i40e/i40evf: Replace header pointers with unions of pointers in Tx checksum path

Orabug: 22342532

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>
(cherry picked from commit b96b78f2b789ab8398e7ec0111bb8b4588ed42bf)
Signed-off-by: Brian Maly <brian.maly@oracle.com>

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index f9c75db99684ca404135da874b236d9325bf1037..fce195107f030df5a3d14f2b0de20737cf57d65c 100644 (file)
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2391,12 +2391,21 @@ 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) {
@@ -2410,10 +2419,10 @@ 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) {
@@ -2433,20 +2442,15 @@ 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.
                 */
@@ -2455,26 +2459,23 @@ 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 2a69af57ceae3a4ce0e48e0e09055965091de0a4..3592067c7a83580e64ecbeeae7f364b0e1b5b7c1 100644 (file)
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1608,12 +1608,21 @@ 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) {
@@ -1624,10 +1633,10 @@ 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) {
@@ -1647,21 +1656,15 @@ 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.
                 */
@@ -1670,26 +1673,23 @@ 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: