numam-dpdk/drivers/net/mlx5/mlx5.h

596 lines
22 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: BSD-3-Clause
* Copyright 2015 6WIND S.A.
* Copyright 2015 Mellanox Technologies, Ltd
*/
#ifndef RTE_PMD_MLX5_H_
#define RTE_PMD_MLX5_H_
#include <stddef.h>
#include <stdbool.h>
#include <stdint.h>
#include <limits.h>
#include <net/if.h>
#include <netinet/in.h>
#include <sys/queue.h>
/* Verbs header. */
/* ISO C doesn't support unnamed structs/unions, disabling -pedantic. */
#ifdef PEDANTIC
#pragma GCC diagnostic ignored "-Wpedantic"
#endif
#include <infiniband/verbs.h>
#ifdef PEDANTIC
#pragma GCC diagnostic error "-Wpedantic"
#endif
#include <rte_pci.h>
#include <rte_ether.h>
#include <rte_ethdev_driver.h>
net/mlx5: add new memory region support This is the new design of Memory Region (MR) for mlx PMD, in order to: - Accommodate the new memory hotplug model. - Support non-contiguous Mempool. There are multiple layers for MR search. L0 is to look up the last-hit entry which is pointed by mr_ctrl->mru (Most Recently Used). If L0 misses, L1 is to look up the address in a fixed-sized array by linear search. L0/L1 is in an inline function - mlx5_mr_lookup_cache(). If L1 misses, the bottom-half function is called to look up the address from the bigger local cache of the queue. This is L2 - mlx5_mr_addr2mr_bh() and it is not an inline function. Data structure for L2 is the Binary Tree. If L2 misses, the search falls into the slowest path which takes locks in order to access global device cache (priv->mr.cache) which is also a B-tree and caches the original MR list (priv->mr.mr_list) of the device. Unless the global cache is overflowed, it is all-inclusive of the MR list. This is L3 - mlx5_mr_lookup_dev(). The size of the L3 cache table is limited and can't be expanded on the fly due to deadlock. Refer to the comments in the code for the details - mr_lookup_dev(). If L3 is overflowed, the list will have to be searched directly bypassing the cache although it is slower. If L3 misses, a new MR for the address should be created - mlx5_mr_create(). When it creates a new MR, it tries to register adjacent memsegs as much as possible which are virtually contiguous around the address. This must take two locks - memory_hotplug_lock and priv->mr.rwlock. Due to memory_hotplug_lock, there can't be any allocation/free of memory inside. In the free callback of the memory hotplug event, freed space is searched from the MR list and corresponding bits are cleared from the bitmap of MRs. This can fragment a MR and the MR will have multiple search entries in the caches. Once there's a change by the event, the global cache must be rebuilt and all the per-queue caches will be flushed as well. If memory is frequently freed in run-time, that may cause jitter on dataplane processing in the worst case by incurring MR cache flush and rebuild. But, it would be the least probable scenario. To guarantee the most optimal performance, it is highly recommended to use an EAL option - '--socket-mem'. Then, the reserved memory will be pinned and won't be freed dynamically. And it is also recommended to configure per-lcore cache of Mempool. Even though there're many MRs for a device or MRs are highly fragmented, the cache of Mempool will be much helpful to reduce misses on per-queue caches anyway. '--legacy-mem' is also supported. Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
2018-05-09 11:09:04 +00:00
#include <rte_rwlock.h>
#include <rte_interrupts.h>
#include <rte_errno.h>
#include <rte_flow.h>
#include "mlx5_utils.h"
net/mlx5: add new memory region support This is the new design of Memory Region (MR) for mlx PMD, in order to: - Accommodate the new memory hotplug model. - Support non-contiguous Mempool. There are multiple layers for MR search. L0 is to look up the last-hit entry which is pointed by mr_ctrl->mru (Most Recently Used). If L0 misses, L1 is to look up the address in a fixed-sized array by linear search. L0/L1 is in an inline function - mlx5_mr_lookup_cache(). If L1 misses, the bottom-half function is called to look up the address from the bigger local cache of the queue. This is L2 - mlx5_mr_addr2mr_bh() and it is not an inline function. Data structure for L2 is the Binary Tree. If L2 misses, the search falls into the slowest path which takes locks in order to access global device cache (priv->mr.cache) which is also a B-tree and caches the original MR list (priv->mr.mr_list) of the device. Unless the global cache is overflowed, it is all-inclusive of the MR list. This is L3 - mlx5_mr_lookup_dev(). The size of the L3 cache table is limited and can't be expanded on the fly due to deadlock. Refer to the comments in the code for the details - mr_lookup_dev(). If L3 is overflowed, the list will have to be searched directly bypassing the cache although it is slower. If L3 misses, a new MR for the address should be created - mlx5_mr_create(). When it creates a new MR, it tries to register adjacent memsegs as much as possible which are virtually contiguous around the address. This must take two locks - memory_hotplug_lock and priv->mr.rwlock. Due to memory_hotplug_lock, there can't be any allocation/free of memory inside. In the free callback of the memory hotplug event, freed space is searched from the MR list and corresponding bits are cleared from the bitmap of MRs. This can fragment a MR and the MR will have multiple search entries in the caches. Once there's a change by the event, the global cache must be rebuilt and all the per-queue caches will be flushed as well. If memory is frequently freed in run-time, that may cause jitter on dataplane processing in the worst case by incurring MR cache flush and rebuild. But, it would be the least probable scenario. To guarantee the most optimal performance, it is highly recommended to use an EAL option - '--socket-mem'. Then, the reserved memory will be pinned and won't be freed dynamically. And it is also recommended to configure per-lcore cache of Mempool. Even though there're many MRs for a device or MRs are highly fragmented, the cache of Mempool will be much helpful to reduce misses on per-queue caches anyway. '--legacy-mem' is also supported. Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
2018-05-09 11:09:04 +00:00
#include "mlx5_mr.h"
#include "mlx5_autoconf.h"
#include "mlx5_defs.h"
enum {
PCI_VENDOR_ID_MELLANOX = 0x15b3,
};
enum {
PCI_DEVICE_ID_MELLANOX_CONNECTX4 = 0x1013,
PCI_DEVICE_ID_MELLANOX_CONNECTX4VF = 0x1014,
PCI_DEVICE_ID_MELLANOX_CONNECTX4LX = 0x1015,
PCI_DEVICE_ID_MELLANOX_CONNECTX4LXVF = 0x1016,
PCI_DEVICE_ID_MELLANOX_CONNECTX5 = 0x1017,
PCI_DEVICE_ID_MELLANOX_CONNECTX5VF = 0x1018,
PCI_DEVICE_ID_MELLANOX_CONNECTX5EX = 0x1019,
PCI_DEVICE_ID_MELLANOX_CONNECTX5EXVF = 0x101a,
PCI_DEVICE_ID_MELLANOX_CONNECTX5BF = 0xa2d2,
PCI_DEVICE_ID_MELLANOX_CONNECTX5BFVF = 0xa2d3,
PCI_DEVICE_ID_MELLANOX_CONNECTX6 = 0x101b,
PCI_DEVICE_ID_MELLANOX_CONNECTX6VF = 0x101c,
};
/* Request types for IPC. */
enum mlx5_mp_req_type {
MLX5_MP_REQ_VERBS_CMD_FD = 1,
MLX5_MP_REQ_CREATE_MR,
MLX5_MP_REQ_START_RXTX,
MLX5_MP_REQ_STOP_RXTX,
MLX5_MP_REQ_QUEUE_STATE_MODIFY,
};
struct mlx5_mp_arg_queue_state_modify {
uint8_t is_wq; /* Set if WQ. */
uint16_t queue_id; /* DPDK queue ID. */
enum ibv_wq_state state; /* WQ requested state. */
};
/* Pameters for IPC. */
struct mlx5_mp_param {
enum mlx5_mp_req_type type;
int port_id;
int result;
RTE_STD_C11
union {
uintptr_t addr; /* MLX5_MP_REQ_CREATE_MR */
struct mlx5_mp_arg_queue_state_modify state_modify;
/* MLX5_MP_REQ_QUEUE_STATE_MODIFY */
} args;
};
/** Request timeout for IPC. */
#define MLX5_MP_REQ_TIMEOUT_SEC 5
/** Key string for IPC. */
#define MLX5_MP_NAME "net_mlx5_mp"
net/mlx5: support PF representor On BlueField platform we have the new entity - PF representor. This one represents the PCI PF attached to external host on the side of ARM. The traffic sent by the external host to the NIC via PF will be seem by ARM on this PF representor. This patch refactors port recognizing capability on the base of physical port name. We have two groups of name formats. Legacy name formats are supported by kernels before ver 5.0 (being more precise - before the patch [1]) or before Mellanox OFED 4.6, and new naming formats added by the patch [1]. Legacy naming formats are supported: - missing physical port name (no sysfs/netlink key) at all, master is assumed - decimal digits (for example "12"), representor is assumed, the value is the index of attached VF New naming formats are supported: - "p" followed by decimal digits, for example "p2", master is assumed - "pf" followed by PF index concatenated with "vf" followed by VF index, for example "pf0vf1", representor is assumed. If index of VF is "-1" it is a special case of host PF representor, this representor must be indexed in devargs as 65535, for example representor=[0-3,65535] will allow representors for VF0, VF1, VF2, VF3 and for host PF. Note: do not specify representor=[0-65535], it causes devargs processing error, because number of ports (rte_eth_dev) is limited. Applications should distinguish representors and master devices exclusively by device flag RTE_ETH_DEV_REPRESENTOR and do not rely on switch port_id (mlx5 PMD deduces ones from representor_id) values returned by dev_infos_get() API. [1] https://www.spinics.net/lists/netdev/msg547007.html Linux-tree: c12ecc23 (Or Gerlitz 2018-04-25 17:32 +0300) "net/mlx5e: Move to use common phys port names for vport representors" Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com> Acked-by: Shahaf Shuler <shahafs@mellanox.com>
2019-04-16 14:10:28 +00:00
/* Recognized Infiniband device physical port name types. */
enum mlx5_phys_port_name_type {
MLX5_PHYS_PORT_NAME_TYPE_NOTSET = 0, /* Not set. */
MLX5_PHYS_PORT_NAME_TYPE_LEGACY, /* before kernel ver < 5.0 */
MLX5_PHYS_PORT_NAME_TYPE_UPLINK, /* p0, kernel ver >= 5.0 */
MLX5_PHYS_PORT_NAME_TYPE_PFVF, /* pf0vf0, kernel ver >= 5.0 */
MLX5_PHYS_PORT_NAME_TYPE_UNKNOWN, /* Unrecognized. */
};
/** Switch information returned by mlx5_nl_switch_info(). */
struct mlx5_switch_info {
uint32_t master:1; /**< Master device. */
uint32_t representor:1; /**< Representor device. */
net/mlx5: support PF representor On BlueField platform we have the new entity - PF representor. This one represents the PCI PF attached to external host on the side of ARM. The traffic sent by the external host to the NIC via PF will be seem by ARM on this PF representor. This patch refactors port recognizing capability on the base of physical port name. We have two groups of name formats. Legacy name formats are supported by kernels before ver 5.0 (being more precise - before the patch [1]) or before Mellanox OFED 4.6, and new naming formats added by the patch [1]. Legacy naming formats are supported: - missing physical port name (no sysfs/netlink key) at all, master is assumed - decimal digits (for example "12"), representor is assumed, the value is the index of attached VF New naming formats are supported: - "p" followed by decimal digits, for example "p2", master is assumed - "pf" followed by PF index concatenated with "vf" followed by VF index, for example "pf0vf1", representor is assumed. If index of VF is "-1" it is a special case of host PF representor, this representor must be indexed in devargs as 65535, for example representor=[0-3,65535] will allow representors for VF0, VF1, VF2, VF3 and for host PF. Note: do not specify representor=[0-65535], it causes devargs processing error, because number of ports (rte_eth_dev) is limited. Applications should distinguish representors and master devices exclusively by device flag RTE_ETH_DEV_REPRESENTOR and do not rely on switch port_id (mlx5 PMD deduces ones from representor_id) values returned by dev_infos_get() API. [1] https://www.spinics.net/lists/netdev/msg547007.html Linux-tree: c12ecc23 (Or Gerlitz 2018-04-25 17:32 +0300) "net/mlx5e: Move to use common phys port names for vport representors" Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com> Acked-by: Shahaf Shuler <shahafs@mellanox.com>
2019-04-16 14:10:28 +00:00
enum mlx5_phys_port_name_type name_type; /** < Port name type. */
int32_t pf_num; /**< PF number (valid for pfxvfx format only). */
int32_t port_name; /**< Representor port name. */
uint64_t switch_id; /**< Switch identifier. */
};
LIST_HEAD(mlx5_dev_list, mlx5_ibv_shared);
net/mlx5: add new memory region support This is the new design of Memory Region (MR) for mlx PMD, in order to: - Accommodate the new memory hotplug model. - Support non-contiguous Mempool. There are multiple layers for MR search. L0 is to look up the last-hit entry which is pointed by mr_ctrl->mru (Most Recently Used). If L0 misses, L1 is to look up the address in a fixed-sized array by linear search. L0/L1 is in an inline function - mlx5_mr_lookup_cache(). If L1 misses, the bottom-half function is called to look up the address from the bigger local cache of the queue. This is L2 - mlx5_mr_addr2mr_bh() and it is not an inline function. Data structure for L2 is the Binary Tree. If L2 misses, the search falls into the slowest path which takes locks in order to access global device cache (priv->mr.cache) which is also a B-tree and caches the original MR list (priv->mr.mr_list) of the device. Unless the global cache is overflowed, it is all-inclusive of the MR list. This is L3 - mlx5_mr_lookup_dev(). The size of the L3 cache table is limited and can't be expanded on the fly due to deadlock. Refer to the comments in the code for the details - mr_lookup_dev(). If L3 is overflowed, the list will have to be searched directly bypassing the cache although it is slower. If L3 misses, a new MR for the address should be created - mlx5_mr_create(). When it creates a new MR, it tries to register adjacent memsegs as much as possible which are virtually contiguous around the address. This must take two locks - memory_hotplug_lock and priv->mr.rwlock. Due to memory_hotplug_lock, there can't be any allocation/free of memory inside. In the free callback of the memory hotplug event, freed space is searched from the MR list and corresponding bits are cleared from the bitmap of MRs. This can fragment a MR and the MR will have multiple search entries in the caches. Once there's a change by the event, the global cache must be rebuilt and all the per-queue caches will be flushed as well. If memory is frequently freed in run-time, that may cause jitter on dataplane processing in the worst case by incurring MR cache flush and rebuild. But, it would be the least probable scenario. To guarantee the most optimal performance, it is highly recommended to use an EAL option - '--socket-mem'. Then, the reserved memory will be pinned and won't be freed dynamically. And it is also recommended to configure per-lcore cache of Mempool. Even though there're many MRs for a device or MRs are highly fragmented, the cache of Mempool will be much helpful to reduce misses on per-queue caches anyway. '--legacy-mem' is also supported. Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
2018-05-09 11:09:04 +00:00
/* Shared data between primary and secondary processes. */
net/mlx5: add new memory region support This is the new design of Memory Region (MR) for mlx PMD, in order to: - Accommodate the new memory hotplug model. - Support non-contiguous Mempool. There are multiple layers for MR search. L0 is to look up the last-hit entry which is pointed by mr_ctrl->mru (Most Recently Used). If L0 misses, L1 is to look up the address in a fixed-sized array by linear search. L0/L1 is in an inline function - mlx5_mr_lookup_cache(). If L1 misses, the bottom-half function is called to look up the address from the bigger local cache of the queue. This is L2 - mlx5_mr_addr2mr_bh() and it is not an inline function. Data structure for L2 is the Binary Tree. If L2 misses, the search falls into the slowest path which takes locks in order to access global device cache (priv->mr.cache) which is also a B-tree and caches the original MR list (priv->mr.mr_list) of the device. Unless the global cache is overflowed, it is all-inclusive of the MR list. This is L3 - mlx5_mr_lookup_dev(). The size of the L3 cache table is limited and can't be expanded on the fly due to deadlock. Refer to the comments in the code for the details - mr_lookup_dev(). If L3 is overflowed, the list will have to be searched directly bypassing the cache although it is slower. If L3 misses, a new MR for the address should be created - mlx5_mr_create(). When it creates a new MR, it tries to register adjacent memsegs as much as possible which are virtually contiguous around the address. This must take two locks - memory_hotplug_lock and priv->mr.rwlock. Due to memory_hotplug_lock, there can't be any allocation/free of memory inside. In the free callback of the memory hotplug event, freed space is searched from the MR list and corresponding bits are cleared from the bitmap of MRs. This can fragment a MR and the MR will have multiple search entries in the caches. Once there's a change by the event, the global cache must be rebuilt and all the per-queue caches will be flushed as well. If memory is frequently freed in run-time, that may cause jitter on dataplane processing in the worst case by incurring MR cache flush and rebuild. But, it would be the least probable scenario. To guarantee the most optimal performance, it is highly recommended to use an EAL option - '--socket-mem'. Then, the reserved memory will be pinned and won't be freed dynamically. And it is also recommended to configure per-lcore cache of Mempool. Even though there're many MRs for a device or MRs are highly fragmented, the cache of Mempool will be much helpful to reduce misses on per-queue caches anyway. '--legacy-mem' is also supported. Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
2018-05-09 11:09:04 +00:00
struct mlx5_shared_data {
rte_spinlock_t lock;
/* Global spinlock for primary and secondary processes. */
int init_done; /* Whether primary has done initialization. */
unsigned int secondary_cnt; /* Number of secondary processes init'd. */
net/mlx5: add new memory region support This is the new design of Memory Region (MR) for mlx PMD, in order to: - Accommodate the new memory hotplug model. - Support non-contiguous Mempool. There are multiple layers for MR search. L0 is to look up the last-hit entry which is pointed by mr_ctrl->mru (Most Recently Used). If L0 misses, L1 is to look up the address in a fixed-sized array by linear search. L0/L1 is in an inline function - mlx5_mr_lookup_cache(). If L1 misses, the bottom-half function is called to look up the address from the bigger local cache of the queue. This is L2 - mlx5_mr_addr2mr_bh() and it is not an inline function. Data structure for L2 is the Binary Tree. If L2 misses, the search falls into the slowest path which takes locks in order to access global device cache (priv->mr.cache) which is also a B-tree and caches the original MR list (priv->mr.mr_list) of the device. Unless the global cache is overflowed, it is all-inclusive of the MR list. This is L3 - mlx5_mr_lookup_dev(). The size of the L3 cache table is limited and can't be expanded on the fly due to deadlock. Refer to the comments in the code for the details - mr_lookup_dev(). If L3 is overflowed, the list will have to be searched directly bypassing the cache although it is slower. If L3 misses, a new MR for the address should be created - mlx5_mr_create(). When it creates a new MR, it tries to register adjacent memsegs as much as possible which are virtually contiguous around the address. This must take two locks - memory_hotplug_lock and priv->mr.rwlock. Due to memory_hotplug_lock, there can't be any allocation/free of memory inside. In the free callback of the memory hotplug event, freed space is searched from the MR list and corresponding bits are cleared from the bitmap of MRs. This can fragment a MR and the MR will have multiple search entries in the caches. Once there's a change by the event, the global cache must be rebuilt and all the per-queue caches will be flushed as well. If memory is frequently freed in run-time, that may cause jitter on dataplane processing in the worst case by incurring MR cache flush and rebuild. But, it would be the least probable scenario. To guarantee the most optimal performance, it is highly recommended to use an EAL option - '--socket-mem'. Then, the reserved memory will be pinned and won't be freed dynamically. And it is also recommended to configure per-lcore cache of Mempool. Even though there're many MRs for a device or MRs are highly fragmented, the cache of Mempool will be much helpful to reduce misses on per-queue caches anyway. '--legacy-mem' is also supported. Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
2018-05-09 11:09:04 +00:00
struct mlx5_dev_list mem_event_cb_list;
rte_rwlock_t mem_event_rwlock;
};
/* Per-process data structure, not visible to other processes. */
struct mlx5_local_data {
int init_done; /* Whether a secondary has done initialization. */
};
net/mlx5: add new memory region support This is the new design of Memory Region (MR) for mlx PMD, in order to: - Accommodate the new memory hotplug model. - Support non-contiguous Mempool. There are multiple layers for MR search. L0 is to look up the last-hit entry which is pointed by mr_ctrl->mru (Most Recently Used). If L0 misses, L1 is to look up the address in a fixed-sized array by linear search. L0/L1 is in an inline function - mlx5_mr_lookup_cache(). If L1 misses, the bottom-half function is called to look up the address from the bigger local cache of the queue. This is L2 - mlx5_mr_addr2mr_bh() and it is not an inline function. Data structure for L2 is the Binary Tree. If L2 misses, the search falls into the slowest path which takes locks in order to access global device cache (priv->mr.cache) which is also a B-tree and caches the original MR list (priv->mr.mr_list) of the device. Unless the global cache is overflowed, it is all-inclusive of the MR list. This is L3 - mlx5_mr_lookup_dev(). The size of the L3 cache table is limited and can't be expanded on the fly due to deadlock. Refer to the comments in the code for the details - mr_lookup_dev(). If L3 is overflowed, the list will have to be searched directly bypassing the cache although it is slower. If L3 misses, a new MR for the address should be created - mlx5_mr_create(). When it creates a new MR, it tries to register adjacent memsegs as much as possible which are virtually contiguous around the address. This must take two locks - memory_hotplug_lock and priv->mr.rwlock. Due to memory_hotplug_lock, there can't be any allocation/free of memory inside. In the free callback of the memory hotplug event, freed space is searched from the MR list and corresponding bits are cleared from the bitmap of MRs. This can fragment a MR and the MR will have multiple search entries in the caches. Once there's a change by the event, the global cache must be rebuilt and all the per-queue caches will be flushed as well. If memory is frequently freed in run-time, that may cause jitter on dataplane processing in the worst case by incurring MR cache flush and rebuild. But, it would be the least probable scenario. To guarantee the most optimal performance, it is highly recommended to use an EAL option - '--socket-mem'. Then, the reserved memory will be pinned and won't be freed dynamically. And it is also recommended to configure per-lcore cache of Mempool. Even though there're many MRs for a device or MRs are highly fragmented, the cache of Mempool will be much helpful to reduce misses on per-queue caches anyway. '--legacy-mem' is also supported. Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
2018-05-09 11:09:04 +00:00
extern struct mlx5_shared_data *mlx5_shared_data;
struct mlx5_counter_ctrl {
/* Name of the counter. */
char dpdk_name[RTE_ETH_XSTATS_NAME_SIZE];
/* Name of the counter on the device table. */
char ctr_name[RTE_ETH_XSTATS_NAME_SIZE];
uint32_t ib:1; /**< Nonzero for IB counters. */
};
struct mlx5_xstats_ctrl {
/* Number of device stats. */
uint16_t stats_n;
/* Number of device stats identified by PMD. */
uint16_t mlx5_stats_n;
/* Index in the device counters table. */
uint16_t dev_table_idx[MLX5_MAX_XSTATS];
uint64_t base[MLX5_MAX_XSTATS];
struct mlx5_counter_ctrl info[MLX5_MAX_XSTATS];
};
struct mlx5_stats_ctrl {
/* Base for imissed counter. */
uint64_t imissed_base;
};
/* devx counter object */
struct mlx5_devx_counter_set {
struct mlx5dv_devx_obj *obj;
int id; /* Flow counter ID */
};
/* HCA attributes. */
struct mlx5_hca_attr {
uint32_t eswitch_manager:1;
};
/* Flow list . */
TAILQ_HEAD(mlx5_flows, rte_flow);
/* Default PMD specific parameter value. */
#define MLX5_ARG_UNSET (-1)
/*
* Device configuration structure.
*
* Merged configuration from:
*
* - Device capabilities,
* - User device parameters disabled features.
*/
struct mlx5_dev_config {
unsigned int hw_csum:1; /* Checksum offload is supported. */
unsigned int hw_vlan_strip:1; /* VLAN stripping is supported. */
unsigned int hw_fcs_strip:1; /* FCS stripping is supported. */
unsigned int hw_padding:1; /* End alignment padding is supported. */
unsigned int vf:1; /* This is a VF. */
unsigned int tunnel_en:1;
/* Whether tunnel stateless offloads are supported. */
unsigned int mpls_en:1; /* MPLS over GRE/UDP is enabled. */
unsigned int cqe_comp:1; /* CQE compression is enabled. */
unsigned int cqe_pad:1; /* CQE padding is enabled. */
unsigned int tso:1; /* Whether TSO is supported. */
unsigned int tx_vec_en:1; /* Tx vector is enabled. */
unsigned int rx_vec_en:1; /* Rx vector is enabled. */
unsigned int mpw_hdr_dseg:1; /* Enable DSEGs in the title WQEBB. */
unsigned int mr_ext_memseg_en:1;
/* Whether memseg should be extended for MR creation. */
unsigned int l3_vxlan_en:1; /* Enable L3 VXLAN flow creation. */
unsigned int vf_nl_en:1; /* Enable Netlink requests in VF mode. */
unsigned int dv_esw_en:1; /* Enable E-Switch DV flow. */
unsigned int dv_flow_en:1; /* Enable DV flow. */
unsigned int swp:1; /* Tx generic tunnel checksum and TSO offload. */
unsigned int devx:1; /* Whether devx interface is available or not. */
struct {
unsigned int enabled:1; /* Whether MPRQ is enabled. */
unsigned int stride_num_n; /* Number of strides. */
unsigned int min_stride_size_n; /* Min size of a stride. */
unsigned int max_stride_size_n; /* Max size of a stride. */
unsigned int max_memcpy_len;
/* Maximum packet size to memcpy Rx packets. */
unsigned int min_rxqs_num;
/* Rx queue count threshold to enable MPRQ. */
} mprq; /* Configurations for Multi-Packet RQ. */
int mps; /* Multi-packet send supported mode. */
unsigned int flow_prio; /* Number of flow priorities. */
unsigned int tso_max_payload_sz; /* Maximum TCP payload for TSO. */
unsigned int ind_table_max_size; /* Maximum indirection table size. */
unsigned int max_dump_files_num; /* Maximum dump files per queue. */
int txq_inline; /* Maximum packet size for inlining. */
int txqs_inline; /* Queue number threshold for inlining. */
int txqs_vec; /* Queue number threshold for vectorized Tx. */
int inline_max_packet_sz; /* Max packet size for inlining. */
struct mlx5_hca_attr hca_attr; /* HCA attributes. */
};
/**
* Type of objet being allocated.
*/
enum mlx5_verbs_alloc_type {
MLX5_VERBS_ALLOC_TYPE_NONE,
MLX5_VERBS_ALLOC_TYPE_TX_QUEUE,
MLX5_VERBS_ALLOC_TYPE_RX_QUEUE,
};
/**
* Verbs allocator needs a context to know in the callback which kind of
* resources it is allocating.
*/
struct mlx5_verbs_alloc_ctx {
enum mlx5_verbs_alloc_type type; /* Kind of object being allocated. */
const void *obj; /* Pointer to the DPDK object. */
};
net/mlx5: add new memory region support This is the new design of Memory Region (MR) for mlx PMD, in order to: - Accommodate the new memory hotplug model. - Support non-contiguous Mempool. There are multiple layers for MR search. L0 is to look up the last-hit entry which is pointed by mr_ctrl->mru (Most Recently Used). If L0 misses, L1 is to look up the address in a fixed-sized array by linear search. L0/L1 is in an inline function - mlx5_mr_lookup_cache(). If L1 misses, the bottom-half function is called to look up the address from the bigger local cache of the queue. This is L2 - mlx5_mr_addr2mr_bh() and it is not an inline function. Data structure for L2 is the Binary Tree. If L2 misses, the search falls into the slowest path which takes locks in order to access global device cache (priv->mr.cache) which is also a B-tree and caches the original MR list (priv->mr.mr_list) of the device. Unless the global cache is overflowed, it is all-inclusive of the MR list. This is L3 - mlx5_mr_lookup_dev(). The size of the L3 cache table is limited and can't be expanded on the fly due to deadlock. Refer to the comments in the code for the details - mr_lookup_dev(). If L3 is overflowed, the list will have to be searched directly bypassing the cache although it is slower. If L3 misses, a new MR for the address should be created - mlx5_mr_create(). When it creates a new MR, it tries to register adjacent memsegs as much as possible which are virtually contiguous around the address. This must take two locks - memory_hotplug_lock and priv->mr.rwlock. Due to memory_hotplug_lock, there can't be any allocation/free of memory inside. In the free callback of the memory hotplug event, freed space is searched from the MR list and corresponding bits are cleared from the bitmap of MRs. This can fragment a MR and the MR will have multiple search entries in the caches. Once there's a change by the event, the global cache must be rebuilt and all the per-queue caches will be flushed as well. If memory is frequently freed in run-time, that may cause jitter on dataplane processing in the worst case by incurring MR cache flush and rebuild. But, it would be the least probable scenario. To guarantee the most optimal performance, it is highly recommended to use an EAL option - '--socket-mem'. Then, the reserved memory will be pinned and won't be freed dynamically. And it is also recommended to configure per-lcore cache of Mempool. Even though there're many MRs for a device or MRs are highly fragmented, the cache of Mempool will be much helpful to reduce misses on per-queue caches anyway. '--legacy-mem' is also supported. Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
2018-05-09 11:09:04 +00:00
LIST_HEAD(mlx5_mr_list, mlx5_mr);
/* Flow drop context necessary due to Verbs API. */
struct mlx5_drop {
struct mlx5_hrxq *hrxq; /* Hash Rx queue queue. */
struct mlx5_rxq_ibv *rxq; /* Verbs Rx queue. */
};
/* Per port data of shared IB device. */
struct mlx5_ibv_shared_port {
uint32_t ih_port_id;
/*
* Interrupt handler port_id. Used by shared interrupt
* handler to find the corresponding rte_eth device
* by IB port index. If value is equal or greater
* RTE_MAX_ETHPORTS it means there is no subhandler
* installed for specified IB port index.
*/
};
/* Table structure. */
struct mlx5_flow_tbl_resource {
void *obj; /**< Pointer to DR table object. */
rte_atomic32_t refcnt; /**< Reference counter. */
};
#define MLX5_MAX_TABLES 1024
#define MLX5_MAX_TABLES_FDB 32
#define MLX5_GROUP_FACTOR 1
/*
* Shared Infiniband device context for Master/Representors
* which belong to same IB device with multiple IB ports.
**/
struct mlx5_ibv_shared {
LIST_ENTRY(mlx5_ibv_shared) next;
uint32_t refcnt;
uint32_t devx:1; /* Opened with DV. */
uint32_t max_port; /* Maximal IB device port index. */
struct ibv_context *ctx; /* Verbs/DV context. */
struct ibv_pd *pd; /* Protection Domain. */
char ibdev_name[IBV_SYSFS_NAME_MAX]; /* IB device name. */
char ibdev_path[IBV_SYSFS_PATH_MAX]; /* IB device path for secondary */
struct ibv_device_attr_ex device_attr; /* Device properties. */
struct rte_pci_device *pci_dev; /* Backend PCI device. */
LIST_ENTRY(mlx5_ibv_shared) mem_event_cb;
/**< Called by memory event callback. */
struct {
uint32_t dev_gen; /* Generation number to flush local caches. */
rte_rwlock_t rwlock; /* MR Lock. */
struct mlx5_mr_btree cache; /* Global MR cache table. */
struct mlx5_mr_list mr_list; /* Registered MR list. */
struct mlx5_mr_list mr_free_list; /* Freed MR list. */
} mr;
/* Shared DV/DR flow data section. */
pthread_mutex_t dv_mutex; /* DV context mutex. */
uint32_t dv_refcnt; /* DV/DR data reference counter. */
void *fdb_domain; /* FDB Direct Rules name space handle. */
struct mlx5_flow_tbl_resource fdb_tbl[MLX5_MAX_TABLES_FDB];
/* FDB Direct Rules tables. */
void *rx_domain; /* RX Direct Rules name space handle. */
struct mlx5_flow_tbl_resource rx_tbl[MLX5_MAX_TABLES];
/* RX Direct Rules tables. */
void *tx_domain; /* TX Direct Rules name space handle. */
struct mlx5_flow_tbl_resource tx_tbl[MLX5_MAX_TABLES];
void *esw_drop_action; /* Pointer to DR E-Switch drop action. */
/* TX Direct Rules tables/ */
LIST_HEAD(matchers, mlx5_flow_dv_matcher) matchers;
LIST_HEAD(encap_decap, mlx5_flow_dv_encap_decap_resource) encaps_decaps;
LIST_HEAD(modify_cmd, mlx5_flow_dv_modify_hdr_resource) modify_cmds;
LIST_HEAD(tag, mlx5_flow_dv_tag_resource) tags;
LIST_HEAD(jump, mlx5_flow_dv_jump_tbl_resource) jump_tbl;
LIST_HEAD(port_id_action_list, mlx5_flow_dv_port_id_action_resource)
port_id_action_list; /* List of port ID actions. */
/* Shared interrupt handler section. */
pthread_mutex_t intr_mutex; /* Interrupt config mutex. */
uint32_t intr_cnt; /* Interrupt handler reference counter. */
struct rte_intr_handle intr_handle; /* Interrupt handler for device. */
struct mlx5_ibv_shared_port port[]; /* per device port data array. */
};
/* Per-process private structure. */
struct mlx5_proc_priv {
size_t uar_table_sz;
/* Size of UAR register table. */
void *uar_table[];
/* Table of UAR registers for each process. */
};
#define MLX5_PROC_PRIV(port_id) \
((struct mlx5_proc_priv *)rte_eth_devices[port_id].process_private)
struct mlx5_priv {
struct rte_eth_dev_data *dev_data; /* Pointer to device data. */
struct mlx5_ibv_shared *sh; /* Shared IB device context. */
uint32_t ibv_port; /* IB device port number. */
struct rte_ether_addr mac[MLX5_MAX_MAC_ADDRESSES]; /* MAC addresses. */
BITFIELD_DECLARE(mac_own, uint64_t, MLX5_MAX_MAC_ADDRESSES);
/* Bit-field of MAC addresses owned by the PMD. */
uint16_t vlan_filter[MLX5_MAX_VLAN_IDS]; /* VLAN filters table. */
unsigned int vlan_filter_n; /* Number of configured VLAN filters. */
/* Device properties. */
uint16_t mtu; /* Configured MTU. */
unsigned int isolated:1; /* Whether isolated mode is enabled. */
unsigned int representor:1; /* Device is a port representor. */
unsigned int master:1; /* Device is a E-Switch master. */
unsigned int dr_shared:1; /* DV/DR data is shared. */
uint16_t domain_id; /* Switch domain identifier. */
uint16_t vport_id; /* Associated VF vport index (if any). */
int32_t representor_id; /* Port representor identifier. */
/* RX/TX queues. */
unsigned int rxqs_n; /* RX queues array size. */
unsigned int txqs_n; /* TX queues array size. */
struct mlx5_rxq_data *(*rxqs)[]; /* RX queues. */
struct mlx5_txq_data *(*txqs)[]; /* TX queues. */
struct rte_mempool *mprq_mp; /* Mempool for Multi-Packet RQ. */
struct rte_eth_rss_conf rss_conf; /* RSS configuration. */
unsigned int (*reta_idx)[]; /* RETA index table. */
unsigned int reta_idx_n; /* RETA index size. */
struct mlx5_drop drop_queue; /* Flow drop queues. */
struct mlx5_flows flows; /* RTE Flow rules. */
struct mlx5_flows ctrl_flows; /* Control flow rules. */
LIST_HEAD(counters, mlx5_flow_counter) flow_counters;
/* Flow counters. */
LIST_HEAD(rxq, mlx5_rxq_ctrl) rxqsctrl; /* DPDK Rx queues. */
LIST_HEAD(rxqibv, mlx5_rxq_ibv) rxqsibv; /* Verbs Rx queues. */
LIST_HEAD(hrxq, mlx5_hrxq) hrxqs; /* Verbs Hash Rx queues. */
LIST_HEAD(txq, mlx5_txq_ctrl) txqsctrl; /* DPDK Tx queues. */
LIST_HEAD(txqibv, mlx5_txq_ibv) txqsibv; /* Verbs Tx queues. */
/* Verbs Indirection tables. */
LIST_HEAD(ind_tables, mlx5_ind_table_ibv) ind_tbls;
/* Pointer to next element. */
rte_atomic32_t refcnt; /**< Reference counter. */
struct ibv_flow_action *verbs_action;
/**< Verbs modify header action object. */
uint8_t ft_type; /**< Flow table type, Rx or Tx. */
/* Tags resources cache. */
uint32_t link_speed_capa; /* Link speed capabilities. */
struct mlx5_xstats_ctrl xstats_ctrl; /* Extended stats control. */
struct mlx5_stats_ctrl stats_ctrl; /* Stats control. */
struct mlx5_dev_config config; /* Device configuration. */
struct mlx5_verbs_alloc_ctx verbs_alloc_ctx;
/* Context for Verbs allocator. */
int nl_socket_rdma; /* Netlink socket (NETLINK_RDMA). */
int nl_socket_route; /* Netlink socket (NETLINK_ROUTE). */
uint32_t nl_sn; /* Netlink message sequence number. */
#ifndef RTE_ARCH_64
rte_spinlock_t uar_lock_cq; /* CQs share a common distinct UAR */
rte_spinlock_t uar_lock[MLX5_UAR_PAGE_NUM_MAX];
/* UAR same-page access control required in 32bit implementations. */
#endif
};
#define PORT_ID(priv) ((priv)->dev_data->port_id)
#define ETH_DEV(priv) (&rte_eth_devices[PORT_ID(priv)])
/* mlx5.c */
int mlx5_getenv_int(const char *);
int mlx5_proc_priv_init(struct rte_eth_dev *dev);
/* mlx5_ethdev.c */
int mlx5_get_ifname(const struct rte_eth_dev *dev, char (*ifname)[IF_NAMESIZE]);
int mlx5_get_ifname_base(const struct rte_eth_dev *base,
const struct rte_eth_dev *dev,
char (*ifname)[IF_NAMESIZE]);
int mlx5_get_master_ifname(const char *ibdev_path, char (*ifname)[IF_NAMESIZE]);
unsigned int mlx5_ifindex(const struct rte_eth_dev *dev);
int mlx5_ifreq(const struct rte_eth_dev *dev, int req, struct ifreq *ifr);
int mlx5_ifreq_base(const struct rte_eth_dev *base,
const struct rte_eth_dev *dev,
int req, struct ifreq *ifr);
int mlx5_get_mtu(struct rte_eth_dev *dev, uint16_t *mtu);
int mlx5_set_flags(struct rte_eth_dev *dev, unsigned int keep,
unsigned int flags);
int mlx5_dev_configure(struct rte_eth_dev *dev);
void mlx5_dev_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *info);
int mlx5_read_clock(struct rte_eth_dev *dev, uint64_t *clock);
int mlx5_fw_version_get(struct rte_eth_dev *dev, char *fw_ver, size_t fw_size);
const uint32_t *mlx5_dev_supported_ptypes_get(struct rte_eth_dev *dev);
int mlx5_link_update(struct rte_eth_dev *dev, int wait_to_complete);
int mlx5_force_link_status_change(struct rte_eth_dev *dev, int status);
int mlx5_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu);
int mlx5_dev_get_flow_ctrl(struct rte_eth_dev *dev,
struct rte_eth_fc_conf *fc_conf);
int mlx5_dev_set_flow_ctrl(struct rte_eth_dev *dev,
struct rte_eth_fc_conf *fc_conf);
int mlx5_ibv_device_to_pci_addr(const struct ibv_device *device,
struct rte_pci_addr *pci_addr);
void mlx5_dev_link_status_handler(void *arg);
void mlx5_dev_interrupt_handler(void *arg);
void mlx5_dev_interrupt_handler_uninstall(struct rte_eth_dev *dev);
void mlx5_dev_interrupt_handler_install(struct rte_eth_dev *dev);
int mlx5_set_link_down(struct rte_eth_dev *dev);
int mlx5_set_link_up(struct rte_eth_dev *dev);
int mlx5_is_removed(struct rte_eth_dev *dev);
eth_tx_burst_t mlx5_select_tx_function(struct rte_eth_dev *dev);
eth_rx_burst_t mlx5_select_rx_function(struct rte_eth_dev *dev);
unsigned int mlx5_dev_to_port_id(const struct rte_device *dev,
uint16_t *port_list,
unsigned int port_list_n);
int mlx5_port_to_eswitch_info(uint16_t port, uint16_t *es_domain_id,
uint16_t *es_port_id);
int mlx5_sysfs_switch_info(unsigned int ifindex,
struct mlx5_switch_info *info);
net/mlx5: support PF representor On BlueField platform we have the new entity - PF representor. This one represents the PCI PF attached to external host on the side of ARM. The traffic sent by the external host to the NIC via PF will be seem by ARM on this PF representor. This patch refactors port recognizing capability on the base of physical port name. We have two groups of name formats. Legacy name formats are supported by kernels before ver 5.0 (being more precise - before the patch [1]) or before Mellanox OFED 4.6, and new naming formats added by the patch [1]. Legacy naming formats are supported: - missing physical port name (no sysfs/netlink key) at all, master is assumed - decimal digits (for example "12"), representor is assumed, the value is the index of attached VF New naming formats are supported: - "p" followed by decimal digits, for example "p2", master is assumed - "pf" followed by PF index concatenated with "vf" followed by VF index, for example "pf0vf1", representor is assumed. If index of VF is "-1" it is a special case of host PF representor, this representor must be indexed in devargs as 65535, for example representor=[0-3,65535] will allow representors for VF0, VF1, VF2, VF3 and for host PF. Note: do not specify representor=[0-65535], it causes devargs processing error, because number of ports (rte_eth_dev) is limited. Applications should distinguish representors and master devices exclusively by device flag RTE_ETH_DEV_REPRESENTOR and do not rely on switch port_id (mlx5 PMD deduces ones from representor_id) values returned by dev_infos_get() API. [1] https://www.spinics.net/lists/netdev/msg547007.html Linux-tree: c12ecc23 (Or Gerlitz 2018-04-25 17:32 +0300) "net/mlx5e: Move to use common phys port names for vport representors" Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com> Acked-by: Shahaf Shuler <shahafs@mellanox.com>
2019-04-16 14:10:28 +00:00
void mlx5_sysfs_check_switch_info(bool device_dir,
struct mlx5_switch_info *switch_info);
void mlx5_nl_check_switch_info(bool nun_vf_set,
struct mlx5_switch_info *switch_info);
void mlx5_translate_port_name(const char *port_name_in,
struct mlx5_switch_info *port_info_out);
void mlx5_intr_callback_unregister(const struct rte_intr_handle *handle,
rte_intr_callback_fn cb_fn, void *cb_arg);
/* mlx5_mac.c */
net: add rte prefix to ether defines Add 'RTE_' prefix to defines: - rename ETHER_ADDR_LEN as RTE_ETHER_ADDR_LEN. - rename ETHER_TYPE_LEN as RTE_ETHER_TYPE_LEN. - rename ETHER_CRC_LEN as RTE_ETHER_CRC_LEN. - rename ETHER_HDR_LEN as RTE_ETHER_HDR_LEN. - rename ETHER_MIN_LEN as RTE_ETHER_MIN_LEN. - rename ETHER_MAX_LEN as RTE_ETHER_MAX_LEN. - rename ETHER_MTU as RTE_ETHER_MTU. - rename ETHER_MAX_VLAN_FRAME_LEN as RTE_ETHER_MAX_VLAN_FRAME_LEN. - rename ETHER_MAX_VLAN_ID as RTE_ETHER_MAX_VLAN_ID. - rename ETHER_MAX_JUMBO_FRAME_LEN as RTE_ETHER_MAX_JUMBO_FRAME_LEN. - rename ETHER_MIN_MTU as RTE_ETHER_MIN_MTU. - rename ETHER_LOCAL_ADMIN_ADDR as RTE_ETHER_LOCAL_ADMIN_ADDR. - rename ETHER_GROUP_ADDR as RTE_ETHER_GROUP_ADDR. - rename ETHER_TYPE_IPv4 as RTE_ETHER_TYPE_IPv4. - rename ETHER_TYPE_IPv6 as RTE_ETHER_TYPE_IPv6. - rename ETHER_TYPE_ARP as RTE_ETHER_TYPE_ARP. - rename ETHER_TYPE_VLAN as RTE_ETHER_TYPE_VLAN. - rename ETHER_TYPE_RARP as RTE_ETHER_TYPE_RARP. - rename ETHER_TYPE_QINQ as RTE_ETHER_TYPE_QINQ. - rename ETHER_TYPE_ETAG as RTE_ETHER_TYPE_ETAG. - rename ETHER_TYPE_1588 as RTE_ETHER_TYPE_1588. - rename ETHER_TYPE_SLOW as RTE_ETHER_TYPE_SLOW. - rename ETHER_TYPE_TEB as RTE_ETHER_TYPE_TEB. - rename ETHER_TYPE_LLDP as RTE_ETHER_TYPE_LLDP. - rename ETHER_TYPE_MPLS as RTE_ETHER_TYPE_MPLS. - rename ETHER_TYPE_MPLSM as RTE_ETHER_TYPE_MPLSM. - rename ETHER_VXLAN_HLEN as RTE_ETHER_VXLAN_HLEN. - rename ETHER_ADDR_FMT_SIZE as RTE_ETHER_ADDR_FMT_SIZE. - rename VXLAN_GPE_TYPE_IPV4 as RTE_VXLAN_GPE_TYPE_IPV4. - rename VXLAN_GPE_TYPE_IPV6 as RTE_VXLAN_GPE_TYPE_IPV6. - rename VXLAN_GPE_TYPE_ETH as RTE_VXLAN_GPE_TYPE_ETH. - rename VXLAN_GPE_TYPE_NSH as RTE_VXLAN_GPE_TYPE_NSH. - rename VXLAN_GPE_TYPE_MPLS as RTE_VXLAN_GPE_TYPE_MPLS. - rename VXLAN_GPE_TYPE_GBP as RTE_VXLAN_GPE_TYPE_GBP. - rename VXLAN_GPE_TYPE_VBNG as RTE_VXLAN_GPE_TYPE_VBNG. - rename ETHER_VXLAN_GPE_HLEN as RTE_ETHER_VXLAN_GPE_HLEN. Do not update the command line library to avoid adding a dependency to librte_net. Signed-off-by: Olivier Matz <olivier.matz@6wind.com> Reviewed-by: Stephen Hemminger <stephen@networkplumber.org> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-05-21 16:13:05 +00:00
int mlx5_get_mac(struct rte_eth_dev *dev, uint8_t (*mac)[RTE_ETHER_ADDR_LEN]);
void mlx5_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index);
int mlx5_mac_addr_add(struct rte_eth_dev *dev, struct rte_ether_addr *mac,
uint32_t index, uint32_t vmdq);
int mlx5_mac_addr_set(struct rte_eth_dev *dev, struct rte_ether_addr *mac_addr);
int mlx5_set_mc_addr_list(struct rte_eth_dev *dev,
struct rte_ether_addr *mc_addr_set,
uint32_t nb_mc_addr);
/* mlx5_rss.c */
int mlx5_rss_hash_update(struct rte_eth_dev *dev,
struct rte_eth_rss_conf *rss_conf);
int mlx5_rss_hash_conf_get(struct rte_eth_dev *dev,
struct rte_eth_rss_conf *rss_conf);
int mlx5_rss_reta_index_resize(struct rte_eth_dev *dev, unsigned int reta_size);
int mlx5_dev_rss_reta_query(struct rte_eth_dev *dev,
struct rte_eth_rss_reta_entry64 *reta_conf,
uint16_t reta_size);
int mlx5_dev_rss_reta_update(struct rte_eth_dev *dev,
struct rte_eth_rss_reta_entry64 *reta_conf,
uint16_t reta_size);
/* mlx5_rxmode.c */
void mlx5_promiscuous_enable(struct rte_eth_dev *dev);
void mlx5_promiscuous_disable(struct rte_eth_dev *dev);
void mlx5_allmulticast_enable(struct rte_eth_dev *dev);
void mlx5_allmulticast_disable(struct rte_eth_dev *dev);
/* mlx5_stats.c */
void mlx5_stats_init(struct rte_eth_dev *dev);
int mlx5_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats);
void mlx5_stats_reset(struct rte_eth_dev *dev);
int mlx5_xstats_get(struct rte_eth_dev *dev, struct rte_eth_xstat *stats,
unsigned int n);
void mlx5_xstats_reset(struct rte_eth_dev *dev);
int mlx5_xstats_get_names(struct rte_eth_dev *dev __rte_unused,
struct rte_eth_xstat_name *xstats_names,
unsigned int n);
/* mlx5_vlan.c */
int mlx5_vlan_filter_set(struct rte_eth_dev *dev, uint16_t vlan_id, int on);
void mlx5_vlan_strip_queue_set(struct rte_eth_dev *dev, uint16_t queue, int on);
int mlx5_vlan_offload_set(struct rte_eth_dev *dev, int mask);
/* mlx5_trigger.c */
int mlx5_dev_start(struct rte_eth_dev *dev);
void mlx5_dev_stop(struct rte_eth_dev *dev);
int mlx5_traffic_enable(struct rte_eth_dev *dev);
void mlx5_traffic_disable(struct rte_eth_dev *dev);
int mlx5_traffic_restart(struct rte_eth_dev *dev);
/* mlx5_flow.c */
int mlx5_flow_discover_priorities(struct rte_eth_dev *dev);
void mlx5_flow_print(struct rte_flow *flow);
int mlx5_flow_validate(struct rte_eth_dev *dev,
const struct rte_flow_attr *attr,
const struct rte_flow_item items[],
const struct rte_flow_action actions[],
struct rte_flow_error *error);
struct rte_flow *mlx5_flow_create(struct rte_eth_dev *dev,
const struct rte_flow_attr *attr,
const struct rte_flow_item items[],
const struct rte_flow_action actions[],
struct rte_flow_error *error);
int mlx5_flow_destroy(struct rte_eth_dev *dev, struct rte_flow *flow,
struct rte_flow_error *error);
void mlx5_flow_list_flush(struct rte_eth_dev *dev, struct mlx5_flows *list);
int mlx5_flow_flush(struct rte_eth_dev *dev, struct rte_flow_error *error);
int mlx5_flow_query(struct rte_eth_dev *dev, struct rte_flow *flow,
const struct rte_flow_action *action, void *data,
struct rte_flow_error *error);
int mlx5_flow_isolate(struct rte_eth_dev *dev, int enable,
struct rte_flow_error *error);
int mlx5_dev_filter_ctrl(struct rte_eth_dev *dev,
enum rte_filter_type filter_type,
enum rte_filter_op filter_op,
void *arg);
int mlx5_flow_start(struct rte_eth_dev *dev, struct mlx5_flows *list);
void mlx5_flow_stop(struct rte_eth_dev *dev, struct mlx5_flows *list);
int mlx5_flow_verify(struct rte_eth_dev *dev);
int mlx5_ctrl_flow_vlan(struct rte_eth_dev *dev,
struct rte_flow_item_eth *eth_spec,
struct rte_flow_item_eth *eth_mask,
struct rte_flow_item_vlan *vlan_spec,
struct rte_flow_item_vlan *vlan_mask);
int mlx5_ctrl_flow(struct rte_eth_dev *dev,
struct rte_flow_item_eth *eth_spec,
struct rte_flow_item_eth *eth_mask);
int mlx5_flow_create_drop_queue(struct rte_eth_dev *dev);
void mlx5_flow_delete_drop_queue(struct rte_eth_dev *dev);
/* mlx5_mp.c */
void mlx5_mp_req_start_rxtx(struct rte_eth_dev *dev);
void mlx5_mp_req_stop_rxtx(struct rte_eth_dev *dev);
int mlx5_mp_req_mr_create(struct rte_eth_dev *dev, uintptr_t addr);
int mlx5_mp_req_verbs_cmd_fd(struct rte_eth_dev *dev);
int mlx5_mp_req_queue_state_modify(struct rte_eth_dev *dev,
struct mlx5_mp_arg_queue_state_modify *sm);
int mlx5_mp_init_primary(void);
void mlx5_mp_uninit_primary(void);
int mlx5_mp_init_secondary(void);
void mlx5_mp_uninit_secondary(void);
/* mlx5_nl.c */
int mlx5_nl_init(int protocol);
int mlx5_nl_mac_addr_add(struct rte_eth_dev *dev, struct rte_ether_addr *mac,
uint32_t index);
int mlx5_nl_mac_addr_remove(struct rte_eth_dev *dev, struct rte_ether_addr *mac,
uint32_t index);
void mlx5_nl_mac_addr_sync(struct rte_eth_dev *dev);
void mlx5_nl_mac_addr_flush(struct rte_eth_dev *dev);
int mlx5_nl_promisc(struct rte_eth_dev *dev, int enable);
int mlx5_nl_allmulti(struct rte_eth_dev *dev, int enable);
unsigned int mlx5_nl_portnum(int nl, const char *name);
unsigned int mlx5_nl_ifindex(int nl, const char *name, uint32_t pindex);
int mlx5_nl_switch_info(int nl, unsigned int ifindex,
struct mlx5_switch_info *info);
/* mlx5_devx_cmds.c */
int mlx5_devx_cmd_flow_counter_alloc(struct ibv_context *ctx,
struct mlx5_devx_counter_set *dcx);
int mlx5_devx_cmd_flow_counter_free(struct mlx5dv_devx_obj *obj);
int mlx5_devx_cmd_flow_counter_query(struct mlx5_devx_counter_set *dcx,
int clear,
uint64_t *pkts, uint64_t *bytes);
int mlx5_devx_cmd_query_hca_attr(struct ibv_context *ctx,
struct mlx5_hca_attr *attr);
#endif /* RTE_PMD_MLX5_H_ */