From: Moni Shoua <mo...@mellanox.com>
ib_ud_header_init() is used to format InfiniBand headers
in a buffer up to (but not with) BTH. For RoCE UDP ENCAP it is
required that this function would be able to build also IP and UDP
headers.
Signed-off-by: Moni Shoua <mo...@mellanox.com>
Signed-off-by: Matan Barak <mat...@mellanox.com>
---
drivers/infiniband/core/ud_header.c | 155 +++++++++++++++++++++++++++++---
drivers/infiniband/hw/mlx4/qp.c | 7 +-
drivers/infiniband/hw/mthca/mthca_qp.c | 2 +-
include/rdma/ib_pack.h | 45 ++++++++--
4 files changed, 188 insertions(+), 21 deletions(-)
diff --git a/drivers/infiniband/core/ud_header.c
b/drivers/infiniband/core/ud_header.c
index 72feee6..96697e7 100644
--- a/drivers/infiniband/core/ud_header.c
+++ b/drivers/infiniband/core/ud_header.c
@@ -35,6 +35,7 @@
#include <linux/string.h>
#include <linux/export.h>
#include <linux/if_ether.h>
+#include <linux/ip.h>
#include <rdma/ib_pack.h>
@@ -116,6 +117,72 @@ static const struct ib_field vlan_table[] = {
.size_bits = 16 }
};
+static const struct ib_field ip4_table[] = {
+ { STRUCT_FIELD(ip4, ver),
+ .offset_words = 0,
+ .offset_bits = 0,
+ .size_bits = 4 },
+ { STRUCT_FIELD(ip4, hdr_len),
+ .offset_words = 0,
+ .offset_bits = 4,
+ .size_bits = 4 },
+ { STRUCT_FIELD(ip4, tos),
+ .offset_words = 0,
+ .offset_bits = 8,
+ .size_bits = 8 },
+ { STRUCT_FIELD(ip4, tot_len),
+ .offset_words = 0,
+ .offset_bits = 16,
+ .size_bits = 16 },
+ { STRUCT_FIELD(ip4, id),
+ .offset_words = 1,
+ .offset_bits = 0,
+ .size_bits = 16 },
+ { STRUCT_FIELD(ip4, frag_off),
+ .offset_words = 1,
+ .offset_bits = 16,
+ .size_bits = 16 },
+ { STRUCT_FIELD(ip4, ttl),
+ .offset_words = 2,
+ .offset_bits = 0,
+ .size_bits = 8 },
+ { STRUCT_FIELD(ip4, protocol),
+ .offset_words = 2,
+ .offset_bits = 8,
+ .size_bits = 8 },
+ { STRUCT_FIELD(ip4, check),
+ .offset_words = 2,
+ .offset_bits = 16,
+ .size_bits = 16 },
+ { STRUCT_FIELD(ip4, saddr),
+ .offset_words = 3,
+ .offset_bits = 0,
+ .size_bits = 32 },
+ { STRUCT_FIELD(ip4, daddr),
+ .offset_words = 4,
+ .offset_bits = 0,
+ .size_bits = 32 }
+};
+
+static const struct ib_field udp_table[] = {
+ { STRUCT_FIELD(udp, sport),
+ .offset_words = 0,
+ .offset_bits = 0,
+ .size_bits = 16 },
+ { STRUCT_FIELD(udp, dport),
+ .offset_words = 0,
+ .offset_bits = 16,
+ .size_bits = 16 },
+ { STRUCT_FIELD(udp, length),
+ .offset_words = 1,
+ .offset_bits = 0,
+ .size_bits = 16 },
+ { STRUCT_FIELD(udp, csum),
+ .offset_words = 1,
+ .offset_bits = 16,
+ .size_bits = 16 }
+};
+
static const struct ib_field grh_table[] = {
{ STRUCT_FIELD(grh, ip_version),
.offset_words = 0,
@@ -213,26 +280,57 @@ static const struct ib_field deth_table[] = {
.size_bits = 24 }
};
+__be16 ib_ud_ip4_csum(struct ib_ud_header *header)
+{
+ struct iphdr iph;
+
+ iph.ihl = 5;
+ iph.version = 4;
+ iph.tos = header->ip4.tos;
+ iph.tot_len = header->ip4.tot_len;
+ iph.id = header->ip4.id;
+ iph.frag_off = header->ip4.frag_off;
+ iph.ttl = header->ip4.ttl;
+ iph.protocol = header->ip4.protocol;
+ iph.check = 0;
+ iph.saddr = header->ip4.saddr;
+ iph.daddr = header->ip4.daddr;
+
+ return ip_fast_csum((u8 *)&iph, iph.ihl);
+}
+EXPORT_SYMBOL(ib_ud_ip4_csum);
+
/**
* ib_ud_header_init - Initialize UD header structure
* @payload_bytes:Length of packet payload
* @lrh_present: specify if LRH is present
* @eth_present: specify if Eth header is present
* @vlan_present: packet is tagged vlan
- * @grh_present:GRH flag (if non-zero, GRH will be included)
+ * @grh_present: GRH flag (if non-zero, GRH will be included)
+ * @ip_version: if non-zero, IP header, V4 or V6, will be included
+ * @udp_present :if non-zero, UDP header will be included
* @immediate_present: specify if immediate data is present
* @header:Structure to initialize
*/
-void ib_ud_header_init(int payload_bytes,
- int lrh_present,
- int eth_present,
- int vlan_present,
- int grh_present,
- int immediate_present,
- struct ib_ud_header *header)
+int ib_ud_header_init(int payload_bytes,
+ int lrh_present,
+ int eth_present,
+ int vlan_present,
+ int grh_present,
+ int ip_version,
+ int udp_present,
+ int immediate_present,
+ struct ib_ud_header *header)
{
+ grh_present = grh_present && !ip_version;
memset(header, 0, sizeof *header);
+ /*
+ * UDP header without IP header doesn't make sense
+ */
+ if (udp_present && ip_version != 4 && ip_version != 6)
+ return -EINVAL;
+
if (lrh_present) {
u16 packet_length;
@@ -252,7 +350,7 @@ void ib_ud_header_init(int
payload_bytes,
if (vlan_present)
header->eth.type = cpu_to_be16(ETH_P_8021Q);
- if (grh_present) {
+ if (ip_version == 6 || grh_present) {
header->grh.ip_version = 6;
header->grh.payload_length =
cpu_to_be16((IB_BTH_BYTES +
@@ -260,8 +358,30 @@ void ib_ud_header_init(int
payload_bytes,
payload_bytes +
4 + /* ICRC */
3) & ~3); /* round up */
- header->grh.next_header = 0x1b;
+ header->grh.next_header = udp_present ? IPPROTO_UDP : 0x1b;
+ }
+
+ if (ip_version == 4) {
+ int udp_bytes = udp_present ? IB_UDP_BYTES : 0;
+
+ header->ip4.ver = 4; /* version 4 */
+ header->ip4.hdr_len = 5; /* 5 words */
+ header->ip4.tot_len =
+ cpu_to_be16(IB_IP4_BYTES +
+ udp_bytes +
+ IB_BTH_BYTES +
+ IB_DETH_BYTES +
+ payload_bytes +
+ 4); /* ICRC */
+ header->ip4.protocol = IPPROTO_UDP;
}
+ if (udp_present && ip_version)
+ header->udp.length =
+ cpu_to_be16(IB_UDP_BYTES +
+ IB_BTH_BYTES +
+ IB_DETH_BYTES +
+ payload_bytes +
+ 4); /* ICRC */
if (immediate_present)
header->bth.opcode =
IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE;
@@ -273,8 +393,11 @@ void ib_ud_header_init(int
payload_bytes,
header->lrh_present = lrh_present;
header->eth_present = eth_present;
header->vlan_present = vlan_present;
- header->grh_present = grh_present;
+ header->grh_present = grh_present || (ip_version == 6);
+ header->ipv4_present = ip_version == 4;
+ header->udp_present = udp_present;
header->immediate_present = immediate_present;
+ return 0;
}
EXPORT_SYMBOL(ib_ud_header_init);
@@ -311,6 +434,16 @@ int ib_ud_header_pack(struct ib_ud_header *header,
&header->grh, buf + len);
len += IB_GRH_BYTES;
}
+ if (header->ipv4_present) {
+ ib_pack(ip4_table, ARRAY_SIZE(ip4_table),
+ &header->ip4, buf + len);
+ len += IB_IP4_BYTES;
+ }
+ if (header->udp_present) {
+ ib_pack(udp_table, ARRAY_SIZE(udp_table),
+ &header->udp, buf + len);
+ len += IB_UDP_BYTES;
+ }
ib_pack(bth_table, ARRAY_SIZE(bth_table),
&header->bth, buf + len);
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 13eaaf4..6049644 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -2168,7 +2168,7 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp,
if (sqp->qp.mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_SMI_OWNER)
send_size += sizeof (struct mlx4_ib_tunnel_header);
- ib_ud_header_init(send_size, 1, 0, 0, 0, 0, &sqp->ud_header);
+ ib_ud_header_init(send_size, 1, 0, 0, 0, 0, 0, 0, &sqp->ud_header);
if (sqp->qp.mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_SMI_OWNER) {
sqp->ud_header.lrh.service_level =
@@ -2314,7 +2314,10 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp,
struct ib_ud_wr *wr,
is_vlan = 1;
}
}
- ib_ud_header_init(send_size, !is_eth, is_eth, is_vlan, is_grh, 0,
&sqp->ud_header);
+ err = ib_ud_header_init(send_size, !is_eth, is_eth, is_vlan, is_grh,
+ 0, 0, 0, &sqp->ud_header);
+ if (err)
+ return err;
if (!is_eth) {
sqp->ud_header.lrh.service_level =
diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c
b/drivers/infiniband/hw/mthca/mthca_qp.c
index 35fe506..96e5fb9 100644
--- a/drivers/infiniband/hw/mthca/mthca_qp.c
+++ b/drivers/infiniband/hw/mthca/mthca_qp.c
@@ -1485,7 +1485,7 @@ static int build_mlx_header(struct mthca_dev *dev, struct
mthca_sqp *sqp,
u16 pkey;
ib_ud_header_init(256, /* assume a MAD */ 1, 0, 0,
- mthca_ah_grh_present(to_mah(wr->ah)), 0,
+ mthca_ah_grh_present(to_mah(wr->ah)), 0, 0, 0,
&sqp->ud_header);
err = mthca_read_ah(dev, to_mah(wr->ah), &sqp->ud_header);
diff --git a/include/rdma/ib_pack.h b/include/rdma/ib_pack.h
index e99d8f9..a193081 100644
--- a/include/rdma/ib_pack.h
+++ b/include/rdma/ib_pack.h
@@ -41,6 +41,8 @@ enum {
IB_ETH_BYTES = 14,
IB_VLAN_BYTES = 4,
IB_GRH_BYTES = 40,
+ IB_IP4_BYTES = 20,
+ IB_UDP_BYTES = 8,
IB_BTH_BYTES = 12,
IB_DETH_BYTES = 8
};
@@ -223,6 +225,27 @@ struct ib_unpacked_eth {
__be16 type;
};
+struct ib_unpacked_ip4 {
+ u8 ver;
+ u8 hdr_len;
+ u8 tos;
+ __be16 tot_len;
+ __be16 id;
+ __be16 frag_off;
+ u8 ttl;
+ u8 protocol;
+ __be16 check;
+ __be32 saddr;
+ __be32 daddr;
+};
+
+struct ib_unpacked_udp {
+ __be16 sport;
+ __be16 dport;
+ __be16 length;
+ __be16 csum;
+};
+
struct ib_unpacked_vlan {
__be16 tag;
__be16 type;
@@ -237,6 +260,10 @@ struct ib_ud_header {
struct ib_unpacked_vlan vlan;
int grh_present;
struct ib_unpacked_grh grh;
+ int ipv4_present;
+ struct ib_unpacked_ip4 ip4;
+ int udp_present;
+ struct ib_unpacked_udp udp;
struct ib_unpacked_bth bth;
struct ib_unpacked_deth deth;
int immediate_present;
@@ -253,13 +280,17 @@ void ib_unpack(const struct ib_field *desc,
void *buf,
void *structure);
-void ib_ud_header_init(int payload_bytes,
- int lrh_present,
- int eth_present,
- int vlan_present,
- int grh_present,
- int immediate_present,
- struct ib_ud_header *header);
+__be16 ib_ud_ip4_csum(struct ib_ud_header *header);
+
+int ib_ud_header_init(int payload_bytes,
+ int lrh_present,
+ int eth_present,
+ int vlan_present,
+ int grh_present,
+ int ip_version,
+ int udp_present,
+ int immediate_present,
+ struct ib_ud_header *header);
int ib_ud_header_pack(struct ib_ud_header *header,
void *buf);
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
