* [dpdk-dev] [PATCH 1/3] net/mlx5: fix Rx checksum macros
2016-11-02 10:39 [dpdk-dev] [PATCH 0/3] fix Rx checksum offloads Nelio Laranjeiro
@ 2016-11-02 10:39 ` Nelio Laranjeiro
2016-11-02 10:39 ` [dpdk-dev] [PATCH 2/3] net/mlx5: define explicit fields for Rx offloads Nelio Laranjeiro
` (2 subsequent siblings)
3 siblings, 0 replies; 6+ messages in thread
From: Nelio Laranjeiro @ 2016-11-02 10:39 UTC (permalink / raw)
To: dev
Add missing:
- MLX5_CQE_RX_IPV4_PACKET
- MLX5_CQE_RX_IPV6_PACKET
- MLX5_CQE_RX_OUTER_IPV4_PACKET
- MLX5_CQE_RX_OUTER_IPV6_PACKET
- MLX5_CQE_RX_TUNNEL_PACKET
- MLX5_CQE_RX_OUTER_IP_CSUM_OK
- MLX5_CQE_RX_OUTER_TCP_UDP_CSUM_OK
Fixes: 51a50a3d9b8f ("net/mlx5: add definitions for data path without Verbs")
Signed-off-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
---
drivers/net/mlx5/mlx5_prm.h | 21 +++++++++++++++++++++
drivers/net/mlx5/mlx5_rxtx.c | 16 ++++++++--------
2 files changed, 29 insertions(+), 8 deletions(-)
diff --git a/drivers/net/mlx5/mlx5_prm.h b/drivers/net/mlx5/mlx5_prm.h
index 90b47f0..500f25a 100644
--- a/drivers/net/mlx5/mlx5_prm.h
+++ b/drivers/net/mlx5/mlx5_prm.h
@@ -84,6 +84,27 @@
#define MLX5_OPCODE_TSO MLX5_OPCODE_LSO_MPW /* Compat with OFED 3.3. */
#endif
+/* IPv4 packet. */
+#define MLX5_CQE_RX_IPV4_PACKET (1u << 2)
+
+/* IPv6 packet. */
+#define MLX5_CQE_RX_IPV6_PACKET (1u << 3)
+
+/* Outer IPv4 packet. */
+#define MLX5_CQE_RX_OUTER_IPV4_PACKET (1u << 7)
+
+/* Outer IPv6 packet. */
+#define MLX5_CQE_RX_OUTER_IPV6_PACKET (1u << 8)
+
+/* Tunnel packet bit in the CQE. */
+#define MLX5_CQE_RX_TUNNEL_PACKET (1u << 4)
+
+/* Outer IP checksum OK. */
+#define MLX5_CQE_RX_OUTER_IP_CSUM_OK (1u << 5)
+
+/* Outer UDP header and checksum OK. */
+#define MLX5_CQE_RX_OUTER_TCP_UDP_CSUM_OK (1u << 6)
+
/* Subset of struct mlx5_wqe_eth_seg. */
struct mlx5_wqe_eth_seg_small {
uint32_t rsvd0;
diff --git a/drivers/net/mlx5/mlx5_rxtx.c b/drivers/net/mlx5/mlx5_rxtx.c
index ba8e202..7ebe557 100644
--- a/drivers/net/mlx5/mlx5_rxtx.c
+++ b/drivers/net/mlx5/mlx5_rxtx.c
@@ -1096,19 +1096,19 @@ rxq_cq_to_pkt_type(volatile struct mlx5_cqe64 *cqe)
uint8_t flags = cqe->l4_hdr_type_etc;
uint8_t info = cqe->rsvd0[0];
- if (info & IBV_EXP_CQ_RX_TUNNEL_PACKET)
+ if (info & MLX5_CQE_RX_TUNNEL_PACKET)
pkt_type =
TRANSPOSE(flags,
- IBV_EXP_CQ_RX_OUTER_IPV4_PACKET,
+ MLX5_CQE_RX_OUTER_IPV4_PACKET,
RTE_PTYPE_L3_IPV4) |
TRANSPOSE(flags,
- IBV_EXP_CQ_RX_OUTER_IPV6_PACKET,
+ MLX5_CQE_RX_OUTER_IPV6_PACKET,
RTE_PTYPE_L3_IPV6) |
TRANSPOSE(flags,
- IBV_EXP_CQ_RX_IPV4_PACKET,
+ MLX5_CQE_RX_IPV4_PACKET,
RTE_PTYPE_INNER_L3_IPV4) |
TRANSPOSE(flags,
- IBV_EXP_CQ_RX_IPV6_PACKET,
+ MLX5_CQE_RX_IPV6_PACKET,
RTE_PTYPE_INNER_L3_IPV6);
else
pkt_type =
@@ -1256,13 +1256,13 @@ rxq_cq_to_ol_flags(struct rxq *rxq, volatile struct mlx5_cqe64 *cqe)
* of PKT_RX_EIP_CKSUM_BAD because the latter is not functional
* (its value is 0).
*/
- if ((info & IBV_EXP_CQ_RX_TUNNEL_PACKET) && (rxq->csum_l2tun))
+ if ((info & MLX5_CQE_RX_TUNNEL_PACKET) && (rxq->csum_l2tun))
ol_flags |=
TRANSPOSE(~cqe->l4_hdr_type_etc,
- IBV_EXP_CQ_RX_OUTER_IP_CSUM_OK,
+ MLX5_CQE_RX_OUTER_IP_CSUM_OK,
PKT_RX_IP_CKSUM_BAD) |
TRANSPOSE(~cqe->l4_hdr_type_etc,
- IBV_EXP_CQ_RX_OUTER_TCP_UDP_CSUM_OK,
+ MLX5_CQE_RX_OUTER_TCP_UDP_CSUM_OK,
PKT_RX_L4_CKSUM_BAD);
return ol_flags;
}
--
2.1.4
^ permalink raw reply [flat|nested] 6+ messages in thread* [dpdk-dev] [PATCH 2/3] net/mlx5: define explicit fields for Rx offloads
2016-11-02 10:39 [dpdk-dev] [PATCH 0/3] fix Rx checksum offloads Nelio Laranjeiro
2016-11-02 10:39 ` [dpdk-dev] [PATCH 1/3] net/mlx5: fix Rx checksum macros Nelio Laranjeiro
@ 2016-11-02 10:39 ` Nelio Laranjeiro
2016-11-02 10:39 ` [dpdk-dev] [PATCH 3/3] net/mlx: fix support for new Rx checksum flags Nelio Laranjeiro
2016-11-02 15:57 ` [dpdk-dev] [PATCH 0/3] fix Rx checksum offloads Adrien Mazarguil
3 siblings, 0 replies; 6+ messages in thread
From: Nelio Laranjeiro @ 2016-11-02 10:39 UTC (permalink / raw)
To: dev
This commit redefines the completion queue element structure as the
original lacks the required fields.
Signed-off-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
---
drivers/net/mlx5/mlx5_prm.h | 16 ++++++++++++-
drivers/net/mlx5/mlx5_rxtx.c | 56 +++++++++++++++++++++-----------------------
2 files changed, 42 insertions(+), 30 deletions(-)
diff --git a/drivers/net/mlx5/mlx5_prm.h b/drivers/net/mlx5/mlx5_prm.h
index 500f25a..7f31a2f 100644
--- a/drivers/net/mlx5/mlx5_prm.h
+++ b/drivers/net/mlx5/mlx5_prm.h
@@ -158,7 +158,21 @@ struct mlx5_cqe {
#if (RTE_CACHE_LINE_SIZE == 128)
uint8_t padding[64];
#endif
- struct mlx5_cqe64 cqe64;
+ uint8_t pkt_info;
+ uint8_t rsvd0[11];
+ uint32_t rx_hash_res;
+ uint8_t rx_hash_type;
+ uint8_t rsvd1[11];
+ uint8_t hds_ip_ext;
+ uint8_t l4_hdr_type_etc;
+ uint16_t vlan_info;
+ uint8_t rsvd2[12];
+ uint32_t byte_cnt;
+ uint64_t timestamp;
+ uint8_t rsvd3[4];
+ uint16_t wqe_counter;
+ uint8_t rsvd4;
+ uint8_t op_own;
};
#endif /* RTE_PMD_MLX5_PRM_H_ */
diff --git a/drivers/net/mlx5/mlx5_rxtx.c b/drivers/net/mlx5/mlx5_rxtx.c
index 7ebe557..b6e0d65 100644
--- a/drivers/net/mlx5/mlx5_rxtx.c
+++ b/drivers/net/mlx5/mlx5_rxtx.c
@@ -83,10 +83,10 @@
* 0 the first time.
*/
static inline int
-check_cqe64_seen(volatile struct mlx5_cqe64 *cqe)
+check_cqe_seen(volatile struct mlx5_cqe *cqe)
{
static const uint8_t magic[] = "seen";
- volatile uint8_t (*buf)[sizeof(cqe->rsvd40)] = &cqe->rsvd40;
+ volatile uint8_t (*buf)[sizeof(cqe->rsvd3)] = &cqe->rsvd3;
int ret = 1;
unsigned int i;
@@ -101,9 +101,9 @@ check_cqe64_seen(volatile struct mlx5_cqe64 *cqe)
#endif /* NDEBUG */
static inline int
-check_cqe64(volatile struct mlx5_cqe64 *cqe,
- unsigned int cqes_n, const uint16_t ci)
- __attribute__((always_inline));
+check_cqe(volatile struct mlx5_cqe *cqe,
+ unsigned int cqes_n, const uint16_t ci)
+ __attribute__((always_inline));
/**
* Check whether CQE is valid.
@@ -119,8 +119,8 @@ check_cqe64(volatile struct mlx5_cqe64 *cqe,
* 0 on success, 1 on failure.
*/
static inline int
-check_cqe64(volatile struct mlx5_cqe64 *cqe,
- unsigned int cqes_n, const uint16_t ci)
+check_cqe(volatile struct mlx5_cqe *cqe,
+ unsigned int cqes_n, const uint16_t ci)
{
uint16_t idx = ci & cqes_n;
uint8_t op_own = cqe->op_own;
@@ -138,14 +138,14 @@ check_cqe64(volatile struct mlx5_cqe64 *cqe,
if ((syndrome == MLX5_CQE_SYNDROME_LOCAL_LENGTH_ERR) ||
(syndrome == MLX5_CQE_SYNDROME_REMOTE_ABORTED_ERR))
return 0;
- if (!check_cqe64_seen(cqe))
+ if (!check_cqe_seen(cqe))
ERROR("unexpected CQE error %u (0x%02x)"
" syndrome 0x%02x",
op_code, op_code, syndrome);
return 1;
} else if ((op_code != MLX5_CQE_RESP_SEND) &&
(op_code != MLX5_CQE_REQ)) {
- if (!check_cqe64_seen(cqe))
+ if (!check_cqe_seen(cqe))
ERROR("unexpected CQE opcode %u (0x%02x)",
op_code, op_code);
return 1;
@@ -174,25 +174,25 @@ txq_complete(struct txq *txq)
uint16_t elts_free = txq->elts_tail;
uint16_t elts_tail;
uint16_t cq_ci = txq->cq_ci;
- volatile struct mlx5_cqe64 *cqe = NULL;
+ volatile struct mlx5_cqe *cqe = NULL;
volatile struct mlx5_wqe *wqe;
do {
- volatile struct mlx5_cqe64 *tmp;
+ volatile struct mlx5_cqe *tmp;
- tmp = &(*txq->cqes)[cq_ci & cqe_cnt].cqe64;
- if (check_cqe64(tmp, cqe_n, cq_ci))
+ tmp = &(*txq->cqes)[cq_ci & cqe_cnt];
+ if (check_cqe(tmp, cqe_n, cq_ci))
break;
cqe = tmp;
#ifndef NDEBUG
if (MLX5_CQE_FORMAT(cqe->op_own) == MLX5_COMPRESSED) {
- if (!check_cqe64_seen(cqe))
+ if (!check_cqe_seen(cqe))
ERROR("unexpected compressed CQE, TX stopped");
return;
}
if ((MLX5_CQE_OPCODE(cqe->op_own) == MLX5_CQE_RESP_ERR) ||
(MLX5_CQE_OPCODE(cqe->op_own) == MLX5_CQE_REQ_ERR)) {
- if (!check_cqe64_seen(cqe))
+ if (!check_cqe_seen(cqe))
ERROR("unexpected error CQE, TX stopped");
return;
}
@@ -1090,13 +1090,12 @@ mlx5_tx_burst_mpw_inline(void *dpdk_txq, struct rte_mbuf **pkts,
* Packet type for struct rte_mbuf.
*/
static inline uint32_t
-rxq_cq_to_pkt_type(volatile struct mlx5_cqe64 *cqe)
+rxq_cq_to_pkt_type(volatile struct mlx5_cqe *cqe)
{
uint32_t pkt_type;
uint8_t flags = cqe->l4_hdr_type_etc;
- uint8_t info = cqe->rsvd0[0];
- if (info & MLX5_CQE_RX_TUNNEL_PACKET)
+ if (cqe->pkt_info & MLX5_CQE_RX_TUNNEL_PACKET)
pkt_type =
TRANSPOSE(flags,
MLX5_CQE_RX_OUTER_IPV4_PACKET,
@@ -1138,7 +1137,7 @@ rxq_cq_to_pkt_type(volatile struct mlx5_cqe64 *cqe)
* with error.
*/
static inline int
-mlx5_rx_poll_len(struct rxq *rxq, volatile struct mlx5_cqe64 *cqe,
+mlx5_rx_poll_len(struct rxq *rxq, volatile struct mlx5_cqe *cqe,
uint16_t cqe_cnt, uint32_t *rss_hash)
{
struct rxq_zip *zip = &rxq->zip;
@@ -1149,7 +1148,7 @@ mlx5_rx_poll_len(struct rxq *rxq, volatile struct mlx5_cqe64 *cqe,
if (zip->ai) {
volatile struct mlx5_mini_cqe8 (*mc)[8] =
(volatile struct mlx5_mini_cqe8 (*)[8])
- (uintptr_t)(&(*rxq->cqes)[zip->ca & cqe_cnt].cqe64);
+ (uintptr_t)(&(*rxq->cqes)[zip->ca & cqe_cnt]);
len = ntohl((*mc)[zip->ai & 7].byte_cnt);
*rss_hash = ntohl((*mc)[zip->ai & 7].rx_hash_result);
@@ -1167,7 +1166,7 @@ mlx5_rx_poll_len(struct rxq *rxq, volatile struct mlx5_cqe64 *cqe,
uint16_t end = zip->cq_ci;
while (idx != end) {
- (*rxq->cqes)[idx & cqe_cnt].cqe64.op_own =
+ (*rxq->cqes)[idx & cqe_cnt].op_own =
MLX5_CQE_INVALIDATE;
++idx;
}
@@ -1179,7 +1178,7 @@ mlx5_rx_poll_len(struct rxq *rxq, volatile struct mlx5_cqe64 *cqe,
int ret;
int8_t op_own;
- ret = check_cqe64(cqe, cqe_n, rxq->cq_ci);
+ ret = check_cqe(cqe, cqe_n, rxq->cq_ci);
if (unlikely(ret == 1))
return 0;
++rxq->cq_ci;
@@ -1188,7 +1187,7 @@ mlx5_rx_poll_len(struct rxq *rxq, volatile struct mlx5_cqe64 *cqe,
volatile struct mlx5_mini_cqe8 (*mc)[8] =
(volatile struct mlx5_mini_cqe8 (*)[8])
(uintptr_t)(&(*rxq->cqes)[rxq->cq_ci &
- cqe_cnt].cqe64);
+ cqe_cnt]);
/* Fix endianness. */
zip->cqe_cnt = ntohl(cqe->byte_cnt);
@@ -1232,12 +1231,11 @@ mlx5_rx_poll_len(struct rxq *rxq, volatile struct mlx5_cqe64 *cqe,
* Offload flags (ol_flags) for struct rte_mbuf.
*/
static inline uint32_t
-rxq_cq_to_ol_flags(struct rxq *rxq, volatile struct mlx5_cqe64 *cqe)
+rxq_cq_to_ol_flags(struct rxq *rxq, volatile struct mlx5_cqe *cqe)
{
uint32_t ol_flags = 0;
uint8_t l3_hdr = (cqe->l4_hdr_type_etc) & MLX5_CQE_L3_HDR_TYPE_MASK;
uint8_t l4_hdr = (cqe->l4_hdr_type_etc) & MLX5_CQE_L4_HDR_TYPE_MASK;
- uint8_t info = cqe->rsvd0[0];
if ((l3_hdr == MLX5_CQE_L3_HDR_TYPE_IPV4) ||
(l3_hdr == MLX5_CQE_L3_HDR_TYPE_IPV6))
@@ -1256,7 +1254,7 @@ rxq_cq_to_ol_flags(struct rxq *rxq, volatile struct mlx5_cqe64 *cqe)
* of PKT_RX_EIP_CKSUM_BAD because the latter is not functional
* (its value is 0).
*/
- if ((info & MLX5_CQE_RX_TUNNEL_PACKET) && (rxq->csum_l2tun))
+ if ((cqe->pkt_info & MLX5_CQE_RX_TUNNEL_PACKET) && (rxq->csum_l2tun))
ol_flags |=
TRANSPOSE(~cqe->l4_hdr_type_etc,
MLX5_CQE_RX_OUTER_IP_CSUM_OK,
@@ -1289,8 +1287,8 @@ mlx5_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n)
const unsigned int sges_n = rxq->sges_n;
struct rte_mbuf *pkt = NULL;
struct rte_mbuf *seg = NULL;
- volatile struct mlx5_cqe64 *cqe =
- &(*rxq->cqes)[rxq->cq_ci & cqe_cnt].cqe64;
+ volatile struct mlx5_cqe *cqe =
+ &(*rxq->cqes)[rxq->cq_ci & cqe_cnt];
unsigned int i = 0;
unsigned int rq_ci = rxq->rq_ci << sges_n;
int len; /* keep its value across iterations. */
@@ -1327,7 +1325,7 @@ mlx5_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n)
break;
}
if (!pkt) {
- cqe = &(*rxq->cqes)[rxq->cq_ci & cqe_cnt].cqe64;
+ cqe = &(*rxq->cqes)[rxq->cq_ci & cqe_cnt];
len = mlx5_rx_poll_len(rxq, cqe, cqe_cnt,
&rss_hash_res);
if (!len) {
--
2.1.4
^ permalink raw reply [flat|nested] 6+ messages in thread* [dpdk-dev] [PATCH 3/3] net/mlx: fix support for new Rx checksum flags
2016-11-02 10:39 [dpdk-dev] [PATCH 0/3] fix Rx checksum offloads Nelio Laranjeiro
2016-11-02 10:39 ` [dpdk-dev] [PATCH 1/3] net/mlx5: fix Rx checksum macros Nelio Laranjeiro
2016-11-02 10:39 ` [dpdk-dev] [PATCH 2/3] net/mlx5: define explicit fields for Rx offloads Nelio Laranjeiro
@ 2016-11-02 10:39 ` Nelio Laranjeiro
2016-11-02 15:57 ` [dpdk-dev] [PATCH 0/3] fix Rx checksum offloads Adrien Mazarguil
3 siblings, 0 replies; 6+ messages in thread
From: Nelio Laranjeiro @ 2016-11-02 10:39 UTC (permalink / raw)
To: dev
Fixes: 5842289a546c ("mbuf: add new Rx checksum flags")
Signed-off-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
---
drivers/net/mlx4/mlx4.c | 21 ++++++++-------------
drivers/net/mlx5/mlx5_rxtx.c | 25 ++++++++++---------------
2 files changed, 18 insertions(+), 28 deletions(-)
diff --git a/drivers/net/mlx4/mlx4.c b/drivers/net/mlx4/mlx4.c
index faa9acd..da61a85 100644
--- a/drivers/net/mlx4/mlx4.c
+++ b/drivers/net/mlx4/mlx4.c
@@ -2995,25 +2995,20 @@ rxq_cq_to_ol_flags(const struct rxq *rxq, uint32_t flags)
if (rxq->csum)
ol_flags |=
- TRANSPOSE(~flags,
+ TRANSPOSE(flags,
IBV_EXP_CQ_RX_IP_CSUM_OK,
- PKT_RX_IP_CKSUM_BAD) |
- TRANSPOSE(~flags,
+ PKT_RX_IP_CKSUM_GOOD) |
+ TRANSPOSE(flags,
IBV_EXP_CQ_RX_TCP_UDP_CSUM_OK,
- PKT_RX_L4_CKSUM_BAD);
- /*
- * PKT_RX_IP_CKSUM_BAD and PKT_RX_L4_CKSUM_BAD are used in place
- * of PKT_RX_EIP_CKSUM_BAD because the latter is not functional
- * (its value is 0).
- */
+ PKT_RX_L4_CKSUM_GOOD);
if ((flags & IBV_EXP_CQ_RX_TUNNEL_PACKET) && (rxq->csum_l2tun))
ol_flags |=
- TRANSPOSE(~flags,
+ TRANSPOSE(flags,
IBV_EXP_CQ_RX_OUTER_IP_CSUM_OK,
- PKT_RX_IP_CKSUM_BAD) |
- TRANSPOSE(~flags,
+ PKT_RX_IP_CKSUM_GOOD) |
+ TRANSPOSE(flags,
IBV_EXP_CQ_RX_OUTER_TCP_UDP_CSUM_OK,
- PKT_RX_L4_CKSUM_BAD);
+ PKT_RX_L4_CKSUM_GOOD);
return ol_flags;
}
diff --git a/drivers/net/mlx5/mlx5_rxtx.c b/drivers/net/mlx5/mlx5_rxtx.c
index b6e0d65..beff580 100644
--- a/drivers/net/mlx5/mlx5_rxtx.c
+++ b/drivers/net/mlx5/mlx5_rxtx.c
@@ -1239,29 +1239,24 @@ rxq_cq_to_ol_flags(struct rxq *rxq, volatile struct mlx5_cqe *cqe)
if ((l3_hdr == MLX5_CQE_L3_HDR_TYPE_IPV4) ||
(l3_hdr == MLX5_CQE_L3_HDR_TYPE_IPV6))
- ol_flags |=
- (!(cqe->hds_ip_ext & MLX5_CQE_L3_OK) *
- PKT_RX_IP_CKSUM_BAD);
+ ol_flags |= TRANSPOSE(cqe->hds_ip_ext,
+ MLX5_CQE_L3_OK,
+ PKT_RX_IP_CKSUM_GOOD);
if ((l4_hdr == MLX5_CQE_L4_HDR_TYPE_TCP) ||
(l4_hdr == MLX5_CQE_L4_HDR_TYPE_TCP_EMP_ACK) ||
(l4_hdr == MLX5_CQE_L4_HDR_TYPE_TCP_ACK) ||
(l4_hdr == MLX5_CQE_L4_HDR_TYPE_UDP))
- ol_flags |=
- (!(cqe->hds_ip_ext & MLX5_CQE_L4_OK) *
- PKT_RX_L4_CKSUM_BAD);
- /*
- * PKT_RX_IP_CKSUM_BAD and PKT_RX_L4_CKSUM_BAD are used in place
- * of PKT_RX_EIP_CKSUM_BAD because the latter is not functional
- * (its value is 0).
- */
+ ol_flags |= TRANSPOSE(cqe->hds_ip_ext,
+ MLX5_CQE_L4_OK,
+ PKT_RX_L4_CKSUM_GOOD);
if ((cqe->pkt_info & MLX5_CQE_RX_TUNNEL_PACKET) && (rxq->csum_l2tun))
ol_flags |=
- TRANSPOSE(~cqe->l4_hdr_type_etc,
+ TRANSPOSE(cqe->l4_hdr_type_etc,
MLX5_CQE_RX_OUTER_IP_CSUM_OK,
- PKT_RX_IP_CKSUM_BAD) |
- TRANSPOSE(~cqe->l4_hdr_type_etc,
+ PKT_RX_IP_CKSUM_GOOD) |
+ TRANSPOSE(cqe->l4_hdr_type_etc,
MLX5_CQE_RX_OUTER_TCP_UDP_CSUM_OK,
- PKT_RX_L4_CKSUM_BAD);
+ PKT_RX_L4_CKSUM_GOOD);
return ol_flags;
}
--
2.1.4
^ permalink raw reply [flat|nested] 6+ messages in thread