* [PATCH 13/17] ipvs: reduce sync rate with time thresholds
From: Simon Horman @ 2012-05-02 1:24 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Hans Schillstrom, Jesper Dangaard Brouer,
Simon Horman
In-Reply-To: <1335921901-21284-1-git-send-email-horms@verge.net.au>
From: Julian Anastasov <ja@ssi.bg>
Add two new sysctl vars to control the sync rate with the
main idea to reduce the rate for connection templates because
currently it depends on the packet rate for controlled connections.
This mechanism should be useful also for normal connections
with high traffic.
sync_refresh_period: in seconds, difference in reported connection
timer that triggers new sync message. It can be used to
avoid sync messages for the specified period (or half of
the connection timeout if it is lower) if connection state
is not changed from last sync.
sync_retries: integer, 0..3, defines sync retries with period of
sync_refresh_period/8. Useful to protect against loss of
sync messages.
Allow sysctl_sync_threshold to be used with
sysctl_sync_period=0, so that only single sync message is sent
if sync_refresh_period is also 0.
Add new field "sync_endtime" in connection structure to
hold the reported time when connection expires. The 2 lowest
bits will represent the retry count.
As the sysctl_sync_period now can be 0 use ACCESS_ONCE to
avoid division by zero.
Special thanks to Aleksey Chudov for being patient with me,
for his extensive reports and helping in all tests.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Tested-by: Aleksey Chudov <aleksey.chudov@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 30 +++++++++-
net/netfilter/ipvs/ip_vs_conn.c | 7 ++-
net/netfilter/ipvs/ip_vs_core.c | 30 +---------
net/netfilter/ipvs/ip_vs_ctl.c | 25 +++++++-
net/netfilter/ipvs/ip_vs_sync.c | 121 +++++++++++++++++++++++++++++++++------
5 files changed, 165 insertions(+), 48 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 8721a78..941df45 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -505,6 +505,7 @@ struct ip_vs_conn {
* state transition triggerd
* synchronization
*/
+ unsigned long sync_endtime; /* jiffies + sent_retries */
/* Control members */
struct ip_vs_conn *control; /* Master control connection */
@@ -876,6 +877,8 @@ struct netns_ipvs {
int sysctl_expire_nodest_conn;
int sysctl_expire_quiescent_template;
int sysctl_sync_threshold[2];
+ unsigned int sysctl_sync_refresh_period;
+ int sysctl_sync_retries;
int sysctl_nat_icmp_send;
/* ip_vs_lblc */
@@ -917,10 +920,13 @@ struct netns_ipvs {
#define DEFAULT_SYNC_THRESHOLD 3
#define DEFAULT_SYNC_PERIOD 50
#define DEFAULT_SYNC_VER 1
+#define DEFAULT_SYNC_REFRESH_PERIOD (0U * HZ)
+#define DEFAULT_SYNC_RETRIES 0
#define IPVS_SYNC_WAKEUP_RATE 8
#define IPVS_SYNC_QLEN_MAX (IPVS_SYNC_WAKEUP_RATE * 4)
#define IPVS_SYNC_SEND_DELAY (HZ / 50)
#define IPVS_SYNC_CHECK_PERIOD HZ
+#define IPVS_SYNC_FLUSH_TIME (HZ * 2)
#ifdef CONFIG_SYSCTL
@@ -931,7 +937,17 @@ static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
static inline int sysctl_sync_period(struct netns_ipvs *ipvs)
{
- return ipvs->sysctl_sync_threshold[1];
+ return ACCESS_ONCE(ipvs->sysctl_sync_threshold[1]);
+}
+
+static inline unsigned int sysctl_sync_refresh_period(struct netns_ipvs *ipvs)
+{
+ return ACCESS_ONCE(ipvs->sysctl_sync_refresh_period);
+}
+
+static inline int sysctl_sync_retries(struct netns_ipvs *ipvs)
+{
+ return ipvs->sysctl_sync_retries;
}
static inline int sysctl_sync_ver(struct netns_ipvs *ipvs)
@@ -961,6 +977,16 @@ static inline int sysctl_sync_period(struct netns_ipvs *ipvs)
return DEFAULT_SYNC_PERIOD;
}
+static inline unsigned int sysctl_sync_refresh_period(struct netns_ipvs *ipvs)
+{
+ return DEFAULT_SYNC_REFRESH_PERIOD;
+}
+
+static inline int sysctl_sync_retries(struct netns_ipvs *ipvs)
+{
+ return DEFAULT_SYNC_RETRIES & 3;
+}
+
static inline int sysctl_sync_ver(struct netns_ipvs *ipvs)
{
return DEFAULT_SYNC_VER;
@@ -1248,7 +1274,7 @@ extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
extern int start_sync_thread(struct net *net, int state, char *mcast_ifn,
__u8 syncid);
extern int stop_sync_thread(struct net *net, int state);
-extern void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp);
+extern void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts);
/*
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 9d237d7..46260fb 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -761,7 +761,8 @@ int ip_vs_check_template(struct ip_vs_conn *ct)
static void ip_vs_conn_expire(unsigned long data)
{
struct ip_vs_conn *cp = (struct ip_vs_conn *)data;
- struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp));
+ struct net *net = ip_vs_conn_net(cp);
+ struct netns_ipvs *ipvs = net_ipvs(net);
cp->timeout = 60*HZ;
@@ -826,6 +827,9 @@ static void ip_vs_conn_expire(unsigned long data)
atomic_read(&cp->refcnt)-1,
atomic_read(&cp->n_control));
+ if (ipvs->sync_state & IP_VS_STATE_MASTER)
+ ip_vs_sync_conn(net, cp, sysctl_sync_threshold(ipvs));
+
ip_vs_conn_put(cp);
}
@@ -899,6 +903,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
/* Set its state and timeout */
cp->state = 0;
cp->timeout = 3*HZ;
+ cp->sync_endtime = jiffies & ~3UL;
/* Bind its packet transmitter */
#ifdef CONFIG_IP_VS_IPV6
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index b5a5c73..7ce5819 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1613,34 +1613,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
else
pkts = atomic_add_return(1, &cp->in_pkts);
- if ((ipvs->sync_state & IP_VS_STATE_MASTER) &&
- cp->protocol == IPPROTO_SCTP) {
- if ((cp->state == IP_VS_SCTP_S_ESTABLISHED &&
- (pkts % sysctl_sync_period(ipvs)
- == sysctl_sync_threshold(ipvs))) ||
- (cp->old_state != cp->state &&
- ((cp->state == IP_VS_SCTP_S_CLOSED) ||
- (cp->state == IP_VS_SCTP_S_SHUT_ACK_CLI) ||
- (cp->state == IP_VS_SCTP_S_SHUT_ACK_SER)))) {
- ip_vs_sync_conn(net, cp);
- goto out;
- }
- }
-
- /* Keep this block last: TCP and others with pp->num_states <= 1 */
- else if ((ipvs->sync_state & IP_VS_STATE_MASTER) &&
- (((cp->protocol != IPPROTO_TCP ||
- cp->state == IP_VS_TCP_S_ESTABLISHED) &&
- (pkts % sysctl_sync_period(ipvs)
- == sysctl_sync_threshold(ipvs))) ||
- ((cp->protocol == IPPROTO_TCP) && (cp->old_state != cp->state) &&
- ((cp->state == IP_VS_TCP_S_FIN_WAIT) ||
- (cp->state == IP_VS_TCP_S_CLOSE) ||
- (cp->state == IP_VS_TCP_S_CLOSE_WAIT) ||
- (cp->state == IP_VS_TCP_S_TIME_WAIT)))))
- ip_vs_sync_conn(net, cp);
-out:
- cp->old_state = cp->state;
+ if (ipvs->sync_state & IP_VS_STATE_MASTER)
+ ip_vs_sync_conn(net, cp, pkts);
ip_vs_conn_put(cp);
return ret;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 854e9a6..83bdbbc 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1599,6 +1599,10 @@ static int ip_vs_zero_all(struct net *net)
}
#ifdef CONFIG_SYSCTL
+
+static int zero;
+static int three = 3;
+
static int
proc_do_defense_mode(ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
@@ -1632,7 +1636,8 @@ proc_do_sync_threshold(ctl_table *table, int write,
memcpy(val, valp, sizeof(val));
rc = proc_dointvec(table, write, buffer, lenp, ppos);
- if (write && (valp[0] < 0 || valp[1] < 0 || valp[0] >= valp[1])) {
+ if (write && (valp[0] < 0 || valp[1] < 0 ||
+ (valp[0] >= valp[1] && valp[1]))) {
/* Restore the correct value */
memcpy(valp, val, sizeof(val));
}
@@ -1755,6 +1760,20 @@ static struct ctl_table vs_vars[] = {
.proc_handler = proc_do_sync_threshold,
},
{
+ .procname = "sync_refresh_period",
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ },
+ {
+ .procname = "sync_retries",
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &three,
+ },
+ {
.procname = "nat_icmp_send",
.maxlen = sizeof(int),
.mode = 0644,
@@ -3685,6 +3704,10 @@ int __net_init ip_vs_control_net_init_sysctl(struct net *net)
ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD;
tbl[idx].data = &ipvs->sysctl_sync_threshold;
tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold);
+ ipvs->sysctl_sync_refresh_period = DEFAULT_SYNC_REFRESH_PERIOD;
+ tbl[idx++].data = &ipvs->sysctl_sync_refresh_period;
+ ipvs->sysctl_sync_retries = clamp_t(int, DEFAULT_SYNC_RETRIES, 0, 3);
+ tbl[idx++].data = &ipvs->sysctl_sync_retries;
tbl[idx++].data = &ipvs->sysctl_nat_icmp_send;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index eafc1d2..4aa9290 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -451,11 +451,94 @@ ip_vs_sync_buff_create_v0(struct netns_ipvs *ipvs)
return sb;
}
+/* Check if conn should be synced.
+ * pkts: conn packets, use sysctl_sync_threshold to avoid packet check
+ * - (1) sync_refresh_period: reduce sync rate. Additionally, retry
+ * sync_retries times with period of sync_refresh_period/8
+ * - (2) if both sync_refresh_period and sync_period are 0 send sync only
+ * for state changes or only once when pkts matches sync_threshold
+ * - (3) templates: rate can be reduced only with sync_refresh_period or
+ * with (2)
+ */
+static int ip_vs_sync_conn_needed(struct netns_ipvs *ipvs,
+ struct ip_vs_conn *cp, int pkts)
+{
+ unsigned long orig = ACCESS_ONCE(cp->sync_endtime);
+ unsigned long now = jiffies;
+ unsigned long n = (now + cp->timeout) & ~3UL;
+ unsigned int sync_refresh_period;
+ int sync_period;
+ int force;
+
+ /* Check if we sync in current state */
+ if (unlikely(cp->flags & IP_VS_CONN_F_TEMPLATE))
+ force = 0;
+ else if (likely(cp->protocol == IPPROTO_TCP)) {
+ if (!((1 << cp->state) &
+ ((1 << IP_VS_TCP_S_ESTABLISHED) |
+ (1 << IP_VS_TCP_S_FIN_WAIT) |
+ (1 << IP_VS_TCP_S_CLOSE) |
+ (1 << IP_VS_TCP_S_CLOSE_WAIT) |
+ (1 << IP_VS_TCP_S_TIME_WAIT))))
+ return 0;
+ force = cp->state != cp->old_state;
+ if (force && cp->state != IP_VS_TCP_S_ESTABLISHED)
+ goto set;
+ } else if (unlikely(cp->protocol == IPPROTO_SCTP)) {
+ if (!((1 << cp->state) &
+ ((1 << IP_VS_SCTP_S_ESTABLISHED) |
+ (1 << IP_VS_SCTP_S_CLOSED) |
+ (1 << IP_VS_SCTP_S_SHUT_ACK_CLI) |
+ (1 << IP_VS_SCTP_S_SHUT_ACK_SER))))
+ return 0;
+ force = cp->state != cp->old_state;
+ if (force && cp->state != IP_VS_SCTP_S_ESTABLISHED)
+ goto set;
+ } else {
+ /* UDP or another protocol with single state */
+ force = 0;
+ }
+
+ sync_refresh_period = sysctl_sync_refresh_period(ipvs);
+ if (sync_refresh_period > 0) {
+ long diff = n - orig;
+ long min_diff = max(cp->timeout >> 1, 10UL * HZ);
+
+ /* Avoid sync if difference is below sync_refresh_period
+ * and below the half timeout.
+ */
+ if (abs(diff) < min_t(long, sync_refresh_period, min_diff)) {
+ int retries = orig & 3;
+
+ if (retries >= sysctl_sync_retries(ipvs))
+ return 0;
+ if (time_before(now, orig - cp->timeout +
+ (sync_refresh_period >> 3)))
+ return 0;
+ n |= retries + 1;
+ }
+ }
+ sync_period = sysctl_sync_period(ipvs);
+ if (sync_period > 0) {
+ if (!(cp->flags & IP_VS_CONN_F_TEMPLATE) &&
+ pkts % sync_period != sysctl_sync_threshold(ipvs))
+ return 0;
+ } else if (sync_refresh_period <= 0 &&
+ pkts != sysctl_sync_threshold(ipvs))
+ return 0;
+
+set:
+ cp->old_state = cp->state;
+ n = cmpxchg(&cp->sync_endtime, orig, n);
+ return n == orig || force;
+}
+
/*
* Version 0 , could be switched in by sys_ctl.
* Add an ip_vs_conn information into the current sync_buff.
*/
-void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp)
+static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp,
+ int pkts)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_sync_mesg_v0 *m;
@@ -468,6 +551,9 @@ void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp)
if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
return;
+ if (!ip_vs_sync_conn_needed(ipvs, cp, pkts))
+ return;
+
spin_lock(&ipvs->sync_buff_lock);
if (!ipvs->sync_buff) {
ipvs->sync_buff =
@@ -513,8 +599,14 @@ void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp)
spin_unlock(&ipvs->sync_buff_lock);
/* synchronize its controller if it has */
- if (cp->control)
- ip_vs_sync_conn(net, cp->control);
+ cp = cp->control;
+ if (cp) {
+ if (cp->flags & IP_VS_CONN_F_TEMPLATE)
+ pkts = atomic_add_return(1, &cp->in_pkts);
+ else
+ pkts = sysctl_sync_threshold(ipvs);
+ ip_vs_sync_conn(net, cp->control, pkts);
+ }
}
/*
@@ -522,7 +614,7 @@ void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp)
* Called by ip_vs_in.
* Sending Version 1 messages
*/
-void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp)
+void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_sync_mesg *m;
@@ -532,13 +624,16 @@ void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp)
/* Handle old version of the protocol */
if (sysctl_sync_ver(ipvs) == 0) {
- ip_vs_sync_conn_v0(net, cp);
+ ip_vs_sync_conn_v0(net, cp, pkts);
return;
}
/* Do not sync ONE PACKET */
if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
goto control;
sloop:
+ if (!ip_vs_sync_conn_needed(ipvs, cp, pkts))
+ goto control;
+
/* Sanity checks */
pe_name_len = 0;
if (cp->pe_data_len) {
@@ -653,16 +748,10 @@ control:
cp = cp->control;
if (!cp)
return;
- /*
- * Reduce sync rate for templates
- * i.e only increment in_pkts for Templates.
- */
- if (cp->flags & IP_VS_CONN_F_TEMPLATE) {
- int pkts = atomic_add_return(1, &cp->in_pkts);
^ permalink raw reply related
* [PATCH 14/17] ipvs: add support for sync threads
From: Simon Horman @ 2012-05-02 1:24 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Hans Schillstrom, Jesper Dangaard Brouer,
Simon Horman
In-Reply-To: <1335921901-21284-1-git-send-email-horms@verge.net.au>
From: Julian Anastasov <ja@ssi.bg>
Allow master and backup servers to use many threads
for sync traffic. Add sysctl var "sync_ports" to define the
number of threads. Every thread will use single UDP port,
thread 0 will use the default port 8848 while last thread
will use port 8848+sync_ports-1.
The sync traffic for connections is scheduled to many
master threads based on the cp address but one connection is
always assigned to same thread to avoid reordering of the
sync messages.
Remove ip_vs_sync_switch_mode because this check
for sync mode change is still risky. Instead, check for mode
change under sync_buff_lock.
Make sure the backup socks do not block on reading.
Special thanks to Aleksey Chudov for helping in all tests.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Tested-by: Aleksey Chudov <aleksey.chudov@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 34 +++-
net/netfilter/ipvs/ip_vs_conn.c | 7 +
net/netfilter/ipvs/ip_vs_ctl.c | 29 ++-
net/netfilter/ipvs/ip_vs_sync.c | 401 ++++++++++++++++++++++++---------------
4 files changed, 305 insertions(+), 166 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 941df45..75824e2 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -785,6 +785,16 @@ struct ip_vs_app {
void (*timeout_change)(struct ip_vs_app *app, int flags);
};
+struct ipvs_master_sync_state {
+ struct list_head sync_queue;
+ struct ip_vs_sync_buff *sync_buff;
+ int sync_queue_len;
+ unsigned int sync_queue_delay;
+ struct task_struct *master_thread;
+ struct delayed_work master_wakeup_work;
+ struct netns_ipvs *ipvs;
+};
+
/* IPVS in network namespace */
struct netns_ipvs {
int gen; /* Generation */
@@ -871,6 +881,7 @@ struct netns_ipvs {
#endif
int sysctl_snat_reroute;
int sysctl_sync_ver;
+ int sysctl_sync_ports;
int sysctl_sync_qlen_max;
int sysctl_sync_sock_size;
int sysctl_cache_bypass;
@@ -894,16 +905,11 @@ struct netns_ipvs {
spinlock_t est_lock;
struct timer_list est_timer; /* Estimation timer */
/* ip_vs_sync */
- struct list_head sync_queue;
- int sync_queue_len;
- unsigned int sync_queue_delay;
- struct delayed_work master_wakeup_work;
spinlock_t sync_lock;
- struct ip_vs_sync_buff *sync_buff;
+ struct ipvs_master_sync_state *ms;
spinlock_t sync_buff_lock;
- struct sockaddr_in sync_mcast_addr;
- struct task_struct *master_thread;
- struct task_struct *backup_thread;
+ struct task_struct **backup_threads;
+ int threads_mask;
int send_mesg_maxlen;
int recv_mesg_maxlen;
volatile int sync_state;
@@ -927,6 +933,7 @@ struct netns_ipvs {
#define IPVS_SYNC_SEND_DELAY (HZ / 50)
#define IPVS_SYNC_CHECK_PERIOD HZ
#define IPVS_SYNC_FLUSH_TIME (HZ * 2)
+#define IPVS_SYNC_PORTS_MAX (1 << 6)
#ifdef CONFIG_SYSCTL
@@ -955,6 +962,11 @@ static inline int sysctl_sync_ver(struct netns_ipvs *ipvs)
return ipvs->sysctl_sync_ver;
}
+static inline int sysctl_sync_ports(struct netns_ipvs *ipvs)
+{
+ return ACCESS_ONCE(ipvs->sysctl_sync_ports);
+}
+
static inline int sysctl_sync_qlen_max(struct netns_ipvs *ipvs)
{
return ipvs->sysctl_sync_qlen_max;
@@ -992,6 +1004,11 @@ static inline int sysctl_sync_ver(struct netns_ipvs *ipvs)
return DEFAULT_SYNC_VER;
}
+static inline int sysctl_sync_ports(struct netns_ipvs *ipvs)
+{
+ return 1;
+}
+
static inline int sysctl_sync_qlen_max(struct netns_ipvs *ipvs)
{
return IPVS_SYNC_QLEN_MAX;
@@ -1242,7 +1259,6 @@ extern struct ip_vs_stats ip_vs_stats;
extern const struct ctl_path net_vs_ctl_path[];
extern int sysctl_ip_vs_sync_ver;
-extern void ip_vs_sync_switch_mode(struct net *net, int mode);
extern struct ip_vs_service *
ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
const union nf_inet_addr *vaddr, __be16 vport);
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 46260fb..6a43c93 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -618,12 +618,19 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp)
if (dest) {
struct ip_vs_proto_data *pd;
+ spin_lock(&cp->lock);
+ if (cp->dest) {
+ spin_unlock(&cp->lock);
+ return dest;
+ }
+
/* Applications work depending on the forwarding method
* but better to reassign them always when binding dest */
if (cp->app)
ip_vs_unbind_app(cp);
ip_vs_bind_dest(cp, dest);
+ spin_unlock(&cp->lock);
/* Update its packet transmitter */
cp->packet_xmit = NULL;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 83bdbbc..0e599a4 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1657,9 +1657,24 @@ proc_do_sync_mode(ctl_table *table, int write,
if ((*valp < 0) || (*valp > 1)) {
/* Restore the correct value */
*valp = val;
- } else {
- struct net *net = current->nsproxy->net_ns;
- ip_vs_sync_switch_mode(net, val);
+ }
+ }
+ return rc;
+}
+
+static int
+proc_do_sync_ports(ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ int *valp = table->data;
+ int val = *valp;
+ int rc;
+
+ rc = proc_dointvec(table, write, buffer, lenp, ppos);
+ if (write && (*valp != val)) {
+ if (*valp < 1 || !is_power_of_2(*valp)) {
+ /* Restore the correct value */
+ *valp = val;
}
}
return rc;
@@ -1723,6 +1738,12 @@ static struct ctl_table vs_vars[] = {
.proc_handler = &proc_do_sync_mode,
},
{
+ .procname = "sync_ports",
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_do_sync_ports,
+ },
+ {
.procname = "sync_qlen_max",
.maxlen = sizeof(int),
.mode = 0644,
@@ -3693,6 +3714,8 @@ int __net_init ip_vs_control_net_init_sysctl(struct net *net)
tbl[idx++].data = &ipvs->sysctl_snat_reroute;
ipvs->sysctl_sync_ver = 1;
tbl[idx++].data = &ipvs->sysctl_sync_ver;
+ ipvs->sysctl_sync_ports = 1;
+ tbl[idx++].data = &ipvs->sysctl_sync_ports;
ipvs->sysctl_sync_qlen_max = nr_free_buffer_pages() / 32;
tbl[idx++].data = &ipvs->sysctl_sync_qlen_max;
ipvs->sysctl_sync_sock_size = 0;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 4aa9290..8550f37 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -196,6 +196,7 @@ struct ip_vs_sync_thread_data {
struct net *net;
struct socket *sock;
char *buf;
+ int id;
};
/* Version 0 definition of packet sizes */
@@ -271,13 +272,6 @@ struct ip_vs_sync_buff {
unsigned char *end;
};
-/* multicast addr */
-static struct sockaddr_in mcast_addr = {
- .sin_family = AF_INET,
- .sin_port = cpu_to_be16(IP_VS_SYNC_PORT),
- .sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP),
-};
-
/*
* Copy of struct ip_vs_seq
* From unaligned network order to aligned host order
@@ -300,22 +294,22 @@ static void hton_seq(struct ip_vs_seq *ho, struct ip_vs_seq *no)
put_unaligned_be32(ho->previous_delta, &no->previous_delta);
}
-static inline struct ip_vs_sync_buff *sb_dequeue(struct netns_ipvs *ipvs)
+static inline struct ip_vs_sync_buff *
+sb_dequeue(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms)
{
struct ip_vs_sync_buff *sb;
spin_lock_bh(&ipvs->sync_lock);
- if (list_empty(&ipvs->sync_queue)) {
+ if (list_empty(&ms->sync_queue)) {
sb = NULL;
__set_current_state(TASK_INTERRUPTIBLE);
} else {
- sb = list_entry(ipvs->sync_queue.next,
- struct ip_vs_sync_buff,
+ sb = list_entry(ms->sync_queue.next, struct ip_vs_sync_buff,
list);
list_del(&sb->list);
- ipvs->sync_queue_len--;
- if (!ipvs->sync_queue_len)
- ipvs->sync_queue_delay = 0;
+ ms->sync_queue_len--;
+ if (!ms->sync_queue_len)
+ ms->sync_queue_delay = 0;
}
spin_unlock_bh(&ipvs->sync_lock);
@@ -338,7 +332,7 @@ ip_vs_sync_buff_create(struct netns_ipvs *ipvs)
kfree(sb);
return NULL;
}
- sb->mesg->reserved = 0; /* old nr_conns i.e. must be zeo now */
+ sb->mesg->reserved = 0; /* old nr_conns i.e. must be zero now */
sb->mesg->version = SYNC_PROTO_VER;
sb->mesg->syncid = ipvs->master_syncid;
sb->mesg->size = sizeof(struct ip_vs_sync_mesg);
@@ -357,20 +351,21 @@ static inline void ip_vs_sync_buff_release(struct ip_vs_sync_buff *sb)
kfree(sb);
}
-static inline void sb_queue_tail(struct netns_ipvs *ipvs)
+static inline void sb_queue_tail(struct netns_ipvs *ipvs,
+ struct ipvs_master_sync_state *ms)
{
- struct ip_vs_sync_buff *sb = ipvs->sync_buff;
+ struct ip_vs_sync_buff *sb = ms->sync_buff;
spin_lock(&ipvs->sync_lock);
if (ipvs->sync_state & IP_VS_STATE_MASTER &&
- ipvs->sync_queue_len < sysctl_sync_qlen_max(ipvs)) {
- if (!ipvs->sync_queue_len)
- schedule_delayed_work(&ipvs->master_wakeup_work,
+ ms->sync_queue_len < sysctl_sync_qlen_max(ipvs)) {
+ if (!ms->sync_queue_len)
+ schedule_delayed_work(&ms->master_wakeup_work,
max(IPVS_SYNC_SEND_DELAY, 1));
- ipvs->sync_queue_len++;
- list_add_tail(&sb->list, &ipvs->sync_queue);
- if ((++ipvs->sync_queue_delay) == IPVS_SYNC_WAKEUP_RATE)
- wake_up_process(ipvs->master_thread);
+ ms->sync_queue_len++;
+ list_add_tail(&sb->list, &ms->sync_queue);
+ if ((++ms->sync_queue_delay) == IPVS_SYNC_WAKEUP_RATE)
+ wake_up_process(ms->master_thread);
} else
ip_vs_sync_buff_release(sb);
spin_unlock(&ipvs->sync_lock);
@@ -381,15 +376,15 @@ static inline void sb_queue_tail(struct netns_ipvs *ipvs)
* than the specified time or the specified time is zero.
*/
static inline struct ip_vs_sync_buff *
-get_curr_sync_buff(struct netns_ipvs *ipvs, unsigned long time)
+get_curr_sync_buff(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms,
+ unsigned long time)
{
struct ip_vs_sync_buff *sb;
spin_lock_bh(&ipvs->sync_buff_lock);
- if (ipvs->sync_buff &&
- time_after_eq(jiffies - ipvs->sync_buff->firstuse, time)) {
- sb = ipvs->sync_buff;
- ipvs->sync_buff = NULL;
+ sb = ms->sync_buff;
+ if (sb && time_after_eq(jiffies - sb->firstuse, time)) {
+ ms->sync_buff = NULL;
__set_current_state(TASK_RUNNING);
} else
sb = NULL;
@@ -397,31 +392,10 @@ get_curr_sync_buff(struct netns_ipvs *ipvs, unsigned long time)
return sb;
}
-/*
- * Switch mode from sending version 0 or 1
- * - must handle sync_buf
- */
-void ip_vs_sync_switch_mode(struct net *net, int mode)
+static inline int
+select_master_thread_id(struct netns_ipvs *ipvs, struct ip_vs_conn *cp)
{
- struct netns_ipvs *ipvs = net_ipvs(net);
- struct ip_vs_sync_buff *sb;
-
- spin_lock_bh(&ipvs->sync_buff_lock);
- if (!(ipvs->sync_state & IP_VS_STATE_MASTER))
- goto unlock;
- sb = ipvs->sync_buff;
- if (mode == sysctl_sync_ver(ipvs) || !sb)
- goto unlock;
-
- /* Buffer empty ? then let buf_create do the job */
- if (sb->mesg->size <= sizeof(struct ip_vs_sync_mesg)) {
- ip_vs_sync_buff_release(sb);
- ipvs->sync_buff = NULL;
- } else
- sb_queue_tail(ipvs);
-
-unlock:
- spin_unlock_bh(&ipvs->sync_buff_lock);
+ return ((long) cp >> (1 + ilog2(sizeof(*cp)))) & ipvs->threads_mask;
}
/*
@@ -543,6 +517,9 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp,
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_sync_mesg_v0 *m;
struct ip_vs_sync_conn_v0 *s;
+ struct ip_vs_sync_buff *buff;
+ struct ipvs_master_sync_state *ms;
+ int id;
int len;
if (unlikely(cp->af != AF_INET))
@@ -555,20 +532,37 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp,
return;
spin_lock(&ipvs->sync_buff_lock);
- if (!ipvs->sync_buff) {
- ipvs->sync_buff =
- ip_vs_sync_buff_create_v0(ipvs);
- if (!ipvs->sync_buff) {
+ if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
+ spin_unlock(&ipvs->sync_buff_lock);
+ return;
+ }
+
+ id = select_master_thread_id(ipvs, cp);
+ ms = &ipvs->ms[id];
+ buff = ms->sync_buff;
+ if (buff) {
+ m = (struct ip_vs_sync_mesg_v0 *) buff->mesg;
+ /* Send buffer if it is for v1 */
+ if (!m->nr_conns) {
+ sb_queue_tail(ipvs, ms);
+ ms->sync_buff = NULL;
+ buff = NULL;
+ }
+ }
+ if (!buff) {
+ buff = ip_vs_sync_buff_create_v0(ipvs);
+ if (!buff) {
spin_unlock(&ipvs->sync_buff_lock);
pr_err("ip_vs_sync_buff_create failed.\n");
return;
}
+ ms->sync_buff = buff;
}
len = (cp->flags & IP_VS_CONN_F_SEQ_MASK) ? FULL_CONN_SIZE :
SIMPLE_CONN_SIZE;
- m = (struct ip_vs_sync_mesg_v0 *)ipvs->sync_buff->mesg;
- s = (struct ip_vs_sync_conn_v0 *)ipvs->sync_buff->head;
+ m = (struct ip_vs_sync_mesg_v0 *) buff->mesg;
+ s = (struct ip_vs_sync_conn_v0 *) buff->head;
/* copy members */
s->reserved = 0;
@@ -589,12 +583,12 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp,
m->nr_conns++;
m->size += len;
- ipvs->sync_buff->head += len;
+ buff->head += len;
/* check if there is a space for next one */
- if (ipvs->sync_buff->head + FULL_CONN_SIZE > ipvs->sync_buff->end) {
- sb_queue_tail(ipvs);
- ipvs->sync_buff = NULL;
+ if (buff->head + FULL_CONN_SIZE > buff->end) {
+ sb_queue_tail(ipvs, ms);
+ ms->sync_buff = NULL;
}
spin_unlock(&ipvs->sync_buff_lock);
@@ -619,6 +613,9 @@ void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts)
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_sync_mesg *m;
union ip_vs_sync_conn *s;
+ struct ip_vs_sync_buff *buff;
+ struct ipvs_master_sync_state *ms;
+ int id;
__u8 *p;
unsigned int len, pe_name_len, pad;
@@ -645,6 +642,13 @@ sloop:
}
spin_lock(&ipvs->sync_buff_lock);
+ if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
+ spin_unlock(&ipvs->sync_buff_lock);
+ return;
+ }
+
+ id = select_master_thread_id(ipvs, cp);
+ ms = &ipvs->ms[id];
#ifdef CONFIG_IP_VS_IPV6
if (cp->af == AF_INET6)
@@ -663,27 +667,32 @@ sloop:
/* check if there is a space for this one */
pad = 0;
- if (ipvs->sync_buff) {
- pad = (4 - (size_t)ipvs->sync_buff->head) & 3;
- if (ipvs->sync_buff->head + len + pad > ipvs->sync_buff->end) {
- sb_queue_tail(ipvs);
- ipvs->sync_buff = NULL;
+ buff = ms->sync_buff;
+ if (buff) {
+ m = buff->mesg;
+ pad = (4 - (size_t) buff->head) & 3;
+ /* Send buffer if it is for v0 */
+ if (buff->head + len + pad > buff->end || m->reserved) {
+ sb_queue_tail(ipvs, ms);
+ ms->sync_buff = NULL;
+ buff = NULL;
pad = 0;
}
}
- if (!ipvs->sync_buff) {
- ipvs->sync_buff = ip_vs_sync_buff_create(ipvs);
- if (!ipvs->sync_buff) {
+ if (!buff) {
+ buff = ip_vs_sync_buff_create(ipvs);
+ if (!buff) {
spin_unlock(&ipvs->sync_buff_lock);
pr_err("ip_vs_sync_buff_create failed.\n");
return;
}
+ ms->sync_buff = buff;
+ m = buff->mesg;
}
- m = ipvs->sync_buff->mesg;
- p = ipvs->sync_buff->head;
- ipvs->sync_buff->head += pad + len;
+ p = buff->head;
+ buff->head += pad + len;
m->size += pad + len;
/* Add ev. padding from prev. sync_conn */
while (pad--)
@@ -834,6 +843,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
kfree(param->pe_data);
dest = cp->dest;
+ spin_lock(&cp->lock);
if ((cp->flags ^ flags) & IP_VS_CONN_F_INACTIVE &&
!(flags & IP_VS_CONN_F_TEMPLATE) && dest) {
if (flags & IP_VS_CONN_F_INACTIVE) {
@@ -847,6 +857,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
flags &= IP_VS_CONN_F_BACKUP_UPD_MASK;
flags |= cp->flags & ~IP_VS_CONN_F_BACKUP_UPD_MASK;
cp->flags = flags;
+ spin_unlock(&cp->lock);
if (!dest) {
dest = ip_vs_try_bind_dest(cp);
if (dest)
@@ -1399,9 +1410,15 @@ static int bind_mcastif_addr(struct socket *sock, char *ifname)
/*
* Set up sending multicast socket over UDP
*/
-static struct socket *make_send_sock(struct net *net)
+static struct socket *make_send_sock(struct net *net, int id)
{
struct netns_ipvs *ipvs = net_ipvs(net);
+ /* multicast addr */
+ struct sockaddr_in mcast_addr = {
+ .sin_family = AF_INET,
+ .sin_port = cpu_to_be16(IP_VS_SYNC_PORT + id),
+ .sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP),
+ };
struct socket *sock;
int result;
@@ -1453,9 +1470,15 @@ error:
/*
* Set up receiving multicast socket over UDP
*/
-static struct socket *make_receive_sock(struct net *net)
+static struct socket *make_receive_sock(struct net *net, int id)
{
struct netns_ipvs *ipvs = net_ipvs(net);
+ /* multicast addr */
+ struct sockaddr_in mcast_addr = {
+ .sin_family = AF_INET,
+ .sin_port = cpu_to_be16(IP_VS_SYNC_PORT + id),
+ .sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP),
+ };
struct socket *sock;
int result;
@@ -1549,10 +1572,10 @@ ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen)
iov.iov_base = buffer;
iov.iov_len = (size_t)buflen;
- len = kernel_recvmsg(sock, &msg, &iov, 1, buflen, 0);
+ len = kernel_recvmsg(sock, &msg, &iov, 1, buflen, MSG_DONTWAIT);
if (len < 0)
- return -1;
+ return len;
LeaveFunction(7);
return len;
@@ -1561,44 +1584,47 @@ ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen)
/* Wakeup the master thread for sending */
static void master_wakeup_work_handler(struct work_struct *work)
{
- struct netns_ipvs *ipvs = container_of(work, struct netns_ipvs,
- master_wakeup_work.work);
+ struct ipvs_master_sync_state *ms =
+ container_of(work, struct ipvs_master_sync_state,
+ master_wakeup_work.work);
+ struct netns_ipvs *ipvs = ms->ipvs;
spin_lock_bh(&ipvs->sync_lock);
- if (ipvs->sync_queue_len &&
- ipvs->sync_queue_delay < IPVS_SYNC_WAKEUP_RATE) {
- ipvs->sync_queue_delay = IPVS_SYNC_WAKEUP_RATE;
- wake_up_process(ipvs->master_thread);
+ if (ms->sync_queue_len &&
+ ms->sync_queue_delay < IPVS_SYNC_WAKEUP_RATE) {
+ ms->sync_queue_delay = IPVS_SYNC_WAKEUP_RATE;
+ wake_up_process(ms->master_thread);
}
spin_unlock_bh(&ipvs->sync_lock);
}
/* Get next buffer to send */
static inline struct ip_vs_sync_buff *
-next_sync_buff(struct netns_ipvs *ipvs)
+next_sync_buff(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms)
{
struct ip_vs_sync_buff *sb;
- sb = sb_dequeue(ipvs);
+ sb = sb_dequeue(ipvs, ms);
if (sb)
return sb;
/* Do not delay entries in buffer for more than 2 seconds */
- return get_curr_sync_buff(ipvs, IPVS_SYNC_FLUSH_TIME);
+ return get_curr_sync_buff(ipvs, ms, IPVS_SYNC_FLUSH_TIME);
}
static int sync_thread_master(void *data)
{
struct ip_vs_sync_thread_data *tinfo = data;
struct netns_ipvs *ipvs = net_ipvs(tinfo->net);
+ struct ipvs_master_sync_state *ms = &ipvs->ms[tinfo->id];
struct sock *sk = tinfo->sock->sk;
struct ip_vs_sync_buff *sb;
pr_info("sync thread started: state = MASTER, mcast_ifn = %s, "
- "syncid = %d\n",
- ipvs->master_mcast_ifn, ipvs->master_syncid);
+ "syncid = %d, id = %d\n",
+ ipvs->master_mcast_ifn, ipvs->master_syncid, tinfo->id);
for (;;) {
- sb = next_sync_buff(ipvs);
+ sb = next_sync_buff(ipvs, ms);
if (unlikely(kthread_should_stop()))
break;
if (!sb) {
@@ -1624,12 +1650,12 @@ done:
ip_vs_sync_buff_release(sb);
/* clean up the sync_buff queue */
- while ((sb = sb_dequeue(ipvs)))
+ while ((sb = sb_dequeue(ipvs, ms)))
ip_vs_sync_buff_release(sb);
__set_current_state(TASK_RUNNING);
/* clean up the current sync_buff */
- sb = get_curr_sync_buff(ipvs, 0);
+ sb = get_curr_sync_buff(ipvs, ms, 0);
if (sb)
ip_vs_sync_buff_release(sb);
@@ -1648,8 +1674,8 @@ static int sync_thread_backup(void *data)
int len;
pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, "
- "syncid = %d\n",
- ipvs->backup_mcast_ifn, ipvs->backup_syncid);
+ "syncid = %d, id = %d\n",
+ ipvs->backup_mcast_ifn, ipvs->backup_syncid, tinfo->id);
while (!kthread_should_stop()) {
wait_event_interruptible(*sk_sleep(tinfo->sock->sk),
@@ -1661,7 +1687,8 @@ static int sync_thread_backup(void *data)
len = ip_vs_receive(tinfo->sock, tinfo->buf,
ipvs->recv_mesg_maxlen);
if (len <= 0) {
- pr_err("receiving message error\n");
+ if (len != -EAGAIN)
+ pr_err("receiving message error\n");
break;
}
@@ -1685,90 +1712,140 @@ static int sync_thread_backup(void *data)
int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid)
{
struct ip_vs_sync_thread_data *tinfo;
- struct task_struct **realtask, *task;
+ struct task_struct **array = NULL, *task;
struct socket *sock;
struct netns_ipvs *ipvs = net_ipvs(net);
- char *name, *buf = NULL;
+ char *name;
int (*threadfn)(void *data);
+ int id, count;
int result = -ENOMEM;
IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current));
IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %Zd bytes\n",
sizeof(struct ip_vs_sync_conn_v0));
+ if (!ipvs->sync_state) {
+ count = clamp(sysctl_sync_ports(ipvs), 1, IPVS_SYNC_PORTS_MAX);
+ ipvs->threads_mask = count - 1;
+ } else
+ count = ipvs->threads_mask + 1;
if (state == IP_VS_STATE_MASTER) {
- if (ipvs->master_thread)
+ if (ipvs->ms)
return -EEXIST;
strlcpy(ipvs->master_mcast_ifn, mcast_ifn,
sizeof(ipvs->master_mcast_ifn));
ipvs->master_syncid = syncid;
- realtask = &ipvs->master_thread;
- name = "ipvs_master:%d";
+ name = "ipvs-m:%d:%d";
threadfn = sync_thread_master;
- ipvs->sync_queue_len = 0;
- ipvs->sync_queue_delay = 0;
- INIT_DELAYED_WORK(&ipvs->master_wakeup_work,
- master_wakeup_work_handler);
- sock = make_send_sock(net);
} else if (state == IP_VS_STATE_BACKUP) {
- if (ipvs->backup_thread)
+ if (ipvs->backup_threads)
return -EEXIST;
strlcpy(ipvs->backup_mcast_ifn, mcast_ifn,
sizeof(ipvs->backup_mcast_ifn));
ipvs->backup_syncid = syncid;
- realtask = &ipvs->backup_thread;
- name = "ipvs_backup:%d";
+ name = "ipvs-b:%d:%d";
threadfn = sync_thread_backup;
- sock = make_receive_sock(net);
} else {
return -EINVAL;
}
- if (IS_ERR(sock)) {
- result = PTR_ERR(sock);
- goto out;
- }
+ if (state == IP_VS_STATE_MASTER) {
+ struct ipvs_master_sync_state *ms;
- set_sync_mesg_maxlen(net, state);
- if (state == IP_VS_STATE_BACKUP) {
- buf = kmalloc(ipvs->recv_mesg_maxlen, GFP_KERNEL);
- if (!buf)
- goto outsocket;
+ ipvs->ms = kzalloc(count * sizeof(ipvs->ms[0]), GFP_KERNEL);
+ if (!ipvs->ms)
+ goto out;
+ ms = ipvs->ms;
+ for (id = 0; id < count; id++, ms++) {
+ INIT_LIST_HEAD(&ms->sync_queue);
+ ms->sync_queue_len = 0;
+ ms->sync_queue_delay = 0;
+ INIT_DELAYED_WORK(&ms->master_wakeup_work,
+ master_wakeup_work_handler);
+ ms->ipvs = ipvs;
+ }
+ } else {
+ array = kzalloc(count * sizeof(struct task_struct *),
+ GFP_KERNEL);
+ if (!array)
+ goto out;
}
+ set_sync_mesg_maxlen(net, state);
- tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
- if (!tinfo)
- goto outbuf;
-
- tinfo->net = net;
- tinfo->sock = sock;
- tinfo->buf = buf;
+ tinfo = NULL;
+ for (id = 0; id < count; id++) {
+ if (state == IP_VS_STATE_MASTER)
+ sock = make_send_sock(net, id);
+ else
+ sock = make_receive_sock(net, id);
+ if (IS_ERR(sock)) {
+ result = PTR_ERR(sock);
+ goto outtinfo;
+ }
+ tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
+ if (!tinfo)
+ goto outsocket;
+ tinfo->net = net;
+ tinfo->sock = sock;
+ if (state == IP_VS_STATE_BACKUP) {
+ tinfo->buf = kmalloc(ipvs->recv_mesg_maxlen,
+ GFP_KERNEL);
+ if (!tinfo->buf)
+ goto outtinfo;
+ }
+ tinfo->id = id;
- task = kthread_run(threadfn, tinfo, name, ipvs->gen);
- if (IS_ERR(task)) {
- result = PTR_ERR(task);
- goto outtinfo;
+ task = kthread_run(threadfn, tinfo, name, ipvs->gen, id);
+ if (IS_ERR(task)) {
+ result = PTR_ERR(task);
+ goto outtinfo;
+ }
+ tinfo = NULL;
+ if (state == IP_VS_STATE_MASTER)
+ ipvs->ms[id].master_thread = task;
+ else
+ array[id] = task;
}
/* mark as active */
- *realtask = task;
+
+ if (state == IP_VS_STATE_BACKUP)
+ ipvs->backup_threads = array;
+ spin_lock_bh(&ipvs->sync_buff_lock);
ipvs->sync_state |= state;
+ spin_unlock_bh(&ipvs->sync_buff_lock);
/* increase the module use count */
ip_vs_use_count_inc();
return 0;
-outtinfo:
- kfree(tinfo);
-outbuf:
- kfree(buf);
outsocket:
sk_release_kernel(sock->sk);
+
+outtinfo:
+ if (tinfo) {
+ sk_release_kernel(tinfo->sock->sk);
+ kfree(tinfo->buf);
+ kfree(tinfo);
+ }
+ count = id;
+ while (count-- > 0) {
+ if (state == IP_VS_STATE_MASTER)
+ kthread_stop(ipvs->ms[count].master_thread);
+ else
+ kthread_stop(array[count]);
+ }
+ kfree(array);
+
out:
+ if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
+ kfree(ipvs->ms);
+ ipvs->ms = NULL;
+ }
return result;
}
@@ -1776,39 +1853,60 @@ out:
int stop_sync_thread(struct net *net, int state)
{
struct netns_ipvs *ipvs = net_ipvs(net);
+ struct task_struct **array;
+ int id;
int retc = -EINVAL;
IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current));
if (state == IP_VS_STATE_MASTER) {
- if (!ipvs->master_thread)
+ if (!ipvs->ms)
return -ESRCH;
- pr_info("stopping master sync thread %d ...\n",
- task_pid_nr(ipvs->master_thread));
-
/*
* The lock synchronizes with sb_queue_tail(), so that we don't
* add sync buffers to the queue, when we are already in
* progress of stopping the master sync daemon.
*/
- spin_lock_bh(&ipvs->sync_lock);
+ spin_lock_bh(&ipvs->sync_buff_lock);
+ spin_lock(&ipvs->sync_lock);
ipvs->sync_state &= ~IP_VS_STATE_MASTER;
- spin_unlock_bh(&ipvs->sync_lock);
- cancel_delayed_work_sync(&ipvs->master_wakeup_work);
- retc = kthread_stop(ipvs->master_thread);
- ipvs->master_thread = NULL;
+ spin_unlock(&ipvs->sync_lock);
+ spin_unlock_bh(&ipvs->sync_buff_lock);
+
+ retc = 0;
+ for (id = ipvs->threads_mask; id >= 0; id--) {
+ struct ipvs_master_sync_state *ms = &ipvs->ms[id];
+ int ret;
+
+ pr_info("stopping master sync thread %d ...\n",
+ task_pid_nr(ms->master_thread));
+ cancel_delayed_work_sync(&ms->master_wakeup_work);
+ ret = kthread_stop(ms->master_thread);
+ if (retc >= 0)
+ retc = ret;
+ }
+ kfree(ipvs->ms);
+ ipvs->ms = NULL;
} else if (state == IP_VS_STATE_BACKUP) {
- if (!ipvs->backup_thread)
+ if (!ipvs->backup_threads)
return -ESRCH;
- pr_info("stopping backup sync thread %d ...\n",
- task_pid_nr(ipvs->backup_thread));
-
ipvs->sync_state &= ~IP_VS_STATE_BACKUP;
- retc = kthread_stop(ipvs->backup_thread);
- ipvs->backup_thread = NULL;
+ array = ipvs->backup_threads;
+ retc = 0;
+ for (id = ipvs->threads_mask; id >= 0; id--) {
+ int ret;
+
+ pr_info("stopping backup sync thread %d ...\n",
+ task_pid_nr(array[id]));
+ ret = kthread_stop(array[id]);
+ if (retc >= 0)
+ retc = ret;
+ }
+ kfree(array);
+ ipvs->backup_threads = NULL;
}
/* decrease the module use count */
@@ -1825,13 +1923,8 @@ int __net_init ip_vs_sync_net_init(struct net *net)
struct netns_ipvs *ipvs = net_ipvs(net);
__mutex_init(&ipvs->sync_mutex, "ipvs->sync_mutex", &__ipvs_sync_key);
- INIT_LIST_HEAD(&ipvs->sync_queue);
spin_lock_init(&ipvs->sync_lock);
spin_lock_init(&ipvs->sync_buff_lock);
^ permalink raw reply related
* [PATCH 16/17] IPVS: ip_vs_ftp.c: local functions should not be exposed globally
From: Simon Horman @ 2012-05-02 1:25 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Hans Schillstrom, Jesper Dangaard Brouer,
H Hartley Sweeten, H Hartley Sweeten, David S. Miller,
Simon Horman
In-Reply-To: <1335921901-21284-1-git-send-email-horms@verge.net.au>
From: H Hartley Sweeten <hartleys@visionengravers.com>
Functions not referenced outside of a source file should be marked
static to prevent it from being exposed globally.
This quiets the sparse warnings:
warning: symbol 'ip_vs_ftp_init' was not declared. Should it be static?
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_ftp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index debb8c7..091bec9 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -483,7 +483,7 @@ static struct pernet_operations ip_vs_ftp_ops = {
.exit = __ip_vs_ftp_exit,
};
-int __init ip_vs_ftp_init(void)
+static int __init ip_vs_ftp_init(void)
{
int rv;
--
1.7.9.5
^ permalink raw reply related
* [PATCH 17/17] IPVS: ip_vs_proto.c: local functions should not be exposed globally
From: Simon Horman @ 2012-05-02 1:25 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Hans Schillstrom, Jesper Dangaard Brouer,
H Hartley Sweeten, H Hartley Sweeten, David S. Miller,
Simon Horman
In-Reply-To: <1335921901-21284-1-git-send-email-horms@verge.net.au>
From: H Hartley Sweeten <hartleys@visionengravers.com>
Functions not referenced outside of a source file should be marked
static to prevent it from being exposed globally.
This quiets the sparse warnings:
warning: symbol '__ipvs_proto_data_get' was not declared. Should it be static?
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_proto.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 8726488..e3f4bb0 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -153,7 +153,7 @@ EXPORT_SYMBOL(ip_vs_proto_get);
/*
* get ip_vs_protocol object data by netns and proto
*/
-struct ip_vs_proto_data *
+static struct ip_vs_proto_data *
__ipvs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto)
{
struct ip_vs_proto_data *pd;
--
1.7.9.5
^ permalink raw reply related
* [PATCH 09/17] ipvs: remove check for IP_VS_CONN_F_SYNC from ip_vs_bind_dest
From: Simon Horman @ 2012-05-02 1:24 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Hans Schillstrom, Jesper Dangaard Brouer,
Simon Horman
In-Reply-To: <1335921901-21284-1-git-send-email-horms@verge.net.au>
From: Julian Anastasov <ja@ssi.bg>
As the IP_VS_CONN_F_INACTIVE bit is properly set
in cp->flags for all kind of connections we do not need to
add special checks for synced connections when updating
the activeconns/inactconns counters for first time. Now
logic will look just like in ip_vs_unbind_dest.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_conn.c | 9 ++++-----
1 file changed, 4 insertions(+), 5 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index f562e63..7647f3b 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -585,11 +585,10 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
/* Update the connection counters */
if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) {
- /* It is a normal connection, so increase the inactive
- connection counter because it is in TCP SYNRECV
- state (inactive) or other protocol inacive state */
- if ((cp->flags & IP_VS_CONN_F_SYNC) &&
- (!(cp->flags & IP_VS_CONN_F_INACTIVE)))
+ /* It is a normal connection, so modify the counters
+ * according to the flags, later the protocol can
+ * update them on state change */
+ if (!(cp->flags & IP_VS_CONN_F_INACTIVE))
atomic_inc(&dest->activeconns);
else
atomic_inc(&dest->inactconns);
--
1.7.9.5
^ permalink raw reply related
* [PATCH 11/17] ipvs: always update some of the flags bits in backup
From: Simon Horman @ 2012-05-02 1:24 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Hans Schillstrom, Jesper Dangaard Brouer,
Simon Horman
In-Reply-To: <1335921901-21284-1-git-send-email-horms@verge.net.au>
From: Julian Anastasov <ja@ssi.bg>
As the goal is to mirror the inactconns/activeconns
counters in the backup server, make sure the cp->flags are
updated even if cp is still not bound to dest. If cp->flags
are not updated ip_vs_bind_dest will rely only on the initial
flags when updating the counters. To avoid mistakes and
complicated checks for protocol state rely only on the
IP_VS_CONN_F_INACTIVE bit when updating the counters.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Tested-by: Aleksey Chudov <aleksey.chudov@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/linux/ip_vs.h | 5 +++
net/netfilter/ipvs/ip_vs_sync.c | 65 ++++++++++++++-------------------------
2 files changed, 28 insertions(+), 42 deletions(-)
diff --git a/include/linux/ip_vs.h b/include/linux/ip_vs.h
index be0ef3d..8a2d438 100644
--- a/include/linux/ip_vs.h
+++ b/include/linux/ip_vs.h
@@ -89,6 +89,7 @@
#define IP_VS_CONN_F_TEMPLATE 0x1000 /* template, not connection */
#define IP_VS_CONN_F_ONE_PACKET 0x2000 /* forward only one packet */
+/* Initial bits allowed in backup server */
#define IP_VS_CONN_F_BACKUP_MASK (IP_VS_CONN_F_FWD_MASK | \
IP_VS_CONN_F_NOOUTPUT | \
IP_VS_CONN_F_INACTIVE | \
@@ -97,6 +98,10 @@
IP_VS_CONN_F_TEMPLATE \
)
+/* Bits allowed to update in backup server */
+#define IP_VS_CONN_F_BACKUP_UPD_MASK (IP_VS_CONN_F_INACTIVE | \
+ IP_VS_CONN_F_SEQ_MASK)
+
/* Flags that are not sent to backup server start from bit 16 */
#define IP_VS_CONN_F_NFCT (1 << 16) /* use netfilter conntrack */
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index f4e0b6c..eeed767 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -731,9 +731,30 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
else
cp = ip_vs_ct_in_get(param);
- if (cp && param->pe_data) /* Free pe_data */
+ if (cp) {
+ /* Free pe_data */
kfree(param->pe_data);
- if (!cp) {
+
+ dest = cp->dest;
+ if ((cp->flags ^ flags) & IP_VS_CONN_F_INACTIVE &&
+ !(flags & IP_VS_CONN_F_TEMPLATE) && dest) {
+ if (flags & IP_VS_CONN_F_INACTIVE) {
+ atomic_dec(&dest->activeconns);
+ atomic_inc(&dest->inactconns);
+ } else {
+ atomic_inc(&dest->activeconns);
+ atomic_dec(&dest->inactconns);
+ }
+ }
+ flags &= IP_VS_CONN_F_BACKUP_UPD_MASK;
+ flags |= cp->flags & ~IP_VS_CONN_F_BACKUP_UPD_MASK;
+ cp->flags = flags;
+ if (!dest) {
+ dest = ip_vs_try_bind_dest(cp);
+ if (dest)
+ atomic_dec(&dest->refcnt);
+ }
+ } else {
/*
* Find the appropriate destination for the connection.
* If it is not found the connection will remain unbound
@@ -742,18 +763,6 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
dest = ip_vs_find_dest(net, type, daddr, dport, param->vaddr,
param->vport, protocol, fwmark, flags);
- /* Set the approprite ativity flag */
- if (protocol == IPPROTO_TCP) {
- if (state != IP_VS_TCP_S_ESTABLISHED)
- flags |= IP_VS_CONN_F_INACTIVE;
- else
- flags &= ~IP_VS_CONN_F_INACTIVE;
- } else if (protocol == IPPROTO_SCTP) {
- if (state != IP_VS_SCTP_S_ESTABLISHED)
- flags |= IP_VS_CONN_F_INACTIVE;
- else
- flags &= ~IP_VS_CONN_F_INACTIVE;
- }
cp = ip_vs_conn_new(param, daddr, dport, flags, dest, fwmark);
if (dest)
atomic_dec(&dest->refcnt);
@@ -763,34 +772,6 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
IP_VS_DBG(2, "BACKUP, add new conn. failed\n");
return;
}
- } else if (!cp->dest) {
- dest = ip_vs_try_bind_dest(cp);
- if (dest)
- atomic_dec(&dest->refcnt);
- } else if ((cp->dest) && (cp->protocol == IPPROTO_TCP) &&
- (cp->state != state)) {
- /* update active/inactive flag for the connection */
- dest = cp->dest;
- if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
- (state != IP_VS_TCP_S_ESTABLISHED)) {
- atomic_dec(&dest->activeconns);
- atomic_inc(&dest->inactconns);
- cp->flags |= IP_VS_CONN_F_INACTIVE;
- } else if ((cp->flags & IP_VS_CONN_F_INACTIVE) &&
- (state == IP_VS_TCP_S_ESTABLISHED)) {
- atomic_inc(&dest->activeconns);
- atomic_dec(&dest->inactconns);
- cp->flags &= ~IP_VS_CONN_F_INACTIVE;
- }
- } else if ((cp->dest) && (cp->protocol == IPPROTO_SCTP) &&
- (cp->state != state)) {
- dest = cp->dest;
- if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
- (state != IP_VS_SCTP_S_ESTABLISHED)) {
- atomic_dec(&dest->activeconns);
- atomic_inc(&dest->inactconns);
- cp->flags &= ~IP_VS_CONN_F_INACTIVE;
- }
}
if (opt)
--
1.7.9.5
^ permalink raw reply related
* [PATCH 06/17] ipvs: SH scheduler does not need GFP_ATOMIC allocation
From: Simon Horman @ 2012-05-02 1:24 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Hans Schillstrom, Jesper Dangaard Brouer,
Hans Schillstrom, Simon Horman
In-Reply-To: <1335921901-21284-1-git-send-email-horms@verge.net.au>
From: Julian Anastasov <ja@ssi.bg>
Schedulers are initialized and bound to services only
on commands.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Hans Schillstrom <hans@schillstrom.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_sh.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
index 91e97ee..0512652 100644
--- a/net/netfilter/ipvs/ip_vs_sh.c
+++ b/net/netfilter/ipvs/ip_vs_sh.c
@@ -162,7 +162,7 @@ static int ip_vs_sh_init_svc(struct ip_vs_service *svc)
/* allocate the SH table for this service */
tbl = kmalloc(sizeof(struct ip_vs_sh_bucket)*IP_VS_SH_TAB_SIZE,
- GFP_ATOMIC);
+ GFP_KERNEL);
if (tbl == NULL)
return -ENOMEM;
--
1.7.9.5
^ permalink raw reply related
* [PATCH 05/17] ipvs: LBLCR scheduler does not need GFP_ATOMIC allocation on init
From: Simon Horman @ 2012-05-02 1:24 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Hans Schillstrom, Jesper Dangaard Brouer,
Hans Schillstrom, Simon Horman
In-Reply-To: <1335921901-21284-1-git-send-email-horms@verge.net.au>
From: Julian Anastasov <ja@ssi.bg>
Schedulers are initialized and bound to services only
on commands.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Hans Schillstrom <hans@schillstrom.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_lblcr.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 7498756..00906ea 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -511,7 +511,7 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc)
/*
* Allocate the ip_vs_lblcr_table for this service
*/
- tbl = kmalloc(sizeof(*tbl), GFP_ATOMIC);
+ tbl = kmalloc(sizeof(*tbl), GFP_KERNEL);
if (tbl == NULL)
return -ENOMEM;
--
1.7.9.5
^ permalink raw reply related
* [PATCH 15/17] ipvs: optimize the use of flags in ip_vs_bind_dest
From: Simon Horman @ 2012-05-02 1:24 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Hans Schillstrom, Jesper Dangaard Brouer,
Simon Horman
In-Reply-To: <1335921901-21284-1-git-send-email-horms@verge.net.au>
From: Julian Anastasov <ja@ssi.bg>
cp->flags is marked volatile but ip_vs_bind_dest
can safely modify the flags, so save some CPU cycles by
using temp variable.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_conn.c | 15 +++++++++------
1 file changed, 9 insertions(+), 6 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 6a43c93..7f21b91 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -548,6 +548,7 @@ static inline void
ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
{
unsigned int conn_flags;
+ __u32 flags;
/* if dest is NULL, then return directly */
if (!dest)
@@ -559,17 +560,19 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
conn_flags = atomic_read(&dest->conn_flags);
if (cp->protocol != IPPROTO_UDP)
conn_flags &= ~IP_VS_CONN_F_ONE_PACKET;
+ flags = cp->flags;
/* Bind with the destination and its corresponding transmitter */
- if (cp->flags & IP_VS_CONN_F_SYNC) {
+ if (flags & IP_VS_CONN_F_SYNC) {
/* if the connection is not template and is created
* by sync, preserve the activity flag.
*/
- if (!(cp->flags & IP_VS_CONN_F_TEMPLATE))
+ if (!(flags & IP_VS_CONN_F_TEMPLATE))
conn_flags &= ~IP_VS_CONN_F_INACTIVE;
/* connections inherit forwarding method from dest */
- cp->flags &= ~(IP_VS_CONN_F_FWD_MASK | IP_VS_CONN_F_NOOUTPUT);
+ flags &= ~(IP_VS_CONN_F_FWD_MASK | IP_VS_CONN_F_NOOUTPUT);
}
- cp->flags |= conn_flags;
+ flags |= conn_flags;
+ cp->flags = flags;
cp->dest = dest;
IP_VS_DBG_BUF(7, "Bind-dest %s c:%s:%d v:%s:%d "
@@ -584,11 +587,11 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
atomic_read(&dest->refcnt));
/* Update the connection counters */
- if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) {
+ if (!(flags & IP_VS_CONN_F_TEMPLATE)) {
/* It is a normal connection, so modify the counters
* according to the flags, later the protocol can
* update them on state change */
- if (!(cp->flags & IP_VS_CONN_F_INACTIVE))
+ if (!(flags & IP_VS_CONN_F_INACTIVE))
atomic_inc(&dest->activeconns);
else
atomic_inc(&dest->inactconns);
--
1.7.9.5
^ permalink raw reply related
* Re: [PATCH] mwl8k: Add 0x2a02 PCI device-id (Marvell 88W8361)
From: Lennert Buytenhek @ 2012-05-02 2:38 UTC (permalink / raw)
To: Pat Erley
Cc: sedat.dilek-Re5JQEeQqe8AvxtiuMwx3w, Sedat Dilek, John W. Linville,
linux-wireless-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA, lautriv, Jim Cromie,
Ben Hutchings, Hauke Mehrtens
In-Reply-To: <4FA089F9.1020602-Jx9fsTfDDR3YtjvyW6yDsg@public.gmane.org>
On Tue, May 01, 2012 at 09:12:25PM -0400, Pat Erley wrote:
> >--- a/drivers/net/wireless/mwl8k.c
> >+++ b/drivers/net/wireless/mwl8k.c
> >@@ -5225,6 +5225,7 @@ static void mwl8k_finalize_join_worker(struct work_struct *work)
> > }
> >
> > enum {
> >+ MWL8361P = 0,
> > MWL8363 = 0,
> > MWL8687,
> > MWL8366,
>
> I'm not an expert, but isn't this giving both 8361P and 8363 the
> same values in the enum?
Yeah, this is broken.
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH 3/4 v2 net-next] net: make GRO aware of skb->head_frag
From: Eric Dumazet @ 2012-05-02 2:45 UTC (permalink / raw)
To: Alexander Duyck
Cc: Alexander Duyck, David Miller, netdev, Neal Cardwell, Tom Herbert,
Jeff Kirsher, Michael Chan, Matt Carlson, Herbert Xu,
Ben Hutchings, Ilpo Järvinen, Maciej Żenczykowski
In-Reply-To: <4FA03D69.6060907@intel.com>
On Tue, 2012-05-01 at 12:45 -0700, Alexander Duyck wrote:
> I wasn't worried about the kfree vs put_page, I was worried about the
> coalesce case. However, it looks like you are correct and I am not
> seeing any issues so everything seems to be working fine.
>
> I have a hacked together ixgbe up and running now with the new build_skb
> logic and RSC/LRO disabled. It looks like it is giving me a 5%
> performance boost for small packet routing, but I am using more CPU for
> netperf TCP receive tests and I was wondering if you had seen anything
> similar on the tg3 driver?
>
Hmm, tg3 perf for small packets is not changed, because tg3 uses
copybreak anyway.
#define TG3_RX_COPY_THRESHOLD 256
For big packets, I have no changes in netperf because GRO cannot really
provide big enough skbs at 1Gb speed.
The changes are noticeable when BDP (Bandwidth*Delay Product) is large
and some packet losses happen : You notice lower latencies in TCP stack,
because of less collapses (big copies)
^ permalink raw reply
* Re: [PATCH 3/4 v2 net-next] net: make GRO aware of skb->head_frag
From: Eric Dumazet @ 2012-05-02 2:47 UTC (permalink / raw)
To: Alexander Duyck
Cc: Alexander Duyck, David Miller, netdev, Neal Cardwell, Tom Herbert,
Jeff Kirsher, Michael Chan, Matt Carlson, Herbert Xu,
Ben Hutchings, Ilpo Järvinen, Maciej Żenczykowski
In-Reply-To: <4FA06D7A.6090800@intel.com>
On Tue, 2012-05-01 at 16:10 -0700, Alexander Duyck wrote:
> On 05/01/2012 03:58 PM, Alexander Duyck wrote:
> > Eric,
> >
> > I think I have found a bug, although it is not specific to this patch
> > but it is related. It looks like the TCP coalesce code is causing
> > tcpdump to fail when using frags. Based on the comments in the patch I
> > am assuming you have an ixgbe adapter to test with as that is what I
> > reproduced this on. To reproduce the issue all you need to do is run
> > "tcpdump -i ethX > /dev/null" on one console, and on a second console
> > run a netperf TCP_MAERTS test to some other server. Tcpdump will exit
> > out with a message about bad address like this:
> >
> > tcpdump: verbose output suppressed, use -v or -vv for full protocol decode
> > listening on eth1, link-type EN10MB (Ethernet), capture size 96 bytes
> > tcpdump: pcap_loop: recvfrom: Bad address
> > 682 packets captured
> > 2357 packets received by filter
> > 1543 packets dropped by kernel
> >
> >
> > A bisect of the issue tracked it down to:
> >
> > 1402d366019fedaa2b024f2bac06b7cc9a8782e1 is first bad commit
> > commit 1402d366019fedaa2b024f2bac06b7cc9a8782e1
> > Author: Eric Dumazet <edumazet@google.com>
> > Date: Mon Apr 23 07:11:42 2012 +0000
> >
> > tcp: introduce tcp_try_coalesce
> >
> > commit c8628155ece3 (tcp: reduce out_of_order memory use) took care of
> > coalescing tcp segments provided by legacy devices (linear skbs)
> >
> > We extend this idea to fragged skbs, as their truesize can be heavy.
> >
> > ixgbe for example uses 256+1024+PAGE_SIZE/2 = 3328 bytes per segment.
> >
> > Use this coalescing strategy for receive queue too.
> >
> > This contributes to reduce number of tcp collapses, at minimal cost, and
> > reduces memory overhead and packets drops.
> >
> > Signed-off-by: Eric Dumazet <edumazet@google.com>
> > Cc: Neal Cardwell <ncardwell@google.com>
> > Cc: Tom Herbert <therbert@google.com>
> > Cc: Maciej Żenczykowski <maze@google.com>
> > Cc: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
> > Acked-by: Neal Cardwell <ncardwell@google.com>
> > Signed-off-by: David S. Miller <davem@davemloft.net>
> >
> > :040000 040000 8ca3e0b4e6c6a8f375fd800069d24203880623f3 2576d34c5c9cfc717a11e2ebe054143956716b93 M net
> >
> > I suspect we are dealing with either a shared or cloned skb in this
> > case, though I haven't verified which it is yet.
> >
> > Thanks,
> >
> > Alex
> >
> One additional note. It looks like LRO and GRO need to be disabled to
> trigger the bug. If either of them are enabled it doesn't seem to
> occur. Likely due to the fact that they are doing the coalescing before
> it gets up to the tcp_try_coalesce call.
>
Thanks Alex, I'll take a look.
It seems my tcpdump is different than yours.
^ permalink raw reply
* [V2 PATCH 1/9] macvtap: zerocopy: fix offset calculation when building skb
From: Jason Wang @ 2012-05-02 3:41 UTC (permalink / raw)
To: eric.dumazet, mst, netdev, linux-kernel, ebiederm, davem
In-Reply-To: <20120502033901.11782.13157.stgit@amd-6168-8-1.englab.nay.redhat.com>
This patch fixes the offset calculation when building skb:
- offset1 were used as skb data offset not vector offset
- reset offset to zero only when we advance to next vector
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/net/macvtap.c | 13 +++++++------
1 files changed, 7 insertions(+), 6 deletions(-)
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 0427c65..bd4a70d 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -505,10 +505,11 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
if (copy > size) {
++from;
--count;
- }
+ offset = 0;
+ } else
+ offset += size;
copy -= size;
offset1 += size;
- offset = 0;
}
if (len == offset1)
@@ -519,13 +520,13 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
int num_pages;
unsigned long base;
- len = from->iov_len - offset1;
+ len = from->iov_len - offset;
if (!len) {
- offset1 = 0;
+ offset = 0;
++from;
continue;
}
- base = (unsigned long)from->iov_base + offset1;
+ base = (unsigned long)from->iov_base + offset;
size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
num_pages = get_user_pages_fast(base, size, 0, &page[i]);
if ((num_pages != size) ||
@@ -546,7 +547,7 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
len -= size;
i++;
}
- offset1 = 0;
+ offset = 0;
++from;
}
return 0;
^ permalink raw reply related
* [V2 PATCH 2/9] macvtap: zerocopy: fix truesize underestimation
From: Jason Wang @ 2012-05-02 3:41 UTC (permalink / raw)
To: eric.dumazet, mst, netdev, linux-kernel, ebiederm, davem
In-Reply-To: <20120502033901.11782.13157.stgit@amd-6168-8-1.englab.nay.redhat.com>
As the skb fragment were pinned/built from user pages, we should
account the page instead of length for truesize.
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/net/macvtap.c | 6 ++++--
1 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index bd4a70d..7cb2684 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -519,6 +519,7 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
struct page *page[MAX_SKB_FRAGS];
int num_pages;
unsigned long base;
+ unsigned long truesize;
len = from->iov_len - offset;
if (!len) {
@@ -533,10 +534,11 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
(num_pages > MAX_SKB_FRAGS - skb_shinfo(skb)->nr_frags))
/* put_page is in skb free */
return -EFAULT;
+ truesize = size * PAGE_SIZE;
skb->data_len += len;
skb->len += len;
- skb->truesize += len;
- atomic_add(len, &skb->sk->sk_wmem_alloc);
+ skb->truesize += truesize;
+ atomic_add(truesize, &skb->sk->sk_wmem_alloc);
while (len) {
int off = base & ~PAGE_MASK;
int size = min_t(int, len, PAGE_SIZE - off);
^ permalink raw reply related
* [V2 PATCH 3/9] macvtap: zerocopy: put page when fail to get all requested user pages
From: Jason Wang @ 2012-05-02 3:41 UTC (permalink / raw)
To: eric.dumazet, mst, netdev, linux-kernel, ebiederm, davem
In-Reply-To: <20120502033901.11782.13157.stgit@amd-6168-8-1.englab.nay.redhat.com>
When get_user_pages_fast() fails to get all requested pages, we could not use
kfree_skb() to free it as it has not been put in the skb fragments. So we need
to call put_page() instead.
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/net/macvtap.c | 6 ++++--
1 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 7cb2684..9ab182a 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -531,9 +531,11 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
num_pages = get_user_pages_fast(base, size, 0, &page[i]);
if ((num_pages != size) ||
- (num_pages > MAX_SKB_FRAGS - skb_shinfo(skb)->nr_frags))
- /* put_page is in skb free */
+ (num_pages > MAX_SKB_FRAGS - skb_shinfo(skb)->nr_frags)) {
+ for (i = 0; i < num_pages; i++)
+ put_page(page[i]);
return -EFAULT;
+ }
truesize = size * PAGE_SIZE;
skb->data_len += len;
skb->len += len;
^ permalink raw reply related
* [V2 PATCH 4/9] macvtap: zerocopy: set SKBTX_DEV_ZEROCOPY only when skb is built successfully
From: Jason Wang @ 2012-05-02 3:42 UTC (permalink / raw)
To: eric.dumazet, mst, netdev, linux-kernel, ebiederm, davem
In-Reply-To: <20120502033901.11782.13157.stgit@amd-6168-8-1.englab.nay.redhat.com>
Current the SKBTX_DEV_ZEROCOPY is set unconditionally after
zerocopy_sg_from_iovec(), this would lead NULL pointer when macvtap
fails to build zerocopy skb because destructor_arg was not
initialized. Solve this by set this flag after the skb were built
successfully.
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/net/macvtap.c | 9 +++++----
1 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 9ab182a..a4ff694 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -699,10 +699,9 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
if (!skb)
goto err;
- if (zerocopy) {
+ if (zerocopy)
err = zerocopy_sg_from_iovec(skb, iv, vnet_hdr_len, count);
- skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
- } else
+ else
err = skb_copy_datagram_from_iovec(skb, 0, iv, vnet_hdr_len,
len);
if (err)
@@ -721,8 +720,10 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
rcu_read_lock_bh();
vlan = rcu_dereference_bh(q->vlan);
/* copy skb_ubuf_info for callback when skb has no error */
- if (zerocopy)
+ if (zerocopy) {
skb_shinfo(skb)->destructor_arg = m->msg_control;
+ skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
+ }
if (vlan)
macvlan_start_xmit(skb, vlan->dev);
else
^ permalink raw reply related
* [V2 PATCH 6/9] vhost_net: zerocopy: fix possible NULL pointer dereference of vq->bufs
From: Jason Wang @ 2012-05-02 3:42 UTC (permalink / raw)
To: eric.dumazet, mst, netdev, linux-kernel, ebiederm, davem
In-Reply-To: <20120502033901.11782.13157.stgit@amd-6168-8-1.englab.nay.redhat.com>
When we want to disable vhost_net backend while there's a tx work, a possible
NULL pointer defernece may happen we we try to deference the vq->bufs after
vhost_net_set_backend() assign a NULL to it.
As suggested by Michael, fix this by checking the vq->bufs instead of
vhost_sock_zcopy().
---
drivers/vhost/net.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index f0da2c3..ffdc0d8 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -166,7 +166,7 @@ static void handle_tx(struct vhost_net *net)
if (wmem < sock->sk->sk_sndbuf / 2)
tx_poll_stop(net);
hdr_size = vq->vhost_hlen;
- zcopy = vhost_sock_zcopy(sock);
+ zcopy = vq->ubufs;
for (;;) {
/* Release DMAs done buffers first */
^ permalink raw reply related
* [V2 PATCH 8/9] vhost_net: zerocopy: adding and signalling immediately when fully copied
From: Jason Wang @ 2012-05-02 3:42 UTC (permalink / raw)
To: eric.dumazet, mst, netdev, linux-kernel, ebiederm, davem
In-Reply-To: <20120502033901.11782.13157.stgit@amd-6168-8-1.englab.nay.redhat.com>
When a packet were fully copied in zerocopy, we don't wait for the DMA done to
mark the done flag, so after the packet were passed to lower device, we need to
add used and signal guest immediately.
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/vhost/net.c | 2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 62828aa..1dc2aeb 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -266,6 +266,8 @@ static void handle_tx(struct vhost_net *net)
" len %d != %zd\n", err, len);
if (!zcopy)
vhost_add_used_and_signal(&net->dev, vq, head, 0);
+ else
+ vhost_zerocopy_signal_used(vq);
total_len += len;
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
vhost_poll_queue(&vq->poll);
^ permalink raw reply related
* [V2 PATCH 9/9] vhost: zerocopy: poll vq in zerocopy callback
From: Jason Wang @ 2012-05-02 3:42 UTC (permalink / raw)
To: eric.dumazet, mst, netdev, linux-kernel, ebiederm, davem
In-Reply-To: <20120502033901.11782.13157.stgit@amd-6168-8-1.englab.nay.redhat.com>
We add used and signal guest in worker thread but did not poll the virtqueue
during the zero copy callback. This may lead the missing of adding and
signalling during zerocopy. Solve this by polling the virtqueue and let it
wakeup the worker during callback.
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/vhost/vhost.c | 1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 947f00d..7b75fdf 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1604,6 +1604,7 @@ void vhost_zerocopy_callback(void *arg)
struct vhost_ubuf_ref *ubufs = ubuf->arg;
struct vhost_virtqueue *vq = ubufs->vq;
+ vhost_poll_queue(&vq->poll);
/* set len = 1 to mark this desc buffers done DMA */
vq->heads[ubuf->desc].len = VHOST_DMA_DONE_LEN;
kref_put(&ubufs->kref, vhost_zerocopy_done_signal);
^ permalink raw reply related
* [V2 PATCH 0/9] vhost/macvtap zeropcopy fixes
From: Jason Wang @ 2012-05-02 3:41 UTC (permalink / raw)
To: eric.dumazet, mst, netdev, linux-kernel, ebiederm, davem
This is an updated since the last series of vhost/macvtap zerocopy fixes which
fixes the the possible transmission stall, host kernel stack overflow and other
misc fixes.
Changes from V1:
- Addressing comments from Eric and Michael.
- Adding more fixes into the seires.
---
Jason Wang (9):
macvtap: zerocopy: fix offset calculation when building skb
macvtap: zerocopy: fix truesize underestimation
macvtap: zerocopy: put page when fail to get all requested user pages
macvtap: zerocopy: set SKBTX_DEV_ZEROCOPY only when skb is built successfully
macvtap: zerocopy: validate vectors before building skb
vhost_net: zerocopy: fix possible NULL pointer dereference of vq->bufs
vhost_net: re-poll only on EAGAIN or ENOBUFS
vhost_net: zerocopy: adding and signalling immediately when fully copied
vhost: zerocopy: poll vq in zerocopy callback
drivers/net/macvtap.c | 57 ++++++++++++++++++++++++++++++++++---------------
drivers/vhost/net.c | 7 ++++--
drivers/vhost/vhost.c | 1 +
3 files changed, 46 insertions(+), 19 deletions(-)
--
Jason Wang
^ permalink raw reply
* [V2 PATCH 5/9] macvtap: zerocopy: validate vectors before building skb
From: Jason Wang @ 2012-05-02 3:42 UTC (permalink / raw)
To: eric.dumazet, mst, netdev, linux-kernel, ebiederm, davem
In-Reply-To: <20120502033901.11782.13157.stgit@amd-6168-8-1.englab.nay.redhat.com>
There're several reasons that the vectors need to be validated:
- Return error when caller provides vectors whose num is greater than UIO_MAXIOV.
- Linearize part of skb when userspace provides vectors grater than MAX_SKB_FRAGS.
- Return error when userspace provides vectors whose total length may exceed
- MAX_SKB_FRAGS * PAGE_SIZE.
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/net/macvtap.c | 25 +++++++++++++++++++++----
1 files changed, 21 insertions(+), 4 deletions(-)
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index a4ff694..163559c 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -529,9 +529,10 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
}
base = (unsigned long)from->iov_base + offset;
size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
+ if (i + size > MAX_SKB_FRAGS)
+ return -EMSGSIZE;
num_pages = get_user_pages_fast(base, size, 0, &page[i]);
- if ((num_pages != size) ||
- (num_pages > MAX_SKB_FRAGS - skb_shinfo(skb)->nr_frags)) {
+ if (num_pages != size) {
for (i = 0; i < num_pages; i++)
put_page(page[i]);
return -EFAULT;
@@ -651,7 +652,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
int err;
struct virtio_net_hdr vnet_hdr = { 0 };
int vnet_hdr_len = 0;
- int copylen;
+ int copylen = 0;
bool zerocopy = false;
if (q->flags & IFF_VNET_HDR) {
@@ -680,15 +681,31 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
if (unlikely(len < ETH_HLEN))
goto err;
+ err = -EMSGSIZE;
+ if (unlikely(count > UIO_MAXIOV))
+ goto err;
+
if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY))
zerocopy = true;
if (zerocopy) {
+ /* Userspace may produce vectors with count greater than
+ * MAX_SKB_FRAGS, so we need to linearize parts of the skb
+ * to let the rest of data to be fit in the frags.
+ */
+ if (count > MAX_SKB_FRAGS) {
+ copylen = iov_length(iv, count - MAX_SKB_FRAGS);
+ if (copylen < vnet_hdr_len)
+ copylen = 0;
+ else
+ copylen -= vnet_hdr_len;
+ }
/* There are 256 bytes to be copied in skb, so there is enough
* room for skb expand head in case it is used.
* The rest buffer is mapped from userspace.
*/
- copylen = vnet_hdr.hdr_len;
+ if (copylen < vnet_hdr.hdr_len)
+ copylen = vnet_hdr.hdr_len;
if (!copylen)
copylen = GOODCOPY_LEN;
} else
^ permalink raw reply related
* [V2 PATCH 7/9] vhost_net: re-poll only on EAGAIN or ENOBUFS
From: Jason Wang @ 2012-05-02 3:42 UTC (permalink / raw)
To: eric.dumazet, mst, netdev, linux-kernel, ebiederm, davem
In-Reply-To: <20120502033901.11782.13157.stgit@amd-6168-8-1.englab.nay.redhat.com>
Currently, we restart tx polling unconditionally when sendmsg()
fails. This would cause unnecessary wakeups of vhost wokers and waste
cpu utlization when evil userspace(guest driver) is able to hit EFAULT or
EINVAL.
The polling is only needed when the socket send buffer were exceeded or not
enough memory. So fix this by restarting polling only when sendmsg() returns
EAGAIN/ENOBUFS.
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/vhost/net.c | 3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index ffdc0d8..62828aa 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -257,7 +257,8 @@ static void handle_tx(struct vhost_net *net)
UIO_MAXIOV;
}
vhost_discard_vq_desc(vq, 1);
- tx_poll_start(net, sock);
+ if (err == -EAGAIN || err == -ENOBUFS)
+ tx_poll_start(net, sock);
break;
}
if (err != len)
^ permalink raw reply related
* Re: [PATCH 3/4 v2 net-next] net: make GRO aware of skb->head_frag
From: Eric Dumazet @ 2012-05-02 3:54 UTC (permalink / raw)
To: Alexander Duyck
Cc: Alexander Duyck, David Miller, netdev, Neal Cardwell, Tom Herbert,
Jeff Kirsher, Michael Chan, Matt Carlson, Herbert Xu,
Ben Hutchings, Ilpo Järvinen, Maciej Żenczykowski
In-Reply-To: <1335926862.22133.42.camel@edumazet-glaptop>
On Wed, 2012-05-02 at 04:47 +0200, Eric Dumazet wrote:
> Thanks Alex, I'll take a look.
>
> It seems my tcpdump is different than yours.
>
>
I'll test following patch in a couple of hours :
Thanks !
net/ipv4/tcp_input.c | 16 +++++++++++++---
1 file changed, 13 insertions(+), 3 deletions(-)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 96a631d..910a794 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4467,7 +4467,8 @@ static bool tcp_try_coalesce(struct sock *sk,
struct sk_buff *from,
bool *fragstolen)
{
- int delta, len = from->len;
+ int i, delta, len = from->len;
+ bool fastpath;
*fragstolen = false;
if (tcp_hdr(from)->fin)
@@ -4484,6 +4485,7 @@ merge:
if (skb_has_frag_list(to) || skb_has_frag_list(from))
return false;
+ fastpath = !from->cloned || atomic_read(&skb_shinfo(from)->dataref) == 1;
if (skb_headlen(from) == 0 &&
(skb_shinfo(to)->nr_frags +
skb_shinfo(from)->nr_frags <= MAX_SKB_FRAGS)) {
@@ -4497,7 +4499,13 @@ copyfrags:
skb_shinfo(from)->frags,
skb_shinfo(from)->nr_frags * sizeof(skb_frag_t));
skb_shinfo(to)->nr_frags += skb_shinfo(from)->nr_frags;
- skb_shinfo(from)->nr_frags = 0;
+
+ if (fastpath)
+ skb_shinfo(from)->nr_frags = 0;
+ else
+ for (i = 0; i < skb_shinfo(from)->nr_frags; i++)
+ skb_frag_ref(from, i);
+
to->truesize += delta;
atomic_add(delta, &sk->sk_rmem_alloc);
sk_mem_charge(sk, delta);
@@ -4515,7 +4523,9 @@ copyfrags:
offset = from->data - (unsigned char *)page_address(page);
skb_fill_page_desc(to, skb_shinfo(to)->nr_frags,
page, offset, skb_headlen(from));
- *fragstolen = true;
+ *fragstolen = fastpath;
+ if (!fastpath)
+ get_page(page);
delta = len; /* we dont know real truesize... */
goto copyfrags;
}
^ permalink raw reply related
* Re: pull request: wireless 2012-05-01
From: David Miller @ 2012-05-02 4:05 UTC (permalink / raw)
To: linville-2XuSBdqkA4R54TAoqtyWWQ
Cc: linux-wireless-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <20120501183157.GA2987-2XuSBdqkA4R54TAoqtyWWQ@public.gmane.org>
From: "John W. Linville" <linville-2XuSBdqkA4R54TAoqtyWWQ@public.gmane.org>
Date: Tue, 1 May 2012 14:31:58 -0400
> Part of these are Bluetooth -- Gustavo says:
>
> "A few more fixes to 3.4, there is three new device id supported, a missing
> break and a fix to retain key during the connection."
>
> Along with those, we have some 802.11 fixes. Felix gives us a fix
> for sending EAP frames for AP VLAN interfaces. Franky gives us
> two brcmfmac fixes, one for missed event completions and another
> for an improperly initialized function pointer. Grazvydas Ignotas
> gives us a couple of wl1251 fixes for some improperly freed memory.
> Jonathan Bither gives us an ath5k fix for an AHB resource leak.
> Seth Forshee gives us a b43 fix to avoid a crash when b43 fails to
> properly initialize. Finally, Wey-yi gives us a fixup for a previously
> merged fix to use the correct firmware for certain iwlwifi devices.
>
> The brcmfmac fixes are bigger than I would like to see. But since
> they are isolated to that driver and fix real problems, I felt they
> were still acceptable.
>
> Please let me know if there are problems!
Pulled, thanks John.
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH] RPS: Sparse connection optimizations
From: Deng-Cheng Zhu @ 2012-05-02 4:08 UTC (permalink / raw)
To: Eric Dumazet; +Cc: davem, therbert, netdev
In-Reply-To: <1335614156.2900.66.camel@edumazet-glaptop>
On 04/28/2012 07:55 PM, Eric Dumazet wrote:
> On Sat, 2012-04-28 at 18:10 +0800, Deng-Cheng Zhu wrote:
>> From: Deng-Cheng Zhu<dczhu@mips.com>
>>
>> Currently, choosing target CPU to process the incoming packet is based on
>> skb->rxhash. In the case of sparse connections, this could lead to
>> relatively low and inconsistent bandwidth while doing network throughput
>> tests -- CPU selection in the RPS map is imbalanced. Even with the same
>> hash value, 2 packets could come from different devices. Besides, on
>> architectures like MIPS with multi-threaded cores, siblings of CPU0 should
>> not be selected when others are not saturated.
>
> What CPU0 is doing so special you have to mention it in this changelog ?
Serve the NIC hardware irq and do the 1st part of softirq in RPS.
Changes relating to this will be made in v2. Thanks.
>>
>> This patch introduces a feature that allows some flows to select their CPUs
>> by looping the RPS CPU maps. Some tests were performed on the MIPS Malta
>> 1004K platform (2 cores, each with 2 VPEs) at 25Mhz with 2 Intel Pro/1000
>> NICs. The Malta board works as a router between 2 PCs. Using iperf, here
>> are results:
>
>
> RPS on a router ? Thats not very good, unless you perform a crazy amount
> of work in iptables rules maybe ?
>
> One packet comes, its better to handle it right now and send it right
> now on the same cpu. No IPI cost, no cache line misses...
Theoretically, you are right. But RPS works early -- when the hot CPU
gets really hot, RPS takes effect even with forwarding workload. Earlier
experiments on the mentioned Malta platform proved it as well
(typically 45% ~ more than doubled, amazingly).
>
> RPS is something more suitable to TCP handling in local host because
> stack has big memory footprint and latencies, not for forwarding
> workload.
See above.
> I suspect you can reach more throughput using appropriate tunings
> (correct interrupt affinities). This sounds like a bad config from the
> very beginning.
Unfortunately, on the Malta platform, NIC irqs are not suitable for SMP
IRQ affinity -- they are based on XT-PIC. However, I did do some RPS
tests where different CPU masks were assigned to the 2 NICs. And the
throughput *WAS* better than that of assigning the same mask to NICs.
But the problem addressed in this patch *STILL* exists -- hash indexing
causes imbalance across CPUs in the case of sparse connections.
>
>> +};
>> +
>> +static struct cpu_flow flow[CONFIG_NR_RPS_MAP_LOOPS][NR_CPUS];
>
> Thats absolutely not allowed to add a [NR_CPUS] array anywhere in linux
> kernel in 2012.
Good advice. Will be different in V2.
>
>> +/*
>> + * We've got CONFIG_SMP to do RPS, so only arch define is needed here to access
>> + * sibling specific information.
>> + */
>> +#if defined(CONFIG_MIPS)
>
> Thats not allowed to add a CONFIG_somearch in net/core/dev.c
Good advice too.
Thanks!
Deng-Cheng
^ 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