Merge branch 'stacked_vlan_tso'

Toshiaki Makita says:

====================
Stacked vlan TSO

On the basis of Netdev 0.1 discussion[1], I made a patch set to enable
TSO for packets with multiple vlans.

Currently, packets with multiple vlans are always segmented by software,
which is caused by that netif_skb_features() drops most feature flags
for multiple tagged packets.

To allow NICs to segment them, we need to get rid of that check from core.
Fortunately, recently introduced ndo_features_check() can be used to
move the check to each driver, and this patch set is based on the idea.

For the initial patch set, I chose 3 drivers, bonding, team, and igb, as
candidates to enable TSO. I tested them and confirmed they works fine
with this change.

Here are samples of performance test results. As I expected, %sys gets
pretty lower than before.

* TEST1: vlan (.1Q) on vlan (.1ad) on igb (I350)

- before

$ netperf -t TCP_STREAM -H 192.168.10.1 -l 60
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    60.02     933.72

Average:        CPU     %user     %nice   %system   %iowait    %steal     %idle
Average:        all      0.13      0.00     11.28      0.01      0.00     88.58

- after

$ netperf -t TCP_STREAM -H 192.168.10.1 -l 60
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    60.01     936.13

Average:        CPU     %user     %nice   %system   %iowait    %steal     %idle
Average:        all      0.24      0.00      4.17      0.01      0.00     95.58

* TEST2: vlan (.1Q) on bridge (.1ad vlan filtering) on team on igb (I350)

- before

$ netperf -t TCP_STREAM -H 192.168.10.1 -l 60
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    60.01     936.28

Average:        CPU     %user     %nice   %system   %iowait    %steal     %idle
Average:        all      0.41      0.00     11.57      0.01      0.00     88.01

- after

$ netperf -t TCP_STREAM -H 192.168.10.1 -l 60
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    60.02     935.72

Average:        CPU     %user     %nice   %system   %iowait    %steal     %idle
Average:        all      0.14      0.00      7.66      0.01      0.00     92.19

In addition to above, I tested these configurations:
- vlan (.1Q) on vlan (1.ad) on bonding on igb (I350)
- vlan (.1Q) on vlan (1.Q) on igb (I350)
- vlan (.1Q) on vlan (1.Q) on team on igb (I350)
And didn't find any problem.

[1] https://netdev01.org/sessions/18
    https://netdev01.org/docs/netdev01_bof_8021ad_makita_150212.pdf
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

10 files changed, 96 insertions, 22 deletions

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index c026ce9cd7b6..7b4684ccdb3f 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4038,6 +4038,7 @@ static const struct net_device_ops bond_netdev_ops = {
 	.ndo_fix_features	= bond_fix_features,
 	.ndo_bridge_setlink	= ndo_dflt_netdev_switch_port_bridge_setlink,
 	.ndo_bridge_dellink	= ndo_dflt_netdev_switch_port_bridge_dellink,
+	.ndo_features_check	= passthru_features_check,
 };
 
 static const struct device_type bond_type = {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 9677431c582a..039b0c1f480e 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -12557,6 +12557,7 @@ static netdev_features_t bnx2x_features_check(struct sk_buff *skb,
 					      struct net_device *dev,
 					      netdev_features_t features)
 {
+	features = vlan_features_check(skb, features);
 	return vxlan_features_check(skb, features);
 }
 
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 0e07545ccc97..8457d0306e3a 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2093,6 +2093,7 @@ static const struct net_device_ops igb_netdev_ops = {
 #endif
 	.ndo_fix_features	= igb_fix_features,
 	.ndo_set_features	= igb_set_features,
+	.ndo_features_check	= passthru_features_check,
 };
 
 /**
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index a8339e98ad24..ebc93a101c93 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2373,6 +2373,7 @@ static netdev_features_t mlx4_en_features_check(struct sk_buff *skb,
 						struct net_device *dev,
 						netdev_features_t features)
 {
+	features = vlan_features_check(skb, features);
 	return vxlan_features_check(skb, features);
 }
 #endif
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index a430a34a4434..367f3976df56 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -507,6 +507,7 @@ static netdev_features_t qlcnic_features_check(struct sk_buff *skb,
 					       struct net_device *dev,
 					       netdev_features_t features)
 {
+	features = vlan_features_check(skb, features);
 	return vxlan_features_check(skb, features);
 }
 #endif
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index a23319fc78ca..6928448f6b7f 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1979,6 +1979,7 @@ static const struct net_device_ops team_netdev_ops = {
 	.ndo_change_carrier     = team_change_carrier,
 	.ndo_bridge_setlink     = ndo_dflt_netdev_switch_port_bridge_setlink,
 	.ndo_bridge_dellink     = ndo_dflt_netdev_switch_port_bridge_dellink,
+	.ndo_features_check	= passthru_features_check,
 };
 
 /***********************
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index b11b28a30b9e..920e4457ce6e 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -561,4 +561,71 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb,
 		skb->protocol = htons(ETH_P_802_2);
 }
 
+/**
+ * skb_vlan_tagged - check if skb is vlan tagged.
+ * @skb: skbuff to query
+ *
+ * Returns true if the skb is tagged, regardless of whether it is hardware
+ * accelerated or not.
+ */
+static inline bool skb_vlan_tagged(const struct sk_buff *skb)
+{
+	if (!skb_vlan_tag_present(skb) &&
+	    likely(skb->protocol != htons(ETH_P_8021Q) &&
+		   skb->protocol != htons(ETH_P_8021AD)))
+		return false;
+
+	return true;
+}
+
+/**
+ * skb_vlan_tagged_multi - check if skb is vlan tagged with multiple headers.
+ * @skb: skbuff to query
+ *
+ * Returns true if the skb is tagged with multiple vlan headers, regardless
+ * of whether it is hardware accelerated or not.
+ */
+static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
+{
+	__be16 protocol = skb->protocol;
+
+	if (!skb_vlan_tag_present(skb)) {
+		struct vlan_ethhdr *veh;
+
+		if (likely(protocol != htons(ETH_P_8021Q) &&
+			   protocol != htons(ETH_P_8021AD)))
+			return false;
+
+		veh = (struct vlan_ethhdr *)skb->data;
+		protocol = veh->h_vlan_encapsulated_proto;
+	}
+
+	if (protocol != htons(ETH_P_8021Q) && protocol != htons(ETH_P_8021AD))
+		return false;
+
+	return true;
+}
+
+/**
+ * vlan_features_check - drop unsafe features for skb with multiple tags.
+ * @skb: skbuff to query
+ * @features: features to be checked
+ *
+ * Returns features without unsafe ones if the skb has multiple tags.
+ */
+static inline netdev_features_t vlan_features_check(const struct sk_buff *skb,
+						    netdev_features_t features)
+{
+	if (skb_vlan_tagged_multi(skb))
+		features = netdev_intersect_features(features,
+						     NETIF_F_SG |
+						     NETIF_F_HIGHDMA |
+						     NETIF_F_FRAGLIST |
+						     NETIF_F_GEN_CSUM |
+						     NETIF_F_HW_VLAN_CTAG_TX |
+						     NETIF_F_HW_VLAN_STAG_TX);
+
+	return features;
+}
+
 #endif /* !(_LINUX_IF_VLAN_H_) */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 08c4ab37189f..967bb4c8caf1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3657,6 +3657,9 @@ void netdev_change_features(struct net_device *dev);
 void netif_stacked_transfer_operstate(const struct net_device *rootdev,
 					struct net_device *dev);
 
+netdev_features_t passthru_features_check(struct sk_buff *skb,
+					  struct net_device *dev,
+					  netdev_features_t features);
 netdev_features_t netif_skb_features(struct sk_buff *skb);
 
 static inline bool net_gso_ok(netdev_features_t features, int gso_type)
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index f196552ec3c4..8b5ab9033b41 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -554,6 +554,7 @@ static int vlan_dev_init(struct net_device *dev)
 	if (dev->features & NETIF_F_VLAN_FEATURES)
 		netdev_warn(real_dev, "VLAN features are set incorrectly.  Q-in-Q configurations may not work correctly.\n");
 
+	dev->vlan_features = real_dev->vlan_features & ~NETIF_F_ALL_FCOE;
 
 	/* ipv6 shared card related stuff */
 	dev->dev_id = real_dev->dev_id;
diff --git a/net/core/dev.c b/net/core/dev.c
index a0408d497dae..3a06003ecafd 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2562,12 +2562,26 @@ static netdev_features_t harmonize_features(struct sk_buff *skb,
 	return features;
 }
 
+netdev_features_t passthru_features_check(struct sk_buff *skb,
+					  struct net_device *dev,
+					  netdev_features_t features)
+{
+	return features;
+}
+EXPORT_SYMBOL(passthru_features_check);
+
+static netdev_features_t dflt_features_check(const struct sk_buff *skb,
+					     struct net_device *dev,
+					     netdev_features_t features)
+{
+	return vlan_features_check(skb, features);
+}
+
 netdev_features_t netif_skb_features(struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
 	netdev_features_t features = dev->features;
 	u16 gso_segs = skb_shinfo(skb)->gso_segs;
-	__be16 protocol = skb->protocol;
 
 	if (gso_segs > dev->gso_max_segs || gso_segs < dev->gso_min_segs)
 		features &= ~NETIF_F_GSO_MASK;
@@ -2579,34 +2593,17 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
 	if (skb->encapsulation)
 		features &= dev->hw_enc_features;
 
-	if (!skb_vlan_tag_present(skb)) {
-		if (unlikely(protocol == htons(ETH_P_8021Q) ||
-			     protocol == htons(ETH_P_8021AD))) {
-			struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
-			protocol = veh->h_vlan_encapsulated_proto;
-		} else {
-			goto finalize;
-		}
-	}
-
-	features = netdev_intersect_features(features,
-					     dev->vlan_features |
-					     NETIF_F_HW_VLAN_CTAG_TX |
-					     NETIF_F_HW_VLAN_STAG_TX);
-
-	if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD))
+	if (skb_vlan_tagged(skb))
 		features = netdev_intersect_features(features,
-						     NETIF_F_SG |
-						     NETIF_F_HIGHDMA |
-						     NETIF_F_FRAGLIST |
-						     NETIF_F_GEN_CSUM |
+						     dev->vlan_features |
 						     NETIF_F_HW_VLAN_CTAG_TX |
 						     NETIF_F_HW_VLAN_STAG_TX);
 
-finalize:
 	if (dev->netdev_ops->ndo_features_check)
 		features &= dev->netdev_ops->ndo_features_check(skb, dev,
 								features);
+	else
+		features &= dflt_features_check(skb, dev, features);
 
 	return harmonize_features(skb, features);
 }