* [PATCH net-next 6/7] ipmr: advertise new mfc entries via rtnl
From: Nicolas Dichtel @ 2012-12-04 11:13 UTC (permalink / raw)
To: netdev; +Cc: davem, Nicolas Dichtel
In-Reply-To: <1354619621-16016-1-git-send-email-nicolas.dichtel@6wind.com>
This patch allows to monitor mfc activities via rtnetlink.
To avoid parsing two times the mfc oifs, we use maxvif to allocate the rtnl
msg, thus we may allocate some superfluous space.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
net/ipv4/ipmr.c | 64 ++++++++++++++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 59 insertions(+), 5 deletions(-)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 084dac3..a9454cb 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -134,6 +134,8 @@ static int ipmr_cache_report(struct mr_table *mrt,
struct sk_buff *pkt, vifi_t vifi, int assert);
static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
struct mfc_cache *c, struct rtmsg *rtm);
+static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
+ int cmd);
static void mroute_clean_tables(struct mr_table *mrt);
static void ipmr_expire_process(unsigned long arg);
@@ -669,6 +671,7 @@ static void ipmr_expire_process(unsigned long arg)
}
list_del(&c->list);
+ mroute_netlink_event(mrt, c, RTM_DELROUTE);
ipmr_destroy_unres(mrt, c);
}
@@ -1026,6 +1029,7 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb)
atomic_inc(&mrt->cache_resolve_queue_len);
list_add(&c->list, &mrt->mfc_unres_queue);
+ mroute_netlink_event(mrt, c, RTM_NEWROUTE);
if (atomic_read(&mrt->cache_resolve_queue_len) == 1)
mod_timer(&mrt->ipmr_expire_timer, c->mfc_un.unres.expires);
@@ -1060,7 +1064,7 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc)
if (c->mfc_origin == mfc->mfcc_origin.s_addr &&
c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) {
list_del_rcu(&c->list);
-
+ mroute_netlink_event(mrt, c, RTM_DELROUTE);
ipmr_cache_free(c);
return 0;
}
@@ -1095,6 +1099,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
if (!mrtsock)
c->mfc_flags |= MFC_STATIC;
write_unlock_bh(&mrt_lock);
+ mroute_netlink_event(mrt, c, RTM_NEWROUTE);
return 0;
}
@@ -1137,6 +1142,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
ipmr_cache_resolve(net, mrt, uc, c);
ipmr_cache_free(uc);
}
+ mroute_netlink_event(mrt, c, RTM_NEWROUTE);
return 0;
}
@@ -1165,6 +1171,7 @@ static void mroute_clean_tables(struct mr_table *mrt)
if (c->mfc_flags & MFC_STATIC)
continue;
list_del_rcu(&c->list);
+ mroute_netlink_event(mrt, c, RTM_DELROUTE);
ipmr_cache_free(c);
}
}
@@ -1173,6 +1180,7 @@ static void mroute_clean_tables(struct mr_table *mrt)
spin_lock_bh(&mfc_unres_lock);
list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) {
list_del(&c->list);
+ mroute_netlink_event(mrt, c, RTM_DELROUTE);
ipmr_destroy_unres(mrt, c);
}
spin_unlock_bh(&mfc_unres_lock);
@@ -2150,13 +2158,13 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb,
}
static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
- u32 portid, u32 seq, struct mfc_cache *c)
+ u32 portid, u32 seq, struct mfc_cache *c, int cmd)
{
struct nlmsghdr *nlh;
struct rtmsg *rtm;
int err;
- nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI);
+ nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI);
if (nlh == NULL)
return -EMSGSIZE;
@@ -2191,6 +2199,52 @@ nla_put_failure:
return -EMSGSIZE;
}
+static size_t mroute_msgsize(bool unresolved, int maxvif)
+{
+ size_t len =
+ NLMSG_ALIGN(sizeof(struct rtmsg))
+ + nla_total_size(4) /* RTA_TABLE */
+ + nla_total_size(4) /* RTA_SRC */
+ + nla_total_size(4) /* RTA_DST */
+ ;
+
+ if (!unresolved)
+ len = len
+ + nla_total_size(4) /* RTA_IIF */
+ + nla_total_size(0) /* RTA_MULTIPATH */
+ + maxvif * NLA_ALIGN(sizeof(struct rtnexthop))
+ /* RTA_MFC_STATS */
+ + nla_total_size(sizeof(struct rta_mfc_stats))
+ ;
+
+ return len;
+}
+
+static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
+ int cmd)
+{
+ struct net *net = read_pnet(&mrt->net);
+ struct sk_buff *skb;
+ int err = -ENOBUFS;
+
+ skb = nlmsg_new(mroute_msgsize(mfc->mfc_parent >= MAXVIFS, mrt->maxvif),
+ GFP_ATOMIC);
+ if (skb == NULL)
+ goto errout;
+
+ err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd);
+ if (err < 0)
+ goto errout;
+
+ rtnl_notify(skb, net, 0, RTNLGRP_IPV4_MROUTE, NULL, GFP_ATOMIC);
+ return;
+
+errout:
+ kfree_skb(skb);
+ if (err < 0)
+ rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE, err);
+}
+
static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
@@ -2217,7 +2271,7 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
if (ipmr_fill_mroute(mrt, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
- mfc) < 0)
+ mfc, RTM_NEWROUTE) < 0)
goto done;
next_entry:
e++;
@@ -2231,7 +2285,7 @@ next_entry:
if (ipmr_fill_mroute(mrt, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
- mfc) < 0) {
+ mfc, RTM_NEWROUTE) < 0) {
spin_unlock_bh(&mfc_unres_lock);
goto done;
}
--
1.8.0.1
^ permalink raw reply related
* [PATCH net-next 5/7] ipmr/ip6mr: allow to get unresolved cache via netlink
From: Nicolas Dichtel @ 2012-12-04 11:13 UTC (permalink / raw)
To: netdev; +Cc: davem, Nicolas Dichtel
In-Reply-To: <1354619621-16016-1-git-send-email-nicolas.dichtel@6wind.com>
/proc/net/ip[6]_mr_cache allows to get all mfc entries, even if they are put in
the unresolved list (mfc[6]_unres_queue). But only the table RT_TABLE_DEFAULT is
displayed.
This patch adds the parsing of the unresolved list when the dump is made via
rtnetlink, hence each table can be checked.
In IPv6, we set rtm_type in ip6mr_fill_mroute(), because in case of unresolved
mfc __ip6mr_fill_mroute() will not set it. In IPv4, it is already done.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
net/ipv4/ipmr.c | 21 ++++++++++++++++++++-
net/ipv6/ip6mr.c | 22 +++++++++++++++++++++-
2 files changed, 41 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 91782a7..084dac3 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2154,6 +2154,7 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
{
struct nlmsghdr *nlh;
struct rtmsg *rtm;
+ int err;
nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI);
if (nlh == NULL)
@@ -2178,7 +2179,9 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
if (nla_put_be32(skb, RTA_SRC, c->mfc_origin) ||
nla_put_be32(skb, RTA_DST, c->mfc_mcastgrp))
goto nla_put_failure;
- if (__ipmr_fill_mroute(mrt, skb, c, rtm) < 0)
+ err = __ipmr_fill_mroute(mrt, skb, c, rtm);
+ /* do not break the dump if cache is unresolved */
+ if (err < 0 && err != -ENOENT)
goto nla_put_failure;
return nlmsg_end(skb, nlh);
@@ -2221,6 +2224,22 @@ next_entry:
}
e = s_e = 0;
}
+ spin_lock_bh(&mfc_unres_lock);
+ list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) {
+ if (e < s_e)
+ goto next_entry2;
+ if (ipmr_fill_mroute(mrt, skb,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ mfc) < 0) {
+ spin_unlock_bh(&mfc_unres_lock);
+ goto done;
+ }
+next_entry2:
+ e++;
+ }
+ spin_unlock_bh(&mfc_unres_lock);
+ e = s_e = 0;
s_h = 0;
next_table:
t++;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index e9ef38f..175270f 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2235,6 +2235,7 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
{
struct nlmsghdr *nlh;
struct rtmsg *rtm;
+ int err;
nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI);
if (nlh == NULL)
@@ -2248,6 +2249,7 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
rtm->rtm_table = mrt->id;
if (nla_put_u32(skb, RTA_TABLE, mrt->id))
goto nla_put_failure;
+ rtm->rtm_type = RTN_MULTICAST;
rtm->rtm_scope = RT_SCOPE_UNIVERSE;
if (c->mfc_flags & MFC_STATIC)
rtm->rtm_protocol = RTPROT_STATIC;
@@ -2258,7 +2260,9 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
if (nla_put(skb, RTA_SRC, 16, &c->mf6c_origin) ||
nla_put(skb, RTA_DST, 16, &c->mf6c_mcastgrp))
goto nla_put_failure;
- if (__ip6mr_fill_mroute(mrt, skb, c, rtm) < 0)
+ err = __ip6mr_fill_mroute(mrt, skb, c, rtm);
+ /* do not break the dump if cache is unresolved */
+ if (err < 0 && err != -ENOENT)
goto nla_put_failure;
return nlmsg_end(skb, nlh);
@@ -2301,6 +2305,22 @@ next_entry:
}
e = s_e = 0;
}
+ spin_lock_bh(&mfc_unres_lock);
+ list_for_each_entry(mfc, &mrt->mfc6_unres_queue, list) {
+ if (e < s_e)
+ goto next_entry2;
+ if (ip6mr_fill_mroute(mrt, skb,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ mfc) < 0) {
+ spin_unlock_bh(&mfc_unres_lock);
+ goto done;
+ }
+next_entry2:
+ e++;
+ }
+ spin_unlock_bh(&mfc_unres_lock);
+ e = s_e = 0;
s_h = 0;
next_table:
t++;
--
1.8.0.1
^ permalink raw reply related
* [PATCH net-next 7/7] ip6mr: advertise new mfc entries via rtnl
From: Nicolas Dichtel @ 2012-12-04 11:13 UTC (permalink / raw)
To: netdev; +Cc: davem, Nicolas Dichtel
In-Reply-To: <1354619621-16016-1-git-send-email-nicolas.dichtel@6wind.com>
This patch allows to monitor mf6c activities via rtnetlink.
To avoid parsing two times the mf6c oifs, we use maxvif to allocate the rtnl
msg, thus we may allocate some superfluous space.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
net/ipv6/ip6mr.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++++----
1 file changed, 59 insertions(+), 4 deletions(-)
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 175270f..26dcdec 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -116,6 +116,8 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt,
mifi_t mifi, int assert);
static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
struct mfc6_cache *c, struct rtmsg *rtm);
+static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
+ int cmd);
static int ip6mr_rtm_dumproute(struct sk_buff *skb,
struct netlink_callback *cb);
static void mroute_clean_tables(struct mr6_table *mrt);
@@ -870,6 +872,7 @@ static void ipmr_do_expire_process(struct mr6_table *mrt)
}
list_del(&c->list);
+ mr6_netlink_event(mrt, c, RTM_DELROUTE);
ip6mr_destroy_unres(mrt, c);
}
@@ -1220,6 +1223,7 @@ ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb)
atomic_inc(&mrt->cache_resolve_queue_len);
list_add(&c->list, &mrt->mfc6_unres_queue);
+ mr6_netlink_event(mrt, c, RTM_NEWROUTE);
ipmr_do_expire_process(mrt);
}
@@ -1257,6 +1261,7 @@ static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc)
list_del(&c->list);
write_unlock_bh(&mrt_lock);
+ mr6_netlink_event(mrt, c, RTM_DELROUTE);
ip6mr_cache_free(c);
return 0;
}
@@ -1421,6 +1426,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
if (!mrtsock)
c->mfc_flags |= MFC_STATIC;
write_unlock_bh(&mrt_lock);
+ mr6_netlink_event(mrt, c, RTM_NEWROUTE);
return 0;
}
@@ -1465,6 +1471,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
ip6mr_cache_resolve(net, mrt, uc, c);
ip6mr_cache_free(uc);
}
+ mr6_netlink_event(mrt, c, RTM_NEWROUTE);
return 0;
}
@@ -1498,6 +1505,7 @@ static void mroute_clean_tables(struct mr6_table *mrt)
list_del(&c->list);
write_unlock_bh(&mrt_lock);
+ mr6_netlink_event(mrt, c, RTM_DELROUTE);
ip6mr_cache_free(c);
}
}
@@ -1506,6 +1514,7 @@ static void mroute_clean_tables(struct mr6_table *mrt)
spin_lock_bh(&mfc_unres_lock);
list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) {
list_del(&c->list);
+ mr6_netlink_event(mrt, c, RTM_DELROUTE);
ip6mr_destroy_unres(mrt, c);
}
spin_unlock_bh(&mfc_unres_lock);
@@ -2231,13 +2240,13 @@ int ip6mr_get_route(struct net *net,
}
static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
- u32 portid, u32 seq, struct mfc6_cache *c)
+ u32 portid, u32 seq, struct mfc6_cache *c, int cmd)
{
struct nlmsghdr *nlh;
struct rtmsg *rtm;
int err;
- nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI);
+ nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI);
if (nlh == NULL)
return -EMSGSIZE;
@@ -2272,6 +2281,52 @@ nla_put_failure:
return -EMSGSIZE;
}
+static int mr6_msgsize(bool unresolved, int maxvif)
+{
+ size_t len =
+ NLMSG_ALIGN(sizeof(struct rtmsg))
+ + nla_total_size(4) /* RTA_TABLE */
+ + nla_total_size(sizeof(struct in6_addr)) /* RTA_SRC */
+ + nla_total_size(sizeof(struct in6_addr)) /* RTA_DST */
+ ;
+
+ if (!unresolved)
+ len = len
+ + nla_total_size(4) /* RTA_IIF */
+ + nla_total_size(0) /* RTA_MULTIPATH */
+ + maxvif * NLA_ALIGN(sizeof(struct rtnexthop))
+ /* RTA_MFC_STATS */
+ + nla_total_size(sizeof(struct rta_mfc_stats))
+ ;
+
+ return len;
+}
+
+static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
+ int cmd)
+{
+ struct net *net = read_pnet(&mrt->net);
+ struct sk_buff *skb;
+ int err = -ENOBUFS;
+
+ skb = nlmsg_new(mr6_msgsize(mfc->mf6c_parent >= MAXMIFS, mrt->maxvif),
+ GFP_ATOMIC);
+ if (skb == NULL)
+ goto errout;
+
+ err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd);
+ if (err < 0)
+ goto errout;
+
+ rtnl_notify(skb, net, 0, RTNLGRP_IPV6_MROUTE, NULL, GFP_ATOMIC);
+ return;
+
+errout:
+ kfree_skb(skb);
+ if (err < 0)
+ rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err);
+}
+
static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
@@ -2298,7 +2353,7 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
if (ip6mr_fill_mroute(mrt, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
- mfc) < 0)
+ mfc, RTM_NEWROUTE) < 0)
goto done;
next_entry:
e++;
@@ -2312,7 +2367,7 @@ next_entry:
if (ip6mr_fill_mroute(mrt, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
- mfc) < 0) {
+ mfc, RTM_NEWROUTE) < 0) {
spin_unlock_bh(&mfc_unres_lock);
goto done;
}
--
1.8.0.1
^ permalink raw reply related
* [PATCH net-next 4/7] ipmr/ip6mr: report origin of mfc entry into rtnl msg
From: Nicolas Dichtel @ 2012-12-04 11:13 UTC (permalink / raw)
To: netdev; +Cc: davem, Nicolas Dichtel
In-Reply-To: <1354619621-16016-1-git-send-email-nicolas.dichtel@6wind.com>
A mfc entry can be static or not (added via the mroute_sk socket). The patch
reports MFC_STATIC flag into rtm_protocol by setting rtm_protocol to
RTPROT_STATIC or RTPROT_MROUTED.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
include/uapi/linux/rtnetlink.h | 1 +
net/ipv4/ipmr.c | 5 ++++-
net/ipv6/ip6mr.c | 5 ++++-
3 files changed, 9 insertions(+), 2 deletions(-)
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 80abe27..33d29ce 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -227,6 +227,7 @@ enum {
#define RTPROT_XORP 14 /* XORP */
#define RTPROT_NTK 15 /* Netsukuku */
#define RTPROT_DHCP 16 /* DHCP client */
+#define RTPROT_MROUTED 17 /* Multicast daemon */
/* rtm_scope
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c5617d6..91782a7 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2169,7 +2169,10 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
goto nla_put_failure;
rtm->rtm_type = RTN_MULTICAST;
rtm->rtm_scope = RT_SCOPE_UNIVERSE;
- rtm->rtm_protocol = RTPROT_UNSPEC;
+ if (c->mfc_flags & MFC_STATIC)
+ rtm->rtm_protocol = RTPROT_STATIC;
+ else
+ rtm->rtm_protocol = RTPROT_MROUTED;
rtm->rtm_flags = 0;
if (nla_put_be32(skb, RTA_SRC, c->mfc_origin) ||
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index b744b98..e9ef38f 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2249,7 +2249,10 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
if (nla_put_u32(skb, RTA_TABLE, mrt->id))
goto nla_put_failure;
rtm->rtm_scope = RT_SCOPE_UNIVERSE;
- rtm->rtm_protocol = RTPROT_UNSPEC;
+ if (c->mfc_flags & MFC_STATIC)
+ rtm->rtm_protocol = RTPROT_STATIC;
+ else
+ rtm->rtm_protocol = RTPROT_MROUTED;
rtm->rtm_flags = 0;
if (nla_put(skb, RTA_SRC, 16, &c->mf6c_origin) ||
--
1.8.0.1
^ permalink raw reply related
* [PATCH net-next 1/7] netconf: advertise mc_forwarding status
From: Nicolas Dichtel @ 2012-12-04 11:13 UTC (permalink / raw)
To: netdev; +Cc: davem, Nicolas Dichtel
In-Reply-To: <1354619621-16016-1-git-send-email-nicolas.dichtel@6wind.com>
This patch advertise the MC_FORWARDING status for IPv4 and IPv6.
This field is readonly, only multicast engine in the kernel updates it.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
include/linux/inetdevice.h | 3 +++
include/net/addrconf.h | 3 +++
include/uapi/linux/netconf.h | 1 +
net/ipv4/devinet.c | 10 ++++++++--
net/ipv4/ipmr.c | 12 ++++++++++++
net/ipv6/addrconf.c | 10 ++++++++--
net/ipv6/ip6mr.c | 20 ++++++++++++++++++--
7 files changed, 53 insertions(+), 6 deletions(-)
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index d032780..a9d8289 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -171,6 +171,9 @@ struct in_ifaddr {
extern int register_inetaddr_notifier(struct notifier_block *nb);
extern int unregister_inetaddr_notifier(struct notifier_block *nb);
+extern void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
+ struct ipv4_devconf *devconf);
+
extern struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref);
static inline struct net_device *ip_dev_find(struct net *net, __be32 addr)
{
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 9e63e76..df4ef94 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -172,6 +172,9 @@ extern bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
extern int register_inet6addr_notifier(struct notifier_block *nb);
extern int unregister_inet6addr_notifier(struct notifier_block *nb);
+extern void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
+ struct ipv6_devconf *devconf);
+
/**
* __in6_dev_get - get inet6_dev pointer from netdevice
* @dev: network device
diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h
index 75dcbc5..64804a7 100644
--- a/include/uapi/linux/netconf.h
+++ b/include/uapi/linux/netconf.h
@@ -13,6 +13,7 @@ enum {
NETCONFA_IFINDEX,
NETCONFA_FORWARDING,
NETCONFA_RP_FILTER,
+ NETCONFA_MC_FORWARDING,
__NETCONFA_MAX
};
#define NETCONFA_MAX (__NETCONFA_MAX - 1)
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index e13183a..cc06a47 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1453,6 +1453,8 @@ static int inet_netconf_msgsize_devconf(int type)
size += nla_total_size(4);
if (type == -1 || type == NETCONFA_RP_FILTER)
size += nla_total_size(4);
+ if (type == -1 || type == NETCONFA_MC_FORWARDING)
+ size += nla_total_size(4);
return size;
}
@@ -1485,6 +1487,10 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
nla_put_s32(skb, NETCONFA_RP_FILTER,
IPV4_DEVCONF(*devconf, RP_FILTER)) < 0)
goto nla_put_failure;
+ if ((type == -1 || type == NETCONFA_MC_FORWARDING) &&
+ nla_put_s32(skb, NETCONFA_MC_FORWARDING,
+ IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0)
+ goto nla_put_failure;
return nlmsg_end(skb, nlh);
@@ -1493,8 +1499,8 @@ nla_put_failure:
return -EMSGSIZE;
}
-static void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
- struct ipv4_devconf *devconf)
+void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
+ struct ipv4_devconf *devconf)
{
struct sk_buff *skb;
int err = -ENOBUFS;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 58e4160..0c452e3 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -65,6 +65,7 @@
#include <net/checksum.h>
#include <net/netlink.h>
#include <net/fib_rules.h>
+#include <linux/netconf.h>
#if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2)
#define CONFIG_IP_PIMSM 1
@@ -582,6 +583,9 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify,
in_dev = __in_dev_get_rtnl(dev);
if (in_dev) {
IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)--;
+ inet_netconf_notify_devconf(dev_net(dev),
+ NETCONFA_MC_FORWARDING,
+ dev->ifindex, &in_dev->cnf);
ip_rt_multicast_event(in_dev);
}
@@ -772,6 +776,8 @@ static int vif_add(struct net *net, struct mr_table *mrt,
return -EADDRNOTAVAIL;
}
IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)++;
+ inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, dev->ifindex,
+ &in_dev->cnf);
ip_rt_multicast_event(in_dev);
/* Fill in the VIF structures */
@@ -1185,6 +1191,9 @@ static void mrtsock_destruct(struct sock *sk)
ipmr_for_each_table(mrt, net) {
if (sk == rtnl_dereference(mrt->mroute_sk)) {
IPV4_DEVCONF_ALL(net, MC_FORWARDING)--;
+ inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+ NETCONFA_IFINDEX_ALL,
+ net->ipv4.devconf_all);
RCU_INIT_POINTER(mrt->mroute_sk, NULL);
mroute_clean_tables(mrt);
}
@@ -1236,6 +1245,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
if (ret == 0) {
rcu_assign_pointer(mrt->mroute_sk, sk);
IPV4_DEVCONF_ALL(net, MC_FORWARDING)++;
+ inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+ NETCONFA_IFINDEX_ALL,
+ net->ipv4.devconf_all);
}
rtnl_unlock();
return ret;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 4b644f6..976543d 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -469,6 +469,8 @@ static int inet6_netconf_msgsize_devconf(int type)
/* type -1 is used for ALL */
if (type == -1 || type == NETCONFA_FORWARDING)
size += nla_total_size(4);
+ if (type == -1 || type == NETCONFA_MC_FORWARDING)
+ size += nla_total_size(4);
return size;
}
@@ -496,6 +498,10 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
if ((type == -1 || type == NETCONFA_FORWARDING) &&
nla_put_s32(skb, NETCONFA_FORWARDING, devconf->forwarding) < 0)
goto nla_put_failure;
+ if ((type == -1 || type == NETCONFA_MC_FORWARDING) &&
+ nla_put_s32(skb, NETCONFA_MC_FORWARDING,
+ devconf->mc_forwarding) < 0)
+ goto nla_put_failure;
return nlmsg_end(skb, nlh);
@@ -504,8 +510,8 @@ nla_put_failure:
return -EMSGSIZE;
}
-static void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
- struct ipv6_devconf *devconf)
+void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
+ struct ipv6_devconf *devconf)
{
struct sk_buff *skb;
int err = -ENOBUFS;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index d7c7e90..efc6d91 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -52,6 +52,7 @@
#include <linux/netfilter_ipv6.h>
#include <linux/export.h>
#include <net/ip6_checksum.h>
+#include <linux/netconf.h>
struct mr6_table {
struct list_head list;
@@ -805,8 +806,12 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head)
dev_set_allmulti(dev, -1);
in6_dev = __in6_dev_get(dev);
- if (in6_dev)
+ if (in6_dev) {
in6_dev->cnf.mc_forwarding--;
+ inet6_netconf_notify_devconf(dev_net(dev),
+ NETCONFA_MC_FORWARDING,
+ dev->ifindex, &in6_dev->cnf);
+ }
if (v->flags & MIFF_REGISTER)
unregister_netdevice_queue(dev, head);
@@ -958,8 +963,12 @@ static int mif6_add(struct net *net, struct mr6_table *mrt,
}
in6_dev = __in6_dev_get(dev);
- if (in6_dev)
+ if (in6_dev) {
in6_dev->cnf.mc_forwarding++;
+ inet6_netconf_notify_devconf(dev_net(dev),
+ NETCONFA_MC_FORWARDING,
+ dev->ifindex, &in6_dev->cnf);
+ }
/*
* Fill in the VIF structures
@@ -1513,6 +1522,9 @@ static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk)
if (likely(mrt->mroute6_sk == NULL)) {
mrt->mroute6_sk = sk;
net->ipv6.devconf_all->mc_forwarding++;
+ inet6_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+ NETCONFA_IFINDEX_ALL,
+ net->ipv6.devconf_all);
}
else
err = -EADDRINUSE;
@@ -1535,6 +1547,10 @@ int ip6mr_sk_done(struct sock *sk)
write_lock_bh(&mrt_lock);
mrt->mroute6_sk = NULL;
net->ipv6.devconf_all->mc_forwarding--;
+ inet6_netconf_notify_devconf(net,
+ NETCONFA_MC_FORWARDING,
+ NETCONFA_IFINDEX_ALL,
+ net->ipv6.devconf_all);
write_unlock_bh(&mrt_lock);
mroute_clean_tables(mrt);
--
1.8.0.1
^ permalink raw reply related
* [PATCH net-next 3/7] ipmr/ip6mr: advertise mfc stats via rtnetlink
From: Nicolas Dichtel @ 2012-12-04 11:13 UTC (permalink / raw)
To: netdev; +Cc: davem, Nicolas Dichtel
In-Reply-To: <1354619621-16016-1-git-send-email-nicolas.dichtel@6wind.com>
These statistics can be checked only via /proc/net/ip_mr_cache or
SIOCGETSGCNT[_IN6] and thus only for the table RT_TABLE_DEFAULT.
Advertising them via rtnetlink allows to get statistics for all cache entries,
whatever the table is.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
include/uapi/linux/rtnetlink.h | 7 +++++++
net/ipv4/ipmr.c | 7 +++++++
net/ipv6/ip6mr.c | 7 +++++++
3 files changed, 21 insertions(+)
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 3dee071..80abe27 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -288,6 +288,7 @@ enum rtattr_type_t {
RTA_MP_ALGO, /* no longer used */
RTA_TABLE,
RTA_MARK,
+ RTA_MFC_STATS,
__RTA_MAX
};
@@ -408,6 +409,12 @@ struct rta_session {
} u;
};
+struct rta_mfc_stats {
+ __u64 mfcs_packets;
+ __u64 mfcs_bytes;
+ __u64 mfcs_wrong_if;
+};
+
/****
* General form of address family dependent message.
****/
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 0c452e3..c5617d6 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2046,6 +2046,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
int ct;
struct rtnexthop *nhp;
struct nlattr *mp_attr;
+ struct rta_mfc_stats mfcs;
/* If cache is unresolved, don't try to parse IIF and OIF */
if (c->mfc_parent >= MAXVIFS)
@@ -2074,6 +2075,12 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
nla_nest_end(skb, mp_attr);
+ mfcs.mfcs_packets = c->mfc_un.res.pkt;
+ mfcs.mfcs_bytes = c->mfc_un.res.bytes;
+ mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if;
+ if (nla_put(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs) < 0)
+ return -EMSGSIZE;
+
rtm->rtm_type = RTN_MULTICAST;
return 1;
}
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 653df91..b744b98 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2120,6 +2120,7 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
int ct;
struct rtnexthop *nhp;
struct nlattr *mp_attr;
+ struct rta_mfc_stats mfcs;
/* If cache is unresolved, don't try to parse IIF and OIF */
if (c->mf6c_parent >= MAXMIFS)
@@ -2149,6 +2150,12 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
nla_nest_end(skb, mp_attr);
+ mfcs.mfcs_packets = c->mfc_un.res.pkt;
+ mfcs.mfcs_bytes = c->mfc_un.res.bytes;
+ mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if;
+ if (nla_put(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs) < 0)
+ return -EMSGSIZE;
+
rtm->rtm_type = RTN_MULTICAST;
return 1;
}
--
1.8.0.1
^ permalink raw reply related
* [PATCH net-next 2/7] ip6mr: use nla_nest_* helpers
From: Nicolas Dichtel @ 2012-12-04 11:13 UTC (permalink / raw)
To: netdev; +Cc: davem, Nicolas Dichtel
In-Reply-To: <1354619621-16016-1-git-send-email-nicolas.dichtel@6wind.com>
This patch removes the skb manipulations when nested attributes are added by
using standard helpers.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
net/ipv6/ip6mr.c | 26 +++++++++++++-------------
1 file changed, 13 insertions(+), 13 deletions(-)
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index efc6d91..653df91 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2119,8 +2119,7 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
{
int ct;
struct rtnexthop *nhp;
- u8 *b = skb_tail_pointer(skb);
- struct rtattr *mp_head;
+ struct nlattr *mp_attr;
/* If cache is unresolved, don't try to parse IIF and OIF */
if (c->mf6c_parent >= MAXMIFS)
@@ -2129,28 +2128,29 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
if (MIF_EXISTS(mrt, c->mf6c_parent) &&
nla_put_u32(skb, RTA_IIF, mrt->vif6_table[c->mf6c_parent].dev->ifindex) < 0)
return -EMSGSIZE;
-
- mp_head = (struct rtattr *)skb_put(skb, RTA_LENGTH(0));
+ mp_attr = nla_nest_start(skb, RTA_MULTIPATH);
+ if (mp_attr == NULL)
+ return -EMSGSIZE;
for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) {
if (MIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) {
- if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4))
- goto rtattr_failure;
- nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp)));
+ nhp = nla_reserve_nohdr(skb, sizeof(*nhp));
+ if (nhp == NULL) {
+ nla_nest_cancel(skb, mp_attr);
+ return -EMSGSIZE;
+ }
+
nhp->rtnh_flags = 0;
nhp->rtnh_hops = c->mfc_un.res.ttls[ct];
nhp->rtnh_ifindex = mrt->vif6_table[ct].dev->ifindex;
nhp->rtnh_len = sizeof(*nhp);
}
}
- mp_head->rta_type = RTA_MULTIPATH;
- mp_head->rta_len = skb_tail_pointer(skb) - (u8 *)mp_head;
+
+ nla_nest_end(skb, mp_attr);
+
rtm->rtm_type = RTN_MULTICAST;
return 1;
-
-rtattr_failure:
- nlmsg_trim(skb, b);
- return -EMSGSIZE;
}
int ip6mr_get_route(struct net *net,
--
1.8.0.1
^ permalink raw reply related
* [PATCH net-next 0/7] Allow to monitor multicast cache event via rtnetlink
From: Nicolas Dichtel @ 2012-12-04 11:13 UTC (permalink / raw)
To: netdev; +Cc: davem
The goal of this serie is to be able to monitor multicast activities via
rtnetlink.
The main changes are:
- when user dumps mfc entries it now get all entries, included the unresolved
cache.
- kernel sends rtnetlink when it adds/deletes mfc entries.
As usual, the patch against iproute2 will be sent once the patches are included and
net-next merged. I can send it on demand.
include/linux/inetdevice.h | 3 +
include/net/addrconf.h | 3 +
include/uapi/linux/netconf.h | 1 +
include/uapi/linux/rtnetlink.h | 8 +++
net/ipv4/devinet.c | 10 ++-
net/ipv4/ipmr.c | 107 +++++++++++++++++++++++++++++--
net/ipv6/addrconf.c | 10 ++-
net/ipv6/ip6mr.c | 141 +++++++++++++++++++++++++++++++++++------
8 files changed, 253 insertions(+), 30 deletions(-)
Comments are welcome.
Regards,
Nicolas
^ permalink raw reply
* [PATCH net-next 3/3] virtio-net: change the number of queues through ethtool
From: Jason Wang @ 2012-12-04 11:07 UTC (permalink / raw)
To: rusty, mst, virtualization, netdev, linux-kernel, davem
Cc: krkumar2, kvm, bhutchings, jwhan, shiyer
In-Reply-To: <1354619278-35702-1-git-send-email-jasowang@redhat.com>
This patch implement the ethtool_{set|get}_channels method of ethool to allow
user to change the number of queues dymaically when the device is running. This
would let the user to configure it on demand.
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/net/virtio_net.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 44 insertions(+), 0 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 912f5b2..b9f9887 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1589,10 +1589,54 @@ static struct virtio_driver virtio_net_driver = {
#endif
};
+/* TODO: Eliminate OOO packets during switching */
+static int virtnet_set_channels(struct net_device *dev,
+ struct ethtool_channels *channels)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+ u16 queue_pairs = channels->combined_count;
+ u16 old_queue_pairs = vi->curr_queue_pairs;
+
+ /* We don't support separate rx/tx channels.
+ * We don't allow setting 'other' channels.
+ */
+ if (channels->rx_count || channels->tx_count || channels->other_count)
+ return -EINVAL;
+
+ if (queue_pairs > vi->max_queue_pairs)
+ return -EINVAL;
+
+ vi->curr_queue_pairs = queue_pairs;
+ if (virtnet_set_queues(vi) == 0) {
+ netif_set_real_num_tx_queues(dev, vi->curr_queue_pairs);
+ netif_set_real_num_rx_queues(dev, vi->curr_queue_pairs);
+
+ virtnet_set_affinity(vi, true);
+ } else
+ vi->curr_queue_pairs = old_queue_pairs;
+
+ return 0;
+}
+
+static void virtnet_get_channels(struct net_device *dev,
+ struct ethtool_channels *channels)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+
+ channels->combined_count = vi->curr_queue_pairs;
+ channels->max_combined = vi->max_queue_pairs;
+ channels->max_other = 0;
+ channels->rx_count = 0;
+ channels->tx_count = 0;
+ channels->other_count = 0;
+}
+
static const struct ethtool_ops virtnet_ethtool_ops = {
.get_drvinfo = virtnet_get_drvinfo,
.get_link = ethtool_op_get_link,
.get_ringparam = virtnet_get_ringparam,
+ .set_channels = virtnet_set_channels,
+ .get_channels = virtnet_get_channels,
};
static int __init init(void)
--
1.7.1
^ permalink raw reply related
* [PATCH net-next 2/3] virtio_net: multiqueue support
From: Jason Wang @ 2012-12-04 11:07 UTC (permalink / raw)
To: rusty, mst, virtualization, netdev, linux-kernel, davem
Cc: krkumar2, kvm, bhutchings, jwhan, shiyer
In-Reply-To: <1354619278-35702-1-git-send-email-jasowang@redhat.com>
This addes multiqueue support to virtio_net driver. In multiple queue modes, the
driver expects the number of queue paris is equal to the number of vcpus. To
eliminate the contention bettwen vcpus and virtqueues, per-cpu virtqueue pairs
were implemented through:
- select the txq based on the smp processor id.
- smp affinity hint were set to the vcpu that owns the queue pairs.
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/net/virtio_net.c | 472 ++++++++++++++++++++++++++++++---------
include/uapi/linux/virtio_net.h | 16 ++
2 files changed, 385 insertions(+), 103 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 266f712..912f5b2 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -81,16 +81,25 @@ struct virtnet_info {
struct virtio_device *vdev;
struct virtqueue *cvq;
struct net_device *dev;
- struct send_queue sq;
- struct receive_queue rq;
+ struct send_queue *sq;
+ struct receive_queue *rq;
unsigned int status;
+ /* Max # of queue pairs supported by the device */
+ u16 max_queue_pairs;
+
+ /* # of queue pairs currently used by the driver */
+ u16 curr_queue_pairs;
+
/* I like... big packets and I cannot lie! */
bool big_packets;
/* Host will merge rx buffers for big packets (shake it! shake it!) */
bool mergeable_rx_bufs;
+ /* Has control virtqueue */
+ bool has_cvq;
+
/* enable config space updates */
bool config_enable;
@@ -125,6 +134,32 @@ struct padded_vnet_hdr {
char padding[6];
};
+static const struct ethtool_ops virtnet_ethtool_ops;
+
+
+/* Converting between virtqueue no. and kernel tx/rx queue no.
+ * 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq
+ */
+static int vq2txq(struct virtqueue *vq)
+{
+ return (virtqueue_get_queue_index(vq) - 1) / 2;
+}
+
+static int txq2vq(int txq)
+{
+ return txq * 2 + 1;
+}
+
+static int vq2rxq(struct virtqueue *vq)
+{
+ return virtqueue_get_queue_index(vq) / 2;
+}
+
+static int rxq2vq(int rxq)
+{
+ return rxq * 2;
+}
+
static inline struct skb_vnet_hdr *skb_vnet_hdr(struct sk_buff *skb)
{
return (struct skb_vnet_hdr *)skb->cb;
@@ -165,7 +200,7 @@ static void skb_xmit_done(struct virtqueue *vq)
virtqueue_disable_cb(vq);
/* We were probably waiting for more output buffers. */
- netif_wake_queue(vi->dev);
+ netif_wake_subqueue(vi->dev, vq2txq(vq));
}
static void set_skb_frag(struct sk_buff *skb, struct page *page,
@@ -502,7 +537,7 @@ static bool try_fill_recv(struct receive_queue *rq, gfp_t gfp)
static void skb_recv_done(struct virtqueue *rvq)
{
struct virtnet_info *vi = rvq->vdev->priv;
- struct receive_queue *rq = &vi->rq;
+ struct receive_queue *rq = &vi->rq[vq2rxq(rvq)];
/* Schedule NAPI, Suppress further interrupts if successful. */
if (napi_schedule_prep(&rq->napi)) {
@@ -532,15 +567,21 @@ static void refill_work(struct work_struct *work)
struct virtnet_info *vi =
container_of(work, struct virtnet_info, refill.work);
bool still_empty;
+ int i;
+
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ struct receive_queue *rq = &vi->rq[i];
- napi_disable(&vi->rq.napi);
- still_empty = !try_fill_recv(&vi->rq, GFP_KERNEL);
- virtnet_napi_enable(&vi->rq);
+ napi_disable(&rq->napi);
+ still_empty = !try_fill_recv(rq, GFP_KERNEL);
+ virtnet_napi_enable(rq);
- /* In theory, this can happen: if we don't get any buffers in
- * we will *never* try to fill again. */
- if (still_empty)
- schedule_delayed_work(&vi->refill, HZ/2);
+ /* In theory, this can happen: if we don't get any buffers in
+ * we will *never* try to fill again.
+ */
+ if (still_empty)
+ schedule_delayed_work(&vi->refill, HZ/2);
+ }
}
static int virtnet_poll(struct napi_struct *napi, int budget)
@@ -650,7 +691,8 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct virtnet_info *vi = netdev_priv(dev);
- struct send_queue *sq = &vi->sq;
+ int qnum = skb_get_queue_mapping(skb);
+ struct send_queue *sq = &vi->sq[qnum];
int capacity;
/* Free up any pending old buffers before queueing new ones. */
@@ -664,13 +706,14 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
if (likely(capacity == -ENOMEM)) {
if (net_ratelimit())
dev_warn(&dev->dev,
- "TX queue failure: out of memory\n");
+ "TXQ (%d) failure: out of memory\n",
+ qnum);
} else {
dev->stats.tx_fifo_errors++;
if (net_ratelimit())
dev_warn(&dev->dev,
- "Unexpected TX queue failure: %d\n",
- capacity);
+ "Unexpected TXQ (%d) failure: %d\n",
+ qnum, capacity);
}
dev->stats.tx_dropped++;
kfree_skb(skb);
@@ -685,12 +728,12 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
/* Apparently nice girls don't return TX_BUSY; stop the queue
* before it gets out of hand. Naturally, this wastes entries. */
if (capacity < 2+MAX_SKB_FRAGS) {
- netif_stop_queue(dev);
+ netif_stop_subqueue(dev, qnum);
if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
/* More just got used, free them then recheck. */
capacity += free_old_xmit_skbs(sq);
if (capacity >= 2+MAX_SKB_FRAGS) {
- netif_start_queue(dev);
+ netif_start_subqueue(dev, qnum);
virtqueue_disable_cb(sq->vq);
}
}
@@ -758,23 +801,13 @@ static struct rtnl_link_stats64 *virtnet_stats(struct net_device *dev,
static void virtnet_netpoll(struct net_device *dev)
{
struct virtnet_info *vi = netdev_priv(dev);
+ int i;
- napi_schedule(&vi->rq.napi);
+ for (i = 0; i < vi->curr_queue_pairs; i++)
+ napi_schedule(&vi->rq[i].napi);
}
#endif
-static int virtnet_open(struct net_device *dev)
-{
- struct virtnet_info *vi = netdev_priv(dev);
-
- /* Make sure we have some buffers: if oom use wq. */
- if (!try_fill_recv(&vi->rq, GFP_KERNEL))
- schedule_delayed_work(&vi->refill, 0);
-
- virtnet_napi_enable(&vi->rq);
- return 0;
-}
-
/*
* Send command via the control virtqueue and check status. Commands
* supported by the hypervisor, as indicated by feature bits, should
@@ -830,13 +863,51 @@ static void virtnet_ack_link_announce(struct virtnet_info *vi)
rtnl_unlock();
}
+/* Caller check the support of cvq and multiqueue. */
+static int virtnet_set_queues(struct virtnet_info *vi)
+{
+ struct scatterlist sg;
+ struct virtio_net_ctrl_rfs s;
+ struct net_device *dev = vi->dev;
+
+ s.virtqueue_pairs = vi->curr_queue_pairs;
+ sg_init_one(&sg, &s, sizeof(s));
+
+ if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RFS,
+ VIRTIO_NET_CTRL_RFS_VQ_PAIRS_SET, &sg, 1, 0)){
+ dev_warn(&dev->dev, "Fail to set num of queue pairs to %d\n",
+ vi->curr_queue_pairs);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int virtnet_open(struct net_device *dev)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+ int i;
+
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ /* Make sure we have some buffers: if oom use wq. */
+ if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
+ schedule_delayed_work(&vi->refill, 0);
+ virtnet_napi_enable(&vi->rq[i]);
+ }
+
+ return 0;
+}
+
static int virtnet_close(struct net_device *dev)
{
struct virtnet_info *vi = netdev_priv(dev);
+ int i;
/* Make sure refill_work doesn't re-enable napi! */
cancel_delayed_work_sync(&vi->refill);
- napi_disable(&vi->rq.napi);
+
+ for (i = 0; i < vi->max_queue_pairs; i++)
+ napi_disable(&vi->rq[i].napi);
return 0;
}
@@ -948,8 +1019,8 @@ static void virtnet_get_ringparam(struct net_device *dev,
{
struct virtnet_info *vi = netdev_priv(dev);
- ring->rx_max_pending = virtqueue_get_vring_size(vi->rq.vq);
- ring->tx_max_pending = virtqueue_get_vring_size(vi->sq.vq);
+ ring->rx_max_pending = virtqueue_get_vring_size(vi->rq[0].vq);
+ ring->tx_max_pending = virtqueue_get_vring_size(vi->sq[0].vq);
ring->rx_pending = ring->rx_max_pending;
ring->tx_pending = ring->tx_max_pending;
}
@@ -967,12 +1038,6 @@ static void virtnet_get_drvinfo(struct net_device *dev,
}
-static const struct ethtool_ops virtnet_ethtool_ops = {
- .get_drvinfo = virtnet_get_drvinfo,
- .get_link = ethtool_op_get_link,
- .get_ringparam = virtnet_get_ringparam,
-};
-
#define MIN_MTU 68
#define MAX_MTU 65535
@@ -984,6 +1049,21 @@ static int virtnet_change_mtu(struct net_device *dev, int new_mtu)
return 0;
}
+/* To avoid contending a lock hold by a vcpu who would exit to host, select the
+ * txq based on the processor id.
+ * TODO: handle cpu hotplug.
+ */
+static u16 virtnet_select_queue(struct net_device *dev, struct sk_buff *skb)
+{
+ int txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) :
+ smp_processor_id();
+
+ while (unlikely(txq >= dev->real_num_tx_queues))
+ txq -= dev->real_num_tx_queues;
+
+ return txq;
+}
+
static const struct net_device_ops virtnet_netdev = {
.ndo_open = virtnet_open,
.ndo_stop = virtnet_close,
@@ -995,6 +1075,7 @@ static const struct net_device_ops virtnet_netdev = {
.ndo_get_stats64 = virtnet_stats,
.ndo_vlan_rx_add_vid = virtnet_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = virtnet_vlan_rx_kill_vid,
+ .ndo_select_queue = virtnet_select_queue,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = virtnet_netpoll,
#endif
@@ -1030,10 +1111,10 @@ static void virtnet_config_changed_work(struct work_struct *work)
if (vi->status & VIRTIO_NET_S_LINK_UP) {
netif_carrier_on(vi->dev);
- netif_wake_queue(vi->dev);
+ netif_tx_wake_all_queues(vi->dev);
} else {
netif_carrier_off(vi->dev);
- netif_stop_queue(vi->dev);
+ netif_tx_stop_all_queues(vi->dev);
}
done:
mutex_unlock(&vi->config_lock);
@@ -1046,41 +1127,219 @@ static void virtnet_config_changed(struct virtio_device *vdev)
schedule_work(&vi->config_work);
}
-static int init_vqs(struct virtnet_info *vi)
+static void free_receive_bufs(struct virtnet_info *vi)
{
- struct virtqueue *vqs[3];
- vq_callback_t *callbacks[] = { skb_recv_done, skb_xmit_done, NULL};
- const char *names[] = { "input", "output", "control" };
- int nvqs, err;
+ int i;
- /* We expect two virtqueues, receive then send,
- * and optionally control. */
- nvqs = virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ) ? 3 : 2;
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ while (vi->rq[i].pages)
+ __free_pages(get_a_page(&vi->rq[i], GFP_KERNEL), 0);
+ }
+}
- err = vi->vdev->config->find_vqs(vi->vdev, nvqs, vqs, callbacks, names);
- if (err)
- return err;
+/* Free memory allocated for send and receive queues */
+static void virtnet_free_queues(struct virtnet_info *vi)
+{
+ kfree(vi->rq);
+ vi->rq = NULL;
+ kfree(vi->sq);
+ vi->sq = NULL;
+}
+
+static void free_unused_bufs(struct virtnet_info *vi)
+{
+ void *buf;
+ int i;
+
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ struct virtqueue *vq = vi->sq[i].vq;
+ while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
+ dev_kfree_skb(buf);
+ }
+
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ struct virtqueue *vq = vi->rq[i].vq;
+
+ while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
+ if (vi->mergeable_rx_bufs || vi->big_packets)
+ give_pages(&vi->rq[i], buf);
+ else
+ dev_kfree_skb(buf);
+ --vi->rq[i].num;
+ }
+ BUG_ON(vi->rq[i].num != 0);
+ }
+}
+
+static void virtnet_set_affinity(struct virtnet_info *vi, bool set)
+{
+ int i;
+
+ /* Don't set the affinity hint when in single queue mode or we have too
+ * much online cpus.
+ */
+ if (vi->curr_queue_pairs == 1 ||
+ vi->max_queue_pairs > num_online_cpus())
+ set = false;
+
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ int cpu = set ? i : -1;
+ virtqueue_set_affinity(vi->rq[i].vq, cpu);
+ virtqueue_set_affinity(vi->sq[i].vq, cpu);
+ }
+}
+
+static void virtnet_del_vqs(struct virtnet_info *vi)
+{
+ struct virtio_device *vdev = vi->vdev;
+
+ virtnet_set_affinity(vi, false);
+
+ vdev->config->del_vqs(vdev);
- vi->rq.vq = vqs[0];
- vi->sq.vq = vqs[1];
+ virtnet_free_queues(vi);
+}
- if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)) {
- vi->cvq = vqs[2];
+static int virtnet_find_vqs(struct virtnet_info *vi)
+{
+ vq_callback_t **callbacks;
+ struct virtqueue **vqs;
+ int ret = -ENOMEM;
+ int i, total_vqs;
+ char **names;
+
+ /* We expect 1 RX virtqueue followed by 1 TX virtqueue, followd by
+ * possible N-1 RX/TX queue pairs used in multiqueue mode, followed by
+ * possible control vq.
+ */
+ total_vqs = vi->max_queue_pairs * 2 +
+ virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ);
+
+ /* Allocate space for find_vqs parameters */
+ vqs = kzalloc(total_vqs * sizeof(*vqs), GFP_KERNEL);
+ callbacks = kzalloc(total_vqs * sizeof(*callbacks), GFP_KERNEL);
+ if (!vqs || !callbacks)
+ goto err_mem;
+ names = kzalloc(total_vqs * sizeof(*names), GFP_KERNEL);
+ if (!names)
+ goto err_mem;
+
+ /* Parameters for control virtqueue, if any */
+ if (vi->has_cvq) {
+ callbacks[total_vqs - 1] = NULL;
+ names[total_vqs - 1] = kasprintf(GFP_KERNEL, "control");
+ }
+ /* Allocate/initialize parameters for send/receive virtqueues */
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ callbacks[rxq2vq(i)] = skb_recv_done;
+ callbacks[txq2vq(i)] = skb_xmit_done;
+ names[rxq2vq(i)] = kasprintf(GFP_KERNEL, "input.%d", i);
+ names[txq2vq(i)] = kasprintf(GFP_KERNEL, "output.%d", i);
+ }
+
+ ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks,
+ (const char **)names);
+ if (ret)
+ goto err_names;
+
+ if (vi->has_cvq) {
+ vi->cvq = vqs[total_vqs - 1];
if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VLAN))
vi->dev->features |= NETIF_F_HW_VLAN_FILTER;
}
+
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ vi->rq[i].vq = vqs[rxq2vq(i)];
+ vi->sq[i].vq = vqs[txq2vq(i)];
+ }
+
+ kfree(callbacks);
+ kfree(vqs);
+
+ return 0;
+
+err_names:
+ for (i = 0; i < total_vqs * 2; i++)
+ kfree(names[i]);
+ kfree(names);
+
+err_mem:
+ kfree(callbacks);
+ kfree(vqs);
+
+ return ret;
+}
+
+static int virtnet_alloc_queues(struct virtnet_info *vi)
+{
+ int i;
+
+ vi->sq = kzalloc(sizeof(vi->sq[0]) * vi->max_queue_pairs, GFP_KERNEL);
+ vi->rq = kzalloc(sizeof(vi->rq[0]) * vi->max_queue_pairs, GFP_KERNEL);
+ if (!vi->rq || !vi->sq)
+ goto err;
+
+ INIT_DELAYED_WORK(&vi->refill, refill_work);
+ /* setup initial receive and send queue parameters */
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ vi->rq[i].pages = NULL;
+ netif_napi_add(vi->dev, &vi->rq[i].napi, virtnet_poll,
+ napi_weight);
+
+ sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg));
+ sg_init_table(vi->sq[i].sg, ARRAY_SIZE(vi->sq[i].sg));
+ }
+
+
+ return 0;
+
+err:
+ virtnet_free_queues(vi);
+ return -ENOMEM;
+}
+
+static int init_vqs(struct virtnet_info *vi)
+{
+ int ret;
+
+ /* Allocate send & receive queues */
+ ret = virtnet_alloc_queues(vi);
+ if (ret)
+ goto err;
+
+ ret = virtnet_find_vqs(vi);
+ if (ret)
+ goto err_free;
+
+ virtnet_set_affinity(vi, true);
return 0;
+
+err_free:
+ virtnet_free_queues(vi);
+err:
+ return ret;
}
static int virtnet_probe(struct virtio_device *vdev)
{
- int err;
+ int i, err;
struct net_device *dev;
struct virtnet_info *vi;
+ u16 max_queue_pairs;
+
+ /* Find if host supports multiqueue virtio_net device */
+ err = virtio_config_val(vdev, VIRTIO_NET_F_RFS,
+ offsetof(struct virtio_net_config,
+ max_virtqueue_pairs), &max_queue_pairs);
+
+ /* We need at least 2 queue's */
+ if (err || max_queue_pairs < VIRTIO_NET_CTRL_RFS_VQ_PAIRS_MIN ||
+ max_queue_pairs > VIRTIO_NET_CTRL_RFS_VQ_PAIRS_MAX)
+ max_queue_pairs = 1;
/* Allocate ourselves a network device with room for our info */
- dev = alloc_etherdev(sizeof(struct virtnet_info));
+ dev = alloc_etherdev_mq(sizeof(struct virtnet_info), max_queue_pairs);
if (!dev)
return -ENOMEM;
@@ -1127,22 +1386,17 @@ static int virtnet_probe(struct virtio_device *vdev)
/* Set up our device-specific information */
vi = netdev_priv(dev);
- netif_napi_add(dev, &vi->rq.napi, virtnet_poll, napi_weight);
vi->dev = dev;
vi->vdev = vdev;
vdev->priv = vi;
- vi->rq.pages = NULL;
vi->stats = alloc_percpu(struct virtnet_stats);
err = -ENOMEM;
if (vi->stats == NULL)
goto free;
- INIT_DELAYED_WORK(&vi->refill, refill_work);
mutex_init(&vi->config_lock);
vi->config_enable = true;
INIT_WORK(&vi->config_work, virtnet_config_changed_work);
- sg_init_table(vi->rq.sg, ARRAY_SIZE(vi->rq.sg));
- sg_init_table(vi->sq.sg, ARRAY_SIZE(vi->sq.sg));
/* If we can receive ANY GSO packets, we must allocate large ones. */
if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
@@ -1153,10 +1407,21 @@ static int virtnet_probe(struct virtio_device *vdev)
if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
vi->mergeable_rx_bufs = true;
+ if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ))
+ vi->has_cvq = true;
+
+ /* Use single tx/rx queue pair as default */
+ vi->curr_queue_pairs = 1;
+ vi->max_queue_pairs = max_queue_pairs;
+
+ /* Allocate/initialize the rx/tx queues, and invoke find_vqs */
err = init_vqs(vi);
if (err)
goto free_stats;
+ netif_set_real_num_tx_queues(dev, 1);
+ netif_set_real_num_rx_queues(dev, 1);
+
err = register_netdev(dev);
if (err) {
pr_debug("virtio_net: registering device failed\n");
@@ -1164,12 +1429,15 @@ static int virtnet_probe(struct virtio_device *vdev)
}
/* Last of all, set up some receive buffers. */
- try_fill_recv(&vi->rq, GFP_KERNEL);
-
- /* If we didn't even get one input buffer, we're useless. */
- if (vi->rq.num == 0) {
- err = -ENOMEM;
- goto unregister;
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ try_fill_recv(&vi->rq[i], GFP_KERNEL);
+
+ /* If we didn't even get one input buffer, we're useless. */
+ if (vi->rq[i].num == 0) {
+ free_unused_bufs(vi);
+ err = -ENOMEM;
+ goto free_recv_bufs;
+ }
}
/* Assume link up if device can't report link status,
@@ -1182,13 +1450,19 @@ static int virtnet_probe(struct virtio_device *vdev)
netif_carrier_on(dev);
}
- pr_debug("virtnet: registered device %s\n", dev->name);
+ pr_debug("virtnet: registered device %s with %d RX and TX vq's\n",
+ dev->name, max_queue_pairs);
+
return 0;
-unregister:
+free_recv_bufs:
+ free_receive_bufs(vi);
unregister_netdev(dev);
+
free_vqs:
- vdev->config->del_vqs(vdev);
+ cancel_delayed_work_sync(&vi->refill);
+ virtnet_del_vqs(vi);
+
free_stats:
free_percpu(vi->stats);
free:
@@ -1196,28 +1470,6 @@ free:
return err;
}
-static void free_unused_bufs(struct virtnet_info *vi)
-{
- void *buf;
- while (1) {
- buf = virtqueue_detach_unused_buf(vi->sq.vq);
- if (!buf)
- break;
- dev_kfree_skb(buf);
- }
- while (1) {
- buf = virtqueue_detach_unused_buf(vi->rq.vq);
- if (!buf)
- break;
- if (vi->mergeable_rx_bufs || vi->big_packets)
- give_pages(&vi->rq, buf);
- else
- dev_kfree_skb(buf);
- --vi->rq.num;
- }
- BUG_ON(vi->rq.num != 0);
-}
-
static void remove_vq_common(struct virtnet_info *vi)
{
vi->vdev->config->reset(vi->vdev);
@@ -1225,10 +1477,9 @@ static void remove_vq_common(struct virtnet_info *vi)
/* Free unused buffers in both send and recv, if any. */
free_unused_bufs(vi);
- vi->vdev->config->del_vqs(vi->vdev);
+ free_receive_bufs(vi);
- while (vi->rq.pages)
- __free_pages(get_a_page(&vi->rq, GFP_KERNEL), 0);
+ virtnet_del_vqs(vi);
}
static void __devexit virtnet_remove(struct virtio_device *vdev)
@@ -1254,6 +1505,7 @@ static void __devexit virtnet_remove(struct virtio_device *vdev)
static int virtnet_freeze(struct virtio_device *vdev)
{
struct virtnet_info *vi = vdev->priv;
+ int i;
/* Prevent config work handler from accessing the device */
mutex_lock(&vi->config_lock);
@@ -1264,7 +1516,10 @@ static int virtnet_freeze(struct virtio_device *vdev)
cancel_delayed_work_sync(&vi->refill);
if (netif_running(vi->dev))
- napi_disable(&vi->rq.napi);
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ napi_disable(&vi->rq[i].napi);
+ netif_napi_del(&vi->rq[i].napi);
+ }
remove_vq_common(vi);
@@ -1276,24 +1531,29 @@ static int virtnet_freeze(struct virtio_device *vdev)
static int virtnet_restore(struct virtio_device *vdev)
{
struct virtnet_info *vi = vdev->priv;
- int err;
+ int err, i;
err = init_vqs(vi);
if (err)
return err;
if (netif_running(vi->dev))
- virtnet_napi_enable(&vi->rq);
+ for (i = 0; i < vi->max_queue_pairs; i++)
+ virtnet_napi_enable(&vi->rq[i]);
netif_device_attach(vi->dev);
- if (!try_fill_recv(&vi->rq, GFP_KERNEL))
- schedule_delayed_work(&vi->refill, 0);
+ for (i = 0; i < vi->max_queue_pairs; i++)
+ if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
+ schedule_delayed_work(&vi->refill, 0);
mutex_lock(&vi->config_lock);
vi->config_enable = true;
mutex_unlock(&vi->config_lock);
+ if (vi->has_cvq && virtio_has_feature(vi->vdev, VIRTIO_NET_F_RFS))
+ virtnet_set_queues(vi);
+
return 0;
}
#endif
@@ -1311,7 +1571,7 @@ static unsigned int features[] = {
VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO,
VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ,
VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN,
- VIRTIO_NET_F_GUEST_ANNOUNCE,
+ VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_RFS,
};
static struct virtio_driver virtio_net_driver = {
@@ -1329,6 +1589,12 @@ static struct virtio_driver virtio_net_driver = {
#endif
};
+static const struct ethtool_ops virtnet_ethtool_ops = {
+ .get_drvinfo = virtnet_get_drvinfo,
+ .get_link = ethtool_op_get_link,
+ .get_ringparam = virtnet_get_ringparam,
+};
+
static int __init init(void)
{
return register_virtio_driver(&virtio_net_driver);
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index 2470f54..6056cec 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h
@@ -51,6 +51,7 @@
#define VIRTIO_NET_F_CTRL_RX_EXTRA 20 /* Extra RX mode control support */
#define VIRTIO_NET_F_GUEST_ANNOUNCE 21 /* Guest can announce device on the
* network */
+#define VIRTIO_NET_F_RFS 22 /* Device supports multiple TXQ/RXQ */
#define VIRTIO_NET_S_LINK_UP 1 /* Link is up */
#define VIRTIO_NET_S_ANNOUNCE 2 /* Announcement is needed */
@@ -60,6 +61,8 @@ struct virtio_net_config {
__u8 mac[6];
/* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */
__u16 status;
+ /* Total number of RX/TX queues */
+ __u16 max_virtqueue_pairs;
} __attribute__((packed));
/* This is the first element of the scatter-gather list. If you don't
@@ -166,4 +169,17 @@ struct virtio_net_ctrl_mac {
#define VIRTIO_NET_CTRL_ANNOUNCE 3
#define VIRTIO_NET_CTRL_ANNOUNCE_ACK 0
+/*
+ * Control multiqueue
+ *
+ */
+struct virtio_net_ctrl_rfs {
+ u16 virtqueue_pairs;
+};
+
+#define VIRTIO_NET_CTRL_RFS 4
+ #define VIRTIO_NET_CTRL_RFS_VQ_PAIRS_SET 0
+ #define VIRTIO_NET_CTRL_RFS_VQ_PAIRS_MIN 1
+ #define VIRTIO_NET_CTRL_RFS_VQ_PAIRS_MAX 0x8000
+
#endif /* _LINUX_VIRTIO_NET_H */
--
1.7.1
^ permalink raw reply related
* [PATCH net-next 1/3] virtio-net: separate fields of sending/receiving queue from virtnet_info
From: Jason Wang @ 2012-12-04 11:07 UTC (permalink / raw)
To: rusty, mst, virtualization, netdev, linux-kernel, davem
Cc: krkumar2, kvm, bhutchings, jwhan, shiyer
In-Reply-To: <1354619278-35702-1-git-send-email-jasowang@redhat.com>
To support multiqueue transmitq/receiveq, the first step is to separate queue
related structure from virtnet_info. This patch introduce send_queue and
receive_queue structure and use the pointer to them as the parameter in
functions handling sending/receiving.
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/net/virtio_net.c | 271 +++++++++++++++++++++++++---------------------
1 files changed, 149 insertions(+), 122 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 8262232..266f712 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -51,16 +51,40 @@ struct virtnet_stats {
u64 rx_packets;
};
-struct virtnet_info {
- struct virtio_device *vdev;
- struct virtqueue *rvq, *svq, *cvq;
- struct net_device *dev;
+/* Internal representation of a send virtqueue */
+struct send_queue {
+ /* Virtqueue associated with this send _queue */
+ struct virtqueue *vq;
+
+ /* TX: fragments + linear part + virtio header */
+ struct scatterlist sg[MAX_SKB_FRAGS + 2];
+};
+
+/* Internal representation of a receive virtqueue */
+struct receive_queue {
+ /* Virtqueue associated with this receive_queue */
+ struct virtqueue *vq;
+
struct napi_struct napi;
- unsigned int status;
/* Number of input buffers, and max we've ever had. */
unsigned int num, max;
+ /* Chain pages by the private ptr. */
+ struct page *pages;
+
+ /* RX: fragments + linear part + virtio header */
+ struct scatterlist sg[MAX_SKB_FRAGS + 2];
+};
+
+struct virtnet_info {
+ struct virtio_device *vdev;
+ struct virtqueue *cvq;
+ struct net_device *dev;
+ struct send_queue sq;
+ struct receive_queue rq;
+ unsigned int status;
+
/* I like... big packets and I cannot lie! */
bool big_packets;
@@ -81,13 +105,6 @@ struct virtnet_info {
/* Lock for config space updates */
struct mutex config_lock;
-
- /* Chain pages by the private ptr. */
- struct page *pages;
-
- /* fragments + linear part + virtio header */
- struct scatterlist rx_sg[MAX_SKB_FRAGS + 2];
- struct scatterlist tx_sg[MAX_SKB_FRAGS + 2];
};
struct skb_vnet_hdr {
@@ -117,22 +134,22 @@ static inline struct skb_vnet_hdr *skb_vnet_hdr(struct sk_buff *skb)
* private is used to chain pages for big packets, put the whole
* most recent used list in the beginning for reuse
*/
-static void give_pages(struct virtnet_info *vi, struct page *page)
+static void give_pages(struct receive_queue *rq, struct page *page)
{
struct page *end;
- /* Find end of list, sew whole thing into vi->pages. */
+ /* Find end of list, sew whole thing into vi->rq.pages. */
for (end = page; end->private; end = (struct page *)end->private);
- end->private = (unsigned long)vi->pages;
- vi->pages = page;
+ end->private = (unsigned long)rq->pages;
+ rq->pages = page;
}
-static struct page *get_a_page(struct virtnet_info *vi, gfp_t gfp_mask)
+static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
{
- struct page *p = vi->pages;
+ struct page *p = rq->pages;
if (p) {
- vi->pages = (struct page *)p->private;
+ rq->pages = (struct page *)p->private;
/* clear private here, it is used to chain pages */
p->private = 0;
} else
@@ -140,12 +157,12 @@ static struct page *get_a_page(struct virtnet_info *vi, gfp_t gfp_mask)
return p;
}
-static void skb_xmit_done(struct virtqueue *svq)
+static void skb_xmit_done(struct virtqueue *vq)
{
- struct virtnet_info *vi = svq->vdev->priv;
+ struct virtnet_info *vi = vq->vdev->priv;
/* Suppress further interrupts. */
- virtqueue_disable_cb(svq);
+ virtqueue_disable_cb(vq);
/* We were probably waiting for more output buffers. */
netif_wake_queue(vi->dev);
@@ -167,9 +184,10 @@ static void set_skb_frag(struct sk_buff *skb, struct page *page,
}
/* Called from bottom half context */
-static struct sk_buff *page_to_skb(struct virtnet_info *vi,
+static struct sk_buff *page_to_skb(struct receive_queue *rq,
struct page *page, unsigned int len)
{
+ struct virtnet_info *vi = rq->vq->vdev->priv;
struct sk_buff *skb;
struct skb_vnet_hdr *hdr;
unsigned int copy, hdr_len, offset;
@@ -224,12 +242,12 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
}
if (page)
- give_pages(vi, page);
+ give_pages(rq, page);
return skb;
}
-static int receive_mergeable(struct virtnet_info *vi, struct sk_buff *skb)
+static int receive_mergeable(struct receive_queue *rq, struct sk_buff *skb)
{
struct skb_vnet_hdr *hdr = skb_vnet_hdr(skb);
struct page *page;
@@ -243,7 +261,7 @@ static int receive_mergeable(struct virtnet_info *vi, struct sk_buff *skb)
skb->dev->stats.rx_length_errors++;
return -EINVAL;
}
- page = virtqueue_get_buf(vi->rvq, &len);
+ page = virtqueue_get_buf(rq->vq, &len);
if (!page) {
pr_debug("%s: rx error: %d buffers missing\n",
skb->dev->name, hdr->mhdr.num_buffers);
@@ -256,14 +274,15 @@ static int receive_mergeable(struct virtnet_info *vi, struct sk_buff *skb)
set_skb_frag(skb, page, 0, &len);
- --vi->num;
+ --rq->num;
}
return 0;
}
-static void receive_buf(struct net_device *dev, void *buf, unsigned int len)
+static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
{
- struct virtnet_info *vi = netdev_priv(dev);
+ struct virtnet_info *vi = rq->vq->vdev->priv;
+ struct net_device *dev = vi->dev;
struct virtnet_stats *stats = this_cpu_ptr(vi->stats);
struct sk_buff *skb;
struct page *page;
@@ -273,7 +292,7 @@ static void receive_buf(struct net_device *dev, void *buf, unsigned int len)
pr_debug("%s: short packet %i\n", dev->name, len);
dev->stats.rx_length_errors++;
if (vi->mergeable_rx_bufs || vi->big_packets)
- give_pages(vi, buf);
+ give_pages(rq, buf);
else
dev_kfree_skb(buf);
return;
@@ -285,14 +304,14 @@ static void receive_buf(struct net_device *dev, void *buf, unsigned int len)
skb_trim(skb, len);
} else {
page = buf;
- skb = page_to_skb(vi, page, len);
+ skb = page_to_skb(rq, page, len);
if (unlikely(!skb)) {
dev->stats.rx_dropped++;
- give_pages(vi, page);
+ give_pages(rq, page);
return;
}
if (vi->mergeable_rx_bufs)
- if (receive_mergeable(vi, skb)) {
+ if (receive_mergeable(rq, skb)) {
dev_kfree_skb(skb);
return;
}
@@ -359,8 +378,9 @@ frame_err:
dev_kfree_skb(skb);
}
-static int add_recvbuf_small(struct virtnet_info *vi, gfp_t gfp)
+static int add_recvbuf_small(struct receive_queue *rq, gfp_t gfp)
{
+ struct virtnet_info *vi = rq->vq->vdev->priv;
struct sk_buff *skb;
struct skb_vnet_hdr *hdr;
int err;
@@ -372,77 +392,77 @@ static int add_recvbuf_small(struct virtnet_info *vi, gfp_t gfp)
skb_put(skb, MAX_PACKET_LEN);
hdr = skb_vnet_hdr(skb);
- sg_set_buf(vi->rx_sg, &hdr->hdr, sizeof hdr->hdr);
+ sg_set_buf(rq->sg, &hdr->hdr, sizeof hdr->hdr);
- skb_to_sgvec(skb, vi->rx_sg + 1, 0, skb->len);
+ skb_to_sgvec(skb, rq->sg + 1, 0, skb->len);
- err = virtqueue_add_buf(vi->rvq, vi->rx_sg, 0, 2, skb, gfp);
+ err = virtqueue_add_buf(rq->vq, rq->sg, 0, 2, skb, gfp);
if (err < 0)
dev_kfree_skb(skb);
return err;
}
-static int add_recvbuf_big(struct virtnet_info *vi, gfp_t gfp)
+static int add_recvbuf_big(struct receive_queue *rq, gfp_t gfp)
{
struct page *first, *list = NULL;
char *p;
int i, err, offset;
- /* page in vi->rx_sg[MAX_SKB_FRAGS + 1] is list tail */
+ /* page in rq->sg[MAX_SKB_FRAGS + 1] is list tail */
for (i = MAX_SKB_FRAGS + 1; i > 1; --i) {
- first = get_a_page(vi, gfp);
+ first = get_a_page(rq, gfp);
if (!first) {
if (list)
- give_pages(vi, list);
+ give_pages(rq, list);
return -ENOMEM;
}
- sg_set_buf(&vi->rx_sg[i], page_address(first), PAGE_SIZE);
+ sg_set_buf(&rq->sg[i], page_address(first), PAGE_SIZE);
/* chain new page in list head to match sg */
first->private = (unsigned long)list;
list = first;
}
- first = get_a_page(vi, gfp);
+ first = get_a_page(rq, gfp);
if (!first) {
- give_pages(vi, list);
+ give_pages(rq, list);
return -ENOMEM;
}
p = page_address(first);
- /* vi->rx_sg[0], vi->rx_sg[1] share the same page */
- /* a separated vi->rx_sg[0] for virtio_net_hdr only due to QEMU bug */
- sg_set_buf(&vi->rx_sg[0], p, sizeof(struct virtio_net_hdr));
+ /* rq->sg[0], rq->sg[1] share the same page */
+ /* a separated rq->sg[0] for virtio_net_hdr only due to QEMU bug */
+ sg_set_buf(&rq->sg[0], p, sizeof(struct virtio_net_hdr));
- /* vi->rx_sg[1] for data packet, from offset */
+ /* rq->sg[1] for data packet, from offset */
offset = sizeof(struct padded_vnet_hdr);
- sg_set_buf(&vi->rx_sg[1], p + offset, PAGE_SIZE - offset);
+ sg_set_buf(&rq->sg[1], p + offset, PAGE_SIZE - offset);
/* chain first in list head */
first->private = (unsigned long)list;
- err = virtqueue_add_buf(vi->rvq, vi->rx_sg, 0, MAX_SKB_FRAGS + 2,
+ err = virtqueue_add_buf(rq->vq, rq->sg, 0, MAX_SKB_FRAGS + 2,
first, gfp);
if (err < 0)
- give_pages(vi, first);
+ give_pages(rq, first);
return err;
}
-static int add_recvbuf_mergeable(struct virtnet_info *vi, gfp_t gfp)
+static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp)
{
struct page *page;
int err;
- page = get_a_page(vi, gfp);
+ page = get_a_page(rq, gfp);
if (!page)
return -ENOMEM;
- sg_init_one(vi->rx_sg, page_address(page), PAGE_SIZE);
+ sg_init_one(rq->sg, page_address(page), PAGE_SIZE);
- err = virtqueue_add_buf(vi->rvq, vi->rx_sg, 0, 1, page, gfp);
+ err = virtqueue_add_buf(rq->vq, rq->sg, 0, 1, page, gfp);
if (err < 0)
- give_pages(vi, page);
+ give_pages(rq, page);
return err;
}
@@ -454,65 +474,68 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi, gfp_t gfp)
* before we're receiving packets, or from refill_work which is
* careful to disable receiving (using napi_disable).
*/
-static bool try_fill_recv(struct virtnet_info *vi, gfp_t gfp)
+static bool try_fill_recv(struct receive_queue *rq, gfp_t gfp)
{
+ struct virtnet_info *vi = rq->vq->vdev->priv;
int err;
bool oom;
do {
if (vi->mergeable_rx_bufs)
- err = add_recvbuf_mergeable(vi, gfp);
+ err = add_recvbuf_mergeable(rq, gfp);
else if (vi->big_packets)
- err = add_recvbuf_big(vi, gfp);
+ err = add_recvbuf_big(rq, gfp);
else
- err = add_recvbuf_small(vi, gfp);
+ err = add_recvbuf_small(rq, gfp);
oom = err == -ENOMEM;
if (err < 0)
break;
- ++vi->num;
+ ++rq->num;
} while (err > 0);
- if (unlikely(vi->num > vi->max))
- vi->max = vi->num;
- virtqueue_kick(vi->rvq);
+ if (unlikely(rq->num > rq->max))
+ rq->max = rq->num;
+ virtqueue_kick(rq->vq);
return !oom;
}
static void skb_recv_done(struct virtqueue *rvq)
{
struct virtnet_info *vi = rvq->vdev->priv;
+ struct receive_queue *rq = &vi->rq;
+
/* Schedule NAPI, Suppress further interrupts if successful. */
- if (napi_schedule_prep(&vi->napi)) {
+ if (napi_schedule_prep(&rq->napi)) {
virtqueue_disable_cb(rvq);
- __napi_schedule(&vi->napi);
+ __napi_schedule(&rq->napi);
}
}
-static void virtnet_napi_enable(struct virtnet_info *vi)
+static void virtnet_napi_enable(struct receive_queue *rq)
{
- napi_enable(&vi->napi);
+ napi_enable(&rq->napi);
/* If all buffers were filled by other side before we napi_enabled, we
* won't get another interrupt, so process any outstanding packets
* now. virtnet_poll wants re-enable the queue, so we disable here.
* We synchronize against interrupts via NAPI_STATE_SCHED */
- if (napi_schedule_prep(&vi->napi)) {
- virtqueue_disable_cb(vi->rvq);
+ if (napi_schedule_prep(&rq->napi)) {
+ virtqueue_disable_cb(rq->vq);
local_bh_disable();
- __napi_schedule(&vi->napi);
+ __napi_schedule(&rq->napi);
local_bh_enable();
}
}
static void refill_work(struct work_struct *work)
{
- struct virtnet_info *vi;
+ struct virtnet_info *vi =
+ container_of(work, struct virtnet_info, refill.work);
bool still_empty;
- vi = container_of(work, struct virtnet_info, refill.work);
- napi_disable(&vi->napi);
- still_empty = !try_fill_recv(vi, GFP_KERNEL);
- virtnet_napi_enable(vi);
+ napi_disable(&vi->rq.napi);
+ still_empty = !try_fill_recv(&vi->rq, GFP_KERNEL);
+ virtnet_napi_enable(&vi->rq);
/* In theory, this can happen: if we don't get any buffers in
* we will *never* try to fill again. */
@@ -522,29 +545,31 @@ static void refill_work(struct work_struct *work)
static int virtnet_poll(struct napi_struct *napi, int budget)
{
- struct virtnet_info *vi = container_of(napi, struct virtnet_info, napi);
+ struct receive_queue *rq =
+ container_of(napi, struct receive_queue, napi);
+ struct virtnet_info *vi = rq->vq->vdev->priv;
void *buf;
unsigned int len, received = 0;
again:
while (received < budget &&
- (buf = virtqueue_get_buf(vi->rvq, &len)) != NULL) {
- receive_buf(vi->dev, buf, len);
- --vi->num;
+ (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
+ receive_buf(rq, buf, len);
+ --rq->num;
received++;
}
- if (vi->num < vi->max / 2) {
- if (!try_fill_recv(vi, GFP_ATOMIC))
+ if (rq->num < rq->max / 2) {
+ if (!try_fill_recv(rq, GFP_ATOMIC))
schedule_delayed_work(&vi->refill, 0);
}
/* Out of packets? */
if (received < budget) {
napi_complete(napi);
- if (unlikely(!virtqueue_enable_cb(vi->rvq)) &&
+ if (unlikely(!virtqueue_enable_cb(rq->vq)) &&
napi_schedule_prep(napi)) {
- virtqueue_disable_cb(vi->rvq);
+ virtqueue_disable_cb(rq->vq);
__napi_schedule(napi);
goto again;
}
@@ -553,13 +578,14 @@ again:
return received;
}
-static unsigned int free_old_xmit_skbs(struct virtnet_info *vi)
+static unsigned int free_old_xmit_skbs(struct send_queue *sq)
{
struct sk_buff *skb;
unsigned int len, tot_sgs = 0;
+ struct virtnet_info *vi = sq->vq->vdev->priv;
struct virtnet_stats *stats = this_cpu_ptr(vi->stats);
- while ((skb = virtqueue_get_buf(vi->svq, &len)) != NULL) {
+ while ((skb = virtqueue_get_buf(sq->vq, &len)) != NULL) {
pr_debug("Sent skb %p\n", skb);
u64_stats_update_begin(&stats->tx_syncp);
@@ -573,10 +599,11 @@ static unsigned int free_old_xmit_skbs(struct virtnet_info *vi)
return tot_sgs;
}
-static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb)
+static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
{
struct skb_vnet_hdr *hdr = skb_vnet_hdr(skb);
const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
+ struct virtnet_info *vi = sq->vq->vdev->priv;
pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest);
@@ -611,25 +638,26 @@ static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb)
/* Encode metadata header at front. */
if (vi->mergeable_rx_bufs)
- sg_set_buf(vi->tx_sg, &hdr->mhdr, sizeof hdr->mhdr);
+ sg_set_buf(sq->sg, &hdr->mhdr, sizeof hdr->mhdr);
else
- sg_set_buf(vi->tx_sg, &hdr->hdr, sizeof hdr->hdr);
+ sg_set_buf(sq->sg, &hdr->hdr, sizeof hdr->hdr);
- hdr->num_sg = skb_to_sgvec(skb, vi->tx_sg + 1, 0, skb->len) + 1;
- return virtqueue_add_buf(vi->svq, vi->tx_sg, hdr->num_sg,
+ hdr->num_sg = skb_to_sgvec(skb, sq->sg + 1, 0, skb->len) + 1;
+ return virtqueue_add_buf(sq->vq, sq->sg, hdr->num_sg,
0, skb, GFP_ATOMIC);
}
static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct virtnet_info *vi = netdev_priv(dev);
+ struct send_queue *sq = &vi->sq;
int capacity;
/* Free up any pending old buffers before queueing new ones. */
- free_old_xmit_skbs(vi);
+ free_old_xmit_skbs(sq);
/* Try to transmit */
- capacity = xmit_skb(vi, skb);
+ capacity = xmit_skb(sq, skb);
/* This can happen with OOM and indirect buffers. */
if (unlikely(capacity < 0)) {
@@ -648,7 +676,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
kfree_skb(skb);
return NETDEV_TX_OK;
}
- virtqueue_kick(vi->svq);
+ virtqueue_kick(sq->vq);
/* Don't wait up for transmitted skbs to be freed. */
skb_orphan(skb);
@@ -658,12 +686,12 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
* before it gets out of hand. Naturally, this wastes entries. */
if (capacity < 2+MAX_SKB_FRAGS) {
netif_stop_queue(dev);
- if (unlikely(!virtqueue_enable_cb_delayed(vi->svq))) {
+ if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
/* More just got used, free them then recheck. */
- capacity += free_old_xmit_skbs(vi);
+ capacity += free_old_xmit_skbs(sq);
if (capacity >= 2+MAX_SKB_FRAGS) {
netif_start_queue(dev);
- virtqueue_disable_cb(vi->svq);
+ virtqueue_disable_cb(sq->vq);
}
}
}
@@ -731,7 +759,7 @@ static void virtnet_netpoll(struct net_device *dev)
{
struct virtnet_info *vi = netdev_priv(dev);
- napi_schedule(&vi->napi);
+ napi_schedule(&vi->rq.napi);
}
#endif
@@ -740,10 +768,10 @@ static int virtnet_open(struct net_device *dev)
struct virtnet_info *vi = netdev_priv(dev);
/* Make sure we have some buffers: if oom use wq. */
- if (!try_fill_recv(vi, GFP_KERNEL))
+ if (!try_fill_recv(&vi->rq, GFP_KERNEL))
schedule_delayed_work(&vi->refill, 0);
- virtnet_napi_enable(vi);
+ virtnet_napi_enable(&vi->rq);
return 0;
}
@@ -808,7 +836,7 @@ static int virtnet_close(struct net_device *dev)
/* Make sure refill_work doesn't re-enable napi! */
cancel_delayed_work_sync(&vi->refill);
- napi_disable(&vi->napi);
+ napi_disable(&vi->rq.napi);
return 0;
}
@@ -920,11 +948,10 @@ static void virtnet_get_ringparam(struct net_device *dev,
{
struct virtnet_info *vi = netdev_priv(dev);
- ring->rx_max_pending = virtqueue_get_vring_size(vi->rvq);
- ring->tx_max_pending = virtqueue_get_vring_size(vi->svq);
+ ring->rx_max_pending = virtqueue_get_vring_size(vi->rq.vq);
+ ring->tx_max_pending = virtqueue_get_vring_size(vi->sq.vq);
ring->rx_pending = ring->rx_max_pending;
ring->tx_pending = ring->tx_max_pending;
-
}
@@ -1034,8 +1061,8 @@ static int init_vqs(struct virtnet_info *vi)
if (err)
return err;
- vi->rvq = vqs[0];
- vi->svq = vqs[1];
+ vi->rq.vq = vqs[0];
+ vi->sq.vq = vqs[1];
if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)) {
vi->cvq = vqs[2];
@@ -1100,11 +1127,11 @@ static int virtnet_probe(struct virtio_device *vdev)
/* Set up our device-specific information */
vi = netdev_priv(dev);
- netif_napi_add(dev, &vi->napi, virtnet_poll, napi_weight);
+ netif_napi_add(dev, &vi->rq.napi, virtnet_poll, napi_weight);
vi->dev = dev;
vi->vdev = vdev;
vdev->priv = vi;
- vi->pages = NULL;
+ vi->rq.pages = NULL;
vi->stats = alloc_percpu(struct virtnet_stats);
err = -ENOMEM;
if (vi->stats == NULL)
@@ -1114,8 +1141,8 @@ static int virtnet_probe(struct virtio_device *vdev)
mutex_init(&vi->config_lock);
vi->config_enable = true;
INIT_WORK(&vi->config_work, virtnet_config_changed_work);
- sg_init_table(vi->rx_sg, ARRAY_SIZE(vi->rx_sg));
- sg_init_table(vi->tx_sg, ARRAY_SIZE(vi->tx_sg));
+ sg_init_table(vi->rq.sg, ARRAY_SIZE(vi->rq.sg));
+ sg_init_table(vi->sq.sg, ARRAY_SIZE(vi->sq.sg));
/* If we can receive ANY GSO packets, we must allocate large ones. */
if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
@@ -1137,10 +1164,10 @@ static int virtnet_probe(struct virtio_device *vdev)
}
/* Last of all, set up some receive buffers. */
- try_fill_recv(vi, GFP_KERNEL);
+ try_fill_recv(&vi->rq, GFP_KERNEL);
/* If we didn't even get one input buffer, we're useless. */
- if (vi->num == 0) {
+ if (vi->rq.num == 0) {
err = -ENOMEM;
goto unregister;
}
@@ -1173,22 +1200,22 @@ static void free_unused_bufs(struct virtnet_info *vi)
{
void *buf;
while (1) {
- buf = virtqueue_detach_unused_buf(vi->svq);
+ buf = virtqueue_detach_unused_buf(vi->sq.vq);
if (!buf)
break;
dev_kfree_skb(buf);
}
while (1) {
- buf = virtqueue_detach_unused_buf(vi->rvq);
+ buf = virtqueue_detach_unused_buf(vi->rq.vq);
if (!buf)
break;
if (vi->mergeable_rx_bufs || vi->big_packets)
- give_pages(vi, buf);
+ give_pages(&vi->rq, buf);
else
dev_kfree_skb(buf);
- --vi->num;
+ --vi->rq.num;
}
- BUG_ON(vi->num != 0);
+ BUG_ON(vi->rq.num != 0);
}
static void remove_vq_common(struct virtnet_info *vi)
@@ -1200,8 +1227,8 @@ static void remove_vq_common(struct virtnet_info *vi)
vi->vdev->config->del_vqs(vi->vdev);
- while (vi->pages)
- __free_pages(get_a_page(vi, GFP_KERNEL), 0);
+ while (vi->rq.pages)
+ __free_pages(get_a_page(&vi->rq, GFP_KERNEL), 0);
}
static void __devexit virtnet_remove(struct virtio_device *vdev)
@@ -1237,7 +1264,7 @@ static int virtnet_freeze(struct virtio_device *vdev)
cancel_delayed_work_sync(&vi->refill);
if (netif_running(vi->dev))
- napi_disable(&vi->napi);
+ napi_disable(&vi->rq.napi);
remove_vq_common(vi);
@@ -1256,11 +1283,11 @@ static int virtnet_restore(struct virtio_device *vdev)
return err;
if (netif_running(vi->dev))
- virtnet_napi_enable(vi);
+ virtnet_napi_enable(&vi->rq);
netif_device_attach(vi->dev);
- if (!try_fill_recv(vi, GFP_KERNEL))
+ if (!try_fill_recv(&vi->rq, GFP_KERNEL))
schedule_delayed_work(&vi->refill, 0);
mutex_lock(&vi->config_lock);
--
1.7.1
^ permalink raw reply related
* [PATCH net-next 0/3] Multiqueue support for virtio-net
From: Jason Wang @ 2012-12-04 11:07 UTC (permalink / raw)
To: rusty, mst, virtualization, netdev, linux-kernel, davem
Cc: krkumar2, kvm, bhutchings, jwhan, shiyer
Hi all:
This series is an update version of multiqueue virtio-net driver based on
Krishna Kumar's work to let virtio-net use multiple rx/tx queues to do the
packets reception and transmission. Please review and comments.
A protype implementation of qemu-kvm support could by found in
git://github.com/jasowang/qemu-kvm-mq.git. To start a guest with two queues, you
could specify the queues parameters to both tap and virtio-net like:
./qemu-kvm -netdev tap,queues=2,... -device virtio-net-pci,queues=2,...
then enable the multiqueue through ethtool by:
ethtool -L eth0 combined 2
Changes from RFC v7:
Addressing Rusty's comments:
- align the implementation (location of cvq) to v5.
- fix the style issue.
- use a global refill instead of per-vq one.
- check the VIRTIO_NET_F_RFS before calling virtnet_set_queues()
Addresing Michael's comments
- rename the curr_queue_pairs in virtnet_probe() to max_queue_pairs
- validate the number of queue pairs supported by the device against
VIRTIO_NET_CTRL_RFS_VQ_PAIRS_MIN and VIRTIO_NET_CTRL_RFS_VQ_PAIRS_MAX.
- don't crash when failing to change the number of virtqueues
- don't set the affinity hint when onle single queue is used or there's too much
virtqueues
- add a TODO of handling cpu hotplug
- allow user to set the nubmer of queue pairs between 1 and max_queue_pairs
Changes from RFC v6:
- Align the implementation with the RFC spec update v5
- Addressing Rusty's comments:
* split the patches
* rename to max_queue_pairs and curr_queue_pairs
* remove the useless status
* fix the hibernation bug
- Addressing Ben's comments:
* check other parameters in ethtool_set_queues
Changes from RFC v5:
- Align the implementation with the RFC spec update v4
- Switch the mode between single mode and multiqueue mode without reset
- Remove the 256 limitation of queues
- Use helpers to do the mapping between virtqueues and tx/rx queues
- Use commbined channels instead of separated rx/tx queus when do the queue
number configuartion
- Other coding style comments from Michael
Changes from RFC v4:
- Add ability to negotiate the number of queues through control virtqueue
- Ethtool -{L|l} support and default the tx/rx queue number to 1
- Expose the API to set irq affinity instead of irq itself
Changes from RFC v3:
- Rebase to the net-next
- Let queue 2 to be the control virtqueue to obey the spec
- Prodives irq affinity
- Choose txq based on processor id
Reference:
- Virtio spec RFC: http://patchwork.ozlabs.org/patch/201303/
- RFC V7:https://lkml.org/lkml/2012/11/27/177
- RFC V6: https://lkml.org/lkml/2012/10/30/127
- RFC V5: http://lwn.net/Articles/505388/
- RFC V4: https://lkml.org/lkml/2012/6/25/120
- RFC V2: http://lwn.net/Articles/467283/
Perf Numbers:
Will do some basic test and post as a reply to this mail.
Jason Wang (3):
virtio-net: separate fields of sending/receiving queue from
virtnet_info
virtio_net: multiqueue support
virtio-net: change the number of queues through ethtool
drivers/net/virtio_net.c | 723 ++++++++++++++++++++++++++++-----------
include/uapi/linux/virtio_net.h | 16 +
2 files changed, 546 insertions(+), 193 deletions(-)
^ permalink raw reply
* Re: [PATCH 3/3] net: cpsw: implement ioctl for MII
From: Jan Lübbe @ 2012-12-04 11:06 UTC (permalink / raw)
To: Mugunthan V N
Cc: netdev, David S. Miller, Vaibhav Hiremath, linux-arm-kernel,
linux-omap
In-Reply-To: <50BCDB9B.80307@ti.com>
On Mon, 2012-12-03 at 22:34 +0530, Mugunthan V N wrote:
> Already ndo_do_ioctl is already implemented. Can you rebase the patch
> with latest git repo
> and resubmit the patch
Sorry, I should have checked that before. I'll update the other patches
and resubmit.
--
Pengutronix e.K. | |
Industrial Linux Solutions | http://www.pengutronix.de/ |
Peiner Str. 6-8, 31137 Hildesheim, Germany | Phone: +49-5121-206917-0 |
Amtsgericht Hildesheim, HRA 2686 | Fax: +49-5121-206917-5555 |
^ permalink raw reply
* [PATCH 3.0.y] route: release dst_entry.hh_cache when handling redirects
From: Michal Kubecek @ 2012-12-04 10:09 UTC (permalink / raw)
To: stable; +Cc: netdev, Eric Dumazet
Stable-3.0 commit 42ab5316 (ipv4: fix redirect handling) was
backport of mainline commit 9cc20b26 from 3.2-rc3 where hh
member of struct dst_entry was already gone.
However, in 3.0 we still have it and we have to clean it as
well, otherwise it keeps pointing to the cleaned up (and
unusable) hh_cache entry and packets cannot be sent out.
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
---
net/ipv4/route.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6b95f74..5ff2614 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1374,6 +1374,7 @@ static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
struct rtable *rt = (struct rtable *) dst;
__be32 orig_gw = rt->rt_gateway;
struct neighbour *n, *old_n;
+ struct hh_cache *old_hh;
dst_confirm(&rt->dst);
@@ -1381,6 +1382,9 @@ static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
n = __arp_bind_neighbour(&rt->dst, rt->rt_gateway);
if (IS_ERR(n))
return PTR_ERR(n);
+ old_hh = xchg(&rt->dst.hh, NULL);
+ if (old_hh)
+ hh_cache_put(old_hh);
old_n = xchg(&rt->dst._neighbour, n);
if (old_n)
neigh_release(old_n);
--
1.7.10.4
^ permalink raw reply related
* [PATCH] ipv4/route/rtnl: get mcast attributes when dst is multicast
From: Nicolas Dichtel @ 2012-12-04 11:03 UTC (permalink / raw)
To: netdev; +Cc: davem, Nicolas Dichtel
Commit f1ce3062c538 (ipv4: Remove 'rt_dst' from 'struct rtable') removes the
call to ipmr_get_route(), which will get multicast parameters of the route.
I revert the part of the patch that remove this call. I think the goal was only
to get rid of rt_dst field.
The patch is only compiled-tested. My first idea was to remove ipmr_get_route()
because rt_fill_info() was the only user, but it seems the previous patch cleans
the code a bit too much ;-)
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
net/ipv4/route.c | 23 +++++++++++++++++++++--
1 file changed, 21 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index df25142..69135ed 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2232,8 +2232,27 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
error = rt->dst.error;
if (rt_is_input_route(rt)) {
- if (nla_put_u32(skb, RTA_IIF, rt->rt_iif))
- goto nla_put_failure;
+#ifdef CONFIG_IP_MROUTE
+ if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) &&
+ IPV4_DEVCONF_ALL(net, MC_FORWARDING)) {
+ int err = ipmr_get_route(net, skb,
+ fl4->saddr, fl4->daddr,
+ r, nowait);
+ if (err <= 0) {
+ if (!nowait) {
+ if (err == 0)
+ return 0;
+ goto nla_put_failure;
+ } else {
+ if (err == -EMSGSIZE)
+ goto nla_put_failure;
+ error = err;
+ }
+ }
+ } else
+#endif
+ if (nla_put_u32(skb, RTA_IIF, rt->rt_iif))
+ goto nla_put_failure;
}
if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0)
--
1.8.0.1
^ permalink raw reply related
* [PATCH] ip6mr: fix rtm_family of rtnl msg
From: Nicolas Dichtel @ 2012-12-04 11:01 UTC (permalink / raw)
To: netdev; +Cc: davem, kaber, Nicolas Dichtel
We talk about IPv6, hence the family is RTNL_FAMILY_IP6MR!
rtnl_register() is already called with RTNL_FAMILY_IP6MR.
The bug is here since the beginning of this function (commit 5b285cac3570).
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
net/ipv6/ip6mr.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index f7c7c63..940aa52 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2212,7 +2212,7 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
return -EMSGSIZE;
rtm = nlmsg_data(nlh);
- rtm->rtm_family = RTNL_FAMILY_IPMR;
+ rtm->rtm_family = RTNL_FAMILY_IP6MR;
rtm->rtm_dst_len = 128;
rtm->rtm_src_len = 128;
rtm->rtm_tos = 0;
--
1.8.0.1
^ permalink raw reply related
* [PATCH net-next v2] bridge: implement multicast fast leave
From: Cong Wang @ 2012-12-04 9:56 UTC (permalink / raw)
To: netdev; +Cc: Herbert Xu, Stephen Hemminger, bridge, David S. Miller, Cong Wang
V2: make the toggle per-port
Fast leave allows bridge to immediately stops the multicast
traffic on the port receives IGMP Leave when IGMP snooping is enabled,
no timeouts are observed.
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
net/bridge/br_multicast.c | 21 +++++++++++++++++++++
net/bridge/br_private.h | 1 +
net/bridge/br_sysfs_if.c | 20 ++++++++++++++++++++
3 files changed, 42 insertions(+), 0 deletions(-)
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index d53e4f4..02da618 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1226,6 +1226,27 @@ static void br_multicast_leave_group(struct net_bridge *br,
if (!mp)
goto out;
+ if (port && port->multicast_fast_leave) {
+ struct net_bridge_port_group __rcu **pp;
+
+ for (pp = &mp->ports;
+ (p = mlock_dereference(*pp, br)) != NULL;
+ pp = &p->next) {
+ if (p->port != port)
+ continue;
+
+ rcu_assign_pointer(*pp, p->next);
+ hlist_del_init(&p->mglist);
+ del_timer(&p->timer);
+ call_rcu_bh(&p->rcu, br_multicast_free_pg);
+
+ if (!mp->ports && !mp->mglist &&
+ netif_running(br->dev))
+ mod_timer(&mp->timer, jiffies);
+ }
+ goto out;
+ }
+
now = jiffies;
time = now + br->multicast_last_member_count *
br->multicast_last_member_interval;
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 6484069..8f0e789 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -142,6 +142,7 @@ struct net_bridge_port
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
u32 multicast_startup_queries_sent;
unsigned char multicast_router;
+ unsigned char multicast_fast_leave;
struct timer_list multicast_router_timer;
struct timer_list multicast_query_timer;
struct hlist_head mglist;
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index 7ff95ba..dc484ac 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -172,6 +172,25 @@ static int store_multicast_router(struct net_bridge_port *p,
}
static BRPORT_ATTR(multicast_router, S_IRUGO | S_IWUSR, show_multicast_router,
store_multicast_router);
+
+static ssize_t show_multicast_fast_leave(struct net_bridge_port *p,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", p->multicast_fast_leave);
+}
+
+static int store_multicast_fast_leave(struct net_bridge_port *p,
+ unsigned long v)
+{
+ if (p->br->multicast_disabled)
+ return -EINVAL;
+
+ p->multicast_fast_leave = !!v;
+ return 0;
+}
+
+static BRPORT_ATTR(multicast_fast_leave, S_IRUGO | S_IWUSR,
+ show_multicast_fast_leave, store_multicast_fast_leave);
#endif
static const struct brport_attribute *brport_attrs[] = {
@@ -195,6 +214,7 @@ static const struct brport_attribute *brport_attrs[] = {
&brport_attr_root_block,
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
&brport_attr_multicast_router,
+ &brport_attr_multicast_fast_leave,
#endif
NULL
};
^ permalink raw reply related
* Re: [PATCH net-next] bridge: implement multicast fast leave
From: Cong Wang @ 2012-12-04 9:55 UTC (permalink / raw)
To: Herbert Xu; +Cc: netdev, Stephen Hemminger, bridge, David S. Miller
In-Reply-To: <20121204070732.GA32550@gondor.apana.org.au>
On Tue, 2012-12-04 at 15:07 +0800, Herbert Xu wrote:
> On Tue, Dec 04, 2012 at 03:04:52PM +0800, Cong Wang wrote:
> >
> > Per-port sounds better than per-bridge. And I will make it enabled by
> > default.
>
> IMHO the default should be off. Suddenly losing your subscription
> because someone else on the same port unsubscribed is a lot more
> annoying than getting a few minutes of unwanted multicast data.
>
You are right, this is why it should only be used when there is one
client behind the port.
Thanks!
^ permalink raw reply
* Re: [net-next rfc v7 2/3] virtio_net: multiqueue support
From: Jason Wang @ 2012-12-04 9:27 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: krkumar2, kvm, netdev, linux-kernel, virtualization, bhutchings,
jwhan, shiyer
In-Reply-To: <20121204073503.GB7499@redhat.com>
On Tuesday, December 04, 2012 09:35:03 AM Michael S. Tsirkin wrote:
> On Mon, Dec 03, 2012 at 06:30:49PM +0800, Jason Wang wrote:
> > On 12/03/2012 06:14 PM, Michael S. Tsirkin wrote:
> > > On Tue, Nov 27, 2012 at 06:15:59PM +0800, Jason Wang wrote:
> > >> > - if (!try_fill_recv(&vi->rq, GFP_KERNEL))
> > >> > - schedule_delayed_work(&vi->rq.refill, 0);
> > >> > + for (i = 0; i < vi->max_queue_pairs; i++)
> > >> > + if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
> > >> > + schedule_delayed_work(&vi->rq[i].refill, 0);
> > >> >
> > >> > mutex_lock(&vi->config_lock);
> > >> > vi->config_enable = true;
> > >> > mutex_unlock(&vi->config_lock);
> > >> >
> > >> > + BUG_ON(virtnet_set_queues(vi));
> > >> > +
> > >> >
> > >> > return 0;
> > >> >
> > >> > }
> > >> > #endif
> > >
> > > Also crashing on device nack of command is also not nice.
> > > In this case it seems we can just switch to
> > > single-queue mode which should always be safe.
> >
> > Not sure it's safe. It depends on the reason why this call fails. If we
> > left a state that the driver only use single queue but the device use
> > multi queues, we may still lost the network.
>
> Looks like we won't: napi will stay enabled on all queues
> so we will process incoming packets.
True, consider there's no bug in qemu. Will leave a just leave a warning in
next version.
Thanks
^ permalink raw reply
* Re: [net-next rfc v7 2/3] virtio_net: multiqueue support
From: Jason Wang @ 2012-12-04 9:24 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: krkumar2, kvm, netdev, linux-kernel, virtualization, bhutchings,
jwhan, shiyer
In-Reply-To: <20121203111118.GC26167@redhat.com>
On Monday, December 03, 2012 01:11:18 PM Michael S. Tsirkin wrote:
> On Mon, Dec 03, 2012 at 06:01:58PM +0800, Jason Wang wrote:
> > On 12/03/2012 05:47 PM, Michael S. Tsirkin wrote:
> > > On Mon, Dec 03, 2012 at 02:05:27PM +0800, Jason Wang wrote:
> > >> On Monday, December 03, 2012 12:34:08 PM Rusty Russell wrote:
> > >>> Jason Wang <jasowang@redhat.com> writes:
> > >>>> +static const struct ethtool_ops virtnet_ethtool_ops;
> > >>>> +
> > >>>> +/*
> > >>>> + * Converting between virtqueue no. and kernel tx/rx queue no.
> > >>>> + * 0:rx0 1:tx0 2:cvq 3:rx1 4:tx1 ... 2N+1:rxN 2N+2:txN
> > >>>> + */
> > >>>> +static int vq2txq(struct virtqueue *vq)
> > >>>> +{
> > >>>> + int index = virtqueue_get_queue_index(vq);
> > >>>> + return index == 1 ? 0 : (index - 2) / 2;
> > >>>> +}
> > >>>> +
> > >>>> +static int txq2vq(int txq)
> > >>>> +{
> > >>>> + return txq ? 2 * txq + 2 : 1;
> > >>>> +}
> > >>>> +
> > >>>> +static int vq2rxq(struct virtqueue *vq)
> > >>>> +{
> > >>>> + int index = virtqueue_get_queue_index(vq);
> > >>>> + return index ? (index - 1) / 2 : 0;
> > >>>> +}
> > >>>> +
> > >>>> +static int rxq2vq(int rxq)
> > >>>> +{
> > >>>> + return rxq ? 2 * rxq + 1 : 0;
> > >>>> +}
> > >>>> +
> > >>>
> > >>> I thought MST changed the proposed spec to make the control queue
> > >>> always
> > >>> the last one, so this logic becomes trivial.
> > >>
> > >> But it may break the support of legacy guest. If we boot a legacy
> > >> single queue guest on a 2 queue virtio-net device. It may think vq 2
> > >> is cvq which is indeed rx1.
> > >
> > > Legacy guyest support should be handled by host using feature
> > > bits in the usual way: host should detect legacy guest
> > > by checking the VIRTIO_NET_F_RFS feature.
> > >
> > > If VIRTIO_NET_F_RFS is acked, cvq is vq max_virtqueue_pairs * 2.
> > > If it's not acked, cvq is vq 2.
> >
> > We could, but we didn't gain much from this.
>
> It just seems cleaner and easier to understand.
>
> > Furthermore, we need also
> > do the dynamic creation/destroying of virtqueues during feature
> > negotiation which seems not supported in qemu now.
>
> It's not *done* in qemu now, but it seems easy: just call
> virtio_add_queue for vq2 and on from virtio_net_set_features.
> As features can be modified multiple times, we
> should add virtio_del_queue and call that beforehand
> to get to the known state (two vqs).
And also need some work after migration like what we need in setting features.
I'm ok with this method, will change to follow spec v5.
Thanks
^ permalink raw reply
* Re: [net-next rfc v7 1/3] virtio-net: separate fields of sending/receiving queue from virtnet_info
From: Jason Wang @ 2012-12-04 9:23 UTC (permalink / raw)
To: Rusty Russell
Cc: krkumar2, kvm, mst, netdev, linux-kernel, virtualization,
bhutchings, jwhan, shiyer
In-Reply-To: <87zk1uh48g.fsf@rustcorp.com.au>
On Tuesday, December 04, 2012 02:13:11 PM Rusty Russell wrote:
> Jason Wang <jasowang@redhat.com> writes:
> > On Monday, December 03, 2012 12:25:42 PM Rusty Russell wrote:
> >> > +
> >> > + /* Work struct for refilling if we run low on memory. */
> >> > + struct delayed_work refill;
> >>
> >> I can't really see the justificaiton for a refill per queue. Just have
> >> one work iterate all the queues if it happens, unless it happens often
> >> (in which case, we need to look harder at this anyway).
> >
> > But during this kind of iteration, we may need enable/disable the napi
> > regardless of whether the receive queue has lots to be refilled. This may
> > add extra latency.
>
> Sure, but does it actually happen? We only use the work when we run out
> of memory. If this happens in normal behaviour we need to change
> something else...
True, I will change to use a global one.
Thanks
>
> Thanks,
> Rusty.
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [net-next rfc v7 1/3] virtio-net: separate fields of sending/receiving queue from virtnet_info
From: Jason Wang @ 2012-12-04 9:22 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: krkumar2, kvm, netdev, linux-kernel, virtualization, bhutchings,
jwhan, shiyer
In-Reply-To: <20121203111848.GD26167@redhat.com>
On Monday, December 03, 2012 01:18:48 PM Michael S. Tsirkin wrote:
> On Mon, Dec 03, 2012 at 01:15:01PM +0800, Jason Wang wrote:
> > > > +
> > > >
> > > > + /* Work struct for refilling if we run low on memory. */
> > > >
> > > > + struct delayed_work refill;
> > >
> > > I can't really see the justificaiton for a refill per queue. Just have
> > >
> > > one work iterate all the queues if it happens, unless it happens often
> > >
> > > (in which case, we need to look harder at this anyway).
> >
> > But during this kind of iteration, we may need enable/disable the napi
> > regardless of whether the receive queue has lots to be refilled. This may
> > add extra latency.
>
> We are running from the timer, so latency is not a concern I think.
Maybe, anyway it's only called when avaiable memory is low, so it should not
be an issue.
^ permalink raw reply
* Re: [PATCH 1/5 net-next v2] tg3: Fix inconsistent locking for tg3_netif_start().
From: Richard Cochran @ 2012-12-04 8:48 UTC (permalink / raw)
To: Michael Chan; +Cc: davem, netdev, nsujir
In-Reply-To: <1354599420-3589-1-git-send-email-mchan@broadcom.com>
On Mon, Dec 03, 2012 at 09:36:56PM -0800, Michael Chan wrote:
> From: Nithin Nayak Sujir <nsujir@broadcom.com>
>
> Every caller holds tp->lock when calling tg3_netif_start() except
> tg3_io_resume(). Fix it so that it is all consistent. The subsequent
> PTP patches add tg3_ptp_resume() to tg3_netif_start() and the tp->lock
> is required.
>
> Signed-off-by: Nithin Nayak Sujir <nsujir@broadcom.com>
> Signed-off-by: Michael Chan <mchan@broadcom.com>
This series looks good to me now.
Acked-by: Richard Cochran <richardcochran@gmail.com>
^ permalink raw reply
* Re: [PATCH 2/4 net-next] tg3: PTP - Implement the ptp api and ethtool functions
From: Richard Cochran @ 2012-12-04 7:53 UTC (permalink / raw)
To: Nithin Nayak Sujir; +Cc: Michael Chan, davem, netdev
In-Reply-To: <50BD1F10.7020105@broadcom.com>
On Mon, Dec 03, 2012 at 01:52:16PM -0800, Nithin Nayak Sujir wrote:
>
> Yes, the hardware does seem to be different from what you describe
> but I think the conversion is right. I tested this with ptp4l in a
> back-to-back configuration and observed convergence of the master
> offset to ~0. Without this code, the offset keeps increasing.
Okay, thanks, just asking.
It appears that this works just like the IGB. The register value is a
binary fraction of the increment value, and not an addend as I
assumed.
Thanks,
Richard
^ permalink raw reply
* Re: [net-next rfc v7 2/3] virtio_net: multiqueue support
From: Michael S. Tsirkin @ 2012-12-04 7:35 UTC (permalink / raw)
To: Jason Wang
Cc: krkumar2, kvm, netdev, linux-kernel, virtualization, bhutchings,
jwhan, shiyer
In-Reply-To: <50BC7F59.301@redhat.com>
On Mon, Dec 03, 2012 at 06:30:49PM +0800, Jason Wang wrote:
> On 12/03/2012 06:14 PM, Michael S. Tsirkin wrote:
> > On Tue, Nov 27, 2012 at 06:15:59PM +0800, Jason Wang wrote:
> >> > - if (!try_fill_recv(&vi->rq, GFP_KERNEL))
> >> > - schedule_delayed_work(&vi->rq.refill, 0);
> >> > + for (i = 0; i < vi->max_queue_pairs; i++)
> >> > + if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
> >> > + schedule_delayed_work(&vi->rq[i].refill, 0);
> >> >
> >> > mutex_lock(&vi->config_lock);
> >> > vi->config_enable = true;
> >> > mutex_unlock(&vi->config_lock);
> >> >
> >> > + BUG_ON(virtnet_set_queues(vi));
> >> > +
> >> > return 0;
> >> > }
> >> > #endif
> > Also crashing on device nack of command is also not nice.
> > In this case it seems we can just switch to
> > single-queue mode which should always be safe.
>
> Not sure it's safe. It depends on the reason why this call fails. If we
> left a state that the driver only use single queue but the device use
> multi queues, we may still lost the network.
Looks like we won't: napi will stay enabled on all queues
so we will process incoming packets.
--
MST
^ permalink raw reply
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