Subash Abhinov Kasiviswanathandev: Defer free of skbs in flush_backlog7df5cb76 years agoHistory
10693 lines · 266.2 KB · C
RawDownload
// SPDX-License-Identifier: GPL-2.0-or-later/* *      NET3    Protocol independent device support routines. * *	Derived from the non IP parts of dev.c 1.0.19 *              Authors:	Ross Biro *				Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> *				Mark Evans, <evansmp@uhura.aston.ac.uk> * *	Additional Authors: *		Florian la Roche <rzsfl@rz.uni-sb.de> *		Alan Cox <gw4pts@gw4pts.ampr.org> *		David Hinds <dahinds@users.sourceforge.net> *		Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> *		Adam Sulmicki <adam@cfar.umd.edu> *              Pekka Riikonen <priikone@poesidon.pspt.fi> * *	Changes: *              D.J. Barrow     :       Fixed bug where dev->refcnt gets set *                                      to 2 if register_netdev gets called *                                      before net_dev_init & also removed a *                                      few lines of code in the process. *		Alan Cox	:	device private ioctl copies fields back. *		Alan Cox	:	Transmit queue code does relevant *					stunts to keep the queue safe. *		Alan Cox	:	Fixed double lock. *		Alan Cox	:	Fixed promisc NULL pointer trap *		????????	:	Support the full private ioctl range *		Alan Cox	:	Moved ioctl permission check into *					drivers *		Tim Kordas	:	SIOCADDMULTI/SIOCDELMULTI *		Alan Cox	:	100 backlog just doesn't cut it when *					you start doing multicast video 8) *		Alan Cox	:	Rewrote net_bh and list manager. *              Alan Cox        :       Fix ETH_P_ALL echoback lengths. *		Alan Cox	:	Took out transmit every packet pass *					Saved a few bytes in the ioctl handler *		Alan Cox	:	Network driver sets packet type before *					calling netif_rx. Saves a function *					call a packet. *		Alan Cox	:	Hashed net_bh() *		Richard Kooijman:	Timestamp fixes. *		Alan Cox	:	Wrong field in SIOCGIFDSTADDR *		Alan Cox	:	Device lock protection. *              Alan Cox        :       Fixed nasty side effect of device close *					changes. *		Rudi Cilibrasi	:	Pass the right thing to *					set_mac_address() *		Dave Miller	:	32bit quantity for the device lock to *					make it work out on a Sparc. *		Bjorn Ekwall	:	Added KERNELD hack. *		Alan Cox	:	Cleaned up the backlog initialise. *		Craig Metz	:	SIOCGIFCONF fix if space for under *					1 device. *	    Thomas Bogendoerfer :	Return ENODEV for dev_open, if there *					is no device open function. *		Andi Kleen	:	Fix error reporting for SIOCGIFCONF *	    Michael Chastain	:	Fix signed/unsigned for SIOCGIFCONF *		Cyrus Durgin	:	Cleaned for KMOD *		Adam Sulmicki   :	Bug Fix : Network Device Unload *					A network device unload needs to purge *					the backlog queue. *	Paul Rusty Russell	:	SIOCSIFNAME *              Pekka Riikonen  :	Netdev boot-time settings code *              Andrew Morton   :       Make unregister_netdevice wait *                                      indefinitely on dev->refcnt *              J Hadi Salim    :       - Backlog queue sampling *				        - netif_rx() feedback */ #include <linux/uaccess.h>#include <linux/bitops.h>#include <linux/capability.h>#include <linux/cpu.h>#include <linux/types.h>#include <linux/kernel.h>#include <linux/hash.h>#include <linux/slab.h>#include <linux/sched.h>#include <linux/sched/mm.h>#include <linux/mutex.h>#include <linux/rwsem.h>#include <linux/string.h>#include <linux/mm.h>#include <linux/socket.h>#include <linux/sockios.h>#include <linux/errno.h>#include <linux/interrupt.h>#include <linux/if_ether.h>#include <linux/netdevice.h>#include <linux/etherdevice.h>#include <linux/ethtool.h>#include <linux/skbuff.h>#include <linux/bpf.h>#include <linux/bpf_trace.h>#include <net/net_namespace.h>#include <net/sock.h>#include <net/busy_poll.h>#include <linux/rtnetlink.h>#include <linux/stat.h>#include <net/dst.h>#include <net/dst_metadata.h>#include <net/pkt_sched.h>#include <net/pkt_cls.h>#include <net/checksum.h>#include <net/xfrm.h>#include <linux/highmem.h>#include <linux/init.h>#include <linux/module.h>#include <linux/netpoll.h>#include <linux/rcupdate.h>#include <linux/delay.h>#include <net/iw_handler.h>#include <asm/current.h>#include <linux/audit.h>#include <linux/dmaengine.h>#include <linux/err.h>#include <linux/ctype.h>#include <linux/if_arp.h>#include <linux/if_vlan.h>#include <linux/ip.h>#include <net/ip.h>#include <net/mpls.h>#include <linux/ipv6.h>#include <linux/in.h>#include <linux/jhash.h>#include <linux/random.h>#include <trace/events/napi.h>#include <trace/events/net.h>#include <trace/events/skb.h>#include <linux/inetdevice.h>#include <linux/cpu_rmap.h>#include <linux/static_key.h>#include <linux/hashtable.h>#include <linux/vmalloc.h>#include <linux/if_macvlan.h>#include <linux/errqueue.h>#include <linux/hrtimer.h>#include <linux/netfilter_ingress.h>#include <linux/crash_dump.h>#include <linux/sctp.h>#include <net/udp_tunnel.h>#include <linux/net_namespace.h>#include <linux/indirect_call_wrapper.h>#include <net/devlink.h> #include "net-sysfs.h" #define MAX_GRO_SKBS 8 /* This should be increased if a protocol with a bigger head is added. */#define GRO_MAX_HEAD (MAX_HEADER + 128) static DEFINE_SPINLOCK(ptype_lock);static DEFINE_SPINLOCK(offload_lock);struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;struct list_head ptype_all __read_mostly;	/* Taps */static struct list_head offload_base __read_mostly; static int netif_rx_internal(struct sk_buff *skb);static int call_netdevice_notifiers_info(unsigned long val,					 struct netdev_notifier_info *info);static int call_netdevice_notifiers_extack(unsigned long val,					   struct net_device *dev,					   struct netlink_ext_ack *extack);static struct napi_struct *napi_by_id(unsigned int napi_id); /* * The @dev_base_head list is protected by @dev_base_lock and the rtnl * semaphore. * * Pure readers hold dev_base_lock for reading, or rcu_read_lock() * * Writers must hold the rtnl semaphore while they loop through the * dev_base_head list, and hold dev_base_lock for writing when they do the * actual updates.  This allows pure readers to access the list even * while a writer is preparing to update it. * * To put it another way, dev_base_lock is held for writing only to * protect against pure readers; the rtnl semaphore provides the * protection against other writers. * * See, for example usages, register_netdevice() and * unregister_netdevice(), which must be called with the rtnl * semaphore held. */DEFINE_RWLOCK(dev_base_lock);EXPORT_SYMBOL(dev_base_lock); static DEFINE_MUTEX(ifalias_mutex); /* protects napi_hash addition/deletion and napi_gen_id */static DEFINE_SPINLOCK(napi_hash_lock); static unsigned int napi_gen_id = NR_CPUS;static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8); static DECLARE_RWSEM(devnet_rename_sem); static inline void dev_base_seq_inc(struct net *net){	while (++net->dev_base_seq == 0)		;} static inline struct hlist_head *dev_name_hash(struct net *net, const char *name){	unsigned int hash = full_name_hash(net, name, strnlen(name, IFNAMSIZ)); 	return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)];} static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex){	return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)];} static inline void rps_lock(struct softnet_data *sd){#ifdef CONFIG_RPS	spin_lock(&sd->input_pkt_queue.lock);#endif} static inline void rps_unlock(struct softnet_data *sd){#ifdef CONFIG_RPS	spin_unlock(&sd->input_pkt_queue.lock);#endif} static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev,						       const char *name){	struct netdev_name_node *name_node; 	name_node = kmalloc(sizeof(*name_node), GFP_KERNEL);	if (!name_node)		return NULL;	INIT_HLIST_NODE(&name_node->hlist);	name_node->dev = dev;	name_node->name = name;	return name_node;} static struct netdev_name_node *netdev_name_node_head_alloc(struct net_device *dev){	struct netdev_name_node *name_node; 	name_node = netdev_name_node_alloc(dev, dev->name);	if (!name_node)		return NULL;	INIT_LIST_HEAD(&name_node->list);	return name_node;} static void netdev_name_node_free(struct netdev_name_node *name_node){	kfree(name_node);} static void netdev_name_node_add(struct net *net,				 struct netdev_name_node *name_node){	hlist_add_head_rcu(&name_node->hlist,			   dev_name_hash(net, name_node->name));} static void netdev_name_node_del(struct netdev_name_node *name_node){	hlist_del_rcu(&name_node->hlist);} static struct netdev_name_node *netdev_name_node_lookup(struct net *net,							const char *name){	struct hlist_head *head = dev_name_hash(net, name);	struct netdev_name_node *name_node; 	hlist_for_each_entry(name_node, head, hlist)		if (!strcmp(name_node->name, name))			return name_node;	return NULL;} static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net,							    const char *name){	struct hlist_head *head = dev_name_hash(net, name);	struct netdev_name_node *name_node; 	hlist_for_each_entry_rcu(name_node, head, hlist)		if (!strcmp(name_node->name, name))			return name_node;	return NULL;} int netdev_name_node_alt_create(struct net_device *dev, const char *name){	struct netdev_name_node *name_node;	struct net *net = dev_net(dev); 	name_node = netdev_name_node_lookup(net, name);	if (name_node)		return -EEXIST;	name_node = netdev_name_node_alloc(dev, name);	if (!name_node)		return -ENOMEM;	netdev_name_node_add(net, name_node);	/* The node that holds dev->name acts as a head of per-device list. */	list_add_tail(&name_node->list, &dev->name_node->list); 	return 0;}EXPORT_SYMBOL(netdev_name_node_alt_create); static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node){	list_del(&name_node->list);	netdev_name_node_del(name_node);	kfree(name_node->name);	netdev_name_node_free(name_node);} int netdev_name_node_alt_destroy(struct net_device *dev, const char *name){	struct netdev_name_node *name_node;	struct net *net = dev_net(dev); 	name_node = netdev_name_node_lookup(net, name);	if (!name_node)		return -ENOENT;	/* lookup might have found our primary name or a name belonging	 * to another device.	 */	if (name_node == dev->name_node || name_node->dev != dev)		return -EINVAL; 	__netdev_name_node_alt_destroy(name_node); 	return 0;}EXPORT_SYMBOL(netdev_name_node_alt_destroy); static void netdev_name_node_alt_flush(struct net_device *dev){	struct netdev_name_node *name_node, *tmp; 	list_for_each_entry_safe(name_node, tmp, &dev->name_node->list, list)		__netdev_name_node_alt_destroy(name_node);} /* Device list insertion */static void list_netdevice(struct net_device *dev){	struct net *net = dev_net(dev); 	ASSERT_RTNL(); 	write_lock_bh(&dev_base_lock);	list_add_tail_rcu(&dev->dev_list, &net->dev_base_head);	netdev_name_node_add(net, dev->name_node);	hlist_add_head_rcu(&dev->index_hlist,			   dev_index_hash(net, dev->ifindex));	write_unlock_bh(&dev_base_lock); 	dev_base_seq_inc(net);} /* Device list removal * caller must respect a RCU grace period before freeing/reusing dev */static void unlist_netdevice(struct net_device *dev){	ASSERT_RTNL(); 	/* Unlink dev from the device chain */	write_lock_bh(&dev_base_lock);	list_del_rcu(&dev->dev_list);	netdev_name_node_del(dev->name_node);	hlist_del_rcu(&dev->index_hlist);	write_unlock_bh(&dev_base_lock); 	dev_base_seq_inc(dev_net(dev));} /* *	Our notifier list */ static RAW_NOTIFIER_HEAD(netdev_chain); /* *	Device drivers call our routines to queue packets here. We empty the *	queue in the local softnet handler. */ DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);EXPORT_PER_CPU_SYMBOL(softnet_data); #ifdef CONFIG_LOCKDEP/* * register_netdevice() inits txq->_xmit_lock and sets lockdep class * according to dev->type */static const unsigned short netdev_lock_type[] = {	 ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25,	 ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET,	 ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM,	 ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP,	 ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD,	 ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25,	 ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP,	 ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD,	 ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI,	 ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE,	 ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET,	 ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL,	 ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM,	 ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE,	 ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE}; static const char *const netdev_lock_name[] = {	"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",	"_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET",	"_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM",	"_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP",	"_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD",	"_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25",	"_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP",	"_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD",	"_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI",	"_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE",	"_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET",	"_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",	"_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM",	"_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE",	"_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; static inline unsigned short netdev_lock_pos(unsigned short dev_type){	int i; 	for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++)		if (netdev_lock_type[i] == dev_type)			return i;	/* the last key is used by default */	return ARRAY_SIZE(netdev_lock_type) - 1;} static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,						 unsigned short dev_type){	int i; 	i = netdev_lock_pos(dev_type);	lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i],				   netdev_lock_name[i]);} static inline void netdev_set_addr_lockdep_class(struct net_device *dev){	int i; 	i = netdev_lock_pos(dev->type);	lockdep_set_class_and_name(&dev->addr_list_lock,				   &netdev_addr_lock_key[i],				   netdev_lock_name[i]);}#elsestatic inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,						 unsigned short dev_type){} static inline void netdev_set_addr_lockdep_class(struct net_device *dev){}#endif /******************************************************************************* * *		Protocol management and registration routines * *******************************************************************************/  /* *	Add a protocol ID to the list. Now that the input handler is *	smarter we can dispense with all the messy stuff that used to be *	here. * *	BEWARE!!! Protocol handlers, mangling input packets, *	MUST BE last in hash buckets and checking protocol handlers *	MUST start from promiscuous ptype_all chain in net_bh. *	It is true now, do not change it.

Lines 1–500 of 10693.