Something went wrong. Try again.
Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Something went wrong. Try again.
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695// SPDX-License-Identifier: GPL-2.0-only/* * 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 <linux/udp.h>#include <net/tcp.h>#include <net/addrconf.h>#include <net/ndisc.h>#include <trace/events/napi.h>#include <linux/kconfig.h>
/* * We maintain a small pool of fully-sized skbs, to make sure the * message gets out even in extreme OOM situations. */
#define MAX_SKBS 32#define USEC_PER_POLL 50
static unsigned int carrier_timeout = 4;module_param(carrier_timeout, uint, 0644);
static netdev_tx_t netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq){ netdev_tx_t 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; unsigned int q_index;
if (!netif_device_present(dev) || !netif_running(dev)) { kfree_skb(skb); continue; }
local_irq_save(flags); /* check if skb->queue_mapping is still valid */ q_index = skb_get_queue_mapping(skb); if (unlikely(q_index >= dev->real_num_tx_queues)) { q_index = q_index % dev->real_num_tx_queues; skb_set_queue_mapping(skb, q_index); } txq = netdev_get_tx_queue(dev, q_index); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (netif_xmit_frozen_or_stopped(txq) || !dev_xmit_complete(netpoll_start_xmit(skb, dev, txq))) { 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); }}
static int netif_local_xmit_active(struct net_device *dev){ int i;
for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
if (netif_tx_owned(txq, smp_processor_id())) return 1; }
return 0;}
static void poll_one_napi(struct napi_struct *napi){ int work;
/* 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)) return;
/* We explicitly pass the polling call a budget of 0 to * indicate that we are clearing the Tx path only. */ work = napi->poll(napi, 0); WARN_ONCE(work, "%pS exceeded budget in poll\n", napi->poll); trace_napi_poll(napi, work, 0);
clear_bit(NAPI_STATE_NPSVC, &napi->state);}
static void poll_napi(struct net_device *dev){ struct napi_struct *napi; int cpu = smp_processor_id();
list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { if (cmpxchg(&napi->poll_owner, -1, cpu) == -1) { poll_one_napi(napi); smp_store_release(&napi->poll_owner, -1); } }}
void netpoll_poll_dev(struct net_device *dev){ struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo); const struct net_device_ops *ops;
/* 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 (!ni || down_trylock(&ni->dev_lock)) return;
/* Some drivers will take the same locks in poll and xmit, * we can't poll if local CPU is already in xmit. */ if (!netif_running(dev) || netif_local_xmit_active(dev)) { up(&ni->dev_lock); return; }
ops = dev->netdev_ops; if (ops->ndo_poll_controller) ops->ndo_poll_controller(dev);
poll_napi(dev);
up(&ni->dev_lock);
netpoll_zap_completion_queue();}EXPORT_SYMBOL(netpoll_poll_dev);
void netpoll_poll_disable(struct net_device *dev){ struct netpoll_info *ni;
might_sleep(); ni = rtnl_dereference(dev->npinfo); if (ni) down(&ni->dev_lock);}
void netpoll_poll_enable(struct net_device *dev){ struct netpoll_info *ni;
ni = rtnl_dereference(dev->npinfo); if (ni) up(&ni->dev_lock);}
static void refill_skbs(struct netpoll *np){ struct sk_buff_head *skb_pool; struct sk_buff *skb;
skb_pool = &np->skb_pool;
while (READ_ONCE(skb_pool->qlen) < MAX_SKBS) { skb = alloc_skb(MAX_SKB_SIZE, GFP_ATOMIC); if (!skb) break;
skb_queue_tail(skb_pool, skb); }}
void netpoll_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)) { refcount_set(&skb->users, 1); dev_kfree_skb_any(skb); /* put this one back */ } else { __kfree_skb(skb); } } }
put_cpu_var(softnet_data);}EXPORT_SYMBOL_NS_GPL(netpoll_zap_completion_queue, "NETDEV_INTERNAL");
static int netpoll_owner_active(struct net_device *dev){ struct napi_struct *napi;
list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { if (READ_ONCE(napi->poll_owner) == smp_processor_id()) return 1; } return 0;}
/* call with IRQ disabled */static netdev_tx_t __netpoll_send_skb(struct netpoll *np, struct sk_buff *skb){ netdev_tx_t status = NETDEV_TX_BUSY; netdev_tx_t ret = NET_XMIT_DROP; struct net_device *dev; unsigned long tries; /* It is up to the caller to keep npinfo alive. */ struct netpoll_info *npinfo;
lockdep_assert_irqs_disabled();
dev = np->dev; /* npinfo->txq belongs to np->dev, so retries must stay bound to it. */ skb->dev = dev; rcu_read_lock(); npinfo = rcu_dereference_bh(dev->npinfo);
if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) { dev_kfree_skb_irq(skb); goto out; }
/* 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_core_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 (dev_xmit_complete(status)) 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 (%pS)\n", dev->name, dev->netdev_ops->ndo_start_xmit);
}
if (!dev_xmit_complete(status)) { skb_queue_tail(&npinfo->txq, skb); schedule_delayed_work(&npinfo->tx_work,0); } ret = NETDEV_TX_OK;out: rcu_read_unlock(); return ret;}
netdev_tx_t netpoll_send_skb(struct netpoll *np, struct sk_buff *skb){ unsigned long flags; netdev_tx_t ret;
if (unlikely(!np)) { dev_kfree_skb_irq(skb); ret = NET_XMIT_DROP; } else { local_irq_save(flags); ret = __netpoll_send_skb(np, skb); local_irq_restore(flags); } return ret;}EXPORT_SYMBOL(netpoll_send_skb);
static void skb_pool_flush(struct netpoll *np){ struct sk_buff_head *skb_pool;
cancel_work_sync(&np->refill_wq); skb_pool = &np->skb_pool; skb_queue_purge_reason(skb_pool, SKB_CONSUMED);}
static void refill_skbs_work_handler(struct work_struct *work){ struct netpoll *np = container_of(work, struct netpoll, refill_wq);
refill_skbs(np);}
int __netpoll_setup(struct netpoll *np, struct net_device *ndev){ struct netpoll_info *npinfo; const struct net_device_ops *ops; int err;
skb_queue_head_init(&np->skb_pool); INIT_WORK(&np->refill_wq, refill_skbs_work_handler);
if (ndev->priv_flags & IFF_DISABLE_NETPOLL) { np_err(np, "%s doesn't support polling, aborting\n", ndev->name); err = -ENOTSUPP; goto out; }
npinfo = rtnl_dereference(ndev->npinfo); if (!npinfo) { npinfo = kmalloc_obj(*npinfo); 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);
refcount_set(&npinfo->refcnt, 1);
ops = ndev->netdev_ops; if (ops->ndo_netpoll_setup) { err = ops->ndo_netpoll_setup(ndev); if (err) goto free_npinfo; } } else { refcount_inc(&npinfo->refcnt); }
np->dev = ndev; strscpy(np->dev_name, ndev->name, IFNAMSIZ);
/* fill up the skb queue */ refill_skbs(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);
/* * Returns a pointer to a string representation of the identifier used * to select the egress interface for the given netpoll instance. buf * is used to format np->dev_mac when np->dev_name is empty; bufsz must * be at least MAC_ADDR_STR_LEN + 1 to fit the formatted MAC address * and its NUL terminator. */static char *egress_dev(struct netpoll *np, char *buf, size_t bufsz){ if (np->dev_name[0]) return np->dev_name;
snprintf(buf, bufsz, "%pM", np->dev_mac); return buf;}
static void netpoll_wait_carrier(struct netpoll *np, struct net_device *ndev, unsigned int timeout){ unsigned long atmost;
atmost = jiffies + timeout * HZ; while (!netif_carrier_ok(ndev)) { if (time_after(jiffies, atmost)) { np_notice(np, "timeout waiting for carrier\n"); break; } msleep(1); }}
/* * Take the IPv6 from ndev and populate local_ip structure in netpoll */static int netpoll_take_ipv6(struct netpoll *np, struct net_device *ndev){ char buf[MAC_ADDR_STR_LEN + 1]; int err = -EDESTADDRREQ; struct inet6_dev *idev;
if (!IS_ENABLED(CONFIG_IPV6)) { np_err(np, "IPv6 is not supported %s, aborting\n", egress_dev(np, buf, sizeof(buf))); return -EINVAL; }
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) != !!(ipv6_addr_type(&np->remote_ip.in6) & IPV6_ADDR_LINKLOCAL)) continue; /* Got the IP, let's return */ 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", egress_dev(np, buf, sizeof(buf))); return err; }
np_info(np, "local IPv6 %pI6c\n", &np->local_ip.in6); return 0;}
/* * Take the IPv4 from ndev and populate local_ip structure in netpoll */static int netpoll_take_ipv4(struct netpoll *np, struct net_device *ndev){ char buf[MAC_ADDR_STR_LEN + 1]; const struct in_ifaddr *ifa; struct in_device *in_dev;
in_dev = __in_dev_get_rtnl(ndev); if (!in_dev) { np_err(np, "no IP address for %s, aborting\n", egress_dev(np, buf, sizeof(buf))); return -EDESTADDRREQ; }
ifa = rtnl_dereference(in_dev->ifa_list); if (!ifa) { np_err(np, "no IP address for %s, aborting\n", egress_dev(np, buf, sizeof(buf))); return -EDESTADDRREQ; }
np->local_ip.ip = ifa->ifa_local; np_info(np, "local IP %pI4\n", &np->local_ip.ip);
return 0;}
/* * Test whether the caller left np->local_ip unset, so that * netpoll_setup() should auto-populate it from the egress device. * * np->local_ip is a union of __be32 (IPv4) and struct in6_addr (IPv6), * so an IPv6 address whose first 4 bytes are zero (e.g. ::1, ::2, * IPv4-mapped ::ffff:a.b.c.d) must not be tested via the IPv4 arm — * doing so would misclassify a caller-supplied address as unset and * silently overwrite it with whatever address the device exposes. */static bool netpoll_local_ip_unset(const struct netpoll *np){ if (np->ipv6) return ipv6_addr_any(&np->local_ip.in6); return !np->local_ip.ip;}
int netpoll_setup(struct netpoll *np){ struct net *net = current->nsproxy->net_ns; char buf[MAC_ADDR_STR_LEN + 1]; struct net_device *ndev = NULL; bool ip_overwritten = false; int err;
rtnl_lock(); if (np->dev_name[0]) ndev = __dev_get_by_name(net, np->dev_name); else if (is_valid_ether_addr(np->dev_mac)) ndev = dev_getbyhwaddr(net, ARPHRD_ETHER, np->dev_mac);
if (!ndev) { np_err(np, "%s doesn't exist, aborting\n", egress_dev(np, buf, sizeof(buf))); err = -ENODEV; goto unlock; } netdev_hold(ndev, &np->dev_tracker, GFP_KERNEL);
if (netdev_master_upper_dev_get(ndev)) { np_err(np, "%s is a slave device, aborting\n", egress_dev(np, buf, sizeof(buf))); err = -EBUSY; goto put; }
if (!netif_running(ndev)) { np_info(np, "device %s not up yet, forcing it\n", egress_dev(np, buf, sizeof(buf)));
err = dev_open(ndev, NULL); if (err) { np_err(np, "failed to open %s\n", ndev->name); goto put; }
rtnl_unlock(); netpoll_wait_carrier(np, ndev, carrier_timeout); rtnl_lock(); }
if (netpoll_local_ip_unset(np)) { if (!np->ipv6) { err = netpoll_take_ipv4(np, ndev); if (err) goto put; } else { err = netpoll_take_ipv6(np, ndev); if (err) goto put; } ip_overwritten = true; }
err = __netpoll_setup(np, ndev); if (err) goto flush; rtnl_unlock();
/* Make sure all NAPI polls which started before dev->npinfo * was visible have exited before we start calling NAPI poll. * NAPI skips locking if dev->npinfo is NULL. */ synchronize_rcu();
return 0;
flush: skb_pool_flush(np);put: DEBUG_NET_WARN_ON_ONCE(np->dev); if (ip_overwritten) memset(&np->local_ip, 0, sizeof(np->local_ip)); netdev_put(ndev, &np->dev_tracker);unlock: rtnl_unlock(); return err;}EXPORT_SYMBOL(netpoll_setup);
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); kfree(npinfo);}
static void __netpoll_cleanup(struct netpoll *np){ struct netpoll_info *npinfo;
npinfo = rtnl_dereference(np->dev->npinfo); if (!npinfo) return;
/* At this point, there is a single npinfo instance per netdevice, and * its refcnt tracks how many netpoll structures are linked to it. We * only perform npinfo cleanup when the refcnt decrements to zero. */ if (refcount_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); disable_delayed_work_sync(&npinfo->tx_work); call_rcu(&npinfo->rcu, rcu_cleanup_netpoll_info); }
skb_pool_flush(np);}
void __netpoll_free(struct netpoll *np){ ASSERT_RTNL();
/* Wait for transmitting packets to finish before freeing. */ synchronize_net(); __netpoll_cleanup(np); kfree(np);}EXPORT_SYMBOL_GPL(__netpoll_free);
void do_netpoll_cleanup(struct netpoll *np){ __netpoll_cleanup(np); netdev_put(np->dev, &np->dev_tracker); np->dev = NULL;}EXPORT_SYMBOL(do_netpoll_cleanup);
void netpoll_cleanup(struct netpoll *np){ rtnl_lock(); if (!np->dev) goto out; do_netpoll_cleanup(np);out: rtnl_unlock();}EXPORT_SYMBOL(netpoll_cleanup);