1 files changed, 142 insertions, 1 deletions

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index c41a5392edc9..38df3ee655ed 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -263,7 +263,7 @@ static void est_reload_work_handler(struct work_struct *work)
 		/* New config ? Stop kthread tasks */
 		if (genid != genid_done)
 			ip_vs_est_kthread_stop(kd);
-		if (!kd->task) {
+		if (!kd->task && !ip_vs_est_stopped(ipvs)) {
 			/* Do not start kthreads above 0 in calc phase */
 			if ((!id || !ipvs->est_calc_phase) &&
 			    ip_vs_est_kthread_start(ipvs, kd) < 0)
@@ -1940,6 +1940,122 @@ proc_do_sync_ports(struct ctl_table *table, int write,
 	return rc;
 }
 
+static int ipvs_proc_est_cpumask_set(struct ctl_table *table, void *buffer)
+{
+	struct netns_ipvs *ipvs = table->extra2;
+	cpumask_var_t *valp = table->data;
+	cpumask_var_t newmask;
+	int ret;
+
+	if (!zalloc_cpumask_var(&newmask, GFP_KERNEL))
+		return -ENOMEM;
+
+	ret = cpulist_parse(buffer, newmask);
+	if (ret)
+		goto out;
+
+	mutex_lock(&ipvs->est_mutex);
+
+	if (!ipvs->est_cpulist_valid) {
+		if (!zalloc_cpumask_var(valp, GFP_KERNEL)) {
+			ret = -ENOMEM;
+			goto unlock;
+		}
+		ipvs->est_cpulist_valid = 1;
+	}
+	cpumask_and(newmask, newmask, &current->cpus_mask);
+	cpumask_copy(*valp, newmask);
+	/* est_max_threads may depend on cpulist size */
+	ipvs->est_max_threads = ip_vs_est_max_threads(ipvs);
+	ipvs->est_calc_phase = 1;
+	ip_vs_est_reload_start(ipvs);
+
+unlock:
+	mutex_unlock(&ipvs->est_mutex);
+
+out:
+	free_cpumask_var(newmask);
+	return ret;
+}
+
+static int ipvs_proc_est_cpumask_get(struct ctl_table *table, void *buffer,
+				     size_t size)
+{
+	struct netns_ipvs *ipvs = table->extra2;
+	cpumask_var_t *valp = table->data;
+	struct cpumask *mask;
+	int ret;
+
+	mutex_lock(&ipvs->est_mutex);
+
+	if (ipvs->est_cpulist_valid)
+		mask = *valp;
+	else
+		mask = (struct cpumask *)housekeeping_cpumask(HK_TYPE_KTHREAD);
+	ret = scnprintf(buffer, size, "%*pbl\n", cpumask_pr_args(mask));
+
+	mutex_unlock(&ipvs->est_mutex);
+
+	return ret;
+}
+
+static int ipvs_proc_est_cpulist(struct ctl_table *table, int write,
+				 void *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret;
+
+	/* Ignore both read and write(append) if *ppos not 0 */
+	if (*ppos || !*lenp) {
+		*lenp = 0;
+		return 0;
+	}
+	if (write) {
+		/* proc_sys_call_handler() appends terminator */
+		ret = ipvs_proc_est_cpumask_set(table, buffer);
+		if (ret >= 0)
+			*ppos += *lenp;
+	} else {
+		/* proc_sys_call_handler() allocates 1 byte for terminator */
+		ret = ipvs_proc_est_cpumask_get(table, buffer, *lenp + 1);
+		if (ret >= 0) {
+			*lenp = ret;
+			*ppos += *lenp;
+			ret = 0;
+		}
+	}
+	return ret;
+}
+
+static int ipvs_proc_est_nice(struct ctl_table *table, int write,
+			      void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct netns_ipvs *ipvs = table->extra2;
+	int *valp = table->data;
+	int val = *valp;
+	int ret;
+
+	struct ctl_table tmp_table = {
+		.data = &val,
+		.maxlen = sizeof(int),
+		.mode = table->mode,
+	};
+
+	ret = proc_dointvec(&tmp_table, write, buffer, lenp, ppos);
+	if (write && ret >= 0) {
+		if (val < MIN_NICE || val > MAX_NICE) {
+			ret = -EINVAL;
+		} else {
+			mutex_lock(&ipvs->est_mutex);
+			if (*valp != val) {
+				*valp = val;
+				ip_vs_est_reload_start(ipvs);
+			}
+			mutex_unlock(&ipvs->est_mutex);
+		}
+	}
+	return ret;
+}
+
 /*
  *	IPVS sysctl table (under the /proc/sys/net/ipv4/vs/)
  *	Do not change order or insert new entries without
@@ -2116,6 +2232,18 @@ static struct ctl_table vs_vars[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "est_cpulist",
+		.maxlen		= NR_CPUS,	/* unused */
+		.mode		= 0644,
+		.proc_handler	= ipvs_proc_est_cpulist,
+	},
+	{
+		.procname	= "est_nice",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= ipvs_proc_est_nice,
+	},
 #ifdef CONFIG_IP_VS_DEBUG
 	{
 		.procname	= "debug_level",
@@ -4134,6 +4262,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
 	INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler);
 	INIT_DELAYED_WORK(&ipvs->expire_nodest_conn_work,
 			  expire_nodest_conn_handler);
+	ipvs->est_stopped = 0;
 
 	if (!net_eq(net, &init_net)) {
 		tbl = kmemdup(vs_vars, sizeof(vs_vars), GFP_KERNEL);
@@ -4195,6 +4324,15 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
 	tbl[idx++].data = &ipvs->sysctl_ignore_tunneled;
 	ipvs->sysctl_run_estimation = 1;
 	tbl[idx++].data = &ipvs->sysctl_run_estimation;
+
+	ipvs->est_cpulist_valid = 0;
+	tbl[idx].extra2 = ipvs;
+	tbl[idx++].data = &ipvs->sysctl_est_cpulist;
+
+	ipvs->sysctl_est_nice = IPVS_EST_NICE;
+	tbl[idx].extra2 = ipvs;
+	tbl[idx++].data = &ipvs->sysctl_est_nice;
+
 #ifdef CONFIG_IP_VS_DEBUG
 	/* Global sysctls must be ro in non-init netns */
 	if (!net_eq(net, &init_net))
@@ -4234,6 +4372,9 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs)
 	unregister_net_sysctl_table(ipvs->sysctl_hdr);
 	ip_vs_stop_estimator(ipvs, &ipvs->tot_stats->s);
 
+	if (ipvs->est_cpulist_valid)
+		free_cpumask_var(ipvs->sysctl_est_cpulist);
+
 	if (!net_eq(net, &init_net))
 		kfree(ipvs->sysctl_tbl);
 }