From a9c9a81f5892eb984234223399ee624f7dbd15e8 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Sun, 24 Jan 2016 21:16:13 -0800
Subject: i40e/i40evf: Drop outer checksum offload that was not requested

The i40e and i40evf drivers contained code for inserting an outer checksum
on UDP tunnels.  The issue however is that the upper levels of the stack
never requested such an offload and it results in possible errors.

In addition the same logic was being applied to the Rx side where it was
attempting to validate the outer checksum, but the logic there was
incorrect in that it was testing for the resultant sum to be equal to the
header checksum instead of being equal to 0.

Since this code is so massively flawed, and doing things that we didn't ask
for it to do I am just dropping it, and will bring it back later to use as
an offload for SKB_GSO_UDP_TUNNEL_CSUM which can make use of such a
feature.

As far as the Rx feature I am dropping it completely since it would need to
be massively expanded and applied to IPv4 and IPv6 checksums for all parts,
not just the one that supports Tx checksum offload for the outer.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c   |  2 --
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 47 +++------------------------
 drivers/net/ethernet/intel/i40e/i40e_txrx.h   |  1 -
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 46 +++-----------------------
 drivers/net/ethernet/intel/i40evf/i40e_txrx.h |  1 -
 5 files changed, 10 insertions(+), 87 deletions(-)

(limited to 'drivers')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 16e5e0b81bd0..0fa52ed1a896 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -7474,8 +7474,6 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi)
 		tx_ring->dcb_tc = 0;
 		if (vsi->back->flags & I40E_FLAG_WB_ON_ITR_CAPABLE)
 			tx_ring->flags = I40E_TXR_FLAGS_WB_ON_ITR;
-		if (vsi->back->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE)
-			tx_ring->flags |= I40E_TXR_FLAGS_OUTER_UDP_CSUM;
 		vsi->tx_rings[i] = tx_ring;
 
 		rx_ring = &tx_ring[1];
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 65f2fd80aa79..d4364ec33022 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1391,9 +1391,6 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(rx_ptype);
 	bool ipv4 = false, ipv6 = false;
 	bool ipv4_tunnel, ipv6_tunnel;
-	__wsum rx_udp_csum;
-	struct iphdr *iph;
-	__sum16 csum;
 
 	ipv4_tunnel = (rx_ptype >= I40E_RX_PTYPE_GRENAT4_MAC_PAY3) &&
 		     (rx_ptype <= I40E_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4);
@@ -1443,37 +1440,12 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT))
 		return;
 
-	/* If VXLAN/GENEVE traffic has an outer UDPv4 checksum we need to check
-	 * it in the driver, hardware does not do it for us.
-	 * Since L3L4P bit was set we assume a valid IHL value (>=5)
-	 * so the total length of IPv4 header is IHL*4 bytes
-	 * The UDP_0 bit *may* bet set if the *inner* header is UDP
+	/* The hardware supported by this driver does not validate outer
+	 * checksums for tunneled VXLAN or GENEVE frames.  I don't agree
+	 * with it but the specification states that you "MAY validate", it
+	 * doesn't make it a hard requirement so if we have validated the
+	 * inner checksum report CHECKSUM_UNNECESSARY.
 	 */
-	if (!(vsi->back->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE) &&
-	    (ipv4_tunnel)) {
-		skb->transport_header = skb->mac_header +
-					sizeof(struct ethhdr) +
-					(ip_hdr(skb)->ihl * 4);
-
-		/* Add 4 bytes for VLAN tagged packets */
-		skb->transport_header += (skb->protocol == htons(ETH_P_8021Q) ||
-					  skb->protocol == htons(ETH_P_8021AD))
-					  ? VLAN_HLEN : 0;
-
-		if ((ip_hdr(skb)->protocol == IPPROTO_UDP) &&
-		    (udp_hdr(skb)->check != 0)) {
-			rx_udp_csum = udp_csum(skb);
-			iph = ip_hdr(skb);
-			csum = csum_tcpudp_magic(
-					iph->saddr, iph->daddr,
-					(skb->len - skb_transport_offset(skb)),
-					IPPROTO_UDP, rx_udp_csum);
-
-			if (udp_hdr(skb)->check != csum)
-				goto checksum_fail;
-
-		} /* else its GRE and so no outer UDP header */
-	}
 
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
 	skb->csum_level = ipv4_tunnel || ipv6_tunnel;
@@ -2453,15 +2425,6 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 			*tx_flags &= ~I40E_TX_FLAGS_IPV4;
 			*tx_flags |= I40E_TX_FLAGS_IPV6;
 		}
-		if ((tx_ring->flags & I40E_TXR_FLAGS_OUTER_UDP_CSUM) &&
-		    (l4_tunnel == I40E_TXD_CTX_UDP_TUNNELING)        &&
-		    (*cd_tunneling & I40E_TXD_CTX_QW0_EXT_IP_MASK)) {
-			oudph->check = ~csum_tcpudp_magic(oiph->saddr,
-					oiph->daddr,
-					(skb->len - skb_transport_offset(skb)),
-					IPPROTO_UDP, 0);
-			*cd_tunneling |= I40E_TXD_CTX_QW0_L4T_CS_MASK;
-		}
 	} else {
 		network_hdr_len = skb_network_header_len(skb);
 		this_ip_hdr = ip_hdr(skb);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 3acc9244134d..fb065d4fe15c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -277,7 +277,6 @@ struct i40e_ring {
 
 	u16 flags;
 #define I40E_TXR_FLAGS_WB_ON_ITR	BIT(0)
-#define I40E_TXR_FLAGS_OUTER_UDP_CSUM	BIT(1)
 #define I40E_TXR_FLAGS_LAST_XMIT_MORE_SET BIT(2)
 
 	/* stats structs */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index fb6cd7e5d3be..8b20ed3f20d1 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -863,9 +863,6 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(rx_ptype);
 	bool ipv4 = false, ipv6 = false;
 	bool ipv4_tunnel, ipv6_tunnel;
-	__wsum rx_udp_csum;
-	struct iphdr *iph;
-	__sum16 csum;
 
 	ipv4_tunnel = (rx_ptype >= I40E_RX_PTYPE_GRENAT4_MAC_PAY3) &&
 		     (rx_ptype <= I40E_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4);
@@ -915,36 +912,12 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT))
 		return;
 
-	/* If VXLAN traffic has an outer UDPv4 checksum we need to check
-	 * it in the driver, hardware does not do it for us.
-	 * Since L3L4P bit was set we assume a valid IHL value (>=5)
-	 * so the total length of IPv4 header is IHL*4 bytes
-	 * The UDP_0 bit *may* bet set if the *inner* header is UDP
+	/* The hardware supported by this driver does not validate outer
+	 * checksums for tunneled VXLAN or GENEVE frames.  I don't agree
+	 * with it but the specification states that you "MAY validate", it
+	 * doesn't make it a hard requirement so if we have validated the
+	 * inner checksum report CHECKSUM_UNNECESSARY.
 	 */
-	if (ipv4_tunnel) {
-		skb->transport_header = skb->mac_header +
-					sizeof(struct ethhdr) +
-					(ip_hdr(skb)->ihl * 4);
-
-		/* Add 4 bytes for VLAN tagged packets */
-		skb->transport_header += (skb->protocol == htons(ETH_P_8021Q) ||
-					  skb->protocol == htons(ETH_P_8021AD))
-					  ? VLAN_HLEN : 0;
-
-		if ((ip_hdr(skb)->protocol == IPPROTO_UDP) &&
-		    (udp_hdr(skb)->check != 0)) {
-			rx_udp_csum = udp_csum(skb);
-			iph = ip_hdr(skb);
-			csum = csum_tcpudp_magic(iph->saddr, iph->daddr,
-						 (skb->len -
-						  skb_transport_offset(skb)),
-						 IPPROTO_UDP, rx_udp_csum);
-
-			if (udp_hdr(skb)->check != csum)
-				goto checksum_fail;
-
-		} /* else its GRE and so no outer UDP header */
-	}
 
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
 	skb->csum_level = ipv4_tunnel || ipv6_tunnel;
@@ -1667,15 +1640,6 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 			*tx_flags |= I40E_TX_FLAGS_IPV6;
 		}
 
-		if ((tx_ring->flags & I40E_TXR_FLAGS_OUTER_UDP_CSUM) &&
-		    (l4_tunnel == I40E_TXD_CTX_UDP_TUNNELING)        &&
-		    (*cd_tunneling & I40E_TXD_CTX_QW0_EXT_IP_MASK)) {
-			oudph->check = ~csum_tcpudp_magic(oiph->saddr,
-					oiph->daddr,
-					(skb->len - skb_transport_offset(skb)),
-					IPPROTO_UDP, 0);
-			*cd_tunneling |= I40E_TXD_CTX_QW0_L4T_CS_MASK;
-		}
 	} else {
 		network_hdr_len = skb_network_header_len(skb);
 		this_ip_hdr = ip_hdr(skb);
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index 81c96619287b..043b9556834f 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -275,7 +275,6 @@ struct i40e_ring {
 
 	u16 flags;
 #define I40E_TXR_FLAGS_WB_ON_ITR	BIT(0)
-#define I40E_TXR_FLAGS_OUTER_UDP_CSUM	BIT(1)
 
 	/* stats structs */
 	struct i40e_queue_stats	stats;
-- 
cgit v1.2.3


From 03f9d6a59f94f70ae775ca2aae04f2accc01a973 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Sun, 24 Jan 2016 21:16:20 -0800
Subject: i40e/i40evf: Use u64 values instead of casting them in TSO function

Instead of casing u32 values to u64 it makes more sense to just start out
with u64 values in the first place.  This way we don't need to create a
mess with all of the casts needed to populate a 64b value.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 9 ++++-----
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 9 ++++-----
 2 files changed, 8 insertions(+), 10 deletions(-)

(limited to 'drivers')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index d4364ec33022..5e825893f203 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2267,7 +2267,7 @@ out:
 static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 		    u8 *hdr_len, u64 *cd_type_cmd_tso_mss)
 {
-	u32 cd_cmd, cd_tso_len, cd_mss;
+	u64 cd_cmd, cd_tso_len, cd_mss;
 	struct ipv6hdr *ipv6h;
 	struct tcphdr *tcph;
 	struct iphdr *iph;
@@ -2309,10 +2309,9 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	cd_cmd = I40E_TX_CTX_DESC_TSO;
 	cd_tso_len = skb->len - *hdr_len;
 	cd_mss = skb_shinfo(skb)->gso_size;
-	*cd_type_cmd_tso_mss |= ((u64)cd_cmd << I40E_TXD_CTX_QW1_CMD_SHIFT) |
-				((u64)cd_tso_len <<
-				 I40E_TXD_CTX_QW1_TSO_LEN_SHIFT) |
-				((u64)cd_mss << I40E_TXD_CTX_QW1_MSS_SHIFT);
+	*cd_type_cmd_tso_mss |= (cd_cmd << I40E_TXD_CTX_QW1_CMD_SHIFT) |
+				(cd_tso_len << I40E_TXD_CTX_QW1_TSO_LEN_SHIFT) |
+				(cd_mss << I40E_TXD_CTX_QW1_MSS_SHIFT);
 	return 1;
 }
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 8b20ed3f20d1..c5f98cba648a 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1527,7 +1527,7 @@ out:
 static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 		    u8 *hdr_len, u64 *cd_type_cmd_tso_mss)
 {
-	u32 cd_cmd, cd_tso_len, cd_mss;
+	u64 cd_cmd, cd_tso_len, cd_mss;
 	struct ipv6hdr *ipv6h;
 	struct tcphdr *tcph;
 	struct iphdr *iph;
@@ -1569,10 +1569,9 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	cd_cmd = I40E_TX_CTX_DESC_TSO;
 	cd_tso_len = skb->len - *hdr_len;
 	cd_mss = skb_shinfo(skb)->gso_size;
-	*cd_type_cmd_tso_mss |= ((u64)cd_cmd << I40E_TXD_CTX_QW1_CMD_SHIFT) |
-				((u64)cd_tso_len <<
-				 I40E_TXD_CTX_QW1_TSO_LEN_SHIFT) |
-				((u64)cd_mss << I40E_TXD_CTX_QW1_MSS_SHIFT);
+	*cd_type_cmd_tso_mss |= (cd_cmd << I40E_TXD_CTX_QW1_CMD_SHIFT) |
+				(cd_tso_len << I40E_TXD_CTX_QW1_TSO_LEN_SHIFT) |
+				(cd_mss << I40E_TXD_CTX_QW1_MSS_SHIFT);
 	return 1;
 }
 
-- 
cgit v1.2.3


From c49a7bc3308099a8d5f9e2e38adfc5ab969804aa Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Sun, 24 Jan 2016 21:16:28 -0800
Subject: i40e/i40evf: Factor out L4 header and checksum from L3 bits in TSO
 path

This patch makes it so that the L4 header offsets and such can be ignored
when dealing with the L3 checksum and length update.  This is done making
use of two things.

First we can just use the offset from the L4 header to the start of the
packet to determine the L4 offset, and from that we can then make use of
the data offset to determine the full length of the headers.

As far as adjusting the checksum to remove the length we can simply add the
inverse of the length instead of having to recompute the entire
pseudo-header without the length.  In the case of an IPv6 header this
should be significantly cheaper since we can make use of a value we already
needed instead of having to read the source and destination address out of
the packet.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 31 ++++++++++++++++-----------
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 31 ++++++++++++++++-----------
 2 files changed, 36 insertions(+), 26 deletions(-)

(limited to 'drivers')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 5e825893f203..ce0234e67cc5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2269,9 +2269,12 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 {
 	u64 cd_cmd, cd_tso_len, cd_mss;
 	struct ipv6hdr *ipv6h;
-	struct tcphdr *tcph;
 	struct iphdr *iph;
-	u32 l4len;
+	union {
+		struct tcphdr *tcp;
+		unsigned char *hdr;
+	} l4;
+	u32 paylen, l4_offset;
 	int err;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
@@ -2286,24 +2289,26 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 	iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb);
 	ipv6h = skb->encapsulation ? inner_ipv6_hdr(skb) : ipv6_hdr(skb);
+	l4.hdr = skb->encapsulation ? skb_inner_transport_header(skb) :
+				      skb_transport_header(skb);
 
 	if (iph->version == 4) {
-		tcph = skb->encapsulation ? inner_tcp_hdr(skb) : tcp_hdr(skb);
 		iph->tot_len = 0;
 		iph->check = 0;
-		tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
-						 0, IPPROTO_TCP, 0);
-	} else if (ipv6h->version == 6) {
-		tcph = skb->encapsulation ? inner_tcp_hdr(skb) : tcp_hdr(skb);
+	} else {
 		ipv6h->payload_len = 0;
-		tcph->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
-					       0, IPPROTO_TCP, 0);
 	}
 
-	l4len = skb->encapsulation ? inner_tcp_hdrlen(skb) : tcp_hdrlen(skb);
-	*hdr_len = (skb->encapsulation
-		    ? (skb_inner_transport_header(skb) - skb->data)
-		    : skb_transport_offset(skb)) + l4len;
+	/* determine offset of inner transport header */
+	l4_offset = l4.hdr - skb->data;
+
+	/* remove payload length from inner checksum */
+	paylen = (__force u16)l4.tcp->check;
+	paylen += ntohs(1) * (u16)~(skb->len - l4_offset);
+	l4.tcp->check = ~csum_fold((__force __wsum)paylen);
+
+	/* compute length of segmentation header */
+	*hdr_len = (l4.tcp->doff * 4) + l4_offset;
 
 	/* find the field values */
 	cd_cmd = I40E_TX_CTX_DESC_TSO;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index c5f98cba648a..881d0ada99fc 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1529,9 +1529,12 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 {
 	u64 cd_cmd, cd_tso_len, cd_mss;
 	struct ipv6hdr *ipv6h;
-	struct tcphdr *tcph;
 	struct iphdr *iph;
-	u32 l4len;
+	union {
+		struct tcphdr *tcp;
+		unsigned char *hdr;
+	} l4;
+	u32 paylen, l4_offset;
 	int err;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
@@ -1546,24 +1549,26 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 	iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb);
 	ipv6h = skb->encapsulation ? inner_ipv6_hdr(skb) : ipv6_hdr(skb);
+	l4.hdr = skb->encapsulation ? skb_inner_transport_header(skb) :
+				      skb_transport_header(skb);
 
 	if (iph->version == 4) {
-		tcph = skb->encapsulation ? inner_tcp_hdr(skb) : tcp_hdr(skb);
 		iph->tot_len = 0;
 		iph->check = 0;
-		tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
-						 0, IPPROTO_TCP, 0);
-	} else if (ipv6h->version == 6) {
-		tcph = skb->encapsulation ? inner_tcp_hdr(skb) : tcp_hdr(skb);
+	} else {
 		ipv6h->payload_len = 0;
-		tcph->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
-					       0, IPPROTO_TCP, 0);
 	}
 
-	l4len = skb->encapsulation ? inner_tcp_hdrlen(skb) : tcp_hdrlen(skb);
-	*hdr_len = (skb->encapsulation
-		    ? (skb_inner_transport_header(skb) - skb->data)
-		    : skb_transport_offset(skb)) + l4len;
+	/* determine offset of inner transport header */
+	l4_offset = l4.hdr - skb->data;
+
+	/* remove payload length from inner checksum */
+	paylen = (__force u16)l4.tcp->check;
+	paylen += ntohs(1) * (u16)~(skb->len - l4_offset);
+	l4.tcp->check = ~csum_fold((__force __wsum)paylen);
+
+	/* compute length of segmentation header */
+	*hdr_len = (l4.tcp->doff * 4) + l4_offset;
 
 	/* find the field values */
 	cd_cmd = I40E_TX_CTX_DESC_TSO;
-- 
cgit v1.2.3


From c777019af1dc7343be8dc44bb4d32f5e2ef072dd Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Sun, 24 Jan 2016 21:16:35 -0800
Subject: i40e/i40evf: Consolidate all header changes into TSO function

This patch goes through and pulls all of the spots where we were updating
either the TCP or IP checksums in the TSO and checksum path into the TSO
function.  The general idea here is that we should only be updating the
header after we verify we have completed a skb_cow_head check to verify the
head is writable.

One other advantage to doing this is that it makes things much more
obvious.  For example, in the case of IPv6 there was one spot where the
offset of the IPv4 header checksum was being updated which is obviously
incorrect.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 44 ++++++++++++++++-----------
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 44 ++++++++++++++++-----------
 2 files changed, 52 insertions(+), 36 deletions(-)

(limited to 'drivers')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index ce0234e67cc5..f47f9cbfefcc 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2268,8 +2268,11 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 		    u8 *hdr_len, u64 *cd_type_cmd_tso_mss)
 {
 	u64 cd_cmd, cd_tso_len, cd_mss;
-	struct ipv6hdr *ipv6h;
-	struct iphdr *iph;
+	union {
+		struct iphdr *v4;
+		struct ipv6hdr *v6;
+		unsigned char *hdr;
+	} ip;
 	union {
 		struct tcphdr *tcp;
 		unsigned char *hdr;
@@ -2287,16 +2290,29 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	if (err < 0)
 		return err;
 
-	iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb);
-	ipv6h = skb->encapsulation ? inner_ipv6_hdr(skb) : ipv6_hdr(skb);
-	l4.hdr = skb->encapsulation ? skb_inner_transport_header(skb) :
-				      skb_transport_header(skb);
+	ip.hdr = skb_network_header(skb);
+	l4.hdr = skb_transport_header(skb);
 
-	if (iph->version == 4) {
-		iph->tot_len = 0;
-		iph->check = 0;
+	/* initialize outer IP header fields */
+	if (ip.v4->version == 4) {
+		ip.v4->tot_len = 0;
+		ip.v4->check = 0;
 	} else {
-		ipv6h->payload_len = 0;
+		ip.v6->payload_len = 0;
+	}
+
+	if (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_GRE)) {
+		/* reset pointers to inner headers */
+		ip.hdr = skb_inner_network_header(skb);
+		l4.hdr = skb_inner_transport_header(skb);
+
+		/* initialize inner IP header fields */
+		if (ip.v4->version == 4) {
+			ip.v4->tot_len = 0;
+			ip.v4->check = 0;
+		} else {
+			ip.v6->payload_len = 0;
+		}
 	}
 
 	/* determine offset of inner transport header */
@@ -2381,15 +2397,11 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 	struct iphdr *this_ip_hdr;
 	u32 network_hdr_len;
 	u8 l4_hdr = 0;
-	struct udphdr *oudph = NULL;
-	struct iphdr *oiph = NULL;
 	u32 l4_tunnel = 0;
 
 	if (skb->encapsulation) {
 		switch (ip_hdr(skb)->protocol) {
 		case IPPROTO_UDP:
-			oudph = udp_hdr(skb);
-			oiph = ip_hdr(skb);
 			l4_tunnel = I40E_TXD_CTX_UDP_TUNNELING;
 			*tx_flags |= I40E_TX_FLAGS_UDP_TUNNEL;
 			break;
@@ -2407,15 +2419,12 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		if (*tx_flags & I40E_TX_FLAGS_IPV4) {
 			if (*tx_flags & I40E_TX_FLAGS_TSO) {
 				*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV4;
-				ip_hdr(skb)->check = 0;
 			} else {
 				*cd_tunneling |=
 					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
 			}
 		} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
 			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
-			if (*tx_flags & I40E_TX_FLAGS_TSO)
-				ip_hdr(skb)->check = 0;
 		}
 
 		/* Now set the ctx descriptor fields */
@@ -2444,7 +2453,6 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		 */
 		if (*tx_flags & I40E_TX_FLAGS_TSO) {
 			*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4_CSUM;
-			this_ip_hdr->check = 0;
 		} else {
 			*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4;
 		}
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 881d0ada99fc..b5b25277ddac 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1528,8 +1528,11 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 		    u8 *hdr_len, u64 *cd_type_cmd_tso_mss)
 {
 	u64 cd_cmd, cd_tso_len, cd_mss;
-	struct ipv6hdr *ipv6h;
-	struct iphdr *iph;
+	union {
+		struct iphdr *v4;
+		struct ipv6hdr *v6;
+		unsigned char *hdr;
+	} ip;
 	union {
 		struct tcphdr *tcp;
 		unsigned char *hdr;
@@ -1547,16 +1550,29 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	if (err < 0)
 		return err;
 
-	iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb);
-	ipv6h = skb->encapsulation ? inner_ipv6_hdr(skb) : ipv6_hdr(skb);
-	l4.hdr = skb->encapsulation ? skb_inner_transport_header(skb) :
-				      skb_transport_header(skb);
+	ip.hdr = skb_network_header(skb);
+	l4.hdr = skb_transport_header(skb);
 
-	if (iph->version == 4) {
-		iph->tot_len = 0;
-		iph->check = 0;
+	/* initialize outer IP header fields */
+	if (ip.v4->version == 4) {
+		ip.v4->tot_len = 0;
+		ip.v4->check = 0;
 	} else {
-		ipv6h->payload_len = 0;
+		ip.v6->payload_len = 0;
+	}
+
+	if (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_GRE)) {
+		/* reset pointers to inner headers */
+		ip.hdr = skb_inner_network_header(skb);
+		l4.hdr = skb_inner_transport_header(skb);
+
+		/* initialize inner IP header fields */
+		if (ip.v4->version == 4) {
+			ip.v4->tot_len = 0;
+			ip.v4->check = 0;
+		} else {
+			ip.v6->payload_len = 0;
+		}
 	}
 
 	/* determine offset of inner transport header */
@@ -1598,15 +1614,11 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 	struct iphdr *this_ip_hdr;
 	u32 network_hdr_len;
 	u8 l4_hdr = 0;
-	struct udphdr *oudph;
-	struct iphdr *oiph;
 	u32 l4_tunnel = 0;
 
 	if (skb->encapsulation) {
 		switch (ip_hdr(skb)->protocol) {
 		case IPPROTO_UDP:
-			oudph = udp_hdr(skb);
-			oiph = ip_hdr(skb);
 			l4_tunnel = I40E_TXD_CTX_UDP_TUNNELING;
 			*tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL;
 			break;
@@ -1621,15 +1633,12 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		if (*tx_flags & I40E_TX_FLAGS_IPV4) {
 			if (*tx_flags & I40E_TX_FLAGS_TSO) {
 				*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV4;
-				ip_hdr(skb)->check = 0;
 			} else {
 				*cd_tunneling |=
 					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
 			}
 		} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
 			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
-			if (*tx_flags & I40E_TX_FLAGS_TSO)
-				ip_hdr(skb)->check = 0;
 		}
 
 		/* Now set the ctx descriptor fields */
@@ -1659,7 +1668,6 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		 */
 		if (*tx_flags & I40E_TX_FLAGS_TSO) {
 			*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4_CSUM;
-			this_ip_hdr->check = 0;
 		} else {
 			*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4;
 		}
-- 
cgit v1.2.3


From b96b78f2b789ab8398e7ec0111bb8b4588ed42bf Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Sun, 24 Jan 2016 21:16:42 -0800
Subject: i40e/i40evf: Replace header pointers with unions of pointers in Tx
 checksum path

The Tx checksum path was maintaining a set of 3 pointers and two lengths in
order to prepare the packet for being checksummed.  The thing is we only
really needed 2 pointers, and the lengths that were being maintained can
easily be computed.

As such we can replace the IPv4 and IPv6 header pointers with one single
union that represents both, or a generic pointer to the start of the
network header.  For the L4 headers we can do the same with TCP and a
generic pointer to the start of the transport header.  The length of the
TCP header is obtained by simply multiplying doff by 4, and the network
header length can be obtained by subtracting the network header pointer
from the transport header pointer.

While I was at it I renamed l4_hdr to l4_proto to make it a bit more clear
and less likely to be confused with l4.hdr which is the transport header
pointer.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 51 +++++++++++++-------------
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 52 +++++++++++++--------------
 2 files changed, 52 insertions(+), 51 deletions(-)

(limited to 'drivers')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index f47f9cbfefcc..5cc7e711068d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2392,12 +2392,21 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 				struct i40e_ring *tx_ring,
 				u32 *cd_tunneling)
 {
-	struct ipv6hdr *this_ipv6_hdr;
-	unsigned int this_tcp_hdrlen;
-	struct iphdr *this_ip_hdr;
-	u32 network_hdr_len;
-	u8 l4_hdr = 0;
+	union {
+		struct iphdr *v4;
+		struct ipv6hdr *v6;
+		unsigned char *hdr;
+	} ip;
+	union {
+		struct tcphdr *tcp;
+		struct udphdr *udp;
+		unsigned char *hdr;
+	} l4;
 	u32 l4_tunnel = 0;
+	u8 l4_proto = 0;
+
+	ip.hdr = skb_network_header(skb);
+	l4.hdr = skb_transport_header(skb);
 
 	if (skb->encapsulation) {
 		switch (ip_hdr(skb)->protocol) {
@@ -2411,10 +2420,10 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		default:
 			return;
 		}
-		network_hdr_len = skb_inner_network_header_len(skb);
-		this_ip_hdr = inner_ip_hdr(skb);
-		this_ipv6_hdr = inner_ipv6_hdr(skb);
-		this_tcp_hdrlen = inner_tcp_hdrlen(skb);
+
+		/* switch L4 header pointer from outer to inner */
+		ip.hdr = skb_inner_network_header(skb);
+		l4.hdr = skb_inner_transport_header(skb);
 
 		if (*tx_flags & I40E_TX_FLAGS_IPV4) {
 			if (*tx_flags & I40E_TX_FLAGS_TSO) {
@@ -2434,20 +2443,15 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 				   ((skb_inner_network_offset(skb) -
 					skb_transport_offset(skb)) >> 1) <<
 				   I40E_TXD_CTX_QW0_NATLEN_SHIFT;
-		if (this_ip_hdr->version == 6) {
+		if (ip.v6->version == 6) {
 			*tx_flags &= ~I40E_TX_FLAGS_IPV4;
 			*tx_flags |= I40E_TX_FLAGS_IPV6;
 		}
-	} else {
-		network_hdr_len = skb_network_header_len(skb);
-		this_ip_hdr = ip_hdr(skb);
-		this_ipv6_hdr = ipv6_hdr(skb);
-		this_tcp_hdrlen = tcp_hdrlen(skb);
 	}
 
 	/* Enable IP checksum offloads */
 	if (*tx_flags & I40E_TX_FLAGS_IPV4) {
-		l4_hdr = this_ip_hdr->protocol;
+		l4_proto = ip.v4->protocol;
 		/* the stack computes the IP header already, the only time we
 		 * need the hardware to recompute it is in the case of TSO.
 		 */
@@ -2456,26 +2460,23 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		} else {
 			*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4;
 		}
-		/* Now set the td_offset for IP header length */
-		*td_offset = (network_hdr_len >> 2) <<
-			      I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
 	} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
-		l4_hdr = this_ipv6_hdr->nexthdr;
+		l4_proto = ip.v6->nexthdr;
 		*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV6;
-		/* Now set the td_offset for IP header length */
-		*td_offset = (network_hdr_len >> 2) <<
-			      I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
 	}
+
+	/* Now set the td_offset for IP header length */
+	*td_offset = ((l4.hdr - ip.hdr) / 4) << I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
 	/* words in MACLEN + dwords in IPLEN + dwords in L4Len */
 	*td_offset |= (skb_network_offset(skb) >> 1) <<
 		       I40E_TX_DESC_LENGTH_MACLEN_SHIFT;
 
 	/* Enable L4 checksum offloads */
-	switch (l4_hdr) {
+	switch (l4_proto) {
 	case IPPROTO_TCP:
 		/* enable checksum offloads */
 		*td_cmd |= I40E_TX_DESC_CMD_L4T_EOFT_TCP;
-		*td_offset |= (this_tcp_hdrlen >> 2) <<
+		*td_offset |= l4.tcp->doff <<
 			       I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
 		break;
 	case IPPROTO_SCTP:
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index b5b25277ddac..29af3c9fc120 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1609,12 +1609,21 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 				struct i40e_ring *tx_ring,
 				u32 *cd_tunneling)
 {
-	struct ipv6hdr *this_ipv6_hdr;
-	unsigned int this_tcp_hdrlen;
-	struct iphdr *this_ip_hdr;
-	u32 network_hdr_len;
-	u8 l4_hdr = 0;
+	union {
+		struct iphdr *v4;
+		struct ipv6hdr *v6;
+		unsigned char *hdr;
+	} ip;
+	union {
+		struct tcphdr *tcp;
+		struct udphdr *udp;
+		unsigned char *hdr;
+	} l4;
 	u32 l4_tunnel = 0;
+	u8 l4_proto = 0;
+
+	ip.hdr = skb_network_header(skb);
+	l4.hdr = skb_transport_header(skb);
 
 	if (skb->encapsulation) {
 		switch (ip_hdr(skb)->protocol) {
@@ -1625,10 +1634,10 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		default:
 			return;
 		}
-		network_hdr_len = skb_inner_network_header_len(skb);
-		this_ip_hdr = inner_ip_hdr(skb);
-		this_ipv6_hdr = inner_ipv6_hdr(skb);
-		this_tcp_hdrlen = inner_tcp_hdrlen(skb);
+
+		/* switch L4 header pointer from outer to inner */
+		ip.hdr = skb_inner_network_header(skb);
+		l4.hdr = skb_inner_transport_header(skb);
 
 		if (*tx_flags & I40E_TX_FLAGS_IPV4) {
 			if (*tx_flags & I40E_TX_FLAGS_TSO) {
@@ -1648,21 +1657,15 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 				   ((skb_inner_network_offset(skb) -
 					skb_transport_offset(skb)) >> 1) <<
 				   I40E_TXD_CTX_QW0_NATLEN_SHIFT;
-		if (this_ip_hdr->version == 6) {
+		if (ip.v6->version == 6) {
 			*tx_flags &= ~I40E_TX_FLAGS_IPV4;
 			*tx_flags |= I40E_TX_FLAGS_IPV6;
 		}
-
-	} else {
-		network_hdr_len = skb_network_header_len(skb);
-		this_ip_hdr = ip_hdr(skb);
-		this_ipv6_hdr = ipv6_hdr(skb);
-		this_tcp_hdrlen = tcp_hdrlen(skb);
 	}
 
 	/* Enable IP checksum offloads */
 	if (*tx_flags & I40E_TX_FLAGS_IPV4) {
-		l4_hdr = this_ip_hdr->protocol;
+		l4_proto = ip.v4->protocol;
 		/* the stack computes the IP header already, the only time we
 		 * need the hardware to recompute it is in the case of TSO.
 		 */
@@ -1671,26 +1674,23 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		} else {
 			*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4;
 		}
-		/* Now set the td_offset for IP header length */
-		*td_offset = (network_hdr_len >> 2) <<
-			      I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
 	} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
-		l4_hdr = this_ipv6_hdr->nexthdr;
+		l4_proto = ip.v6->nexthdr;
 		*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV6;
-		/* Now set the td_offset for IP header length */
-		*td_offset = (network_hdr_len >> 2) <<
-			      I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
 	}
+
+	/* Now set the td_offset for IP header length */
+	*td_offset = ((l4.hdr - ip.hdr) / 4) << I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
 	/* words in MACLEN + dwords in IPLEN + dwords in L4Len */
 	*td_offset |= (skb_network_offset(skb) >> 1) <<
 		       I40E_TX_DESC_LENGTH_MACLEN_SHIFT;
 
 	/* Enable L4 checksum offloads */
-	switch (l4_hdr) {
+	switch (l4_proto) {
 	case IPPROTO_TCP:
 		/* enable checksum offloads */
 		*td_cmd |= I40E_TX_DESC_CMD_L4T_EOFT_TCP;
-		*td_offset |= (this_tcp_hdrlen >> 2) <<
+		*td_offset |= l4.tcp->doff <<
 			       I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
 		break;
 	case IPPROTO_SCTP:
-- 
cgit v1.2.3


From a0064728f8a34f7a5afd9df86d9cdd8210977c8d Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Sun, 24 Jan 2016 21:16:48 -0800
Subject: i40e/i40evf: Add support for IPv4 encapsulated in IPv6

This patch fixes two issues.  First was the fact that iphdr(skb)->protocl
was being used to test for the outer transport protocol.  This completely
breaks IPv6 support.  Second was the fact that we cleared the flag for v4
going to v6, but we didn't take care of txflags going the other way.  As
such we would have the v6 flag still set even if the inner header was v4.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 38 +++++++++++++++----------
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 41 +++++++++++++++++----------
 2 files changed, 49 insertions(+), 30 deletions(-)

(limited to 'drivers')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 5cc7e711068d..1404cae04b83 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2409,13 +2409,28 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 	l4.hdr = skb_transport_header(skb);
 
 	if (skb->encapsulation) {
-		switch (ip_hdr(skb)->protocol) {
+		/* define outer network header type */
+		if (*tx_flags & I40E_TX_FLAGS_IPV4) {
+			if (*tx_flags & I40E_TX_FLAGS_TSO)
+				*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV4;
+			else
+				*cd_tunneling |=
+					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
+			l4_proto = ip.v4->protocol;
+		} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
+			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
+			l4_proto = ip.v6->nexthdr;
+		}
+
+		/* define outer transport */
+		switch (l4_proto) {
 		case IPPROTO_UDP:
 			l4_tunnel = I40E_TXD_CTX_UDP_TUNNELING;
 			*tx_flags |= I40E_TX_FLAGS_UDP_TUNNEL;
 			break;
 		case IPPROTO_GRE:
 			l4_tunnel = I40E_TXD_CTX_GRE_TUNNELING;
+			*tx_flags |= I40E_TX_FLAGS_UDP_TUNNEL;
 			break;
 		default:
 			return;
@@ -2424,17 +2439,7 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		/* switch L4 header pointer from outer to inner */
 		ip.hdr = skb_inner_network_header(skb);
 		l4.hdr = skb_inner_transport_header(skb);
-
-		if (*tx_flags & I40E_TX_FLAGS_IPV4) {
-			if (*tx_flags & I40E_TX_FLAGS_TSO) {
-				*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV4;
-			} else {
-				*cd_tunneling |=
-					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
-			}
-		} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
-			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
-		}
+		l4_proto = 0;
 
 		/* Now set the ctx descriptor fields */
 		*cd_tunneling |= (skb_network_header_len(skb) >> 2) <<
@@ -2443,10 +2448,13 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 				   ((skb_inner_network_offset(skb) -
 					skb_transport_offset(skb)) >> 1) <<
 				   I40E_TXD_CTX_QW0_NATLEN_SHIFT;
-		if (ip.v6->version == 6) {
-			*tx_flags &= ~I40E_TX_FLAGS_IPV4;
+
+		/* reset type as we transition from outer to inner headers */
+		*tx_flags &= ~(I40E_TX_FLAGS_IPV4 | I40E_TX_FLAGS_IPV6);
+		if (ip.v4->version == 4)
+			*tx_flags |= I40E_TX_FLAGS_IPV4;
+		if (ip.v6->version == 6)
 			*tx_flags |= I40E_TX_FLAGS_IPV6;
-		}
 	}
 
 	/* Enable IP checksum offloads */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 29af3c9fc120..39d5f807f08c 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1626,11 +1626,29 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 	l4.hdr = skb_transport_header(skb);
 
 	if (skb->encapsulation) {
-		switch (ip_hdr(skb)->protocol) {
+		/* define outer network header type */
+		if (*tx_flags & I40E_TX_FLAGS_IPV4) {
+			if (*tx_flags & I40E_TX_FLAGS_TSO)
+				*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV4;
+			else
+				*cd_tunneling |=
+					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
+			l4_proto = ip.v4->protocol;
+		} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
+			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
+			l4_proto = ip.v6->nexthdr;
+		}
+
+		/* define outer transport */
+		switch (l4_proto) {
 		case IPPROTO_UDP:
 			l4_tunnel = I40E_TXD_CTX_UDP_TUNNELING;
 			*tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL;
 			break;
+		case IPPROTO_GRE:
+			l4_tunnel = I40E_TXD_CTX_GRE_TUNNELING;
+			*tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL;
+			break;
 		default:
 			return;
 		}
@@ -1638,17 +1656,7 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		/* switch L4 header pointer from outer to inner */
 		ip.hdr = skb_inner_network_header(skb);
 		l4.hdr = skb_inner_transport_header(skb);
-
-		if (*tx_flags & I40E_TX_FLAGS_IPV4) {
-			if (*tx_flags & I40E_TX_FLAGS_TSO) {
-				*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV4;
-			} else {
-				*cd_tunneling |=
-					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
-			}
-		} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
-			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
-		}
+		l4_proto = 0;
 
 		/* Now set the ctx descriptor fields */
 		*cd_tunneling |= (skb_network_header_len(skb) >> 2) <<
@@ -1657,10 +1665,13 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 				   ((skb_inner_network_offset(skb) -
 					skb_transport_offset(skb)) >> 1) <<
 				   I40E_TXD_CTX_QW0_NATLEN_SHIFT;
-		if (ip.v6->version == 6) {
-			*tx_flags &= ~I40E_TX_FLAGS_IPV4;
+
+		/* reset type as we transition from outer to inner headers */
+		*tx_flags &= ~(I40E_TX_FLAGS_IPV4 | I40E_TX_FLAGS_IPV6);
+		if (ip.v4->version == 4)
+			*tx_flags |= I40E_TX_FLAGS_IPV4;
+		if (ip.v6->version == 6)
 			*tx_flags |= I40E_TX_FLAGS_IPV6;
-		}
 	}
 
 	/* Enable IP checksum offloads */
-- 
cgit v1.2.3


From a3fd9d8876a589f05725237aced606b995956860 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Sun, 24 Jan 2016 21:16:54 -0800
Subject: i40e/i40evf: Handle IPv6 extension headers in checksum offload

This patch adds support for IPv6 extension headers in setting up the Tx
checksum.  Without this patch extension headers would cause IPv6 traffic to
fail as the transport protocol could not be identified.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 14 +++++++++++++-
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 14 +++++++++++++-
 2 files changed, 26 insertions(+), 2 deletions(-)

(limited to 'drivers')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 1404cae04b83..e49fe8f580b1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2402,7 +2402,9 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		struct udphdr *udp;
 		unsigned char *hdr;
 	} l4;
+	unsigned char *exthdr;
 	u32 l4_tunnel = 0;
+	__be16 frag_off;
 	u8 l4_proto = 0;
 
 	ip.hdr = skb_network_header(skb);
@@ -2419,7 +2421,12 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 			l4_proto = ip.v4->protocol;
 		} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
 			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
+
+			exthdr = ip.hdr + sizeof(*ip.v6);
 			l4_proto = ip.v6->nexthdr;
+			if (l4.hdr != exthdr)
+				ipv6_skip_exthdr(skb, exthdr - skb->data,
+						 &l4_proto, &frag_off);
 		}
 
 		/* define outer transport */
@@ -2469,8 +2476,13 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 			*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4;
 		}
 	} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
-		l4_proto = ip.v6->nexthdr;
 		*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV6;
+
+		exthdr = ip.hdr + sizeof(*ip.v6);
+		l4_proto = ip.v6->nexthdr;
+		if (l4.hdr != exthdr)
+			ipv6_skip_exthdr(skb, exthdr - skb->data,
+					 &l4_proto, &frag_off);
 	}
 
 	/* Now set the td_offset for IP header length */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 39d5f807f08c..48ec7631b3dd 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1619,7 +1619,9 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		struct udphdr *udp;
 		unsigned char *hdr;
 	} l4;
+	unsigned char *exthdr;
 	u32 l4_tunnel = 0;
+	__be16 frag_off;
 	u8 l4_proto = 0;
 
 	ip.hdr = skb_network_header(skb);
@@ -1636,7 +1638,12 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 			l4_proto = ip.v4->protocol;
 		} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
 			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
+
+			exthdr = ip.hdr + sizeof(*ip.v6);
 			l4_proto = ip.v6->nexthdr;
+			if (l4.hdr != exthdr)
+				ipv6_skip_exthdr(skb, exthdr - skb->data,
+						 &l4_proto, &frag_off);
 		}
 
 		/* define outer transport */
@@ -1686,8 +1693,13 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 			*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4;
 		}
 	} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
-		l4_proto = ip.v6->nexthdr;
 		*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV6;
+
+		exthdr = ip.hdr + sizeof(*ip.v6);
+		l4_proto = ip.v6->nexthdr;
+		if (l4.hdr != exthdr)
+			ipv6_skip_exthdr(skb, exthdr - skb->data,
+					 &l4_proto, &frag_off);
 	}
 
 	/* Now set the td_offset for IP header length */
-- 
cgit v1.2.3


From 475b4205aa52c16feef08d55c8fd76e815b6bee7 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Sun, 24 Jan 2016 21:17:01 -0800
Subject: i40e/i40evf: Do not write to descriptor unless we complete

This patch defers writing to the Tx descriptor bits until we know we have
successfully completed a given operation.  So for example we defer updating
the tunnelling portion of the context descriptor until we have fully
identified the type.

The advantage to this approach is that we can assemble values as we go
instead of having to try and kludge everything together all at once.  As a
result we can significantly clean up the tunneling configuration for
instance as we can just do a pointer walk and do the math for the distance
between each set of points.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 80 ++++++++++++++-------------
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 80 ++++++++++++++-------------
 2 files changed, 84 insertions(+), 76 deletions(-)

(limited to 'drivers')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index e49fe8f580b1..5b591b865fd5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2403,24 +2403,26 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		unsigned char *hdr;
 	} l4;
 	unsigned char *exthdr;
-	u32 l4_tunnel = 0;
+	u32 offset, cmd = 0, tunnel = 0;
 	__be16 frag_off;
 	u8 l4_proto = 0;
 
 	ip.hdr = skb_network_header(skb);
 	l4.hdr = skb_transport_header(skb);
 
+	/* compute outer L2 header size */
+	offset = ((ip.hdr - skb->data) / 2) << I40E_TX_DESC_LENGTH_MACLEN_SHIFT;
+
 	if (skb->encapsulation) {
 		/* define outer network header type */
 		if (*tx_flags & I40E_TX_FLAGS_IPV4) {
-			if (*tx_flags & I40E_TX_FLAGS_TSO)
-				*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV4;
-			else
-				*cd_tunneling |=
-					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
+			tunnel |= (*tx_flags & I40E_TX_FLAGS_TSO) ?
+				  I40E_TX_CTX_EXT_IP_IPV4 :
+				  I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
+
 			l4_proto = ip.v4->protocol;
 		} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
-			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
+			tunnel |= I40E_TX_CTX_EXT_IP_IPV6;
 
 			exthdr = ip.hdr + sizeof(*ip.v6);
 			l4_proto = ip.v6->nexthdr;
@@ -2429,33 +2431,38 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 						 &l4_proto, &frag_off);
 		}
 
+		/* compute outer L3 header size */
+		tunnel |= ((l4.hdr - ip.hdr) / 4) <<
+			  I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT;
+
+		/* switch IP header pointer from outer to inner header */
+		ip.hdr = skb_inner_network_header(skb);
+
 		/* define outer transport */
 		switch (l4_proto) {
 		case IPPROTO_UDP:
-			l4_tunnel = I40E_TXD_CTX_UDP_TUNNELING;
+			tunnel |= I40E_TXD_CTX_UDP_TUNNELING;
 			*tx_flags |= I40E_TX_FLAGS_UDP_TUNNEL;
 			break;
 		case IPPROTO_GRE:
-			l4_tunnel = I40E_TXD_CTX_GRE_TUNNELING;
+			tunnel |= I40E_TXD_CTX_GRE_TUNNELING;
 			*tx_flags |= I40E_TX_FLAGS_UDP_TUNNEL;
 			break;
 		default:
 			return;
 		}
 
+		/* compute tunnel header size */
+		tunnel |= ((ip.hdr - l4.hdr) / 2) <<
+			  I40E_TXD_CTX_QW0_NATLEN_SHIFT;
+
+		/* record tunnel offload values */
+		*cd_tunneling |= tunnel;
+
 		/* switch L4 header pointer from outer to inner */
-		ip.hdr = skb_inner_network_header(skb);
 		l4.hdr = skb_inner_transport_header(skb);
 		l4_proto = 0;
 
-		/* Now set the ctx descriptor fields */
-		*cd_tunneling |= (skb_network_header_len(skb) >> 2) <<
-				   I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT      |
-				   l4_tunnel                             |
-				   ((skb_inner_network_offset(skb) -
-					skb_transport_offset(skb)) >> 1) <<
-				   I40E_TXD_CTX_QW0_NATLEN_SHIFT;
-
 		/* reset type as we transition from outer to inner headers */
 		*tx_flags &= ~(I40E_TX_FLAGS_IPV4 | I40E_TX_FLAGS_IPV6);
 		if (ip.v4->version == 4)
@@ -2470,13 +2477,11 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		/* the stack computes the IP header already, the only time we
 		 * need the hardware to recompute it is in the case of TSO.
 		 */
-		if (*tx_flags & I40E_TX_FLAGS_TSO) {
-			*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4_CSUM;
-		} else {
-			*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4;
-		}
+		cmd |= (*tx_flags & I40E_TX_FLAGS_TSO) ?
+		       I40E_TX_DESC_CMD_IIPT_IPV4_CSUM :
+		       I40E_TX_DESC_CMD_IIPT_IPV4;
 	} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
-		*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV6;
+		cmd |= I40E_TX_DESC_CMD_IIPT_IPV6;
 
 		exthdr = ip.hdr + sizeof(*ip.v6);
 		l4_proto = ip.v6->nexthdr;
@@ -2485,35 +2490,34 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 					 &l4_proto, &frag_off);
 	}
 
-	/* Now set the td_offset for IP header length */
-	*td_offset = ((l4.hdr - ip.hdr) / 4) << I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
-	/* words in MACLEN + dwords in IPLEN + dwords in L4Len */
-	*td_offset |= (skb_network_offset(skb) >> 1) <<
-		       I40E_TX_DESC_LENGTH_MACLEN_SHIFT;
+	/* compute inner L3 header size */
+	offset |= ((l4.hdr - ip.hdr) / 4) << I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
 
 	/* Enable L4 checksum offloads */
 	switch (l4_proto) {
 	case IPPROTO_TCP:
 		/* enable checksum offloads */
-		*td_cmd |= I40E_TX_DESC_CMD_L4T_EOFT_TCP;
-		*td_offset |= l4.tcp->doff <<
-			       I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
+		cmd |= I40E_TX_DESC_CMD_L4T_EOFT_TCP;
+		offset |= l4.tcp->doff << I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
 		break;
 	case IPPROTO_SCTP:
 		/* enable SCTP checksum offload */
-		*td_cmd |= I40E_TX_DESC_CMD_L4T_EOFT_SCTP;
-		*td_offset |= (sizeof(struct sctphdr) >> 2) <<
-			       I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
+		cmd |= I40E_TX_DESC_CMD_L4T_EOFT_SCTP;
+		offset |= (sizeof(struct sctphdr) >> 2) <<
+			  I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
 		break;
 	case IPPROTO_UDP:
 		/* enable UDP checksum offload */
-		*td_cmd |= I40E_TX_DESC_CMD_L4T_EOFT_UDP;
-		*td_offset |= (sizeof(struct udphdr) >> 2) <<
-			       I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
+		cmd |= I40E_TX_DESC_CMD_L4T_EOFT_UDP;
+		offset |= (sizeof(struct udphdr) >> 2) <<
+			  I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
 		break;
 	default:
 		break;
 	}
+
+	*td_cmd |= cmd;
+	*td_offset |= offset;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 48ec7631b3dd..0ee13f6619c4 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1620,24 +1620,26 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		unsigned char *hdr;
 	} l4;
 	unsigned char *exthdr;
-	u32 l4_tunnel = 0;
+	u32 offset, cmd = 0, tunnel = 0;
 	__be16 frag_off;
 	u8 l4_proto = 0;
 
 	ip.hdr = skb_network_header(skb);
 	l4.hdr = skb_transport_header(skb);
 
+	/* compute outer L2 header size */
+	offset = ((ip.hdr - skb->data) / 2) << I40E_TX_DESC_LENGTH_MACLEN_SHIFT;
+
 	if (skb->encapsulation) {
 		/* define outer network header type */
 		if (*tx_flags & I40E_TX_FLAGS_IPV4) {
-			if (*tx_flags & I40E_TX_FLAGS_TSO)
-				*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV4;
-			else
-				*cd_tunneling |=
-					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
+			tunnel |= (*tx_flags & I40E_TX_FLAGS_TSO) ?
+				  I40E_TX_CTX_EXT_IP_IPV4 :
+				  I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
+
 			l4_proto = ip.v4->protocol;
 		} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
-			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
+			tunnel |= I40E_TX_CTX_EXT_IP_IPV6;
 
 			exthdr = ip.hdr + sizeof(*ip.v6);
 			l4_proto = ip.v6->nexthdr;
@@ -1646,33 +1648,38 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 						 &l4_proto, &frag_off);
 		}
 
+		/* compute outer L3 header size */
+		tunnel |= ((l4.hdr - ip.hdr) / 4) <<
+			  I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT;
+
+		/* switch IP header pointer from outer to inner header */
+		ip.hdr = skb_inner_network_header(skb);
+
 		/* define outer transport */
 		switch (l4_proto) {
 		case IPPROTO_UDP:
-			l4_tunnel = I40E_TXD_CTX_UDP_TUNNELING;
+			tunnel |= I40E_TXD_CTX_UDP_TUNNELING;
 			*tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL;
 			break;
 		case IPPROTO_GRE:
-			l4_tunnel = I40E_TXD_CTX_GRE_TUNNELING;
+			tunnel |= I40E_TXD_CTX_GRE_TUNNELING;
 			*tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL;
 			break;
 		default:
 			return;
 		}
 
+		/* compute tunnel header size */
+		tunnel |= ((ip.hdr - l4.hdr) / 2) <<
+			  I40E_TXD_CTX_QW0_NATLEN_SHIFT;
+
+		/* record tunnel offload values */
+		*cd_tunneling |= tunnel;
+
 		/* switch L4 header pointer from outer to inner */
-		ip.hdr = skb_inner_network_header(skb);
 		l4.hdr = skb_inner_transport_header(skb);
 		l4_proto = 0;
 
-		/* Now set the ctx descriptor fields */
-		*cd_tunneling |= (skb_network_header_len(skb) >> 2) <<
-				   I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT      |
-				   l4_tunnel                             |
-				   ((skb_inner_network_offset(skb) -
-					skb_transport_offset(skb)) >> 1) <<
-				   I40E_TXD_CTX_QW0_NATLEN_SHIFT;
-
 		/* reset type as we transition from outer to inner headers */
 		*tx_flags &= ~(I40E_TX_FLAGS_IPV4 | I40E_TX_FLAGS_IPV6);
 		if (ip.v4->version == 4)
@@ -1687,13 +1694,11 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		/* the stack computes the IP header already, the only time we
 		 * need the hardware to recompute it is in the case of TSO.
 		 */
-		if (*tx_flags & I40E_TX_FLAGS_TSO) {
-			*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4_CSUM;
-		} else {
-			*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4;
-		}
+		cmd |= (*tx_flags & I40E_TX_FLAGS_TSO) ?
+		       I40E_TX_DESC_CMD_IIPT_IPV4_CSUM :
+		       I40E_TX_DESC_CMD_IIPT_IPV4;
 	} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
-		*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV6;
+		cmd |= I40E_TX_DESC_CMD_IIPT_IPV6;
 
 		exthdr = ip.hdr + sizeof(*ip.v6);
 		l4_proto = ip.v6->nexthdr;
@@ -1702,35 +1707,34 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 					 &l4_proto, &frag_off);
 	}
 
-	/* Now set the td_offset for IP header length */
-	*td_offset = ((l4.hdr - ip.hdr) / 4) << I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
-	/* words in MACLEN + dwords in IPLEN + dwords in L4Len */
-	*td_offset |= (skb_network_offset(skb) >> 1) <<
-		       I40E_TX_DESC_LENGTH_MACLEN_SHIFT;
+	/* compute inner L3 header size */
+	offset |= ((l4.hdr - ip.hdr) / 4) << I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
 
 	/* Enable L4 checksum offloads */
 	switch (l4_proto) {
 	case IPPROTO_TCP:
 		/* enable checksum offloads */
-		*td_cmd |= I40E_TX_DESC_CMD_L4T_EOFT_TCP;
-		*td_offset |= l4.tcp->doff <<
-			       I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
+		cmd |= I40E_TX_DESC_CMD_L4T_EOFT_TCP;
+		offset |= l4.tcp->doff << I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
 		break;
 	case IPPROTO_SCTP:
 		/* enable SCTP checksum offload */
-		*td_cmd |= I40E_TX_DESC_CMD_L4T_EOFT_SCTP;
-		*td_offset |= (sizeof(struct sctphdr) >> 2) <<
-			       I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
+		cmd |= I40E_TX_DESC_CMD_L4T_EOFT_SCTP;
+		offset |= (sizeof(struct sctphdr) >> 2) <<
+			  I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
 		break;
 	case IPPROTO_UDP:
 		/* enable UDP checksum offload */
-		*td_cmd |= I40E_TX_DESC_CMD_L4T_EOFT_UDP;
-		*td_offset |= (sizeof(struct udphdr) >> 2) <<
-			       I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
+		cmd |= I40E_TX_DESC_CMD_L4T_EOFT_UDP;
+		offset |= (sizeof(struct udphdr) >> 2) <<
+			  I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
 		break;
 	default:
 		break;
 	}
+
+	*td_cmd |= cmd;
+	*td_offset |= offset;
 }
 
 /**
-- 
cgit v1.2.3


From 529f1f652e3c3c6db6ab5a6e3a35469ddfd9575d Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Sun, 24 Jan 2016 21:17:10 -0800
Subject: i40e/i40evf: Add exception handling for Tx checksum

Add exception handling to the Tx checksum path so that we can handle cases
of TSO where the frame is bad, or Tx checksum where we didn't recognize a
protocol

Drop I40E_TX_FLAGS_CSUM as it is unused, move the CHECKSUM_PARTIAL check
into the function itself so that we can decrease indent.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 34 +++++++++++++++++---------
 drivers/net/ethernet/intel/i40e/i40e_txrx.h   |  1 -
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 35 ++++++++++++++++++---------
 drivers/net/ethernet/intel/i40evf/i40e_txrx.h |  1 -
 4 files changed, 45 insertions(+), 26 deletions(-)

(limited to 'drivers')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 5b591b865fd5..6b08b0fa6dcf 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2387,10 +2387,10 @@ static int i40e_tsyn(struct i40e_ring *tx_ring, struct sk_buff *skb,
  * @tx_ring: Tx descriptor ring
  * @cd_tunneling: ptr to context desc bits
  **/
-static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
-				u32 *td_cmd, u32 *td_offset,
-				struct i40e_ring *tx_ring,
-				u32 *cd_tunneling)
+static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
+			       u32 *td_cmd, u32 *td_offset,
+			       struct i40e_ring *tx_ring,
+			       u32 *cd_tunneling)
 {
 	union {
 		struct iphdr *v4;
@@ -2407,6 +2407,9 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 	__be16 frag_off;
 	u8 l4_proto = 0;
 
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return 0;
+
 	ip.hdr = skb_network_header(skb);
 	l4.hdr = skb_transport_header(skb);
 
@@ -2449,7 +2452,11 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 			*tx_flags |= I40E_TX_FLAGS_UDP_TUNNEL;
 			break;
 		default:
-			return;
+			if (*tx_flags & I40E_TX_FLAGS_TSO)
+				return -1;
+
+			skb_checksum_help(skb);
+			return 0;
 		}
 
 		/* compute tunnel header size */
@@ -2513,11 +2520,16 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 			  I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
 		break;
 	default:
-		break;
+		if (*tx_flags & I40E_TX_FLAGS_TSO)
+			return -1;
+		skb_checksum_help(skb);
+		return 0;
 	}
 
 	*td_cmd |= cmd;
 	*td_offset |= offset;
+
+	return 1;
 }
 
 /**
@@ -2954,12 +2966,10 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	td_cmd |= I40E_TX_DESC_CMD_ICRC;
 
 	/* Always offload the checksum, since it's in the data descriptor */
-	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		tx_flags |= I40E_TX_FLAGS_CSUM;
-
-		i40e_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset,
-				    tx_ring, &cd_tunneling);
-	}
+	tso = i40e_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset,
+				  tx_ring, &cd_tunneling);
+	if (tso < 0)
+		goto out_drop;
 
 	i40e_create_tx_ctx(tx_ring, cd_type_cmd_tso_mss,
 			   cd_tunneling, cd_l2tag2);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index fb065d4fe15c..fde5f42524fb 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -153,7 +153,6 @@ enum i40e_dyn_idx_t {
 #define DESC_NEEDED (MAX_SKB_FRAGS + 4)
 #define I40E_MIN_DESC_PENDING	4
 
-#define I40E_TX_FLAGS_CSUM		BIT(0)
 #define I40E_TX_FLAGS_HW_VLAN		BIT(1)
 #define I40E_TX_FLAGS_SW_VLAN		BIT(2)
 #define I40E_TX_FLAGS_TSO		BIT(3)
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 0ee13f6619c4..143c5703f54e 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1602,12 +1602,13 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
  * @tx_flags: pointer to Tx flags currently set
  * @td_cmd: Tx descriptor command bits to set
  * @td_offset: Tx descriptor header offsets to set
+ * @tx_ring: Tx descriptor ring
  * @cd_tunneling: ptr to context desc bits
  **/
-static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
-				u32 *td_cmd, u32 *td_offset,
-				struct i40e_ring *tx_ring,
-				u32 *cd_tunneling)
+static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
+			       u32 *td_cmd, u32 *td_offset,
+			       struct i40e_ring *tx_ring,
+			       u32 *cd_tunneling)
 {
 	union {
 		struct iphdr *v4;
@@ -1624,6 +1625,9 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 	__be16 frag_off;
 	u8 l4_proto = 0;
 
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return 0;
+
 	ip.hdr = skb_network_header(skb);
 	l4.hdr = skb_transport_header(skb);
 
@@ -1666,7 +1670,11 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 			*tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL;
 			break;
 		default:
-			return;
+			if (*tx_flags & I40E_TX_FLAGS_TSO)
+				return -1;
+
+			skb_checksum_help(skb);
+			return 0;
 		}
 
 		/* compute tunnel header size */
@@ -1730,11 +1738,16 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 			  I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
 		break;
 	default:
-		break;
+		if (*tx_flags & I40E_TX_FLAGS_TSO)
+			return -1;
+		skb_checksum_help(skb);
+		return 0;
 	}
 
 	*td_cmd |= cmd;
 	*td_offset |= offset;
+
+	return 1;
 }
 
 /**
@@ -2150,12 +2163,10 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	td_cmd |= I40E_TX_DESC_CMD_ICRC;
 
 	/* Always offload the checksum, since it's in the data descriptor */
-	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		tx_flags |= I40E_TX_FLAGS_CSUM;
-
-		i40e_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset,
-				    tx_ring, &cd_tunneling);
-	}
+	tso = i40e_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset,
+				  tx_ring, &cd_tunneling);
+	if (tso < 0)
+		goto out_drop;
 
 	i40e_create_tx_ctx(tx_ring, cd_type_cmd_tso_mss,
 			   cd_tunneling, cd_l2tag2);
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index 043b9556834f..6ea8701cf066 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -153,7 +153,6 @@ enum i40e_dyn_idx_t {
 #define DESC_NEEDED (MAX_SKB_FRAGS + 4)
 #define I40E_MIN_DESC_PENDING	4
 
-#define I40E_TX_FLAGS_CSUM		BIT(0)
 #define I40E_TX_FLAGS_HW_VLAN		BIT(1)
 #define I40E_TX_FLAGS_SW_VLAN		BIT(2)
 #define I40E_TX_FLAGS_TSO		BIT(3)
-- 
cgit v1.2.3


From fad57330b6d0710fdf39dc1c2b28ccebb97ae8a1 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Sun, 24 Jan 2016 21:17:22 -0800
Subject: i40e/i40evf: Clean-up Rx packet checksum handling

This is mostly a minor clean-up for the Rx checksum path in order to avoid
some of the unnecessary conditional checks that were being applied.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 23 ++++++++++-------------
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 23 ++++++++++-------------
 2 files changed, 20 insertions(+), 26 deletions(-)

(limited to 'drivers')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 6b08b0fa6dcf..ded73c021510 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1389,13 +1389,7 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 				    u16 rx_ptype)
 {
 	struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(rx_ptype);
-	bool ipv4 = false, ipv6 = false;
-	bool ipv4_tunnel, ipv6_tunnel;
-
-	ipv4_tunnel = (rx_ptype >= I40E_RX_PTYPE_GRENAT4_MAC_PAY3) &&
-		     (rx_ptype <= I40E_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4);
-	ipv6_tunnel = (rx_ptype >= I40E_RX_PTYPE_GRENAT6_MAC_PAY3) &&
-		     (rx_ptype <= I40E_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4);
+	bool ipv4, ipv6, ipv4_tunnel, ipv6_tunnel;
 
 	skb->ip_summed = CHECKSUM_NONE;
 
@@ -1411,12 +1405,10 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	if (!(decoded.known && decoded.outer_ip))
 		return;
 
-	if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP &&
-	    decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV4)
-		ipv4 = true;
-	else if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP &&
-		 decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV6)
-		ipv6 = true;
+	ipv4 = (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP) &&
+	       (decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV4);
+	ipv6 = (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP) &&
+	       (decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV6);
 
 	if (ipv4 &&
 	    (rx_error & (BIT(I40E_RX_DESC_ERROR_IPE_SHIFT) |
@@ -1447,6 +1439,11 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	 * inner checksum report CHECKSUM_UNNECESSARY.
 	 */
 
+	ipv4_tunnel = (rx_ptype >= I40E_RX_PTYPE_GRENAT4_MAC_PAY3) &&
+		     (rx_ptype <= I40E_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4);
+	ipv6_tunnel = (rx_ptype >= I40E_RX_PTYPE_GRENAT6_MAC_PAY3) &&
+		     (rx_ptype <= I40E_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4);
+
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
 	skb->csum_level = ipv4_tunnel || ipv6_tunnel;
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 143c5703f54e..3f40e0e26066 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -861,13 +861,7 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 				    u16 rx_ptype)
 {
 	struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(rx_ptype);
-	bool ipv4 = false, ipv6 = false;
-	bool ipv4_tunnel, ipv6_tunnel;
-
-	ipv4_tunnel = (rx_ptype >= I40E_RX_PTYPE_GRENAT4_MAC_PAY3) &&
-		     (rx_ptype <= I40E_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4);
-	ipv6_tunnel = (rx_ptype >= I40E_RX_PTYPE_GRENAT6_MAC_PAY3) &&
-		     (rx_ptype <= I40E_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4);
+	bool ipv4, ipv6, ipv4_tunnel, ipv6_tunnel;
 
 	skb->ip_summed = CHECKSUM_NONE;
 
@@ -883,12 +877,10 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	if (!(decoded.known && decoded.outer_ip))
 		return;
 
-	if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP &&
-	    decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV4)
-		ipv4 = true;
-	else if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP &&
-		 decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV6)
-		ipv6 = true;
+	ipv4 = (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP) &&
+	       (decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV4);
+	ipv6 = (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP) &&
+	       (decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV6);
 
 	if (ipv4 &&
 	    (rx_error & (BIT(I40E_RX_DESC_ERROR_IPE_SHIFT) |
@@ -919,6 +911,11 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	 * inner checksum report CHECKSUM_UNNECESSARY.
 	 */
 
+	ipv4_tunnel = (rx_ptype >= I40E_RX_PTYPE_GRENAT4_MAC_PAY3) &&
+		     (rx_ptype <= I40E_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4);
+	ipv6_tunnel = (rx_ptype >= I40E_RX_PTYPE_GRENAT6_MAC_PAY3) &&
+		     (rx_ptype <= I40E_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4);
+
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
 	skb->csum_level = ipv4_tunnel || ipv6_tunnel;
 
-- 
cgit v1.2.3


From 5453205cd0975b845f6f8837f0c2b7c8cb80fcf8 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Sun, 24 Jan 2016 21:17:29 -0800
Subject: i40e/i40evf: Enable support for SKB_GSO_UDP_TUNNEL_CSUM

The XL722 has support for providing the outer UDP tunnel checksum on
transmits.  Make use of this feature to support segmenting UDP tunnels with
outer checksums enabled.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 19 ++++++++++++++++++-
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 19 ++++++++++++++++++-
 2 files changed, 36 insertions(+), 2 deletions(-)

(limited to 'drivers')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index ded73c021510..1955c849a452 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2272,6 +2272,7 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	} ip;
 	union {
 		struct tcphdr *tcp;
+		struct udphdr *udp;
 		unsigned char *hdr;
 	} l4;
 	u32 paylen, l4_offset;
@@ -2298,7 +2299,18 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 		ip.v6->payload_len = 0;
 	}
 
-	if (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_GRE)) {
+	if (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_GRE |
+					 SKB_GSO_UDP_TUNNEL_CSUM)) {
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM) {
+			/* determine offset of outer transport header */
+			l4_offset = l4.hdr - skb->data;
+
+			/* remove payload length from outer checksum */
+			paylen = (__force u16)l4.udp->check;
+			paylen += ntohs(1) * (u16)~(skb->len - l4_offset);
+			l4.udp->check = ~csum_fold((__force __wsum)paylen);
+		}
+
 		/* reset pointers to inner headers */
 		ip.hdr = skb_inner_network_header(skb);
 		l4.hdr = skb_inner_transport_header(skb);
@@ -2460,6 +2472,11 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		tunnel |= ((ip.hdr - l4.hdr) / 2) <<
 			  I40E_TXD_CTX_QW0_NATLEN_SHIFT;
 
+		/* indicate if we need to offload outer UDP header */
+		if ((*tx_flags & I40E_TX_FLAGS_TSO) &&
+		    (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM))
+			tunnel |= I40E_TXD_CTX_QW0_L4T_CS_MASK;
+
 		/* record tunnel offload values */
 		*cd_tunneling |= tunnel;
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 3f40e0e26066..6d66fcdc6122 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1532,6 +1532,7 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	} ip;
 	union {
 		struct tcphdr *tcp;
+		struct udphdr *udp;
 		unsigned char *hdr;
 	} l4;
 	u32 paylen, l4_offset;
@@ -1558,7 +1559,18 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 		ip.v6->payload_len = 0;
 	}
 
-	if (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_GRE)) {
+	if (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_GRE |
+					 SKB_GSO_UDP_TUNNEL_CSUM)) {
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM) {
+			/* determine offset of outer transport header */
+			l4_offset = l4.hdr - skb->data;
+
+			/* remove payload length from outer checksum */
+			paylen = (__force u16)l4.udp->check;
+			paylen += ntohs(1) * (u16)~(skb->len - l4_offset);
+			l4.udp->check = ~csum_fold((__force __wsum)paylen);
+		}
+
 		/* reset pointers to inner headers */
 		ip.hdr = skb_inner_network_header(skb);
 		l4.hdr = skb_inner_transport_header(skb);
@@ -1678,6 +1690,11 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		tunnel |= ((ip.hdr - l4.hdr) / 2) <<
 			  I40E_TXD_CTX_QW0_NATLEN_SHIFT;
 
+		/* indicate if we need to offload outer UDP header */
+		if ((*tx_flags & I40E_TX_FLAGS_TSO) &&
+		    (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM))
+			tunnel |= I40E_TXD_CTX_QW0_L4T_CS_MASK;
+
 		/* record tunnel offload values */
 		*cd_tunneling |= tunnel;
 
-- 
cgit v1.2.3


From 6b037cd465ff6e5f6b96524658f47d59d1acc554 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Sun, 24 Jan 2016 21:17:36 -0800
Subject: i40e: Fix ATR in relation to tunnels

This patch contains a number of fixes to make certain that we are using
the correct protocols when parsing both the inner and outer headers of a
frame that is mixed between IPv4 and IPv6 for inner and outer.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Acked-by: Kiran Patil <kiran.patil@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c | 28 +++++++++++-----------------
 1 file changed, 11 insertions(+), 17 deletions(-)

(limited to 'drivers')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 1955c849a452..159fb6eed375 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2030,10 +2030,9 @@ tx_only:
  * @tx_ring:  ring to add programming descriptor to
  * @skb:      send buffer
  * @tx_flags: send tx flags
- * @protocol: wire protocol
  **/
 static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
-		     u32 tx_flags, __be16 protocol)
+		     u32 tx_flags)
 {
 	struct i40e_filter_program_desc *fdir_desc;
 	struct i40e_pf *pf = tx_ring->vsi->back;
@@ -2045,6 +2044,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	struct tcphdr *th;
 	unsigned int hlen;
 	u32 flex_ptype, dtype_cmd;
+	u8 l4_proto;
 	u16 i;
 
 	/* make sure ATR is enabled */
@@ -2058,6 +2058,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	if (!tx_ring->atr_sample_rate)
 		return;
 
+	/* Currently only IPv4/IPv6 with TCP is supported */
 	if (!(tx_flags & (I40E_TX_FLAGS_IPV4 | I40E_TX_FLAGS_IPV6)))
 		return;
 
@@ -2065,29 +2066,22 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 		/* snag network header to get L4 type and address */
 		hdr.network = skb_network_header(skb);
 
-		/* Currently only IPv4/IPv6 with TCP is supported
-		 * access ihl as u8 to avoid unaligned access on ia64
-		 */
+		/* access ihl as u8 to avoid unaligned access on ia64 */
 		if (tx_flags & I40E_TX_FLAGS_IPV4)
 			hlen = (hdr.network[0] & 0x0F) << 2;
-		else if (protocol == htons(ETH_P_IPV6))
-			hlen = sizeof(struct ipv6hdr);
 		else
-			return;
+			hlen = sizeof(struct ipv6hdr);
 	} else {
 		hdr.network = skb_inner_network_header(skb);
 		hlen = skb_inner_network_header_len(skb);
 	}
 
-	/* Currently only IPv4/IPv6 with TCP is supported
-	 * Note: tx_flags gets modified to reflect inner protocols in
+	/* Note: tx_flags gets modified to reflect inner protocols in
 	 * tx_enable_csum function if encap is enabled.
 	 */
-	if ((tx_flags & I40E_TX_FLAGS_IPV4) &&
-	    (hdr.ipv4->protocol != IPPROTO_TCP))
-		return;
-	else if ((tx_flags & I40E_TX_FLAGS_IPV6) &&
-		 (hdr.ipv6->nexthdr != IPPROTO_TCP))
+	l4_proto = (tx_flags & I40E_TX_FLAGS_IPV4) ? hdr.ipv4->protocol :
+						     hdr.ipv6->nexthdr;
+	if (l4_proto != IPPROTO_TCP)
 		return;
 
 	th = (struct tcphdr *)(hdr.network + hlen);
@@ -2124,7 +2118,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 	flex_ptype = (tx_ring->queue_index << I40E_TXD_FLTR_QW0_QINDEX_SHIFT) &
 		      I40E_TXD_FLTR_QW0_QINDEX_MASK;
-	flex_ptype |= (protocol == htons(ETH_P_IP)) ?
+	flex_ptype |= (tx_flags & I40E_TX_FLAGS_IPV4) ?
 		      (I40E_FILTER_PCTYPE_NONF_IPV4_TCP <<
 		       I40E_TXD_FLTR_QW0_PCTYPE_SHIFT) :
 		      (I40E_FILTER_PCTYPE_NONF_IPV6_TCP <<
@@ -2992,7 +2986,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	 *
 	 * NOTE: this must always be directly before the data descriptor.
 	 */
-	i40e_atr(tx_ring, skb, tx_flags, protocol);
+	i40e_atr(tx_ring, skb, tx_flags);
 
 	i40e_tx_map(tx_ring, skb, first, tx_flags, hdr_len,
 		    td_cmd, td_offset);
-- 
cgit v1.2.3


From 84d5946d49cf9552d0f1740ad62d0f126cb3b6a9 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Sun, 24 Jan 2016 21:17:43 -0800
Subject: i40e: Do not drop support for IPv6 VXLAN or GENEVE tunnels

All of the documentation in the datasheets for the XL710 do not call out
any reason to exclude support for IPv6 based tunnels.  As such I am
dropping the code that was excluding these tunnel types from having their
port numbers recognized.  This way we can take advantage of things such as
checksum offload for inner headers over IPv6 based VXLAN or GENEVE
tunnels.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 12 ------------
 1 file changed, 12 deletions(-)

(limited to 'drivers')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 0fa52ed1a896..955dc71d1236 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -8626,9 +8626,6 @@ static void i40e_add_vxlan_port(struct net_device *netdev,
 	u8 next_idx;
 	u8 idx;
 
-	if (sa_family == AF_INET6)
-		return;
-
 	idx = i40e_get_udp_port_idx(pf, port);
 
 	/* Check if port already exists */
@@ -8668,9 +8665,6 @@ static void i40e_del_vxlan_port(struct net_device *netdev,
 	struct i40e_pf *pf = vsi->back;
 	u8 idx;
 
-	if (sa_family == AF_INET6)
-		return;
-
 	idx = i40e_get_udp_port_idx(pf, port);
 
 	/* Check if port already exists */
@@ -8707,9 +8701,6 @@ static void i40e_add_geneve_port(struct net_device *netdev,
 	if (!(pf->flags & I40E_FLAG_GENEVE_OFFLOAD_CAPABLE))
 		return;
 
-	if (sa_family == AF_INET6)
-		return;
-
 	idx = i40e_get_udp_port_idx(pf, port);
 
 	/* Check if port already exists */
@@ -8751,9 +8742,6 @@ static void i40e_del_geneve_port(struct net_device *netdev,
 	struct i40e_pf *pf = vsi->back;
 	u8 idx;
 
-	if (sa_family == AF_INET6)
-		return;
-
 	if (!(pf->flags & I40E_FLAG_GENEVE_OFFLOAD_CAPABLE))
 		return;
 
-- 
cgit v1.2.3


From bc5d252b363cca63b7ddc1e20dd8b8b242631006 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Sun, 24 Jan 2016 21:17:50 -0800
Subject: i40e: Update feature flags to reflect newly enabled features

Recent changes should have enabled support for IPv6 based tunnels and
support for TSO with outer UDP checksums.  As such we can update the
feature flags to reflect that.

In addition we can clean-up the flags that aren't needed such as SCTP and
RXCSUM since having the bits there doesn't add any value.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

(limited to 'drivers')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 955dc71d1236..2f2b2d714f63 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -9032,10 +9032,14 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	np = netdev_priv(netdev);
 	np->vsi = vsi;
 
-	netdev->hw_enc_features |= NETIF_F_IP_CSUM	  |
-				   NETIF_F_GSO_UDP_TUNNEL |
-				   NETIF_F_GSO_GRE	  |
-				   NETIF_F_TSO		  |
+	netdev->hw_enc_features |= NETIF_F_IP_CSUM	       |
+				   NETIF_F_IPV6_CSUM	       |
+				   NETIF_F_TSO		       |
+				   NETIF_F_TSO6		       |
+				   NETIF_F_TSO_ECN	       |
+				   NETIF_F_GSO_GRE	       |
+				   NETIF_F_GSO_UDP_TUNNEL      |
+				   NETIF_F_GSO_UDP_TUNNEL_CSUM |
 				   0;
 
 	netdev->features = NETIF_F_SG		       |
@@ -9057,6 +9061,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 
 	if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
 		netdev->features |= NETIF_F_NTUPLE;
+	if (pf->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE)
+		netdev->features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
 
 	/* copy netdev features into list of user selectable features */
 	netdev->hw_features |= netdev->features;
-- 
cgit v1.2.3


From f608e6a60fc85e4f261daab5e7aac6225e2120d6 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Sun, 24 Jan 2016 21:17:57 -0800
Subject: i40evf: Update feature flags to reflect newly enabled features

Recent changes should have enabled support for IPv6 based tunnels and
support for TSO with outer UDP checksums.  As such we can update the
feature flags to reflect that.

In addition we can clean-up the flags that aren't needed such as SCTP and
RXCSUM since having the bits there doesn't add any value.

I also found one spot where we were setting the same flag twice.  It looks
like it was probably a git merge error that resulted in the line being
duplicated.  As such I have dropped it in this patch.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Acked-by: Anjali Singhai Jain <anjali.singhai@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40evf/i40evf_main.c | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

(limited to 'drivers')

diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 41369a30dfb8..3396fe32cc6d 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -2337,9 +2337,24 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
 			    NETIF_F_IPV6_CSUM |
 			    NETIF_F_TSO |
 			    NETIF_F_TSO6 |
+			    NETIF_F_TSO_ECN |
+			    NETIF_F_GSO_GRE	       |
+			    NETIF_F_GSO_UDP_TUNNEL |
 			    NETIF_F_RXCSUM |
 			    NETIF_F_GRO;
 
+	netdev->hw_enc_features |= NETIF_F_IP_CSUM	       |
+				   NETIF_F_IPV6_CSUM	       |
+				   NETIF_F_TSO		       |
+				   NETIF_F_TSO6		       |
+				   NETIF_F_TSO_ECN	       |
+				   NETIF_F_GSO_GRE	       |
+				   NETIF_F_GSO_UDP_TUNNEL      |
+				   NETIF_F_GSO_UDP_TUNNEL_CSUM;
+
+	if (adapter->flags & I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE)
+		netdev->features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+
 	/* copy netdev features into list of user selectable features */
 	netdev->hw_features |= netdev->features;
 	netdev->hw_features &= ~NETIF_F_RXCSUM;
@@ -2478,6 +2493,10 @@ static void i40evf_init_task(struct work_struct *work)
 	default:
 		goto err_alloc;
 	}
+
+	if (hw->mac.type == I40E_MAC_X722_VF)
+		adapter->flags |= I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE;
+
 	if (i40evf_process_config(adapter))
 		goto err_alloc;
 	adapter->current_op = I40E_VIRTCHNL_OP_UNKNOWN;
@@ -2518,10 +2537,6 @@ static void i40evf_init_task(struct work_struct *work)
 	if (err)
 		goto err_sw_init;
 	i40evf_map_rings_to_vectors(adapter);
-	if (adapter->vf_res->vf_offload_flags &
-		    I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR)
-		adapter->flags |= I40EVF_FLAG_WB_ON_ITR_CAPABLE;
-
 	if (adapter->vf_res->vf_offload_flags &
 	    I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR)
 		adapter->flags |= I40EVF_FLAG_WB_ON_ITR_CAPABLE;
-- 
cgit v1.2.3


From ffcc55c0c2a85835a4ac080bc1053c3a277b88e2 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Mon, 25 Jan 2016 19:32:54 -0800
Subject: i40e: Add support for ATR w/ IPv6 extension headers

This patch updates the code for determining the L4 protocol and L3 header
length so that when IPv6 extension headers are being used we can determine
the offset and type of the L4 protocol.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c | 28 +++++++++++++---------------
 1 file changed, 13 insertions(+), 15 deletions(-)

(limited to 'drivers')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 159fb6eed375..1d3afa7dda18 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2044,7 +2044,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	struct tcphdr *th;
 	unsigned int hlen;
 	u32 flex_ptype, dtype_cmd;
-	u8 l4_proto;
+	int l4_proto;
 	u16 i;
 
 	/* make sure ATR is enabled */
@@ -2062,25 +2062,23 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	if (!(tx_flags & (I40E_TX_FLAGS_IPV4 | I40E_TX_FLAGS_IPV6)))
 		return;
 
-	if (!(tx_flags & I40E_TX_FLAGS_UDP_TUNNEL)) {
-		/* snag network header to get L4 type and address */
-		hdr.network = skb_network_header(skb);
+	/* snag network header to get L4 type and address */
+	hdr.network = (tx_flags & I40E_TX_FLAGS_UDP_TUNNEL) ?
+		      skb_inner_network_header(skb) : skb_network_header(skb);
 
+	/* Note: tx_flags gets modified to reflect inner protocols in
+	 * tx_enable_csum function if encap is enabled.
+	 */
+	if (tx_flags & I40E_TX_FLAGS_IPV4) {
 		/* access ihl as u8 to avoid unaligned access on ia64 */
-		if (tx_flags & I40E_TX_FLAGS_IPV4)
-			hlen = (hdr.network[0] & 0x0F) << 2;
-		else
-			hlen = sizeof(struct ipv6hdr);
+		hlen = (hdr.network[0] & 0x0F) << 2;
+		l4_proto = hdr.ipv4->protocol;
 	} else {
-		hdr.network = skb_inner_network_header(skb);
-		hlen = skb_inner_network_header_len(skb);
+		hlen = hdr.network - skb->data;
+		l4_proto = ipv6_find_hdr(skb, &hlen, IPPROTO_TCP, NULL, NULL);
+		hlen -= hdr.network - skb->data;
 	}
 
-	/* Note: tx_flags gets modified to reflect inner protocols in
-	 * tx_enable_csum function if encap is enabled.
-	 */
-	l4_proto = (tx_flags & I40E_TX_FLAGS_IPV4) ? hdr.ipv4->protocol :
-						     hdr.ipv6->nexthdr;
 	if (l4_proto != IPPROTO_TCP)
 		return;
 
-- 
cgit v1.2.3