From d206940319c41df4299db75ed56142177bb2e5f6 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 13 Feb 2014 23:09:11 +0100
Subject: net: core: introduce netif_skb_dev_features

Will be used by upcoming ipv4 forward path change that needs to
determine feature mask using skb->dst->dev instead of skb->dev.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 440a02ee6f92..21d4e6be8949 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3068,7 +3068,12 @@ 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 netif_skb_features(struct sk_buff *skb);
+netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
+					 const struct net_device *dev);
+static inline netdev_features_t netif_skb_features(struct sk_buff *skb)
+{
+	return netif_skb_dev_features(skb, skb->dev);
+}
 
 static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 {
-- 
cgit v1.2.3


From fe6cc55f3a9a053482a76f5a6b2257cee51b4663 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 13 Feb 2014 23:09:12 +0100
Subject: net: ip, ipv6: handle gso skbs in forwarding path

Marcelo Ricardo Leitner reported problems when the forwarding link path
has a lower mtu than the incoming one if the inbound interface supports GRO.

Given:
Host <mtu1500> R1 <mtu1200> R2

Host sends tcp stream which is routed via R1 and R2.  R1 performs GRO.

In this case, the kernel will fail to send ICMP fragmentation needed
messages (or pkt too big for ipv6), as GSO packets currently bypass dstmtu
checks in forward path. Instead, Linux tries to send out packets exceeding
the mtu.

When locking route MTU on Host (i.e., no ipv4 DF bit set), R1 does
not fragment the packets when forwarding, and again tries to send out
packets exceeding R1-R2 link mtu.

This alters the forwarding dstmtu checks to take the individual gso
segment lengths into account.

For ipv6, we send out pkt too big error for gso if the individual
segments are too big.

For ipv4, we either send icmp fragmentation needed, or, if the DF bit
is not set, perform software segmentation and let the output path
create fragments when the packet is leaving the machine.
It is not 100% correct as the error message will contain the headers of
the GRO skb instead of the original/segmented one, but it seems to
work fine in my (limited) tests.

Eric Dumazet suggested to simply shrink mss via ->gso_size to avoid
sofware segmentation.

However it turns out that skb_segment() assumes skb nr_frags is related
to mss size so we would BUG there.  I don't want to mess with it considering
Herbert and Eric disagree on what the correct behavior should be.

Hannes Frederic Sowa notes that when we would shrink gso_size
skb_segment would then also need to deal with the case where
SKB_MAX_FRAGS would be exceeded.

This uses sofware segmentation in the forward path when we hit ipv4
non-DF packets and the outgoing link mtu is too small.  Its not perfect,
but given the lack of bug reports wrt. GRO fwd being broken this is a
rare case anyway.  Also its not like this could not be improved later
once the dust settles.

Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Reported-by: Marcelo Ricardo Leitner <mleitner@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 17 ++++++++++++
 net/ipv4/ip_forward.c  | 71 ++++++++++++++++++++++++++++++++++++++++++++++++--
 net/ipv6/ip6_output.c  | 17 ++++++++++--
 3 files changed, 101 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f589c9af8cbf..3ebbbe7b6d05 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2916,5 +2916,22 @@ static inline bool skb_head_is_locked(const struct sk_buff *skb)
 {
 	return !skb->head_frag || skb_cloned(skb);
 }
+
+/**
+ * skb_gso_network_seglen - Return length of individual segments of a gso packet
+ *
+ * @skb: GSO skb
+ *
+ * skb_gso_network_seglen is used to determine the real size of the
+ * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP).
+ *
+ * The MAC/L2 header is not accounted for.
+ */
+static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb)
+{
+	unsigned int hdr_len = skb_transport_header(skb) -
+			       skb_network_header(skb);
+	return hdr_len + skb_gso_transport_seglen(skb);
+}
 #endif	/* __KERNEL__ */
 #endif	/* _LINUX_SKBUFF_H */
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index e9f1217a8afd..f3869c186d97 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -39,6 +39,71 @@
 #include <net/route.h>
 #include <net/xfrm.h>
 
+static bool ip_may_fragment(const struct sk_buff *skb)
+{
+	return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
+	       !skb->local_df;
+}
+
+static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+{
+	if (skb->len <= mtu || skb->local_df)
+		return false;
+
+	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+		return false;
+
+	return true;
+}
+
+static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb)
+{
+	unsigned int mtu;
+
+	if (skb->local_df || !skb_is_gso(skb))
+		return false;
+
+	mtu = ip_dst_mtu_maybe_forward(skb_dst(skb), true);
+
+	/* if seglen > mtu, do software segmentation for IP fragmentation on
+	 * output.  DF bit cannot be set since ip_forward would have sent
+	 * icmp error.
+	 */
+	return skb_gso_network_seglen(skb) > mtu;
+}
+
+/* called if GSO skb needs to be fragmented on forward */
+static int ip_forward_finish_gso(struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	netdev_features_t features;
+	struct sk_buff *segs;
+	int ret = 0;
+
+	features = netif_skb_dev_features(skb, dst->dev);
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+	if (IS_ERR(segs)) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	consume_skb(skb);
+
+	do {
+		struct sk_buff *nskb = segs->next;
+		int err;
+
+		segs->next = NULL;
+		err = dst_output(segs);
+
+		if (err && ret == 0)
+			ret = err;
+		segs = nskb;
+	} while (segs);
+
+	return ret;
+}
+
 static int ip_forward_finish(struct sk_buff *skb)
 {
 	struct ip_options *opt	= &(IPCB(skb)->opt);
@@ -49,6 +114,9 @@ static int ip_forward_finish(struct sk_buff *skb)
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
 
+	if (ip_gso_exceeds_dst_mtu(skb))
+		return ip_forward_finish_gso(skb);
+
 	return dst_output(skb);
 }
 
@@ -91,8 +159,7 @@ int ip_forward(struct sk_buff *skb)
 
 	IPCB(skb)->flags |= IPSKB_FORWARDED;
 	mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
-	if (unlikely(skb->len > mtu && !skb_is_gso(skb) &&
-		     (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
+	if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, mtu)) {
 		IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);
 		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 			  htonl(mtu));
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ef02b26ccf81..070a2fae2375 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -342,6 +342,20 @@ static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
 	return mtu;
 }
 
+static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
+{
+	if (skb->len <= mtu || skb->local_df)
+		return false;
+
+	if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)
+		return true;
+
+	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+		return false;
+
+	return true;
+}
+
 int ip6_forward(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
@@ -466,8 +480,7 @@ int ip6_forward(struct sk_buff *skb)
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 
-	if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) ||
-	    (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) {
+	if (ip6_pkt_too_big(skb, mtu)) {
 		/* Again, force OUTPUT device used as source address */
 		skb->dev = dst->dev;
 		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
-- 
cgit v1.2.3


From 99932d4fc03a13bb3e94938fe25458fabc8f2fc3 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Sun, 16 Feb 2014 15:55:20 +0100
Subject: netdevice: add queue selection fallback handler for ndo_select_queue

Add a new argument for ndo_select_queue() callback that passes a
fallback handler. This gets invoked through netdev_pick_tx();
fallback handler is currently __netdev_pick_tx() as most drivers
invoke this function within their customized implementation in
case for skbs that don't need any special handling. This fallback
handler can then be replaced on other call-sites with different
queue selection methods (e.g. in packet sockets, pktgen etc).

This also has the nice side-effect that __netdev_pick_tx() is
then only invoked from netdev_pick_tx() and export of that
function to modules can be undone.

Suggested-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c                 | 2 +-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 4 ++--
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c   | 6 +++---
 drivers/net/ethernet/lantiq_etop.c              | 2 +-
 drivers/net/ethernet/mellanox/mlx4/en_tx.c      | 4 ++--
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h    | 2 +-
 drivers/net/ethernet/tile/tilegx.c              | 2 +-
 drivers/net/team/team.c                         | 2 +-
 drivers/net/tun.c                               | 2 +-
 drivers/net/wireless/mwifiex/main.c             | 2 +-
 drivers/staging/bcm/Bcmnet.c                    | 2 +-
 drivers/staging/netlogic/xlr_net.c              | 2 +-
 drivers/staging/rtl8188eu/os_dep/os_intfs.c     | 2 +-
 include/linux/netdevice.h                       | 9 ++++++---
 net/core/flow_dissector.c                       | 7 +++----
 net/mac80211/iface.c                            | 6 ++++--
 17 files changed, 31 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 867664918715..1c6104d3501d 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3707,7 +3707,7 @@ static inline int bond_slave_override(struct bonding *bond,
 
 
 static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     void *accel_priv)
+			     void *accel_priv, select_queue_fallback_t fallback)
 {
 	/*
 	 * This helper function exists to help dev_pick_tx get the correct
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 9d7419e0390b..66c0df78c3ff 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1873,7 +1873,7 @@ void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw)
 }
 
 u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv)
+		       void *accel_priv, select_queue_fallback_t fallback)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 
@@ -1895,7 +1895,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	/* select a non-FCoE queue */
-	return __netdev_pick_tx(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp);
+	return fallback(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp);
 }
 
 void bnx2x_set_num_queues(struct bnx2x *bp)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index bfc58d488bb5..a89a40f88c25 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -496,7 +496,7 @@ int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos);
 
 /* select_queue callback */
 u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv);
+		       void *accel_priv, select_queue_fallback_t fallback);
 
 static inline void bnx2x_update_rx_prod(struct bnx2x *bp,
 					struct bnx2x_fastpath *fp,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 6d4ada72dfd0..18076c4178b4 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -6881,7 +6881,7 @@ static inline int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size)
 }
 
 static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
-			      void *accel_priv)
+			      void *accel_priv, select_queue_fallback_t fallback)
 {
 	struct ixgbe_fwd_adapter *fwd_adapter = accel_priv;
 #ifdef IXGBE_FCOE
@@ -6907,7 +6907,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 		if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)
 			break;
 	default:
-		return __netdev_pick_tx(dev, skb);
+		return fallback(dev, skb);
 	}
 
 	f = &adapter->ring_feature[RING_F_FCOE];
@@ -6920,7 +6920,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 
 	return txq + f->offset;
 #else
-	return __netdev_pick_tx(dev, skb);
+	return fallback(dev, skb);
 #endif
 }
 
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 8f9266c64c75..fd4b6aecf6ee 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -619,7 +619,7 @@ ltq_etop_set_multicast_list(struct net_device *dev)
 
 static u16
 ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb,
-		      void *accel_priv)
+		      void *accel_priv, select_queue_fallback_t fallback)
 {
 	/* we are currently only using the first queue */
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 8e8a7eb43a2c..13457032d15f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -629,7 +629,7 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, struct sk_buff *sk
 }
 
 u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
-			 void *accel_priv)
+			 void *accel_priv, select_queue_fallback_t fallback)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	u16 rings_p_up = priv->num_tx_rings_p_up;
@@ -641,7 +641,7 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
 	if (vlan_tx_tag_present(skb))
 		up = vlan_tx_tag_get(skb) >> VLAN_PRIO_SHIFT;
 
-	return __netdev_pick_tx(dev, skb) % rings_p_up + up * rings_p_up;
+	return fallback(dev, skb) % rings_p_up + up * rings_p_up;
 }
 
 static void mlx4_bf_copy(void __iomem *dst, unsigned long *src, unsigned bytecnt)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 3af04c3f42ea..9ca223bc90fc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -723,7 +723,7 @@ int mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
 
 void mlx4_en_tx_irq(struct mlx4_cq *mcq);
 u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
-			 void *accel_priv);
+			 void *accel_priv, select_queue_fallback_t fallback);
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
index 023237a65720..17503da9f7a5 100644
--- a/drivers/net/ethernet/tile/tilegx.c
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -2071,7 +2071,7 @@ static int tile_net_tx(struct sk_buff *skb, struct net_device *dev)
 
 /* Return subqueue id on this core (one per core). */
 static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb,
-				 void *accel_priv)
+				 void *accel_priv, select_queue_fallback_t fallback)
 {
 	return smp_processor_id();
 }
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 28407426fd6f..c8624a8235ab 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1648,7 +1648,7 @@ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev)
 }
 
 static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     void *accel_priv)
+			     void *accel_priv, select_queue_fallback_t fallback)
 {
 	/*
 	 * This helper function exists to help dev_pick_tx get the correct
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 44c4db8450f0..8fe9cb7d0f72 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -366,7 +366,7 @@ static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash)
  * hope the rxq no. may help here.
  */
 static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    void *accel_priv)
+			    void *accel_priv, select_queue_fallback_t fallback)
 {
 	struct tun_struct *tun = netdev_priv(dev);
 	struct tun_flow_entry *e;
diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c
index 4d79761b9c87..9d3d2758ec35 100644
--- a/drivers/net/wireless/mwifiex/main.c
+++ b/drivers/net/wireless/mwifiex/main.c
@@ -748,7 +748,7 @@ static struct net_device_stats *mwifiex_get_stats(struct net_device *dev)
 
 static u16
 mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb,
-				void *accel_priv)
+				void *accel_priv, select_queue_fallback_t fallback)
 {
 	skb->priority = cfg80211_classify8021d(skb, NULL);
 	return mwifiex_1d_to_wmm_queue[skb->priority];
diff --git a/drivers/staging/bcm/Bcmnet.c b/drivers/staging/bcm/Bcmnet.c
index 8dfdd2732bdc..95a2358267ba 100644
--- a/drivers/staging/bcm/Bcmnet.c
+++ b/drivers/staging/bcm/Bcmnet.c
@@ -40,7 +40,7 @@ static INT bcm_close(struct net_device *dev)
 }
 
 static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    void *accel_priv)
+			    void *accel_priv, select_queue_fallback_t fallback)
 {
 	return ClassifyPacket(netdev_priv(dev), skb);
 }
diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c
index eedffed17e39..6f9ac27730af 100644
--- a/drivers/staging/netlogic/xlr_net.c
+++ b/drivers/staging/netlogic/xlr_net.c
@@ -307,7 +307,7 @@ static netdev_tx_t xlr_net_start_xmit(struct sk_buff *skb,
 }
 
 static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb,
-				void *accel_priv)
+				void *accel_priv, select_queue_fallback_t fallback)
 {
 	return (u16)smp_processor_id();
 }
diff --git a/drivers/staging/rtl8188eu/os_dep/os_intfs.c b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
index 68f98fa114d2..7c9ee58f47bb 100644
--- a/drivers/staging/rtl8188eu/os_dep/os_intfs.c
+++ b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
@@ -653,7 +653,7 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb)
 }
 
 static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    void *accel_priv)
+			    void *accel_priv, select_queue_fallback_t fallback)
 {
 	struct adapter	*padapter = rtw_netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 21d4e6be8949..1de9c136b066 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -752,6 +752,9 @@ struct netdev_phys_port_id {
 	unsigned char id_len;
 };
 
+typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
+				       struct sk_buff *skb);
+
 /*
  * This structure defines the management hooks for network devices.
  * The following hooks can be defined; unless noted otherwise, they are
@@ -783,7 +786,7 @@ struct netdev_phys_port_id {
  *	Required can not be NULL.
  *
  * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
- *                         void *accel_priv);
+ *                         void *accel_priv, select_queue_fallback_t fallback);
  *	Called to decide which queue to when device supports multiple
  *	transmit queues.
  *
@@ -1005,7 +1008,8 @@ struct net_device_ops {
 						   struct net_device *dev);
 	u16			(*ndo_select_queue)(struct net_device *dev,
 						    struct sk_buff *skb,
-						    void *accel_priv);
+						    void *accel_priv,
+						    select_queue_fallback_t fallback);
 	void			(*ndo_change_rx_flags)(struct net_device *dev,
 						       int flags);
 	void			(*ndo_set_rx_mode)(struct net_device *dev);
@@ -1551,7 +1555,6 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 				    struct sk_buff *skb,
 				    void *accel_priv);
-u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb);
 
 /*
  * Net namespace inlines
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 87577d447554..75fe83f590ea 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -372,7 +372,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 #endif
 }
 
-u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
+static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
 {
 	struct sock *sk = skb->sk;
 	int queue_index = sk_tx_queue_get(sk);
@@ -392,7 +392,6 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
 
 	return queue_index;
 }
-EXPORT_SYMBOL(__netdev_pick_tx);
 
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 				    struct sk_buff *skb,
@@ -403,8 +402,8 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 	if (dev->real_num_tx_queues != 1) {
 		const struct net_device_ops *ops = dev->netdev_ops;
 		if (ops->ndo_select_queue)
-			queue_index = ops->ndo_select_queue(dev, skb,
-							    accel_priv);
+			queue_index = ops->ndo_select_queue(dev, skb, accel_priv,
+							    __netdev_pick_tx);
 		else
 			queue_index = __netdev_pick_tx(dev, skb);
 
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index d6d1f1df9119..ce1c44370610 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1057,7 +1057,8 @@ static void ieee80211_uninit(struct net_device *dev)
 
 static u16 ieee80211_netdev_select_queue(struct net_device *dev,
 					 struct sk_buff *skb,
-					 void *accel_priv)
+					 void *accel_priv,
+					 select_queue_fallback_t fallback)
 {
 	return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb);
 }
@@ -1075,7 +1076,8 @@ static const struct net_device_ops ieee80211_dataif_ops = {
 
 static u16 ieee80211_monitor_select_queue(struct net_device *dev,
 					  struct sk_buff *skb,
-					  void *accel_priv)
+					  void *accel_priv,
+					  select_queue_fallback_t fallback)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = sdata->local;
-- 
cgit v1.2.3


From b9507bdaf40e91fea2b1c0c1ee7dc627c8ee6fd6 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Sun, 16 Feb 2014 15:55:21 +0100
Subject: netdevice: move netdev_cap_txqueue for shared usage to header

In order to allow users to invoke netdev_cap_txqueue, it needs to
be moved into netdevice.h header file. While at it, also add kernel
doc header to document the API.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 20 ++++++++++++++++++++
 net/core/flow_dissector.c | 13 +------------
 2 files changed, 21 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1de9c136b066..e8eeebd49a98 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2278,6 +2278,26 @@ static inline void netdev_reset_queue(struct net_device *dev_queue)
 	netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0));
 }
 
+/**
+ * 	netdev_cap_txqueue - check if selected tx queue exceeds device queues
+ * 	@dev: network device
+ * 	@queue_index: given tx queue index
+ *
+ * 	Returns 0 if given tx queue index >= number of device tx queues,
+ * 	otherwise returns the originally passed tx queue index.
+ */
+static inline u16 netdev_cap_txqueue(struct net_device *dev, u16 queue_index)
+{
+	if (unlikely(queue_index >= dev->real_num_tx_queues)) {
+		net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n",
+				     dev->name, queue_index,
+				     dev->real_num_tx_queues);
+		return 0;
+	}
+
+	return queue_index;
+}
+
 /**
  *	netif_running - test if up
  *	@dev: network device
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 75fe83f590ea..e29e810663d7 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -323,17 +323,6 @@ u32 __skb_get_poff(const struct sk_buff *skb)
 	return poff;
 }
 
-static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index)
-{
-	if (unlikely(queue_index >= dev->real_num_tx_queues)) {
-		net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n",
-				     dev->name, queue_index,
-				     dev->real_num_tx_queues);
-		return 0;
-	}
-	return queue_index;
-}
-
 static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 {
 #ifdef CONFIG_XPS
@@ -408,7 +397,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 			queue_index = __netdev_pick_tx(dev, skb);
 
 		if (!accel_priv)
-			queue_index = dev_cap_txqueue(dev, queue_index);
+			queue_index = netdev_cap_txqueue(dev, queue_index);
 	}
 
 	skb_set_queue_mapping(skb, queue_index);
-- 
cgit v1.2.3