/* Broadcom NetXtreme-C/E network driver.
*
* Copyright (c) 2014-2016 Broadcom Corporation
* Copyright (c) 2016-2019 Broadcom Limited
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation.
*/
#include <linux/module.h>
#include <linux/stringify.h>
#include <linux/kernel.h>
#include <linux/timer.h>
#include <linux/errno.h>
#include <linux/ioport.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/interrupt.h>
#include <linux/pci.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/dma-mapping.h>
#include <linux/bitops.h>
#include <linux/io.h>
#include <linux/irq.h>
#include <linux/delay.h>
#include <asm /byteorder.h>
#include <asm /page.h>
#include <linux/time.h>
#include <linux/mii.h>
#include <linux/mdio.h>
#include <linux/if .h>
#include <linux/if_vlan.h>
#include <linux/if_bridge.h>
#include <linux/rtc.h>
#include <linux/bpf.h>
#include <net/gro.h>
#include <net/ip.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/checksum.h>
#include <net/ip6_checksum.h>
#include <net/udp_tunnel.h>
#include <linux/workqueue.h>
#include <linux/prefetch.h>
#include <linux/cache.h>
#include <linux/log2.h>
#include <linux/bitmap.h>
#include <linux/cpu_rmap.h>
#include <linux/cpumask.h>
#include <net/pkt_cls.h>
#include <net/page_pool/helpers.h>
#include <linux/align.h>
#include <net/netdev_lock.h>
#include <net/netdev_queues.h>
#include <net/netdev_rx_queue.h>
#include <linux/pci-tph.h>
#include <linux/bnxt/hsi.h>
#include "bnxt.h"
#include "bnxt_hwrm.h"
#include "bnxt_ulp.h"
#include "bnxt_sriov.h"
#include "bnxt_ethtool.h"
#include "bnxt_dcb.h"
#include "bnxt_xdp.h"
#include "bnxt_ptp.h"
#include "bnxt_vfr.h"
#include "bnxt_tc.h"
#include "bnxt_devlink.h"
#include "bnxt_debugfs.h"
#include "bnxt_coredump.h"
#include "bnxt_hwmon.h"
#define BNXT_TX_TIMEOUT (5 * HZ)
#define BNXT_DEF_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_HW | \
NETIF_MSG_TX_ERR)
MODULE_IMPORT_NS("NETDEV_INTERNAL" );
MODULE_LICENSE("GPL" );
MODULE_DESCRIPTION("Broadcom NetXtreme network driver" );
#define BNXT_RX_OFFSET (NET_SKB_PAD + NET_IP_ALIGN)
#define BNXT_RX_DMA_OFFSET NET_SKB_PAD
#define BNXT_TX_PUSH_THRESH 164
/* indexed by enum board_idx */
static const struct {
char *name;
} board_info[] = {
[BCM57301] = { "Broadcom BCM57301 NetXtreme-C 10Gb Ethernet" },
[BCM57302] = { "Broadcom BCM57302 NetXtreme-C 10Gb/25Gb Ethernet" },
[BCM57304] = { "Broadcom BCM57304 NetXtreme-C 10Gb/25Gb/40Gb/50Gb Ethernet" },
[BCM57417_NPAR] = { "Broadcom BCM57417 NetXtreme-E Ethernet Partition" },
[BCM58700] = { "Broadcom BCM58700 Nitro 1Gb/2.5Gb/10Gb Ethernet" },
[BCM57311] = { "Broadcom BCM57311 NetXtreme-C 10Gb Ethernet" },
[BCM57312] = { "Broadcom BCM57312 NetXtreme-C 10Gb/25Gb Ethernet" },
[BCM57402] = { "Broadcom BCM57402 NetXtreme-E 10Gb Ethernet" },
[BCM57404] = { "Broadcom BCM57404 NetXtreme-E 10Gb/25Gb Ethernet" },
[BCM57406] = { "Broadcom BCM57406 NetXtreme-E 10GBase-T Ethernet" },
[BCM57402_NPAR] = { "Broadcom BCM57402 NetXtreme-E Ethernet Partition" },
[BCM57407] = { "Broadcom BCM57407 NetXtreme-E 10GBase-T Ethernet" },
[BCM57412] = { "Broadcom BCM57412 NetXtreme-E 10Gb Ethernet" },
[BCM57414] = { "Broadcom BCM57414 NetXtreme-E 10Gb/25Gb Ethernet" },
[BCM57416] = { "Broadcom BCM57416 NetXtreme-E 10GBase-T Ethernet" },
[BCM57417] = { "Broadcom BCM57417 NetXtreme-E 10GBase-T Ethernet" },
[BCM57412_NPAR] = { "Broadcom BCM57412 NetXtreme-E Ethernet Partition" },
[BCM57314] = { "Broadcom BCM57314 NetXtreme-C 10Gb/25Gb/40Gb/50Gb Ethernet" },
[BCM57417_SFP] = { "Broadcom BCM57417 NetXtreme-E 10Gb/25Gb Ethernet" },
[BCM57416_SFP] = { "Broadcom BCM57416 NetXtreme-E 10Gb Ethernet" },
[BCM57404_NPAR] = { "Broadcom BCM57404 NetXtreme-E Ethernet Partition" },
[BCM57406_NPAR] = { "Broadcom BCM57406 NetXtreme-E Ethernet Partition" },
[BCM57407_SFP] = { "Broadcom BCM57407 NetXtreme-E 25Gb Ethernet" },
[BCM57407_NPAR] = { "Broadcom BCM57407 NetXtreme-E Ethernet Partition" },
[BCM57414_NPAR] = { "Broadcom BCM57414 NetXtreme-E Ethernet Partition" },
[BCM57416_NPAR] = { "Broadcom BCM57416 NetXtreme-E Ethernet Partition" },
[BCM57452] = { "Broadcom BCM57452 NetXtreme-E 10Gb/25Gb/40Gb/50Gb Ethernet" },
[BCM57454] = { "Broadcom BCM57454 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
[BCM5745x_NPAR] = { "Broadcom BCM5745x NetXtreme-E Ethernet Partition" },
[BCM57508] = { "Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" },
[BCM57504] = { "Broadcom BCM57504 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" },
[BCM57502] = { "Broadcom BCM57502 NetXtreme-E 10Gb/25Gb/50Gb Ethernet" },
[BCM57608] = { "Broadcom BCM57608 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb/400Gb Ethernet" },
[BCM57604] = { "Broadcom BCM57604 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" },
[BCM57602] = { "Broadcom BCM57602 NetXtreme-E 10Gb/25Gb/50Gb/100Gb Ethernet" },
[BCM57601] = { "Broadcom BCM57601 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb/400Gb Ethernet" },
[BCM57508_NPAR] = { "Broadcom BCM57508 NetXtreme-E Ethernet Partition" },
[BCM57504_NPAR] = { "Broadcom BCM57504 NetXtreme-E Ethernet Partition" },
[BCM57502_NPAR] = { "Broadcom BCM57502 NetXtreme-E Ethernet Partition" },
[BCM58802] = { "Broadcom BCM58802 NetXtreme-S 10Gb/25Gb/40Gb/50Gb Ethernet" },
[BCM58804] = { "Broadcom BCM58804 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
[BCM58808] = { "Broadcom BCM58808 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
[NETXTREME_E_VF] = { "Broadcom NetXtreme-E Ethernet Virtual Function" },
[NETXTREME_C_VF] = { "Broadcom NetXtreme-C Ethernet Virtual Function" },
[NETXTREME_S_VF] = { "Broadcom NetXtreme-S Ethernet Virtual Function" },
[NETXTREME_C_VF_HV] = { "Broadcom NetXtreme-C Virtual Function for Hyper-V" },
[NETXTREME_E_VF_HV] = { "Broadcom NetXtreme-E Virtual Function for Hyper-V" },
[NETXTREME_E_P5_VF] = { "Broadcom BCM5750X NetXtreme-E Ethernet Virtual Function" },
[NETXTREME_E_P5_VF_HV] = { "Broadcom BCM5750X NetXtreme-E Virtual Function for Hyper-V" },
[NETXTREME_E_P7_VF] = { "Broadcom BCM5760X Virtual Function" },
[NETXTREME_E_P7_VF_HV] = { "Broadcom BCM5760X Virtual Function for Hyper-V" },
};
static const struct pci_device_id bnxt_pci_tbl[] = {
{ PCI_VDEVICE(BROADCOM, 0x1604), .driver_data = BCM5745x_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x1605), .driver_data = BCM5745x_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x1614), .driver_data = BCM57454 },
{ PCI_VDEVICE(BROADCOM, 0x16c0), .driver_data = BCM57417_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x16c8), .driver_data = BCM57301 },
{ PCI_VDEVICE(BROADCOM, 0x16c9), .driver_data = BCM57302 },
{ PCI_VDEVICE(BROADCOM, 0x16ca), .driver_data = BCM57304 },
{ PCI_VDEVICE(BROADCOM, 0x16cc), .driver_data = BCM57417_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x16cd), .driver_data = BCM58700 },
{ PCI_VDEVICE(BROADCOM, 0x16ce), .driver_data = BCM57311 },
{ PCI_VDEVICE(BROADCOM, 0x16cf), .driver_data = BCM57312 },
{ PCI_VDEVICE(BROADCOM, 0x16d0), .driver_data = BCM57402 },
{ PCI_VDEVICE(BROADCOM, 0x16d1), .driver_data = BCM57404 },
{ PCI_VDEVICE(BROADCOM, 0x16d2), .driver_data = BCM57406 },
{ PCI_VDEVICE(BROADCOM, 0x16d4), .driver_data = BCM57402_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x16d5), .driver_data = BCM57407 },
{ PCI_VDEVICE(BROADCOM, 0x16d6), .driver_data = BCM57412 },
{ PCI_VDEVICE(BROADCOM, 0x16d7), .driver_data = BCM57414 },
{ PCI_VDEVICE(BROADCOM, 0x16d8), .driver_data = BCM57416 },
{ PCI_VDEVICE(BROADCOM, 0x16d9), .driver_data = BCM57417 },
{ PCI_VDEVICE(BROADCOM, 0x16de), .driver_data = BCM57412_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x16df), .driver_data = BCM57314 },
{ PCI_VDEVICE(BROADCOM, 0x16e2), .driver_data = BCM57417_SFP },
{ PCI_VDEVICE(BROADCOM, 0x16e3), .driver_data = BCM57416_SFP },
{ PCI_VDEVICE(BROADCOM, 0x16e7), .driver_data = BCM57404_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x16e8), .driver_data = BCM57406_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x16e9), .driver_data = BCM57407_SFP },
{ PCI_VDEVICE(BROADCOM, 0x16ea), .driver_data = BCM57407_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x16eb), .driver_data = BCM57412_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x16ec), .driver_data = BCM57414_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x16ed), .driver_data = BCM57414_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x16ee), .driver_data = BCM57416_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x16ef), .driver_data = BCM57416_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x16f0), .driver_data = BCM58808 },
{ PCI_VDEVICE(BROADCOM, 0x16f1), .driver_data = BCM57452 },
{ PCI_VDEVICE(BROADCOM, 0x1750), .driver_data = BCM57508 },
{ PCI_VDEVICE(BROADCOM, 0x1751), .driver_data = BCM57504 },
{ PCI_VDEVICE(BROADCOM, 0x1752), .driver_data = BCM57502 },
{ PCI_VDEVICE(BROADCOM, 0x1760), .driver_data = BCM57608 },
{ PCI_VDEVICE(BROADCOM, 0x1761), .driver_data = BCM57604 },
{ PCI_VDEVICE(BROADCOM, 0x1762), .driver_data = BCM57602 },
{ PCI_VDEVICE(BROADCOM, 0x1763), .driver_data = BCM57601 },
{ PCI_VDEVICE(BROADCOM, 0x1800), .driver_data = BCM57502_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x1801), .driver_data = BCM57504_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x1802), .driver_data = BCM57508_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x1803), .driver_data = BCM57502_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x1804), .driver_data = BCM57504_NPAR },
{ PCI_VDEVICE(BROADCOM, 0x1805), .driver_data = BCM57508_NPAR },
{ PCI_VDEVICE(BROADCOM, 0xd802), .driver_data = BCM58802 },
{ PCI_VDEVICE(BROADCOM, 0xd804), .driver_data = BCM58804 },
#ifdef CONFIG_BNXT_SRIOV
{ PCI_VDEVICE(BROADCOM, 0x1606), .driver_data = NETXTREME_E_VF },
{ PCI_VDEVICE(BROADCOM, 0x1607), .driver_data = NETXTREME_E_VF_HV },
{ PCI_VDEVICE(BROADCOM, 0x1608), .driver_data = NETXTREME_E_VF_HV },
{ PCI_VDEVICE(BROADCOM, 0x1609), .driver_data = NETXTREME_E_VF },
{ PCI_VDEVICE(BROADCOM, 0x16bd), .driver_data = NETXTREME_E_VF_HV },
{ PCI_VDEVICE(BROADCOM, 0x16c1), .driver_data = NETXTREME_E_VF },
{ PCI_VDEVICE(BROADCOM, 0x16c2), .driver_data = NETXTREME_C_VF_HV },
{ PCI_VDEVICE(BROADCOM, 0x16c3), .driver_data = NETXTREME_C_VF_HV },
{ PCI_VDEVICE(BROADCOM, 0x16c4), .driver_data = NETXTREME_E_VF_HV },
{ PCI_VDEVICE(BROADCOM, 0x16c5), .driver_data = NETXTREME_E_VF_HV },
{ PCI_VDEVICE(BROADCOM, 0x16cb), .driver_data = NETXTREME_C_VF },
{ PCI_VDEVICE(BROADCOM, 0x16d3), .driver_data = NETXTREME_E_VF },
{ PCI_VDEVICE(BROADCOM, 0x16dc), .driver_data = NETXTREME_E_VF },
{ PCI_VDEVICE(BROADCOM, 0x16e1), .driver_data = NETXTREME_C_VF },
{ PCI_VDEVICE(BROADCOM, 0x16e5), .driver_data = NETXTREME_C_VF },
{ PCI_VDEVICE(BROADCOM, 0x16e6), .driver_data = NETXTREME_C_VF_HV },
{ PCI_VDEVICE(BROADCOM, 0x1806), .driver_data = NETXTREME_E_P5_VF },
{ PCI_VDEVICE(BROADCOM, 0x1807), .driver_data = NETXTREME_E_P5_VF },
{ PCI_VDEVICE(BROADCOM, 0x1808), .driver_data = NETXTREME_E_P5_VF_HV },
{ PCI_VDEVICE(BROADCOM, 0x1809), .driver_data = NETXTREME_E_P5_VF_HV },
{ PCI_VDEVICE(BROADCOM, 0x1819), .driver_data = NETXTREME_E_P7_VF },
{ PCI_VDEVICE(BROADCOM, 0x181b), .driver_data = NETXTREME_E_P7_VF_HV },
{ PCI_VDEVICE(BROADCOM, 0xd800), .driver_data = NETXTREME_S_VF },
#endif
{ 0 }
};
MODULE_DEVICE_TABLE(pci, bnxt_pci_tbl);
static const u16 bnxt_vf_req_snif[] = {
HWRM_FUNC_CFG,
HWRM_FUNC_VF_CFG,
HWRM_PORT_PHY_QCFG,
HWRM_CFA_L2_FILTER_ALLOC,
};
static const u16 bnxt_async_events_arr[] = {
ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE,
ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CHANGE,
ASYNC_EVENT_CMPL_EVENT_ID_PF_DRVR_UNLOAD,
ASYNC_EVENT_CMPL_EVENT_ID_PORT_CONN_NOT_ALLOWED,
ASYNC_EVENT_CMPL_EVENT_ID_VF_CFG_CHANGE,
ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_CHANGE,
ASYNC_EVENT_CMPL_EVENT_ID_PORT_PHY_CFG_CHANGE,
ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY,
ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY,
ASYNC_EVENT_CMPL_EVENT_ID_DEBUG_NOTIFICATION,
ASYNC_EVENT_CMPL_EVENT_ID_DEFERRED_RESPONSE,
ASYNC_EVENT_CMPL_EVENT_ID_RING_MONITOR_MSG,
ASYNC_EVENT_CMPL_EVENT_ID_ECHO_REQUEST,
ASYNC_EVENT_CMPL_EVENT_ID_PPS_TIMESTAMP,
ASYNC_EVENT_CMPL_EVENT_ID_ERROR_REPORT,
ASYNC_EVENT_CMPL_EVENT_ID_PHC_UPDATE,
ASYNC_EVENT_CMPL_EVENT_ID_DBG_BUF_PRODUCER,
};
const u16 bnxt_bstore_to_trace[] = {
[BNXT_CTX_SRT] = DBG_LOG_BUFFER_FLUSH_REQ_TYPE_SRT_TRACE,
[BNXT_CTX_SRT2] = DBG_LOG_BUFFER_FLUSH_REQ_TYPE_SRT2_TRACE,
[BNXT_CTX_CRT] = DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CRT_TRACE,
[BNXT_CTX_CRT2] = DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CRT2_TRACE,
[BNXT_CTX_RIGP0] = DBG_LOG_BUFFER_FLUSH_REQ_TYPE_RIGP0_TRACE,
[BNXT_CTX_L2HWRM] = DBG_LOG_BUFFER_FLUSH_REQ_TYPE_L2_HWRM_TRACE,
[BNXT_CTX_REHWRM] = DBG_LOG_BUFFER_FLUSH_REQ_TYPE_ROCE_HWRM_TRACE,
[BNXT_CTX_CA0] = DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CA0_TRACE,
[BNXT_CTX_CA1] = DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CA1_TRACE,
[BNXT_CTX_CA2] = DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CA2_TRACE,
[BNXT_CTX_RIGP1] = DBG_LOG_BUFFER_FLUSH_REQ_TYPE_RIGP1_TRACE,
[BNXT_CTX_KONG] = DBG_LOG_BUFFER_FLUSH_REQ_TYPE_AFM_KONG_HWRM_TRACE,
};
static struct workqueue_struct *bnxt_pf_wq;
#define BNXT_IPV6_MASK_ALL {{{ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, \
0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }}}
#define BNXT_IPV6_MASK_NONE {{{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }}}
const struct bnxt_flow_masks BNXT_FLOW_MASK_NONE = {
.ports = {
.src = 0,
.dst = 0,
},
.addrs = {
.v6addrs = {
.src = BNXT_IPV6_MASK_NONE,
.dst = BNXT_IPV6_MASK_NONE,
},
},
};
const struct bnxt_flow_masks BNXT_FLOW_IPV6_MASK_ALL = {
.ports = {
.src = cpu_to_be16(0xffff),
.dst = cpu_to_be16(0xffff),
},
.addrs = {
.v6addrs = {
.src = BNXT_IPV6_MASK_ALL,
.dst = BNXT_IPV6_MASK_ALL,
},
},
};
const struct bnxt_flow_masks BNXT_FLOW_IPV4_MASK_ALL = {
.ports = {
.src = cpu_to_be16(0xffff),
.dst = cpu_to_be16(0xffff),
},
.addrs = {
.v4addrs = {
.src = cpu_to_be32(0xffffffff),
.dst = cpu_to_be32(0xffffffff),
},
},
};
static bool bnxt_vf_pciid(enum board_idx idx)
{
return (idx == NETXTREME_C_VF || idx == NETXTREME_E_VF ||
idx == NETXTREME_S_VF || idx == NETXTREME_C_VF_HV ||
idx == NETXTREME_E_VF_HV || idx == NETXTREME_E_P5_VF ||
idx == NETXTREME_E_P5_VF_HV || idx == NETXTREME_E_P7_VF ||
idx == NETXTREME_E_P7_VF_HV);
}
#define DB_CP_REARM_FLAGS (DB_KEY_CP | DB_IDX_VALID)
#define DB_CP_FLAGS (DB_KEY_CP | DB_IDX_VALID | DB_IRQ_DIS)
#define BNXT_DB_CQ(db, idx) \
writel(DB_CP_FLAGS | DB_RING_IDX(db, idx), (db)->doorbell)
#define BNXT_DB_NQ_P5(db, idx) \
bnxt_writeq(bp, (db)->db_key64 | DBR_TYPE_NQ | DB_RING_IDX(db, idx),\
(db)->doorbell)
#define BNXT_DB_NQ_P7(db, idx) \
bnxt_writeq(bp, (db)->db_key64 | DBR_TYPE_NQ_MASK | \
DB_RING_IDX(db, idx), (db)->doorbell)
#define BNXT_DB_CQ_ARM(db, idx) \
writel(DB_CP_REARM_FLAGS | DB_RING_IDX(db, idx), (db)->doorbell)
#define BNXT_DB_NQ_ARM_P5(db, idx) \
bnxt_writeq(bp, (db)->db_key64 | DBR_TYPE_NQ_ARM | \
DB_RING_IDX(db, idx), (db)->doorbell)
static void bnxt_db_nq(struct bnxt *bp, struct bnxt_db_info *db, u32 idx)
{
if (bp->flags & BNXT_FLAG_CHIP_P7)
BNXT_DB_NQ_P7(db, idx);
else if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
BNXT_DB_NQ_P5(db, idx);
else
BNXT_DB_CQ(db, idx);
}
static void bnxt_db_nq_arm(struct bnxt *bp, struct bnxt_db_info *db, u32 idx)
{
if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
BNXT_DB_NQ_ARM_P5(db, idx);
else
BNXT_DB_CQ_ARM(db, idx);
}
static void bnxt_db_cq(struct bnxt *bp, struct bnxt_db_info *db, u32 idx)
{
if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
bnxt_writeq(bp, db->db_key64 | DBR_TYPE_CQ_ARMALL |
DB_RING_IDX(db, idx), db->doorbell);
else
BNXT_DB_CQ(db, idx);
}
static void bnxt_queue_fw_reset_work(struct bnxt *bp, unsigned long delay)
{
if (!(test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)))
return ;
if (BNXT_PF(bp))
queue_delayed_work(bnxt_pf_wq, &bp->fw_reset_task, delay);
else
schedule_delayed_work(&bp->fw_reset_task, delay);
}
static void __bnxt_queue_sp_work(struct bnxt *bp)
{
if (BNXT_PF(bp))
queue_work(bnxt_pf_wq, &bp->sp_task);
else
schedule_work(&bp->sp_task);
}
static void bnxt_queue_sp_work(struct bnxt *bp, unsigned int event)
{
set_bit(event, &bp->sp_event);
__bnxt_queue_sp_work(bp);
}
static void bnxt_sched_reset_rxr(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
{
if (!rxr->bnapi->in_reset) {
rxr->bnapi->in_reset = true ;
if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
set_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event);
else
set_bit(BNXT_RST_RING_SP_EVENT, &bp->sp_event);
__bnxt_queue_sp_work(bp);
}
rxr->rx_next_cons = 0xffff;
}
void bnxt_sched_reset_txr(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
u16 curr)
{
struct bnxt_napi *bnapi = txr->bnapi;
if (bnapi->tx_fault)
return ;
netdev_err(bp->dev, "Invalid Tx completion (ring:%d tx_hw_cons:%u cons:%u prod:%u curr:%u)" ,
txr->txq_index, txr->tx_hw_cons,
txr->tx_cons, txr->tx_prod, curr);
WARN_ON_ONCE(1);
bnapi->tx_fault = 1;
bnxt_queue_sp_work(bp, BNXT_RESET_TASK_SP_EVENT);
}
const u16 bnxt_lhint_arr[] = {
TX_BD_FLAGS_LHINT_512_AND_SMALLER,
TX_BD_FLAGS_LHINT_512_TO_1023,
TX_BD_FLAGS_LHINT_1024_TO_2047,
TX_BD_FLAGS_LHINT_1024_TO_2047,
TX_BD_FLAGS_LHINT_2048_AND_LARGER,
TX_BD_FLAGS_LHINT_2048_AND_LARGER,
TX_BD_FLAGS_LHINT_2048_AND_LARGER,
TX_BD_FLAGS_LHINT_2048_AND_LARGER,
TX_BD_FLAGS_LHINT_2048_AND_LARGER,
TX_BD_FLAGS_LHINT_2048_AND_LARGER,
TX_BD_FLAGS_LHINT_2048_AND_LARGER,
TX_BD_FLAGS_LHINT_2048_AND_LARGER,
TX_BD_FLAGS_LHINT_2048_AND_LARGER,
TX_BD_FLAGS_LHINT_2048_AND_LARGER,
TX_BD_FLAGS_LHINT_2048_AND_LARGER,
TX_BD_FLAGS_LHINT_2048_AND_LARGER,
TX_BD_FLAGS_LHINT_2048_AND_LARGER,
TX_BD_FLAGS_LHINT_2048_AND_LARGER,
TX_BD_FLAGS_LHINT_2048_AND_LARGER,
};
static u16 bnxt_xmit_get_cfa_action(struct sk_buff *skb)
{
struct metadata_dst *md_dst = skb_metadata_dst(skb);
if (!md_dst || md_dst->type != METADATA_HW_PORT_MUX)
return 0;
return md_dst->u.port_info.port_id;
}
static void bnxt_txr_db_kick(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
u16 prod)
{
/* Sync BD data before updating doorbell */
wmb();
bnxt_db_write(bp, &txr->tx_db, prod);
txr->kick_pending = 0;
}
static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct bnxt *bp = netdev_priv(dev);
struct tx_bd *txbd, *txbd0;
struct tx_bd_ext *txbd1;
struct netdev_queue *txq;
int i;
dma_addr_t mapping;
unsigned int length, pad = 0;
u32 len, free_size, vlan_tag_flags, cfa_action, flags;
struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
struct pci_dev *pdev = bp->pdev;
u16 prod, last_frag, txts_prod;
struct bnxt_tx_ring_info *txr;
struct bnxt_sw_tx_bd *tx_buf;
__le32 lflags = 0;
skb_frag_t *frag;
i = skb_get_queue_mapping(skb);
if (unlikely(i >= bp->tx_nr_rings)) {
dev_kfree_skb_any(skb);
dev_core_stats_tx_dropped_inc(dev);
return NETDEV_TX_OK;
}
txq = netdev_get_tx_queue(dev, i);
txr = &bp->tx_ring[bp->tx_ring_map[i]];
prod = txr->tx_prod;
#if (MAX_SKB_FRAGS > TX_MAX_FRAGS)
if (skb_shinfo(skb)->nr_frags > TX_MAX_FRAGS) {
netdev_warn_once(dev, "SKB has too many (%d) fragments, max supported is %d. SKB will be linearized.\n" ,
skb_shinfo(skb)->nr_frags, TX_MAX_FRAGS);
if (skb_linearize(skb)) {
dev_kfree_skb_any(skb);
dev_core_stats_tx_dropped_inc(dev);
return NETDEV_TX_OK;
}
}
#endif
free_size = bnxt_tx_avail(bp, txr);
if (unlikely(free_size < skb_shinfo(skb)->nr_frags + 2)) {
/* We must have raced with NAPI cleanup */
if (net_ratelimit() && txr->kick_pending)
netif_warn(bp, tx_err, dev,
"bnxt: ring busy w/ flush pending!\n" );
if (!netif_txq_try_stop(txq, bnxt_tx_avail(bp, txr),
bp->tx_wake_thresh))
return NETDEV_TX_BUSY;
}
if (unlikely(ipv6_hopopt_jumbo_remove(skb)))
goto tx_free;
length = skb->len;
len = skb_headlen(skb);
last_frag = skb_shinfo(skb)->nr_frags;
txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
tx_buf->skb = skb;
tx_buf->nr_frags = last_frag;
vlan_tag_flags = 0;
cfa_action = bnxt_xmit_get_cfa_action(skb);
if (skb_vlan_tag_present(skb)) {
vlan_tag_flags = TX_BD_CFA_META_KEY_VLAN |
skb_vlan_tag_get(skb);
/* Currently supports 8021Q, 8021AD vlan offloads
* QINQ1, QINQ2, QINQ3 vlan headers are deprecated
*/
if (skb->vlan_proto == htons(ETH_P_8021Q))
vlan_tag_flags |= 1 << TX_BD_CFA_META_TPID_SHIFT;
}
if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && ptp &&
ptp->tx_tstamp_en) {
if (bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP) {
lflags |= cpu_to_le32(TX_BD_FLAGS_STAMP);
tx_buf->is_ts_pkt = 1;
skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
} else if (!skb_is_gso(skb)) {
u16 seq_id, hdr_off;
if (!bnxt_ptp_parse(skb, &seq_id, &hdr_off) &&
!bnxt_ptp_get_txts_prod(ptp, &txts_prod)) {
if (vlan_tag_flags)
hdr_off += VLAN_HLEN;
lflags |= cpu_to_le32(TX_BD_FLAGS_STAMP);
tx_buf->is_ts_pkt = 1;
skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
ptp->txts_req[txts_prod].tx_seqid = seq_id;
ptp->txts_req[txts_prod].tx_hdr_off = hdr_off;
tx_buf->txts_prod = txts_prod;
}
}
}
if (unlikely(skb->no_fcs))
lflags |= cpu_to_le32(TX_BD_FLAGS_NO_CRC);
if (free_size == bp->tx_ring_size && length <= bp->tx_push_thresh &&
skb_frags_readable(skb) && !lflags) {
struct tx_push_buffer *tx_push_buf = txr->tx_push;
struct tx_push_bd *tx_push = &tx_push_buf->push_bd;
struct tx_bd_ext *tx_push1 = &tx_push->txbd2;
void __iomem *db = txr->tx_db.doorbell;
void *pdata = tx_push_buf->data;
u64 *end;
int j, push_len;
/* Set COAL_NOW to be ready quickly for the next push */
tx_push->tx_bd_len_flags_type =
cpu_to_le32((length << TX_BD_LEN_SHIFT) |
TX_BD_TYPE_LONG_TX_BD |
TX_BD_FLAGS_LHINT_512_AND_SMALLER |
TX_BD_FLAGS_COAL_NOW |
TX_BD_FLAGS_PACKET_END |
TX_BD_CNT(2));
if (skb->ip_summed == CHECKSUM_PARTIAL)
tx_push1->tx_bd_hsize_lflags =
cpu_to_le32(TX_BD_FLAGS_TCP_UDP_CHKSUM);
else
tx_push1->tx_bd_hsize_lflags = 0;
tx_push1->tx_bd_cfa_meta = cpu_to_le32(vlan_tag_flags);
tx_push1->tx_bd_cfa_action =
cpu_to_le32(cfa_action << TX_BD_CFA_ACTION_SHIFT);
end = pdata + length;
end = PTR_ALIGN(end, 8) - 1;
*end = 0;
skb_copy_from_linear_data(skb, pdata, len);
pdata += len;
for (j = 0; j < last_frag; j++) {
void *fptr;
frag = &skb_shinfo(skb)->frags[j];
fptr = skb_frag_address_safe(frag);
if (!fptr)
goto normal_tx;
memcpy(pdata, fptr, skb_frag_size(frag));
pdata += skb_frag_size(frag);
}
txbd->tx_bd_len_flags_type = tx_push->tx_bd_len_flags_type;
txbd->tx_bd_haddr = txr->data_mapping;
txbd->tx_bd_opaque = SET_TX_OPAQUE(bp, txr, prod, 2);
prod = NEXT_TX(prod);
tx_push->tx_bd_opaque = txbd->tx_bd_opaque;
txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
memcpy(txbd, tx_push1, sizeof (*txbd));
prod = NEXT_TX(prod);
tx_push->doorbell =
cpu_to_le32(DB_KEY_TX_PUSH | DB_LONG_TX_PUSH |
DB_RING_IDX(&txr->tx_db, prod));
WRITE_ONCE(txr->tx_prod, prod);
tx_buf->is_push = 1;
netdev_tx_sent_queue(txq, skb->len);
wmb(); /* Sync is_push and byte queue before pushing data */
push_len = (length + sizeof (*tx_push) + 7) / 8;
if (push_len > 16) {
__iowrite64_copy(db, tx_push_buf, 16);
__iowrite32_copy(db + 4, tx_push_buf + 1,
(push_len - 16) << 1);
} else {
__iowrite64_copy(db, tx_push_buf, push_len);
}
goto tx_done;
}
normal_tx:
if (length < BNXT_MIN_PKT_SIZE) {
pad = BNXT_MIN_PKT_SIZE - length;
if (skb_pad(skb, pad))
/* SKB already freed. */
goto tx_kick_pending;
length = BNXT_MIN_PKT_SIZE;
}
mapping = dma_map_single(&pdev->dev, skb->data, len, DMA_TO_DEVICE);
if (unlikely(dma_mapping_error(&pdev->dev, mapping)))
goto tx_free;
dma_unmap_addr_set(tx_buf, mapping, mapping);
flags = (len << TX_BD_LEN_SHIFT) | TX_BD_TYPE_LONG_TX_BD |
TX_BD_CNT(last_frag + 2);
txbd->tx_bd_haddr = cpu_to_le64(mapping);
txbd->tx_bd_opaque = SET_TX_OPAQUE(bp, txr, prod, 2 + last_frag);
prod = NEXT_TX(prod);
txbd1 = (struct tx_bd_ext *)
&txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
txbd1->tx_bd_hsize_lflags = lflags;
if (skb_is_gso(skb)) {
bool udp_gso = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4);
u32 hdr_len;
if (skb->encapsulation) {
if (udp_gso)
hdr_len = skb_inner_transport_offset(skb) +
sizeof (struct udphdr);
else
hdr_len = skb_inner_tcp_all_headers(skb);
} else if (udp_gso) {
hdr_len = skb_transport_offset(skb) +
sizeof (struct udphdr);
} else {
hdr_len = skb_tcp_all_headers(skb);
}
txbd1->tx_bd_hsize_lflags |= cpu_to_le32(TX_BD_FLAGS_LSO |
TX_BD_FLAGS_T_IPID |
(hdr_len << (TX_BD_HSIZE_SHIFT - 1)));
length = skb_shinfo(skb)->gso_size;
txbd1->tx_bd_mss = cpu_to_le32(length);
length += hdr_len;
} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
txbd1->tx_bd_hsize_lflags |=
cpu_to_le32(TX_BD_FLAGS_TCP_UDP_CHKSUM);
txbd1->tx_bd_mss = 0;
}
length >>= 9;
if (unlikely(length >= ARRAY_SIZE(bnxt_lhint_arr))) {
dev_warn_ratelimited(&pdev->dev, "Dropped oversize %d bytes TX packet.\n" ,
skb->len);
i = 0;
goto tx_dma_error;
}
flags |= bnxt_lhint_arr[length];
txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
txbd1->tx_bd_cfa_meta = cpu_to_le32(vlan_tag_flags);
txbd1->tx_bd_cfa_action =
cpu_to_le32(cfa_action << TX_BD_CFA_ACTION_SHIFT);
txbd0 = txbd;
for (i = 0; i < last_frag; i++) {
frag = &skb_shinfo(skb)->frags[i];
prod = NEXT_TX(prod);
txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
len = skb_frag_size(frag);
mapping = skb_frag_dma_map(&pdev->dev, frag, 0, len,
DMA_TO_DEVICE);
if (unlikely(dma_mapping_error(&pdev->dev, mapping)))
goto tx_dma_error;
tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
netmem_dma_unmap_addr_set(skb_frag_netmem(frag), tx_buf,
mapping, mapping);
txbd->tx_bd_haddr = cpu_to_le64(mapping);
flags = len << TX_BD_LEN_SHIFT;
txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
}
flags &= ~TX_BD_LEN;
txbd->tx_bd_len_flags_type =
cpu_to_le32(((len + pad) << TX_BD_LEN_SHIFT) | flags |
TX_BD_FLAGS_PACKET_END);
netdev_tx_sent_queue(txq, skb->len);
skb_tx_timestamp(skb);
prod = NEXT_TX(prod);
WRITE_ONCE(txr->tx_prod, prod);
if (!netdev_xmit_more() || netif_xmit_stopped(txq)) {
bnxt_txr_db_kick(bp, txr, prod);
} else {
if (free_size >= bp->tx_wake_thresh)
txbd0->tx_bd_len_flags_type |=
cpu_to_le32(TX_BD_FLAGS_NO_CMPL);
txr->kick_pending = 1;
}
tx_done:
if (unlikely(bnxt_tx_avail(bp, txr) <= MAX_SKB_FRAGS + 1)) {
if (netdev_xmit_more() && !tx_buf->is_push) {
txbd0->tx_bd_len_flags_type &=
cpu_to_le32(~TX_BD_FLAGS_NO_CMPL);
bnxt_txr_db_kick(bp, txr, prod);
}
netif_txq_try_stop(txq, bnxt_tx_avail(bp, txr),
bp->tx_wake_thresh);
}
return NETDEV_TX_OK;
tx_dma_error:
last_frag = i;
/* start back at beginning and unmap skb */
prod = txr->tx_prod;
tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
dma_unmap_single(&pdev->dev, dma_unmap_addr(tx_buf, mapping),
skb_headlen(skb), DMA_TO_DEVICE);
prod = NEXT_TX(prod);
/* unmap remaining mapped pages */
for (i = 0; i < last_frag; i++) {
prod = NEXT_TX(prod);
tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
frag = &skb_shinfo(skb)->frags[i];
netmem_dma_unmap_page_attrs(&pdev->dev,
dma_unmap_addr(tx_buf, mapping),
skb_frag_size(frag),
DMA_TO_DEVICE, 0);
}
tx_free:
dev_kfree_skb_any(skb);
tx_kick_pending:
if (BNXT_TX_PTP_IS_SET(lflags)) {
txr->tx_buf_ring[RING_TX(bp, txr->tx_prod)].is_ts_pkt = 0;
atomic64_inc(&bp->ptp_cfg->stats.ts_err);
if (!(bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP))
/* set SKB to err so PTP worker will clean up */
ptp->txts_req[txts_prod].tx_skb = ERR_PTR(-EIO);
}
if (txr->kick_pending)
bnxt_txr_db_kick(bp, txr, txr->tx_prod);
txr->tx_buf_ring[RING_TX(bp, txr->tx_prod)].skb = NULL;
dev_core_stats_tx_dropped_inc(dev);
return NETDEV_TX_OK;
}
/* Returns true if some remaining TX packets not processed. */
static bool __bnxt_tx_int(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
int budget)
{
struct netdev_queue *txq = netdev_get_tx_queue(bp->dev, txr->txq_index);
struct pci_dev *pdev = bp->pdev;
u16 hw_cons = txr->tx_hw_cons;
unsigned int tx_bytes = 0;
u16 cons = txr->tx_cons;
skb_frag_t *frag;
int tx_pkts = 0;
bool rc = false ;
while (RING_TX(bp, cons) != hw_cons) {
struct bnxt_sw_tx_bd *tx_buf;
struct sk_buff *skb;
bool is_ts_pkt;
int j, last;
tx_buf = &txr->tx_buf_ring[RING_TX(bp, cons)];
skb = tx_buf->skb;
if (unlikely(!skb)) {
bnxt_sched_reset_txr(bp, txr, cons);
return rc;
}
is_ts_pkt = tx_buf->is_ts_pkt;
if (is_ts_pkt && (bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP)) {
rc = true ;
break ;
}
cons = NEXT_TX(cons);
tx_pkts++;
tx_bytes += skb->len;
tx_buf->skb = NULL;
tx_buf->is_ts_pkt = 0;
if (tx_buf->is_push) {
tx_buf->is_push = 0;
goto next_tx_int;
}
dma_unmap_single(&pdev->dev, dma_unmap_addr(tx_buf, mapping),
skb_headlen(skb), DMA_TO_DEVICE);
last = tx_buf->nr_frags;
for (j = 0; j < last; j++) {
frag = &skb_shinfo(skb)->frags[j];
cons = NEXT_TX(cons);
tx_buf = &txr->tx_buf_ring[RING_TX(bp, cons)];
netmem_dma_unmap_page_attrs(&pdev->dev,
dma_unmap_addr(tx_buf,
mapping),
skb_frag_size(frag),
DMA_TO_DEVICE, 0);
}
if (unlikely(is_ts_pkt)) {
if (BNXT_CHIP_P5(bp)) {
/* PTP worker takes ownership of the skb */
bnxt_get_tx_ts_p5(bp, skb, tx_buf->txts_prod);
skb = NULL;
}
}
next_tx_int:
cons = NEXT_TX(cons);
dev_consume_skb_any(skb);
}
WRITE_ONCE(txr->tx_cons, cons);
__netif_txq_completed_wake(txq, tx_pkts, tx_bytes,
bnxt_tx_avail(bp, txr), bp->tx_wake_thresh,
READ_ONCE(txr->dev_state) == BNXT_DEV_STATE_CLOSING);
return rc;
}
static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
{
struct bnxt_tx_ring_info *txr;
bool more = false ;
int i;
bnxt_for_each_napi_tx(i, bnapi, txr) {
if (txr->tx_hw_cons != RING_TX(bp, txr->tx_cons))
more |= __bnxt_tx_int(bp, txr, budget);
}
if (!more)
bnapi->events &= ~BNXT_TX_CMP_EVENT;
}
static bool bnxt_separate_head_pool(struct bnxt_rx_ring_info *rxr)
{
return rxr->need_head_pool || PAGE_SIZE > BNXT_RX_PAGE_SIZE;
}
static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
struct bnxt_rx_ring_info *rxr,
unsigned int *offset,
gfp_t gfp)
{
struct page *page;
if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) {
page = page_pool_dev_alloc_frag(rxr->page_pool, offset,
BNXT_RX_PAGE_SIZE);
} else {
page = page_pool_dev_alloc_pages(rxr->page_pool);
*offset = 0;
}
if (!page)
return NULL;
*mapping = page_pool_get_dma_addr(page) + *offset;
return page;
}
static netmem_ref __bnxt_alloc_rx_netmem(struct bnxt *bp, dma_addr_t *mapping,
struct bnxt_rx_ring_info *rxr,
unsigned int *offset,
gfp_t gfp)
{
netmem_ref netmem;
if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) {
netmem = page_pool_alloc_frag_netmem(rxr->page_pool, offset, BNXT_RX_PAGE_SIZE, gfp);
} else {
netmem = page_pool_alloc_netmems(rxr->page_pool, gfp);
*offset = 0;
}
if (!netmem)
return 0;
*mapping = page_pool_get_dma_addr_netmem(netmem) + *offset;
return netmem;
}
static inline u8 *__bnxt_alloc_rx_frag(struct bnxt *bp, dma_addr_t *mapping,
struct bnxt_rx_ring_info *rxr,
gfp_t gfp)
{
unsigned int offset;
struct page *page;
page = page_pool_alloc_frag(rxr->head_pool, &offset,
bp->rx_buf_size, gfp);
if (!page)
return NULL;
*mapping = page_pool_get_dma_addr(page) + bp->rx_dma_offset + offset;
return page_address(page) + offset;
}
int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
u16 prod, gfp_t gfp)
{
struct rx_bd *rxbd = &rxr->rx_desc_ring[RX_RING(bp, prod)][RX_IDX(prod)];
struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[RING_RX(bp, prod)];
dma_addr_t mapping;
if (BNXT_RX_PAGE_MODE(bp)) {
unsigned int offset;
struct page *page =
__bnxt_alloc_rx_page(bp, &mapping, rxr, &offset, gfp);
if (!page)
return -ENOMEM;
mapping += bp->rx_dma_offset;
rx_buf->data = page;
rx_buf->data_ptr = page_address(page) + offset + bp->rx_offset;
} else {
u8 *data = __bnxt_alloc_rx_frag(bp, &mapping, rxr, gfp);
if (!data)
return -ENOMEM;
rx_buf->data = data;
rx_buf->data_ptr = data + bp->rx_offset;
}
rx_buf->mapping = mapping;
rxbd->rx_bd_haddr = cpu_to_le64(mapping);
return 0;
}
void bnxt_reuse_rx_data(struct bnxt_rx_ring_info *rxr, u16 cons, void *data)
{
u16 prod = rxr->rx_prod;
struct bnxt_sw_rx_bd *cons_rx_buf, *prod_rx_buf;
struct bnxt *bp = rxr->bnapi->bp;
struct rx_bd *cons_bd, *prod_bd;
prod_rx_buf = &rxr->rx_buf_ring[RING_RX(bp, prod)];
cons_rx_buf = &rxr->rx_buf_ring[cons];
prod_rx_buf->data = data;
prod_rx_buf->data_ptr = cons_rx_buf->data_ptr;
prod_rx_buf->mapping = cons_rx_buf->mapping;
prod_bd = &rxr->rx_desc_ring[RX_RING(bp, prod)][RX_IDX(prod)];
cons_bd = &rxr->rx_desc_ring[RX_RING(bp, cons)][RX_IDX(cons)];
prod_bd->rx_bd_haddr = cons_bd->rx_bd_haddr;
}
static inline u16 bnxt_find_next_agg_idx(struct bnxt_rx_ring_info *rxr, u16 idx)
{
u16 next, max = rxr->rx_agg_bmap_size;
next = find_next_zero_bit(rxr->rx_agg_bmap, max, idx);
if (next >= max)
next = find_first_zero_bit(rxr->rx_agg_bmap, max);
return next;
}
static int bnxt_alloc_rx_netmem(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
u16 prod, gfp_t gfp)
{
struct rx_bd *rxbd =
&rxr->rx_agg_desc_ring[RX_AGG_RING(bp, prod)][RX_IDX(prod)];
struct bnxt_sw_rx_agg_bd *rx_agg_buf;
u16 sw_prod = rxr->rx_sw_agg_prod;
unsigned int offset = 0;
dma_addr_t mapping;
netmem_ref netmem;
netmem = __bnxt_alloc_rx_netmem(bp, &mapping, rxr, &offset, gfp);
if (!netmem)
return -ENOMEM;
if (unlikely(test_bit(sw_prod, rxr->rx_agg_bmap)))
sw_prod = bnxt_find_next_agg_idx(rxr, sw_prod);
__set_bit(sw_prod, rxr->rx_agg_bmap);
rx_agg_buf = &rxr->rx_agg_ring[sw_prod];
rxr->rx_sw_agg_prod = RING_RX_AGG(bp, NEXT_RX_AGG(sw_prod));
rx_agg_buf->netmem = netmem;
rx_agg_buf->offset = offset;
rx_agg_buf->mapping = mapping;
rxbd->rx_bd_haddr = cpu_to_le64(mapping);
rxbd->rx_bd_opaque = sw_prod;
return 0;
}
static struct rx_agg_cmp *bnxt_get_agg(struct bnxt *bp,
struct bnxt_cp_ring_info *cpr,
u16 cp_cons, u16 curr)
{
struct rx_agg_cmp *agg;
cp_cons = RING_CMP(ADV_RAW_CMP(cp_cons, curr));
agg = (struct rx_agg_cmp *)
&cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)];
return agg;
}
static struct rx_agg_cmp *bnxt_get_tpa_agg_p5(struct bnxt *bp,
struct bnxt_rx_ring_info *rxr,
u16 agg_id, u16 curr)
{
struct bnxt_tpa_info *tpa_info = &rxr->rx_tpa[agg_id];
return &tpa_info->agg_arr[curr];
}
static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx,
u16 start, u32 agg_bufs, bool tpa)
{
struct bnxt_napi *bnapi = cpr->bnapi;
struct bnxt *bp = bnapi->bp;
struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
u16 prod = rxr->rx_agg_prod;
u16 sw_prod = rxr->rx_sw_agg_prod;
bool p5_tpa = false ;
u32 i;
if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) && tpa)
p5_tpa = true ;
for (i = 0; i < agg_bufs; i++) {
struct bnxt_sw_rx_agg_bd *cons_rx_buf, *prod_rx_buf;
struct rx_agg_cmp *agg;
struct rx_bd *prod_bd;
netmem_ref netmem;
u16 cons;
if (p5_tpa)
agg = bnxt_get_tpa_agg_p5(bp, rxr, idx, start + i);
else
agg = bnxt_get_agg(bp, cpr, idx, start + i);
cons = agg->rx_agg_cmp_opaque;
__clear_bit(cons, rxr->rx_agg_bmap);
if (unlikely(test_bit(sw_prod, rxr->rx_agg_bmap)))
sw_prod = bnxt_find_next_agg_idx(rxr, sw_prod);
__set_bit(sw_prod, rxr->rx_agg_bmap);
prod_rx_buf = &rxr->rx_agg_ring[sw_prod];
cons_rx_buf = &rxr->rx_agg_ring[cons];
/* It is possible for sw_prod to be equal to cons, so
* set cons_rx_buf->netmem to 0 first.
*/
netmem = cons_rx_buf->netmem;
cons_rx_buf->netmem = 0;
prod_rx_buf->netmem = netmem;
prod_rx_buf->offset = cons_rx_buf->offset;
prod_rx_buf->mapping = cons_rx_buf->mapping;
prod_bd = &rxr->rx_agg_desc_ring[RX_AGG_RING(bp, prod)][RX_IDX(prod)];
prod_bd->rx_bd_haddr = cpu_to_le64(cons_rx_buf->mapping);
prod_bd->rx_bd_opaque = sw_prod;
prod = NEXT_RX_AGG(prod);
sw_prod = RING_RX_AGG(bp, NEXT_RX_AGG(sw_prod));
}
rxr->rx_agg_prod = prod;
rxr->rx_sw_agg_prod = sw_prod;
}
static struct sk_buff *bnxt_rx_multi_page_skb(struct bnxt *bp,
struct bnxt_rx_ring_info *rxr,
u16 cons, void *data, u8 *data_ptr,
dma_addr_t dma_addr,
unsigned int offset_and_len)
{
unsigned int len = offset_and_len & 0xffff;
struct page *page = data;
u16 prod = rxr->rx_prod;
struct sk_buff *skb;
int err;
err = bnxt_alloc_rx_data(bp, rxr, prod, GFP_ATOMIC);
if (unlikely(err)) {
bnxt_reuse_rx_data(rxr, cons, data);
return NULL;
}
dma_addr -= bp->rx_dma_offset;
dma_sync_single_for_cpu(&bp->pdev->dev, dma_addr, BNXT_RX_PAGE_SIZE,
bp->rx_dir);
skb = napi_build_skb(data_ptr - bp->rx_offset, BNXT_RX_PAGE_SIZE);
if (!skb) {
page_pool_recycle_direct(rxr->page_pool, page);
return NULL;
}
skb_mark_for_recycle(skb);
skb_reserve(skb, bp->rx_offset);
__skb_put(skb, len);
return skb;
}
static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp,
struct bnxt_rx_ring_info *rxr,
u16 cons, void *data, u8 *data_ptr,
dma_addr_t dma_addr,
unsigned int offset_and_len)
{
unsigned int payload = offset_and_len >> 16;
unsigned int len = offset_and_len & 0xffff;
skb_frag_t *frag;
struct page *page = data;
u16 prod = rxr->rx_prod;
struct sk_buff *skb;
int off, err;
err = bnxt_alloc_rx_data(bp, rxr, prod, GFP_ATOMIC);
if (unlikely(err)) {
bnxt_reuse_rx_data(rxr, cons, data);
return NULL;
}
dma_addr -= bp->rx_dma_offset;
dma_sync_single_for_cpu(&bp->pdev->dev, dma_addr, BNXT_RX_PAGE_SIZE,
bp->rx_dir);
if (unlikely(!payload))
payload = eth_get_headlen(bp->dev, data_ptr, len);
skb = napi_alloc_skb(&rxr->bnapi->napi, payload);
if (!skb) {
page_pool_recycle_direct(rxr->page_pool, page);
return NULL;
}
skb_mark_for_recycle(skb);
off = (void *)data_ptr - page_address(page);
skb_add_rx_frag(skb, 0, page, off, len, BNXT_RX_PAGE_SIZE);
memcpy(skb->data - NET_IP_ALIGN, data_ptr - NET_IP_ALIGN,
payload + NET_IP_ALIGN);
frag = &skb_shinfo(skb)->frags[0];
skb_frag_size_sub(frag, payload);
skb_frag_off_add(frag, payload);
skb->data_len -= payload;
skb->tail += payload;
return skb;
}
static struct sk_buff *bnxt_rx_skb(struct bnxt *bp,
struct bnxt_rx_ring_info *rxr, u16 cons,
void *data, u8 *data_ptr,
dma_addr_t dma_addr,
unsigned int offset_and_len)
{
u16 prod = rxr->rx_prod;
struct sk_buff *skb;
int err;
err = bnxt_alloc_rx_data(bp, rxr, prod, GFP_ATOMIC);
if (unlikely(err)) {
bnxt_reuse_rx_data(rxr, cons, data);
return NULL;
}
skb = napi_build_skb(data, bp->rx_buf_size);
dma_sync_single_for_cpu(&bp->pdev->dev, dma_addr, bp->rx_buf_use_size,
bp->rx_dir);
if (!skb) {
page_pool_free_va(rxr->head_pool, data, true );
return NULL;
}
skb_mark_for_recycle(skb);
skb_reserve(skb, bp->rx_offset);
skb_put(skb, offset_and_len & 0xffff);
return skb;
}
static u32 __bnxt_rx_agg_netmems(struct bnxt *bp,
struct bnxt_cp_ring_info *cpr,
u16 idx, u32 agg_bufs, bool tpa,
struct sk_buff *skb,
struct xdp_buff *xdp)
{
struct bnxt_napi *bnapi = cpr->bnapi;
struct skb_shared_info *shinfo;
struct bnxt_rx_ring_info *rxr;
u32 i, total_frag_len = 0;
bool p5_tpa = false ;
u16 prod;
rxr = bnapi->rx_ring;
prod = rxr->rx_agg_prod;
if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) && tpa)
p5_tpa = true ;
if (skb)
shinfo = skb_shinfo(skb);
else
shinfo = xdp_get_shared_info_from_buff(xdp);
for (i = 0; i < agg_bufs; i++) {
struct bnxt_sw_rx_agg_bd *cons_rx_buf;
struct rx_agg_cmp *agg;
u16 cons, frag_len;
netmem_ref netmem;
if (p5_tpa)
agg = bnxt_get_tpa_agg_p5(bp, rxr, idx, i);
else
agg = bnxt_get_agg(bp, cpr, idx, i);
cons = agg->rx_agg_cmp_opaque;
frag_len = (le32_to_cpu(agg->rx_agg_cmp_len_flags_type) &
RX_AGG_CMP_LEN) >> RX_AGG_CMP_LEN_SHIFT;
cons_rx_buf = &rxr->rx_agg_ring[cons];
if (skb) {
skb_add_rx_frag_netmem(skb, i, cons_rx_buf->netmem,
cons_rx_buf->offset,
frag_len, BNXT_RX_PAGE_SIZE);
} else {
skb_frag_t *frag = &shinfo->frags[i];
skb_frag_fill_netmem_desc(frag, cons_rx_buf->netmem,
cons_rx_buf->offset,
frag_len);
shinfo->nr_frags = i + 1;
}
__clear_bit(cons, rxr->rx_agg_bmap);
/* It is possible for bnxt_alloc_rx_netmem() to allocate
* a sw_prod index that equals the cons index, so we
* need to clear the cons entry now.
*/
netmem = cons_rx_buf->netmem;
cons_rx_buf->netmem = 0;
if (xdp && netmem_is_pfmemalloc(netmem))
xdp_buff_set_frag_pfmemalloc(xdp);
if (bnxt_alloc_rx_netmem(bp, rxr, prod, GFP_ATOMIC) != 0) {
if (skb) {
skb->len -= frag_len;
skb->data_len -= frag_len;
skb->truesize -= BNXT_RX_PAGE_SIZE;
}
--shinfo->nr_frags;
cons_rx_buf->netmem = netmem;
/* Update prod since possibly some netmems have been
* allocated already.
*/
rxr->rx_agg_prod = prod;
bnxt_reuse_rx_agg_bufs(cpr, idx, i, agg_bufs - i, tpa);
return 0;
}
page_pool_dma_sync_netmem_for_cpu(rxr->page_pool, netmem, 0,
BNXT_RX_PAGE_SIZE);
total_frag_len += frag_len;
prod = NEXT_RX_AGG(prod);
}
rxr->rx_agg_prod = prod;
return total_frag_len;
}
static struct sk_buff *bnxt_rx_agg_netmems_skb(struct bnxt *bp,
struct bnxt_cp_ring_info *cpr,
struct sk_buff *skb, u16 idx,
u32 agg_bufs, bool tpa)
{
u32 total_frag_len = 0;
total_frag_len = __bnxt_rx_agg_netmems(bp, cpr, idx, agg_bufs, tpa,
skb, NULL);
if (!total_frag_len) {
skb_mark_for_recycle(skb);
dev_kfree_skb(skb);
return NULL;
}
return skb;
}
static u32 bnxt_rx_agg_netmems_xdp(struct bnxt *bp,
struct bnxt_cp_ring_info *cpr,
struct xdp_buff *xdp, u16 idx,
u32 agg_bufs, bool tpa)
{
struct skb_shared_info *shinfo = xdp_get_shared_info_from_buff(xdp);
u32 total_frag_len = 0;
if (!xdp_buff_has_frags(xdp))
shinfo->nr_frags = 0;
total_frag_len = __bnxt_rx_agg_netmems(bp, cpr, idx, agg_bufs, tpa,
NULL, xdp);
if (total_frag_len) {
xdp_buff_set_frags_flag(xdp);
shinfo->nr_frags = agg_bufs;
shinfo->xdp_frags_size = total_frag_len;
}
return total_frag_len;
}
static int bnxt_agg_bufs_valid(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
u8 agg_bufs, u32 *raw_cons)
{
u16 last;
struct rx_agg_cmp *agg;
*raw_cons = ADV_RAW_CMP(*raw_cons, agg_bufs);
last = RING_CMP(*raw_cons);
agg = (struct rx_agg_cmp *)
&cpr->cp_desc_ring[CP_RING(last)][CP_IDX(last)];
return RX_AGG_CMP_VALID(agg, *raw_cons);
}
static struct sk_buff *bnxt_copy_data(struct bnxt_napi *bnapi, u8 *data,
unsigned int len,
dma_addr_t mapping)
{
struct bnxt *bp = bnapi->bp;
struct pci_dev *pdev = bp->pdev;
struct sk_buff *skb;
skb = napi_alloc_skb(&bnapi->napi, len);
if (!skb)
return NULL;
dma_sync_single_for_cpu(&pdev->dev, mapping, bp->rx_copybreak,
bp->rx_dir);
memcpy(skb->data - NET_IP_ALIGN, data - NET_IP_ALIGN,
len + NET_IP_ALIGN);
dma_sync_single_for_device(&pdev->dev, mapping, bp->rx_copybreak,
bp->rx_dir);
skb_put(skb, len);
return skb;
}
static struct sk_buff *bnxt_copy_skb(struct bnxt_napi *bnapi, u8 *data,
unsigned int len,
dma_addr_t mapping)
{
return bnxt_copy_data(bnapi, data, len, mapping);
}
static struct sk_buff *bnxt_copy_xdp(struct bnxt_napi *bnapi,
struct xdp_buff *xdp,
unsigned int len,
dma_addr_t mapping)
{
unsigned int metasize = 0;
u8 *data = xdp->data;
struct sk_buff *skb;
len = xdp->data_end - xdp->data_meta;
metasize = xdp->data - xdp->data_meta;
data = xdp->data_meta;
skb = bnxt_copy_data(bnapi, data, len, mapping);
if (!skb)
return skb;
if (metasize) {
skb_metadata_set(skb, metasize);
__skb_pull(skb, metasize);
}
return skb;
}
static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
u32 *raw_cons, void *cmp)
{
struct rx_cmp *rxcmp = cmp;
u32 tmp_raw_cons = *raw_cons;
u8 cmp_type, agg_bufs = 0;
cmp_type = RX_CMP_TYPE(rxcmp);
if (cmp_type == CMP_TYPE_RX_L2_CMP) {
agg_bufs = (le32_to_cpu(rxcmp->rx_cmp_misc_v1) &
RX_CMP_AGG_BUFS) >>
RX_CMP_AGG_BUFS_SHIFT;
} else if (cmp_type == CMP_TYPE_RX_L2_TPA_END_CMP) {
struct rx_tpa_end_cmp *tpa_end = cmp;
if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
return 0;
agg_bufs = TPA_END_AGG_BUFS(tpa_end);
}
if (agg_bufs) {
if (!bnxt_agg_bufs_valid(bp, cpr, agg_bufs, &tmp_raw_cons))
return -EBUSY;
}
*raw_cons = tmp_raw_cons;
return 0;
}
static u16 bnxt_alloc_agg_idx(struct bnxt_rx_ring_info *rxr, u16 agg_id)
{
struct bnxt_tpa_idx_map *map = rxr->rx_tpa_idx_map;
u16 idx = agg_id & MAX_TPA_P5_MASK;
if (test_bit(idx, map->agg_idx_bmap))
idx = find_first_zero_bit(map->agg_idx_bmap,
BNXT_AGG_IDX_BMAP_SIZE);
__set_bit(idx, map->agg_idx_bmap);
map->agg_id_tbl[agg_id] = idx;
return idx;
}
static void bnxt_free_agg_idx(struct bnxt_rx_ring_info *rxr, u16 idx)
{
struct bnxt_tpa_idx_map *map = rxr->rx_tpa_idx_map;
__clear_bit(idx, map->agg_idx_bmap);
}
static u16 bnxt_lookup_agg_idx(struct bnxt_rx_ring_info *rxr, u16 agg_id)
{
struct bnxt_tpa_idx_map *map = rxr->rx_tpa_idx_map;
return map->agg_id_tbl[agg_id];
}
static void bnxt_tpa_metadata(struct bnxt_tpa_info *tpa_info,
struct rx_tpa_start_cmp *tpa_start,
struct rx_tpa_start_cmp_ext *tpa_start1)
{
tpa_info->cfa_code_valid = 1;
tpa_info->cfa_code = TPA_START_CFA_CODE(tpa_start1);
tpa_info->vlan_valid = 0;
if (tpa_info->flags2 & RX_CMP_FLAGS2_META_FORMAT_VLAN) {
tpa_info->vlan_valid = 1;
tpa_info->metadata =
le32_to_cpu(tpa_start1->rx_tpa_start_cmp_metadata);
}
}
static void bnxt_tpa_metadata_v2(struct bnxt_tpa_info *tpa_info,
struct rx_tpa_start_cmp *tpa_start,
struct rx_tpa_start_cmp_ext *tpa_start1)
{
tpa_info->vlan_valid = 0;
if (TPA_START_VLAN_VALID(tpa_start)) {
u32 tpid_sel = TPA_START_VLAN_TPID_SEL(tpa_start);
u32 vlan_proto = ETH_P_8021Q;
tpa_info->vlan_valid = 1;
if (tpid_sel == RX_TPA_START_METADATA1_TPID_8021AD)
vlan_proto = ETH_P_8021AD;
tpa_info->metadata = vlan_proto << 16 |
TPA_START_METADATA0_TCI(tpa_start1);
}
}
static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
u8 cmp_type, struct rx_tpa_start_cmp *tpa_start,
struct rx_tpa_start_cmp_ext *tpa_start1)
{
struct bnxt_sw_rx_bd *cons_rx_buf, *prod_rx_buf;
struct bnxt_tpa_info *tpa_info;
u16 cons, prod, agg_id;
struct rx_bd *prod_bd;
dma_addr_t mapping;
if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
agg_id = TPA_START_AGG_ID_P5(tpa_start);
agg_id = bnxt_alloc_agg_idx(rxr, agg_id);
} else {
agg_id = TPA_START_AGG_ID(tpa_start);
}
cons = tpa_start->rx_tpa_start_cmp_opaque;
prod = rxr->rx_prod;
cons_rx_buf = &rxr->rx_buf_ring[cons];
prod_rx_buf = &rxr->rx_buf_ring[RING_RX(bp, prod)];
tpa_info = &rxr->rx_tpa[agg_id];
if (unlikely(cons != rxr->rx_next_cons ||
TPA_START_ERROR(tpa_start))) {
netdev_warn(bp->dev, "TPA cons %x, expected cons %x, error code %x\n" ,
cons, rxr->rx_next_cons,
TPA_START_ERROR_CODE(tpa_start1));
bnxt_sched_reset_rxr(bp, rxr);
return ;
}
prod_rx_buf->data = tpa_info->data;
prod_rx_buf->data_ptr = tpa_info->data_ptr;
mapping = tpa_info->mapping;
prod_rx_buf->mapping = mapping;
prod_bd = &rxr->rx_desc_ring[RX_RING(bp, prod)][RX_IDX(prod)];
prod_bd->rx_bd_haddr = cpu_to_le64(mapping);
tpa_info->data = cons_rx_buf->data;
tpa_info->data_ptr = cons_rx_buf->data_ptr;
cons_rx_buf->data = NULL;
tpa_info->mapping = cons_rx_buf->mapping;
tpa_info->len =
le32_to_cpu(tpa_start->rx_tpa_start_cmp_len_flags_type) >>
RX_TPA_START_CMP_LEN_SHIFT;
if (likely(TPA_START_HASH_VALID(tpa_start))) {
tpa_info->hash_type = PKT_HASH_TYPE_L4;
tpa_info->gso_type = SKB_GSO_TCPV4;
if (TPA_START_IS_IPV6(tpa_start1))
tpa_info->gso_type = SKB_GSO_TCPV6;
/* RSS profiles 1 and 3 with extract code 0 for inner 4-tuple */
else if (!BNXT_CHIP_P4_PLUS(bp) &&
TPA_START_HASH_TYPE(tpa_start) == 3)
tpa_info->gso_type = SKB_GSO_TCPV6;
tpa_info->rss_hash =
le32_to_cpu(tpa_start->rx_tpa_start_cmp_rss_hash);
} else {
tpa_info->hash_type = PKT_HASH_TYPE_NONE;
tpa_info->gso_type = 0;
netif_warn(bp, rx_err, bp->dev, "TPA packet without valid hash\n" );
}
tpa_info->flags2 = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_flags2);
tpa_info->hdr_info = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_hdr_info);
if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP)
bnxt_tpa_metadata(tpa_info, tpa_start, tpa_start1);
else
bnxt_tpa_metadata_v2(tpa_info, tpa_start, tpa_start1);
tpa_info->agg_count = 0;
rxr->rx_prod = NEXT_RX(prod);
cons = RING_RX(bp, NEXT_RX(cons));
rxr->rx_next_cons = RING_RX(bp, NEXT_RX(cons));
cons_rx_buf = &rxr->rx_buf_ring[cons];
bnxt_reuse_rx_data(rxr, cons, cons_rx_buf->data);
rxr->rx_prod = NEXT_RX(rxr->rx_prod);
cons_rx_buf->data = NULL;
}
static void bnxt_abort_tpa(struct bnxt_cp_ring_info *cpr, u16 idx, u32 agg_bufs)
{
if (agg_bufs)
bnxt_reuse_rx_agg_bufs(cpr, idx, 0, agg_bufs, true );
}
#ifdef CONFIG_INET
static void bnxt_gro_tunnel(struct sk_buff *skb, __be16 ip_proto)
{
struct udphdr *uh = NULL;
if (ip_proto == htons(ETH_P_IP)) {
struct iphdr *iph = (struct iphdr *)skb->data;
if (iph->protocol == IPPROTO_UDP)
uh = (struct udphdr *)(iph + 1);
} else {
struct ipv6hdr *iph = (struct ipv6hdr *)skb->data;
if (iph->nexthdr == IPPROTO_UDP)
uh = (struct udphdr *)(iph + 1);
}
if (uh) {
if (uh->check)
skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
else
skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
}
}
#endif
static struct sk_buff *bnxt_gro_func_5731x(struct bnxt_tpa_info *tpa_info,
int payload_off, int tcp_ts,
struct sk_buff *skb)
{
#ifdef CONFIG_INET
struct tcphdr *th;
int len, nw_off;
u16 outer_ip_off, inner_ip_off, inner_mac_off;
u32 hdr_info = tpa_info->hdr_info;
bool loopback = false ;
inner_ip_off = BNXT_TPA_INNER_L3_OFF(hdr_info);
inner_mac_off = BNXT_TPA_INNER_L2_OFF(hdr_info);
outer_ip_off = BNXT_TPA_OUTER_L3_OFF(hdr_info);
/* If the packet is an internal loopback packet, the offsets will
* have an extra 4 bytes.
*/
if (inner_mac_off == 4) {
loopback = true ;
} else if (inner_mac_off > 4) {
__be16 proto = *((__be16 *)(skb->data + inner_ip_off -
ETH_HLEN - 2));
/* We only support inner iPv4/ipv6. If we don't see the
* correct protocol ID, it must be a loopback packet where
* the offsets are off by 4.
*/
if (proto != htons(ETH_P_IP) && proto != htons(ETH_P_IPV6))
loopback = true ;
}
if (loopback) {
/* internal loopback packet, subtract all offsets by 4 */
inner_ip_off -= 4;
inner_mac_off -= 4;
outer_ip_off -= 4;
}
nw_off = inner_ip_off - ETH_HLEN;
skb_set_network_header(skb, nw_off);
if (tpa_info->flags2 & RX_TPA_START_CMP_FLAGS2_IP_TYPE) {
struct ipv6hdr *iph = ipv6_hdr(skb);
skb_set_transport_header(skb, nw_off + sizeof (struct ipv6hdr));
len = skb->len - skb_transport_offset(skb);
th = tcp_hdr(skb);
th->check = ~tcp_v6_check(len, &iph->saddr, &iph->daddr, 0);
} else {
struct iphdr *iph = ip_hdr(skb);
skb_set_transport_header(skb, nw_off + sizeof (struct iphdr));
len = skb->len - skb_transport_offset(skb);
th = tcp_hdr(skb);
th->check = ~tcp_v4_check(len, iph->saddr, iph->daddr, 0);
}
if (inner_mac_off) { /* tunnel */
__be16 proto = *((__be16 *)(skb->data + outer_ip_off -
ETH_HLEN - 2));
bnxt_gro_tunnel(skb, proto);
}
#endif
return skb;
}
static struct sk_buff *bnxt_gro_func_5750x(struct bnxt_tpa_info *tpa_info,
int payload_off, int tcp_ts,
struct sk_buff *skb)
{
#ifdef CONFIG_INET
u16 outer_ip_off, inner_ip_off, inner_mac_off;
u32 hdr_info = tpa_info->hdr_info;
int iphdr_len, nw_off;
inner_ip_off = BNXT_TPA_INNER_L3_OFF(hdr_info);
inner_mac_off = BNXT_TPA_INNER_L2_OFF(hdr_info);
outer_ip_off = BNXT_TPA_OUTER_L3_OFF(hdr_info);
nw_off = inner_ip_off - ETH_HLEN;
skb_set_network_header(skb, nw_off);
iphdr_len = (tpa_info->flags2 & RX_TPA_START_CMP_FLAGS2_IP_TYPE) ?
sizeof (struct ipv6hdr) : sizeof (struct iphdr);
skb_set_transport_header(skb, nw_off + iphdr_len);
if (inner_mac_off) { /* tunnel */
__be16 proto = *((__be16 *)(skb->data + outer_ip_off -
ETH_HLEN - 2));
bnxt_gro_tunnel(skb, proto);
}
#endif
return skb;
}
#define BNXT_IPV4_HDR_SIZE (sizeof (struct iphdr) + sizeof (struct tcphdr))
#define BNXT_IPV6_HDR_SIZE (sizeof (struct ipv6hdr) + sizeof (struct tcphdr))
static struct sk_buff *bnxt_gro_func_5730x(struct bnxt_tpa_info *tpa_info,
int payload_off, int tcp_ts,
struct sk_buff *skb)
{
#ifdef CONFIG_INET
struct tcphdr *th;
int len, nw_off, tcp_opt_len = 0;
if (tcp_ts)
tcp_opt_len = 12;
if (tpa_info->gso_type == SKB_GSO_TCPV4) {
struct iphdr *iph;
nw_off = payload_off - BNXT_IPV4_HDR_SIZE - tcp_opt_len -
ETH_HLEN;
skb_set_network_header(skb, nw_off);
iph = ip_hdr(skb);
skb_set_transport_header(skb, nw_off + sizeof (struct iphdr));
len = skb->len - skb_transport_offset(skb);
th = tcp_hdr(skb);
th->check = ~tcp_v4_check(len, iph->saddr, iph->daddr, 0);
} else if (tpa_info->gso_type == SKB_GSO_TCPV6) {
struct ipv6hdr *iph;
nw_off = payload_off - BNXT_IPV6_HDR_SIZE - tcp_opt_len -
ETH_HLEN;
skb_set_network_header(skb, nw_off);
iph = ipv6_hdr(skb);
skb_set_transport_header(skb, nw_off + sizeof (struct ipv6hdr));
len = skb->len - skb_transport_offset(skb);
th = tcp_hdr(skb);
th->check = ~tcp_v6_check(len, &iph->saddr, &iph->daddr, 0);
} else {
dev_kfree_skb_any(skb);
return NULL;
}
if (nw_off) /* tunnel */
bnxt_gro_tunnel(skb, skb->protocol);
#endif
return skb;
}
static inline struct sk_buff *bnxt_gro_skb(struct bnxt *bp,
struct bnxt_tpa_info *tpa_info,
struct rx_tpa_end_cmp *tpa_end,
struct rx_tpa_end_cmp_ext *tpa_end1,
struct sk_buff *skb)
{
#ifdef CONFIG_INET
int payload_off;
u16 segs;
segs = TPA_END_TPA_SEGS(tpa_end);
if (segs == 1)
return skb;
NAPI_GRO_CB(skb)->count = segs;
skb_shinfo(skb)->gso_size =
le32_to_cpu(tpa_end1->rx_tpa_end_cmp_seg_len);
skb_shinfo(skb)->gso_type = tpa_info->gso_type;
if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
payload_off = TPA_END_PAYLOAD_OFF_P5(tpa_end1);
else
payload_off = TPA_END_PAYLOAD_OFF(tpa_end);
skb = bp->gro_func(tpa_info, payload_off, TPA_END_GRO_TS(tpa_end), skb);
if (likely(skb))
tcp_gro_complete(skb);
#endif
return skb;
}
/* Given the cfa_code of a received packet determine which
* netdev (vf-rep or PF) the packet is destined to.
*/
static struct net_device *bnxt_get_pkt_dev(struct bnxt *bp, u16 cfa_code)
{
struct net_device *dev = bnxt_get_vf_rep(bp, cfa_code);
/* if vf-rep dev is NULL, it must belong to the PF */
return dev ? dev : bp->dev;
}
static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
struct bnxt_cp_ring_info *cpr,
u32 *raw_cons,
struct rx_tpa_end_cmp *tpa_end,
struct rx_tpa_end_cmp_ext *tpa_end1,
u8 *event)
{
struct bnxt_napi *bnapi = cpr->bnapi;
struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
struct net_device *dev = bp->dev;
u8 *data_ptr, agg_bufs;
unsigned int len;
struct bnxt_tpa_info *tpa_info;
dma_addr_t mapping;
struct sk_buff *skb;
u16 idx = 0, agg_id;
void *data;
bool gro;
if (unlikely(bnapi->in_reset)) {
int rc = bnxt_discard_rx(bp, cpr, raw_cons, tpa_end);
if (rc < 0)
return ERR_PTR(-EBUSY);
return NULL;
}
if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
agg_id = TPA_END_AGG_ID_P5(tpa_end);
agg_id = bnxt_lookup_agg_idx(rxr, agg_id);
agg_bufs = TPA_END_AGG_BUFS_P5(tpa_end1);
tpa_info = &rxr->rx_tpa[agg_id];
if (unlikely(agg_bufs != tpa_info->agg_count)) {
netdev_warn(bp->dev, "TPA end agg_buf %d != expected agg_bufs %d\n" ,
agg_bufs, tpa_info->agg_count);
agg_bufs = tpa_info->agg_count;
}
tpa_info->agg_count = 0;
*event |= BNXT_AGG_EVENT;
bnxt_free_agg_idx(rxr, agg_id);
idx = agg_id;
gro = !!(bp->flags & BNXT_FLAG_GRO);
} else {
agg_id = TPA_END_AGG_ID(tpa_end);
agg_bufs = TPA_END_AGG_BUFS(tpa_end);
tpa_info = &rxr->rx_tpa[agg_id];
idx = RING_CMP(*raw_cons);
if (agg_bufs) {
if (!bnxt_agg_bufs_valid(bp, cpr, agg_bufs, raw_cons))
return ERR_PTR(-EBUSY);
*event |= BNXT_AGG_EVENT;
idx = NEXT_CMP(idx);
}
gro = !!TPA_END_GRO(tpa_end);
}
data = tpa_info->data;
data_ptr = tpa_info->data_ptr;
prefetch(data_ptr);
len = tpa_info->len;
mapping = tpa_info->mapping;
if (unlikely(agg_bufs > MAX_SKB_FRAGS || TPA_END_ERRORS(tpa_end1))) {
bnxt_abort_tpa(cpr, idx, agg_bufs);
if (agg_bufs > MAX_SKB_FRAGS)
netdev_warn(bp->dev, "TPA frags %d exceeded MAX_SKB_FRAGS %d\n" ,
agg_bufs, (int )MAX_SKB_FRAGS);
return NULL;
}
if (len <= bp->rx_copybreak) {
skb = bnxt_copy_skb(bnapi, data_ptr, len, mapping);
if (!skb) {
bnxt_abort_tpa(cpr, idx, agg_bufs);
cpr->sw_stats->rx.rx_oom_discards += 1;
return NULL;
}
} else {
u8 *new_data;
dma_addr_t new_mapping;
new_data = __bnxt_alloc_rx_frag(bp, &new_mapping, rxr,
GFP_ATOMIC);
if (!new_data) {
bnxt_abort_tpa(cpr, idx, agg_bufs);
cpr->sw_stats->rx.rx_oom_discards += 1;
return NULL;
}
tpa_info->data = new_data;
tpa_info->data_ptr = new_data + bp->rx_offset;
tpa_info->mapping = new_mapping;
skb = napi_build_skb(data, bp->rx_buf_size);
dma_sync_single_for_cpu(&bp->pdev->dev, mapping,
bp->rx_buf_use_size, bp->rx_dir);
if (!skb) {
page_pool_free_va(rxr->head_pool, data, true );
bnxt_abort_tpa(cpr, idx, agg_bufs);
cpr->sw_stats->rx.rx_oom_discards += 1;
return NULL;
}
skb_mark_for_recycle(skb);
skb_reserve(skb, bp->rx_offset);
skb_put(skb, len);
}
if (agg_bufs) {
skb = bnxt_rx_agg_netmems_skb(bp, cpr, skb, idx, agg_bufs,
true );
if (!skb) {
/* Page reuse already handled by bnxt_rx_pages(). */
cpr->sw_stats->rx.rx_oom_discards += 1;
return NULL;
}
}
if (tpa_info->cfa_code_valid)
dev = bnxt_get_pkt_dev(bp, tpa_info->cfa_code);
skb->protocol = eth_type_trans(skb, dev);
if (tpa_info->hash_type != PKT_HASH_TYPE_NONE)
skb_set_hash(skb, tpa_info->rss_hash, tpa_info->hash_type);
if (tpa_info->vlan_valid &&
(dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) {
__be16 vlan_proto = htons(tpa_info->metadata >>
RX_CMP_FLAGS2_METADATA_TPID_SFT);
u16 vtag = tpa_info->metadata & RX_CMP_FLAGS2_METADATA_TCI_MASK;
if (eth_type_vlan(vlan_proto)) {
__vlan_hwaccel_put_tag(skb, vlan_proto, vtag);
} else {
dev_kfree_skb(skb);
return NULL;
}
}
skb_checksum_none_assert(skb);
if (likely(tpa_info->flags2 & RX_TPA_START_CMP_FLAGS2_L4_CS_CALC)) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
skb->csum_level =
(tpa_info->flags2 & RX_CMP_FLAGS2_T_L4_CS_CALC) >> 3;
}
if (gro)
skb = bnxt_gro_skb(bp, tpa_info, tpa_end, tpa_end1, skb);
return skb;
}
static void bnxt_tpa_agg(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
struct rx_agg_cmp *rx_agg)
{
u16 agg_id = TPA_AGG_AGG_ID(rx_agg);
struct bnxt_tpa_info *tpa_info;
agg_id = bnxt_lookup_agg_idx(rxr, agg_id);
tpa_info = &rxr->rx_tpa[agg_id];
BUG_ON(tpa_info->agg_count >= MAX_SKB_FRAGS);
tpa_info->agg_arr[tpa_info->agg_count++] = *rx_agg;
}
static void bnxt_deliver_skb(struct bnxt *bp, struct bnxt_napi *bnapi,
struct sk_buff *skb)
{
skb_mark_for_recycle(skb);
if (skb->dev != bp->dev) {
/* this packet belongs to a vf-rep */
bnxt_vf_rep_rx(bp, skb);
return ;
}
skb_record_rx_queue(skb, bnapi->index);
napi_gro_receive(&bnapi->napi, skb);
}
static bool bnxt_rx_ts_valid(struct bnxt *bp, u32 flags,
struct rx_cmp_ext *rxcmp1, u32 *cmpl_ts)
{
u32 ts = le32_to_cpu(rxcmp1->rx_cmp_timestamp);
if (BNXT_PTP_RX_TS_VALID(flags))
goto ts_valid;
if (!bp->ptp_all_rx_tstamp || !ts || !BNXT_ALL_RX_TS_VALID(flags))
return false ;
ts_valid:
*cmpl_ts = ts;
return true ;
}
static struct sk_buff *bnxt_rx_vlan(struct sk_buff *skb, u8 cmp_type,
struct rx_cmp *rxcmp,
struct rx_cmp_ext *rxcmp1)
{
__be16 vlan_proto;
u16 vtag;
if (cmp_type == CMP_TYPE_RX_L2_CMP) {
__le32 flags2 = rxcmp1->rx_cmp_flags2;
u32 meta_data;
if (!(flags2 & cpu_to_le32(RX_CMP_FLAGS2_META_FORMAT_VLAN)))
return skb;
meta_data = le32_to_cpu(rxcmp1->rx_cmp_meta_data);
vtag = meta_data & RX_CMP_FLAGS2_METADATA_TCI_MASK;
vlan_proto = htons(meta_data >> RX_CMP_FLAGS2_METADATA_TPID_SFT);
if (eth_type_vlan(vlan_proto))
__vlan_hwaccel_put_tag(skb, vlan_proto, vtag);
else
goto vlan_err;
} else if (cmp_type == CMP_TYPE_RX_L2_V3_CMP) {
if (RX_CMP_VLAN_VALID(rxcmp)) {
u32 tpid_sel = RX_CMP_VLAN_TPID_SEL(rxcmp);
if (tpid_sel == RX_CMP_METADATA1_TPID_8021Q)
vlan_proto = htons(ETH_P_8021Q);
else if (tpid_sel == RX_CMP_METADATA1_TPID_8021AD)
vlan_proto = htons(ETH_P_8021AD);
else
goto vlan_err;
vtag = RX_CMP_METADATA0_TCI(rxcmp1);
__vlan_hwaccel_put_tag(skb, vlan_proto, vtag);
}
}
return skb;
vlan_err:
skb_mark_for_recycle(skb);
dev_kfree_skb(skb);
return NULL;
}
static enum pkt_hash_types bnxt_rss_ext_op(struct bnxt *bp,
struct rx_cmp *rxcmp)
{
u8 ext_op;
ext_op = RX_CMP_V3_HASH_TYPE(bp, rxcmp);
switch (ext_op) {
case EXT_OP_INNER_4:
case EXT_OP_OUTER_4:
case EXT_OP_INNFL_3:
case EXT_OP_OUTFL_3:
return PKT_HASH_TYPE_L4;
default :
return PKT_HASH_TYPE_L3;
}
}
/* returns the following:
* 1 - 1 packet successfully received
* 0 - successful TPA_START, packet not completed yet
* -EBUSY - completion ring does not have all the agg buffers yet
* -ENOMEM - packet aborted due to out of memory
* -EIO - packet aborted due to hw error indicated in BD
*/
static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
u32 *raw_cons, u8 *event)
{
struct bnxt_napi *bnapi = cpr->bnapi;
struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
struct net_device *dev = bp->dev;
struct rx_cmp *rxcmp;
struct rx_cmp_ext *rxcmp1;
u32 tmp_raw_cons = *raw_cons;
u16 cons, prod, cp_cons = RING_CMP(tmp_raw_cons);
struct skb_shared_info *sinfo;
struct bnxt_sw_rx_bd *rx_buf;
unsigned int len;
u8 *data_ptr, agg_bufs, cmp_type;
bool xdp_active = false ;
dma_addr_t dma_addr;
struct sk_buff *skb;
struct xdp_buff xdp;
u32 flags, misc;
u32 cmpl_ts;
void *data;
int rc = 0;
rxcmp = (struct rx_cmp *)
&cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)];
cmp_type = RX_CMP_TYPE(rxcmp);
if (cmp_type == CMP_TYPE_RX_TPA_AGG_CMP) {
bnxt_tpa_agg(bp, rxr, (struct rx_agg_cmp *)rxcmp);
goto next_rx_no_prod_no_len;
}
tmp_raw_cons = NEXT_RAW_CMP(tmp_raw_cons);
cp_cons = RING_CMP(tmp_raw_cons);
rxcmp1 = (struct rx_cmp_ext *)
&cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)];
if (!RX_CMP_VALID(rxcmp1, tmp_raw_cons))
return -EBUSY;
/* The valid test of the entry must be done first before
* reading any further.
*/
dma_rmb();
prod = rxr->rx_prod;
if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP ||
cmp_type == CMP_TYPE_RX_L2_TPA_START_V3_CMP) {
bnxt_tpa_start(bp, rxr, cmp_type,
(struct rx_tpa_start_cmp *)rxcmp,
(struct rx_tpa_start_cmp_ext *)rxcmp1);
*event |= BNXT_RX_EVENT;
goto next_rx_no_prod_no_len;
} else if (cmp_type == CMP_TYPE_RX_L2_TPA_END_CMP) {
skb = bnxt_tpa_end(bp, cpr, &tmp_raw_cons,
(struct rx_tpa_end_cmp *)rxcmp,
(struct rx_tpa_end_cmp_ext *)rxcmp1, event);
if (IS_ERR(skb))
return -EBUSY;
rc = -ENOMEM;
if (likely(skb)) {
bnxt_deliver_skb(bp, bnapi, skb);
rc = 1;
}
*event |= BNXT_RX_EVENT;
goto next_rx_no_prod_no_len;
}
cons = rxcmp->rx_cmp_opaque;
if (unlikely(cons != rxr->rx_next_cons)) {
int rc1 = bnxt_discard_rx(bp, cpr, &tmp_raw_cons, rxcmp);
/* 0xffff is forced error, don't print it */
if (rxr->rx_next_cons != 0xffff)
netdev_warn(bp->dev, "RX cons %x != expected cons %x\n" ,
cons, rxr->rx_next_cons);
bnxt_sched_reset_rxr(bp, rxr);
if (rc1)
return rc1;
goto next_rx_no_prod_no_len;
}
rx_buf = &rxr->rx_buf_ring[cons];
data = rx_buf->data;
data_ptr = rx_buf->data_ptr;
prefetch(data_ptr);
misc = le32_to_cpu(rxcmp->rx_cmp_misc_v1);
agg_bufs = (misc & RX_CMP_AGG_BUFS) >> RX_CMP_AGG_BUFS_SHIFT;
if (agg_bufs) {
if (!bnxt_agg_bufs_valid(bp, cpr, agg_bufs, &tmp_raw_cons))
return -EBUSY;
cp_cons = NEXT_CMP(cp_cons);
*event |= BNXT_AGG_EVENT;
}
*event |= BNXT_RX_EVENT;
rx_buf->data = NULL;
if (rxcmp1->rx_cmp_cfa_code_errors_v2 & RX_CMP_L2_ERRORS) {
u32 rx_err = le32_to_cpu(rxcmp1->rx_cmp_cfa_code_errors_v2);
bnxt_reuse_rx_data(rxr, cons, data);
if (agg_bufs)
bnxt_reuse_rx_agg_bufs(cpr, cp_cons, 0, agg_bufs,
false );
rc = -EIO;
if (rx_err & RX_CMPL_ERRORS_BUFFER_ERROR_MASK) {
bnapi->cp_ring.sw_stats->rx.rx_buf_errors++;
if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS) &&
!(bp->fw_cap & BNXT_FW_CAP_RING_MONITOR)) {
netdev_warn_once(bp->dev, "RX buffer error %x\n" ,
rx_err);
bnxt_sched_reset_rxr(bp, rxr);
}
}
goto next_rx_no_len;
}
flags = le32_to_cpu(rxcmp->rx_cmp_len_flags_type);
len = flags >> RX_CMP_LEN_SHIFT;
--> --------------------
--> maximum size reached
--> --------------------
Messung V0.5 C=97 H=91 G=93
¤ Dauer der Verarbeitung: 0.24 Sekunden
(vorverarbeitet)
¤
*© Formatika GbR, Deutschland