/nf_nat_core.c | 1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index 76600f8..610eb44 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -622,6 +622,7 @@ static int nfnetlink_parse_nat_proto(struct nlattr *attr,
static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = {
[CTA_NAT_MINIP] = { .type = NLA_U32 },
[CTA_NAT_MAXIP] = { .type = NLA_U32 },
+ [CTA_NAT_PROTO] = { .type = NLA_NESTED },
};
static int
--
1.7.2.5
^ permalink raw reply related
* [PATCH 10/19] netfilter: nf_nat: export NAT definitions to userspace
From: pablo @ 2011-12-25 1:57 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1324778255-2830-1-git-send-email-pablo@netfilter.org>
From: Patrick McHardy <kaber@trash.net>
Export the NAT definitions to userspace. So far userspace (specifically,
iptables) has been copying the headers files from include/net. Also
rename some structures and definitions in preparation for IPv6 NAT.
Since these have never been officially exported, this doesn't affect
existing userspace code.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/linux/netfilter/Kbuild | 1 +
.../linux/netfilter/nf_conntrack_tuple_common.h | 27 +++++++++
include/linux/netfilter/nf_nat.h | 25 +++++++++
include/linux/netfilter_ipv4/Kbuild | 1 -
include/linux/netfilter_ipv4/nf_nat.h | 58 --------------------
include/net/netfilter/nf_conntrack_tuple.h | 1 -
include/net/netfilter/nf_nat.h | 10 ++--
include/net/netfilter/nf_nat_core.h | 2 +-
include/net/netfilter/nf_nat_protocol.h | 14 +++---
net/ipv4/netfilter/ipt_MASQUERADE.c | 16 +++---
net/ipv4/netfilter/ipt_NETMAP.c | 14 +++---
net/ipv4/netfilter/ipt_REDIRECT.c | 16 +++---
net/ipv4/netfilter/nf_nat_core.c | 54 +++++++++---------
net/ipv4/netfilter/nf_nat_h323.c | 20 ++++----
net/ipv4/netfilter/nf_nat_helper.c | 10 ++--
net/ipv4/netfilter/nf_nat_pptp.c | 14 +++---
net/ipv4/netfilter/nf_nat_proto_common.c | 24 ++++----
net/ipv4/netfilter/nf_nat_proto_dccp.c | 4 +-
net/ipv4/netfilter/nf_nat_proto_gre.c | 8 ++--
net/ipv4/netfilter/nf_nat_proto_icmp.c | 4 +-
net/ipv4/netfilter/nf_nat_proto_sctp.c | 4 +-
net/ipv4/netfilter/nf_nat_proto_tcp.c | 4 +-
net/ipv4/netfilter/nf_nat_proto_udp.c | 4 +-
net/ipv4/netfilter/nf_nat_proto_udplite.c | 4 +-
net/ipv4/netfilter/nf_nat_proto_unknown.c | 2 +-
net/ipv4/netfilter/nf_nat_rule.c | 22 ++++----
net/ipv4/netfilter/nf_nat_sip.c | 10 ++--
net/ipv4/netfilter/nf_nat_standalone.c | 2 +-
net/netfilter/nf_conntrack_netlink.c | 4 +-
29 files changed, 185 insertions(+), 194 deletions(-)
create mode 100644 include/linux/netfilter/nf_nat.h
delete mode 100644 include/linux/netfilter_ipv4/nf_nat.h
diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index a1b410c..d81f771 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -5,6 +5,7 @@ header-y += nf_conntrack_ftp.h
header-y += nf_conntrack_sctp.h
header-y += nf_conntrack_tcp.h
header-y += nf_conntrack_tuple_common.h
+header-y += nf_nat.h
header-y += nfnetlink.h
header-y += nfnetlink_compat.h
header-y += nfnetlink_conntrack.h
diff --git a/include/linux/netfilter/nf_conntrack_tuple_common.h b/include/linux/netfilter/nf_conntrack_tuple_common.h
index 2ea22b0..2f6bbc5 100644
--- a/include/linux/netfilter/nf_conntrack_tuple_common.h
+++ b/include/linux/netfilter/nf_conntrack_tuple_common.h
@@ -7,6 +7,33 @@ enum ip_conntrack_dir {
IP_CT_DIR_MAX
};
+/* The protocol-specific manipulable parts of the tuple: always in
+ * network order
+ */
+union nf_conntrack_man_proto {
+ /* Add other protocols here. */
+ __be16 all;
+
+ struct {
+ __be16 port;
+ } tcp;
+ struct {
+ __be16 port;
+ } udp;
+ struct {
+ __be16 id;
+ } icmp;
+ struct {
+ __be16 port;
+ } dccp;
+ struct {
+ __be16 port;
+ } sctp;
+ struct {
+ __be16 key; /* GRE key is 32bit, PPtP only uses 16bit */
+ } gre;
+};
+
#define CTINFO2DIR(ctinfo) ((ctinfo) >= IP_CT_IS_REPLY ? IP_CT_DIR_REPLY : IP_CT_DIR_ORIGINAL)
#endif /* _NF_CONNTRACK_TUPLE_COMMON_H */
diff --git a/include/linux/netfilter/nf_nat.h b/include/linux/netfilter/nf_nat.h
new file mode 100644
index 0000000..8df2d13
--- /dev/null
+++ b/include/linux/netfilter/nf_nat.h
@@ -0,0 +1,25 @@
+#ifndef _NETFILTER_NF_NAT_H
+#define _NETFILTER_NF_NAT_H
+
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_conntrack_tuple_common.h>
+
+#define NF_NAT_RANGE_MAP_IPS 1
+#define NF_NAT_RANGE_PROTO_SPECIFIED 2
+#define NF_NAT_RANGE_PROTO_RANDOM 4
+#define NF_NAT_RANGE_PERSISTENT 8
+
+struct nf_nat_ipv4_range {
+ unsigned int flags;
+ __be32 min_ip;
+ __be32 max_ip;
+ union nf_conntrack_man_proto min;
+ union nf_conntrack_man_proto max;
+};
+
+struct nf_nat_ipv4_multi_range_compat {
+ unsigned int rangesize;
+ struct nf_nat_ipv4_range range[1];
+};
+
+#endif /* _NETFILTER_NF_NAT_H */
diff --git a/include/linux/netfilter_ipv4/Kbuild b/include/linux/netfilter_ipv4/Kbuild
index c3b4548..f9930c8 100644
--- a/include/linux/netfilter_ipv4/Kbuild
+++ b/include/linux/netfilter_ipv4/Kbuild
@@ -12,4 +12,3 @@ header-y += ipt_ah.h
header-y += ipt_ecn.h
header-y += ipt_realm.h
header-y += ipt_ttl.h
-header-y += nf_nat.h
diff --git a/include/linux/netfilter_ipv4/nf_nat.h b/include/linux/netfilter_ipv4/nf_nat.h
deleted file mode 100644
index 7a861d0..0000000
--- a/include/linux/netfilter_ipv4/nf_nat.h
+++ /dev/null
@@ -1,58 +0,0 @@
-#ifndef _LINUX_NF_NAT_H
-#define _LINUX_NF_NAT_H
-
-#include <linux/types.h>
-
-#define IP_NAT_RANGE_MAP_IPS 1
-#define IP_NAT_RANGE_PROTO_SPECIFIED 2
-#define IP_NAT_RANGE_PROTO_RANDOM 4
-#define IP_NAT_RANGE_PERSISTENT 8
-
-/* The protocol-specific manipulable parts of the tuple. */
-union nf_conntrack_man_proto {
- /* Add other protocols here. */
- __be16 all;
-
- struct {
- __be16 port;
- } tcp;
- struct {
- __be16 port;
- } udp;
- struct {
- __be16 id;
- } icmp;
- struct {
- __be16 port;
- } dccp;
- struct {
- __be16 port;
- } sctp;
- struct {
- __be16 key; /* GRE key is 32bit, PPtP only uses 16bit */
- } gre;
-};
-
-/* Single range specification. */
-struct nf_nat_range {
- /* Set to OR of flags above. */
- unsigned int flags;
-
- /* Inclusive: network order. */
- __be32 min_ip, max_ip;
-
- /* Inclusive: network order */
- union nf_conntrack_man_proto min, max;
-};
-
-/* For backwards compat: don't use in modern code. */
-struct nf_nat_multi_range_compat {
- unsigned int rangesize; /* Must be 1. */
-
- /* hangs off end. */
- struct nf_nat_range range[1];
-};
-
-#define nf_nat_multi_range nf_nat_multi_range_compat
-
-#endif
diff --git a/include/net/netfilter/nf_conntrack_tuple.h b/include/net/netfilter/nf_conntrack_tuple.h
index 2f8fb77..aea3f82 100644
--- a/include/net/netfilter/nf_conntrack_tuple.h
+++ b/include/net/netfilter/nf_conntrack_tuple.h
@@ -12,7 +12,6 @@
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter/nf_conntrack_tuple_common.h>
-#include <linux/netfilter_ipv4/nf_nat.h>
#include <linux/list_nulls.h>
/* A `tuple' is a structure containing the information to uniquely
diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
index b8872df..b4de990 100644
--- a/include/net/netfilter/nf_nat.h
+++ b/include/net/netfilter/nf_nat.h
@@ -1,14 +1,12 @@
#ifndef _NF_NAT_H
#define _NF_NAT_H
#include <linux/netfilter_ipv4.h>
-#include <linux/netfilter_ipv4/nf_nat.h>
+#include <linux/netfilter/nf_nat.h>
#include <net/netfilter/nf_conntrack_tuple.h>
-#define NF_NAT_MAPPING_TYPE_MAX_NAMELEN 16
-
enum nf_nat_manip_type {
- IP_NAT_MANIP_SRC,
- IP_NAT_MANIP_DST
+ NF_NAT_MANIP_SRC,
+ NF_NAT_MANIP_DST
};
/* SRC manip occurs POST_ROUTING or LOCAL_IN */
@@ -52,7 +50,7 @@ struct nf_conn_nat {
/* Set up the info structure to map into this range. */
extern unsigned int nf_nat_setup_info(struct nf_conn *ct,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype);
/* Is this tuple already taken? (not by us)*/
diff --git a/include/net/netfilter/nf_nat_core.h b/include/net/netfilter/nf_nat_core.h
index 3dc7b98..b13d8d1 100644
--- a/include/net/netfilter/nf_nat_core.h
+++ b/include/net/netfilter/nf_nat_core.h
@@ -20,7 +20,7 @@ extern int nf_nat_icmp_reply_translation(struct nf_conn *ct,
static inline int nf_nat_initialized(struct nf_conn *ct,
enum nf_nat_manip_type manip)
{
- if (manip == IP_NAT_MANIP_SRC)
+ if (manip == NF_NAT_MANIP_SRC)
return ct->status & IPS_SRC_NAT_DONE;
else
return ct->status & IPS_DST_NAT_DONE;
diff --git a/include/net/netfilter/nf_nat_protocol.h b/include/net/netfilter/nf_nat_protocol.h
index 93cc90d..7156c00 100644
--- a/include/net/netfilter/nf_nat_protocol.h
+++ b/include/net/netfilter/nf_nat_protocol.h
@@ -4,7 +4,7 @@
#include <net/netfilter/nf_nat.h>
#include <linux/netfilter/nfnetlink_conntrack.h>
-struct nf_nat_range;
+struct nf_nat_ipv4_range;
struct nf_nat_protocol {
/* Protocol number. */
@@ -30,15 +30,15 @@ struct nf_nat_protocol {
possible. Per-protocol part of tuple is initialized to the
incoming packet. */
void (*unique_tuple)(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct);
int (*range_to_nlattr)(struct sk_buff *skb,
- const struct nf_nat_range *range);
+ const struct nf_nat_ipv4_range *range);
int (*nlattr_to_range)(struct nlattr *tb[],
- struct nf_nat_range *range);
+ struct nf_nat_ipv4_range *range);
};
/* Protocol registration. */
@@ -61,14 +61,14 @@ extern bool nf_nat_proto_in_range(const struct nf_conntrack_tuple *tuple,
const union nf_conntrack_man_proto *max);
extern void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct,
u_int16_t *rover);
extern int nf_nat_proto_range_to_nlattr(struct sk_buff *skb,
- const struct nf_nat_range *range);
+ const struct nf_nat_ipv4_range *range);
extern int nf_nat_proto_nlattr_to_range(struct nlattr *tb[],
- struct nf_nat_range *range);
+ struct nf_nat_ipv4_range *range);
#endif /*_NF_NAT_PROTO_H*/
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index 9931152..2f210c7 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -30,9 +30,9 @@ MODULE_DESCRIPTION("Xtables: automatic-address SNAT");
/* FIXME: Multiple targets. --RR */
static int masquerade_tg_check(const struct xt_tgchk_param *par)
{
- const struct nf_nat_multi_range_compat *mr = par->targinfo;
+ const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
- if (mr->range[0].flags & IP_NAT_RANGE_MAP_IPS) {
+ if (mr->range[0].flags & NF_NAT_RANGE_MAP_IPS) {
pr_debug("bad MAP_IPS.\n");
return -EINVAL;
}
@@ -49,8 +49,8 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
struct nf_conn *ct;
struct nf_conn_nat *nat;
enum ip_conntrack_info ctinfo;
- struct nf_nat_range newrange;
- const struct nf_nat_multi_range_compat *mr;
+ struct nf_nat_ipv4_range newrange;
+ const struct nf_nat_ipv4_multi_range_compat *mr;
const struct rtable *rt;
__be32 newsrc;
@@ -79,13 +79,13 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
nat->masq_index = par->out->ifindex;
/* Transfer from original range. */
- newrange = ((struct nf_nat_range)
- { mr->range[0].flags | IP_NAT_RANGE_MAP_IPS,
+ newrange = ((struct nf_nat_ipv4_range)
+ { mr->range[0].flags | NF_NAT_RANGE_MAP_IPS,
newsrc, newsrc,
mr->range[0].min, mr->range[0].max });
/* Hand modified range to generic setup. */
- return nf_nat_setup_info(ct, &newrange, IP_NAT_MANIP_SRC);
+ return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
}
static int
@@ -139,7 +139,7 @@ static struct xt_target masquerade_tg_reg __read_mostly = {
.name = "MASQUERADE",
.family = NFPROTO_IPV4,
.target = masquerade_tg,
- .targetsize = sizeof(struct nf_nat_multi_range_compat),
+ .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat),
.table = "nat",
.hooks = 1 << NF_INET_POST_ROUTING,
.checkentry = masquerade_tg_check,
diff --git a/net/ipv4/netfilter/ipt_NETMAP.c b/net/ipv4/netfilter/ipt_NETMAP.c
index 6cdb298..b5bfbba 100644
--- a/net/ipv4/netfilter/ipt_NETMAP.c
+++ b/net/ipv4/netfilter/ipt_NETMAP.c
@@ -24,9 +24,9 @@ MODULE_DESCRIPTION("Xtables: 1:1 NAT mapping of IPv4 subnets");
static int netmap_tg_check(const struct xt_tgchk_param *par)
{
- const struct nf_nat_multi_range_compat *mr = par->targinfo;
+ const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
- if (!(mr->range[0].flags & IP_NAT_RANGE_MAP_IPS)) {
+ if (!(mr->range[0].flags & NF_NAT_RANGE_MAP_IPS)) {
pr_debug("bad MAP_IPS.\n");
return -EINVAL;
}
@@ -43,8 +43,8 @@ netmap_tg(struct sk_buff *skb, const struct xt_action_param *par)
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
__be32 new_ip, netmask;
- const struct nf_nat_multi_range_compat *mr = par->targinfo;
- struct nf_nat_range newrange;
+ const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
+ struct nf_nat_ipv4_range newrange;
NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING ||
par->hooknum == NF_INET_POST_ROUTING ||
@@ -61,8 +61,8 @@ netmap_tg(struct sk_buff *skb, const struct xt_action_param *par)
new_ip = ip_hdr(skb)->saddr & ~netmask;
new_ip |= mr->range[0].min_ip & netmask;
- newrange = ((struct nf_nat_range)
- { mr->range[0].flags | IP_NAT_RANGE_MAP_IPS,
+ newrange = ((struct nf_nat_ipv4_range)
+ { mr->range[0].flags | NF_NAT_RANGE_MAP_IPS,
new_ip, new_ip,
mr->range[0].min, mr->range[0].max });
@@ -74,7 +74,7 @@ static struct xt_target netmap_tg_reg __read_mostly = {
.name = "NETMAP",
.family = NFPROTO_IPV4,
.target = netmap_tg,
- .targetsize = sizeof(struct nf_nat_multi_range_compat),
+ .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat),
.table = "nat",
.hooks = (1 << NF_INET_PRE_ROUTING) |
(1 << NF_INET_POST_ROUTING) |
diff --git a/net/ipv4/netfilter/ipt_REDIRECT.c b/net/ipv4/netfilter/ipt_REDIRECT.c
index 18a0656..7c0103a 100644
--- a/net/ipv4/netfilter/ipt_REDIRECT.c
+++ b/net/ipv4/netfilter/ipt_REDIRECT.c
@@ -28,9 +28,9 @@ MODULE_DESCRIPTION("Xtables: Connection redirection to localhost");
/* FIXME: Take multiple ranges --RR */
static int redirect_tg_check(const struct xt_tgchk_param *par)
{
- const struct nf_nat_multi_range_compat *mr = par->targinfo;
+ const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
- if (mr->range[0].flags & IP_NAT_RANGE_MAP_IPS) {
+ if (mr->range[0].flags & NF_NAT_RANGE_MAP_IPS) {
pr_debug("bad MAP_IPS.\n");
return -EINVAL;
}
@@ -47,8 +47,8 @@ redirect_tg(struct sk_buff *skb, const struct xt_action_param *par)
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
__be32 newdst;
- const struct nf_nat_multi_range_compat *mr = par->targinfo;
- struct nf_nat_range newrange;
+ const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
+ struct nf_nat_ipv4_range newrange;
NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING ||
par->hooknum == NF_INET_LOCAL_OUT);
@@ -76,20 +76,20 @@ redirect_tg(struct sk_buff *skb, const struct xt_action_param *par)
}
/* Transfer from original range. */
- newrange = ((struct nf_nat_range)
- { mr->range[0].flags | IP_NAT_RANGE_MAP_IPS,
+ newrange = ((struct nf_nat_ipv4_range)
+ { mr->range[0].flags | NF_NAT_RANGE_MAP_IPS,
newdst, newdst,
mr->range[0].min, mr->range[0].max });
/* Hand modified range to generic setup. */
- return nf_nat_setup_info(ct, &newrange, IP_NAT_MANIP_DST);
+ return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST);
}
static struct xt_target redirect_tg_reg __read_mostly = {
.name = "REDIRECT",
.family = NFPROTO_IPV4,
.target = redirect_tg,
- .targetsize = sizeof(struct nf_nat_multi_range_compat),
+ .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat),
.table = "nat",
.hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT),
.checkentry = redirect_tg_check,
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index 447bc5c..58ab7a4 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -82,14 +82,14 @@ EXPORT_SYMBOL(nf_nat_used_tuple);
* that meet the constraints of range. */
static int
in_range(const struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range)
+ const struct nf_nat_ipv4_range *range)
{
const struct nf_nat_protocol *proto;
int ret = 0;
/* If we are supposed to map IPs, then we must be in the
range specified, otherwise let this drag us onto a new src IP. */
- if (range->flags & IP_NAT_RANGE_MAP_IPS) {
+ if (range->flags & NF_NAT_RANGE_MAP_IPS) {
if (ntohl(tuple->src.u3.ip) < ntohl(range->min_ip) ||
ntohl(tuple->src.u3.ip) > ntohl(range->max_ip))
return 0;
@@ -97,8 +97,8 @@ in_range(const struct nf_conntrack_tuple *tuple,
rcu_read_lock();
proto = __nf_nat_proto_find(tuple->dst.protonum);
- if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) ||
- proto->in_range(tuple, IP_NAT_MANIP_SRC,
+ if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) ||
+ proto->in_range(tuple, NF_NAT_MANIP_SRC,
&range->min, &range->max))
ret = 1;
rcu_read_unlock();
@@ -123,7 +123,7 @@ static int
find_appropriate_src(struct net *net, u16 zone,
const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple *result,
- const struct nf_nat_range *range)
+ const struct nf_nat_ipv4_range *range)
{
unsigned int h = hash_by_src(net, zone, tuple);
const struct nf_conn_nat *nat;
@@ -157,7 +157,7 @@ find_appropriate_src(struct net *net, u16 zone,
*/
static void
find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
const struct nf_conn *ct,
enum nf_nat_manip_type maniptype)
{
@@ -166,10 +166,10 @@ find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple,
u_int32_t minip, maxip, j;
/* No IP mapping? Do nothing. */
- if (!(range->flags & IP_NAT_RANGE_MAP_IPS))
+ if (!(range->flags & NF_NAT_RANGE_MAP_IPS))
return;
- if (maniptype == IP_NAT_MANIP_SRC)
+ if (maniptype == NF_NAT_MANIP_SRC)
var_ipp = &tuple->src.u3.ip;
else
var_ipp = &tuple->dst.u3.ip;
@@ -189,7 +189,7 @@ find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple,
minip = ntohl(range->min_ip);
maxip = ntohl(range->max_ip);
j = jhash_2words((__force u32)tuple->src.u3.ip,
- range->flags & IP_NAT_RANGE_PERSISTENT ?
+ range->flags & NF_NAT_RANGE_PERSISTENT ?
0 : (__force u32)tuple->dst.u3.ip ^ zone, 0);
j = ((u64)j * (maxip - minip + 1)) >> 32;
*var_ipp = htonl(minip + j);
@@ -204,7 +204,7 @@ find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple,
static void
get_unique_tuple(struct nf_conntrack_tuple *tuple,
const struct nf_conntrack_tuple *orig_tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
struct nf_conn *ct,
enum nf_nat_manip_type maniptype)
{
@@ -219,8 +219,8 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
This is only required for source (ie. NAT/masq) mappings.
So far, we don't do local source mappings, so multiple
manips not an issue. */
- if (maniptype == IP_NAT_MANIP_SRC &&
- !(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) {
+ if (maniptype == NF_NAT_MANIP_SRC &&
+ !(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) {
/* try the original tuple first */
if (in_range(orig_tuple, range)) {
if (!nf_nat_used_tuple(orig_tuple, ct)) {
@@ -247,8 +247,8 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
proto = __nf_nat_proto_find(orig_tuple->dst.protonum);
/* Only bother mapping if it's not already in range and unique */
- if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) {
- if (range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) {
+ if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) {
+ if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) {
if (proto->in_range(tuple, maniptype, &range->min,
&range->max) &&
(range->min.all == range->max.all ||
@@ -267,7 +267,7 @@ out:
unsigned int
nf_nat_setup_info(struct nf_conn *ct,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype)
{
struct net *net = nf_ct_net(ct);
@@ -284,8 +284,8 @@ nf_nat_setup_info(struct nf_conn *ct,
}
}
- NF_CT_ASSERT(maniptype == IP_NAT_MANIP_SRC ||
- maniptype == IP_NAT_MANIP_DST);
+ NF_CT_ASSERT(maniptype == NF_NAT_MANIP_SRC ||
+ maniptype == NF_NAT_MANIP_DST);
BUG_ON(nf_nat_initialized(ct, maniptype));
/* What we've got will look like inverse of reply. Normally
@@ -306,13 +306,13 @@ nf_nat_setup_info(struct nf_conn *ct,
nf_conntrack_alter_reply(ct, &reply);
/* Non-atomic: we own this at the moment. */
- if (maniptype == IP_NAT_MANIP_SRC)
+ if (maniptype == NF_NAT_MANIP_SRC)
ct->status |= IPS_SRC_NAT;
else
ct->status |= IPS_DST_NAT;
}
- if (maniptype == IP_NAT_MANIP_SRC) {
+ if (maniptype == NF_NAT_MANIP_SRC) {
unsigned int srchash;
srchash = hash_by_src(net, nf_ct_zone(ct),
@@ -327,7 +327,7 @@ nf_nat_setup_info(struct nf_conn *ct,
}
/* It's done. */
- if (maniptype == IP_NAT_MANIP_DST)
+ if (maniptype == NF_NAT_MANIP_DST)
ct->status |= IPS_DST_NAT_DONE;
else
ct->status |= IPS_SRC_NAT_DONE;
@@ -361,7 +361,7 @@ manip_pkt(u_int16_t proto,
iph = (void *)skb->data + iphdroff;
- if (maniptype == IP_NAT_MANIP_SRC) {
+ if (maniptype == NF_NAT_MANIP_SRC) {
csum_replace4(&iph->check, iph->saddr, target->src.u3.ip);
iph->saddr = target->src.u3.ip;
} else {
@@ -381,7 +381,7 @@ unsigned int nf_nat_packet(struct nf_conn *ct,
unsigned long statusbit;
enum nf_nat_manip_type mtype = HOOK2MANIP(hooknum);
- if (mtype == IP_NAT_MANIP_SRC)
+ if (mtype == NF_NAT_MANIP_SRC)
statusbit = IPS_SRC_NAT;
else
statusbit = IPS_DST_NAT;
@@ -447,7 +447,7 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct,
return 0;
}
- if (manip == IP_NAT_MANIP_SRC)
+ if (manip == NF_NAT_MANIP_SRC)
statusbit = IPS_SRC_NAT;
else
statusbit = IPS_DST_NAT;
@@ -602,7 +602,7 @@ static const struct nla_policy protonat_nla_policy[CTA_PROTONAT_MAX+1] = {
static int nfnetlink_parse_nat_proto(struct nlattr *attr,
const struct nf_conn *ct,
- struct nf_nat_range *range)
+ struct nf_nat_ipv4_range *range)
{
struct nlattr *tb[CTA_PROTONAT_MAX+1];
const struct nf_nat_protocol *npt;
@@ -626,7 +626,7 @@ static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = {
static int
nfnetlink_parse_nat(const struct nlattr *nat,
- const struct nf_conn *ct, struct nf_nat_range *range)
+ const struct nf_conn *ct, struct nf_nat_ipv4_range *range)
{
struct nlattr *tb[CTA_NAT_MAX+1];
int err;
@@ -646,7 +646,7 @@ nfnetlink_parse_nat(const struct nlattr *nat,
range->max_ip = nla_get_be32(tb[CTA_NAT_MAXIP]);
if (range->min_ip)
- range->flags |= IP_NAT_RANGE_MAP_IPS;
+ range->flags |= NF_NAT_RANGE_MAP_IPS;
if (!tb[CTA_NAT_PROTO])
return 0;
@@ -663,7 +663,7 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct,
enum nf_nat_manip_type manip,
const struct nlattr *attr)
{
- struct nf_nat_range range;
+ struct nf_nat_ipv4_range range;
if (nfnetlink_parse_nat(attr, ct, &range) < 0)
return -EINVAL;
diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c
index b9a1136..dc1dd91 100644
--- a/net/ipv4/netfilter/nf_nat_h323.c
+++ b/net/ipv4/netfilter/nf_nat_h323.c
@@ -398,7 +398,7 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct,
static void ip_nat_q931_expect(struct nf_conn *new,
struct nf_conntrack_expect *this)
{
- struct nf_nat_range range;
+ struct nf_nat_ipv4_range range;
if (this->tuple.src.u3.ip != 0) { /* Only accept calls from GK */
nf_nat_follow_master(new, this);
@@ -409,16 +409,16 @@ static void ip_nat_q931_expect(struct nf_conn *new,
BUG_ON(new->status & IPS_NAT_DONE_MASK);
/* Change src to where master sends to */
- range.flags = IP_NAT_RANGE_MAP_IPS;
+ range.flags = NF_NAT_RANGE_MAP_IPS;
range.min_ip = range.max_ip = new->tuplehash[!this->dir].tuple.src.u3.ip;
- nf_nat_setup_info(new, &range, IP_NAT_MANIP_SRC);
+ nf_nat_setup_info(new, &range, NF_NAT_MANIP_SRC);
/* For DST manip, map port here to where it's expected. */
- range.flags = (IP_NAT_RANGE_MAP_IPS | IP_NAT_RANGE_PROTO_SPECIFIED);
+ range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED);
range.min = range.max = this->saved_proto;
range.min_ip = range.max_ip =
new->master->tuplehash[!this->dir].tuple.src.u3.ip;
- nf_nat_setup_info(new, &range, IP_NAT_MANIP_DST);
+ nf_nat_setup_info(new, &range, NF_NAT_MANIP_DST);
}
/****************************************************************************/
@@ -496,21 +496,21 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct,
static void ip_nat_callforwarding_expect(struct nf_conn *new,
struct nf_conntrack_expect *this)
{
- struct nf_nat_range range;
+ struct nf_nat_ipv4_range range;
/* This must be a fresh one. */
BUG_ON(new->status & IPS_NAT_DONE_MASK);
/* Change src to where master sends to */
- range.flags = IP_NAT_RANGE_MAP_IPS;
+ range.flags = NF_NAT_RANGE_MAP_IPS;
range.min_ip = range.max_ip = new->tuplehash[!this->dir].tuple.src.u3.ip;
- nf_nat_setup_info(new, &range, IP_NAT_MANIP_SRC);
+ nf_nat_setup_info(new, &range, NF_NAT_MANIP_SRC);
/* For DST manip, map port here to where it's expected. */
- range.flags = (IP_NAT_RANGE_MAP_IPS | IP_NAT_RANGE_PROTO_SPECIFIED);
+ range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED);
range.min = range.max = this->saved_proto;
range.min_ip = range.max_ip = this->saved_ip;
- nf_nat_setup_info(new, &range, IP_NAT_MANIP_DST);
+ nf_nat_setup_info(new, &range, NF_NAT_MANIP_DST);
}
/****************************************************************************/
diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c
index ebc5f88..049e8b7 100644
--- a/net/ipv4/netfilter/nf_nat_helper.c
+++ b/net/ipv4/netfilter/nf_nat_helper.c
@@ -430,22 +430,22 @@ nf_nat_seq_adjust(struct sk_buff *skb,
void nf_nat_follow_master(struct nf_conn *ct,
struct nf_conntrack_expect *exp)
{
- struct nf_nat_range range;
+ struct nf_nat_ipv4_range range;
/* This must be a fresh one. */
BUG_ON(ct->status & IPS_NAT_DONE_MASK);
/* Change src to where master sends to */
- range.flags = IP_NAT_RANGE_MAP_IPS;
+ range.flags = NF_NAT_RANGE_MAP_IPS;
range.min_ip = range.max_ip
= ct->master->tuplehash[!exp->dir].tuple.dst.u3.ip;
- nf_nat_setup_info(ct, &range, IP_NAT_MANIP_SRC);
+ nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC);
/* For DST manip, map port here to where it's expected. */
- range.flags = (IP_NAT_RANGE_MAP_IPS | IP_NAT_RANGE_PROTO_SPECIFIED);
+ range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED);
range.min = range.max = exp->saved_proto;
range.min_ip = range.max_ip
= ct->master->tuplehash[!exp->dir].tuple.src.u3.ip;
- nf_nat_setup_info(ct, &range, IP_NAT_MANIP_DST);
+ nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST);
}
EXPORT_SYMBOL(nf_nat_follow_master);
diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c
index 3e8284b..c273d58 100644
--- a/net/ipv4/netfilter/nf_nat_pptp.c
+++ b/net/ipv4/netfilter/nf_nat_pptp.c
@@ -47,7 +47,7 @@ static void pptp_nat_expected(struct nf_conn *ct,
struct nf_conntrack_tuple t;
const struct nf_ct_pptp_master *ct_pptp_info;
const struct nf_nat_pptp *nat_pptp_info;
- struct nf_nat_range range;
+ struct nf_nat_ipv4_range range;
ct_pptp_info = &nfct_help(master)->help.ct_pptp_info;
nat_pptp_info = &nfct_nat(master)->help.nat_pptp_info;
@@ -88,24 +88,24 @@ static void pptp_nat_expected(struct nf_conn *ct,
BUG_ON(ct->status & IPS_NAT_DONE_MASK);
/* Change src to where master sends to */
- range.flags = IP_NAT_RANGE_MAP_IPS;
+ range.flags = NF_NAT_RANGE_MAP_IPS;
range.min_ip = range.max_ip
= ct->master->tuplehash[!exp->dir].tuple.dst.u3.ip;
if (exp->dir == IP_CT_DIR_ORIGINAL) {
- range.flags |= IP_NAT_RANGE_PROTO_SPECIFIED;
+ range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
range.min = range.max = exp->saved_proto;
}
- nf_nat_setup_info(ct, &range, IP_NAT_MANIP_SRC);
+ nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC);
/* For DST manip, map port here to where it's expected. */
- range.flags = IP_NAT_RANGE_MAP_IPS;
+ range.flags = NF_NAT_RANGE_MAP_IPS;
range.min_ip = range.max_ip
= ct->master->tuplehash[!exp->dir].tuple.src.u3.ip;
if (exp->dir == IP_CT_DIR_REPLY) {
- range.flags |= IP_NAT_RANGE_PROTO_SPECIFIED;
+ range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
range.min = range.max = exp->saved_proto;
}
- nf_nat_setup_info(ct, &range, IP_NAT_MANIP_DST);
+ nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST);
}
/* outbound packets == from PNS to PAC */
diff --git a/net/ipv4/netfilter/nf_nat_proto_common.c b/net/ipv4/netfilter/nf_nat_proto_common.c
index a3d9976..47fff91 100644
--- a/net/ipv4/netfilter/nf_nat_proto_common.c
+++ b/net/ipv4/netfilter/nf_nat_proto_common.c
@@ -26,7 +26,7 @@ bool nf_nat_proto_in_range(const struct nf_conntrack_tuple *tuple,
{
__be16 port;
- if (maniptype == IP_NAT_MANIP_SRC)
+ if (maniptype == NF_NAT_MANIP_SRC)
port = tuple->src.u.all;
else
port = tuple->dst.u.all;
@@ -37,7 +37,7 @@ bool nf_nat_proto_in_range(const struct nf_conntrack_tuple *tuple,
EXPORT_SYMBOL_GPL(nf_nat_proto_in_range);
void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct,
u_int16_t *rover)
@@ -46,15 +46,15 @@ void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
__be16 *portptr;
u_int16_t off;
- if (maniptype == IP_NAT_MANIP_SRC)
+ if (maniptype == NF_NAT_MANIP_SRC)
portptr = &tuple->src.u.all;
else
portptr = &tuple->dst.u.all;
/* If no range specified... */
- if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED)) {
+ if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) {
/* If it's dst rewrite, can't change port */
- if (maniptype == IP_NAT_MANIP_DST)
+ if (maniptype == NF_NAT_MANIP_DST)
return;
if (ntohs(*portptr) < 1024) {
@@ -75,9 +75,9 @@ void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
range_size = ntohs(range->max.all) - min + 1;
}
- if (range->flags & IP_NAT_RANGE_PROTO_RANDOM)
+ if (range->flags & NF_NAT_RANGE_PROTO_RANDOM)
off = secure_ipv4_port_ephemeral(tuple->src.u3.ip, tuple->dst.u3.ip,
- maniptype == IP_NAT_MANIP_SRC
+ maniptype == NF_NAT_MANIP_SRC
? tuple->dst.u.all
: tuple->src.u.all);
else
@@ -87,7 +87,7 @@ void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
*portptr = htons(min + off % range_size);
if (++i != range_size && nf_nat_used_tuple(tuple, ct))
continue;
- if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM))
+ if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM))
*rover = off;
return;
}
@@ -97,7 +97,7 @@ EXPORT_SYMBOL_GPL(nf_nat_proto_unique_tuple);
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
int nf_nat_proto_range_to_nlattr(struct sk_buff *skb,
- const struct nf_nat_range *range)
+ const struct nf_nat_ipv4_range *range)
{
NLA_PUT_BE16(skb, CTA_PROTONAT_PORT_MIN, range->min.all);
NLA_PUT_BE16(skb, CTA_PROTONAT_PORT_MAX, range->max.all);
@@ -109,16 +109,16 @@ nla_put_failure:
EXPORT_SYMBOL_GPL(nf_nat_proto_nlattr_to_range);
int nf_nat_proto_nlattr_to_range(struct nlattr *tb[],
- struct nf_nat_range *range)
+ struct nf_nat_ipv4_range *range)
{
if (tb[CTA_PROTONAT_PORT_MIN]) {
range->min.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MIN]);
range->max.all = range->min.tcp.port;
- range->flags |= IP_NAT_RANGE_PROTO_SPECIFIED;
+ range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
}
if (tb[CTA_PROTONAT_PORT_MAX]) {
range->max.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MAX]);
- range->flags |= IP_NAT_RANGE_PROTO_SPECIFIED;
+ range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
}
return 0;
}
diff --git a/net/ipv4/netfilter/nf_nat_proto_dccp.c b/net/ipv4/netfilter/nf_nat_proto_dccp.c
index 570faf2..c43d5b3 100644
--- a/net/ipv4/netfilter/nf_nat_proto_dccp.c
+++ b/net/ipv4/netfilter/nf_nat_proto_dccp.c
@@ -24,7 +24,7 @@ static u_int16_t dccp_port_rover;
static void
dccp_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
@@ -54,7 +54,7 @@ dccp_manip_pkt(struct sk_buff *skb,
iph = (struct iphdr *)(skb->data + iphdroff);
hdr = (struct dccp_hdr *)(skb->data + hdroff);
- if (maniptype == IP_NAT_MANIP_SRC) {
+ if (maniptype == NF_NAT_MANIP_SRC) {
oldip = iph->saddr;
newip = tuple->src.u3.ip;
newport = tuple->src.u.dccp.port;
diff --git a/net/ipv4/netfilter/nf_nat_proto_gre.c b/net/ipv4/netfilter/nf_nat_proto_gre.c
index bc8d83a..9b1c629 100644
--- a/net/ipv4/netfilter/nf_nat_proto_gre.c
+++ b/net/ipv4/netfilter/nf_nat_proto_gre.c
@@ -39,7 +39,7 @@ MODULE_DESCRIPTION("Netfilter NAT protocol helper module for GRE");
/* generate unique tuple ... */
static void
gre_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
@@ -52,12 +52,12 @@ gre_unique_tuple(struct nf_conntrack_tuple *tuple,
if (!ct->master)
return;
- if (maniptype == IP_NAT_MANIP_SRC)
+ if (maniptype == NF_NAT_MANIP_SRC)
keyptr = &tuple->src.u.gre.key;
else
keyptr = &tuple->dst.u.gre.key;
- if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED)) {
+ if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) {
pr_debug("%p: NATing GRE PPTP\n", ct);
min = 1;
range_size = 0xffff;
@@ -99,7 +99,7 @@ gre_manip_pkt(struct sk_buff *skb, unsigned int iphdroff,
/* we only have destination manip of a packet, since 'source key'
* is not present in the packet itself */
- if (maniptype != IP_NAT_MANIP_DST)
+ if (maniptype != NF_NAT_MANIP_DST)
return true;
switch (greh->version) {
case GRE_VERSION_1701:
diff --git a/net/ipv4/netfilter/nf_nat_proto_icmp.c b/net/ipv4/netfilter/nf_nat_proto_icmp.c
index 9f4dc12..8f87b4b 100644
--- a/net/ipv4/netfilter/nf_nat_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_nat_proto_icmp.c
@@ -30,7 +30,7 @@ icmp_in_range(const struct nf_conntrack_tuple *tuple,
static void
icmp_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
@@ -40,7 +40,7 @@ icmp_unique_tuple(struct nf_conntrack_tuple *tuple,
range_size = ntohs(range->max.icmp.id) - ntohs(range->min.icmp.id) + 1;
/* If no range specified... */
- if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED))
+ if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED))
range_size = 0xFFFF;
for (i = 0; ; ++id) {
diff --git a/net/ipv4/netfilter/nf_nat_proto_sctp.c b/net/ipv4/netfilter/nf_nat_proto_sctp.c
index bd5a80a..4e70dc6 100644
--- a/net/ipv4/netfilter/nf_nat_proto_sctp.c
+++ b/net/ipv4/netfilter/nf_nat_proto_sctp.c
@@ -19,7 +19,7 @@ static u_int16_t nf_sctp_port_rover;
static void
sctp_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
@@ -46,7 +46,7 @@ sctp_manip_pkt(struct sk_buff *skb,
iph = (struct iphdr *)(skb->data + iphdroff);
hdr = (struct sctphdr *)(skb->data + hdroff);
- if (maniptype == IP_NAT_MANIP_SRC) {
+ if (maniptype == NF_NAT_MANIP_SRC) {
/* Get rid of src ip and src pt */
oldip = iph->saddr;
newip = tuple->src.u3.ip;
diff --git a/net/ipv4/netfilter/nf_nat_proto_tcp.c b/net/ipv4/netfilter/nf_nat_proto_tcp.c
index 0d67bb8..6fcc865 100644
--- a/net/ipv4/netfilter/nf_nat_proto_tcp.c
+++ b/net/ipv4/netfilter/nf_nat_proto_tcp.c
@@ -23,7 +23,7 @@ static u_int16_t tcp_port_rover;
static void
tcp_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
@@ -55,7 +55,7 @@ tcp_manip_pkt(struct sk_buff *skb,
iph = (struct iphdr *)(skb->data + iphdroff);
hdr = (struct tcphdr *)(skb->data + hdroff);
- if (maniptype == IP_NAT_MANIP_SRC) {
+ if (maniptype == NF_NAT_MANIP_SRC) {
/* Get rid of src ip and src pt */
oldip = iph->saddr;
newip = tuple->src.u3.ip;
diff --git a/net/ipv4/netfilter/nf_nat_proto_udp.c b/net/ipv4/netfilter/nf_nat_proto_udp.c
index 0b1b860..18ea44e 100644
--- a/net/ipv4/netfilter/nf_nat_proto_udp.c
+++ b/net/ipv4/netfilter/nf_nat_proto_udp.c
@@ -22,7 +22,7 @@ static u_int16_t udp_port_rover;
static void
udp_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
@@ -47,7 +47,7 @@ udp_manip_pkt(struct sk_buff *skb,
iph = (struct iphdr *)(skb->data + iphdroff);
hdr = (struct udphdr *)(skb->data + hdroff);
- if (maniptype == IP_NAT_MANIP_SRC) {
+ if (maniptype == NF_NAT_MANIP_SRC) {
/* Get rid of src ip and src pt */
oldip = iph->saddr;
newip = tuple->src.u3.ip;
diff --git a/net/ipv4/netfilter/nf_nat_proto_udplite.c b/net/ipv4/netfilter/nf_nat_proto_udplite.c
index f83ef23..a17b75b 100644
--- a/net/ipv4/netfilter/nf_nat_proto_udplite.c
+++ b/net/ipv4/netfilter/nf_nat_proto_udplite.c
@@ -21,7 +21,7 @@ static u_int16_t udplite_port_rover;
static void
udplite_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
@@ -47,7 +47,7 @@ udplite_manip_pkt(struct sk_buff *skb,
iph = (struct iphdr *)(skb->data + iphdroff);
hdr = (struct udphdr *)(skb->data + hdroff);
- if (maniptype == IP_NAT_MANIP_SRC) {
+ if (maniptype == NF_NAT_MANIP_SRC) {
/* Get rid of src ip and src pt */
oldip = iph->saddr;
newip = tuple->src.u3.ip;
diff --git a/net/ipv4/netfilter/nf_nat_proto_unknown.c b/net/ipv4/netfilter/nf_nat_proto_unknown.c
index a50f2bc..ab8e8c1 100644
--- a/net/ipv4/netfilter/nf_nat_proto_unknown.c
+++ b/net/ipv4/netfilter/nf_nat_proto_unknown.c
@@ -27,7 +27,7 @@ static bool unknown_in_range(const struct nf_conntrack_tuple *tuple,
}
static void unknown_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c
index 733c9ab..d2a9dc3 100644
--- a/net/ipv4/netfilter/nf_nat_rule.c
+++ b/net/ipv4/netfilter/nf_nat_rule.c
@@ -44,7 +44,7 @@ ipt_snat_target(struct sk_buff *skb, const struct xt_action_param *par)
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
- const struct nf_nat_multi_range_compat *mr = par->targinfo;
+ const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
NF_CT_ASSERT(par->hooknum == NF_INET_POST_ROUTING ||
par->hooknum == NF_INET_LOCAL_IN);
@@ -56,7 +56,7 @@ ipt_snat_target(struct sk_buff *skb, const struct xt_action_param *par)
ctinfo == IP_CT_RELATED_REPLY));
NF_CT_ASSERT(par->out != NULL);
- return nf_nat_setup_info(ct, &mr->range[0], IP_NAT_MANIP_SRC);
+ return nf_nat_setup_info(ct, &mr->range[0], NF_NAT_MANIP_SRC);
}
static unsigned int
@@ -64,7 +64,7 @@ ipt_dnat_target(struct sk_buff *skb, const struct xt_action_param *par)
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
- const struct nf_nat_multi_range_compat *mr = par->targinfo;
+ const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING ||
par->hooknum == NF_INET_LOCAL_OUT);
@@ -74,12 +74,12 @@ ipt_dnat_target(struct sk_buff *skb, const struct xt_action_param *par)
/* Connection must be valid and new. */
NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED));
- return nf_nat_setup_info(ct, &mr->range[0], IP_NAT_MANIP_DST);
+ return nf_nat_setup_info(ct, &mr->range[0], NF_NAT_MANIP_DST);
}
static int ipt_snat_checkentry(const struct xt_tgchk_param *par)
{
- const struct nf_nat_multi_range_compat *mr = par->targinfo;
+ const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
/* Must be a valid range */
if (mr->rangesize != 1) {
@@ -91,7 +91,7 @@ static int ipt_snat_checkentry(const struct xt_tgchk_param *par)
static int ipt_dnat_checkentry(const struct xt_tgchk_param *par)
{
- const struct nf_nat_multi_range_compat *mr = par->targinfo;
+ const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
/* Must be a valid range */
if (mr->rangesize != 1) {
@@ -105,13 +105,13 @@ static unsigned int
alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
{
/* Force range to this IP; let proto decide mapping for
- per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED).
+ per-proto parts (hence not NF_NAT_RANGE_PROTO_SPECIFIED).
*/
- struct nf_nat_range range;
+ struct nf_nat_ipv4_range range;
range.flags = 0;
pr_debug("Allocating NULL binding for %p (%pI4)\n", ct,
- HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC ?
+ HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ?
&ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip :
&ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip);
@@ -140,7 +140,7 @@ int nf_nat_rule_find(struct sk_buff *skb,
static struct xt_target ipt_snat_reg __read_mostly = {
.name = "SNAT",
.target = ipt_snat_target,
- .targetsize = sizeof(struct nf_nat_multi_range_compat),
+ .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat),
.table = "nat",
.hooks = (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_IN),
.checkentry = ipt_snat_checkentry,
@@ -150,7 +150,7 @@ static struct xt_target ipt_snat_reg __read_mostly = {
static struct xt_target ipt_dnat_reg __read_mostly = {
.name = "DNAT",
.target = ipt_dnat_target,
- .targetsize = sizeof(struct nf_nat_multi_range_compat),
+ .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat),
.table = "nat",
.hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT),
.checkentry = ipt_dnat_checkentry,
diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c
index 78844d9..d0319f9 100644
--- a/net/ipv4/netfilter/nf_nat_sip.c
+++ b/net/ipv4/netfilter/nf_nat_sip.c
@@ -249,25 +249,25 @@ static void ip_nat_sip_seq_adjust(struct sk_buff *skb, s16 off)
static void ip_nat_sip_expected(struct nf_conn *ct,
struct nf_conntrack_expect *exp)
{
- struct nf_nat_range range;
+ struct nf_nat_ipv4_range range;
/* This must be a fresh one. */
BUG_ON(ct->status & IPS_NAT_DONE_MASK);
/* For DST manip, map port here to where it's expected. */
- range.flags = (IP_NAT_RANGE_MAP_IPS | IP_NAT_RANGE_PROTO_SPECIFIED);
+ range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED);
range.min = range.max = exp->saved_proto;
range.min_ip = range.max_ip = exp->saved_ip;
- nf_nat_setup_info(ct, &range, IP_NAT_MANIP_DST);
+ nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST);
/* Change src to where master sends to, but only if the connection
* actually came from the same source. */
if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip ==
ct->master->tuplehash[exp->dir].tuple.src.u3.ip) {
- range.flags = IP_NAT_RANGE_MAP_IPS;
+ range.flags = NF_NAT_RANGE_MAP_IPS;
range.min_ip = range.max_ip
= ct->master->tuplehash[!exp->dir].tuple.dst.u3.ip;
- nf_nat_setup_info(ct, &range, IP_NAT_MANIP_SRC);
+ nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC);
}
}
diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c
index 9290048..3828a42 100644
--- a/net/ipv4/netfilter/nf_nat_standalone.c
+++ b/net/ipv4/netfilter/nf_nat_standalone.c
@@ -137,7 +137,7 @@ nf_nat_fn(unsigned int hooknum,
return ret;
} else
pr_debug("Already setup manip %s for ct %p\n",
- maniptype == IP_NAT_MANIP_SRC ? "SRC" : "DST",
+ maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
ct);
break;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 7395480..4f9c941 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1102,14 +1102,14 @@ ctnetlink_change_nat(struct nf_conn *ct, const struct nlattr * const cda[])
if (cda[CTA_NAT_DST]) {
ret = ctnetlink_parse_nat_setup(ct,
- IP_NAT_MANIP_DST,
+ NF_NAT_MANIP_DST,
cda[CTA_NAT_DST]);
if (ret < 0)
return ret;
}
if (cda[CTA_NAT_SRC]) {
ret = ctnetlink_parse_nat_setup(ct,
- IP_NAT_MANIP_SRC,
+ NF_NAT_MANIP_SRC,
cda[CTA_NAT_SRC]);
if (ret < 0)
return ret;
--
1.7.2.5
^ permalink raw reply related
* [PATCH 19/19] netfilter: xtables: add nfacct match to support extended accounting
From: pablo @ 2011-12-25 1:57 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1324778255-2830-1-git-send-email-pablo@netfilter.org>
From: Pablo Neira Ayuso <pablo@netfilter.org>
This patch adds the match that allows to perform extended
accounting. It requires the new nfnetlink_acct infrastructure.
# iptables -I INPUT -p tcp --sport 80 -m nfacct --nfacct-name http-traffic
# iptables -I OUTPUT -p tcp --dport 80 -m nfacct --nfacct-name http-traffic
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/linux/netfilter/Kbuild | 1 +
include/linux/netfilter/xt_nfacct.h | 13 ++++++
net/netfilter/Kconfig | 10 +++++
net/netfilter/Makefile | 1 +
net/netfilter/xt_nfacct.c | 76 +++++++++++++++++++++++++++++++++++
5 files changed, 101 insertions(+), 0 deletions(-)
create mode 100644 include/linux/netfilter/xt_nfacct.h
create mode 100644 net/netfilter/xt_nfacct.c
diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index 6785246..e630a2e 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -23,6 +23,7 @@ header-y += xt_DSCP.h
header-y += xt_IDLETIMER.h
header-y += xt_LED.h
header-y += xt_MARK.h
+header-y += xt_nfacct.h
header-y += xt_NFLOG.h
header-y += xt_NFQUEUE.h
header-y += xt_RATEEST.h
diff --git a/include/linux/netfilter/xt_nfacct.h b/include/linux/netfilter/xt_nfacct.h
new file mode 100644
index 0000000..3e19c8a
--- /dev/null
+++ b/include/linux/netfilter/xt_nfacct.h
@@ -0,0 +1,13 @@
+#ifndef _XT_NFACCT_MATCH_H
+#define _XT_NFACCT_MATCH_H
+
+#include <linux/netfilter/nfnetlink_acct.h>
+
+struct nf_acct;
+
+struct xt_nfacct_match_info {
+ char name[NFACCT_NAME_MAX];
+ struct nf_acct *nfacct;
+};
+
+#endif /* _XT_NFACCT_MATCH_H */
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 77326ac..bac93ba 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -887,6 +887,16 @@ config NETFILTER_XT_MATCH_MULTIPORT
To compile it as a module, choose M here. If unsure, say N.
+config NETFILTER_XT_MATCH_NFACCT
+ tristate '"nfacct" match support'
+ default m if NETFILTER_ADVANCED=n
+ select NETFILTER_NETLINK_ACCT
+ help
+ This option allows you to use the extended accounting through
+ nfnetlink_acct.
+
+ To compile it as a module, choose M here. If unsure, say N.
+
config NETFILTER_XT_MATCH_OSF
tristate '"osf" Passive OS fingerprint match'
depends on NETFILTER_ADVANCED && NETFILTER_NETLINK
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 4da1c87..b2eee4d 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -91,6 +91,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_LENGTH) += xt_length.o
obj-$(CONFIG_NETFILTER_XT_MATCH_LIMIT) += xt_limit.o
obj-$(CONFIG_NETFILTER_XT_MATCH_MAC) += xt_mac.o
obj-$(CONFIG_NETFILTER_XT_MATCH_MULTIPORT) += xt_multiport.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_NFACCT) += xt_nfacct.o
obj-$(CONFIG_NETFILTER_XT_MATCH_OSF) += xt_osf.o
obj-$(CONFIG_NETFILTER_XT_MATCH_OWNER) += xt_owner.o
obj-$(CONFIG_NETFILTER_XT_MATCH_PHYSDEV) += xt_physdev.o
diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c
new file mode 100644
index 0000000..b3be0ef
--- /dev/null
+++ b/net/netfilter/xt_nfacct.c
@@ -0,0 +1,76 @@
+/*
+ * (C) 2011 Pablo Neira Ayuso <pablo@netfilter.org>
+ * (C) 2011 Intra2net AG <http://www.intra2net.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 (or any
+ * later at your option) as published by the Free Software Foundation.
+ */
+#include <linux/module.h>
+#include <linux/skbuff.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/nfnetlink_acct.h>
+#include <linux/netfilter/xt_nfacct.h>
+
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_DESCRIPTION("Xtables: match for the extended accounting infrastructure");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("ipt_nfacct");
+MODULE_ALIAS("ip6t_nfacct");
+
+static bool nfacct_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_nfacct_match_info *info = par->targinfo;
+
+ nfnl_acct_update(skb, info->nfacct);
+
+ return true;
+}
+
+static int
+nfacct_mt_checkentry(const struct xt_mtchk_param *par)
+{
+ struct xt_nfacct_match_info *info = par->matchinfo;
+ struct nf_acct *nfacct;
+
+ nfacct = nfnl_acct_find_get(info->name);
+ if (nfacct == NULL) {
+ pr_info("xt_nfacct: accounting object with name `%s' "
+ "does not exists\n", info->name);
+ return -ENOENT;
+ }
+ info->nfacct = nfacct;
+ return 0;
+}
+
+static void
+nfacct_mt_destroy(const struct xt_mtdtor_param *par)
+{
+ const struct xt_nfacct_match_info *info = par->matchinfo;
+
+ nfnl_acct_put(info->nfacct);
+}
+
+static struct xt_match nfacct_mt_reg __read_mostly = {
+ .name = "nfacct",
+ .family = NFPROTO_UNSPEC,
+ .checkentry = nfacct_mt_checkentry,
+ .match = nfacct_mt,
+ .destroy = nfacct_mt_destroy,
+ .matchsize = sizeof(struct xt_nfacct_match_info),
+ .me = THIS_MODULE,
+};
+
+static int __init nfacct_mt_init(void)
+{
+ return xt_register_match(&nfacct_mt_reg);
+}
+
+static void __exit nfacct_mt_exit(void)
+{
+ xt_unregister_match(&nfacct_mt_reg);
+}
+
+module_init(nfacct_mt_init);
+module_exit(nfacct_mt_exit);
--
1.7.2.5
^ permalink raw reply related
* [PATCH 18/19] netfilter: add extended accounting infrastructure over nfnetlink
From: pablo @ 2011-12-25 1:57 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1324778255-2830-1-git-send-email-pablo@netfilter.org>
From: Pablo Neira Ayuso <pablo@netfilter.org>
We currently have two ways to account traffic in netfilter:
- iptables chain and rule counters:
# iptables -L -n -v
Chain INPUT (policy DROP 3 packets, 867 bytes)
pkts bytes target prot opt in out source destination
8 1104 ACCEPT all -- lo * 0.0.0.0/0 0.0.0.0/0
- use flow-based accounting provided by ctnetlink:
# conntrack -L
tcp 6 431999 ESTABLISHED src=192.168.1.130 dst=212.106.219.168 sport=58152 dport=80 packets=47 bytes=7654 src=212.106.219.168 dst=192.168.1.130 sport=80 dport=58152 packets=49 bytes=66340 [ASSURED] mark=0 use=1
While trying to display real-time accounting statistics, we require
to pool the kernel periodically to obtain this information. This is
OK if the number of flows is relatively low. However, in case that
the number of flows is huge, we can spend a considerable amount of
cycles to iterate over the list of flows that have been obtained.
Moreover, if we want to obtain the sum of the flow accounting results
that match some criteria, we have to iterate over the whole list of
existing flows, look for matchings and update the counters.
This patch adds the extended accounting infrastructure for
nfnetlink which aims to allow displaying real-time traffic accounting
without the need of complicated and resource-consuming implementation
in user-space. Basically, this new infrastructure allows you to create
accounting objects. One accounting object is composed of packet and
byte counters.
In order to manipulate create accounting objects, you require the
new libnetfilter_acct library. It contains several examples of use:
libnetfilter_acct/examples# ./nfacct-add http-traffic
libnetfilter_acct/examples# ./nfacct-get
http-traffic = { pkts = 000000000000, bytes = 000000000000 };
Then, you can use one of this accounting objects in several iptables
rules using the new nfacct match (which comes in a follow-up patch):
# iptables -I INPUT -p tcp --sport 80 -m nfacct --nfacct-name http-traffic
# iptables -I OUTPUT -p tcp --dport 80 -m nfacct --nfacct-name http-traffic
The idea is simple: if one packet matches the rule, the nfacct match
updates the counters.
Thanks to Patrick McHardy, Eric Dumazet, Changli Gao for reviewing and
providing feedback for this contribution.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/linux/netfilter/Kbuild | 1 +
include/linux/netfilter/nfnetlink.h | 3 +-
include/linux/netfilter/nfnetlink_acct.h | 36 +++
net/netfilter/Kconfig | 8 +
net/netfilter/Makefile | 1 +
net/netfilter/nfnetlink_acct.c | 352 ++++++++++++++++++++++++++++++
6 files changed, 400 insertions(+), 1 deletions(-)
create mode 100644 include/linux/netfilter/nfnetlink_acct.h
create mode 100644 net/netfilter/nfnetlink_acct.c
diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index d81f771..6785246 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -7,6 +7,7 @@ header-y += nf_conntrack_tcp.h
header-y += nf_conntrack_tuple_common.h
header-y += nf_nat.h
header-y += nfnetlink.h
+header-y += nfnetlink_acct.h
header-y += nfnetlink_compat.h
header-y += nfnetlink_conntrack.h
header-y += nfnetlink_log.h
diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index 74d3386..b64454c 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -48,7 +48,8 @@ struct nfgenmsg {
#define NFNL_SUBSYS_ULOG 4
#define NFNL_SUBSYS_OSF 5
#define NFNL_SUBSYS_IPSET 6
-#define NFNL_SUBSYS_COUNT 7
+#define NFNL_SUBSYS_ACCT 7
+#define NFNL_SUBSYS_COUNT 8
#ifdef __KERNEL__
diff --git a/include/linux/netfilter/nfnetlink_acct.h b/include/linux/netfilter/nfnetlink_acct.h
new file mode 100644
index 0000000..7c4279b
--- /dev/null
+++ b/include/linux/netfilter/nfnetlink_acct.h
@@ -0,0 +1,36 @@
+#ifndef _NFNL_ACCT_H_
+#define _NFNL_ACCT_H_
+
+#ifndef NFACCT_NAME_MAX
+#define NFACCT_NAME_MAX 32
+#endif
+
+enum nfnl_acct_msg_types {
+ NFNL_MSG_ACCT_NEW,
+ NFNL_MSG_ACCT_GET,
+ NFNL_MSG_ACCT_GET_CTRZERO,
+ NFNL_MSG_ACCT_DEL,
+ NFNL_MSG_ACCT_MAX
+};
+
+enum nfnl_acct_type {
+ NFACCT_UNSPEC,
+ NFACCT_NAME,
+ NFACCT_PKTS,
+ NFACCT_BYTES,
+ NFACCT_USE,
+ __NFACCT_MAX
+};
+#define NFACCT_MAX (__NFACCT_MAX - 1)
+
+#ifdef __KERNEL__
+
+struct nf_acct;
+
+extern struct nf_acct *nfnl_acct_find_get(const char *filter_name);
+extern void nfnl_acct_put(struct nf_acct *acct);
+extern void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct);
+
+#endif /* __KERNEL__ */
+
+#endif /* _NFNL_ACCT_H */
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index d5597b7..77326ac 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -4,6 +4,14 @@ menu "Core Netfilter Configuration"
config NETFILTER_NETLINK
tristate
+config NETFILTER_NETLINK_ACCT
+tristate "Netfilter NFACCT over NFNETLINK interface"
+ depends on NETFILTER_ADVANCED
+ select NETFILTER_NETLINK
+ help
+ If this option is enabled, the kernel will include support
+ for extended accounting via NFNETLINK.
+
config NETFILTER_NETLINK_QUEUE
tristate "Netfilter NFQUEUE over NFNETLINK interface"
depends on NETFILTER_ADVANCED
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 1a02853..4da1c87 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -7,6 +7,7 @@ nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o
obj-$(CONFIG_NETFILTER) = netfilter.o
obj-$(CONFIG_NETFILTER_NETLINK) += nfnetlink.o
+obj-$(CONFIG_NETFILTER_NETLINK_ACCT) += nfnetlink_acct.o
obj-$(CONFIG_NETFILTER_NETLINK_QUEUE) += nfnetlink_queue.o
obj-$(CONFIG_NETFILTER_NETLINK_LOG) += nfnetlink_log.o
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
new file mode 100644
index 0000000..362ab6c
--- /dev/null
+++ b/net/netfilter/nfnetlink_acct.c
@@ -0,0 +1,352 @@
+/*
+ * (C) 2011 Pablo Neira Ayuso <pablo@netfilter.org>
+ * (C) 2011 Intra2net AG <http://www.intra2net.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation (or any later at your option).
+ */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+#include <linux/rculist.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <net/netlink.h>
+#include <net/sock.h>
+#include <asm/atomic.h>
+
+#include <linux/netfilter.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_acct.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_DESCRIPTION("nfacct: Extended Netfilter accounting infrastructure");
+
+static LIST_HEAD(nfnl_acct_list);
+
+struct nf_acct {
+ atomic64_t pkts;
+ atomic64_t bytes;
+ struct list_head head;
+ atomic_t refcnt;
+ char name[NFACCT_NAME_MAX];
+ struct rcu_head rcu_head;
+};
+
+static int
+nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb,
+ const struct nlmsghdr *nlh, const struct nlattr * const tb[])
+{
+ struct nf_acct *nfacct, *matching = NULL;
+ char *acct_name;
+
+ if (!tb[NFACCT_NAME])
+ return -EINVAL;
+
+ acct_name = nla_data(tb[NFACCT_NAME]);
+
+ list_for_each_entry(nfacct, &nfnl_acct_list, head) {
+ if (strncmp(nfacct->name, acct_name, NFACCT_NAME_MAX) != 0)
+ continue;
+
+ if (nlh->nlmsg_flags & NLM_F_EXCL)
+ return -EEXIST;
+
+ matching = nfacct;
+ break;
+ }
+
+ if (matching) {
+ if (nlh->nlmsg_flags & NLM_F_REPLACE) {
+ /* reset counters if you request a replacement. */
+ atomic64_set(&matching->pkts, 0);
+ atomic64_set(&matching->bytes, 0);
+ return 0;
+ }
+ return -EBUSY;
+ }
+
+ nfacct = kzalloc(sizeof(struct nf_acct), GFP_KERNEL);
+ if (nfacct == NULL)
+ return -ENOMEM;
+
+ strncpy(nfacct->name, nla_data(tb[NFACCT_NAME]), NFACCT_NAME_MAX);
+
+ if (tb[NFACCT_BYTES]) {
+ atomic64_set(&nfacct->bytes,
+ be64_to_cpu(nla_get_u64(tb[NFACCT_BYTES])));
+ }
+ if (tb[NFACCT_PKTS]) {
+ atomic64_set(&nfacct->pkts,
+ be64_to_cpu(nla_get_u64(tb[NFACCT_PKTS])));
+ }
+ atomic_set(&nfacct->refcnt, 1);
+ list_add_tail_rcu(&nfacct->head, &nfnl_acct_list);
+ return 0;
+}
+
+static int
+nfnl_acct_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type,
+ int event, struct nf_acct *acct)
+{
+ struct nlmsghdr *nlh;
+ struct nfgenmsg *nfmsg;
+ unsigned int flags = pid ? NLM_F_MULTI : 0;
+ u64 pkts, bytes;
+
+ event |= NFNL_SUBSYS_ACCT << 8;
+ nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags);
+ if (nlh == NULL)
+ goto nlmsg_failure;
+
+ nfmsg = nlmsg_data(nlh);
+ nfmsg->nfgen_family = AF_UNSPEC;
+ nfmsg->version = NFNETLINK_V0;
+ nfmsg->res_id = 0;
+
+ NLA_PUT_STRING(skb, NFACCT_NAME, acct->name);
+
+ if (type == NFNL_MSG_ACCT_GET_CTRZERO) {
+ pkts = atomic64_xchg(&acct->pkts, 0);
+ bytes = atomic64_xchg(&acct->bytes, 0);
+ } else {
+ pkts = atomic64_read(&acct->pkts);
+ bytes = atomic64_read(&acct->bytes);
+ }
+ NLA_PUT_BE64(skb, NFACCT_PKTS, cpu_to_be64(pkts));
+ NLA_PUT_BE64(skb, NFACCT_BYTES, cpu_to_be64(bytes));
+ NLA_PUT_BE32(skb, NFACCT_USE, htonl(atomic_read(&acct->refcnt)));
+
+ nlmsg_end(skb, nlh);
+ return skb->len;
+
+nlmsg_failure:
+nla_put_failure:
+ nlmsg_cancel(skb, nlh);
+ return -1;
+}
+
+static int
+nfnl_acct_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct nf_acct *cur, *last;
+
+ if (cb->args[2])
+ return 0;
+
+ last = (struct nf_acct *)cb->args[1];
+ if (cb->args[1])
+ cb->args[1] = 0;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(cur, &nfnl_acct_list, head) {
+ if (last && cur != last)
+ continue;
+
+ if (nfnl_acct_fill_info(skb, NETLINK_CB(cb->skb).pid,
+ cb->nlh->nlmsg_seq,
+ NFNL_MSG_TYPE(cb->nlh->nlmsg_type),
+ NFNL_MSG_ACCT_NEW, cur) < 0) {
+ cb->args[1] = (unsigned long)cur;
+ break;
+ }
+ }
+ if (!cb->args[1])
+ cb->args[2] = 1;
+ rcu_read_unlock();
+ return skb->len;
+}
+
+static int
+nfnl_acct_get(struct sock *nfnl, struct sk_buff *skb,
+ const struct nlmsghdr *nlh, const struct nlattr * const tb[])
+{
+ int ret = 0;
+ struct nf_acct *cur;
+ char *acct_name;
+
+ if (nlh->nlmsg_flags & NLM_F_DUMP) {
+ return netlink_dump_start(nfnl, skb, nlh, nfnl_acct_dump,
+ NULL, 0);
+ }
+
+ if (!tb[NFACCT_NAME])
+ return -EINVAL;
+ acct_name = nla_data(tb[NFACCT_NAME]);
+
+ list_for_each_entry(cur, &nfnl_acct_list, head) {
+ struct sk_buff *skb2;
+
+ if (strncmp(cur->name, acct_name, NFACCT_NAME_MAX)!= 0)
+ continue;
+
+ skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (skb2 == NULL)
+ break;
+
+ ret = nfnl_acct_fill_info(skb2, NETLINK_CB(skb).pid,
+ nlh->nlmsg_seq,
+ NFNL_MSG_TYPE(nlh->nlmsg_type),
+ NFNL_MSG_ACCT_NEW, cur);
+ if (ret <= 0)
+ kfree_skb(skb2);
+
+ break;
+ }
+ return ret;
+}
+
+/* try to delete object, fail if it is still in use. */
+static int nfnl_acct_try_del(struct nf_acct *cur)
+{
+ int ret = 0;
+
+ /* we want to avoid races with nfnl_acct_find_get. */
+ if (atomic_dec_and_test(&cur->refcnt)) {
+ /* We are protected by nfnl mutex. */
+ list_del_rcu(&cur->head);
+ kfree_rcu(cur, rcu_head);
+ } else {
+ /* still in use, restore reference counter. */
+ atomic_inc(&cur->refcnt);
+ ret = -EBUSY;
+ }
+ return ret;
+}
+
+static int
+nfnl_acct_del(struct sock *nfnl, struct sk_buff *skb,
+ const struct nlmsghdr *nlh, const struct nlattr * const tb[])
+{
+ char *acct_name;
+ struct nf_acct *cur;
+ int ret = -ENOENT;
+
+ if (!tb[NFACCT_NAME]) {
+ list_for_each_entry(cur, &nfnl_acct_list, head)
+ nfnl_acct_try_del(cur);
+
+ return 0;
+ }
+ acct_name = nla_data(tb[NFACCT_NAME]);
+
+ list_for_each_entry(cur, &nfnl_acct_list, head) {
+ if (strncmp(cur->name, acct_name, NFACCT_NAME_MAX) != 0)
+ continue;
+
+ ret = nfnl_acct_try_del(cur);
+ if (ret < 0)
+ return ret;
+
+ break;
+ }
+ return ret;
+}
+
+static const struct nla_policy nfnl_acct_policy[NFACCT_MAX+1] = {
+ [NFACCT_NAME] = { .type = NLA_NUL_STRING, .len = NFACCT_NAME_MAX-1 },
+ [NFACCT_BYTES] = { .type = NLA_U64 },
+ [NFACCT_PKTS] = { .type = NLA_U64 },
+};
+
+static const struct nfnl_callback nfnl_acct_cb[NFNL_MSG_ACCT_MAX] = {
+ [NFNL_MSG_ACCT_NEW] = { .call = nfnl_acct_new,
+ .attr_count = NFACCT_MAX,
+ .policy = nfnl_acct_policy },
+ [NFNL_MSG_ACCT_GET] = { .call = nfnl_acct_get,
+ .attr_count = NFACCT_MAX,
+ .policy = nfnl_acct_policy },
+ [NFNL_MSG_ACCT_GET_CTRZERO] = { .call = nfnl_acct_get,
+ .attr_count = NFACCT_MAX,
+ .policy = nfnl_acct_policy },
+ [NFNL_MSG_ACCT_DEL] = { .call = nfnl_acct_del,
+ .attr_count = NFACCT_MAX,
+ .policy = nfnl_acct_policy },
+};
+
+static const struct nfnetlink_subsystem nfnl_acct_subsys = {
+ .name = "acct",
+ .subsys_id = NFNL_SUBSYS_ACCT,
+ .cb_count = NFNL_MSG_ACCT_MAX,
+ .cb = nfnl_acct_cb,
+};
+
+MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_ACCT);
+
+struct nf_acct *nfnl_acct_find_get(const char *acct_name)
+{
+ struct nf_acct *cur, *acct = NULL;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(cur, &nfnl_acct_list, head) {
+ if (strncmp(cur->name, acct_name, NFACCT_NAME_MAX)!= 0)
+ continue;
+
+ if (!try_module_get(THIS_MODULE))
+ goto err;
+
+ if (!atomic_inc_not_zero(&cur->refcnt)) {
+ module_put(THIS_MODULE);
+ goto err;
+ }
+
+ acct = cur;
+ break;
+ }
+err:
+ rcu_read_unlock();
+ return acct;
+}
+EXPORT_SYMBOL_GPL(nfnl_acct_find_get);
+
+void nfnl_acct_put(struct nf_acct *acct)
+{
+ atomic_dec(&acct->refcnt);
+ module_put(THIS_MODULE);
+}
+EXPORT_SYMBOL_GPL(nfnl_acct_put);
+
+void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct)
+{
+ atomic64_inc(&nfacct->pkts);
+ atomic64_add(skb->len, &nfacct->bytes);
+}
+EXPORT_SYMBOL_GPL(nfnl_acct_update);
+
+static int __init nfnl_acct_init(void)
+{
+ int ret;
+
+ pr_info("nfnl_acct: registering with nfnetlink.\n");
+ ret = nfnetlink_subsys_register(&nfnl_acct_subsys);
+ if (ret < 0) {
+ pr_err("nfnl_acct_init: cannot register with nfnetlink.\n");
+ goto err_out;
+ }
+ return 0;
+err_out:
+ return ret;
+}
+
+static void __exit nfnl_acct_exit(void)
+{
+ struct nf_acct *cur, *tmp;
+
+ pr_info("nfnl_acct: unregistering from nfnetlink.\n");
+ nfnetlink_subsys_unregister(&nfnl_acct_subsys);
+
+ list_for_each_entry_safe(cur, tmp, &nfnl_acct_list, head) {
+ list_del_rcu(&cur->head);
+ /* We are sure that our objects have no clients at this point,
+ * it's safe to release them all without checking refcnt. */
+ kfree_rcu(cur, rcu_head);
+ }
+}
+
+module_init(nfnl_acct_init);
+module_exit(nfnl_acct_exit);
--
1.7.2.5
^ permalink raw reply related
* Re: [PATCH 00/19] netfilter updates for net-next (upcoming 3.3)
From: David Miller @ 2011-12-25 8:12 UTC (permalink / raw)
To: pablo; +Cc: netfilter-devel, netdev
In-Reply-To: <1324778255-2830-1-git-send-email-pablo@netfilter.org>
From: pablo@netfilter.org
Date: Sun, 25 Dec 2011 02:57:16 +0100
> The following patchset includes the Netfilter updates for net-next.
> It contains:
>
> - New reverse path filter matches for xtables from Florian Westphal.
>
> - Use of atomic64_t for the conntrack packet and bytes counters, instead
> of using spinlock to protect counters updates from Eric Dumazet.
>
> - One enhancement for the SH scheduler (IPVS) from Michael Maxim.
>
> - Seven patches from Patrick McHardy to cleanup several aspects of the
> existing NAT code.
>
> - The rework of the user-space expectation support by myself.
>
> - Several updates for ctnetlink by myself.
>
> - The new nfacct infrastructure and the corresponding xtables match
> by myself.
>
> You can pull these changes from:
>
> git://1984.lsi.us.es/net-next nf-next
Pulled, thanks a lot.
^ permalink raw reply
* [PATCH] skge: restore multicast rx filter on resume
From: Florian Zumbiehl @ 2011-12-25 8:18 UTC (permalink / raw)
To: netdev, shemminger
Hi,
no clue whether this is really the correct[tm] way to fix this, but it
makes it so that IPv6 doesn't start failing after a suspend/resume cycle
because neighbour discovery stops working ...
Florian
---------------------------------------------------------------------------
skge: restore multicast rx filter on resume
Signed-off-by: Florian Zumbiehl <florz@florz.de>
diff --git a/drivers/net/skge.c b/drivers/net/skge.c
index f4be5c7..cd968e5 100644
--- a/drivers/net/skge.c
+++ b/drivers/net/skge.c
@@ -4046,6 +4046,7 @@ static int skge_resume(struct device *dev)
dev_close(dev);
goto out;
}
+ skge_set_multicast(dev);
}
}
out:
^ permalink raw reply related
* Re: [PATCH net-next 2/2] igb: offer a PTP Hardware Clock instead of the timecompare method
From: Richard Cochran @ 2011-12-25 11:30 UTC (permalink / raw)
To: Wyborny, Carolyn
Cc: Brandeburg, Jesse, netdev@vger.kernel.org,
e1000-devel@lists.sourceforge.net, Keller, Jacob E,
Kirsher, Jeffrey T, Ronciak, John, John Stultz, Thomas Gleixner
In-Reply-To: <EDC0E76513226749BFBC9C3FB031318F018669B7BB@orsmsx508.amr.corp.intel.com>
On Thu, Dec 15, 2011 at 08:46:55AM -0800, Wyborny, Carolyn wrote:
> >-----Original Message-----
> >From: Richard Cochran [mailto:richardcochran@gmail.com]
...
> >Any chance of getting the driver tested on a 82576?
> >
> >Thanks,
> >
> >Richard
>
> I will request this testing and let you know.
Never mind about testing this patch. I have already found a bug in the
code path for the 82576. I will post a new, corrected patch later on
this week.
Thanks, and Merry Christmas to All,
Richard
^ permalink raw reply
* Re: [PATCH] SUNRPC: make SUNPRC clients list per network namespace context
From: Trond Myklebust @ 2011-12-25 12:48 UTC (permalink / raw)
To: Stanislav Kinsbursky
Cc: linux-nfs, xemul, neilb, netdev, linux-kernel, jbottomley,
bfields, davem, devel
In-Reply-To: <20111214081918.2804.59143.stgit@localhost6.localdomain6>
On Wed, 2011-12-14 at 12:19 +0300, Stanislav Kinsbursky wrote:
> This patch moves static SUNRPC clients list and it's lock to sunrpc_net
> structure.
> Currently this list is used only for debug purposes. But later it will be used
> also for selecting clients by networks namespace on PipeFS mount/umount events.
> Per-network namespace lists will make this faster and simplier.
>
> Note: client list is taken from "init_net" network namespace context in
> rpc_show_tasks(). This will be changed with making SUNRPC sysctl's per network
> namespace context.
>
> Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
This doesn't seem to integrate with any of your patch series, and
conflicts with everything that touches netns.h, for instance...
--
Trond Myklebust
Linux NFS client maintainer
NetApp
Trond.Myklebust@netapp.com
www.netapp.com
^ permalink raw reply
* Re: [PATCH 6/6] SUNRPC: split SUNPRC PipeFS dentry and private pipe data creation
From: Trond Myklebust @ 2011-12-25 13:16 UTC (permalink / raw)
To: Stanislav Kinsbursky
Cc: linux-nfs, xemul, neilb, netdev, linux-kernel, jbottomley,
bfields, davem, devel
In-Reply-To: <20111122144215.479.20931.stgit@localhost6.localdomain6>
On Tue, 2011-11-22 at 18:42 +0300, Stanislav Kinsbursky wrote:
> This patch is a final step towards to removing PipeFS inode references from
> kernel code other than PipeFS itself. It makes all kernel SUNRPC PipeFS users
> depends on pipe private data, which state depend on their specific operations,
> etc.
> This patch completes SUNRPC PipeFS preparations and allows to create pipe
> private data and PipeFS dentries independently.
> Next step will be making SUNPRC PipeFS dentries allocated by SUNRPC PipeFS
> network namespace aware routines.
>
> Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
>
> ---
> fs/nfs/blocklayout/blocklayout.c | 16 ++++++++--
> fs/nfs/blocklayout/blocklayout.h | 2 +
> fs/nfs/blocklayout/blocklayoutdev.c | 2 +
> fs/nfs/blocklayout/blocklayoutdm.c | 2 +
> fs/nfs/idmap.c | 28 +++++++++++++-----
> include/linux/sunrpc/rpc_pipe_fs.h | 7 +++--
> net/sunrpc/auth_gss/auth_gss.c | 54 +++++++++++++++++++++++------------
> net/sunrpc/rpc_pipe.c | 54 ++++++++++++++++++++---------------
> 8 files changed, 107 insertions(+), 58 deletions(-)
>
> diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
> index 9561c8f..c26633e 100644
> --- a/fs/nfs/blocklayout/blocklayout.c
> +++ b/fs/nfs/blocklayout/blocklayout.c
> @@ -46,7 +46,7 @@ MODULE_LICENSE("GPL");
> MODULE_AUTHOR("Andy Adamson <andros@citi.umich.edu>");
> MODULE_DESCRIPTION("The NFSv4.1 pNFS Block layout driver");
>
> -struct dentry *bl_device_pipe;
> +struct rpc_pipe *bl_device_pipe;
> wait_queue_head_t bl_wq;
>
> static void print_page(struct page *page)
> @@ -991,15 +991,22 @@ static int __init nfs4blocklayout_init(void)
> if (ret)
> goto out_remove;
>
> - bl_device_pipe = rpc_mkpipe(path.dentry, "blocklayout", NULL,
> - &bl_upcall_ops, 0);
Needs a rebase: this is missing a bugfix for a leaked struct path...
> + bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0);
> if (IS_ERR(bl_device_pipe)) {
> ret = PTR_ERR(bl_device_pipe);
> goto out_remove;
> }
> + bl_device_pipe->dentry = rpc_mkpipe_dentry(path.dentry, "blocklayout",
> + NULL, bl_device_pipe);
> + if (IS_ERR(bl_device_pipe->dentry)) {
> + ret = PTR_ERR(bl_device_pipe->dentry);
> + goto out_destroy_pipe;
> + }
> out:
> return ret;
>
> +out_destroy_pipe:
> + rpc_destroy_pipe_data(bl_device_pipe);
> out_remove:
> pnfs_unregister_layoutdriver(&blocklayout_type);
> return ret;
> @@ -1011,7 +1018,8 @@ static void __exit nfs4blocklayout_exit(void)
> __func__);
>
> pnfs_unregister_layoutdriver(&blocklayout_type);
> - rpc_unlink(bl_device_pipe);
> + rpc_unlink(bl_device_pipe->dentry);
> + rpc_destroy_pipe_data(bl_device_pipe);
> }
>
> MODULE_ALIAS("nfs-layouttype4-3");
> diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
> index f27d827..5f30941 100644
> --- a/fs/nfs/blocklayout/blocklayout.h
> +++ b/fs/nfs/blocklayout/blocklayout.h
> @@ -159,7 +159,7 @@ struct bl_msg_hdr {
> u16 totallen; /* length of entire message, including hdr itself */
> };
>
> -extern struct dentry *bl_device_pipe;
> +extern struct rpc_pipe *bl_device_pipe;
> extern wait_queue_head_t bl_wq;
>
> #define BL_DEVICE_UMOUNT 0x0 /* Umount--delete devices */
> diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c
> index 44dc348..79f4752 100644
> --- a/fs/nfs/blocklayout/blocklayoutdev.c
> +++ b/fs/nfs/blocklayout/blocklayoutdev.c
> @@ -168,7 +168,7 @@ nfs4_blk_decode_device(struct nfs_server *server,
>
> dprintk("%s CALLING USERSPACE DAEMON\n", __func__);
> add_wait_queue(&bl_wq, &wq);
> - if (rpc_queue_upcall(RPC_I(bl_device_pipe->d_inode)->pipe, &msg) < 0) {
> + if (rpc_queue_upcall(bl_device_pipe, &msg) < 0) {
> remove_wait_queue(&bl_wq, &wq);
> goto out;
> }
> diff --git a/fs/nfs/blocklayout/blocklayoutdm.c b/fs/nfs/blocklayout/blocklayoutdm.c
> index 3c38244..631f254 100644
> --- a/fs/nfs/blocklayout/blocklayoutdm.c
> +++ b/fs/nfs/blocklayout/blocklayoutdm.c
> @@ -66,7 +66,7 @@ static void dev_remove(dev_t dev)
> msg.len = sizeof(bl_msg) + bl_msg.totallen;
>
> add_wait_queue(&bl_wq, &wq);
> - if (rpc_queue_upcall(RPC_I(bl_device_pipe->d_inode)->pipe, &msg) < 0) {
> + if (rpc_queue_upcall(bl_device_pipe, &msg) < 0) {
> remove_wait_queue(&bl_wq, &wq);
> goto out;
> }
> diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
> index 7e3d8dd..b09a7f1 100644
> --- a/fs/nfs/idmap.c
> +++ b/fs/nfs/idmap.c
> @@ -327,7 +327,7 @@ struct idmap_hashtable {
> };
>
> struct idmap {
> - struct dentry *idmap_dentry;
> + struct rpc_pipe *idmap_pipe;
> wait_queue_head_t idmap_wq;
> struct idmap_msg idmap_im;
> struct mutex idmap_lock; /* Serializes upcalls */
> @@ -354,6 +354,7 @@ int
> nfs_idmap_new(struct nfs_client *clp)
> {
> struct idmap *idmap;
> + struct rpc_pipe *pipe;
> int error;
>
> BUG_ON(clp->cl_idmap != NULL);
> @@ -362,14 +363,23 @@ nfs_idmap_new(struct nfs_client *clp)
> if (idmap == NULL)
> return -ENOMEM;
>
> - idmap->idmap_dentry = rpc_mkpipe(clp->cl_rpcclient->cl_path.dentry,
> - "idmap", idmap, &idmap_upcall_ops, 0);
> - if (IS_ERR(idmap->idmap_dentry)) {
> - error = PTR_ERR(idmap->idmap_dentry);
> + pipe = rpc_mkpipe_data(&idmap_upcall_ops, 0);
> + if (IS_ERR(pipe)) {
> + error = PTR_ERR(pipe);
> kfree(idmap);
> return error;
> }
>
> + if (clp->cl_rpcclient->cl_path.dentry)
> + pipe->dentry = rpc_mkpipe_dentry(clp->cl_rpcclient->cl_path.dentry,
> + "idmap", idmap, pipe);
> + if (IS_ERR(pipe->dentry)) {
> + error = PTR_ERR(pipe->dentry);
> + rpc_destroy_pipe_data(pipe);
> + kfree(idmap);
> + return error;
> + }
> + idmap->idmap_pipe = pipe;
> mutex_init(&idmap->idmap_lock);
> mutex_init(&idmap->idmap_im_lock);
> init_waitqueue_head(&idmap->idmap_wq);
> @@ -387,7 +397,9 @@ nfs_idmap_delete(struct nfs_client *clp)
>
> if (!idmap)
> return;
> - rpc_unlink(idmap->idmap_dentry);
> + if (idmap->idmap_pipe->dentry)
Shouldn't this be a test for IS_ERR(idmap->idmap_pipe->dentry)?
> + rpc_unlink(idmap->idmap_pipe->dentry);
> + rpc_destroy_pipe_data(idmap->idmap_pipe);
> clp->cl_idmap = NULL;
> kfree(idmap);
> }
> @@ -508,7 +520,7 @@ nfs_idmap_id(struct idmap *idmap, struct idmap_hashtable *h,
> msg.len = sizeof(*im);
>
> add_wait_queue(&idmap->idmap_wq, &wq);
> - if (rpc_queue_upcall(RPC_I(idmap->idmap_dentry->d_inode)->pipe, &msg) < 0) {
> + if (rpc_queue_upcall(idmap->idmap_pipe, &msg) < 0) {
> remove_wait_queue(&idmap->idmap_wq, &wq);
> goto out;
> }
> @@ -569,7 +581,7 @@ nfs_idmap_name(struct idmap *idmap, struct idmap_hashtable *h,
>
> add_wait_queue(&idmap->idmap_wq, &wq);
>
> - if (rpc_queue_upcall(RPC_I(idmap->idmap_dentry->d_inode)->pipe, &msg) < 0) {
> + if (rpc_queue_upcall(idmap->idmap_pipe, &msg) < 0) {
> remove_wait_queue(&idmap->idmap_wq, &wq);
> goto out;
> }
> diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h
> index ad78bea..0808ed2 100644
> --- a/include/linux/sunrpc/rpc_pipe_fs.h
> +++ b/include/linux/sunrpc/rpc_pipe_fs.h
> @@ -34,6 +34,7 @@ struct rpc_pipe {
> struct delayed_work queue_timeout;
> const struct rpc_pipe_ops *ops;
> spinlock_t lock;
> + struct dentry *dentry;
> };
>
> struct rpc_inode {
> @@ -77,8 +78,10 @@ extern struct dentry *rpc_create_cache_dir(struct dentry *,
> struct cache_detail *);
> extern void rpc_remove_cache_dir(struct dentry *);
>
> -extern struct dentry *rpc_mkpipe(struct dentry *, const char *, void *,
> - const struct rpc_pipe_ops *, int flags);
> +struct rpc_pipe *rpc_mkpipe_data(const struct rpc_pipe_ops *ops, int flags);
> +void rpc_destroy_pipe_data(struct rpc_pipe *pipe);
> +extern struct dentry *rpc_mkpipe_dentry(struct dentry *, const char *, void *,
> + struct rpc_pipe *);
> extern int rpc_unlink(struct dentry *);
> extern struct vfsmount *rpc_get_mount(void);
> extern void rpc_put_mount(void);
> diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
> index 15fd9fe..2b25a7b 100644
> --- a/net/sunrpc/auth_gss/auth_gss.c
> +++ b/net/sunrpc/auth_gss/auth_gss.c
> @@ -81,7 +81,7 @@ struct gss_auth {
> * mechanism (for example, "krb5") and exists for
> * backwards-compatibility with older gssd's.
> */
> - struct dentry *dentry[2];
> + struct rpc_pipe *pipe[2];
> };
>
> /* pipe_version >= 0 if and only if someone has a pipe open. */
> @@ -451,7 +451,7 @@ gss_alloc_msg(struct gss_auth *gss_auth, uid_t uid, struct rpc_clnt *clnt,
> kfree(gss_msg);
> return ERR_PTR(vers);
> }
> - gss_msg->pipe = RPC_I(gss_auth->dentry[vers]->d_inode)->pipe;
> + gss_msg->pipe = gss_auth->pipe[vers];
> INIT_LIST_HEAD(&gss_msg->list);
> rpc_init_wait_queue(&gss_msg->rpc_waitqueue, "RPCSEC_GSS upcall waitq");
> init_waitqueue_head(&gss_msg->waitqueue);
> @@ -821,21 +821,33 @@ gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor)
> * that we supported only the old pipe. So we instead create
> * the new pipe first.
> */
> - gss_auth->dentry[1] = rpc_mkpipe(clnt->cl_path.dentry,
> - "gssd",
> - clnt, &gss_upcall_ops_v1,
> - RPC_PIPE_WAIT_FOR_OPEN);
> - if (IS_ERR(gss_auth->dentry[1])) {
> - err = PTR_ERR(gss_auth->dentry[1]);
> + gss_auth->pipe[1] = rpc_mkpipe_data(&gss_upcall_ops_v1,
> + RPC_PIPE_WAIT_FOR_OPEN);
> + if (IS_ERR(gss_auth->pipe[1])) {
> + err = PTR_ERR(gss_auth->pipe[1]);
> goto err_put_mech;
> }
>
> - gss_auth->dentry[0] = rpc_mkpipe(clnt->cl_path.dentry,
> - gss_auth->mech->gm_name,
> - clnt, &gss_upcall_ops_v0,
> - RPC_PIPE_WAIT_FOR_OPEN);
> - if (IS_ERR(gss_auth->dentry[0])) {
> - err = PTR_ERR(gss_auth->dentry[0]);
> + gss_auth->pipe[0] = rpc_mkpipe_data(&gss_upcall_ops_v0,
> + RPC_PIPE_WAIT_FOR_OPEN);
> + if (IS_ERR(gss_auth->pipe[0])) {
> + err = PTR_ERR(gss_auth->pipe[0]);
> + goto err_destroy_pipe_1;
> + }
> +
> + gss_auth->pipe[1]->dentry = rpc_mkpipe_dentry(clnt->cl_path.dentry,
> + "gssd",
> + clnt, gss_auth->pipe[1]);
> + if (IS_ERR(gss_auth->pipe[1]->dentry)) {
> + err = PTR_ERR(gss_auth->pipe[1]->dentry);
> + goto err_destroy_pipe_0;
> + }
> +
> + gss_auth->pipe[0]->dentry = rpc_mkpipe_dentry(clnt->cl_path.dentry,
> + gss_auth->mech->gm_name,
> + clnt, gss_auth->pipe[0]);
> + if (IS_ERR(gss_auth->pipe[0]->dentry)) {
> + err = PTR_ERR(gss_auth->pipe[0]->dentry);
> goto err_unlink_pipe_1;
> }
> err = rpcauth_init_credcache(auth);
> @@ -844,9 +856,13 @@ gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor)
>
> return auth;
> err_unlink_pipe_0:
> - rpc_unlink(gss_auth->dentry[0]);
> + rpc_unlink(gss_auth->pipe[0]->dentry);
> err_unlink_pipe_1:
> - rpc_unlink(gss_auth->dentry[1]);
> + rpc_unlink(gss_auth->pipe[1]->dentry);
> +err_destroy_pipe_0:
> + rpc_destroy_pipe_data(gss_auth->pipe[0]);
> +err_destroy_pipe_1:
> + rpc_destroy_pipe_data(gss_auth->pipe[1]);
> err_put_mech:
> gss_mech_put(gss_auth->mech);
> err_free:
> @@ -859,8 +875,10 @@ out_dec:
> static void
> gss_free(struct gss_auth *gss_auth)
> {
> - rpc_unlink(gss_auth->dentry[1]);
> - rpc_unlink(gss_auth->dentry[0]);
> + rpc_unlink(gss_auth->pipe[0]->dentry);
> + rpc_unlink(gss_auth->pipe[1]->dentry);
> + rpc_destroy_pipe_data(gss_auth->pipe[0]);
> + rpc_destroy_pipe_data(gss_auth->pipe[1]);
> gss_mech_put(gss_auth->mech);
>
> kfree(gss_auth);
> diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
> index 0eed975..8e59580 100644
> --- a/net/sunrpc/rpc_pipe.c
> +++ b/net/sunrpc/rpc_pipe.c
> @@ -187,7 +187,6 @@ rpc_i_callback(struct rcu_head *head)
> {
> struct inode *inode = container_of(head, struct inode, i_rcu);
> INIT_LIST_HEAD(&inode->i_dentry);
> - kfree(RPC_I(inode)->pipe);
> kmem_cache_free(rpc_inode_cachep, RPC_I(inode));
> }
>
> @@ -556,34 +555,44 @@ init_pipe(struct rpc_pipe *pipe)
> rpc_timeout_upcall_queue);
> pipe->ops = NULL;
> spin_lock_init(&pipe->lock);
> + pipe->dentry = NULL;
> +}
>
> +void rpc_destroy_pipe_data(struct rpc_pipe *pipe)
> +{
> + kfree(pipe);
> }
> +EXPORT_SYMBOL_GPL(rpc_destroy_pipe_data);
>
> -static int __rpc_mkpipe(struct inode *dir, struct dentry *dentry,
> - umode_t mode,
> - const struct file_operations *i_fop,
> - void *private,
> - const struct rpc_pipe_ops *ops,
> - int flags)
> +struct rpc_pipe *rpc_mkpipe_data(const struct rpc_pipe_ops *ops, int flags)
> {
> struct rpc_pipe *pipe;
> - struct rpc_inode *rpci;
> - int err;
>
> pipe = kzalloc(sizeof(struct rpc_pipe), GFP_KERNEL);
> if (!pipe)
> - return -ENOMEM;
> + return ERR_PTR(-ENOMEM);
> init_pipe(pipe);
> + pipe->ops = ops;
> + pipe->flags = flags;
> + return pipe;
> +}
> +EXPORT_SYMBOL_GPL(rpc_mkpipe_data);
> +
> +static int __rpc_mkpipe_dentry(struct inode *dir, struct dentry *dentry,
> + umode_t mode,
> + const struct file_operations *i_fop,
> + void *private,
> + struct rpc_pipe *pipe)
> +{
> + struct rpc_inode *rpci;
> + int err;
> +
> err = __rpc_create_common(dir, dentry, S_IFIFO | mode, i_fop, private);
> - if (err) {
> - kfree(pipe);
> + if (err)
> return err;
> - }
> rpci = RPC_I(dentry->d_inode);
> rpci->private = private;
> rpci->pipe = pipe;
> - rpci->pipe->flags = flags;
> - rpci->pipe->ops = ops;
> fsnotify_create(dir, dentry);
> return 0;
> }
> @@ -800,9 +809,8 @@ static int rpc_rmdir_depopulate(struct dentry *dentry,
> * The @private argument passed here will be available to all these methods
> * from the file pointer, via RPC_I(file->f_dentry->d_inode)->private.
> */
> -struct dentry *rpc_mkpipe(struct dentry *parent, const char *name,
> - void *private, const struct rpc_pipe_ops *ops,
> - int flags)
> +struct dentry *rpc_mkpipe_dentry(struct dentry *parent, const char *name,
> + void *private, struct rpc_pipe *pipe)
> {
> struct dentry *dentry;
> struct inode *dir = parent->d_inode;
> @@ -810,9 +818,9 @@ struct dentry *rpc_mkpipe(struct dentry *parent, const char *name,
> struct qstr q;
> int err;
>
> - if (ops->upcall == NULL)
> + if (pipe->ops->upcall == NULL)
> umode &= ~S_IRUGO;
> - if (ops->downcall == NULL)
> + if (pipe->ops->downcall == NULL)
> umode &= ~S_IWUGO;
>
> q.name = name;
> @@ -823,8 +831,8 @@ struct dentry *rpc_mkpipe(struct dentry *parent, const char *name,
> dentry = __rpc_lookup_create_exclusive(parent, &q);
> if (IS_ERR(dentry))
> goto out;
> - err = __rpc_mkpipe(dir, dentry, umode, &rpc_pipe_fops,
> - private, ops, flags);
> + err = __rpc_mkpipe_dentry(dir, dentry, umode, &rpc_pipe_fops,
> + private, pipe);
> if (err)
> goto out_err;
> out:
> @@ -837,7 +845,7 @@ out_err:
> err);
> goto out;
> }
> -EXPORT_SYMBOL_GPL(rpc_mkpipe);
> +EXPORT_SYMBOL_GPL(rpc_mkpipe_dentry);
>
> /**
> * rpc_unlink - remove a pipe
>
--
Trond Myklebust
Linux NFS client maintainer
NetApp
Trond.Myklebust@netapp.com
www.netapp.com
^ permalink raw reply
* Re: [PATCH 4/6] SUNPRC: cleanup RPC PipeFS pipes upcall interface
From: Trond Myklebust @ 2011-12-25 13:17 UTC (permalink / raw)
To: Stanislav Kinsbursky
Cc: linux-nfs-u79uwXL29TY76Z2rM5mHXA, xemul-bzQdu9zFT3WakBO8gow8eQ,
neilb-l3A5Bk7waGM, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
jbottomley-bzQdu9zFT3WakBO8gow8eQ, bfields-uC3wQj2KruNg9hUCZPvPmw,
davem-fT/PcQaiUtIeIZ0/mPfg9Q, devel-GEFAQzZX7r8dnm+yROfE0A
In-Reply-To: <20111122144159.479.68045.stgit-bi+AKbBUZKagILUCTcTcHdKyNwTtLsGr@public.gmane.org>
On Tue, 2011-11-22 at 18:41 +0300, Stanislav Kinsbursky wrote:
> RPC pipe upcall doesn't requires only private pipe data. Thus RPC inode
> references in this code can be removed.
>
> Signed-off-by: Stanislav Kinsbursky <skinsbursky-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
>
> ---
> fs/nfs/blocklayout/blocklayoutdev.c | 2 +-
> fs/nfs/blocklayout/blocklayoutdm.c | 2 +-
> fs/nfs/idmap.c | 4 ++--
> include/linux/sunrpc/rpc_pipe_fs.h | 2 +-
> net/sunrpc/auth_gss/auth_gss.c | 3 +--
> net/sunrpc/rpc_pipe.c | 3 +--
> 6 files changed, 7 insertions(+), 9 deletions(-)
>
> diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c
> index a83b393..44dc348 100644
> --- a/fs/nfs/blocklayout/blocklayoutdev.c
> +++ b/fs/nfs/blocklayout/blocklayoutdev.c
> @@ -168,7 +168,7 @@ nfs4_blk_decode_device(struct nfs_server *server,
>
> dprintk("%s CALLING USERSPACE DAEMON\n", __func__);
> add_wait_queue(&bl_wq, &wq);
> - if (rpc_queue_upcall(bl_device_pipe->d_inode, &msg) < 0) {
> + if (rpc_queue_upcall(RPC_I(bl_device_pipe->d_inode)->pipe, &msg) < 0) {
Needs a rebase: the above doesn't apply...
> remove_wait_queue(&bl_wq, &wq);
> goto out;
> }
--
Trond Myklebust
Linux NFS client maintainer
NetApp
Trond.Myklebust-HgOvQuBEEgTQT0dZR+AlfA@public.gmane.org
www.netapp.com
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH net-next 1/2] igb: add PTP Hardware Clock code
From: Richard Cochran @ 2011-12-25 15:30 UTC (permalink / raw)
To: netdev
Cc: e1000-devel, John Ronciak, John Stultz, Jacob Keller,
Thomas Gleixner
In-Reply-To: <382db16df224b31b126f26f0671cb5f67904e834.1323744725.git.richardcochran@gmail.com>
Just for the record, reviewing my own patch and pointing out the
mistakes WRT the 82576.
On Tue, Dec 13, 2011 at 04:00:34AM +0100, Richard Cochran wrote:
> +static void igb_82576_systim_write(struct igb_adapter *igb, u64 ns)
> +{
> + u32 hi, lo;
> + struct e1000_hw *hw = &igb->hw;
> +
> + hi = (ns >> 8) & 0xffffffff;
> + lo = (ns & 0xff) << NS_SHIFT_82576;
Should have been:
hi = (ns >> 13) & 0xffffffff;
lo = (ns & 0x1fff) << NS_SHIFT_82576;
> +
> + wr32(E1000_SYSTIML, lo);
> + wr32(E1000_SYSTIMH, hi);
> +
> + igb_overflow_set(igb, ns, hi & SYSTIMH_MSB_82576, OFL_SHIFT_82576);
> +}
------------------------------------------------------------------------------
Write once. Port to many.
Get the SDK and tools to simplify cross-platform app development. Create
new or port existing apps to sell to consumers worldwide. Explore the
Intel AppUpSM program developer opportunity. appdeveloper.intel.com/join
http://p.sf.net/sfu/intel-appdev
_______________________________________________
E1000-devel mailing list
E1000-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/e1000-devel
To learn more about Intel® Ethernet, visit http://communities.intel.com/community/wired
^ permalink raw reply
* Re: [PATCH net-next 2/2] igb: offer a PTP Hardware Clock instead of the timecompare method
From: Richard Cochran @ 2011-12-25 15:32 UTC (permalink / raw)
To: netdev
Cc: e1000-devel, Jacob Keller, Jeff Kirsher, John Ronciak,
John Stultz, Thomas Gleixner
In-Reply-To: <388385c50909f63bff239894c60dbb00abc65c93.1323744725.git.richardcochran@gmail.com>
On Tue, Dec 13, 2011 at 04:00:35AM +0100, Richard Cochran wrote:
> +void igb_systim_to_hwtstamp(struct igb_adapter *adapter,
> + struct skb_shared_hwtstamps *hwtstamps,
> + u64 systim)
> +{
> + u64 ns;
> + unsigned long flags;
> + unsigned int shift;
> + int msb_set;
> +
> + switch (adapter->hw.mac.type) {
> + case e1000_i350:
> + case e1000_82580:
> + shift = OFL_SHIFT_82580;
> + msb_set = (systim >> 32) & SYSTIMH_MSB_82580;
> + break;
> + case e1000_82576:
> + shift = OFL_SHIFT_82576;
> + msb_set = (systim >> 32) & SYSTIMH_MSB_82576;
Should have converted systim to nanoseconds here.
> + break;
> + default:
> + return;
> + }
> +
> + spin_lock_irqsave(&adapter->tmreg_lock, flags);
> +
> + ns = igb_overflow_get(adapter, systim, msb_set, shift);
> +
> + spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
> +
> + memset(hwtstamps, 0, sizeof(*hwtstamps));
> + hwtstamps->hwtstamp = ns_to_ktime(ns);
> +}
> --
> 1.7.2.5
>
^ permalink raw reply
* [PATCH] unix_diag: Fix incoming connections nla length
From: Pavel Emelyanov @ 2011-12-25 19:58 UTC (permalink / raw)
To: David Miller, Linux Netdev List
The NLA_PUT macro should accept the actual attribute length, not
the amount of elements in array :(
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
---
net/unix/diag.c | 3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 91d5782..39e44c9 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -72,7 +72,8 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb)
if (sk->sk_state == TCP_LISTEN) {
spin_lock(&sk->sk_receive_queue.lock);
- buf = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_ICONS, sk->sk_receive_queue.qlen);
+ buf = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_ICONS,
+ sk->sk_receive_queue.qlen * sizeof(u32));
i = 0;
skb_queue_walk(&sk->sk_receive_queue, skb) {
struct sock *req, *peer;
--
1.5.5.6
^ permalink raw reply related
* Re: pull request: wireless 2011-12-15
From: Rafał Miłecki @ 2011-12-25 23:36 UTC (permalink / raw)
To: John W. Linville, Greg KH; +Cc: davem, linux-wireless, netdev, linux-kernel
In-Reply-To: <CACna6rz3qDpw4eJOoCXx7=z1719v7kS-Ou-WUseR9_vB-O2dag@mail.gmail.com>
W dniu 16 grudnia 2011 07:40 użytkownik Rafał Miłecki
<zajec5@gmail.com> napisał:
> W dniu 15 grudnia 2011 22:38 użytkownik John W. Linville
> <linville@tuxdriver.com> napisał:
>> On Thu, Dec 15, 2011 at 09:04:29PM +0100, Rafał Miłecki wrote:
>>> 2011/12/15 John W. Linville <linville@tuxdriver.com>:
>>> > commit 42a3b63bb2ca4996a3d1210a004eae2333f1119e
>>> >
>>> > Dave,
>>> >
>>> > Here are a few more fixes intended for the 3.2 release. They are
>>> > all small and narrowly focused.
>>>
>>> John, I've made a mistake and didn't use [PATCH 3.2] header to make it
>>> clean my patch is fix. Could you take a look at
>>> [PATCH] bcma: support for suspend and resume
>>> please?
>>>
>>> It's not one-liner, but fixes lock ups, which I believe - we really
>>> want to avoid.
>>
>> It's late in the release cycle, and Dave specifically asked me to slow down.
>>
>> Are these suspend/resume lockups a regression? Or have they always
>> been there? Do they happen to everyone?
>
> The bug is present since first days of bcma. That's why I even decided
> to add stable to CC.
>
> Personally I've tested that only on 1 machine (I don't have more
> suspendable machines with mini PCIe slot). However all Macbook 8.1/8.2
> users have to remove b43 & bcma before suspending [0], they complain
> about that since ever.
>
> Arend: I know you're also complaining for suspend in bcma. Can you
> comment on this?
>
> [0] http://ubuntuforums.org/showthread.php?t=1695746
User nephyrin on #bcm-users has confirmed this patch fixes
suspend&resume for him. Without this patch he got deadlock without
seeing any kernel panic logs - quite an ugly case.
I still think this patch may be worth taking as fix and backporting too.
--
Rafał
^ permalink raw reply
* [PATCH] packet: fix dev refcnt leak when bind fail
From: Wei Yongjun @ 2011-12-26 9:02 UTC (permalink / raw)
To: davem; +Cc: netdev
From: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
If bind is fail such as bind is called after set PACKET_FANOUT
sock option, the dev refcnt will leak.
Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
---
net/packet/af_packet.c | 7 ++++++-
1 files changed, 6 insertions(+), 1 deletions(-)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 3891702..b6ac234 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2501,8 +2501,11 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
strlcpy(name, uaddr->sa_data, sizeof(name));
dev = dev_get_by_name(sock_net(sk), name);
- if (dev)
+ if (dev) {
err = packet_do_bind(sk, dev, pkt_sk(sk)->num);
+ if (err)
+ dev_put(dev);
+ }
return err;
}
@@ -2530,6 +2533,8 @@ static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len
goto out;
}
err = packet_do_bind(sk, dev, sll->sll_protocol ? : pkt_sk(sk)->num);
+ if (err && dev)
+ dev_put(dev);
out:
return err;
--
1.7.7
^ permalink raw reply related
* Re: [PATCH] Partial revert "Basic kernel memory functionality for the Memory Controller"
From: KAMEZAWA Hiroyuki @ 2011-12-26 9:32 UTC (permalink / raw)
To: Michal Hocko
Cc: Glauber Costa, davem-fT/PcQaiUtIeIZ0/mPfg9Q,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA,
eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w,
cgroups-u79uwXL29TY76Z2rM5mHXA, Kirill A. Shutemov, Paul Menage,
Greg Thelen, Johannes Weiner
In-Reply-To: <20111222104339.GA8833-VqjxzfR4DlwKmadIfiO5sKVXKuFTiq87@public.gmane.org>
On Thu, 22 Dec 2011 11:43:39 +0100
Michal Hocko <mhocko-AlSwsSmVLrQ@public.gmane.org> wrote:
> On Thu 22-12-11 12:53:10, Glauber Costa wrote:
> > This reverts commit e5671dfae59b165e2adfd4dfbdeab11ac8db5bda.
> >
> > After a follow up discussion with Michal, it was agreed it would
> > be better to leave the kmem controller with just the tcp files,
> > deferring the behavior of the other general memory.kmem.* files
> > for a later time, when more caches are controlled.
>
> "Because generic kmem files are not used by tcp accounting and it is
> not clear how other slab caches would fit into the scheme."
>
> >
> > We are reverting the original commit so we can track the reference.
> > Part of the patch is kept, because it was used by the later tcp
> > code. Conflicts are shown in the bottom. init/Kconfig is removed from
> > the revert entirely.
> >
> > Signed-off-by: Glauber Costa <glommer-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
> > CC: Kirill A. Shutemov <kirill-oKw7cIdHH8eLwutG50LtGA@public.gmane.org>
> > CC: Paul Menage <paul-inf54ven1CmVyaH7bEyXVA@public.gmane.org>
> > CC: Greg Thelen <gthelen-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
> > CC: Johannes Weiner <jweiner-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
> > CC: Michal Hocko <mhocko-AlSwsSmVLrQ@public.gmane.org>
> > CC: David S. Miller <davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org>
>
> Acked-by: Michal Hocko <mhocko-AlSwsSmVLrQ@public.gmane.org>
>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
^ permalink raw reply
* [PATCH] mlx4: Add missing include of linux/slab.h
From: Axel Lin @ 2011-12-26 9:35 UTC (permalink / raw)
To: linux-kernel
Cc: David S. Miller, Yevgeny Petrilin, Jack Morgenstein,
Marcel Apfelbaum, Eugenia Emantayev, netdev
Include linux/slab.h to fix below build error:
CC drivers/net/ethernet/mellanox/mlx4/resource_tracker.o
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'mlx4_init_resource_tracker':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:233: error: implicit declaration of function 'kzalloc'
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:234: warning: assignment makes pointer from integer without a cast
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'mlx4_free_resource_tracker':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:264: error: implicit declaration of function 'kfree'
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'alloc_qp_tr':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:370: warning: assignment makes pointer from integer without a cast
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'alloc_mtt_tr':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:386: warning: assignment makes pointer from integer without a cast
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'alloc_mpt_tr':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:402: warning: assignment makes pointer from integer without a cast
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'alloc_eq_tr':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:417: warning: assignment makes pointer from integer without a cast
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'alloc_cq_tr':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:431: warning: assignment makes pointer from integer without a cast
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'alloc_srq_tr':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:446: warning: assignment makes pointer from integer without a cast
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'alloc_counter_tr':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:461: warning: assignment makes pointer from integer without a cast
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'add_res_range':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:521: warning: assignment makes pointer from integer without a cast
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'mac_add_to_slave':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:1193: warning: assignment makes pointer from integer without a cast
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'add_mcg_res':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:2521: warning: assignment makes pointer from integer without a cast
make[5]: *** [drivers/net/ethernet/mellanox/mlx4/resource_tracker.o] Error 1
make[4]: *** [drivers/net/ethernet/mellanox/mlx4] Error 2
make[3]: *** [drivers/net/ethernet/mellanox] Error 2
make[2]: *** [drivers/net/ethernet] Error 2
make[1]: *** [drivers/net] Error 2
make: *** [drivers] Error 2
Signed-off-by: Axel Lin <axel.lin@gmail.com>
---
.../net/ethernet/mellanox/mlx4/resource_tracker.c | 1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index b41762d..ed20751 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -38,6 +38,7 @@
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/io.h>
+#include <linux/slab.h>
#include <linux/mlx4/cmd.h>
#include <linux/mlx4/qp.h>
--
1.7.5.4
^ permalink raw reply related
* Re: [PATCH 6/6] SUNRPC: split SUNPRC PipeFS dentry and private pipe data creation
From: Stanislav Kinsbursky @ 2011-12-26 10:45 UTC (permalink / raw)
To: Trond Myklebust
Cc: linux-nfs@vger.kernel.org, Pavel Emelianov, neilb@suse.de,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
James Bottomley, bfields@fieldses.org, davem@davemloft.net,
devel@openvz.org
In-Reply-To: <1324819019.5195.4.camel@lade.trondhjem.org>
25.12.2011 17:16, Trond Myklebust пишет:
>> @@ -387,7 +397,9 @@ nfs_idmap_delete(struct nfs_client *clp)
>> >
>> > if (!idmap)
>> > return;
>> > - rpc_unlink(idmap->idmap_dentry);
>> > + if (idmap->idmap_pipe->dentry)
> Shouldn't this be a test for IS_ERR(idmap->idmap_pipe->dentry)?
>
Nope. This dentry is either NULL or valid pointer.
Will resend rebased version soon.
--
Best regards,
Stanislav Kinsbursky
^ permalink raw reply
* [PATCH v2 4/6] SUNPRC: cleanup RPC PipeFS pipes upcall interface
From: Stanislav Kinsbursky @ 2011-12-26 12:43 UTC (permalink / raw)
To: Trond.Myklebust
Cc: linux-nfs, xemul, neilb, netdev, linux-kernel, jbottomley,
bfields, davem, devel
In-Reply-To: <20111226114042.13743.73804.stgit@localhost6.localdomain6>
RPC pipe upcall doesn't requires only private pipe data. Thus RPC inode
references in this code can be removed.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
---
fs/nfs/blocklayout/blocklayoutdev.c | 2 +-
fs/nfs/blocklayout/blocklayoutdm.c | 2 +-
fs/nfs/idmap.c | 4 ++--
include/linux/sunrpc/rpc_pipe_fs.h | 2 +-
net/sunrpc/auth_gss/auth_gss.c | 3 +--
net/sunrpc/rpc_pipe.c | 3 +--
6 files changed, 7 insertions(+), 9 deletions(-)
diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c
index d08ba91..8101919 100644
--- a/fs/nfs/blocklayout/blocklayoutdev.c
+++ b/fs/nfs/blocklayout/blocklayoutdev.c
@@ -146,7 +146,7 @@ nfs4_blk_decode_device(struct nfs_server *server,
dprintk("%s CALLING USERSPACE DAEMON\n", __func__);
add_wait_queue(&bl_wq, &wq);
- rc = rpc_queue_upcall(bl_device_pipe->d_inode, &msg);
+ rc = rpc_queue_upcall(RPC_I(bl_device_pipe->d_inode)->pipe, &msg);
if (rc < 0) {
remove_wait_queue(&bl_wq, &wq);
rv = ERR_PTR(rc);
diff --git a/fs/nfs/blocklayout/blocklayoutdm.c b/fs/nfs/blocklayout/blocklayoutdm.c
index d055c75..3c38244 100644
--- a/fs/nfs/blocklayout/blocklayoutdm.c
+++ b/fs/nfs/blocklayout/blocklayoutdm.c
@@ -66,7 +66,7 @@ static void dev_remove(dev_t dev)
msg.len = sizeof(bl_msg) + bl_msg.totallen;
add_wait_queue(&bl_wq, &wq);
- if (rpc_queue_upcall(bl_device_pipe->d_inode, &msg) < 0) {
+ if (rpc_queue_upcall(RPC_I(bl_device_pipe->d_inode)->pipe, &msg) < 0) {
remove_wait_queue(&bl_wq, &wq);
goto out;
}
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index 47d1c6f..4194129 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -506,7 +506,7 @@ nfs_idmap_id(struct idmap *idmap, struct idmap_hashtable *h,
msg.len = sizeof(*im);
add_wait_queue(&idmap->idmap_wq, &wq);
- if (rpc_queue_upcall(idmap->idmap_dentry->d_inode, &msg) < 0) {
+ if (rpc_queue_upcall(RPC_I(idmap->idmap_dentry->d_inode)->pipe, &msg) < 0) {
remove_wait_queue(&idmap->idmap_wq, &wq);
goto out;
}
@@ -567,7 +567,7 @@ nfs_idmap_name(struct idmap *idmap, struct idmap_hashtable *h,
add_wait_queue(&idmap->idmap_wq, &wq);
- if (rpc_queue_upcall(idmap->idmap_dentry->d_inode, &msg) < 0) {
+ if (rpc_queue_upcall(RPC_I(idmap->idmap_dentry->d_inode)->pipe, &msg) < 0) {
remove_wait_queue(&idmap->idmap_wq, &wq);
goto out;
}
diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h
index c2fa330..ad78bea 100644
--- a/include/linux/sunrpc/rpc_pipe_fs.h
+++ b/include/linux/sunrpc/rpc_pipe_fs.h
@@ -64,7 +64,7 @@ extern void rpc_put_sb_net(const struct net *net);
extern ssize_t rpc_pipe_generic_upcall(struct file *, struct rpc_pipe_msg *,
char __user *, size_t);
-extern int rpc_queue_upcall(struct inode *, struct rpc_pipe_msg *);
+extern int rpc_queue_upcall(struct rpc_pipe *, struct rpc_pipe_msg *);
struct rpc_clnt;
extern struct dentry *rpc_create_client_dir(struct dentry *, struct qstr *, struct rpc_clnt *);
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 89fc914..5ba678d 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -475,8 +475,7 @@ gss_setup_upcall(struct rpc_clnt *clnt, struct gss_auth *gss_auth, struct rpc_cr
return gss_new;
gss_msg = gss_add_msg(gss_new);
if (gss_msg == gss_new) {
- struct inode *inode = &gss_new->inode->vfs_inode;
- int res = rpc_queue_upcall(inode, &gss_new->msg);
+ int res = rpc_queue_upcall(gss_new->inode->pipe, &gss_new->msg);
if (res) {
gss_unhash_msg(gss_new);
gss_msg = ERR_PTR(res);
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index cecdc1f..dc24af3 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -130,9 +130,8 @@ EXPORT_SYMBOL_GPL(rpc_pipe_generic_upcall);
* initialize the fields of @msg (other than @msg->list) appropriately.
*/
int
-rpc_queue_upcall(struct inode *inode, struct rpc_pipe_msg *msg)
+rpc_queue_upcall(struct rpc_pipe *pipe, struct rpc_pipe_msg *msg)
{
- struct rpc_pipe *pipe = RPC_I(inode)->pipe;
int res = -EPIPE;
spin_lock(&pipe->lock);
^ permalink raw reply related
* Re: [PATCH v2 0/6] SUNPRC: cleanup PipeFS for network-namespace-aware users
From: Stanislav Kinsbursky @ 2011-12-26 11:50 UTC (permalink / raw)
To: Trond.Myklebust@netapp.com
Cc: linux-nfs@vger.kernel.org, Pavel Emelianov, neilb@suse.de,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
James Bottomley, bfields@fieldses.org, davem@davemloft.net,
devel@openvz.org
In-Reply-To: <20111226114042.13743.73804.stgit@localhost6.localdomain6>
Hello, Trond.
This patch set depend on
"SUNRPC: initial part of making pipefs work in net ns"
and
"SUNRPC: remove non-exclusive pipe creation from RPC pipefs"
I'm not sure about did you applied them already or not, so I've rebased and
resent them too.
--
Best regards,
Stanislav Kinsbursky
^ permalink raw reply
* Re: [PATCH 1/2] bna: Added flash sub-module and ethtool eeprom entry points.
From: Jan Ceuleers @ 2011-12-26 12:02 UTC (permalink / raw)
To: Ben Hutchings
Cc: Krishna Gudipati, 'davem@davemloft.net',
'netdev@vger.kernel.org', Adapter Linux Open SRC Team,
Rasesh Mody
In-Reply-To: <1324721314.3860.11.camel@deadeye>
On 12/24/2011 11:08 AM, Ben Hutchings wrote:
> I asked how long a single call would take, because the RTNL lock will be
> held for this time. Presumably it doesn't take very long to write a 4K
> chunk, so this shouldn't be a problem.
>
461K is around 115 4K blocks. If these take around 3 minutes to flash
then that's about 1.5s per 4K block.
Is it OK to hold the RTNL lock for that length of time?
^ permalink raw reply
* Re: [PATCH] SUNRPC: make SUNPRC clients list per network namespace context
From: Stanislav Kinsbursky @ 2011-12-26 12:25 UTC (permalink / raw)
To: Trond Myklebust
Cc: linux-nfs@vger.kernel.org, Pavel Emelianov, neilb@suse.de,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
James Bottomley, bfields@fieldses.org, davem@davemloft.net,
devel@openvz.org
In-Reply-To: <1324817295.5195.0.camel@lade.trondhjem.org>
25.12.2011 16:48, Trond Myklebust пишет:
> On Wed, 2011-12-14 at 12:19 +0300, Stanislav Kinsbursky wrote:
>> This patch moves static SUNRPC clients list and it's lock to sunrpc_net
>> structure.
>> Currently this list is used only for debug purposes. But later it will be used
>> also for selecting clients by networks namespace on PipeFS mount/umount events.
>> Per-network namespace lists will make this faster and simplier.
>>
>> Note: client list is taken from "init_net" network namespace context in
>> rpc_show_tasks(). This will be changed with making SUNRPC sysctl's per network
>> namespace context.
>>
>> Signed-off-by: Stanislav Kinsbursky<skinsbursky@parallels.com>
>
> This doesn't seem to integrate with any of your patch series, and
> conflicts with everything that touches netns.h, for instance...
>
Yep, you are right. Currently this path doesn't apply, if you'll try to apply
patches in the same order I've sent them.
This is caused by different development branches.
Anyway, most of the patches will not apply to current tree.
And I'll be glad to rebase and resent them on request.
--
Best regards,
Stanislav Kinsbursky
^ permalink raw reply
* [PATCH net-next V2 1/2] igb: add PTP Hardware Clock code
From: Richard Cochran @ 2011-12-26 12:26 UTC (permalink / raw)
To: netdev
Cc: e1000-devel, John Ronciak, John Stultz, Jacob Keller,
Thomas Gleixner
In-Reply-To: <cover.1324901880.git.richardcochran@gmail.com>
This patch adds a source file implementing a PHC. Only the basic
clock operations have been implemented, although the hardware
would offer some ancillary functions. The code is fairly self
contained and is not yet used in the main igb driver.
Every timestamp and clock read operation must consult the overflow
counter to form a correct time value. Access to the counter is
protected by a spin lock, and this would be sufficient, assuming that
the time values are monotonic.
However, this assumption does not hold in general. Consider the
following sequence.
1. Hardware latches a receive timestamp (just before counter overflow).
2. User calls clock_gettime() (just after counter overflow).
3. User takes lock, detects 1-0 transition, and increments overflow count.
4. Driver takes lock, incorrectly combines overflow count with timestamp.
A very similar race condition exists between two nearly simultaneous
hardware timestamps.
The implementation detects this race by checking the two most
significant bits for a transition from 11b to 00b. When this pattern
is detected, the code uses the previous value of the overflow count.
The two most significant bits divide the overflow period into four
regions, and so the watchdog timeout is set to sample the counter at
just over four times per period.
Signed-off-by: Richard Cochran <richardcochran@gmail.com>
---
drivers/net/ethernet/intel/igb/igb.h | 8 +
drivers/net/ethernet/intel/igb/igb_ptp.c | 420 ++++++++++++++++++++++++++++++
2 files changed, 428 insertions(+), 0 deletions(-)
create mode 100644 drivers/net/ethernet/intel/igb/igb_ptp.c
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index c69feeb..f30458d 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -37,6 +37,7 @@
#include <linux/clocksource.h>
#include <linux/timecompare.h>
#include <linux/net_tstamp.h>
+#include <linux/ptp_clock_kernel.h>
#include <linux/bitops.h>
#include <linux/if_vlan.h>
@@ -364,6 +365,13 @@ struct igb_adapter {
u32 wvbr;
int node;
u32 *shadow_vfta;
+
+ struct ptp_clock *ptp_clock;
+ struct ptp_clock_info caps;
+ struct delayed_work overflow_work;
+ spinlock_t tmreg_lock;
+ u32 overflow_counter;
+ unsigned int last_msb;
};
#define IGB_FLAG_HAS_MSI (1 << 0)
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
new file mode 100644
index 0000000..cef31cb
--- /dev/null
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -0,0 +1,420 @@
+/*
+ * PTP Hardware Clock (PHC) driver for the Intel 82576 and 82580
+ *
+ * Copyright (C) 2011 Richard Cochran <richardcochran@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+#include <linux/device.h>
+#include <linux/pci.h>
+
+#include "igb.h"
+
+#define INCVALUE_MASK 0x7fffffff
+#define ISGN 0x80000000
+
+/*
+ * Neither the 82576 nor the 82580 offer registers wide enough to hold
+ * nanoseconds time values for very long. For the 82580, SYSTIM always
+ * counts nanoseconds, but the upper 24 bits are not availible. The
+ * frequency is adjusted by changing the 32 bit fractional nanoseconds
+ * register, TIMINCA.
+ *
+ * For the 82576, the SYSTIM register time unit is affect by the
+ * choice of the 24 bit TININCA:IV (incvalue) field. Five bits of this
+ * field are needed to provide the nominal 16 nanosecond period,
+ * leaving 19 bits for fractional nanoseconds.
+ *
+ *
+ * SYSTIMH SYSTIML
+ * +--------------+ +---+---+------+
+ * 82576 | 32 | | 8 | 5 | 19 |
+ * +--------------+ +---+---+------+
+ * \________ 45 bits _______/ fract
+ *
+ * +----------+---+ +--------------+
+ * 82580 | 24 | 8 | | 32 |
+ * +----------+---+ +--------------+
+ * reserved \______ 40 bits _____/
+ *
+ *
+ * The 45 bit 82576 SYSTIM overflows every
+ * 2^45 * 10^-9 / 3600 = 9.77 hours.
+ *
+ * The 40 bit 82580 SYSTIM overflows every
+ * 2^40 * 10^-9 / 60 = 18.3 minutes.
+ *
+ * We implement a 32 bit overflow counter in software to hold the
+ * missing 19 or 24 bits, for a combined virtual nanosecond time
+ * register of 64 bits.
+ */
+
+#define IGB_OVERFLOW_PERIOD (HZ * 60 * 4)
+#define INCPERIOD_82576 (1 << E1000_TIMINCA_16NS_SHIFT)
+#define INCVALUE_82576_MASK ((1 << E1000_TIMINCA_16NS_SHIFT) - 1)
+#define INCVALUE_82576 (16 << IGB_82576_TSYNC_SHIFT)
+#define OFL_SHIFT_82580 40
+#define OFL_SHIFT_82576 45
+#define NS_SHIFT_82576 IGB_82576_TSYNC_SHIFT
+
+/*
+ * Overflow counter for the SYSTIM register.
+ */
+
+static u64 igb_overflow_get(struct igb_adapter *igb, u64 low, unsigned int nbit)
+{
+ unsigned int msb_set = (low >> (nbit - 2)) & 0x3;
+
+ if (msb_set == 0x3 && igb->last_msb == 0x0) {
+ /*
+ * This time stamp was taken before the last overflow,
+ * but it lost the race to read the overflow counter.
+ * Therefore, we just use the previous overflow value.
+ */
+ low |= ((u64) igb->overflow_counter - 1ULL) << nbit;
+ return low;
+ }
+
+ /*
+ * Test for a one to zero transition of the most significant
+ * bit, and increment the overflow counter.
+ */
+ if ((igb->last_msb & 0x2) && !(msb_set & 0x2))
+ igb->overflow_counter++;
+
+ igb->last_msb = msb_set;
+
+ low |= ((u64) igb->overflow_counter) << nbit;
+
+ return low;
+}
+
+static void igb_overflow_set(struct igb_adapter *igb, u64 ns, unsigned int nbit)
+{
+ igb->overflow_counter = ns >> nbit;
+ igb->last_msb = (ns >> (nbit - 2)) & 0x3;
+}
+
+/*
+ * SYSTIM / overflow access functions for the 82576
+ */
+
+static u64 igb_82576_systim_read(struct igb_adapter *igb)
+{
+ u64 ns;
+ u32 lo, hi;
+ struct e1000_hw *hw = &igb->hw;
+
+ lo = rd32(E1000_SYSTIML);
+ hi = rd32(E1000_SYSTIMH);
+
+ ns = ((u64) hi) << 32;
+ ns |= lo;
+ ns >>= NS_SHIFT_82576;
+
+ ns = igb_overflow_get(igb, ns, OFL_SHIFT_82576);
+
+ return ns;
+}
+
+static void igb_82576_systim_write(struct igb_adapter *igb, u64 ns)
+{
+ u32 hi, lo;
+ struct e1000_hw *hw = &igb->hw;
+
+ hi = (ns >> 13) & 0xffffffff;
+ lo = (ns & 0x1fff) << NS_SHIFT_82576;
+
+ wr32(E1000_SYSTIML, lo);
+ wr32(E1000_SYSTIMH, hi);
+
+ igb_overflow_set(igb, ns, OFL_SHIFT_82576);
+}
+
+/*
+ * SYSTIM / overflow access functions for the 82580
+ */
+
+static u64 igb_82580_systim_read(struct igb_adapter *igb)
+{
+ u64 ns;
+ u32 lo, hi, jk;
+ struct e1000_hw *hw = &igb->hw;
+
+ jk = rd32(E1000_SYSTIMR);
+ lo = rd32(E1000_SYSTIML);
+ hi = rd32(E1000_SYSTIMH);
+
+ ns = ((u64) hi) << 32;
+ ns |= lo;
+
+ ns = igb_overflow_get(igb, ns, OFL_SHIFT_82580);
+
+ return ns;
+}
+
+static void igb_82580_systim_write(struct igb_adapter *igb, u64 ns)
+{
+ u32 hi, lo;
+ struct e1000_hw *hw = &igb->hw;
+
+ hi = ns >> 32;
+ lo = ns & 0xffffffff;
+
+ wr32(E1000_SYSTIMR, 0);
+ wr32(E1000_SYSTIML, lo);
+ wr32(E1000_SYSTIMH, hi & 0xff);
+
+ igb_overflow_set(igb, ns, OFL_SHIFT_82580);
+}
+
+/*
+ * SYSTIM / overflow register access functions
+ * Callers must hold tmreg_lock.
+ */
+
+static u64 igb_systim_read(struct igb_adapter *igb)
+{
+ switch (igb->hw.mac.type) {
+ case e1000_i350:
+ case e1000_82580:
+ return igb_82580_systim_read(igb);
+ case e1000_82576:
+ return igb_82576_systim_read(igb);
+ default:
+ return 0;
+ }
+}
+
+static void igb_systim_write(struct igb_adapter *igb, u64 ns)
+{
+ switch (igb->hw.mac.type) {
+ case e1000_i350:
+ case e1000_82580:
+ igb_82580_systim_write(igb, ns);
+ break;
+ case e1000_82576:
+ igb_82576_systim_write(igb, ns);
+ break;
+ default:
+ break;
+ }
+}
+
+/*
+ * PTP clock operations
+ */
+
+static int ptp_82576_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
+{
+ u64 rate;
+ u32 incvalue;
+ int neg_adj = 0;
+ struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps);
+ struct e1000_hw *hw = &igb->hw;
+
+ if (ppb < 0) {
+ neg_adj = 1;
+ ppb = -ppb;
+ }
+ rate = ppb;
+ rate <<= 14;
+ rate = div_u64(rate, 1953125);
+
+ incvalue = 16 << IGB_82576_TSYNC_SHIFT;
+
+ if (neg_adj)
+ incvalue -= rate;
+ else
+ incvalue += rate;
+
+ wr32(E1000_TIMINCA, INCPERIOD_82576 | (incvalue & INCVALUE_82576_MASK));
+
+ return 0;
+}
+
+static int ptp_82580_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
+{
+ u64 rate;
+ u32 inca;
+ int neg_adj = 0;
+ struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps);
+ struct e1000_hw *hw = &igb->hw;
+
+ if (ppb < 0) {
+ neg_adj = 1;
+ ppb = -ppb;
+ }
+ rate = ppb;
+ rate <<= 26;
+ rate = div_u64(rate, 1953125);
+
+ inca = rate & INCVALUE_MASK;
+ if (neg_adj)
+ inca |= ISGN;
+
+ wr32(E1000_TIMINCA, inca);
+
+ return 0;
+}
+
+static int igb_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+ s64 now;
+ unsigned long flags;
+ struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps);
+
+ spin_lock_irqsave(&igb->tmreg_lock, flags);
+
+ now = igb_systim_read(igb);
+ now += delta;
+ igb_systim_write(igb, now);
+
+ spin_unlock_irqrestore(&igb->tmreg_lock, flags);
+
+ return 0;
+}
+
+static int igb_gettime(struct ptp_clock_info *ptp, struct timespec *ts)
+{
+ u64 ns;
+ u32 remainder;
+ unsigned long flags;
+ struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps);
+
+ spin_lock_irqsave(&igb->tmreg_lock, flags);
+
+ ns = igb_systim_read(igb);
+
+ spin_unlock_irqrestore(&igb->tmreg_lock, flags);
+
+ ts->tv_sec = div_u64_rem(ns, 1000000000, &remainder);
+ ts->tv_nsec = remainder;
+
+ return 0;
+}
+
+static int igb_settime(struct ptp_clock_info *ptp, const struct timespec *ts)
+{
+ u64 ns;
+ unsigned long flags;
+ struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps);
+
+ ns = ts->tv_sec * 1000000000ULL;
+ ns += ts->tv_nsec;
+
+ spin_lock_irqsave(&igb->tmreg_lock, flags);
+
+ igb_systim_write(igb, ns);
+
+ spin_unlock_irqrestore(&igb->tmreg_lock, flags);
+
+ return 0;
+}
+
+static int ptp_82576_enable(struct ptp_clock_info *ptp,
+ struct ptp_clock_request *rq, int on)
+{
+ return -EOPNOTSUPP;
+}
+
+static int ptp_82580_enable(struct ptp_clock_info *ptp,
+ struct ptp_clock_request *rq, int on)
+{
+ return -EOPNOTSUPP;
+}
+
+static void igb_overflow_check(struct work_struct *work)
+{
+ struct timespec ts;
+ struct igb_adapter *igb =
+ container_of(work, struct igb_adapter, overflow_work.work);
+
+ igb_gettime(&igb->caps, &ts);
+
+ pr_debug("igb overflow check at %ld.%09lu\n", ts.tv_sec, ts.tv_nsec);
+
+ schedule_delayed_work(&igb->overflow_work, IGB_OVERFLOW_PERIOD);
+}
+
+void igb_ptp_init(struct igb_adapter *adapter)
+{
+ struct e1000_hw *hw = &adapter->hw;
+
+ switch (hw->mac.type) {
+ case e1000_i350:
+ case e1000_82580:
+ adapter->caps.owner = THIS_MODULE;
+ strcpy(adapter->caps.name, "igb-82580");
+ adapter->caps.max_adj = 62499999;
+ adapter->caps.n_ext_ts = 0;
+ adapter->caps.pps = 0;
+ adapter->caps.adjfreq = ptp_82580_adjfreq;
+ adapter->caps.adjtime = igb_adjtime;
+ adapter->caps.gettime = igb_gettime;
+ adapter->caps.settime = igb_settime;
+ adapter->caps.enable = ptp_82580_enable;
+ /* Enable the timer functions by clearing bit 31. */
+ wr32(E1000_TSAUXC, 0x0);
+ break;
+
+ case e1000_82576:
+ adapter->caps.owner = THIS_MODULE;
+ strcpy(adapter->caps.name, "igb-82576");
+ adapter->caps.max_adj = 1000000000;
+ adapter->caps.n_ext_ts = 0;
+ adapter->caps.pps = 0;
+ adapter->caps.adjfreq = ptp_82576_adjfreq;
+ adapter->caps.adjtime = igb_adjtime;
+ adapter->caps.gettime = igb_gettime;
+ adapter->caps.settime = igb_settime;
+ adapter->caps.enable = ptp_82576_enable;
+ /* Dial the nominal frequency. */
+ wr32(E1000_TIMINCA, INCPERIOD_82576 | INCVALUE_82576);
+ break;
+
+ default:
+ adapter->ptp_clock = NULL;
+ return;
+ }
+
+ wrfl();
+
+ INIT_DELAYED_WORK(&adapter->overflow_work, igb_overflow_check);
+
+ spin_lock_init(&adapter->tmreg_lock);
+
+ adapter->ptp_clock = ptp_clock_register(&adapter->caps);
+ if (IS_ERR(adapter->ptp_clock)) {
+ adapter->ptp_clock = NULL;
+ dev_err(&adapter->pdev->dev, "ptp_clock_register failed\n");
+ return;
+ }
+
+ schedule_delayed_work(&adapter->overflow_work, IGB_OVERFLOW_PERIOD);
+
+ dev_info(&adapter->pdev->dev, "added PHC on %s\n",
+ adapter->netdev->name);
+}
+
+void igb_ptp_remove(struct igb_adapter *adapter)
+{
+ if (adapter->ptp_clock) {
+ cancel_delayed_work_sync(&adapter->overflow_work);
+ ptp_clock_unregister(adapter->ptp_clock);
+ dev_info(&adapter->pdev->dev, "removed PHC on %s\n",
+ adapter->netdev->name);
+ }
+}
--
1.7.2.5
------------------------------------------------------------------------------
Write once. Port to many.
Get the SDK and tools to simplify cross-platform app development. Create
new or port existing apps to sell to consumers worldwide. Explore the
Intel AppUpSM program developer opportunity. appdeveloper.intel.com/join
http://p.sf.net/sfu/intel-appdev
_______________________________________________
E1000-devel mailing list
E1000-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/e1000-devel
To learn more about Intel® Ethernet, visit http://communities.intel.com/community/wired
^ 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