3955 lines
101 KiB
C
3955 lines
101 KiB
C
/****************************************************************************
|
|
* Driver for Solarflare network controllers and boards
|
|
* Copyright 2005-2006 Fen Systems Ltd.
|
|
* Copyright 2005-2013 Solarflare Communications Inc.
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
* under the terms of the GNU General Public License version 2 as published
|
|
* by the Free Software Foundation, incorporated herein by reference.
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/pci.h>
|
|
#include <linux/netdevice.h>
|
|
#include <linux/etherdevice.h>
|
|
#include <linux/delay.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/ip.h>
|
|
#include <linux/tcp.h>
|
|
#include <linux/in.h>
|
|
#include <linux/ethtool.h>
|
|
#include <linux/topology.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/aer.h>
|
|
#include <linux/interrupt.h>
|
|
#include "net_driver.h"
|
|
#include <net/gre.h>
|
|
#include <net/udp_tunnel.h>
|
|
#include "efx.h"
|
|
#include "nic.h"
|
|
#include "io.h"
|
|
#include "selftest.h"
|
|
#include "sriov.h"
|
|
|
|
#include "mcdi.h"
|
|
#include "mcdi_pcol.h"
|
|
#include "workarounds.h"
|
|
|
|
/**************************************************************************
|
|
*
|
|
* Type name strings
|
|
*
|
|
**************************************************************************
|
|
*/
|
|
|
|
/* Loopback mode names (see LOOPBACK_MODE()) */
|
|
const unsigned int efx_loopback_mode_max = LOOPBACK_MAX;
|
|
const char *const efx_loopback_mode_names[] = {
|
|
[LOOPBACK_NONE] = "NONE",
|
|
[LOOPBACK_DATA] = "DATAPATH",
|
|
[LOOPBACK_GMAC] = "GMAC",
|
|
[LOOPBACK_XGMII] = "XGMII",
|
|
[LOOPBACK_XGXS] = "XGXS",
|
|
[LOOPBACK_XAUI] = "XAUI",
|
|
[LOOPBACK_GMII] = "GMII",
|
|
[LOOPBACK_SGMII] = "SGMII",
|
|
[LOOPBACK_XGBR] = "XGBR",
|
|
[LOOPBACK_XFI] = "XFI",
|
|
[LOOPBACK_XAUI_FAR] = "XAUI_FAR",
|
|
[LOOPBACK_GMII_FAR] = "GMII_FAR",
|
|
[LOOPBACK_SGMII_FAR] = "SGMII_FAR",
|
|
[LOOPBACK_XFI_FAR] = "XFI_FAR",
|
|
[LOOPBACK_GPHY] = "GPHY",
|
|
[LOOPBACK_PHYXS] = "PHYXS",
|
|
[LOOPBACK_PCS] = "PCS",
|
|
[LOOPBACK_PMAPMD] = "PMA/PMD",
|
|
[LOOPBACK_XPORT] = "XPORT",
|
|
[LOOPBACK_XGMII_WS] = "XGMII_WS",
|
|
[LOOPBACK_XAUI_WS] = "XAUI_WS",
|
|
[LOOPBACK_XAUI_WS_FAR] = "XAUI_WS_FAR",
|
|
[LOOPBACK_XAUI_WS_NEAR] = "XAUI_WS_NEAR",
|
|
[LOOPBACK_GMII_WS] = "GMII_WS",
|
|
[LOOPBACK_XFI_WS] = "XFI_WS",
|
|
[LOOPBACK_XFI_WS_FAR] = "XFI_WS_FAR",
|
|
[LOOPBACK_PHYXS_WS] = "PHYXS_WS",
|
|
};
|
|
|
|
const unsigned int efx_reset_type_max = RESET_TYPE_MAX;
|
|
const char *const efx_reset_type_names[] = {
|
|
[RESET_TYPE_INVISIBLE] = "INVISIBLE",
|
|
[RESET_TYPE_ALL] = "ALL",
|
|
[RESET_TYPE_RECOVER_OR_ALL] = "RECOVER_OR_ALL",
|
|
[RESET_TYPE_WORLD] = "WORLD",
|
|
[RESET_TYPE_RECOVER_OR_DISABLE] = "RECOVER_OR_DISABLE",
|
|
[RESET_TYPE_DATAPATH] = "DATAPATH",
|
|
[RESET_TYPE_MC_BIST] = "MC_BIST",
|
|
[RESET_TYPE_DISABLE] = "DISABLE",
|
|
[RESET_TYPE_TX_WATCHDOG] = "TX_WATCHDOG",
|
|
[RESET_TYPE_INT_ERROR] = "INT_ERROR",
|
|
[RESET_TYPE_DMA_ERROR] = "DMA_ERROR",
|
|
[RESET_TYPE_TX_SKIP] = "TX_SKIP",
|
|
[RESET_TYPE_MC_FAILURE] = "MC_FAILURE",
|
|
[RESET_TYPE_MCDI_TIMEOUT] = "MCDI_TIMEOUT (FLR)",
|
|
};
|
|
|
|
/* UDP tunnel type names */
|
|
static const char *const efx_udp_tunnel_type_names[] = {
|
|
[TUNNEL_ENCAP_UDP_PORT_ENTRY_VXLAN] = "vxlan",
|
|
[TUNNEL_ENCAP_UDP_PORT_ENTRY_GENEVE] = "geneve",
|
|
};
|
|
|
|
void efx_get_udp_tunnel_type_name(u16 type, char *buf, size_t buflen)
|
|
{
|
|
if (type < ARRAY_SIZE(efx_udp_tunnel_type_names) &&
|
|
efx_udp_tunnel_type_names[type] != NULL)
|
|
snprintf(buf, buflen, "%s", efx_udp_tunnel_type_names[type]);
|
|
else
|
|
snprintf(buf, buflen, "type %d", type);
|
|
}
|
|
|
|
/* Reset workqueue. If any NIC has a hardware failure then a reset will be
|
|
* queued onto this work queue. This is not a per-nic work queue, because
|
|
* efx_reset_work() acquires the rtnl lock, so resets are naturally serialised.
|
|
*/
|
|
static struct workqueue_struct *reset_workqueue;
|
|
|
|
/* How often and how many times to poll for a reset while waiting for a
|
|
* BIST that another function started to complete.
|
|
*/
|
|
#define BIST_WAIT_DELAY_MS 100
|
|
#define BIST_WAIT_DELAY_COUNT 100
|
|
|
|
/**************************************************************************
|
|
*
|
|
* Configurable values
|
|
*
|
|
*************************************************************************/
|
|
|
|
/*
|
|
* Use separate channels for TX and RX events
|
|
*
|
|
* Set this to 1 to use separate channels for TX and RX. It allows us
|
|
* to control interrupt affinity separately for TX and RX.
|
|
*
|
|
* This is only used in MSI-X interrupt mode
|
|
*/
|
|
bool efx_separate_tx_channels;
|
|
module_param(efx_separate_tx_channels, bool, 0444);
|
|
MODULE_PARM_DESC(efx_separate_tx_channels,
|
|
"Use separate channels for TX and RX");
|
|
|
|
/* This is the weight assigned to each of the (per-channel) virtual
|
|
* NAPI devices.
|
|
*/
|
|
static int napi_weight = 64;
|
|
|
|
/* This is the time (in jiffies) between invocations of the hardware
|
|
* monitor.
|
|
* On Falcon-based NICs, this will:
|
|
* - Check the on-board hardware monitor;
|
|
* - Poll the link state and reconfigure the hardware as necessary.
|
|
* On Siena-based NICs for power systems with EEH support, this will give EEH a
|
|
* chance to start.
|
|
*/
|
|
static unsigned int efx_monitor_interval = 1 * HZ;
|
|
|
|
/* Initial interrupt moderation settings. They can be modified after
|
|
* module load with ethtool.
|
|
*
|
|
* The default for RX should strike a balance between increasing the
|
|
* round-trip latency and reducing overhead.
|
|
*/
|
|
static unsigned int rx_irq_mod_usec = 60;
|
|
|
|
/* Initial interrupt moderation settings. They can be modified after
|
|
* module load with ethtool.
|
|
*
|
|
* This default is chosen to ensure that a 10G link does not go idle
|
|
* while a TX queue is stopped after it has become full. A queue is
|
|
* restarted when it drops below half full. The time this takes (assuming
|
|
* worst case 3 descriptors per packet and 1024 descriptors) is
|
|
* 512 / 3 * 1.2 = 205 usec.
|
|
*/
|
|
static unsigned int tx_irq_mod_usec = 150;
|
|
|
|
/* This is the first interrupt mode to try out of:
|
|
* 0 => MSI-X
|
|
* 1 => MSI
|
|
* 2 => legacy
|
|
*/
|
|
static unsigned int interrupt_mode;
|
|
|
|
/* This is the requested number of CPUs to use for Receive-Side Scaling (RSS),
|
|
* i.e. the number of CPUs among which we may distribute simultaneous
|
|
* interrupt handling.
|
|
*
|
|
* Cards without MSI-X will only target one CPU via legacy or MSI interrupt.
|
|
* The default (0) means to assign an interrupt to each core.
|
|
*/
|
|
static unsigned int rss_cpus;
|
|
module_param(rss_cpus, uint, 0444);
|
|
MODULE_PARM_DESC(rss_cpus, "Number of CPUs to use for Receive-Side Scaling");
|
|
|
|
static bool phy_flash_cfg;
|
|
module_param(phy_flash_cfg, bool, 0644);
|
|
MODULE_PARM_DESC(phy_flash_cfg, "Set PHYs into reflash mode initially");
|
|
|
|
static unsigned irq_adapt_low_thresh = 8000;
|
|
module_param(irq_adapt_low_thresh, uint, 0644);
|
|
MODULE_PARM_DESC(irq_adapt_low_thresh,
|
|
"Threshold score for reducing IRQ moderation");
|
|
|
|
static unsigned irq_adapt_high_thresh = 16000;
|
|
module_param(irq_adapt_high_thresh, uint, 0644);
|
|
MODULE_PARM_DESC(irq_adapt_high_thresh,
|
|
"Threshold score for increasing IRQ moderation");
|
|
|
|
static unsigned debug = (NETIF_MSG_DRV | NETIF_MSG_PROBE |
|
|
NETIF_MSG_LINK | NETIF_MSG_IFDOWN |
|
|
NETIF_MSG_IFUP | NETIF_MSG_RX_ERR |
|
|
NETIF_MSG_TX_ERR | NETIF_MSG_HW);
|
|
module_param(debug, uint, 0);
|
|
MODULE_PARM_DESC(debug, "Bitmapped debugging message enable value");
|
|
|
|
/**************************************************************************
|
|
*
|
|
* Utility functions and prototypes
|
|
*
|
|
*************************************************************************/
|
|
|
|
static int efx_soft_enable_interrupts(struct efx_nic *efx);
|
|
static void efx_soft_disable_interrupts(struct efx_nic *efx);
|
|
static void efx_remove_channel(struct efx_channel *channel);
|
|
static void efx_remove_channels(struct efx_nic *efx);
|
|
static const struct efx_channel_type efx_default_channel_type;
|
|
static void efx_remove_port(struct efx_nic *efx);
|
|
static void efx_init_napi_channel(struct efx_channel *channel);
|
|
static void efx_fini_napi(struct efx_nic *efx);
|
|
static void efx_fini_napi_channel(struct efx_channel *channel);
|
|
static void efx_fini_struct(struct efx_nic *efx);
|
|
static void efx_start_all(struct efx_nic *efx);
|
|
static void efx_stop_all(struct efx_nic *efx);
|
|
|
|
#define EFX_ASSERT_RESET_SERIALISED(efx) \
|
|
do { \
|
|
if ((efx->state == STATE_READY) || \
|
|
(efx->state == STATE_RECOVERY) || \
|
|
(efx->state == STATE_DISABLED)) \
|
|
ASSERT_RTNL(); \
|
|
} while (0)
|
|
|
|
static int efx_check_disabled(struct efx_nic *efx)
|
|
{
|
|
if (efx->state == STATE_DISABLED || efx->state == STATE_RECOVERY) {
|
|
netif_err(efx, drv, efx->net_dev,
|
|
"device is disabled due to earlier errors\n");
|
|
return -EIO;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/**************************************************************************
|
|
*
|
|
* Event queue processing
|
|
*
|
|
*************************************************************************/
|
|
|
|
/* Process channel's event queue
|
|
*
|
|
* This function is responsible for processing the event queue of a
|
|
* single channel. The caller must guarantee that this function will
|
|
* never be concurrently called more than once on the same channel,
|
|
* though different channels may be being processed concurrently.
|
|
*/
|
|
static int efx_process_channel(struct efx_channel *channel, int budget)
|
|
{
|
|
struct efx_tx_queue *tx_queue;
|
|
struct list_head rx_list;
|
|
int spent;
|
|
|
|
if (unlikely(!channel->enabled))
|
|
return 0;
|
|
|
|
/* Prepare the batch receive list */
|
|
EFX_WARN_ON_PARANOID(channel->rx_list != NULL);
|
|
INIT_LIST_HEAD(&rx_list);
|
|
channel->rx_list = &rx_list;
|
|
|
|
efx_for_each_channel_tx_queue(tx_queue, channel) {
|
|
tx_queue->pkts_compl = 0;
|
|
tx_queue->bytes_compl = 0;
|
|
}
|
|
|
|
spent = efx_nic_process_eventq(channel, budget);
|
|
if (spent && efx_channel_has_rx_queue(channel)) {
|
|
struct efx_rx_queue *rx_queue =
|
|
efx_channel_get_rx_queue(channel);
|
|
|
|
efx_rx_flush_packet(channel);
|
|
efx_fast_push_rx_descriptors(rx_queue, true);
|
|
}
|
|
|
|
/* Update BQL */
|
|
efx_for_each_channel_tx_queue(tx_queue, channel) {
|
|
if (tx_queue->bytes_compl) {
|
|
netdev_tx_completed_queue(tx_queue->core_txq,
|
|
tx_queue->pkts_compl, tx_queue->bytes_compl);
|
|
}
|
|
}
|
|
|
|
/* Receive any packets we queued up */
|
|
netif_receive_skb_list(channel->rx_list);
|
|
channel->rx_list = NULL;
|
|
|
|
return spent;
|
|
}
|
|
|
|
/* NAPI poll handler
|
|
*
|
|
* NAPI guarantees serialisation of polls of the same device, which
|
|
* provides the guarantee required by efx_process_channel().
|
|
*/
|
|
static void efx_update_irq_mod(struct efx_nic *efx, struct efx_channel *channel)
|
|
{
|
|
int step = efx->irq_mod_step_us;
|
|
|
|
if (channel->irq_mod_score < irq_adapt_low_thresh) {
|
|
if (channel->irq_moderation_us > step) {
|
|
channel->irq_moderation_us -= step;
|
|
efx->type->push_irq_moderation(channel);
|
|
}
|
|
} else if (channel->irq_mod_score > irq_adapt_high_thresh) {
|
|
if (channel->irq_moderation_us <
|
|
efx->irq_rx_moderation_us) {
|
|
channel->irq_moderation_us += step;
|
|
efx->type->push_irq_moderation(channel);
|
|
}
|
|
}
|
|
|
|
channel->irq_count = 0;
|
|
channel->irq_mod_score = 0;
|
|
}
|
|
|
|
static int efx_poll(struct napi_struct *napi, int budget)
|
|
{
|
|
struct efx_channel *channel =
|
|
container_of(napi, struct efx_channel, napi_str);
|
|
struct efx_nic *efx = channel->efx;
|
|
int spent;
|
|
|
|
netif_vdbg(efx, intr, efx->net_dev,
|
|
"channel %d NAPI poll executing on CPU %d\n",
|
|
channel->channel, raw_smp_processor_id());
|
|
|
|
spent = efx_process_channel(channel, budget);
|
|
|
|
if (spent < budget) {
|
|
if (efx_channel_has_rx_queue(channel) &&
|
|
efx->irq_rx_adaptive &&
|
|
unlikely(++channel->irq_count == 1000)) {
|
|
efx_update_irq_mod(efx, channel);
|
|
}
|
|
|
|
#ifdef CONFIG_RFS_ACCEL
|
|
/* Perhaps expire some ARFS filters */
|
|
schedule_work(&channel->filter_work);
|
|
#endif
|
|
|
|
/* There is no race here; although napi_disable() will
|
|
* only wait for napi_complete(), this isn't a problem
|
|
* since efx_nic_eventq_read_ack() will have no effect if
|
|
* interrupts have already been disabled.
|
|
*/
|
|
if (napi_complete_done(napi, spent))
|
|
efx_nic_eventq_read_ack(channel);
|
|
}
|
|
|
|
return spent;
|
|
}
|
|
|
|
/* Create event queue
|
|
* Event queue memory allocations are done only once. If the channel
|
|
* is reset, the memory buffer will be reused; this guards against
|
|
* errors during channel reset and also simplifies interrupt handling.
|
|
*/
|
|
static int efx_probe_eventq(struct efx_channel *channel)
|
|
{
|
|
struct efx_nic *efx = channel->efx;
|
|
unsigned long entries;
|
|
|
|
netif_dbg(efx, probe, efx->net_dev,
|
|
"chan %d create event queue\n", channel->channel);
|
|
|
|
/* Build an event queue with room for one event per tx and rx buffer,
|
|
* plus some extra for link state events and MCDI completions. */
|
|
entries = roundup_pow_of_two(efx->rxq_entries + efx->txq_entries + 128);
|
|
EFX_WARN_ON_PARANOID(entries > EFX_MAX_EVQ_SIZE);
|
|
channel->eventq_mask = max(entries, EFX_MIN_EVQ_SIZE) - 1;
|
|
|
|
return efx_nic_probe_eventq(channel);
|
|
}
|
|
|
|
/* Prepare channel's event queue */
|
|
static int efx_init_eventq(struct efx_channel *channel)
|
|
{
|
|
struct efx_nic *efx = channel->efx;
|
|
int rc;
|
|
|
|
EFX_WARN_ON_PARANOID(channel->eventq_init);
|
|
|
|
netif_dbg(efx, drv, efx->net_dev,
|
|
"chan %d init event queue\n", channel->channel);
|
|
|
|
rc = efx_nic_init_eventq(channel);
|
|
if (rc == 0) {
|
|
efx->type->push_irq_moderation(channel);
|
|
channel->eventq_read_ptr = 0;
|
|
channel->eventq_init = true;
|
|
}
|
|
return rc;
|
|
}
|
|
|
|
/* Enable event queue processing and NAPI */
|
|
void efx_start_eventq(struct efx_channel *channel)
|
|
{
|
|
netif_dbg(channel->efx, ifup, channel->efx->net_dev,
|
|
"chan %d start event queue\n", channel->channel);
|
|
|
|
/* Make sure the NAPI handler sees the enabled flag set */
|
|
channel->enabled = true;
|
|
smp_wmb();
|
|
|
|
napi_enable(&channel->napi_str);
|
|
efx_nic_eventq_read_ack(channel);
|
|
}
|
|
|
|
/* Disable event queue processing and NAPI */
|
|
void efx_stop_eventq(struct efx_channel *channel)
|
|
{
|
|
if (!channel->enabled)
|
|
return;
|
|
|
|
napi_disable(&channel->napi_str);
|
|
channel->enabled = false;
|
|
}
|
|
|
|
static void efx_fini_eventq(struct efx_channel *channel)
|
|
{
|
|
if (!channel->eventq_init)
|
|
return;
|
|
|
|
netif_dbg(channel->efx, drv, channel->efx->net_dev,
|
|
"chan %d fini event queue\n", channel->channel);
|
|
|
|
efx_nic_fini_eventq(channel);
|
|
channel->eventq_init = false;
|
|
}
|
|
|
|
static void efx_remove_eventq(struct efx_channel *channel)
|
|
{
|
|
netif_dbg(channel->efx, drv, channel->efx->net_dev,
|
|
"chan %d remove event queue\n", channel->channel);
|
|
|
|
efx_nic_remove_eventq(channel);
|
|
}
|
|
|
|
/**************************************************************************
|
|
*
|
|
* Channel handling
|
|
*
|
|
*************************************************************************/
|
|
|
|
/* Allocate and initialise a channel structure. */
|
|
static struct efx_channel *
|
|
efx_alloc_channel(struct efx_nic *efx, int i, struct efx_channel *old_channel)
|
|
{
|
|
struct efx_channel *channel;
|
|
struct efx_rx_queue *rx_queue;
|
|
struct efx_tx_queue *tx_queue;
|
|
int j;
|
|
|
|
channel = kzalloc(sizeof(*channel), GFP_KERNEL);
|
|
if (!channel)
|
|
return NULL;
|
|
|
|
channel->efx = efx;
|
|
channel->channel = i;
|
|
channel->type = &efx_default_channel_type;
|
|
|
|
for (j = 0; j < EFX_TXQ_TYPES; j++) {
|
|
tx_queue = &channel->tx_queue[j];
|
|
tx_queue->efx = efx;
|
|
tx_queue->queue = i * EFX_TXQ_TYPES + j;
|
|
tx_queue->channel = channel;
|
|
}
|
|
|
|
#ifdef CONFIG_RFS_ACCEL
|
|
INIT_WORK(&channel->filter_work, efx_filter_rfs_expire);
|
|
#endif
|
|
|
|
rx_queue = &channel->rx_queue;
|
|
rx_queue->efx = efx;
|
|
timer_setup(&rx_queue->slow_fill, efx_rx_slow_fill, 0);
|
|
|
|
return channel;
|
|
}
|
|
|
|
/* Allocate and initialise a channel structure, copying parameters
|
|
* (but not resources) from an old channel structure.
|
|
*/
|
|
static struct efx_channel *
|
|
efx_copy_channel(const struct efx_channel *old_channel)
|
|
{
|
|
struct efx_channel *channel;
|
|
struct efx_rx_queue *rx_queue;
|
|
struct efx_tx_queue *tx_queue;
|
|
int j;
|
|
|
|
channel = kmalloc(sizeof(*channel), GFP_KERNEL);
|
|
if (!channel)
|
|
return NULL;
|
|
|
|
*channel = *old_channel;
|
|
|
|
channel->napi_dev = NULL;
|
|
INIT_HLIST_NODE(&channel->napi_str.napi_hash_node);
|
|
channel->napi_str.napi_id = 0;
|
|
channel->napi_str.state = 0;
|
|
memset(&channel->eventq, 0, sizeof(channel->eventq));
|
|
|
|
for (j = 0; j < EFX_TXQ_TYPES; j++) {
|
|
tx_queue = &channel->tx_queue[j];
|
|
if (tx_queue->channel)
|
|
tx_queue->channel = channel;
|
|
tx_queue->buffer = NULL;
|
|
memset(&tx_queue->txd, 0, sizeof(tx_queue->txd));
|
|
}
|
|
|
|
rx_queue = &channel->rx_queue;
|
|
rx_queue->buffer = NULL;
|
|
memset(&rx_queue->rxd, 0, sizeof(rx_queue->rxd));
|
|
timer_setup(&rx_queue->slow_fill, efx_rx_slow_fill, 0);
|
|
#ifdef CONFIG_RFS_ACCEL
|
|
INIT_WORK(&channel->filter_work, efx_filter_rfs_expire);
|
|
#endif
|
|
|
|
return channel;
|
|
}
|
|
|
|
static int efx_probe_channel(struct efx_channel *channel)
|
|
{
|
|
struct efx_tx_queue *tx_queue;
|
|
struct efx_rx_queue *rx_queue;
|
|
int rc;
|
|
|
|
netif_dbg(channel->efx, probe, channel->efx->net_dev,
|
|
"creating channel %d\n", channel->channel);
|
|
|
|
rc = channel->type->pre_probe(channel);
|
|
if (rc)
|
|
goto fail;
|
|
|
|
rc = efx_probe_eventq(channel);
|
|
if (rc)
|
|
goto fail;
|
|
|
|
efx_for_each_channel_tx_queue(tx_queue, channel) {
|
|
rc = efx_probe_tx_queue(tx_queue);
|
|
if (rc)
|
|
goto fail;
|
|
}
|
|
|
|
efx_for_each_channel_rx_queue(rx_queue, channel) {
|
|
rc = efx_probe_rx_queue(rx_queue);
|
|
if (rc)
|
|
goto fail;
|
|
}
|
|
|
|
channel->rx_list = NULL;
|
|
|
|
return 0;
|
|
|
|
fail:
|
|
efx_remove_channel(channel);
|
|
return rc;
|
|
}
|
|
|
|
static void
|
|
efx_get_channel_name(struct efx_channel *channel, char *buf, size_t len)
|
|
{
|
|
struct efx_nic *efx = channel->efx;
|
|
const char *type;
|
|
int number;
|
|
|
|
number = channel->channel;
|
|
if (efx->tx_channel_offset == 0) {
|
|
type = "";
|
|
} else if (channel->channel < efx->tx_channel_offset) {
|
|
type = "-rx";
|
|
} else {
|
|
type = "-tx";
|
|
number -= efx->tx_channel_offset;
|
|
}
|
|
snprintf(buf, len, "%s%s-%d", efx->name, type, number);
|
|
}
|
|
|
|
static void efx_set_channel_names(struct efx_nic *efx)
|
|
{
|
|
struct efx_channel *channel;
|
|
|
|
efx_for_each_channel(channel, efx)
|
|
channel->type->get_name(channel,
|
|
efx->msi_context[channel->channel].name,
|
|
sizeof(efx->msi_context[0].name));
|
|
}
|
|
|
|
static int efx_probe_channels(struct efx_nic *efx)
|
|
{
|
|
struct efx_channel *channel;
|
|
int rc;
|
|
|
|
/* Restart special buffer allocation */
|
|
efx->next_buffer_table = 0;
|
|
|
|
/* Probe channels in reverse, so that any 'extra' channels
|
|
* use the start of the buffer table. This allows the traffic
|
|
* channels to be resized without moving them or wasting the
|
|
* entries before them.
|
|
*/
|
|
efx_for_each_channel_rev(channel, efx) {
|
|
rc = efx_probe_channel(channel);
|
|
if (rc) {
|
|
netif_err(efx, probe, efx->net_dev,
|
|
"failed to create channel %d\n",
|
|
channel->channel);
|
|
goto fail;
|
|
}
|
|
}
|
|
efx_set_channel_names(efx);
|
|
|
|
return 0;
|
|
|
|
fail:
|
|
efx_remove_channels(efx);
|
|
return rc;
|
|
}
|
|
|
|
/* Channels are shutdown and reinitialised whilst the NIC is running
|
|
* to propagate configuration changes (mtu, checksum offload), or
|
|
* to clear hardware error conditions
|
|
*/
|
|
static void efx_start_datapath(struct efx_nic *efx)
|
|
{
|
|
netdev_features_t old_features = efx->net_dev->features;
|
|
bool old_rx_scatter = efx->rx_scatter;
|
|
struct efx_tx_queue *tx_queue;
|
|
struct efx_rx_queue *rx_queue;
|
|
struct efx_channel *channel;
|
|
size_t rx_buf_len;
|
|
|
|
/* Calculate the rx buffer allocation parameters required to
|
|
* support the current MTU, including padding for header
|
|
* alignment and overruns.
|
|
*/
|
|
efx->rx_dma_len = (efx->rx_prefix_size +
|
|
EFX_MAX_FRAME_LEN(efx->net_dev->mtu) +
|
|
efx->type->rx_buffer_padding);
|
|
rx_buf_len = (sizeof(struct efx_rx_page_state) +
|
|
efx->rx_ip_align + efx->rx_dma_len);
|
|
if (rx_buf_len <= PAGE_SIZE) {
|
|
efx->rx_scatter = efx->type->always_rx_scatter;
|
|
efx->rx_buffer_order = 0;
|
|
} else if (efx->type->can_rx_scatter) {
|
|
BUILD_BUG_ON(EFX_RX_USR_BUF_SIZE % L1_CACHE_BYTES);
|
|
BUILD_BUG_ON(sizeof(struct efx_rx_page_state) +
|
|
2 * ALIGN(NET_IP_ALIGN + EFX_RX_USR_BUF_SIZE,
|
|
EFX_RX_BUF_ALIGNMENT) >
|
|
PAGE_SIZE);
|
|
efx->rx_scatter = true;
|
|
efx->rx_dma_len = EFX_RX_USR_BUF_SIZE;
|
|
efx->rx_buffer_order = 0;
|
|
} else {
|
|
efx->rx_scatter = false;
|
|
efx->rx_buffer_order = get_order(rx_buf_len);
|
|
}
|
|
|
|
efx_rx_config_page_split(efx);
|
|
if (efx->rx_buffer_order)
|
|
netif_dbg(efx, drv, efx->net_dev,
|
|
"RX buf len=%u; page order=%u batch=%u\n",
|
|
efx->rx_dma_len, efx->rx_buffer_order,
|
|
efx->rx_pages_per_batch);
|
|
else
|
|
netif_dbg(efx, drv, efx->net_dev,
|
|
"RX buf len=%u step=%u bpp=%u; page batch=%u\n",
|
|
efx->rx_dma_len, efx->rx_page_buf_step,
|
|
efx->rx_bufs_per_page, efx->rx_pages_per_batch);
|
|
|
|
/* Restore previously fixed features in hw_features and remove
|
|
* features which are fixed now
|
|
*/
|
|
efx->net_dev->hw_features |= efx->net_dev->features;
|
|
efx->net_dev->hw_features &= ~efx->fixed_features;
|
|
efx->net_dev->features |= efx->fixed_features;
|
|
if (efx->net_dev->features != old_features)
|
|
netdev_features_change(efx->net_dev);
|
|
|
|
/* RX filters may also have scatter-enabled flags */
|
|
if (efx->rx_scatter != old_rx_scatter)
|
|
efx->type->filter_update_rx_scatter(efx);
|
|
|
|
/* We must keep at least one descriptor in a TX ring empty.
|
|
* We could avoid this when the queue size does not exactly
|
|
* match the hardware ring size, but it's not that important.
|
|
* Therefore we stop the queue when one more skb might fill
|
|
* the ring completely. We wake it when half way back to
|
|
* empty.
|
|
*/
|
|
efx->txq_stop_thresh = efx->txq_entries - efx_tx_max_skb_descs(efx);
|
|
efx->txq_wake_thresh = efx->txq_stop_thresh / 2;
|
|
|
|
/* Initialise the channels */
|
|
efx_for_each_channel(channel, efx) {
|
|
efx_for_each_channel_tx_queue(tx_queue, channel) {
|
|
efx_init_tx_queue(tx_queue);
|
|
atomic_inc(&efx->active_queues);
|
|
}
|
|
|
|
efx_for_each_channel_rx_queue(rx_queue, channel) {
|
|
efx_init_rx_queue(rx_queue);
|
|
atomic_inc(&efx->active_queues);
|
|
efx_stop_eventq(channel);
|
|
efx_fast_push_rx_descriptors(rx_queue, false);
|
|
efx_start_eventq(channel);
|
|
}
|
|
|
|
WARN_ON(channel->rx_pkt_n_frags);
|
|
}
|
|
|
|
efx_ptp_start_datapath(efx);
|
|
|
|
if (netif_device_present(efx->net_dev))
|
|
netif_tx_wake_all_queues(efx->net_dev);
|
|
}
|
|
|
|
static void efx_stop_datapath(struct efx_nic *efx)
|
|
{
|
|
struct efx_channel *channel;
|
|
struct efx_tx_queue *tx_queue;
|
|
struct efx_rx_queue *rx_queue;
|
|
int rc;
|
|
|
|
EFX_ASSERT_RESET_SERIALISED(efx);
|
|
BUG_ON(efx->port_enabled);
|
|
|
|
efx_ptp_stop_datapath(efx);
|
|
|
|
/* Stop RX refill */
|
|
efx_for_each_channel(channel, efx) {
|
|
efx_for_each_channel_rx_queue(rx_queue, channel)
|
|
rx_queue->refill_enabled = false;
|
|
}
|
|
|
|
efx_for_each_channel(channel, efx) {
|
|
/* RX packet processing is pipelined, so wait for the
|
|
* NAPI handler to complete. At least event queue 0
|
|
* might be kept active by non-data events, so don't
|
|
* use napi_synchronize() but actually disable NAPI
|
|
* temporarily.
|
|
*/
|
|
if (efx_channel_has_rx_queue(channel)) {
|
|
efx_stop_eventq(channel);
|
|
efx_start_eventq(channel);
|
|
}
|
|
}
|
|
|
|
rc = efx->type->fini_dmaq(efx);
|
|
if (rc) {
|
|
netif_err(efx, drv, efx->net_dev, "failed to flush queues\n");
|
|
} else {
|
|
netif_dbg(efx, drv, efx->net_dev,
|
|
"successfully flushed all queues\n");
|
|
}
|
|
|
|
efx_for_each_channel(channel, efx) {
|
|
efx_for_each_channel_rx_queue(rx_queue, channel)
|
|
efx_fini_rx_queue(rx_queue);
|
|
efx_for_each_possible_channel_tx_queue(tx_queue, channel)
|
|
efx_fini_tx_queue(tx_queue);
|
|
}
|
|
}
|
|
|
|
static void efx_remove_channel(struct efx_channel *channel)
|
|
{
|
|
struct efx_tx_queue *tx_queue;
|
|
struct efx_rx_queue *rx_queue;
|
|
|
|
netif_dbg(channel->efx, drv, channel->efx->net_dev,
|
|
"destroy chan %d\n", channel->channel);
|
|
|
|
efx_for_each_channel_rx_queue(rx_queue, channel)
|
|
efx_remove_rx_queue(rx_queue);
|
|
efx_for_each_possible_channel_tx_queue(tx_queue, channel)
|
|
efx_remove_tx_queue(tx_queue);
|
|
efx_remove_eventq(channel);
|
|
channel->type->post_remove(channel);
|
|
}
|
|
|
|
static void efx_remove_channels(struct efx_nic *efx)
|
|
{
|
|
struct efx_channel *channel;
|
|
|
|
efx_for_each_channel(channel, efx)
|
|
efx_remove_channel(channel);
|
|
}
|
|
|
|
int
|
|
efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries)
|
|
{
|
|
struct efx_channel *other_channel[EFX_MAX_CHANNELS], *channel;
|
|
u32 old_rxq_entries, old_txq_entries;
|
|
unsigned i, next_buffer_table = 0;
|
|
int rc, rc2;
|
|
|
|
rc = efx_check_disabled(efx);
|
|
if (rc)
|
|
return rc;
|
|
|
|
/* Not all channels should be reallocated. We must avoid
|
|
* reallocating their buffer table entries.
|
|
*/
|
|
efx_for_each_channel(channel, efx) {
|
|
struct efx_rx_queue *rx_queue;
|
|
struct efx_tx_queue *tx_queue;
|
|
|
|
if (channel->type->copy)
|
|
continue;
|
|
next_buffer_table = max(next_buffer_table,
|
|
channel->eventq.index +
|
|
channel->eventq.entries);
|
|
efx_for_each_channel_rx_queue(rx_queue, channel)
|
|
next_buffer_table = max(next_buffer_table,
|
|
rx_queue->rxd.index +
|
|
rx_queue->rxd.entries);
|
|
efx_for_each_channel_tx_queue(tx_queue, channel)
|
|
next_buffer_table = max(next_buffer_table,
|
|
tx_queue->txd.index +
|
|
tx_queue->txd.entries);
|
|
}
|
|
|
|
efx_device_detach_sync(efx);
|
|
efx_stop_all(efx);
|
|
efx_soft_disable_interrupts(efx);
|
|
|
|
/* Clone channels (where possible) */
|
|
memset(other_channel, 0, sizeof(other_channel));
|
|
for (i = 0; i < efx->n_channels; i++) {
|
|
channel = efx->channel[i];
|
|
if (channel->type->copy)
|
|
channel = channel->type->copy(channel);
|
|
if (!channel) {
|
|
rc = -ENOMEM;
|
|
goto out;
|
|
}
|
|
other_channel[i] = channel;
|
|
}
|
|
|
|
/* Swap entry counts and channel pointers */
|
|
old_rxq_entries = efx->rxq_entries;
|
|
old_txq_entries = efx->txq_entries;
|
|
efx->rxq_entries = rxq_entries;
|
|
efx->txq_entries = txq_entries;
|
|
for (i = 0; i < efx->n_channels; i++) {
|
|
channel = efx->channel[i];
|
|
efx->channel[i] = other_channel[i];
|
|
other_channel[i] = channel;
|
|
}
|
|
|
|
/* Restart buffer table allocation */
|
|
efx->next_buffer_table = next_buffer_table;
|
|
|
|
for (i = 0; i < efx->n_channels; i++) {
|
|
channel = efx->channel[i];
|
|
if (!channel->type->copy)
|
|
continue;
|
|
rc = efx_probe_channel(channel);
|
|
if (rc)
|
|
goto rollback;
|
|
efx_init_napi_channel(efx->channel[i]);
|
|
}
|
|
|
|
out:
|
|
/* Destroy unused channel structures */
|
|
for (i = 0; i < efx->n_channels; i++) {
|
|
channel = other_channel[i];
|
|
if (channel && channel->type->copy) {
|
|
efx_fini_napi_channel(channel);
|
|
efx_remove_channel(channel);
|
|
kfree(channel);
|
|
}
|
|
}
|
|
|
|
rc2 = efx_soft_enable_interrupts(efx);
|
|
if (rc2) {
|
|
rc = rc ? rc : rc2;
|
|
netif_err(efx, drv, efx->net_dev,
|
|
"unable to restart interrupts on channel reallocation\n");
|
|
efx_schedule_reset(efx, RESET_TYPE_DISABLE);
|
|
} else {
|
|
efx_start_all(efx);
|
|
efx_device_attach_if_not_resetting(efx);
|
|
}
|
|
return rc;
|
|
|
|
rollback:
|
|
/* Swap back */
|
|
efx->rxq_entries = old_rxq_entries;
|
|
efx->txq_entries = old_txq_entries;
|
|
for (i = 0; i < efx->n_channels; i++) {
|
|
channel = efx->channel[i];
|
|
efx->channel[i] = other_channel[i];
|
|
other_channel[i] = channel;
|
|
}
|
|
goto out;
|
|
}
|
|
|
|
void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue)
|
|
{
|
|
mod_timer(&rx_queue->slow_fill, jiffies + msecs_to_jiffies(100));
|
|
}
|
|
|
|
static bool efx_default_channel_want_txqs(struct efx_channel *channel)
|
|
{
|
|
return channel->channel - channel->efx->tx_channel_offset <
|
|
channel->efx->n_tx_channels;
|
|
}
|
|
|
|
static const struct efx_channel_type efx_default_channel_type = {
|
|
.pre_probe = efx_channel_dummy_op_int,
|
|
.post_remove = efx_channel_dummy_op_void,
|
|
.get_name = efx_get_channel_name,
|
|
.copy = efx_copy_channel,
|
|
.want_txqs = efx_default_channel_want_txqs,
|
|
.keep_eventq = false,
|
|
.want_pio = true,
|
|
};
|
|
|
|
int efx_channel_dummy_op_int(struct efx_channel *channel)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
void efx_channel_dummy_op_void(struct efx_channel *channel)
|
|
{
|
|
}
|
|
|
|
/**************************************************************************
|
|
*
|
|
* Port handling
|
|
*
|
|
**************************************************************************/
|
|
|
|
/* This ensures that the kernel is kept informed (via
|
|
* netif_carrier_on/off) of the link status, and also maintains the
|
|
* link status's stop on the port's TX queue.
|
|
*/
|
|
void efx_link_status_changed(struct efx_nic *efx)
|
|
{
|
|
struct efx_link_state *link_state = &efx->link_state;
|
|
|
|
/* SFC Bug 5356: A net_dev notifier is registered, so we must ensure
|
|
* that no events are triggered between unregister_netdev() and the
|
|
* driver unloading. A more general condition is that NETDEV_CHANGE
|
|
* can only be generated between NETDEV_UP and NETDEV_DOWN */
|
|
if (!netif_running(efx->net_dev))
|
|
return;
|
|
|
|
if (link_state->up != netif_carrier_ok(efx->net_dev)) {
|
|
efx->n_link_state_changes++;
|
|
|
|
if (link_state->up)
|
|
netif_carrier_on(efx->net_dev);
|
|
else
|
|
netif_carrier_off(efx->net_dev);
|
|
}
|
|
|
|
/* Status message for kernel log */
|
|
if (link_state->up)
|
|
netif_info(efx, link, efx->net_dev,
|
|
"link up at %uMbps %s-duplex (MTU %d)\n",
|
|
link_state->speed, link_state->fd ? "full" : "half",
|
|
efx->net_dev->mtu);
|
|
else
|
|
netif_info(efx, link, efx->net_dev, "link down\n");
|
|
}
|
|
|
|
void efx_link_set_advertising(struct efx_nic *efx,
|
|
const unsigned long *advertising)
|
|
{
|
|
memcpy(efx->link_advertising, advertising,
|
|
sizeof(__ETHTOOL_DECLARE_LINK_MODE_MASK()));
|
|
|
|
efx->link_advertising[0] |= ADVERTISED_Autoneg;
|
|
if (advertising[0] & ADVERTISED_Pause)
|
|
efx->wanted_fc |= (EFX_FC_TX | EFX_FC_RX);
|
|
else
|
|
efx->wanted_fc &= ~(EFX_FC_TX | EFX_FC_RX);
|
|
if (advertising[0] & ADVERTISED_Asym_Pause)
|
|
efx->wanted_fc ^= EFX_FC_TX;
|
|
}
|
|
|
|
/* Equivalent to efx_link_set_advertising with all-zeroes, except does not
|
|
* force the Autoneg bit on.
|
|
*/
|
|
void efx_link_clear_advertising(struct efx_nic *efx)
|
|
{
|
|
bitmap_zero(efx->link_advertising, __ETHTOOL_LINK_MODE_MASK_NBITS);
|
|
efx->wanted_fc &= ~(EFX_FC_TX | EFX_FC_RX);
|
|
}
|
|
|
|
void efx_link_set_wanted_fc(struct efx_nic *efx, u8 wanted_fc)
|
|
{
|
|
efx->wanted_fc = wanted_fc;
|
|
if (efx->link_advertising[0]) {
|
|
if (wanted_fc & EFX_FC_RX)
|
|
efx->link_advertising[0] |= (ADVERTISED_Pause |
|
|
ADVERTISED_Asym_Pause);
|
|
else
|
|
efx->link_advertising[0] &= ~(ADVERTISED_Pause |
|
|
ADVERTISED_Asym_Pause);
|
|
if (wanted_fc & EFX_FC_TX)
|
|
efx->link_advertising[0] ^= ADVERTISED_Asym_Pause;
|
|
}
|
|
}
|
|
|
|
static void efx_fini_port(struct efx_nic *efx);
|
|
|
|
/* We assume that efx->type->reconfigure_mac will always try to sync RX
|
|
* filters and therefore needs to read-lock the filter table against freeing
|
|
*/
|
|
void efx_mac_reconfigure(struct efx_nic *efx)
|
|
{
|
|
down_read(&efx->filter_sem);
|
|
efx->type->reconfigure_mac(efx);
|
|
up_read(&efx->filter_sem);
|
|
}
|
|
|
|
/* Push loopback/power/transmit disable settings to the PHY, and reconfigure
|
|
* the MAC appropriately. All other PHY configuration changes are pushed
|
|
* through phy_op->set_settings(), and pushed asynchronously to the MAC
|
|
* through efx_monitor().
|
|
*
|
|
* Callers must hold the mac_lock
|
|
*/
|
|
int __efx_reconfigure_port(struct efx_nic *efx)
|
|
{
|
|
enum efx_phy_mode phy_mode;
|
|
int rc;
|
|
|
|
WARN_ON(!mutex_is_locked(&efx->mac_lock));
|
|
|
|
/* Disable PHY transmit in mac level loopbacks */
|
|
phy_mode = efx->phy_mode;
|
|
if (LOOPBACK_INTERNAL(efx))
|
|
efx->phy_mode |= PHY_MODE_TX_DISABLED;
|
|
else
|
|
efx->phy_mode &= ~PHY_MODE_TX_DISABLED;
|
|
|
|
rc = efx->type->reconfigure_port(efx);
|
|
|
|
if (rc)
|
|
efx->phy_mode = phy_mode;
|
|
|
|
return rc;
|
|
}
|
|
|
|
/* Reinitialise the MAC to pick up new PHY settings, even if the port is
|
|
* disabled. */
|
|
int efx_reconfigure_port(struct efx_nic *efx)
|
|
{
|
|
int rc;
|
|
|
|
EFX_ASSERT_RESET_SERIALISED(efx);
|
|
|
|
mutex_lock(&efx->mac_lock);
|
|
rc = __efx_reconfigure_port(efx);
|
|
mutex_unlock(&efx->mac_lock);
|
|
|
|
return rc;
|
|
}
|
|
|
|
/* Asynchronous work item for changing MAC promiscuity and multicast
|
|
* hash. Avoid a drain/rx_ingress enable by reconfiguring the current
|
|
* MAC directly. */
|
|
static void efx_mac_work(struct work_struct *data)
|
|
{
|
|
struct efx_nic *efx = container_of(data, struct efx_nic, mac_work);
|
|
|
|
mutex_lock(&efx->mac_lock);
|
|
if (efx->port_enabled)
|
|
efx_mac_reconfigure(efx);
|
|
mutex_unlock(&efx->mac_lock);
|
|
}
|
|
|
|
static int efx_probe_port(struct efx_nic *efx)
|
|
{
|
|
int rc;
|
|
|
|
netif_dbg(efx, probe, efx->net_dev, "create port\n");
|
|
|
|
if (phy_flash_cfg)
|
|
efx->phy_mode = PHY_MODE_SPECIAL;
|
|
|
|
/* Connect up MAC/PHY operations table */
|
|
rc = efx->type->probe_port(efx);
|
|
if (rc)
|
|
return rc;
|
|
|
|
/* Initialise MAC address to permanent address */
|
|
ether_addr_copy(efx->net_dev->dev_addr, efx->net_dev->perm_addr);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int efx_init_port(struct efx_nic *efx)
|
|
{
|
|
int rc;
|
|
|
|
netif_dbg(efx, drv, efx->net_dev, "init port\n");
|
|
|
|
mutex_lock(&efx->mac_lock);
|
|
|
|
rc = efx->phy_op->init(efx);
|
|
if (rc)
|
|
goto fail1;
|
|
|
|
efx->port_initialized = true;
|
|
|
|
/* Reconfigure the MAC before creating dma queues (required for
|
|
* Falcon/A1 where RX_INGR_EN/TX_DRAIN_EN isn't supported) */
|
|
efx_mac_reconfigure(efx);
|
|
|
|
/* Ensure the PHY advertises the correct flow control settings */
|
|
rc = efx->phy_op->reconfigure(efx);
|
|
if (rc && rc != -EPERM)
|
|
goto fail2;
|
|
|
|
mutex_unlock(&efx->mac_lock);
|
|
return 0;
|
|
|
|
fail2:
|
|
efx->phy_op->fini(efx);
|
|
fail1:
|
|
mutex_unlock(&efx->mac_lock);
|
|
return rc;
|
|
}
|
|
|
|
static void efx_start_port(struct efx_nic *efx)
|
|
{
|
|
netif_dbg(efx, ifup, efx->net_dev, "start port\n");
|
|
BUG_ON(efx->port_enabled);
|
|
|
|
mutex_lock(&efx->mac_lock);
|
|
efx->port_enabled = true;
|
|
|
|
/* Ensure MAC ingress/egress is enabled */
|
|
efx_mac_reconfigure(efx);
|
|
|
|
mutex_unlock(&efx->mac_lock);
|
|
}
|
|
|
|
/* Cancel work for MAC reconfiguration, periodic hardware monitoring
|
|
* and the async self-test, wait for them to finish and prevent them
|
|
* being scheduled again. This doesn't cover online resets, which
|
|
* should only be cancelled when removing the device.
|
|
*/
|
|
static void efx_stop_port(struct efx_nic *efx)
|
|
{
|
|
netif_dbg(efx, ifdown, efx->net_dev, "stop port\n");
|
|
|
|
EFX_ASSERT_RESET_SERIALISED(efx);
|
|
|
|
mutex_lock(&efx->mac_lock);
|
|
efx->port_enabled = false;
|
|
mutex_unlock(&efx->mac_lock);
|
|
|
|
/* Serialise against efx_set_multicast_list() */
|
|
netif_addr_lock_bh(efx->net_dev);
|
|
netif_addr_unlock_bh(efx->net_dev);
|
|
|
|
cancel_delayed_work_sync(&efx->monitor_work);
|
|
efx_selftest_async_cancel(efx);
|
|
cancel_work_sync(&efx->mac_work);
|
|
}
|
|
|
|
static void efx_fini_port(struct efx_nic *efx)
|
|
{
|
|
netif_dbg(efx, drv, efx->net_dev, "shut down port\n");
|
|
|
|
if (!efx->port_initialized)
|
|
return;
|
|
|
|
efx->phy_op->fini(efx);
|
|
efx->port_initialized = false;
|
|
|
|
efx->link_state.up = false;
|
|
efx_link_status_changed(efx);
|
|
}
|
|
|
|
static void efx_remove_port(struct efx_nic *efx)
|
|
{
|
|
netif_dbg(efx, drv, efx->net_dev, "destroying port\n");
|
|
|
|
efx->type->remove_port(efx);
|
|
}
|
|
|
|
/**************************************************************************
|
|
*
|
|
* NIC handling
|
|
*
|
|
**************************************************************************/
|
|
|
|
static LIST_HEAD(efx_primary_list);
|
|
static LIST_HEAD(efx_unassociated_list);
|
|
|
|
static bool efx_same_controller(struct efx_nic *left, struct efx_nic *right)
|
|
{
|
|
return left->type == right->type &&
|
|
left->vpd_sn && right->vpd_sn &&
|
|
!strcmp(left->vpd_sn, right->vpd_sn);
|
|
}
|
|
|
|
static void efx_associate(struct efx_nic *efx)
|
|
{
|
|
struct efx_nic *other, *next;
|
|
|
|
if (efx->primary == efx) {
|
|
/* Adding primary function; look for secondaries */
|
|
|
|
netif_dbg(efx, probe, efx->net_dev, "adding to primary list\n");
|
|
list_add_tail(&efx->node, &efx_primary_list);
|
|
|
|
list_for_each_entry_safe(other, next, &efx_unassociated_list,
|
|
node) {
|
|
if (efx_same_controller(efx, other)) {
|
|
list_del(&other->node);
|
|
netif_dbg(other, probe, other->net_dev,
|
|
"moving to secondary list of %s %s\n",
|
|
pci_name(efx->pci_dev),
|
|
efx->net_dev->name);
|
|
list_add_tail(&other->node,
|
|
&efx->secondary_list);
|
|
other->primary = efx;
|
|
}
|
|
}
|
|
} else {
|
|
/* Adding secondary function; look for primary */
|
|
|
|
list_for_each_entry(other, &efx_primary_list, node) {
|
|
if (efx_same_controller(efx, other)) {
|
|
netif_dbg(efx, probe, efx->net_dev,
|
|
"adding to secondary list of %s %s\n",
|
|
pci_name(other->pci_dev),
|
|
other->net_dev->name);
|
|
list_add_tail(&efx->node,
|
|
&other->secondary_list);
|
|
efx->primary = other;
|
|
return;
|
|
}
|
|
}
|
|
|
|
netif_dbg(efx, probe, efx->net_dev,
|
|
"adding to unassociated list\n");
|
|
list_add_tail(&efx->node, &efx_unassociated_list);
|
|
}
|
|
}
|
|
|
|
static void efx_dissociate(struct efx_nic *efx)
|
|
{
|
|
struct efx_nic *other, *next;
|
|
|
|
list_del(&efx->node);
|
|
efx->primary = NULL;
|
|
|
|
list_for_each_entry_safe(other, next, &efx->secondary_list, node) {
|
|
list_del(&other->node);
|
|
netif_dbg(other, probe, other->net_dev,
|
|
"moving to unassociated list\n");
|
|
list_add_tail(&other->node, &efx_unassociated_list);
|
|
other->primary = NULL;
|
|
}
|
|
}
|
|
|
|
/* This configures the PCI device to enable I/O and DMA. */
|
|
static int efx_init_io(struct efx_nic *efx)
|
|
{
|
|
struct pci_dev *pci_dev = efx->pci_dev;
|
|
dma_addr_t dma_mask = efx->type->max_dma_mask;
|
|
unsigned int mem_map_size = efx->type->mem_map_size(efx);
|
|
int rc, bar;
|
|
|
|
netif_dbg(efx, probe, efx->net_dev, "initialising I/O\n");
|
|
|
|
bar = efx->type->mem_bar(efx);
|
|
|
|
rc = pci_enable_device(pci_dev);
|
|
if (rc) {
|
|
netif_err(efx, probe, efx->net_dev,
|
|
"failed to enable PCI device\n");
|
|
goto fail1;
|
|
}
|
|
|
|
pci_set_master(pci_dev);
|
|
|
|
/* Set the PCI DMA mask. Try all possibilities from our genuine mask
|
|
* down to 32 bits, because some architectures will allow 40 bit
|
|
* masks event though they reject 46 bit masks.
|
|
*/
|
|
while (dma_mask > 0x7fffffffUL) {
|
|
rc = dma_set_mask_and_coherent(&pci_dev->dev, dma_mask);
|
|
if (rc == 0)
|
|
break;
|
|
dma_mask >>= 1;
|
|
}
|
|
if (rc) {
|
|
netif_err(efx, probe, efx->net_dev,
|
|
"could not find a suitable DMA mask\n");
|
|
goto fail2;
|
|
}
|
|
netif_dbg(efx, probe, efx->net_dev,
|
|
"using DMA mask %llx\n", (unsigned long long) dma_mask);
|
|
|
|
efx->membase_phys = pci_resource_start(efx->pci_dev, bar);
|
|
rc = pci_request_region(pci_dev, bar, "sfc");
|
|
if (rc) {
|
|
netif_err(efx, probe, efx->net_dev,
|
|
"request for memory BAR failed\n");
|
|
rc = -EIO;
|
|
goto fail3;
|
|
}
|
|
efx->membase = ioremap_nocache(efx->membase_phys, mem_map_size);
|
|
if (!efx->membase) {
|
|
netif_err(efx, probe, efx->net_dev,
|
|
"could not map memory BAR at %llx+%x\n",
|
|
(unsigned long long)efx->membase_phys, mem_map_size);
|
|
rc = -ENOMEM;
|
|
goto fail4;
|
|
}
|
|
netif_dbg(efx, probe, efx->net_dev,
|
|
"memory BAR at %llx+%x (virtual %p)\n",
|
|
(unsigned long long)efx->membase_phys, mem_map_size,
|
|
efx->membase);
|
|
|
|
return 0;
|
|
|
|
fail4:
|
|
pci_release_region(efx->pci_dev, bar);
|
|
fail3:
|
|
efx->membase_phys = 0;
|
|
fail2:
|
|
pci_disable_device(efx->pci_dev);
|
|
fail1:
|
|
return rc;
|
|
}
|
|
|
|
static void efx_fini_io(struct efx_nic *efx)
|
|
{
|
|
int bar;
|
|
|
|
netif_dbg(efx, drv, efx->net_dev, "shutting down I/O\n");
|
|
|
|
if (efx->membase) {
|
|
iounmap(efx->membase);
|
|
efx->membase = NULL;
|
|
}
|
|
|
|
if (efx->membase_phys) {
|
|
bar = efx->type->mem_bar(efx);
|
|
pci_release_region(efx->pci_dev, bar);
|
|
efx->membase_phys = 0;
|
|
}
|
|
|
|
/* Don't disable bus-mastering if VFs are assigned */
|
|
if (!pci_vfs_assigned(efx->pci_dev))
|
|
pci_disable_device(efx->pci_dev);
|
|
}
|
|
|
|
void efx_set_default_rx_indir_table(struct efx_nic *efx,
|
|
struct efx_rss_context *ctx)
|
|
{
|
|
size_t i;
|
|
|
|
for (i = 0; i < ARRAY_SIZE(ctx->rx_indir_table); i++)
|
|
ctx->rx_indir_table[i] =
|
|
ethtool_rxfh_indir_default(i, efx->rss_spread);
|
|
}
|
|
|
|
static unsigned int efx_wanted_parallelism(struct efx_nic *efx)
|
|
{
|
|
cpumask_var_t thread_mask;
|
|
unsigned int count;
|
|
int cpu;
|
|
|
|
if (rss_cpus) {
|
|
count = rss_cpus;
|
|
} else {
|
|
if (unlikely(!zalloc_cpumask_var(&thread_mask, GFP_KERNEL))) {
|
|
netif_warn(efx, probe, efx->net_dev,
|
|
"RSS disabled due to allocation failure\n");
|
|
return 1;
|
|
}
|
|
|
|
count = 0;
|
|
for_each_online_cpu(cpu) {
|
|
if (!cpumask_test_cpu(cpu, thread_mask)) {
|
|
++count;
|
|
cpumask_or(thread_mask, thread_mask,
|
|
topology_sibling_cpumask(cpu));
|
|
}
|
|
}
|
|
|
|
free_cpumask_var(thread_mask);
|
|
}
|
|
|
|
if (count > EFX_MAX_RX_QUEUES) {
|
|
netif_cond_dbg(efx, probe, efx->net_dev, !rss_cpus, warn,
|
|
"Reducing number of rx queues from %u to %u.\n",
|
|
count, EFX_MAX_RX_QUEUES);
|
|
count = EFX_MAX_RX_QUEUES;
|
|
}
|
|
|
|
/* If RSS is requested for the PF *and* VFs then we can't write RSS
|
|
* table entries that are inaccessible to VFs
|
|
*/
|
|
#ifdef CONFIG_SFC_SRIOV
|
|
if (efx->type->sriov_wanted) {
|
|
if (efx->type->sriov_wanted(efx) && efx_vf_size(efx) > 1 &&
|
|
count > efx_vf_size(efx)) {
|
|
netif_warn(efx, probe, efx->net_dev,
|
|
"Reducing number of RSS channels from %u to %u for "
|
|
"VF support. Increase vf-msix-limit to use more "
|
|
"channels on the PF.\n",
|
|
count, efx_vf_size(efx));
|
|
count = efx_vf_size(efx);
|
|
}
|
|
}
|
|
#endif
|
|
|
|
return count;
|
|
}
|
|
|
|
/* Probe the number and type of interrupts we are able to obtain, and
|
|
* the resulting numbers of channels and RX queues.
|
|
*/
|
|
static int efx_probe_interrupts(struct efx_nic *efx)
|
|
{
|
|
unsigned int extra_channels = 0;
|
|
unsigned int i, j;
|
|
int rc;
|
|
|
|
for (i = 0; i < EFX_MAX_EXTRA_CHANNELS; i++)
|
|
if (efx->extra_channel_type[i])
|
|
++extra_channels;
|
|
|
|
if (efx->interrupt_mode == EFX_INT_MODE_MSIX) {
|
|
struct msix_entry xentries[EFX_MAX_CHANNELS];
|
|
unsigned int n_channels;
|
|
|
|
n_channels = efx_wanted_parallelism(efx);
|
|
if (efx_separate_tx_channels)
|
|
n_channels *= 2;
|
|
n_channels += extra_channels;
|
|
n_channels = min(n_channels, efx->max_channels);
|
|
|
|
for (i = 0; i < n_channels; i++)
|
|
xentries[i].entry = i;
|
|
rc = pci_enable_msix_range(efx->pci_dev,
|
|
xentries, 1, n_channels);
|
|
if (rc < 0) {
|
|
/* Fall back to single channel MSI */
|
|
netif_err(efx, drv, efx->net_dev,
|
|
"could not enable MSI-X\n");
|
|
if (efx->type->min_interrupt_mode >= EFX_INT_MODE_MSI)
|
|
efx->interrupt_mode = EFX_INT_MODE_MSI;
|
|
else
|
|
return rc;
|
|
} else if (rc < n_channels) {
|
|
netif_err(efx, drv, efx->net_dev,
|
|
"WARNING: Insufficient MSI-X vectors"
|
|
" available (%d < %u).\n", rc, n_channels);
|
|
netif_err(efx, drv, efx->net_dev,
|
|
"WARNING: Performance may be reduced.\n");
|
|
n_channels = rc;
|
|
}
|
|
|
|
if (rc > 0) {
|
|
efx->n_channels = n_channels;
|
|
if (n_channels > extra_channels)
|
|
n_channels -= extra_channels;
|
|
if (efx_separate_tx_channels) {
|
|
efx->n_tx_channels = min(max(n_channels / 2,
|
|
1U),
|
|
efx->max_tx_channels);
|
|
efx->n_rx_channels = max(n_channels -
|
|
efx->n_tx_channels,
|
|
1U);
|
|
} else {
|
|
efx->n_tx_channels = min(n_channels,
|
|
efx->max_tx_channels);
|
|
efx->n_rx_channels = n_channels;
|
|
}
|
|
for (i = 0; i < efx->n_channels; i++)
|
|
efx_get_channel(efx, i)->irq =
|
|
xentries[i].vector;
|
|
}
|
|
}
|
|
|
|
/* Try single interrupt MSI */
|
|
if (efx->interrupt_mode == EFX_INT_MODE_MSI) {
|
|
efx->n_channels = 1;
|
|
efx->n_rx_channels = 1;
|
|
efx->n_tx_channels = 1;
|
|
rc = pci_enable_msi(efx->pci_dev);
|
|
if (rc == 0) {
|
|
efx_get_channel(efx, 0)->irq = efx->pci_dev->irq;
|
|
} else {
|
|
netif_err(efx, drv, efx->net_dev,
|
|
"could not enable MSI\n");
|
|
if (efx->type->min_interrupt_mode >= EFX_INT_MODE_LEGACY)
|
|
efx->interrupt_mode = EFX_INT_MODE_LEGACY;
|
|
else
|
|
return rc;
|
|
}
|
|
}
|
|
|
|
/* Assume legacy interrupts */
|
|
if (efx->interrupt_mode == EFX_INT_MODE_LEGACY) {
|
|
efx->n_channels = 1 + (efx_separate_tx_channels ? 1 : 0);
|
|
efx->n_rx_channels = 1;
|
|
efx->n_tx_channels = 1;
|
|
efx->legacy_irq = efx->pci_dev->irq;
|
|
}
|
|
|
|
/* Assign extra channels if possible */
|
|
efx->n_extra_tx_channels = 0;
|
|
j = efx->n_channels;
|
|
for (i = 0; i < EFX_MAX_EXTRA_CHANNELS; i++) {
|
|
if (!efx->extra_channel_type[i])
|
|
continue;
|
|
if (efx->interrupt_mode != EFX_INT_MODE_MSIX ||
|
|
efx->n_channels <= extra_channels) {
|
|
efx->extra_channel_type[i]->handle_no_channel(efx);
|
|
} else {
|
|
--j;
|
|
efx_get_channel(efx, j)->type =
|
|
efx->extra_channel_type[i];
|
|
if (efx_channel_has_tx_queues(efx_get_channel(efx, j)))
|
|
efx->n_extra_tx_channels++;
|
|
}
|
|
}
|
|
|
|
/* RSS might be usable on VFs even if it is disabled on the PF */
|
|
#ifdef CONFIG_SFC_SRIOV
|
|
if (efx->type->sriov_wanted) {
|
|
efx->rss_spread = ((efx->n_rx_channels > 1 ||
|
|
!efx->type->sriov_wanted(efx)) ?
|
|
efx->n_rx_channels : efx_vf_size(efx));
|
|
return 0;
|
|
}
|
|
#endif
|
|
efx->rss_spread = efx->n_rx_channels;
|
|
|
|
return 0;
|
|
}
|
|
|
|
#if defined(CONFIG_SMP)
|
|
static void efx_set_interrupt_affinity(struct efx_nic *efx)
|
|
{
|
|
struct efx_channel *channel;
|
|
unsigned int cpu;
|
|
|
|
efx_for_each_channel(channel, efx) {
|
|
cpu = cpumask_local_spread(channel->channel,
|
|
pcibus_to_node(efx->pci_dev->bus));
|
|
irq_set_affinity_hint(channel->irq, cpumask_of(cpu));
|
|
}
|
|
}
|
|
|
|
static void efx_clear_interrupt_affinity(struct efx_nic *efx)
|
|
{
|
|
struct efx_channel *channel;
|
|
|
|
efx_for_each_channel(channel, efx)
|
|
irq_set_affinity_hint(channel->irq, NULL);
|
|
}
|
|
#else
|
|
static void
|
|
efx_set_interrupt_affinity(struct efx_nic *efx __attribute__ ((unused)))
|
|
{
|
|
}
|
|
|
|
static void
|
|
efx_clear_interrupt_affinity(struct efx_nic *efx __attribute__ ((unused)))
|
|
{
|
|
}
|
|
#endif /* CONFIG_SMP */
|
|
|
|
static int efx_soft_enable_interrupts(struct efx_nic *efx)
|
|
{
|
|
struct efx_channel *channel, *end_channel;
|
|
int rc;
|
|
|
|
BUG_ON(efx->state == STATE_DISABLED);
|
|
|
|
efx->irq_soft_enabled = true;
|
|
smp_wmb();
|
|
|
|
efx_for_each_channel(channel, efx) {
|
|
if (!channel->type->keep_eventq) {
|
|
rc = efx_init_eventq(channel);
|
|
if (rc)
|
|
goto fail;
|
|
}
|
|
efx_start_eventq(channel);
|
|
}
|
|
|
|
efx_mcdi_mode_event(efx);
|
|
|
|
return 0;
|
|
fail:
|
|
end_channel = channel;
|
|
efx_for_each_channel(channel, efx) {
|
|
if (channel == end_channel)
|
|
break;
|
|
efx_stop_eventq(channel);
|
|
if (!channel->type->keep_eventq)
|
|
efx_fini_eventq(channel);
|
|
}
|
|
|
|
return rc;
|
|
}
|
|
|
|
static void efx_soft_disable_interrupts(struct efx_nic *efx)
|
|
{
|
|
struct efx_channel *channel;
|
|
|
|
if (efx->state == STATE_DISABLED)
|
|
return;
|
|
|
|
efx_mcdi_mode_poll(efx);
|
|
|
|
efx->irq_soft_enabled = false;
|
|
smp_wmb();
|
|
|
|
if (efx->legacy_irq)
|
|
synchronize_irq(efx->legacy_irq);
|
|
|
|
efx_for_each_channel(channel, efx) {
|
|
if (channel->irq)
|
|
synchronize_irq(channel->irq);
|
|
|
|
efx_stop_eventq(channel);
|
|
if (!channel->type->keep_eventq)
|
|
efx_fini_eventq(channel);
|
|
}
|
|
|
|
/* Flush the asynchronous MCDI request queue */
|
|
efx_mcdi_flush_async(efx);
|
|
}
|
|
|
|
static int efx_enable_interrupts(struct efx_nic *efx)
|
|
{
|
|
struct efx_channel *channel, *end_channel;
|
|
int rc;
|
|
|
|
BUG_ON(efx->state == STATE_DISABLED);
|
|
|
|
if (efx->eeh_disabled_legacy_irq) {
|
|
enable_irq(efx->legacy_irq);
|
|
efx->eeh_disabled_legacy_irq = false;
|
|
}
|
|
|
|
efx->type->irq_enable_master(efx);
|
|
|
|
efx_for_each_channel(channel, efx) {
|
|
if (channel->type->keep_eventq) {
|
|
rc = efx_init_eventq(channel);
|
|
if (rc)
|
|
goto fail;
|
|
}
|
|
}
|
|
|
|
rc = efx_soft_enable_interrupts(efx);
|
|
if (rc)
|
|
goto fail;
|
|
|
|
return 0;
|
|
|
|
fail:
|
|
end_channel = channel;
|
|
efx_for_each_channel(channel, efx) {
|
|
if (channel == end_channel)
|
|
break;
|
|
if (channel->type->keep_eventq)
|
|
efx_fini_eventq(channel);
|
|
}
|
|
|
|
efx->type->irq_disable_non_ev(efx);
|
|
|
|
return rc;
|
|
}
|
|
|
|
static void efx_disable_interrupts(struct efx_nic *efx)
|
|
{
|
|
struct efx_channel *channel;
|
|
|
|
efx_soft_disable_interrupts(efx);
|
|
|
|
efx_for_each_channel(channel, efx) {
|
|
if (channel->type->keep_eventq)
|
|
efx_fini_eventq(channel);
|
|
}
|
|
|
|
efx->type->irq_disable_non_ev(efx);
|
|
}
|
|
|
|
static void efx_remove_interrupts(struct efx_nic *efx)
|
|
{
|
|
struct efx_channel *channel;
|
|
|
|
/* Remove MSI/MSI-X interrupts */
|
|
efx_for_each_channel(channel, efx)
|
|
channel->irq = 0;
|
|
pci_disable_msi(efx->pci_dev);
|
|
pci_disable_msix(efx->pci_dev);
|
|
|
|
/* Remove legacy interrupt */
|
|
efx->legacy_irq = 0;
|
|
}
|
|
|
|
static void efx_set_channels(struct efx_nic *efx)
|
|
{
|
|
struct efx_channel *channel;
|
|
struct efx_tx_queue *tx_queue;
|
|
|
|
efx->tx_channel_offset =
|
|
efx_separate_tx_channels ?
|
|
efx->n_channels - efx->n_tx_channels : 0;
|
|
|
|
/* We need to mark which channels really have RX and TX
|
|
* queues, and adjust the TX queue numbers if we have separate
|
|
* RX-only and TX-only channels.
|
|
*/
|
|
efx_for_each_channel(channel, efx) {
|
|
if (channel->channel < efx->n_rx_channels)
|
|
channel->rx_queue.core_index = channel->channel;
|
|
else
|
|
channel->rx_queue.core_index = -1;
|
|
|
|
efx_for_each_channel_tx_queue(tx_queue, channel)
|
|
tx_queue->queue -= (efx->tx_channel_offset *
|
|
EFX_TXQ_TYPES);
|
|
}
|
|
}
|
|
|
|
static int efx_probe_nic(struct efx_nic *efx)
|
|
{
|
|
int rc;
|
|
|
|
netif_dbg(efx, probe, efx->net_dev, "creating NIC\n");
|
|
|
|
/* Carry out hardware-type specific initialisation */
|
|
rc = efx->type->probe(efx);
|
|
if (rc)
|
|
return rc;
|
|
|
|
do {
|
|
if (!efx->max_channels || !efx->max_tx_channels) {
|
|
netif_err(efx, drv, efx->net_dev,
|
|
"Insufficient resources to allocate"
|
|
" any channels\n");
|
|
rc = -ENOSPC;
|
|
goto fail1;
|
|
}
|
|
|
|
/* Determine the number of channels and queues by trying
|
|
* to hook in MSI-X interrupts.
|
|
*/
|
|
rc = efx_probe_interrupts(efx);
|
|
if (rc)
|
|
goto fail1;
|
|
|
|
efx_set_channels(efx);
|
|
|
|
/* dimension_resources can fail with EAGAIN */
|
|
rc = efx->type->dimension_resources(efx);
|
|
if (rc != 0 && rc != -EAGAIN)
|
|
goto fail2;
|
|
|
|
if (rc == -EAGAIN)
|
|
/* try again with new max_channels */
|
|
efx_remove_interrupts(efx);
|
|
|
|
} while (rc == -EAGAIN);
|
|
|
|
if (efx->n_channels > 1)
|
|
netdev_rss_key_fill(efx->rss_context.rx_hash_key,
|
|
sizeof(efx->rss_context.rx_hash_key));
|
|
efx_set_default_rx_indir_table(efx, &efx->rss_context);
|
|
|
|
netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels);
|
|
netif_set_real_num_rx_queues(efx->net_dev, efx->n_rx_channels);
|
|
|
|
/* Initialise the interrupt moderation settings */
|
|
efx->irq_mod_step_us = DIV_ROUND_UP(efx->timer_quantum_ns, 1000);
|
|
efx_init_irq_moderation(efx, tx_irq_mod_usec, rx_irq_mod_usec, true,
|
|
true);
|
|
|
|
return 0;
|
|
|
|
fail2:
|
|
efx_remove_interrupts(efx);
|
|
fail1:
|
|
efx->type->remove(efx);
|
|
return rc;
|
|
}
|
|
|
|
static void efx_remove_nic(struct efx_nic *efx)
|
|
{
|
|
netif_dbg(efx, drv, efx->net_dev, "destroying NIC\n");
|
|
|
|
efx_remove_interrupts(efx);
|
|
efx->type->remove(efx);
|
|
}
|
|
|
|
static int efx_probe_filters(struct efx_nic *efx)
|
|
{
|
|
int rc;
|
|
|
|
init_rwsem(&efx->filter_sem);
|
|
mutex_lock(&efx->mac_lock);
|
|
down_write(&efx->filter_sem);
|
|
rc = efx->type->filter_table_probe(efx);
|
|
if (rc)
|
|
goto out_unlock;
|
|
|
|
#ifdef CONFIG_RFS_ACCEL
|
|
if (efx->type->offload_features & NETIF_F_NTUPLE) {
|
|
struct efx_channel *channel;
|
|
int i, success = 1;
|
|
|
|
efx_for_each_channel(channel, efx) {
|
|
channel->rps_flow_id =
|
|
kcalloc(efx->type->max_rx_ip_filters,
|
|
sizeof(*channel->rps_flow_id),
|
|
GFP_KERNEL);
|
|
if (!channel->rps_flow_id)
|
|
success = 0;
|
|
else
|
|
for (i = 0;
|
|
i < efx->type->max_rx_ip_filters;
|
|
++i)
|
|
channel->rps_flow_id[i] =
|
|
RPS_FLOW_ID_INVALID;
|
|
}
|
|
|
|
if (!success) {
|
|
efx_for_each_channel(channel, efx)
|
|
kfree(channel->rps_flow_id);
|
|
efx->type->filter_table_remove(efx);
|
|
rc = -ENOMEM;
|
|
goto out_unlock;
|
|
}
|
|
|
|
efx->rps_expire_index = efx->rps_expire_channel = 0;
|
|
}
|
|
#endif
|
|
out_unlock:
|
|
up_write(&efx->filter_sem);
|
|
mutex_unlock(&efx->mac_lock);
|
|
return rc;
|
|
}
|
|
|
|
static void efx_remove_filters(struct efx_nic *efx)
|
|
{
|
|
#ifdef CONFIG_RFS_ACCEL
|
|
struct efx_channel *channel;
|
|
|
|
efx_for_each_channel(channel, efx)
|
|
kfree(channel->rps_flow_id);
|
|
#endif
|
|
down_write(&efx->filter_sem);
|
|
efx->type->filter_table_remove(efx);
|
|
up_write(&efx->filter_sem);
|
|
}
|
|
|
|
|
|
/**************************************************************************
|
|
*
|
|
* NIC startup/shutdown
|
|
*
|
|
*************************************************************************/
|
|
|
|
static int efx_probe_all(struct efx_nic *efx)
|
|
{
|
|
int rc;
|
|
|
|
rc = efx_probe_nic(efx);
|
|
if (rc) {
|
|
netif_err(efx, probe, efx->net_dev, "failed to create NIC\n");
|
|
goto fail1;
|
|
}
|
|
|
|
rc = efx_probe_port(efx);
|
|
if (rc) {
|
|
netif_err(efx, probe, efx->net_dev, "failed to create port\n");
|
|
goto fail2;
|
|
}
|
|
|
|
BUILD_BUG_ON(EFX_DEFAULT_DMAQ_SIZE < EFX_RXQ_MIN_ENT);
|
|
if (WARN_ON(EFX_DEFAULT_DMAQ_SIZE < EFX_TXQ_MIN_ENT(efx))) {
|
|
rc = -EINVAL;
|
|
goto fail3;
|
|
}
|
|
efx->rxq_entries = efx->txq_entries = EFX_DEFAULT_DMAQ_SIZE;
|
|
|
|
#ifdef CONFIG_SFC_SRIOV
|
|
rc = efx->type->vswitching_probe(efx);
|
|
if (rc) /* not fatal; the PF will still work fine */
|
|
netif_warn(efx, probe, efx->net_dev,
|
|
"failed to setup vswitching rc=%d;"
|
|
" VFs may not function\n", rc);
|
|
#endif
|
|
|
|
rc = efx_probe_filters(efx);
|
|
if (rc) {
|
|
netif_err(efx, probe, efx->net_dev,
|
|
"failed to create filter tables\n");
|
|
goto fail4;
|
|
}
|
|
|
|
rc = efx_probe_channels(efx);
|
|
if (rc)
|
|
goto fail5;
|
|
|
|
return 0;
|
|
|
|
fail5:
|
|
efx_remove_filters(efx);
|
|
fail4:
|
|
#ifdef CONFIG_SFC_SRIOV
|
|
efx->type->vswitching_remove(efx);
|
|
#endif
|
|
fail3:
|
|
efx_remove_port(efx);
|
|
fail2:
|
|
efx_remove_nic(efx);
|
|
fail1:
|
|
return rc;
|
|
}
|
|
|
|
/* If the interface is supposed to be running but is not, start
|
|
* the hardware and software data path, regular activity for the port
|
|
* (MAC statistics, link polling, etc.) and schedule the port to be
|
|
* reconfigured. Interrupts must already be enabled. This function
|
|
* is safe to call multiple times, so long as the NIC is not disabled.
|
|
* Requires the RTNL lock.
|
|
*/
|
|
static void efx_start_all(struct efx_nic *efx)
|
|
{
|
|
EFX_ASSERT_RESET_SERIALISED(efx);
|
|
BUG_ON(efx->state == STATE_DISABLED);
|
|
|
|
/* Check that it is appropriate to restart the interface. All
|
|
* of these flags are safe to read under just the rtnl lock */
|
|
if (efx->port_enabled || !netif_running(efx->net_dev) ||
|
|
efx->reset_pending)
|
|
return;
|
|
|
|
efx_start_port(efx);
|
|
efx_start_datapath(efx);
|
|
|
|
/* Start the hardware monitor if there is one */
|
|
if (efx->type->monitor != NULL)
|
|
queue_delayed_work(efx->workqueue, &efx->monitor_work,
|
|
efx_monitor_interval);
|
|
|
|
/* Link state detection is normally event-driven; we have
|
|
* to poll now because we could have missed a change
|
|
*/
|
|
mutex_lock(&efx->mac_lock);
|
|
if (efx->phy_op->poll(efx))
|
|
efx_link_status_changed(efx);
|
|
mutex_unlock(&efx->mac_lock);
|
|
|
|
efx->type->start_stats(efx);
|
|
efx->type->pull_stats(efx);
|
|
spin_lock_bh(&efx->stats_lock);
|
|
efx->type->update_stats(efx, NULL, NULL);
|
|
spin_unlock_bh(&efx->stats_lock);
|
|
}
|
|
|
|
/* Quiesce the hardware and software data path, and regular activity
|
|
* for the port without bringing the link down. Safe to call multiple
|
|
* times with the NIC in almost any state, but interrupts should be
|
|
* enabled. Requires the RTNL lock.
|
|
*/
|
|
static void efx_stop_all(struct efx_nic *efx)
|
|
{
|
|
EFX_ASSERT_RESET_SERIALISED(efx);
|
|
|
|
/* port_enabled can be read safely under the rtnl lock */
|
|
if (!efx->port_enabled)
|
|
return;
|
|
|
|
/* update stats before we go down so we can accurately count
|
|
* rx_nodesc_drops
|
|
*/
|
|
efx->type->pull_stats(efx);
|
|
spin_lock_bh(&efx->stats_lock);
|
|
efx->type->update_stats(efx, NULL, NULL);
|
|
spin_unlock_bh(&efx->stats_lock);
|
|
efx->type->stop_stats(efx);
|
|
efx_stop_port(efx);
|
|
|
|
/* Stop the kernel transmit interface. This is only valid if
|
|
* the device is stopped or detached; otherwise the watchdog
|
|
* may fire immediately.
|
|
*/
|
|
WARN_ON(netif_running(efx->net_dev) &&
|
|
netif_device_present(efx->net_dev));
|
|
netif_tx_disable(efx->net_dev);
|
|
|
|
efx_stop_datapath(efx);
|
|
}
|
|
|
|
static void efx_remove_all(struct efx_nic *efx)
|
|
{
|
|
efx_remove_channels(efx);
|
|
efx_remove_filters(efx);
|
|
#ifdef CONFIG_SFC_SRIOV
|
|
efx->type->vswitching_remove(efx);
|
|
#endif
|
|
efx_remove_port(efx);
|
|
efx_remove_nic(efx);
|
|
}
|
|
|
|
/**************************************************************************
|
|
*
|
|
* Interrupt moderation
|
|
*
|
|
**************************************************************************/
|
|
unsigned int efx_usecs_to_ticks(struct efx_nic *efx, unsigned int usecs)
|
|
{
|
|
if (usecs == 0)
|
|
return 0;
|
|
if (usecs * 1000 < efx->timer_quantum_ns)
|
|
return 1; /* never round down to 0 */
|
|
return usecs * 1000 / efx->timer_quantum_ns;
|
|
}
|
|
|
|
unsigned int efx_ticks_to_usecs(struct efx_nic *efx, unsigned int ticks)
|
|
{
|
|
/* We must round up when converting ticks to microseconds
|
|
* because we round down when converting the other way.
|
|
*/
|
|
return DIV_ROUND_UP(ticks * efx->timer_quantum_ns, 1000);
|
|
}
|
|
|
|
/* Set interrupt moderation parameters */
|
|
int efx_init_irq_moderation(struct efx_nic *efx, unsigned int tx_usecs,
|
|
unsigned int rx_usecs, bool rx_adaptive,
|
|
bool rx_may_override_tx)
|
|
{
|
|
struct efx_channel *channel;
|
|
unsigned int timer_max_us;
|
|
|
|
EFX_ASSERT_RESET_SERIALISED(efx);
|
|
|
|
timer_max_us = efx->timer_max_ns / 1000;
|
|
|
|
if (tx_usecs > timer_max_us || rx_usecs > timer_max_us)
|
|
return -EINVAL;
|
|
|
|
if (tx_usecs != rx_usecs && efx->tx_channel_offset == 0 &&
|
|
!rx_may_override_tx) {
|
|
netif_err(efx, drv, efx->net_dev, "Channels are shared. "
|
|
"RX and TX IRQ moderation must be equal\n");
|
|
return -EINVAL;
|
|
}
|
|
|
|
efx->irq_rx_adaptive = rx_adaptive;
|
|
efx->irq_rx_moderation_us = rx_usecs;
|
|
efx_for_each_channel(channel, efx) {
|
|
if (efx_channel_has_rx_queue(channel))
|
|
channel->irq_moderation_us = rx_usecs;
|
|
else if (efx_channel_has_tx_queues(channel))
|
|
channel->irq_moderation_us = tx_usecs;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
void efx_get_irq_moderation(struct efx_nic *efx, unsigned int *tx_usecs,
|
|
unsigned int *rx_usecs, bool *rx_adaptive)
|
|
{
|
|
*rx_adaptive = efx->irq_rx_adaptive;
|
|
*rx_usecs = efx->irq_rx_moderation_us;
|
|
|
|
/* If channels are shared between RX and TX, so is IRQ
|
|
* moderation. Otherwise, IRQ moderation is the same for all
|
|
* TX channels and is not adaptive.
|
|
*/
|
|
if (efx->tx_channel_offset == 0) {
|
|
*tx_usecs = *rx_usecs;
|
|
} else {
|
|
struct efx_channel *tx_channel;
|
|
|
|
tx_channel = efx->channel[efx->tx_channel_offset];
|
|
*tx_usecs = tx_channel->irq_moderation_us;
|
|
}
|
|
}
|
|
|
|
/**************************************************************************
|
|
*
|
|
* Hardware monitor
|
|
*
|
|
**************************************************************************/
|
|
|
|
/* Run periodically off the general workqueue */
|
|
static void efx_monitor(struct work_struct *data)
|
|
{
|
|
struct efx_nic *efx = container_of(data, struct efx_nic,
|
|
monitor_work.work);
|
|
|
|
netif_vdbg(efx, timer, efx->net_dev,
|
|
"hardware monitor executing on CPU %d\n",
|
|
raw_smp_processor_id());
|
|
BUG_ON(efx->type->monitor == NULL);
|
|
|
|
/* If the mac_lock is already held then it is likely a port
|
|
* reconfiguration is already in place, which will likely do
|
|
* most of the work of monitor() anyway. */
|
|
if (mutex_trylock(&efx->mac_lock)) {
|
|
if (efx->port_enabled)
|
|
efx->type->monitor(efx);
|
|
mutex_unlock(&efx->mac_lock);
|
|
}
|
|
|
|
queue_delayed_work(efx->workqueue, &efx->monitor_work,
|
|
efx_monitor_interval);
|
|
}
|
|
|
|
/**************************************************************************
|
|
*
|
|
* ioctls
|
|
*
|
|
*************************************************************************/
|
|
|
|
/* Net device ioctl
|
|
* Context: process, rtnl_lock() held.
|
|
*/
|
|
static int efx_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd)
|
|
{
|
|
struct efx_nic *efx = netdev_priv(net_dev);
|
|
struct mii_ioctl_data *data = if_mii(ifr);
|
|
|
|
if (cmd == SIOCSHWTSTAMP)
|
|
return efx_ptp_set_ts_config(efx, ifr);
|
|
if (cmd == SIOCGHWTSTAMP)
|
|
return efx_ptp_get_ts_config(efx, ifr);
|
|
|
|
/* Convert phy_id from older PRTAD/DEVAD format */
|
|
if ((cmd == SIOCGMIIREG || cmd == SIOCSMIIREG) &&
|
|
(data->phy_id & 0xfc00) == 0x0400)
|
|
data->phy_id ^= MDIO_PHY_ID_C45 | 0x0400;
|
|
|
|
return mdio_mii_ioctl(&efx->mdio, data, cmd);
|
|
}
|
|
|
|
/**************************************************************************
|
|
*
|
|
* NAPI interface
|
|
*
|
|
**************************************************************************/
|
|
|
|
static void efx_init_napi_channel(struct efx_channel *channel)
|
|
{
|
|
struct efx_nic *efx = channel->efx;
|
|
|
|
channel->napi_dev = efx->net_dev;
|
|
netif_napi_add(channel->napi_dev, &channel->napi_str,
|
|
efx_poll, napi_weight);
|
|
}
|
|
|
|
static void efx_init_napi(struct efx_nic *efx)
|
|
{
|
|
struct efx_channel *channel;
|
|
|
|
efx_for_each_channel(channel, efx)
|
|
efx_init_napi_channel(channel);
|
|
}
|
|
|
|
static void efx_fini_napi_channel(struct efx_channel *channel)
|
|
{
|
|
if (channel->napi_dev)
|
|
netif_napi_del(&channel->napi_str);
|
|
|
|
channel->napi_dev = NULL;
|
|
}
|
|
|
|
static void efx_fini_napi(struct efx_nic *efx)
|
|
{
|
|
struct efx_channel *channel;
|
|
|
|
efx_for_each_channel(channel, efx)
|
|
efx_fini_napi_channel(channel);
|
|
}
|
|
|
|
/**************************************************************************
|
|
*
|
|
* Kernel net device interface
|
|
*
|
|
*************************************************************************/
|
|
|
|
/* Context: process, rtnl_lock() held. */
|
|
int efx_net_open(struct net_device *net_dev)
|
|
{
|
|
struct efx_nic *efx = netdev_priv(net_dev);
|
|
int rc;
|
|
|
|
netif_dbg(efx, ifup, efx->net_dev, "opening device on CPU %d\n",
|
|
raw_smp_processor_id());
|
|
|
|
rc = efx_check_disabled(efx);
|
|
if (rc)
|
|
return rc;
|
|
if (efx->phy_mode & PHY_MODE_SPECIAL)
|
|
return -EBUSY;
|
|
if (efx_mcdi_poll_reboot(efx) && efx_reset(efx, RESET_TYPE_ALL))
|
|
return -EIO;
|
|
|
|
/* Notify the kernel of the link state polled during driver load,
|
|
* before the monitor starts running */
|
|
efx_link_status_changed(efx);
|
|
|
|
efx_start_all(efx);
|
|
if (efx->state == STATE_DISABLED || efx->reset_pending)
|
|
netif_device_detach(efx->net_dev);
|
|
efx_selftest_async_start(efx);
|
|
return 0;
|
|
}
|
|
|
|
/* Context: process, rtnl_lock() held.
|
|
* Note that the kernel will ignore our return code; this method
|
|
* should really be a void.
|
|
*/
|
|
int efx_net_stop(struct net_device *net_dev)
|
|
{
|
|
struct efx_nic *efx = netdev_priv(net_dev);
|
|
|
|
netif_dbg(efx, ifdown, efx->net_dev, "closing on CPU %d\n",
|
|
raw_smp_processor_id());
|
|
|
|
/* Stop the device and flush all the channels */
|
|
efx_stop_all(efx);
|
|
|
|
return 0;
|
|
}
|
|
|
|
/* Context: process, dev_base_lock or RTNL held, non-blocking. */
|
|
static void efx_net_stats(struct net_device *net_dev,
|
|
struct rtnl_link_stats64 *stats)
|
|
{
|
|
struct efx_nic *efx = netdev_priv(net_dev);
|
|
|
|
spin_lock_bh(&efx->stats_lock);
|
|
efx->type->update_stats(efx, NULL, stats);
|
|
spin_unlock_bh(&efx->stats_lock);
|
|
}
|
|
|
|
/* Context: netif_tx_lock held, BHs disabled. */
|
|
static void efx_watchdog(struct net_device *net_dev)
|
|
{
|
|
struct efx_nic *efx = netdev_priv(net_dev);
|
|
|
|
netif_err(efx, tx_err, efx->net_dev,
|
|
"TX stuck with port_enabled=%d: resetting channels\n",
|
|
efx->port_enabled);
|
|
|
|
efx_schedule_reset(efx, RESET_TYPE_TX_WATCHDOG);
|
|
}
|
|
|
|
|
|
/* Context: process, rtnl_lock() held. */
|
|
static int efx_change_mtu(struct net_device *net_dev, int new_mtu)
|
|
{
|
|
struct efx_nic *efx = netdev_priv(net_dev);
|
|
int rc;
|
|
|
|
rc = efx_check_disabled(efx);
|
|
if (rc)
|
|
return rc;
|
|
|
|
netif_dbg(efx, drv, efx->net_dev, "changing MTU to %d\n", new_mtu);
|
|
|
|
efx_device_detach_sync(efx);
|
|
efx_stop_all(efx);
|
|
|
|
mutex_lock(&efx->mac_lock);
|
|
net_dev->mtu = new_mtu;
|
|
efx_mac_reconfigure(efx);
|
|
mutex_unlock(&efx->mac_lock);
|
|
|
|
efx_start_all(efx);
|
|
efx_device_attach_if_not_resetting(efx);
|
|
return 0;
|
|
}
|
|
|
|
static int efx_set_mac_address(struct net_device *net_dev, void *data)
|
|
{
|
|
struct efx_nic *efx = netdev_priv(net_dev);
|
|
struct sockaddr *addr = data;
|
|
u8 *new_addr = addr->sa_data;
|
|
u8 old_addr[6];
|
|
int rc;
|
|
|
|
if (!is_valid_ether_addr(new_addr)) {
|
|
netif_err(efx, drv, efx->net_dev,
|
|
"invalid ethernet MAC address requested: %pM\n",
|
|
new_addr);
|
|
return -EADDRNOTAVAIL;
|
|
}
|
|
|
|
/* save old address */
|
|
ether_addr_copy(old_addr, net_dev->dev_addr);
|
|
ether_addr_copy(net_dev->dev_addr, new_addr);
|
|
if (efx->type->set_mac_address) {
|
|
rc = efx->type->set_mac_address(efx);
|
|
if (rc) {
|
|
ether_addr_copy(net_dev->dev_addr, old_addr);
|
|
return rc;
|
|
}
|
|
}
|
|
|
|
/* Reconfigure the MAC */
|
|
mutex_lock(&efx->mac_lock);
|
|
efx_mac_reconfigure(efx);
|
|
mutex_unlock(&efx->mac_lock);
|
|
|
|
return 0;
|
|
}
|
|
|
|
/* Context: netif_addr_lock held, BHs disabled. */
|
|
static void efx_set_rx_mode(struct net_device *net_dev)
|
|
{
|
|
struct efx_nic *efx = netdev_priv(net_dev);
|
|
|
|
if (efx->port_enabled)
|
|
queue_work(efx->workqueue, &efx->mac_work);
|
|
/* Otherwise efx_start_port() will do this */
|
|
}
|
|
|
|
static int efx_set_features(struct net_device *net_dev, netdev_features_t data)
|
|
{
|
|
struct efx_nic *efx = netdev_priv(net_dev);
|
|
int rc;
|
|
|
|
/* If disabling RX n-tuple filtering, clear existing filters */
|
|
if (net_dev->features & ~data & NETIF_F_NTUPLE) {
|
|
rc = efx->type->filter_clear_rx(efx, EFX_FILTER_PRI_MANUAL);
|
|
if (rc)
|
|
return rc;
|
|
}
|
|
|
|
/* If Rx VLAN filter is changed, update filters via mac_reconfigure.
|
|
* If rx-fcs is changed, mac_reconfigure updates that too.
|
|
*/
|
|
if ((net_dev->features ^ data) & (NETIF_F_HW_VLAN_CTAG_FILTER |
|
|
NETIF_F_RXFCS)) {
|
|
/* efx_set_rx_mode() will schedule MAC work to update filters
|
|
* when a new features are finally set in net_dev.
|
|
*/
|
|
efx_set_rx_mode(net_dev);
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int efx_get_phys_port_id(struct net_device *net_dev,
|
|
struct netdev_phys_item_id *ppid)
|
|
{
|
|
struct efx_nic *efx = netdev_priv(net_dev);
|
|
|
|
if (efx->type->get_phys_port_id)
|
|
return efx->type->get_phys_port_id(efx, ppid);
|
|
else
|
|
return -EOPNOTSUPP;
|
|
}
|
|
|
|
static int efx_get_phys_port_name(struct net_device *net_dev,
|
|
char *name, size_t len)
|
|
{
|
|
struct efx_nic *efx = netdev_priv(net_dev);
|
|
|
|
if (snprintf(name, len, "p%u", efx->port_num) >= len)
|
|
return -EINVAL;
|
|
return 0;
|
|
}
|
|
|
|
static int efx_vlan_rx_add_vid(struct net_device *net_dev, __be16 proto, u16 vid)
|
|
{
|
|
struct efx_nic *efx = netdev_priv(net_dev);
|
|
|
|
if (efx->type->vlan_rx_add_vid)
|
|
return efx->type->vlan_rx_add_vid(efx, proto, vid);
|
|
else
|
|
return -EOPNOTSUPP;
|
|
}
|
|
|
|
static int efx_vlan_rx_kill_vid(struct net_device *net_dev, __be16 proto, u16 vid)
|
|
{
|
|
struct efx_nic *efx = netdev_priv(net_dev);
|
|
|
|
if (efx->type->vlan_rx_kill_vid)
|
|
return efx->type->vlan_rx_kill_vid(efx, proto, vid);
|
|
else
|
|
return -EOPNOTSUPP;
|
|
}
|
|
|
|
static int efx_udp_tunnel_type_map(enum udp_parsable_tunnel_type in)
|
|
{
|
|
switch (in) {
|
|
case UDP_TUNNEL_TYPE_VXLAN:
|
|
return TUNNEL_ENCAP_UDP_PORT_ENTRY_VXLAN;
|
|
case UDP_TUNNEL_TYPE_GENEVE:
|
|
return TUNNEL_ENCAP_UDP_PORT_ENTRY_GENEVE;
|
|
default:
|
|
return -1;
|
|
}
|
|
}
|
|
|
|
static void efx_udp_tunnel_add(struct net_device *dev, struct udp_tunnel_info *ti)
|
|
{
|
|
struct efx_nic *efx = netdev_priv(dev);
|
|
struct efx_udp_tunnel tnl;
|
|
int efx_tunnel_type;
|
|
|
|
efx_tunnel_type = efx_udp_tunnel_type_map(ti->type);
|
|
if (efx_tunnel_type < 0)
|
|
return;
|
|
|
|
tnl.type = (u16)efx_tunnel_type;
|
|
tnl.port = ti->port;
|
|
|
|
if (efx->type->udp_tnl_add_port)
|
|
(void)efx->type->udp_tnl_add_port(efx, tnl);
|
|
}
|
|
|
|
static void efx_udp_tunnel_del(struct net_device *dev, struct udp_tunnel_info *ti)
|
|
{
|
|
struct efx_nic *efx = netdev_priv(dev);
|
|
struct efx_udp_tunnel tnl;
|
|
int efx_tunnel_type;
|
|
|
|
efx_tunnel_type = efx_udp_tunnel_type_map(ti->type);
|
|
if (efx_tunnel_type < 0)
|
|
return;
|
|
|
|
tnl.type = (u16)efx_tunnel_type;
|
|
tnl.port = ti->port;
|
|
|
|
if (efx->type->udp_tnl_del_port)
|
|
(void)efx->type->udp_tnl_del_port(efx, tnl);
|
|
}
|
|
|
|
static const struct net_device_ops efx_netdev_ops = {
|
|
.ndo_open = efx_net_open,
|
|
.ndo_stop = efx_net_stop,
|
|
.ndo_get_stats64 = efx_net_stats,
|
|
.ndo_tx_timeout = efx_watchdog,
|
|
.ndo_start_xmit = efx_hard_start_xmit,
|
|
.ndo_validate_addr = eth_validate_addr,
|
|
.ndo_do_ioctl = efx_ioctl,
|
|
.ndo_change_mtu = efx_change_mtu,
|
|
.ndo_set_mac_address = efx_set_mac_address,
|
|
.ndo_set_rx_mode = efx_set_rx_mode,
|
|
.ndo_set_features = efx_set_features,
|
|
.ndo_vlan_rx_add_vid = efx_vlan_rx_add_vid,
|
|
.ndo_vlan_rx_kill_vid = efx_vlan_rx_kill_vid,
|
|
#ifdef CONFIG_SFC_SRIOV
|
|
.ndo_set_vf_mac = efx_sriov_set_vf_mac,
|
|
.ndo_set_vf_vlan = efx_sriov_set_vf_vlan,
|
|
.ndo_set_vf_spoofchk = efx_sriov_set_vf_spoofchk,
|
|
.ndo_get_vf_config = efx_sriov_get_vf_config,
|
|
.ndo_set_vf_link_state = efx_sriov_set_vf_link_state,
|
|
#endif
|
|
.ndo_get_phys_port_id = efx_get_phys_port_id,
|
|
.ndo_get_phys_port_name = efx_get_phys_port_name,
|
|
.ndo_setup_tc = efx_setup_tc,
|
|
#ifdef CONFIG_RFS_ACCEL
|
|
.ndo_rx_flow_steer = efx_filter_rfs,
|
|
#endif
|
|
.ndo_udp_tunnel_add = efx_udp_tunnel_add,
|
|
.ndo_udp_tunnel_del = efx_udp_tunnel_del,
|
|
};
|
|
|
|
static void efx_update_name(struct efx_nic *efx)
|
|
{
|
|
strcpy(efx->name, efx->net_dev->name);
|
|
efx_mtd_rename(efx);
|
|
efx_set_channel_names(efx);
|
|
}
|
|
|
|
static int efx_netdev_event(struct notifier_block *this,
|
|
unsigned long event, void *ptr)
|
|
{
|
|
struct net_device *net_dev = netdev_notifier_info_to_dev(ptr);
|
|
|
|
if ((net_dev->netdev_ops == &efx_netdev_ops) &&
|
|
event == NETDEV_CHANGENAME)
|
|
efx_update_name(netdev_priv(net_dev));
|
|
|
|
return NOTIFY_DONE;
|
|
}
|
|
|
|
static struct notifier_block efx_netdev_notifier = {
|
|
.notifier_call = efx_netdev_event,
|
|
};
|
|
|
|
static ssize_t
|
|
show_phy_type(struct device *dev, struct device_attribute *attr, char *buf)
|
|
{
|
|
struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
|
|
return sprintf(buf, "%d\n", efx->phy_type);
|
|
}
|
|
static DEVICE_ATTR(phy_type, 0444, show_phy_type, NULL);
|
|
|
|
#ifdef CONFIG_SFC_MCDI_LOGGING
|
|
static ssize_t show_mcdi_log(struct device *dev, struct device_attribute *attr,
|
|
char *buf)
|
|
{
|
|
struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
|
|
struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
|
|
|
|
return scnprintf(buf, PAGE_SIZE, "%d\n", mcdi->logging_enabled);
|
|
}
|
|
static ssize_t set_mcdi_log(struct device *dev, struct device_attribute *attr,
|
|
const char *buf, size_t count)
|
|
{
|
|
struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
|
|
struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
|
|
bool enable = count > 0 && *buf != '0';
|
|
|
|
mcdi->logging_enabled = enable;
|
|
return count;
|
|
}
|
|
static DEVICE_ATTR(mcdi_logging, 0644, show_mcdi_log, set_mcdi_log);
|
|
#endif
|
|
|
|
static int efx_register_netdev(struct efx_nic *efx)
|
|
{
|
|
struct net_device *net_dev = efx->net_dev;
|
|
struct efx_channel *channel;
|
|
int rc;
|
|
|
|
net_dev->watchdog_timeo = 5 * HZ;
|
|
net_dev->irq = efx->pci_dev->irq;
|
|
net_dev->netdev_ops = &efx_netdev_ops;
|
|
if (efx_nic_rev(efx) >= EFX_REV_HUNT_A0)
|
|
net_dev->priv_flags |= IFF_UNICAST_FLT;
|
|
net_dev->ethtool_ops = &efx_ethtool_ops;
|
|
net_dev->gso_max_segs = EFX_TSO_MAX_SEGS;
|
|
net_dev->min_mtu = EFX_MIN_MTU;
|
|
net_dev->max_mtu = EFX_MAX_MTU;
|
|
|
|
rtnl_lock();
|
|
|
|
/* Enable resets to be scheduled and check whether any were
|
|
* already requested. If so, the NIC is probably hosed so we
|
|
* abort.
|
|
*/
|
|
efx->state = STATE_READY;
|
|
smp_mb(); /* ensure we change state before checking reset_pending */
|
|
if (efx->reset_pending) {
|
|
netif_err(efx, probe, efx->net_dev,
|
|
"aborting probe due to scheduled reset\n");
|
|
rc = -EIO;
|
|
goto fail_locked;
|
|
}
|
|
|
|
rc = dev_alloc_name(net_dev, net_dev->name);
|
|
if (rc < 0)
|
|
goto fail_locked;
|
|
efx_update_name(efx);
|
|
|
|
/* Always start with carrier off; PHY events will detect the link */
|
|
netif_carrier_off(net_dev);
|
|
|
|
rc = register_netdevice(net_dev);
|
|
if (rc)
|
|
goto fail_locked;
|
|
|
|
efx_for_each_channel(channel, efx) {
|
|
struct efx_tx_queue *tx_queue;
|
|
efx_for_each_channel_tx_queue(tx_queue, channel)
|
|
efx_init_tx_queue_core_txq(tx_queue);
|
|
}
|
|
|
|
efx_associate(efx);
|
|
|
|
rtnl_unlock();
|
|
|
|
rc = device_create_file(&efx->pci_dev->dev, &dev_attr_phy_type);
|
|
if (rc) {
|
|
netif_err(efx, drv, efx->net_dev,
|
|
"failed to init net dev attributes\n");
|
|
goto fail_registered;
|
|
}
|
|
#ifdef CONFIG_SFC_MCDI_LOGGING
|
|
rc = device_create_file(&efx->pci_dev->dev, &dev_attr_mcdi_logging);
|
|
if (rc) {
|
|
netif_err(efx, drv, efx->net_dev,
|
|
"failed to init net dev attributes\n");
|
|
goto fail_attr_mcdi_logging;
|
|
}
|
|
#endif
|
|
|
|
return 0;
|
|
|
|
#ifdef CONFIG_SFC_MCDI_LOGGING
|
|
fail_attr_mcdi_logging:
|
|
device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type);
|
|
#endif
|
|
fail_registered:
|
|
rtnl_lock();
|
|
efx_dissociate(efx);
|
|
unregister_netdevice(net_dev);
|
|
fail_locked:
|
|
efx->state = STATE_UNINIT;
|
|
rtnl_unlock();
|
|
netif_err(efx, drv, efx->net_dev, "could not register net dev\n");
|
|
return rc;
|
|
}
|
|
|
|
static void efx_unregister_netdev(struct efx_nic *efx)
|
|
{
|
|
if (!efx->net_dev)
|
|
return;
|
|
|
|
BUG_ON(netdev_priv(efx->net_dev) != efx);
|
|
|
|
if (efx_dev_registered(efx)) {
|
|
strlcpy(efx->name, pci_name(efx->pci_dev), sizeof(efx->name));
|
|
#ifdef CONFIG_SFC_MCDI_LOGGING
|
|
device_remove_file(&efx->pci_dev->dev, &dev_attr_mcdi_logging);
|
|
#endif
|
|
device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type);
|
|
unregister_netdev(efx->net_dev);
|
|
}
|
|
}
|
|
|
|
/**************************************************************************
|
|
*
|
|
* Device reset and suspend
|
|
*
|
|
**************************************************************************/
|
|
|
|
/* Tears down the entire software state and most of the hardware state
|
|
* before reset. */
|
|
void efx_reset_down(struct efx_nic *efx, enum reset_type method)
|
|
{
|
|
EFX_ASSERT_RESET_SERIALISED(efx);
|
|
|
|
if (method == RESET_TYPE_MCDI_TIMEOUT)
|
|
efx->type->prepare_flr(efx);
|
|
|
|
efx_stop_all(efx);
|
|
efx_disable_interrupts(efx);
|
|
|
|
mutex_lock(&efx->mac_lock);
|
|
down_write(&efx->filter_sem);
|
|
mutex_lock(&efx->rss_lock);
|
|
if (efx->port_initialized && method != RESET_TYPE_INVISIBLE &&
|
|
method != RESET_TYPE_DATAPATH)
|
|
efx->phy_op->fini(efx);
|
|
efx->type->fini(efx);
|
|
}
|
|
|
|
/* This function will always ensure that the locks acquired in
|
|
* efx_reset_down() are released. A failure return code indicates
|
|
* that we were unable to reinitialise the hardware, and the
|
|
* driver should be disabled. If ok is false, then the rx and tx
|
|
* engines are not restarted, pending a RESET_DISABLE. */
|
|
int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok)
|
|
{
|
|
int rc;
|
|
|
|
EFX_ASSERT_RESET_SERIALISED(efx);
|
|
|
|
if (method == RESET_TYPE_MCDI_TIMEOUT)
|
|
efx->type->finish_flr(efx);
|
|
|
|
/* Ensure that SRAM is initialised even if we're disabling the device */
|
|
rc = efx->type->init(efx);
|
|
if (rc) {
|
|
netif_err(efx, drv, efx->net_dev, "failed to initialise NIC\n");
|
|
goto fail;
|
|
}
|
|
|
|
if (!ok)
|
|
goto fail;
|
|
|
|
if (efx->port_initialized && method != RESET_TYPE_INVISIBLE &&
|
|
method != RESET_TYPE_DATAPATH) {
|
|
rc = efx->phy_op->init(efx);
|
|
if (rc)
|
|
goto fail;
|
|
rc = efx->phy_op->reconfigure(efx);
|
|
if (rc && rc != -EPERM)
|
|
netif_err(efx, drv, efx->net_dev,
|
|
"could not restore PHY settings\n");
|
|
}
|
|
|
|
rc = efx_enable_interrupts(efx);
|
|
if (rc)
|
|
goto fail;
|
|
|
|
#ifdef CONFIG_SFC_SRIOV
|
|
rc = efx->type->vswitching_restore(efx);
|
|
if (rc) /* not fatal; the PF will still work fine */
|
|
netif_warn(efx, probe, efx->net_dev,
|
|
"failed to restore vswitching rc=%d;"
|
|
" VFs may not function\n", rc);
|
|
#endif
|
|
|
|
if (efx->type->rx_restore_rss_contexts)
|
|
efx->type->rx_restore_rss_contexts(efx);
|
|
mutex_unlock(&efx->rss_lock);
|
|
efx->type->filter_table_restore(efx);
|
|
up_write(&efx->filter_sem);
|
|
if (efx->type->sriov_reset)
|
|
efx->type->sriov_reset(efx);
|
|
|
|
mutex_unlock(&efx->mac_lock);
|
|
|
|
efx_start_all(efx);
|
|
|
|
if (efx->type->udp_tnl_push_ports)
|
|
efx->type->udp_tnl_push_ports(efx);
|
|
|
|
return 0;
|
|
|
|
fail:
|
|
efx->port_initialized = false;
|
|
|
|
mutex_unlock(&efx->rss_lock);
|
|
up_write(&efx->filter_sem);
|
|
mutex_unlock(&efx->mac_lock);
|
|
|
|
return rc;
|
|
}
|
|
|
|
/* Reset the NIC using the specified method. Note that the reset may
|
|
* fail, in which case the card will be left in an unusable state.
|
|
*
|
|
* Caller must hold the rtnl_lock.
|
|
*/
|
|
int efx_reset(struct efx_nic *efx, enum reset_type method)
|
|
{
|
|
int rc, rc2;
|
|
bool disabled;
|
|
|
|
netif_info(efx, drv, efx->net_dev, "resetting (%s)\n",
|
|
RESET_TYPE(method));
|
|
|
|
efx_device_detach_sync(efx);
|
|
efx_reset_down(efx, method);
|
|
|
|
rc = efx->type->reset(efx, method);
|
|
if (rc) {
|
|
netif_err(efx, drv, efx->net_dev, "failed to reset hardware\n");
|
|
goto out;
|
|
}
|
|
|
|
/* Clear flags for the scopes we covered. We assume the NIC and
|
|
* driver are now quiescent so that there is no race here.
|
|
*/
|
|
if (method < RESET_TYPE_MAX_METHOD)
|
|
efx->reset_pending &= -(1 << (method + 1));
|
|
else /* it doesn't fit into the well-ordered scope hierarchy */
|
|
__clear_bit(method, &efx->reset_pending);
|
|
|
|
/* Reinitialise bus-mastering, which may have been turned off before
|
|
* the reset was scheduled. This is still appropriate, even in the
|
|
* RESET_TYPE_DISABLE since this driver generally assumes the hardware
|
|
* can respond to requests. */
|
|
pci_set_master(efx->pci_dev);
|
|
|
|
out:
|
|
/* Leave device stopped if necessary */
|
|
disabled = rc ||
|
|
method == RESET_TYPE_DISABLE ||
|
|
method == RESET_TYPE_RECOVER_OR_DISABLE;
|
|
rc2 = efx_reset_up(efx, method, !disabled);
|
|
if (rc2) {
|
|
disabled = true;
|
|
if (!rc)
|
|
rc = rc2;
|
|
}
|
|
|
|
if (disabled) {
|
|
dev_close(efx->net_dev);
|
|
netif_err(efx, drv, efx->net_dev, "has been disabled\n");
|
|
efx->state = STATE_DISABLED;
|
|
} else {
|
|
netif_dbg(efx, drv, efx->net_dev, "reset complete\n");
|
|
efx_device_attach_if_not_resetting(efx);
|
|
}
|
|
return rc;
|
|
}
|
|
|
|
/* Try recovery mechanisms.
|
|
* For now only EEH is supported.
|
|
* Returns 0 if the recovery mechanisms are unsuccessful.
|
|
* Returns a non-zero value otherwise.
|
|
*/
|
|
int efx_try_recovery(struct efx_nic *efx)
|
|
{
|
|
#ifdef CONFIG_EEH
|
|
/* A PCI error can occur and not be seen by EEH because nothing
|
|
* happens on the PCI bus. In this case the driver may fail and
|
|
* schedule a 'recover or reset', leading to this recovery handler.
|
|
* Manually call the eeh failure check function.
|
|
*/
|
|
struct eeh_dev *eehdev = pci_dev_to_eeh_dev(efx->pci_dev);
|
|
if (eeh_dev_check_failure(eehdev)) {
|
|
/* The EEH mechanisms will handle the error and reset the
|
|
* device if necessary.
|
|
*/
|
|
return 1;
|
|
}
|
|
#endif
|
|
return 0;
|
|
}
|
|
|
|
static void efx_wait_for_bist_end(struct efx_nic *efx)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < BIST_WAIT_DELAY_COUNT; ++i) {
|
|
if (efx_mcdi_poll_reboot(efx))
|
|
goto out;
|
|
msleep(BIST_WAIT_DELAY_MS);
|
|
}
|
|
|
|
netif_err(efx, drv, efx->net_dev, "Warning: No MC reboot after BIST mode\n");
|
|
out:
|
|
/* Either way unset the BIST flag. If we found no reboot we probably
|
|
* won't recover, but we should try.
|
|
*/
|
|
efx->mc_bist_for_other_fn = false;
|
|
}
|
|
|
|
/* The worker thread exists so that code that cannot sleep can
|
|
* schedule a reset for later.
|
|
*/
|
|
static void efx_reset_work(struct work_struct *data)
|
|
{
|
|
struct efx_nic *efx = container_of(data, struct efx_nic, reset_work);
|
|
unsigned long pending;
|
|
enum reset_type method;
|
|
|
|
pending = READ_ONCE(efx->reset_pending);
|
|
method = fls(pending) - 1;
|
|
|
|
if (method == RESET_TYPE_MC_BIST)
|
|
efx_wait_for_bist_end(efx);
|
|
|
|
if ((method == RESET_TYPE_RECOVER_OR_DISABLE ||
|
|
method == RESET_TYPE_RECOVER_OR_ALL) &&
|
|
efx_try_recovery(efx))
|
|
return;
|
|
|
|
if (!pending)
|
|
return;
|
|
|
|
rtnl_lock();
|
|
|
|
/* We checked the state in efx_schedule_reset() but it may
|
|
* have changed by now. Now that we have the RTNL lock,
|
|
* it cannot change again.
|
|
*/
|
|
if (efx->state == STATE_READY)
|
|
(void)efx_reset(efx, method);
|
|
|
|
rtnl_unlock();
|
|
}
|
|
|
|
void efx_schedule_reset(struct efx_nic *efx, enum reset_type type)
|
|
{
|
|
enum reset_type method;
|
|
|
|
if (efx->state == STATE_RECOVERY) {
|
|
netif_dbg(efx, drv, efx->net_dev,
|
|
"recovering: skip scheduling %s reset\n",
|
|
RESET_TYPE(type));
|
|
return;
|
|
}
|
|
|
|
switch (type) {
|
|
case RESET_TYPE_INVISIBLE:
|
|
case RESET_TYPE_ALL:
|
|
case RESET_TYPE_RECOVER_OR_ALL:
|
|
case RESET_TYPE_WORLD:
|
|
case RESET_TYPE_DISABLE:
|
|
case RESET_TYPE_RECOVER_OR_DISABLE:
|
|
case RESET_TYPE_DATAPATH:
|
|
case RESET_TYPE_MC_BIST:
|
|
case RESET_TYPE_MCDI_TIMEOUT:
|
|
method = type;
|
|
netif_dbg(efx, drv, efx->net_dev, "scheduling %s reset\n",
|
|
RESET_TYPE(method));
|
|
break;
|
|
default:
|
|
method = efx->type->map_reset_reason(type);
|
|
netif_dbg(efx, drv, efx->net_dev,
|
|
"scheduling %s reset for %s\n",
|
|
RESET_TYPE(method), RESET_TYPE(type));
|
|
break;
|
|
}
|
|
|
|
set_bit(method, &efx->reset_pending);
|
|
smp_mb(); /* ensure we change reset_pending before checking state */
|
|
|
|
/* If we're not READY then just leave the flags set as the cue
|
|
* to abort probing or reschedule the reset later.
|
|
*/
|
|
if (READ_ONCE(efx->state) != STATE_READY)
|
|
return;
|
|
|
|
/* efx_process_channel() will no longer read events once a
|
|
* reset is scheduled. So switch back to poll'd MCDI completions. */
|
|
efx_mcdi_mode_poll(efx);
|
|
|
|
queue_work(reset_workqueue, &efx->reset_work);
|
|
}
|
|
|
|
/**************************************************************************
|
|
*
|
|
* List of NICs we support
|
|
*
|
|
**************************************************************************/
|
|
|
|
/* PCI device ID table */
|
|
static const struct pci_device_id efx_pci_table[] = {
|
|
{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x0803), /* SFC9020 */
|
|
.driver_data = (unsigned long) &siena_a0_nic_type},
|
|
{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x0813), /* SFL9021 */
|
|
.driver_data = (unsigned long) &siena_a0_nic_type},
|
|
{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x0903), /* SFC9120 PF */
|
|
.driver_data = (unsigned long) &efx_hunt_a0_nic_type},
|
|
{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x1903), /* SFC9120 VF */
|
|
.driver_data = (unsigned long) &efx_hunt_a0_vf_nic_type},
|
|
{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x0923), /* SFC9140 PF */
|
|
.driver_data = (unsigned long) &efx_hunt_a0_nic_type},
|
|
{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x1923), /* SFC9140 VF */
|
|
.driver_data = (unsigned long) &efx_hunt_a0_vf_nic_type},
|
|
{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x0a03), /* SFC9220 PF */
|
|
.driver_data = (unsigned long) &efx_hunt_a0_nic_type},
|
|
{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x1a03), /* SFC9220 VF */
|
|
.driver_data = (unsigned long) &efx_hunt_a0_vf_nic_type},
|
|
{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x0b03), /* SFC9250 PF */
|
|
.driver_data = (unsigned long) &efx_hunt_a0_nic_type},
|
|
{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x1b03), /* SFC9250 VF */
|
|
.driver_data = (unsigned long) &efx_hunt_a0_vf_nic_type},
|
|
{0} /* end of list */
|
|
};
|
|
|
|
/**************************************************************************
|
|
*
|
|
* Dummy PHY/MAC operations
|
|
*
|
|
* Can be used for some unimplemented operations
|
|
* Needed so all function pointers are valid and do not have to be tested
|
|
* before use
|
|
*
|
|
**************************************************************************/
|
|
int efx_port_dummy_op_int(struct efx_nic *efx)
|
|
{
|
|
return 0;
|
|
}
|
|
void efx_port_dummy_op_void(struct efx_nic *efx) {}
|
|
|
|
static bool efx_port_dummy_op_poll(struct efx_nic *efx)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static const struct efx_phy_operations efx_dummy_phy_operations = {
|
|
.init = efx_port_dummy_op_int,
|
|
.reconfigure = efx_port_dummy_op_int,
|
|
.poll = efx_port_dummy_op_poll,
|
|
.fini = efx_port_dummy_op_void,
|
|
};
|
|
|
|
/**************************************************************************
|
|
*
|
|
* Data housekeeping
|
|
*
|
|
**************************************************************************/
|
|
|
|
/* This zeroes out and then fills in the invariants in a struct
|
|
* efx_nic (including all sub-structures).
|
|
*/
|
|
static int efx_init_struct(struct efx_nic *efx,
|
|
struct pci_dev *pci_dev, struct net_device *net_dev)
|
|
{
|
|
int rc = -ENOMEM, i;
|
|
|
|
/* Initialise common structures */
|
|
INIT_LIST_HEAD(&efx->node);
|
|
INIT_LIST_HEAD(&efx->secondary_list);
|
|
spin_lock_init(&efx->biu_lock);
|
|
#ifdef CONFIG_SFC_MTD
|
|
INIT_LIST_HEAD(&efx->mtd_list);
|
|
#endif
|
|
INIT_WORK(&efx->reset_work, efx_reset_work);
|
|
INIT_DELAYED_WORK(&efx->monitor_work, efx_monitor);
|
|
INIT_DELAYED_WORK(&efx->selftest_work, efx_selftest_async_work);
|
|
efx->pci_dev = pci_dev;
|
|
efx->msg_enable = debug;
|
|
efx->state = STATE_UNINIT;
|
|
strlcpy(efx->name, pci_name(pci_dev), sizeof(efx->name));
|
|
|
|
efx->net_dev = net_dev;
|
|
efx->rx_prefix_size = efx->type->rx_prefix_size;
|
|
efx->rx_ip_align =
|
|
NET_IP_ALIGN ? (efx->rx_prefix_size + NET_IP_ALIGN) % 4 : 0;
|
|
efx->rx_packet_hash_offset =
|
|
efx->type->rx_hash_offset - efx->type->rx_prefix_size;
|
|
efx->rx_packet_ts_offset =
|
|
efx->type->rx_ts_offset - efx->type->rx_prefix_size;
|
|
INIT_LIST_HEAD(&efx->rss_context.list);
|
|
mutex_init(&efx->rss_lock);
|
|
spin_lock_init(&efx->stats_lock);
|
|
efx->vi_stride = EFX_DEFAULT_VI_STRIDE;
|
|
efx->num_mac_stats = MC_CMD_MAC_NSTATS;
|
|
BUILD_BUG_ON(MC_CMD_MAC_NSTATS - 1 != MC_CMD_MAC_GENERATION_END);
|
|
mutex_init(&efx->mac_lock);
|
|
#ifdef CONFIG_RFS_ACCEL
|
|
mutex_init(&efx->rps_mutex);
|
|
spin_lock_init(&efx->rps_hash_lock);
|
|
/* Failure to allocate is not fatal, but may degrade ARFS performance */
|
|
efx->rps_hash_table = kcalloc(EFX_ARFS_HASH_TABLE_SIZE,
|
|
sizeof(*efx->rps_hash_table), GFP_KERNEL);
|
|
#endif
|
|
efx->phy_op = &efx_dummy_phy_operations;
|
|
efx->mdio.dev = net_dev;
|
|
INIT_WORK(&efx->mac_work, efx_mac_work);
|
|
init_waitqueue_head(&efx->flush_wq);
|
|
|
|
for (i = 0; i < EFX_MAX_CHANNELS; i++) {
|
|
efx->channel[i] = efx_alloc_channel(efx, i, NULL);
|
|
if (!efx->channel[i])
|
|
goto fail;
|
|
efx->msi_context[i].efx = efx;
|
|
efx->msi_context[i].index = i;
|
|
}
|
|
|
|
/* Higher numbered interrupt modes are less capable! */
|
|
if (WARN_ON_ONCE(efx->type->max_interrupt_mode >
|
|
efx->type->min_interrupt_mode)) {
|
|
rc = -EIO;
|
|
goto fail;
|
|
}
|
|
efx->interrupt_mode = max(efx->type->max_interrupt_mode,
|
|
interrupt_mode);
|
|
efx->interrupt_mode = min(efx->type->min_interrupt_mode,
|
|
interrupt_mode);
|
|
|
|
/* Would be good to use the net_dev name, but we're too early */
|
|
snprintf(efx->workqueue_name, sizeof(efx->workqueue_name), "sfc%s",
|
|
pci_name(pci_dev));
|
|
efx->workqueue = create_singlethread_workqueue(efx->workqueue_name);
|
|
if (!efx->workqueue)
|
|
goto fail;
|
|
|
|
return 0;
|
|
|
|
fail:
|
|
efx_fini_struct(efx);
|
|
return rc;
|
|
}
|
|
|
|
static void efx_fini_struct(struct efx_nic *efx)
|
|
{
|
|
int i;
|
|
|
|
#ifdef CONFIG_RFS_ACCEL
|
|
kfree(efx->rps_hash_table);
|
|
#endif
|
|
|
|
for (i = 0; i < EFX_MAX_CHANNELS; i++)
|
|
kfree(efx->channel[i]);
|
|
|
|
kfree(efx->vpd_sn);
|
|
|
|
if (efx->workqueue) {
|
|
destroy_workqueue(efx->workqueue);
|
|
efx->workqueue = NULL;
|
|
}
|
|
}
|
|
|
|
void efx_update_sw_stats(struct efx_nic *efx, u64 *stats)
|
|
{
|
|
u64 n_rx_nodesc_trunc = 0;
|
|
struct efx_channel *channel;
|
|
|
|
efx_for_each_channel(channel, efx)
|
|
n_rx_nodesc_trunc += channel->n_rx_nodesc_trunc;
|
|
stats[GENERIC_STAT_rx_nodesc_trunc] = n_rx_nodesc_trunc;
|
|
stats[GENERIC_STAT_rx_noskb_drops] = atomic_read(&efx->n_rx_noskb_drops);
|
|
}
|
|
|
|
bool efx_filter_spec_equal(const struct efx_filter_spec *left,
|
|
const struct efx_filter_spec *right)
|
|
{
|
|
if ((left->match_flags ^ right->match_flags) |
|
|
((left->flags ^ right->flags) &
|
|
(EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX)))
|
|
return false;
|
|
|
|
return memcmp(&left->outer_vid, &right->outer_vid,
|
|
sizeof(struct efx_filter_spec) -
|
|
offsetof(struct efx_filter_spec, outer_vid)) == 0;
|
|
}
|
|
|
|
u32 efx_filter_spec_hash(const struct efx_filter_spec *spec)
|
|
{
|
|
BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3);
|
|
return jhash2((const u32 *)&spec->outer_vid,
|
|
(sizeof(struct efx_filter_spec) -
|
|
offsetof(struct efx_filter_spec, outer_vid)) / 4,
|
|
0);
|
|
}
|
|
|
|
#ifdef CONFIG_RFS_ACCEL
|
|
bool efx_rps_check_rule(struct efx_arfs_rule *rule, unsigned int filter_idx,
|
|
bool *force)
|
|
{
|
|
if (rule->filter_id == EFX_ARFS_FILTER_ID_PENDING) {
|
|
/* ARFS is currently updating this entry, leave it */
|
|
return false;
|
|
}
|
|
if (rule->filter_id == EFX_ARFS_FILTER_ID_ERROR) {
|
|
/* ARFS tried and failed to update this, so it's probably out
|
|
* of date. Remove the filter and the ARFS rule entry.
|
|
*/
|
|
rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING;
|
|
*force = true;
|
|
return true;
|
|
} else if (WARN_ON(rule->filter_id != filter_idx)) { /* can't happen */
|
|
/* ARFS has moved on, so old filter is not needed. Since we did
|
|
* not mark the rule with EFX_ARFS_FILTER_ID_REMOVING, it will
|
|
* not be removed by efx_rps_hash_del() subsequently.
|
|
*/
|
|
*force = true;
|
|
return true;
|
|
}
|
|
/* Remove it iff ARFS wants to. */
|
|
return true;
|
|
}
|
|
|
|
static
|
|
struct hlist_head *efx_rps_hash_bucket(struct efx_nic *efx,
|
|
const struct efx_filter_spec *spec)
|
|
{
|
|
u32 hash = efx_filter_spec_hash(spec);
|
|
|
|
WARN_ON(!spin_is_locked(&efx->rps_hash_lock));
|
|
if (!efx->rps_hash_table)
|
|
return NULL;
|
|
return &efx->rps_hash_table[hash % EFX_ARFS_HASH_TABLE_SIZE];
|
|
}
|
|
|
|
struct efx_arfs_rule *efx_rps_hash_find(struct efx_nic *efx,
|
|
const struct efx_filter_spec *spec)
|
|
{
|
|
struct efx_arfs_rule *rule;
|
|
struct hlist_head *head;
|
|
struct hlist_node *node;
|
|
|
|
head = efx_rps_hash_bucket(efx, spec);
|
|
if (!head)
|
|
return NULL;
|
|
hlist_for_each(node, head) {
|
|
rule = container_of(node, struct efx_arfs_rule, node);
|
|
if (efx_filter_spec_equal(spec, &rule->spec))
|
|
return rule;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
struct efx_arfs_rule *efx_rps_hash_add(struct efx_nic *efx,
|
|
const struct efx_filter_spec *spec,
|
|
bool *new)
|
|
{
|
|
struct efx_arfs_rule *rule;
|
|
struct hlist_head *head;
|
|
struct hlist_node *node;
|
|
|
|
head = efx_rps_hash_bucket(efx, spec);
|
|
if (!head)
|
|
return NULL;
|
|
hlist_for_each(node, head) {
|
|
rule = container_of(node, struct efx_arfs_rule, node);
|
|
if (efx_filter_spec_equal(spec, &rule->spec)) {
|
|
*new = false;
|
|
return rule;
|
|
}
|
|
}
|
|
rule = kmalloc(sizeof(*rule), GFP_ATOMIC);
|
|
*new = true;
|
|
if (rule) {
|
|
memcpy(&rule->spec, spec, sizeof(rule->spec));
|
|
hlist_add_head(&rule->node, head);
|
|
}
|
|
return rule;
|
|
}
|
|
|
|
void efx_rps_hash_del(struct efx_nic *efx, const struct efx_filter_spec *spec)
|
|
{
|
|
struct efx_arfs_rule *rule;
|
|
struct hlist_head *head;
|
|
struct hlist_node *node;
|
|
|
|
head = efx_rps_hash_bucket(efx, spec);
|
|
if (WARN_ON(!head))
|
|
return;
|
|
hlist_for_each(node, head) {
|
|
rule = container_of(node, struct efx_arfs_rule, node);
|
|
if (efx_filter_spec_equal(spec, &rule->spec)) {
|
|
/* Someone already reused the entry. We know that if
|
|
* this check doesn't fire (i.e. filter_id == REMOVING)
|
|
* then the REMOVING mark was put there by our caller,
|
|
* because caller is holding a lock on filter table and
|
|
* only holders of that lock set REMOVING.
|
|
*/
|
|
if (rule->filter_id != EFX_ARFS_FILTER_ID_REMOVING)
|
|
return;
|
|
hlist_del(node);
|
|
kfree(rule);
|
|
return;
|
|
}
|
|
}
|
|
/* We didn't find it. */
|
|
WARN_ON(1);
|
|
}
|
|
#endif
|
|
|
|
/* RSS contexts. We're using linked lists and crappy O(n) algorithms, because
|
|
* (a) this is an infrequent control-plane operation and (b) n is small (max 64)
|
|
*/
|
|
struct efx_rss_context *efx_alloc_rss_context_entry(struct efx_nic *efx)
|
|
{
|
|
struct list_head *head = &efx->rss_context.list;
|
|
struct efx_rss_context *ctx, *new;
|
|
u32 id = 1; /* Don't use zero, that refers to the master RSS context */
|
|
|
|
WARN_ON(!mutex_is_locked(&efx->rss_lock));
|
|
|
|
/* Search for first gap in the numbering */
|
|
list_for_each_entry(ctx, head, list) {
|
|
if (ctx->user_id != id)
|
|
break;
|
|
id++;
|
|
/* Check for wrap. If this happens, we have nearly 2^32
|
|
* allocated RSS contexts, which seems unlikely.
|
|
*/
|
|
if (WARN_ON_ONCE(!id))
|
|
return NULL;
|
|
}
|
|
|
|
/* Create the new entry */
|
|
new = kmalloc(sizeof(struct efx_rss_context), GFP_KERNEL);
|
|
if (!new)
|
|
return NULL;
|
|
new->context_id = EFX_EF10_RSS_CONTEXT_INVALID;
|
|
new->rx_hash_udp_4tuple = false;
|
|
|
|
/* Insert the new entry into the gap */
|
|
new->user_id = id;
|
|
list_add_tail(&new->list, &ctx->list);
|
|
return new;
|
|
}
|
|
|
|
struct efx_rss_context *efx_find_rss_context_entry(struct efx_nic *efx, u32 id)
|
|
{
|
|
struct list_head *head = &efx->rss_context.list;
|
|
struct efx_rss_context *ctx;
|
|
|
|
WARN_ON(!mutex_is_locked(&efx->rss_lock));
|
|
|
|
list_for_each_entry(ctx, head, list)
|
|
if (ctx->user_id == id)
|
|
return ctx;
|
|
return NULL;
|
|
}
|
|
|
|
void efx_free_rss_context_entry(struct efx_rss_context *ctx)
|
|
{
|
|
list_del(&ctx->list);
|
|
kfree(ctx);
|
|
}
|
|
|
|
/**************************************************************************
|
|
*
|
|
* PCI interface
|
|
*
|
|
**************************************************************************/
|
|
|
|
/* Main body of final NIC shutdown code
|
|
* This is called only at module unload (or hotplug removal).
|
|
*/
|
|
static void efx_pci_remove_main(struct efx_nic *efx)
|
|
{
|
|
/* Flush reset_work. It can no longer be scheduled since we
|
|
* are not READY.
|
|
*/
|
|
BUG_ON(efx->state == STATE_READY);
|
|
cancel_work_sync(&efx->reset_work);
|
|
|
|
efx_disable_interrupts(efx);
|
|
efx_clear_interrupt_affinity(efx);
|
|
efx_nic_fini_interrupt(efx);
|
|
efx_fini_port(efx);
|
|
efx->type->fini(efx);
|
|
efx_fini_napi(efx);
|
|
efx_remove_all(efx);
|
|
}
|
|
|
|
/* Final NIC shutdown
|
|
* This is called only at module unload (or hotplug removal). A PF can call
|
|
* this on its VFs to ensure they are unbound first.
|
|
*/
|
|
static void efx_pci_remove(struct pci_dev *pci_dev)
|
|
{
|
|
struct efx_nic *efx;
|
|
|
|
efx = pci_get_drvdata(pci_dev);
|
|
if (!efx)
|
|
return;
|
|
|
|
/* Mark the NIC as fini, then stop the interface */
|
|
rtnl_lock();
|
|
efx_dissociate(efx);
|
|
dev_close(efx->net_dev);
|
|
efx_disable_interrupts(efx);
|
|
efx->state = STATE_UNINIT;
|
|
rtnl_unlock();
|
|
|
|
if (efx->type->sriov_fini)
|
|
efx->type->sriov_fini(efx);
|
|
|
|
efx_unregister_netdev(efx);
|
|
|
|
efx_mtd_remove(efx);
|
|
|
|
efx_pci_remove_main(efx);
|
|
|
|
efx_fini_io(efx);
|
|
netif_dbg(efx, drv, efx->net_dev, "shutdown successful\n");
|
|
|
|
efx_fini_struct(efx);
|
|
free_netdev(efx->net_dev);
|
|
|
|
pci_disable_pcie_error_reporting(pci_dev);
|
|
};
|
|
|
|
/* NIC VPD information
|
|
* Called during probe to display the part number of the
|
|
* installed NIC. VPD is potentially very large but this should
|
|
* always appear within the first 512 bytes.
|
|
*/
|
|
#define SFC_VPD_LEN 512
|
|
static void efx_probe_vpd_strings(struct efx_nic *efx)
|
|
{
|
|
struct pci_dev *dev = efx->pci_dev;
|
|
char vpd_data[SFC_VPD_LEN];
|
|
ssize_t vpd_size;
|
|
int ro_start, ro_size, i, j;
|
|
|
|
/* Get the vpd data from the device */
|
|
vpd_size = pci_read_vpd(dev, 0, sizeof(vpd_data), vpd_data);
|
|
if (vpd_size <= 0) {
|
|
netif_err(efx, drv, efx->net_dev, "Unable to read VPD\n");
|
|
return;
|
|
}
|
|
|
|
/* Get the Read only section */
|
|
ro_start = pci_vpd_find_tag(vpd_data, 0, vpd_size, PCI_VPD_LRDT_RO_DATA);
|
|
if (ro_start < 0) {
|
|
netif_err(efx, drv, efx->net_dev, "VPD Read-only not found\n");
|
|
return;
|
|
}
|
|
|
|
ro_size = pci_vpd_lrdt_size(&vpd_data[ro_start]);
|
|
j = ro_size;
|
|
i = ro_start + PCI_VPD_LRDT_TAG_SIZE;
|
|
if (i + j > vpd_size)
|
|
j = vpd_size - i;
|
|
|
|
/* Get the Part number */
|
|
i = pci_vpd_find_info_keyword(vpd_data, i, j, "PN");
|
|
if (i < 0) {
|
|
netif_err(efx, drv, efx->net_dev, "Part number not found\n");
|
|
return;
|
|
}
|
|
|
|
j = pci_vpd_info_field_size(&vpd_data[i]);
|
|
i += PCI_VPD_INFO_FLD_HDR_SIZE;
|
|
if (i + j > vpd_size) {
|
|
netif_err(efx, drv, efx->net_dev, "Incomplete part number\n");
|
|
return;
|
|
}
|
|
|
|
netif_info(efx, drv, efx->net_dev,
|
|
"Part Number : %.*s\n", j, &vpd_data[i]);
|
|
|
|
i = ro_start + PCI_VPD_LRDT_TAG_SIZE;
|
|
j = ro_size;
|
|
i = pci_vpd_find_info_keyword(vpd_data, i, j, "SN");
|
|
if (i < 0) {
|
|
netif_err(efx, drv, efx->net_dev, "Serial number not found\n");
|
|
return;
|
|
}
|
|
|
|
j = pci_vpd_info_field_size(&vpd_data[i]);
|
|
i += PCI_VPD_INFO_FLD_HDR_SIZE;
|
|
if (i + j > vpd_size) {
|
|
netif_err(efx, drv, efx->net_dev, "Incomplete serial number\n");
|
|
return;
|
|
}
|
|
|
|
efx->vpd_sn = kmalloc(j + 1, GFP_KERNEL);
|
|
if (!efx->vpd_sn)
|
|
return;
|
|
|
|
snprintf(efx->vpd_sn, j + 1, "%s", &vpd_data[i]);
|
|
}
|
|
|
|
|
|
/* Main body of NIC initialisation
|
|
* This is called at module load (or hotplug insertion, theoretically).
|
|
*/
|
|
static int efx_pci_probe_main(struct efx_nic *efx)
|
|
{
|
|
int rc;
|
|
|
|
/* Do start-of-day initialisation */
|
|
rc = efx_probe_all(efx);
|
|
if (rc)
|
|
goto fail1;
|
|
|
|
efx_init_napi(efx);
|
|
|
|
down_write(&efx->filter_sem);
|
|
rc = efx->type->init(efx);
|
|
up_write(&efx->filter_sem);
|
|
if (rc) {
|
|
netif_err(efx, probe, efx->net_dev,
|
|
"failed to initialise NIC\n");
|
|
goto fail3;
|
|
}
|
|
|
|
rc = efx_init_port(efx);
|
|
if (rc) {
|
|
netif_err(efx, probe, efx->net_dev,
|
|
"failed to initialise port\n");
|
|
goto fail4;
|
|
}
|
|
|
|
rc = efx_nic_init_interrupt(efx);
|
|
if (rc)
|
|
goto fail5;
|
|
|
|
efx_set_interrupt_affinity(efx);
|
|
rc = efx_enable_interrupts(efx);
|
|
if (rc)
|
|
goto fail6;
|
|
|
|
return 0;
|
|
|
|
fail6:
|
|
efx_clear_interrupt_affinity(efx);
|
|
efx_nic_fini_interrupt(efx);
|
|
fail5:
|
|
efx_fini_port(efx);
|
|
fail4:
|
|
efx->type->fini(efx);
|
|
fail3:
|
|
efx_fini_napi(efx);
|
|
efx_remove_all(efx);
|
|
fail1:
|
|
return rc;
|
|
}
|
|
|
|
static int efx_pci_probe_post_io(struct efx_nic *efx)
|
|
{
|
|
struct net_device *net_dev = efx->net_dev;
|
|
int rc = efx_pci_probe_main(efx);
|
|
|
|
if (rc)
|
|
return rc;
|
|
|
|
if (efx->type->sriov_init) {
|
|
rc = efx->type->sriov_init(efx);
|
|
if (rc)
|
|
netif_err(efx, probe, efx->net_dev,
|
|
"SR-IOV can't be enabled rc %d\n", rc);
|
|
}
|
|
|
|
/* Determine netdevice features */
|
|
net_dev->features |= (efx->type->offload_features | NETIF_F_SG |
|
|
NETIF_F_TSO | NETIF_F_RXCSUM | NETIF_F_RXALL);
|
|
if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
|
|
net_dev->features |= NETIF_F_TSO6;
|
|
/* Check whether device supports TSO */
|
|
if (!efx->type->tso_versions || !efx->type->tso_versions(efx))
|
|
net_dev->features &= ~NETIF_F_ALL_TSO;
|
|
/* Mask for features that also apply to VLAN devices */
|
|
net_dev->vlan_features |= (NETIF_F_HW_CSUM | NETIF_F_SG |
|
|
NETIF_F_HIGHDMA | NETIF_F_ALL_TSO |
|
|
NETIF_F_RXCSUM);
|
|
|
|
net_dev->hw_features |= net_dev->features & ~efx->fixed_features;
|
|
|
|
/* Disable receiving frames with bad FCS, by default. */
|
|
net_dev->features &= ~NETIF_F_RXALL;
|
|
|
|
/* Disable VLAN filtering by default. It may be enforced if
|
|
* the feature is fixed (i.e. VLAN filters are required to
|
|
* receive VLAN tagged packets due to vPort restrictions).
|
|
*/
|
|
net_dev->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
|
|
net_dev->features |= efx->fixed_features;
|
|
|
|
rc = efx_register_netdev(efx);
|
|
if (!rc)
|
|
return 0;
|
|
|
|
efx_pci_remove_main(efx);
|
|
return rc;
|
|
}
|
|
|
|
/* NIC initialisation
|
|
*
|
|
* This is called at module load (or hotplug insertion,
|
|
* theoretically). It sets up PCI mappings, resets the NIC,
|
|
* sets up and registers the network devices with the kernel and hooks
|
|
* the interrupt service routine. It does not prepare the device for
|
|
* transmission; this is left to the first time one of the network
|
|
* interfaces is brought up (i.e. efx_net_open).
|
|
*/
|
|
static int efx_pci_probe(struct pci_dev *pci_dev,
|
|
const struct pci_device_id *entry)
|
|
{
|
|
struct net_device *net_dev;
|
|
struct efx_nic *efx;
|
|
int rc;
|
|
|
|
/* Allocate and initialise a struct net_device and struct efx_nic */
|
|
net_dev = alloc_etherdev_mqs(sizeof(*efx), EFX_MAX_CORE_TX_QUEUES,
|
|
EFX_MAX_RX_QUEUES);
|
|
if (!net_dev)
|
|
return -ENOMEM;
|
|
efx = netdev_priv(net_dev);
|
|
efx->type = (const struct efx_nic_type *) entry->driver_data;
|
|
efx->fixed_features |= NETIF_F_HIGHDMA;
|
|
|
|
pci_set_drvdata(pci_dev, efx);
|
|
SET_NETDEV_DEV(net_dev, &pci_dev->dev);
|
|
rc = efx_init_struct(efx, pci_dev, net_dev);
|
|
if (rc)
|
|
goto fail1;
|
|
|
|
netif_info(efx, probe, efx->net_dev,
|
|
"Solarflare NIC detected\n");
|
|
|
|
if (!efx->type->is_vf)
|
|
efx_probe_vpd_strings(efx);
|
|
|
|
/* Set up basic I/O (BAR mappings etc) */
|
|
rc = efx_init_io(efx);
|
|
if (rc)
|
|
goto fail2;
|
|
|
|
rc = efx_pci_probe_post_io(efx);
|
|
if (rc) {
|
|
/* On failure, retry once immediately.
|
|
* If we aborted probe due to a scheduled reset, dismiss it.
|
|
*/
|
|
efx->reset_pending = 0;
|
|
rc = efx_pci_probe_post_io(efx);
|
|
if (rc) {
|
|
/* On another failure, retry once more
|
|
* after a 50-305ms delay.
|
|
*/
|
|
unsigned char r;
|
|
|
|
get_random_bytes(&r, 1);
|
|
msleep((unsigned int)r + 50);
|
|
efx->reset_pending = 0;
|
|
rc = efx_pci_probe_post_io(efx);
|
|
}
|
|
}
|
|
if (rc)
|
|
goto fail3;
|
|
|
|
netif_dbg(efx, probe, efx->net_dev, "initialisation successful\n");
|
|
|
|
/* Try to create MTDs, but allow this to fail */
|
|
rtnl_lock();
|
|
rc = efx_mtd_probe(efx);
|
|
rtnl_unlock();
|
|
if (rc && rc != -EPERM)
|
|
netif_warn(efx, probe, efx->net_dev,
|
|
"failed to create MTDs (%d)\n", rc);
|
|
|
|
rc = pci_enable_pcie_error_reporting(pci_dev);
|
|
if (rc && rc != -EINVAL)
|
|
netif_notice(efx, probe, efx->net_dev,
|
|
"PCIE error reporting unavailable (%d).\n",
|
|
rc);
|
|
|
|
if (efx->type->udp_tnl_push_ports)
|
|
efx->type->udp_tnl_push_ports(efx);
|
|
|
|
return 0;
|
|
|
|
fail3:
|
|
efx_fini_io(efx);
|
|
fail2:
|
|
efx_fini_struct(efx);
|
|
fail1:
|
|
WARN_ON(rc > 0);
|
|
netif_dbg(efx, drv, efx->net_dev, "initialisation failed. rc=%d\n", rc);
|
|
free_netdev(net_dev);
|
|
return rc;
|
|
}
|
|
|
|
/* efx_pci_sriov_configure returns the actual number of Virtual Functions
|
|
* enabled on success
|
|
*/
|
|
#ifdef CONFIG_SFC_SRIOV
|
|
static int efx_pci_sriov_configure(struct pci_dev *dev, int num_vfs)
|
|
{
|
|
int rc;
|
|
struct efx_nic *efx = pci_get_drvdata(dev);
|
|
|
|
if (efx->type->sriov_configure) {
|
|
rc = efx->type->sriov_configure(efx, num_vfs);
|
|
if (rc)
|
|
return rc;
|
|
else
|
|
return num_vfs;
|
|
} else
|
|
return -EOPNOTSUPP;
|
|
}
|
|
#endif
|
|
|
|
static int efx_pm_freeze(struct device *dev)
|
|
{
|
|
struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
|
|
|
|
rtnl_lock();
|
|
|
|
if (efx->state != STATE_DISABLED) {
|
|
efx->state = STATE_UNINIT;
|
|
|
|
efx_device_detach_sync(efx);
|
|
|
|
efx_stop_all(efx);
|
|
efx_disable_interrupts(efx);
|
|
}
|
|
|
|
rtnl_unlock();
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int efx_pm_thaw(struct device *dev)
|
|
{
|
|
int rc;
|
|
struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
|
|
|
|
rtnl_lock();
|
|
|
|
if (efx->state != STATE_DISABLED) {
|
|
rc = efx_enable_interrupts(efx);
|
|
if (rc)
|
|
goto fail;
|
|
|
|
mutex_lock(&efx->mac_lock);
|
|
efx->phy_op->reconfigure(efx);
|
|
mutex_unlock(&efx->mac_lock);
|
|
|
|
efx_start_all(efx);
|
|
|
|
efx_device_attach_if_not_resetting(efx);
|
|
|
|
efx->state = STATE_READY;
|
|
|
|
efx->type->resume_wol(efx);
|
|
}
|
|
|
|
rtnl_unlock();
|
|
|
|
/* Reschedule any quenched resets scheduled during efx_pm_freeze() */
|
|
queue_work(reset_workqueue, &efx->reset_work);
|
|
|
|
return 0;
|
|
|
|
fail:
|
|
rtnl_unlock();
|
|
|
|
return rc;
|
|
}
|
|
|
|
static int efx_pm_poweroff(struct device *dev)
|
|
{
|
|
struct pci_dev *pci_dev = to_pci_dev(dev);
|
|
struct efx_nic *efx = pci_get_drvdata(pci_dev);
|
|
|
|
efx->type->fini(efx);
|
|
|
|
efx->reset_pending = 0;
|
|
|
|
pci_save_state(pci_dev);
|
|
return pci_set_power_state(pci_dev, PCI_D3hot);
|
|
}
|
|
|
|
/* Used for both resume and restore */
|
|
static int efx_pm_resume(struct device *dev)
|
|
{
|
|
struct pci_dev *pci_dev = to_pci_dev(dev);
|
|
struct efx_nic *efx = pci_get_drvdata(pci_dev);
|
|
int rc;
|
|
|
|
rc = pci_set_power_state(pci_dev, PCI_D0);
|
|
if (rc)
|
|
return rc;
|
|
pci_restore_state(pci_dev);
|
|
rc = pci_enable_device(pci_dev);
|
|
if (rc)
|
|
return rc;
|
|
pci_set_master(efx->pci_dev);
|
|
rc = efx->type->reset(efx, RESET_TYPE_ALL);
|
|
if (rc)
|
|
return rc;
|
|
down_write(&efx->filter_sem);
|
|
rc = efx->type->init(efx);
|
|
up_write(&efx->filter_sem);
|
|
if (rc)
|
|
return rc;
|
|
rc = efx_pm_thaw(dev);
|
|
return rc;
|
|
}
|
|
|
|
static int efx_pm_suspend(struct device *dev)
|
|
{
|
|
int rc;
|
|
|
|
efx_pm_freeze(dev);
|
|
rc = efx_pm_poweroff(dev);
|
|
if (rc)
|
|
efx_pm_resume(dev);
|
|
return rc;
|
|
}
|
|
|
|
static const struct dev_pm_ops efx_pm_ops = {
|
|
.suspend = efx_pm_suspend,
|
|
.resume = efx_pm_resume,
|
|
.freeze = efx_pm_freeze,
|
|
.thaw = efx_pm_thaw,
|
|
.poweroff = efx_pm_poweroff,
|
|
.restore = efx_pm_resume,
|
|
};
|
|
|
|
/* A PCI error affecting this device was detected.
|
|
* At this point MMIO and DMA may be disabled.
|
|
* Stop the software path and request a slot reset.
|
|
*/
|
|
static pci_ers_result_t efx_io_error_detected(struct pci_dev *pdev,
|
|
enum pci_channel_state state)
|
|
{
|
|
pci_ers_result_t status = PCI_ERS_RESULT_RECOVERED;
|
|
struct efx_nic *efx = pci_get_drvdata(pdev);
|
|
|
|
if (state == pci_channel_io_perm_failure)
|
|
return PCI_ERS_RESULT_DISCONNECT;
|
|
|
|
rtnl_lock();
|
|
|
|
if (efx->state != STATE_DISABLED) {
|
|
efx->state = STATE_RECOVERY;
|
|
efx->reset_pending = 0;
|
|
|
|
efx_device_detach_sync(efx);
|
|
|
|
efx_stop_all(efx);
|
|
efx_disable_interrupts(efx);
|
|
|
|
status = PCI_ERS_RESULT_NEED_RESET;
|
|
} else {
|
|
/* If the interface is disabled we don't want to do anything
|
|
* with it.
|
|
*/
|
|
status = PCI_ERS_RESULT_RECOVERED;
|
|
}
|
|
|
|
rtnl_unlock();
|
|
|
|
pci_disable_device(pdev);
|
|
|
|
return status;
|
|
}
|
|
|
|
/* Fake a successful reset, which will be performed later in efx_io_resume. */
|
|
static pci_ers_result_t efx_io_slot_reset(struct pci_dev *pdev)
|
|
{
|
|
struct efx_nic *efx = pci_get_drvdata(pdev);
|
|
pci_ers_result_t status = PCI_ERS_RESULT_RECOVERED;
|
|
|
|
if (pci_enable_device(pdev)) {
|
|
netif_err(efx, hw, efx->net_dev,
|
|
"Cannot re-enable PCI device after reset.\n");
|
|
status = PCI_ERS_RESULT_DISCONNECT;
|
|
}
|
|
|
|
return status;
|
|
}
|
|
|
|
/* Perform the actual reset and resume I/O operations. */
|
|
static void efx_io_resume(struct pci_dev *pdev)
|
|
{
|
|
struct efx_nic *efx = pci_get_drvdata(pdev);
|
|
int rc;
|
|
|
|
rtnl_lock();
|
|
|
|
if (efx->state == STATE_DISABLED)
|
|
goto out;
|
|
|
|
rc = efx_reset(efx, RESET_TYPE_ALL);
|
|
if (rc) {
|
|
netif_err(efx, hw, efx->net_dev,
|
|
"efx_reset failed after PCI error (%d)\n", rc);
|
|
} else {
|
|
efx->state = STATE_READY;
|
|
netif_dbg(efx, hw, efx->net_dev,
|
|
"Done resetting and resuming IO after PCI error.\n");
|
|
}
|
|
|
|
out:
|
|
rtnl_unlock();
|
|
}
|
|
|
|
/* For simplicity and reliability, we always require a slot reset and try to
|
|
* reset the hardware when a pci error affecting the device is detected.
|
|
* We leave both the link_reset and mmio_enabled callback unimplemented:
|
|
* with our request for slot reset the mmio_enabled callback will never be
|
|
* called, and the link_reset callback is not used by AER or EEH mechanisms.
|
|
*/
|
|
static const struct pci_error_handlers efx_err_handlers = {
|
|
.error_detected = efx_io_error_detected,
|
|
.slot_reset = efx_io_slot_reset,
|
|
.resume = efx_io_resume,
|
|
};
|
|
|
|
static struct pci_driver efx_pci_driver = {
|
|
.name = KBUILD_MODNAME,
|
|
.id_table = efx_pci_table,
|
|
.probe = efx_pci_probe,
|
|
.remove = efx_pci_remove,
|
|
.driver.pm = &efx_pm_ops,
|
|
.err_handler = &efx_err_handlers,
|
|
#ifdef CONFIG_SFC_SRIOV
|
|
.sriov_configure = efx_pci_sriov_configure,
|
|
#endif
|
|
};
|
|
|
|
/**************************************************************************
|
|
*
|
|
* Kernel module interface
|
|
*
|
|
*************************************************************************/
|
|
|
|
module_param(interrupt_mode, uint, 0444);
|
|
MODULE_PARM_DESC(interrupt_mode,
|
|
"Interrupt mode (0=>MSIX 1=>MSI 2=>legacy)");
|
|
|
|
static int __init efx_init_module(void)
|
|
{
|
|
int rc;
|
|
|
|
printk(KERN_INFO "Solarflare NET driver v" EFX_DRIVER_VERSION "\n");
|
|
|
|
rc = register_netdevice_notifier(&efx_netdev_notifier);
|
|
if (rc)
|
|
goto err_notifier;
|
|
|
|
#ifdef CONFIG_SFC_SRIOV
|
|
rc = efx_init_sriov();
|
|
if (rc)
|
|
goto err_sriov;
|
|
#endif
|
|
|
|
reset_workqueue = create_singlethread_workqueue("sfc_reset");
|
|
if (!reset_workqueue) {
|
|
rc = -ENOMEM;
|
|
goto err_reset;
|
|
}
|
|
|
|
rc = pci_register_driver(&efx_pci_driver);
|
|
if (rc < 0)
|
|
goto err_pci;
|
|
|
|
return 0;
|
|
|
|
err_pci:
|
|
destroy_workqueue(reset_workqueue);
|
|
err_reset:
|
|
#ifdef CONFIG_SFC_SRIOV
|
|
efx_fini_sriov();
|
|
err_sriov:
|
|
#endif
|
|
unregister_netdevice_notifier(&efx_netdev_notifier);
|
|
err_notifier:
|
|
return rc;
|
|
}
|
|
|
|
static void __exit efx_exit_module(void)
|
|
{
|
|
printk(KERN_INFO "Solarflare NET driver unloading\n");
|
|
|
|
pci_unregister_driver(&efx_pci_driver);
|
|
destroy_workqueue(reset_workqueue);
|
|
#ifdef CONFIG_SFC_SRIOV
|
|
efx_fini_sriov();
|
|
#endif
|
|
unregister_netdevice_notifier(&efx_netdev_notifier);
|
|
|
|
}
|
|
|
|
module_init(efx_init_module);
|
|
module_exit(efx_exit_module);
|
|
|
|
MODULE_AUTHOR("Solarflare Communications and "
|
|
"Michael Brown <mbrown@fensystems.co.uk>");
|
|
MODULE_DESCRIPTION("Solarflare network driver");
|
|
MODULE_LICENSE("GPL");
|
|
MODULE_DEVICE_TABLE(pci, efx_pci_table);
|
|
MODULE_VERSION(EFX_DRIVER_VERSION);
|