![Neil Horman](/assets/img/avatar_default.png)
Drivers might call napi_disable while not holding the napi instance poll_lock. In those instances, its possible for a race condition to exist between poll_one_napi and napi_disable. That is to say, poll_one_napi only tests the NAPI_STATE_SCHED bit to see if there is work to do during a poll, and as such the following may happen: CPU0 CPU1 ndo_tx_timeout napi_poll_dev napi_disable poll_one_napi test_and_set_bit (ret 0) test_bit (ret 1) reset adapter napi_poll_routine If the adapter gets a tx timeout without a napi instance scheduled, its possible for the adapter to think it has exclusive access to the hardware (as the napi instance is now scheduled via the napi_disable call), while the netpoll code thinks there is simply work to do. The result is parallel hardware access leading to corrupt data structures in the driver, and a crash. Additionaly, there is another, more critical race between netpoll and napi_disable. The disabled napi state is actually identical to the scheduled state for a given napi instance. The implication being that, if a napi instance is disabled, a netconsole instance would see the napi state of the device as having been scheduled, and poll it, likely while the driver was dong something requiring exclusive access. In the case above, its fairly clear that not having the rings in a state ready to be polled will cause any number of crashes. The fix should be pretty easy. netpoll uses its own bit to indicate that that the napi instance is in a state of being serviced by netpoll (NAPI_STATE_NPSVC). We can just gate disabling on that bit as well as the sched bit. That should prevent netpoll from conducting a napi poll if we convert its set bit to a test_and_set_bit operation to provide mutual exclusion Change notes: V2) Remove a trailing whtiespace Resubmit with proper subject prefix V3) Clean up spacing nits Signed-off-by: Neil Horman <nhorman@tuxdriver.com> CC: "David S. Miller" <davem@davemloft.net> CC: jmaxwell@redhat.com Tested-by: jmaxwell@redhat.com Signed-off-by: David S. Miller <davem@davemloft.net>
861 lines
19 KiB
C
861 lines
19 KiB
C
/*
|
|
* Common framework for low-level network console, dump, and debugger code
|
|
*
|
|
* Sep 8 2003 Matt Mackall <mpm@selenic.com>
|
|
*
|
|
* based on the netconsole code from:
|
|
*
|
|
* Copyright (C) 2001 Ingo Molnar <mingo@redhat.com>
|
|
* Copyright (C) 2002 Red Hat, Inc.
|
|
*/
|
|
|
|
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
|
|
|
|
#include <linux/moduleparam.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/netdevice.h>
|
|
#include <linux/etherdevice.h>
|
|
#include <linux/string.h>
|
|
#include <linux/if_arp.h>
|
|
#include <linux/inetdevice.h>
|
|
#include <linux/inet.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/netpoll.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/delay.h>
|
|
#include <linux/rcupdate.h>
|
|
#include <linux/workqueue.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/export.h>
|
|
#include <linux/if_vlan.h>
|
|
#include <net/tcp.h>
|
|
#include <net/udp.h>
|
|
#include <net/addrconf.h>
|
|
#include <net/ndisc.h>
|
|
#include <net/ip6_checksum.h>
|
|
#include <asm/unaligned.h>
|
|
#include <trace/events/napi.h>
|
|
|
|
/*
|
|
* We maintain a small pool of fully-sized skbs, to make sure the
|
|
* message gets out even in extreme OOM situations.
|
|
*/
|
|
|
|
#define MAX_UDP_CHUNK 1460
|
|
#define MAX_SKBS 32
|
|
|
|
static struct sk_buff_head skb_pool;
|
|
|
|
DEFINE_STATIC_SRCU(netpoll_srcu);
|
|
|
|
#define USEC_PER_POLL 50
|
|
|
|
#define MAX_SKB_SIZE \
|
|
(sizeof(struct ethhdr) + \
|
|
sizeof(struct iphdr) + \
|
|
sizeof(struct udphdr) + \
|
|
MAX_UDP_CHUNK)
|
|
|
|
static void zap_completion_queue(void);
|
|
static void netpoll_async_cleanup(struct work_struct *work);
|
|
|
|
static unsigned int carrier_timeout = 4;
|
|
module_param(carrier_timeout, uint, 0644);
|
|
|
|
#define np_info(np, fmt, ...) \
|
|
pr_info("%s: " fmt, np->name, ##__VA_ARGS__)
|
|
#define np_err(np, fmt, ...) \
|
|
pr_err("%s: " fmt, np->name, ##__VA_ARGS__)
|
|
#define np_notice(np, fmt, ...) \
|
|
pr_notice("%s: " fmt, np->name, ##__VA_ARGS__)
|
|
|
|
static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
|
|
struct netdev_queue *txq)
|
|
{
|
|
int status = NETDEV_TX_OK;
|
|
netdev_features_t features;
|
|
|
|
features = netif_skb_features(skb);
|
|
|
|
if (skb_vlan_tag_present(skb) &&
|
|
!vlan_hw_offload_capable(features, skb->vlan_proto)) {
|
|
skb = __vlan_hwaccel_push_inside(skb);
|
|
if (unlikely(!skb)) {
|
|
/* This is actually a packet drop, but we
|
|
* don't want the code that calls this
|
|
* function to try and operate on a NULL skb.
|
|
*/
|
|
goto out;
|
|
}
|
|
}
|
|
|
|
status = netdev_start_xmit(skb, dev, txq, false);
|
|
|
|
out:
|
|
return status;
|
|
}
|
|
|
|
static void queue_process(struct work_struct *work)
|
|
{
|
|
struct netpoll_info *npinfo =
|
|
container_of(work, struct netpoll_info, tx_work.work);
|
|
struct sk_buff *skb;
|
|
unsigned long flags;
|
|
|
|
while ((skb = skb_dequeue(&npinfo->txq))) {
|
|
struct net_device *dev = skb->dev;
|
|
struct netdev_queue *txq;
|
|
|
|
if (!netif_device_present(dev) || !netif_running(dev)) {
|
|
kfree_skb(skb);
|
|
continue;
|
|
}
|
|
|
|
txq = skb_get_tx_queue(dev, skb);
|
|
|
|
local_irq_save(flags);
|
|
HARD_TX_LOCK(dev, txq, smp_processor_id());
|
|
if (netif_xmit_frozen_or_stopped(txq) ||
|
|
netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
|
|
skb_queue_head(&npinfo->txq, skb);
|
|
HARD_TX_UNLOCK(dev, txq);
|
|
local_irq_restore(flags);
|
|
|
|
schedule_delayed_work(&npinfo->tx_work, HZ/10);
|
|
return;
|
|
}
|
|
HARD_TX_UNLOCK(dev, txq);
|
|
local_irq_restore(flags);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Check whether delayed processing was scheduled for our NIC. If so,
|
|
* we attempt to grab the poll lock and use ->poll() to pump the card.
|
|
* If this fails, either we've recursed in ->poll() or it's already
|
|
* running on another CPU.
|
|
*
|
|
* Note: we don't mask interrupts with this lock because we're using
|
|
* trylock here and interrupts are already disabled in the softirq
|
|
* case. Further, we test the poll_owner to avoid recursion on UP
|
|
* systems where the lock doesn't exist.
|
|
*/
|
|
static int poll_one_napi(struct napi_struct *napi, int budget)
|
|
{
|
|
int work = 0;
|
|
|
|
/* net_rx_action's ->poll() invocations and our's are
|
|
* synchronized by this test which is only made while
|
|
* holding the napi->poll_lock.
|
|
*/
|
|
if (!test_bit(NAPI_STATE_SCHED, &napi->state))
|
|
return budget;
|
|
|
|
/* If we set this bit but see that it has already been set,
|
|
* that indicates that napi has been disabled and we need
|
|
* to abort this operation
|
|
*/
|
|
if (test_and_set_bit(NAPI_STATE_NPSVC, &napi->state))
|
|
goto out;
|
|
|
|
work = napi->poll(napi, budget);
|
|
WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll);
|
|
trace_napi_poll(napi);
|
|
|
|
clear_bit(NAPI_STATE_NPSVC, &napi->state);
|
|
|
|
out:
|
|
return budget - work;
|
|
}
|
|
|
|
static void poll_napi(struct net_device *dev, int budget)
|
|
{
|
|
struct napi_struct *napi;
|
|
|
|
list_for_each_entry(napi, &dev->napi_list, dev_list) {
|
|
if (napi->poll_owner != smp_processor_id() &&
|
|
spin_trylock(&napi->poll_lock)) {
|
|
budget = poll_one_napi(napi, budget);
|
|
spin_unlock(&napi->poll_lock);
|
|
}
|
|
}
|
|
}
|
|
|
|
static void netpoll_poll_dev(struct net_device *dev)
|
|
{
|
|
const struct net_device_ops *ops;
|
|
struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
|
|
int budget = 0;
|
|
|
|
/* Don't do any rx activity if the dev_lock mutex is held
|
|
* the dev_open/close paths use this to block netpoll activity
|
|
* while changing device state
|
|
*/
|
|
if (down_trylock(&ni->dev_lock))
|
|
return;
|
|
|
|
if (!netif_running(dev)) {
|
|
up(&ni->dev_lock);
|
|
return;
|
|
}
|
|
|
|
ops = dev->netdev_ops;
|
|
if (!ops->ndo_poll_controller) {
|
|
up(&ni->dev_lock);
|
|
return;
|
|
}
|
|
|
|
/* Process pending work on NIC */
|
|
ops->ndo_poll_controller(dev);
|
|
|
|
poll_napi(dev, budget);
|
|
|
|
up(&ni->dev_lock);
|
|
|
|
zap_completion_queue();
|
|
}
|
|
|
|
void netpoll_poll_disable(struct net_device *dev)
|
|
{
|
|
struct netpoll_info *ni;
|
|
int idx;
|
|
might_sleep();
|
|
idx = srcu_read_lock(&netpoll_srcu);
|
|
ni = srcu_dereference(dev->npinfo, &netpoll_srcu);
|
|
if (ni)
|
|
down(&ni->dev_lock);
|
|
srcu_read_unlock(&netpoll_srcu, idx);
|
|
}
|
|
EXPORT_SYMBOL(netpoll_poll_disable);
|
|
|
|
void netpoll_poll_enable(struct net_device *dev)
|
|
{
|
|
struct netpoll_info *ni;
|
|
rcu_read_lock();
|
|
ni = rcu_dereference(dev->npinfo);
|
|
if (ni)
|
|
up(&ni->dev_lock);
|
|
rcu_read_unlock();
|
|
}
|
|
EXPORT_SYMBOL(netpoll_poll_enable);
|
|
|
|
static void refill_skbs(void)
|
|
{
|
|
struct sk_buff *skb;
|
|
unsigned long flags;
|
|
|
|
spin_lock_irqsave(&skb_pool.lock, flags);
|
|
while (skb_pool.qlen < MAX_SKBS) {
|
|
skb = alloc_skb(MAX_SKB_SIZE, GFP_ATOMIC);
|
|
if (!skb)
|
|
break;
|
|
|
|
__skb_queue_tail(&skb_pool, skb);
|
|
}
|
|
spin_unlock_irqrestore(&skb_pool.lock, flags);
|
|
}
|
|
|
|
static void zap_completion_queue(void)
|
|
{
|
|
unsigned long flags;
|
|
struct softnet_data *sd = &get_cpu_var(softnet_data);
|
|
|
|
if (sd->completion_queue) {
|
|
struct sk_buff *clist;
|
|
|
|
local_irq_save(flags);
|
|
clist = sd->completion_queue;
|
|
sd->completion_queue = NULL;
|
|
local_irq_restore(flags);
|
|
|
|
while (clist != NULL) {
|
|
struct sk_buff *skb = clist;
|
|
clist = clist->next;
|
|
if (!skb_irq_freeable(skb)) {
|
|
atomic_inc(&skb->users);
|
|
dev_kfree_skb_any(skb); /* put this one back */
|
|
} else {
|
|
__kfree_skb(skb);
|
|
}
|
|
}
|
|
}
|
|
|
|
put_cpu_var(softnet_data);
|
|
}
|
|
|
|
static struct sk_buff *find_skb(struct netpoll *np, int len, int reserve)
|
|
{
|
|
int count = 0;
|
|
struct sk_buff *skb;
|
|
|
|
zap_completion_queue();
|
|
refill_skbs();
|
|
repeat:
|
|
|
|
skb = alloc_skb(len, GFP_ATOMIC);
|
|
if (!skb)
|
|
skb = skb_dequeue(&skb_pool);
|
|
|
|
if (!skb) {
|
|
if (++count < 10) {
|
|
netpoll_poll_dev(np->dev);
|
|
goto repeat;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
atomic_set(&skb->users, 1);
|
|
skb_reserve(skb, reserve);
|
|
return skb;
|
|
}
|
|
|
|
static int netpoll_owner_active(struct net_device *dev)
|
|
{
|
|
struct napi_struct *napi;
|
|
|
|
list_for_each_entry(napi, &dev->napi_list, dev_list) {
|
|
if (napi->poll_owner == smp_processor_id())
|
|
return 1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/* call with IRQ disabled */
|
|
void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
|
|
struct net_device *dev)
|
|
{
|
|
int status = NETDEV_TX_BUSY;
|
|
unsigned long tries;
|
|
/* It is up to the caller to keep npinfo alive. */
|
|
struct netpoll_info *npinfo;
|
|
|
|
WARN_ON_ONCE(!irqs_disabled());
|
|
|
|
npinfo = rcu_dereference_bh(np->dev->npinfo);
|
|
if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) {
|
|
dev_kfree_skb_irq(skb);
|
|
return;
|
|
}
|
|
|
|
/* don't get messages out of order, and no recursion */
|
|
if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) {
|
|
struct netdev_queue *txq;
|
|
|
|
txq = netdev_pick_tx(dev, skb, NULL);
|
|
|
|
/* try until next clock tick */
|
|
for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
|
|
tries > 0; --tries) {
|
|
if (HARD_TX_TRYLOCK(dev, txq)) {
|
|
if (!netif_xmit_stopped(txq))
|
|
status = netpoll_start_xmit(skb, dev, txq);
|
|
|
|
HARD_TX_UNLOCK(dev, txq);
|
|
|
|
if (status == NETDEV_TX_OK)
|
|
break;
|
|
|
|
}
|
|
|
|
/* tickle device maybe there is some cleanup */
|
|
netpoll_poll_dev(np->dev);
|
|
|
|
udelay(USEC_PER_POLL);
|
|
}
|
|
|
|
WARN_ONCE(!irqs_disabled(),
|
|
"netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pF)\n",
|
|
dev->name, dev->netdev_ops->ndo_start_xmit);
|
|
|
|
}
|
|
|
|
if (status != NETDEV_TX_OK) {
|
|
skb_queue_tail(&npinfo->txq, skb);
|
|
schedule_delayed_work(&npinfo->tx_work,0);
|
|
}
|
|
}
|
|
EXPORT_SYMBOL(netpoll_send_skb_on_dev);
|
|
|
|
void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
|
|
{
|
|
int total_len, ip_len, udp_len;
|
|
struct sk_buff *skb;
|
|
struct udphdr *udph;
|
|
struct iphdr *iph;
|
|
struct ethhdr *eth;
|
|
static atomic_t ip_ident;
|
|
struct ipv6hdr *ip6h;
|
|
|
|
WARN_ON_ONCE(!irqs_disabled());
|
|
|
|
udp_len = len + sizeof(*udph);
|
|
if (np->ipv6)
|
|
ip_len = udp_len + sizeof(*ip6h);
|
|
else
|
|
ip_len = udp_len + sizeof(*iph);
|
|
|
|
total_len = ip_len + LL_RESERVED_SPACE(np->dev);
|
|
|
|
skb = find_skb(np, total_len + np->dev->needed_tailroom,
|
|
total_len - len);
|
|
if (!skb)
|
|
return;
|
|
|
|
skb_copy_to_linear_data(skb, msg, len);
|
|
skb_put(skb, len);
|
|
|
|
skb_push(skb, sizeof(*udph));
|
|
skb_reset_transport_header(skb);
|
|
udph = udp_hdr(skb);
|
|
udph->source = htons(np->local_port);
|
|
udph->dest = htons(np->remote_port);
|
|
udph->len = htons(udp_len);
|
|
|
|
if (np->ipv6) {
|
|
udph->check = 0;
|
|
udph->check = csum_ipv6_magic(&np->local_ip.in6,
|
|
&np->remote_ip.in6,
|
|
udp_len, IPPROTO_UDP,
|
|
csum_partial(udph, udp_len, 0));
|
|
if (udph->check == 0)
|
|
udph->check = CSUM_MANGLED_0;
|
|
|
|
skb_push(skb, sizeof(*ip6h));
|
|
skb_reset_network_header(skb);
|
|
ip6h = ipv6_hdr(skb);
|
|
|
|
/* ip6h->version = 6; ip6h->priority = 0; */
|
|
put_unaligned(0x60, (unsigned char *)ip6h);
|
|
ip6h->flow_lbl[0] = 0;
|
|
ip6h->flow_lbl[1] = 0;
|
|
ip6h->flow_lbl[2] = 0;
|
|
|
|
ip6h->payload_len = htons(sizeof(struct udphdr) + len);
|
|
ip6h->nexthdr = IPPROTO_UDP;
|
|
ip6h->hop_limit = 32;
|
|
ip6h->saddr = np->local_ip.in6;
|
|
ip6h->daddr = np->remote_ip.in6;
|
|
|
|
eth = (struct ethhdr *) skb_push(skb, ETH_HLEN);
|
|
skb_reset_mac_header(skb);
|
|
skb->protocol = eth->h_proto = htons(ETH_P_IPV6);
|
|
} else {
|
|
udph->check = 0;
|
|
udph->check = csum_tcpudp_magic(np->local_ip.ip,
|
|
np->remote_ip.ip,
|
|
udp_len, IPPROTO_UDP,
|
|
csum_partial(udph, udp_len, 0));
|
|
if (udph->check == 0)
|
|
udph->check = CSUM_MANGLED_0;
|
|
|
|
skb_push(skb, sizeof(*iph));
|
|
skb_reset_network_header(skb);
|
|
iph = ip_hdr(skb);
|
|
|
|
/* iph->version = 4; iph->ihl = 5; */
|
|
put_unaligned(0x45, (unsigned char *)iph);
|
|
iph->tos = 0;
|
|
put_unaligned(htons(ip_len), &(iph->tot_len));
|
|
iph->id = htons(atomic_inc_return(&ip_ident));
|
|
iph->frag_off = 0;
|
|
iph->ttl = 64;
|
|
iph->protocol = IPPROTO_UDP;
|
|
iph->check = 0;
|
|
put_unaligned(np->local_ip.ip, &(iph->saddr));
|
|
put_unaligned(np->remote_ip.ip, &(iph->daddr));
|
|
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
|
|
|
|
eth = (struct ethhdr *) skb_push(skb, ETH_HLEN);
|
|
skb_reset_mac_header(skb);
|
|
skb->protocol = eth->h_proto = htons(ETH_P_IP);
|
|
}
|
|
|
|
ether_addr_copy(eth->h_source, np->dev->dev_addr);
|
|
ether_addr_copy(eth->h_dest, np->remote_mac);
|
|
|
|
skb->dev = np->dev;
|
|
|
|
netpoll_send_skb(np, skb);
|
|
}
|
|
EXPORT_SYMBOL(netpoll_send_udp);
|
|
|
|
void netpoll_print_options(struct netpoll *np)
|
|
{
|
|
np_info(np, "local port %d\n", np->local_port);
|
|
if (np->ipv6)
|
|
np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6);
|
|
else
|
|
np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip);
|
|
np_info(np, "interface '%s'\n", np->dev_name);
|
|
np_info(np, "remote port %d\n", np->remote_port);
|
|
if (np->ipv6)
|
|
np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6);
|
|
else
|
|
np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip);
|
|
np_info(np, "remote ethernet address %pM\n", np->remote_mac);
|
|
}
|
|
EXPORT_SYMBOL(netpoll_print_options);
|
|
|
|
static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr)
|
|
{
|
|
const char *end;
|
|
|
|
if (!strchr(str, ':') &&
|
|
in4_pton(str, -1, (void *)addr, -1, &end) > 0) {
|
|
if (!*end)
|
|
return 0;
|
|
}
|
|
if (in6_pton(str, -1, addr->in6.s6_addr, -1, &end) > 0) {
|
|
#if IS_ENABLED(CONFIG_IPV6)
|
|
if (!*end)
|
|
return 1;
|
|
#else
|
|
return -1;
|
|
#endif
|
|
}
|
|
return -1;
|
|
}
|
|
|
|
int netpoll_parse_options(struct netpoll *np, char *opt)
|
|
{
|
|
char *cur=opt, *delim;
|
|
int ipv6;
|
|
bool ipversion_set = false;
|
|
|
|
if (*cur != '@') {
|
|
if ((delim = strchr(cur, '@')) == NULL)
|
|
goto parse_failed;
|
|
*delim = 0;
|
|
if (kstrtou16(cur, 10, &np->local_port))
|
|
goto parse_failed;
|
|
cur = delim;
|
|
}
|
|
cur++;
|
|
|
|
if (*cur != '/') {
|
|
ipversion_set = true;
|
|
if ((delim = strchr(cur, '/')) == NULL)
|
|
goto parse_failed;
|
|
*delim = 0;
|
|
ipv6 = netpoll_parse_ip_addr(cur, &np->local_ip);
|
|
if (ipv6 < 0)
|
|
goto parse_failed;
|
|
else
|
|
np->ipv6 = (bool)ipv6;
|
|
cur = delim;
|
|
}
|
|
cur++;
|
|
|
|
if (*cur != ',') {
|
|
/* parse out dev name */
|
|
if ((delim = strchr(cur, ',')) == NULL)
|
|
goto parse_failed;
|
|
*delim = 0;
|
|
strlcpy(np->dev_name, cur, sizeof(np->dev_name));
|
|
cur = delim;
|
|
}
|
|
cur++;
|
|
|
|
if (*cur != '@') {
|
|
/* dst port */
|
|
if ((delim = strchr(cur, '@')) == NULL)
|
|
goto parse_failed;
|
|
*delim = 0;
|
|
if (*cur == ' ' || *cur == '\t')
|
|
np_info(np, "warning: whitespace is not allowed\n");
|
|
if (kstrtou16(cur, 10, &np->remote_port))
|
|
goto parse_failed;
|
|
cur = delim;
|
|
}
|
|
cur++;
|
|
|
|
/* dst ip */
|
|
if ((delim = strchr(cur, '/')) == NULL)
|
|
goto parse_failed;
|
|
*delim = 0;
|
|
ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip);
|
|
if (ipv6 < 0)
|
|
goto parse_failed;
|
|
else if (ipversion_set && np->ipv6 != (bool)ipv6)
|
|
goto parse_failed;
|
|
else
|
|
np->ipv6 = (bool)ipv6;
|
|
cur = delim + 1;
|
|
|
|
if (*cur != 0) {
|
|
/* MAC address */
|
|
if (!mac_pton(cur, np->remote_mac))
|
|
goto parse_failed;
|
|
}
|
|
|
|
netpoll_print_options(np);
|
|
|
|
return 0;
|
|
|
|
parse_failed:
|
|
np_info(np, "couldn't parse config at '%s'!\n", cur);
|
|
return -1;
|
|
}
|
|
EXPORT_SYMBOL(netpoll_parse_options);
|
|
|
|
int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
|
|
{
|
|
struct netpoll_info *npinfo;
|
|
const struct net_device_ops *ops;
|
|
int err;
|
|
|
|
np->dev = ndev;
|
|
strlcpy(np->dev_name, ndev->name, IFNAMSIZ);
|
|
INIT_WORK(&np->cleanup_work, netpoll_async_cleanup);
|
|
|
|
if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) ||
|
|
!ndev->netdev_ops->ndo_poll_controller) {
|
|
np_err(np, "%s doesn't support polling, aborting\n",
|
|
np->dev_name);
|
|
err = -ENOTSUPP;
|
|
goto out;
|
|
}
|
|
|
|
if (!ndev->npinfo) {
|
|
npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL);
|
|
if (!npinfo) {
|
|
err = -ENOMEM;
|
|
goto out;
|
|
}
|
|
|
|
sema_init(&npinfo->dev_lock, 1);
|
|
skb_queue_head_init(&npinfo->txq);
|
|
INIT_DELAYED_WORK(&npinfo->tx_work, queue_process);
|
|
|
|
atomic_set(&npinfo->refcnt, 1);
|
|
|
|
ops = np->dev->netdev_ops;
|
|
if (ops->ndo_netpoll_setup) {
|
|
err = ops->ndo_netpoll_setup(ndev, npinfo);
|
|
if (err)
|
|
goto free_npinfo;
|
|
}
|
|
} else {
|
|
npinfo = rtnl_dereference(ndev->npinfo);
|
|
atomic_inc(&npinfo->refcnt);
|
|
}
|
|
|
|
npinfo->netpoll = np;
|
|
|
|
/* last thing to do is link it to the net device structure */
|
|
rcu_assign_pointer(ndev->npinfo, npinfo);
|
|
|
|
return 0;
|
|
|
|
free_npinfo:
|
|
kfree(npinfo);
|
|
out:
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__netpoll_setup);
|
|
|
|
int netpoll_setup(struct netpoll *np)
|
|
{
|
|
struct net_device *ndev = NULL;
|
|
struct in_device *in_dev;
|
|
int err;
|
|
|
|
rtnl_lock();
|
|
if (np->dev_name) {
|
|
struct net *net = current->nsproxy->net_ns;
|
|
ndev = __dev_get_by_name(net, np->dev_name);
|
|
}
|
|
if (!ndev) {
|
|
np_err(np, "%s doesn't exist, aborting\n", np->dev_name);
|
|
err = -ENODEV;
|
|
goto unlock;
|
|
}
|
|
dev_hold(ndev);
|
|
|
|
if (netdev_master_upper_dev_get(ndev)) {
|
|
np_err(np, "%s is a slave device, aborting\n", np->dev_name);
|
|
err = -EBUSY;
|
|
goto put;
|
|
}
|
|
|
|
if (!netif_running(ndev)) {
|
|
unsigned long atmost, atleast;
|
|
|
|
np_info(np, "device %s not up yet, forcing it\n", np->dev_name);
|
|
|
|
err = dev_open(ndev);
|
|
|
|
if (err) {
|
|
np_err(np, "failed to open %s\n", ndev->name);
|
|
goto put;
|
|
}
|
|
|
|
rtnl_unlock();
|
|
atleast = jiffies + HZ/10;
|
|
atmost = jiffies + carrier_timeout * HZ;
|
|
while (!netif_carrier_ok(ndev)) {
|
|
if (time_after(jiffies, atmost)) {
|
|
np_notice(np, "timeout waiting for carrier\n");
|
|
break;
|
|
}
|
|
msleep(1);
|
|
}
|
|
|
|
/* If carrier appears to come up instantly, we don't
|
|
* trust it and pause so that we don't pump all our
|
|
* queued console messages into the bitbucket.
|
|
*/
|
|
|
|
if (time_before(jiffies, atleast)) {
|
|
np_notice(np, "carrier detect appears untrustworthy, waiting 4 seconds\n");
|
|
msleep(4000);
|
|
}
|
|
rtnl_lock();
|
|
}
|
|
|
|
if (!np->local_ip.ip) {
|
|
if (!np->ipv6) {
|
|
in_dev = __in_dev_get_rtnl(ndev);
|
|
|
|
if (!in_dev || !in_dev->ifa_list) {
|
|
np_err(np, "no IP address for %s, aborting\n",
|
|
np->dev_name);
|
|
err = -EDESTADDRREQ;
|
|
goto put;
|
|
}
|
|
|
|
np->local_ip.ip = in_dev->ifa_list->ifa_local;
|
|
np_info(np, "local IP %pI4\n", &np->local_ip.ip);
|
|
} else {
|
|
#if IS_ENABLED(CONFIG_IPV6)
|
|
struct inet6_dev *idev;
|
|
|
|
err = -EDESTADDRREQ;
|
|
idev = __in6_dev_get(ndev);
|
|
if (idev) {
|
|
struct inet6_ifaddr *ifp;
|
|
|
|
read_lock_bh(&idev->lock);
|
|
list_for_each_entry(ifp, &idev->addr_list, if_list) {
|
|
if (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)
|
|
continue;
|
|
np->local_ip.in6 = ifp->addr;
|
|
err = 0;
|
|
break;
|
|
}
|
|
read_unlock_bh(&idev->lock);
|
|
}
|
|
if (err) {
|
|
np_err(np, "no IPv6 address for %s, aborting\n",
|
|
np->dev_name);
|
|
goto put;
|
|
} else
|
|
np_info(np, "local IPv6 %pI6c\n", &np->local_ip.in6);
|
|
#else
|
|
np_err(np, "IPv6 is not supported %s, aborting\n",
|
|
np->dev_name);
|
|
err = -EINVAL;
|
|
goto put;
|
|
#endif
|
|
}
|
|
}
|
|
|
|
/* fill up the skb queue */
|
|
refill_skbs();
|
|
|
|
err = __netpoll_setup(np, ndev);
|
|
if (err)
|
|
goto put;
|
|
|
|
rtnl_unlock();
|
|
return 0;
|
|
|
|
put:
|
|
dev_put(ndev);
|
|
unlock:
|
|
rtnl_unlock();
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL(netpoll_setup);
|
|
|
|
static int __init netpoll_init(void)
|
|
{
|
|
skb_queue_head_init(&skb_pool);
|
|
return 0;
|
|
}
|
|
core_initcall(netpoll_init);
|
|
|
|
static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head)
|
|
{
|
|
struct netpoll_info *npinfo =
|
|
container_of(rcu_head, struct netpoll_info, rcu);
|
|
|
|
skb_queue_purge(&npinfo->txq);
|
|
|
|
/* we can't call cancel_delayed_work_sync here, as we are in softirq */
|
|
cancel_delayed_work(&npinfo->tx_work);
|
|
|
|
/* clean after last, unfinished work */
|
|
__skb_queue_purge(&npinfo->txq);
|
|
/* now cancel it again */
|
|
cancel_delayed_work(&npinfo->tx_work);
|
|
kfree(npinfo);
|
|
}
|
|
|
|
void __netpoll_cleanup(struct netpoll *np)
|
|
{
|
|
struct netpoll_info *npinfo;
|
|
|
|
/* rtnl_dereference would be preferable here but
|
|
* rcu_cleanup_netpoll path can put us in here safely without
|
|
* holding the rtnl, so plain rcu_dereference it is
|
|
*/
|
|
npinfo = rtnl_dereference(np->dev->npinfo);
|
|
if (!npinfo)
|
|
return;
|
|
|
|
synchronize_srcu(&netpoll_srcu);
|
|
|
|
if (atomic_dec_and_test(&npinfo->refcnt)) {
|
|
const struct net_device_ops *ops;
|
|
|
|
ops = np->dev->netdev_ops;
|
|
if (ops->ndo_netpoll_cleanup)
|
|
ops->ndo_netpoll_cleanup(np->dev);
|
|
|
|
RCU_INIT_POINTER(np->dev->npinfo, NULL);
|
|
call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info);
|
|
} else
|
|
RCU_INIT_POINTER(np->dev->npinfo, NULL);
|
|
}
|
|
EXPORT_SYMBOL_GPL(__netpoll_cleanup);
|
|
|
|
static void netpoll_async_cleanup(struct work_struct *work)
|
|
{
|
|
struct netpoll *np = container_of(work, struct netpoll, cleanup_work);
|
|
|
|
rtnl_lock();
|
|
__netpoll_cleanup(np);
|
|
rtnl_unlock();
|
|
kfree(np);
|
|
}
|
|
|
|
void __netpoll_free_async(struct netpoll *np)
|
|
{
|
|
schedule_work(&np->cleanup_work);
|
|
}
|
|
EXPORT_SYMBOL_GPL(__netpoll_free_async);
|
|
|
|
void netpoll_cleanup(struct netpoll *np)
|
|
{
|
|
rtnl_lock();
|
|
if (!np->dev)
|
|
goto out;
|
|
__netpoll_cleanup(np);
|
|
dev_put(np->dev);
|
|
np->dev = NULL;
|
|
out:
|
|
rtnl_unlock();
|
|
}
|
|
EXPORT_SYMBOL(netpoll_cleanup);
|