Google Git
Sign in
linux / linux / kernel / git / bpf / bpf / 242a6df688dcad7c55105280a79aaff83addf7ce / . / drivers / net / ethernet / ibm / ibmvnic.c
blob: 4bd33245bad625d7bffb7a7002dc776effd3e956 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0-or-later
/**************************************************************************/
/* */
/* IBM System i and System p Virtual NIC Device Driver */
/* Copyright (C) 2014 IBM Corp. */
/* Santiago Leon (santi_leon@yahoo.com) */
/* Thomas Falcon (tlfalcon@linux.vnet.ibm.com) */
/* John Allen (jallen@linux.vnet.ibm.com) */
/* */
/* */
/* This module contains the implementation of a virtual ethernet device */
/* for use with IBM i/p Series LPAR Linux. It utilizes the logical LAN */
/* option of the RS/6000 Platform Architecture to interface with virtual */
/* ethernet NICs that are presented to the partition by the hypervisor. */
/* */
/* Messages are passed between the VNIC driver and the VNIC server using */
/* Command/Response Queues (CRQs) and sub CRQs (sCRQs). CRQs are used to */
/* issue and receive commands that initiate communication with the server */
/* on driver initialization. Sub CRQs (sCRQs) are similar to CRQs, but */
/* are used by the driver to notify the server that a packet is */
/* ready for transmission or that a buffer has been added to receive a */
/* packet. Subsequently, sCRQs are used by the server to notify the */
/* driver that a packet transmission has been completed or that a packet */
/* has been received and placed in a waiting buffer. */
/* */
/* In lieu of a more conventional "on-the-fly" DMA mapping strategy in */
/* which skbs are DMA mapped and immediately unmapped when the transmit */
/* or receive has been completed, the VNIC driver is required to use */
/* "long term mapping". This entails that large, continuous DMA mapped */
/* buffers are allocated on driver initialization and these buffers are */
/* then continuously reused to pass skbs to and from the VNIC server. */
/* */
/**************************************************************************/
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/completion.h>
#include <linux/ioport.h>
#include <linux/dma-mapping.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/mm.h>
#include <linux/ethtool.h>
#include <linux/proc_fs.h>
#include <linux/if_arp.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/irq.h>
#include <linux/kthread.h>
#include <linux/seq_file.h>
#include <linux/interrupt.h>
#include <net/net_namespace.h>
#include <asm/hvcall.h>
#include <linux/atomic.h>
#include <asm/vio.h>
#include <asm/iommu.h>
#include <linux/uaccess.h>
#include <asm/firmware.h>
#include <linux/workqueue.h>
#include <linux/if_vlan.h>
#include <linux/utsname.h>
#include "ibmvnic.h"
static const char ibmvnic_driver_name[] = "ibmvnic";
static const char ibmvnic_driver_string[] = "IBM System i/p Virtual NIC Driver";
MODULE_AUTHOR("Santiago Leon");
MODULE_DESCRIPTION("IBM System i/p Virtual NIC Driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(IBMVNIC_DRIVER_VERSION);
static int ibmvnic_version = IBMVNIC_INITIAL_VERSION;
static int ibmvnic_remove(struct vio_dev *);
static void release_sub_crqs(struct ibmvnic_adapter *, bool);
static int ibmvnic_reset_crq(struct ibmvnic_adapter *);
static int ibmvnic_send_crq_init(struct ibmvnic_adapter *);
static int ibmvnic_reenable_crq_queue(struct ibmvnic_adapter *);
static int ibmvnic_send_crq(struct ibmvnic_adapter *, union ibmvnic_crq *);
static int send_subcrq(struct ibmvnic_adapter *adapter, u64 remote_handle,
union sub_crq *sub_crq);
static int send_subcrq_indirect(struct ibmvnic_adapter *, u64, u64, u64);
static irqreturn_t ibmvnic_interrupt_rx(int irq, void *instance);
static int enable_scrq_irq(struct ibmvnic_adapter *,
struct ibmvnic_sub_crq_queue *);
static int disable_scrq_irq(struct ibmvnic_adapter *,
struct ibmvnic_sub_crq_queue *);
static int pending_scrq(struct ibmvnic_adapter *,
struct ibmvnic_sub_crq_queue *);
static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *,
struct ibmvnic_sub_crq_queue *);
static int ibmvnic_poll(struct napi_struct *napi, int data);
static void send_map_query(struct ibmvnic_adapter *adapter);
static int send_request_map(struct ibmvnic_adapter *, dma_addr_t, __be32, u8);
static int send_request_unmap(struct ibmvnic_adapter *, u8);
static int send_login(struct ibmvnic_adapter *adapter);
static void send_cap_queries(struct ibmvnic_adapter *adapter);
static int init_sub_crqs(struct ibmvnic_adapter *);
static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter);
static int ibmvnic_init(struct ibmvnic_adapter *);
static int ibmvnic_reset_init(struct ibmvnic_adapter *);
static void release_crq_queue(struct ibmvnic_adapter *);
static int __ibmvnic_set_mac(struct net_device *, u8 *);
static int init_crq_queue(struct ibmvnic_adapter *adapter);
static int send_query_phys_parms(struct ibmvnic_adapter *adapter);
struct ibmvnic_stat {
char name[ETH_GSTRING_LEN];
int offset;
};
#define IBMVNIC_STAT_OFF(stat) (offsetof(struct ibmvnic_adapter, stats) + \
offsetof(struct ibmvnic_statistics, stat))
#define IBMVNIC_GET_STAT(a, off) (*((u64 *)(((unsigned long)(a)) + off)))
static const struct ibmvnic_stat ibmvnic_stats[] = {
{"rx_packets", IBMVNIC_STAT_OFF(rx_packets)},
{"rx_bytes", IBMVNIC_STAT_OFF(rx_bytes)},
{"tx_packets", IBMVNIC_STAT_OFF(tx_packets)},
{"tx_bytes", IBMVNIC_STAT_OFF(tx_bytes)},
{"ucast_tx_packets", IBMVNIC_STAT_OFF(ucast_tx_packets)},
{"ucast_rx_packets", IBMVNIC_STAT_OFF(ucast_rx_packets)},
{"mcast_tx_packets", IBMVNIC_STAT_OFF(mcast_tx_packets)},
{"mcast_rx_packets", IBMVNIC_STAT_OFF(mcast_rx_packets)},
{"bcast_tx_packets", IBMVNIC_STAT_OFF(bcast_tx_packets)},
{"bcast_rx_packets", IBMVNIC_STAT_OFF(bcast_rx_packets)},
{"align_errors", IBMVNIC_STAT_OFF(align_errors)},
{"fcs_errors", IBMVNIC_STAT_OFF(fcs_errors)},
{"single_collision_frames", IBMVNIC_STAT_OFF(single_collision_frames)},
{"multi_collision_frames", IBMVNIC_STAT_OFF(multi_collision_frames)},
{"sqe_test_errors", IBMVNIC_STAT_OFF(sqe_test_errors)},
{"deferred_tx", IBMVNIC_STAT_OFF(deferred_tx)},
{"late_collisions", IBMVNIC_STAT_OFF(late_collisions)},
{"excess_collisions", IBMVNIC_STAT_OFF(excess_collisions)},
{"internal_mac_tx_errors", IBMVNIC_STAT_OFF(internal_mac_tx_errors)},
{"carrier_sense", IBMVNIC_STAT_OFF(carrier_sense)},
{"too_long_frames", IBMVNIC_STAT_OFF(too_long_frames)},
{"internal_mac_rx_errors", IBMVNIC_STAT_OFF(internal_mac_rx_errors)},
};
static long h_reg_sub_crq(unsigned long unit_address, unsigned long token,
unsigned long length, unsigned long *number,
unsigned long *irq)
{
unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
long rc;
rc = plpar_hcall(H_REG_SUB_CRQ, retbuf, unit_address, token, length);
*number = retbuf[0];
*irq = retbuf[1];
return rc;
}
/**
* ibmvnic_wait_for_completion - Check device state and wait for completion
* @adapter: private device data
* @comp_done: completion structure to wait for
* @timeout: time to wait in milliseconds
*
* Wait for a completion signal or until the timeout limit is reached
* while checking that the device is still active.
*/
static int ibmvnic_wait_for_completion(struct ibmvnic_adapter *adapter,
struct completion *comp_done,
unsigned long timeout)
{
struct net_device *netdev;
unsigned long div_timeout;
u8 retry;
netdev = adapter->netdev;
retry = 5;
div_timeout = msecs_to_jiffies(timeout / retry);
while (true) {
if (!adapter->crq.active) {
netdev_err(netdev, "Device down!\n");
return -ENODEV;
}
if (!retry--)
break;
if (wait_for_completion_timeout(comp_done, div_timeout))
return 0;
}
netdev_err(netdev, "Operation timed out.\n");
return -ETIMEDOUT;
}
static int alloc_long_term_buff(struct ibmvnic_adapter *adapter,
struct ibmvnic_long_term_buff *ltb, int size)
{
struct device *dev = &adapter->vdev->dev;
int rc;
ltb->size = size;
ltb->buff = dma_alloc_coherent(dev, ltb->size, &ltb->addr,
GFP_KERNEL);
if (!ltb->buff) {
dev_err(dev, "Couldn't alloc long term buffer\n");
return -ENOMEM;
}
ltb->map_id = adapter->map_id;
adapter->map_id++;
mutex_lock(&adapter->fw_lock);
adapter->fw_done_rc = 0;
reinit_completion(&adapter->fw_done);
rc = send_request_map(adapter, ltb->addr,
ltb->size, ltb->map_id);
if (rc) {
dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr);
mutex_unlock(&adapter->fw_lock);
return rc;
}
rc = ibmvnic_wait_for_completion(adapter, &adapter->fw_done, 10000);
if (rc) {
dev_err(dev,
"Long term map request aborted or timed out,rc = %d\n",
rc);
dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr);
mutex_unlock(&adapter->fw_lock);
return rc;
}
if (adapter->fw_done_rc) {
dev_err(dev, "Couldn't map long term buffer,rc = %d\n",
adapter->fw_done_rc);
dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr);
mutex_unlock(&adapter->fw_lock);
return -1;
}
mutex_unlock(&adapter->fw_lock);
return 0;
}
static void free_long_term_buff(struct ibmvnic_adapter *adapter,
struct ibmvnic_long_term_buff *ltb)
{
struct device *dev = &adapter->vdev->dev;
if (!ltb->buff)
return;
if (adapter->reset_reason != VNIC_RESET_FAILOVER &&
adapter->reset_reason != VNIC_RESET_MOBILITY)
send_request_unmap(adapter, ltb->map_id);
dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr);
}
static int reset_long_term_buff(struct ibmvnic_adapter *adapter,
struct ibmvnic_long_term_buff *ltb)
{
struct device *dev = &adapter->vdev->dev;
int rc;
memset(ltb->buff, 0, ltb->size);
mutex_lock(&adapter->fw_lock);
adapter->fw_done_rc = 0;
reinit_completion(&adapter->fw_done);
rc = send_request_map(adapter, ltb->addr, ltb->size, ltb->map_id);
if (rc) {
mutex_unlock(&adapter->fw_lock);
return rc;
}
rc = ibmvnic_wait_for_completion(adapter, &adapter->fw_done, 10000);
if (rc) {
dev_info(dev,
"Reset failed, long term map request timed out or aborted\n");
mutex_unlock(&adapter->fw_lock);
return rc;
}
if (adapter->fw_done_rc) {
dev_info(dev,
"Reset failed, attempting to free and reallocate buffer\n");
free_long_term_buff(adapter, ltb);
mutex_unlock(&adapter->fw_lock);
return alloc_long_term_buff(adapter, ltb, ltb->size);
}
mutex_unlock(&adapter->fw_lock);
return 0;
}
static void deactivate_rx_pools(struct ibmvnic_adapter *adapter)
{
int i;
for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
i++)
adapter->rx_pool[i].active = 0;
}
static void replenish_rx_pool(struct ibmvnic_adapter *adapter,
struct ibmvnic_rx_pool *pool)
{
int count = pool->size - atomic_read(&pool->available);
struct device *dev = &adapter->vdev->dev;
int buffers_added = 0;
unsigned long lpar_rc;
union sub_crq sub_crq;
struct sk_buff *skb;
unsigned int offset;
dma_addr_t dma_addr;
unsigned char *dst;
u64 *handle_array;
int shift = 0;
int index;
int i;
if (!pool->active)
return;
handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
be32_to_cpu(adapter->login_rsp_buf->
off_rxadd_subcrqs));
for (i = 0; i < count; ++i) {
skb = alloc_skb(pool->buff_size, GFP_ATOMIC);
if (!skb) {
dev_err(dev, "Couldn't replenish rx buff\n");
adapter->replenish_no_mem++;
break;
}
index = pool->free_map[pool->next_free];
if (pool->rx_buff[index].skb)
dev_err(dev, "Inconsistent free_map!\n");
/* Copy the skb to the long term mapped DMA buffer */
offset = index * pool->buff_size;
dst = pool->long_term_buff.buff + offset;
memset(dst, 0, pool->buff_size);
dma_addr = pool->long_term_buff.addr + offset;
pool->rx_buff[index].data = dst;
pool->free_map[pool->next_free] = IBMVNIC_INVALID_MAP;
pool->rx_buff[index].dma = dma_addr;
pool->rx_buff[index].skb = skb;
pool->rx_buff[index].pool_index = pool->index;
pool->rx_buff[index].size = pool->buff_size;
memset(&sub_crq, 0, sizeof(sub_crq));
sub_crq.rx_add.first = IBMVNIC_CRQ_CMD;
sub_crq.rx_add.correlator =
cpu_to_be64((u64)&pool->rx_buff[index]);
sub_crq.rx_add.ioba = cpu_to_be32(dma_addr);
sub_crq.rx_add.map_id = pool->long_term_buff.map_id;
/* The length field of the sCRQ is defined to be 24 bits so the
* buffer size needs to be left shifted by a byte before it is
* converted to big endian to prevent the last byte from being
* truncated.
*/
#ifdef __LITTLE_ENDIAN__
shift = 8;
#endif
sub_crq.rx_add.len = cpu_to_be32(pool->buff_size << shift);
lpar_rc = send_subcrq(adapter, handle_array[pool->index],
&sub_crq);
if (lpar_rc != H_SUCCESS)
goto failure;
buffers_added++;
adapter->replenish_add_buff_success++;
pool->next_free = (pool->next_free + 1) % pool->size;
}
atomic_add(buffers_added, &pool->available);
return;
failure:
if (lpar_rc != H_PARAMETER && lpar_rc != H_CLOSED)
dev_err_ratelimited(dev, "rx: replenish packet buffer failed\n");
pool->free_map[pool->next_free] = index;
pool->rx_buff[index].skb = NULL;
dev_kfree_skb_any(skb);
adapter->replenish_add_buff_failure++;
atomic_add(buffers_added, &pool->available);
if (lpar_rc == H_CLOSED || adapter->failover_pending) {
/* Disable buffer pool replenishment and report carrier off if
* queue is closed or pending failover.
* Firmware guarantees that a signal will be sent to the
* driver, triggering a reset.
*/
deactivate_rx_pools(adapter);
netif_carrier_off(adapter->netdev);
}
}
static void replenish_pools(struct ibmvnic_adapter *adapter)
{
int i;
adapter->replenish_task_cycles++;
for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
i++) {
if (adapter->rx_pool[i].active)
replenish_rx_pool(adapter, &adapter->rx_pool[i]);
}
}
static void release_stats_buffers(struct ibmvnic_adapter *adapter)
{
kfree(adapter->tx_stats_buffers);
kfree(adapter->rx_stats_buffers);
adapter->tx_stats_buffers = NULL;
adapter->rx_stats_buffers = NULL;
}
static int init_stats_buffers(struct ibmvnic_adapter *adapter)
{
adapter->tx_stats_buffers =
kcalloc(IBMVNIC_MAX_QUEUES,
sizeof(struct ibmvnic_tx_queue_stats),
GFP_KERNEL);
if (!adapter->tx_stats_buffers)
return -ENOMEM;
adapter->rx_stats_buffers =
kcalloc(IBMVNIC_MAX_QUEUES,
sizeof(struct ibmvnic_rx_queue_stats),
GFP_KERNEL);
if (!adapter->rx_stats_buffers)
return -ENOMEM;
return 0;
}
static void release_stats_token(struct ibmvnic_adapter *adapter)
{
struct device *dev = &adapter->vdev->dev;
if (!adapter->stats_token)
return;
dma_unmap_single(dev, adapter->stats_token,
sizeof(struct ibmvnic_statistics),
DMA_FROM_DEVICE);
adapter->stats_token = 0;
}
static int init_stats_token(struct ibmvnic_adapter *adapter)
{
struct device *dev = &adapter->vdev->dev;
dma_addr_t stok;
stok = dma_map_single(dev, &adapter->stats,
sizeof(struct ibmvnic_statistics),
DMA_FROM_DEVICE);
if (dma_mapping_error(dev, stok)) {
dev_err(dev, "Couldn't map stats buffer\n");
return -1;
}
adapter->stats_token = stok;
netdev_dbg(adapter->netdev, "Stats token initialized (%llx)\n", stok);
return 0;
}
static int reset_rx_pools(struct ibmvnic_adapter *adapter)
{
struct ibmvnic_rx_pool *rx_pool;
int rx_scrqs;
int i, j, rc;
u64 *size_array;
size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size));
rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
for (i = 0; i < rx_scrqs; i++) {
rx_pool = &adapter->rx_pool[i];
netdev_dbg(adapter->netdev, "Re-setting rx_pool[%d]\n", i);
if (rx_pool->buff_size != be64_to_cpu(size_array[i])) {
free_long_term_buff(adapter, &rx_pool->long_term_buff);
rx_pool->buff_size = be64_to_cpu(size_array[i]);
rc = alloc_long_term_buff(adapter,
&rx_pool->long_term_buff,
rx_pool->size *
rx_pool->buff_size);
} else {
rc = reset_long_term_buff(adapter,
&rx_pool->long_term_buff);
}
if (rc)
return rc;
for (j = 0; j < rx_pool->size; j++)
rx_pool->free_map[j] = j;
memset(rx_pool->rx_buff, 0,
rx_pool->size * sizeof(struct ibmvnic_rx_buff));
atomic_set(&rx_pool->available, 0);
rx_pool->next_alloc = 0;
rx_pool->next_free = 0;
rx_pool->active = 1;
}
return 0;
}
static void release_rx_pools(struct ibmvnic_adapter *adapter)
{
struct ibmvnic_rx_pool *rx_pool;
int i, j;
if (!adapter->rx_pool)
return;
for (i = 0; i < adapter->num_active_rx_pools; i++) {
rx_pool = &adapter->rx_pool[i];
netdev_dbg(adapter->netdev, "Releasing rx_pool[%d]\n", i);
kfree(rx_pool->free_map);
free_long_term_buff(adapter, &rx_pool->long_term_buff);
if (!rx_pool->rx_buff)
continue;
for (j = 0; j < rx_pool->size; j++) {
if (rx_pool->rx_buff[j].skb) {
dev_kfree_skb_any(rx_pool->rx_buff[j].skb);
rx_pool->rx_buff[j].skb = NULL;
}
}
kfree(rx_pool->rx_buff);
}
kfree(adapter->rx_pool);
adapter->rx_pool = NULL;
adapter->num_active_rx_pools = 0;
}
static int init_rx_pools(struct net_device *netdev)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
struct device *dev = &adapter->vdev->dev;
struct ibmvnic_rx_pool *rx_pool;
int rxadd_subcrqs;
u64 *size_array;
int i, j;
rxadd_subcrqs =
be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size));
adapter->rx_pool = kcalloc(rxadd_subcrqs,
sizeof(struct ibmvnic_rx_pool),
GFP_KERNEL);
if (!adapter->rx_pool) {
dev_err(dev, "Failed to allocate rx pools\n");
return -1;
}
adapter->num_active_rx_pools = rxadd_subcrqs;
for (i = 0; i < rxadd_subcrqs; i++) {
rx_pool = &adapter->rx_pool[i];
netdev_dbg(adapter->netdev,
"Initializing rx_pool[%d], %lld buffs, %lld bytes each\n",
i, adapter->req_rx_add_entries_per_subcrq,
be64_to_cpu(size_array[i]));
rx_pool->size = adapter->req_rx_add_entries_per_subcrq;
rx_pool->index = i;
rx_pool->buff_size = be64_to_cpu(size_array[i]);
rx_pool->active = 1;
rx_pool->free_map = kcalloc(rx_pool->size, sizeof(int),
GFP_KERNEL);
if (!rx_pool->free_map) {
release_rx_pools(adapter);
return -1;
}
rx_pool->rx_buff = kcalloc(rx_pool->size,
sizeof(struct ibmvnic_rx_buff),
GFP_KERNEL);
if (!rx_pool->rx_buff) {
dev_err(dev, "Couldn't alloc rx buffers\n");
release_rx_pools(adapter);
return -1;
}
if (alloc_long_term_buff(adapter, &rx_pool->long_term_buff,
rx_pool->size * rx_pool->buff_size)) {
release_rx_pools(adapter);
return -1;
}
for (j = 0; j < rx_pool->size; ++j)
rx_pool->free_map[j] = j;
atomic_set(&rx_pool->available, 0);
rx_pool->next_alloc = 0;
rx_pool->next_free = 0;
}
return 0;
}
static int reset_one_tx_pool(struct ibmvnic_adapter *adapter,
struct ibmvnic_tx_pool *tx_pool)
{
int rc, i;
rc = reset_long_term_buff(adapter, &tx_pool->long_term_buff);
if (rc)
return rc;
memset(tx_pool->tx_buff, 0,
tx_pool->num_buffers *
sizeof(struct ibmvnic_tx_buff));
for (i = 0; i < tx_pool->num_buffers; i++)
tx_pool->free_map[i] = i;
tx_pool->consumer_index = 0;
tx_pool->producer_index = 0;
return 0;
}
static int reset_tx_pools(struct ibmvnic_adapter *adapter)
{
int tx_scrqs;
int i, rc;
tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
for (i = 0; i < tx_scrqs; i++) {
rc = reset_one_tx_pool(adapter, &adapter->tso_pool[i]);
if (rc)
return rc;
rc = reset_one_tx_pool(adapter, &adapter->tx_pool[i]);
if (rc)
return rc;
}
return 0;
}
static void release_vpd_data(struct ibmvnic_adapter *adapter)
{
if (!adapter->vpd)
return;
kfree(adapter->vpd->buff);
kfree(adapter->vpd);
adapter->vpd = NULL;
}
static void release_one_tx_pool(struct ibmvnic_adapter *adapter,
struct ibmvnic_tx_pool *tx_pool)
{
kfree(tx_pool->tx_buff);
kfree(tx_pool->free_map);
free_long_term_buff(adapter, &tx_pool->long_term_buff);
}
static void release_tx_pools(struct ibmvnic_adapter *adapter)
{
int i;
if (!adapter->tx_pool)
return;
for (i = 0; i < adapter->num_active_tx_pools; i++) {
release_one_tx_pool(adapter, &adapter->tx_pool[i]);
release_one_tx_pool(adapter, &adapter->tso_pool[i]);
}
kfree(adapter->tx_pool);
adapter->tx_pool = NULL;
kfree(adapter->tso_pool);
adapter->tso_pool = NULL;
adapter->num_active_tx_pools = 0;
}
static int init_one_tx_pool(struct net_device *netdev,
struct ibmvnic_tx_pool *tx_pool,
int num_entries, int buf_size)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
int i;
tx_pool->tx_buff = kcalloc(num_entries,
sizeof(struct ibmvnic_tx_buff),
GFP_KERNEL);
if (!tx_pool->tx_buff)
return -1;
if (alloc_long_term_buff(adapter, &tx_pool->long_term_buff,
num_entries * buf_size))
return -1;
tx_pool->free_map = kcalloc(num_entries, sizeof(int), GFP_KERNEL);
if (!tx_pool->free_map)
return -1;
for (i = 0; i < num_entries; i++)
tx_pool->free_map[i] = i;
tx_pool->consumer_index = 0;
tx_pool->producer_index = 0;
tx_pool->num_buffers = num_entries;
tx_pool->buf_size = buf_size;
return 0;
}
static int init_tx_pools(struct net_device *netdev)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
int tx_subcrqs;
int i, rc;
tx_subcrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
adapter->tx_pool = kcalloc(tx_subcrqs,
sizeof(struct ibmvnic_tx_pool), GFP_KERNEL);
if (!adapter->tx_pool)
return -1;
adapter->tso_pool = kcalloc(tx_subcrqs,
sizeof(struct ibmvnic_tx_pool), GFP_KERNEL);
if (!adapter->tso_pool)
return -1;
adapter->num_active_tx_pools = tx_subcrqs;
for (i = 0; i < tx_subcrqs; i++) {
rc = init_one_tx_pool(netdev, &adapter->tx_pool[i],
adapter->req_tx_entries_per_subcrq,
adapter->req_mtu + VLAN_HLEN);
if (rc) {
release_tx_pools(adapter);
return rc;
}
rc = init_one_tx_pool(netdev, &adapter->tso_pool[i],
IBMVNIC_TSO_BUFS,
IBMVNIC_TSO_BUF_SZ);
if (rc) {
release_tx_pools(adapter);
return rc;
}
}
return 0;
}
static void ibmvnic_napi_enable(struct ibmvnic_adapter *adapter)
{
int i;
if (adapter->napi_enabled)
return;
for (i = 0; i < adapter->req_rx_queues; i++)
napi_enable(&adapter->napi[i]);
adapter->napi_enabled = true;
}
static void ibmvnic_napi_disable(struct ibmvnic_adapter *adapter)
{
int i;
if (!adapter->napi_enabled)
return;
for (i = 0; i < adapter->req_rx_queues; i++) {
netdev_dbg(adapter->netdev, "Disabling napi[%d]\n", i);
napi_disable(&adapter->napi[i]);
}
adapter->napi_enabled = false;
}
static int init_napi(struct ibmvnic_adapter *adapter)
{
int i;
adapter->napi = kcalloc(adapter->req_rx_queues,
sizeof(struct napi_struct), GFP_KERNEL);
if (!adapter->napi)
return -ENOMEM;
for (i = 0; i < adapter->req_rx_queues; i++) {
netdev_dbg(adapter->netdev, "Adding napi[%d]\n", i);
netif_napi_add(adapter->netdev, &adapter->napi[i],
ibmvnic_poll, NAPI_POLL_WEIGHT);
}
adapter->num_active_rx_napi = adapter->req_rx_queues;
return 0;
}
static void release_napi(struct ibmvnic_adapter *adapter)
{
int i;
if (!adapter->napi)
return;
for (i = 0; i < adapter->num_active_rx_napi; i++) {
netdev_dbg(adapter->netdev, "Releasing napi[%d]\n", i);
netif_napi_del(&adapter->napi[i]);
}
kfree(adapter->napi);
adapter->napi = NULL;
adapter->num_active_rx_napi = 0;
adapter->napi_enabled = false;
}
static int ibmvnic_login(struct net_device *netdev)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
unsigned long timeout = msecs_to_jiffies(30000);
int retry_count = 0;
bool retry;
int rc;
do {
retry = false;
if (retry_count > IBMVNIC_MAX_QUEUES) {
netdev_warn(netdev, "Login attempts exceeded\n");
return -1;
}
adapter->init_done_rc = 0;
reinit_completion(&adapter->init_done);
rc = send_login(adapter);
if (rc) {
netdev_warn(netdev, "Unable to login\n");
return rc;
}
if (!wait_for_completion_timeout(&adapter->init_done,
timeout)) {
netdev_warn(netdev, "Login timed out\n");
return -1;
}
if (adapter->init_done_rc == PARTIALSUCCESS) {
retry_count++;
release_sub_crqs(adapter, 1);
retry = true;
netdev_dbg(netdev,
"Received partial success, retrying...\n");
adapter->init_done_rc = 0;
reinit_completion(&adapter->init_done);
send_cap_queries(adapter);
if (!wait_for_completion_timeout(&adapter->init_done,
timeout)) {
netdev_warn(netdev,
"Capabilities query timed out\n");
return -1;
}
rc = init_sub_crqs(adapter);
if (rc) {
netdev_warn(netdev,
"SCRQ initialization failed\n");
return -1;
}
rc = init_sub_crq_irqs(adapter);
if (rc) {
netdev_warn(netdev,
"SCRQ irq initialization failed\n");
return -1;
}
} else if (adapter->init_done_rc) {
netdev_warn(netdev, "Adapter login failed\n");
return -1;
}
} while (retry);
__ibmvnic_set_mac(netdev, adapter->mac_addr);
return 0;
}
static void release_login_buffer(struct ibmvnic_adapter *adapter)
{
kfree(adapter->login_buf);
adapter->login_buf = NULL;
}
static void release_login_rsp_buffer(struct ibmvnic_adapter *adapter)
{
kfree(adapter->login_rsp_buf);
adapter->login_rsp_buf = NULL;
}
static void release_resources(struct ibmvnic_adapter *adapter)
{
release_vpd_data(adapter);
release_tx_pools(adapter);
release_rx_pools(adapter);
release_napi(adapter);
release_login_rsp_buffer(adapter);
}
static int set_link_state(struct ibmvnic_adapter *adapter, u8 link_state)
{
struct net_device *netdev = adapter->netdev;
unsigned long timeout = msecs_to_jiffies(30000);
union ibmvnic_crq crq;
bool resend;
int rc;
netdev_dbg(netdev, "setting link state %d\n", link_state);
memset(&crq, 0, sizeof(crq));
crq.logical_link_state.first = IBMVNIC_CRQ_CMD;
crq.logical_link_state.cmd = LOGICAL_LINK_STATE;
crq.logical_link_state.link_state = link_state;
do {
resend = false;
reinit_completion(&adapter->init_done);
rc = ibmvnic_send_crq(adapter, &crq);
if (rc) {
netdev_err(netdev, "Failed to set link state\n");
return rc;
}
if (!wait_for_completion_timeout(&adapter->init_done,
timeout)) {
netdev_err(netdev, "timeout setting link state\n");
return -1;
}
if (adapter->init_done_rc == 1) {
/* Partuial success, delay and re-send */
mdelay(1000);
resend = true;
} else if (adapter->init_done_rc) {
netdev_warn(netdev, "Unable to set link state, rc=%d\n",
adapter->init_done_rc);
return adapter->init_done_rc;
}
} while (resend);
return 0;
}
static int set_real_num_queues(struct net_device *netdev)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
int rc;
netdev_dbg(netdev, "Setting real tx/rx queues (%llx/%llx)\n",
adapter->req_tx_queues, adapter->req_rx_queues);
rc = netif_set_real_num_tx_queues(netdev, adapter->req_tx_queues);
if (rc) {
netdev_err(netdev, "failed to set the number of tx queues\n");
return rc;
}
rc = netif_set_real_num_rx_queues(netdev, adapter->req_rx_queues);
if (rc)
netdev_err(netdev, "failed to set the number of rx queues\n");
return rc;
}
static int ibmvnic_get_vpd(struct ibmvnic_adapter *adapter)
{
struct device *dev = &adapter->vdev->dev;
union ibmvnic_crq crq;
int len = 0;
int rc;
if (adapter->vpd->buff)
len = adapter->vpd->len;
mutex_lock(&adapter->fw_lock);
adapter->fw_done_rc = 0;
reinit_completion(&adapter->fw_done);
crq.get_vpd_size.first = IBMVNIC_CRQ_CMD;
crq.get_vpd_size.cmd = GET_VPD_SIZE;
rc = ibmvnic_send_crq(adapter, &crq);
if (rc) {
mutex_unlock(&adapter->fw_lock);
return rc;
}
rc = ibmvnic_wait_for_completion(adapter, &adapter->fw_done, 10000);
if (rc) {
dev_err(dev, "Could not retrieve VPD size, rc = %d\n", rc);
mutex_unlock(&adapter->fw_lock);
return rc;
}
mutex_unlock(&adapter->fw_lock);
if (!adapter->vpd->len)
return -ENODATA;
if (!adapter->vpd->buff)
adapter->vpd->buff = kzalloc(adapter->vpd->len, GFP_KERNEL);
else if (adapter->vpd->len != len)
adapter->vpd->buff =
krealloc(adapter->vpd->buff,
adapter->vpd->len, GFP_KERNEL);
if (!adapter->vpd->buff) {
dev_err(dev, "Could allocate VPD buffer\n");
return -ENOMEM;
}
adapter->vpd->dma_addr =
dma_map_single(dev, adapter->vpd->buff, adapter->vpd->len,
DMA_FROM_DEVICE);
if (dma_mapping_error(dev, adapter->vpd->dma_addr)) {
dev_err(dev, "Could not map VPD buffer\n");
kfree(adapter->vpd->buff);
adapter->vpd->buff = NULL;
return -ENOMEM;
}
mutex_lock(&adapter->fw_lock);
adapter->fw_done_rc = 0;
reinit_completion(&adapter->fw_done);
crq.get_vpd.first = IBMVNIC_CRQ_CMD;
crq.get_vpd.cmd = GET_VPD;
crq.get_vpd.ioba = cpu_to_be32(adapter->vpd->dma_addr);
crq.get_vpd.len = cpu_to_be32((u32)adapter->vpd->len);
rc = ibmvnic_send_crq(adapter, &crq);
if (rc) {
kfree(adapter->vpd->buff);
adapter->vpd->buff = NULL;
mutex_unlock(&adapter->fw_lock);
return rc;
}
rc = ibmvnic_wait_for_completion(adapter, &adapter->fw_done, 10000);
if (rc) {
dev_err(dev, "Unable to retrieve VPD, rc = %d\n", rc);
kfree(adapter->vpd->buff);
adapter->vpd->buff = NULL;
mutex_unlock(&adapter->fw_lock);
return rc;
}
mutex_unlock(&adapter->fw_lock);
return 0;
}
static int init_resources(struct ibmvnic_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
int rc;
rc = set_real_num_queues(netdev);
if (rc)
return rc;
adapter->vpd = kzalloc(sizeof(*adapter->vpd), GFP_KERNEL);
if (!adapter->vpd)
return -ENOMEM;
/* Vital Product Data (VPD) */
rc = ibmvnic_get_vpd(adapter);
if (rc) {
netdev_err(netdev, "failed to initialize Vital Product Data (VPD)\n");
return rc;
}
adapter->map_id = 1;
rc = init_napi(adapter);
if (rc)
return rc;
send_map_query(adapter);
rc = init_rx_pools(netdev);
if (rc)
return rc;
rc = init_tx_pools(netdev);
return rc;
}
static int __ibmvnic_open(struct net_device *netdev)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
enum vnic_state prev_state = adapter->state;
int i, rc;
adapter->state = VNIC_OPENING;
replenish_pools(adapter);
ibmvnic_napi_enable(adapter);
/* We're ready to receive frames, enable the sub-crq interrupts and
* set the logical link state to up
*/
for (i = 0; i < adapter->req_rx_queues; i++) {
netdev_dbg(netdev, "Enabling rx_scrq[%d] irq\n", i);
if (prev_state == VNIC_CLOSED)
enable_irq(adapter->rx_scrq[i]->irq);
enable_scrq_irq(adapter, adapter->rx_scrq[i]);
}
for (i = 0; i < adapter->req_tx_queues; i++) {
netdev_dbg(netdev, "Enabling tx_scrq[%d] irq\n", i);
if (prev_state == VNIC_CLOSED)
enable_irq(adapter->tx_scrq[i]->irq);
enable_scrq_irq(adapter, adapter->tx_scrq[i]);
}
rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_UP);
if (rc) {
for (i = 0; i < adapter->req_rx_queues; i++)
napi_disable(&adapter->napi[i]);
release_resources(adapter);
return rc;
}
netif_tx_start_all_queues(netdev);
if (prev_state == VNIC_CLOSED) {
for (i = 0; i < adapter->req_rx_queues; i++)
napi_schedule(&adapter->napi[i]);
}
adapter->state = VNIC_OPEN;
return rc;
}
static int ibmvnic_open(struct net_device *netdev)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
int rc;
/* If device failover is pending, just set device state and return.
* Device operation will be handled by reset routine.
*/
if (adapter->failover_pending) {
adapter->state = VNIC_OPEN;
return 0;
}
if (adapter->state != VNIC_CLOSED) {
rc = ibmvnic_login(netdev);
if (rc)
return rc;
rc = init_resources(adapter);
if (rc) {
netdev_err(netdev, "failed to initialize resources\n");
release_resources(adapter);
return rc;
}
}
rc = __ibmvnic_open(netdev);
return rc;
}
static void clean_rx_pools(struct ibmvnic_adapter *adapter)
{
struct ibmvnic_rx_pool *rx_pool;
struct ibmvnic_rx_buff *rx_buff;
u64 rx_entries;
int rx_scrqs;
int i, j;
if (!adapter->rx_pool)
return;
rx_scrqs = adapter->num_active_rx_pools;
rx_entries = adapter->req_rx_add_entries_per_subcrq;
/* Free any remaining skbs in the rx buffer pools */
for (i = 0; i < rx_scrqs; i++) {
rx_pool = &adapter->rx_pool[i];
if (!rx_pool || !rx_pool->rx_buff)
continue;
netdev_dbg(adapter->netdev, "Cleaning rx_pool[%d]\n", i);
for (j = 0; j < rx_entries; j++) {
rx_buff = &rx_pool->rx_buff[j];
if (rx_buff && rx_buff->skb) {
dev_kfree_skb_any(rx_buff->skb);
rx_buff->skb = NULL;
}
}
}
}
static void clean_one_tx_pool(struct ibmvnic_adapter *adapter,
struct ibmvnic_tx_pool *tx_pool)
{
struct ibmvnic_tx_buff *tx_buff;
u64 tx_entries;
int i;
if (!tx_pool || !tx_pool->tx_buff)
return;
tx_entries = tx_pool->num_buffers;
for (i = 0; i < tx_entries; i++) {
tx_buff = &tx_pool->tx_buff[i];
if (tx_buff && tx_buff->skb) {
dev_kfree_skb_any(tx_buff->skb);
tx_buff->skb = NULL;
}
}
}
static void clean_tx_pools(struct ibmvnic_adapter *adapter)
{
int tx_scrqs;
int i;
if (!adapter->tx_pool || !adapter->tso_pool)
return;
tx_scrqs = adapter->num_active_tx_pools;
/* Free any remaining skbs in the tx buffer pools */
for (i = 0; i < tx_scrqs; i++) {
netdev_dbg(adapter->netdev, "Cleaning tx_pool[%d]\n", i);
clean_one_tx_pool(adapter, &adapter->tx_pool[i]);
clean_one_tx_pool(adapter, &adapter->tso_pool[i]);
}
}
static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
int i;
if (adapter->tx_scrq) {
for (i = 0; i < adapter->req_tx_queues; i++)
if (adapter->tx_scrq[i]->irq) {
netdev_dbg(netdev,
"Disabling tx_scrq[%d] irq\n", i);
disable_scrq_irq(adapter, adapter->tx_scrq[i]);
disable_irq(adapter->tx_scrq[i]->irq);
}
}
if (adapter->rx_scrq) {
for (i = 0; i < adapter->req_rx_queues; i++) {
if (adapter->rx_scrq[i]->irq) {
netdev_dbg(netdev,
"Disabling rx_scrq[%d] irq\n", i);
disable_scrq_irq(adapter, adapter->rx_scrq[i]);
disable_irq(adapter->rx_scrq[i]->irq);
}
}
}
}
static void ibmvnic_cleanup(struct net_device *netdev)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
/* ensure that transmissions are stopped if called by do_reset */
if (test_bit(0, &adapter->resetting))
netif_tx_disable(netdev);
else
netif_tx_stop_all_queues(netdev);
ibmvnic_napi_disable(adapter);
ibmvnic_disable_irqs(adapter);
clean_rx_pools(adapter);
clean_tx_pools(adapter);
}
static int __ibmvnic_close(struct net_device *netdev)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
int rc = 0;
adapter->state = VNIC_CLOSING;
rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_DN);
if (rc)
return rc;
adapter->state = VNIC_CLOSED;
return 0;
}
static int ibmvnic_close(struct net_device *netdev)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
int rc;
/* If device failover is pending, just set device state and return.
* Device operation will be handled by reset routine.
*/
if (adapter->failover_pending) {
adapter->state = VNIC_CLOSED;
return 0;
}
rc = __ibmvnic_close(netdev);
ibmvnic_cleanup(netdev);
return rc;
}
/**
* build_hdr_data - creates L2/L3/L4 header data buffer
* @hdr_field - bitfield determining needed headers
* @skb - socket buffer
* @hdr_len - array of header lengths
* @tot_len - total length of data
*
* Reads hdr_field to determine which headers are needed by firmware.
* Builds a buffer containing these headers. Saves individual header
* lengths and total buffer length to be used to build descriptors.
*/
static int build_hdr_data(u8 hdr_field, struct sk_buff *skb,
int *hdr_len, u8 *hdr_data)
{
int len = 0;
u8 *hdr;
if (skb_vlan_tagged(skb) && !skb_vlan_tag_present(skb))
hdr_len[0] = sizeof(struct vlan_ethhdr);
else
hdr_len[0] = sizeof(struct ethhdr);
if (skb->protocol == htons(ETH_P_IP)) {
hdr_len[1] = ip_hdr(skb)->ihl * 4;
if (ip_hdr(skb)->protocol == IPPROTO_TCP)
hdr_len[2] = tcp_hdrlen(skb);
else if (ip_hdr(skb)->protocol == IPPROTO_UDP)
hdr_len[2] = sizeof(struct udphdr);
} else if (skb->protocol == htons(ETH_P_IPV6)) {
hdr_len[1] = sizeof(struct ipv6hdr);
if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
hdr_len[2] = tcp_hdrlen(skb);
else if (ipv6_hdr(skb)->nexthdr == IPPROTO_UDP)
hdr_len[2] = sizeof(struct udphdr);
} else if (skb->protocol == htons(ETH_P_ARP)) {
hdr_len[1] = arp_hdr_len(skb->dev);
hdr_len[2] = 0;
}
memset(hdr_data, 0, 120);
if ((hdr_field >> 6) & 1) {
hdr = skb_mac_header(skb);
memcpy(hdr_data, hdr, hdr_len[0]);
len += hdr_len[0];
}
if ((hdr_field >> 5) & 1) {
hdr = skb_network_header(skb);
memcpy(hdr_data + len, hdr, hdr_len[1]);
len += hdr_len[1];
}
if ((hdr_field >> 4) & 1) {
hdr = skb_transport_header(skb);
memcpy(hdr_data + len, hdr, hdr_len[2]);
len += hdr_len[2];
}
return len;
}
/**
* create_hdr_descs - create header and header extension descriptors
* @hdr_field - bitfield determining needed headers
* @data - buffer containing header data
* @len - length of data buffer
* @hdr_len - array of individual header lengths
* @scrq_arr - descriptor array
*
* Creates header and, if needed, header extension descriptors and
* places them in a descriptor array, scrq_arr
*/
static int create_hdr_descs(u8 hdr_field, u8 *hdr_data, int len, int *hdr_len,
union sub_crq *scrq_arr)
{
union sub_crq hdr_desc;
int tmp_len = len;
int num_descs = 0;
u8 *data, *cur;
int tmp;
while (tmp_len > 0) {
cur = hdr_data + len - tmp_len;
memset(&hdr_desc, 0, sizeof(hdr_desc));
if (cur != hdr_data) {
data = hdr_desc.hdr_ext.data;
tmp = tmp_len > 29 ? 29 : tmp_len;
hdr_desc.hdr_ext.first = IBMVNIC_CRQ_CMD;
hdr_desc.hdr_ext.type = IBMVNIC_HDR_EXT_DESC;
hdr_desc.hdr_ext.len = tmp;
} else {
data = hdr_desc.hdr.data;
tmp = tmp_len > 24 ? 24 : tmp_len;
hdr_desc.hdr.first = IBMVNIC_CRQ_CMD;
hdr_desc.hdr.type = IBMVNIC_HDR_DESC;
hdr_desc.hdr.len = tmp;
hdr_desc.hdr.l2_len = (u8)hdr_len[0];
hdr_desc.hdr.l3_len = cpu_to_be16((u16)hdr_len[1]);
hdr_desc.hdr.l4_len = (u8)hdr_len[2];
hdr_desc.hdr.flag = hdr_field << 1;
}
memcpy(data, cur, tmp);
tmp_len -= tmp;
*scrq_arr = hdr_desc;
scrq_arr++;
num_descs++;
}
return num_descs;
}
/**
* build_hdr_descs_arr - build a header descriptor array
* @skb - socket buffer
* @num_entries - number of descriptors to be sent
* @subcrq - first TX descriptor
* @hdr_field - bit field determining which headers will be sent
*
* This function will build a TX descriptor array with applicable
* L2/L3/L4 packet header descriptors to be sent by send_subcrq_indirect.
*/
static void build_hdr_descs_arr(struct ibmvnic_tx_buff *txbuff,
int *num_entries, u8 hdr_field)
{
int hdr_len[3] = {0, 0, 0};
int tot_len;
u8 *hdr_data = txbuff->hdr_data;
tot_len = build_hdr_data(hdr_field, txbuff->skb, hdr_len,
txbuff->hdr_data);
*num_entries += create_hdr_descs(hdr_field, hdr_data, tot_len, hdr_len,
txbuff->indir_arr + 1);
}
static int ibmvnic_xmit_workarounds(struct sk_buff *skb,
struct net_device *netdev)
{
/* For some backing devices, mishandling of small packets
* can result in a loss of connection or TX stall. Device
* architects recommend that no packet should be smaller
* than the minimum MTU value provided to the driver, so
* pad any packets to that length
*/
if (skb->len < netdev->min_mtu)
return skb_put_padto(skb, netdev->min_mtu);
return 0;
}
static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
int queue_num = skb_get_queue_mapping(skb);
u8 *hdrs = (u8 *)&adapter->tx_rx_desc_req;
struct device *dev = &adapter->vdev->dev;
struct ibmvnic_tx_buff *tx_buff = NULL;
struct ibmvnic_sub_crq_queue *tx_scrq;
struct ibmvnic_tx_pool *tx_pool;
unsigned int tx_send_failed = 0;
unsigned int tx_map_failed = 0;
unsigned int tx_dropped = 0;
unsigned int tx_packets = 0;
unsigned int tx_bytes = 0;
dma_addr_t data_dma_addr;
struct netdev_queue *txq;
unsigned long lpar_rc;
union sub_crq tx_crq;
unsigned int offset;
int num_entries = 1;
unsigned char *dst;
u64 *handle_array;
int index = 0;
u8 proto = 0;
netdev_tx_t ret = NETDEV_TX_OK;
if (test_bit(0, &adapter->resetting)) {
if (!netif_subqueue_stopped(netdev, skb))
netif_stop_subqueue(netdev, queue_num);
dev_kfree_skb_any(skb);
tx_send_failed++;
tx_dropped++;
ret = NETDEV_TX_OK;
goto out;
}
if (ibmvnic_xmit_workarounds(skb, netdev)) {
tx_dropped++;
tx_send_failed++;
ret = NETDEV_TX_OK;
goto out;
}
if (skb_is_gso(skb))
tx_pool = &adapter->tso_pool[queue_num];
else
tx_pool = &adapter->tx_pool[queue_num];
tx_scrq = adapter->tx_scrq[queue_num];
txq = netdev_get_tx_queue(netdev, skb_get_queue_mapping(skb));
handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
be32_to_cpu(adapter->login_rsp_buf->off_txsubm_subcrqs));
index = tx_pool->free_map[tx_pool->consumer_index];
if (index == IBMVNIC_INVALID_MAP) {
dev_kfree_skb_any(skb);
tx_send_failed++;
tx_dropped++;
ret = NETDEV_TX_OK;
goto out;
}
tx_pool->free_map[tx_pool->consumer_index] = IBMVNIC_INVALID_MAP;
offset = index * tx_pool->buf_size;
dst = tx_pool->long_term_buff.buff + offset;
memset(dst, 0, tx_pool->buf_size);
data_dma_addr = tx_pool->long_term_buff.addr + offset;
if (skb_shinfo(skb)->nr_frags) {
int cur, i;
/* Copy the head */
skb_copy_from_linear_data(skb, dst, skb_headlen(skb));
cur = skb_headlen(skb);
/* Copy the frags */
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
memcpy(dst + cur,
page_address(skb_frag_page(frag)) +
skb_frag_off(frag), skb_frag_size(frag));
cur += skb_frag_size(frag);
}
} else {
skb_copy_from_linear_data(skb, dst, skb->len);
}
tx_pool->consumer_index =
(tx_pool->consumer_index + 1) % tx_pool->num_buffers;
tx_buff = &tx_pool->tx_buff[index];
tx_buff->skb = skb;
tx_buff->data_dma[0] = data_dma_addr;
tx_buff->data_len[0] = skb->len;
tx_buff->index = index;
tx_buff->pool_index = queue_num;
tx_buff->last_frag = true;
memset(&tx_crq, 0, sizeof(tx_crq));
tx_crq.v1.first = IBMVNIC_CRQ_CMD;
tx_crq.v1.type = IBMVNIC_TX_DESC;
tx_crq.v1.n_crq_elem = 1;
tx_crq.v1.n_sge = 1;
tx_crq.v1.flags1 = IBMVNIC_TX_COMP_NEEDED;
if (skb_is_gso(skb))
tx_crq.v1.correlator =
cpu_to_be32(index | IBMVNIC_TSO_POOL_MASK);
else
tx_crq.v1.correlator = cpu_to_be32(index);
tx_crq.v1.dma_reg = cpu_to_be16(tx_pool->long_term_buff.map_id);
tx_crq.v1.sge_len = cpu_to_be32(skb->len);
tx_crq.v1.ioba = cpu_to_be64(data_dma_addr);
if (adapter->vlan_header_insertion && skb_vlan_tag_present(skb)) {
tx_crq.v1.flags2 |= IBMVNIC_TX_VLAN_INSERT;
tx_crq.v1.vlan_id = cpu_to_be16(skb->vlan_tci);
}
if (skb->protocol == htons(ETH_P_IP)) {
tx_crq.v1.flags1 |= IBMVNIC_TX_PROT_IPV4;
proto = ip_hdr(skb)->protocol;
} else if (skb->protocol == htons(ETH_P_IPV6)) {
tx_crq.v1.flags1 |= IBMVNIC_TX_PROT_IPV6;
proto = ipv6_hdr(skb)->nexthdr;
}
if (proto == IPPROTO_TCP)
tx_crq.v1.flags1 |= IBMVNIC_TX_PROT_TCP;
else if (proto == IPPROTO_UDP)
tx_crq.v1.flags1 |= IBMVNIC_TX_PROT_UDP;
if (skb->ip_summed == CHECKSUM_PARTIAL) {
tx_crq.v1.flags1 |= IBMVNIC_TX_CHKSUM_OFFLOAD;
hdrs += 2;
}
if (skb_is_gso(skb)) {
tx_crq.v1.flags1 |= IBMVNIC_TX_LSO;
tx_crq.v1.mss = cpu_to_be16(skb_shinfo(skb)->gso_size);
hdrs += 2;
}
/* determine if l2/3/4 headers are sent to firmware */
if ((*hdrs >> 7) & 1) {
build_hdr_descs_arr(tx_buff, &num_entries, *hdrs);
tx_crq.v1.n_crq_elem = num_entries;
tx_buff->num_entries = num_entries;
tx_buff->indir_arr[0] = tx_crq;
tx_buff->indir_dma = dma_map_single(dev, tx_buff->indir_arr,
sizeof(tx_buff->indir_arr),
DMA_TO_DEVICE);
if (dma_mapping_error(dev, tx_buff->indir_dma)) {
dev_kfree_skb_any(skb);
tx_buff->skb = NULL;
if (!firmware_has_feature(FW_FEATURE_CMO))
dev_err(dev, "tx: unable to map descriptor array\n");
tx_map_failed++;
tx_dropped++;
ret = NETDEV_TX_OK;
goto tx_err_out;
}
lpar_rc = send_subcrq_indirect(adapter, handle_array[queue_num],
(u64)tx_buff->indir_dma,
(u64)num_entries);
dma_unmap_single(dev, tx_buff->indir_dma,
sizeof(tx_buff->indir_arr), DMA_TO_DEVICE);
} else {
tx_buff->num_entries = num_entries;
lpar_rc = send_subcrq(adapter, handle_array[queue_num],
&tx_crq);
}
if (lpar_rc != H_SUCCESS) {
if (lpar_rc != H_CLOSED && lpar_rc != H_PARAMETER)
dev_err_ratelimited(dev, "tx: send failed\n");
dev_kfree_skb_any(skb);
tx_buff->skb = NULL;
if (lpar_rc == H_CLOSED || adapter->failover_pending) {
/* Disable TX and report carrier off if queue is closed
* or pending failover.
* Firmware guarantees that a signal will be sent to the
* driver, triggering a reset or some other action.
*/
netif_tx_stop_all_queues(netdev);
netif_carrier_off(netdev);
}
tx_send_failed++;
tx_dropped++;
ret = NETDEV_TX_OK;
goto tx_err_out;
}
if (atomic_add_return(num_entries, &tx_scrq->used)
>= adapter->req_tx_entries_per_subcrq) {
netdev_dbg(netdev, "Stopping queue %d\n", queue_num);
netif_stop_subqueue(netdev, queue_num);
}
tx_packets++;
tx_bytes += skb->len;
txq->trans_start = jiffies;
ret = NETDEV_TX_OK;
goto out;
tx_err_out:
/* roll back consumer index and map array*/
if (tx_pool->consumer_index == 0)
tx_pool->consumer_index =
tx_pool->num_buffers - 1;
else
tx_pool->consumer_index--;
tx_pool->free_map[tx_pool->consumer_index] = index;
out:
netdev->stats.tx_dropped += tx_dropped;
netdev->stats.tx_bytes += tx_bytes;
netdev->stats.tx_packets += tx_packets;
adapter->tx_send_failed += tx_send_failed;
adapter->tx_map_failed += tx_map_failed;
adapter->tx_stats_buffers[queue_num].packets += tx_packets;
adapter->tx_stats_buffers[queue_num].bytes += tx_bytes;
adapter->tx_stats_buffers[queue_num].dropped_packets += tx_dropped;
return ret;
}
static void ibmvnic_set_multi(struct net_device *netdev)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
struct netdev_hw_addr *ha;
union ibmvnic_crq crq;
memset(&crq, 0, sizeof(crq));
crq.request_capability.first = IBMVNIC_CRQ_CMD;
crq.request_capability.cmd = REQUEST_CAPABILITY;
if (netdev->flags & IFF_PROMISC) {
if (!adapter->promisc_supported)
return;
} else {
if (netdev->flags & IFF_ALLMULTI) {
/* Accept all multicast */
memset(&crq, 0, sizeof(crq));
crq.multicast_ctrl.first = IBMVNIC_CRQ_CMD;
crq.multicast_ctrl.cmd = MULTICAST_CTRL;
crq.multicast_ctrl.flags = IBMVNIC_ENABLE_ALL;
ibmvnic_send_crq(adapter, &crq);
} else if (netdev_mc_empty(netdev)) {
/* Reject all multicast */
memset(&crq, 0, sizeof(crq));
crq.multicast_ctrl.first = IBMVNIC_CRQ_CMD;
crq.multicast_ctrl.cmd = MULTICAST_CTRL;
crq.multicast_ctrl.flags = IBMVNIC_DISABLE_ALL;
ibmvnic_send_crq(adapter, &crq);
} else {
/* Accept one or more multicast(s) */
netdev_for_each_mc_addr(ha, netdev) {
memset(&crq, 0, sizeof(crq));
crq.multicast_ctrl.first = IBMVNIC_CRQ_CMD;
crq.multicast_ctrl.cmd = MULTICAST_CTRL;
crq.multicast_ctrl.flags = IBMVNIC_ENABLE_MC;
ether_addr_copy(&crq.multicast_ctrl.mac_addr[0],
ha->addr);
ibmvnic_send_crq(adapter, &crq);
}
}
}
}
static int __ibmvnic_set_mac(struct net_device *netdev, u8 *dev_addr)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
union ibmvnic_crq crq;
int rc;
if (!is_valid_ether_addr(dev_addr)) {
rc = -EADDRNOTAVAIL;
goto err;
}
memset(&crq, 0, sizeof(crq));
crq.change_mac_addr.first = IBMVNIC_CRQ_CMD;
crq.change_mac_addr.cmd = CHANGE_MAC_ADDR;
ether_addr_copy(&crq.change_mac_addr.mac_addr[0], dev_addr);
mutex_lock(&adapter->fw_lock);
adapter->fw_done_rc = 0;
reinit_completion(&adapter->fw_done);
rc = ibmvnic_send_crq(adapter, &crq);
if (rc) {
rc = -EIO;
mutex_unlock(&adapter->fw_lock);
goto err;
}
rc = ibmvnic_wait_for_completion(adapter, &adapter->fw_done, 10000);
/* netdev->dev_addr is changed in handle_change_mac_rsp function */
if (rc || adapter->fw_done_rc) {
rc = -EIO;
mutex_unlock(&adapter->fw_lock);
goto err;
}
mutex_unlock(&adapter->fw_lock);
return 0;
err:
ether_addr_copy(adapter->mac_addr, netdev->dev_addr);
return rc;
}
static int ibmvnic_set_mac(struct net_device *netdev, void *p)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
struct sockaddr *addr = p;
int rc;
rc = 0;
ether_addr_copy(adapter->mac_addr, addr->sa_data);
if (adapter->state != VNIC_PROBED)
rc = __ibmvnic_set_mac(netdev, addr->sa_data);
return rc;
}
/**
* do_change_param_reset returns zero if we are able to keep processing reset
* events, or non-zero if we hit a fatal error and must halt.
*/
static int do_change_param_reset(struct ibmvnic_adapter *adapter,
struct ibmvnic_rwi *rwi,
u32 reset_state)
{
struct net_device *netdev = adapter->netdev;
int i, rc;
netdev_dbg(adapter->netdev, "Change param resetting driver (%d)\n",
rwi->reset_reason);
netif_carrier_off(netdev);
adapter->reset_reason = rwi->reset_reason;
ibmvnic_cleanup(netdev);
if (reset_state == VNIC_OPEN) {
rc = __ibmvnic_close(netdev);
if (rc)
return rc;
}
release_resources(adapter);
release_sub_crqs(adapter, 1);
release_crq_queue(adapter);
adapter->state = VNIC_PROBED;
rc = init_crq_queue(adapter);
if (rc) {
netdev_err(adapter->netdev,
"Couldn't initialize crq. rc=%d\n", rc);
return rc;
}
rc = ibmvnic_reset_init(adapter);
if (rc)
return IBMVNIC_INIT_FAILED;
/* If the adapter was in PROBE state prior to the reset,
* exit here.
*/
if (reset_state == VNIC_PROBED)
return 0;
rc = ibmvnic_login(netdev);
if (rc) {
adapter->state = reset_state;
return rc;
}
rc = init_resources(adapter);
if (rc)
return rc;
ibmvnic_disable_irqs(adapter);
adapter->state = VNIC_CLOSED;
if (reset_state == VNIC_CLOSED)
return 0;
rc = __ibmvnic_open(netdev);
if (rc)
return IBMVNIC_OPEN_FAILED;
/* refresh device's multicast list */
ibmvnic_set_multi(netdev);
/* kick napi */
for (i = 0; i < adapter->req_rx_queues; i++)
napi_schedule(&adapter->napi[i]);
return 0;
}
/**
* do_reset returns zero if we are able to keep processing reset events, or
* non-zero if we hit a fatal error and must halt.
*/
static int do_reset(struct ibmvnic_adapter *adapter,
struct ibmvnic_rwi *rwi, u32 reset_state)
{
u64 old_num_rx_queues, old_num_tx_queues;
u64 old_num_rx_slots, old_num_tx_slots;
struct net_device *netdev = adapter->netdev;
int i, rc;
netdev_dbg(adapter->netdev, "Re-setting driver (%d)\n",
rwi->reset_reason);
rtnl_lock();
netif_carrier_off(netdev);
adapter->reset_reason = rwi->reset_reason;
old_num_rx_queues = adapter->req_rx_queues;
old_num_tx_queues = adapter->req_tx_queues;
old_num_rx_slots = adapter->req_rx_add_entries_per_subcrq;
old_num_tx_slots = adapter->req_tx_entries_per_subcrq;
ibmvnic_cleanup(netdev);
if (reset_state == VNIC_OPEN &&
adapter->reset_reason != VNIC_RESET_MOBILITY &&
adapter->reset_reason != VNIC_RESET_FAILOVER) {
adapter->state = VNIC_CLOSING;
/* Release the RTNL lock before link state change and
* re-acquire after the link state change to allow
* linkwatch_event to grab the RTNL lock and run during
* a reset.
*/
rtnl_unlock();
rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_DN);
rtnl_lock();
if (rc)
goto out;
if (adapter->state != VNIC_CLOSING) {
rc = -1;
goto out;
}
adapter->state = VNIC_CLOSED;
}
if (adapter->reset_reason != VNIC_RESET_NON_FATAL) {
/* remove the closed state so when we call open it appears
* we are coming from the probed state.
*/
adapter->state = VNIC_PROBED;
if (adapter->reset_reason == VNIC_RESET_MOBILITY) {
rc = ibmvnic_reenable_crq_queue(adapter);
release_sub_crqs(adapter, 1);
} else {
rc = ibmvnic_reset_crq(adapter);
if (!rc)
rc = vio_enable_interrupts(adapter->vdev);
}
if (rc) {
netdev_err(adapter->netdev,
"Couldn't initialize crq. rc=%d\n", rc);
goto out;
}
rc = ibmvnic_reset_init(adapter);
if (rc) {
rc = IBMVNIC_INIT_FAILED;
goto out;
}
/* If the adapter was in PROBE state prior to the reset,
* exit here.
*/
if (reset_state == VNIC_PROBED) {
rc = 0;
goto out;
}
rc = ibmvnic_login(netdev);
if (rc) {
adapter->state = reset_state;
goto out;
}
if (adapter->req_rx_queues != old_num_rx_queues ||
adapter->req_tx_queues != old_num_tx_queues ||
adapter->req_rx_add_entries_per_subcrq !=
old_num_rx_slots ||
adapter->req_tx_entries_per_subcrq !=
old_num_tx_slots) {
release_rx_pools(adapter);
release_tx_pools(adapter);
release_napi(adapter);
release_vpd_data(adapter);
rc = init_resources(adapter);
if (rc)
goto out;
} else {
rc = reset_tx_pools(adapter);
if (rc)
goto out;
rc = reset_rx_pools(adapter);
if (rc)
goto out;
}
ibmvnic_disable_irqs(adapter);
}
adapter->state = VNIC_CLOSED;
if (reset_state == VNIC_CLOSED) {
rc = 0;
goto out;
}
rc = __ibmvnic_open(netdev);
if (rc) {
rc = IBMVNIC_OPEN_FAILED;
goto out;
}
/* refresh device's multicast list */
ibmvnic_set_multi(netdev);
/* kick napi */
for (i = 0; i < adapter->req_rx_queues; i++)
napi_schedule(&adapter->napi[i]);
if (adapter->reset_reason != VNIC_RESET_FAILOVER)
call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, netdev);
rc = 0;
out:
rtnl_unlock();
return rc;
}
static int do_hard_reset(struct ibmvnic_adapter *adapter,
struct ibmvnic_rwi *rwi, u32 reset_state)
{
struct net_device *netdev = adapter->netdev;
int rc;
netdev_dbg(adapter->netdev, "Hard resetting driver (%d)\n",
rwi->reset_reason);
netif_carrier_off(netdev);
adapter->reset_reason = rwi->reset_reason;
ibmvnic_cleanup(netdev);
release_resources(adapter);
release_sub_crqs(adapter, 0);
release_crq_queue(adapter);
/* remove the closed state so when we call open it appears
* we are coming from the probed state.
*/
adapter->state = VNIC_PROBED;
reinit_completion(&adapter->init_done);
rc = init_crq_queue(adapter);
if (rc) {
netdev_err(adapter->netdev,
"Couldn't initialize crq. rc=%d\n", rc);
return rc;
}
rc = ibmvnic_init(adapter);
if (rc)
return rc;
/* If the adapter was in PROBE state prior to the reset,
* exit here.
*/
if (reset_state == VNIC_PROBED)
return 0;
rc = ibmvnic_login(netdev);
if (rc) {
adapter->state = VNIC_PROBED;
return 0;
}
rc = init_resources(adapter);
if (rc)
return rc;
ibmvnic_disable_irqs(adapter);
adapter->state = VNIC_CLOSED;
if (reset_state == VNIC_CLOSED)
return 0;
rc = __ibmvnic_open(netdev);
if (rc)
return IBMVNIC_OPEN_FAILED;
return 0;
}
static struct ibmvnic_rwi *get_next_rwi(struct ibmvnic_adapter *adapter)
{
struct ibmvnic_rwi *rwi;
unsigned long flags;
spin_lock_irqsave(&adapter->rwi_lock, flags);
if (!list_empty(&adapter->rwi_list)) {
rwi = list_first_entry(&adapter->rwi_list, struct ibmvnic_rwi,
list);
list_del(&rwi->list);
} else {
rwi = NULL;
}
spin_unlock_irqrestore(&adapter->rwi_lock, flags);
return rwi;
}
static void free_all_rwi(struct ibmvnic_adapter *adapter)
{
struct ibmvnic_rwi *rwi;
rwi = get_next_rwi(adapter);
while (rwi) {
kfree(rwi);
rwi = get_next_rwi(adapter);
}
}
static void __ibmvnic_reset(struct work_struct *work)
{
struct ibmvnic_rwi *rwi;
struct ibmvnic_adapter *adapter;
bool saved_state = false;
unsigned long flags;
u32 reset_state;
int rc = 0;
adapter = container_of(work, struct ibmvnic_adapter, ibmvnic_reset);
if (test_and_set_bit_lock(0, &adapter->resetting)) {
schedule_delayed_work(&adapter->ibmvnic_delayed_reset,
IBMVNIC_RESET_DELAY);
return;
}
rwi = get_next_rwi(adapter);
while (rwi) {
spin_lock_irqsave(&adapter->state_lock, flags);
if (adapter->state == VNIC_REMOVING ||
adapter->state == VNIC_REMOVED) {
spin_unlock_irqrestore(&adapter->state_lock, flags);
kfree(rwi);
rc = EBUSY;
break;
}
if (!saved_state) {
reset_state = adapter->state;
adapter->state = VNIC_RESETTING;
saved_state = true;
}
spin_unlock_irqrestore(&adapter->state_lock, flags);
if (rwi->reset_reason == VNIC_RESET_CHANGE_PARAM) {
/* CHANGE_PARAM requestor holds rtnl_lock */
rc = do_change_param_reset(adapter, rwi, reset_state);
} else if (adapter->force_reset_recovery) {
/* Transport event occurred during previous reset */
if (adapter->wait_for_reset) {
/* Previous was CHANGE_PARAM; caller locked */
adapter->force_reset_recovery = false;
rc = do_hard_reset(adapter, rwi, reset_state);
} else {
rtnl_lock();
adapter->force_reset_recovery = false;
rc = do_hard_reset(adapter, rwi, reset_state);
rtnl_unlock();
}
} else {
rc = do_reset(adapter, rwi, reset_state);
}
kfree(rwi);
if (rc == IBMVNIC_OPEN_FAILED) {
if (list_empty(&adapter->rwi_list))
adapter->state = VNIC_CLOSED;
else
adapter->state = reset_state;
rc = 0;
} else if (rc && rc != IBMVNIC_INIT_FAILED &&
!adapter->force_reset_recovery)
break;
rwi = get_next_rwi(adapter);
if (rwi && (rwi->reset_reason == VNIC_RESET_FAILOVER ||
rwi->reset_reason == VNIC_RESET_MOBILITY))
adapter->force_reset_recovery = true;
}
if (adapter->wait_for_reset) {
adapter->reset_done_rc = rc;
complete(&adapter->reset_done);
}
if (rc) {
netdev_dbg(adapter->netdev, "Reset failed\n");
free_all_rwi(adapter);
}
clear_bit_unlock(0, &adapter->resetting);
}
static void __ibmvnic_delayed_reset(struct work_struct *work)
{
struct ibmvnic_adapter *adapter;
adapter = container_of(work, struct ibmvnic_adapter,
ibmvnic_delayed_reset.work);
__ibmvnic_reset(&adapter->ibmvnic_reset);
}
static int ibmvnic_reset(struct ibmvnic_adapter *adapter,
enum ibmvnic_reset_reason reason)
{
struct list_head *entry, *tmp_entry;
struct ibmvnic_rwi *rwi, *tmp;
struct net_device *netdev = adapter->netdev;
unsigned long flags;
int ret;
if (adapter->state == VNIC_REMOVING ||
adapter->state == VNIC_REMOVED ||
adapter->failover_pending) {
ret = EBUSY;
netdev_dbg(netdev, "Adapter removing or pending failover, skipping reset\n");
goto err;
}
if (adapter->state == VNIC_PROBING) {
netdev_warn(netdev, "Adapter reset during probe\n");
ret = adapter->init_done_rc = EAGAIN;
goto err;
}
spin_lock_irqsave(&adapter->rwi_lock, flags);
list_for_each(entry, &adapter->rwi_list) {
tmp = list_entry(entry, struct ibmvnic_rwi, list);
if (tmp->reset_reason == reason) {
netdev_dbg(netdev, "Skipping matching reset\n");
spin_unlock_irqrestore(&adapter->rwi_lock, flags);
ret = EBUSY;
goto err;
}
}
rwi = kzalloc(sizeof(*rwi), GFP_ATOMIC);
if (!rwi) {
spin_unlock_irqrestore(&adapter->rwi_lock, flags);
ibmvnic_close(netdev);
ret = ENOMEM;
goto err;
}
/* if we just received a transport event,
* flush reset queue and process this reset
*/
if (adapter->force_reset_recovery && !list_empty(&adapter->rwi_list)) {
list_for_each_safe(entry, tmp_entry, &adapter->rwi_list)
list_del(entry);
}
rwi->reset_reason = reason;
list_add_tail(&rwi->list, &adapter->rwi_list);
spin_unlock_irqrestore(&adapter->rwi_lock, flags);
netdev_dbg(adapter->netdev, "Scheduling reset (reason %d)\n", reason);
schedule_work(&adapter->ibmvnic_reset);
return 0;
err:
return -ret;
}
static void ibmvnic_tx_timeout(struct net_device *dev, unsigned int txqueue)
{
struct ibmvnic_adapter *adapter = netdev_priv(dev);
ibmvnic_reset(adapter, VNIC_RESET_TIMEOUT);
}
static void remove_buff_from_pool(struct ibmvnic_adapter *adapter,
struct ibmvnic_rx_buff *rx_buff)
{
struct ibmvnic_rx_pool *pool = &adapter->rx_pool[rx_buff->pool_index];
rx_buff->skb = NULL;
pool->free_map[pool->next_alloc] = (int)(rx_buff - pool->rx_buff);
pool->next_alloc = (pool->next_alloc + 1) % pool->size;
atomic_dec(&pool->available);
}
static int ibmvnic_poll(struct napi_struct *napi, int budget)
{
struct net_device *netdev = napi->dev;
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
int scrq_num = (int)(napi - adapter->napi);
int frames_processed = 0;
restart_poll:
while (frames_processed < budget) {
struct sk_buff *skb;
struct ibmvnic_rx_buff *rx_buff;
union sub_crq *next;
u32 length;
u16 offset;
u8 flags = 0;
if (unlikely(test_bit(0, &adapter->resetting) &&
adapter->reset_reason != VNIC_RESET_NON_FATAL)) {
enable_scrq_irq(adapter, adapter->rx_scrq[scrq_num]);
napi_complete_done(napi, frames_processed);
return frames_processed;
}
if (!pending_scrq(adapter, adapter->rx_scrq[scrq_num]))
break;
next = ibmvnic_next_scrq(adapter, adapter->rx_scrq[scrq_num]);
rx_buff =
(struct ibmvnic_rx_buff *)be64_to_cpu(next->
rx_comp.correlator);
/* do error checking */
if (next->rx_comp.rc) {
netdev_dbg(netdev, "rx buffer returned with rc %x\n",
be16_to_cpu(next->rx_comp.rc));
/* free the entry */
next->rx_comp.first = 0;
dev_kfree_skb_any(rx_buff->skb);
remove_buff_from_pool(adapter, rx_buff);
continue;
} else if (!rx_buff->skb) {
/* free the entry */
next->rx_comp.first = 0;
remove_buff_from_pool(adapter, rx_buff);
continue;
}
length = be32_to_cpu(next->rx_comp.len);
offset = be16_to_cpu(next->rx_comp.off_frame_data);
flags = next->rx_comp.flags;
skb = rx_buff->skb;
skb_copy_to_linear_data(skb, rx_buff->data + offset,
length);
/* VLAN Header has been stripped by the system firmware and
* needs to be inserted by the driver
*/
if (adapter->rx_vlan_header_insertion &&
(flags & IBMVNIC_VLAN_STRIPPED))
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
ntohs(next->rx_comp.vlan_tci));
/* free the entry */
next->rx_comp.first = 0;
remove_buff_from_pool(adapter, rx_buff);
skb_put(skb, length);
skb->protocol = eth_type_trans(skb, netdev);
skb_record_rx_queue(skb, scrq_num);
if (flags & IBMVNIC_IP_CHKSUM_GOOD &&
flags & IBMVNIC_TCP_UDP_CHKSUM_GOOD) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
length = skb->len;
napi_gro_receive(napi, skb); /* send it up */
netdev->stats.rx_packets++;
netdev->stats.rx_bytes += length;
adapter->rx_stats_buffers[scrq_num].packets++;
adapter->rx_stats_buffers[scrq_num].bytes += length;
frames_processed++;
}
if (adapter->state != VNIC_CLOSING)
replenish_rx_pool(adapter, &adapter->rx_pool[scrq_num]);
if (frames_processed < budget) {
enable_scrq_irq(adapter, adapter->rx_scrq[scrq_num]);
napi_complete_done(napi, frames_processed);
if (pending_scrq(adapter, adapter->rx_scrq[scrq_num]) &&
napi_reschedule(napi)) {
disable_scrq_irq(adapter, adapter->rx_scrq[scrq_num]);
goto restart_poll;
}
}
return frames_processed;
}
static int wait_for_reset(struct ibmvnic_adapter *adapter)
{
int rc, ret;
adapter->fallback.mtu = adapter->req_mtu;
adapter->fallback.rx_queues = adapter->req_rx_queues;
adapter->fallback.tx_queues = adapter->req_tx_queues;
adapter->fallback.rx_entries = adapter->req_rx_add_entries_per_subcrq;
adapter->fallback.tx_entries = adapter->req_tx_entries_per_subcrq;
reinit_completion(&adapter->reset_done);
adapter->wait_for_reset = true;
rc = ibmvnic_reset(adapter, VNIC_RESET_CHANGE_PARAM);
if (rc) {
ret = rc;
goto out;
}
rc = ibmvnic_wait_for_completion(adapter, &adapter->reset_done, 60000);
if (rc) {
ret = -ENODEV;
goto out;
}
ret = 0;
if (adapter->reset_done_rc) {
ret = -EIO;
adapter->desired.mtu = adapter->fallback.mtu;
adapter->desired.rx_queues = adapter->fallback.rx_queues;
adapter->desired.tx_queues = adapter->fallback.tx_queues;
adapter->desired.rx_entries = adapter->fallback.rx_entries;
adapter->desired.tx_entries = adapter->fallback.tx_entries;
reinit_completion(&adapter->reset_done);
adapter->wait_for_reset = true;
rc = ibmvnic_reset(adapter, VNIC_RESET_CHANGE_PARAM);
if (rc) {
ret = rc;
goto out;
}
rc = ibmvnic_wait_for_completion(adapter, &adapter->reset_done,
60000);
if (rc) {
ret = -ENODEV;
goto out;
}
}
out:
adapter->wait_for_reset = false;
return ret;
}
static int ibmvnic_change_mtu(struct net_device *netdev, int new_mtu)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
adapter->desired.mtu = new_mtu + ETH_HLEN;
return wait_for_reset(adapter);
}
static netdev_features_t ibmvnic_features_check(struct sk_buff *skb,
struct net_device *dev,
netdev_features_t features)
{
/* Some backing hardware adapters can not
* handle packets with a MSS less than 224
* or with only one segment.
*/
if (skb_is_gso(skb)) {
if (skb_shinfo(skb)->gso_size < 224 ||
skb_shinfo(skb)->gso_segs == 1)
features &= ~NETIF_F_GSO_MASK;
}
return features;
}
static const struct net_device_ops ibmvnic_netdev_ops = {
.ndo_open = ibmvnic_open,
.ndo_stop = ibmvnic_close,
.ndo_start_xmit = ibmvnic_xmit,
.ndo_set_rx_mode = ibmvnic_set_multi,
.ndo_set_mac_address = ibmvnic_set_mac,
.ndo_validate_addr = eth_validate_addr,
.ndo_tx_timeout = ibmvnic_tx_timeout,
.ndo_change_mtu = ibmvnic_change_mtu,
.ndo_features_check = ibmvnic_features_check,
};
/* ethtool functions */
static int ibmvnic_get_link_ksettings(struct net_device *netdev,
struct ethtool_link_ksettings *cmd)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
int rc;
rc = send_query_phys_parms(adapter);
if (rc) {
adapter->speed = SPEED_UNKNOWN;
adapter->duplex = DUPLEX_UNKNOWN;
}
cmd->base.speed = adapter->speed;
cmd->base.duplex = adapter->duplex;
cmd->base.port = PORT_FIBRE;
cmd->base.phy_address = 0;
cmd->base.autoneg = AUTONEG_ENABLE;
return 0;
}
static void ibmvnic_get_drvinfo(struct net_device *netdev,
struct ethtool_drvinfo *info)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
strlcpy(info->driver, ibmvnic_driver_name, sizeof(info->driver));
strlcpy(info->version, IBMVNIC_DRIVER_VERSION, sizeof(info->version));
strlcpy(info->fw_version, adapter->fw_version,
sizeof(info->fw_version));
}
static u32 ibmvnic_get_msglevel(struct net_device *netdev)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
return adapter->msg_enable;
}
static void ibmvnic_set_msglevel(struct net_device *netdev, u32 data)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
adapter->msg_enable = data;
}
static u32 ibmvnic_get_link(struct net_device *netdev)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
/* Don't need to send a query because we request a logical link up at
* init and then we wait for link state indications
*/
return adapter->logical_link_state;
}
static void ibmvnic_get_ringparam(struct net_device *netdev,
struct ethtool_ringparam *ring)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
if (adapter->priv_flags & IBMVNIC_USE_SERVER_MAXES) {
ring->rx_max_pending = adapter->max_rx_add_entries_per_subcrq;
ring->tx_max_pending = adapter->max_tx_entries_per_subcrq;
} else {
ring->rx_max_pending = IBMVNIC_MAX_QUEUE_SZ;
ring->tx_max_pending = IBMVNIC_MAX_QUEUE_SZ;
}
ring->rx_mini_max_pending = 0;
ring->rx_jumbo_max_pending = 0;
ring->rx_pending = adapter->req_rx_add_entries_per_subcrq;
ring->tx_pending = adapter->req_tx_entries_per_subcrq;
ring->rx_mini_pending = 0;
ring->rx_jumbo_pending = 0;
}
static int ibmvnic_set_ringparam(struct net_device *netdev,
struct ethtool_ringparam *ring)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
int ret;
ret = 0;
adapter->desired.rx_entries = ring->rx_pending;
adapter->desired.tx_entries = ring->tx_pending;
ret = wait_for_reset(adapter);
if (!ret &&
(adapter->req_rx_add_entries_per_subcrq != ring->rx_pending ||
adapter->req_tx_entries_per_subcrq != ring->tx_pending))
netdev_info(netdev,
"Could not match full ringsize request. Requested: RX %d, TX %d; Allowed: RX %llu, TX %llu\n",
ring->rx_pending, ring->tx_pending,
adapter->req_rx_add_entries_per_subcrq,
adapter->req_tx_entries_per_subcrq);
return ret;
}
static void ibmvnic_get_channels(struct net_device *netdev,
struct ethtool_channels *channels)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
if (adapter->priv_flags & IBMVNIC_USE_SERVER_MAXES) {
channels->max_rx = adapter->max_rx_queues;
channels->max_tx = adapter->max_tx_queues;
} else {
channels->max_rx = IBMVNIC_MAX_QUEUES;
channels->max_tx = IBMVNIC_MAX_QUEUES;
}
channels->max_other = 0;
channels->max_combined = 0;
channels->rx_count = adapter->req_rx_queues;
channels->tx_count = adapter->req_tx_queues;
channels->other_count = 0;
channels->combined_count = 0;
}
static int ibmvnic_set_channels(struct net_device *netdev,
struct ethtool_channels *channels)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
int ret;
ret = 0;
adapter->desired.rx_queues = channels->rx_count;
adapter->desired.tx_queues = channels->tx_count;
ret = wait_for_reset(adapter);
if (!ret &&
(adapter->req_rx_queues != channels->rx_count ||
adapter->req_tx_queues != channels->tx_count))
netdev_info(netdev,
"Could not match full channels request. Requested: RX %d, TX %d; Allowed: RX %llu, TX %llu\n",
channels->rx_count, channels->tx_count,
adapter->req_rx_queues, adapter->req_tx_queues);
return ret;
}
static void ibmvnic_get_strings(struct net_device *dev, u32 stringset, u8 *data)
{
struct ibmvnic_adapter *adapter = netdev_priv(dev);
int i;
switch (stringset) {
case ETH_SS_STATS:
for (i = 0; i < ARRAY_SIZE(ibmvnic_stats);
i++, data += ETH_GSTRING_LEN)
memcpy(data, ibmvnic_stats[i].name, ETH_GSTRING_LEN);
for (i = 0; i < adapter->req_tx_queues; i++) {
snprintf(data, ETH_GSTRING_LEN, "tx%d_packets", i);
data += ETH_GSTRING_LEN;
snprintf(data, ETH_GSTRING_LEN, "tx%d_bytes", i);
data += ETH_GSTRING_LEN;
snprintf(data, ETH_GSTRING_LEN,
"tx%d_dropped_packets", i);
data += ETH_GSTRING_LEN;
}
for (i = 0; i < adapter->req_rx_queues; i++) {
snprintf(data, ETH_GSTRING_LEN, "rx%d_packets", i);
data += ETH_GSTRING_LEN;
snprintf(data, ETH_GSTRING_LEN, "rx%d_bytes", i);
data += ETH_GSTRING_LEN;
snprintf(data, ETH_GSTRING_LEN, "rx%d_interrupts", i);
data += ETH_GSTRING_LEN;
}
break;
case ETH_SS_PRIV_FLAGS:
for (i = 0; i < ARRAY_SIZE(ibmvnic_priv_flags); i++)
strcpy(data + i * ETH_GSTRING_LEN,
ibmvnic_priv_flags[i]);
break;
default:
return;
}
}
static int ibmvnic_get_sset_count(struct net_device *dev, int sset)
{
struct ibmvnic_adapter *adapter = netdev_priv(dev);
switch (sset) {
case ETH_SS_STATS:
return ARRAY_SIZE(ibmvnic_stats) +
adapter->req_tx_queues * NUM_TX_STATS +
adapter->req_rx_queues * NUM_RX_STATS;
case ETH_SS_PRIV_FLAGS:
return ARRAY_SIZE(ibmvnic_priv_flags);
default:
return -EOPNOTSUPP;
}
}
static void ibmvnic_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
struct ibmvnic_adapter