numam-dpdk/drivers/net/mlx5/mlx5_prm.h
Yongseok Koh 6ce84bd889 net/mlx5: add enhanced multi-packet send for ConnectX-5
ConnectX-5 supports enhanced version of multi-packet send (MPS). An MPS Tx
descriptor can carry multiple packets either by including pointers of
packets or by inlining packets. Inlining packet data can be helpful to
better utilize PCIe bandwidth. In addition, Enhanced MPS supports hybrid
mode - mixing inlined packets and pointers in a descriptor. This feature is
enabled by default if supported by HW.

Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
2017-04-04 18:59:41 +02:00

299 lines
7.5 KiB
C

/*-
* BSD LICENSE
*
* Copyright 2016 6WIND S.A.
* Copyright 2016 Mellanox.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
* * Neither the name of 6WIND S.A. nor the names of its
* contributors may be used to endorse or promote products derived
* from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#ifndef RTE_PMD_MLX5_PRM_H_
#define RTE_PMD_MLX5_PRM_H_
#include <assert.h>
/* Verbs header. */
/* ISO C doesn't support unnamed structs/unions, disabling -pedantic. */
#ifdef PEDANTIC
#pragma GCC diagnostic ignored "-Wpedantic"
#endif
#include <infiniband/mlx5_hw.h>
#ifdef PEDANTIC
#pragma GCC diagnostic error "-Wpedantic"
#endif
#include <rte_vect.h>
#include "mlx5_autoconf.h"
/* Get CQE owner bit. */
#define MLX5_CQE_OWNER(op_own) ((op_own) & MLX5_CQE_OWNER_MASK)
/* Get CQE format. */
#define MLX5_CQE_FORMAT(op_own) (((op_own) & MLX5E_CQE_FORMAT_MASK) >> 2)
/* Get CQE opcode. */
#define MLX5_CQE_OPCODE(op_own) (((op_own) & 0xf0) >> 4)
/* Get CQE solicited event. */
#define MLX5_CQE_SE(op_own) (((op_own) >> 1) & 1)
/* Invalidate a CQE. */
#define MLX5_CQE_INVALIDATE (MLX5_CQE_INVALID << 4)
/* Maximum number of packets a multi-packet WQE can handle. */
#define MLX5_MPW_DSEG_MAX 5
/* WQE DWORD size */
#define MLX5_WQE_DWORD_SIZE 16
/* WQE size */
#define MLX5_WQE_SIZE (4 * MLX5_WQE_DWORD_SIZE)
/* Max size of a WQE session. */
#define MLX5_WQE_SIZE_MAX 960U
/* Compute the number of DS. */
#define MLX5_WQE_DS(n) \
(((n) + MLX5_WQE_DWORD_SIZE - 1) / MLX5_WQE_DWORD_SIZE)
/* Room for inline data in multi-packet WQE. */
#define MLX5_MWQE64_INL_DATA 28
/* Default minimum number of Tx queues for inlining packets. */
#define MLX5_EMPW_MIN_TXQS 8
/* Default max packet length to be inlined. */
#define MLX5_EMPW_MAX_INLINE_LEN (4U * MLX5_WQE_SIZE)
#ifndef HAVE_VERBS_MLX5_OPCODE_TSO
#define MLX5_OPCODE_TSO MLX5_OPCODE_LSO_MPW /* Compat with OFED 3.3. */
#endif
#define MLX5_OPC_MOD_ENHANCED_MPSW 0
#define MLX5_OPCODE_ENHANCED_MPSW 0x29
/* CQE value to inform that VLAN is stripped. */
#define MLX5_CQE_VLAN_STRIPPED (1u << 0)
/* IPv4 options. */
#define MLX5_CQE_RX_IP_EXT_OPTS_PACKET (1u << 1)
/* IPv6 packet. */
#define MLX5_CQE_RX_IPV6_PACKET (1u << 2)
/* IPv4 packet. */
#define MLX5_CQE_RX_IPV4_PACKET (1u << 3)
/* TCP packet. */
#define MLX5_CQE_RX_TCP_PACKET (1u << 4)
/* UDP packet. */
#define MLX5_CQE_RX_UDP_PACKET (1u << 5)
/* IP is fragmented. */
#define MLX5_CQE_RX_IP_FRAG_PACKET (1u << 7)
/* L2 header is valid. */
#define MLX5_CQE_RX_L2_HDR_VALID (1u << 8)
/* L3 header is valid. */
#define MLX5_CQE_RX_L3_HDR_VALID (1u << 9)
/* L4 header is valid. */
#define MLX5_CQE_RX_L4_HDR_VALID (1u << 10)
/* Outer packet, 0 IPv4, 1 IPv6. */
#define MLX5_CQE_RX_OUTER_PACKET (1u << 1)
/* Tunnel packet bit in the CQE. */
#define MLX5_CQE_RX_TUNNEL_PACKET (1u << 0)
/* Inner L3 checksum offload (Tunneled packets only). */
#define MLX5_ETH_WQE_L3_INNER_CSUM (1u << 4)
/* Inner L4 checksum offload (Tunneled packets only). */
#define MLX5_ETH_WQE_L4_INNER_CSUM (1u << 5)
/* INVALID is used by packets matching no flow rules. */
#define MLX5_FLOW_MARK_INVALID 0
/* Maximum allowed value to mark a packet. */
#define MLX5_FLOW_MARK_MAX 0xfffff0
/* Default mark value used when none is provided. */
#define MLX5_FLOW_MARK_DEFAULT 0xffffff
/* Subset of struct mlx5_wqe_eth_seg. */
struct mlx5_wqe_eth_seg_small {
uint32_t rsvd0;
uint8_t cs_flags;
uint8_t rsvd1;
uint16_t mss;
uint32_t rsvd2;
uint16_t inline_hdr_sz;
uint8_t inline_hdr[2];
} __rte_aligned(MLX5_WQE_DWORD_SIZE);
struct mlx5_wqe_inl_small {
uint32_t byte_cnt;
uint8_t raw;
} __rte_aligned(MLX5_WQE_DWORD_SIZE);
struct mlx5_wqe_ctrl {
uint32_t ctrl0;
uint32_t ctrl1;
uint32_t ctrl2;
uint32_t ctrl3;
} __rte_aligned(MLX5_WQE_DWORD_SIZE);
/* Small common part of the WQE. */
struct mlx5_wqe {
uint32_t ctrl[4];
struct mlx5_wqe_eth_seg_small eseg;
};
/* Vectorize WQE header. */
struct mlx5_wqe_v {
rte_v128u32_t ctrl;
rte_v128u32_t eseg;
};
/* WQE. */
struct mlx5_wqe64 {
struct mlx5_wqe hdr;
uint8_t raw[32];
} __rte_aligned(MLX5_WQE_SIZE);
/* MPW mode. */
enum mlx5_mpw_mode {
MLX5_MPW_DISABLED,
MLX5_MPW,
MLX5_MPW_ENHANCED, /* Enhanced Multi-Packet Send WQE, a.k.a MPWv2. */
};
/* MPW session status. */
enum mlx5_mpw_state {
MLX5_MPW_STATE_OPENED,
MLX5_MPW_INL_STATE_OPENED,
MLX5_MPW_ENHANCED_STATE_OPENED,
MLX5_MPW_STATE_CLOSED,
};
/* MPW session descriptor. */
struct mlx5_mpw {
enum mlx5_mpw_state state;
unsigned int pkts_n;
unsigned int len;
unsigned int total_len;
volatile struct mlx5_wqe *wqe;
union {
volatile struct mlx5_wqe_data_seg *dseg[MLX5_MPW_DSEG_MAX];
volatile uint8_t *raw;
} data;
};
/* CQ element structure - should be equal to the cache line size */
struct mlx5_cqe {
#if (RTE_CACHE_LINE_SIZE == 128)
uint8_t padding[64];
#endif
uint8_t pkt_info;
uint8_t rsvd0[11];
uint32_t rx_hash_res;
uint8_t rx_hash_type;
uint8_t rsvd1[11];
uint16_t hdr_type_etc;
uint16_t vlan_info;
uint8_t rsvd2[12];
uint32_t byte_cnt;
uint64_t timestamp;
uint32_t sop_drop_qpn;
uint16_t wqe_counter;
uint8_t rsvd4;
uint8_t op_own;
};
/**
* Convert a user mark to flow mark.
*
* @param val
* Mark value to convert.
*
* @return
* Converted mark value.
*/
static inline uint32_t
mlx5_flow_mark_set(uint32_t val)
{
uint32_t ret;
/*
* Add one to the user value to differentiate un-marked flows from
* marked flows, if the ID is equal to MLX5_FLOW_MARK_DEFAULT it
* remains untouched.
*/
if (val != MLX5_FLOW_MARK_DEFAULT)
++val;
#if RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
/*
* Mark is 24 bits (minus reserved values) but is stored on a 32 bit
* word, byte-swapped by the kernel on little-endian systems. In this
* case, left-shifting the resulting big-endian value ensures the
* least significant 24 bits are retained when converting it back.
*/
ret = rte_cpu_to_be_32(val) >> 8;
#else
ret = val;
#endif
return ret;
}
/**
* Convert a mark to user mark.
*
* @param val
* Mark value to convert.
*
* @return
* Converted mark value.
*/
static inline uint32_t
mlx5_flow_mark_get(uint32_t val)
{
/*
* Subtract one from the retrieved value. It was added by
* mlx5_flow_mark_set() to distinguish unmarked flows.
*/
#if RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
return (val >> 8) - 1;
#else
return val - 1;
#endif
}
#endif /* RTE_PMD_MLX5_PRM_H_ */