Merge remote-tracking branch 'tip/perf/urgent' into perf/core

To pick up fixes.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

6 files changed, 109 insertions, 46 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 82114e1111e6..93243479085f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1752,6 +1752,28 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
 }
 EXPORT_SYMBOL(call_netdevice_notifiers);
 
+/**
+ *	call_netdevice_notifiers_mtu - call all network notifier blocks
+ *	@val: value passed unmodified to notifier function
+ *	@dev: net_device pointer passed unmodified to notifier function
+ *	@arg: additional u32 argument passed to the notifier function
+ *
+ *	Call all network notifier blocks.  Parameters and return value
+ *	are as for raw_notifier_call_chain().
+ */
+static int call_netdevice_notifiers_mtu(unsigned long val,
+					struct net_device *dev, u32 arg)
+{
+	struct netdev_notifier_info_ext info = {
+		.info.dev = dev,
+		.ext.mtu = arg,
+	};
+
+	BUILD_BUG_ON(offsetof(struct netdev_notifier_info_ext, info) != 0);
+
+	return call_netdevice_notifiers_info(val, &info.info);
+}
+
 #ifdef CONFIG_NET_INGRESS
 static DEFINE_STATIC_KEY_FALSE(ingress_needed_key);
 
@@ -7574,14 +7596,16 @@ int dev_set_mtu_ext(struct net_device *dev, int new_mtu,
 	err = __dev_set_mtu(dev, new_mtu);
 
 	if (!err) {
-		err = call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
+		err = call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev,
+						   orig_mtu);
 		err = notifier_to_errno(err);
 		if (err) {
 			/* setting mtu back and notifying everyone again,
 			 * so that they have a chance to revert changes.
 			 */
 			__dev_set_mtu(dev, orig_mtu);
-			call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
+			call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev,
+						     new_mtu);
 		}
 	}
 	return err;
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 8c0ed225e280..6bc42933be4a 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -2995,6 +2995,8 @@ devlink_param_value_get_from_info(const struct devlink_param *param,
 				  struct genl_info *info,
 				  union devlink_param_value *value)
 {
+	int len;
+
 	if (param->type != DEVLINK_PARAM_TYPE_BOOL &&
 	    !info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])
 		return -EINVAL;
@@ -3010,10 +3012,13 @@ devlink_param_value_get_from_info(const struct devlink_param *param,
 		value->vu32 = nla_get_u32(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
 		break;
 	case DEVLINK_PARAM_TYPE_STRING:
-		if (nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) >
-		    DEVLINK_PARAM_MAX_STRING_VALUE)
+		len = strnlen(nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]),
+			      nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]));
+		if (len == nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) ||
+		    len >= __DEVLINK_PARAM_MAX_STRING_VALUE)
 			return -EINVAL;
-		value->vstr = nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+		strcpy(value->vstr,
+		       nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]));
 		break;
 	case DEVLINK_PARAM_TYPE_BOOL:
 		value->vbool = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA] ?
@@ -3100,7 +3105,10 @@ static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb,
 		return -EOPNOTSUPP;
 
 	if (cmode == DEVLINK_PARAM_CMODE_DRIVERINIT) {
-		param_item->driverinit_value = value;
+		if (param->type == DEVLINK_PARAM_TYPE_STRING)
+			strcpy(param_item->driverinit_value.vstr, value.vstr);
+		else
+			param_item->driverinit_value = value;
 		param_item->driverinit_value_valid = true;
 	} else {
 		if (!param->set)
@@ -4540,7 +4548,10 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
 					      DEVLINK_PARAM_CMODE_DRIVERINIT))
 		return -EOPNOTSUPP;
 
-	*init_val = param_item->driverinit_value;
+	if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING)
+		strcpy(init_val->vstr, param_item->driverinit_value.vstr);
+	else
+		*init_val = param_item->driverinit_value;
 
 	return 0;
 }
@@ -4571,7 +4582,10 @@ int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
 					      DEVLINK_PARAM_CMODE_DRIVERINIT))
 		return -EOPNOTSUPP;
 
-	param_item->driverinit_value = init_val;
+	if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING)
+		strcpy(param_item->driverinit_value.vstr, init_val.vstr);
+	else
+		param_item->driverinit_value = init_val;
 	param_item->driverinit_value_valid = true;
 
 	devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW);
@@ -4604,6 +4618,23 @@ void devlink_param_value_changed(struct devlink *devlink, u32 param_id)
 EXPORT_SYMBOL_GPL(devlink_param_value_changed);
 
 /**
+ *	devlink_param_value_str_fill - Safely fill-up the string preventing
+ *				       from overflow of the preallocated buffer
+ *
+ *	@dst_val: destination devlink_param_value
+ *	@src: source buffer
+ */
+void devlink_param_value_str_fill(union devlink_param_value *dst_val,
+				  const char *src)
+{
+	size_t len;
+
+	len = strlcpy(dst_val->vstr, src, __DEVLINK_PARAM_MAX_STRING_VALUE);
+	WARN_ON(len >= __DEVLINK_PARAM_MAX_STRING_VALUE);
+}
+EXPORT_SYMBOL_GPL(devlink_param_value_str_fill);
+
+/**
  *	devlink_region_create - create a new address region
  *
  *	@devlink: devlink
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 234a0ec2e932..0762aaf8e964 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1483,6 +1483,7 @@ static int ethtool_get_wol(struct net_device *dev, char __user *useraddr)
 static int ethtool_set_wol(struct net_device *dev, char __user *useraddr)
 {
 	struct ethtool_wolinfo wol;
+	int ret;
 
 	if (!dev->ethtool_ops->set_wol)
 		return -EOPNOTSUPP;
@@ -1490,7 +1491,13 @@ static int ethtool_set_wol(struct net_device *dev, char __user *useraddr)
 	if (copy_from_user(&wol, useraddr, sizeof(wol)))
 		return -EFAULT;
 
-	return dev->ethtool_ops->set_wol(dev, &wol);
+	ret = dev->ethtool_ops->set_wol(dev, &wol);
+	if (ret)
+		return ret;
+
+	dev->wol_enabled = !!wol.wolopts;
+
+	return 0;
 }
 
 static int ethtool_get_eee(struct net_device *dev, char __user *useraddr)
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 3219a2932463..de1d1ba92f2d 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -135,27 +135,9 @@ static void queue_process(struct work_struct *work)
 	}
 }
 
-/*
- * Check whether delayed processing was scheduled for our NIC. If so,
- * we attempt to grab the poll lock and use ->poll() to pump the card.
- * If this fails, either we've recursed in ->poll() or it's already
- * running on another CPU.
- *
- * Note: we don't mask interrupts with this lock because we're using
- * trylock here and interrupts are already disabled in the softirq
- * case. Further, we test the poll_owner to avoid recursion on UP
- * systems where the lock doesn't exist.
- */
 static void poll_one_napi(struct napi_struct *napi)
 {
-	int work = 0;
-
-	/* net_rx_action's ->poll() invocations and our's are
-	 * synchronized by this test which is only made while
-	 * holding the napi->poll_lock.
-	 */
-	if (!test_bit(NAPI_STATE_SCHED, &napi->state))
-		return;
+	int work;
 
 	/* If we set this bit but see that it has already been set,
 	 * that indicates that napi has been disabled and we need
@@ -330,6 +312,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 	/* It is up to the caller to keep npinfo alive. */
 	struct netpoll_info *npinfo;
 
+	rcu_read_lock_bh();
 	lockdep_assert_irqs_disabled();
 
 	npinfo = rcu_dereference_bh(np->dev->npinfo);
@@ -374,6 +357,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 		skb_queue_tail(&npinfo->txq, skb);
 		schedule_delayed_work(&npinfo->tx_work,0);
 	}
+	rcu_read_unlock_bh();
 }
 EXPORT_SYMBOL(netpoll_send_skb_on_dev);
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 63ce2283a456..37c7936124e6 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1898,10 +1898,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 		if (tb[IFLA_IF_NETNSID]) {
 			netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]);
 			tgt_net = get_target_net(skb->sk, netnsid);
-			if (IS_ERR(tgt_net)) {
-				tgt_net = net;
-				netnsid = -1;
-			}
+			if (IS_ERR(tgt_net))
+				return PTR_ERR(tgt_net);
 		}
 
 		if (tb[IFLA_EXT_MASK])
@@ -2837,6 +2835,12 @@ struct net_device *rtnl_create_link(struct net *net,
 	else if (ops->get_num_rx_queues)
 		num_rx_queues = ops->get_num_rx_queues();
 
+	if (num_tx_queues < 1 || num_tx_queues > 4096)
+		return ERR_PTR(-EINVAL);
+
+	if (num_rx_queues < 1 || num_rx_queues > 4096)
+		return ERR_PTR(-EINVAL);
+
 	dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type,
 			       ops->setup, num_tx_queues, num_rx_queues);
 	if (!dev)
@@ -3744,16 +3748,27 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	int err = 0;
 	int fidx = 0;
 
-	err = nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb,
-			  IFLA_MAX, ifla_policy, NULL);
-	if (err < 0) {
-		return -EINVAL;
-	} else if (err == 0) {
-		if (tb[IFLA_MASTER])
-			br_idx = nla_get_u32(tb[IFLA_MASTER]);
-	}
+	/* A hack to preserve kernel<->userspace interface.
+	 * Before Linux v4.12 this code accepted ndmsg since iproute2 v3.3.0.
+	 * However, ndmsg is shorter than ifinfomsg thus nlmsg_parse() bails.
+	 * So, check for ndmsg with an optional u32 attribute (not used here).
+	 * Fortunately these sizes don't conflict with the size of ifinfomsg
+	 * with an optional attribute.
+	 */
+	if (nlmsg_len(cb->nlh) != sizeof(struct ndmsg) &&
+	    (nlmsg_len(cb->nlh) != sizeof(struct ndmsg) +
+	     nla_attr_size(sizeof(u32)))) {
+		err = nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb,
+				  IFLA_MAX, ifla_policy, NULL);
+		if (err < 0) {
+			return -EINVAL;
+		} else if (err == 0) {
+			if (tb[IFLA_MASTER])
+				br_idx = nla_get_u32(tb[IFLA_MASTER]);
+		}
 
-	brport_idx = ifm->ifi_index;
+		brport_idx = ifm->ifi_index;
+	}
 
 	if (br_idx) {
 		br_dev = __dev_get_by_index(net, br_idx);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b2c807f67aba..428094b577fc 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4452,14 +4452,16 @@ EXPORT_SYMBOL_GPL(skb_complete_wifi_ack);
  */
 bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
 {
-	if (unlikely(start > skb_headlen(skb)) ||
-	    unlikely((int)start + off > skb_headlen(skb) - 2)) {
-		net_warn_ratelimited("bad partial csum: csum=%u/%u len=%u\n",
-				     start, off, skb_headlen(skb));
+	u32 csum_end = (u32)start + (u32)off + sizeof(__sum16);
+	u32 csum_start = skb_headroom(skb) + (u32)start;
+
+	if (unlikely(csum_start > U16_MAX || csum_end > skb_headlen(skb))) {
+		net_warn_ratelimited("bad partial csum: csum=%u/%u headroom=%u headlen=%u\n",
+				     start, off, skb_headroom(skb), skb_headlen(skb));
 		return false;
 	}
 	skb->ip_summed = CHECKSUM_PARTIAL;
-	skb->csum_start = skb_headroom(skb) + start;
+	skb->csum_start = csum_start;
 	skb->csum_offset = off;
 	skb_set_transport_header(skb, start);
 	return true;