* [patch v4 08/12] IPVS: Add persistence engine data to /proc/net/ip_vs_conn
From: Simon Horman @ 2010-10-04 9:04 UTC (permalink / raw)
To: lvs-devel, netdev, netfilter, netfilter-devel
Cc: Jan Engelhardt, Stephen Hemminger, Wensong Zhang,
Julian Anastasov, Patrick McHardy
In-Reply-To: <20101004090352.966809749@akiko.akashicho.tokyo.vergenet.net>
[-- Attachment #1: 0008-IPVS-Add-persistence-engine-data-to-proc-net-ip_vs_c.patch --]
[-- Type: text/plain, Size: 3131 bytes --]
This shouldn't break compatibility with userspace as the new data
is at the end of the line.
I have confirmed that this doesn't break ipvsadm, the main (only?)
user-space user of this data.
Signed-off-by: Simon Horman <horms@verge.net.au>
Acked-by: Julian Anastasov <ja@ssi.bg>
---
* Jan Engelhardt suggested using netlink to do this, but it seems like
overkill to me. I'm willing to be convinced otherwise.
v2
* Trivial rediff
v3
* As suggested by Julian Anastasov
- ip_vs_conn_seq_show(): cp->dest is optional
so test for its presence accordingly
- Re-diff for addition of inverse parameter to ip_vs_conn_hashkey_param()
Index: lvs-test-2.6/include/net/ip_vs.h
===================================================================
--- lvs-test-2.6.orig/include/net/ip_vs.h 2010-10-02 10:55:43.000000000 +0900
+++ lvs-test-2.6/include/net/ip_vs.h 2010-10-02 10:55:49.000000000 +0900
@@ -572,6 +572,7 @@ struct ip_vs_pe {
struct ip_vs_conn *ct);
u32 (*hashkey_raw)(const struct ip_vs_conn_param *p, u32 initval,
bool inverse);
+ int (*show_pe_data)(const struct ip_vs_conn *cp, char *buf);
};
/*
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_conn.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_conn.c 2010-10-02 10:55:43.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_conn.c 2010-10-02 10:57:00.000000000 +0900
@@ -950,30 +950,45 @@ static int ip_vs_conn_seq_show(struct se
if (v == SEQ_START_TOKEN)
seq_puts(seq,
- "Pro FromIP FPrt ToIP TPrt DestIP DPrt State Expires\n");
+ "Pro FromIP FPrt ToIP TPrt DestIP DPrt State Expires PEName PEData\n");
else {
const struct ip_vs_conn *cp = v;
+ char pe_data[IP_VS_PENAME_MAXLEN + IP_VS_PEDATA_MAXLEN + 3];
+ size_t len = 0;
+
+ if (cp->dest && cp->dest->svc->pe &&
+ cp->dest->svc->pe->show_pe_data) {
+ pe_data[0] = ' ';
+ len = strlen(cp->dest->svc->pe->name);
+ memcpy(pe_data + 1, cp->dest->svc->pe->name, len);
+ pe_data[len + 1] = ' ';
+ len += 2;
+ len += cp->dest->svc->pe->show_pe_data(cp,
+ pe_data + len);
+ }
+ pe_data[len] = '\0';
#ifdef CONFIG_IP_VS_IPV6
if (cp->af == AF_INET6)
- seq_printf(seq, "%-3s %pI6 %04X %pI6 %04X %pI6 %04X %-11s %7lu\n",
+ seq_printf(seq, "%-3s %pI6 %04X %pI6 %04X "
+ "%pI6 %04X %-11s %7lu%s\n",
ip_vs_proto_name(cp->protocol),
&cp->caddr.in6, ntohs(cp->cport),
&cp->vaddr.in6, ntohs(cp->vport),
&cp->daddr.in6, ntohs(cp->dport),
ip_vs_state_name(cp->protocol, cp->state),
- (cp->timer.expires-jiffies)/HZ);
+ (cp->timer.expires-jiffies)/HZ, pe_data);
else
#endif
seq_printf(seq,
"%-3s %08X %04X %08X %04X"
- " %08X %04X %-11s %7lu\n",
+ " %08X %04X %-11s %7lu%s\n",
ip_vs_proto_name(cp->protocol),
ntohl(cp->caddr.ip), ntohs(cp->cport),
ntohl(cp->vaddr.ip), ntohs(cp->vport),
ntohl(cp->daddr.ip), ntohs(cp->dport),
ip_vs_state_name(cp->protocol, cp->state),
- (cp->timer.expires-jiffies)/HZ);
+ (cp->timer.expires-jiffies)/HZ, pe_data);
}
return 0;
}
^ permalink raw reply
* [patch v4 06/12] IPVS: ip_vs_{un,}bind_scheduler NULL arguments
From: Simon Horman @ 2010-10-04 9:03 UTC (permalink / raw)
To: lvs-devel, netdev, netfilter, netfilter-devel
Cc: Jan Engelhardt, Stephen Hemminger, Wensong Zhang,
Julian Anastasov, Patrick McHardy
In-Reply-To: <20101004090352.966809749@akiko.akashicho.tokyo.vergenet.net>
[-- Attachment #1: 0006-IPVS-ip_vs_-un-bind_scheduler-NULL-arguments.patch --]
[-- Type: text/plain, Size: 2011 bytes --]
In general NULL arguments aren't passed by the few callers that exist,
so don't test for them.
The exception is to make passing NULL to ip_vs_unbind_scheduler() a noop.
Signed-off-by: Simon Horman <horms@verge.net.au>
Acked-by: Julian Anastasov <ja@ssi.bg>
---
v2
* Trivial rediff
v3
* Trivial rediff
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_ctl.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_ctl.c 2010-10-02 10:15:45.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_ctl.c 2010-10-02 10:15:47.000000000 +0900
@@ -1206,8 +1206,7 @@ ip_vs_add_service(struct ip_vs_service_u
out_err:
if (svc != NULL) {
- if (svc->scheduler)
- ip_vs_unbind_scheduler(svc);
+ ip_vs_unbind_scheduler(svc);
if (svc->inc) {
local_bh_disable();
ip_vs_app_inc_put(svc->inc);
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_sched.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_sched.c 2010-10-02 10:15:45.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_sched.c 2010-10-02 10:15:47.000000000 +0900
@@ -46,15 +46,6 @@ int ip_vs_bind_scheduler(struct ip_vs_se
{
int ret;
- if (svc == NULL) {
- pr_err("%s(): svc arg NULL\n", __func__);
- return -EINVAL;
- }
- if (scheduler == NULL) {
- pr_err("%s(): scheduler arg NULL\n", __func__);
- return -EINVAL;
- }
-
svc->scheduler = scheduler;
if (scheduler->init_service) {
@@ -74,18 +65,10 @@ int ip_vs_bind_scheduler(struct ip_vs_se
*/
int ip_vs_unbind_scheduler(struct ip_vs_service *svc)
{
- struct ip_vs_scheduler *sched;
+ struct ip_vs_scheduler *sched = svc->scheduler;
- if (svc == NULL) {
- pr_err("%s(): svc arg NULL\n", __func__);
- return -EINVAL;
- }
-
- sched = svc->scheduler;
- if (sched == NULL) {
- pr_err("%s(): svc isn't bound\n", __func__);
- return -EINVAL;
- }
+ if (!sched)
+ return 0;
if (sched->done_service) {
if (sched->done_service(svc) != 0) {
^ permalink raw reply
* [patch v4 02/12] netfilter: nf_conntrack_sip: Add callid parser
From: Simon Horman @ 2010-10-04 9:03 UTC (permalink / raw)
To: lvs-devel, netdev, netfilter, netfilter-devel
Cc: Jan Engelhardt, Stephen Hemminger, Wensong Zhang,
Julian Anastasov, Patrick McHardy
In-Reply-To: <20101004090352.966809749@akiko.akashicho.tokyo.vergenet.net>
[-- Attachment #1: 0002-netfilter-nf_conntrack_sip-Add-callid-parser.patch --]
[-- Type: text/plain, Size: 2483 bytes --]
Signed-off-by: Simon Horman <horms@verge.net.au>
Acked-by: Julian Anastasov <ja@ssi.bg>
---
The motivation for this is for it to be used by LVS as per
subsequent patches.
* Patrick McHardy suggested changing word_len to check for the
next newline or whitespace. But I believe this is incorrect.
For example '#' would be permitted but it is invalid
in a word according to RFC3261.
diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h
index ff8cfbc..0ce91d5 100644
--- a/include/linux/netfilter/nf_conntrack_sip.h
+++ b/include/linux/netfilter/nf_conntrack_sip.h
@@ -89,6 +89,7 @@ enum sip_header_types {
SIP_HDR_VIA_TCP,
SIP_HDR_EXPIRES,
SIP_HDR_CONTENT_LENGTH,
+ SIP_HDR_CALL_ID,
};
enum sdp_header_types {
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 2fd1ea2..715ce54 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -130,6 +130,44 @@ static int digits_len(const struct nf_conn *ct, const char *dptr,
return len;
}
+static int iswordc(const char c)
+{
+ if (isalnum(c) || c == '!' || c == '"' || c == '%' ||
+ (c >= '(' && c <= '/') || c == ':' || c == '<' || c == '>' ||
+ c == '?' || (c >= '[' && c <= ']') || c == '_' || c == '`' ||
+ c == '{' || c == '}' || c == '~')
+ return 1;
+ return 0;
+}
+
+static int word_len(const char *dptr, const char *limit)
+{
+ int len = 0;
+ while (dptr < limit && iswordc(*dptr)) {
+ dptr++;
+ len++;
+ }
+ return len;
+}
+
+static int callid_len(const struct nf_conn *ct, const char *dptr,
+ const char *limit, int *shift)
+{
+ int len, domain_len;
+
+ len = word_len(dptr, limit);
+ dptr += len;
+ if (!len || dptr == limit || *dptr != '@')
+ return len;
+ dptr++;
+ len++;
+
+ domain_len = word_len(dptr, limit);
+ if (!domain_len)
+ return 0;
+ return len + domain_len;
+}
+
/* get media type + port length */
static int media_len(const struct nf_conn *ct, const char *dptr,
const char *limit, int *shift)
@@ -299,6 +337,7 @@ static const struct sip_header ct_sip_hdrs[] = {
[SIP_HDR_VIA_TCP] = SIP_HDR("Via", "v", "TCP ", epaddr_len),
[SIP_HDR_EXPIRES] = SIP_HDR("Expires", NULL, NULL, digits_len),
[SIP_HDR_CONTENT_LENGTH] = SIP_HDR("Content-Length", "l", NULL, digits_len),
+ [SIP_HDR_CALL_ID] = SIP_HDR("Call-Id", "i", NULL, callid_len),
};
static const char *sip_follow_continuation(const char *dptr, const char *limit)
--
1.7.1
^ permalink raw reply related
* Re: [PATCH] sysctl: fix min/max handling in __do_proc_doulongvec_minmax()
From: Eric Dumazet @ 2010-10-04 9:04 UTC (permalink / raw)
To: Robin Holt
Cc: Andrew Morton, linux-kernel, Willy Tarreau, David S. Miller,
netdev, James Morris, Hideaki YOSHIFUJI, Pekka Savola (ipv6),
Patrick McHardy, Alexey Kuznetsov
In-Reply-To: <20101004085913.GR14068@sgi.com>
Le lundi 04 octobre 2010 à 03:59 -0500, Robin Holt a écrit :
> On Sat, Oct 02, 2010 at 03:17:49PM +0200, Eric Dumazet wrote:
> > When proc_doulongvec_minmax() is used with an array of longs,
> > and no min/max check requested (.extra1 or .extra2 being NULL), we
> > dereference a NULL pointer for the second element of the array.
> >
> > Noticed while doing some changes in network stack for the "16TB problem"
> >
> > Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
> > ---
> > kernel/sysctl.c | 3 ++-
> > 1 file changed, 2 insertions(+), 1 deletion(-)
> >
> > diff --git a/kernel/sysctl.c b/kernel/sysctl.c
> > index f88552c..4fba86d 100644
> > --- a/kernel/sysctl.c
> > +++ b/kernel/sysctl.c
> > @@ -2500,7 +2500,8 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
> > break;
> > if (neg)
> > continue;
> > - if ((min && val < *min) || (max && val > *max))
> > + if ((table->extra1 && val < *min) ||
> > + (table->extra2 && val > *max))
>
> How about changing:
> for (; left && vleft--; i++, min++, max++, first=0) {
> into:
> for (; left && vleft--; i++, min = min ? min + 1 : NULL, max = max ? max + 1: NULL, first=0) {
>
> That would make min and max correct and reduce the chances somebody in
> the future overlooks the fact they are currently filled with garbage.
I prefer my solution, because the check is done only in the 'write'
case, while its done also for 'read' in your solution, not counting the
for (;;) is really ugly...
^ permalink raw reply
* [patch v4 12/12] IPVS: sip persistence engine
From: Simon Horman @ 2010-10-04 9:04 UTC (permalink / raw)
To: lvs-devel, netdev, netfilter, netfilter-devel
Cc: Jan Engelhardt, Stephen Hemminger, Wensong Zhang,
Julian Anastasov, Patrick McHardy
In-Reply-To: <20101004090352.966809749@akiko.akashicho.tokyo.vergenet.net>
[-- Attachment #1: 0012-IPVS-sip-persistence-engine.patch --]
[-- Type: text/plain, Size: 7221 bytes --]
Add the SIP callid as a key for persistence.
This allows multiple connections from the same IP address to be
differentiated on the basis of the callid.
When used in conjunction with the persistence mask, it allows connections
from different IP addresses to be aggregated on the basis of the callid.
It is envisaged that a persistence mask of 0.0.0.0 will be a useful
setting. That is, ignore the source IP address when checking for
persistence.
It is envisaged that this option will be used in conjunction with
one-packet scheduling.
This only works with UDP and cannot be made to work with TCP
within the current framework.
Signed-off-by: Simon Horman <horms@verge.net.au>
Acked-by: Julian Anastasov <ja@ssi.bg>
---
v1
* Use buf[] instead of poiter arithmetic in ip_vs_dbg_callid()
As suggested by Jan Engelhardt
v2
* Use GFP_ATOMIC for allocations inside of ip_vs_sip_fill_param()
which is called in an atomic context. This resolves the
"scheduling while atomic" problem.
* As noted by Julian Anastasov RFC 3261 section 8.1.1.4 says
"Call-IDs are case-sensitive and are simply compared byte-by-byte",
so may be memcmp should be used instead of strnicmp() in
ip_vs_sip_ct_match().
* Spelling fix in comment: persistance -> persistence
* Trivial rediff
v3
* Trivial whitespace fixes
* Update for addition of inverse parameter to ip_vs_conn_hashkey_param()
Index: lvs-test-2.6/net/netfilter/ipvs/Kconfig
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/Kconfig 2010-10-02 10:49:37.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/Kconfig 2010-10-02 10:50:16.000000000 +0900
@@ -256,4 +256,11 @@ config IP_VS_NFCT
connection state to be exported to the Netfilter framework
for filtering purposes.
+config IP_VS_PE_SIP
+ tristate "SIP persistence engine"
+ depends on IP_VS_PROTO_UDP
+ depends on NF_CONNTRACK_SIP
+ ---help---
+ Allow persistence based on the SIP Call-ID
+
endif # IP_VS
Index: lvs-test-2.6/net/netfilter/ipvs/Makefile
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/Makefile 2010-10-02 10:50:16.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/Makefile 2010-10-02 10:50:16.000000000 +0900
@@ -35,3 +35,6 @@ obj-$(CONFIG_IP_VS_NQ) += ip_vs_nq.o
# IPVS application helpers
obj-$(CONFIG_IP_VS_FTP) += ip_vs_ftp.o
+
+# IPVS connection template retrievers
+obj-$(CONFIG_IP_VS_PE_SIP) += ip_vs_pe_sip.o
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_pe_sip.c
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_pe_sip.c 2010-10-02 10:52:08.000000000 +0900
@@ -0,0 +1,167 @@
+#define KMSG_COMPONENT "IPVS"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+
+#include <net/ip_vs.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <linux/netfilter/nf_conntrack_sip.h>
+
+static const char *ip_vs_dbg_callid(char *buf, size_t buf_len,
+ const char *callid, size_t callid_len,
+ int *idx)
+{
+ size_t len = min(min(callid_len, (size_t)64), buf_len - *idx - 1);
+ memcpy(buf + *idx, callid, len);
+ buf[*idx+len] = '\0';
+ *idx += len + 1;
+ return buf + *idx - len;
+}
+
+#define IP_VS_DEBUG_CALLID(callid, len) \
+ ip_vs_dbg_callid(ip_vs_dbg_buf, sizeof(ip_vs_dbg_buf), \
+ callid, len, &ip_vs_dbg_idx)
+
+static int get_callid(const char *dptr, unsigned int dataoff,
+ unsigned int datalen,
+ unsigned int *matchoff, unsigned int *matchlen)
+{
+ /* Find callid */
+ while (1) {
+ int ret = ct_sip_get_header(NULL, dptr, dataoff, datalen,
+ SIP_HDR_CALL_ID, matchoff,
+ matchlen);
+ if (ret > 0)
+ break;
+ if (!ret)
+ return 0;
+ dataoff += *matchoff;
+ }
+
+ /* Empty callid is useless */
+ if (!*matchlen)
+ return -EINVAL;
+
+ /* Too large is useless */
+ if (*matchlen > IP_VS_PEDATA_MAXLEN)
+ return -EINVAL;
+
+ /* SIP headers are always followed by a line terminator */
+ if (*matchoff + *matchlen == datalen)
+ return -EINVAL;
+
+ /* RFC 2543 allows lines to be terminated with CR, LF or CRLF,
+ * RFC 3261 allows only CRLF, we support both. */
+ if (*(dptr + *matchoff + *matchlen) != '\r' &&
+ *(dptr + *matchoff + *matchlen) != '\n')
+ return -EINVAL;
+
+ IP_VS_DBG_BUF(9, "SIP callid %s (%d bytes)\n",
+ IP_VS_DEBUG_CALLID(dptr + *matchoff, *matchlen),
+ *matchlen);
+ return 0;
+}
+
+static int
+ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
+{
+ struct ip_vs_iphdr iph;
+ unsigned int dataoff, datalen, matchoff, matchlen;
+ const char *dptr;
+
+ ip_vs_fill_iphdr(p->af, skb_network_header(skb), &iph);
+
+ /* Only useful with UDP */
+ if (iph.protocol != IPPROTO_UDP)
+ return -EINVAL;
+
+ /* No Data ? */
+ dataoff = iph.len + sizeof(struct udphdr);
+ if (dataoff >= skb->len)
+ return -EINVAL;
+
+ dptr = skb->data + dataoff;
+ datalen = skb->len - dataoff;
+
+ if (get_callid(dptr, dataoff, datalen, &matchoff, &matchlen))
+ return -EINVAL;
+
+ p->pe_data = kmalloc(matchlen, GFP_ATOMIC);
+ if (!p->pe_data)
+ return -ENOMEM;
+
+ /* N.B: pe_data is only set on success,
+ * this allows fallback to the default persistence logic on failure
+ */
+ memcpy(p->pe_data, dptr + matchoff, matchlen);
+ p->pe_data_len = matchlen;
+
+ return 0;
+}
+
+static bool ip_vs_sip_ct_match(const struct ip_vs_conn_param *p,
+ struct ip_vs_conn *ct)
+
+{
+ bool ret = 0;
+
+ if (ct->af == p->af &&
+ ip_vs_addr_equal(p->af, p->caddr, &ct->caddr) &&
+ /* protocol should only be IPPROTO_IP if
+ * d_addr is a fwmark */
+ ip_vs_addr_equal(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af,
+ p->vaddr, &ct->vaddr) &&
+ ct->vport == p->vport &&
+ ct->flags & IP_VS_CONN_F_TEMPLATE &&
+ ct->protocol == p->protocol &&
+ ct->pe_data && ct->pe_data_len == p->pe_data_len &&
+ !memcmp(ct->pe_data, p->pe_data, p->pe_data_len))
+ ret = 1;
+
+ IP_VS_DBG_BUF(9, "SIP template match %s %s->%s:%d %s\n",
+ ip_vs_proto_name(p->protocol),
+ IP_VS_DEBUG_CALLID(p->pe_data, p->pe_data_len),
+ IP_VS_DBG_ADDR(p->af, p->vaddr), ntohs(p->vport),
+ ret ? "hit" : "not hit");
+
+ return ret;
+}
+
+static u32 ip_vs_sip_hashkey_raw(const struct ip_vs_conn_param *p,
+ u32 initval, bool inverse)
+{
+ return jhash(p->pe_data, p->pe_data_len, initval);
+}
+
+static int ip_vs_sip_show_pe_data(const struct ip_vs_conn *cp, char *buf)
+{
+ memcpy(buf, cp->pe_data, cp->pe_data_len);
+ return cp->pe_data_len;
+}
+
+static struct ip_vs_pe ip_vs_sip_pe =
+{
+ .name = "sip",
+ .refcnt = ATOMIC_INIT(0),
+ .module = THIS_MODULE,
+ .n_list = LIST_HEAD_INIT(ip_vs_sip_pe.n_list),
+ .fill_param = ip_vs_sip_fill_param,
+ .ct_match = ip_vs_sip_ct_match,
+ .hashkey_raw = ip_vs_sip_hashkey_raw,
+ .show_pe_data = ip_vs_sip_show_pe_data,
+};
+
+static int __init ip_vs_sip_init(void)
+{
+ return register_ip_vs_pe(&ip_vs_sip_pe);
+}
+
+static void __exit ip_vs_sip_cleanup(void)
+{
+ unregister_ip_vs_pe(&ip_vs_sip_pe);
+}
+
+module_init(ip_vs_sip_init);
+module_exit(ip_vs_sip_cleanup);
+MODULE_LICENSE("GPL");
^ permalink raw reply
* [patch v4 11/12] IPVS: Fallback if persistence engine fails
From: Simon Horman @ 2010-10-04 9:04 UTC (permalink / raw)
To: lvs-devel, netdev, netfilter, netfilter-devel
Cc: Jan Engelhardt, Stephen Hemminger, Wensong Zhang,
Julian Anastasov, Patrick McHardy
In-Reply-To: <20101004090352.966809749@akiko.akashicho.tokyo.vergenet.net>
[-- Attachment #1: 0011-IPVS-Fallback-if-persistence-engine-fails.patch --]
[-- Type: text/plain, Size: 3034 bytes --]
Fall back to normal persistence handling if the persistence
engine fails to recognise a packet.
This way, at least the packet will go somewhere.
It is envisaged that iptables could be used to block packets
such if this is not desired although nf_conntrack_sip would
likely need to be enhanced first.
Signed-off-by: Simon Horman <horms@verge.net.au>
Acked-by: Julian Anastasov <ja@ssi.bg>
---
v2
* Trivial rediff
v3
* Re-diff for addition of inverse parameter to ip_vs_conn_hashkey_param()
and checking of cp->dest in ip_vs_conn_seq_show()
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_conn.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_conn.c 2010-10-02 10:48:09.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_conn.c 2010-10-02 10:48:35.000000000 +0900
@@ -154,7 +154,7 @@ static unsigned int ip_vs_conn_hashkey_p
const union nf_inet_addr *addr;
__be16 port;
- if (p->pe && p->pe->hashkey_raw)
+ if (p->pe_data && p->pe->hashkey_raw)
return p->pe->hashkey_raw(p, ip_vs_conn_rnd, inverse) &
ip_vs_conn_tab_mask;
@@ -353,7 +353,7 @@ struct ip_vs_conn *ip_vs_ct_in_get(const
ct_read_lock(hash);
list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
- if (p->pe && p->pe->ct_match) {
+ if (p->pe_data && p->pe->ct_match) {
if (p->pe->ct_match(p, cp))
goto out;
continue;
@@ -956,7 +956,7 @@ static int ip_vs_conn_seq_show(struct se
char pe_data[IP_VS_PENAME_MAXLEN + IP_VS_PEDATA_MAXLEN + 3];
size_t len = 0;
- if (cp->dest && cp->dest->svc->pe &&
+ if (cp->dest && cp->pe_data &&
cp->dest->svc->pe->show_pe_data) {
pe_data[0] = ' ';
len = strlen(cp->dest->svc->pe->name);
memcpy(pe_data + 1, cp->dest->svc->pe->name, len);
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_core.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_core.c 2010-10-02 10:48:09.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_core.c 2010-10-02 10:48:35.000000000 +0900
@@ -176,7 +176,7 @@ ip_vs_set_state(struct ip_vs_conn *cp, i
return pp->state_transition(cp, direction, skb, pp);
}
-static inline int
+static inline void
ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc,
struct sk_buff *skb, int protocol,
const union nf_inet_addr *caddr, __be16 cport,
@@ -186,8 +186,7 @@ ip_vs_conn_fill_param_persist(const stru
ip_vs_conn_fill_param(svc->af, protocol, caddr, cport, vaddr, vport, p);
p->pe = svc->pe;
if (p->pe && p->pe->fill_param)
- return p->pe->fill_param(p, skb);
- return 0;
+ p->pe->fill_param(p, skb);
}
/*
@@ -268,9 +267,8 @@ ip_vs_sched_persist(struct ip_vs_service
vaddr = &fwmark;
}
}
- if (ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0,
- vaddr, vport, ¶m))
- return NULL;
+ ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0,
+ vaddr, vport, ¶m);
}
/* Check if a template already exists */
^ permalink raw reply
* [patch v4 10/12] IPVS: Allow configuration of persistence engines
From: Simon Horman @ 2010-10-04 9:04 UTC (permalink / raw)
To: lvs-devel, netdev, netfilter, netfilter-devel
Cc: Jan Engelhardt, Stephen Hemminger, Wensong Zhang,
Julian Anastasov, Patrick McHardy
In-Reply-To: <20101004090352.966809749@akiko.akashicho.tokyo.vergenet.net>
[-- Attachment #1: 0010-IPVS-Allow-configuration-of-persistence-engines.patch --]
[-- Type: text/plain, Size: 7170 bytes --]
Allow the persistence engine of a virtual service to be set, edited
and unset.
This feature only works with the netlink user-space interface.
Signed-off-by: Simon Horman <horms@verge.net.au>
Acked-by: Julian Anastasov <ja@ssi.bg>
---
v2
* Dereference persistence engine when a service is deleted.
This allows persistence modules to be removed from the kernel
once they are no longer used.
* Update for the recent "ipvs: changes related to service usecnt" change
* Trivial rediff
v4
* As suggested by Julian Anastasov <ja@ssi.bg>
- Initialise ip_vs_service_user_kern to zero in ip_vs_copy_usvc_compat()
to avoid a crash caused by the pe_name element being uninitialised.
Index: lvs-test-2.6/include/linux/ip_vs.h
===================================================================
--- lvs-test-2.6.orig/include/linux/ip_vs.h 2010-10-04 17:14:56.000000000 +0900
+++ lvs-test-2.6/include/linux/ip_vs.h 2010-10-04 17:15:01.000000000 +0900
@@ -336,6 +336,9 @@ enum {
IPVS_SVC_ATTR_NETMASK, /* persistent netmask */
IPVS_SVC_ATTR_STATS, /* nested attribute for service stats */
+
+ IPVS_SVC_ATTR_PE_NAME, /* name of ct retriever */
+
__IPVS_SVC_ATTR_MAX,
};
Index: lvs-test-2.6/include/net/ip_vs.h
===================================================================
--- lvs-test-2.6.orig/include/net/ip_vs.h 2010-10-04 17:14:56.000000000 +0900
+++ lvs-test-2.6/include/net/ip_vs.h 2010-10-04 17:15:01.000000000 +0900
@@ -444,6 +444,7 @@ struct ip_vs_service_user_kern {
/* virtual service options */
char *sched_name;
+ char *pe_name;
unsigned flags; /* virtual service flags */
unsigned timeout; /* persistent timeout in sec */
u32 netmask; /* persistent netmask */
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_ctl.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_ctl.c 2010-10-04 17:14:56.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_ctl.c 2010-10-04 17:16:11.000000000 +0900
@@ -1134,6 +1134,7 @@ ip_vs_add_service(struct ip_vs_service_u
{
int ret = 0;
struct ip_vs_scheduler *sched = NULL;
+ struct ip_vs_pe *pe = NULL;
struct ip_vs_service *svc = NULL;
/* increase the module use count */
@@ -1147,6 +1148,16 @@ ip_vs_add_service(struct ip_vs_service_u
goto out_err;
}
+ if (u->pe_name && *u->pe_name) {
+ pe = ip_vs_pe_get(u->pe_name);
+ if (pe == NULL) {
+ pr_info("persistence engine module ip_vs_pe_%s "
+ "not found\n", u->pe_name);
+ ret = -ENOENT;
+ goto out_err;
+ }
+ }
+
#ifdef CONFIG_IP_VS_IPV6
if (u->af == AF_INET6 && (u->netmask < 1 || u->netmask > 128)) {
ret = -EINVAL;
@@ -1184,6 +1195,10 @@ ip_vs_add_service(struct ip_vs_service_u
goto out_err;
sched = NULL;
+ /* Bind the ct retriever */
+ ip_vs_bind_pe(svc, pe);
+ pe = NULL;
+
/* Update the virtual service counters */
if (svc->port == FTPPORT)
atomic_inc(&ip_vs_ftpsvc_counter);
@@ -1215,6 +1230,7 @@ ip_vs_add_service(struct ip_vs_service_u
kfree(svc);
}
ip_vs_scheduler_put(sched);
+ ip_vs_pe_put(pe);
/* decrease the module use count */
ip_vs_use_count_dec();
@@ -1230,6 +1246,7 @@ static int
ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
{
struct ip_vs_scheduler *sched, *old_sched;
+ struct ip_vs_pe *pe = NULL, *old_pe = NULL;
int ret = 0;
/*
@@ -1242,6 +1259,17 @@ ip_vs_edit_service(struct ip_vs_service
}
old_sched = sched;
+ if (u->pe_name && *u->pe_name) {
+ pe = ip_vs_pe_get(u->pe_name);
+ if (pe == NULL) {
+ pr_info("persistence engine module ip_vs_pe_%s "
+ "not found\n", u->pe_name);
+ ret = -ENOENT;
+ goto out;
+ }
+ old_pe = pe;
+ }
+
#ifdef CONFIG_IP_VS_IPV6
if (u->af == AF_INET6 && (u->netmask < 1 || u->netmask > 128)) {
ret = -EINVAL;
@@ -1293,12 +1321,17 @@ ip_vs_edit_service(struct ip_vs_service
}
}
+ old_pe = svc->pe;
+ if (pe != old_pe) {
+ ip_vs_unbind_pe(svc);
+ ip_vs_bind_pe(svc, pe);
+ }
+
out_unlock:
write_unlock_bh(&__ip_vs_svc_lock);
-#ifdef CONFIG_IP_VS_IPV6
out:
-#endif
ip_vs_scheduler_put(old_sched);
+ ip_vs_pe_put(old_pe);
return ret;
}
@@ -1312,6 +1345,9 @@ static void __ip_vs_del_service(struct i
{
struct ip_vs_dest *dest, *nxt;
struct ip_vs_scheduler *old_sched;
+ struct ip_vs_pe *old_pe;
+
+ pr_info("%s: enter\n", __func__);
/* Count only IPv4 services for old get/setsockopt interface */
if (svc->af == AF_INET)
@@ -1324,6 +1360,11 @@ static void __ip_vs_del_service(struct i
ip_vs_unbind_scheduler(svc);
ip_vs_scheduler_put(old_sched);
+ /* Unbind persistence engine */
+ old_pe = svc->pe;
+ ip_vs_unbind_pe(svc);
+ ip_vs_pe_put(old_pe);
+
/* Unbind app inc */
if (svc->inc) {
ip_vs_app_inc_put(svc->inc);
@@ -2026,6 +2067,8 @@ static const unsigned char set_arglen[SE
static void ip_vs_copy_usvc_compat(struct ip_vs_service_user_kern *usvc,
struct ip_vs_service_user *usvc_compat)
{
+ memset(usvc, 0, sizeof(*usvc));
+
usvc->af = AF_INET;
usvc->protocol = usvc_compat->protocol;
usvc->addr.ip = usvc_compat->addr;
@@ -2043,6 +2086,8 @@ static void ip_vs_copy_usvc_compat(struc
static void ip_vs_copy_udest_compat(struct ip_vs_dest_user_kern *udest,
struct ip_vs_dest_user *udest_compat)
{
+ memset(usvc, 0, sizeof(*udest));
+
udest->addr.ip = udest_compat->addr;
udest->port = udest_compat->port;
udest->conn_flags = udest_compat->conn_flags;
@@ -2539,6 +2584,8 @@ static const struct nla_policy ip_vs_svc
[IPVS_SVC_ATTR_FWMARK] = { .type = NLA_U32 },
[IPVS_SVC_ATTR_SCHED_NAME] = { .type = NLA_NUL_STRING,
.len = IP_VS_SCHEDNAME_MAXLEN },
+ [IPVS_SVC_ATTR_PE_NAME] = { .type = NLA_NUL_STRING,
+ .len = IP_VS_PENAME_MAXLEN },
[IPVS_SVC_ATTR_FLAGS] = { .type = NLA_BINARY,
.len = sizeof(struct ip_vs_flags) },
[IPVS_SVC_ATTR_TIMEOUT] = { .type = NLA_U32 },
@@ -2615,6 +2662,8 @@ static int ip_vs_genl_fill_service(struc
}
NLA_PUT_STRING(skb, IPVS_SVC_ATTR_SCHED_NAME, svc->scheduler->name);
+ if (svc->pe)
+ NLA_PUT_STRING(skb, IPVS_SVC_ATTR_PE_NAME, svc->pe->name);
NLA_PUT(skb, IPVS_SVC_ATTR_FLAGS, sizeof(flags), &flags);
NLA_PUT_U32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ);
NLA_PUT_U32(skb, IPVS_SVC_ATTR_NETMASK, svc->netmask);
@@ -2741,11 +2790,12 @@ static int ip_vs_genl_parse_service(stru
/* If a full entry was requested, check for the additional fields */
if (full_entry) {
- struct nlattr *nla_sched, *nla_flags, *nla_timeout,
+ struct nlattr *nla_sched, *nla_flags, *nla_pe, *nla_timeout,
*nla_netmask;
struct ip_vs_flags flags;
nla_sched = attrs[IPVS_SVC_ATTR_SCHED_NAME];
+ nla_pe = attrs[IPVS_SVC_ATTR_PE_NAME];
nla_flags = attrs[IPVS_SVC_ATTR_FLAGS];
nla_timeout = attrs[IPVS_SVC_ATTR_TIMEOUT];
nla_netmask = attrs[IPVS_SVC_ATTR_NETMASK];
@@ -2763,6 +2813,7 @@ static int ip_vs_genl_parse_service(stru
usvc->flags = (usvc->flags & ~flags.mask) |
(flags.flags & flags.mask);
usvc->sched_name = nla_data(nla_sched);
+ usvc->pe_name = nla_pe ? nla_data(nla_pe) : NULL;
usvc->timeout = nla_get_u32(nla_timeout);
usvc->netmask = nla_get_u32(nla_netmask);
}
^ permalink raw reply
* [patch v4 09/12] IPVS: management of persistence engine modules
From: Simon Horman @ 2010-10-04 9:04 UTC (permalink / raw)
To: lvs-devel, netdev, netfilter, netfilter-devel
Cc: Jan Engelhardt, Stephen Hemminger, Wensong Zhang,
Julian Anastasov, Patrick McHardy
In-Reply-To: <20101004090352.966809749@akiko.akashicho.tokyo.vergenet.net>
[-- Attachment #1: 0009-IPVS-management-of-persistence-engine-modules.patch --]
[-- Type: text/plain, Size: 5764 bytes --]
This is based heavily on the scheduler management code
Signed-off-by: Simon Horman <horms@verge.net.au>
Acked-by: Julian Anastasov <ja@ssi.bg>
---
v0.4
* Export register_ip_vs_pe and unregister_ip_vs_pe
* Use one line comment format for one line comments.
* Only use at most one blank line consecutively
v1
* As suggested by Stephen Hemminger
- Convert __ip_vs_pe_lock from a rwlock to a spinlock.
This code isn't performance-critical, so there is no need for RCU.
- Rename __ip_vs_pe_lock as ip_vs_pe_lock
* Stephen also suggested open-coding ip_vs_{un,}bind_pe()
as they are very short. But I would prefer to keep them as they are used
along side ip_vs_{un,}bind_scheduler which are too long to be open-coded.
v2
* Update for recent addition of ip_vs_nfct.c
* Trivial rediff
v3
* Trivial rediff
Index: lvs-test-2.6/include/net/ip_vs.h
===================================================================
--- lvs-test-2.6.orig/include/net/ip_vs.h 2010-10-02 10:45:06.000000000 +0900
+++ lvs-test-2.6/include/net/ip_vs.h 2010-10-02 10:45:41.000000000 +0900
@@ -796,6 +796,12 @@ extern int ip_vs_app_pkt_in(struct ip_vs
extern int ip_vs_app_init(void);
extern void ip_vs_app_cleanup(void);
+void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe);
+void ip_vs_unbind_pe(struct ip_vs_service *svc);
+int register_ip_vs_pe(struct ip_vs_pe *pe);
+int unregister_ip_vs_pe(struct ip_vs_pe *pe);
+extern struct ip_vs_pe *ip_vs_pe_get(const char *name);
+extern void ip_vs_pe_put(struct ip_vs_pe *pe);
/*
* IPVS protocol functions (from ip_vs_proto.c)
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_pe.c
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_pe.c 2010-10-02 10:45:41.000000000 +0900
@@ -0,0 +1,147 @@
+#define KMSG_COMPONENT "IPVS"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
+#include <asm/string.h>
+#include <linux/kmod.h>
+#include <linux/sysctl.h>
+
+#include <net/ip_vs.h>
+
+/* IPVS pe list */
+static LIST_HEAD(ip_vs_pe);
+
+/* lock for service table */
+static DEFINE_SPINLOCK(ip_vs_pe_lock);
+
+/* Bind a service with a pe */
+void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe)
+{
+ svc->pe = pe;
+}
+
+/* Unbind a service from its pe */
+void ip_vs_unbind_pe(struct ip_vs_service *svc)
+{
+ svc->pe = NULL;
+}
+
+/* Get pe in the pe list by name */
+static struct ip_vs_pe *
+ip_vs_pe_getbyname(const char *pe_name)
+{
+ struct ip_vs_pe *pe;
+
+ IP_VS_DBG(2, "%s(): pe_name \"%s\"\n", __func__,
+ pe_name);
+
+ spin_lock_bh(&ip_vs_pe_lock);
+
+ list_for_each_entry(pe, &ip_vs_pe, n_list) {
+ /* Test and get the modules atomically */
+ if (pe->module &&
+ !try_module_get(pe->module)) {
+ /* This pe is just deleted */
+ continue;
+ }
+ if (strcmp(pe_name, pe->name)==0) {
+ /* HIT */
+ spin_unlock_bh(&ip_vs_pe_lock);
+ return pe;
+ }
+ if (pe->module)
+ module_put(pe->module);
+ }
+
+ spin_unlock_bh(&ip_vs_pe_lock);
+ return NULL;
+}
+
+/* Lookup pe and try to load it if it doesn't exist */
+struct ip_vs_pe *ip_vs_pe_get(const char *name)
+{
+ struct ip_vs_pe *pe;
+
+ /* Search for the pe by name */
+ pe = ip_vs_pe_getbyname(name);
+
+ /* If pe not found, load the module and search again */
+ if (!pe) {
+ request_module("ip_vs_pe_%s", name);
+ pe = ip_vs_pe_getbyname(name);
+ }
+
+ return pe;
+}
+
+void ip_vs_pe_put(struct ip_vs_pe *pe)
+{
+ if (pe && pe->module)
+ module_put(pe->module);
+}
+
+/* Register a pe in the pe list */
+int register_ip_vs_pe(struct ip_vs_pe *pe)
+{
+ struct ip_vs_pe *tmp;
+
+ /* increase the module use count */
+ ip_vs_use_count_inc();
+
+ spin_lock_bh(&ip_vs_pe_lock);
+
+ if (!list_empty(&pe->n_list)) {
+ spin_unlock_bh(&ip_vs_pe_lock);
+ ip_vs_use_count_dec();
+ pr_err("%s(): [%s] pe already linked\n",
+ __func__, pe->name);
+ return -EINVAL;
+ }
+
+ /* Make sure that the pe with this name doesn't exist
+ * in the pe list.
+ */
+ list_for_each_entry(tmp, &ip_vs_pe, n_list) {
+ if (strcmp(tmp->name, pe->name) == 0) {
+ spin_unlock_bh(&ip_vs_pe_lock);
+ ip_vs_use_count_dec();
+ pr_err("%s(): [%s] pe already existed "
+ "in the system\n", __func__, pe->name);
+ return -EINVAL;
+ }
+ }
+ /* Add it into the d-linked pe list */
+ list_add(&pe->n_list, &ip_vs_pe);
+ spin_unlock_bh(&ip_vs_pe_lock);
+
+ pr_info("[%s] pe registered.\n", pe->name);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(register_ip_vs_pe);
+
+/* Unregister a pe from the pe list */
+int unregister_ip_vs_pe(struct ip_vs_pe *pe)
+{
+ spin_lock_bh(&ip_vs_pe_lock);
+ if (list_empty(&pe->n_list)) {
+ spin_unlock_bh(&ip_vs_pe_lock);
+ pr_err("%s(): [%s] pe is not in the list. failed\n",
+ __func__, pe->name);
+ return -EINVAL;
+ }
+
+ /* Remove it from the d-linked pe list */
+ list_del(&pe->n_list);
+ spin_unlock_bh(&ip_vs_pe_lock);
+
+ /* decrease the module use count */
+ ip_vs_use_count_dec();
+
+ pr_info("[%s] pe unregistered.\n", pe->name);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(unregister_ip_vs_pe);
Index: lvs-test-2.6/net/netfilter/ipvs/Makefile
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/Makefile 2010-10-02 10:29:43.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/Makefile 2010-10-02 10:45:41.000000000 +0900
@@ -14,7 +14,7 @@ ip_vs-extra_objs-$(CONFIG_IP_VS_NFCT) +=
ip_vs-objs := ip_vs_conn.o ip_vs_core.o ip_vs_ctl.o ip_vs_sched.o \
ip_vs_xmit.o ip_vs_app.o ip_vs_sync.o \
- ip_vs_est.o ip_vs_proto.o \
+ ip_vs_est.o ip_vs_proto.o ip_vs_pe.o \
$(ip_vs_proto-objs-y) $(ip_vs-extra_objs-y)
^ permalink raw reply
* [patch v4 07/12] IPVS: Add struct ip_vs_pe
From: Simon Horman @ 2010-10-04 9:03 UTC (permalink / raw)
To: lvs-devel, netdev, netfilter, netfilter-devel
Cc: Jan Engelhardt, Stephen Hemminger, Wensong Zhang,
Julian Anastasov, Patrick McHardy
In-Reply-To: <20101004090352.966809749@akiko.akashicho.tokyo.vergenet.net>
[-- Attachment #1: 0007-IPVS-Add-struct-ip_vs_pe.patch --]
[-- Type: text/plain, Size: 12003 bytes --]
Signed-off-by: Simon Horman <horms@verge.net.au>
Acked-by: Julian Anastasov <ja@ssi.bg>
---
This the first of several patches that add persistence engines.
v2
* Don't leak pe_data
- It wasn't being freed anywhere, ever
* Trivial rediff
v3
* As suggested by Julian Anastasov
- ip_vs_conn_fill_param(): cp->dest is optional
so check for its presence accordingly
- ip_vs_conn_out_get() needs to hash on vaddr/vport
whereas ip_vs_conn_hash() hashes on caddr/cport.
Add an inverse parameter to ip_vs_conn_hashkey_param()
to allow it to handle both cases.
* Rediff for dport logic fix in "IPVS: compact ip_vs_sched_persist()"
Index: lvs-test-2.6/include/linux/ip_vs.h
===================================================================
--- lvs-test-2.6.orig/include/linux/ip_vs.h 2010-10-02 10:59:26.000000000 +0900
+++ lvs-test-2.6/include/linux/ip_vs.h 2010-10-02 11:09:03.000000000 +0900
@@ -99,8 +99,10 @@
0)
#define IP_VS_SCHEDNAME_MAXLEN 16
+#define IP_VS_PENAME_MAXLEN 16
#define IP_VS_IFNAME_MAXLEN 16
+#define IP_VS_PEDATA_MAXLEN 255
/*
* The struct ip_vs_service_user and struct ip_vs_dest_user are
Index: lvs-test-2.6/include/net/ip_vs.h
===================================================================
--- lvs-test-2.6.orig/include/net/ip_vs.h 2010-10-02 11:05:43.000000000 +0900
+++ lvs-test-2.6/include/net/ip_vs.h 2010-10-02 11:09:03.000000000 +0900
@@ -364,6 +364,10 @@ struct ip_vs_conn_param {
__be16 vport;
__u16 protocol;
u16 af;
+
+ const struct ip_vs_pe *pe;
+ char *pe_data;
+ __u8 pe_data_len;
};
/*
@@ -416,6 +420,9 @@ struct ip_vs_conn {
void *app_data; /* Application private data */
struct ip_vs_seq in_seq; /* incoming seq. struct */
struct ip_vs_seq out_seq; /* outgoing seq. struct */
+
+ char *pe_data;
+ __u8 pe_data_len;
};
@@ -486,6 +493,9 @@ struct ip_vs_service {
struct ip_vs_scheduler *scheduler; /* bound scheduler object */
rwlock_t sched_lock; /* lock sched_data */
void *sched_data; /* scheduler application data */
+
+ /* alternate persistence engine */
+ struct ip_vs_pe *pe;
};
@@ -549,6 +559,20 @@ struct ip_vs_scheduler {
const struct sk_buff *skb);
};
+/* The persistence engine object */
+struct ip_vs_pe {
+ struct list_head n_list; /* d-linked list head */
+ char *name; /* scheduler name */
+ atomic_t refcnt; /* reference counter */
+ struct module *module; /* THIS_MODULE/NULL */
+
+ /* get the connection template, if any */
+ int (*fill_param)(struct ip_vs_conn_param *p, struct sk_buff *skb);
+ bool (*ct_match)(const struct ip_vs_conn_param *p,
+ struct ip_vs_conn *ct);
+ u32 (*hashkey_raw)(const struct ip_vs_conn_param *p, u32 initval,
+ bool inverse);
+};
/*
* The application module object (a.k.a. app incarnation)
@@ -648,6 +672,8 @@ static inline void ip_vs_conn_fill_param
p->cport = cport;
p->vaddr = vaddr;
p->vport = vport;
+ p->pe = NULL;
+ p->pe_data = NULL;
}
struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p);
@@ -803,7 +829,7 @@ extern int ip_vs_unbind_scheduler(struct
extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name);
extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler);
extern struct ip_vs_conn *
-ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb);
+ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb);
extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
struct ip_vs_protocol *pp);
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_conn.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_conn.c 2010-10-02 11:05:43.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_conn.c 2010-10-02 11:09:03.000000000 +0900
@@ -148,6 +148,42 @@ static unsigned int ip_vs_conn_hashkey(i
& ip_vs_conn_tab_mask;
}
+static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p,
+ bool inverse)
+{
+ const union nf_inet_addr *addr;
+ __be16 port;
+
+ if (p->pe && p->pe->hashkey_raw)
+ return p->pe->hashkey_raw(p, ip_vs_conn_rnd, inverse) &
+ ip_vs_conn_tab_mask;
+
+ if (likely(!inverse)) {
+ addr = p->caddr;
+ port = p->cport;
+ } else {
+ addr = p->vaddr;
+ port = p->vport;
+ }
+
+ return ip_vs_conn_hashkey(p->af, p->protocol, addr, port);
+}
+
+static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp)
+{
+ struct ip_vs_conn_param p;
+
+ ip_vs_conn_fill_param(cp->af, cp->protocol, &cp->caddr, cp->cport,
+ NULL, 0, &p);
+
+ if (cp->dest && cp->dest->svc->pe) {
+ p.pe = cp->dest->svc->pe;
+ p.pe_data = cp->pe_data;
+ p.pe_data_len = cp->pe_data_len;
+ }
+
+ return ip_vs_conn_hashkey_param(&p, false);
+}
/*
* Hashes ip_vs_conn in ip_vs_conn_tab by proto,addr,port.
@@ -162,7 +198,7 @@ static inline int ip_vs_conn_hash(struct
return 0;
/* Hash by protocol, client address and port */
- hash = ip_vs_conn_hashkey(cp->af, cp->protocol, &cp->caddr, cp->cport);
+ hash = ip_vs_conn_hashkey_conn(cp);
ct_write_lock(hash);
spin_lock(&cp->lock);
@@ -195,7 +231,7 @@ static inline int ip_vs_conn_unhash(stru
int ret;
/* unhash it and decrease its reference counter */
- hash = ip_vs_conn_hashkey(cp->af, cp->protocol, &cp->caddr, cp->cport);
+ hash = ip_vs_conn_hashkey_conn(cp);
ct_write_lock(hash);
spin_lock(&cp->lock);
@@ -227,7 +263,7 @@ __ip_vs_conn_in_get(const struct ip_vs_c
unsigned hash;
struct ip_vs_conn *cp;
- hash = ip_vs_conn_hashkey(p->af, p->protocol, p->caddr, p->cport);
+ hash = ip_vs_conn_hashkey_param(p, false);
ct_read_lock(hash);
@@ -312,11 +348,17 @@ struct ip_vs_conn *ip_vs_ct_in_get(const
unsigned hash;
struct ip_vs_conn *cp;
- hash = ip_vs_conn_hashkey(p->af, p->protocol, p->caddr, p->cport);
+ hash = ip_vs_conn_hashkey_param(p, false);
ct_read_lock(hash);
list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
+ if (p->pe && p->pe->ct_match) {
+ if (p->pe->ct_match(p, cp))
+ goto out;
+ continue;
+ }
+
if (cp->af == p->af &&
ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) &&
/* protocol should only be IPPROTO_IP if
@@ -325,15 +367,14 @@ struct ip_vs_conn *ip_vs_ct_in_get(const
p->af, p->vaddr, &cp->vaddr) &&
p->cport == cp->cport && p->vport == cp->vport &&
cp->flags & IP_VS_CONN_F_TEMPLATE &&
- p->protocol == cp->protocol) {
- /* HIT */
- atomic_inc(&cp->refcnt);
+ p->protocol == cp->protocol)
goto out;
- }
}
cp = NULL;
out:
+ if (cp)
+ atomic_inc(&cp->refcnt);
ct_read_unlock(hash);
IP_VS_DBG_BUF(9, "template lookup/in %s %s:%d->%s:%d %s\n",
@@ -357,7 +398,7 @@ struct ip_vs_conn *ip_vs_conn_out_get(co
/*
* Check for "full" addressed entries
*/
- hash = ip_vs_conn_hashkey(p->af, p->protocol, p->vaddr, p->vport);
+ hash = ip_vs_conn_hashkey_param(p, true);
ct_read_lock(hash);
@@ -722,6 +763,7 @@ static void ip_vs_conn_expire(unsigned l
if (cp->flags & IP_VS_CONN_F_NFCT)
ip_vs_conn_drop_conntrack(cp);
+ kfree(cp->pe_data);
if (unlikely(cp->app != NULL))
ip_vs_unbind_app(cp);
ip_vs_unbind_dest(cp);
@@ -782,6 +824,10 @@ ip_vs_conn_new(const struct ip_vs_conn_p
&cp->daddr, daddr);
cp->dport = dport;
cp->flags = flags;
+ if (flags & IP_VS_CONN_F_TEMPLATE && p->pe_data) {
+ cp->pe_data = p->pe_data;
+ cp->pe_data_len = p->pe_data_len;
+ }
spin_lock_init(&cp->lock);
/*
@@ -832,7 +878,6 @@ ip_vs_conn_new(const struct ip_vs_conn_p
return cp;
}
-
/*
* /proc/net/ip_vs_conn entries
*/
@@ -848,7 +893,7 @@ static void *ip_vs_conn_array(struct seq
list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
if (pos-- == 0) {
seq->private = &ip_vs_conn_tab[idx];
- return cp;
+ return cp;
}
}
ct_read_unlock_bh(idx);
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_core.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_core.c 2010-10-02 11:05:43.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_core.c 2010-10-02 11:09:03.000000000 +0900
@@ -176,6 +176,19 @@ ip_vs_set_state(struct ip_vs_conn *cp, i
return pp->state_transition(cp, direction, skb, pp);
}
+static inline int
+ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc,
+ struct sk_buff *skb, int protocol,
+ const union nf_inet_addr *caddr, __be16 cport,
+ const union nf_inet_addr *vaddr, __be16 vport,
+ struct ip_vs_conn_param *p)
+{
+ ip_vs_conn_fill_param(svc->af, protocol, caddr, cport, vaddr, vport, p);
+ p->pe = svc->pe;
+ if (p->pe && p->pe->fill_param)
+ return p->pe->fill_param(p, skb);
+ return 0;
+}
/*
* IPVS persistent scheduling function
@@ -186,7 +199,7 @@ ip_vs_set_state(struct ip_vs_conn *cp, i
*/
static struct ip_vs_conn *
ip_vs_sched_persist(struct ip_vs_service *svc,
- const struct sk_buff *skb,
+ struct sk_buff *skb,
__be16 ports[2])
{
struct ip_vs_conn *cp = NULL;
@@ -255,8 +268,9 @@ ip_vs_sched_persist(struct ip_vs_service
vaddr = &fwmark;
}
}
- ip_vs_conn_fill_param(svc->af, protocol, &snet, 0,
- vaddr, vport, ¶m);
+ if (ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0,
+ vaddr, vport, ¶m))
+ return NULL;
}
/* Check if a template already exists */
@@ -268,22 +282,30 @@ ip_vs_sched_persist(struct ip_vs_service
dest = svc->scheduler->schedule(svc, skb);
if (!dest) {
IP_VS_DBG(1, "p-schedule: no dest found.\n");
+ kfree(param.pe_data);
return NULL;
}
if (ports[1] == svc->port && svc->port != FTPPORT)
dport = dest->port;
- /* Create a template */
+ /* Create a template
+ * This adds param.pe_data to the template,
+ * and thus param.pe_data will be destroyed
+ * when the template expires */
ct = ip_vs_conn_new(¶m, &dest->addr, dport,
IP_VS_CONN_F_TEMPLATE, dest);
- if (ct == NULL)
+ if (ct == NULL) {
+ kfree(param.pe_data);
return NULL;
+ }
ct->timeout = svc->timeout;
- } else
+ } else {
/* set destination with the found template */
dest = ct->dest;
+ kfree(param.pe_data);
+ }
dport = ports[1];
if (dport == svc->port && dest->port)
@@ -322,7 +344,7 @@ ip_vs_sched_persist(struct ip_vs_service
* Protocols supported: TCP, UDP
*/
struct ip_vs_conn *
-ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
+ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb)
{
struct ip_vs_conn *cp = NULL;
struct ip_vs_iphdr iph;
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_sync.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_sync.c 2010-10-02 11:05:43.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_sync.c 2010-10-02 11:09:03.000000000 +0900
@@ -288,6 +288,16 @@ void ip_vs_sync_conn(struct ip_vs_conn *
ip_vs_sync_conn(cp->control);
}
+static inline int
+ip_vs_conn_fill_param_sync(int af, int protocol,
+ const union nf_inet_addr *caddr, __be16 cport,
+ const union nf_inet_addr *vaddr, __be16 vport,
+ struct ip_vs_conn_param *p)
+{
+ /* XXX: Need to take into account persistence engine */
+ ip_vs_conn_fill_param(af, protocol, caddr, cport, vaddr, vport, p);
+ return 0;
+}
/*
* Process received multicast message and create the corresponding
@@ -372,11 +382,14 @@ static void ip_vs_process_message(const
}
{
- ip_vs_conn_fill_param(AF_INET, s->protocol,
+ if (ip_vs_conn_fill_param_sync(AF_INET, s->protocol,
(union nf_inet_addr *)&s->caddr,
s->cport,
(union nf_inet_addr *)&s->vaddr,
- s->vport, ¶m);
+ s->vport, ¶m)) {
+ pr_err("ip_vs_conn_fill_param_sync failed");
+ return;
+ }
if (!(flags & IP_VS_CONN_F_TEMPLATE))
cp = ip_vs_conn_in_get(¶m);
else
^ permalink raw reply
* [patch v4 05/12] IPVS: Allow null argument to ip_vs_scheduler_put()
From: Simon Horman @ 2010-10-04 9:03 UTC (permalink / raw)
To: lvs-devel, netdev, netfilter, netfilter-devel
Cc: Jan Engelhardt, Stephen Hemminger, Wensong Zhang,
Julian Anastasov, Patrick McHardy
In-Reply-To: <20101004090352.966809749@akiko.akashicho.tokyo.vergenet.net>
[-- Attachment #1: 0005-IPVS-Allow-null-argument-to-ip_vs_scheduler_put.patch --]
[-- Type: text/plain, Size: 2081 bytes --]
This simplifies caller logic sightly.
Signed-off-by: Simon Horman <horms@verge.net.au>
Acked-by: Julian Anastasov <ja@ssi.bg>
---
v2
* Trivial rediff
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_ctl.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_ctl.c 2010-10-01 22:25:53.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_ctl.c 2010-10-01 22:26:10.000000000 +0900
@@ -1144,7 +1144,7 @@ ip_vs_add_service(struct ip_vs_service_u
if (sched == NULL) {
pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name);
ret = -ENOENT;
- goto out_mod_dec;
+ goto out_err;
}
#ifdef CONFIG_IP_VS_IPV6
@@ -1204,7 +1204,7 @@ ip_vs_add_service(struct ip_vs_service_u
*svc_p = svc;
return 0;
- out_err:
+ out_err:
if (svc != NULL) {
if (svc->scheduler)
ip_vs_unbind_scheduler(svc);
@@ -1217,7 +1217,6 @@ ip_vs_add_service(struct ip_vs_service_u
}
ip_vs_scheduler_put(sched);
- out_mod_dec:
/* decrease the module use count */
ip_vs_use_count_dec();
@@ -1300,10 +1299,7 @@ ip_vs_edit_service(struct ip_vs_service
#ifdef CONFIG_IP_VS_IPV6
out:
#endif
-
- if (old_sched)
- ip_vs_scheduler_put(old_sched);
-
+ ip_vs_scheduler_put(old_sched);
return ret;
}
@@ -1327,8 +1323,7 @@ static void __ip_vs_del_service(struct i
/* Unbind scheduler */
old_sched = svc->scheduler;
ip_vs_unbind_scheduler(svc);
- if (old_sched)
- ip_vs_scheduler_put(old_sched);
+ ip_vs_scheduler_put(old_sched);
/* Unbind app inc */
if (svc->inc) {
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_sched.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_sched.c 2010-10-01 22:25:53.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_sched.c 2010-10-01 22:26:10.000000000 +0900
@@ -159,7 +159,7 @@ struct ip_vs_scheduler *ip_vs_scheduler_
void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler)
{
- if (scheduler->module)
+ if (scheduler && scheduler->module)
module_put(scheduler->module);
}
^ permalink raw reply
* [patch v4 04/12] IPVS: Add struct ip_vs_conn_param
From: Simon Horman @ 2010-10-04 9:03 UTC (permalink / raw)
To: lvs-devel, netdev, netfilter, netfilter-devel
Cc: Jan Engelhardt, Stephen Hemminger, Wensong Zhang,
Julian Anastasov, Patrick McHardy
In-Reply-To: <20101004090352.966809749@akiko.akashicho.tokyo.vergenet.net>
[-- Attachment #1: 0004-IPVS-Add-struct-ip_vs_conn_param.patch --]
[-- Type: text/plain, Size: 26203 bytes --]
Signed-off-by: Simon Horman <horms@verge.net.au>
Acked-by: Julian Anastasov <ja@ssi.bg>
---
The motivation for this is to allow persistence engine modules to
fill in the parameters.
v0.3
* Add missing changes to ip_vs_ftp.c
v2
* make "union nf_inet_addr fwmark" const
* Update for the recent addition of ip_vs_nfct.c
v3
* As suggested by Julian Anastasov
- Correct logic for inverse case in ip_vs_conn_fill_param_proto()
and ah_esp_conn_fill_param_proto()
- Update ip_vs_conn_out_get()'s comments as its parameters have changed
- Add missing call to ip_vs_conn_fill_param() before the second
invocation of ip_vs_conn_new() in ip_vs_sched_persist()
* Trivial re-diff
v4
* As suggested by Julian Anastasov
- Fix logic in ip_vs_conn_out_get_proto()
+ An error occurs if ip_vs_conn_fill_param_proto is non-zero,
not if it is zero
Index: lvs-test-2.6/include/net/ip_vs.h
===================================================================
--- lvs-test-2.6.orig/include/net/ip_vs.h 2010-10-04 17:00:28.000000000 +0900
+++ lvs-test-2.6/include/net/ip_vs.h 2010-10-04 17:49:20.000000000 +0900
@@ -357,6 +357,15 @@ struct ip_vs_protocol {
extern struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto);
+struct ip_vs_conn_param {
+ const union nf_inet_addr *caddr;
+ const union nf_inet_addr *vaddr;
+ __be16 cport;
+ __be16 vport;
+ __u16 protocol;
+ u16 af;
+};
+
/*
* IP_VS structure allocated for each dynamically scheduled connection
*/
@@ -626,13 +635,23 @@ enum {
IP_VS_DIR_LAST,
};
-extern struct ip_vs_conn *ip_vs_conn_in_get
-(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port,
- const union nf_inet_addr *d_addr, __be16 d_port);
-
-extern struct ip_vs_conn *ip_vs_ct_in_get
-(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port,
- const union nf_inet_addr *d_addr, __be16 d_port);
+static inline void ip_vs_conn_fill_param(int af, int protocol,
+ const union nf_inet_addr *caddr,
+ __be16 cport,
+ const union nf_inet_addr *vaddr,
+ __be16 vport,
+ struct ip_vs_conn_param *p)
+{
+ p->af = af;
+ p->protocol = protocol;
+ p->caddr = caddr;
+ p->cport = cport;
+ p->vaddr = vaddr;
+ p->vport = vport;
+}
+
+struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p);
+struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p);
struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
struct ip_vs_protocol *pp,
@@ -640,9 +659,7 @@ struct ip_vs_conn * ip_vs_conn_in_get_pr
unsigned int proto_off,
int inverse);
-extern struct ip_vs_conn *ip_vs_conn_out_get
-(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port,
- const union nf_inet_addr *d_addr, __be16 d_port);
+struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p);
struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb,
struct ip_vs_protocol *pp,
@@ -658,11 +675,10 @@ static inline void __ip_vs_conn_put(stru
extern void ip_vs_conn_put(struct ip_vs_conn *cp);
extern void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport);
-extern struct ip_vs_conn *
-ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport,
- const union nf_inet_addr *vaddr, __be16 vport,
- const union nf_inet_addr *daddr, __be16 dport, unsigned flags,
- struct ip_vs_dest *dest);
+struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p,
+ const union nf_inet_addr *daddr,
+ __be16 dport, unsigned flags,
+ struct ip_vs_dest *dest);
extern void ip_vs_conn_expire_now(struct ip_vs_conn *cp);
extern const char * ip_vs_state_name(__u16 proto, int state);
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_conn.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_conn.c 2010-10-04 17:00:28.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_conn.c 2010-10-04 17:49:20.000000000 +0900
@@ -218,27 +218,26 @@ static inline int ip_vs_conn_unhash(stru
/*
* Gets ip_vs_conn associated with supplied parameters in the ip_vs_conn_tab.
* Called for pkts coming from OUTside-to-INside.
- * s_addr, s_port: pkt source address (foreign host)
- * d_addr, d_port: pkt dest address (load balancer)
+ * p->caddr, p->cport: pkt source address (foreign host)
+ * p->vaddr, p->vport: pkt dest address (load balancer)
*/
-static inline struct ip_vs_conn *__ip_vs_conn_in_get
-(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port,
- const union nf_inet_addr *d_addr, __be16 d_port)
+static inline struct ip_vs_conn *
+__ip_vs_conn_in_get(const struct ip_vs_conn_param *p)
{
unsigned hash;
struct ip_vs_conn *cp;
- hash = ip_vs_conn_hashkey(af, protocol, s_addr, s_port);
+ hash = ip_vs_conn_hashkey(p->af, p->protocol, p->caddr, p->cport);
ct_read_lock(hash);
list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
- if (cp->af == af &&
- ip_vs_addr_equal(af, s_addr, &cp->caddr) &&
- ip_vs_addr_equal(af, d_addr, &cp->vaddr) &&
- s_port == cp->cport && d_port == cp->vport &&
- ((!s_port) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) &&
- protocol == cp->protocol) {
+ if (cp->af == p->af &&
+ ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) &&
+ ip_vs_addr_equal(p->af, p->vaddr, &cp->vaddr) &&
+ p->cport == cp->cport && p->vport == cp->vport &&
+ ((!p->cport) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) &&
+ p->protocol == cp->protocol) {
/* HIT */
atomic_inc(&cp->refcnt);
ct_read_unlock(hash);
@@ -251,71 +250,82 @@ static inline struct ip_vs_conn *__ip_vs
return NULL;
}
-struct ip_vs_conn *ip_vs_conn_in_get
-(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port,
- const union nf_inet_addr *d_addr, __be16 d_port)
+struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p)
{
struct ip_vs_conn *cp;
- cp = __ip_vs_conn_in_get(af, protocol, s_addr, s_port, d_addr, d_port);
- if (!cp && atomic_read(&ip_vs_conn_no_cport_cnt))
- cp = __ip_vs_conn_in_get(af, protocol, s_addr, 0, d_addr,
- d_port);
+ cp = __ip_vs_conn_in_get(p);
+ if (!cp && atomic_read(&ip_vs_conn_no_cport_cnt)) {
+ struct ip_vs_conn_param cport_zero_p = *p;
+ cport_zero_p.cport = 0;
+ cp = __ip_vs_conn_in_get(&cport_zero_p);
+ }
IP_VS_DBG_BUF(9, "lookup/in %s %s:%d->%s:%d %s\n",
- ip_vs_proto_name(protocol),
- IP_VS_DBG_ADDR(af, s_addr), ntohs(s_port),
- IP_VS_DBG_ADDR(af, d_addr), ntohs(d_port),
+ ip_vs_proto_name(p->protocol),
+ IP_VS_DBG_ADDR(p->af, p->caddr), ntohs(p->cport),
+ IP_VS_DBG_ADDR(p->af, p->vaddr), ntohs(p->vport),
cp ? "hit" : "not hit");
return cp;
}
+static int
+ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb,
+ const struct ip_vs_iphdr *iph,
+ unsigned int proto_off, int inverse,
+ struct ip_vs_conn_param *p)
+{
+ __be16 _ports[2], *pptr;
+
+ pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
+ if (pptr == NULL)
+ return 1;
+
+ if (likely(!inverse))
+ ip_vs_conn_fill_param(af, iph->protocol, &iph->saddr, pptr[0],
+ &iph->daddr, pptr[1], p);
+ else
+ ip_vs_conn_fill_param(af, iph->protocol, &iph->daddr, pptr[1],
+ &iph->saddr, pptr[0], p);
+ return 0;
+}
+
struct ip_vs_conn *
ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
struct ip_vs_protocol *pp,
const struct ip_vs_iphdr *iph,
unsigned int proto_off, int inverse)
{
- __be16 _ports[2], *pptr;
+ struct ip_vs_conn_param p;
- pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
- if (pptr == NULL)
+ if (ip_vs_conn_fill_param_proto(af, skb, iph, proto_off, inverse, &p))
return NULL;
- if (likely(!inverse))
- return ip_vs_conn_in_get(af, iph->protocol,
- &iph->saddr, pptr[0],
- &iph->daddr, pptr[1]);
- else
- return ip_vs_conn_in_get(af, iph->protocol,
- &iph->daddr, pptr[1],
- &iph->saddr, pptr[0]);
+ return ip_vs_conn_in_get(&p);
}
EXPORT_SYMBOL_GPL(ip_vs_conn_in_get_proto);
/* Get reference to connection template */
-struct ip_vs_conn *ip_vs_ct_in_get
-(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port,
- const union nf_inet_addr *d_addr, __be16 d_port)
+struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p)
{
unsigned hash;
struct ip_vs_conn *cp;
- hash = ip_vs_conn_hashkey(af, protocol, s_addr, s_port);
+ hash = ip_vs_conn_hashkey(p->af, p->protocol, p->caddr, p->cport);
ct_read_lock(hash);
list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
- if (cp->af == af &&
- ip_vs_addr_equal(af, s_addr, &cp->caddr) &&
+ if (cp->af == p->af &&
+ ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) &&
/* protocol should only be IPPROTO_IP if
- * d_addr is a fwmark */
- ip_vs_addr_equal(protocol == IPPROTO_IP ? AF_UNSPEC : af,
- d_addr, &cp->vaddr) &&
- s_port == cp->cport && d_port == cp->vport &&
+ * p->vaddr is a fwmark */
+ ip_vs_addr_equal(p->protocol == IPPROTO_IP ? AF_UNSPEC :
+ p->af, p->vaddr, &cp->vaddr) &&
+ p->cport == cp->cport && p->vport == cp->vport &&
cp->flags & IP_VS_CONN_F_TEMPLATE &&
- protocol == cp->protocol) {
+ p->protocol == cp->protocol) {
/* HIT */
atomic_inc(&cp->refcnt);
goto out;
@@ -327,23 +337,19 @@ struct ip_vs_conn *ip_vs_ct_in_get
ct_read_unlock(hash);
IP_VS_DBG_BUF(9, "template lookup/in %s %s:%d->%s:%d %s\n",
- ip_vs_proto_name(protocol),
- IP_VS_DBG_ADDR(af, s_addr), ntohs(s_port),
- IP_VS_DBG_ADDR(af, d_addr), ntohs(d_port),
+ ip_vs_proto_name(p->protocol),
+ IP_VS_DBG_ADDR(p->af, p->caddr), ntohs(p->cport),
+ IP_VS_DBG_ADDR(p->af, p->vaddr), ntohs(p->vport),
cp ? "hit" : "not hit");
return cp;
}
-/*
- * Gets ip_vs_conn associated with supplied parameters in the ip_vs_conn_tab.
- * Called for pkts coming from inside-to-OUTside.
- * s_addr, s_port: pkt source address (inside host)
- * d_addr, d_port: pkt dest address (foreign host)
- */
-struct ip_vs_conn *ip_vs_conn_out_get
-(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port,
- const union nf_inet_addr *d_addr, __be16 d_port)
+/* Gets ip_vs_conn associated with supplied parameters in the ip_vs_conn_tab.
+ * Called for pkts coming from inside-to-OUTside.
+ * p->caddr, p->cport: pkt source address (inside host)
+ * p->vaddr, p->vport: pkt dest address (foreign host) */
+struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
{
unsigned hash;
struct ip_vs_conn *cp, *ret=NULL;
@@ -351,16 +357,16 @@ struct ip_vs_conn *ip_vs_conn_out_get
/*
* Check for "full" addressed entries
*/
- hash = ip_vs_conn_hashkey(af, protocol, d_addr, d_port);
+ hash = ip_vs_conn_hashkey(p->af, p->protocol, p->vaddr, p->vport);
ct_read_lock(hash);
list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
- if (cp->af == af &&
- ip_vs_addr_equal(af, d_addr, &cp->caddr) &&
- ip_vs_addr_equal(af, s_addr, &cp->daddr) &&
- d_port == cp->cport && s_port == cp->dport &&
- protocol == cp->protocol) {
+ if (cp->af == p->af &&
+ ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) &&
+ ip_vs_addr_equal(p->af, p->caddr, &cp->daddr) &&
+ p->vport == cp->cport && p->cport == cp->dport &&
+ p->protocol == cp->protocol) {
/* HIT */
atomic_inc(&cp->refcnt);
ret = cp;
@@ -371,9 +377,9 @@ struct ip_vs_conn *ip_vs_conn_out_get
ct_read_unlock(hash);
IP_VS_DBG_BUF(9, "lookup/out %s %s:%d->%s:%d %s\n",
- ip_vs_proto_name(protocol),
- IP_VS_DBG_ADDR(af, s_addr), ntohs(s_port),
- IP_VS_DBG_ADDR(af, d_addr), ntohs(d_port),
+ ip_vs_proto_name(p->protocol),
+ IP_VS_DBG_ADDR(p->af, p->caddr), ntohs(p->cport),
+ IP_VS_DBG_ADDR(p->af, p->vaddr), ntohs(p->vport),
ret ? "hit" : "not hit");
return ret;
@@ -385,20 +391,12 @@ ip_vs_conn_out_get_proto(int af, const s
const struct ip_vs_iphdr *iph,
unsigned int proto_off, int inverse)
{
- __be16 _ports[2], *pptr;
+ struct ip_vs_conn_param p;
- pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
- if (pptr == NULL)
+ if (ip_vs_conn_fill_param_proto(af, skb, iph, proto_off, inverse, &p))
return NULL;
- if (likely(!inverse))
- return ip_vs_conn_out_get(af, iph->protocol,
- &iph->saddr, pptr[0],
- &iph->daddr, pptr[1]);
- else
- return ip_vs_conn_out_get(af, iph->protocol,
- &iph->daddr, pptr[1],
- &iph->saddr, pptr[0]);
+ return ip_vs_conn_out_get(&p);
}
EXPORT_SYMBOL_GPL(ip_vs_conn_out_get_proto);
@@ -758,13 +756,12 @@ void ip_vs_conn_expire_now(struct ip_vs_
* Create a new connection entry and hash it into the ip_vs_conn_tab
*/
struct ip_vs_conn *
-ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport,
- const union nf_inet_addr *vaddr, __be16 vport,
+ip_vs_conn_new(const struct ip_vs_conn_param *p,
const union nf_inet_addr *daddr, __be16 dport, unsigned flags,
struct ip_vs_dest *dest)
{
struct ip_vs_conn *cp;
- struct ip_vs_protocol *pp = ip_vs_proto_get(proto);
+ struct ip_vs_protocol *pp = ip_vs_proto_get(p->protocol);
cp = kmem_cache_zalloc(ip_vs_conn_cachep, GFP_ATOMIC);
if (cp == NULL) {
@@ -774,14 +771,14 @@ ip_vs_conn_new(int af, int proto, const
INIT_LIST_HEAD(&cp->c_list);
setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp);
- cp->af = af;
- cp->protocol = proto;
- ip_vs_addr_copy(af, &cp->caddr, caddr);
- cp->cport = cport;
- ip_vs_addr_copy(af, &cp->vaddr, vaddr);
- cp->vport = vport;
+ cp->af = p->af;
+ cp->protocol = p->protocol;
+ ip_vs_addr_copy(p->af, &cp->caddr, p->caddr);
+ cp->cport = p->cport;
+ ip_vs_addr_copy(p->af, &cp->vaddr, p->vaddr);
+ cp->vport = p->vport;
/* proto should only be IPPROTO_IP if d_addr is a fwmark */
- ip_vs_addr_copy(proto == IPPROTO_IP ? AF_UNSPEC : af,
+ ip_vs_addr_copy(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af,
&cp->daddr, daddr);
cp->dport = dport;
cp->flags = flags;
@@ -810,7 +807,7 @@ ip_vs_conn_new(int af, int proto, const
/* Bind its packet transmitter */
#ifdef CONFIG_IP_VS_IPV6
- if (af == AF_INET6)
+ if (p->af == AF_INET6)
ip_vs_bind_xmit_v6(cp);
else
#endif
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_core.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_core.c 2010-10-04 17:00:45.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_core.c 2010-10-04 17:49:20.000000000 +0900
@@ -193,14 +193,11 @@ ip_vs_sched_persist(struct ip_vs_service
struct ip_vs_iphdr iph;
struct ip_vs_dest *dest;
struct ip_vs_conn *ct;
- int protocol = iph.protocol;
__be16 dport = 0; /* destination port to forward */
- __be16 vport = 0; /* virtual service port */
unsigned int flags;
+ struct ip_vs_conn_param param;
union nf_inet_addr snet; /* source network of the client,
after masking */
- const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) };
- const union nf_inet_addr *vaddr = &iph.daddr;
ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
@@ -232,6 +229,11 @@ ip_vs_sched_persist(struct ip_vs_service
* is created for other persistent services.
*/
{
+ int protocol = iph.protocol;
+ const union nf_inet_addr *vaddr = &iph.daddr;
+ const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) };
+ __be16 vport = 0;
+
if (ports[1] == svc->port) {
/* non-FTP template:
* <protocol, caddr, 0, vaddr, vport, daddr, dport>
@@ -253,11 +255,12 @@ ip_vs_sched_persist(struct ip_vs_service
vaddr = &fwmark;
}
}
+ ip_vs_conn_fill_param(svc->af, protocol, &snet, 0,
+ vaddr, vport, ¶m);
}
/* Check if a template already exists */
- ct = ip_vs_ct_in_get(svc->af, protocol, &snet, 0, vaddr, vport);
-
+ ct = ip_vs_ct_in_get(¶m);
if (!ct || !ip_vs_check_template(ct)) {
/* No template found or the dest of the connection
* template is not available.
@@ -272,8 +275,7 @@ ip_vs_sched_persist(struct ip_vs_service
dport = dest->port;
/* Create a template */
- ct = ip_vs_conn_new(svc->af, protocol, &snet, 0,vaddr, vport,
- &dest->addr, dport,
+ ct = ip_vs_conn_new(¶m, &dest->addr, dport,
IP_VS_CONN_F_TEMPLATE, dest);
if (ct == NULL)
return NULL;
@@ -294,12 +296,9 @@ ip_vs_sched_persist(struct ip_vs_service
/*
* Create a new connection according to the template
*/
- cp = ip_vs_conn_new(svc->af, iph.protocol,
- &iph.saddr, ports[0],
- &iph.daddr, ports[1],
- &dest->addr, dport,
- flags,
- dest);
+ ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr, ports[0],
+ &iph.daddr, ports[1], ¶m);
+ cp = ip_vs_conn_new(¶m, &dest->addr, dport, flags, dest);
if (cp == NULL) {
ip_vs_conn_put(ct);
return NULL;
@@ -366,14 +365,16 @@ ip_vs_schedule(struct ip_vs_service *svc
/*
* Create a connection entry.
*/
- cp = ip_vs_conn_new(svc->af, iph.protocol,
- &iph.saddr, pptr[0],
- &iph.daddr, pptr[1],
- &dest->addr, dest->port ? dest->port : pptr[1],
- flags,
- dest);
- if (cp == NULL)
- return NULL;
+ {
+ struct ip_vs_conn_param p;
+ ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr,
+ pptr[0], &iph.daddr, pptr[1], &p);
+ cp = ip_vs_conn_new(&p, &dest->addr,
+ dest->port ? dest->port : pptr[1],
+ flags, dest);
+ if (!cp)
+ return NULL;
+ }
IP_VS_DBG_BUF(6, "Schedule fwd:%c c:%s:%u v:%s:%u "
"d:%s:%u conn->flags:%X conn->refcnt:%d\n",
@@ -429,14 +430,17 @@ int ip_vs_leave(struct ip_vs_service *sv
/* create a new connection entry */
IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__);
- cp = ip_vs_conn_new(svc->af, iph.protocol,
- &iph.saddr, pptr[0],
- &iph.daddr, pptr[1],
- &daddr, 0,
- IP_VS_CONN_F_BYPASS | flags,
- NULL);
- if (cp == NULL)
- return NF_DROP;
+ {
+ struct ip_vs_conn_param p;
+ ip_vs_conn_fill_param(svc->af, iph.protocol,
+ &iph.saddr, pptr[0],
+ &iph.daddr, pptr[1], &p);
+ cp = ip_vs_conn_new(&p, &daddr, 0,
+ IP_VS_CONN_F_BYPASS | flags,
+ NULL);
+ if (!cp)
+ return NF_DROP;
+ }
/* statistics */
ip_vs_in_stats(cp, skb);
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_ftp.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_ftp.c 2010-10-04 16:58:31.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_ftp.c 2010-10-04 17:00:45.000000000 +0900
@@ -195,13 +195,17 @@ static int ip_vs_ftp_out(struct ip_vs_ap
/*
* Now update or create an connection entry for it
*/
- n_cp = ip_vs_conn_out_get(AF_INET, iph->protocol, &from, port,
- &cp->caddr, 0);
+ {
+ struct ip_vs_conn_param p;
+ ip_vs_conn_fill_param(AF_INET, iph->protocol,
+ &from, port, &cp->caddr, 0, &p);
+ n_cp = ip_vs_conn_out_get(&p);
+ }
if (!n_cp) {
- n_cp = ip_vs_conn_new(AF_INET, IPPROTO_TCP,
- &cp->caddr, 0,
- &cp->vaddr, port,
- &from, port,
+ struct ip_vs_conn_param p;
+ ip_vs_conn_fill_param(AF_INET, IPPROTO_TCP, &cp->caddr,
+ 0, &cp->vaddr, port, &p);
+ n_cp = ip_vs_conn_new(&p, &from, port,
IP_VS_CONN_F_NO_CPORT |
IP_VS_CONN_F_NFCT,
cp->dest);
@@ -347,21 +351,22 @@ static int ip_vs_ftp_in(struct ip_vs_app
ip_vs_proto_name(iph->protocol),
&to.ip, ntohs(port), &cp->vaddr.ip, 0);
- n_cp = ip_vs_conn_in_get(AF_INET, iph->protocol,
- &to, port,
- &cp->vaddr, htons(ntohs(cp->vport)-1));
- if (!n_cp) {
- n_cp = ip_vs_conn_new(AF_INET, IPPROTO_TCP,
- &to, port,
+ {
+ struct ip_vs_conn_param p;
+ ip_vs_conn_fill_param(AF_INET, iph->protocol, &to, port,
&cp->vaddr, htons(ntohs(cp->vport)-1),
- &cp->daddr, htons(ntohs(cp->dport)-1),
- IP_VS_CONN_F_NFCT,
- cp->dest);
- if (!n_cp)
- return 0;
+ &p);
+ n_cp = ip_vs_conn_in_get(&p);
+ if (!n_cp) {
+ n_cp = ip_vs_conn_new(&p, &cp->daddr,
+ htons(ntohs(cp->dport)-1),
+ IP_VS_CONN_F_NFCT, cp->dest);
+ if (!n_cp)
+ return 0;
- /* add its controller */
- ip_vs_control_add(n_cp, cp);
+ /* add its controller */
+ ip_vs_control_add(n_cp, cp);
+ }
}
/*
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_nfct.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_nfct.c 2010-10-04 16:58:31.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_nfct.c 2010-10-04 17:00:45.000000000 +0900
@@ -140,6 +140,7 @@ static void ip_vs_nfct_expect_callback(s
{
struct nf_conntrack_tuple *orig, new_reply;
struct ip_vs_conn *cp;
+ struct ip_vs_conn_param p;
if (exp->tuple.src.l3num != PF_INET)
return;
@@ -154,9 +155,10 @@ static void ip_vs_nfct_expect_callback(s
/* RS->CLIENT */
orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
- cp = ip_vs_conn_out_get(exp->tuple.src.l3num, orig->dst.protonum,
- &orig->src.u3, orig->src.u.tcp.port,
- &orig->dst.u3, orig->dst.u.tcp.port);
+ ip_vs_conn_fill_param(exp->tuple.src.l3num, orig->dst.protonum,
+ &orig->src.u3, orig->src.u.tcp.port,
+ &orig->dst.u3, orig->dst.u.tcp.port, &p);
+ cp = ip_vs_conn_out_get(&p);
if (cp) {
/* Change reply CLIENT->RS to CLIENT->VS */
new_reply = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
@@ -176,9 +178,7 @@ static void ip_vs_nfct_expect_callback(s
}
/* CLIENT->VS */
- cp = ip_vs_conn_in_get(exp->tuple.src.l3num, orig->dst.protonum,
- &orig->src.u3, orig->src.u.tcp.port,
- &orig->dst.u3, orig->dst.u.tcp.port);
+ cp = ip_vs_conn_in_get(&p);
if (cp) {
/* Change reply VS->CLIENT to RS->CLIENT */
new_reply = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_proto_ah_esp.c 2010-10-04 16:58:31.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_proto_ah_esp.c 2010-10-04 17:00:45.000000000 +0900
@@ -40,6 +40,19 @@ struct isakmp_hdr {
#define PORT_ISAKMP 500
+static void
+ah_esp_conn_fill_param_proto(int af, const struct ip_vs_iphdr *iph,
+ int inverse, struct ip_vs_conn_param *p)
+{
+ if (likely(!inverse))
+ ip_vs_conn_fill_param(af, IPPROTO_UDP,
+ &iph->saddr, htons(PORT_ISAKMP),
+ &iph->daddr, htons(PORT_ISAKMP), p);
+ else
+ ip_vs_conn_fill_param(af, IPPROTO_UDP,
+ &iph->daddr, htons(PORT_ISAKMP),
+ &iph->saddr, htons(PORT_ISAKMP), p);
+}
static struct ip_vs_conn *
ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp,
@@ -47,21 +60,10 @@ ah_esp_conn_in_get(int af, const struct
int inverse)
{
struct ip_vs_conn *cp;
+ struct ip_vs_conn_param p;
- if (likely(!inverse)) {
- cp = ip_vs_conn_in_get(af, IPPROTO_UDP,
- &iph->saddr,
- htons(PORT_ISAKMP),
- &iph->daddr,
- htons(PORT_ISAKMP));
- } else {
- cp = ip_vs_conn_in_get(af, IPPROTO_UDP,
- &iph->daddr,
- htons(PORT_ISAKMP),
- &iph->saddr,
- htons(PORT_ISAKMP));
- }
-
+ ah_esp_conn_fill_param_proto(af, iph, inverse, &p);
+ cp = ip_vs_conn_in_get(&p);
if (!cp) {
/*
* We are not sure if the packet is from our
@@ -87,21 +89,10 @@ ah_esp_conn_out_get(int af, const struct
int inverse)
{
struct ip_vs_conn *cp;
+ struct ip_vs_conn_param p;
- if (likely(!inverse)) {
- cp = ip_vs_conn_out_get(af, IPPROTO_UDP,
- &iph->saddr,
- htons(PORT_ISAKMP),
- &iph->daddr,
- htons(PORT_ISAKMP));
- } else {
- cp = ip_vs_conn_out_get(af, IPPROTO_UDP,
- &iph->daddr,
- htons(PORT_ISAKMP),
- &iph->saddr,
- htons(PORT_ISAKMP));
- }
-
+ ah_esp_conn_fill_param_proto(af, iph, inverse, &p);
+ cp = ip_vs_conn_out_get(&p);
if (!cp) {
IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for inout packet "
"%s%s %s->%s\n",
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_sync.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_sync.c 2010-10-04 16:58:31.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_sync.c 2010-10-04 17:49:20.000000000 +0900
@@ -301,6 +301,7 @@ static void ip_vs_process_message(const
struct ip_vs_conn *cp;
struct ip_vs_protocol *pp;
struct ip_vs_dest *dest;
+ struct ip_vs_conn_param param;
char *p;
int i;
@@ -370,18 +371,17 @@ static void ip_vs_process_message(const
}
}
- if (!(flags & IP_VS_CONN_F_TEMPLATE))
- cp = ip_vs_conn_in_get(AF_INET, s->protocol,
- (union nf_inet_addr *)&s->caddr,
- s->cport,
- (union nf_inet_addr *)&s->vaddr,
- s->vport);
- else
- cp = ip_vs_ct_in_get(AF_INET, s->protocol,
- (union nf_inet_addr *)&s->caddr,
- s->cport,
- (union nf_inet_addr *)&s->vaddr,
- s->vport);
+ {
+ ip_vs_conn_fill_param(AF_INET, s->protocol,
+ (union nf_inet_addr *)&s->caddr,
+ s->cport,
+ (union nf_inet_addr *)&s->vaddr,
+ s->vport, ¶m);
+ if (!(flags & IP_VS_CONN_F_TEMPLATE))
+ cp = ip_vs_conn_in_get(¶m);
+ else
+ cp = ip_vs_ct_in_get(¶m);
+ }
if (!cp) {
/*
* Find the appropriate destination for the connection.
@@ -406,14 +406,9 @@ static void ip_vs_process_message(const
else
flags &= ~IP_VS_CONN_F_INACTIVE;
}
- cp = ip_vs_conn_new(AF_INET, s->protocol,
- (union nf_inet_addr *)&s->caddr,
- s->cport,
- (union nf_inet_addr *)&s->vaddr,
- s->vport,
+ cp = ip_vs_conn_new(¶m,
(union nf_inet_addr *)&s->daddr,
- s->dport,
- flags, dest);
+ s->dport, flags, dest);
if (dest)
atomic_dec(&dest->refcnt);
if (!cp) {
^ permalink raw reply
* [patch v4 03/12] IPVS: compact ip_vs_sched_persist()
From: Simon Horman @ 2010-10-04 9:03 UTC (permalink / raw)
To: lvs-devel, netdev, netfilter, netfilter-devel
Cc: Jan Engelhardt, Stephen Hemminger, Wensong Zhang,
Julian Anastasov, Patrick McHardy
In-Reply-To: <20101004090352.966809749@akiko.akashicho.tokyo.vergenet.net>
[-- Attachment #1: 0003-IPVS-compact-ip_vs_sched_persist.patch --]
[-- Type: text/plain, Size: 5897 bytes --]
Compact ip_vs_sched_persist() by setting up parameters
and calling functions once.
Signed-off-by: Simon Horman <horms@verge.net.au>
Acked-by: Julian Anastasov <ja@ssi.bg>
---
v2
* Make "union nf_inet_addr fwmark" const
* Don't remove the comment next to the declaration of dport
* Add a comment to the declaration of vport
v3
* As suggested by Julian Anastasov
- Correct dport logic
Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_core.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_core.c 2010-10-02 10:54:57.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_core.c 2010-10-02 11:04:04.000000000 +0900
@@ -193,10 +193,14 @@ ip_vs_sched_persist(struct ip_vs_service
struct ip_vs_iphdr iph;
struct ip_vs_dest *dest;
struct ip_vs_conn *ct;
- __be16 dport; /* destination port to forward */
+ int protocol = iph.protocol;
+ __be16 dport = 0; /* destination port to forward */
+ __be16 vport = 0; /* virtual service port */
unsigned int flags;
union nf_inet_addr snet; /* source network of the client,
after masking */
+ const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) };
+ const union nf_inet_addr *vaddr = &iph.daddr;
ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
@@ -227,119 +231,61 @@ ip_vs_sched_persist(struct ip_vs_service
* service, and a template like <caddr, 0, vaddr, vport, daddr, dport>
* is created for other persistent services.
*/
- if (ports[1] == svc->port) {
- /* Check if a template already exists */
- if (svc->port != FTPPORT)
- ct = ip_vs_ct_in_get(svc->af, iph.protocol, &snet, 0,
- &iph.daddr, ports[1]);
- else
- ct = ip_vs_ct_in_get(svc->af, iph.protocol, &snet, 0,
- &iph.daddr, 0);
-
- if (!ct || !ip_vs_check_template(ct)) {
- /*
- * No template found or the dest of the connection
- * template is not available.
- */
- dest = svc->scheduler->schedule(svc, skb);
- if (dest == NULL) {
- IP_VS_DBG(1, "p-schedule: no dest found.\n");
- return NULL;
- }
-
- /*
- * Create a template like <protocol,caddr,0,
- * vaddr,vport,daddr,dport> for non-ftp service,
- * and <protocol,caddr,0,vaddr,0,daddr,0>
- * for ftp service.
+ {
+ if (ports[1] == svc->port) {
+ /* non-FTP template:
+ * <protocol, caddr, 0, vaddr, vport, daddr, dport>
+ * FTP template:
+ * <protocol, caddr, 0, vaddr, 0, daddr, 0>
*/
if (svc->port != FTPPORT)
- ct = ip_vs_conn_new(svc->af, iph.protocol,
- &snet, 0,
- &iph.daddr,
- ports[1],
- &dest->addr, dest->port,
- IP_VS_CONN_F_TEMPLATE,
- dest);
- else
- ct = ip_vs_conn_new(svc->af, iph.protocol,
- &snet, 0,
- &iph.daddr, 0,
- &dest->addr, 0,
- IP_VS_CONN_F_TEMPLATE,
- dest);
- if (ct == NULL)
- return NULL;
-
- ct->timeout = svc->timeout;
+ vport = ports[1];
} else {
- /* set destination with the found template */
- dest = ct->dest;
- }
- dport = dest->port;
- } else {
- /*
- * Note: persistent fwmark-based services and persistent
- * port zero service are handled here.
- * fwmark template: <IPPROTO_IP,caddr,0,fwmark,0,daddr,0>
- * port zero template: <protocol,caddr,0,vaddr,0,daddr,0>
- */
- if (svc->fwmark) {
- union nf_inet_addr fwmark = {
- .ip = htonl(svc->fwmark)
- };
-
- ct = ip_vs_ct_in_get(svc->af, IPPROTO_IP, &snet, 0,
- &fwmark, 0);
- } else
- ct = ip_vs_ct_in_get(svc->af, iph.protocol, &snet, 0,
- &iph.daddr, 0);
-
- if (!ct || !ip_vs_check_template(ct)) {
- /*
- * If it is not persistent port zero, return NULL,
- * otherwise create a connection template.
+ /* Note: persistent fwmark-based services and
+ * persistent port zero service are handled here.
+ * fwmark template:
+ * <IPPROTO_IP,caddr,0,fwmark,0,daddr,0>
+ * port zero template:
+ * <protocol,caddr,0,vaddr,0,daddr,0>
*/
- if (svc->port)
- return NULL;
-
- dest = svc->scheduler->schedule(svc, skb);
- if (dest == NULL) {
- IP_VS_DBG(1, "p-schedule: no dest found.\n");
- return NULL;
+ if (svc->fwmark) {
+ protocol = IPPROTO_IP;
+ vaddr = &fwmark;
}
+ }
+ }
- /*
- * Create a template according to the service
- */
- if (svc->fwmark) {
- union nf_inet_addr fwmark = {
- .ip = htonl(svc->fwmark)
- };
-
- ct = ip_vs_conn_new(svc->af, IPPROTO_IP,
- &snet, 0,
- &fwmark, 0,
- &dest->addr, 0,
- IP_VS_CONN_F_TEMPLATE,
- dest);
- } else
- ct = ip_vs_conn_new(svc->af, iph.protocol,
- &snet, 0,
- &iph.daddr, 0,
- &dest->addr, 0,
- IP_VS_CONN_F_TEMPLATE,
- dest);
- if (ct == NULL)
- return NULL;
+ /* Check if a template already exists */
+ ct = ip_vs_ct_in_get(svc->af, protocol, &snet, 0, vaddr, vport);
- ct->timeout = svc->timeout;
- } else {
- /* set destination with the found template */
- dest = ct->dest;
+ if (!ct || !ip_vs_check_template(ct)) {
+ /* No template found or the dest of the connection
+ * template is not available.
+ */
+ dest = svc->scheduler->schedule(svc, skb);
+ if (!dest) {
+ IP_VS_DBG(1, "p-schedule: no dest found.\n");
+ return NULL;
}
- dport = ports[1];
- }
+
+ if (ports[1] == svc->port && svc->port != FTPPORT)
+ dport = dest->port;
+
+ /* Create a template */
+ ct = ip_vs_conn_new(svc->af, protocol, &snet, 0,vaddr, vport,
+ &dest->addr, dport,
+ IP_VS_CONN_F_TEMPLATE, dest);
+ if (ct == NULL)
+ return NULL;
+
+ ct->timeout = svc->timeout;
+ } else
+ /* set destination with the found template */
+ dest = ct->dest;
+
+ dport = ports[1];
+ if (dport == svc->port && dest->port)
+ dport = dest->port;
flags = (svc->flags & IP_VS_SVC_F_ONEPACKET
&& iph.protocol == IPPROTO_UDP)?
^ permalink raw reply
* [patch v4 01/12] netfilter: nf_conntrack_sip: Allow ct_sip_get_header() to be called with a null ct argument
From: Simon Horman @ 2010-10-04 9:03 UTC (permalink / raw)
To: lvs-devel, netdev, netfilter, netfilter-devel
Cc: Jan Engelhardt, Stephen Hemminger, Wensong Zhang,
Julian Anastasov, Patrick McHardy
In-Reply-To: <20101004090352.966809749@akiko.akashicho.tokyo.vergenet.net>
[-- Attachment #1: 0001-netfilter-nf_conntrack_sip-Allow-ct_sip_get_header-t.patch --]
[-- Type: text/plain, Size: 515 bytes --]
Signed-off-by: Simon Horman <horms@verge.net.au>
Acked-by: Julian Anastasov <ja@ssi.bg>
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 53d8922..2fd1ea2 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -152,6 +152,9 @@ static int parse_addr(const struct nf_conn *ct, const char *cp,
const char *end;
int ret = 0;
+ if (!ct)
+ return 0;
+
memset(addr, 0, sizeof(*addr));
switch (nf_ct_l3num(ct)) {
case AF_INET:
--
1.7.1
^ permalink raw reply related
* [patch v4 00/12] IPVS: SIP Persistence Engine
From: Simon Horman @ 2010-10-04 9:03 UTC (permalink / raw)
To: lvs-devel, netdev, netfilter, netfilter-devel
Cc: Jan Engelhardt, Stephen Hemminger, Wensong Zhang,
Julian Anastasov, Patrick McHardy
This patch series adds load-balancing of UDP SIP based on Call-ID to
IPVS as well as a frame-work for extending IPVS to handle alternate
persistence requirements.
REVISIONS
This is v4 of the patch series which addresses the following concerns
raised by Julian Anastasov:
- initialize compat structures to avoid crash in
ip_vs_add_service for pe_name
- fix ip_vs_conn_out_get_proto to properly check the
ip_vs_conn_fill_param_proto result
These changes and changes from previous revisions of this patch series
are noted on a per-patch basis.
I have taken the liberty of including Acked-by: Julian Anastasov <ja@ssi.bg>
although the ack was provided before the two problems above were discovered.
OVERVIEW
The approach that I have taken is what I call persistence engines.
The basic idea being that you can provide a module to LVS that alters
the way that it handles connection templates, which are at the core
of persistence. In particular, an additional key can be added, and
any of the normal IP address, port and protocol information can either
be used or ignored.
In the case of the SIP persistence engine, the only persistence engine, all
the keys used by the default persistence behaviour are used and the callid
is added as an extra key. I originally intended to ignore the cip, but this
can optionally be done by setting the persistence mask (-M) to 0.0.0.0
while allowing the flexibility of other mask values.
It is envisaged that the SIP persistence engine will be used in conjunction
with one-packet scheduling. I'm interested to hear if that doesn't fit your
needs.
CONFIGURATION
A persistence engine is associated with a virtual service
(as are schedulers). I have added the --pe option to the
ivpsadm -A and -E commands to allow the persistence engine
of a virtual service to be added, changed, or deleted.
e.g. ipvsadm -A -u 10.4.3.192:5060 -p 60 -M 0.0.0.0 -o --pe sip
There are no other configuration parameters at this time.
RUNNING
When a connection template is created, if its virtual service
has a persistence engine, then the persistence engine can add
an extra key to the connection template. For the SIP module this
is the callid. More generically, it is known as "pe data". And
both the name of the persistence engine, "pe name", and "pe data"
can be viewed in /proc/net/ip_vs_conn and by passing the
--persistent-conn option to ipvsadm -Lc.
e.g.
# ipvsadm -Lcn --persistent-conn
UDP 00:38 UDP 10.4.3.0:0 10.4.3.192:5060 127.0.0.1:5060 sip 193373839
Here we see a single persistence template (cport is 0), which has been
handled by the sip persistence engine. The pe data (callid) is 193373839.
In the case where the persistence engine can't match a packet for some
reason, the connection will fall back to the normal persistence handling.
This seems reasonable, as that if the packet ought to be dropped, iptables
could be used.
A limited amount of debugging information has been added which
can be enabled using a value of 9 or greater in
/proc/sys/net/ipv4/vs/debug_level
CODE AVAILABILITY
The kernel patches (12) are available in git as the pe-3 branch of
git://git.kernel.org/pub/scm/linux/kernel/git/horms/lvs-test-2.6.git
The ipvsadm patches (2) are available in git as the pe-3 branch of
git://github.com/horms/ipvsadm-test.git
There is no change to the ipvsadm patches since the v2 series
so I will not repost them.
^ permalink raw reply
* [PATCH net-next] net: relax rtnl_dereference()
From: Eric Dumazet @ 2010-10-04 9:00 UTC (permalink / raw)
To: David Miller; +Cc: hadi, netdev, Jarek Poplawski
In-Reply-To: <1286181729.18293.8.camel@edumazet-laptop>
Le lundi 04 octobre 2010 à 10:42 +0200, Eric Dumazet a écrit :
> BTW, rtnl_dereference() should be changed to use
> rcu_dereference_protected() instead of rcu_dereference_check() :
> If RTBL is held, there is no need to force a barrier.
>
[PATCH net-next] net: relax rtnl_dereference()
rtnl_dereference() is used in contexts where RTNL is held, to fetch an
RCU protected pointer.
Updates to this pointer are prevented by RTNL, so we dont need
smp_read_barrier_depends() and the ACCESS_ONCE() provided in
rcu_dereference_check().
rtnl_dereference() is mainly a macro to document the locking invariant.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
include/linux/rtnetlink.h | 10 ++++++----
1 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 68c436b..d3c4efa 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -754,20 +754,22 @@ extern int lockdep_rtnl_is_held(void);
* @p: The pointer to read, prior to dereferencing
*
* Do an rcu_dereference(p), but check caller either holds rcu_read_lock()
- * or RTNL
+ * or RTNL. Note : Please prefer rtnl_dereference() or rcu_dereference()
*/
#define rcu_dereference_rtnl(p) \
rcu_dereference_check(p, rcu_read_lock_held() || \
lockdep_rtnl_is_held())
/**
- * rtnl_dereference - rcu_dereference with debug checking
+ * rtnl_dereference - fetch RCU pointer when updates are prevented by RTNL
* @p: The pointer to read, prior to dereferencing
*
- * Do an rcu_dereference(p), but check caller holds RTNL
+ * Return the value of the specified RCU-protected pointer, but omit
+ * both the smp_read_barrier_depends() and the ACCESS_ONCE(), because
+ * caller holds RTNL.
*/
#define rtnl_dereference(p) \
- rcu_dereference_check(p, lockdep_rtnl_is_held())
+ rcu_dereference_protected(p, lockdep_rtnl_is_held())
extern void rtnetlink_init(void);
extern void __rtnl_unlock(void);
^ permalink raw reply related
* Re: [PATCH] sysctl: fix min/max handling in __do_proc_doulongvec_minmax()
From: Robin Holt @ 2010-10-04 8:59 UTC (permalink / raw)
To: Eric Dumazet
Cc: Andrew Morton, linux-kernel, Robin Holt, Willy Tarreau,
David S. Miller, netdev, James Morris, Hideaki YOSHIFUJI,
Pekka Savola (ipv6), Patrick McHardy, Alexey Kuznetsov
In-Reply-To: <1286025469.2582.1806.camel@edumazet-laptop>
On Sat, Oct 02, 2010 at 03:17:49PM +0200, Eric Dumazet wrote:
> When proc_doulongvec_minmax() is used with an array of longs,
> and no min/max check requested (.extra1 or .extra2 being NULL), we
> dereference a NULL pointer for the second element of the array.
>
> Noticed while doing some changes in network stack for the "16TB problem"
>
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
> ---
> kernel/sysctl.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/kernel/sysctl.c b/kernel/sysctl.c
> index f88552c..4fba86d 100644
> --- a/kernel/sysctl.c
> +++ b/kernel/sysctl.c
> @@ -2500,7 +2500,8 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
> break;
> if (neg)
> continue;
> - if ((min && val < *min) || (max && val > *max))
> + if ((table->extra1 && val < *min) ||
> + (table->extra2 && val > *max))
How about changing:
for (; left && vleft--; i++, min++, max++, first=0) {
into:
for (; left && vleft--; i++, min = min ? min + 1 : NULL, max = max ? max + 1: NULL, first=0) {
That would make min and max correct and reduce the chances somebody in
the future overlooks the fact they are currently filled with garbage.
Robin
^ permalink raw reply
* Re: [PATCH net-next V3] net: dynamic ingress_queue allocation
From: Eric Dumazet @ 2010-10-04 8:42 UTC (permalink / raw)
To: Jarek Poplawski; +Cc: hadi, David Miller, netdev
In-Reply-To: <20101003094221.GA2028@del.dom.local>
Le dimanche 03 octobre 2010 à 11:42 +0200, Jarek Poplawski a écrit :
> I'd consider rcu_dereference_rtnl(). Btw, technically qdisc_lookup()
> doesn't require rtnl, and there was time it was used without it
> (on xmit path).
Hmm, for me, rcu_dereference_rtnl() is a bit lazy.
Either we are a reader and should use rcu_dereference(), or a writer and
RTNL should be held.
Mixing two conditions in a "super macro" is a workaround that we used to
promptly shutup some lockdep splats. Real fix would be to use strict
lockdep conditions, because this better documents the code and the
locking invariants.
BTW, rtnl_dereference() should be changed to use
rcu_dereference_protected() instead of rcu_dereference_check() :
If RTBL is held, there is no need to force a barrier.
> I think you should also add a comment here why this rcu is used, and
> that it changes only once in dev's liftime.
>
This comment was needed in the previous version of the patch, with the
smb_wmb() barrier. Now I switched to regular rcu use, nothing prevents
us to change dev->ingress_queue in flight. Of course there is no current
interest doing so.
^ permalink raw reply
* Re: [PATCHv4 net-next-2.6 4/5] XFRM,IPv6: Add IRO remapping hook in xfrm_input()
From: Herbert Xu @ 2010-10-04 8:40 UTC (permalink / raw)
To: Arnaud Ebalard; +Cc: David S. Miller, Eric Dumazet, Hideaki YOSHIFUJI, netdev
In-Reply-To: <db067c0a2ab679dfb16c84e8509e671fa6c5cb01.1286139129.git.arno@natisbad.org>
On Mon, Oct 04, 2010 at 08:25:23AM +0200, Arnaud Ebalard wrote:
> Add a hook in xfrm_input() to allow IRO remapping to occur when
> an incoming packet matching an existing SA (based on SPI) with
> an unexpected destination or source address is received.
> Because IRO does not consume additional bits in a packet (that's
> the point), there is no way to demultiplex based on something
> like nh or spi. Instead, IRO input handlers (for source and
> destination address remapping) are called upon address mismatch
> during IPsec processing.
> For that to work, we rely on the fact that SPI values generated
> locally are no more linked to destination address (first patch
> of the set) and we postpone a bit the expected address check in
> xfrm_input() (inside xfrm_state_lookup() against daddr param) by
> introducing a call to the input_addr_check() handler from the
> struct xfrm_state_afinfo associated with the address family.
>
> Signed-off-by: Arnaud Ebalard <arno@natisbad.org>
I would prefer for this check to go into x->type->input since
it does not apply to IPsec.
Just because the SPI is unique for inbound SAs, it doesn't mean
that we should ignore the destination IP address in the packet for
IPsec.
I think another way of getting what you want is to simply add
inbound SAs with a zero destination address in your case which
can then be made to match any destination IP address. You can
then follow that up with additional checks in x->type->input.
Cheers,
--
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
* Re: [PATCH] tms380tr: fix long delays in initialization
From: Meelis Roos @ 2010-10-04 8:39 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20101003.200109.226763463.davem@davemloft.net>
> > tms380tr driver tries to use udelay (meaning busy loop) for several half
> > second delays during hardware initialization. Crazy overly long busy
> > wait delays mean no delay at all so driver initialization fails without
> > waiting. Fix it by using msleep() for long delays and leave it to
> > udelay() for short delays.
> >
> > Signed-off-by: Meelis Roos <mroos@linux.ee>
>
> You can't use msleep() here because this code can be invoked
> from interrupts and thus cannot sleep.
I checked these two functions that contain long delays that I changed -
tms380tr_bringup_diags() and tms380tr_init_adapter() - to be called only
from tms380tr_chipset_init() that is only called from tms380tr_open() so
no call paths from interrupts AFAICS. Short delyas from interrupt
context are not changed in any way, they still use udelay().
--
Meelis Roos (mroos@linux.ee)
^ permalink raw reply
* Re: [PATCHv4 net-next-2.6 1/5] XFRM,IPv6: Remove xfrm_spi_hash() dependency on destination address
From: Herbert Xu @ 2010-10-04 8:33 UTC (permalink / raw)
To: Arnaud Ebalard; +Cc: David S. Miller, Eric Dumazet, Hideaki YOSHIFUJI, netdev
In-Reply-To: <5a0e320544e253cc903cfd3292600b6bec044a5f.1286139129.git.arno@natisbad.org>
On Mon, Oct 04, 2010 at 08:25:07AM +0200, Arnaud Ebalard wrote:
>
> At the moment, Linux XFRM stack includes the address when computing
> the hash to perform state lookup by SPI. This patch changes XFRM
> state hash computation to prevent destination address to be
> used. This will later allow finding states for packets w/ mangled
> destination addresses.
I'm fine with doing this for inbound SAs. However, I can't see
how we can do this for outbound SAs where the SPI is chosen by
the remote end.
Incidentally, it appears that our hash could do with some
strengthening.
Cheers,
--
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
* Re: ipvs: Use frag walker helper in SCTP proto support.
From: Simon Horman @ 2010-10-04 7:59 UTC (permalink / raw)
To: David Miller; +Cc: netdev, netfilter-devel, lvs-devel, Patrick McHardy
In-Reply-To: <20101003.234601.232735559.davem@davemloft.net>
On Sun, Oct 03, 2010 at 11:46:01PM -0700, David Miller wrote:
>
> Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Simon Horman <horms@verge.net.au>
Dave, I'm happy for this to go via your tree or Partick's.
I don't believe it conflicts with any of the other changes
that are pending.
^ permalink raw reply
* powerpc, fs_enet: scanning PHY after Linux is up
From: Heiko Schocher @ 2010-10-04 7:32 UTC (permalink / raw)
To: linuxppc-dev; +Cc: devicetree-discuss, Holger Brunck, Detlev Zundel, netdev
Hello all,
we have on the mgcoge arch/powerpc/boot/dts/mgcoge.dts 3 fs_enet
devices. The first is accessible on boot, and so get correct
probed and works fine. For the other two fs_enet devices the PHYs
are on startup in reset, and gets later, through userapplikations,
out of reset ... so, on bootup, this 2 fs_enet devices could
not detect the PHY in drivers/of/of_mdio.c of_mdiobus_register(),
and if we want to use them later, we get for example:
-bash-3.2# ifconfig eth2 172.31.31.33
net eth2: Could not attach to PHY
SIOCSIFFLAGS: No such device
So the problem is, that we cannot rescan the PHYs, if they are
accessible. Also we could not load the fs_enet driver as a module,
because the first port is used fix.
So, first question which comes in my mind, is:
Is detecting the phy in drivers/of/of_mdio.c of_mdiobus_register()
the right place, or should it not better be done, when really
using the port?
But we found another way to solve this issue:
After the PHYs are out of reset, we just have to rescan the PHYs
with (for example PHY with addr 1)
err = mdiobus_scan(bus, 1);
and
of_find_node_by_path("/soc@f0000000/cpm@119c0/mdio@10d40/ethernet-phy@1");
of_node_get(np);
dev_archdata_set_node(&err->dev.archdata, np);
but thats just a hack ...
So, the question is, is there a possibility to solve this problem?
If there is no standard option, what would be with adding a
"scan_phy" file in
/proc/device-tree/soc\@f0000000/cpm\@119c0/mdio\@10d40
(or better destination?)
which with we could rescan a PHY with
"echo addr > /proc/device-tree/soc\@f0000000/cpm\@119c0/mdio\@10d40/scan_phy"
(so there is no need for using of_find_node_by_path(), as we should
have the associated device node here, and can step through the child
nodes with "for_each_child_of_node(np, child)" and check if reg == addr)
or shouldn;t be at least, if the phy couldn;t be found when opening
the port, retrigger a scanning, if the phy now is accessible?
bye,
Heiko
--
DENX Software Engineering GmbH, MD: Wolfgang Denk & Detlev Zundel
HRB 165235 Munich, Office: Kirchenstr.5, D-82194 Groebenzell, Germany
^ permalink raw reply
* Re: [PATCH net-next] net: introduce DST_NOCACHE flag
From: Eric Dumazet @ 2010-10-04 7:19 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20101003.221846.245388012.davem@davemloft.net>
Le dimanche 03 octobre 2010 à 22:18 -0700, David Miller a écrit :
> Cute, and applied, but it shows that we're RCU'd so much of the
> surrounding infrastructure that the neighbour cache is now pretty
> high on the list of things to RCU.
Yes, this is the plan, I began the work friday evening ;)
^ permalink raw reply
* ixgbe: normalize frag_list usage
From: David Miller @ 2010-10-04 6:54 UTC (permalink / raw)
To: jeffrey.t.kirsher; +Cc: jesse.brandeburg, bruce.w.allan, netdev
Signed-off-by: David S. Miller <davem@davemloft.net>
---
Basically I want to get the whole tree to consistently use
the convention that the frag list is built as packets arrive
by using "skb->prev" of the head skb to track the tail member
of the frag list.
This will allow me to do something like:
struct sk_buff {
union {
struct {
struct sk_buff *next;
struct sk_buff *prev;
};
struct {
struct sk_buff *frag_next;
struct sk_buff *frag_tail_tracker;
};
}
...
}
And have all frag_list code use these members consistently.
While doing this patch I noticed that there are some left-over bits in
the IXGBEVF driver that builds these IXGBE style (before my patch)
skb->prev RSC chains.
But nothing other than the RX ring shutdown code processes them, so
likely if they are created they will leak or cause some other kind of
problem.
Please take a look, thanks.
diff --git a/drivers/net/ixgbe/ixgbe.h b/drivers/net/ixgbe/ixgbe.h
index 5cebc37..434c9fa 100644
--- a/drivers/net/ixgbe/ixgbe.h
+++ b/drivers/net/ixgbe/ixgbe.h
@@ -181,6 +181,7 @@ struct ixgbe_ring {
struct ixgbe_queue_stats stats;
unsigned long reinit_state;
int numa_node;
+ struct sk_buff *rsc_skb; /* RSC packet being built */
u64 rsc_count; /* stat for coalesced packets */
u64 rsc_flush; /* stats for flushed packets */
u32 restart_queue; /* track tx queue restarts */
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index c35e13c..43987a4 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -1130,36 +1130,6 @@ static inline u32 ixgbe_get_rsc_count(union ixgbe_adv_rx_desc *rx_desc)
IXGBE_RXDADV_RSCCNT_SHIFT;
}
-/**
- * ixgbe_transform_rsc_queue - change rsc queue into a full packet
- * @skb: pointer to the last skb in the rsc queue
- * @count: pointer to number of packets coalesced in this context
- *
- * This function changes a queue full of hw rsc buffers into a completed
- * packet. It uses the ->prev pointers to find the first packet and then
- * turns it into the frag list owner.
- **/
-static inline struct sk_buff *ixgbe_transform_rsc_queue(struct sk_buff *skb,
- u64 *count)
-{
- unsigned int frag_list_size = 0;
-
- while (skb->prev) {
- struct sk_buff *prev = skb->prev;
- frag_list_size += skb->len;
- skb->prev = NULL;
- skb = prev;
- *count += 1;
- }
-
- skb_shinfo(skb)->frag_list = skb->next;
- skb->next = NULL;
- skb->len += frag_list_size;
- skb->data_len += frag_list_size;
- skb->truesize += frag_list_size;
- return skb;
-}
-
struct ixgbe_rsc_cb {
dma_addr_t dma;
bool delay_unmap;
@@ -1216,10 +1186,13 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
prefetch(skb->data);
rx_buffer_info->skb = NULL;
+ if (!(staterr & IXGBE_RXD_STAT_EOP)) {
+ rx_ring->rsc_skb = skb;
+ rx_ring->rsc_count++;
+ }
if (rx_buffer_info->dma) {
if ((adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) &&
- (!(staterr & IXGBE_RXD_STAT_EOP)) &&
- (!(skb->prev))) {
+ rx_ring->rsc_skb == skb) {
/*
* When HWRSC is enabled, delay unmapping
* of the first packet. It carries the
@@ -1279,9 +1252,12 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
}
if (staterr & IXGBE_RXD_STAT_EOP) {
- if (skb->prev)
- skb = ixgbe_transform_rsc_queue(skb,
- &(rx_ring->rsc_count));
+ if (rx_ring->rsc_skb) {
+ skb = rx_ring->rsc_skb;
+ rx_ring->rsc_skb = NULL;
+
+ skb->prev = NULL;
+ }
if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) {
if (IXGBE_RSC_CB(skb)->delay_unmap) {
dma_unmap_single(&pdev->dev,
@@ -1307,8 +1283,22 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
next_buffer->skb = skb;
next_buffer->dma = 0;
} else {
- skb->next = next_buffer->skb;
- skb->next->prev = skb;
+ struct sk_buff *head = rx_ring->rsc_skb;
+ struct sk_buff *next = next_buffer->skb;
+
+ if (!skb_shinfo(head)->frag_list) {
+ skb_shinfo(head)->frag_list = next;
+ } else {
+ head->prev->next = next;
+ }
+
+ /* ->prev tracks the last skb in the frag_list */
+ head->prev = next;
+ rx_ring->rsc_count++;
+
+ head->len += next->len;
+ head->data_len += next->len;
+ head->truesize += next->len;
}
rx_ring->non_eop_descs++;
goto next_desc;
^ permalink raw reply related
* ipvs: Use frag walker helper in SCTP proto support.
From: David Miller @ 2010-10-04 6:46 UTC (permalink / raw)
To: horms; +Cc: netdev, netfilter-devel
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/netfilter/ipvs/ip_vs_proto_sctp.c | 19 ++++++++++---------
1 files changed, 10 insertions(+), 9 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 4c0855c..2f982a4 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -61,6 +61,7 @@ sctp_snat_handler(struct sk_buff *skb,
{
sctp_sctphdr_t *sctph;
unsigned int sctphoff;
+ struct sk_buff *iter;
__be32 crc32;
#ifdef CONFIG_IP_VS_IPV6
@@ -89,8 +90,8 @@ sctp_snat_handler(struct sk_buff *skb,
/* Calculate the checksum */
crc32 = sctp_start_cksum((u8 *) sctph, skb_headlen(skb) - sctphoff);
- for (skb = skb_shinfo(skb)->frag_list; skb; skb = skb->next)
- crc32 = sctp_update_cksum((u8 *) skb->data, skb_headlen(skb),
+ skb_walk_frags(skb, iter)
+ crc32 = sctp_update_cksum((u8 *) iter->data, skb_headlen(iter),
crc32);
crc32 = sctp_end_cksum(crc32);
sctph->checksum = crc32;
@@ -102,9 +103,9 @@ static int
sctp_dnat_handler(struct sk_buff *skb,
struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
{
-
sctp_sctphdr_t *sctph;
unsigned int sctphoff;
+ struct sk_buff *iter;
__be32 crc32;
#ifdef CONFIG_IP_VS_IPV6
@@ -133,8 +134,8 @@ sctp_dnat_handler(struct sk_buff *skb,
/* Calculate the checksum */
crc32 = sctp_start_cksum((u8 *) sctph, skb_headlen(skb) - sctphoff);
- for (skb = skb_shinfo(skb)->frag_list; skb; skb = skb->next)
- crc32 = sctp_update_cksum((u8 *) skb->data, skb_headlen(skb),
+ skb_walk_frags(skb, iter)
+ crc32 = sctp_update_cksum((u8 *) iter->data, skb_headlen(iter),
crc32);
crc32 = sctp_end_cksum(crc32);
sctph->checksum = crc32;
@@ -145,9 +146,9 @@ sctp_dnat_handler(struct sk_buff *skb,
static int
sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
{
- struct sk_buff *list = skb_shinfo(skb)->frag_list;
unsigned int sctphoff;
struct sctphdr *sh, _sctph;
+ struct sk_buff *iter;
__le32 cmp;
__le32 val;
__u32 tmp;
@@ -166,9 +167,9 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
cmp = sh->checksum;
tmp = sctp_start_cksum((__u8 *) sh, skb_headlen(skb));
- for (; list; list = list->next)
- tmp = sctp_update_cksum((__u8 *) list->data,
- skb_headlen(list), tmp);
+ skb_walk_frags(skb, iter)
+ tmp = sctp_update_cksum((__u8 *) iter->data,
+ skb_headlen(iter), tmp);
val = sctp_end_cksum(tmp);
--
1.7.3.1
^ 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