d/numam-dpdk
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
1785806098
numam-dpdk/drivers/net/iavf/iavf_ethdev.c

2880 lines
76 KiB
C
Raw Normal View History

net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
/* SPDX-License-Identifier: BSD-3-Clause
* Copyright(c) 2017 Intel Corporation
*/
eal: remove unneeded includes from a public header Do not include <ctype.h>, <errno.h>, and <stdlib.h> from <rte_common.h>, because they are not used by this file. Include the needed headers directly from the files that need them. Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com> Acked-by: Bruce Richardson <bruce.richardson@intel.com>
2022-08-27 11:32:22 +00:00
#include <ctype.h>
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
#include <sys/queue.h>
#include <stdio.h>
#include <errno.h>
#include <stdint.h>
#include <string.h>
#include <unistd.h>
#include <stdarg.h>
#include <inttypes.h>
#include <rte_byteorder.h>
#include <rte_common.h>
#include <rte_interrupts.h>
#include <rte_debug.h>
#include <rte_pci.h>
net/iavf: enable interrupt polling For VF hosted by Intel 700 series NICs, internal Rx interrupt and adminq interrupt share the same source, that cause a lot CPU cycles be wasted on interrupt handler on Rx path. The patch disable PCI interrupt and remove the interrupt handler, replace it with a low frequency(50ms) interrupt polling daemon which is implemented by registering an alarm callback periodically. The virtual channel capability bit VIRTCHNL_VF_OFFLOAD_WB_ON_ITR can be used to negotiate if iavf PMD needs to enable background alarm or not, so ideally this change will not impact the case hosted by Intel 800 series NICS. This patch implements the same logic with an early i40e commit: commit 864a800d706d ("net/i40e: remove VF interrupt handler") Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Pallavi Kadam <pallavi.kadam@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-08-25 08:34:35 +00:00
#include <rte_alarm.h>
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
#include <rte_atomic.h>
#include <rte_eal.h>
#include <rte_ether.h>
ethdev: make driver-only headers private The rte_ethdev_driver.h, rte_ethdev_vdev.h and rte_ethdev_pci.h files are for drivers only and should be a private to DPDK and not installed. Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com> Acked-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: Steven Webster <steven.webster@windriver.com>
2021-01-29 16:48:19 +00:00
#include <ethdev_driver.h>
#include <ethdev_pci.h>
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
#include <rte_malloc.h>
#include <rte_memzone.h>
dev: hide driver object Make rte_driver opaque for non internal users. This will make extending this object possible without breaking the ABI. Introduce a new driver header and move rte_driver definition. Update drivers and library to use the internal header. Some applications may have been dereferencing rte_driver objects, mark this object's accessors as stable. Signed-off-by: David Marchand <david.marchand@redhat.com> Acked-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Jay Jayatheerthan <jay.jayatheerthan@intel.com> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Akhil Goyal <gakhil@marvell.com> Acked-by: Abhinandan Gujjar <abhinandan.gujjar@intel.com>
2022-07-28 15:26:37 +00:00
#include <dev_driver.h>
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
net/iavf: rename avf to iavf Rename Intel Ethernet Adaptive Virtual Function driver avf to iavf. This is the first patch which will only renames the directory name, lib name, filenames and updates the new name in makefile and meson files. Also updates the #include files in source files. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:51 +00:00
#include "iavf.h"
#include "iavf_rxtx.h"
net/iavf: support generic flow API This patch added iavf_flow_create, iavf_flow_destroy, iavf_flow_flush and iavf_flow_validate support, these are used to handle all the generic filters. This patch supported basic L2, L3, L4 and GTPU patterns. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-04-03 05:42:41 +00:00
#include "iavf_generic_flow.h"
net/iavf: support flex desc metadata extraction Enable metadata extraction for flexible descriptors in AVF, that would allow network function directly get metadata without additional parsing which would reduce the CPU cost for VFs. The enabling metadata extractions involve the metadata of VLAN/IPv4/IPv6/IPv6-FLOW/TCP/MPLS flexible descriptors, and the VF could negotiate the capability of the flexible descriptor with PF and correspondingly configure the specific offload at receiving queues. Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Haiyue Wang <haiyue.wang@intel.com>
2020-10-30 08:40:30 +00:00
#include "rte_pmd_iavf.h"
net/iavf: support IPsec inline crypto Add support for inline crypto for IPsec, for ESP transport and tunnel over IPv4 and IPv6, as well as supporting the offload for ESP over UDP, and in conjunction with TSO for UDP and TCP flows. Implement support for rte_security packet metadata Add definition for IPsec descriptors, extend support for offload in data and context descriptor to support Add support to virtual channel mailbox for IPsec Crypto request operations. IPsec Crypto requests receive an initial acknowledgment from physical function driver of receipt of request and then an asynchronous response with success/failure of request including any response data. Add enhanced descriptor debugging Refactor of scalar tx burst function to support integration of offload Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Abhijit Sinha <abhijit.sinha@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Reviewed-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:57 +00:00
#include "iavf_ipsec_crypto.h"
net/iavf: support flex desc metadata extraction Enable metadata extraction for flexible descriptors in AVF, that would allow network function directly get metadata without additional parsing which would reduce the CPU cost for VFs. The enabling metadata extractions involve the metadata of VLAN/IPv4/IPv6/IPv6-FLOW/TCP/MPLS flexible descriptors, and the VF could negotiate the capability of the flexible descriptor with PF and correspondingly configure the specific offload at receiving queues. Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Haiyue Wang <haiyue.wang@intel.com>
2020-10-30 08:40:30 +00:00
/* devargs */
#define IAVF_PROTO_XTR_ARG "proto_xtr"
net/iavf: support quanta size configuration This patch adds quanta size configuration support. Quanta size should between 256 and 4096, and be a product of 64. Signed-off-by: Wenjun Wu <wenjun1.wu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-04-22 01:43:00 +00:00
#define IAVF_QUANTA_SIZE_ARG "quanta_size"
net/iavf: support flex desc metadata extraction Enable metadata extraction for flexible descriptors in AVF, that would allow network function directly get metadata without additional parsing which would reduce the CPU cost for VFs. The enabling metadata extractions involve the metadata of VLAN/IPv4/IPv6/IPv6-FLOW/TCP/MPLS flexible descriptors, and the VF could negotiate the capability of the flexible descriptor with PF and correspondingly configure the specific offload at receiving queues. Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Haiyue Wang <haiyue.wang@intel.com>
2020-10-30 08:40:30 +00:00
net/iavf: enable Rx timestamp on flex descriptor Dump Rx timestamp value into dynamic mbuf field by flex descriptor. This feature is turned on by dev config "enable-rx-timestamp". Currently, it's only supported under scalar path. Signed-off-by: Simei Su <simei.su@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-04-28 08:13:45 +00:00
uint64_t iavf_timestamp_dynflag;
int iavf_timestamp_dynfield_offset = -1;
net/iavf: support flex desc metadata extraction Enable metadata extraction for flexible descriptors in AVF, that would allow network function directly get metadata without additional parsing which would reduce the CPU cost for VFs. The enabling metadata extractions involve the metadata of VLAN/IPv4/IPv6/IPv6-FLOW/TCP/MPLS flexible descriptors, and the VF could negotiate the capability of the flexible descriptor with PF and correspondingly configure the specific offload at receiving queues. Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Haiyue Wang <haiyue.wang@intel.com>
2020-10-30 08:40:30 +00:00
static const char * const iavf_valid_args[] = {
IAVF_PROTO_XTR_ARG,
net/iavf: support quanta size configuration This patch adds quanta size configuration support. Quanta size should between 256 and 4096, and be a product of 64. Signed-off-by: Wenjun Wu <wenjun1.wu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-04-22 01:43:00 +00:00
IAVF_QUANTA_SIZE_ARG,
net/iavf: support flex desc metadata extraction Enable metadata extraction for flexible descriptors in AVF, that would allow network function directly get metadata without additional parsing which would reduce the CPU cost for VFs. The enabling metadata extractions involve the metadata of VLAN/IPv4/IPv6/IPv6-FLOW/TCP/MPLS flexible descriptors, and the VF could negotiate the capability of the flexible descriptor with PF and correspondingly configure the specific offload at receiving queues. Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Haiyue Wang <haiyue.wang@intel.com>
2020-10-30 08:40:30 +00:00
NULL
};
static const struct rte_mbuf_dynfield iavf_proto_xtr_metadata_param = {
.name = "intel_pmd_dynfield_proto_xtr_metadata",
.size = sizeof(uint32_t),
.align = __alignof__(uint32_t),
.flags = 0,
};
struct iavf_proto_xtr_ol {
const struct rte_mbuf_dynflag param;
uint64_t *ol_flag;
bool required;
};
static struct iavf_proto_xtr_ol iavf_proto_xtr_params[] = {
[IAVF_PROTO_XTR_VLAN] = {
.param = { .name = "intel_pmd_dynflag_proto_xtr_vlan" },
.ol_flag = &rte_pmd_ifd_dynflag_proto_xtr_vlan_mask },
[IAVF_PROTO_XTR_IPV4] = {
.param = { .name = "intel_pmd_dynflag_proto_xtr_ipv4" },
.ol_flag = &rte_pmd_ifd_dynflag_proto_xtr_ipv4_mask },
[IAVF_PROTO_XTR_IPV6] = {
.param = { .name = "intel_pmd_dynflag_proto_xtr_ipv6" },
.ol_flag = &rte_pmd_ifd_dynflag_proto_xtr_ipv6_mask },
[IAVF_PROTO_XTR_IPV6_FLOW] = {
.param = { .name = "intel_pmd_dynflag_proto_xtr_ipv6_flow" },
.ol_flag = &rte_pmd_ifd_dynflag_proto_xtr_ipv6_flow_mask },
[IAVF_PROTO_XTR_TCP] = {
.param = { .name = "intel_pmd_dynflag_proto_xtr_tcp" },
.ol_flag = &rte_pmd_ifd_dynflag_proto_xtr_tcp_mask },
[IAVF_PROTO_XTR_IP_OFFSET] = {
.param = { .name = "intel_pmd_dynflag_proto_xtr_ip_offset" },
.ol_flag = &rte_pmd_ifd_dynflag_proto_xtr_ip_offset_mask },
net/iavf: support IPsec inline crypto Add support for inline crypto for IPsec, for ESP transport and tunnel over IPv4 and IPv6, as well as supporting the offload for ESP over UDP, and in conjunction with TSO for UDP and TCP flows. Implement support for rte_security packet metadata Add definition for IPsec descriptors, extend support for offload in data and context descriptor to support Add support to virtual channel mailbox for IPsec Crypto request operations. IPsec Crypto requests receive an initial acknowledgment from physical function driver of receipt of request and then an asynchronous response with success/failure of request including any response data. Add enhanced descriptor debugging Refactor of scalar tx burst function to support integration of offload Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Abhijit Sinha <abhijit.sinha@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Reviewed-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:57 +00:00
[IAVF_PROTO_XTR_IPSEC_CRYPTO_SAID] = {
.param = {
.name = "intel_pmd_dynflag_proto_xtr_ipsec_crypto_said" },
.ol_flag =
&rte_pmd_ifd_dynflag_proto_xtr_ipsec_crypto_said_mask },
net/iavf: support flex desc metadata extraction Enable metadata extraction for flexible descriptors in AVF, that would allow network function directly get metadata without additional parsing which would reduce the CPU cost for VFs. The enabling metadata extractions involve the metadata of VLAN/IPv4/IPv6/IPv6-FLOW/TCP/MPLS flexible descriptors, and the VF could negotiate the capability of the flexible descriptor with PF and correspondingly configure the specific offload at receiving queues. Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Haiyue Wang <haiyue.wang@intel.com>
2020-10-30 08:40:30 +00:00
};
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
static int iavf_dev_configure(struct rte_eth_dev *dev);
static int iavf_dev_start(struct rte_eth_dev *dev);
ethdev: change stop operation callback to return int Change eth_dev_stop_t return value from void to int. Make eth_dev_stop_t implementations across all drivers to return negative errno values if case of error conditions. Signed-off-by: Ivan Ilchenko <ivan.ilchenko@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2020-10-15 13:30:45 +00:00
static int iavf_dev_stop(struct rte_eth_dev *dev);
ethdev: allow drivers to return error on close The device operation .dev_close was returning void. This driver interface is changed to return an int. Note that the API rte_eth_dev_close() is still returning void, although a deprecation notice is pending to change it as well. Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Reviewed-by: Rosen Xu <rosen.xu@intel.com> Reviewed-by: Sachin Saxena <sachin.saxena@oss.nxp.com> Reviewed-by: Liron Himi <lironh@marvell.com> Reviewed-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Jeff Guo <jia.guo@intel.com> Reviewed-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org>
2020-09-28 23:14:10 +00:00
static int iavf_dev_close(struct rte_eth_dev *dev);
net/iavf: enable port reset This patch is intended to add iavf_dev_reset ops, enable iavf to support "port reset all". Signed-off-by: Lunyuan Cui <lunyuanx.cui@intel.com> Tested-by: Zhaoyan Chen <zhaoyan.chen@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com> Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
2020-04-01 07:12:14 +00:00
static int iavf_dev_reset(struct rte_eth_dev *dev);
ethdev: change device info get callback to return int Change eth_dev_infos_get_t return value from void to int. Make eth_dev_infos_get_t implementations across all drivers to return negative errno values if case of error conditions. Signed-off-by: Ivan Ilchenko <ivan.ilchenko@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-09-12 16:42:28 +00:00
static int iavf_dev_info_get(struct rte_eth_dev *dev,
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
struct rte_eth_dev_info *dev_info);
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
static const uint32_t *iavf_dev_supported_ptypes_get(struct rte_eth_dev *dev);
static int iavf_dev_stats_get(struct rte_eth_dev *dev,
net/avf: support stats Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:58 +00:00
struct rte_eth_stats *stats);
ethdev: make stats and xstats reset callbacks return int Change return value of the callbacks from void to int. Make implementations across all drivers return negative errno values in case of error conditions. Both callbacks are updated together because a large number of drivers assign the same function to both callbacks. Signed-off-by: Igor Romanov <igor.romanov@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-09-06 14:34:54 +00:00
static int iavf_dev_stats_reset(struct rte_eth_dev *dev);
net/iavf: support xstats for inline IPsec crypto Add per queue counters for maintaining statistics for inline IPsec crypto offload, which can be retrieved through the rte_security_session_stats_get() with more detailed errors through the rte_ethdev xstats. Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:58 +00:00
static int iavf_dev_xstats_reset(struct rte_eth_dev *dev);
net/iavf: add extended stats Add implementation of xstats() functions in iavf PMD. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:25 +00:00
static int iavf_dev_xstats_get(struct rte_eth_dev *dev,
struct rte_eth_xstat *xstats, unsigned int n);
static int iavf_dev_xstats_get_names(struct rte_eth_dev *dev,
struct rte_eth_xstat_name *xstats_names,
unsigned int limit);
ethdev: change promiscuous callbacks to return status Enabling/disabling of promiscuous mode is not always successful and it should be taken into account to be able to handle it properly. When correct return status is unclear from driver code, -EAGAIN is used. Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: Matan Azrad <matan@mellanox.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com>
2019-09-14 11:37:24 +00:00
static int iavf_dev_promiscuous_enable(struct rte_eth_dev *dev);
static int iavf_dev_promiscuous_disable(struct rte_eth_dev *dev);
ethdev: change allmulticast callbacks to return status Enabling/disabling of allmulticast mode is not always successful and it should be taken into account to be able to handle it properly. When correct return status is unclear from driver code, -EAGAIN is used. Signed-off-by: Ivan Ilchenko <ivan.ilchenko@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com>
2019-09-24 12:56:10 +00:00
static int iavf_dev_allmulticast_enable(struct rte_eth_dev *dev);
static int iavf_dev_allmulticast_disable(struct rte_eth_dev *dev);
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
static int iavf_dev_add_mac_addr(struct rte_eth_dev *dev,
net: add rte prefix to ether structures Add 'rte_' prefix to structures: - rename struct ether_addr as struct rte_ether_addr. - rename struct ether_hdr as struct rte_ether_hdr. - rename struct vlan_hdr as struct rte_vlan_hdr. - rename struct vxlan_hdr as struct rte_vxlan_hdr. - rename struct vxlan_gpe_hdr as struct rte_vxlan_gpe_hdr. 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 16:13:03 +00:00
struct rte_ether_addr *addr,
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
uint32_t index,
uint32_t pool);
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
static void iavf_dev_del_mac_addr(struct rte_eth_dev *dev, uint32_t index);
static int iavf_dev_vlan_filter_set(struct rte_eth_dev *dev,
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
uint16_t vlan_id, int on);
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
static int iavf_dev_vlan_offload_set(struct rte_eth_dev *dev, int mask);
static int iavf_dev_rss_reta_update(struct rte_eth_dev *dev,
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
struct rte_eth_rss_reta_entry64 *reta_conf,
uint16_t reta_size);
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
static int iavf_dev_rss_reta_query(struct rte_eth_dev *dev,
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
struct rte_eth_rss_reta_entry64 *reta_conf,
uint16_t reta_size);
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
static int iavf_dev_rss_hash_update(struct rte_eth_dev *dev,
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
struct rte_eth_rss_conf *rss_conf);
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
static int iavf_dev_rss_hash_conf_get(struct rte_eth_dev *dev,
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
struct rte_eth_rss_conf *rss_conf);
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
static int iavf_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu);
static int iavf_dev_set_default_mac_addr(struct rte_eth_dev *dev,
net: add rte prefix to ether structures Add 'rte_' prefix to structures: - rename struct ether_addr as struct rte_ether_addr. - rename struct ether_hdr as struct rte_ether_hdr. - rename struct vlan_hdr as struct rte_vlan_hdr. - rename struct vxlan_hdr as struct rte_vxlan_hdr. - rename struct vxlan_gpe_hdr as struct rte_vxlan_gpe_hdr. 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 16:13:03 +00:00
struct rte_ether_addr *mac_addr);
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
static int iavf_dev_rx_queue_intr_enable(struct rte_eth_dev *dev,
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
uint16_t queue_id);
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
static int iavf_dev_rx_queue_intr_disable(struct rte_eth_dev *dev,
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
uint16_t queue_id);
ethdev: replace callback getting filter operations Since rte_flow is the only API for filtering operations, the legacy driver interface filter_ctrl was too much complicated for the simple task of getting the struct rte_flow_ops. The filter type RTE_ETH_FILTER_GENERIC and the filter operarion RTE_ETH_FILTER_GET are removed. The new driver callback flow_ops_get replaces filter_ctrl. Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2021-03-21 09:00:00 +00:00
static int iavf_dev_flow_ops_get(struct rte_eth_dev *dev,
const struct rte_flow_ops **ops);
net/iavf: support multicast configuration This patch enable add multicast address for iavf. Signed-off-by: Wei Zhao <wei.zhao1@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-07-13 07:48:11 +00:00
static int iavf_set_mc_addr_list(struct rte_eth_dev *dev,
struct rte_ether_addr *mc_addrs,
uint32_t mc_addrs_num);
net/iavf: query QoS capabilities and set queue TC mapping This patch added the support for VF to config the ETS-based Tx QoS, including querying current QoS configuration from PF and config queue TC mapping. PF QoS is configured in advance and the queried info is provided to the user for future usage. VF queues are mapped to different TCs in PF through virtchnl. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-07-01 11:41:22 +00:00
static int iavf_tm_ops_get(struct rte_eth_dev *dev __rte_unused, void *arg);
net/iavf: support generic flow API This patch added iavf_flow_create, iavf_flow_destroy, iavf_flow_flush and iavf_flow_validate support, these are used to handle all the generic filters. This patch supported basic L2, L3, L4 and GTPU patterns. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-04-03 05:42:41 +00:00
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
static const struct rte_pci_id pci_id_iavf_map[] = {
{ RTE_PCI_DEVICE(IAVF_INTEL_VENDOR_ID, IAVF_DEV_ID_ADAPTIVE_VF) },
net/iavf: deprecate i40evf PMD The i40evf PMD will be deprecated, iavf will be the only VF driver for Intel 700 serial (i40e) NIC family. To reach this, there will be 2 steps: Step 1: iavf will be the default VF driver, while i40evf still can be selected by devarg: "driver=i40evf". This is covered by this patch, which include: 1) add all 700 serial NIC VF device ID into iavf PMD 2) skip probe if devargs contain "driver=i40evf" in iavf 3) continue probe if devargs contain "driver=i40evf" in i40evf Step 2: i40evf and related devarg are removed, this will happen at DPDK 21.11 Between step 1 and step 2, no new feature will be added into i40evf except bug fix. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-19 03:05:39 +00:00
{ RTE_PCI_DEVICE(IAVF_INTEL_VENDOR_ID, IAVF_DEV_ID_VF) },
{ RTE_PCI_DEVICE(IAVF_INTEL_VENDOR_ID, IAVF_DEV_ID_VF_HV) },
{ RTE_PCI_DEVICE(IAVF_INTEL_VENDOR_ID, IAVF_DEV_ID_X722_VF) },
{ RTE_PCI_DEVICE(IAVF_INTEL_VENDOR_ID, IAVF_DEV_ID_X722_A0_VF) },
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
{ .vendor_id = 0, /* sentinel */ },
};
net/iavf: add extended stats Add implementation of xstats() functions in iavf PMD. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:25 +00:00
struct rte_iavf_xstats_name_off {
char name[RTE_ETH_XSTATS_NAME_SIZE];
unsigned int offset;
};
net/iavf: support xstats for inline IPsec crypto Add per queue counters for maintaining statistics for inline IPsec crypto offload, which can be retrieved through the rte_security_session_stats_get() with more detailed errors through the rte_ethdev xstats. Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:58 +00:00
#define _OFF_OF(a) offsetof(struct iavf_eth_xstats, a)
net/iavf: add extended stats Add implementation of xstats() functions in iavf PMD. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:25 +00:00
static const struct rte_iavf_xstats_name_off rte_iavf_stats_strings[] = {
net/iavf: support xstats for inline IPsec crypto Add per queue counters for maintaining statistics for inline IPsec crypto offload, which can be retrieved through the rte_security_session_stats_get() with more detailed errors through the rte_ethdev xstats. Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:58 +00:00
{"rx_bytes", _OFF_OF(eth_stats.rx_bytes)},
{"rx_unicast_packets", _OFF_OF(eth_stats.rx_unicast)},
{"rx_multicast_packets", _OFF_OF(eth_stats.rx_multicast)},
{"rx_broadcast_packets", _OFF_OF(eth_stats.rx_broadcast)},
{"rx_dropped_packets", _OFF_OF(eth_stats.rx_discards)},
net/iavf: add extended stats Add implementation of xstats() functions in iavf PMD. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:25 +00:00
{"rx_unknown_protocol_packets", offsetof(struct iavf_eth_stats,
rx_unknown_protocol)},
net/iavf: support xstats for inline IPsec crypto Add per queue counters for maintaining statistics for inline IPsec crypto offload, which can be retrieved through the rte_security_session_stats_get() with more detailed errors through the rte_ethdev xstats. Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:58 +00:00
{"tx_bytes", _OFF_OF(eth_stats.tx_bytes)},
{"tx_unicast_packets", _OFF_OF(eth_stats.tx_unicast)},
{"tx_multicast_packets", _OFF_OF(eth_stats.tx_multicast)},
{"tx_broadcast_packets", _OFF_OF(eth_stats.tx_broadcast)},
{"tx_dropped_packets", _OFF_OF(eth_stats.tx_discards)},
{"tx_error_packets", _OFF_OF(eth_stats.tx_errors)},
{"inline_ipsec_crypto_ipackets", _OFF_OF(ips_stats.icount)},
{"inline_ipsec_crypto_ibytes", _OFF_OF(ips_stats.ibytes)},
{"inline_ipsec_crypto_ierrors", _OFF_OF(ips_stats.ierrors.count)},
{"inline_ipsec_crypto_ierrors_sad_lookup",
_OFF_OF(ips_stats.ierrors.sad_miss)},
{"inline_ipsec_crypto_ierrors_not_processed",
_OFF_OF(ips_stats.ierrors.not_processed)},
{"inline_ipsec_crypto_ierrors_icv_fail",
_OFF_OF(ips_stats.ierrors.icv_check)},
{"inline_ipsec_crypto_ierrors_length",
_OFF_OF(ips_stats.ierrors.ipsec_length)},
{"inline_ipsec_crypto_ierrors_misc",
_OFF_OF(ips_stats.ierrors.misc)},
net/iavf: add extended stats Add implementation of xstats() functions in iavf PMD. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:25 +00:00
};
net/iavf: support xstats for inline IPsec crypto Add per queue counters for maintaining statistics for inline IPsec crypto offload, which can be retrieved through the rte_security_session_stats_get() with more detailed errors through the rte_ethdev xstats. Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:58 +00:00
#undef _OFF_OF
net/iavf: add extended stats Add implementation of xstats() functions in iavf PMD. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:25 +00:00
#define IAVF_NB_XSTATS (sizeof(rte_iavf_stats_strings) / \
sizeof(rte_iavf_stats_strings[0]))
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
static const struct eth_dev_ops iavf_eth_dev_ops = {
.dev_configure = iavf_dev_configure,
.dev_start = iavf_dev_start,
.dev_stop = iavf_dev_stop,
.dev_close = iavf_dev_close,
net/iavf: enable port reset This patch is intended to add iavf_dev_reset ops, enable iavf to support "port reset all". Signed-off-by: Lunyuan Cui <lunyuanx.cui@intel.com> Tested-by: Zhaoyan Chen <zhaoyan.chen@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com> Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
2020-04-01 07:12:14 +00:00
.dev_reset = iavf_dev_reset,
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
.dev_infos_get = iavf_dev_info_get,
.dev_supported_ptypes_get = iavf_dev_supported_ptypes_get,
.link_update = iavf_dev_link_update,
.stats_get = iavf_dev_stats_get,
net/iavf: fix stats reset stats_reset has been missed when support stats in iavf driver. This patch add statistics reset function. Fixes: f4a41a6953af ("net/avf: support stats") Cc: stable@dpdk.org Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2019-04-22 02:18:37 +00:00
.stats_reset = iavf_dev_stats_reset,
net/iavf: add extended stats Add implementation of xstats() functions in iavf PMD. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:25 +00:00
.xstats_get = iavf_dev_xstats_get,
.xstats_get_names = iavf_dev_xstats_get_names,
net/iavf: support xstats for inline IPsec crypto Add per queue counters for maintaining statistics for inline IPsec crypto offload, which can be retrieved through the rte_security_session_stats_get() with more detailed errors through the rte_ethdev xstats. Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:58 +00:00
.xstats_reset = iavf_dev_xstats_reset,
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
.promiscuous_enable = iavf_dev_promiscuous_enable,
.promiscuous_disable = iavf_dev_promiscuous_disable,
.allmulticast_enable = iavf_dev_allmulticast_enable,
.allmulticast_disable = iavf_dev_allmulticast_disable,
.mac_addr_add = iavf_dev_add_mac_addr,
.mac_addr_remove = iavf_dev_del_mac_addr,
net/iavf: support multicast configuration This patch enable add multicast address for iavf. Signed-off-by: Wei Zhao <wei.zhao1@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-07-13 07:48:11 +00:00
.set_mc_addr_list = iavf_set_mc_addr_list,
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
.vlan_filter_set = iavf_dev_vlan_filter_set,
.vlan_offload_set = iavf_dev_vlan_offload_set,
.rx_queue_start = iavf_dev_rx_queue_start,
.rx_queue_stop = iavf_dev_rx_queue_stop,
.tx_queue_start = iavf_dev_tx_queue_start,
.tx_queue_stop = iavf_dev_tx_queue_stop,
.rx_queue_setup = iavf_dev_rx_queue_setup,
.rx_queue_release = iavf_dev_rx_queue_release,
.tx_queue_setup = iavf_dev_tx_queue_setup,
.tx_queue_release = iavf_dev_tx_queue_release,
.mac_addr_set = iavf_dev_set_default_mac_addr,
.reta_update = iavf_dev_rss_reta_update,
.reta_query = iavf_dev_rss_reta_query,
.rss_hash_update = iavf_dev_rss_hash_update,
.rss_hash_conf_get = iavf_dev_rss_hash_conf_get,
.rxq_info_get = iavf_dev_rxq_info_get,
.txq_info_get = iavf_dev_txq_info_get,
.mtu_set = iavf_dev_mtu_set,
.rx_queue_intr_enable = iavf_dev_rx_queue_intr_enable,
.rx_queue_intr_disable = iavf_dev_rx_queue_intr_disable,
ethdev: replace callback getting filter operations Since rte_flow is the only API for filtering operations, the legacy driver interface filter_ctrl was too much complicated for the simple task of getting the struct rte_flow_ops. The filter type RTE_ETH_FILTER_GENERIC and the filter operarion RTE_ETH_FILTER_GET are removed. The new driver callback flow_ops_get replaces filter_ctrl. Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2021-03-21 09:00:00 +00:00
.flow_ops_get = iavf_dev_flow_ops_get,
net/iavf: cleanup Tx buffers Add support to the iavf driver for the API rte_eth_tx_done_cleanup to force free consumed buffers on Tx ring. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:24 +00:00
.tx_done_cleanup = iavf_dev_tx_done_cleanup,
net/iavf: implement power management Implement support for the power management API by implementing a `get_monitor_addr` function that will return an address of an RX ring's status bit. This patch is basically a cut-and-paste of the changes already committed in ixgbe, i40e and ice drivers in 21.02. This extends the availability of the power-saving mechanism to the iavf driver, which is needed for those use-cases using virtual functions. Patchset where PMD Power Management added in 21.02: http://patchwork.dpdk.org/project/dpdk/list/?series=14756 Signed-off-by: David Hunt <david.hunt@intel.com> Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
2021-03-11 11:55:10 +00:00
.get_monitor_addr = iavf_get_monitor_addr,
net/iavf: query QoS capabilities and set queue TC mapping This patch added the support for VF to config the ETS-based Tx QoS, including querying current QoS configuration from PF and config queue TC mapping. PF QoS is configured in advance and the queried info is provided to the user for future usage. VF queues are mapped to different TCs in PF through virtchnl. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-07-01 11:41:22 +00:00
.tm_ops_get = iavf_tm_ops_get,
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
};
net/iavf: query QoS capabilities and set queue TC mapping This patch added the support for VF to config the ETS-based Tx QoS, including querying current QoS configuration from PF and config queue TC mapping. PF QoS is configured in advance and the queried info is provided to the user for future usage. VF queues are mapped to different TCs in PF through virtchnl. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-07-01 11:41:22 +00:00
static int
net/iavf: fix crash after VF reset failure Some pointers will be set to NULL when iavf_dev_reset() failed, for example vf->vf_res, vf->vsi_res vf->rss_key and etc. APIs access these NULL pointers will trigger segfault. This patch adds closed flag to indicate that the VF is closed, and rejects API calls in this state to avoid coredump. Fixes: e74e1bb6280d ("net/iavf: enable port reset") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-12 10:48:51 +00:00
iavf_tm_ops_get(struct rte_eth_dev *dev,
net/iavf: query QoS capabilities and set queue TC mapping This patch added the support for VF to config the ETS-based Tx QoS, including querying current QoS configuration from PF and config queue TC mapping. PF QoS is configured in advance and the queried info is provided to the user for future usage. VF queues are mapped to different TCs in PF through virtchnl. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-07-01 11:41:22 +00:00
void *arg)
{
net/iavf: fix crash after VF reset failure Some pointers will be set to NULL when iavf_dev_reset() failed, for example vf->vf_res, vf->vsi_res vf->rss_key and etc. APIs access these NULL pointers will trigger segfault. This patch adds closed flag to indicate that the VF is closed, and rejects API calls in this state to avoid coredump. Fixes: e74e1bb6280d ("net/iavf: enable port reset") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-12 10:48:51 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
if (adapter->closed)
return -EIO;
net/iavf: query QoS capabilities and set queue TC mapping This patch added the support for VF to config the ETS-based Tx QoS, including querying current QoS configuration from PF and config queue TC mapping. PF QoS is configured in advance and the queried info is provided to the user for future usage. VF queues are mapped to different TCs in PF through virtchnl. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-07-01 11:41:22 +00:00
if (!arg)
return -EINVAL;
*(const void **)arg = &iavf_tm_ops;
return 0;
}
net/iavf: add watchdog for VF FLR Add watchdog to iAVF PMD which support monitoring the VFLR register. If the device is not already in reset then if a VF reset in progress is detected then notify user through callback and set into reset state. If the device is already in reset then poll for completion of reset. The watchdog is disabled by default, to enable it set IAVF_DEV_WATCHDOG_PERIOD to a non zero value (microseconds) Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:59 +00:00
__rte_unused
static int
iavf_vfr_inprogress(struct iavf_hw *hw)
{
int inprogress = 0;
if ((IAVF_READ_REG(hw, IAVF_VFGEN_RSTAT) &
IAVF_VFGEN_RSTAT_VFR_STATE_MASK) ==
VIRTCHNL_VFR_INPROGRESS)
inprogress = 1;
if (inprogress)
PMD_DRV_LOG(INFO, "Watchdog detected VFR in progress");
return inprogress;
}
__rte_unused
static void
iavf_dev_watchdog(void *cb_arg)
{
struct iavf_adapter *adapter = cb_arg;
struct iavf_hw *hw = IAVF_DEV_PRIVATE_TO_HW(adapter);
int vfr_inprogress = 0, rc = 0;
/* check if watchdog has been disabled since last call */
if (!adapter->vf.watchdog_enabled)
return;
/* If in reset then poll vfr_inprogress register for completion */
if (adapter->vf.vf_reset) {
vfr_inprogress = iavf_vfr_inprogress(hw);
if (!vfr_inprogress) {
PMD_DRV_LOG(INFO, "VF \"%s\" reset has completed",
adapter->vf.eth_dev->data->name);
adapter->vf.vf_reset = false;
}
/* If not in reset then poll vfr_inprogress register for VFLR event */
} else {
vfr_inprogress = iavf_vfr_inprogress(hw);
if (vfr_inprogress) {
PMD_DRV_LOG(INFO,
"VF \"%s\" reset event detected by watchdog",
adapter->vf.eth_dev->data->name);
/* enter reset state with VFLR event */
adapter->vf.vf_reset = true;
rte_eth_dev_callback_process(adapter->vf.eth_dev,
RTE_ETH_EVENT_INTR_RESET, NULL);
}
}
/* re-alarm watchdog */
rc = rte_eal_alarm_set(IAVF_DEV_WATCHDOG_PERIOD,
&iavf_dev_watchdog, cb_arg);
if (rc)
PMD_DRV_LOG(ERR, "Failed \"%s\" to reset device watchdog alarm",
adapter->vf.eth_dev->data->name);
}
static void
iavf_dev_watchdog_enable(struct iavf_adapter *adapter __rte_unused)
{
#if (IAVF_DEV_WATCHDOG_PERIOD > 0)
PMD_DRV_LOG(INFO, "Enabling device watchdog");
adapter->vf.watchdog_enabled = true;
if (rte_eal_alarm_set(IAVF_DEV_WATCHDOG_PERIOD,
&iavf_dev_watchdog, (void *)adapter))
PMD_DRV_LOG(ERR, "Failed to enabled device watchdog");
#endif
}
static void
iavf_dev_watchdog_disable(struct iavf_adapter *adapter __rte_unused)
{
#if (IAVF_DEV_WATCHDOG_PERIOD > 0)
PMD_DRV_LOG(INFO, "Disabling device watchdog");
adapter->vf.watchdog_enabled = false;
#endif
}
net/iavf: support multicast configuration This patch enable add multicast address for iavf. Signed-off-by: Wei Zhao <wei.zhao1@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-07-13 07:48:11 +00:00
static int
iavf_set_mc_addr_list(struct rte_eth_dev *dev,
struct rte_ether_addr *mc_addrs,
uint32_t mc_addrs_num)
{
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
net/iavf: fix adding multicast MAC address When the multicast address list is added, it will flush previous addresses first, and then add new ones. If the number of multicast address in the list exceeds the upper limit, it will cause failure, then need to roll back previous addresses. This patch fixes the issue. Fixes: 05e4c3aff35f ("net/iavf: support multicast configuration") Cc: stable@dpdk.org Signed-off-by: Guinan Sun <guinanx.sun@intel.com> Tested-by: Yuan Peng <yuan.peng@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-15 08:43:05 +00:00
int err, ret;
if (mc_addrs_num > IAVF_NUM_MACADDR_MAX) {
PMD_DRV_LOG(ERR,
"can't add more than a limited number (%u) of addresses.",
(uint32_t)IAVF_NUM_MACADDR_MAX);
return -EINVAL;
}
net/iavf: support multicast configuration This patch enable add multicast address for iavf. Signed-off-by: Wei Zhao <wei.zhao1@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-07-13 07:48:11 +00:00
net/iavf: fix crash after VF reset failure Some pointers will be set to NULL when iavf_dev_reset() failed, for example vf->vf_res, vf->vsi_res vf->rss_key and etc. APIs access these NULL pointers will trigger segfault. This patch adds closed flag to indicate that the VF is closed, and rejects API calls in this state to avoid coredump. Fixes: e74e1bb6280d ("net/iavf: enable port reset") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-12 10:48:51 +00:00
if (adapter->closed)
return -EIO;
net/iavf: support multicast configuration This patch enable add multicast address for iavf. Signed-off-by: Wei Zhao <wei.zhao1@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-07-13 07:48:11 +00:00
/* flush previous addresses */
err = iavf_add_del_mc_addr_list(adapter, vf->mc_addrs, vf->mc_addrs_num,
false);
if (err)
return err;
/* add new ones */
err = iavf_add_del_mc_addr_list(adapter, mc_addrs, mc_addrs_num, true);
net/iavf: fix adding multicast MAC address When the multicast address list is added, it will flush previous addresses first, and then add new ones. If the number of multicast address in the list exceeds the upper limit, it will cause failure, then need to roll back previous addresses. This patch fixes the issue. Fixes: 05e4c3aff35f ("net/iavf: support multicast configuration") Cc: stable@dpdk.org Signed-off-by: Guinan Sun <guinanx.sun@intel.com> Tested-by: Yuan Peng <yuan.peng@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-15 08:43:05 +00:00
if (err) {
/* if adding mac address list fails, should add the previous
* addresses back.
*/
ret = iavf_add_del_mc_addr_list(adapter, vf->mc_addrs,
vf->mc_addrs_num, true);
if (ret)
return ret;
} else {
vf->mc_addrs_num = mc_addrs_num;
memcpy(vf->mc_addrs,
mc_addrs, mc_addrs_num * sizeof(*mc_addrs));
}
return err;
net/iavf: support multicast configuration This patch enable add multicast address for iavf. Signed-off-by: Wei Zhao <wei.zhao1@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-07-13 07:48:11 +00:00
}
net/iavf: relax RSS virtual channel commands Kernel PF may not respond to virtual channel commands VIRTCHNL_OP_GET_RSS_HENA_CAPS and VIRTCHNL_OP_SET_RSS_HENA, which will cause VF to fail to start. RSS offload type configuration is not a necessary feature for VF, so in order to improve VF compatibility, in this patch the PMD will ignore the error result of above two commands and will print warnings instead. Fixes: 5a038d19962d ("net/iavf: fix RSS configuration on i40e VF") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-07-26 09:17:24 +00:00
static void
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
iavf_config_rss_hf(struct iavf_adapter *adapter, uint64_t rss_hf)
{
static const uint64_t map_hena_rss[] = {
/* IPv4 */
[IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP] =
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_RSS_NONFRAG_IPV4_UDP,
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
[IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP] =
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_RSS_NONFRAG_IPV4_UDP,
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
[IAVF_FILTER_PCTYPE_NONF_IPV4_UDP] =
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_RSS_NONFRAG_IPV4_UDP,
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
[IAVF_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK] =
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_RSS_NONFRAG_IPV4_TCP,
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
[IAVF_FILTER_PCTYPE_NONF_IPV4_TCP] =
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_RSS_NONFRAG_IPV4_TCP,
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
[IAVF_FILTER_PCTYPE_NONF_IPV4_SCTP] =
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_RSS_NONFRAG_IPV4_SCTP,
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
[IAVF_FILTER_PCTYPE_NONF_IPV4_OTHER] =
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_RSS_NONFRAG_IPV4_OTHER,
[IAVF_FILTER_PCTYPE_FRAG_IPV4] = RTE_ETH_RSS_FRAG_IPV4,
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
/* IPv6 */
[IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP] =
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_RSS_NONFRAG_IPV6_UDP,
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
[IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP] =
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_RSS_NONFRAG_IPV6_UDP,
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
[IAVF_FILTER_PCTYPE_NONF_IPV6_UDP] =
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_RSS_NONFRAG_IPV6_UDP,
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
[IAVF_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK] =
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_RSS_NONFRAG_IPV6_TCP,
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
[IAVF_FILTER_PCTYPE_NONF_IPV6_TCP] =
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_RSS_NONFRAG_IPV6_TCP,
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
[IAVF_FILTER_PCTYPE_NONF_IPV6_SCTP] =
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_RSS_NONFRAG_IPV6_SCTP,
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
[IAVF_FILTER_PCTYPE_NONF_IPV6_OTHER] =
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_RSS_NONFRAG_IPV6_OTHER,
[IAVF_FILTER_PCTYPE_FRAG_IPV6] = RTE_ETH_RSS_FRAG_IPV6,
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
/* L2 Payload */
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
[IAVF_FILTER_PCTYPE_L2_PAYLOAD] = RTE_ETH_RSS_L2_PAYLOAD
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
};
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
const uint64_t ipv4_rss = RTE_ETH_RSS_NONFRAG_IPV4_UDP |
RTE_ETH_RSS_NONFRAG_IPV4_TCP |
RTE_ETH_RSS_NONFRAG_IPV4_SCTP |
RTE_ETH_RSS_NONFRAG_IPV4_OTHER |
RTE_ETH_RSS_FRAG_IPV4;
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
const uint64_t ipv6_rss = RTE_ETH_RSS_NONFRAG_IPV6_UDP |
RTE_ETH_RSS_NONFRAG_IPV6_TCP |
RTE_ETH_RSS_NONFRAG_IPV6_SCTP |
RTE_ETH_RSS_NONFRAG_IPV6_OTHER |
RTE_ETH_RSS_FRAG_IPV6;
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
uint64_t caps = 0, hena = 0, valid_rss_hf = 0;
uint32_t i;
int ret;
ret = iavf_get_hena_caps(adapter, &caps);
net/iavf: relax RSS virtual channel commands Kernel PF may not respond to virtual channel commands VIRTCHNL_OP_GET_RSS_HENA_CAPS and VIRTCHNL_OP_SET_RSS_HENA, which will cause VF to fail to start. RSS offload type configuration is not a necessary feature for VF, so in order to improve VF compatibility, in this patch the PMD will ignore the error result of above two commands and will print warnings instead. Fixes: 5a038d19962d ("net/iavf: fix RSS configuration on i40e VF") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-07-26 09:17:24 +00:00
if (ret) {
/**
* RSS offload type configuration is not a necessary feature
* for VF, so here just print a warning and return.
*/
PMD_DRV_LOG(WARNING,
"fail to get RSS offload type caps, ret: %d", ret);
return;
}
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
/**
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
* RTE_ETH_RSS_IPV4 and RTE_ETH_RSS_IPV6 can be considered as 2
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
* generalizations of all other IPv4 and IPv6 RSS types.
*/
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
if (rss_hf & RTE_ETH_RSS_IPV4)
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
rss_hf |= ipv4_rss;
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
if (rss_hf & RTE_ETH_RSS_IPV6)
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
rss_hf |= ipv6_rss;
RTE_BUILD_BUG_ON(RTE_DIM(map_hena_rss) > sizeof(uint64_t) * CHAR_BIT);
for (i = 0; i < RTE_DIM(map_hena_rss); i++) {
uint64_t bit = BIT_ULL(i);
if ((caps & bit) && (map_hena_rss[i] & rss_hf)) {
valid_rss_hf |= map_hena_rss[i];
hena |= bit;
}
}
ret = iavf_set_hena(adapter, hena);
net/iavf: relax RSS virtual channel commands Kernel PF may not respond to virtual channel commands VIRTCHNL_OP_GET_RSS_HENA_CAPS and VIRTCHNL_OP_SET_RSS_HENA, which will cause VF to fail to start. RSS offload type configuration is not a necessary feature for VF, so in order to improve VF compatibility, in this patch the PMD will ignore the error result of above two commands and will print warnings instead. Fixes: 5a038d19962d ("net/iavf: fix RSS configuration on i40e VF") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-07-26 09:17:24 +00:00
if (ret) {
/**
* RSS offload type configuration is not a necessary feature
* for VF, so here just print a warning and return.
*/
PMD_DRV_LOG(WARNING,
"fail to set RSS offload types, ret: %d", ret);
return;
}
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
if (valid_rss_hf & ipv4_rss)
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
valid_rss_hf |= rss_hf & RTE_ETH_RSS_IPV4;
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
if (valid_rss_hf & ipv6_rss)
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
valid_rss_hf |= rss_hf & RTE_ETH_RSS_IPV6;
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
if (rss_hf & ~valid_rss_hf)
PMD_DRV_LOG(WARNING, "Unsupported rss_hf 0x%" PRIx64,
rss_hf & ~valid_rss_hf);
vf->rss_hf = valid_rss_hf;
}
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_init_rss(struct iavf_adapter *adapter)
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
struct rte_eth_rss_conf *rss_conf;
net/iavf: fix iterator for RSS LUT Change RSS LUT iterator from uint8_t to uint16_t since the RSS LUT size could exceed 255. Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Cc: stable@dpdk.org Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Ting Xu <ting.xu@intel.com>
2020-09-21 08:30:58 +00:00
uint16_t i, j, nb_q;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
int ret;
net/iavf: fix multi-process shared data When the iavf_adapter instance is not initialized completely in the primary process, the secondary process accesses its "rte_eth_dev" member, it causes secondary process crash. This patch replaces eth_dev with eth_dev_data in iavf_adapter. Fixes: f978c1c9b3b5 ("net/iavf: add RSS hash parsing in AVX path") Fixes: 9c9aa0040344 ("net/iavf: add offload path for Rx AVX512 flex descriptor") Fixes: 63660ea3ee0b ("net/iavf: add RSS hash parsing in SSE path") Cc: stable@dpdk.org Signed-off-by: Dapeng Yu <dapengx.yu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-10-11 02:01:31 +00:00
rss_conf = &adapter->dev_data->dev_conf.rx_adv_conf.rss_conf;
nb_q = RTE_MIN(adapter->dev_data->nb_rx_queues,
net/iavf: negotiate large VF and request more queues Negotiate large VF capability with PF during VF initialization. If large VF is supported and the number of queues larger than 16 is required, VF requests additional queues from PF. Mark the state that large VF is supported. If the allocated queues number is larger than 16, the max RSS queue region cannot be 16 anymore. Add the function to query max RSS queue region from PF, use it in the RSS initialization and future filters configuration. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:48:59 +00:00
vf->max_rss_qregion);
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
if (!(vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF)) {
PMD_DRV_LOG(DEBUG, "RSS is not supported");
return -ENOTSUP;
}
/* configure RSS key */
if (!rss_conf->rss_key) {
/* Calculate the default hash key */
net/iavf: fix RSS key access out of bound The array rss_key has size 'vf->vf_res->rss_key_size', the array index should be less than that. Cc: stable@dpdk.org Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-05-19 07:59:33 +00:00
for (i = 0; i < vf->vf_res->rss_key_size; i++)
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
vf->rss_key[i] = (uint8_t)rte_rand();
} else
rte_memcpy(vf->rss_key, rss_conf->rss_key,
RTE_MIN(rss_conf->rss_key_len,
vf->vf_res->rss_key_size));
/* init RSS LUT table */
net/avf: fix uninitialized variables This patch fixes the coverity UNINIT issue. Coverity issue: 257016, 257036 Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Reported-by: John McNamara <john.mcnamara@intel.com> Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-30 03:32:58 +00:00
for (i = 0, j = 0; i < vf->vf_res->rss_lut_size; i++, j++) {
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
if (j >= nb_q)
j = 0;
vf->rss_lut[i] = j;
}
fix spelling in comments and strings The tool comes from https://github.com/jsoref Signed-off-by: Josh Soref <jsoref@gmail.com> Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
2021-11-29 16:08:02 +00:00
/* send virtchnl ops to configure RSS */
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
ret = iavf_configure_rss_lut(adapter);
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
if (ret)
return ret;
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
ret = iavf_configure_rss_key(adapter);
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
if (ret)
return ret;
net/iavf: fix default RSS configuration Add advanced RSS offloads check due to some legacy driver (kernel/DPDK PF) does not support virtual channel command VIRTCHNL_OP_RSS_HENA with hena = 0 and VIRTCHNL_OP_ADD_RSS_CFG. Fixes: 95f2f0e9fc2a ("net/iavf: improve default RSS") Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-31 10:47:24 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF) {
/* Set RSS hash configuration based on rss_conf->rss_hf. */
ret = iavf_rss_hash_set(adapter, rss_conf->rss_hf, true);
if (ret) {
PMD_DRV_LOG(ERR, "fail to set default RSS");
return ret;
}
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
} else {
net/iavf: relax RSS virtual channel commands Kernel PF may not respond to virtual channel commands VIRTCHNL_OP_GET_RSS_HENA_CAPS and VIRTCHNL_OP_SET_RSS_HENA, which will cause VF to fail to start. RSS offload type configuration is not a necessary feature for VF, so in order to improve VF compatibility, in this patch the PMD will ignore the error result of above two commands and will print warnings instead. Fixes: 5a038d19962d ("net/iavf: fix RSS configuration on i40e VF") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-07-26 09:17:24 +00:00
iavf_config_rss_hf(adapter, rss_conf->rss_hf);
net/iavf: improve default RSS Add support to actively configure the RSS through port config. Any kernel PF enabled default RSS will be disabled during initialization. Besides, default RSS will be configured based on rte_eth_rss_conf->rss_hf. Currently supported default rss_type: ipv4[6], ipv4[6]_udp, ipv4[6]_tcp, ipv4[6]_sctp. Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-12-23 12:52:28 +00:00
}
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
return 0;
}
net/iavf: negotiate large VF and request more queues Negotiate large VF capability with PF during VF initialization. If large VF is supported and the number of queues larger than 16 is required, VF requests additional queues from PF. Mark the state that large VF is supported. If the allocated queues number is larger than 16, the max RSS queue region cannot be 16 anymore. Add the function to query max RSS queue region from PF, use it in the RSS initialization and future filters configuration. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:48:59 +00:00
static int
iavf_queues_req_reset(struct rte_eth_dev *dev, uint16_t num)
{
struct iavf_adapter *ad =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(ad);
int ret;
net/iavf: fix multi-process shared data When the iavf_adapter instance is not initialized completely in the primary process, the secondary process accesses its "rte_eth_dev" member, it causes secondary process crash. This patch replaces eth_dev with eth_dev_data in iavf_adapter. Fixes: f978c1c9b3b5 ("net/iavf: add RSS hash parsing in AVX path") Fixes: 9c9aa0040344 ("net/iavf: add offload path for Rx AVX512 flex descriptor") Fixes: 63660ea3ee0b ("net/iavf: add RSS hash parsing in SSE path") Cc: stable@dpdk.org Signed-off-by: Dapeng Yu <dapengx.yu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-10-11 02:01:31 +00:00
ret = iavf_request_queues(dev, num);
net/iavf: negotiate large VF and request more queues Negotiate large VF capability with PF during VF initialization. If large VF is supported and the number of queues larger than 16 is required, VF requests additional queues from PF. Mark the state that large VF is supported. If the allocated queues number is larger than 16, the max RSS queue region cannot be 16 anymore. Add the function to query max RSS queue region from PF, use it in the RSS initialization and future filters configuration. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:48:59 +00:00
if (ret) {
PMD_DRV_LOG(ERR, "request queues from PF failed");
return ret;
}
PMD_DRV_LOG(INFO, "change queue pairs from %u to %u",
vf->vsi_res->num_queue_pairs, num);
ret = iavf_dev_reset(dev);
if (ret) {
PMD_DRV_LOG(ERR, "vf reset failed");
return ret;
}
return 0;
}
net/iavf: support new VLAN capabilities The new VLAN virtchnl opcodes introduce new capabilities like VLAN filtering, stripping and insertion. The AVF needs to query the VLAN capabilities based on current device configuration firstly. AVF is able to configure inner VLAN filter when port VLAN is enabled base on negotiation; and AVF is able to configure outer VLAN (0x8100) if port VLAN is disabled to be compatible with legacy mode. When port VLAN is updated by DCF, the AVF needs to reset to query the new VLAN capabilities. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-12 08:13:02 +00:00
static int
iavf_dev_vlan_insert_set(struct rte_eth_dev *dev)
{
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
bool enable;
if (!(vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN_V2))
return 0;
enable = !!(dev->data->dev_conf.txmode.offloads &
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_TX_OFFLOAD_VLAN_INSERT);
net/iavf: support new VLAN capabilities The new VLAN virtchnl opcodes introduce new capabilities like VLAN filtering, stripping and insertion. The AVF needs to query the VLAN capabilities based on current device configuration firstly. AVF is able to configure inner VLAN filter when port VLAN is enabled base on negotiation; and AVF is able to configure outer VLAN (0x8100) if port VLAN is disabled to be compatible with legacy mode. When port VLAN is updated by DCF, the AVF needs to reset to query the new VLAN capabilities. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-12 08:13:02 +00:00
iavf_config_vlan_insert_v2(adapter, enable);
return 0;
}
static int
iavf_dev_init_vlan(struct rte_eth_dev *dev)
{
int err;
err = iavf_dev_vlan_offload_set(dev,
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_VLAN_STRIP_MASK |
RTE_ETH_QINQ_STRIP_MASK |
RTE_ETH_VLAN_FILTER_MASK |
RTE_ETH_VLAN_EXTEND_MASK);
net/iavf: support new VLAN capabilities The new VLAN virtchnl opcodes introduce new capabilities like VLAN filtering, stripping and insertion. The AVF needs to query the VLAN capabilities based on current device configuration firstly. AVF is able to configure inner VLAN filter when port VLAN is enabled base on negotiation; and AVF is able to configure outer VLAN (0x8100) if port VLAN is disabled to be compatible with legacy mode. When port VLAN is updated by DCF, the AVF needs to reset to query the new VLAN capabilities. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-12 08:13:02 +00:00
if (err) {
PMD_DRV_LOG(ERR, "Failed to update vlan offload");
return err;
}
err = iavf_dev_vlan_insert_set(dev);
if (err)
PMD_DRV_LOG(ERR, "Failed to update vlan insertion");
return err;
}
net/iavf: fix RSS RETA after restart This patch moved the RSS initialization from dev start to dev configure, to fix the issue that RSS redirection table can not be kept after restarting port. Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Cc: stable@dpdk.org Signed-off-by: Junyu Jiang <junyux.jiang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
2020-06-19 07:44:02 +00:00
static int
iavf_dev_configure(struct rte_eth_dev *dev)
{
struct iavf_adapter *ad =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(ad);
net/iavf: negotiate large VF and request more queues Negotiate large VF capability with PF during VF initialization. If large VF is supported and the number of queues larger than 16 is required, VF requests additional queues from PF. Mark the state that large VF is supported. If the allocated queues number is larger than 16, the max RSS queue region cannot be 16 anymore. Add the function to query max RSS queue region from PF, use it in the RSS initialization and future filters configuration. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:48:59 +00:00
uint16_t num_queue_pairs = RTE_MAX(dev->data->nb_rx_queues,
dev->data->nb_tx_queues);
int ret;
net/iavf: fix RSS RETA after restart This patch moved the RSS initialization from dev start to dev configure, to fix the issue that RSS redirection table can not be kept after restarting port. Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Cc: stable@dpdk.org Signed-off-by: Junyu Jiang <junyux.jiang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
2020-06-19 07:44:02 +00:00
net/iavf: fix crash after VF reset failure Some pointers will be set to NULL when iavf_dev_reset() failed, for example vf->vf_res, vf->vsi_res vf->rss_key and etc. APIs access these NULL pointers will trigger segfault. This patch adds closed flag to indicate that the VF is closed, and rejects API calls in this state to avoid coredump. Fixes: e74e1bb6280d ("net/iavf: enable port reset") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-12 10:48:51 +00:00
if (ad->closed)
return -EIO;
net/iavf: fix RSS RETA after restart This patch moved the RSS initialization from dev start to dev configure, to fix the issue that RSS redirection table can not be kept after restarting port. Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Cc: stable@dpdk.org Signed-off-by: Junyu Jiang <junyux.jiang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
2020-06-19 07:44:02 +00:00
ad->rx_bulk_alloc_allowed = true;
/* Initialize to TRUE. If any of Rx queues doesn't meet the
* vector Rx/Tx preconditions, it will be reset.
*/
ad->rx_vec_allowed = true;
ad->tx_vec_allowed = true;
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
if (dev->data->dev_conf.rxmode.mq_mode & RTE_ETH_MQ_RX_RSS_FLAG)
dev->data->dev_conf.rxmode.offloads |= RTE_ETH_RX_OFFLOAD_RSS_HASH;
net/iavf: fix RSS RETA after restart This patch moved the RSS initialization from dev start to dev configure, to fix the issue that RSS redirection table can not be kept after restarting port. Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Cc: stable@dpdk.org Signed-off-by: Junyu Jiang <junyux.jiang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
2020-06-19 07:44:02 +00:00
net/iavf: negotiate large VF and request more queues Negotiate large VF capability with PF during VF initialization. If large VF is supported and the number of queues larger than 16 is required, VF requests additional queues from PF. Mark the state that large VF is supported. If the allocated queues number is larger than 16, the max RSS queue region cannot be 16 anymore. Add the function to query max RSS queue region from PF, use it in the RSS initialization and future filters configuration. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:48:59 +00:00
/* Large VF setting */
if (num_queue_pairs > IAVF_MAX_NUM_QUEUES_DFLT) {
if (!(vf->vf_res->vf_cap_flags &
VIRTCHNL_VF_LARGE_NUM_QPAIRS)) {
PMD_DRV_LOG(ERR, "large VF is not supported");
return -1;
}
if (num_queue_pairs > IAVF_MAX_NUM_QUEUES_LV) {
PMD_DRV_LOG(ERR, "queue pairs number cannot be larger than %u",
IAVF_MAX_NUM_QUEUES_LV);
return -1;
}
ret = iavf_queues_req_reset(dev, num_queue_pairs);
if (ret)
return ret;
ret = iavf_get_max_rss_queue_region(ad);
if (ret) {
PMD_INIT_LOG(ERR, "get max rss queue region failed");
return ret;
}
vf->lv_enabled = true;
} else {
/* Check if large VF is already enabled. If so, disable and
* release redundant queue resource.
net/iavf: fix queue pairs configuration Check if there are enough queue pairs currently allocated, and if not, request PF to allocate them. Fixes: e436cd43835b ("net/iavf: negotiate large VF and request more queues") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Tested-by: Zhimin Huang <zhiminx.huang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-12-23 05:29:36 +00:00
* Or check if enough queue pairs. If not, request them from PF.
net/iavf: negotiate large VF and request more queues Negotiate large VF capability with PF during VF initialization. If large VF is supported and the number of queues larger than 16 is required, VF requests additional queues from PF. Mark the state that large VF is supported. If the allocated queues number is larger than 16, the max RSS queue region cannot be 16 anymore. Add the function to query max RSS queue region from PF, use it in the RSS initialization and future filters configuration. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:48:59 +00:00
*/
net/iavf: fix queue pairs configuration Check if there are enough queue pairs currently allocated, and if not, request PF to allocate them. Fixes: e436cd43835b ("net/iavf: negotiate large VF and request more queues") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Tested-by: Zhimin Huang <zhiminx.huang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-12-23 05:29:36 +00:00
if (vf->lv_enabled ||
num_queue_pairs > vf->vsi_res->num_queue_pairs) {
net/iavf: negotiate large VF and request more queues Negotiate large VF capability with PF during VF initialization. If large VF is supported and the number of queues larger than 16 is required, VF requests additional queues from PF. Mark the state that large VF is supported. If the allocated queues number is larger than 16, the max RSS queue region cannot be 16 anymore. Add the function to query max RSS queue region from PF, use it in the RSS initialization and future filters configuration. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:48:59 +00:00
ret = iavf_queues_req_reset(dev, num_queue_pairs);
if (ret)
return ret;
vf->lv_enabled = false;
}
/* if large VF is not required, use default rss queue region */
vf->max_rss_qregion = IAVF_MAX_NUM_QUEUES_DFLT;
}
net/iavf: support new VLAN capabilities The new VLAN virtchnl opcodes introduce new capabilities like VLAN filtering, stripping and insertion. The AVF needs to query the VLAN capabilities based on current device configuration firstly. AVF is able to configure inner VLAN filter when port VLAN is enabled base on negotiation; and AVF is able to configure outer VLAN (0x8100) if port VLAN is disabled to be compatible with legacy mode. When port VLAN is updated by DCF, the AVF needs to reset to query the new VLAN capabilities. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-12 08:13:02 +00:00
ret = iavf_dev_init_vlan(dev);
net/iavf: adjust VLAN initialize failure handling Instead of returning error on VLAN init failure, just log the error, so that the VF device can continue to be configured. Fixes: 1c301e8c3cff ("net/iavf: support new VLAN capabilities") Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-25 11:44:21 +00:00
if (ret)
net/iavf: support new VLAN capabilities The new VLAN virtchnl opcodes introduce new capabilities like VLAN filtering, stripping and insertion. The AVF needs to query the VLAN capabilities based on current device configuration firstly. AVF is able to configure inner VLAN filter when port VLAN is enabled base on negotiation; and AVF is able to configure outer VLAN (0x8100) if port VLAN is disabled to be compatible with legacy mode. When port VLAN is updated by DCF, the AVF needs to reset to query the new VLAN capabilities. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-12 08:13:02 +00:00
PMD_DRV_LOG(ERR, "configure VLAN failed: %d", ret);
net/iavf: fix RSS RETA after restart This patch moved the RSS initialization from dev start to dev configure, to fix the issue that RSS redirection table can not be kept after restarting port. Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Cc: stable@dpdk.org Signed-off-by: Junyu Jiang <junyux.jiang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
2020-06-19 07:44:02 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF) {
if (iavf_init_rss(ad) != 0) {
PMD_DRV_LOG(ERR, "configure rss failed");
return -1;
}
}
return 0;
}
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_init_rxq(struct rte_eth_dev *dev, struct iavf_rx_queue *rxq)
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_hw *hw = IAVF_DEV_PRIVATE_TO_HW(dev->data->dev_private);
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
struct rte_eth_dev_data *dev_data = dev->data;
net/iavf: fix overflow in maximum packet length config The len variable, used in the computation of max_pkt_len could overflow, if used to store the result of the following computation: rxq->rx_buf_len * IAVF_MAX_CHAINED_RX_BUFFERS Since, we could define the mbuf size to have a large value (i.e 13312), and IAVF_MAX_CHAINED_RX_BUFFERS is defined as 5, the computation mentioned above could potentially result in a value which might be bigger than MAX_USHORT. The result will be that Jumbo Frames will not work properly Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Cc: stable@dpdk.org Signed-off-by: Tudor Cornea <tudor.cornea@gmail.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-08-05 11:35:23 +00:00
uint16_t buf_size, max_pkt_len;
ethdev: fix max Rx packet length There is a confusion on setting max Rx packet length, this patch aims to clarify it. 'rte_eth_dev_configure()' API accepts max Rx packet size via 'uint32_t max_rx_pkt_len' field of the config struct 'struct rte_eth_conf'. Also 'rte_eth_dev_set_mtu()' API can be used to set the MTU, and result stored into '(struct rte_eth_dev)->data->mtu'. These two APIs are related but they work in a disconnected way, they store the set values in different variables which makes hard to figure out which one to use, also having two different method for a related functionality is confusing for the users. Other issues causing confusion is: * maximum transmission unit (MTU) is payload of the Ethernet frame. And 'max_rx_pkt_len' is the size of the Ethernet frame. Difference is Ethernet frame overhead, and this overhead may be different from device to device based on what device supports, like VLAN and QinQ. * 'max_rx_pkt_len' is only valid when application requested jumbo frame, which adds additional confusion and some APIs and PMDs already discards this documented behavior. * For the jumbo frame enabled case, 'max_rx_pkt_len' is an mandatory field, this adds configuration complexity for application. As solution, both APIs gets MTU as parameter, and both saves the result in same variable '(struct rte_eth_dev)->data->mtu'. For this 'max_rx_pkt_len' updated as 'mtu', and it is always valid independent from jumbo frame. For 'rte_eth_dev_configure()', 'dev->data->dev_conf.rxmode.mtu' is user request and it should be used only within configure function and result should be stored to '(struct rte_eth_dev)->data->mtu'. After that point both application and PMD uses MTU from this variable. When application doesn't provide an MTU during 'rte_eth_dev_configure()' default 'RTE_ETHER_MTU' value is used. Additional clarification done on scattered Rx configuration, in relation to MTU and Rx buffer size. MTU is used to configure the device for physical Rx/Tx size limitation, Rx buffer is where to store Rx packets, many PMDs use mbuf data buffer size as Rx buffer size. PMDs compare MTU against Rx buffer size to decide enabling scattered Rx or not. If scattered Rx is not supported by device, MTU bigger than Rx buffer size should fail. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com> Acked-by: Huisong Li <lihuisong@huawei.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com>
2021-10-18 13:48:48 +00:00
uint32_t frame_size = dev->data->mtu + IAVF_ETH_OVERHEAD;
net/iavf: enable Rx timestamp on flex descriptor Dump Rx timestamp value into dynamic mbuf field by flex descriptor. This feature is turned on by dev config "enable-rx-timestamp". Currently, it's only supported under scalar path. Signed-off-by: Simei Su <simei.su@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-04-28 08:13:45 +00:00
enum iavf_status err;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
buf_size = rte_pktmbuf_data_room_size(rxq->mp) - RTE_PKTMBUF_HEADROOM;
/* Calculate the maximum packet length allowed */
net/iavf: fix overflow in maximum packet length config The len variable, used in the computation of max_pkt_len could overflow, if used to store the result of the following computation: rxq->rx_buf_len * IAVF_MAX_CHAINED_RX_BUFFERS Since, we could define the mbuf size to have a large value (i.e 13312), and IAVF_MAX_CHAINED_RX_BUFFERS is defined as 5, the computation mentioned above could potentially result in a value which might be bigger than MAX_USHORT. The result will be that Jumbo Frames will not work properly Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Cc: stable@dpdk.org Signed-off-by: Tudor Cornea <tudor.cornea@gmail.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-08-05 11:35:23 +00:00
max_pkt_len = RTE_MIN((uint32_t)
rxq->rx_buf_len * IAVF_MAX_CHAINED_RX_BUFFERS,
ethdev: fix max Rx packet length There is a confusion on setting max Rx packet length, this patch aims to clarify it. 'rte_eth_dev_configure()' API accepts max Rx packet size via 'uint32_t max_rx_pkt_len' field of the config struct 'struct rte_eth_conf'. Also 'rte_eth_dev_set_mtu()' API can be used to set the MTU, and result stored into '(struct rte_eth_dev)->data->mtu'. These two APIs are related but they work in a disconnected way, they store the set values in different variables which makes hard to figure out which one to use, also having two different method for a related functionality is confusing for the users. Other issues causing confusion is: * maximum transmission unit (MTU) is payload of the Ethernet frame. And 'max_rx_pkt_len' is the size of the Ethernet frame. Difference is Ethernet frame overhead, and this overhead may be different from device to device based on what device supports, like VLAN and QinQ. * 'max_rx_pkt_len' is only valid when application requested jumbo frame, which adds additional confusion and some APIs and PMDs already discards this documented behavior. * For the jumbo frame enabled case, 'max_rx_pkt_len' is an mandatory field, this adds configuration complexity for application. As solution, both APIs gets MTU as parameter, and both saves the result in same variable '(struct rte_eth_dev)->data->mtu'. For this 'max_rx_pkt_len' updated as 'mtu', and it is always valid independent from jumbo frame. For 'rte_eth_dev_configure()', 'dev->data->dev_conf.rxmode.mtu' is user request and it should be used only within configure function and result should be stored to '(struct rte_eth_dev)->data->mtu'. After that point both application and PMD uses MTU from this variable. When application doesn't provide an MTU during 'rte_eth_dev_configure()' default 'RTE_ETHER_MTU' value is used. Additional clarification done on scattered Rx configuration, in relation to MTU and Rx buffer size. MTU is used to configure the device for physical Rx/Tx size limitation, Rx buffer is where to store Rx packets, many PMDs use mbuf data buffer size as Rx buffer size. PMDs compare MTU against Rx buffer size to decide enabling scattered Rx or not. If scattered Rx is not supported by device, MTU bigger than Rx buffer size should fail. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com> Acked-by: Huisong Li <lihuisong@huawei.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com>
2021-10-18 13:48:48 +00:00
frame_size);
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
drivers/net: fix removing jumbo offload flag After DEV_RX_OFFLOAD_JUMBO_FRAME flag removed, drivers give jumbo frame decisions based on MTU value checks, but some of the checks were wrong by mistake, causing device initialization to fail, fixing them. Fixes: b563c1421282 ("ethdev: remove jumbo offload flag") Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Tested-by: Yu Jiang <yux.jiang@intel.com>
2021-10-22 12:57:15 +00:00
/* Check if maximum packet length is set correctly. */
if (max_pkt_len <= RTE_ETHER_MIN_LEN ||
max_pkt_len > IAVF_FRAME_SIZE_MAX) {
PMD_DRV_LOG(ERR, "maximum packet length must be "
"larger than %u and smaller than %u",
(uint32_t)IAVF_ETH_MAX_LEN,
(uint32_t)IAVF_FRAME_SIZE_MAX);
return -EINVAL;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
}
net/iavf: enable Rx timestamp on flex descriptor Dump Rx timestamp value into dynamic mbuf field by flex descriptor. This feature is turned on by dev config "enable-rx-timestamp". Currently, it's only supported under scalar path. Signed-off-by: Simei Su <simei.su@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-04-28 08:13:45 +00:00
if (rxq->offloads & RTE_ETH_RX_OFFLOAD_TIMESTAMP) {
/* Register mbuf field and flag for Rx timestamp */
err = rte_mbuf_dyn_rx_timestamp_register(
&iavf_timestamp_dynfield_offset,
&iavf_timestamp_dynflag);
if (err) {
PMD_DRV_LOG(ERR,
"Cannot register mbuf field/flag for timestamp");
return -EINVAL;
}
}
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
rxq->max_pkt_len = max_pkt_len;
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
if ((dev_data->dev_conf.rxmode.offloads & RTE_ETH_RX_OFFLOAD_SCATTER) ||
net/iavf: fix scattered Rx enabling No need to add additional vlan tag size for max packet size, the queue's Rx Max Frame Size (rxq->max_pkt_len) already includes the vlan header size in iavf. Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Cc: stable@dpdk.org Signed-off-by: Steve Yang <stevex.yang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-09-04 07:29:02 +00:00
rxq->max_pkt_len > buf_size) {
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
dev_data->scattered_rx = 1;
}
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
IAVF_PCI_REG_WRITE(rxq->qrx_tail, rxq->nb_rx_desc - 1);
IAVF_WRITE_FLUSH(hw);
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
return 0;
}
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_init_queues(struct rte_eth_dev *dev)
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_rx_queue **rxq =
(struct iavf_rx_queue **)dev->data->rx_queues;
int i, ret = IAVF_SUCCESS;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
for (i = 0; i < dev->data->nb_rx_queues; i++) {
if (!rxq[i] || !rxq[i]->q_set)
continue;
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
ret = iavf_init_rxq(dev, rxq[i]);
if (ret != IAVF_SUCCESS)
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
break;
}
net/avf: enable basic Rx Tx Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
2018-01-10 13:01:56 +00:00
/* set rx/tx function to vector/scatter/single-segment
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
* according to parameters
*/
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_set_rx_function(dev);
iavf_set_tx_function(dev);
net/avf: enable basic Rx Tx Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
2018-01-10 13:01:56 +00:00
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
return ret;
}
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
static int iavf_config_rx_queues_irqs(struct rte_eth_dev *dev,
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
struct rte_intr_handle *intr_handle)
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
struct iavf_hw *hw = IAVF_DEV_PRIVATE_TO_HW(adapter);
net/iavf: enable IRQ mapping configuration for large VF The current IRQ mapping configuration only supports max 16 queues and 16 MSIX vectors. Change the queue vector mapping structure to indicate up to 256 queues. A new opcode is used to handle the case with large number of queues. To avoid adminq buffer size limitation, we support to send the virtchnl message multiple times if needed. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:49:01 +00:00
struct iavf_qv_map *qv_map;
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
uint16_t interval, i;
int vec;
net/avf: fix VF Rx interrupt enabling As UIO doesn't support multiple interrupt, and the interrupt is occupied by the control plane. PMD should not try to enable RX queue interrupt. Then APP can know the RX queue interrupt is not enabled and only choose the polling mode. Fixes: d6bde6b5eae9 ("net/avf: enable Rx interrupt") Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2018-01-24 08:16:53 +00:00
if (rte_intr_cap_multiple(intr_handle) &&
dev->data->dev_conf.intr_conf.rxq) {
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
if (rte_intr_efd_enable(intr_handle, dev->data->nb_rx_queues))
return -1;
}
drivers: remove direct access to interrupt handle Removing direct access to interrupt handle structure fields, rather use respective get set APIs for the same. Making changes to all the drivers access the interrupt handle fields. Signed-off-by: Harman Kalra <hkalra@marvell.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com> Signed-off-by: David Marchand <david.marchand@redhat.com> Tested-by: Raslan Darawsheh <rasland@nvidia.com>
2021-10-22 20:49:32 +00:00
if (rte_intr_dp_is_en(intr_handle)) {
if (rte_intr_vec_list_alloc(intr_handle, "intr_vec",
dev->data->nb_rx_queues)) {
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
PMD_DRV_LOG(ERR, "Failed to allocate %d rx intr_vec",
dev->data->nb_rx_queues);
return -1;
}
}
drivers: remove direct access to interrupt handle Removing direct access to interrupt handle structure fields, rather use respective get set APIs for the same. Making changes to all the drivers access the interrupt handle fields. Signed-off-by: Harman Kalra <hkalra@marvell.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com> Signed-off-by: David Marchand <david.marchand@redhat.com> Tested-by: Raslan Darawsheh <rasland@nvidia.com>
2021-10-22 20:49:32 +00:00
net/iavf: enable IRQ mapping configuration for large VF The current IRQ mapping configuration only supports max 16 queues and 16 MSIX vectors. Change the queue vector mapping structure to indicate up to 256 queues. A new opcode is used to handle the case with large number of queues. To avoid adminq buffer size limitation, we support to send the virtchnl message multiple times if needed. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:49:01 +00:00
qv_map = rte_zmalloc("qv_map",
dev->data->nb_rx_queues * sizeof(struct iavf_qv_map), 0);
if (!qv_map) {
PMD_DRV_LOG(ERR, "Failed to allocate %d queue-vector map",
dev->data->nb_rx_queues);
net/iavf: fix Rx queue IRQ resource leak In the iavf_config_rx_queues_irqs function, the memory pointed to by the intr_handle->intr_vec and qv_map addresses is not released in the subsequent hook branch, resulting in resource leakage. Fixes: f593944fc988 ("net/iavf: enable IRQ mapping configuration for large VF") Cc: stable@dpdk.org Signed-off-by: Qiming Chen <chenqiming_huawei@163.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-09-10 06:54:57 +00:00
goto qv_map_alloc_err;
net/iavf: enable IRQ mapping configuration for large VF The current IRQ mapping configuration only supports max 16 queues and 16 MSIX vectors. Change the queue vector mapping structure to indicate up to 256 queues. A new opcode is used to handle the case with large number of queues. To avoid adminq buffer size limitation, we support to send the virtchnl message multiple times if needed. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:49:01 +00:00
}
net/avf: fix VF Rx interrupt enabling As UIO doesn't support multiple interrupt, and the interrupt is occupied by the control plane. PMD should not try to enable RX queue interrupt. Then APP can know the RX queue interrupt is not enabled and only choose the polling mode. Fixes: d6bde6b5eae9 ("net/avf: enable Rx interrupt") Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2018-01-24 08:16:53 +00:00
if (!dev->data->dev_conf.intr_conf.rxq ||
!rte_intr_dp_is_en(intr_handle)) {
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
/* Rx interrupt disabled, Map interrupt only for writeback */
vf->nb_msix = 1;
if (vf->vf_res->vf_cap_flags &
VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) {
/* If WB_ON_ITR supports, enable it */
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
vf->msix_base = IAVF_RX_VEC_START;
net/iavf: fix performance with writeback policy The iavf driver was trying to use writeback on ITR, but was never setting an ITR, so it didn't work. This caused performance to be limited due to too much PCIe traffic and partial writes during most benchmarking workloads. Set the ITR during queue setup, which can be checked at runtime by reading register 0x2800. Setting the value to 2us allows for generally good streaming packet performance while keeping latency down. Fixes: d6bde6b5eae9 ("net/avf: enable Rx interrupt") Cc: stable@dpdk.org Reported-by: Brian Johnson <brian.johnson@intel.com> Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-10-23 20:21:59 +00:00
/* Set the ITR for index zero, to 2us to make sure that
* we leave time for aggregation to occur, but don't
* increase latency dramatically.
*/
net/iavf/base: rename register macro Rename all register macro to align with kernel driver's implementation. Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com> Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
2019-12-03 07:03:04 +00:00
IAVF_WRITE_REG(hw,
IAVF_VFINT_DYN_CTLN1(vf->msix_base - 1),
net/iavf: fix performance with writeback policy The iavf driver was trying to use writeback on ITR, but was never setting an ITR, so it didn't work. This caused performance to be limited due to too much PCIe traffic and partial writes during most benchmarking workloads. Set the ITR during queue setup, which can be checked at runtime by reading register 0x2800. Setting the value to 2us allows for generally good streaming packet performance while keeping latency down. Fixes: d6bde6b5eae9 ("net/avf: enable Rx interrupt") Cc: stable@dpdk.org Reported-by: Brian Johnson <brian.johnson@intel.com> Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-10-23 20:21:59 +00:00
(0 << IAVF_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) |
IAVF_VFINT_DYN_CTLN1_WB_ON_ITR_MASK |
(2UL << IAVF_VFINT_DYN_CTLN1_INTERVAL_SHIFT));
/* debug - check for success! the return value
* should be 2, offset is 0x2800
*/
/* IAVF_READ_REG(hw, IAVF_VFINT_ITRN1(0, 0)); */
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
} else {
/* If no WB_ON_ITR offload flags, need to set
* interrupt for descriptor write back.
*/
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
vf->msix_base = IAVF_MISC_VEC_ID;
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
net/iavf: enable interrupt polling For VF hosted by Intel 700 series NICs, internal Rx interrupt and adminq interrupt share the same source, that cause a lot CPU cycles be wasted on interrupt handler on Rx path. The patch disable PCI interrupt and remove the interrupt handler, replace it with a low frequency(50ms) interrupt polling daemon which is implemented by registering an alarm callback periodically. The virtual channel capability bit VIRTCHNL_VF_OFFLOAD_WB_ON_ITR can be used to negotiate if iavf PMD needs to enable background alarm or not, so ideally this change will not impact the case hosted by Intel 800 series NICS. This patch implements the same logic with an early i40e commit: commit 864a800d706d ("net/i40e: remove VF interrupt handler") Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Pallavi Kadam <pallavi.kadam@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-08-25 08:34:35 +00:00
/* set ITR to default */
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
interval = iavf_calc_itr_interval(
net/iavf: enable interrupt polling For VF hosted by Intel 700 series NICs, internal Rx interrupt and adminq interrupt share the same source, that cause a lot CPU cycles be wasted on interrupt handler on Rx path. The patch disable PCI interrupt and remove the interrupt handler, replace it with a low frequency(50ms) interrupt polling daemon which is implemented by registering an alarm callback periodically. The virtual channel capability bit VIRTCHNL_VF_OFFLOAD_WB_ON_ITR can be used to negotiate if iavf PMD needs to enable background alarm or not, so ideally this change will not impact the case hosted by Intel 800 series NICS. This patch implements the same logic with an early i40e commit: commit 864a800d706d ("net/i40e: remove VF interrupt handler") Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Pallavi Kadam <pallavi.kadam@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-08-25 08:34:35 +00:00
IAVF_QUEUE_ITR_INTERVAL_DEFAULT);
net/iavf/base: rename register macro Rename all register macro to align with kernel driver's implementation. Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com> Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
2019-12-03 07:03:04 +00:00
IAVF_WRITE_REG(hw, IAVF_VFINT_DYN_CTL01,
IAVF_VFINT_DYN_CTL01_INTENA_MASK |
(IAVF_ITR_INDEX_DEFAULT <<
IAVF_VFINT_DYN_CTL01_ITR_INDX_SHIFT) |
(interval <<
IAVF_VFINT_DYN_CTL01_INTERVAL_SHIFT));
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
}
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
IAVF_WRITE_FLUSH(hw);
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
/* map all queues to the same interrupt */
net/iavf: enable IRQ mapping configuration for large VF The current IRQ mapping configuration only supports max 16 queues and 16 MSIX vectors. Change the queue vector mapping structure to indicate up to 256 queues. A new opcode is used to handle the case with large number of queues. To avoid adminq buffer size limitation, we support to send the virtchnl message multiple times if needed. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:49:01 +00:00
for (i = 0; i < dev->data->nb_rx_queues; i++) {
qv_map[i].queue_id = i;
qv_map[i].vector_id = vf->msix_base;
}
vf->qv_map = qv_map;
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
} else {
if (!rte_intr_allow_others(intr_handle)) {
vf->nb_msix = 1;
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
vf->msix_base = IAVF_MISC_VEC_ID;
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
for (i = 0; i < dev->data->nb_rx_queues; i++) {
net/iavf: enable IRQ mapping configuration for large VF The current IRQ mapping configuration only supports max 16 queues and 16 MSIX vectors. Change the queue vector mapping structure to indicate up to 256 queues. A new opcode is used to handle the case with large number of queues. To avoid adminq buffer size limitation, we support to send the virtchnl message multiple times if needed. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:49:01 +00:00
qv_map[i].queue_id = i;
qv_map[i].vector_id = vf->msix_base;
drivers: remove direct access to interrupt handle Removing direct access to interrupt handle structure fields, rather use respective get set APIs for the same. Making changes to all the drivers access the interrupt handle fields. Signed-off-by: Harman Kalra <hkalra@marvell.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com> Signed-off-by: David Marchand <david.marchand@redhat.com> Tested-by: Raslan Darawsheh <rasland@nvidia.com>
2021-10-22 20:49:32 +00:00
rte_intr_vec_list_index_set(intr_handle,
i, IAVF_MISC_VEC_ID);
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
}
net/iavf: enable IRQ mapping configuration for large VF The current IRQ mapping configuration only supports max 16 queues and 16 MSIX vectors. Change the queue vector mapping structure to indicate up to 256 queues. A new opcode is used to handle the case with large number of queues. To avoid adminq buffer size limitation, we support to send the virtchnl message multiple times if needed. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:49:01 +00:00
vf->qv_map = qv_map;
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
PMD_DRV_LOG(DEBUG,
net/avf: fix Rx interrupt mapping Vector used for rx mapping is different if WB_ON_ITR is supported. The mapping table need to be updated. Fixes: d6bde6b5eae9 ("net/avf: enable Rx interrupt") Signed-off-by: Jingjing Wu <jingjing.wu@intel.com> Cc: stable@dpdk.org
2018-05-11 15:09:48 +00:00
"vector %u are mapping to all Rx queues",
vf->msix_base);
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
} else {
fix spelling in comments and strings The tool comes from https://github.com/jsoref Signed-off-by: Josh Soref <jsoref@gmail.com> Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
2021-11-29 16:08:02 +00:00
/* If Rx interrupt is required, and we can use
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
* multi interrupts, then the vec is from 1
*/
drivers: remove direct access to interrupt handle Removing direct access to interrupt handle structure fields, rather use respective get set APIs for the same. Making changes to all the drivers access the interrupt handle fields. Signed-off-by: Harman Kalra <hkalra@marvell.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com> Signed-off-by: David Marchand <david.marchand@redhat.com> Tested-by: Raslan Darawsheh <rasland@nvidia.com>
2021-10-22 20:49:32 +00:00
vf->nb_msix =
RTE_MIN(rte_intr_nb_efd_get(intr_handle),
(uint16_t)(vf->vf_res->max_vectors - 1));
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
vf->msix_base = IAVF_RX_VEC_START;
vec = IAVF_RX_VEC_START;
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
for (i = 0; i < dev->data->nb_rx_queues; i++) {
net/iavf: enable IRQ mapping configuration for large VF The current IRQ mapping configuration only supports max 16 queues and 16 MSIX vectors. Change the queue vector mapping structure to indicate up to 256 queues. A new opcode is used to handle the case with large number of queues. To avoid adminq buffer size limitation, we support to send the virtchnl message multiple times if needed. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:49:01 +00:00
qv_map[i].queue_id = i;
qv_map[i].vector_id = vec;
drivers: remove direct access to interrupt handle Removing direct access to interrupt handle structure fields, rather use respective get set APIs for the same. Making changes to all the drivers access the interrupt handle fields. Signed-off-by: Harman Kalra <hkalra@marvell.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com> Signed-off-by: David Marchand <david.marchand@redhat.com> Tested-by: Raslan Darawsheh <rasland@nvidia.com>
2021-10-22 20:49:32 +00:00
rte_intr_vec_list_index_set(intr_handle,
i, vec++);
net/iavf: fix vector mapping with queue Fix the vector mapping with queue by changing the recircle when exceeds RX_VEC_START + nb_msix; Fixes: d6bde6b5eae9 ("net/avf: enable Rx interrupt") Cc: stable@dpdk.org Signed-off-by: Jingjing Wu <jingjing.wu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-01-28 15:00:21 +00:00
if (vec >= vf->nb_msix + IAVF_RX_VEC_START)
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
vec = IAVF_RX_VEC_START;
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
}
net/iavf: enable IRQ mapping configuration for large VF The current IRQ mapping configuration only supports max 16 queues and 16 MSIX vectors. Change the queue vector mapping structure to indicate up to 256 queues. A new opcode is used to handle the case with large number of queues. To avoid adminq buffer size limitation, we support to send the virtchnl message multiple times if needed. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:49:01 +00:00
vf->qv_map = qv_map;
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
PMD_DRV_LOG(DEBUG,
"%u vectors are mapping to %u Rx queues",
vf->nb_msix, dev->data->nb_rx_queues);
}
}
net/iavf: enable IRQ mapping configuration for large VF The current IRQ mapping configuration only supports max 16 queues and 16 MSIX vectors. Change the queue vector mapping structure to indicate up to 256 queues. A new opcode is used to handle the case with large number of queues. To avoid adminq buffer size limitation, we support to send the virtchnl message multiple times if needed. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:49:01 +00:00
if (!vf->lv_enabled) {
if (iavf_config_irq_map(adapter)) {
PMD_DRV_LOG(ERR, "config interrupt mapping failed");
net/iavf: fix Rx queue IRQ resource leak In the iavf_config_rx_queues_irqs function, the memory pointed to by the intr_handle->intr_vec and qv_map addresses is not released in the subsequent hook branch, resulting in resource leakage. Fixes: f593944fc988 ("net/iavf: enable IRQ mapping configuration for large VF") Cc: stable@dpdk.org Signed-off-by: Qiming Chen <chenqiming_huawei@163.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-09-10 06:54:57 +00:00
goto config_irq_map_err;
net/iavf: enable IRQ mapping configuration for large VF The current IRQ mapping configuration only supports max 16 queues and 16 MSIX vectors. Change the queue vector mapping structure to indicate up to 256 queues. A new opcode is used to handle the case with large number of queues. To avoid adminq buffer size limitation, we support to send the virtchnl message multiple times if needed. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:49:01 +00:00
}
} else {
uint16_t num_qv_maps = dev->data->nb_rx_queues;
uint16_t index = 0;
while (num_qv_maps > IAVF_IRQ_MAP_NUM_PER_BUF) {
if (iavf_config_irq_map_lv(adapter,
IAVF_IRQ_MAP_NUM_PER_BUF, index)) {
PMD_DRV_LOG(ERR, "config interrupt mapping for large VF failed");
net/iavf: fix Rx queue IRQ resource leak In the iavf_config_rx_queues_irqs function, the memory pointed to by the intr_handle->intr_vec and qv_map addresses is not released in the subsequent hook branch, resulting in resource leakage. Fixes: f593944fc988 ("net/iavf: enable IRQ mapping configuration for large VF") Cc: stable@dpdk.org Signed-off-by: Qiming Chen <chenqiming_huawei@163.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-09-10 06:54:57 +00:00
goto config_irq_map_err;
net/iavf: enable IRQ mapping configuration for large VF The current IRQ mapping configuration only supports max 16 queues and 16 MSIX vectors. Change the queue vector mapping structure to indicate up to 256 queues. A new opcode is used to handle the case with large number of queues. To avoid adminq buffer size limitation, we support to send the virtchnl message multiple times if needed. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:49:01 +00:00
}
num_qv_maps -= IAVF_IRQ_MAP_NUM_PER_BUF;
index += IAVF_IRQ_MAP_NUM_PER_BUF;
}
if (iavf_config_irq_map_lv(adapter, num_qv_maps, index)) {
PMD_DRV_LOG(ERR, "config interrupt mapping for large VF failed");
net/iavf: fix Rx queue IRQ resource leak In the iavf_config_rx_queues_irqs function, the memory pointed to by the intr_handle->intr_vec and qv_map addresses is not released in the subsequent hook branch, resulting in resource leakage. Fixes: f593944fc988 ("net/iavf: enable IRQ mapping configuration for large VF") Cc: stable@dpdk.org Signed-off-by: Qiming Chen <chenqiming_huawei@163.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-09-10 06:54:57 +00:00
goto config_irq_map_err;
net/iavf: enable IRQ mapping configuration for large VF The current IRQ mapping configuration only supports max 16 queues and 16 MSIX vectors. Change the queue vector mapping structure to indicate up to 256 queues. A new opcode is used to handle the case with large number of queues. To avoid adminq buffer size limitation, we support to send the virtchnl message multiple times if needed. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:49:01 +00:00
}
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
}
return 0;
net/iavf: fix Rx queue IRQ resource leak In the iavf_config_rx_queues_irqs function, the memory pointed to by the intr_handle->intr_vec and qv_map addresses is not released in the subsequent hook branch, resulting in resource leakage. Fixes: f593944fc988 ("net/iavf: enable IRQ mapping configuration for large VF") Cc: stable@dpdk.org Signed-off-by: Qiming Chen <chenqiming_huawei@163.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-09-10 06:54:57 +00:00
config_irq_map_err:
rte_free(vf->qv_map);
vf->qv_map = NULL;
qv_map_alloc_err:
drivers: remove direct access to interrupt handle Removing direct access to interrupt handle structure fields, rather use respective get set APIs for the same. Making changes to all the drivers access the interrupt handle fields. Signed-off-by: Harman Kalra <hkalra@marvell.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com> Signed-off-by: David Marchand <david.marchand@redhat.com> Tested-by: Raslan Darawsheh <rasland@nvidia.com>
2021-10-22 20:49:32 +00:00
rte_intr_vec_list_free(intr_handle);
net/iavf: fix Rx queue IRQ resource leak In the iavf_config_rx_queues_irqs function, the memory pointed to by the intr_handle->intr_vec and qv_map addresses is not released in the subsequent hook branch, resulting in resource leakage. Fixes: f593944fc988 ("net/iavf: enable IRQ mapping configuration for large VF") Cc: stable@dpdk.org Signed-off-by: Qiming Chen <chenqiming_huawei@163.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-09-10 06:54:57 +00:00
return -1;
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
}
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_start_queues(struct rte_eth_dev *dev)
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_rx_queue *rxq;
struct iavf_tx_queue *txq;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
int i;
net/iavf: fix queue start exception handling If any queue start fail during dev_start, all started queues should be stopped. Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Cc: stable@dpdk.org Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-19 05:01:56 +00:00
uint16_t nb_txq, nb_rxq;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
net/iavf: fix queue start exception handling If any queue start fail during dev_start, all started queues should be stopped. Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Cc: stable@dpdk.org Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-19 05:01:56 +00:00
for (nb_txq = 0; nb_txq < dev->data->nb_tx_queues; nb_txq++) {
txq = dev->data->tx_queues[nb_txq];
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
if (txq->tx_deferred_start)
continue;
net/iavf: fix queue start exception handling If any queue start fail during dev_start, all started queues should be stopped. Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Cc: stable@dpdk.org Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-19 05:01:56 +00:00
if (iavf_dev_tx_queue_start(dev, nb_txq) != 0) {
PMD_DRV_LOG(ERR, "Fail to start tx queue %u", nb_txq);
goto tx_err;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
}
}
net/iavf: fix queue start exception handling If any queue start fail during dev_start, all started queues should be stopped. Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Cc: stable@dpdk.org Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-19 05:01:56 +00:00
for (nb_rxq = 0; nb_rxq < dev->data->nb_rx_queues; nb_rxq++) {
rxq = dev->data->rx_queues[nb_rxq];
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
if (rxq->rx_deferred_start)
continue;
net/iavf: fix queue start exception handling If any queue start fail during dev_start, all started queues should be stopped. Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Cc: stable@dpdk.org Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-19 05:01:56 +00:00
if (iavf_dev_rx_queue_start(dev, nb_rxq) != 0) {
PMD_DRV_LOG(ERR, "Fail to start rx queue %u", nb_rxq);
goto rx_err;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
}
}
return 0;
net/iavf: fix queue start exception handling If any queue start fail during dev_start, all started queues should be stopped. Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Cc: stable@dpdk.org Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-19 05:01:56 +00:00
rx_err:
for (i = 0; i < nb_rxq; i++)
iavf_dev_rx_queue_stop(dev, i);
tx_err:
for (i = 0; i < nb_txq; i++)
iavf_dev_tx_queue_stop(dev, i);
return -1;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
}
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_start(struct rte_eth_dev *dev)
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
struct rte_intr_handle *intr_handle = dev->intr_handle;
net/iavf: enable multiple queues configuration for large VF Since the adminq buffer size has a 4K limitation, the current virtchnl command VIRTCHNL_OP_CONFIG_VSI_QUEUES cannot send the message only once to configure up to 256 queues. In this patch, we send the messages multiple times to make sure that the buffer size is less than 4K each time. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:49:00 +00:00
uint16_t num_queue_pairs;
uint16_t index = 0;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
PMD_INIT_FUNC_TRACE();
net/iavf: fix crash after VF reset failure Some pointers will be set to NULL when iavf_dev_reset() failed, for example vf->vf_res, vf->vsi_res vf->rss_key and etc. APIs access these NULL pointers will trigger segfault. This patch adds closed flag to indicate that the VF is closed, and rejects API calls in this state to avoid coredump. Fixes: e74e1bb6280d ("net/iavf: enable port reset") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-12 10:48:51 +00:00
if (adapter->closed)
return -1;
net/iavf: move device state flag Move device state flag from ice_hw to ice_adapter since it should not be a part of base code. Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
2019-12-03 07:03:17 +00:00
adapter->stopped = 0;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
ethdev: fix max Rx packet length There is a confusion on setting max Rx packet length, this patch aims to clarify it. 'rte_eth_dev_configure()' API accepts max Rx packet size via 'uint32_t max_rx_pkt_len' field of the config struct 'struct rte_eth_conf'. Also 'rte_eth_dev_set_mtu()' API can be used to set the MTU, and result stored into '(struct rte_eth_dev)->data->mtu'. These two APIs are related but they work in a disconnected way, they store the set values in different variables which makes hard to figure out which one to use, also having two different method for a related functionality is confusing for the users. Other issues causing confusion is: * maximum transmission unit (MTU) is payload of the Ethernet frame. And 'max_rx_pkt_len' is the size of the Ethernet frame. Difference is Ethernet frame overhead, and this overhead may be different from device to device based on what device supports, like VLAN and QinQ. * 'max_rx_pkt_len' is only valid when application requested jumbo frame, which adds additional confusion and some APIs and PMDs already discards this documented behavior. * For the jumbo frame enabled case, 'max_rx_pkt_len' is an mandatory field, this adds configuration complexity for application. As solution, both APIs gets MTU as parameter, and both saves the result in same variable '(struct rte_eth_dev)->data->mtu'. For this 'max_rx_pkt_len' updated as 'mtu', and it is always valid independent from jumbo frame. For 'rte_eth_dev_configure()', 'dev->data->dev_conf.rxmode.mtu' is user request and it should be used only within configure function and result should be stored to '(struct rte_eth_dev)->data->mtu'. After that point both application and PMD uses MTU from this variable. When application doesn't provide an MTU during 'rte_eth_dev_configure()' default 'RTE_ETHER_MTU' value is used. Additional clarification done on scattered Rx configuration, in relation to MTU and Rx buffer size. MTU is used to configure the device for physical Rx/Tx size limitation, Rx buffer is where to store Rx packets, many PMDs use mbuf data buffer size as Rx buffer size. PMDs compare MTU against Rx buffer size to decide enabling scattered Rx or not. If scattered Rx is not supported by device, MTU bigger than Rx buffer size should fail. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com> Acked-by: Huisong Li <lihuisong@huawei.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com>
2021-10-18 13:48:48 +00:00
vf->max_pkt_len = dev->data->mtu + IAVF_ETH_OVERHEAD;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
vf->num_queue_pairs = RTE_MAX(dev->data->nb_rx_queues,
dev->data->nb_tx_queues);
net/iavf: enable multiple queues configuration for large VF Since the adminq buffer size has a 4K limitation, the current virtchnl command VIRTCHNL_OP_CONFIG_VSI_QUEUES cannot send the message only once to configure up to 256 queues. In this patch, we send the messages multiple times to make sure that the buffer size is less than 4K each time. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:49:00 +00:00
num_queue_pairs = vf->num_queue_pairs;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
net/iavf: query QoS capabilities and set queue TC mapping This patch added the support for VF to config the ETS-based Tx QoS, including querying current QoS configuration from PF and config queue TC mapping. PF QoS is configured in advance and the queried info is provided to the user for future usage. VF queues are mapped to different TCs in PF through virtchnl. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-07-01 11:41:22 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_QOS)
if (iavf_get_qos_cap(adapter)) {
PMD_INIT_LOG(ERR, "Failed to get qos capability");
return -1;
}
net/iavf: enable Rx timestamp on flex descriptor Dump Rx timestamp value into dynamic mbuf field by flex descriptor. This feature is turned on by dev config "enable-rx-timestamp". Currently, it's only supported under scalar path. Signed-off-by: Simei Su <simei.su@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-04-28 08:13:45 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_CAP_PTP) {
if (iavf_get_ptp_cap(adapter)) {
PMD_INIT_LOG(ERR, "Failed to get ptp capability");
return -1;
}
}
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
if (iavf_init_queues(dev) != 0) {
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
PMD_DRV_LOG(ERR, "failed to do Queue init");
return -1;
}
net/iavf: support quanta size configuration This patch adds quanta size configuration support. Quanta size should between 256 and 4096, and be a product of 64. Signed-off-by: Wenjun Wu <wenjun1.wu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-04-22 01:43:00 +00:00
if (iavf_set_vf_quanta_size(adapter, index, num_queue_pairs) != 0)
PMD_DRV_LOG(WARNING, "configure quanta size failed");
net/iavf: enable multiple queues configuration for large VF Since the adminq buffer size has a 4K limitation, the current virtchnl command VIRTCHNL_OP_CONFIG_VSI_QUEUES cannot send the message only once to configure up to 256 queues. In this patch, we send the messages multiple times to make sure that the buffer size is less than 4K each time. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:49:00 +00:00
/* If needed, send configure queues msg multiple times to make the
* adminq buffer length smaller than the 4K limitation.
*/
while (num_queue_pairs > IAVF_CFG_Q_NUM_PER_BUF) {
if (iavf_configure_queues(adapter,
IAVF_CFG_Q_NUM_PER_BUF, index) != 0) {
PMD_DRV_LOG(ERR, "configure queues failed");
goto err_queue;
}
num_queue_pairs -= IAVF_CFG_Q_NUM_PER_BUF;
index += IAVF_CFG_Q_NUM_PER_BUF;
}
if (iavf_configure_queues(adapter, num_queue_pairs, index) != 0) {
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
PMD_DRV_LOG(ERR, "configure queues failed");
goto err_queue;
}
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
if (iavf_config_rx_queues_irqs(dev, intr_handle) != 0) {
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
PMD_DRV_LOG(ERR, "configure irq failed");
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
goto err_queue;
}
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
/* re-enable intr again, because efd assign may change */
if (dev->data->dev_conf.intr_conf.rxq != 0) {
net/iavf: enable interrupt polling For VF hosted by Intel 700 series NICs, internal Rx interrupt and adminq interrupt share the same source, that cause a lot CPU cycles be wasted on interrupt handler on Rx path. The patch disable PCI interrupt and remove the interrupt handler, replace it with a low frequency(50ms) interrupt polling daemon which is implemented by registering an alarm callback periodically. The virtual channel capability bit VIRTCHNL_VF_OFFLOAD_WB_ON_ITR can be used to negotiate if iavf PMD needs to enable background alarm or not, so ideally this change will not impact the case hosted by Intel 800 series NICS. This patch implements the same logic with an early i40e commit: commit 864a800d706d ("net/i40e: remove VF interrupt handler") Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Pallavi Kadam <pallavi.kadam@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-08-25 08:34:35 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_WB_ON_ITR)
rte_intr_disable(intr_handle);
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
rte_intr_enable(intr_handle);
}
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
/* Set all mac addrs */
net/iavf: unify bool type value Replaces the redefined TRUE and FALSE values with standard ones to match the 'bool' type definition. Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
2020-01-15 00:50:25 +00:00
iavf_add_del_all_mac_addr(adapter, true);
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
net/iavf: support multicast configuration This patch enable add multicast address for iavf. Signed-off-by: Wei Zhao <wei.zhao1@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-07-13 07:48:11 +00:00
/* Set all multicast addresses */
iavf_add_del_mc_addr_list(adapter, vf->mc_addrs, vf->mc_addrs_num,
true);
net/iavf: fix race condition with Rx timestamp offload In multi-cores cases for Rx timestamp offload, if packets arrive too fast, aq command to get phc time will be pended. This patch adds spinlock to fix this issue. To avoid phc time being frequently overwritten, move related variables to iavf_rx_queue structure, and each queue will handle timestamp calculation by itself. Fixes: b5cd735132f6 ("net/iavf: enable Rx timestamp on flex descriptor") Fixes: 33db16136e55 ("net/iavf: improve performance of Rx timestamp offload") Signed-off-by: Wenjun Wu <wenjun1.wu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-23 04:49:00 +00:00
rte_spinlock_init(&vf->phc_time_aq_lock);
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
if (iavf_start_queues(dev) != 0) {
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
PMD_DRV_LOG(ERR, "enable queues failed");
goto err_mac;
}
return 0;
err_mac:
net/iavf: unify bool type value Replaces the redefined TRUE and FALSE values with standard ones to match the 'bool' type definition. Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
2020-01-15 00:50:25 +00:00
iavf_add_del_all_mac_addr(adapter, false);
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
err_queue:
return -1;
}
ethdev: change stop operation callback to return int Change eth_dev_stop_t return value from void to int. Make eth_dev_stop_t implementations across all drivers to return negative errno values if case of error conditions. Signed-off-by: Ivan Ilchenko <ivan.ilchenko@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2020-10-15 13:30:45 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_stop(struct rte_eth_dev *dev)
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
{
net/iavf: support multicast configuration This patch enable add multicast address for iavf. Signed-off-by: Wei Zhao <wei.zhao1@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-07-13 07:48:11 +00:00
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
struct rte_intr_handle *intr_handle = dev->intr_handle;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
PMD_INIT_FUNC_TRACE();
net/iavf: fix crash after VF reset failure Some pointers will be set to NULL when iavf_dev_reset() failed, for example vf->vf_res, vf->vsi_res vf->rss_key and etc. APIs access these NULL pointers will trigger segfault. This patch adds closed flag to indicate that the VF is closed, and rejects API calls in this state to avoid coredump. Fixes: e74e1bb6280d ("net/iavf: enable port reset") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-12 10:48:51 +00:00
if (adapter->closed)
return -1;
net/iavf: enable interrupt polling For VF hosted by Intel 700 series NICs, internal Rx interrupt and adminq interrupt share the same source, that cause a lot CPU cycles be wasted on interrupt handler on Rx path. The patch disable PCI interrupt and remove the interrupt handler, replace it with a low frequency(50ms) interrupt polling daemon which is implemented by registering an alarm callback periodically. The virtual channel capability bit VIRTCHNL_VF_OFFLOAD_WB_ON_ITR can be used to negotiate if iavf PMD needs to enable background alarm or not, so ideally this change will not impact the case hosted by Intel 800 series NICS. This patch implements the same logic with an early i40e commit: commit 864a800d706d ("net/i40e: remove VF interrupt handler") Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Pallavi Kadam <pallavi.kadam@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-08-25 08:34:35 +00:00
if (!(vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) &&
dev->data->dev_conf.intr_conf.rxq != 0)
rte_intr_disable(intr_handle);
net/iavf: move device state flag Move device state flag from ice_hw to ice_adapter since it should not be a part of base code. Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
2019-12-03 07:03:17 +00:00
if (adapter->stopped == 1)
ethdev: change stop operation callback to return int Change eth_dev_stop_t return value from void to int. Make eth_dev_stop_t implementations across all drivers to return negative errno values if case of error conditions. Signed-off-by: Ivan Ilchenko <ivan.ilchenko@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2020-10-15 13:30:45 +00:00
return 0;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_stop_queues(dev);
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
/* Disable the interrupt for Rx */
rte_intr_efd_disable(intr_handle);
/* Rx interrupt vector mapping free */
drivers: remove direct access to interrupt handle Removing direct access to interrupt handle structure fields, rather use respective get set APIs for the same. Making changes to all the drivers access the interrupt handle fields. Signed-off-by: Harman Kalra <hkalra@marvell.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com> Signed-off-by: David Marchand <david.marchand@redhat.com> Tested-by: Raslan Darawsheh <rasland@nvidia.com>
2021-10-22 20:49:32 +00:00
rte_intr_vec_list_free(intr_handle);
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
/* remove all mac addrs */
net/iavf: unify bool type value Replaces the redefined TRUE and FALSE values with standard ones to match the 'bool' type definition. Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
2020-01-15 00:50:25 +00:00
iavf_add_del_all_mac_addr(adapter, false);
net/iavf: support multicast configuration This patch enable add multicast address for iavf. Signed-off-by: Wei Zhao <wei.zhao1@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-07-13 07:48:11 +00:00
/* remove all multicast addresses */
iavf_add_del_mc_addr_list(adapter, vf->mc_addrs, vf->mc_addrs_num,
false);
net/iavf: move device state flag Move device state flag from ice_hw to ice_adapter since it should not be a part of base code. Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
2019-12-03 07:03:17 +00:00
adapter->stopped = 1;
ethdev: remove forcing stopped state upon close When closing a port, it is supposed to be already stopped, and marked as such with "dev_started" state zeroed by the stop API. Resetting "dev_started" before calling the driver close operation was hiding the case of not properly stopped port being closed. The flag "dev_started" is not changed anymore in "rte_eth_dev_close()". In case the "dev_stop" function is called from "dev_close", bypassing "rte_eth_dev_stop()" API, the "dev_started" state must be explicitly reset in the PMD in order to keep the same behaviour. Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Reviewed-by: Andrew Rybchenko <arybchenko@solarflare.com>
2020-10-16 13:32:57 +00:00
dev->data->dev_started = 0;
ethdev: change stop operation callback to return int Change eth_dev_stop_t return value from void to int. Make eth_dev_stop_t implementations across all drivers to return negative errno values if case of error conditions. Signed-off-by: Ivan Ilchenko <ivan.ilchenko@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2020-10-15 13:30:45 +00:00
return 0;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
}
ethdev: change device info get callback to return int Change eth_dev_infos_get_t return value from void to int. Make eth_dev_infos_get_t implementations across all drivers to return negative errno values if case of error conditions. Signed-off-by: Ivan Ilchenko <ivan.ilchenko@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-09-12 16:42:28 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
{
net/iavf: support IPsec inline crypto Add support for inline crypto for IPsec, for ESP transport and tunnel over IPv4 and IPv6, as well as supporting the offload for ESP over UDP, and in conjunction with TSO for UDP and TCP flows. Implement support for rte_security packet metadata Add definition for IPsec descriptors, extend support for offload in data and context descriptor to support Add support to virtual channel mailbox for IPsec Crypto request operations. IPsec Crypto requests receive an initial acknowledgment from physical function driver of receipt of request and then an asynchronous response with success/failure of request including any response data. Add enhanced descriptor debugging Refactor of scalar tx burst function to support integration of offload Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Abhijit Sinha <abhijit.sinha@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Reviewed-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:57 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = &adapter->vf;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
net/iavf: fix crash after VF reset failure Some pointers will be set to NULL when iavf_dev_reset() failed, for example vf->vf_res, vf->vsi_res vf->rss_key and etc. APIs access these NULL pointers will trigger segfault. This patch adds closed flag to indicate that the VF is closed, and rejects API calls in this state to avoid coredump. Fixes: e74e1bb6280d ("net/iavf: enable port reset") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-12 10:48:51 +00:00
if (adapter->closed)
return -EIO;
net/iavf: negotiate large VF and request more queues Negotiate large VF capability with PF during VF initialization. If large VF is supported and the number of queues larger than 16 is required, VF requests additional queues from PF. Mark the state that large VF is supported. If the allocated queues number is larger than 16, the max RSS queue region cannot be 16 anymore. Add the function to query max RSS queue region from PF, use it in the RSS initialization and future filters configuration. Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2020-10-22 06:48:59 +00:00
dev_info->max_rx_queues = IAVF_MAX_NUM_QUEUES_LV;
dev_info->max_tx_queues = IAVF_MAX_NUM_QUEUES_LV;
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
dev_info->min_rx_bufsize = IAVF_BUF_SIZE_MIN;
dev_info->max_rx_pktlen = IAVF_FRAME_SIZE_MAX;
net/iavf: set min and max MTU for VF This commit sets the min and max supported MTU values for iavf VF devices via the iavf_dev_info_get() function. Min MTU supported is set to RTE_ETHER_MIN_MTU and max MTU is calculated as the max packet length supported minus the transport overhead. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:20 +00:00
dev_info->max_mtu = dev_info->max_rx_pktlen - IAVF_ETH_OVERHEAD;
dev_info->min_mtu = RTE_ETHER_MIN_MTU;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
dev_info->hash_key_size = vf->vf_res->rss_key_size;
dev_info->reta_size = vf->vf_res->rss_lut_size;
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
dev_info->flow_type_rss_offloads = IAVF_RSS_OFFLOAD_ALL;
dev_info->max_mac_addrs = IAVF_NUM_MACADDR_MAX;
drivers/net: advertise no support for keeping flow rules When RTE_ETH_DEV_CAPA_FLOW_RULE_KEEP capability bit is zero, the specified behavior is the same as it had been before this bit was introduced. Explicitly reset it in all PMDs supporting rte_flow API in order to attract the attention of maintainers, who should eventually choose to advertise the new capability or not. It is already known that mlx4 and mlx5 will not support this capability. For RTE_ETH_DEV_CAPA_FLOW_SHARED_OBJECT_KEEP similar action is not performed, because no PMD except mlx5 supports indirect actions. Any PMD that starts doing so will anyway have to consider all relevant API, including this capability. Suggested-by: Ferruh Yigit <ferruh.yigit@intel.com> Signed-off-by: Dmitry Kozlyuk <dkozlyuk@nvidia.com> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2021-11-02 17:01:32 +00:00
dev_info->dev_capa &= ~RTE_ETH_DEV_CAPA_FLOW_RULE_KEEP;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
dev_info->rx_offload_capa =
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_RX_OFFLOAD_VLAN_STRIP |
RTE_ETH_RX_OFFLOAD_QINQ_STRIP |
RTE_ETH_RX_OFFLOAD_IPV4_CKSUM |
RTE_ETH_RX_OFFLOAD_UDP_CKSUM |
RTE_ETH_RX_OFFLOAD_TCP_CKSUM |
RTE_ETH_RX_OFFLOAD_OUTER_IPV4_CKSUM |
RTE_ETH_RX_OFFLOAD_SCATTER |
RTE_ETH_RX_OFFLOAD_VLAN_FILTER |
RTE_ETH_RX_OFFLOAD_RSS_HASH;
net/iavf: support new VLAN capabilities The new VLAN virtchnl opcodes introduce new capabilities like VLAN filtering, stripping and insertion. The AVF needs to query the VLAN capabilities based on current device configuration firstly. AVF is able to configure inner VLAN filter when port VLAN is enabled base on negotiation; and AVF is able to configure outer VLAN (0x8100) if port VLAN is disabled to be compatible with legacy mode. When port VLAN is updated by DCF, the AVF needs to reset to query the new VLAN capabilities. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-12 08:13:02 +00:00
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
dev_info->tx_offload_capa =
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_TX_OFFLOAD_VLAN_INSERT |
RTE_ETH_TX_OFFLOAD_QINQ_INSERT |
RTE_ETH_TX_OFFLOAD_IPV4_CKSUM |
RTE_ETH_TX_OFFLOAD_UDP_CKSUM |
RTE_ETH_TX_OFFLOAD_TCP_CKSUM |
RTE_ETH_TX_OFFLOAD_SCTP_CKSUM |
RTE_ETH_TX_OFFLOAD_OUTER_IPV4_CKSUM |
net/iavf: enable inner and outer Tx checksum offload This patch is to enable scalar path inner and outer Tx checksum offload for tunnel packet by configure ol_flags. Signed-off-by: Peng Zhang <peng1x.zhang@intel.com> Signed-off-by: Zhichao Zeng <zhichaox.zeng@intel.com> Tested-by: Ke Xu <ke1.xu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-09-20 09:14:52 +00:00
RTE_ETH_TX_OFFLOAD_OUTER_UDP_CKSUM |
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_TX_OFFLOAD_TCP_TSO |
RTE_ETH_TX_OFFLOAD_VXLAN_TNL_TSO |
RTE_ETH_TX_OFFLOAD_GRE_TNL_TSO |
RTE_ETH_TX_OFFLOAD_IPIP_TNL_TSO |
RTE_ETH_TX_OFFLOAD_GENEVE_TNL_TSO |
RTE_ETH_TX_OFFLOAD_MULTI_SEGS |
RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
net/iavf: support CRC strip disabling The VF will check the PF's CRC strip capability firstly, then set the 'CRC strip disable' value in the queue configuration according to the RX CRC offload setting. Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-12 08:13:00 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_CRC)
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
dev_info->rx_offload_capa |= RTE_ETH_RX_OFFLOAD_KEEP_CRC;
net/iavf: support CRC strip disabling The VF will check the PF's CRC strip capability firstly, then set the 'CRC strip disable' value in the queue configuration according to the RX CRC offload setting. Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-12 08:13:00 +00:00
net/iavf: enable Rx timestamp on flex descriptor Dump Rx timestamp value into dynamic mbuf field by flex descriptor. This feature is turned on by dev config "enable-rx-timestamp". Currently, it's only supported under scalar path. Signed-off-by: Simei Su <simei.su@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-04-28 08:13:45 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_CAP_PTP)
dev_info->rx_offload_capa |= RTE_ETH_RX_OFFLOAD_TIMESTAMP;
net/iavf: support IPsec inline crypto Add support for inline crypto for IPsec, for ESP transport and tunnel over IPv4 and IPv6, as well as supporting the offload for ESP over UDP, and in conjunction with TSO for UDP and TCP flows. Implement support for rte_security packet metadata Add definition for IPsec descriptors, extend support for offload in data and context descriptor to support Add support to virtual channel mailbox for IPsec Crypto request operations. IPsec Crypto requests receive an initial acknowledgment from physical function driver of receipt of request and then an asynchronous response with success/failure of request including any response data. Add enhanced descriptor debugging Refactor of scalar tx burst function to support integration of offload Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Abhijit Sinha <abhijit.sinha@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Reviewed-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:57 +00:00
if (iavf_ipsec_crypto_supported(adapter)) {
dev_info->rx_offload_capa |= RTE_ETH_RX_OFFLOAD_SECURITY;
dev_info->tx_offload_capa |= RTE_ETH_TX_OFFLOAD_SECURITY;
}
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
dev_info->default_rxconf = (struct rte_eth_rxconf) {
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
.rx_free_thresh = IAVF_DEFAULT_RX_FREE_THRESH,
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
.rx_drop_en = 0,
net/avf: convert to new Rx and Tx offload API Ethdev Tx offloads API has changed since: commit cba7f53b717d ("ethdev: introduce Tx queue offloads API") This commit support the new Rx and Tx offloads API. Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2018-03-01 06:41:46 +00:00
.offloads = 0,
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
};
dev_info->default_txconf = (struct rte_eth_txconf) {
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
.tx_free_thresh = IAVF_DEFAULT_TX_FREE_THRESH,
.tx_rs_thresh = IAVF_DEFAULT_TX_RS_THRESH,
net/avf: convert to new Rx and Tx offload API Ethdev Tx offloads API has changed since: commit cba7f53b717d ("ethdev: introduce Tx queue offloads API") This commit support the new Rx and Tx offloads API. Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2018-03-01 06:41:46 +00:00
.offloads = 0,
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
};
dev_info->rx_desc_lim = (struct rte_eth_desc_lim) {
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
.nb_max = IAVF_MAX_RING_DESC,
.nb_min = IAVF_MIN_RING_DESC,
.nb_align = IAVF_ALIGN_RING_DESC,
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
};
dev_info->tx_desc_lim = (struct rte_eth_desc_lim) {
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
.nb_max = IAVF_MAX_RING_DESC,
.nb_min = IAVF_MIN_RING_DESC,
.nb_align = IAVF_ALIGN_RING_DESC,
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
};
ethdev: change device info get callback to return int Change eth_dev_infos_get_t return value from void to int. Make eth_dev_infos_get_t implementations across all drivers to return negative errno values if case of error conditions. Signed-off-by: Ivan Ilchenko <ivan.ilchenko@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-09-12 16:42:28 +00:00
return 0;
net/avf: enable queue and device enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:55 +00:00
}
net/avf: enable basic Rx Tx Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
2018-01-10 13:01:56 +00:00
static const uint32_t *
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_supported_ptypes_get(struct rte_eth_dev *dev __rte_unused)
net/avf: enable basic Rx Tx Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
2018-01-10 13:01:56 +00:00
{
static const uint32_t ptypes[] = {
RTE_PTYPE_L2_ETHER,
RTE_PTYPE_L3_IPV4_EXT_UNKNOWN,
RTE_PTYPE_L4_FRAG,
RTE_PTYPE_L4_ICMP,
RTE_PTYPE_L4_NONFRAG,
RTE_PTYPE_L4_SCTP,
RTE_PTYPE_L4_TCP,
RTE_PTYPE_L4_UDP,
RTE_PTYPE_UNKNOWN
};
return ptypes;
}
net/avf: enable link status update Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:57 +00:00
int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_link_update(struct rte_eth_dev *dev,
net/avf: enable link status update Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:57 +00:00
__rte_unused int wait_to_complete)
{
struct rte_eth_link new_link;
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
net/avf: enable link status update Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:57 +00:00
net/iavf: fix uninitialized variable This is observed with experimental gcc 11, although the older gcc versions don't complain about it, issue seems a valid one. gcc version 11.0.0 20200621 (experimental) (GCC) Build error .../drivers/net/iavf/iavf_ethdev.c: In function ‘iavf_dev_link_update’: .../drivers/net/iavf/iavf_ethdev.c:641:6: error: ‘new_link’ is used uninitialized [-Werror=uninitialized] 641 | if (rte_atomic64_cmpset((uint64_t *)&dev->data->dev_link, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 642 | *(uint64_t *)&dev->data->dev_link, | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 643 | *(uint64_t *)&new_link) == 0) | ~~~~~~~~~~~~~~~~~~~~~~~ .../drivers/net/iavf/iavf_ethdev.c:596:22: note: ‘new_link’ declared here 596 | struct rte_eth_link new_link; | ^~~~~~~~ cc1: all warnings being treated as error All fields of the 'new_link' struct is already set in function, so the 'uninitialized' warning is hard to get. This is because the combination of aligning and bitfield usage of the struct The definition of the struct is: struct rte_eth_link { uint32_t link_speed; /**< ETH_SPEED_NUM_ */ uint16_t link_duplex : 1; /**< ETH_LINK_[HALF/FULL]_DUPLEX */ uint16_t link_autoneg : 1; /**< ETH_LINK_[AUTONEG/FIXED] */ uint16_t link_status : 1; /**< ETH_LINK_[DOWN/UP] */ } __rte_aligned(8); /**< aligned for atomic64 read/write */ Overall the size of the 'struct rte_eth_link' is 64 bits, but function only sets the 35 bits of it, because only 3 bits of 16 bits variable are used. When the struct cast to 'uint64_t' because of the 'rte_atomic64_cmpset' the upper 29 bits are used without initialization. To fix the uninitialized usage, memset the variable 'new_link' before using it. Fixes: 48de41ca11f0 ("net/avf: enable link status update") Cc: stable@dpdk.org Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-06-23 13:45:31 +00:00
memset(&new_link, 0, sizeof(new_link));
net/avf: enable link status update Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:57 +00:00
/* Only read status info stored in VF, and the info is updated
* when receive LINK_CHANGE evnet from PF by Virtchnnl.
*/
switch (vf->link_speed) {
net/iavf: enable more link speed Enable advanced link speed mode (VIRTCHNL_VF_CAP_ADV_LINK_SPEED) so iavf PMD can identify more link speed that reported by pf. Cc: stable@dpdk.org Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Wei Zhao <wei.zhao1@intel.com>
2019-05-04 14:09:10 +00:00
case 10:
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
new_link.link_speed = RTE_ETH_SPEED_NUM_10M;
net/iavf: enable more link speed Enable advanced link speed mode (VIRTCHNL_VF_CAP_ADV_LINK_SPEED) so iavf PMD can identify more link speed that reported by pf. Cc: stable@dpdk.org Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Wei Zhao <wei.zhao1@intel.com>
2019-05-04 14:09:10 +00:00
break;
case 100:
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
new_link.link_speed = RTE_ETH_SPEED_NUM_100M;
net/avf: enable link status update Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:57 +00:00
break;
net/iavf: enable more link speed Enable advanced link speed mode (VIRTCHNL_VF_CAP_ADV_LINK_SPEED) so iavf PMD can identify more link speed that reported by pf. Cc: stable@dpdk.org Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Wei Zhao <wei.zhao1@intel.com>
2019-05-04 14:09:10 +00:00
case 1000:
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
new_link.link_speed = RTE_ETH_SPEED_NUM_1G;
net/avf: enable link status update Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:57 +00:00
break;
net/iavf: enable more link speed Enable advanced link speed mode (VIRTCHNL_VF_CAP_ADV_LINK_SPEED) so iavf PMD can identify more link speed that reported by pf. Cc: stable@dpdk.org Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Wei Zhao <wei.zhao1@intel.com>
2019-05-04 14:09:10 +00:00
case 10000:
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
new_link.link_speed = RTE_ETH_SPEED_NUM_10G;
net/avf: enable link status update Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:57 +00:00
break;
net/iavf: enable more link speed Enable advanced link speed mode (VIRTCHNL_VF_CAP_ADV_LINK_SPEED) so iavf PMD can identify more link speed that reported by pf. Cc: stable@dpdk.org Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Wei Zhao <wei.zhao1@intel.com>
2019-05-04 14:09:10 +00:00
case 20000:
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
new_link.link_speed = RTE_ETH_SPEED_NUM_20G;
net/avf: enable link status update Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:57 +00:00
break;
net/iavf: enable more link speed Enable advanced link speed mode (VIRTCHNL_VF_CAP_ADV_LINK_SPEED) so iavf PMD can identify more link speed that reported by pf. Cc: stable@dpdk.org Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Wei Zhao <wei.zhao1@intel.com>
2019-05-04 14:09:10 +00:00
case 25000:
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
new_link.link_speed = RTE_ETH_SPEED_NUM_25G;
net/avf: enable link status update Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:57 +00:00
break;
net/iavf: enable more link speed Enable advanced link speed mode (VIRTCHNL_VF_CAP_ADV_LINK_SPEED) so iavf PMD can identify more link speed that reported by pf. Cc: stable@dpdk.org Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Wei Zhao <wei.zhao1@intel.com>
2019-05-04 14:09:10 +00:00
case 40000:
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
new_link.link_speed = RTE_ETH_SPEED_NUM_40G;
net/avf: enable link status update Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:57 +00:00
break;
net/iavf: enable more link speed Enable advanced link speed mode (VIRTCHNL_VF_CAP_ADV_LINK_SPEED) so iavf PMD can identify more link speed that reported by pf. Cc: stable@dpdk.org Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Wei Zhao <wei.zhao1@intel.com>
2019-05-04 14:09:10 +00:00
case 50000:
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
new_link.link_speed = RTE_ETH_SPEED_NUM_50G;
net/iavf: enable more link speed Enable advanced link speed mode (VIRTCHNL_VF_CAP_ADV_LINK_SPEED) so iavf PMD can identify more link speed that reported by pf. Cc: stable@dpdk.org Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Wei Zhao <wei.zhao1@intel.com>
2019-05-04 14:09:10 +00:00
break;
case 100000:
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
new_link.link_speed = RTE_ETH_SPEED_NUM_100G;
net/iavf: enable more link speed Enable advanced link speed mode (VIRTCHNL_VF_CAP_ADV_LINK_SPEED) so iavf PMD can identify more link speed that reported by pf. Cc: stable@dpdk.org Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Wei Zhao <wei.zhao1@intel.com>
2019-05-04 14:09:10 +00:00
break;
net/avf: enable link status update Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:57 +00:00
default:
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
new_link.link_speed = RTE_ETH_SPEED_NUM_NONE;
net/avf: enable link status update Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:57 +00:00
break;
}
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
new_link.link_duplex = RTE_ETH_LINK_FULL_DUPLEX;
new_link.link_status = vf->link_up ? RTE_ETH_LINK_UP :
RTE_ETH_LINK_DOWN;
net/avf: fix link autoneg value Intention of the logic is: If ETH_LINK_SPEED_FIXED is set in dev_conf, set link_autoneg to ETH_LINK_FIXED, else set it to ETH_LINK_AUTONEG ETH_LINK_SPEED_FIXED value is 1, and ETH_LINK_FIXED is 0; Current logic is broken, fix it according above values. Fixes: 48de41ca11f0 ("net/avf: enable link status update") Cc: stable@dpdk.org Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2018-03-09 17:56:31 +00:00
new_link.link_autoneg = !(dev->data->dev_conf.link_speeds &
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_LINK_SPEED_FIXED);
net/avf: enable link status update Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:57 +00:00
net/iavf: use link status helper functions Use new rte_eth_linkstatus_get/set helper functions to handle link status update. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:19 +00:00
return rte_eth_linkstatus_set(dev, &new_link);
net/avf: enable link status update Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:57 +00:00
}
ethdev: change promiscuous callbacks to return status Enabling/disabling of promiscuous mode is not always successful and it should be taken into account to be able to handle it properly. When correct return status is unclear from driver code, -EAGAIN is used. Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: Matan Azrad <matan@mellanox.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com>
2019-09-14 11:37:24 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_promiscuous_enable(struct rte_eth_dev *dev)
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
ethdev: change promiscuous callbacks to return status Enabling/disabling of promiscuous mode is not always successful and it should be taken into account to be able to handle it properly. When correct return status is unclear from driver code, -EAGAIN is used. Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: Matan Azrad <matan@mellanox.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com>
2019-09-14 11:37:24 +00:00
net/iavf: optimize promiscuous device operations This patch is to improve efficiency and eliminate code redundancy of promiscuous ops. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:22 +00:00
return iavf_config_promisc(adapter,
true, vf->promisc_multicast_enabled);
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
}
ethdev: change promiscuous callbacks to return status Enabling/disabling of promiscuous mode is not always successful and it should be taken into account to be able to handle it properly. When correct return status is unclear from driver code, -EAGAIN is used. Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: Matan Azrad <matan@mellanox.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com>
2019-09-14 11:37:24 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_promiscuous_disable(struct rte_eth_dev *dev)
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
ethdev: change promiscuous callbacks to return status Enabling/disabling of promiscuous mode is not always successful and it should be taken into account to be able to handle it properly. When correct return status is unclear from driver code, -EAGAIN is used. Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: Matan Azrad <matan@mellanox.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com>
2019-09-14 11:37:24 +00:00
net/iavf: optimize promiscuous device operations This patch is to improve efficiency and eliminate code redundancy of promiscuous ops. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:22 +00:00
return iavf_config_promisc(adapter,
false, vf->promisc_multicast_enabled);
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
}
ethdev: change allmulticast callbacks to return status Enabling/disabling of allmulticast mode is not always successful and it should be taken into account to be able to handle it properly. When correct return status is unclear from driver code, -EAGAIN is used. Signed-off-by: Ivan Ilchenko <ivan.ilchenko@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com>
2019-09-24 12:56:10 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_allmulticast_enable(struct rte_eth_dev *dev)
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
ethdev: change allmulticast callbacks to return status Enabling/disabling of allmulticast mode is not always successful and it should be taken into account to be able to handle it properly. When correct return status is unclear from driver code, -EAGAIN is used. Signed-off-by: Ivan Ilchenko <ivan.ilchenko@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com>
2019-09-24 12:56:10 +00:00
net/iavf: optimize promiscuous device operations This patch is to improve efficiency and eliminate code redundancy of promiscuous ops. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:22 +00:00
return iavf_config_promisc(adapter,
vf->promisc_unicast_enabled, true);
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
}
ethdev: change allmulticast callbacks to return status Enabling/disabling of allmulticast mode is not always successful and it should be taken into account to be able to handle it properly. When correct return status is unclear from driver code, -EAGAIN is used. Signed-off-by: Ivan Ilchenko <ivan.ilchenko@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com>
2019-09-24 12:56:10 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_allmulticast_disable(struct rte_eth_dev *dev)
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
ethdev: change allmulticast callbacks to return status Enabling/disabling of allmulticast mode is not always successful and it should be taken into account to be able to handle it properly. When correct return status is unclear from driver code, -EAGAIN is used. Signed-off-by: Ivan Ilchenko <ivan.ilchenko@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com>
2019-09-24 12:56:10 +00:00
net/iavf: optimize promiscuous device operations This patch is to improve efficiency and eliminate code redundancy of promiscuous ops. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:22 +00:00
return iavf_config_promisc(adapter,
vf->promisc_unicast_enabled, false);
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
}
static int
net: add rte prefix to ether structures Add 'rte_' prefix to structures: - rename struct ether_addr as struct rte_ether_addr. - rename struct ether_hdr as struct rte_ether_hdr. - rename struct vlan_hdr as struct rte_vlan_hdr. - rename struct vxlan_hdr as struct rte_vxlan_hdr. - rename struct vxlan_gpe_hdr as struct rte_vxlan_gpe_hdr. 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 16:13:03 +00:00
iavf_dev_add_mac_addr(struct rte_eth_dev *dev, struct rte_ether_addr *addr,
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
__rte_unused uint32_t index,
__rte_unused uint32_t pool)
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
int err;
net: add rte prefix to ether functions Add 'rte_' prefix to functions: - rename is_same_ether_addr() as rte_is_same_ether_addr(). - rename is_zero_ether_addr() as rte_is_zero_ether_addr(). - rename is_unicast_ether_addr() as rte_is_unicast_ether_addr(). - rename is_multicast_ether_addr() as rte_is_multicast_ether_addr(). - rename is_broadcast_ether_addr() as rte_is_broadcast_ether_addr(). - rename is_universal_ether_addr() as rte_is_universal_ether_addr(). - rename is_local_admin_ether_addr() as rte_is_local_admin_ether_addr(). - rename is_valid_assigned_ether_addr() as rte_is_valid_assigned_ether_addr(). - rename eth_random_addr() as rte_eth_random_addr(). - rename ether_addr_copy() as rte_ether_addr_copy(). - rename ether_format_addr() as rte_ether_format_addr(). 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 16:13:04 +00:00
if (rte_is_zero_ether_addr(addr)) {
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
PMD_DRV_LOG(ERR, "Invalid Ethernet Address");
return -EINVAL;
}
net/iavf: fix lack of MAC type when set MAC address When set default MAC address, use type VIRTCHNL_ETHER_ADDR_PRIMARY as this case is changing device/primary unicast MAC. For other cases, such as adding or deleting extra unicast addresses and multicast addresses, use type VIRTCHNL_ETHER_ADDR_EXTRA. Fixes: cb25d4323fbf ("net/avf: enable MAC VLAN and promisc ops") Cc: stable@dpdk.org Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Tested-by: Yan Xia <yanx.xia@intel.com>
2021-03-19 09:20:19 +00:00
err = iavf_add_del_eth_addr(adapter, addr, true, VIRTCHNL_ETHER_ADDR_EXTRA);
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
if (err) {
PMD_DRV_LOG(ERR, "fail to add MAC address");
return -EIO;
}
vf->mac_num++;
return 0;
}
static void
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_del_mac_addr(struct rte_eth_dev *dev, uint32_t index)
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
net: add rte prefix to ether structures Add 'rte_' prefix to structures: - rename struct ether_addr as struct rte_ether_addr. - rename struct ether_hdr as struct rte_ether_hdr. - rename struct vlan_hdr as struct rte_vlan_hdr. - rename struct vxlan_hdr as struct rte_vxlan_hdr. - rename struct vxlan_gpe_hdr as struct rte_vxlan_gpe_hdr. 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 16:13:03 +00:00
struct rte_ether_addr *addr;
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
int err;
addr = &dev->data->mac_addrs[index];
net/iavf: fix lack of MAC type when set MAC address When set default MAC address, use type VIRTCHNL_ETHER_ADDR_PRIMARY as this case is changing device/primary unicast MAC. For other cases, such as adding or deleting extra unicast addresses and multicast addresses, use type VIRTCHNL_ETHER_ADDR_EXTRA. Fixes: cb25d4323fbf ("net/avf: enable MAC VLAN and promisc ops") Cc: stable@dpdk.org Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Tested-by: Yan Xia <yanx.xia@intel.com>
2021-03-19 09:20:19 +00:00
err = iavf_add_del_eth_addr(adapter, addr, false, VIRTCHNL_ETHER_ADDR_EXTRA);
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
if (err)
PMD_DRV_LOG(ERR, "fail to delete MAC address");
vf->mac_num--;
}
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_vlan_filter_set(struct rte_eth_dev *dev, uint16_t vlan_id, int on)
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
int err;
net/iavf: fix crash after VF reset failure Some pointers will be set to NULL when iavf_dev_reset() failed, for example vf->vf_res, vf->vsi_res vf->rss_key and etc. APIs access these NULL pointers will trigger segfault. This patch adds closed flag to indicate that the VF is closed, and rejects API calls in this state to avoid coredump. Fixes: e74e1bb6280d ("net/iavf: enable port reset") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-12 10:48:51 +00:00
if (adapter->closed)
return -EIO;
net/iavf: support new VLAN capabilities The new VLAN virtchnl opcodes introduce new capabilities like VLAN filtering, stripping and insertion. The AVF needs to query the VLAN capabilities based on current device configuration firstly. AVF is able to configure inner VLAN filter when port VLAN is enabled base on negotiation; and AVF is able to configure outer VLAN (0x8100) if port VLAN is disabled to be compatible with legacy mode. When port VLAN is updated by DCF, the AVF needs to reset to query the new VLAN capabilities. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-12 08:13:02 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN_V2) {
err = iavf_add_del_vlan_v2(adapter, vlan_id, on);
if (err)
return -EIO;
return 0;
}
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
if (!(vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN))
return -ENOTSUP;
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
err = iavf_add_del_vlan(adapter, vlan_id, on);
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
if (err)
return -EIO;
return 0;
}
net/iavf: support new VLAN capabilities The new VLAN virtchnl opcodes introduce new capabilities like VLAN filtering, stripping and insertion. The AVF needs to query the VLAN capabilities based on current device configuration firstly. AVF is able to configure inner VLAN filter when port VLAN is enabled base on negotiation; and AVF is able to configure outer VLAN (0x8100) if port VLAN is disabled to be compatible with legacy mode. When port VLAN is updated by DCF, the AVF needs to reset to query the new VLAN capabilities. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-12 08:13:02 +00:00
static void
iavf_iterate_vlan_filters_v2(struct rte_eth_dev *dev, bool enable)
{
struct rte_vlan_filter_conf *vfc = &dev->data->vlan_filter_conf;
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
uint32_t i, j;
uint64_t ids;
for (i = 0; i < RTE_DIM(vfc->ids); i++) {
if (vfc->ids[i] == 0)
continue;
ids = vfc->ids[i];
for (j = 0; ids != 0 && j < 64; j++, ids >>= 1) {
if (ids & 1)
iavf_add_del_vlan_v2(adapter,
64 * i + j, enable);
}
}
}
static int
iavf_dev_vlan_offload_set_v2(struct rte_eth_dev *dev, int mask)
{
struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode;
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
bool enable;
int err;
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
if (mask & RTE_ETH_VLAN_FILTER_MASK) {
enable = !!(rxmode->offloads & RTE_ETH_RX_OFFLOAD_VLAN_FILTER);
net/iavf: support new VLAN capabilities The new VLAN virtchnl opcodes introduce new capabilities like VLAN filtering, stripping and insertion. The AVF needs to query the VLAN capabilities based on current device configuration firstly. AVF is able to configure inner VLAN filter when port VLAN is enabled base on negotiation; and AVF is able to configure outer VLAN (0x8100) if port VLAN is disabled to be compatible with legacy mode. When port VLAN is updated by DCF, the AVF needs to reset to query the new VLAN capabilities. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-12 08:13:02 +00:00
iavf_iterate_vlan_filters_v2(dev, enable);
}
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
if (mask & RTE_ETH_VLAN_STRIP_MASK) {
enable = !!(rxmode->offloads & RTE_ETH_RX_OFFLOAD_VLAN_STRIP);
net/iavf: support new VLAN capabilities The new VLAN virtchnl opcodes introduce new capabilities like VLAN filtering, stripping and insertion. The AVF needs to query the VLAN capabilities based on current device configuration firstly. AVF is able to configure inner VLAN filter when port VLAN is enabled base on negotiation; and AVF is able to configure outer VLAN (0x8100) if port VLAN is disabled to be compatible with legacy mode. When port VLAN is updated by DCF, the AVF needs to reset to query the new VLAN capabilities. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-12 08:13:02 +00:00
err = iavf_config_vlan_strip_v2(adapter, enable);
net/iavf: fix VLAN strip configuration For AVF with single VLAN mode (SVM), port VLAN stripping config has already been disabled by PF. In this scenario, the error of -ENOTSUP can be ignored. Fixes: 1c301e8c3cff ("net/iavf: support new VLAN capabilities") Signed-off-by: Junfeng Guo <junfeng.guo@intel.com> Acked-by: Haiyue Wang <haiyue.wang@intel.com>
2021-01-22 13:35:41 +00:00
/* If not support, the stripping is already disabled by PF */
if (err == -ENOTSUP && !enable)
err = 0;
net/iavf: support new VLAN capabilities The new VLAN virtchnl opcodes introduce new capabilities like VLAN filtering, stripping and insertion. The AVF needs to query the VLAN capabilities based on current device configuration firstly. AVF is able to configure inner VLAN filter when port VLAN is enabled base on negotiation; and AVF is able to configure outer VLAN (0x8100) if port VLAN is disabled to be compatible with legacy mode. When port VLAN is updated by DCF, the AVF needs to reset to query the new VLAN capabilities. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-12 08:13:02 +00:00
if (err)
return -EIO;
}
return 0;
}
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_vlan_offload_set(struct rte_eth_dev *dev, int mask)
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
struct rte_eth_conf *dev_conf = &dev->data->dev_conf;
int err;
net/iavf: fix crash after VF reset failure Some pointers will be set to NULL when iavf_dev_reset() failed, for example vf->vf_res, vf->vsi_res vf->rss_key and etc. APIs access these NULL pointers will trigger segfault. This patch adds closed flag to indicate that the VF is closed, and rejects API calls in this state to avoid coredump. Fixes: e74e1bb6280d ("net/iavf: enable port reset") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-12 10:48:51 +00:00
if (adapter->closed)
return -EIO;
net/iavf: support new VLAN capabilities The new VLAN virtchnl opcodes introduce new capabilities like VLAN filtering, stripping and insertion. The AVF needs to query the VLAN capabilities based on current device configuration firstly. AVF is able to configure inner VLAN filter when port VLAN is enabled base on negotiation; and AVF is able to configure outer VLAN (0x8100) if port VLAN is disabled to be compatible with legacy mode. When port VLAN is updated by DCF, the AVF needs to reset to query the new VLAN capabilities. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-12 08:13:02 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN_V2)
return iavf_dev_vlan_offload_set_v2(dev, mask);
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
if (!(vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN))
return -ENOTSUP;
/* Vlan stripping setting */
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
if (mask & RTE_ETH_VLAN_STRIP_MASK) {
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
/* Enable or disable VLAN stripping */
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
if (dev_conf->rxmode.offloads & RTE_ETH_RX_OFFLOAD_VLAN_STRIP)
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
err = iavf_enable_vlan_strip(adapter);
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
else
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
err = iavf_disable_vlan_strip(adapter);
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
net/avf: fix uninitialized variables This patch fixes the coverity UNINIT issue. Coverity issue: 257016, 257036 Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Reported-by: John McNamara <john.mcnamara@intel.com> Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-30 03:32:58 +00:00
if (err)
return -EIO;
}
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
return 0;
}
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_rss_reta_update(struct rte_eth_dev *dev,
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
struct rte_eth_rss_reta_entry64 *reta_conf,
uint16_t reta_size)
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
uint8_t *lut;
uint16_t i, idx, shift;
int ret;
net/iavf: fix crash after VF reset failure Some pointers will be set to NULL when iavf_dev_reset() failed, for example vf->vf_res, vf->vsi_res vf->rss_key and etc. APIs access these NULL pointers will trigger segfault. This patch adds closed flag to indicate that the VF is closed, and rejects API calls in this state to avoid coredump. Fixes: e74e1bb6280d ("net/iavf: enable port reset") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-12 10:48:51 +00:00
if (adapter->closed)
return -EIO;
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
if (!(vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF))
return -ENOTSUP;
if (reta_size != vf->vf_res->rss_lut_size) {
PMD_DRV_LOG(ERR, "The size of hash lookup table configured "
"(%d) doesn't match the number of hardware can "
"support (%d)", reta_size, vf->vf_res->rss_lut_size);
return -EINVAL;
}
lut = rte_zmalloc("rss_lut", reta_size, 0);
if (!lut) {
PMD_DRV_LOG(ERR, "No memory can be allocated");
return -ENOMEM;
}
/* store the old lut table temporarily */
rte_memcpy(lut, vf->rss_lut, reta_size);
for (i = 0; i < reta_size; i++) {
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
idx = i / RTE_ETH_RETA_GROUP_SIZE;
shift = i % RTE_ETH_RETA_GROUP_SIZE;
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
if (reta_conf[idx].mask & (1ULL << shift))
lut[i] = reta_conf[idx].reta[shift];
}
rte_memcpy(vf->rss_lut, lut, reta_size);
fix spelling in comments and strings The tool comes from https://github.com/jsoref Signed-off-by: Josh Soref <jsoref@gmail.com> Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
2021-11-29 16:08:02 +00:00
/* send virtchnl ops to configure RSS */
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
ret = iavf_configure_rss_lut(adapter);
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
if (ret) /* revert back */
rte_memcpy(vf->rss_lut, lut, reta_size);
rte_free(lut);
return ret;
}
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_rss_reta_query(struct rte_eth_dev *dev,
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
struct rte_eth_rss_reta_entry64 *reta_conf,
uint16_t reta_size)
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
uint16_t i, idx, shift;
net/iavf: fix crash after VF reset failure Some pointers will be set to NULL when iavf_dev_reset() failed, for example vf->vf_res, vf->vsi_res vf->rss_key and etc. APIs access these NULL pointers will trigger segfault. This patch adds closed flag to indicate that the VF is closed, and rejects API calls in this state to avoid coredump. Fixes: e74e1bb6280d ("net/iavf: enable port reset") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-12 10:48:51 +00:00
if (adapter->closed)
return -EIO;
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
if (!(vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF))
return -ENOTSUP;
if (reta_size != vf->vf_res->rss_lut_size) {
PMD_DRV_LOG(ERR, "The size of hash lookup table configured "
"(%d) doesn't match the number of hardware can "
"support (%d)", reta_size, vf->vf_res->rss_lut_size);
return -EINVAL;
}
for (i = 0; i < reta_size; i++) {
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
idx = i / RTE_ETH_RETA_GROUP_SIZE;
shift = i % RTE_ETH_RETA_GROUP_SIZE;
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
if (reta_conf[idx].mask & (1ULL << shift))
reta_conf[idx].reta[shift] = vf->rss_lut[i];
}
return 0;
}
static int
net/iavf: improve default RSS Add support to actively configure the RSS through port config. Any kernel PF enabled default RSS will be disabled during initialization. Besides, default RSS will be configured based on rte_eth_rss_conf->rss_hf. Currently supported default rss_type: ipv4[6], ipv4[6]_udp, ipv4[6]_tcp, ipv4[6]_sctp. Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-12-23 12:52:28 +00:00
iavf_set_rss_key(struct iavf_adapter *adapter, uint8_t *key, uint8_t key_len)
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
/* HENA setting, it is enabled by default, no change */
net/iavf: improve default RSS Add support to actively configure the RSS through port config. Any kernel PF enabled default RSS will be disabled during initialization. Besides, default RSS will be configured based on rte_eth_rss_conf->rss_hf. Currently supported default rss_type: ipv4[6], ipv4[6]_udp, ipv4[6]_tcp, ipv4[6]_sctp. Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-12-23 12:52:28 +00:00
if (!key || key_len == 0) {
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
PMD_DRV_LOG(DEBUG, "No key to be configured");
return 0;
net/iavf: improve default RSS Add support to actively configure the RSS through port config. Any kernel PF enabled default RSS will be disabled during initialization. Besides, default RSS will be configured based on rte_eth_rss_conf->rss_hf. Currently supported default rss_type: ipv4[6], ipv4[6]_udp, ipv4[6]_tcp, ipv4[6]_sctp. Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-12-23 12:52:28 +00:00
} else if (key_len != vf->vf_res->rss_key_size) {
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
PMD_DRV_LOG(ERR, "The size of hash key configured "
"(%d) doesn't match the size of hardware can "
net/iavf: improve default RSS Add support to actively configure the RSS through port config. Any kernel PF enabled default RSS will be disabled during initialization. Besides, default RSS will be configured based on rte_eth_rss_conf->rss_hf. Currently supported default rss_type: ipv4[6], ipv4[6]_udp, ipv4[6]_tcp, ipv4[6]_sctp. Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-12-23 12:52:28 +00:00
"support (%d)", key_len,
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
vf->vf_res->rss_key_size);
return -EINVAL;
}
net/iavf: improve default RSS Add support to actively configure the RSS through port config. Any kernel PF enabled default RSS will be disabled during initialization. Besides, default RSS will be configured based on rte_eth_rss_conf->rss_hf. Currently supported default rss_type: ipv4[6], ipv4[6]_udp, ipv4[6]_tcp, ipv4[6]_sctp. Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-12-23 12:52:28 +00:00
rte_memcpy(vf->rss_key, key, key_len);
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
return iavf_configure_rss_key(adapter);
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
}
net/iavf: improve default RSS Add support to actively configure the RSS through port config. Any kernel PF enabled default RSS will be disabled during initialization. Besides, default RSS will be configured based on rte_eth_rss_conf->rss_hf. Currently supported default rss_type: ipv4[6], ipv4[6]_udp, ipv4[6]_tcp, ipv4[6]_sctp. Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-12-23 12:52:28 +00:00
static int
iavf_dev_rss_hash_update(struct rte_eth_dev *dev,
struct rte_eth_rss_conf *rss_conf)
{
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
int ret;
net/iavf: fix multi-process shared data When the iavf_adapter instance is not initialized completely in the primary process, the secondary process accesses its "rte_eth_dev" member, it causes secondary process crash. This patch replaces eth_dev with eth_dev_data in iavf_adapter. Fixes: f978c1c9b3b5 ("net/iavf: add RSS hash parsing in AVX path") Fixes: 9c9aa0040344 ("net/iavf: add offload path for Rx AVX512 flex descriptor") Fixes: 63660ea3ee0b ("net/iavf: add RSS hash parsing in SSE path") Cc: stable@dpdk.org Signed-off-by: Dapeng Yu <dapengx.yu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-10-11 02:01:31 +00:00
adapter->dev_data->dev_conf.rx_adv_conf.rss_conf = *rss_conf;
net/iavf: improve default RSS Add support to actively configure the RSS through port config. Any kernel PF enabled default RSS will be disabled during initialization. Besides, default RSS will be configured based on rte_eth_rss_conf->rss_hf. Currently supported default rss_type: ipv4[6], ipv4[6]_udp, ipv4[6]_tcp, ipv4[6]_sctp. Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-12-23 12:52:28 +00:00
net/iavf: fix crash after VF reset failure Some pointers will be set to NULL when iavf_dev_reset() failed, for example vf->vf_res, vf->vsi_res vf->rss_key and etc. APIs access these NULL pointers will trigger segfault. This patch adds closed flag to indicate that the VF is closed, and rejects API calls in this state to avoid coredump. Fixes: e74e1bb6280d ("net/iavf: enable port reset") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-12 10:48:51 +00:00
if (adapter->closed)
return -EIO;
net/iavf: improve default RSS Add support to actively configure the RSS through port config. Any kernel PF enabled default RSS will be disabled during initialization. Besides, default RSS will be configured based on rte_eth_rss_conf->rss_hf. Currently supported default rss_type: ipv4[6], ipv4[6]_udp, ipv4[6]_tcp, ipv4[6]_sctp. Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-12-23 12:52:28 +00:00
if (!(vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF))
return -ENOTSUP;
/* Set hash key. */
ret = iavf_set_rss_key(adapter, rss_conf->rss_key,
rss_conf->rss_key_len);
if (ret)
return ret;
net/iavf: fix RSS hash update This patch change judgment statements to disable RSS for vf when users need to disable RSS or RSS hash function configured is not supported. Fixes: 95f2f0e9fc2a ("net/iavf: improve default RSS") Cc: stable@dpdk.org Signed-off-by: Wenjun Wu <wenjun1.wu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-03-15 00:59:53 +00:00
if (rss_conf->rss_hf == 0) {
vf->rss_hf = 0;
ret = iavf_set_hena(adapter, 0);
/* It is a workaround, temporarily allow error to be returned
* due to possible lack of PF handling for hena = 0.
*/
if (ret)
PMD_DRV_LOG(WARNING, "fail to clean existing RSS, lack PF support");
net/iavf: improve default RSS Add support to actively configure the RSS through port config. Any kernel PF enabled default RSS will be disabled during initialization. Besides, default RSS will be configured based on rte_eth_rss_conf->rss_hf. Currently supported default rss_type: ipv4[6], ipv4[6]_udp, ipv4[6]_tcp, ipv4[6]_sctp. Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-12-23 12:52:28 +00:00
return 0;
net/iavf: fix RSS hash update This patch change judgment statements to disable RSS for vf when users need to disable RSS or RSS hash function configured is not supported. Fixes: 95f2f0e9fc2a ("net/iavf: improve default RSS") Cc: stable@dpdk.org Signed-off-by: Wenjun Wu <wenjun1.wu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-03-15 00:59:53 +00:00
}
net/iavf: improve default RSS Add support to actively configure the RSS through port config. Any kernel PF enabled default RSS will be disabled during initialization. Besides, default RSS will be configured based on rte_eth_rss_conf->rss_hf. Currently supported default rss_type: ipv4[6], ipv4[6]_udp, ipv4[6]_tcp, ipv4[6]_sctp. Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-12-23 12:52:28 +00:00
net/iavf: fix default RSS configuration Add advanced RSS offloads check due to some legacy driver (kernel/DPDK PF) does not support virtual channel command VIRTCHNL_OP_RSS_HENA with hena = 0 and VIRTCHNL_OP_ADD_RSS_CFG. Fixes: 95f2f0e9fc2a ("net/iavf: improve default RSS") Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-31 10:47:24 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF) {
/* Clear existing RSS. */
ret = iavf_set_hena(adapter, 0);
net/iavf: workaround RSS cleanup failure handling Allow to ignore error returned from virtual channel command VIRTCHNL_OP_SET_RSS_HENA with hena = 0 due to some legacy kernel driver does not support this. Add warning message when this happen. Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-18 08:28:26 +00:00
net/iavf: fix default RSS configuration Add advanced RSS offloads check due to some legacy driver (kernel/DPDK PF) does not support virtual channel command VIRTCHNL_OP_RSS_HENA with hena = 0 and VIRTCHNL_OP_ADD_RSS_CFG. Fixes: 95f2f0e9fc2a ("net/iavf: improve default RSS") Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-31 10:47:24 +00:00
/* It is a workaround, temporarily allow error to be returned
* due to possible lack of PF handling for hena = 0.
*/
if (ret)
PMD_DRV_LOG(WARNING, "fail to clean existing RSS,"
"lack PF support");
net/iavf: improve default RSS Add support to actively configure the RSS through port config. Any kernel PF enabled default RSS will be disabled during initialization. Besides, default RSS will be configured based on rte_eth_rss_conf->rss_hf. Currently supported default rss_type: ipv4[6], ipv4[6]_udp, ipv4[6]_tcp, ipv4[6]_sctp. Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-12-23 12:52:28 +00:00
net/iavf: fix default RSS configuration Add advanced RSS offloads check due to some legacy driver (kernel/DPDK PF) does not support virtual channel command VIRTCHNL_OP_RSS_HENA with hena = 0 and VIRTCHNL_OP_ADD_RSS_CFG. Fixes: 95f2f0e9fc2a ("net/iavf: improve default RSS") Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-31 10:47:24 +00:00
/* Set new RSS configuration. */
ret = iavf_rss_hash_set(adapter, rss_conf->rss_hf, true);
if (ret) {
PMD_DRV_LOG(ERR, "fail to set new RSS");
return ret;
}
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
} else {
net/iavf: relax RSS virtual channel commands Kernel PF may not respond to virtual channel commands VIRTCHNL_OP_GET_RSS_HENA_CAPS and VIRTCHNL_OP_SET_RSS_HENA, which will cause VF to fail to start. RSS offload type configuration is not a necessary feature for VF, so in order to improve VF compatibility, in this patch the PMD will ignore the error result of above two commands and will print warnings instead. Fixes: 5a038d19962d ("net/iavf: fix RSS configuration on i40e VF") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-07-26 09:17:24 +00:00
iavf_config_rss_hf(adapter, rss_conf->rss_hf);
net/iavf: improve default RSS Add support to actively configure the RSS through port config. Any kernel PF enabled default RSS will be disabled during initialization. Besides, default RSS will be configured based on rte_eth_rss_conf->rss_hf. Currently supported default rss_type: ipv4[6], ipv4[6]_udp, ipv4[6]_tcp, ipv4[6]_sctp. Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-12-23 12:52:28 +00:00
}
return 0;
}
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_rss_hash_conf_get(struct rte_eth_dev *dev,
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
struct rte_eth_rss_conf *rss_conf)
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
net/iavf: fix crash after VF reset failure Some pointers will be set to NULL when iavf_dev_reset() failed, for example vf->vf_res, vf->vsi_res vf->rss_key and etc. APIs access these NULL pointers will trigger segfault. This patch adds closed flag to indicate that the VF is closed, and rejects API calls in this state to avoid coredump. Fixes: e74e1bb6280d ("net/iavf: enable port reset") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-12 10:48:51 +00:00
if (adapter->closed)
return -EIO;
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
if (!(vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF))
return -ENOTSUP;
net/iavf: improve default RSS Add support to actively configure the RSS through port config. Any kernel PF enabled default RSS will be disabled during initialization. Besides, default RSS will be configured based on rte_eth_rss_conf->rss_hf. Currently supported default rss_type: ipv4[6], ipv4[6]_udp, ipv4[6]_tcp, ipv4[6]_sctp. Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-12-23 12:52:28 +00:00
rss_conf->rss_hf = vf->rss_hf;
net/avf: enable ops for RSS setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:00 +00:00
if (!rss_conf->rss_key)
return 0;
rss_conf->rss_key_len = vf->vf_res->rss_key_size;
rte_memcpy(rss_conf->rss_key, vf->rss_key, rss_conf->rss_key_len);
return 0;
}
net/avf: enable ops for MTU setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:01 +00:00
static int
ethdev: move MTU set check to library Move requested MTU value check to the API to prevent the duplicated code. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Reviewed-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
2021-10-18 13:48:50 +00:00
iavf_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu __rte_unused)
net/avf: enable ops for MTU setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:01 +00:00
{
/* mtu setting is forbidden if port is start */
if (dev->data->dev_started) {
PMD_DRV_LOG(ERR, "port must be stopped before configuration");
return -EBUSY;
}
ethdev: move MTU set check to library Move requested MTU value check to the API to prevent the duplicated code. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Reviewed-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
2021-10-18 13:48:50 +00:00
return 0;
net/avf: enable ops for MTU setting Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:01 +00:00
}
ethdev: return diagnostic when setting MAC address Change the prototype and the behavior of dev_ops->eth_mac_addr_set(): a return code is added to notify the caller (librte_ether) if an error occurred in the PMD. The new default MAC address is now copied in dev->data->mac_addrs[0] only if the operation is successful. The patch also updates all the PMDs accordingly. Signed-off-by: Olivier Matz <olivier.matz@6wind.com> Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru> Acked-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com> Acked-by: Shreyansh Jain <shreyansh.jain@nxp.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
2018-04-11 16:32:51 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_set_default_mac_addr(struct rte_eth_dev *dev,
net: add rte prefix to ether structures Add 'rte_' prefix to structures: - rename struct ether_addr as struct rte_ether_addr. - rename struct ether_hdr as struct rte_ether_hdr. - rename struct vlan_hdr as struct rte_vlan_hdr. - rename struct vxlan_hdr as struct rte_vxlan_hdr. - rename struct vxlan_gpe_hdr as struct rte_vxlan_gpe_hdr. 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 16:13:03 +00:00
struct rte_ether_addr *mac_addr)
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_hw *hw = IAVF_DEV_PRIVATE_TO_HW(adapter);
net/iavf: fix lack of MAC type when set MAC address When set default MAC address, use type VIRTCHNL_ETHER_ADDR_PRIMARY as this case is changing device/primary unicast MAC. For other cases, such as adding or deleting extra unicast addresses and multicast addresses, use type VIRTCHNL_ETHER_ADDR_EXTRA. Fixes: cb25d4323fbf ("net/avf: enable MAC VLAN and promisc ops") Cc: stable@dpdk.org Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Tested-by: Yan Xia <yanx.xia@intel.com>
2021-03-19 09:20:19 +00:00
struct rte_ether_addr *old_addr;
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
int ret;
net: add rte prefix to ether structures Add 'rte_' prefix to structures: - rename struct ether_addr as struct rte_ether_addr. - rename struct ether_hdr as struct rte_ether_hdr. - rename struct vlan_hdr as struct rte_vlan_hdr. - rename struct vxlan_hdr as struct rte_vxlan_hdr. - rename struct vxlan_gpe_hdr as struct rte_vxlan_gpe_hdr. 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 16:13:03 +00:00
old_addr = (struct rte_ether_addr *)hw->mac.addr;
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
net/iavf: fix lack of MAC type when set MAC address When set default MAC address, use type VIRTCHNL_ETHER_ADDR_PRIMARY as this case is changing device/primary unicast MAC. For other cases, such as adding or deleting extra unicast addresses and multicast addresses, use type VIRTCHNL_ETHER_ADDR_EXTRA. Fixes: cb25d4323fbf ("net/avf: enable MAC VLAN and promisc ops") Cc: stable@dpdk.org Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Tested-by: Yan Xia <yanx.xia@intel.com>
2021-03-19 09:20:19 +00:00
if (rte_is_same_ether_addr(old_addr, mac_addr))
return 0;
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
net/iavf: fix lack of MAC type when set MAC address When set default MAC address, use type VIRTCHNL_ETHER_ADDR_PRIMARY as this case is changing device/primary unicast MAC. For other cases, such as adding or deleting extra unicast addresses and multicast addresses, use type VIRTCHNL_ETHER_ADDR_EXTRA. Fixes: cb25d4323fbf ("net/avf: enable MAC VLAN and promisc ops") Cc: stable@dpdk.org Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Tested-by: Yan Xia <yanx.xia@intel.com>
2021-03-19 09:20:19 +00:00
ret = iavf_add_del_eth_addr(adapter, old_addr, false, VIRTCHNL_ETHER_ADDR_PRIMARY);
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
if (ret)
PMD_DRV_LOG(ERR, "Fail to delete old MAC:"
net: add macro for MAC address print Added macro to print six bytes of MAC address. The MAC addresses will be printed in upper case hexadecimal format. In case there is a specific check for lower case MAC address, the user may need to make a change in such test case after this patch. Signed-off-by: Aman Deep Singh <aman.deep.singh@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2021-08-25 17:27:33 +00:00
RTE_ETHER_ADDR_PRT_FMT,
net: add macro to extract MAC address bytes Added macros to simplify print of MAC address. The six bytes of a MAC address are extracted in a macro here, to improve code readablity. Signed-off-by: Aman Deep Singh <aman.deep.singh@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2021-08-25 17:27:34 +00:00
RTE_ETHER_ADDR_BYTES(old_addr));
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
net/iavf: fix lack of MAC type when set MAC address When set default MAC address, use type VIRTCHNL_ETHER_ADDR_PRIMARY as this case is changing device/primary unicast MAC. For other cases, such as adding or deleting extra unicast addresses and multicast addresses, use type VIRTCHNL_ETHER_ADDR_EXTRA. Fixes: cb25d4323fbf ("net/avf: enable MAC VLAN and promisc ops") Cc: stable@dpdk.org Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Tested-by: Yan Xia <yanx.xia@intel.com>
2021-03-19 09:20:19 +00:00
ret = iavf_add_del_eth_addr(adapter, mac_addr, true, VIRTCHNL_ETHER_ADDR_PRIMARY);
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
if (ret)
PMD_DRV_LOG(ERR, "Fail to add new MAC:"
net: add macro for MAC address print Added macro to print six bytes of MAC address. The MAC addresses will be printed in upper case hexadecimal format. In case there is a specific check for lower case MAC address, the user may need to make a change in such test case after this patch. Signed-off-by: Aman Deep Singh <aman.deep.singh@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2021-08-25 17:27:33 +00:00
RTE_ETHER_ADDR_PRT_FMT,
net: add macro to extract MAC address bytes Added macros to simplify print of MAC address. The six bytes of a MAC address are extracted in a macro here, to improve code readablity. Signed-off-by: Aman Deep Singh <aman.deep.singh@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2021-08-25 17:27:34 +00:00
RTE_ETHER_ADDR_BYTES(mac_addr));
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
ethdev: return diagnostic when setting MAC address Change the prototype and the behavior of dev_ops->eth_mac_addr_set(): a return code is added to notify the caller (librte_ether) if an error occurred in the PMD. The new default MAC address is now copied in dev->data->mac_addrs[0] only if the operation is successful. The patch also updates all the PMDs accordingly. Signed-off-by: Olivier Matz <olivier.matz@6wind.com> Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru> Acked-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com> Acked-by: Shreyansh Jain <shreyansh.jain@nxp.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
2018-04-11 16:32:51 +00:00
if (ret)
return -EIO;
net: add rte prefix to ether functions Add 'rte_' prefix to functions: - rename is_same_ether_addr() as rte_is_same_ether_addr(). - rename is_zero_ether_addr() as rte_is_zero_ether_addr(). - rename is_unicast_ether_addr() as rte_is_unicast_ether_addr(). - rename is_multicast_ether_addr() as rte_is_multicast_ether_addr(). - rename is_broadcast_ether_addr() as rte_is_broadcast_ether_addr(). - rename is_universal_ether_addr() as rte_is_universal_ether_addr(). - rename is_local_admin_ether_addr() as rte_is_local_admin_ether_addr(). - rename is_valid_assigned_ether_addr() as rte_is_valid_assigned_ether_addr(). - rename eth_random_addr() as rte_eth_random_addr(). - rename ether_addr_copy() as rte_ether_addr_copy(). - rename ether_format_addr() as rte_ether_format_addr(). 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 16:13:04 +00:00
rte_ether_addr_copy(mac_addr, (struct rte_ether_addr *)hw->mac.addr);
ethdev: return diagnostic when setting MAC address Change the prototype and the behavior of dev_ops->eth_mac_addr_set(): a return code is added to notify the caller (librte_ether) if an error occurred in the PMD. The new default MAC address is now copied in dev->data->mac_addrs[0] only if the operation is successful. The patch also updates all the PMDs accordingly. Signed-off-by: Olivier Matz <olivier.matz@6wind.com> Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru> Acked-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com> Acked-by: Shreyansh Jain <shreyansh.jain@nxp.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
2018-04-11 16:32:51 +00:00
return 0;
net/avf: enable MAC VLAN and promisc ops - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:59 +00:00
}
net/iavf: fix stats reset stats_reset has been missed when support stats in iavf driver. This patch add statistics reset function. Fixes: f4a41a6953af ("net/avf: support stats") Cc: stable@dpdk.org Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2019-04-22 02:18:37 +00:00
static void
iavf_stat_update_48(uint64_t *offset, uint64_t *stat)
{
if (*stat >= *offset)
*stat = *stat - *offset;
else
*stat = (uint64_t)((*stat +
((uint64_t)1 << IAVF_48_BIT_WIDTH)) - *offset);
*stat &= IAVF_48_BIT_MASK;
}
static void
iavf_stat_update_32(uint64_t *offset, uint64_t *stat)
{
if (*stat >= *offset)
*stat = (uint64_t)(*stat - *offset);
else
*stat = (uint64_t)((*stat +
((uint64_t)1 << IAVF_32_BIT_WIDTH)) - *offset);
}
static void
iavf_update_stats(struct iavf_vsi *vsi, struct virtchnl_eth_stats *nes)
{
net/iavf: support xstats for inline IPsec crypto Add per queue counters for maintaining statistics for inline IPsec crypto offload, which can be retrieved through the rte_security_session_stats_get() with more detailed errors through the rte_ethdev xstats. Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:58 +00:00
struct virtchnl_eth_stats *oes = &vsi->eth_stats_offset.eth_stats;
net/iavf: fix stats reset stats_reset has been missed when support stats in iavf driver. This patch add statistics reset function. Fixes: f4a41a6953af ("net/avf: support stats") Cc: stable@dpdk.org Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2019-04-22 02:18:37 +00:00
iavf_stat_update_48(&oes->rx_bytes, &nes->rx_bytes);
iavf_stat_update_48(&oes->rx_unicast, &nes->rx_unicast);
iavf_stat_update_48(&oes->rx_multicast, &nes->rx_multicast);
iavf_stat_update_48(&oes->rx_broadcast, &nes->rx_broadcast);
iavf_stat_update_32(&oes->rx_discards, &nes->rx_discards);
iavf_stat_update_48(&oes->tx_bytes, &nes->tx_bytes);
iavf_stat_update_48(&oes->tx_unicast, &nes->tx_unicast);
iavf_stat_update_48(&oes->tx_multicast, &nes->tx_multicast);
iavf_stat_update_48(&oes->tx_broadcast, &nes->tx_broadcast);
iavf_stat_update_32(&oes->tx_errors, &nes->tx_errors);
iavf_stat_update_32(&oes->tx_discards, &nes->tx_discards);
}
net/avf: support stats Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:58 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats)
net/avf: support stats Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:58 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
net/iavf: fix stats reset stats_reset has been missed when support stats in iavf driver. This patch add statistics reset function. Fixes: f4a41a6953af ("net/avf: support stats") Cc: stable@dpdk.org Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2019-04-22 02:18:37 +00:00
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
struct iavf_vsi *vsi = &vf->vsi;
net/avf: support stats Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:58 +00:00
struct virtchnl_eth_stats *pstats = NULL;
int ret;
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
ret = iavf_query_stats(adapter, &pstats);
net/avf: support stats Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:58 +00:00
if (ret == 0) {
net/iavf: adjust CRC statistics calculation The AVF can support to enable / disable CRC strip, so it needs to adjust the statistics calculation for ibytes according to offload setting. Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-15 06:57:08 +00:00
uint8_t crc_stats_len = (dev->data->dev_conf.rxmode.offloads &
ethdev: add namespace Add 'RTE_ETH' namespace to all enums & macros in a backward compatible way. The macros for backward compatibility can be removed in next LTS. Also updated some struct names to have 'rte_eth' prefix. All internal components switched to using new names. Syntax fixed on lines that this patch touches. Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Wisam Jaddo <wisamm@nvidia.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Chenbo Xia <chenbo.xia@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
2021-10-22 11:03:12 +00:00
RTE_ETH_RX_OFFLOAD_KEEP_CRC) ? 0 :
net/iavf: adjust CRC statistics calculation The AVF can support to enable / disable CRC strip, so it needs to adjust the statistics calculation for ibytes according to offload setting. Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-15 06:57:08 +00:00
RTE_ETHER_CRC_LEN;
net/iavf: fix stats reset stats_reset has been missed when support stats in iavf driver. This patch add statistics reset function. Fixes: f4a41a6953af ("net/avf: support stats") Cc: stable@dpdk.org Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2019-04-22 02:18:37 +00:00
iavf_update_stats(vsi, pstats);
net/avf: support stats Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:58 +00:00
stats->ipackets = pstats->rx_unicast + pstats->rx_multicast +
net/iavf: fix Rx total stats Rx total stats is the total number of successfully received packets, so exclude the number of rx_discards for Rx total stats. Fixes: f4a41a6953af ("net/avf: support stats") Cc: stable@dpdk.org Signed-off-by: Jiaqi Min <jiaqix.min@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2019-12-13 01:23:29 +00:00
pstats->rx_broadcast - pstats->rx_discards;
net/avf: support stats Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:58 +00:00
stats->opackets = pstats->tx_broadcast + pstats->tx_multicast +
pstats->tx_unicast;
stats->imissed = pstats->rx_discards;
stats->oerrors = pstats->tx_errors + pstats->tx_discards;
stats->ibytes = pstats->rx_bytes;
net/iavf: adjust CRC statistics calculation The AVF can support to enable / disable CRC strip, so it needs to adjust the statistics calculation for ibytes according to offload setting. Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-15 06:57:08 +00:00
stats->ibytes -= stats->ipackets * crc_stats_len;
net/avf: support stats Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:58 +00:00
stats->obytes = pstats->tx_bytes;
} else {
PMD_DRV_LOG(ERR, "Get statistics failed");
}
net/iavf: fix stats query error code The iavf_dev_stats_get function should return ret instead of -eio. Fixes: f4a41a6953af ("net/avf: support stats") Cc: stable@dpdk.org Signed-off-by: Cheng Peng <cheng.peng5@zte.com.cn> Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
2020-04-14 01:56:57 +00:00
return ret;
net/avf: support stats Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:58 +00:00
}
ethdev: make stats and xstats reset callbacks return int Change return value of the callbacks from void to int. Make implementations across all drivers return negative errno values in case of error conditions. Both callbacks are updated together because a large number of drivers assign the same function to both callbacks. Signed-off-by: Igor Romanov <igor.romanov@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-09-06 14:34:54 +00:00
static int
net/iavf: fix stats reset stats_reset has been missed when support stats in iavf driver. This patch add statistics reset function. Fixes: f4a41a6953af ("net/avf: support stats") Cc: stable@dpdk.org Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2019-04-22 02:18:37 +00:00
iavf_dev_stats_reset(struct rte_eth_dev *dev)
{
int ret;
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
struct iavf_vsi *vsi = &vf->vsi;
struct virtchnl_eth_stats *pstats = NULL;
/* read stat values to clear hardware registers */
ret = iavf_query_stats(adapter, &pstats);
ethdev: make stats and xstats reset callbacks return int Change return value of the callbacks from void to int. Make implementations across all drivers return negative errno values in case of error conditions. Both callbacks are updated together because a large number of drivers assign the same function to both callbacks. Signed-off-by: Igor Romanov <igor.romanov@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-09-06 14:34:54 +00:00
if (ret != 0)
return ret;
net/iavf: fix stats reset stats_reset has been missed when support stats in iavf driver. This patch add statistics reset function. Fixes: f4a41a6953af ("net/avf: support stats") Cc: stable@dpdk.org Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2019-04-22 02:18:37 +00:00
/* set stats offset base on current values */
net/iavf: support xstats for inline IPsec crypto Add per queue counters for maintaining statistics for inline IPsec crypto offload, which can be retrieved through the rte_security_session_stats_get() with more detailed errors through the rte_ethdev xstats. Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:58 +00:00
vsi->eth_stats_offset.eth_stats = *pstats;
return 0;
}
static int
iavf_dev_xstats_reset(struct rte_eth_dev *dev)
{
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
iavf_dev_stats_reset(dev);
net/iavf: fix xstats reset Wrong offset used to clear the extended stats section resulting in eth stats not being reset. Fixes: ccb49b834cd7 ("net/iavf: support xstats for inline IPsec crypto") Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-11-09 10:33:03 +00:00
memset(&vf->vsi.eth_stats_offset.ips_stats, 0,
sizeof(struct iavf_ipsec_crypto_stats));
ethdev: make stats and xstats reset callbacks return int Change return value of the callbacks from void to int. Make implementations across all drivers return negative errno values in case of error conditions. Both callbacks are updated together because a large number of drivers assign the same function to both callbacks. Signed-off-by: Igor Romanov <igor.romanov@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-09-06 14:34:54 +00:00
return 0;
net/iavf: fix stats reset stats_reset has been missed when support stats in iavf driver. This patch add statistics reset function. Fixes: f4a41a6953af ("net/avf: support stats") Cc: stable@dpdk.org Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2019-04-22 02:18:37 +00:00
}
net/iavf: add extended stats Add implementation of xstats() functions in iavf PMD. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:25 +00:00
static int iavf_dev_xstats_get_names(__rte_unused struct rte_eth_dev *dev,
struct rte_eth_xstat_name *xstats_names,
__rte_unused unsigned int limit)
{
unsigned int i;
if (xstats_names != NULL)
for (i = 0; i < IAVF_NB_XSTATS; i++) {
snprintf(xstats_names[i].name,
sizeof(xstats_names[i].name),
"%s", rte_iavf_stats_strings[i].name);
}
return IAVF_NB_XSTATS;
}
net/iavf: support xstats for inline IPsec crypto Add per queue counters for maintaining statistics for inline IPsec crypto offload, which can be retrieved through the rte_security_session_stats_get() with more detailed errors through the rte_ethdev xstats. Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:58 +00:00
static void
iavf_dev_update_ipsec_xstats(struct rte_eth_dev *ethdev,
struct iavf_ipsec_crypto_stats *ips)
{
uint16_t idx;
for (idx = 0; idx < ethdev->data->nb_rx_queues; idx++) {
struct iavf_rx_queue *rxq;
struct iavf_ipsec_crypto_stats *stats;
rxq = (struct iavf_rx_queue *)ethdev->data->rx_queues[idx];
stats = &rxq->stats.ipsec_crypto;
ips->icount += stats->icount;
ips->ibytes += stats->ibytes;
ips->ierrors.count += stats->ierrors.count;
ips->ierrors.sad_miss += stats->ierrors.sad_miss;
ips->ierrors.not_processed += stats->ierrors.not_processed;
ips->ierrors.icv_check += stats->ierrors.icv_check;
ips->ierrors.ipsec_length += stats->ierrors.ipsec_length;
ips->ierrors.misc += stats->ierrors.misc;
}
}
net/iavf: add extended stats Add implementation of xstats() functions in iavf PMD. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:25 +00:00
static int iavf_dev_xstats_get(struct rte_eth_dev *dev,
struct rte_eth_xstat *xstats, unsigned int n)
{
int ret;
unsigned int i;
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
struct iavf_vsi *vsi = &vf->vsi;
struct virtchnl_eth_stats *pstats = NULL;
net/iavf: support xstats for inline IPsec crypto Add per queue counters for maintaining statistics for inline IPsec crypto offload, which can be retrieved through the rte_security_session_stats_get() with more detailed errors through the rte_ethdev xstats. Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:58 +00:00
struct iavf_eth_xstats iavf_xtats = {{0}};
net/iavf: add extended stats Add implementation of xstats() functions in iavf PMD. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:25 +00:00
if (n < IAVF_NB_XSTATS)
return IAVF_NB_XSTATS;
ret = iavf_query_stats(adapter, &pstats);
if (ret != 0)
return 0;
if (!xstats)
return 0;
iavf_update_stats(vsi, pstats);
net/iavf: support xstats for inline IPsec crypto Add per queue counters for maintaining statistics for inline IPsec crypto offload, which can be retrieved through the rte_security_session_stats_get() with more detailed errors through the rte_ethdev xstats. Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:58 +00:00
iavf_xtats.eth_stats = *pstats;
if (iavf_ipsec_crypto_supported(adapter))
iavf_dev_update_ipsec_xstats(dev, &iavf_xtats.ips_stats);
net/iavf: add extended stats Add implementation of xstats() functions in iavf PMD. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:25 +00:00
/* loop over xstats array and values from pstats */
for (i = 0; i < IAVF_NB_XSTATS; i++) {
xstats[i].id = i;
net/iavf: support xstats for inline IPsec crypto Add per queue counters for maintaining statistics for inline IPsec crypto offload, which can be retrieved through the rte_security_session_stats_get() with more detailed errors through the rte_ethdev xstats. Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:58 +00:00
xstats[i].value = *(uint64_t *)(((char *)&iavf_xtats) +
net/iavf: add extended stats Add implementation of xstats() functions in iavf PMD. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:25 +00:00
rte_iavf_stats_strings[i].offset);
}
return IAVF_NB_XSTATS;
}
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_rx_queue_intr_enable(struct rte_eth_dev *dev, uint16_t queue_id)
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
struct rte_pci_device *pci_dev = RTE_ETH_DEV_TO_PCI(dev);
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_hw *hw = IAVF_DEV_PRIVATE_TO_HW(adapter);
net/iavf: enable interrupt polling For VF hosted by Intel 700 series NICs, internal Rx interrupt and adminq interrupt share the same source, that cause a lot CPU cycles be wasted on interrupt handler on Rx path. The patch disable PCI interrupt and remove the interrupt handler, replace it with a low frequency(50ms) interrupt polling daemon which is implemented by registering an alarm callback periodically. The virtual channel capability bit VIRTCHNL_VF_OFFLOAD_WB_ON_ITR can be used to negotiate if iavf PMD needs to enable background alarm or not, so ideally this change will not impact the case hosted by Intel 800 series NICS. This patch implements the same logic with an early i40e commit: commit 864a800d706d ("net/i40e: remove VF interrupt handler") Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Pallavi Kadam <pallavi.kadam@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-08-25 08:34:35 +00:00
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
uint16_t msix_intr;
net/iavf: fix crash after VF reset failure Some pointers will be set to NULL when iavf_dev_reset() failed, for example vf->vf_res, vf->vsi_res vf->rss_key and etc. APIs access these NULL pointers will trigger segfault. This patch adds closed flag to indicate that the VF is closed, and rejects API calls in this state to avoid coredump. Fixes: e74e1bb6280d ("net/iavf: enable port reset") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-12 10:48:51 +00:00
if (adapter->closed)
return -EIO;
drivers: remove direct access to interrupt handle Removing direct access to interrupt handle structure fields, rather use respective get set APIs for the same. Making changes to all the drivers access the interrupt handle fields. Signed-off-by: Harman Kalra <hkalra@marvell.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com> Signed-off-by: David Marchand <david.marchand@redhat.com> Tested-by: Raslan Darawsheh <rasland@nvidia.com>
2021-10-22 20:49:32 +00:00
msix_intr = rte_intr_vec_list_index_get(pci_dev->intr_handle,
queue_id);
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
if (msix_intr == IAVF_MISC_VEC_ID) {
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
PMD_DRV_LOG(INFO, "MISC is also enabled for control");
net/iavf/base: rename register macro Rename all register macro to align with kernel driver's implementation. Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com> Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
2019-12-03 07:03:04 +00:00
IAVF_WRITE_REG(hw, IAVF_VFINT_DYN_CTL01,
IAVF_VFINT_DYN_CTL01_INTENA_MASK |
IAVF_VFINT_DYN_CTL01_CLEARPBA_MASK |
IAVF_VFINT_DYN_CTL01_ITR_INDX_MASK);
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
} else {
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
IAVF_WRITE_REG(hw,
net/iavf/base: rename register macro Rename all register macro to align with kernel driver's implementation. Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com> Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
2019-12-03 07:03:04 +00:00
IAVF_VFINT_DYN_CTLN1
(msix_intr - IAVF_RX_VEC_START),
IAVF_VFINT_DYN_CTLN1_INTENA_MASK |
IAVF_VFINT_DYN_CTL01_CLEARPBA_MASK |
IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK);
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
}
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
IAVF_WRITE_FLUSH(hw);
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
net/iavf: enable interrupt polling For VF hosted by Intel 700 series NICs, internal Rx interrupt and adminq interrupt share the same source, that cause a lot CPU cycles be wasted on interrupt handler on Rx path. The patch disable PCI interrupt and remove the interrupt handler, replace it with a low frequency(50ms) interrupt polling daemon which is implemented by registering an alarm callback periodically. The virtual channel capability bit VIRTCHNL_VF_OFFLOAD_WB_ON_ITR can be used to negotiate if iavf PMD needs to enable background alarm or not, so ideally this change will not impact the case hosted by Intel 800 series NICS. This patch implements the same logic with an early i40e commit: commit 864a800d706d ("net/i40e: remove VF interrupt handler") Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Pallavi Kadam <pallavi.kadam@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-08-25 08:34:35 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_WB_ON_ITR)
drivers: remove direct access to interrupt handle Removing direct access to interrupt handle structure fields, rather use respective get set APIs for the same. Making changes to all the drivers access the interrupt handle fields. Signed-off-by: Harman Kalra <hkalra@marvell.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com> Signed-off-by: David Marchand <david.marchand@redhat.com> Tested-by: Raslan Darawsheh <rasland@nvidia.com>
2021-10-22 20:49:32 +00:00
rte_intr_ack(pci_dev->intr_handle);
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
return 0;
}
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_rx_queue_intr_disable(struct rte_eth_dev *dev, uint16_t queue_id)
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
{
struct rte_pci_device *pci_dev = RTE_ETH_DEV_TO_PCI(dev);
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_hw *hw = IAVF_DEV_PRIVATE_TO_HW(dev->data->dev_private);
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
uint16_t msix_intr;
drivers: remove direct access to interrupt handle Removing direct access to interrupt handle structure fields, rather use respective get set APIs for the same. Making changes to all the drivers access the interrupt handle fields. Signed-off-by: Harman Kalra <hkalra@marvell.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com> Signed-off-by: David Marchand <david.marchand@redhat.com> Tested-by: Raslan Darawsheh <rasland@nvidia.com>
2021-10-22 20:49:32 +00:00
msix_intr = rte_intr_vec_list_index_get(pci_dev->intr_handle,
queue_id);
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
if (msix_intr == IAVF_MISC_VEC_ID) {
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
PMD_DRV_LOG(ERR, "MISC is used for control, cannot disable it");
return -EIO;
}
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
IAVF_WRITE_REG(hw,
net/iavf/base: rename register macro Rename all register macro to align with kernel driver's implementation. Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com> Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
2019-12-03 07:03:04 +00:00
IAVF_VFINT_DYN_CTLN1(msix_intr - IAVF_RX_VEC_START),
net/iavf: fix Rx queue interrupt setting For Rx-Queue Interrupt Setting, when VF Rx interrupt disable (INTENA=0), there are two ways to write back descriptor to host memory: 1) Set WB_ON_ITR bit 0 to Interrupt Dynamic Control Register: Completed descriptors are posted to host memory according to the internal descriptor cache policy (in other words when a full cache line is available for write-back). A internal descriptor size is 16 bytes or 32 bytes, a cache line size is 64 bytes or 128 bytes from datasheet : PCIe Global Config 2 - GLPCI_CNF2 (0x000BE004; RO) so the full cache line could contains 4 packets, it means Network card will send 4 packets to host when a full cache line is available. 2) Set WB_ON_ITR bit 1 to Interrupt Dynamic Control Register: Completed descriptors also trigger the ITR. Following ITR expiration, all leftover completed descriptors are posted to host memory. Network card will send packet to host even if only one descriptor is completed. Changing 1) to 2) to make sure VF send the packet to host even if there is only one Rx packet is ready in hardware. Fixes: d6bde6b5eae9 ("net/avf: enable Rx interrupt") Cc: stable@dpdk.org Signed-off-by: Ke Zhang <ke1x.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-20 03:00:23 +00:00
IAVF_VFINT_DYN_CTLN1_WB_ON_ITR_MASK);
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
IAVF_WRITE_FLUSH(hw);
net/avf: enable Rx interrupt Update the doc for the AVF features either. Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:02:06 +00:00
return 0;
}
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_check_vf_reset_done(struct iavf_hw *hw)
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
{
int i, reset;
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
for (i = 0; i < IAVF_RESET_WAIT_CNT; i++) {
net/iavf/base: rename register macro Rename all register macro to align with kernel driver's implementation. Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com> Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
2019-12-03 07:03:04 +00:00
reset = IAVF_READ_REG(hw, IAVF_VFGEN_RSTAT) &
IAVF_VFGEN_RSTAT_VFR_STATE_MASK;
reset = reset >> IAVF_VFGEN_RSTAT_VFR_STATE_SHIFT;
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
if (reset == VIRTCHNL_VFR_VFACTIVE ||
reset == VIRTCHNL_VFR_COMPLETED)
break;
rte_delay_ms(20);
}
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
if (i >= IAVF_RESET_WAIT_CNT)
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
return -1;
return 0;
}
net/iavf: support flex desc metadata extraction Enable metadata extraction for flexible descriptors in AVF, that would allow network function directly get metadata without additional parsing which would reduce the CPU cost for VFs. The enabling metadata extractions involve the metadata of VLAN/IPv4/IPv6/IPv6-FLOW/TCP/MPLS flexible descriptors, and the VF could negotiate the capability of the flexible descriptor with PF and correspondingly configure the specific offload at receiving queues. Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Haiyue Wang <haiyue.wang@intel.com>
2020-10-30 08:40:30 +00:00
static int
iavf_lookup_proto_xtr_type(const char *flex_name)
{
static struct {
const char *name;
enum iavf_proto_xtr_type type;
} xtr_type_map[] = {
{ "vlan", IAVF_PROTO_XTR_VLAN },
{ "ipv4", IAVF_PROTO_XTR_IPV4 },
{ "ipv6", IAVF_PROTO_XTR_IPV6 },
{ "ipv6_flow", IAVF_PROTO_XTR_IPV6_FLOW },
{ "tcp", IAVF_PROTO_XTR_TCP },
{ "ip_offset", IAVF_PROTO_XTR_IP_OFFSET },
net/iavf: support IPsec inline crypto Add support for inline crypto for IPsec, for ESP transport and tunnel over IPv4 and IPv6, as well as supporting the offload for ESP over UDP, and in conjunction with TSO for UDP and TCP flows. Implement support for rte_security packet metadata Add definition for IPsec descriptors, extend support for offload in data and context descriptor to support Add support to virtual channel mailbox for IPsec Crypto request operations. IPsec Crypto requests receive an initial acknowledgment from physical function driver of receipt of request and then an asynchronous response with success/failure of request including any response data. Add enhanced descriptor debugging Refactor of scalar tx burst function to support integration of offload Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Abhijit Sinha <abhijit.sinha@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Reviewed-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:57 +00:00
{ "ipsec_crypto_said", IAVF_PROTO_XTR_IPSEC_CRYPTO_SAID },
net/iavf: support flex desc metadata extraction Enable metadata extraction for flexible descriptors in AVF, that would allow network function directly get metadata without additional parsing which would reduce the CPU cost for VFs. The enabling metadata extractions involve the metadata of VLAN/IPv4/IPv6/IPv6-FLOW/TCP/MPLS flexible descriptors, and the VF could negotiate the capability of the flexible descriptor with PF and correspondingly configure the specific offload at receiving queues. Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Haiyue Wang <haiyue.wang@intel.com>
2020-10-30 08:40:30 +00:00
};
uint32_t i;
for (i = 0; i < RTE_DIM(xtr_type_map); i++) {
if (strcmp(flex_name, xtr_type_map[i].name) == 0)
return xtr_type_map[i].type;
}
net/iavf: support IPsec inline crypto Add support for inline crypto for IPsec, for ESP transport and tunnel over IPv4 and IPv6, as well as supporting the offload for ESP over UDP, and in conjunction with TSO for UDP and TCP flows. Implement support for rte_security packet metadata Add definition for IPsec descriptors, extend support for offload in data and context descriptor to support Add support to virtual channel mailbox for IPsec Crypto request operations. IPsec Crypto requests receive an initial acknowledgment from physical function driver of receipt of request and then an asynchronous response with success/failure of request including any response data. Add enhanced descriptor debugging Refactor of scalar tx burst function to support integration of offload Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Abhijit Sinha <abhijit.sinha@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Reviewed-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:57 +00:00
PMD_DRV_LOG(ERR, "wrong proto_xtr type, it should be: "
"vlan|ipv4|ipv6|ipv6_flow|tcp|ip_offset|ipsec_crypto_said");
net/iavf: support flex desc metadata extraction Enable metadata extraction for flexible descriptors in AVF, that would allow network function directly get metadata without additional parsing which would reduce the CPU cost for VFs. The enabling metadata extractions involve the metadata of VLAN/IPv4/IPv6/IPv6-FLOW/TCP/MPLS flexible descriptors, and the VF could negotiate the capability of the flexible descriptor with PF and correspondingly configure the specific offload at receiving queues. Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Haiyue Wang <haiyue.wang@intel.com>
2020-10-30 08:40:30 +00:00
return -1;
}
/**
* Parse elem, the elem could be single number/range or '(' ')' group
* 1) A single number elem, it's just a simple digit. e.g. 9
* 2) A single range elem, two digits with a '-' between. e.g. 2-6
* 3) A group elem, combines multiple 1) or 2) with '( )'. e.g (0,2-4,6)
* Within group elem, '-' used for a range separator;
* ',' used for a single number.
*/
static int
iavf_parse_queue_set(const char *input, int xtr_type,
struct iavf_devargs *devargs)
{
const char *str = input;
char *end = NULL;
uint32_t min, max;
uint32_t idx;
while (isblank(*str))
str++;
if (!isdigit(*str) && *str != '(')
return -1;
/* process single number or single range of number */
if (*str != '(') {
errno = 0;
idx = strtoul(str, &end, 10);
if (errno || !end || idx >= IAVF_MAX_QUEUE_NUM)
return -1;
while (isblank(*end))
end++;
min = idx;
max = idx;
/* process single <number>-<number> */
if (*end == '-') {
end++;
while (isblank(*end))
end++;
if (!isdigit(*end))
return -1;
errno = 0;
idx = strtoul(end, &end, 10);
if (errno || !end || idx >= IAVF_MAX_QUEUE_NUM)
return -1;
max = idx;
while (isblank(*end))
end++;
}
if (*end != ':')
return -1;
for (idx = RTE_MIN(min, max);
idx <= RTE_MAX(min, max); idx++)
devargs->proto_xtr[idx] = xtr_type;
return 0;
}
/* process set within bracket */
str++;
while (isblank(*str))
str++;
if (*str == '\0')
return -1;
min = IAVF_MAX_QUEUE_NUM;
do {
/* go ahead to the first digit */
while (isblank(*str))
str++;
if (!isdigit(*str))
return -1;
/* get the digit value */
errno = 0;
idx = strtoul(str, &end, 10);
if (errno || !end || idx >= IAVF_MAX_QUEUE_NUM)
return -1;
/* go ahead to separator '-',',' and ')' */
while (isblank(*end))
end++;
if (*end == '-') {
if (min == IAVF_MAX_QUEUE_NUM)
min = idx;
else /* avoid continuous '-' */
return -1;
} else if (*end == ',' || *end == ')') {
max = idx;
if (min == IAVF_MAX_QUEUE_NUM)
min = idx;
for (idx = RTE_MIN(min, max);
idx <= RTE_MAX(min, max); idx++)
devargs->proto_xtr[idx] = xtr_type;
min = IAVF_MAX_QUEUE_NUM;
} else {
return -1;
}
str = end + 1;
} while (*end != ')' && *end != '\0');
return 0;
}
static int
iavf_parse_queue_proto_xtr(const char *queues, struct iavf_devargs *devargs)
{
const char *queue_start;
uint32_t idx;
int xtr_type;
char flex_name[32];
while (isblank(*queues))
queues++;
if (*queues != '[') {
xtr_type = iavf_lookup_proto_xtr_type(queues);
if (xtr_type < 0)
return -1;
devargs->proto_xtr_dflt = xtr_type;
return 0;
}
queues++;
do {
while (isblank(*queues))
queues++;
if (*queues == '\0')
return -1;
queue_start = queues;
/* go across a complete bracket */
if (*queue_start == '(') {
queues += strcspn(queues, ")");
if (*queues != ')')
return -1;
}
/* scan the separator ':' */
queues += strcspn(queues, ":");
if (*queues++ != ':')
return -1;
while (isblank(*queues))
queues++;
for (idx = 0; ; idx++) {
if (isblank(queues[idx]) ||
queues[idx] == ',' ||
queues[idx] == ']' ||
queues[idx] == '\0')
break;
if (idx > sizeof(flex_name) - 2)
return -1;
flex_name[idx] = queues[idx];
}
flex_name[idx] = '\0';
xtr_type = iavf_lookup_proto_xtr_type(flex_name);
if (xtr_type < 0)
return -1;
queues += idx;
while (isblank(*queues) || *queues == ',' || *queues == ']')
queues++;
if (iavf_parse_queue_set(queue_start, xtr_type, devargs) < 0)
return -1;
} while (*queues != '\0');
return 0;
}
static int
iavf_handle_proto_xtr_arg(__rte_unused const char *key, const char *value,
void *extra_args)
{
struct iavf_devargs *devargs = extra_args;
if (!value || !extra_args)
return -EINVAL;
if (iavf_parse_queue_proto_xtr(value, devargs) < 0) {
PMD_DRV_LOG(ERR, "the proto_xtr's parameter is wrong : '%s'",
value);
return -1;
}
return 0;
}
net/iavf: support quanta size configuration This patch adds quanta size configuration support. Quanta size should between 256 and 4096, and be a product of 64. Signed-off-by: Wenjun Wu <wenjun1.wu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-04-22 01:43:00 +00:00
static int
parse_u16(__rte_unused const char *key, const char *value, void *args)
{
u16 *num = (u16 *)args;
u16 tmp;
errno = 0;
tmp = strtoull(value, NULL, 10);
if (errno || !tmp) {
PMD_DRV_LOG(WARNING, "%s: \"%s\" is not a valid u16",
key, value);
return -1;
}
*num = tmp;
return 0;
}
net/iavf: support flex desc metadata extraction Enable metadata extraction for flexible descriptors in AVF, that would allow network function directly get metadata without additional parsing which would reduce the CPU cost for VFs. The enabling metadata extractions involve the metadata of VLAN/IPv4/IPv6/IPv6-FLOW/TCP/MPLS flexible descriptors, and the VF could negotiate the capability of the flexible descriptor with PF and correspondingly configure the specific offload at receiving queues. Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Haiyue Wang <haiyue.wang@intel.com>
2020-10-30 08:40:30 +00:00
static int iavf_parse_devargs(struct rte_eth_dev *dev)
{
struct iavf_adapter *ad =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct rte_devargs *devargs = dev->device->devargs;
struct rte_kvargs *kvlist;
int ret;
if (!devargs)
return 0;
kvlist = rte_kvargs_parse(devargs->args, iavf_valid_args);
if (!kvlist) {
PMD_INIT_LOG(ERR, "invalid kvargs key\n");
return -EINVAL;
}
ad->devargs.proto_xtr_dflt = IAVF_PROTO_XTR_NONE;
memset(ad->devargs.proto_xtr, IAVF_PROTO_XTR_NONE,
sizeof(ad->devargs.proto_xtr));
ret = rte_kvargs_process(kvlist, IAVF_PROTO_XTR_ARG,
&iavf_handle_proto_xtr_arg, &ad->devargs);
if (ret)
goto bail;
net/iavf: support quanta size configuration This patch adds quanta size configuration support. Quanta size should between 256 and 4096, and be a product of 64. Signed-off-by: Wenjun Wu <wenjun1.wu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-04-22 01:43:00 +00:00
ret = rte_kvargs_process(kvlist, IAVF_QUANTA_SIZE_ARG,
&parse_u16, &ad->devargs.quanta_size);
if (ret)
goto bail;
net/iavf: fix initialization with quanta configuration When kernel driver does not support quanta size configuration, it will return error. We do not expect it to occur in default initialization process. Fixes: b14e8a57b9fe ("net/iavf: support quanta size configuration") Signed-off-by: Wenjun Wu <wenjun1.wu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-27 05:38:51 +00:00
if (ad->devargs.quanta_size != 0 &&
(ad->devargs.quanta_size < 256 || ad->devargs.quanta_size > 4096 ||
ad->devargs.quanta_size & 0x40)) {
net/iavf: support quanta size configuration This patch adds quanta size configuration support. Quanta size should between 256 and 4096, and be a product of 64. Signed-off-by: Wenjun Wu <wenjun1.wu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-04-22 01:43:00 +00:00
PMD_INIT_LOG(ERR, "invalid quanta size\n");
net/iavf: fix memory leak Set an invalid quanta size from devargs will cause memory leak and this is reported by coverity. The patch fix the issue by correcting the error handle. Coverity issue: 378017 Fixes: b14e8a57b9fe ("net/iavf: support quanta size configuration") Signed-off-by: Wenjun Wu <wenjun1.wu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-10 00:54:25 +00:00
ret = -EINVAL;
goto bail;
net/iavf: support quanta size configuration This patch adds quanta size configuration support. Quanta size should between 256 and 4096, and be a product of 64. Signed-off-by: Wenjun Wu <wenjun1.wu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-04-22 01:43:00 +00:00
}
net/iavf: support flex desc metadata extraction Enable metadata extraction for flexible descriptors in AVF, that would allow network function directly get metadata without additional parsing which would reduce the CPU cost for VFs. The enabling metadata extractions involve the metadata of VLAN/IPv4/IPv6/IPv6-FLOW/TCP/MPLS flexible descriptors, and the VF could negotiate the capability of the flexible descriptor with PF and correspondingly configure the specific offload at receiving queues. Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Haiyue Wang <haiyue.wang@intel.com>
2020-10-30 08:40:30 +00:00
bail:
rte_kvargs_free(kvlist);
return ret;
}
static void
iavf_init_proto_xtr(struct rte_eth_dev *dev)
{
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
struct iavf_adapter *ad =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
const struct iavf_proto_xtr_ol *xtr_ol;
bool proto_xtr_enable = false;
int offset;
uint16_t i;
vf->proto_xtr = rte_zmalloc("vf proto xtr",
vf->vsi_res->num_queue_pairs, 0);
if (unlikely(!(vf->proto_xtr))) {
PMD_DRV_LOG(ERR, "no memory for setting up proto_xtr's table");
return;
}
for (i = 0; i < vf->vsi_res->num_queue_pairs; i++) {
vf->proto_xtr[i] = ad->devargs.proto_xtr[i] !=
IAVF_PROTO_XTR_NONE ?
ad->devargs.proto_xtr[i] :
ad->devargs.proto_xtr_dflt;
if (vf->proto_xtr[i] != IAVF_PROTO_XTR_NONE) {
uint8_t type = vf->proto_xtr[i];
iavf_proto_xtr_params[type].required = true;
proto_xtr_enable = true;
}
}
if (likely(!proto_xtr_enable))
return;
offset = rte_mbuf_dynfield_register(&iavf_proto_xtr_metadata_param);
if (unlikely(offset == -1)) {
PMD_DRV_LOG(ERR,
"failed to extract protocol metadata, error %d",
-rte_errno);
return;
}
PMD_DRV_LOG(DEBUG,
"proto_xtr metadata offset in mbuf is : %d",
offset);
rte_pmd_ifd_dynfield_proto_xtr_metadata_offs = offset;
for (i = 0; i < RTE_DIM(iavf_proto_xtr_params); i++) {
xtr_ol = &iavf_proto_xtr_params[i];
uint8_t rxdid = iavf_proto_xtr_type_to_rxdid((uint8_t)i);
if (!xtr_ol->required)
continue;
if (!(vf->supported_rxdid & BIT(rxdid))) {
PMD_DRV_LOG(ERR,
"rxdid[%u] is not supported in hardware",
rxdid);
rte_pmd_ifd_dynfield_proto_xtr_metadata_offs = -1;
break;
}
offset = rte_mbuf_dynflag_register(&xtr_ol->param);
if (unlikely(offset == -1)) {
PMD_DRV_LOG(ERR,
"failed to register proto_xtr offload '%s', error %d",
xtr_ol->param.name, -rte_errno);
rte_pmd_ifd_dynfield_proto_xtr_metadata_offs = -1;
break;
}
PMD_DRV_LOG(DEBUG,
"proto_xtr offload '%s' offset in mbuf is : %d",
xtr_ol->param.name, offset);
*xtr_ol->ol_flag = 1ULL << offset;
}
}
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_init_vf(struct rte_eth_dev *dev)
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
{
net/avf: fix unused variables and label Compiling with all warnings turned on causes errors about unused variables and an unused label. Remove these to allow building without having to disable those warnings. Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Fixes: 3fd7a3719c66 ("net/avf: enable ops for MTU setting") Fixes: d6bde6b5eae9 ("net/avf: enable Rx interrupt") Fixes: 22b123a36d07 ("net/avf: initialize PMD") Fixes: 319c421f3890 ("net/avf: enable SSE Rx Tx") Fixes: a2b29a7733ef ("net/avf: enable basic Rx Tx") Fixes: 1060591eada5 ("net/avf: enable bulk allocate Rx") CC: stable@dpdk.org Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Luca Boccassi <bluca@debian.org>
2018-09-19 10:04:15 +00:00
int err, bufsz;
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_hw *hw = IAVF_DEV_PRIVATE_TO_HW(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
net/iavf: fix multi-process shared data When the iavf_adapter instance is not initialized completely in the primary process, the secondary process accesses its "rte_eth_dev" member, it causes secondary process crash. This patch replaces eth_dev with eth_dev_data in iavf_adapter. Fixes: f978c1c9b3b5 ("net/iavf: add RSS hash parsing in AVX path") Fixes: 9c9aa0040344 ("net/iavf: add offload path for Rx AVX512 flex descriptor") Fixes: 63660ea3ee0b ("net/iavf: add RSS hash parsing in SSE path") Cc: stable@dpdk.org Signed-off-by: Dapeng Yu <dapengx.yu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-10-11 02:01:31 +00:00
vf->eth_dev = dev;
net/iavf: support flex desc metadata extraction Enable metadata extraction for flexible descriptors in AVF, that would allow network function directly get metadata without additional parsing which would reduce the CPU cost for VFs. The enabling metadata extractions involve the metadata of VLAN/IPv4/IPv6/IPv6-FLOW/TCP/MPLS flexible descriptors, and the VF could negotiate the capability of the flexible descriptor with PF and correspondingly configure the specific offload at receiving queues. Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Haiyue Wang <haiyue.wang@intel.com>
2020-10-30 08:40:30 +00:00
err = iavf_parse_devargs(dev);
if (err) {
PMD_INIT_LOG(ERR, "Failed to parse devargs");
goto err;
}
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
err = iavf_set_mac_type(hw);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
if (err) {
PMD_INIT_LOG(ERR, "set_mac_type failed: %d", err);
goto err;
}
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
err = iavf_check_vf_reset_done(hw);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
if (err) {
PMD_INIT_LOG(ERR, "VF is still resetting");
goto err;
}
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_init_adminq_parameter(hw);
err = iavf_init_adminq(hw);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
if (err) {
PMD_INIT_LOG(ERR, "init_adminq failed: %d", err);
goto err;
}
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
vf->aq_resp = rte_zmalloc("vf_aq_resp", IAVF_AQ_BUF_SZ, 0);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
if (!vf->aq_resp) {
PMD_INIT_LOG(ERR, "unable to allocate vf_aq_resp memory");
goto err_aq;
}
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
if (iavf_check_api_version(adapter) != 0) {
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
PMD_INIT_LOG(ERR, "check_api version failed");
goto err_api;
}
bufsz = sizeof(struct virtchnl_vf_resource) +
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
(IAVF_MAX_VF_VSI * sizeof(struct virtchnl_vsi_resource));
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
vf->vf_res = rte_zmalloc("vf_res", bufsz, 0);
if (!vf->vf_res) {
PMD_INIT_LOG(ERR, "unable to allocate vf_res memory");
goto err_api;
}
net/iavf: query QoS capabilities and set queue TC mapping This patch added the support for VF to config the ETS-based Tx QoS, including querying current QoS configuration from PF and config queue TC mapping. PF QoS is configured in advance and the queried info is provided to the user for future usage. VF queues are mapped to different TCs in PF through virtchnl. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-07-01 11:41:22 +00:00
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
if (iavf_get_vf_resource(adapter) != 0) {
PMD_INIT_LOG(ERR, "iavf_get_vf_config failed");
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
goto err_alloc;
}
/* Allocate memort for RSS info */
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF) {
vf->rss_key = rte_zmalloc("rss_key",
vf->vf_res->rss_key_size, 0);
if (!vf->rss_key) {
PMD_INIT_LOG(ERR, "unable to allocate rss_key memory");
goto err_rss;
}
vf->rss_lut = rte_zmalloc("rss_lut",
vf->vf_res->rss_lut_size, 0);
if (!vf->rss_lut) {
PMD_INIT_LOG(ERR, "unable to allocate rss_lut memory");
goto err_rss;
}
}
net/iavf: support flexible Rx descriptor in normal path Support flexible Rx descriptor format in normal path of iAVF PMD. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Qi Zhang <qi.z.zhang@intel.com>
2020-04-20 06:16:17 +00:00
net/iavf: initialize large VF setting at startup lv_enabled is used to remember if large VF setting is configured, but its value is not initialized at startup. This can lead to a different configuration regarding the initial configuration of the PF. For example, a first start is done with 8 rx and 8 tx queues. Large VF is not needed and reta size is 64. A second start is done with 20 rx and tx queues. Large VF is required and reta size is 256. A third start is done with 2 rx and tx queues. Large VF is not needed but reta size is 256 as the PF has been configured during the second start. In order to have a consistent behavior regarding reta size whatever the configuration of the PF (may be changed by a previous boot) the lv_enabled must be set properly at the init phase. Signed-off-by: Ghalem Boudour <ghalem.boudour@6wind.com> Signed-off-by: Thibaut Collet <thibaut.collet@6wind.com> Reviewed-by: Olivier Matz <olivier.matz@6wind.com> Acked-by: Ting Xu <ting.xu@intel.com>
2022-02-10 10:49:14 +00:00
if (vf->vsi_res->num_queue_pairs > IAVF_MAX_NUM_QUEUES_DFLT)
vf->lv_enabled = true;
net/iavf: support flexible Rx descriptor in normal path Support flexible Rx descriptor format in normal path of iAVF PMD. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Qi Zhang <qi.z.zhang@intel.com>
2020-04-20 06:16:17 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) {
if (iavf_get_supported_rxdid(adapter) != 0) {
PMD_INIT_LOG(ERR, "failed to do get supported rxdid");
goto err_rss;
}
}
net/iavf: support new VLAN capabilities The new VLAN virtchnl opcodes introduce new capabilities like VLAN filtering, stripping and insertion. The AVF needs to query the VLAN capabilities based on current device configuration firstly. AVF is able to configure inner VLAN filter when port VLAN is enabled base on negotiation; and AVF is able to configure outer VLAN (0x8100) if port VLAN is disabled to be compatible with legacy mode. When port VLAN is updated by DCF, the AVF needs to reset to query the new VLAN capabilities. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-12 08:13:02 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN_V2) {
if (iavf_get_vlan_offload_caps_v2(adapter) != 0) {
PMD_INIT_LOG(ERR, "failed to do get VLAN offload v2 capabilities");
goto err_rss;
}
}
net/iavf: query QoS capabilities and set queue TC mapping This patch added the support for VF to config the ETS-based Tx QoS, including querying current QoS configuration from PF and config queue TC mapping. PF QoS is configured in advance and the queried info is provided to the user for future usage. VF queues are mapped to different TCs in PF through virtchnl. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-07-01 11:41:22 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_QOS) {
bufsz = sizeof(struct virtchnl_qos_cap_list) +
IAVF_MAX_TRAFFIC_CLASS *
sizeof(struct virtchnl_qos_cap_elem);
vf->qos_cap = rte_zmalloc("qos_cap", bufsz, 0);
if (!vf->qos_cap) {
PMD_INIT_LOG(ERR, "unable to allocate qos_cap memory");
goto err_rss;
}
iavf_tm_conf_init(dev);
}
net/iavf: support flex desc metadata extraction Enable metadata extraction for flexible descriptors in AVF, that would allow network function directly get metadata without additional parsing which would reduce the CPU cost for VFs. The enabling metadata extractions involve the metadata of VLAN/IPv4/IPv6/IPv6-FLOW/TCP/MPLS flexible descriptors, and the VF could negotiate the capability of the flexible descriptor with PF and correspondingly configure the specific offload at receiving queues. Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Haiyue Wang <haiyue.wang@intel.com>
2020-10-30 08:40:30 +00:00
iavf_init_proto_xtr(dev);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
return 0;
err_rss:
rte_free(vf->rss_key);
rte_free(vf->rss_lut);
err_alloc:
net/iavf: query QoS capabilities and set queue TC mapping This patch added the support for VF to config the ETS-based Tx QoS, including querying current QoS configuration from PF and config queue TC mapping. PF QoS is configured in advance and the queried info is provided to the user for future usage. VF queues are mapped to different TCs in PF through virtchnl. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-07-01 11:41:22 +00:00
rte_free(vf->qos_cap);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
rte_free(vf->vf_res);
vf->vsi_res = NULL;
err_api:
rte_free(vf->aq_resp);
err_aq:
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_shutdown_adminq(hw);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
err:
return -1;
}
net/iavf: fix resource leak on probing failure During the port probe process, there are two abnormal branches that did not release the previously requested memory, resulting in leakage. The patch adds an iavf_uninit_vf function, which corresponds to the iavf_init_vf function. Fixes: ff2d0c345c3b ("net/iavf: support generic flow API") Cc: stable@dpdk.org Signed-off-by: Qiming Chen <chenqiming_huawei@163.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-09-10 07:48:35 +00:00
static void
iavf_uninit_vf(struct rte_eth_dev *dev)
{
struct iavf_hw *hw = IAVF_DEV_PRIVATE_TO_HW(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
iavf_shutdown_adminq(hw);
rte_free(vf->vf_res);
vf->vsi_res = NULL;
vf->vf_res = NULL;
rte_free(vf->aq_resp);
vf->aq_resp = NULL;
rte_free(vf->qos_cap);
vf->qos_cap = NULL;
rte_free(vf->rss_lut);
vf->rss_lut = NULL;
rte_free(vf->rss_key);
vf->rss_key = NULL;
}
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
/* Enable default admin queue interrupt setting */
static inline void
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_enable_irq0(struct iavf_hw *hw)
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
{
/* Enable admin queue interrupt trigger */
net/iavf/base: rename register macro Rename all register macro to align with kernel driver's implementation. Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com> Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
2019-12-03 07:03:04 +00:00
IAVF_WRITE_REG(hw, IAVF_VFINT_ICR0_ENA1,
IAVF_VFINT_ICR0_ENA1_ADMINQ_MASK);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
net/iavf/base: rename register macro Rename all register macro to align with kernel driver's implementation. Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com> Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
2019-12-03 07:03:04 +00:00
IAVF_WRITE_REG(hw, IAVF_VFINT_DYN_CTL01,
IAVF_VFINT_DYN_CTL01_INTENA_MASK |
IAVF_VFINT_DYN_CTL01_CLEARPBA_MASK |
IAVF_VFINT_DYN_CTL01_ITR_INDX_MASK);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
IAVF_WRITE_FLUSH(hw);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
}
static inline void
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_disable_irq0(struct iavf_hw *hw)
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
{
/* Disable all interrupt types */
net/iavf/base: rename register macro Rename all register macro to align with kernel driver's implementation. Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com> Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
2019-12-03 07:03:04 +00:00
IAVF_WRITE_REG(hw, IAVF_VFINT_ICR0_ENA1, 0);
IAVF_WRITE_REG(hw, IAVF_VFINT_DYN_CTL01,
IAVF_VFINT_DYN_CTL01_ITR_INDX_MASK);
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
IAVF_WRITE_FLUSH(hw);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
}
static void
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_interrupt_handler(void *param)
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
{
struct rte_eth_dev *dev = (struct rte_eth_dev *)param;
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_hw *hw = IAVF_DEV_PRIVATE_TO_HW(dev->data->dev_private);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_disable_irq0(hw);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_handle_virtchnl_msg(dev);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_enable_irq0(hw);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
}
net/iavf: enable interrupt polling For VF hosted by Intel 700 series NICs, internal Rx interrupt and adminq interrupt share the same source, that cause a lot CPU cycles be wasted on interrupt handler on Rx path. The patch disable PCI interrupt and remove the interrupt handler, replace it with a low frequency(50ms) interrupt polling daemon which is implemented by registering an alarm callback periodically. The virtual channel capability bit VIRTCHNL_VF_OFFLOAD_WB_ON_ITR can be used to negotiate if iavf PMD needs to enable background alarm or not, so ideally this change will not impact the case hosted by Intel 800 series NICS. This patch implements the same logic with an early i40e commit: commit 864a800d706d ("net/i40e: remove VF interrupt handler") Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Pallavi Kadam <pallavi.kadam@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-08-25 08:34:35 +00:00
void
iavf_dev_alarm_handler(void *param)
{
struct rte_eth_dev *dev = (struct rte_eth_dev *)param;
struct iavf_hw *hw = IAVF_DEV_PRIVATE_TO_HW(dev->data->dev_private);
uint32_t icr0;
iavf_disable_irq0(hw);
/* read out interrupt causes */
icr0 = IAVF_READ_REG(hw, IAVF_VFINT_ICR01);
if (icr0 & IAVF_VFINT_ICR01_ADMINQ_MASK) {
PMD_DRV_LOG(DEBUG, "ICR01_ADMINQ is reported");
iavf_handle_virtchnl_msg(dev);
}
iavf_enable_irq0(hw);
rte_eal_alarm_set(IAVF_ALARM_INTERVAL,
iavf_dev_alarm_handler, dev);
}
net/iavf: support generic flow API This patch added iavf_flow_create, iavf_flow_destroy, iavf_flow_flush and iavf_flow_validate support, these are used to handle all the generic filters. This patch supported basic L2, L3, L4 and GTPU patterns. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-04-03 05:42:41 +00:00
static int
ethdev: replace callback getting filter operations Since rte_flow is the only API for filtering operations, the legacy driver interface filter_ctrl was too much complicated for the simple task of getting the struct rte_flow_ops. The filter type RTE_ETH_FILTER_GENERIC and the filter operarion RTE_ETH_FILTER_GET are removed. The new driver callback flow_ops_get replaces filter_ctrl. Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2021-03-21 09:00:00 +00:00
iavf_dev_flow_ops_get(struct rte_eth_dev *dev,
const struct rte_flow_ops **ops)
net/iavf: support generic flow API This patch added iavf_flow_create, iavf_flow_destroy, iavf_flow_flush and iavf_flow_validate support, these are used to handle all the generic filters. This patch supported basic L2, L3, L4 and GTPU patterns. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-04-03 05:42:41 +00:00
{
net/iavf: fix crash after VF reset failure Some pointers will be set to NULL when iavf_dev_reset() failed, for example vf->vf_res, vf->vsi_res vf->rss_key and etc. APIs access these NULL pointers will trigger segfault. This patch adds closed flag to indicate that the VF is closed, and rejects API calls in this state to avoid coredump. Fixes: e74e1bb6280d ("net/iavf: enable port reset") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-12 10:48:51 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
if (adapter->closed)
return -EIO;
net/iavf: support generic flow API This patch added iavf_flow_create, iavf_flow_destroy, iavf_flow_flush and iavf_flow_validate support, these are used to handle all the generic filters. This patch supported basic L2, L3, L4 and GTPU patterns. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-04-03 05:42:41 +00:00
ethdev: replace callback getting filter operations Since rte_flow is the only API for filtering operations, the legacy driver interface filter_ctrl was too much complicated for the simple task of getting the struct rte_flow_ops. The filter type RTE_ETH_FILTER_GENERIC and the filter operarion RTE_ETH_FILTER_GET are removed. The new driver callback flow_ops_get replaces filter_ctrl. Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Rosen Xu <rosen.xu@intel.com> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2021-03-21 09:00:00 +00:00
*ops = &iavf_flow_ops;
return 0;
net/iavf: support generic flow API This patch added iavf_flow_create, iavf_flow_destroy, iavf_flow_flush and iavf_flow_validate support, these are used to handle all the generic filters. This patch supported basic L2, L3, L4 and GTPU patterns. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-04-03 05:42:41 +00:00
}
net/iavf: fix default RSS configuration Add advanced RSS offloads check due to some legacy driver (kernel/DPDK PF) does not support virtual channel command VIRTCHNL_OP_RSS_HENA with hena = 0 and VIRTCHNL_OP_ADD_RSS_CFG. Fixes: 95f2f0e9fc2a ("net/iavf: improve default RSS") Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-31 10:47:24 +00:00
static void
iavf_default_rss_disable(struct iavf_adapter *adapter)
{
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
int ret = 0;
net/iavf: fix RSS configuration on i40e VF The iavf does not support configuring RSS type on i40e VF, because the i40e kernel driver does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. This patch adds support of RSS type configuration for i40e VF by sending VIRTCHNL_OP_SET_RSS_HENA message to the PF after checking that the PF does not support VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability. Fixes: c678299594a8 ("net/iavf: fix default RSS configuration") Cc: stable@dpdk.org Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-04-25 05:08:47 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF) {
net/iavf: fix default RSS configuration Add advanced RSS offloads check due to some legacy driver (kernel/DPDK PF) does not support virtual channel command VIRTCHNL_OP_RSS_HENA with hena = 0 and VIRTCHNL_OP_ADD_RSS_CFG. Fixes: 95f2f0e9fc2a ("net/iavf: improve default RSS") Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-31 10:47:24 +00:00
/* Set hena = 0 to ask PF to cleanup all existing RSS. */
ret = iavf_set_hena(adapter, 0);
if (ret)
/* It is a workaround, temporarily allow error to be
* returned due to possible lack of PF handling for
* hena = 0.
*/
PMD_INIT_LOG(WARNING, "fail to disable default RSS,"
"lack PF support");
}
}
net/iavf: support generic flow API This patch added iavf_flow_create, iavf_flow_destroy, iavf_flow_flush and iavf_flow_validate support, these are used to handle all the generic filters. This patch supported basic L2, L3, L4 and GTPU patterns. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-04-03 05:42:41 +00:00
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_init(struct rte_eth_dev *eth_dev)
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(eth_dev->data->dev_private);
struct iavf_hw *hw = IAVF_DEV_PRIVATE_TO_HW(adapter);
net/iavf: enable interrupt polling For VF hosted by Intel 700 series NICs, internal Rx interrupt and adminq interrupt share the same source, that cause a lot CPU cycles be wasted on interrupt handler on Rx path. The patch disable PCI interrupt and remove the interrupt handler, replace it with a low frequency(50ms) interrupt polling daemon which is implemented by registering an alarm callback periodically. The virtual channel capability bit VIRTCHNL_VF_OFFLOAD_WB_ON_ITR can be used to negotiate if iavf PMD needs to enable background alarm or not, so ideally this change will not impact the case hosted by Intel 800 series NICS. This patch implements the same logic with an early i40e commit: commit 864a800d706d ("net/i40e: remove VF interrupt handler") Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Pallavi Kadam <pallavi.kadam@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-08-25 08:34:35 +00:00
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(adapter);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
struct rte_pci_device *pci_dev = RTE_ETH_DEV_TO_PCI(eth_dev);
net/iavf: support generic flow API This patch added iavf_flow_create, iavf_flow_destroy, iavf_flow_flush and iavf_flow_validate support, these are used to handle all the generic filters. This patch supported basic L2, L3, L4 and GTPU patterns. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-04-03 05:42:41 +00:00
int ret = 0;
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
PMD_INIT_FUNC_TRACE();
/* assign ops func pointer */
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
eth_dev->dev_ops = &iavf_eth_dev_ops;
ethdev: move inline device operations This patch is a preparation to hide the 'struct eth_dev_ops' from applications by moving some device operations from 'struct eth_dev_ops' to 'struct rte_eth_dev'. Mentioned ethdev APIs are in the data path and implemented as inline because of performance reasons. Exposing 'struct eth_dev_ops' to applications is bad because it is a contract between ethdev and PMDs, not really needs to be known by applications, also changes in the struct causing ABI breakages which shouldn't. To be able to both keep APIs inline and hide the 'struct eth_dev_ops', moving device operations used in ethdev inline APIs to 'struct rte_eth_dev' to the same level with Rx/Tx burst functions. The list of dev_ops moved: eth_rx_queue_count_t rx_queue_count; eth_rx_descriptor_done_t rx_descriptor_done; eth_rx_descriptor_status_t rx_descriptor_status; eth_tx_descriptor_status_t tx_descriptor_status; Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Reviewed-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: David Marchand <david.marchand@redhat.com> Acked-by: Sachin Saxena <sachin.saxena@nxp.com>
2020-09-09 13:01:43 +00:00
eth_dev->rx_queue_count = iavf_dev_rxq_count;
eth_dev->rx_descriptor_status = iavf_dev_rx_desc_status;
eth_dev->tx_descriptor_status = iavf_dev_tx_desc_status;
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
eth_dev->rx_pkt_burst = &iavf_recv_pkts;
eth_dev->tx_pkt_burst = &iavf_xmit_pkts;
eth_dev->tx_pkt_prepare = &iavf_prep_pkts;
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
net/avf: enable basic Rx Tx Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
2018-01-10 13:01:56 +00:00
/* For secondary processes, we don't initialise any further as primary
* has already done this work. Only check if we need a different RX
* and TX function.
*/
if (rte_eal_process_type() != RTE_PROC_PRIMARY) {
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_set_rx_function(eth_dev);
iavf_set_tx_function(eth_dev);
net/avf: enable basic Rx Tx Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
2018-01-10 13:01:56 +00:00
return 0;
}
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
rte_eth_copy_pci_info(eth_dev, pci_dev);
hw->vendor_id = pci_dev->id.vendor_id;
hw->device_id = pci_dev->id.device_id;
hw->subsystem_vendor_id = pci_dev->id.subsystem_vendor_id;
hw->subsystem_device_id = pci_dev->id.subsystem_device_id;
hw->bus.bus_id = pci_dev->addr.bus;
hw->bus.device = pci_dev->addr.devid;
hw->bus.func = pci_dev->addr.function;
hw->hw_addr = (void *)pci_dev->mem_resource[0].addr;
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
hw->back = IAVF_DEV_PRIVATE_TO_ADAPTER(eth_dev->data->dev_private);
net/iavf: fix multi-process shared data When the iavf_adapter instance is not initialized completely in the primary process, the secondary process accesses its "rte_eth_dev" member, it causes secondary process crash. This patch replaces eth_dev with eth_dev_data in iavf_adapter. Fixes: f978c1c9b3b5 ("net/iavf: add RSS hash parsing in AVX path") Fixes: 9c9aa0040344 ("net/iavf: add offload path for Rx AVX512 flex descriptor") Fixes: 63660ea3ee0b ("net/iavf: add RSS hash parsing in SSE path") Cc: stable@dpdk.org Signed-off-by: Dapeng Yu <dapengx.yu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-10-11 02:01:31 +00:00
adapter->dev_data = eth_dev->data;
net/iavf: move device state flag Move device state flag from ice_hw to ice_adapter since it should not be a part of base code. Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
2019-12-03 07:03:17 +00:00
adapter->stopped = 1;
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
if (iavf_init_vf(eth_dev) != 0) {
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
PMD_INIT_LOG(ERR, "Init vf failed");
return -1;
}
net/iavf: unify Rx packet type table This patch unified the Rx ptype table. Signed-off-by: Shougang Wang <shougangx.wang@intel.com> Acked-by: Leyi Rong <leyi.rong@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2020-03-06 02:24:19 +00:00
/* set default ptype table */
net/iavf: fix shared data in multi-process The shared pointer is initialized to a static local array defined in the primary process and it shall not be accessed in the secondary process. This patch copies the local data to shared data, to avoid data access violation. Fixes: 040b44551f77 ("net/iavf: unify Rx packet type table") Cc: stable@dpdk.org Signed-off-by: Dapeng Yu <dapengx.yu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-10-27 08:28:39 +00:00
iavf_set_default_ptype_table(eth_dev);
net/iavf: unify Rx packet type table This patch unified the Rx ptype table. Signed-off-by: Shougang Wang <shougangx.wang@intel.com> Acked-by: Leyi Rong <leyi.rong@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2020-03-06 02:24:19 +00:00
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
/* copy mac addr */
eth_dev->data->mac_addrs = rte_zmalloc(
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
"iavf_mac", RTE_ETHER_ADDR_LEN * IAVF_NUM_MACADDR_MAX, 0);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
if (!eth_dev->data->mac_addrs) {
PMD_INIT_LOG(ERR, "Failed to allocate %d bytes needed to"
" store MAC addresses",
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
RTE_ETHER_ADDR_LEN * IAVF_NUM_MACADDR_MAX);
net/iavf: fix resource leak on probing failure During the port probe process, there are two abnormal branches that did not release the previously requested memory, resulting in leakage. The patch adds an iavf_uninit_vf function, which corresponds to the iavf_init_vf function. Fixes: ff2d0c345c3b ("net/iavf: support generic flow API") Cc: stable@dpdk.org Signed-off-by: Qiming Chen <chenqiming_huawei@163.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-09-10 07:48:35 +00:00
ret = -ENOMEM;
goto init_vf_err;
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
}
/* If the MAC address is not configured by host,
* generate a random one.
*/
net: add rte prefix to ether functions Add 'rte_' prefix to functions: - rename is_same_ether_addr() as rte_is_same_ether_addr(). - rename is_zero_ether_addr() as rte_is_zero_ether_addr(). - rename is_unicast_ether_addr() as rte_is_unicast_ether_addr(). - rename is_multicast_ether_addr() as rte_is_multicast_ether_addr(). - rename is_broadcast_ether_addr() as rte_is_broadcast_ether_addr(). - rename is_universal_ether_addr() as rte_is_universal_ether_addr(). - rename is_local_admin_ether_addr() as rte_is_local_admin_ether_addr(). - rename is_valid_assigned_ether_addr() as rte_is_valid_assigned_ether_addr(). - rename eth_random_addr() as rte_eth_random_addr(). - rename ether_addr_copy() as rte_ether_addr_copy(). - rename ether_format_addr() as rte_ether_format_addr(). 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 16:13:04 +00:00
if (!rte_is_valid_assigned_ether_addr(
net: add rte prefix to ether structures Add 'rte_' prefix to structures: - rename struct ether_addr as struct rte_ether_addr. - rename struct ether_hdr as struct rte_ether_hdr. - rename struct vlan_hdr as struct rte_vlan_hdr. - rename struct vxlan_hdr as struct rte_vxlan_hdr. - rename struct vxlan_gpe_hdr as struct rte_vxlan_gpe_hdr. 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 16:13:03 +00:00
(struct rte_ether_addr *)hw->mac.addr))
net: add rte prefix to ether functions Add 'rte_' prefix to functions: - rename is_same_ether_addr() as rte_is_same_ether_addr(). - rename is_zero_ether_addr() as rte_is_zero_ether_addr(). - rename is_unicast_ether_addr() as rte_is_unicast_ether_addr(). - rename is_multicast_ether_addr() as rte_is_multicast_ether_addr(). - rename is_broadcast_ether_addr() as rte_is_broadcast_ether_addr(). - rename is_universal_ether_addr() as rte_is_universal_ether_addr(). - rename is_local_admin_ether_addr() as rte_is_local_admin_ether_addr(). - rename is_valid_assigned_ether_addr() as rte_is_valid_assigned_ether_addr(). - rename eth_random_addr() as rte_eth_random_addr(). - rename ether_addr_copy() as rte_ether_addr_copy(). - rename ether_format_addr() as rte_ether_format_addr(). 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 16:13:04 +00:00
rte_eth_random_addr(hw->mac.addr);
rte_ether_addr_copy((struct rte_ether_addr *)hw->mac.addr,
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
&eth_dev->data->mac_addrs[0]);
net/iavf: enable interrupt polling For VF hosted by Intel 700 series NICs, internal Rx interrupt and adminq interrupt share the same source, that cause a lot CPU cycles be wasted on interrupt handler on Rx path. The patch disable PCI interrupt and remove the interrupt handler, replace it with a low frequency(50ms) interrupt polling daemon which is implemented by registering an alarm callback periodically. The virtual channel capability bit VIRTCHNL_VF_OFFLOAD_WB_ON_ITR can be used to negotiate if iavf PMD needs to enable background alarm or not, so ideally this change will not impact the case hosted by Intel 800 series NICS. This patch implements the same logic with an early i40e commit: commit 864a800d706d ("net/i40e: remove VF interrupt handler") Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Pallavi Kadam <pallavi.kadam@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-08-25 08:34:35 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) {
/* register callback func to eal lib */
drivers: remove direct access to interrupt handle Removing direct access to interrupt handle structure fields, rather use respective get set APIs for the same. Making changes to all the drivers access the interrupt handle fields. Signed-off-by: Harman Kalra <hkalra@marvell.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com> Signed-off-by: David Marchand <david.marchand@redhat.com> Tested-by: Raslan Darawsheh <rasland@nvidia.com>
2021-10-22 20:49:32 +00:00
rte_intr_callback_register(pci_dev->intr_handle,
net/iavf: enable interrupt polling For VF hosted by Intel 700 series NICs, internal Rx interrupt and adminq interrupt share the same source, that cause a lot CPU cycles be wasted on interrupt handler on Rx path. The patch disable PCI interrupt and remove the interrupt handler, replace it with a low frequency(50ms) interrupt polling daemon which is implemented by registering an alarm callback periodically. The virtual channel capability bit VIRTCHNL_VF_OFFLOAD_WB_ON_ITR can be used to negotiate if iavf PMD needs to enable background alarm or not, so ideally this change will not impact the case hosted by Intel 800 series NICS. This patch implements the same logic with an early i40e commit: commit 864a800d706d ("net/i40e: remove VF interrupt handler") Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Pallavi Kadam <pallavi.kadam@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-08-25 08:34:35 +00:00
iavf_dev_interrupt_handler,
(void *)eth_dev);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
net/iavf: enable interrupt polling For VF hosted by Intel 700 series NICs, internal Rx interrupt and adminq interrupt share the same source, that cause a lot CPU cycles be wasted on interrupt handler on Rx path. The patch disable PCI interrupt and remove the interrupt handler, replace it with a low frequency(50ms) interrupt polling daemon which is implemented by registering an alarm callback periodically. The virtual channel capability bit VIRTCHNL_VF_OFFLOAD_WB_ON_ITR can be used to negotiate if iavf PMD needs to enable background alarm or not, so ideally this change will not impact the case hosted by Intel 800 series NICS. This patch implements the same logic with an early i40e commit: commit 864a800d706d ("net/i40e: remove VF interrupt handler") Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Pallavi Kadam <pallavi.kadam@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-08-25 08:34:35 +00:00
/* enable uio intr after callback register */
drivers: remove direct access to interrupt handle Removing direct access to interrupt handle structure fields, rather use respective get set APIs for the same. Making changes to all the drivers access the interrupt handle fields. Signed-off-by: Harman Kalra <hkalra@marvell.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com> Signed-off-by: David Marchand <david.marchand@redhat.com> Tested-by: Raslan Darawsheh <rasland@nvidia.com>
2021-10-22 20:49:32 +00:00
rte_intr_enable(pci_dev->intr_handle);
net/iavf: enable interrupt polling For VF hosted by Intel 700 series NICs, internal Rx interrupt and adminq interrupt share the same source, that cause a lot CPU cycles be wasted on interrupt handler on Rx path. The patch disable PCI interrupt and remove the interrupt handler, replace it with a low frequency(50ms) interrupt polling daemon which is implemented by registering an alarm callback periodically. The virtual channel capability bit VIRTCHNL_VF_OFFLOAD_WB_ON_ITR can be used to negotiate if iavf PMD needs to enable background alarm or not, so ideally this change will not impact the case hosted by Intel 800 series NICS. This patch implements the same logic with an early i40e commit: commit 864a800d706d ("net/i40e: remove VF interrupt handler") Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Pallavi Kadam <pallavi.kadam@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-08-25 08:34:35 +00:00
} else {
rte_eal_alarm_set(IAVF_ALARM_INTERVAL,
iavf_dev_alarm_handler, eth_dev);
}
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
/* configure and enable device interrupt */
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_enable_irq0(hw);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
net/iavf: support generic flow API This patch added iavf_flow_create, iavf_flow_destroy, iavf_flow_flush and iavf_flow_validate support, these are used to handle all the generic filters. This patch supported basic L2, L3, L4 and GTPU patterns. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-04-03 05:42:41 +00:00
ret = iavf_flow_init(adapter);
if (ret) {
PMD_INIT_LOG(ERR, "Failed to initialize flow");
net/iavf: fix resource leak on probing failure During the port probe process, there are two abnormal branches that did not release the previously requested memory, resulting in leakage. The patch adds an iavf_uninit_vf function, which corresponds to the iavf_init_vf function. Fixes: ff2d0c345c3b ("net/iavf: support generic flow API") Cc: stable@dpdk.org Signed-off-by: Qiming Chen <chenqiming_huawei@163.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-09-10 07:48:35 +00:00
goto flow_init_err;
net/iavf: support generic flow API This patch added iavf_flow_create, iavf_flow_destroy, iavf_flow_flush and iavf_flow_validate support, these are used to handle all the generic filters. This patch supported basic L2, L3, L4 and GTPU patterns. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-04-03 05:42:41 +00:00
}
net/iavf: support IPsec inline crypto Add support for inline crypto for IPsec, for ESP transport and tunnel over IPv4 and IPv6, as well as supporting the offload for ESP over UDP, and in conjunction with TSO for UDP and TCP flows. Implement support for rte_security packet metadata Add definition for IPsec descriptors, extend support for offload in data and context descriptor to support Add support to virtual channel mailbox for IPsec Crypto request operations. IPsec Crypto requests receive an initial acknowledgment from physical function driver of receipt of request and then an asynchronous response with success/failure of request including any response data. Add enhanced descriptor debugging Refactor of scalar tx burst function to support integration of offload Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Abhijit Sinha <abhijit.sinha@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Reviewed-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:57 +00:00
/** Check if the IPsec Crypto offload is supported and create
* security_ctx if it is.
*/
if (iavf_ipsec_crypto_supported(adapter)) {
/* Initialize security_ctx only for primary process*/
ret = iavf_security_ctx_create(adapter);
if (ret) {
PMD_INIT_LOG(ERR, "failed to create ipsec crypto security instance");
return ret;
}
ret = iavf_security_init(adapter);
if (ret) {
PMD_INIT_LOG(ERR, "failed to initialized ipsec crypto resources");
return ret;
}
}
net/iavf: fix default RSS configuration Add advanced RSS offloads check due to some legacy driver (kernel/DPDK PF) does not support virtual channel command VIRTCHNL_OP_RSS_HENA with hena = 0 and VIRTCHNL_OP_ADD_RSS_CFG. Fixes: 95f2f0e9fc2a ("net/iavf: improve default RSS") Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-01-31 10:47:24 +00:00
iavf_default_rss_disable(adapter);
net/iavf: improve default RSS Add support to actively configure the RSS through port config. Any kernel PF enabled default RSS will be disabled during initialization. Besides, default RSS will be configured based on rte_eth_rss_conf->rss_hf. Currently supported default rss_type: ipv4[6], ipv4[6]_udp, ipv4[6]_tcp, ipv4[6]_sctp. Signed-off-by: Xuan Ding <xuan.ding@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-12-23 12:52:28 +00:00
net/iavf: add watchdog for VF FLR Add watchdog to iAVF PMD which support monitoring the VFLR register. If the device is not already in reset then if a VF reset in progress is detected then notify user through callback and set into reset state. If the device is already in reset then poll for completion of reset. The watchdog is disabled by default, to enable it set IAVF_DEV_WATCHDOG_PERIOD to a non zero value (microseconds) Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:59 +00:00
/* Start device watchdog */
iavf_dev_watchdog_enable(adapter);
net/iavf: fix crash after VF reset failure Some pointers will be set to NULL when iavf_dev_reset() failed, for example vf->vf_res, vf->vsi_res vf->rss_key and etc. APIs access these NULL pointers will trigger segfault. This patch adds closed flag to indicate that the VF is closed, and rejects API calls in this state to avoid coredump. Fixes: e74e1bb6280d ("net/iavf: enable port reset") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-12 10:48:51 +00:00
adapter->closed = false;
net/iavf: add watchdog for VF FLR Add watchdog to iAVF PMD which support monitoring the VFLR register. If the device is not already in reset then if a VF reset in progress is detected then notify user through callback and set into reset state. If the device is already in reset then poll for completion of reset. The watchdog is disabled by default, to enable it set IAVF_DEV_WATCHDOG_PERIOD to a non zero value (microseconds) Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:59 +00:00
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
return 0;
net/iavf: fix resource leak on probing failure During the port probe process, there are two abnormal branches that did not release the previously requested memory, resulting in leakage. The patch adds an iavf_uninit_vf function, which corresponds to the iavf_init_vf function. Fixes: ff2d0c345c3b ("net/iavf: support generic flow API") Cc: stable@dpdk.org Signed-off-by: Qiming Chen <chenqiming_huawei@163.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-09-10 07:48:35 +00:00
flow_init_err:
rte_free(eth_dev->data->mac_addrs);
eth_dev->data->mac_addrs = NULL;
init_vf_err:
iavf_uninit_vf(eth_dev);
return ret;
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
}
ethdev: allow drivers to return error on close The device operation .dev_close was returning void. This driver interface is changed to return an int. Note that the API rte_eth_dev_close() is still returning void, although a deprecation notice is pending to change it as well. Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Reviewed-by: Rosen Xu <rosen.xu@intel.com> Reviewed-by: Sachin Saxena <sachin.saxena@oss.nxp.com> Reviewed-by: Liron Himi <lironh@marvell.com> Reviewed-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Jeff Guo <jia.guo@intel.com> Reviewed-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org>
2020-09-28 23:14:10 +00:00
static int
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_dev_close(struct rte_eth_dev *dev)
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
struct iavf_hw *hw = IAVF_DEV_PRIVATE_TO_HW(dev->data->dev_private);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
struct rte_pci_device *pci_dev = RTE_ETH_DEV_TO_PCI(dev);
drivers: remove direct access to interrupt handle Removing direct access to interrupt handle structure fields, rather use respective get set APIs for the same. Making changes to all the drivers access the interrupt handle fields. Signed-off-by: Harman Kalra <hkalra@marvell.com> Acked-by: Hyong Youb Kim <hyonkim@cisco.com> Signed-off-by: David Marchand <david.marchand@redhat.com> Tested-by: Raslan Darawsheh <rasland@nvidia.com>
2021-10-22 20:49:32 +00:00
struct rte_intr_handle *intr_handle = pci_dev->intr_handle;
net/iavf: support generic flow API This patch added iavf_flow_create, iavf_flow_destroy, iavf_flow_flush and iavf_flow_validate support, these are used to handle all the generic filters. This patch supported basic L2, L3, L4 and GTPU patterns. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-04-03 05:42:41 +00:00
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
net/iavf: release port upon close Set RTE_ETH_DEV_CLOSE_REMOVE upon probe so all the private resources for the port can be freed by rte_eth_dev_close(). Signed-off-by: Steve Yang <stevex.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-08-11 07:27:52 +00:00
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
ethdev: change stop operation callback to return int Change eth_dev_stop_t return value from void to int. Make eth_dev_stop_t implementations across all drivers to return negative errno values if case of error conditions. Signed-off-by: Ivan Ilchenko <ivan.ilchenko@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2020-10-15 13:30:45 +00:00
int ret;
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
drivers/net: check process type in close operation The secondary processes are not allowed to release shared resources. Only process-private resources should be freed in a secondary process. Most of the time, there is no process-private resource, so the close operation is just forbidden in a secondary process. After adding proper check in the port close functions, some redundant checks in the device remove functions are dropped. Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Reviewed-by: Rosen Xu <rosen.xu@intel.com> Reviewed-by: Sachin Saxena <sachin.saxena@oss.nxp.com> Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Reviewed-by: Liron Himi <lironh@marvell.com> Reviewed-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Jeff Guo <jia.guo@intel.com> Reviewed-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org>
2020-09-28 23:14:31 +00:00
if (rte_eal_process_type() != RTE_PROC_PRIMARY)
return 0;
net/iavf: fix VF reset When the VF is in closed state, the vf_reset flag can not be reverted if the VF is reset asynchronously. This prevents all virtchnl commands from executing, causing subsequent calls to iavf_dev_reset() to fail. So the vf_reset flag needs to be reverted even when VF is in closed state. Fixes: 676d986b4b86 ("net/iavf: fix crash after VF reset failure") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-06-27 07:22:32 +00:00
if (adapter->closed) {
ret = 0;
goto out;
}
net/iavf: fix crash after VF reset failure Some pointers will be set to NULL when iavf_dev_reset() failed, for example vf->vf_res, vf->vsi_res vf->rss_key and etc. APIs access these NULL pointers will trigger segfault. This patch adds closed flag to indicate that the VF is closed, and rejects API calls in this state to avoid coredump. Fixes: e74e1bb6280d ("net/iavf: enable port reset") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-12 10:48:51 +00:00
ethdev: change stop operation callback to return int Change eth_dev_stop_t return value from void to int. Make eth_dev_stop_t implementations across all drivers to return negative errno values if case of error conditions. Signed-off-by: Ivan Ilchenko <ivan.ilchenko@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2020-10-15 13:30:45 +00:00
ret = iavf_dev_stop(dev);
net/iavf: fix crash after VF reset failure Some pointers will be set to NULL when iavf_dev_reset() failed, for example vf->vf_res, vf->vsi_res vf->rss_key and etc. APIs access these NULL pointers will trigger segfault. This patch adds closed flag to indicate that the VF is closed, and rejects API calls in this state to avoid coredump. Fixes: e74e1bb6280d ("net/iavf: enable port reset") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-12 10:48:51 +00:00
adapter->closed = true;
ethdev: change stop operation callback to return int Change eth_dev_stop_t return value from void to int. Make eth_dev_stop_t implementations across all drivers to return negative errno values if case of error conditions. Signed-off-by: Ivan Ilchenko <ivan.ilchenko@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2020-10-15 13:30:45 +00:00
net/iavf: fix device stop Move security context destroy from device stop to device close function. Deleting the context on device stop can prevent the application from properly cleaning and releasing resources. Fixes: 6bc987ecb860 ("net/iavf: support IPsec inline crypto") Cc: stable@dpdk.org Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-05-23 12:04:36 +00:00
/* free iAVF security device context all related resources */
iavf_security_ctx_destroy(adapter);
net/iavf: fix VF reset for flow director rule After VF reset, FDIR rule still takes effect. To solve the issue, this patch adds to flush all flows before flow uninit. VIRTCHNL sends message to PF by Admin Queue, so flow flush should be implemented before Admin Queue shut down. Fixes: ff2d0c345c3b ("net/iavf: support generic flow API") Signed-off-by: Simei Su <simei.su@intel.com> Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
2020-04-28 05:49:19 +00:00
iavf_flow_flush(dev, NULL);
net/iavf: fix flow uninit When closing VF device, the process of shutdown adminq should be after the process of uninit the flow, since the VF might still need to use the adminq to uninit flow. Fixes: 9e03acd726cf ("net/iavf: fix flow access") Fixes: ff2d0c345c3b ("net/iavf: support generic flow API") Cc: stable@dpdk.org Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
2020-05-27 07:16:50 +00:00
iavf_flow_uninit(adapter);
net/iavf: disable promiscuous mode on close In scenario of Kernel Driver runs on PF and PMD runs on VF, PMD exit doesn't disable promiscuous mode, this will cause vlan filter set by Kernel Driver will not take effect. This patch will fix it, add promiscuous disable at device disable. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-27 07:26:23 +00:00
/*
* disable promiscuous mode before reset vf
* it is a workaround solution when work with kernel driver
* and it is not the normal way
*/
if (vf->promisc_unicast_enabled || vf->promisc_multicast_enabled)
iavf_config_promisc(adapter, false, false);
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_shutdown_adminq(hw);
net/iavf: enable interrupt polling For VF hosted by Intel 700 series NICs, internal Rx interrupt and adminq interrupt share the same source, that cause a lot CPU cycles be wasted on interrupt handler on Rx path. The patch disable PCI interrupt and remove the interrupt handler, replace it with a low frequency(50ms) interrupt polling daemon which is implemented by registering an alarm callback periodically. The virtual channel capability bit VIRTCHNL_VF_OFFLOAD_WB_ON_ITR can be used to negotiate if iavf PMD needs to enable background alarm or not, so ideally this change will not impact the case hosted by Intel 800 series NICS. This patch implements the same logic with an early i40e commit: commit 864a800d706d ("net/i40e: remove VF interrupt handler") Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Pallavi Kadam <pallavi.kadam@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-08-25 08:34:35 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) {
/* disable uio intr before callback unregister */
rte_intr_disable(intr_handle);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
net/iavf: enable interrupt polling For VF hosted by Intel 700 series NICs, internal Rx interrupt and adminq interrupt share the same source, that cause a lot CPU cycles be wasted on interrupt handler on Rx path. The patch disable PCI interrupt and remove the interrupt handler, replace it with a low frequency(50ms) interrupt polling daemon which is implemented by registering an alarm callback periodically. The virtual channel capability bit VIRTCHNL_VF_OFFLOAD_WB_ON_ITR can be used to negotiate if iavf PMD needs to enable background alarm or not, so ideally this change will not impact the case hosted by Intel 800 series NICS. This patch implements the same logic with an early i40e commit: commit 864a800d706d ("net/i40e: remove VF interrupt handler") Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Pallavi Kadam <pallavi.kadam@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-08-25 08:34:35 +00:00
/* unregister callback func from eal lib */
rte_intr_callback_unregister(intr_handle,
iavf_dev_interrupt_handler, dev);
} else {
rte_eal_alarm_cancel(iavf_dev_alarm_handler, dev);
}
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
iavf_disable_irq0(hw);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
net/iavf: query QoS capabilities and set queue TC mapping This patch added the support for VF to config the ETS-based Tx QoS, including querying current QoS configuration from PF and config queue TC mapping. PF QoS is configured in advance and the queried info is provided to the user for future usage. VF queues are mapped to different TCs in PF through virtchnl. Signed-off-by: Qiming Yang <qiming.yang@intel.com> Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-07-01 11:41:22 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_QOS)
iavf_tm_conf_uninit(dev);
net/iavf: release port upon close Set RTE_ETH_DEV_CLOSE_REMOVE upon probe so all the private resources for the port can be freed by rte_eth_dev_close(). Signed-off-by: Steve Yang <stevex.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-08-11 07:27:52 +00:00
if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF) {
if (vf->rss_lut) {
rte_free(vf->rss_lut);
vf->rss_lut = NULL;
}
if (vf->rss_key) {
rte_free(vf->rss_key);
vf->rss_key = NULL;
}
}
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
rte_free(vf->vf_res);
vf->vsi_res = NULL;
vf->vf_res = NULL;
rte_free(vf->aq_resp);
vf->aq_resp = NULL;
ethdev: allow drivers to return error on close The device operation .dev_close was returning void. This driver interface is changed to return an int. Note that the API rte_eth_dev_close() is still returning void, although a deprecation notice is pending to change it as well. Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Reviewed-by: Rosen Xu <rosen.xu@intel.com> Reviewed-by: Sachin Saxena <sachin.saxena@oss.nxp.com> Reviewed-by: Liron Himi <lironh@marvell.com> Reviewed-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Jeff Guo <jia.guo@intel.com> Reviewed-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org>
2020-09-28 23:14:10 +00:00
net/iavf: enable PCI bus master after reset The VF reset can be triggered by the PF reset event, then the PCI bus master will be cleared, the VF will be not allowed to issue any Memory or I/O Requests. So after the reset event is detected, always enable the PCI bus master. And if failed, the device or system may be in an invalid state, so keep the VF reset state to mark it as I/O error. Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-05-24 01:23:44 +00:00
/*
* If the VF is reset via VFLR, the device will be knocked out of bus
* master mode, and the driver will fail to recover from the reset. Fix
* this by enabling bus mastering after every reset. In a non-VFLR case,
* the bus master bit will not be disabled, and this call will have no
* effect.
*/
net/iavf: fix VF reset When the VF is in closed state, the vf_reset flag can not be reverted if the VF is reset asynchronously. This prevents all virtchnl commands from executing, causing subsequent calls to iavf_dev_reset() to fail. So the vf_reset flag needs to be reverted even when VF is in closed state. Fixes: 676d986b4b86 ("net/iavf: fix crash after VF reset failure") Cc: stable@dpdk.org Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2022-06-27 07:22:32 +00:00
out:
net/iavf: enable PCI bus master after reset The VF reset can be triggered by the PF reset event, then the PCI bus master will be cleared, the VF will be not allowed to issue any Memory or I/O Requests. So after the reset event is detected, always enable the PCI bus master. And if failed, the device or system may be in an invalid state, so keep the VF reset state to mark it as I/O error. Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
2021-05-24 01:23:44 +00:00
if (vf->vf_reset && !rte_pci_set_bus_master(pci_dev, true))
vf->vf_reset = false;
net/iavf: fix flow flush after PF reset When VF begin reset after PF reset, VF will be uninitialized at first and then be initialized, during the time any invalid cmd such as flow flush should not be sent to PF until the uninitialization is finished. Fixes: 1eab95fe2e36 ("net/iavf: fix command after PF reset") Cc: stable@dpdk.org Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-09-30 05:44:12 +00:00
net/iavf: add watchdog for VF FLR Add watchdog to iAVF PMD which support monitoring the VFLR register. If the device is not already in reset then if a VF reset in progress is detected then notify user through callback and set into reset state. If the device is already in reset then poll for completion of reset. The watchdog is disabled by default, to enable it set IAVF_DEV_WATCHDOG_PERIOD to a non zero value (microseconds) Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
2021-10-28 16:04:59 +00:00
/* disable watchdog */
iavf_dev_watchdog_disable(adapter);
ethdev: change stop operation callback to return int Change eth_dev_stop_t return value from void to int. Make eth_dev_stop_t implementations across all drivers to return negative errno values if case of error conditions. Signed-off-by: Ivan Ilchenko <ivan.ilchenko@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2020-10-15 13:30:45 +00:00
return ret;
net/iavf: release port upon close Set RTE_ETH_DEV_CLOSE_REMOVE upon probe so all the private resources for the port can be freed by rte_eth_dev_close(). Signed-off-by: Steve Yang <stevex.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-08-11 07:27:52 +00:00
}
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
net/iavf: release port upon close Set RTE_ETH_DEV_CLOSE_REMOVE upon probe so all the private resources for the port can be freed by rte_eth_dev_close(). Signed-off-by: Steve Yang <stevex.yang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-08-11 07:27:52 +00:00
static int
iavf_dev_uninit(struct rte_eth_dev *dev)
{
if (rte_eal_process_type() != RTE_PROC_PRIMARY)
return -EPERM;
iavf_dev_close(dev);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
return 0;
}
net/iavf: enable port reset This patch is intended to add iavf_dev_reset ops, enable iavf to support "port reset all". Signed-off-by: Lunyuan Cui <lunyuanx.cui@intel.com> Tested-by: Zhaoyan Chen <zhaoyan.chen@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com> Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
2020-04-01 07:12:14 +00:00
/*
* Reset VF device only to re-initialize resources in PMD layer
*/
static int
iavf_dev_reset(struct rte_eth_dev *dev)
{
int ret;
ret = iavf_dev_uninit(dev);
if (ret)
return ret;
return iavf_dev_init(dev);
}
net/iavf: stop PCI probe in DCF mode A new DCF PMD will be introduced, which runs on Intel VF hardware, and it is a pure software design to control the advance functionality (such as switch, ACL) for rest of the VFs. So if the DCF (Device Config Function) mode is specified by the devarg 'cap=dcf', then it will stop the PCI probe in the iavf PMD. Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Reviewed-by: Xiaolong Ye <xiaolong.ye@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-03-27 02:56:35 +00:00
static int
iavf_dcf_cap_check_handler(__rte_unused const char *key,
const char *value, __rte_unused void *opaque)
{
if (strcmp(value, "dcf"))
return -1;
return 0;
}
static int
iavf_dcf_cap_selected(struct rte_devargs *devargs)
{
struct rte_kvargs *kvlist;
const char *key = "cap";
int ret = 0;
if (devargs == NULL)
return 0;
kvlist = rte_kvargs_parse(devargs->args, NULL);
if (kvlist == NULL)
return 0;
if (!rte_kvargs_count(kvlist, key))
goto exit;
/* dcf capability selected when there's a key-value pair: cap=dcf */
if (rte_kvargs_process(kvlist, key,
iavf_dcf_cap_check_handler, NULL) < 0)
goto exit;
ret = 1;
exit:
rte_kvargs_free(kvlist);
return ret;
}
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
static int eth_iavf_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
struct rte_pci_device *pci_dev)
{
net/iavf: remove i40evf devargs option Due to i40evf will be removed, so there's no need to keep the devargs option "driver=i40evf" in iavf. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-09-24 06:22:27 +00:00
if (iavf_dcf_cap_selected(pci_dev->device.devargs))
net/iavf: stop PCI probe in DCF mode A new DCF PMD will be introduced, which runs on Intel VF hardware, and it is a pure software design to control the advance functionality (such as switch, ACL) for rest of the VFs. So if the DCF (Device Config Function) mode is specified by the devarg 'cap=dcf', then it will stop the PCI probe in the iavf PMD. Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Reviewed-by: Xiaolong Ye <xiaolong.ye@intel.com> Acked-by: Jingjing Wu <jingjing.wu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2020-03-27 02:56:35 +00:00
return 1;
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
return rte_eth_dev_pci_generic_probe(pci_dev,
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
sizeof(struct iavf_adapter), iavf_dev_init);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
}
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
static int eth_iavf_pci_remove(struct rte_pci_device *pci_dev)
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
{
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
return rte_eth_dev_pci_generic_remove(pci_dev, iavf_dev_uninit);
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
}
/* Adaptive virtual function driver struct */
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
static struct rte_pci_driver rte_iavf_pmd = {
.id_table = pci_id_iavf_map,
eal: fix IOVA mode selection as VA for PCI drivers The incriminated commit broke the use of RTE_PCI_DRV_IOVA_AS_VA which was intended to mean "driver only supports VA" but had been understood as "driver supports both PA and VA" by most net drivers and used to let dpdk processes to run as non root (which do not have access to physical addresses on recent kernels). The check on physical addresses actually closed the gap for those drivers. We don't need to mark them with RTE_PCI_DRV_IOVA_AS_VA and this flag can retain its intended meaning. Document explicitly its meaning. We can check that a driver requirement wrt to IOVA mode is fulfilled before trying to probe a device. Finally, document the heuristic used to select the IOVA mode and hope that we won't break it again. Fixes: 703458e19c16 ("bus/pci: consider only usable devices for IOVA mode") Signed-off-by: David Marchand <david.marchand@redhat.com> Reviewed-by: Jerin Jacob <jerinj@marvell.com> Tested-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
2019-07-22 12:56:51 +00:00
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
.probe = eth_iavf_pci_probe,
.remove = eth_iavf_pci_remove,
net/avf: initialize PMD Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
2018-01-10 13:01:54 +00:00
};
net/iavf: rename remaining avf strings This is the main patch which renames the macros, functions, structs and any remaining strings in the iavf code. Signed-off-by: Leyi Rong <leyi.rong@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-02-25 17:18:52 +00:00
RTE_PMD_REGISTER_PCI(net_iavf, rte_iavf_pmd);
RTE_PMD_REGISTER_PCI_TABLE(net_iavf, pci_id_iavf_map);
RTE_PMD_REGISTER_KMOD_DEP(net_iavf, "* igb_uio | vfio-pci");
net/iavf: remove i40evf devargs option Due to i40evf will be removed, so there's no need to keep the devargs option "driver=i40evf" in iavf. Signed-off-by: Robin Zhang <robinx.zhang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
2021-09-24 06:22:27 +00:00
RTE_PMD_REGISTER_PARAM_STRING(net_iavf, "cap=dcf");
log: register with standardized names Let's try to enforce the convention where most drivers use a pmd. logtype with their class reflected in it, and libraries use a lib. logtype. Introduce two new macros: - RTE_LOG_REGISTER_DEFAULT can be used when a single logtype is used in a component. It is associated to the default name provided by the build system, - RTE_LOG_REGISTER_SUFFIX can be used when multiple logtypes are used, and then the passed name is appended to the default name, RTE_LOG_REGISTER is left untouched for existing external users and for components that do not comply with the convention. There is a new Meson variable log_prefix to adapt the default name for baseband (pmd.bb.), bus (no pmd.) and mempool (no pmd.) classes. Note: achieved with below commands + reverted change on net/bonding + edits on crypto/virtio, compress/mlx5, regex/mlx5 $ git grep -l RTE_LOG_REGISTER drivers/ | while read file; do pattern=${file##drivers/}; class=${pattern%%/*}; pattern=${pattern#$class/}; drv=${pattern%%/*}; case "$class" in baseband) pattern=pmd.bb.$drv;; bus) pattern=bus.$drv;; mempool) pattern=mempool.$drv;; *) pattern=pmd.$class.$drv;; esac sed -i -e 's/RTE_LOG_REGISTER(\(.*\), '$pattern',/RTE_LOG_REGISTER_DEFAULT(\1,/' $file; sed -i -e 's/RTE_LOG_REGISTER(\(.*\), '$pattern'\.\(.*\),/RTE_LOG_REGISTER_SUFFIX(\1, \2,/' $file; done $ git grep -l RTE_LOG_REGISTER lib/ | while read file; do pattern=${file##lib/}; pattern=lib.${pattern%%/*}; sed -i -e 's/RTE_LOG_REGISTER(\(.*\), '$pattern',/RTE_LOG_REGISTER_DEFAULT(\1,/' $file; sed -i -e 's/RTE_LOG_REGISTER(\(.*\), '$pattern'\.\(.*\),/RTE_LOG_REGISTER_SUFFIX(\1, \2,/' $file; done Signed-off-by: David Marchand <david.marchand@redhat.com> Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: Bruce Richardson <bruce.richardson@intel.com>
2021-04-26 12:51:08 +00:00
RTE_LOG_REGISTER_SUFFIX(iavf_logtype_init, init, NOTICE);
RTE_LOG_REGISTER_SUFFIX(iavf_logtype_driver, driver, NOTICE);
net/iavf: refine debug build option 1. replace RTE_LIBRTE_IAVF_DEBUG_RX with RTE_ETHDEV_DEBUG_RX. 2. replace RTE_LIBRTE_IAVF_DEBUG_TX with RTE_ETHDEV_DEBUG_TX. 3. merge RTE_LIBRTE_IAVF_DEBUG_TX_FREE and RTE_LIBRTE_ETHDEV_DEBUG into RTE_ETHDEV_DEBUG_TX Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2021-03-31 09:52:51 +00:00
#ifdef RTE_ETHDEV_DEBUG_RX
log: register with standardized names Let's try to enforce the convention where most drivers use a pmd. logtype with their class reflected in it, and libraries use a lib. logtype. Introduce two new macros: - RTE_LOG_REGISTER_DEFAULT can be used when a single logtype is used in a component. It is associated to the default name provided by the build system, - RTE_LOG_REGISTER_SUFFIX can be used when multiple logtypes are used, and then the passed name is appended to the default name, RTE_LOG_REGISTER is left untouched for existing external users and for components that do not comply with the convention. There is a new Meson variable log_prefix to adapt the default name for baseband (pmd.bb.), bus (no pmd.) and mempool (no pmd.) classes. Note: achieved with below commands + reverted change on net/bonding + edits on crypto/virtio, compress/mlx5, regex/mlx5 $ git grep -l RTE_LOG_REGISTER drivers/ | while read file; do pattern=${file##drivers/}; class=${pattern%%/*}; pattern=${pattern#$class/}; drv=${pattern%%/*}; case "$class" in baseband) pattern=pmd.bb.$drv;; bus) pattern=bus.$drv;; mempool) pattern=mempool.$drv;; *) pattern=pmd.$class.$drv;; esac sed -i -e 's/RTE_LOG_REGISTER(\(.*\), '$pattern',/RTE_LOG_REGISTER_DEFAULT(\1,/' $file; sed -i -e 's/RTE_LOG_REGISTER(\(.*\), '$pattern'\.\(.*\),/RTE_LOG_REGISTER_SUFFIX(\1, \2,/' $file; done $ git grep -l RTE_LOG_REGISTER lib/ | while read file; do pattern=${file##lib/}; pattern=lib.${pattern%%/*}; sed -i -e 's/RTE_LOG_REGISTER(\(.*\), '$pattern',/RTE_LOG_REGISTER_DEFAULT(\1,/' $file; sed -i -e 's/RTE_LOG_REGISTER(\(.*\), '$pattern'\.\(.*\),/RTE_LOG_REGISTER_SUFFIX(\1, \2,/' $file; done Signed-off-by: David Marchand <david.marchand@redhat.com> Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: Bruce Richardson <bruce.richardson@intel.com>
2021-04-26 12:51:08 +00:00
RTE_LOG_REGISTER_SUFFIX(iavf_logtype_rx, rx, DEBUG);
net/iavf: use dynamic log type for Tx/Rx debug The generic RTE_LOGTYPE_PMD is a historical relic and should not be used. Every driver must dynamic log types. Signed-off-by: Stephen Hemminger <stephen@networkplumber.org> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-07-16 15:40:13 +00:00
#endif
net/iavf: refine debug build option 1. replace RTE_LIBRTE_IAVF_DEBUG_RX with RTE_ETHDEV_DEBUG_RX. 2. replace RTE_LIBRTE_IAVF_DEBUG_TX with RTE_ETHDEV_DEBUG_TX. 3. merge RTE_LIBRTE_IAVF_DEBUG_TX_FREE and RTE_LIBRTE_ETHDEV_DEBUG into RTE_ETHDEV_DEBUG_TX Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2021-03-31 09:52:51 +00:00
#ifdef RTE_ETHDEV_DEBUG_TX
log: register with standardized names Let's try to enforce the convention where most drivers use a pmd. logtype with their class reflected in it, and libraries use a lib. logtype. Introduce two new macros: - RTE_LOG_REGISTER_DEFAULT can be used when a single logtype is used in a component. It is associated to the default name provided by the build system, - RTE_LOG_REGISTER_SUFFIX can be used when multiple logtypes are used, and then the passed name is appended to the default name, RTE_LOG_REGISTER is left untouched for existing external users and for components that do not comply with the convention. There is a new Meson variable log_prefix to adapt the default name for baseband (pmd.bb.), bus (no pmd.) and mempool (no pmd.) classes. Note: achieved with below commands + reverted change on net/bonding + edits on crypto/virtio, compress/mlx5, regex/mlx5 $ git grep -l RTE_LOG_REGISTER drivers/ | while read file; do pattern=${file##drivers/}; class=${pattern%%/*}; pattern=${pattern#$class/}; drv=${pattern%%/*}; case "$class" in baseband) pattern=pmd.bb.$drv;; bus) pattern=bus.$drv;; mempool) pattern=mempool.$drv;; *) pattern=pmd.$class.$drv;; esac sed -i -e 's/RTE_LOG_REGISTER(\(.*\), '$pattern',/RTE_LOG_REGISTER_DEFAULT(\1,/' $file; sed -i -e 's/RTE_LOG_REGISTER(\(.*\), '$pattern'\.\(.*\),/RTE_LOG_REGISTER_SUFFIX(\1, \2,/' $file; done $ git grep -l RTE_LOG_REGISTER lib/ | while read file; do pattern=${file##lib/}; pattern=lib.${pattern%%/*}; sed -i -e 's/RTE_LOG_REGISTER(\(.*\), '$pattern',/RTE_LOG_REGISTER_DEFAULT(\1,/' $file; sed -i -e 's/RTE_LOG_REGISTER(\(.*\), '$pattern'\.\(.*\),/RTE_LOG_REGISTER_SUFFIX(\1, \2,/' $file; done Signed-off-by: David Marchand <david.marchand@redhat.com> Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: Bruce Richardson <bruce.richardson@intel.com>
2021-04-26 12:51:08 +00:00
RTE_LOG_REGISTER_SUFFIX(iavf_logtype_tx, tx, DEBUG);
net/iavf: use dynamic log type for Tx/Rx debug The generic RTE_LOGTYPE_PMD is a historical relic and should not be used. Every driver must dynamic log types. Signed-off-by: Stephen Hemminger <stephen@networkplumber.org> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-07-16 15:40:13 +00:00
#endif
Reference in New Issue Copy Permalink