@@ -63,7 +63,7 @@ static __be32 rxe_crc32(struct rxe_dev *rxe, __be32 crc, void *next, size_t len)
/**
* rxe_icrc_hdr() - Compute the partial ICRC for the network and transport
- * headers of a packet.
+ * headers of a packet.
* @skb: packet buffer
* @pkt: packet information
*
@@ -129,6 +129,56 @@ static __be32 rxe_icrc_hdr(struct sk_buff *skb, struct rxe_pkt_info *pkt)
return crc;
}
+/**
+ * rxe_icrc_payload() - Compute the ICRC for a packet payload and also
+ * compute the address of the icrc in the packet.
+ * @skb: packet buffer
+ * @pkt: packet information
+ * @icrc: current icrc i.e. including headers
+ * @icrcp: returned pointer to icrc in skb
+ *
+ * Return: 0 if the values match else an error
+ */
+static __be32 rxe_icrc_payload(struct sk_buff *skb, struct rxe_pkt_info *pkt,
+ __be32 icrc, __be32 **icrcp)
+{
+ struct skb_shared_info *shinfo = skb_shinfo(skb);
+ skb_frag_t *frag;
+ u8 *addr;
+ int hdr_len;
+ int len;
+ int i;
+
+ /* handle any payload left in the linear buffer */
+ hdr_len = rxe_opcode[pkt->opcode].length;
+ addr = pkt->hdr + hdr_len;
+ len = skb_tail_pointer(skb) - skb_transport_header(skb)
+ - sizeof(struct udphdr) - hdr_len;
+ if (!shinfo->nr_frags) {
+ len -= RXE_ICRC_SIZE;
+ *icrcp = (__be32 *)(addr + len);
+ }
+ if (len > 0)
+ icrc = rxe_crc32(pkt->rxe, icrc, payload_addr(pkt), len);
+ WARN_ON(len < 0);
+
+ /* handle any payload in frags */
+ for (i = 0; i < shinfo->nr_frags; i++) {
+ frag = &shinfo->frags[i];
+ addr = page_to_virt(frag->bv_page) + frag->bv_offset;
+ len = frag->bv_len;
+ if (i == shinfo->nr_frags - 1) {
+ len -= RXE_ICRC_SIZE;
+ *icrcp = (__be32 *)(addr + len);
+ }
+ if (len > 0)
+ icrc = rxe_crc32(pkt->rxe, icrc, addr, len);
+ WARN_ON(len < 0);
+ }
+
+ return icrc;
+}
+
/**
* rxe_icrc_check() - Compute ICRC for a packet and compare to the ICRC
* delivered in the packet.
@@ -143,13 +193,11 @@ int rxe_icrc_check(struct sk_buff *skb, struct rxe_pkt_info *pkt)
__be32 pkt_icrc;
__be32 icrc;
- icrcp = (__be32 *)(pkt->hdr + pkt->paylen - RXE_ICRC_SIZE);
- pkt_icrc = *icrcp;
-
icrc = rxe_icrc_hdr(skb, pkt);
- icrc = rxe_crc32(pkt->rxe, icrc, (u8 *)payload_addr(pkt),
- payload_size(pkt) + bth_pad(pkt));
+ icrc = rxe_icrc_payload(skb, pkt, icrc, &icrcp);
+
icrc = ~icrc;
+ pkt_icrc = *icrcp;
if (unlikely(icrc != pkt_icrc))
return -EINVAL;
@@ -167,9 +215,8 @@ void rxe_icrc_generate(struct sk_buff *skb, struct rxe_pkt_info *pkt)
__be32 *icrcp;
__be32 icrc;
- icrcp = (__be32 *)(pkt->hdr + pkt->paylen - RXE_ICRC_SIZE);
icrc = rxe_icrc_hdr(skb, pkt);
- icrc = rxe_crc32(pkt->rxe, icrc, (u8 *)payload_addr(pkt),
- payload_size(pkt) + bth_pad(pkt));
+ icrc = rxe_icrc_payload(skb, pkt, icrc, &icrcp);
+
*icrcp = ~icrc;
}
@@ -134,32 +134,51 @@ static int rxe_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
struct rxe_dev *rxe;
struct net_device *ndev = skb->dev;
struct rxe_pkt_info *pkt = SKB_TO_PKT(skb);
+ u8 opcode;
+ u8 buf[1];
+ u8 *p;
- /* takes a reference on rxe->ib_dev
- * drop when skb is freed
- */
+ /* Takes a reference on rxe->ib_dev. Drop when skb is freed */
rxe = rxe_get_dev_from_net(ndev);
if (!rxe && is_vlan_dev(ndev))
rxe = rxe_get_dev_from_net(vlan_dev_real_dev(ndev));
if (!rxe)
- goto drop;
+ goto err_drop;
- if (skb_linearize(skb)) {
- ib_device_put(&rxe->ib_dev);
- goto drop;
+ /* Get bth opcode out of skb */
+ p = skb_header_pointer(skb, sizeof(struct udphdr), 1, buf);
+ if (!p)
+ goto err_device_put;
+ opcode = *p;
+
+ /* If using fragmented skbs make sure roce headers
+ * are in linear buffer else make skb linear
+ */
+ if (rxe_use_sg && skb_is_nonlinear(skb)) {
+ int delta = rxe_opcode[opcode].length -
+ (skb_headlen(skb) - sizeof(struct udphdr));
+
+ if (delta > 0 && !__pskb_pull_tail(skb, delta))
+ goto err_device_put;
+ } else {
+ if (skb_linearize(skb))
+ goto err_device_put;
}
udph = udp_hdr(skb);
pkt->rxe = rxe;
pkt->port_num = 1;
pkt->hdr = (u8 *)(udph + 1);
- pkt->mask = RXE_GRH_MASK;
+ pkt->mask = rxe_opcode[opcode].mask | RXE_GRH_MASK;
pkt->paylen = be16_to_cpu(udph->len) - sizeof(*udph);
rxe_rcv(skb);
return 0;
-drop:
+
+err_device_put:
+ ib_device_put(&rxe->ib_dev);
+err_drop:
kfree_skb(skb);
return 0;
@@ -385,21 +404,32 @@ static int rxe_send(struct sk_buff *skb, struct rxe_pkt_info *pkt)
*/
static int rxe_loopback(struct sk_buff *skb, struct rxe_pkt_info *pkt)
{
- memcpy(SKB_TO_PKT(skb), pkt, sizeof(*pkt));
+ struct rxe_pkt_info *newpkt;
+ int err;
+ /* make loopback line up with rxe_udp_encap_recv */
if (skb->protocol == htons(ETH_P_IP))
skb_pull(skb, sizeof(struct iphdr));
else
skb_pull(skb, sizeof(struct ipv6hdr));
+ skb_reset_transport_header(skb);
+
+ newpkt = SKB_TO_PKT(skb);
+ memcpy(newpkt, pkt, sizeof(*newpkt));
+ newpkt->hdr = skb_transport_header(skb) + sizeof(struct udphdr);
if (WARN_ON(!ib_device_try_get(&pkt->rxe->ib_dev))) {
kfree_skb(skb);
- return -EIO;
+ err = -EINVAL;
+ goto drop;
}
rxe_rcv(skb);
-
return 0;
+
+drop:
+ kfree_skb(skb);
+ return err;
}
int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt,
@@ -415,6 +445,7 @@ int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt,
goto drop;
}
+ /* skb->data points at IP header */
rxe_icrc_generate(skb, pkt);
if (pkt->mask & RXE_LOOPBACK_MASK)
@@ -329,6 +329,7 @@ void rxe_rcv(struct sk_buff *skb)
if (unlikely(err))
goto drop;
+ /* skb->data points at UDP header */
err = rxe_icrc_check(skb, pkt);
if (unlikely(err))
goto drop;
Extend the subroutines rxe_icrc_generate() and rxe_icrc_check() to support skb frags. This is in preparation for supporting fragmented skbs. Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com> --- drivers/infiniband/sw/rxe/rxe_icrc.c | 65 ++++++++++++++++++++++++---- drivers/infiniband/sw/rxe/rxe_net.c | 55 ++++++++++++++++++----- drivers/infiniband/sw/rxe/rxe_recv.c | 1 + 3 files changed, 100 insertions(+), 21 deletions(-)