diff options
Diffstat (limited to 'net')
567 files changed, 19503 insertions, 12695 deletions
diff --git a/net/802/Makefile b/net/802/Makefile index 7893d679910..a30d6e385ae 100644 --- a/net/802/Makefile +++ b/net/802/Makefile @@ -4,7 +4,6 @@ # Check the p8022 selections against net/core/Makefile. obj-$(CONFIG_LLC) += p8022.o psnap.o -obj-$(CONFIG_TR) += p8022.o psnap.o tr.o obj-$(CONFIG_NET_FC) += fc.o obj-$(CONFIG_FDDI) += fddi.o obj-$(CONFIG_HIPPI) += hippi.o diff --git a/net/802/fc.c b/net/802/fc.c index b324e31401a..05eea6b98bb 100644 --- a/net/802/fc.c +++ b/net/802/fc.c @@ -35,7 +35,7 @@ static int fc_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, - const void *daddr, const void *saddr, unsigned len) + const void *daddr, const void *saddr, unsigned int len) { struct fch_hdr *fch; int hdr_len; diff --git a/net/802/fddi.c b/net/802/fddi.c index 5ab25cd4314..9cda40661e0 100644 --- a/net/802/fddi.c +++ b/net/802/fddi.c @@ -51,7 +51,7 @@ static int fddi_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, - const void *daddr, const void *saddr, unsigned len) + const void *daddr, const void *saddr, unsigned int len) { int hl = FDDI_K_SNAP_HLEN; struct fddihdr *fddi; diff --git a/net/802/garp.c b/net/802/garp.c index 8e21b6db398..8456f5d98b8 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -157,9 +157,9 @@ static struct garp_attr *garp_attr_lookup(const struct garp_applicant *app, while (parent) { attr = rb_entry(parent, struct garp_attr, node); d = garp_attr_cmp(attr, data, len, type); - if (d < 0) + if (d > 0) parent = parent->rb_left; - else if (d > 0) + else if (d < 0) parent = parent->rb_right; else return attr; @@ -167,7 +167,8 @@ static struct garp_attr *garp_attr_lookup(const struct garp_applicant *app, return NULL; } -static void garp_attr_insert(struct garp_applicant *app, struct garp_attr *new) +static struct garp_attr *garp_attr_create(struct garp_applicant *app, + const void *data, u8 len, u8 type) { struct rb_node *parent = NULL, **p = &app->gid.rb_node; struct garp_attr *attr; @@ -176,21 +177,16 @@ static void garp_attr_insert(struct garp_applicant *app, struct garp_attr *new) while (*p) { parent = *p; attr = rb_entry(parent, struct garp_attr, node); - d = garp_attr_cmp(attr, new->data, new->dlen, new->type); - if (d < 0) + d = garp_attr_cmp(attr, data, len, type); + if (d > 0) p = &parent->rb_left; - else if (d > 0) + else if (d < 0) p = &parent->rb_right; + else { + /* The attribute already exists; re-use it. */ + return attr; + } } - rb_link_node(&new->node, parent, p); - rb_insert_color(&new->node, &app->gid); -} - -static struct garp_attr *garp_attr_create(struct garp_applicant *app, - const void *data, u8 len, u8 type) -{ - struct garp_attr *attr; - attr = kmalloc(sizeof(*attr) + len, GFP_ATOMIC); if (!attr) return attr; @@ -198,7 +194,9 @@ static struct garp_attr *garp_attr_create(struct garp_applicant *app, attr->type = type; attr->dlen = len; memcpy(attr->data, data, len); - garp_attr_insert(app, attr); + + rb_link_node(&attr->node, parent, p); + rb_insert_color(&attr->node, &app->gid); return attr; } diff --git a/net/802/hippi.c b/net/802/hippi.c index 056794e6637..51a1f530417 100644 --- a/net/802/hippi.c +++ b/net/802/hippi.c @@ -45,7 +45,7 @@ static int hippi_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, - const void *daddr, const void *saddr, unsigned len) + const void *daddr, const void *saddr, unsigned int len) { struct hippi_hdr *hip = (struct hippi_hdr *)skb_push(skb, HIPPI_HLEN); struct hippi_cb *hcb = (struct hippi_cb *) skb->cb; diff --git a/net/802/p8022.c b/net/802/p8022.c index 7f353c4f437..0bda8de7df5 100644 --- a/net/802/p8022.c +++ b/net/802/p8022.c @@ -1,6 +1,5 @@ /* - * NET3: Support for 802.2 demultiplexing off Ethernet (Token ring - * is kept separate see p8022tr.c) + * NET3: Support for 802.2 demultiplexing off Ethernet * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version diff --git a/net/802/stp.c b/net/802/stp.c index 15540b7323c..2c40ba0ec11 100644 --- a/net/802/stp.c +++ b/net/802/stp.c @@ -46,7 +46,7 @@ static int stp_pdu_rcv(struct sk_buff *skb, struct net_device *dev, proto = rcu_dereference(garp_protos[eh->h_dest[5] - GARP_ADDR_MIN]); if (proto && - compare_ether_addr(eh->h_dest, proto->group_address)) + !ether_addr_equal(eh->h_dest, proto->group_address)) goto err; } else proto = rcu_dereference(stp_proto); diff --git a/net/802/tr.c b/net/802/tr.c deleted file mode 100644 index b9a3a145e34..00000000000 --- a/net/802/tr.c +++ /dev/null @@ -1,676 +0,0 @@ -/* - * NET3: Token ring device handling subroutines - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * Fixes: 3 Feb 97 Paul Norton <pnorton@cts.com> Minor routing fixes. - * Added rif table to /proc/net/tr_rif and rif timeout to - * /proc/sys/net/token-ring/rif_timeout. - * 22 Jun 98 Paul Norton <p.norton@computer.org> Rearranged - * tr_header and tr_type_trans to handle passing IPX SNAP and - * 802.2 through the correct layers. Eliminated tr_reformat. - * - */ - -#include <asm/uaccess.h> -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/jiffies.h> -#include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/in.h> -#include <linux/inet.h> -#include <linux/netdevice.h> -#include <linux/trdevice.h> -#include <linux/skbuff.h> -#include <linux/errno.h> -#include <linux/timer.h> -#include <linux/net.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/init.h> -#include <linux/sysctl.h> -#include <linux/slab.h> -#include <net/arp.h> -#include <net/net_namespace.h> - -static void tr_add_rif_info(struct trh_hdr *trh, struct net_device *dev); -static void rif_check_expire(unsigned long dummy); - -#define TR_SR_DEBUG 0 - -/* - * Each RIF entry we learn is kept this way - */ - -struct rif_cache { - unsigned char addr[TR_ALEN]; - int iface; - __be16 rcf; - __be16 rseg[8]; - struct rif_cache *next; - unsigned long last_used; - unsigned char local_ring; -}; - -#define RIF_TABLE_SIZE 32 - -/* - * We hash the RIF cache 32 ways. We do after all have to look it - * up a lot. - */ - -static struct rif_cache *rif_table[RIF_TABLE_SIZE]; - -static DEFINE_SPINLOCK(rif_lock); - - -/* - * Garbage disposal timer. - */ - -static struct timer_list rif_timer; - -static int sysctl_tr_rif_timeout = 60*10*HZ; - -static inline unsigned long rif_hash(const unsigned char *addr) -{ - unsigned long x; - - x = addr[0]; - x = (x << 2) ^ addr[1]; - x = (x << 2) ^ addr[2]; - x = (x << 2) ^ addr[3]; - x = (x << 2) ^ addr[4]; - x = (x << 2) ^ addr[5]; - - x ^= x >> 8; - - return x & (RIF_TABLE_SIZE - 1); -} - -/* - * Put the headers on a token ring packet. Token ring source routing - * makes this a little more exciting than on ethernet. - */ - -static int tr_header(struct sk_buff *skb, struct net_device *dev, - unsigned short type, - const void *daddr, const void *saddr, unsigned len) -{ - struct trh_hdr *trh; - int hdr_len; - - /* - * Add the 802.2 SNAP header if IP as the IPv4/IPv6 code calls - * dev->hard_header directly. - */ - if (type == ETH_P_IP || type == ETH_P_IPV6 || type == ETH_P_ARP) - { - struct trllc *trllc; - - hdr_len = sizeof(struct trh_hdr) + sizeof(struct trllc); - trh = (struct trh_hdr *)skb_push(skb, hdr_len); - trllc = (struct trllc *)(trh+1); - trllc->dsap = trllc->ssap = EXTENDED_SAP; - trllc->llc = UI_CMD; - trllc->protid[0] = trllc->protid[1] = trllc->protid[2] = 0x00; - trllc->ethertype = htons(type); - } - else - { - hdr_len = sizeof(struct trh_hdr); - trh = (struct trh_hdr *)skb_push(skb, hdr_len); - } - - trh->ac=AC; - trh->fc=LLC_FRAME; - - if(saddr) - memcpy(trh->saddr,saddr,dev->addr_len); - else - memcpy(trh->saddr,dev->dev_addr,dev->addr_len); - - /* - * Build the destination and then source route the frame - */ - - if(daddr) - { - memcpy(trh->daddr,daddr,dev->addr_len); - tr_source_route(skb, trh, dev); - return hdr_len; - } - - return -hdr_len; -} - -/* - * A neighbour discovery of some species (eg arp) has completed. We - * can now send the packet. - */ - -static int tr_rebuild_header(struct sk_buff *skb) -{ - struct trh_hdr *trh=(struct trh_hdr *)skb->data; - struct trllc *trllc=(struct trllc *)(skb->data+sizeof(struct trh_hdr)); - struct net_device *dev = skb->dev; - - /* - * FIXME: We don't yet support IPv6 over token rings - */ - - if(trllc->ethertype != htons(ETH_P_IP)) { - printk("tr_rebuild_header: Don't know how to resolve type %04X addresses ?\n", ntohs(trllc->ethertype)); - return 0; - } - -#ifdef CONFIG_INET - if(arp_find(trh->daddr, skb)) { - return 1; - } - else -#endif - { - tr_source_route(skb,trh,dev); - return 0; - } -} - -/* - * Some of this is a bit hackish. We intercept RIF information - * used for source routing. We also grab IP directly and don't feed - * it via SNAP. - */ - -__be16 tr_type_trans(struct sk_buff *skb, struct net_device *dev) -{ - - struct trh_hdr *trh; - struct trllc *trllc; - unsigned riflen=0; - - skb->dev = dev; - skb_reset_mac_header(skb); - trh = tr_hdr(skb); - - if(trh->saddr[0] & TR_RII) - riflen = (ntohs(trh->rcf) & TR_RCF_LEN_MASK) >> 8; - - trllc = (struct trllc *)(skb->data+sizeof(struct trh_hdr)-TR_MAXRIFLEN+riflen); - - skb_pull(skb,sizeof(struct trh_hdr)-TR_MAXRIFLEN+riflen); - - if(*trh->daddr & 0x80) - { - if(!memcmp(trh->daddr,dev->broadcast,TR_ALEN)) - skb->pkt_type=PACKET_BROADCAST; - else - skb->pkt_type=PACKET_MULTICAST; - } - else if ( (trh->daddr[0] & 0x01) && (trh->daddr[1] & 0x00) && (trh->daddr[2] & 0x5E)) - { - skb->pkt_type=PACKET_MULTICAST; - } - else if(dev->flags & IFF_PROMISC) - { - if(memcmp(trh->daddr, dev->dev_addr, TR_ALEN)) - skb->pkt_type=PACKET_OTHERHOST; - } - - if ((skb->pkt_type != PACKET_BROADCAST) && - (skb->pkt_type != PACKET_MULTICAST)) - tr_add_rif_info(trh,dev) ; - - /* - * Strip the SNAP header from ARP packets since we don't - * pass them through to the 802.2/SNAP layers. - */ - - if (trllc->dsap == EXTENDED_SAP && - (trllc->ethertype == htons(ETH_P_IP) || - trllc->ethertype == htons(ETH_P_IPV6) || - trllc->ethertype == htons(ETH_P_ARP))) - { - skb_pull(skb, sizeof(struct trllc)); - return trllc->ethertype; - } - - return htons(ETH_P_TR_802_2); -} - -/* - * We try to do source routing... - */ - -void tr_source_route(struct sk_buff *skb,struct trh_hdr *trh, - struct net_device *dev) -{ - int slack; - unsigned int hash; - struct rif_cache *entry; - unsigned char *olddata; - unsigned long flags; - static const unsigned char mcast_func_addr[] - = {0xC0,0x00,0x00,0x04,0x00,0x00}; - - spin_lock_irqsave(&rif_lock, flags); - - /* - * Broadcasts are single route as stated in RFC 1042 - */ - if( (!memcmp(&(trh->daddr[0]),&(dev->broadcast[0]),TR_ALEN)) || - (!memcmp(&(trh->daddr[0]),&(mcast_func_addr[0]), TR_ALEN)) ) - { - trh->rcf=htons((((sizeof(trh->rcf)) << 8) & TR_RCF_LEN_MASK) - | TR_RCF_FRAME2K | TR_RCF_LIMITED_BROADCAST); - trh->saddr[0]|=TR_RII; - } - else - { - hash = rif_hash(trh->daddr); - /* - * Walk the hash table and look for an entry - */ - for(entry=rif_table[hash];entry && memcmp(&(entry->addr[0]),&(trh->daddr[0]),TR_ALEN);entry=entry->next); - - /* - * If we found an entry we can route the frame. - */ - if(entry) - { -#if TR_SR_DEBUG -printk("source routing for %pM\n", trh->daddr); -#endif - if(!entry->local_ring && (ntohs(entry->rcf) & TR_RCF_LEN_MASK) >> 8) - { - trh->rcf=entry->rcf; - memcpy(&trh->rseg[0],&entry->rseg[0],8*sizeof(unsigned short)); - trh->rcf^=htons(TR_RCF_DIR_BIT); - trh->rcf&=htons(0x1fff); /* Issam Chehab <ichehab@madge1.demon.co.uk> */ - - trh->saddr[0]|=TR_RII; -#if TR_SR_DEBUG - printk("entry found with rcf %04x\n", entry->rcf); - } - else - { - printk("entry found but without rcf length, local=%02x\n", entry->local_ring); -#endif - } - entry->last_used=jiffies; - } - else - { - /* - * Without the information we simply have to shout - * on the wire. The replies should rapidly clean this - * situation up. - */ - trh->rcf=htons((((sizeof(trh->rcf)) << 8) & TR_RCF_LEN_MASK) - | TR_RCF_FRAME2K | TR_RCF_LIMITED_BROADCAST); - trh->saddr[0]|=TR_RII; -#if TR_SR_DEBUG - printk("no entry in rif table found - broadcasting frame\n"); -#endif - } - } - - /* Compress the RIF here so we don't have to do it in the driver(s) */ - if (!(trh->saddr[0] & 0x80)) - slack = 18; - else - slack = 18 - ((ntohs(trh->rcf) & TR_RCF_LEN_MASK)>>8); - olddata = skb->data; - spin_unlock_irqrestore(&rif_lock, flags); - - skb_pull(skb, slack); - memmove(skb->data, olddata, sizeof(struct trh_hdr) - slack); -} - -/* - * We have learned some new RIF information for our source - * routing. - */ - -static void tr_add_rif_info(struct trh_hdr *trh, struct net_device *dev) -{ - unsigned int hash, rii_p = 0; - unsigned long flags; - struct rif_cache *entry; - unsigned char saddr0; - - spin_lock_irqsave(&rif_lock, flags); - saddr0 = trh->saddr[0]; - - /* - * Firstly see if the entry exists - */ - - if(trh->saddr[0] & TR_RII) - { - trh->saddr[0]&=0x7f; - if (((ntohs(trh->rcf) & TR_RCF_LEN_MASK) >> 8) > 2) - { - rii_p = 1; - } - } - - hash = rif_hash(trh->saddr); - for(entry=rif_table[hash];entry && memcmp(&(entry->addr[0]),&(trh->saddr[0]),TR_ALEN);entry=entry->next); - - if(entry==NULL) - { -#if TR_SR_DEBUG - printk("adding rif_entry: addr:%pM rcf:%04X\n", - trh->saddr, ntohs(trh->rcf)); -#endif - /* - * Allocate our new entry. A failure to allocate loses - * use the information. This is harmless. - * - * FIXME: We ought to keep some kind of cache size - * limiting and adjust the timers to suit. - */ - entry=kmalloc(sizeof(struct rif_cache),GFP_ATOMIC); - - if(!entry) - { - printk(KERN_DEBUG "tr.c: Couldn't malloc rif cache entry !\n"); - spin_unlock_irqrestore(&rif_lock, flags); - return; - } - - memcpy(&(entry->addr[0]),&(trh->saddr[0]),TR_ALEN); - entry->iface = dev->ifindex; - entry->next=rif_table[hash]; - entry->last_used=jiffies; - rif_table[hash]=entry; - - if (rii_p) - { - entry->rcf = trh->rcf & htons((unsigned short)~TR_RCF_BROADCAST_MASK); - memcpy(&(entry->rseg[0]),&(trh->rseg[0]),8*sizeof(unsigned short)); - entry->local_ring = 0; - } - else - { - entry->local_ring = 1; - } - } - else /* Y. Tahara added */ - { - /* - * Update existing entries - */ - if (!entry->local_ring) - if (entry->rcf != (trh->rcf & htons((unsigned short)~TR_RCF_BROADCAST_MASK)) && - !(trh->rcf & htons(TR_RCF_BROADCAST_MASK))) - { -#if TR_SR_DEBUG -printk("updating rif_entry: addr:%pM rcf:%04X\n", - trh->saddr, ntohs(trh->rcf)); -#endif - entry->rcf = trh->rcf & htons((unsigned short)~TR_RCF_BROADCAST_MASK); - memcpy(&(entry->rseg[0]),&(trh->rseg[0]),8*sizeof(unsigned short)); - } - entry->last_used=jiffies; - } - trh->saddr[0]=saddr0; /* put the routing indicator back for tcpdump */ - spin_unlock_irqrestore(&rif_lock, flags); -} - -/* - * Scan the cache with a timer and see what we need to throw out. - */ - -static void rif_check_expire(unsigned long dummy) -{ - int i; - unsigned long flags, next_interval = jiffies + sysctl_tr_rif_timeout/2; - - spin_lock_irqsave(&rif_lock, flags); - - for(i =0; i < RIF_TABLE_SIZE; i++) { - struct rif_cache *entry, **pentry; - - pentry = rif_table+i; - while((entry=*pentry) != NULL) { - unsigned long expires - = entry->last_used + sysctl_tr_rif_timeout; - - if (time_before_eq(expires, jiffies)) { - *pentry = entry->next; - kfree(entry); - } else { - pentry = &entry->next; - - if (time_before(expires, next_interval)) - next_interval = expires; - } - } - } - - spin_unlock_irqrestore(&rif_lock, flags); - - mod_timer(&rif_timer, next_interval); - -} - -/* - * Generate the /proc/net information for the token ring RIF - * routing. - */ - -#ifdef CONFIG_PROC_FS - -static struct rif_cache *rif_get_idx(loff_t pos) -{ - int i; - struct rif_cache *entry; - loff_t off = 0; - - for(i = 0; i < RIF_TABLE_SIZE; i++) - for(entry = rif_table[i]; entry; entry = entry->next) { - if (off == pos) - return entry; - ++off; - } - - return NULL; -} - -static void *rif_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(&rif_lock) -{ - spin_lock_irq(&rif_lock); - - return *pos ? rif_get_idx(*pos - 1) : SEQ_START_TOKEN; -} - -static void *rif_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - int i; - struct rif_cache *ent = v; - - ++*pos; - - if (v == SEQ_START_TOKEN) { - i = -1; - goto scan; - } - - if (ent->next) - return ent->next; - - i = rif_hash(ent->addr); - scan: - while (++i < RIF_TABLE_SIZE) { - if ((ent = rif_table[i]) != NULL) - return ent; - } - return NULL; -} - -static void rif_seq_stop(struct seq_file *seq, void *v) - __releases(&rif_lock) -{ - spin_unlock_irq(&rif_lock); -} - -static int rif_seq_show(struct seq_file *seq, void *v) -{ - int j, rcf_len, segment, brdgnmb; - struct rif_cache *entry = v; - - if (v == SEQ_START_TOKEN) - seq_puts(seq, - "if TR address TTL rcf routing segments\n"); - else { - struct net_device *dev = dev_get_by_index(&init_net, entry->iface); - long ttl = (long) (entry->last_used + sysctl_tr_rif_timeout) - - (long) jiffies; - - seq_printf(seq, "%s %pM %7li ", - dev?dev->name:"?", - entry->addr, - ttl/HZ); - - if (entry->local_ring) - seq_puts(seq, "local\n"); - else { - - seq_printf(seq, "%04X", ntohs(entry->rcf)); - rcf_len = ((ntohs(entry->rcf) & TR_RCF_LEN_MASK)>>8)-2; - if (rcf_len) - rcf_len >>= 1; - for(j = 1; j < rcf_len; j++) { - if(j==1) { - segment=ntohs(entry->rseg[j-1])>>4; - seq_printf(seq," %03X",segment); - } - - segment=ntohs(entry->rseg[j])>>4; - brdgnmb=ntohs(entry->rseg[j-1])&0x00f; - seq_printf(seq,"-%01X-%03X",brdgnmb,segment); - } - seq_putc(seq, '\n'); - } - - if (dev) - dev_put(dev); - } - return 0; -} - - -static const struct seq_operations rif_seq_ops = { - .start = rif_seq_start, - .next = rif_seq_next, - .stop = rif_seq_stop, - .show = rif_seq_show, -}; - -static int rif_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &rif_seq_ops); -} - -static const struct file_operations rif_seq_fops = { - .owner = THIS_MODULE, - .open = rif_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -#endif - -static const struct header_ops tr_header_ops = { - .create = tr_header, - .rebuild= tr_rebuild_header, -}; - -static void tr_setup(struct net_device *dev) -{ - /* - * Configure and register - */ - - dev->header_ops = &tr_header_ops; - - dev->type = ARPHRD_IEEE802_TR; - dev->hard_header_len = TR_HLEN; - dev->mtu = 2000; - dev->addr_len = TR_ALEN; - dev->tx_queue_len = 100; /* Long queues on tr */ - - memset(dev->broadcast,0xFF, TR_ALEN); - - /* New-style flags. */ - dev->flags = IFF_BROADCAST | IFF_MULTICAST ; -} - -/** - * alloc_trdev - Register token ring device - * @sizeof_priv: Size of additional driver-private structure to be allocated - * for this token ring device - * - * Fill in the fields of the device structure with token ring-generic values. - * - * Constructs a new net device, complete with a private data area of - * size @sizeof_priv. A 32-byte (not bit) alignment is enforced for - * this private data area. - */ -struct net_device *alloc_trdev(int sizeof_priv) -{ - return alloc_netdev(sizeof_priv, "tr%d", tr_setup); -} - -#ifdef CONFIG_SYSCTL -static struct ctl_table tr_table[] = { - { - .procname = "rif_timeout", - .data = &sysctl_tr_rif_timeout, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { }, -}; - -static __initdata struct ctl_path tr_path[] = { - { .procname = "net", }, - { .procname = "token-ring", }, - { } -}; -#endif - -/* - * Called during bootup. We don't actually have to initialise - * too much for this. - */ - -static int __init rif_init(void) -{ - rif_timer.expires = jiffies + sysctl_tr_rif_timeout; - setup_timer(&rif_timer, rif_check_expire, 0); - add_timer(&rif_timer); -#ifdef CONFIG_SYSCTL - register_sysctl_paths(tr_path, tr_table); -#endif - proc_net_fops_create(&init_net, "tr_rif", S_IRUGO, &rif_seq_fops); - return 0; -} - -module_init(rif_init); - -EXPORT_SYMBOL(tr_type_trans); -EXPORT_SYMBOL(alloc_trdev); - -MODULE_LICENSE("GPL"); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index efea35b02e7..6089f0cf23b 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -266,19 +266,19 @@ static void vlan_sync_address(struct net_device *dev, struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); /* May be called without an actual change */ - if (!compare_ether_addr(vlan->real_dev_addr, dev->dev_addr)) + if (ether_addr_equal(vlan->real_dev_addr, dev->dev_addr)) return; /* vlan address was different from the old address and is equal to * the new address */ - if (compare_ether_addr(vlandev->dev_addr, vlan->real_dev_addr) && - !compare_ether_addr(vlandev->dev_addr, dev->dev_addr)) + if (!ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) && + ether_addr_equal(vlandev->dev_addr, dev->dev_addr)) dev_uc_del(dev, vlandev->dev_addr); /* vlan address was equal to the old address and is different from * the new address */ - if (!compare_ether_addr(vlandev->dev_addr, vlan->real_dev_addr) && - compare_ether_addr(vlandev->dev_addr, dev->dev_addr)) + if (ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) && + !ether_addr_equal(vlandev->dev_addr, dev->dev_addr)) dev_uc_add(dev, vlandev->dev_addr); memcpy(vlan->real_dev_addr, dev->dev_addr, ETH_ALEN); diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 4d39d802be2..8ca533c95de 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -31,8 +31,7 @@ bool vlan_do_receive(struct sk_buff **skbp, bool last_handler) /* Our lower layer thinks this is not local, let's make sure. * This allows the VLAN to have a different MAC than the * underlying device, and still route correctly. */ - if (!compare_ether_addr(eth_hdr(skb)->h_dest, - vlan_dev->dev_addr)) + if (ether_addr_equal(eth_hdr(skb)->h_dest, vlan_dev->dev_addr)) skb->pkt_type = PACKET_HOST; } diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 9988d4abb37..da1bc9c3cf3 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -157,7 +157,7 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, skb = __vlan_hwaccel_put_tag(skb, vlan_tci); } - skb_set_dev(skb, vlan_dev_priv(dev)->real_dev); + skb->dev = vlan_dev_priv(dev)->real_dev; len = skb->len; if (netpoll_tx_running(dev)) return skb->dev->netdev_ops->ndo_start_xmit(skb, skb->dev); @@ -277,7 +277,7 @@ static int vlan_dev_open(struct net_device *dev) !(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) return -ENETDOWN; - if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr)) { + if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr)) { err = dev_uc_add(real_dev, dev->dev_addr); if (err < 0) goto out; @@ -307,7 +307,7 @@ clear_allmulti: if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(real_dev, -1); del_unicast: - if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr)) + if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr)) dev_uc_del(real_dev, dev->dev_addr); out: netif_carrier_off(dev); @@ -326,7 +326,7 @@ static int vlan_dev_stop(struct net_device *dev) if (dev->flags & IFF_PROMISC) dev_set_promiscuity(real_dev, -1); - if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr)) + if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr)) dev_uc_del(real_dev, dev->dev_addr); netif_carrier_off(dev); @@ -345,13 +345,13 @@ static int vlan_dev_set_mac_address(struct net_device *dev, void *p) if (!(dev->flags & IFF_UP)) goto out; - if (compare_ether_addr(addr->sa_data, real_dev->dev_addr)) { + if (!ether_addr_equal(addr->sa_data, real_dev->dev_addr)) { err = dev_uc_add(real_dev, addr->sa_data); if (err < 0) return err; } - if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr)) + if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr)) dev_uc_del(real_dev, dev->dev_addr); out: diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 50711368ad6..708c80ea187 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -166,11 +166,13 @@ static int vlan_fill_info(struct sk_buff *skb, const struct net_device *dev) struct nlattr *nest; unsigned int i; - NLA_PUT_U16(skb, IFLA_VLAN_ID, vlan_dev_priv(dev)->vlan_id); + if (nla_put_u16(skb, IFLA_VLAN_ID, vlan_dev_priv(dev)->vlan_id)) + goto nla_put_failure; if (vlan->flags) { f.flags = vlan->flags; f.mask = ~0; - NLA_PUT(skb, IFLA_VLAN_FLAGS, sizeof(f), &f); + if (nla_put(skb, IFLA_VLAN_FLAGS, sizeof(f), &f)) + goto nla_put_failure; } if (vlan->nr_ingress_mappings) { nest = nla_nest_start(skb, IFLA_VLAN_INGRESS_QOS); @@ -183,8 +185,9 @@ static int vlan_fill_info(struct sk_buff *skb, const struct net_device *dev) m.from = i; m.to = vlan->ingress_priority_map[i]; - NLA_PUT(skb, IFLA_VLAN_QOS_MAPPING, - sizeof(m), &m); + if (nla_put(skb, IFLA_VLAN_QOS_MAPPING, + sizeof(m), &m)) + goto nla_put_failure; } nla_nest_end(skb, nest); } @@ -202,8 +205,9 @@ static int vlan_fill_info(struct sk_buff *skb, const struct net_device *dev) m.from = pm->priority; m.to = (pm->vlan_qos >> 13) & 0x7; - NLA_PUT(skb, IFLA_VLAN_QOS_MAPPING, - sizeof(m), &m); + if (nla_put(skb, IFLA_VLAN_QOS_MAPPING, + sizeof(m), &m)) + goto nla_put_failure; } } nla_nest_end(skb, nest); diff --git a/net/9p/client.c b/net/9p/client.c index b23a17c431c..a170893d70e 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -1530,7 +1530,7 @@ p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset, p9_debug(P9_DEBUG_9P, ">>> TREAD fid %d offset %llu %d\n", - fid->fid, (long long unsigned) offset, count); + fid->fid, (unsigned long long) offset, count); err = 0; clnt = fid->clnt; @@ -1605,7 +1605,7 @@ p9_client_write(struct p9_fid *fid, char *data, const char __user *udata, struct p9_req_t *req; p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %d\n", - fid->fid, (long long unsigned) offset, count); + fid->fid, (unsigned long long) offset, count); err = 0; clnt = fid->clnt; @@ -2040,7 +2040,7 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) char *dataptr; p9_debug(P9_DEBUG_9P, ">>> TREADDIR fid %d offset %llu count %d\n", - fid->fid, (long long unsigned) offset, count); + fid->fid, (unsigned long long) offset, count); err = 0; clnt = fid->clnt; diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index fccae26fa67..6449bae1570 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -513,7 +513,7 @@ error: clear_bit(Wworksched, &m->wsched); } -static int p9_pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key) +static int p9_pollwake(wait_queue_t *wait, unsigned int mode, int sync, void *key) { struct p9_poll_wait *pwait = container_of(wait, struct p9_poll_wait, wait); diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 3d432068f62..5af18d11b51 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -615,7 +615,8 @@ static void p9_virtio_remove(struct virtio_device *vdev) { struct virtio_chan *chan = vdev->priv; - BUG_ON(chan->inuse); + if (chan->inuse) + p9_virtio_close(chan->client); vdev->config->del_vqs(vdev); mutex_lock(&virtio_9p_lock); diff --git a/net/Kconfig b/net/Kconfig index e07272d0bb2..245831bec09 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -207,10 +207,10 @@ source "net/ipx/Kconfig" source "drivers/net/appletalk/Kconfig" source "net/x25/Kconfig" source "net/lapb/Kconfig" -source "net/econet/Kconfig" source "net/wanrouter/Kconfig" source "net/phonet/Kconfig" source "net/ieee802154/Kconfig" +source "net/mac802154/Kconfig" source "net/sched/Kconfig" source "net/dcb/Kconfig" source "net/dns_resolver/Kconfig" @@ -246,9 +246,6 @@ config BQL select DQL default y -config HAVE_BPF_JIT - bool - config BPF_JIT bool "enable BPF Just In Time compiler" depends on HAVE_BPF_JIT @@ -295,7 +292,7 @@ config NET_TCPPROBE module will be called tcp_probe. config NET_DROP_MONITOR - boolean "Network packet drop alerting service" + tristate "Network packet drop alerting service" depends on INET && EXPERIMENTAL && TRACEPOINTS ---help--- This feature provides an alerting service to userspace in the @@ -340,3 +337,7 @@ source "net/nfc/Kconfig" endif # if NET + +# Used by archs to tell that they support BPF_JIT +config HAVE_BPF_JIT + bool diff --git a/net/Makefile b/net/Makefile index ad432fa4d93..4f4ee083064 100644 --- a/net/Makefile +++ b/net/Makefile @@ -40,7 +40,6 @@ obj-$(CONFIG_AF_RXRPC) += rxrpc/ obj-$(CONFIG_ATM) += atm/ obj-$(CONFIG_L2TP) += l2tp/ obj-$(CONFIG_DECNET) += decnet/ -obj-$(CONFIG_ECONET) += econet/ obj-$(CONFIG_PHONET) += phonet/ ifneq ($(CONFIG_VLAN_8021Q),) obj-y += 8021q/ @@ -60,6 +59,7 @@ ifneq ($(CONFIG_DCB),) obj-y += dcb/ endif obj-$(CONFIG_IEEE802154) += ieee802154/ +obj-$(CONFIG_MAC802154) += mac802154/ ifeq ($(CONFIG_NET),y) obj-$(CONFIG_SYSCTL) += sysctl_net.o diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index bfa9ab93eda..0301b328cf0 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -63,7 +63,7 @@ #include <net/tcp_states.h> #include <net/route.h> #include <linux/atalk.h> -#include "../core/kmap_skb.h" +#include <linux/highmem.h> struct datalink_proto *ddp_dl, *aarp_dl; static const struct proto_ops atalk_dgram_ops; @@ -960,10 +960,10 @@ static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset, if (copy > len) copy = len; - vaddr = kmap_skb_frag(frag); + vaddr = kmap_atomic(skb_frag_page(frag)); sum = atalk_sum_partial(vaddr + frag->page_offset + offset - start, copy, sum); - kunmap_skb_frag(vaddr); + kunmap_atomic(vaddr); if (!(len -= copy)) return sum; diff --git a/net/appletalk/sysctl_net_atalk.c b/net/appletalk/sysctl_net_atalk.c index 04e9c0da7aa..ebb864361f7 100644 --- a/net/appletalk/sysctl_net_atalk.c +++ b/net/appletalk/sysctl_net_atalk.c @@ -42,20 +42,14 @@ static struct ctl_table atalk_table[] = { { }, }; -static struct ctl_path atalk_path[] = { - { .procname = "net", }, - { .procname = "appletalk", }, - { } -}; - static struct ctl_table_header *atalk_table_header; void atalk_register_sysctl(void) { - atalk_table_header = register_sysctl_paths(atalk_path, atalk_table); + atalk_table_header = register_net_sysctl(&init_net, "net/appletalk", atalk_table); } void atalk_unregister_sysctl(void) { - unregister_sysctl_table(atalk_table_header); + unregister_net_sysctl_table(atalk_table_header); } diff --git a/net/atm/br2684.c b/net/atm/br2684.c index 353fccf1cde..4819d31533e 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -73,7 +73,7 @@ struct br2684_vcc { #ifdef CONFIG_ATM_BR2684_IPFILTER struct br2684_filter filter; #endif /* CONFIG_ATM_BR2684_IPFILTER */ - unsigned copies_needed, copies_failed; + unsigned int copies_needed, copies_failed; }; struct br2684_dev { diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c index 62dc8bfe6fe..bbd3b639992 100644 --- a/net/atm/ioctl.c +++ b/net/atm/ioctl.c @@ -97,9 +97,8 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd, error = sock_get_timestampns(sk, argp); goto done; case ATM_SETSC: - if (net_ratelimit()) - pr_warning("ATM_SETSC is obsolete; used by %s:%d\n", - current->comm, task_pid_nr(current)); + net_warn_ratelimited("ATM_SETSC is obsolete; used by %s:%d\n", + current->comm, task_pid_nr(current)); error = 0; goto done; case ATMSIGD_CTRL: @@ -123,8 +122,7 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd, work for 32-bit userspace. TBH I don't really want to think about it at all. dwmw2. */ if (compat) { - if (net_ratelimit()) - pr_warning("32-bit task cannot be atmsigd\n"); + net_warn_ratelimited("32-bit task cannot be atmsigd\n"); error = -EINVAL; goto done; } diff --git a/net/atm/lec.c b/net/atm/lec.c index f1964caa0f8..a7d172105c9 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -26,11 +26,6 @@ #include <linux/spinlock.h> #include <linux/seq_file.h> -/* TokenRing if needed */ -#ifdef CONFIG_TR -#include <linux/trdevice.h> -#endif - /* And atm device */ #include <linux/atmdev.h> #include <linux/atmlec.h> @@ -163,50 +158,6 @@ static void lec_handle_bridge(struct sk_buff *skb, struct net_device *dev) #endif /* defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) */ /* - * Modelled after tr_type_trans - * All multicast and ARE or STE frames go to BUS. - * Non source routed frames go by destination address. - * Last hop source routed frames go by destination address. - * Not last hop source routed frames go by _next_ route descriptor. - * Returns pointer to destination MAC address or fills in rdesc - * and returns NULL. - */ -#ifdef CONFIG_TR -static unsigned char *get_tr_dst(unsigned char *packet, unsigned char *rdesc) -{ - struct trh_hdr *trh; - unsigned int riflen, num_rdsc; - - trh = (struct trh_hdr *)packet; - if (trh->daddr[0] & (uint8_t) 0x80) - return bus_mac; /* multicast */ - - if (trh->saddr[0] & TR_RII) { - riflen = (ntohs(trh->rcf) & TR_RCF_LEN_MASK) >> 8; - if ((ntohs(trh->rcf) >> 13) != 0) - return bus_mac; /* ARE or STE */ - } else - return trh->daddr; /* not source routed */ - - if (riflen < 6) - return trh->daddr; /* last hop, source routed */ - - /* riflen is 6 or more, packet has more than one route descriptor */ - num_rdsc = (riflen / 2) - 1; - memset(rdesc, 0, ETH_ALEN); - /* offset 4 comes from LAN destination field in LE control frames */ - if (trh->rcf & htons((uint16_t) TR_RCF_DIR_BIT)) - memcpy(&rdesc[4], &trh->rseg[num_rdsc - 2], sizeof(__be16)); - else { - memcpy(&rdesc[4], &trh->rseg[1], sizeof(__be16)); - rdesc[5] = ((ntohs(trh->rseg[0]) & 0x000f) | (rdesc[5] & 0xf0)); - } - - return NULL; -} -#endif /* CONFIG_TR */ - -/* * Open/initialize the netdevice. This is called (in the current kernel) * sometime after booting when the 'ifconfig' program is run. * @@ -257,9 +208,6 @@ static netdev_tx_t lec_start_xmit(struct sk_buff *skb, struct lec_arp_table *entry; unsigned char *dst; int min_frame_size; -#ifdef CONFIG_TR - unsigned char rdesc[ETH_ALEN]; /* Token Ring route descriptor */ -#endif int is_rdesc; pr_debug("called\n"); @@ -290,24 +238,10 @@ static netdev_tx_t lec_start_xmit(struct sk_buff *skb, } skb_push(skb, 2); - /* Put le header to place, works for TokenRing too */ + /* Put le header to place */ lec_h = (struct lecdatahdr_8023 *)skb->data; lec_h->le_header = htons(priv->lecid); -#ifdef CONFIG_TR - /* - * Ugly. Use this to realign Token Ring packets for - * e.g. PCA-200E driver. - */ - if (priv->is_trdev) { - skb2 = skb_realloc_headroom(skb, LEC_HEADER_LEN); - kfree_skb(skb); - if (skb2 == NULL) - return NETDEV_TX_OK; - skb = skb2; - } -#endif - #if DUMP_PACKETS >= 2 #define MAX_DUMP_SKB 99 #elif DUMP_PACKETS >= 1 @@ -321,12 +255,7 @@ static netdev_tx_t lec_start_xmit(struct sk_buff *skb, #endif /* DUMP_PACKETS >= 1 */ /* Minimum ethernet-frame size */ -#ifdef CONFIG_TR - if (priv->is_trdev) - min_frame_size = LEC_MINIMUM_8025_SIZE; - else -#endif - min_frame_size = LEC_MINIMUM_8023_SIZE; + min_frame_size = LEC_MINIMUM_8023_SIZE; if (skb->len < min_frame_size) { if ((skb->len + skb_tailroom(skb)) < min_frame_size) { skb2 = skb_copy_expand(skb, 0, @@ -345,15 +274,6 @@ static netdev_tx_t lec_start_xmit(struct sk_buff *skb, /* Send to right vcc */ is_rdesc = 0; dst = lec_h->h_dest; -#ifdef CONFIG_TR - if (priv->is_trdev) { - dst = get_tr_dst(skb->data + 2, rdesc); - if (dst == NULL) { - dst = rdesc; - is_rdesc = 1; - } - } -#endif entry = NULL; vcc = lec_arp_resolve(priv, dst, is_rdesc, &entry); pr_debug("%s:vcc:%p vcc_flags:%lx, entry:%p\n", @@ -710,12 +630,7 @@ static void lec_push(struct atm_vcc *vcc, struct sk_buff *skb) dev_kfree_skb(skb); return; } -#ifdef CONFIG_TR - if (priv->is_trdev) - dst = ((struct lecdatahdr_8025 *)skb->data)->h_dest; - else -#endif - dst = ((struct lecdatahdr_8023 *)skb->data)->h_dest; + dst = ((struct lecdatahdr_8023 *)skb->data)->h_dest; /* * If this is a Data Direct VCC, and the VCC does not match @@ -723,16 +638,7 @@ static void lec_push(struct atm_vcc *vcc, struct sk_buff *skb) */ spin_lock_irqsave(&priv->lec_arp_lock, flags); if (lec_is_data_direct(vcc)) { -#ifdef CONFIG_TR - if (priv->is_trdev) - src = - ((struct lecdatahdr_8025 *)skb->data)-> - h_source; - else -#endif - src = - ((struct lecdatahdr_8023 *)skb->data)-> - h_source; + src = ((struct lecdatahdr_8023 *)skb->data)->h_source; entry = lec_arp_find(priv, src); if (entry && entry->vcc != vcc) { lec_arp_remove(priv, entry); @@ -750,12 +656,7 @@ static void lec_push(struct atm_vcc *vcc, struct sk_buff *skb) if (!hlist_empty(&priv->lec_arp_empty_ones)) lec_arp_check_empties(priv, vcc, skb); skb_pull(skb, 2); /* skip lec_id */ -#ifdef CONFIG_TR - if (priv->is_trdev) - skb->protocol = tr_type_trans(skb, dev); - else -#endif - skb->protocol = eth_type_trans(skb, dev); + skb->protocol = eth_type_trans(skb, dev); dev->stats.rx_packets++; dev->stats.rx_bytes += skb->len; memset(ATM_SKB(skb), 0, sizeof(struct atm_skb_data)); @@ -827,27 +728,13 @@ static int lecd_attach(struct atm_vcc *vcc, int arg) i = 0; else i = arg; -#ifdef CONFIG_TR if (arg >= MAX_LEC_ITF) return -EINVAL; -#else /* Reserve the top NUM_TR_DEVS for TR */ - if (arg >= (MAX_LEC_ITF - NUM_TR_DEVS)) - return -EINVAL; -#endif if (!dev_lec[i]) { - int is_trdev, size; - - is_trdev = 0; - if (i >= (MAX_LEC_ITF - NUM_TR_DEVS)) - is_trdev = 1; + int size; size = sizeof(struct lec_priv); -#ifdef CONFIG_TR - if (is_trdev) - dev_lec[i] = alloc_trdev(size); - else -#endif - dev_lec[i] = alloc_etherdev(size); + dev_lec[i] = alloc_etherdev(size); if (!dev_lec[i]) return -ENOMEM; dev_lec[i]->netdev_ops = &lec_netdev_ops; @@ -858,7 +745,6 @@ static int lecd_attach(struct atm_vcc *vcc, int arg) } priv = netdev_priv(dev_lec[i]); - priv->is_trdev = is_trdev; } else { priv = netdev_priv(dev_lec[i]); if (priv->lecd) @@ -1255,7 +1141,7 @@ static int lane2_associate_req(struct net_device *dev, const u8 *lan_dst, struct sk_buff *skb; struct lec_priv *priv = netdev_priv(dev); - if (compare_ether_addr(lan_dst, dev->dev_addr)) + if (!ether_addr_equal(lan_dst, dev->dev_addr)) return 0; /* not our mac address */ kfree(priv->tlvs); /* NULL if there was no previous association */ @@ -1662,7 +1548,7 @@ static struct lec_arp_table *lec_arp_find(struct lec_priv *priv, head = &priv->lec_arp_tables[HASH(mac_addr[ETH_ALEN - 1])]; hlist_for_each_entry(entry, node, head, next) { - if (!compare_ether_addr(mac_addr, entry->mac_addr)) + if (ether_addr_equal(mac_addr, entry->mac_addr)) return entry; } return NULL; @@ -1849,7 +1735,7 @@ static struct atm_vcc *lec_arp_resolve(struct lec_priv *priv, case 1: return priv->mcast_vcc; case 2: /* LANE2 wants arp for multicast addresses */ - if (!compare_ether_addr(mac_to_find, bus_mac)) + if (ether_addr_equal(mac_to_find, bus_mac)) return priv->mcast_vcc; break; default: @@ -2372,15 +2258,7 @@ lec_arp_check_empties(struct lec_priv *priv, struct hlist_node *node, *next; struct lec_arp_table *entry, *tmp; struct lecdatahdr_8023 *hdr = (struct lecdatahdr_8023 *)skb->data; - unsigned char *src; -#ifdef CONFIG_TR - struct lecdatahdr_8025 *tr_hdr = (struct lecdatahdr_8025 *)skb->data; - - if (priv->is_trdev) - src = tr_hdr->h_source; - else -#endif - src = hdr->h_source; + unsigned char *src = hdr->h_source; spin_lock_irqsave(&priv->lec_arp_lock, flags); hlist_for_each_entry_safe(entry, node, next, diff --git a/net/atm/lec.h b/net/atm/lec.h index dfc07196646..c730e57de19 100644 --- a/net/atm/lec.h +++ b/net/atm/lec.h @@ -142,7 +142,6 @@ struct lec_priv { int itfnum; /* e.g. 2 for lec2, 5 for lec5 */ struct lane2_ops *lane2_ops; /* can be NULL for LANE v1 */ int is_proxy; /* bridge between ATM and Ethernet */ - int is_trdev; /* Device type, 0 = Ethernet, 1 = TokenRing */ }; struct lec_vcc_priv { diff --git a/net/atm/mpc.c b/net/atm/mpc.c index aa972409f09..d4cc1be5c36 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -592,8 +592,7 @@ static netdev_tx_t mpc_send_packet(struct sk_buff *skb, goto non_ip; while (i < mpc->number_of_mps_macs) { - if (!compare_ether_addr(eth->h_dest, - (mpc->mps_macs + i*ETH_ALEN))) + if (ether_addr_equal(eth->h_dest, mpc->mps_macs + i * ETH_ALEN)) if (send_via_shortcut(skb, mpc) == 0) /* try shortcut */ return NETDEV_TX_OK; i++; diff --git a/net/atm/mpoa_proc.c b/net/atm/mpoa_proc.c index 53e50029227..5bdd300db0f 100644 --- a/net/atm/mpoa_proc.c +++ b/net/atm/mpoa_proc.c @@ -207,7 +207,7 @@ static ssize_t proc_mpc_write(struct file *file, const char __user *buff, size_t nbytes, loff_t *ppos) { char *page, *p; - unsigned len; + unsigned int len; if (nbytes == 0) return 0; diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c index 614d3fc47ed..ce1e59fdae7 100644 --- a/net/atm/pppoatm.c +++ b/net/atm/pppoatm.c @@ -62,12 +62,25 @@ struct pppoatm_vcc { void (*old_pop)(struct atm_vcc *, struct sk_buff *); /* keep old push/pop for detaching */ enum pppoatm_encaps encaps; + atomic_t inflight; + unsigned long blocked; int flags; /* SC_COMP_PROT - compress protocol */ struct ppp_channel chan; /* interface to generic ppp layer */ struct tasklet_struct wakeup_tasklet; }; /* + * We want to allow two packets in the queue. The one that's currently in + * flight, and *one* queued up ready for the ATM device to send immediately + * from its TX done IRQ. We want to be able to use atomic_inc_not_zero(), so + * inflight == -2 represents an empty queue, -1 one packet, and zero means + * there are two packets in the queue. + */ +#define NONE_INFLIGHT -2 + +#define BLOCKED 0 + +/* * Header used for LLC Encapsulated PPP (4 bytes) followed by the LCP protocol * ID (0xC021) used in autodetection */ @@ -102,16 +115,30 @@ static void pppoatm_wakeup_sender(unsigned long arg) static void pppoatm_pop(struct atm_vcc *atmvcc, struct sk_buff *skb) { struct pppoatm_vcc *pvcc = atmvcc_to_pvcc(atmvcc); + pvcc->old_pop(atmvcc, skb); + atomic_dec(&pvcc->inflight); + /* - * We don't really always want to do this since it's - * really inefficient - it would be much better if we could - * test if we had actually throttled the generic layer. - * Unfortunately then there would be a nasty SMP race where - * we could clear that flag just as we refuse another packet. - * For now we do the safe thing. + * We always used to run the wakeup tasklet unconditionally here, for + * fear of race conditions where we clear the BLOCKED flag just as we + * refuse another packet in pppoatm_send(). This was quite inefficient. + * + * In fact it's OK. The PPP core will only ever call pppoatm_send() + * while holding the channel->downl lock. And ppp_output_wakeup() as + * called by the tasklet will *also* grab that lock. So even if another + * CPU is in pppoatm_send() right now, the tasklet isn't going to race + * with it. The wakeup *will* happen after the other CPU is safely out + * of pppoatm_send() again. + * + * So if the CPU in pppoatm_send() has already set the BLOCKED bit and + * it about to return, that's fine. We trigger a wakeup which will + * happen later. And if the CPU in pppoatm_send() *hasn't* set the + * BLOCKED bit yet, that's fine too because of the double check in + * pppoatm_may_send() which is commented there. */ - tasklet_schedule(&pvcc->wakeup_tasklet); + if (test_and_clear_bit(BLOCKED, &pvcc->blocked)) + tasklet_schedule(&pvcc->wakeup_tasklet); } /* @@ -184,6 +211,51 @@ error: ppp_input_error(&pvcc->chan, 0); } +static inline int pppoatm_may_send(struct pppoatm_vcc *pvcc, int size) +{ + /* + * It's not clear that we need to bother with using atm_may_send() + * to check we don't exceed sk->sk_sndbuf. If userspace sets a + * value of sk_sndbuf which is lower than the MTU, we're going to + * block for ever. But the code always did that before we introduced + * the packet count limit, so... + */ + if (atm_may_send(pvcc->atmvcc, size) && + atomic_inc_not_zero_hint(&pvcc->inflight, NONE_INFLIGHT)) + return 1; + + /* + * We use test_and_set_bit() rather than set_bit() here because + * we need to ensure there's a memory barrier after it. The bit + * *must* be set before we do the atomic_inc() on pvcc->inflight. + * There's no smp_mb__after_set_bit(), so it's this or abuse + * smp_mb__after_clear_bit(). + */ + test_and_set_bit(BLOCKED, &pvcc->blocked); + + /* + * We may have raced with pppoatm_pop(). If it ran for the + * last packet in the queue, *just* before we set the BLOCKED + * bit, then it might never run again and the channel could + * remain permanently blocked. Cope with that race by checking + * *again*. If it did run in that window, we'll have space on + * the queue now and can return success. It's harmless to leave + * the BLOCKED flag set, since it's only used as a trigger to + * run the wakeup tasklet. Another wakeup will never hurt. + * If pppoatm_pop() is running but hasn't got as far as making + * space on the queue yet, then it hasn't checked the BLOCKED + * flag yet either, so we're safe in that case too. It'll issue + * an "immediate" wakeup... where "immediate" actually involves + * taking the PPP channel's ->downl lock, which is held by the + * code path that calls pppoatm_send(), and is thus going to + * wait for us to finish. + */ + if (atm_may_send(pvcc->atmvcc, size) && + atomic_inc_not_zero(&pvcc->inflight)) + return 1; + + return 0; +} /* * Called by the ppp_generic.c to send a packet - returns true if packet * was accepted. If we return false, then it's our job to call @@ -207,7 +279,7 @@ static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb) struct sk_buff *n; n = skb_realloc_headroom(skb, LLC_LEN); if (n != NULL && - !atm_may_send(pvcc->atmvcc, n->truesize)) { + !pppoatm_may_send(pvcc, n->truesize)) { kfree_skb(n); goto nospace; } @@ -215,12 +287,12 @@ static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb) skb = n; if (skb == NULL) return DROP_PACKET; - } else if (!atm_may_send(pvcc->atmvcc, skb->truesize)) + } else if (!pppoatm_may_send(pvcc, skb->truesize)) goto nospace; memcpy(skb_push(skb, LLC_LEN), pppllc, LLC_LEN); break; case e_vc: - if (!atm_may_send(pvcc->atmvcc, skb->truesize)) + if (!pppoatm_may_send(pvcc, skb->truesize)) goto nospace; break; case e_autodetect: @@ -285,6 +357,9 @@ static int pppoatm_assign_vcc(struct atm_vcc *atmvcc, void __user *arg) if (pvcc == NULL) return -ENOMEM; pvcc->atmvcc = atmvcc; + + /* Maximum is zero, so that we can use atomic_inc_not_zero() */ + atomic_set(&pvcc->inflight, NONE_INFLIGHT); pvcc->old_push = atmvcc->push; pvcc->old_pop = atmvcc->pop; pvcc->encaps = (enum pppoatm_encaps) be.encaps; diff --git a/net/atm/signaling.c b/net/atm/signaling.c index 509c8ac02b6..86767ca908a 100644 --- a/net/atm/signaling.c +++ b/net/atm/signaling.c @@ -166,7 +166,7 @@ void sigd_enq2(struct atm_vcc *vcc, enum atmsvc_msg_type type, { struct sk_buff *skb; struct atmsvc_msg *msg; - static unsigned session = 0; + static unsigned int session = 0; pr_debug("%d (0x%p)\n", (int)type, vcc); while (!(skb = alloc_skb(sizeof(struct atmsvc_msg), GFP_KERNEL))) diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 0906c194a41..051f7abae66 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1990,7 +1990,6 @@ static int __init ax25_init(void) sock_register(&ax25_family_ops); dev_add_pack(&ax25_packet_type); register_netdevice_notifier(&ax25_dev_notifier); - ax25_register_sysctl(); proc_net_fops_create(&init_net, "ax25_route", S_IRUGO, &ax25_route_fops); proc_net_fops_create(&init_net, "ax25", S_IRUGO, &ax25_info_fops); @@ -2011,16 +2010,16 @@ static void __exit ax25_exit(void) proc_net_remove(&init_net, "ax25_route"); proc_net_remove(&init_net, "ax25"); proc_net_remove(&init_net, "ax25_calls"); - ax25_rt_free(); - ax25_uid_free(); - ax25_dev_free(); - ax25_unregister_sysctl(); unregister_netdevice_notifier(&ax25_dev_notifier); dev_remove_pack(&ax25_packet_type); sock_unregister(PF_AX25); proto_unregister(&ax25_proto); + + ax25_rt_free(); + ax25_uid_free(); + ax25_dev_free(); } module_exit(ax25_exit); diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c index d0de30e8959..3d106767b27 100644 --- a/net/ax25/ax25_dev.c +++ b/net/ax25/ax25_dev.c @@ -59,8 +59,6 @@ void ax25_dev_device_up(struct net_device *dev) return; } - ax25_unregister_sysctl(); - dev->ax25_ptr = ax25_dev; ax25_dev->dev = dev; dev_hold(dev); @@ -90,7 +88,7 @@ void ax25_dev_device_up(struct net_device *dev) ax25_dev_list = ax25_dev; spin_unlock_bh(&ax25_dev_lock); - ax25_register_sysctl(); + ax25_register_dev_sysctl(ax25_dev); } void ax25_dev_device_down(struct net_device *dev) @@ -100,7 +98,7 @@ void ax25_dev_device_down(struct net_device *dev) if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL) return; - ax25_unregister_sysctl(); + ax25_unregister_dev_sysctl(ax25_dev); spin_lock_bh(&ax25_dev_lock); @@ -120,7 +118,6 @@ void ax25_dev_device_down(struct net_device *dev) spin_unlock_bh(&ax25_dev_lock); dev_put(dev); kfree(ax25_dev); - ax25_register_sysctl(); return; } @@ -130,7 +127,6 @@ void ax25_dev_device_down(struct net_device *dev) spin_unlock_bh(&ax25_dev_lock); dev_put(dev); kfree(ax25_dev); - ax25_register_sysctl(); return; } @@ -138,8 +134,6 @@ void ax25_dev_device_down(struct net_device *dev) } spin_unlock_bh(&ax25_dev_lock); dev->ax25_ptr = NULL; - - ax25_register_sysctl(); } int ax25_fwd_ioctl(unsigned int cmd, struct ax25_fwd_struct *fwd) diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c index 846ae4e2b11..67de6b33f2c 100644 --- a/net/ax25/ax25_ip.c +++ b/net/ax25/ax25_ip.c @@ -48,7 +48,7 @@ int ax25_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, - const void *saddr, unsigned len) + const void *saddr, unsigned int len) { unsigned char *buff; @@ -219,7 +219,7 @@ put: int ax25_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, - const void *saddr, unsigned len) + const void *saddr, unsigned int len) { return -AX25_HEADER_LEN; } diff --git a/net/ax25/sysctl_net_ax25.c b/net/ax25/sysctl_net_ax25.c index ebe0ef3f1d8..d5744b75251 100644 --- a/net/ax25/sysctl_net_ax25.c +++ b/net/ax25/sysctl_net_ax25.c @@ -29,17 +29,6 @@ static int min_proto[1], max_proto[] = { AX25_PROTO_MAX }; static int min_ds_timeout[1], max_ds_timeout[] = {65535000}; #endif -static struct ctl_table_header *ax25_table_header; - -static ctl_table *ax25_table; -static int ax25_table_size; - -static struct ctl_path ax25_path[] = { - { .procname = "net", }, - { .procname = "ax25", }, - { } -}; - static const ctl_table ax25_param_table[] = { { .procname = "ip_default_mode", @@ -159,52 +148,37 @@ static const ctl_table ax25_param_table[] = { { } /* that's all, folks! */ }; -void ax25_register_sysctl(void) +int ax25_register_dev_sysctl(ax25_dev *ax25_dev) { - ax25_dev *ax25_dev; - int n, k; - - spin_lock_bh(&ax25_dev_lock); - for (ax25_table_size = sizeof(ctl_table), ax25_dev = ax25_dev_list; ax25_dev != NULL; ax25_dev = ax25_dev->next) - ax25_table_size += sizeof(ctl_table); - - if ((ax25_table = kzalloc(ax25_table_size, GFP_ATOMIC)) == NULL) { - spin_unlock_bh(&ax25_dev_lock); - return; - } - - for (n = 0, ax25_dev = ax25_dev_list; ax25_dev != NULL; ax25_dev = ax25_dev->next) { - struct ctl_table *child = kmemdup(ax25_param_table, - sizeof(ax25_param_table), - GFP_ATOMIC); - if (!child) { - while (n--) - kfree(ax25_table[n].child); - kfree(ax25_table); - spin_unlock_bh(&ax25_dev_lock); - return; - } - ax25_table[n].child = ax25_dev->systable = child; - ax25_table[n].procname = ax25_dev->dev->name; - ax25_table[n].mode = 0555; - - - for (k = 0; k < AX25_MAX_VALUES; k++) - child[k].data = &ax25_dev->values[k]; - - n++; + char path[sizeof("net/ax25/") + IFNAMSIZ]; + int k; + struct ctl_table *table; + + table = kmemdup(ax25_param_table, sizeof(ax25_param_table), GFP_KERNEL); + if (!table) + return -ENOMEM; + + for (k = 0; k < AX25_MAX_VALUES; k++) + table[k].data = &ax25_dev->values[k]; + + snprintf(path, sizeof(path), "net/ax25/%s", ax25_dev->dev->name); + ax25_dev->sysheader = register_net_sysctl(&init_net, path, table); + if (!ax25_dev->sysheader) { + kfree(table); + return -ENOMEM; } - spin_unlock_bh(&ax25_dev_lock); - - ax25_table_header = register_sysctl_paths(ax25_path, ax25_table); + return 0; } -void ax25_unregister_sysctl(void) +void ax25_unregister_dev_sysctl(ax25_dev *ax25_dev) { - ctl_table *p; - unregister_sysctl_table(ax25_table_header); - - for (p = ax25_table; p->procname; p++) - kfree(p->child); - kfree(ax25_table); + struct ctl_table_header *header = ax25_dev->sysheader; + struct ctl_table *table; + + if (header) { + ax25_dev->sysheader = NULL; + table = header->ctl_table_arg; + unregister_net_sysctl_table(header); + kfree(table); + } } diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index 2b68d068eaf..53f5244e28f 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -7,19 +7,28 @@ config BATMAN_ADV depends on NET select CRC16 default n - ---help--- + help + B.A.T.M.A.N. (better approach to mobile ad-hoc networking) is + a routing protocol for multi-hop ad-hoc mesh networks. The + networks may be wired or wireless. See + http://www.open-mesh.org/ for more information and user space + tools. - B.A.T.M.A.N. (better approach to mobile ad-hoc networking) is - a routing protocol for multi-hop ad-hoc mesh networks. The - networks may be wired or wireless. See - http://www.open-mesh.org/ for more information and user space - tools. +config BATMAN_ADV_BLA + bool "Bridge Loop Avoidance" + depends on BATMAN_ADV && INET + default y + help + This option enables BLA (Bridge Loop Avoidance), a mechanism + to avoid Ethernet frames looping when mesh nodes are connected + to both the same LAN and the same mesh. If you will never use + more than one mesh node in the same LAN, you can safely remove + this feature and save some space. config BATMAN_ADV_DEBUG bool "B.A.T.M.A.N. debugging" - depends on BATMAN_ADV != n - ---help--- - + depends on BATMAN_ADV + help This is an option for use by developers; most people should say N here. This enables compilation of support for outputting debugging information to the kernel log. The diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index 4e392ebedb6..6d5c1940667 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -23,6 +23,7 @@ batman-adv-y += bat_debugfs.o batman-adv-y += bat_iv_ogm.o batman-adv-y += bat_sysfs.o batman-adv-y += bitarray.o +batman-adv-$(CONFIG_BATMAN_ADV_BLA) += bridge_loop_avoidance.o batman-adv-y += gateway_client.o batman-adv-y += gateway_common.o batman-adv-y += hard-interface.o diff --git a/net/batman-adv/bat_debugfs.c b/net/batman-adv/bat_debugfs.c index c3b0548b175..3b588f86d77 100644 --- a/net/batman-adv/bat_debugfs.c +++ b/net/batman-adv/bat_debugfs.c @@ -32,6 +32,7 @@ #include "soft-interface.h" #include "vis.h" #include "icmp_socket.h" +#include "bridge_loop_avoidance.h" static struct dentry *bat_debugfs; @@ -82,8 +83,8 @@ int debug_log(struct bat_priv *bat_priv, const char *fmt, ...) va_start(args, fmt); vscnprintf(tmp_log_buf, sizeof(tmp_log_buf), fmt, args); - fdebug_log(bat_priv->debug_log, "[%10lu] %s", - (jiffies / HZ), tmp_log_buf); + fdebug_log(bat_priv->debug_log, "[%10u] %s", + jiffies_to_msecs(jiffies), tmp_log_buf); va_end(args); return 0; @@ -238,17 +239,19 @@ static int gateways_open(struct inode *inode, struct file *file) return single_open(file, gw_client_seq_print_text, net_dev); } -static int softif_neigh_open(struct inode *inode, struct file *file) +static int transtable_global_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; - return single_open(file, softif_neigh_seq_print_text, net_dev); + return single_open(file, tt_global_seq_print_text, net_dev); } -static int transtable_global_open(struct inode *inode, struct file *file) +#ifdef CONFIG_BATMAN_ADV_BLA +static int bla_claim_table_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; - return single_open(file, tt_global_seq_print_text, net_dev); + return single_open(file, bla_claim_table_seq_print_text, net_dev); } +#endif static int transtable_local_open(struct inode *inode, struct file *file) { @@ -282,16 +285,20 @@ struct bat_debuginfo bat_debuginfo_##_name = { \ static BAT_DEBUGINFO(routing_algos, S_IRUGO, bat_algorithms_open); static BAT_DEBUGINFO(originators, S_IRUGO, originators_open); static BAT_DEBUGINFO(gateways, S_IRUGO, gateways_open); -static BAT_DEBUGINFO(softif_neigh, S_IRUGO, softif_neigh_open); static BAT_DEBUGINFO(transtable_global, S_IRUGO, transtable_global_open); +#ifdef CONFIG_BATMAN_ADV_BLA +static BAT_DEBUGINFO(bla_claim_table, S_IRUGO, bla_claim_table_open); +#endif static BAT_DEBUGINFO(transtable_local, S_IRUGO, transtable_local_open); static BAT_DEBUGINFO(vis_data, S_IRUGO, vis_data_open); static struct bat_debuginfo *mesh_debuginfos[] = { &bat_debuginfo_originators, &bat_debuginfo_gateways, - &bat_debuginfo_softif_neigh, &bat_debuginfo_transtable_global, +#ifdef CONFIG_BATMAN_ADV_BLA + &bat_debuginfo_bla_claim_table, +#endif &bat_debuginfo_transtable_local, &bat_debuginfo_vis_data, NULL, diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index a6d5d63fb6a..dc53798ebb4 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -30,33 +30,69 @@ #include "send.h" #include "bat_algo.h" -static void bat_iv_ogm_init(struct hard_iface *hard_iface) +static struct neigh_node *bat_iv_ogm_neigh_new(struct hard_iface *hard_iface, + const uint8_t *neigh_addr, + struct orig_node *orig_node, + struct orig_node *orig_neigh, + uint32_t seqno) +{ + struct neigh_node *neigh_node; + + neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr, seqno); + if (!neigh_node) + goto out; + + INIT_LIST_HEAD(&neigh_node->bonding_list); + + neigh_node->orig_node = orig_neigh; + neigh_node->if_incoming = hard_iface; + + spin_lock_bh(&orig_node->neigh_list_lock); + hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); + spin_unlock_bh(&orig_node->neigh_list_lock); + +out: + return neigh_node; +} + +static int bat_iv_ogm_iface_enable(struct hard_iface *hard_iface) { struct batman_ogm_packet *batman_ogm_packet; + uint32_t random_seqno; + int res = -1; - hard_iface->packet_len = BATMAN_OGM_LEN; + /* randomize initial seqno to avoid collision */ + get_random_bytes(&random_seqno, sizeof(random_seqno)); + atomic_set(&hard_iface->seqno, random_seqno); + + hard_iface->packet_len = BATMAN_OGM_HLEN; hard_iface->packet_buff = kmalloc(hard_iface->packet_len, GFP_ATOMIC); + if (!hard_iface->packet_buff) + goto out; + batman_ogm_packet = (struct batman_ogm_packet *)hard_iface->packet_buff; - batman_ogm_packet->header.packet_type = BAT_OGM; + batman_ogm_packet->header.packet_type = BAT_IV_OGM; batman_ogm_packet->header.version = COMPAT_VERSION; batman_ogm_packet->header.ttl = 2; batman_ogm_packet->flags = NO_FLAGS; batman_ogm_packet->tq = TQ_MAX_VALUE; batman_ogm_packet->tt_num_changes = 0; batman_ogm_packet->ttvn = 0; + + res = 0; + +out: + return res; } -static void bat_iv_ogm_init_primary(struct hard_iface *hard_iface) +static void bat_iv_ogm_iface_disable(struct hard_iface *hard_iface) { - struct batman_ogm_packet *batman_ogm_packet; - - batman_ogm_packet = (struct batman_ogm_packet *)hard_iface->packet_buff; - batman_ogm_packet->flags = PRIMARIES_FIRST_HOP; - batman_ogm_packet->header.ttl = TTL; + kfree(hard_iface->packet_buff); + hard_iface->packet_buff = NULL; } -static void bat_iv_ogm_update_mac(struct hard_iface *hard_iface) +static void bat_iv_ogm_iface_update_mac(struct hard_iface *hard_iface) { struct batman_ogm_packet *batman_ogm_packet; @@ -67,6 +103,15 @@ static void bat_iv_ogm_update_mac(struct hard_iface *hard_iface) hard_iface->net_dev->dev_addr, ETH_ALEN); } +static void bat_iv_ogm_primary_iface_set(struct hard_iface *hard_iface) +{ + struct batman_ogm_packet *batman_ogm_packet; + + batman_ogm_packet = (struct batman_ogm_packet *)hard_iface->packet_buff; + batman_ogm_packet->flags = PRIMARIES_FIRST_HOP; + batman_ogm_packet->header.ttl = TTL; +} + /* when do we schedule our own ogm to be sent */ static unsigned long bat_iv_ogm_emit_send_time(const struct bat_priv *bat_priv) { @@ -92,7 +137,7 @@ static uint8_t hop_penalty(uint8_t tq, const struct bat_priv *bat_priv) static int bat_iv_ogm_aggr_packet(int buff_pos, int packet_len, int tt_num_changes) { - int next_buff_pos = buff_pos + BATMAN_OGM_LEN + tt_len(tt_num_changes); + int next_buff_pos = buff_pos + BATMAN_OGM_HLEN + tt_len(tt_num_changes); return (next_buff_pos <= packet_len) && (next_buff_pos <= MAX_AGGREGATION_BYTES); @@ -132,7 +177,7 @@ static void bat_iv_ogm_send_to_if(struct forw_packet *forw_packet, "Sending own" : "Forwarding")); bat_dbg(DBG_BATMAN, bat_priv, - "%s %spacket (originator %pM, seqno %d, TQ %d, TTL %d, IDF %s, ttvn %d) on interface %s [%pM]\n", + "%s %spacket (originator %pM, seqno %u, TQ %d, TTL %d, IDF %s, ttvn %d) on interface %s [%pM]\n", fwd_str, (packet_num > 0 ? "aggregated " : ""), batman_ogm_packet->orig, ntohl(batman_ogm_packet->seqno), @@ -142,7 +187,7 @@ static void bat_iv_ogm_send_to_if(struct forw_packet *forw_packet, batman_ogm_packet->ttvn, hard_iface->net_dev->name, hard_iface->net_dev->dev_addr); - buff_pos += BATMAN_OGM_LEN + + buff_pos += BATMAN_OGM_HLEN + tt_len(batman_ogm_packet->tt_num_changes); packet_num++; batman_ogm_packet = (struct batman_ogm_packet *) @@ -191,7 +236,7 @@ static void bat_iv_ogm_emit(struct forw_packet *forw_packet) /* FIXME: what about aggregated packets ? */ bat_dbg(DBG_BATMAN, bat_priv, - "%s packet (originator %pM, seqno %d, TTL %d) on interface %s [%pM]\n", + "%s packet (originator %pM, seqno %u, TTL %d) on interface %s [%pM]\n", (forw_packet->own ? "Sending own" : "Forwarding"), batman_ogm_packet->orig, ntohl(batman_ogm_packet->seqno), @@ -335,10 +380,9 @@ static void bat_iv_ogm_aggregate_new(const unsigned char *packet_buff, if ((atomic_read(&bat_priv->aggregated_ogms)) && (packet_len < MAX_AGGREGATION_BYTES)) forw_packet_aggr->skb = dev_alloc_skb(MAX_AGGREGATION_BYTES + - sizeof(struct ethhdr)); + ETH_HLEN); else - forw_packet_aggr->skb = dev_alloc_skb(packet_len + - sizeof(struct ethhdr)); + forw_packet_aggr->skb = dev_alloc_skb(packet_len + ETH_HLEN); if (!forw_packet_aggr->skb) { if (!own_packet) @@ -346,7 +390,7 @@ static void bat_iv_ogm_aggregate_new(const unsigned char *packet_buff, kfree(forw_packet_aggr); goto out; } - skb_reserve(forw_packet_aggr->skb, sizeof(struct ethhdr)); + skb_reserve(forw_packet_aggr->skb, ETH_HLEN); INIT_HLIST_NODE(&forw_packet_aggr->list); @@ -461,11 +505,11 @@ static void bat_iv_ogm_queue_add(struct bat_priv *bat_priv, static void bat_iv_ogm_forward(struct orig_node *orig_node, const struct ethhdr *ethhdr, struct batman_ogm_packet *batman_ogm_packet, - int directlink, struct hard_iface *if_incoming) + bool is_single_hop_neigh, + bool is_from_best_next_hop, + struct hard_iface *if_incoming) { struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); - struct neigh_node *router; - uint8_t in_tq, in_ttl, tq_avg = 0; uint8_t tt_num_changes; if (batman_ogm_packet->header.ttl <= 1) { @@ -473,54 +517,43 @@ static void bat_iv_ogm_forward(struct orig_node *orig_node, return; } - router = orig_node_get_router(orig_node); + if (!is_from_best_next_hop) { + /* Mark the forwarded packet when it is not coming from our + * best next hop. We still need to forward the packet for our + * neighbor link quality detection to work in case the packet + * originated from a single hop neighbor. Otherwise we can + * simply drop the ogm. + */ + if (is_single_hop_neigh) + batman_ogm_packet->flags |= NOT_BEST_NEXT_HOP; + else + return; + } - in_tq = batman_ogm_packet->tq; - in_ttl = batman_ogm_packet->header.ttl; tt_num_changes = batman_ogm_packet->tt_num_changes; batman_ogm_packet->header.ttl--; memcpy(batman_ogm_packet->prev_sender, ethhdr->h_source, ETH_ALEN); - /* rebroadcast tq of our best ranking neighbor to ensure the rebroadcast - * of our best tq value */ - if (router && router->tq_avg != 0) { - - /* rebroadcast ogm of best ranking neighbor as is */ - if (!compare_eth(router->addr, ethhdr->h_source)) { - batman_ogm_packet->tq = router->tq_avg; - - if (router->last_ttl) - batman_ogm_packet->header.ttl = - router->last_ttl - 1; - } - - tq_avg = router->tq_avg; - } - - if (router) - neigh_node_free_ref(router); - /* apply hop penalty */ batman_ogm_packet->tq = hop_penalty(batman_ogm_packet->tq, bat_priv); bat_dbg(DBG_BATMAN, bat_priv, - "Forwarding packet: tq_orig: %i, tq_avg: %i, tq_forw: %i, ttl_orig: %i, ttl_forw: %i\n", - in_tq, tq_avg, batman_ogm_packet->tq, in_ttl - 1, - batman_ogm_packet->header.ttl); + "Forwarding packet: tq: %i, ttl: %i\n", + batman_ogm_packet->tq, batman_ogm_packet->header.ttl); batman_ogm_packet->seqno = htonl(batman_ogm_packet->seqno); batman_ogm_packet->tt_crc = htons(batman_ogm_packet->tt_crc); /* switch of primaries first hop flag when forwarding */ batman_ogm_packet->flags &= ~PRIMARIES_FIRST_HOP; - if (directlink) + if (is_single_hop_neigh) batman_ogm_packet->flags |= DIRECTLINK; else batman_ogm_packet->flags &= ~DIRECTLINK; bat_iv_ogm_queue_add(bat_priv, (unsigned char *)batman_ogm_packet, - BATMAN_OGM_LEN + tt_len(tt_num_changes), + BATMAN_OGM_HLEN + tt_len(tt_num_changes), if_incoming, 0, bat_iv_ogm_fwd_send_time()); } @@ -603,12 +636,12 @@ static void bat_iv_ogm_orig_update(struct bat_priv *bat_priv, if (is_duplicate) continue; - spin_lock_bh(&tmp_neigh_node->tq_lock); + spin_lock_bh(&tmp_neigh_node->lq_update_lock); ring_buffer_set(tmp_neigh_node->tq_recv, &tmp_neigh_node->tq_index, 0); tmp_neigh_node->tq_avg = ring_buffer_avg(tmp_neigh_node->tq_recv); - spin_unlock_bh(&tmp_neigh_node->tq_lock); + spin_unlock_bh(&tmp_neigh_node->lq_update_lock); } if (!neigh_node) { @@ -618,8 +651,9 @@ static void bat_iv_ogm_orig_update(struct bat_priv *bat_priv, if (!orig_tmp) goto unlock; - neigh_node = create_neighbor(orig_node, orig_tmp, - ethhdr->h_source, if_incoming); + neigh_node = bat_iv_ogm_neigh_new(if_incoming, ethhdr->h_source, + orig_node, orig_tmp, + batman_ogm_packet->seqno); orig_node_free_ref(orig_tmp); if (!neigh_node) @@ -631,14 +665,14 @@ static void bat_iv_ogm_orig_update(struct bat_priv *bat_priv, rcu_read_unlock(); orig_node->flags = batman_ogm_packet->flags; - neigh_node->last_valid = jiffies; + neigh_node->last_seen = jiffies; - spin_lock_bh(&neigh_node->tq_lock); + spin_lock_bh(&neigh_node->lq_update_lock); ring_buffer_set(neigh_node->tq_recv, &neigh_node->tq_index, batman_ogm_packet->tq); neigh_node->tq_avg = ring_buffer_avg(neigh_node->tq_recv); - spin_unlock_bh(&neigh_node->tq_lock); + spin_unlock_bh(&neigh_node->lq_update_lock); if (!is_duplicate) { orig_node->last_ttl = batman_ogm_packet->header.ttl; @@ -744,19 +778,20 @@ static int bat_iv_ogm_calc_tq(struct orig_node *orig_node, rcu_read_unlock(); if (!neigh_node) - neigh_node = create_neighbor(orig_neigh_node, - orig_neigh_node, - orig_neigh_node->orig, - if_incoming); + neigh_node = bat_iv_ogm_neigh_new(if_incoming, + orig_neigh_node->orig, + orig_neigh_node, + orig_neigh_node, + batman_ogm_packet->seqno); if (!neigh_node) goto out; - /* if orig_node is direct neighbor update neigh_node last_valid */ + /* if orig_node is direct neighbor update neigh_node last_seen */ if (orig_node == orig_neigh_node) - neigh_node->last_valid = jiffies; + neigh_node->last_seen = jiffies; - orig_node->last_valid = jiffies; + orig_node->last_seen = jiffies; /* find packet count of corresponding one hop neighbor */ spin_lock_bh(&orig_node->ogm_cnt_lock); @@ -842,7 +877,8 @@ static int bat_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, seq_diff = batman_ogm_packet->seqno - orig_node->last_real_seqno; /* signalize caller that the packet is to be dropped. */ - if (window_protected(bat_priv, seq_diff, + if (!hlist_empty(&orig_node->neigh_list) && + window_protected(bat_priv, seq_diff, &orig_node->batman_seqno_reset)) goto out; @@ -850,9 +886,9 @@ static int bat_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, hlist_for_each_entry_rcu(tmp_neigh_node, node, &orig_node->neigh_list, list) { - is_duplicate |= get_bit_status(tmp_neigh_node->real_bits, - orig_node->last_real_seqno, - batman_ogm_packet->seqno); + is_duplicate |= bat_test_bit(tmp_neigh_node->real_bits, + orig_node->last_real_seqno, + batman_ogm_packet->seqno); if (compare_eth(tmp_neigh_node->addr, ethhdr->h_source) && (tmp_neigh_node->if_incoming == if_incoming)) @@ -866,13 +902,14 @@ static int bat_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, seq_diff, set_mark); tmp_neigh_node->real_packet_count = - bit_packet_count(tmp_neigh_node->real_bits); + bitmap_weight(tmp_neigh_node->real_bits, + TQ_LOCAL_WINDOW_SIZE); } rcu_read_unlock(); if (need_update) { bat_dbg(DBG_BATMAN, bat_priv, - "updating last_seqno: old %d, new %d\n", + "updating last_seqno: old %u, new %u\n", orig_node->last_real_seqno, batman_ogm_packet->seqno); orig_node->last_real_seqno = batman_ogm_packet->seqno; } @@ -897,7 +934,9 @@ static void bat_iv_ogm_process(const struct ethhdr *ethhdr, struct neigh_node *orig_neigh_router = NULL; int has_directlink_flag; int is_my_addr = 0, is_my_orig = 0, is_my_oldorig = 0; - int is_broadcast = 0, is_bidirectional, is_single_hop_neigh; + int is_broadcast = 0, is_bidirectional; + bool is_single_hop_neigh = false; + bool is_from_best_next_hop = false; int is_duplicate; uint32_t if_incoming_seqno; @@ -913,7 +952,7 @@ static void bat_iv_ogm_process(const struct ethhdr *ethhdr, * packet in an aggregation. Here we expect that the padding * is always zero (or not 0x01) */ - if (batman_ogm_packet->header.packet_type != BAT_OGM) + if (batman_ogm_packet->header.packet_type != BAT_IV_OGM) return; /* could be changed by schedule_own_packet() */ @@ -921,11 +960,11 @@ static void bat_iv_ogm_process(const struct ethhdr *ethhdr, has_directlink_flag = (batman_ogm_packet->flags & DIRECTLINK ? 1 : 0); - is_single_hop_neigh = (compare_eth(ethhdr->h_source, - batman_ogm_packet->orig) ? 1 : 0); + if (compare_eth(ethhdr->h_source, batman_ogm_packet->orig)) + is_single_hop_neigh = true; bat_dbg(DBG_BATMAN, bat_priv, - "Received BATMAN packet via NB: %pM, IF: %s [%pM] (from OG: %pM, via prev OG: %pM, seqno %d, ttvn %u, crc %u, changes %u, td %d, TTL %d, V %d, IDF %d)\n", + "Received BATMAN packet via NB: %pM, IF: %s [%pM] (from OG: %pM, via prev OG: %pM, seqno %u, ttvn %u, crc %u, changes %u, td %d, TTL %d, V %d, IDF %d)\n", ethhdr->h_source, if_incoming->net_dev->name, if_incoming->net_dev->dev_addr, batman_ogm_packet->orig, batman_ogm_packet->prev_sender, batman_ogm_packet->seqno, @@ -998,11 +1037,11 @@ static void bat_iv_ogm_process(const struct ethhdr *ethhdr, spin_lock_bh(&orig_neigh_node->ogm_cnt_lock); word = &(orig_neigh_node->bcast_own[offset]); - bit_mark(word, - if_incoming_seqno - + bat_set_bit(word, + if_incoming_seqno - batman_ogm_packet->seqno - 2); orig_neigh_node->bcast_own_sum[if_incoming->if_num] = - bit_packet_count(word); + bitmap_weight(word, TQ_LOCAL_WINDOW_SIZE); spin_unlock_bh(&orig_neigh_node->ogm_cnt_lock); } @@ -1019,6 +1058,13 @@ static void bat_iv_ogm_process(const struct ethhdr *ethhdr, return; } + if (batman_ogm_packet->flags & NOT_BEST_NEXT_HOP) { + bat_dbg(DBG_BATMAN, bat_priv, + "Drop packet: ignoring all packets not forwarded from the best next hop (sender: %pM)\n", + ethhdr->h_source); + return; + } + orig_node = get_orig_node(bat_priv, batman_ogm_packet->orig); if (!orig_node) return; @@ -1043,6 +1089,10 @@ static void bat_iv_ogm_process(const struct ethhdr *ethhdr, if (router) router_router = orig_node_get_router(router->orig_node); + if ((router && router->tq_avg != 0) && + (compare_eth(router->addr, ethhdr->h_source))) + is_from_best_next_hop = true; + /* avoid temporary routing loops */ if (router && router_router && (compare_eth(router->addr, batman_ogm_packet->prev_sender)) && @@ -1093,7 +1143,8 @@ static void bat_iv_ogm_process(const struct ethhdr *ethhdr, /* mark direct link on incoming interface */ bat_iv_ogm_forward(orig_node, ethhdr, batman_ogm_packet, - 1, if_incoming); + is_single_hop_neigh, is_from_best_next_hop, + if_incoming); bat_dbg(DBG_BATMAN, bat_priv, "Forwarding packet: rebroadcast neighbor packet with direct link flag\n"); @@ -1116,7 +1167,8 @@ static void bat_iv_ogm_process(const struct ethhdr *ethhdr, bat_dbg(DBG_BATMAN, bat_priv, "Forwarding packet: rebroadcast originator packet\n"); bat_iv_ogm_forward(orig_node, ethhdr, batman_ogm_packet, - 0, if_incoming); + is_single_hop_neigh, is_from_best_next_hop, + if_incoming); out_neigh: if ((orig_neigh_node) && (!is_single_hop_neigh)) @@ -1132,13 +1184,25 @@ out: orig_node_free_ref(orig_node); } -static void bat_iv_ogm_receive(struct hard_iface *if_incoming, - struct sk_buff *skb) +static int bat_iv_ogm_receive(struct sk_buff *skb, + struct hard_iface *if_incoming) { + struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batman_ogm_packet *batman_ogm_packet; struct ethhdr *ethhdr; int buff_pos = 0, packet_len; unsigned char *tt_buff, *packet_buff; + bool ret; + + ret = check_management_packet(skb, if_incoming, BATMAN_OGM_HLEN); + if (!ret) + return NET_RX_DROP; + + /* did we receive a B.A.T.M.A.N. IV OGM packet on an interface + * that does not have B.A.T.M.A.N. IV enabled ? + */ + if (bat_priv->bat_algo_ops->bat_ogm_emit != bat_iv_ogm_emit) + return NET_RX_DROP; packet_len = skb_headlen(skb); ethhdr = (struct ethhdr *)skb_mac_header(skb); @@ -1152,31 +1216,50 @@ static void bat_iv_ogm_receive(struct hard_iface *if_incoming, batman_ogm_packet->seqno = ntohl(batman_ogm_packet->seqno); batman_ogm_packet->tt_crc = ntohs(batman_ogm_packet->tt_crc); - tt_buff = packet_buff + buff_pos + BATMAN_OGM_LEN; + tt_buff = packet_buff + buff_pos + BATMAN_OGM_HLEN; bat_iv_ogm_process(ethhdr, batman_ogm_packet, tt_buff, if_incoming); - buff_pos += BATMAN_OGM_LEN + + buff_pos += BATMAN_OGM_HLEN + tt_len(batman_ogm_packet->tt_num_changes); batman_ogm_packet = (struct batman_ogm_packet *) (packet_buff + buff_pos); } while (bat_iv_ogm_aggr_packet(buff_pos, packet_len, batman_ogm_packet->tt_num_changes)); + + kfree_skb(skb); + return NET_RX_SUCCESS; } static struct bat_algo_ops batman_iv __read_mostly = { .name = "BATMAN IV", - .bat_ogm_init = bat_iv_ogm_init, - .bat_ogm_init_primary = bat_iv_ogm_init_primary, - .bat_ogm_update_mac = bat_iv_ogm_update_mac, + .bat_iface_enable = bat_iv_ogm_iface_enable, + .bat_iface_disable = bat_iv_ogm_iface_disable, + .bat_iface_update_mac = bat_iv_ogm_iface_update_mac, + .bat_primary_iface_set = bat_iv_ogm_primary_iface_set, .bat_ogm_schedule = bat_iv_ogm_schedule, .bat_ogm_emit = bat_iv_ogm_emit, - .bat_ogm_receive = bat_iv_ogm_receive, }; int __init bat_iv_init(void) { - return bat_algo_register(&batman_iv); + int ret; + + /* batman originator packet */ + ret = recv_handler_register(BAT_IV_OGM, bat_iv_ogm_receive); + if (ret < 0) + goto out; + + ret = bat_algo_register(&batman_iv); + if (ret < 0) + goto handler_unregister; + + goto out; + +handler_unregister: + recv_handler_unregister(BAT_IV_OGM); +out: + return ret; } diff --git a/net/batman-adv/bat_sysfs.c b/net/batman-adv/bat_sysfs.c index 68ff759fc30..5bc7b66d32d 100644 --- a/net/batman-adv/bat_sysfs.c +++ b/net/batman-adv/bat_sysfs.c @@ -63,7 +63,7 @@ struct bat_attribute bat_attr_##_name = { \ .store = _store, \ }; -#define BAT_ATTR_STORE_BOOL(_name, _post_func) \ +#define BAT_ATTR_SIF_STORE_BOOL(_name, _post_func) \ ssize_t store_##_name(struct kobject *kobj, struct attribute *attr, \ char *buff, size_t count) \ { \ @@ -73,9 +73,9 @@ ssize_t store_##_name(struct kobject *kobj, struct attribute *attr, \ &bat_priv->_name, net_dev); \ } -#define BAT_ATTR_SHOW_BOOL(_name) \ -ssize_t show_##_name(struct kobject *kobj, struct attribute *attr, \ - char *buff) \ +#define BAT_ATTR_SIF_SHOW_BOOL(_name) \ +ssize_t show_##_name(struct kobject *kobj, \ + struct attribute *attr, char *buff) \ { \ struct bat_priv *bat_priv = kobj_to_batpriv(kobj); \ return sprintf(buff, "%s\n", \ @@ -83,16 +83,17 @@ ssize_t show_##_name(struct kobject *kobj, struct attribute *attr, \ "disabled" : "enabled"); \ } \ -/* Use this, if you are going to turn a [name] in bat_priv on or off */ -#define BAT_ATTR_BOOL(_name, _mode, _post_func) \ - static BAT_ATTR_STORE_BOOL(_name, _post_func) \ - static BAT_ATTR_SHOW_BOOL(_name) \ +/* Use this, if you are going to turn a [name] in the soft-interface + * (bat_priv) on or off */ +#define BAT_ATTR_SIF_BOOL(_name, _mode, _post_func) \ + static BAT_ATTR_SIF_STORE_BOOL(_name, _post_func) \ + static BAT_ATTR_SIF_SHOW_BOOL(_name) \ static BAT_ATTR(_name, _mode, show_##_name, store_##_name) -#define BAT_ATTR_STORE_UINT(_name, _min, _max, _post_func) \ +#define BAT_ATTR_SIF_STORE_UINT(_name, _min, _max, _post_func) \ ssize_t store_##_name(struct kobject *kobj, struct attribute *attr, \ - char *buff, size_t count) \ + char *buff, size_t count) \ { \ struct net_device *net_dev = kobj_to_netdev(kobj); \ struct bat_priv *bat_priv = netdev_priv(net_dev); \ @@ -100,19 +101,62 @@ ssize_t store_##_name(struct kobject *kobj, struct attribute *attr, \ attr, &bat_priv->_name, net_dev); \ } -#define BAT_ATTR_SHOW_UINT(_name) \ -ssize_t show_##_name(struct kobject *kobj, struct attribute *attr, \ - char *buff) \ +#define BAT_ATTR_SIF_SHOW_UINT(_name) \ +ssize_t show_##_name(struct kobject *kobj, \ + struct attribute *attr, char *buff) \ { \ struct bat_priv *bat_priv = kobj_to_batpriv(kobj); \ return sprintf(buff, "%i\n", atomic_read(&bat_priv->_name)); \ } \ -/* Use this, if you are going to set [name] in bat_priv to unsigned integer - * values only */ -#define BAT_ATTR_UINT(_name, _mode, _min, _max, _post_func) \ - static BAT_ATTR_STORE_UINT(_name, _min, _max, _post_func) \ - static BAT_ATTR_SHOW_UINT(_name) \ +/* Use this, if you are going to set [name] in the soft-interface + * (bat_priv) to an unsigned integer value */ +#define BAT_ATTR_SIF_UINT(_name, _mode, _min, _max, _post_func) \ + static BAT_ATTR_SIF_STORE_UINT(_name, _min, _max, _post_func) \ + static BAT_ATTR_SIF_SHOW_UINT(_name) \ + static BAT_ATTR(_name, _mode, show_##_name, store_##_name) + + +#define BAT_ATTR_HIF_STORE_UINT(_name, _min, _max, _post_func) \ +ssize_t store_##_name(struct kobject *kobj, struct attribute *attr, \ + char *buff, size_t count) \ +{ \ + struct net_device *net_dev = kobj_to_netdev(kobj); \ + struct hard_iface *hard_iface = hardif_get_by_netdev(net_dev); \ + ssize_t length; \ + \ + if (!hard_iface) \ + return 0; \ + \ + length = __store_uint_attr(buff, count, _min, _max, _post_func, \ + attr, &hard_iface->_name, net_dev); \ + \ + hardif_free_ref(hard_iface); \ + return length; \ +} + +#define BAT_ATTR_HIF_SHOW_UINT(_name) \ +ssize_t show_##_name(struct kobject *kobj, \ + struct attribute *attr, char *buff) \ +{ \ + struct net_device *net_dev = kobj_to_netdev(kobj); \ + struct hard_iface *hard_iface = hardif_get_by_netdev(net_dev); \ + ssize_t length; \ + \ + if (!hard_iface) \ + return 0; \ + \ + length = sprintf(buff, "%i\n", atomic_read(&hard_iface->_name));\ + \ + hardif_free_ref(hard_iface); \ + return length; \ +} + +/* Use this, if you are going to set [name] in hard_iface to an + * unsigned integer value*/ +#define BAT_ATTR_HIF_UINT(_name, _mode, _min, _max, _post_func) \ + static BAT_ATTR_HIF_STORE_UINT(_name, _min, _max, _post_func) \ + static BAT_ATTR_HIF_SHOW_UINT(_name) \ static BAT_ATTR(_name, _mode, show_##_name, store_##_name) @@ -149,7 +193,7 @@ static int store_bool_attr(char *buff, size_t count, atomic_read(attr) == 1 ? "enabled" : "disabled", enabled == 1 ? "enabled" : "disabled"); - atomic_set(attr, (unsigned)enabled); + atomic_set(attr, (unsigned int)enabled); return count; } @@ -268,7 +312,7 @@ static ssize_t store_vis_mode(struct kobject *kobj, struct attribute *attr, "client" : "server", vis_mode_tmp == VIS_TYPE_CLIENT_UPDATE ? "client" : "server"); - atomic_set(&bat_priv->vis_mode, (unsigned)vis_mode_tmp); + atomic_set(&bat_priv->vis_mode, (unsigned int)vis_mode_tmp); return count; } @@ -354,7 +398,7 @@ static ssize_t store_gw_mode(struct kobject *kobj, struct attribute *attr, curr_gw_mode_str, buff); gw_deselect(bat_priv); - atomic_set(&bat_priv->gw_mode, (unsigned)gw_mode_tmp); + atomic_set(&bat_priv->gw_mode, (unsigned int)gw_mode_tmp); return count; } @@ -384,26 +428,32 @@ static ssize_t store_gw_bwidth(struct kobject *kobj, struct attribute *attr, return gw_bandwidth_set(net_dev, buff, count); } -BAT_ATTR_BOOL(aggregated_ogms, S_IRUGO | S_IWUSR, NULL); -BAT_ATTR_BOOL(bonding, S_IRUGO | S_IWUSR, NULL); -BAT_ATTR_BOOL(fragmentation, S_IRUGO | S_IWUSR, update_min_mtu); -BAT_ATTR_BOOL(ap_isolation, S_IRUGO | S_IWUSR, NULL); +BAT_ATTR_SIF_BOOL(aggregated_ogms, S_IRUGO | S_IWUSR, NULL); +BAT_ATTR_SIF_BOOL(bonding, S_IRUGO | S_IWUSR, NULL); +#ifdef CONFIG_BATMAN_ADV_BLA +BAT_ATTR_SIF_BOOL(bridge_loop_avoidance, S_IRUGO | S_IWUSR, NULL); +#endif +BAT_ATTR_SIF_BOOL(fragmentation, S_IRUGO | S_IWUSR, update_min_mtu); +BAT_ATTR_SIF_BOOL(ap_isolation, S_IRUGO | S_IWUSR, NULL); static BAT_ATTR(vis_mode, S_IRUGO | S_IWUSR, show_vis_mode, store_vis_mode); static BAT_ATTR(routing_algo, S_IRUGO, show_bat_algo, NULL); static BAT_ATTR(gw_mode, S_IRUGO | S_IWUSR, show_gw_mode, store_gw_mode); -BAT_ATTR_UINT(orig_interval, S_IRUGO | S_IWUSR, 2 * JITTER, INT_MAX, NULL); -BAT_ATTR_UINT(hop_penalty, S_IRUGO | S_IWUSR, 0, TQ_MAX_VALUE, NULL); -BAT_ATTR_UINT(gw_sel_class, S_IRUGO | S_IWUSR, 1, TQ_MAX_VALUE, - post_gw_deselect); +BAT_ATTR_SIF_UINT(orig_interval, S_IRUGO | S_IWUSR, 2 * JITTER, INT_MAX, NULL); +BAT_ATTR_SIF_UINT(hop_penalty, S_IRUGO | S_IWUSR, 0, TQ_MAX_VALUE, NULL); +BAT_ATTR_SIF_UINT(gw_sel_class, S_IRUGO | S_IWUSR, 1, TQ_MAX_VALUE, + post_gw_deselect); static BAT_ATTR(gw_bandwidth, S_IRUGO | S_IWUSR, show_gw_bwidth, store_gw_bwidth); #ifdef CONFIG_BATMAN_ADV_DEBUG -BAT_ATTR_UINT(log_level, S_IRUGO | S_IWUSR, 0, 7, NULL); +BAT_ATTR_SIF_UINT(log_level, S_IRUGO | S_IWUSR, 0, 15, NULL); #endif static struct bat_attribute *mesh_attrs[] = { &bat_attr_aggregated_ogms, &bat_attr_bonding, +#ifdef CONFIG_BATMAN_ADV_BLA + &bat_attr_bridge_loop_avoidance, +#endif &bat_attr_fragmentation, &bat_attr_ap_isolation, &bat_attr_vis_mode, diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index 6d0aa216b23..07ae6e1b8ac 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -24,100 +24,13 @@ #include <linux/bitops.h> -/* returns true if the corresponding bit in the given seq_bits indicates true - * and curr_seqno is within range of last_seqno */ -int get_bit_status(const unsigned long *seq_bits, uint32_t last_seqno, - uint32_t curr_seqno) -{ - int32_t diff, word_offset, word_num; - - diff = last_seqno - curr_seqno; - if (diff < 0 || diff >= TQ_LOCAL_WINDOW_SIZE) { - return 0; - } else { - /* which word */ - word_num = (last_seqno - curr_seqno) / WORD_BIT_SIZE; - /* which position in the selected word */ - word_offset = (last_seqno - curr_seqno) % WORD_BIT_SIZE; - - if (test_bit(word_offset, &seq_bits[word_num])) - return 1; - else - return 0; - } -} - -/* turn corresponding bit on, so we can remember that we got the packet */ -void bit_mark(unsigned long *seq_bits, int32_t n) -{ - int32_t word_offset, word_num; - - /* if too old, just drop it */ - if (n < 0 || n >= TQ_LOCAL_WINDOW_SIZE) - return; - - /* which word */ - word_num = n / WORD_BIT_SIZE; - /* which position in the selected word */ - word_offset = n % WORD_BIT_SIZE; - - set_bit(word_offset, &seq_bits[word_num]); /* turn the position on */ -} - /* shift the packet array by n places. */ -static void bit_shift(unsigned long *seq_bits, int32_t n) +static void bat_bitmap_shift_left(unsigned long *seq_bits, int32_t n) { - int32_t word_offset, word_num; - int32_t i; - if (n <= 0 || n >= TQ_LOCAL_WINDOW_SIZE) return; - word_offset = n % WORD_BIT_SIZE;/* shift how much inside each word */ - word_num = n / WORD_BIT_SIZE; /* shift over how much (full) words */ - - for (i = NUM_WORDS - 1; i > word_num; i--) { - /* going from old to new, so we don't overwrite the data we copy - * from. - * - * left is high, right is low: FEDC BA98 7654 3210 - * ^^ ^^ - * vvvv - * ^^^^ = from, vvvvv =to, we'd have word_num==1 and - * word_offset==WORD_BIT_SIZE/2 ????? in this example. - * (=24 bits) - * - * our desired output would be: 9876 5432 1000 0000 - * */ - - seq_bits[i] = - (seq_bits[i - word_num] << word_offset) + - /* take the lower port from the left half, shift it left - * to its final position */ - (seq_bits[i - word_num - 1] >> - (WORD_BIT_SIZE-word_offset)); - /* and the upper part of the right half and shift it left to - * its position */ - /* for our example that would be: word[0] = 9800 + 0076 = - * 9876 */ - } - /* now for our last word, i==word_num, we only have its "left" half. - * that's the 1000 word in our example.*/ - - seq_bits[i] = (seq_bits[i - word_num] << word_offset); - - /* pad the rest with 0, if there is anything */ - i--; - - for (; i >= 0; i--) - seq_bits[i] = 0; -} - -static void bit_reset_window(unsigned long *seq_bits) -{ - int i; - for (i = 0; i < NUM_WORDS; i++) - seq_bits[i] = 0; + bitmap_shift_left(seq_bits, seq_bits, n, TQ_LOCAL_WINDOW_SIZE); } @@ -137,7 +50,7 @@ int bit_get_packet(void *priv, unsigned long *seq_bits, if ((seq_num_diff <= 0) && (seq_num_diff > -TQ_LOCAL_WINDOW_SIZE)) { if (set_mark) - bit_mark(seq_bits, -seq_num_diff); + bat_set_bit(seq_bits, -seq_num_diff); return 0; } @@ -145,10 +58,10 @@ int bit_get_packet(void *priv, unsigned long *seq_bits, * set the mark if required */ if ((seq_num_diff > 0) && (seq_num_diff < TQ_LOCAL_WINDOW_SIZE)) { - bit_shift(seq_bits, seq_num_diff); + bat_bitmap_shift_left(seq_bits, seq_num_diff); if (set_mark) - bit_mark(seq_bits, 0); + bat_set_bit(seq_bits, 0); return 1; } @@ -159,9 +72,9 @@ int bit_get_packet(void *priv, unsigned long *seq_bits, bat_dbg(DBG_BATMAN, bat_priv, "We missed a lot of packets (%i) !\n", seq_num_diff - 1); - bit_reset_window(seq_bits); + bitmap_zero(seq_bits, TQ_LOCAL_WINDOW_SIZE); if (set_mark) - bit_mark(seq_bits, 0); + bat_set_bit(seq_bits, 0); return 1; } @@ -176,9 +89,9 @@ int bit_get_packet(void *priv, unsigned long *seq_bits, bat_dbg(DBG_BATMAN, bat_priv, "Other host probably restarted!\n"); - bit_reset_window(seq_bits); + bitmap_zero(seq_bits, TQ_LOCAL_WINDOW_SIZE); if (set_mark) - bit_mark(seq_bits, 0); + bat_set_bit(seq_bits, 0); return 1; } @@ -186,16 +99,3 @@ int bit_get_packet(void *priv, unsigned long *seq_bits, /* never reached */ return 0; } - -/* count the hamming weight, how many good packets did we receive? just count - * the 1's. - */ -int bit_packet_count(const unsigned long *seq_bits) -{ - int i, hamming = 0; - - for (i = 0; i < NUM_WORDS; i++) - hamming += hweight_long(seq_bits[i]); - - return hamming; -} diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index c6135728a68..1835c15cda4 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -22,23 +22,33 @@ #ifndef _NET_BATMAN_ADV_BITARRAY_H_ #define _NET_BATMAN_ADV_BITARRAY_H_ -#define WORD_BIT_SIZE (sizeof(unsigned long) * 8) - /* returns true if the corresponding bit in the given seq_bits indicates true * and curr_seqno is within range of last_seqno */ -int get_bit_status(const unsigned long *seq_bits, uint32_t last_seqno, - uint32_t curr_seqno); +static inline int bat_test_bit(const unsigned long *seq_bits, + uint32_t last_seqno, uint32_t curr_seqno) +{ + int32_t diff; + + diff = last_seqno - curr_seqno; + if (diff < 0 || diff >= TQ_LOCAL_WINDOW_SIZE) + return 0; + else + return test_bit(diff, seq_bits); +} /* turn corresponding bit on, so we can remember that we got the packet */ -void bit_mark(unsigned long *seq_bits, int32_t n); +static inline void bat_set_bit(unsigned long *seq_bits, int32_t n) +{ + /* if too old, just drop it */ + if (n < 0 || n >= TQ_LOCAL_WINDOW_SIZE) + return; + set_bit(n, seq_bits); /* turn the position on */ +} /* receive and process one packet, returns 1 if received seq_num is considered * new, 0 if old */ int bit_get_packet(void *priv, unsigned long *seq_bits, int32_t seq_num_diff, int set_mark); -/* count the hamming weight, how many good packets did we receive? */ -int bit_packet_count(const unsigned long *seq_bits); - #endif /* _NET_BATMAN_ADV_BITARRAY_H_ */ diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c new file mode 100644 index 00000000000..8bf97515a77 --- /dev/null +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -0,0 +1,1580 @@ +/* + * Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: + * + * Simon Wunderlich + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA + * + */ + +#include "main.h" +#include "hash.h" +#include "hard-interface.h" +#include "originator.h" +#include "bridge_loop_avoidance.h" +#include "translation-table.h" +#include "send.h" + +#include <linux/etherdevice.h> +#include <linux/crc16.h> +#include <linux/if_arp.h> +#include <net/arp.h> +#include <linux/if_vlan.h> + +static const uint8_t announce_mac[4] = {0x43, 0x05, 0x43, 0x05}; + +static void bla_periodic_work(struct work_struct *work); +static void bla_send_announce(struct bat_priv *bat_priv, + struct backbone_gw *backbone_gw); + +/* return the index of the claim */ +static inline uint32_t choose_claim(const void *data, uint32_t size) +{ + const unsigned char *key = data; + uint32_t hash = 0; + size_t i; + + for (i = 0; i < ETH_ALEN + sizeof(short); i++) { + hash += key[i]; + hash += (hash << 10); + hash ^= (hash >> 6); + } + + hash += (hash << 3); + hash ^= (hash >> 11); + hash += (hash << 15); + + return hash % size; +} + +/* return the index of the backbone gateway */ +static inline uint32_t choose_backbone_gw(const void *data, uint32_t size) +{ + const unsigned char *key = data; + uint32_t hash = 0; + size_t i; + + for (i = 0; i < ETH_ALEN + sizeof(short); i++) { + hash += key[i]; + hash += (hash << 10); + hash ^= (hash >> 6); + } + + hash += (hash << 3); + hash ^= (hash >> 11); + hash += (hash << 15); + + return hash % size; +} + + +/* compares address and vid of two backbone gws */ +static int compare_backbone_gw(const struct hlist_node *node, const void *data2) +{ + const void *data1 = container_of(node, struct backbone_gw, + hash_entry); + + return (memcmp(data1, data2, ETH_ALEN + sizeof(short)) == 0 ? 1 : 0); +} + +/* compares address and vid of two claims */ +static int compare_claim(const struct hlist_node *node, const void *data2) +{ + const void *data1 = container_of(node, struct claim, + hash_entry); + + return (memcmp(data1, data2, ETH_ALEN + sizeof(short)) == 0 ? 1 : 0); +} + +/* free a backbone gw */ +static void backbone_gw_free_ref(struct backbone_gw *backbone_gw) +{ + if (atomic_dec_and_test(&backbone_gw->refcount)) + kfree_rcu(backbone_gw, rcu); +} + +/* finally deinitialize the claim */ +static void claim_free_rcu(struct rcu_head *rcu) +{ + struct claim *claim; + + claim = container_of(rcu, struct claim, rcu); + + backbone_gw_free_ref(claim->backbone_gw); + kfree(claim); +} + +/* free a claim, call claim_free_rcu if its the last reference */ +static void claim_free_ref(struct claim *claim) +{ + if (atomic_dec_and_test(&claim->refcount)) + call_rcu(&claim->rcu, claim_free_rcu); +} + +/** + * @bat_priv: the bat priv with all the soft interface information + * @data: search data (may be local/static data) + * + * looks for a claim in the hash, and returns it if found + * or NULL otherwise. + */ +static struct claim *claim_hash_find(struct bat_priv *bat_priv, + struct claim *data) +{ + struct hashtable_t *hash = bat_priv->claim_hash; + struct hlist_head *head; + struct hlist_node *node; + struct claim *claim; + struct claim *claim_tmp = NULL; + int index; + + if (!hash) + return NULL; + + index = choose_claim(data, hash->size); + head = &hash->table[index]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(claim, node, head, hash_entry) { + if (!compare_claim(&claim->hash_entry, data)) + continue; + + if (!atomic_inc_not_zero(&claim->refcount)) + continue; + + claim_tmp = claim; + break; + } + rcu_read_unlock(); + + return claim_tmp; +} + +/** + * @bat_priv: the bat priv with all the soft interface information + * @addr: the address of the originator + * @vid: the VLAN ID + * + * looks for a claim in the hash, and returns it if found + * or NULL otherwise. + */ +static struct backbone_gw *backbone_hash_find(struct bat_priv *bat_priv, + uint8_t *addr, short vid) +{ + struct hashtable_t *hash = bat_priv->backbone_hash; + struct hlist_head *head; + struct hlist_node *node; + struct backbone_gw search_entry, *backbone_gw; + struct backbone_gw *backbone_gw_tmp = NULL; + int index; + + if (!hash) + return NULL; + + memcpy(search_entry.orig, addr, ETH_ALEN); + search_entry.vid = vid; + + index = choose_backbone_gw(&search_entry, hash->size); + head = &hash->table[index]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(backbone_gw, node, head, hash_entry) { + if (!compare_backbone_gw(&backbone_gw->hash_entry, + &search_entry)) + continue; + + if (!atomic_inc_not_zero(&backbone_gw->refcount)) + continue; + + backbone_gw_tmp = backbone_gw; + break; + } + rcu_read_unlock(); + + return backbone_gw_tmp; +} + +/* delete all claims for a backbone */ +static void bla_del_backbone_claims(struct backbone_gw *backbone_gw) +{ + struct hashtable_t *hash; + struct hlist_node *node, *node_tmp; + struct hlist_head *head; + struct claim *claim; + int i; + spinlock_t *list_lock; /* protects write access to the hash lists */ + + hash = backbone_gw->bat_priv->claim_hash; + if (!hash) + return; + + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + list_lock = &hash->list_locks[i]; + + spin_lock_bh(list_lock); + hlist_for_each_entry_safe(claim, node, node_tmp, + head, hash_entry) { + + if (claim->backbone_gw != backbone_gw) + continue; + + claim_free_ref(claim); + hlist_del_rcu(node); + } + spin_unlock_bh(list_lock); + } + + /* all claims gone, intialize CRC */ + backbone_gw->crc = BLA_CRC_INIT; +} + +/** + * @bat_priv: the bat priv with all the soft interface information + * @orig: the mac address to be announced within the claim + * @vid: the VLAN ID + * @claimtype: the type of the claim (CLAIM, UNCLAIM, ANNOUNCE, ...) + * + * sends a claim frame according to the provided info. + */ +static void bla_send_claim(struct bat_priv *bat_priv, uint8_t *mac, + short vid, int claimtype) +{ + struct sk_buff *skb; + struct ethhdr *ethhdr; + struct hard_iface *primary_if; + struct net_device *soft_iface; + uint8_t *hw_src; + struct bla_claim_dst local_claim_dest; + uint32_t zeroip = 0; + + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + return; + + memcpy(&local_claim_dest, &bat_priv->claim_dest, + sizeof(local_claim_dest)); + local_claim_dest.type = claimtype; + + soft_iface = primary_if->soft_iface; + + skb = arp_create(ARPOP_REPLY, ETH_P_ARP, + /* IP DST: 0.0.0.0 */ + zeroip, + primary_if->soft_iface, + /* IP SRC: 0.0.0.0 */ + zeroip, + /* Ethernet DST: Broadcast */ + NULL, + /* Ethernet SRC/HW SRC: originator mac */ + primary_if->net_dev->dev_addr, + /* HW DST: FF:43:05:XX:00:00 + * with XX = claim type + * and YY:YY = group id + */ + (uint8_t *)&local_claim_dest); + + if (!skb) + goto out; + + ethhdr = (struct ethhdr *)skb->data; + hw_src = (uint8_t *)ethhdr + ETH_HLEN + sizeof(struct arphdr); + + /* now we pretend that the client would have sent this ... */ + switch (claimtype) { + case CLAIM_TYPE_ADD: + /* normal claim frame + * set Ethernet SRC to the clients mac + */ + memcpy(ethhdr->h_source, mac, ETH_ALEN); + bat_dbg(DBG_BLA, bat_priv, + "bla_send_claim(): CLAIM %pM on vid %d\n", mac, vid); + break; + case CLAIM_TYPE_DEL: + /* unclaim frame + * set HW SRC to the clients mac + */ + memcpy(hw_src, mac, ETH_ALEN); + bat_dbg(DBG_BLA, bat_priv, + "bla_send_claim(): UNCLAIM %pM on vid %d\n", mac, vid); + break; + case CLAIM_TYPE_ANNOUNCE: + /* announcement frame + * set HW SRC to the special mac containg the crc + */ + memcpy(hw_src, mac, ETH_ALEN); + bat_dbg(DBG_BLA, bat_priv, + "bla_send_claim(): ANNOUNCE of %pM on vid %d\n", + ethhdr->h_source, vid); + break; + case CLAIM_TYPE_REQUEST: + /* request frame + * set HW SRC to the special mac containg the crc + */ + memcpy(hw_src, mac, ETH_ALEN); + memcpy(ethhdr->h_dest, mac, ETH_ALEN); + bat_dbg(DBG_BLA, bat_priv, + "bla_send_claim(): REQUEST of %pM to %pMon vid %d\n", + ethhdr->h_source, ethhdr->h_dest, vid); + break; + + } + + if (vid != -1) + skb = vlan_insert_tag(skb, vid); + + skb_reset_mac_header(skb); + skb->protocol = eth_type_trans(skb, soft_iface); + bat_priv->stats.rx_packets++; + bat_priv->stats.rx_bytes += skb->len + ETH_HLEN; + soft_iface->last_rx = jiffies; + + netif_rx(skb); +out: + if (primary_if) + hardif_free_ref(primary_if); +} + +/** + * @bat_priv: the bat priv with all the soft interface information + * @orig: the mac address of the originator + * @vid: the VLAN ID + * + * searches for the backbone gw or creates a new one if it could not + * be found. + */ +static struct backbone_gw *bla_get_backbone_gw(struct bat_priv *bat_priv, + uint8_t *orig, short vid) +{ + struct backbone_gw *entry; + struct orig_node *orig_node; + int hash_added; + + entry = backbone_hash_find(bat_priv, orig, vid); + + if (entry) + return entry; + + bat_dbg(DBG_BLA, bat_priv, + "bla_get_backbone_gw(): not found (%pM, %d), creating new entry\n", + orig, vid); + + entry = kzalloc(sizeof(*entry), GFP_ATOMIC); + if (!entry) + return NULL; + + entry->vid = vid; + entry->lasttime = jiffies; + entry->crc = BLA_CRC_INIT; + entry->bat_priv = bat_priv; + atomic_set(&entry->request_sent, 0); + memcpy(entry->orig, orig, ETH_ALEN); + + /* one for the hash, one for returning */ + atomic_set(&entry->refcount, 2); + + hash_added = hash_add(bat_priv->backbone_hash, compare_backbone_gw, + choose_backbone_gw, entry, &entry->hash_entry); + + if (unlikely(hash_added != 0)) { + /* hash failed, free the structure */ + kfree(entry); + return NULL; + } + + /* this is a gateway now, remove any tt entries */ + orig_node = orig_hash_find(bat_priv, orig); + if (orig_node) { + tt_global_del_orig(bat_priv, orig_node, + "became a backbone gateway"); + orig_node_free_ref(orig_node); + } + return entry; +} + +/* update or add the own backbone gw to make sure we announce + * where we receive other backbone gws + */ +static void bla_update_own_backbone_gw(struct bat_priv *bat_priv, + struct hard_iface *primary_if, + short vid) +{ + struct backbone_gw *backbone_gw; + + backbone_gw = bla_get_backbone_gw(bat_priv, + primary_if->net_dev->dev_addr, vid); + if (unlikely(!backbone_gw)) + return; + + backbone_gw->lasttime = jiffies; + backbone_gw_free_ref(backbone_gw); +} + +/** + * @bat_priv: the bat priv with all the soft interface information + * @vid: the vid where the request came on + * + * Repeat all of our own claims, and finally send an ANNOUNCE frame + * to allow the requester another check if the CRC is correct now. + */ +static void bla_answer_request(struct bat_priv *bat_priv, + struct hard_iface *primary_if, short vid) +{ + struct hlist_node *node; + struct hlist_head *head; + struct hashtable_t *hash; + struct claim *claim; + struct backbone_gw *backbone_gw; + int i; + + bat_dbg(DBG_BLA, bat_priv, + "bla_answer_request(): received a claim request, send all of our own claims again\n"); + + backbone_gw = backbone_hash_find(bat_priv, + primary_if->net_dev->dev_addr, vid); + if (!backbone_gw) + return; + + hash = bat_priv->claim_hash; + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(claim, node, head, hash_entry) { + /* only own claims are interesting */ + if (claim->backbone_gw != backbone_gw) + continue; + + bla_send_claim(bat_priv, claim->addr, claim->vid, + CLAIM_TYPE_ADD); + } + rcu_read_unlock(); + } + + /* finally, send an announcement frame */ + bla_send_announce(bat_priv, backbone_gw); + backbone_gw_free_ref(backbone_gw); +} + +/** + * @backbone_gw: the backbone gateway from whom we are out of sync + * + * When the crc is wrong, ask the backbone gateway for a full table update. + * After the request, it will repeat all of his own claims and finally + * send an announcement claim with which we can check again. + */ +static void bla_send_request(struct backbone_gw *backbone_gw) +{ + /* first, remove all old entries */ + bla_del_backbone_claims(backbone_gw); + + bat_dbg(DBG_BLA, backbone_gw->bat_priv, + "Sending REQUEST to %pM\n", + backbone_gw->orig); + + /* send request */ + bla_send_claim(backbone_gw->bat_priv, backbone_gw->orig, + backbone_gw->vid, CLAIM_TYPE_REQUEST); + + /* no local broadcasts should be sent or received, for now. */ + if (!atomic_read(&backbone_gw->request_sent)) { + atomic_inc(&backbone_gw->bat_priv->bla_num_requests); + atomic_set(&backbone_gw->request_sent, 1); + } +} + +/** + * @bat_priv: the bat priv with all the soft interface information + * @backbone_gw: our backbone gateway which should be announced + * + * This function sends an announcement. It is called from multiple + * places. + */ +static void bla_send_announce(struct bat_priv *bat_priv, + struct backbone_gw *backbone_gw) +{ + uint8_t mac[ETH_ALEN]; + uint16_t crc; + + memcpy(mac, announce_mac, 4); + crc = htons(backbone_gw->crc); + memcpy(&mac[4], (uint8_t *)&crc, 2); + + bla_send_claim(bat_priv, mac, backbone_gw->vid, CLAIM_TYPE_ANNOUNCE); + +} + +/** + * @bat_priv: the bat priv with all the soft interface information + * @mac: the mac address of the claim + * @vid: the VLAN ID of the frame + * @backbone_gw: the backbone gateway which claims it + * + * Adds a claim in the claim hash. + */ +static void bla_add_claim(struct bat_priv *bat_priv, const uint8_t *mac, + const short vid, struct backbone_gw *backbone_gw) +{ + struct claim *claim; + struct claim search_claim; + int hash_added; + + memcpy(search_claim.addr, mac, ETH_ALEN); + search_claim.vid = vid; + claim = claim_hash_find(bat_priv, &search_claim); + + /* create a new claim entry if it does not exist yet. */ + if (!claim) { + claim = kzalloc(sizeof(*claim), GFP_ATOMIC); + if (!claim) + return; + + memcpy(claim->addr, mac, ETH_ALEN); + claim->vid = vid; + claim->lasttime = jiffies; + claim->backbone_gw = backbone_gw; + + atomic_set(&claim->refcount, 2); + bat_dbg(DBG_BLA, bat_priv, + "bla_add_claim(): adding new entry %pM, vid %d to hash ...\n", + mac, vid); + hash_added = hash_add(bat_priv->claim_hash, compare_claim, + choose_claim, claim, &claim->hash_entry); + + if (unlikely(hash_added != 0)) { + /* only local changes happened. */ + kfree(claim); + return; + } + } else { + claim->lasttime = jiffies; + if (claim->backbone_gw == backbone_gw) + /* no need to register a new backbone */ + goto claim_free_ref; + + bat_dbg(DBG_BLA, bat_priv, + "bla_add_claim(): changing ownership for %pM, vid %d\n", + mac, vid); + + claim->backbone_gw->crc ^= + crc16(0, claim->addr, ETH_ALEN); + backbone_gw_free_ref(claim->backbone_gw); + + } + /* set (new) backbone gw */ + atomic_inc(&backbone_gw->refcount); + claim->backbone_gw = backbone_gw; + + backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); + backbone_gw->lasttime = jiffies; + +claim_free_ref: + claim_free_ref(claim); +} + +/* Delete a claim from the claim hash which has the + * given mac address and vid. + */ +static void bla_del_claim(struct bat_priv *bat_priv, const uint8_t *mac, + const short vid) +{ + struct claim search_claim, *claim; + + memcpy(search_claim.addr, mac, ETH_ALEN); + search_claim.vid = vid; + claim = claim_hash_find(bat_priv, &search_claim); + if (!claim) + return; + + bat_dbg(DBG_BLA, bat_priv, "bla_del_claim(): %pM, vid %d\n", mac, vid); + + hash_remove(bat_priv->claim_hash, compare_claim, choose_claim, claim); + claim_free_ref(claim); /* reference from the hash is gone */ + + claim->backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); + + /* don't need the reference from hash_find() anymore */ + claim_free_ref(claim); +} + +/* check for ANNOUNCE frame, return 1 if handled */ +static int handle_announce(struct bat_priv *bat_priv, + uint8_t *an_addr, uint8_t *backbone_addr, short vid) +{ + struct backbone_gw *backbone_gw; + uint16_t crc; + + if (memcmp(an_addr, announce_mac, 4) != 0) + return 0; + + backbone_gw = bla_get_backbone_gw(bat_priv, backbone_addr, vid); + + if (unlikely(!backbone_gw)) + return 1; + + + /* handle as ANNOUNCE frame */ + backbone_gw->lasttime = jiffies; + crc = ntohs(*((uint16_t *)(&an_addr[4]))); + + bat_dbg(DBG_BLA, bat_priv, + "handle_announce(): ANNOUNCE vid %d (sent by %pM)... CRC = %04x\n", + vid, backbone_gw->orig, crc); + + if (backbone_gw->crc != crc) { + bat_dbg(DBG_BLA, backbone_gw->bat_priv, + "handle_announce(): CRC FAILED for %pM/%d (my = %04x, sent = %04x)\n", + backbone_gw->orig, backbone_gw->vid, backbone_gw->crc, + crc); + + bla_send_request(backbone_gw); + } else { + /* if we have sent a request and the crc was OK, + * we can allow traffic again. + */ + if (atomic_read(&backbone_gw->request_sent)) { + atomic_dec(&backbone_gw->bat_priv->bla_num_requests); + atomic_set(&backbone_gw->request_sent, 0); + } + } + + backbone_gw_free_ref(backbone_gw); + return 1; +} + +/* check for REQUEST frame, return 1 if handled */ +static int handle_request(struct bat_priv *bat_priv, + struct hard_iface *primary_if, + uint8_t *backbone_addr, + struct ethhdr *ethhdr, short vid) +{ + /* check for REQUEST frame */ + if (!compare_eth(backbone_addr, ethhdr->h_dest)) + return 0; + + /* sanity check, this should not happen on a normal switch, + * we ignore it in this case. + */ + if (!compare_eth(ethhdr->h_dest, primary_if->net_dev->dev_addr)) + return 1; + + bat_dbg(DBG_BLA, bat_priv, + "handle_request(): REQUEST vid %d (sent by %pM)...\n", + vid, ethhdr->h_source); + + bla_answer_request(bat_priv, primary_if, vid); + return 1; +} + +/* check for UNCLAIM frame, return 1 if handled */ +static int handle_unclaim(struct bat_priv *bat_priv, + struct hard_iface *primary_if, + uint8_t *backbone_addr, + uint8_t *claim_addr, short vid) +{ + struct backbone_gw *backbone_gw; + + /* unclaim in any case if it is our own */ + if (primary_if && compare_eth(backbone_addr, + primary_if->net_dev->dev_addr)) + bla_send_claim(bat_priv, claim_addr, vid, CLAIM_TYPE_DEL); + + backbone_gw = backbone_hash_find(bat_priv, backbone_addr, vid); + + if (!backbone_gw) + return 1; + + /* this must be an UNCLAIM frame */ + bat_dbg(DBG_BLA, bat_priv, + "handle_unclaim(): UNCLAIM %pM on vid %d (sent by %pM)...\n", + claim_addr, vid, backbone_gw->orig); + + bla_del_claim(bat_priv, claim_addr, vid); + backbone_gw_free_ref(backbone_gw); + return 1; +} + +/* check for CLAIM frame, return 1 if handled */ +static int handle_claim(struct bat_priv *bat_priv, + struct hard_iface *primary_if, uint8_t *backbone_addr, + uint8_t *claim_addr, short vid) +{ + struct backbone_gw *backbone_gw; + + /* register the gateway if not yet available, and add the claim. */ + + backbone_gw = bla_get_backbone_gw(bat_priv, backbone_addr, vid); + + if (unlikely(!backbone_gw)) + return 1; + + /* this must be a CLAIM frame */ + bla_add_claim(bat_priv, claim_addr, vid, backbone_gw); + if (compare_eth(backbone_addr, primary_if->net_dev->dev_addr)) + bla_send_claim(bat_priv, claim_addr, vid, CLAIM_TYPE_ADD); + + /* TODO: we could call something like tt_local_del() here. */ + + backbone_gw_free_ref(backbone_gw); + return 1; +} + +/** + * @bat_priv: the bat priv with all the soft interface information + * @hw_src: the Hardware source in the ARP Header + * @hw_dst: the Hardware destination in the ARP Header + * @ethhdr: pointer to the Ethernet header of the claim frame + * + * checks if it is a claim packet and if its on the same group. + * This function also applies the group ID of the sender + * if it is in the same mesh. + * + * returns: + * 2 - if it is a claim packet and on the same group + * 1 - if is a claim packet from another group + * 0 - if it is not a claim packet + */ +static int check_claim_group(struct bat_priv *bat_priv, + struct hard_iface *primary_if, + uint8_t *hw_src, uint8_t *hw_dst, + struct ethhdr *ethhdr) +{ + uint8_t *backbone_addr; + struct orig_node *orig_node; + struct bla_claim_dst *bla_dst, *bla_dst_own; + + bla_dst = (struct bla_claim_dst *)hw_dst; + bla_dst_own = &bat_priv->claim_dest; + + /* check if it is a claim packet in general */ + if (memcmp(bla_dst->magic, bla_dst_own->magic, + sizeof(bla_dst->magic)) != 0) + return 0; + + /* if announcement packet, use the source, + * otherwise assume it is in the hw_src + */ + switch (bla_dst->type) { + case CLAIM_TYPE_ADD: + backbone_addr = hw_src; + break; + case CLAIM_TYPE_REQUEST: + case CLAIM_TYPE_ANNOUNCE: + case CLAIM_TYPE_DEL: + backbone_addr = ethhdr->h_source; + break; + default: + return 0; + } + + /* don't accept claim frames from ourselves */ + if (compare_eth(backbone_addr, primary_if->net_dev->dev_addr)) + return 0; + + /* if its already the same group, it is fine. */ + if (bla_dst->group == bla_dst_own->group) + return 2; + + /* lets see if this originator is in our mesh */ + orig_node = orig_hash_find(bat_priv, backbone_addr); + + /* dont accept claims from gateways which are not in + * the same mesh or group. + */ + if (!orig_node) + return 1; + + /* if our mesh friends mac is bigger, use it for ourselves. */ + if (ntohs(bla_dst->group) > ntohs(bla_dst_own->group)) { + bat_dbg(DBG_BLA, bat_priv, + "taking other backbones claim group: %04x\n", + ntohs(bla_dst->group)); + bla_dst_own->group = bla_dst->group; + } + + orig_node_free_ref(orig_node); + + return 2; +} + + +/** + * @bat_priv: the bat priv with all the soft interface information + * @skb: the frame to be checked + * + * Check if this is a claim frame, and process it accordingly. + * + * returns 1 if it was a claim frame, otherwise return 0 to + * tell the callee that it can use the frame on its own. + */ +static int bla_process_claim(struct bat_priv *bat_priv, + struct hard_iface *primary_if, + struct sk_buff *skb) +{ + struct ethhdr *ethhdr; + struct vlan_ethhdr *vhdr; + struct arphdr *arphdr; + uint8_t *hw_src, *hw_dst; + struct bla_claim_dst *bla_dst; + uint16_t proto; + int headlen; + short vid = -1; + int ret; + + ethhdr = (struct ethhdr *)skb_mac_header(skb); + + if (ntohs(ethhdr->h_proto) == ETH_P_8021Q) { + vhdr = (struct vlan_ethhdr *)ethhdr; + vid = ntohs(vhdr->h_vlan_TCI) & VLAN_VID_MASK; + proto = ntohs(vhdr->h_vlan_encapsulated_proto); + headlen = sizeof(*vhdr); + } else { + proto = ntohs(ethhdr->h_proto); + headlen = ETH_HLEN; + } + + if (proto != ETH_P_ARP) + return 0; /* not a claim frame */ + + /* this must be a ARP frame. check if it is a claim. */ + + if (unlikely(!pskb_may_pull(skb, headlen + arp_hdr_len(skb->dev)))) + return 0; + + /* pskb_may_pull() may have modified the pointers, get ethhdr again */ + ethhdr = (struct ethhdr *)skb_mac_header(skb); + arphdr = (struct arphdr *)((uint8_t *)ethhdr + headlen); + + /* Check whether the ARP frame carries a valid + * IP information + */ + + if (arphdr->ar_hrd != htons(ARPHRD_ETHER)) + return 0; + if (arphdr->ar_pro != htons(ETH_P_IP)) + return 0; + if (arphdr->ar_hln != ETH_ALEN) + return 0; + if (arphdr->ar_pln != 4) + return 0; + + hw_src = (uint8_t *)arphdr + sizeof(struct arphdr); + hw_dst = hw_src + ETH_ALEN + 4; + bla_dst = (struct bla_claim_dst *)hw_dst; + + /* check if it is a claim frame. */ + ret = check_claim_group(bat_priv, primary_if, hw_src, hw_dst, ethhdr); + if (ret == 1) + bat_dbg(DBG_BLA, bat_priv, + "bla_process_claim(): received a claim frame from another group. From: %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n", + ethhdr->h_source, vid, hw_src, hw_dst); + + if (ret < 2) + return ret; + + /* become a backbone gw ourselves on this vlan if not happened yet */ + bla_update_own_backbone_gw(bat_priv, primary_if, vid); + + /* check for the different types of claim frames ... */ + switch (bla_dst->type) { + case CLAIM_TYPE_ADD: + if (handle_claim(bat_priv, primary_if, hw_src, + ethhdr->h_source, vid)) + return 1; + break; + case CLAIM_TYPE_DEL: + if (handle_unclaim(bat_priv, primary_if, + ethhdr->h_source, hw_src, vid)) + return 1; + break; + + case CLAIM_TYPE_ANNOUNCE: + if (handle_announce(bat_priv, hw_src, ethhdr->h_source, vid)) + return 1; + break; + case CLAIM_TYPE_REQUEST: + if (handle_request(bat_priv, primary_if, hw_src, ethhdr, vid)) + return 1; + break; + } + + bat_dbg(DBG_BLA, bat_priv, + "bla_process_claim(): ERROR - this looks like a claim frame, but is useless. eth src %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n", + ethhdr->h_source, vid, hw_src, hw_dst); + return 1; +} + +/* Check when we last heard from other nodes, and remove them in case of + * a time out, or clean all backbone gws if now is set. + */ +static void bla_purge_backbone_gw(struct bat_priv *bat_priv, int now) +{ + struct backbone_gw *backbone_gw; + struct hlist_node *node, *node_tmp; + struct hlist_head *head; + struct hashtable_t *hash; + spinlock_t *list_lock; /* protects write access to the hash lists */ + int i; + + hash = bat_priv->backbone_hash; + if (!hash) + return; + + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + list_lock = &hash->list_locks[i]; + + spin_lock_bh(list_lock); + hlist_for_each_entry_safe(backbone_gw, node, node_tmp, + head, hash_entry) { + if (now) + goto purge_now; + if (!has_timed_out(backbone_gw->lasttime, + BLA_BACKBONE_TIMEOUT)) + continue; + + bat_dbg(DBG_BLA, backbone_gw->bat_priv, + "bla_purge_backbone_gw(): backbone gw %pM timed out\n", + backbone_gw->orig); + +purge_now: + /* don't wait for the pending request anymore */ + if (atomic_read(&backbone_gw->request_sent)) + atomic_dec(&bat_priv->bla_num_requests); + + bla_del_backbone_claims(backbone_gw); + + hlist_del_rcu(node); + backbone_gw_free_ref(backbone_gw); + } + spin_unlock_bh(list_lock); + } +} + +/** + * @bat_priv: the bat priv with all the soft interface information + * @primary_if: the selected primary interface, may be NULL if now is set + * @now: whether the whole hash shall be wiped now + * + * Check when we heard last time from our own claims, and remove them in case of + * a time out, or clean all claims if now is set + */ +static void bla_purge_claims(struct bat_priv *bat_priv, + struct hard_iface *primary_if, int now) +{ + struct claim *claim; + struct hlist_node *node; + struct hlist_head *head; + struct hashtable_t *hash; + int i; + + hash = bat_priv->claim_hash; + if (!hash) + return; + + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(claim, node, head, hash_entry) { + if (now) + goto purge_now; + if (!compare_eth(claim->backbone_gw->orig, + primary_if->net_dev->dev_addr)) + continue; + if (!has_timed_out(claim->lasttime, + BLA_CLAIM_TIMEOUT)) + continue; + + bat_dbg(DBG_BLA, bat_priv, + "bla_purge_claims(): %pM, vid %d, time out\n", + claim->addr, claim->vid); + +purge_now: + handle_unclaim(bat_priv, primary_if, + claim->backbone_gw->orig, + claim->addr, claim->vid); + } + rcu_read_unlock(); + } +} + +/** + * @bat_priv: the bat priv with all the soft interface information + * @primary_if: the new selected primary_if + * @oldif: the old primary interface, may be NULL + * + * Update the backbone gateways when the own orig address changes. + * + */ +void bla_update_orig_address(struct bat_priv *bat_priv, + struct hard_iface *primary_if, + struct hard_iface *oldif) +{ + struct backbone_gw *backbone_gw; + struct hlist_node *node; + struct hlist_head *head; + struct hashtable_t *hash; + int i; + + /* reset bridge loop avoidance group id */ + bat_priv->claim_dest.group = + htons(crc16(0, primary_if->net_dev->dev_addr, ETH_ALEN)); + + if (!oldif) { + bla_purge_claims(bat_priv, NULL, 1); + bla_purge_backbone_gw(bat_priv, 1); + return; + } + + hash = bat_priv->backbone_hash; + if (!hash) + return; + + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(backbone_gw, node, head, hash_entry) { + /* own orig still holds the old value. */ + if (!compare_eth(backbone_gw->orig, + oldif->net_dev->dev_addr)) + continue; + + memcpy(backbone_gw->orig, + primary_if->net_dev->dev_addr, ETH_ALEN); + /* send an announce frame so others will ask for our + * claims and update their tables. + */ + bla_send_announce(bat_priv, backbone_gw); + } + rcu_read_unlock(); + } +} + + + +/* (re)start the timer */ +static void bla_start_timer(struct bat_priv *bat_priv) +{ + INIT_DELAYED_WORK(&bat_priv->bla_work, bla_periodic_work); + queue_delayed_work(bat_event_workqueue, &bat_priv->bla_work, + msecs_to_jiffies(BLA_PERIOD_LENGTH)); +} + +/* periodic work to do: + * * purge structures when they are too old + * * send announcements + */ +static void bla_periodic_work(struct work_struct *work) +{ + struct delayed_work *delayed_work = + container_of(work, struct delayed_work, work); + struct bat_priv *bat_priv = + container_of(delayed_work, struct bat_priv, bla_work); + struct hlist_node *node; + struct hlist_head *head; + struct backbone_gw *backbone_gw; + struct hashtable_t *hash; + struct hard_iface *primary_if; + int i; + + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; + + bla_purge_claims(bat_priv, primary_if, 0); + bla_purge_backbone_gw(bat_priv, 0); + + if (!atomic_read(&bat_priv->bridge_loop_avoidance)) + goto out; + + hash = bat_priv->backbone_hash; + if (!hash) + goto out; + + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(backbone_gw, node, head, hash_entry) { + if (!compare_eth(backbone_gw->orig, + primary_if->net_dev->dev_addr)) + continue; + + backbone_gw->lasttime = jiffies; + + bla_send_announce(bat_priv, backbone_gw); + } + rcu_read_unlock(); + } +out: + if (primary_if) + hardif_free_ref(primary_if); + + bla_start_timer(bat_priv); +} + +/* initialize all bla structures */ +int bla_init(struct bat_priv *bat_priv) +{ + int i; + uint8_t claim_dest[ETH_ALEN] = {0xff, 0x43, 0x05, 0x00, 0x00, 0x00}; + struct hard_iface *primary_if; + + bat_dbg(DBG_BLA, bat_priv, "bla hash registering\n"); + + /* setting claim destination address */ + memcpy(&bat_priv->claim_dest.magic, claim_dest, 3); + bat_priv->claim_dest.type = 0; + primary_if = primary_if_get_selected(bat_priv); + if (primary_if) { + bat_priv->claim_dest.group = + htons(crc16(0, primary_if->net_dev->dev_addr, + ETH_ALEN)); + hardif_free_ref(primary_if); + } else { + bat_priv->claim_dest.group = 0; /* will be set later */ + } + + /* initialize the duplicate list */ + for (i = 0; i < DUPLIST_SIZE; i++) + bat_priv->bcast_duplist[i].entrytime = + jiffies - msecs_to_jiffies(DUPLIST_TIMEOUT); + bat_priv->bcast_duplist_curr = 0; + + if (bat_priv->claim_hash) + return 1; + + bat_priv->claim_hash = hash_new(128); + bat_priv->backbone_hash = hash_new(32); + + if (!bat_priv->claim_hash || !bat_priv->backbone_hash) + return -1; + + bat_dbg(DBG_BLA, bat_priv, "bla hashes initialized\n"); + + bla_start_timer(bat_priv); + return 1; +} + +/** + * @bat_priv: the bat priv with all the soft interface information + * @bcast_packet: originator mac address + * @hdr_size: maximum length of the frame + * + * check if it is on our broadcast list. Another gateway might + * have sent the same packet because it is connected to the same backbone, + * so we have to remove this duplicate. + * + * This is performed by checking the CRC, which will tell us + * with a good chance that it is the same packet. If it is furthermore + * sent by another host, drop it. We allow equal packets from + * the same host however as this might be intended. + * + **/ + +int bla_check_bcast_duplist(struct bat_priv *bat_priv, + struct bcast_packet *bcast_packet, + int hdr_size) +{ + int i, length, curr; + uint8_t *content; + uint16_t crc; + struct bcast_duplist_entry *entry; + + length = hdr_size - sizeof(*bcast_packet); + content = (uint8_t *)bcast_packet; + content += sizeof(*bcast_packet); + + /* calculate the crc ... */ + crc = crc16(0, content, length); + + for (i = 0 ; i < DUPLIST_SIZE; i++) { + curr = (bat_priv->bcast_duplist_curr + i) % DUPLIST_SIZE; + entry = &bat_priv->bcast_duplist[curr]; + + /* we can stop searching if the entry is too old ; + * later entries will be even older + */ + if (has_timed_out(entry->entrytime, DUPLIST_TIMEOUT)) + break; + + if (entry->crc != crc) + continue; + + if (compare_eth(entry->orig, bcast_packet->orig)) + continue; + + /* this entry seems to match: same crc, not too old, + * and from another gw. therefore return 1 to forbid it. + */ + return 1; + } + /* not found, add a new entry (overwrite the oldest entry) */ + curr = (bat_priv->bcast_duplist_curr + DUPLIST_SIZE - 1) % DUPLIST_SIZE; + entry = &bat_priv->bcast_duplist[curr]; + entry->crc = crc; + entry->entrytime = jiffies; + memcpy(entry->orig, bcast_packet->orig, ETH_ALEN); + bat_priv->bcast_duplist_curr = curr; + + /* allow it, its the first occurence. */ + return 0; +} + + + +/** + * @bat_priv: the bat priv with all the soft interface information + * @orig: originator mac address + * + * check if the originator is a gateway for any VLAN ID. + * + * returns 1 if it is found, 0 otherwise + * + */ + +int bla_is_backbone_gw_orig(struct bat_priv *bat_priv, uint8_t *orig) +{ + struct hashtable_t *hash = bat_priv->backbone_hash; + struct hlist_head *head; + struct hlist_node *node; + struct backbone_gw *backbone_gw; + int i; + + if (!atomic_read(&bat_priv->bridge_loop_avoidance)) + return 0; + + if (!hash) + return 0; + + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(backbone_gw, node, head, hash_entry) { + if (compare_eth(backbone_gw->orig, orig)) { + rcu_read_unlock(); + return 1; + } + } + rcu_read_unlock(); + } + + return 0; +} + + +/** + * @skb: the frame to be checked + * @orig_node: the orig_node of the frame + * @hdr_size: maximum length of the frame + * + * bla_is_backbone_gw inspects the skb for the VLAN ID and returns 1 + * if the orig_node is also a gateway on the soft interface, otherwise it + * returns 0. + * + */ +int bla_is_backbone_gw(struct sk_buff *skb, + struct orig_node *orig_node, int hdr_size) +{ + struct ethhdr *ethhdr; + struct vlan_ethhdr *vhdr; + struct backbone_gw *backbone_gw; + short vid = -1; + + if (!atomic_read(&orig_node->bat_priv->bridge_loop_avoidance)) + return 0; + + /* first, find out the vid. */ + if (!pskb_may_pull(skb, hdr_size + ETH_HLEN)) + return 0; + + ethhdr = (struct ethhdr *)(((uint8_t *)skb->data) + hdr_size); + + if (ntohs(ethhdr->h_proto) == ETH_P_8021Q) { + if (!pskb_may_pull(skb, hdr_size + sizeof(struct vlan_ethhdr))) + return 0; + + vhdr = (struct vlan_ethhdr *)(((uint8_t *)skb->data) + + hdr_size); + vid = ntohs(vhdr->h_vlan_TCI) & VLAN_VID_MASK; + } + + /* see if this originator is a backbone gw for this VLAN */ + + backbone_gw = backbone_hash_find(orig_node->bat_priv, + orig_node->orig, vid); + if (!backbone_gw) + return 0; + + backbone_gw_free_ref(backbone_gw); + return 1; +} + +/* free all bla structures (for softinterface free or module unload) */ +void bla_free(struct bat_priv *bat_priv) +{ + struct hard_iface *primary_if; + + cancel_delayed_work_sync(&bat_priv->bla_work); + primary_if = primary_if_get_selected(bat_priv); + + if (bat_priv->claim_hash) { + bla_purge_claims(bat_priv, primary_if, 1); + hash_destroy(bat_priv->claim_hash); + bat_priv->claim_hash = NULL; + } + if (bat_priv->backbone_hash) { + bla_purge_backbone_gw(bat_priv, 1); + hash_destroy(bat_priv->backbone_hash); + bat_priv->backbone_hash = NULL; + } + if (primary_if) + hardif_free_ref(primary_if); +} + +/** + * @bat_priv: the bat priv with all the soft interface information + * @skb: the frame to be checked + * @vid: the VLAN ID of the frame + * + * bla_rx avoidance checks if: + * * we have to race for a claim + * * if the frame is allowed on the LAN + * + * in these cases, the skb is further handled by this function and + * returns 1, otherwise it returns 0 and the caller shall further + * process the skb. + * + */ +int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid) +{ + struct ethhdr *ethhdr; + struct claim search_claim, *claim = NULL; + struct hard_iface *primary_if; + int ret; + + ethhdr = (struct ethhdr *)skb_mac_header(skb); + + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + goto handled; + + if (!atomic_read(&bat_priv->bridge_loop_avoidance)) + goto allow; + + + if (unlikely(atomic_read(&bat_priv->bla_num_requests))) + /* don't allow broadcasts while requests are in flight */ + if (is_multicast_ether_addr(ethhdr->h_dest)) + goto handled; + + memcpy(search_claim.addr, ethhdr->h_source, ETH_ALEN); + search_claim.vid = vid; + claim = claim_hash_find(bat_priv, &search_claim); + + if (!claim) { + /* possible optimization: race for a claim */ + /* No claim exists yet, claim it for us! + */ + handle_claim(bat_priv, primary_if, + primary_if->net_dev->dev_addr, + ethhdr->h_source, vid); + goto allow; + } + + /* if it is our own claim ... */ + if (compare_eth(claim->backbone_gw->orig, + primary_if->net_dev->dev_addr)) { + /* ... allow it in any case */ + claim->lasttime = jiffies; + goto allow; + } + + /* if it is a broadcast ... */ + if (is_multicast_ether_addr(ethhdr->h_dest)) { + /* ... drop it. the responsible gateway is in charge. */ + goto handled; + } else { + /* seems the client considers us as its best gateway. + * send a claim and update the claim table + * immediately. + */ + handle_claim(bat_priv, primary_if, + primary_if->net_dev->dev_addr, + ethhdr->h_source, vid); + goto allow; + } +allow: + bla_update_own_backbone_gw(bat_priv, primary_if, vid); + ret = 0; + goto out; + +handled: + kfree_skb(skb); + ret = 1; + +out: + if (primary_if) + hardif_free_ref(primary_if); + if (claim) + claim_free_ref(claim); + return ret; +} + +/** + * @bat_priv: the bat priv with all the soft interface information + * @skb: the frame to be checked + * @vid: the VLAN ID of the frame + * + * bla_tx checks if: + * * a claim was received which has to be processed + * * the frame is allowed on the mesh + * + * in these cases, the skb is further handled by this function and + * returns 1, otherwise it returns 0 and the caller shall further + * process the skb. + * + */ +int bla_tx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid) +{ + struct ethhdr *ethhdr; + struct claim search_claim, *claim = NULL; + struct hard_iface *primary_if; + int ret = 0; + + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; + + if (!atomic_read(&bat_priv->bridge_loop_avoidance)) + goto allow; + + /* in VLAN case, the mac header might not be set. */ + skb_reset_mac_header(skb); + + if (bla_process_claim(bat_priv, primary_if, skb)) + goto handled; + + ethhdr = (struct ethhdr *)skb_mac_header(skb); + + if (unlikely(atomic_read(&bat_priv->bla_num_requests))) + /* don't allow broadcasts while requests are in flight */ + if (is_multicast_ether_addr(ethhdr->h_dest)) + goto handled; + + memcpy(search_claim.addr, ethhdr->h_source, ETH_ALEN); + search_claim.vid = vid; + + claim = claim_hash_find(bat_priv, &search_claim); + + /* if no claim exists, allow it. */ + if (!claim) + goto allow; + + /* check if we are responsible. */ + if (compare_eth(claim->backbone_gw->orig, + primary_if->net_dev->dev_addr)) { + /* if yes, the client has roamed and we have + * to unclaim it. + */ + handle_unclaim(bat_priv, primary_if, + primary_if->net_dev->dev_addr, + ethhdr->h_source, vid); + goto allow; + } + + /* check if it is a multicast/broadcast frame */ + if (is_multicast_ether_addr(ethhdr->h_dest)) { + /* drop it. the responsible gateway has forwarded it into + * the backbone network. + */ + goto handled; + } else { + /* we must allow it. at least if we are + * responsible for the DESTINATION. + */ + goto allow; + } +allow: + bla_update_own_backbone_gw(bat_priv, primary_if, vid); + ret = 0; + goto out; +handled: + ret = 1; +out: + if (primary_if) + hardif_free_ref(primary_if); + if (claim) + claim_free_ref(claim); + return ret; +} + +int bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) +{ + struct net_device *net_dev = (struct net_device *)seq->private; + struct bat_priv *bat_priv = netdev_priv(net_dev); + struct hashtable_t *hash = bat_priv->claim_hash; + struct claim *claim; + struct hard_iface *primary_if; + struct hlist_node *node; + struct hlist_head *head; + uint32_t i; + bool is_own; + int ret = 0; + + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) { + ret = seq_printf(seq, + "BATMAN mesh %s disabled - please specify interfaces to enable it\n", + net_dev->name); + goto out; + } + + if (primary_if->if_status != IF_ACTIVE) { + ret = seq_printf(seq, + "BATMAN mesh %s disabled - primary interface not active\n", + net_dev->name); + goto out; + } + + seq_printf(seq, + "Claims announced for the mesh %s (orig %pM, group id %04x)\n", + net_dev->name, primary_if->net_dev->dev_addr, + ntohs(bat_priv->claim_dest.group)); + seq_printf(seq, " %-17s %-5s %-17s [o] (%-4s)\n", + "Client", "VID", "Originator", "CRC"); + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(claim, node, head, hash_entry) { + is_own = compare_eth(claim->backbone_gw->orig, + primary_if->net_dev->dev_addr); + seq_printf(seq, " * %pM on % 5d by %pM [%c] (%04x)\n", + claim->addr, claim->vid, + claim->backbone_gw->orig, + (is_own ? 'x' : ' '), + claim->backbone_gw->crc); + } + rcu_read_unlock(); + } +out: + if (primary_if) + hardif_free_ref(primary_if); + return ret; +} diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h new file mode 100644 index 00000000000..e39f93acc28 --- /dev/null +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -0,0 +1,98 @@ +/* + * Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: + * + * Simon Wunderlich + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA + * + */ + +#ifndef _NET_BATMAN_ADV_BLA_H_ +#define _NET_BATMAN_ADV_BLA_H_ + +#ifdef CONFIG_BATMAN_ADV_BLA +int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid); +int bla_tx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid); +int bla_is_backbone_gw(struct sk_buff *skb, + struct orig_node *orig_node, int hdr_size); +int bla_claim_table_seq_print_text(struct seq_file *seq, void *offset); +int bla_is_backbone_gw_orig(struct bat_priv *bat_priv, uint8_t *orig); +int bla_check_bcast_duplist(struct bat_priv *bat_priv, + struct bcast_packet *bcast_packet, int hdr_size); +void bla_update_orig_address(struct bat_priv *bat_priv, + struct hard_iface *primary_if, + struct hard_iface *oldif); +int bla_init(struct bat_priv *bat_priv); +void bla_free(struct bat_priv *bat_priv); + +#define BLA_CRC_INIT 0 +#else /* ifdef CONFIG_BATMAN_ADV_BLA */ + +static inline int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, + short vid) +{ + return 0; +} + +static inline int bla_tx(struct bat_priv *bat_priv, struct sk_buff *skb, + short vid) +{ + return 0; +} + +static inline int bla_is_backbone_gw(struct sk_buff *skb, + struct orig_node *orig_node, + int hdr_size) +{ + return 0; +} + +static inline int bla_claim_table_seq_print_text(struct seq_file *seq, + void *offset) +{ + return 0; +} + +static inline int bla_is_backbone_gw_orig(struct bat_priv *bat_priv, + uint8_t *orig) +{ + return 0; +} + +static inline int bla_check_bcast_duplist(struct bat_priv *bat_priv, + struct bcast_packet *bcast_packet, + int hdr_size) +{ + return 0; +} + +static inline void bla_update_orig_address(struct bat_priv *bat_priv, + struct hard_iface *primary_if, + struct hard_iface *oldif) +{ +} + +static inline int bla_init(struct bat_priv *bat_priv) +{ + return 1; +} + +static inline void bla_free(struct bat_priv *bat_priv) +{ +} + +#endif /* ifdef CONFIG_BATMAN_ADV_BLA */ + +#endif /* ifndef _NET_BATMAN_ADV_BLA_H_ */ diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 6f9b9b78f77..47f7186dcef 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -558,10 +558,10 @@ static bool is_type_dhcprequest(struct sk_buff *skb, int header_len) p++; /* ...and then we jump over the data */ - if (pkt_len < *p) + if (pkt_len < 1 + (*p)) goto out; - pkt_len -= *p; - p += (*p); + pkt_len -= 1 + (*p); + p += 1 + (*p); } } out: diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 377897701a8..dc334fa8984 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -28,15 +28,10 @@ #include "bat_sysfs.h" #include "originator.h" #include "hash.h" +#include "bridge_loop_avoidance.h" #include <linux/if_arp.h> - -static int batman_skb_recv(struct sk_buff *skb, - struct net_device *dev, - struct packet_type *ptype, - struct net_device *orig_dev); - void hardif_free_rcu(struct rcu_head *rcu) { struct hard_iface *hard_iface; @@ -107,7 +102,8 @@ out: return hard_iface; } -static void primary_if_update_addr(struct bat_priv *bat_priv) +static void primary_if_update_addr(struct bat_priv *bat_priv, + struct hard_iface *oldif) { struct vis_packet *vis_packet; struct hard_iface *primary_if; @@ -122,6 +118,7 @@ static void primary_if_update_addr(struct bat_priv *bat_priv) memcpy(vis_packet->sender_orig, primary_if->net_dev->dev_addr, ETH_ALEN); + bla_update_orig_address(bat_priv, primary_if, oldif); out: if (primary_if) hardif_free_ref(primary_if); @@ -140,14 +137,15 @@ static void primary_if_select(struct bat_priv *bat_priv, curr_hard_iface = rcu_dereference_protected(bat_priv->primary_if, 1); rcu_assign_pointer(bat_priv->primary_if, new_hard_iface); - if (curr_hard_iface) - hardif_free_ref(curr_hard_iface); - if (!new_hard_iface) - return; + goto out; + + bat_priv->bat_algo_ops->bat_primary_iface_set(new_hard_iface); + primary_if_update_addr(bat_priv, curr_hard_iface); - bat_priv->bat_algo_ops->bat_ogm_init_primary(new_hard_iface); - primary_if_update_addr(bat_priv); +out: + if (curr_hard_iface) + hardif_free_ref(curr_hard_iface); } static bool hardif_is_iface_up(const struct hard_iface *hard_iface) @@ -175,9 +173,9 @@ static void check_known_mac_addr(const struct net_device *net_dev) net_dev->dev_addr)) continue; - pr_warning("The newly added mac address (%pM) already exists on: %s\n", - net_dev->dev_addr, hard_iface->net_dev->name); - pr_warning("It is strongly recommended to keep mac addresses unique to avoid problems!\n"); + pr_warn("The newly added mac address (%pM) already exists on: %s\n", + net_dev->dev_addr, hard_iface->net_dev->name); + pr_warn("It is strongly recommended to keep mac addresses unique to avoid problems!\n"); } rcu_read_unlock(); } @@ -230,7 +228,7 @@ static void hardif_activate_interface(struct hard_iface *hard_iface) bat_priv = netdev_priv(hard_iface->soft_iface); - bat_priv->bat_algo_ops->bat_ogm_update_mac(hard_iface); + bat_priv->bat_algo_ops->bat_iface_update_mac(hard_iface); hard_iface->if_status = IF_TO_BE_ACTIVATED; /** @@ -300,22 +298,17 @@ int hardif_enable_interface(struct hard_iface *hard_iface, if (!softif_is_valid(soft_iface)) { pr_err("Can't create batman mesh interface %s: already exists as regular interface\n", soft_iface->name); - dev_put(soft_iface); ret = -EINVAL; - goto err; + goto err_dev; } hard_iface->soft_iface = soft_iface; bat_priv = netdev_priv(hard_iface->soft_iface); - bat_priv->bat_algo_ops->bat_ogm_init(hard_iface); - - if (!hard_iface->packet_buff) { - bat_err(hard_iface->soft_iface, - "Can't add interface packet (%s): out of memory\n", - hard_iface->net_dev->name); + ret = bat_priv->bat_algo_ops->bat_iface_enable(hard_iface); + if (ret < 0) { ret = -ENOMEM; - goto err; + goto err_dev; } hard_iface->if_num = bat_priv->num_ifaces; @@ -328,7 +321,6 @@ int hardif_enable_interface(struct hard_iface *hard_iface, hard_iface->batman_adv_ptype.dev = hard_iface->net_dev; dev_add_pack(&hard_iface->batman_adv_ptype); - atomic_set(&hard_iface->seqno, 1); atomic_set(&hard_iface->frag_seqno, 1); bat_info(hard_iface->soft_iface, "Adding interface: %s\n", hard_iface->net_dev->name); @@ -360,6 +352,8 @@ int hardif_enable_interface(struct hard_iface *hard_iface, out: return 0; +err_dev: + dev_put(soft_iface); err: hardif_free_ref(hard_iface); return ret; @@ -394,8 +388,7 @@ void hardif_disable_interface(struct hard_iface *hard_iface) hardif_free_ref(new_if); } - kfree(hard_iface->packet_buff); - hard_iface->packet_buff = NULL; + bat_priv->bat_algo_ops->bat_iface_disable(hard_iface); hard_iface->if_status = IF_NOT_IN_USE; /* delete all references to this hard_iface */ @@ -447,6 +440,13 @@ static struct hard_iface *hardif_add_interface(struct net_device *net_dev) check_known_mac_addr(hard_iface->net_dev); list_add_tail_rcu(&hard_iface->list, &hardif_list); + /** + * This can't be called via a bat_priv callback because + * we have no bat_priv yet. + */ + atomic_set(&hard_iface->seqno, 1); + hard_iface->packet_buff = NULL; + return hard_iface; free_if: @@ -524,14 +524,14 @@ static int hard_if_event(struct notifier_block *this, check_known_mac_addr(hard_iface->net_dev); bat_priv = netdev_priv(hard_iface->soft_iface); - bat_priv->bat_algo_ops->bat_ogm_update_mac(hard_iface); + bat_priv->bat_algo_ops->bat_iface_update_mac(hard_iface); primary_if = primary_if_get_selected(bat_priv); if (!primary_if) goto hardif_put; if (hard_iface == primary_if) - primary_if_update_addr(bat_priv); + primary_if_update_addr(bat_priv, NULL); break; default: break; @@ -545,114 +545,6 @@ out: return NOTIFY_DONE; } -/* incoming packets with the batman ethertype received on any active hard - * interface */ -static int batman_skb_recv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *ptype, - struct net_device *orig_dev) -{ - struct bat_priv *bat_priv; - struct batman_ogm_packet *batman_ogm_packet; - struct hard_iface *hard_iface; - int ret; - - hard_iface = container_of(ptype, struct hard_iface, batman_adv_ptype); - skb = skb_share_check(skb, GFP_ATOMIC); - - /* skb was released by skb_share_check() */ - if (!skb) - goto err_out; - - /* packet should hold at least type and version */ - if (unlikely(!pskb_may_pull(skb, 2))) - goto err_free; - - /* expect a valid ethernet header here. */ - if (unlikely(skb->mac_len != sizeof(struct ethhdr) || - !skb_mac_header(skb))) - goto err_free; - - if (!hard_iface->soft_iface) - goto err_free; - - bat_priv = netdev_priv(hard_iface->soft_iface); - - if (atomic_read(&bat_priv->mesh_state) != MESH_ACTIVE) - goto err_free; - - /* discard frames on not active interfaces */ - if (hard_iface->if_status != IF_ACTIVE) - goto err_free; - - batman_ogm_packet = (struct batman_ogm_packet *)skb->data; - - if (batman_ogm_packet->header.version != COMPAT_VERSION) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: incompatible batman version (%i)\n", - batman_ogm_packet->header.version); - goto err_free; - } - - /* all receive handlers return whether they received or reused - * the supplied skb. if not, we have to free the skb. */ - - switch (batman_ogm_packet->header.packet_type) { - /* batman originator packet */ - case BAT_OGM: - ret = recv_bat_ogm_packet(skb, hard_iface); - break; - - /* batman icmp packet */ - case BAT_ICMP: - ret = recv_icmp_packet(skb, hard_iface); - break; - - /* unicast packet */ - case BAT_UNICAST: - ret = recv_unicast_packet(skb, hard_iface); - break; - - /* fragmented unicast packet */ - case BAT_UNICAST_FRAG: - ret = recv_ucast_frag_packet(skb, hard_iface); - break; - - /* broadcast packet */ - case BAT_BCAST: - ret = recv_bcast_packet(skb, hard_iface); - break; - - /* vis packet */ - case BAT_VIS: - ret = recv_vis_packet(skb, hard_iface); - break; - /* Translation table query (request or response) */ - case BAT_TT_QUERY: - ret = recv_tt_query(skb, hard_iface); - break; - /* Roaming advertisement */ - case BAT_ROAM_ADV: - ret = recv_roam_adv(skb, hard_iface); - break; - default: - ret = NET_RX_DROP; - } - - if (ret == NET_RX_DROP) - kfree_skb(skb); - - /* return NET_RX_SUCCESS in any case as we - * most probably dropped the packet for - * routing-logical reasons. */ - - return NET_RX_SUCCESS; - -err_free: - kfree_skb(skb); -err_out: - return NET_RX_DROP; -} - /* This function returns true if the interface represented by ifindex is a * 802.11 wireless device */ bool is_wifi_iface(int ifindex) diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index b87518edcef..2e98a57f340 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -175,13 +175,13 @@ static ssize_t bat_socket_write(struct file *file, const char __user *buff, if (len >= sizeof(struct icmp_packet_rr)) packet_len = sizeof(struct icmp_packet_rr); - skb = dev_alloc_skb(packet_len + sizeof(struct ethhdr)); + skb = dev_alloc_skb(packet_len + ETH_HLEN); if (!skb) { len = -ENOMEM; goto out; } - skb_reserve(skb, sizeof(struct ethhdr)); + skb_reserve(skb, ETH_HLEN); icmp_packet = (struct icmp_packet_rr *)skb_put(skb, packet_len); if (copy_from_user(icmp_packet, buff, packet_len)) { diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 6d51caaf8ce..083a2993efe 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -30,6 +30,7 @@ #include "translation-table.h" #include "hard-interface.h" #include "gateway_client.h" +#include "bridge_loop_avoidance.h" #include "vis.h" #include "hash.h" #include "bat_algo.h" @@ -38,6 +39,7 @@ /* List manipulations on hardif_list have to be rtnl_lock()'ed, * list traversals just rcu-locked */ struct list_head hardif_list; +static int (*recv_packet_handler[256])(struct sk_buff *, struct hard_iface *); char bat_routing_algo[20] = "BATMAN IV"; static struct hlist_head bat_algo_list; @@ -45,11 +47,15 @@ unsigned char broadcast_addr[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; struct workqueue_struct *bat_event_workqueue; +static void recv_handler_init(void); + static int __init batman_init(void) { INIT_LIST_HEAD(&hardif_list); INIT_HLIST_HEAD(&bat_algo_list); + recv_handler_init(); + bat_iv_init(); /* the name should not be longer than 10 chars - see @@ -96,13 +102,10 @@ int mesh_init(struct net_device *soft_iface) spin_lock_init(&bat_priv->gw_list_lock); spin_lock_init(&bat_priv->vis_hash_lock); spin_lock_init(&bat_priv->vis_list_lock); - spin_lock_init(&bat_priv->softif_neigh_lock); - spin_lock_init(&bat_priv->softif_neigh_vid_lock); INIT_HLIST_HEAD(&bat_priv->forw_bat_list); INIT_HLIST_HEAD(&bat_priv->forw_bcast_list); INIT_HLIST_HEAD(&bat_priv->gw_list); - INIT_HLIST_HEAD(&bat_priv->softif_neigh_vids); INIT_LIST_HEAD(&bat_priv->tt_changes_list); INIT_LIST_HEAD(&bat_priv->tt_req_list); INIT_LIST_HEAD(&bat_priv->tt_roam_list); @@ -118,6 +121,9 @@ int mesh_init(struct net_device *soft_iface) if (vis_init(bat_priv) < 1) goto err; + if (bla_init(bat_priv) < 1) + goto err; + atomic_set(&bat_priv->gw_reselect, 0); atomic_set(&bat_priv->mesh_state, MESH_ACTIVE); goto end; @@ -145,7 +151,7 @@ void mesh_free(struct net_device *soft_iface) tt_free(bat_priv); - softif_neigh_purge(bat_priv); + bla_free(bat_priv); atomic_set(&bat_priv->mesh_state, MESH_INACTIVE); } @@ -178,6 +184,120 @@ int is_my_mac(const uint8_t *addr) return 0; } +static int recv_unhandled_packet(struct sk_buff *skb, + struct hard_iface *recv_if) +{ + return NET_RX_DROP; +} + +/* incoming packets with the batman ethertype received on any active hard + * interface + */ +int batman_skb_recv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *ptype, struct net_device *orig_dev) +{ + struct bat_priv *bat_priv; + struct batman_ogm_packet *batman_ogm_packet; + struct hard_iface *hard_iface; + uint8_t idx; + int ret; + + hard_iface = container_of(ptype, struct hard_iface, batman_adv_ptype); + skb = skb_share_check(skb, GFP_ATOMIC); + + /* skb was released by skb_share_check() */ + if (!skb) + goto err_out; + + /* packet should hold at least type and version */ + if (unlikely(!pskb_may_pull(skb, 2))) + goto err_free; + + /* expect a valid ethernet header here. */ + if (unlikely(skb->mac_len != ETH_HLEN || !skb_mac_header(skb))) + goto err_free; + + if (!hard_iface->soft_iface) + goto err_free; + + bat_priv = netdev_priv(hard_iface->soft_iface); + + if (atomic_read(&bat_priv->mesh_state) != MESH_ACTIVE) + goto err_free; + + /* discard frames on not active interfaces */ + if (hard_iface->if_status != IF_ACTIVE) + goto err_free; + + batman_ogm_packet = (struct batman_ogm_packet *)skb->data; + + if (batman_ogm_packet->header.version != COMPAT_VERSION) { + bat_dbg(DBG_BATMAN, bat_priv, + "Drop packet: incompatible batman version (%i)\n", + batman_ogm_packet->header.version); + goto err_free; + } + + /* all receive handlers return whether they received or reused + * the supplied skb. if not, we have to free the skb. + */ + idx = batman_ogm_packet->header.packet_type; + ret = (*recv_packet_handler[idx])(skb, hard_iface); + + if (ret == NET_RX_DROP) + kfree_skb(skb); + + /* return NET_RX_SUCCESS in any case as we + * most probably dropped the packet for + * routing-logical reasons. + */ + return NET_RX_SUCCESS; + +err_free: + kfree_skb(skb); +err_out: + return NET_RX_DROP; +} + +static void recv_handler_init(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(recv_packet_handler); i++) + recv_packet_handler[i] = recv_unhandled_packet; + + /* batman icmp packet */ + recv_packet_handler[BAT_ICMP] = recv_icmp_packet; + /* unicast packet */ + recv_packet_handler[BAT_UNICAST] = recv_unicast_packet; + /* fragmented unicast packet */ + recv_packet_handler[BAT_UNICAST_FRAG] = recv_ucast_frag_packet; + /* broadcast packet */ + recv_packet_handler[BAT_BCAST] = recv_bcast_packet; + /* vis packet */ + recv_packet_handler[BAT_VIS] = recv_vis_packet; + /* Translation table query (request or response) */ + recv_packet_handler[BAT_TT_QUERY] = recv_tt_query; + /* Roaming advertisement */ + recv_packet_handler[BAT_ROAM_ADV] = recv_roam_adv; +} + +int recv_handler_register(uint8_t packet_type, + int (*recv_handler)(struct sk_buff *, + struct hard_iface *)) +{ + if (recv_packet_handler[packet_type] != &recv_unhandled_packet) + return -EBUSY; + + recv_packet_handler[packet_type] = recv_handler; + return 0; +} + +void recv_handler_unregister(uint8_t packet_type) +{ + recv_packet_handler[packet_type] = recv_unhandled_packet; +} + static struct bat_algo_ops *bat_algo_get(char *name) { struct bat_algo_ops *bat_algo_ops = NULL, *bat_algo_ops_tmp; @@ -207,12 +327,12 @@ int bat_algo_register(struct bat_algo_ops *bat_algo_ops) } /* all algorithms must implement all ops (for now) */ - if (!bat_algo_ops->bat_ogm_init || - !bat_algo_ops->bat_ogm_init_primary || - !bat_algo_ops->bat_ogm_update_mac || + if (!bat_algo_ops->bat_iface_enable || + !bat_algo_ops->bat_iface_disable || + !bat_algo_ops->bat_iface_update_mac || + !bat_algo_ops->bat_primary_iface_set || !bat_algo_ops->bat_ogm_schedule || - !bat_algo_ops->bat_ogm_emit || - !bat_algo_ops->bat_ogm_receive) { + !bat_algo_ops->bat_ogm_emit) { pr_info("Routing algo '%s' does not implement required ops\n", bat_algo_ops->name); goto out; diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 94fa1c2393a..f4a3ec00347 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -28,7 +28,7 @@ #define DRIVER_DEVICE "batman-adv" #ifndef SOURCE_VERSION -#define SOURCE_VERSION "2012.1.0" +#define SOURCE_VERSION "2012.2.0" #endif /* B.A.T.M.A.N. parameters */ @@ -65,7 +65,7 @@ #define NULL_IFINDEX 0 /* dummy ifindex used to avoid iface checks */ -#define NUM_WORDS (TQ_LOCAL_WINDOW_SIZE / WORD_BIT_SIZE) +#define NUM_WORDS BITS_TO_LONGS(TQ_LOCAL_WINDOW_SIZE) #define LOG_BUF_LEN 8192 /* has to be a power of 2 */ @@ -80,8 +80,12 @@ #define MAX_AGGREGATION_BYTES 512 #define MAX_AGGREGATION_MS 100 -#define SOFTIF_NEIGH_TIMEOUT 180000 /* 3 minutes */ +#define BLA_PERIOD_LENGTH 10000 /* 10 seconds */ +#define BLA_BACKBONE_TIMEOUT (BLA_PERIOD_LENGTH * 3) +#define BLA_CLAIM_TIMEOUT (BLA_PERIOD_LENGTH * 10) +#define DUPLIST_SIZE 16 +#define DUPLIST_TIMEOUT 500 /* 500 ms */ /* don't reset again within 30 seconds */ #define RESET_PROTECTION_MS 30000 #define EXPECTED_SEQNO_RANGE 65536 @@ -119,7 +123,8 @@ enum dbg_level { DBG_BATMAN = 1 << 0, DBG_ROUTES = 1 << 1, /* route added / changed / deleted */ DBG_TT = 1 << 2, /* translation table operations */ - DBG_ALL = 7 + DBG_BLA = 1 << 3, /* bridge loop avoidance */ + DBG_ALL = 15 }; /* Kernel headers */ @@ -150,6 +155,12 @@ void mesh_free(struct net_device *soft_iface); void inc_module_count(void); void dec_module_count(void); int is_my_mac(const uint8_t *addr); +int batman_skb_recv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *ptype, struct net_device *orig_dev); +int recv_handler_register(uint8_t packet_type, + int (*recv_handler)(struct sk_buff *, + struct hard_iface *)); +void recv_handler_unregister(uint8_t packet_type); int bat_algo_register(struct bat_algo_ops *bat_algo_ops); int bat_algo_select(struct bat_priv *bat_priv, char *name); int bat_algo_seq_print_text(struct seq_file *seq, void *offset); diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 43c0a4f1399..41147942ba5 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -28,13 +28,15 @@ #include "hard-interface.h" #include "unicast.h" #include "soft-interface.h" +#include "bridge_loop_avoidance.h" static void purge_orig(struct work_struct *work); static void start_purge_timer(struct bat_priv *bat_priv) { INIT_DELAYED_WORK(&bat_priv->orig_work, purge_orig); - queue_delayed_work(bat_event_workqueue, &bat_priv->orig_work, 1 * HZ); + queue_delayed_work(bat_event_workqueue, + &bat_priv->orig_work, msecs_to_jiffies(1000)); } /* returns 1 if they are the same originator */ @@ -83,35 +85,30 @@ struct neigh_node *orig_node_get_router(struct orig_node *orig_node) return router; } -struct neigh_node *create_neighbor(struct orig_node *orig_node, - struct orig_node *orig_neigh_node, - const uint8_t *neigh, - struct hard_iface *if_incoming) +struct neigh_node *batadv_neigh_node_new(struct hard_iface *hard_iface, + const uint8_t *neigh_addr, + uint32_t seqno) { - struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); + struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct neigh_node *neigh_node; - bat_dbg(DBG_BATMAN, bat_priv, - "Creating new last-hop neighbor of originator\n"); - neigh_node = kzalloc(sizeof(*neigh_node), GFP_ATOMIC); if (!neigh_node) - return NULL; + goto out; INIT_HLIST_NODE(&neigh_node->list); - INIT_LIST_HEAD(&neigh_node->bonding_list); - spin_lock_init(&neigh_node->tq_lock); - memcpy(neigh_node->addr, neigh, ETH_ALEN); - neigh_node->orig_node = orig_neigh_node; - neigh_node->if_incoming = if_incoming; + memcpy(neigh_node->addr, neigh_addr, ETH_ALEN); + spin_lock_init(&neigh_node->lq_update_lock); /* extra reference for return */ atomic_set(&neigh_node->refcount, 2); - spin_lock_bh(&orig_node->neigh_list_lock); - hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); - spin_unlock_bh(&orig_node->neigh_list_lock); + bat_dbg(DBG_BATMAN, bat_priv, + "Creating new neighbor %pM, initial seqno %d\n", + neigh_addr, seqno); + +out: return neigh_node; } @@ -273,6 +270,7 @@ static bool purge_orig_neighbors(struct bat_priv *bat_priv, struct hlist_node *node, *node_tmp; struct neigh_node *neigh_node; bool neigh_purged = false; + unsigned long last_seen; *best_neigh_node = NULL; @@ -282,11 +280,13 @@ static bool purge_orig_neighbors(struct bat_priv *bat_priv, hlist_for_each_entry_safe(neigh_node, node, node_tmp, &orig_node->neigh_list, list) { - if ((has_timed_out(neigh_node->last_valid, PURGE_TIMEOUT)) || + if ((has_timed_out(neigh_node->last_seen, PURGE_TIMEOUT)) || (neigh_node->if_incoming->if_status == IF_INACTIVE) || (neigh_node->if_incoming->if_status == IF_NOT_IN_USE) || (neigh_node->if_incoming->if_status == IF_TO_BE_REMOVED)) { + last_seen = neigh_node->last_seen; + if ((neigh_node->if_incoming->if_status == IF_INACTIVE) || (neigh_node->if_incoming->if_status == @@ -299,9 +299,9 @@ static bool purge_orig_neighbors(struct bat_priv *bat_priv, neigh_node->if_incoming->net_dev->name); else bat_dbg(DBG_BATMAN, bat_priv, - "neighbor timeout: originator %pM, neighbor: %pM, last_valid: %lu\n", + "neighbor timeout: originator %pM, neighbor: %pM, last_seen: %u\n", orig_node->orig, neigh_node->addr, - (neigh_node->last_valid / HZ)); + jiffies_to_msecs(last_seen)); neigh_purged = true; @@ -324,10 +324,11 @@ static bool purge_orig_node(struct bat_priv *bat_priv, { struct neigh_node *best_neigh_node; - if (has_timed_out(orig_node->last_valid, 2 * PURGE_TIMEOUT)) { + if (has_timed_out(orig_node->last_seen, 2 * PURGE_TIMEOUT)) { bat_dbg(DBG_BATMAN, bat_priv, - "Originator timeout: originator %pM, last_valid %lu\n", - orig_node->orig, (orig_node->last_valid / HZ)); + "Originator timeout: originator %pM, last_seen %u\n", + orig_node->orig, + jiffies_to_msecs(orig_node->last_seen)); return true; } else { if (purge_orig_neighbors(bat_priv, orig_node, @@ -375,8 +376,6 @@ static void _purge_orig(struct bat_priv *bat_priv) gw_node_purge(bat_priv); gw_election(bat_priv); - - softif_neigh_purge(bat_priv); } static void purge_orig(struct work_struct *work) @@ -447,9 +446,9 @@ int orig_seq_print_text(struct seq_file *seq, void *offset) goto next; last_seen_secs = jiffies_to_msecs(jiffies - - orig_node->last_valid) / 1000; + orig_node->last_seen) / 1000; last_seen_msecs = jiffies_to_msecs(jiffies - - orig_node->last_valid) % 1000; + orig_node->last_seen) % 1000; seq_printf(seq, "%pM %4i.%03is (%3i) %pM [%10s]:", orig_node->orig, last_seen_secs, diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 3fe2eda8565..f74d0d69335 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -29,10 +29,9 @@ void originator_free(struct bat_priv *bat_priv); void purge_orig_ref(struct bat_priv *bat_priv); void orig_node_free_ref(struct orig_node *orig_node); struct orig_node *get_orig_node(struct bat_priv *bat_priv, const uint8_t *addr); -struct neigh_node *create_neighbor(struct orig_node *orig_node, - struct orig_node *orig_neigh_node, - const uint8_t *neigh, - struct hard_iface *if_incoming); +struct neigh_node *batadv_neigh_node_new(struct hard_iface *hard_iface, + const uint8_t *neigh_addr, + uint32_t seqno); void neigh_node_free_ref(struct neigh_node *neigh_node); struct neigh_node *orig_node_get_router(struct orig_node *orig_node); int orig_seq_print_text(struct seq_file *seq, void *offset); diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index 441f3db1bd9..0ee1af77079 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -25,7 +25,7 @@ #define ETH_P_BATMAN 0x4305 /* unofficial/not registered Ethertype */ enum bat_packettype { - BAT_OGM = 0x01, + BAT_IV_OGM = 0x01, BAT_ICMP = 0x02, BAT_UNICAST = 0x03, BAT_BCAST = 0x04, @@ -38,7 +38,8 @@ enum bat_packettype { /* this file is included by batctl which needs these defines */ #define COMPAT_VERSION 14 -enum batman_flags { +enum batman_iv_flags { + NOT_BEST_NEXT_HOP = 1 << 3, PRIMARIES_FIRST_HOP = 1 << 4, VIS_SERVER = 1 << 5, DIRECTLINK = 1 << 6 @@ -90,6 +91,23 @@ enum tt_client_flags { TT_CLIENT_PENDING = 1 << 10 }; +/* claim frame types for the bridge loop avoidance */ +enum bla_claimframe { + CLAIM_TYPE_ADD = 0x00, + CLAIM_TYPE_DEL = 0x01, + CLAIM_TYPE_ANNOUNCE = 0x02, + CLAIM_TYPE_REQUEST = 0x03 +}; + +/* the destination hardware field in the ARP frame is used to + * transport the claim type and the group id + */ +struct bla_claim_dst { + uint8_t magic[3]; /* FF:43:05 */ + uint8_t type; /* bla_claimframe */ + uint16_t group; /* group id */ +} __packed; + struct batman_header { uint8_t packet_type; uint8_t version; /* batman version field */ @@ -100,8 +118,8 @@ struct batman_ogm_packet { struct batman_header header; uint8_t flags; /* 0x40: DIRECTLINK flag, 0x20 VIS_SERVER flag... */ uint32_t seqno; - uint8_t orig[6]; - uint8_t prev_sender[6]; + uint8_t orig[ETH_ALEN]; + uint8_t prev_sender[ETH_ALEN]; uint8_t gw_flags; /* flags related to gateway class */ uint8_t tq; uint8_t tt_num_changes; @@ -109,13 +127,13 @@ struct batman_ogm_packet { uint16_t tt_crc; } __packed; -#define BATMAN_OGM_LEN sizeof(struct batman_ogm_packet) +#define BATMAN_OGM_HLEN sizeof(struct batman_ogm_packet) struct icmp_packet { struct batman_header header; uint8_t msg_type; /* see ICMP message types above */ - uint8_t dst[6]; - uint8_t orig[6]; + uint8_t dst[ETH_ALEN]; + uint8_t orig[ETH_ALEN]; uint16_t seqno; uint8_t uid; uint8_t reserved; @@ -128,8 +146,8 @@ struct icmp_packet { struct icmp_packet_rr { struct batman_header header; uint8_t msg_type; /* see ICMP message types above */ - uint8_t dst[6]; - uint8_t orig[6]; + uint8_t dst[ETH_ALEN]; + uint8_t orig[ETH_ALEN]; uint16_t seqno; uint8_t uid; uint8_t rr_cur; @@ -139,16 +157,16 @@ struct icmp_packet_rr { struct unicast_packet { struct batman_header header; uint8_t ttvn; /* destination translation table version number */ - uint8_t dest[6]; + uint8_t dest[ETH_ALEN]; } __packed; struct unicast_frag_packet { struct batman_header header; uint8_t ttvn; /* destination translation table version number */ - uint8_t dest[6]; + uint8_t dest[ETH_ALEN]; uint8_t flags; uint8_t align; - uint8_t orig[6]; + uint8_t orig[ETH_ALEN]; uint16_t seqno; } __packed; @@ -156,7 +174,7 @@ struct bcast_packet { struct batman_header header; uint8_t reserved; uint32_t seqno; - uint8_t orig[6]; + uint8_t orig[ETH_ALEN]; } __packed; struct vis_packet { @@ -165,9 +183,9 @@ struct vis_packet { uint32_t seqno; /* sequence number */ uint8_t entries; /* number of entries behind this struct */ uint8_t reserved; - uint8_t vis_orig[6]; /* originator that announces its neighbors */ - uint8_t target_orig[6]; /* who should receive this packet */ - uint8_t sender_orig[6]; /* who sent or rebroadcasted this packet */ + uint8_t vis_orig[ETH_ALEN]; /* originator reporting its neighbors */ + uint8_t target_orig[ETH_ALEN]; /* who should receive this packet */ + uint8_t sender_orig[ETH_ALEN]; /* who sent or forwarded this packet */ } __packed; struct tt_query_packet { diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 7f8e1589941..840e2c64a30 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -29,6 +29,10 @@ #include "originator.h" #include "vis.h" #include "unicast.h" +#include "bridge_loop_avoidance.h" + +static int route_unicast_packet(struct sk_buff *skb, + struct hard_iface *recv_if); void slide_own_bcast_window(struct hard_iface *hard_iface) { @@ -52,7 +56,7 @@ void slide_own_bcast_window(struct hard_iface *hard_iface) bit_get_packet(bat_priv, word, 1, 0); orig_node->bcast_own_sum[hard_iface->if_num] = - bit_packet_count(word); + bitmap_weight(word, TQ_LOCAL_WINDOW_SIZE); spin_unlock_bh(&orig_node->ogm_cnt_lock); } rcu_read_unlock(); @@ -230,51 +234,46 @@ int window_protected(struct bat_priv *bat_priv, int32_t seq_num_diff, { if ((seq_num_diff <= -TQ_LOCAL_WINDOW_SIZE) || (seq_num_diff >= EXPECTED_SEQNO_RANGE)) { - if (has_timed_out(*last_reset, RESET_PROTECTION_MS)) { - - *last_reset = jiffies; - bat_dbg(DBG_BATMAN, bat_priv, - "old packet received, start protection\n"); - - return 0; - } else { + if (!has_timed_out(*last_reset, RESET_PROTECTION_MS)) return 1; - } + + *last_reset = jiffies; + bat_dbg(DBG_BATMAN, bat_priv, + "old packet received, start protection\n"); } + return 0; } -int recv_bat_ogm_packet(struct sk_buff *skb, struct hard_iface *hard_iface) +bool check_management_packet(struct sk_buff *skb, + struct hard_iface *hard_iface, + int header_len) { - struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct ethhdr *ethhdr; /* drop packet if it has not necessary minimum size */ - if (unlikely(!pskb_may_pull(skb, BATMAN_OGM_LEN))) - return NET_RX_DROP; + if (unlikely(!pskb_may_pull(skb, header_len))) + return false; ethhdr = (struct ethhdr *)skb_mac_header(skb); /* packet with broadcast indication but unicast recipient */ if (!is_broadcast_ether_addr(ethhdr->h_dest)) - return NET_RX_DROP; + return false; /* packet with broadcast sender address */ if (is_broadcast_ether_addr(ethhdr->h_source)) - return NET_RX_DROP; + return false; /* create a copy of the skb, if needed, to modify it. */ if (skb_cow(skb, 0) < 0) - return NET_RX_DROP; + return false; /* keep skb linear */ if (skb_linearize(skb) < 0) - return NET_RX_DROP; - - bat_priv->bat_algo_ops->bat_ogm_receive(hard_iface, skb); + return false; - kfree_skb(skb); - return NET_RX_SUCCESS; + return true; } static int recv_my_icmp_packet(struct bat_priv *bat_priv, @@ -309,7 +308,7 @@ static int recv_my_icmp_packet(struct bat_priv *bat_priv, goto out; /* create a copy of the skb, if needed, to modify it. */ - if (skb_cow(skb, sizeof(struct ethhdr)) < 0) + if (skb_cow(skb, ETH_HLEN) < 0) goto out; icmp_packet = (struct icmp_packet_rr *)skb->data; @@ -364,7 +363,7 @@ static int recv_icmp_ttl_exceeded(struct bat_priv *bat_priv, goto out; /* create a copy of the skb, if needed, to modify it. */ - if (skb_cow(skb, sizeof(struct ethhdr)) < 0) + if (skb_cow(skb, ETH_HLEN) < 0) goto out; icmp_packet = (struct icmp_packet *)skb->data; @@ -450,7 +449,7 @@ int recv_icmp_packet(struct sk_buff *skb, struct hard_iface *recv_if) goto out; /* create a copy of the skb, if needed, to modify it. */ - if (skb_cow(skb, sizeof(struct ethhdr)) < 0) + if (skb_cow(skb, ETH_HLEN) < 0) goto out; icmp_packet = (struct icmp_packet_rr *)skb->data; @@ -669,6 +668,13 @@ int recv_roam_adv(struct sk_buff *skb, struct hard_iface *recv_if) if (!is_my_mac(roam_adv_packet->dst)) return route_unicast_packet(skb, recv_if); + /* check if it is a backbone gateway. we don't accept + * roaming advertisement from it, as it has the same + * entries as we have. + */ + if (bla_is_backbone_gw_orig(bat_priv, roam_adv_packet->src)) + goto out; + orig_node = orig_hash_find(bat_priv, roam_adv_packet->src); if (!orig_node) goto out; @@ -798,7 +804,7 @@ static int check_unicast_packet(struct sk_buff *skb, int hdr_size) return 0; } -int route_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if) +static int route_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if) { struct bat_priv *bat_priv = netdev_priv(recv_if->soft_iface); struct orig_node *orig_node = NULL; @@ -830,7 +836,7 @@ int route_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if) goto out; /* create a copy of the skb, if needed, to modify it. */ - if (skb_cow(skb, sizeof(struct ethhdr)) < 0) + if (skb_cow(skb, ETH_HLEN) < 0) goto out; unicast_packet = (struct unicast_packet *)skb->data; @@ -907,12 +913,20 @@ static int check_unicast_ttvn(struct bat_priv *bat_priv, /* Check whether I have to reroute the packet */ if (seq_before(unicast_packet->ttvn, curr_ttvn) || tt_poss_change) { - /* Linearize the skb before accessing it */ - if (skb_linearize(skb) < 0) + /* check if there is enough data before accessing it */ + if (pskb_may_pull(skb, sizeof(struct unicast_packet) + + ETH_HLEN) < 0) return 0; ethhdr = (struct ethhdr *)(skb->data + sizeof(struct unicast_packet)); + + /* we don't have an updated route for this client, so we should + * not try to reroute the packet!! + */ + if (tt_global_client_is_roaming(bat_priv, ethhdr->h_dest)) + return 1; + orig_node = transtable_search(bat_priv, NULL, ethhdr->h_dest); if (!orig_node) { @@ -1047,8 +1061,8 @@ int recv_bcast_packet(struct sk_buff *skb, struct hard_iface *recv_if) spin_lock_bh(&orig_node->bcast_seqno_lock); /* check whether the packet is a duplicate */ - if (get_bit_status(orig_node->bcast_bits, orig_node->last_bcast_seqno, - ntohl(bcast_packet->seqno))) + if (bat_test_bit(orig_node->bcast_bits, orig_node->last_bcast_seqno, + ntohl(bcast_packet->seqno))) goto spin_unlock; seq_diff = ntohl(bcast_packet->seqno) - orig_node->last_bcast_seqno; @@ -1065,9 +1079,19 @@ int recv_bcast_packet(struct sk_buff *skb, struct hard_iface *recv_if) spin_unlock_bh(&orig_node->bcast_seqno_lock); + /* check whether this has been sent by another originator before */ + if (bla_check_bcast_duplist(bat_priv, bcast_packet, hdr_size)) + goto out; + /* rebroadcast packet */ add_bcast_packet_to_list(bat_priv, skb, 1); + /* don't hand the broadcast up if it is from an originator + * from the same backbone. + */ + if (bla_is_backbone_gw(skb, orig_node, hdr_size)) + goto out; + /* broadcast for me */ interface_rx(recv_if->soft_iface, skb, recv_if, hdr_size); ret = NET_RX_SUCCESS; diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index 92ac100d83d..d6bbbebb656 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -23,15 +23,16 @@ #define _NET_BATMAN_ADV_ROUTING_H_ void slide_own_bcast_window(struct hard_iface *hard_iface); +bool check_management_packet(struct sk_buff *skb, + struct hard_iface *hard_iface, + int header_len); void update_route(struct bat_priv *bat_priv, struct orig_node *orig_node, struct neigh_node *neigh_node); -int route_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_icmp_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_ucast_frag_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_bcast_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_vis_packet(struct sk_buff *skb, struct hard_iface *recv_if); -int recv_bat_ogm_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_tt_query(struct sk_buff *skb, struct hard_iface *recv_if); int recv_roam_adv(struct sk_buff *skb, struct hard_iface *recv_if); struct neigh_node *find_router(struct bat_priv *bat_priv, diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index af7a6741a68..f47299f22c6 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -45,13 +45,13 @@ int send_skb_packet(struct sk_buff *skb, struct hard_iface *hard_iface, goto send_skb_err; if (!(hard_iface->net_dev->flags & IFF_UP)) { - pr_warning("Interface %s is not up - can't send packet via that interface!\n", - hard_iface->net_dev->name); + pr_warn("Interface %s is not up - can't send packet via that interface!\n", + hard_iface->net_dev->name); goto send_skb_err; } /* push to the ethernet header. */ - if (my_skb_head_push(skb, sizeof(*ethhdr)) < 0) + if (my_skb_head_push(skb, ETH_HLEN) < 0) goto send_skb_err; skb_reset_mac_header(skb); @@ -87,7 +87,7 @@ static void realloc_packet_buffer(struct hard_iface *hard_iface, /* keep old buffer if kmalloc should fail */ if (new_buff) { memcpy(new_buff, hard_iface->packet_buff, - BATMAN_OGM_LEN); + BATMAN_OGM_HLEN); kfree(hard_iface->packet_buff); hard_iface->packet_buff = new_buff; @@ -101,13 +101,13 @@ static int prepare_packet_buffer(struct bat_priv *bat_priv, { int new_len; - new_len = BATMAN_OGM_LEN + + new_len = BATMAN_OGM_HLEN + tt_len((uint8_t)atomic_read(&bat_priv->tt_local_changes)); /* if we have too many changes for one packet don't send any * and wait for the tt table request which will be fragmented */ if (new_len > hard_iface->soft_iface->mtu) - new_len = BATMAN_OGM_LEN; + new_len = BATMAN_OGM_HLEN; realloc_packet_buffer(hard_iface, new_len); @@ -117,14 +117,14 @@ static int prepare_packet_buffer(struct bat_priv *bat_priv, atomic_set(&bat_priv->tt_ogm_append_cnt, TT_OGM_APPEND_MAX); return tt_changes_fill_buffer(bat_priv, - hard_iface->packet_buff + BATMAN_OGM_LEN, - hard_iface->packet_len - BATMAN_OGM_LEN); + hard_iface->packet_buff + BATMAN_OGM_HLEN, + hard_iface->packet_len - BATMAN_OGM_HLEN); } static int reset_packet_buffer(struct bat_priv *bat_priv, struct hard_iface *hard_iface) { - realloc_packet_buffer(hard_iface, BATMAN_OGM_LEN); + realloc_packet_buffer(hard_iface, BATMAN_OGM_HLEN); return 0; } @@ -292,7 +292,7 @@ static void send_outstanding_bcast_packet(struct work_struct *work) /* if we still have some more bcasts to send */ if (forw_packet->num_packets < 3) { _add_bcast_packet_to_list(bat_priv, forw_packet, - ((5 * HZ) / 1000)); + msecs_to_jiffies(5)); return; } diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index a5590f4193f..6e2530b0204 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -36,6 +36,7 @@ #include <linux/etherdevice.h> #include <linux/if_vlan.h> #include "unicast.h" +#include "bridge_loop_avoidance.h" static int bat_get_settings(struct net_device *dev, struct ethtool_cmd *cmd); @@ -73,439 +74,6 @@ int my_skb_head_push(struct sk_buff *skb, unsigned int len) return 0; } -static void softif_neigh_free_ref(struct softif_neigh *softif_neigh) -{ - if (atomic_dec_and_test(&softif_neigh->refcount)) - kfree_rcu(softif_neigh, rcu); -} - -static void softif_neigh_vid_free_rcu(struct rcu_head *rcu) -{ - struct softif_neigh_vid *softif_neigh_vid; - struct softif_neigh *softif_neigh; - struct hlist_node *node, *node_tmp; - struct bat_priv *bat_priv; - - softif_neigh_vid = container_of(rcu, struct softif_neigh_vid, rcu); - bat_priv = softif_neigh_vid->bat_priv; - - spin_lock_bh(&bat_priv->softif_neigh_lock); - hlist_for_each_entry_safe(softif_neigh, node, node_tmp, - &softif_neigh_vid->softif_neigh_list, list) { - hlist_del_rcu(&softif_neigh->list); - softif_neigh_free_ref(softif_neigh); - } - spin_unlock_bh(&bat_priv->softif_neigh_lock); - - kfree(softif_neigh_vid); -} - -static void softif_neigh_vid_free_ref(struct softif_neigh_vid *softif_neigh_vid) -{ - if (atomic_dec_and_test(&softif_neigh_vid->refcount)) - call_rcu(&softif_neigh_vid->rcu, softif_neigh_vid_free_rcu); -} - -static struct softif_neigh_vid *softif_neigh_vid_get(struct bat_priv *bat_priv, - short vid) -{ - struct softif_neigh_vid *softif_neigh_vid; - struct hlist_node *node; - - rcu_read_lock(); - hlist_for_each_entry_rcu(softif_neigh_vid, node, - &bat_priv->softif_neigh_vids, list) { - if (softif_neigh_vid->vid != vid) - continue; - - if (!atomic_inc_not_zero(&softif_neigh_vid->refcount)) - continue; - - goto out; - } - - softif_neigh_vid = kzalloc(sizeof(*softif_neigh_vid), GFP_ATOMIC); - if (!softif_neigh_vid) - goto out; - - softif_neigh_vid->vid = vid; - softif_neigh_vid->bat_priv = bat_priv; - - /* initialize with 2 - caller decrements counter by one */ - atomic_set(&softif_neigh_vid->refcount, 2); - INIT_HLIST_HEAD(&softif_neigh_vid->softif_neigh_list); - INIT_HLIST_NODE(&softif_neigh_vid->list); - spin_lock_bh(&bat_priv->softif_neigh_vid_lock); - hlist_add_head_rcu(&softif_neigh_vid->list, - &bat_priv->softif_neigh_vids); - spin_unlock_bh(&bat_priv->softif_neigh_vid_lock); - -out: - rcu_read_unlock(); - return softif_neigh_vid; -} - -static struct softif_neigh *softif_neigh_get(struct bat_priv *bat_priv, - const uint8_t *addr, short vid) -{ - struct softif_neigh_vid *softif_neigh_vid; - struct softif_neigh *softif_neigh = NULL; - struct hlist_node *node; - - softif_neigh_vid = softif_neigh_vid_get(bat_priv, vid); - if (!softif_neigh_vid) - goto out; - - rcu_read_lock(); - hlist_for_each_entry_rcu(softif_neigh, node, - &softif_neigh_vid->softif_neigh_list, - list) { - if (!compare_eth(softif_neigh->addr, addr)) - continue; - - if (!atomic_inc_not_zero(&softif_neigh->refcount)) - continue; - - softif_neigh->last_seen = jiffies; - goto unlock; - } - - softif_neigh = kzalloc(sizeof(*softif_neigh), GFP_ATOMIC); - if (!softif_neigh) - goto unlock; - - memcpy(softif_neigh->addr, addr, ETH_ALEN); - softif_neigh->last_seen = jiffies; - /* initialize with 2 - caller decrements counter by one */ - atomic_set(&softif_neigh->refcount, 2); - - INIT_HLIST_NODE(&softif_neigh->list); - spin_lock_bh(&bat_priv->softif_neigh_lock); - hlist_add_head_rcu(&softif_neigh->list, - &softif_neigh_vid->softif_neigh_list); - spin_unlock_bh(&bat_priv->softif_neigh_lock); - -unlock: - rcu_read_unlock(); -out: - if (softif_neigh_vid) - softif_neigh_vid_free_ref(softif_neigh_vid); - return softif_neigh; -} - -static struct softif_neigh *softif_neigh_get_selected( - struct softif_neigh_vid *softif_neigh_vid) -{ - struct softif_neigh *softif_neigh; - - rcu_read_lock(); - softif_neigh = rcu_dereference(softif_neigh_vid->softif_neigh); - - if (softif_neigh && !atomic_inc_not_zero(&softif_neigh->refcount)) - softif_neigh = NULL; - - rcu_read_unlock(); - return softif_neigh; -} - -static struct softif_neigh *softif_neigh_vid_get_selected( - struct bat_priv *bat_priv, - short vid) -{ - struct softif_neigh_vid *softif_neigh_vid; - struct softif_neigh *softif_neigh = NULL; - - softif_neigh_vid = softif_neigh_vid_get(bat_priv, vid); - if (!softif_neigh_vid) - goto out; - - softif_neigh = softif_neigh_get_selected(softif_neigh_vid); -out: - if (softif_neigh_vid) - softif_neigh_vid_free_ref(softif_neigh_vid); - return softif_neigh; -} - -static void softif_neigh_vid_select(struct bat_priv *bat_priv, - struct softif_neigh *new_neigh, - short vid) -{ - struct softif_neigh_vid *softif_neigh_vid; - struct softif_neigh *curr_neigh; - - softif_neigh_vid = softif_neigh_vid_get(bat_priv, vid); - if (!softif_neigh_vid) - goto out; - - spin_lock_bh(&bat_priv->softif_neigh_lock); - - if (new_neigh && !atomic_inc_not_zero(&new_neigh->refcount)) - new_neigh = NULL; - - curr_neigh = rcu_dereference_protected(softif_neigh_vid->softif_neigh, - 1); - rcu_assign_pointer(softif_neigh_vid->softif_neigh, new_neigh); - - if ((curr_neigh) && (!new_neigh)) - bat_dbg(DBG_ROUTES, bat_priv, - "Removing mesh exit point on vid: %d (prev: %pM).\n", - vid, curr_neigh->addr); - else if ((curr_neigh) && (new_neigh)) - bat_dbg(DBG_ROUTES, bat_priv, - "Changing mesh exit point on vid: %d from %pM to %pM.\n", - vid, curr_neigh->addr, new_neigh->addr); - else if ((!curr_neigh) && (new_neigh)) - bat_dbg(DBG_ROUTES, bat_priv, - "Setting mesh exit point on vid: %d to %pM.\n", - vid, new_neigh->addr); - - if (curr_neigh) - softif_neigh_free_ref(curr_neigh); - - spin_unlock_bh(&bat_priv->softif_neigh_lock); - -out: - if (softif_neigh_vid) - softif_neigh_vid_free_ref(softif_neigh_vid); -} - -static void softif_neigh_vid_deselect(struct bat_priv *bat_priv, - struct softif_neigh_vid *softif_neigh_vid) -{ - struct softif_neigh *curr_neigh; - struct softif_neigh *softif_neigh = NULL, *softif_neigh_tmp; - struct hard_iface *primary_if = NULL; - struct hlist_node *node; - - primary_if = primary_if_get_selected(bat_priv); - if (!primary_if) - goto out; - - /* find new softif_neigh immediately to avoid temporary loops */ - rcu_read_lock(); - curr_neigh = rcu_dereference(softif_neigh_vid->softif_neigh); - - hlist_for_each_entry_rcu(softif_neigh_tmp, node, - &softif_neigh_vid->softif_neigh_list, - list) { - if (softif_neigh_tmp == curr_neigh) - continue; - - /* we got a neighbor but its mac is 'bigger' than ours */ - if (memcmp(primary_if->net_dev->dev_addr, - softif_neigh_tmp->addr, ETH_ALEN) < 0) - continue; - - if (!atomic_inc_not_zero(&softif_neigh_tmp->refcount)) - continue; - - softif_neigh = softif_neigh_tmp; - goto unlock; - } - -unlock: - rcu_read_unlock(); -out: - softif_neigh_vid_select(bat_priv, softif_neigh, softif_neigh_vid->vid); - - if (primary_if) - hardif_free_ref(primary_if); - if (softif_neigh) - softif_neigh_free_ref(softif_neigh); -} - -int softif_neigh_seq_print_text(struct seq_file *seq, void *offset) -{ - struct net_device *net_dev = (struct net_device *)seq->private; - struct bat_priv *bat_priv = netdev_priv(net_dev); - struct softif_neigh_vid *softif_neigh_vid; - struct softif_neigh *softif_neigh; - struct hard_iface *primary_if; - struct hlist_node *node, *node_tmp; - struct softif_neigh *curr_softif_neigh; - int ret = 0, last_seen_secs, last_seen_msecs; - - primary_if = primary_if_get_selected(bat_priv); - if (!primary_if) { - ret = seq_printf(seq, - "BATMAN mesh %s disabled - please specify interfaces to enable it\n", - net_dev->name); - goto out; - } - - if (primary_if->if_status != IF_ACTIVE) { - ret = seq_printf(seq, - "BATMAN mesh %s disabled - primary interface not active\n", - net_dev->name); - goto out; - } - - seq_printf(seq, "Softif neighbor list (%s)\n", net_dev->name); - - rcu_read_lock(); - hlist_for_each_entry_rcu(softif_neigh_vid, node, - &bat_priv->softif_neigh_vids, list) { - seq_printf(seq, " %-15s %s on vid: %d\n", - "Originator", "last-seen", softif_neigh_vid->vid); - - curr_softif_neigh = softif_neigh_get_selected(softif_neigh_vid); - - hlist_for_each_entry_rcu(softif_neigh, node_tmp, - &softif_neigh_vid->softif_neigh_list, - list) { - last_seen_secs = jiffies_to_msecs(jiffies - - softif_neigh->last_seen) / 1000; - last_seen_msecs = jiffies_to_msecs(jiffies - - softif_neigh->last_seen) % 1000; - seq_printf(seq, "%s %pM %3i.%03is\n", - curr_softif_neigh == softif_neigh - ? "=>" : " ", softif_neigh->addr, - last_seen_secs, last_seen_msecs); - } - - if (curr_softif_neigh) - softif_neigh_free_ref(curr_softif_neigh); - - seq_printf(seq, "\n"); - } - rcu_read_unlock(); - -out: - if (primary_if) - hardif_free_ref(primary_if); - return ret; -} - -void softif_neigh_purge(struct bat_priv *bat_priv) -{ - struct softif_neigh *softif_neigh, *curr_softif_neigh; - struct softif_neigh_vid *softif_neigh_vid; - struct hlist_node *node, *node_tmp, *node_tmp2; - int do_deselect; - - rcu_read_lock(); - hlist_for_each_entry_rcu(softif_neigh_vid, node, - &bat_priv->softif_neigh_vids, list) { - if (!atomic_inc_not_zero(&softif_neigh_vid->refcount)) - continue; - - curr_softif_neigh = softif_neigh_get_selected(softif_neigh_vid); - do_deselect = 0; - - spin_lock_bh(&bat_priv->softif_neigh_lock); - hlist_for_each_entry_safe(softif_neigh, node_tmp, node_tmp2, - &softif_neigh_vid->softif_neigh_list, - list) { - if ((!has_timed_out(softif_neigh->last_seen, - SOFTIF_NEIGH_TIMEOUT)) && - (atomic_read(&bat_priv->mesh_state) == MESH_ACTIVE)) - continue; - - if (curr_softif_neigh == softif_neigh) { - bat_dbg(DBG_ROUTES, bat_priv, - "Current mesh exit point on vid: %d '%pM' vanished.\n", - softif_neigh_vid->vid, - softif_neigh->addr); - do_deselect = 1; - } - - hlist_del_rcu(&softif_neigh->list); - softif_neigh_free_ref(softif_neigh); - } - spin_unlock_bh(&bat_priv->softif_neigh_lock); - - /* soft_neigh_vid_deselect() needs to acquire the - * softif_neigh_lock */ - if (do_deselect) - softif_neigh_vid_deselect(bat_priv, softif_neigh_vid); - - if (curr_softif_neigh) - softif_neigh_free_ref(curr_softif_neigh); - - softif_neigh_vid_free_ref(softif_neigh_vid); - } - rcu_read_unlock(); - - spin_lock_bh(&bat_priv->softif_neigh_vid_lock); - hlist_for_each_entry_safe(softif_neigh_vid, node, node_tmp, - &bat_priv->softif_neigh_vids, list) { - if (!hlist_empty(&softif_neigh_vid->softif_neigh_list)) - continue; - - hlist_del_rcu(&softif_neigh_vid->list); - softif_neigh_vid_free_ref(softif_neigh_vid); - } - spin_unlock_bh(&bat_priv->softif_neigh_vid_lock); - -} - -static void softif_batman_recv(struct sk_buff *skb, struct net_device *dev, - short vid) -{ - struct bat_priv *bat_priv = netdev_priv(dev); - struct ethhdr *ethhdr = (struct ethhdr *)skb->data; - struct batman_ogm_packet *batman_ogm_packet; - struct softif_neigh *softif_neigh = NULL; - struct hard_iface *primary_if = NULL; - struct softif_neigh *curr_softif_neigh = NULL; - - if (ntohs(ethhdr->h_proto) == ETH_P_8021Q) - batman_ogm_packet = (struct batman_ogm_packet *) - (skb->data + ETH_HLEN + VLAN_HLEN); - else - batman_ogm_packet = (struct batman_ogm_packet *) - (skb->data + ETH_HLEN); - - if (batman_ogm_packet->header.version != COMPAT_VERSION) - goto out; - - if (batman_ogm_packet->header.packet_type != BAT_OGM) - goto out; - - if (!(batman_ogm_packet->flags & PRIMARIES_FIRST_HOP)) - goto out; - - if (is_my_mac(batman_ogm_packet->orig)) - goto out; - - softif_neigh = softif_neigh_get(bat_priv, batman_ogm_packet->orig, vid); - if (!softif_neigh) - goto out; - - curr_softif_neigh = softif_neigh_vid_get_selected(bat_priv, vid); - if (curr_softif_neigh == softif_neigh) - goto out; - - primary_if = primary_if_get_selected(bat_priv); - if (!primary_if) - goto out; - - /* we got a neighbor but its mac is 'bigger' than ours */ - if (memcmp(primary_if->net_dev->dev_addr, - softif_neigh->addr, ETH_ALEN) < 0) - goto out; - - /* close own batX device and use softif_neigh as exit node */ - if (!curr_softif_neigh) { - softif_neigh_vid_select(bat_priv, softif_neigh, vid); - goto out; - } - - /* switch to new 'smallest neighbor' */ - if (memcmp(softif_neigh->addr, curr_softif_neigh->addr, ETH_ALEN) < 0) - softif_neigh_vid_select(bat_priv, softif_neigh, vid); - -out: - kfree_skb(skb); - if (softif_neigh) - softif_neigh_free_ref(softif_neigh); - if (curr_softif_neigh) - softif_neigh_free_ref(curr_softif_neigh); - if (primary_if) - hardif_free_ref(primary_if); - return; -} - static int interface_open(struct net_device *dev) { netif_start_queue(dev); @@ -562,10 +130,11 @@ static int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) struct hard_iface *primary_if = NULL; struct bcast_packet *bcast_packet; struct vlan_ethhdr *vhdr; - struct softif_neigh *curr_softif_neigh = NULL; + static const uint8_t stp_addr[ETH_ALEN] = {0x01, 0x80, 0xC2, 0x00, 0x00, + 0x00}; unsigned int header_len = 0; int data_len = skb->len, ret; - short vid = -1; + short vid __maybe_unused = -1; bool do_bcast = false; if (atomic_read(&bat_priv->mesh_state) != MESH_ACTIVE) @@ -583,21 +152,21 @@ static int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) /* fall through */ case ETH_P_BATMAN: - softif_batman_recv(skb, soft_iface, vid); - goto end; + goto dropped; } - /** - * if we have a another chosen mesh exit node in range - * it will transport the packets to the mesh - */ - curr_softif_neigh = softif_neigh_vid_get_selected(bat_priv, vid); - if (curr_softif_neigh) + if (bla_tx(bat_priv, skb, vid)) goto dropped; /* Register the client MAC in the transtable */ tt_local_add(soft_iface, ethhdr->h_source, skb->skb_iif); + /* don't accept stp packets. STP does not help in meshes. + * better use the bridge loop avoidance ... + */ + if (compare_eth(ethhdr->h_dest, stp_addr)) + goto dropped; + if (is_multicast_ether_addr(ethhdr->h_dest)) { do_bcast = true; @@ -675,8 +244,6 @@ dropped: dropped_freed: bat_priv->stats.tx_dropped++; end: - if (curr_softif_neigh) - softif_neigh_free_ref(curr_softif_neigh); if (primary_if) hardif_free_ref(primary_if); return NETDEV_TX_OK; @@ -687,12 +254,9 @@ void interface_rx(struct net_device *soft_iface, int hdr_size) { struct bat_priv *bat_priv = netdev_priv(soft_iface); - struct unicast_packet *unicast_packet; struct ethhdr *ethhdr; struct vlan_ethhdr *vhdr; - struct softif_neigh *curr_softif_neigh = NULL; - short vid = -1; - int ret; + short vid __maybe_unused = -1; /* check if enough space is available for pulling, and pull */ if (!pskb_may_pull(skb, hdr_size)) @@ -716,30 +280,6 @@ void interface_rx(struct net_device *soft_iface, goto dropped; } - /** - * if we have a another chosen mesh exit node in range - * it will transport the packets to the non-mesh network - */ - curr_softif_neigh = softif_neigh_vid_get_selected(bat_priv, vid); - if (curr_softif_neigh) { - skb_push(skb, hdr_size); - unicast_packet = (struct unicast_packet *)skb->data; - - if ((unicast_packet->header.packet_type != BAT_UNICAST) && - (unicast_packet->header.packet_type != BAT_UNICAST_FRAG)) - goto dropped; - - skb_reset_mac_header(skb); - - memcpy(unicast_packet->dest, - curr_softif_neigh->addr, ETH_ALEN); - ret = route_unicast_packet(skb, recv_if); - if (ret == NET_RX_DROP) - goto dropped; - - goto out; - } - /* skb->dev & skb->pkt_type are set here */ if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) goto dropped; @@ -752,21 +292,25 @@ void interface_rx(struct net_device *soft_iface, /* skb->ip_summed = CHECKSUM_UNNECESSARY;*/ bat_priv->stats.rx_packets++; - bat_priv->stats.rx_bytes += skb->len + sizeof(struct ethhdr); + bat_priv->stats.rx_bytes += skb->len + ETH_HLEN; soft_iface->last_rx = jiffies; if (is_ap_isolated(bat_priv, ethhdr->h_source, ethhdr->h_dest)) goto dropped; + /* Let the bridge loop avoidance check the packet. If will + * not handle it, we can safely push it up. + */ + if (bla_rx(bat_priv, skb, vid)) + goto out; + netif_rx(skb); goto out; dropped: kfree_skb(skb); out: - if (curr_softif_neigh) - softif_neigh_free_ref(curr_softif_neigh); return; } @@ -828,13 +372,14 @@ struct net_device *softif_create(const char *name) atomic_set(&bat_priv->aggregated_ogms, 1); atomic_set(&bat_priv->bonding, 0); + atomic_set(&bat_priv->bridge_loop_avoidance, 0); atomic_set(&bat_priv->ap_isolation, 0); atomic_set(&bat_priv->vis_mode, VIS_TYPE_CLIENT_UPDATE); atomic_set(&bat_priv->gw_mode, GW_MODE_OFF); atomic_set(&bat_priv->gw_sel_class, 20); atomic_set(&bat_priv->gw_bandwidth, 41); atomic_set(&bat_priv->orig_interval, 1000); - atomic_set(&bat_priv->hop_penalty, 10); + atomic_set(&bat_priv->hop_penalty, 30); atomic_set(&bat_priv->log_level, 0); atomic_set(&bat_priv->fragmentation, 1); atomic_set(&bat_priv->bcast_queue_left, BCAST_QUEUE_LEN); @@ -845,6 +390,7 @@ struct net_device *softif_create(const char *name) atomic_set(&bat_priv->ttvn, 0); atomic_set(&bat_priv->tt_local_changes, 0); atomic_set(&bat_priv->tt_ogm_append_cnt, 0); + atomic_set(&bat_priv->bla_num_requests, 0); bat_priv->tt_buff = NULL; bat_priv->tt_buff_len = 0; diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index 756eab5b8dd..02030067388 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -23,8 +23,6 @@ #define _NET_BATMAN_ADV_SOFT_INTERFACE_H_ int my_skb_head_push(struct sk_buff *skb, unsigned int len); -int softif_neigh_seq_print_text(struct seq_file *seq, void *offset); -void softif_neigh_purge(struct bat_priv *bat_priv); void interface_rx(struct net_device *soft_iface, struct sk_buff *skb, struct hard_iface *recv_if, int hdr_size); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 1f869212784..a66c2dcd108 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1,7 +1,7 @@ /* * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * - * Marek Lindner, Simon Wunderlich + * Marek Lindner, Simon Wunderlich, Antonio Quartulli * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -27,13 +27,14 @@ #include "hash.h" #include "originator.h" #include "routing.h" +#include "bridge_loop_avoidance.h" #include <linux/crc16.h> -static void _tt_global_del(struct bat_priv *bat_priv, - struct tt_global_entry *tt_global_entry, - const char *message); +static void send_roam_adv(struct bat_priv *bat_priv, uint8_t *client, + struct orig_node *orig_node); static void tt_purge(struct work_struct *work); +static void tt_global_del_orig_list(struct tt_global_entry *tt_global_entry); /* returns 1 if they are the same mac addr */ static int compare_tt(const struct hlist_node *node, const void *data2) @@ -123,17 +124,31 @@ static void tt_global_entry_free_rcu(struct rcu_head *rcu) tt_global_entry = container_of(tt_common_entry, struct tt_global_entry, common); - if (tt_global_entry->orig_node) - orig_node_free_ref(tt_global_entry->orig_node); - kfree(tt_global_entry); } static void tt_global_entry_free_ref(struct tt_global_entry *tt_global_entry) { - if (atomic_dec_and_test(&tt_global_entry->common.refcount)) + if (atomic_dec_and_test(&tt_global_entry->common.refcount)) { + tt_global_del_orig_list(tt_global_entry); call_rcu(&tt_global_entry->common.rcu, tt_global_entry_free_rcu); + } +} + +static void tt_orig_list_entry_free_rcu(struct rcu_head *rcu) +{ + struct tt_orig_list_entry *orig_entry; + + orig_entry = container_of(rcu, struct tt_orig_list_entry, rcu); + atomic_dec(&orig_entry->orig_node->tt_size); + orig_node_free_ref(orig_entry->orig_node); + kfree(orig_entry); +} + +static void tt_orig_list_entry_free_ref(struct tt_orig_list_entry *orig_entry) +{ + call_rcu(&orig_entry->rcu, tt_orig_list_entry_free_rcu); } static void tt_local_event(struct bat_priv *bat_priv, const uint8_t *addr, @@ -182,12 +197,17 @@ void tt_local_add(struct net_device *soft_iface, const uint8_t *addr, struct bat_priv *bat_priv = netdev_priv(soft_iface); struct tt_local_entry *tt_local_entry = NULL; struct tt_global_entry *tt_global_entry = NULL; + struct hlist_head *head; + struct hlist_node *node; + struct tt_orig_list_entry *orig_entry; int hash_added; tt_local_entry = tt_local_hash_find(bat_priv, addr); if (tt_local_entry) { tt_local_entry->last_seen = jiffies; + /* possibly unset the TT_CLIENT_PENDING flag */ + tt_local_entry->common.flags &= ~TT_CLIENT_PENDING; goto out; } @@ -232,14 +252,21 @@ void tt_local_add(struct net_device *soft_iface, const uint8_t *addr, /* Check whether it is a roaming! */ if (tt_global_entry) { - /* This node is probably going to update its tt table */ - tt_global_entry->orig_node->tt_poss_change = true; - /* The global entry has to be marked as ROAMING and has to be - * kept for consistency purpose */ + /* These node are probably going to update their tt table */ + head = &tt_global_entry->orig_list; + rcu_read_lock(); + hlist_for_each_entry_rcu(orig_entry, node, head, list) { + orig_entry->orig_node->tt_poss_change = true; + + send_roam_adv(bat_priv, tt_global_entry->common.addr, + orig_entry->orig_node); + } + rcu_read_unlock(); + /* The global entry has to be marked as ROAMING and + * has to be kept for consistency purpose + */ tt_global_entry->common.flags |= TT_CLIENT_ROAM; tt_global_entry->roam_at = jiffies; - send_roam_adv(bat_priv, tt_global_entry->common.addr, - tt_global_entry->orig_node); } out: if (tt_local_entry) @@ -490,33 +517,76 @@ static void tt_changes_list_free(struct bat_priv *bat_priv) spin_unlock_bh(&bat_priv->tt_changes_list_lock); } +/* find out if an orig_node is already in the list of a tt_global_entry. + * returns 1 if found, 0 otherwise + */ +static bool tt_global_entry_has_orig(const struct tt_global_entry *entry, + const struct orig_node *orig_node) +{ + struct tt_orig_list_entry *tmp_orig_entry; + const struct hlist_head *head; + struct hlist_node *node; + bool found = false; + + rcu_read_lock(); + head = &entry->orig_list; + hlist_for_each_entry_rcu(tmp_orig_entry, node, head, list) { + if (tmp_orig_entry->orig_node == orig_node) { + found = true; + break; + } + } + rcu_read_unlock(); + return found; +} + +static void tt_global_add_orig_entry(struct tt_global_entry *tt_global_entry, + struct orig_node *orig_node, + int ttvn) +{ + struct tt_orig_list_entry *orig_entry; + + orig_entry = kzalloc(sizeof(*orig_entry), GFP_ATOMIC); + if (!orig_entry) + return; + + INIT_HLIST_NODE(&orig_entry->list); + atomic_inc(&orig_node->refcount); + atomic_inc(&orig_node->tt_size); + orig_entry->orig_node = orig_node; + orig_entry->ttvn = ttvn; + + spin_lock_bh(&tt_global_entry->list_lock); + hlist_add_head_rcu(&orig_entry->list, + &tt_global_entry->orig_list); + spin_unlock_bh(&tt_global_entry->list_lock); +} + /* caller must hold orig_node refcount */ int tt_global_add(struct bat_priv *bat_priv, struct orig_node *orig_node, const unsigned char *tt_addr, uint8_t ttvn, bool roaming, bool wifi) { - struct tt_global_entry *tt_global_entry; - struct orig_node *orig_node_tmp; + struct tt_global_entry *tt_global_entry = NULL; int ret = 0; int hash_added; tt_global_entry = tt_global_hash_find(bat_priv, tt_addr); if (!tt_global_entry) { - tt_global_entry = - kmalloc(sizeof(*tt_global_entry), - GFP_ATOMIC); + tt_global_entry = kzalloc(sizeof(*tt_global_entry), + GFP_ATOMIC); if (!tt_global_entry) goto out; memcpy(tt_global_entry->common.addr, tt_addr, ETH_ALEN); + tt_global_entry->common.flags = NO_FLAGS; - atomic_set(&tt_global_entry->common.refcount, 2); - /* Assign the new orig_node */ - atomic_inc(&orig_node->refcount); - tt_global_entry->orig_node = orig_node; - tt_global_entry->ttvn = ttvn; tt_global_entry->roam_at = 0; + atomic_set(&tt_global_entry->common.refcount, 2); + + INIT_HLIST_HEAD(&tt_global_entry->orig_list); + spin_lock_init(&tt_global_entry->list_lock); hash_added = hash_add(bat_priv->tt_global_hash, compare_tt, choose_orig, &tt_global_entry->common, @@ -527,19 +597,27 @@ int tt_global_add(struct bat_priv *bat_priv, struct orig_node *orig_node, tt_global_entry_free_ref(tt_global_entry); goto out_remove; } - atomic_inc(&orig_node->tt_size); + + tt_global_add_orig_entry(tt_global_entry, orig_node, ttvn); } else { - if (tt_global_entry->orig_node != orig_node) { - atomic_dec(&tt_global_entry->orig_node->tt_size); - orig_node_tmp = tt_global_entry->orig_node; - atomic_inc(&orig_node->refcount); - tt_global_entry->orig_node = orig_node; - orig_node_free_ref(orig_node_tmp); - atomic_inc(&orig_node->tt_size); + /* there is already a global entry, use this one. */ + + /* If there is the TT_CLIENT_ROAM flag set, there is only one + * originator left in the list and we previously received a + * delete + roaming change for this originator. + * + * We should first delete the old originator before adding the + * new one. + */ + if (tt_global_entry->common.flags & TT_CLIENT_ROAM) { + tt_global_del_orig_list(tt_global_entry); + tt_global_entry->common.flags &= ~TT_CLIENT_ROAM; + tt_global_entry->roam_at = 0; } - tt_global_entry->common.flags = NO_FLAGS; - tt_global_entry->ttvn = ttvn; - tt_global_entry->roam_at = 0; + + if (!tt_global_entry_has_orig(tt_global_entry, orig_node)) + tt_global_add_orig_entry(tt_global_entry, orig_node, + ttvn); } if (wifi) @@ -560,6 +638,34 @@ out: return ret; } +/* print all orig nodes who announce the address for this global entry. + * it is assumed that the caller holds rcu_read_lock(); + */ +static void tt_global_print_entry(struct tt_global_entry *tt_global_entry, + struct seq_file *seq) +{ + struct hlist_head *head; + struct hlist_node *node; + struct tt_orig_list_entry *orig_entry; + struct tt_common_entry *tt_common_entry; + uint16_t flags; + uint8_t last_ttvn; + + tt_common_entry = &tt_global_entry->common; + + head = &tt_global_entry->orig_list; + + hlist_for_each_entry_rcu(orig_entry, node, head, list) { + flags = tt_common_entry->flags; + last_ttvn = atomic_read(&orig_entry->orig_node->last_ttvn); + seq_printf(seq, " * %pM (%3u) via %pM (%3u) [%c%c]\n", + tt_global_entry->common.addr, orig_entry->ttvn, + orig_entry->orig_node->orig, last_ttvn, + (flags & TT_CLIENT_ROAM ? 'R' : '.'), + (flags & TT_CLIENT_WIFI ? 'W' : '.')); + } +} + int tt_global_seq_print_text(struct seq_file *seq, void *offset) { struct net_device *net_dev = (struct net_device *)seq->private; @@ -603,18 +709,7 @@ int tt_global_seq_print_text(struct seq_file *seq, void *offset) tt_global_entry = container_of(tt_common_entry, struct tt_global_entry, common); - seq_printf(seq, - " * %pM (%3u) via %pM (%3u) [%c%c]\n", - tt_global_entry->common.addr, - tt_global_entry->ttvn, - tt_global_entry->orig_node->orig, - (uint8_t) atomic_read( - &tt_global_entry->orig_node-> - last_ttvn), - (tt_global_entry->common.flags & - TT_CLIENT_ROAM ? 'R' : '.'), - (tt_global_entry->common.flags & - TT_CLIENT_WIFI ? 'W' : '.')); + tt_global_print_entry(tt_global_entry, seq); } rcu_read_unlock(); } @@ -624,59 +719,150 @@ out: return ret; } -static void _tt_global_del(struct bat_priv *bat_priv, - struct tt_global_entry *tt_global_entry, - const char *message) +/* deletes the orig list of a tt_global_entry */ +static void tt_global_del_orig_list(struct tt_global_entry *tt_global_entry) { - if (!tt_global_entry) - goto out; + struct hlist_head *head; + struct hlist_node *node, *safe; + struct tt_orig_list_entry *orig_entry; - bat_dbg(DBG_TT, bat_priv, - "Deleting global tt entry %pM (via %pM): %s\n", - tt_global_entry->common.addr, tt_global_entry->orig_node->orig, - message); + spin_lock_bh(&tt_global_entry->list_lock); + head = &tt_global_entry->orig_list; + hlist_for_each_entry_safe(orig_entry, node, safe, head, list) { + hlist_del_rcu(node); + tt_orig_list_entry_free_ref(orig_entry); + } + spin_unlock_bh(&tt_global_entry->list_lock); - atomic_dec(&tt_global_entry->orig_node->tt_size); +} + +static void tt_global_del_orig_entry(struct bat_priv *bat_priv, + struct tt_global_entry *tt_global_entry, + struct orig_node *orig_node, + const char *message) +{ + struct hlist_head *head; + struct hlist_node *node, *safe; + struct tt_orig_list_entry *orig_entry; + + spin_lock_bh(&tt_global_entry->list_lock); + head = &tt_global_entry->orig_list; + hlist_for_each_entry_safe(orig_entry, node, safe, head, list) { + if (orig_entry->orig_node == orig_node) { + bat_dbg(DBG_TT, bat_priv, + "Deleting %pM from global tt entry %pM: %s\n", + orig_node->orig, tt_global_entry->common.addr, + message); + hlist_del_rcu(node); + tt_orig_list_entry_free_ref(orig_entry); + } + } + spin_unlock_bh(&tt_global_entry->list_lock); +} + +static void tt_global_del_struct(struct bat_priv *bat_priv, + struct tt_global_entry *tt_global_entry, + const char *message) +{ + bat_dbg(DBG_TT, bat_priv, + "Deleting global tt entry %pM: %s\n", + tt_global_entry->common.addr, message); hash_remove(bat_priv->tt_global_hash, compare_tt, choose_orig, tt_global_entry->common.addr); -out: - if (tt_global_entry) - tt_global_entry_free_ref(tt_global_entry); + tt_global_entry_free_ref(tt_global_entry); + } -void tt_global_del(struct bat_priv *bat_priv, - struct orig_node *orig_node, const unsigned char *addr, - const char *message, bool roaming) +/* If the client is to be deleted, we check if it is the last origantor entry + * within tt_global entry. If yes, we set the TT_CLIENT_ROAM flag and the timer, + * otherwise we simply remove the originator scheduled for deletion. + */ +static void tt_global_del_roaming(struct bat_priv *bat_priv, + struct tt_global_entry *tt_global_entry, + struct orig_node *orig_node, + const char *message) +{ + bool last_entry = true; + struct hlist_head *head; + struct hlist_node *node; + struct tt_orig_list_entry *orig_entry; + + /* no local entry exists, case 1: + * Check if this is the last one or if other entries exist. + */ + + rcu_read_lock(); + head = &tt_global_entry->orig_list; + hlist_for_each_entry_rcu(orig_entry, node, head, list) { + if (orig_entry->orig_node != orig_node) { + last_entry = false; + break; + } + } + rcu_read_unlock(); + + if (last_entry) { + /* its the last one, mark for roaming. */ + tt_global_entry->common.flags |= TT_CLIENT_ROAM; + tt_global_entry->roam_at = jiffies; + } else + /* there is another entry, we can simply delete this + * one and can still use the other one. + */ + tt_global_del_orig_entry(bat_priv, tt_global_entry, + orig_node, message); +} + + + +static void tt_global_del(struct bat_priv *bat_priv, + struct orig_node *orig_node, + const unsigned char *addr, + const char *message, bool roaming) { struct tt_global_entry *tt_global_entry = NULL; struct tt_local_entry *tt_local_entry = NULL; tt_global_entry = tt_global_hash_find(bat_priv, addr); - if (!tt_global_entry || tt_global_entry->orig_node != orig_node) + if (!tt_global_entry) goto out; - if (!roaming) - goto out_del; + if (!roaming) { + tt_global_del_orig_entry(bat_priv, tt_global_entry, orig_node, + message); + + if (hlist_empty(&tt_global_entry->orig_list)) + tt_global_del_struct(bat_priv, tt_global_entry, + message); + + goto out; + } /* if we are deleting a global entry due to a roam * event, there are two possibilities: - * 1) the client roamed from node A to node B => we mark + * 1) the client roamed from node A to node B => if there + * is only one originator left for this client, we mark * it with TT_CLIENT_ROAM, we start a timer and we * wait for node B to claim it. In case of timeout * the entry is purged. + * + * If there are other originators left, we directly delete + * the originator. * 2) the client roamed to us => we can directly delete * the global entry, since it is useless now. */ + tt_local_entry = tt_local_hash_find(bat_priv, tt_global_entry->common.addr); - if (!tt_local_entry) { - tt_global_entry->common.flags |= TT_CLIENT_ROAM; - tt_global_entry->roam_at = jiffies; - goto out; - } + if (tt_local_entry) { + /* local entry exists, case 2: client roamed to us. */ + tt_global_del_orig_list(tt_global_entry); + tt_global_del_struct(bat_priv, tt_global_entry, message); + } else + /* no local entry exists, case 1: check for roaming */ + tt_global_del_roaming(bat_priv, tt_global_entry, orig_node, + message); -out_del: - _tt_global_del(bat_priv, tt_global_entry, message); out: if (tt_global_entry) @@ -709,11 +895,14 @@ void tt_global_del_orig(struct bat_priv *bat_priv, tt_global_entry = container_of(tt_common_entry, struct tt_global_entry, common); - if (tt_global_entry->orig_node == orig_node) { + + tt_global_del_orig_entry(bat_priv, tt_global_entry, + orig_node, message); + + if (hlist_empty(&tt_global_entry->orig_list)) { bat_dbg(DBG_TT, bat_priv, - "Deleting global tt entry %pM (via %pM): %s\n", + "Deleting global tt entry %pM: %s\n", tt_global_entry->common.addr, - tt_global_entry->orig_node->orig, message); hlist_del_rcu(node); tt_global_entry_free_ref(tt_global_entry); @@ -754,7 +943,7 @@ static void tt_global_roam_purge(struct bat_priv *bat_priv) bat_dbg(DBG_TT, bat_priv, "Deleting global tt entry (%pM): Roaming timeout\n", tt_global_entry->common.addr); - atomic_dec(&tt_global_entry->orig_node->tt_size); + hlist_del_rcu(node); tt_global_entry_free_ref(tt_global_entry); } @@ -817,6 +1006,11 @@ struct orig_node *transtable_search(struct bat_priv *bat_priv, struct tt_local_entry *tt_local_entry = NULL; struct tt_global_entry *tt_global_entry = NULL; struct orig_node *orig_node = NULL; + struct neigh_node *router = NULL; + struct hlist_head *head; + struct hlist_node *node; + struct tt_orig_list_entry *orig_entry; + int best_tq; if (src && atomic_read(&bat_priv->ap_isolation)) { tt_local_entry = tt_local_hash_find(bat_priv, src); @@ -833,11 +1027,25 @@ struct orig_node *transtable_search(struct bat_priv *bat_priv, if (tt_local_entry && _is_ap_isolated(tt_local_entry, tt_global_entry)) goto out; - if (!atomic_inc_not_zero(&tt_global_entry->orig_node->refcount)) - goto out; + best_tq = 0; - orig_node = tt_global_entry->orig_node; + rcu_read_lock(); + head = &tt_global_entry->orig_list; + hlist_for_each_entry_rcu(orig_entry, node, head, list) { + router = orig_node_get_router(orig_entry->orig_node); + if (!router) + continue; + if (router->tq_avg > best_tq) { + orig_node = orig_entry->orig_node; + best_tq = router->tq_avg; + } + neigh_node_free_ref(router); + } + /* found anything? */ + if (orig_node && !atomic_inc_not_zero(&orig_node->refcount)) + orig_node = NULL; + rcu_read_unlock(); out: if (tt_global_entry) tt_global_entry_free_ref(tt_global_entry); @@ -848,7 +1056,8 @@ out: } /* Calculates the checksum of the local table of a given orig_node */ -uint16_t tt_global_crc(struct bat_priv *bat_priv, struct orig_node *orig_node) +static uint16_t tt_global_crc(struct bat_priv *bat_priv, + struct orig_node *orig_node) { uint16_t total = 0, total_one; struct hashtable_t *hash = bat_priv->tt_global_hash; @@ -868,20 +1077,26 @@ uint16_t tt_global_crc(struct bat_priv *bat_priv, struct orig_node *orig_node) tt_global_entry = container_of(tt_common_entry, struct tt_global_entry, common); - if (compare_eth(tt_global_entry->orig_node, - orig_node)) { - /* Roaming clients are in the global table for - * consistency only. They don't have to be - * taken into account while computing the - * global crc */ - if (tt_common_entry->flags & TT_CLIENT_ROAM) - continue; - total_one = 0; - for (j = 0; j < ETH_ALEN; j++) - total_one = crc16_byte(total_one, - tt_common_entry->addr[j]); - total ^= total_one; - } + /* Roaming clients are in the global table for + * consistency only. They don't have to be + * taken into account while computing the + * global crc + */ + if (tt_global_entry->common.flags & TT_CLIENT_ROAM) + continue; + + /* find out if this global entry is announced by this + * originator + */ + if (!tt_global_entry_has_orig(tt_global_entry, + orig_node)) + continue; + + total_one = 0; + for (j = 0; j < ETH_ALEN; j++) + total_one = crc16_byte(total_one, + tt_global_entry->common.addr[j]); + total ^= total_one; } rcu_read_unlock(); } @@ -936,8 +1151,10 @@ static void tt_req_list_free(struct bat_priv *bat_priv) spin_unlock_bh(&bat_priv->tt_req_list_lock); } -void tt_save_orig_buffer(struct bat_priv *bat_priv, struct orig_node *orig_node, - const unsigned char *tt_buff, uint8_t tt_num_changes) +static void tt_save_orig_buffer(struct bat_priv *bat_priv, + struct orig_node *orig_node, + const unsigned char *tt_buff, + uint8_t tt_num_changes) { uint16_t tt_buff_len = tt_len(tt_num_changes); @@ -1020,7 +1237,7 @@ static int tt_global_valid_entry(const void *entry_ptr, const void *data_ptr) tt_global_entry = container_of(tt_common_entry, struct tt_global_entry, common); - return (tt_global_entry->orig_node == orig_node); + return tt_global_entry_has_orig(tt_global_entry, orig_node); } static struct sk_buff *tt_response_fill_table(uint16_t tt_len, uint8_t ttvn, @@ -1124,7 +1341,7 @@ static int send_tt_request(struct bat_priv *bat_priv, memcpy(tt_request->dst, dst_orig_node->orig, ETH_ALEN); tt_request->header.ttl = TTL; tt_request->ttvn = ttvn; - tt_request->tt_data = tt_crc; + tt_request->tt_data = htons(tt_crc); tt_request->flags = TT_REQUEST; if (full_table) @@ -1401,10 +1618,15 @@ out: bool send_tt_response(struct bat_priv *bat_priv, struct tt_query_packet *tt_request) { - if (is_my_mac(tt_request->dst)) + if (is_my_mac(tt_request->dst)) { + /* don't answer backbone gws! */ + if (bla_is_backbone_gw_orig(bat_priv, tt_request->src)) + return true; + return send_my_tt_response(bat_priv, tt_request); - else + } else { return send_other_tt_response(bat_priv, tt_request); + } } static void _tt_update_changes(struct bat_priv *bat_priv, @@ -1508,6 +1730,10 @@ void handle_tt_response(struct bat_priv *bat_priv, tt_response->src, tt_response->ttvn, tt_response->tt_data, (tt_response->flags & TT_FULL_TABLE ? 'F' : '.')); + /* we should have never asked a backbone gw */ + if (bla_is_backbone_gw_orig(bat_priv, tt_response->src)) + goto out; + orig_node = orig_hash_find(bat_priv, tt_response->src); if (!orig_node) goto out; @@ -1627,8 +1853,8 @@ unlock: return ret; } -void send_roam_adv(struct bat_priv *bat_priv, uint8_t *client, - struct orig_node *orig_node) +static void send_roam_adv(struct bat_priv *bat_priv, uint8_t *client, + struct orig_node *orig_node) { struct neigh_node *neigh_node = NULL; struct sk_buff *skb = NULL; @@ -1796,6 +2022,8 @@ void tt_commit_changes(struct bat_priv *bat_priv) /* Increment the TTVN only once per OGM interval */ atomic_inc(&bat_priv->ttvn); + bat_dbg(DBG_TT, bat_priv, "Local changes committed, updating to ttvn %u\n", + (uint8_t)atomic_read(&bat_priv->ttvn)); bat_priv->tt_poss_change = false; } @@ -1836,6 +2064,10 @@ void tt_update_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, uint8_t orig_ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); bool full_table = true; + /* don't care about a backbone gateways updates. */ + if (bla_is_backbone_gw_orig(bat_priv, orig_node->orig)) + return; + /* orig table not initialised AND first diff is in the OGM OR the ttvn * increased by one -> we can apply the attached changes */ if ((!orig_node->tt_initialised && ttvn == 1) || @@ -1873,6 +2105,7 @@ void tt_update_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, } else { /* if we missed more than one change or our tables are not * in sync anymore -> request fresh tt data */ + if (!orig_node->tt_initialised || ttvn != orig_ttvn || orig_node->tt_crc != tt_crc) { request_table: @@ -1886,3 +2119,22 @@ request_table: } } } + +/* returns true whether we know that the client has moved from its old + * originator to another one. This entry is kept is still kept for consistency + * purposes + */ +bool tt_global_client_is_roaming(struct bat_priv *bat_priv, uint8_t *addr) +{ + struct tt_global_entry *tt_global_entry; + bool ret = false; + + tt_global_entry = tt_global_hash_find(bat_priv, addr); + if (!tt_global_entry) + goto out; + + ret = tt_global_entry->common.flags & TT_CLIENT_ROAM; + tt_global_entry_free_ref(tt_global_entry); +out: + return ret; +} diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index c753633b1da..c43374dc364 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -1,7 +1,7 @@ /* * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * - * Marek Lindner, Simon Wunderlich + * Marek Lindner, Simon Wunderlich, Antonio Quartulli * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -39,27 +39,21 @@ int tt_global_add(struct bat_priv *bat_priv, struct orig_node *orig_node, int tt_global_seq_print_text(struct seq_file *seq, void *offset); void tt_global_del_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, const char *message); -void tt_global_del(struct bat_priv *bat_priv, - struct orig_node *orig_node, const unsigned char *addr, - const char *message, bool roaming); struct orig_node *transtable_search(struct bat_priv *bat_priv, const uint8_t *src, const uint8_t *addr); -void tt_save_orig_buffer(struct bat_priv *bat_priv, struct orig_node *orig_node, - const unsigned char *tt_buff, uint8_t tt_num_changes); uint16_t tt_local_crc(struct bat_priv *bat_priv); -uint16_t tt_global_crc(struct bat_priv *bat_priv, struct orig_node *orig_node); void tt_free(struct bat_priv *bat_priv); bool send_tt_response(struct bat_priv *bat_priv, struct tt_query_packet *tt_request); bool is_my_client(struct bat_priv *bat_priv, const uint8_t *addr); void handle_tt_response(struct bat_priv *bat_priv, struct tt_query_packet *tt_response); -void send_roam_adv(struct bat_priv *bat_priv, uint8_t *client, - struct orig_node *orig_node); void tt_commit_changes(struct bat_priv *bat_priv); bool is_ap_isolated(struct bat_priv *bat_priv, uint8_t *src, uint8_t *dst); void tt_update_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, const unsigned char *tt_buff, uint8_t tt_num_changes, uint8_t ttvn, uint16_t tt_crc); +bool tt_global_client_is_roaming(struct bat_priv *bat_priv, uint8_t *addr); + #endif /* _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ */ diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 302efb52347..61308e8016f 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -27,7 +27,7 @@ #include "packet.h" #include "bitarray.h" -#define BAT_HEADER_LEN (sizeof(struct ethhdr) + \ +#define BAT_HEADER_LEN (ETH_HLEN + \ ((sizeof(struct unicast_packet) > sizeof(struct bcast_packet) ? \ sizeof(struct unicast_packet) : \ sizeof(struct bcast_packet)))) @@ -52,7 +52,7 @@ struct hard_iface { /** * orig_node - structure for orig_list maintaining nodes of mesh * @primary_addr: hosts primary interface address - * @last_valid: when last packet from this node was received + * @last_seen: when last packet from this node was received * @bcast_seqno_reset: time when the broadcast seqno window was reset * @batman_seqno_reset: time when the batman seqno window was reset * @gw_flags: flags related to gateway class @@ -70,7 +70,7 @@ struct orig_node { struct neigh_node __rcu *router; /* rcu protected pointer */ unsigned long *bcast_own; uint8_t *bcast_own_sum; - unsigned long last_valid; + unsigned long last_seen; unsigned long bcast_seqno_reset; unsigned long batman_seqno_reset; uint8_t gw_flags; @@ -90,7 +90,7 @@ struct orig_node { bool tt_poss_change; uint32_t last_real_seqno; uint8_t last_ttl; - unsigned long bcast_bits[NUM_WORDS]; + DECLARE_BITMAP(bcast_bits, TQ_LOCAL_WINDOW_SIZE); uint32_t last_bcast_seqno; struct hlist_head neigh_list; struct list_head frag_list; @@ -120,7 +120,7 @@ struct gw_node { /** * neigh_node - * @last_valid: when last packet via this neighbor was received + * @last_seen: when last packet via this neighbor was received */ struct neigh_node { struct hlist_node list; @@ -131,15 +131,22 @@ struct neigh_node { uint8_t tq_avg; uint8_t last_ttl; struct list_head bonding_list; - unsigned long last_valid; - unsigned long real_bits[NUM_WORDS]; + unsigned long last_seen; + DECLARE_BITMAP(real_bits, TQ_LOCAL_WINDOW_SIZE); atomic_t refcount; struct rcu_head rcu; struct orig_node *orig_node; struct hard_iface *if_incoming; - spinlock_t tq_lock; /* protects: tq_recv, tq_index */ + spinlock_t lq_update_lock; /* protects: tq_recv, tq_index */ }; +#ifdef CONFIG_BATMAN_ADV_BLA +struct bcast_duplist_entry { + uint8_t orig[ETH_ALEN]; + uint16_t crc; + unsigned long entrytime; +}; +#endif struct bat_priv { atomic_t mesh_state; @@ -148,6 +155,7 @@ struct bat_priv { atomic_t bonding; /* boolean */ atomic_t fragmentation; /* boolean */ atomic_t ap_isolation; /* boolean */ + atomic_t bridge_loop_avoidance; /* boolean */ atomic_t vis_mode; /* VIS_TYPE_* */ atomic_t gw_mode; /* GW_MODE_* */ atomic_t gw_sel_class; /* uint */ @@ -161,6 +169,7 @@ struct bat_priv { atomic_t ttvn; /* translation table version number */ atomic_t tt_ogm_append_cnt; atomic_t tt_local_changes; /* changes registered in a OGM interval */ + atomic_t bla_num_requests; /* number of bla requests in flight */ /* The tt_poss_change flag is used to detect an ongoing roaming phase. * If true, then I received a Roaming_adv and I have to inspect every * packet directed to me to check whether I am still the true @@ -174,15 +183,23 @@ struct bat_priv { struct hlist_head forw_bat_list; struct hlist_head forw_bcast_list; struct hlist_head gw_list; - struct hlist_head softif_neigh_vids; struct list_head tt_changes_list; /* tracks changes in a OGM int */ struct list_head vis_send_list; struct hashtable_t *orig_hash; struct hashtable_t *tt_local_hash; struct hashtable_t *tt_global_hash; +#ifdef CONFIG_BATMAN_ADV_BLA + struct hashtable_t *claim_hash; + struct hashtable_t *backbone_hash; +#endif struct list_head tt_req_list; /* list of pending tt_requests */ struct list_head tt_roam_list; struct hashtable_t *vis_hash; +#ifdef CONFIG_BATMAN_ADV_BLA + struct bcast_duplist_entry bcast_duplist[DUPLIST_SIZE]; + int bcast_duplist_curr; + struct bla_claim_dst claim_dest; +#endif spinlock_t forw_bat_list_lock; /* protects forw_bat_list */ spinlock_t forw_bcast_list_lock; /* protects */ spinlock_t tt_changes_list_lock; /* protects tt_changes */ @@ -191,8 +208,6 @@ struct bat_priv { spinlock_t gw_list_lock; /* protects gw_list and curr_gw */ spinlock_t vis_hash_lock; /* protects vis_hash */ spinlock_t vis_list_lock; /* protects vis_info::recv_list */ - spinlock_t softif_neigh_lock; /* protects soft-interface neigh list */ - spinlock_t softif_neigh_vid_lock; /* protects soft-interface vid list */ atomic_t num_local_tt; /* Checksum of the local table, recomputed before sending a new OGM */ atomic_t tt_crc; @@ -202,6 +217,7 @@ struct bat_priv { struct delayed_work tt_work; struct delayed_work orig_work; struct delayed_work vis_work; + struct delayed_work bla_work; struct gw_node __rcu *curr_gw; /* rcu protected pointer */ atomic_t gw_reselect; struct hard_iface __rcu *primary_if; /* rcu protected pointer */ @@ -239,10 +255,41 @@ struct tt_local_entry { struct tt_global_entry { struct tt_common_entry common; + struct hlist_head orig_list; + spinlock_t list_lock; /* protects the list */ + unsigned long roam_at; /* time at which TT_GLOBAL_ROAM was set */ +}; + +struct tt_orig_list_entry { struct orig_node *orig_node; uint8_t ttvn; - unsigned long roam_at; /* time at which TT_GLOBAL_ROAM was set */ + struct rcu_head rcu; + struct hlist_node list; +}; + +#ifdef CONFIG_BATMAN_ADV_BLA +struct backbone_gw { + uint8_t orig[ETH_ALEN]; + short vid; /* used VLAN ID */ + struct hlist_node hash_entry; + struct bat_priv *bat_priv; + unsigned long lasttime; /* last time we heard of this backbone gw */ + atomic_t request_sent; + atomic_t refcount; + struct rcu_head rcu; + uint16_t crc; /* crc checksum over all claims */ +}; + +struct claim { + uint8_t addr[ETH_ALEN]; + short vid; + struct backbone_gw *backbone_gw; + unsigned long lasttime; /* last time we heard of claim (locals only) */ + struct rcu_head rcu; + atomic_t refcount; + struct hlist_node hash_entry; }; +#endif struct tt_change_node { struct list_head list; @@ -327,41 +374,24 @@ struct recvlist_node { uint8_t mac[ETH_ALEN]; }; -struct softif_neigh_vid { - struct hlist_node list; - struct bat_priv *bat_priv; - short vid; - atomic_t refcount; - struct softif_neigh __rcu *softif_neigh; - struct rcu_head rcu; - struct hlist_head softif_neigh_list; -}; - -struct softif_neigh { - struct hlist_node list; - uint8_t addr[ETH_ALEN]; - unsigned long last_seen; - atomic_t refcount; - struct rcu_head rcu; -}; - struct bat_algo_ops { struct hlist_node list; char *name; - /* init OGM when hard-interface is enabled */ - void (*bat_ogm_init)(struct hard_iface *hard_iface); - /* init primary OGM when primary interface is selected */ - void (*bat_ogm_init_primary)(struct hard_iface *hard_iface); - /* init mac addresses of the OGM belonging to this hard-interface */ - void (*bat_ogm_update_mac)(struct hard_iface *hard_iface); + /* init routing info when hard-interface is enabled */ + int (*bat_iface_enable)(struct hard_iface *hard_iface); + /* de-init routing info when hard-interface is disabled */ + void (*bat_iface_disable)(struct hard_iface *hard_iface); + /* (re-)init mac addresses of the protocol information + * belonging to this hard-interface + */ + void (*bat_iface_update_mac)(struct hard_iface *hard_iface); + /* called when primary interface is selected / changed */ + void (*bat_primary_iface_set)(struct hard_iface *hard_iface); /* prepare a new outgoing OGM for the send queue */ void (*bat_ogm_schedule)(struct hard_iface *hard_iface, int tt_num_changes); /* send scheduled OGM */ void (*bat_ogm_emit)(struct forw_packet *forw_packet); - /* receive incoming OGM */ - void (*bat_ogm_receive)(struct hard_iface *if_incoming, - struct sk_buff *skb); }; #endif /* _NET_BATMAN_ADV_TYPES_H_ */ diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c index 676f6a626b2..74175c21085 100644 --- a/net/batman-adv/unicast.c +++ b/net/batman-adv/unicast.c @@ -331,6 +331,14 @@ find_router: unicast_packet->ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); + /* inform the destination node that we are still missing a correct route + * for this client. The destination will receive this packet and will + * try to reroute it because the ttvn contained in the header is less + * than the current one + */ + if (tt_global_client_is_roaming(bat_priv, ethhdr->h_dest)) + unicast_packet->ttvn = unicast_packet->ttvn - 1; + if (atomic_read(&bat_priv->fragmentation) && data_len + sizeof(*unicast_packet) > neigh_node->if_incoming->net_dev->mtu) { diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c index c4a5b8cafad..cec216fb77c 100644 --- a/net/batman-adv/vis.c +++ b/net/batman-adv/vis.c @@ -434,12 +434,12 @@ static struct vis_info *add_packet(struct bat_priv *bat_priv, return NULL; info->skb_packet = dev_alloc_skb(sizeof(*packet) + vis_info_len + - sizeof(struct ethhdr)); + ETH_HLEN); if (!info->skb_packet) { kfree(info); return NULL; } - skb_reserve(info->skb_packet, sizeof(struct ethhdr)); + skb_reserve(info->skb_packet, ETH_HLEN); packet = (struct vis_packet *)skb_put(info->skb_packet, sizeof(*packet) + vis_info_len); @@ -894,11 +894,11 @@ int vis_init(struct bat_priv *bat_priv) bat_priv->my_vis_info->skb_packet = dev_alloc_skb(sizeof(*packet) + MAX_VIS_PACKET_SIZE + - sizeof(struct ethhdr)); + ETH_HLEN); if (!bat_priv->my_vis_info->skb_packet) goto free_info; - skb_reserve(bat_priv->my_vis_info->skb_packet, sizeof(struct ethhdr)); + skb_reserve(bat_priv->my_vis_info->skb_packet, ETH_HLEN); packet = (struct vis_packet *)skb_put(bat_priv->my_vis_info->skb_packet, sizeof(*packet)); diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 72eb187a5f6..6fb68a9743a 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -450,7 +450,7 @@ unsigned int bt_sock_poll(struct file *file, struct socket *sock, poll_table *wa sk->sk_state == BT_CONFIG) return mask; - if (sock_writeable(sk)) + if (!bt_sk(sk)->suspended && sock_writeable(sk)) mask |= POLLOUT | POLLWRNORM | POLLWRBAND; else set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index a779ec70332..88884d1d95f 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -69,7 +69,7 @@ static struct bnep_session *__bnep_get_session(u8 *dst) BT_DBG(""); list_for_each_entry(s, &bnep_session_list, list) - if (!compare_ether_addr(dst, s->eh.h_source)) + if (ether_addr_equal(dst, s->eh.h_source)) return s; return NULL; @@ -422,10 +422,10 @@ static inline int bnep_tx_frame(struct bnep_session *s, struct sk_buff *skb) iv[il++] = (struct kvec) { &type, 1 }; len++; - if (compress_src && !compare_ether_addr(eh->h_dest, s->eh.h_source)) + if (compress_src && ether_addr_equal(eh->h_dest, s->eh.h_source)) type |= 0x01; - if (compress_dst && !compare_ether_addr(eh->h_source, s->eh.h_dest)) + if (compress_dst && ether_addr_equal(eh->h_source, s->eh.h_dest)) type |= 0x02; if (type) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index e33af63a884..d6dc44cd15b 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -665,6 +665,11 @@ int hci_dev_open(__u16 dev) hci_req_lock(hdev); + if (test_bit(HCI_UNREGISTER, &hdev->dev_flags)) { + ret = -ENODEV; + goto done; + } + if (hdev->rfkill && rfkill_blocked(hdev->rfkill)) { ret = -ERFKILL; goto done; @@ -1210,40 +1215,40 @@ struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) return NULL; } -static int hci_persistent_key(struct hci_dev *hdev, struct hci_conn *conn, +static bool hci_persistent_key(struct hci_dev *hdev, struct hci_conn *conn, u8 key_type, u8 old_key_type) { /* Legacy key */ if (key_type < 0x03) - return 1; + return true; /* Debug keys are insecure so don't store them persistently */ if (key_type == HCI_LK_DEBUG_COMBINATION) - return 0; + return false; /* Changed combination key and there's no previous one */ if (key_type == HCI_LK_CHANGED_COMBINATION && old_key_type == 0xff) - return 0; + return false; /* Security mode 3 case */ if (!conn) - return 1; + return true; /* Neither local nor remote side had no-bonding as requirement */ if (conn->auth_type > 0x01 && conn->remote_auth > 0x01) - return 1; + return true; /* Local side had dedicated bonding as requirement */ if (conn->auth_type == 0x02 || conn->auth_type == 0x03) - return 1; + return true; /* Remote side had dedicated bonding as requirement */ if (conn->remote_auth == 0x02 || conn->remote_auth == 0x03) - return 1; + return true; /* If none of the above criteria match, then don't store the key * persistently */ - return 0; + return false; } struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, u8 rand[8]) @@ -1280,7 +1285,8 @@ int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key, bdaddr_t *bdaddr, u8 *val, u8 type, u8 pin_len) { struct link_key *key, *old_key; - u8 old_key_type, persistent; + u8 old_key_type; + bool persistent; old_key = hci_find_link_key(hdev, bdaddr); if (old_key) { @@ -1323,10 +1329,8 @@ int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key, mgmt_new_link_key(hdev, key, persistent); - if (!persistent) { - list_del(&key->list); - kfree(key); - } + if (conn) + conn->flush_key = !persistent; return 0; } @@ -1849,6 +1853,8 @@ void hci_unregister_dev(struct hci_dev *hdev) BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); + set_bit(HCI_UNREGISTER, &hdev->dev_flags); + write_lock(&hci_dev_list_lock); list_del(&hdev->list); write_unlock(&hci_dev_list_lock); @@ -2778,6 +2784,14 @@ static inline void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) if (conn) { hci_conn_enter_active_mode(conn, BT_POWER_FORCE_ACTIVE_OFF); + hci_dev_lock(hdev); + if (test_bit(HCI_MGMT, &hdev->dev_flags) && + !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) + mgmt_device_connected(hdev, &conn->dst, conn->type, + conn->dst_type, 0, NULL, 0, + conn->dev_class); + hci_dev_unlock(hdev); + /* Send to upper protocol */ l2cap_recv_acldata(conn, skb, flags); return; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index b37531094c4..1266f78fa8e 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1901,6 +1901,8 @@ static inline void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff } if (ev->status == 0) { + if (conn->type == ACL_LINK && conn->flush_key) + hci_remove_link_key(hdev, &conn->dst); hci_proto_disconn_cfm(conn, ev->reason); hci_conn_del(conn); } @@ -2037,6 +2039,12 @@ static inline void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff * clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); + if (ev->status && conn->state == BT_CONNECTED) { + hci_acl_disconn(conn, 0x13); + hci_conn_put(conn); + goto unlock; + } + if (conn->state == BT_CONFIG) { if (!ev->status) conn->state = BT_CONNECTED; @@ -2047,6 +2055,7 @@ static inline void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff * hci_encrypt_cfm(conn, ev->status, ev->encrypt); } +unlock: hci_dev_unlock(hdev); } @@ -2100,7 +2109,7 @@ static inline void hci_remote_features_evt(struct hci_dev *hdev, struct sk_buff goto unlock; } - if (!ev->status) { + if (!ev->status && !test_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) { struct hci_cp_remote_name_req cp; memset(&cp, 0, sizeof(cp)); bacpy(&cp.bdaddr, &conn->dst); @@ -2311,6 +2320,7 @@ static inline void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *sk case HCI_OP_USER_PASSKEY_NEG_REPLY: hci_cc_user_passkey_neg_reply(hdev, skb); + break; case HCI_OP_LE_SET_SCAN_PARAM: hci_cc_le_set_scan_param(hdev, skb); @@ -2868,7 +2878,7 @@ static inline void hci_remote_ext_features_evt(struct hci_dev *hdev, struct sk_b if (conn->state != BT_CONFIG) goto unlock; - if (!ev->status) { + if (!ev->status && !test_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) { struct hci_cp_remote_name_req cp; memset(&cp, 0, sizeof(cp)); bacpy(&cp.bdaddr, &conn->dst); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index b8e17e4dac8..6f9c25b633a 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1308,6 +1308,7 @@ static void l2cap_monitor_timeout(struct work_struct *work) if (chan->retry_count >= chan->remote_max_tx) { l2cap_send_disconn_req(chan->conn, chan, ECONNABORTED); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); return; } @@ -1316,6 +1317,7 @@ static void l2cap_monitor_timeout(struct work_struct *work) l2cap_send_rr_or_rnr(chan, L2CAP_CTRL_POLL); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); } static void l2cap_retrans_timeout(struct work_struct *work) @@ -1335,6 +1337,7 @@ static void l2cap_retrans_timeout(struct work_struct *work) l2cap_send_rr_or_rnr(chan, L2CAP_CTRL_POLL); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); } static void l2cap_drop_acked_frames(struct l2cap_chan *chan) @@ -4586,6 +4589,11 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) if (!status && (chan->state == BT_CONNECTED || chan->state == BT_CONFIG)) { + struct sock *sk = chan->sk; + + bt_sk(sk)->suspended = false; + sk->sk_state_change(sk); + l2cap_check_encryption(chan, encrypt); l2cap_chan_unlock(chan); continue; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index c4fe583b0af..04e7c172d49 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -82,7 +82,7 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) } if (la.l2_cid) - err = l2cap_add_scid(chan, la.l2_cid); + err = l2cap_add_scid(chan, __le16_to_cpu(la.l2_cid)); else err = l2cap_add_psm(chan, &la.l2_bdaddr, la.l2_psm); @@ -123,7 +123,8 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int al if (la.l2_cid && la.l2_psm) return -EINVAL; - err = l2cap_chan_connect(chan, la.l2_psm, la.l2_cid, &la.l2_bdaddr); + err = l2cap_chan_connect(chan, la.l2_psm, __le16_to_cpu(la.l2_cid), + &la.l2_bdaddr); if (err) return err; @@ -591,10 +592,14 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch sk->sk_state = BT_CONFIG; chan->state = BT_CONFIG; - /* or for ACL link, under defer_setup time */ - } else if (sk->sk_state == BT_CONNECT2 && - bt_sk(sk)->defer_setup) { - err = l2cap_chan_check_security(chan); + /* or for ACL link */ + } else if ((sk->sk_state == BT_CONNECT2 && + bt_sk(sk)->defer_setup) || + sk->sk_state == BT_CONNECTED) { + if (!l2cap_chan_check_security(chan)) + bt_sk(sk)->suspended = true; + else + sk->sk_state_change(sk); } else { err = -EINVAL; } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 7fcff888713..4bb03b11112 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2523,13 +2523,18 @@ static int set_fast_connectable(struct sock *sk, struct hci_dev *hdev, if (cp->val) { type = PAGE_SCAN_TYPE_INTERLACED; - acp.interval = 0x0024; /* 22.5 msec page scan interval */ + + /* 22.5 msec page scan interval */ + acp.interval = __constant_cpu_to_le16(0x0024); } else { type = PAGE_SCAN_TYPE_STANDARD; /* default */ - acp.interval = 0x0800; /* default 1.28 sec page scan */ + + /* default 1.28 sec page scan */ + acp.interval = __constant_cpu_to_le16(0x0800); } - acp.window = 0x0012; /* default 11.25 msec page scan window */ + /* default 11.25 msec page scan window */ + acp.window = __constant_cpu_to_le16(0x0012); err = hci_send_cmd(hdev, HCI_OP_WRITE_PAGE_SCAN_ACTIVITY, sizeof(acp), &acp); @@ -2879,7 +2884,7 @@ int mgmt_write_scan_failed(struct hci_dev *hdev, u8 scan, u8 status) return 0; } -int mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, u8 persistent) +int mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, bool persistent) { struct mgmt_ev_new_link_key ev; @@ -2936,7 +2941,7 @@ int mgmt_device_connected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, name, name_len); if (dev_class && memcmp(dev_class, "\0\0\0", 3) != 0) - eir_len = eir_append_data(&ev->eir[eir_len], eir_len, + eir_len = eir_append_data(ev->eir, eir_len, EIR_CLASS_OF_DEV, dev_class, 3); put_unaligned_le16(eir_len, &ev->eir_len); diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 4bf54b37725..aa5d73b786a 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -48,13 +48,12 @@ static struct tty_driver *rfcomm_tty_driver; struct rfcomm_dev { + struct tty_port port; struct list_head list; - atomic_t refcnt; char name[12]; int id; unsigned long flags; - atomic_t opened; int err; bdaddr_t src; @@ -64,9 +63,7 @@ struct rfcomm_dev { uint modem_status; struct rfcomm_dlc *dlc; - struct tty_struct *tty; wait_queue_head_t wait; - struct work_struct wakeup_task; struct device *tty_dev; @@ -82,11 +79,18 @@ static void rfcomm_dev_data_ready(struct rfcomm_dlc *dlc, struct sk_buff *skb); static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err); static void rfcomm_dev_modem_status(struct rfcomm_dlc *dlc, u8 v24_sig); -static void rfcomm_tty_wakeup(struct work_struct *work); - /* ---- Device functions ---- */ -static void rfcomm_dev_destruct(struct rfcomm_dev *dev) + +/* + * The reason this isn't actually a race, as you no doubt have a little voice + * screaming at you in your head, is that the refcount should never actually + * reach zero unless the device has already been taken off the list, in + * rfcomm_dev_del(). And if that's not true, we'll hit the BUG() in + * rfcomm_dev_destruct() anyway. + */ +static void rfcomm_dev_destruct(struct tty_port *port) { + struct rfcomm_dev *dev = container_of(port, struct rfcomm_dev, port); struct rfcomm_dlc *dlc = dev->dlc; BT_DBG("dev %p dlc %p", dev, dlc); @@ -113,23 +117,9 @@ static void rfcomm_dev_destruct(struct rfcomm_dev *dev) module_put(THIS_MODULE); } -static inline void rfcomm_dev_hold(struct rfcomm_dev *dev) -{ - atomic_inc(&dev->refcnt); -} - -static inline void rfcomm_dev_put(struct rfcomm_dev *dev) -{ - /* The reason this isn't actually a race, as you no - doubt have a little voice screaming at you in your - head, is that the refcount should never actually - reach zero unless the device has already been taken - off the list, in rfcomm_dev_del(). And if that's not - true, we'll hit the BUG() in rfcomm_dev_destruct() - anyway. */ - if (atomic_dec_and_test(&dev->refcnt)) - rfcomm_dev_destruct(dev); -} +static const struct tty_port_operations rfcomm_port_ops = { + .destruct = rfcomm_dev_destruct, +}; static struct rfcomm_dev *__rfcomm_dev_get(int id) { @@ -154,7 +144,7 @@ static inline struct rfcomm_dev *rfcomm_dev_get(int id) if (test_bit(RFCOMM_TTY_RELEASED, &dev->flags)) dev = NULL; else - rfcomm_dev_hold(dev); + tty_port_get(&dev->port); } spin_unlock(&rfcomm_dev_lock); @@ -241,7 +231,6 @@ static int rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc) sprintf(dev->name, "rfcomm%d", dev->id); list_add(&dev->list, head); - atomic_set(&dev->refcnt, 1); bacpy(&dev->src, &req->src); bacpy(&dev->dst, &req->dst); @@ -250,10 +239,9 @@ static int rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc) dev->flags = req->flags & ((1 << RFCOMM_RELEASE_ONHUP) | (1 << RFCOMM_REUSE_DLC)); - atomic_set(&dev->opened, 0); - + tty_port_init(&dev->port); + dev->port.ops = &rfcomm_port_ops; init_waitqueue_head(&dev->wait); - INIT_WORK(&dev->wakeup_task, rfcomm_tty_wakeup); skb_queue_head_init(&dev->pending); @@ -320,18 +308,23 @@ free: static void rfcomm_dev_del(struct rfcomm_dev *dev) { + unsigned long flags; BT_DBG("dev %p", dev); BUG_ON(test_and_set_bit(RFCOMM_TTY_RELEASED, &dev->flags)); - if (atomic_read(&dev->opened) > 0) + spin_lock_irqsave(&dev->port.lock, flags); + if (dev->port.count > 0) { + spin_unlock_irqrestore(&dev->port.lock, flags); return; + } + spin_unlock_irqrestore(&dev->port.lock, flags); spin_lock(&rfcomm_dev_lock); list_del_init(&dev->list); spin_unlock(&rfcomm_dev_lock); - rfcomm_dev_put(dev); + tty_port_put(&dev->port); } /* ---- Send buffer ---- */ @@ -345,15 +338,16 @@ static inline unsigned int rfcomm_room(struct rfcomm_dlc *dlc) static void rfcomm_wfree(struct sk_buff *skb) { struct rfcomm_dev *dev = (void *) skb->sk; + struct tty_struct *tty = dev->port.tty; atomic_sub(skb->truesize, &dev->wmem_alloc); - if (test_bit(RFCOMM_TTY_ATTACHED, &dev->flags)) - queue_work(system_nrt_wq, &dev->wakeup_task); - rfcomm_dev_put(dev); + if (test_bit(RFCOMM_TTY_ATTACHED, &dev->flags) && tty) + tty_wakeup(tty); + tty_port_put(&dev->port); } static inline void rfcomm_set_owner_w(struct sk_buff *skb, struct rfcomm_dev *dev) { - rfcomm_dev_hold(dev); + tty_port_get(&dev->port); atomic_add(skb->truesize, &dev->wmem_alloc); skb->sk = (void *) dev; skb->destructor = rfcomm_wfree; @@ -432,7 +426,7 @@ static int rfcomm_release_dev(void __user *arg) return -ENODEV; if (dev->flags != NOCAP_FLAGS && !capable(CAP_NET_ADMIN)) { - rfcomm_dev_put(dev); + tty_port_put(&dev->port); return -EPERM; } @@ -440,12 +434,12 @@ static int rfcomm_release_dev(void __user *arg) rfcomm_dlc_close(dev->dlc, 0); /* Shut down TTY synchronously before freeing rfcomm_dev */ - if (dev->tty) - tty_vhangup(dev->tty); + if (dev->port.tty) + tty_vhangup(dev->port.tty); if (!test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags)) rfcomm_dev_del(dev); - rfcomm_dev_put(dev); + tty_port_put(&dev->port); return 0; } @@ -523,7 +517,7 @@ static int rfcomm_get_dev_info(void __user *arg) if (copy_to_user(arg, &di, sizeof(di))) err = -EFAULT; - rfcomm_dev_put(dev); + tty_port_put(&dev->port); return err; } @@ -559,7 +553,7 @@ static void rfcomm_dev_data_ready(struct rfcomm_dlc *dlc, struct sk_buff *skb) return; } - tty = dev->tty; + tty = dev->port.tty; if (!tty || !skb_queue_empty(&dev->pending)) { skb_queue_tail(&dev->pending, skb); return; @@ -585,13 +579,13 @@ static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err) wake_up_interruptible(&dev->wait); if (dlc->state == BT_CLOSED) { - if (!dev->tty) { + if (!dev->port.tty) { if (test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags)) { /* Drop DLC lock here to avoid deadlock * 1. rfcomm_dev_get will take rfcomm_dev_lock * but in rfcomm_dev_add there's lock order: * rfcomm_dev_lock -> dlc lock - * 2. rfcomm_dev_put will deadlock if it's + * 2. tty_port_put will deadlock if it's * the last reference */ rfcomm_dlc_unlock(dlc); @@ -601,11 +595,11 @@ static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err) } rfcomm_dev_del(dev); - rfcomm_dev_put(dev); + tty_port_put(&dev->port); rfcomm_dlc_lock(dlc); } } else - tty_hangup(dev->tty); + tty_hangup(dev->port.tty); } } @@ -618,8 +612,8 @@ static void rfcomm_dev_modem_status(struct rfcomm_dlc *dlc, u8 v24_sig) BT_DBG("dlc %p dev %p v24_sig 0x%02x", dlc, dev, v24_sig); if ((dev->modem_status & TIOCM_CD) && !(v24_sig & RFCOMM_V24_DV)) { - if (dev->tty && !C_CLOCAL(dev->tty)) - tty_hangup(dev->tty); + if (dev->port.tty && !C_CLOCAL(dev->port.tty)) + tty_hangup(dev->port.tty); } dev->modem_status = @@ -630,21 +624,9 @@ static void rfcomm_dev_modem_status(struct rfcomm_dlc *dlc, u8 v24_sig) } /* ---- TTY functions ---- */ -static void rfcomm_tty_wakeup(struct work_struct *work) -{ - struct rfcomm_dev *dev = container_of(work, struct rfcomm_dev, - wakeup_task); - struct tty_struct *tty = dev->tty; - if (!tty) - return; - - BT_DBG("dev %p tty %p", dev, tty); - tty_wakeup(tty); -} - static void rfcomm_tty_copy_pending(struct rfcomm_dev *dev) { - struct tty_struct *tty = dev->tty; + struct tty_struct *tty = dev->port.tty; struct sk_buff *skb; int inserted = 0; @@ -671,6 +653,7 @@ static int rfcomm_tty_open(struct tty_struct *tty, struct file *filp) DECLARE_WAITQUEUE(wait, current); struct rfcomm_dev *dev; struct rfcomm_dlc *dlc; + unsigned long flags; int err, id; id = tty->index; @@ -686,10 +669,14 @@ static int rfcomm_tty_open(struct tty_struct *tty, struct file *filp) return -ENODEV; BT_DBG("dev %p dst %s channel %d opened %d", dev, batostr(&dev->dst), - dev->channel, atomic_read(&dev->opened)); + dev->channel, dev->port.count); - if (atomic_inc_return(&dev->opened) > 1) + spin_lock_irqsave(&dev->port.lock, flags); + if (++dev->port.count > 1) { + spin_unlock_irqrestore(&dev->port.lock, flags); return 0; + } + spin_unlock_irqrestore(&dev->port.lock, flags); dlc = dev->dlc; @@ -697,7 +684,7 @@ static int rfcomm_tty_open(struct tty_struct *tty, struct file *filp) rfcomm_dlc_lock(dlc); tty->driver_data = dev; - dev->tty = tty; + dev->port.tty = tty; rfcomm_dlc_unlock(dlc); set_bit(RFCOMM_TTY_ATTACHED, &dev->flags); @@ -723,9 +710,9 @@ static int rfcomm_tty_open(struct tty_struct *tty, struct file *filp) break; } - tty_unlock(); + tty_unlock(tty); schedule(); - tty_lock(); + tty_lock(tty); } set_current_state(TASK_RUNNING); remove_wait_queue(&dev->wait, &wait); @@ -744,13 +731,17 @@ static int rfcomm_tty_open(struct tty_struct *tty, struct file *filp) static void rfcomm_tty_close(struct tty_struct *tty, struct file *filp) { struct rfcomm_dev *dev = (struct rfcomm_dev *) tty->driver_data; + unsigned long flags; + if (!dev) return; BT_DBG("tty %p dev %p dlc %p opened %d", tty, dev, dev->dlc, - atomic_read(&dev->opened)); + dev->port.count); - if (atomic_dec_and_test(&dev->opened)) { + spin_lock_irqsave(&dev->port.lock, flags); + if (!--dev->port.count) { + spin_unlock_irqrestore(&dev->port.lock, flags); if (dev->tty_dev->parent) device_move(dev->tty_dev, NULL, DPM_ORDER_DEV_LAST); @@ -758,11 +749,10 @@ static void rfcomm_tty_close(struct tty_struct *tty, struct file *filp) rfcomm_dlc_close(dev->dlc, 0); clear_bit(RFCOMM_TTY_ATTACHED, &dev->flags); - cancel_work_sync(&dev->wakeup_task); rfcomm_dlc_lock(dev->dlc); tty->driver_data = NULL; - dev->tty = NULL; + dev->port.tty = NULL; rfcomm_dlc_unlock(dev->dlc); if (test_bit(RFCOMM_TTY_RELEASED, &dev->flags)) { @@ -770,11 +760,12 @@ static void rfcomm_tty_close(struct tty_struct *tty, struct file *filp) list_del_init(&dev->list); spin_unlock(&rfcomm_dev_lock); - rfcomm_dev_put(dev); + tty_port_put(&dev->port); } - } + } else + spin_unlock_irqrestore(&dev->port.lock, flags); - rfcomm_dev_put(dev); + tty_port_put(&dev->port); } static int rfcomm_tty_write(struct tty_struct *tty, const unsigned char *buf, int count) @@ -1083,7 +1074,7 @@ static void rfcomm_tty_hangup(struct tty_struct *tty) if (rfcomm_dev_get(dev->id) == NULL) return; rfcomm_dev_del(dev); - rfcomm_dev_put(dev); + tty_port_put(&dev->port); } } diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index ba829de8442..929e48aed44 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -170,7 +170,7 @@ static int br_set_mac_address(struct net_device *dev, void *p) return -EADDRNOTAVAIL; spin_lock_bh(&br->lock); - if (compare_ether_addr(dev->dev_addr, addr->sa_data)) { + if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) { dev->addr_assign_type &= ~NET_ADDR_RANDOM; memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); br_fdb_change_mac_address(br, addr->sa_data); @@ -317,6 +317,9 @@ static const struct net_device_ops br_netdev_ops = { .ndo_add_slave = br_add_slave, .ndo_del_slave = br_del_slave, .ndo_fix_features = br_fix_features, + .ndo_fdb_add = br_fdb_add, + .ndo_fdb_del = br_fdb_delete, + .ndo_fdb_dump = br_fdb_dump, }; static void br_dev_free(struct net_device *dev) diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 5ba0c844d50..d21f3238351 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -107,8 +107,8 @@ void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr) struct net_bridge_port *op; list_for_each_entry(op, &br->port_list, list) { if (op != p && - !compare_ether_addr(op->dev->dev_addr, - f->addr.addr)) { + ether_addr_equal(op->dev->dev_addr, + f->addr.addr)) { f->dst = op; goto insert; } @@ -214,8 +214,8 @@ void br_fdb_delete_by_port(struct net_bridge *br, struct net_bridge_port *op; list_for_each_entry(op, &br->port_list, list) { if (op != p && - !compare_ether_addr(op->dev->dev_addr, - f->addr.addr)) { + ether_addr_equal(op->dev->dev_addr, + f->addr.addr)) { f->dst = op; goto skip_delete; } @@ -237,7 +237,7 @@ struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br, struct net_bridge_fdb_entry *fdb; hlist_for_each_entry_rcu(fdb, h, &br->hash[br_mac_hash(addr)], hlist) { - if (!compare_ether_addr(fdb->addr.addr, addr)) { + if (ether_addr_equal(fdb->addr.addr, addr)) { if (unlikely(has_expired(br, fdb))) break; return fdb; @@ -331,7 +331,7 @@ static struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head, struct net_bridge_fdb_entry *fdb; hlist_for_each_entry(fdb, h, head, hlist) { - if (!compare_ether_addr(fdb->addr.addr, addr)) + if (ether_addr_equal(fdb->addr.addr, addr)) return fdb; } return NULL; @@ -344,7 +344,7 @@ static struct net_bridge_fdb_entry *fdb_find_rcu(struct hlist_head *head, struct net_bridge_fdb_entry *fdb; hlist_for_each_entry_rcu(fdb, h, head, hlist) { - if (!compare_ether_addr(fdb->addr.addr, addr)) + if (ether_addr_equal(fdb->addr.addr, addr)) return fdb; } return NULL; @@ -487,14 +487,14 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, ndm->ndm_ifindex = fdb->dst ? fdb->dst->dev->ifindex : br->dev->ifindex; ndm->ndm_state = fdb_to_nud(fdb); - NLA_PUT(skb, NDA_LLADDR, ETH_ALEN, &fdb->addr); - + if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->addr)) + goto nla_put_failure; ci.ndm_used = jiffies_to_clock_t(now - fdb->used); ci.ndm_confirmed = 0; ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated); ci.ndm_refcnt = 0; - NLA_PUT(skb, NDA_CACHEINFO, sizeof(ci), &ci); - + if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) + goto nla_put_failure; return nlmsg_end(skb, nlh); nla_put_failure: @@ -535,44 +535,38 @@ errout: } /* Dump information about entries, in response to GETNEIGH */ -int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) +int br_fdb_dump(struct sk_buff *skb, + struct netlink_callback *cb, + struct net_device *dev, + int idx) { - struct net *net = sock_net(skb->sk); - struct net_device *dev; - int idx = 0; - - rcu_read_lock(); - for_each_netdev_rcu(net, dev) { - struct net_bridge *br = netdev_priv(dev); - int i; + struct net_bridge *br = netdev_priv(dev); + int i; - if (!(dev->priv_flags & IFF_EBRIDGE)) - continue; + if (!(dev->priv_flags & IFF_EBRIDGE)) + goto out; - for (i = 0; i < BR_HASH_SIZE; i++) { - struct hlist_node *h; - struct net_bridge_fdb_entry *f; - - hlist_for_each_entry_rcu(f, h, &br->hash[i], hlist) { - if (idx < cb->args[0]) - goto skip; + for (i = 0; i < BR_HASH_SIZE; i++) { + struct hlist_node *h; + struct net_bridge_fdb_entry *f; - if (fdb_fill_info(skb, br, f, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, - RTM_NEWNEIGH, - NLM_F_MULTI) < 0) - break; + hlist_for_each_entry_rcu(f, h, &br->hash[i], hlist) { + if (idx < cb->args[0]) + goto skip; + + if (fdb_fill_info(skb, br, f, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGH, + NLM_F_MULTI) < 0) + break; skip: - ++idx; - } + ++idx; } } - rcu_read_unlock(); - cb->args[0] = idx; - - return skb->len; +out: + return idx; } /* Update (create or replace) forwarding database entry */ @@ -614,43 +608,11 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, } /* Add new permanent fdb entry with RTM_NEWNEIGH */ -int br_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +int br_fdb_add(struct ndmsg *ndm, struct net_device *dev, + unsigned char *addr, u16 nlh_flags) { - struct net *net = sock_net(skb->sk); - struct ndmsg *ndm; - struct nlattr *tb[NDA_MAX+1]; - struct net_device *dev; struct net_bridge_port *p; - const __u8 *addr; - int err; - - ASSERT_RTNL(); - err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); - if (err < 0) - return err; - - ndm = nlmsg_data(nlh); - if (ndm->ndm_ifindex == 0) { - pr_info("bridge: RTM_NEWNEIGH with invalid ifindex\n"); - return -EINVAL; - } - - dev = __dev_get_by_index(net, ndm->ndm_ifindex); - if (dev == NULL) { - pr_info("bridge: RTM_NEWNEIGH with unknown ifindex\n"); - return -ENODEV; - } - - if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) { - pr_info("bridge: RTM_NEWNEIGH with invalid address\n"); - return -EINVAL; - } - - addr = nla_data(tb[NDA_LLADDR]); - if (!is_valid_ether_addr(addr)) { - pr_info("bridge: RTM_NEWNEIGH with invalid ether address\n"); - return -EINVAL; - } + int err = 0; if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) { pr_info("bridge: RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state); @@ -670,14 +632,14 @@ int br_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) rcu_read_unlock(); } else { spin_lock_bh(&p->br->hash_lock); - err = fdb_add_entry(p, addr, ndm->ndm_state, nlh->nlmsg_flags); + err = fdb_add_entry(p, addr, ndm->ndm_state, nlh_flags); spin_unlock_bh(&p->br->hash_lock); } return err; } -static int fdb_delete_by_addr(struct net_bridge_port *p, const u8 *addr) +static int fdb_delete_by_addr(struct net_bridge_port *p, u8 *addr) { struct net_bridge *br = p->br; struct hlist_head *head = &br->hash[br_mac_hash(addr)]; @@ -692,40 +654,12 @@ static int fdb_delete_by_addr(struct net_bridge_port *p, const u8 *addr) } /* Remove neighbor entry with RTM_DELNEIGH */ -int br_fdb_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +int br_fdb_delete(struct ndmsg *ndm, struct net_device *dev, + unsigned char *addr) { - struct net *net = sock_net(skb->sk); - struct ndmsg *ndm; struct net_bridge_port *p; - struct nlattr *llattr; - const __u8 *addr; - struct net_device *dev; int err; - ASSERT_RTNL(); - if (nlmsg_len(nlh) < sizeof(*ndm)) - return -EINVAL; - - ndm = nlmsg_data(nlh); - if (ndm->ndm_ifindex == 0) { - pr_info("bridge: RTM_DELNEIGH with invalid ifindex\n"); - return -EINVAL; - } - - dev = __dev_get_by_index(net, ndm->ndm_ifindex); - if (dev == NULL) { - pr_info("bridge: RTM_DELNEIGH with unknown ifindex\n"); - return -ENODEV; - } - - llattr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_LLADDR); - if (llattr == NULL || nla_len(llattr) != ETH_ALEN) { - pr_info("bridge: RTM_DELNEIGH with invalid address\n"); - return -EINVAL; - } - - addr = nla_data(llattr); - p = br_port_get_rtnl(dev); if (p == NULL) { pr_info("bridge: RTM_DELNEIGH %s not a bridge port\n", diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 61f65344e71..e9466d41270 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -34,7 +34,7 @@ static inline int should_deliver(const struct net_bridge_port *p, p->state == BR_STATE_FORWARDING); } -static inline unsigned packet_length(const struct sk_buff *skb) +static inline unsigned int packet_length(const struct sk_buff *skb) { return skb->len - (skb->protocol == htons(ETH_P_8021Q) ? VLAN_HLEN : 0); } @@ -47,6 +47,7 @@ int br_dev_queue_push_xmit(struct sk_buff *skb) kfree_skb(skb); } else { skb_push(skb, ETH_HLEN); + br_drop_fake_rtable(skb); dev_queue_xmit(skb); } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 5a31731be4d..76f15fda021 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -216,7 +216,7 @@ forward: } /* fall through */ case BR_STATE_LEARNING: - if (!compare_ether_addr(p->br->dev->dev_addr, dest)) + if (ether_addr_equal(p->br->dev->dev_addr, dest)) skb->pkt_type = PACKET_HOST; NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL, diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 702a1ae9220..b66581208cb 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -36,6 +36,8 @@ #define mlock_dereference(X, br) \ rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock)) +static void br_multicast_start_querier(struct net_bridge *br); + #if IS_ENABLED(CONFIG_IPV6) static inline int ipv6_is_transient_multicast(const struct in6_addr *addr) { @@ -241,7 +243,6 @@ static void br_multicast_group_expired(unsigned long data) hlist_del_rcu(&mp->hlist[mdb->ver]); mdb->size--; - del_timer(&mp->query_timer); call_rcu_bh(&mp->rcu, br_multicast_free_group); out: @@ -271,7 +272,6 @@ static void br_multicast_del_pg(struct net_bridge *br, rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); - del_timer(&p->query_timer); call_rcu_bh(&p->rcu, br_multicast_free_pg); if (!mp->ports && !mp->mglist && @@ -460,8 +460,8 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, hopopt[3] = 2; /* Length of RA Option */ hopopt[4] = 0; /* Type = 0x0000 (MLD) */ hopopt[5] = 0; - hopopt[6] = IPV6_TLV_PAD0; /* Pad0 */ - hopopt[7] = IPV6_TLV_PAD0; /* Pad0 */ + hopopt[6] = IPV6_TLV_PAD1; /* Pad1 */ + hopopt[7] = IPV6_TLV_PAD1; /* Pad1 */ skb_put(skb, sizeof(*ip6h) + 8); @@ -507,74 +507,6 @@ static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br, return NULL; } -static void br_multicast_send_group_query(struct net_bridge_mdb_entry *mp) -{ - struct net_bridge *br = mp->br; - struct sk_buff *skb; - - skb = br_multicast_alloc_query(br, &mp->addr); - if (!skb) - goto timer; - - netif_rx(skb); - -timer: - if (++mp->queries_sent < br->multicast_last_member_count) - mod_timer(&mp->query_timer, - jiffies + br->multicast_last_member_interval); -} - -static void br_multicast_group_query_expired(unsigned long data) -{ - struct net_bridge_mdb_entry *mp = (void *)data; - struct net_bridge *br = mp->br; - - spin_lock(&br->multicast_lock); - if (!netif_running(br->dev) || !mp->mglist || - mp->queries_sent >= br->multicast_last_member_count) - goto out; - - br_multicast_send_group_query(mp); - -out: - spin_unlock(&br->multicast_lock); -} - -static void br_multicast_send_port_group_query(struct net_bridge_port_group *pg) -{ - struct net_bridge_port *port = pg->port; - struct net_bridge *br = port->br; - struct sk_buff *skb; - - skb = br_multicast_alloc_query(br, &pg->addr); - if (!skb) - goto timer; - - br_deliver(port, skb); - -timer: - if (++pg->queries_sent < br->multicast_last_member_count) - mod_timer(&pg->query_timer, - jiffies + br->multicast_last_member_interval); -} - -static void br_multicast_port_group_query_expired(unsigned long data) -{ - struct net_bridge_port_group *pg = (void *)data; - struct net_bridge_port *port = pg->port; - struct net_bridge *br = port->br; - - spin_lock(&br->multicast_lock); - if (!netif_running(br->dev) || hlist_unhashed(&pg->mglist) || - pg->queries_sent >= br->multicast_last_member_count) - goto out; - - br_multicast_send_port_group_query(pg); - -out: - spin_unlock(&br->multicast_lock); -} - static struct net_bridge_mdb_entry *br_multicast_get_group( struct net_bridge *br, struct net_bridge_port *port, struct br_ip *group, int hash) @@ -582,8 +514,8 @@ static struct net_bridge_mdb_entry *br_multicast_get_group( struct net_bridge_mdb_htable *mdb; struct net_bridge_mdb_entry *mp; struct hlist_node *p; - unsigned count = 0; - unsigned max; + unsigned int count = 0; + unsigned int max; int elasticity; int err; @@ -690,8 +622,6 @@ rehash: mp->addr = *group; setup_timer(&mp->timer, br_multicast_group_expired, (unsigned long)mp); - setup_timer(&mp->query_timer, br_multicast_group_query_expired, - (unsigned long)mp); hlist_add_head_rcu(&mp->hlist[mdb->ver], &mdb->mhash[hash]); mdb->size++; @@ -746,8 +676,6 @@ static int br_multicast_add_group(struct net_bridge *br, hlist_add_head(&p->mglist, &port->mglist); setup_timer(&p->timer, br_multicast_port_group_expired, (unsigned long)p); - setup_timer(&p->query_timer, br_multicast_port_group_query_expired, - (unsigned long)p); rcu_assign_pointer(*pp, p); @@ -814,6 +742,20 @@ static void br_multicast_local_router_expired(unsigned long data) { } +static void br_multicast_querier_expired(unsigned long data) +{ + struct net_bridge *br = (void *)data; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || br->multicast_disabled) + goto out; + + br_multicast_start_querier(br); + +out: + spin_unlock(&br->multicast_lock); +} + static void __br_multicast_send_query(struct net_bridge *br, struct net_bridge_port *port, struct br_ip *ip) @@ -840,6 +782,7 @@ static void br_multicast_send_query(struct net_bridge *br, struct br_ip br_group; if (!netif_running(br->dev) || br->multicast_disabled || + !br->multicast_querier || timer_pending(&br->multicast_querier_timer)) return; @@ -1291,9 +1234,6 @@ static void br_multicast_leave_group(struct net_bridge *br, time_after(mp->timer.expires, time) : try_to_del_timer_sync(&mp->timer) >= 0)) { mod_timer(&mp->timer, time); - - mp->queries_sent = 0; - mod_timer(&mp->query_timer, now); } goto out; @@ -1310,9 +1250,6 @@ static void br_multicast_leave_group(struct net_bridge *br, time_after(p->timer.expires, time) : try_to_del_timer_sync(&p->timer) >= 0)) { mod_timer(&p->timer, time); - - p->queries_sent = 0; - mod_timer(&p->query_timer, now); } break; @@ -1361,8 +1298,8 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, struct sk_buff *skb2 = skb; const struct iphdr *iph; struct igmphdr *ih; - unsigned len; - unsigned offset; + unsigned int len; + unsigned int offset; int err; /* We treat OOM as packet loss for now. */ @@ -1462,7 +1399,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, u8 icmp6_type; u8 nexthdr; __be16 frag_off; - unsigned len; + unsigned int len; int offset; int err; @@ -1628,6 +1565,7 @@ void br_multicast_init(struct net_bridge *br) br->hash_max = 512; br->multicast_router = 1; + br->multicast_querier = 0; br->multicast_last_member_count = 2; br->multicast_startup_query_count = 2; @@ -1642,7 +1580,7 @@ void br_multicast_init(struct net_bridge *br) setup_timer(&br->multicast_router_timer, br_multicast_local_router_expired, 0); setup_timer(&br->multicast_querier_timer, - br_multicast_local_router_expired, 0); + br_multicast_querier_expired, (unsigned long)br); setup_timer(&br->multicast_query_timer, br_multicast_query_expired, (unsigned long)br); } @@ -1681,7 +1619,6 @@ void br_multicast_stop(struct net_bridge *br) hlist_for_each_entry_safe(mp, p, n, &mdb->mhash[i], hlist[ver]) { del_timer(&mp->timer); - del_timer(&mp->query_timer); call_rcu_bh(&mp->rcu, br_multicast_free_group); } } @@ -1770,9 +1707,23 @@ unlock: return err; } -int br_multicast_toggle(struct net_bridge *br, unsigned long val) +static void br_multicast_start_querier(struct net_bridge *br) { struct net_bridge_port *port; + + br_multicast_open(br); + + list_for_each_entry(port, &br->port_list, list) { + if (port->state == BR_STATE_DISABLED || + port->state == BR_STATE_BLOCKING) + continue; + + __br_multicast_enable_port(port); + } +} + +int br_multicast_toggle(struct net_bridge *br, unsigned long val) +{ int err = 0; struct net_bridge_mdb_htable *mdb; @@ -1802,14 +1753,7 @@ rollback: goto rollback; } - br_multicast_open(br); - list_for_each_entry(port, &br->port_list, list) { - if (port->state == BR_STATE_DISABLED || - port->state == BR_STATE_BLOCKING) - continue; - - __br_multicast_enable_port(port); - } + br_multicast_start_querier(br); unlock: spin_unlock_bh(&br->multicast_lock); @@ -1817,6 +1761,24 @@ unlock: return err; } +int br_multicast_set_querier(struct net_bridge *br, unsigned long val) +{ + val = !!val; + + spin_lock_bh(&br->multicast_lock); + if (br->multicast_querier == val) + goto unlock; + + br->multicast_querier = val; + if (val) + br_multicast_start_querier(br); + +unlock: + spin_unlock_bh(&br->multicast_lock); + + return 0; +} + int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val) { int err = -ENOENT; diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index dec4f381713..e41456bd3cc 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -54,12 +54,14 @@ static int brnf_call_ip6tables __read_mostly = 1; static int brnf_call_arptables __read_mostly = 1; static int brnf_filter_vlan_tagged __read_mostly = 0; static int brnf_filter_pppoe_tagged __read_mostly = 0; +static int brnf_pass_vlan_indev __read_mostly = 0; #else #define brnf_call_iptables 1 #define brnf_call_ip6tables 1 #define brnf_call_arptables 1 #define brnf_filter_vlan_tagged 0 #define brnf_filter_pppoe_tagged 0 +#define brnf_pass_vlan_indev 0 #endif #define IS_IP(skb) \ @@ -156,7 +158,7 @@ void br_netfilter_rtable_init(struct net_bridge *br) rt->dst.dev = br->dev; rt->dst.path = &rt->dst; dst_init_metrics(&rt->dst, br_dst_default_metrics, true); - rt->dst.flags = DST_NOXFRM | DST_NOPEER; + rt->dst.flags = DST_NOXFRM | DST_NOPEER | DST_FAKE_RTABLE; rt->dst.ops = &fake_dst_ops; } @@ -503,6 +505,19 @@ bridged_dnat: return 0; } +static struct net_device *brnf_get_logical_dev(struct sk_buff *skb, const struct net_device *dev) +{ + struct net_device *vlan, *br; + + br = bridge_parent(dev); + if (brnf_pass_vlan_indev == 0 || !vlan_tx_tag_present(skb)) + return br; + + vlan = __vlan_find_dev_deep(br, vlan_tx_tag_get(skb) & VLAN_VID_MASK); + + return vlan ? vlan : br; +} + /* Some common code for IPv4/IPv6 */ static struct net_device *setup_pre_routing(struct sk_buff *skb) { @@ -515,7 +530,7 @@ static struct net_device *setup_pre_routing(struct sk_buff *skb) nf_bridge->mask |= BRNF_NF_BRIDGE_PREROUTING; nf_bridge->physindev = skb->dev; - skb->dev = bridge_parent(skb->dev); + skb->dev = brnf_get_logical_dev(skb, skb->dev); if (skb->protocol == htons(ETH_P_8021Q)) nf_bridge->mask |= BRNF_8021Q; else if (skb->protocol == htons(ETH_P_PPP_SES)) @@ -543,7 +558,7 @@ static int check_hbh_len(struct sk_buff *skb) int optlen = nh[off + 1] + 2; switch (nh[off]) { - case IPV6_TLV_PAD0: + case IPV6_TLV_PAD1: optlen = 1; break; @@ -694,11 +709,7 @@ static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff *skb, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - struct rtable *rt = skb_rtable(skb); - - if (rt && rt == bridge_parent_rtable(in)) - skb_dst_drop(skb); - + br_drop_fake_rtable(skb); return NF_ACCEPT; } @@ -778,7 +789,7 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb, else skb->protocol = htons(ETH_P_IPV6); - NF_HOOK(pf, NF_INET_FORWARD, skb, bridge_parent(in), parent, + NF_HOOK(pf, NF_INET_FORWARD, skb, brnf_get_logical_dev(skb, in), parent, br_nf_forward_finish); return NF_STOLEN; @@ -1006,12 +1017,13 @@ static ctl_table brnf_table[] = { .mode = 0644, .proc_handler = brnf_sysctl_call_tables, }, - { } -}; - -static struct ctl_path brnf_path[] = { - { .procname = "net", }, - { .procname = "bridge", }, + { + .procname = "bridge-nf-pass-vlan-input-dev", + .data = &brnf_pass_vlan_indev, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = brnf_sysctl_call_tables, + }, { } }; #endif @@ -1030,7 +1042,7 @@ int __init br_netfilter_init(void) return ret; } #ifdef CONFIG_SYSCTL - brnf_sysctl_header = register_sysctl_paths(brnf_path, brnf_table); + brnf_sysctl_header = register_net_sysctl(&init_net, "net/bridge", brnf_table); if (brnf_sysctl_header == NULL) { printk(KERN_WARNING "br_netfilter: can't register to sysctl.\n"); @@ -1047,7 +1059,7 @@ void br_netfilter_fini(void) { nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); #ifdef CONFIG_SYSCTL - unregister_sysctl_table(brnf_sysctl_header); + unregister_net_sysctl_table(brnf_sysctl_header); #endif dst_entries_destroy(&fake_dst_ops); } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index a1daf8227ed..2080485515f 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -60,20 +60,17 @@ static int br_fill_ifinfo(struct sk_buff *skb, const struct net_bridge_port *por hdr->ifi_flags = dev_get_flags(dev); hdr->ifi_change = 0; - NLA_PUT_STRING(skb, IFLA_IFNAME, dev->name); - NLA_PUT_U32(skb, IFLA_MASTER, br->dev->ifindex); - NLA_PUT_U32(skb, IFLA_MTU, dev->mtu); - NLA_PUT_U8(skb, IFLA_OPERSTATE, operstate); - - if (dev->addr_len) - NLA_PUT(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr); - - if (dev->ifindex != dev->iflink) - NLA_PUT_U32(skb, IFLA_LINK, dev->iflink); - - if (event == RTM_NEWLINK) - NLA_PUT_U8(skb, IFLA_PROTINFO, port->state); - + if (nla_put_string(skb, IFLA_IFNAME, dev->name) || + nla_put_u32(skb, IFLA_MASTER, br->dev->ifindex) || + nla_put_u32(skb, IFLA_MTU, dev->mtu) || + nla_put_u8(skb, IFLA_OPERSTATE, operstate) || + (dev->addr_len && + nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || + (dev->ifindex != dev->iflink && + nla_put_u32(skb, IFLA_LINK, dev->iflink)) || + (event == RTM_NEWLINK && + nla_put_u8(skb, IFLA_PROTINFO, port->state))) + goto nla_put_failure; return nlmsg_end(skb, nlh); nla_put_failure: @@ -91,7 +88,7 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port) int err = -ENOBUFS; br_debug(port->br, "port %u(%s) event %d\n", - (unsigned)port->port_no, port->dev->name, event); + (unsigned int)port->port_no, port->dev->name, event); skb = nlmsg_new(br_nlmsg_size(), GFP_ATOMIC); if (skb == NULL) @@ -235,18 +232,6 @@ int __init br_netlink_init(void) br_rtm_setlink, NULL, NULL); if (err) goto err3; - err = __rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, - br_fdb_add, NULL, NULL); - if (err) - goto err3; - err = __rtnl_register(PF_BRIDGE, RTM_DELNEIGH, - br_fdb_delete, NULL, NULL); - if (err) - goto err3; - err = __rtnl_register(PF_BRIDGE, RTM_GETNEIGH, - NULL, br_fdb_dump, NULL); - if (err) - goto err3; return 0; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 0b67a63ad7a..1a8ad4fb9a6 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -82,9 +82,7 @@ struct net_bridge_port_group { struct hlist_node mglist; struct rcu_head rcu; struct timer_list timer; - struct timer_list query_timer; struct br_ip addr; - u32 queries_sent; }; struct net_bridge_mdb_entry @@ -94,10 +92,8 @@ struct net_bridge_mdb_entry struct net_bridge_port_group __rcu *ports; struct rcu_head rcu; struct timer_list timer; - struct timer_list query_timer; struct br_ip addr; bool mglist; - u32 queries_sent; }; struct net_bridge_mdb_htable @@ -228,6 +224,7 @@ struct net_bridge unsigned char multicast_router; u8 multicast_disabled:1; + u8 multicast_querier:1; u32 hash_elasticity; u32 hash_max; @@ -363,9 +360,18 @@ extern int br_fdb_insert(struct net_bridge *br, extern void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr); -extern int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb); -extern int br_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg); -extern int br_fdb_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg); + +extern int br_fdb_delete(struct ndmsg *ndm, + struct net_device *dev, + unsigned char *addr); +extern int br_fdb_add(struct ndmsg *nlh, + struct net_device *dev, + unsigned char *addr, + u16 nlh_flags); +extern int br_fdb_dump(struct sk_buff *skb, + struct netlink_callback *cb, + struct net_device *dev, + int idx); /* br_forward.c */ extern void br_deliver(const struct net_bridge_port *to, @@ -421,6 +427,7 @@ extern int br_multicast_set_router(struct net_bridge *br, unsigned long val); extern int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val); extern int br_multicast_toggle(struct net_bridge *br, unsigned long val); +extern int br_multicast_set_querier(struct net_bridge *br, unsigned long val); extern int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val); static inline bool br_multicast_is_router(struct net_bridge *br) diff --git a/net/bridge/br_private_stp.h b/net/bridge/br_private_stp.h index 05ed9bc7e42..0c0fe36e7aa 100644 --- a/net/bridge/br_private_stp.h +++ b/net/bridge/br_private_stp.h @@ -29,10 +29,9 @@ #define BR_MIN_PATH_COST 1 #define BR_MAX_PATH_COST 65535 -struct br_config_bpdu -{ - unsigned topology_change:1; - unsigned topology_change_ack:1; +struct br_config_bpdu { + unsigned int topology_change:1; + unsigned int topology_change_ack:1; bridge_id root; int root_path_cost; bridge_id bridge_id; diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 8c836d96ba7..af9a12099ba 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -32,7 +32,7 @@ static const char *const br_port_state_names[] = { void br_log_state(const struct net_bridge_port *p) { br_info(p->br, "port %u(%s) entered %s state\n", - (unsigned) p->port_no, p->dev->name, + (unsigned int) p->port_no, p->dev->name, br_port_state_names[p->state]); } @@ -478,7 +478,7 @@ void br_received_tcn_bpdu(struct net_bridge_port *p) { if (br_is_designated_port(p)) { br_info(p->br, "port %u(%s) received tcn bpdu\n", - (unsigned) p->port_no, p->dev->name); + (unsigned int) p->port_no, p->dev->name); br_topology_change_detection(p->br); br_topology_change_acknowledge(p); diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index e16aade51ae..fd30a6022de 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -167,7 +167,7 @@ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, if (p->state == BR_STATE_DISABLED) goto out; - if (compare_ether_addr(dest, br->group_addr) != 0) + if (!ether_addr_equal(dest, br->group_addr)) goto out; buf = skb_pull(skb, 3); diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index f494496373d..9d5a414a394 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -178,7 +178,7 @@ void br_stp_set_enabled(struct net_bridge *br, unsigned long val) /* called under bridge lock */ void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *addr) { - /* should be aligned on 2 bytes for compare_ether_addr() */ + /* should be aligned on 2 bytes for ether_addr_equal() */ unsigned short oldaddr_aligned[ETH_ALEN >> 1]; unsigned char *oldaddr = (unsigned char *)oldaddr_aligned; struct net_bridge_port *p; @@ -191,12 +191,11 @@ void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *addr) memcpy(br->dev->dev_addr, addr, ETH_ALEN); list_for_each_entry(p, &br->port_list, list) { - if (!compare_ether_addr(p->designated_bridge.addr, oldaddr)) + if (ether_addr_equal(p->designated_bridge.addr, oldaddr)) memcpy(p->designated_bridge.addr, addr, ETH_ALEN); - if (!compare_ether_addr(p->designated_root.addr, oldaddr)) + if (ether_addr_equal(p->designated_root.addr, oldaddr)) memcpy(p->designated_root.addr, addr, ETH_ALEN); - } br_configuration_update(br); @@ -205,7 +204,7 @@ void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *addr) br_become_root_bridge(br); } -/* should be aligned on 2 bytes for compare_ether_addr() */ +/* should be aligned on 2 bytes for ether_addr_equal() */ static const unsigned short br_mac_zero_aligned[ETH_ALEN >> 1]; /* called under bridge lock */ @@ -227,7 +226,7 @@ bool br_stp_recalculate_bridge_id(struct net_bridge *br) } - if (compare_ether_addr(br->bridge_id.addr, addr) == 0) + if (ether_addr_equal(br->bridge_id.addr, addr)) return false; /* no change */ br_stp_change_bridge_id(br, addr); diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c index 58de2a0f997..a6747e67342 100644 --- a/net/bridge/br_stp_timer.c +++ b/net/bridge/br_stp_timer.c @@ -56,7 +56,7 @@ static void br_message_age_timer_expired(unsigned long arg) return; br_info(br, "port %u(%s) neighbor %.2x%.2x.%pM lost\n", - (unsigned) p->port_no, p->dev->name, + (unsigned int) p->port_no, p->dev->name, id->prio[0], id->prio[1], &id->addr); /* @@ -84,7 +84,7 @@ static void br_forward_delay_timer_expired(unsigned long arg) struct net_bridge *br = p->br; br_debug(br, "port %u(%s) forward delay timer\n", - (unsigned) p->port_no, p->dev->name); + (unsigned int) p->port_no, p->dev->name); spin_lock(&br->lock); if (p->state == BR_STATE_LISTENING) { p->state = BR_STATE_LEARNING; @@ -131,7 +131,7 @@ static void br_hold_timer_expired(unsigned long arg) struct net_bridge_port *p = (struct net_bridge_port *) arg; br_debug(p->br, "port %u(%s) hold timer expired\n", - (unsigned) p->port_no, p->dev->name); + (unsigned int) p->port_no, p->dev->name); spin_lock(&p->br->lock); if (p->config_pending) diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index c236c0e4398..c5c059333ea 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -297,7 +297,7 @@ static ssize_t store_group_addr(struct device *d, const char *buf, size_t len) { struct net_bridge *br = to_bridge(d); - unsigned new_addr[6]; + unsigned int new_addr[6]; int i; if (!capable(CAP_NET_ADMIN)) @@ -379,6 +379,23 @@ static ssize_t store_multicast_snooping(struct device *d, static DEVICE_ATTR(multicast_snooping, S_IRUGO | S_IWUSR, show_multicast_snooping, store_multicast_snooping); +static ssize_t show_multicast_querier(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%d\n", br->multicast_querier); +} + +static ssize_t store_multicast_querier(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, br_multicast_set_querier); +} +static DEVICE_ATTR(multicast_querier, S_IRUGO | S_IWUSR, + show_multicast_querier, store_multicast_querier); + static ssize_t show_hash_elasticity(struct device *d, struct device_attribute *attr, char *buf) { @@ -702,6 +719,7 @@ static struct attribute *bridge_attrs[] = { #ifdef CONFIG_BRIDGE_IGMP_SNOOPING &dev_attr_multicast_router.attr, &dev_attr_multicast_snooping.attr, + &dev_attr_multicast_querier.attr, &dev_attr_hash_elasticity.attr, &dev_attr_hash_max.attr, &dev_attr_multicast_last_member_count.attr, diff --git a/net/bridge/netfilter/ebt_stp.c b/net/bridge/netfilter/ebt_stp.c index 5b33a2e634a..071d87214dd 100644 --- a/net/bridge/netfilter/ebt_stp.c +++ b/net/bridge/netfilter/ebt_stp.c @@ -164,8 +164,8 @@ static int ebt_stp_mt_check(const struct xt_mtchk_param *par) !(info->bitmask & EBT_STP_MASK)) return -EINVAL; /* Make sure the match only receives stp frames */ - if (compare_ether_addr(e->destmac, bridge_ula) || - compare_ether_addr(e->destmsk, msk) || !(e->bitmask & EBT_DESTMAC)) + if (!ether_addr_equal(e->destmac, bridge_ula) || + !ether_addr_equal(e->destmsk, msk) || !(e->bitmask & EBT_DESTMAC)) return -EINVAL; return 0; diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 5016fa57b62..fb894435526 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -19,7 +19,7 @@ #include <linux/uaccess.h> #include <linux/debugfs.h> #include <linux/caif/caif_socket.h> -#include <linux/atomic.h> +#include <linux/pkt_sched.h> #include <net/sock.h> #include <net/tcp_states.h> #include <net/caif/caif_layer.h> @@ -130,11 +130,10 @@ static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) struct caifsock *cf_sk = container_of(sk, struct caifsock, sk); if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned)sk->sk_rcvbuf && rx_flow_is_on(cf_sk)) { - if (net_ratelimit()) - pr_debug("sending flow OFF (queue len = %d %d)\n", - atomic_read(&cf_sk->sk.sk_rmem_alloc), - sk_rcvbuf_lowwater(cf_sk)); + (unsigned int)sk->sk_rcvbuf && rx_flow_is_on(cf_sk)) { + net_dbg_ratelimited("sending flow OFF (queue len = %d %d)\n", + atomic_read(&cf_sk->sk.sk_rmem_alloc), + sk_rcvbuf_lowwater(cf_sk)); set_rx_flow_off(cf_sk); caif_flow_ctrl(sk, CAIF_MODEMCMD_FLOW_OFF_REQ); } @@ -144,8 +143,7 @@ static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) return err; if (!sk_rmem_schedule(sk, skb->truesize) && rx_flow_is_on(cf_sk)) { set_rx_flow_off(cf_sk); - if (net_ratelimit()) - pr_debug("sending flow OFF due to rmem_schedule\n"); + net_dbg_ratelimited("sending flow OFF due to rmem_schedule\n"); caif_flow_ctrl(sk, CAIF_MODEMCMD_FLOW_OFF_REQ); } skb->dev = NULL; @@ -505,6 +503,7 @@ static int transmit_skb(struct sk_buff *skb, struct caifsock *cf_sk, pkt = cfpkt_fromnative(CAIF_DIR_OUT, skb); memset(skb->cb, 0, sizeof(struct caif_payload_info)); + cfpkt_set_prio(pkt, cf_sk->sk.sk_priority); if (cf_sk->layer.dn == NULL) { kfree_skb(skb); @@ -1062,6 +1061,18 @@ static int caif_create(struct net *net, struct socket *sock, int protocol, /* Store the protocol */ sk->sk_protocol = (unsigned char) protocol; + /* Initialize default priority for well-known cases */ + switch (protocol) { + case CAIFPROTO_AT: + sk->sk_priority = TC_PRIO_CONTROL; + break; + case CAIFPROTO_RFM: + sk->sk_priority = TC_PRIO_INTERACTIVE_BULK; + break; + default: + sk->sk_priority = TC_PRIO_BESTEFFORT; + } + /* * Lock in order to try to stop someone from opening the socket * too early. @@ -1081,7 +1092,6 @@ static int caif_create(struct net *net, struct socket *sock, int protocol, set_rx_flow_on(cf_sk); /* Set default options on configuration */ - cf_sk->sk.sk_priority = CAIF_PRIO_NORMAL; cf_sk->conn_req.link_selector = CAIF_LINK_LOW_LATENCY; cf_sk->conn_req.protocol = protocol; release_sock(&cf_sk->sk); diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c index 5cf52225692..047cd0eec02 100644 --- a/net/caif/cfctrl.c +++ b/net/caif/cfctrl.c @@ -9,6 +9,7 @@ #include <linux/stddef.h> #include <linux/spinlock.h> #include <linux/slab.h> +#include <linux/pkt_sched.h> #include <net/caif/caif_layer.h> #include <net/caif/cfpkt.h> #include <net/caif/cfctrl.h> @@ -189,6 +190,7 @@ void cfctrl_enum_req(struct cflayer *layer, u8 physlinkid) cfctrl->serv.dev_info.id = physlinkid; cfpkt_addbdy(pkt, CFCTRL_CMD_ENUM); cfpkt_addbdy(pkt, physlinkid); + cfpkt_set_prio(pkt, TC_PRIO_CONTROL); dn->transmit(dn, pkt); } @@ -281,6 +283,7 @@ int cfctrl_linkup_request(struct cflayer *layer, * might arrive with the newly allocated channel ID. */ cfpkt_info(pkt)->dev_info->id = param->phyid; + cfpkt_set_prio(pkt, TC_PRIO_CONTROL); ret = dn->transmit(dn, pkt); if (ret < 0) { @@ -314,6 +317,7 @@ int cfctrl_linkdown_req(struct cflayer *layer, u8 channelid, cfpkt_addbdy(pkt, CFCTRL_CMD_LINK_DESTROY); cfpkt_addbdy(pkt, channelid); init_info(cfpkt_info(pkt), cfctrl); + cfpkt_set_prio(pkt, TC_PRIO_CONTROL); ret = dn->transmit(dn, pkt); #ifndef CAIF_NO_LOOP diff --git a/net/caif/cfpkt_skbuff.c b/net/caif/cfpkt_skbuff.c index e335ba859b9..863dedd91bb 100644 --- a/net/caif/cfpkt_skbuff.c +++ b/net/caif/cfpkt_skbuff.c @@ -381,6 +381,7 @@ struct cfpkt *cfpkt_split(struct cfpkt *pkt, u16 pos) memcpy(skb2->data, split, len2nd); skb2->tail += len2nd; skb2->len += len2nd; + skb2->priority = skb->priority; return skb_to_pkt(skb2); } @@ -394,3 +395,9 @@ struct caif_payload_info *cfpkt_info(struct cfpkt *pkt) return (struct caif_payload_info *)&pkt_to_skb(pkt)->cb; } EXPORT_SYMBOL(cfpkt_info); + +void cfpkt_set_prio(struct cfpkt *pkt, int prio) +{ + pkt_to_skb(pkt)->priority = prio; +} +EXPORT_SYMBOL(cfpkt_set_prio); diff --git a/net/caif/cfsrvl.c b/net/caif/cfsrvl.c index 4aa33d4496b..dd485f6128e 100644 --- a/net/caif/cfsrvl.c +++ b/net/caif/cfsrvl.c @@ -11,6 +11,7 @@ #include <linux/errno.h> #include <linux/slab.h> #include <linux/module.h> +#include <linux/pkt_sched.h> #include <net/caif/caif_layer.h> #include <net/caif/cfsrvl.h> #include <net/caif/cfpkt.h> @@ -120,6 +121,7 @@ static int cfservl_modemcmd(struct cflayer *layr, enum caif_modemcmd ctrl) info->channel_id = service->layer.id; info->hdr_len = 1; info->dev_info = &service->dev_info; + cfpkt_set_prio(pkt, TC_PRIO_CONTROL); return layr->dn->transmit(layr->dn, pkt); } case CAIF_MODEMCMD_FLOW_OFF_REQ: @@ -140,6 +142,7 @@ static int cfservl_modemcmd(struct cflayer *layr, enum caif_modemcmd ctrl) info->channel_id = service->layer.id; info->hdr_len = 1; info->dev_info = &service->dev_info; + cfpkt_set_prio(pkt, TC_PRIO_CONTROL); return layr->dn->transmit(layr->dn, pkt); } default: diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 20618dd3088..69771c04ba8 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -103,6 +103,7 @@ static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt) skb->protocol = htons(ETH_P_IPV6); break; default: + kfree_skb(skb); priv->netdev->stats.rx_errors++; return -EINVAL; } @@ -220,14 +221,16 @@ static int chnl_net_start_xmit(struct sk_buff *skb, struct net_device *dev) if (skb->len > priv->netdev->mtu) { pr_warn("Size of skb exceeded MTU\n"); + kfree_skb(skb); dev->stats.tx_errors++; - return -ENOSPC; + return NETDEV_TX_OK; } if (!priv->flowenabled) { pr_debug("dropping packets flow off\n"); + kfree_skb(skb); dev->stats.tx_dropped++; - return NETDEV_TX_BUSY; + return NETDEV_TX_OK; } if (priv->conn_req.protocol == CAIFPROTO_DATAGRAM_LOOP) @@ -242,7 +245,7 @@ static int chnl_net_start_xmit(struct sk_buff *skb, struct net_device *dev) result = priv->chnl.dn->transmit(priv->chnl.dn, pkt); if (result) { dev->stats.tx_dropped++; - return result; + return NETDEV_TX_OK; } /* Update statistics. */ @@ -421,14 +424,14 @@ static int ipcaif_fill_info(struct sk_buff *skb, const struct net_device *dev) struct chnl_net *priv; u8 loop; priv = netdev_priv(dev); - NLA_PUT_U32(skb, IFLA_CAIF_IPV4_CONNID, - priv->conn_req.sockaddr.u.dgm.connection_id); - NLA_PUT_U32(skb, IFLA_CAIF_IPV6_CONNID, - priv->conn_req.sockaddr.u.dgm.connection_id); + if (nla_put_u32(skb, IFLA_CAIF_IPV4_CONNID, + priv->conn_req.sockaddr.u.dgm.connection_id) || + nla_put_u32(skb, IFLA_CAIF_IPV6_CONNID, + priv->conn_req.sockaddr.u.dgm.connection_id)) + goto nla_put_failure; loop = priv->conn_req.protocol == CAIFPROTO_DATAGRAM_LOOP; - NLA_PUT_U8(skb, IFLA_CAIF_LOOPBACK, loop); - - + if (nla_put_u8(skb, IFLA_CAIF_LOOPBACK, loop)) + goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; diff --git a/net/can/gw.c b/net/can/gw.c index 3d79b127881..b41acf25668 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -66,7 +66,7 @@ MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>"); MODULE_ALIAS("can-gw"); -HLIST_HEAD(cgw_list); +static HLIST_HEAD(cgw_list); static struct notifier_block notifier; static struct kmem_cache *cgw_cache __read_mostly; diff --git a/net/ceph/auth_x.h b/net/ceph/auth_x.h index e02da7a5c5a..f459e93b774 100644 --- a/net/ceph/auth_x.h +++ b/net/ceph/auth_x.h @@ -13,7 +13,7 @@ */ struct ceph_x_ticket_handler { struct rb_node node; - unsigned service; + unsigned int service; struct ceph_crypto_key session_key; struct ceph_timespec validity; @@ -27,7 +27,7 @@ struct ceph_x_ticket_handler { struct ceph_x_authorizer { struct ceph_buffer *buf; - unsigned service; + unsigned int service; u64 nonce; char reply_buf[128]; /* big enough for encrypted blob */ }; @@ -38,7 +38,7 @@ struct ceph_x_info { bool starting; u64 server_challenge; - unsigned have_keys; + unsigned int have_keys; struct rb_root ticket_handlers; struct ceph_x_authorizer auth_authorizer; diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index cc913193d99..a776f751edb 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -441,8 +441,8 @@ EXPORT_SYMBOL(ceph_client_id); * create a fresh client instance */ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private, - unsigned supported_features, - unsigned required_features) + unsigned int supported_features, + unsigned int required_features) { struct ceph_client *client; struct ceph_entity_addr *myaddr = NULL; diff --git a/net/ceph/ceph_hash.c b/net/ceph/ceph_hash.c index 0a1b53bce76..67bb1f11e61 100644 --- a/net/ceph/ceph_hash.c +++ b/net/ceph/ceph_hash.c @@ -20,7 +20,7 @@ c = c - a; c = c - b; c = c ^ (b >> 15); \ } while (0) -unsigned ceph_str_hash_rjenkins(const char *str, unsigned length) +unsigned int ceph_str_hash_rjenkins(const char *str, unsigned int length) { const unsigned char *k = (const unsigned char *)str; __u32 a, b, c; /* the internal state */ @@ -81,7 +81,7 @@ unsigned ceph_str_hash_rjenkins(const char *str, unsigned length) /* * linux dcache hash */ -unsigned ceph_str_hash_linux(const char *str, unsigned length) +unsigned int ceph_str_hash_linux(const char *str, unsigned int length) { unsigned long hash = 0; unsigned char c; @@ -94,7 +94,7 @@ unsigned ceph_str_hash_linux(const char *str, unsigned length) } -unsigned ceph_str_hash(int type, const char *s, unsigned len) +unsigned int ceph_str_hash(int type, const char *s, unsigned int len) { switch (type) { case CEPH_STR_HASH_LINUX: diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index b79747c4b64..363f8f7e6c3 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -20,6 +20,7 @@ #include <linux/crush/crush.h> #include <linux/crush/hash.h> +#include <linux/crush/mapper.h> /* * Implement the core CRUSH mapping algorithm. @@ -68,8 +69,8 @@ int crush_find_rule(struct crush_map *map, int ruleset, int type, int size) static int bucket_perm_choose(struct crush_bucket *bucket, int x, int r) { - unsigned pr = r % bucket->size; - unsigned i, s; + unsigned int pr = r % bucket->size; + unsigned int i, s; /* start a new permutation if @x has changed */ if (bucket->perm_x != x || bucket->perm_n == 0) { @@ -100,13 +101,13 @@ static int bucket_perm_choose(struct crush_bucket *bucket, for (i = 0; i < bucket->perm_n; i++) dprintk(" perm_choose have %d: %d\n", i, bucket->perm[i]); while (bucket->perm_n <= pr) { - unsigned p = bucket->perm_n; + unsigned int p = bucket->perm_n; /* no point in swapping the final entry */ if (p < bucket->size - 1) { i = crush_hash32_3(bucket->hash, x, bucket->id, p) % (bucket->size - p); if (i) { - unsigned t = bucket->perm[p + i]; + unsigned int t = bucket->perm[p + i]; bucket->perm[p + i] = bucket->perm[p]; bucket->perm[p] = t; } diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c index 27d4ea315d1..54b531a0112 100644 --- a/net/ceph/debugfs.c +++ b/net/ceph/debugfs.c @@ -94,9 +94,9 @@ static int monc_show(struct seq_file *s, void *p) mutex_lock(&monc->mutex); if (monc->have_mdsmap) - seq_printf(s, "have mdsmap %u\n", (unsigned)monc->have_mdsmap); + seq_printf(s, "have mdsmap %u\n", (unsigned int)monc->have_mdsmap); if (monc->have_osdmap) - seq_printf(s, "have osdmap %u\n", (unsigned)monc->have_osdmap); + seq_printf(s, "have osdmap %u\n", (unsigned int)monc->have_osdmap); if (monc->want_next_osdmap) seq_printf(s, "want next osdmap\n"); @@ -146,7 +146,7 @@ static int osdc_show(struct seq_file *s, void *pp) if (req->r_reassert_version.epoch) seq_printf(s, "\t%u'%llu", - (unsigned)le32_to_cpu(req->r_reassert_version.epoch), + (unsigned int)le32_to_cpu(req->r_reassert_version.epoch), le64_to_cpu(req->r_reassert_version.version)); else seq_printf(s, "\t"); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index f0993af2ae4..36fa6bf6849 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -699,7 +699,7 @@ static int prepare_write_connect(struct ceph_messenger *msgr, struct ceph_connection *con, int include_banner) { - unsigned global_seq = get_global_seq(con->msgr, 0); + unsigned int global_seq = get_global_seq(con->msgr, 0); int proto; switch (con->peer_name.type) { @@ -816,7 +816,7 @@ static void iter_bio_next(struct bio **bio_iter, int *seg) static int write_partial_msg_pages(struct ceph_connection *con) { struct ceph_msg *msg = con->out_msg; - unsigned data_len = le32_to_cpu(msg->hdr.data_len); + unsigned int data_len = le32_to_cpu(msg->hdr.data_len); size_t len; bool do_datacrc = !con->msgr->nocrc; int ret; @@ -1554,7 +1554,7 @@ static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con, static int read_partial_message_pages(struct ceph_connection *con, struct page **pages, - unsigned data_len, bool do_datacrc) + unsigned int data_len, bool do_datacrc) { void *p; int ret; @@ -1587,7 +1587,7 @@ static int read_partial_message_pages(struct ceph_connection *con, #ifdef CONFIG_BLOCK static int read_partial_message_bio(struct ceph_connection *con, struct bio **bio_iter, int *bio_seg, - unsigned data_len, bool do_datacrc) + unsigned int data_len, bool do_datacrc) { struct bio_vec *bv = bio_iovec_idx(*bio_iter, *bio_seg); void *p; @@ -1629,7 +1629,7 @@ static int read_partial_message(struct ceph_connection *con) struct ceph_msg *m = con->in_msg; int ret; int to, left; - unsigned front_len, middle_len, data_len; + unsigned int front_len, middle_len, data_len; bool do_datacrc = !con->msgr->nocrc; int skip; u64 seq; @@ -2345,9 +2345,9 @@ void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg) { mutex_lock(&con->mutex); if (con->in_msg && con->in_msg == msg) { - unsigned front_len = le32_to_cpu(con->in_hdr.front_len); - unsigned middle_len = le32_to_cpu(con->in_hdr.middle_len); - unsigned data_len = le32_to_cpu(con->in_hdr.data_len); + unsigned int front_len = le32_to_cpu(con->in_hdr.front_len); + unsigned int middle_len = le32_to_cpu(con->in_hdr.middle_len); + unsigned int data_len = le32_to_cpu(con->in_hdr.data_len); /* skip rest of message */ dout("con_revoke_pages %p msg %p revoked\n", con, msg); diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 1845cde2622..10d6008d31f 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -168,7 +168,7 @@ static bool __sub_expired(struct ceph_mon_client *monc) */ static void __schedule_delayed(struct ceph_mon_client *monc) { - unsigned delay; + unsigned int delay; if (monc->cur_mon < 0 || __sub_expired(monc)) delay = 10 * HZ; @@ -184,7 +184,7 @@ static void __schedule_delayed(struct ceph_mon_client *monc) static void __send_subscribe(struct ceph_mon_client *monc) { dout("__send_subscribe sub_sent=%u exp=%u want_osd=%d\n", - (unsigned)monc->sub_sent, __sub_expired(monc), + (unsigned int)monc->sub_sent, __sub_expired(monc), monc->want_next_osdmap); if ((__sub_expired(monc) && !monc->sub_sent) || monc->want_next_osdmap == 1) { @@ -201,7 +201,7 @@ static void __send_subscribe(struct ceph_mon_client *monc) if (monc->want_next_osdmap) { dout("__send_subscribe to 'osdmap' %u\n", - (unsigned)monc->have_osdmap); + (unsigned int)monc->have_osdmap); ceph_encode_string(&p, end, "osdmap", 6); i = p; i->have = cpu_to_le64(monc->have_osdmap); @@ -211,7 +211,7 @@ static void __send_subscribe(struct ceph_mon_client *monc) } if (monc->want_mdsmap) { dout("__send_subscribe to 'mdsmap' %u+\n", - (unsigned)monc->have_mdsmap); + (unsigned int)monc->have_mdsmap); ceph_encode_string(&p, end, "mdsmap", 6); i = p; i->have = cpu_to_le64(monc->have_mdsmap); @@ -236,7 +236,7 @@ static void __send_subscribe(struct ceph_mon_client *monc) static void handle_subscribe_ack(struct ceph_mon_client *monc, struct ceph_msg *msg) { - unsigned seconds; + unsigned int seconds; struct ceph_mon_subscribe_ack *h = msg->front.iov_base; if (msg->front.iov_len < sizeof(*h)) diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 5e254055c91..1b0ef3c4d39 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1214,7 +1214,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, } if (!req->r_got_reply) { - unsigned bytes; + unsigned int bytes; req->r_result = le32_to_cpu(rhead->result); bytes = le32_to_cpu(msg->hdr.data_len); diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 29ad46ec9dc..56e561a6900 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -38,7 +38,7 @@ done: /* maps */ -static int calc_bits_of(unsigned t) +static int calc_bits_of(unsigned int t) { int b = 0; while (t) { @@ -154,7 +154,7 @@ static struct crush_map *crush_decode(void *pbyval, void *end) magic = ceph_decode_32(p); if (magic != CRUSH_MAGIC) { pr_err("crush_decode magic %x != current %x\n", - (unsigned)magic, (unsigned)CRUSH_MAGIC); + (unsigned int)magic, (unsigned int)CRUSH_MAGIC); goto bad; } c->max_buckets = ceph_decode_32(p); @@ -460,7 +460,7 @@ static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi) static int __decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) { - unsigned n, m; + unsigned int n, m; ceph_decode_copy(p, &pi->v, sizeof(pi->v)); calc_pg_masks(pi); @@ -970,7 +970,7 @@ void ceph_calc_file_object_mapping(struct ceph_file_layout *layout, objsetno = stripeno / su_per_object; *ono = objsetno * sc + stripepos; - dout("objset %u * sc %u = ono %u\n", objsetno, sc, (unsigned)*ono); + dout("objset %u * sc %u = ono %u\n", objsetno, sc, (unsigned int)*ono); /* *oxoff = *off % layout->fl_stripe_unit; # offset in su */ t = off; @@ -998,12 +998,12 @@ int ceph_calc_object_layout(struct ceph_object_layout *ol, struct ceph_file_layout *fl, struct ceph_osdmap *osdmap) { - unsigned num, num_mask; + unsigned int num, num_mask; struct ceph_pg pgid; s32 preferred = (s32)le32_to_cpu(fl->fl_pg_preferred); int poolid = le32_to_cpu(fl->fl_pg_pool); struct ceph_pg_pool_info *pool; - unsigned ps; + unsigned int ps; BUG_ON(!osdmap); @@ -1045,7 +1045,7 @@ static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid, struct ceph_pg_mapping *pg; struct ceph_pg_pool_info *pool; int ruleno; - unsigned poolid, ps, pps, t; + unsigned int poolid, ps, pps, t; int preferred; poolid = le32_to_cpu(pgid.pool); diff --git a/net/compat.c b/net/compat.c index e055708b8ec..1b96281892d 100644 --- a/net/compat.c +++ b/net/compat.c @@ -328,14 +328,6 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm) __scm_destroy(scm); } -/* - * A struct sock_filter is architecture independent. - */ -struct compat_sock_fprog { - u16 len; - compat_uptr_t filter; /* struct sock_filter * */ -}; - static int do_set_attach_filter(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { @@ -741,13 +733,13 @@ static unsigned char nas[21] = { }; #undef AL -asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned flags) +asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags) { return sys_sendmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg, - unsigned vlen, unsigned int flags) + unsigned int vlen, unsigned int flags) { return __sys_sendmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT); @@ -758,20 +750,20 @@ asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, uns return sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } -asmlinkage long compat_sys_recv(int fd, void __user *buf, size_t len, unsigned flags) +asmlinkage long compat_sys_recv(int fd, void __user *buf, size_t len, unsigned int flags) { return sys_recv(fd, buf, len, flags | MSG_CMSG_COMPAT); } asmlinkage long compat_sys_recvfrom(int fd, void __user *buf, size_t len, - unsigned flags, struct sockaddr __user *addr, + unsigned int flags, struct sockaddr __user *addr, int __user *addrlen) { return sys_recvfrom(fd, buf, len, flags | MSG_CMSG_COMPAT, addr, addrlen); } asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, - unsigned vlen, unsigned int flags, + unsigned int vlen, unsigned int flags, struct compat_timespec __user *timeout) { int datagrams; diff --git a/net/core/datagram.c b/net/core/datagram.c index e4fbfd6e2bd..ae6acf6a3de 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -65,7 +65,7 @@ static inline int connection_based(struct sock *sk) return sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM; } -static int receiver_wake_function(wait_queue_t *wait, unsigned mode, int sync, +static int receiver_wake_function(wait_queue_t *wait, unsigned int mode, int sync, void *key) { unsigned long bits = (unsigned long)key; @@ -158,7 +158,7 @@ out_noerr: * quite explicitly by POSIX 1003.1g, don't change them without having * the standard around please. */ -struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, +struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, int *peeked, int *off, int *err) { struct sk_buff *skb; @@ -216,7 +216,7 @@ no_packet: } EXPORT_SYMBOL(__skb_recv_datagram); -struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, +struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int noblock, int *err) { int peeked, off = 0; diff --git a/net/core/dev.c b/net/core/dev.c index 5d59155adf2..cd0981977f5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -208,7 +208,8 @@ static inline void dev_base_seq_inc(struct net *net) static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) { - unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ)); + unsigned int hash = full_name_hash(name, strnlen(name, IFNAMSIZ)); + return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)]; } @@ -299,10 +300,9 @@ static const unsigned short netdev_lock_type[] = 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_IEEE802_TR, ARPHRD_IEEE80211, - ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, - ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154, - ARPHRD_VOID, ARPHRD_NONE}; + 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", @@ -317,10 +317,9 @@ static const char *const netdev_lock_name[] = "_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_IEEE802_TR", "_xmit_IEEE80211", - "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", - "_xmit_PHONET_PIPE", "_xmit_IEEE802154", - "_xmit_VOID", "_xmit_NONE"}; + "_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)]; @@ -1409,14 +1408,34 @@ EXPORT_SYMBOL(register_netdevice_notifier); * register_netdevice_notifier(). The notifier is unlinked into the * kernel structures and may then be reused. A negative errno code * is returned on a failure. + * + * After unregistering unregister and down device events are synthesized + * for all devices on the device list to the removed notifier to remove + * the need for special case cleanup code. */ int unregister_netdevice_notifier(struct notifier_block *nb) { + struct net_device *dev; + struct net *net; int err; rtnl_lock(); err = raw_notifier_chain_unregister(&netdev_chain, nb); + if (err) + goto unlock; + + for_each_net(net) { + for_each_netdev(net, dev) { + if (dev->flags & IFF_UP) { + nb->notifier_call(nb, NETDEV_GOING_DOWN, dev); + nb->notifier_call(nb, NETDEV_DOWN, dev); + } + nb->notifier_call(nb, NETDEV_UNREGISTER, dev); + nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev); + } + } +unlock: rtnl_unlock(); return err; } @@ -1596,10 +1615,15 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) kfree_skb(skb); return NET_RX_DROP; } - skb_set_dev(skb, dev); + skb->skb_iif = 0; + skb->dev = dev; + skb_dst_drop(skb); skb->tstamp.tv64 = 0; skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, dev); + skb->mark = 0; + secpath_reset(skb); + nf_reset(skb); return netif_rx(skb); } EXPORT_SYMBOL_GPL(dev_forward_skb); @@ -1651,10 +1675,9 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) if (skb_network_header(skb2) < skb2->data || skb2->network_header > skb2->tail) { - if (net_ratelimit()) - pr_crit("protocol %04x is buggy, dev %s\n", - ntohs(skb2->protocol), - dev->name); + net_crit_ratelimited("protocol %04x is buggy, dev %s\n", + ntohs(skb2->protocol), + dev->name); skb_reset_network_header(skb2); } @@ -1848,36 +1871,6 @@ void netif_device_attach(struct net_device *dev) } EXPORT_SYMBOL(netif_device_attach); -/** - * skb_dev_set -- assign a new device to a buffer - * @skb: buffer for the new device - * @dev: network device - * - * If an skb is owned by a device already, we have to reset - * all data private to the namespace a device belongs to - * before assigning it a new device. - */ -#ifdef CONFIG_NET_NS -void skb_set_dev(struct sk_buff *skb, struct net_device *dev) -{ - skb_dst_drop(skb); - if (skb->dev && !net_eq(dev_net(skb->dev), dev_net(dev))) { - secpath_reset(skb); - nf_reset(skb); - skb_init_secmark(skb); - skb->mark = 0; - skb->priority = 0; - skb->nf_trace = 0; - skb->ipvs_property = 0; -#ifdef CONFIG_NET_SCHED - skb->tc_index = 0; -#endif - } - skb->dev = dev; -} -EXPORT_SYMBOL(skb_set_dev); -#endif /* CONFIG_NET_NS */ - static void skb_warn_bad_offload(const struct sk_buff *skb) { static const netdev_features_t null_features = 0; @@ -2321,11 +2314,9 @@ EXPORT_SYMBOL(__skb_tx_hash); static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) { if (unlikely(queue_index >= dev->real_num_tx_queues)) { - if (net_ratelimit()) { - pr_warn("%s selects TX queue %d, but real number of TX queues is %d\n", - dev->name, queue_index, - dev->real_num_tx_queues); - } + net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", + dev->name, queue_index, + dev->real_num_tx_queues); return 0; } return queue_index; @@ -2567,17 +2558,15 @@ int dev_queue_xmit(struct sk_buff *skb) } } HARD_TX_UNLOCK(dev, txq); - if (net_ratelimit()) - pr_crit("Virtual device %s asks to queue packet!\n", - dev->name); + net_crit_ratelimited("Virtual device %s asks to queue packet!\n", + dev->name); } else { /* Recursion is detected! It is possible, * unfortunately */ recursion_alert: - if (net_ratelimit()) - pr_crit("Dead loop on virtual device %s, fix it urgently!\n", - dev->name); + net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n", + dev->name); } } @@ -3058,9 +3047,8 @@ static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq) struct Qdisc *q; if (unlikely(MAX_RED_LOOP < ttl++)) { - if (net_ratelimit()) - pr_warn("Redir loop detected Dropping packet (%d->%d)\n", - skb->skb_iif, dev->ifindex); + net_warn_ratelimited("Redir loop detected Dropping packet (%d->%d)\n", + skb->skb_iif, dev->ifindex); return TC_ACT_SHOT; } @@ -3520,10 +3508,16 @@ gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) break; case GRO_DROP: - case GRO_MERGED_FREE: kfree_skb(skb); break; + case GRO_MERGED_FREE: + if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) + kmem_cache_free(skbuff_head_cache, skb); + else + __kfree_skb(skb); + break; + case GRO_HELD: case GRO_MERGED: break; @@ -3608,7 +3602,7 @@ gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, } EXPORT_SYMBOL(napi_frags_finish); -struct sk_buff *napi_frags_skb(struct napi_struct *napi) +static struct sk_buff *napi_frags_skb(struct napi_struct *napi) { struct sk_buff *skb = napi->skb; struct ethhdr *eth; @@ -3643,7 +3637,6 @@ struct sk_buff *napi_frags_skb(struct napi_struct *napi) out: return skb; } -EXPORT_SYMBOL(napi_frags_skb); gro_result_t napi_gro_frags(struct napi_struct *napi) { @@ -4027,54 +4020,41 @@ static int dev_ifconf(struct net *net, char __user *arg) #ifdef CONFIG_PROC_FS -#define BUCKET_SPACE (32 - NETDEV_HASHBITS) - -struct dev_iter_state { - struct seq_net_private p; - unsigned int pos; /* bucket << BUCKET_SPACE + offset */ -}; +#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1) #define get_bucket(x) ((x) >> BUCKET_SPACE) #define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1)) #define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o)) -static inline struct net_device *dev_from_same_bucket(struct seq_file *seq) +static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos) { - struct dev_iter_state *state = seq->private; struct net *net = seq_file_net(seq); struct net_device *dev; struct hlist_node *p; struct hlist_head *h; - unsigned int count, bucket, offset; + unsigned int count = 0, offset = get_offset(*pos); - bucket = get_bucket(state->pos); - offset = get_offset(state->pos); - h = &net->dev_name_head[bucket]; - count = 0; + h = &net->dev_name_head[get_bucket(*pos)]; hlist_for_each_entry_rcu(dev, p, h, name_hlist) { - if (count++ == offset) { - state->pos = set_bucket_offset(bucket, count); + if (++count == offset) return dev; - } } return NULL; } -static inline struct net_device *dev_from_new_bucket(struct seq_file *seq) +static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos) { - struct dev_iter_state *state = seq->private; struct net_device *dev; unsigned int bucket; - bucket = get_bucket(state->pos); do { - dev = dev_from_same_bucket(seq); + dev = dev_from_same_bucket(seq, pos); if (dev) return dev; - bucket++; - state->pos = set_bucket_offset(bucket, 0); + bucket = get_bucket(*pos) + 1; + *pos = set_bucket_offset(bucket, 1); } while (bucket < NETDEV_HASHENTRIES); return NULL; @@ -4087,33 +4067,20 @@ static inline struct net_device *dev_from_new_bucket(struct seq_file *seq) void *dev_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { - struct dev_iter_state *state = seq->private; - rcu_read_lock(); if (!*pos) return SEQ_START_TOKEN; - /* check for end of the hash */ - if (state->pos == 0 && *pos > 1) + if (get_bucket(*pos) >= NETDEV_HASHENTRIES) return NULL; - return dev_from_new_bucket(seq); + return dev_from_bucket(seq, pos); } void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct net_device *dev; - ++*pos; - - if (v == SEQ_START_TOKEN) - return dev_from_new_bucket(seq); - - dev = dev_from_same_bucket(seq); - if (dev) - return dev; - - return dev_from_new_bucket(seq); + return dev_from_bucket(seq, pos); } void dev_seq_stop(struct seq_file *seq, void *v) @@ -4212,13 +4179,7 @@ static const struct seq_operations dev_seq_ops = { static int dev_seq_open(struct inode *inode, struct file *file) { return seq_open_net(inode, file, &dev_seq_ops, - sizeof(struct dev_iter_state)); -} - -int dev_seq_open_ops(struct inode *inode, struct file *file, - const struct seq_operations *ops) -{ - return seq_open_net(inode, file, ops, sizeof(struct dev_iter_state)); + sizeof(struct seq_net_private)); } static const struct file_operations dev_seq_fops = { @@ -4629,9 +4590,9 @@ void dev_set_rx_mode(struct net_device *dev) * * Get the combination of flag bits exported through APIs to userspace. */ -unsigned dev_get_flags(const struct net_device *dev) +unsigned int dev_get_flags(const struct net_device *dev) { - unsigned flags; + unsigned int flags; flags = (dev->flags & ~(IFF_PROMISC | IFF_ALLMULTI | diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 29c07fef922..c4cc2bc49f0 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -21,12 +21,35 @@ * General list handling functions */ +static int __hw_addr_create_ex(struct netdev_hw_addr_list *list, + unsigned char *addr, int addr_len, + unsigned char addr_type, bool global) +{ + struct netdev_hw_addr *ha; + int alloc_size; + + alloc_size = sizeof(*ha); + if (alloc_size < L1_CACHE_BYTES) + alloc_size = L1_CACHE_BYTES; + ha = kmalloc(alloc_size, GFP_ATOMIC); + if (!ha) + return -ENOMEM; + memcpy(ha->addr, addr, addr_len); + ha->type = addr_type; + ha->refcount = 1; + ha->global_use = global; + ha->synced = false; + list_add_tail_rcu(&ha->list, &list->list); + list->count++; + + return 0; +} + static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, unsigned char *addr, int addr_len, unsigned char addr_type, bool global) { struct netdev_hw_addr *ha; - int alloc_size; if (addr_len > MAX_ADDR_LEN) return -EINVAL; @@ -46,21 +69,7 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, } } - - alloc_size = sizeof(*ha); - if (alloc_size < L1_CACHE_BYTES) - alloc_size = L1_CACHE_BYTES; - ha = kmalloc(alloc_size, GFP_ATOMIC); - if (!ha) - return -ENOMEM; - memcpy(ha->addr, addr, addr_len); - ha->type = addr_type; - ha->refcount = 1; - ha->global_use = global; - ha->synced = false; - list_add_tail_rcu(&ha->list, &list->list); - list->count++; - return 0; + return __hw_addr_create_ex(list, addr, addr_len, addr_type, global); } static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char *addr, @@ -377,6 +386,34 @@ EXPORT_SYMBOL(dev_addr_del_multiple); */ /** + * dev_uc_add_excl - Add a global secondary unicast address + * @dev: device + * @addr: address to add + */ +int dev_uc_add_excl(struct net_device *dev, unsigned char *addr) +{ + struct netdev_hw_addr *ha; + int err; + + netif_addr_lock_bh(dev); + list_for_each_entry(ha, &dev->uc.list, list) { + if (!memcmp(ha->addr, addr, dev->addr_len) && + ha->type == NETDEV_HW_ADDR_T_UNICAST) { + err = -EEXIST; + goto out; + } + } + err = __hw_addr_create_ex(&dev->uc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_UNICAST, true); + if (!err) + __dev_set_rx_mode(dev); +out: + netif_addr_unlock_bh(dev); + return err; +} +EXPORT_SYMBOL(dev_uc_add_excl); + +/** * dev_uc_add - Add a secondary unicast address * @dev: device * @addr: address to add @@ -501,6 +538,34 @@ EXPORT_SYMBOL(dev_uc_init); * Multicast list handling functions */ +/** + * dev_mc_add_excl - Add a global secondary multicast address + * @dev: device + * @addr: address to add + */ +int dev_mc_add_excl(struct net_device *dev, unsigned char *addr) +{ + struct netdev_hw_addr *ha; + int err; + + netif_addr_lock_bh(dev); + list_for_each_entry(ha, &dev->mc.list, list) { + if (!memcmp(ha->addr, addr, dev->addr_len) && + ha->type == NETDEV_HW_ADDR_T_MULTICAST) { + err = -EEXIST; + goto out; + } + } + err = __hw_addr_create_ex(&dev->mc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_MULTICAST, true); + if (!err) + __dev_set_rx_mode(dev); +out: + netif_addr_unlock_bh(dev); + return err; +} +EXPORT_SYMBOL(dev_mc_add_excl); + static int __dev_mc_add(struct net_device *dev, unsigned char *addr, bool global) { @@ -696,7 +761,8 @@ static const struct seq_operations dev_mc_seq_ops = { static int dev_mc_seq_open(struct inode *inode, struct file *file) { - return dev_seq_open_ops(inode, file, &dev_mc_seq_ops); + return seq_open_net(inode, file, &dev_mc_seq_ops, + sizeof(struct seq_net_private)); } static const struct file_operations dev_mc_seq_fops = { diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 7f36b38e060..3252e7e0a00 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -4,6 +4,8 @@ * Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/string.h> @@ -22,6 +24,7 @@ #include <linux/timer.h> #include <linux/bitops.h> #include <linux/slab.h> +#include <linux/module.h> #include <net/genetlink.h> #include <net/netevent.h> @@ -42,13 +45,14 @@ static void send_dm_alert(struct work_struct *unused); * netlink alerts */ static int trace_state = TRACE_OFF; -static DEFINE_SPINLOCK(trace_state_lock); +static DEFINE_MUTEX(trace_state_mutex); struct per_cpu_dm_data { struct work_struct dm_alert_work; - struct sk_buff *skb; + struct sk_buff __rcu *skb; atomic_t dm_hit_count; struct timer_list send_timer; + int cpu; }; struct dm_hw_stat_delta { @@ -79,29 +83,53 @@ static void reset_per_cpu_data(struct per_cpu_dm_data *data) size_t al; struct net_dm_alert_msg *msg; struct nlattr *nla; + struct sk_buff *skb; + struct sk_buff *oskb = rcu_dereference_protected(data->skb, 1); al = sizeof(struct net_dm_alert_msg); al += dm_hit_limit * sizeof(struct net_dm_drop_point); al += sizeof(struct nlattr); - data->skb = genlmsg_new(al, GFP_KERNEL); - genlmsg_put(data->skb, 0, 0, &net_drop_monitor_family, - 0, NET_DM_CMD_ALERT); - nla = nla_reserve(data->skb, NLA_UNSPEC, sizeof(struct net_dm_alert_msg)); - msg = nla_data(nla); - memset(msg, 0, al); - atomic_set(&data->dm_hit_count, dm_hit_limit); + skb = genlmsg_new(al, GFP_KERNEL); + + if (skb) { + genlmsg_put(skb, 0, 0, &net_drop_monitor_family, + 0, NET_DM_CMD_ALERT); + nla = nla_reserve(skb, NLA_UNSPEC, + sizeof(struct net_dm_alert_msg)); + msg = nla_data(nla); + memset(msg, 0, al); + } else + schedule_work_on(data->cpu, &data->dm_alert_work); + + /* + * Don't need to lock this, since we are guaranteed to only + * run this on a single cpu at a time. + * Note also that we only update data->skb if the old and new skb + * pointers don't match. This ensures that we don't continually call + * synchornize_rcu if we repeatedly fail to alloc a new netlink message. + */ + if (skb != oskb) { + rcu_assign_pointer(data->skb, skb); + + synchronize_rcu(); + + atomic_set(&data->dm_hit_count, dm_hit_limit); + } + } static void send_dm_alert(struct work_struct *unused) { struct sk_buff *skb; - struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data); + struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data); + + WARN_ON_ONCE(data->cpu != smp_processor_id()); /* * Grab the skb we're about to send */ - skb = data->skb; + skb = rcu_dereference_protected(data->skb, 1); /* * Replace it with a new one @@ -111,8 +139,10 @@ static void send_dm_alert(struct work_struct *unused) /* * Ship it! */ - genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL); + if (skb) + genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL); + put_cpu_var(dm_cpu_data); } /* @@ -123,9 +153,11 @@ static void send_dm_alert(struct work_struct *unused) */ static void sched_send_work(unsigned long unused) { - struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data); + struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data); + + schedule_work_on(smp_processor_id(), &data->dm_alert_work); - schedule_work(&data->dm_alert_work); + put_cpu_var(dm_cpu_data); } static void trace_drop_common(struct sk_buff *skb, void *location) @@ -134,9 +166,16 @@ static void trace_drop_common(struct sk_buff *skb, void *location) struct nlmsghdr *nlh; struct nlattr *nla; int i; - struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data); + struct sk_buff *dskb; + struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data); + rcu_read_lock(); + dskb = rcu_dereference(data->skb); + + if (!dskb) + goto out; + if (!atomic_add_unless(&data->dm_hit_count, -1, 0)) { /* * we're already at zero, discard this hit @@ -144,12 +183,13 @@ static void trace_drop_common(struct sk_buff *skb, void *location) goto out; } - nlh = (struct nlmsghdr *)data->skb->data; + nlh = (struct nlmsghdr *)dskb->data; nla = genlmsg_data(nlmsg_data(nlh)); msg = nla_data(nla); for (i = 0; i < msg->entries; i++) { if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) { msg->points[i].count++; + atomic_inc(&data->dm_hit_count); goto out; } } @@ -157,7 +197,7 @@ static void trace_drop_common(struct sk_buff *skb, void *location) /* * We need to create a new entry */ - __nla_reserve_nohdr(data->skb, sizeof(struct net_dm_drop_point)); + __nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point)); nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point)); memcpy(msg->points[msg->entries].pc, &location, sizeof(void *)); msg->points[msg->entries].count = 1; @@ -169,6 +209,8 @@ static void trace_drop_common(struct sk_buff *skb, void *location) } out: + rcu_read_unlock(); + put_cpu_var(dm_cpu_data); return; } @@ -213,7 +255,7 @@ static int set_all_monitor_traces(int state) struct dm_hw_stat_delta *new_stat = NULL; struct dm_hw_stat_delta *temp; - spin_lock(&trace_state_lock); + mutex_lock(&trace_state_mutex); if (state == trace_state) { rc = -EAGAIN; @@ -222,9 +264,15 @@ static int set_all_monitor_traces(int state) switch (state) { case TRACE_ON: + if (!try_module_get(THIS_MODULE)) { + rc = -ENODEV; + break; + } + rc |= register_trace_kfree_skb(trace_kfree_skb_hit, NULL); rc |= register_trace_napi_poll(trace_napi_poll_hit, NULL); break; + case TRACE_OFF: rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit, NULL); rc |= unregister_trace_napi_poll(trace_napi_poll_hit, NULL); @@ -240,6 +288,9 @@ static int set_all_monitor_traces(int state) kfree_rcu(new_stat, rcu); } } + + module_put(THIS_MODULE); + break; default: rc = 1; @@ -252,7 +303,7 @@ static int set_all_monitor_traces(int state) rc = -EINPROGRESS; out_unlock: - spin_unlock(&trace_state_lock); + mutex_unlock(&trace_state_mutex); return rc; } @@ -295,12 +346,12 @@ static int dropmon_net_event(struct notifier_block *ev_block, new_stat->dev = dev; new_stat->last_rx = jiffies; - spin_lock(&trace_state_lock); + mutex_lock(&trace_state_mutex); list_add_rcu(&new_stat->list, &hw_stats_list); - spin_unlock(&trace_state_lock); + mutex_unlock(&trace_state_mutex); break; case NETDEV_UNREGISTER: - spin_lock(&trace_state_lock); + mutex_lock(&trace_state_mutex); list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) { if (new_stat->dev == dev) { new_stat->dev = NULL; @@ -311,7 +362,7 @@ static int dropmon_net_event(struct notifier_block *ev_block, } } } - spin_unlock(&trace_state_lock); + mutex_unlock(&trace_state_mutex); break; } out: @@ -342,10 +393,10 @@ static int __init init_net_drop_monitor(void) struct per_cpu_dm_data *data; int cpu, rc; - printk(KERN_INFO "Initializing network drop monitor service\n"); + pr_info("Initializing network drop monitor service\n"); if (sizeof(void *) > 8) { - printk(KERN_ERR "Unable to store program counters on this arch, Drop monitor failed\n"); + pr_err("Unable to store program counters on this arch, Drop monitor failed\n"); return -ENOSPC; } @@ -353,27 +404,29 @@ static int __init init_net_drop_monitor(void) dropmon_ops, ARRAY_SIZE(dropmon_ops)); if (rc) { - printk(KERN_ERR "Could not create drop monitor netlink family\n"); + pr_err("Could not create drop monitor netlink family\n"); return rc; } rc = register_netdevice_notifier(&dropmon_net_notifier); if (rc < 0) { - printk(KERN_CRIT "Failed to register netdevice notifier\n"); + pr_crit("Failed to register netdevice notifier\n"); goto out_unreg; } rc = 0; - for_each_present_cpu(cpu) { + for_each_possible_cpu(cpu) { data = &per_cpu(dm_cpu_data, cpu); - reset_per_cpu_data(data); + data->cpu = cpu; INIT_WORK(&data->dm_alert_work, send_dm_alert); init_timer(&data->send_timer); data->send_timer.data = cpu; data->send_timer.function = sched_send_work; + reset_per_cpu_data(data); } + goto out; out_unreg: @@ -382,4 +435,36 @@ out: return rc; } -late_initcall(init_net_drop_monitor); +static void exit_net_drop_monitor(void) +{ + struct per_cpu_dm_data *data; + int cpu; + + BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); + + /* + * Because of the module_get/put we do in the trace state change path + * we are guarnateed not to have any current users when we get here + * all we need to do is make sure that we don't have any running timers + * or pending schedule calls + */ + + for_each_possible_cpu(cpu) { + data = &per_cpu(dm_cpu_data, cpu); + del_timer_sync(&data->send_timer); + cancel_work_sync(&data->dm_alert_work); + /* + * At this point, we should have exclusive access + * to this struct and can free the skb inside it + */ + kfree_skb(data->skb); + } + + BUG_ON(genl_unregister_family(&net_drop_monitor_family)); +} + +module_init(init_net_drop_monitor); +module_exit(exit_net_drop_monitor); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>"); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 6d6d7d25caa..9c2afb48027 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -17,6 +17,8 @@ #include <linux/errno.h> #include <linux/ethtool.h> #include <linux/netdevice.h> +#include <linux/net_tstamp.h> +#include <linux/phy.h> #include <linux/bitops.h> #include <linux/uaccess.h> #include <linux/vmalloc.h> @@ -36,6 +38,17 @@ u32 ethtool_op_get_link(struct net_device *dev) } EXPORT_SYMBOL(ethtool_op_get_link); +int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) +{ + info->so_timestamping = + SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + info->phc_index = -1; + return 0; +} +EXPORT_SYMBOL(ethtool_op_get_ts_info); + /* Handlers for each ethtool command */ #define ETHTOOL_DEV_FEATURE_WORDS ((NETDEV_FEATURE_COUNT + 31) / 32) @@ -738,18 +751,17 @@ static int ethtool_get_link(struct net_device *dev, char __user *useraddr) return 0; } -static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr) +static int ethtool_get_any_eeprom(struct net_device *dev, void __user *useraddr, + int (*getter)(struct net_device *, + struct ethtool_eeprom *, u8 *), + u32 total_len) { struct ethtool_eeprom eeprom; - const struct ethtool_ops *ops = dev->ethtool_ops; void __user *userbuf = useraddr + sizeof(eeprom); u32 bytes_remaining; u8 *data; int ret = 0; - if (!ops->get_eeprom || !ops->get_eeprom_len) - return -EOPNOTSUPP; - if (copy_from_user(&eeprom, useraddr, sizeof(eeprom))) return -EFAULT; @@ -758,7 +770,7 @@ static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr) return -EINVAL; /* Check for exceeding total eeprom len */ - if (eeprom.offset + eeprom.len > ops->get_eeprom_len(dev)) + if (eeprom.offset + eeprom.len > total_len) return -EINVAL; data = kmalloc(PAGE_SIZE, GFP_USER); @@ -769,7 +781,7 @@ static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr) while (bytes_remaining > 0) { eeprom.len = min(bytes_remaining, (u32)PAGE_SIZE); - ret = ops->get_eeprom(dev, &eeprom, data); + ret = getter(dev, &eeprom, data); if (ret) break; if (copy_to_user(userbuf, data, eeprom.len)) { @@ -790,6 +802,17 @@ static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr) return ret; } +static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (!ops->get_eeprom || !ops->get_eeprom_len) + return -EOPNOTSUPP; + + return ethtool_get_any_eeprom(dev, useraddr, ops->get_eeprom, + ops->get_eeprom_len(dev)); +} + static int ethtool_set_eeprom(struct net_device *dev, void __user *useraddr) { struct ethtool_eeprom eeprom; @@ -1278,6 +1301,81 @@ out: return ret; } +static int ethtool_get_ts_info(struct net_device *dev, void __user *useraddr) +{ + int err = 0; + struct ethtool_ts_info info; + const struct ethtool_ops *ops = dev->ethtool_ops; + struct phy_device *phydev = dev->phydev; + + memset(&info, 0, sizeof(info)); + info.cmd = ETHTOOL_GET_TS_INFO; + + if (phydev && phydev->drv && phydev->drv->ts_info) { + + err = phydev->drv->ts_info(phydev, &info); + + } else if (dev->ethtool_ops && dev->ethtool_ops->get_ts_info) { + + err = ops->get_ts_info(dev, &info); + + } else { + info.so_timestamping = + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + info.phc_index = -1; + } + + if (err) + return err; + + if (copy_to_user(useraddr, &info, sizeof(info))) + err = -EFAULT; + + return err; +} + +static int ethtool_get_module_info(struct net_device *dev, + void __user *useraddr) +{ + int ret; + struct ethtool_modinfo modinfo; + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (!ops->get_module_info) + return -EOPNOTSUPP; + + if (copy_from_user(&modinfo, useraddr, sizeof(modinfo))) + return -EFAULT; + + ret = ops->get_module_info(dev, &modinfo); + if (ret) + return ret; + + if (copy_to_user(useraddr, &modinfo, sizeof(modinfo))) + return -EFAULT; + + return 0; +} + +static int ethtool_get_module_eeprom(struct net_device *dev, + void __user *useraddr) +{ + int ret; + struct ethtool_modinfo modinfo; + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (!ops->get_module_info || !ops->get_module_eeprom) + return -EOPNOTSUPP; + + ret = ops->get_module_info(dev, &modinfo); + if (ret) + return ret; + + return ethtool_get_any_eeprom(dev, useraddr, ops->get_module_eeprom, + modinfo.eeprom_len); +} + /* The main entry point in this file. Called from net/core/dev.c */ int dev_ethtool(struct net *net, struct ifreq *ifr) @@ -1295,11 +1393,13 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) return -EFAULT; if (!dev->ethtool_ops) { - /* ETHTOOL_GDRVINFO does not require any driver support. - * It is also unprivileged and does not change anything, - * so we can take a shortcut to it. */ + /* A few commands do not require any driver support, + * are unprivileged, and do not change anything, so we + * can take a shortcut to them. */ if (ethcmd == ETHTOOL_GDRVINFO) return ethtool_get_drvinfo(dev, useraddr); + else if (ethcmd == ETHTOOL_GET_TS_INFO) + return ethtool_get_ts_info(dev, useraddr); else return -EOPNOTSUPP; } @@ -1330,6 +1430,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GRXCLSRULE: case ETHTOOL_GRXCLSRLALL: case ETHTOOL_GFEATURES: + case ETHTOOL_GET_TS_INFO: break; default: if (!capable(CAP_NET_ADMIN)) @@ -1496,6 +1597,15 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GET_DUMP_DATA: rc = ethtool_get_dump_data(dev, useraddr); break; + case ETHTOOL_GET_TS_INFO: + rc = ethtool_get_ts_info(dev, useraddr); + break; + case ETHTOOL_GMODULEINFO: + rc = ethtool_get_module_info(dev, useraddr); + break; + case ETHTOOL_GMODULEEEPROM: + rc = ethtool_get_module_eeprom(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index c02e63c908d..72cceb79d0d 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -542,7 +542,8 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh = nlmsg_data(nlh); frh->family = ops->family; frh->table = rule->table; - NLA_PUT_U32(skb, FRA_TABLE, rule->table); + if (nla_put_u32(skb, FRA_TABLE, rule->table)) + goto nla_put_failure; frh->res1 = 0; frh->res2 = 0; frh->action = rule->action; @@ -553,31 +554,28 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh->flags |= FIB_RULE_UNRESOLVED; if (rule->iifname[0]) { - NLA_PUT_STRING(skb, FRA_IIFNAME, rule->iifname); - + if (nla_put_string(skb, FRA_IIFNAME, rule->iifname)) + goto nla_put_failure; if (rule->iifindex == -1) frh->flags |= FIB_RULE_IIF_DETACHED; } if (rule->oifname[0]) { - NLA_PUT_STRING(skb, FRA_OIFNAME, rule->oifname); - + if (nla_put_string(skb, FRA_OIFNAME, rule->oifname)) + goto nla_put_failure; if (rule->oifindex == -1) frh->flags |= FIB_RULE_OIF_DETACHED; } - if (rule->pref) - NLA_PUT_U32(skb, FRA_PRIORITY, rule->pref); - - if (rule->mark) - NLA_PUT_U32(skb, FRA_FWMARK, rule->mark); - - if (rule->mark_mask || rule->mark) - NLA_PUT_U32(skb, FRA_FWMASK, rule->mark_mask); - - if (rule->target) - NLA_PUT_U32(skb, FRA_GOTO, rule->target); - + if ((rule->pref && + nla_put_u32(skb, FRA_PRIORITY, rule->pref)) || + (rule->mark && + nla_put_u32(skb, FRA_FWMARK, rule->mark)) || + ((rule->mark_mask || rule->mark) && + nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) || + (rule->target && + nla_put_u32(skb, FRA_GOTO, rule->target))) + goto nla_put_failure; if (ops->fill(rule, skb, frh) < 0) goto nla_put_failure; diff --git a/net/core/filter.c b/net/core/filter.c index cf4989ac503..a3eddb515d1 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -38,9 +38,13 @@ #include <linux/filter.h> #include <linux/reciprocal_div.h> #include <linux/ratelimit.h> +#include <linux/seccomp.h> -/* No hurry in this branch */ -static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size) +/* No hurry in this branch + * + * Exported for the bpf jit load helper. + */ +void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size) { u8 *ptr = NULL; @@ -59,7 +63,7 @@ static inline void *load_pointer(const struct sk_buff *skb, int k, { if (k >= 0) return skb_header_pointer(skb, k, size, buffer); - return __load_pointer(skb, k, size); + return bpf_internal_load_pointer_neg_helper(skb, k, size); } /** @@ -314,6 +318,9 @@ load_b: case BPF_S_ANC_CPU: A = raw_smp_processor_id(); continue; + case BPF_S_ANC_ALU_XOR_X: + A ^= X; + continue; case BPF_S_ANC_NLATTR: { struct nlattr *nla; @@ -349,6 +356,11 @@ load_b: A = 0; continue; } +#ifdef CONFIG_SECCOMP_FILTER + case BPF_S_ANC_SECCOMP_LD_W: + A = seccomp_bpf_load(fentry->k); + continue; +#endif default: WARN_RATELIMIT(1, "Unknown code:%u jt:%u tf:%u k:%u\n", fentry->code, fentry->jt, @@ -525,7 +537,7 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) * Compare this with conditional jumps below, * where offsets are limited. --ANK (981016) */ - if (ftest->k >= (unsigned)(flen-pc-1)) + if (ftest->k >= (unsigned int)(flen-pc-1)) return -EINVAL; break; case BPF_S_JMP_JEQ_K: @@ -558,6 +570,7 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) ANCILLARY(HATYPE); ANCILLARY(RXHASH); ANCILLARY(CPU); + ANCILLARY(ALU_XOR_X); } } ftest->code = code; @@ -586,6 +599,67 @@ void sk_filter_release_rcu(struct rcu_head *rcu) } EXPORT_SYMBOL(sk_filter_release_rcu); +static int __sk_prepare_filter(struct sk_filter *fp) +{ + int err; + + fp->bpf_func = sk_run_filter; + + err = sk_chk_filter(fp->insns, fp->len); + if (err) + return err; + + bpf_jit_compile(fp); + return 0; +} + +/** + * sk_unattached_filter_create - create an unattached filter + * @fprog: the filter program + * @sk: the socket to use + * + * Create a filter independent ofr any socket. We first run some + * sanity checks on it to make sure it does not explode on us later. + * If an error occurs or there is insufficient memory for the filter + * a negative errno code is returned. On success the return is zero. + */ +int sk_unattached_filter_create(struct sk_filter **pfp, + struct sock_fprog *fprog) +{ + struct sk_filter *fp; + unsigned int fsize = sizeof(struct sock_filter) * fprog->len; + int err; + + /* Make sure new filter is there and in the right amounts. */ + if (fprog->filter == NULL) + return -EINVAL; + + fp = kmalloc(fsize + sizeof(*fp), GFP_KERNEL); + if (!fp) + return -ENOMEM; + memcpy(fp->insns, fprog->filter, fsize); + + atomic_set(&fp->refcnt, 1); + fp->len = fprog->len; + + err = __sk_prepare_filter(fp); + if (err) + goto free_mem; + + *pfp = fp; + return 0; +free_mem: + kfree(fp); + return err; +} +EXPORT_SYMBOL_GPL(sk_unattached_filter_create); + +void sk_unattached_filter_destroy(struct sk_filter *fp) +{ + sk_filter_release(fp); +} +EXPORT_SYMBOL_GPL(sk_unattached_filter_destroy); + /** * sk_attach_filter - attach a socket filter * @fprog: the filter program @@ -616,16 +690,13 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) atomic_set(&fp->refcnt, 1); fp->len = fprog->len; - fp->bpf_func = sk_run_filter; - err = sk_chk_filter(fp->insns, fp->len); + err = __sk_prepare_filter(fp); if (err) { sk_filter_uncharge(sk, fp); return err; } - bpf_jit_compile(fp); - old_fp = rcu_dereference_protected(sk->sk_filter, sock_owned_by_user(sk)); rcu_assign_pointer(sk->sk_filter, fp); diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index 0452eb27a27..ddedf211e58 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -27,7 +27,8 @@ static inline int gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size) { - NLA_PUT(d->skb, type, size, buf); + if (nla_put(d->skb, type, size, buf)) + goto nla_put_failure; return 0; nla_put_failure: diff --git a/net/core/kmap_skb.h b/net/core/kmap_skb.h deleted file mode 100644 index 52d0a445904..00000000000 --- a/net/core/kmap_skb.h +++ /dev/null @@ -1,19 +0,0 @@ -#include <linux/highmem.h> - -static inline void *kmap_skb_frag(const skb_frag_t *frag) -{ -#ifdef CONFIG_HIGHMEM - BUG_ON(in_irq()); - - local_bh_disable(); -#endif - return kmap_atomic(skb_frag_page(frag)); -} - -static inline void kunmap_skb_frag(void *vaddr) -{ - kunmap_atomic(vaddr); -#ifdef CONFIG_HIGHMEM - local_bh_enable(); -#endif -} diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 0a68045782d..eb09f8bbbf0 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -15,6 +15,8 @@ * Harald Welte Add neighbour cache statistics like rtstat */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> @@ -712,14 +714,13 @@ void neigh_destroy(struct neighbour *neigh) NEIGH_CACHE_STAT_INC(neigh->tbl, destroys); if (!neigh->dead) { - printk(KERN_WARNING - "Destroying alive neighbour %p\n", neigh); + pr_warn("Destroying alive neighbour %p\n", neigh); dump_stack(); return; } if (neigh_del_timer(neigh)) - printk(KERN_WARNING "Impossible event.\n"); + pr_warn("Impossible event\n"); skb_queue_purge(&neigh->arp_queue); neigh->arp_queue_len_bytes = 0; @@ -890,7 +891,7 @@ static void neigh_timer_handler(unsigned long arg) { unsigned long now, next; struct neighbour *neigh = (struct neighbour *)arg; - unsigned state; + unsigned int state; int notify = 0; write_lock(&neigh->lock); @@ -1500,7 +1501,7 @@ static void neigh_parms_destroy(struct neigh_parms *parms) static struct lock_class_key neigh_table_proxy_queue_class; -void neigh_table_init_no_netlink(struct neigh_table *tbl) +static void neigh_table_init_no_netlink(struct neigh_table *tbl) { unsigned long now = jiffies; unsigned long phsize; @@ -1538,7 +1539,6 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl) tbl->last_flush = now; tbl->last_rand = now + tbl->parms.reachable_time * 20; } -EXPORT_SYMBOL(neigh_table_init_no_netlink); void neigh_table_init(struct neigh_table *tbl) { @@ -1555,8 +1555,8 @@ void neigh_table_init(struct neigh_table *tbl) write_unlock(&neigh_tbl_lock); if (unlikely(tmp)) { - printk(KERN_ERR "NEIGH: Registering multiple tables for " - "family %d\n", tbl->family); + pr_err("Registering multiple tables for family %d\n", + tbl->family); dump_stack(); } } @@ -1572,7 +1572,7 @@ int neigh_table_clear(struct neigh_table *tbl) pneigh_queue_purge(&tbl->proxy_queue); neigh_ifdown(tbl, NULL); if (atomic_read(&tbl->entries)) - printk(KERN_CRIT "neighbour leakage\n"); + pr_crit("neighbour leakage\n"); write_lock(&neigh_tbl_lock); for (tp = &neigh_tables; *tp; tp = &(*tp)->next) { if (*tp == tbl) { @@ -1768,29 +1768,29 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) if (nest == NULL) return -ENOBUFS; - if (parms->dev) - NLA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex); - - NLA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)); - NLA_PUT_U32(skb, NDTPA_QUEUE_LENBYTES, parms->queue_len_bytes); - /* approximative value for deprecated QUEUE_LEN (in packets) */ - NLA_PUT_U32(skb, NDTPA_QUEUE_LEN, - DIV_ROUND_UP(parms->queue_len_bytes, - SKB_TRUESIZE(ETH_FRAME_LEN))); - NLA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen); - NLA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes); - NLA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes); - NLA_PUT_U32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes); - NLA_PUT_MSECS(skb, NDTPA_REACHABLE_TIME, parms->reachable_time); - NLA_PUT_MSECS(skb, NDTPA_BASE_REACHABLE_TIME, - parms->base_reachable_time); - NLA_PUT_MSECS(skb, NDTPA_GC_STALETIME, parms->gc_staletime); - NLA_PUT_MSECS(skb, NDTPA_DELAY_PROBE_TIME, parms->delay_probe_time); - NLA_PUT_MSECS(skb, NDTPA_RETRANS_TIME, parms->retrans_time); - NLA_PUT_MSECS(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay); - NLA_PUT_MSECS(skb, NDTPA_PROXY_DELAY, parms->proxy_delay); - NLA_PUT_MSECS(skb, NDTPA_LOCKTIME, parms->locktime); - + if ((parms->dev && + nla_put_u32(skb, NDTPA_IFINDEX, parms->dev->ifindex)) || + nla_put_u32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)) || + nla_put_u32(skb, NDTPA_QUEUE_LENBYTES, parms->queue_len_bytes) || + /* approximative value for deprecated QUEUE_LEN (in packets) */ + nla_put_u32(skb, NDTPA_QUEUE_LEN, + DIV_ROUND_UP(parms->queue_len_bytes, + SKB_TRUESIZE(ETH_FRAME_LEN))) || + nla_put_u32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen) || + nla_put_u32(skb, NDTPA_APP_PROBES, parms->app_probes) || + nla_put_u32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes) || + nla_put_u32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes) || + nla_put_msecs(skb, NDTPA_REACHABLE_TIME, parms->reachable_time) || + nla_put_msecs(skb, NDTPA_BASE_REACHABLE_TIME, + parms->base_reachable_time) || + nla_put_msecs(skb, NDTPA_GC_STALETIME, parms->gc_staletime) || + nla_put_msecs(skb, NDTPA_DELAY_PROBE_TIME, + parms->delay_probe_time) || + nla_put_msecs(skb, NDTPA_RETRANS_TIME, parms->retrans_time) || + nla_put_msecs(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay) || + nla_put_msecs(skb, NDTPA_PROXY_DELAY, parms->proxy_delay) || + nla_put_msecs(skb, NDTPA_LOCKTIME, parms->locktime)) + goto nla_put_failure; return nla_nest_end(skb, nest); nla_put_failure: @@ -1815,12 +1815,12 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, ndtmsg->ndtm_pad1 = 0; ndtmsg->ndtm_pad2 = 0; - NLA_PUT_STRING(skb, NDTA_NAME, tbl->id); - NLA_PUT_MSECS(skb, NDTA_GC_INTERVAL, tbl->gc_interval); - NLA_PUT_U32(skb, NDTA_THRESH1, tbl->gc_thresh1); - NLA_PUT_U32(skb, NDTA_THRESH2, tbl->gc_thresh2); - NLA_PUT_U32(skb, NDTA_THRESH3, tbl->gc_thresh3); - + if (nla_put_string(skb, NDTA_NAME, tbl->id) || + nla_put_msecs(skb, NDTA_GC_INTERVAL, tbl->gc_interval) || + nla_put_u32(skb, NDTA_THRESH1, tbl->gc_thresh1) || + nla_put_u32(skb, NDTA_THRESH2, tbl->gc_thresh2) || + nla_put_u32(skb, NDTA_THRESH3, tbl->gc_thresh3)) + goto nla_put_failure; { unsigned long now = jiffies; unsigned int flush_delta = now - tbl->last_flush; @@ -1841,7 +1841,8 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, ndc.ndtc_hash_mask = ((1 << nht->hash_shift) - 1); rcu_read_unlock_bh(); - NLA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc); + if (nla_put(skb, NDTA_CONFIG, sizeof(ndc), &ndc)) + goto nla_put_failure; } { @@ -1866,7 +1867,8 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, ndst.ndts_forced_gc_runs += st->forced_gc_runs; } - NLA_PUT(skb, NDTA_STATS, sizeof(ndst), &ndst); + if (nla_put(skb, NDTA_STATS, sizeof(ndst), &ndst)) + goto nla_put_failure; } BUG_ON(tbl->parms.dev); @@ -2137,7 +2139,8 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, ndm->ndm_type = neigh->type; ndm->ndm_ifindex = neigh->dev->ifindex; - NLA_PUT(skb, NDA_DST, neigh->tbl->key_len, neigh->primary_key); + if (nla_put(skb, NDA_DST, neigh->tbl->key_len, neigh->primary_key)) + goto nla_put_failure; read_lock_bh(&neigh->lock); ndm->ndm_state = neigh->nud_state; @@ -2157,8 +2160,9 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, ci.ndm_refcnt = atomic_read(&neigh->refcnt) - 1; read_unlock_bh(&neigh->lock); - NLA_PUT_U32(skb, NDA_PROBES, atomic_read(&neigh->probes)); - NLA_PUT(skb, NDA_CACHEINFO, sizeof(ci), &ci); + if (nla_put_u32(skb, NDA_PROBES, atomic_read(&neigh->probes)) || + nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) + goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -2187,7 +2191,8 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, ndm->ndm_ifindex = pn->dev->ifindex; ndm->ndm_state = NUD_NONE; - NLA_PUT(skb, NDA_DST, tbl->key_len, pn->key); + if (nla_put(skb, NDA_DST, tbl->key_len, pn->key)) + goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -2795,7 +2800,6 @@ enum { static struct neigh_sysctl_table { struct ctl_table_header *sysctl_header; struct ctl_table neigh_vars[NEIGH_VAR_MAX + 1]; - char *dev_name; } neigh_sysctl_template __read_mostly = { .neigh_vars = { [NEIGH_VAR_MCAST_PROBE] = { @@ -2921,19 +2925,7 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, { struct neigh_sysctl_table *t; const char *dev_name_source = NULL; - -#define NEIGH_CTL_PATH_ROOT 0 -#define NEIGH_CTL_PATH_PROTO 1 -#define NEIGH_CTL_PATH_NEIGH 2 -#define NEIGH_CTL_PATH_DEV 3 - - struct ctl_path neigh_path[] = { - { .procname = "net", }, - { .procname = "proto", }, - { .procname = "neigh", }, - { .procname = "default", }, - { }, - }; + char neigh_path[ sizeof("net//neigh/") + IFNAMSIZ + IFNAMSIZ ]; t = kmemdup(&neigh_sysctl_template, sizeof(*t), GFP_KERNEL); if (!t) @@ -2961,7 +2953,7 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, memset(&t->neigh_vars[NEIGH_VAR_GC_INTERVAL], 0, sizeof(t->neigh_vars[NEIGH_VAR_GC_INTERVAL])); } else { - dev_name_source = neigh_path[NEIGH_CTL_PATH_DEV].procname; + dev_name_source = "default"; t->neigh_vars[NEIGH_VAR_GC_INTERVAL].data = (int *)(p + 1); t->neigh_vars[NEIGH_VAR_GC_THRESH1].data = (int *)(p + 1) + 1; t->neigh_vars[NEIGH_VAR_GC_THRESH2].data = (int *)(p + 1) + 2; @@ -2984,23 +2976,16 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].extra1 = dev; } - t->dev_name = kstrdup(dev_name_source, GFP_KERNEL); - if (!t->dev_name) - goto free; - - neigh_path[NEIGH_CTL_PATH_DEV].procname = t->dev_name; - neigh_path[NEIGH_CTL_PATH_PROTO].procname = p_name; - + snprintf(neigh_path, sizeof(neigh_path), "net/%s/neigh/%s", + p_name, dev_name_source); t->sysctl_header = - register_net_sysctl_table(neigh_parms_net(p), neigh_path, t->neigh_vars); + register_net_sysctl(neigh_parms_net(p), neigh_path, t->neigh_vars); if (!t->sysctl_header) - goto free_procname; + goto free; p->sysctl_table = t; return 0; -free_procname: - kfree(t->dev_name); free: kfree(t); err: @@ -3013,8 +2998,7 @@ void neigh_sysctl_unregister(struct neigh_parms *p) if (p->sysctl_table) { struct neigh_sysctl_table *t = p->sysctl_table; p->sysctl_table = NULL; - unregister_sysctl_table(t->sysctl_header); - kfree(t->dev_name); + unregister_net_sysctl_table(t->sysctl_header); kfree(t); } } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 495586232aa..fdf9e61d065 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -74,15 +74,14 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, int (*set)(struct net_device *, unsigned long)) { struct net_device *net = to_net_dev(dev); - char *endp; unsigned long new; int ret = -EINVAL; if (!capable(CAP_NET_ADMIN)) return -EPERM; - new = simple_strtoul(buf, &endp, 0); - if (endp == buf) + ret = kstrtoul(buf, 0, &new); + if (ret) goto err; if (!rtnl_trylock()) @@ -232,7 +231,7 @@ NETDEVICE_SHOW(flags, fmt_hex); static int change_flags(struct net_device *net, unsigned long new_flags) { - return dev_change_flags(net, (unsigned) new_flags); + return dev_change_flags(net, (unsigned int) new_flags); } static ssize_t store_flags(struct device *dev, struct device_attribute *attr, @@ -582,7 +581,7 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, return err; } - map = kzalloc(max_t(unsigned, + map = kzalloc(max_t(unsigned int, RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES), GFP_KERNEL); if (!map) { @@ -903,7 +902,7 @@ static ssize_t bql_set_hold_time(struct netdev_queue *queue, const char *buf, size_t len) { struct dql *dql = &queue->dql; - unsigned value; + unsigned int value; int err; err = kstrtouint(buf, 10, &value); @@ -1107,7 +1106,7 @@ static ssize_t store_xps_map(struct netdev_queue *queue, return err; } - new_dev_maps = kzalloc(max_t(unsigned, + new_dev_maps = kzalloc(max_t(unsigned int, XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES), GFP_KERNEL); if (!new_dev_maps) { free_cpumask_var(mask); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 0e950fda9a0..dddbacb8f28 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -1,3 +1,5 @@ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/workqueue.h> #include <linux/rtnetlink.h> #include <linux/cache.h> @@ -83,21 +85,29 @@ assign: static int ops_init(const struct pernet_operations *ops, struct net *net) { - int err; + int err = -ENOMEM; + void *data = NULL; + if (ops->id && ops->size) { - void *data = kzalloc(ops->size, GFP_KERNEL); + data = kzalloc(ops->size, GFP_KERNEL); if (!data) - return -ENOMEM; + goto out; err = net_assign_generic(net, *ops->id, data); - if (err) { - kfree(data); - return err; - } + if (err) + goto cleanup; } + err = 0; if (ops->init) - return ops->init(net); - return 0; + err = ops->init(net); + if (!err) + return 0; + +cleanup: + kfree(data); + +out: + return err; } static void ops_free(const struct pernet_operations *ops, struct net *net) @@ -204,8 +214,8 @@ static void net_free(struct net *net) { #ifdef NETNS_REFCNT_DEBUG if (unlikely(atomic_read(&net->use_count) != 0)) { - printk(KERN_EMERG "network namespace not free! Usage: %d\n", - atomic_read(&net->use_count)); + pr_emerg("network namespace not free! Usage: %d\n", + atomic_read(&net->use_count)); return; } #endif @@ -448,12 +458,7 @@ static void __unregister_pernet_operations(struct pernet_operations *ops) static int __register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { - int err = 0; - err = ops_init(ops, &init_net); - if (err) - ops_free(ops, &init_net); - return err; - + return ops_init(ops, &init_net); } static void __unregister_pernet_operations(struct pernet_operations *ops) diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index b2a59866699..5b8aa2fae48 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -9,6 +9,8 @@ * Authors: Neil Horman <nhorman@tuxdriver.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> @@ -73,7 +75,7 @@ static void extend_netdev_table(struct net_device *dev, u32 new_len) old_priomap = rtnl_dereference(dev->priomap); if (!new_priomap) { - printk(KERN_WARNING "Unable to alloc new priomap!\n"); + pr_warn("Unable to alloc new priomap!\n"); return; } @@ -121,7 +123,7 @@ static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp) ret = get_prioidx(&cs->prioidx); if (ret != 0) { - printk(KERN_WARNING "No space in priority index array\n"); + pr_warn("No space in priority index array\n"); kfree(cs); return ERR_PTR(ret); } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 4d8ce93cd50..cce9e53528b 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -320,7 +320,7 @@ struct pktgen_dev { (see RFC 3260, sec. 4) */ /* MPLS */ - unsigned nr_labels; /* Depth of stack, 0 = no MPLS */ + unsigned int nr_labels; /* Depth of stack, 0 = no MPLS */ __be32 labels[MAX_MPLS_LABELS]; /* VLAN/SVLAN (802.1Q/Q-in-Q) */ @@ -373,10 +373,10 @@ struct pktgen_dev { */ char odevname[32]; struct flow_state *flows; - unsigned cflows; /* Concurrent flows (config) */ - unsigned lflow; /* Flow length (config) */ - unsigned nflows; /* accumulated flows (stats) */ - unsigned curfl; /* current sequenced flow (state)*/ + unsigned int cflows; /* Concurrent flows (config) */ + unsigned int lflow; /* Flow length (config) */ + unsigned int nflows; /* accumulated flows (stats) */ + unsigned int curfl; /* current sequenced flow (state)*/ u16 queue_map_min; u16 queue_map_max; @@ -592,7 +592,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v) pkt_dev->src_mac_count, pkt_dev->dst_mac_count); if (pkt_dev->nr_labels) { - unsigned i; + unsigned int i; seq_printf(seq, " mpls: "); for (i = 0; i < pkt_dev->nr_labels; i++) seq_printf(seq, "%08x%s", ntohl(pkt_dev->labels[i]), @@ -812,7 +812,7 @@ done_str: static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev) { - unsigned n = 0; + unsigned int n = 0; char c; ssize_t i = 0; int len; @@ -891,8 +891,8 @@ static ssize_t pktgen_if_write(struct file *file, if (copy_from_user(tb, user_buffer, copy)) return -EFAULT; tb[copy] = 0; - printk(KERN_DEBUG "pktgen: %s,%lu buffer -:%s:-\n", name, - (unsigned long)count, tb); + pr_debug("%s,%lu buffer -:%s:-\n", + name, (unsigned long)count, tb); } if (!strcmp(name, "min_pkt_size")) { @@ -1261,8 +1261,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->cur_daddr = pkt_dev->daddr_min; } if (debug) - printk(KERN_DEBUG "pktgen: dst_min set to: %s\n", - pkt_dev->dst_min); + pr_debug("dst_min set to: %s\n", pkt_dev->dst_min); i += len; sprintf(pg_result, "OK: dst_min=%s", pkt_dev->dst_min); return count; @@ -1284,8 +1283,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->cur_daddr = pkt_dev->daddr_max; } if (debug) - printk(KERN_DEBUG "pktgen: dst_max set to: %s\n", - pkt_dev->dst_max); + pr_debug("dst_max set to: %s\n", pkt_dev->dst_max); i += len; sprintf(pg_result, "OK: dst_max=%s", pkt_dev->dst_max); return count; @@ -1307,7 +1305,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->cur_in6_daddr = pkt_dev->in6_daddr; if (debug) - printk(KERN_DEBUG "pktgen: dst6 set to: %s\n", buf); + pr_debug("dst6 set to: %s\n", buf); i += len; sprintf(pg_result, "OK: dst6=%s", buf); @@ -1329,7 +1327,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->cur_in6_daddr = pkt_dev->min_in6_daddr; if (debug) - printk(KERN_DEBUG "pktgen: dst6_min set to: %s\n", buf); + pr_debug("dst6_min set to: %s\n", buf); i += len; sprintf(pg_result, "OK: dst6_min=%s", buf); @@ -1350,7 +1348,7 @@ static ssize_t pktgen_if_write(struct file *file, snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->max_in6_daddr); if (debug) - printk(KERN_DEBUG "pktgen: dst6_max set to: %s\n", buf); + pr_debug("dst6_max set to: %s\n", buf); i += len; sprintf(pg_result, "OK: dst6_max=%s", buf); @@ -1373,7 +1371,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->cur_in6_saddr = pkt_dev->in6_saddr; if (debug) - printk(KERN_DEBUG "pktgen: src6 set to: %s\n", buf); + pr_debug("src6 set to: %s\n", buf); i += len; sprintf(pg_result, "OK: src6=%s", buf); @@ -1394,8 +1392,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->cur_saddr = pkt_dev->saddr_min; } if (debug) - printk(KERN_DEBUG "pktgen: src_min set to: %s\n", - pkt_dev->src_min); + pr_debug("src_min set to: %s\n", pkt_dev->src_min); i += len; sprintf(pg_result, "OK: src_min=%s", pkt_dev->src_min); return count; @@ -1415,8 +1412,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->cur_saddr = pkt_dev->saddr_max; } if (debug) - printk(KERN_DEBUG "pktgen: src_max set to: %s\n", - pkt_dev->src_max); + pr_debug("src_max set to: %s\n", pkt_dev->src_max); i += len; sprintf(pg_result, "OK: src_max=%s", pkt_dev->src_max); return count; @@ -1510,7 +1506,7 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "mpls")) { - unsigned n, cnt; + unsigned int n, cnt; len = get_labels(&user_buffer[i], pkt_dev); if (len < 0) @@ -1527,7 +1523,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->svlan_id = 0xffff; if (debug) - printk(KERN_DEBUG "pktgen: VLAN/SVLAN auto turned off\n"); + pr_debug("VLAN/SVLAN auto turned off\n"); } return count; } @@ -1542,10 +1538,10 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->vlan_id = value; /* turn on VLAN */ if (debug) - printk(KERN_DEBUG "pktgen: VLAN turned on\n"); + pr_debug("VLAN turned on\n"); if (debug && pkt_dev->nr_labels) - printk(KERN_DEBUG "pktgen: MPLS auto turned off\n"); + pr_debug("MPLS auto turned off\n"); pkt_dev->nr_labels = 0; /* turn off MPLS */ sprintf(pg_result, "OK: vlan_id=%u", pkt_dev->vlan_id); @@ -1554,7 +1550,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->svlan_id = 0xffff; if (debug) - printk(KERN_DEBUG "pktgen: VLAN/SVLAN turned off\n"); + pr_debug("VLAN/SVLAN turned off\n"); } return count; } @@ -1599,10 +1595,10 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->svlan_id = value; /* turn on SVLAN */ if (debug) - printk(KERN_DEBUG "pktgen: SVLAN turned on\n"); + pr_debug("SVLAN turned on\n"); if (debug && pkt_dev->nr_labels) - printk(KERN_DEBUG "pktgen: MPLS auto turned off\n"); + pr_debug("MPLS auto turned off\n"); pkt_dev->nr_labels = 0; /* turn off MPLS */ sprintf(pg_result, "OK: svlan_id=%u", pkt_dev->svlan_id); @@ -1611,7 +1607,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->svlan_id = 0xffff; if (debug) - printk(KERN_DEBUG "pktgen: VLAN/SVLAN turned off\n"); + pr_debug("VLAN/SVLAN turned off\n"); } return count; } @@ -1779,8 +1775,7 @@ static ssize_t pktgen_thread_write(struct file *file, i += len; if (debug) - printk(KERN_DEBUG "pktgen: t=%s, count=%lu\n", - name, (unsigned long)count); + pr_debug("t=%s, count=%lu\n", name, (unsigned long)count); if (!t) { pr_err("ERROR: No thread\n"); @@ -1931,7 +1926,7 @@ static int pktgen_device_event(struct notifier_block *unused, { struct net_device *dev = ptr; - if (!net_eq(dev_net(dev), &init_net)) + if (!net_eq(dev_net(dev), &init_net) || pktgen_exiting) return NOTIFY_DONE; /* It is OK that we do not hold the group lock right now, @@ -2324,7 +2319,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) } if (pkt_dev->flags & F_MPLS_RND) { - unsigned i; + unsigned int i; for (i = 0; i < pkt_dev->nr_labels; i++) if (pkt_dev->labels[i] & MPLS_STACK_BOTTOM) pkt_dev->labels[i] = MPLS_STACK_BOTTOM | @@ -2550,7 +2545,7 @@ err: static void mpls_push(__be32 *mpls, struct pktgen_dev *pkt_dev) { - unsigned i; + unsigned int i; for (i = 0; i < pkt_dev->nr_labels; i++) *mpls++ = pkt_dev->labels[i] & ~MPLS_STACK_BOTTOM; @@ -2934,8 +2929,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, if (datalen < sizeof(struct pktgen_hdr)) { datalen = sizeof(struct pktgen_hdr); - if (net_ratelimit()) - pr_info("increased datalen to %d\n", datalen); + net_info_ratelimited("increased datalen to %d\n", datalen); } udph->source = htons(pkt_dev->cur_udp_src); @@ -3365,8 +3359,8 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) pkt_dev->errors++; break; default: /* Drivers are not supposed to return other values! */ - if (net_ratelimit()) - pr_info("%s xmit error: %d\n", pkt_dev->odevname, ret); + net_info_ratelimited("%s xmit error: %d\n", + pkt_dev->odevname, ret); pkt_dev->errors++; /* fallthru */ case NETDEV_TX_LOCKED: @@ -3755,12 +3749,18 @@ static void __exit pg_cleanup(void) { struct pktgen_thread *t; struct list_head *q, *n; + LIST_HEAD(list); /* Stop all interfaces & threads */ pktgen_exiting = true; - list_for_each_safe(q, n, &pktgen_threads) { + mutex_lock(&pktgen_thread_lock); + list_splice_init(&pktgen_threads, &list); + mutex_unlock(&pktgen_thread_lock); + + list_for_each_safe(q, n, &list) { t = list_entry(q, struct pktgen_thread, th_list); + list_del(&t->th_list); kthread_stop(t->tsk); kfree(t); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 90430b776ec..21318d15bbc 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -35,7 +35,9 @@ #include <linux/security.h> #include <linux/mutex.h> #include <linux/if_addr.h> +#include <linux/if_bridge.h> #include <linux/pci.h> +#include <linux/etherdevice.h> #include <asm/uaccess.h> @@ -552,7 +554,7 @@ void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data } EXPORT_SYMBOL(__rta_fill); -int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned group, int echo) +int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int group, int echo) { struct sock *rtnl = net->rtnl; int err = 0; @@ -607,7 +609,8 @@ int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) for (i = 0; i < RTAX_MAX; i++) { if (metrics[i]) { valid++; - NLA_PUT_U32(skb, i+1, metrics[i]); + if (nla_put_u32(skb, i+1, metrics[i])) + goto nla_put_failure; } } @@ -782,6 +785,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_MTU */ + nla_total_size(4) /* IFLA_LINK */ + nla_total_size(4) /* IFLA_MASTER */ + + nla_total_size(4) /* IFLA_PROMISCUITY */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ + nla_total_size(ext_filter_mask @@ -807,7 +811,8 @@ static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev) vf_port = nla_nest_start(skb, IFLA_VF_PORT); if (!vf_port) goto nla_put_failure; - NLA_PUT_U32(skb, IFLA_PORT_VF, vf); + if (nla_put_u32(skb, IFLA_PORT_VF, vf)) + goto nla_put_failure; err = dev->netdev_ops->ndo_get_vf_port(dev, vf, skb); if (err == -EMSGSIZE) goto nla_put_failure; @@ -891,25 +896,23 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, ifm->ifi_flags = dev_get_flags(dev); ifm->ifi_change = change; - NLA_PUT_STRING(skb, IFLA_IFNAME, dev->name); - NLA_PUT_U32(skb, IFLA_TXQLEN, dev->tx_queue_len); - NLA_PUT_U8(skb, IFLA_OPERSTATE, - netif_running(dev) ? dev->operstate : IF_OPER_DOWN); - NLA_PUT_U8(skb, IFLA_LINKMODE, dev->link_mode); - NLA_PUT_U32(skb, IFLA_MTU, dev->mtu); - NLA_PUT_U32(skb, IFLA_GROUP, dev->group); - - if (dev->ifindex != dev->iflink) - NLA_PUT_U32(skb, IFLA_LINK, dev->iflink); - - if (dev->master) - NLA_PUT_U32(skb, IFLA_MASTER, dev->master->ifindex); - - if (dev->qdisc) - NLA_PUT_STRING(skb, IFLA_QDISC, dev->qdisc->ops->id); - - if (dev->ifalias) - NLA_PUT_STRING(skb, IFLA_IFALIAS, dev->ifalias); + if (nla_put_string(skb, IFLA_IFNAME, dev->name) || + nla_put_u32(skb, IFLA_TXQLEN, dev->tx_queue_len) || + nla_put_u8(skb, IFLA_OPERSTATE, + netif_running(dev) ? dev->operstate : IF_OPER_DOWN) || + nla_put_u8(skb, IFLA_LINKMODE, dev->link_mode) || + nla_put_u32(skb, IFLA_MTU, dev->mtu) || + nla_put_u32(skb, IFLA_GROUP, dev->group) || + nla_put_u32(skb, IFLA_PROMISCUITY, dev->promiscuity) || + (dev->ifindex != dev->iflink && + nla_put_u32(skb, IFLA_LINK, dev->iflink)) || + (dev->master && + nla_put_u32(skb, IFLA_MASTER, dev->master->ifindex)) || + (dev->qdisc && + nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) || + (dev->ifalias && + nla_put_string(skb, IFLA_IFALIAS, dev->ifalias))) + goto nla_put_failure; if (1) { struct rtnl_link_ifmap map = { @@ -920,12 +923,14 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, .dma = dev->dma, .port = dev->if_port, }; - NLA_PUT(skb, IFLA_MAP, sizeof(map), &map); + if (nla_put(skb, IFLA_MAP, sizeof(map), &map)) + goto nla_put_failure; } if (dev->addr_len) { - NLA_PUT(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr); - NLA_PUT(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast); + if (nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr) || + nla_put(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast)) + goto nla_put_failure; } attr = nla_reserve(skb, IFLA_STATS, @@ -942,8 +947,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, goto nla_put_failure; copy_rtnl_link_stats64(nla_data(attr), stats); - if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF)) - NLA_PUT_U32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent)); + if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF) && + nla_put_u32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent))) + goto nla_put_failure; if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF)) { @@ -986,12 +992,13 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_nest_cancel(skb, vfinfo); goto nla_put_failure; } - NLA_PUT(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac); - NLA_PUT(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan); - NLA_PUT(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate), - &vf_tx_rate); - NLA_PUT(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk), - &vf_spoofchk); + if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) || + nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) || + nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate), + &vf_tx_rate) || + nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk), + &vf_spoofchk)) + goto nla_put_failure; nla_nest_end(skb, vf); } nla_nest_end(skb, vfinfo); @@ -1113,6 +1120,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_PORT_SELF] = { .type = NLA_NESTED }, [IFLA_AF_SPEC] = { .type = NLA_NESTED }, [IFLA_EXT_MASK] = { .type = NLA_U32 }, + [IFLA_PROMISCUITY] = { .type = NLA_U32 }, }; EXPORT_SYMBOL(ifla_policy); @@ -1516,11 +1524,9 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, err = 0; errout: - if (err < 0 && modified && net_ratelimit()) - printk(KERN_WARNING "A link change request failed with " - "some changes committed already. Interface %s may " - "have been left with an inconsistent configuration, " - "please check.\n", dev->name); + if (err < 0 && modified) + net_warn_ratelimited("A link change request failed with some changes committed already. Interface %s may have been left with an inconsistent configuration, please check.\n", + dev->name); if (send_addr_notify) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); @@ -1634,14 +1640,14 @@ struct net_device *rtnl_create_link(struct net *src_net, struct net *net, int err; struct net_device *dev; unsigned int num_queues = 1; - unsigned int real_num_queues = 1; if (ops->get_tx_queues) { - err = ops->get_tx_queues(src_net, tb, &num_queues, - &real_num_queues); - if (err) + err = ops->get_tx_queues(src_net, tb); + if (err < 0) goto err; + num_queues = err; } + err = -ENOMEM; dev = alloc_netdev_mq(ops->priv_size, ifname, ops->setup, num_queues); if (!dev) @@ -1947,7 +1953,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } -void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change) +void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change) { struct net *net = dev_net(dev); struct sk_buff *skb; @@ -1972,6 +1978,267 @@ errout: rtnl_set_sk_err(net, RTNLGRP_LINK, err); } +static int nlmsg_populate_fdb_fill(struct sk_buff *skb, + struct net_device *dev, + u8 *addr, u32 pid, u32 seq, + int type, unsigned int flags) +{ + struct nlmsghdr *nlh; + struct ndmsg *ndm; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), NLM_F_MULTI); + if (!nlh) + return -EMSGSIZE; + + ndm = nlmsg_data(nlh); + ndm->ndm_family = AF_BRIDGE; + ndm->ndm_pad1 = 0; + ndm->ndm_pad2 = 0; + ndm->ndm_flags = flags; + ndm->ndm_type = 0; + ndm->ndm_ifindex = dev->ifindex; + ndm->ndm_state = NUD_PERMANENT; + + if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr)) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static inline size_t rtnl_fdb_nlmsg_size(void) +{ + return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN); +} + +static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, int type) +{ + struct net *net = dev_net(dev); + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(rtnl_fdb_nlmsg_size(), GFP_ATOMIC); + if (!skb) + goto errout; + + err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF); + if (err < 0) { + kfree_skb(skb); + goto errout; + } + + rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); + return; +errout: + rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); +} + +static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +{ + struct net *net = sock_net(skb->sk); + struct net_device *master = NULL; + struct ndmsg *ndm; + struct nlattr *tb[NDA_MAX+1]; + struct net_device *dev; + u8 *addr; + int err; + + err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); + if (err < 0) + return err; + + ndm = nlmsg_data(nlh); + if (ndm->ndm_ifindex == 0) { + pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ifindex\n"); + return -EINVAL; + } + + dev = __dev_get_by_index(net, ndm->ndm_ifindex); + if (dev == NULL) { + pr_info("PF_BRIDGE: RTM_NEWNEIGH with unknown ifindex\n"); + return -ENODEV; + } + + if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) { + pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid address\n"); + return -EINVAL; + } + + addr = nla_data(tb[NDA_LLADDR]); + if (!is_valid_ether_addr(addr)) { + pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ether address\n"); + return -EINVAL; + } + + err = -EOPNOTSUPP; + + /* Support fdb on master device the net/bridge default case */ + if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) && + (dev->priv_flags & IFF_BRIDGE_PORT)) { + master = dev->master; + err = master->netdev_ops->ndo_fdb_add(ndm, dev, addr, + nlh->nlmsg_flags); + if (err) + goto out; + else + ndm->ndm_flags &= ~NTF_MASTER; + } + + /* Embedded bridge, macvlan, and any other device support */ + if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_add) { + err = dev->netdev_ops->ndo_fdb_add(ndm, dev, addr, + nlh->nlmsg_flags); + + if (!err) { + rtnl_fdb_notify(dev, addr, RTM_NEWNEIGH); + ndm->ndm_flags &= ~NTF_SELF; + } + } +out: + return err; +} + +static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +{ + struct net *net = sock_net(skb->sk); + struct ndmsg *ndm; + struct nlattr *llattr; + struct net_device *dev; + int err = -EINVAL; + __u8 *addr; + + if (nlmsg_len(nlh) < sizeof(*ndm)) + return -EINVAL; + + ndm = nlmsg_data(nlh); + if (ndm->ndm_ifindex == 0) { + pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ifindex\n"); + return -EINVAL; + } + + dev = __dev_get_by_index(net, ndm->ndm_ifindex); + if (dev == NULL) { + pr_info("PF_BRIDGE: RTM_DELNEIGH with unknown ifindex\n"); + return -ENODEV; + } + + llattr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_LLADDR); + if (llattr == NULL || nla_len(llattr) != ETH_ALEN) { + pr_info("PF_BRIGDE: RTM_DELNEIGH with invalid address\n"); + return -EINVAL; + } + + addr = nla_data(llattr); + err = -EOPNOTSUPP; + + /* Support fdb on master device the net/bridge default case */ + if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) && + (dev->priv_flags & IFF_BRIDGE_PORT)) { + struct net_device *master = dev->master; + + if (master->netdev_ops->ndo_fdb_del) + err = master->netdev_ops->ndo_fdb_del(ndm, dev, addr); + + if (err) + goto out; + else + ndm->ndm_flags &= ~NTF_MASTER; + } + + /* Embedded bridge, macvlan, and any other device support */ + if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_del) { + err = dev->netdev_ops->ndo_fdb_del(ndm, dev, addr); + + if (!err) { + rtnl_fdb_notify(dev, addr, RTM_DELNEIGH); + ndm->ndm_flags &= ~NTF_SELF; + } + } +out: + return err; +} + +static int nlmsg_populate_fdb(struct sk_buff *skb, + struct netlink_callback *cb, + struct net_device *dev, + int *idx, + struct netdev_hw_addr_list *list) +{ + struct netdev_hw_addr *ha; + int err; + u32 pid, seq; + + pid = NETLINK_CB(cb->skb).pid; + seq = cb->nlh->nlmsg_seq; + + list_for_each_entry(ha, &list->list, list) { + if (*idx < cb->args[0]) + goto skip; + + err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, + pid, seq, 0, NTF_SELF); + if (err < 0) + return err; +skip: + *idx += 1; + } + return 0; +} + +/** + * ndo_dflt_fdb_dump: default netdevice operation to dump an FDB table. + * @nlh: netlink message header + * @dev: netdevice + * + * Default netdevice operation to dump the existing unicast address list. + * Returns zero on success. + */ +int ndo_dflt_fdb_dump(struct sk_buff *skb, + struct netlink_callback *cb, + struct net_device *dev, + int idx) +{ + int err; + + netif_addr_lock_bh(dev); + err = nlmsg_populate_fdb(skb, cb, dev, &idx, &dev->uc); + if (err) + goto out; + nlmsg_populate_fdb(skb, cb, dev, &idx, &dev->mc); +out: + netif_addr_unlock_bh(dev); + return idx; +} +EXPORT_SYMBOL(ndo_dflt_fdb_dump); + +static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + int idx = 0; + struct net *net = sock_net(skb->sk); + struct net_device *dev; + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + if (dev->priv_flags & IFF_BRIDGE_PORT) { + struct net_device *master = dev->master; + const struct net_device_ops *ops = master->netdev_ops; + + if (ops->ndo_fdb_dump) + idx = ops->ndo_fdb_dump(skb, cb, dev, idx); + } + + if (dev->netdev_ops->ndo_fdb_dump) + idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, idx); + } + rcu_read_unlock(); + + cb->args[0] = idx; + return skb->len; +} + /* Protected by RTNL sempahore. */ static struct rtattr **rta_buf; static int rtattr_max; @@ -2042,7 +2309,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) struct rtattr *attr = (void *)nlh + NLMSG_ALIGN(min_len); while (RTA_OK(attr, attrlen)) { - unsigned flavor = attr->rta_type; + unsigned int flavor = attr->rta_type; if (flavor) { if (flavor > rta_max[sz_idx]) return -EINVAL; @@ -2144,5 +2411,9 @@ void __init rtnetlink_init(void) rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, NULL); rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, NULL); + + rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, NULL); + rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, NULL); + rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, rtnl_fdb_dump, NULL); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f223cdc75da..016694d6248 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -36,6 +36,8 @@ * The functions in this file will not compile correctly with gcc 2.4.x */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> @@ -67,10 +69,9 @@ #include <asm/uaccess.h> #include <trace/events/skb.h> +#include <linux/highmem.h> -#include "kmap_skb.h" - -static struct kmem_cache *skbuff_head_cache __read_mostly; +struct kmem_cache *skbuff_head_cache __read_mostly; static struct kmem_cache *skbuff_fclone_cache __read_mostly; static void sock_pipe_buf_release(struct pipe_inode_info *pipe, @@ -119,11 +120,10 @@ static const struct pipe_buf_operations sock_pipe_buf_ops = { */ static void skb_over_panic(struct sk_buff *skb, int sz, void *here) { - printk(KERN_EMERG "skb_over_panic: text:%p len:%d put:%d head:%p " - "data:%p tail:%#lx end:%#lx dev:%s\n", - here, skb->len, sz, skb->head, skb->data, - (unsigned long)skb->tail, (unsigned long)skb->end, - skb->dev ? skb->dev->name : "<NULL>"); + pr_emerg("%s: text:%p len:%d put:%d head:%p data:%p tail:%#lx end:%#lx dev:%s\n", + __func__, here, skb->len, sz, skb->head, skb->data, + (unsigned long)skb->tail, (unsigned long)skb->end, + skb->dev ? skb->dev->name : "<NULL>"); BUG(); } @@ -138,11 +138,10 @@ static void skb_over_panic(struct sk_buff *skb, int sz, void *here) static void skb_under_panic(struct sk_buff *skb, int sz, void *here) { - printk(KERN_EMERG "skb_under_panic: text:%p len:%d put:%d head:%p " - "data:%p tail:%#lx end:%#lx dev:%s\n", - here, skb->len, sz, skb->head, skb->data, - (unsigned long)skb->tail, (unsigned long)skb->end, - skb->dev ? skb->dev->name : "<NULL>"); + pr_emerg("%s: text:%p len:%d put:%d head:%p data:%p tail:%#lx end:%#lx dev:%s\n", + __func__, here, skb->len, sz, skb->head, skb->data, + (unsigned long)skb->tail, (unsigned long)skb->end, + skb->dev ? skb->dev->name : "<NULL>"); BUG(); } @@ -246,6 +245,7 @@ EXPORT_SYMBOL(__alloc_skb); /** * build_skb - build a network buffer * @data: data buffer provided by caller + * @frag_size: size of fragment, or 0 if head was kmalloced * * Allocate a new &sk_buff. Caller provides space holding head and * skb_shared_info. @data must have been allocated by kmalloc() @@ -259,20 +259,21 @@ EXPORT_SYMBOL(__alloc_skb); * before giving packet to stack. * RX rings only contains data buffers, not full skbs. */ -struct sk_buff *build_skb(void *data) +struct sk_buff *build_skb(void *data, unsigned int frag_size) { struct skb_shared_info *shinfo; struct sk_buff *skb; - unsigned int size; + unsigned int size = frag_size ? : ksize(data); skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); if (!skb) return NULL; - size = ksize(data) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); memset(skb, 0, offsetof(struct sk_buff, tail)); skb->truesize = SKB_TRUESIZE(size); + skb->head_frag = frag_size != 0; atomic_set(&skb->users, 1); skb->head = data; skb->data = data; @@ -292,6 +293,46 @@ struct sk_buff *build_skb(void *data) } EXPORT_SYMBOL(build_skb); +struct netdev_alloc_cache { + struct page *page; + unsigned int offset; +}; +static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache); + +/** + * netdev_alloc_frag - allocate a page fragment + * @fragsz: fragment size + * + * Allocates a frag from a page for receive buffer. + * Uses GFP_ATOMIC allocations. + */ +void *netdev_alloc_frag(unsigned int fragsz) +{ + struct netdev_alloc_cache *nc; + void *data = NULL; + unsigned long flags; + + local_irq_save(flags); + nc = &__get_cpu_var(netdev_alloc_cache); + if (unlikely(!nc->page)) { +refill: + nc->page = alloc_page(GFP_ATOMIC | __GFP_COLD); + nc->offset = 0; + } + if (likely(nc->page)) { + if (nc->offset + fragsz > PAGE_SIZE) { + put_page(nc->page); + goto refill; + } + data = page_address(nc->page) + nc->offset; + nc->offset += fragsz; + get_page(nc->page); + } + local_irq_restore(flags); + return data; +} +EXPORT_SYMBOL(netdev_alloc_frag); + /** * __netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on @@ -306,11 +347,23 @@ EXPORT_SYMBOL(build_skb); * %NULL is returned if there is no free memory. */ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, - unsigned int length, gfp_t gfp_mask) + unsigned int length, gfp_t gfp_mask) { - struct sk_buff *skb; + struct sk_buff *skb = NULL; + unsigned int fragsz = SKB_DATA_ALIGN(length + NET_SKB_PAD) + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + if (fragsz <= PAGE_SIZE && !(gfp_mask & __GFP_WAIT)) { + void *data = netdev_alloc_frag(fragsz); - skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE); + if (likely(data)) { + skb = build_skb(data, fragsz); + if (unlikely(!skb)) + put_page(virt_to_head_page(data)); + } + } else { + skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE); + } if (likely(skb)) { skb_reserve(skb, NET_SKB_PAD); skb->dev = dev; @@ -329,28 +382,6 @@ void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, } EXPORT_SYMBOL(skb_add_rx_frag); -/** - * dev_alloc_skb - allocate an skbuff for receiving - * @length: length to allocate - * - * Allocate a new &sk_buff and assign it a usage count of one. The - * buffer has unspecified headroom built in. Users should allocate - * the headroom they think they need without accounting for the - * built in space. The built in space is used for optimisations. - * - * %NULL is returned if there is no free memory. Although this function - * allocates memory it can be called from an interrupt. - */ -struct sk_buff *dev_alloc_skb(unsigned int length) -{ - /* - * There is more code here than it seems: - * __dev_alloc_skb is an inline - */ - return __dev_alloc_skb(length, GFP_ATOMIC); -} -EXPORT_SYMBOL(dev_alloc_skb); - static void skb_drop_list(struct sk_buff **listp) { struct sk_buff *list = *listp; @@ -377,6 +408,14 @@ static void skb_clone_fraglist(struct sk_buff *skb) skb_get(list); } +static void skb_free_head(struct sk_buff *skb) +{ + if (skb->head_frag) + put_page(virt_to_head_page(skb->head)); + else + kfree(skb->head); +} + static void skb_release_data(struct sk_buff *skb) { if (!skb->cloned || @@ -403,7 +442,7 @@ static void skb_release_data(struct sk_buff *skb) if (skb_has_frag_list(skb)) skb_drop_fraglist(skb); - kfree(skb->head); + skb_free_head(skb); } } @@ -645,6 +684,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) C(tail); C(end); C(head); + C(head_frag); C(data); C(truesize); atomic_set(&n->users, 1); @@ -707,10 +747,10 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) } return -ENOMEM; } - vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]); + vaddr = kmap_atomic(skb_frag_page(f)); memcpy(page_address(page), vaddr + f->page_offset, skb_frag_size(f)); - kunmap_skb_frag(vaddr); + kunmap_atomic(vaddr); page->private = (unsigned long)head; head = page; } @@ -819,7 +859,7 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { int headerlen = skb_headroom(skb); - unsigned int size = (skb_end_pointer(skb) - skb->head) + skb->data_len; + unsigned int size = skb_end_offset(skb) + skb->data_len; struct sk_buff *n = alloc_skb(size, gfp_mask); if (!n) @@ -920,9 +960,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, { int i; u8 *data; - int size = nhead + (skb_end_pointer(skb) - skb->head) + ntail; + int size = nhead + skb_end_offset(skb) + ntail; long off; - bool fastpath; BUG_ON(nhead < 0); @@ -931,30 +970,11 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, size = SKB_DATA_ALIGN(size); - /* Check if we can avoid taking references on fragments if we own - * the last reference on skb->head. (see skb_release_data()) - */ - if (!skb->cloned) - fastpath = true; - else { - int delta = skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1; - fastpath = atomic_read(&skb_shinfo(skb)->dataref) == delta; - } - - if (fastpath && - size + sizeof(struct skb_shared_info) <= ksize(skb->head)) { - memmove(skb->head + size, skb_shinfo(skb), - offsetof(struct skb_shared_info, - frags[skb_shinfo(skb)->nr_frags])); - memmove(skb->head + nhead, skb->head, - skb_tail_pointer(skb) - skb->head); - off = nhead; - goto adjust_others; - } - - data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask); + data = kmalloc(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), + gfp_mask); if (!data) goto nodata; + size = SKB_WITH_OVERHEAD(ksize(data)); /* Copy only real data... and, alas, header. This should be * optimized for the cases when header is void. @@ -965,9 +985,12 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, skb_shinfo(skb), offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags])); - if (fastpath) { - kfree(skb->head); - } else { + /* + * if shinfo is shared we must drop the old head gracefully, but if it + * is not we can just drop the old head and let the existing refcount + * be since all we did is relocate the values + */ + if (skb_cloned(skb)) { /* copy this zero copy skb frags */ if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { if (skb_copy_ubufs(skb, gfp_mask)) @@ -980,11 +1003,13 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, skb_clone_fraglist(skb); skb_release_data(skb); + } else { + skb_free_head(skb); } off = (data + nhead) - skb->head; skb->head = data; -adjust_others: + skb->head_frag = 0; skb->data += off; #ifdef NET_SKBUFF_DATA_USES_OFFSET skb->end = size; @@ -1273,7 +1298,7 @@ drop_pages: return -ENOMEM; nfrag->next = frag->next; - kfree_skb(frag); + consume_skb(frag); frag = nfrag; *fragp = frag; } @@ -1485,21 +1510,22 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + skb_frag_t *f = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); - end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); + end = start + skb_frag_size(f); if ((copy = end - offset) > 0) { u8 *vaddr; if (copy > len) copy = len; - vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]); + vaddr = kmap_atomic(skb_frag_page(f)); memcpy(to, - vaddr + skb_shinfo(skb)->frags[i].page_offset+ - offset - start, copy); - kunmap_skb_frag(vaddr); + vaddr + f->page_offset + offset - start, + copy); + kunmap_atomic(vaddr); if ((len -= copy) == 0) return 0; @@ -1545,9 +1571,9 @@ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) put_page(spd->pages[i]); } -static inline struct page *linear_to_page(struct page *page, unsigned int *len, - unsigned int *offset, - struct sk_buff *skb, struct sock *sk) +static struct page *linear_to_page(struct page *page, unsigned int *len, + unsigned int *offset, + struct sk_buff *skb, struct sock *sk) { struct page *p = sk->sk_sndmsg_page; unsigned int off; @@ -1563,6 +1589,9 @@ new_page: } else { unsigned int mlen; + /* If we are the only user of the page, we can reset offset */ + if (page_count(p) == 1) + sk->sk_sndmsg_off = 0; off = sk->sk_sndmsg_off; mlen = PAGE_SIZE - off; if (mlen < 64 && mlen < *len) { @@ -1576,36 +1605,48 @@ new_page: memcpy(page_address(p) + off, page_address(page) + *offset, *len); sk->sk_sndmsg_off += *len; *offset = off; - get_page(p); return p; } +static bool spd_can_coalesce(const struct splice_pipe_desc *spd, + struct page *page, + unsigned int offset) +{ + return spd->nr_pages && + spd->pages[spd->nr_pages - 1] == page && + (spd->partial[spd->nr_pages - 1].offset + + spd->partial[spd->nr_pages - 1].len == offset); +} + /* * Fill page/offset/length into spd, if it can hold more pages. */ -static inline int spd_fill_page(struct splice_pipe_desc *spd, - struct pipe_inode_info *pipe, struct page *page, - unsigned int *len, unsigned int offset, - struct sk_buff *skb, int linear, - struct sock *sk) +static bool spd_fill_page(struct splice_pipe_desc *spd, + struct pipe_inode_info *pipe, struct page *page, + unsigned int *len, unsigned int offset, + struct sk_buff *skb, bool linear, + struct sock *sk) { - if (unlikely(spd->nr_pages == pipe->buffers)) - return 1; + if (unlikely(spd->nr_pages == MAX_SKB_FRAGS)) + return true; if (linear) { page = linear_to_page(page, len, &offset, skb, sk); if (!page) - return 1; - } else - get_page(page); - + return true; + } + if (spd_can_coalesce(spd, page, offset)) { + spd->partial[spd->nr_pages - 1].len += *len; + return false; + } + get_page(page); spd->pages[spd->nr_pages] = page; spd->partial[spd->nr_pages].len = *len; spd->partial[spd->nr_pages].offset = offset; spd->nr_pages++; - return 0; + return false; } static inline void __segment_seek(struct page **page, unsigned int *poff, @@ -1622,20 +1663,20 @@ static inline void __segment_seek(struct page **page, unsigned int *poff, *plen -= off; } -static inline int __splice_segment(struct page *page, unsigned int poff, - unsigned int plen, unsigned int *off, - unsigned int *len, struct sk_buff *skb, - struct splice_pipe_desc *spd, int linear, - struct sock *sk, - struct pipe_inode_info *pipe) +static bool __splice_segment(struct page *page, unsigned int poff, + unsigned int plen, unsigned int *off, + unsigned int *len, struct sk_buff *skb, + struct splice_pipe_desc *spd, bool linear, + struct sock *sk, + struct pipe_inode_info *pipe) { if (!*len) - return 1; + return true; /* skip this segment if already processed */ if (*off >= plen) { *off -= plen; - return 0; + return false; } /* ignore any bits we already processed */ @@ -1651,34 +1692,38 @@ static inline int __splice_segment(struct page *page, unsigned int poff, flen = min_t(unsigned int, flen, PAGE_SIZE - poff); if (spd_fill_page(spd, pipe, page, &flen, poff, skb, linear, sk)) - return 1; + return true; __segment_seek(&page, &poff, &plen, flen); *len -= flen; } while (*len && plen); - return 0; + return false; } /* - * Map linear and fragment data from the skb to spd. It reports failure if the + * Map linear and fragment data from the skb to spd. It reports true if the * pipe is full or if we already spliced the requested length. */ -static int __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, - unsigned int *offset, unsigned int *len, - struct splice_pipe_desc *spd, struct sock *sk) +static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, + unsigned int *offset, unsigned int *len, + struct splice_pipe_desc *spd, struct sock *sk) { int seg; - /* - * map the linear part + /* map the linear part : + * If skb->head_frag is set, this 'linear' part is backed by a + * fragment, and if the head is not shared with any clones then + * we can avoid a copy since we own the head portion of this page. */ if (__splice_segment(virt_to_page(skb->data), (unsigned long) skb->data & (PAGE_SIZE - 1), skb_headlen(skb), - offset, len, skb, spd, 1, sk, pipe)) - return 1; + offset, len, skb, spd, + skb_head_is_locked(skb), + sk, pipe)) + return true; /* * then map the fragments @@ -1688,11 +1733,11 @@ static int __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, if (__splice_segment(skb_frag_page(f), f->page_offset, skb_frag_size(f), - offset, len, skb, spd, 0, sk, pipe)) - return 1; + offset, len, skb, spd, false, sk, pipe)) + return true; } - return 0; + return false; } /* @@ -1705,8 +1750,8 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, struct pipe_inode_info *pipe, unsigned int tlen, unsigned int flags) { - struct partial_page partial[PIPE_DEF_BUFFERS]; - struct page *pages[PIPE_DEF_BUFFERS]; + struct partial_page partial[MAX_SKB_FRAGS]; + struct page *pages[MAX_SKB_FRAGS]; struct splice_pipe_desc spd = { .pages = pages, .partial = partial, @@ -1718,9 +1763,6 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, struct sock *sk = skb->sk; int ret = 0; - if (splice_grow_spd(pipe, &spd)) - return -ENOMEM; - /* * __skb_splice_bits() only fails if the output has no room left, * so no point in going over the frag_list for the error case. @@ -1756,7 +1798,6 @@ done: lock_sock(sk); } - splice_shrink_spd(pipe, &spd); return ret; } @@ -1804,10 +1845,10 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) if (copy > len) copy = len; - vaddr = kmap_skb_frag(frag); + vaddr = kmap_atomic(skb_frag_page(frag)); memcpy(vaddr + frag->page_offset + offset - start, from, copy); - kunmap_skb_frag(vaddr); + kunmap_atomic(vaddr); if ((len -= copy) == 0) return 0; @@ -1867,21 +1908,21 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); - end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); + end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { __wsum csum2; u8 *vaddr; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; if (copy > len) copy = len; - vaddr = kmap_skb_frag(frag); + vaddr = kmap_atomic(skb_frag_page(frag)); csum2 = csum_partial(vaddr + frag->page_offset + offset - start, copy, 0); - kunmap_skb_frag(vaddr); + kunmap_atomic(vaddr); csum = csum_block_add(csum, csum2, pos); if (!(len -= copy)) return csum; @@ -1953,12 +1994,12 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, if (copy > len) copy = len; - vaddr = kmap_skb_frag(frag); + vaddr = kmap_atomic(skb_frag_page(frag)); csum2 = csum_partial_copy_nocheck(vaddr + frag->page_offset + offset - start, to, copy, 0); - kunmap_skb_frag(vaddr); + kunmap_atomic(vaddr); csum = csum_block_add(csum, csum2, pos); if (!(len -= copy)) return csum; @@ -2478,7 +2519,7 @@ next_skb: if (abs_offset < block_limit) { if (!st->frag_data) - st->frag_data = kmap_skb_frag(frag); + st->frag_data = kmap_atomic(skb_frag_page(frag)); *data = (u8 *) st->frag_data + frag->page_offset + (abs_offset - st->stepped_offset); @@ -2487,7 +2528,7 @@ next_skb: } if (st->frag_data) { - kunmap_skb_frag(st->frag_data); + kunmap_atomic(st->frag_data); st->frag_data = NULL; } @@ -2496,7 +2537,7 @@ next_skb: } if (st->frag_data) { - kunmap_skb_frag(st->frag_data); + kunmap_atomic(st->frag_data); st->frag_data = NULL; } @@ -2524,7 +2565,7 @@ EXPORT_SYMBOL(skb_seq_read); void skb_abort_seq_read(struct skb_seq_state *st) { if (st->frag_data) - kunmap_skb_frag(st->frag_data); + kunmap_atomic(st->frag_data); } EXPORT_SYMBOL(skb_abort_seq_read); @@ -2716,14 +2757,13 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) if (unlikely(!nskb)) goto err; - hsize = skb_end_pointer(nskb) - nskb->head; + hsize = skb_end_offset(nskb); if (skb_cow_head(nskb, doffset + headroom)) { kfree_skb(nskb); goto err; } - nskb->truesize += skb_end_pointer(nskb) - nskb->head - - hsize; + nskb->truesize += skb_end_offset(nskb) - hsize; skb_release_head_state(nskb); __skb_push(nskb, doffset); } else { @@ -2841,6 +2881,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) unsigned int len = skb_gro_len(skb); unsigned int offset = skb_gro_offset(skb); unsigned int headlen = skb_headlen(skb); + unsigned int delta_truesize; if (p->len + len >= 65536) return -E2BIG; @@ -2870,11 +2911,41 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) frag->page_offset += offset; skb_frag_size_sub(frag, offset); + /* all fragments truesize : remove (head size + sk_buff) */ + delta_truesize = skb->truesize - + SKB_TRUESIZE(skb_end_offset(skb)); + skb->truesize -= skb->data_len; skb->len -= skb->data_len; skb->data_len = 0; - NAPI_GRO_CB(skb)->free = 1; + NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE; + goto done; + } else if (skb->head_frag) { + int nr_frags = pinfo->nr_frags; + skb_frag_t *frag = pinfo->frags + nr_frags; + struct page *page = virt_to_head_page(skb->head); + unsigned int first_size = headlen - offset; + unsigned int first_offset; + + if (nr_frags + 1 + skbinfo->nr_frags > MAX_SKB_FRAGS) + return -E2BIG; + + first_offset = skb->data - + (unsigned char *)page_address(page) + + offset; + + pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags; + + frag->page.p = page; + frag->page_offset = first_offset; + skb_frag_size_set(frag, first_size); + + memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags); + /* We dont need to clear skbinfo->nr_frags here */ + + delta_truesize = skb->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff)); + NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD; goto done; } else if (skb_gro_len(p) != pinfo->gso_size) return -E2BIG; @@ -2916,7 +2987,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) p = nskb; merge: - p->truesize += skb->truesize - len; + delta_truesize = skb->truesize; if (offset > headlen) { unsigned int eat = offset - headlen; @@ -2936,7 +3007,7 @@ merge: done: NAPI_GRO_CB(p)->count++; p->data_len += len; - p->truesize += len; + p->truesize += delta_truesize; p->len += len; NAPI_GRO_CB(skb)->same_flow = 1; @@ -3161,8 +3232,10 @@ static void sock_rmem_free(struct sk_buff *skb) */ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) { + int len = skb->len; + if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned)sk->sk_rcvbuf) + (unsigned int)sk->sk_rcvbuf) return -ENOMEM; skb_orphan(skb); @@ -3175,7 +3248,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk, len); return 0; } EXPORT_SYMBOL(sock_queue_err_skb); @@ -3256,10 +3329,8 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) { if (unlikely(start > skb_headlen(skb)) || unlikely((int)start + off > skb_headlen(skb) - 2)) { - if (net_ratelimit()) - printk(KERN_WARNING - "bad partial csum: csum=%u/%u len=%u\n", - start, off, skb_headlen(skb)); + net_warn_ratelimited("bad partial csum: csum=%u/%u len=%u\n", + start, off, skb_headlen(skb)); return false; } skb->ip_summed = CHECKSUM_PARTIAL; @@ -3271,8 +3342,93 @@ EXPORT_SYMBOL_GPL(skb_partial_csum_set); void __skb_warn_lro_forwarding(const struct sk_buff *skb) { - if (net_ratelimit()) - pr_warning("%s: received packets cannot be forwarded" - " while LRO is enabled\n", skb->dev->name); + net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n", + skb->dev->name); } EXPORT_SYMBOL(__skb_warn_lro_forwarding); + +void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) +{ + if (head_stolen) + kmem_cache_free(skbuff_head_cache, skb); + else + __kfree_skb(skb); +} +EXPORT_SYMBOL(kfree_skb_partial); + +/** + * skb_try_coalesce - try to merge skb to prior one + * @to: prior buffer + * @from: buffer to add + * @fragstolen: pointer to boolean + * + */ +bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, + bool *fragstolen, int *delta_truesize) +{ + int i, delta, len = from->len; + + *fragstolen = false; + + if (skb_cloned(to)) + return false; + + if (len <= skb_tailroom(to)) { + BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len)); + *delta_truesize = 0; + return true; + } + + if (skb_has_frag_list(to) || skb_has_frag_list(from)) + return false; + + if (skb_headlen(from) != 0) { + struct page *page; + unsigned int offset; + + if (skb_shinfo(to)->nr_frags + + skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) + return false; + + if (skb_head_is_locked(from)) + return false; + + delta = from->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff)); + + page = virt_to_head_page(from->head); + offset = from->data - (unsigned char *)page_address(page); + + skb_fill_page_desc(to, skb_shinfo(to)->nr_frags, + page, offset, skb_headlen(from)); + *fragstolen = true; + } else { + if (skb_shinfo(to)->nr_frags + + skb_shinfo(from)->nr_frags > MAX_SKB_FRAGS) + return false; + + delta = from->truesize - + SKB_TRUESIZE(skb_end_pointer(from) - from->head); + } + + WARN_ON_ONCE(delta < len); + + memcpy(skb_shinfo(to)->frags + skb_shinfo(to)->nr_frags, + skb_shinfo(from)->frags, + skb_shinfo(from)->nr_frags * sizeof(skb_frag_t)); + skb_shinfo(to)->nr_frags += skb_shinfo(from)->nr_frags; + + if (!skb_cloned(from)) + skb_shinfo(from)->nr_frags = 0; + + /* if the skb is cloned this does nothing since we set nr_frags to 0 */ + for (i = 0; i < skb_shinfo(from)->nr_frags; i++) + skb_frag_ref(from, i); + + to->truesize += delta; + to->len += len; + to->data_len += len; + + *delta_truesize = delta; + return true; +} +EXPORT_SYMBOL(skb_try_coalesce); diff --git a/net/core/sock.c b/net/core/sock.c index 878f7447cf6..f372d9bf497 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -89,6 +89,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> @@ -113,6 +115,7 @@ #include <linux/user_namespace.h> #include <linux/static_key.h> #include <linux/memcontrol.h> +#include <linux/prefetch.h> #include <asm/uaccess.h> @@ -258,7 +261,9 @@ static struct lock_class_key af_callback_keys[AF_MAX]; /* Run time adjustable parameters. */ __u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX; +EXPORT_SYMBOL(sysctl_wmem_max); __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; +EXPORT_SYMBOL(sysctl_rmem_max); __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; @@ -294,9 +299,8 @@ static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) *timeo_p = 0; if (warned < 10 && net_ratelimit()) { warned++; - printk(KERN_INFO "sock_set_timeout: `%s' (pid %d) " - "tries to set negative timeout\n", - current->comm, task_pid_nr(current)); + pr_info("%s: `%s' (pid %d) tries to set negative timeout\n", + __func__, current->comm, task_pid_nr(current)); } return 0; } @@ -314,8 +318,8 @@ static void sock_warn_obsolete_bsdism(const char *name) static char warncomm[TASK_COMM_LEN]; if (strcmp(warncomm, current->comm) && warned < 5) { strcpy(warncomm, current->comm); - printk(KERN_WARNING "process `%s' is using obsolete " - "%s SO_BSDCOMPAT\n", warncomm, name); + pr_warn("process `%s' is using obsolete %s SO_BSDCOMPAT\n", + warncomm, name); warned++; } } @@ -389,7 +393,7 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) skb->dev = NULL; - if (sk_rcvqueues_full(sk, skb)) { + if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) { atomic_inc(&sk->sk_drops); goto discard_and_relse; } @@ -406,7 +410,7 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) rc = sk_backlog_rcv(sk, skb); mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_); - } else if (sk_add_backlog(sk, skb)) { + } else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) { bh_unlock_sock(sk); atomic_inc(&sk->sk_drops); goto discard_and_relse; @@ -561,7 +565,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname, sock_valbool_flag(sk, SOCK_DBG, valbool); break; case SO_REUSEADDR: - sk->sk_reuse = valbool; + sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); break; case SO_TYPE: case SO_PROTOCOL: @@ -577,23 +581,15 @@ int sock_setsockopt(struct socket *sock, int level, int optname, break; case SO_SNDBUF: /* Don't error on this BSD doesn't and if you think - about it this is right. Otherwise apps have to - play 'guess the biggest size' games. RCVBUF/SNDBUF - are treated in BSD as hints */ - - if (val > sysctl_wmem_max) - val = sysctl_wmem_max; + * about it this is right. Otherwise apps have to + * play 'guess the biggest size' games. RCVBUF/SNDBUF + * are treated in BSD as hints + */ + val = min_t(u32, val, sysctl_wmem_max); set_sndbuf: sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - if ((val * 2) < SOCK_MIN_SNDBUF) - sk->sk_sndbuf = SOCK_MIN_SNDBUF; - else - sk->sk_sndbuf = val * 2; - - /* - * Wake up sending tasks if we - * upped the value. - */ + sk->sk_sndbuf = max_t(u32, val * 2, SOCK_MIN_SNDBUF); + /* Wake up sending tasks if we upped the value. */ sk->sk_write_space(sk); break; @@ -606,12 +602,11 @@ set_sndbuf: case SO_RCVBUF: /* Don't error on this BSD doesn't and if you think - about it this is right. Otherwise apps have to - play 'guess the biggest size' games. RCVBUF/SNDBUF - are treated in BSD as hints */ - - if (val > sysctl_rmem_max) - val = sysctl_rmem_max; + * about it this is right. Otherwise apps have to + * play 'guess the biggest size' games. RCVBUF/SNDBUF + * are treated in BSD as hints + */ + val = min_t(u32, val, sysctl_rmem_max); set_rcvbuf: sk->sk_userlocks |= SOCK_RCVBUF_LOCK; /* @@ -629,10 +624,7 @@ set_rcvbuf: * returning the value we actually used in getsockopt * is the most desirable behavior. */ - if ((val * 2) < SOCK_MIN_RCVBUF) - sk->sk_rcvbuf = SOCK_MIN_RCVBUF; - else - sk->sk_rcvbuf = val * 2; + sk->sk_rcvbuf = max_t(u32, val * 2, SOCK_MIN_RCVBUF); break; case SO_RCVBUFFORCE: @@ -858,7 +850,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_BROADCAST: - v.val = !!sock_flag(sk, SOCK_BROADCAST); + v.val = sock_flag(sk, SOCK_BROADCAST); break; case SO_SNDBUF: @@ -874,7 +866,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_KEEPALIVE: - v.val = !!sock_flag(sk, SOCK_KEEPOPEN); + v.val = sock_flag(sk, SOCK_KEEPOPEN); break; case SO_TYPE: @@ -896,7 +888,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_OOBINLINE: - v.val = !!sock_flag(sk, SOCK_URGINLINE); + v.val = sock_flag(sk, SOCK_URGINLINE); break; case SO_NO_CHECK: @@ -909,7 +901,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, case SO_LINGER: lv = sizeof(v.ling); - v.ling.l_onoff = !!sock_flag(sk, SOCK_LINGER); + v.ling.l_onoff = sock_flag(sk, SOCK_LINGER); v.ling.l_linger = sk->sk_lingertime / HZ; break; @@ -975,7 +967,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_PASSCRED: - v.val = test_bit(SOCK_PASSCRED, &sock->flags) ? 1 : 0; + v.val = !!test_bit(SOCK_PASSCRED, &sock->flags); break; case SO_PEERCRED: @@ -1010,7 +1002,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_PASSSEC: - v.val = test_bit(SOCK_PASSSEC, &sock->flags) ? 1 : 0; + v.val = !!test_bit(SOCK_PASSSEC, &sock->flags); break; case SO_PEERSEC: @@ -1021,11 +1013,11 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_RXQ_OVFL: - v.val = !!sock_flag(sk, SOCK_RXQ_OVFL); + v.val = sock_flag(sk, SOCK_RXQ_OVFL); break; case SO_WIFI_STATUS: - v.val = !!sock_flag(sk, SOCK_WIFI_STATUS); + v.val = sock_flag(sk, SOCK_WIFI_STATUS); break; case SO_PEEK_OFF: @@ -1035,7 +1027,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_peek_off; break; case SO_NOFCS: - v.val = !!sock_flag(sk, SOCK_NOFCS); + v.val = sock_flag(sk, SOCK_NOFCS); break; default: return -ENOPROTOOPT; @@ -1247,8 +1239,8 @@ static void __sk_free(struct sock *sk) sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP); if (atomic_read(&sk->sk_omem_alloc)) - printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n", - __func__, atomic_read(&sk->sk_omem_alloc)); + pr_debug("%s: optmem leakage (%d bytes) detected\n", + __func__, atomic_read(&sk->sk_omem_alloc)); if (sk->sk_peer_cred) put_cred(sk->sk_peer_cred); @@ -1534,7 +1526,7 @@ struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force, */ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) { - if ((unsigned)size <= sysctl_optmem_max && + if ((unsigned int)size <= sysctl_optmem_max && atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) { void *mem; /* First do the add, to avoid the race if kmalloc @@ -1712,6 +1704,7 @@ static void __release_sock(struct sock *sk) do { struct sk_buff *next = skb->next; + prefetch(next); WARN_ON_ONCE(skb_dst_is_noref(skb)); skb->next = NULL; sk_backlog_rcv(sk, skb); @@ -2432,7 +2425,7 @@ static void assign_proto_idx(struct proto *prot) prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR); if (unlikely(prot->inuse_idx == PROTO_INUSE_NR - 1)) { - printk(KERN_ERR "PROTO_INUSE_NR exhausted\n"); + pr_err("PROTO_INUSE_NR exhausted\n"); return; } @@ -2462,8 +2455,8 @@ int proto_register(struct proto *prot, int alloc_slab) NULL); if (prot->slab == NULL) { - printk(KERN_CRIT "%s: Can't create sock SLAB cache!\n", - prot->name); + pr_crit("%s: Can't create sock SLAB cache!\n", + prot->name); goto out; } @@ -2477,8 +2470,8 @@ int proto_register(struct proto *prot, int alloc_slab) SLAB_HWCACHE_ALIGN, NULL); if (prot->rsk_prot->slab == NULL) { - printk(KERN_CRIT "%s: Can't create request sock SLAB cache!\n", - prot->name); + pr_crit("%s: Can't create request sock SLAB cache!\n", + prot->name); goto out_free_request_sock_slab_name; } } @@ -2576,7 +2569,7 @@ static char proto_method_implemented(const void *method) } static long sock_prot_memory_allocated(struct proto *proto) { - return proto->memory_allocated != NULL ? proto_memory_allocated(proto): -1L; + return proto->memory_allocated != NULL ? proto_memory_allocated(proto) : -1L; } static char *sock_prot_memory_pressure(struct proto *proto) diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index b9868e1fd62..5fd146720f3 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -10,7 +10,7 @@ #include <linux/inet_diag.h> #include <linux/sock_diag.h> -static struct sock_diag_handler *sock_diag_handlers[AF_MAX]; +static const struct sock_diag_handler *sock_diag_handlers[AF_MAX]; static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh); static DEFINE_MUTEX(sock_diag_table_mutex); @@ -70,7 +70,7 @@ void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlms } EXPORT_SYMBOL_GPL(sock_diag_unregister_inet_compat); -int sock_diag_register(struct sock_diag_handler *hndl) +int sock_diag_register(const struct sock_diag_handler *hndl) { int err = 0; @@ -88,7 +88,7 @@ int sock_diag_register(struct sock_diag_handler *hndl) } EXPORT_SYMBOL_GPL(sock_diag_register); -void sock_diag_unregister(struct sock_diag_handler *hnld) +void sock_diag_unregister(const struct sock_diag_handler *hnld) { int family = hnld->family; @@ -102,7 +102,7 @@ void sock_diag_unregister(struct sock_diag_handler *hnld) } EXPORT_SYMBOL_GPL(sock_diag_unregister); -static inline struct sock_diag_handler *sock_diag_lock_handler(int family) +static const inline struct sock_diag_handler *sock_diag_lock_handler(int family) { if (sock_diag_handlers[family] == NULL) request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, @@ -112,7 +112,7 @@ static inline struct sock_diag_handler *sock_diag_lock_handler(int family) return sock_diag_handlers[family]; } -static inline void sock_diag_unlock_handler(struct sock_diag_handler *h) +static inline void sock_diag_unlock_handler(const struct sock_diag_handler *h) { mutex_unlock(&sock_diag_table_mutex); } @@ -121,7 +121,7 @@ static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { int err; struct sock_diag_req *req = NLMSG_DATA(nlh); - struct sock_diag_handler *hndl; + const struct sock_diag_handler *hndl; if (nlmsg_len(nlh) < sizeof(*req)) return -EINVAL; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 0c285087425..a7c36845b12 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -14,6 +14,7 @@ #include <linux/vmalloc.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/kmemleak.h> #include <net/ip.h> #include <net/sock.h> @@ -202,12 +203,6 @@ static struct ctl_table netns_core_table[] = { { } }; -__net_initdata struct ctl_path net_core_path[] = { - { .procname = "net", }, - { .procname = "core", }, - { }, -}; - static __net_init int sysctl_core_net_init(struct net *net) { struct ctl_table *tbl; @@ -223,8 +218,7 @@ static __net_init int sysctl_core_net_init(struct net *net) tbl[0].data = &net->core.sysctl_somaxconn; } - net->core.sysctl_hdr = register_net_sysctl_table(net, - net_core_path, tbl); + net->core.sysctl_hdr = register_net_sysctl(net, "net/core", tbl); if (net->core.sysctl_hdr == NULL) goto err_reg; @@ -254,10 +248,7 @@ static __net_initdata struct pernet_operations sysctl_core_ops = { static __init int sysctl_core_init(void) { - static struct ctl_table empty[1]; - - register_sysctl_paths(net_core_path, empty); - register_net_sysctl_rotable(net_core_path, net_core_table); + register_net_sysctl(&init_net, "net/core", net_core_table); return register_pernet_subsys(&sysctl_core_ops); } diff --git a/net/core/utils.c b/net/core/utils.c index dc3c3faff2f..39895a65e54 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -58,14 +58,11 @@ __be32 in_aton(const char *str) int i; l = 0; - for (i = 0; i < 4; i++) - { + for (i = 0; i < 4; i++) { l <<= 8; - if (*str != '\0') - { + if (*str != '\0') { val = 0; - while (*str != '\0' && *str != '.' && *str != '\n') - { + while (*str != '\0' && *str != '.' && *str != '\n') { val *= 10; val += *str - '0'; str++; diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index d86053002c1..656c7c75b19 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -178,6 +178,7 @@ static const struct nla_policy dcbnl_ieee_policy[DCB_ATTR_IEEE_MAX + 1] = { [DCB_ATTR_IEEE_ETS] = {.len = sizeof(struct ieee_ets)}, [DCB_ATTR_IEEE_PFC] = {.len = sizeof(struct ieee_pfc)}, [DCB_ATTR_IEEE_APP_TABLE] = {.type = NLA_NESTED}, + [DCB_ATTR_IEEE_MAXRATE] = {.len = sizeof(struct ieee_maxrate)}, }; static const struct nla_policy dcbnl_ieee_app[DCB_ATTR_IEEE_APP_MAX + 1] = { @@ -703,6 +704,7 @@ static int dcbnl_setapp(struct net_device *netdev, struct nlattr **tb, ret = dcbnl_reply(err, RTM_SETDCB, DCB_CMD_SAPP, DCB_ATTR_APP, pid, seq, flags); + dcbnl_cee_notify(netdev, RTM_SETDCB, DCB_CMD_SAPP, seq, 0); out: return ret; } @@ -935,6 +937,7 @@ static int dcbnl_setall(struct net_device *netdev, struct nlattr **tb, ret = dcbnl_reply(netdev->dcbnl_ops->setall(netdev), RTM_SETDCB, DCB_CMD_SET_ALL, DCB_ATTR_SET_ALL, pid, seq, flags); + dcbnl_cee_notify(netdev, RTM_SETDCB, DCB_CMD_SET_ALL, seq, 0); return ret; } @@ -1205,13 +1208,15 @@ static int dcbnl_build_peer_app(struct net_device *netdev, struct sk_buff* skb, if (!app) goto nla_put_failure; - if (app_info_type) - NLA_PUT(skb, app_info_type, sizeof(info), &info); - - for (i = 0; i < app_count; i++) - NLA_PUT(skb, app_entry_type, sizeof(struct dcb_app), - &table[i]); + if (app_info_type && + nla_put(skb, app_info_type, sizeof(info), &info)) + goto nla_put_failure; + for (i = 0; i < app_count; i++) { + if (nla_put(skb, app_entry_type, sizeof(struct dcb_app), + &table[i])) + goto nla_put_failure; + } nla_nest_end(skb, app); } err = 0; @@ -1230,8 +1235,8 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) int dcbx; int err = -EMSGSIZE; - NLA_PUT_STRING(skb, DCB_ATTR_IFNAME, netdev->name); - + if (nla_put_string(skb, DCB_ATTR_IFNAME, netdev->name)) + goto nla_put_failure; ieee = nla_nest_start(skb, DCB_ATTR_IEEE); if (!ieee) goto nla_put_failure; @@ -1239,15 +1244,28 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) if (ops->ieee_getets) { struct ieee_ets ets; err = ops->ieee_getets(netdev, &ets); - if (!err) - NLA_PUT(skb, DCB_ATTR_IEEE_ETS, sizeof(ets), &ets); + if (!err && + nla_put(skb, DCB_ATTR_IEEE_ETS, sizeof(ets), &ets)) + goto nla_put_failure; + } + + if (ops->ieee_getmaxrate) { + struct ieee_maxrate maxrate; + err = ops->ieee_getmaxrate(netdev, &maxrate); + if (!err) { + err = nla_put(skb, DCB_ATTR_IEEE_MAXRATE, + sizeof(maxrate), &maxrate); + if (err) + goto nla_put_failure; + } } if (ops->ieee_getpfc) { struct ieee_pfc pfc; err = ops->ieee_getpfc(netdev, &pfc); - if (!err) - NLA_PUT(skb, DCB_ATTR_IEEE_PFC, sizeof(pfc), &pfc); + if (!err && + nla_put(skb, DCB_ATTR_IEEE_PFC, sizeof(pfc), &pfc)) + goto nla_put_failure; } app = nla_nest_start(skb, DCB_ATTR_IEEE_APP_TABLE); @@ -1278,15 +1296,17 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) if (ops->ieee_peer_getets) { struct ieee_ets ets; err = ops->ieee_peer_getets(netdev, &ets); - if (!err) - NLA_PUT(skb, DCB_ATTR_IEEE_PEER_ETS, sizeof(ets), &ets); + if (!err && + nla_put(skb, DCB_ATTR_IEEE_PEER_ETS, sizeof(ets), &ets)) + goto nla_put_failure; } if (ops->ieee_peer_getpfc) { struct ieee_pfc pfc; err = ops->ieee_peer_getpfc(netdev, &pfc); - if (!err) - NLA_PUT(skb, DCB_ATTR_IEEE_PEER_PFC, sizeof(pfc), &pfc); + if (!err && + nla_put(skb, DCB_ATTR_IEEE_PEER_PFC, sizeof(pfc), &pfc)) + goto nla_put_failure; } if (ops->peer_getappinfo && ops->peer_getapptable) { @@ -1340,10 +1360,11 @@ static int dcbnl_cee_pg_fill(struct sk_buff *skb, struct net_device *dev, ops->getpgtccfgtx(dev, i - DCB_PG_ATTR_TC_0, &prio, &pgid, &tc_pct, &up_map); - NLA_PUT_U8(skb, DCB_TC_ATTR_PARAM_PGID, pgid); - NLA_PUT_U8(skb, DCB_TC_ATTR_PARAM_UP_MAPPING, up_map); - NLA_PUT_U8(skb, DCB_TC_ATTR_PARAM_STRICT_PRIO, prio); - NLA_PUT_U8(skb, DCB_TC_ATTR_PARAM_BW_PCT, tc_pct); + if (nla_put_u8(skb, DCB_TC_ATTR_PARAM_PGID, pgid) || + nla_put_u8(skb, DCB_TC_ATTR_PARAM_UP_MAPPING, up_map) || + nla_put_u8(skb, DCB_TC_ATTR_PARAM_STRICT_PRIO, prio) || + nla_put_u8(skb, DCB_TC_ATTR_PARAM_BW_PCT, tc_pct)) + goto nla_put_failure; nla_nest_end(skb, tc_nest); } @@ -1356,7 +1377,8 @@ static int dcbnl_cee_pg_fill(struct sk_buff *skb, struct net_device *dev, else ops->getpgbwgcfgtx(dev, i - DCB_PG_ATTR_BW_ID_0, &tc_pct); - NLA_PUT_U8(skb, i, tc_pct); + if (nla_put_u8(skb, i, tc_pct)) + goto nla_put_failure; } nla_nest_end(skb, pg); return 0; @@ -1373,8 +1395,8 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) int dcbx, i, err = -EMSGSIZE; u8 value; - NLA_PUT_STRING(skb, DCB_ATTR_IFNAME, netdev->name); - + if (nla_put_string(skb, DCB_ATTR_IFNAME, netdev->name)) + goto nla_put_failure; cee = nla_nest_start(skb, DCB_ATTR_CEE); if (!cee) goto nla_put_failure; @@ -1401,7 +1423,8 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) for (i = DCB_PFC_UP_ATTR_0; i <= DCB_PFC_UP_ATTR_7; i++) { ops->getpfccfg(netdev, i - DCB_PFC_UP_ATTR_0, &value); - NLA_PUT_U8(skb, i, value); + if (nla_put_u8(skb, i, value)) + goto nla_put_failure; } nla_nest_end(skb, pfc_nest); } @@ -1454,8 +1477,9 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) for (i = DCB_FEATCFG_ATTR_ALL + 1; i <= DCB_FEATCFG_ATTR_MAX; i++) - if (!ops->getfeatcfg(netdev, i, &value)) - NLA_PUT_U8(skb, i, value); + if (!ops->getfeatcfg(netdev, i, &value) && + nla_put_u8(skb, i, value)) + goto nla_put_failure; nla_nest_end(skb, feat); } @@ -1464,15 +1488,17 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) if (ops->cee_peer_getpg) { struct cee_pg pg; err = ops->cee_peer_getpg(netdev, &pg); - if (!err) - NLA_PUT(skb, DCB_ATTR_CEE_PEER_PG, sizeof(pg), &pg); + if (!err && + nla_put(skb, DCB_ATTR_CEE_PEER_PG, sizeof(pg), &pg)) + goto nla_put_failure; } if (ops->cee_peer_getpfc) { struct cee_pfc pfc; err = ops->cee_peer_getpfc(netdev, &pfc); - if (!err) - NLA_PUT(skb, DCB_ATTR_CEE_PEER_PFC, sizeof(pfc), &pfc); + if (!err && + nla_put(skb, DCB_ATTR_CEE_PEER_PFC, sizeof(pfc), &pfc)) + goto nla_put_failure; } if (ops->peer_getappinfo && ops->peer_getapptable) { @@ -1589,6 +1615,14 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlattr **tb, goto err; } + if (ieee[DCB_ATTR_IEEE_MAXRATE] && ops->ieee_setmaxrate) { + struct ieee_maxrate *maxrate = + nla_data(ieee[DCB_ATTR_IEEE_MAXRATE]); + err = ops->ieee_setmaxrate(netdev, maxrate); + if (err) + goto err; + } + if (ieee[DCB_ATTR_IEEE_PFC] && ops->ieee_setpfc) { struct ieee_pfc *pfc = nla_data(ieee[DCB_ATTR_IEEE_PFC]); err = ops->ieee_setpfc(netdev, pfc); diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index 70bfaf2d196..8c67bedf85b 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -100,7 +100,7 @@ static void ccid3_update_send_interval(struct ccid3_hc_tx_sock *hc) DCCP_BUG_ON(hc->tx_t_ipi == 0); ccid3_pr_debug("t_ipi=%u, s=%u, X=%u\n", hc->tx_t_ipi, - hc->tx_s, (unsigned)(hc->tx_x >> 6)); + hc->tx_s, (unsigned int)(hc->tx_x >> 6)); } static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hc, ktime_t now) @@ -153,9 +153,9 @@ static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp) if (hc->tx_x != old_x) { ccid3_pr_debug("X_prev=%u, X_now=%u, X_calc=%u, " - "X_recv=%u\n", (unsigned)(old_x >> 6), - (unsigned)(hc->tx_x >> 6), hc->tx_x_calc, - (unsigned)(hc->tx_x_recv >> 6)); + "X_recv=%u\n", (unsigned int)(old_x >> 6), + (unsigned int)(hc->tx_x >> 6), hc->tx_x_calc, + (unsigned int)(hc->tx_x_recv >> 6)); ccid3_update_send_interval(hc); } @@ -425,8 +425,8 @@ done_computing_x: "p=%u, X_calc=%u, X_recv=%u, X=%u\n", dccp_role(sk), sk, hc->tx_rtt, r_sample, hc->tx_s, hc->tx_p, hc->tx_x_calc, - (unsigned)(hc->tx_x_recv >> 6), - (unsigned)(hc->tx_x >> 6)); + (unsigned int)(hc->tx_x_recv >> 6), + (unsigned int)(hc->tx_x >> 6)); /* unschedule no feedback timer */ sk_stop_timer(sk, &hc->tx_no_feedback_timer); diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 29d6bb629a6..9040be049d8 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -75,7 +75,7 @@ extern void dccp_time_wait(struct sock *sk, int state, int timeo); * state, about 60 seconds */ /* RFC 1122, 4.2.3.1 initial RTO value */ -#define DCCP_TIMEOUT_INIT ((unsigned)(3 * HZ)) +#define DCCP_TIMEOUT_INIT ((unsigned int)(3 * HZ)) /* * The maximum back-off value for retransmissions. This is needed for @@ -84,7 +84,7 @@ extern void dccp_time_wait(struct sock *sk, int state, int timeo); * - feature-negotiation retransmission (sec. 6.6.3), * - Acks in client-PARTOPEN state (sec. 8.1.5). */ -#define DCCP_RTO_MAX ((unsigned)(64 * HZ)) +#define DCCP_RTO_MAX ((unsigned int)(64 * HZ)) /* * RTT sampling: sanity bounds and fallback RTT value from RFC 4340, section 3.4 @@ -287,9 +287,9 @@ extern struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, extern int dccp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); extern int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, - struct dccp_hdr *dh, unsigned len); + struct dccp_hdr *dh, unsigned int len); extern int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, - const struct dccp_hdr *dh, const unsigned len); + const struct dccp_hdr *dh, const unsigned int len); extern int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized); extern void dccp_destroy_sock(struct sock *sk); diff --git a/net/dccp/input.c b/net/dccp/input.c index 51d5fe5fffb..bc93a333931 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -285,7 +285,7 @@ static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb) } static int __dccp_rcv_established(struct sock *sk, struct sk_buff *skb, - const struct dccp_hdr *dh, const unsigned len) + const struct dccp_hdr *dh, const unsigned int len) { struct dccp_sock *dp = dccp_sk(sk); @@ -366,7 +366,7 @@ discard: } int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, - const struct dccp_hdr *dh, const unsigned len) + const struct dccp_hdr *dh, const unsigned int len) { if (dccp_check_seqno(sk, skb)) goto discard; @@ -388,7 +388,7 @@ EXPORT_SYMBOL_GPL(dccp_rcv_established); static int dccp_rcv_request_sent_state_process(struct sock *sk, struct sk_buff *skb, const struct dccp_hdr *dh, - const unsigned len) + const unsigned int len) { /* * Step 4: Prepare sequence numbers in REQUEST @@ -521,7 +521,7 @@ unable_to_proceed: static int dccp_rcv_respond_partopen_state_process(struct sock *sk, struct sk_buff *skb, const struct dccp_hdr *dh, - const unsigned len) + const unsigned int len) { struct dccp_sock *dp = dccp_sk(sk); u32 sample = dp->dccps_options_received.dccpor_timestamp_echo; @@ -572,7 +572,7 @@ static int dccp_rcv_respond_partopen_state_process(struct sock *sk, } int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, - struct dccp_hdr *dh, unsigned len) + struct dccp_hdr *dh, unsigned int len) { struct dccp_sock *dp = dccp_sk(sk); struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index caf6e1734b6..07f5579ca75 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -574,6 +574,11 @@ static void dccp_v4_reqsk_destructor(struct request_sock *req) kfree(inet_rsk(req)->opt); } +void dccp_syn_ack_timeout(struct sock *sk, struct request_sock *req) +{ +} +EXPORT_SYMBOL(dccp_syn_ack_timeout); + static struct request_sock_ops dccp_request_sock_ops __read_mostly = { .family = PF_INET, .obj_size = sizeof(struct dccp_request_sock), @@ -581,6 +586,7 @@ static struct request_sock_ops dccp_request_sock_ops __read_mostly = { .send_ack = dccp_reqsk_send_ack, .destructor = dccp_v4_reqsk_destructor, .send_reset = dccp_v4_ctl_send_reset, + .syn_ack_timeout = dccp_syn_ack_timeout, }; int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 4dc588f520e..fa9512d86f3 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -343,6 +343,7 @@ static struct request_sock_ops dccp6_request_sock_ops = { .send_ack = dccp_reqsk_send_ack, .destructor = dccp_v6_reqsk_destructor, .send_reset = dccp_v6_ctl_send_reset, + .syn_ack_timeout = dccp_syn_ack_timeout, }; static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) @@ -579,7 +580,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, newnp->pktoptions = NULL; if (ireq6->pktopts != NULL) { newnp->pktoptions = skb_clone(ireq6->pktopts, GFP_ATOMIC); - kfree_skb(ireq6->pktopts); + consume_skb(ireq6->pktopts); ireq6->pktopts = NULL; if (newnp->pktoptions) skb_set_owner_r(newnp->pktoptions, newsk); diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 7065c0ae1e7..6c7c78b8394 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -848,7 +848,7 @@ int dccp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, default: dccp_pr_debug("packet_type=%s\n", dccp_packet_name(dh->dccph_type)); - sk_eat_skb(sk, skb, 0); + sk_eat_skb(sk, skb, false); } verify_sock_status: if (sock_flag(sk, SOCK_DONE)) { @@ -905,7 +905,7 @@ verify_sock_status: len = skb->len; found_fin_ok: if (!(flags & MSG_PEEK)) - sk_eat_skb(sk, skb, 0); + sk_eat_skb(sk, skb, false); break; } while (1); out: diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c index 42348824ee3..607ab71b5a0 100644 --- a/net/dccp/sysctl.c +++ b/net/dccp/sysctl.c @@ -98,18 +98,11 @@ static struct ctl_table dccp_default_table[] = { { } }; -static struct ctl_path dccp_path[] = { - { .procname = "net", }, - { .procname = "dccp", }, - { .procname = "default", }, - { } -}; - static struct ctl_table_header *dccp_table_header; int __init dccp_sysctl_init(void) { - dccp_table_header = register_sysctl_paths(dccp_path, + dccp_table_header = register_net_sysctl(&init_net, "net/dccp/default", dccp_default_table); return dccp_table_header != NULL ? 0 : -ENOMEM; @@ -118,7 +111,7 @@ int __init dccp_sysctl_init(void) void dccp_sysctl_exit(void) { if (dccp_table_header != NULL) { - unregister_sysctl_table(dccp_table_header); + unregister_net_sysctl_table(dccp_table_header); dccp_table_header = NULL; } } diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 4136987d94d..2ba1a2814c2 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -250,7 +250,7 @@ static void dn_unhash_sock_bh(struct sock *sk) static struct hlist_head *listen_hash(struct sockaddr_dn *addr) { int i; - unsigned hash = addr->sdn_objnum; + unsigned int hash = addr->sdn_objnum; if (hash == 0) { hash = addr->sdn_objnamel; @@ -1844,9 +1844,9 @@ static inline int dn_queue_too_long(struct dn_scp *scp, struct sk_buff_head *que * inclusion (or not) of the two 16 bit acknowledgement fields so it doesn't * make much practical difference. */ -unsigned dn_mss_from_pmtu(struct net_device *dev, int mtu) +unsigned int dn_mss_from_pmtu(struct net_device *dev, int mtu) { - unsigned mss = 230 - DN_MAX_NSP_DATA_HEADER; + unsigned int mss = 230 - DN_MAX_NSP_DATA_HEADER; if (dev) { struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); mtu -= LL_RESERVED_SPACE(dev); diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index c00e3077988..f3924ab1e01 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -209,15 +209,7 @@ static void dn_dev_sysctl_register(struct net_device *dev, struct dn_dev_parms * struct dn_dev_sysctl_table *t; int i; -#define DN_CTL_PATH_DEV 3 - - struct ctl_path dn_ctl_path[] = { - { .procname = "net", }, - { .procname = "decnet", }, - { .procname = "conf", }, - { /* to be set */ }, - { }, - }; + char path[sizeof("net/decnet/conf/") + IFNAMSIZ]; t = kmemdup(&dn_dev_sysctl, sizeof(*t), GFP_KERNEL); if (t == NULL) @@ -228,15 +220,12 @@ static void dn_dev_sysctl_register(struct net_device *dev, struct dn_dev_parms * t->dn_dev_vars[i].data = ((char *)parms) + offset; } - if (dev) { - dn_ctl_path[DN_CTL_PATH_DEV].procname = dev->name; - } else { - dn_ctl_path[DN_CTL_PATH_DEV].procname = parms->name; - } + snprintf(path, sizeof(path), "net/decnet/conf/%s", + dev? dev->name : parms->name); t->dn_dev_vars[0].extra1 = (void *)dev; - t->sysctl_header = register_sysctl_paths(dn_ctl_path, t->dn_dev_vars); + t->sysctl_header = register_net_sysctl(&init_net, path, t->dn_dev_vars); if (t->sysctl_header == NULL) kfree(t); else @@ -248,7 +237,7 @@ static void dn_dev_sysctl_unregister(struct dn_dev_parms *parms) if (parms->sysctl) { struct dn_dev_sysctl_table *t = parms->sysctl; parms->sysctl = NULL; - unregister_sysctl_table(t->sysctl_header); + unregister_net_sysctl_table(t->sysctl_header); kfree(t); } } @@ -694,13 +683,13 @@ static int dn_nl_fill_ifaddr(struct sk_buff *skb, struct dn_ifaddr *ifa, ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; - if (ifa->ifa_address) - NLA_PUT_LE16(skb, IFA_ADDRESS, ifa->ifa_address); - if (ifa->ifa_local) - NLA_PUT_LE16(skb, IFA_LOCAL, ifa->ifa_local); - if (ifa->ifa_label[0]) - NLA_PUT_STRING(skb, IFA_LABEL, ifa->ifa_label); - + if ((ifa->ifa_address && + nla_put_le16(skb, IFA_ADDRESS, ifa->ifa_address)) || + (ifa->ifa_local && + nla_put_le16(skb, IFA_LOCAL, ifa->ifa_local)) || + (ifa->ifa_label[0] && + nla_put_string(skb, IFA_LABEL, ifa->ifa_label))) + goto nla_put_failure; return nlmsg_end(skb, nlh); nla_put_failure: diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 9e885f180b6..7eaf9879972 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -302,11 +302,12 @@ struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r, struct dn_kern_rta struct rtattr *attr = RTA_DATA(rta->rta_mx); while(RTA_OK(attr, attrlen)) { - unsigned flavour = attr->rta_type; + unsigned int flavour = attr->rta_type; + if (flavour) { if (flavour > RTAX_MAX) goto err_inval; - fi->fib_metrics[flavour-1] = *(unsigned*)RTA_DATA(attr); + fi->fib_metrics[flavour-1] = *(unsigned int *)RTA_DATA(attr); } attr = RTA_NEXT(attr, attrlen); } @@ -437,9 +438,8 @@ int dn_fib_semantic_match(int type, struct dn_fib_info *fi, const struct flowidn res->fi = NULL; return 1; default: - if (net_ratelimit()) - printk("DECnet: impossible routing event : dn_fib_semantic_match type=%d\n", - type); + net_err_ratelimited("DECnet: impossible routing event : dn_fib_semantic_match type=%d\n", + type); res->fi = NULL; return -EINVAL; } diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index ee7013f24fc..ac90f658586 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -162,8 +162,8 @@ static int dn_neigh_construct(struct neighbour *neigh) else if ((dev->type == ARPHRD_ETHER) || (dev->type == ARPHRD_LOOPBACK)) dn_dn2eth(neigh->ha, dn->addr); else { - if (net_ratelimit()) - printk(KERN_DEBUG "Trying to create neigh for hw %d\n", dev->type); + net_dbg_ratelimited("Trying to create neigh for hw %d\n", + dev->type); return -EINVAL; } @@ -236,15 +236,13 @@ static int dn_long_output(struct neighbour *neigh, struct sk_buff *skb) if (skb_headroom(skb) < headroom) { struct sk_buff *skb2 = skb_realloc_headroom(skb, headroom); if (skb2 == NULL) { - if (net_ratelimit()) - printk(KERN_CRIT "dn_long_output: no memory\n"); + net_crit_ratelimited("dn_long_output: no memory\n"); kfree_skb(skb); return -ENOBUFS; } kfree_skb(skb); skb = skb2; - if (net_ratelimit()) - printk(KERN_INFO "dn_long_output: Increasing headroom\n"); + net_info_ratelimited("dn_long_output: Increasing headroom\n"); } data = skb_push(skb, sizeof(struct dn_long_packet) + 3); @@ -281,15 +279,13 @@ static int dn_short_output(struct neighbour *neigh, struct sk_buff *skb) if (skb_headroom(skb) < headroom) { struct sk_buff *skb2 = skb_realloc_headroom(skb, headroom); if (skb2 == NULL) { - if (net_ratelimit()) - printk(KERN_CRIT "dn_short_output: no memory\n"); + net_crit_ratelimited("dn_short_output: no memory\n"); kfree_skb(skb); return -ENOBUFS; } kfree_skb(skb); skb = skb2; - if (net_ratelimit()) - printk(KERN_INFO "dn_short_output: Increasing headroom\n"); + net_info_ratelimited("dn_short_output: Increasing headroom\n"); } data = skb_push(skb, sizeof(struct dn_short_packet) + 2); @@ -322,15 +318,13 @@ static int dn_phase3_output(struct neighbour *neigh, struct sk_buff *skb) if (skb_headroom(skb) < headroom) { struct sk_buff *skb2 = skb_realloc_headroom(skb, headroom); if (skb2 == NULL) { - if (net_ratelimit()) - printk(KERN_CRIT "dn_phase3_output: no memory\n"); + net_crit_ratelimited("dn_phase3_output: no memory\n"); kfree_skb(skb); return -ENOBUFS; } kfree_skb(skb); skb = skb2; - if (net_ratelimit()) - printk(KERN_INFO "dn_phase3_output: Increasing headroom\n"); + net_info_ratelimited("dn_phase3_output: Increasing headroom\n"); } data = skb_push(skb, sizeof(struct dn_short_packet) + 2); diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c index f6544b2c91b..c344163e6ac 100644 --- a/net/decnet/dn_nsp_in.c +++ b/net/decnet/dn_nsp_in.c @@ -80,12 +80,15 @@ extern int decnet_log_martians; static void dn_log_martian(struct sk_buff *skb, const char *msg) { - if (decnet_log_martians && net_ratelimit()) { + if (decnet_log_martians) { char *devname = skb->dev ? skb->dev->name : "???"; struct dn_skb_cb *cb = DN_SKB_CB(skb); - printk(KERN_INFO "DECnet: Martian packet (%s) dev=%s src=0x%04hx dst=0x%04hx srcport=0x%04hx dstport=0x%04hx\n", - msg, devname, le16_to_cpu(cb->src), le16_to_cpu(cb->dst), - le16_to_cpu(cb->src_port), le16_to_cpu(cb->dst_port)); + net_info_ratelimited("DECnet: Martian packet (%s) dev=%s src=0x%04hx dst=0x%04hx srcport=0x%04hx dstport=0x%04hx\n", + msg, devname, + le16_to_cpu(cb->src), + le16_to_cpu(cb->dst), + le16_to_cpu(cb->src_port), + le16_to_cpu(cb->dst_port)); } } @@ -588,7 +591,7 @@ static __inline__ int dn_queue_skb(struct sock *sk, struct sk_buff *skb, int sig number of warnings when compiling with -W --ANK */ if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned)sk->sk_rcvbuf) { + (unsigned int)sk->sk_rcvbuf) { err = -ENOMEM; goto out; } diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c index e446e85e64a..564a6ad13ce 100644 --- a/net/decnet/dn_nsp_out.c +++ b/net/decnet/dn_nsp_out.c @@ -1,4 +1,3 @@ - /* * DECnet An implementation of the DECnet protocol suite for the LINUX * operating system. DECnet is implemented using the BSD Socket @@ -209,7 +208,7 @@ static void dn_nsp_rtt(struct sock *sk, long rtt) * * Returns: The number of times the packet has been sent previously */ -static inline unsigned dn_nsp_clone_and_send(struct sk_buff *skb, +static inline unsigned int dn_nsp_clone_and_send(struct sk_buff *skb, gfp_t gfp) { struct dn_skb_cb *cb = DN_SKB_CB(skb); @@ -240,7 +239,7 @@ void dn_nsp_output(struct sock *sk) { struct dn_scp *scp = DN_SK(sk); struct sk_buff *skb; - unsigned reduce_win = 0; + unsigned int reduce_win = 0; /* * First we check for otherdata/linkservice messages @@ -554,8 +553,8 @@ static __inline__ void dn_nsp_do_disc(struct sock *sk, unsigned char msgflg, unsigned char *msg; if ((dst == NULL) || (rem == 0)) { - if (net_ratelimit()) - printk(KERN_DEBUG "DECnet: dn_nsp_do_disc: BUG! Please report this to SteveW@ACM.org rem=%u dst=%p\n", le16_to_cpu(rem), dst); + net_dbg_ratelimited("DECnet: dn_nsp_do_disc: BUG! Please report this to SteveW@ACM.org rem=%u dst=%p\n", + le16_to_cpu(rem), dst); return; } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 80a3de4906d..586302e557a 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -122,7 +122,7 @@ static int dn_route_input(struct sk_buff *); static void dn_run_flush(unsigned long dummy); static struct dn_rt_hash_bucket *dn_rt_hash_table; -static unsigned dn_rt_hash_mask; +static unsigned int dn_rt_hash_mask; static struct timer_list dn_route_timer; static DEFINE_TIMER(dn_rt_flush_timer, dn_run_flush, 0, 0); @@ -149,13 +149,13 @@ static void dn_dst_destroy(struct dst_entry *dst) dst_destroy_metrics_generic(dst); } -static __inline__ unsigned dn_hash(__le16 src, __le16 dst) +static __inline__ unsigned int dn_hash(__le16 src, __le16 dst) { __u16 tmp = (__u16 __force)(src ^ dst); tmp ^= (tmp >> 3); tmp ^= (tmp >> 5); tmp ^= (tmp >> 10); - return dn_rt_hash_mask & (unsigned)tmp; + return dn_rt_hash_mask & (unsigned int)tmp; } static inline void dnrt_free(struct dn_route *rt) @@ -297,7 +297,7 @@ static inline int compare_keys(struct flowidn *fl1, struct flowidn *fl2) (fl1->flowidn_iif ^ fl2->flowidn_iif)) == 0; } -static int dn_insert_route(struct dn_route *rt, unsigned hash, struct dn_route **rp) +static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_route **rp) { struct dn_route *rth; struct dn_route __rcu **rthp; @@ -748,8 +748,7 @@ static int dn_output(struct sk_buff *skb) dn_to_neigh_output); error: - if (net_ratelimit()) - printk(KERN_DEBUG "dn_output: This should not happen\n"); + net_dbg_ratelimited("dn_output: This should not happen\n"); kfree_skb(skb); @@ -807,12 +806,10 @@ drop: */ static int dn_rt_bug(struct sk_buff *skb) { - if (net_ratelimit()) { - struct dn_skb_cb *cb = DN_SKB_CB(skb); + struct dn_skb_cb *cb = DN_SKB_CB(skb); - printk(KERN_DEBUG "dn_rt_bug: skb from:%04x to:%04x\n", - le16_to_cpu(cb->src), le16_to_cpu(cb->dst)); - } + net_dbg_ratelimited("dn_rt_bug: skb from:%04x to:%04x\n", + le16_to_cpu(cb->src), le16_to_cpu(cb->dst)); kfree_skb(skb); @@ -934,8 +931,8 @@ static int dn_route_output_slow(struct dst_entry **pprt, const struct flowidn *o struct dn_route *rt = NULL; struct net_device *dev_out = NULL, *dev; struct neighbour *neigh = NULL; - unsigned hash; - unsigned flags = 0; + unsigned int hash; + unsigned int flags = 0; struct dn_fib_res res = { .fi = NULL, .type = RTN_UNICAST }; int err; int free_res = 0; @@ -1209,7 +1206,7 @@ e_neighbour: */ static int __dn_route_output_key(struct dst_entry **pprt, const struct flowidn *flp, int flags) { - unsigned hash = dn_hash(flp->saddr, flp->daddr); + unsigned int hash = dn_hash(flp->saddr, flp->daddr); struct dn_route *rt = NULL; if (!(flags & MSG_TRYHARD)) { @@ -1275,7 +1272,7 @@ static int dn_route_input_slow(struct sk_buff *skb) struct net_device *out_dev = NULL; struct dn_dev *dn_db; struct neighbour *neigh = NULL; - unsigned hash; + unsigned int hash; int flags = 0; __le16 gateway = 0; __le16 local_src = 0; @@ -1327,9 +1324,7 @@ static int dn_route_input_slow(struct sk_buff *skb) out_dev = DN_FIB_RES_DEV(res); if (out_dev == NULL) { - if (net_ratelimit()) - printk(KERN_CRIT "Bug in dn_route_input_slow() " - "No output device\n"); + net_crit_ratelimited("Bug in dn_route_input_slow() No output device\n"); goto e_inval; } dev_hold(out_dev); @@ -1490,7 +1485,7 @@ static int dn_route_input(struct sk_buff *skb) { struct dn_route *rt; struct dn_skb_cb *cb = DN_SKB_CB(skb); - unsigned hash = dn_hash(cb->src, cb->dst); + unsigned int hash = dn_hash(cb->src, cb->dst); if (skb_dst(skb)) return 0; diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index f65c9ddaee4..e65f2c856e0 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -177,11 +177,11 @@ static int dn_fib_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, return 1; } -unsigned dnet_addr_type(__le16 addr) +unsigned int dnet_addr_type(__le16 addr) { struct flowidn fld = { .daddr = addr }; struct dn_fib_res res; - unsigned ret = RTN_UNICAST; + unsigned int ret = RTN_UNICAST; struct dn_fib_table *tb = dn_fib_get_table(RT_TABLE_LOCAL, 0); res.r = NULL; @@ -204,11 +204,11 @@ static int dn_fib_rule_fill(struct fib_rule *rule, struct sk_buff *skb, frh->src_len = r->src_len; frh->tos = 0; - if (r->dst_len) - NLA_PUT_LE16(skb, FRA_DST, r->dst); - if (r->src_len) - NLA_PUT_LE16(skb, FRA_SRC, r->src); - + if ((r->dst_len && + nla_put_le16(skb, FRA_DST, r->dst)) || + (r->src_len && + nla_put_le16(skb, FRA_SRC, r->src))) + goto nla_put_failure; return 0; nla_put_failure: diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index a9a62f225a6..650f3380c98 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -836,8 +836,8 @@ struct dn_fib_table *dn_fib_get_table(u32 n, int create) if (!create) return NULL; - if (in_interrupt() && net_ratelimit()) { - printk(KERN_DEBUG "DECnet: BUG! Attempt to create routing table from interrupt\n"); + if (in_interrupt()) { + net_dbg_ratelimited("DECnet: BUG! Attempt to create routing table from interrupt\n"); return NULL; } diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c index 1531135130d..44b890936fc 100644 --- a/net/decnet/netfilter/dn_rtmsg.c +++ b/net/decnet/netfilter/dn_rtmsg.c @@ -57,8 +57,7 @@ nlmsg_failure: if (skb) kfree_skb(skb); *errp = -ENOMEM; - if (net_ratelimit()) - printk(KERN_ERR "dn_rtmsg: error creating netlink message\n"); + net_err_ratelimited("dn_rtmsg: error creating netlink message\n"); return NULL; } diff --git a/net/decnet/sysctl_net_decnet.c b/net/decnet/sysctl_net_decnet.c index 02e75d11cfb..a55eeccaa72 100644 --- a/net/decnet/sysctl_net_decnet.c +++ b/net/decnet/sysctl_net_decnet.c @@ -351,20 +351,14 @@ static ctl_table dn_table[] = { { } }; -static struct ctl_path dn_path[] = { - { .procname = "net", }, - { .procname = "decnet", }, - { } -}; - void dn_register_sysctl(void) { - dn_table_header = register_sysctl_paths(dn_path, dn_table); + dn_table_header = register_net_sysctl(&init_net, "net/decnet", dn_table); } void dn_unregister_sysctl(void) { - unregister_sysctl_table(dn_table_header); + unregister_net_sysctl_table(dn_table_header); } #else /* CONFIG_SYSCTL */ diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index c73bba326d7..d9507dd0581 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -38,7 +38,7 @@ MODULE_DESCRIPTION("DNS Resolver"); MODULE_AUTHOR("Wang Lei"); MODULE_LICENSE("GPL"); -unsigned dns_resolver_debug; +unsigned int dns_resolver_debug; module_param_named(debug, dns_resolver_debug, uint, S_IWUSR | S_IRUGO); MODULE_PARM_DESC(debug, "DNS Resolver debugging mask"); @@ -249,9 +249,6 @@ static int __init init_dns_resolver(void) struct key *keyring; int ret; - printk(KERN_NOTICE "Registering the %s key type\n", - key_type_dns_resolver.name); - /* create an override credential set with a special thread keyring in * which DNS requests are cached * @@ -301,8 +298,6 @@ static void __exit exit_dns_resolver(void) key_revoke(dns_resolver_cache->thread_keyring); unregister_key_type(&key_type_dns_resolver); put_cred(dns_resolver_cache); - printk(KERN_NOTICE "Unregistered %s key type\n", - key_type_dns_resolver.name); } module_init(init_dns_resolver) diff --git a/net/dns_resolver/internal.h b/net/dns_resolver/internal.h index 189ca9e9b78..17c7886b5b3 100644 --- a/net/dns_resolver/internal.h +++ b/net/dns_resolver/internal.h @@ -31,7 +31,7 @@ extern const struct cred *dns_resolver_cache; /* * debug tracing */ -extern unsigned dns_resolver_debug; +extern unsigned int dns_resolver_debug; #define kdebug(FMT, ...) \ do { \ diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 56cf9b8e1c7..e32083d5d8f 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -66,7 +66,7 @@ static int dsa_slave_open(struct net_device *dev) if (!(master->flags & IFF_UP)) return -ENETDOWN; - if (compare_ether_addr(dev->dev_addr, master->dev_addr)) { + if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) { err = dev_uc_add(master, dev->dev_addr); if (err < 0) goto out; @@ -89,7 +89,7 @@ clear_allmulti: if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(master, -1); del_unicast: - if (compare_ether_addr(dev->dev_addr, master->dev_addr)) + if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) dev_uc_del(master, dev->dev_addr); out: return err; @@ -107,7 +107,7 @@ static int dsa_slave_close(struct net_device *dev) if (dev->flags & IFF_PROMISC) dev_set_promiscuity(master, -1); - if (compare_ether_addr(dev->dev_addr, master->dev_addr)) + if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) dev_uc_del(master, dev->dev_addr); return 0; @@ -146,13 +146,13 @@ static int dsa_slave_set_mac_address(struct net_device *dev, void *a) if (!(dev->flags & IFF_UP)) goto out; - if (compare_ether_addr(addr->sa_data, master->dev_addr)) { + if (!ether_addr_equal(addr->sa_data, master->dev_addr)) { err = dev_uc_add(master, addr->sa_data); if (err < 0) return err; } - if (compare_ether_addr(dev->dev_addr, master->dev_addr)) + if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) dev_uc_del(master, dev->dev_addr); out: diff --git a/net/econet/Kconfig b/net/econet/Kconfig deleted file mode 100644 index 39a2d2975e0..00000000000 --- a/net/econet/Kconfig +++ /dev/null @@ -1,36 +0,0 @@ -# -# Acorn Econet/AUN protocols -# - -config ECONET - tristate "Acorn Econet/AUN protocols (EXPERIMENTAL)" - depends on EXPERIMENTAL && INET - ---help--- - Econet is a fairly old and slow networking protocol mainly used by - Acorn computers to access file and print servers. It uses native - Econet network cards. AUN is an implementation of the higher level - parts of Econet that runs over ordinary Ethernet connections, on - top of the UDP packet protocol, which in turn runs on top of the - Internet protocol IP. - - If you say Y here, you can choose with the next two options whether - to send Econet/AUN traffic over a UDP Ethernet connection or over - a native Econet network card. - - To compile this driver as a module, choose M here: the module - will be called econet. - -config ECONET_AUNUDP - bool "AUN over UDP" - depends on ECONET - help - Say Y here if you want to send Econet/AUN traffic over a UDP - connection (UDP is a packet based protocol that runs on top of the - Internet protocol IP) using an ordinary Ethernet network card. - -config ECONET_NATIVE - bool "Native Econet" - depends on ECONET - help - Say Y here if you have a native Econet network card installed in - your computer. diff --git a/net/econet/Makefile b/net/econet/Makefile deleted file mode 100644 index 05fae8be2fe..00000000000 --- a/net/econet/Makefile +++ /dev/null @@ -1,7 +0,0 @@ -# -# Makefile for Econet support code. -# - -obj-$(CONFIG_ECONET) += econet.o - -econet-y := af_econet.o diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c deleted file mode 100644 index 71b5edcee40..00000000000 --- a/net/econet/af_econet.c +++ /dev/null @@ -1,1172 +0,0 @@ -/* - * An implementation of the Acorn Econet and AUN protocols. - * Philip Blundell <philb@gnu.org> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - */ - -#define pr_fmt(fmt) fmt - -#include <linux/module.h> - -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> -#include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/if_ether.h> -#include <linux/netdevice.h> -#include <linux/inetdevice.h> -#include <linux/route.h> -#include <linux/inet.h> -#include <linux/etherdevice.h> -#include <linux/if_arp.h> -#include <linux/wireless.h> -#include <linux/skbuff.h> -#include <linux/udp.h> -#include <linux/slab.h> -#include <linux/vmalloc.h> -#include <net/sock.h> -#include <net/inet_common.h> -#include <linux/stat.h> -#include <linux/init.h> -#include <linux/if_ec.h> -#include <net/udp.h> -#include <net/ip.h> -#include <linux/spinlock.h> -#include <linux/rcupdate.h> -#include <linux/bitops.h> -#include <linux/mutex.h> - -#include <linux/uaccess.h> - -static const struct proto_ops econet_ops; -static struct hlist_head econet_sklist; -static DEFINE_SPINLOCK(econet_lock); -static DEFINE_MUTEX(econet_mutex); - -/* Since there are only 256 possible network numbers (or fewer, depends - how you count) it makes sense to use a simple lookup table. */ -static struct net_device *net2dev_map[256]; - -#define EC_PORT_IP 0xd2 - -#ifdef CONFIG_ECONET_AUNUDP -static DEFINE_SPINLOCK(aun_queue_lock); -static struct socket *udpsock; -#define AUN_PORT 0x8000 - -struct aunhdr { - unsigned char code; /* AUN magic protocol byte */ - unsigned char port; - unsigned char cb; - unsigned char pad; - unsigned long handle; -}; - -static unsigned long aun_seq; - -/* Queue of packets waiting to be transmitted. */ -static struct sk_buff_head aun_queue; -static struct timer_list ab_cleanup_timer; - -#endif /* CONFIG_ECONET_AUNUDP */ - -/* Per-packet information */ -struct ec_cb { - struct sockaddr_ec sec; - unsigned long cookie; /* Supplied by user. */ -#ifdef CONFIG_ECONET_AUNUDP - int done; - unsigned long seq; /* Sequencing */ - unsigned long timeout; /* Timeout */ - unsigned long start; /* jiffies */ -#endif -#ifdef CONFIG_ECONET_NATIVE - void (*sent)(struct sk_buff *, int result); -#endif -}; - -static void econet_remove_socket(struct hlist_head *list, struct sock *sk) -{ - spin_lock_bh(&econet_lock); - sk_del_node_init(sk); - spin_unlock_bh(&econet_lock); -} - -static void econet_insert_socket(struct hlist_head *list, struct sock *sk) -{ - spin_lock_bh(&econet_lock); - sk_add_node(sk, list); - spin_unlock_bh(&econet_lock); -} - -/* - * Pull a packet from our receive queue and hand it to the user. - * If necessary we block. - */ - -static int econet_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len, int flags) -{ - struct sock *sk = sock->sk; - struct sk_buff *skb; - size_t copied; - int err; - - msg->msg_namelen = sizeof(struct sockaddr_ec); - - mutex_lock(&econet_mutex); - - /* - * Call the generic datagram receiver. This handles all sorts - * of horrible races and re-entrancy so we can forget about it - * in the protocol layers. - * - * Now it will return ENETDOWN, if device have just gone down, - * but then it will block. - */ - - skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err); - - /* - * An error occurred so return it. Because skb_recv_datagram() - * handles the blocking we don't see and worry about blocking - * retries. - */ - - if (skb == NULL) - goto out; - - /* - * You lose any data beyond the buffer you gave. If it worries a - * user program they can ask the device for its MTU anyway. - */ - - copied = skb->len; - if (copied > len) { - copied = len; - msg->msg_flags |= MSG_TRUNC; - } - - /* We can't use skb_copy_datagram here */ - err = memcpy_toiovec(msg->msg_iov, skb->data, copied); - if (err) - goto out_free; - sk->sk_stamp = skb->tstamp; - - if (msg->msg_name) - memcpy(msg->msg_name, skb->cb, msg->msg_namelen); - - /* - * Free or return the buffer as appropriate. Again this - * hides all the races and re-entrancy issues from us. - */ - err = copied; - -out_free: - skb_free_datagram(sk, skb); -out: - mutex_unlock(&econet_mutex); - return err; -} - -/* - * Bind an Econet socket. - */ - -static int econet_bind(struct socket *sock, struct sockaddr *uaddr, - int addr_len) -{ - struct sockaddr_ec *sec = (struct sockaddr_ec *)uaddr; - struct sock *sk; - struct econet_sock *eo; - - /* - * Check legality - */ - - if (addr_len < sizeof(struct sockaddr_ec) || - sec->sec_family != AF_ECONET) - return -EINVAL; - - mutex_lock(&econet_mutex); - - sk = sock->sk; - eo = ec_sk(sk); - - eo->cb = sec->cb; - eo->port = sec->port; - eo->station = sec->addr.station; - eo->net = sec->addr.net; - - mutex_unlock(&econet_mutex); - - return 0; -} - -#if defined(CONFIG_ECONET_AUNUDP) || defined(CONFIG_ECONET_NATIVE) -/* - * Queue a transmit result for the user to be told about. - */ - -static void tx_result(struct sock *sk, unsigned long cookie, int result) -{ - struct sk_buff *skb = alloc_skb(0, GFP_ATOMIC); - struct ec_cb *eb; - struct sockaddr_ec *sec; - - if (skb == NULL) { - pr_debug("econet: memory squeeze, transmit result dropped\n"); - return; - } - - eb = (struct ec_cb *)&skb->cb; - sec = (struct sockaddr_ec *)&eb->sec; - memset(sec, 0, sizeof(struct sockaddr_ec)); - sec->cookie = cookie; - sec->type = ECTYPE_TRANSMIT_STATUS | result; - sec->sec_family = AF_ECONET; - - if (sock_queue_rcv_skb(sk, skb) < 0) - kfree_skb(skb); -} -#endif - -#ifdef CONFIG_ECONET_NATIVE -/* - * Called by the Econet hardware driver when a packet transmit - * has completed. Tell the user. - */ - -static void ec_tx_done(struct sk_buff *skb, int result) -{ - struct ec_cb *eb = (struct ec_cb *)&skb->cb; - tx_result(skb->sk, eb->cookie, result); -} -#endif - -/* - * Send a packet. We have to work out which device it's going out on - * and hence whether to use real Econet or the UDP emulation. - */ - -static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) -{ - struct sockaddr_ec *saddr = (struct sockaddr_ec *)msg->msg_name; - struct net_device *dev; - struct ec_addr addr; - int err; - unsigned char port, cb; -#if defined(CONFIG_ECONET_AUNUDP) || defined(CONFIG_ECONET_NATIVE) - struct sock *sk = sock->sk; - struct sk_buff *skb; - struct ec_cb *eb; -#endif -#ifdef CONFIG_ECONET_AUNUDP - struct msghdr udpmsg; - struct iovec iov[2]; - struct aunhdr ah; - struct sockaddr_in udpdest; - __kernel_size_t size; - mm_segment_t oldfs; - char *userbuf; -#endif - - /* - * Check the flags. - */ - - if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_CMSG_COMPAT)) - return -EINVAL; - - /* - * Get and verify the address. - */ - - mutex_lock(&econet_mutex); - - if (saddr == NULL || msg->msg_namelen < sizeof(struct sockaddr_ec)) { - mutex_unlock(&econet_mutex); - return -EINVAL; - } - addr.station = saddr->addr.station; - addr.net = saddr->addr.net; - port = saddr->port; - cb = saddr->cb; - - /* Look for a device with the right network number. */ - dev = net2dev_map[addr.net]; - - /* If not directly reachable, use some default */ - if (dev == NULL) { - dev = net2dev_map[0]; - /* No interfaces at all? */ - if (dev == NULL) { - mutex_unlock(&econet_mutex); - return -ENETDOWN; - } - } - - if (dev->type == ARPHRD_ECONET) { - /* Real hardware Econet. We're not worthy etc. */ -#ifdef CONFIG_ECONET_NATIVE - unsigned short proto = 0; - int hlen, tlen; - int res; - - if (len + 15 > dev->mtu) { - mutex_unlock(&econet_mutex); - return -EMSGSIZE; - } - - dev_hold(dev); - - hlen = LL_RESERVED_SPACE(dev); - tlen = dev->needed_tailroom; - skb = sock_alloc_send_skb(sk, len + hlen + tlen, - msg->msg_flags & MSG_DONTWAIT, &err); - if (skb == NULL) - goto out_unlock; - - skb_reserve(skb, hlen); - skb_reset_network_header(skb); - - eb = (struct ec_cb *)&skb->cb; - - eb->cookie = saddr->cookie; - eb->sec = *saddr; - eb->sent = ec_tx_done; - - err = -EINVAL; - res = dev_hard_header(skb, dev, ntohs(proto), &addr, NULL, len); - if (res < 0) - goto out_free; - if (res > 0) { - struct ec_framehdr *fh; - /* Poke in our control byte and - port number. Hack, hack. */ - fh = (struct ec_framehdr *)skb->data; - fh->cb = cb; - fh->port = port; - if (sock->type != SOCK_DGRAM) { - skb_reset_tail_pointer(skb); - skb->len = 0; - } - } - - /* Copy the data. Returns -EFAULT on error */ - err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len); - skb->protocol = proto; - skb->dev = dev; - skb->priority = sk->sk_priority; - if (err) - goto out_free; - - err = -ENETDOWN; - if (!(dev->flags & IFF_UP)) - goto out_free; - - /* - * Now send it - */ - - dev_queue_xmit(skb); - dev_put(dev); - mutex_unlock(&econet_mutex); - return len; - -out_free: - kfree_skb(skb); -out_unlock: - if (dev) - dev_put(dev); -#else - err = -EPROTOTYPE; -#endif - mutex_unlock(&econet_mutex); - - return err; - } - -#ifdef CONFIG_ECONET_AUNUDP - /* AUN virtual Econet. */ - - if (udpsock == NULL) { - mutex_unlock(&econet_mutex); - return -ENETDOWN; /* No socket - can't send */ - } - - if (len > 32768) { - err = -E2BIG; - goto error; - } - - /* Make up a UDP datagram and hand it off to some higher intellect. */ - - memset(&udpdest, 0, sizeof(udpdest)); - udpdest.sin_family = AF_INET; - udpdest.sin_port = htons(AUN_PORT); - - /* At the moment we use the stupid Acorn scheme of Econet address - y.x maps to IP a.b.c.x. This should be replaced with something - more flexible and more aware of subnet masks. */ - { - struct in_device *idev; - unsigned long network = 0; - - rcu_read_lock(); - idev = __in_dev_get_rcu(dev); - if (idev) { - if (idev->ifa_list) - network = ntohl(idev->ifa_list->ifa_address) & - 0xffffff00; /* !!! */ - } - rcu_read_unlock(); - udpdest.sin_addr.s_addr = htonl(network | addr.station); - } - - memset(&ah, 0, sizeof(ah)); - ah.port = port; - ah.cb = cb & 0x7f; - ah.code = 2; /* magic */ - - /* tack our header on the front of the iovec */ - size = sizeof(struct aunhdr); - iov[0].iov_base = (void *)&ah; - iov[0].iov_len = size; - - userbuf = vmalloc(len); - if (userbuf == NULL) { - err = -ENOMEM; - goto error; - } - - iov[1].iov_base = userbuf; - iov[1].iov_len = len; - err = memcpy_fromiovec(userbuf, msg->msg_iov, len); - if (err) - goto error_free_buf; - - /* Get a skbuff (no data, just holds our cb information) */ - skb = sock_alloc_send_skb(sk, 0, msg->msg_flags & MSG_DONTWAIT, &err); - if (skb == NULL) - goto error_free_buf; - - eb = (struct ec_cb *)&skb->cb; - - eb->cookie = saddr->cookie; - eb->timeout = 5 * HZ; - eb->start = jiffies; - ah.handle = aun_seq; - eb->seq = (aun_seq++); - eb->sec = *saddr; - - skb_queue_tail(&aun_queue, skb); - - udpmsg.msg_name = (void *)&udpdest; - udpmsg.msg_namelen = sizeof(udpdest); - udpmsg.msg_iov = &iov[0]; - udpmsg.msg_iovlen = 2; - udpmsg.msg_control = NULL; - udpmsg.msg_controllen = 0; - udpmsg.msg_flags = 0; - - oldfs = get_fs(); - set_fs(KERNEL_DS); /* More privs :-) */ - err = sock_sendmsg(udpsock, &udpmsg, size); - set_fs(oldfs); - -error_free_buf: - vfree(userbuf); -error: -#else - err = -EPROTOTYPE; -#endif - mutex_unlock(&econet_mutex); - - return err; -} - -/* - * Look up the address of a socket. - */ - -static int econet_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) -{ - struct sock *sk; - struct econet_sock *eo; - struct sockaddr_ec *sec = (struct sockaddr_ec *)uaddr; - - if (peer) - return -EOPNOTSUPP; - - memset(sec, 0, sizeof(*sec)); - mutex_lock(&econet_mutex); - - sk = sock->sk; - eo = ec_sk(sk); - - sec->sec_family = AF_ECONET; - sec->port = eo->port; - sec->addr.station = eo->station; - sec->addr.net = eo->net; - - mutex_unlock(&econet_mutex); - - *uaddr_len = sizeof(*sec); - return 0; -} - -static void econet_destroy_timer(unsigned long data) -{ - struct sock *sk = (struct sock *)data; - - if (!sk_has_allocations(sk)) { - sk_free(sk); - return; - } - - sk->sk_timer.expires = jiffies + 10 * HZ; - add_timer(&sk->sk_timer); - pr_debug("econet: socket destroy delayed\n"); -} - -/* - * Close an econet socket. - */ - -static int econet_release(struct socket *sock) -{ - struct sock *sk; - - mutex_lock(&econet_mutex); - - sk = sock->sk; - if (!sk) - goto out_unlock; - - econet_remove_socket(&econet_sklist, sk); - - /* - * Now the socket is dead. No more input will appear. - */ - - sk->sk_state_change(sk); /* It is useless. Just for sanity. */ - - sock_orphan(sk); - - /* Purge queues */ - - skb_queue_purge(&sk->sk_receive_queue); - - if (sk_has_allocations(sk)) { - sk->sk_timer.data = (unsigned long)sk; - sk->sk_timer.expires = jiffies + HZ; - sk->sk_timer.function = econet_destroy_timer; - add_timer(&sk->sk_timer); - - goto out_unlock; - } - - sk_free(sk); - -out_unlock: - mutex_unlock(&econet_mutex); - return 0; -} - -static struct proto econet_proto = { - .name = "ECONET", - .owner = THIS_MODULE, - .obj_size = sizeof(struct econet_sock), -}; - -/* - * Create an Econet socket - */ - -static int econet_create(struct net *net, struct socket *sock, int protocol, - int kern) -{ - struct sock *sk; - struct econet_sock *eo; - int err; - - if (!net_eq(net, &init_net)) - return -EAFNOSUPPORT; - - /* Econet only provides datagram services. */ - if (sock->type != SOCK_DGRAM) - return -ESOCKTNOSUPPORT; - - sock->state = SS_UNCONNECTED; - - err = -ENOBUFS; - sk = sk_alloc(net, PF_ECONET, GFP_KERNEL, &econet_proto); - if (sk == NULL) - goto out; - - sk->sk_reuse = 1; - sock->ops = &econet_ops; - sock_init_data(sock, sk); - - eo = ec_sk(sk); - sock_reset_flag(sk, SOCK_ZAPPED); - sk->sk_family = PF_ECONET; - eo->num = protocol; - - econet_insert_socket(&econet_sklist, sk); - return 0; -out: - return err; -} - -/* - * Handle Econet specific ioctls - */ - -static int ec_dev_ioctl(struct socket *sock, unsigned int cmd, void __user *arg) -{ - struct ifreq ifr; - struct ec_device *edev; - struct net_device *dev; - struct sockaddr_ec *sec; - int err; - - /* - * Fetch the caller's info block into kernel space - */ - - if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) - return -EFAULT; - - dev = dev_get_by_name(&init_net, ifr.ifr_name); - if (dev == NULL) - return -ENODEV; - - sec = (struct sockaddr_ec *)&ifr.ifr_addr; - - mutex_lock(&econet_mutex); - - err = 0; - switch (cmd) { - case SIOCSIFADDR: - if (!capable(CAP_NET_ADMIN)) { - err = -EPERM; - break; - } - - edev = dev->ec_ptr; - if (edev == NULL) { - /* Magic up a new one. */ - edev = kzalloc(sizeof(struct ec_device), GFP_KERNEL); - if (edev == NULL) { - err = -ENOMEM; - break; - } - dev->ec_ptr = edev; - } else - net2dev_map[edev->net] = NULL; - edev->station = sec->addr.station; - edev->net = sec->addr.net; - net2dev_map[sec->addr.net] = dev; - if (!net2dev_map[0]) - net2dev_map[0] = dev; - break; - - case SIOCGIFADDR: - edev = dev->ec_ptr; - if (edev == NULL) { - err = -ENODEV; - break; - } - memset(sec, 0, sizeof(struct sockaddr_ec)); - sec->addr.station = edev->station; - sec->addr.net = edev->net; - sec->sec_family = AF_ECONET; - dev_put(dev); - if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) - err = -EFAULT; - break; - - default: - err = -EINVAL; - break; - } - - mutex_unlock(&econet_mutex); - - dev_put(dev); - - return err; -} - -/* - * Handle generic ioctls - */ - -static int econet_ioctl(struct socket *sock, unsigned int cmd, - unsigned long arg) -{ - struct sock *sk = sock->sk; - void __user *argp = (void __user *)arg; - - switch (cmd) { - case SIOCGSTAMP: - return sock_get_timestamp(sk, argp); - - case SIOCGSTAMPNS: - return sock_get_timestampns(sk, argp); - - case SIOCSIFADDR: - case SIOCGIFADDR: - return ec_dev_ioctl(sock, cmd, argp); - - } - - return -ENOIOCTLCMD; -} - -static const struct net_proto_family econet_family_ops = { - .family = PF_ECONET, - .create = econet_create, - .owner = THIS_MODULE, -}; - -static const struct proto_ops econet_ops = { - .family = PF_ECONET, - .owner = THIS_MODULE, - .release = econet_release, - .bind = econet_bind, - .connect = sock_no_connect, - .socketpair = sock_no_socketpair, - .accept = sock_no_accept, - .getname = econet_getname, - .poll = datagram_poll, - .ioctl = econet_ioctl, - .listen = sock_no_listen, - .shutdown = sock_no_shutdown, - .setsockopt = sock_no_setsockopt, - .getsockopt = sock_no_getsockopt, - .sendmsg = econet_sendmsg, - .recvmsg = econet_recvmsg, - .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, -}; - -#if defined(CONFIG_ECONET_AUNUDP) || defined(CONFIG_ECONET_NATIVE) -/* - * Find the listening socket, if any, for the given data. - */ - -static struct sock *ec_listening_socket(unsigned char port, unsigned char - station, unsigned char net) -{ - struct sock *sk; - struct hlist_node *node; - - spin_lock(&econet_lock); - sk_for_each(sk, node, &econet_sklist) { - struct econet_sock *opt = ec_sk(sk); - if ((opt->port == port || opt->port == 0) && - (opt->station == station || opt->station == 0) && - (opt->net == net || opt->net == 0)) { - sock_hold(sk); - goto found; - } - } - sk = NULL; -found: - spin_unlock(&econet_lock); - return sk; -} - -/* - * Queue a received packet for a socket. - */ - -static int ec_queue_packet(struct sock *sk, struct sk_buff *skb, - unsigned char stn, unsigned char net, - unsigned char cb, unsigned char port) -{ - struct ec_cb *eb = (struct ec_cb *)&skb->cb; - struct sockaddr_ec *sec = (struct sockaddr_ec *)&eb->sec; - - memset(sec, 0, sizeof(struct sockaddr_ec)); - sec->sec_family = AF_ECONET; - sec->type = ECTYPE_PACKET_RECEIVED; - sec->port = port; - sec->cb = cb; - sec->addr.net = net; - sec->addr.station = stn; - - return sock_queue_rcv_skb(sk, skb); -} -#endif - -#ifdef CONFIG_ECONET_AUNUDP -/* - * Send an AUN protocol response. - */ - -static void aun_send_response(__u32 addr, unsigned long seq, int code, int cb) -{ - struct sockaddr_in sin = { - .sin_family = AF_INET, - .sin_port = htons(AUN_PORT), - .sin_addr = {.s_addr = addr} - }; - struct aunhdr ah = {.code = code, .cb = cb, .handle = seq}; - struct kvec iov = {.iov_base = (void *)&ah, .iov_len = sizeof(ah)}; - struct msghdr udpmsg; - - udpmsg.msg_name = (void *)&sin; - udpmsg.msg_namelen = sizeof(sin); - udpmsg.msg_control = NULL; - udpmsg.msg_controllen = 0; - udpmsg.msg_flags = 0; - - kernel_sendmsg(udpsock, &udpmsg, &iov, 1, sizeof(ah)); -} - - -/* - * Handle incoming AUN packets. Work out if anybody wants them, - * and send positive or negative acknowledgements as appropriate. - */ - -static void aun_incoming(struct sk_buff *skb, struct aunhdr *ah, size_t len) -{ - struct iphdr *ip = ip_hdr(skb); - unsigned char stn = ntohl(ip->saddr) & 0xff; - struct dst_entry *dst = skb_dst(skb); - struct ec_device *edev = NULL; - struct sock *sk = NULL; - struct sk_buff *newskb; - - if (dst) - edev = dst->dev->ec_ptr; - - if (!edev) - goto bad; - - sk = ec_listening_socket(ah->port, stn, edev->net); - if (sk == NULL) - goto bad; /* Nobody wants it */ - - newskb = alloc_skb((len - sizeof(struct aunhdr) + 15) & ~15, - GFP_ATOMIC); - if (newskb == NULL) { - pr_debug("AUN: memory squeeze, dropping packet\n"); - /* Send nack and hope sender tries again */ - goto bad; - } - - memcpy(skb_put(newskb, len - sizeof(struct aunhdr)), (void *)(ah + 1), - len - sizeof(struct aunhdr)); - - if (ec_queue_packet(sk, newskb, stn, edev->net, ah->cb, ah->port)) { - /* Socket is bankrupt. */ - kfree_skb(newskb); - goto bad; - } - - aun_send_response(ip->saddr, ah->handle, 3, 0); - sock_put(sk); - return; - -bad: - aun_send_response(ip->saddr, ah->handle, 4, 0); - if (sk) - sock_put(sk); -} - -/* - * Handle incoming AUN transmit acknowledgements. If the sequence - * number matches something in our backlog then kill it and tell - * the user. If the remote took too long to reply then we may have - * dropped the packet already. - */ - -static void aun_tx_ack(unsigned long seq, int result) -{ - struct sk_buff *skb; - unsigned long flags; - struct ec_cb *eb; - - spin_lock_irqsave(&aun_queue_lock, flags); - skb_queue_walk(&aun_queue, skb) { - eb = (struct ec_cb *)&skb->cb; - if (eb->seq == seq) - goto foundit; - } - spin_unlock_irqrestore(&aun_queue_lock, flags); - pr_debug("AUN: unknown sequence %ld\n", seq); - return; - -foundit: - tx_result(skb->sk, eb->cookie, result); - skb_unlink(skb, &aun_queue); - spin_unlock_irqrestore(&aun_queue_lock, flags); - kfree_skb(skb); -} - -/* - * Deal with received AUN frames - sort out what type of thing it is - * and hand it to the right function. - */ - -static void aun_data_available(struct sock *sk, int slen) -{ - int err; - struct sk_buff *skb; - unsigned char *data; - struct aunhdr *ah; - size_t len; - - while ((skb = skb_recv_datagram(sk, 0, 1, &err)) == NULL) { - if (err == -EAGAIN) { - pr_err("AUN: no data available?!\n"); - return; - } - pr_debug("AUN: recvfrom() error %d\n", -err); - } - - data = skb_transport_header(skb) + sizeof(struct udphdr); - ah = (struct aunhdr *)data; - len = skb->len - sizeof(struct udphdr); - - switch (ah->code) { - case 2: - aun_incoming(skb, ah, len); - break; - case 3: - aun_tx_ack(ah->handle, ECTYPE_TRANSMIT_OK); - break; - case 4: - aun_tx_ack(ah->handle, ECTYPE_TRANSMIT_NOT_LISTENING); - break; - default: - pr_debug("AUN: unknown packet type: %d\n", data[0]); - } - - skb_free_datagram(sk, skb); -} - -/* - * Called by the timer to manage the AUN transmit queue. If a packet - * was sent to a dead or nonexistent host then we will never get an - * acknowledgement back. After a few seconds we need to spot this and - * drop the packet. - */ - -static void ab_cleanup(unsigned long h) -{ - struct sk_buff *skb, *n; - unsigned long flags; - - spin_lock_irqsave(&aun_queue_lock, flags); - skb_queue_walk_safe(&aun_queue, skb, n) { - struct ec_cb *eb = (struct ec_cb *)&skb->cb; - if ((jiffies - eb->start) > eb->timeout) { - tx_result(skb->sk, eb->cookie, - ECTYPE_TRANSMIT_NOT_PRESENT); - skb_unlink(skb, &aun_queue); - kfree_skb(skb); - } - } - spin_unlock_irqrestore(&aun_queue_lock, flags); - - mod_timer(&ab_cleanup_timer, jiffies + (HZ * 2)); -} - -static int __init aun_udp_initialise(void) -{ - int error; - struct sockaddr_in sin; - - skb_queue_head_init(&aun_queue); - setup_timer(&ab_cleanup_timer, ab_cleanup, 0); - ab_cleanup_timer.expires = jiffies + (HZ * 2); - add_timer(&ab_cleanup_timer); - - memset(&sin, 0, sizeof(sin)); - sin.sin_port = htons(AUN_PORT); - - /* We can count ourselves lucky Acorn machines are too dim to - speak IPv6. :-) */ - error = sock_create_kern(PF_INET, SOCK_DGRAM, 0, &udpsock); - if (error < 0) { - pr_err("AUN: socket error %d\n", -error); - return error; - } - - udpsock->sk->sk_reuse = 1; - udpsock->sk->sk_allocation = GFP_ATOMIC; /* we're going to call it - from interrupts */ - - error = udpsock->ops->bind(udpsock, (struct sockaddr *)&sin, - sizeof(sin)); - if (error < 0) { - pr_err("AUN: bind error %d\n", -error); - goto release; - } - - udpsock->sk->sk_data_ready = aun_data_available; - - return 0; - -release: - sock_release(udpsock); - udpsock = NULL; - return error; -} -#endif - -#ifdef CONFIG_ECONET_NATIVE - -/* - * Receive an Econet frame from a device. - */ - -static int econet_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev) -{ - struct ec_framehdr *hdr; - struct sock *sk = NULL; - struct ec_device *edev = dev->ec_ptr; - - if (!net_eq(dev_net(dev), &init_net)) - goto drop; - - if (skb->pkt_type == PACKET_OTHERHOST) - goto drop; - - if (!edev) - goto drop; - - skb = skb_share_check(skb, GFP_ATOMIC); - if (skb == NULL) - return NET_RX_DROP; - - if (!pskb_may_pull(skb, sizeof(struct ec_framehdr))) - goto drop; - - hdr = (struct ec_framehdr *)skb->data; - - /* First check for encapsulated IP */ - if (hdr->port == EC_PORT_IP) { - skb->protocol = htons(ETH_P_IP); - skb_pull(skb, sizeof(struct ec_framehdr)); - netif_rx(skb); - return NET_RX_SUCCESS; - } - - sk = ec_listening_socket(hdr->port, hdr->src_stn, hdr->src_net); - if (!sk) - goto drop; - - if (ec_queue_packet(sk, skb, edev->net, hdr->src_stn, hdr->cb, - hdr->port)) - goto drop; - sock_put(sk); - return NET_RX_SUCCESS; - -drop: - if (sk) - sock_put(sk); - kfree_skb(skb); - return NET_RX_DROP; -} - -static struct packet_type econet_packet_type __read_mostly = { - .type = cpu_to_be16(ETH_P_ECONET), - .func = econet_rcv, -}; - -static void econet_hw_initialise(void) -{ - dev_add_pack(&econet_packet_type); -} - -#endif - -static int econet_notifier(struct notifier_block *this, unsigned long msg, - void *data) -{ - struct net_device *dev = data; - struct ec_device *edev; - - if (!net_eq(dev_net(dev), &init_net)) - return NOTIFY_DONE; - - switch (msg) { - case NETDEV_UNREGISTER: - /* A device has gone down - kill any data we hold for it. */ - edev = dev->ec_ptr; - if (edev) { - if (net2dev_map[0] == dev) - net2dev_map[0] = NULL; - net2dev_map[edev->net] = NULL; - kfree(edev); - dev->ec_ptr = NULL; - } - break; - } - - return NOTIFY_DONE; -} - -static struct notifier_block econet_netdev_notifier = { - .notifier_call = econet_notifier, -}; - -static void __exit econet_proto_exit(void) -{ -#ifdef CONFIG_ECONET_AUNUDP - del_timer(&ab_cleanup_timer); - if (udpsock) - sock_release(udpsock); -#endif - unregister_netdevice_notifier(&econet_netdev_notifier); -#ifdef CONFIG_ECONET_NATIVE - dev_remove_pack(&econet_packet_type); -#endif - sock_unregister(econet_family_ops.family); - proto_unregister(&econet_proto); -} - -static int __init econet_proto_init(void) -{ - int err = proto_register(&econet_proto, 0); - - if (err != 0) - goto out; - sock_register(&econet_family_ops); -#ifdef CONFIG_ECONET_AUNUDP - aun_udp_initialise(); -#endif -#ifdef CONFIG_ECONET_NATIVE - econet_hw_initialise(); -#endif - register_netdevice_notifier(&econet_netdev_notifier); -out: - return err; -} - -module_init(econet_proto_init); -module_exit(econet_proto_exit); - -MODULE_LICENSE("GPL"); -MODULE_ALIAS_NETPROTO(PF_ECONET); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index bf10a311cf1..36e58800a9e 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -77,7 +77,7 @@ __setup("ether=", netdev_boot_setup); */ int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, - const void *daddr, const void *saddr, unsigned len) + const void *daddr, const void *saddr, unsigned int len) { struct ethhdr *eth = (struct ethhdr *)skb_push(skb, ETH_HLEN); @@ -164,7 +164,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) eth = eth_hdr(skb); if (unlikely(is_multicast_ether_addr(eth->h_dest))) { - if (!compare_ether_addr_64bits(eth->h_dest, dev->broadcast)) + if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) skb->pkt_type = PACKET_BROADCAST; else skb->pkt_type = PACKET_MULTICAST; @@ -179,7 +179,8 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) */ else if (1 /*dev->flags&IFF_PROMISC */ ) { - if (unlikely(compare_ether_addr_64bits(eth->h_dest, dev->dev_addr))) + if (unlikely(!ether_addr_equal_64bits(eth->h_dest, + dev->dev_addr))) skb->pkt_type = PACKET_OTHERHOST; } diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c index 36851588536..32eb4179e8f 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan.c @@ -196,7 +196,7 @@ lowpan_compress_addr_64(u8 **hc06_ptr, u8 shift, const struct in6_addr *ipaddr, static void lowpan_uip_ds6_set_addr_iid(struct in6_addr *ipaddr, unsigned char *lladdr) { - memcpy(&ipaddr->s6_addr[8], lladdr, IEEE802154_ALEN); + memcpy(&ipaddr->s6_addr[8], lladdr, IEEE802154_ADDR_LEN); /* second bit-flip (Universe/Local) is done according RFC2464 */ ipaddr->s6_addr[8] ^= 0x02; } @@ -221,7 +221,7 @@ lowpan_uncompress_addr(struct sk_buff *skb, struct in6_addr *ipaddr, if (lladdr) lowpan_raw_dump_inline(__func__, "linklocal address", - lladdr, IEEE802154_ALEN); + lladdr, IEEE802154_ADDR_LEN); if (prefcount > 0) memcpy(ipaddr, prefix, prefcount); @@ -371,7 +371,7 @@ err: static int lowpan_header_create(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *_daddr, - const void *_saddr, unsigned len) + const void *_saddr, unsigned int len) { u8 tmp, iphc0, iphc1, *hc06_ptr; struct ipv6hdr *hdr; @@ -650,6 +650,53 @@ static void lowpan_fragment_timer_expired(unsigned long entry_addr) kfree(entry); } +static struct lowpan_fragment * +lowpan_alloc_new_frame(struct sk_buff *skb, u8 iphc0, u8 len, u8 tag) +{ + struct lowpan_fragment *frame; + + frame = kzalloc(sizeof(struct lowpan_fragment), + GFP_ATOMIC); + if (!frame) + goto frame_err; + + INIT_LIST_HEAD(&frame->list); + + frame->length = (iphc0 & 7) | (len << 3); + frame->tag = tag; + + /* allocate buffer for frame assembling */ + frame->skb = alloc_skb(frame->length + + sizeof(struct ipv6hdr), GFP_ATOMIC); + + if (!frame->skb) + goto skb_err; + + frame->skb->priority = skb->priority; + frame->skb->dev = skb->dev; + + /* reserve headroom for uncompressed ipv6 header */ + skb_reserve(frame->skb, sizeof(struct ipv6hdr)); + skb_put(frame->skb, frame->length); + + init_timer(&frame->timer); + /* time out is the same as for ipv6 - 60 sec */ + frame->timer.expires = jiffies + LOWPAN_FRAG_TIMEOUT; + frame->timer.data = (unsigned long)frame; + frame->timer.function = lowpan_fragment_timer_expired; + + add_timer(&frame->timer); + + list_add_tail(&frame->list, &lowpan_fragments); + + return frame; + +skb_err: + kfree(frame); +frame_err: + return NULL; +} + static int lowpan_process_data(struct sk_buff *skb) { @@ -692,41 +739,9 @@ lowpan_process_data(struct sk_buff *skb) /* alloc new frame structure */ if (!found) { - frame = kzalloc(sizeof(struct lowpan_fragment), - GFP_ATOMIC); + frame = lowpan_alloc_new_frame(skb, iphc0, len, tag); if (!frame) goto unlock_and_drop; - - INIT_LIST_HEAD(&frame->list); - - frame->length = (iphc0 & 7) | (len << 3); - frame->tag = tag; - - /* allocate buffer for frame assembling */ - frame->skb = alloc_skb(frame->length + - sizeof(struct ipv6hdr), GFP_ATOMIC); - - if (!frame->skb) { - kfree(frame); - goto unlock_and_drop; - } - - frame->skb->priority = skb->priority; - frame->skb->dev = skb->dev; - - /* reserve headroom for uncompressed ipv6 header */ - skb_reserve(frame->skb, sizeof(struct ipv6hdr)); - skb_put(frame->skb, frame->length); - - init_timer(&frame->timer); - /* time out is the same as for ipv6 - 60 sec */ - frame->timer.expires = jiffies + LOWPAN_FRAG_TIMEOUT; - frame->timer.data = (unsigned long)frame; - frame->timer.function = lowpan_fragment_timer_expired; - - add_timer(&frame->timer); - - list_add_tail(&frame->list, &lowpan_fragments); } if ((iphc0 & LOWPAN_DISPATCH_MASK) == LOWPAN_DISPATCH_FRAG1) @@ -1044,6 +1059,24 @@ static void lowpan_dev_free(struct net_device *dev) free_netdev(dev); } +static struct wpan_phy *lowpan_get_phy(const struct net_device *dev) +{ + struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; + return ieee802154_mlme_ops(real_dev)->get_phy(real_dev); +} + +static u16 lowpan_get_pan_id(const struct net_device *dev) +{ + struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; + return ieee802154_mlme_ops(real_dev)->get_pan_id(real_dev); +} + +static u16 lowpan_get_short_addr(const struct net_device *dev) +{ + struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; + return ieee802154_mlme_ops(real_dev)->get_short_addr(real_dev); +} + static struct header_ops lowpan_header_ops = { .create = lowpan_header_create, }; @@ -1053,6 +1086,12 @@ static const struct net_device_ops lowpan_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, }; +static struct ieee802154_mlme_ops lowpan_mlme = { + .get_pan_id = lowpan_get_pan_id, + .get_phy = lowpan_get_phy, + .get_short_addr = lowpan_get_short_addr, +}; + static void lowpan_setup(struct net_device *dev) { pr_debug("(%s)\n", __func__); @@ -1070,6 +1109,7 @@ static void lowpan_setup(struct net_device *dev) dev->netdev_ops = &lowpan_netdev_ops; dev->header_ops = &lowpan_header_ops; + dev->ml_priv = &lowpan_mlme; dev->destructor = lowpan_dev_free; } @@ -1143,6 +1183,8 @@ static int lowpan_newlink(struct net *src_net, struct net_device *dev, list_add_tail(&entry->list, &lowpan_devices); mutex_unlock(&lowpan_dev_info(dev)->dev_list_mtx); + spin_lock_init(&flist_lock); + register_netdevice(dev); return 0; @@ -1152,11 +1194,20 @@ static void lowpan_dellink(struct net_device *dev, struct list_head *head) { struct lowpan_dev_info *lowpan_dev = lowpan_dev_info(dev); struct net_device *real_dev = lowpan_dev->real_dev; - struct lowpan_dev_record *entry; - struct lowpan_dev_record *tmp; + struct lowpan_dev_record *entry, *tmp; + struct lowpan_fragment *frame, *tframe; ASSERT_RTNL(); + spin_lock(&flist_lock); + list_for_each_entry_safe(frame, tframe, &lowpan_fragments, list) { + del_timer(&frame->timer); + list_del(&frame->list); + dev_kfree_skb(frame->skb); + kfree(frame); + } + spin_unlock(&flist_lock); + mutex_lock(&lowpan_dev_info(dev)->dev_list_mtx); list_for_each_entry_safe(entry, tmp, &lowpan_devices, list) { if (entry->ldev == dev) { diff --git a/net/ieee802154/6lowpan.h b/net/ieee802154/6lowpan.h index aeff3f31048..8c2251fb0a3 100644 --- a/net/ieee802154/6lowpan.h +++ b/net/ieee802154/6lowpan.h @@ -53,9 +53,6 @@ #ifndef __6LOWPAN_H__ #define __6LOWPAN_H__ -/* need to know address length to manipulate with it */ -#define IEEE802154_ALEN 8 - #define UIP_802154_SHORTADDR_LEN 2 /* compressed ipv6 address length */ #define UIP_IPH_LEN 40 /* ipv6 fixed header size */ #define UIP_PROTO_UDP 17 /* ipv6 next header value for UDP */ diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index 1b09eaabaac..6fbb2ad7bb6 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -44,8 +44,8 @@ struct dgram_sock { struct ieee802154_addr src_addr; struct ieee802154_addr dst_addr; - unsigned bound:1; - unsigned want_ack:1; + unsigned int bound:1; + unsigned int want_ack:1; }; static inline struct dgram_sock *dgram_sk(const struct sock *sk) @@ -206,7 +206,7 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t size) { struct net_device *dev; - unsigned mtu; + unsigned int mtu; struct sk_buff *skb; struct dgram_sock *ro = dgram_sk(sk); int hlen, tlen; diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c index adaf4621490..ca92587720f 100644 --- a/net/ieee802154/nl-mac.c +++ b/net/ieee802154/nl-mac.c @@ -63,15 +63,14 @@ int ieee802154_nl_assoc_indic(struct net_device *dev, if (!msg) return -ENOBUFS; - NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); - NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); - NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, - dev->dev_addr); - - NLA_PUT(msg, IEEE802154_ATTR_SRC_HW_ADDR, IEEE802154_ADDR_LEN, - addr->hwaddr); - - NLA_PUT_U8(msg, IEEE802154_ATTR_CAPABILITY, cap); + if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || + nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || + nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, + dev->dev_addr) || + nla_put(msg, IEEE802154_ATTR_SRC_HW_ADDR, IEEE802154_ADDR_LEN, + addr->hwaddr) || + nla_put_u8(msg, IEEE802154_ATTR_CAPABILITY, cap)) + goto nla_put_failure; return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id); @@ -92,14 +91,13 @@ int ieee802154_nl_assoc_confirm(struct net_device *dev, u16 short_addr, if (!msg) return -ENOBUFS; - NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); - NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); - NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, - dev->dev_addr); - - NLA_PUT_U16(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr); - NLA_PUT_U8(msg, IEEE802154_ATTR_STATUS, status); - + if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || + nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || + nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, + dev->dev_addr) || + nla_put_u16(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr) || + nla_put_u8(msg, IEEE802154_ATTR_STATUS, status)) + goto nla_put_failure; return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id); nla_put_failure: @@ -119,20 +117,22 @@ int ieee802154_nl_disassoc_indic(struct net_device *dev, if (!msg) return -ENOBUFS; - NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); - NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); - NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, - dev->dev_addr); - - if (addr->addr_type == IEEE802154_ADDR_LONG) - NLA_PUT(msg, IEEE802154_ATTR_SRC_HW_ADDR, IEEE802154_ADDR_LEN, - addr->hwaddr); - else - NLA_PUT_U16(msg, IEEE802154_ATTR_SRC_SHORT_ADDR, - addr->short_addr); - - NLA_PUT_U8(msg, IEEE802154_ATTR_REASON, reason); - + if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || + nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || + nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, + dev->dev_addr)) + goto nla_put_failure; + if (addr->addr_type == IEEE802154_ADDR_LONG) { + if (nla_put(msg, IEEE802154_ATTR_SRC_HW_ADDR, IEEE802154_ADDR_LEN, + addr->hwaddr)) + goto nla_put_failure; + } else { + if (nla_put_u16(msg, IEEE802154_ATTR_SRC_SHORT_ADDR, + addr->short_addr)) + goto nla_put_failure; + } + if (nla_put_u8(msg, IEEE802154_ATTR_REASON, reason)) + goto nla_put_failure; return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id); nla_put_failure: @@ -151,13 +151,12 @@ int ieee802154_nl_disassoc_confirm(struct net_device *dev, u8 status) if (!msg) return -ENOBUFS; - NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); - NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); - NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, - dev->dev_addr); - - NLA_PUT_U8(msg, IEEE802154_ATTR_STATUS, status); - + if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || + nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || + nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, + dev->dev_addr) || + nla_put_u8(msg, IEEE802154_ATTR_STATUS, status)) + goto nla_put_failure; return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id); nla_put_failure: @@ -177,13 +176,13 @@ int ieee802154_nl_beacon_indic(struct net_device *dev, if (!msg) return -ENOBUFS; - NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); - NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); - NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, - dev->dev_addr); - NLA_PUT_U16(msg, IEEE802154_ATTR_COORD_SHORT_ADDR, coord_addr); - NLA_PUT_U16(msg, IEEE802154_ATTR_COORD_PAN_ID, panid); - + if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || + nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || + nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, + dev->dev_addr) || + nla_put_u16(msg, IEEE802154_ATTR_COORD_SHORT_ADDR, coord_addr) || + nla_put_u16(msg, IEEE802154_ATTR_COORD_PAN_ID, panid)) + goto nla_put_failure; return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id); nla_put_failure: @@ -204,19 +203,17 @@ int ieee802154_nl_scan_confirm(struct net_device *dev, if (!msg) return -ENOBUFS; - NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); - NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); - NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, - dev->dev_addr); - - NLA_PUT_U8(msg, IEEE802154_ATTR_STATUS, status); - NLA_PUT_U8(msg, IEEE802154_ATTR_SCAN_TYPE, scan_type); - NLA_PUT_U32(msg, IEEE802154_ATTR_CHANNELS, unscanned); - NLA_PUT_U8(msg, IEEE802154_ATTR_PAGE, page); - - if (edl) - NLA_PUT(msg, IEEE802154_ATTR_ED_LIST, 27, edl); - + if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || + nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || + nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, + dev->dev_addr) || + nla_put_u8(msg, IEEE802154_ATTR_STATUS, status) || + nla_put_u8(msg, IEEE802154_ATTR_SCAN_TYPE, scan_type) || + nla_put_u32(msg, IEEE802154_ATTR_CHANNELS, unscanned) || + nla_put_u8(msg, IEEE802154_ATTR_PAGE, page) || + (edl && + nla_put(msg, IEEE802154_ATTR_ED_LIST, 27, edl))) + goto nla_put_failure; return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id); nla_put_failure: @@ -235,13 +232,12 @@ int ieee802154_nl_start_confirm(struct net_device *dev, u8 status) if (!msg) return -ENOBUFS; - NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); - NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); - NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, - dev->dev_addr); - - NLA_PUT_U8(msg, IEEE802154_ATTR_STATUS, status); - + if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || + nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || + nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, + dev->dev_addr) || + nla_put_u8(msg, IEEE802154_ATTR_STATUS, status)) + goto nla_put_failure; return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id); nla_put_failure: @@ -266,16 +262,16 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 pid, phy = ieee802154_mlme_ops(dev)->get_phy(dev); BUG_ON(!phy); - NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); - NLA_PUT_STRING(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)); - NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); - - NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, - dev->dev_addr); - NLA_PUT_U16(msg, IEEE802154_ATTR_SHORT_ADDR, - ieee802154_mlme_ops(dev)->get_short_addr(dev)); - NLA_PUT_U16(msg, IEEE802154_ATTR_PAN_ID, - ieee802154_mlme_ops(dev)->get_pan_id(dev)); + if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || + nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) || + nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || + nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, + dev->dev_addr) || + nla_put_u16(msg, IEEE802154_ATTR_SHORT_ADDR, + ieee802154_mlme_ops(dev)->get_short_addr(dev)) || + nla_put_u16(msg, IEEE802154_ATTR_PAN_ID, + ieee802154_mlme_ops(dev)->get_pan_id(dev))) + goto nla_put_failure; wpan_phy_put(phy); return genlmsg_end(msg, hdr); diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index c64a38d57aa..eed291626da 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -53,18 +53,18 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 pid, goto out; mutex_lock(&phy->pib_lock); - NLA_PUT_STRING(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)); - - NLA_PUT_U8(msg, IEEE802154_ATTR_PAGE, phy->current_page); - NLA_PUT_U8(msg, IEEE802154_ATTR_CHANNEL, phy->current_channel); + if (nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) || + nla_put_u8(msg, IEEE802154_ATTR_PAGE, phy->current_page) || + nla_put_u8(msg, IEEE802154_ATTR_CHANNEL, phy->current_channel)) + goto nla_put_failure; for (i = 0; i < 32; i++) { if (phy->channels_supported[i]) buf[pages++] = phy->channels_supported[i] | (i << 27); } - if (pages) - NLA_PUT(msg, IEEE802154_ATTR_CHANNEL_PAGE_LIST, - pages * sizeof(uint32_t), buf); - + if (pages && + nla_put(msg, IEEE802154_ATTR_CHANNEL_PAGE_LIST, + pages * sizeof(uint32_t), buf)) + goto nla_put_failure; mutex_unlock(&phy->pib_lock); kfree(buf); return genlmsg_end(msg, hdr); @@ -179,6 +179,7 @@ static int ieee802154_add_iface(struct sk_buff *skb, const char *devname; int rc = -ENOBUFS; struct net_device *dev; + int type = __IEEE802154_DEV_INVALID; pr_debug("%s\n", __func__); @@ -221,7 +222,13 @@ static int ieee802154_add_iface(struct sk_buff *skb, goto nla_put_failure; } - dev = phy->add_iface(phy, devname); + if (info->attrs[IEEE802154_ATTR_DEV_TYPE]) { + type = nla_get_u8(info->attrs[IEEE802154_ATTR_DEV_TYPE]); + if (type >= __IEEE802154_DEV_MAX) + return -EINVAL; + } + + dev = phy->add_iface(phy, devname, type); if (IS_ERR(dev)) { rc = PTR_ERR(dev); goto nla_put_failure; @@ -245,9 +252,9 @@ static int ieee802154_add_iface(struct sk_buff *skb, goto dev_unregister; } - NLA_PUT_STRING(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)); - NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); - + if (nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) || + nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name)) + goto nla_put_failure; dev_put(dev); wpan_phy_put(phy); @@ -333,10 +340,9 @@ static int ieee802154_del_iface(struct sk_buff *skb, rtnl_unlock(); - - NLA_PUT_STRING(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)); - NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, name); - + if (nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) || + nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, name)) + goto nla_put_failure; wpan_phy_put(phy); return ieee802154_nl_reply(msg, info); diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c index f96bae8fd33..50e823927d4 100644 --- a/net/ieee802154/raw.c +++ b/net/ieee802154/raw.c @@ -106,7 +106,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t size) { struct net_device *dev; - unsigned mtu; + unsigned int mtu; struct sk_buff *skb; int hlen, tlen; int err; diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index d183262943d..20f1cb5c8ab 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -262,8 +262,8 @@ config ARPD bool "IP: ARP daemon support" ---help--- The kernel maintains an internal cache which maps IP addresses to - hardware addresses on the local network, so that Ethernet/Token Ring/ - etc. frames are sent to the proper address on the physical networking + hardware addresses on the local network, so that Ethernet + frames are sent to the proper address on the physical networking layer. Normally, kernel uses the ARP protocol to resolve these mappings. @@ -312,7 +312,7 @@ config SYN_COOKIES config INET_AH tristate "IP: AH transformation" - select XFRM + select XFRM_ALGO select CRYPTO select CRYPTO_HMAC select CRYPTO_MD5 @@ -324,7 +324,7 @@ config INET_AH config INET_ESP tristate "IP: ESP transformation" - select XFRM + select XFRM_ALGO select CRYPTO select CRYPTO_AUTHENC select CRYPTO_HMAC diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 10e3751466b..c8f7aee587d 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -350,7 +350,7 @@ lookup_protocol: err = 0; sk->sk_no_check = answer_no_check; if (INET_PROTOSW_REUSE & answer_flags) - sk->sk_reuse = 1; + sk->sk_reuse = SK_CAN_REUSE; inet = inet_sk(sk); inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; @@ -541,7 +541,7 @@ out: } EXPORT_SYMBOL(inet_bind); -int inet_dgram_connect(struct socket *sock, struct sockaddr * uaddr, +int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index fd508b52601..e8f2617ecd4 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -77,7 +77,7 @@ static inline struct scatterlist *ah_req_sg(struct crypto_ahash *ahash, static int ip_clear_mutable_options(const struct iphdr *iph, __be32 *daddr) { - unsigned char * optptr = (unsigned char*)(iph+1); + unsigned char *optptr = (unsigned char *)(iph+1); int l = iph->ihl*4 - sizeof(struct iphdr); int optlen; @@ -406,8 +406,8 @@ static void ah4_err(struct sk_buff *skb, u32 info) ah->spi, IPPROTO_AH, AF_INET); if (!x) return; - printk(KERN_DEBUG "pmtu discovery on SA AH/%08x/%08x\n", - ntohl(ah->spi), ntohl(iph->daddr)); + pr_debug("pmtu discovery on SA AH/%08x/%08x\n", + ntohl(ah->spi), ntohl(iph->daddr)); xfrm_state_put(x); } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 18d9b81ecb1..cda37be02f8 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -73,6 +73,8 @@ * Jesper D. Brouer: Proxy ARP PVLAN RFC 3069 support. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/types.h> #include <linux/string.h> @@ -89,7 +91,6 @@ #include <linux/etherdevice.h> #include <linux/fddidevice.h> #include <linux/if_arp.h> -#include <linux/trdevice.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> @@ -193,9 +194,6 @@ int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir) case ARPHRD_IEEE802: ip_eth_mc_map(addr, haddr); return 0; - case ARPHRD_IEEE802_TR: - ip_tr_mc_map(addr, haddr); - return 0; case ARPHRD_INFINIBAND: ip_ib_mc_map(addr, dev->broadcast, haddr); return 0; @@ -364,8 +362,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) probes -= neigh->parms->ucast_probes; if (probes < 0) { if (!(neigh->nud_state & NUD_VALID)) - printk(KERN_DEBUG - "trying to ucast probe in NUD_INVALID\n"); + pr_debug("trying to ucast probe in NUD_INVALID\n"); dst_ha = neigh->ha; read_lock_bh(&neigh->lock); } else { @@ -452,7 +449,7 @@ static int arp_set_predefined(int addr_hint, unsigned char *haddr, { switch (addr_hint) { case RTN_LOCAL: - printk(KERN_DEBUG "ARP: arp called for own IP address\n"); + pr_debug("arp called for own IP address\n"); memcpy(haddr, dev->dev_addr, dev->addr_len); return 1; case RTN_MULTICAST: @@ -473,7 +470,7 @@ int arp_find(unsigned char *haddr, struct sk_buff *skb) struct neighbour *n; if (!skb_dst(skb)) { - printk(KERN_DEBUG "arp_find is called with dst==NULL\n"); + pr_debug("arp_find is called with dst==NULL\n"); kfree_skb(skb); return 1; } @@ -648,12 +645,6 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, arp->ar_pro = htons(ETH_P_IP); break; #endif -#if IS_ENABLED(CONFIG_TR) - case ARPHRD_IEEE802_TR: - arp->ar_hrd = htons(ARPHRD_IEEE802); - arp->ar_pro = htons(ETH_P_IP); - break; -#endif } arp->ar_hln = dev->addr_len; @@ -751,11 +742,10 @@ static int arp_process(struct sk_buff *skb) goto out; break; case ARPHRD_ETHER: - case ARPHRD_IEEE802_TR: case ARPHRD_FDDI: case ARPHRD_IEEE802: /* - * ETHERNET, Token Ring and Fibre Channel (which are IEEE 802 + * ETHERNET, and Fibre Channel (which are IEEE 802 * devices, according to RFC 2625) devices will accept ARP * hardware types of either 1 (Ethernet) or 6 (IEEE 802.2). * This is the case also of FDDI, where the RFC 1390 says that @@ -1059,7 +1049,7 @@ static int arp_req_set(struct net *net, struct arpreq *r, neigh = __neigh_lookup_errno(&arp_tbl, &ip, dev); err = PTR_ERR(neigh); if (!IS_ERR(neigh)) { - unsigned state = NUD_STALE; + unsigned int state = NUD_STALE; if (r->arp_flags & ATF_PERM) state = NUD_PERMANENT; err = neigh_update(neigh, (r->arp_flags & ATF_COM) ? @@ -1071,7 +1061,7 @@ static int arp_req_set(struct net *net, struct arpreq *r, return err; } -static unsigned arp_state_to_flags(struct neighbour *neigh) +static unsigned int arp_state_to_flags(struct neighbour *neigh) { if (neigh->nud_state&NUD_PERMANENT) return ATF_PERM | ATF_COM; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 6e447ff94df..10e15a144e9 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -217,8 +217,7 @@ void in_dev_finish_destroy(struct in_device *idev) WARN_ON(idev->ifa_list); WARN_ON(idev->mc_list); #ifdef NET_REFCNT_DEBUG - printk(KERN_DEBUG "in_dev_finish_destroy: %p=%s\n", - idev, dev ? dev->name : "NIL"); + pr_debug("%s: %p=%s\n", __func__, idev, dev ? dev->name : "NIL"); #endif dev_put(dev); if (!idev->dead) @@ -1125,7 +1124,7 @@ skip: } } -static inline bool inetdev_valid_mtu(unsigned mtu) +static inline bool inetdev_valid_mtu(unsigned int mtu) { return mtu >= 68; } @@ -1174,7 +1173,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, switch (event) { case NETDEV_REGISTER: - printk(KERN_DEBUG "inetdev_event: bug\n"); + pr_debug("%s: bug\n", __func__); RCU_INIT_POINTER(dev->ip_ptr, NULL); break; case NETDEV_UP: @@ -1266,17 +1265,15 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; - if (ifa->ifa_address) - NLA_PUT_BE32(skb, IFA_ADDRESS, ifa->ifa_address); - - if (ifa->ifa_local) - NLA_PUT_BE32(skb, IFA_LOCAL, ifa->ifa_local); - - if (ifa->ifa_broadcast) - NLA_PUT_BE32(skb, IFA_BROADCAST, ifa->ifa_broadcast); - - if (ifa->ifa_label[0]) - NLA_PUT_STRING(skb, IFA_LABEL, ifa->ifa_label); + if ((ifa->ifa_address && + nla_put_be32(skb, IFA_ADDRESS, ifa->ifa_address)) || + (ifa->ifa_local && + nla_put_be32(skb, IFA_LOCAL, ifa->ifa_local)) || + (ifa->ifa_broadcast && + nla_put_be32(skb, IFA_BROADCAST, ifa->ifa_broadcast)) || + (ifa->ifa_label[0] && + nla_put_string(skb, IFA_LABEL, ifa->ifa_label))) + goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -1587,7 +1584,6 @@ static int ipv4_doint_and_flush(ctl_table *ctl, int write, static struct devinet_sysctl_table { struct ctl_table_header *sysctl_header; struct ctl_table devinet_vars[__IPV4_DEVCONF_MAX]; - char *dev_name; } devinet_sysctl = { .devinet_vars = { DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding", @@ -1629,16 +1625,7 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name, { int i; struct devinet_sysctl_table *t; - -#define DEVINET_CTL_PATH_DEV 3 - - struct ctl_path devinet_ctl_path[] = { - { .procname = "net", }, - { .procname = "ipv4", }, - { .procname = "conf", }, - { /* to be set */ }, - { }, - }; + char path[sizeof("net/ipv4/conf/") + IFNAMSIZ]; t = kmemdup(&devinet_sysctl, sizeof(*t), GFP_KERNEL); if (!t) @@ -1650,27 +1637,15 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name, t->devinet_vars[i].extra2 = net; } - /* - * Make a copy of dev_name, because '.procname' is regarded as const - * by sysctl and we wouldn't want anyone to change it under our feet - * (see SIOCSIFNAME). - */ - t->dev_name = kstrdup(dev_name, GFP_KERNEL); - if (!t->dev_name) - goto free; - - devinet_ctl_path[DEVINET_CTL_PATH_DEV].procname = t->dev_name; + snprintf(path, sizeof(path), "net/ipv4/conf/%s", dev_name); - t->sysctl_header = register_net_sysctl_table(net, devinet_ctl_path, - t->devinet_vars); + t->sysctl_header = register_net_sysctl(net, path, t->devinet_vars); if (!t->sysctl_header) - goto free_procname; + goto free; p->sysctl = t; return 0; -free_procname: - kfree(t->dev_name); free: kfree(t); out: @@ -1686,7 +1661,6 @@ static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf) cnf->sysctl = NULL; unregister_net_sysctl_table(t->sysctl_header); - kfree(t->dev_name); kfree(t); } @@ -1716,12 +1690,6 @@ static struct ctl_table ctl_forward_entry[] = { }, { }, }; - -static __net_initdata struct ctl_path net_ipv4_path[] = { - { .procname = "net", }, - { .procname = "ipv4", }, - { }, -}; #endif static __net_init int devinet_init_net(struct net *net) @@ -1767,7 +1735,7 @@ static __net_init int devinet_init_net(struct net *net) goto err_reg_dflt; err = -ENOMEM; - forw_hdr = register_net_sysctl_table(net, net_ipv4_path, tbl); + forw_hdr = register_net_sysctl(net, "net/ipv4", tbl); if (forw_hdr == NULL) goto err_reg_ctl; net->ipv4.forw_hdr = forw_hdr; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index cbe3a68507c..3854411fa37 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -136,13 +136,13 @@ static void fib_flush(struct net *net) * Find address type as if only "dev" was present in the system. If * on_dev is NULL then all interfaces are taken into consideration. */ -static inline unsigned __inet_dev_addr_type(struct net *net, - const struct net_device *dev, - __be32 addr) +static inline unsigned int __inet_dev_addr_type(struct net *net, + const struct net_device *dev, + __be32 addr) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res; - unsigned ret = RTN_BROADCAST; + unsigned int ret = RTN_BROADCAST; struct fib_table *local_table; if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) @@ -740,7 +740,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) #define BRD_OK 2 #define BRD0_OK 4 #define BRD1_OK 8 - unsigned ok = 0; + unsigned int ok = 0; int subnet = 0; /* Primary network */ int gone = 1; /* Address is missing */ int same_prefsrc = 0; /* Another primary with same IP */ diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 799fc790b3c..2d043f71ef7 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -221,15 +221,15 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb, frh->src_len = rule4->src_len; frh->tos = rule4->tos; - if (rule4->dst_len) - NLA_PUT_BE32(skb, FRA_DST, rule4->dst); - - if (rule4->src_len) - NLA_PUT_BE32(skb, FRA_SRC, rule4->src); - + if ((rule4->dst_len && + nla_put_be32(skb, FRA_DST, rule4->dst)) || + (rule4->src_len && + nla_put_be32(skb, FRA_SRC, rule4->src))) + goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID - if (rule4->tclassid) - NLA_PUT_U32(skb, FRA_FLOW, rule4->tclassid); + if (rule4->tclassid && + nla_put_u32(skb, FRA_FLOW, rule4->tclassid)) + goto nla_put_failure; #endif return 0; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 5063fa38ac7..a8bdf740543 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -931,33 +931,36 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, rtm->rtm_table = tb_id; else rtm->rtm_table = RT_TABLE_COMPAT; - NLA_PUT_U32(skb, RTA_TABLE, tb_id); + if (nla_put_u32(skb, RTA_TABLE, tb_id)) + goto nla_put_failure; rtm->rtm_type = type; rtm->rtm_flags = fi->fib_flags; rtm->rtm_scope = fi->fib_scope; rtm->rtm_protocol = fi->fib_protocol; - if (rtm->rtm_dst_len) - NLA_PUT_BE32(skb, RTA_DST, dst); - - if (fi->fib_priority) - NLA_PUT_U32(skb, RTA_PRIORITY, fi->fib_priority); - + if (rtm->rtm_dst_len && + nla_put_be32(skb, RTA_DST, dst)) + goto nla_put_failure; + if (fi->fib_priority && + nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority)) + goto nla_put_failure; if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0) goto nla_put_failure; - if (fi->fib_prefsrc) - NLA_PUT_BE32(skb, RTA_PREFSRC, fi->fib_prefsrc); - + if (fi->fib_prefsrc && + nla_put_be32(skb, RTA_PREFSRC, fi->fib_prefsrc)) + goto nla_put_failure; if (fi->fib_nhs == 1) { - if (fi->fib_nh->nh_gw) - NLA_PUT_BE32(skb, RTA_GATEWAY, fi->fib_nh->nh_gw); - - if (fi->fib_nh->nh_oif) - NLA_PUT_U32(skb, RTA_OIF, fi->fib_nh->nh_oif); + if (fi->fib_nh->nh_gw && + nla_put_be32(skb, RTA_GATEWAY, fi->fib_nh->nh_gw)) + goto nla_put_failure; + if (fi->fib_nh->nh_oif && + nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif)) + goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID - if (fi->fib_nh[0].nh_tclassid) - NLA_PUT_U32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid); + if (fi->fib_nh[0].nh_tclassid && + nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid)) + goto nla_put_failure; #endif } #ifdef CONFIG_IP_ROUTE_MULTIPATH @@ -978,11 +981,13 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, rtnh->rtnh_hops = nh->nh_weight - 1; rtnh->rtnh_ifindex = nh->nh_oif; - if (nh->nh_gw) - NLA_PUT_BE32(skb, RTA_GATEWAY, nh->nh_gw); + if (nh->nh_gw && + nla_put_be32(skb, RTA_GATEWAY, nh->nh_gw)) + goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID - if (nh->nh_tclassid) - NLA_PUT_U32(skb, RTA_FLOW, nh->nh_tclassid); + if (nh->nh_tclassid && + nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) + goto nla_put_failure; #endif /* length of rtnetlink header + attributes */ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index bce36f1a37b..30b88d7b4bd 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1370,6 +1370,8 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l, if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos) continue; + if (fi->fib_dead) + continue; if (fa->fa_info->fib_scope < flp->flowi4_scope) continue; fib_alias_accessed(fa); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 2cb2bf84564..c75efbdc71c 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -713,11 +713,10 @@ static void icmp_unreach(struct sk_buff *skb) if (!net->ipv4.sysctl_icmp_ignore_bogus_error_responses && inet_addr_type(net, iph->daddr) == RTN_BROADCAST) { - if (net_ratelimit()) - pr_warn("%pI4 sent an invalid ICMP type %u, code %u error to a broadcast: %pI4 on %s\n", - &ip_hdr(skb)->saddr, - icmph->type, icmph->code, - &iph->daddr, skb->dev->name); + net_warn_ratelimited("%pI4 sent an invalid ICMP type %u, code %u error to a broadcast: %pI4 on %s\n", + &ip_hdr(skb)->saddr, + icmph->type, icmph->code, + &iph->daddr, skb->dev->name); goto out; } @@ -906,8 +905,7 @@ out_err: static void icmp_address(struct sk_buff *skb) { #if 0 - if (net_ratelimit()) - printk(KERN_DEBUG "a guy asks for address mask. Who is it?\n"); + net_dbg_ratelimited("a guy asks for address mask. Who is it?\n"); #endif } @@ -943,10 +941,10 @@ static void icmp_address_reply(struct sk_buff *skb) inet_ifa_match(ip_hdr(skb)->saddr, ifa)) break; } - if (!ifa && net_ratelimit()) { - pr_info("Wrong address mask %pI4 from %s/%pI4\n", - mp, dev->name, &ip_hdr(skb)->saddr); - } + if (!ifa) + net_info_ratelimited("Wrong address mask %pI4 from %s/%pI4\n", + mp, + dev->name, &ip_hdr(skb)->saddr); } } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 5dfecfd7d5e..6699f23e6f5 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -344,10 +344,10 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ ip_select_ident(pip, &rt->dst, NULL); - ((u8*)&pip[1])[0] = IPOPT_RA; - ((u8*)&pip[1])[1] = 4; - ((u8*)&pip[1])[2] = 0; - ((u8*)&pip[1])[3] = 0; + ((u8 *)&pip[1])[0] = IPOPT_RA; + ((u8 *)&pip[1])[1] = 4; + ((u8 *)&pip[1])[2] = 0; + ((u8 *)&pip[1])[3] = 0; skb->transport_header = skb->network_header + sizeof(struct iphdr) + 4; skb_put(skb, sizeof(*pig)); @@ -688,10 +688,10 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; ip_select_ident(iph, &rt->dst, NULL); - ((u8*)&iph[1])[0] = IPOPT_RA; - ((u8*)&iph[1])[1] = 4; - ((u8*)&iph[1])[2] = 0; - ((u8*)&iph[1])[3] = 0; + ((u8 *)&iph[1])[0] = IPOPT_RA; + ((u8 *)&iph[1])[1] = 4; + ((u8 *)&iph[1])[2] = 0; + ((u8 *)&iph[1])[3] = 0; ih = (struct igmphdr *)skb_put(skb, sizeof(struct igmphdr)); ih->type = type; @@ -774,7 +774,7 @@ static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) if (psf->sf_count[MCAST_INCLUDE] || pmc->sfcount[MCAST_EXCLUDE] != psf->sf_count[MCAST_EXCLUDE]) - continue; + break; if (srcs[i] == psf->sf_inaddr) { scount++; break; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 19d66cefd7d..95e61596e60 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -42,7 +42,8 @@ EXPORT_SYMBOL(sysctl_local_reserved_ports); void inet_get_local_port_range(int *low, int *high) { - unsigned seq; + unsigned int seq; + do { seq = read_seqbegin(&sysctl_local_ports.lock); @@ -53,7 +54,7 @@ void inet_get_local_port_range(int *low, int *high) EXPORT_SYMBOL(inet_get_local_port_range); int inet_csk_bind_conflict(const struct sock *sk, - const struct inet_bind_bucket *tb) + const struct inet_bind_bucket *tb, bool relax) { struct sock *sk2; struct hlist_node *node; @@ -79,6 +80,14 @@ int inet_csk_bind_conflict(const struct sock *sk, sk2_rcv_saddr == sk_rcv_saddr(sk)) break; } + if (!relax && reuse && sk2->sk_reuse && + sk2->sk_state != TCP_LISTEN) { + const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2); + + if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) || + sk2_rcv_saddr == sk_rcv_saddr(sk)) + break; + } } } return node != NULL; @@ -122,12 +131,13 @@ again: (tb->num_owners < smallest_size || smallest_size == -1)) { smallest_size = tb->num_owners; smallest_rover = rover; - if (atomic_read(&hashinfo->bsockets) > (high - low) + 1) { + if (atomic_read(&hashinfo->bsockets) > (high - low) + 1 && + !inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false)) { snum = smallest_rover; goto tb_found; } } - if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) { + if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false)) { snum = rover; goto tb_found; } @@ -172,18 +182,22 @@ have_snum: goto tb_not_found; tb_found: if (!hlist_empty(&tb->owners)) { + if (sk->sk_reuse == SK_FORCE_REUSE) + goto success; + if (tb->fastreuse > 0 && sk->sk_reuse && sk->sk_state != TCP_LISTEN && smallest_size == -1) { goto success; } else { ret = 1; - if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) { + if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true)) { if (sk->sk_reuse && sk->sk_state != TCP_LISTEN && smallest_size != -1 && --attempts >= 0) { spin_unlock(&head->lock); goto again; } + goto fail_unlock; } } @@ -514,7 +528,7 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. - * If synack was not acknowledged for 3 seconds, it means + * If synack was not acknowledged for 1 second, it means * one of the following things: synack was lost, ack was lost, * rtt is high or nobody planned to ack (i.e. synflood). * When server is a bit loaded, queue is populated with old @@ -555,8 +569,7 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, syn_ack_recalc(req, thresh, max_retries, queue->rskq_defer_accept, &expire, &resend); - if (req->rsk_ops->syn_ack_timeout) - req->rsk_ops->syn_ack_timeout(parent, req); + req->rsk_ops->syn_ack_timeout(parent, req); if (!expire && (!resend || !req->rsk_ops->rtx_syn_ack(parent, req, NULL) || diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 8d25a1c557e..46d1e7199a8 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -141,7 +141,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, goto rtattr_failure; if (icsk == NULL) { - r->idiag_rqueue = r->idiag_wqueue = 0; + handler->idiag_get_info(sk, r, NULL); goto out; } @@ -999,12 +999,12 @@ static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) return inet_diag_get_exact(skb, h, (struct inet_diag_req_v2 *)NLMSG_DATA(h)); } -static struct sock_diag_handler inet_diag_handler = { +static const struct sock_diag_handler inet_diag_handler = { .family = AF_INET, .dump = inet_diag_handler_dump, }; -static struct sock_diag_handler inet6_diag_handler = { +static const struct sock_diag_handler inet6_diag_handler = { .family = AF_INET6, .dump = inet_diag_handler_dump, }; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 984ec656b03..7880af97020 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -217,7 +217,7 @@ begin: } EXPORT_SYMBOL_GPL(__inet_lookup_listener); -struct sock * __inet_lookup_established(struct net *net, +struct sock *__inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 hnum, diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 89168c6351f..2784db3155f 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -89,8 +89,8 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw, #ifdef SOCK_REFCNT_DEBUG if (atomic_read(&tw->tw_refcnt) != 1) { - printk(KERN_DEBUG "%s timewait_sock %p refcnt=%d\n", - tw->tw_prot->name, tw, atomic_read(&tw->tw_refcnt)); + pr_debug("%s timewait_sock %p refcnt=%d\n", + tw->tw_prot->name, tw, atomic_read(&tw->tw_refcnt)); } #endif while (refcnt) { @@ -263,7 +263,7 @@ rescan: void inet_twdr_hangman(unsigned long data) { struct inet_timewait_death_row *twdr; - int unsigned need_timer; + unsigned int need_timer; twdr = (struct inet_timewait_death_row *)data; spin_lock(&twdr->death_lock); diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 29a07b6c716..e5c44fc586a 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -41,7 +41,7 @@ static int ip_forward_finish(struct sk_buff *skb) { - struct ip_options * opt = &(IPCB(skb)->opt); + struct ip_options *opt = &(IPCB(skb)->opt); IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); @@ -55,7 +55,7 @@ int ip_forward(struct sk_buff *skb) { struct iphdr *iph; /* Our header */ struct rtable *rt; /* Route we use */ - struct ip_options * opt = &(IPCB(skb)->opt); + struct ip_options *opt = &(IPCB(skb)->opt); if (skb_warn_if_lro(skb)) goto drop; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 3727e234c88..9dbd3dd6022 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -148,17 +148,17 @@ static unsigned int ip4_hashfn(struct inet_frag_queue *q) return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol); } -static int ip4_frag_match(struct inet_frag_queue *q, void *a) +static bool ip4_frag_match(struct inet_frag_queue *q, void *a) { struct ipq *qp; struct ip4_create_arg *arg = a; qp = container_of(q, struct ipq, q); return qp->id == arg->iph->id && - qp->saddr == arg->iph->saddr && - qp->daddr == arg->iph->daddr && - qp->protocol == arg->iph->protocol && - qp->user == arg->user; + qp->saddr == arg->iph->saddr && + qp->daddr == arg->iph->daddr && + qp->protocol == arg->iph->protocol && + qp->user == arg->user; } /* Memory Tracking Functions. */ @@ -545,6 +545,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, int len; int ihlen; int err; + int sum_truesize; u8 ecn; ipq_kill(qp); @@ -569,7 +570,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, skb_morph(head, qp->q.fragments); head->next = qp->q.fragments->next; - kfree_skb(qp->q.fragments); + consume_skb(qp->q.fragments); qp->q.fragments = head; } @@ -611,19 +612,32 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, atomic_add(clone->truesize, &qp->q.net->mem); } - skb_shinfo(head)->frag_list = head->next; skb_push(head, head->data - skb_network_header(head)); - for (fp=head->next; fp; fp = fp->next) { - head->data_len += fp->len; - head->len += fp->len; + sum_truesize = head->truesize; + for (fp = head->next; fp;) { + bool headstolen; + int delta; + struct sk_buff *next = fp->next; + + sum_truesize += fp->truesize; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); - head->truesize += fp->truesize; + + if (skb_try_coalesce(head, fp, &headstolen, &delta)) { + kfree_skb_partial(fp, headstolen); + } else { + if (!skb_shinfo(head)->frag_list) + skb_shinfo(head)->frag_list = fp; + head->data_len += fp->len; + head->len += fp->len; + head->truesize += fp->truesize; + } + fp = next; } - atomic_sub(head->truesize, &qp->q.net->mem); + atomic_sub(sum_truesize, &qp->q.net->mem); head->next = NULL; head->dev = dev; @@ -644,8 +658,7 @@ out_nomem: err = -ENOMEM; goto out_fail; out_oversize: - if (net_ratelimit()) - pr_info("Oversized IP packet from %pI4\n", &qp->saddr); + net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr); out_fail: IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS); return err; @@ -782,7 +795,7 @@ static int __net_init ip4_frags_ns_ctl_register(struct net *net) table[2].data = &net->ipv4.frags.timeout; } - hdr = register_net_sysctl_table(net, net_ipv4_ctl_path, table); + hdr = register_net_sysctl(net, "net/ipv4", table); if (hdr == NULL) goto err_reg; @@ -807,7 +820,7 @@ static void __net_exit ip4_frags_ns_ctl_unregister(struct net *net) static void ip4_frags_ctl_register(void) { - register_net_sysctl_rotable(net_ipv4_ctl_path, ip4_frags_ctl_table); + register_net_sysctl(&init_net, "net/ipv4", ip4_frags_ctl_table); } #else static inline int ip4_frags_ns_ctl_register(struct net *net) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index b57532d4742..f49047b7960 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -169,37 +169,56 @@ struct ipgre_net { /* often modified stats are per cpu, other are shared (netdev->stats) */ struct pcpu_tstats { - unsigned long rx_packets; - unsigned long rx_bytes; - unsigned long tx_packets; - unsigned long tx_bytes; -} __attribute__((aligned(4*sizeof(unsigned long)))); + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; + struct u64_stats_sync syncp; +}; -static struct net_device_stats *ipgre_get_stats(struct net_device *dev) +static struct rtnl_link_stats64 *ipgre_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *tot) { - struct pcpu_tstats sum = { 0 }; int i; for_each_possible_cpu(i) { const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); - - sum.rx_packets += tstats->rx_packets; - sum.rx_bytes += tstats->rx_bytes; - sum.tx_packets += tstats->tx_packets; - sum.tx_bytes += tstats->tx_bytes; + u64 rx_packets, rx_bytes, tx_packets, tx_bytes; + unsigned int start; + + do { + start = u64_stats_fetch_begin_bh(&tstats->syncp); + rx_packets = tstats->rx_packets; + tx_packets = tstats->tx_packets; + rx_bytes = tstats->rx_bytes; + tx_bytes = tstats->tx_bytes; + } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); + + tot->rx_packets += rx_packets; + tot->tx_packets += tx_packets; + tot->rx_bytes += rx_bytes; + tot->tx_bytes += tx_bytes; } - dev->stats.rx_packets = sum.rx_packets; - dev->stats.rx_bytes = sum.rx_bytes; - dev->stats.tx_packets = sum.tx_packets; - dev->stats.tx_bytes = sum.tx_bytes; - return &dev->stats; + + tot->multicast = dev->stats.multicast; + tot->rx_crc_errors = dev->stats.rx_crc_errors; + tot->rx_fifo_errors = dev->stats.rx_fifo_errors; + tot->rx_length_errors = dev->stats.rx_length_errors; + tot->rx_errors = dev->stats.rx_errors; + tot->tx_fifo_errors = dev->stats.tx_fifo_errors; + tot->tx_carrier_errors = dev->stats.tx_carrier_errors; + tot->tx_dropped = dev->stats.tx_dropped; + tot->tx_aborted_errors = dev->stats.tx_aborted_errors; + tot->tx_errors = dev->stats.tx_errors; + + return tot; } /* Given src, dst and key, find appropriate for input tunnel. */ -static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev, - __be32 remote, __be32 local, - __be32 key, __be16 gre_proto) +static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev, + __be32 remote, __be32 local, + __be32 key, __be16 gre_proto) { struct net *net = dev_net(dev); int link = dev->ifindex; @@ -464,7 +483,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info) */ const struct iphdr *iph = (const struct iphdr *)skb->data; - __be16 *p = (__be16*)(skb->data+(iph->ihl<<2)); + __be16 *p = (__be16 *)(skb->data+(iph->ihl<<2)); int grehlen = (iph->ihl<<2) + 4; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; @@ -574,7 +593,7 @@ static int ipgre_rcv(struct sk_buff *skb) iph = ip_hdr(skb); h = skb->data; - flags = *(__be16*)h; + flags = *(__be16 *)h; if (flags&(GRE_CSUM|GRE_KEY|GRE_ROUTING|GRE_SEQ|GRE_VERSION)) { /* - Version must be 0. @@ -598,11 +617,11 @@ static int ipgre_rcv(struct sk_buff *skb) offset += 4; } if (flags&GRE_KEY) { - key = *(__be32*)(h + offset); + key = *(__be32 *)(h + offset); offset += 4; } if (flags&GRE_SEQ) { - seqno = ntohl(*(__be32*)(h + offset)); + seqno = ntohl(*(__be32 *)(h + offset)); offset += 4; } } @@ -672,8 +691,10 @@ static int ipgre_rcv(struct sk_buff *skb) } tstats = this_cpu_ptr(tunnel->dev->tstats); + u64_stats_update_begin(&tstats->syncp); tstats->rx_packets++; tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); __skb_tunnel_rx(skb, tunnel->dev); @@ -900,7 +921,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev htons(ETH_P_TEB) : skb->protocol; if (tunnel->parms.o_flags&(GRE_KEY|GRE_CSUM|GRE_SEQ)) { - __be32 *ptr = (__be32*)(((u8*)iph) + tunnel->hlen - 4); + __be32 *ptr = (__be32 *)(((u8 *)iph) + tunnel->hlen - 4); if (tunnel->parms.o_flags&GRE_SEQ) { ++tunnel->o_seqno; @@ -913,7 +934,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } if (tunnel->parms.o_flags&GRE_CSUM) { *ptr = 0; - *(__sum16*)ptr = ip_compute_csum((void*)(iph+1), skb->len - sizeof(struct iphdr)); + *(__sum16 *)ptr = ip_compute_csum((void *)(iph+1), skb->len - sizeof(struct iphdr)); } } @@ -1169,7 +1190,7 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, { struct ip_tunnel *t = netdev_priv(dev); struct iphdr *iph = (struct iphdr *)skb_push(skb, t->hlen); - __be16 *p = (__be16*)(iph+1); + __be16 *p = (__be16 *)(iph+1); memcpy(iph, &t->parms.iph, sizeof(struct iphdr)); p[0] = t->parms.o_flags; @@ -1253,7 +1274,7 @@ static const struct net_device_ops ipgre_netdev_ops = { .ndo_start_xmit = ipgre_tunnel_xmit, .ndo_do_ioctl = ipgre_tunnel_ioctl, .ndo_change_mtu = ipgre_tunnel_change_mtu, - .ndo_get_stats = ipgre_get_stats, + .ndo_get_stats64 = ipgre_get_stats64, }; static void ipgre_dev_free(struct net_device *dev) @@ -1507,7 +1528,7 @@ static const struct net_device_ops ipgre_tap_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ipgre_tunnel_change_mtu, - .ndo_get_stats = ipgre_get_stats, + .ndo_get_stats64 = ipgre_get_stats64, }; static void ipgre_tap_setup(struct net_device *dev) @@ -1654,17 +1675,18 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm *p = &t->parms; - NLA_PUT_U32(skb, IFLA_GRE_LINK, p->link); - NLA_PUT_BE16(skb, IFLA_GRE_IFLAGS, p->i_flags); - NLA_PUT_BE16(skb, IFLA_GRE_OFLAGS, p->o_flags); - NLA_PUT_BE32(skb, IFLA_GRE_IKEY, p->i_key); - NLA_PUT_BE32(skb, IFLA_GRE_OKEY, p->o_key); - NLA_PUT_BE32(skb, IFLA_GRE_LOCAL, p->iph.saddr); - NLA_PUT_BE32(skb, IFLA_GRE_REMOTE, p->iph.daddr); - NLA_PUT_U8(skb, IFLA_GRE_TTL, p->iph.ttl); - NLA_PUT_U8(skb, IFLA_GRE_TOS, p->iph.tos); - NLA_PUT_U8(skb, IFLA_GRE_PMTUDISC, !!(p->iph.frag_off & htons(IP_DF))); - + if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || + nla_put_be16(skb, IFLA_GRE_IFLAGS, p->i_flags) || + nla_put_be16(skb, IFLA_GRE_OFLAGS, p->o_flags) || + nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || + nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || + nla_put_be32(skb, IFLA_GRE_LOCAL, p->iph.saddr) || + nla_put_be32(skb, IFLA_GRE_REMOTE, p->iph.daddr) || + nla_put_u8(skb, IFLA_GRE_TTL, p->iph.ttl) || + nla_put_u8(skb, IFLA_GRE_TOS, p->iph.tos) || + nla_put_u8(skb, IFLA_GRE_PMTUDISC, + !!(p->iph.frag_off & htons(IP_DF)))) + goto nla_put_failure; return 0; nla_put_failure: diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 26eccc5bab1..8590144ca33 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -210,9 +210,8 @@ static int ip_local_deliver_finish(struct sk_buff *skb) int ret; if (!net_eq(net, &init_net) && !ipprot->netns_ok) { - if (net_ratelimit()) - printk("%s: proto %d isn't netns-ready\n", - __func__, protocol); + net_info_ratelimited("%s: proto %d isn't netns-ready\n", + __func__, protocol); kfree_skb(skb); goto out; } @@ -298,10 +297,10 @@ static inline bool ip_rcv_options(struct sk_buff *skb) if (in_dev) { if (!IN_DEV_SOURCE_ROUTE(in_dev)) { - if (IN_DEV_LOG_MARTIANS(in_dev) && - net_ratelimit()) - pr_info("source route option %pI4 -> %pI4\n", - &iph->saddr, &iph->daddr); + if (IN_DEV_LOG_MARTIANS(in_dev)) + net_info_ratelimited("source route option %pI4 -> %pI4\n", + &iph->saddr, + &iph->daddr); goto drop; } } diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index a0d0d9d9b87..708b99494e2 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -210,10 +210,10 @@ int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb) * Simple and stupid 8), but the most efficient way. */ -void ip_options_fragment(struct sk_buff * skb) +void ip_options_fragment(struct sk_buff *skb) { unsigned char *optptr = skb_network_header(skb) + sizeof(struct iphdr); - struct ip_options * opt = &(IPCB(skb)->opt); + struct ip_options *opt = &(IPCB(skb)->opt); int l = opt->optlen; int optlen; @@ -248,13 +248,13 @@ void ip_options_fragment(struct sk_buff * skb) */ int ip_options_compile(struct net *net, - struct ip_options * opt, struct sk_buff * skb) + struct ip_options *opt, struct sk_buff *skb) { int l; - unsigned char * iph; - unsigned char * optptr; + unsigned char *iph; + unsigned char *optptr; int optlen; - unsigned char * pp_ptr = NULL; + unsigned char *pp_ptr = NULL; struct rtable *rt = NULL; if (skb != NULL) { @@ -413,7 +413,7 @@ int ip_options_compile(struct net *net, opt->is_changed = 1; } } else { - unsigned overflow = optptr[3]>>4; + unsigned int overflow = optptr[3]>>4; if (overflow == 15) { pp_ptr = optptr + 3; goto error; @@ -473,20 +473,20 @@ EXPORT_SYMBOL(ip_options_compile); * Undo all the changes done by ip_options_compile(). */ -void ip_options_undo(struct ip_options * opt) +void ip_options_undo(struct ip_options *opt) { if (opt->srr) { - unsigned char * optptr = opt->__data+opt->srr-sizeof(struct iphdr); + unsigned char *optptr = opt->__data+opt->srr-sizeof(struct iphdr); memmove(optptr+7, optptr+3, optptr[1]-7); memcpy(optptr+3, &opt->faddr, 4); } if (opt->rr_needaddr) { - unsigned char * optptr = opt->__data+opt->rr-sizeof(struct iphdr); + unsigned char *optptr = opt->__data+opt->rr-sizeof(struct iphdr); optptr[2] -= 4; memset(&optptr[optptr[2]-1], 0, 4); } if (opt->ts) { - unsigned char * optptr = opt->__data+opt->ts-sizeof(struct iphdr); + unsigned char *optptr = opt->__data+opt->ts-sizeof(struct iphdr); if (opt->ts_needtime) { optptr[2] -= 4; memset(&optptr[optptr[2]-1], 0, 4); @@ -549,8 +549,8 @@ int ip_options_get(struct net *net, struct ip_options_rcu **optp, void ip_forward_options(struct sk_buff *skb) { - struct ip_options * opt = &(IPCB(skb)->opt); - unsigned char * optptr; + struct ip_options *opt = &(IPCB(skb)->opt); + unsigned char *optptr; struct rtable *rt = skb_rtable(skb); unsigned char *raw = skb_network_header(skb); @@ -578,8 +578,10 @@ void ip_forward_options(struct sk_buff *skb) ip_hdr(skb)->daddr = opt->nexthop; ip_rt_get_source(&optptr[srrptr-1], skb, rt); optptr[2] = srrptr+4; - } else if (net_ratelimit()) - pr_crit("%s(): Argh! Destination lost!\n", __func__); + } else { + net_crit_ratelimited("%s(): Argh! Destination lost!\n", + __func__); + } if (opt->ts_needaddr) { optptr = raw + opt->ts; ip_rt_get_source(&optptr[optptr[2]-9], skb, rt); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 4910176d24e..451f97c42eb 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -214,8 +214,8 @@ static inline int ip_finish_output2(struct sk_buff *skb) } rcu_read_unlock(); - if (net_ratelimit()) - printk(KERN_DEBUG "ip_finish_output2: No header cache and no neighbour!\n"); + net_dbg_ratelimited("%s: No header cache and no neighbour!\n", + __func__); kfree_skb(skb); return -EINVAL; } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 2fd0fba7712..0d11f234d61 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -90,7 +90,7 @@ static void ip_cmsg_recv_opts(struct msghdr *msg, struct sk_buff *skb) static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb) { unsigned char optbuf[sizeof(struct ip_options) + 40]; - struct ip_options * opt = (struct ip_options *)optbuf; + struct ip_options *opt = (struct ip_options *)optbuf; if (IPCB(skb)->opt.optlen == 0) return; @@ -147,7 +147,7 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) { struct inet_sock *inet = inet_sk(skb->sk); - unsigned flags = inet->cmsg_flags; + unsigned int flags = inet->cmsg_flags; /* Ordered by supposed usage frequency */ if (flags & 1) @@ -673,10 +673,15 @@ static int do_ip_setsockopt(struct sock *sk, int level, break; } else { memset(&mreq, 0, sizeof(mreq)); - if (optlen >= sizeof(struct in_addr) && - copy_from_user(&mreq.imr_address, optval, - sizeof(struct in_addr))) - break; + if (optlen >= sizeof(struct ip_mreq)) { + if (copy_from_user(&mreq, optval, + sizeof(struct ip_mreq))) + break; + } else if (optlen >= sizeof(struct in_addr)) { + if (copy_from_user(&mreq.imr_address, optval, + sizeof(struct in_addr))) + break; + } } if (!mreq.imr_ifindex) { @@ -1094,7 +1099,7 @@ EXPORT_SYMBOL(compat_ip_setsockopt); */ static int do_ip_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen, unsigned flags) + char __user *optval, int __user *optlen, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); int val; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 92ac7e7363a..67e8a6b086e 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -808,8 +808,6 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d b->op = BOOTP_REQUEST; if (dev->type < 256) /* check for false types */ b->htype = dev->type; - else if (dev->type == ARPHRD_IEEE802_TR) /* fix for token ring */ - b->htype = ARPHRD_IEEE802; else if (dev->type == ARPHRD_FDDI) b->htype = ARPHRD_ETHER; else { @@ -955,8 +953,7 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str /* Fragments are not supported */ if (ip_is_fragment(h)) { - if (net_ratelimit()) - pr_err("DHCP/BOOTP: Ignoring fragmented reply\n"); + net_err_ratelimited("DHCP/BOOTP: Ignoring fragmented reply\n"); goto drop; } @@ -1004,16 +1001,14 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str /* Is it a reply to our BOOTP request? */ if (b->op != BOOTP_REPLY || b->xid != d->xid) { - if (net_ratelimit()) - pr_err("DHCP/BOOTP: Reply not for us, op[%x] xid[%x]\n", - b->op, b->xid); + net_err_ratelimited("DHCP/BOOTP: Reply not for us, op[%x] xid[%x]\n", + b->op, b->xid); goto drop_unlock; } /* Is it a reply for the device we are configuring? */ if (b->xid != ic_dev_xid) { - if (net_ratelimit()) - pr_err("DHCP/BOOTP: Ignoring delayed packet\n"); + net_err_ratelimited("DHCP/BOOTP: Ignoring delayed packet\n"); goto drop_unlock; } @@ -1198,7 +1193,7 @@ static int __init ic_dynamic(void) d = ic_first_dev; retries = CONF_SEND_RETRIES; get_random_bytes(&timeout, sizeof(timeout)); - timeout = CONF_BASE_TIMEOUT + (timeout % (unsigned) CONF_TIMEOUT_RANDOM); + timeout = CONF_BASE_TIMEOUT + (timeout % (unsigned int) CONF_TIMEOUT_RANDOM); for (;;) { /* Track the device we are configuring */ ic_dev_xid = d->xid; @@ -1626,11 +1621,13 @@ static int __init ip_auto_config_setup(char *addrs) return 1; } +__setup("ip=", ip_auto_config_setup); static int __init nfsaddrs_config_setup(char *addrs) { return ip_auto_config_setup(addrs); } +__setup("nfsaddrs=", nfsaddrs_config_setup); static int __init vendor_class_identifier_setup(char *addrs) { @@ -1641,7 +1638,4 @@ static int __init vendor_class_identifier_setup(char *addrs) vendor_class_identifier); return 1; } - -__setup("ip=", ip_auto_config_setup); -__setup("nfsaddrs=", nfsaddrs_config_setup); __setup("dhcpclass=", vendor_class_identifier_setup); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index ae1413e3f2f..2d0f99bf61b 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -144,33 +144,48 @@ static void ipip_dev_free(struct net_device *dev); /* often modified stats are per cpu, other are shared (netdev->stats) */ struct pcpu_tstats { - unsigned long rx_packets; - unsigned long rx_bytes; - unsigned long tx_packets; - unsigned long tx_bytes; -} __attribute__((aligned(4*sizeof(unsigned long)))); + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; + struct u64_stats_sync syncp; +}; -static struct net_device_stats *ipip_get_stats(struct net_device *dev) +static struct rtnl_link_stats64 *ipip_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *tot) { - struct pcpu_tstats sum = { 0 }; int i; for_each_possible_cpu(i) { const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); - - sum.rx_packets += tstats->rx_packets; - sum.rx_bytes += tstats->rx_bytes; - sum.tx_packets += tstats->tx_packets; - sum.tx_bytes += tstats->tx_bytes; + u64 rx_packets, rx_bytes, tx_packets, tx_bytes; + unsigned int start; + + do { + start = u64_stats_fetch_begin_bh(&tstats->syncp); + rx_packets = tstats->rx_packets; + tx_packets = tstats->tx_packets; + rx_bytes = tstats->rx_bytes; + tx_bytes = tstats->tx_bytes; + } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); + + tot->rx_packets += rx_packets; + tot->tx_packets += tx_packets; + tot->rx_bytes += rx_bytes; + tot->tx_bytes += tx_bytes; } - dev->stats.rx_packets = sum.rx_packets; - dev->stats.rx_bytes = sum.rx_bytes; - dev->stats.tx_packets = sum.tx_packets; - dev->stats.tx_bytes = sum.tx_bytes; - return &dev->stats; + + tot->tx_fifo_errors = dev->stats.tx_fifo_errors; + tot->tx_carrier_errors = dev->stats.tx_carrier_errors; + tot->tx_dropped = dev->stats.tx_dropped; + tot->tx_aborted_errors = dev->stats.tx_aborted_errors; + tot->tx_errors = dev->stats.tx_errors; + tot->collisions = dev->stats.collisions; + + return tot; } -static struct ip_tunnel * ipip_tunnel_lookup(struct net *net, +static struct ip_tunnel *ipip_tunnel_lookup(struct net *net, __be32 remote, __be32 local) { unsigned int h0 = HASH(remote); @@ -245,7 +260,7 @@ static void ipip_tunnel_link(struct ipip_net *ipn, struct ip_tunnel *t) rcu_assign_pointer(*tp, t); } -static struct ip_tunnel * ipip_tunnel_locate(struct net *net, +static struct ip_tunnel *ipip_tunnel_locate(struct net *net, struct ip_tunnel_parm *parms, int create) { __be32 remote = parms->iph.daddr; @@ -404,8 +419,10 @@ static int ipip_rcv(struct sk_buff *skb) skb->pkt_type = PACKET_HOST; tstats = this_cpu_ptr(tunnel->dev->tstats); + u64_stats_update_begin(&tstats->syncp); tstats->rx_packets++; tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); __skb_tunnel_rx(skb, tunnel->dev); @@ -730,7 +747,7 @@ static const struct net_device_ops ipip_netdev_ops = { .ndo_start_xmit = ipip_tunnel_xmit, .ndo_do_ioctl = ipip_tunnel_ioctl, .ndo_change_mtu = ipip_tunnel_change_mtu, - .ndo_get_stats = ipip_get_stats, + .ndo_get_stats64 = ipip_get_stats64, }; static void ipip_dev_free(struct net_device *dev) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 960fbfc3e97..a9e519ad6db 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -949,8 +949,7 @@ static int ipmr_cache_report(struct mr_table *mrt, ret = sock_queue_rcv_skb(mroute_sk, skb); rcu_read_unlock(); if (ret < 0) { - if (net_ratelimit()) - pr_warn("mroute: pending queue full, dropping entries\n"); + net_warn_ratelimited("mroute: pending queue full, dropping entries\n"); kfree_skb(skb); } @@ -2119,15 +2118,16 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, rtm->rtm_src_len = 32; rtm->rtm_tos = 0; rtm->rtm_table = mrt->id; - NLA_PUT_U32(skb, RTA_TABLE, mrt->id); + if (nla_put_u32(skb, RTA_TABLE, mrt->id)) + goto nla_put_failure; rtm->rtm_type = RTN_MULTICAST; rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = RTPROT_UNSPEC; rtm->rtm_flags = 0; - NLA_PUT_BE32(skb, RTA_SRC, c->mfc_origin); - NLA_PUT_BE32(skb, RTA_DST, c->mfc_mcastgrp); - + if (nla_put_be32(skb, RTA_SRC, c->mfc_origin) || + nla_put_be32(skb, RTA_DST, c->mfc_mcastgrp)) + goto nla_put_failure; if (__ipmr_fill_mroute(mrt, skb, c, rtm) < 0) goto nla_put_failure; diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 4f47e064e26..ed1b3678319 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -12,7 +12,7 @@ #include <net/netfilter/nf_queue.h> /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */ -int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) +int ip_route_me_harder(struct sk_buff *skb, unsigned int addr_type) { struct net *net = dev_net(skb_dst(skb)->dev); const struct iphdr *iph = ip_hdr(skb); @@ -237,13 +237,3 @@ static void ipv4_netfilter_fini(void) module_init(ipv4_netfilter_init); module_exit(ipv4_netfilter_fini); - -#ifdef CONFIG_SYSCTL -struct ctl_path nf_net_ipv4_netfilter_sysctl_path[] = { - { .procname = "net", }, - { .procname = "ipv4", }, - { .procname = "netfilter", }, - { } -}; -EXPORT_SYMBOL_GPL(nf_net_ipv4_netfilter_sysctl_path); -#endif /* CONFIG_SYSCTL */ diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 240b68469a7..c20674dc945 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -66,6 +66,3 @@ obj-$(CONFIG_IP_NF_ARP_MANGLE) += arpt_mangle.o # just filtering instance of ARP tables for now obj-$(CONFIG_IP_NF_ARPFILTER) += arptable_filter.o - -obj-$(CONFIG_IP_NF_QUEUE) += ip_queue.o - diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index fd7a3f68917..97e61eadf58 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -221,9 +221,8 @@ static inline int arp_checkentry(const struct arpt_arp *arp) static unsigned int arpt_error(struct sk_buff *skb, const struct xt_action_param *par) { - if (net_ratelimit()) - pr_err("arp_tables: error: '%s'\n", - (const char *)par->targinfo); + net_err_ratelimited("arp_tables: error: '%s'\n", + (const char *)par->targinfo); return NF_DROP; } @@ -303,7 +302,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, if (v < 0) { /* Pop from stack? */ if (v != XT_RETURN) { - verdict = (unsigned)(-v) - 1; + verdict = (unsigned int)(-v) - 1; break; } e = back; diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c deleted file mode 100644 index 94d45e1f888..00000000000 --- a/net/ipv4/netfilter/ip_queue.c +++ /dev/null @@ -1,639 +0,0 @@ -/* - * This is a module which is used for queueing IPv4 packets and - * communicating with userspace via netlink. - * - * (C) 2000-2002 James Morris <jmorris@intercode.com.au> - * (C) 2003-2005 Netfilter Core Team <coreteam@netfilter.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/init.h> -#include <linux/ip.h> -#include <linux/notifier.h> -#include <linux/netdevice.h> -#include <linux/netfilter.h> -#include <linux/netfilter_ipv4/ip_queue.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netlink.h> -#include <linux/spinlock.h> -#include <linux/sysctl.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/security.h> -#include <linux/net.h> -#include <linux/mutex.h> -#include <linux/slab.h> -#include <net/net_namespace.h> -#include <net/sock.h> -#include <net/route.h> -#include <net/netfilter/nf_queue.h> -#include <net/ip.h> - -#define IPQ_QMAX_DEFAULT 1024 -#define IPQ_PROC_FS_NAME "ip_queue" -#define NET_IPQ_QMAX 2088 -#define NET_IPQ_QMAX_NAME "ip_queue_maxlen" - -typedef int (*ipq_cmpfn)(struct nf_queue_entry *, unsigned long); - -static unsigned char copy_mode __read_mostly = IPQ_COPY_NONE; -static unsigned int queue_maxlen __read_mostly = IPQ_QMAX_DEFAULT; -static DEFINE_SPINLOCK(queue_lock); -static int peer_pid __read_mostly; -static unsigned int copy_range __read_mostly; -static unsigned int queue_total; -static unsigned int queue_dropped = 0; -static unsigned int queue_user_dropped = 0; -static struct sock *ipqnl __read_mostly; -static LIST_HEAD(queue_list); -static DEFINE_MUTEX(ipqnl_mutex); - -static inline void -__ipq_enqueue_entry(struct nf_queue_entry *entry) -{ - list_add_tail(&entry->list, &queue_list); - queue_total++; -} - -static inline int -__ipq_set_mode(unsigned char mode, unsigned int range) -{ - int status = 0; - - switch(mode) { - case IPQ_COPY_NONE: - case IPQ_COPY_META: - copy_mode = mode; - copy_range = 0; - break; - - case IPQ_COPY_PACKET: - if (range > 0xFFFF) - range = 0xFFFF; - copy_range = range; - copy_mode = mode; - break; - - default: - status = -EINVAL; - - } - return status; -} - -static void __ipq_flush(ipq_cmpfn cmpfn, unsigned long data); - -static inline void -__ipq_reset(void) -{ - peer_pid = 0; - net_disable_timestamp(); - __ipq_set_mode(IPQ_COPY_NONE, 0); - __ipq_flush(NULL, 0); -} - -static struct nf_queue_entry * -ipq_find_dequeue_entry(unsigned long id) -{ - struct nf_queue_entry *entry = NULL, *i; - - spin_lock_bh(&queue_lock); - - list_for_each_entry(i, &queue_list, list) { - if ((unsigned long)i == id) { - entry = i; - break; - } - } - - if (entry) { - list_del(&entry->list); - queue_total--; - } - - spin_unlock_bh(&queue_lock); - return entry; -} - -static void -__ipq_flush(ipq_cmpfn cmpfn, unsigned long data) -{ - struct nf_queue_entry *entry, *next; - - list_for_each_entry_safe(entry, next, &queue_list, list) { - if (!cmpfn || cmpfn(entry, data)) { - list_del(&entry->list); - queue_total--; - nf_reinject(entry, NF_DROP); - } - } -} - -static void -ipq_flush(ipq_cmpfn cmpfn, unsigned long data) -{ - spin_lock_bh(&queue_lock); - __ipq_flush(cmpfn, data); - spin_unlock_bh(&queue_lock); -} - -static struct sk_buff * -ipq_build_packet_message(struct nf_queue_entry *entry, int *errp) -{ - sk_buff_data_t old_tail; - size_t size = 0; - size_t data_len = 0; - struct sk_buff *skb; - struct ipq_packet_msg *pmsg; - struct nlmsghdr *nlh; - struct timeval tv; - - switch (ACCESS_ONCE(copy_mode)) { - case IPQ_COPY_META: - case IPQ_COPY_NONE: - size = NLMSG_SPACE(sizeof(*pmsg)); - break; - - case IPQ_COPY_PACKET: - if (entry->skb->ip_summed == CHECKSUM_PARTIAL && - (*errp = skb_checksum_help(entry->skb))) - return NULL; - - data_len = ACCESS_ONCE(copy_range); - if (data_len == 0 || data_len > entry->skb->len) - data_len = entry->skb->len; - - size = NLMSG_SPACE(sizeof(*pmsg) + data_len); - break; - - default: - *errp = -EINVAL; - return NULL; - } - - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) - goto nlmsg_failure; - - old_tail = skb->tail; - nlh = NLMSG_PUT(skb, 0, 0, IPQM_PACKET, size - sizeof(*nlh)); - pmsg = NLMSG_DATA(nlh); - memset(pmsg, 0, sizeof(*pmsg)); - - pmsg->packet_id = (unsigned long )entry; - pmsg->data_len = data_len; - tv = ktime_to_timeval(entry->skb->tstamp); - pmsg->timestamp_sec = tv.tv_sec; - pmsg->timestamp_usec = tv.tv_usec; - pmsg->mark = entry->skb->mark; - pmsg->hook = entry->hook; - pmsg->hw_protocol = entry->skb->protocol; - - if (entry->indev) - strcpy(pmsg->indev_name, entry->indev->name); - else - pmsg->indev_name[0] = '\0'; - - if (entry->outdev) - strcpy(pmsg->outdev_name, entry->outdev->name); - else - pmsg->outdev_name[0] = '\0'; - - if (entry->indev && entry->skb->dev && - entry->skb->mac_header != entry->skb->network_header) { - pmsg->hw_type = entry->skb->dev->type; - pmsg->hw_addrlen = dev_parse_header(entry->skb, - pmsg->hw_addr); - } - - if (data_len) - if (skb_copy_bits(entry->skb, 0, pmsg->payload, data_len)) - BUG(); - - nlh->nlmsg_len = skb->tail - old_tail; - return skb; - -nlmsg_failure: - kfree_skb(skb); - *errp = -EINVAL; - printk(KERN_ERR "ip_queue: error creating packet message\n"); - return NULL; -} - -static int -ipq_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) -{ - int status = -EINVAL; - struct sk_buff *nskb; - - if (copy_mode == IPQ_COPY_NONE) - return -EAGAIN; - - nskb = ipq_build_packet_message(entry, &status); - if (nskb == NULL) - return status; - - spin_lock_bh(&queue_lock); - - if (!peer_pid) - goto err_out_free_nskb; - - if (queue_total >= queue_maxlen) { - queue_dropped++; - status = -ENOSPC; - if (net_ratelimit()) - printk (KERN_WARNING "ip_queue: full at %d entries, " - "dropping packets(s). Dropped: %d\n", queue_total, - queue_dropped); - goto err_out_free_nskb; - } - - /* netlink_unicast will either free the nskb or attach it to a socket */ - status = netlink_unicast(ipqnl, nskb, peer_pid, MSG_DONTWAIT); - if (status < 0) { - queue_user_dropped++; - goto err_out_unlock; - } - - __ipq_enqueue_entry(entry); - - spin_unlock_bh(&queue_lock); - return status; - -err_out_free_nskb: - kfree_skb(nskb); - -err_out_unlock: - spin_unlock_bh(&queue_lock); - return status; -} - -static int -ipq_mangle_ipv4(ipq_verdict_msg_t *v, struct nf_queue_entry *e) -{ - int diff; - struct iphdr *user_iph = (struct iphdr *)v->payload; - struct sk_buff *nskb; - - if (v->data_len < sizeof(*user_iph)) - return 0; - diff = v->data_len - e->skb->len; - if (diff < 0) { - if (pskb_trim(e->skb, v->data_len)) - return -ENOMEM; - } else if (diff > 0) { - if (v->data_len > 0xFFFF) - return -EINVAL; - if (diff > skb_tailroom(e->skb)) { - nskb = skb_copy_expand(e->skb, skb_headroom(e->skb), - diff, GFP_ATOMIC); - if (!nskb) { - printk(KERN_WARNING "ip_queue: error " - "in mangle, dropping packet\n"); - return -ENOMEM; - } - kfree_skb(e->skb); - e->skb = nskb; - } - skb_put(e->skb, diff); - } - if (!skb_make_writable(e->skb, v->data_len)) - return -ENOMEM; - skb_copy_to_linear_data(e->skb, v->payload, v->data_len); - e->skb->ip_summed = CHECKSUM_NONE; - - return 0; -} - -static int -ipq_set_verdict(struct ipq_verdict_msg *vmsg, unsigned int len) -{ - struct nf_queue_entry *entry; - - if (vmsg->value > NF_MAX_VERDICT || vmsg->value == NF_STOLEN) - return -EINVAL; - - entry = ipq_find_dequeue_entry(vmsg->id); - if (entry == NULL) - return -ENOENT; - else { - int verdict = vmsg->value; - - if (vmsg->data_len && vmsg->data_len == len) - if (ipq_mangle_ipv4(vmsg, entry) < 0) - verdict = NF_DROP; - - nf_reinject(entry, verdict); - return 0; - } -} - -static int -ipq_set_mode(unsigned char mode, unsigned int range) -{ - int status; - - spin_lock_bh(&queue_lock); - status = __ipq_set_mode(mode, range); - spin_unlock_bh(&queue_lock); - return status; -} - -static int -ipq_receive_peer(struct ipq_peer_msg *pmsg, - unsigned char type, unsigned int len) -{ - int status = 0; - - if (len < sizeof(*pmsg)) - return -EINVAL; - - switch (type) { - case IPQM_MODE: - status = ipq_set_mode(pmsg->msg.mode.value, - pmsg->msg.mode.range); - break; - - case IPQM_VERDICT: - status = ipq_set_verdict(&pmsg->msg.verdict, - len - sizeof(*pmsg)); - break; - default: - status = -EINVAL; - } - return status; -} - -static int -dev_cmp(struct nf_queue_entry *entry, unsigned long ifindex) -{ - if (entry->indev) - if (entry->indev->ifindex == ifindex) - return 1; - if (entry->outdev) - if (entry->outdev->ifindex == ifindex) - return 1; -#ifdef CONFIG_BRIDGE_NETFILTER - if (entry->skb->nf_bridge) { - if (entry->skb->nf_bridge->physindev && - entry->skb->nf_bridge->physindev->ifindex == ifindex) - return 1; - if (entry->skb->nf_bridge->physoutdev && - entry->skb->nf_bridge->physoutdev->ifindex == ifindex) - return 1; - } -#endif - return 0; -} - -static void -ipq_dev_drop(int ifindex) -{ - ipq_flush(dev_cmp, ifindex); -} - -#define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err)); return; } while (0) - -static inline void -__ipq_rcv_skb(struct sk_buff *skb) -{ - int status, type, pid, flags; - unsigned int nlmsglen, skblen; - struct nlmsghdr *nlh; - bool enable_timestamp = false; - - skblen = skb->len; - if (skblen < sizeof(*nlh)) - return; - - nlh = nlmsg_hdr(skb); - nlmsglen = nlh->nlmsg_len; - if (nlmsglen < sizeof(*nlh) || skblen < nlmsglen) - return; - - pid = nlh->nlmsg_pid; - flags = nlh->nlmsg_flags; - - if(pid <= 0 || !(flags & NLM_F_REQUEST) || flags & NLM_F_MULTI) - RCV_SKB_FAIL(-EINVAL); - - if (flags & MSG_TRUNC) - RCV_SKB_FAIL(-ECOMM); - - type = nlh->nlmsg_type; - if (type < NLMSG_NOOP || type >= IPQM_MAX) - RCV_SKB_FAIL(-EINVAL); - - if (type <= IPQM_BASE) - return; - - if (!capable(CAP_NET_ADMIN)) - RCV_SKB_FAIL(-EPERM); - - spin_lock_bh(&queue_lock); - - if (peer_pid) { - if (peer_pid != pid) { - spin_unlock_bh(&queue_lock); - RCV_SKB_FAIL(-EBUSY); - } - } else { - enable_timestamp = true; - peer_pid = pid; - } - - spin_unlock_bh(&queue_lock); - if (enable_timestamp) - net_enable_timestamp(); - status = ipq_receive_peer(NLMSG_DATA(nlh), type, - nlmsglen - NLMSG_LENGTH(0)); - if (status < 0) - RCV_SKB_FAIL(status); - - if (flags & NLM_F_ACK) - netlink_ack(skb, nlh, 0); -} - -static void -ipq_rcv_skb(struct sk_buff *skb) -{ - mutex_lock(&ipqnl_mutex); - __ipq_rcv_skb(skb); - mutex_unlock(&ipqnl_mutex); -} - -static int -ipq_rcv_dev_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - struct net_device *dev = ptr; - - if (!net_eq(dev_net(dev), &init_net)) - return NOTIFY_DONE; - - /* Drop any packets associated with the downed device */ - if (event == NETDEV_DOWN) - ipq_dev_drop(dev->ifindex); - return NOTIFY_DONE; -} - -static struct notifier_block ipq_dev_notifier = { - .notifier_call = ipq_rcv_dev_event, -}; - -static int -ipq_rcv_nl_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - struct netlink_notify *n = ptr; - - if (event == NETLINK_URELEASE && n->protocol == NETLINK_FIREWALL) { - spin_lock_bh(&queue_lock); - if ((net_eq(n->net, &init_net)) && (n->pid == peer_pid)) - __ipq_reset(); - spin_unlock_bh(&queue_lock); - } - return NOTIFY_DONE; -} - -static struct notifier_block ipq_nl_notifier = { - .notifier_call = ipq_rcv_nl_event, -}; - -#ifdef CONFIG_SYSCTL -static struct ctl_table_header *ipq_sysctl_header; - -static ctl_table ipq_table[] = { - { - .procname = NET_IPQ_QMAX_NAME, - .data = &queue_maxlen, - .maxlen = sizeof(queue_maxlen), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { } -}; -#endif - -#ifdef CONFIG_PROC_FS -static int ip_queue_show(struct seq_file *m, void *v) -{ - spin_lock_bh(&queue_lock); - - seq_printf(m, - "Peer PID : %d\n" - "Copy mode : %hu\n" - "Copy range : %u\n" - "Queue length : %u\n" - "Queue max. length : %u\n" - "Queue dropped : %u\n" - "Netlink dropped : %u\n", - peer_pid, - copy_mode, - copy_range, - queue_total, - queue_maxlen, - queue_dropped, - queue_user_dropped); - - spin_unlock_bh(&queue_lock); - return 0; -} - -static int ip_queue_open(struct inode *inode, struct file *file) -{ - return single_open(file, ip_queue_show, NULL); -} - -static const struct file_operations ip_queue_proc_fops = { - .open = ip_queue_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; -#endif - -static const struct nf_queue_handler nfqh = { - .name = "ip_queue", - .outfn = &ipq_enqueue_packet, -}; - -static int __init ip_queue_init(void) -{ - int status = -ENOMEM; - struct proc_dir_entry *proc __maybe_unused; - - netlink_register_notifier(&ipq_nl_notifier); - ipqnl = netlink_kernel_create(&init_net, NETLINK_FIREWALL, 0, - ipq_rcv_skb, NULL, THIS_MODULE); - if (ipqnl == NULL) { - printk(KERN_ERR "ip_queue: failed to create netlink socket\n"); - goto cleanup_netlink_notifier; - } - -#ifdef CONFIG_PROC_FS - proc = proc_create(IPQ_PROC_FS_NAME, 0, init_net.proc_net, - &ip_queue_proc_fops); - if (!proc) { - printk(KERN_ERR "ip_queue: failed to create proc entry\n"); - goto cleanup_ipqnl; - } -#endif - register_netdevice_notifier(&ipq_dev_notifier); -#ifdef CONFIG_SYSCTL - ipq_sysctl_header = register_sysctl_paths(net_ipv4_ctl_path, ipq_table); -#endif - status = nf_register_queue_handler(NFPROTO_IPV4, &nfqh); - if (status < 0) { - printk(KERN_ERR "ip_queue: failed to register queue handler\n"); - goto cleanup_sysctl; - } - return status; - -cleanup_sysctl: -#ifdef CONFIG_SYSCTL - unregister_sysctl_table(ipq_sysctl_header); -#endif - unregister_netdevice_notifier(&ipq_dev_notifier); - proc_net_remove(&init_net, IPQ_PROC_FS_NAME); -cleanup_ipqnl: __maybe_unused - netlink_kernel_release(ipqnl); - mutex_lock(&ipqnl_mutex); - mutex_unlock(&ipqnl_mutex); - -cleanup_netlink_notifier: - netlink_unregister_notifier(&ipq_nl_notifier); - return status; -} - -static void __exit ip_queue_fini(void) -{ - nf_unregister_queue_handlers(&nfqh); - - ipq_flush(NULL, 0); - -#ifdef CONFIG_SYSCTL - unregister_sysctl_table(ipq_sysctl_header); -#endif - unregister_netdevice_notifier(&ipq_dev_notifier); - proc_net_remove(&init_net, IPQ_PROC_FS_NAME); - - netlink_kernel_release(ipqnl); - mutex_lock(&ipqnl_mutex); - mutex_unlock(&ipqnl_mutex); - - netlink_unregister_notifier(&ipq_nl_notifier); -} - -MODULE_DESCRIPTION("IPv4 packet queue handler"); -MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_FIREWALL); - -module_init(ip_queue_init); -module_exit(ip_queue_fini); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 24e556e83a3..170b1fdd6b7 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -153,8 +153,7 @@ ip_checkentry(const struct ipt_ip *ip) static unsigned int ipt_error(struct sk_buff *skb, const struct xt_action_param *par) { - if (net_ratelimit()) - pr_info("error: `%s'\n", (const char *)par->targinfo); + net_info_ratelimited("error: `%s'\n", (const char *)par->targinfo); return NF_DROP; } @@ -377,7 +376,7 @@ ipt_do_table(struct sk_buff *skb, if (v < 0) { /* Pop from stack? */ if (v != XT_RETURN) { - verdict = (unsigned)(-v) - 1; + verdict = (unsigned int)(-v) - 1; break; } if (*stackptr <= origptr) { diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index a639967eb72..fe5daea5214 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -246,8 +246,7 @@ clusterip_hashfn(const struct sk_buff *skb, dport = ports[1]; } } else { - if (net_ratelimit()) - pr_info("unknown protocol %u\n", iph->protocol); + net_info_ratelimited("unknown protocol %u\n", iph->protocol); } switch (config->hash_mode) { diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index de9da21113a..91747d4ebc2 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -74,16 +74,24 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); if (iph == NULL) - return -NF_DROP; + return -NF_ACCEPT; /* Conntrack defragments packets, we might still see fragments * inside ICMP packets though. */ if (iph->frag_off & htons(IP_OFFSET)) - return -NF_DROP; + return -NF_ACCEPT; *dataoff = nhoff + (iph->ihl << 2); *protonum = iph->protocol; + /* Check bogus IP headers */ + if (*dataoff > skb->len) { + pr_debug("nf_conntrack_ipv4: bogus IPv4 packet: " + "nhoff %u, ihl %u, skblen %u\n", + nhoff, iph->ihl << 2, skb->len); + return -NF_ACCEPT; + } + return NF_ACCEPT; } @@ -303,8 +311,9 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) static int ipv4_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { - NLA_PUT_BE32(skb, CTA_IP_V4_SRC, tuple->src.u3.ip); - NLA_PUT_BE32(skb, CTA_IP_V4_DST, tuple->dst.u3.ip); + if (nla_put_be32(skb, CTA_IP_V4_SRC, tuple->src.u3.ip) || + nla_put_be32(skb, CTA_IP_V4_DST, tuple->dst.u3.ip)) + goto nla_put_failure; return 0; nla_put_failure: @@ -356,7 +365,7 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = { .nla_policy = ipv4_nla_policy, #endif #if defined(CONFIG_SYSCTL) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) - .ctl_table_path = nf_net_ipv4_netfilter_sysctl_path, + .ctl_table_path = "net/ipv4/netfilter", .ctl_table = ip_ct_sysctl_table, #endif .me = THIS_MODULE, diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 7cbe9cb261c..0847e373d33 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -228,10 +228,10 @@ icmp_error(struct net *net, struct nf_conn *tmpl, static int icmp_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *t) { - NLA_PUT_BE16(skb, CTA_PROTO_ICMP_ID, t->src.u.icmp.id); - NLA_PUT_U8(skb, CTA_PROTO_ICMP_TYPE, t->dst.u.icmp.type); - NLA_PUT_U8(skb, CTA_PROTO_ICMP_CODE, t->dst.u.icmp.code); - + if (nla_put_be16(skb, CTA_PROTO_ICMP_ID, t->src.u.icmp.id) || + nla_put_u8(skb, CTA_PROTO_ICMP_TYPE, t->dst.u.icmp.type) || + nla_put_u8(skb, CTA_PROTO_ICMP_CODE, t->dst.u.icmp.code)) + goto nla_put_failure; return 0; nla_put_failure: @@ -293,8 +293,8 @@ icmp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeout = data; - NLA_PUT_BE32(skb, CTA_TIMEOUT_ICMP_TIMEOUT, htonl(*timeout / HZ)); - + if (nla_put_be32(skb, CTA_TIMEOUT_ICMP_TIMEOUT, htonl(*timeout / HZ))) + goto nla_put_failure; return 0; nla_put_failure: diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index 82536701e3a..cad29c12131 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -42,9 +42,7 @@ static int set_addr(struct sk_buff *skb, if (!nf_nat_mangle_tcp_packet(skb, ct, ctinfo, addroff, sizeof(buf), (char *) &buf, sizeof(buf))) { - if (net_ratelimit()) - pr_notice("nf_nat_h323: nf_nat_mangle_tcp_packet" - " error\n"); + net_notice_ratelimited("nf_nat_h323: nf_nat_mangle_tcp_packet error\n"); return -1; } @@ -58,9 +56,7 @@ static int set_addr(struct sk_buff *skb, if (!nf_nat_mangle_udp_packet(skb, ct, ctinfo, addroff, sizeof(buf), (char *) &buf, sizeof(buf))) { - if (net_ratelimit()) - pr_notice("nf_nat_h323: nf_nat_mangle_udp_packet" - " error\n"); + net_notice_ratelimited("nf_nat_h323: nf_nat_mangle_udp_packet error\n"); return -1; } /* nf_nat_mangle_udp_packet uses skb_make_writable() to copy @@ -214,8 +210,7 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, /* Run out of expectations */ if (i >= H323_RTP_CHANNEL_MAX) { - if (net_ratelimit()) - pr_notice("nf_nat_h323: out of expectations\n"); + net_notice_ratelimited("nf_nat_h323: out of expectations\n"); return 0; } @@ -244,8 +239,7 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, } if (nated_port == 0) { /* No port available */ - if (net_ratelimit()) - pr_notice("nf_nat_h323: out of RTP ports\n"); + net_notice_ratelimited("nf_nat_h323: out of RTP ports\n"); return 0; } @@ -308,8 +302,7 @@ static int nat_t120(struct sk_buff *skb, struct nf_conn *ct, } if (nated_port == 0) { /* No port available */ - if (net_ratelimit()) - pr_notice("nf_nat_h323: out of TCP ports\n"); + net_notice_ratelimited("nf_nat_h323: out of TCP ports\n"); return 0; } @@ -365,8 +358,7 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, } if (nated_port == 0) { /* No port available */ - if (net_ratelimit()) - pr_notice("nf_nat_q931: out of TCP ports\n"); + net_notice_ratelimited("nf_nat_q931: out of TCP ports\n"); return 0; } @@ -456,8 +448,7 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, } if (nated_port == 0) { /* No port available */ - if (net_ratelimit()) - pr_notice("nf_nat_ras: out of TCP ports\n"); + net_notice_ratelimited("nf_nat_ras: out of TCP ports\n"); return 0; } @@ -545,8 +536,7 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, } if (nated_port == 0) { /* No port available */ - if (net_ratelimit()) - pr_notice("nf_nat_q931: out of TCP ports\n"); + net_notice_ratelimited("nf_nat_q931: out of TCP ports\n"); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index 57932c43960..ea4a23813d2 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -283,7 +283,7 @@ static unsigned int ip_nat_sip_expect(struct sk_buff *skb, unsigned int dataoff, __be32 newip; u_int16_t port; char buffer[sizeof("nnn.nnn.nnn.nnn:nnnnn")]; - unsigned buflen; + unsigned int buflen; /* Connection will come from reply */ if (ct->tuplehash[dir].tuple.src.u3.ip == ct->tuplehash[!dir].tuple.dst.u3.ip) diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 2133c30a4a5..746edec8b86 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -1206,8 +1206,7 @@ static int snmp_translate(struct nf_conn *ct, if (!snmp_parse_mangle((unsigned char *)udph + sizeof(struct udphdr), paylen, &map, &udph->check)) { - if (net_ratelimit()) - printk(KERN_WARNING "bsalg: parser failed\n"); + net_warn_ratelimited("bsalg: parser failed\n"); return NF_DROP; } return NF_ACCEPT; @@ -1241,9 +1240,8 @@ static int help(struct sk_buff *skb, unsigned int protoff, * can mess around with the payload. */ if (ntohs(udph->len) != skb->len - (iph->ihl << 2)) { - if (net_ratelimit()) - printk(KERN_WARNING "SNMP: dropping malformed packet src=%pI4 dst=%pI4\n", - &iph->saddr, &iph->daddr); + net_warn_ratelimited("SNMP: dropping malformed packet src=%pI4 dst=%pI4\n", + &iph->saddr, &iph->daddr); return NF_DROP; } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 50009c787bc..6e930c7174d 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -51,15 +51,16 @@ static struct ping_table ping_table; static u16 ping_port_rover; -static inline int ping_hashfn(struct net *net, unsigned num, unsigned mask) +static inline int ping_hashfn(struct net *net, unsigned int num, unsigned int mask) { int res = (num + net_hash_mix(net)) & mask; + pr_debug("hash(%d) = %d\n", num, res); return res; } static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table, - struct net *net, unsigned num) + struct net *net, unsigned int num) { return &table->hash[ping_hashfn(net, num, PING_HTABLE_MASK)]; } @@ -188,7 +189,8 @@ static void inet_get_ping_group_range_net(struct net *net, gid_t *low, gid_t *high) { gid_t *data = net->ipv4.sysctl_ping_group_range; - unsigned seq; + unsigned int seq; + do { seq = read_seqbegin(&sysctl_local_ports.lock); @@ -410,7 +412,7 @@ struct pingfakehdr { __wsum wcheck; }; -static int ping_getfrag(void *from, char * to, +static int ping_getfrag(void *from, char *to, int offset, int fraglen, int odd, struct sk_buff *skb) { struct pingfakehdr *pfh = (struct pingfakehdr *)from; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index bbd604c68e6..4032b818f3e 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -288,7 +288,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) read_unlock(&raw_v4_hashinfo.lock); } -static int raw_rcv_skb(struct sock * sk, struct sk_buff * skb) +static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb) { /* Charge it to the socket. */ diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 4dc1c104c94..ffcb3b01684 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -109,6 +109,7 @@ #include <net/rtnetlink.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> +#include <linux/kmemleak.h> #endif #include <net/secure_seq.h> @@ -229,7 +230,7 @@ const __u8 ip_tos2prio[16] = { TC_PRIO_INTERACTIVE_BULK, ECN_OR_COST(INTERACTIVE_BULK) }; - +EXPORT_SYMBOL(ip_tos2prio); /* * Route cache. @@ -296,7 +297,7 @@ static inline void rt_hash_lock_init(void) #endif static struct rt_hash_bucket *rt_hash_table __read_mostly; -static unsigned rt_hash_mask __read_mostly; +static unsigned int rt_hash_mask __read_mostly; static unsigned int rt_hash_log __read_mostly; static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); @@ -959,8 +960,7 @@ void rt_cache_flush_batch(struct net *net) static void rt_emergency_hash_rebuild(struct net *net) { - if (net_ratelimit()) - pr_warn("Route hash chain too long!\n"); + net_warn_ratelimited("Route hash chain too long!\n"); rt_cache_invalidate(net); } @@ -1083,8 +1083,7 @@ static int rt_garbage_collect(struct dst_ops *ops) goto out; if (dst_entries_get_slow(&ipv4_dst_ops) < ip_rt_max_size) goto out; - if (net_ratelimit()) - pr_warn("dst cache overflow\n"); + net_warn_ratelimited("dst cache overflow\n"); RT_CACHE_STAT_INC(gc_dst_overflow); return 1; @@ -1143,7 +1142,7 @@ static int rt_bind_neighbour(struct rtable *rt) return 0; } -static struct rtable *rt_intern_hash(unsigned hash, struct rtable *rt, +static struct rtable *rt_intern_hash(unsigned int hash, struct rtable *rt, struct sk_buff *skb, int ifindex) { struct rtable *rth, *cand; @@ -1181,8 +1180,7 @@ restart: if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) { int err = rt_bind_neighbour(rt); if (err) { - if (net_ratelimit()) - pr_warn("Neighbour table failure & not caching routes\n"); + net_warn_ratelimited("Neighbour table failure & not caching routes\n"); ip_rt_put(rt); return ERR_PTR(err); } @@ -1298,8 +1296,7 @@ restart: goto restart; } - if (net_ratelimit()) - pr_warn("Neighbour table overflow\n"); + net_warn_ratelimited("Neighbour table overflow\n"); rt_drop(rt); return ERR_PTR(-ENOBUFS); } @@ -1377,14 +1374,13 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) return; } } else if (!rt) - printk(KERN_DEBUG "rt_bind_peer(0) @%p\n", - __builtin_return_address(0)); + pr_debug("rt_bind_peer(0) @%p\n", __builtin_return_address(0)); ip_select_fb_ident(iph); } EXPORT_SYMBOL(__ip_select_ident); -static void rt_del(unsigned hash, struct rtable *rt) +static void rt_del(unsigned int hash, struct rtable *rt) { struct rtable __rcu **rthp; struct rtable *aux; @@ -1502,11 +1498,11 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, reject_redirect: #ifdef CONFIG_IP_ROUTE_VERBOSE - if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit()) - pr_info("Redirect from %pI4 on %s about %pI4 ignored\n" - " Advised path = %pI4 -> %pI4\n", - &old_gw, dev->name, &new_gw, - &saddr, &daddr); + if (IN_DEV_LOG_MARTIANS(in_dev)) + net_info_ratelimited("Redirect from %pI4 on %s about %pI4 ignored\n" + " Advised path = %pI4 -> %pI4\n", + &old_gw, dev->name, &new_gw, + &saddr, &daddr); #endif ; } @@ -1538,7 +1534,7 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) ip_rt_put(rt); ret = NULL; } else if (rt->rt_flags & RTCF_REDIRECTED) { - unsigned hash = rt_hash(rt->rt_key_dst, rt->rt_key_src, + unsigned int hash = rt_hash(rt->rt_key_dst, rt->rt_key_src, rt->rt_oif, rt_genid(dev_net(dst->dev))); rt_del(hash, rt); @@ -1616,11 +1612,10 @@ void ip_rt_send_redirect(struct sk_buff *skb) ++peer->rate_tokens; #ifdef CONFIG_IP_ROUTE_VERBOSE if (log_martians && - peer->rate_tokens == ip_rt_redirect_number && - net_ratelimit()) - pr_warn("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", - &ip_hdr(skb)->saddr, rt->rt_iif, - &rt->rt_dst, &rt->rt_gateway); + peer->rate_tokens == ip_rt_redirect_number) + net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", + &ip_hdr(skb)->saddr, rt->rt_iif, + &rt->rt_dst, &rt->rt_gateway); #endif } } @@ -1843,9 +1838,9 @@ static void ipv4_link_failure(struct sk_buff *skb) static int ip_rt_bug(struct sk_buff *skb) { - printk(KERN_DEBUG "ip_rt_bug: %pI4 -> %pI4, %s\n", - &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, - skb->dev ? skb->dev->name : "?"); + pr_debug("%s: %pI4 -> %pI4, %s\n", + __func__, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, + skb->dev ? skb->dev->name : "?"); kfree_skb(skb); WARN_ON(1); return 0; @@ -2041,7 +2036,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (err < 0) goto e_err; } - rth = rt_dst_alloc(init_net.loopback_dev, + rth = rt_dst_alloc(dev_net(dev)->loopback_dev, IN_DEV_CONF_GET(in_dev, NOPOLICY), false); if (!rth) goto e_nobufs; @@ -2134,8 +2129,7 @@ static int __mkroute_input(struct sk_buff *skb, /* get a working reference to the output device */ out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res)); if (out_dev == NULL) { - if (net_ratelimit()) - pr_crit("Bug in ip_route_input_slow(). Please report.\n"); + net_crit_ratelimited("Bug in ip_route_input_slow(). Please report.\n"); return -EINVAL; } @@ -2215,9 +2209,9 @@ static int ip_mkroute_input(struct sk_buff *skb, struct in_device *in_dev, __be32 daddr, __be32 saddr, u32 tos) { - struct rtable* rth = NULL; + struct rtable *rth = NULL; int err; - unsigned hash; + unsigned int hash; #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi && res->fi->fib_nhs > 1) @@ -2255,13 +2249,13 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, struct fib_result res; struct in_device *in_dev = __in_dev_get_rcu(dev); struct flowi4 fl4; - unsigned flags = 0; + unsigned int flags = 0; u32 itag = 0; - struct rtable * rth; - unsigned hash; + struct rtable *rth; + unsigned int hash; __be32 spec_dst; int err = -EINVAL; - struct net * net = dev_net(dev); + struct net *net = dev_net(dev); /* IP on this device is disabled. */ @@ -2406,9 +2400,9 @@ no_route: martian_destination: RT_CACHE_STAT_INC(in_martian_dst); #ifdef CONFIG_IP_ROUTE_VERBOSE - if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit()) - pr_warn("martian destination %pI4 from %pI4, dev %s\n", - &daddr, &saddr, dev->name); + if (IN_DEV_LOG_MARTIANS(in_dev)) + net_warn_ratelimited("martian destination %pI4 from %pI4, dev %s\n", + &daddr, &saddr, dev->name); #endif e_hostunreach: @@ -2433,8 +2427,8 @@ martian_source_keep_err: int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, bool noref) { - struct rtable * rth; - unsigned hash; + struct rtable *rth; + unsigned int hash; int iif = dev->ifindex; struct net *net; int res; @@ -2972,7 +2966,8 @@ static int rt_fill_info(struct net *net, r->rtm_src_len = 0; r->rtm_tos = rt->rt_key_tos; r->rtm_table = RT_TABLE_MAIN; - NLA_PUT_U32(skb, RTA_TABLE, RT_TABLE_MAIN); + if (nla_put_u32(skb, RTA_TABLE, RT_TABLE_MAIN)) + goto nla_put_failure; r->rtm_type = rt->rt_type; r->rtm_scope = RT_SCOPE_UNIVERSE; r->rtm_protocol = RTPROT_UNSPEC; @@ -2980,31 +2975,38 @@ static int rt_fill_info(struct net *net, if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; - NLA_PUT_BE32(skb, RTA_DST, rt->rt_dst); - + if (nla_put_be32(skb, RTA_DST, rt->rt_dst)) + goto nla_put_failure; if (rt->rt_key_src) { r->rtm_src_len = 32; - NLA_PUT_BE32(skb, RTA_SRC, rt->rt_key_src); + if (nla_put_be32(skb, RTA_SRC, rt->rt_key_src)) + goto nla_put_failure; } - if (rt->dst.dev) - NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex); + if (rt->dst.dev && + nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex)) + goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID - if (rt->dst.tclassid) - NLA_PUT_U32(skb, RTA_FLOW, rt->dst.tclassid); + if (rt->dst.tclassid && + nla_put_u32(skb, RTA_FLOW, rt->dst.tclassid)) + goto nla_put_failure; #endif - if (rt_is_input_route(rt)) - NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_spec_dst); - else if (rt->rt_src != rt->rt_key_src) - NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_src); - - if (rt->rt_dst != rt->rt_gateway) - NLA_PUT_BE32(skb, RTA_GATEWAY, rt->rt_gateway); + if (rt_is_input_route(rt)) { + if (nla_put_be32(skb, RTA_PREFSRC, rt->rt_spec_dst)) + goto nla_put_failure; + } else if (rt->rt_src != rt->rt_key_src) { + if (nla_put_be32(skb, RTA_PREFSRC, rt->rt_src)) + goto nla_put_failure; + } + if (rt->rt_dst != rt->rt_gateway && + nla_put_be32(skb, RTA_GATEWAY, rt->rt_gateway)) + goto nla_put_failure; if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) goto nla_put_failure; - if (rt->rt_mark) - NLA_PUT_BE32(skb, RTA_MARK, rt->rt_mark); + if (rt->rt_mark && + nla_put_be32(skb, RTA_MARK, rt->rt_mark)) + goto nla_put_failure; error = rt->dst.error; if (peer) { @@ -3045,7 +3047,8 @@ static int rt_fill_info(struct net *net, } } else #endif - NLA_PUT_U32(skb, RTA_IIF, rt->rt_iif); + if (nla_put_u32(skb, RTA_IIF, rt->rt_iif)) + goto nla_put_failure; } if (rtnl_put_cacheinfo(skb, &rt->dst, id, ts, tsage, @@ -3059,7 +3062,7 @@ nla_put_failure: return -EMSGSIZE; } -static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) +static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(in_skb->sk); struct rtmsg *rtm; @@ -3334,23 +3337,6 @@ static ctl_table ipv4_route_table[] = { { } }; -static struct ctl_table empty[1]; - -static struct ctl_table ipv4_skeleton[] = -{ - { .procname = "route", - .mode = 0555, .child = ipv4_route_table}, - { .procname = "neigh", - .mode = 0555, .child = empty}, - { } -}; - -static __net_initdata struct ctl_path ipv4_path[] = { - { .procname = "net", }, - { .procname = "ipv4", }, - { }, -}; - static struct ctl_table ipv4_route_flush_table[] = { { .procname = "flush", @@ -3361,13 +3347,6 @@ static struct ctl_table ipv4_route_flush_table[] = { { }, }; -static __net_initdata struct ctl_path ipv4_route_path[] = { - { .procname = "net", }, - { .procname = "ipv4", }, - { .procname = "route", }, - { }, -}; - static __net_init int sysctl_route_net_init(struct net *net) { struct ctl_table *tbl; @@ -3380,8 +3359,7 @@ static __net_init int sysctl_route_net_init(struct net *net) } tbl[0].extra1 = net; - net->ipv4.route_hdr = - register_net_sysctl_table(net, ipv4_route_path, tbl); + net->ipv4.route_hdr = register_net_sysctl(net, "net/ipv4/route", tbl); if (net->ipv4.route_hdr == NULL) goto err_reg; return 0; @@ -3430,9 +3408,15 @@ struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; static __initdata unsigned long rhash_entries; static int __init set_rhash_entries(char *str) { + ssize_t ret; + if (!str) return 0; - rhash_entries = simple_strtoul(str, &str, 0); + + ret = kstrtoul(str, 0, &rhash_entries); + if (ret) + return 0; + return 1; } __setup("rhash_entries=", set_rhash_entries); @@ -3505,6 +3489,6 @@ int __init ip_rt_init(void) */ void __init ip_static_sysctl_init(void) { - register_sysctl_paths(ipv4_path, ipv4_skeleton); + register_net_sysctl(&init_net, "net/ipv4/route", ipv4_route_table); } #endif diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 7a7724da9bf..ef32956ed65 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -27,6 +27,7 @@ #include <net/tcp_memcontrol.h> static int zero; +static int two = 2; static int tcp_retr1_max = 255; static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; @@ -78,7 +79,7 @@ static int ipv4_local_port_range(ctl_table *table, int write, static void inet_get_ping_group_range_table(struct ctl_table *table, gid_t *low, gid_t *high) { gid_t *data = table->data; - unsigned seq; + unsigned int seq; do { seq = read_seqbegin(&sysctl_local_ports.lock); @@ -677,6 +678,15 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { + .procname = "tcp_early_retrans", + .data = &sysctl_tcp_early_retrans, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &two, + }, + { .procname = "udp_mem", .data = &sysctl_udp_mem, .maxlen = sizeof(sysctl_udp_mem), @@ -768,13 +778,6 @@ static struct ctl_table ipv4_net_table[] = { { } }; -struct ctl_path net_ipv4_ctl_path[] = { - { .procname = "net", }, - { .procname = "ipv4", }, - { }, -}; -EXPORT_SYMBOL_GPL(net_ipv4_ctl_path); - static __net_init int ipv4_sysctl_init_net(struct net *net) { struct ctl_table *table; @@ -815,8 +818,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) tcp_init_mem(net); - net->ipv4.ipv4_hdr = register_net_sysctl_table(net, - net_ipv4_ctl_path, table); + net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); if (net->ipv4.ipv4_hdr == NULL) goto err_reg; @@ -857,12 +859,12 @@ static __init int sysctl_ipv4_init(void) if (!i->procname) return -EINVAL; - hdr = register_sysctl_paths(net_ipv4_ctl_path, ipv4_table); + hdr = register_net_sysctl(&init_net, "net/ipv4", ipv4_table); if (hdr == NULL) return -ENOMEM; if (register_pernet_subsys(&ipv4_sysctl_ops)) { - unregister_sysctl_table(hdr); + unregister_net_sysctl_table(hdr); return -ENOMEM; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index cfd7edda0a8..bb485fcb077 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -363,6 +363,71 @@ static int retrans_to_secs(u8 retrans, int timeout, int rto_max) return period; } +/* Address-family independent initialization for a tcp_sock. + * + * NOTE: A lot of things set to zero explicitly by call to + * sk_alloc() so need not be done here. + */ +void tcp_init_sock(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + + skb_queue_head_init(&tp->out_of_order_queue); + tcp_init_xmit_timers(sk); + tcp_prequeue_init(tp); + + icsk->icsk_rto = TCP_TIMEOUT_INIT; + tp->mdev = TCP_TIMEOUT_INIT; + + /* So many TCP implementations out there (incorrectly) count the + * initial SYN frame in their delayed-ACK and congestion control + * algorithms that we must have the following bandaid to talk + * efficiently to them. -DaveM + */ + tp->snd_cwnd = TCP_INIT_CWND; + + /* See draft-stevens-tcpca-spec-01 for discussion of the + * initialization of these values. + */ + tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; + tp->snd_cwnd_clamp = ~0; + tp->mss_cache = TCP_MSS_DEFAULT; + + tp->reordering = sysctl_tcp_reordering; + tcp_enable_early_retrans(tp); + icsk->icsk_ca_ops = &tcp_init_congestion_ops; + + sk->sk_state = TCP_CLOSE; + + sk->sk_write_space = sk_stream_write_space; + sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); + + icsk->icsk_sync_mss = tcp_sync_mss; + + /* TCP Cookie Transactions */ + if (sysctl_tcp_cookie_size > 0) { + /* Default, cookies without s_data_payload. */ + tp->cookie_values = + kzalloc(sizeof(*tp->cookie_values), + sk->sk_allocation); + if (tp->cookie_values != NULL) + kref_init(&tp->cookie_values->kref); + } + /* Presumed zeroed, in order of appearance: + * cookie_in_always, cookie_out_never, + * s_data_constant, s_data_in, s_data_out + */ + sk->sk_sndbuf = sysctl_tcp_wmem[1]; + sk->sk_rcvbuf = sysctl_tcp_rmem[1]; + + local_bh_disable(); + sock_update_memcg(sk); + sk_sockets_allocated_inc(sk); + local_bh_enable(); +} +EXPORT_SYMBOL(tcp_init_sock); + /* * Wait for a TCP event. * @@ -528,7 +593,7 @@ static inline void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb) tp->pushed_seq = tp->write_seq; } -static inline int forced_push(const struct tcp_sock *tp) +static inline bool forced_push(const struct tcp_sock *tp) { return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1)); } @@ -701,11 +766,12 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp) skb = alloc_skb_fclone(size + sk->sk_prot->max_header, gfp); if (skb) { if (sk_wmem_schedule(sk, skb->truesize)) { + skb_reserve(skb, sk->sk_prot->max_header); /* * Make sure that we have exactly size bytes * available to the caller, no more, no less. */ - skb_reserve(skb, skb_tailroom(skb) - size); + skb->avail_size = size; return skb; } __kfree_skb(skb); @@ -783,9 +849,10 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffse while (psize > 0) { struct sk_buff *skb = tcp_write_queue_tail(sk); struct page *page = pages[poffset / PAGE_SIZE]; - int copy, i, can_coalesce; + int copy, i; int offset = poffset % PAGE_SIZE; int size = min_t(size_t, psize, PAGE_SIZE - offset); + bool can_coalesce; if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0) { new_segment: @@ -850,8 +917,7 @@ new_segment: wait_for_sndbuf: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); wait_for_memory: - if (copied) - tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH); + tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH); if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) goto do_error; @@ -860,7 +926,7 @@ wait_for_memory: } out: - if (copied) + if (copied && !(flags & MSG_SENDPAGE_NOTLAST)) tcp_push(sk, flags, mss_now, tp->nonagle); return copied; @@ -918,7 +984,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; int iovlen, flags, err, copied; - int mss_now, size_goal; + int mss_now = 0, size_goal; bool sg; long timeo; @@ -932,6 +998,19 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if ((err = sk_stream_wait_connect(sk, &timeo)) != 0) goto out_err; + if (unlikely(tp->repair)) { + if (tp->repair_queue == TCP_RECV_QUEUE) { + copied = tcp_send_rcvq(sk, msg, size); + goto out; + } + + err = -EINVAL; + if (tp->repair_queue == TCP_NO_QUEUE) + goto out_err; + + /* 'common' sending to sendq */ + } + /* This should be in poll */ clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); @@ -995,15 +1074,14 @@ new_segment: copy = seglen; /* Where to copy to? */ - if (skb_tailroom(skb) > 0) { + if (skb_availroom(skb) > 0) { /* We have some space in skb head. Superb! */ - if (copy > skb_tailroom(skb)) - copy = skb_tailroom(skb); + copy = min_t(int, copy, skb_availroom(skb)); err = skb_add_data_nocache(sk, skb, from, copy); if (err) goto do_fault; } else { - int merge = 0; + bool merge = false; int i = skb_shinfo(skb)->nr_frags; struct page *page = sk->sk_sndmsg_page; int off; @@ -1017,7 +1095,7 @@ new_segment: off != PAGE_SIZE) { /* We can extend the last page * fragment. */ - merge = 1; + merge = true; } else if (i == MAX_SKB_FRAGS || !sg) { /* Need to add new fragment and cannot * do this because interface is non-SG, @@ -1089,7 +1167,7 @@ new_segment: if ((seglen -= copy) == 0 && iovlen == 0) goto out; - if (skb->len < max || (flags & MSG_OOB)) + if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair)) continue; if (forced_push(tp)) { @@ -1102,7 +1180,7 @@ new_segment: wait_for_sndbuf: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); wait_for_memory: - if (copied) + if (copied && likely(!tp->repair)) tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH); if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) @@ -1113,7 +1191,7 @@ wait_for_memory: } out: - if (copied) + if (copied && likely(!tp->repair)) tcp_push(sk, flags, mss_now, tp->nonagle); release_sock(sk); return copied; @@ -1187,6 +1265,24 @@ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags) return -EAGAIN; } +static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) +{ + struct sk_buff *skb; + int copied = 0, err = 0; + + /* XXX -- need to support SO_PEEK_OFF */ + + skb_queue_walk(&sk->sk_write_queue, skb) { + err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, skb->len); + if (err) + break; + + copied += skb->len; + } + + return err ?: copied; +} + /* Clean up the receive buffer for full frames taken by the user, * then send an ACK if necessary. COPIED is the number of bytes * tcp_recvmsg has given to the user so far, it speeds up the @@ -1196,7 +1292,7 @@ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags) void tcp_cleanup_rbuf(struct sock *sk, int copied) { struct tcp_sock *tp = tcp_sk(sk); - int time_to_ack = 0; + bool time_to_ack = false; struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); @@ -1222,7 +1318,7 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) && !icsk->icsk_ack.pingpong)) && !atomic_read(&sk->sk_rmem_alloc))) - time_to_ack = 1; + time_to_ack = true; } /* We send an ACK if we can now advertise a non-zero window @@ -1244,7 +1340,7 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) * "Lots" means "at least twice" here. */ if (new_window && new_window >= 2 * rcv_window_now) - time_to_ack = 1; + time_to_ack = true; } } if (time_to_ack) @@ -1376,11 +1472,11 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, break; } if (tcp_hdr(skb)->fin) { - sk_eat_skb(sk, skb, 0); + sk_eat_skb(sk, skb, false); ++seq; break; } - sk_eat_skb(sk, skb, 0); + sk_eat_skb(sk, skb, false); if (!desc->count) break; tp->copied_seq = seq; @@ -1416,7 +1512,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, int target; /* Read at least this many bytes */ long timeo; struct task_struct *user_recv = NULL; - int copied_early = 0; + bool copied_early = false; struct sk_buff *skb; u32 urg_hole = 0; @@ -1432,6 +1528,21 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (flags & MSG_OOB) goto recv_urg; + if (unlikely(tp->repair)) { + err = -EPERM; + if (!(flags & MSG_PEEK)) + goto out; + + if (tp->repair_queue == TCP_SEND_QUEUE) + goto recv_sndq; + + err = -EINVAL; + if (tp->repair_queue == TCP_NO_QUEUE) + goto out; + + /* 'common' recv queue MSG_PEEK-ing */ + } + seq = &tp->copied_seq; if (flags & MSG_PEEK) { peek_seq = tp->copied_seq; @@ -1452,7 +1563,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if ((available < target) && (len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) && !sysctl_tcp_low_latency && - dma_find_channel(DMA_MEMCPY)) { + net_dma_find_channel()) { preempt_enable_no_resched(); tp->ucopy.pinned_list = dma_pin_iovec_pages(msg->msg_iov, len); @@ -1633,9 +1744,9 @@ do_prequeue: } if ((flags & MSG_PEEK) && (peek_seq - copied - urg_hole != tp->copied_seq)) { - if (net_ratelimit()) - printk(KERN_DEBUG "TCP(%s:%d): Application bug, race in MSG_PEEK.\n", - current->comm, task_pid_nr(current)); + net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n", + current->comm, + task_pid_nr(current)); peek_seq = tp->copied_seq; } continue; @@ -1667,7 +1778,7 @@ do_prequeue: if (!(flags & MSG_TRUNC)) { #ifdef CONFIG_NET_DMA if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY); + tp->ucopy.dma_chan = net_dma_find_channel(); if (tp->ucopy.dma_chan) { tp->ucopy.dma_cookie = dma_skb_copy_datagram_iovec( @@ -1689,7 +1800,7 @@ do_prequeue: dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); if ((offset + used) == skb->len) - copied_early = 1; + copied_early = true; } else #endif @@ -1723,7 +1834,7 @@ skip_copy: goto found_fin_ok; if (!(flags & MSG_PEEK)) { sk_eat_skb(sk, skb, copied_early); - copied_early = 0; + copied_early = false; } continue; @@ -1732,7 +1843,7 @@ skip_copy: ++*seq; if (!(flags & MSG_PEEK)) { sk_eat_skb(sk, skb, copied_early); - copied_early = 0; + copied_early = false; } break; } while (len > 0); @@ -1783,6 +1894,10 @@ out: recv_urg: err = tcp_recv_urg(sk, msg, len, flags); goto out; + +recv_sndq: + err = tcp_peek_sndq(sk, msg, len); + goto out; } EXPORT_SYMBOL(tcp_recvmsg); @@ -1886,10 +2001,10 @@ bool tcp_check_oom(struct sock *sk, int shift) too_many_orphans = tcp_too_many_orphans(sk, shift); out_of_socket_memory = tcp_out_of_memory(sk); - if (too_many_orphans && net_ratelimit()) - pr_info("too many orphaned sockets\n"); - if (out_of_socket_memory && net_ratelimit()) - pr_info("out of memory -- consider tuning tcp_mem\n"); + if (too_many_orphans) + net_info_ratelimited("too many orphaned sockets\n"); + if (out_of_socket_memory) + net_info_ratelimited("out of memory -- consider tuning tcp_mem\n"); return too_many_orphans || out_of_socket_memory; } @@ -1935,7 +2050,9 @@ void tcp_close(struct sock *sk, long timeout) * advertise a zero window, then kill -9 the FTP client, wheee... * Note: timeout is always zero in such a case. */ - if (data_was_unread) { + if (unlikely(tcp_sk(sk)->repair)) { + sk->sk_prot->disconnect(sk, 0); + } else if (data_was_unread) { /* Unread data was tossed, zap the connection. */ NET_INC_STATS_USER(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); @@ -2053,7 +2170,7 @@ EXPORT_SYMBOL(tcp_close); /* These states need RST on ABORT according to RFC793 */ -static inline int tcp_need_reset(int state) +static inline bool tcp_need_reset(int state) { return (1 << state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_FIN_WAIT1 | @@ -2074,6 +2191,8 @@ int tcp_disconnect(struct sock *sk, int flags) /* ABORT function of RFC793 */ if (old_state == TCP_LISTEN) { inet_csk_listen_stop(sk); + } else if (unlikely(tp->repair)) { + sk->sk_err = ECONNABORTED; } else if (tcp_need_reset(old_state) || (tp->snd_nxt != tp->write_seq && (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK))) { @@ -2125,6 +2244,54 @@ int tcp_disconnect(struct sock *sk, int flags) } EXPORT_SYMBOL(tcp_disconnect); +static inline bool tcp_can_repair_sock(const struct sock *sk) +{ + return capable(CAP_NET_ADMIN) && + ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_ESTABLISHED)); +} + +static int tcp_repair_options_est(struct tcp_sock *tp, + struct tcp_repair_opt __user *optbuf, unsigned int len) +{ + struct tcp_repair_opt opt; + + while (len >= sizeof(opt)) { + if (copy_from_user(&opt, optbuf, sizeof(opt))) + return -EFAULT; + + optbuf++; + len -= sizeof(opt); + + switch (opt.opt_code) { + case TCPOPT_MSS: + tp->rx_opt.mss_clamp = opt.opt_val; + break; + case TCPOPT_WINDOW: + if (opt.opt_val > 14) + return -EFBIG; + + tp->rx_opt.snd_wscale = opt.opt_val; + break; + case TCPOPT_SACK_PERM: + if (opt.opt_val != 0) + return -EINVAL; + + tp->rx_opt.sack_ok |= TCP_SACK_SEEN; + if (sysctl_tcp_fack) + tcp_enable_fack(tp); + break; + case TCPOPT_TIMESTAMP: + if (opt.opt_val != 0) + return -EINVAL; + + tp->rx_opt.tstamp_ok = 1; + break; + } + } + + return 0; +} + /* * Socket option code for TCP. */ @@ -2295,6 +2462,55 @@ static int do_tcp_setsockopt(struct sock *sk, int level, err = -EINVAL; else tp->thin_dupack = val; + if (tp->thin_dupack) + tcp_disable_early_retrans(tp); + break; + + case TCP_REPAIR: + if (!tcp_can_repair_sock(sk)) + err = -EPERM; + else if (val == 1) { + tp->repair = 1; + sk->sk_reuse = SK_FORCE_REUSE; + tp->repair_queue = TCP_NO_QUEUE; + } else if (val == 0) { + tp->repair = 0; + sk->sk_reuse = SK_NO_REUSE; + tcp_send_window_probe(sk); + } else + err = -EINVAL; + + break; + + case TCP_REPAIR_QUEUE: + if (!tp->repair) + err = -EPERM; + else if (val < TCP_QUEUES_NR) + tp->repair_queue = val; + else + err = -EINVAL; + break; + + case TCP_QUEUE_SEQ: + if (sk->sk_state != TCP_CLOSE) + err = -EPERM; + else if (tp->repair_queue == TCP_SEND_QUEUE) + tp->write_seq = val; + else if (tp->repair_queue == TCP_RECV_QUEUE) + tp->rcv_nxt = val; + else + err = -EINVAL; + break; + + case TCP_REPAIR_OPTIONS: + if (!tp->repair) + err = -EINVAL; + else if (sk->sk_state == TCP_ESTABLISHED) + err = tcp_repair_options_est(tp, + (struct tcp_repair_opt __user *)optval, + optlen); + else + err = -EPERM; break; case TCP_CORK: @@ -2530,6 +2746,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = tp->mss_cache; if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) val = tp->rx_opt.user_mss; + if (tp->repair) + val = tp->rx_opt.mss_clamp; break; case TCP_NODELAY: val = !!(tp->nonagle&TCP_NAGLE_OFF); @@ -2632,6 +2850,26 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = tp->thin_dupack; break; + case TCP_REPAIR: + val = tp->repair; + break; + + case TCP_REPAIR_QUEUE: + if (tp->repair) + val = tp->repair_queue; + else + return -EINVAL; + break; + + case TCP_QUEUE_SEQ: + if (tp->repair_queue == TCP_SEND_QUEUE) + val = tp->write_seq; + else if (tp->repair_queue == TCP_RECV_QUEUE) + val = tp->rcv_nxt; + else + return -EINVAL; + break; + case TCP_USER_TIMEOUT: val = jiffies_to_msecs(icsk->icsk_user_timeout); break; @@ -2675,7 +2913,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, { struct sk_buff *segs = ERR_PTR(-EINVAL); struct tcphdr *th; - unsigned thlen; + unsigned int thlen; unsigned int seq; __be32 delta; unsigned int oldlen; @@ -2933,13 +3171,13 @@ out_free: struct tcp_md5sig_pool __percpu *tcp_alloc_md5sig_pool(struct sock *sk) { struct tcp_md5sig_pool __percpu *pool; - int alloc = 0; + bool alloc = false; retry: spin_lock_bh(&tcp_md5sig_pool_lock); pool = tcp_md5sig_pool; if (tcp_md5sig_users++ == 0) { - alloc = 1; + alloc = true; spin_unlock_bh(&tcp_md5sig_pool_lock); } else if (!pool) { tcp_md5sig_users--; @@ -3033,9 +3271,9 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp, struct scatterlist sg; const struct tcphdr *tp = tcp_hdr(skb); struct hash_desc *desc = &hp->md5_desc; - unsigned i; - const unsigned head_data_len = skb_headlen(skb) > header_len ? - skb_headlen(skb) - header_len : 0; + unsigned int i; + const unsigned int head_data_len = skb_headlen(skb) > header_len ? + skb_headlen(skb) - header_len : 0; const struct skb_shared_info *shi = skb_shinfo(skb); struct sk_buff *frag_iter; @@ -3223,9 +3461,15 @@ extern struct tcp_congestion_ops tcp_reno; static __initdata unsigned long thash_entries; static int __init set_thash_entries(char *str) { + ssize_t ret; + if (!str) return 0; - thash_entries = simple_strtoul(str, &str, 0); + + ret = kstrtoul(str, 0, &thash_entries); + if (ret) + return 0; + return 1; } __setup("thash_entries=", set_thash_entries); @@ -3243,7 +3487,7 @@ void __init tcp_init(void) { struct sk_buff *skb = NULL; unsigned long limit; - int max_share, cnt; + int max_rshare, max_wshare, cnt; unsigned int i; unsigned long jiffy = jiffies; @@ -3302,17 +3546,17 @@ void __init tcp_init(void) tcp_init_mem(&init_net); /* Set per-socket limits to no more than 1/128 the pressure threshold */ - limit = nr_free_buffer_pages() << (PAGE_SHIFT - 10); - limit = max(limit, 128UL); - max_share = min(4UL*1024*1024, limit); + limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7); + max_wshare = min(4UL*1024*1024, limit); + max_rshare = min(6UL*1024*1024, limit); sysctl_tcp_wmem[0] = SK_MEM_QUANTUM; sysctl_tcp_wmem[1] = 16*1024; - sysctl_tcp_wmem[2] = max(64*1024, max_share); + sysctl_tcp_wmem[2] = max(64*1024, max_wshare); sysctl_tcp_rmem[0] = SK_MEM_QUANTUM; sysctl_tcp_rmem[1] = 87380; - sysctl_tcp_rmem[2] = max(87380, max_share); + sysctl_tcp_rmem[2] = max(87380, max_rshare); pr_info("Hash tables configured (established %u bind %u)\n", tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 272a84593c8..04dbd7ae7c6 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -280,19 +280,19 @@ int tcp_set_congestion_control(struct sock *sk, const char *name) /* RFC2861 Check whether we are limited by application or congestion window * This is the inverse of cwnd check in tcp_tso_should_defer */ -int tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight) +bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight) { const struct tcp_sock *tp = tcp_sk(sk); u32 left; if (in_flight >= tp->snd_cwnd) - return 1; + return true; left = tp->snd_cwnd - in_flight; if (sk_can_gso(sk) && left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd && left * tp->mss_cache < sk->sk_gso_max_size) - return 1; + return true; return left <= tcp_max_tso_deferred_mss(tp); } EXPORT_SYMBOL_GPL(tcp_is_cwnd_limited); diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c index fe3ecf484b4..57bdd17dff4 100644 --- a/net/ipv4/tcp_hybla.c +++ b/net/ipv4/tcp_hybla.c @@ -15,7 +15,7 @@ /* Tcp Hybla structure. */ struct hybla { - u8 hybla_en; + bool hybla_en; u32 snd_cwnd_cents; /* Keeps increment values when it is <1, <<7 */ u32 rho; /* Rho parameter, integer part */ u32 rho2; /* Rho * Rho, integer part */ @@ -24,8 +24,7 @@ struct hybla { u32 minrtt; /* Minimum smoothed round trip time value seen */ }; -/* Hybla reference round trip time (default= 1/40 sec = 25 ms), - expressed in jiffies */ +/* Hybla reference round trip time (default= 1/40 sec = 25 ms), in ms */ static int rtt0 = 25; module_param(rtt0, int, 0644); MODULE_PARM_DESC(rtt0, "reference rout trip time (ms)"); @@ -39,7 +38,7 @@ static inline void hybla_recalc_param (struct sock *sk) ca->rho_3ls = max_t(u32, tcp_sk(sk)->srtt / msecs_to_jiffies(rtt0), 8); ca->rho = ca->rho_3ls >> 3; ca->rho2_7ls = (ca->rho_3ls * ca->rho_3ls) << 1; - ca->rho2 = ca->rho2_7ls >>7; + ca->rho2 = ca->rho2_7ls >> 7; } static void hybla_init(struct sock *sk) @@ -52,7 +51,7 @@ static void hybla_init(struct sock *sk) ca->rho_3ls = 0; ca->rho2_7ls = 0; ca->snd_cwnd_cents = 0; - ca->hybla_en = 1; + ca->hybla_en = true; tp->snd_cwnd = 2; tp->snd_cwnd_clamp = 65535; @@ -67,6 +66,7 @@ static void hybla_init(struct sock *sk) static void hybla_state(struct sock *sk, u8 ca_state) { struct hybla *ca = inet_csk_ca(sk); + ca->hybla_en = (ca_state == TCP_CA_Open); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e886e2f7fa8..cfa2aa12834 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -85,7 +85,7 @@ int sysctl_tcp_ecn __read_mostly = 2; EXPORT_SYMBOL(sysctl_tcp_ecn); int sysctl_tcp_dsack __read_mostly = 1; int sysctl_tcp_app_win __read_mostly = 31; -int sysctl_tcp_adv_win_scale __read_mostly = 2; +int sysctl_tcp_adv_win_scale __read_mostly = 1; EXPORT_SYMBOL(sysctl_tcp_adv_win_scale); int sysctl_tcp_stdurg __read_mostly; @@ -99,6 +99,7 @@ int sysctl_tcp_thin_dupack __read_mostly; int sysctl_tcp_moderate_rcvbuf __read_mostly = 1; int sysctl_tcp_abc __read_mostly; +int sysctl_tcp_early_retrans __read_mostly = 2; #define FLAG_DATA 0x01 /* Incoming frame contained data. */ #define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */ @@ -175,7 +176,7 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) static void tcp_incr_quickack(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - unsigned quickacks = tcp_sk(sk)->rcv_wnd / (2 * icsk->icsk_ack.rcv_mss); + unsigned int quickacks = tcp_sk(sk)->rcv_wnd / (2 * icsk->icsk_ack.rcv_mss); if (quickacks == 0) quickacks = 2; @@ -195,9 +196,10 @@ static void tcp_enter_quickack_mode(struct sock *sk) * and the session is not interactive. */ -static inline int tcp_in_quickack_mode(const struct sock *sk) +static inline bool tcp_in_quickack_mode(const struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); + return icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong; } @@ -252,11 +254,11 @@ static inline void TCP_ECN_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th) tp->ecn_flags &= ~TCP_ECN_OK; } -static inline int TCP_ECN_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr *th) +static bool TCP_ECN_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr *th) { if (th->ece && !th->syn && (tp->ecn_flags & TCP_ECN_OK)) - return 1; - return 0; + return true; + return false; } /* Buffer size and advertised window tuning. @@ -335,6 +337,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) incr = __tcp_grow_window(sk, skb); if (incr) { + incr = max_t(int, incr, 2 * skb->len); tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr, tp->window_clamp); inet_csk(sk)->icsk_ack.quick |= 1; @@ -474,8 +477,11 @@ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep) if (!win_dep) { m -= (new_sample >> 3); new_sample += m; - } else if (m < new_sample) - new_sample = m << 3; + } else { + m <<= 3; + if (m < new_sample) + new_sample = m; + } } else { /* No previous measure. */ new_sample = m << 3; @@ -491,7 +497,7 @@ static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp) goto new_measure; if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq)) return; - tcp_rcv_rtt_update(tp, jiffies - tp->rcv_rtt_est.time, 1); + tcp_rcv_rtt_update(tp, tcp_time_stamp - tp->rcv_rtt_est.time, 1); new_measure: tp->rcv_rtt_est.seq = tp->rcv_nxt + tp->rcv_wnd; @@ -902,6 +908,7 @@ static void tcp_init_metrics(struct sock *sk) if (dst_metric(dst, RTAX_REORDERING) && tp->reordering != dst_metric(dst, RTAX_REORDERING)) { tcp_disable_fack(tp); + tcp_disable_early_retrans(tp); tp->reordering = dst_metric(dst, RTAX_REORDERING); } @@ -933,7 +940,7 @@ static void tcp_init_metrics(struct sock *sk) tcp_set_rto(sk); reset: if (tp->srtt == 0) { - /* RFC2988bis: We've failed to get a valid RTT sample from + /* RFC6298: 5.7 We've failed to get a valid RTT sample from * 3WHS. This is most likely due to retransmission, * including spurious one. Reset the RTO back to 3secs * from the more aggressive 1sec to avoid more spurious @@ -943,7 +950,7 @@ reset: inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK; } /* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been - * retransmitted. In light of RFC2988bis' more aggressive 1sec + * retransmitted. In light of RFC6298 more aggressive 1sec * initRTO, we only reset cwnd when more than 1 SYN/SYN-ACK * retransmission has occurred. */ @@ -975,15 +982,18 @@ static void tcp_update_reordering(struct sock *sk, const int metric, NET_INC_STATS_BH(sock_net(sk), mib_idx); #if FASTRETRANS_DEBUG > 1 - printk(KERN_DEBUG "Disorder%d %d %u f%u s%u rr%d\n", - tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state, - tp->reordering, - tp->fackets_out, - tp->sacked_out, - tp->undo_marker ? tp->undo_retrans : 0); + pr_debug("Disorder%d %d %u f%u s%u rr%d\n", + tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state, + tp->reordering, + tp->fackets_out, + tp->sacked_out, + tp->undo_marker ? tp->undo_retrans : 0); #endif tcp_disable_fack(tp); } + + if (metric > 0) + tcp_disable_early_retrans(tp); } /* This must be called before lost_out is incremented */ @@ -1114,36 +1124,36 @@ static void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, * the exact amount is rather hard to quantify. However, tp->max_window can * be used as an exaggerated estimate. */ -static int tcp_is_sackblock_valid(struct tcp_sock *tp, int is_dsack, - u32 start_seq, u32 end_seq) +static bool tcp_is_sackblock_valid(struct tcp_sock *tp, bool is_dsack, + u32 start_seq, u32 end_seq) { /* Too far in future, or reversed (interpretation is ambiguous) */ if (after(end_seq, tp->snd_nxt) || !before(start_seq, end_seq)) - return 0; + return false; /* Nasty start_seq wrap-around check (see comments above) */ if (!before(start_seq, tp->snd_nxt)) - return 0; + return false; /* In outstanding window? ...This is valid exit for D-SACKs too. * start_seq == snd_una is non-sensical (see comments above) */ if (after(start_seq, tp->snd_una)) - return 1; + return true; if (!is_dsack || !tp->undo_marker) - return 0; + return false; /* ...Then it's D-SACK, and must reside below snd_una completely */ if (after(end_seq, tp->snd_una)) - return 0; + return false; if (!before(start_seq, tp->undo_marker)) - return 1; + return true; /* Too old */ if (!after(end_seq, tp->undo_marker)) - return 0; + return false; /* Undo_marker boundary crossing (overestimates a lot). Known already: * start_seq < undo_marker and end_seq >= undo_marker. @@ -1215,17 +1225,17 @@ static void tcp_mark_lost_retrans(struct sock *sk) tp->lost_retrans_low = new_low_seq; } -static int tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, - struct tcp_sack_block_wire *sp, int num_sacks, - u32 prior_snd_una) +static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, + struct tcp_sack_block_wire *sp, int num_sacks, + u32 prior_snd_una) { struct tcp_sock *tp = tcp_sk(sk); u32 start_seq_0 = get_unaligned_be32(&sp[0].start_seq); u32 end_seq_0 = get_unaligned_be32(&sp[0].end_seq); - int dup_sack = 0; + bool dup_sack = false; if (before(start_seq_0, TCP_SKB_CB(ack_skb)->ack_seq)) { - dup_sack = 1; + dup_sack = true; tcp_dsack_seen(tp); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDSACKRECV); } else if (num_sacks > 1) { @@ -1234,7 +1244,7 @@ static int tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, if (!after(end_seq_0, end_seq_1) && !before(start_seq_0, start_seq_1)) { - dup_sack = 1; + dup_sack = true; tcp_dsack_seen(tp); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDSACKOFORECV); @@ -1265,9 +1275,10 @@ struct tcp_sacktag_state { * FIXME: this could be merged to shift decision code */ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, - u32 start_seq, u32 end_seq) + u32 start_seq, u32 end_seq) { - int in_sack, err; + int err; + bool in_sack; unsigned int pkt_len; unsigned int mss; @@ -1313,7 +1324,7 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, static u8 tcp_sacktag_one(struct sock *sk, struct tcp_sacktag_state *state, u8 sacked, u32 start_seq, u32 end_seq, - int dup_sack, int pcount) + bool dup_sack, int pcount) { struct tcp_sock *tp = tcp_sk(sk); int fack_count = state->fack_count; @@ -1393,10 +1404,10 @@ static u8 tcp_sacktag_one(struct sock *sk, /* Shift newly-SACKed bytes from this skb to the immediately previous * already-SACKed sk_buff. Mark the newly-SACKed bytes as such. */ -static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, - struct tcp_sacktag_state *state, - unsigned int pcount, int shifted, int mss, - int dup_sack) +static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, + struct tcp_sacktag_state *state, + unsigned int pcount, int shifted, int mss, + bool dup_sack) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *prev = tcp_write_queue_prev(sk, skb); @@ -1446,7 +1457,7 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, if (skb->len > 0) { BUG_ON(!tcp_skb_pcount(skb)); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SACKSHIFTED); - return 0; + return false; } /* Whole SKB was eaten :-) */ @@ -1469,7 +1480,7 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SACKMERGED); - return 1; + return true; } /* I wish gso_size would have a bit more sane initialization than @@ -1492,7 +1503,7 @@ static int skb_can_shift(const struct sk_buff *skb) static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, struct tcp_sacktag_state *state, u32 start_seq, u32 end_seq, - int dup_sack) + bool dup_sack) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *prev; @@ -1631,14 +1642,14 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, struct tcp_sack_block *next_dup, struct tcp_sacktag_state *state, u32 start_seq, u32 end_seq, - int dup_sack_in) + bool dup_sack_in) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *tmp; tcp_for_write_queue_from(skb, sk) { int in_sack = 0; - int dup_sack = dup_sack_in; + bool dup_sack = dup_sack_in; if (skb == tcp_send_head(sk)) break; @@ -1653,7 +1664,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, next_dup->start_seq, next_dup->end_seq); if (in_sack > 0) - dup_sack = 1; + dup_sack = true; } /* skb reference here is a bit tricky to get right, since @@ -1758,7 +1769,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, struct sk_buff *skb; int num_sacks = min(TCP_NUM_SACKS, (ptr[1] - TCPOLEN_SACK_BASE) >> 3); int used_sacks; - int found_dup_sack = 0; + bool found_dup_sack = false; int i, j; int first_sack_index; @@ -1789,7 +1800,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, used_sacks = 0; first_sack_index = 0; for (i = 0; i < num_sacks; i++) { - int dup_sack = !i && found_dup_sack; + bool dup_sack = !i && found_dup_sack; sp[used_sacks].start_seq = get_unaligned_be32(&sp_wire[i].start_seq); sp[used_sacks].end_seq = get_unaligned_be32(&sp_wire[i].end_seq); @@ -1856,7 +1867,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, while (i < used_sacks) { u32 start_seq = sp[i].start_seq; u32 end_seq = sp[i].end_seq; - int dup_sack = (found_dup_sack && (i == first_sack_index)); + bool dup_sack = (found_dup_sack && (i == first_sack_index)); struct tcp_sack_block *next_dup = NULL; if (found_dup_sack && ((i + 1) == first_sack_index)) @@ -1958,9 +1969,9 @@ out: } /* Limits sacked_out so that sum with lost_out isn't ever larger than - * packets_out. Returns zero if sacked_out adjustement wasn't necessary. + * packets_out. Returns false if sacked_out adjustement wasn't necessary. */ -static int tcp_limit_reno_sacked(struct tcp_sock *tp) +static bool tcp_limit_reno_sacked(struct tcp_sock *tp) { u32 holes; @@ -1969,9 +1980,9 @@ static int tcp_limit_reno_sacked(struct tcp_sock *tp) if ((tp->sacked_out + holes) > tp->packets_out) { tp->sacked_out = tp->packets_out - holes; - return 1; + return true; } - return 0; + return false; } /* If we receive more dupacks than we expected counting segments @@ -2025,40 +2036,40 @@ static int tcp_is_sackfrto(const struct tcp_sock *tp) /* F-RTO can only be used if TCP has never retransmitted anything other than * head (SACK enhanced variant from Appendix B of RFC4138 is more robust here) */ -int tcp_use_frto(struct sock *sk) +bool tcp_use_frto(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); struct sk_buff *skb; if (!sysctl_tcp_frto) - return 0; + return false; /* MTU probe and F-RTO won't really play nicely along currently */ if (icsk->icsk_mtup.probe_size) - return 0; + return false; if (tcp_is_sackfrto(tp)) - return 1; + return true; /* Avoid expensive walking of rexmit queue if possible */ if (tp->retrans_out > 1) - return 0; + return false; skb = tcp_write_queue_head(sk); if (tcp_skb_is_last(sk, skb)) - return 1; + return true; skb = tcp_write_queue_next(sk, skb); /* Skips head */ tcp_for_write_queue_from(skb, sk) { if (skb == tcp_send_head(sk)) break; if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) - return 0; + return false; /* Short-circuit when first non-SACKed skb has been checked */ if (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) break; } - return 1; + return true; } /* RTO occurred, but do not yet enter Loss state. Instead, defer RTO @@ -2294,7 +2305,7 @@ void tcp_enter_loss(struct sock *sk, int how) * * Do processing similar to RTO timeout. */ -static int tcp_check_sack_reneging(struct sock *sk, int flag) +static bool tcp_check_sack_reneging(struct sock *sk, int flag) { if (flag & FLAG_SACK_RENEGING) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -2305,9 +2316,9 @@ static int tcp_check_sack_reneging(struct sock *sk, int flag) tcp_retransmit_skb(sk, tcp_write_queue_head(sk)); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX); - return 1; + return true; } - return 0; + return false; } static inline int tcp_fackets_out(const struct tcp_sock *tp) @@ -2335,6 +2346,27 @@ static inline int tcp_dupack_heuristics(const struct tcp_sock *tp) return tcp_is_fack(tp) ? tp->fackets_out : tp->sacked_out + 1; } +static bool tcp_pause_early_retransmit(struct sock *sk, int flag) +{ + struct tcp_sock *tp = tcp_sk(sk); + unsigned long delay; + + /* Delay early retransmit and entering fast recovery for + * max(RTT/4, 2msec) unless ack has ECE mark, no RTT samples + * available, or RTO is scheduled to fire first. + */ + if (sysctl_tcp_early_retrans < 2 || (flag & FLAG_ECE) || !tp->srtt) + return false; + + delay = max_t(unsigned long, (tp->srtt >> 5), msecs_to_jiffies(2)); + if (!time_after(inet_csk(sk)->icsk_timeout, (jiffies + delay))) + return false; + + inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, delay, TCP_RTO_MAX); + tp->early_retrans_delayed = 1; + return true; +} + static inline int tcp_skb_timedout(const struct sock *sk, const struct sk_buff *skb) { @@ -2442,28 +2474,28 @@ static inline int tcp_head_timedout(const struct sock *sk) * Main question: may we further continue forward transmission * with the same cwnd? */ -static int tcp_time_to_recover(struct sock *sk) +static bool tcp_time_to_recover(struct sock *sk, int flag) { struct tcp_sock *tp = tcp_sk(sk); __u32 packets_out; /* Do not perform any recovery during F-RTO algorithm */ if (tp->frto_counter) - return 0; + return false; /* Trick#1: The loss is proven. */ if (tp->lost_out) - return 1; + return true; /* Not-A-Trick#2 : Classic rule... */ if (tcp_dupack_heuristics(tp) > tp->reordering) - return 1; + return true; /* Trick#3 : when we use RFC2988 timer restart, fast * retransmit can be triggered by timeout of queue head. */ if (tcp_is_fack(tp) && tcp_head_timedout(sk)) - return 1; + return true; /* Trick#4: It is still not OK... But will it be useful to delay * recovery more? @@ -2475,7 +2507,7 @@ static int tcp_time_to_recover(struct sock *sk) /* We have nothing to send. This connection is limited * either by receiver window or by application. */ - return 1; + return true; } /* If a thin stream is detected, retransmit after first @@ -2486,9 +2518,19 @@ static int tcp_time_to_recover(struct sock *sk) if ((tp->thin_dupack || sysctl_tcp_thin_dupack) && tcp_stream_is_thin(tp) && tcp_dupack_heuristics(tp) > 1 && tcp_is_sack(tp) && !tcp_send_head(sk)) - return 1; + return true; - return 0; + /* Trick#6: TCP early retransmit, per RFC5827. To avoid spurious + * retransmissions due to small network reorderings, we implement + * Mitigation A.3 in the RFC and delay the retransmission for a short + * interval if appropriate. + */ + if (tp->do_early_retrans && !tp->retrans_out && tp->sacked_out && + (tp->packets_out == (tp->sacked_out + 1) && tp->packets_out < 4) && + !tcp_may_send_now(sk)) + return !tcp_pause_early_retransmit(sk, flag); + + return false; } /* New heuristics: it is possible only after we switched to restart timer @@ -2676,22 +2718,22 @@ static void DBGUNDO(struct sock *sk, const char *msg) struct inet_sock *inet = inet_sk(sk); if (sk->sk_family == AF_INET) { - printk(KERN_DEBUG "Undo %s %pI4/%u c%u l%u ss%u/%u p%u\n", - msg, - &inet->inet_daddr, ntohs(inet->inet_dport), - tp->snd_cwnd, tcp_left_out(tp), - tp->snd_ssthresh, tp->prior_ssthresh, - tp->packets_out); + pr_debug("Undo %s %pI4/%u c%u l%u ss%u/%u p%u\n", + msg, + &inet->inet_daddr, ntohs(inet->inet_dport), + tp->snd_cwnd, tcp_left_out(tp), + tp->snd_ssthresh, tp->prior_ssthresh, + tp->packets_out); } #if IS_ENABLED(CONFIG_IPV6) else if (sk->sk_family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); - printk(KERN_DEBUG "Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n", - msg, - &np->daddr, ntohs(inet->inet_dport), - tp->snd_cwnd, tcp_left_out(tp), - tp->snd_ssthresh, tp->prior_ssthresh, - tp->packets_out); + pr_debug("Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n", + msg, + &np->daddr, ntohs(inet->inet_dport), + tp->snd_cwnd, tcp_left_out(tp), + tp->snd_ssthresh, tp->prior_ssthresh, + tp->packets_out); } #endif } @@ -2727,7 +2769,7 @@ static inline int tcp_may_undo(const struct tcp_sock *tp) } /* People celebrate: "We love our President!" */ -static int tcp_try_undo_recovery(struct sock *sk) +static bool tcp_try_undo_recovery(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); @@ -2752,10 +2794,10 @@ static int tcp_try_undo_recovery(struct sock *sk) * is ACKed. For Reno it is MUST to prevent false * fast retransmits (RFC2582). SACK TCP is safe. */ tcp_moderate_cwnd(tp); - return 1; + return true; } tcp_set_ca_state(sk, TCP_CA_Open); - return 0; + return false; } /* Try to undo cwnd reduction, because D-SACKs acked all retransmitted data */ @@ -2785,19 +2827,19 @@ static void tcp_try_undo_dsack(struct sock *sk) * that successive retransmissions of a segment must not advance * retrans_stamp under any conditions. */ -static int tcp_any_retrans_done(const struct sock *sk) +static bool tcp_any_retrans_done(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; if (tp->retrans_out) - return 1; + return true; skb = tcp_write_queue_head(sk); if (unlikely(skb && TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS)) - return 1; + return true; - return 0; + return false; } /* Undo during fast recovery after partial ACK. */ @@ -2831,7 +2873,7 @@ static int tcp_try_undo_partial(struct sock *sk, int acked) } /* Undo during loss recovery after partial ACK. */ -static int tcp_try_undo_loss(struct sock *sk) +static bool tcp_try_undo_loss(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); @@ -2853,9 +2895,9 @@ static int tcp_try_undo_loss(struct sock *sk) tp->undo_marker = 0; if (tcp_is_sack(tp)) tcp_set_ca_state(sk, TCP_CA_Open); - return 1; + return true; } - return 0; + return false; } static inline void tcp_complete_cwr(struct sock *sk) @@ -2864,11 +2906,14 @@ static inline void tcp_complete_cwr(struct sock *sk) /* Do not moderate cwnd if it's already undone in cwr or recovery. */ if (tp->undo_marker) { - if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR) + if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR) { tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh); - else /* PRR */ + tp->snd_cwnd_stamp = tcp_time_stamp; + } else if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH) { + /* PRR algorithm. */ tp->snd_cwnd = tp->snd_ssthresh; - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_time_stamp; + } } tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR); } @@ -3018,6 +3063,38 @@ static void tcp_update_cwnd_in_recovery(struct sock *sk, int newly_acked_sacked, tp->snd_cwnd = tcp_packets_in_flight(tp) + sndcnt; } +static void tcp_enter_recovery(struct sock *sk, bool ece_ack) +{ + struct tcp_sock *tp = tcp_sk(sk); + int mib_idx; + + if (tcp_is_reno(tp)) + mib_idx = LINUX_MIB_TCPRENORECOVERY; + else + mib_idx = LINUX_MIB_TCPSACKRECOVERY; + + NET_INC_STATS_BH(sock_net(sk), mib_idx); + + tp->high_seq = tp->snd_nxt; + tp->prior_ssthresh = 0; + tp->undo_marker = tp->snd_una; + tp->undo_retrans = tp->retrans_out; + + if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) { + if (!ece_ack) + tp->prior_ssthresh = tcp_current_ssthresh(sk); + tp->snd_ssthresh = inet_csk(sk)->icsk_ca_ops->ssthresh(sk); + TCP_ECN_queue_cwr(tp); + } + + tp->bytes_acked = 0; + tp->snd_cwnd_cnt = 0; + tp->prior_cwnd = tp->snd_cwnd; + tp->prr_delivered = 0; + tp->prr_out = 0; + tcp_set_ca_state(sk, TCP_CA_Recovery); +} + /* Process an event, which can update packets-in-flight not trivially. * Main goal of this function is to calculate new estimate for left_out, * taking into account both packets sitting in receiver's buffer and @@ -3037,7 +3114,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, struct tcp_sock *tp = tcp_sk(sk); int do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) && (tcp_fackets_out(tp) > tp->reordering)); - int fast_rexmit = 0, mib_idx; + int fast_rexmit = 0; if (WARN_ON(!tp->packets_out && tp->sacked_out)) tp->sacked_out = 0; @@ -3121,7 +3198,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, if (icsk->icsk_ca_state <= TCP_CA_Disorder) tcp_try_undo_dsack(sk); - if (!tcp_time_to_recover(sk)) { + if (!tcp_time_to_recover(sk, flag)) { tcp_try_to_open(sk, flag); return; } @@ -3138,32 +3215,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, } /* Otherwise enter Recovery state */ - - if (tcp_is_reno(tp)) - mib_idx = LINUX_MIB_TCPRENORECOVERY; - else - mib_idx = LINUX_MIB_TCPSACKRECOVERY; - - NET_INC_STATS_BH(sock_net(sk), mib_idx); - - tp->high_seq = tp->snd_nxt; - tp->prior_ssthresh = 0; - tp->undo_marker = tp->snd_una; - tp->undo_retrans = tp->retrans_out; - - if (icsk->icsk_ca_state < TCP_CA_CWR) { - if (!(flag & FLAG_ECE)) - tp->prior_ssthresh = tcp_current_ssthresh(sk); - tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk); - TCP_ECN_queue_cwr(tp); - } - - tp->bytes_acked = 0; - tp->snd_cwnd_cnt = 0; - tp->prior_cwnd = tp->snd_cwnd; - tp->prr_delivered = 0; - tp->prr_out = 0; - tcp_set_ca_state(sk, TCP_CA_Recovery); + tcp_enter_recovery(sk, (flag & FLAG_ECE)); fast_rexmit = 1; } @@ -3245,16 +3297,47 @@ static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) /* Restart timer after forward progress on connection. * RFC2988 recommends to restart timer to now+rto. */ -static void tcp_rearm_rto(struct sock *sk) +void tcp_rearm_rto(struct sock *sk) { - const struct tcp_sock *tp = tcp_sk(sk); + struct tcp_sock *tp = tcp_sk(sk); if (!tp->packets_out) { inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS); } else { - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - inet_csk(sk)->icsk_rto, TCP_RTO_MAX); + u32 rto = inet_csk(sk)->icsk_rto; + /* Offset the time elapsed after installing regular RTO */ + if (tp->early_retrans_delayed) { + struct sk_buff *skb = tcp_write_queue_head(sk); + const u32 rto_time_stamp = TCP_SKB_CB(skb)->when + rto; + s32 delta = (s32)(rto_time_stamp - tcp_time_stamp); + /* delta may not be positive if the socket is locked + * when the delayed ER timer fires and is rescheduled. + */ + if (delta > 0) + rto = delta; + } + inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto, + TCP_RTO_MAX); } + tp->early_retrans_delayed = 0; +} + +/* This function is called when the delayed ER timer fires. TCP enters + * fast recovery and performs fast-retransmit. + */ +void tcp_resume_early_retransmit(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + tcp_rearm_rto(sk); + + /* Stop if ER is disabled after the delayed ER timer is scheduled */ + if (!tp->do_early_retrans) + return; + + tcp_enter_recovery(sk, false); + tcp_update_scoreboard(sk, 1); + tcp_xmit_retransmit_queue(sk); } /* If we get here, the whole TSO packet has not been acked. */ @@ -3289,7 +3372,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, const struct inet_connection_sock *icsk = inet_csk(sk); struct sk_buff *skb; u32 now = tcp_time_stamp; - int fully_acked = 1; + int fully_acked = true; int flag = 0; u32 pkts_acked = 0; u32 reord = tp->packets_out; @@ -3313,7 +3396,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (!acked_pcount) break; - fully_acked = 0; + fully_acked = false; } else { acked_pcount = tcp_skb_pcount(skb); } @@ -3430,18 +3513,18 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (!tp->packets_out && tcp_is_sack(tp)) { icsk = inet_csk(sk); if (tp->lost_out) { - printk(KERN_DEBUG "Leak l=%u %d\n", - tp->lost_out, icsk->icsk_ca_state); + pr_debug("Leak l=%u %d\n", + tp->lost_out, icsk->icsk_ca_state); tp->lost_out = 0; } if (tp->sacked_out) { - printk(KERN_DEBUG "Leak s=%u %d\n", - tp->sacked_out, icsk->icsk_ca_state); + pr_debug("Leak s=%u %d\n", + tp->sacked_out, icsk->icsk_ca_state); tp->sacked_out = 0; } if (tp->retrans_out) { - printk(KERN_DEBUG "Leak r=%u %d\n", - tp->retrans_out, icsk->icsk_ca_state); + pr_debug("Leak r=%u %d\n", + tp->retrans_out, icsk->icsk_ca_state); tp->retrans_out = 0; } } @@ -3592,7 +3675,7 @@ static void tcp_undo_spur_to_response(struct sock *sk, int flag) * to prove that the RTO is indeed spurious. It transfers the control * from F-RTO to the conventional RTO recovery */ -static int tcp_process_frto(struct sock *sk, int flag) +static bool tcp_process_frto(struct sock *sk, int flag) { struct tcp_sock *tp = tcp_sk(sk); @@ -3608,7 +3691,7 @@ static int tcp_process_frto(struct sock *sk, int flag) if (!before(tp->snd_una, tp->frto_highmark)) { tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 2 : 3), flag); - return 1; + return true; } if (!tcp_is_sackfrto(tp)) { @@ -3617,19 +3700,19 @@ static int tcp_process_frto(struct sock *sk, int flag) * data, winupdate */ if (!(flag & FLAG_ANY_PROGRESS) && (flag & FLAG_NOT_DUP)) - return 1; + return true; if (!(flag & FLAG_DATA_ACKED)) { tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 0 : 3), flag); - return 1; + return true; } } else { if (!(flag & FLAG_DATA_ACKED) && (tp->frto_counter == 1)) { /* Prevent sending of new data. */ tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp)); - return 1; + return true; } if ((tp->frto_counter >= 2) && @@ -3639,10 +3722,10 @@ static int tcp_process_frto(struct sock *sk, int flag) /* RFC4138 shortcoming (see comment above) */ if (!(flag & FLAG_FORWARD_PROGRESS) && (flag & FLAG_NOT_DUP)) - return 1; + return true; tcp_enter_frto_loss(sk, 3, flag); - return 1; + return true; } } @@ -3654,7 +3737,7 @@ static int tcp_process_frto(struct sock *sk, int flag) if (!tcp_may_send_now(sk)) tcp_enter_frto_loss(sk, 2, flag); - return 1; + return true; } else { switch (sysctl_tcp_frto_response) { case 2: @@ -3671,7 +3754,7 @@ static int tcp_process_frto(struct sock *sk, int flag) tp->undo_marker = 0; NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSPURIOUSRTOS); } - return 0; + return false; } /* This routine deals with incoming acks, but not outgoing ones. */ @@ -3689,7 +3772,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) int prior_sacked = tp->sacked_out; int pkts_acked = 0; int newly_acked_sacked = 0; - int frto_cwnd = 0; + bool frto_cwnd = false; /* If the ack is older than previous acks * then we can probably ignore it. @@ -3703,6 +3786,9 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (after(ack, tp->snd_nxt)) goto invalid_ack; + if (tp->early_retrans_delayed) + tcp_rearm_rto(sk); + if (after(ack, prior_snd_una)) flag |= FLAG_SND_UNA_ADVANCED; @@ -3868,10 +3954,9 @@ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *o __u8 snd_wscale = *(__u8 *)ptr; opt_rx->wscale_ok = 1; if (snd_wscale > 14) { - if (net_ratelimit()) - pr_info("%s: Illegal window scaling value %d >14 received\n", - __func__, - snd_wscale); + net_info_ratelimited("%s: Illegal window scaling value %d >14 received\n", + __func__, + snd_wscale); snd_wscale = 14; } opt_rx->snd_wscale = snd_wscale; @@ -3942,7 +4027,7 @@ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *o } EXPORT_SYMBOL(tcp_parse_options); -static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr *th) +static bool tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr *th) { const __be32 *ptr = (const __be32 *)(th + 1); @@ -3953,31 +4038,31 @@ static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr tp->rx_opt.rcv_tsval = ntohl(*ptr); ++ptr; tp->rx_opt.rcv_tsecr = ntohl(*ptr); - return 1; + return true; } - return 0; + return false; } /* Fast parse options. This hopes to only see timestamps. * If it is wrong it falls back on tcp_parse_options(). */ -static int tcp_fast_parse_options(const struct sk_buff *skb, - const struct tcphdr *th, - struct tcp_sock *tp, const u8 **hvpp) +static bool tcp_fast_parse_options(const struct sk_buff *skb, + const struct tcphdr *th, + struct tcp_sock *tp, const u8 **hvpp) { /* In the spirit of fast parsing, compare doff directly to constant * values. Because equality is used, short doff can be ignored here. */ if (th->doff == (sizeof(*th) / 4)) { tp->rx_opt.saw_tstamp = 0; - return 0; + return false; } else if (tp->rx_opt.tstamp_ok && th->doff == ((sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) / 4)) { if (tcp_parse_aligned_timestamp(tp, th)) - return 1; + return true; } tcp_parse_options(skb, &tp->rx_opt, hvpp, 1); - return 1; + return true; } #ifdef CONFIG_TCP_MD5SIG @@ -4218,7 +4303,7 @@ static void tcp_fin(struct sock *sk) } } -static inline int tcp_sack_extend(struct tcp_sack_block *sp, u32 seq, +static inline bool tcp_sack_extend(struct tcp_sack_block *sp, u32 seq, u32 end_seq) { if (!after(seq, sp->end_seq) && !after(sp->start_seq, end_seq)) { @@ -4226,9 +4311,9 @@ static inline int tcp_sack_extend(struct tcp_sack_block *sp, u32 seq, sp->start_seq = seq; if (after(end_seq, sp->end_seq)) sp->end_seq = end_seq; - return 1; + return true; } - return 0; + return false; } static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq) @@ -4424,10 +4509,10 @@ static void tcp_ofo_queue(struct sock *sk) } } -static int tcp_prune_ofo_queue(struct sock *sk); +static bool tcp_prune_ofo_queue(struct sock *sk); static int tcp_prune_queue(struct sock *sk); -static inline int tcp_try_rmem_schedule(struct sock *sk, unsigned int size) +static int tcp_try_rmem_schedule(struct sock *sk, unsigned int size) { if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || !sk_rmem_schedule(sk, size)) { @@ -4446,6 +4531,41 @@ static inline int tcp_try_rmem_schedule(struct sock *sk, unsigned int size) return 0; } +/** + * tcp_try_coalesce - try to merge skb to prior one + * @sk: socket + * @to: prior buffer + * @from: buffer to add in queue + * @fragstolen: pointer to boolean + * + * Before queueing skb @from after @to, try to merge them + * to reduce overall memory use and queue lengths, if cost is small. + * Packets in ofo or receive queues can stay a long time. + * Better try to coalesce them right now to avoid future collapses. + * Returns true if caller should free @from instead of queueing it + */ +static bool tcp_try_coalesce(struct sock *sk, + struct sk_buff *to, + struct sk_buff *from, + bool *fragstolen) +{ + int delta; + + *fragstolen = false; + + if (tcp_hdr(from)->fin) + return false; + if (!skb_try_coalesce(to, from, fragstolen, &delta)) + return false; + + atomic_add(delta, &sk->sk_rmem_alloc); + sk_mem_charge(sk, delta); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRCVCOALESCE); + TCP_SKB_CB(to)->end_seq = TCP_SKB_CB(from)->end_seq; + TCP_SKB_CB(to)->ack_seq = TCP_SKB_CB(from)->ack_seq; + return true; +} + static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); @@ -4484,23 +4604,13 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) end_seq = TCP_SKB_CB(skb)->end_seq; if (seq == TCP_SKB_CB(skb1)->end_seq) { - /* Packets in ofo can stay in queue a long time. - * Better try to coalesce them right now - * to avoid future tcp_collapse_ofo_queue(), - * probably the most expensive function in tcp stack. - */ - if (skb->len <= skb_tailroom(skb1) && !tcp_hdr(skb)->fin) { - NET_INC_STATS_BH(sock_net(sk), - LINUX_MIB_TCPRCVCOALESCE); - BUG_ON(skb_copy_bits(skb, 0, - skb_put(skb1, skb->len), - skb->len)); - TCP_SKB_CB(skb1)->end_seq = end_seq; - TCP_SKB_CB(skb1)->ack_seq = TCP_SKB_CB(skb)->ack_seq; - __kfree_skb(skb); - skb = NULL; - } else { + bool fragstolen; + + if (!tcp_try_coalesce(sk, skb1, skb, &fragstolen)) { __skb_queue_after(&tp->out_of_order_queue, skb1, skb); + } else { + kfree_skb_partial(skb, fragstolen); + skb = NULL; } if (!tp->rx_opt.num_sacks || @@ -4576,12 +4686,65 @@ end: skb_set_owner_r(skb, sk); } +static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int hdrlen, + bool *fragstolen) +{ + int eaten; + struct sk_buff *tail = skb_peek_tail(&sk->sk_receive_queue); + + __skb_pull(skb, hdrlen); + eaten = (tail && + tcp_try_coalesce(sk, tail, skb, fragstolen)) ? 1 : 0; + tcp_sk(sk)->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + if (!eaten) { + __skb_queue_tail(&sk->sk_receive_queue, skb); + skb_set_owner_r(skb, sk); + } + return eaten; +} + +int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size) +{ + struct sk_buff *skb; + struct tcphdr *th; + bool fragstolen; + + if (tcp_try_rmem_schedule(sk, size + sizeof(*th))) + goto err; + + skb = alloc_skb(size + sizeof(*th), sk->sk_allocation); + if (!skb) + goto err; + + th = (struct tcphdr *)skb_put(skb, sizeof(*th)); + skb_reset_transport_header(skb); + memset(th, 0, sizeof(*th)); + + if (memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size)) + goto err_free; + + TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt; + TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + size; + TCP_SKB_CB(skb)->ack_seq = tcp_sk(sk)->snd_una - 1; + + if (tcp_queue_rcv(sk, skb, sizeof(*th), &fragstolen)) { + WARN_ON_ONCE(fragstolen); /* should not happen */ + __kfree_skb(skb); + } + return size; + +err_free: + kfree_skb(skb); +err: + return -ENOMEM; +} static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); struct tcp_sock *tp = tcp_sk(sk); int eaten = -1; + bool fragstolen = false; if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) goto drop; @@ -4626,8 +4789,7 @@ queue_and_out: tcp_try_rmem_schedule(sk, skb->truesize)) goto drop; - skb_set_owner_r(skb, sk); - __skb_queue_tail(&sk->sk_receive_queue, skb); + eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen); } tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; if (skb->len) @@ -4651,7 +4813,7 @@ queue_and_out: tcp_fast_path_check(sk); if (eaten > 0) - __kfree_skb(skb); + kfree_skb_partial(skb, fragstolen); else if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk, 0); return; @@ -4871,10 +5033,10 @@ static void tcp_collapse_ofo_queue(struct sock *sk) * Purge the out-of-order queue. * Return true if queue was pruned. */ -static int tcp_prune_ofo_queue(struct sock *sk) +static bool tcp_prune_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - int res = 0; + bool res = false; if (!skb_queue_empty(&tp->out_of_order_queue)) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_OFOPRUNED); @@ -4888,7 +5050,7 @@ static int tcp_prune_ofo_queue(struct sock *sk) if (tp->rx_opt.sack_ok) tcp_sack_reset(&tp->rx_opt); sk_mem_reclaim(sk); - res = 1; + res = true; } return res; } @@ -4965,7 +5127,7 @@ void tcp_cwnd_application_limited(struct sock *sk) tp->snd_cwnd_stamp = tcp_time_stamp; } -static int tcp_should_expand_sndbuf(const struct sock *sk) +static bool tcp_should_expand_sndbuf(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); @@ -4973,21 +5135,21 @@ static int tcp_should_expand_sndbuf(const struct sock *sk) * not modify it. */ if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) - return 0; + return false; /* If we are under global TCP memory pressure, do not expand. */ if (sk_under_memory_pressure(sk)) - return 0; + return false; /* If we are under soft global TCP memory pressure, do not expand. */ if (sk_memory_allocated(sk) >= sk_prot_mem_limits(sk, 0)) - return 0; + return false; /* If we filled the congestion window, do not expand. */ if (tp->packets_out >= tp->snd_cwnd) - return 0; + return false; - return 1; + return true; } /* When incoming ACK allowed to free some skb from write_queue, @@ -5213,19 +5375,19 @@ static inline int tcp_checksum_complete_user(struct sock *sk, } #ifdef CONFIG_NET_DMA -static int tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb, +static bool tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb, int hlen) { struct tcp_sock *tp = tcp_sk(sk); int chunk = skb->len - hlen; int dma_cookie; - int copied_early = 0; + bool copied_early = false; if (tp->ucopy.wakeup) - return 0; + return false; if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY); + tp->ucopy.dma_chan = net_dma_find_channel(); if (tp->ucopy.dma_chan && skb_csum_unnecessary(skb)) { @@ -5238,7 +5400,7 @@ static int tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb, goto out; tp->ucopy.dma_cookie = dma_cookie; - copied_early = 1; + copied_early = true; tp->ucopy.len -= chunk; tp->copied_seq += chunk; @@ -5430,6 +5592,7 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, } else { int eaten = 0; int copied_early = 0; + bool fragstolen = false; if (tp->copied_seq == tp->rcv_nxt && len - tcp_header_len <= tp->ucopy.len) { @@ -5487,10 +5650,8 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITS); /* Bulk data transfer: receiver */ - __skb_pull(skb, tcp_header_len); - __skb_queue_tail(&sk->sk_receive_queue, skb); - skb_set_owner_r(skb, sk); - tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + eaten = tcp_queue_rcv(sk, skb, tcp_header_len, + &fragstolen); } tcp_event_data_recv(sk, skb); @@ -5512,7 +5673,7 @@ no_ack: else #endif if (eaten) - __kfree_skb(skb); + kfree_skb_partial(skb, fragstolen); else sk->sk_data_ready(sk, 0); return 0; @@ -5556,6 +5717,44 @@ discard: } EXPORT_SYMBOL(tcp_rcv_established); +void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); + + tcp_set_state(sk, TCP_ESTABLISHED); + + if (skb != NULL) + security_inet_conn_established(sk, skb); + + /* Make sure socket is routed, for correct metrics. */ + icsk->icsk_af_ops->rebuild_header(sk); + + tcp_init_metrics(sk); + + tcp_init_congestion_control(sk); + + /* Prevent spurious tcp_cwnd_restart() on first data + * packet. + */ + tp->lsndtime = tcp_time_stamp; + + tcp_init_buffer_space(sk); + + if (sock_flag(sk, SOCK_KEEPOPEN)) + inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp)); + + if (!tp->rx_opt.snd_wscale) + __tcp_fast_path_on(tp, tp->snd_wnd); + else + tp->pred_flags = 0; + + if (!sock_flag(sk, SOCK_DEAD)) { + sk->sk_state_change(sk); + sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT); + } +} + static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, unsigned int len) { @@ -5688,36 +5887,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, } smp_mb(); - tcp_set_state(sk, TCP_ESTABLISHED); - - security_inet_conn_established(sk, skb); - - /* Make sure socket is routed, for correct metrics. */ - icsk->icsk_af_ops->rebuild_header(sk); - tcp_init_metrics(sk); - - tcp_init_congestion_control(sk); - - /* Prevent spurious tcp_cwnd_restart() on first data - * packet. - */ - tp->lsndtime = tcp_time_stamp; - - tcp_init_buffer_space(sk); - - if (sock_flag(sk, SOCK_KEEPOPEN)) - inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp)); - - if (!tp->rx_opt.snd_wscale) - __tcp_fast_path_on(tp, tp->snd_wnd); - else - tp->pred_flags = 0; - - if (!sock_flag(sk, SOCK_DEAD)) { - sk->sk_state_change(sk); - sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT); - } + tcp_finish_connect(sk, skb); if (sk->sk_write_pending || icsk->icsk_accept_queue.rskq_defer_accept || @@ -5731,8 +5902,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, */ inet_csk_schedule_ack(sk); icsk->icsk_ack.lrcvtime = tcp_time_stamp; - icsk->icsk_ack.ato = TCP_ATO_MIN; - tcp_incr_quickack(sk); tcp_enter_quickack_mode(sk); inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, TCP_DELACK_MAX, TCP_RTO_MAX); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3a25cf743f8..a43b87dfe80 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -138,6 +138,14 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) } EXPORT_SYMBOL_GPL(tcp_twsk_unique); +static int tcp_repair_connect(struct sock *sk) +{ + tcp_connect_init(sk); + tcp_finish_connect(sk, NULL); + + return 0; +} + /* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { @@ -196,7 +204,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) /* Reset inherited state */ tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; - tp->write_seq = 0; + if (likely(!tp->repair)) + tp->write_seq = 0; } if (tcp_death_row.sysctl_tw_recycle && @@ -247,7 +256,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) sk->sk_gso_type = SKB_GSO_TCPV4; sk_setup_caps(sk, &rt->dst); - if (!tp->write_seq) + if (!tp->write_seq && likely(!tp->repair)) tp->write_seq = secure_tcp_sequence_number(inet->inet_saddr, inet->inet_daddr, inet->inet_sport, @@ -255,7 +264,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_id = tp->write_seq ^ jiffies; - err = tcp_connect(sk); + if (likely(!tp->repair)) + err = tcp_connect(sk); + else + err = tcp_repair_connect(sk); + rt = NULL; if (err) goto failure; @@ -853,14 +866,14 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req) } /* - * Return 1 if a syncookie should be sent + * Return true if a syncookie should be sent */ -int tcp_syn_flood_action(struct sock *sk, +bool tcp_syn_flood_action(struct sock *sk, const struct sk_buff *skb, const char *proto) { const char *msg = "Dropping request"; - int want_cookie = 0; + bool want_cookie = false; struct listen_sock *lopt; @@ -868,7 +881,7 @@ int tcp_syn_flood_action(struct sock *sk, #ifdef CONFIG_SYN_COOKIES if (sysctl_tcp_syncookies) { msg = "Sending cookies"; - want_cookie = 1; + want_cookie = true; NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES); } else #endif @@ -1183,7 +1196,7 @@ clear_hash_noput: } EXPORT_SYMBOL(tcp_v4_md5_hash_skb); -static int tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) +static bool tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) { /* * This gets called for each TCP segment that arrives @@ -1206,16 +1219,16 @@ static int tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) /* We've parsed the options - do we have a hash? */ if (!hash_expected && !hash_location) - return 0; + return false; if (hash_expected && !hash_location) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); - return 1; + return true; } if (!hash_expected && hash_location) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); - return 1; + return true; } /* Okay, so this is hash_expected and hash_location - @@ -1226,15 +1239,14 @@ static int tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) NULL, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { - if (net_ratelimit()) { - pr_info("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n", - &iph->saddr, ntohs(th->source), - &iph->daddr, ntohs(th->dest), - genhash ? " tcp_v4_calc_md5_hash failed" : ""); - } - return 1; + net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n", + &iph->saddr, ntohs(th->source), + &iph->daddr, ntohs(th->dest), + genhash ? " tcp_v4_calc_md5_hash failed" + : ""); + return true; } - return 0; + return false; } #endif @@ -1268,7 +1280,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) __be32 saddr = ip_hdr(skb)->saddr; __be32 daddr = ip_hdr(skb)->daddr; __u32 isn = TCP_SKB_CB(skb)->when; - int want_cookie = 0; + bool want_cookie = false; /* Never answer to SYNs send to broadcast or multicast */ if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) @@ -1327,7 +1339,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) while (l-- > 0) *c++ ^= *hash_location++; - want_cookie = 0; /* not our kind of cookie */ + want_cookie = false; /* not our kind of cookie */ tmp_ext.cookie_out_never = 0; /* false */ tmp_ext.cookie_plus = tmp_opt.cookie_plus; } else if (!tp->rx_opt.cookie_in_always) { @@ -1355,7 +1367,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_free; if (!want_cookie || tmp_opt.tstamp_ok) - TCP_ECN_create_request(req, tcp_hdr(skb)); + TCP_ECN_create_request(req, skb); if (want_cookie) { isn = cookie_v4_init_sequence(sk, skb, &req->mss); @@ -1730,7 +1742,7 @@ process: #ifdef CONFIG_NET_DMA struct tcp_sock *tp = tcp_sk(sk); if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY); + tp->ucopy.dma_chan = net_dma_find_channel(); if (tp->ucopy.dma_chan) ret = tcp_v4_do_rcv(sk, skb); else @@ -1739,7 +1751,8 @@ process: if (!tcp_prequeue(sk, skb)) ret = tcp_v4_do_rcv(sk, skb); } - } else if (unlikely(sk_add_backlog(sk, skb))) { + } else if (unlikely(sk_add_backlog(sk, skb, + sk->sk_rcvbuf + sk->sk_sndbuf))) { bh_unlock_sock(sk); NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP); goto discard_and_relse; @@ -1875,64 +1888,15 @@ static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = { static int tcp_v4_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_sock *tp = tcp_sk(sk); - skb_queue_head_init(&tp->out_of_order_queue); - tcp_init_xmit_timers(sk); - tcp_prequeue_init(tp); - - icsk->icsk_rto = TCP_TIMEOUT_INIT; - tp->mdev = TCP_TIMEOUT_INIT; - - /* So many TCP implementations out there (incorrectly) count the - * initial SYN frame in their delayed-ACK and congestion control - * algorithms that we must have the following bandaid to talk - * efficiently to them. -DaveM - */ - tp->snd_cwnd = TCP_INIT_CWND; - - /* See draft-stevens-tcpca-spec-01 for discussion of the - * initialization of these values. - */ - tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; - tp->snd_cwnd_clamp = ~0; - tp->mss_cache = TCP_MSS_DEFAULT; - - tp->reordering = sysctl_tcp_reordering; - icsk->icsk_ca_ops = &tcp_init_congestion_ops; - - sk->sk_state = TCP_CLOSE; - - sk->sk_write_space = sk_stream_write_space; - sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); + tcp_init_sock(sk); icsk->icsk_af_ops = &ipv4_specific; - icsk->icsk_sync_mss = tcp_sync_mss; + #ifdef CONFIG_TCP_MD5SIG - tp->af_specific = &tcp_sock_ipv4_specific; + tcp_sk(sk)->af_specific = &tcp_sock_ipv4_specific; #endif - /* TCP Cookie Transactions */ - if (sysctl_tcp_cookie_size > 0) { - /* Default, cookies without s_data_payload. */ - tp->cookie_values = - kzalloc(sizeof(*tp->cookie_values), - sk->sk_allocation); - if (tp->cookie_values != NULL) - kref_init(&tp->cookie_values->kref); - } - /* Presumed zeroed, in order of appearance: - * cookie_in_always, cookie_out_never, - * s_data_constant, s_data_in, s_data_out - */ - sk->sk_sndbuf = sysctl_tcp_wmem[1]; - sk->sk_rcvbuf = sysctl_tcp_rmem[1]; - - local_bh_disable(); - sock_update_memcg(sk); - sk_sockets_allocated_inc(sk); - local_bh_enable(); - return 0; } @@ -2109,7 +2073,7 @@ static void *listening_get_idx(struct seq_file *seq, loff_t *pos) return rc; } -static inline int empty_bucket(struct tcp_iter_state *st) +static inline bool empty_bucket(struct tcp_iter_state *st) { return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain) && hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].twchain); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 3cabafb5cdd..b85d9fe7d66 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -55,7 +55,7 @@ EXPORT_SYMBOL_GPL(tcp_death_row); * state. */ -static int tcp_remember_stamp(struct sock *sk) +static bool tcp_remember_stamp(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -72,13 +72,13 @@ static int tcp_remember_stamp(struct sock *sk) } if (release_it) inet_putpeer(peer); - return 1; + return true; } - return 0; + return false; } -static int tcp_tw_remember_stamp(struct inet_timewait_sock *tw) +static bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw) { struct sock *sk = (struct sock *) tw; struct inet_peer *peer; @@ -94,17 +94,17 @@ static int tcp_tw_remember_stamp(struct inet_timewait_sock *tw) peer->tcp_ts = tcptw->tw_ts_recent; } inet_putpeer(peer); - return 1; + return true; } - return 0; + return false; } -static __inline__ int tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win) +static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win) { if (seq == s_win) - return 1; + return true; if (after(end_seq, s_win) && before(seq, e_win)) - return 1; + return true; return seq == e_win && seq == end_seq; } @@ -143,7 +143,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, struct tcp_options_received tmp_opt; const u8 *hash_location; struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); - int paws_reject = 0; + bool paws_reject = false; tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) { @@ -316,7 +316,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) struct inet_timewait_sock *tw = NULL; const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); - int recycle_ok = 0; + bool recycle_ok = false; if (tcp_death_row.sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp) recycle_ok = tcp_remember_stamp(sk); @@ -482,6 +482,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newtp->sacked_out = 0; newtp->fackets_out = 0; newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH; + tcp_enable_early_retrans(newtp); /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control @@ -574,7 +575,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct sock *child; const struct tcphdr *th = tcp_hdr(skb); __be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK); - int paws_reject = 0; + bool paws_reject = false; tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(struct tcphdr)>>2)) { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 364784a9193..803cbfe82fb 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -34,6 +34,8 @@ * */ +#define pr_fmt(fmt) "TCP: " fmt + #include <net/tcp.h> #include <linux/compiler.h> @@ -78,9 +80,8 @@ static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) tp->frto_counter = 3; tp->packets_out += tcp_skb_pcount(skb); - if (!prior_packets) - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - inet_csk(sk)->icsk_rto, TCP_RTO_MAX); + if (!prior_packets || tp->early_retrans_delayed) + tcp_rearm_rto(sk); } /* SND.NXT, if window was not shrunk. @@ -369,7 +370,7 @@ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags) TCP_SKB_CB(skb)->end_seq = seq; } -static inline int tcp_urg_mode(const struct tcp_sock *tp) +static inline bool tcp_urg_mode(const struct tcp_sock *tp) { return tp->snd_una != tp->snd_up; } @@ -563,13 +564,13 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, /* Compute TCP options for SYN packets. This is not the final * network wire format yet. */ -static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, +static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_cookie_values *cvp = tp->cookie_values; - unsigned remaining = MAX_TCP_OPTION_SPACE; + unsigned int remaining = MAX_TCP_OPTION_SPACE; u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ? tcp_cookie_size_check(cvp->cookie_desired) : 0; @@ -663,15 +664,15 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, } /* Set up TCP options for SYN-ACKs. */ -static unsigned tcp_synack_options(struct sock *sk, +static unsigned int tcp_synack_options(struct sock *sk, struct request_sock *req, - unsigned mss, struct sk_buff *skb, + unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5, struct tcp_extend_values *xvp) { struct inet_request_sock *ireq = inet_rsk(req); - unsigned remaining = MAX_TCP_OPTION_SPACE; + unsigned int remaining = MAX_TCP_OPTION_SPACE; u8 cookie_plus = (xvp != NULL && !xvp->cookie_out_never) ? xvp->cookie_plus : 0; @@ -742,13 +743,13 @@ static unsigned tcp_synack_options(struct sock *sk, /* Compute TCP options for ESTABLISHED sockets. This is not the * final wire format yet. */ -static unsigned tcp_established_options(struct sock *sk, struct sk_buff *skb, +static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5) { struct tcp_skb_cb *tcb = skb ? TCP_SKB_CB(skb) : NULL; struct tcp_sock *tp = tcp_sk(sk); - unsigned size = 0; + unsigned int size = 0; unsigned int eff_sacks; #ifdef CONFIG_TCP_MD5SIG @@ -770,9 +771,9 @@ static unsigned tcp_established_options(struct sock *sk, struct sk_buff *skb, eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack; if (unlikely(eff_sacks)) { - const unsigned remaining = MAX_TCP_OPTION_SPACE - size; + const unsigned int remaining = MAX_TCP_OPTION_SPACE - size; opts->num_sack_blocks = - min_t(unsigned, eff_sacks, + min_t(unsigned int, eff_sacks, (remaining - TCPOLEN_SACK_BASE_ALIGNED) / TCPOLEN_SACK_PERBLOCK); size += TCPOLEN_SACK_BASE_ALIGNED + @@ -801,7 +802,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, struct tcp_sock *tp; struct tcp_skb_cb *tcb; struct tcp_out_options opts; - unsigned tcp_options_size, tcp_header_size; + unsigned int tcp_options_size, tcp_header_size; struct tcp_md5sig_key *md5; struct tcphdr *th; int err; @@ -1096,6 +1097,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len) eat = min_t(int, len, skb_headlen(skb)); if (eat) { __skb_pull(skb, eat); + skb->avail_size -= eat; len -= eat; if (!len) return; @@ -1149,7 +1151,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) } /* Calculate MSS. Not accounting for SACKs here. */ -int tcp_mtu_to_mss(const struct sock *sk, int pmtu) +int tcp_mtu_to_mss(struct sock *sk, int pmtu) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1160,6 +1162,14 @@ int tcp_mtu_to_mss(const struct sock *sk, int pmtu) */ mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr); + /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ + if (icsk->icsk_af_ops->net_frag_header_len) { + const struct dst_entry *dst = __sk_dst_get(sk); + + if (dst && dst_allfrag(dst)) + mss_now -= icsk->icsk_af_ops->net_frag_header_len; + } + /* Clamp it (mss_clamp does not include tcp options) */ if (mss_now > tp->rx_opt.mss_clamp) mss_now = tp->rx_opt.mss_clamp; @@ -1178,7 +1188,7 @@ int tcp_mtu_to_mss(const struct sock *sk, int pmtu) } /* Inverse of above */ -int tcp_mss_to_mtu(const struct sock *sk, int mss) +int tcp_mss_to_mtu(struct sock *sk, int mss) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1189,6 +1199,13 @@ int tcp_mss_to_mtu(const struct sock *sk, int mss) icsk->icsk_ext_hdr_len + icsk->icsk_af_ops->net_header_len; + /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ + if (icsk->icsk_af_ops->net_frag_header_len) { + const struct dst_entry *dst = __sk_dst_get(sk); + + if (dst && dst_allfrag(dst)) + mtu += icsk->icsk_af_ops->net_frag_header_len; + } return mtu; } @@ -1258,7 +1275,7 @@ unsigned int tcp_current_mss(struct sock *sk) const struct tcp_sock *tp = tcp_sk(sk); const struct dst_entry *dst = __sk_dst_get(sk); u32 mss_now; - unsigned header_len; + unsigned int header_len; struct tcp_out_options opts; struct tcp_md5sig_key *md5; @@ -1374,33 +1391,33 @@ static int tcp_init_tso_segs(const struct sock *sk, struct sk_buff *skb, } /* Minshall's variant of the Nagle send check. */ -static inline int tcp_minshall_check(const struct tcp_sock *tp) +static inline bool tcp_minshall_check(const struct tcp_sock *tp) { return after(tp->snd_sml, tp->snd_una) && !after(tp->snd_sml, tp->snd_nxt); } -/* Return 0, if packet can be sent now without violation Nagle's rules: +/* Return false, if packet can be sent now without violation Nagle's rules: * 1. It is full sized. * 2. Or it contains FIN. (already checked by caller) * 3. Or TCP_CORK is not set, and TCP_NODELAY is set. * 4. Or TCP_CORK is not set, and all sent packets are ACKed. * With Minshall's modification: all sent small packets are ACKed. */ -static inline int tcp_nagle_check(const struct tcp_sock *tp, +static inline bool tcp_nagle_check(const struct tcp_sock *tp, const struct sk_buff *skb, - unsigned mss_now, int nonagle) + unsigned int mss_now, int nonagle) { return skb->len < mss_now && ((nonagle & TCP_NAGLE_CORK) || (!nonagle && tp->packets_out && tcp_minshall_check(tp))); } -/* Return non-zero if the Nagle test allows this packet to be +/* Return true if the Nagle test allows this packet to be * sent now. */ -static inline int tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buff *skb, - unsigned int cur_mss, int nonagle) +static inline bool tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buff *skb, + unsigned int cur_mss, int nonagle) { /* Nagle rule does not apply to frames, which sit in the middle of the * write_queue (they have no chances to get new data). @@ -1409,24 +1426,25 @@ static inline int tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buff * argument based upon the location of SKB in the send queue. */ if (nonagle & TCP_NAGLE_PUSH) - return 1; + return true; /* Don't use the nagle rule for urgent data (or for the final FIN). * Nagle can be ignored during F-RTO too (see RFC4138). */ if (tcp_urg_mode(tp) || (tp->frto_counter == 2) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) - return 1; + return true; if (!tcp_nagle_check(tp, skb, cur_mss, nonagle)) - return 1; + return true; - return 0; + return false; } /* Does at least the first segment of SKB fit into the send window? */ -static inline int tcp_snd_wnd_test(const struct tcp_sock *tp, const struct sk_buff *skb, - unsigned int cur_mss) +static bool tcp_snd_wnd_test(const struct tcp_sock *tp, + const struct sk_buff *skb, + unsigned int cur_mss) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; @@ -1459,7 +1477,7 @@ static unsigned int tcp_snd_test(const struct sock *sk, struct sk_buff *skb, } /* Test if sending is allowed right now. */ -int tcp_may_send_now(struct sock *sk) +bool tcp_may_send_now(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb = tcp_send_head(sk); @@ -1529,7 +1547,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, * * This algorithm is from John Heffner. */ -static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) +static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1589,11 +1607,11 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) /* Ok, it looks like it is advisable to defer. */ tp->tso_deferred = 1 | (jiffies << 1); - return 1; + return true; send_now: tp->tso_deferred = 0; - return 0; + return false; } /* Create a new MTU probe if we are ready. @@ -1735,11 +1753,11 @@ static int tcp_mtu_probe(struct sock *sk) * snd_up-64k-mss .. snd_up cannot be large. However, taking into * account rare use of URG, this is not a big flaw. * - * Returns 1, if no segments are in flight and we have queued segments, but - * cannot send anything now because of SWS or another problem. + * Returns true, if no segments are in flight and we have queued segments, + * but cannot send anything now because of SWS or another problem. */ -static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, - int push_one, gfp_t gfp) +static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, + int push_one, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; @@ -1753,7 +1771,7 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, /* Do MTU probing. */ result = tcp_mtu_probe(sk); if (!result) { - return 0; + return false; } else if (result > 0) { sent_pkts = 1; } @@ -1812,7 +1830,7 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (likely(sent_pkts)) { tcp_cwnd_validate(sk); - return 0; + return false; } return !tp->packets_out && tcp_send_head(sk); } @@ -2011,22 +2029,22 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) } /* Check if coalescing SKBs is legal. */ -static int tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) +static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) { if (tcp_skb_pcount(skb) > 1) - return 0; + return false; /* TODO: SACK collapsing could be used to remove this condition */ if (skb_shinfo(skb)->nr_frags != 0) - return 0; + return false; if (skb_cloned(skb)) - return 0; + return false; if (skb == tcp_send_head(sk)) - return 0; + return false; /* Some heurestics for collapsing over SACK'd could be invented */ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) - return 0; + return false; - return 1; + return true; } /* Collapse packets in the retransmit queue to make to create @@ -2037,7 +2055,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb = to, *tmp; - int first = 1; + bool first = true; if (!sysctl_tcp_retrans_collapse) return; @@ -2051,7 +2069,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, space -= skb->len; if (first) { - first = 0; + first = false; continue; } @@ -2060,7 +2078,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, /* Punt if not enough space exists in the first SKB for * the data in the second */ - if (skb->len > skb_tailroom(to)) + if (skb->len > skb_availroom(to)) break; if (after(TCP_SKB_CB(skb)->end_seq, tcp_wnd_end(tp))) @@ -2166,8 +2184,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) #if FASTRETRANS_DEBUG > 0 if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { - if (net_ratelimit()) - printk(KERN_DEBUG "retrans_out leaked.\n"); + net_dbg_ratelimited("retrans_out leaked\n"); } #endif if (!tp->retrans_out) @@ -2192,18 +2209,18 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) /* Check if we forward retransmits are possible in the current * window/congestion state. */ -static int tcp_can_forward_retransmit(struct sock *sk) +static bool tcp_can_forward_retransmit(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); /* Forward retransmissions are possible only during Recovery. */ if (icsk->icsk_ca_state != TCP_CA_Recovery) - return 0; + return false; /* No forward retransmissions in Reno are possible. */ if (tcp_is_reno(tp)) - return 0; + return false; /* Yeah, we have to make difficult choice between forward transmission * and retransmission... Both ways have their merits... @@ -2214,9 +2231,9 @@ static int tcp_can_forward_retransmit(struct sock *sk) */ if (tcp_may_send_now(sk)) - return 0; + return false; - return 1; + return true; } /* This gets called after a retransmit timeout, and the initially @@ -2401,7 +2418,7 @@ int tcp_send_synack(struct sock *sk) skb = tcp_write_queue_head(sk); if (skb == NULL || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { - printk(KERN_DEBUG "tcp_send_synack: wrong queue state\n"); + pr_debug("%s: wrong queue state\n", __func__); return -EFAULT; } if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) { @@ -2561,7 +2578,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, EXPORT_SYMBOL(tcp_make_synack); /* Do all connect socket setups that can be done AF independent. */ -static void tcp_connect_init(struct sock *sk) +void tcp_connect_init(struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -2616,9 +2633,12 @@ static void tcp_connect_init(struct sock *sk) tp->snd_una = tp->write_seq; tp->snd_sml = tp->write_seq; tp->snd_up = tp->write_seq; - tp->rcv_nxt = 0; - tp->rcv_wup = 0; - tp->copied_seq = 0; + tp->snd_nxt = tp->write_seq; + + if (likely(!tp->repair)) + tp->rcv_nxt = 0; + tp->rcv_wup = tp->rcv_nxt; + tp->copied_seq = tp->rcv_nxt; inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT; inet_csk(sk)->icsk_retransmits = 0; @@ -2641,7 +2661,6 @@ int tcp_connect(struct sock *sk) /* Reserve space for headers. */ skb_reserve(buff, MAX_TCP_HEADER); - tp->snd_nxt = tp->write_seq; tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); TCP_ECN_send_syn(sk, buff); @@ -2790,6 +2809,15 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent) return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC); } +void tcp_send_window_probe(struct sock *sk) +{ + if (sk->sk_state == TCP_ESTABLISHED) { + tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1; + tcp_sk(sk)->snd_nxt = tcp_sk(sk)->write_seq; + tcp_xmit_probe_skb(sk, 0); + } +} + /* Initiate keepalive or window probe from timer. */ int tcp_write_wakeup(struct sock *sk) { diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index a981cdc0a6e..4526fe68e60 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -91,7 +91,7 @@ static inline int tcp_probe_avail(void) * Note: arguments must match tcp_rcv_established()! */ static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, - struct tcphdr *th, unsigned len) + struct tcphdr *th, unsigned int len) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_sock *inet = inet_sk(sk); @@ -138,7 +138,7 @@ static struct jprobe tcp_jprobe = { .entry = jtcp_rcv_established, }; -static int tcpprobe_open(struct inode * inode, struct file * file) +static int tcpprobe_open(struct inode *inode, struct file *file) { /* Reset (empty) log */ spin_lock_bh(&tcp_probe.lock); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 34d4a02c2f1..e911e6c523e 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -319,6 +319,11 @@ void tcp_retransmit_timer(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + if (tp->early_retrans_delayed) { + tcp_resume_early_retransmit(sk); + return; + } + if (!tp->packets_out) goto out; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index fe141052a1b..609397ee78f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -107,6 +107,7 @@ #include <net/checksum.h> #include <net/xfrm.h> #include <trace/events/udp.h> +#include <linux/static_key.h> #include "udp_impl.h" struct udp_table udp_table __read_mostly; @@ -206,7 +207,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, if (!snum) { int low, high, remaining; - unsigned rand; + unsigned int rand; unsigned short first, last; DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN); @@ -846,7 +847,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, * Get and verify the address. */ if (msg->msg_name) { - struct sockaddr_in * usin = (struct sockaddr_in *)msg->msg_name; + struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name; if (msg->msg_namelen < sizeof(*usin)) return -EINVAL; if (usin->sin_family != AF_INET) { @@ -1379,6 +1380,14 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } +static struct static_key udp_encap_needed __read_mostly; +void udp_encap_enable(void) +{ + if (!static_key_enabled(&udp_encap_needed)) + static_key_slow_inc(&udp_encap_needed); +} +EXPORT_SYMBOL(udp_encap_enable); + /* returns: * -1: error * 0: success @@ -1400,7 +1409,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) goto drop; nf_reset(skb); - if (up->encap_type) { + if (static_key_false(&udp_encap_needed) && up->encap_type) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); /* @@ -1470,7 +1479,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) goto drop; - if (sk_rcvqueues_full(sk, skb)) + if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) goto drop; rc = 0; @@ -1479,7 +1488,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) bh_lock_sock(sk); if (!sock_owned_by_user(sk)) rc = __udp_queue_rcv_skb(sk, skb); - else if (sk_add_backlog(sk, skb)) { + else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) { bh_unlock_sock(sk); goto drop; } @@ -1760,6 +1769,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, /* FALLTHROUGH */ case UDP_ENCAP_L2TPINUDP: up->encap_type = val; + udp_encap_enable(); break; default: err = -ENOPROTOOPT; @@ -2163,9 +2173,15 @@ void udp4_proc_exit(void) static __initdata unsigned long uhash_entries; static int __init set_uhash_entries(char *str) { + ssize_t ret; + if (!str) return 0; - uhash_entries = simple_strtoul(str, &str, 0); + + ret = kstrtoul(str, 0, &uhash_entries); + if (ret) + return 0; + if (uhash_entries && uhash_entries < UDP_HTABLE_SIZE_MIN) uhash_entries = UDP_HTABLE_SIZE_MIN; return 1; diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 8a949f19deb..a7f86a3cd50 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -146,9 +146,17 @@ static int udp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, return udp_dump_one(&udp_table, in_skb, nlh, req); } +static void udp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, + void *info) +{ + r->idiag_rqueue = sk_rmem_alloc_get(sk); + r->idiag_wqueue = sk_wmem_alloc_get(sk); +} + static const struct inet_diag_handler udp_diag_handler = { .dump = udp_diag_dump, .dump_one = udp_diag_dump_one, + .idiag_get_info = udp_diag_get_info, .idiag_type = IPPROTO_UDP, }; @@ -167,6 +175,7 @@ static int udplite_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr * static const struct inet_diag_handler udplite_diag_handler = { .dump = udplite_diag_dump, .dump_one = udplite_diag_dump_one, + .idiag_get_info = udp_diag_get_info, .idiag_type = IPPROTO_UDPLITE, }; diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h index aaad650d47d..5a681e298b9 100644 --- a/net/ipv4/udp_impl.h +++ b/net/ipv4/udp_impl.h @@ -25,7 +25,7 @@ extern int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len); extern int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); -extern int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb); +extern int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); extern void udp_destroy_sock(struct sock *sk); #ifdef CONFIG_PROC_FS diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index a0b4c5da8d4..0d3426cb5c4 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -152,7 +152,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) case IPPROTO_AH: if (pskb_may_pull(skb, xprth + 8 - skb->data)) { - __be32 *ah_hdr = (__be32*)xprth; + __be32 *ah_hdr = (__be32 *)xprth; fl4->fl4_ipsec_spi = ah_hdr[1]; } @@ -298,8 +298,8 @@ void __init xfrm4_init(int rt_max_size) xfrm4_state_init(); xfrm4_policy_init(); #ifdef CONFIG_SYSCTL - sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv4_ctl_path, - xfrm4_policy_table); + sysctl_hdr = register_net_sysctl(&init_net, "net/ipv4", + xfrm4_policy_table); #endif } diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 36d7437ac05..5728695b544 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -69,7 +69,7 @@ config IPV6_OPTIMISTIC_DAD config INET6_AH tristate "IPv6: AH transformation" - select XFRM + select XFRM_ALGO select CRYPTO select CRYPTO_HMAC select CRYPTO_MD5 @@ -81,7 +81,7 @@ config INET6_AH config INET6_ESP tristate "IPv6: ESP transformation" - select XFRM + select XFRM_ALGO select CRYPTO select CRYPTO_AUTHENC select CRYPTO_HMAC diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 6a3bb6077e1..8f6411c9718 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -38,6 +38,8 @@ * status etc. */ +#define pr_fmt(fmt) "IPv6: " fmt + #include <linux/errno.h> #include <linux/types.h> #include <linux/kernel.h> @@ -66,6 +68,7 @@ #include <net/sock.h> #include <net/snmp.h> +#include <net/af_ieee802154.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/ndisc.h> @@ -149,7 +152,7 @@ static void addrconf_type_change(struct net_device *dev, unsigned long event); static int addrconf_ifdown(struct net_device *dev, int how); -static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags); +static void addrconf_dad_start(struct inet6_ifaddr *ifp); static void addrconf_dad_timer(unsigned long data); static void addrconf_dad_completed(struct inet6_ifaddr *ifp); static void addrconf_dad_run(struct inet6_dev *idev); @@ -326,20 +329,19 @@ void in6_dev_finish_destroy(struct inet6_dev *idev) WARN_ON(idev->mc_list != NULL); #ifdef NET_REFCNT_DEBUG - printk(KERN_DEBUG "in6_dev_finish_destroy: %s\n", dev ? dev->name : "NIL"); + pr_debug("%s: %s\n", __func__, dev ? dev->name : "NIL"); #endif dev_put(dev); if (!idev->dead) { - pr_warning("Freeing alive inet6 device %p\n", idev); + pr_warn("Freeing alive inet6 device %p\n", idev); return; } snmp6_free_dev(idev); kfree_rcu(idev, rcu); } - EXPORT_SYMBOL(in6_dev_finish_destroy); -static struct inet6_dev * ipv6_add_dev(struct net_device *dev) +static struct inet6_dev *ipv6_add_dev(struct net_device *dev) { struct inet6_dev *ndev; @@ -372,7 +374,7 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) if (snmp6_alloc_dev(ndev) < 0) { ADBG((KERN_WARNING - "%s(): cannot allocate memory for statistics; dev=%s.\n", + "%s: cannot allocate memory for statistics; dev=%s.\n", __func__, dev->name)); neigh_parms_release(&nd_tbl, ndev->nd_parms); dev_put(dev); @@ -382,7 +384,7 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) if (snmp6_register_dev(ndev) < 0) { ADBG((KERN_WARNING - "%s(): cannot create /proc/net/dev_snmp6/%s\n", + "%s: cannot create /proc/net/dev_snmp6/%s\n", __func__, dev->name)); neigh_parms_release(&nd_tbl, ndev->nd_parms); ndev->dead = 1; @@ -400,9 +402,7 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) #if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) if (dev->type == ARPHRD_SIT && (dev->priv_flags & IFF_ISATAP)) { - printk(KERN_INFO - "%s: Disabled Multicast RS\n", - dev->name); + pr_info("%s: Disabled Multicast RS\n", dev->name); ndev->cnf.rtr_solicits = 0; } #endif @@ -441,7 +441,7 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) return ndev; } -static struct inet6_dev * ipv6_find_idev(struct net_device *dev) +static struct inet6_dev *ipv6_find_idev(struct net_device *dev) { struct inet6_dev *idev; @@ -542,7 +542,7 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) WARN_ON(!hlist_unhashed(&ifp->addr_lst)); #ifdef NET_REFCNT_DEBUG - printk(KERN_DEBUG "inet6_ifa_finish_destroy\n"); + pr_debug("%s\n", __func__); #endif in6_dev_put(ifp->idev); @@ -551,7 +551,7 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) pr_notice("Timer is still running, when freeing ifa=%p\n", ifp); if (ifp->state != INET6_IFADDR_STATE_DEAD) { - pr_warning("Freeing alive inet6 address %p\n", ifp); + pr_warn("Freeing alive inet6 address %p\n", ifp); return; } dst_release(&ifp->rt->dst); @@ -803,8 +803,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) ip6_del_rt(rt); rt = NULL; } else if (!(rt->rt6i_flags & RTF_EXPIRES)) { - rt->dst.expires = expires; - rt->rt6i_flags |= RTF_EXPIRES; + rt6_set_expires(rt, expires); } } dst_release(&rt->dst); @@ -842,8 +841,7 @@ retry: in6_dev_hold(idev); if (idev->cnf.use_tempaddr <= 0) { write_unlock(&idev->lock); - printk(KERN_INFO - "ipv6_create_tempaddr(): use_tempaddr is disabled.\n"); + pr_info("%s: use_tempaddr is disabled\n", __func__); in6_dev_put(idev); ret = -1; goto out; @@ -853,8 +851,8 @@ retry: idev->cnf.use_tempaddr = -1; /*XXX*/ spin_unlock_bh(&ifp->lock); write_unlock(&idev->lock); - printk(KERN_WARNING - "ipv6_create_tempaddr(): regeneration time exceeded. disabled temporary address support.\n"); + pr_warn("%s: regeneration time exceeded - disabled temporary address support\n", + __func__); in6_dev_put(idev); ret = -1; goto out; @@ -864,8 +862,8 @@ retry: if (__ipv6_try_regen_rndid(idev, tmpaddr) < 0) { spin_unlock_bh(&ifp->lock); write_unlock(&idev->lock); - printk(KERN_WARNING - "ipv6_create_tempaddr(): regeneration of randomized interface id failed.\n"); + pr_warn("%s: regeneration of randomized interface id failed\n", + __func__); in6_ifa_put(ifp); in6_dev_put(idev); ret = -1; @@ -915,8 +913,7 @@ retry: if (!ift || IS_ERR(ift)) { in6_ifa_put(ifp); in6_dev_put(idev); - printk(KERN_INFO - "ipv6_create_tempaddr(): retry temporary address regeneration.\n"); + pr_info("%s: retry temporary address regeneration\n", __func__); tmpaddr = &addr; write_lock(&idev->lock); goto retry; @@ -930,7 +927,7 @@ retry: ift->tstamp = tmp_tstamp; spin_unlock_bh(&ift->lock); - addrconf_dad_start(ift, 0); + addrconf_dad_start(ift); in6_ifa_put(ift); in6_dev_put(idev); out: @@ -1333,7 +1330,6 @@ int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev) rcu_read_unlock(); return onlink; } - EXPORT_SYMBOL(ipv6_chk_prefix); struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr, @@ -1417,9 +1413,8 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) return; } - if (net_ratelimit()) - printk(KERN_INFO "%s: IPv6 duplicate address %pI6c detected!\n", - ifp->idev->dev->name, &ifp->addr); + net_info_ratelimited("%s: IPv6 duplicate address %pI6c detected!\n", + ifp->idev->dev->name, &ifp->addr); if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) { struct in6_addr addr; @@ -1432,7 +1427,7 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) /* DAD failed for link-local based on MAC address */ idev->cnf.disable_ipv6 = 1; - printk(KERN_INFO "%s: IPv6 being disabled!\n", + pr_info("%s: IPv6 being disabled!\n", ifp->idev->dev->name); } } @@ -1517,13 +1512,21 @@ static int addrconf_ifid_eui48(u8 *eui, struct net_device *dev) return 0; } +static int addrconf_ifid_eui64(u8 *eui, struct net_device *dev) +{ + if (dev->addr_len != IEEE802154_ADDR_LEN) + return -1; + memcpy(eui, dev->dev_addr, 8); + return 0; +} + static int addrconf_ifid_arcnet(u8 *eui, struct net_device *dev) { /* XXX: inherit EUI-64 from other interface -- yoshfuji */ if (dev->addr_len != ARCNET_ALEN) return -1; memset(eui, 0, 7); - eui[7] = *(u8*)dev->dev_addr; + eui[7] = *(u8 *)dev->dev_addr; return 0; } @@ -1570,7 +1573,6 @@ static int ipv6_generate_eui64(u8 *eui, struct net_device *dev) switch (dev->type) { case ARPHRD_ETHER: case ARPHRD_FDDI: - case ARPHRD_IEEE802_TR: return addrconf_ifid_eui48(eui, dev); case ARPHRD_ARCNET: return addrconf_ifid_arcnet(eui, dev); @@ -1580,6 +1582,8 @@ static int ipv6_generate_eui64(u8 *eui, struct net_device *dev) return addrconf_ifid_sit(eui, dev); case ARPHRD_IPGRE: return addrconf_ifid_gre(eui, dev); + case ARPHRD_IEEE802154: + return addrconf_ifid_eui64(eui, dev); } return -1; } @@ -1653,9 +1657,8 @@ static void ipv6_regen_rndid(unsigned long data) idev->cnf.regen_max_retry * idev->cnf.dad_transmits * idev->nd_parms->retrans_time - idev->cnf.max_desync_factor * HZ; if (time_before(expires, jiffies)) { - printk(KERN_WARNING - "ipv6_regen_rndid(): too short regeneration interval; timer disabled for %s.\n", - idev->dev->name); + pr_warn("%s: too short regeneration interval; timer disabled for %s\n", + __func__, idev->dev->name); goto out; } @@ -1668,7 +1671,8 @@ out: in6_dev_put(idev); } -static int __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr) { +static int __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr) +{ int ret = 0; if (tmpaddr && memcmp(idev->rndid, &tmpaddr->s6_addr[8], 8) == 0) @@ -1838,16 +1842,15 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) prefered_lft = ntohl(pinfo->prefered); if (prefered_lft > valid_lft) { - if (net_ratelimit()) - printk(KERN_WARNING "addrconf: prefix option has invalid lifetime\n"); + net_warn_ratelimited("addrconf: prefix option has invalid lifetime\n"); return; } in6_dev = in6_dev_get(dev); if (in6_dev == NULL) { - if (net_ratelimit()) - printk(KERN_DEBUG "addrconf: device %s not configured\n", dev->name); + net_dbg_ratelimited("addrconf: device %s not configured\n", + dev->name); return; } @@ -1887,11 +1890,9 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) rt = NULL; } else if (addrconf_finite_timeout(rt_expires)) { /* not infinity */ - rt->dst.expires = jiffies + rt_expires; - rt->rt6i_flags |= RTF_EXPIRES; + rt6_set_expires(rt, jiffies + rt_expires); } else { - rt->rt6i_flags &= ~RTF_EXPIRES; - rt->dst.expires = 0; + rt6_clean_expires(rt); } } else if (valid_lft) { clock_t expires = 0; @@ -1911,7 +1912,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) /* Try to figure out our local address for this prefix */ if (pinfo->autoconf && in6_dev->cnf.autoconf) { - struct inet6_ifaddr * ifp; + struct inet6_ifaddr *ifp; struct in6_addr addr; int create = 0, update_lft = 0; @@ -1924,9 +1925,8 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) } goto ok; } - if (net_ratelimit()) - printk(KERN_DEBUG "IPv6 addrconf: prefix with wrong length %d\n", - pinfo->prefix_len); + net_dbg_ratelimited("IPv6 addrconf: prefix with wrong length %d\n", + pinfo->prefix_len); in6_dev_put(in6_dev); return; @@ -1960,7 +1960,7 @@ ok: update_lft = create = 1; ifp->cstamp = jiffies; - addrconf_dad_start(ifp, RTF_ADDRCONF|RTF_PREFIX_RT); + addrconf_dad_start(ifp); } if (ifp) { @@ -2239,7 +2239,7 @@ static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *p * that the Optimistic flag should not be set for * manually configured addresses */ - addrconf_dad_start(ifp, 0); + addrconf_dad_start(ifp); in6_ifa_put(ifp); addrconf_verify(0); return 0; @@ -2365,9 +2365,9 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) } for_each_netdev(net, dev) { - struct in_device * in_dev = __in_dev_get_rtnl(dev); + struct in_device *in_dev = __in_dev_get_rtnl(dev); if (in_dev && (dev->flags & IFF_UP)) { - struct in_ifaddr * ifa; + struct in_ifaddr *ifa; int flag = scope; @@ -2404,7 +2404,7 @@ static void init_loopback(struct net_device *dev) ASSERT_RTNL(); if ((idev = ipv6_find_idev(dev)) == NULL) { - printk(KERN_DEBUG "init loopback: add_dev failed\n"); + pr_debug("%s: add_dev failed\n", __func__); return; } @@ -2413,7 +2413,7 @@ static void init_loopback(struct net_device *dev) static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr) { - struct inet6_ifaddr * ifp; + struct inet6_ifaddr *ifp; u32 addr_flags = IFA_F_PERMANENT; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD @@ -2426,7 +2426,7 @@ static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr ifp = ipv6_add_addr(idev, addr, 64, IFA_LINK, addr_flags); if (!IS_ERR(ifp)) { addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev, 0, 0); - addrconf_dad_start(ifp, 0); + addrconf_dad_start(ifp); in6_ifa_put(ifp); } } @@ -2434,15 +2434,15 @@ static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr static void addrconf_dev_config(struct net_device *dev) { struct in6_addr addr; - struct inet6_dev * idev; + struct inet6_dev *idev; ASSERT_RTNL(); if ((dev->type != ARPHRD_ETHER) && (dev->type != ARPHRD_FDDI) && - (dev->type != ARPHRD_IEEE802_TR) && (dev->type != ARPHRD_ARCNET) && - (dev->type != ARPHRD_INFINIBAND)) { + (dev->type != ARPHRD_INFINIBAND) && + (dev->type != ARPHRD_IEEE802154)) { /* Alas, we support only Ethernet autoconfiguration. */ return; } @@ -2472,7 +2472,7 @@ static void addrconf_sit_config(struct net_device *dev) */ if ((idev = ipv6_find_idev(dev)) == NULL) { - printk(KERN_DEBUG "init sit: add_dev failed\n"); + pr_debug("%s: add_dev failed\n", __func__); return; } @@ -2502,12 +2502,12 @@ static void addrconf_gre_config(struct net_device *dev) struct inet6_dev *idev; struct in6_addr addr; - pr_info("ipv6: addrconf_gre_config(%s)\n", dev->name); + pr_info("%s(%s)\n", __func__, dev->name); ASSERT_RTNL(); if ((idev = ipv6_find_idev(dev)) == NULL) { - printk(KERN_DEBUG "init gre: add_dev failed\n"); + pr_debug("%s: add_dev failed\n", __func__); return; } @@ -2547,7 +2547,7 @@ static void ip6_tnl_add_linklocal(struct inet6_dev *idev) if (!ipv6_inherit_linklocal(idev, link_dev)) return; } - printk(KERN_DEBUG "init ip6-ip6: add_linklocal failed\n"); + pr_debug("init ip6-ip6: add_linklocal failed\n"); } /* @@ -2563,14 +2563,14 @@ static void addrconf_ip6_tnl_config(struct net_device *dev) idev = addrconf_add_dev(dev); if (IS_ERR(idev)) { - printk(KERN_DEBUG "init ip6-ip6: add_dev failed\n"); + pr_debug("init ip6-ip6: add_dev failed\n"); return; } ip6_tnl_add_linklocal(idev); } static int addrconf_notify(struct notifier_block *this, unsigned long event, - void * data) + void *data) { struct net_device *dev = (struct net_device *) data; struct inet6_dev *idev = __in6_dev_get(dev); @@ -2594,9 +2594,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (event == NETDEV_UP) { if (!addrconf_qdisc_ok(dev)) { /* device is not ready yet. */ - printk(KERN_INFO - "ADDRCONF(NETDEV_UP): %s: " - "link is not ready\n", + pr_info("ADDRCONF(NETDEV_UP): %s: link is not ready\n", dev->name); break; } @@ -2621,10 +2619,8 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, idev->if_flags |= IF_READY; } - printk(KERN_INFO - "ADDRCONF(NETDEV_CHANGE): %s: " - "link becomes ready\n", - dev->name); + pr_info("ADDRCONF(NETDEV_CHANGE): %s: link becomes ready\n", + dev->name); run_pending = 1; } @@ -2895,8 +2891,7 @@ static void addrconf_rs_timer(unsigned long data) * Note: we do not support deprecated "all on-link" * assumption any longer. */ - printk(KERN_DEBUG "%s: no IPv6 routers present\n", - idev->dev->name); + pr_debug("%s: no IPv6 routers present\n", idev->dev->name); } out: @@ -2921,7 +2916,7 @@ static void addrconf_dad_kick(struct inet6_ifaddr *ifp) addrconf_mod_timer(ifp, AC_DAD, rand_num); } -static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) +static void addrconf_dad_start(struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net_device *dev = idev->dev; @@ -3794,7 +3789,7 @@ static int inet6_dump_ifacaddr(struct sk_buff *skb, struct netlink_callback *cb) return inet6_dump_addr(skb, cb, type); } -static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr* nlh, +static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(in_skb->sk); @@ -3989,14 +3984,14 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev) struct nlattr *nla; struct ifla_cacheinfo ci; - NLA_PUT_U32(skb, IFLA_INET6_FLAGS, idev->if_flags); - + if (nla_put_u32(skb, IFLA_INET6_FLAGS, idev->if_flags)) + goto nla_put_failure; ci.max_reasm_len = IPV6_MAXPLEN; ci.tstamp = cstamp_delta(idev->tstamp); ci.reachable_time = jiffies_to_msecs(idev->nd_parms->reachable_time); ci.retrans_time = jiffies_to_msecs(idev->nd_parms->retrans_time); - NLA_PUT(skb, IFLA_INET6_CACHEINFO, sizeof(ci), &ci); - + if (nla_put(skb, IFLA_INET6_CACHEINFO, sizeof(ci), &ci)) + goto nla_put_failure; nla = nla_reserve(skb, IFLA_INET6_CONF, DEVCONF_MAX * sizeof(s32)); if (nla == NULL) goto nla_put_failure; @@ -4061,15 +4056,13 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, hdr->ifi_flags = dev_get_flags(dev); hdr->ifi_change = 0; - NLA_PUT_STRING(skb, IFLA_IFNAME, dev->name); - - if (dev->addr_len) - NLA_PUT(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr); - - NLA_PUT_U32(skb, IFLA_MTU, dev->mtu); - if (dev->ifindex != dev->iflink) - NLA_PUT_U32(skb, IFLA_LINK, dev->iflink); - + if (nla_put_string(skb, IFLA_IFNAME, dev->name) || + (dev->addr_len && + nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || + nla_put_u32(skb, IFLA_MTU, dev->mtu) || + (dev->ifindex != dev->iflink && + nla_put_u32(skb, IFLA_LINK, dev->iflink))) + goto nla_put_failure; protoinfo = nla_nest_start(skb, IFLA_PROTINFO); if (protoinfo == NULL) goto nla_put_failure; @@ -4182,12 +4175,12 @@ static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev, if (pinfo->autoconf) pmsg->prefix_flags |= IF_PREFIX_AUTOCONF; - NLA_PUT(skb, PREFIX_ADDRESS, sizeof(pinfo->prefix), &pinfo->prefix); - + if (nla_put(skb, PREFIX_ADDRESS, sizeof(pinfo->prefix), &pinfo->prefix)) + goto nla_put_failure; ci.preferred_time = ntohl(pinfo->prefered); ci.valid_time = ntohl(pinfo->valid); - NLA_PUT(skb, PREFIX_CACHEINFO, sizeof(ci), &ci); - + if (nla_put(skb, PREFIX_CACHEINFO, sizeof(ci), &ci)) + goto nla_put_failure; return nlmsg_end(skb, nlh); nla_put_failure: @@ -4371,7 +4364,6 @@ static struct addrconf_sysctl_table { struct ctl_table_header *sysctl_header; ctl_table addrconf_vars[DEVCONF_MAX+1]; - char *dev_name; } addrconf_sysctl __read_mostly = { .sysctl_header = NULL, .addrconf_vars = { @@ -4600,17 +4592,7 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name, { int i; struct addrconf_sysctl_table *t; - -#define ADDRCONF_CTL_PATH_DEV 3 - - struct ctl_path addrconf_ctl_path[] = { - { .procname = "net", }, - { .procname = "ipv6", }, - { .procname = "conf", }, - { /* to be set */ }, - { }, - }; - + char path[sizeof("net/ipv6/conf/") + IFNAMSIZ]; t = kmemdup(&addrconf_sysctl, sizeof(*t), GFP_KERNEL); if (t == NULL) @@ -4622,27 +4604,15 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name, t->addrconf_vars[i].extra2 = net; } - /* - * Make a copy of dev_name, because '.procname' is regarded as const - * by sysctl and we wouldn't want anyone to change it under our feet - * (see SIOCSIFNAME). - */ - t->dev_name = kstrdup(dev_name, GFP_KERNEL); - if (!t->dev_name) - goto free; - - addrconf_ctl_path[ADDRCONF_CTL_PATH_DEV].procname = t->dev_name; + snprintf(path, sizeof(path), "net/ipv6/conf/%s", dev_name); - t->sysctl_header = register_net_sysctl_table(net, addrconf_ctl_path, - t->addrconf_vars); + t->sysctl_header = register_net_sysctl(net, path, t->addrconf_vars); if (t->sysctl_header == NULL) - goto free_procname; + goto free; p->sysctl = t; return 0; -free_procname: - kfree(t->dev_name); free: kfree(t); out: @@ -4659,7 +4629,6 @@ static void __addrconf_sysctl_unregister(struct ipv6_devconf *p) t = p->sysctl; p->sysctl = NULL; unregister_net_sysctl_table(t->sysctl_header); - kfree(t->dev_name); kfree(t); } @@ -4778,8 +4747,8 @@ int __init addrconf_init(void) err = ipv6_addr_label_init(); if (err < 0) { - printk(KERN_CRIT "IPv6 Addrconf:" - " cannot initialize default policy table: %d.\n", err); + pr_crit("%s: cannot initialize default policy table: %d\n", + __func__, err); goto out; } diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 399287e595d..d051e5f4bf3 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -8,9 +8,9 @@ #define IPV6_ADDR_SCOPE_TYPE(scope) ((scope) << 16) -static inline unsigned ipv6_addr_scope2type(unsigned scope) +static inline unsigned int ipv6_addr_scope2type(unsigned int scope) { - switch(scope) { + switch (scope) { case IPV6_ADDR_SCOPE_NODELOCAL: return (IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_NODELOCAL) | IPV6_ADDR_LOOPBACK); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 2d8ddba9ee5..eb6a63632d3 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -129,7 +129,7 @@ static void ip6addrlbl_free_rcu(struct rcu_head *h) ip6addrlbl_free(container_of(h, struct ip6addrlbl_entry, rcu)); } -static inline int ip6addrlbl_hold(struct ip6addrlbl_entry *p) +static bool ip6addrlbl_hold(struct ip6addrlbl_entry *p) { return atomic_inc_not_zero(&p->refcnt); } @@ -141,20 +141,20 @@ static inline void ip6addrlbl_put(struct ip6addrlbl_entry *p) } /* Find label */ -static int __ip6addrlbl_match(struct net *net, - struct ip6addrlbl_entry *p, - const struct in6_addr *addr, - int addrtype, int ifindex) +static bool __ip6addrlbl_match(struct net *net, + const struct ip6addrlbl_entry *p, + const struct in6_addr *addr, + int addrtype, int ifindex) { if (!net_eq(ip6addrlbl_net(p), net)) - return 0; + return false; if (p->ifindex && p->ifindex != ifindex) - return 0; + return false; if (p->addrtype && p->addrtype != addrtype) - return 0; + return false; if (!ipv6_prefix_equal(addr, &p->prefix, p->prefixlen)) - return 0; - return 1; + return false; + return true; } static struct ip6addrlbl_entry *__ipv6_addr_label(struct net *net, @@ -350,7 +350,7 @@ static int __net_init ip6addrlbl_net_init(struct net *net) int err = 0; int i; - ADDRLABEL(KERN_DEBUG "%s()\n", __func__); + ADDRLABEL(KERN_DEBUG "%s\n", __func__); for (i = 0; i < ARRAY_SIZE(ip6addrlbl_init_table); i++) { int ret = ip6addrlbl_add(net, @@ -456,8 +456,8 @@ static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh, return err; } -static inline void ip6addrlbl_putmsg(struct nlmsghdr *nlh, - int prefixlen, int ifindex, u32 lseq) +static void ip6addrlbl_putmsg(struct nlmsghdr *nlh, + int prefixlen, int ifindex, u32 lseq) { struct ifaddrlblmsg *ifal = nlmsg_data(nlh); ifal->ifal_family = AF_INET6; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 8ed1b930e75..e22e6d88bac 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -18,6 +18,7 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) "IPv6: " fmt #include <linux/module.h> #include <linux/capability.h> @@ -77,7 +78,7 @@ struct ipv6_params ipv6_defaults = { .autoconf = 1, }; -static int disable_ipv6_mod = 0; +static int disable_ipv6_mod; module_param_named(disable, disable_ipv6_mod, int, 0444); MODULE_PARM_DESC(disable, "Disable IPv6 module such that it is non-functional"); @@ -180,7 +181,7 @@ lookup_protocol: err = 0; sk->sk_no_check = answer_no_check; if (INET_PROTOSW_REUSE & answer_flags) - sk->sk_reuse = 1; + sk->sk_reuse = SK_CAN_REUSE; inet = inet_sk(sk); inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; @@ -256,7 +257,7 @@ out_rcu_unlock: /* bind for INET6 API */ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { - struct sockaddr_in6 *addr=(struct sockaddr_in6 *)uaddr; + struct sockaddr_in6 *addr = (struct sockaddr_in6 *)uaddr; struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -390,7 +391,6 @@ out_unlock: rcu_read_unlock(); goto out; } - EXPORT_SYMBOL(inet6_bind); int inet6_release(struct socket *sock) @@ -408,7 +408,6 @@ int inet6_release(struct socket *sock) return inet_release(sock); } - EXPORT_SYMBOL(inet6_release); void inet6_destroy_sock(struct sock *sk) @@ -419,10 +418,12 @@ void inet6_destroy_sock(struct sock *sk) /* Release rx options */ - if ((skb = xchg(&np->pktoptions, NULL)) != NULL) + skb = xchg(&np->pktoptions, NULL); + if (skb != NULL) kfree_skb(skb); - if ((skb = xchg(&np->rxpmtu, NULL)) != NULL) + skb = xchg(&np->rxpmtu, NULL); + if (skb != NULL) kfree_skb(skb); /* Free flowlabels */ @@ -430,10 +431,10 @@ void inet6_destroy_sock(struct sock *sk) /* Free tx options */ - if ((opt = xchg(&np->opt, NULL)) != NULL) + opt = xchg(&np->opt, NULL); + if (opt != NULL) sock_kfree_s(sk, opt, opt->tot_len); } - EXPORT_SYMBOL_GPL(inet6_destroy_sock); /* @@ -443,7 +444,7 @@ EXPORT_SYMBOL_GPL(inet6_destroy_sock); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len, int peer) { - struct sockaddr_in6 *sin=(struct sockaddr_in6 *)uaddr; + struct sockaddr_in6 *sin = (struct sockaddr_in6 *)uaddr; struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -474,7 +475,6 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, *uaddr_len = sizeof(*sin); return 0; } - EXPORT_SYMBOL(inet6_getname); int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) @@ -482,8 +482,7 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) struct sock *sk = sock->sk; struct net *net = sock_net(sk); - switch(cmd) - { + switch (cmd) { case SIOCGSTAMP: return sock_get_timestamp(sk, (struct timeval __user *)arg); @@ -509,7 +508,6 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) /*NOTREACHED*/ return 0; } - EXPORT_SYMBOL(inet6_ioctl); const struct proto_ops inet6_stream_ops = { @@ -615,25 +613,21 @@ out: return ret; out_permanent: - printk(KERN_ERR "Attempt to override permanent protocol %d.\n", - protocol); + pr_err("Attempt to override permanent protocol %d\n", protocol); goto out; out_illegal: - printk(KERN_ERR - "Ignoring attempt to register invalid socket type %d.\n", + pr_err("Ignoring attempt to register invalid socket type %d\n", p->type); goto out; } - EXPORT_SYMBOL(inet6_register_protosw); void inet6_unregister_protosw(struct inet_protosw *p) { if (INET_PROTOSW_PERMANENT & p->flags) { - printk(KERN_ERR - "Attempt to unregister permanent protocol %d.\n", + pr_err("Attempt to unregister permanent protocol %d\n", p->protocol); } else { spin_lock_bh(&inetsw6_lock); @@ -643,7 +637,6 @@ inet6_unregister_protosw(struct inet_protosw *p) synchronize_net(); } } - EXPORT_SYMBOL(inet6_unregister_protosw); int inet6_sk_rebuild_header(struct sock *sk) @@ -683,13 +676,12 @@ int inet6_sk_rebuild_header(struct sock *sk) return 0; } - EXPORT_SYMBOL_GPL(inet6_sk_rebuild_header); -int ipv6_opt_accepted(struct sock *sk, struct sk_buff *skb) +bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb) { - struct ipv6_pinfo *np = inet6_sk(sk); - struct inet6_skb_parm *opt = IP6CB(skb); + const struct ipv6_pinfo *np = inet6_sk(sk); + const struct inet6_skb_parm *opt = IP6CB(skb); if (np->rxopt.all) { if ((opt->hop && (np->rxopt.bits.hopopts || @@ -701,11 +693,10 @@ int ipv6_opt_accepted(struct sock *sk, struct sk_buff *skb) np->rxopt.bits.osrcrt)) || ((opt->dst1 || opt->dst0) && (np->rxopt.bits.dstopts || np->rxopt.bits.odstopts))) - return 1; + return true; } - return 0; + return false; } - EXPORT_SYMBOL_GPL(ipv6_opt_accepted); static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto) @@ -1070,13 +1061,11 @@ static int __init inet6_init(void) BUILD_BUG_ON(sizeof(struct inet6_skb_parm) > sizeof(dummy_skb->cb)); /* Register the socket-side information for inet6_create. */ - for(r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r) + for (r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r) INIT_LIST_HEAD(r); if (disable_ipv6_mod) { - printk(KERN_INFO - "IPv6: Loaded, but administratively disabled, " - "reboot required to enable\n"); + pr_info("Loaded, but administratively disabled, reboot required to enable\n"); goto out; } @@ -1111,11 +1100,6 @@ static int __init inet6_init(void) if (err) goto out_sock_register_fail; -#ifdef CONFIG_SYSCTL - err = ipv6_static_sysctl_register(); - if (err) - goto static_sysctl_fail; -#endif tcpv6_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem; /* @@ -1242,10 +1226,6 @@ ipmr_fail: icmp_fail: unregister_pernet_subsys(&inet6_net_ops); register_pernet_fail: -#ifdef CONFIG_SYSCTL - ipv6_static_sysctl_unregister(); -static_sysctl_fail: -#endif sock_unregister(PF_INET6); rtnl_unregister_all(PF_INET6); out_sock_register_fail: @@ -1272,9 +1252,6 @@ static void __exit inet6_exit(void) /* Disallow any further netlink messages */ rtnl_unregister_all(PF_INET6); -#ifdef CONFIG_SYSCTL - ipv6_sysctl_unregister(); -#endif udpv6_exit(); udplitev6_exit(); tcpv6_exit(); @@ -1302,9 +1279,6 @@ static void __exit inet6_exit(void) rawv6_exit(); unregister_pernet_subsys(&inet6_net_ops); -#ifdef CONFIG_SYSCTL - ipv6_static_sysctl_unregister(); -#endif proto_unregister(&rawv6_prot); proto_unregister(&udplitev6_prot); proto_unregister(&udpv6_prot); diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 2ae79dbeec2..f1a4a2c28ed 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -24,6 +24,8 @@ * This file is derived from net/ipv4/ah.c. */ +#define pr_fmt(fmt) "IPv6: " fmt + #include <crypto/hash.h> #include <linux/module.h> #include <linux/slab.h> @@ -111,7 +113,7 @@ static inline struct scatterlist *ah_req_sg(struct crypto_ahash *ahash, __alignof__(struct scatterlist)); } -static int zero_out_mutable_opts(struct ipv6_opt_hdr *opthdr) +static bool zero_out_mutable_opts(struct ipv6_opt_hdr *opthdr) { u8 *opt = (u8 *)opthdr; int len = ipv6_optlen(opthdr); @@ -125,7 +127,7 @@ static int zero_out_mutable_opts(struct ipv6_opt_hdr *opthdr) switch (opt[off]) { - case IPV6_TLV_PAD0: + case IPV6_TLV_PAD1: optlen = 1; break; default: @@ -143,10 +145,10 @@ static int zero_out_mutable_opts(struct ipv6_opt_hdr *opthdr) len -= optlen; } if (len == 0) - return 1; + return true; bad: - return 0; + return false; } #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) @@ -169,7 +171,7 @@ static void ipv6_rearrange_destopt(struct ipv6hdr *iph, struct ipv6_opt_hdr *des switch (opt[off]) { - case IPV6_TLV_PAD0: + case IPV6_TLV_PAD1: optlen = 1; break; default: @@ -189,8 +191,8 @@ static void ipv6_rearrange_destopt(struct ipv6hdr *iph, struct ipv6_opt_hdr *des hao = (struct ipv6_destopt_hao *)&opt[off]; if (hao->length != sizeof(hao->addr)) { - if (net_ratelimit()) - printk(KERN_WARNING "destopt hao: invalid header length: %u\n", hao->length); + net_warn_ratelimited("destopt hao: invalid header length: %u\n", + hao->length); goto bad; } final_addr = hao->addr; @@ -659,9 +661,9 @@ static int ah6_init_state(struct xfrm_state *x) if (aalg_desc->uinfo.auth.icv_fullbits/8 != crypto_ahash_digestsize(ahash)) { - printk(KERN_INFO "AH: %s digestsize %u != %hu\n", - x->aalg->alg_name, crypto_ahash_digestsize(ahash), - aalg_desc->uinfo.auth.icv_fullbits/8); + pr_info("AH: %s digestsize %u != %hu\n", + x->aalg->alg_name, crypto_ahash_digestsize(ahash), + aalg_desc->uinfo.auth.icv_fullbits/8); goto error; } @@ -727,12 +729,12 @@ static const struct inet6_protocol ah6_protocol = { static int __init ah6_init(void) { if (xfrm_register_type(&ah6_type, AF_INET6) < 0) { - printk(KERN_INFO "ipv6 ah init: can't add xfrm type\n"); + pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } if (inet6_add_protocol(&ah6_protocol, IPPROTO_AH) < 0) { - printk(KERN_INFO "ipv6 ah init: can't add protocol\n"); + pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ah6_type, AF_INET6); return -EAGAIN; } @@ -743,10 +745,10 @@ static int __init ah6_init(void) static void __exit ah6_fini(void) { if (inet6_del_protocol(&ah6_protocol, IPPROTO_AH) < 0) - printk(KERN_INFO "ipv6 ah close: can't remove protocol\n"); + pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&ah6_type, AF_INET6) < 0) - printk(KERN_INFO "ipv6 ah close: can't remove xfrm type\n"); + pr_info("%s: can't remove xfrm type\n", __func__); } diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index db00d27ffb1..cdf02be5f19 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -342,7 +342,7 @@ static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr) * check if the interface has this anycast address * called with rcu_read_lock() */ -static int ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *addr) +static bool ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *addr) { struct inet6_dev *idev; struct ifacaddr6 *aca; @@ -356,16 +356,16 @@ static int ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *add read_unlock_bh(&idev->lock); return aca != NULL; } - return 0; + return false; } /* * check if given interface (or any, if dev==0) has this anycast address */ -int ipv6_chk_acast_addr(struct net *net, struct net_device *dev, - const struct in6_addr *addr) +bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, + const struct in6_addr *addr) { - int found = 0; + bool found = false; rcu_read_lock(); if (dev) @@ -373,7 +373,7 @@ int ipv6_chk_acast_addr(struct net *net, struct net_device *dev, else for_each_netdev_rcu(net, dev) if (ipv6_chk_acast_dev(dev, addr)) { - found = 1; + found = true; break; } rcu_read_unlock(); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 76832c8dc89..be2b67d631e 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -22,6 +22,7 @@ #include <linux/ipv6.h> #include <linux/route.h> #include <linux/slab.h> +#include <linux/export.h> #include <net/ipv6.h> #include <net/ndisc.h> @@ -33,9 +34,9 @@ #include <linux/errqueue.h> #include <asm/uaccess.h> -static inline int ipv6_mapped_addr_any(const struct in6_addr *a) +static bool ipv6_mapped_addr_any(const struct in6_addr *a) { - return (ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0)); + return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0); } int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) @@ -98,7 +99,7 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) sin.sin_port = usin->sin6_port; err = ip4_datagram_connect(sk, - (struct sockaddr*) &sin, + (struct sockaddr *) &sin, sizeof(sin)); ipv4_connected: @@ -202,6 +203,7 @@ out: fl6_sock_release(flowlabel); return err; } +EXPORT_SYMBOL_GPL(ip6_datagram_connect); void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload) @@ -414,6 +416,7 @@ out_free_skb: out: return err; } +EXPORT_SYMBOL_GPL(ipv6_recv_error); /* * Handle IPV6_RECVPATHMTU @@ -515,10 +518,10 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) u8 nexthdr = ipv6_hdr(skb)->nexthdr; while (off <= opt->lastopt) { - unsigned len; + unsigned int len; u8 *ptr = nh + off; - switch(nexthdr) { + switch (nexthdr) { case IPPROTO_DSTOPTS: nexthdr = ptr[0]; len = (ptr[1] + 1) << 3; @@ -827,9 +830,8 @@ int datagram_send_ctl(struct net *net, struct sock *sk, int tc; err = -EINVAL; - if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) { + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) goto exit_f; - } tc = *(int *)CMSG_DATA(cmsg); if (tc < -1 || tc > 0xff) @@ -846,9 +848,8 @@ int datagram_send_ctl(struct net *net, struct sock *sk, int df; err = -EINVAL; - if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) { + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) goto exit_f; - } df = *(int *)CMSG_DATA(cmsg); if (df < 0 || df > 1) @@ -870,3 +871,4 @@ int datagram_send_ctl(struct net *net, struct sock *sk, exit_f: return err; } +EXPORT_SYMBOL_GPL(datagram_send_ctl); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 1ac7938dd9e..1e62b7557b0 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -24,6 +24,8 @@ * This file is derived from net/ipv4/esp.c */ +#define pr_fmt(fmt) "IPv6: " fmt + #include <crypto/aead.h> #include <crypto/authenc.h> #include <linux/err.h> @@ -442,8 +444,8 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, esph->spi, IPPROTO_ESP, AF_INET6); if (!x) return; - printk(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%pI6\n", - ntohl(esph->spi), &iph->daddr); + pr_debug("pmtu discovery on SA ESP/%08x/%pI6\n", + ntohl(esph->spi), &iph->daddr); xfrm_state_put(x); } @@ -651,11 +653,11 @@ static const struct inet6_protocol esp6_protocol = { static int __init esp6_init(void) { if (xfrm_register_type(&esp6_type, AF_INET6) < 0) { - printk(KERN_INFO "ipv6 esp init: can't add xfrm type\n"); + pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } if (inet6_add_protocol(&esp6_protocol, IPPROTO_ESP) < 0) { - printk(KERN_INFO "ipv6 esp init: can't add protocol\n"); + pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&esp6_type, AF_INET6); return -EAGAIN; } @@ -666,9 +668,9 @@ static int __init esp6_init(void) static void __exit esp6_fini(void) { if (inet6_del_protocol(&esp6_protocol, IPPROTO_ESP) < 0) - printk(KERN_INFO "ipv6 esp close: can't remove protocol\n"); + pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&esp6_type, AF_INET6) < 0) - printk(KERN_INFO "ipv6 esp close: can't remove xfrm type\n"); + pr_info("%s: can't remove xfrm type\n", __func__); } module_init(esp6_init); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 3d641b6e9b0..6447dc49429 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -75,7 +75,7 @@ int ipv6_find_tlv(struct sk_buff *skb, int offset, int type) return offset; switch (opttype) { - case IPV6_TLV_PAD0: + case IPV6_TLV_PAD1: optlen = 1; break; default: @@ -96,14 +96,14 @@ EXPORT_SYMBOL_GPL(ipv6_find_tlv); /* * Parsing tlv encoded headers. * - * Parsing function "func" returns 1, if parsing succeed - * and 0, if it failed. + * Parsing function "func" returns true, if parsing succeed + * and false, if it failed. * It MUST NOT touch skb->h. */ struct tlvtype_proc { int type; - int (*func)(struct sk_buff *skb, int offset); + bool (*func)(struct sk_buff *skb, int offset); }; /********************* @@ -112,11 +112,11 @@ struct tlvtype_proc { /* An unknown option is detected, decide what to do */ -static int ip6_tlvopt_unknown(struct sk_buff *skb, int optoff) +static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff) { switch ((skb_network_header(skb)[optoff] & 0xC0) >> 6) { case 0: /* ignore */ - return 1; + return true; case 1: /* drop packet */ break; @@ -129,21 +129,22 @@ static int ip6_tlvopt_unknown(struct sk_buff *skb, int optoff) break; case 2: /* send ICMP PARM PROB regardless and drop packet */ icmpv6_param_prob(skb, ICMPV6_UNK_OPTION, optoff); - return 0; + return false; } kfree_skb(skb); - return 0; + return false; } /* Parse tlv encoded option header (hop-by-hop or destination) */ -static int ip6_parse_tlv(struct tlvtype_proc *procs, struct sk_buff *skb) +static bool ip6_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb) { - struct tlvtype_proc *curr; + const struct tlvtype_proc *curr; const unsigned char *nh = skb_network_header(skb); int off = skb_network_header_len(skb); int len = (skb_transport_header(skb)[1] + 1) << 3; + int padlen = 0; if (skb_transport_offset(skb) + len > skb_headlen(skb)) goto bad; @@ -153,13 +154,33 @@ static int ip6_parse_tlv(struct tlvtype_proc *procs, struct sk_buff *skb) while (len > 0) { int optlen = nh[off + 1] + 2; + int i; switch (nh[off]) { - case IPV6_TLV_PAD0: + case IPV6_TLV_PAD1: optlen = 1; + padlen++; + if (padlen > 7) + goto bad; break; case IPV6_TLV_PADN: + /* RFC 2460 states that the purpose of PadN is + * to align the containing header to multiples + * of 8. 7 is therefore the highest valid value. + * See also RFC 4942, Section 2.1.9.5. + */ + padlen += optlen; + if (padlen > 7) + goto bad; + /* RFC 4942 recommends receiving hosts to + * actively check PadN payload to contain + * only zeroes. + */ + for (i = 2; i < optlen; i++) { + if (nh[off + i] != 0) + goto bad; + } break; default: /* Other TLV code so scan list */ @@ -170,25 +191,33 @@ static int ip6_parse_tlv(struct tlvtype_proc *procs, struct sk_buff *skb) /* type specific length/alignment checks will be performed in the func(). */ - if (curr->func(skb, off) == 0) - return 0; + if (curr->func(skb, off) == false) + return false; break; } } if (curr->type < 0) { if (ip6_tlvopt_unknown(skb, off) == 0) - return 0; + return false; } + padlen = 0; break; } off += optlen; len -= optlen; } + /* This case will not be caught by above check since its padding + * length is smaller than 7: + * 1 byte NH + 1 byte Length + 6 bytes Padding + */ + if ((padlen == 6) && ((off - skb_network_header_len(skb)) == 8)) + goto bad; + if (len == 0) - return 1; + return true; bad: kfree_skb(skb); - return 0; + return false; } /***************************** @@ -196,7 +225,7 @@ bad: *****************************/ #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) -static int ipv6_dest_hao(struct sk_buff *skb, int optoff) +static bool ipv6_dest_hao(struct sk_buff *skb, int optoff) { struct ipv6_destopt_hao *hao; struct inet6_skb_parm *opt = IP6CB(skb); @@ -250,15 +279,15 @@ static int ipv6_dest_hao(struct sk_buff *skb, int optoff) if (skb->tstamp.tv64 == 0) __net_timestamp(skb); - return 1; + return true; discard: kfree_skb(skb); - return 0; + return false; } #endif -static struct tlvtype_proc tlvprocdestopt_lst[] = { +static const struct tlvtype_proc tlvprocdestopt_lst[] = { #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) { .type = IPV6_TLV_HAO, @@ -563,23 +592,23 @@ static inline struct net *ipv6_skb_net(struct sk_buff *skb) /* Router Alert as of RFC 2711 */ -static int ipv6_hop_ra(struct sk_buff *skb, int optoff) +static bool ipv6_hop_ra(struct sk_buff *skb, int optoff) { const unsigned char *nh = skb_network_header(skb); if (nh[optoff + 1] == 2) { IP6CB(skb)->ra = optoff; - return 1; + return true; } LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_ra: wrong RA length %d\n", nh[optoff + 1]); kfree_skb(skb); - return 0; + return false; } /* Jumbo payload */ -static int ipv6_hop_jumbo(struct sk_buff *skb, int optoff) +static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff) { const unsigned char *nh = skb_network_header(skb); struct net *net = ipv6_skb_net(skb); @@ -598,13 +627,13 @@ static int ipv6_hop_jumbo(struct sk_buff *skb, int optoff) IP6_INC_STATS_BH(net, ipv6_skb_idev(skb), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff+2); - return 0; + return false; } if (ipv6_hdr(skb)->payload_len) { IP6_INC_STATS_BH(net, ipv6_skb_idev(skb), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff); - return 0; + return false; } if (pkt_len > skb->len - sizeof(struct ipv6hdr)) { @@ -616,14 +645,14 @@ static int ipv6_hop_jumbo(struct sk_buff *skb, int optoff) if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) goto drop; - return 1; + return true; drop: kfree_skb(skb); - return 0; + return false; } -static struct tlvtype_proc tlvprochopopt_lst[] = { +static const struct tlvtype_proc tlvprochopopt_lst[] = { { .type = IPV6_TLV_ROUTERALERT, .func = ipv6_hop_ra, @@ -722,7 +751,6 @@ void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, if (opt->hopopt) ipv6_push_exthdr(skb, proto, NEXTHDR_HOP, opt->hopopt); } - EXPORT_SYMBOL(ipv6_push_nfrag_opts); void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto) @@ -738,20 +766,19 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt) opt2 = sock_kmalloc(sk, opt->tot_len, GFP_ATOMIC); if (opt2) { - long dif = (char*)opt2 - (char*)opt; + long dif = (char *)opt2 - (char *)opt; memcpy(opt2, opt, opt->tot_len); if (opt2->hopopt) - *((char**)&opt2->hopopt) += dif; + *((char **)&opt2->hopopt) += dif; if (opt2->dst0opt) - *((char**)&opt2->dst0opt) += dif; + *((char **)&opt2->dst0opt) += dif; if (opt2->dst1opt) - *((char**)&opt2->dst1opt) += dif; + *((char **)&opt2->dst1opt) += dif; if (opt2->srcrt) - *((char**)&opt2->srcrt) += dif; + *((char **)&opt2->srcrt) += dif; } return opt2; } - EXPORT_SYMBOL_GPL(ipv6_dup_options); static int ipv6_renew_option(void *ohdr, @@ -869,6 +896,7 @@ struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, return opt; } +EXPORT_SYMBOL_GPL(ipv6_fixup_options); /** * fl6_update_dst - update flowi destination address with info given @@ -892,5 +920,4 @@ struct in6_addr *fl6_update_dst(struct flowi6 *fl6, fl6->daddr = *((struct rt0_hdr *)opt->srcrt)->addr; return orig; } - EXPORT_SYMBOL_GPL(fl6_update_dst); diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 72957f4a7c6..f73d59a1413 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -9,7 +9,7 @@ * find out if nexthdr is a well-known extension header or a protocol */ -int ipv6_ext_hdr(u8 nexthdr) +bool ipv6_ext_hdr(u8 nexthdr) { /* * find out if nexthdr is an extension header or a protocol @@ -21,6 +21,7 @@ int ipv6_ext_hdr(u8 nexthdr) (nexthdr == NEXTHDR_NONE) || (nexthdr == NEXTHDR_DEST); } +EXPORT_SYMBOL(ipv6_ext_hdr); /* * Skip any extension headers. This is used by the ICMP module. @@ -109,6 +110,4 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp, *nexthdrp = nexthdr; return start; } - -EXPORT_SYMBOL(ipv6_ext_hdr); EXPORT_SYMBOL(ipv6_skip_exthdr); diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index b6c57315206..0ff1cfd55bc 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -22,8 +22,7 @@ #include <net/ip6_route.h> #include <net/netlink.h> -struct fib6_rule -{ +struct fib6_rule { struct fib_rule common; struct rt6key src; struct rt6key dst; @@ -215,14 +214,13 @@ static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb, frh->src_len = rule6->src.plen; frh->tos = rule6->tclass; - if (rule6->dst.plen) - NLA_PUT(skb, FRA_DST, sizeof(struct in6_addr), - &rule6->dst.addr); - - if (rule6->src.plen) - NLA_PUT(skb, FRA_SRC, sizeof(struct in6_addr), - &rule6->src.addr); - + if ((rule6->dst.plen && + nla_put(skb, FRA_DST, sizeof(struct in6_addr), + &rule6->dst.addr)) || + (rule6->src.plen && + nla_put(skb, FRA_SRC, sizeof(struct in6_addr), + &rule6->src.addr))) + goto nla_put_failure; return 0; nla_put_failure: diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 27ac95a6342..091a2971c7b 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -29,6 +29,8 @@ * Kazunori MIYAZAWA @USAGI: change output process to use ip6_append_data */ +#define pr_fmt(fmt) "IPv6: " fmt + #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> @@ -129,7 +131,7 @@ void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) * --ANK (980726) */ -static int is_ineligible(struct sk_buff *skb) +static bool is_ineligible(const struct sk_buff *skb) { int ptr = (u8 *)(ipv6_hdr(skb) + 1) - skb->data; int len = skb->len - ptr; @@ -137,11 +139,11 @@ static int is_ineligible(struct sk_buff *skb) __be16 frag_off; if (len < 0) - return 1; + return true; ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr, &frag_off); if (ptr < 0) - return 0; + return false; if (nexthdr == IPPROTO_ICMPV6) { u8 _type, *tp; tp = skb_header_pointer(skb, @@ -149,9 +151,9 @@ static int is_ineligible(struct sk_buff *skb) sizeof(_type), &_type); if (tp == NULL || !(*tp & ICMPV6_INFOMSG_MASK)) - return 1; + return true; } - return 0; + return false; } /* @@ -206,14 +208,14 @@ static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type, * highest-order two bits set to 10 */ -static __inline__ int opt_unrec(struct sk_buff *skb, __u32 offset) +static bool opt_unrec(struct sk_buff *skb, __u32 offset) { u8 _optval, *op; offset += skb_network_offset(skb); op = skb_header_pointer(skb, offset, sizeof(_optval), &_optval); if (op == NULL) - return 1; + return true; return (*op & 0xC0) == 0x80; } @@ -498,7 +500,7 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) err = ip6_append_data(sk, icmpv6_getfrag, &msg, len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), hlimit, - np->tclass, NULL, &fl6, (struct rt6_info*)dst, + np->tclass, NULL, &fl6, (struct rt6_info *)dst, MSG_DONTWAIT, np->dontfrag); if (err) { ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS); @@ -579,7 +581,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl6, - (struct rt6_info*)dst, MSG_DONTWAIT, + (struct rt6_info *)dst, MSG_DONTWAIT, np->dontfrag); if (err) { @@ -820,9 +822,7 @@ static int __net_init icmpv6_sk_init(struct net *net) err = inet_ctl_sock_create(&sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { - printk(KERN_ERR - "Failed to initialize the ICMP6 control socket " - "(err %d).\n", + pr_err("Failed to initialize the ICMP6 control socket (err %d)\n", err); goto fail; } @@ -881,7 +881,7 @@ int __init icmpv6_init(void) return 0; fail: - printk(KERN_ERR "Failed to register ICMP6 protocol\n"); + pr_err("Failed to register ICMP6 protocol\n"); unregister_pernet_subsys(&icmpv6_sk_ops); return err; } @@ -950,7 +950,6 @@ int icmpv6_err_convert(u8 type, u8 code, int *err) return fatal; } - EXPORT_SYMBOL(icmpv6_err_convert); #ifdef CONFIG_SYSCTL diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 02dd203d9ea..e6cee5292a0 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -28,7 +28,7 @@ #include <net/inet6_connection_sock.h> int inet6_csk_bind_conflict(const struct sock *sk, - const struct inet_bind_bucket *tb) + const struct inet_bind_bucket *tb, bool relax) { const struct sock *sk2; const struct hlist_node *node; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 5b27fbcae34..0c220a41662 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -18,6 +18,9 @@ * routing table. * Ville Nuorvala: Fixed routing subtrees. */ + +#define pr_fmt(fmt) "IPv6: " fmt + #include <linux/errno.h> #include <linux/types.h> #include <linux/net.h> @@ -38,7 +41,7 @@ #define RT6_DEBUG 2 #if RT6_DEBUG >= 3 -#define RT6_TRACE(x...) printk(KERN_DEBUG x) +#define RT6_TRACE(x...) pr_debug(x) #else #define RT6_TRACE(x...) do { ; } while (0) #endif @@ -451,12 +454,10 @@ static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) { if (!allow_create) { if (replace_required) { - pr_warn("IPv6: Can't replace route, " - "no match found\n"); + pr_warn("Can't replace route, no match found\n"); return ERR_PTR(-ENOENT); } - pr_warn("IPv6: NLM_F_CREATE should be set " - "when creating new route\n"); + pr_warn("NLM_F_CREATE should be set when creating new route\n"); } goto insert_above; } @@ -499,11 +500,10 @@ static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, * That would keep IPv6 consistent with IPv4 */ if (replace_required) { - pr_warn("IPv6: Can't replace route, no match found\n"); + pr_warn("Can't replace route, no match found\n"); return ERR_PTR(-ENOENT); } - pr_warn("IPv6: NLM_F_CREATE should be set " - "when creating new route\n"); + pr_warn("NLM_F_CREATE should be set when creating new route\n"); } /* * We walked to the bottom of tree. @@ -673,11 +673,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, &rt->rt6i_gateway)) { if (!(iter->rt6i_flags & RTF_EXPIRES)) return -EEXIST; - iter->dst.expires = rt->dst.expires; - if (!(rt->rt6i_flags & RTF_EXPIRES)) { - iter->rt6i_flags &= ~RTF_EXPIRES; - iter->dst.expires = 0; - } + if (!(rt->rt6i_flags & RTF_EXPIRES)) + rt6_clean_expires(iter); + else + rt6_set_expires(iter, rt->dst.expires); return -EEXIST; } } @@ -697,7 +696,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, */ if (!replace) { if (!add) - pr_warn("IPv6: NLM_F_CREATE should be set when creating new route\n"); + pr_warn("NLM_F_CREATE should be set when creating new route\n"); add: rt->dst.rt6_next = iter; @@ -716,7 +715,7 @@ add: if (!found) { if (add) goto add; - pr_warn("IPv6: NLM_F_REPLACE set, but no existing node found!\n"); + pr_warn("NLM_F_REPLACE set, but no existing node found!\n"); return -ENOENT; } *ins = rt; @@ -769,7 +768,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) replace_required = 1; } if (!allow_create && !replace_required) - pr_warn("IPv6: RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); + pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); fn = fib6_add_1(root, &rt->rt6i_dst.addr, sizeof(struct in6_addr), rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), @@ -1421,7 +1420,8 @@ static int fib6_clean_node(struct fib6_walker_t *w) res = fib6_del(rt, &info); if (res) { #if RT6_DEBUG >= 2 - printk(KERN_DEBUG "fib6_clean_node: del failed: rt=%p@%p err=%d\n", rt, rt->rt6i_node, res); + pr_debug("%s: del failed: rt=%p@%p err=%d\n", + __func__, rt, rt->rt6i_node, res); #endif continue; } diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index b7867a1215b..9772fbd8a3f 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -294,6 +294,7 @@ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions * opt_space, opt_space->opt_flen = fopt->opt_flen; return opt_space; } +EXPORT_SYMBOL_GPL(fl6_merge_options); static unsigned long check_linger(unsigned long ttl) { @@ -432,32 +433,32 @@ static int mem_check(struct sock *sk) return 0; } -static int ipv6_hdr_cmp(struct ipv6_opt_hdr *h1, struct ipv6_opt_hdr *h2) +static bool ipv6_hdr_cmp(struct ipv6_opt_hdr *h1, struct ipv6_opt_hdr *h2) { if (h1 == h2) - return 0; + return false; if (h1 == NULL || h2 == NULL) - return 1; + return true; if (h1->hdrlen != h2->hdrlen) - return 1; + return true; return memcmp(h1+1, h2+1, ((h1->hdrlen+1)<<3) - sizeof(*h1)); } -static int ipv6_opt_cmp(struct ipv6_txoptions *o1, struct ipv6_txoptions *o2) +static bool ipv6_opt_cmp(struct ipv6_txoptions *o1, struct ipv6_txoptions *o2) { if (o1 == o2) - return 0; + return false; if (o1 == NULL || o2 == NULL) - return 1; + return true; if (o1->opt_nflen != o2->opt_nflen) - return 1; + return true; if (ipv6_hdr_cmp(o1->hopopt, o2->hopopt)) - return 1; + return true; if (ipv6_hdr_cmp(o1->dst0opt, o2->dst0opt)) - return 1; + return true; if (ipv6_hdr_cmp((struct ipv6_opt_hdr *)o1->srcrt, (struct ipv6_opt_hdr *)o2->srcrt)) - return 1; - return 0; + return true; + return false; } static inline void fl_link(struct ipv6_pinfo *np, struct ipv6_fl_socklist *sfl, @@ -705,9 +706,9 @@ static int ip6fl_seq_show(struct seq_file *seq, void *v) struct ip6_flowlabel *fl = v; seq_printf(seq, "%05X %-1d %-6d %-6d %-6ld %-8ld %pi6 %-4d\n", - (unsigned)ntohl(fl->label), + (unsigned int)ntohl(fl->label), fl->share, - (unsigned)fl->owner, + (int)fl->owner, atomic_read(&fl->users), fl->linger/HZ, (long)(fl->expires - jiffies)/HZ, diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 1ca5d45a12e..21a15dfe4a9 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -170,7 +170,8 @@ static int ip6_input_finish(struct sk_buff *skb) { const struct inet6_protocol *ipprot; unsigned int nhoff; - int nexthdr, raw; + int nexthdr; + bool raw; u8 hash; struct inet6_dev *idev; struct net *net = dev_net(skb_dst(skb)->dev); @@ -251,7 +252,7 @@ int ip6_input(struct sk_buff *skb) int ip6_mc_input(struct sk_buff *skb) { const struct ipv6hdr *hdr; - int deliver; + bool deliver; IP6_UPD_PO_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INMCAST, @@ -287,7 +288,7 @@ int ip6_mc_input(struct sk_buff *skb) * is for MLD (0x0000). */ if ((ptr[2] | ptr[3]) == 0) { - deliver = 0; + deliver = false; if (!ipv6_ext_hdr(nexthdr)) { /* BUG */ @@ -312,7 +313,7 @@ int ip6_mc_input(struct sk_buff *skb) case ICMPV6_MGM_REPORT: case ICMPV6_MGM_REDUCTION: case ICMPV6_MLD2_REPORT: - deliver = 1; + deliver = true; break; } goto out; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index b7ca46161cb..d99fdc69962 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -210,7 +210,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, kfree_skb(skb); return -ENOBUFS; } - kfree_skb(skb); + consume_skb(skb); skb = skb2; skb_set_owner_w(skb, sk); } @@ -252,8 +252,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, dst->dev, dst_output); } - if (net_ratelimit()) - printk(KERN_DEBUG "IPv6: sending pkt_too_big to self\n"); + net_dbg_ratelimited("IPv6: sending pkt_too_big to self\n"); skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); @@ -644,7 +643,10 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) /* We must not fragment if the socket is set to force MTU discovery * or if the skb it not generated by a local socket. */ - if (!skb->local_df && skb->len > mtu) { + if (unlikely(!skb->local_df && skb->len > mtu)) { + if (skb->sk && dst_allfrag(skb_dst(skb))) + sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK); + skb->dev = skb_dst(skb)->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), @@ -789,6 +791,10 @@ slow_path_clean: } slow_path: + if ((skb->ip_summed == CHECKSUM_PARTIAL) && + skb_checksum_help(skb)) + goto fail; + left = skb->len - hlen; /* Space per frame */ ptr = hlen; /* Where to start from */ @@ -889,7 +895,7 @@ slow_path: } IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGOKS); - kfree_skb(skb); + consume_skb(skb); return err; fail: @@ -1199,7 +1205,6 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int copy; int err; int offset = 0; - int csummode = CHECKSUM_NONE; __u8 tx_flags = 0; if (flags&MSG_PROBE) @@ -1412,7 +1417,7 @@ alloc_new_skb: /* * Fill in the control structures */ - skb->ip_summed = csummode; + skb->ip_summed = CHECKSUM_NONE; skb->csum = 0; /* reserve for fragmentation and ipsec header */ skb_reserve(skb, hh_len + sizeof(struct frag_hdr) + @@ -1455,7 +1460,6 @@ alloc_new_skb: transhdrlen = 0; exthdrlen = 0; dst_exthdrlen = 0; - csummode = CHECKSUM_NONE; /* * Put the packet on the pending queue @@ -1535,6 +1539,7 @@ error: IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); return err; } +EXPORT_SYMBOL_GPL(ip6_append_data); static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np) { @@ -1638,6 +1643,7 @@ error: IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); goto out; } +EXPORT_SYMBOL_GPL(ip6_push_pending_frames); void ip6_flush_pending_frames(struct sock *sk) { @@ -1652,3 +1658,4 @@ void ip6_flush_pending_frames(struct sock *sk) ip6_cork_release(inet_sk(sk), inet6_sk(sk)); } +EXPORT_SYMBOL_GPL(ip6_flush_pending_frames); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index aa21da6a09c..c9015fad8d6 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -18,6 +18,8 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> @@ -60,7 +62,7 @@ MODULE_LICENSE("GPL"); MODULE_ALIAS_NETDEV("ip6tnl0"); #ifdef IP6_TNL_DEBUG -#define IP6_TNL_TRACE(x...) printk(KERN_DEBUG "%s:" x "\n", __func__) +#define IP6_TNL_TRACE(x...) pr_debug("%s:" x "\n", __func__) #else #define IP6_TNL_TRACE(x...) do {;} while(0) #endif @@ -198,7 +200,7 @@ ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct ip6_tnl_parm *p) { const struct in6_addr *remote = &p->raddr; const struct in6_addr *local = &p->laddr; - unsigned h = 0; + unsigned int h = 0; int prio = 0; if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) { @@ -460,19 +462,14 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, struct ipv6_tlv_tnl_enc_lim *tel; __u32 mtu; case ICMPV6_DEST_UNREACH: - if (net_ratelimit()) - printk(KERN_WARNING - "%s: Path to destination invalid " - "or inactive!\n", t->parms.name); + net_warn_ratelimited("%s: Path to destination invalid or inactive!\n", + t->parms.name); rel_msg = 1; break; case ICMPV6_TIME_EXCEED: if ((*code) == ICMPV6_EXC_HOPLIMIT) { - if (net_ratelimit()) - printk(KERN_WARNING - "%s: Too small hop limit or " - "routing loop in tunnel!\n", - t->parms.name); + net_warn_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", + t->parms.name); rel_msg = 1; } break; @@ -484,17 +481,13 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, if (teli && teli == *info - 2) { tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli]; if (tel->encap_limit == 0) { - if (net_ratelimit()) - printk(KERN_WARNING - "%s: Too small encapsulation " - "limit or routing loop in " - "tunnel!\n", t->parms.name); + net_warn_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", + t->parms.name); rel_msg = 1; } - } else if (net_ratelimit()) { - printk(KERN_WARNING - "%s: Recipient unable to parse tunneled " - "packet!\n ", t->parms.name); + } else { + net_warn_ratelimited("%s: Recipient unable to parse tunneled packet!\n", + t->parms.name); } break; case ICMPV6_PKT_TOOBIG: @@ -825,7 +818,7 @@ static void init_tel_txopt(struct ipv6_tel_txoption *opt, __u8 encap_limit) * 0 else **/ -static inline int +static inline bool ip6_tnl_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr) { return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); @@ -845,15 +838,12 @@ static inline int ip6_tnl_xmit_ctl(struct ip6_tnl *t) ldev = dev_get_by_index_rcu(net, p->link); if (unlikely(!ipv6_chk_addr(net, &p->laddr, ldev, 0))) - printk(KERN_WARNING - "%s xmit: Local address not yet configured!\n", - p->name); + pr_warn("%s xmit: Local address not yet configured!\n", + p->name); else if (!ipv6_addr_is_multicast(&p->raddr) && unlikely(ipv6_chk_addr(net, &p->raddr, NULL, 0))) - printk(KERN_WARNING - "%s xmit: Routing loop! " - "Remote address found on this node!\n", - p->name); + pr_warn("%s xmit: Routing loop! Remote address found on this node!\n", + p->name); else ret = 1; rcu_read_unlock(); @@ -919,10 +909,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, if (tdev == dev) { stats->collisions++; - if (net_ratelimit()) - printk(KERN_WARNING - "%s: Local routing loop detected!\n", - t->parms.name); + net_warn_ratelimited("%s: Local routing loop detected!\n", + t->parms.name); goto tx_err_dst_release; } mtu = dst_mtu(dst) - sizeof (*ipv6h); @@ -954,7 +942,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, if (skb->sk) skb_set_owner_w(new_skb, skb->sk); - kfree_skb(skb); + consume_skb(skb); skb = new_skb; } skb_dst_drop(skb); @@ -1553,13 +1541,13 @@ static int __init ip6_tunnel_init(void) err = xfrm6_tunnel_register(&ip4ip6_handler, AF_INET); if (err < 0) { - printk(KERN_ERR "ip6_tunnel init: can't register ip4ip6\n"); + pr_err("%s: can't register ip4ip6\n", __func__); goto out_ip4ip6; } err = xfrm6_tunnel_register(&ip6ip6_handler, AF_INET6); if (err < 0) { - printk(KERN_ERR "ip6_tunnel init: can't register ip6ip6\n"); + pr_err("%s: can't register ip6ip6\n", __func__); goto out_ip6ip6; } @@ -1580,10 +1568,10 @@ out_pernet: static void __exit ip6_tunnel_cleanup(void) { if (xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET)) - printk(KERN_INFO "ip6_tunnel close: can't deregister ip4ip6\n"); + pr_info("%s: can't deregister ip4ip6\n", __func__); if (xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6)) - printk(KERN_INFO "ip6_tunnel close: can't deregister ip6ip6\n"); + pr_info("%s: can't deregister ip6ip6\n", __func__); unregister_pernet_device(&ip6_tnl_net_ops); } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 8110362e0af..b15dc08643a 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1147,8 +1147,7 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, */ ret = sock_queue_rcv_skb(mrt->mroute6_sk, skb); if (ret < 0) { - if (net_ratelimit()) - printk(KERN_WARNING "mroute6: pending queue full, dropping entries.\n"); + net_warn_ratelimited("mroute6: pending queue full, dropping entries\n"); kfree_skb(skb); } @@ -1351,7 +1350,7 @@ int __init ip6_mr_init(void) goto reg_notif_fail; #ifdef CONFIG_IPV6_PIMSM_V2 if (inet6_add_protocol(&pim6_protocol, IPPROTO_PIM) < 0) { - printk(KERN_ERR "ip6_mr_init: can't add PIM protocol\n"); + pr_err("%s: can't add PIM protocol\n", __func__); err = -EAGAIN; goto add_proto_fail; } @@ -2215,14 +2214,15 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, rtm->rtm_src_len = 128; rtm->rtm_tos = 0; rtm->rtm_table = mrt->id; - NLA_PUT_U32(skb, RTA_TABLE, mrt->id); + if (nla_put_u32(skb, RTA_TABLE, mrt->id)) + goto nla_put_failure; rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = RTPROT_UNSPEC; rtm->rtm_flags = 0; - NLA_PUT(skb, RTA_SRC, 16, &c->mf6c_origin); - NLA_PUT(skb, RTA_DST, 16, &c->mf6c_mcastgrp); - + if (nla_put(skb, RTA_SRC, 16, &c->mf6c_origin) || + nla_put(skb, RTA_DST, 16, &c->mf6c_mcastgrp)) + goto nla_put_failure; if (__ip6mr_fill_mroute(mrt, skb, c, rtm) < 0) goto nla_put_failure; diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index bba658d9a03..5cb75bfe45b 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -30,6 +30,9 @@ * The decompression of IP datagram MUST be done after the reassembly, * AH/ESP processing. */ + +#define pr_fmt(fmt) "IPv6: " fmt + #include <linux/module.h> #include <net/ip.h> #include <net/xfrm.h> @@ -69,8 +72,8 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!x) return; - printk(KERN_DEBUG "pmtu discovery on SA IPCOMP/%08x/%pI6\n", - spi, &iph->daddr); + pr_debug("pmtu discovery on SA IPCOMP/%08x/%pI6\n", + spi, &iph->daddr); xfrm_state_put(x); } @@ -190,11 +193,11 @@ static const struct inet6_protocol ipcomp6_protocol = static int __init ipcomp6_init(void) { if (xfrm_register_type(&ipcomp6_type, AF_INET6) < 0) { - printk(KERN_INFO "ipcomp6 init: can't add xfrm type\n"); + pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } if (inet6_add_protocol(&ipcomp6_protocol, IPPROTO_COMP) < 0) { - printk(KERN_INFO "ipcomp6 init: can't add protocol\n"); + pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ipcomp6_type, AF_INET6); return -EAGAIN; } @@ -204,9 +207,9 @@ static int __init ipcomp6_init(void) static void __exit ipcomp6_fini(void) { if (inet6_del_protocol(&ipcomp6_protocol, IPPROTO_COMP) < 0) - printk(KERN_INFO "ipv6 ipcomp close: can't remove protocol\n"); + pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&ipcomp6_type, AF_INET6) < 0) - printk(KERN_INFO "ipv6 ipcomp close: can't remove xfrm type\n"); + pr_info("%s: can't remove xfrm type\n", __func__); } module_init(ipcomp6_init); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 63dd1f89ed7..ba6d13d1f1e 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -678,7 +678,6 @@ done: } case MCAST_MSFILTER: { - extern int sysctl_mld_max_msf; struct group_filter *gsf; if (optlen < GROUP_FILTER_SIZE(0)) @@ -943,7 +942,7 @@ static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt, } static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen, unsigned flags) + char __user *optval, int __user *optlen, unsigned int flags) { struct ipv6_pinfo *np = inet6_sk(sk); int len; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 16c33e30812..6d0f5dc8e3a 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -606,13 +606,13 @@ done: return err; } -int inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, - const struct in6_addr *src_addr) +bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, + const struct in6_addr *src_addr) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist *mc; struct ip6_sf_socklist *psl; - int rv = 1; + bool rv = true; rcu_read_lock(); for_each_pmc_rcu(np, mc) { @@ -621,7 +621,7 @@ int inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, } if (!mc) { rcu_read_unlock(); - return 1; + return true; } read_lock(&mc->sflock); psl = mc->sflist; @@ -635,9 +635,9 @@ int inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, break; } if (mc->sfmode == MCAST_INCLUDE && i >= psl->sl_count) - rv = 0; + rv = false; if (mc->sfmode == MCAST_EXCLUDE && i < psl->sl_count) - rv = 0; + rv = false; } read_unlock(&mc->sflock); rcu_read_unlock(); @@ -931,15 +931,15 @@ int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr) /* * identify MLD packets for MLD filter exceptions */ -int ipv6_is_mld(struct sk_buff *skb, int nexthdr) +bool ipv6_is_mld(struct sk_buff *skb, int nexthdr) { struct icmp6hdr *pic; if (nexthdr != IPPROTO_ICMPV6) - return 0; + return false; if (!pskb_may_pull(skb, sizeof(struct icmp6hdr))) - return 0; + return false; pic = icmp6_hdr(skb); @@ -948,22 +948,22 @@ int ipv6_is_mld(struct sk_buff *skb, int nexthdr) case ICMPV6_MGM_REPORT: case ICMPV6_MGM_REDUCTION: case ICMPV6_MLD2_REPORT: - return 1; + return true; default: break; } - return 0; + return false; } /* * check if the interface/address pair is valid */ -int ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, - const struct in6_addr *src_addr) +bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, + const struct in6_addr *src_addr) { struct inet6_dev *idev; struct ifmcaddr6 *mc; - int rv = 0; + bool rv = false; rcu_read_lock(); idev = __in6_dev_get(dev); @@ -990,7 +990,7 @@ int ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, rv = mc->mca_sfcount[MCAST_EXCLUDE] !=0; spin_unlock_bh(&mc->mca_lock); } else - rv = 1; /* don't filter unspecified source */ + rv = true; /* don't filter unspecified source */ } read_unlock_bh(&idev->lock); } @@ -1046,8 +1046,8 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) } /* mark EXCLUDE-mode sources */ -static int mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs, - const struct in6_addr *srcs) +static bool mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs, + const struct in6_addr *srcs) { struct ip6_sf_list *psf; int i, scount; @@ -1061,7 +1061,7 @@ static int mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs, if (psf->sf_count[MCAST_INCLUDE] || pmc->mca_sfcount[MCAST_EXCLUDE] != psf->sf_count[MCAST_EXCLUDE]) - continue; + break; if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) { scount++; break; @@ -1070,12 +1070,12 @@ static int mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs, } pmc->mca_flags &= ~MAF_GSQUERY; if (scount == nsrcs) /* all sources excluded */ - return 0; - return 1; + return false; + return true; } -static int mld_marksources(struct ifmcaddr6 *pmc, int nsrcs, - const struct in6_addr *srcs) +static bool mld_marksources(struct ifmcaddr6 *pmc, int nsrcs, + const struct in6_addr *srcs) { struct ip6_sf_list *psf; int i, scount; @@ -1099,10 +1099,10 @@ static int mld_marksources(struct ifmcaddr6 *pmc, int nsrcs, } if (!scount) { pmc->mca_flags &= ~MAF_GSQUERY; - return 0; + return false; } pmc->mca_flags |= MAF_GSQUERY; - return 1; + return true; } /* called with rcu_read_lock() */ @@ -1276,17 +1276,17 @@ int igmp6_event_report(struct sk_buff *skb) return 0; } -static int is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type, - int gdeleted, int sdeleted) +static bool is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type, + int gdeleted, int sdeleted) { switch (type) { case MLD2_MODE_IS_INCLUDE: case MLD2_MODE_IS_EXCLUDE: if (gdeleted || sdeleted) - return 0; + return false; if (!((pmc->mca_flags & MAF_GSQUERY) && !psf->sf_gsresp)) { if (pmc->mca_sfmode == MCAST_INCLUDE) - return 1; + return true; /* don't include if this source is excluded * in all filters */ @@ -1295,29 +1295,29 @@ static int is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type, return pmc->mca_sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; } - return 0; + return false; case MLD2_CHANGE_TO_INCLUDE: if (gdeleted || sdeleted) - return 0; + return false; return psf->sf_count[MCAST_INCLUDE] != 0; case MLD2_CHANGE_TO_EXCLUDE: if (gdeleted || sdeleted) - return 0; + return false; if (pmc->mca_sfcount[MCAST_EXCLUDE] == 0 || psf->sf_count[MCAST_INCLUDE]) - return 0; + return false; return pmc->mca_sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; case MLD2_ALLOW_NEW_SOURCES: if (gdeleted || !psf->sf_crcount) - return 0; + return false; return (pmc->mca_sfmode == MCAST_INCLUDE) ^ sdeleted; case MLD2_BLOCK_OLD_SOURCES: if (pmc->mca_sfmode == MCAST_INCLUDE) return gdeleted || (psf->sf_crcount && sdeleted); return psf->sf_crcount && !gdeleted && !sdeleted; } - return 0; + return false; } static int @@ -2044,7 +2044,7 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, if (!delta) pmc->mca_sfcount[sfmode]--; for (j=0; j<i; j++) - (void) ip6_mc_del1_src(pmc, sfmode, &psfsrc[i]); + ip6_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->mca_sfcount[MCAST_EXCLUDE] != 0)) { struct ip6_sf_list *psf; @@ -2627,8 +2627,7 @@ static int __net_init igmp6_net_init(struct net *net) err = inet_ctl_sock_create(&net->ipv6.igmp_sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { - printk(KERN_ERR - "Failed to initialize the IGMP6 control socket (err %d).\n", + pr_err("Failed to initialize the IGMP6 control socket (err %d)\n", err); goto out; } diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 7e1e0fbfef2..5b087c31d87 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -22,6 +22,8 @@ * Masahide NAKAMURA @USAGI */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/skbuff.h> #include <linux/time.h> @@ -44,7 +46,7 @@ static inline void *mip6_padn(__u8 *data, __u8 padlen) if (!data) return NULL; if (padlen == 1) { - data[0] = IPV6_TLV_PAD0; + data[0] = IPV6_TLV_PAD1; } else if (padlen > 1) { data[0] = IPV6_TLV_PADN; data[1] = padlen - 2; @@ -307,13 +309,12 @@ static int mip6_destopt_offset(struct xfrm_state *x, struct sk_buff *skb, static int mip6_destopt_init_state(struct xfrm_state *x) { if (x->id.spi) { - printk(KERN_INFO "%s: spi is not 0: %u\n", __func__, - x->id.spi); + pr_info("%s: spi is not 0: %u\n", __func__, x->id.spi); return -EINVAL; } if (x->props.mode != XFRM_MODE_ROUTEOPTIMIZATION) { - printk(KERN_INFO "%s: state's mode is not %u: %u\n", - __func__, XFRM_MODE_ROUTEOPTIMIZATION, x->props.mode); + pr_info("%s: state's mode is not %u: %u\n", + __func__, XFRM_MODE_ROUTEOPTIMIZATION, x->props.mode); return -EINVAL; } @@ -443,13 +444,12 @@ static int mip6_rthdr_offset(struct xfrm_state *x, struct sk_buff *skb, static int mip6_rthdr_init_state(struct xfrm_state *x) { if (x->id.spi) { - printk(KERN_INFO "%s: spi is not 0: %u\n", __func__, - x->id.spi); + pr_info("%s: spi is not 0: %u\n", __func__, x->id.spi); return -EINVAL; } if (x->props.mode != XFRM_MODE_ROUTEOPTIMIZATION) { - printk(KERN_INFO "%s: state's mode is not %u: %u\n", - __func__, XFRM_MODE_ROUTEOPTIMIZATION, x->props.mode); + pr_info("%s: state's mode is not %u: %u\n", + __func__, XFRM_MODE_ROUTEOPTIMIZATION, x->props.mode); return -EINVAL; } @@ -481,18 +481,18 @@ static const struct xfrm_type mip6_rthdr_type = static int __init mip6_init(void) { - printk(KERN_INFO "Mobile IPv6\n"); + pr_info("Mobile IPv6\n"); if (xfrm_register_type(&mip6_destopt_type, AF_INET6) < 0) { - printk(KERN_INFO "%s: can't add xfrm type(destopt)\n", __func__); + pr_info("%s: can't add xfrm type(destopt)\n", __func__); goto mip6_destopt_xfrm_fail; } if (xfrm_register_type(&mip6_rthdr_type, AF_INET6) < 0) { - printk(KERN_INFO "%s: can't add xfrm type(rthdr)\n", __func__); + pr_info("%s: can't add xfrm type(rthdr)\n", __func__); goto mip6_rthdr_xfrm_fail; } if (rawv6_mh_filter_register(mip6_mh_filter) < 0) { - printk(KERN_INFO "%s: can't add rawv6 mh filter\n", __func__); + pr_info("%s: can't add rawv6 mh filter\n", __func__); goto mip6_rawv6_mh_fail; } @@ -510,11 +510,11 @@ static int __init mip6_init(void) static void __exit mip6_fini(void) { if (rawv6_mh_filter_unregister(mip6_mh_filter) < 0) - printk(KERN_INFO "%s: can't remove rawv6 mh filter\n", __func__); + pr_info("%s: can't remove rawv6 mh filter\n", __func__); if (xfrm_unregister_type(&mip6_rthdr_type, AF_INET6) < 0) - printk(KERN_INFO "%s: can't remove xfrm type(rthdr)\n", __func__); + pr_info("%s: can't remove xfrm type(rthdr)\n", __func__); if (xfrm_unregister_type(&mip6_destopt_type, AF_INET6) < 0) - printk(KERN_INFO "%s: can't remove xfrm type(destopt)\n", __func__); + pr_info("%s: can't remove xfrm type(destopt)\n", __func__); } module_init(mip6_init); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 3dcdb81ec3e..54f62d3b8dd 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -15,6 +15,7 @@ /* * Changes: * + * Alexey I. Froloff : RFC6106 (DNSSL) support * Pierre Ynard : export userland ND options * through netlink (RDNSS support) * Lars Fenneberg : fixed MTU setting on receipt @@ -26,27 +27,7 @@ * YOSHIFUJI Hideaki @USAGI : Verify ND options properly */ -/* Set to 3 to get tracing... */ -#define ND_DEBUG 1 - -#define ND_PRINTK(fmt, args...) do { if (net_ratelimit()) { printk(fmt, ## args); } } while(0) -#define ND_NOPRINTK(x...) do { ; } while(0) -#define ND_PRINTK0 ND_PRINTK -#define ND_PRINTK1 ND_NOPRINTK -#define ND_PRINTK2 ND_NOPRINTK -#define ND_PRINTK3 ND_NOPRINTK -#if ND_DEBUG >= 1 -#undef ND_PRINTK1 -#define ND_PRINTK1 ND_PRINTK -#endif -#if ND_DEBUG >= 2 -#undef ND_PRINTK2 -#define ND_PRINTK2 ND_PRINTK -#endif -#if ND_DEBUG >= 3 -#undef ND_PRINTK3 -#define ND_PRINTK3 ND_PRINTK -#endif +#define pr_fmt(fmt) "ICMPv6: " fmt #include <linux/module.h> #include <linux/errno.h> @@ -91,6 +72,15 @@ #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> +/* Set to 3 to get tracing... */ +#define ND_DEBUG 1 + +#define ND_PRINTK(val, level, fmt, ...) \ +do { \ + if (val <= ND_DEBUG) \ + net_##level##_ratelimited(fmt, ##__VA_ARGS__); \ +} while (0) + static u32 ndisc_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); @@ -228,7 +218,8 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, static inline int ndisc_is_useropt(struct nd_opt_hdr *opt) { - return opt->nd_opt_type == ND_OPT_RDNSS; + return opt->nd_opt_type == ND_OPT_RDNSS || + opt->nd_opt_type == ND_OPT_DNSSL; } static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur, @@ -263,10 +254,9 @@ static struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, case ND_OPT_MTU: case ND_OPT_REDIRECT_HDR: if (ndopts->nd_opt_array[nd_opt->nd_opt_type]) { - ND_PRINTK2(KERN_WARNING - "%s(): duplicated ND6 option found: type=%d\n", - __func__, - nd_opt->nd_opt_type); + ND_PRINTK(2, warn, + "%s: duplicated ND6 option found: type=%d\n", + __func__, nd_opt->nd_opt_type); } else { ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt; } @@ -294,10 +284,11 @@ static struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, * to accommodate future extension to the * protocol. */ - ND_PRINTK2(KERN_NOTICE - "%s(): ignored unsupported option; type=%d, len=%d\n", - __func__, - nd_opt->nd_opt_type, nd_opt->nd_opt_len); + ND_PRINTK(2, notice, + "%s: ignored unsupported option; type=%d, len=%d\n", + __func__, + nd_opt->nd_opt_type, + nd_opt->nd_opt_len); } } opt_len -= l; @@ -325,9 +316,6 @@ int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, case ARPHRD_FDDI: ipv6_eth_mc_map(addr, buf); return 0; - case ARPHRD_IEEE802_TR: - ipv6_tr_mc_map(addr,buf); - return 0; case ARPHRD_ARCNET: ipv6_arcnet_mc_map(addr, buf); return 0; @@ -360,7 +348,7 @@ static int ndisc_constructor(struct neighbour *neigh) struct net_device *dev = neigh->dev; struct inet6_dev *in6_dev; struct neigh_parms *parms; - int is_multicast = ipv6_addr_is_multicast(addr); + bool is_multicast = ipv6_addr_is_multicast(addr); in6_dev = in6_dev_get(dev); if (in6_dev == NULL) { @@ -456,9 +444,8 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev, len + hlen + tlen), 1, &err); if (!skb) { - ND_PRINTK0(KERN_ERR - "ICMPv6 ND: %s() failed to allocate an skb, err=%d.\n", - __func__, err); + ND_PRINTK(0, err, "ND: %s failed to allocate an skb, err=%d\n", + __func__, err); return NULL; } @@ -694,8 +681,9 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) if ((probes -= neigh->parms->ucast_probes) < 0) { if (!(neigh->nud_state & NUD_VALID)) { - ND_PRINTK1(KERN_DEBUG "%s(): trying to ucast probe in NUD_INVALID: %pI6\n", - __func__, target); + ND_PRINTK(1, dbg, + "%s: trying to ucast probe in NUD_INVALID: %pI6\n", + __func__, target); } ndisc_send_ns(dev, neigh, target, target, saddr); } else if ((probes -= neigh->parms->app_probes) < 0) { @@ -737,12 +725,11 @@ static void ndisc_recv_ns(struct sk_buff *skb) struct inet6_dev *idev = NULL; struct neighbour *neigh; int dad = ipv6_addr_any(saddr); - int inc; + bool inc; int is_router = -1; if (ipv6_addr_is_multicast(&msg->target)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NS: multicast target address"); + ND_PRINTK(2, warn, "NS: multicast target address\n"); return; } @@ -755,22 +742,20 @@ static void ndisc_recv_ns(struct sk_buff *skb) daddr->s6_addr32[1] == htonl(0x00000000) && daddr->s6_addr32[2] == htonl(0x00000001) && daddr->s6_addr [12] == 0xff )) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NS: bad DAD packet (wrong destination)\n"); + ND_PRINTK(2, warn, "NS: bad DAD packet (wrong destination)\n"); return; } if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NS: invalid ND options\n"); + ND_PRINTK(2, warn, "NS: invalid ND options\n"); return; } if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, dev); if (!lladdr) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NS: invalid link-layer address length\n"); + ND_PRINTK(2, warn, + "NS: invalid link-layer address length\n"); return; } @@ -780,8 +765,8 @@ static void ndisc_recv_ns(struct sk_buff *skb) * in the message. */ if (dad) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NS: bad DAD packet (link-layer address option)\n"); + ND_PRINTK(2, warn, + "NS: bad DAD packet (link-layer address option)\n"); return; } } @@ -793,20 +778,6 @@ static void ndisc_recv_ns(struct sk_buff *skb) if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) { if (dad) { - if (dev->type == ARPHRD_IEEE802_TR) { - const unsigned char *sadr; - sadr = skb_mac_header(skb); - if (((sadr[8] ^ dev->dev_addr[0]) & 0x7f) == 0 && - sadr[9] == dev->dev_addr[1] && - sadr[10] == dev->dev_addr[2] && - sadr[11] == dev->dev_addr[3] && - sadr[12] == dev->dev_addr[4] && - sadr[13] == dev->dev_addr[5]) { - /* looped-back to us */ - goto out; - } - } - /* * We are colliding with another node * who is doing DAD @@ -913,34 +884,30 @@ static void ndisc_recv_na(struct sk_buff *skb) struct neighbour *neigh; if (skb->len < sizeof(struct nd_msg)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NA: packet too short\n"); + ND_PRINTK(2, warn, "NA: packet too short\n"); return; } if (ipv6_addr_is_multicast(&msg->target)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NA: target address is multicast.\n"); + ND_PRINTK(2, warn, "NA: target address is multicast\n"); return; } if (ipv6_addr_is_multicast(daddr) && msg->icmph.icmp6_solicited) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NA: solicited NA is multicasted.\n"); + ND_PRINTK(2, warn, "NA: solicited NA is multicasted\n"); return; } if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NS: invalid ND option\n"); + ND_PRINTK(2, warn, "NS: invalid ND option\n"); return; } if (ndopts.nd_opts_tgt_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, dev); if (!lladdr) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NA: invalid link-layer address length\n"); + ND_PRINTK(2, warn, + "NA: invalid link-layer address length\n"); return; } } @@ -961,9 +928,9 @@ static void ndisc_recv_na(struct sk_buff *skb) unsolicited advertisement. */ if (skb->pkt_type != PACKET_LOOPBACK) - ND_PRINTK1(KERN_WARNING - "ICMPv6 NA: someone advertises our address %pI6 on %s!\n", - &ifp->addr, ifp->idev->dev->name); + ND_PRINTK(1, warn, + "NA: someone advertises our address %pI6 on %s!\n", + &ifp->addr, ifp->idev->dev->name); in6_ifa_put(ifp); return; } @@ -1025,8 +992,7 @@ static void ndisc_recv_rs(struct sk_buff *skb) idev = __in6_dev_get(skb->dev); if (!idev) { - if (net_ratelimit()) - ND_PRINTK1("ICMP6 RS: can't find in6 device\n"); + ND_PRINTK(1, err, "RS: can't find in6 device\n"); return; } @@ -1043,8 +1009,7 @@ static void ndisc_recv_rs(struct sk_buff *skb) /* Parse ND options */ if (!ndisc_parse_options(rs_msg->opt, ndoptlen, &ndopts)) { - if (net_ratelimit()) - ND_PRINTK2("ICMP6 NS: invalid ND option, ignored\n"); + ND_PRINTK(2, notice, "NS: invalid ND option, ignored\n"); goto out; } @@ -1099,8 +1064,9 @@ static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt) memcpy(ndmsg + 1, opt, opt->nd_opt_len << 3); - NLA_PUT(skb, NDUSEROPT_SRCADDR, sizeof(struct in6_addr), - &ipv6_hdr(ra)->saddr); + if (nla_put(skb, NDUSEROPT_SRCADDR, sizeof(struct in6_addr), + &ipv6_hdr(ra)->saddr)) + goto nla_put_failure; nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_ND_USEROPT, NULL, GFP_ATOMIC); @@ -1141,20 +1107,17 @@ static void ndisc_router_discovery(struct sk_buff *skb) optlen = (skb->tail - skb->transport_header) - sizeof(struct ra_msg); if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 RA: source address is not link-local.\n"); + ND_PRINTK(2, warn, "RA: source address is not link-local\n"); return; } if (optlen < 0) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 RA: packet too short\n"); + ND_PRINTK(2, warn, "RA: packet too short\n"); return; } #ifdef CONFIG_IPV6_NDISC_NODETYPE if (skb->ndisc_nodetype == NDISC_NODETYPE_HOST) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 RA: from host or unauthorized router\n"); + ND_PRINTK(2, warn, "RA: from host or unauthorized router\n"); return; } #endif @@ -1165,15 +1128,13 @@ static void ndisc_router_discovery(struct sk_buff *skb) in6_dev = __in6_dev_get(skb->dev); if (in6_dev == NULL) { - ND_PRINTK0(KERN_ERR - "ICMPv6 RA: can't find inet6 device for %s.\n", - skb->dev->name); + ND_PRINTK(0, err, "RA: can't find inet6 device for %s\n", + skb->dev->name); return; } if (!ndisc_parse_options(opt, optlen, &ndopts)) { - ND_PRINTK2(KERN_WARNING - "ICMP6 RA: invalid ND options\n"); + ND_PRINTK(2, warn, "RA: invalid ND options\n"); return; } @@ -1226,9 +1187,9 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (rt) { neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr); if (!neigh) { - ND_PRINTK0(KERN_ERR - "ICMPv6 RA: %s() got default router without neighbour.\n", - __func__); + ND_PRINTK(0, err, + "RA: %s got default router without neighbour\n", + __func__); dst_release(&rt->dst); return; } @@ -1239,22 +1200,21 @@ static void ndisc_router_discovery(struct sk_buff *skb) } if (rt == NULL && lifetime) { - ND_PRINTK3(KERN_DEBUG - "ICMPv6 RA: adding default router.\n"); + ND_PRINTK(3, dbg, "RA: adding default router\n"); rt = rt6_add_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev, pref); if (rt == NULL) { - ND_PRINTK0(KERN_ERR - "ICMPv6 RA: %s() failed to add default route.\n", - __func__); + ND_PRINTK(0, err, + "RA: %s failed to add default route\n", + __func__); return; } neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr); if (neigh == NULL) { - ND_PRINTK0(KERN_ERR - "ICMPv6 RA: %s() got default router without neighbour.\n", - __func__); + ND_PRINTK(0, err, + "RA: %s got default router without neighbour\n", + __func__); dst_release(&rt->dst); return; } @@ -1264,8 +1224,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) } if (rt) - rt->dst.expires = jiffies + (HZ * lifetime); - + rt6_set_expires(rt, jiffies + (HZ * lifetime)); if (ra_msg->icmph.icmp6_hop_limit) { in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; if (rt) @@ -1323,8 +1282,8 @@ skip_linkparms: lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, skb->dev); if (!lladdr) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 RA: invalid link-layer address length\n"); + ND_PRINTK(2, warn, + "RA: invalid link-layer address length\n"); goto out; } } @@ -1388,9 +1347,7 @@ skip_routeinfo: mtu = ntohl(n); if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 RA: invalid mtu: %d\n", - mtu); + ND_PRINTK(2, warn, "RA: invalid mtu: %d\n", mtu); } else if (in6_dev->cnf.mtu6 != mtu) { in6_dev->cnf.mtu6 = mtu; @@ -1411,8 +1368,7 @@ skip_routeinfo: } if (ndopts.nd_opts_tgt_lladdr || ndopts.nd_opts_rh) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 RA: invalid RA options"); + ND_PRINTK(2, warn, "RA: invalid RA options\n"); } out: if (rt) @@ -1437,15 +1393,15 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) switch (skb->ndisc_nodetype) { case NDISC_NODETYPE_HOST: case NDISC_NODETYPE_NODEFAULT: - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: from host or unauthorized router\n"); + ND_PRINTK(2, warn, + "Redirect: from host or unauthorized router\n"); return; } #endif if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: source address is not link-local.\n"); + ND_PRINTK(2, warn, + "Redirect: source address is not link-local\n"); return; } @@ -1453,8 +1409,7 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) optlen -= sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr); if (optlen < 0) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: packet too short\n"); + ND_PRINTK(2, warn, "Redirect: packet too short\n"); return; } @@ -1463,8 +1418,8 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) dest = target + 1; if (ipv6_addr_is_multicast(dest)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: destination address is multicast.\n"); + ND_PRINTK(2, warn, + "Redirect: destination address is multicast\n"); return; } @@ -1472,8 +1427,8 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) on_link = 1; } else if (ipv6_addr_type(target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: target address is not link-local unicast.\n"); + ND_PRINTK(2, warn, + "Redirect: target address is not link-local unicast\n"); return; } @@ -1489,16 +1444,15 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) */ if (!ndisc_parse_options((u8*)(dest + 1), optlen, &ndopts)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: invalid ND options\n"); + ND_PRINTK(2, warn, "Redirect: invalid ND options\n"); return; } if (ndopts.nd_opts_tgt_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, skb->dev); if (!lladdr) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: invalid link-layer address length\n"); + ND_PRINTK(2, warn, + "Redirect: invalid link-layer address length\n"); return; } } @@ -1533,16 +1487,15 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) u8 ha_buf[MAX_ADDR_LEN], *ha = NULL; if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: no link-local address on %s\n", - dev->name); + ND_PRINTK(2, warn, "Redirect: no link-local address on %s\n", + dev->name); return; } if (!ipv6_addr_equal(&ipv6_hdr(skb)->daddr, target) && ipv6_addr_type(target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: target address is not link-local unicast.\n"); + ND_PRINTK(2, warn, + "Redirect: target address is not link-local unicast\n"); return; } @@ -1561,8 +1514,8 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) rt = (struct rt6_info *) dst; if (rt->rt6i_flags & RTF_GATEWAY) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: destination is not a neighbour.\n"); + ND_PRINTK(2, warn, + "Redirect: destination is not a neighbour\n"); goto release; } if (!rt->rt6i_peer) @@ -1573,8 +1526,8 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) if (dev->addr_len) { struct neighbour *neigh = dst_neigh_lookup(skb_dst(skb), target); if (!neigh) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: no neigh for target address\n"); + ND_PRINTK(2, warn, + "Redirect: no neigh for target address\n"); goto release; } @@ -1602,9 +1555,9 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) len + hlen + tlen), 1, &err); if (buff == NULL) { - ND_PRINTK0(KERN_ERR - "ICMPv6 Redirect: %s() failed to allocate an skb, err=%d.\n", - __func__, err); + ND_PRINTK(0, err, + "Redirect: %s failed to allocate an skb, err=%d\n", + __func__, err); goto release; } @@ -1689,16 +1642,14 @@ int ndisc_rcv(struct sk_buff *skb) __skb_push(skb, skb->data - skb_transport_header(skb)); if (ipv6_hdr(skb)->hop_limit != 255) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NDISC: invalid hop-limit: %d\n", - ipv6_hdr(skb)->hop_limit); + ND_PRINTK(2, warn, "NDISC: invalid hop-limit: %d\n", + ipv6_hdr(skb)->hop_limit); return 0; } if (msg->icmph.icmp6_code != 0) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NDISC: invalid ICMPv6 code: %d\n", - msg->icmph.icmp6_code); + ND_PRINTK(2, warn, "NDISC: invalid ICMPv6 code: %d\n", + msg->icmph.icmp6_code); return 0; } @@ -1765,11 +1716,7 @@ static void ndisc_warn_deprecated_sysctl(struct ctl_table *ctl, static int warned; if (strcmp(warncomm, current->comm) && warned < 5) { strcpy(warncomm, current->comm); - printk(KERN_WARNING - "process `%s' is using deprecated sysctl (%s) " - "net.ipv6.neigh.%s.%s; " - "Use net.ipv6.neigh.%s.%s_ms " - "instead.\n", + pr_warn("process `%s' is using deprecated sysctl (%s) net.ipv6.neigh.%s.%s - use net.ipv6.neigh.%s.%s_ms instead\n", warncomm, func, dev_name, ctl->procname, dev_name, ctl->procname); @@ -1823,9 +1770,9 @@ static int __net_init ndisc_net_init(struct net *net) err = inet_ctl_sock_create(&sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { - ND_PRINTK0(KERN_ERR - "ICMPv6 NDISC: Failed to initialize the control socket (err %d).\n", - err); + ND_PRINTK(0, err, + "NDISC: Failed to initialize the control socket (err %d)\n", + err); return err; } diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index d33cddd16fb..10135342799 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -25,28 +25,6 @@ config NF_CONNTRACK_IPV6 To compile it as a module, choose M here. If unsure, say N. -config IP6_NF_QUEUE - tristate "IP6 Userspace queueing via NETLINK (OBSOLETE)" - depends on INET && IPV6 && NETFILTER - depends on NETFILTER_ADVANCED - ---help--- - - This option adds a queue handler to the kernel for IPv6 - packets which enables users to receive the filtered packets - with QUEUE target using libipq. - - This option enables the old IPv6-only "ip6_queue" implementation - which has been obsoleted by the new "nfnetlink_queue" code (see - CONFIG_NETFILTER_NETLINK_QUEUE). - - (C) Fernando Anton 2001 - IPv64 Project - Work based in IPv64 draft by Arturo Azcorra. - Universidad Carlos III de Madrid - Universidad Politecnica de Alcala de Henares - email: <fanton@it.uc3m.es>. - - To compile it as a module, choose M here. If unsure, say N. - config IP6_NF_IPTABLES tristate "IP6 tables support (required for filtering)" depends on INET && IPV6 diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index d4dfd0a2109..534d3f216f7 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -6,7 +6,6 @@ obj-$(CONFIG_IP6_NF_IPTABLES) += ip6_tables.o obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o -obj-$(CONFIG_IP6_NF_QUEUE) += ip6_queue.o obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c deleted file mode 100644 index a34c9e4c792..00000000000 --- a/net/ipv6/netfilter/ip6_queue.c +++ /dev/null @@ -1,641 +0,0 @@ -/* - * This is a module which is used for queueing IPv6 packets and - * communicating with userspace via netlink. - * - * (C) 2001 Fernando Anton, this code is GPL. - * IPv64 Project - Work based in IPv64 draft by Arturo Azcorra. - * Universidad Carlos III de Madrid - Leganes (Madrid) - Spain - * Universidad Politecnica de Alcala de Henares - Alcala de H. (Madrid) - Spain - * email: fanton@it.uc3m.es - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/init.h> -#include <linux/ipv6.h> -#include <linux/notifier.h> -#include <linux/netdevice.h> -#include <linux/netfilter.h> -#include <linux/netlink.h> -#include <linux/spinlock.h> -#include <linux/sysctl.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/mutex.h> -#include <linux/slab.h> -#include <net/net_namespace.h> -#include <net/sock.h> -#include <net/ipv6.h> -#include <net/ip6_route.h> -#include <net/netfilter/nf_queue.h> -#include <linux/netfilter_ipv4/ip_queue.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv6/ip6_tables.h> - -#define IPQ_QMAX_DEFAULT 1024 -#define IPQ_PROC_FS_NAME "ip6_queue" -#define NET_IPQ_QMAX_NAME "ip6_queue_maxlen" - -typedef int (*ipq_cmpfn)(struct nf_queue_entry *, unsigned long); - -static unsigned char copy_mode __read_mostly = IPQ_COPY_NONE; -static unsigned int queue_maxlen __read_mostly = IPQ_QMAX_DEFAULT; -static DEFINE_SPINLOCK(queue_lock); -static int peer_pid __read_mostly; -static unsigned int copy_range __read_mostly; -static unsigned int queue_total; -static unsigned int queue_dropped = 0; -static unsigned int queue_user_dropped = 0; -static struct sock *ipqnl __read_mostly; -static LIST_HEAD(queue_list); -static DEFINE_MUTEX(ipqnl_mutex); - -static inline void -__ipq_enqueue_entry(struct nf_queue_entry *entry) -{ - list_add_tail(&entry->list, &queue_list); - queue_total++; -} - -static inline int -__ipq_set_mode(unsigned char mode, unsigned int range) -{ - int status = 0; - - switch(mode) { - case IPQ_COPY_NONE: - case IPQ_COPY_META: - copy_mode = mode; - copy_range = 0; - break; - - case IPQ_COPY_PACKET: - if (range > 0xFFFF) - range = 0xFFFF; - copy_range = range; - copy_mode = mode; - break; - - default: - status = -EINVAL; - - } - return status; -} - -static void __ipq_flush(ipq_cmpfn cmpfn, unsigned long data); - -static inline void -__ipq_reset(void) -{ - peer_pid = 0; - net_disable_timestamp(); - __ipq_set_mode(IPQ_COPY_NONE, 0); - __ipq_flush(NULL, 0); -} - -static struct nf_queue_entry * -ipq_find_dequeue_entry(unsigned long id) -{ - struct nf_queue_entry *entry = NULL, *i; - - spin_lock_bh(&queue_lock); - - list_for_each_entry(i, &queue_list, list) { - if ((unsigned long)i == id) { - entry = i; - break; - } - } - - if (entry) { - list_del(&entry->list); - queue_total--; - } - - spin_unlock_bh(&queue_lock); - return entry; -} - -static void -__ipq_flush(ipq_cmpfn cmpfn, unsigned long data) -{ - struct nf_queue_entry *entry, *next; - - list_for_each_entry_safe(entry, next, &queue_list, list) { - if (!cmpfn || cmpfn(entry, data)) { - list_del(&entry->list); - queue_total--; - nf_reinject(entry, NF_DROP); - } - } -} - -static void -ipq_flush(ipq_cmpfn cmpfn, unsigned long data) -{ - spin_lock_bh(&queue_lock); - __ipq_flush(cmpfn, data); - spin_unlock_bh(&queue_lock); -} - -static struct sk_buff * -ipq_build_packet_message(struct nf_queue_entry *entry, int *errp) -{ - sk_buff_data_t old_tail; - size_t size = 0; - size_t data_len = 0; - struct sk_buff *skb; - struct ipq_packet_msg *pmsg; - struct nlmsghdr *nlh; - struct timeval tv; - - switch (ACCESS_ONCE(copy_mode)) { - case IPQ_COPY_META: - case IPQ_COPY_NONE: - size = NLMSG_SPACE(sizeof(*pmsg)); - break; - - case IPQ_COPY_PACKET: - if (entry->skb->ip_summed == CHECKSUM_PARTIAL && - (*errp = skb_checksum_help(entry->skb))) - return NULL; - - data_len = ACCESS_ONCE(copy_range); - if (data_len == 0 || data_len > entry->skb->len) - data_len = entry->skb->len; - - size = NLMSG_SPACE(sizeof(*pmsg) + data_len); - break; - - default: - *errp = -EINVAL; - return NULL; - } - - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) - goto nlmsg_failure; - - old_tail = skb->tail; - nlh = NLMSG_PUT(skb, 0, 0, IPQM_PACKET, size - sizeof(*nlh)); - pmsg = NLMSG_DATA(nlh); - memset(pmsg, 0, sizeof(*pmsg)); - - pmsg->packet_id = (unsigned long )entry; - pmsg->data_len = data_len; - tv = ktime_to_timeval(entry->skb->tstamp); - pmsg->timestamp_sec = tv.tv_sec; - pmsg->timestamp_usec = tv.tv_usec; - pmsg->mark = entry->skb->mark; - pmsg->hook = entry->hook; - pmsg->hw_protocol = entry->skb->protocol; - - if (entry->indev) - strcpy(pmsg->indev_name, entry->indev->name); - else - pmsg->indev_name[0] = '\0'; - - if (entry->outdev) - strcpy(pmsg->outdev_name, entry->outdev->name); - else - pmsg->outdev_name[0] = '\0'; - - if (entry->indev && entry->skb->dev && - entry->skb->mac_header != entry->skb->network_header) { - pmsg->hw_type = entry->skb->dev->type; - pmsg->hw_addrlen = dev_parse_header(entry->skb, pmsg->hw_addr); - } - - if (data_len) - if (skb_copy_bits(entry->skb, 0, pmsg->payload, data_len)) - BUG(); - - nlh->nlmsg_len = skb->tail - old_tail; - return skb; - -nlmsg_failure: - kfree_skb(skb); - *errp = -EINVAL; - printk(KERN_ERR "ip6_queue: error creating packet message\n"); - return NULL; -} - -static int -ipq_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) -{ - int status = -EINVAL; - struct sk_buff *nskb; - - if (copy_mode == IPQ_COPY_NONE) - return -EAGAIN; - - nskb = ipq_build_packet_message(entry, &status); - if (nskb == NULL) - return status; - - spin_lock_bh(&queue_lock); - - if (!peer_pid) - goto err_out_free_nskb; - - if (queue_total >= queue_maxlen) { - queue_dropped++; - status = -ENOSPC; - if (net_ratelimit()) - printk (KERN_WARNING "ip6_queue: fill at %d entries, " - "dropping packet(s). Dropped: %d\n", queue_total, - queue_dropped); - goto err_out_free_nskb; - } - - /* netlink_unicast will either free the nskb or attach it to a socket */ - status = netlink_unicast(ipqnl, nskb, peer_pid, MSG_DONTWAIT); - if (status < 0) { - queue_user_dropped++; - goto err_out_unlock; - } - - __ipq_enqueue_entry(entry); - - spin_unlock_bh(&queue_lock); - return status; - -err_out_free_nskb: - kfree_skb(nskb); - -err_out_unlock: - spin_unlock_bh(&queue_lock); - return status; -} - -static int -ipq_mangle_ipv6(ipq_verdict_msg_t *v, struct nf_queue_entry *e) -{ - int diff; - struct ipv6hdr *user_iph = (struct ipv6hdr *)v->payload; - struct sk_buff *nskb; - - if (v->data_len < sizeof(*user_iph)) - return 0; - diff = v->data_len - e->skb->len; - if (diff < 0) { - if (pskb_trim(e->skb, v->data_len)) - return -ENOMEM; - } else if (diff > 0) { - if (v->data_len > 0xFFFF) - return -EINVAL; - if (diff > skb_tailroom(e->skb)) { - nskb = skb_copy_expand(e->skb, skb_headroom(e->skb), - diff, GFP_ATOMIC); - if (!nskb) { - printk(KERN_WARNING "ip6_queue: OOM " - "in mangle, dropping packet\n"); - return -ENOMEM; - } - kfree_skb(e->skb); - e->skb = nskb; - } - skb_put(e->skb, diff); - } - if (!skb_make_writable(e->skb, v->data_len)) - return -ENOMEM; - skb_copy_to_linear_data(e->skb, v->payload, v->data_len); - e->skb->ip_summed = CHECKSUM_NONE; - - return 0; -} - -static int -ipq_set_verdict(struct ipq_verdict_msg *vmsg, unsigned int len) -{ - struct nf_queue_entry *entry; - - if (vmsg->value > NF_MAX_VERDICT || vmsg->value == NF_STOLEN) - return -EINVAL; - - entry = ipq_find_dequeue_entry(vmsg->id); - if (entry == NULL) - return -ENOENT; - else { - int verdict = vmsg->value; - - if (vmsg->data_len && vmsg->data_len == len) - if (ipq_mangle_ipv6(vmsg, entry) < 0) - verdict = NF_DROP; - - nf_reinject(entry, verdict); - return 0; - } -} - -static int -ipq_set_mode(unsigned char mode, unsigned int range) -{ - int status; - - spin_lock_bh(&queue_lock); - status = __ipq_set_mode(mode, range); - spin_unlock_bh(&queue_lock); - return status; -} - -static int -ipq_receive_peer(struct ipq_peer_msg *pmsg, - unsigned char type, unsigned int len) -{ - int status = 0; - - if (len < sizeof(*pmsg)) - return -EINVAL; - - switch (type) { - case IPQM_MODE: - status = ipq_set_mode(pmsg->msg.mode.value, - pmsg->msg.mode.range); - break; - - case IPQM_VERDICT: - status = ipq_set_verdict(&pmsg->msg.verdict, - len - sizeof(*pmsg)); - break; - default: - status = -EINVAL; - } - return status; -} - -static int -dev_cmp(struct nf_queue_entry *entry, unsigned long ifindex) -{ - if (entry->indev) - if (entry->indev->ifindex == ifindex) - return 1; - - if (entry->outdev) - if (entry->outdev->ifindex == ifindex) - return 1; -#ifdef CONFIG_BRIDGE_NETFILTER - if (entry->skb->nf_bridge) { - if (entry->skb->nf_bridge->physindev && - entry->skb->nf_bridge->physindev->ifindex == ifindex) - return 1; - if (entry->skb->nf_bridge->physoutdev && - entry->skb->nf_bridge->physoutdev->ifindex == ifindex) - return 1; - } -#endif - return 0; -} - -static void -ipq_dev_drop(int ifindex) -{ - ipq_flush(dev_cmp, ifindex); -} - -#define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err)); return; } while (0) - -static inline void -__ipq_rcv_skb(struct sk_buff *skb) -{ - int status, type, pid, flags; - unsigned int nlmsglen, skblen; - struct nlmsghdr *nlh; - bool enable_timestamp = false; - - skblen = skb->len; - if (skblen < sizeof(*nlh)) - return; - - nlh = nlmsg_hdr(skb); - nlmsglen = nlh->nlmsg_len; - if (nlmsglen < sizeof(*nlh) || skblen < nlmsglen) - return; - - pid = nlh->nlmsg_pid; - flags = nlh->nlmsg_flags; - - if(pid <= 0 || !(flags & NLM_F_REQUEST) || flags & NLM_F_MULTI) - RCV_SKB_FAIL(-EINVAL); - - if (flags & MSG_TRUNC) - RCV_SKB_FAIL(-ECOMM); - - type = nlh->nlmsg_type; - if (type < NLMSG_NOOP || type >= IPQM_MAX) - RCV_SKB_FAIL(-EINVAL); - - if (type <= IPQM_BASE) - return; - - if (!capable(CAP_NET_ADMIN)) - RCV_SKB_FAIL(-EPERM); - - spin_lock_bh(&queue_lock); - - if (peer_pid) { - if (peer_pid != pid) { - spin_unlock_bh(&queue_lock); - RCV_SKB_FAIL(-EBUSY); - } - } else { - enable_timestamp = true; - peer_pid = pid; - } - - spin_unlock_bh(&queue_lock); - if (enable_timestamp) - net_enable_timestamp(); - - status = ipq_receive_peer(NLMSG_DATA(nlh), type, - nlmsglen - NLMSG_LENGTH(0)); - if (status < 0) - RCV_SKB_FAIL(status); - - if (flags & NLM_F_ACK) - netlink_ack(skb, nlh, 0); -} - -static void -ipq_rcv_skb(struct sk_buff *skb) -{ - mutex_lock(&ipqnl_mutex); - __ipq_rcv_skb(skb); - mutex_unlock(&ipqnl_mutex); -} - -static int -ipq_rcv_dev_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - struct net_device *dev = ptr; - - if (!net_eq(dev_net(dev), &init_net)) - return NOTIFY_DONE; - - /* Drop any packets associated with the downed device */ - if (event == NETDEV_DOWN) - ipq_dev_drop(dev->ifindex); - return NOTIFY_DONE; -} - -static struct notifier_block ipq_dev_notifier = { - .notifier_call = ipq_rcv_dev_event, -}; - -static int -ipq_rcv_nl_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - struct netlink_notify *n = ptr; - - if (event == NETLINK_URELEASE && n->protocol == NETLINK_IP6_FW) { - spin_lock_bh(&queue_lock); - if ((net_eq(n->net, &init_net)) && (n->pid == peer_pid)) - __ipq_reset(); - spin_unlock_bh(&queue_lock); - } - return NOTIFY_DONE; -} - -static struct notifier_block ipq_nl_notifier = { - .notifier_call = ipq_rcv_nl_event, -}; - -#ifdef CONFIG_SYSCTL -static struct ctl_table_header *ipq_sysctl_header; - -static ctl_table ipq_table[] = { - { - .procname = NET_IPQ_QMAX_NAME, - .data = &queue_maxlen, - .maxlen = sizeof(queue_maxlen), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { } -}; -#endif - -#ifdef CONFIG_PROC_FS -static int ip6_queue_show(struct seq_file *m, void *v) -{ - spin_lock_bh(&queue_lock); - - seq_printf(m, - "Peer PID : %d\n" - "Copy mode : %hu\n" - "Copy range : %u\n" - "Queue length : %u\n" - "Queue max. length : %u\n" - "Queue dropped : %u\n" - "Netfilter dropped : %u\n", - peer_pid, - copy_mode, - copy_range, - queue_total, - queue_maxlen, - queue_dropped, - queue_user_dropped); - - spin_unlock_bh(&queue_lock); - return 0; -} - -static int ip6_queue_open(struct inode *inode, struct file *file) -{ - return single_open(file, ip6_queue_show, NULL); -} - -static const struct file_operations ip6_queue_proc_fops = { - .open = ip6_queue_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; -#endif - -static const struct nf_queue_handler nfqh = { - .name = "ip6_queue", - .outfn = &ipq_enqueue_packet, -}; - -static int __init ip6_queue_init(void) -{ - int status = -ENOMEM; - struct proc_dir_entry *proc __maybe_unused; - - netlink_register_notifier(&ipq_nl_notifier); - ipqnl = netlink_kernel_create(&init_net, NETLINK_IP6_FW, 0, - ipq_rcv_skb, NULL, THIS_MODULE); - if (ipqnl == NULL) { - printk(KERN_ERR "ip6_queue: failed to create netlink socket\n"); - goto cleanup_netlink_notifier; - } - -#ifdef CONFIG_PROC_FS - proc = proc_create(IPQ_PROC_FS_NAME, 0, init_net.proc_net, - &ip6_queue_proc_fops); - if (!proc) { - printk(KERN_ERR "ip6_queue: failed to create proc entry\n"); - goto cleanup_ipqnl; - } -#endif - register_netdevice_notifier(&ipq_dev_notifier); -#ifdef CONFIG_SYSCTL - ipq_sysctl_header = register_sysctl_paths(net_ipv6_ctl_path, ipq_table); -#endif - status = nf_register_queue_handler(NFPROTO_IPV6, &nfqh); - if (status < 0) { - printk(KERN_ERR "ip6_queue: failed to register queue handler\n"); - goto cleanup_sysctl; - } - return status; - -cleanup_sysctl: -#ifdef CONFIG_SYSCTL - unregister_sysctl_table(ipq_sysctl_header); -#endif - unregister_netdevice_notifier(&ipq_dev_notifier); - proc_net_remove(&init_net, IPQ_PROC_FS_NAME); - -cleanup_ipqnl: __maybe_unused - netlink_kernel_release(ipqnl); - mutex_lock(&ipqnl_mutex); - mutex_unlock(&ipqnl_mutex); - -cleanup_netlink_notifier: - netlink_unregister_notifier(&ipq_nl_notifier); - return status; -} - -static void __exit ip6_queue_fini(void) -{ - nf_unregister_queue_handlers(&nfqh); - - ipq_flush(NULL, 0); - -#ifdef CONFIG_SYSCTL - unregister_sysctl_table(ipq_sysctl_header); -#endif - unregister_netdevice_notifier(&ipq_dev_notifier); - proc_net_remove(&init_net, IPQ_PROC_FS_NAME); - - netlink_kernel_release(ipqnl); - mutex_lock(&ipqnl_mutex); - mutex_unlock(&ipqnl_mutex); - - netlink_unregister_notifier(&ipq_nl_notifier); -} - -MODULE_DESCRIPTION("IPv6 packet queue handler"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_IP6_FW); - -module_init(ip6_queue_init); -module_exit(ip6_queue_fini); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 94874b0bdcd..d7cb04506c3 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -78,19 +78,6 @@ EXPORT_SYMBOL_GPL(ip6t_alloc_initial_table); Hence the start of any table is given by get_table() below. */ -/* Check for an extension */ -int -ip6t_ext_hdr(u8 nexthdr) -{ - return (nexthdr == IPPROTO_HOPOPTS) || - (nexthdr == IPPROTO_ROUTING) || - (nexthdr == IPPROTO_FRAGMENT) || - (nexthdr == IPPROTO_ESP) || - (nexthdr == IPPROTO_AH) || - (nexthdr == IPPROTO_NONE) || - (nexthdr == IPPROTO_DSTOPTS); -} - /* Returns whether matches rule or not. */ /* Performance critical - called for every packet */ static inline bool @@ -146,7 +133,7 @@ ip6_packet_match(const struct sk_buff *skb, int protohdr; unsigned short _frag_off; - protohdr = ipv6_find_hdr(skb, protoff, -1, &_frag_off); + protohdr = ipv6_find_hdr(skb, protoff, -1, &_frag_off, NULL); if (protohdr < 0) { if (_frag_off == 0) *hotdrop = true; @@ -194,8 +181,7 @@ ip6_checkentry(const struct ip6t_ip6 *ipv6) static unsigned int ip6t_error(struct sk_buff *skb, const struct xt_action_param *par) { - if (net_ratelimit()) - pr_info("error: `%s'\n", (const char *)par->targinfo); + net_info_ratelimited("error: `%s'\n", (const char *)par->targinfo); return NF_DROP; } @@ -375,6 +361,7 @@ ip6t_do_table(struct sk_buff *skb, const struct xt_entry_match *ematch; IP_NF_ASSERT(e); + acpar.thoff = 0; if (!ip6_packet_match(skb, indev, outdev, &e->ipv6, &acpar.thoff, &acpar.fragoff, &acpar.hotdrop)) { no_match: @@ -409,7 +396,7 @@ ip6t_do_table(struct sk_buff *skb, if (v < 0) { /* Pop from stack? */ if (v != XT_RETURN) { - verdict = (unsigned)(-v) - 1; + verdict = (unsigned int)(-v) - 1; break; } if (*stackptr <= origptr) @@ -2291,6 +2278,10 @@ static void __exit ip6_tables_fini(void) * if target < 0. "last header" is transport protocol header, ESP, or * "No next header". * + * Note that *offset is used as input/output parameter. an if it is not zero, + * then it must be a valid offset to an inner IPv6 header. This can be used + * to explore inner IPv6 header, eg. ICMPv6 error messages. + * * If target header is found, its offset is set in *offset and return protocol * number. Otherwise, return -1. * @@ -2302,17 +2293,33 @@ static void __exit ip6_tables_fini(void) * *offset is meaningless and fragment offset is stored in *fragoff if fragoff * isn't NULL. * + * if flags is not NULL and it's a fragment, then the frag flag IP6T_FH_F_FRAG + * will be set. If it's an AH header, the IP6T_FH_F_AUTH flag is set and + * target < 0, then this function will stop at the AH header. */ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, - int target, unsigned short *fragoff) + int target, unsigned short *fragoff, int *flags) { unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr); u8 nexthdr = ipv6_hdr(skb)->nexthdr; - unsigned int len = skb->len - start; + unsigned int len; if (fragoff) *fragoff = 0; + if (*offset) { + struct ipv6hdr _ip6, *ip6; + + ip6 = skb_header_pointer(skb, *offset, sizeof(_ip6), &_ip6); + if (!ip6 || (ip6->version != 6)) { + printk(KERN_ERR "IPv6 header not found\n"); + return -EBADMSG; + } + start = *offset + sizeof(struct ipv6hdr); + nexthdr = ip6->nexthdr; + } + len = skb->len - start; + while (nexthdr != target) { struct ipv6_opt_hdr _hdr, *hp; unsigned int hdrlen; @@ -2329,6 +2336,9 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, if (nexthdr == NEXTHDR_FRAGMENT) { unsigned short _frag_off; __be16 *fp; + + if (flags) /* Indicate that this is a fragment */ + *flags |= IP6T_FH_F_FRAG; fp = skb_header_pointer(skb, start+offsetof(struct frag_hdr, frag_off), @@ -2349,9 +2359,11 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, return -ENOENT; } hdrlen = 8; - } else if (nexthdr == NEXTHDR_AUTH) + } else if (nexthdr == NEXTHDR_AUTH) { + if (flags && (*flags & IP6T_FH_F_AUTH) && (target < 0)) + break; hdrlen = (hp->hdrlen + 2) << 2; - else + } else hdrlen = ipv6_optlen(hp); nexthdr = hp->nexthdr; @@ -2366,7 +2378,6 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, EXPORT_SYMBOL(ip6t_register_table); EXPORT_SYMBOL(ip6t_unregister_table); EXPORT_SYMBOL(ip6t_do_table); -EXPORT_SYMBOL(ip6t_ext_hdr); EXPORT_SYMBOL(ipv6_find_hdr); module_init(ip6_tables_init); diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index aad2fa41cf4..fd4fb34c51c 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -114,8 +114,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) GFP_ATOMIC); if (!nskb) { - if (net_ratelimit()) - pr_debug("cannot alloc skb\n"); + net_dbg_ratelimited("cannot alloc skb\n"); dst_release(dst); return; } @@ -210,8 +209,7 @@ reject_tg6(struct sk_buff *skb, const struct xt_action_param *par) send_reset(net, skb); break; default: - if (net_ratelimit()) - pr_info("case %u not handled yet\n", reject->with); + net_info_ratelimited("case %u not handled yet\n", reject->with); break; } diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c index 89cccc5a9c9..04099ab7d2e 100644 --- a/net/ipv6/netfilter/ip6t_ah.c +++ b/net/ipv6/netfilter/ip6t_ah.c @@ -41,11 +41,11 @@ static bool ah_mt6(const struct sk_buff *skb, struct xt_action_param *par) struct ip_auth_hdr _ah; const struct ip_auth_hdr *ah; const struct ip6t_ah *ahinfo = par->matchinfo; - unsigned int ptr; + unsigned int ptr = 0; unsigned int hdrlen = 0; int err; - err = ipv6_find_hdr(skb, &ptr, NEXTHDR_AUTH, NULL); + err = ipv6_find_hdr(skb, &ptr, NEXTHDR_AUTH, NULL, NULL); if (err < 0) { if (err != -ENOENT) par->hotdrop = true; diff --git a/net/ipv6/netfilter/ip6t_frag.c b/net/ipv6/netfilter/ip6t_frag.c index eda898fda6c..3b5735e56bf 100644 --- a/net/ipv6/netfilter/ip6t_frag.c +++ b/net/ipv6/netfilter/ip6t_frag.c @@ -40,10 +40,10 @@ frag_mt6(const struct sk_buff *skb, struct xt_action_param *par) struct frag_hdr _frag; const struct frag_hdr *fh; const struct ip6t_frag *fraginfo = par->matchinfo; - unsigned int ptr; + unsigned int ptr = 0; int err; - err = ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL); + err = ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL, NULL); if (err < 0) { if (err != -ENOENT) par->hotdrop = true; diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c index 59df051eaef..01df142bb02 100644 --- a/net/ipv6/netfilter/ip6t_hbh.c +++ b/net/ipv6/netfilter/ip6t_hbh.c @@ -50,7 +50,7 @@ hbh_mt6(const struct sk_buff *skb, struct xt_action_param *par) const struct ipv6_opt_hdr *oh; const struct ip6t_opts *optinfo = par->matchinfo; unsigned int temp; - unsigned int ptr; + unsigned int ptr = 0; unsigned int hdrlen = 0; bool ret = false; u8 _opttype; @@ -62,7 +62,7 @@ hbh_mt6(const struct sk_buff *skb, struct xt_action_param *par) err = ipv6_find_hdr(skb, &ptr, (par->match == &hbh_mt6_reg[0]) ? - NEXTHDR_HOP : NEXTHDR_DEST, NULL); + NEXTHDR_HOP : NEXTHDR_DEST, NULL, NULL); if (err < 0) { if (err != -ENOENT) par->hotdrop = true; diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c index d8488c50a8e..2c99b94eeca 100644 --- a/net/ipv6/netfilter/ip6t_rt.c +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -42,14 +42,14 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par) const struct ipv6_rt_hdr *rh; const struct ip6t_rt *rtinfo = par->matchinfo; unsigned int temp; - unsigned int ptr; + unsigned int ptr = 0; unsigned int hdrlen = 0; bool ret = false; struct in6_addr _addr; const struct in6_addr *ap; int err; - err = ipv6_find_hdr(skb, &ptr, NEXTHDR_ROUTING, NULL); + err = ipv6_find_hdr(skb, &ptr, NEXTHDR_ROUTING, NULL, NULL); if (err < 0) { if (err != -ENOENT) par->hotdrop = true; diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 00d19173db7..4d782405f12 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -42,8 +42,7 @@ ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out) /* root is playing with raw sockets. */ if (skb->len < sizeof(struct iphdr) || ip_hdrlen(skb) < sizeof(struct iphdr)) { - if (net_ratelimit()) - pr_warning("ip6t_hook: happy cracking.\n"); + net_warn_ratelimited("ip6t_hook: happy cracking\n"); return NF_ACCEPT; } #endif diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 4111050a9fc..3224ef90a21 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -232,8 +232,7 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum, { /* root is playing with raw sockets. */ if (skb->len < sizeof(struct ipv6hdr)) { - if (net_ratelimit()) - pr_notice("ipv6_conntrack_local: packet too short\n"); + net_notice_ratelimited("ipv6_conntrack_local: packet too short\n"); return NF_ACCEPT; } return __ipv6_conntrack_in(dev_net(out), hooknum, skb, okfn); @@ -278,10 +277,11 @@ static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { static int ipv6_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { - NLA_PUT(skb, CTA_IP_V6_SRC, sizeof(u_int32_t) * 4, - &tuple->src.u3.ip6); - NLA_PUT(skb, CTA_IP_V6_DST, sizeof(u_int32_t) * 4, - &tuple->dst.u3.ip6); + if (nla_put(skb, CTA_IP_V6_SRC, sizeof(u_int32_t) * 4, + &tuple->src.u3.ip6) || + nla_put(skb, CTA_IP_V6_DST, sizeof(u_int32_t) * 4, + &tuple->dst.u3.ip6)) + goto nla_put_failure; return 0; nla_put_failure: diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 92cc9f2931a..3e81904fbbc 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -234,10 +234,10 @@ icmpv6_error(struct net *net, struct nf_conn *tmpl, static int icmpv6_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *t) { - NLA_PUT_BE16(skb, CTA_PROTO_ICMPV6_ID, t->src.u.icmp.id); - NLA_PUT_U8(skb, CTA_PROTO_ICMPV6_TYPE, t->dst.u.icmp.type); - NLA_PUT_U8(skb, CTA_PROTO_ICMPV6_CODE, t->dst.u.icmp.code); - + if (nla_put_be16(skb, CTA_PROTO_ICMPV6_ID, t->src.u.icmp.id) || + nla_put_u8(skb, CTA_PROTO_ICMPV6_TYPE, t->dst.u.icmp.type) || + nla_put_u8(skb, CTA_PROTO_ICMPV6_CODE, t->dst.u.icmp.code)) + goto nla_put_failure; return 0; nla_put_failure: @@ -300,8 +300,8 @@ icmpv6_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeout = data; - NLA_PUT_BE32(skb, CTA_TIMEOUT_ICMPV6_TIMEOUT, htonl(*timeout / HZ)); - + if (nla_put_be32(skb, CTA_TIMEOUT_ICMPV6_TIMEOUT, htonl(*timeout / HZ))) + goto nla_put_failure; return 0; nla_put_failure: diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 38f00b0298d..c9c78c2e666 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -444,12 +444,11 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev) return head; out_oversize: - if (net_ratelimit()) - printk(KERN_DEBUG "nf_ct_frag6_reasm: payload len = %d\n", payload_len); + net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n", + payload_len); goto out_fail; out_oom: - if (net_ratelimit()) - printk(KERN_DEBUG "nf_ct_frag6_reasm: no memory for reassembly\n"); + net_dbg_ratelimited("nf_ct_frag6_reasm: no memory for reassembly\n"); out_fail: return NULL; } @@ -626,8 +625,8 @@ int nf_ct_frag6_init(void) inet_frags_init(&nf_frags); #ifdef CONFIG_SYSCTL - nf_ct_frag6_sysctl_header = register_sysctl_paths(nf_net_netfilter_sysctl_path, - nf_ct_frag6_sysctl_table); + nf_ct_frag6_sysctl_header = register_net_sysctl(&init_net, "net/netfilter", + nf_ct_frag6_sysctl_table); if (!nf_ct_frag6_sysctl_header) { inet_frags_fini(&nf_frags); return -ENOMEM; @@ -640,7 +639,7 @@ int nf_ct_frag6_init(void) void nf_ct_frag6_cleanup(void) { #ifdef CONFIG_SYSCTL - unregister_sysctl_table(nf_ct_frag6_sysctl_header); + unregister_net_sysctl_table(nf_ct_frag6_sysctl_header); nf_ct_frag6_sysctl_header = NULL; #endif inet_frags_fini(&nf_frags); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 5bddea77884..93d69836fde 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -72,7 +72,7 @@ static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, const struct in6_addr *rmt_addr, int dif) { struct hlist_node *node; - int is_multicast = ipv6_addr_is_multicast(loc_addr); + bool is_multicast = ipv6_addr_is_multicast(loc_addr); sk_for_each_from(sk, node) if (inet_sk(sk)->inet_num == num) { @@ -153,12 +153,12 @@ EXPORT_SYMBOL(rawv6_mh_filter_unregister); * * Caller owns SKB so we must make clones. */ -static int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) +static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) { const struct in6_addr *saddr; const struct in6_addr *daddr; struct sock *sk; - int delivered = 0; + bool delivered = false; __u8 hash; struct net *net; @@ -179,7 +179,7 @@ static int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) while (sk) { int filtered; - delivered = 1; + delivered = true; switch (nexthdr) { case IPPROTO_ICMPV6: filtered = icmpv6_filter(sk, skb); @@ -225,7 +225,7 @@ out: return delivered; } -int raw6_local_deliver(struct sk_buff *skb, int nexthdr) +bool raw6_local_deliver(struct sk_buff *skb, int nexthdr) { struct sock *raw_sk; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 9447bd69873..4ff9af628e7 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -134,15 +134,16 @@ static unsigned int ip6_hashfn(struct inet_frag_queue *q) return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr, ip6_frags.rnd); } -int ip6_frag_match(struct inet_frag_queue *q, void *a) +bool ip6_frag_match(struct inet_frag_queue *q, void *a) { struct frag_queue *fq; struct ip6_create_arg *arg = a; fq = container_of(q, struct frag_queue, q); - return (fq->id == arg->id && fq->user == arg->user && - ipv6_addr_equal(&fq->saddr, arg->src) && - ipv6_addr_equal(&fq->daddr, arg->dst)); + return fq->id == arg->id && + fq->user == arg->user && + ipv6_addr_equal(&fq->saddr, arg->src) && + ipv6_addr_equal(&fq->daddr, arg->dst); } EXPORT_SYMBOL(ip6_frag_match); @@ -414,6 +415,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, struct sk_buff *fp, *head = fq->q.fragments; int payload_len; unsigned int nhoff; + int sum_truesize; fq_kill(fq); @@ -433,7 +435,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, skb_morph(head, fq->q.fragments); head->next = fq->q.fragments->next; - kfree_skb(fq->q.fragments); + consume_skb(fq->q.fragments); fq->q.fragments = head; } @@ -483,20 +485,33 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, head->mac_header += sizeof(struct frag_hdr); head->network_header += sizeof(struct frag_hdr); - skb_shinfo(head)->frag_list = head->next; skb_reset_transport_header(head); skb_push(head, head->data - skb_network_header(head)); - for (fp=head->next; fp; fp = fp->next) { - head->data_len += fp->len; - head->len += fp->len; + sum_truesize = head->truesize; + for (fp = head->next; fp;) { + bool headstolen; + int delta; + struct sk_buff *next = fp->next; + + sum_truesize += fp->truesize; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); - head->truesize += fp->truesize; + + if (skb_try_coalesce(head, fp, &headstolen, &delta)) { + kfree_skb_partial(fp, headstolen); + } else { + if (!skb_shinfo(head)->frag_list) + skb_shinfo(head)->frag_list = fp; + head->data_len += fp->len; + head->len += fp->len; + head->truesize += fp->truesize; + } + fp = next; } - atomic_sub(head->truesize, &fq->q.net->mem); + atomic_sub(sum_truesize, &fq->q.net->mem); head->next = NULL; head->dev = dev; @@ -518,12 +533,10 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, return 1; out_oversize: - if (net_ratelimit()) - printk(KERN_DEBUG "ip6_frag_reasm: payload len = %d\n", payload_len); + net_dbg_ratelimited("ip6_frag_reasm: payload len = %d\n", payload_len); goto out_fail; out_oom: - if (net_ratelimit()) - printk(KERN_DEBUG "ip6_frag_reasm: no memory for reassembly\n"); + net_dbg_ratelimited("ip6_frag_reasm: no memory for reassembly\n"); out_fail: rcu_read_lock(); IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); @@ -646,7 +659,7 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net) table[2].data = &net->ipv6.frags.timeout; } - hdr = register_net_sysctl_table(net, net_ipv6_ctl_path, table); + hdr = register_net_sysctl(net, "net/ipv6", table); if (hdr == NULL) goto err_reg; @@ -674,7 +687,7 @@ static struct ctl_table_header *ip6_ctl_header; static int ip6_frags_sysctl_register(void) { - ip6_ctl_header = register_net_sysctl_rotable(net_ipv6_ctl_path, + ip6_ctl_header = register_net_sysctl(&init_net, "net/ipv6", ip6_frags_ctl_table); return ip6_ctl_header == NULL ? -ENOMEM : 0; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 496b62712fe..999a982ad3f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -24,6 +24,8 @@ * Fixed routing subtrees. */ +#define pr_fmt(fmt) "IPv6: " fmt + #include <linux/capability.h> #include <linux/errno.h> #include <linux/export.h> @@ -62,7 +64,7 @@ #include <linux/sysctl.h> #endif -static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort, +static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, const struct in6_addr *dest); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); @@ -82,7 +84,7 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu); static struct rt6_info *rt6_add_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, int ifindex, - unsigned pref); + unsigned int pref); static struct rt6_info *rt6_get_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, int ifindex); @@ -285,6 +287,10 @@ static void ip6_dst_destroy(struct dst_entry *dst) rt->rt6i_idev = NULL; in6_dev_put(idev); } + + if (!(rt->rt6i_flags & RTF_EXPIRES) && dst->from) + dst_release(dst->from); + if (peer) { rt->rt6i_peer = NULL; inet_putpeer(peer); @@ -327,13 +333,22 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, } } -static __inline__ int rt6_check_expired(const struct rt6_info *rt) +static bool rt6_check_expired(const struct rt6_info *rt) { - return (rt->rt6i_flags & RTF_EXPIRES) && - time_after(jiffies, rt->dst.expires); + struct rt6_info *ort = NULL; + + if (rt->rt6i_flags & RTF_EXPIRES) { + if (time_after(jiffies, rt->dst.expires)) + return true; + } else if (rt->dst.from) { + ort = (struct rt6_info *) rt->dst.from; + return (ort->rt6i_flags & RTF_EXPIRES) && + time_after(jiffies, ort->dst.expires); + } + return false; } -static inline int rt6_need_strict(const struct in6_addr *daddr) +static bool rt6_need_strict(const struct in6_addr *daddr) { return ipv6_addr_type(daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); @@ -620,12 +635,11 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); if (rt) { - if (!addrconf_finite_timeout(lifetime)) { - rt->rt6i_flags &= ~RTF_EXPIRES; - } else { - rt->dst.expires = jiffies + HZ * lifetime; - rt->rt6i_flags |= RTF_EXPIRES; - } + if (!addrconf_finite_timeout(lifetime)) + rt6_clean_expires(rt); + else + rt6_set_expires(rt, jiffies + HZ * lifetime); + dst_release(&rt->dst); } return 0; @@ -730,7 +744,7 @@ int ip6_ins_rt(struct rt6_info *rt) return __ip6_ins_rt(rt, &info); } -static struct rt6_info *rt6_alloc_cow(const struct rt6_info *ort, +static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, const struct in6_addr *daddr, const struct in6_addr *saddr) { @@ -782,9 +796,7 @@ static struct rt6_info *rt6_alloc_cow(const struct rt6_info *ort, goto retry; } - if (net_ratelimit()) - printk(KERN_WARNING - "ipv6: Neighbour table overflow.\n"); + net_warn_ratelimited("Neighbour table overflow\n"); dst_free(&rt->dst); return NULL; } @@ -881,6 +893,16 @@ static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table * return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, flags); } +static struct dst_entry *ip6_route_input_lookup(struct net *net, + struct net_device *dev, + struct flowi6 *fl6, int flags) +{ + if (rt6_need_strict(&fl6->daddr) && dev->type != ARPHRD_PIMREG) + flags |= RT6_LOOKUP_F_IFACE; + + return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_input); +} + void ip6_route_input(struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); @@ -895,10 +917,7 @@ void ip6_route_input(struct sk_buff *skb) .flowi6_proto = iph->nexthdr, }; - if (rt6_need_strict(&iph->daddr) && skb->dev->type != ARPHRD_PIMREG) - flags |= RT6_LOOKUP_F_IFACE; - - skb_dst_set(skb, fib6_rule_lookup(net, &fl6, flags, ip6_pol_route_input)); + skb_dst_set(skb, ip6_route_input_lookup(net, skb->dev, &fl6, flags)); } static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table, @@ -947,10 +966,10 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori rt->rt6i_idev = ort->rt6i_idev; if (rt->rt6i_idev) in6_dev_hold(rt->rt6i_idev); - rt->dst.expires = 0; rt->rt6i_gateway = ort->rt6i_gateway; - rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES; + rt->rt6i_flags = ort->rt6i_flags; + rt6_clean_expires(rt); rt->rt6i_metric = 0; memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); @@ -1012,10 +1031,9 @@ static void ip6_link_failure(struct sk_buff *skb) rt = (struct rt6_info *) skb_dst(skb); if (rt) { - if (rt->rt6i_flags & RTF_CACHE) { - dst_set_expires(&rt->dst, 0); - rt->rt6i_flags |= RTF_EXPIRES; - } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) + if (rt->rt6i_flags & RTF_CACHE) + rt6_update_expires(rt, 0); + else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) rt->rt6i_node->fn_sernum = -1; } } @@ -1264,7 +1282,7 @@ int ip6_route_add(struct fib6_config *cfg) !(cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_CREATE)) { table = fib6_get_table(net, cfg->fc_table); if (!table) { - printk(KERN_WARNING "IPv6: NLM_F_CREATE should be specified when creating new route\n"); + pr_warn("NLM_F_CREATE should be specified when creating new route\n"); table = fib6_new_table(net, cfg->fc_table); } } else { @@ -1282,9 +1300,12 @@ int ip6_route_add(struct fib6_config *cfg) } rt->dst.obsolete = -1; - rt->dst.expires = (cfg->fc_flags & RTF_EXPIRES) ? - jiffies + clock_t_to_jiffies(cfg->fc_expires) : - 0; + + if (cfg->fc_flags & RTF_EXPIRES) + rt6_set_expires(rt, jiffies + + clock_t_to_jiffies(cfg->fc_expires)); + else + rt6_clean_expires(rt); if (cfg->fc_protocol == RTPROT_UNSPEC) cfg->fc_protocol = RTPROT_BOOT; @@ -1622,9 +1643,7 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src, rt = ip6_route_redirect(dest, src, saddr, neigh->dev); if (rt == net->ipv6.ip6_null_entry) { - if (net_ratelimit()) - printk(KERN_DEBUG "rt6_redirect: source isn't a valid nexthop " - "for redirect target\n"); + net_dbg_ratelimited("rt6_redirect: source isn't a valid nexthop for redirect target\n"); goto out; } @@ -1729,8 +1748,8 @@ again: features |= RTAX_FEATURE_ALLFRAG; dst_metric_set(&rt->dst, RTAX_FEATURES, features); } - dst_set_expires(&rt->dst, net->ipv6.sysctl.ip6_rt_mtu_expires); - rt->rt6i_flags |= RTF_MODIFIED|RTF_EXPIRES; + rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires); + rt->rt6i_flags |= RTF_MODIFIED; goto out; } @@ -1758,9 +1777,8 @@ again: * which is 10 mins. After 10 mins the decreased pmtu is expired * and detecting PMTU increase will be automatically happened. */ - dst_set_expires(&nrt->dst, net->ipv6.sysctl.ip6_rt_mtu_expires); - nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES; - + rt6_update_expires(nrt, net->ipv6.sysctl.ip6_rt_mtu_expires); + nrt->rt6i_flags |= RTF_DYNAMIC; ip6_ins_rt(nrt); } out: @@ -1792,7 +1810,7 @@ void rt6_pmtu_discovery(const struct in6_addr *daddr, const struct in6_addr *sad * Misc support functions */ -static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort, +static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, const struct in6_addr *dest) { struct net *net = dev_net(ort->dst.dev); @@ -1812,10 +1830,14 @@ static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort, if (rt->rt6i_idev) in6_dev_hold(rt->rt6i_idev); rt->dst.lastuse = jiffies; - rt->dst.expires = 0; rt->rt6i_gateway = ort->rt6i_gateway; - rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES; + rt->rt6i_flags = ort->rt6i_flags; + if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) == + (RTF_DEFAULT | RTF_ADDRCONF)) + rt6_set_from(rt, ort); + else + rt6_clean_expires(rt); rt->rt6i_metric = 0; #ifdef CONFIG_IPV6_SUBTREES @@ -1863,7 +1885,7 @@ out: static struct rt6_info *rt6_add_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, int ifindex, - unsigned pref) + unsigned int pref) { struct fib6_config cfg = { .fc_table = RT6_TABLE_INFO, @@ -2082,9 +2104,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, int err; if (!rt) { - if (net_ratelimit()) - pr_warning("IPv6: Maximum number of routes reached," - " consider increasing route/max_size.\n"); + net_warn_ratelimited("Maximum number of routes reached, consider increasing route/max_size\n"); return ERR_PTR(-ENOMEM); } @@ -2193,10 +2213,9 @@ void rt6_ifdown(struct net *net, struct net_device *dev) icmp6_clean_all(fib6_ifdown, &adn); } -struct rt6_mtu_change_arg -{ +struct rt6_mtu_change_arg { struct net_device *dev; - unsigned mtu; + unsigned int mtu; }; static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) @@ -2238,7 +2257,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) return 0; } -void rt6_mtu_change(struct net_device *dev, unsigned mtu) +void rt6_mtu_change(struct net_device *dev, unsigned int mtu) { struct rt6_mtu_change_arg arg = { .dev = dev, @@ -2406,7 +2425,8 @@ static int rt6_fill_node(struct net *net, else table = RT6_TABLE_UNSPEC; rtm->rtm_table = table; - NLA_PUT_U32(skb, RTA_TABLE, table); + if (nla_put_u32(skb, RTA_TABLE, table)) + goto nla_put_failure; if (rt->rt6i_flags & RTF_REJECT) rtm->rtm_type = RTN_UNREACHABLE; else if (rt->rt6i_flags & RTF_LOCAL) @@ -2429,16 +2449,20 @@ static int rt6_fill_node(struct net *net, rtm->rtm_flags |= RTM_F_CLONED; if (dst) { - NLA_PUT(skb, RTA_DST, 16, dst); + if (nla_put(skb, RTA_DST, 16, dst)) + goto nla_put_failure; rtm->rtm_dst_len = 128; } else if (rtm->rtm_dst_len) - NLA_PUT(skb, RTA_DST, 16, &rt->rt6i_dst.addr); + if (nla_put(skb, RTA_DST, 16, &rt->rt6i_dst.addr)) + goto nla_put_failure; #ifdef CONFIG_IPV6_SUBTREES if (src) { - NLA_PUT(skb, RTA_SRC, 16, src); + if (nla_put(skb, RTA_SRC, 16, src)) + goto nla_put_failure; rtm->rtm_src_len = 128; - } else if (rtm->rtm_src_len) - NLA_PUT(skb, RTA_SRC, 16, &rt->rt6i_src.addr); + } else if (rtm->rtm_src_len && + nla_put(skb, RTA_SRC, 16, &rt->rt6i_src.addr)) + goto nla_put_failure; #endif if (iif) { #ifdef CONFIG_IPV6_MROUTE @@ -2456,17 +2480,20 @@ static int rt6_fill_node(struct net *net, } } else #endif - NLA_PUT_U32(skb, RTA_IIF, iif); + if (nla_put_u32(skb, RTA_IIF, iif)) + goto nla_put_failure; } else if (dst) { struct in6_addr saddr_buf; - if (ip6_route_get_saddr(net, rt, dst, 0, &saddr_buf) == 0) - NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); + if (ip6_route_get_saddr(net, rt, dst, 0, &saddr_buf) == 0 && + nla_put(skb, RTA_PREFSRC, 16, &saddr_buf)) + goto nla_put_failure; } if (rt->rt6i_prefsrc.plen) { struct in6_addr saddr_buf; saddr_buf = rt->rt6i_prefsrc.addr; - NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); + if (nla_put(skb, RTA_PREFSRC, 16, &saddr_buf)) + goto nla_put_failure; } if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) @@ -2482,11 +2509,11 @@ static int rt6_fill_node(struct net *net, } rcu_read_unlock(); - if (rt->dst.dev) - NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex); - - NLA_PUT_U32(skb, RTA_PRIORITY, rt->rt6i_metric); - + if (rt->dst.dev && + nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex)) + goto nla_put_failure; + if (nla_put_u32(skb, RTA_PRIORITY, rt->rt6i_metric)) + goto nla_put_failure; if (!(rt->rt6i_flags & RTF_EXPIRES)) expires = 0; else if (rt->dst.expires - jiffies < INT_MAX) @@ -2537,7 +2564,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void struct sk_buff *skb; struct rtmsg *rtm; struct flowi6 fl6; - int err, iif = 0; + int err, iif = 0, oif = 0; err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy); if (err < 0) @@ -2564,19 +2591,34 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void iif = nla_get_u32(tb[RTA_IIF]); if (tb[RTA_OIF]) - fl6.flowi6_oif = nla_get_u32(tb[RTA_OIF]); + oif = nla_get_u32(tb[RTA_OIF]); if (iif) { struct net_device *dev; + int flags = 0; + dev = __dev_get_by_index(net, iif); if (!dev) { err = -ENODEV; goto errout; } + + fl6.flowi6_iif = iif; + + if (!ipv6_addr_any(&fl6.saddr)) + flags |= RT6_LOOKUP_F_HAS_SADDR; + + rt = (struct rt6_info *)ip6_route_input_lookup(net, dev, &fl6, + flags); + } else { + fl6.flowi6_oif = oif; + + rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6); } skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { + dst_release(&rt->dst); err = -ENOBUFS; goto errout; } @@ -2587,7 +2629,6 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void skb_reset_mac_header(skb); skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr)); - rt = (struct rt6_info*) ip6_route_output(net, NULL, &fl6); skb_dst_set(skb, &rt->dst); err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif, diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index c4ffd174352..60415711563 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -17,6 +17,8 @@ * Fred Templin <fred.l.templin@boeing.com>: isatap support */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> @@ -87,35 +89,51 @@ struct sit_net { /* often modified stats are per cpu, other are shared (netdev->stats) */ struct pcpu_tstats { - unsigned long rx_packets; - unsigned long rx_bytes; - unsigned long tx_packets; - unsigned long tx_bytes; -} __attribute__((aligned(4*sizeof(unsigned long)))); + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; + struct u64_stats_sync syncp; +}; -static struct net_device_stats *ipip6_get_stats(struct net_device *dev) +static struct rtnl_link_stats64 *ipip6_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *tot) { - struct pcpu_tstats sum = { 0 }; int i; for_each_possible_cpu(i) { const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); - - sum.rx_packets += tstats->rx_packets; - sum.rx_bytes += tstats->rx_bytes; - sum.tx_packets += tstats->tx_packets; - sum.tx_bytes += tstats->tx_bytes; + u64 rx_packets, rx_bytes, tx_packets, tx_bytes; + unsigned int start; + + do { + start = u64_stats_fetch_begin_bh(&tstats->syncp); + rx_packets = tstats->rx_packets; + tx_packets = tstats->tx_packets; + rx_bytes = tstats->rx_bytes; + tx_bytes = tstats->tx_bytes; + } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); + + tot->rx_packets += rx_packets; + tot->tx_packets += tx_packets; + tot->rx_bytes += rx_bytes; + tot->tx_bytes += tx_bytes; } - dev->stats.rx_packets = sum.rx_packets; - dev->stats.rx_bytes = sum.rx_bytes; - dev->stats.tx_packets = sum.tx_packets; - dev->stats.tx_bytes = sum.tx_bytes; - return &dev->stats; + + tot->rx_errors = dev->stats.rx_errors; + tot->tx_fifo_errors = dev->stats.tx_fifo_errors; + tot->tx_carrier_errors = dev->stats.tx_carrier_errors; + tot->tx_dropped = dev->stats.tx_dropped; + tot->tx_aborted_errors = dev->stats.tx_aborted_errors; + tot->tx_errors = dev->stats.tx_errors; + + return tot; } + /* * Must be invoked with rcu_read_lock */ -static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net, +static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, struct net_device *dev, __be32 remote, __be32 local) { unsigned int h0 = HASH(remote); @@ -686,12 +704,11 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (neigh == NULL) { - if (net_ratelimit()) - printk(KERN_DEBUG "sit: nexthop == NULL\n"); + net_dbg_ratelimited("sit: nexthop == NULL\n"); goto tx_error; } - addr6 = (const struct in6_addr*)&neigh->primary_key; + addr6 = (const struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if ((addr_type & IPV6_ADDR_UNICAST) && @@ -716,12 +733,11 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (neigh == NULL) { - if (net_ratelimit()) - printk(KERN_DEBUG "sit: nexthop == NULL\n"); + net_dbg_ratelimited("sit: nexthop == NULL\n"); goto tx_error; } - addr6 = (const struct in6_addr*)&neigh->primary_key; + addr6 = (const struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) { @@ -1126,7 +1142,7 @@ static const struct net_device_ops ipip6_netdev_ops = { .ndo_start_xmit = ipip6_tunnel_xmit, .ndo_do_ioctl = ipip6_tunnel_ioctl, .ndo_change_mtu = ipip6_tunnel_change_mtu, - .ndo_get_stats = ipip6_get_stats, + .ndo_get_stats64= ipip6_get_stats64, }; static void ipip6_dev_free(struct net_device *dev) @@ -1287,7 +1303,7 @@ static int __init sit_init(void) { int err; - printk(KERN_INFO "IPv6 over IPv4 tunneling driver\n"); + pr_info("IPv6 over IPv4 tunneling driver\n"); err = register_pernet_device(&sit_net_ops); if (err < 0) @@ -1295,7 +1311,7 @@ static int __init sit_init(void) err = xfrm4_tunnel_register(&sit_handler, AF_INET6); if (err < 0) { unregister_pernet_device(&sit_net_ops); - printk(KERN_INFO "sit init: Can't add protocol\n"); + pr_info("%s: can't add protocol\n", __func__); } return err; } diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 166a57c47d3..e85c48bd404 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -16,32 +16,8 @@ #include <net/addrconf.h> #include <net/inet_frag.h> -static struct ctl_table empty[1]; - -static ctl_table ipv6_static_skeleton[] = { - { - .procname = "neigh", - .maxlen = 0, - .mode = 0555, - .child = empty, - }, - { } -}; - static ctl_table ipv6_table_template[] = { { - .procname = "route", - .maxlen = 0, - .mode = 0555, - .child = ipv6_route_table_template - }, - { - .procname = "icmp", - .maxlen = 0, - .mode = 0555, - .child = ipv6_icmp_table_template - }, - { .procname = "bindv6only", .data = &init_net.ipv6.sysctl.bindv6only, .maxlen = sizeof(int), @@ -62,13 +38,6 @@ static ctl_table ipv6_rotable[] = { { } }; -struct ctl_path net_ipv6_ctl_path[] = { - { .procname = "net", }, - { .procname = "ipv6", }, - { }, -}; -EXPORT_SYMBOL_GPL(net_ipv6_ctl_path); - static int __net_init ipv6_sysctl_net_init(struct net *net) { struct ctl_table *ipv6_table; @@ -81,28 +50,37 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) GFP_KERNEL); if (!ipv6_table) goto out; + ipv6_table[0].data = &net->ipv6.sysctl.bindv6only; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) goto out_ipv6_table; - ipv6_table[0].child = ipv6_route_table; ipv6_icmp_table = ipv6_icmp_sysctl_init(net); if (!ipv6_icmp_table) goto out_ipv6_route_table; - ipv6_table[1].child = ipv6_icmp_table; - ipv6_table[2].data = &net->ipv6.sysctl.bindv6only; - - net->ipv6.sysctl.table = register_net_sysctl_table(net, net_ipv6_ctl_path, - ipv6_table); - if (!net->ipv6.sysctl.table) + net->ipv6.sysctl.hdr = register_net_sysctl(net, "net/ipv6", ipv6_table); + if (!net->ipv6.sysctl.hdr) goto out_ipv6_icmp_table; + net->ipv6.sysctl.route_hdr = + register_net_sysctl(net, "net/ipv6/route", ipv6_route_table); + if (!net->ipv6.sysctl.route_hdr) + goto out_unregister_ipv6_table; + + net->ipv6.sysctl.icmp_hdr = + register_net_sysctl(net, "net/ipv6/icmp", ipv6_icmp_table); + if (!net->ipv6.sysctl.icmp_hdr) + goto out_unregister_route_table; + err = 0; out: return err; - +out_unregister_route_table: + unregister_net_sysctl_table(net->ipv6.sysctl.route_hdr); +out_unregister_ipv6_table: + unregister_net_sysctl_table(net->ipv6.sysctl.hdr); out_ipv6_icmp_table: kfree(ipv6_icmp_table); out_ipv6_route_table: @@ -118,11 +96,13 @@ static void __net_exit ipv6_sysctl_net_exit(struct net *net) struct ctl_table *ipv6_route_table; struct ctl_table *ipv6_icmp_table; - ipv6_table = net->ipv6.sysctl.table->ctl_table_arg; - ipv6_route_table = ipv6_table[0].child; - ipv6_icmp_table = ipv6_table[1].child; + ipv6_table = net->ipv6.sysctl.hdr->ctl_table_arg; + ipv6_route_table = net->ipv6.sysctl.route_hdr->ctl_table_arg; + ipv6_icmp_table = net->ipv6.sysctl.icmp_hdr->ctl_table_arg; - unregister_net_sysctl_table(net->ipv6.sysctl.table); + unregister_net_sysctl_table(net->ipv6.sysctl.icmp_hdr); + unregister_net_sysctl_table(net->ipv6.sysctl.route_hdr); + unregister_net_sysctl_table(net->ipv6.sysctl.hdr); kfree(ipv6_table); kfree(ipv6_route_table); @@ -140,7 +120,7 @@ int ipv6_sysctl_register(void) { int err = -ENOMEM; - ip6_header = register_net_sysctl_rotable(net_ipv6_ctl_path, ipv6_rotable); + ip6_header = register_net_sysctl(&init_net, "net/ipv6", ipv6_rotable); if (ip6_header == NULL) goto out; @@ -160,18 +140,3 @@ void ipv6_sysctl_unregister(void) unregister_net_sysctl_table(ip6_header); unregister_pernet_subsys(&ipv6_sysctl_net_ops); } - -static struct ctl_table_header *ip6_base; - -int ipv6_static_sysctl_register(void) -{ - ip6_base = register_sysctl_paths(net_ipv6_ctl_path, ipv6_static_skeleton); - if (ip6_base == NULL) - return -ENOMEM; - return 0; -} - -void ipv6_static_sysctl_unregister(void) -{ - unregister_net_sysctl_table(ip6_base); -} diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 12c6ece67f3..554d5999abc 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -723,12 +723,10 @@ static int tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) NULL, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { - if (net_ratelimit()) { - printk(KERN_INFO "MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u\n", - genhash ? "failed" : "mismatch", - &ip6h->saddr, ntohs(th->source), - &ip6h->daddr, ntohs(th->dest)); - } + net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u\n", + genhash ? "failed" : "mismatch", + &ip6h->saddr, ntohs(th->source), + &ip6h->daddr, ntohs(th->dest)); return 1; } return 0; @@ -1057,7 +1055,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); __u32 isn = TCP_SKB_CB(skb)->when; struct dst_entry *dst = NULL; - int want_cookie = 0; + bool want_cookie = false; if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_conn_request(sk, skb); @@ -1118,7 +1116,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) while (l-- > 0) *c++ ^= *hash_location++; - want_cookie = 0; /* not our kind of cookie */ + want_cookie = false; /* not our kind of cookie */ tmp_ext.cookie_out_never = 0; /* false */ tmp_ext.cookie_plus = tmp_opt.cookie_plus; } else if (!tp->rx_opt.cookie_in_always) { @@ -1140,7 +1138,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) treq->rmt_addr = ipv6_hdr(skb)->saddr; treq->loc_addr = ipv6_hdr(skb)->daddr; if (!want_cookie || tmp_opt.tstamp_ok) - TCP_ECN_create_request(req, tcp_hdr(skb)); + TCP_ECN_create_request(req, skb); treq->iif = sk->sk_bound_dev_if; @@ -1353,7 +1351,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newnp->pktoptions = NULL; if (treq->pktopts != NULL) { newnp->pktoptions = skb_clone(treq->pktopts, GFP_ATOMIC); - kfree_skb(treq->pktopts); + consume_skb(treq->pktopts); treq->pktopts = NULL; if (newnp->pktoptions) skb_set_owner_r(newnp->pktoptions, newsk); @@ -1383,6 +1381,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, tcp_mtup_init(newsk); tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = dst_metric_advmss(dst); + if (tcp_sk(sk)->rx_opt.user_mss && + tcp_sk(sk)->rx_opt.user_mss < newtp->advmss) + newtp->advmss = tcp_sk(sk)->rx_opt.user_mss; + tcp_initialize_rcv_mss(newsk); if (tcp_rsk(req)->snt_synack) tcp_valid_rtt_meas(newsk, @@ -1645,7 +1647,7 @@ process: #ifdef CONFIG_NET_DMA struct tcp_sock *tp = tcp_sk(sk); if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY); + tp->ucopy.dma_chan = net_dma_find_channel(); if (tp->ucopy.dma_chan) ret = tcp_v6_do_rcv(sk, skb); else @@ -1654,7 +1656,8 @@ process: if (!tcp_prequeue(sk, skb)) ret = tcp_v6_do_rcv(sk, skb); } - } else if (unlikely(sk_add_backlog(sk, skb))) { + } else if (unlikely(sk_add_backlog(sk, skb, + sk->sk_rcvbuf + sk->sk_sndbuf))) { bh_unlock_sock(sk); NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP); goto discard_and_relse; @@ -1773,6 +1776,7 @@ static const struct inet_connection_sock_af_ops ipv6_specific = { .syn_recv_sock = tcp_v6_syn_recv_sock, .get_peer = tcp_v6_get_peer, .net_header_len = sizeof(struct ipv6hdr), + .net_frag_header_len = sizeof(struct frag_hdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .addr2sockaddr = inet6_csk_addr2sockaddr, @@ -1829,64 +1833,15 @@ static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = { static int tcp_v6_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_sock *tp = tcp_sk(sk); - - skb_queue_head_init(&tp->out_of_order_queue); - tcp_init_xmit_timers(sk); - tcp_prequeue_init(tp); - - icsk->icsk_rto = TCP_TIMEOUT_INIT; - tp->mdev = TCP_TIMEOUT_INIT; - - /* So many TCP implementations out there (incorrectly) count the - * initial SYN frame in their delayed-ACK and congestion control - * algorithms that we must have the following bandaid to talk - * efficiently to them. -DaveM - */ - tp->snd_cwnd = 2; - /* See draft-stevens-tcpca-spec-01 for discussion of the - * initialization of these values. - */ - tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; - tp->snd_cwnd_clamp = ~0; - tp->mss_cache = TCP_MSS_DEFAULT; - - tp->reordering = sysctl_tcp_reordering; - - sk->sk_state = TCP_CLOSE; + tcp_init_sock(sk); icsk->icsk_af_ops = &ipv6_specific; - icsk->icsk_ca_ops = &tcp_init_congestion_ops; - icsk->icsk_sync_mss = tcp_sync_mss; - sk->sk_write_space = sk_stream_write_space; - sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); #ifdef CONFIG_TCP_MD5SIG - tp->af_specific = &tcp_sock_ipv6_specific; + tcp_sk(sk)->af_specific = &tcp_sock_ipv6_specific; #endif - /* TCP Cookie Transactions */ - if (sysctl_tcp_cookie_size > 0) { - /* Default, cookies without s_data_payload. */ - tp->cookie_values = - kzalloc(sizeof(*tp->cookie_values), - sk->sk_allocation); - if (tp->cookie_values != NULL) - kref_init(&tp->cookie_values->kref); - } - /* Presumed zeroed, in order of appearance: - * cookie_in_always, cookie_out_never, - * s_data_constant, s_data_in, s_data_out - */ - sk->sk_sndbuf = sysctl_tcp_wmem[1]; - sk->sk_rcvbuf = sysctl_tcp_rmem[1]; - - local_bh_disable(); - sock_update_memcg(sk); - sk_sockets_allocated_inc(sk); - local_bh_enable(); - return 0; } diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c index 4f3cec12aa8..4b0f50d9a96 100644 --- a/net/ipv6/tunnel6.c +++ b/net/ipv6/tunnel6.c @@ -19,6 +19,8 @@ * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> */ +#define pr_fmt(fmt) "IPv6: " fmt + #include <linux/icmpv6.h> #include <linux/init.h> #include <linux/module.h> @@ -160,11 +162,11 @@ static const struct inet6_protocol tunnel46_protocol = { static int __init tunnel6_init(void) { if (inet6_add_protocol(&tunnel6_protocol, IPPROTO_IPV6)) { - printk(KERN_ERR "tunnel6 init(): can't add protocol\n"); + pr_err("%s: can't add protocol\n", __func__); return -EAGAIN; } if (inet6_add_protocol(&tunnel46_protocol, IPPROTO_IPIP)) { - printk(KERN_ERR "tunnel6 init(): can't add protocol\n"); + pr_err("%s: can't add protocol\n", __func__); inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6); return -EAGAIN; } @@ -174,9 +176,9 @@ static int __init tunnel6_init(void) static void __exit tunnel6_fini(void) { if (inet6_del_protocol(&tunnel46_protocol, IPPROTO_IPIP)) - printk(KERN_ERR "tunnel6 close: can't remove protocol\n"); + pr_err("%s: can't remove protocol\n", __func__); if (inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6)) - printk(KERN_ERR "tunnel6 close: can't remove protocol\n"); + pr_err("%s: can't remove protocol\n", __func__); } module_init(tunnel6_init); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 37b0699e95e..f05099fc590 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -103,7 +103,7 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum) { unsigned int hash2_nulladdr = udp6_portaddr_hash(sock_net(sk), &in6addr_any, snum); - unsigned int hash2_partial = + unsigned int hash2_partial = udp6_portaddr_hash(sock_net(sk), &inet6_sk(sk)->rcv_saddr, 0); /* precompute partial secondary hash */ @@ -349,7 +349,7 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, bool slow; if (addr_len) - *addr_len=sizeof(struct sockaddr_in6); + *addr_len = sizeof(struct sockaddr_in6); if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len); @@ -496,6 +496,28 @@ out: sock_put(sk); } +static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + int rc; + + if (!ipv6_addr_any(&inet6_sk(sk)->daddr)) + sock_rps_save_rxhash(sk, skb); + + rc = sock_queue_rcv_skb(sk, skb); + if (rc < 0) { + int is_udplite = IS_UDPLITE(sk); + + /* Note that an ENOMEM error is charged twice */ + if (rc == -ENOMEM) + UDP6_INC_STATS_BH(sock_net(sk), + UDP_MIB_RCVBUFERRORS, is_udplite); + UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + kfree_skb(skb); + return -1; + } + return 0; +} + static __inline__ void udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info ) @@ -503,18 +525,54 @@ static __inline__ void udpv6_err(struct sk_buff *skb, __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table); } -int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) +static struct static_key udpv6_encap_needed __read_mostly; +void udpv6_encap_enable(void) +{ + if (!static_key_enabled(&udpv6_encap_needed)) + static_key_slow_inc(&udpv6_encap_needed); +} +EXPORT_SYMBOL(udpv6_encap_enable); + +int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { struct udp_sock *up = udp_sk(sk); int rc; int is_udplite = IS_UDPLITE(sk); - if (!ipv6_addr_any(&inet6_sk(sk)->daddr)) - sock_rps_save_rxhash(sk, skb); - if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto drop; + if (static_key_false(&udpv6_encap_needed) && up->encap_type) { + int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); + + /* + * This is an encapsulation socket so pass the skb to + * the socket's udp_encap_rcv() hook. Otherwise, just + * fall through and pass this up the UDP socket. + * up->encap_rcv() returns the following value: + * =0 if skb was successfully passed to the encap + * handler or was discarded by it. + * >0 if skb should be passed on to UDP. + * <0 if skb should be resubmitted as proto -N + */ + + /* if we're overly short, let UDP handle it */ + encap_rcv = ACCESS_ONCE(up->encap_rcv); + if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) { + int ret; + + ret = encap_rcv(sk, skb); + if (ret <= 0) { + UDP_INC_STATS_BH(sock_net(sk), + UDP_MIB_INDATAGRAMS, + is_udplite); + return -ret; + } + } + + /* FALLTHROUGH -- it's a UDP Packet */ + } + /* * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c). */ @@ -539,21 +597,25 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) goto drop; } + if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) + goto drop; + skb_dst_drop(skb); - rc = sock_queue_rcv_skb(sk, skb); - if (rc < 0) { - /* Note that an ENOMEM error is charged twice */ - if (rc == -ENOMEM) - UDP6_INC_STATS_BH(sock_net(sk), - UDP_MIB_RCVBUFERRORS, is_udplite); - goto drop_no_sk_drops_inc; + + bh_lock_sock(sk); + rc = 0; + if (!sock_owned_by_user(sk)) + rc = __udpv6_queue_rcv_skb(sk, skb); + else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) { + bh_unlock_sock(sk); + goto drop; } + bh_unlock_sock(sk); - return 0; + return rc; drop: - atomic_inc(&sk->sk_drops); -drop_no_sk_drops_inc: UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + atomic_inc(&sk->sk_drops); kfree_skb(skb); return -1; } @@ -602,37 +664,27 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, static void flush_stack(struct sock **stack, unsigned int count, struct sk_buff *skb, unsigned int final) { - unsigned int i; + struct sk_buff *skb1 = NULL; struct sock *sk; - struct sk_buff *skb1; + unsigned int i; for (i = 0; i < count; i++) { - skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC); - sk = stack[i]; - if (skb1) { - if (sk_rcvqueues_full(sk, skb1)) { - kfree_skb(skb1); - goto drop; - } - bh_lock_sock(sk); - if (!sock_owned_by_user(sk)) - udpv6_queue_rcv_skb(sk, skb1); - else if (sk_add_backlog(sk, skb1)) { - kfree_skb(skb1); - bh_unlock_sock(sk); - goto drop; - } - bh_unlock_sock(sk); - continue; + if (likely(skb1 == NULL)) + skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC); + if (!skb1) { + atomic_inc(&sk->sk_drops); + UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, + IS_UDPLITE(sk)); + UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, + IS_UDPLITE(sk)); } -drop: - atomic_inc(&sk->sk_drops); - UDP6_INC_STATS_BH(sock_net(sk), - UDP_MIB_RCVBUFERRORS, IS_UDPLITE(sk)); - UDP6_INC_STATS_BH(sock_net(sk), - UDP_MIB_INERRORS, IS_UDPLITE(sk)); + + if (skb1 && udpv6_queue_rcv_skb(sk, skb1) <= 0) + skb1 = NULL; } + if (unlikely(skb1)) + kfree_skb(skb1); } /* * Note: called only from the BH handler context, @@ -772,39 +824,29 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, * for sock caches... i'll skip this for now. */ sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable); + if (sk != NULL) { + int ret = udpv6_queue_rcv_skb(sk, skb); + sock_put(sk); - if (sk == NULL) { - if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) - goto discard; - - if (udp_lib_checksum_complete(skb)) - goto discard; - UDP6_INC_STATS_BH(net, UDP_MIB_NOPORTS, - proto == IPPROTO_UDPLITE); - - icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); + /* a return value > 0 means to resubmit the input, but + * it wants the return to be -protocol, or 0 + */ + if (ret > 0) + return -ret; - kfree_skb(skb); return 0; } - /* deliver */ - - if (sk_rcvqueues_full(sk, skb)) { - sock_put(sk); + if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard; - } - bh_lock_sock(sk); - if (!sock_owned_by_user(sk)) - udpv6_queue_rcv_skb(sk, skb); - else if (sk_add_backlog(sk, skb)) { - atomic_inc(&sk->sk_drops); - bh_unlock_sock(sk); - sock_put(sk); + + if (udp_lib_checksum_complete(skb)) goto discard; - } - bh_unlock_sock(sk); - sock_put(sk); + + UDP6_INC_STATS_BH(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); + + kfree_skb(skb); return 0; short_packet: @@ -1337,7 +1379,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, * do checksum of UDP packets sent as multiple IP fragments. */ offset = skb_checksum_start_offset(skb); - csum = skb_checksum(skb, offset, skb->len- offset, 0); + csum = skb_checksum(skb, offset, skb->len - offset, 0); offset += skb->csum_offset; *(__sum16 *)(skb->data + offset) = csum_fold(csum); skb->ip_summed = CHECKSUM_NONE; @@ -1471,7 +1513,7 @@ struct proto udpv6_prot = { .getsockopt = udpv6_getsockopt, .sendmsg = udpv6_sendmsg, .recvmsg = udpv6_recvmsg, - .backlog_rcv = udpv6_queue_rcv_skb, + .backlog_rcv = __udpv6_queue_rcv_skb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, .rehash = udp_v6_rehash, diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 8ea65e03273..8625fba96db 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -334,8 +334,8 @@ int __init xfrm6_init(void) goto out_policy; #ifdef CONFIG_SYSCTL - sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv6_ctl_path, - xfrm6_policy_table); + sysctl_hdr = register_net_sysctl(&init_net, "net/ipv6", + xfrm6_policy_table); #endif out: return ret; diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 4fe1db12d2a..ee5a7065aac 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -68,9 +68,9 @@ static DEFINE_SPINLOCK(xfrm6_tunnel_spi_lock); static struct kmem_cache *xfrm6_tunnel_spi_kmem __read_mostly; -static inline unsigned xfrm6_tunnel_spi_hash_byaddr(const xfrm_address_t *addr) +static inline unsigned int xfrm6_tunnel_spi_hash_byaddr(const xfrm_address_t *addr) { - unsigned h; + unsigned int h; h = (__force u32)(addr->a6[0] ^ addr->a6[1] ^ addr->a6[2] ^ addr->a6[3]); h ^= h >> 16; @@ -80,7 +80,7 @@ static inline unsigned xfrm6_tunnel_spi_hash_byaddr(const xfrm_address_t *addr) return h; } -static inline unsigned xfrm6_tunnel_spi_hash_byspi(u32 spi) +static inline unsigned int xfrm6_tunnel_spi_hash_byspi(u32 spi) { return spi % XFRM6_TUNNEL_SPI_BYSPI_HSIZE; } diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index 9680226640e..dfd6faaf0ea 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -983,10 +983,6 @@ static int ipxitf_create(struct ipx_interface_definition *idef) goto out; switch (idef->ipx_dlink_type) { - case IPX_FRAME_TR_8022: - printk(KERN_WARNING "IPX frame type 802.2TR is " - "obsolete Use 802.2 instead.\n"); - /* fall through */ case IPX_FRAME_8022: dlink_type = htons(ETH_P_802_2); datalink = p8022_datalink; @@ -996,10 +992,7 @@ static int ipxitf_create(struct ipx_interface_definition *idef) dlink_type = htons(ETH_P_IPX); datalink = pEII_datalink; break; - } else - printk(KERN_WARNING "IPX frame type EtherII over " - "token-ring is obsolete. Use SNAP " - "instead.\n"); + } /* fall through */ case IPX_FRAME_SNAP: dlink_type = htons(ETH_P_SNAP); @@ -1275,7 +1268,6 @@ const char *ipx_frame_name(__be16 frame) case ETH_P_802_2: rc = "802.2"; break; case ETH_P_SNAP: rc = "SNAP"; break; case ETH_P_802_3: rc = "802.3"; break; - case ETH_P_TR_802_2: rc = "802.2TR"; break; } return rc; @@ -1909,9 +1901,7 @@ static int ipx_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) (const unsigned short __user *)argp); break; case SIOCGSTAMP: - rc = -EINVAL; - if (sk) - rc = sock_get_timestamp(sk, argp); + rc = sock_get_timestamp(sk, argp); break; case SIOCGIFDSTADDR: case SIOCSIFDSTADDR: diff --git a/net/ipx/sysctl_net_ipx.c b/net/ipx/sysctl_net_ipx.c index bd6dca00fb8..ad7c03dedaa 100644 --- a/net/ipx/sysctl_net_ipx.c +++ b/net/ipx/sysctl_net_ipx.c @@ -8,6 +8,7 @@ #include <linux/mm.h> #include <linux/sysctl.h> +#include <net/net_namespace.h> #ifndef CONFIG_SYSCTL #error This file should not be compiled without CONFIG_SYSCTL defined @@ -27,20 +28,14 @@ static struct ctl_table ipx_table[] = { { }, }; -static struct ctl_path ipx_path[] = { - { .procname = "net", }, - { .procname = "ipx", }, - { } -}; - static struct ctl_table_header *ipx_table_header; void ipx_register_sysctl(void) { - ipx_table_header = register_sysctl_paths(ipx_path, ipx_table); + ipx_table_header = register_net_sysctl(&init_net, "net/ipx", ipx_table); } void ipx_unregister_sysctl(void) { - unregister_sysctl_table(ipx_table_header); + unregister_net_sysctl_table(ipx_table_header); } diff --git a/net/irda/ircomm/ircomm_tty_ioctl.c b/net/irda/ircomm/ircomm_tty_ioctl.c index 77c5e6499f8..d0667d68351 100644 --- a/net/irda/ircomm/ircomm_tty_ioctl.c +++ b/net/irda/ircomm/ircomm_tty_ioctl.c @@ -54,7 +54,7 @@ */ static void ircomm_tty_change_speed(struct ircomm_tty_cb *self) { - unsigned cflag, cval; + unsigned int cflag, cval; int baud; IRDA_DEBUG(2, "%s()\n", __func__ ); diff --git a/net/irda/irsysctl.c b/net/irda/irsysctl.c index 2615ffc8e78..de73f6496db 100644 --- a/net/irda/irsysctl.c +++ b/net/irda/irsysctl.c @@ -235,12 +235,6 @@ static ctl_table irda_table[] = { { } }; -static struct ctl_path irda_path[] = { - { .procname = "net", }, - { .procname = "irda", }, - { } -}; - static struct ctl_table_header *irda_table_header; /* @@ -251,7 +245,7 @@ static struct ctl_table_header *irda_table_header; */ int __init irda_sysctl_register(void) { - irda_table_header = register_sysctl_paths(irda_path, irda_table); + irda_table_header = register_net_sysctl(&init_net, "net/irda", irda_table); if (!irda_table_header) return -ENOMEM; @@ -266,7 +260,7 @@ int __init irda_sysctl_register(void) */ void irda_sysctl_unregister(void) { - unregister_sysctl_table(irda_table_header); + unregister_net_sysctl_table(irda_table_header); } diff --git a/net/key/af_key.c b/net/key/af_key.c index 11dbb2255cc..34e418508a6 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1714,7 +1714,7 @@ static int key_notify_sa_flush(const struct km_event *c) static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); - unsigned proto; + unsigned int proto; struct km_event c; struct xfrm_audit audit_info; int err, err2; @@ -3480,7 +3480,7 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, /* Addresses to be used by KM for negotiation, if ext is available */ if (k != NULL && (set_sadb_kmaddress(skb, k) < 0)) - return -EINVAL; + goto err; /* selector src */ set_sadb_address(skb, sasize_sel, SADB_EXT_ADDRESS_SRC, sel); @@ -3547,7 +3547,7 @@ static int pfkey_sendmsg(struct kiocb *kiocb, goto out; err = -EMSGSIZE; - if ((unsigned)len > sk->sk_sndbuf - 32) + if ((unsigned int)len > sk->sk_sndbuf - 32) goto out; err = -ENOBUFS; diff --git a/net/l2tp/Makefile b/net/l2tp/Makefile index 110e7bc2de5..2870f41ea44 100644 --- a/net/l2tp/Makefile +++ b/net/l2tp/Makefile @@ -10,3 +10,6 @@ obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_IP)) += l2tp_ip.o obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_V3)) += l2tp_netlink.o obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_ETH)) += l2tp_eth.o obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_DEBUGFS)) += l2tp_debugfs.o +ifneq ($(CONFIG_IPV6),) +obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_IP)) += l2tp_ip6.o +endif diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 89ff8c67943..32b2155e7ab 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -18,6 +18,8 @@ * published by the Free Software Foundation. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/string.h> #include <linux/list.h> @@ -53,6 +55,10 @@ #include <net/inet_common.h> #include <net/xfrm.h> #include <net/protocol.h> +#include <net/inet6_connection_sock.h> +#include <net/inet_ecn.h> +#include <net/ip6_route.h> +#include <net/ip6_checksum.h> #include <asm/byteorder.h> #include <linux/atomic.h> @@ -82,12 +88,6 @@ /* Default trace flags */ #define L2TP_DEFAULT_DEBUG_FLAGS 0 -#define PRINTK(_mask, _type, _lvl, _fmt, args...) \ - do { \ - if ((_mask) & (_type)) \ - printk(_lvl "L2TP: " _fmt, ##args); \ - } while (0) - /* Private data stored for received packets in the skb. */ struct l2tp_skb_cb { @@ -137,14 +137,20 @@ static inline void l2tp_tunnel_dec_refcount_1(struct l2tp_tunnel *tunnel) l2tp_tunnel_free(tunnel); } #ifdef L2TP_REFCNT_DEBUG -#define l2tp_tunnel_inc_refcount(_t) do { \ - printk(KERN_DEBUG "l2tp_tunnel_inc_refcount: %s:%d %s: cnt=%d\n", __func__, __LINE__, (_t)->name, atomic_read(&_t->ref_count)); \ - l2tp_tunnel_inc_refcount_1(_t); \ - } while (0) -#define l2tp_tunnel_dec_refcount(_t) do { \ - printk(KERN_DEBUG "l2tp_tunnel_dec_refcount: %s:%d %s: cnt=%d\n", __func__, __LINE__, (_t)->name, atomic_read(&_t->ref_count)); \ - l2tp_tunnel_dec_refcount_1(_t); \ - } while (0) +#define l2tp_tunnel_inc_refcount(_t) \ +do { \ + pr_debug("l2tp_tunnel_inc_refcount: %s:%d %s: cnt=%d\n", \ + __func__, __LINE__, (_t)->name, \ + atomic_read(&_t->ref_count)); \ + l2tp_tunnel_inc_refcount_1(_t); \ +} while (0) +#define l2tp_tunnel_dec_refcount(_t) +do { \ + pr_debug("l2tp_tunnel_dec_refcount: %s:%d %s: cnt=%d\n", \ + __func__, __LINE__, (_t)->name, \ + atomic_read(&_t->ref_count)); \ + l2tp_tunnel_dec_refcount_1(_t); \ +} while (0) #else #define l2tp_tunnel_inc_refcount(t) l2tp_tunnel_inc_refcount_1(t) #define l2tp_tunnel_dec_refcount(t) l2tp_tunnel_dec_refcount_1(t) @@ -326,16 +332,20 @@ static void l2tp_recv_queue_skb(struct l2tp_session *session, struct sk_buff *sk struct sk_buff *skbp; struct sk_buff *tmp; u32 ns = L2TP_SKB_CB(skb)->ns; + struct l2tp_stats *sstats; spin_lock_bh(&session->reorder_q.lock); + sstats = &session->stats; skb_queue_walk_safe(&session->reorder_q, skbp, tmp) { if (L2TP_SKB_CB(skbp)->ns > ns) { __skb_queue_before(&session->reorder_q, skbp, skb); - PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG, - "%s: pkt %hu, inserted before %hu, reorder_q len=%d\n", - session->name, ns, L2TP_SKB_CB(skbp)->ns, - skb_queue_len(&session->reorder_q)); - session->stats.rx_oos_packets++; + l2tp_dbg(session, L2TP_MSG_SEQ, + "%s: pkt %hu, inserted before %hu, reorder_q len=%d\n", + session->name, ns, L2TP_SKB_CB(skbp)->ns, + skb_queue_len(&session->reorder_q)); + u64_stats_update_begin(&sstats->syncp); + sstats->rx_oos_packets++; + u64_stats_update_end(&sstats->syncp); goto out; } } @@ -352,16 +362,23 @@ static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff * { struct l2tp_tunnel *tunnel = session->tunnel; int length = L2TP_SKB_CB(skb)->length; + struct l2tp_stats *tstats, *sstats; /* We're about to requeue the skb, so return resources * to its current owner (a socket receive buffer). */ skb_orphan(skb); - tunnel->stats.rx_packets++; - tunnel->stats.rx_bytes += length; - session->stats.rx_packets++; - session->stats.rx_bytes += length; + tstats = &tunnel->stats; + u64_stats_update_begin(&tstats->syncp); + sstats = &session->stats; + u64_stats_update_begin(&sstats->syncp); + tstats->rx_packets++; + tstats->rx_bytes += length; + sstats->rx_packets++; + sstats->rx_bytes += length; + u64_stats_update_end(&tstats->syncp); + u64_stats_update_end(&sstats->syncp); if (L2TP_SKB_CB(skb)->has_seq) { /* Bump our Nr */ @@ -371,8 +388,8 @@ static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff * else session->nr &= 0xffffff; - PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG, - "%s: updated nr to %hu\n", session->name, session->nr); + l2tp_dbg(session, L2TP_MSG_SEQ, "%s: updated nr to %hu\n", + session->name, session->nr); } /* call private receive handler */ @@ -392,6 +409,7 @@ static void l2tp_recv_dequeue(struct l2tp_session *session) { struct sk_buff *skb; struct sk_buff *tmp; + struct l2tp_stats *sstats; /* If the pkt at the head of the queue has the nr that we * expect to send up next, dequeue it and any other @@ -399,16 +417,19 @@ static void l2tp_recv_dequeue(struct l2tp_session *session) */ start: spin_lock_bh(&session->reorder_q.lock); + sstats = &session->stats; skb_queue_walk_safe(&session->reorder_q, skb, tmp) { if (time_after(jiffies, L2TP_SKB_CB(skb)->expires)) { - session->stats.rx_seq_discards++; - session->stats.rx_errors++; - PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG, - "%s: oos pkt %u len %d discarded (too old), " - "waiting for %u, reorder_q_len=%d\n", - session->name, L2TP_SKB_CB(skb)->ns, - L2TP_SKB_CB(skb)->length, session->nr, - skb_queue_len(&session->reorder_q)); + u64_stats_update_begin(&sstats->syncp); + sstats->rx_seq_discards++; + sstats->rx_errors++; + u64_stats_update_end(&sstats->syncp); + l2tp_dbg(session, L2TP_MSG_SEQ, + "%s: oos pkt %u len %d discarded (too old), waiting for %u, reorder_q_len=%d\n", + session->name, L2TP_SKB_CB(skb)->ns, + L2TP_SKB_CB(skb)->length, session->nr, + skb_queue_len(&session->reorder_q)); + session->reorder_skip = 1; __skb_unlink(skb, &session->reorder_q); kfree_skb(skb); if (session->deref) @@ -417,13 +438,20 @@ start: } if (L2TP_SKB_CB(skb)->has_seq) { + if (session->reorder_skip) { + l2tp_dbg(session, L2TP_MSG_SEQ, + "%s: advancing nr to next pkt: %u -> %u", + session->name, session->nr, + L2TP_SKB_CB(skb)->ns); + session->reorder_skip = 0; + session->nr = L2TP_SKB_CB(skb)->ns; + } if (L2TP_SKB_CB(skb)->ns != session->nr) { - PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG, - "%s: holding oos pkt %u len %d, " - "waiting for %u, reorder_q_len=%d\n", - session->name, L2TP_SKB_CB(skb)->ns, - L2TP_SKB_CB(skb)->length, session->nr, - skb_queue_len(&session->reorder_q)); + l2tp_dbg(session, L2TP_MSG_SEQ, + "%s: holding oos pkt %u len %d, waiting for %u, reorder_q_len=%d\n", + session->name, L2TP_SKB_CB(skb)->ns, + L2TP_SKB_CB(skb)->length, session->nr, + skb_queue_len(&session->reorder_q)); goto out; } } @@ -446,21 +474,43 @@ static inline int l2tp_verify_udp_checksum(struct sock *sk, { struct udphdr *uh = udp_hdr(skb); u16 ulen = ntohs(uh->len); - struct inet_sock *inet; __wsum psum; - if (sk->sk_no_check || skb_csum_unnecessary(skb) || !uh->check) + if (sk->sk_no_check || skb_csum_unnecessary(skb)) return 0; - inet = inet_sk(sk); - psum = csum_tcpudp_nofold(inet->inet_saddr, inet->inet_daddr, ulen, - IPPROTO_UDP, 0); - - if ((skb->ip_summed == CHECKSUM_COMPLETE) && - !csum_fold(csum_add(psum, skb->csum))) - return 0; - - skb->csum = psum; +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == PF_INET6) { + if (!uh->check) { + LIMIT_NETDEBUG(KERN_INFO "L2TP: IPv6: checksum is 0\n"); + return 1; + } + if ((skb->ip_summed == CHECKSUM_COMPLETE) && + !csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, ulen, + IPPROTO_UDP, skb->csum)) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + return 0; + } + skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len, IPPROTO_UDP, + 0)); + } else +#endif + { + struct inet_sock *inet; + if (!uh->check) + return 0; + inet = inet_sk(sk); + psum = csum_tcpudp_nofold(inet->inet_saddr, inet->inet_daddr, + ulen, IPPROTO_UDP, 0); + + if ((skb->ip_summed == CHECKSUM_COMPLETE) && + !csum_fold(csum_add(psum, skb->csum))) + return 0; + skb->csum = psum; + } return __skb_checksum_complete(skb); } @@ -532,6 +582,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, struct l2tp_tunnel *tunnel = session->tunnel; int offset; u32 ns, nr; + struct l2tp_stats *sstats = &session->stats; /* The ref count is increased since we now hold a pointer to * the session. Take care to decrement the refcnt when exiting @@ -544,10 +595,13 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, /* Parse and check optional cookie */ if (session->peer_cookie_len > 0) { if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) { - PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_INFO, - "%s: cookie mismatch (%u/%u). Discarding.\n", - tunnel->name, tunnel->tunnel_id, session->session_id); - session->stats.rx_cookie_discards++; + l2tp_info(tunnel, L2TP_MSG_DATA, + "%s: cookie mismatch (%u/%u). Discarding.\n", + tunnel->name, tunnel->tunnel_id, + session->session_id); + u64_stats_update_begin(&sstats->syncp); + sstats->rx_cookie_discards++; + u64_stats_update_end(&sstats->syncp); goto discard; } ptr += session->peer_cookie_len; @@ -573,9 +627,9 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, L2TP_SKB_CB(skb)->ns = ns; L2TP_SKB_CB(skb)->has_seq = 1; - PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG, - "%s: recv data ns=%u, nr=%u, session nr=%u\n", - session->name, ns, nr, session->nr); + l2tp_dbg(session, L2TP_MSG_SEQ, + "%s: recv data ns=%u, nr=%u, session nr=%u\n", + session->name, ns, nr, session->nr); } } else if (session->l2specific_type == L2TP_L2SPECTYPE_DEFAULT) { u32 l2h = ntohl(*(__be32 *) ptr); @@ -587,9 +641,9 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, L2TP_SKB_CB(skb)->ns = ns; L2TP_SKB_CB(skb)->has_seq = 1; - PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG, - "%s: recv data ns=%u, session nr=%u\n", - session->name, ns, session->nr); + l2tp_dbg(session, L2TP_MSG_SEQ, + "%s: recv data ns=%u, session nr=%u\n", + session->name, ns, session->nr); } } @@ -602,9 +656,9 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, * configure it so. */ if ((!session->lns_mode) && (!session->send_seq)) { - PRINTK(session->debug, L2TP_MSG_SEQ, KERN_INFO, - "%s: requested to enable seq numbers by LNS\n", - session->name); + l2tp_info(session, L2TP_MSG_SEQ, + "%s: requested to enable seq numbers by LNS\n", + session->name); session->send_seq = -1; l2tp_session_set_header_len(session, tunnel->version); } @@ -613,10 +667,12 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, * If user has configured mandatory sequence numbers, discard. */ if (session->recv_seq) { - PRINTK(session->debug, L2TP_MSG_SEQ, KERN_WARNING, - "%s: recv data has no seq numbers when required. " - "Discarding\n", session->name); - session->stats.rx_seq_discards++; + l2tp_warn(session, L2TP_MSG_SEQ, + "%s: recv data has no seq numbers when required. Discarding.\n", + session->name); + u64_stats_update_begin(&sstats->syncp); + sstats->rx_seq_discards++; + u64_stats_update_end(&sstats->syncp); goto discard; } @@ -626,16 +682,18 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, * LAC is broken. Discard the frame. */ if ((!session->lns_mode) && (session->send_seq)) { - PRINTK(session->debug, L2TP_MSG_SEQ, KERN_INFO, - "%s: requested to disable seq numbers by LNS\n", - session->name); + l2tp_info(session, L2TP_MSG_SEQ, + "%s: requested to disable seq numbers by LNS\n", + session->name); session->send_seq = 0; l2tp_session_set_header_len(session, tunnel->version); } else if (session->send_seq) { - PRINTK(session->debug, L2TP_MSG_SEQ, KERN_WARNING, - "%s: recv data has no seq numbers when required. " - "Discarding\n", session->name); - session->stats.rx_seq_discards++; + l2tp_warn(session, L2TP_MSG_SEQ, + "%s: recv data has no seq numbers when required. Discarding.\n", + session->name); + u64_stats_update_begin(&sstats->syncp); + sstats->rx_seq_discards++; + u64_stats_update_end(&sstats->syncp); goto discard; } } @@ -689,13 +747,14 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, * packets */ if (L2TP_SKB_CB(skb)->ns != session->nr) { - session->stats.rx_seq_discards++; - PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG, - "%s: oos pkt %u len %d discarded, " - "waiting for %u, reorder_q_len=%d\n", - session->name, L2TP_SKB_CB(skb)->ns, - L2TP_SKB_CB(skb)->length, session->nr, - skb_queue_len(&session->reorder_q)); + u64_stats_update_begin(&sstats->syncp); + sstats->rx_seq_discards++; + u64_stats_update_end(&sstats->syncp); + l2tp_dbg(session, L2TP_MSG_SEQ, + "%s: oos pkt %u len %d discarded, waiting for %u, reorder_q_len=%d\n", + session->name, L2TP_SKB_CB(skb)->ns, + L2TP_SKB_CB(skb)->length, session->nr, + skb_queue_len(&session->reorder_q)); goto discard; } skb_queue_tail(&session->reorder_q, skb); @@ -716,7 +775,9 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, return; discard: - session->stats.rx_errors++; + u64_stats_update_begin(&sstats->syncp); + sstats->rx_errors++; + u64_stats_update_end(&sstats->syncp); kfree_skb(skb); if (session->deref) @@ -739,9 +800,9 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, unsigned char *ptr, *optr; u16 hdrflags; u32 tunnel_id, session_id; - int offset; u16 version; int length; + struct l2tp_stats *tstats; if (tunnel->sock && l2tp_verify_udp_checksum(tunnel->sock, skb)) goto discard_bad_csum; @@ -751,8 +812,9 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, /* Short packet? */ if (!pskb_may_pull(skb, L2TP_HDR_SIZE_SEQ)) { - PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_INFO, - "%s: recv short packet (len=%d)\n", tunnel->name, skb->len); + l2tp_info(tunnel, L2TP_MSG_DATA, + "%s: recv short packet (len=%d)\n", + tunnel->name, skb->len); goto error; } @@ -762,14 +824,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, if (!pskb_may_pull(skb, length)) goto error; - printk(KERN_DEBUG "%s: recv: ", tunnel->name); - - offset = 0; - do { - printk(" %02X", skb->data[offset]); - } while (++offset < length); - - printk("\n"); + pr_debug("%s: recv\n", tunnel->name); + print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, skb->data, length); } /* Point to L2TP header */ @@ -781,9 +837,9 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, /* Check protocol version */ version = hdrflags & L2TP_HDR_VER_MASK; if (version != tunnel->version) { - PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_INFO, - "%s: recv protocol version mismatch: got %d expected %d\n", - tunnel->name, version, tunnel->version); + l2tp_info(tunnel, L2TP_MSG_DATA, + "%s: recv protocol version mismatch: got %d expected %d\n", + tunnel->name, version, tunnel->version); goto error; } @@ -792,8 +848,9 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, /* If type is control packet, it is handled by userspace. */ if (hdrflags & L2TP_HDRFLAG_T) { - PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_DEBUG, - "%s: recv control packet, len=%d\n", tunnel->name, length); + l2tp_dbg(tunnel, L2TP_MSG_DATA, + "%s: recv control packet, len=%d\n", + tunnel->name, length); goto error; } @@ -821,9 +878,9 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, session = l2tp_session_find(tunnel->l2tp_net, tunnel, session_id); if (!session || !session->recv_skb) { /* Not found? Pass to userspace to deal with */ - PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_INFO, - "%s: no session found (%u/%u). Passing up.\n", - tunnel->name, tunnel_id, session_id); + l2tp_info(tunnel, L2TP_MSG_DATA, + "%s: no session found (%u/%u). Passing up.\n", + tunnel->name, tunnel_id, session_id); goto error; } @@ -834,7 +891,10 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, discard_bad_csum: LIMIT_NETDEBUG("%s: UDP: bad checksum\n", tunnel->name); UDP_INC_STATS_USER(tunnel->l2tp_net, UDP_MIB_INERRORS, 0); - tunnel->stats.rx_errors++; + tstats = &tunnel->stats; + u64_stats_update_begin(&tstats->syncp); + tstats->rx_errors++; + u64_stats_update_end(&tstats->syncp); kfree_skb(skb); return 0; @@ -860,8 +920,8 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) if (tunnel == NULL) goto pass_up; - PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_DEBUG, - "%s: received %d bytes\n", tunnel->name, skb->len); + l2tp_dbg(tunnel, L2TP_MSG_DATA, "%s: received %d bytes\n", + tunnel->name, skb->len); if (l2tp_udp_recv_core(tunnel, skb, tunnel->recv_payload_hook)) goto pass_up_put; @@ -903,8 +963,8 @@ static int l2tp_build_l2tpv2_header(struct l2tp_session *session, void *buf) *bufp++ = 0; session->ns++; session->ns &= 0xffff; - PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG, - "%s: updated ns to %u\n", session->name, session->ns); + l2tp_dbg(session, L2TP_MSG_SEQ, "%s: updated ns to %u\n", + session->name, session->ns); } return bufp - optr; @@ -940,8 +1000,9 @@ static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf) l2h = 0x40000000 | session->ns; session->ns++; session->ns &= 0xffffff; - PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG, - "%s: updated ns to %u\n", session->name, session->ns); + l2tp_dbg(session, L2TP_MSG_SEQ, + "%s: updated ns to %u\n", + session->name, session->ns); } *((__be32 *) bufp) = htonl(l2h); @@ -960,46 +1021,50 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, struct l2tp_tunnel *tunnel = session->tunnel; unsigned int len = skb->len; int error; + struct l2tp_stats *tstats, *sstats; /* Debug */ if (session->send_seq) - PRINTK(session->debug, L2TP_MSG_DATA, KERN_DEBUG, - "%s: send %Zd bytes, ns=%u\n", session->name, - data_len, session->ns - 1); + l2tp_dbg(session, L2TP_MSG_DATA, "%s: send %Zd bytes, ns=%u\n", + session->name, data_len, session->ns - 1); else - PRINTK(session->debug, L2TP_MSG_DATA, KERN_DEBUG, - "%s: send %Zd bytes\n", session->name, data_len); + l2tp_dbg(session, L2TP_MSG_DATA, "%s: send %Zd bytes\n", + session->name, data_len); if (session->debug & L2TP_MSG_DATA) { - int i; int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0; unsigned char *datap = skb->data + uhlen; - printk(KERN_DEBUG "%s: xmit:", session->name); - for (i = 0; i < (len - uhlen); i++) { - printk(" %02X", *datap++); - if (i == 31) { - printk(" ..."); - break; - } - } - printk("\n"); + pr_debug("%s: xmit\n", session->name); + print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, + datap, min_t(size_t, 32, len - uhlen)); } /* Queue the packet to IP for output */ skb->local_df = 1; - error = ip_queue_xmit(skb, fl); +#if IS_ENABLED(CONFIG_IPV6) + if (skb->sk->sk_family == PF_INET6) + error = inet6_csk_xmit(skb, NULL); + else +#endif + error = ip_queue_xmit(skb, fl); /* Update stats */ + tstats = &tunnel->stats; + u64_stats_update_begin(&tstats->syncp); + sstats = &session->stats; + u64_stats_update_begin(&sstats->syncp); if (error >= 0) { - tunnel->stats.tx_packets++; - tunnel->stats.tx_bytes += len; - session->stats.tx_packets++; - session->stats.tx_bytes += len; + tstats->tx_packets++; + tstats->tx_bytes += len; + sstats->tx_packets++; + sstats->tx_bytes += len; } else { - tunnel->stats.tx_errors++; - session->stats.tx_errors++; + tstats->tx_errors++; + sstats->tx_errors++; } + u64_stats_update_end(&tstats->syncp); + u64_stats_update_end(&sstats->syncp); return 0; } @@ -1021,6 +1086,31 @@ static inline void l2tp_skb_set_owner_w(struct sk_buff *skb, struct sock *sk) skb->destructor = l2tp_sock_wfree; } +#if IS_ENABLED(CONFIG_IPV6) +static void l2tp_xmit_ipv6_csum(struct sock *sk, struct sk_buff *skb, + int udp_len) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct udphdr *uh = udp_hdr(skb); + + if (!skb_dst(skb) || !skb_dst(skb)->dev || + !(skb_dst(skb)->dev->features & NETIF_F_IPV6_CSUM)) { + __wsum csum = skb_checksum(skb, 0, udp_len, 0); + skb->ip_summed = CHECKSUM_UNNECESSARY; + uh->check = csum_ipv6_magic(&np->saddr, &np->daddr, udp_len, + IPPROTO_UDP, csum); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + } else { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + uh->check = ~csum_ipv6_magic(&np->saddr, &np->daddr, + udp_len, IPPROTO_UDP, 0); + } +} +#endif + /* If caller requires the skb to have a ppp header, the header must be * inserted in the skb data before calling this function. */ @@ -1089,6 +1179,11 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len uh->check = 0; /* Calculate UDP checksum if configured to do so */ +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == PF_INET6) + l2tp_xmit_ipv6_csum(sk, skb, udp_len); + else +#endif if (sk->sk_no_check == UDP_CSUM_NOXMIT) skb->ip_summed = CHECKSUM_NONE; else if ((skb_dst(skb) && skb_dst(skb)->dev) && @@ -1141,8 +1236,7 @@ static void l2tp_tunnel_destruct(struct sock *sk) if (tunnel == NULL) goto end; - PRINTK(tunnel->debug, L2TP_MSG_CONTROL, KERN_INFO, - "%s: closing...\n", tunnel->name); + l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing...\n", tunnel->name); /* Close all sessions */ l2tp_tunnel_closeall(tunnel); @@ -1184,8 +1278,8 @@ static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) BUG_ON(tunnel == NULL); - PRINTK(tunnel->debug, L2TP_MSG_CONTROL, KERN_INFO, - "%s: closing all sessions...\n", tunnel->name); + l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing all sessions...\n", + tunnel->name); write_lock_bh(&tunnel->hlist_lock); for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { @@ -1193,8 +1287,8 @@ again: hlist_for_each_safe(walk, tmp, &tunnel->session_hlist[hash]) { session = hlist_entry(walk, struct l2tp_session, hlist); - PRINTK(session->debug, L2TP_MSG_CONTROL, KERN_INFO, - "%s: closing session\n", session->name); + l2tp_info(session, L2TP_MSG_CONTROL, + "%s: closing session\n", session->name); hlist_del_init(&session->hlist); @@ -1247,8 +1341,7 @@ static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) BUG_ON(atomic_read(&tunnel->ref_count) != 0); BUG_ON(tunnel->sock != NULL); - PRINTK(tunnel->debug, L2TP_MSG_CONTROL, KERN_INFO, - "%s: free...\n", tunnel->name); + l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: free...\n", tunnel->name); /* Remove from tunnel list */ spin_lock_bh(&pn->l2tp_tunnel_list_lock); @@ -1268,31 +1361,69 @@ static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2t { int err = -EINVAL; struct sockaddr_in udp_addr; +#if IS_ENABLED(CONFIG_IPV6) + struct sockaddr_in6 udp6_addr; + struct sockaddr_l2tpip6 ip6_addr; +#endif struct sockaddr_l2tpip ip_addr; struct socket *sock = NULL; switch (cfg->encap) { case L2TP_ENCAPTYPE_UDP: - err = sock_create(AF_INET, SOCK_DGRAM, 0, sockp); - if (err < 0) - goto out; +#if IS_ENABLED(CONFIG_IPV6) + if (cfg->local_ip6 && cfg->peer_ip6) { + err = sock_create(AF_INET6, SOCK_DGRAM, 0, sockp); + if (err < 0) + goto out; - sock = *sockp; + sock = *sockp; - memset(&udp_addr, 0, sizeof(udp_addr)); - udp_addr.sin_family = AF_INET; - udp_addr.sin_addr = cfg->local_ip; - udp_addr.sin_port = htons(cfg->local_udp_port); - err = kernel_bind(sock, (struct sockaddr *) &udp_addr, sizeof(udp_addr)); - if (err < 0) - goto out; + memset(&udp6_addr, 0, sizeof(udp6_addr)); + udp6_addr.sin6_family = AF_INET6; + memcpy(&udp6_addr.sin6_addr, cfg->local_ip6, + sizeof(udp6_addr.sin6_addr)); + udp6_addr.sin6_port = htons(cfg->local_udp_port); + err = kernel_bind(sock, (struct sockaddr *) &udp6_addr, + sizeof(udp6_addr)); + if (err < 0) + goto out; - udp_addr.sin_family = AF_INET; - udp_addr.sin_addr = cfg->peer_ip; - udp_addr.sin_port = htons(cfg->peer_udp_port); - err = kernel_connect(sock, (struct sockaddr *) &udp_addr, sizeof(udp_addr), 0); - if (err < 0) - goto out; + udp6_addr.sin6_family = AF_INET6; + memcpy(&udp6_addr.sin6_addr, cfg->peer_ip6, + sizeof(udp6_addr.sin6_addr)); + udp6_addr.sin6_port = htons(cfg->peer_udp_port); + err = kernel_connect(sock, + (struct sockaddr *) &udp6_addr, + sizeof(udp6_addr), 0); + if (err < 0) + goto out; + } else +#endif + { + err = sock_create(AF_INET, SOCK_DGRAM, 0, sockp); + if (err < 0) + goto out; + + sock = *sockp; + + memset(&udp_addr, 0, sizeof(udp_addr)); + udp_addr.sin_family = AF_INET; + udp_addr.sin_addr = cfg->local_ip; + udp_addr.sin_port = htons(cfg->local_udp_port); + err = kernel_bind(sock, (struct sockaddr *) &udp_addr, + sizeof(udp_addr)); + if (err < 0) + goto out; + + udp_addr.sin_family = AF_INET; + udp_addr.sin_addr = cfg->peer_ip; + udp_addr.sin_port = htons(cfg->peer_udp_port); + err = kernel_connect(sock, + (struct sockaddr *) &udp_addr, + sizeof(udp_addr), 0); + if (err < 0) + goto out; + } if (!cfg->use_udp_checksums) sock->sk->sk_no_check = UDP_CSUM_NOXMIT; @@ -1300,27 +1431,61 @@ static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2t break; case L2TP_ENCAPTYPE_IP: - err = sock_create(AF_INET, SOCK_DGRAM, IPPROTO_L2TP, sockp); - if (err < 0) - goto out; +#if IS_ENABLED(CONFIG_IPV6) + if (cfg->local_ip6 && cfg->peer_ip6) { + err = sock_create(AF_INET6, SOCK_DGRAM, IPPROTO_L2TP, + sockp); + if (err < 0) + goto out; - sock = *sockp; + sock = *sockp; - memset(&ip_addr, 0, sizeof(ip_addr)); - ip_addr.l2tp_family = AF_INET; - ip_addr.l2tp_addr = cfg->local_ip; - ip_addr.l2tp_conn_id = tunnel_id; - err = kernel_bind(sock, (struct sockaddr *) &ip_addr, sizeof(ip_addr)); - if (err < 0) - goto out; + memset(&ip6_addr, 0, sizeof(ip6_addr)); + ip6_addr.l2tp_family = AF_INET6; + memcpy(&ip6_addr.l2tp_addr, cfg->local_ip6, + sizeof(ip6_addr.l2tp_addr)); + ip6_addr.l2tp_conn_id = tunnel_id; + err = kernel_bind(sock, (struct sockaddr *) &ip6_addr, + sizeof(ip6_addr)); + if (err < 0) + goto out; - ip_addr.l2tp_family = AF_INET; - ip_addr.l2tp_addr = cfg->peer_ip; - ip_addr.l2tp_conn_id = peer_tunnel_id; - err = kernel_connect(sock, (struct sockaddr *) &ip_addr, sizeof(ip_addr), 0); - if (err < 0) - goto out; + ip6_addr.l2tp_family = AF_INET6; + memcpy(&ip6_addr.l2tp_addr, cfg->peer_ip6, + sizeof(ip6_addr.l2tp_addr)); + ip6_addr.l2tp_conn_id = peer_tunnel_id; + err = kernel_connect(sock, + (struct sockaddr *) &ip6_addr, + sizeof(ip6_addr), 0); + if (err < 0) + goto out; + } else +#endif + { + err = sock_create(AF_INET, SOCK_DGRAM, IPPROTO_L2TP, + sockp); + if (err < 0) + goto out; + + sock = *sockp; + + memset(&ip_addr, 0, sizeof(ip_addr)); + ip_addr.l2tp_family = AF_INET; + ip_addr.l2tp_addr = cfg->local_ip; + ip_addr.l2tp_conn_id = tunnel_id; + err = kernel_bind(sock, (struct sockaddr *) &ip_addr, + sizeof(ip_addr)); + if (err < 0) + goto out; + ip_addr.l2tp_family = AF_INET; + ip_addr.l2tp_addr = cfg->peer_ip; + ip_addr.l2tp_conn_id = peer_tunnel_id; + err = kernel_connect(sock, (struct sockaddr *) &ip_addr, + sizeof(ip_addr), 0); + if (err < 0) + goto out; + } break; default: @@ -1357,7 +1522,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 err = -EBADF; sock = sockfd_lookup(fd, &err); if (!sock) { - printk(KERN_ERR "tunl %hu: sockfd_lookup(fd=%d) returned %d\n", + pr_err("tunl %hu: sockfd_lookup(fd=%d) returned %d\n", tunnel_id, fd, err); goto err; } @@ -1373,7 +1538,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 case L2TP_ENCAPTYPE_UDP: err = -EPROTONOSUPPORT; if (sk->sk_protocol != IPPROTO_UDP) { - printk(KERN_ERR "tunl %hu: fd %d wrong protocol, got %d, expected %d\n", + pr_err("tunl %hu: fd %d wrong protocol, got %d, expected %d\n", tunnel_id, fd, sk->sk_protocol, IPPROTO_UDP); goto err; } @@ -1381,7 +1546,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 case L2TP_ENCAPTYPE_IP: err = -EPROTONOSUPPORT; if (sk->sk_protocol != IPPROTO_L2TP) { - printk(KERN_ERR "tunl %hu: fd %d wrong protocol, got %d, expected %d\n", + pr_err("tunl %hu: fd %d wrong protocol, got %d, expected %d\n", tunnel_id, fd, sk->sk_protocol, IPPROTO_L2TP); goto err; } @@ -1424,6 +1589,12 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 /* Mark socket as an encapsulation socket. See net/ipv4/udp.c */ udp_sk(sk)->encap_type = UDP_ENCAP_L2TPINUDP; udp_sk(sk)->encap_rcv = l2tp_udp_encap_recv; +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == PF_INET6) + udpv6_encap_enable(); + else +#endif + udp_encap_enable(); } sk->sk_user_data = tunnel; @@ -1577,7 +1748,7 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn session->session_id = session_id; session->peer_session_id = peer_session_id; - session->nr = 1; + session->nr = 0; sprintf(&session->name[0], "sess %u/%u", tunnel->tunnel_id, session->session_id); @@ -1683,7 +1854,7 @@ static int __init l2tp_init(void) if (rc) goto out; - printk(KERN_INFO "L2TP core driver, %s\n", L2TP_DRV_VERSION); + pr_info("L2TP core driver, %s\n", L2TP_DRV_VERSION); out: return rc; diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index a16a48e79fa..a38ec6cdeee 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -45,6 +45,7 @@ struct l2tp_stats { u64 rx_oos_packets; u64 rx_errors; u64 rx_cookie_discards; + struct u64_stats_sync syncp; }; struct l2tp_tunnel; @@ -54,15 +55,15 @@ struct l2tp_tunnel; */ struct l2tp_session_cfg { enum l2tp_pwtype pw_type; - unsigned data_seq:2; /* data sequencing level + unsigned int data_seq:2; /* data sequencing level * 0 => none, 1 => IP only, * 2 => all */ - unsigned recv_seq:1; /* expect receive packets with + unsigned int recv_seq:1; /* expect receive packets with * sequence numbers? */ - unsigned send_seq:1; /* send packets with sequence + unsigned int send_seq:1; /* send packets with sequence * numbers? */ - unsigned lns_mode:1; /* behave as LNS? LAC enables + unsigned int lns_mode:1; /* behave as LNS? LAC enables * sequence numbers under * control of LNS. */ int debug; /* bitmask of debug message @@ -107,21 +108,22 @@ struct l2tp_session { char name[32]; /* for logging */ char ifname[IFNAMSIZ]; - unsigned data_seq:2; /* data sequencing level + unsigned int data_seq:2; /* data sequencing level * 0 => none, 1 => IP only, * 2 => all */ - unsigned recv_seq:1; /* expect receive packets with + unsigned int recv_seq:1; /* expect receive packets with * sequence numbers? */ - unsigned send_seq:1; /* send packets with sequence + unsigned int send_seq:1; /* send packets with sequence * numbers? */ - unsigned lns_mode:1; /* behave as LNS? LAC enables + unsigned int lns_mode:1; /* behave as LNS? LAC enables * sequence numbers under * control of LNS. */ int debug; /* bitmask of debug message * categories */ int reorder_timeout; /* configured reorder timeout * (in jiffies) */ + int reorder_skip; /* set if skip to next nr */ int mtu; int mru; enum l2tp_pwtype pwtype; @@ -150,6 +152,10 @@ struct l2tp_tunnel_cfg { /* Used only for kernel-created sockets */ struct in_addr local_ip; struct in_addr peer_ip; +#if IS_ENABLED(CONFIG_IPV6) + struct in6_addr *local_ip6; + struct in6_addr *peer_ip6; +#endif u16 local_udp_port; u16 peer_udp_port; unsigned int use_udp_checksums:1; @@ -255,17 +261,36 @@ static inline void l2tp_session_dec_refcount_1(struct l2tp_session *session) } #ifdef L2TP_REFCNT_DEBUG -#define l2tp_session_inc_refcount(_s) do { \ - printk(KERN_DEBUG "l2tp_session_inc_refcount: %s:%d %s: cnt=%d\n", __func__, __LINE__, (_s)->name, atomic_read(&_s->ref_count)); \ - l2tp_session_inc_refcount_1(_s); \ - } while (0) -#define l2tp_session_dec_refcount(_s) do { \ - printk(KERN_DEBUG "l2tp_session_dec_refcount: %s:%d %s: cnt=%d\n", __func__, __LINE__, (_s)->name, atomic_read(&_s->ref_count)); \ - l2tp_session_dec_refcount_1(_s); \ - } while (0) +#define l2tp_session_inc_refcount(_s) \ +do { \ + pr_debug("l2tp_session_inc_refcount: %s:%d %s: cnt=%d\n", \ + __func__, __LINE__, (_s)->name, \ + atomic_read(&_s->ref_count)); \ + l2tp_session_inc_refcount_1(_s); \ +} while (0) +#define l2tp_session_dec_refcount(_s) \ +do { \ + pr_debug("l2tp_session_dec_refcount: %s:%d %s: cnt=%d\n", \ + __func__, __LINE__, (_s)->name, \ + atomic_read(&_s->ref_count)); \ + l2tp_session_dec_refcount_1(_s); \ +} while (0) #else #define l2tp_session_inc_refcount(s) l2tp_session_inc_refcount_1(s) #define l2tp_session_dec_refcount(s) l2tp_session_dec_refcount_1(s) #endif +#define l2tp_printk(ptr, type, func, fmt, ...) \ +do { \ + if (((ptr)->debug) & (type)) \ + func(fmt, ##__VA_ARGS__); \ +} while (0) + +#define l2tp_warn(ptr, type, fmt, ...) \ + l2tp_printk(ptr, type, pr_warn, fmt, ##__VA_ARGS__) +#define l2tp_info(ptr, type, fmt, ...) \ + l2tp_printk(ptr, type, pr_info, fmt, ##__VA_ARGS__) +#define l2tp_dbg(ptr, type, fmt, ...) \ + l2tp_printk(ptr, type, pr_debug, fmt, ##__VA_ARGS__) + #endif /* _L2TP_CORE_H_ */ diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 76130134bfa..c3813bc8455 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/skbuff.h> #include <linux/socket.h> @@ -122,6 +124,14 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v) seq_printf(m, "\nTUNNEL %u peer %u", tunnel->tunnel_id, tunnel->peer_tunnel_id); if (tunnel->sock) { struct inet_sock *inet = inet_sk(tunnel->sock); + +#if IS_ENABLED(CONFIG_IPV6) + if (tunnel->sock->sk_family == AF_INET6) { + struct ipv6_pinfo *np = inet6_sk(tunnel->sock); + seq_printf(m, " from %pI6c to %pI6c\n", + &np->saddr, &np->daddr); + } else +#endif seq_printf(m, " from %pI4 to %pI4\n", &inet->inet_saddr, &inet->inet_daddr); if (tunnel->encap == L2TP_ENCAPTYPE_UDP) @@ -317,11 +327,11 @@ static int __init l2tp_debugfs_init(void) if (tunnels == NULL) rc = -EIO; - printk(KERN_INFO "L2TP debugfs support\n"); + pr_info("L2TP debugfs support\n"); out: if (rc) - printk(KERN_WARNING "l2tp debugfs: unable to init\n"); + pr_warn("unable to init\n"); return rc; } diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 63fe5f353f0..443591d629c 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/skbuff.h> #include <linux/socket.h> @@ -115,21 +117,14 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, if (session->debug & L2TP_MSG_DATA) { unsigned int length; - int offset; u8 *ptr = skb->data; length = min(32u, skb->len); if (!pskb_may_pull(skb, length)) goto error; - printk(KERN_DEBUG "%s: eth recv: ", session->name); - - offset = 0; - do { - printk(" %02X", ptr[offset]); - } while (++offset < length); - - printk("\n"); + pr_debug("%s: eth recv\n", session->name); + print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } if (!pskb_may_pull(skb, sizeof(ETH_HLEN))) @@ -308,7 +303,7 @@ static int __init l2tp_eth_init(void) if (err) goto out_unreg; - printk(KERN_INFO "L2TP ethernet pseudowire support (L2TPv3)\n"); + pr_info("L2TP ethernet pseudowire support (L2TPv3)\n"); return 0; diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 55670ec3cd0..889f5d13d7b 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/icmp.h> #include <linux/module.h> #include <linux/skbuff.h> @@ -32,15 +34,8 @@ struct l2tp_ip_sock { /* inet_sock has to be the first member of l2tp_ip_sock */ struct inet_sock inet; - __u32 conn_id; - __u32 peer_conn_id; - - __u64 tx_packets; - __u64 tx_bytes; - __u64 tx_errors; - __u64 rx_packets; - __u64 rx_bytes; - __u64 rx_errors; + u32 conn_id; + u32 peer_conn_id; }; static DEFINE_RWLOCK(l2tp_ip_lock); @@ -127,7 +122,6 @@ static int l2tp_ip_recv(struct sk_buff *skb) struct l2tp_session *session; struct l2tp_tunnel *tunnel = NULL; int length; - int offset; /* Point to L2TP header */ optr = ptr = skb->data; @@ -162,14 +156,8 @@ static int l2tp_ip_recv(struct sk_buff *skb) if (!pskb_may_pull(skb, length)) goto discard; - printk(KERN_DEBUG "%s: ip recv: ", tunnel->name); - - offset = 0; - do { - printk(" %02X", ptr[offset]); - } while (++offset < length); - - printk("\n"); + pr_debug("%s: ip recv\n", tunnel->name); + print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } l2tp_recv_common(session, skb, ptr, optr, 0, skb->len, tunnel->recv_payload_hook); @@ -232,7 +220,7 @@ static void l2tp_ip_close(struct sock *sk, long timeout) { write_lock_bh(&l2tp_ip_lock); hlist_del_init(&sk->sk_bind_node); - hlist_del_init(&sk->sk_node); + sk_del_node_init(sk); write_unlock_bh(&l2tp_ip_lock); sk_common_release(sk); } @@ -271,7 +259,8 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST) goto out; - inet->inet_rcv_saddr = inet->inet_saddr = addr->l2tp_addr.s_addr; + if (addr->l2tp_addr.s_addr) + inet->inet_rcv_saddr = inet->inet_saddr = addr->l2tp_addr.s_addr; if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ sk_dst_reset(sk); @@ -297,68 +286,27 @@ out_in_use: static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *) uaddr; - struct inet_sock *inet = inet_sk(sk); - struct flowi4 *fl4; - struct rtable *rt; - __be32 saddr; - int oif, rc; + int rc; - rc = -EINVAL; if (addr_len < sizeof(*lsa)) - goto out; + return -EINVAL; - rc = -EAFNOSUPPORT; - if (lsa->l2tp_family != AF_INET) - goto out; - - lock_sock(sk); - - sk_dst_reset(sk); - - oif = sk->sk_bound_dev_if; - saddr = inet->inet_saddr; - - rc = -EINVAL; if (ipv4_is_multicast(lsa->l2tp_addr.s_addr)) - goto out; + return -EINVAL; - fl4 = &inet->cork.fl.u.ip4; - rt = ip_route_connect(fl4, lsa->l2tp_addr.s_addr, saddr, - RT_CONN_FLAGS(sk), oif, - IPPROTO_L2TP, - 0, 0, sk, true); - if (IS_ERR(rt)) { - rc = PTR_ERR(rt); - if (rc == -ENETUNREACH) - IP_INC_STATS_BH(&init_net, IPSTATS_MIB_OUTNOROUTES); - goto out; - } + rc = ip4_datagram_connect(sk, uaddr, addr_len); + if (rc < 0) + return rc; - rc = -ENETUNREACH; - if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) { - ip_rt_put(rt); - goto out; - } + lock_sock(sk); l2tp_ip_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; - if (!inet->inet_saddr) - inet->inet_saddr = fl4->saddr; - if (!inet->inet_rcv_saddr) - inet->inet_rcv_saddr = fl4->saddr; - inet->inet_daddr = fl4->daddr; - sk->sk_state = TCP_ESTABLISHED; - inet->inet_id = jiffies; - - sk_dst_set(sk, &rt->dst); - write_lock_bh(&l2tp_ip_lock); hlist_del_init(&sk->sk_bind_node); sk_add_bind_node(sk, &l2tp_ip_bind_table); write_unlock_bh(&l2tp_ip_lock); - rc = 0; -out: release_sock(sk); return rc; } @@ -413,7 +361,6 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m { struct sk_buff *skb; int rc; - struct l2tp_ip_sock *lsa = l2tp_ip_sk(sk); struct inet_sock *inet = inet_sk(sk); struct rtable *rt = NULL; struct flowi4 *fl4; @@ -441,8 +388,9 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m daddr = lip->l2tp_addr.s_addr; } else { + rc = -EDESTADDRREQ; if (sk->sk_state != TCP_ESTABLISHED) - return -EDESTADDRREQ; + goto out; daddr = inet->inet_daddr; connected = 1; @@ -512,14 +460,8 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m rcu_read_unlock(); error: - /* Update stats */ - if (rc >= 0) { - lsa->tx_packets++; - lsa->tx_bytes += len; + if (rc >= 0) rc = len; - } else { - lsa->tx_errors++; - } out: release_sock(sk); @@ -537,7 +479,6 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m size_t len, int noblock, int flags, int *addr_len) { struct inet_sock *inet = inet_sk(sk); - struct l2tp_ip_sock *lsk = l2tp_ip_sk(sk); size_t copied = 0; int err = -EOPNOTSUPP; struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; @@ -579,15 +520,7 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m done: skb_free_datagram(sk, skb); out: - if (err) { - lsk->rx_errors++; - return err; - } - - lsk->rx_packets++; - lsk->rx_bytes += copied; - - return copied; + return err ? err : copied; } static struct proto l2tp_ip_prot = { @@ -655,7 +588,7 @@ static int __init l2tp_ip_init(void) { int err; - printk(KERN_INFO "L2TP IP encapsulation support (L2TPv3)\n"); + pr_info("L2TP IP encapsulation support (L2TPv3)\n"); err = proto_register(&l2tp_ip_prot, 1); if (err != 0) diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c new file mode 100644 index 00000000000..0291d8d85f3 --- /dev/null +++ b/net/l2tp/l2tp_ip6.c @@ -0,0 +1,787 @@ +/* + * L2TPv3 IP encapsulation support for IPv6 + * + * Copyright (c) 2012 Katalix Systems Ltd + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/icmp.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/random.h> +#include <linux/socket.h> +#include <linux/l2tp.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <net/sock.h> +#include <net/ip.h> +#include <net/icmp.h> +#include <net/udp.h> +#include <net/inet_common.h> +#include <net/inet_hashtables.h> +#include <net/tcp_states.h> +#include <net/protocol.h> +#include <net/xfrm.h> + +#include <net/transp_v6.h> +#include <net/addrconf.h> +#include <net/ip6_route.h> + +#include "l2tp_core.h" + +struct l2tp_ip6_sock { + /* inet_sock has to be the first member of l2tp_ip6_sock */ + struct inet_sock inet; + + u32 conn_id; + u32 peer_conn_id; + + /* ipv6_pinfo has to be the last member of l2tp_ip6_sock, see + inet6_sk_generic */ + struct ipv6_pinfo inet6; +}; + +static DEFINE_RWLOCK(l2tp_ip6_lock); +static struct hlist_head l2tp_ip6_table; +static struct hlist_head l2tp_ip6_bind_table; + +static inline struct l2tp_ip6_sock *l2tp_ip6_sk(const struct sock *sk) +{ + return (struct l2tp_ip6_sock *)sk; +} + +static struct sock *__l2tp_ip6_bind_lookup(struct net *net, + struct in6_addr *laddr, + int dif, u32 tunnel_id) +{ + struct hlist_node *node; + struct sock *sk; + + sk_for_each_bound(sk, node, &l2tp_ip6_bind_table) { + struct in6_addr *addr = inet6_rcv_saddr(sk); + struct l2tp_ip6_sock *l2tp = l2tp_ip6_sk(sk); + + if (l2tp == NULL) + continue; + + if ((l2tp->conn_id == tunnel_id) && + net_eq(sock_net(sk), net) && + !(addr && ipv6_addr_equal(addr, laddr)) && + !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) + goto found; + } + + sk = NULL; +found: + return sk; +} + +static inline struct sock *l2tp_ip6_bind_lookup(struct net *net, + struct in6_addr *laddr, + int dif, u32 tunnel_id) +{ + struct sock *sk = __l2tp_ip6_bind_lookup(net, laddr, dif, tunnel_id); + if (sk) + sock_hold(sk); + + return sk; +} + +/* When processing receive frames, there are two cases to + * consider. Data frames consist of a non-zero session-id and an + * optional cookie. Control frames consist of a regular L2TP header + * preceded by 32-bits of zeros. + * + * L2TPv3 Session Header Over IP + * + * 0 1 2 3 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Session ID | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Cookie (optional, maximum 64 bits)... + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * L2TPv3 Control Message Header Over IP + * + * 0 1 2 3 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | (32 bits of zeros) | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * |T|L|x|x|S|x|x|x|x|x|x|x| Ver | Length | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Control Connection ID | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Ns | Nr | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * All control frames are passed to userspace. + */ +static int l2tp_ip6_recv(struct sk_buff *skb) +{ + struct sock *sk; + u32 session_id; + u32 tunnel_id; + unsigned char *ptr, *optr; + struct l2tp_session *session; + struct l2tp_tunnel *tunnel = NULL; + int length; + + /* Point to L2TP header */ + optr = ptr = skb->data; + + if (!pskb_may_pull(skb, 4)) + goto discard; + + session_id = ntohl(*((__be32 *) ptr)); + ptr += 4; + + /* RFC3931: L2TP/IP packets have the first 4 bytes containing + * the session_id. If it is 0, the packet is a L2TP control + * frame and the session_id value can be discarded. + */ + if (session_id == 0) { + __skb_pull(skb, 4); + goto pass_up; + } + + /* Ok, this is a data packet. Lookup the session. */ + session = l2tp_session_find(&init_net, NULL, session_id); + if (session == NULL) + goto discard; + + tunnel = session->tunnel; + if (tunnel == NULL) + goto discard; + + /* Trace packet contents, if enabled */ + if (tunnel->debug & L2TP_MSG_DATA) { + length = min(32u, skb->len); + if (!pskb_may_pull(skb, length)) + goto discard; + + pr_debug("%s: ip recv\n", tunnel->name); + print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); + } + + l2tp_recv_common(session, skb, ptr, optr, 0, skb->len, + tunnel->recv_payload_hook); + return 0; + +pass_up: + /* Get the tunnel_id from the L2TP header */ + if (!pskb_may_pull(skb, 12)) + goto discard; + + if ((skb->data[0] & 0xc0) != 0xc0) + goto discard; + + tunnel_id = ntohl(*(__be32 *) &skb->data[4]); + tunnel = l2tp_tunnel_find(&init_net, tunnel_id); + if (tunnel != NULL) + sk = tunnel->sock; + else { + struct ipv6hdr *iph = ipv6_hdr(skb); + + read_lock_bh(&l2tp_ip6_lock); + sk = __l2tp_ip6_bind_lookup(&init_net, &iph->daddr, + 0, tunnel_id); + read_unlock_bh(&l2tp_ip6_lock); + } + + if (sk == NULL) + goto discard; + + sock_hold(sk); + + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) + goto discard_put; + + nf_reset(skb); + + return sk_receive_skb(sk, skb, 1); + +discard_put: + sock_put(sk); + +discard: + kfree_skb(skb); + return 0; +} + +static int l2tp_ip6_open(struct sock *sk) +{ + /* Prevent autobind. We don't have ports. */ + inet_sk(sk)->inet_num = IPPROTO_L2TP; + + write_lock_bh(&l2tp_ip6_lock); + sk_add_node(sk, &l2tp_ip6_table); + write_unlock_bh(&l2tp_ip6_lock); + + return 0; +} + +static void l2tp_ip6_close(struct sock *sk, long timeout) +{ + write_lock_bh(&l2tp_ip6_lock); + hlist_del_init(&sk->sk_bind_node); + sk_del_node_init(sk); + write_unlock_bh(&l2tp_ip6_lock); + + sk_common_release(sk); +} + +static void l2tp_ip6_destroy_sock(struct sock *sk) +{ + lock_sock(sk); + ip6_flush_pending_frames(sk); + release_sock(sk); + + inet6_destroy_sock(sk); +} + +static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) +{ + struct inet_sock *inet = inet_sk(sk); + struct ipv6_pinfo *np = inet6_sk(sk); + struct sockaddr_l2tpip6 *addr = (struct sockaddr_l2tpip6 *) uaddr; + __be32 v4addr = 0; + int addr_type; + int err; + + if (addr_len < sizeof(*addr)) + return -EINVAL; + + addr_type = ipv6_addr_type(&addr->l2tp_addr); + + /* l2tp_ip6 sockets are IPv6 only */ + if (addr_type == IPV6_ADDR_MAPPED) + return -EADDRNOTAVAIL; + + /* L2TP is point-point, not multicast */ + if (addr_type & IPV6_ADDR_MULTICAST) + return -EADDRNOTAVAIL; + + err = -EADDRINUSE; + read_lock_bh(&l2tp_ip6_lock); + if (__l2tp_ip6_bind_lookup(&init_net, &addr->l2tp_addr, + sk->sk_bound_dev_if, addr->l2tp_conn_id)) + goto out_in_use; + read_unlock_bh(&l2tp_ip6_lock); + + lock_sock(sk); + + err = -EINVAL; + if (sk->sk_state != TCP_CLOSE) + goto out_unlock; + + /* Check if the address belongs to the host. */ + rcu_read_lock(); + if (addr_type != IPV6_ADDR_ANY) { + struct net_device *dev = NULL; + + if (addr_type & IPV6_ADDR_LINKLOCAL) { + if (addr_len >= sizeof(struct sockaddr_in6) && + addr->l2tp_scope_id) { + /* Override any existing binding, if another + * one is supplied by user. + */ + sk->sk_bound_dev_if = addr->l2tp_scope_id; + } + + /* Binding to link-local address requires an + interface */ + if (!sk->sk_bound_dev_if) + goto out_unlock_rcu; + + err = -ENODEV; + dev = dev_get_by_index_rcu(sock_net(sk), + sk->sk_bound_dev_if); + if (!dev) + goto out_unlock_rcu; + } + + /* ipv4 addr of the socket is invalid. Only the + * unspecified and mapped address have a v4 equivalent. + */ + v4addr = LOOPBACK4_IPV6; + err = -EADDRNOTAVAIL; + if (!ipv6_chk_addr(sock_net(sk), &addr->l2tp_addr, dev, 0)) + goto out_unlock_rcu; + } + rcu_read_unlock(); + + inet->inet_rcv_saddr = inet->inet_saddr = v4addr; + np->rcv_saddr = addr->l2tp_addr; + np->saddr = addr->l2tp_addr; + + l2tp_ip6_sk(sk)->conn_id = addr->l2tp_conn_id; + + write_lock_bh(&l2tp_ip6_lock); + sk_add_bind_node(sk, &l2tp_ip6_bind_table); + sk_del_node_init(sk); + write_unlock_bh(&l2tp_ip6_lock); + + release_sock(sk); + return 0; + +out_unlock_rcu: + rcu_read_unlock(); +out_unlock: + release_sock(sk); + return err; + +out_in_use: + read_unlock_bh(&l2tp_ip6_lock); + return err; +} + +static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, + int addr_len) +{ + struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *) uaddr; + struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; + struct in6_addr *daddr; + int addr_type; + int rc; + + if (addr_len < sizeof(*lsa)) + return -EINVAL; + + addr_type = ipv6_addr_type(&usin->sin6_addr); + if (addr_type & IPV6_ADDR_MULTICAST) + return -EINVAL; + + if (addr_type & IPV6_ADDR_MAPPED) { + daddr = &usin->sin6_addr; + if (ipv4_is_multicast(daddr->s6_addr32[3])) + return -EINVAL; + } + + rc = ip6_datagram_connect(sk, uaddr, addr_len); + + lock_sock(sk); + + l2tp_ip6_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; + + write_lock_bh(&l2tp_ip6_lock); + hlist_del_init(&sk->sk_bind_node); + sk_add_bind_node(sk, &l2tp_ip6_bind_table); + write_unlock_bh(&l2tp_ip6_lock); + + release_sock(sk); + + return rc; +} + +static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr, + int *uaddr_len, int peer) +{ + struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)uaddr; + struct sock *sk = sock->sk; + struct ipv6_pinfo *np = inet6_sk(sk); + struct l2tp_ip6_sock *lsk = l2tp_ip6_sk(sk); + + lsa->l2tp_family = AF_INET6; + lsa->l2tp_flowinfo = 0; + lsa->l2tp_scope_id = 0; + if (peer) { + if (!lsk->peer_conn_id) + return -ENOTCONN; + lsa->l2tp_conn_id = lsk->peer_conn_id; + lsa->l2tp_addr = np->daddr; + if (np->sndflow) + lsa->l2tp_flowinfo = np->flow_label; + } else { + if (ipv6_addr_any(&np->rcv_saddr)) + lsa->l2tp_addr = np->saddr; + else + lsa->l2tp_addr = np->rcv_saddr; + + lsa->l2tp_conn_id = lsk->conn_id; + } + if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL) + lsa->l2tp_scope_id = sk->sk_bound_dev_if; + *uaddr_len = sizeof(*lsa); + return 0; +} + +static int l2tp_ip6_backlog_recv(struct sock *sk, struct sk_buff *skb) +{ + int rc; + + /* Charge it to the socket, dropping if the queue is full. */ + rc = sock_queue_rcv_skb(sk, skb); + if (rc < 0) + goto drop; + + return 0; + +drop: + IP_INC_STATS(&init_net, IPSTATS_MIB_INDISCARDS); + kfree_skb(skb); + return -1; +} + +static int l2tp_ip6_push_pending_frames(struct sock *sk) +{ + struct sk_buff *skb; + __be32 *transhdr = NULL; + int err = 0; + + skb = skb_peek(&sk->sk_write_queue); + if (skb == NULL) + goto out; + + transhdr = (__be32 *)skb_transport_header(skb); + *transhdr = 0; + + err = ip6_push_pending_frames(sk); + +out: + return err; +} + +/* Userspace will call sendmsg() on the tunnel socket to send L2TP + * control frames. + */ +static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk, + struct msghdr *msg, size_t len) +{ + struct ipv6_txoptions opt_space; + struct sockaddr_l2tpip6 *lsa = + (struct sockaddr_l2tpip6 *) msg->msg_name; + struct in6_addr *daddr, *final_p, final; + struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6_txoptions *opt = NULL; + struct ip6_flowlabel *flowlabel = NULL; + struct dst_entry *dst = NULL; + struct flowi6 fl6; + int addr_len = msg->msg_namelen; + int hlimit = -1; + int tclass = -1; + int dontfrag = -1; + int transhdrlen = 4; /* zero session-id */ + int ulen = len + transhdrlen; + int err; + + /* Rough check on arithmetic overflow, + better check is made in ip6_append_data(). + */ + if (len > INT_MAX) + return -EMSGSIZE; + + /* Mirror BSD error message compatibility */ + if (msg->msg_flags & MSG_OOB) + return -EOPNOTSUPP; + + /* + * Get and verify the address. + */ + memset(&fl6, 0, sizeof(fl6)); + + fl6.flowi6_mark = sk->sk_mark; + + if (lsa) { + if (addr_len < SIN6_LEN_RFC2133) + return -EINVAL; + + if (lsa->l2tp_family && lsa->l2tp_family != AF_INET6) + return -EAFNOSUPPORT; + + daddr = &lsa->l2tp_addr; + if (np->sndflow) { + fl6.flowlabel = lsa->l2tp_flowinfo & IPV6_FLOWINFO_MASK; + if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { + flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); + if (flowlabel == NULL) + return -EINVAL; + daddr = &flowlabel->dst; + } + } + + /* + * Otherwise it will be difficult to maintain + * sk->sk_dst_cache. + */ + if (sk->sk_state == TCP_ESTABLISHED && + ipv6_addr_equal(daddr, &np->daddr)) + daddr = &np->daddr; + + if (addr_len >= sizeof(struct sockaddr_in6) && + lsa->l2tp_scope_id && + ipv6_addr_type(daddr) & IPV6_ADDR_LINKLOCAL) + fl6.flowi6_oif = lsa->l2tp_scope_id; + } else { + if (sk->sk_state != TCP_ESTABLISHED) + return -EDESTADDRREQ; + + daddr = &np->daddr; + fl6.flowlabel = np->flow_label; + } + + if (fl6.flowi6_oif == 0) + fl6.flowi6_oif = sk->sk_bound_dev_if; + + if (msg->msg_controllen) { + opt = &opt_space; + memset(opt, 0, sizeof(struct ipv6_txoptions)); + opt->tot_len = sizeof(struct ipv6_txoptions); + + err = datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, + &hlimit, &tclass, &dontfrag); + if (err < 0) { + fl6_sock_release(flowlabel); + return err; + } + if ((fl6.flowlabel & IPV6_FLOWLABEL_MASK) && !flowlabel) { + flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); + if (flowlabel == NULL) + return -EINVAL; + } + if (!(opt->opt_nflen|opt->opt_flen)) + opt = NULL; + } + + if (opt == NULL) + opt = np->opt; + if (flowlabel) + opt = fl6_merge_options(&opt_space, flowlabel, opt); + opt = ipv6_fixup_options(&opt_space, opt); + + fl6.flowi6_proto = sk->sk_protocol; + if (!ipv6_addr_any(daddr)) + fl6.daddr = *daddr; + else + fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ + if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) + fl6.saddr = np->saddr; + + final_p = fl6_update_dst(&fl6, opt, &final); + + if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) + fl6.flowi6_oif = np->mcast_oif; + else if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->ucast_oif; + + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + + dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + goto out; + } + + if (hlimit < 0) { + if (ipv6_addr_is_multicast(&fl6.daddr)) + hlimit = np->mcast_hops; + else + hlimit = np->hop_limit; + if (hlimit < 0) + hlimit = ip6_dst_hoplimit(dst); + } + + if (tclass < 0) + tclass = np->tclass; + + if (dontfrag < 0) + dontfrag = np->dontfrag; + + if (msg->msg_flags & MSG_CONFIRM) + goto do_confirm; + +back_from_confirm: + lock_sock(sk); + err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov, + ulen, transhdrlen, hlimit, tclass, opt, + &fl6, (struct rt6_info *)dst, + msg->msg_flags, dontfrag); + if (err) + ip6_flush_pending_frames(sk); + else if (!(msg->msg_flags & MSG_MORE)) + err = l2tp_ip6_push_pending_frames(sk); + release_sock(sk); +done: + dst_release(dst); +out: + fl6_sock_release(flowlabel); + + return err < 0 ? err : len; + +do_confirm: + dst_confirm(dst); + if (!(msg->msg_flags & MSG_PROBE) || len) + goto back_from_confirm; + err = 0; + goto done; +} + +static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk, + struct msghdr *msg, size_t len, int noblock, + int flags, int *addr_len) +{ + struct inet_sock *inet = inet_sk(sk); + struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)msg->msg_name; + size_t copied = 0; + int err = -EOPNOTSUPP; + struct sk_buff *skb; + + if (flags & MSG_OOB) + goto out; + + if (addr_len) + *addr_len = sizeof(*lsa); + + if (flags & MSG_ERRQUEUE) + return ipv6_recv_error(sk, msg, len); + + skb = skb_recv_datagram(sk, flags, noblock, &err); + if (!skb) + goto out; + + copied = skb->len; + if (len < copied) { + msg->msg_flags |= MSG_TRUNC; + copied = len; + } + + err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); + if (err) + goto done; + + sock_recv_timestamp(msg, sk, skb); + + /* Copy the address. */ + if (lsa) { + lsa->l2tp_family = AF_INET6; + lsa->l2tp_unused = 0; + lsa->l2tp_addr = ipv6_hdr(skb)->saddr; + lsa->l2tp_flowinfo = 0; + lsa->l2tp_scope_id = 0; + if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL) + lsa->l2tp_scope_id = IP6CB(skb)->iif; + } + + if (inet->cmsg_flags) + ip_cmsg_recv(msg, skb); + + if (flags & MSG_TRUNC) + copied = skb->len; +done: + skb_free_datagram(sk, skb); +out: + return err ? err : copied; +} + +static struct proto l2tp_ip6_prot = { + .name = "L2TP/IPv6", + .owner = THIS_MODULE, + .init = l2tp_ip6_open, + .close = l2tp_ip6_close, + .bind = l2tp_ip6_bind, + .connect = l2tp_ip6_connect, + .disconnect = udp_disconnect, + .ioctl = udp_ioctl, + .destroy = l2tp_ip6_destroy_sock, + .setsockopt = ipv6_setsockopt, + .getsockopt = ipv6_getsockopt, + .sendmsg = l2tp_ip6_sendmsg, + .recvmsg = l2tp_ip6_recvmsg, + .backlog_rcv = l2tp_ip6_backlog_recv, + .hash = inet_hash, + .unhash = inet_unhash, + .obj_size = sizeof(struct l2tp_ip6_sock), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_ipv6_setsockopt, + .compat_getsockopt = compat_ipv6_getsockopt, +#endif +}; + +static const struct proto_ops l2tp_ip6_ops = { + .family = PF_INET6, + .owner = THIS_MODULE, + .release = inet6_release, + .bind = inet6_bind, + .connect = inet_dgram_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = l2tp_ip6_getname, + .poll = datagram_poll, + .ioctl = inet6_ioctl, + .listen = sock_no_listen, + .shutdown = inet_shutdown, + .setsockopt = sock_common_setsockopt, + .getsockopt = sock_common_getsockopt, + .sendmsg = inet_sendmsg, + .recvmsg = sock_common_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_sock_common_setsockopt, + .compat_getsockopt = compat_sock_common_getsockopt, +#endif +}; + +static struct inet_protosw l2tp_ip6_protosw = { + .type = SOCK_DGRAM, + .protocol = IPPROTO_L2TP, + .prot = &l2tp_ip6_prot, + .ops = &l2tp_ip6_ops, + .no_check = 0, +}; + +static struct inet6_protocol l2tp_ip6_protocol __read_mostly = { + .handler = l2tp_ip6_recv, +}; + +static int __init l2tp_ip6_init(void) +{ + int err; + + pr_info("L2TP IP encapsulation support for IPv6 (L2TPv3)\n"); + + err = proto_register(&l2tp_ip6_prot, 1); + if (err != 0) + goto out; + + err = inet6_add_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP); + if (err) + goto out1; + + inet6_register_protosw(&l2tp_ip6_protosw); + return 0; + +out1: + proto_unregister(&l2tp_ip6_prot); +out: + return err; +} + +static void __exit l2tp_ip6_exit(void) +{ + inet6_unregister_protosw(&l2tp_ip6_protosw); + inet6_del_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP); + proto_unregister(&l2tp_ip6_prot); +} + +module_init(l2tp_ip6_init); +module_exit(l2tp_ip6_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Chris Elston <celston@katalix.com>"); +MODULE_DESCRIPTION("L2TP IP encapsulation for IPv6"); +MODULE_VERSION("1.0"); + +/* Use the value of SOCK_DGRAM (2) directory, because __stringify doesn't like + * enums + */ +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 2, IPPROTO_L2TP); diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 93a41a09458..8577264378f 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -14,6 +14,8 @@ * published by the Free Software Foundation. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <net/sock.h> #include <net/genetlink.h> #include <net/udp.h> @@ -133,10 +135,25 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info if (info->attrs[L2TP_ATTR_FD]) { fd = nla_get_u32(info->attrs[L2TP_ATTR_FD]); } else { - if (info->attrs[L2TP_ATTR_IP_SADDR]) - cfg.local_ip.s_addr = nla_get_be32(info->attrs[L2TP_ATTR_IP_SADDR]); - if (info->attrs[L2TP_ATTR_IP_DADDR]) - cfg.peer_ip.s_addr = nla_get_be32(info->attrs[L2TP_ATTR_IP_DADDR]); +#if IS_ENABLED(CONFIG_IPV6) + if (info->attrs[L2TP_ATTR_IP6_SADDR] && + info->attrs[L2TP_ATTR_IP6_DADDR]) { + cfg.local_ip6 = nla_data( + info->attrs[L2TP_ATTR_IP6_SADDR]); + cfg.peer_ip6 = nla_data( + info->attrs[L2TP_ATTR_IP6_DADDR]); + } else +#endif + if (info->attrs[L2TP_ATTR_IP_SADDR] && + info->attrs[L2TP_ATTR_IP_DADDR]) { + cfg.local_ip.s_addr = nla_get_be32( + info->attrs[L2TP_ATTR_IP_SADDR]); + cfg.peer_ip.s_addr = nla_get_be32( + info->attrs[L2TP_ATTR_IP_DADDR]); + } else { + ret = -EINVAL; + goto out; + } if (info->attrs[L2TP_ATTR_UDP_SPORT]) cfg.local_udp_port = nla_get_u16(info->attrs[L2TP_ATTR_UDP_SPORT]); if (info->attrs[L2TP_ATTR_UDP_DPORT]) @@ -225,47 +242,85 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 pid, u32 seq, int flags, struct nlattr *nest; struct sock *sk = NULL; struct inet_sock *inet; +#if IS_ENABLED(CONFIG_IPV6) + struct ipv6_pinfo *np = NULL; +#endif + struct l2tp_stats stats; + unsigned int start; hdr = genlmsg_put(skb, pid, seq, &l2tp_nl_family, flags, L2TP_CMD_TUNNEL_GET); if (IS_ERR(hdr)) return PTR_ERR(hdr); - NLA_PUT_U8(skb, L2TP_ATTR_PROTO_VERSION, tunnel->version); - NLA_PUT_U32(skb, L2TP_ATTR_CONN_ID, tunnel->tunnel_id); - NLA_PUT_U32(skb, L2TP_ATTR_PEER_CONN_ID, tunnel->peer_tunnel_id); - NLA_PUT_U32(skb, L2TP_ATTR_DEBUG, tunnel->debug); - NLA_PUT_U16(skb, L2TP_ATTR_ENCAP_TYPE, tunnel->encap); + if (nla_put_u8(skb, L2TP_ATTR_PROTO_VERSION, tunnel->version) || + nla_put_u32(skb, L2TP_ATTR_CONN_ID, tunnel->tunnel_id) || + nla_put_u32(skb, L2TP_ATTR_PEER_CONN_ID, tunnel->peer_tunnel_id) || + nla_put_u32(skb, L2TP_ATTR_DEBUG, tunnel->debug) || + nla_put_u16(skb, L2TP_ATTR_ENCAP_TYPE, tunnel->encap)) + goto nla_put_failure; nest = nla_nest_start(skb, L2TP_ATTR_STATS); if (nest == NULL) goto nla_put_failure; - NLA_PUT_U64(skb, L2TP_ATTR_TX_PACKETS, tunnel->stats.tx_packets); - NLA_PUT_U64(skb, L2TP_ATTR_TX_BYTES, tunnel->stats.tx_bytes); - NLA_PUT_U64(skb, L2TP_ATTR_TX_ERRORS, tunnel->stats.tx_errors); - NLA_PUT_U64(skb, L2TP_ATTR_RX_PACKETS, tunnel->stats.rx_packets); - NLA_PUT_U64(skb, L2TP_ATTR_RX_BYTES, tunnel->stats.rx_bytes); - NLA_PUT_U64(skb, L2TP_ATTR_RX_SEQ_DISCARDS, tunnel->stats.rx_seq_discards); - NLA_PUT_U64(skb, L2TP_ATTR_RX_OOS_PACKETS, tunnel->stats.rx_oos_packets); - NLA_PUT_U64(skb, L2TP_ATTR_RX_ERRORS, tunnel->stats.rx_errors); + do { + start = u64_stats_fetch_begin(&tunnel->stats.syncp); + stats.tx_packets = tunnel->stats.tx_packets; + stats.tx_bytes = tunnel->stats.tx_bytes; + stats.tx_errors = tunnel->stats.tx_errors; + stats.rx_packets = tunnel->stats.rx_packets; + stats.rx_bytes = tunnel->stats.rx_bytes; + stats.rx_errors = tunnel->stats.rx_errors; + stats.rx_seq_discards = tunnel->stats.rx_seq_discards; + stats.rx_oos_packets = tunnel->stats.rx_oos_packets; + } while (u64_stats_fetch_retry(&tunnel->stats.syncp, start)); + + if (nla_put_u64(skb, L2TP_ATTR_TX_PACKETS, stats.tx_packets) || + nla_put_u64(skb, L2TP_ATTR_TX_BYTES, stats.tx_bytes) || + nla_put_u64(skb, L2TP_ATTR_TX_ERRORS, stats.tx_errors) || + nla_put_u64(skb, L2TP_ATTR_RX_PACKETS, stats.rx_packets) || + nla_put_u64(skb, L2TP_ATTR_RX_BYTES, stats.rx_bytes) || + nla_put_u64(skb, L2TP_ATTR_RX_SEQ_DISCARDS, + stats.rx_seq_discards) || + nla_put_u64(skb, L2TP_ATTR_RX_OOS_PACKETS, + stats.rx_oos_packets) || + nla_put_u64(skb, L2TP_ATTR_RX_ERRORS, stats.rx_errors)) + goto nla_put_failure; nla_nest_end(skb, nest); sk = tunnel->sock; if (!sk) goto out; +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) + np = inet6_sk(sk); +#endif + inet = inet_sk(sk); switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: - NLA_PUT_U16(skb, L2TP_ATTR_UDP_SPORT, ntohs(inet->inet_sport)); - NLA_PUT_U16(skb, L2TP_ATTR_UDP_DPORT, ntohs(inet->inet_dport)); - NLA_PUT_U8(skb, L2TP_ATTR_UDP_CSUM, (sk->sk_no_check != UDP_CSUM_NOXMIT)); + if (nla_put_u16(skb, L2TP_ATTR_UDP_SPORT, ntohs(inet->inet_sport)) || + nla_put_u16(skb, L2TP_ATTR_UDP_DPORT, ntohs(inet->inet_dport)) || + nla_put_u8(skb, L2TP_ATTR_UDP_CSUM, + (sk->sk_no_check != UDP_CSUM_NOXMIT))) + goto nla_put_failure; /* NOBREAK */ case L2TP_ENCAPTYPE_IP: - NLA_PUT_BE32(skb, L2TP_ATTR_IP_SADDR, inet->inet_saddr); - NLA_PUT_BE32(skb, L2TP_ATTR_IP_DADDR, inet->inet_daddr); +#if IS_ENABLED(CONFIG_IPV6) + if (np) { + if (nla_put(skb, L2TP_ATTR_IP6_SADDR, sizeof(np->saddr), + &np->saddr) || + nla_put(skb, L2TP_ATTR_IP6_DADDR, sizeof(np->daddr), + &np->daddr)) + goto nla_put_failure; + } else +#endif + if (nla_put_be32(skb, L2TP_ATTR_IP_SADDR, inet->inet_saddr) || + nla_put_be32(skb, L2TP_ATTR_IP_DADDR, inet->inet_daddr)) + goto nla_put_failure; break; } @@ -556,6 +611,8 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 pid, u32 seq, int flags struct nlattr *nest; struct l2tp_tunnel *tunnel = session->tunnel; struct sock *sk = NULL; + struct l2tp_stats stats; + unsigned int start; sk = tunnel->sock; @@ -563,43 +620,64 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 pid, u32 seq, int flags if (IS_ERR(hdr)) return PTR_ERR(hdr); - NLA_PUT_U32(skb, L2TP_ATTR_CONN_ID, tunnel->tunnel_id); - NLA_PUT_U32(skb, L2TP_ATTR_SESSION_ID, session->session_id); - NLA_PUT_U32(skb, L2TP_ATTR_PEER_CONN_ID, tunnel->peer_tunnel_id); - NLA_PUT_U32(skb, L2TP_ATTR_PEER_SESSION_ID, session->peer_session_id); - NLA_PUT_U32(skb, L2TP_ATTR_DEBUG, session->debug); - NLA_PUT_U16(skb, L2TP_ATTR_PW_TYPE, session->pwtype); - NLA_PUT_U16(skb, L2TP_ATTR_MTU, session->mtu); - if (session->mru) - NLA_PUT_U16(skb, L2TP_ATTR_MRU, session->mru); - - if (session->ifname && session->ifname[0]) - NLA_PUT_STRING(skb, L2TP_ATTR_IFNAME, session->ifname); - if (session->cookie_len) - NLA_PUT(skb, L2TP_ATTR_COOKIE, session->cookie_len, &session->cookie[0]); - if (session->peer_cookie_len) - NLA_PUT(skb, L2TP_ATTR_PEER_COOKIE, session->peer_cookie_len, &session->peer_cookie[0]); - NLA_PUT_U8(skb, L2TP_ATTR_RECV_SEQ, session->recv_seq); - NLA_PUT_U8(skb, L2TP_ATTR_SEND_SEQ, session->send_seq); - NLA_PUT_U8(skb, L2TP_ATTR_LNS_MODE, session->lns_mode); + if (nla_put_u32(skb, L2TP_ATTR_CONN_ID, tunnel->tunnel_id) || + nla_put_u32(skb, L2TP_ATTR_SESSION_ID, session->session_id) || + nla_put_u32(skb, L2TP_ATTR_PEER_CONN_ID, tunnel->peer_tunnel_id) || + nla_put_u32(skb, L2TP_ATTR_PEER_SESSION_ID, + session->peer_session_id) || + nla_put_u32(skb, L2TP_ATTR_DEBUG, session->debug) || + nla_put_u16(skb, L2TP_ATTR_PW_TYPE, session->pwtype) || + nla_put_u16(skb, L2TP_ATTR_MTU, session->mtu) || + (session->mru && + nla_put_u16(skb, L2TP_ATTR_MRU, session->mru))) + goto nla_put_failure; + + if ((session->ifname && session->ifname[0] && + nla_put_string(skb, L2TP_ATTR_IFNAME, session->ifname)) || + (session->cookie_len && + nla_put(skb, L2TP_ATTR_COOKIE, session->cookie_len, + &session->cookie[0])) || + (session->peer_cookie_len && + nla_put(skb, L2TP_ATTR_PEER_COOKIE, session->peer_cookie_len, + &session->peer_cookie[0])) || + nla_put_u8(skb, L2TP_ATTR_RECV_SEQ, session->recv_seq) || + nla_put_u8(skb, L2TP_ATTR_SEND_SEQ, session->send_seq) || + nla_put_u8(skb, L2TP_ATTR_LNS_MODE, session->lns_mode) || #ifdef CONFIG_XFRM - if ((sk) && (sk->sk_policy[0] || sk->sk_policy[1])) - NLA_PUT_U8(skb, L2TP_ATTR_USING_IPSEC, 1); + (((sk) && (sk->sk_policy[0] || sk->sk_policy[1])) && + nla_put_u8(skb, L2TP_ATTR_USING_IPSEC, 1)) || #endif - if (session->reorder_timeout) - NLA_PUT_MSECS(skb, L2TP_ATTR_RECV_TIMEOUT, session->reorder_timeout); + (session->reorder_timeout && + nla_put_msecs(skb, L2TP_ATTR_RECV_TIMEOUT, session->reorder_timeout))) + goto nla_put_failure; nest = nla_nest_start(skb, L2TP_ATTR_STATS); if (nest == NULL) goto nla_put_failure; - NLA_PUT_U64(skb, L2TP_ATTR_TX_PACKETS, session->stats.tx_packets); - NLA_PUT_U64(skb, L2TP_ATTR_TX_BYTES, session->stats.tx_bytes); - NLA_PUT_U64(skb, L2TP_ATTR_TX_ERRORS, session->stats.tx_errors); - NLA_PUT_U64(skb, L2TP_ATTR_RX_PACKETS, session->stats.rx_packets); - NLA_PUT_U64(skb, L2TP_ATTR_RX_BYTES, session->stats.rx_bytes); - NLA_PUT_U64(skb, L2TP_ATTR_RX_SEQ_DISCARDS, session->stats.rx_seq_discards); - NLA_PUT_U64(skb, L2TP_ATTR_RX_OOS_PACKETS, session->stats.rx_oos_packets); - NLA_PUT_U64(skb, L2TP_ATTR_RX_ERRORS, session->stats.rx_errors); + + do { + start = u64_stats_fetch_begin(&session->stats.syncp); + stats.tx_packets = session->stats.tx_packets; + stats.tx_bytes = session->stats.tx_bytes; + stats.tx_errors = session->stats.tx_errors; + stats.rx_packets = session->stats.rx_packets; + stats.rx_bytes = session->stats.rx_bytes; + stats.rx_errors = session->stats.rx_errors; + stats.rx_seq_discards = session->stats.rx_seq_discards; + stats.rx_oos_packets = session->stats.rx_oos_packets; + } while (u64_stats_fetch_retry(&session->stats.syncp, start)); + + if (nla_put_u64(skb, L2TP_ATTR_TX_PACKETS, stats.tx_packets) || + nla_put_u64(skb, L2TP_ATTR_TX_BYTES, stats.tx_bytes) || + nla_put_u64(skb, L2TP_ATTR_TX_ERRORS, stats.tx_errors) || + nla_put_u64(skb, L2TP_ATTR_RX_PACKETS, stats.rx_packets) || + nla_put_u64(skb, L2TP_ATTR_RX_BYTES, stats.rx_bytes) || + nla_put_u64(skb, L2TP_ATTR_RX_SEQ_DISCARDS, + stats.rx_seq_discards) || + nla_put_u64(skb, L2TP_ATTR_RX_OOS_PACKETS, + stats.rx_oos_packets) || + nla_put_u64(skb, L2TP_ATTR_RX_ERRORS, stats.rx_errors)) + goto nla_put_failure; nla_nest_end(skb, nest); return genlmsg_end(skb, hdr); @@ -708,6 +786,14 @@ static struct nla_policy l2tp_nl_policy[L2TP_ATTR_MAX + 1] = { [L2TP_ATTR_MTU] = { .type = NLA_U16, }, [L2TP_ATTR_MRU] = { .type = NLA_U16, }, [L2TP_ATTR_STATS] = { .type = NLA_NESTED, }, + [L2TP_ATTR_IP6_SADDR] = { + .type = NLA_BINARY, + .len = sizeof(struct in6_addr), + }, + [L2TP_ATTR_IP6_DADDR] = { + .type = NLA_BINARY, + .len = sizeof(struct in6_addr), + }, [L2TP_ATTR_IFNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1, @@ -818,7 +904,7 @@ static int l2tp_nl_init(void) { int err; - printk(KERN_INFO "L2TP netlink interface\n"); + pr_info("L2TP netlink interface\n"); err = genl_register_family_with_ops(&l2tp_nl_family, l2tp_nl_ops, ARRAY_SIZE(l2tp_nl_ops)); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 1addd9f3f40..8ef6b9416cb 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -57,6 +57,8 @@ * http://openl2tp.sourceforge.net. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/string.h> #include <linux/list.h> @@ -106,12 +108,6 @@ /* Space for UDP, L2TP and PPP headers */ #define PPPOL2TP_HEADER_OVERHEAD 40 -#define PRINTK(_mask, _type, _lvl, _fmt, args...) \ - do { \ - if ((_mask) & (_type)) \ - printk(_lvl "PPPOL2TP: " _fmt, ##args); \ - } while (0) - /* Number of bytes to build transmit L2TP headers. * Unfortunately the size is different depending on whether sequence numbers * are enabled. @@ -236,9 +232,9 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int if (sk->sk_state & PPPOX_BOUND) { struct pppox_sock *po; - PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG, - "%s: recv %d byte data frame, passing to ppp\n", - session->name, data_len); + l2tp_dbg(session, PPPOL2TP_MSG_DATA, + "%s: recv %d byte data frame, passing to ppp\n", + session->name, data_len); /* We need to forget all info related to the L2TP packet * gathered in the skb as we are going to reuse the same @@ -259,8 +255,8 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int po = pppox_sk(sk); ppp_input(&po->chan, skb); } else { - PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_INFO, - "%s: socket not bound\n", session->name); + l2tp_info(session, PPPOL2TP_MSG_DATA, "%s: socket not bound\n", + session->name); /* Not bound. Nothing we can do, so discard. */ session->stats.rx_errors++; @@ -270,8 +266,7 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int return; no_sock: - PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_INFO, - "%s: no socket\n", session->name); + l2tp_info(session, PPPOL2TP_MSG_DATA, "%s: no socket\n", session->name); kfree_skb(skb); } @@ -628,7 +623,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, { struct sock *sk = sock->sk; struct sockaddr_pppol2tp *sp = (struct sockaddr_pppol2tp *) uservaddr; - struct sockaddr_pppol2tpv3 *sp3 = (struct sockaddr_pppol2tpv3 *) uservaddr; struct pppox_sock *po = pppox_sk(sk); struct l2tp_session *session = NULL; struct l2tp_tunnel *tunnel; @@ -657,7 +651,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, if (sk->sk_user_data) goto end; /* socket is already attached */ - /* Get params from socket address. Handle L2TPv2 and L2TPv3 */ + /* Get params from socket address. Handle L2TPv2 and L2TPv3. + * This is nasty because there are different sockaddr_pppol2tp + * structs for L2TPv2, L2TPv3, over IPv4 and IPv6. We use + * the sockaddr size to determine which structure the caller + * is using. + */ + peer_tunnel_id = 0; if (sockaddr_len == sizeof(struct sockaddr_pppol2tp)) { fd = sp->pppol2tp.fd; tunnel_id = sp->pppol2tp.s_tunnel; @@ -665,12 +665,31 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, session_id = sp->pppol2tp.s_session; peer_session_id = sp->pppol2tp.d_session; } else if (sockaddr_len == sizeof(struct sockaddr_pppol2tpv3)) { + struct sockaddr_pppol2tpv3 *sp3 = + (struct sockaddr_pppol2tpv3 *) sp; ver = 3; fd = sp3->pppol2tp.fd; tunnel_id = sp3->pppol2tp.s_tunnel; peer_tunnel_id = sp3->pppol2tp.d_tunnel; session_id = sp3->pppol2tp.s_session; peer_session_id = sp3->pppol2tp.d_session; + } else if (sockaddr_len == sizeof(struct sockaddr_pppol2tpin6)) { + struct sockaddr_pppol2tpin6 *sp6 = + (struct sockaddr_pppol2tpin6 *) sp; + fd = sp6->pppol2tp.fd; + tunnel_id = sp6->pppol2tp.s_tunnel; + peer_tunnel_id = sp6->pppol2tp.d_tunnel; + session_id = sp6->pppol2tp.s_session; + peer_session_id = sp6->pppol2tp.d_session; + } else if (sockaddr_len == sizeof(struct sockaddr_pppol2tpv3in6)) { + struct sockaddr_pppol2tpv3in6 *sp6 = + (struct sockaddr_pppol2tpv3in6 *) sp; + ver = 3; + fd = sp6->pppol2tp.fd; + tunnel_id = sp6->pppol2tp.s_tunnel; + peer_tunnel_id = sp6->pppol2tp.d_tunnel; + session_id = sp6->pppol2tp.s_session; + peer_session_id = sp6->pppol2tp.d_session; } else { error = -EINVAL; goto end; /* bad socket address */ @@ -711,12 +730,8 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, if (tunnel->recv_payload_hook == NULL) tunnel->recv_payload_hook = pppol2tp_recv_payload_hook; - if (tunnel->peer_tunnel_id == 0) { - if (ver == 2) - tunnel->peer_tunnel_id = sp->pppol2tp.d_tunnel; - else - tunnel->peer_tunnel_id = sp3->pppol2tp.d_tunnel; - } + if (tunnel->peer_tunnel_id == 0) + tunnel->peer_tunnel_id = peer_tunnel_id; /* Create session if it doesn't already exist. We handle the * case where a session was previously created by the netlink @@ -807,8 +822,8 @@ out_no_ppp: /* This is how we get the session context from the socket. */ sk->sk_user_data = session; sk->sk_state = PPPOX_CONNECTED; - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: created\n", session->name); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: created\n", + session->name); end: release_sock(sk); @@ -861,8 +876,8 @@ static int pppol2tp_session_create(struct net *net, u32 tunnel_id, u32 session_i ps = l2tp_session_priv(session); ps->tunnel_sock = tunnel->sock; - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: created\n", session->name); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: created\n", + session->name); error = 0; @@ -916,7 +931,7 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, } inet = inet_sk(tunnel->sock); - if (tunnel->version == 2) { + if ((tunnel->version == 2) && (tunnel->sock->sk_family == AF_INET)) { struct sockaddr_pppol2tp sp; len = sizeof(sp); memset(&sp, 0, len); @@ -932,6 +947,46 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, sp.pppol2tp.addr.sin_port = inet->inet_dport; sp.pppol2tp.addr.sin_addr.s_addr = inet->inet_daddr; memcpy(uaddr, &sp, len); +#if IS_ENABLED(CONFIG_IPV6) + } else if ((tunnel->version == 2) && + (tunnel->sock->sk_family == AF_INET6)) { + struct ipv6_pinfo *np = inet6_sk(tunnel->sock); + struct sockaddr_pppol2tpin6 sp; + len = sizeof(sp); + memset(&sp, 0, len); + sp.sa_family = AF_PPPOX; + sp.sa_protocol = PX_PROTO_OL2TP; + sp.pppol2tp.fd = tunnel->fd; + sp.pppol2tp.pid = pls->owner; + sp.pppol2tp.s_tunnel = tunnel->tunnel_id; + sp.pppol2tp.d_tunnel = tunnel->peer_tunnel_id; + sp.pppol2tp.s_session = session->session_id; + sp.pppol2tp.d_session = session->peer_session_id; + sp.pppol2tp.addr.sin6_family = AF_INET6; + sp.pppol2tp.addr.sin6_port = inet->inet_dport; + memcpy(&sp.pppol2tp.addr.sin6_addr, &np->daddr, + sizeof(np->daddr)); + memcpy(uaddr, &sp, len); + } else if ((tunnel->version == 3) && + (tunnel->sock->sk_family == AF_INET6)) { + struct ipv6_pinfo *np = inet6_sk(tunnel->sock); + struct sockaddr_pppol2tpv3in6 sp; + len = sizeof(sp); + memset(&sp, 0, len); + sp.sa_family = AF_PPPOX; + sp.sa_protocol = PX_PROTO_OL2TP; + sp.pppol2tp.fd = tunnel->fd; + sp.pppol2tp.pid = pls->owner; + sp.pppol2tp.s_tunnel = tunnel->tunnel_id; + sp.pppol2tp.d_tunnel = tunnel->peer_tunnel_id; + sp.pppol2tp.s_session = session->session_id; + sp.pppol2tp.d_session = session->peer_session_id; + sp.pppol2tp.addr.sin6_family = AF_INET6; + sp.pppol2tp.addr.sin6_port = inet->inet_dport; + memcpy(&sp.pppol2tp.addr.sin6_addr, &np->daddr, + sizeof(np->daddr)); + memcpy(uaddr, &sp, len); +#endif } else if (tunnel->version == 3) { struct sockaddr_pppol2tpv3 sp; len = sizeof(sp); @@ -998,9 +1053,9 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session, struct l2tp_tunnel *tunnel = session->tunnel; struct pppol2tp_ioc_stats stats; - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_DEBUG, - "%s: pppol2tp_session_ioctl(cmd=%#x, arg=%#lx)\n", - session->name, cmd, arg); + l2tp_dbg(session, PPPOL2TP_MSG_CONTROL, + "%s: pppol2tp_session_ioctl(cmd=%#x, arg=%#lx)\n", + session->name, cmd, arg); sk = ps->sock; sock_hold(sk); @@ -1018,8 +1073,8 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session, if (copy_to_user((void __user *) arg, &ifr, sizeof(struct ifreq))) break; - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: get mtu=%d\n", session->name, session->mtu); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: get mtu=%d\n", + session->name, session->mtu); err = 0; break; @@ -1034,8 +1089,8 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session, session->mtu = ifr.ifr_mtu; - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: set mtu=%d\n", session->name, session->mtu); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: set mtu=%d\n", + session->name, session->mtu); err = 0; break; @@ -1048,8 +1103,8 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session, if (put_user(session->mru, (int __user *) arg)) break; - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: get mru=%d\n", session->name, session->mru); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: get mru=%d\n", + session->name, session->mru); err = 0; break; @@ -1063,8 +1118,8 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session, break; session->mru = val; - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: set mru=%d\n", session->name, session->mru); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: set mru=%d\n", + session->name, session->mru); err = 0; break; @@ -1073,8 +1128,8 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session, if (put_user(ps->flags, (int __user *) arg)) break; - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: get flags=%d\n", session->name, ps->flags); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: get flags=%d\n", + session->name, ps->flags); err = 0; break; @@ -1083,8 +1138,8 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session, if (get_user(val, (int __user *) arg)) break; ps->flags = val; - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: set flags=%d\n", session->name, ps->flags); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: set flags=%d\n", + session->name, ps->flags); err = 0; break; @@ -1100,8 +1155,8 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session, if (copy_to_user((void __user *) arg, &stats, sizeof(stats))) break; - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: get L2TP stats\n", session->name); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: get L2TP stats\n", + session->name); err = 0; break; @@ -1128,9 +1183,9 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel, struct sock *sk; struct pppol2tp_ioc_stats stats; - PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_DEBUG, - "%s: pppol2tp_tunnel_ioctl(cmd=%#x, arg=%#lx)\n", - tunnel->name, cmd, arg); + l2tp_dbg(tunnel, PPPOL2TP_MSG_CONTROL, + "%s: pppol2tp_tunnel_ioctl(cmd=%#x, arg=%#lx)\n", + tunnel->name, cmd, arg); sk = tunnel->sock; sock_hold(sk); @@ -1164,8 +1219,8 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel, err = -EFAULT; break; } - PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: get L2TP stats\n", tunnel->name); + l2tp_info(tunnel, PPPOL2TP_MSG_CONTROL, "%s: get L2TP stats\n", + tunnel->name); err = 0; break; @@ -1254,8 +1309,8 @@ static int pppol2tp_tunnel_setsockopt(struct sock *sk, switch (optname) { case PPPOL2TP_SO_DEBUG: tunnel->debug = val; - PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: set debug=%x\n", tunnel->name, tunnel->debug); + l2tp_info(tunnel, PPPOL2TP_MSG_CONTROL, "%s: set debug=%x\n", + tunnel->name, tunnel->debug); break; default: @@ -1282,8 +1337,9 @@ static int pppol2tp_session_setsockopt(struct sock *sk, break; } session->recv_seq = val ? -1 : 0; - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: set recv_seq=%d\n", session->name, session->recv_seq); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, + "%s: set recv_seq=%d\n", + session->name, session->recv_seq); break; case PPPOL2TP_SO_SENDSEQ: @@ -1298,8 +1354,9 @@ static int pppol2tp_session_setsockopt(struct sock *sk, po->chan.hdrlen = val ? PPPOL2TP_L2TP_HDR_SIZE_SEQ : PPPOL2TP_L2TP_HDR_SIZE_NOSEQ; } - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: set send_seq=%d\n", session->name, session->send_seq); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, + "%s: set send_seq=%d\n", + session->name, session->send_seq); break; case PPPOL2TP_SO_LNSMODE: @@ -1308,20 +1365,22 @@ static int pppol2tp_session_setsockopt(struct sock *sk, break; } session->lns_mode = val ? -1 : 0; - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: set lns_mode=%d\n", session->name, session->lns_mode); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, + "%s: set lns_mode=%d\n", + session->name, session->lns_mode); break; case PPPOL2TP_SO_DEBUG: session->debug = val; - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: set debug=%x\n", session->name, session->debug); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: set debug=%x\n", + session->name, session->debug); break; case PPPOL2TP_SO_REORDERTO: session->reorder_timeout = msecs_to_jiffies(val); - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: set reorder_timeout=%d\n", session->name, session->reorder_timeout); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, + "%s: set reorder_timeout=%d\n", + session->name, session->reorder_timeout); break; default: @@ -1400,8 +1459,8 @@ static int pppol2tp_tunnel_getsockopt(struct sock *sk, switch (optname) { case PPPOL2TP_SO_DEBUG: *val = tunnel->debug; - PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: get debug=%x\n", tunnel->name, tunnel->debug); + l2tp_info(tunnel, PPPOL2TP_MSG_CONTROL, "%s: get debug=%x\n", + tunnel->name, tunnel->debug); break; default: @@ -1423,32 +1482,32 @@ static int pppol2tp_session_getsockopt(struct sock *sk, switch (optname) { case PPPOL2TP_SO_RECVSEQ: *val = session->recv_seq; - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: get recv_seq=%d\n", session->name, *val); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, + "%s: get recv_seq=%d\n", session->name, *val); break; case PPPOL2TP_SO_SENDSEQ: *val = session->send_seq; - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: get send_seq=%d\n", session->name, *val); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, + "%s: get send_seq=%d\n", session->name, *val); break; case PPPOL2TP_SO_LNSMODE: *val = session->lns_mode; - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: get lns_mode=%d\n", session->name, *val); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, + "%s: get lns_mode=%d\n", session->name, *val); break; case PPPOL2TP_SO_DEBUG: *val = session->debug; - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: get debug=%d\n", session->name, *val); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: get debug=%d\n", + session->name, *val); break; case PPPOL2TP_SO_REORDERTO: *val = (int) jiffies_to_msecs(session->reorder_timeout); - PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO, - "%s: get reorder_timeout=%d\n", session->name, *val); + l2tp_info(session, PPPOL2TP_MSG_CONTROL, + "%s: get reorder_timeout=%d\n", session->name, *val); break; default: @@ -1811,8 +1870,7 @@ static int __init pppol2tp_init(void) goto out_unregister_pppox; #endif - printk(KERN_INFO "PPPoL2TP kernel driver, %s\n", - PPPOL2TP_DRV_VERSION); + pr_info("PPPoL2TP kernel driver, %s\n", PPPOL2TP_DRV_VERSION); out: return err; diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c index ab3d35f2325..3cdaa046c1b 100644 --- a/net/lapb/lapb_iface.c +++ b/net/lapb/lapb_iface.c @@ -15,6 +15,8 @@ * 2000-10-29 Henner Eisen lapb_data_indication() return status. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> @@ -279,9 +281,7 @@ int lapb_connect_request(struct net_device *dev) lapb_establish_data_link(lapb); -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S0 -> S1\n", lapb->dev); -#endif + lapb_dbg(0, "(%p) S0 -> S1\n", lapb->dev); lapb->state = LAPB_STATE_1; rc = LAPB_OK; @@ -305,12 +305,8 @@ int lapb_disconnect_request(struct net_device *dev) goto out_put; case LAPB_STATE_1: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 TX DISC(1)\n", lapb->dev); -#endif -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S1 -> S0\n", lapb->dev); -#endif + lapb_dbg(1, "(%p) S1 TX DISC(1)\n", lapb->dev); + lapb_dbg(0, "(%p) S1 -> S0\n", lapb->dev); lapb_send_control(lapb, LAPB_DISC, LAPB_POLLON, LAPB_COMMAND); lapb->state = LAPB_STATE_0; lapb_start_t1timer(lapb); @@ -329,12 +325,8 @@ int lapb_disconnect_request(struct net_device *dev) lapb_stop_t2timer(lapb); lapb->state = LAPB_STATE_2; -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 DISC(1)\n", lapb->dev); -#endif -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S3 -> S2\n", lapb->dev); -#endif + lapb_dbg(1, "(%p) S3 DISC(1)\n", lapb->dev); + lapb_dbg(0, "(%p) S3 -> S2\n", lapb->dev); rc = LAPB_OK; out_put: diff --git a/net/lapb/lapb_in.c b/net/lapb/lapb_in.c index f4e3c1accab..5dba899131b 100644 --- a/net/lapb/lapb_in.c +++ b/net/lapb/lapb_in.c @@ -15,6 +15,8 @@ * 2000-10-29 Henner Eisen lapb_data_indication() return status. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> @@ -44,25 +46,16 @@ static void lapb_state0_machine(struct lapb_cb *lapb, struct sk_buff *skb, { switch (frame->type) { case LAPB_SABM: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S0 RX SABM(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S0 RX SABM(%d)\n", lapb->dev, frame->pf); if (lapb->mode & LAPB_EXTENDED) { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S0 TX DM(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S0 TX DM(%d)\n", + lapb->dev, frame->pf); lapb_send_control(lapb, LAPB_DM, frame->pf, LAPB_RESPONSE); } else { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S0 TX UA(%d)\n", - lapb->dev, frame->pf); -#endif -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S0 -> S3\n", lapb->dev); -#endif + lapb_dbg(1, "(%p) S0 TX UA(%d)\n", + lapb->dev, frame->pf); + lapb_dbg(0, "(%p) S0 -> S3\n", lapb->dev); lapb_send_control(lapb, LAPB_UA, frame->pf, LAPB_RESPONSE); lapb_stop_t1timer(lapb); @@ -78,18 +71,11 @@ static void lapb_state0_machine(struct lapb_cb *lapb, struct sk_buff *skb, break; case LAPB_SABME: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S0 RX SABME(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S0 RX SABME(%d)\n", lapb->dev, frame->pf); if (lapb->mode & LAPB_EXTENDED) { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S0 TX UA(%d)\n", - lapb->dev, frame->pf); -#endif -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S0 -> S3\n", lapb->dev); -#endif + lapb_dbg(1, "(%p) S0 TX UA(%d)\n", + lapb->dev, frame->pf); + lapb_dbg(0, "(%p) S0 -> S3\n", lapb->dev); lapb_send_control(lapb, LAPB_UA, frame->pf, LAPB_RESPONSE); lapb_stop_t1timer(lapb); @@ -102,22 +88,16 @@ static void lapb_state0_machine(struct lapb_cb *lapb, struct sk_buff *skb, lapb->va = 0; lapb_connect_indication(lapb, LAPB_OK); } else { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S0 TX DM(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S0 TX DM(%d)\n", + lapb->dev, frame->pf); lapb_send_control(lapb, LAPB_DM, frame->pf, LAPB_RESPONSE); } break; case LAPB_DISC: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S0 RX DISC(%d)\n", - lapb->dev, frame->pf); - printk(KERN_DEBUG "lapb: (%p) S0 TX UA(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S0 RX DISC(%d)\n", lapb->dev, frame->pf); + lapb_dbg(1, "(%p) S0 TX UA(%d)\n", lapb->dev, frame->pf); lapb_send_control(lapb, LAPB_UA, frame->pf, LAPB_RESPONSE); break; @@ -137,68 +117,45 @@ static void lapb_state1_machine(struct lapb_cb *lapb, struct sk_buff *skb, { switch (frame->type) { case LAPB_SABM: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 RX SABM(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S1 RX SABM(%d)\n", lapb->dev, frame->pf); if (lapb->mode & LAPB_EXTENDED) { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 TX DM(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S1 TX DM(%d)\n", + lapb->dev, frame->pf); lapb_send_control(lapb, LAPB_DM, frame->pf, LAPB_RESPONSE); } else { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 TX UA(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S1 TX UA(%d)\n", + lapb->dev, frame->pf); lapb_send_control(lapb, LAPB_UA, frame->pf, LAPB_RESPONSE); } break; case LAPB_SABME: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 RX SABME(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S1 RX SABME(%d)\n", lapb->dev, frame->pf); if (lapb->mode & LAPB_EXTENDED) { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 TX UA(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S1 TX UA(%d)\n", + lapb->dev, frame->pf); lapb_send_control(lapb, LAPB_UA, frame->pf, LAPB_RESPONSE); } else { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 TX DM(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S1 TX DM(%d)\n", + lapb->dev, frame->pf); lapb_send_control(lapb, LAPB_DM, frame->pf, LAPB_RESPONSE); } break; case LAPB_DISC: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 RX DISC(%d)\n", - lapb->dev, frame->pf); - printk(KERN_DEBUG "lapb: (%p) S1 TX DM(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S1 RX DISC(%d)\n", lapb->dev, frame->pf); + lapb_dbg(1, "(%p) S1 TX DM(%d)\n", lapb->dev, frame->pf); lapb_send_control(lapb, LAPB_DM, frame->pf, LAPB_RESPONSE); break; case LAPB_UA: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 RX UA(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S1 RX UA(%d)\n", lapb->dev, frame->pf); if (frame->pf) { -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S1 -> S3\n", lapb->dev); -#endif + lapb_dbg(0, "(%p) S1 -> S3\n", lapb->dev); lapb_stop_t1timer(lapb); lapb_stop_t2timer(lapb); lapb->state = LAPB_STATE_3; @@ -212,14 +169,9 @@ static void lapb_state1_machine(struct lapb_cb *lapb, struct sk_buff *skb, break; case LAPB_DM: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 RX DM(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S1 RX DM(%d)\n", lapb->dev, frame->pf); if (frame->pf) { -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S1 -> S0\n", lapb->dev); -#endif + lapb_dbg(0, "(%p) S1 -> S0\n", lapb->dev); lapb_clear_queues(lapb); lapb->state = LAPB_STATE_0; lapb_start_t1timer(lapb); @@ -242,34 +194,22 @@ static void lapb_state2_machine(struct lapb_cb *lapb, struct sk_buff *skb, switch (frame->type) { case LAPB_SABM: case LAPB_SABME: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S2 RX {SABM,SABME}(%d)\n", - lapb->dev, frame->pf); - printk(KERN_DEBUG "lapb: (%p) S2 TX DM(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S2 RX {SABM,SABME}(%d)\n", + lapb->dev, frame->pf); + lapb_dbg(1, "(%p) S2 TX DM(%d)\n", lapb->dev, frame->pf); lapb_send_control(lapb, LAPB_DM, frame->pf, LAPB_RESPONSE); break; case LAPB_DISC: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S2 RX DISC(%d)\n", - lapb->dev, frame->pf); - printk(KERN_DEBUG "lapb: (%p) S2 TX UA(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S2 RX DISC(%d)\n", lapb->dev, frame->pf); + lapb_dbg(1, "(%p) S2 TX UA(%d)\n", lapb->dev, frame->pf); lapb_send_control(lapb, LAPB_UA, frame->pf, LAPB_RESPONSE); break; case LAPB_UA: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S2 RX UA(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S2 RX UA(%d)\n", lapb->dev, frame->pf); if (frame->pf) { -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S2 -> S0\n", lapb->dev); -#endif + lapb_dbg(0, "(%p) S2 -> S0\n", lapb->dev); lapb->state = LAPB_STATE_0; lapb_start_t1timer(lapb); lapb_stop_t2timer(lapb); @@ -278,14 +218,9 @@ static void lapb_state2_machine(struct lapb_cb *lapb, struct sk_buff *skb, break; case LAPB_DM: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S2 RX DM(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S2 RX DM(%d)\n", lapb->dev, frame->pf); if (frame->pf) { -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S2 -> S0\n", lapb->dev); -#endif + lapb_dbg(0, "(%p) S2 -> S0\n", lapb->dev); lapb->state = LAPB_STATE_0; lapb_start_t1timer(lapb); lapb_stop_t2timer(lapb); @@ -297,12 +232,9 @@ static void lapb_state2_machine(struct lapb_cb *lapb, struct sk_buff *skb, case LAPB_REJ: case LAPB_RNR: case LAPB_RR: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S2 RX {I,REJ,RNR,RR}(%d)\n", - lapb->dev, frame->pf); - printk(KERN_DEBUG "lapb: (%p) S2 RX DM(%d)\n", + lapb_dbg(1, "(%p) S2 RX {I,REJ,RNR,RR}(%d)\n", lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S2 RX DM(%d)\n", lapb->dev, frame->pf); if (frame->pf) lapb_send_control(lapb, LAPB_DM, frame->pf, LAPB_RESPONSE); @@ -325,22 +257,15 @@ static void lapb_state3_machine(struct lapb_cb *lapb, struct sk_buff *skb, switch (frame->type) { case LAPB_SABM: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX SABM(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S3 RX SABM(%d)\n", lapb->dev, frame->pf); if (lapb->mode & LAPB_EXTENDED) { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 TX DM(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S3 TX DM(%d)\n", + lapb->dev, frame->pf); lapb_send_control(lapb, LAPB_DM, frame->pf, LAPB_RESPONSE); } else { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 TX UA(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S3 TX UA(%d)\n", + lapb->dev, frame->pf); lapb_send_control(lapb, LAPB_UA, frame->pf, LAPB_RESPONSE); lapb_stop_t1timer(lapb); @@ -355,15 +280,10 @@ static void lapb_state3_machine(struct lapb_cb *lapb, struct sk_buff *skb, break; case LAPB_SABME: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX SABME(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S3 RX SABME(%d)\n", lapb->dev, frame->pf); if (lapb->mode & LAPB_EXTENDED) { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 TX UA(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S3 TX UA(%d)\n", + lapb->dev, frame->pf); lapb_send_control(lapb, LAPB_UA, frame->pf, LAPB_RESPONSE); lapb_stop_t1timer(lapb); @@ -375,23 +295,16 @@ static void lapb_state3_machine(struct lapb_cb *lapb, struct sk_buff *skb, lapb->va = 0; lapb_requeue_frames(lapb); } else { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 TX DM(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S3 TX DM(%d)\n", + lapb->dev, frame->pf); lapb_send_control(lapb, LAPB_DM, frame->pf, LAPB_RESPONSE); } break; case LAPB_DISC: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX DISC(%d)\n", - lapb->dev, frame->pf); -#endif -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S3 -> S0\n", lapb->dev); -#endif + lapb_dbg(1, "(%p) S3 RX DISC(%d)\n", lapb->dev, frame->pf); + lapb_dbg(0, "(%p) S3 -> S0\n", lapb->dev); lapb_clear_queues(lapb); lapb_send_control(lapb, LAPB_UA, frame->pf, LAPB_RESPONSE); lapb_start_t1timer(lapb); @@ -401,13 +314,8 @@ static void lapb_state3_machine(struct lapb_cb *lapb, struct sk_buff *skb, break; case LAPB_DM: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX DM(%d)\n", - lapb->dev, frame->pf); -#endif -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S3 -> S0\n", lapb->dev); -#endif + lapb_dbg(1, "(%p) S3 RX DM(%d)\n", lapb->dev, frame->pf); + lapb_dbg(0, "(%p) S3 -> S0\n", lapb->dev); lapb_clear_queues(lapb); lapb->state = LAPB_STATE_0; lapb_start_t1timer(lapb); @@ -416,10 +324,8 @@ static void lapb_state3_machine(struct lapb_cb *lapb, struct sk_buff *skb, break; case LAPB_RNR: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX RNR(%d) R%d\n", - lapb->dev, frame->pf, frame->nr); -#endif + lapb_dbg(1, "(%p) S3 RX RNR(%d) R%d\n", + lapb->dev, frame->pf, frame->nr); lapb->condition |= LAPB_PEER_RX_BUSY_CONDITION; lapb_check_need_response(lapb, frame->cr, frame->pf); if (lapb_validate_nr(lapb, frame->nr)) { @@ -428,9 +334,7 @@ static void lapb_state3_machine(struct lapb_cb *lapb, struct sk_buff *skb, lapb->frmr_data = *frame; lapb->frmr_type = LAPB_FRMR_Z; lapb_transmit_frmr(lapb); -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S3 -> S4\n", lapb->dev); -#endif + lapb_dbg(0, "(%p) S3 -> S4\n", lapb->dev); lapb_start_t1timer(lapb); lapb_stop_t2timer(lapb); lapb->state = LAPB_STATE_4; @@ -439,10 +343,8 @@ static void lapb_state3_machine(struct lapb_cb *lapb, struct sk_buff *skb, break; case LAPB_RR: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX RR(%d) R%d\n", - lapb->dev, frame->pf, frame->nr); -#endif + lapb_dbg(1, "(%p) S3 RX RR(%d) R%d\n", + lapb->dev, frame->pf, frame->nr); lapb->condition &= ~LAPB_PEER_RX_BUSY_CONDITION; lapb_check_need_response(lapb, frame->cr, frame->pf); if (lapb_validate_nr(lapb, frame->nr)) { @@ -451,9 +353,7 @@ static void lapb_state3_machine(struct lapb_cb *lapb, struct sk_buff *skb, lapb->frmr_data = *frame; lapb->frmr_type = LAPB_FRMR_Z; lapb_transmit_frmr(lapb); -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S3 -> S4\n", lapb->dev); -#endif + lapb_dbg(0, "(%p) S3 -> S4\n", lapb->dev); lapb_start_t1timer(lapb); lapb_stop_t2timer(lapb); lapb->state = LAPB_STATE_4; @@ -462,10 +362,8 @@ static void lapb_state3_machine(struct lapb_cb *lapb, struct sk_buff *skb, break; case LAPB_REJ: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX REJ(%d) R%d\n", - lapb->dev, frame->pf, frame->nr); -#endif + lapb_dbg(1, "(%p) S3 RX REJ(%d) R%d\n", + lapb->dev, frame->pf, frame->nr); lapb->condition &= ~LAPB_PEER_RX_BUSY_CONDITION; lapb_check_need_response(lapb, frame->cr, frame->pf); if (lapb_validate_nr(lapb, frame->nr)) { @@ -477,9 +375,7 @@ static void lapb_state3_machine(struct lapb_cb *lapb, struct sk_buff *skb, lapb->frmr_data = *frame; lapb->frmr_type = LAPB_FRMR_Z; lapb_transmit_frmr(lapb); -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S3 -> S4\n", lapb->dev); -#endif + lapb_dbg(0, "(%p) S3 -> S4\n", lapb->dev); lapb_start_t1timer(lapb); lapb_stop_t2timer(lapb); lapb->state = LAPB_STATE_4; @@ -488,17 +384,13 @@ static void lapb_state3_machine(struct lapb_cb *lapb, struct sk_buff *skb, break; case LAPB_I: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX I(%d) S%d R%d\n", - lapb->dev, frame->pf, frame->ns, frame->nr); -#endif + lapb_dbg(1, "(%p) S3 RX I(%d) S%d R%d\n", + lapb->dev, frame->pf, frame->ns, frame->nr); if (!lapb_validate_nr(lapb, frame->nr)) { lapb->frmr_data = *frame; lapb->frmr_type = LAPB_FRMR_Z; lapb_transmit_frmr(lapb); -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S3 -> S4\n", lapb->dev); -#endif + lapb_dbg(0, "(%p) S3 -> S4\n", lapb->dev); lapb_start_t1timer(lapb); lapb_stop_t2timer(lapb); lapb->state = LAPB_STATE_4; @@ -522,7 +414,7 @@ static void lapb_state3_machine(struct lapb_cb *lapb, struct sk_buff *skb, * a frame lost on the wire. */ if (cn == NET_RX_DROP) { - printk(KERN_DEBUG "LAPB: rx congestion\n"); + pr_debug("rx congestion\n"); break; } lapb->vr = (lapb->vr + 1) % modulus; @@ -541,11 +433,8 @@ static void lapb_state3_machine(struct lapb_cb *lapb, struct sk_buff *skb, if (frame->pf) lapb_enquiry_response(lapb); } else { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG - "lapb: (%p) S3 TX REJ(%d) R%d\n", - lapb->dev, frame->pf, lapb->vr); -#endif + lapb_dbg(1, "(%p) S3 TX REJ(%d) R%d\n", + lapb->dev, frame->pf, lapb->vr); lapb->condition |= LAPB_REJECT_CONDITION; lapb_send_control(lapb, LAPB_REJ, frame->pf, LAPB_RESPONSE); @@ -555,31 +444,22 @@ static void lapb_state3_machine(struct lapb_cb *lapb, struct sk_buff *skb, break; case LAPB_FRMR: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX FRMR(%d) %02X " - "%02X %02X %02X %02X\n", lapb->dev, frame->pf, - skb->data[0], skb->data[1], skb->data[2], - skb->data[3], skb->data[4]); -#endif + lapb_dbg(1, "(%p) S3 RX FRMR(%d) %02X %02X %02X %02X %02X\n", + lapb->dev, frame->pf, + skb->data[0], skb->data[1], skb->data[2], + skb->data[3], skb->data[4]); lapb_establish_data_link(lapb); -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S3 -> S1\n", lapb->dev); -#endif + lapb_dbg(0, "(%p) S3 -> S1\n", lapb->dev); lapb_requeue_frames(lapb); lapb->state = LAPB_STATE_1; break; case LAPB_ILLEGAL: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX ILLEGAL(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S3 RX ILLEGAL(%d)\n", lapb->dev, frame->pf); lapb->frmr_data = *frame; lapb->frmr_type = LAPB_FRMR_W; lapb_transmit_frmr(lapb); -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S3 -> S4\n", lapb->dev); -#endif + lapb_dbg(0, "(%p) S3 -> S4\n", lapb->dev); lapb_start_t1timer(lapb); lapb_stop_t2timer(lapb); lapb->state = LAPB_STATE_4; @@ -600,25 +480,16 @@ static void lapb_state4_machine(struct lapb_cb *lapb, struct sk_buff *skb, { switch (frame->type) { case LAPB_SABM: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S4 RX SABM(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S4 RX SABM(%d)\n", lapb->dev, frame->pf); if (lapb->mode & LAPB_EXTENDED) { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S4 TX DM(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S4 TX DM(%d)\n", + lapb->dev, frame->pf); lapb_send_control(lapb, LAPB_DM, frame->pf, LAPB_RESPONSE); } else { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S4 TX UA(%d)\n", - lapb->dev, frame->pf); -#endif -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S4 -> S3\n", lapb->dev); -#endif + lapb_dbg(1, "(%p) S4 TX UA(%d)\n", + lapb->dev, frame->pf); + lapb_dbg(0, "(%p) S4 -> S3\n", lapb->dev); lapb_send_control(lapb, LAPB_UA, frame->pf, LAPB_RESPONSE); lapb_stop_t1timer(lapb); @@ -634,18 +505,11 @@ static void lapb_state4_machine(struct lapb_cb *lapb, struct sk_buff *skb, break; case LAPB_SABME: -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S4 RX SABME(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S4 RX SABME(%d)\n", lapb->dev, frame->pf); if (lapb->mode & LAPB_EXTENDED) { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S4 TX UA(%d)\n", - lapb->dev, frame->pf); -#endif -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S4 -> S3\n", lapb->dev); -#endif + lapb_dbg(1, "(%p) S4 TX UA(%d)\n", + lapb->dev, frame->pf); + lapb_dbg(0, "(%p) S4 -> S3\n", lapb->dev); lapb_send_control(lapb, LAPB_UA, frame->pf, LAPB_RESPONSE); lapb_stop_t1timer(lapb); @@ -658,10 +522,8 @@ static void lapb_state4_machine(struct lapb_cb *lapb, struct sk_buff *skb, lapb->va = 0; lapb_connect_indication(lapb, LAPB_OK); } else { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S4 TX DM(%d)\n", - lapb->dev, frame->pf); -#endif + lapb_dbg(1, "(%p) S4 TX DM(%d)\n", + lapb->dev, frame->pf); lapb_send_control(lapb, LAPB_DM, frame->pf, LAPB_RESPONSE); } diff --git a/net/lapb/lapb_out.c b/net/lapb/lapb_out.c index baab2760f65..ba4d015bd1a 100644 --- a/net/lapb/lapb_out.c +++ b/net/lapb/lapb_out.c @@ -14,6 +14,8 @@ * LAPB 002 Jonathan Naylor New timer architecture. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> @@ -60,10 +62,8 @@ static void lapb_send_iframe(struct lapb_cb *lapb, struct sk_buff *skb, int poll *frame |= lapb->vs << 1; } -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S%d TX I(%d) S%d R%d\n", - lapb->dev, lapb->state, poll_bit, lapb->vs, lapb->vr); -#endif + lapb_dbg(1, "(%p) S%d TX I(%d) S%d R%d\n", + lapb->dev, lapb->state, poll_bit, lapb->vs, lapb->vr); lapb_transmit_buffer(lapb, skb, LAPB_COMMAND); } @@ -148,11 +148,9 @@ void lapb_transmit_buffer(struct lapb_cb *lapb, struct sk_buff *skb, int type) } } -#if LAPB_DEBUG > 2 - printk(KERN_DEBUG "lapb: (%p) S%d TX %02X %02X %02X\n", - lapb->dev, lapb->state, - skb->data[0], skb->data[1], skb->data[2]); -#endif + lapb_dbg(2, "(%p) S%d TX %02X %02X %02X\n", + lapb->dev, lapb->state, + skb->data[0], skb->data[1], skb->data[2]); if (!lapb_data_transmit(lapb, skb)) kfree_skb(skb); @@ -164,16 +162,10 @@ void lapb_establish_data_link(struct lapb_cb *lapb) lapb->n2count = 0; if (lapb->mode & LAPB_EXTENDED) { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S%d TX SABME(1)\n", - lapb->dev, lapb->state); -#endif + lapb_dbg(1, "(%p) S%d TX SABME(1)\n", lapb->dev, lapb->state); lapb_send_control(lapb, LAPB_SABME, LAPB_POLLON, LAPB_COMMAND); } else { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S%d TX SABM(1)\n", - lapb->dev, lapb->state); -#endif + lapb_dbg(1, "(%p) S%d TX SABM(1)\n", lapb->dev, lapb->state); lapb_send_control(lapb, LAPB_SABM, LAPB_POLLON, LAPB_COMMAND); } @@ -183,10 +175,8 @@ void lapb_establish_data_link(struct lapb_cb *lapb) void lapb_enquiry_response(struct lapb_cb *lapb) { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S%d TX RR(1) R%d\n", - lapb->dev, lapb->state, lapb->vr); -#endif + lapb_dbg(1, "(%p) S%d TX RR(1) R%d\n", + lapb->dev, lapb->state, lapb->vr); lapb_send_control(lapb, LAPB_RR, LAPB_POLLON, LAPB_RESPONSE); @@ -195,10 +185,8 @@ void lapb_enquiry_response(struct lapb_cb *lapb) void lapb_timeout_response(struct lapb_cb *lapb) { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S%d TX RR(0) R%d\n", - lapb->dev, lapb->state, lapb->vr); -#endif + lapb_dbg(1, "(%p) S%d TX RR(0) R%d\n", + lapb->dev, lapb->state, lapb->vr); lapb_send_control(lapb, LAPB_RR, LAPB_POLLOFF, LAPB_RESPONSE); lapb->condition &= ~LAPB_ACK_PENDING_CONDITION; diff --git a/net/lapb/lapb_subr.c b/net/lapb/lapb_subr.c index 066225b4e82..9d0a426eccb 100644 --- a/net/lapb/lapb_subr.c +++ b/net/lapb/lapb_subr.c @@ -13,6 +13,8 @@ * LAPB 001 Jonathan Naylor Started Coding */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> @@ -111,11 +113,9 @@ int lapb_decode(struct lapb_cb *lapb, struct sk_buff *skb, { frame->type = LAPB_ILLEGAL; -#if LAPB_DEBUG > 2 - printk(KERN_DEBUG "lapb: (%p) S%d RX %02X %02X %02X\n", - lapb->dev, lapb->state, - skb->data[0], skb->data[1], skb->data[2]); -#endif + lapb_dbg(2, "(%p) S%d RX %02X %02X %02X\n", + lapb->dev, lapb->state, + skb->data[0], skb->data[1], skb->data[2]); /* We always need to look at 2 bytes, sometimes we need * to look at 3 and those cases are handled below. @@ -284,12 +284,10 @@ void lapb_transmit_frmr(struct lapb_cb *lapb) dptr++; *dptr++ = lapb->frmr_type; -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S%d TX FRMR %02X %02X %02X %02X %02X\n", - lapb->dev, lapb->state, - skb->data[1], skb->data[2], skb->data[3], - skb->data[4], skb->data[5]); -#endif + lapb_dbg(1, "(%p) S%d TX FRMR %02X %02X %02X %02X %02X\n", + lapb->dev, lapb->state, + skb->data[1], skb->data[2], skb->data[3], + skb->data[4], skb->data[5]); } else { dptr = skb_put(skb, 4); *dptr++ = LAPB_FRMR; @@ -301,11 +299,9 @@ void lapb_transmit_frmr(struct lapb_cb *lapb) dptr++; *dptr++ = lapb->frmr_type; -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S%d TX FRMR %02X %02X %02X\n", - lapb->dev, lapb->state, skb->data[1], - skb->data[2], skb->data[3]); -#endif + lapb_dbg(1, "(%p) S%d TX FRMR %02X %02X %02X\n", + lapb->dev, lapb->state, skb->data[1], + skb->data[2], skb->data[3]); } lapb_transmit_buffer(lapb, skb, LAPB_RESPONSE); diff --git a/net/lapb/lapb_timer.c b/net/lapb/lapb_timer.c index f8cd641dfc8..54563ad8aeb 100644 --- a/net/lapb/lapb_timer.c +++ b/net/lapb/lapb_timer.c @@ -14,6 +14,8 @@ * LAPB 002 Jonathan Naylor New timer architecture. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> @@ -105,21 +107,17 @@ static void lapb_t1timer_expiry(unsigned long param) lapb_clear_queues(lapb); lapb->state = LAPB_STATE_0; lapb_disconnect_indication(lapb, LAPB_TIMEDOUT); -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S1 -> S0\n", lapb->dev); -#endif + lapb_dbg(0, "(%p) S1 -> S0\n", lapb->dev); return; } else { lapb->n2count++; if (lapb->mode & LAPB_EXTENDED) { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 TX SABME(1)\n", lapb->dev); -#endif + lapb_dbg(1, "(%p) S1 TX SABME(1)\n", + lapb->dev); lapb_send_control(lapb, LAPB_SABME, LAPB_POLLON, LAPB_COMMAND); } else { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 TX SABM(1)\n", lapb->dev); -#endif + lapb_dbg(1, "(%p) S1 TX SABM(1)\n", + lapb->dev); lapb_send_control(lapb, LAPB_SABM, LAPB_POLLON, LAPB_COMMAND); } } @@ -133,15 +131,11 @@ static void lapb_t1timer_expiry(unsigned long param) lapb_clear_queues(lapb); lapb->state = LAPB_STATE_0; lapb_disconnect_confirmation(lapb, LAPB_TIMEDOUT); -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S2 -> S0\n", lapb->dev); -#endif + lapb_dbg(0, "(%p) S2 -> S0\n", lapb->dev); return; } else { lapb->n2count++; -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S2 TX DISC(1)\n", lapb->dev); -#endif + lapb_dbg(1, "(%p) S2 TX DISC(1)\n", lapb->dev); lapb_send_control(lapb, LAPB_DISC, LAPB_POLLON, LAPB_COMMAND); } break; @@ -155,9 +149,7 @@ static void lapb_t1timer_expiry(unsigned long param) lapb->state = LAPB_STATE_0; lapb_stop_t2timer(lapb); lapb_disconnect_indication(lapb, LAPB_TIMEDOUT); -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S3 -> S0\n", lapb->dev); -#endif + lapb_dbg(0, "(%p) S3 -> S0\n", lapb->dev); return; } else { lapb->n2count++; @@ -173,9 +165,7 @@ static void lapb_t1timer_expiry(unsigned long param) lapb_clear_queues(lapb); lapb->state = LAPB_STATE_0; lapb_disconnect_indication(lapb, LAPB_TIMEDOUT); -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S4 -> S0\n", lapb->dev); -#endif + lapb_dbg(0, "(%p) S4 -> S0\n", lapb->dev); return; } else { lapb->n2count++; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index b9bef2c7502..fe5453c3e71 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -71,8 +71,7 @@ static inline u16 llc_ui_next_link_no(int sap) */ static inline __be16 llc_proto_type(u16 arphrd) { - return arphrd == ARPHRD_IEEE802_TR ? - htons(ETH_P_TR_802_2) : htons(ETH_P_802_2); + return htons(ETH_P_802_2); } /** @@ -518,7 +517,7 @@ static int llc_ui_listen(struct socket *sock, int backlog) if (sock_flag(sk, SOCK_ZAPPED)) goto out; rc = 0; - if (!(unsigned)backlog) /* BSDism */ + if (!(unsigned int)backlog) /* BSDism */ backlog = 1; sk->sk_max_ack_backlog = backlog; if (sk->sk_state != TCP_LISTEN) { @@ -806,10 +805,9 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, sk_wait_data(sk, &timeo); if ((flags & MSG_PEEK) && peek_seq != llc->copied_seq) { - if (net_ratelimit()) - printk(KERN_DEBUG "LLC(%s:%d): Application " - "bug, race in MSG_PEEK.\n", - current->comm, task_pid_nr(current)); + net_dbg_ratelimited("LLC(%s:%d): Application bug, race in MSG_PEEK\n", + current->comm, + task_pid_nr(current)); peek_seq = llc->copied_seq; } continue; @@ -840,7 +838,7 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, if (!(flags & MSG_PEEK)) { spin_lock_irqsave(&sk->sk_receive_queue.lock, cpu_flags); - sk_eat_skb(sk, skb, 0); + sk_eat_skb(sk, skb, false); spin_unlock_irqrestore(&sk->sk_receive_queue.lock, cpu_flags); *seq = 0; } @@ -863,7 +861,7 @@ copy_uaddr: if (!(flags & MSG_PEEK)) { spin_lock_irqsave(&sk->sk_receive_queue.lock, cpu_flags); - sk_eat_skb(sk, skb, 0); + sk_eat_skb(sk, skb, false); spin_unlock_irqrestore(&sk->sk_receive_queue.lock, cpu_flags); *seq = 0; } diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index ba137a6a224..0d0d416dfab 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -828,7 +828,7 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb) else { dprintk("%s: adding to backlog...\n", __func__); llc_set_backlog_type(skb, LLC_PACKET); - if (sk_add_backlog(sk, skb)) + if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) goto drop_unlock; } out: diff --git a/net/llc/llc_output.c b/net/llc/llc_output.c index b658cba89fd..2dae8a5df23 100644 --- a/net/llc/llc_output.c +++ b/net/llc/llc_output.c @@ -14,9 +14,7 @@ */ #include <linux/if_arp.h> -#include <linux/if_tr.h> #include <linux/netdevice.h> -#include <linux/trdevice.h> #include <linux/skbuff.h> #include <linux/export.h> #include <net/llc.h> @@ -37,7 +35,6 @@ int llc_mac_hdr_init(struct sk_buff *skb, int rc = -EINVAL; switch (skb->dev->type) { - case ARPHRD_IEEE802_TR: case ARPHRD_ETHER: case ARPHRD_LOOPBACK: rc = dev_hard_header(skb, skb->dev, ETH_P_802_2, da, sa, diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index 94e7fca75b8..7c5073badc7 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -31,10 +31,6 @@ static int llc_mac_header_len(unsigned short devtype) case ARPHRD_ETHER: case ARPHRD_LOOPBACK: return sizeof(struct ethhdr); -#if defined(CONFIG_TR) || defined(CONFIG_TR_MODULE) - case ARPHRD_IEEE802_TR: - return sizeof(struct trh_hdr); -#endif } return 0; } diff --git a/net/llc/sysctl_net_llc.c b/net/llc/sysctl_net_llc.c index e2ebe358626..d75306b9c2f 100644 --- a/net/llc/sysctl_net_llc.c +++ b/net/llc/sysctl_net_llc.c @@ -7,6 +7,7 @@ #include <linux/mm.h> #include <linux/init.h> #include <linux/sysctl.h> +#include <net/net_namespace.h> #include <net/llc.h> #ifndef CONFIG_SYSCTL @@ -56,48 +57,29 @@ static struct ctl_table llc_station_table[] = { { }, }; -static struct ctl_table llc2_dir_timeout_table[] = { - { - .procname = "timeout", - .mode = 0555, - .child = llc2_timeout_table, - }, - { }, -}; - -static struct ctl_table llc_table[] = { - { - .procname = "llc2", - .mode = 0555, - .child = llc2_dir_timeout_table, - }, - { - .procname = "station", - .mode = 0555, - .child = llc_station_table, - }, - { }, -}; - -static struct ctl_path llc_path[] = { - { .procname = "net", }, - { .procname = "llc", }, - { } -}; - -static struct ctl_table_header *llc_table_header; +static struct ctl_table_header *llc2_timeout_header; +static struct ctl_table_header *llc_station_header; int __init llc_sysctl_init(void) { - llc_table_header = register_sysctl_paths(llc_path, llc_table); + llc2_timeout_header = register_net_sysctl(&init_net, "net/llc/llc2/timeout", llc2_timeout_table); + llc_station_header = register_net_sysctl(&init_net, "net/llc/station", llc_station_table); - return llc_table_header ? 0 : -ENOMEM; + if (!llc2_timeout_header || !llc_station_header) { + llc_sysctl_exit(); + return -ENOMEM; + } + return 0; } void llc_sysctl_exit(void) { - if (llc_table_header) { - unregister_sysctl_table(llc_table_header); - llc_table_header = NULL; + if (llc2_timeout_header) { + unregister_net_sysctl_table(llc2_timeout_header); + llc2_timeout_header = NULL; + } + if (llc_station_header) { + unregister_net_sysctl_table(llc_station_header); + llc_station_header = NULL; } } diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index 96ddb72760b..8d249d70598 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -225,6 +225,17 @@ config MAC80211_VERBOSE_MHWMP_DEBUG Do not select this option. +config MAC80211_VERBOSE_MESH_SYNC_DEBUG + bool "Verbose mesh mesh synchronization debugging" + depends on MAC80211_DEBUG_MENU + depends on MAC80211_MESH + ---help--- + Selecting this option causes mac80211 to print out very verbose mesh + synchronization debugging messages (when mac80211 is taking part in a + mesh network). + + Do not select this option. + config MAC80211_VERBOSE_TDLS_DEBUG bool "Verbose TDLS debugging" depends on MAC80211_DEBUG_MENU diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index 1be7a454aa7..3e9d931bba3 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -38,7 +38,8 @@ mac80211-$(CONFIG_MAC80211_MESH) += \ mesh.o \ mesh_pathtbl.o \ mesh_plink.o \ - mesh_hwmp.o + mesh_hwmp.o \ + mesh_sync.o mac80211-$(CONFIG_PM) += pm.o diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 1068f668ac4..26ddb699d69 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -49,6 +49,8 @@ static void ieee80211_free_tid_rx(struct rcu_head *h) container_of(h, struct tid_ampdu_rx, rcu_head); int i; + del_timer_sync(&tid_rx->reorder_timer); + for (i = 0; i < tid_rx->buf_size; i++) dev_kfree_skb(tid_rx->reorder_buf[i]); kfree(tid_rx->reorder_buf); @@ -91,7 +93,6 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, tid, WLAN_BACK_RECIPIENT, reason); del_timer_sync(&tid_rx->session_timer); - del_timer_sync(&tid_rx->reorder_timer); call_rcu(&tid_rx->rcu_head, ieee80211_free_tid_rx); } @@ -141,6 +142,18 @@ static void sta_rx_agg_session_timer_expired(unsigned long data) u8 *timer_to_id = ptid - *ptid; struct sta_info *sta = container_of(timer_to_id, struct sta_info, timer_to_tid[0]); + struct tid_ampdu_rx *tid_rx; + unsigned long timeout; + + tid_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[*ptid]); + if (!tid_rx) + return; + + timeout = tid_rx->last_rx + TU_TO_JIFFIES(tid_rx->timeout); + if (time_is_after_jiffies(timeout)) { + mod_timer(&tid_rx->session_timer, timeout); + return; + } #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "rx session timer expired on tid %d\n", (u16)*ptid); @@ -247,11 +260,8 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, (buf_size > IEEE80211_MAX_AMPDU_BUF)) { status = WLAN_STATUS_INVALID_QOS_PARAM; #ifdef CONFIG_MAC80211_HT_DEBUG - if (net_ratelimit()) - printk(KERN_DEBUG "AddBA Req with bad params from " - "%pM on tid %u. policy %d, buffer size %d\n", - mgmt->sa, tid, ba_policy, - buf_size); + net_dbg_ratelimited("AddBA Req with bad params from %pM on tid %u. policy %d, buffer size %d\n", + mgmt->sa, tid, ba_policy, buf_size); #endif /* CONFIG_MAC80211_HT_DEBUG */ goto end_no_lock; } @@ -268,10 +278,8 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, if (sta->ampdu_mlme.tid_rx[tid]) { #ifdef CONFIG_MAC80211_HT_DEBUG - if (net_ratelimit()) - printk(KERN_DEBUG "unexpected AddBA Req from " - "%pM on tid %u\n", - mgmt->sa, tid); + net_dbg_ratelimited("unexpected AddBA Req from %pM on tid %u\n", + mgmt->sa, tid); #endif /* CONFIG_MAC80211_HT_DEBUG */ /* delete existing Rx BA session on the same tid */ @@ -290,7 +298,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, /* rx timer */ tid_agg_rx->session_timer.function = sta_rx_agg_session_timer_expired; tid_agg_rx->session_timer.data = (unsigned long)&sta->timer_to_tid[tid]; - init_timer(&tid_agg_rx->session_timer); + init_timer_deferrable(&tid_agg_rx->session_timer); /* rx reorder timer */ tid_agg_rx->reorder_timer.function = sta_rx_agg_reorder_timer_expired; @@ -334,8 +342,10 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, /* activate it for RX */ rcu_assign_pointer(sta->ampdu_mlme.tid_rx[tid], tid_agg_rx); - if (timeout) + if (timeout) { mod_timer(&tid_agg_rx->session_timer, TU_TO_EXP_TIME(timeout)); + tid_agg_rx->last_rx = jiffies; + } end: mutex_unlock(&sta->ampdu_mlme.mtx); diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 76be6174419..5b7053c5873 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -286,25 +286,25 @@ static inline int ieee80211_ac_from_tid(int tid) * a global "agg_queue_stop" refcount. */ static void __acquires(agg_queue) -ieee80211_stop_queue_agg(struct ieee80211_local *local, int tid) +ieee80211_stop_queue_agg(struct ieee80211_sub_if_data *sdata, int tid) { - int queue = ieee80211_ac_from_tid(tid); + int queue = sdata->vif.hw_queue[ieee80211_ac_from_tid(tid)]; - if (atomic_inc_return(&local->agg_queue_stop[queue]) == 1) + if (atomic_inc_return(&sdata->local->agg_queue_stop[queue]) == 1) ieee80211_stop_queue_by_reason( - &local->hw, queue, + &sdata->local->hw, queue, IEEE80211_QUEUE_STOP_REASON_AGGREGATION); __acquire(agg_queue); } static void __releases(agg_queue) -ieee80211_wake_queue_agg(struct ieee80211_local *local, int tid) +ieee80211_wake_queue_agg(struct ieee80211_sub_if_data *sdata, int tid) { - int queue = ieee80211_ac_from_tid(tid); + int queue = sdata->vif.hw_queue[ieee80211_ac_from_tid(tid)]; - if (atomic_dec_return(&local->agg_queue_stop[queue]) == 0) + if (atomic_dec_return(&sdata->local->agg_queue_stop[queue]) == 0) ieee80211_wake_queue_by_reason( - &local->hw, queue, + &sdata->local->hw, queue, IEEE80211_QUEUE_STOP_REASON_AGGREGATION); __release(agg_queue); } @@ -314,13 +314,14 @@ ieee80211_wake_queue_agg(struct ieee80211_local *local, int tid) * requires a call to ieee80211_agg_splice_finish later */ static void __acquires(agg_queue) -ieee80211_agg_splice_packets(struct ieee80211_local *local, +ieee80211_agg_splice_packets(struct ieee80211_sub_if_data *sdata, struct tid_ampdu_tx *tid_tx, u16 tid) { - int queue = ieee80211_ac_from_tid(tid); + struct ieee80211_local *local = sdata->local; + int queue = sdata->vif.hw_queue[ieee80211_ac_from_tid(tid)]; unsigned long flags; - ieee80211_stop_queue_agg(local, tid); + ieee80211_stop_queue_agg(sdata, tid); if (WARN(!tid_tx, "TID %d gone but expected when splicing aggregates" " from the pending queue\n", tid)) @@ -336,9 +337,9 @@ ieee80211_agg_splice_packets(struct ieee80211_local *local, } static void __releases(agg_queue) -ieee80211_agg_splice_finish(struct ieee80211_local *local, u16 tid) +ieee80211_agg_splice_finish(struct ieee80211_sub_if_data *sdata, u16 tid) { - ieee80211_wake_queue_agg(local, tid); + ieee80211_wake_queue_agg(sdata, tid); } void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) @@ -376,9 +377,9 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) " tid %d\n", tid); #endif spin_lock_bh(&sta->lock); - ieee80211_agg_splice_packets(local, tid_tx, tid); + ieee80211_agg_splice_packets(sdata, tid_tx, tid); ieee80211_assign_tid_tx(sta, tid, NULL); - ieee80211_agg_splice_finish(local, tid); + ieee80211_agg_splice_finish(sdata, tid); spin_unlock_bh(&sta->lock); kfree_rcu(tid_tx, rcu_head); @@ -417,6 +418,18 @@ static void sta_tx_agg_session_timer_expired(unsigned long data) u8 *timer_to_id = ptid - *ptid; struct sta_info *sta = container_of(timer_to_id, struct sta_info, timer_to_tid[0]); + struct tid_ampdu_tx *tid_tx; + unsigned long timeout; + + tid_tx = rcu_dereference_protected_tid_tx(sta, *ptid); + if (!tid_tx) + return; + + timeout = tid_tx->last_tx + TU_TO_JIFFIES(tid_tx->timeout); + if (time_is_after_jiffies(timeout)) { + mod_timer(&tid_tx->session_timer, timeout); + return; + } #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "tx session timer expired on tid %d\n", (u16)*ptid); @@ -542,7 +555,7 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, /* tx timer */ tid_tx->session_timer.function = sta_tx_agg_session_timer_expired; tid_tx->session_timer.data = (unsigned long)&sta->timer_to_tid[tid]; - init_timer(&tid_tx->session_timer); + init_timer_deferrable(&tid_tx->session_timer); /* assign a dialog token */ sta->ampdu_mlme.dialog_token_allocator++; @@ -586,14 +599,14 @@ static void ieee80211_agg_tx_operational(struct ieee80211_local *local, */ spin_lock_bh(&sta->lock); - ieee80211_agg_splice_packets(local, tid_tx, tid); + ieee80211_agg_splice_packets(sta->sdata, tid_tx, tid); /* * Now mark as operational. This will be visible * in the TX path, and lets it go lock-free in * the common case. */ set_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state); - ieee80211_agg_splice_finish(local, tid); + ieee80211_agg_splice_finish(sta->sdata, tid); spin_unlock_bh(&sta->lock); } @@ -778,12 +791,12 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid) * more. */ - ieee80211_agg_splice_packets(local, tid_tx, tid); + ieee80211_agg_splice_packets(sta->sdata, tid_tx, tid); /* future packets must not find the tid_tx struct any more */ ieee80211_assign_tid_tx(sta, tid, NULL); - ieee80211_agg_splice_finish(local, tid); + ieee80211_agg_splice_finish(sta->sdata, tid); kfree_rcu(tid_tx, rcu_head); @@ -884,9 +897,11 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, sta->ampdu_mlme.addba_req_num[tid] = 0; - if (tid_tx->timeout) + if (tid_tx->timeout) { mod_timer(&tid_tx->session_timer, TU_TO_EXP_TIME(tid_tx->timeout)); + tid_tx->last_tx = jiffies; + } } else { ___ieee80211_stop_tx_ba_session(sta, tid, WLAN_BACK_INITIATOR, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 677d6592978..495831ee48f 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -412,6 +412,10 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) sinfo->llid = le16_to_cpu(sta->llid); sinfo->plid = le16_to_cpu(sta->plid); sinfo->plink_state = sta->plink_state; + if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) { + sinfo->filled |= STATION_INFO_T_OFFSET; + sinfo->t_offset = sta->t_offset; + } #endif } @@ -446,6 +450,180 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_TDLS_PEER); } +static const char ieee80211_gstrings_sta_stats[][ETH_GSTRING_LEN] = { + "rx_packets", "rx_bytes", "wep_weak_iv_count", + "rx_duplicates", "rx_fragments", "rx_dropped", + "tx_packets", "tx_bytes", "tx_fragments", + "tx_filtered", "tx_retry_failed", "tx_retries", + "beacon_loss", "sta_state", "txrate", "rxrate", "signal", + "channel", "noise", "ch_time", "ch_time_busy", + "ch_time_ext_busy", "ch_time_rx", "ch_time_tx" +}; +#define STA_STATS_LEN ARRAY_SIZE(ieee80211_gstrings_sta_stats) + +static int ieee80211_get_et_sset_count(struct wiphy *wiphy, + struct net_device *dev, + int sset) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + int rv = 0; + + if (sset == ETH_SS_STATS) + rv += STA_STATS_LEN; + + rv += drv_get_et_sset_count(sdata, sset); + + if (rv == 0) + return -EOPNOTSUPP; + return rv; +} + +static void ieee80211_get_et_stats(struct wiphy *wiphy, + struct net_device *dev, + struct ethtool_stats *stats, + u64 *data) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct sta_info *sta; + struct ieee80211_local *local = sdata->local; + struct station_info sinfo; + struct survey_info survey; + int i, q; +#define STA_STATS_SURVEY_LEN 7 + + memset(data, 0, sizeof(u64) * STA_STATS_LEN); + +#define ADD_STA_STATS(sta) \ + do { \ + data[i++] += sta->rx_packets; \ + data[i++] += sta->rx_bytes; \ + data[i++] += sta->wep_weak_iv_count; \ + data[i++] += sta->num_duplicates; \ + data[i++] += sta->rx_fragments; \ + data[i++] += sta->rx_dropped; \ + \ + data[i++] += sta->tx_packets; \ + data[i++] += sta->tx_bytes; \ + data[i++] += sta->tx_fragments; \ + data[i++] += sta->tx_filtered_count; \ + data[i++] += sta->tx_retry_failed; \ + data[i++] += sta->tx_retry_count; \ + data[i++] += sta->beacon_loss_count; \ + } while (0) + + /* For Managed stations, find the single station based on BSSID + * and use that. For interface types, iterate through all available + * stations and add stats for any station that is assigned to this + * network device. + */ + + rcu_read_lock(); + + if (sdata->vif.type == NL80211_IFTYPE_STATION) { + sta = sta_info_get_bss(sdata, sdata->u.mgd.bssid); + + if (!(sta && !WARN_ON(sta->sdata->dev != dev))) + goto do_survey; + + i = 0; + ADD_STA_STATS(sta); + + data[i++] = sta->sta_state; + + sinfo.filled = 0; + sta_set_sinfo(sta, &sinfo); + + if (sinfo.filled | STATION_INFO_TX_BITRATE) + data[i] = 100000 * + cfg80211_calculate_bitrate(&sinfo.txrate); + i++; + if (sinfo.filled | STATION_INFO_RX_BITRATE) + data[i] = 100000 * + cfg80211_calculate_bitrate(&sinfo.rxrate); + i++; + + if (sinfo.filled | STATION_INFO_SIGNAL_AVG) + data[i] = (u8)sinfo.signal_avg; + i++; + } else { + list_for_each_entry_rcu(sta, &local->sta_list, list) { + /* Make sure this station belongs to the proper dev */ + if (sta->sdata->dev != dev) + continue; + + i = 0; + ADD_STA_STATS(sta); + } + } + +do_survey: + i = STA_STATS_LEN - STA_STATS_SURVEY_LEN; + /* Get survey stats for current channel */ + q = 0; + while (true) { + survey.filled = 0; + if (drv_get_survey(local, q, &survey) != 0) { + survey.filled = 0; + break; + } + + if (survey.channel && + (local->oper_channel->center_freq == + survey.channel->center_freq)) + break; + q++; + } + + if (survey.filled) + data[i++] = survey.channel->center_freq; + else + data[i++] = 0; + if (survey.filled & SURVEY_INFO_NOISE_DBM) + data[i++] = (u8)survey.noise; + else + data[i++] = -1LL; + if (survey.filled & SURVEY_INFO_CHANNEL_TIME) + data[i++] = survey.channel_time; + else + data[i++] = -1LL; + if (survey.filled & SURVEY_INFO_CHANNEL_TIME_BUSY) + data[i++] = survey.channel_time_busy; + else + data[i++] = -1LL; + if (survey.filled & SURVEY_INFO_CHANNEL_TIME_EXT_BUSY) + data[i++] = survey.channel_time_ext_busy; + else + data[i++] = -1LL; + if (survey.filled & SURVEY_INFO_CHANNEL_TIME_RX) + data[i++] = survey.channel_time_rx; + else + data[i++] = -1LL; + if (survey.filled & SURVEY_INFO_CHANNEL_TIME_TX) + data[i++] = survey.channel_time_tx; + else + data[i++] = -1LL; + + rcu_read_unlock(); + + if (WARN_ON(i != STA_STATS_LEN)) + return; + + drv_get_et_stats(sdata, stats, &(data[STA_STATS_LEN])); +} + +static void ieee80211_get_et_strings(struct wiphy *wiphy, + struct net_device *dev, + u32 sset, u8 *data) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + int sz_sta_stats = 0; + + if (sset == ETH_SS_STATS) { + sz_sta_stats = sizeof(ieee80211_gstrings_sta_stats); + memcpy(data, *ieee80211_gstrings_sta_stats, sz_sta_stats); + } + drv_get_et_strings(sdata, sset, &(data[sz_sta_stats])); +} static int ieee80211_dump_station(struct wiphy *wiphy, struct net_device *dev, int idx, u8 *mac, struct station_info *sinfo) @@ -640,6 +818,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, ieee80211_bss_info_change_notify(sdata, changed); + netif_carrier_on(dev); + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) + netif_carrier_on(vlan->dev); + return 0; } @@ -665,7 +847,7 @@ static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev, static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) { - struct ieee80211_sub_if_data *sdata; + struct ieee80211_sub_if_data *sdata, *vlan; struct beacon_data *old; sdata = IEEE80211_DEV_TO_SUB_IF(dev); @@ -674,6 +856,10 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) if (!old) return -ENOENT; + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) + netif_carrier_off(vlan->dev); + netif_carrier_off(dev); + RCU_INIT_POINTER(sdata->u.ap.beacon, NULL); kfree_rcu(old, rcu_head); @@ -907,7 +1093,7 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, } else sdata = IEEE80211_DEV_TO_SUB_IF(dev); - if (compare_ether_addr(mac, sdata->vif.addr) == 0) + if (ether_addr_equal(mac, sdata->vif.addr)) return -EINVAL; if (is_multicast_ether_addr(mac)) @@ -993,6 +1179,9 @@ static int ieee80211_change_station(struct wiphy *wiphy, } if (params->vlan && params->vlan != sta->sdata->dev) { + bool prev_4addr = false; + bool new_4addr = false; + vlansdata = IEEE80211_DEV_TO_SUB_IF(params->vlan); if (vlansdata->vif.type != NL80211_IFTYPE_AP_VLAN && @@ -1008,9 +1197,25 @@ static int ieee80211_change_station(struct wiphy *wiphy, } rcu_assign_pointer(vlansdata->u.vlan.sta, sta); + new_4addr = true; + } + + if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN && + sta->sdata->u.vlan.sta) { + rcu_assign_pointer(sta->sdata->u.vlan.sta, NULL); + prev_4addr = true; } sta->sdata = vlansdata; + + if (sta->sta_state == IEEE80211_STA_AUTHORIZED && + prev_4addr != new_4addr) { + if (new_4addr) + atomic_dec(&sta->sdata->bss->num_mcast_sta); + else + atomic_inc(&sta->sdata->bss->num_mcast_sta); + } + ieee80211_send_layer2_update(sta); } @@ -1235,6 +1440,7 @@ static int copy_mesh_setup(struct ieee80211_if_mesh *ifmsh, /* now copy the rest of the setup parameters */ ifmsh->mesh_id_len = setup->mesh_id_len; memcpy(ifmsh->mesh_id, setup->mesh_id, ifmsh->mesh_id_len); + ifmsh->mesh_sp_id = setup->sync_method; ifmsh->mesh_pp_id = setup->path_sel_proto; ifmsh->mesh_pm_id = setup->path_metric; ifmsh->security = IEEE80211_MESH_SEC_NONE; @@ -1279,6 +1485,9 @@ static int ieee80211_update_mesh_config(struct wiphy *wiphy, conf->dot11MeshTTL = nconf->element_ttl; if (_chg_mesh_attr(NL80211_MESHCONF_AUTO_OPEN_PLINKS, mask)) conf->auto_open_plinks = nconf->auto_open_plinks; + if (_chg_mesh_attr(NL80211_MESHCONF_SYNC_OFFSET_MAX_NEIGHBOR, mask)) + conf->dot11MeshNbrOffsetMaxNeighbor = + nconf->dot11MeshNbrOffsetMaxNeighbor; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES, mask)) conf->dot11MeshHWMPmaxPREQretries = nconf->dot11MeshHWMPmaxPREQretries; @@ -1329,6 +1538,11 @@ static int ieee80211_update_mesh_config(struct wiphy *wiphy, return -ENOTSUPP; conf->rssi_threshold = nconf->rssi_threshold; } + if (_chg_mesh_attr(NL80211_MESHCONF_HT_OPMODE, mask)) { + conf->ht_opmode = nconf->ht_opmode; + sdata->vif.bss_conf.ht_operation_mode = nconf->ht_opmode; + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_HT); + } return 0; } @@ -1437,6 +1651,9 @@ static int ieee80211_set_txq_params(struct wiphy *wiphy, if (!local->ops->conf_tx) return -EOPNOTSUPP; + if (local->hw.queues < IEEE80211_NUM_ACS) + return -EOPNOTSUPP; + memset(&p, 0, sizeof(p)); p.aifs = params->aifs; p.cw_max = params->cwmax; @@ -1449,14 +1666,11 @@ static int ieee80211_set_txq_params(struct wiphy *wiphy, */ p.uapsd = false; - if (params->queue >= local->hw.queues) - return -EINVAL; - - sdata->tx_conf[params->queue] = p; - if (drv_conf_tx(local, sdata, params->queue, &p)) { + sdata->tx_conf[params->ac] = p; + if (drv_conf_tx(local, sdata, params->ac, &p)) { wiphy_debug(local->hw.wiphy, - "failed to set TX queue parameters for queue %d\n", - params->queue); + "failed to set TX queue parameters for AC %d\n", + params->ac); return -EINVAL; } @@ -2090,6 +2304,10 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct net_device *dev, IEEE80211_SKB_CB(skb)->flags = flags; + if (flags & IEEE80211_TX_CTL_TX_OFFCHAN) + IEEE80211_SKB_CB(skb)->hw_queue = + local->hw.offchannel_tx_hw_queue; + skb->dev = sdata->dev; *cookie = (unsigned long) skb; @@ -2131,6 +2349,8 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct net_device *dev, /* modify cookie to prevent API mismatches */ *cookie ^= 2; IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_CTL_TX_OFFCHAN; + IEEE80211_SKB_CB(skb)->hw_queue = + local->hw.offchannel_tx_hw_queue; local->hw_roc_skb = skb; local->hw_roc_skb_for_status = skb; mutex_unlock(&local->mtx); @@ -2350,8 +2570,8 @@ ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev, tf->u.setup_req.capability = cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); - ieee80211_add_srates_ie(&sdata->vif, skb); - ieee80211_add_ext_srates_ie(&sdata->vif, skb); + ieee80211_add_srates_ie(&sdata->vif, skb, false); + ieee80211_add_ext_srates_ie(&sdata->vif, skb, false); ieee80211_tdls_add_ext_capab(skb); break; case WLAN_TDLS_SETUP_RESPONSE: @@ -2364,8 +2584,8 @@ ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev, tf->u.setup_resp.capability = cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); - ieee80211_add_srates_ie(&sdata->vif, skb); - ieee80211_add_ext_srates_ie(&sdata->vif, skb); + ieee80211_add_srates_ie(&sdata->vif, skb, false); + ieee80211_add_ext_srates_ie(&sdata->vif, skb, false); ieee80211_tdls_add_ext_capab(skb); break; case WLAN_TDLS_SETUP_CONFIRM: @@ -2425,8 +2645,8 @@ ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev, mgmt->u.action.u.tdls_discover_resp.capability = cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); - ieee80211_add_srates_ie(&sdata->vif, skb); - ieee80211_add_ext_srates_ie(&sdata->vif, skb); + ieee80211_add_srates_ie(&sdata->vif, skb, false); + ieee80211_add_ext_srates_ie(&sdata->vif, skb, false); ieee80211_tdls_add_ext_capab(skb); break; default: @@ -2666,13 +2886,22 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev, } static struct ieee80211_channel * -ieee80211_wiphy_get_channel(struct wiphy *wiphy) +ieee80211_wiphy_get_channel(struct wiphy *wiphy, + enum nl80211_channel_type *type) { struct ieee80211_local *local = wiphy_priv(wiphy); + *type = local->_oper_channel_type; return local->oper_channel; } +#ifdef CONFIG_PM +static void ieee80211_set_wakeup(struct wiphy *wiphy, bool enabled) +{ + drv_set_wakeup(wiphy_priv(wiphy), enabled); +} +#endif + struct cfg80211_ops mac80211_config_ops = { .add_virtual_intf = ieee80211_add_iface, .del_virtual_intf = ieee80211_del_iface, @@ -2741,4 +2970,10 @@ struct cfg80211_ops mac80211_config_ops = { .probe_client = ieee80211_probe_client, .get_channel = ieee80211_wiphy_get_channel, .set_noack_map = ieee80211_set_noack_map, +#ifdef CONFIG_PM + .set_wakeup = ieee80211_set_wakeup, +#endif + .get_et_sset_count = ieee80211_get_et_sset_count, + .get_et_stats = ieee80211_get_et_stats, + .get_et_strings = ieee80211_get_et_strings, }; diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index e00ce8c3e28..c76cf7230c7 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -135,29 +135,3 @@ bool ieee80211_set_channel_type(struct ieee80211_local *local, return result; } - -/* - * ieee80211_get_tx_channel_type returns the channel type we should - * use for packet transmission, given the channel capability and - * whatever regulatory flags we have been given. - */ -enum nl80211_channel_type ieee80211_get_tx_channel_type( - struct ieee80211_local *local, - enum nl80211_channel_type channel_type) -{ - switch (channel_type) { - case NL80211_CHAN_HT40PLUS: - if (local->hw.conf.channel->flags & - IEEE80211_CHAN_NO_HT40PLUS) - return NL80211_CHAN_HT20; - break; - case NL80211_CHAN_HT40MINUS: - if (local->hw.conf.channel->flags & - IEEE80211_CHAN_NO_HT40MINUS) - return NL80211_CHAN_HT20; - break; - default: - break; - } - return channel_type; -} diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index cc5b7a6e7e0..778e5916d7c 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -15,12 +15,6 @@ #include "rate.h" #include "debugfs.h" -int mac80211_open_file_generic(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - #define DEBUGFS_FORMAT_BUFFER_SIZE 100 int mac80211_format_buffer(char __user *userbuf, size_t count, @@ -50,7 +44,7 @@ static ssize_t name## _read(struct file *file, char __user *userbuf, \ #define DEBUGFS_READONLY_FILE_OPS(name) \ static const struct file_operations name## _ops = { \ .read = name## _read, \ - .open = mac80211_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; @@ -93,7 +87,7 @@ static ssize_t reset_write(struct file *file, const char __user *user_buf, static const struct file_operations reset_ops = { .write = reset_write, - .open = mac80211_open_file_generic, + .open = simple_open, .llseek = noop_llseek, }; @@ -254,7 +248,7 @@ static ssize_t stats_ ##name## _read(struct file *file, \ \ static const struct file_operations stats_ ##name## _ops = { \ .read = stats_ ##name## _read, \ - .open = mac80211_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; diff --git a/net/mac80211/debugfs.h b/net/mac80211/debugfs.h index 7c87529630f..9be4e6d71d0 100644 --- a/net/mac80211/debugfs.h +++ b/net/mac80211/debugfs.h @@ -3,7 +3,6 @@ #ifdef CONFIG_MAC80211_DEBUGFS extern void debugfs_hw_add(struct ieee80211_local *local); -extern int mac80211_open_file_generic(struct inode *inode, struct file *file); extern int mac80211_format_buffer(char __user *userbuf, size_t count, loff_t *ppos, char *fmt, ...); #else diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c index 59edcd95a58..7932767bb48 100644 --- a/net/mac80211/debugfs_key.c +++ b/net/mac80211/debugfs_key.c @@ -30,7 +30,7 @@ static ssize_t key_##name##_read(struct file *file, \ #define KEY_OPS(name) \ static const struct file_operations key_ ##name## _ops = { \ .read = key_##name##_read, \ - .open = mac80211_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ } @@ -45,7 +45,7 @@ static const struct file_operations key_ ##name## _ops = { \ #define KEY_CONF_OPS(name) \ static const struct file_operations key_ ##name## _ops = { \ .read = key_conf_##name##_read, \ - .open = mac80211_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ } diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index a32eeda04aa..ea0122dbd2b 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -135,7 +135,7 @@ static ssize_t ieee80211_if_read_##name(struct file *file, \ static const struct file_operations name##_ops = { \ .read = ieee80211_if_read_##name, \ .write = (_write), \ - .open = mac80211_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ } @@ -394,7 +394,7 @@ static ssize_t ieee80211_if_parse_uapsd_max_sp_len( __IEEE80211_IF_FILE_W(uapsd_max_sp_len); /* AP attributes */ -IEEE80211_IF_FILE(num_sta_authorized, u.ap.num_sta_authorized, ATOMIC); +IEEE80211_IF_FILE(num_mcast_sta, u.ap.num_mcast_sta, ATOMIC); IEEE80211_IF_FILE(num_sta_ps, u.ap.num_sta_ps, ATOMIC); IEEE80211_IF_FILE(dtim_count, u.ap.dtim_count, DEC); @@ -424,6 +424,7 @@ static ssize_t ieee80211_if_parse_tsf( struct ieee80211_local *local = sdata->local; unsigned long long tsf; int ret; + int tsf_is_delta = 0; if (strncmp(buf, "reset", 5) == 0) { if (local->ops->reset_tsf) { @@ -431,9 +432,20 @@ static ssize_t ieee80211_if_parse_tsf( wiphy_info(local->hw.wiphy, "debugfs reset TSF\n"); } } else { + if (buflen > 10 && buf[1] == '=') { + if (buf[0] == '+') + tsf_is_delta = 1; + else if (buf[0] == '-') + tsf_is_delta = -1; + else + return -EINVAL; + buf += 2; + } ret = kstrtoull(buf, 10, &tsf); if (ret < 0) return -EINVAL; + if (tsf_is_delta) + tsf = drv_get_tsf(local, sdata) + tsf_is_delta * tsf; if (local->ops->set_tsf) { drv_set_tsf(local, sdata, tsf); wiphy_info(local->hw.wiphy, @@ -499,26 +511,23 @@ IEEE80211_IF_FILE(dot11MeshForwarding, u.mesh.mshcfg.dot11MeshForwarding, DEC); IEEE80211_IF_FILE(rssi_threshold, u.mesh.mshcfg.rssi_threshold, DEC); #endif - -#define DEBUGFS_ADD(name) \ - debugfs_create_file(#name, 0400, sdata->debugfs.dir, \ - sdata, &name##_ops); - #define DEBUGFS_ADD_MODE(name, mode) \ debugfs_create_file(#name, mode, sdata->debugfs.dir, \ sdata, &name##_ops); -static void add_sta_files(struct ieee80211_sub_if_data *sdata) +#define DEBUGFS_ADD(name) DEBUGFS_ADD_MODE(name, 0400) + +static void add_common_files(struct ieee80211_sub_if_data *sdata) { DEBUGFS_ADD(drop_unencrypted); - DEBUGFS_ADD(flags); - DEBUGFS_ADD(state); - DEBUGFS_ADD(channel_type); DEBUGFS_ADD(rc_rateidx_mask_2ghz); DEBUGFS_ADD(rc_rateidx_mask_5ghz); DEBUGFS_ADD(rc_rateidx_mcs_mask_2ghz); DEBUGFS_ADD(rc_rateidx_mcs_mask_5ghz); +} +static void add_sta_files(struct ieee80211_sub_if_data *sdata) +{ DEBUGFS_ADD(bssid); DEBUGFS_ADD(aid); DEBUGFS_ADD(last_beacon); @@ -531,16 +540,7 @@ static void add_sta_files(struct ieee80211_sub_if_data *sdata) static void add_ap_files(struct ieee80211_sub_if_data *sdata) { - DEBUGFS_ADD(drop_unencrypted); - DEBUGFS_ADD(flags); - DEBUGFS_ADD(state); - DEBUGFS_ADD(channel_type); - DEBUGFS_ADD(rc_rateidx_mask_2ghz); - DEBUGFS_ADD(rc_rateidx_mask_5ghz); - DEBUGFS_ADD(rc_rateidx_mcs_mask_2ghz); - DEBUGFS_ADD(rc_rateidx_mcs_mask_5ghz); - - DEBUGFS_ADD(num_sta_authorized); + DEBUGFS_ADD(num_mcast_sta); DEBUGFS_ADD(num_sta_ps); DEBUGFS_ADD(dtim_count); DEBUGFS_ADD(num_buffered_multicast); @@ -549,48 +549,14 @@ static void add_ap_files(struct ieee80211_sub_if_data *sdata) static void add_ibss_files(struct ieee80211_sub_if_data *sdata) { - DEBUGFS_ADD(channel_type); - DEBUGFS_ADD(rc_rateidx_mask_2ghz); - DEBUGFS_ADD(rc_rateidx_mask_5ghz); - DEBUGFS_ADD(rc_rateidx_mcs_mask_2ghz); - DEBUGFS_ADD(rc_rateidx_mcs_mask_5ghz); - DEBUGFS_ADD_MODE(tsf, 0600); } static void add_wds_files(struct ieee80211_sub_if_data *sdata) { - DEBUGFS_ADD(drop_unencrypted); - DEBUGFS_ADD(flags); - DEBUGFS_ADD(state); - DEBUGFS_ADD(channel_type); - DEBUGFS_ADD(rc_rateidx_mask_2ghz); - DEBUGFS_ADD(rc_rateidx_mask_5ghz); - DEBUGFS_ADD(rc_rateidx_mcs_mask_2ghz); - DEBUGFS_ADD(rc_rateidx_mcs_mask_5ghz); - DEBUGFS_ADD(peer); } -static void add_vlan_files(struct ieee80211_sub_if_data *sdata) -{ - DEBUGFS_ADD(drop_unencrypted); - DEBUGFS_ADD(flags); - DEBUGFS_ADD(state); - DEBUGFS_ADD(channel_type); - DEBUGFS_ADD(rc_rateidx_mask_2ghz); - DEBUGFS_ADD(rc_rateidx_mask_5ghz); - DEBUGFS_ADD(rc_rateidx_mcs_mask_2ghz); - DEBUGFS_ADD(rc_rateidx_mcs_mask_5ghz); -} - -static void add_monitor_files(struct ieee80211_sub_if_data *sdata) -{ - DEBUGFS_ADD(flags); - DEBUGFS_ADD(state); - DEBUGFS_ADD(channel_type); -} - #ifdef CONFIG_MAC80211_MESH static void add_mesh_files(struct ieee80211_sub_if_data *sdata) @@ -651,6 +617,13 @@ static void add_files(struct ieee80211_sub_if_data *sdata) if (!sdata->debugfs.dir) return; + DEBUGFS_ADD(flags); + DEBUGFS_ADD(state); + DEBUGFS_ADD(channel_type); + + if (sdata->vif.type != NL80211_IFTYPE_MONITOR) + add_common_files(sdata); + switch (sdata->vif.type) { case NL80211_IFTYPE_MESH_POINT: #ifdef CONFIG_MAC80211_MESH @@ -671,12 +644,6 @@ static void add_files(struct ieee80211_sub_if_data *sdata) case NL80211_IFTYPE_WDS: add_wds_files(sdata); break; - case NL80211_IFTYPE_MONITOR: - add_monitor_files(sdata); - break; - case NL80211_IFTYPE_AP_VLAN: - add_vlan_files(sdata); - break; default: break; } diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 6d45804d09b..5ccec2c1e9f 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -33,7 +33,7 @@ static ssize_t sta_ ##name## _read(struct file *file, \ #define STA_OPS(name) \ static const struct file_operations sta_ ##name## _ops = { \ .read = sta_##name##_read, \ - .open = mac80211_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ } @@ -41,7 +41,7 @@ static const struct file_operations sta_ ##name## _ops = { \ static const struct file_operations sta_ ##name## _ops = { \ .read = sta_##name##_read, \ .write = sta_##name##_write, \ - .open = mac80211_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ } @@ -63,7 +63,7 @@ static ssize_t sta_flags_read(struct file *file, char __user *userbuf, test_sta_flag(sta, WLAN_STA_##flg) ? #flg "\n" : "" int res = scnprintf(buf, sizeof(buf), - "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s", + "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s", TEST(AUTH), TEST(ASSOC), TEST(PS_STA), TEST(PS_DRIVER), TEST(AUTHORIZED), TEST(SHORT_PREAMBLE), @@ -71,7 +71,8 @@ static ssize_t sta_flags_read(struct file *file, char __user *userbuf, TEST(MFP), TEST(BLOCK_BA), TEST(PSPOLL), TEST(UAPSD), TEST(SP), TEST(TDLS_PEER), TEST(TDLS_PEER_AUTH), TEST(4ADDR_EVENT), - TEST(INSERTED), TEST(RATE_CONTROL)); + TEST(INSERTED), TEST(RATE_CONTROL), + TEST(TOFFSET_KNOWN)); #undef TEST return simple_read_from_buffer(userbuf, count, ppos, buf, res); } diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index af4691fed64..6d33a0c743a 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -7,7 +7,9 @@ static inline void check_sdata_in_driver(struct ieee80211_sub_if_data *sdata) { - WARN_ON(!(sdata->flags & IEEE80211_SDATA_IN_DRIVER)); + WARN(!(sdata->flags & IEEE80211_SDATA_IN_DRIVER), + "%s: Failed check-sdata-in-driver check, flags: 0x%x\n", + sdata->dev->name, sdata->flags); } static inline struct ieee80211_sub_if_data * @@ -33,6 +35,43 @@ static inline void drv_tx_frags(struct ieee80211_local *local, local->ops->tx_frags(&local->hw, vif, sta, skbs); } +static inline void drv_get_et_strings(struct ieee80211_sub_if_data *sdata, + u32 sset, u8 *data) +{ + struct ieee80211_local *local = sdata->local; + if (local->ops->get_et_strings) { + trace_drv_get_et_strings(local, sset); + local->ops->get_et_strings(&local->hw, &sdata->vif, sset, data); + trace_drv_return_void(local); + } +} + +static inline void drv_get_et_stats(struct ieee80211_sub_if_data *sdata, + struct ethtool_stats *stats, + u64 *data) +{ + struct ieee80211_local *local = sdata->local; + if (local->ops->get_et_stats) { + trace_drv_get_et_stats(local); + local->ops->get_et_stats(&local->hw, &sdata->vif, stats, data); + trace_drv_return_void(local); + } +} + +static inline int drv_get_et_sset_count(struct ieee80211_sub_if_data *sdata, + int sset) +{ + struct ieee80211_local *local = sdata->local; + int rv = 0; + if (local->ops->get_et_sset_count) { + trace_drv_get_et_sset_count(local, sset); + rv = local->ops->get_et_sset_count(&local->hw, &sdata->vif, + sset); + trace_drv_return_int(local, rv); + } + return rv; +} + static inline int drv_start(struct ieee80211_local *local) { int ret; @@ -89,6 +128,19 @@ static inline int drv_resume(struct ieee80211_local *local) trace_drv_return_int(local, ret); return ret; } + +static inline void drv_set_wakeup(struct ieee80211_local *local, + bool enabled) +{ + might_sleep(); + + if (!local->ops->set_wakeup) + return; + + trace_drv_set_wakeup(local, enabled); + local->ops->set_wakeup(&local->hw, enabled); + trace_drv_return_void(local); +} #endif static inline int drv_add_interface(struct ieee80211_local *local, @@ -99,7 +151,8 @@ static inline int drv_add_interface(struct ieee80211_local *local, might_sleep(); if (WARN_ON(sdata->vif.type == NL80211_IFTYPE_AP_VLAN || - sdata->vif.type == NL80211_IFTYPE_MONITOR)) + (sdata->vif.type == NL80211_IFTYPE_MONITOR && + !(local->hw.flags & IEEE80211_HW_WANT_MONITOR_VIF)))) return -EINVAL; trace_drv_add_interface(local, sdata); @@ -474,8 +527,23 @@ int drv_sta_state(struct ieee80211_local *local, return ret; } +static inline void drv_sta_rc_update(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, u32 changed) +{ + sdata = get_bss_sdata(sdata); + check_sdata_in_driver(sdata); + + trace_drv_sta_rc_update(local, sdata, sta, changed); + if (local->ops->sta_rc_update) + local->ops->sta_rc_update(&local->hw, &sdata->vif, + sta, changed); + + trace_drv_return_void(local); +} + static inline int drv_conf_tx(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, u16 queue, + struct ieee80211_sub_if_data *sdata, u16 ac, const struct ieee80211_tx_queue_params *params) { int ret = -EOPNOTSUPP; @@ -484,10 +552,10 @@ static inline int drv_conf_tx(struct ieee80211_local *local, check_sdata_in_driver(sdata); - trace_drv_conf_tx(local, sdata, queue, params); + trace_drv_conf_tx(local, sdata, ac, params); if (local->ops->conf_tx) ret = local->ops->conf_tx(&local->hw, &sdata->vif, - queue, params); + ac, params); trace_drv_return_int(local, ret); return ret; } diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h index 21d6f5290a1..6de00b2c268 100644 --- a/net/mac80211/driver-trace.h +++ b/net/mac80211/driver-trace.h @@ -161,6 +161,21 @@ DEFINE_EVENT(local_only_evt, drv_start, TP_ARGS(local) ); +DEFINE_EVENT(local_u32_evt, drv_get_et_strings, + TP_PROTO(struct ieee80211_local *local, u32 sset), + TP_ARGS(local, sset) +); + +DEFINE_EVENT(local_u32_evt, drv_get_et_sset_count, + TP_PROTO(struct ieee80211_local *local, u32 sset), + TP_ARGS(local, sset) +); + +DEFINE_EVENT(local_only_evt, drv_get_et_stats, + TP_PROTO(struct ieee80211_local *local), + TP_ARGS(local) +); + DEFINE_EVENT(local_only_evt, drv_suspend, TP_PROTO(struct ieee80211_local *local), TP_ARGS(local) @@ -171,6 +186,20 @@ DEFINE_EVENT(local_only_evt, drv_resume, TP_ARGS(local) ); +TRACE_EVENT(drv_set_wakeup, + TP_PROTO(struct ieee80211_local *local, bool enabled), + TP_ARGS(local, enabled), + TP_STRUCT__entry( + LOCAL_ENTRY + __field(bool, enabled) + ), + TP_fast_assign( + LOCAL_ASSIGN; + __entry->enabled = enabled; + ), + TP_printk(LOCAL_PR_FMT " enabled:%d", LOCAL_PR_ARG, __entry->enabled) +); + DEFINE_EVENT(local_only_evt, drv_stop, TP_PROTO(struct ieee80211_local *local), TP_ARGS(local) @@ -624,6 +653,34 @@ TRACE_EVENT(drv_sta_state, ) ); +TRACE_EVENT(drv_sta_rc_update, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, + u32 changed), + + TP_ARGS(local, sdata, sta, changed), + + TP_STRUCT__entry( + LOCAL_ENTRY + VIF_ENTRY + STA_ENTRY + __field(u32, changed) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + VIF_ASSIGN; + STA_ASSIGN; + __entry->changed = changed; + ), + + TP_printk( + LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " changed: 0x%x", + LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->changed + ) +); + TRACE_EVENT(drv_sta_add, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, @@ -677,15 +734,14 @@ TRACE_EVENT(drv_sta_remove, TRACE_EVENT(drv_conf_tx, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, - u16 queue, - const struct ieee80211_tx_queue_params *params), + u16 ac, const struct ieee80211_tx_queue_params *params), - TP_ARGS(local, sdata, queue, params), + TP_ARGS(local, sdata, ac, params), TP_STRUCT__entry( LOCAL_ENTRY VIF_ENTRY - __field(u16, queue) + __field(u16, ac) __field(u16, txop) __field(u16, cw_min) __field(u16, cw_max) @@ -696,7 +752,7 @@ TRACE_EVENT(drv_conf_tx, TP_fast_assign( LOCAL_ASSIGN; VIF_ASSIGN; - __entry->queue = queue; + __entry->ac = ac; __entry->txop = params->txop; __entry->cw_max = params->cw_max; __entry->cw_min = params->cw_min; @@ -705,8 +761,8 @@ TRACE_EVENT(drv_conf_tx, ), TP_printk( - LOCAL_PR_FMT VIF_PR_FMT " queue:%d", - LOCAL_PR_ARG, VIF_PR_ARG, __entry->queue + LOCAL_PR_FMT VIF_PR_FMT " AC:%d", + LOCAL_PR_ARG, VIF_PR_ARG, __entry->ac ) ); diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index f25fff7607d..6f8615c54b2 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -19,15 +19,6 @@ #include "ieee80211_i.h" #include "rate.h" -bool ieee80111_cfg_override_disables_ht40(struct ieee80211_sub_if_data *sdata) -{ - const __le16 flg = cpu_to_le16(IEEE80211_HT_CAP_SUP_WIDTH_20_40); - if ((sdata->u.mgd.ht_capa_mask.cap_info & flg) && - !(sdata->u.mgd.ht_capa.cap_info & flg)) - return true; - return false; -} - static void __check_htcap_disable(struct ieee80211_sub_if_data *sdata, struct ieee80211_sta_ht_cap *ht_cap, u16 flag) @@ -315,10 +306,10 @@ void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, initiator = (params & IEEE80211_DELBA_PARAM_INITIATOR_MASK) >> 11; #ifdef CONFIG_MAC80211_HT_DEBUG - if (net_ratelimit()) - printk(KERN_DEBUG "delba from %pM (%s) tid %d reason code %d\n", - mgmt->sa, initiator ? "initiator" : "recipient", tid, - le16_to_cpu(mgmt->u.action.u.delba.reason_code)); + net_dbg_ratelimited("delba from %pM (%s) tid %d reason code %d\n", + mgmt->sa, initiator ? "initiator" : "recipient", + tid, + le16_to_cpu(mgmt->u.action.u.delba.reason_code)); #endif /* CONFIG_MAC80211_HT_DEBUG */ if (initiator == WLAN_BACK_INITIATOR) diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 33fd8d9f714..3ad33a82462 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -66,7 +66,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, skb_reset_tail_pointer(skb); skb_reserve(skb, sdata->local->hw.extra_tx_headroom); - if (compare_ether_addr(ifibss->bssid, bssid)) + if (!ether_addr_equal(ifibss->bssid, bssid)) sta_info_flush(sdata->local, sdata); /* if merging, indicate to driver that we leave the old IBSS */ @@ -160,16 +160,14 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, if (channel_type && sband->ht_cap.ht_supported) { pos = skb_put(skb, 4 + sizeof(struct ieee80211_ht_cap) + - sizeof(struct ieee80211_ht_info)); + sizeof(struct ieee80211_ht_operation)); pos = ieee80211_ie_build_ht_cap(pos, &sband->ht_cap, sband->ht_cap.cap); - pos = ieee80211_ie_build_ht_info(pos, - &sband->ht_cap, - chan, - channel_type); + pos = ieee80211_ie_build_ht_oper(pos, &sband->ht_cap, + chan, channel_type, 0); } - if (local->hw.queues >= 4) { + if (local->hw.queues >= IEEE80211_NUM_ACS) { pos = skb_put(skb, 9); *pos++ = WLAN_EID_VENDOR_SPECIFIC; *pos++ = 7; /* len */ @@ -305,9 +303,8 @@ ieee80211_ibss_add_sta(struct ieee80211_sub_if_data *sdata, * allow new one to be added. */ if (local->num_sta >= IEEE80211_IBSS_MAX_STA_ENTRIES) { - if (net_ratelimit()) - printk(KERN_DEBUG "%s: No room for a new IBSS STA entry %pM\n", - sdata->name, addr); + net_dbg_ratelimited("%s: No room for a new IBSS STA entry %pM\n", + sdata->name, addr); rcu_read_lock(); return NULL; } @@ -317,7 +314,7 @@ ieee80211_ibss_add_sta(struct ieee80211_sub_if_data *sdata, return NULL; } - if (compare_ether_addr(bssid, sdata->u.ibss.bssid)) { + if (!ether_addr_equal(bssid, sdata->u.ibss.bssid)) { rcu_read_lock(); return NULL; } @@ -403,14 +400,14 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, return; if (sdata->vif.type == NL80211_IFTYPE_ADHOC && - compare_ether_addr(mgmt->bssid, sdata->u.ibss.bssid) == 0) { + ether_addr_equal(mgmt->bssid, sdata->u.ibss.bssid)) { rcu_read_lock(); sta = sta_info_get(sdata, mgmt->sa); if (elems->supp_rates) { supp_rates = ieee80211_sta_get_rates(local, elems, - band); + band, NULL); if (sta) { u32 prev_rates; @@ -441,13 +438,13 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, if (sta && elems->wmm_info) set_sta_flag(sta, WLAN_STA_WME); - if (sta && elems->ht_info_elem && elems->ht_cap_elem && + if (sta && elems->ht_operation && elems->ht_cap_elem && sdata->u.ibss.channel_type != NL80211_CHAN_NO_HT) { /* we both use HT */ struct ieee80211_sta_ht_cap sta_ht_cap_new; enum nl80211_channel_type channel_type = - ieee80211_ht_info_to_channel_type( - elems->ht_info_elem); + ieee80211_ht_oper_to_channel_type( + elems->ht_operation); ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband, elems->ht_cap_elem, @@ -457,8 +454,8 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, * fall back to HT20 if we don't use or use * the other extension channel */ - if ((channel_type == NL80211_CHAN_HT40MINUS || - channel_type == NL80211_CHAN_HT40PLUS) && + if (!(channel_type == NL80211_CHAN_HT40MINUS || + channel_type == NL80211_CHAN_HT40PLUS) || channel_type != sdata->u.ibss.channel_type) sta_ht_cap_new.cap &= ~IEEE80211_HT_CAP_SUP_WIDTH_20_40; @@ -508,7 +505,7 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, goto put_bss; /* same BSSID */ - if (compare_ether_addr(cbss->bssid, sdata->u.ibss.bssid) == 0) + if (ether_addr_equal(cbss->bssid, sdata->u.ibss.bssid)) goto put_bss; if (rx_status->flag & RX_FLAG_MACTIME_MPDU) { @@ -560,7 +557,7 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, sdata->name, mgmt->bssid); #endif ieee80211_sta_join_ibss(sdata, bss); - supp_rates = ieee80211_sta_get_rates(local, elems, band); + supp_rates = ieee80211_sta_get_rates(local, elems, band, NULL); ieee80211_ibss_add_sta(sdata, mgmt->bssid, mgmt->sa, supp_rates, true); rcu_read_unlock(); @@ -584,16 +581,15 @@ void ieee80211_ibss_rx_no_sta(struct ieee80211_sub_if_data *sdata, * allow new one to be added. */ if (local->num_sta >= IEEE80211_IBSS_MAX_STA_ENTRIES) { - if (net_ratelimit()) - printk(KERN_DEBUG "%s: No room for a new IBSS STA entry %pM\n", - sdata->name, addr); + net_dbg_ratelimited("%s: No room for a new IBSS STA entry %pM\n", + sdata->name, addr); return; } if (ifibss->state == IEEE80211_IBSS_MLME_SEARCH) return; - if (compare_ether_addr(bssid, sdata->u.ibss.bssid)) + if (!ether_addr_equal(bssid, sdata->u.ibss.bssid)) return; sta = sta_info_alloc(sdata, addr, GFP_ATOMIC); @@ -831,7 +827,7 @@ static void ieee80211_rx_mgmt_probe_req(struct ieee80211_sub_if_data *sdata, if (!tx_last_beacon && is_multicast_ether_addr(mgmt->da)) return; - if (compare_ether_addr(mgmt->bssid, ifibss->bssid) != 0 && + if (!ether_addr_equal(mgmt->bssid, ifibss->bssid) && !is_broadcast_ether_addr(mgmt->bssid)) return; @@ -1063,7 +1059,7 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata, 4 /* IBSS params */ + 2 + (IEEE80211_MAX_SUPP_RATES - 8) + 2 + sizeof(struct ieee80211_ht_cap) + - 2 + sizeof(struct ieee80211_ht_info) + + 2 + sizeof(struct ieee80211_ht_operation) + params->ie_len); if (!skb) return -ENOMEM; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index d9798a307f2..3f3cd50fff1 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -52,7 +52,8 @@ struct ieee80211_local; * increased memory use (about 2 kB of RAM per entry). */ #define IEEE80211_FRAGMENT_MAX 4 -#define TU_TO_EXP_TIME(x) (jiffies + usecs_to_jiffies((x) * 1024)) +#define TU_TO_JIFFIES(x) (usecs_to_jiffies((x) * 1024)) +#define TU_TO_EXP_TIME(x) (jiffies + TU_TO_JIFFIES(x)) #define IEEE80211_DEFAULT_UAPSD_QUEUES \ (IEEE80211_WMM_IE_STA_QOSINFO_AC_BK | \ @@ -281,7 +282,7 @@ struct ieee80211_if_ap { u8 tim[sizeof(unsigned long) * BITS_TO_LONGS(IEEE80211_MAX_AID + 1)]; struct sk_buff_head ps_bc_buf; atomic_t num_sta_ps; /* number of stations in PS mode */ - atomic_t num_sta_authorized; /* number of authorized stations */ + atomic_t num_mcast_sta; /* number of stations receiving multicast */ int dtim_count; bool dtim_bc_mc; }; @@ -378,6 +379,7 @@ enum ieee80211_sta_flags { IEEE80211_STA_UAPSD_ENABLED = BIT(7), IEEE80211_STA_NULLFUNC_ACKED = BIT(8), IEEE80211_STA_RESET_SIGNAL_AVE = BIT(9), + IEEE80211_STA_DISABLE_40MHZ = BIT(10), }; struct ieee80211_mgd_auth_data { @@ -397,7 +399,7 @@ struct ieee80211_mgd_auth_data { struct ieee80211_mgd_assoc_data { struct cfg80211_bss *bss; const u8 *supp_rates; - const u8 *ht_information_ie; + const u8 *ht_operation_ie; unsigned long timeout; int tries; @@ -552,6 +554,24 @@ struct ieee80211_if_ibss { } state; }; +/** + * struct ieee80211_mesh_sync_ops - Extensible synchronization framework interface + * + * these declarations define the interface, which enables + * vendor-specific mesh synchronization + * + */ +struct ieee802_11_elems; +struct ieee80211_mesh_sync_ops { + void (*rx_bcn_presp)(struct ieee80211_sub_if_data *sdata, + u16 stype, + struct ieee80211_mgmt *mgmt, + struct ieee802_11_elems *elems, + struct ieee80211_rx_status *rx_status); + void (*adjust_tbtt)(struct ieee80211_sub_if_data *sdata); + /* add other framework functions here */ +}; + struct ieee80211_if_mesh { struct timer_list housekeeping_timer; struct timer_list mesh_path_timer; @@ -600,6 +620,11 @@ struct ieee80211_if_mesh { IEEE80211_MESH_SEC_AUTHED = 0x1, IEEE80211_MESH_SEC_SECURED = 0x2, } security; + /* Extensible Synchronization Framework */ + struct ieee80211_mesh_sync_ops *sync_ops; + s64 sync_offset_clockdrift_max; + spinlock_t sync_offset_lock; + bool adjusting_tbtt; }; #ifdef CONFIG_MAC80211_MESH @@ -666,12 +691,6 @@ struct ieee80211_sub_if_data { char name[IFNAMSIZ]; - /* - * keep track of whether the HT opmode (stored in - * vif.bss_info.ht_operation_mode) is valid. - */ - bool ht_opmode_valid; - /* to detect idle changes */ bool old_idle; @@ -691,7 +710,7 @@ struct ieee80211_sub_if_data { __be16 control_port_protocol; bool control_port_no_encrypt; - struct ieee80211_tx_queue_params tx_conf[IEEE80211_MAX_QUEUES]; + struct ieee80211_tx_queue_params tx_conf[IEEE80211_NUM_ACS]; struct work_struct work; struct sk_buff_head skb_queue; @@ -761,7 +780,6 @@ enum queue_stop_reason { IEEE80211_QUEUE_STOP_REASON_AGGREGATION, IEEE80211_QUEUE_STOP_REASON_SUSPEND, IEEE80211_QUEUE_STOP_REASON_SKB_ADD, - IEEE80211_QUEUE_STOP_REASON_CHTYPE_CHANGE, }; #ifdef CONFIG_MAC80211_LEDS @@ -785,6 +803,8 @@ struct tpt_led_trigger { * well be on the operating channel * @SCAN_HW_SCANNING: The hardware is scanning for us, we have no way to * determine if we are on the operating channel or not + * @SCAN_ONCHANNEL_SCANNING: Do a software scan on only the current operating + * channel. This should not interrupt normal traffic. * @SCAN_COMPLETED: Set for our scan work function when the driver reported * that the scan completed. * @SCAN_ABORTED: Set for our scan work function when the driver reported @@ -793,6 +813,7 @@ struct tpt_led_trigger { enum { SCAN_SW_SCANNING, SCAN_HW_SCANNING, + SCAN_ONCHANNEL_SCANNING, SCAN_COMPLETED, SCAN_ABORTED, }; @@ -1082,6 +1103,9 @@ struct ieee80211_local { struct net_device napi_dev; struct napi_struct napi; + + /* virtual monitor interface */ + struct ieee80211_sub_if_data __rcu *monitor_sdata; }; static inline struct ieee80211_sub_if_data * @@ -1117,7 +1141,7 @@ struct ieee802_11_elems { u8 *wmm_info; u8 *wmm_param; struct ieee80211_ht_cap *ht_cap_elem; - struct ieee80211_ht_info *ht_info_elem; + struct ieee80211_ht_operation *ht_operation; struct ieee80211_meshconf_ie *mesh_config; u8 *mesh_id; u8 *peering; @@ -1171,7 +1195,7 @@ static inline struct ieee80211_local *hw_to_local( static inline int ieee80211_bssid_match(const u8 *raddr, const u8 *addr) { - return compare_ether_addr(raddr, addr) == 0 || + return ether_addr_equal(raddr, addr) || is_broadcast_ether_addr(raddr); } @@ -1210,7 +1234,7 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); void ieee80211_sta_reset_beacon_monitor(struct ieee80211_sub_if_data *sdata); void ieee80211_sta_reset_conn_monitor(struct ieee80211_sub_if_data *sdata); -void ieee80211_mgd_teardown(struct ieee80211_sub_if_data *sdata); +void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata); /* IBSS code */ void ieee80211_ibss_notify_scan_completed(struct ieee80211_local *local); @@ -1239,6 +1263,7 @@ int ieee80211_request_internal_scan(struct ieee80211_sub_if_data *sdata, int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req); void ieee80211_scan_cancel(struct ieee80211_local *local); +void ieee80211_run_deferred_scan(struct ieee80211_local *local); ieee80211_rx_result ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); @@ -1251,9 +1276,6 @@ ieee80211_bss_info_update(struct ieee80211_local *local, struct ieee802_11_elems *elems, struct ieee80211_channel *channel, bool beacon); -struct ieee80211_bss * -ieee80211_rx_bss_get(struct ieee80211_local *local, u8 *bssid, int freq, - u8 *ssid, u8 ssid_len); void ieee80211_rx_bss_put(struct ieee80211_local *local, struct ieee80211_bss *bss); @@ -1299,7 +1321,6 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev); /* HT */ -bool ieee80111_cfg_override_disables_ht40(struct ieee80211_sub_if_data *sdata); void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata, struct ieee80211_sta_ht_cap *ht_cap); void ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata, @@ -1383,7 +1404,7 @@ static inline int __ieee80211_resume(struct ieee80211_hw *hw) extern void *mac80211_wiphy_privid; /* for wiphy privid */ u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len, enum nl80211_iftype type); -int ieee80211_frame_duration(struct ieee80211_local *local, size_t len, +int ieee80211_frame_duration(enum ieee80211_band band, size_t len, int rate, int erp, int short_preamble); void mac80211_ev_michael_mic_failure(struct ieee80211_sub_if_data *sdata, int keyidx, struct ieee80211_hdr *hdr, const u8 *tsc, @@ -1429,13 +1450,17 @@ void ieee80211_wake_queue_by_reason(struct ieee80211_hw *hw, int queue, enum queue_stop_reason reason); void ieee80211_stop_queue_by_reason(struct ieee80211_hw *hw, int queue, enum queue_stop_reason reason); +void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue); void ieee80211_add_pending_skb(struct ieee80211_local *local, struct sk_buff *skb); -void ieee80211_add_pending_skbs(struct ieee80211_local *local, - struct sk_buff_head *skbs); void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local, struct sk_buff_head *skbs, void (*fn)(void *data), void *data); +static inline void ieee80211_add_pending_skbs(struct ieee80211_local *local, + struct sk_buff_head *skbs) +{ + ieee80211_add_pending_skbs_fn(local, skbs, NULL, NULL); +} void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, u16 transaction, u16 auth_alg, @@ -1460,7 +1485,7 @@ void ieee80211_sta_def_wmm_params(struct ieee80211_sub_if_data *sdata, const u8 *supp_rates); u32 ieee80211_sta_get_rates(struct ieee80211_local *local, struct ieee802_11_elems *elems, - enum ieee80211_band band); + enum ieee80211_band band, u32 *basic_rates); int __ieee80211_request_smps(struct ieee80211_sub_if_data *sdata, enum ieee80211_smps_mode smps_mode); void ieee80211_recalc_smps(struct ieee80211_local *local); @@ -1470,10 +1495,10 @@ size_t ieee80211_ie_split(const u8 *ies, size_t ielen, size_t ieee80211_ie_split_vendor(const u8 *ies, size_t ielen, size_t offset); u8 *ieee80211_ie_build_ht_cap(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, u16 cap); -u8 *ieee80211_ie_build_ht_info(u8 *pos, - struct ieee80211_sta_ht_cap *ht_cap, - struct ieee80211_channel *channel, - enum nl80211_channel_type channel_type); +u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, + struct ieee80211_channel *channel, + enum nl80211_channel_type channel_type, + u16 prot_mode); /* internal work items */ void ieee80211_work_init(struct ieee80211_local *local); @@ -1501,10 +1526,7 @@ bool ieee80211_set_channel_type(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, enum nl80211_channel_type chantype); enum nl80211_channel_type -ieee80211_ht_info_to_channel_type(struct ieee80211_ht_info *ht_info); -enum nl80211_channel_type ieee80211_get_tx_channel_type( - struct ieee80211_local *local, - enum nl80211_channel_type channel_type); +ieee80211_ht_oper_to_channel_type(struct ieee80211_ht_operation *ht_oper); #ifdef CONFIG_MAC80211_NOINLINE #define debug_noinline noinline diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 401c01f0731..856237c5c1f 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -127,7 +127,7 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata, * The remaining checks are only performed for interfaces * with the same MAC address. */ - if (compare_ether_addr(dev->dev_addr, ndev->dev_addr)) + if (!ether_addr_equal(dev->dev_addr, ndev->dev_addr)) continue; /* @@ -149,6 +149,35 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata, return 0; } +static int ieee80211_check_queues(struct ieee80211_sub_if_data *sdata) +{ + int n_queues = sdata->local->hw.queues; + int i; + + for (i = 0; i < IEEE80211_NUM_ACS; i++) { + if (WARN_ON_ONCE(sdata->vif.hw_queue[i] == + IEEE80211_INVAL_HW_QUEUE)) + return -EINVAL; + if (WARN_ON_ONCE(sdata->vif.hw_queue[i] >= + n_queues)) + return -EINVAL; + } + + if ((sdata->vif.type != NL80211_IFTYPE_AP) || + !(sdata->local->hw.flags & IEEE80211_HW_QUEUE_CONTROL)) { + sdata->vif.cab_queue = IEEE80211_INVAL_HW_QUEUE; + return 0; + } + + if (WARN_ON_ONCE(sdata->vif.cab_queue == IEEE80211_INVAL_HW_QUEUE)) + return -EINVAL; + + if (WARN_ON_ONCE(sdata->vif.cab_queue >= n_queues)) + return -EINVAL; + + return 0; +} + void ieee80211_adjust_monitor_flags(struct ieee80211_sub_if_data *sdata, const int offset) { @@ -169,6 +198,81 @@ void ieee80211_adjust_monitor_flags(struct ieee80211_sub_if_data *sdata, #undef ADJUST } +static void ieee80211_set_default_queues(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + int i; + + for (i = 0; i < IEEE80211_NUM_ACS; i++) { + if (local->hw.flags & IEEE80211_HW_QUEUE_CONTROL) + sdata->vif.hw_queue[i] = IEEE80211_INVAL_HW_QUEUE; + else + sdata->vif.hw_queue[i] = i; + } + sdata->vif.cab_queue = IEEE80211_INVAL_HW_QUEUE; +} + +static int ieee80211_add_virtual_monitor(struct ieee80211_local *local) +{ + struct ieee80211_sub_if_data *sdata; + int ret; + + if (!(local->hw.flags & IEEE80211_HW_WANT_MONITOR_VIF)) + return 0; + + if (local->monitor_sdata) + return 0; + + sdata = kzalloc(sizeof(*sdata) + local->hw.vif_data_size, GFP_KERNEL); + if (!sdata) + return -ENOMEM; + + /* set up data */ + sdata->local = local; + sdata->vif.type = NL80211_IFTYPE_MONITOR; + snprintf(sdata->name, IFNAMSIZ, "%s-monitor", + wiphy_name(local->hw.wiphy)); + + ieee80211_set_default_queues(sdata); + + ret = drv_add_interface(local, sdata); + if (WARN_ON(ret)) { + /* ok .. stupid driver, it asked for this! */ + kfree(sdata); + return ret; + } + + ret = ieee80211_check_queues(sdata); + if (ret) { + kfree(sdata); + return ret; + } + + rcu_assign_pointer(local->monitor_sdata, sdata); + + return 0; +} + +static void ieee80211_del_virtual_monitor(struct ieee80211_local *local) +{ + struct ieee80211_sub_if_data *sdata; + + if (!(local->hw.flags & IEEE80211_HW_WANT_MONITOR_VIF)) + return; + + sdata = rtnl_dereference(local->monitor_sdata); + + if (!sdata) + return; + + rcu_assign_pointer(local->monitor_sdata, NULL); + synchronize_net(); + + drv_remove_interface(local, sdata); + + kfree(sdata); +} + /* * NOTE: Be very careful when changing this function, it must NOT return * an error on interface type changes that have been pre-checked, so most @@ -246,15 +350,18 @@ static int ieee80211_do_open(struct net_device *dev, bool coming_up) memcpy(dev->perm_addr, dev->dev_addr, ETH_ALEN); if (!is_valid_ether_addr(dev->dev_addr)) { - if (!local->open_count) - drv_stop(local); - return -EADDRNOTAVAIL; + res = -EADDRNOTAVAIL; + goto err_stop; } } switch (sdata->vif.type) { case NL80211_IFTYPE_AP_VLAN: - /* no need to tell driver */ + /* no need to tell driver, but set carrier */ + if (rtnl_dereference(sdata->bss->beacon)) + netif_carrier_on(dev); + else + netif_carrier_off(dev); break; case NL80211_IFTYPE_MONITOR: if (sdata->u.mntr_flags & MONITOR_FLAG_COOK_FRAMES) { @@ -262,6 +369,12 @@ static int ieee80211_do_open(struct net_device *dev, bool coming_up) break; } + if (local->monitors == 0 && local->open_count == 0) { + res = ieee80211_add_virtual_monitor(local); + if (res) + goto err_stop; + } + /* must be before the call to ieee80211_configure_filter */ local->monitors++; if (local->monitors == 1) { @@ -276,9 +389,14 @@ static int ieee80211_do_open(struct net_device *dev, bool coming_up) break; default: if (coming_up) { + ieee80211_del_virtual_monitor(local); + res = drv_add_interface(local, sdata); if (res) goto err_stop; + res = ieee80211_check_queues(sdata); + if (res) + goto err_del_interface; } if (sdata->vif.type == NL80211_IFTYPE_AP) { @@ -294,7 +412,8 @@ static int ieee80211_do_open(struct net_device *dev, bool coming_up) ieee80211_bss_info_change_notify(sdata, changed); if (sdata->vif.type == NL80211_IFTYPE_STATION || - sdata->vif.type == NL80211_IFTYPE_ADHOC) + sdata->vif.type == NL80211_IFTYPE_ADHOC || + sdata->vif.type == NL80211_IFTYPE_AP) netif_carrier_off(dev); else netif_carrier_on(dev); @@ -366,6 +485,7 @@ static int ieee80211_do_open(struct net_device *dev, bool coming_up) sdata->bss = NULL; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) list_del(&sdata->u.vlan.list); + /* might already be clear but that doesn't matter */ clear_bit(SDATA_STATE_RUNNING, &sdata->state); return res; } @@ -486,6 +606,8 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, /* free all potentially still buffered bcast frames */ local->total_ps_buffered -= skb_queue_len(&sdata->u.ap.ps_bc_buf); skb_queue_purge(&sdata->u.ap.ps_bc_buf); + } else if (sdata->vif.type == NL80211_IFTYPE_STATION) { + ieee80211_mgd_stop(sdata); } if (going_down) @@ -506,6 +628,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, if (local->monitors == 0) { local->hw.conf.flags &= ~IEEE80211_CONF_MONITOR; hw_reconf_flags |= IEEE80211_CONF_CHANGE_MONITOR; + ieee80211_del_virtual_monitor(local); } ieee80211_adjust_monitor_flags(sdata, -1); @@ -579,6 +702,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, } } spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + + if (local->monitors == local->open_count && local->monitors > 0) + ieee80211_add_virtual_monitor(local); } static int ieee80211_stop(struct net_device *dev) @@ -644,8 +770,6 @@ static void ieee80211_teardown_sdata(struct net_device *dev) if (ieee80211_vif_is_mesh(&sdata->vif)) mesh_rmc_free(sdata); - else if (sdata->vif.type == NL80211_IFTYPE_STATION) - ieee80211_mgd_teardown(sdata); flushed = sta_info_flush(local, sdata); WARN_ON(flushed); @@ -676,7 +800,7 @@ static u16 ieee80211_monitor_select_queue(struct net_device *dev, struct ieee80211_hdr *hdr; struct ieee80211_radiotap_header *rtap = (void *)skb->data; - if (local->hw.queues < 4) + if (local->hw.queues < IEEE80211_NUM_ACS) return 0; if (skb->len < 4 || @@ -907,6 +1031,18 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, ieee80211_debugfs_add_netdev(sdata); } +static void ieee80211_clean_sdata(struct ieee80211_sub_if_data *sdata) +{ + switch (sdata->vif.type) { + case NL80211_IFTYPE_MESH_POINT: + mesh_path_flush_by_iface(sdata); + break; + + default: + break; + } +} + static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, enum nl80211_iftype type) { @@ -970,6 +1106,13 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, if (ret) type = sdata->vif.type; + /* + * Ignore return value here, there's not much we can do since + * the driver changed the interface type internally already. + * The warnings will hopefully make driver authors fix it :-) + */ + ieee80211_check_queues(sdata); + ieee80211_setup_sdata(sdata, type); err = ieee80211_do_open(sdata->dev, false); @@ -1133,11 +1276,15 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, struct net_device *ndev; struct ieee80211_sub_if_data *sdata = NULL; int ret, i; + int txqs = 1; ASSERT_RTNL(); + if (local->hw.queues >= IEEE80211_NUM_ACS) + txqs = IEEE80211_NUM_ACS; + ndev = alloc_netdev_mqs(sizeof(*sdata) + local->hw.vif_data_size, - name, ieee80211_if_setup, local->hw.queues, 1); + name, ieee80211_if_setup, txqs, 1); if (!ndev) return -ENOMEM; dev_net_set(ndev, wiphy_net(local->hw.wiphy)); @@ -1192,6 +1339,8 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, sizeof(sdata->rc_rateidx_mcs_mask[i])); } + ieee80211_set_default_queues(sdata); + /* setup type-dependent data */ ieee80211_setup_sdata(sdata, type); @@ -1227,8 +1376,8 @@ void ieee80211_if_remove(struct ieee80211_sub_if_data *sdata) list_del_rcu(&sdata->list); mutex_unlock(&sdata->local->iflist_mtx); - if (ieee80211_vif_is_mesh(&sdata->vif)) - mesh_path_flush_by_iface(sdata); + /* clean up type-dependent data */ + ieee80211_clean_sdata(sdata); synchronize_rcu(); unregister_netdevice(sdata->dev); @@ -1249,8 +1398,7 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) { list_del(&sdata->list); - if (ieee80211_vif_is_mesh(&sdata->vif)) - mesh_path_flush_by_iface(sdata); + ieee80211_clean_sdata(sdata); unregister_netdevice_queue(sdata->dev, &unreg_list); } diff --git a/net/mac80211/main.c b/net/mac80211/main.c index b581a24fa15..b70f7f09da6 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -47,7 +47,8 @@ void ieee80211_configure_filter(struct ieee80211_local *local) if (atomic_read(&local->iff_allmultis)) new_flags |= FIF_ALLMULTI; - if (local->monitors || test_bit(SCAN_SW_SCANNING, &local->scanning)) + if (local->monitors || test_bit(SCAN_SW_SCANNING, &local->scanning) || + test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning)) new_flags |= FIF_BCN_PRBRESP_PROMISC; if (local->fif_probe_req || local->probe_req_reg) @@ -102,9 +103,6 @@ int ieee80211_hw_config(struct ieee80211_local *local, u32 changed) might_sleep(); - /* If this off-channel logic ever changes, ieee80211_on_oper_channel - * may need to change as well. - */ offchannel_flag = local->hw.conf.flags & IEEE80211_CONF_OFFCHANNEL; if (local->scan_channel) { chan = local->scan_channel; @@ -151,6 +149,7 @@ int ieee80211_hw_config(struct ieee80211_local *local, u32 changed) } if (test_bit(SCAN_SW_SCANNING, &local->scanning) || + test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning) || test_bit(SCAN_HW_SCANNING, &local->scanning)) power = chan->max_power; else @@ -560,8 +559,10 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, WIPHY_FLAG_4ADDR_AP | WIPHY_FLAG_4ADDR_STATION | WIPHY_FLAG_REPORTS_OBSS | - WIPHY_FLAG_OFFCHAN_TX | - WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL; + WIPHY_FLAG_OFFCHAN_TX; + + if (ops->remain_on_channel) + wiphy->flags |= WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL; wiphy->features = NL80211_FEATURE_SK_TX_STATUS | NL80211_FEATURE_HT_IBSS; @@ -592,6 +593,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, local->hw.max_report_rates = 0; local->hw.max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF; local->hw.max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF; + local->hw.offchannel_tx_hw_queue = IEEE80211_INVAL_HW_QUEUE; local->hw.conf.long_frame_max_tx_count = wiphy->retry_long; local->hw.conf.short_frame_max_tx_count = wiphy->retry_short; local->user_power_level = -1; @@ -688,6 +690,11 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) WLAN_CIPHER_SUITE_AES_CMAC }; + if (hw->flags & IEEE80211_HW_QUEUE_CONTROL && + (local->hw.offchannel_tx_hw_queue == IEEE80211_INVAL_HW_QUEUE || + local->hw.offchannel_tx_hw_queue >= local->hw.queues)) + return -EINVAL; + if ((hw->wiphy->wowlan.flags || hw->wiphy->wowlan.n_patterns) #ifdef CONFIG_PM && (!local->ops->suspend || !local->ops->resume) diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index e5fbb7cf356..0675a2fec6a 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -13,9 +13,6 @@ #include "ieee80211_i.h" #include "mesh.h" -#define MESHCONF_CAPAB_ACCEPT_PLINKS 0x01 -#define MESHCONF_CAPAB_FORWARDING 0x08 - #define TMR_RUNNING_HK 0 #define TMR_RUNNING_MP 1 #define TMR_RUNNING_MPR 2 @@ -67,16 +64,19 @@ static void ieee80211_mesh_housekeeping_timer(unsigned long data) /** * mesh_matches_local - check if the config of a mesh point matches ours * - * @ie: information elements of a management frame from the mesh peer * @sdata: local mesh subif + * @ie: information elements of a management frame from the mesh peer * * This function checks if the mesh configuration of a mesh point matches the * local mesh configuration, i.e. if both nodes belong to the same mesh network. */ -bool mesh_matches_local(struct ieee802_11_elems *ie, struct ieee80211_sub_if_data *sdata) +bool mesh_matches_local(struct ieee80211_sub_if_data *sdata, + struct ieee802_11_elems *ie) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct ieee80211_local *local = sdata->local; + u32 basic_rates = 0; + enum nl80211_channel_type sta_channel_type = NL80211_CHAN_NO_HT; /* * As support for each feature is added, check for matching @@ -97,10 +97,21 @@ bool mesh_matches_local(struct ieee802_11_elems *ie, struct ieee80211_sub_if_dat (ifmsh->mesh_auth_id == ie->mesh_config->meshconf_auth))) goto mismatch; - /* disallow peering with mismatched channel types for now */ - if (ie->ht_info_elem && - (local->_oper_channel_type != - ieee80211_ht_info_to_channel_type(ie->ht_info_elem))) + ieee80211_sta_get_rates(local, ie, local->oper_channel->band, + &basic_rates); + + if (sdata->vif.bss_conf.basic_rates != basic_rates) + goto mismatch; + + if (ie->ht_operation) + sta_channel_type = + ieee80211_ht_oper_to_channel_type(ie->ht_operation); + + /* Disallow HT40+/- mismatch */ + if (ie->ht_operation && + local->_oper_channel_type > NL80211_CHAN_HT20 && + sta_channel_type > NL80211_CHAN_HT20 && + local->_oper_channel_type != sta_channel_type) goto mismatch; return true; @@ -204,7 +215,7 @@ int mesh_rmc_check(u8 *sa, struct ieee80211s_hdr *mesh_hdr, kmem_cache_free(rm_cache, p); --entries; } else if ((seqnum == p->seqnum) && - (compare_ether_addr(sa, p->sa) == 0)) + (ether_addr_equal(sa, p->sa))) return -1; } @@ -251,8 +262,10 @@ mesh_add_meshconf_ie(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata) /* Mesh capability */ ifmsh->accepting_plinks = mesh_plink_availables(sdata); *pos = MESHCONF_CAPAB_FORWARDING; - *pos++ |= ifmsh->accepting_plinks ? + *pos |= ifmsh->accepting_plinks ? MESHCONF_CAPAB_ACCEPT_PLINKS : 0x00; + *pos++ |= ifmsh->adjusting_tbtt ? + MESHCONF_CAPAB_TBTT_ADJUSTING : 0x00; *pos++ = 0x00; return 0; @@ -371,7 +384,7 @@ int mesh_add_ht_cap_ie(struct sk_buff *skb, return 0; } -int mesh_add_ht_info_ie(struct sk_buff *skb, +int mesh_add_ht_oper_ie(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; @@ -385,11 +398,12 @@ int mesh_add_ht_info_ie(struct sk_buff *skb, if (!ht_cap->ht_supported || channel_type == NL80211_CHAN_NO_HT) return 0; - if (skb_tailroom(skb) < 2 + sizeof(struct ieee80211_ht_info)) + if (skb_tailroom(skb) < 2 + sizeof(struct ieee80211_ht_operation)) return -ENOMEM; - pos = skb_put(skb, 2 + sizeof(struct ieee80211_ht_info)); - ieee80211_ie_build_ht_info(pos, ht_cap, channel, channel_type); + pos = skb_put(skb, 2 + sizeof(struct ieee80211_ht_operation)); + ieee80211_ie_build_ht_oper(pos, ht_cap, channel, channel_type, + sdata->vif.bss_conf.ht_operation_mode); return 0; } @@ -573,14 +587,24 @@ void ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata) ieee80211_configure_filter(local); ifmsh->mesh_cc_id = 0; /* Disabled */ - ifmsh->mesh_sp_id = 0; /* Neighbor Offset */ ifmsh->mesh_auth_id = 0; /* Disabled */ + /* register sync ops from extensible synchronization framework */ + ifmsh->sync_ops = ieee80211_mesh_sync_ops_get(ifmsh->mesh_sp_id); + ifmsh->adjusting_tbtt = false; + ifmsh->sync_offset_clockdrift_max = 0; set_bit(MESH_WORK_HOUSEKEEPING, &ifmsh->wrkq_flags); ieee80211_mesh_root_setup(ifmsh); ieee80211_queue_work(&local->hw, &sdata->work); + sdata->vif.bss_conf.ht_operation_mode = + ifmsh->mshcfg.ht_opmode; sdata->vif.bss_conf.beacon_int = MESH_DEFAULT_BEACON_INTERVAL; + sdata->vif.bss_conf.basic_rates = + ieee80211_mandatory_rates(sdata->local, + sdata->local->hw.conf.channel->band); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON | BSS_CHANGED_BEACON_ENABLED | + BSS_CHANGED_HT | + BSS_CHANGED_BASIC_RATES | BSS_CHANGED_BEACON_INT); } @@ -616,16 +640,16 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, struct ieee80211_rx_status *rx_status) { struct ieee80211_local *local = sdata->local; + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct ieee802_11_elems elems; struct ieee80211_channel *channel; - u32 supp_rates = 0; size_t baselen; int freq; enum ieee80211_band band = rx_status->band; /* ignore ProbeResp to foreign address */ if (stype == IEEE80211_STYPE_PROBE_RESP && - compare_ether_addr(mgmt->da, sdata->vif.addr)) + !ether_addr_equal(mgmt->da, sdata->vif.addr)) return; baselen = (u8 *) mgmt->u.probe_resp.variable - (u8 *) mgmt; @@ -650,10 +674,12 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, return; if (elems.mesh_id && elems.mesh_config && - mesh_matches_local(&elems, sdata)) { - supp_rates = ieee80211_sta_get_rates(local, &elems, band); - mesh_neighbour_update(mgmt->sa, supp_rates, sdata, &elems); - } + mesh_matches_local(sdata, &elems)) + mesh_neighbour_update(sdata, mgmt->sa, &elems); + + if (ifmsh->sync_ops) + ifmsh->sync_ops->rx_bcn_presp(sdata, + stype, mgmt, &elems, rx_status); } static void ieee80211_mesh_rx_mgmt_action(struct ieee80211_sub_if_data *sdata, @@ -721,6 +747,9 @@ void ieee80211_mesh_work(struct ieee80211_sub_if_data *sdata) if (test_and_clear_bit(MESH_WORK_ROOT, &ifmsh->wrkq_flags)) ieee80211_mesh_rootpath(sdata); + + if (test_and_clear_bit(MESH_WORK_DRIFT_ADJUST, &ifmsh->wrkq_flags)) + mesh_sync_adjust_tbtt(sdata); } void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local) @@ -761,4 +790,5 @@ void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata) (unsigned long) sdata); INIT_LIST_HEAD(&ifmsh->preq_queue.list); spin_lock_init(&ifmsh->mesh_preq_queue_lock); + spin_lock_init(&ifmsh->sync_offset_lock); } diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 8d53b71378e..e3642756f8f 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -19,6 +19,20 @@ /* Data structures */ /** + * enum mesh_config_capab_flags - mesh config IE capability flags + * + * @MESHCONF_CAPAB_ACCEPT_PLINKS: STA is willing to establish + * additional mesh peerings with other mesh STAs + * @MESHCONF_CAPAB_FORWARDING: the STA forwards MSDUs + * @MESHCONF_CAPAB_TBTT_ADJUSTING: TBTT adjustment procedure is ongoing + */ +enum mesh_config_capab_flags { + MESHCONF_CAPAB_ACCEPT_PLINKS = BIT(0), + MESHCONF_CAPAB_FORWARDING = BIT(3), + MESHCONF_CAPAB_TBTT_ADJUSTING = BIT(5), +}; + +/** * enum mesh_path_flags - mac80211 mesh path flags * * @@ -56,12 +70,15 @@ enum mesh_path_flags { * @MESH_WORK_GROW_MPP_TABLE: the mesh portals table is full and needs to * grow * @MESH_WORK_ROOT: the mesh root station needs to send a frame + * @MESH_WORK_DRIFT_ADJUST: time to compensate for clock drift relative to other + * mesh nodes */ enum mesh_deferred_task_flags { MESH_WORK_HOUSEKEEPING, MESH_WORK_GROW_MPATH_TABLE, MESH_WORK_GROW_MPP_TABLE, MESH_WORK_ROOT, + MESH_WORK_DRIFT_ADJUST, }; /** @@ -86,6 +103,7 @@ enum mesh_deferred_task_flags { * mpath itself. No need to take this lock when adding or removing * an mpath to a hash bucket on a path table. * @rann_snd_addr: the RANN sender address + * @rann_metric: the aggregated path metric towards the root node * @is_root: the destination station of this path is a root node * @is_gate: the destination station of this path is a mesh gate * @@ -112,6 +130,7 @@ struct mesh_path { enum mesh_path_flags flags; spinlock_t state_lock; u8 rann_snd_addr[ETH_ALEN]; + u32 rann_metric; bool is_root; bool is_gate; }; @@ -203,8 +222,8 @@ int ieee80211_new_mesh_header(struct ieee80211s_hdr *meshhdr, char *addr6); int mesh_rmc_check(u8 *addr, struct ieee80211s_hdr *mesh_hdr, struct ieee80211_sub_if_data *sdata); -bool mesh_matches_local(struct ieee802_11_elems *ie, - struct ieee80211_sub_if_data *sdata); +bool mesh_matches_local(struct ieee80211_sub_if_data *sdata, + struct ieee802_11_elems *ie); void mesh_ids_set_default(struct ieee80211_if_mesh *mesh); void mesh_mgmt_ies_add(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata); @@ -220,7 +239,7 @@ int mesh_add_ds_params_ie(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata); int mesh_add_ht_cap_ie(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata); -int mesh_add_ht_info_ie(struct sk_buff *skb, +int mesh_add_ht_oper_ie(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata); void mesh_rmc_free(struct ieee80211_sub_if_data *sdata); int mesh_rmc_init(struct ieee80211_sub_if_data *sdata); @@ -232,6 +251,7 @@ void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata); void ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata); void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata); void ieee80211_mesh_root_setup(struct ieee80211_if_mesh *ifmsh); +struct ieee80211_mesh_sync_ops *ieee80211_mesh_sync_ops_get(u8 method); /* Mesh paths */ int mesh_nexthop_lookup(struct sk_buff *skb, @@ -256,9 +276,9 @@ int mesh_path_add_gate(struct mesh_path *mpath); int mesh_path_send_to_gates(struct mesh_path *mpath); int mesh_gate_num(struct ieee80211_sub_if_data *sdata); /* Mesh plinks */ -void mesh_neighbour_update(u8 *hw_addr, u32 rates, - struct ieee80211_sub_if_data *sdata, - struct ieee802_11_elems *ie); +void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata, + u8 *hw_addr, + struct ieee802_11_elems *ie); bool mesh_peer_accepts_plinks(struct ieee802_11_elems *ie); void mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata); void mesh_plink_broken(struct sta_info *sta); @@ -284,7 +304,6 @@ void mesh_pathtbl_unregister(void); int mesh_path_del(u8 *addr, struct ieee80211_sub_if_data *sdata); void mesh_path_timer(unsigned long data); void mesh_path_flush_by_nexthop(struct sta_info *sta); -void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata); void mesh_path_discard_frame(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata); void mesh_path_quiesce(struct ieee80211_sub_if_data *sdata); @@ -325,6 +344,8 @@ void ieee80211_mesh_quiesce(struct ieee80211_sub_if_data *sdata); void ieee80211_mesh_restart(struct ieee80211_sub_if_data *sdata); void mesh_plink_quiesce(struct sta_info *sta); void mesh_plink_restart(struct sta_info *sta); +void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata); +void mesh_sync_adjust_tbtt(struct ieee80211_sub_if_data *sdata); #else #define mesh_allocated 0 static inline void @@ -337,6 +358,8 @@ static inline void mesh_plink_quiesce(struct sta_info *sta) {} static inline void mesh_plink_restart(struct sta_info *sta) {} static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata) { return false; } +static inline void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata) +{} #endif #endif /* IEEE80211S_H */ diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 1c6f3d02aeb..27e0c2f0679 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -86,8 +86,8 @@ static inline u32 u16_field_get(u8 *preq_elem, int offset, bool ae) #define PERR_IE_TARGET_RCODE(x) u16_field_get(x, 13, 0) #define MSEC_TO_TU(x) (x*1000/1024) -#define SN_GT(x, y) ((long) (y) - (long) (x) < 0) -#define SN_LT(x, y) ((long) (x) - (long) (y) < 0) +#define SN_GT(x, y) ((s32)(y - x) < 0) +#define SN_LT(x, y) ((s32)(x - y) < 0) #define net_traversal_jiffies(s) \ msecs_to_jiffies(s->u.mesh.mshcfg.dot11MeshHWMPnetDiameterTraversalTime) @@ -422,7 +422,7 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, new_metric = MAX_METRIC; exp_time = TU_TO_EXP_TIME(orig_lifetime); - if (compare_ether_addr(orig_addr, sdata->vif.addr) == 0) { + if (ether_addr_equal(orig_addr, sdata->vif.addr)) { /* This MP is the originator, we are not interested in this * frame, except for updating transmitter's path info. */ @@ -472,7 +472,7 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, /* Update and check transmitter routing info */ ta = mgmt->sa; - if (compare_ether_addr(orig_addr, ta) == 0) + if (ether_addr_equal(orig_addr, ta)) fresh_info = false; else { fresh_info = true; @@ -533,7 +533,7 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, mhwmp_dbg("received PREQ from %pM", orig_addr); - if (compare_ether_addr(target_addr, sdata->vif.addr) == 0) { + if (ether_addr_equal(target_addr, sdata->vif.addr)) { mhwmp_dbg("PREQ is for us"); forward = false; reply = true; @@ -631,7 +631,7 @@ static void hwmp_prep_frame_process(struct ieee80211_sub_if_data *sdata, mhwmp_dbg("received PREP from %pM", PREP_IE_ORIG_ADDR(prep_elem)); orig_addr = PREP_IE_ORIG_ADDR(prep_elem); - if (compare_ether_addr(orig_addr, sdata->vif.addr) == 0) + if (ether_addr_equal(orig_addr, sdata->vif.addr)) /* destination, no forwarding required */ return; @@ -709,7 +709,7 @@ static void hwmp_perr_frame_process(struct ieee80211_sub_if_data *sdata, spin_lock_bh(&mpath->state_lock); sta = next_hop_deref_protected(mpath); if (mpath->flags & MESH_PATH_ACTIVE && - compare_ether_addr(ta, sta->sta.addr) == 0 && + ether_addr_equal(ta, sta->sta.addr) && (!(mpath->flags & MESH_PATH_SN_VALID) || SN_GT(target_sn, mpath->sn))) { mpath->flags &= ~MESH_PATH_ACTIVE; @@ -732,11 +732,12 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, struct ieee80211_rann_ie *rann) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; struct mesh_path *mpath; u8 ttl, flags, hopcount; u8 *orig_addr; - u32 orig_sn, metric; - u32 interval = ifmsh->mshcfg.dot11MeshHWMPRannInterval; + u32 orig_sn, metric, metric_txsta, interval; bool root_is_gate; ttl = rann->rann_ttl; @@ -748,19 +749,28 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, flags = rann->rann_flags; root_is_gate = !!(flags & RANN_FLAG_IS_GATE); orig_addr = rann->rann_addr; - orig_sn = rann->rann_seq; + orig_sn = le32_to_cpu(rann->rann_seq); + interval = le32_to_cpu(rann->rann_interval); hopcount = rann->rann_hopcount; hopcount++; - metric = rann->rann_metric; + metric = le32_to_cpu(rann->rann_metric); /* Ignore our own RANNs */ - if (compare_ether_addr(orig_addr, sdata->vif.addr) == 0) + if (ether_addr_equal(orig_addr, sdata->vif.addr)) return; mhwmp_dbg("received RANN from %pM via neighbour %pM (is_gate=%d)", orig_addr, mgmt->sa, root_is_gate); rcu_read_lock(); + sta = sta_info_get(sdata, mgmt->sa); + if (!sta) { + rcu_read_unlock(); + return; + } + + metric_txsta = airtime_link_metric_get(local, sta); + mpath = mesh_path_lookup(orig_addr, sdata); if (!mpath) { mesh_path_add(orig_addr, sdata); @@ -780,18 +790,21 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, mesh_queue_preq(mpath, PREQ_Q_F_START | PREQ_Q_F_REFRESH); } - if (mpath->sn < orig_sn && ifmsh->mshcfg.dot11MeshForwarding) { + if ((SN_LT(mpath->sn, orig_sn) || (mpath->sn == orig_sn && + metric < mpath->rann_metric)) && ifmsh->mshcfg.dot11MeshForwarding) { mesh_path_sel_frame_tx(MPATH_RANN, flags, orig_addr, cpu_to_le32(orig_sn), 0, NULL, 0, broadcast_addr, hopcount, ttl, cpu_to_le32(interval), - cpu_to_le32(metric + mpath->metric), + cpu_to_le32(metric + metric_txsta), 0, sdata); mpath->sn = orig_sn; + mpath->rann_metric = metric + metric_txsta; + /* Recording RANNs sender address to send individually + * addressed PREQs destined for root mesh STA */ + memcpy(mpath->rann_snd_addr, mgmt->sa, ETH_ALEN); } - /* Using individually addressed PREQ for root node */ - memcpy(mpath->rann_snd_addr, mgmt->sa, ETH_ALEN); mpath->is_root = true; if (root_is_gate) @@ -1086,7 +1099,7 @@ int mesh_nexthop_lookup(struct sk_buff *skb, if (time_after(jiffies, mpath->exp_time - msecs_to_jiffies(sdata->u.mesh.mshcfg.path_refresh_time)) && - !compare_ether_addr(sdata->vif.addr, hdr->addr4) && + ether_addr_equal(sdata->vif.addr, hdr->addr4) && !(mpath->flags & MESH_PATH_RESOLVING) && !(mpath->flags & MESH_PATH_FIXED)) mesh_queue_preq(mpath, PREQ_Q_F_START | PREQ_Q_F_REFRESH); diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 49aaefd9963..b39224d8255 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -348,7 +348,7 @@ static struct mesh_path *mpath_lookup(struct mesh_table *tbl, u8 *dst, hlist_for_each_entry_rcu(node, n, bucket, list) { mpath = node->mpath; if (mpath->sdata == sdata && - compare_ether_addr(dst, mpath->dst) == 0) { + ether_addr_equal(dst, mpath->dst)) { if (MPATH_EXPIRED(mpath)) { spin_lock_bh(&mpath->state_lock); mpath->flags &= ~MESH_PATH_ACTIVE; @@ -517,7 +517,7 @@ int mesh_path_add(u8 *dst, struct ieee80211_sub_if_data *sdata) int err = 0; u32 hash_idx; - if (compare_ether_addr(dst, sdata->vif.addr) == 0) + if (ether_addr_equal(dst, sdata->vif.addr)) /* never add ourselves as neighbours */ return -ENOTSUPP; @@ -538,6 +538,8 @@ int mesh_path_add(u8 *dst, struct ieee80211_sub_if_data *sdata) read_lock_bh(&pathtbl_resize_lock); memcpy(new_mpath->dst, dst, ETH_ALEN); + memset(new_mpath->rann_snd_addr, 0xff, ETH_ALEN); + new_mpath->is_root = false; new_mpath->sdata = sdata; new_mpath->flags = 0; skb_queue_head_init(&new_mpath->frame_queue); @@ -559,7 +561,7 @@ int mesh_path_add(u8 *dst, struct ieee80211_sub_if_data *sdata) hlist_for_each_entry(node, n, bucket, list) { mpath = node->mpath; if (mpath->sdata == sdata && - compare_ether_addr(dst, mpath->dst) == 0) + ether_addr_equal(dst, mpath->dst)) goto err_exists; } @@ -650,7 +652,7 @@ int mpp_path_add(u8 *dst, u8 *mpp, struct ieee80211_sub_if_data *sdata) int err = 0; u32 hash_idx; - if (compare_ether_addr(dst, sdata->vif.addr) == 0) + if (ether_addr_equal(dst, sdata->vif.addr)) /* never add ourselves as neighbours */ return -ENOTSUPP; @@ -688,7 +690,7 @@ int mpp_path_add(u8 *dst, u8 *mpp, struct ieee80211_sub_if_data *sdata) hlist_for_each_entry(node, n, bucket, list) { mpath = node->mpath; if (mpath->sdata == sdata && - compare_ether_addr(dst, mpath->dst) == 0) + ether_addr_equal(dst, mpath->dst)) goto err_exists; } @@ -882,7 +884,7 @@ int mesh_path_del(u8 *addr, struct ieee80211_sub_if_data *sdata) hlist_for_each_entry(node, n, bucket, list) { mpath = node->mpath; if (mpath->sdata == sdata && - compare_ether_addr(addr, mpath->dst) == 0) { + ether_addr_equal(addr, mpath->dst)) { __mesh_path_del(tbl, node); goto enddel; } diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index 4e53c4cbca9..8cc8461b48a 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -82,20 +82,14 @@ static inline void mesh_plink_fsm_restart(struct sta_info *sta) } /* - * NOTE: This is just an alias for sta_info_alloc(), see notes - * on it in the lifecycle management section! + * Allocate mesh sta entry and insert into station table */ static struct sta_info *mesh_plink_alloc(struct ieee80211_sub_if_data *sdata, - u8 *hw_addr, u32 rates, - struct ieee802_11_elems *elems) + u8 *hw_addr) { - struct ieee80211_local *local = sdata->local; - struct ieee80211_supported_band *sband; struct sta_info *sta; - sband = local->hw.wiphy->bands[local->oper_channel->band]; - - if (local->num_sta >= MESH_MAX_PLINKS) + if (sdata->local->num_sta >= MESH_MAX_PLINKS) return NULL; sta = sta_info_alloc(sdata, hw_addr, GFP_KERNEL); @@ -108,16 +102,70 @@ static struct sta_info *mesh_plink_alloc(struct ieee80211_sub_if_data *sdata, set_sta_flag(sta, WLAN_STA_WME); - sta->sta.supp_rates[local->hw.conf.channel->band] = rates; - if (elems->ht_cap_elem) - ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband, - elems->ht_cap_elem, - &sta->sta.ht_cap); - rate_control_rate_init(sta); - return sta; } +/** mesh_set_ht_prot_mode - set correct HT protection mode + * + * Section 9.23.3.5 of IEEE 80211s standard describes the protection rules for + * HT mesh STA in a MBSS. Three HT protection modes are supported for now, + * non-HT mixed mode, 20MHz-protection and no-protection mode. non-HT mixed + * mode is selected if any non-HT peers are present in our MBSS. + * 20MHz-protection mode is selected if all peers in our 20/40MHz MBSS support + * HT and atleast one HT20 peer is present. Otherwise no-protection mode is + * selected. + */ +static u32 mesh_set_ht_prot_mode(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; + u32 changed = 0; + u16 ht_opmode; + bool non_ht_sta = false, ht20_sta = false; + + if (local->_oper_channel_type == NL80211_CHAN_NO_HT) + return 0; + + rcu_read_lock(); + list_for_each_entry_rcu(sta, &local->sta_list, list) { + if (sdata == sta->sdata && + sta->plink_state == NL80211_PLINK_ESTAB) { + switch (sta->ch_type) { + case NL80211_CHAN_NO_HT: + mpl_dbg("mesh_plink %pM: nonHT sta (%pM) is present", + sdata->vif.addr, sta->sta.addr); + non_ht_sta = true; + goto out; + case NL80211_CHAN_HT20: + mpl_dbg("mesh_plink %pM: HT20 sta (%pM) is present", + sdata->vif.addr, sta->sta.addr); + ht20_sta = true; + default: + break; + } + } + } +out: + rcu_read_unlock(); + + if (non_ht_sta) + ht_opmode = IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED; + else if (ht20_sta && local->_oper_channel_type > NL80211_CHAN_HT20) + ht_opmode = IEEE80211_HT_OP_MODE_PROTECTION_20MHZ; + else + ht_opmode = IEEE80211_HT_OP_MODE_PROTECTION_NONE; + + if (sdata->vif.bss_conf.ht_operation_mode != ht_opmode) { + sdata->vif.bss_conf.ht_operation_mode = ht_opmode; + sdata->u.mesh.mshcfg.ht_opmode = ht_opmode; + changed = BSS_CHANGED_HT; + mpl_dbg("mesh_plink %pM: protection mode changed to %d", + sdata->vif.addr, ht_opmode); + } + + return changed; +} + /** * __mesh_plink_deactivate - deactivate mesh peer link * @@ -187,7 +235,7 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, 2 + sdata->u.mesh.mesh_id_len + 2 + sizeof(struct ieee80211_meshconf_ie) + 2 + sizeof(struct ieee80211_ht_cap) + - 2 + sizeof(struct ieee80211_ht_info) + + 2 + sizeof(struct ieee80211_ht_operation) + 2 + 8 + /* peering IE */ sdata->u.mesh.ie_len); if (!skb) @@ -212,8 +260,8 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, pos = skb_put(skb, 2); memcpy(pos + 2, &plid, 2); } - if (ieee80211_add_srates_ie(&sdata->vif, skb) || - ieee80211_add_ext_srates_ie(&sdata->vif, skb) || + if (ieee80211_add_srates_ie(&sdata->vif, skb, true) || + ieee80211_add_ext_srates_ie(&sdata->vif, skb, true) || mesh_add_rsn_ie(skb, sdata) || mesh_add_meshid_ie(skb, sdata) || mesh_add_meshconf_ie(skb, sdata)) @@ -263,7 +311,7 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, if (action != WLAN_SP_MESH_PEERING_CLOSE) { if (mesh_add_ht_cap_ie(skb, sdata) || - mesh_add_ht_info_ie(skb, sdata)) + mesh_add_ht_oper_ie(skb, sdata)) return -1; } @@ -274,43 +322,93 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, return 0; } -void mesh_neighbour_update(u8 *hw_addr, u32 rates, - struct ieee80211_sub_if_data *sdata, - struct ieee802_11_elems *elems) +/* mesh_peer_init - initialize new mesh peer and return resulting sta_info + * + * @sdata: local meshif + * @addr: peer's address + * @elems: IEs from beacon or mesh peering frame + * + * call under RCU + */ +static struct sta_info *mesh_peer_init(struct ieee80211_sub_if_data *sdata, + u8 *addr, + struct ieee802_11_elems *elems) { struct ieee80211_local *local = sdata->local; + enum ieee80211_band band = local->oper_channel->band; + struct ieee80211_supported_band *sband; + u32 rates, basic_rates = 0; struct sta_info *sta; + bool insert = false; - rcu_read_lock(); + sband = local->hw.wiphy->bands[band]; + rates = ieee80211_sta_get_rates(local, elems, band, &basic_rates); - sta = sta_info_get(sdata, hw_addr); + sta = sta_info_get(sdata, addr); if (!sta) { - rcu_read_unlock(); - /* Userspace handles peer allocation when security is enabled - * */ - if (sdata->u.mesh.security & IEEE80211_MESH_SEC_AUTHED) - cfg80211_notify_new_peer_candidate(sdata->dev, hw_addr, - elems->ie_start, elems->total_len, - GFP_KERNEL); - else - sta = mesh_plink_alloc(sdata, hw_addr, rates, elems); + sta = mesh_plink_alloc(sdata, addr); if (!sta) - return; - if (sta_info_insert_rcu(sta)) { - rcu_read_unlock(); - return; - } + return NULL; + insert = true; } + spin_lock_bh(&sta->lock); sta->last_rx = jiffies; - sta->sta.supp_rates[local->hw.conf.channel->band] = rates; + sta->sta.supp_rates[band] = rates; + if (elems->ht_cap_elem && + sdata->local->_oper_channel_type != NL80211_CHAN_NO_HT) + ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband, + elems->ht_cap_elem, + &sta->sta.ht_cap); + else + memset(&sta->sta.ht_cap, 0, sizeof(sta->sta.ht_cap)); + + if (elems->ht_operation) { + if (!(elems->ht_operation->ht_param & + IEEE80211_HT_PARAM_CHAN_WIDTH_ANY)) + sta->sta.ht_cap.cap &= + ~IEEE80211_HT_CAP_SUP_WIDTH_20_40; + sta->ch_type = + ieee80211_ht_oper_to_channel_type(elems->ht_operation); + } + + rate_control_rate_init(sta); + spin_unlock_bh(&sta->lock); + + if (insert && sta_info_insert(sta)) + return NULL; + + return sta; +} + +void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata, + u8 *hw_addr, + struct ieee802_11_elems *elems) +{ + struct sta_info *sta; + + /* Userspace handles peer allocation when security is enabled */ + if (sdata->u.mesh.security & IEEE80211_MESH_SEC_AUTHED) { + cfg80211_notify_new_peer_candidate(sdata->dev, hw_addr, + elems->ie_start, + elems->total_len, + GFP_KERNEL); + return; + } + + rcu_read_lock(); + sta = mesh_peer_init(sdata, hw_addr, elems); + if (!sta) + goto out; + if (mesh_peer_accepts_plinks(elems) && - sta->plink_state == NL80211_PLINK_LISTEN && - sdata->u.mesh.accepting_plinks && - sdata->u.mesh.mshcfg.auto_open_plinks && - rssi_threshold_check(sta, sdata)) + sta->plink_state == NL80211_PLINK_LISTEN && + sdata->u.mesh.accepting_plinks && + sdata->u.mesh.mshcfg.auto_open_plinks && + rssi_threshold_check(sta, sdata)) mesh_plink_open(sta); +out: rcu_read_unlock(); } @@ -456,15 +554,15 @@ void mesh_plink_block(struct sta_info *sta) void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len, struct ieee80211_rx_status *rx_status) { - struct ieee80211_local *local = sdata->local; struct ieee802_11_elems elems; struct sta_info *sta; enum plink_event event; enum ieee80211_self_protected_actioncode ftype; size_t baselen; - bool deactivated, matches_local = true; + bool matches_local = true; u8 ie_len; u8 *baseaddr; + u32 changed = 0; __le16 plid, llid, reason; #ifdef CONFIG_MAC80211_VERBOSE_MPL_DEBUG static const char *mplstates[] = { @@ -560,7 +658,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m /* Now we will figure out the appropriate event... */ event = PLINK_UNDEFINED; if (ftype != WLAN_SP_MESH_PEERING_CLOSE && - (!mesh_matches_local(&elems, sdata))) { + !mesh_matches_local(sdata, &elems)) { matches_local = false; switch (ftype) { case WLAN_SP_MESH_PEERING_OPEN: @@ -583,29 +681,13 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m return; } else if (!sta) { /* ftype == WLAN_SP_MESH_PEERING_OPEN */ - u32 rates; - - rcu_read_unlock(); - if (!mesh_plink_free_count(sdata)) { mpl_dbg("Mesh plink error: no more free plinks\n"); - return; - } - - rates = ieee80211_sta_get_rates(local, &elems, rx_status->band); - sta = mesh_plink_alloc(sdata, mgmt->sa, rates, &elems); - if (!sta) { - mpl_dbg("Mesh plink error: plink table full\n"); - return; - } - if (sta_info_insert_rcu(sta)) { rcu_read_unlock(); return; } event = OPN_ACPT; - spin_lock_bh(&sta->lock); } else if (matches_local) { - spin_lock_bh(&sta->lock); switch (ftype) { case WLAN_SP_MESH_PEERING_OPEN: if (!mesh_plink_free_count(sdata) || @@ -642,12 +724,19 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m break; default: mpl_dbg("Mesh plink: unknown frame subtype\n"); - spin_unlock_bh(&sta->lock); rcu_read_unlock(); return; } - } else { - spin_lock_bh(&sta->lock); + } + + if (event == OPN_ACPT) { + /* allocate sta entry if necessary and update info */ + sta = mesh_peer_init(sdata, mgmt->sa, &elems); + if (!sta) { + mpl_dbg("Mesh plink: failed to init peer!\n"); + rcu_read_unlock(); + return; + } } mpl_dbg("Mesh plink (peer, state, llid, plid, event): %pM %s %d %d %d\n", @@ -655,6 +744,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m le16_to_cpu(sta->llid), le16_to_cpu(sta->plid), event); reason = 0; + spin_lock_bh(&sta->lock); switch (sta->plink_state) { /* spin_unlock as soon as state is updated at each case */ case NL80211_PLINK_LISTEN: @@ -758,7 +848,8 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m sta->plink_state = NL80211_PLINK_ESTAB; spin_unlock_bh(&sta->lock); mesh_plink_inc_estab_count(sdata); - ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON); + changed |= mesh_set_ht_prot_mode(sdata); + changed |= BSS_CHANGED_BEACON; mpl_dbg("Mesh plink with %pM ESTABLISHED\n", sta->sta.addr); break; @@ -793,7 +884,8 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m sta->plink_state = NL80211_PLINK_ESTAB; spin_unlock_bh(&sta->lock); mesh_plink_inc_estab_count(sdata); - ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON); + changed |= mesh_set_ht_prot_mode(sdata); + changed |= BSS_CHANGED_BEACON; mpl_dbg("Mesh plink with %pM ESTABLISHED\n", sta->sta.addr); mesh_plink_frame_tx(sdata, @@ -811,13 +903,13 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m case CLS_ACPT: reason = cpu_to_le16(WLAN_REASON_MESH_CLOSE); sta->reason = reason; - deactivated = __mesh_plink_deactivate(sta); + __mesh_plink_deactivate(sta); sta->plink_state = NL80211_PLINK_HOLDING; llid = sta->llid; mod_plink_timer(sta, dot11MeshHoldingTimeout(sdata)); spin_unlock_bh(&sta->lock); - if (deactivated) - ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON); + changed |= mesh_set_ht_prot_mode(sdata); + changed |= BSS_CHANGED_BEACON; mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, sta->sta.addr, llid, plid, reason); break; @@ -864,4 +956,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m } rcu_read_unlock(); + + if (changed) + ieee80211_bss_info_change_notify(sdata, changed); } diff --git a/net/mac80211/mesh_sync.c b/net/mac80211/mesh_sync.c new file mode 100644 index 00000000000..38d30e8ce6d --- /dev/null +++ b/net/mac80211/mesh_sync.c @@ -0,0 +1,316 @@ +/* + * Copyright 2011-2012, Pavel Zubarev <pavel.zubarev@gmail.com> + * Copyright 2011-2012, Marco Porsch <marco.porsch@s2005.tu-chemnitz.de> + * Copyright 2011-2012, cozybit Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "ieee80211_i.h" +#include "mesh.h" +#include "driver-ops.h" + +#ifdef CONFIG_MAC80211_VERBOSE_MESH_SYNC_DEBUG +#define msync_dbg(fmt, args...) \ + printk(KERN_DEBUG "Mesh sync (%s): " fmt "\n", sdata->name, ##args) +#else +#define msync_dbg(fmt, args...) do { (void)(0); } while (0) +#endif + +/* This is not in the standard. It represents a tolerable tbtt drift below + * which we do no TSF adjustment. + */ +#define TOFFSET_MINIMUM_ADJUSTMENT 10 + +/* This is not in the standard. It is a margin added to the + * Toffset setpoint to mitigate TSF overcorrection + * introduced by TSF adjustment latency. + */ +#define TOFFSET_SET_MARGIN 20 + +/* This is not in the standard. It represents the maximum Toffset jump above + * which we'll invalidate the Toffset setpoint and choose a new setpoint. This + * could be, for instance, in case a neighbor is restarted and its TSF counter + * reset. + */ +#define TOFFSET_MAXIMUM_ADJUSTMENT 30000 /* 30 ms */ + +struct sync_method { + u8 method; + struct ieee80211_mesh_sync_ops ops; +}; + +/** + * mesh_peer_tbtt_adjusting - check if an mp is currently adjusting its TBTT + * + * @ie: information elements of a management frame from the mesh peer + */ +static bool mesh_peer_tbtt_adjusting(struct ieee802_11_elems *ie) +{ + return (ie->mesh_config->meshconf_cap & + MESHCONF_CAPAB_TBTT_ADJUSTING) != 0; +} + +void mesh_sync_adjust_tbtt(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + /* sdata->vif.bss_conf.beacon_int in 1024us units, 0.04% */ + u64 beacon_int_fraction = sdata->vif.bss_conf.beacon_int * 1024 / 2500; + u64 tsf; + u64 tsfdelta; + + spin_lock_bh(&ifmsh->sync_offset_lock); + + if (ifmsh->sync_offset_clockdrift_max < beacon_int_fraction) { + msync_dbg("TBTT : max clockdrift=%lld; adjusting", + (long long) ifmsh->sync_offset_clockdrift_max); + tsfdelta = -ifmsh->sync_offset_clockdrift_max; + ifmsh->sync_offset_clockdrift_max = 0; + } else { + msync_dbg("TBTT : max clockdrift=%lld; adjusting by %llu", + (long long) ifmsh->sync_offset_clockdrift_max, + (unsigned long long) beacon_int_fraction); + tsfdelta = -beacon_int_fraction; + ifmsh->sync_offset_clockdrift_max -= beacon_int_fraction; + } + + tsf = drv_get_tsf(local, sdata); + if (tsf != -1ULL) + drv_set_tsf(local, sdata, tsf + tsfdelta); + spin_unlock_bh(&ifmsh->sync_offset_lock); +} + +static void mesh_sync_offset_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, + u16 stype, + struct ieee80211_mgmt *mgmt, + struct ieee802_11_elems *elems, + struct ieee80211_rx_status *rx_status) +{ + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; + u64 t_t, t_r; + + WARN_ON(ifmsh->mesh_sp_id != IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET); + + /* standard mentions only beacons */ + if (stype != IEEE80211_STYPE_BEACON) + return; + + /* The current tsf is a first approximation for the timestamp + * for the received beacon. Further down we try to get a + * better value from the rx_status->mactime field if + * available. Also we have to call drv_get_tsf() before + * entering the rcu-read section.*/ + t_r = drv_get_tsf(local, sdata); + + rcu_read_lock(); + sta = sta_info_get(sdata, mgmt->sa); + if (!sta) + goto no_sync; + + /* check offset sync conditions (13.13.2.2.1) + * + * TODO also sync to + * dot11MeshNbrOffsetMaxNeighbor non-peer non-MBSS neighbors + */ + + if (elems->mesh_config && mesh_peer_tbtt_adjusting(elems)) { + clear_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN); + msync_dbg("STA %pM : is adjusting TBTT", sta->sta.addr); + goto no_sync; + } + + if (rx_status->flag & RX_FLAG_MACTIME_MPDU && rx_status->mactime) { + /* + * The mactime is defined as the time the first data symbol + * of the frame hits the PHY, and the timestamp of the beacon + * is defined as "the time that the data symbol containing the + * first bit of the timestamp is transmitted to the PHY plus + * the transmitting STA's delays through its local PHY from the + * MAC-PHY interface to its interface with the WM" (802.11 + * 11.1.2) + * + * T_r, in 13.13.2.2.2, is just defined as "the frame reception + * time" but we unless we interpret that time to be the same + * time of the beacon timestamp, the offset calculation will be + * off. Below we adjust t_r to be "the time at which the first + * symbol of the timestamp element in the beacon is received". + * This correction depends on the rate. + * + * Based on similar code in ibss.c + */ + int rate; + + if (rx_status->flag & RX_FLAG_HT) { + /* TODO: + * In principle there could be HT-beacons (Dual Beacon + * HT Operation options), but for now ignore them and + * just use the primary (i.e. non-HT) beacons for + * synchronization. + * */ + goto no_sync; + } else + rate = local->hw.wiphy->bands[rx_status->band]-> + bitrates[rx_status->rate_idx].bitrate; + + /* 24 bytes of header * 8 bits/byte * + * 10*(100 Kbps)/Mbps / rate (100 Kbps)*/ + t_r = rx_status->mactime + (24 * 8 * 10 / rate); + } + + /* Timing offset calculation (see 13.13.2.2.2) */ + t_t = le64_to_cpu(mgmt->u.beacon.timestamp); + sta->t_offset = t_t - t_r; + + if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) { + s64 t_clockdrift = sta->t_offset_setpoint + - sta->t_offset; + msync_dbg("STA %pM : sta->t_offset=%lld, sta->t_offset_setpoint=%lld, t_clockdrift=%lld", + sta->sta.addr, + (long long) sta->t_offset, + (long long) + sta->t_offset_setpoint, + (long long) t_clockdrift); + + if (t_clockdrift > TOFFSET_MAXIMUM_ADJUSTMENT || + t_clockdrift < -TOFFSET_MAXIMUM_ADJUSTMENT) { + msync_dbg("STA %pM : t_clockdrift=%lld too large, setpoint reset", + sta->sta.addr, + (long long) t_clockdrift); + clear_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN); + goto no_sync; + } + + rcu_read_unlock(); + + spin_lock_bh(&ifmsh->sync_offset_lock); + if (t_clockdrift > + ifmsh->sync_offset_clockdrift_max) + ifmsh->sync_offset_clockdrift_max + = t_clockdrift; + spin_unlock_bh(&ifmsh->sync_offset_lock); + + } else { + sta->t_offset_setpoint = sta->t_offset - TOFFSET_SET_MARGIN; + set_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN); + msync_dbg("STA %pM : offset was invalid, " + " sta->t_offset=%lld", + sta->sta.addr, + (long long) sta->t_offset); + rcu_read_unlock(); + } + return; + +no_sync: + rcu_read_unlock(); +} + +static void mesh_sync_offset_adjust_tbtt(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + + WARN_ON(ifmsh->mesh_sp_id + != IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET); + BUG_ON(!rcu_read_lock_held()); + + spin_lock_bh(&ifmsh->sync_offset_lock); + + if (ifmsh->sync_offset_clockdrift_max > + TOFFSET_MINIMUM_ADJUSTMENT) { + /* Since ajusting the tsf here would + * require a possibly blocking call + * to the driver tsf setter, we punt + * the tsf adjustment to the mesh tasklet + */ + msync_dbg("TBTT : kicking off TBTT " + "adjustment with " + "clockdrift_max=%lld", + ifmsh->sync_offset_clockdrift_max); + set_bit(MESH_WORK_DRIFT_ADJUST, + &ifmsh->wrkq_flags); + } else { + msync_dbg("TBTT : max clockdrift=%lld; " + "too small to adjust", + (long long) + ifmsh->sync_offset_clockdrift_max); + ifmsh->sync_offset_clockdrift_max = 0; + } + spin_unlock_bh(&ifmsh->sync_offset_lock); +} + +static const u8 *mesh_get_vendor_oui(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + u8 offset; + + if (!ifmsh->ie || !ifmsh->ie_len) + return NULL; + + offset = ieee80211_ie_split_vendor(ifmsh->ie, + ifmsh->ie_len, 0); + + if (!offset) + return NULL; + + return ifmsh->ie + offset + 2; +} + +static void mesh_sync_vendor_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, + u16 stype, + struct ieee80211_mgmt *mgmt, + struct ieee802_11_elems *elems, + struct ieee80211_rx_status *rx_status) +{ + const u8 *oui; + + WARN_ON(sdata->u.mesh.mesh_sp_id != IEEE80211_SYNC_METHOD_VENDOR); + msync_dbg("called mesh_sync_vendor_rx_bcn_presp"); + oui = mesh_get_vendor_oui(sdata); + /* here you would implement the vendor offset tracking for this oui */ +} + +static void mesh_sync_vendor_adjust_tbtt(struct ieee80211_sub_if_data *sdata) +{ + const u8 *oui; + + WARN_ON(sdata->u.mesh.mesh_sp_id != IEEE80211_SYNC_METHOD_VENDOR); + msync_dbg("called mesh_sync_vendor_adjust_tbtt"); + oui = mesh_get_vendor_oui(sdata); + /* here you would implement the vendor tsf adjustment for this oui */ +} + +/* global variable */ +static struct sync_method sync_methods[] = { + { + .method = IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET, + .ops = { + .rx_bcn_presp = &mesh_sync_offset_rx_bcn_presp, + .adjust_tbtt = &mesh_sync_offset_adjust_tbtt, + } + }, + { + .method = IEEE80211_SYNC_METHOD_VENDOR, + .ops = { + .rx_bcn_presp = &mesh_sync_vendor_rx_bcn_presp, + .adjust_tbtt = &mesh_sync_vendor_adjust_tbtt, + } + }, +}; + +struct ieee80211_mesh_sync_ops *ieee80211_mesh_sync_ops_get(u8 method) +{ + struct ieee80211_mesh_sync_ops *ops = NULL; + u8 i; + + for (i = 0 ; i < ARRAY_SIZE(sync_methods); ++i) { + if (sync_methods[i].method == method) { + ops = &sync_methods[i].ops; + break; + } + } + return ops; +} diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 576fb25456d..b3b3c264ff6 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -171,122 +171,64 @@ static int ecw2cw(int ecw) return (1 << ecw) - 1; } -/* - * ieee80211_enable_ht should be called only after the operating band - * has been determined as ht configuration depends on the hw's - * HT abilities for a specific band. - */ -static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, - struct ieee80211_ht_info *hti, - const u8 *bssid, u16 ap_ht_cap_flags, - bool beacon_htcap_ie) +static u32 ieee80211_config_ht_tx(struct ieee80211_sub_if_data *sdata, + struct ieee80211_ht_operation *ht_oper, + const u8 *bssid, bool reconfig) { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; struct sta_info *sta; u32 changed = 0; - int hti_cfreq; u16 ht_opmode; - bool enable_ht = true; - enum nl80211_channel_type prev_chantype; - enum nl80211_channel_type rx_channel_type = NL80211_CHAN_NO_HT; - enum nl80211_channel_type tx_channel_type; + bool disable_40 = false; sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; - prev_chantype = sdata->vif.bss_conf.channel_type; - - hti_cfreq = ieee80211_channel_to_frequency(hti->control_chan, - sband->band); - /* check that channel matches the right operating channel */ - if (local->hw.conf.channel->center_freq != hti_cfreq) { - /* Some APs mess this up, evidently. - * Netgear WNDR3700 sometimes reports 4 higher than - * the actual channel, for instance. - */ - printk(KERN_DEBUG - "%s: Wrong control channel in association" - " response: configured center-freq: %d" - " hti-cfreq: %d hti->control_chan: %d" - " band: %d. Disabling HT.\n", - sdata->name, - local->hw.conf.channel->center_freq, - hti_cfreq, hti->control_chan, - sband->band); - enable_ht = false; - } - - if (enable_ht) { - rx_channel_type = NL80211_CHAN_HT20; - - if (!(ap_ht_cap_flags & IEEE80211_HT_CAP_40MHZ_INTOLERANT) && - !ieee80111_cfg_override_disables_ht40(sdata) && - (sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) && - (hti->ht_param & IEEE80211_HT_PARAM_CHAN_WIDTH_ANY)) { - switch(hti->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) { - case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: - rx_channel_type = NL80211_CHAN_HT40PLUS; - break; - case IEEE80211_HT_PARAM_CHA_SEC_BELOW: - rx_channel_type = NL80211_CHAN_HT40MINUS; - break; - } - } + switch (sdata->vif.bss_conf.channel_type) { + case NL80211_CHAN_HT40PLUS: + if (local->hw.conf.channel->flags & IEEE80211_CHAN_NO_HT40PLUS) + disable_40 = true; + break; + case NL80211_CHAN_HT40MINUS: + if (local->hw.conf.channel->flags & IEEE80211_CHAN_NO_HT40MINUS) + disable_40 = true; + break; + default: + break; } - tx_channel_type = ieee80211_get_tx_channel_type(local, rx_channel_type); + /* This can change during the lifetime of the BSS */ + if (!(ht_oper->ht_param & IEEE80211_HT_PARAM_CHAN_WIDTH_ANY)) + disable_40 = true; - if (local->tmp_channel) - local->tmp_channel_type = rx_channel_type; - - if (!ieee80211_set_channel_type(local, sdata, rx_channel_type)) { - /* can only fail due to HT40+/- mismatch */ - rx_channel_type = NL80211_CHAN_HT20; - WARN_ON(!ieee80211_set_channel_type(local, sdata, - rx_channel_type)); - } - - if (beacon_htcap_ie && (prev_chantype != rx_channel_type)) { - /* - * Whenever the AP announces the HT mode change that can be - * 40MHz intolerant or etc., it would be safer to stop tx - * queues before doing hw config to avoid buffer overflow. - */ - ieee80211_stop_queues_by_reason(&sdata->local->hw, - IEEE80211_QUEUE_STOP_REASON_CHTYPE_CHANGE); + mutex_lock(&local->sta_mtx); + sta = sta_info_get(sdata, bssid); - /* flush out all packets */ - synchronize_net(); + WARN_ON_ONCE(!sta); - drv_flush(local, false); - } + if (sta && !sta->supports_40mhz) + disable_40 = true; - /* channel_type change automatically detected */ - ieee80211_hw_config(local, 0); + if (sta && (!reconfig || + (disable_40 != !(sta->sta.ht_cap.cap & + IEEE80211_HT_CAP_SUP_WIDTH_20_40)))) { - if (prev_chantype != tx_channel_type) { - rcu_read_lock(); - sta = sta_info_get(sdata, bssid); - if (sta) - rate_control_rate_update(local, sband, sta, - IEEE80211_RC_HT_CHANGED, - tx_channel_type); - rcu_read_unlock(); + if (disable_40) + sta->sta.ht_cap.cap &= ~IEEE80211_HT_CAP_SUP_WIDTH_20_40; + else + sta->sta.ht_cap.cap |= IEEE80211_HT_CAP_SUP_WIDTH_20_40; - if (beacon_htcap_ie) - ieee80211_wake_queues_by_reason(&sdata->local->hw, - IEEE80211_QUEUE_STOP_REASON_CHTYPE_CHANGE); + rate_control_rate_update(local, sband, sta, + IEEE80211_RC_BW_CHANGED); } + mutex_unlock(&local->sta_mtx); - ht_opmode = le16_to_cpu(hti->operation_mode); + ht_opmode = le16_to_cpu(ht_oper->operation_mode); /* if bss configuration changed store the new one */ - if (sdata->ht_opmode_valid != enable_ht || - sdata->vif.bss_conf.ht_operation_mode != ht_opmode || - prev_chantype != rx_channel_type) { + if (!reconfig || (sdata->vif.bss_conf.ht_operation_mode != ht_opmode)) { changed |= BSS_CHANGED_HT; sdata->vif.bss_conf.ht_operation_mode = ht_opmode; - sdata->ht_opmode_valid = enable_ht; } return changed; @@ -316,12 +258,12 @@ static int ieee80211_compatible_rates(const u8 *supp_rates, int supp_rates_len, } static void ieee80211_add_ht_ie(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, const u8 *ht_info_ie, + struct sk_buff *skb, const u8 *ht_oper_ie, struct ieee80211_supported_band *sband, struct ieee80211_channel *channel, enum ieee80211_smps_mode smps) { - struct ieee80211_ht_info *ht_info; + struct ieee80211_ht_operation *ht_oper; u8 *pos; u32 flags = channel->flags; u16 cap; @@ -329,21 +271,21 @@ static void ieee80211_add_ht_ie(struct ieee80211_sub_if_data *sdata, BUILD_BUG_ON(sizeof(ht_cap) != sizeof(sband->ht_cap)); - if (!ht_info_ie) + if (!ht_oper_ie) return; - if (ht_info_ie[1] < sizeof(struct ieee80211_ht_info)) + if (ht_oper_ie[1] < sizeof(struct ieee80211_ht_operation)) return; memcpy(&ht_cap, &sband->ht_cap, sizeof(ht_cap)); ieee80211_apply_htcap_overrides(sdata, &ht_cap); - ht_info = (struct ieee80211_ht_info *)(ht_info_ie + 2); + ht_oper = (struct ieee80211_ht_operation *)(ht_oper_ie + 2); /* determine capability flags */ cap = ht_cap.cap; - switch (ht_info->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) { + switch (ht_oper->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) { case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: if (flags & IEEE80211_CHAN_NO_HT40PLUS) { cap &= ~IEEE80211_HT_CAP_SUP_WIDTH_20_40; @@ -358,6 +300,16 @@ static void ieee80211_add_ht_ie(struct ieee80211_sub_if_data *sdata, break; } + /* + * If 40 MHz was disabled associate as though we weren't + * capable of 40 MHz -- some broken APs will never fall + * back to trying to transmit in 20 MHz. + */ + if (sdata->u.mgd.flags & IEEE80211_STA_DISABLE_40MHZ) { + cap &= ~IEEE80211_HT_CAP_SUP_WIDTH_20_40; + cap &= ~IEEE80211_HT_CAP_SGI_40; + } + /* set SM PS mode properly */ cap &= ~IEEE80211_HT_CAP_SM_PS; switch (smps) { @@ -557,7 +509,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) } if (!(ifmgd->flags & IEEE80211_STA_DISABLE_11N)) - ieee80211_add_ht_ie(sdata, skb, assoc_data->ht_information_ie, + ieee80211_add_ht_ie(sdata, skb, assoc_data->ht_operation_ie, sband, local->oper_channel, ifmgd->ap_smps); /* if present, add any custom non-vendor IEs that go after HT */ @@ -1182,7 +1134,7 @@ static void ieee80211_sta_wmm_params(struct ieee80211_local *local, if (!local->ops->conf_tx) return; - if (local->hw.queues < 4) + if (local->hw.queues < IEEE80211_NUM_ACS) return; if (!wmm_param) @@ -1435,7 +1387,6 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, sdata->vif.bss_conf.assoc = false; /* on the next assoc, re-program HT parameters */ - sdata->ht_opmode_valid = false; memset(&ifmgd->ht_capa, 0, sizeof(ifmgd->ht_capa)); memset(&ifmgd->ht_capa_mask, 0, sizeof(ifmgd->ht_capa_mask)); @@ -1496,19 +1447,24 @@ void ieee80211_sta_rx_notify(struct ieee80211_sub_if_data *sdata, static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + struct ieee80211_local *local = sdata->local; + mutex_lock(&local->mtx); if (!(ifmgd->flags & (IEEE80211_STA_BEACON_POLL | - IEEE80211_STA_CONNECTION_POLL))) - return; + IEEE80211_STA_CONNECTION_POLL))) { + mutex_unlock(&local->mtx); + return; + } ifmgd->flags &= ~(IEEE80211_STA_CONNECTION_POLL | IEEE80211_STA_BEACON_POLL); - mutex_lock(&sdata->local->iflist_mtx); - ieee80211_recalc_ps(sdata->local, -1); - mutex_unlock(&sdata->local->iflist_mtx); + + mutex_lock(&local->iflist_mtx); + ieee80211_recalc_ps(local, -1); + mutex_unlock(&local->iflist_mtx); if (sdata->local->hw.flags & IEEE80211_HW_CONNECTION_MONITOR) - return; + goto out; /* * We've received a probe response, but are not sure whether @@ -1520,6 +1476,9 @@ static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata) mod_timer(&ifmgd->conn_mon_timer, round_jiffies_up(jiffies + IEEE80211_CONNECTION_IDLE_TIME)); +out: + ieee80211_run_deferred_scan(local); + mutex_unlock(&local->mtx); } void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata, @@ -1567,14 +1526,23 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) ifmgd->nullfunc_failed = false; ieee80211_send_nullfunc(sdata->local, sdata, 0); } else { + int ssid_len; + ssid = ieee80211_bss_get_ie(ifmgd->associated, WLAN_EID_SSID); - ieee80211_send_probe_req(sdata, dst, ssid + 2, ssid[1], NULL, 0, - (u32) -1, true, false); + if (WARN_ON_ONCE(ssid == NULL)) + ssid_len = 0; + else + ssid_len = ssid[1]; + + ieee80211_send_probe_req(sdata, dst, ssid + 2, ssid_len, NULL, + 0, (u32) -1, true, false); } ifmgd->probe_send_count++; ifmgd->probe_timeout = jiffies + msecs_to_jiffies(probe_wait_ms); run_again(ifmgd, ifmgd->probe_timeout); + if (sdata->local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) + drv_flush(sdata->local, false); } static void ieee80211_mgd_probe_ap(struct ieee80211_sub_if_data *sdata, @@ -1586,21 +1554,22 @@ static void ieee80211_mgd_probe_ap(struct ieee80211_sub_if_data *sdata, if (!ieee80211_sdata_running(sdata)) return; - if (sdata->local->scanning) - return; - - if (sdata->local->tmp_channel) - return; - mutex_lock(&ifmgd->mtx); if (!ifmgd->associated) goto out; + mutex_lock(&sdata->local->mtx); + + if (sdata->local->tmp_channel || sdata->local->scanning) { + mutex_unlock(&sdata->local->mtx); + goto out; + } + #ifdef CONFIG_MAC80211_VERBOSE_DEBUG - if (beacon && net_ratelimit()) - printk(KERN_DEBUG "%s: detected beacon loss from AP " - "- sending probe request\n", sdata->name); + if (beacon) + net_dbg_ratelimited("%s: detected beacon loss from AP - sending probe request\n", + sdata->name); #endif /* @@ -1623,6 +1592,8 @@ static void ieee80211_mgd_probe_ap(struct ieee80211_sub_if_data *sdata, else ifmgd->flags |= IEEE80211_STA_CONNECTION_POLL; + mutex_unlock(&sdata->local->mtx); + if (already) goto out; @@ -1643,6 +1614,7 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct sk_buff *skb; const u8 *ssid; + int ssid_len; if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION)) return NULL; @@ -1653,8 +1625,13 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, return NULL; ssid = ieee80211_bss_get_ie(ifmgd->associated, WLAN_EID_SSID); + if (WARN_ON_ONCE(ssid == NULL)) + ssid_len = 0; + else + ssid_len = ssid[1]; + skb = ieee80211_build_probe_req(sdata, ifmgd->associated->bssid, - (u32) -1, ssid + 2, ssid[1], + (u32) -1, ssid + 2, ssid_len, NULL, 0, true); return skb; @@ -1799,7 +1776,7 @@ ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, memcpy(bssid, ifmgd->auth_data->bss->bssid, ETH_ALEN); - if (compare_ether_addr(bssid, mgmt->bssid)) + if (!ether_addr_equal(bssid, mgmt->bssid)) return RX_MGMT_NONE; auth_alg = le16_to_cpu(mgmt->u.auth.auth_alg); @@ -1876,7 +1853,7 @@ ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata, return RX_MGMT_NONE; if (!ifmgd->associated || - compare_ether_addr(mgmt->bssid, ifmgd->associated->bssid)) + !ether_addr_equal(mgmt->bssid, ifmgd->associated->bssid)) return RX_MGMT_NONE; bssid = ifmgd->associated->bssid; @@ -1909,7 +1886,7 @@ ieee80211_rx_mgmt_disassoc(struct ieee80211_sub_if_data *sdata, return RX_MGMT_NONE; if (!ifmgd->associated || - compare_ether_addr(mgmt->bssid, ifmgd->associated->bssid)) + !ether_addr_equal(mgmt->bssid, ifmgd->associated->bssid)) return RX_MGMT_NONE; reason_code = le16_to_cpu(mgmt->u.disassoc.reason_code); @@ -2000,7 +1977,6 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf; u32 changed = 0; int err; - u16 ap_ht_cap_flags; /* AssocResp and ReassocResp have identical structure */ @@ -2051,7 +2027,8 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband, elems.ht_cap_elem, &sta->sta.ht_cap); - ap_ht_cap_flags = sta->sta.ht_cap.cap; + sta->supports_40mhz = + sta->sta.ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40; rate_control_rate_init(sta); @@ -2092,11 +2069,10 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, ieee80211_set_wmm_default(sdata, false); changed |= BSS_CHANGED_QOS; - if (elems.ht_info_elem && elems.wmm_param && + if (elems.ht_operation && elems.wmm_param && !(ifmgd->flags & IEEE80211_STA_DISABLE_11N)) - changed |= ieee80211_enable_ht(sdata, elems.ht_info_elem, - cbss->bssid, ap_ht_cap_flags, - false); + changed |= ieee80211_config_ht_tx(sdata, elems.ht_operation, + cbss->bssid, false); /* set AID and assoc capability, * ieee80211_set_associated() will tell the driver */ @@ -2137,7 +2113,7 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, if (!assoc_data) return RX_MGMT_NONE; - if (compare_ether_addr(assoc_data->bss->bssid, mgmt->bssid)) + if (!ether_addr_equal(assoc_data->bss->bssid, mgmt->bssid)) return RX_MGMT_NONE; /* @@ -2217,8 +2193,7 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, bool need_ps = false; if (sdata->u.mgd.associated && - compare_ether_addr(mgmt->bssid, sdata->u.mgd.associated->bssid) - == 0) { + ether_addr_equal(mgmt->bssid, sdata->u.mgd.associated->bssid)) { bss = (void *)sdata->u.mgd.associated->priv; /* not previously set so we may need to recalc */ need_ps = !bss->dtim_period; @@ -2273,7 +2248,7 @@ static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata, ASSERT_MGD_MTX(ifmgd); - if (compare_ether_addr(mgmt->da, sdata->vif.addr)) + if (!ether_addr_equal(mgmt->da, sdata->vif.addr)) return; /* ignore ProbeResp to foreign address */ baselen = (u8 *) mgmt->u.probe_resp.variable - (u8 *) mgmt; @@ -2286,12 +2261,11 @@ static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata, ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems, false); if (ifmgd->associated && - compare_ether_addr(mgmt->bssid, ifmgd->associated->bssid) == 0) + ether_addr_equal(mgmt->bssid, ifmgd->associated->bssid)) ieee80211_reset_ap_probe(sdata); if (ifmgd->auth_data && !ifmgd->auth_data->bss->proberesp_ies && - compare_ether_addr(mgmt->bssid, ifmgd->auth_data->bss->bssid) - == 0) { + ether_addr_equal(mgmt->bssid, ifmgd->auth_data->bss->bssid)) { /* got probe response, continue with auth */ printk(KERN_DEBUG "%s: direct probe responded\n", sdata->name); ifmgd->auth_data->tries = 0; @@ -2319,7 +2293,7 @@ static const u64 care_about_ies = (1ULL << WLAN_EID_CHANNEL_SWITCH) | (1ULL << WLAN_EID_PWR_CONSTRAINT) | (1ULL << WLAN_EID_HT_CAPABILITY) | - (1ULL << WLAN_EID_HT_INFORMATION); + (1ULL << WLAN_EID_HT_OPERATION); static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, @@ -2348,8 +2322,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, return; if (ifmgd->assoc_data && !ifmgd->assoc_data->have_beacon && - compare_ether_addr(mgmt->bssid, ifmgd->assoc_data->bss->bssid) - == 0) { + ether_addr_equal(mgmt->bssid, ifmgd->assoc_data->bss->bssid)) { ieee802_11_parse_elems(mgmt->u.beacon.variable, len - baselen, &elems); @@ -2364,7 +2337,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, } if (!ifmgd->associated || - compare_ether_addr(mgmt->bssid, ifmgd->associated->bssid)) + !ether_addr_equal(mgmt->bssid, ifmgd->associated->bssid)) return; bssid = ifmgd->associated->bssid; @@ -2431,10 +2404,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (ifmgd->flags & IEEE80211_STA_BEACON_POLL) { #ifdef CONFIG_MAC80211_VERBOSE_DEBUG - if (net_ratelimit()) { - printk(KERN_DEBUG "%s: cancelling probereq poll due " - "to a received beacon\n", sdata->name); - } + net_dbg_ratelimited("%s: cancelling probereq poll due to a received beacon\n", + sdata->name); #endif ifmgd->flags &= ~IEEE80211_STA_BEACON_POLL; mutex_lock(&local->iflist_mtx); @@ -2468,11 +2439,13 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) { if (directed_tim) { if (local->hw.conf.dynamic_ps_timeout > 0) { - local->hw.conf.flags &= ~IEEE80211_CONF_PS; - ieee80211_hw_config(local, - IEEE80211_CONF_CHANGE_PS); + if (local->hw.conf.flags & IEEE80211_CONF_PS) { + local->hw.conf.flags &= ~IEEE80211_CONF_PS; + ieee80211_hw_config(local, + IEEE80211_CONF_CHANGE_PS); + } ieee80211_send_nullfunc(local, sdata, 0); - } else { + } else if (!local->pspolling && sdata->u.mgd.powersave) { local->pspolling = true; /* @@ -2504,31 +2477,14 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, erp_valid, erp_value); - if (elems.ht_cap_elem && elems.ht_info_elem && elems.wmm_param && + if (elems.ht_cap_elem && elems.ht_operation && elems.wmm_param && !(ifmgd->flags & IEEE80211_STA_DISABLE_11N)) { - struct sta_info *sta; struct ieee80211_supported_band *sband; - u16 ap_ht_cap_flags; - - rcu_read_lock(); - - sta = sta_info_get(sdata, bssid); - if (WARN_ON(!sta)) { - rcu_read_unlock(); - return; - } sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; - ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband, - elems.ht_cap_elem, &sta->sta.ht_cap); - - ap_ht_cap_flags = sta->sta.ht_cap.cap; - - rcu_read_unlock(); - - changed |= ieee80211_enable_ht(sdata, elems.ht_info_elem, - bssid, ap_ht_cap_flags, true); + changed |= ieee80211_config_ht_tx(sdata, elems.ht_operation, + bssid, true); } /* Note: country IE parsing is done for us by cfg80211 */ @@ -3060,6 +3016,11 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, struct sta_info *sta; bool have_sta = false; int err; + int ht_cfreq; + enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; + const u8 *ht_oper_ie; + const struct ieee80211_ht_operation *ht_oper = NULL; + struct ieee80211_supported_band *sband; if (WARN_ON(!ifmgd->auth_data && !ifmgd->assoc_data)) return -EINVAL; @@ -3081,17 +3042,76 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, mutex_unlock(&local->mtx); /* switch to the right channel */ + sband = local->hw.wiphy->bands[cbss->channel->band]; + + ifmgd->flags &= ~IEEE80211_STA_DISABLE_40MHZ; + + if (sband->ht_cap.ht_supported) { + ht_oper_ie = cfg80211_find_ie(WLAN_EID_HT_OPERATION, + cbss->information_elements, + cbss->len_information_elements); + if (ht_oper_ie && ht_oper_ie[1] >= sizeof(*ht_oper)) + ht_oper = (void *)(ht_oper_ie + 2); + } + + if (ht_oper) { + ht_cfreq = ieee80211_channel_to_frequency(ht_oper->primary_chan, + cbss->channel->band); + /* check that channel matches the right operating channel */ + if (cbss->channel->center_freq != ht_cfreq) { + /* + * It's possible that some APs are confused here; + * Netgear WNDR3700 sometimes reports 4 higher than + * the actual channel in association responses, but + * since we look at probe response/beacon data here + * it should be OK. + */ + printk(KERN_DEBUG + "%s: Wrong control channel: center-freq: %d" + " ht-cfreq: %d ht->primary_chan: %d" + " band: %d. Disabling HT.\n", + sdata->name, cbss->channel->center_freq, + ht_cfreq, ht_oper->primary_chan, + cbss->channel->band); + ht_oper = NULL; + } + } + + if (ht_oper) { + channel_type = NL80211_CHAN_HT20; + + if (sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) { + switch (ht_oper->ht_param & + IEEE80211_HT_PARAM_CHA_SEC_OFFSET) { + case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: + channel_type = NL80211_CHAN_HT40PLUS; + break; + case IEEE80211_HT_PARAM_CHA_SEC_BELOW: + channel_type = NL80211_CHAN_HT40MINUS; + break; + } + } + } + + if (!ieee80211_set_channel_type(local, sdata, channel_type)) { + /* can only fail due to HT40+/- mismatch */ + channel_type = NL80211_CHAN_HT20; + printk(KERN_DEBUG + "%s: disabling 40 MHz due to multi-vif mismatch\n", + sdata->name); + ifmgd->flags |= IEEE80211_STA_DISABLE_40MHZ; + WARN_ON(!ieee80211_set_channel_type(local, sdata, + channel_type)); + } + local->oper_channel = cbss->channel; - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); + ieee80211_hw_config(local, 0); if (!have_sta) { - struct ieee80211_supported_band *sband; u32 rates = 0, basic_rates = 0; bool have_higher_than_11mbit; int min_rate = INT_MAX, min_rate_index = -1; - sband = sdata->local->hw.wiphy->bands[cbss->channel->band]; - ieee80211_get_rates(sband, bss->supp_rates, bss->supp_rates_len, &rates, &basic_rates, @@ -3141,7 +3161,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, return err; } } else - WARN_ON_ONCE(compare_ether_addr(ifmgd->bssid, cbss->bssid)); + WARN_ON_ONCE(!ether_addr_equal(ifmgd->bssid, cbss->bssid)); return 0; } @@ -3281,7 +3301,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, bool match; /* keep sta info, bssid if matching */ - match = compare_ether_addr(ifmgd->bssid, req->bss->bssid) == 0; + match = ether_addr_equal(ifmgd->bssid, req->bss->bssid); ieee80211_destroy_auth_data(sdata, match); } @@ -3311,7 +3331,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, /* Also disable HT if we don't support it or the AP doesn't use WMM */ sband = local->hw.wiphy->bands[req->bss->channel->band]; if (!sband->ht_cap.ht_supported || - local->hw.queues < 4 || !bss->wmm_used) + local->hw.queues < IEEE80211_NUM_ACS || !bss->wmm_used) ifmgd->flags |= IEEE80211_STA_DISABLE_11N; memcpy(&ifmgd->ht_capa, &req->ht_capa, sizeof(ifmgd->ht_capa)); @@ -3334,11 +3354,12 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, ifmgd->ap_smps = ifmgd->req_smps; assoc_data->capability = req->bss->capability; - assoc_data->wmm = bss->wmm_used && (local->hw.queues >= 4); + assoc_data->wmm = bss->wmm_used && + (local->hw.queues >= IEEE80211_NUM_ACS); assoc_data->supp_rates = bss->supp_rates; assoc_data->supp_rates_len = bss->supp_rates_len; - assoc_data->ht_information_ie = - ieee80211_bss_get_ie(req->bss, WLAN_EID_HT_INFORMATION); + assoc_data->ht_operation_ie = + ieee80211_bss_get_ie(req->bss, WLAN_EID_HT_OPERATION); if (bss->wmm_used && bss->uapsd_supported && (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)) { @@ -3387,8 +3408,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, */ printk(KERN_DEBUG "%s: waiting for beacon from %pM\n", sdata->name, ifmgd->bssid); - assoc_data->timeout = jiffies + - TU_TO_EXP_TIME(req->bss->beacon_interval); + assoc_data->timeout = TU_TO_EXP_TIME(req->bss->beacon_interval); } else { assoc_data->have_beacon = true; assoc_data->sent_assoc = false; @@ -3441,7 +3461,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, sdata->name, req->bssid, req->reason_code); if (ifmgd->associated && - compare_ether_addr(ifmgd->associated->bssid, req->bssid) == 0) + ether_addr_equal(ifmgd->associated->bssid, req->bssid)) ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, req->reason_code, true, frame_buf); else @@ -3498,7 +3518,7 @@ int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata, return 0; } -void ieee80211_mgd_teardown(struct ieee80211_sub_if_data *sdata) +void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index ef8eba1d736..af1c4e26e96 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -127,6 +127,10 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) drv_remove_interface(local, sdata); } + sdata = rtnl_dereference(local->monitor_sdata); + if (sdata) + drv_remove_interface(local, sdata); + /* stop hardware - this must stop RX */ if (local->open_count) ieee80211_stop_device(local); diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index b4f7600a3e3..3313c117b32 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -145,7 +145,7 @@ static ssize_t rcname_read(struct file *file, char __user *userbuf, static const struct file_operations rcname_ops = { .read = rcname_read, - .open = mac80211_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; #endif diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h index fbb1efdc4d0..6e4fd32c661 100644 --- a/net/mac80211/rate.h +++ b/net/mac80211/rate.h @@ -17,6 +17,7 @@ #include <net/mac80211.h> #include "ieee80211_i.h" #include "sta_info.h" +#include "driver-ops.h" struct rate_control_ref { struct ieee80211_local *local; @@ -63,8 +64,7 @@ static inline void rate_control_rate_init(struct sta_info *sta) static inline void rate_control_rate_update(struct ieee80211_local *local, struct ieee80211_supported_band *sband, - struct sta_info *sta, u32 changed, - enum nl80211_channel_type oper_chan_type) + struct sta_info *sta, u32 changed) { struct rate_control_ref *ref = local->rate_ctrl; struct ieee80211_sta *ista = &sta->sta; @@ -72,7 +72,8 @@ static inline void rate_control_rate_update(struct ieee80211_local *local, if (ref && ref->ops->rate_update) ref->ops->rate_update(ref->priv, sband, ista, - priv_sta, changed, oper_chan_type); + priv_sta, changed); + drv_sta_rc_update(local, sta->sdata, &sta->sta, changed); } static inline void *rate_control_alloc_sta(struct rate_control_ref *ref, diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index b39dda523f3..79633ae06fd 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -334,14 +334,15 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, static void -calc_rate_durations(struct ieee80211_local *local, struct minstrel_rate *d, +calc_rate_durations(enum ieee80211_band band, + struct minstrel_rate *d, struct ieee80211_rate *rate) { int erp = !!(rate->flags & IEEE80211_RATE_ERP_G); - d->perfect_tx_time = ieee80211_frame_duration(local, 1200, + d->perfect_tx_time = ieee80211_frame_duration(band, 1200, rate->bitrate, erp, 1); - d->ack_time = ieee80211_frame_duration(local, 10, + d->ack_time = ieee80211_frame_duration(band, 10, rate->bitrate, erp, 1); } @@ -379,14 +380,14 @@ minstrel_rate_init(void *priv, struct ieee80211_supported_band *sband, { struct minstrel_sta_info *mi = priv_sta; struct minstrel_priv *mp = priv; - struct ieee80211_local *local = hw_to_local(mp->hw); struct ieee80211_rate *ctl_rate; unsigned int i, n = 0; unsigned int t_slot = 9; /* FIXME: get real slot time */ mi->lowest_rix = rate_lowest_index(sband, sta); ctl_rate = &sband->bitrates[mi->lowest_rix]; - mi->sp_ack_dur = ieee80211_frame_duration(local, 10, ctl_rate->bitrate, + mi->sp_ack_dur = ieee80211_frame_duration(sband->band, 10, + ctl_rate->bitrate, !!(ctl_rate->flags & IEEE80211_RATE_ERP_G), 1); for (i = 0; i < sband->n_bitrates; i++) { @@ -402,7 +403,7 @@ minstrel_rate_init(void *priv, struct ieee80211_supported_band *sband, mr->rix = i; mr->bitrate = sband->bitrates[i].bitrate / 5; - calc_rate_durations(local, mr, &sband->bitrates[i]); + calc_rate_durations(sband->band, mr, &sband->bitrates[i]); /* calculate maximum number of retransmissions before * fallback (based on maximum segment size) */ diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 16e0b277b9a..2d1acc6c544 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -686,14 +686,12 @@ minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta, static void minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband, - struct ieee80211_sta *sta, void *priv_sta, - enum nl80211_channel_type oper_chan_type) + struct ieee80211_sta *sta, void *priv_sta) { struct minstrel_priv *mp = priv; struct minstrel_ht_sta_priv *msp = priv_sta; struct minstrel_ht_sta *mi = &msp->ht; struct ieee80211_mcs_info *mcs = &sta->ht_cap.mcs; - struct ieee80211_local *local = hw_to_local(mp->hw); u16 sta_cap = sta->ht_cap.cap; int n_supported = 0; int ack_dur; @@ -712,8 +710,8 @@ minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband, memset(mi, 0, sizeof(*mi)); mi->stats_update = jiffies; - ack_dur = ieee80211_frame_duration(local, 10, 60, 1, 1); - mi->overhead = ieee80211_frame_duration(local, 0, 60, 1, 1) + ack_dur; + ack_dur = ieee80211_frame_duration(sband->band, 10, 60, 1, 1); + mi->overhead = ieee80211_frame_duration(sband->band, 0, 60, 1, 1) + ack_dur; mi->overhead_rtscts = mi->overhead + 2 * ack_dur; mi->avg_ampdu_len = MINSTREL_FRAC(1, 1); @@ -735,10 +733,6 @@ minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband, if (sta_cap & IEEE80211_HT_CAP_LDPC_CODING) mi->tx_flags |= IEEE80211_TX_CTL_LDPC; - if (oper_chan_type != NL80211_CHAN_HT40MINUS && - oper_chan_type != NL80211_CHAN_HT40PLUS) - sta_cap &= ~IEEE80211_HT_CAP_SUP_WIDTH_20_40; - smps = (sta_cap & IEEE80211_HT_CAP_SM_PS) >> IEEE80211_HT_CAP_SM_PS_SHIFT; @@ -788,17 +782,15 @@ static void minstrel_ht_rate_init(void *priv, struct ieee80211_supported_band *sband, struct ieee80211_sta *sta, void *priv_sta) { - struct minstrel_priv *mp = priv; - - minstrel_ht_update_caps(priv, sband, sta, priv_sta, mp->hw->conf.channel_type); + minstrel_ht_update_caps(priv, sband, sta, priv_sta); } static void minstrel_ht_rate_update(void *priv, struct ieee80211_supported_band *sband, struct ieee80211_sta *sta, void *priv_sta, - u32 changed, enum nl80211_channel_type oper_chan_type) + u32 changed) { - minstrel_ht_update_caps(priv, sband, sta, priv_sta, oper_chan_type); + minstrel_ht_update_caps(priv, sband, sta, priv_sta); } static void * diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index bcfe8c77c83..8257a09eeed 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -103,7 +103,7 @@ static void ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, struct sk_buff *skb, struct ieee80211_rate *rate, - int rtap_len) + int rtap_len, bool has_fcs) { struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct ieee80211_radiotap_header *rthdr; @@ -134,7 +134,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, } /* IEEE80211_RADIOTAP_FLAGS */ - if (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS) + if (has_fcs && (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS)) *pos |= IEEE80211_RADIOTAP_F_FCS; if (status->flag & (RX_FLAG_FAILED_FCS_CRC | RX_FLAG_FAILED_PLCP_CRC)) *pos |= IEEE80211_RADIOTAP_F_BADFCS; @@ -294,7 +294,8 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, } /* prepend radiotap information */ - ieee80211_add_rx_radiotap_header(local, skb, rate, needed_headroom); + ieee80211_add_rx_radiotap_header(local, skb, rate, needed_headroom, + true); skb_reset_mac_header(skb); skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -425,6 +426,7 @@ ieee80211_rx_h_passive_scan(struct ieee80211_rx_data *rx) if (test_bit(SCAN_HW_SCANNING, &local->scanning) || test_bit(SCAN_SW_SCANNING, &local->scanning) || + test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning) || local->sched_scanning) return ieee80211_scan_rx(rx->sdata, skb); @@ -490,12 +492,12 @@ ieee80211_rx_mesh_check(struct ieee80211_rx_data *rx) if (ieee80211_has_tods(hdr->frame_control) || !ieee80211_has_fromds(hdr->frame_control)) return RX_DROP_MONITOR; - if (compare_ether_addr(hdr->addr3, dev_addr) == 0) + if (ether_addr_equal(hdr->addr3, dev_addr)) return RX_DROP_MONITOR; } else { if (!ieee80211_has_a4(hdr->frame_control)) return RX_DROP_MONITOR; - if (compare_ether_addr(hdr->addr4, dev_addr) == 0) + if (ether_addr_equal(hdr->addr4, dev_addr)) return RX_DROP_MONITOR; } } @@ -793,8 +795,7 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx) /* reset session timer */ if (tid_agg_rx->timeout) - mod_timer(&tid_agg_rx->session_timer, - TU_TO_EXP_TIME(tid_agg_rx->timeout)); + tid_agg_rx->last_rx = jiffies; /* if this mpdu is fragmented - terminate rx aggregation session */ sc = le16_to_cpu(hdr->seq_ctrl); @@ -1274,7 +1275,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) if (rx->sdata->vif.type == NL80211_IFTYPE_ADHOC) { u8 *bssid = ieee80211_get_bssid(hdr, rx->skb->len, NL80211_IFTYPE_ADHOC); - if (compare_ether_addr(bssid, rx->sdata->u.ibss.bssid) == 0) { + if (ether_addr_equal(bssid, rx->sdata->u.ibss.bssid)) { sta->last_rx = jiffies; if (ieee80211_is_data(hdr->frame_control)) { sta->last_rx_rate_idx = status->rate_idx; @@ -1437,8 +1438,8 @@ ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, */ if (((hdr->frame_control ^ f_hdr->frame_control) & cpu_to_le16(IEEE80211_FCTL_FTYPE)) || - compare_ether_addr(hdr->addr1, f_hdr->addr1) != 0 || - compare_ether_addr(hdr->addr2, f_hdr->addr2) != 0) + !ether_addr_equal(hdr->addr1, f_hdr->addr1) || + !ether_addr_equal(hdr->addr2, f_hdr->addr2)) continue; if (time_after(jiffies, entry->first_frag_time + 2 * HZ)) { @@ -1713,8 +1714,8 @@ static bool ieee80211_frame_allowed(struct ieee80211_rx_data *rx, __le16 fc) * of whether the frame was encrypted or not. */ if (ehdr->h_proto == rx->sdata->control_port_protocol && - (compare_ether_addr(ehdr->h_dest, rx->sdata->vif.addr) == 0 || - compare_ether_addr(ehdr->h_dest, pae_group_addr) == 0)) + (ether_addr_equal(ehdr->h_dest, rx->sdata->vif.addr) || + ether_addr_equal(ehdr->h_dest, pae_group_addr))) return true; if (ieee80211_802_1x_port_control(rx) || @@ -1751,9 +1752,9 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) * local net stack and back to the wireless medium */ xmit_skb = skb_copy(skb, GFP_ATOMIC); - if (!xmit_skb && net_ratelimit()) - printk(KERN_DEBUG "%s: failed to clone " - "multicast frame\n", dev->name); + if (!xmit_skb) + net_dbg_ratelimited("%s: failed to clone multicast frame\n", + dev->name); } else { dsta = sta_info_get(sdata, skb->data); if (dsta) { @@ -1924,7 +1925,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) mpp_path_add(proxied_addr, mpp_addr, sdata); } else { spin_lock_bh(&mppath->state_lock); - if (compare_ether_addr(mppath->mpp, mpp_addr) != 0) + if (!ether_addr_equal(mppath->mpp, mpp_addr)) memcpy(mppath->mpp, mpp_addr, ETH_ALEN); spin_unlock_bh(&mppath->state_lock); } @@ -1933,7 +1934,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) /* Frame has reached destination. Don't forward */ if (!is_multicast_ether_addr(hdr->addr1) && - compare_ether_addr(sdata->vif.addr, hdr->addr3) == 0) + ether_addr_equal(sdata->vif.addr, hdr->addr3)) return RX_CONTINUE; q = ieee80211_select_queue_80211(local, skb, hdr); @@ -1956,9 +1957,8 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) fwd_skb = skb_copy(skb, GFP_ATOMIC); if (!fwd_skb) { - if (net_ratelimit()) - printk(KERN_DEBUG "%s: failed to clone mesh frame\n", - sdata->name); + net_dbg_ratelimited("%s: failed to clone mesh frame\n", + sdata->name); goto out; } @@ -2121,13 +2121,13 @@ static void ieee80211_process_sa_query_req(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb; struct ieee80211_mgmt *resp; - if (compare_ether_addr(mgmt->da, sdata->vif.addr) != 0) { + if (!ether_addr_equal(mgmt->da, sdata->vif.addr)) { /* Not to own unicast address */ return; } - if (compare_ether_addr(mgmt->sa, sdata->u.mgd.bssid) != 0 || - compare_ether_addr(mgmt->bssid, sdata->u.mgd.bssid) != 0) { + if (!ether_addr_equal(mgmt->sa, sdata->u.mgd.bssid) || + !ether_addr_equal(mgmt->bssid, sdata->u.mgd.bssid)) { /* Not from the current AP or not associated yet. */ return; } @@ -2269,11 +2269,8 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) sband = rx->local->hw.wiphy->bands[status->band]; - rate_control_rate_update( - local, sband, rx->sta, - IEEE80211_RC_SMPS_CHANGED, - ieee80211_get_tx_channel_type( - local, local->_oper_channel_type)); + rate_control_rate_update(local, sband, rx->sta, + IEEE80211_RC_SMPS_CHANGED); goto handled; } default: @@ -2340,7 +2337,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) if (sdata->vif.type != NL80211_IFTYPE_STATION) break; - if (compare_ether_addr(mgmt->bssid, sdata->u.mgd.bssid)) + if (!ether_addr_equal(mgmt->bssid, sdata->u.mgd.bssid)) break; goto queue; @@ -2571,7 +2568,8 @@ static void ieee80211_rx_cooked_monitor(struct ieee80211_rx_data *rx, goto out_free_skb; /* prepend radiotap information */ - ieee80211_add_rx_radiotap_header(local, skb, rate, needed_headroom); + ieee80211_add_rx_radiotap_header(local, skb, rate, needed_headroom, + false); skb_set_mac_header(skb, 0); skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -2773,7 +2771,7 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, if (!bssid && !sdata->u.mgd.use_4addr) return 0; if (!multicast && - compare_ether_addr(sdata->vif.addr, hdr->addr1) != 0) { + !ether_addr_equal(sdata->vif.addr, hdr->addr1)) { if (!(sdata->dev->flags & IFF_PROMISC) || sdata->u.mgd.use_4addr) return 0; @@ -2791,8 +2789,7 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, return 0; status->rx_flags &= ~IEEE80211_RX_RA_MATCH; } else if (!multicast && - compare_ether_addr(sdata->vif.addr, - hdr->addr1) != 0) { + !ether_addr_equal(sdata->vif.addr, hdr->addr1)) { if (!(sdata->dev->flags & IFF_PROMISC)) return 0; status->rx_flags &= ~IEEE80211_RX_RA_MATCH; @@ -2808,8 +2805,7 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, break; case NL80211_IFTYPE_MESH_POINT: if (!multicast && - compare_ether_addr(sdata->vif.addr, - hdr->addr1) != 0) { + !ether_addr_equal(sdata->vif.addr, hdr->addr1)) { if (!(sdata->dev->flags & IFF_PROMISC)) return 0; @@ -2819,8 +2815,7 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_AP: if (!bssid) { - if (compare_ether_addr(sdata->vif.addr, - hdr->addr1)) + if (!ether_addr_equal(sdata->vif.addr, hdr->addr1)) return 0; } else if (!ieee80211_bssid_match(bssid, sdata->vif.addr)) { @@ -2842,7 +2837,7 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, case NL80211_IFTYPE_WDS: if (bssid || !ieee80211_is_data(hdr->frame_control)) return 0; - if (compare_ether_addr(sdata->u.wds.remote_addr, hdr->addr2)) + if (!ether_addr_equal(sdata->u.wds.remote_addr, hdr->addr2)) return 0; break; default: @@ -2919,6 +2914,7 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, local->dot11ReceivedFragmentCount++; if (unlikely(test_bit(SCAN_HW_SCANNING, &local->scanning) || + test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning) || test_bit(SCAN_SW_SCANNING, &local->scanning))) status->rx_flags |= IEEE80211_RX_IN_SCAN; diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 33cd1690137..169da0742c8 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -29,20 +29,6 @@ #define IEEE80211_CHANNEL_TIME (HZ / 33) #define IEEE80211_PASSIVE_CHANNEL_TIME (HZ / 8) -struct ieee80211_bss * -ieee80211_rx_bss_get(struct ieee80211_local *local, u8 *bssid, int freq, - u8 *ssid, u8 ssid_len) -{ - struct cfg80211_bss *cbss; - - cbss = cfg80211_get_bss(local->hw.wiphy, - ieee80211_get_channel(local->hw.wiphy, freq), - bssid, ssid, ssid_len, 0, 0); - if (!cbss) - return NULL; - return (void *)cbss->priv; -} - static void ieee80211_rx_bss_free(struct cfg80211_bss *cbss) { struct ieee80211_bss *bss = (void *)cbss->priv; @@ -208,7 +194,7 @@ ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) presp = ieee80211_is_probe_resp(fc); if (presp) { /* ignore ProbeResp to foreign address */ - if (compare_ether_addr(mgmt->da, sdata->vif.addr)) + if (!ether_addr_equal(mgmt->da, sdata->vif.addr)) return RX_DROP_MONITOR; presp = true; @@ -370,7 +356,7 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local) */ drv_sw_scan_start(local); - local->leave_oper_channel_time = 0; + local->leave_oper_channel_time = jiffies; local->next_scan_state = SCAN_DECISION; local->scan_channel_idx = 0; @@ -387,6 +373,57 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local) return 0; } +static bool ieee80211_can_scan(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) +{ + if (!list_empty(&local->work_list)) + return false; + + if (sdata->vif.type == NL80211_IFTYPE_STATION && + sdata->u.mgd.flags & (IEEE80211_STA_BEACON_POLL | + IEEE80211_STA_CONNECTION_POLL)) + return false; + + return true; +} + +void ieee80211_run_deferred_scan(struct ieee80211_local *local) +{ + lockdep_assert_held(&local->mtx); + + if (!local->scan_req || local->scanning) + return; + + if (!ieee80211_can_scan(local, local->scan_sdata)) + return; + + ieee80211_queue_delayed_work(&local->hw, &local->scan_work, + round_jiffies_relative(0)); +} + +static void ieee80211_scan_state_send_probe(struct ieee80211_local *local, + unsigned long *next_delay) +{ + int i; + struct ieee80211_sub_if_data *sdata = local->scan_sdata; + enum ieee80211_band band = local->hw.conf.channel->band; + + for (i = 0; i < local->scan_req->n_ssids; i++) + ieee80211_send_probe_req( + sdata, NULL, + local->scan_req->ssids[i].ssid, + local->scan_req->ssids[i].ssid_len, + local->scan_req->ie, local->scan_req->ie_len, + local->scan_req->rates[band], false, + local->scan_req->no_cck); + + /* + * After sending probe requests, wait for probe responses + * on the channel. + */ + *next_delay = IEEE80211_CHANNEL_TIME; + local->next_scan_state = SCAN_DECISION; +} static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req) @@ -399,7 +436,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, if (local->scan_req) return -EBUSY; - if (!list_empty(&local->work_list)) { + if (!ieee80211_can_scan(local, sdata)) { /* wait for the work to finish/time out */ local->scan_req = req; local->scan_sdata = sdata; @@ -438,10 +475,47 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, local->scan_req = req; local->scan_sdata = sdata; - if (local->ops->hw_scan) + if (local->ops->hw_scan) { __set_bit(SCAN_HW_SCANNING, &local->scanning); - else + } else if ((req->n_channels == 1) && + (req->channels[0]->center_freq == + local->hw.conf.channel->center_freq)) { + + /* If we are scanning only on the current channel, then + * we do not need to stop normal activities + */ + unsigned long next_delay; + + __set_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning); + + ieee80211_recalc_idle(local); + + /* Notify driver scan is starting, keep order of operations + * same as normal software scan, in case that matters. */ + drv_sw_scan_start(local); + + ieee80211_configure_filter(local); /* accept probe-responses */ + + /* We need to ensure power level is at max for scanning. */ + ieee80211_hw_config(local, 0); + + if ((req->channels[0]->flags & + IEEE80211_CHAN_PASSIVE_SCAN) || + !local->scan_req->n_ssids) { + next_delay = IEEE80211_PASSIVE_CHANNEL_TIME; + } else { + ieee80211_scan_state_send_probe(local, &next_delay); + next_delay = IEEE80211_CHANNEL_TIME; + } + + /* Now, just wait a bit and we are all done! */ + ieee80211_queue_delayed_work(&local->hw, &local->scan_work, + next_delay); + return 0; + } else { + /* Do normal software scan */ __set_bit(SCAN_SW_SCANNING, &local->scanning); + } ieee80211_recalc_idle(local); @@ -598,30 +672,6 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local, local->next_scan_state = SCAN_SEND_PROBE; } -static void ieee80211_scan_state_send_probe(struct ieee80211_local *local, - unsigned long *next_delay) -{ - int i; - struct ieee80211_sub_if_data *sdata = local->scan_sdata; - enum ieee80211_band band = local->hw.conf.channel->band; - - for (i = 0; i < local->scan_req->n_ssids; i++) - ieee80211_send_probe_req( - sdata, NULL, - local->scan_req->ssids[i].ssid, - local->scan_req->ssids[i].ssid_len, - local->scan_req->ie, local->scan_req->ie_len, - local->scan_req->rates[band], false, - local->scan_req->no_cck); - - /* - * After sending probe requests, wait for probe responses - * on the channel. - */ - *next_delay = IEEE80211_CHANNEL_TIME; - local->next_scan_state = SCAN_DECISION; -} - static void ieee80211_scan_state_suspend(struct ieee80211_local *local, unsigned long *next_delay) { @@ -672,6 +722,12 @@ void ieee80211_scan_work(struct work_struct *work) sdata = local->scan_sdata; + /* When scanning on-channel, the first-callback means completed. */ + if (test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning)) { + aborted = test_and_clear_bit(SCAN_ABORTED, &local->scanning); + goto out_complete; + } + if (test_and_clear_bit(SCAN_COMPLETED, &local->scanning)) { aborted = test_and_clear_bit(SCAN_ABORTED, &local->scanning); goto out_complete; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 38137cb5f6f..f5b1638fbf8 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -102,7 +102,7 @@ struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata, lockdep_is_held(&local->sta_mtx)); while (sta) { if (sta->sdata == sdata && - compare_ether_addr(sta->sta.addr, addr) == 0) + ether_addr_equal(sta->sta.addr, addr)) break; sta = rcu_dereference_check(sta->hnext, lockdep_is_held(&local->sta_mtx)); @@ -125,7 +125,7 @@ struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata, while (sta) { if ((sta->sdata == sdata || (sta->sdata->bss && sta->sdata->bss == sdata->bss)) && - compare_ether_addr(sta->sta.addr, addr) == 0) + ether_addr_equal(sta->sta.addr, addr)) break; sta = rcu_dereference_check(sta->hnext, lockdep_is_held(&local->sta_mtx)); @@ -302,7 +302,7 @@ static int sta_info_insert_check(struct sta_info *sta) if (unlikely(!ieee80211_sdata_running(sdata))) return -ENETDOWN; - if (WARN_ON(compare_ether_addr(sta->sta.addr, sdata->vif.addr) == 0 || + if (WARN_ON(ether_addr_equal(sta->sta.addr, sdata->vif.addr) || is_multicast_ether_addr(sta->sta.addr))) return -EINVAL; @@ -912,7 +912,7 @@ struct ieee80211_sta *ieee80211_find_sta_by_ifaddr(struct ieee80211_hw *hw, */ for_each_sta_info(hw_to_local(hw), addr, sta, nxt) { if (localaddr && - compare_ether_addr(sta->sdata->vif.addr, localaddr) != 0) + !ether_addr_equal(sta->sdata->vif.addr, localaddr)) continue; if (!sta->uploaded) return NULL; @@ -1195,13 +1195,15 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, ieee80211_is_qos_nullfunc(hdr->frame_control)) qoshdr = ieee80211_get_qos_ctl(hdr); - /* set EOSP for the frame */ - if (reason == IEEE80211_FRAME_RELEASE_UAPSD && - qoshdr && skb_queue_empty(&frames)) - *qoshdr |= IEEE80211_QOS_CTL_EOSP; + /* end service period after last frame */ + if (skb_queue_empty(&frames)) { + if (reason == IEEE80211_FRAME_RELEASE_UAPSD && + qoshdr) + *qoshdr |= IEEE80211_QOS_CTL_EOSP; - info->flags |= IEEE80211_TX_STATUS_EOSP | - IEEE80211_TX_CTL_REQ_TX_STATUS; + info->flags |= IEEE80211_TX_STATUS_EOSP | + IEEE80211_TX_CTL_REQ_TX_STATUS; + } if (qoshdr) tids |= BIT(*qoshdr & IEEE80211_QOS_CTL_TID_MASK); @@ -1415,15 +1417,19 @@ int sta_info_move_state(struct sta_info *sta, if (sta->sta_state == IEEE80211_STA_AUTH) { set_bit(WLAN_STA_ASSOC, &sta->_flags); } else if (sta->sta_state == IEEE80211_STA_AUTHORIZED) { - if (sta->sdata->vif.type == NL80211_IFTYPE_AP) - atomic_dec(&sta->sdata->u.ap.num_sta_authorized); + if (sta->sdata->vif.type == NL80211_IFTYPE_AP || + (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN && + !sta->sdata->u.vlan.sta)) + atomic_dec(&sta->sdata->bss->num_mcast_sta); clear_bit(WLAN_STA_AUTHORIZED, &sta->_flags); } break; case IEEE80211_STA_AUTHORIZED: if (sta->sta_state == IEEE80211_STA_ASSOC) { - if (sta->sdata->vif.type == NL80211_IFTYPE_AP) - atomic_inc(&sta->sdata->u.ap.num_sta_authorized); + if (sta->sdata->vif.type == NL80211_IFTYPE_AP || + (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN && + !sta->sdata->u.vlan.sta)) + atomic_inc(&sta->sdata->bss->num_mcast_sta); set_bit(WLAN_STA_AUTHORIZED, &sta->_flags); } break; diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index ab0576827ba..3bb24a121c9 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -55,6 +55,7 @@ * @WLAN_STA_4ADDR_EVENT: 4-addr event was already sent for this frame. * @WLAN_STA_INSERTED: This station is inserted into the hash table. * @WLAN_STA_RATE_CONTROL: rate control was initialized for this station. + * @WLAN_STA_TOFFSET_KNOWN: toffset calculated for this station is valid. */ enum ieee80211_sta_info_flags { WLAN_STA_AUTH, @@ -76,6 +77,7 @@ enum ieee80211_sta_info_flags { WLAN_STA_4ADDR_EVENT, WLAN_STA_INSERTED, WLAN_STA_RATE_CONTROL, + WLAN_STA_TOFFSET_KNOWN, }; #define STA_TID_NUM 16 @@ -101,6 +103,7 @@ enum ieee80211_sta_info_flags { * @dialog_token: dialog token for aggregation session * @timeout: session timeout value to be filled in ADDBA requests * @state: session state (see above) + * @last_tx: jiffies of last tx activity * @stop_initiator: initiator of a session stop * @tx_stop: TX DelBA frame when stopping * @buf_size: reorder buffer size at receiver @@ -122,6 +125,7 @@ struct tid_ampdu_tx { struct timer_list addba_resp_timer; struct sk_buff_head pending; unsigned long state; + unsigned long last_tx; u16 timeout; u8 dialog_token; u8 stop_initiator; @@ -139,6 +143,7 @@ struct tid_ampdu_tx { * @reorder_time: jiffies when skb was added * @session_timer: check if peer keeps Tx-ing on the TID (by timeout value) * @reorder_timer: releases expired frames from the reorder buffer. + * @last_rx: jiffies of last rx activity * @head_seq_num: head sequence number in reordering buffer. * @stored_mpdu_num: number of MPDUs in reordering buffer * @ssn: Starting Sequence Number expected to be aggregated. @@ -163,6 +168,7 @@ struct tid_ampdu_rx { unsigned long *reorder_time; struct timer_list session_timer; struct timer_list reorder_timer; + unsigned long last_rx; u16 head_seq_num; u16 stored_mpdu_num; u16 ssn; @@ -264,6 +270,7 @@ struct sta_ampdu_mlme { * @plink_timeout: timeout of peer link * @plink_timer: peer link watch timer * @plink_timer_was_running: used by suspend/resume to restore timers + * @t_offset: timing offset relative to this host * @debugfs: debug filesystem info * @dead: set to true when sta is unlinked * @uploaded: set to true when sta is uploaded to the driver @@ -353,6 +360,9 @@ struct sta_info { enum nl80211_plink_state plink_state; u32 plink_timeout; struct timer_list plink_timer; + s64 t_offset; + s64 t_offset_setpoint; + enum nl80211_channel_type ch_type; #endif #ifdef CONFIG_MAC80211_DEBUGFS @@ -365,6 +375,8 @@ struct sta_info { unsigned int lost_packets; unsigned int beacon_loss_count; + bool supports_40mhz; + /* keep last! */ struct ieee80211_sta sta; }; @@ -490,7 +502,7 @@ void for_each_sta_info_type_check(struct ieee80211_local *local, nxt = _sta ? rcu_dereference(_sta->hnext) : NULL \ ) \ /* compare address and run code only if it matches */ \ - if (compare_ether_addr(_sta->sta.addr, (_addr)) == 0) + if (ether_addr_equal(_sta->sta.addr, (_addr))) /* * Get STA info by index, BROKEN! diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 5f8f89e89d6..28cfa981cfb 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -355,7 +355,13 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) int rtap_len; for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { - if (info->status.rates[i].idx < 0) { + if ((info->flags & IEEE80211_TX_CTL_AMPDU) && + !(info->flags & IEEE80211_TX_STAT_AMPDU)) { + /* just the first aggr frame carry status info */ + info->status.rates[i].idx = -1; + info->status.rates[i].count = 0; + break; + } else if (info->status.rates[i].idx < 0) { break; } else if (i >= hw->max_report_rates) { /* the HW cannot have attempted that rate */ @@ -378,7 +384,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) for_each_sta_info(local, hdr->addr1, sta, tmp) { /* skip wrong virtual interface */ - if (compare_ether_addr(hdr->addr2, sta->sdata->vif.addr)) + if (!ether_addr_equal(hdr->addr2, sta->sdata->vif.addr)) continue; if (info->flags & IEEE80211_TX_STATUS_EOSP) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 782a60198df..5f827a6b0d8 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -159,7 +159,7 @@ static __le16 ieee80211_duration(struct ieee80211_tx_data *tx, /* Time needed to transmit ACK * (10 bytes + 4-byte FCS = 112 bits) plus SIFS; rounded up * to closest integer */ - dur = ieee80211_frame_duration(local, 10, rate, erp, + dur = ieee80211_frame_duration(sband->band, 10, rate, erp, tx->sdata->vif.bss_conf.use_short_preamble); if (next_frag_len) { @@ -167,7 +167,7 @@ static __le16 ieee80211_duration(struct ieee80211_tx_data *tx, * transmit next fragment plus ACK and 2 x SIFS. */ dur *= 2; /* ACK + SIFS */ /* next fragment */ - dur += ieee80211_frame_duration(local, next_frag_len, + dur += ieee80211_frame_duration(sband->band, next_frag_len, txrate->bitrate, erp, tx->sdata->vif.bss_conf.use_short_preamble); } @@ -230,9 +230,9 @@ ieee80211_tx_h_dynamic_ps(struct ieee80211_tx_data *tx) * changed via debugfs, user needs to reassociate manually to have * everything in sync. */ - if ((ifmgd->flags & IEEE80211_STA_UAPSD_ENABLED) - && (ifmgd->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VO) - && skb_get_queue_mapping(tx->skb) == 0) + if ((ifmgd->flags & IEEE80211_STA_UAPSD_ENABLED) && + (ifmgd->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VO) && + skb_get_queue_mapping(tx->skb) == IEEE80211_AC_VO) return TX_CONTINUE; if (local->hw.conf.flags & IEEE80211_CONF_PS) { @@ -306,7 +306,7 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx) } } else if (unlikely(tx->sdata->vif.type == NL80211_IFTYPE_AP && ieee80211_is_data(hdr->frame_control) && - !atomic_read(&tx->sdata->u.ap.num_sta_authorized))) { + !atomic_read(&tx->sdata->u.ap.num_mcast_sta))) { /* * No associated STAs - no need to send multicast * frames. @@ -400,6 +400,8 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx) return TX_CONTINUE; info->flags |= IEEE80211_TX_CTL_SEND_AFTER_DTIM; + if (tx->local->hw.flags & IEEE80211_HW_QUEUE_CONTROL) + info->hw_queue = tx->sdata->vif.cab_queue; /* device releases frame after DTIM beacon */ if (!(tx->local->hw.flags & IEEE80211_HW_HOST_BROADCAST_PS_BUFFERING)) @@ -411,9 +413,8 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx) if (skb_queue_len(&tx->sdata->bss->ps_bc_buf) >= AP_MAX_BC_BUFFER) { #ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - if (net_ratelimit()) - printk(KERN_DEBUG "%s: BC TX buffer full - dropping the oldest frame\n", - tx->sdata->name); + net_dbg_ratelimited("%s: BC TX buffer full - dropping the oldest frame\n", + tx->sdata->name); #endif dev_kfree_skb(skb_dequeue(&tx->sdata->bss->ps_bc_buf)); } else @@ -474,10 +475,8 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) if (skb_queue_len(&sta->ps_tx_buf[ac]) >= STA_MAX_TX_BUFFER) { struct sk_buff *old = skb_dequeue(&sta->ps_tx_buf[ac]); #ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - if (net_ratelimit()) - printk(KERN_DEBUG "%s: STA %pM TX buffer for " - "AC %d full - dropping oldest frame\n", - tx->sdata->name, sta->sta.addr, ac); + net_dbg_ratelimited("%s: STA %pM TX buffer for AC %d full - dropping oldest frame\n", + tx->sdata->name, sta->sta.addr, ac); #endif dev_kfree_skb(old); } else @@ -1118,8 +1117,7 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx, /* reset session timer */ if (reset_agg_timer && tid_tx->timeout) - mod_timer(&tid_tx->session_timer, - TU_TO_EXP_TIME(tid_tx->timeout)); + tid_tx->last_tx = jiffies; return queued; } @@ -1158,7 +1156,8 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, tx->sta = rcu_dereference(sdata->u.vlan.sta); if (!tx->sta && sdata->dev->ieee80211_ptr->use_4addr) return TX_DROP; - } else if (info->flags & IEEE80211_TX_CTL_INJECTED) { + } else if (info->flags & IEEE80211_TX_CTL_INJECTED || + tx->sdata->control_port_protocol == tx->skb->protocol) { tx->sta = sta_info_get_bss(sdata, hdr->addr1); } if (!tx->sta) @@ -1215,11 +1214,19 @@ static bool ieee80211_tx_frags(struct ieee80211_local *local, bool txpending) { struct sk_buff *skb, *tmp; - struct ieee80211_tx_info *info; unsigned long flags; skb_queue_walk_safe(skbs, skb, tmp) { - int q = skb_get_queue_mapping(skb); + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + int q = info->hw_queue; + +#ifdef CONFIG_MAC80211_VERBOSE_DEBUG + if (WARN_ON_ONCE(q >= local->hw.queues)) { + __skb_unlink(skb, skbs); + dev_kfree_skb(skb); + continue; + } +#endif spin_lock_irqsave(&local->queue_stop_reason_lock, flags); if (local->queue_stop_reasons[q] || @@ -1241,7 +1248,6 @@ static bool ieee80211_tx_frags(struct ieee80211_local *local, } spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); - info = IEEE80211_SKB_CB(skb); info->control.vif = vif; info->control.sta = sta; @@ -1284,8 +1290,16 @@ static bool __ieee80211_tx(struct ieee80211_local *local, switch (sdata->vif.type) { case NL80211_IFTYPE_MONITOR: - sdata = NULL; - vif = NULL; + sdata = rcu_dereference(local->monitor_sdata); + if (sdata) { + vif = &sdata->vif; + info->hw_queue = + vif->hw_queue[skb_get_queue_mapping(skb)]; + } else if (local->hw.flags & IEEE80211_HW_QUEUE_CONTROL) { + dev_kfree_skb(skb); + return true; + } else + vif = NULL; break; case NL80211_IFTYPE_AP_VLAN: sdata = container_of(sdata->bss, @@ -1400,6 +1414,12 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, tx.channel = local->hw.conf.channel; info->band = tx.channel->band; + /* set up hw_queue value early */ + if (!(info->flags & IEEE80211_TX_CTL_TX_OFFCHAN) || + !(local->hw.flags & IEEE80211_HW_QUEUE_CONTROL)) + info->hw_queue = + sdata->vif.hw_queue[skb_get_queue_mapping(skb)]; + if (!invoke_tx_handlers(&tx)) result = __ieee80211_tx(local, &tx.skbs, led_len, tx.sta, txpending); @@ -1468,12 +1488,12 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) if (ieee80211_vif_is_mesh(&sdata->vif) && ieee80211_is_data(hdr->frame_control) && - !is_multicast_ether_addr(hdr->addr1)) - if (mesh_nexthop_resolve(skb, sdata)) { - /* skb queued: don't free */ - rcu_read_unlock(); - return; - } + !is_multicast_ether_addr(hdr->addr1) && + mesh_nexthop_resolve(skb, sdata)) { + /* skb queued: don't free */ + rcu_read_unlock(); + return; + } ieee80211_set_qos_hdr(sdata, skb); ieee80211_tx(sdata, skb, false); @@ -1642,7 +1662,7 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, skb->len >= len_rthdr + hdrlen + sizeof(rfc1042_header) + 2) { u8 *payload = (u8 *)hdr + hdrlen; - if (compare_ether_addr(payload, rfc1042_header) == 0) + if (ether_addr_equal(payload, rfc1042_header)) skb->protocol = cpu_to_be16((payload[6] << 8) | payload[7]); } @@ -1675,7 +1695,7 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, tmp_sdata->vif.type == NL80211_IFTYPE_AP_VLAN || tmp_sdata->vif.type == NL80211_IFTYPE_WDS) continue; - if (compare_ether_addr(tmp_sdata->vif.addr, hdr->addr2) == 0) { + if (ether_addr_equal(tmp_sdata->vif.addr, hdr->addr2)) { sdata = tmp_sdata; break; } @@ -1792,9 +1812,8 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, * is being proxied by a portal (i.e. portal address * differs from proxied address) */ - if (compare_ether_addr(sdata->vif.addr, - skb->data + ETH_ALEN) == 0 && - !(mppath && compare_ether_addr(mppath->mpp, skb->data))) { + if (ether_addr_equal(sdata->vif.addr, skb->data + ETH_ALEN) && + !(mppath && !ether_addr_equal(mppath->mpp, skb->data))) { hdrlen = ieee80211_fill_mesh_addresses(&hdr, &fc, skb->data, skb->data + ETH_ALEN); rcu_read_unlock(); @@ -1929,7 +1948,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, wme_sta = true; /* receiver and we are QoS enabled, use a QoS type frame */ - if (wme_sta && local->hw.queues >= 4) { + if (wme_sta && local->hw.queues >= IEEE80211_NUM_ACS) { fc |= cpu_to_le16(IEEE80211_STYPE_QOS_DATA); hdrlen += 2; } @@ -1941,12 +1960,10 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, if (unlikely(!ieee80211_vif_is_mesh(&sdata->vif) && !is_multicast_ether_addr(hdr.addr1) && !authorized && (cpu_to_be16(ethertype) != sdata->control_port_protocol || - compare_ether_addr(sdata->vif.addr, skb->data + ETH_ALEN)))) { + !ether_addr_equal(sdata->vif.addr, skb->data + ETH_ALEN)))) { #ifdef CONFIG_MAC80211_VERBOSE_DEBUG - if (net_ratelimit()) - printk(KERN_DEBUG "%s: dropped frame to %pM" - " (unauthorized port)\n", dev->name, - hdr.addr1); + net_dbg_ratelimited("%s: dropped frame to %pM (unauthorized port)\n", + dev->name, hdr.addr1); #endif I802_DEBUG_INC(local->tx_handlers_drop_unauth_port); @@ -2170,7 +2187,6 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local, void ieee80211_tx_pending(unsigned long data) { struct ieee80211_local *local = (struct ieee80211_local *)data; - struct ieee80211_sub_if_data *sdata; unsigned long flags; int i; bool txok; @@ -2207,8 +2223,7 @@ void ieee80211_tx_pending(unsigned long data) } if (skb_queue_empty(&local->pending[i])) - list_for_each_entry_rcu(sdata, &local->interfaces, list) - netif_wake_subqueue(sdata->dev, i); + ieee80211_propagate_queue_wake(local, i); } spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); @@ -2374,6 +2389,7 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, IEEE80211_STYPE_BEACON); } else if (ieee80211_vif_is_mesh(&sdata->vif)) { struct ieee80211_mgmt *mgmt; + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; u8 *pos; int hdr_len = offsetof(struct ieee80211_mgmt, u.beacon) + sizeof(mgmt->u.beacon); @@ -2383,6 +2399,10 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, goto out; #endif + if (ifmsh->sync_ops) + ifmsh->sync_ops->adjust_tbtt( + sdata); + skb = dev_alloc_skb(local->tx_headroom + hdr_len + 2 + /* NULL SSID */ @@ -2390,7 +2410,7 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, 2 + 3 + /* DS params */ 2 + (IEEE80211_MAX_SUPP_RATES - 8) + 2 + sizeof(struct ieee80211_ht_cap) + - 2 + sizeof(struct ieee80211_ht_info) + + 2 + sizeof(struct ieee80211_ht_operation) + 2 + sdata->u.mesh.mesh_id_len + 2 + sizeof(struct ieee80211_meshconf_ie) + sdata->u.mesh.ie_len); @@ -2414,12 +2434,12 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, *pos++ = WLAN_EID_SSID; *pos++ = 0x0; - if (ieee80211_add_srates_ie(&sdata->vif, skb) || + if (ieee80211_add_srates_ie(&sdata->vif, skb, true) || mesh_add_ds_params_ie(skb, sdata) || - ieee80211_add_ext_srates_ie(&sdata->vif, skb) || + ieee80211_add_ext_srates_ie(&sdata->vif, skb, true) || mesh_add_rsn_ie(skb, sdata) || mesh_add_ht_cap_ie(skb, sdata) || - mesh_add_ht_info_ie(skb, sdata) || + mesh_add_ht_oper_ie(skb, sdata) || mesh_add_meshid_ie(skb, sdata) || mesh_add_meshconf_ie(skb, sdata) || mesh_add_vendor_ies(skb, sdata)) { @@ -2603,7 +2623,7 @@ struct sk_buff *ieee80211_probereq_get(struct ieee80211_hw *hw, pos = skb_put(skb, ie_ssid_len); *pos++ = WLAN_EID_SSID; *pos++ = ssid_len; - if (ssid) + if (ssid_len) memcpy(pos, ssid, ssid_len); pos += ssid_len; @@ -2710,11 +2730,13 @@ EXPORT_SYMBOL(ieee80211_get_buffered_bc); void ieee80211_tx_skb_tid(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, int tid) { + int ac = ieee802_1d_to_ac[tid]; + skb_set_mac_header(skb, 0); skb_set_network_header(skb, 0); skb_set_transport_header(skb, 0); - skb_set_queue_mapping(skb, ieee802_1d_to_ac[tid]); + skb_set_queue_mapping(skb, ac); skb->priority = tid; /* diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 32f7a3b3d43..22f2216b397 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -106,7 +106,7 @@ void ieee80211_tx_set_protected(struct ieee80211_tx_data *tx) } } -int ieee80211_frame_duration(struct ieee80211_local *local, size_t len, +int ieee80211_frame_duration(enum ieee80211_band band, size_t len, int rate, int erp, int short_preamble) { int dur; @@ -120,7 +120,7 @@ int ieee80211_frame_duration(struct ieee80211_local *local, size_t len, * DIV_ROUND_UP() operations. */ - if (local->hw.conf.channel->band == IEEE80211_BAND_5GHZ || erp) { + if (band == IEEE80211_BAND_5GHZ || erp) { /* * OFDM: * @@ -162,10 +162,10 @@ int ieee80211_frame_duration(struct ieee80211_local *local, size_t len, /* Exported duration function for driver use */ __le16 ieee80211_generic_frame_duration(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + enum ieee80211_band band, size_t frame_len, struct ieee80211_rate *rate) { - struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_sub_if_data *sdata; u16 dur; int erp; @@ -179,7 +179,7 @@ __le16 ieee80211_generic_frame_duration(struct ieee80211_hw *hw, erp = rate->flags & IEEE80211_RATE_ERP_G; } - dur = ieee80211_frame_duration(local, frame_len, rate->bitrate, erp, + dur = ieee80211_frame_duration(band, frame_len, rate->bitrate, erp, short_preamble); return cpu_to_le16(dur); @@ -198,7 +198,7 @@ __le16 ieee80211_rts_duration(struct ieee80211_hw *hw, u16 dur; struct ieee80211_supported_band *sband; - sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; + sband = local->hw.wiphy->bands[frame_txctl->band]; short_preamble = false; @@ -213,13 +213,13 @@ __le16 ieee80211_rts_duration(struct ieee80211_hw *hw, } /* CTS duration */ - dur = ieee80211_frame_duration(local, 10, rate->bitrate, + dur = ieee80211_frame_duration(sband->band, 10, rate->bitrate, erp, short_preamble); /* Data frame duration */ - dur += ieee80211_frame_duration(local, frame_len, rate->bitrate, + dur += ieee80211_frame_duration(sband->band, frame_len, rate->bitrate, erp, short_preamble); /* ACK duration */ - dur += ieee80211_frame_duration(local, 10, rate->bitrate, + dur += ieee80211_frame_duration(sband->band, 10, rate->bitrate, erp, short_preamble); return cpu_to_le16(dur); @@ -239,7 +239,7 @@ __le16 ieee80211_ctstoself_duration(struct ieee80211_hw *hw, u16 dur; struct ieee80211_supported_band *sband; - sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; + sband = local->hw.wiphy->bands[frame_txctl->band]; short_preamble = false; @@ -253,11 +253,11 @@ __le16 ieee80211_ctstoself_duration(struct ieee80211_hw *hw, } /* Data frame duration */ - dur = ieee80211_frame_duration(local, frame_len, rate->bitrate, + dur = ieee80211_frame_duration(sband->band, frame_len, rate->bitrate, erp, short_preamble); if (!(frame_txctl->flags & IEEE80211_TX_CTL_NO_ACK)) { /* ACK duration */ - dur += ieee80211_frame_duration(local, 10, rate->bitrate, + dur += ieee80211_frame_duration(sband->band, 10, rate->bitrate, erp, short_preamble); } @@ -265,17 +265,45 @@ __le16 ieee80211_ctstoself_duration(struct ieee80211_hw *hw, } EXPORT_SYMBOL(ieee80211_ctstoself_duration); +void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue) +{ + struct ieee80211_sub_if_data *sdata; + + list_for_each_entry_rcu(sdata, &local->interfaces, list) { + int ac; + + if (test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state)) + continue; + + if (sdata->vif.cab_queue != IEEE80211_INVAL_HW_QUEUE && + local->queue_stop_reasons[sdata->vif.cab_queue] != 0) + continue; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + int ac_queue = sdata->vif.hw_queue[ac]; + + if (ac_queue == queue || + (sdata->vif.cab_queue == queue && + local->queue_stop_reasons[ac_queue] == 0 && + skb_queue_empty(&local->pending[ac_queue]))) + netif_wake_subqueue(sdata->dev, ac); + } + } +} + static void __ieee80211_wake_queue(struct ieee80211_hw *hw, int queue, enum queue_stop_reason reason) { struct ieee80211_local *local = hw_to_local(hw); - struct ieee80211_sub_if_data *sdata; trace_wake_queue(local, queue, reason); if (WARN_ON(queue >= hw->queues)) return; + if (!test_bit(reason, &local->queue_stop_reasons[queue])) + return; + __clear_bit(reason, &local->queue_stop_reasons[queue]); if (local->queue_stop_reasons[queue] != 0) @@ -284,11 +312,7 @@ static void __ieee80211_wake_queue(struct ieee80211_hw *hw, int queue, if (skb_queue_empty(&local->pending[queue])) { rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, list) { - if (test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state)) - continue; - netif_wake_subqueue(sdata->dev, queue); - } + ieee80211_propagate_queue_wake(local, queue); rcu_read_unlock(); } else tasklet_schedule(&local->tx_pending_tasklet); @@ -323,11 +347,21 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue, if (WARN_ON(queue >= hw->queues)) return; + if (test_bit(reason, &local->queue_stop_reasons[queue])) + return; + __set_bit(reason, &local->queue_stop_reasons[queue]); rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, list) - netif_stop_subqueue(sdata->dev, queue); + list_for_each_entry_rcu(sdata, &local->interfaces, list) { + int ac; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + if (sdata->vif.hw_queue[ac] == queue || + sdata->vif.cab_queue == queue) + netif_stop_subqueue(sdata->dev, ac); + } + } rcu_read_unlock(); } @@ -354,8 +388,8 @@ void ieee80211_add_pending_skb(struct ieee80211_local *local, { struct ieee80211_hw *hw = &local->hw; unsigned long flags; - int queue = skb_get_queue_mapping(skb); struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + int queue = info->hw_queue; if (WARN_ON(!info->control.vif)) { kfree_skb(skb); @@ -379,10 +413,6 @@ void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local, int queue, i; spin_lock_irqsave(&local->queue_stop_reason_lock, flags); - for (i = 0; i < hw->queues; i++) - __ieee80211_stop_queue(hw, i, - IEEE80211_QUEUE_STOP_REASON_SKB_ADD); - while ((skb = skb_dequeue(skbs))) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); @@ -391,7 +421,11 @@ void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local, continue; } - queue = skb_get_queue_mapping(skb); + queue = info->hw_queue; + + __ieee80211_stop_queue(hw, queue, + IEEE80211_QUEUE_STOP_REASON_SKB_ADD); + __skb_queue_tail(&local->pending[queue], skb); } @@ -404,12 +438,6 @@ void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local, spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } -void ieee80211_add_pending_skbs(struct ieee80211_local *local, - struct sk_buff_head *skbs) -{ - ieee80211_add_pending_skbs_fn(local, skbs, NULL, NULL); -} - void ieee80211_stop_queues_by_reason(struct ieee80211_hw *hw, enum queue_stop_reason reason) { @@ -684,9 +712,9 @@ u32 ieee802_11_parse_elems_crc(u8 *start, size_t len, else elem_parse_failed = true; break; - case WLAN_EID_HT_INFORMATION: - if (elen >= sizeof(struct ieee80211_ht_info)) - elems->ht_info_elem = (void *)pos; + case WLAN_EID_HT_OPERATION: + if (elen >= sizeof(struct ieee80211_ht_operation)) + elems->ht_operation = (void *)pos; else elem_parse_failed = true; break; @@ -775,19 +803,22 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_queue_params qparam; - int queue; + int ac; bool use_11b; int aCWmin, aCWmax; if (!local->ops->conf_tx) return; + if (local->hw.queues < IEEE80211_NUM_ACS) + return; + memset(&qparam, 0, sizeof(qparam)); use_11b = (local->hw.conf.channel->band == IEEE80211_BAND_2GHZ) && !(sdata->flags & IEEE80211_SDATA_OPERATING_GMODE); - for (queue = 0; queue < local->hw.queues; queue++) { + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { /* Set defaults according to 802.11-2007 Table 7-37 */ aCWmax = 1023; if (use_11b) @@ -795,21 +826,21 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata, else aCWmin = 15; - switch (queue) { - case 3: /* AC_BK */ + switch (ac) { + case IEEE80211_AC_BK: qparam.cw_max = aCWmax; qparam.cw_min = aCWmin; qparam.txop = 0; qparam.aifs = 7; break; default: /* never happens but let's not leave undefined */ - case 2: /* AC_BE */ + case IEEE80211_AC_BE: qparam.cw_max = aCWmax; qparam.cw_min = aCWmin; qparam.txop = 0; qparam.aifs = 3; break; - case 1: /* AC_VI */ + case IEEE80211_AC_VI: qparam.cw_max = aCWmin; qparam.cw_min = (aCWmin + 1) / 2 - 1; if (use_11b) @@ -818,7 +849,7 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata, qparam.txop = 3008/32; qparam.aifs = 2; break; - case 0: /* AC_VO */ + case IEEE80211_AC_VO: qparam.cw_max = (aCWmin + 1) / 2 - 1; qparam.cw_min = (aCWmin + 1) / 4 - 1; if (use_11b) @@ -831,8 +862,8 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata, qparam.uapsd = false; - sdata->tx_conf[queue] = qparam; - drv_conf_tx(local, sdata, queue, &qparam); + sdata->tx_conf[ac] = qparam; + drv_conf_tx(local, sdata, ac, &qparam); } /* after reinitialize QoS TX queues setting to default, @@ -878,10 +909,8 @@ u32 ieee80211_mandatory_rates(struct ieee80211_local *local, int i; sband = local->hw.wiphy->bands[band]; - if (!sband) { - WARN_ON(1); - sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; - } + if (WARN_ON(!sband)) + return 1; if (band == IEEE80211_BAND_2GHZ) mandatory_flag = IEEE80211_RATE_MANDATORY_B; @@ -1106,7 +1135,7 @@ void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst, u32 ieee80211_sta_get_rates(struct ieee80211_local *local, struct ieee802_11_elems *elems, - enum ieee80211_band band) + enum ieee80211_band band, u32 *basic_rates) { struct ieee80211_supported_band *sband; struct ieee80211_rate *bitrates; @@ -1115,10 +1144,8 @@ u32 ieee80211_sta_get_rates(struct ieee80211_local *local, int i, j; sband = local->hw.wiphy->bands[band]; - if (!sband) { - WARN_ON(1); - sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; - } + if (WARN_ON(!sband)) + return 1; bitrates = sband->bitrates; num_rates = sband->n_bitrates; @@ -1127,15 +1154,25 @@ u32 ieee80211_sta_get_rates(struct ieee80211_local *local, elems->ext_supp_rates_len; i++) { u8 rate = 0; int own_rate; + bool is_basic; if (i < elems->supp_rates_len) rate = elems->supp_rates[i]; else if (elems->ext_supp_rates) rate = elems->ext_supp_rates [i - elems->supp_rates_len]; own_rate = 5 * (rate & 0x7f); - for (j = 0; j < num_rates; j++) - if (bitrates[j].bitrate == own_rate) + is_basic = !!(rate & 0x80); + + if (is_basic && (rate & 0x7f) == BSS_MEMBERSHIP_SELECTOR_HT_PHY) + continue; + + for (j = 0; j < num_rates; j++) { + if (bitrates[j].bitrate == own_rate) { supp_rates |= BIT(j); + if (basic_rates && is_basic) + *basic_rates |= BIT(j); + } + } } return supp_rates; } @@ -1210,6 +1247,16 @@ int ieee80211_reconfig(struct ieee80211_local *local) IEEE80211_TPT_LEDTRIG_FL_RADIO, 0); /* add interfaces */ + sdata = rtnl_dereference(local->monitor_sdata); + if (sdata) { + res = drv_add_interface(local, sdata); + if (WARN_ON(res)) { + rcu_assign_pointer(local->monitor_sdata, NULL); + synchronize_net(); + kfree(sdata); + } + } + list_for_each_entry(sdata, &local->interfaces, list) { if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN && sdata->vif.type != NL80211_IFTYPE_MONITOR && @@ -1232,14 +1279,17 @@ int ieee80211_reconfig(struct ieee80211_local *local) mutex_unlock(&local->sta_mtx); /* reconfigure tx conf */ - list_for_each_entry(sdata, &local->interfaces, list) { - if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN || - sdata->vif.type == NL80211_IFTYPE_MONITOR || - !ieee80211_sdata_running(sdata)) - continue; + if (hw->queues >= IEEE80211_NUM_ACS) { + list_for_each_entry(sdata, &local->interfaces, list) { + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN || + sdata->vif.type == NL80211_IFTYPE_MONITOR || + !ieee80211_sdata_running(sdata)) + continue; - for (i = 0; i < hw->queues; i++) - drv_conf_tx(local, sdata, i, &sdata->tx_conf[i]); + for (i = 0; i < IEEE80211_NUM_ACS; i++) + drv_conf_tx(local, sdata, i, + &sdata->tx_conf[i]); + } } /* reconfigure hardware */ @@ -1611,57 +1661,55 @@ u8 *ieee80211_ie_build_ht_cap(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, return pos; } -u8 *ieee80211_ie_build_ht_info(u8 *pos, - struct ieee80211_sta_ht_cap *ht_cap, +u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, struct ieee80211_channel *channel, - enum nl80211_channel_type channel_type) + enum nl80211_channel_type channel_type, + u16 prot_mode) { - struct ieee80211_ht_info *ht_info; + struct ieee80211_ht_operation *ht_oper; /* Build HT Information */ - *pos++ = WLAN_EID_HT_INFORMATION; - *pos++ = sizeof(struct ieee80211_ht_info); - ht_info = (struct ieee80211_ht_info *)pos; - ht_info->control_chan = + *pos++ = WLAN_EID_HT_OPERATION; + *pos++ = sizeof(struct ieee80211_ht_operation); + ht_oper = (struct ieee80211_ht_operation *)pos; + ht_oper->primary_chan = ieee80211_frequency_to_channel(channel->center_freq); switch (channel_type) { case NL80211_CHAN_HT40MINUS: - ht_info->ht_param = IEEE80211_HT_PARAM_CHA_SEC_BELOW; + ht_oper->ht_param = IEEE80211_HT_PARAM_CHA_SEC_BELOW; break; case NL80211_CHAN_HT40PLUS: - ht_info->ht_param = IEEE80211_HT_PARAM_CHA_SEC_ABOVE; + ht_oper->ht_param = IEEE80211_HT_PARAM_CHA_SEC_ABOVE; break; case NL80211_CHAN_HT20: default: - ht_info->ht_param = IEEE80211_HT_PARAM_CHA_SEC_NONE; + ht_oper->ht_param = IEEE80211_HT_PARAM_CHA_SEC_NONE; break; } - if (ht_cap->cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) - ht_info->ht_param |= IEEE80211_HT_PARAM_CHAN_WIDTH_ANY; + if (ht_cap->cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 && + channel_type != NL80211_CHAN_NO_HT && + channel_type != NL80211_CHAN_HT20) + ht_oper->ht_param |= IEEE80211_HT_PARAM_CHAN_WIDTH_ANY; - /* - * Note: According to 802.11n-2009 9.13.3.1, HT Protection field and - * RIFS Mode are reserved in IBSS mode, therefore keep them at 0 - */ - ht_info->operation_mode = 0x0000; - ht_info->stbc_param = 0x0000; + ht_oper->operation_mode = cpu_to_le16(prot_mode); + ht_oper->stbc_param = 0x0000; /* It seems that Basic MCS set and Supported MCS set are identical for the first 10 bytes */ - memset(&ht_info->basic_set, 0, 16); - memcpy(&ht_info->basic_set, &ht_cap->mcs, 10); + memset(&ht_oper->basic_set, 0, 16); + memcpy(&ht_oper->basic_set, &ht_cap->mcs, 10); - return pos + sizeof(struct ieee80211_ht_info); + return pos + sizeof(struct ieee80211_ht_operation); } enum nl80211_channel_type -ieee80211_ht_info_to_channel_type(struct ieee80211_ht_info *ht_info) +ieee80211_ht_oper_to_channel_type(struct ieee80211_ht_operation *ht_oper) { enum nl80211_channel_type channel_type; - if (!ht_info) + if (!ht_oper) return NL80211_CHAN_NO_HT; - switch (ht_info->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) { + switch (ht_oper->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) { case IEEE80211_HT_PARAM_CHA_SEC_NONE: channel_type = NL80211_CHAN_HT20; break; @@ -1678,13 +1726,15 @@ ieee80211_ht_info_to_channel_type(struct ieee80211_ht_info *ht_info) return channel_type; } -int ieee80211_add_srates_ie(struct ieee80211_vif *vif, struct sk_buff *skb) +int ieee80211_add_srates_ie(struct ieee80211_vif *vif, + struct sk_buff *skb, bool need_basic) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; int rate; u8 i, rates, *pos; + u32 basic_rates = vif->bss_conf.basic_rates; sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; rates = sband->n_bitrates; @@ -1698,20 +1748,25 @@ int ieee80211_add_srates_ie(struct ieee80211_vif *vif, struct sk_buff *skb) *pos++ = WLAN_EID_SUPP_RATES; *pos++ = rates; for (i = 0; i < rates; i++) { + u8 basic = 0; + if (need_basic && basic_rates & BIT(i)) + basic = 0x80; rate = sband->bitrates[i].bitrate; - *pos++ = (u8) (rate / 5); + *pos++ = basic | (u8) (rate / 5); } return 0; } -int ieee80211_add_ext_srates_ie(struct ieee80211_vif *vif, struct sk_buff *skb) +int ieee80211_add_ext_srates_ie(struct ieee80211_vif *vif, + struct sk_buff *skb, bool need_basic) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; int rate; u8 i, exrates, *pos; + u32 basic_rates = vif->bss_conf.basic_rates; sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; exrates = sband->n_bitrates; @@ -1728,9 +1783,25 @@ int ieee80211_add_ext_srates_ie(struct ieee80211_vif *vif, struct sk_buff *skb) *pos++ = WLAN_EID_EXT_SUPP_RATES; *pos++ = exrates; for (i = 8; i < sband->n_bitrates; i++) { + u8 basic = 0; + if (need_basic && basic_rates & BIT(i)) + basic = 0x80; rate = sband->bitrates[i].bitrate; - *pos++ = (u8) (rate / 5); + *pos++ = basic | (u8) (rate / 5); } } return 0; } + +int ieee80211_ave_rssi(struct ieee80211_vif *vif) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + + if (WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_STATION)) { + /* non-managed type inferfaces */ + return 0; + } + return ifmgd->ave_beacon_signal; +} +EXPORT_SYMBOL_GPL(ieee80211_ave_rssi); diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index 89511be3111..c3d643a6536 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -52,6 +52,26 @@ static int wme_downgrade_ac(struct sk_buff *skb) } } +static u16 ieee80211_downgrade_queue(struct ieee80211_local *local, + struct sk_buff *skb) +{ + /* in case we are a client verify acm is not set for this ac */ + while (unlikely(local->wmm_acm & BIT(skb->priority))) { + if (wme_downgrade_ac(skb)) { + /* + * This should not really happen. The AP has marked all + * lower ACs to require admission control which is not + * a reasonable configuration. Allow the frame to be + * transmitted using AC_BK as a workaround. + */ + break; + } + } + + /* look up which queue to use for frames with this 1d tag */ + return ieee802_1d_to_ac[skb->priority]; +} + /* Indicate which queue to use for this fully formed 802.11 frame */ u16 ieee80211_select_queue_80211(struct ieee80211_local *local, struct sk_buff *skb, @@ -59,7 +79,7 @@ u16 ieee80211_select_queue_80211(struct ieee80211_local *local, { u8 *p; - if (local->hw.queues < 4) + if (local->hw.queues < IEEE80211_NUM_ACS) return 0; if (!ieee80211_is_data(hdr->frame_control)) { @@ -86,9 +106,9 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, const u8 *ra = NULL; bool qos = false; - if (local->hw.queues < 4 || skb->len < 6) { + if (local->hw.queues < IEEE80211_NUM_ACS || skb->len < 6) { skb->priority = 0; /* required for correct WPA/11i MIC */ - return min_t(u16, local->hw.queues - 1, IEEE80211_AC_BE); + return 0; } rcu_read_lock(); @@ -139,26 +159,6 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, return ieee80211_downgrade_queue(local, skb); } -u16 ieee80211_downgrade_queue(struct ieee80211_local *local, - struct sk_buff *skb) -{ - /* in case we are a client verify acm is not set for this ac */ - while (unlikely(local->wmm_acm & BIT(skb->priority))) { - if (wme_downgrade_ac(skb)) { - /* - * This should not really happen. The AP has marked all - * lower ACs to require admission control which is not - * a reasonable configuration. Allow the frame to be - * transmitted using AC_BK as a workaround. - */ - break; - } - } - - /* look up which queue to use for frames with this 1d tag */ - return ieee802_1d_to_ac[skb->priority]; -} - void ieee80211_set_qos_hdr(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { diff --git a/net/mac80211/wme.h b/net/mac80211/wme.h index 94edceb617f..ca80818b7b6 100644 --- a/net/mac80211/wme.h +++ b/net/mac80211/wme.h @@ -22,8 +22,5 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); void ieee80211_set_qos_hdr(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); -u16 ieee80211_downgrade_queue(struct ieee80211_local *local, - struct sk_buff *skb); - #endif /* _WME_H */ diff --git a/net/mac80211/work.c b/net/mac80211/work.c index c6e230efa04..b2650a9d45f 100644 --- a/net/mac80211/work.c +++ b/net/mac80211/work.c @@ -122,9 +122,6 @@ static void ieee80211_work_work(struct work_struct *work) enum work_action rma; bool remain_off_channel = false; - if (local->scanning) - return; - /* * ieee80211_queue_work() should have picked up most cases, * here we'll pick the rest. @@ -134,6 +131,11 @@ static void ieee80211_work_work(struct work_struct *work) mutex_lock(&local->mtx); + if (local->scanning) { + mutex_unlock(&local->mtx); + return; + } + ieee80211_recalc_idle(local); list_for_each_entry_safe(wk, tmp, &local->work_list, list) { @@ -226,13 +228,8 @@ static void ieee80211_work_work(struct work_struct *work) run_again(local, jiffies + HZ/2); } - if (list_empty(&local->work_list) && local->scan_req && - !local->scanning) - ieee80211_queue_delayed_work(&local->hw, - &local->scan_work, - round_jiffies_relative(0)); - ieee80211_recalc_idle(local); + ieee80211_run_deferred_scan(local); mutex_unlock(&local->mtx); diff --git a/net/mac802154/Kconfig b/net/mac802154/Kconfig new file mode 100644 index 00000000000..a967ddaa4e2 --- /dev/null +++ b/net/mac802154/Kconfig @@ -0,0 +1,16 @@ +config MAC802154 + tristate "Generic IEEE 802.15.4 Soft Networking Stack (mac802154)" + depends on IEEE802154 && EXPERIMENTAL + select CRC_CCITT + ---help--- + This option enables the hardware independent IEEE 802.15.4 + networking stack for SoftMAC devices (the ones implementing + only PHY level of IEEE 802.15.4 standard). + + Note: this implementation is neither certified, nor feature + complete! Compatibility with other implementations hasn't + been tested yet! + + If you plan to use HardMAC IEEE 802.15.4 devices, you can + say N here. Alternatievly you can say M to compile it as + module. diff --git a/net/mac802154/Makefile b/net/mac802154/Makefile new file mode 100644 index 00000000000..ec1bd3fc127 --- /dev/null +++ b/net/mac802154/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_MAC802154) += mac802154.o +mac802154-objs := ieee802154_dev.o rx.o tx.o mac_cmd.o mib.o monitor.o diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c new file mode 100644 index 00000000000..e3edfb0661b --- /dev/null +++ b/net/mac802154/ieee802154_dev.c @@ -0,0 +1,294 @@ +/* + * Copyright (C) 2007-2012 Siemens AG + * + * Written by: + * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> + * + * Based on the code from 'linux-zigbee.sourceforge.net' project. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/netdevice.h> + +#include <net/netlink.h> +#include <linux/nl802154.h> +#include <net/mac802154.h> +#include <net/route.h> +#include <net/wpan-phy.h> + +#include "mac802154.h" + +int mac802154_slave_open(struct net_device *dev) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + struct mac802154_priv *ipriv = priv->hw; + int res = 0; + + if (ipriv->open_count++ == 0) { + res = ipriv->ops->start(&ipriv->hw); + WARN_ON(res); + if (res) + goto err; + } + + if (ipriv->ops->ieee_addr) { + res = ipriv->ops->ieee_addr(&ipriv->hw, dev->dev_addr); + WARN_ON(res); + if (res) + goto err; + mac802154_dev_set_ieee_addr(dev); + } + + netif_start_queue(dev); + return 0; +err: + priv->hw->open_count--; + + return res; +} + +int mac802154_slave_close(struct net_device *dev) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + struct mac802154_priv *ipriv = priv->hw; + + netif_stop_queue(dev); + + if (!--ipriv->open_count) + ipriv->ops->stop(&ipriv->hw); + + return 0; +} + +static int +mac802154_netdev_register(struct wpan_phy *phy, struct net_device *dev) +{ + struct mac802154_sub_if_data *priv; + struct mac802154_priv *ipriv; + int err; + + ipriv = wpan_phy_priv(phy); + + priv = netdev_priv(dev); + priv->dev = dev; + priv->hw = ipriv; + + dev->needed_headroom = ipriv->hw.extra_tx_headroom; + + SET_NETDEV_DEV(dev, &ipriv->phy->dev); + + mutex_lock(&ipriv->slaves_mtx); + if (!ipriv->running) { + mutex_unlock(&ipriv->slaves_mtx); + return -ENODEV; + } + mutex_unlock(&ipriv->slaves_mtx); + + err = register_netdev(dev); + if (err < 0) + return err; + + rtnl_lock(); + mutex_lock(&ipriv->slaves_mtx); + list_add_tail_rcu(&priv->list, &ipriv->slaves); + mutex_unlock(&ipriv->slaves_mtx); + rtnl_unlock(); + + return 0; +} + +static void +mac802154_del_iface(struct wpan_phy *phy, struct net_device *dev) +{ + struct mac802154_sub_if_data *sdata; + ASSERT_RTNL(); + + sdata = netdev_priv(dev); + + BUG_ON(sdata->hw->phy != phy); + + mutex_lock(&sdata->hw->slaves_mtx); + list_del_rcu(&sdata->list); + mutex_unlock(&sdata->hw->slaves_mtx); + + synchronize_rcu(); + unregister_netdevice(sdata->dev); +} + +static struct net_device * +mac802154_add_iface(struct wpan_phy *phy, const char *name, int type) +{ + struct net_device *dev; + int err = -ENOMEM; + + switch (type) { + case IEEE802154_DEV_MONITOR: + dev = alloc_netdev(sizeof(struct mac802154_sub_if_data), + name, mac802154_monitor_setup); + break; + default: + dev = NULL; + err = -EINVAL; + break; + } + if (!dev) + goto err; + + err = mac802154_netdev_register(phy, dev); + if (err) + goto err_free; + + dev_hold(dev); /* we return an incremented device refcount */ + return dev; + +err_free: + free_netdev(dev); +err: + return ERR_PTR(err); +} + +struct ieee802154_dev * +ieee802154_alloc_device(size_t priv_data_len, struct ieee802154_ops *ops) +{ + struct wpan_phy *phy; + struct mac802154_priv *priv; + size_t priv_size; + + if (!ops || !ops->xmit || !ops->ed || !ops->start || + !ops->stop || !ops->set_channel) { + printk(KERN_ERR + "undefined IEEE802.15.4 device operations\n"); + return NULL; + } + + /* Ensure 32-byte alignment of our private data and hw private data. + * We use the wpan_phy priv data for both our mac802154_priv and for + * the driver's private data + * + * in memory it'll be like this: + * + * +-----------------------+ + * | struct wpan_phy | + * +-----------------------+ + * | struct mac802154_priv | + * +-----------------------+ + * | driver's private data | + * +-----------------------+ + * + * Due to ieee802154 layer isn't aware of driver and MAC structures, + * so lets allign them here. + */ + + priv_size = ALIGN(sizeof(*priv), NETDEV_ALIGN) + priv_data_len; + + phy = wpan_phy_alloc(priv_size); + if (!phy) { + printk(KERN_ERR + "failure to allocate master IEEE802.15.4 device\n"); + return NULL; + } + + priv = wpan_phy_priv(phy); + priv->hw.phy = priv->phy = phy; + priv->hw.priv = (char *)priv + ALIGN(sizeof(*priv), NETDEV_ALIGN); + priv->ops = ops; + + INIT_LIST_HEAD(&priv->slaves); + mutex_init(&priv->slaves_mtx); + + return &priv->hw; +} +EXPORT_SYMBOL(ieee802154_alloc_device); + +void ieee802154_free_device(struct ieee802154_dev *hw) +{ + struct mac802154_priv *priv = mac802154_to_priv(hw); + + BUG_ON(!list_empty(&priv->slaves)); + + wpan_phy_free(priv->phy); + + mutex_destroy(&priv->slaves_mtx); +} +EXPORT_SYMBOL(ieee802154_free_device); + +int ieee802154_register_device(struct ieee802154_dev *dev) +{ + struct mac802154_priv *priv = mac802154_to_priv(dev); + int rc = -ENOMEM; + + priv->dev_workqueue = + create_singlethread_workqueue(wpan_phy_name(priv->phy)); + if (!priv->dev_workqueue) + goto out; + + wpan_phy_set_dev(priv->phy, priv->hw.parent); + + priv->phy->add_iface = mac802154_add_iface; + priv->phy->del_iface = mac802154_del_iface; + + rc = wpan_phy_register(priv->phy); + if (rc < 0) + goto out_wq; + + rtnl_lock(); + + mutex_lock(&priv->slaves_mtx); + priv->running = MAC802154_DEVICE_RUN; + mutex_unlock(&priv->slaves_mtx); + + rtnl_unlock(); + + return 0; + +out_wq: + destroy_workqueue(priv->dev_workqueue); +out: + return rc; +} +EXPORT_SYMBOL(ieee802154_register_device); + +void ieee802154_unregister_device(struct ieee802154_dev *dev) +{ + struct mac802154_priv *priv = mac802154_to_priv(dev); + struct mac802154_sub_if_data *sdata, *next; + + flush_workqueue(priv->dev_workqueue); + destroy_workqueue(priv->dev_workqueue); + + rtnl_lock(); + + mutex_lock(&priv->slaves_mtx); + priv->running = MAC802154_DEVICE_STOPPED; + mutex_unlock(&priv->slaves_mtx); + + list_for_each_entry_safe(sdata, next, &priv->slaves, list) { + mutex_lock(&sdata->hw->slaves_mtx); + list_del(&sdata->list); + mutex_unlock(&sdata->hw->slaves_mtx); + + unregister_netdevice(sdata->dev); + } + + rtnl_unlock(); + + wpan_phy_unregister(priv->phy); +} +EXPORT_SYMBOL(ieee802154_unregister_device); + +MODULE_DESCRIPTION("IEEE 802.15.4 implementation"); +MODULE_LICENSE("GPL v2"); diff --git a/net/mac802154/mac802154.h b/net/mac802154/mac802154.h new file mode 100644 index 00000000000..789d9c948ae --- /dev/null +++ b/net/mac802154/mac802154.h @@ -0,0 +1,109 @@ +/* + * Copyright (C) 2007-2012 Siemens AG + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * + * Written by: + * Pavel Smolenskiy <pavel.smolenskiy@gmail.com> + * Maxim Gorbachyov <maxim.gorbachev@siemens.com> + * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> + * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> + */ +#ifndef MAC802154_H +#define MAC802154_H + +/* mac802154 device private data */ +struct mac802154_priv { + struct ieee802154_dev hw; + struct ieee802154_ops *ops; + + /* ieee802154 phy */ + struct wpan_phy *phy; + + int open_count; + + /* As in mac80211 slaves list is modified: + * 1) under the RTNL + * 2) protected by slaves_mtx; + * 3) in an RCU manner + * + * So atomic readers can use any of this protection methods. + */ + struct list_head slaves; + struct mutex slaves_mtx; + + /* This one is used for scanning and other jobs not to be interfered + * with serial driver. + */ + struct workqueue_struct *dev_workqueue; + + /* SoftMAC device is registered and running. One can add subinterfaces. + * This flag should be modified under slaves_mtx and RTNL, so you can + * read them using any of protection methods. + */ + bool running; +}; + +#define MAC802154_DEVICE_STOPPED 0x00 +#define MAC802154_DEVICE_RUN 0x01 + +/* Slave interface definition. + * + * Slaves represent typical network interfaces available from userspace. + * Each ieee802154 device/transceiver may have several slaves and able + * to be associated with several networks at the same time. + */ +struct mac802154_sub_if_data { + struct list_head list; /* the ieee802154_priv->slaves list */ + + struct mac802154_priv *hw; + struct net_device *dev; + + int type; + + spinlock_t mib_lock; + + __le16 pan_id; + __le16 short_addr; + + u8 chan; + u8 page; + + /* MAC BSN field */ + u8 bsn; + /* MAC DSN field */ + u8 dsn; +}; + +#define mac802154_to_priv(_hw) container_of(_hw, struct mac802154_priv, hw) + +#define MAC802154_MAX_XMIT_ATTEMPTS 3 + +#define MAC802154_CHAN_NONE (~(u8)0) /* No channel is assigned */ + +extern struct ieee802154_reduced_mlme_ops mac802154_mlme_reduced; + +int mac802154_slave_open(struct net_device *dev); +int mac802154_slave_close(struct net_device *dev); + +void mac802154_monitors_rx(struct mac802154_priv *priv, struct sk_buff *skb); +void mac802154_monitor_setup(struct net_device *dev); + +netdev_tx_t mac802154_tx(struct mac802154_priv *priv, struct sk_buff *skb, + u8 page, u8 chan); + +/* MIB callbacks */ +void mac802154_dev_set_ieee_addr(struct net_device *dev); + +#endif /* MAC802154_H */ diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c new file mode 100644 index 00000000000..7a5d0e052cd --- /dev/null +++ b/net/mac802154/mac_cmd.c @@ -0,0 +1,45 @@ +/* + * MAC commands interface + * + * Copyright 2007-2012 Siemens AG + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * + * Written by: + * Sergey Lapin <slapin@ossfans.org> + * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> + * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> + */ + +#include <linux/skbuff.h> +#include <linux/if_arp.h> + +#include <net/ieee802154_netdev.h> +#include <net/wpan-phy.h> +#include <net/mac802154.h> + +#include "mac802154.h" + +struct wpan_phy *mac802154_get_phy(const struct net_device *dev) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + return to_phy(get_device(&priv->hw->phy->dev)); +} + +struct ieee802154_reduced_mlme_ops mac802154_mlme_reduced = { + .get_phy = mac802154_get_phy, +}; diff --git a/net/mac802154/mib.c b/net/mac802154/mib.c new file mode 100644 index 00000000000..ab59821ec72 --- /dev/null +++ b/net/mac802154/mib.c @@ -0,0 +1,93 @@ +/* + * Copyright 2007-2012 Siemens AG + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * + * Written by: + * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> + * Sergey Lapin <slapin@ossfans.org> + * Maxim Gorbachyov <maxim.gorbachev@siemens.com> + * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> + */ + +#include <linux/if_arp.h> + +#include <net/mac802154.h> +#include <net/wpan-phy.h> + +#include "mac802154.h" + +struct hw_addr_filt_notify_work { + struct work_struct work; + struct net_device *dev; + unsigned long changed; +}; + +struct mac802154_priv *mac802154_slave_get_priv(struct net_device *dev) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + return priv->hw; +} + +static void hw_addr_notify(struct work_struct *work) +{ + struct hw_addr_filt_notify_work *nw = container_of(work, + struct hw_addr_filt_notify_work, work); + struct mac802154_priv *hw = mac802154_slave_get_priv(nw->dev); + int res; + + res = hw->ops->set_hw_addr_filt(&hw->hw, + &hw->hw.hw_filt, + nw->changed); + if (res) + pr_debug("failed changed mask %lx\n", nw->changed); + + kfree(nw); + + return; +} + +static void set_hw_addr_filt(struct net_device *dev, unsigned long changed) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + struct hw_addr_filt_notify_work *work; + + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) + return; + + INIT_WORK(&work->work, hw_addr_notify); + work->dev = dev; + work->changed = changed; + queue_work(priv->hw->dev_workqueue, &work->work); + + return; +} + +void mac802154_dev_set_ieee_addr(struct net_device *dev) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + struct mac802154_priv *mac = priv->hw; + + if (mac->ops->set_hw_addr_filt && + memcmp(mac->hw.hw_filt.ieee_addr, + dev->dev_addr, IEEE802154_ADDR_LEN)) { + memcpy(mac->hw.hw_filt.ieee_addr, + dev->dev_addr, IEEE802154_ADDR_LEN); + set_hw_addr_filt(dev, IEEE802515_AFILT_IEEEADDR_CHANGED); + } +} diff --git a/net/mac802154/monitor.c b/net/mac802154/monitor.c new file mode 100644 index 00000000000..434a26f76a8 --- /dev/null +++ b/net/mac802154/monitor.c @@ -0,0 +1,116 @@ +/* + * Copyright 2007, 2008, 2009 Siemens AG + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * + * Written by: + * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> + * Sergey Lapin <slapin@ossfans.org> + * Maxim Gorbachyov <maxim.gorbachev@siemens.com> + * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> + */ + +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <linux/if_arp.h> +#include <linux/crc-ccitt.h> + +#include <net/ieee802154.h> +#include <net/mac802154.h> +#include <net/netlink.h> +#include <net/wpan-phy.h> +#include <linux/nl802154.h> + +#include "mac802154.h" + +static netdev_tx_t mac802154_monitor_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct mac802154_sub_if_data *priv; + u8 chan, page; + + priv = netdev_priv(dev); + + /* FIXME: locking */ + chan = priv->hw->phy->current_channel; + page = priv->hw->phy->current_page; + + if (chan == MAC802154_CHAN_NONE) /* not initialized */ + return NETDEV_TX_OK; + + if (WARN_ON(page >= WPAN_NUM_PAGES) || + WARN_ON(chan >= WPAN_NUM_CHANNELS)) + return NETDEV_TX_OK; + + skb->skb_iif = dev->ifindex; + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; + + return mac802154_tx(priv->hw, skb, page, chan); +} + + +void mac802154_monitors_rx(struct mac802154_priv *priv, struct sk_buff *skb) +{ + struct sk_buff *skb2; + struct mac802154_sub_if_data *sdata; + u16 crc = crc_ccitt(0, skb->data, skb->len); + u8 *data; + + rcu_read_lock(); + list_for_each_entry_rcu(sdata, &priv->slaves, list) { + if (sdata->type != IEEE802154_DEV_MONITOR) + continue; + + skb2 = skb_clone(skb, GFP_ATOMIC); + skb2->dev = sdata->dev; + skb2->pkt_type = PACKET_HOST; + data = skb_put(skb2, 2); + data[0] = crc & 0xff; + data[1] = crc >> 8; + + netif_rx_ni(skb2); + } + rcu_read_unlock(); +} + +static const struct net_device_ops mac802154_monitor_ops = { + .ndo_open = mac802154_slave_open, + .ndo_stop = mac802154_slave_close, + .ndo_start_xmit = mac802154_monitor_xmit, +}; + +void mac802154_monitor_setup(struct net_device *dev) +{ + struct mac802154_sub_if_data *priv; + + dev->addr_len = 0; + dev->hard_header_len = 0; + dev->needed_tailroom = 2; /* room for FCS */ + dev->mtu = IEEE802154_MTU; + dev->tx_queue_len = 10; + dev->type = ARPHRD_IEEE802154_MONITOR; + dev->flags = IFF_NOARP | IFF_BROADCAST; + dev->watchdog_timeo = 0; + + dev->destructor = free_netdev; + dev->netdev_ops = &mac802154_monitor_ops; + dev->ml_priv = &mac802154_mlme_reduced; + + priv = netdev_priv(dev); + priv->type = IEEE802154_DEV_MONITOR; + + priv->chan = MAC802154_CHAN_NONE; /* not initialized */ + priv->page = 0; +} diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c new file mode 100644 index 00000000000..4a7d76d4f8b --- /dev/null +++ b/net/mac802154/rx.c @@ -0,0 +1,114 @@ +/* + * Copyright (C) 2007-2012 Siemens AG + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * + * Written by: + * Pavel Smolenskiy <pavel.smolenskiy@gmail.com> + * Maxim Gorbachyov <maxim.gorbachev@siemens.com> + * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> + * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/workqueue.h> +#include <linux/netdevice.h> +#include <linux/crc-ccitt.h> + +#include <net/mac802154.h> +#include <net/ieee802154_netdev.h> + +#include "mac802154.h" + +/* The IEEE 802.15.4 standard defines 4 MAC packet types: + * - beacon frame + * - MAC command frame + * - acknowledgement frame + * - data frame + * + * and only the data frame should be pushed to the upper layers, other types + * are just internal MAC layer management information. So only data packets + * are going to be sent to the networking queue, all other will be processed + * right here by using the device workqueue. + */ +struct rx_work { + struct sk_buff *skb; + struct work_struct work; + struct ieee802154_dev *dev; + u8 lqi; +}; + +static void +mac802154_subif_rx(struct ieee802154_dev *hw, struct sk_buff *skb, u8 lqi) +{ + struct mac802154_priv *priv = mac802154_to_priv(hw); + + mac_cb(skb)->lqi = lqi; + skb->protocol = htons(ETH_P_IEEE802154); + skb_reset_mac_header(skb); + + BUILD_BUG_ON(sizeof(struct ieee802154_mac_cb) > sizeof(skb->cb)); + + if (!(priv->hw.flags & IEEE802154_HW_OMIT_CKSUM)) { + u16 crc; + + if (skb->len < 2) { + pr_debug("got invalid frame\n"); + goto out; + } + crc = crc_ccitt(0, skb->data, skb->len); + if (crc) { + pr_debug("CRC mismatch\n"); + goto out; + } + skb_trim(skb, skb->len - 2); /* CRC */ + } + + mac802154_monitors_rx(priv, skb); +out: + dev_kfree_skb(skb); + return; +} + +static void mac802154_rx_worker(struct work_struct *work) +{ + struct rx_work *rw = container_of(work, struct rx_work, work); + struct sk_buff *skb = rw->skb; + + mac802154_subif_rx(rw->dev, skb, rw->lqi); + kfree(rw); +} + +void +ieee802154_rx_irqsafe(struct ieee802154_dev *dev, struct sk_buff *skb, u8 lqi) +{ + struct mac802154_priv *priv = mac802154_to_priv(dev); + struct rx_work *work; + + if (!skb) + return; + + work = kzalloc(sizeof(struct rx_work), GFP_ATOMIC); + if (!work) + return; + + INIT_WORK(&work->work, mac802154_rx_worker); + work->skb = skb; + work->dev = dev; + work->lqi = lqi; + + queue_work(priv->dev_workqueue, &work->work); +} +EXPORT_SYMBOL(ieee802154_rx_irqsafe); diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c new file mode 100644 index 00000000000..8781d8f904d --- /dev/null +++ b/net/mac802154/tx.c @@ -0,0 +1,116 @@ +/* + * Copyright 2007-2012 Siemens AG + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * + * Written by: + * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> + * Sergey Lapin <slapin@ossfans.org> + * Maxim Gorbachyov <maxim.gorbachev@siemens.com> + * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> + */ + +#include <linux/netdevice.h> +#include <linux/if_arp.h> +#include <linux/crc-ccitt.h> + +#include <net/mac802154.h> +#include <net/wpan-phy.h> + +#include "mac802154.h" + +/* IEEE 802.15.4 transceivers can sleep during the xmit session, so process + * packets through the workqueue. + */ +struct xmit_work { + struct sk_buff *skb; + struct work_struct work; + struct mac802154_priv *priv; + u8 chan; + u8 page; + u8 xmit_attempts; +}; + +static void mac802154_xmit_worker(struct work_struct *work) +{ + struct xmit_work *xw = container_of(work, struct xmit_work, work); + int res; + + mutex_lock(&xw->priv->phy->pib_lock); + if (xw->priv->phy->current_channel != xw->chan || + xw->priv->phy->current_page != xw->page) { + res = xw->priv->ops->set_channel(&xw->priv->hw, + xw->page, + xw->chan); + if (res) { + pr_debug("set_channel failed\n"); + goto out; + } + } + + res = xw->priv->ops->xmit(&xw->priv->hw, xw->skb); + +out: + mutex_unlock(&xw->priv->phy->pib_lock); + + if (res) { + if (xw->xmit_attempts++ < MAC802154_MAX_XMIT_ATTEMPTS) { + queue_work(xw->priv->dev_workqueue, &xw->work); + return; + } else + pr_debug("transmission failed for %d times", + MAC802154_MAX_XMIT_ATTEMPTS); + } + + dev_kfree_skb(xw->skb); + + kfree(xw); +} + +netdev_tx_t mac802154_tx(struct mac802154_priv *priv, struct sk_buff *skb, + u8 page, u8 chan) +{ + struct xmit_work *work; + + if (!(priv->phy->channels_supported[page] & (1 << chan))) + WARN_ON(1); + return NETDEV_TX_OK; + + if (!(priv->hw.flags & IEEE802154_HW_OMIT_CKSUM)) { + u16 crc = crc_ccitt(0, skb->data, skb->len); + u8 *data = skb_put(skb, 2); + data[0] = crc & 0xff; + data[1] = crc >> 8; + } + + if (skb_cow_head(skb, priv->hw.extra_tx_headroom)) { + dev_kfree_skb(skb); + return NETDEV_TX_OK; + } + + work = kzalloc(sizeof(struct xmit_work), GFP_ATOMIC); + if (!work) + return NETDEV_TX_BUSY; + + INIT_WORK(&work->work, mac802154_xmit_worker); + work->skb = skb; + work->priv = priv; + work->page = page; + work->chan = chan; + work->xmit_attempts = 0; + + queue_work(priv->dev_workqueue, &work->work); + + return NETDEV_TX_OK; +} diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 0c6f67e8f2e..209c1ed4336 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -509,6 +509,21 @@ config NETFILTER_XT_TARGET_HL since you can easily create immortal packets that loop forever on the network. +config NETFILTER_XT_TARGET_HMARK + tristate '"HMARK" target support' + depends on (IP6_NF_IPTABLES || IP6_NF_IPTABLES=n) + depends on NETFILTER_ADVANCED + ---help--- + This option adds the "HMARK" target. + + The target allows you to create rules in the "raw" and "mangle" tables + which set the skbuff mark by means of hash calculation within a given + range. The nfmark can influence the routing method (see "Use netfilter + MARK value as routing key") and can also be used by other subsystems to + change their behaviour. + + To compile it as a module, choose M here. If unsure, say N. + config NETFILTER_XT_TARGET_IDLETIMER tristate "IDLETIMER target support" depends on NETFILTER_ADVANCED diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index ca3676586f5..4e7960cc7b9 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -59,6 +59,7 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_CONNSECMARK) += xt_CONNSECMARK.o obj-$(CONFIG_NETFILTER_XT_TARGET_CT) += xt_CT.o obj-$(CONFIG_NETFILTER_XT_TARGET_DSCP) += xt_DSCP.o obj-$(CONFIG_NETFILTER_XT_TARGET_HL) += xt_HL.o +obj-$(CONFIG_NETFILTER_XT_TARGET_HMARK) += xt_HMARK.o obj-$(CONFIG_NETFILTER_XT_TARGET_LED) += xt_LED.o obj-$(CONFIG_NETFILTER_XT_TARGET_LOG) += xt_LOG.o obj-$(CONFIG_NETFILTER_XT_TARGET_NFLOG) += xt_NFLOG.o diff --git a/net/netfilter/core.c b/net/netfilter/core.c index e1b7e051332..e19f3653db2 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -290,12 +290,3 @@ void __init netfilter_init(void) if (netfilter_log_init() < 0) panic("cannot initialize nf_log"); } - -#ifdef CONFIG_SYSCTL -struct ctl_path nf_net_netfilter_sysctl_path[] = { - { .procname = "net", }, - { .procname = "netfilter", }, - { } -}; -EXPORT_SYMBOL_GPL(nf_net_netfilter_sysctl_path); -#endif /* CONFIG_SYSCTL */ diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index a72a4dff003..7e1b061aeeb 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -109,8 +109,9 @@ bitmap_ip_list(const struct ip_set *set, } else goto nla_put_failure; } - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, - htonl(map->first_ip + id * map->hosts)); + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, + htonl(map->first_ip + id * map->hosts))) + goto nla_put_failure; ipset_nest_end(skb, nested); } ipset_nest_end(skb, atd); @@ -194,10 +195,11 @@ bitmap_ip_tlist(const struct ip_set *set, } else goto nla_put_failure; } - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, - htonl(map->first_ip + id * map->hosts)); - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, - htonl(ip_set_timeout_get(members[id]))); + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, + htonl(map->first_ip + id * map->hosts)) || + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(members[id])))) + goto nla_put_failure; ipset_nest_end(skb, nested); } ipset_nest_end(skb, adt); @@ -334,15 +336,16 @@ bitmap_ip_head(struct ip_set *set, struct sk_buff *skb) nested = ipset_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, htonl(map->first_ip)); - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip)); - if (map->netmask != 32) - NLA_PUT_U8(skb, IPSET_ATTR_NETMASK, map->netmask); - NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)); - NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, - htonl(sizeof(*map) + map->memsize)); - if (with_timeout(map->timeout)) - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout)); + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, htonl(map->first_ip)) || + nla_put_ipaddr4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip)) || + (map->netmask != 32 && + nla_put_u8(skb, IPSET_ATTR_NETMASK, map->netmask)) || + nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) || + nla_put_net32(skb, IPSET_ATTR_MEMSIZE, + htonl(sizeof(*map) + map->memsize)) || + (with_timeout(map->timeout) && + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout)))) + goto nla_put_failure; ipset_nest_end(skb, nested); return 0; diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 81324c12c5b..d7eaf10edb6 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -111,7 +111,7 @@ bitmap_ipmac_test(struct ip_set *set, void *value, u32 timeout, u32 flags) return -EAGAIN; case MAC_FILLED: return data->ether == NULL || - compare_ether_addr(data->ether, elem->ether) == 0; + ether_addr_equal(data->ether, elem->ether); } return 0; } @@ -186,11 +186,12 @@ bitmap_ipmac_list(const struct ip_set *set, } else goto nla_put_failure; } - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, - htonl(map->first_ip + id)); - if (elem->match == MAC_FILLED) - NLA_PUT(skb, IPSET_ATTR_ETHER, ETH_ALEN, - elem->ether); + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, + htonl(map->first_ip + id)) || + (elem->match == MAC_FILLED && + nla_put(skb, IPSET_ATTR_ETHER, ETH_ALEN, + elem->ether))) + goto nla_put_failure; ipset_nest_end(skb, nested); } ipset_nest_end(skb, atd); @@ -224,7 +225,7 @@ bitmap_ipmac_ttest(struct ip_set *set, void *value, u32 timeout, u32 flags) return -EAGAIN; case MAC_FILLED: return (data->ether == NULL || - compare_ether_addr(data->ether, elem->ether) == 0) && + ether_addr_equal(data->ether, elem->ether)) && !bitmap_expired(map, data->id); } return 0; @@ -314,14 +315,16 @@ bitmap_ipmac_tlist(const struct ip_set *set, } else goto nla_put_failure; } - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, - htonl(map->first_ip + id)); - if (elem->match == MAC_FILLED) - NLA_PUT(skb, IPSET_ATTR_ETHER, ETH_ALEN, - elem->ether); + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, + htonl(map->first_ip + id)) || + (elem->match == MAC_FILLED && + nla_put(skb, IPSET_ATTR_ETHER, ETH_ALEN, + elem->ether))) + goto nla_put_failure; timeout = elem->match == MAC_UNSET ? elem->timeout : ip_set_timeout_get(elem->timeout); - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(timeout)); + if (nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(timeout))) + goto nla_put_failure; ipset_nest_end(skb, nested); } ipset_nest_end(skb, atd); @@ -438,14 +441,16 @@ bitmap_ipmac_head(struct ip_set *set, struct sk_buff *skb) nested = ipset_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, htonl(map->first_ip)); - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip)); - NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)); - NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, - htonl(sizeof(*map) - + (map->last_ip - map->first_ip + 1) * map->dsize)); - if (with_timeout(map->timeout)) - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout)); + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, htonl(map->first_ip)) || + nla_put_ipaddr4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip)) || + nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) || + nla_put_net32(skb, IPSET_ATTR_MEMSIZE, + htonl(sizeof(*map) + + ((map->last_ip - map->first_ip + 1) * + map->dsize))) || + (with_timeout(map->timeout) && + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout)))) + goto nla_put_failure; ipset_nest_end(skb, nested); return 0; diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index 382ec28ba72..b9f1fce7053 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -96,8 +96,9 @@ bitmap_port_list(const struct ip_set *set, } else goto nla_put_failure; } - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, - htons(map->first_port + id)); + if (nla_put_net16(skb, IPSET_ATTR_PORT, + htons(map->first_port + id))) + goto nla_put_failure; ipset_nest_end(skb, nested); } ipset_nest_end(skb, atd); @@ -183,10 +184,11 @@ bitmap_port_tlist(const struct ip_set *set, } else goto nla_put_failure; } - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, - htons(map->first_port + id)); - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, - htonl(ip_set_timeout_get(members[id]))); + if (nla_put_net16(skb, IPSET_ATTR_PORT, + htons(map->first_port + id)) || + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(members[id])))) + goto nla_put_failure; ipset_nest_end(skb, nested); } ipset_nest_end(skb, adt); @@ -320,13 +322,14 @@ bitmap_port_head(struct ip_set *set, struct sk_buff *skb) nested = ipset_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, htons(map->first_port)); - NLA_PUT_NET16(skb, IPSET_ATTR_PORT_TO, htons(map->last_port)); - NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)); - NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, - htonl(sizeof(*map) + map->memsize)); - if (with_timeout(map->timeout)) - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout)); + if (nla_put_net16(skb, IPSET_ATTR_PORT, htons(map->first_port)) || + nla_put_net16(skb, IPSET_ATTR_PORT_TO, htons(map->last_port)) || + nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) || + nla_put_net32(skb, IPSET_ATTR_MEMSIZE, + htonl(sizeof(*map) + map->memsize)) || + (with_timeout(map->timeout) && + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout)))) + goto nla_put_failure; ipset_nest_end(skb, nested); return 0; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index e6c1c9605a5..819c342f5b3 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1092,19 +1092,21 @@ dump_last: ret = -EMSGSIZE; goto release_refcount; } - NLA_PUT_U8(skb, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL); - NLA_PUT_STRING(skb, IPSET_ATTR_SETNAME, set->name); + if (nla_put_u8(skb, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL) || + nla_put_string(skb, IPSET_ATTR_SETNAME, set->name)) + goto nla_put_failure; if (dump_flags & IPSET_FLAG_LIST_SETNAME) goto next_set; switch (cb->args[2]) { case 0: /* Core header data */ - NLA_PUT_STRING(skb, IPSET_ATTR_TYPENAME, - set->type->name); - NLA_PUT_U8(skb, IPSET_ATTR_FAMILY, - set->family); - NLA_PUT_U8(skb, IPSET_ATTR_REVISION, - set->revision); + if (nla_put_string(skb, IPSET_ATTR_TYPENAME, + set->type->name) || + nla_put_u8(skb, IPSET_ATTR_FAMILY, + set->family) || + nla_put_u8(skb, IPSET_ATTR_REVISION, + set->revision)) + goto nla_put_failure; ret = set->variant->head(set, skb); if (ret < 0) goto release_refcount; @@ -1410,11 +1412,12 @@ ip_set_header(struct sock *ctnl, struct sk_buff *skb, IPSET_CMD_HEADER); if (!nlh2) goto nlmsg_failure; - NLA_PUT_U8(skb2, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL); - NLA_PUT_STRING(skb2, IPSET_ATTR_SETNAME, set->name); - NLA_PUT_STRING(skb2, IPSET_ATTR_TYPENAME, set->type->name); - NLA_PUT_U8(skb2, IPSET_ATTR_FAMILY, set->family); - NLA_PUT_U8(skb2, IPSET_ATTR_REVISION, set->revision); + if (nla_put_u8(skb2, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL) || + nla_put_string(skb2, IPSET_ATTR_SETNAME, set->name) || + nla_put_string(skb2, IPSET_ATTR_TYPENAME, set->type->name) || + nla_put_u8(skb2, IPSET_ATTR_FAMILY, set->family) || + nla_put_u8(skb2, IPSET_ATTR_REVISION, set->revision)) + goto nla_put_failure; nlmsg_end(skb2, nlh2); ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); @@ -1469,11 +1472,12 @@ ip_set_type(struct sock *ctnl, struct sk_buff *skb, IPSET_CMD_TYPE); if (!nlh2) goto nlmsg_failure; - NLA_PUT_U8(skb2, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL); - NLA_PUT_STRING(skb2, IPSET_ATTR_TYPENAME, typename); - NLA_PUT_U8(skb2, IPSET_ATTR_FAMILY, family); - NLA_PUT_U8(skb2, IPSET_ATTR_REVISION, max); - NLA_PUT_U8(skb2, IPSET_ATTR_REVISION_MIN, min); + if (nla_put_u8(skb2, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL) || + nla_put_string(skb2, IPSET_ATTR_TYPENAME, typename) || + nla_put_u8(skb2, IPSET_ATTR_FAMILY, family) || + nla_put_u8(skb2, IPSET_ATTR_REVISION, max) || + nla_put_u8(skb2, IPSET_ATTR_REVISION_MIN, min)) + goto nla_put_failure; nlmsg_end(skb2, nlh2); pr_debug("Send TYPE, nlmsg_len: %u\n", nlh2->nlmsg_len); @@ -1517,7 +1521,8 @@ ip_set_protocol(struct sock *ctnl, struct sk_buff *skb, IPSET_CMD_PROTOCOL); if (!nlh2) goto nlmsg_failure; - NLA_PUT_U8(skb2, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL); + if (nla_put_u8(skb2, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL)) + goto nla_put_failure; nlmsg_end(skb2, nlh2); ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); @@ -1613,7 +1618,7 @@ static struct nfnetlink_subsystem ip_set_netlink_subsys __read_mostly = { static int ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) { - unsigned *op; + unsigned int *op; void *data; int copylen = *len, ret = 0; @@ -1621,7 +1626,7 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) return -EPERM; if (optval != SO_IP_SET) return -EBADF; - if (*len < sizeof(unsigned)) + if (*len < sizeof(unsigned int)) return -EINVAL; data = vmalloc(*len); @@ -1631,7 +1636,7 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) ret = -EFAULT; goto done; } - op = (unsigned *) data; + op = (unsigned int *) data; if (*op < IP_SET_OP_VERSION) { /* Check the version at the beginning of operations */ diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index 5139dea6019..a68dbd4f1e4 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -81,7 +81,8 @@ hash_ip4_data_zero_out(struct hash_ip4_elem *elem) static inline bool hash_ip4_data_list(struct sk_buff *skb, const struct hash_ip4_elem *data) { - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip)) + goto nla_put_failure; return 0; nla_put_failure: @@ -94,9 +95,10 @@ hash_ip4_data_tlist(struct sk_buff *skb, const struct hash_ip4_elem *data) const struct hash_ip4_telem *tdata = (const struct hash_ip4_telem *)data; - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, tdata->ip); - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, - htonl(ip_set_timeout_get(tdata->timeout))); + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, tdata->ip) || + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(tdata->timeout)))) + goto nla_put_failure; return 0; @@ -262,7 +264,8 @@ ip6_netmask(union nf_inet_addr *ip, u8 prefix) static bool hash_ip6_data_list(struct sk_buff *skb, const struct hash_ip6_elem *data) { - NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip); + if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6)) + goto nla_put_failure; return 0; nla_put_failure: @@ -275,9 +278,10 @@ hash_ip6_data_tlist(struct sk_buff *skb, const struct hash_ip6_elem *data) const struct hash_ip6_telem *e = (const struct hash_ip6_telem *)data; - NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip); - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, - htonl(ip_set_timeout_get(e->timeout))); + if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &e->ip.in6) || + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(e->timeout)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -364,6 +368,7 @@ hash_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags) { u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; u8 netmask, hbits; + size_t hsize; struct ip_set_hash *h; if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6)) @@ -405,9 +410,12 @@ hash_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags) h->timeout = IPSET_NO_TIMEOUT; hbits = htable_bits(hashsize); - h->table = ip_set_alloc( - sizeof(struct htable) - + jhash_size(hbits) * sizeof(struct hbucket)); + hsize = htable_size(hbits); + if (hsize == 0) { + kfree(h); + return -ENOMEM; + } + h->table = ip_set_alloc(hsize); if (!h->table) { kfree(h); return -ENOMEM; diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 9c27e249c17..92722bb82ee 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -93,9 +93,10 @@ static bool hash_ipport4_data_list(struct sk_buff *skb, const struct hash_ipport4_elem *data) { - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); - NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || + nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || + nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) + goto nla_put_failure; return 0; nla_put_failure: @@ -109,12 +110,12 @@ hash_ipport4_data_tlist(struct sk_buff *skb, const struct hash_ipport4_telem *tdata = (const struct hash_ipport4_telem *)data; - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, tdata->ip); - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, tdata->port); - NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, - htonl(ip_set_timeout_get(tdata->timeout))); - + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, tdata->ip) || + nla_put_net16(skb, IPSET_ATTR_PORT, tdata->port) || + nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(tdata->timeout)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -308,9 +309,10 @@ static bool hash_ipport6_data_list(struct sk_buff *skb, const struct hash_ipport6_elem *data) { - NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip); - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); - NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) || + nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || + nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) + goto nla_put_failure; return 0; nla_put_failure: @@ -324,11 +326,12 @@ hash_ipport6_data_tlist(struct sk_buff *skb, const struct hash_ipport6_telem *e = (const struct hash_ipport6_telem *)data; - NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip); - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); - NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, - htonl(ip_set_timeout_get(e->timeout))); + if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &e->ip.in6) || + nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || + nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(e->timeout)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -449,6 +452,7 @@ hash_ipport_create(struct ip_set *set, struct nlattr *tb[], u32 flags) struct ip_set_hash *h; u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; u8 hbits; + size_t hsize; if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6)) return -IPSET_ERR_INVALID_FAMILY; @@ -476,9 +480,12 @@ hash_ipport_create(struct ip_set *set, struct nlattr *tb[], u32 flags) h->timeout = IPSET_NO_TIMEOUT; hbits = htable_bits(hashsize); - h->table = ip_set_alloc( - sizeof(struct htable) - + jhash_size(hbits) * sizeof(struct hbucket)); + hsize = htable_size(hbits); + if (hsize == 0) { + kfree(h); + return -ENOMEM; + } + h->table = ip_set_alloc(hsize); if (!h->table) { kfree(h); return -ENOMEM; diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index 9134057c072..0637ce096de 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -94,10 +94,11 @@ static bool hash_ipportip4_data_list(struct sk_buff *skb, const struct hash_ipportip4_elem *data) { - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP2, data->ip2); - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); - NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || + nla_put_ipaddr4(skb, IPSET_ATTR_IP2, data->ip2) || + nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || + nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) + goto nla_put_failure; return 0; nla_put_failure: @@ -111,13 +112,13 @@ hash_ipportip4_data_tlist(struct sk_buff *skb, const struct hash_ipportip4_telem *tdata = (const struct hash_ipportip4_telem *)data; - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, tdata->ip); - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP2, tdata->ip2); - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, tdata->port); - NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, - htonl(ip_set_timeout_get(tdata->timeout))); - + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, tdata->ip) || + nla_put_ipaddr4(skb, IPSET_ATTR_IP2, tdata->ip2) || + nla_put_net16(skb, IPSET_ATTR_PORT, tdata->port) || + nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(tdata->timeout)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -319,10 +320,11 @@ static bool hash_ipportip6_data_list(struct sk_buff *skb, const struct hash_ipportip6_elem *data) { - NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip); - NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP2, &data->ip2); - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); - NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) || + nla_put_ipaddr6(skb, IPSET_ATTR_IP2, &data->ip2.in6) || + nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || + nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) + goto nla_put_failure; return 0; nla_put_failure: @@ -336,12 +338,13 @@ hash_ipportip6_data_tlist(struct sk_buff *skb, const struct hash_ipportip6_telem *e = (const struct hash_ipportip6_telem *)data; - NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip); - NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP2, &data->ip2); - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); - NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, - htonl(ip_set_timeout_get(e->timeout))); + if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &e->ip.in6) || + nla_put_ipaddr6(skb, IPSET_ATTR_IP2, &data->ip2.in6) || + nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || + nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(e->timeout)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -467,6 +470,7 @@ hash_ipportip_create(struct ip_set *set, struct nlattr *tb[], u32 flags) struct ip_set_hash *h; u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; u8 hbits; + size_t hsize; if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6)) return -IPSET_ERR_INVALID_FAMILY; @@ -494,9 +498,12 @@ hash_ipportip_create(struct ip_set *set, struct nlattr *tb[], u32 flags) h->timeout = IPSET_NO_TIMEOUT; hbits = htable_bits(hashsize); - h->table = ip_set_alloc( - sizeof(struct htable) - + jhash_size(hbits) * sizeof(struct hbucket)); + hsize = htable_size(hbits); + if (hsize == 0) { + kfree(h); + return -ENOMEM; + } + h->table = ip_set_alloc(hsize); if (!h->table) { kfree(h); return -ENOMEM; diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 5d05e696986..1ce21ca976e 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -124,13 +124,14 @@ hash_ipportnet4_data_list(struct sk_buff *skb, { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP2, data->ip2); - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR2, data->cidr + 1); - NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); - if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || + nla_put_ipaddr4(skb, IPSET_ATTR_IP2, data->ip2) || + nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || + nla_put_u8(skb, IPSET_ATTR_CIDR2, data->cidr + 1) || + nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || + (flags && + nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -145,16 +146,16 @@ hash_ipportnet4_data_tlist(struct sk_buff *skb, (const struct hash_ipportnet4_telem *)data; u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, tdata->ip); - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP2, tdata->ip2); - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, tdata->port); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR2, data->cidr + 1); - NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, - htonl(ip_set_timeout_get(tdata->timeout))); - if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); - + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, tdata->ip) || + nla_put_ipaddr4(skb, IPSET_ATTR_IP2, tdata->ip2) || + nla_put_net16(skb, IPSET_ATTR_PORT, tdata->port) || + nla_put_u8(skb, IPSET_ATTR_CIDR2, data->cidr + 1) || + nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(tdata->timeout))) || + (flags && + nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -436,13 +437,14 @@ hash_ipportnet6_data_list(struct sk_buff *skb, { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; - NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip); - NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP2, &data->ip2); - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR2, data->cidr + 1); - NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); - if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); + if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) || + nla_put_ipaddr6(skb, IPSET_ATTR_IP2, &data->ip2.in6) || + nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || + nla_put_u8(skb, IPSET_ATTR_CIDR2, data->cidr + 1) || + nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || + (flags && + nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -457,15 +459,16 @@ hash_ipportnet6_data_tlist(struct sk_buff *skb, (const struct hash_ipportnet6_telem *)data; u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; - NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip); - NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP2, &data->ip2); - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR2, data->cidr + 1); - NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, - htonl(ip_set_timeout_get(e->timeout))); - if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); + if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &e->ip.in6) || + nla_put_ipaddr6(skb, IPSET_ATTR_IP2, &data->ip2.in6) || + nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || + nla_put_u8(skb, IPSET_ATTR_CIDR2, data->cidr + 1) || + nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(e->timeout))) || + (flags && + nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -616,6 +619,7 @@ hash_ipportnet_create(struct ip_set *set, struct nlattr *tb[], u32 flags) struct ip_set_hash *h; u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; u8 hbits; + size_t hsize; if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6)) return -IPSET_ERR_INVALID_FAMILY; @@ -645,9 +649,12 @@ hash_ipportnet_create(struct ip_set *set, struct nlattr *tb[], u32 flags) h->timeout = IPSET_NO_TIMEOUT; hbits = htable_bits(hashsize); - h->table = ip_set_alloc( - sizeof(struct htable) - + jhash_size(hbits) * sizeof(struct hbucket)); + hsize = htable_size(hbits); + if (hsize == 0) { + kfree(h); + return -ENOMEM; + } + h->table = ip_set_alloc(hsize); if (!h->table) { kfree(h); return -ENOMEM; diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 7c3d945517c..c57a6a09906 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -111,10 +111,11 @@ hash_net4_data_list(struct sk_buff *skb, const struct hash_net4_elem *data) { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); - if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || + nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr) || + (flags && + nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -128,13 +129,13 @@ hash_net4_data_tlist(struct sk_buff *skb, const struct hash_net4_elem *data) (const struct hash_net4_telem *)data; u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, tdata->ip); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR, tdata->cidr); - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, - htonl(ip_set_timeout_get(tdata->timeout))); - if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); - + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, tdata->ip) || + nla_put_u8(skb, IPSET_ATTR_CIDR, tdata->cidr) || + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(tdata->timeout))) || + (flags && + nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -339,10 +340,11 @@ hash_net6_data_list(struct sk_buff *skb, const struct hash_net6_elem *data) { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; - NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); - if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); + if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) || + nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr) || + (flags && + nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -356,12 +358,13 @@ hash_net6_data_tlist(struct sk_buff *skb, const struct hash_net6_elem *data) (const struct hash_net6_telem *)data; u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; - NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR, e->cidr); - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, - htonl(ip_set_timeout_get(e->timeout))); - if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); + if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &e->ip.in6) || + nla_put_u8(skb, IPSET_ATTR_CIDR, e->cidr) || + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(e->timeout))) || + (flags && + nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -460,6 +463,7 @@ hash_net_create(struct ip_set *set, struct nlattr *tb[], u32 flags) u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; struct ip_set_hash *h; u8 hbits; + size_t hsize; if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6)) return -IPSET_ERR_INVALID_FAMILY; @@ -489,9 +493,12 @@ hash_net_create(struct ip_set *set, struct nlattr *tb[], u32 flags) h->timeout = IPSET_NO_TIMEOUT; hbits = htable_bits(hashsize); - h->table = ip_set_alloc( - sizeof(struct htable) - + jhash_size(hbits) * sizeof(struct hbucket)); + hsize = htable_size(hbits); + if (hsize == 0) { + kfree(h); + return -ENOMEM; + } + h->table = ip_set_alloc(hsize); if (!h->table) { kfree(h); return -ENOMEM; diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index f24037ff432..ee863943c82 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -252,11 +252,12 @@ hash_netiface4_data_list(struct sk_buff *skb, if (data->nomatch) flags |= IPSET_FLAG_NOMATCH; - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); - NLA_PUT_STRING(skb, IPSET_ATTR_IFACE, data->iface); - if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || + nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr) || + nla_put_string(skb, IPSET_ATTR_IFACE, data->iface) || + (flags && + nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -273,13 +274,14 @@ hash_netiface4_data_tlist(struct sk_buff *skb, if (data->nomatch) flags |= IPSET_FLAG_NOMATCH; - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); - NLA_PUT_STRING(skb, IPSET_ATTR_IFACE, data->iface); - if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, - htonl(ip_set_timeout_get(tdata->timeout))); + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || + nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr) || + nla_put_string(skb, IPSET_ATTR_IFACE, data->iface) || + (flags && + nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))) || + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(tdata->timeout)))) + goto nla_put_failure; return 0; @@ -555,11 +557,12 @@ hash_netiface6_data_list(struct sk_buff *skb, if (data->nomatch) flags |= IPSET_FLAG_NOMATCH; - NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); - NLA_PUT_STRING(skb, IPSET_ATTR_IFACE, data->iface); - if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); + if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) || + nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr) || + nla_put_string(skb, IPSET_ATTR_IFACE, data->iface) || + (flags && + nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -576,13 +579,14 @@ hash_netiface6_data_tlist(struct sk_buff *skb, if (data->nomatch) flags |= IPSET_FLAG_NOMATCH; - NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); - NLA_PUT_STRING(skb, IPSET_ATTR_IFACE, data->iface); - if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, - htonl(ip_set_timeout_get(e->timeout))); + if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &e->ip.in6) || + nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr) || + nla_put_string(skb, IPSET_ATTR_IFACE, data->iface) || + (flags && + nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))) || + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(e->timeout)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -722,6 +726,7 @@ hash_netiface_create(struct ip_set *set, struct nlattr *tb[], u32 flags) struct ip_set_hash *h; u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; u8 hbits; + size_t hsize; if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6)) return -IPSET_ERR_INVALID_FAMILY; @@ -752,9 +757,12 @@ hash_netiface_create(struct ip_set *set, struct nlattr *tb[], u32 flags) h->ahash_max = AHASH_MAX_SIZE; hbits = htable_bits(hashsize); - h->table = ip_set_alloc( - sizeof(struct htable) - + jhash_size(hbits) * sizeof(struct hbucket)); + hsize = htable_size(hbits); + if (hsize == 0) { + kfree(h); + return -ENOMEM; + } + h->table = ip_set_alloc(hsize); if (!h->table) { kfree(h); return -ENOMEM; diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index ce2e77100b6..fc3143a2d41 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -124,12 +124,13 @@ hash_netport4_data_list(struct sk_buff *skb, { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr + 1); - NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); - if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || + nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || + nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr + 1) || + nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || + (flags && + nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -144,15 +145,15 @@ hash_netport4_data_tlist(struct sk_buff *skb, (const struct hash_netport4_telem *)data; u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; - NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, tdata->ip); - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, tdata->port); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr + 1); - NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, - htonl(ip_set_timeout_get(tdata->timeout))); - if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); - + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, tdata->ip) || + nla_put_net16(skb, IPSET_ATTR_PORT, tdata->port) || + nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr + 1) || + nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(tdata->timeout))) || + (flags && + nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -402,12 +403,13 @@ hash_netport6_data_list(struct sk_buff *skb, { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; - NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip); - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr + 1); - NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); - if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); + if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) || + nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || + nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr + 1) || + nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || + (flags && + nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -422,14 +424,15 @@ hash_netport6_data_tlist(struct sk_buff *skb, (const struct hash_netport6_telem *)data; u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; - NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip); - NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr + 1); - NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, - htonl(ip_set_timeout_get(e->timeout))); - if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); + if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &e->ip.in6) || + nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || + nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr + 1) || + nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(e->timeout))) || + (flags && + nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -572,6 +575,7 @@ hash_netport_create(struct ip_set *set, struct nlattr *tb[], u32 flags) struct ip_set_hash *h; u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; u8 hbits; + size_t hsize; if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6)) return -IPSET_ERR_INVALID_FAMILY; @@ -601,9 +605,12 @@ hash_netport_create(struct ip_set *set, struct nlattr *tb[], u32 flags) h->timeout = IPSET_NO_TIMEOUT; hbits = htable_bits(hashsize); - h->table = ip_set_alloc( - sizeof(struct htable) - + jhash_size(hbits) * sizeof(struct hbucket)); + hsize = htable_size(hbits); + if (hsize == 0) { + kfree(h); + return -ENOMEM; + } + h->table = ip_set_alloc(hsize); if (!h->table) { kfree(h); return -ENOMEM; diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 7e095f9005f..6cb1225765f 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -402,12 +402,13 @@ list_set_head(struct ip_set *set, struct sk_buff *skb) nested = ipset_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; - NLA_PUT_NET32(skb, IPSET_ATTR_SIZE, htonl(map->size)); - if (with_timeout(map->timeout)) - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout)); - NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)); - NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, - htonl(sizeof(*map) + map->size * map->dsize)); + if (nla_put_net32(skb, IPSET_ATTR_SIZE, htonl(map->size)) || + (with_timeout(map->timeout) && + nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout))) || + nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) || + nla_put_net32(skb, IPSET_ATTR_MEMSIZE, + htonl(sizeof(*map) + map->size * map->dsize))) + goto nla_put_failure; ipset_nest_end(skb, nested); return 0; @@ -442,13 +443,15 @@ list_set_list(const struct ip_set *set, } else goto nla_put_failure; } - NLA_PUT_STRING(skb, IPSET_ATTR_NAME, - ip_set_name_byindex(e->id)); + if (nla_put_string(skb, IPSET_ATTR_NAME, + ip_set_name_byindex(e->id))) + goto nla_put_failure; if (with_timeout(map->timeout)) { const struct set_telem *te = (const struct set_telem *) e; - NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, - htonl(ip_set_timeout_get(te->timeout))); + __be32 to = htonl(ip_set_timeout_get(te->timeout)); + if (nla_put_net32(skb, IPSET_ATTR_TIMEOUT, to)) + goto nla_put_failure; } ipset_nest_end(skb, nested); } diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 52856178c9d..64f9e8f1320 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -313,7 +313,7 @@ vs_fix_ack_seq(const struct ip_vs_seq *vseq, struct tcphdr *th) * Assumes already checked proto==IPPROTO_TCP and diff!=0. */ static inline void vs_seq_update(struct ip_vs_conn *cp, struct ip_vs_seq *vseq, - unsigned flag, __u32 seq, int diff) + unsigned int flag, __u32 seq, int diff) { /* spinlock is to keep updating cp->flags atomic */ spin_lock(&cp->lock); diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 29fa5badde7..1548df9a752 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -86,42 +86,42 @@ struct ip_vs_aligned_lock static struct ip_vs_aligned_lock __ip_vs_conntbl_lock_array[CT_LOCKARRAY_SIZE] __cacheline_aligned; -static inline void ct_read_lock(unsigned key) +static inline void ct_read_lock(unsigned int key) { read_lock(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); } -static inline void ct_read_unlock(unsigned key) +static inline void ct_read_unlock(unsigned int key) { read_unlock(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); } -static inline void ct_write_lock(unsigned key) +static inline void ct_write_lock(unsigned int key) { write_lock(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); } -static inline void ct_write_unlock(unsigned key) +static inline void ct_write_unlock(unsigned int key) { write_unlock(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); } -static inline void ct_read_lock_bh(unsigned key) +static inline void ct_read_lock_bh(unsigned int key) { read_lock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); } -static inline void ct_read_unlock_bh(unsigned key) +static inline void ct_read_unlock_bh(unsigned int key) { read_unlock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); } -static inline void ct_write_lock_bh(unsigned key) +static inline void ct_write_lock_bh(unsigned int key) { write_lock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); } -static inline void ct_write_unlock_bh(unsigned key) +static inline void ct_write_unlock_bh(unsigned int key) { write_unlock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); } @@ -130,7 +130,7 @@ static inline void ct_write_unlock_bh(unsigned key) /* * Returns hash value for IPVS connection entry */ -static unsigned int ip_vs_conn_hashkey(struct net *net, int af, unsigned proto, +static unsigned int ip_vs_conn_hashkey(struct net *net, int af, unsigned int proto, const union nf_inet_addr *addr, __be16 port) { @@ -188,7 +188,7 @@ static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp) */ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) { - unsigned hash; + unsigned int hash; int ret; if (cp->flags & IP_VS_CONN_F_ONE_PACKET) @@ -224,7 +224,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) */ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) { - unsigned hash; + unsigned int hash; int ret; /* unhash it and decrease its reference counter */ @@ -257,7 +257,7 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) static inline struct ip_vs_conn * __ip_vs_conn_in_get(const struct ip_vs_conn_param *p) { - unsigned hash; + unsigned int hash; struct ip_vs_conn *cp; struct hlist_node *n; @@ -344,7 +344,7 @@ EXPORT_SYMBOL_GPL(ip_vs_conn_in_get_proto); /* Get reference to connection template */ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) { - unsigned hash; + unsigned int hash; struct ip_vs_conn *cp; struct hlist_node *n; @@ -394,7 +394,7 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) * p->vaddr, p->vport: pkt dest address (foreign host) */ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) { - unsigned hash; + unsigned int hash; struct ip_vs_conn *cp, *ret=NULL; struct hlist_node *n; @@ -548,6 +548,7 @@ static inline void ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) { unsigned int conn_flags; + __u32 flags; /* if dest is NULL, then return directly */ if (!dest) @@ -559,17 +560,19 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) conn_flags = atomic_read(&dest->conn_flags); if (cp->protocol != IPPROTO_UDP) conn_flags &= ~IP_VS_CONN_F_ONE_PACKET; + flags = cp->flags; /* Bind with the destination and its corresponding transmitter */ - if (cp->flags & IP_VS_CONN_F_SYNC) { + if (flags & IP_VS_CONN_F_SYNC) { /* if the connection is not template and is created * by sync, preserve the activity flag. */ - if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) + if (!(flags & IP_VS_CONN_F_TEMPLATE)) conn_flags &= ~IP_VS_CONN_F_INACTIVE; /* connections inherit forwarding method from dest */ - cp->flags &= ~IP_VS_CONN_F_FWD_MASK; + flags &= ~(IP_VS_CONN_F_FWD_MASK | IP_VS_CONN_F_NOOUTPUT); } - cp->flags |= conn_flags; + flags |= conn_flags; + cp->flags = flags; cp->dest = dest; IP_VS_DBG_BUF(7, "Bind-dest %s c:%s:%d v:%s:%d " @@ -584,12 +587,12 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) atomic_read(&dest->refcnt)); /* Update the connection counters */ - if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) { - /* It is a normal connection, so increase the inactive - connection counter because it is in TCP SYNRECV - state (inactive) or other protocol inacive state */ - if ((cp->flags & IP_VS_CONN_F_SYNC) && - (!(cp->flags & IP_VS_CONN_F_INACTIVE))) + if (!(flags & IP_VS_CONN_F_TEMPLATE)) { + /* It is a normal connection, so modify the counters + * according to the flags, later the protocol can + * update them on state change + */ + if (!(flags & IP_VS_CONN_F_INACTIVE)) atomic_inc(&dest->activeconns); else atomic_inc(&dest->inactconns); @@ -613,14 +616,40 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp) { struct ip_vs_dest *dest; - if ((cp) && (!cp->dest)) { - dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, &cp->daddr, - cp->dport, &cp->vaddr, cp->vport, - cp->protocol, cp->fwmark, cp->flags); + dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, &cp->daddr, + cp->dport, &cp->vaddr, cp->vport, + cp->protocol, cp->fwmark, cp->flags); + if (dest) { + struct ip_vs_proto_data *pd; + + spin_lock(&cp->lock); + if (cp->dest) { + spin_unlock(&cp->lock); + return dest; + } + + /* Applications work depending on the forwarding method + * but better to reassign them always when binding dest */ + if (cp->app) + ip_vs_unbind_app(cp); + ip_vs_bind_dest(cp, dest); - return dest; - } else - return NULL; + spin_unlock(&cp->lock); + + /* Update its packet transmitter */ + cp->packet_xmit = NULL; +#ifdef CONFIG_IP_VS_IPV6 + if (cp->af == AF_INET6) + ip_vs_bind_xmit_v6(cp); + else +#endif + ip_vs_bind_xmit(cp); + + pd = ip_vs_proto_data_get(ip_vs_conn_net(cp), cp->protocol); + if (pd && atomic_read(&pd->appcnt)) + ip_vs_bind_app(cp, pd->pp); + } + return dest; } @@ -743,7 +772,8 @@ int ip_vs_check_template(struct ip_vs_conn *ct) static void ip_vs_conn_expire(unsigned long data) { struct ip_vs_conn *cp = (struct ip_vs_conn *)data; - struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp)); + struct net *net = ip_vs_conn_net(cp); + struct netns_ipvs *ipvs = net_ipvs(net); cp->timeout = 60*HZ; @@ -808,6 +838,9 @@ static void ip_vs_conn_expire(unsigned long data) atomic_read(&cp->refcnt)-1, atomic_read(&cp->n_control)); + if (ipvs->sync_state & IP_VS_STATE_MASTER) + ip_vs_sync_conn(net, cp, sysctl_sync_threshold(ipvs)); + ip_vs_conn_put(cp); } @@ -824,7 +857,7 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp) */ struct ip_vs_conn * ip_vs_conn_new(const struct ip_vs_conn_param *p, - const union nf_inet_addr *daddr, __be16 dport, unsigned flags, + const union nf_inet_addr *daddr, __be16 dport, unsigned int flags, struct ip_vs_dest *dest, __u32 fwmark) { struct ip_vs_conn *cp; @@ -881,6 +914,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, /* Set its state and timeout */ cp->state = 0; cp->timeout = 3*HZ; + cp->sync_endtime = jiffies & ~3UL; /* Bind its packet transmitter */ #ifdef CONFIG_IP_VS_IPV6 @@ -1057,7 +1091,7 @@ static const struct file_operations ip_vs_conn_fops = { .release = seq_release_net, }; -static const char *ip_vs_origin_name(unsigned flags) +static const char *ip_vs_origin_name(unsigned int flags) { if (flags & IP_VS_CONN_F_SYNC) return "SYNC"; @@ -1169,7 +1203,7 @@ void ip_vs_random_dropentry(struct net *net) * Randomly scan 1/32 of the whole table every second */ for (idx = 0; idx < (ip_vs_conn_tab_size>>5); idx++) { - unsigned hash = net_random() & ip_vs_conn_tab_mask; + unsigned int hash = net_random() & ip_vs_conn_tab_mask; struct hlist_node *n; /* diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 2555816e778..a54b018c6ee 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -80,7 +80,7 @@ static atomic_t ipvs_netns_cnt = ATOMIC_INIT(0); #define icmp_id(icmph) (((icmph)->un).echo.id) #define icmpv6_id(icmph) (icmph->icmp6_dataun.u_echo.identifier) -const char *ip_vs_proto_name(unsigned proto) +const char *ip_vs_proto_name(unsigned int proto) { static char buf[20]; @@ -1613,34 +1613,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) else pkts = atomic_add_return(1, &cp->in_pkts); - if ((ipvs->sync_state & IP_VS_STATE_MASTER) && - cp->protocol == IPPROTO_SCTP) { - if ((cp->state == IP_VS_SCTP_S_ESTABLISHED && - (pkts % sysctl_sync_period(ipvs) - == sysctl_sync_threshold(ipvs))) || - (cp->old_state != cp->state && - ((cp->state == IP_VS_SCTP_S_CLOSED) || - (cp->state == IP_VS_SCTP_S_SHUT_ACK_CLI) || - (cp->state == IP_VS_SCTP_S_SHUT_ACK_SER)))) { - ip_vs_sync_conn(net, cp); - goto out; - } - } - - /* Keep this block last: TCP and others with pp->num_states <= 1 */ - else if ((ipvs->sync_state & IP_VS_STATE_MASTER) && - (((cp->protocol != IPPROTO_TCP || - cp->state == IP_VS_TCP_S_ESTABLISHED) && - (pkts % sysctl_sync_period(ipvs) - == sysctl_sync_threshold(ipvs))) || - ((cp->protocol == IPPROTO_TCP) && (cp->old_state != cp->state) && - ((cp->state == IP_VS_TCP_S_FIN_WAIT) || - (cp->state == IP_VS_TCP_S_CLOSE) || - (cp->state == IP_VS_TCP_S_CLOSE_WAIT) || - (cp->state == IP_VS_TCP_S_TIME_WAIT))))) - ip_vs_sync_conn(net, cp); -out: - cp->old_state = cp->state; + if (ipvs->sync_state & IP_VS_STATE_MASTER) + ip_vs_sync_conn(net, cp, pkts); ip_vs_conn_put(cp); return ret; @@ -1924,6 +1898,7 @@ protocol_fail: control_fail: ip_vs_estimator_net_cleanup(net); estimator_fail: + net->ipvs = NULL; return -ENOMEM; } @@ -1936,6 +1911,7 @@ static void __net_exit __ip_vs_cleanup(struct net *net) ip_vs_control_net_cleanup(net); ip_vs_estimator_net_cleanup(net); IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen); + net->ipvs = NULL; } static void __net_exit __ip_vs_dev_cleanup(struct net *net) @@ -1993,10 +1969,18 @@ static int __init ip_vs_init(void) goto cleanup_dev; } + ret = ip_vs_register_nl_ioctl(); + if (ret < 0) { + pr_err("can't register netlink/ioctl.\n"); + goto cleanup_hooks; + } + pr_info("ipvs loaded.\n"); return ret; +cleanup_hooks: + nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); cleanup_dev: unregister_pernet_device(&ipvs_core_dev_ops); cleanup_sub: @@ -2012,6 +1996,7 @@ exit: static void __exit ip_vs_cleanup(void) { + ip_vs_unregister_nl_ioctl(); nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); unregister_pernet_device(&ipvs_core_dev_ops); unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index b3afe189af6..dd811b8dd97 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -265,11 +265,11 @@ static struct list_head ip_vs_svc_fwm_table[IP_VS_SVC_TAB_SIZE]; /* * Returns hash value for virtual service */ -static inline unsigned -ip_vs_svc_hashkey(struct net *net, int af, unsigned proto, +static inline unsigned int +ip_vs_svc_hashkey(struct net *net, int af, unsigned int proto, const union nf_inet_addr *addr, __be16 port) { - register unsigned porth = ntohs(port); + register unsigned int porth = ntohs(port); __be32 addr_fold = addr->ip; #ifdef CONFIG_IP_VS_IPV6 @@ -286,7 +286,7 @@ ip_vs_svc_hashkey(struct net *net, int af, unsigned proto, /* * Returns hash value of fwmark for virtual service lookup */ -static inline unsigned ip_vs_svc_fwm_hashkey(struct net *net, __u32 fwmark) +static inline unsigned int ip_vs_svc_fwm_hashkey(struct net *net, __u32 fwmark) { return (((size_t)net>>8) ^ fwmark) & IP_VS_SVC_TAB_MASK; } @@ -298,7 +298,7 @@ static inline unsigned ip_vs_svc_fwm_hashkey(struct net *net, __u32 fwmark) */ static int ip_vs_svc_hash(struct ip_vs_service *svc) { - unsigned hash; + unsigned int hash; if (svc->flags & IP_VS_SVC_F_HASHED) { pr_err("%s(): request for already hashed, called from %pF\n", @@ -361,7 +361,7 @@ static inline struct ip_vs_service * __ip_vs_service_find(struct net *net, int af, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport) { - unsigned hash; + unsigned int hash; struct ip_vs_service *svc; /* Check for "full" addressed entries */ @@ -388,7 +388,7 @@ __ip_vs_service_find(struct net *net, int af, __u16 protocol, static inline struct ip_vs_service * __ip_vs_svc_fwm_find(struct net *net, int af, __u32 fwmark) { - unsigned hash; + unsigned int hash; struct ip_vs_service *svc; /* Check for fwmark addressed entries */ @@ -489,11 +489,11 @@ __ip_vs_unbind_svc(struct ip_vs_dest *dest) /* * Returns hash value for real service */ -static inline unsigned ip_vs_rs_hashkey(int af, +static inline unsigned int ip_vs_rs_hashkey(int af, const union nf_inet_addr *addr, __be16 port) { - register unsigned porth = ntohs(port); + register unsigned int porth = ntohs(port); __be32 addr_fold = addr->ip; #ifdef CONFIG_IP_VS_IPV6 @@ -512,7 +512,7 @@ static inline unsigned ip_vs_rs_hashkey(int af, */ static int ip_vs_rs_hash(struct netns_ipvs *ipvs, struct ip_vs_dest *dest) { - unsigned hash; + unsigned int hash; if (!list_empty(&dest->d_list)) { return 0; @@ -555,7 +555,7 @@ ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol, __be16 dport) { struct netns_ipvs *ipvs = net_ipvs(net); - unsigned hash; + unsigned int hash; struct ip_vs_dest *dest; /* @@ -842,7 +842,7 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, struct ip_vs_dest **dest_p) { struct ip_vs_dest *dest; - unsigned atype; + unsigned int atype; EnterFunction(2); @@ -1599,6 +1599,10 @@ static int ip_vs_zero_all(struct net *net) } #ifdef CONFIG_SYSCTL + +static int zero; +static int three = 3; + static int proc_do_defense_mode(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -1632,7 +1636,8 @@ proc_do_sync_threshold(ctl_table *table, int write, memcpy(val, valp, sizeof(val)); rc = proc_dointvec(table, write, buffer, lenp, ppos); - if (write && (valp[0] < 0 || valp[1] < 0 || valp[0] >= valp[1])) { + if (write && (valp[0] < 0 || valp[1] < 0 || + (valp[0] >= valp[1] && valp[1]))) { /* Restore the correct value */ memcpy(valp, val, sizeof(val)); } @@ -1652,9 +1657,24 @@ proc_do_sync_mode(ctl_table *table, int write, if ((*valp < 0) || (*valp > 1)) { /* Restore the correct value */ *valp = val; - } else { - struct net *net = current->nsproxy->net_ns; - ip_vs_sync_switch_mode(net, val); + } + } + return rc; +} + +static int +proc_do_sync_ports(ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int *valp = table->data; + int val = *valp; + int rc; + + rc = proc_dointvec(table, write, buffer, lenp, ppos); + if (write && (*valp != val)) { + if (*valp < 1 || !is_power_of_2(*valp)) { + /* Restore the correct value */ + *valp = val; } } return rc; @@ -1718,6 +1738,24 @@ static struct ctl_table vs_vars[] = { .proc_handler = &proc_do_sync_mode, }, { + .procname = "sync_ports", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_do_sync_ports, + }, + { + .procname = "sync_qlen_max", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "sync_sock_size", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "cache_bypass", .maxlen = sizeof(int), .mode = 0644, @@ -1743,6 +1781,20 @@ static struct ctl_table vs_vars[] = { .proc_handler = proc_do_sync_threshold, }, { + .procname = "sync_refresh_period", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { + .procname = "sync_retries", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &three, + }, + { .procname = "nat_icmp_send", .maxlen = sizeof(int), .mode = 0644, @@ -1846,13 +1898,6 @@ static struct ctl_table vs_vars[] = { { } }; -const struct ctl_path net_vs_ctl_path[] = { - { .procname = "net", }, - { .procname = "ipv4", }, - { .procname = "vs", }, - { } -}; -EXPORT_SYMBOL_GPL(net_vs_ctl_path); #endif #ifdef CONFIG_PROC_FS @@ -1867,7 +1912,7 @@ struct ip_vs_iter { * Write the contents of the VS rule table to a PROCfs file. * (It is kept just for backward compatibility) */ -static inline const char *ip_vs_fwd_name(unsigned flags) +static inline const char *ip_vs_fwd_name(unsigned int flags) { switch (flags & IP_VS_CONN_F_FWD_MASK) { case IP_VS_CONN_F_LOCALNODE: @@ -2816,17 +2861,17 @@ static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type, ip_vs_copy_stats(&ustats, stats); - NLA_PUT_U32(skb, IPVS_STATS_ATTR_CONNS, ustats.conns); - NLA_PUT_U32(skb, IPVS_STATS_ATTR_INPKTS, ustats.inpkts); - NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTPKTS, ustats.outpkts); - NLA_PUT_U64(skb, IPVS_STATS_ATTR_INBYTES, ustats.inbytes); - NLA_PUT_U64(skb, IPVS_STATS_ATTR_OUTBYTES, ustats.outbytes); - NLA_PUT_U32(skb, IPVS_STATS_ATTR_CPS, ustats.cps); - NLA_PUT_U32(skb, IPVS_STATS_ATTR_INPPS, ustats.inpps); - NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTPPS, ustats.outpps); - NLA_PUT_U32(skb, IPVS_STATS_ATTR_INBPS, ustats.inbps); - NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTBPS, ustats.outbps); - + if (nla_put_u32(skb, IPVS_STATS_ATTR_CONNS, ustats.conns) || + nla_put_u32(skb, IPVS_STATS_ATTR_INPKTS, ustats.inpkts) || + nla_put_u32(skb, IPVS_STATS_ATTR_OUTPKTS, ustats.outpkts) || + nla_put_u64(skb, IPVS_STATS_ATTR_INBYTES, ustats.inbytes) || + nla_put_u64(skb, IPVS_STATS_ATTR_OUTBYTES, ustats.outbytes) || + nla_put_u32(skb, IPVS_STATS_ATTR_CPS, ustats.cps) || + nla_put_u32(skb, IPVS_STATS_ATTR_INPPS, ustats.inpps) || + nla_put_u32(skb, IPVS_STATS_ATTR_OUTPPS, ustats.outpps) || + nla_put_u32(skb, IPVS_STATS_ATTR_INBPS, ustats.inbps) || + nla_put_u32(skb, IPVS_STATS_ATTR_OUTBPS, ustats.outbps)) + goto nla_put_failure; nla_nest_end(skb, nl_stats); return 0; @@ -2847,23 +2892,25 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb, if (!nl_service) return -EMSGSIZE; - NLA_PUT_U16(skb, IPVS_SVC_ATTR_AF, svc->af); - + if (nla_put_u16(skb, IPVS_SVC_ATTR_AF, svc->af)) + goto nla_put_failure; if (svc->fwmark) { - NLA_PUT_U32(skb, IPVS_SVC_ATTR_FWMARK, svc->fwmark); + if (nla_put_u32(skb, IPVS_SVC_ATTR_FWMARK, svc->fwmark)) + goto nla_put_failure; } else { - NLA_PUT_U16(skb, IPVS_SVC_ATTR_PROTOCOL, svc->protocol); - NLA_PUT(skb, IPVS_SVC_ATTR_ADDR, sizeof(svc->addr), &svc->addr); - NLA_PUT_U16(skb, IPVS_SVC_ATTR_PORT, svc->port); + if (nla_put_u16(skb, IPVS_SVC_ATTR_PROTOCOL, svc->protocol) || + nla_put(skb, IPVS_SVC_ATTR_ADDR, sizeof(svc->addr), &svc->addr) || + nla_put_u16(skb, IPVS_SVC_ATTR_PORT, svc->port)) + goto nla_put_failure; } - NLA_PUT_STRING(skb, IPVS_SVC_ATTR_SCHED_NAME, svc->scheduler->name); - if (svc->pe) - NLA_PUT_STRING(skb, IPVS_SVC_ATTR_PE_NAME, svc->pe->name); - NLA_PUT(skb, IPVS_SVC_ATTR_FLAGS, sizeof(flags), &flags); - NLA_PUT_U32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ); - NLA_PUT_U32(skb, IPVS_SVC_ATTR_NETMASK, svc->netmask); - + if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, svc->scheduler->name) || + (svc->pe && + nla_put_string(skb, IPVS_SVC_ATTR_PE_NAME, svc->pe->name)) || + nla_put(skb, IPVS_SVC_ATTR_FLAGS, sizeof(flags), &flags) || + nla_put_u32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ) || + nla_put_u32(skb, IPVS_SVC_ATTR_NETMASK, svc->netmask)) + goto nla_put_failure; if (ip_vs_genl_fill_stats(skb, IPVS_SVC_ATTR_STATS, &svc->stats)) goto nla_put_failure; @@ -3038,21 +3085,22 @@ static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest) if (!nl_dest) return -EMSGSIZE; - NLA_PUT(skb, IPVS_DEST_ATTR_ADDR, sizeof(dest->addr), &dest->addr); - NLA_PUT_U16(skb, IPVS_DEST_ATTR_PORT, dest->port); - - NLA_PUT_U32(skb, IPVS_DEST_ATTR_FWD_METHOD, - atomic_read(&dest->conn_flags) & IP_VS_CONN_F_FWD_MASK); - NLA_PUT_U32(skb, IPVS_DEST_ATTR_WEIGHT, atomic_read(&dest->weight)); - NLA_PUT_U32(skb, IPVS_DEST_ATTR_U_THRESH, dest->u_threshold); - NLA_PUT_U32(skb, IPVS_DEST_ATTR_L_THRESH, dest->l_threshold); - NLA_PUT_U32(skb, IPVS_DEST_ATTR_ACTIVE_CONNS, - atomic_read(&dest->activeconns)); - NLA_PUT_U32(skb, IPVS_DEST_ATTR_INACT_CONNS, - atomic_read(&dest->inactconns)); - NLA_PUT_U32(skb, IPVS_DEST_ATTR_PERSIST_CONNS, - atomic_read(&dest->persistconns)); - + if (nla_put(skb, IPVS_DEST_ATTR_ADDR, sizeof(dest->addr), &dest->addr) || + nla_put_u16(skb, IPVS_DEST_ATTR_PORT, dest->port) || + nla_put_u32(skb, IPVS_DEST_ATTR_FWD_METHOD, + (atomic_read(&dest->conn_flags) & + IP_VS_CONN_F_FWD_MASK)) || + nla_put_u32(skb, IPVS_DEST_ATTR_WEIGHT, + atomic_read(&dest->weight)) || + nla_put_u32(skb, IPVS_DEST_ATTR_U_THRESH, dest->u_threshold) || + nla_put_u32(skb, IPVS_DEST_ATTR_L_THRESH, dest->l_threshold) || + nla_put_u32(skb, IPVS_DEST_ATTR_ACTIVE_CONNS, + atomic_read(&dest->activeconns)) || + nla_put_u32(skb, IPVS_DEST_ATTR_INACT_CONNS, + atomic_read(&dest->inactconns)) || + nla_put_u32(skb, IPVS_DEST_ATTR_PERSIST_CONNS, + atomic_read(&dest->persistconns))) + goto nla_put_failure; if (ip_vs_genl_fill_stats(skb, IPVS_DEST_ATTR_STATS, &dest->stats)) goto nla_put_failure; @@ -3181,10 +3229,10 @@ static int ip_vs_genl_fill_daemon(struct sk_buff *skb, __be32 state, if (!nl_daemon) return -EMSGSIZE; - NLA_PUT_U32(skb, IPVS_DAEMON_ATTR_STATE, state); - NLA_PUT_STRING(skb, IPVS_DAEMON_ATTR_MCAST_IFN, mcast_ifn); - NLA_PUT_U32(skb, IPVS_DAEMON_ATTR_SYNC_ID, syncid); - + if (nla_put_u32(skb, IPVS_DAEMON_ATTR_STATE, state) || + nla_put_string(skb, IPVS_DAEMON_ATTR_MCAST_IFN, mcast_ifn) || + nla_put_u32(skb, IPVS_DAEMON_ATTR_SYNC_ID, syncid)) + goto nla_put_failure; nla_nest_end(skb, nl_daemon); return 0; @@ -3473,21 +3521,26 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info) __ip_vs_get_timeouts(net, &t); #ifdef CONFIG_IP_VS_PROTO_TCP - NLA_PUT_U32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP, t.tcp_timeout); - NLA_PUT_U32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP_FIN, - t.tcp_fin_timeout); + if (nla_put_u32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP, + t.tcp_timeout) || + nla_put_u32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP_FIN, + t.tcp_fin_timeout)) + goto nla_put_failure; #endif #ifdef CONFIG_IP_VS_PROTO_UDP - NLA_PUT_U32(msg, IPVS_CMD_ATTR_TIMEOUT_UDP, t.udp_timeout); + if (nla_put_u32(msg, IPVS_CMD_ATTR_TIMEOUT_UDP, t.udp_timeout)) + goto nla_put_failure; #endif break; } case IPVS_CMD_GET_INFO: - NLA_PUT_U32(msg, IPVS_INFO_ATTR_VERSION, IP_VS_VERSION_CODE); - NLA_PUT_U32(msg, IPVS_INFO_ATTR_CONN_TAB_SIZE, - ip_vs_conn_tab_size); + if (nla_put_u32(msg, IPVS_INFO_ATTR_VERSION, + IP_VS_VERSION_CODE) || + nla_put_u32(msg, IPVS_INFO_ATTR_CONN_TAB_SIZE, + ip_vs_conn_tab_size)) + goto nla_put_failure; break; } @@ -3654,6 +3707,12 @@ int __net_init ip_vs_control_net_init_sysctl(struct net *net) tbl[idx++].data = &ipvs->sysctl_snat_reroute; ipvs->sysctl_sync_ver = 1; tbl[idx++].data = &ipvs->sysctl_sync_ver; + ipvs->sysctl_sync_ports = 1; + tbl[idx++].data = &ipvs->sysctl_sync_ports; + ipvs->sysctl_sync_qlen_max = nr_free_buffer_pages() / 32; + tbl[idx++].data = &ipvs->sysctl_sync_qlen_max; + ipvs->sysctl_sync_sock_size = 0; + tbl[idx++].data = &ipvs->sysctl_sync_sock_size; tbl[idx++].data = &ipvs->sysctl_cache_bypass; tbl[idx++].data = &ipvs->sysctl_expire_nodest_conn; tbl[idx++].data = &ipvs->sysctl_expire_quiescent_template; @@ -3661,11 +3720,14 @@ int __net_init ip_vs_control_net_init_sysctl(struct net *net) ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD; tbl[idx].data = &ipvs->sysctl_sync_threshold; tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold); + ipvs->sysctl_sync_refresh_period = DEFAULT_SYNC_REFRESH_PERIOD; + tbl[idx++].data = &ipvs->sysctl_sync_refresh_period; + ipvs->sysctl_sync_retries = clamp_t(int, DEFAULT_SYNC_RETRIES, 0, 3); + tbl[idx++].data = &ipvs->sysctl_sync_retries; tbl[idx++].data = &ipvs->sysctl_nat_icmp_send; - ipvs->sysctl_hdr = register_net_sysctl_table(net, net_vs_ctl_path, - tbl); + ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl); if (ipvs->sysctl_hdr == NULL) { if (!net_eq(net, &init_net)) kfree(tbl); @@ -3680,7 +3742,7 @@ int __net_init ip_vs_control_net_init_sysctl(struct net *net) return 0; } -void __net_init ip_vs_control_net_cleanup_sysctl(struct net *net) +void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -3692,7 +3754,7 @@ void __net_init ip_vs_control_net_cleanup_sysctl(struct net *net) #else int __net_init ip_vs_control_net_init_sysctl(struct net *net) { return 0; } -void __net_init ip_vs_control_net_cleanup_sysctl(struct net *net) { } +void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) { } #endif @@ -3750,21 +3812,10 @@ void __net_exit ip_vs_control_net_cleanup(struct net *net) free_percpu(ipvs->tot_stats.cpustats); } -int __init ip_vs_control_init(void) +int __init ip_vs_register_nl_ioctl(void) { - int idx; int ret; - EnterFunction(2); - - /* Initialize svc_table, ip_vs_svc_fwm_table, rs_table */ - for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { - INIT_LIST_HEAD(&ip_vs_svc_table[idx]); - INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]); - } - - smp_wmb(); /* Do we really need it now ? */ - ret = nf_register_sockopt(&ip_vs_sockopts); if (ret) { pr_err("cannot register sockopt.\n"); @@ -3776,28 +3827,47 @@ int __init ip_vs_control_init(void) pr_err("cannot register Generic Netlink interface.\n"); goto err_genl; } - - ret = register_netdevice_notifier(&ip_vs_dst_notifier); - if (ret < 0) - goto err_notf; - - LeaveFunction(2); return 0; -err_notf: - ip_vs_genl_unregister(); err_genl: nf_unregister_sockopt(&ip_vs_sockopts); err_sock: return ret; } +void ip_vs_unregister_nl_ioctl(void) +{ + ip_vs_genl_unregister(); + nf_unregister_sockopt(&ip_vs_sockopts); +} + +int __init ip_vs_control_init(void) +{ + int idx; + int ret; + + EnterFunction(2); + + /* Initialize svc_table, ip_vs_svc_fwm_table, rs_table */ + for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { + INIT_LIST_HEAD(&ip_vs_svc_table[idx]); + INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]); + } + + smp_wmb(); /* Do we really need it now ? */ + + ret = register_netdevice_notifier(&ip_vs_dst_notifier); + if (ret < 0) + return ret; + + LeaveFunction(2); + return 0; +} + void ip_vs_control_cleanup(void) { EnterFunction(2); unregister_netdevice_notifier(&ip_vs_dst_notifier); - ip_vs_genl_unregister(); - nf_unregister_sockopt(&ip_vs_sockopts); LeaveFunction(2); } diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c index 1c269e56200..8b7dca9ea42 100644 --- a/net/netfilter/ipvs/ip_vs_dh.c +++ b/net/netfilter/ipvs/ip_vs_dh.c @@ -68,7 +68,7 @@ struct ip_vs_dh_bucket { /* * Returns hash value for IPVS DH entry */ -static inline unsigned ip_vs_dh_hashkey(int af, const union nf_inet_addr *addr) +static inline unsigned int ip_vs_dh_hashkey(int af, const union nf_inet_addr *addr) { __be32 addr_fold = addr->ip; @@ -149,7 +149,7 @@ static int ip_vs_dh_init_svc(struct ip_vs_service *svc) /* allocate the DH table for this service */ tbl = kmalloc(sizeof(struct ip_vs_dh_bucket)*IP_VS_DH_TAB_SIZE, - GFP_ATOMIC); + GFP_KERNEL); if (tbl == NULL) return -ENOMEM; diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 538d74ee4f6..b20b29c903e 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -177,7 +177,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, __be16 port; struct ip_vs_conn *n_cp; char buf[24]; /* xxx.xxx.xxx.xxx,ppp,ppp\000 */ - unsigned buf_len; + unsigned int buf_len; int ret = 0; enum ip_conntrack_info ctinfo; struct nf_conn *ct; @@ -439,6 +439,8 @@ static int __net_init __ip_vs_ftp_init(struct net *net) struct ip_vs_app *app; struct netns_ipvs *ipvs = net_ipvs(net); + if (!ipvs) + return -ENOENT; app = kmemdup(&ip_vs_ftp, sizeof(struct ip_vs_app), GFP_KERNEL); if (!app) return -ENOMEM; @@ -483,7 +485,7 @@ static struct pernet_operations ip_vs_ftp_ops = { .exit = __ip_vs_ftp_exit, }; -int __init ip_vs_ftp_init(void) +static int __init ip_vs_ftp_init(void) { int rv; diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 0f16283fd05..df646ccf08a 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -142,7 +142,7 @@ static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en) /* * Returns hash value for IPVS LBLC entry */ -static inline unsigned +static inline unsigned int ip_vs_lblc_hashkey(int af, const union nf_inet_addr *addr) { __be32 addr_fold = addr->ip; @@ -163,7 +163,7 @@ ip_vs_lblc_hashkey(int af, const union nf_inet_addr *addr) static void ip_vs_lblc_hash(struct ip_vs_lblc_table *tbl, struct ip_vs_lblc_entry *en) { - unsigned hash = ip_vs_lblc_hashkey(en->af, &en->addr); + unsigned int hash = ip_vs_lblc_hashkey(en->af, &en->addr); list_add(&en->list, &tbl->bucket[hash]); atomic_inc(&tbl->entries); @@ -178,7 +178,7 @@ static inline struct ip_vs_lblc_entry * ip_vs_lblc_get(int af, struct ip_vs_lblc_table *tbl, const union nf_inet_addr *addr) { - unsigned hash = ip_vs_lblc_hashkey(af, addr); + unsigned int hash = ip_vs_lblc_hashkey(af, addr); struct ip_vs_lblc_entry *en; list_for_each_entry(en, &tbl->bucket[hash], list) @@ -342,7 +342,7 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc) /* * Allocate the ip_vs_lblc_table for this service */ - tbl = kmalloc(sizeof(*tbl), GFP_ATOMIC); + tbl = kmalloc(sizeof(*tbl), GFP_KERNEL); if (tbl == NULL) return -ENOMEM; @@ -551,6 +551,9 @@ static int __net_init __ip_vs_lblc_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); + if (!ipvs) + return -ENOENT; + if (!net_eq(net, &init_net)) { ipvs->lblc_ctl_table = kmemdup(vs_vars_table, sizeof(vs_vars_table), @@ -563,8 +566,7 @@ static int __net_init __ip_vs_lblc_init(struct net *net) ipvs->lblc_ctl_table[0].data = &ipvs->sysctl_lblc_expiration; ipvs->lblc_ctl_header = - register_net_sysctl_table(net, net_vs_ctl_path, - ipvs->lblc_ctl_table); + register_net_sysctl(net, "net/ipv4/vs", ipvs->lblc_ctl_table); if (!ipvs->lblc_ctl_header) { if (!net_eq(net, &init_net)) kfree(ipvs->lblc_ctl_table); diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index eec797f8cce..570e31ea427 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -311,7 +311,7 @@ static inline void ip_vs_lblcr_free(struct ip_vs_lblcr_entry *en) /* * Returns hash value for IPVS LBLCR entry */ -static inline unsigned +static inline unsigned int ip_vs_lblcr_hashkey(int af, const union nf_inet_addr *addr) { __be32 addr_fold = addr->ip; @@ -332,7 +332,7 @@ ip_vs_lblcr_hashkey(int af, const union nf_inet_addr *addr) static void ip_vs_lblcr_hash(struct ip_vs_lblcr_table *tbl, struct ip_vs_lblcr_entry *en) { - unsigned hash = ip_vs_lblcr_hashkey(en->af, &en->addr); + unsigned int hash = ip_vs_lblcr_hashkey(en->af, &en->addr); list_add(&en->list, &tbl->bucket[hash]); atomic_inc(&tbl->entries); @@ -347,7 +347,7 @@ static inline struct ip_vs_lblcr_entry * ip_vs_lblcr_get(int af, struct ip_vs_lblcr_table *tbl, const union nf_inet_addr *addr) { - unsigned hash = ip_vs_lblcr_hashkey(af, addr); + unsigned int hash = ip_vs_lblcr_hashkey(af, addr); struct ip_vs_lblcr_entry *en; list_for_each_entry(en, &tbl->bucket[hash], list) @@ -511,7 +511,7 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc) /* * Allocate the ip_vs_lblcr_table for this service */ - tbl = kmalloc(sizeof(*tbl), GFP_ATOMIC); + tbl = kmalloc(sizeof(*tbl), GFP_KERNEL); if (tbl == NULL) return -ENOMEM; @@ -745,6 +745,9 @@ static int __net_init __ip_vs_lblcr_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); + if (!ipvs) + return -ENOENT; + if (!net_eq(net, &init_net)) { ipvs->lblcr_ctl_table = kmemdup(vs_vars_table, sizeof(vs_vars_table), @@ -757,8 +760,7 @@ static int __net_init __ip_vs_lblcr_init(struct net *net) ipvs->lblcr_ctl_table[0].data = &ipvs->sysctl_lblcr_expiration; ipvs->lblcr_ctl_header = - register_net_sysctl_table(net, net_vs_ctl_path, - ipvs->lblcr_ctl_table); + register_net_sysctl(net, "net/ipv4/vs", ipvs->lblcr_ctl_table); if (!ipvs->lblcr_ctl_header) { if (!net_eq(net, &init_net)) kfree(ipvs->lblcr_ctl_table); diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index f843a883325..50d82186da8 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -48,7 +48,7 @@ static struct ip_vs_protocol *ip_vs_proto_table[IP_VS_PROTO_TAB_SIZE]; */ static int __used __init register_ip_vs_protocol(struct ip_vs_protocol *pp) { - unsigned hash = IP_VS_PROTO_HASH(pp->protocol); + unsigned int hash = IP_VS_PROTO_HASH(pp->protocol); pp->next = ip_vs_proto_table[hash]; ip_vs_proto_table[hash] = pp; @@ -59,9 +59,6 @@ static int __used __init register_ip_vs_protocol(struct ip_vs_protocol *pp) return 0; } -#if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP) || \ - defined(CONFIG_IP_VS_PROTO_SCTP) || defined(CONFIG_IP_VS_PROTO_AH) || \ - defined(CONFIG_IP_VS_PROTO_ESP) /* * register an ipvs protocols netns related data */ @@ -69,9 +66,9 @@ static int register_ip_vs_proto_netns(struct net *net, struct ip_vs_protocol *pp) { struct netns_ipvs *ipvs = net_ipvs(net); - unsigned hash = IP_VS_PROTO_HASH(pp->protocol); + unsigned int hash = IP_VS_PROTO_HASH(pp->protocol); struct ip_vs_proto_data *pd = - kzalloc(sizeof(struct ip_vs_proto_data), GFP_ATOMIC); + kzalloc(sizeof(struct ip_vs_proto_data), GFP_KERNEL); if (!pd) return -ENOMEM; @@ -81,12 +78,18 @@ register_ip_vs_proto_netns(struct net *net, struct ip_vs_protocol *pp) ipvs->proto_data_table[hash] = pd; atomic_set(&pd->appcnt, 0); /* Init app counter */ - if (pp->init_netns != NULL) - pp->init_netns(net, pd); + if (pp->init_netns != NULL) { + int ret = pp->init_netns(net, pd); + if (ret) { + /* unlink an free proto data */ + ipvs->proto_data_table[hash] = pd->next; + kfree(pd); + return ret; + } + } return 0; } -#endif /* * unregister an ipvs protocol @@ -94,7 +97,7 @@ register_ip_vs_proto_netns(struct net *net, struct ip_vs_protocol *pp) static int unregister_ip_vs_protocol(struct ip_vs_protocol *pp) { struct ip_vs_protocol **pp_p; - unsigned hash = IP_VS_PROTO_HASH(pp->protocol); + unsigned int hash = IP_VS_PROTO_HASH(pp->protocol); pp_p = &ip_vs_proto_table[hash]; for (; *pp_p; pp_p = &(*pp_p)->next) { @@ -117,7 +120,7 @@ unregister_ip_vs_proto_netns(struct net *net, struct ip_vs_proto_data *pd) { struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_proto_data **pd_p; - unsigned hash = IP_VS_PROTO_HASH(pd->pp->protocol); + unsigned int hash = IP_VS_PROTO_HASH(pd->pp->protocol); pd_p = &ipvs->proto_data_table[hash]; for (; *pd_p; pd_p = &(*pd_p)->next) { @@ -139,7 +142,7 @@ unregister_ip_vs_proto_netns(struct net *net, struct ip_vs_proto_data *pd) struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto) { struct ip_vs_protocol *pp; - unsigned hash = IP_VS_PROTO_HASH(proto); + unsigned int hash = IP_VS_PROTO_HASH(proto); for (pp = ip_vs_proto_table[hash]; pp; pp = pp->next) { if (pp->protocol == proto) @@ -153,11 +156,11 @@ EXPORT_SYMBOL(ip_vs_proto_get); /* * get ip_vs_protocol object data by netns and proto */ -struct ip_vs_proto_data * +static struct ip_vs_proto_data * __ipvs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto) { struct ip_vs_proto_data *pd; - unsigned hash = IP_VS_PROTO_HASH(proto); + unsigned int hash = IP_VS_PROTO_HASH(proto); for (pd = ipvs->proto_data_table[hash]; pd; pd = pd->next) { if (pd->pp->protocol == proto) @@ -196,7 +199,7 @@ void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags) int * ip_vs_create_timeout_table(int *table, int size) { - return kmemdup(table, size, GFP_ATOMIC); + return kmemdup(table, size, GFP_KERNEL); } @@ -316,22 +319,35 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp, */ int __net_init ip_vs_protocol_net_init(struct net *net) { + int i, ret; + static struct ip_vs_protocol *protos[] = { #ifdef CONFIG_IP_VS_PROTO_TCP - register_ip_vs_proto_netns(net, &ip_vs_protocol_tcp); + &ip_vs_protocol_tcp, #endif #ifdef CONFIG_IP_VS_PROTO_UDP - register_ip_vs_proto_netns(net, &ip_vs_protocol_udp); + &ip_vs_protocol_udp, #endif #ifdef CONFIG_IP_VS_PROTO_SCTP - register_ip_vs_proto_netns(net, &ip_vs_protocol_sctp); + &ip_vs_protocol_sctp, #endif #ifdef CONFIG_IP_VS_PROTO_AH - register_ip_vs_proto_netns(net, &ip_vs_protocol_ah); + &ip_vs_protocol_ah, #endif #ifdef CONFIG_IP_VS_PROTO_ESP - register_ip_vs_proto_netns(net, &ip_vs_protocol_esp); + &ip_vs_protocol_esp, #endif + }; + + for (i = 0; i < ARRAY_SIZE(protos); i++) { + ret = register_ip_vs_proto_netns(net, protos[i]); + if (ret < 0) + goto cleanup; + } return 0; + +cleanup: + ip_vs_protocol_net_cleanup(net); + return ret; } void __net_exit ip_vs_protocol_net_cleanup(struct net *net) diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 1fbf7a2816f..9f3fb751c49 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -1090,7 +1090,7 @@ out: * timeouts is netns related now. * --------------------------------------------- */ -static void __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd) +static int __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -1098,6 +1098,9 @@ static void __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd) spin_lock_init(&ipvs->sctp_app_lock); pd->timeout_table = ip_vs_create_timeout_table((int *)sctp_timeouts, sizeof(sctp_timeouts)); + if (!pd->timeout_table) + return -ENOMEM; + return 0; } static void __ip_vs_sctp_exit(struct net *net, struct ip_vs_proto_data *pd) diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index ef8641f7af8..cd609cc6272 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -677,7 +677,7 @@ void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp) * timeouts is netns related now. * --------------------------------------------- */ -static void __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd) +static int __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -685,7 +685,10 @@ static void __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd) spin_lock_init(&ipvs->tcp_app_lock); pd->timeout_table = ip_vs_create_timeout_table((int *)tcp_timeouts, sizeof(tcp_timeouts)); + if (!pd->timeout_table) + return -ENOMEM; pd->tcp_state_table = tcp_states; + return 0; } static void __ip_vs_tcp_exit(struct net *net, struct ip_vs_proto_data *pd) diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index f4b7262896b..2fedb2dcb3d 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -467,7 +467,7 @@ udp_state_transition(struct ip_vs_conn *cp, int direction, cp->timeout = pd->timeout_table[IP_VS_UDP_S_NORMAL]; } -static void __udp_init(struct net *net, struct ip_vs_proto_data *pd) +static int __udp_init(struct net *net, struct ip_vs_proto_data *pd) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -475,6 +475,9 @@ static void __udp_init(struct net *net, struct ip_vs_proto_data *pd) spin_lock_init(&ipvs->udp_app_lock); pd->timeout_table = ip_vs_create_timeout_table((int *)udp_timeouts, sizeof(udp_timeouts)); + if (!pd->timeout_table) + return -ENOMEM; + return 0; } static void __udp_exit(struct net *net, struct ip_vs_proto_data *pd) diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c index 069e8d4d5c0..05126521743 100644 --- a/net/netfilter/ipvs/ip_vs_sh.c +++ b/net/netfilter/ipvs/ip_vs_sh.c @@ -70,7 +70,7 @@ struct ip_vs_sh_bucket { /* * Returns hash value for IPVS SH entry */ -static inline unsigned ip_vs_sh_hashkey(int af, const union nf_inet_addr *addr) +static inline unsigned int ip_vs_sh_hashkey(int af, const union nf_inet_addr *addr) { __be32 addr_fold = addr->ip; @@ -162,7 +162,7 @@ static int ip_vs_sh_init_svc(struct ip_vs_service *svc) /* allocate the SH table for this service */ tbl = kmalloc(sizeof(struct ip_vs_sh_bucket)*IP_VS_SH_TAB_SIZE, - GFP_ATOMIC); + GFP_KERNEL); if (tbl == NULL) return -ENOMEM; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 8a0d6d6889f..effa10c9e4e 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -196,6 +196,7 @@ struct ip_vs_sync_thread_data { struct net *net; struct socket *sock; char *buf; + int id; }; /* Version 0 definition of packet sizes */ @@ -271,13 +272,6 @@ struct ip_vs_sync_buff { unsigned char *end; }; -/* multicast addr */ -static struct sockaddr_in mcast_addr = { - .sin_family = AF_INET, - .sin_port = cpu_to_be16(IP_VS_SYNC_PORT), - .sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP), -}; - /* * Copy of struct ip_vs_seq * From unaligned network order to aligned host order @@ -300,18 +294,22 @@ static void hton_seq(struct ip_vs_seq *ho, struct ip_vs_seq *no) put_unaligned_be32(ho->previous_delta, &no->previous_delta); } -static inline struct ip_vs_sync_buff *sb_dequeue(struct netns_ipvs *ipvs) +static inline struct ip_vs_sync_buff * +sb_dequeue(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms) { struct ip_vs_sync_buff *sb; spin_lock_bh(&ipvs->sync_lock); - if (list_empty(&ipvs->sync_queue)) { + if (list_empty(&ms->sync_queue)) { sb = NULL; + __set_current_state(TASK_INTERRUPTIBLE); } else { - sb = list_entry(ipvs->sync_queue.next, - struct ip_vs_sync_buff, + sb = list_entry(ms->sync_queue.next, struct ip_vs_sync_buff, list); list_del(&sb->list); + ms->sync_queue_len--; + if (!ms->sync_queue_len) + ms->sync_queue_delay = 0; } spin_unlock_bh(&ipvs->sync_lock); @@ -334,7 +332,7 @@ ip_vs_sync_buff_create(struct netns_ipvs *ipvs) kfree(sb); return NULL; } - sb->mesg->reserved = 0; /* old nr_conns i.e. must be zeo now */ + sb->mesg->reserved = 0; /* old nr_conns i.e. must be zero now */ sb->mesg->version = SYNC_PROTO_VER; sb->mesg->syncid = ipvs->master_syncid; sb->mesg->size = sizeof(struct ip_vs_sync_mesg); @@ -353,14 +351,22 @@ static inline void ip_vs_sync_buff_release(struct ip_vs_sync_buff *sb) kfree(sb); } -static inline void sb_queue_tail(struct netns_ipvs *ipvs) +static inline void sb_queue_tail(struct netns_ipvs *ipvs, + struct ipvs_master_sync_state *ms) { - struct ip_vs_sync_buff *sb = ipvs->sync_buff; + struct ip_vs_sync_buff *sb = ms->sync_buff; spin_lock(&ipvs->sync_lock); - if (ipvs->sync_state & IP_VS_STATE_MASTER) - list_add_tail(&sb->list, &ipvs->sync_queue); - else + if (ipvs->sync_state & IP_VS_STATE_MASTER && + ms->sync_queue_len < sysctl_sync_qlen_max(ipvs)) { + if (!ms->sync_queue_len) + schedule_delayed_work(&ms->master_wakeup_work, + max(IPVS_SYNC_SEND_DELAY, 1)); + ms->sync_queue_len++; + list_add_tail(&sb->list, &ms->sync_queue); + if ((++ms->sync_queue_delay) == IPVS_SYNC_WAKEUP_RATE) + wake_up_process(ms->master_thread); + } else ip_vs_sync_buff_release(sb); spin_unlock(&ipvs->sync_lock); } @@ -370,49 +376,26 @@ static inline void sb_queue_tail(struct netns_ipvs *ipvs) * than the specified time or the specified time is zero. */ static inline struct ip_vs_sync_buff * -get_curr_sync_buff(struct netns_ipvs *ipvs, unsigned long time) +get_curr_sync_buff(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms, + unsigned long time) { struct ip_vs_sync_buff *sb; spin_lock_bh(&ipvs->sync_buff_lock); - if (ipvs->sync_buff && - time_after_eq(jiffies - ipvs->sync_buff->firstuse, time)) { - sb = ipvs->sync_buff; - ipvs->sync_buff = NULL; + sb = ms->sync_buff; + if (sb && time_after_eq(jiffies - sb->firstuse, time)) { + ms->sync_buff = NULL; + __set_current_state(TASK_RUNNING); } else sb = NULL; spin_unlock_bh(&ipvs->sync_buff_lock); return sb; } -/* - * Switch mode from sending version 0 or 1 - * - must handle sync_buf - */ -void ip_vs_sync_switch_mode(struct net *net, int mode) +static inline int +select_master_thread_id(struct netns_ipvs *ipvs, struct ip_vs_conn *cp) { - struct netns_ipvs *ipvs = net_ipvs(net); - - if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) - return; - if (mode == sysctl_sync_ver(ipvs) || !ipvs->sync_buff) - return; - - spin_lock_bh(&ipvs->sync_buff_lock); - /* Buffer empty ? then let buf_create do the job */ - if (ipvs->sync_buff->mesg->size <= sizeof(struct ip_vs_sync_mesg)) { - kfree(ipvs->sync_buff); - ipvs->sync_buff = NULL; - } else { - spin_lock_bh(&ipvs->sync_lock); - if (ipvs->sync_state & IP_VS_STATE_MASTER) - list_add_tail(&ipvs->sync_buff->list, - &ipvs->sync_queue); - else - ip_vs_sync_buff_release(ipvs->sync_buff); - spin_unlock_bh(&ipvs->sync_lock); - } - spin_unlock_bh(&ipvs->sync_buff_lock); + return ((long) cp >> (1 + ilog2(sizeof(*cp)))) & ipvs->threads_mask; } /* @@ -442,15 +425,101 @@ ip_vs_sync_buff_create_v0(struct netns_ipvs *ipvs) return sb; } +/* Check if conn should be synced. + * pkts: conn packets, use sysctl_sync_threshold to avoid packet check + * - (1) sync_refresh_period: reduce sync rate. Additionally, retry + * sync_retries times with period of sync_refresh_period/8 + * - (2) if both sync_refresh_period and sync_period are 0 send sync only + * for state changes or only once when pkts matches sync_threshold + * - (3) templates: rate can be reduced only with sync_refresh_period or + * with (2) + */ +static int ip_vs_sync_conn_needed(struct netns_ipvs *ipvs, + struct ip_vs_conn *cp, int pkts) +{ + unsigned long orig = ACCESS_ONCE(cp->sync_endtime); + unsigned long now = jiffies; + unsigned long n = (now + cp->timeout) & ~3UL; + unsigned int sync_refresh_period; + int sync_period; + int force; + + /* Check if we sync in current state */ + if (unlikely(cp->flags & IP_VS_CONN_F_TEMPLATE)) + force = 0; + else if (likely(cp->protocol == IPPROTO_TCP)) { + if (!((1 << cp->state) & + ((1 << IP_VS_TCP_S_ESTABLISHED) | + (1 << IP_VS_TCP_S_FIN_WAIT) | + (1 << IP_VS_TCP_S_CLOSE) | + (1 << IP_VS_TCP_S_CLOSE_WAIT) | + (1 << IP_VS_TCP_S_TIME_WAIT)))) + return 0; + force = cp->state != cp->old_state; + if (force && cp->state != IP_VS_TCP_S_ESTABLISHED) + goto set; + } else if (unlikely(cp->protocol == IPPROTO_SCTP)) { + if (!((1 << cp->state) & + ((1 << IP_VS_SCTP_S_ESTABLISHED) | + (1 << IP_VS_SCTP_S_CLOSED) | + (1 << IP_VS_SCTP_S_SHUT_ACK_CLI) | + (1 << IP_VS_SCTP_S_SHUT_ACK_SER)))) + return 0; + force = cp->state != cp->old_state; + if (force && cp->state != IP_VS_SCTP_S_ESTABLISHED) + goto set; + } else { + /* UDP or another protocol with single state */ + force = 0; + } + + sync_refresh_period = sysctl_sync_refresh_period(ipvs); + if (sync_refresh_period > 0) { + long diff = n - orig; + long min_diff = max(cp->timeout >> 1, 10UL * HZ); + + /* Avoid sync if difference is below sync_refresh_period + * and below the half timeout. + */ + if (abs(diff) < min_t(long, sync_refresh_period, min_diff)) { + int retries = orig & 3; + + if (retries >= sysctl_sync_retries(ipvs)) + return 0; + if (time_before(now, orig - cp->timeout + + (sync_refresh_period >> 3))) + return 0; + n |= retries + 1; + } + } + sync_period = sysctl_sync_period(ipvs); + if (sync_period > 0) { + if (!(cp->flags & IP_VS_CONN_F_TEMPLATE) && + pkts % sync_period != sysctl_sync_threshold(ipvs)) + return 0; + } else if (sync_refresh_period <= 0 && + pkts != sysctl_sync_threshold(ipvs)) + return 0; + +set: + cp->old_state = cp->state; + n = cmpxchg(&cp->sync_endtime, orig, n); + return n == orig || force; +} + /* * Version 0 , could be switched in by sys_ctl. * Add an ip_vs_conn information into the current sync_buff. */ -void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp) +static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp, + int pkts) { struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_sync_mesg_v0 *m; struct ip_vs_sync_conn_v0 *s; + struct ip_vs_sync_buff *buff; + struct ipvs_master_sync_state *ms; + int id; int len; if (unlikely(cp->af != AF_INET)) @@ -459,21 +528,41 @@ void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp) if (cp->flags & IP_VS_CONN_F_ONE_PACKET) return; + if (!ip_vs_sync_conn_needed(ipvs, cp, pkts)) + return; + spin_lock(&ipvs->sync_buff_lock); - if (!ipvs->sync_buff) { - ipvs->sync_buff = - ip_vs_sync_buff_create_v0(ipvs); - if (!ipvs->sync_buff) { + if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) { + spin_unlock(&ipvs->sync_buff_lock); + return; + } + + id = select_master_thread_id(ipvs, cp); + ms = &ipvs->ms[id]; + buff = ms->sync_buff; + if (buff) { + m = (struct ip_vs_sync_mesg_v0 *) buff->mesg; + /* Send buffer if it is for v1 */ + if (!m->nr_conns) { + sb_queue_tail(ipvs, ms); + ms->sync_buff = NULL; + buff = NULL; + } + } + if (!buff) { + buff = ip_vs_sync_buff_create_v0(ipvs); + if (!buff) { spin_unlock(&ipvs->sync_buff_lock); pr_err("ip_vs_sync_buff_create failed.\n"); return; } + ms->sync_buff = buff; } len = (cp->flags & IP_VS_CONN_F_SEQ_MASK) ? FULL_CONN_SIZE : SIMPLE_CONN_SIZE; - m = (struct ip_vs_sync_mesg_v0 *)ipvs->sync_buff->mesg; - s = (struct ip_vs_sync_conn_v0 *)ipvs->sync_buff->head; + m = (struct ip_vs_sync_mesg_v0 *) buff->mesg; + s = (struct ip_vs_sync_conn_v0 *) buff->head; /* copy members */ s->reserved = 0; @@ -494,18 +583,24 @@ void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp) m->nr_conns++; m->size += len; - ipvs->sync_buff->head += len; + buff->head += len; /* check if there is a space for next one */ - if (ipvs->sync_buff->head + FULL_CONN_SIZE > ipvs->sync_buff->end) { - sb_queue_tail(ipvs); - ipvs->sync_buff = NULL; + if (buff->head + FULL_CONN_SIZE > buff->end) { + sb_queue_tail(ipvs, ms); + ms->sync_buff = NULL; } spin_unlock(&ipvs->sync_buff_lock); /* synchronize its controller if it has */ - if (cp->control) - ip_vs_sync_conn(net, cp->control); + cp = cp->control; + if (cp) { + if (cp->flags & IP_VS_CONN_F_TEMPLATE) + pkts = atomic_add_return(1, &cp->in_pkts); + else + pkts = sysctl_sync_threshold(ipvs); + ip_vs_sync_conn(net, cp->control, pkts); + } } /* @@ -513,23 +608,29 @@ void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp) * Called by ip_vs_in. * Sending Version 1 messages */ -void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp) +void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts) { struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_sync_mesg *m; union ip_vs_sync_conn *s; + struct ip_vs_sync_buff *buff; + struct ipvs_master_sync_state *ms; + int id; __u8 *p; unsigned int len, pe_name_len, pad; /* Handle old version of the protocol */ if (sysctl_sync_ver(ipvs) == 0) { - ip_vs_sync_conn_v0(net, cp); + ip_vs_sync_conn_v0(net, cp, pkts); return; } /* Do not sync ONE PACKET */ if (cp->flags & IP_VS_CONN_F_ONE_PACKET) goto control; sloop: + if (!ip_vs_sync_conn_needed(ipvs, cp, pkts)) + goto control; + /* Sanity checks */ pe_name_len = 0; if (cp->pe_data_len) { @@ -541,6 +642,13 @@ sloop: } spin_lock(&ipvs->sync_buff_lock); + if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) { + spin_unlock(&ipvs->sync_buff_lock); + return; + } + + id = select_master_thread_id(ipvs, cp); + ms = &ipvs->ms[id]; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) @@ -559,27 +667,32 @@ sloop: /* check if there is a space for this one */ pad = 0; - if (ipvs->sync_buff) { - pad = (4 - (size_t)ipvs->sync_buff->head) & 3; - if (ipvs->sync_buff->head + len + pad > ipvs->sync_buff->end) { - sb_queue_tail(ipvs); - ipvs->sync_buff = NULL; + buff = ms->sync_buff; + if (buff) { + m = buff->mesg; + pad = (4 - (size_t) buff->head) & 3; + /* Send buffer if it is for v0 */ + if (buff->head + len + pad > buff->end || m->reserved) { + sb_queue_tail(ipvs, ms); + ms->sync_buff = NULL; + buff = NULL; pad = 0; } } - if (!ipvs->sync_buff) { - ipvs->sync_buff = ip_vs_sync_buff_create(ipvs); - if (!ipvs->sync_buff) { + if (!buff) { + buff = ip_vs_sync_buff_create(ipvs); + if (!buff) { spin_unlock(&ipvs->sync_buff_lock); pr_err("ip_vs_sync_buff_create failed.\n"); return; } + ms->sync_buff = buff; + m = buff->mesg; } - m = ipvs->sync_buff->mesg; - p = ipvs->sync_buff->head; - ipvs->sync_buff->head += pad + len; + p = buff->head; + buff->head += pad + len; m->size += pad + len; /* Add ev. padding from prev. sync_conn */ while (pad--) @@ -644,16 +757,10 @@ control: cp = cp->control; if (!cp) return; - /* - * Reduce sync rate for templates - * i.e only increment in_pkts for Templates. - */ - if (cp->flags & IP_VS_CONN_F_TEMPLATE) { - int pkts = atomic_add_return(1, &cp->in_pkts); - - if (pkts % sysctl_sync_period(ipvs) != 1) - return; - } + if (cp->flags & IP_VS_CONN_F_TEMPLATE) + pkts = atomic_add_return(1, &cp->in_pkts); + else + pkts = sysctl_sync_threshold(ipvs); goto sloop; } @@ -731,9 +838,32 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, else cp = ip_vs_ct_in_get(param); - if (cp && param->pe_data) /* Free pe_data */ + if (cp) { + /* Free pe_data */ kfree(param->pe_data); - if (!cp) { + + dest = cp->dest; + spin_lock(&cp->lock); + if ((cp->flags ^ flags) & IP_VS_CONN_F_INACTIVE && + !(flags & IP_VS_CONN_F_TEMPLATE) && dest) { + if (flags & IP_VS_CONN_F_INACTIVE) { + atomic_dec(&dest->activeconns); + atomic_inc(&dest->inactconns); + } else { + atomic_inc(&dest->activeconns); + atomic_dec(&dest->inactconns); + } + } + flags &= IP_VS_CONN_F_BACKUP_UPD_MASK; + flags |= cp->flags & ~IP_VS_CONN_F_BACKUP_UPD_MASK; + cp->flags = flags; + spin_unlock(&cp->lock); + if (!dest) { + dest = ip_vs_try_bind_dest(cp); + if (dest) + atomic_dec(&dest->refcnt); + } + } else { /* * Find the appropriate destination for the connection. * If it is not found the connection will remain unbound @@ -742,18 +872,6 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, dest = ip_vs_find_dest(net, type, daddr, dport, param->vaddr, param->vport, protocol, fwmark, flags); - /* Set the approprite ativity flag */ - if (protocol == IPPROTO_TCP) { - if (state != IP_VS_TCP_S_ESTABLISHED) - flags |= IP_VS_CONN_F_INACTIVE; - else - flags &= ~IP_VS_CONN_F_INACTIVE; - } else if (protocol == IPPROTO_SCTP) { - if (state != IP_VS_SCTP_S_ESTABLISHED) - flags |= IP_VS_CONN_F_INACTIVE; - else - flags &= ~IP_VS_CONN_F_INACTIVE; - } cp = ip_vs_conn_new(param, daddr, dport, flags, dest, fwmark); if (dest) atomic_dec(&dest->refcnt); @@ -763,34 +881,6 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, IP_VS_DBG(2, "BACKUP, add new conn. failed\n"); return; } - } else if (!cp->dest) { - dest = ip_vs_try_bind_dest(cp); - if (dest) - atomic_dec(&dest->refcnt); - } else if ((cp->dest) && (cp->protocol == IPPROTO_TCP) && - (cp->state != state)) { - /* update active/inactive flag for the connection */ - dest = cp->dest; - if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && - (state != IP_VS_TCP_S_ESTABLISHED)) { - atomic_dec(&dest->activeconns); - atomic_inc(&dest->inactconns); - cp->flags |= IP_VS_CONN_F_INACTIVE; - } else if ((cp->flags & IP_VS_CONN_F_INACTIVE) && - (state == IP_VS_TCP_S_ESTABLISHED)) { - atomic_inc(&dest->activeconns); - atomic_dec(&dest->inactconns); - cp->flags &= ~IP_VS_CONN_F_INACTIVE; - } - } else if ((cp->dest) && (cp->protocol == IPPROTO_SCTP) && - (cp->state != state)) { - dest = cp->dest; - if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && - (state != IP_VS_SCTP_S_ESTABLISHED)) { - atomic_dec(&dest->activeconns); - atomic_inc(&dest->inactconns); - cp->flags &= ~IP_VS_CONN_F_INACTIVE; - } } if (opt) @@ -839,7 +929,7 @@ static void ip_vs_process_message_v0(struct net *net, const char *buffer, p = (char *)buffer + sizeof(struct ip_vs_sync_mesg_v0); for (i=0; i<m->nr_conns; i++) { - unsigned flags, state; + unsigned int flags, state; if (p + SIMPLE_CONN_SIZE > buffer+buflen) { IP_VS_ERR_RL("BACKUP v0, bogus conn\n"); @@ -1109,7 +1199,7 @@ static void ip_vs_process_message(struct net *net, __u8 *buffer, for (i=0; i<nr_conns; i++) { union ip_vs_sync_conn *s; - unsigned size; + unsigned int size; int retc; p = msg_end; @@ -1149,6 +1239,28 @@ static void ip_vs_process_message(struct net *net, __u8 *buffer, /* + * Setup sndbuf (mode=1) or rcvbuf (mode=0) + */ +static void set_sock_size(struct sock *sk, int mode, int val) +{ + /* setsockopt(sock, SOL_SOCKET, SO_SNDBUF, &val, sizeof(val)); */ + /* setsockopt(sock, SOL_SOCKET, SO_RCVBUF, &val, sizeof(val)); */ + lock_sock(sk); + if (mode) { + val = clamp_t(int, val, (SOCK_MIN_SNDBUF + 1) / 2, + sysctl_wmem_max); + sk->sk_sndbuf = val * 2; + sk->sk_userlocks |= SOCK_SNDBUF_LOCK; + } else { + val = clamp_t(int, val, (SOCK_MIN_RCVBUF + 1) / 2, + sysctl_rmem_max); + sk->sk_rcvbuf = val * 2; + sk->sk_userlocks |= SOCK_RCVBUF_LOCK; + } + release_sock(sk); +} + +/* * Setup loopback of outgoing multicasts on a sending socket */ static void set_mcast_loop(struct sock *sk, u_char loop) @@ -1298,9 +1410,15 @@ static int bind_mcastif_addr(struct socket *sock, char *ifname) /* * Set up sending multicast socket over UDP */ -static struct socket *make_send_sock(struct net *net) +static struct socket *make_send_sock(struct net *net, int id) { struct netns_ipvs *ipvs = net_ipvs(net); + /* multicast addr */ + struct sockaddr_in mcast_addr = { + .sin_family = AF_INET, + .sin_port = cpu_to_be16(IP_VS_SYNC_PORT + id), + .sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP), + }; struct socket *sock; int result; @@ -1324,6 +1442,9 @@ static struct socket *make_send_sock(struct net *net) set_mcast_loop(sock->sk, 0); set_mcast_ttl(sock->sk, 1); + result = sysctl_sync_sock_size(ipvs); + if (result > 0) + set_sock_size(sock->sk, 1, result); result = bind_mcastif_addr(sock, ipvs->master_mcast_ifn); if (result < 0) { @@ -1349,9 +1470,15 @@ error: /* * Set up receiving multicast socket over UDP */ -static struct socket *make_receive_sock(struct net *net) +static struct socket *make_receive_sock(struct net *net, int id) { struct netns_ipvs *ipvs = net_ipvs(net); + /* multicast addr */ + struct sockaddr_in mcast_addr = { + .sin_family = AF_INET, + .sin_port = cpu_to_be16(IP_VS_SYNC_PORT + id), + .sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP), + }; struct socket *sock; int result; @@ -1368,7 +1495,10 @@ static struct socket *make_receive_sock(struct net *net) */ sk_change_net(sock->sk, net); /* it is equivalent to the REUSEADDR option in user-space */ - sock->sk->sk_reuse = 1; + sock->sk->sk_reuse = SK_CAN_REUSE; + result = sysctl_sync_sock_size(ipvs); + if (result > 0) + set_sock_size(sock->sk, 0, result); result = sock->ops->bind(sock, (struct sockaddr *) &mcast_addr, sizeof(struct sockaddr)); @@ -1411,18 +1541,22 @@ ip_vs_send_async(struct socket *sock, const char *buffer, const size_t length) return len; } -static void +static int ip_vs_send_sync_msg(struct socket *sock, struct ip_vs_sync_mesg *msg) { int msize; + int ret; msize = msg->size; /* Put size in network byte order */ msg->size = htons(msg->size); - if (ip_vs_send_async(sock, (char *)msg, msize) != msize) - pr_err("ip_vs_send_async error\n"); + ret = ip_vs_send_async(sock, (char *)msg, msize); + if (ret >= 0 || ret == -EAGAIN) + return ret; + pr_err("ip_vs_send_async error %d\n", ret); + return 0; } static int @@ -1438,48 +1572,90 @@ ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen) iov.iov_base = buffer; iov.iov_len = (size_t)buflen; - len = kernel_recvmsg(sock, &msg, &iov, 1, buflen, 0); + len = kernel_recvmsg(sock, &msg, &iov, 1, buflen, MSG_DONTWAIT); if (len < 0) - return -1; + return len; LeaveFunction(7); return len; } +/* Wakeup the master thread for sending */ +static void master_wakeup_work_handler(struct work_struct *work) +{ + struct ipvs_master_sync_state *ms = + container_of(work, struct ipvs_master_sync_state, + master_wakeup_work.work); + struct netns_ipvs *ipvs = ms->ipvs; + + spin_lock_bh(&ipvs->sync_lock); + if (ms->sync_queue_len && + ms->sync_queue_delay < IPVS_SYNC_WAKEUP_RATE) { + ms->sync_queue_delay = IPVS_SYNC_WAKEUP_RATE; + wake_up_process(ms->master_thread); + } + spin_unlock_bh(&ipvs->sync_lock); +} + +/* Get next buffer to send */ +static inline struct ip_vs_sync_buff * +next_sync_buff(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms) +{ + struct ip_vs_sync_buff *sb; + + sb = sb_dequeue(ipvs, ms); + if (sb) + return sb; + /* Do not delay entries in buffer for more than 2 seconds */ + return get_curr_sync_buff(ipvs, ms, IPVS_SYNC_FLUSH_TIME); +} static int sync_thread_master(void *data) { struct ip_vs_sync_thread_data *tinfo = data; struct netns_ipvs *ipvs = net_ipvs(tinfo->net); + struct ipvs_master_sync_state *ms = &ipvs->ms[tinfo->id]; + struct sock *sk = tinfo->sock->sk; struct ip_vs_sync_buff *sb; pr_info("sync thread started: state = MASTER, mcast_ifn = %s, " - "syncid = %d\n", - ipvs->master_mcast_ifn, ipvs->master_syncid); + "syncid = %d, id = %d\n", + ipvs->master_mcast_ifn, ipvs->master_syncid, tinfo->id); - while (!kthread_should_stop()) { - while ((sb = sb_dequeue(ipvs))) { - ip_vs_send_sync_msg(tinfo->sock, sb->mesg); - ip_vs_sync_buff_release(sb); + for (;;) { + sb = next_sync_buff(ipvs, ms); + if (unlikely(kthread_should_stop())) + break; + if (!sb) { + schedule_timeout(IPVS_SYNC_CHECK_PERIOD); + continue; } - - /* check if entries stay in ipvs->sync_buff for 2 seconds */ - sb = get_curr_sync_buff(ipvs, 2 * HZ); - if (sb) { - ip_vs_send_sync_msg(tinfo->sock, sb->mesg); - ip_vs_sync_buff_release(sb); + while (ip_vs_send_sync_msg(tinfo->sock, sb->mesg) < 0) { + int ret = 0; + + __wait_event_interruptible(*sk_sleep(sk), + sock_writeable(sk) || + kthread_should_stop(), + ret); + if (unlikely(kthread_should_stop())) + goto done; } - - schedule_timeout_interruptible(HZ); + ip_vs_sync_buff_release(sb); } +done: + __set_current_state(TASK_RUNNING); + if (sb) + ip_vs_sync_buff_release(sb); + /* clean up the sync_buff queue */ - while ((sb = sb_dequeue(ipvs))) + while ((sb = sb_dequeue(ipvs, ms))) ip_vs_sync_buff_release(sb); + __set_current_state(TASK_RUNNING); /* clean up the current sync_buff */ - sb = get_curr_sync_buff(ipvs, 0); + sb = get_curr_sync_buff(ipvs, ms, 0); if (sb) ip_vs_sync_buff_release(sb); @@ -1498,8 +1674,8 @@ static int sync_thread_backup(void *data) int len; pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, " - "syncid = %d\n", - ipvs->backup_mcast_ifn, ipvs->backup_syncid); + "syncid = %d, id = %d\n", + ipvs->backup_mcast_ifn, ipvs->backup_syncid, tinfo->id); while (!kthread_should_stop()) { wait_event_interruptible(*sk_sleep(tinfo->sock->sk), @@ -1511,7 +1687,8 @@ static int sync_thread_backup(void *data) len = ip_vs_receive(tinfo->sock, tinfo->buf, ipvs->recv_mesg_maxlen); if (len <= 0) { - pr_err("receiving message error\n"); + if (len != -EAGAIN) + pr_err("receiving message error\n"); break; } @@ -1535,86 +1712,140 @@ static int sync_thread_backup(void *data) int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid) { struct ip_vs_sync_thread_data *tinfo; - struct task_struct **realtask, *task; + struct task_struct **array = NULL, *task; struct socket *sock; struct netns_ipvs *ipvs = net_ipvs(net); - char *name, *buf = NULL; + char *name; int (*threadfn)(void *data); + int id, count; int result = -ENOMEM; IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current)); IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %Zd bytes\n", sizeof(struct ip_vs_sync_conn_v0)); + if (!ipvs->sync_state) { + count = clamp(sysctl_sync_ports(ipvs), 1, IPVS_SYNC_PORTS_MAX); + ipvs->threads_mask = count - 1; + } else + count = ipvs->threads_mask + 1; if (state == IP_VS_STATE_MASTER) { - if (ipvs->master_thread) + if (ipvs->ms) return -EEXIST; strlcpy(ipvs->master_mcast_ifn, mcast_ifn, sizeof(ipvs->master_mcast_ifn)); ipvs->master_syncid = syncid; - realtask = &ipvs->master_thread; - name = "ipvs_master:%d"; + name = "ipvs-m:%d:%d"; threadfn = sync_thread_master; - sock = make_send_sock(net); } else if (state == IP_VS_STATE_BACKUP) { - if (ipvs->backup_thread) + if (ipvs->backup_threads) return -EEXIST; strlcpy(ipvs->backup_mcast_ifn, mcast_ifn, sizeof(ipvs->backup_mcast_ifn)); ipvs->backup_syncid = syncid; - realtask = &ipvs->backup_thread; - name = "ipvs_backup:%d"; + name = "ipvs-b:%d:%d"; threadfn = sync_thread_backup; - sock = make_receive_sock(net); } else { return -EINVAL; } - if (IS_ERR(sock)) { - result = PTR_ERR(sock); - goto out; - } + if (state == IP_VS_STATE_MASTER) { + struct ipvs_master_sync_state *ms; - set_sync_mesg_maxlen(net, state); - if (state == IP_VS_STATE_BACKUP) { - buf = kmalloc(ipvs->recv_mesg_maxlen, GFP_KERNEL); - if (!buf) - goto outsocket; + ipvs->ms = kzalloc(count * sizeof(ipvs->ms[0]), GFP_KERNEL); + if (!ipvs->ms) + goto out; + ms = ipvs->ms; + for (id = 0; id < count; id++, ms++) { + INIT_LIST_HEAD(&ms->sync_queue); + ms->sync_queue_len = 0; + ms->sync_queue_delay = 0; + INIT_DELAYED_WORK(&ms->master_wakeup_work, + master_wakeup_work_handler); + ms->ipvs = ipvs; + } + } else { + array = kzalloc(count * sizeof(struct task_struct *), + GFP_KERNEL); + if (!array) + goto out; } + set_sync_mesg_maxlen(net, state); - tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL); - if (!tinfo) - goto outbuf; - - tinfo->net = net; - tinfo->sock = sock; - tinfo->buf = buf; + tinfo = NULL; + for (id = 0; id < count; id++) { + if (state == IP_VS_STATE_MASTER) + sock = make_send_sock(net, id); + else + sock = make_receive_sock(net, id); + if (IS_ERR(sock)) { + result = PTR_ERR(sock); + goto outtinfo; + } + tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL); + if (!tinfo) + goto outsocket; + tinfo->net = net; + tinfo->sock = sock; + if (state == IP_VS_STATE_BACKUP) { + tinfo->buf = kmalloc(ipvs->recv_mesg_maxlen, + GFP_KERNEL); + if (!tinfo->buf) + goto outtinfo; + } + tinfo->id = id; - task = kthread_run(threadfn, tinfo, name, ipvs->gen); - if (IS_ERR(task)) { - result = PTR_ERR(task); - goto outtinfo; + task = kthread_run(threadfn, tinfo, name, ipvs->gen, id); + if (IS_ERR(task)) { + result = PTR_ERR(task); + goto outtinfo; + } + tinfo = NULL; + if (state == IP_VS_STATE_MASTER) + ipvs->ms[id].master_thread = task; + else + array[id] = task; } /* mark as active */ - *realtask = task; + + if (state == IP_VS_STATE_BACKUP) + ipvs->backup_threads = array; + spin_lock_bh(&ipvs->sync_buff_lock); ipvs->sync_state |= state; + spin_unlock_bh(&ipvs->sync_buff_lock); /* increase the module use count */ ip_vs_use_count_inc(); return 0; -outtinfo: - kfree(tinfo); -outbuf: - kfree(buf); outsocket: sk_release_kernel(sock->sk); + +outtinfo: + if (tinfo) { + sk_release_kernel(tinfo->sock->sk); + kfree(tinfo->buf); + kfree(tinfo); + } + count = id; + while (count-- > 0) { + if (state == IP_VS_STATE_MASTER) + kthread_stop(ipvs->ms[count].master_thread); + else + kthread_stop(array[count]); + } + kfree(array); + out: + if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) { + kfree(ipvs->ms); + ipvs->ms = NULL; + } return result; } @@ -1622,38 +1853,60 @@ out: int stop_sync_thread(struct net *net, int state) { struct netns_ipvs *ipvs = net_ipvs(net); + struct task_struct **array; + int id; int retc = -EINVAL; IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current)); if (state == IP_VS_STATE_MASTER) { - if (!ipvs->master_thread) + if (!ipvs->ms) return -ESRCH; - pr_info("stopping master sync thread %d ...\n", - task_pid_nr(ipvs->master_thread)); - /* * The lock synchronizes with sb_queue_tail(), so that we don't * add sync buffers to the queue, when we are already in * progress of stopping the master sync daemon. */ - spin_lock_bh(&ipvs->sync_lock); + spin_lock_bh(&ipvs->sync_buff_lock); + spin_lock(&ipvs->sync_lock); ipvs->sync_state &= ~IP_VS_STATE_MASTER; - spin_unlock_bh(&ipvs->sync_lock); - retc = kthread_stop(ipvs->master_thread); - ipvs->master_thread = NULL; + spin_unlock(&ipvs->sync_lock); + spin_unlock_bh(&ipvs->sync_buff_lock); + + retc = 0; + for (id = ipvs->threads_mask; id >= 0; id--) { + struct ipvs_master_sync_state *ms = &ipvs->ms[id]; + int ret; + + pr_info("stopping master sync thread %d ...\n", + task_pid_nr(ms->master_thread)); + cancel_delayed_work_sync(&ms->master_wakeup_work); + ret = kthread_stop(ms->master_thread); + if (retc >= 0) + retc = ret; + } + kfree(ipvs->ms); + ipvs->ms = NULL; } else if (state == IP_VS_STATE_BACKUP) { - if (!ipvs->backup_thread) + if (!ipvs->backup_threads) return -ESRCH; - pr_info("stopping backup sync thread %d ...\n", - task_pid_nr(ipvs->backup_thread)); - ipvs->sync_state &= ~IP_VS_STATE_BACKUP; - retc = kthread_stop(ipvs->backup_thread); - ipvs->backup_thread = NULL; + array = ipvs->backup_threads; + retc = 0; + for (id = ipvs->threads_mask; id >= 0; id--) { + int ret; + + pr_info("stopping backup sync thread %d ...\n", + task_pid_nr(array[id])); + ret = kthread_stop(array[id]); + if (retc >= 0) + retc = ret; + } + kfree(array); + ipvs->backup_threads = NULL; } /* decrease the module use count */ @@ -1670,13 +1923,8 @@ int __net_init ip_vs_sync_net_init(struct net *net) struct netns_ipvs *ipvs = net_ipvs(net); __mutex_init(&ipvs->sync_mutex, "ipvs->sync_mutex", &__ipvs_sync_key); - INIT_LIST_HEAD(&ipvs->sync_queue); spin_lock_init(&ipvs->sync_lock); spin_lock_init(&ipvs->sync_buff_lock); - - ipvs->sync_mcast_addr.sin_family = AF_INET; - ipvs->sync_mcast_addr.sin_port = cpu_to_be16(IP_VS_SYNC_PORT); - ipvs->sync_mcast_addr.sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP); return 0; } diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c index fd0d4e09876..231be7dd547 100644 --- a/net/netfilter/ipvs/ip_vs_wrr.c +++ b/net/netfilter/ipvs/ip_vs_wrr.c @@ -84,7 +84,7 @@ static int ip_vs_wrr_init_svc(struct ip_vs_service *svc) /* * Allocate the mark variable for WRR scheduling */ - mark = kmalloc(sizeof(struct ip_vs_wrr_mark), GFP_ATOMIC); + mark = kmalloc(sizeof(struct ip_vs_wrr_mark), GFP_KERNEL); if (mark == NULL) return -ENOMEM; diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c index f4f8cda0598..d61e0782a79 100644 --- a/net/netfilter/nf_conntrack_acct.c +++ b/net/netfilter/nf_conntrack_acct.c @@ -69,8 +69,8 @@ static int nf_conntrack_acct_init_sysctl(struct net *net) table[0].data = &net->ct.sysctl_acct; - net->ct.acct_sysctl_header = register_net_sysctl_table(net, - nf_net_netfilter_sysctl_path, table); + net->ct.acct_sysctl_header = register_net_sysctl(net, "net/netfilter", + table); if (!net->ct.acct_sysctl_header) { printk(KERN_ERR "nf_conntrack_acct: can't register to sysctl.\n"); goto out_register; diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c index 13fd2c55e32..f2de8c55ac5 100644 --- a/net/netfilter/nf_conntrack_amanda.c +++ b/net/netfilter/nf_conntrack_amanda.c @@ -107,8 +107,7 @@ static int amanda_help(struct sk_buff *skb, /* No data? */ dataoff = protoff + sizeof(struct udphdr); if (dataoff >= skb->len) { - if (net_ratelimit()) - printk(KERN_ERR "amanda_help: skblen = %u\n", skb->len); + net_err_ratelimited("amanda_help: skblen = %u\n", skb->len); return NF_ACCEPT; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index cbdb754dbb1..ac3af97cc46 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -683,10 +683,7 @@ __nf_conntrack_alloc(struct net *net, u16 zone, unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) { if (!early_drop(net, hash_bucket(hash, net))) { atomic_dec(&net->ct.count); - if (net_ratelimit()) - printk(KERN_WARNING - "nf_conntrack: table full, dropping" - " packet.\n"); + net_warn_ratelimited("nf_conntrack: table full, dropping packet\n"); return ERR_PTR(-ENOMEM); } } @@ -735,6 +732,7 @@ __nf_conntrack_alloc(struct net *net, u16 zone, #ifdef CONFIG_NF_CONNTRACK_ZONES out_free: + atomic_dec(&net->ct.count); kmem_cache_free(net->ct.nf_conntrack_cachep, ct); return ERR_PTR(-ENOMEM); #endif @@ -1151,8 +1149,9 @@ static struct nf_ct_ext_type nf_ct_zone_extend __read_mostly = { int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { - NLA_PUT_BE16(skb, CTA_PROTO_SRC_PORT, tuple->src.u.tcp.port); - NLA_PUT_BE16(skb, CTA_PROTO_DST_PORT, tuple->dst.u.tcp.port); + if (nla_put_be16(skb, CTA_PROTO_SRC_PORT, tuple->src.u.tcp.port) || + nla_put_be16(skb, CTA_PROTO_DST_PORT, tuple->dst.u.tcp.port)) + goto nla_put_failure; return 0; nla_put_failure: @@ -1334,7 +1333,6 @@ static void nf_conntrack_cleanup_init_net(void) while (untrack_refs() > 0) schedule(); - nf_conntrack_helper_fini(); nf_conntrack_proto_fini(); #ifdef CONFIG_NF_CONNTRACK_ZONES nf_ct_extend_unregister(&nf_ct_zone_extend); @@ -1352,6 +1350,7 @@ static void nf_conntrack_cleanup_net(struct net *net) } nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size); + nf_conntrack_helper_fini(net); nf_conntrack_timeout_fini(net); nf_conntrack_ecache_fini(net); nf_conntrack_tstamp_fini(net); @@ -1502,10 +1501,6 @@ static int nf_conntrack_init_init_net(void) if (ret < 0) goto err_proto; - ret = nf_conntrack_helper_init(); - if (ret < 0) - goto err_helper; - #ifdef CONFIG_NF_CONNTRACK_ZONES ret = nf_ct_extend_register(&nf_ct_zone_extend); if (ret < 0) @@ -1523,10 +1518,8 @@ static int nf_conntrack_init_init_net(void) #ifdef CONFIG_NF_CONNTRACK_ZONES err_extend: - nf_conntrack_helper_fini(); -#endif -err_helper: nf_conntrack_proto_fini(); +#endif err_proto: return ret; } @@ -1587,11 +1580,16 @@ static int nf_conntrack_init_net(struct net *net) ret = nf_conntrack_timeout_init(net); if (ret < 0) goto err_timeout; + ret = nf_conntrack_helper_init(net); + if (ret < 0) + goto err_helper; return 0; -err_timeout: +err_helper: nf_conntrack_timeout_fini(net); +err_timeout: + nf_conntrack_ecache_fini(net); err_ecache: nf_conntrack_tstamp_fini(net); err_tstamp: diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 5bd3047ddee..e7be79e640d 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -84,7 +84,7 @@ EXPORT_SYMBOL_GPL(nf_ct_deliver_cached_events); int nf_conntrack_register_notifier(struct net *net, struct nf_ct_event_notifier *new) { - int ret = 0; + int ret; struct nf_ct_event_notifier *notify; mutex_lock(&nf_ct_ecache_mutex); @@ -95,8 +95,7 @@ int nf_conntrack_register_notifier(struct net *net, goto out_unlock; } rcu_assign_pointer(net->ct.nf_conntrack_event_cb, new); - mutex_unlock(&nf_ct_ecache_mutex); - return ret; + ret = 0; out_unlock: mutex_unlock(&nf_ct_ecache_mutex); @@ -121,7 +120,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier); int nf_ct_expect_register_notifier(struct net *net, struct nf_exp_event_notifier *new) { - int ret = 0; + int ret; struct nf_exp_event_notifier *notify; mutex_lock(&nf_ct_ecache_mutex); @@ -132,8 +131,7 @@ int nf_ct_expect_register_notifier(struct net *net, goto out_unlock; } rcu_assign_pointer(net->ct.nf_expect_event_cb, new); - mutex_unlock(&nf_ct_ecache_mutex); - return ret; + ret = 0; out_unlock: mutex_unlock(&nf_ct_ecache_mutex); @@ -199,8 +197,7 @@ static int nf_conntrack_event_init_sysctl(struct net *net) table[1].data = &net->ct.sysctl_events_retry_timeout; net->ct.event_sysctl_header = - register_net_sysctl_table(net, - nf_net_netfilter_sysctl_path, table); + register_net_sysctl(net, "net/netfilter", table); if (!net->ct.event_sysctl_header) { printk(KERN_ERR "nf_ct_event: can't register to sysctl.\n"); goto out_register; diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 4147ba3f653..45cf602a76b 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -424,9 +424,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) } if (net->ct.expect_count >= nf_ct_expect_max) { - if (net_ratelimit()) - printk(KERN_WARNING - "nf_conntrack: expectation table full\n"); + net_warn_ratelimited("nf_conntrack: expectation table full\n"); ret = -EMFILE; } out: diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 722291f8af7..46d69d7f1bb 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -605,8 +605,7 @@ static int h245_help(struct sk_buff *skb, unsigned int protoff, drop: spin_unlock_bh(&nf_h323_lock); - if (net_ratelimit()) - pr_info("nf_ct_h245: packet dropped\n"); + net_info_ratelimited("nf_ct_h245: packet dropped\n"); return NF_DROP; } @@ -1156,8 +1155,7 @@ static int q931_help(struct sk_buff *skb, unsigned int protoff, drop: spin_unlock_bh(&nf_h323_lock); - if (net_ratelimit()) - pr_info("nf_ct_q931: packet dropped\n"); + net_info_ratelimited("nf_ct_q931: packet dropped\n"); return NF_DROP; } @@ -1230,7 +1228,7 @@ static struct nf_conntrack_expect *find_expect(struct nf_conn *ct, /****************************************************************************/ static int set_expect_timeout(struct nf_conntrack_expect *exp, - unsigned timeout) + unsigned int timeout) { if (!exp || !del_timer(&exp->timeout)) return 0; @@ -1731,8 +1729,7 @@ static int ras_help(struct sk_buff *skb, unsigned int protoff, drop: spin_unlock_bh(&nf_h323_lock); - if (net_ratelimit()) - pr_info("nf_ct_ras: packet dropped\n"); + net_info_ratelimited("nf_ct_ras: packet dropped\n"); return NF_DROP; } @@ -1833,4 +1830,6 @@ MODULE_AUTHOR("Jing Min Zhao <zhaojingmin@users.sourceforge.net>"); MODULE_DESCRIPTION("H.323 connection tracking helper"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ip_conntrack_h323"); -MODULE_ALIAS_NFCT_HELPER("h323"); +MODULE_ALIAS_NFCT_HELPER("RAS"); +MODULE_ALIAS_NFCT_HELPER("Q.931"); +MODULE_ALIAS_NFCT_HELPER("H.245"); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 436b7cb79ba..4fa2ff961f5 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -34,6 +34,67 @@ static struct hlist_head *nf_ct_helper_hash __read_mostly; static unsigned int nf_ct_helper_hsize __read_mostly; static unsigned int nf_ct_helper_count __read_mostly; +static bool nf_ct_auto_assign_helper __read_mostly = true; +module_param_named(nf_conntrack_helper, nf_ct_auto_assign_helper, bool, 0644); +MODULE_PARM_DESC(nf_conntrack_helper, + "Enable automatic conntrack helper assignment (default 1)"); + +#ifdef CONFIG_SYSCTL +static struct ctl_table helper_sysctl_table[] = { + { + .procname = "nf_conntrack_helper", + .data = &init_net.ct.sysctl_auto_assign_helper, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + {} +}; + +static int nf_conntrack_helper_init_sysctl(struct net *net) +{ + struct ctl_table *table; + + table = kmemdup(helper_sysctl_table, sizeof(helper_sysctl_table), + GFP_KERNEL); + if (!table) + goto out; + + table[0].data = &net->ct.sysctl_auto_assign_helper; + + net->ct.helper_sysctl_header = + register_net_sysctl(net, "net/netfilter", table); + + if (!net->ct.helper_sysctl_header) { + pr_err("nf_conntrack_helper: can't register to sysctl.\n"); + goto out_register; + } + return 0; + +out_register: + kfree(table); +out: + return -ENOMEM; +} + +static void nf_conntrack_helper_fini_sysctl(struct net *net) +{ + struct ctl_table *table; + + table = net->ct.helper_sysctl_header->ctl_table_arg; + unregister_net_sysctl_table(net->ct.helper_sysctl_header); + kfree(table); +} +#else +static int nf_conntrack_helper_init_sysctl(struct net *net) +{ + return 0; +} + +static void nf_conntrack_helper_fini_sysctl(struct net *net) +{ +} +#endif /* CONFIG_SYSCTL */ /* Stupid hash, but collision free for the default registrations of the * helpers currently in the kernel. */ @@ -118,17 +179,38 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, { struct nf_conntrack_helper *helper = NULL; struct nf_conn_help *help; + struct net *net = nf_ct_net(ct); int ret = 0; + /* We already got a helper explicitly attached. The function + * nf_conntrack_alter_reply - in case NAT is in use - asks for looking + * the helper up again. Since now the user is in full control of + * making consistent helper configurations, skip this automatic + * re-lookup, otherwise we'll lose the helper. + */ + if (test_bit(IPS_HELPER_BIT, &ct->status)) + return 0; + if (tmpl != NULL) { help = nfct_help(tmpl); - if (help != NULL) + if (help != NULL) { helper = help->helper; + set_bit(IPS_HELPER_BIT, &ct->status); + } } help = nfct_help(ct); - if (helper == NULL) + if (net->ct.sysctl_auto_assign_helper && helper == NULL) { helper = __nf_ct_helper_find(&ct->tuplehash[IP_CT_DIR_REPLY].tuple); + if (unlikely(!net->ct.auto_assign_helper_warned && helper)) { + pr_info("nf_conntrack: automatic helper " + "assignment is deprecated and it will " + "be removed soon. Use the iptables CT target " + "to attach helpers instead.\n"); + net->ct.auto_assign_helper_warned = true; + } + } + if (helper == NULL) { if (help) RCU_INIT_POINTER(help->helper, NULL); @@ -315,28 +397,44 @@ static struct nf_ct_ext_type helper_extend __read_mostly = { .id = NF_CT_EXT_HELPER, }; -int nf_conntrack_helper_init(void) +int nf_conntrack_helper_init(struct net *net) { int err; - nf_ct_helper_hsize = 1; /* gets rounded up to use one page */ - nf_ct_helper_hash = nf_ct_alloc_hashtable(&nf_ct_helper_hsize, 0); - if (!nf_ct_helper_hash) - return -ENOMEM; + net->ct.auto_assign_helper_warned = false; + net->ct.sysctl_auto_assign_helper = nf_ct_auto_assign_helper; + + if (net_eq(net, &init_net)) { + nf_ct_helper_hsize = 1; /* gets rounded up to use one page */ + nf_ct_helper_hash = + nf_ct_alloc_hashtable(&nf_ct_helper_hsize, 0); + if (!nf_ct_helper_hash) + return -ENOMEM; - err = nf_ct_extend_register(&helper_extend); + err = nf_ct_extend_register(&helper_extend); + if (err < 0) + goto err1; + } + + err = nf_conntrack_helper_init_sysctl(net); if (err < 0) - goto err1; + goto out_sysctl; return 0; +out_sysctl: + if (net_eq(net, &init_net)) + nf_ct_extend_unregister(&helper_extend); err1: nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); return err; } -void nf_conntrack_helper_fini(void) +void nf_conntrack_helper_fini(struct net *net) { - nf_ct_extend_unregister(&helper_extend); - nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); + nf_conntrack_helper_fini_sysctl(net); + if (net_eq(net, &init_net)) { + nf_ct_extend_unregister(&helper_extend); + nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); + } } diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index 4f9390b9869..81366c11827 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -185,11 +185,9 @@ static int help(struct sk_buff *skb, unsigned int protoff, tuple = &ct->tuplehash[dir].tuple; if (tuple->src.u3.ip != dcc_ip && tuple->dst.u3.ip != dcc_ip) { - if (net_ratelimit()) - printk(KERN_WARNING - "Forged DCC command from %pI4: %pI4:%u\n", - &tuple->src.u3.ip, - &dcc_ip, dcc_port); + net_warn_ratelimited("Forged DCC command from %pI4: %pI4:%u\n", + &tuple->src.u3.ip, + &dcc_ip, dcc_port); continue; } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index ca7e8354e4f..6f4b00a8fc7 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -66,7 +66,8 @@ ctnetlink_dump_tuples_proto(struct sk_buff *skb, nest_parms = nla_nest_start(skb, CTA_TUPLE_PROTO | NLA_F_NESTED); if (!nest_parms) goto nla_put_failure; - NLA_PUT_U8(skb, CTA_PROTO_NUM, tuple->dst.protonum); + if (nla_put_u8(skb, CTA_PROTO_NUM, tuple->dst.protonum)) + goto nla_put_failure; if (likely(l4proto->tuple_to_nlattr)) ret = l4proto->tuple_to_nlattr(skb, tuple); @@ -126,7 +127,8 @@ ctnetlink_dump_tuples(struct sk_buff *skb, static inline int ctnetlink_dump_status(struct sk_buff *skb, const struct nf_conn *ct) { - NLA_PUT_BE32(skb, CTA_STATUS, htonl(ct->status)); + if (nla_put_be32(skb, CTA_STATUS, htonl(ct->status))) + goto nla_put_failure; return 0; nla_put_failure: @@ -141,7 +143,8 @@ ctnetlink_dump_timeout(struct sk_buff *skb, const struct nf_conn *ct) if (timeout < 0) timeout = 0; - NLA_PUT_BE32(skb, CTA_TIMEOUT, htonl(timeout)); + if (nla_put_be32(skb, CTA_TIMEOUT, htonl(timeout))) + goto nla_put_failure; return 0; nla_put_failure: @@ -190,7 +193,8 @@ ctnetlink_dump_helpinfo(struct sk_buff *skb, const struct nf_conn *ct) nest_helper = nla_nest_start(skb, CTA_HELP | NLA_F_NESTED); if (!nest_helper) goto nla_put_failure; - NLA_PUT_STRING(skb, CTA_HELP_NAME, helper->name); + if (nla_put_string(skb, CTA_HELP_NAME, helper->name)) + goto nla_put_failure; if (helper->to_nlattr) helper->to_nlattr(skb, ct); @@ -214,8 +218,9 @@ dump_counters(struct sk_buff *skb, u64 pkts, u64 bytes, if (!nest_count) goto nla_put_failure; - NLA_PUT_BE64(skb, CTA_COUNTERS_PACKETS, cpu_to_be64(pkts)); - NLA_PUT_BE64(skb, CTA_COUNTERS_BYTES, cpu_to_be64(bytes)); + if (nla_put_be64(skb, CTA_COUNTERS_PACKETS, cpu_to_be64(pkts)) || + nla_put_be64(skb, CTA_COUNTERS_BYTES, cpu_to_be64(bytes))) + goto nla_put_failure; nla_nest_end(skb, nest_count); @@ -260,11 +265,10 @@ ctnetlink_dump_timestamp(struct sk_buff *skb, const struct nf_conn *ct) if (!nest_count) goto nla_put_failure; - NLA_PUT_BE64(skb, CTA_TIMESTAMP_START, cpu_to_be64(tstamp->start)); - if (tstamp->stop != 0) { - NLA_PUT_BE64(skb, CTA_TIMESTAMP_STOP, - cpu_to_be64(tstamp->stop)); - } + if (nla_put_be64(skb, CTA_TIMESTAMP_START, cpu_to_be64(tstamp->start)) || + (tstamp->stop != 0 && nla_put_be64(skb, CTA_TIMESTAMP_STOP, + cpu_to_be64(tstamp->stop)))) + goto nla_put_failure; nla_nest_end(skb, nest_count); return 0; @@ -277,7 +281,8 @@ nla_put_failure: static inline int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct) { - NLA_PUT_BE32(skb, CTA_MARK, htonl(ct->mark)); + if (nla_put_be32(skb, CTA_MARK, htonl(ct->mark))) + goto nla_put_failure; return 0; nla_put_failure: @@ -304,7 +309,8 @@ ctnetlink_dump_secctx(struct sk_buff *skb, const struct nf_conn *ct) if (!nest_secctx) goto nla_put_failure; - NLA_PUT_STRING(skb, CTA_SECCTX_NAME, secctx); + if (nla_put_string(skb, CTA_SECCTX_NAME, secctx)) + goto nla_put_failure; nla_nest_end(skb, nest_secctx); ret = 0; @@ -349,12 +355,13 @@ dump_nat_seq_adj(struct sk_buff *skb, const struct nf_nat_seq *natseq, int type) if (!nest_parms) goto nla_put_failure; - NLA_PUT_BE32(skb, CTA_NAT_SEQ_CORRECTION_POS, - htonl(natseq->correction_pos)); - NLA_PUT_BE32(skb, CTA_NAT_SEQ_OFFSET_BEFORE, - htonl(natseq->offset_before)); - NLA_PUT_BE32(skb, CTA_NAT_SEQ_OFFSET_AFTER, - htonl(natseq->offset_after)); + if (nla_put_be32(skb, CTA_NAT_SEQ_CORRECTION_POS, + htonl(natseq->correction_pos)) || + nla_put_be32(skb, CTA_NAT_SEQ_OFFSET_BEFORE, + htonl(natseq->offset_before)) || + nla_put_be32(skb, CTA_NAT_SEQ_OFFSET_AFTER, + htonl(natseq->offset_after))) + goto nla_put_failure; nla_nest_end(skb, nest_parms); @@ -390,7 +397,8 @@ ctnetlink_dump_nat_seq_adj(struct sk_buff *skb, const struct nf_conn *ct) static inline int ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct) { - NLA_PUT_BE32(skb, CTA_ID, htonl((unsigned long)ct)); + if (nla_put_be32(skb, CTA_ID, htonl((unsigned long)ct))) + goto nla_put_failure; return 0; nla_put_failure: @@ -400,7 +408,8 @@ nla_put_failure: static inline int ctnetlink_dump_use(struct sk_buff *skb, const struct nf_conn *ct) { - NLA_PUT_BE32(skb, CTA_USE, htonl(atomic_read(&ct->ct_general.use))); + if (nla_put_be32(skb, CTA_USE, htonl(atomic_read(&ct->ct_general.use)))) + goto nla_put_failure; return 0; nla_put_failure: @@ -440,8 +449,9 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, goto nla_put_failure; nla_nest_end(skb, nest_parms); - if (nf_ct_zone(ct)) - NLA_PUT_BE16(skb, CTA_ZONE, htons(nf_ct_zone(ct))); + if (nf_ct_zone(ct) && + nla_put_be16(skb, CTA_ZONE, htons(nf_ct_zone(ct)))) + goto nla_put_failure; if (ctnetlink_dump_status(skb, ct) < 0 || ctnetlink_dump_timeout(skb, ct) < 0 || @@ -617,8 +627,9 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) goto nla_put_failure; nla_nest_end(skb, nest_parms); - if (nf_ct_zone(ct)) - NLA_PUT_BE16(skb, CTA_ZONE, htons(nf_ct_zone(ct))); + if (nf_ct_zone(ct) && + nla_put_be16(skb, CTA_ZONE, htons(nf_ct_zone(ct)))) + goto nla_put_failure; if (ctnetlink_dump_id(skb, ct) < 0) goto nla_put_failure; @@ -1705,7 +1716,8 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, if (!nest_parms) goto nla_put_failure; - NLA_PUT_BE32(skb, CTA_EXPECT_NAT_DIR, htonl(exp->dir)); + if (nla_put_be32(skb, CTA_EXPECT_NAT_DIR, htonl(exp->dir))) + goto nla_put_failure; nat_tuple.src.l3num = nf_ct_l3num(master); nat_tuple.src.u3.ip = exp->saved_ip; @@ -1718,21 +1730,24 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, nla_nest_end(skb, nest_parms); } #endif - NLA_PUT_BE32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)); - NLA_PUT_BE32(skb, CTA_EXPECT_ID, htonl((unsigned long)exp)); - NLA_PUT_BE32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)); - NLA_PUT_BE32(skb, CTA_EXPECT_CLASS, htonl(exp->class)); + if (nla_put_be32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)) || + nla_put_be32(skb, CTA_EXPECT_ID, htonl((unsigned long)exp)) || + nla_put_be32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)) || + nla_put_be32(skb, CTA_EXPECT_CLASS, htonl(exp->class))) + goto nla_put_failure; help = nfct_help(master); if (help) { struct nf_conntrack_helper *helper; helper = rcu_dereference(help->helper); - if (helper) - NLA_PUT_STRING(skb, CTA_EXPECT_HELP_NAME, helper->name); + if (helper && + nla_put_string(skb, CTA_EXPECT_HELP_NAME, helper->name)) + goto nla_put_failure; } expfn = nf_ct_helper_expectfn_find_by_symbol(exp->expectfn); - if (expfn != NULL) - NLA_PUT_STRING(skb, CTA_EXPECT_FN, expfn->name); + if (expfn != NULL && + nla_put_string(skb, CTA_EXPECT_FN, expfn->name)) + goto nla_put_failure; return 0; @@ -2065,7 +2080,15 @@ static int ctnetlink_change_expect(struct nf_conntrack_expect *x, const struct nlattr * const cda[]) { - return -EOPNOTSUPP; + if (cda[CTA_EXPECT_TIMEOUT]) { + if (!del_timer(&x->timeout)) + return -ETIME; + + x->timeout.expires = jiffies + + ntohl(nla_get_be32(cda[CTA_EXPECT_TIMEOUT])) * HZ; + add_timer(&x->timeout); + } + return 0; } static const struct nla_policy exp_nat_nla_policy[CTA_EXPECT_NAT_MAX+1] = { diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index be3da2c8cdc..8b631b07a64 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -36,11 +36,11 @@ static DEFINE_MUTEX(nf_ct_proto_mutex); #ifdef CONFIG_SYSCTL static int -nf_ct_register_sysctl(struct ctl_table_header **header, struct ctl_path *path, +nf_ct_register_sysctl(struct ctl_table_header **header, const char *path, struct ctl_table *table, unsigned int *users) { if (*header == NULL) { - *header = register_sysctl_paths(path, table); + *header = register_net_sysctl(&init_net, path, table); if (*header == NULL) return -ENOMEM; } @@ -56,7 +56,7 @@ nf_ct_unregister_sysctl(struct ctl_table_header **header, if (users != NULL && --*users > 0) return; - unregister_sysctl_table(*header); + unregister_net_sysctl_table(*header); *header = NULL; } #endif @@ -250,7 +250,7 @@ static int nf_ct_l4proto_register_sysctl(struct nf_conntrack_l4proto *l4proto) #ifdef CONFIG_SYSCTL if (l4proto->ctl_table != NULL) { err = nf_ct_register_sysctl(l4proto->ctl_table_header, - nf_net_netfilter_sysctl_path, + "net/netfilter", l4proto->ctl_table, l4proto->ctl_table_users); if (err < 0) @@ -259,7 +259,7 @@ static int nf_ct_l4proto_register_sysctl(struct nf_conntrack_l4proto *l4proto) #ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT if (l4proto->ctl_compat_table != NULL) { err = nf_ct_register_sysctl(&l4proto->ctl_compat_table_header, - nf_net_ipv4_netfilter_sysctl_path, + "net/ipv4/netfilter", l4proto->ctl_compat_table, NULL); if (err == 0) goto out; diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 24fdce256cb..ef706a485be 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -643,11 +643,12 @@ static int dccp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, nest_parms = nla_nest_start(skb, CTA_PROTOINFO_DCCP | NLA_F_NESTED); if (!nest_parms) goto nla_put_failure; - NLA_PUT_U8(skb, CTA_PROTOINFO_DCCP_STATE, ct->proto.dccp.state); - NLA_PUT_U8(skb, CTA_PROTOINFO_DCCP_ROLE, - ct->proto.dccp.role[IP_CT_DIR_ORIGINAL]); - NLA_PUT_BE64(skb, CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ, - cpu_to_be64(ct->proto.dccp.handshake_seq)); + if (nla_put_u8(skb, CTA_PROTOINFO_DCCP_STATE, ct->proto.dccp.state) || + nla_put_u8(skb, CTA_PROTOINFO_DCCP_ROLE, + ct->proto.dccp.role[IP_CT_DIR_ORIGINAL]) || + nla_put_be64(skb, CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ, + cpu_to_be64(ct->proto.dccp.handshake_seq))) + goto nla_put_failure; nla_nest_end(skb, nest_parms); spin_unlock_bh(&ct->lock); return 0; @@ -739,9 +740,10 @@ dccp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) const unsigned int *timeouts = data; int i; - for (i=CTA_TIMEOUT_DCCP_UNSPEC+1; i<CTA_TIMEOUT_DCCP_MAX+1; i++) - NLA_PUT_BE32(skb, i, htonl(timeouts[i] / HZ)); - + for (i=CTA_TIMEOUT_DCCP_UNSPEC+1; i<CTA_TIMEOUT_DCCP_MAX+1; i++) { + if (nla_put_be32(skb, i, htonl(timeouts[i] / HZ))) + goto nla_put_failure; + } return 0; nla_put_failure: @@ -908,8 +910,8 @@ static __net_init int dccp_net_init(struct net *net) dn->sysctl_table[6].data = &dn->dccp_timeout[CT_DCCP_TIMEWAIT]; dn->sysctl_table[7].data = &dn->dccp_loose; - dn->sysctl_header = register_net_sysctl_table(net, - nf_net_netfilter_sysctl_path, dn->sysctl_table); + dn->sysctl_header = register_net_sysctl(net, "net/netfilter", + dn->sysctl_table); if (!dn->sysctl_header) { kfree(dn->sysctl_table); return -ENOMEM; diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index 835e24c58f0..d8923d54b35 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -90,7 +90,8 @@ generic_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeout = data; - NLA_PUT_BE32(skb, CTA_TIMEOUT_GENERIC_TIMEOUT, htonl(*timeout / HZ)); + if (nla_put_be32(skb, CTA_TIMEOUT_GENERIC_TIMEOUT, htonl(*timeout / HZ))) + goto nla_put_failure; return 0; diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 659648c4b14..4bf6b4e4b77 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -321,10 +321,11 @@ gre_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeouts = data; - NLA_PUT_BE32(skb, CTA_TIMEOUT_GRE_UNREPLIED, - htonl(timeouts[GRE_CT_UNREPLIED] / HZ)); - NLA_PUT_BE32(skb, CTA_TIMEOUT_GRE_REPLIED, - htonl(timeouts[GRE_CT_REPLIED] / HZ)); + if (nla_put_be32(skb, CTA_TIMEOUT_GRE_UNREPLIED, + htonl(timeouts[GRE_CT_UNREPLIED] / HZ)) || + nla_put_be32(skb, CTA_TIMEOUT_GRE_REPLIED, + htonl(timeouts[GRE_CT_REPLIED] / HZ))) + goto nla_put_failure; return 0; nla_put_failure: diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 72b5088592d..996db2fa21f 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -482,15 +482,12 @@ static int sctp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, if (!nest_parms) goto nla_put_failure; - NLA_PUT_U8(skb, CTA_PROTOINFO_SCTP_STATE, ct->proto.sctp.state); - - NLA_PUT_BE32(skb, - CTA_PROTOINFO_SCTP_VTAG_ORIGINAL, - ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL]); - - NLA_PUT_BE32(skb, - CTA_PROTOINFO_SCTP_VTAG_REPLY, - ct->proto.sctp.vtag[IP_CT_DIR_REPLY]); + if (nla_put_u8(skb, CTA_PROTOINFO_SCTP_STATE, ct->proto.sctp.state) || + nla_put_be32(skb, CTA_PROTOINFO_SCTP_VTAG_ORIGINAL, + ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL]) || + nla_put_be32(skb, CTA_PROTOINFO_SCTP_VTAG_REPLY, + ct->proto.sctp.vtag[IP_CT_DIR_REPLY])) + goto nla_put_failure; spin_unlock_bh(&ct->lock); @@ -578,9 +575,10 @@ sctp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) const unsigned int *timeouts = data; int i; - for (i=CTA_TIMEOUT_SCTP_UNSPEC+1; i<CTA_TIMEOUT_SCTP_MAX+1; i++) - NLA_PUT_BE32(skb, i, htonl(timeouts[i] / HZ)); - + for (i=CTA_TIMEOUT_SCTP_UNSPEC+1; i<CTA_TIMEOUT_SCTP_MAX+1; i++) { + if (nla_put_be32(skb, i, htonl(timeouts[i] / HZ))) + goto nla_put_failure; + } return 0; nla_put_failure: diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 361eade62a0..21ff1a99f53 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -584,8 +584,8 @@ static bool tcp_in_window(const struct nf_conn *ct, * Let's try to use the data from the packet. */ sender->td_end = end; - win <<= sender->td_scale; - sender->td_maxwin = (win == 0 ? 1 : win); + swin = win << sender->td_scale; + sender->td_maxwin = (swin == 0 ? 1 : swin); sender->td_maxend = end + sender->td_maxwin; /* * We haven't seen traffic in the other direction yet @@ -952,7 +952,8 @@ static int tcp_packet(struct nf_conn *ct, spin_unlock_bh(&ct->lock); if (LOG_INVALID(net, IPPROTO_TCP)) nf_log_packet(pf, 0, skb, NULL, NULL, NULL, - "nf_ct_tcp: invalid packet ignored "); + "nf_ct_tcp: invalid packet ignored in " + "state %s ", tcp_conntrack_names[old_state]); return NF_ACCEPT; case TCP_CONNTRACK_MAX: /* Invalid packet */ @@ -1147,21 +1148,22 @@ static int tcp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, if (!nest_parms) goto nla_put_failure; - NLA_PUT_U8(skb, CTA_PROTOINFO_TCP_STATE, ct->proto.tcp.state); - - NLA_PUT_U8(skb, CTA_PROTOINFO_TCP_WSCALE_ORIGINAL, - ct->proto.tcp.seen[0].td_scale); - - NLA_PUT_U8(skb, CTA_PROTOINFO_TCP_WSCALE_REPLY, - ct->proto.tcp.seen[1].td_scale); + if (nla_put_u8(skb, CTA_PROTOINFO_TCP_STATE, ct->proto.tcp.state) || + nla_put_u8(skb, CTA_PROTOINFO_TCP_WSCALE_ORIGINAL, + ct->proto.tcp.seen[0].td_scale) || + nla_put_u8(skb, CTA_PROTOINFO_TCP_WSCALE_REPLY, + ct->proto.tcp.seen[1].td_scale)) + goto nla_put_failure; tmp.flags = ct->proto.tcp.seen[0].flags; - NLA_PUT(skb, CTA_PROTOINFO_TCP_FLAGS_ORIGINAL, - sizeof(struct nf_ct_tcp_flags), &tmp); + if (nla_put(skb, CTA_PROTOINFO_TCP_FLAGS_ORIGINAL, + sizeof(struct nf_ct_tcp_flags), &tmp)) + goto nla_put_failure; tmp.flags = ct->proto.tcp.seen[1].flags; - NLA_PUT(skb, CTA_PROTOINFO_TCP_FLAGS_REPLY, - sizeof(struct nf_ct_tcp_flags), &tmp); + if (nla_put(skb, CTA_PROTOINFO_TCP_FLAGS_REPLY, + sizeof(struct nf_ct_tcp_flags), &tmp)) + goto nla_put_failure; spin_unlock_bh(&ct->lock); nla_nest_end(skb, nest_parms); @@ -1310,28 +1312,29 @@ tcp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeouts = data; - NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_SYN_SENT, - htonl(timeouts[TCP_CONNTRACK_SYN_SENT] / HZ)); - NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_SYN_RECV, - htonl(timeouts[TCP_CONNTRACK_SYN_RECV] / HZ)); - NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_ESTABLISHED, - htonl(timeouts[TCP_CONNTRACK_ESTABLISHED] / HZ)); - NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_FIN_WAIT, - htonl(timeouts[TCP_CONNTRACK_FIN_WAIT] / HZ)); - NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_CLOSE_WAIT, - htonl(timeouts[TCP_CONNTRACK_CLOSE_WAIT] / HZ)); - NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_LAST_ACK, - htonl(timeouts[TCP_CONNTRACK_LAST_ACK] / HZ)); - NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_TIME_WAIT, - htonl(timeouts[TCP_CONNTRACK_TIME_WAIT] / HZ)); - NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_CLOSE, - htonl(timeouts[TCP_CONNTRACK_CLOSE] / HZ)); - NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_SYN_SENT2, - htonl(timeouts[TCP_CONNTRACK_SYN_SENT2] / HZ)); - NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_RETRANS, - htonl(timeouts[TCP_CONNTRACK_RETRANS] / HZ)); - NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_UNACK, - htonl(timeouts[TCP_CONNTRACK_UNACK] / HZ)); + if (nla_put_be32(skb, CTA_TIMEOUT_TCP_SYN_SENT, + htonl(timeouts[TCP_CONNTRACK_SYN_SENT] / HZ)) || + nla_put_be32(skb, CTA_TIMEOUT_TCP_SYN_RECV, + htonl(timeouts[TCP_CONNTRACK_SYN_RECV] / HZ)) || + nla_put_be32(skb, CTA_TIMEOUT_TCP_ESTABLISHED, + htonl(timeouts[TCP_CONNTRACK_ESTABLISHED] / HZ)) || + nla_put_be32(skb, CTA_TIMEOUT_TCP_FIN_WAIT, + htonl(timeouts[TCP_CONNTRACK_FIN_WAIT] / HZ)) || + nla_put_be32(skb, CTA_TIMEOUT_TCP_CLOSE_WAIT, + htonl(timeouts[TCP_CONNTRACK_CLOSE_WAIT] / HZ)) || + nla_put_be32(skb, CTA_TIMEOUT_TCP_LAST_ACK, + htonl(timeouts[TCP_CONNTRACK_LAST_ACK] / HZ)) || + nla_put_be32(skb, CTA_TIMEOUT_TCP_TIME_WAIT, + htonl(timeouts[TCP_CONNTRACK_TIME_WAIT] / HZ)) || + nla_put_be32(skb, CTA_TIMEOUT_TCP_CLOSE, + htonl(timeouts[TCP_CONNTRACK_CLOSE] / HZ)) || + nla_put_be32(skb, CTA_TIMEOUT_TCP_SYN_SENT2, + htonl(timeouts[TCP_CONNTRACK_SYN_SENT2] / HZ)) || + nla_put_be32(skb, CTA_TIMEOUT_TCP_RETRANS, + htonl(timeouts[TCP_CONNTRACK_RETRANS] / HZ)) || + nla_put_be32(skb, CTA_TIMEOUT_TCP_UNACK, + htonl(timeouts[TCP_CONNTRACK_UNACK] / HZ))) + goto nla_put_failure; return 0; nla_put_failure: diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index a9073dc1548..7259a6bdeb4 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -181,10 +181,11 @@ udp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeouts = data; - NLA_PUT_BE32(skb, CTA_TIMEOUT_UDP_UNREPLIED, - htonl(timeouts[UDP_CT_UNREPLIED] / HZ)); - NLA_PUT_BE32(skb, CTA_TIMEOUT_UDP_REPLIED, - htonl(timeouts[UDP_CT_REPLIED] / HZ)); + if (nla_put_be32(skb, CTA_TIMEOUT_UDP_UNREPLIED, + htonl(timeouts[UDP_CT_UNREPLIED] / HZ)) || + nla_put_be32(skb, CTA_TIMEOUT_UDP_REPLIED, + htonl(timeouts[UDP_CT_REPLIED] / HZ))) + goto nla_put_failure; return 0; nla_put_failure: diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index e0606392cda..4d60a5376aa 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -185,10 +185,11 @@ udplite_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeouts = data; - NLA_PUT_BE32(skb, CTA_TIMEOUT_UDPLITE_UNREPLIED, - htonl(timeouts[UDPLITE_CT_UNREPLIED] / HZ)); - NLA_PUT_BE32(skb, CTA_TIMEOUT_UDPLITE_REPLIED, - htonl(timeouts[UDPLITE_CT_REPLIED] / HZ)); + if (nla_put_be32(skb, CTA_TIMEOUT_UDPLITE_UNREPLIED, + htonl(timeouts[UDPLITE_CT_UNREPLIED] / HZ)) || + nla_put_be32(skb, CTA_TIMEOUT_UDPLITE_REPLIED, + htonl(timeouts[UDPLITE_CT_REPLIED] / HZ))) + goto nla_put_failure; return 0; nla_put_failure: diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 885f5ab9bc2..9b3943252a5 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -468,18 +468,13 @@ static ctl_table nf_ct_netfilter_table[] = { { } }; -static struct ctl_path nf_ct_path[] = { - { .procname = "net", }, - { } -}; - static int nf_conntrack_standalone_init_sysctl(struct net *net) { struct ctl_table *table; if (net_eq(net, &init_net)) { nf_ct_netfilter_header = - register_sysctl_paths(nf_ct_path, nf_ct_netfilter_table); + register_net_sysctl(&init_net, "net", nf_ct_netfilter_table); if (!nf_ct_netfilter_header) goto out; } @@ -494,8 +489,7 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) table[3].data = &net->ct.sysctl_checksum; table[4].data = &net->ct.sysctl_log_invalid; - net->ct.sysctl_header = register_net_sysctl_table(net, - nf_net_netfilter_sysctl_path, table); + net->ct.sysctl_header = register_net_sysctl(net, "net/netfilter", table); if (!net->ct.sysctl_header) goto out_unregister_netfilter; @@ -505,7 +499,7 @@ out_unregister_netfilter: kfree(table); out_kmemdup: if (net_eq(net, &init_net)) - unregister_sysctl_table(nf_ct_netfilter_header); + unregister_net_sysctl_table(nf_ct_netfilter_header); out: printk(KERN_ERR "nf_conntrack: can't register to sysctl.\n"); return -ENOMEM; @@ -516,7 +510,7 @@ static void nf_conntrack_standalone_fini_sysctl(struct net *net) struct ctl_table *table; if (net_eq(net, &init_net)) - unregister_sysctl_table(nf_ct_netfilter_header); + unregister_net_sysctl_table(nf_ct_netfilter_header); table = net->ct.sysctl_header->ctl_table_arg; unregister_net_sysctl_table(net->ct.sysctl_header); kfree(table); diff --git a/net/netfilter/nf_conntrack_timestamp.c b/net/netfilter/nf_conntrack_timestamp.c index e8d27afbbdb..dbb364f62d6 100644 --- a/net/netfilter/nf_conntrack_timestamp.c +++ b/net/netfilter/nf_conntrack_timestamp.c @@ -51,8 +51,8 @@ static int nf_conntrack_tstamp_init_sysctl(struct net *net) table[0].data = &net->ct.sysctl_tstamp; - net->ct.tstamp_sysctl_header = register_net_sysctl_table(net, - nf_net_netfilter_sysctl_path, table); + net->ct.tstamp_sysctl_header = register_net_sysctl(net, "net/netfilter", + table); if (!net->ct.tstamp_sysctl_header) { printk(KERN_ERR "nf_ct_tstamp: can't register to sysctl.\n"); goto out_register; diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 957374a234d..703fb26aa48 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -214,13 +214,6 @@ static const struct file_operations nflog_file_ops = { #endif /* PROC_FS */ #ifdef CONFIG_SYSCTL -static struct ctl_path nf_log_sysctl_path[] = { - { .procname = "net", }, - { .procname = "netfilter", }, - { .procname = "nf_log", }, - { } -}; - static char nf_log_sysctl_fnames[NFPROTO_NUMPROTO-NFPROTO_UNSPEC][3]; static struct ctl_table nf_log_sysctl_table[NFPROTO_NUMPROTO+1]; static struct ctl_table_header *nf_log_dir_header; @@ -283,7 +276,7 @@ static __init int netfilter_log_sysctl_init(void) nf_log_sysctl_table[i].extra1 = (void *)(unsigned long) i; } - nf_log_dir_header = register_sysctl_paths(nf_log_sysctl_path, + nf_log_dir_header = register_net_sysctl(&init_net, "net/netfilter/nf_log", nf_log_sysctl_table); if (!nf_log_dir_header) return -ENOMEM; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index e6ddde16561..3e797d1fcb9 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -103,7 +103,7 @@ int nfnetlink_has_listeners(struct net *net, unsigned int group) EXPORT_SYMBOL_GPL(nfnetlink_has_listeners); int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, - unsigned group, int echo, gfp_t flags) + unsigned int group, int echo, gfp_t flags) { return nlmsg_notify(net->nfnl, skb, pid, group, echo, flags); } diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 3eb348bfc4f..b2e7310ca0b 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -10,6 +10,7 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/skbuff.h> +#include <linux/atomic.h> #include <linux/netlink.h> #include <linux/rculist.h> #include <linux/slab.h> @@ -17,7 +18,6 @@ #include <linux/errno.h> #include <net/netlink.h> #include <net/sock.h> -#include <asm/atomic.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> @@ -109,7 +109,8 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, nfmsg->version = NFNETLINK_V0; nfmsg->res_id = 0; - NLA_PUT_STRING(skb, NFACCT_NAME, acct->name); + if (nla_put_string(skb, NFACCT_NAME, acct->name)) + goto nla_put_failure; if (type == NFNL_MSG_ACCT_GET_CTRZERO) { pkts = atomic64_xchg(&acct->pkts, 0); @@ -118,9 +119,10 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, pkts = atomic64_read(&acct->pkts); bytes = atomic64_read(&acct->bytes); } - NLA_PUT_BE64(skb, NFACCT_PKTS, cpu_to_be64(pkts)); - NLA_PUT_BE64(skb, NFACCT_BYTES, cpu_to_be64(bytes)); - NLA_PUT_BE32(skb, NFACCT_USE, htonl(atomic_read(&acct->refcnt))); + if (nla_put_be64(skb, NFACCT_PKTS, cpu_to_be64(pkts)) || + nla_put_be64(skb, NFACCT_BYTES, cpu_to_be64(bytes)) || + nla_put_be32(skb, NFACCT_USE, htonl(atomic_read(&acct->refcnt)))) + goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 2b9e79f5ef0..3e655288d1d 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -170,11 +170,12 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, nfmsg->version = NFNETLINK_V0; nfmsg->res_id = 0; - NLA_PUT_STRING(skb, CTA_TIMEOUT_NAME, timeout->name); - NLA_PUT_BE16(skb, CTA_TIMEOUT_L3PROTO, htons(timeout->l3num)); - NLA_PUT_U8(skb, CTA_TIMEOUT_L4PROTO, timeout->l4proto->l4proto); - NLA_PUT_BE32(skb, CTA_TIMEOUT_USE, - htonl(atomic_read(&timeout->refcnt))); + if (nla_put_string(skb, CTA_TIMEOUT_NAME, timeout->name) || + nla_put_be16(skb, CTA_TIMEOUT_L3PROTO, htons(timeout->l3num)) || + nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, timeout->l4proto->l4proto) || + nla_put_be32(skb, CTA_TIMEOUT_USE, + htonl(atomic_read(&timeout->refcnt)))) + goto nla_put_failure; if (likely(l4proto->ctnl_timeout.obj_to_nlattr)) { struct nlattr *nest_parms; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 66b2c54c544..3c3cfc0cc9b 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -391,67 +391,78 @@ __build_packet_message(struct nfulnl_instance *inst, pmsg.hw_protocol = skb->protocol; pmsg.hook = hooknum; - NLA_PUT(inst->skb, NFULA_PACKET_HDR, sizeof(pmsg), &pmsg); + if (nla_put(inst->skb, NFULA_PACKET_HDR, sizeof(pmsg), &pmsg)) + goto nla_put_failure; - if (prefix) - NLA_PUT(inst->skb, NFULA_PREFIX, plen, prefix); + if (prefix && + nla_put(inst->skb, NFULA_PREFIX, plen, prefix)) + goto nla_put_failure; if (indev) { #ifndef CONFIG_BRIDGE_NETFILTER - NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_INDEV, - htonl(indev->ifindex)); + if (nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV, + htonl(indev->ifindex))) + goto nla_put_failure; #else if (pf == PF_BRIDGE) { /* Case 1: outdev is physical input device, we need to * look for bridge group (when called from * netfilter_bridge) */ - NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_PHYSINDEV, - htonl(indev->ifindex)); + if (nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV, + htonl(indev->ifindex)) || /* this is the bridge group "brX" */ /* rcu_read_lock()ed by nf_hook_slow or nf_log_packet */ - NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_INDEV, - htonl(br_port_get_rcu(indev)->br->dev->ifindex)); + nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV, + htonl(br_port_get_rcu(indev)->br->dev->ifindex))) + goto nla_put_failure; } else { /* Case 2: indev is bridge group, we need to look for * physical device (when called from ipv4) */ - NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_INDEV, - htonl(indev->ifindex)); - if (skb->nf_bridge && skb->nf_bridge->physindev) - NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_PHYSINDEV, - htonl(skb->nf_bridge->physindev->ifindex)); + if (nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV, + htonl(indev->ifindex))) + goto nla_put_failure; + if (skb->nf_bridge && skb->nf_bridge->physindev && + nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV, + htonl(skb->nf_bridge->physindev->ifindex))) + goto nla_put_failure; } #endif } if (outdev) { #ifndef CONFIG_BRIDGE_NETFILTER - NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_OUTDEV, - htonl(outdev->ifindex)); + if (nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV, + htonl(outdev->ifindex))) + goto nla_put_failure; #else if (pf == PF_BRIDGE) { /* Case 1: outdev is physical output device, we need to * look for bridge group (when called from * netfilter_bridge) */ - NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_PHYSOUTDEV, - htonl(outdev->ifindex)); + if (nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSOUTDEV, + htonl(outdev->ifindex)) || /* this is the bridge group "brX" */ /* rcu_read_lock()ed by nf_hook_slow or nf_log_packet */ - NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_OUTDEV, - htonl(br_port_get_rcu(outdev)->br->dev->ifindex)); + nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV, + htonl(br_port_get_rcu(outdev)->br->dev->ifindex))) + goto nla_put_failure; } else { /* Case 2: indev is a bridge group, we need to look * for physical device (when called from ipv4) */ - NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_OUTDEV, - htonl(outdev->ifindex)); - if (skb->nf_bridge && skb->nf_bridge->physoutdev) - NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_PHYSOUTDEV, - htonl(skb->nf_bridge->physoutdev->ifindex)); + if (nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV, + htonl(outdev->ifindex))) + goto nla_put_failure; + if (skb->nf_bridge && skb->nf_bridge->physoutdev && + nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSOUTDEV, + htonl(skb->nf_bridge->physoutdev->ifindex))) + goto nla_put_failure; } #endif } - if (skb->mark) - NLA_PUT_BE32(inst->skb, NFULA_MARK, htonl(skb->mark)); + if (skb->mark && + nla_put_be32(inst->skb, NFULA_MARK, htonl(skb->mark))) + goto nla_put_failure; if (indev && skb->dev && skb->mac_header != skb->network_header) { @@ -459,16 +470,18 @@ __build_packet_message(struct nfulnl_instance *inst, int len = dev_parse_header(skb, phw.hw_addr); if (len > 0) { phw.hw_addrlen = htons(len); - NLA_PUT(inst->skb, NFULA_HWADDR, sizeof(phw), &phw); + if (nla_put(inst->skb, NFULA_HWADDR, sizeof(phw), &phw)) + goto nla_put_failure; } } if (indev && skb_mac_header_was_set(skb)) { - NLA_PUT_BE16(inst->skb, NFULA_HWTYPE, htons(skb->dev->type)); - NLA_PUT_BE16(inst->skb, NFULA_HWLEN, - htons(skb->dev->hard_header_len)); - NLA_PUT(inst->skb, NFULA_HWHEADER, skb->dev->hard_header_len, - skb_mac_header(skb)); + if (nla_put_be32(inst->skb, NFULA_HWTYPE, htons(skb->dev->type)) || + nla_put_be16(inst->skb, NFULA_HWLEN, + htons(skb->dev->hard_header_len)) || + nla_put(inst->skb, NFULA_HWHEADER, skb->dev->hard_header_len, + skb_mac_header(skb))) + goto nla_put_failure; } if (skb->tstamp.tv64) { @@ -477,7 +490,8 @@ __build_packet_message(struct nfulnl_instance *inst, ts.sec = cpu_to_be64(tv.tv_sec); ts.usec = cpu_to_be64(tv.tv_usec); - NLA_PUT(inst->skb, NFULA_TIMESTAMP, sizeof(ts), &ts); + if (nla_put(inst->skb, NFULA_TIMESTAMP, sizeof(ts), &ts)) + goto nla_put_failure; } /* UID */ @@ -487,22 +501,24 @@ __build_packet_message(struct nfulnl_instance *inst, struct file *file = skb->sk->sk_socket->file; __be32 uid = htonl(file->f_cred->fsuid); __be32 gid = htonl(file->f_cred->fsgid); - /* need to unlock here since NLA_PUT may goto */ read_unlock_bh(&skb->sk->sk_callback_lock); - NLA_PUT_BE32(inst->skb, NFULA_UID, uid); - NLA_PUT_BE32(inst->skb, NFULA_GID, gid); + if (nla_put_be32(inst->skb, NFULA_UID, uid) || + nla_put_be32(inst->skb, NFULA_GID, gid)) + goto nla_put_failure; } else read_unlock_bh(&skb->sk->sk_callback_lock); } /* local sequence number */ - if (inst->flags & NFULNL_CFG_F_SEQ) - NLA_PUT_BE32(inst->skb, NFULA_SEQ, htonl(inst->seq++)); + if ((inst->flags & NFULNL_CFG_F_SEQ) && + nla_put_be32(inst->skb, NFULA_SEQ, htonl(inst->seq++))) + goto nla_put_failure; /* global sequence number */ - if (inst->flags & NFULNL_CFG_F_SEQ_GLOBAL) - NLA_PUT_BE32(inst->skb, NFULA_SEQ_GLOBAL, - htonl(atomic_inc_return(&global_seq))); + if ((inst->flags & NFULNL_CFG_F_SEQ_GLOBAL) && + nla_put_be32(inst->skb, NFULA_SEQ_GLOBAL, + htonl(atomic_inc_return(&global_seq)))) + goto nla_put_failure; if (data_len) { struct nlattr *nla; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index a80b0cb03f1..4162437b836 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -288,58 +288,67 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, indev = entry->indev; if (indev) { #ifndef CONFIG_BRIDGE_NETFILTER - NLA_PUT_BE32(skb, NFQA_IFINDEX_INDEV, htonl(indev->ifindex)); + if (nla_put_be32(skb, NFQA_IFINDEX_INDEV, htonl(indev->ifindex))) + goto nla_put_failure; #else if (entry->pf == PF_BRIDGE) { /* Case 1: indev is physical input device, we need to * look for bridge group (when called from * netfilter_bridge) */ - NLA_PUT_BE32(skb, NFQA_IFINDEX_PHYSINDEV, - htonl(indev->ifindex)); + if (nla_put_be32(skb, NFQA_IFINDEX_PHYSINDEV, + htonl(indev->ifindex)) || /* this is the bridge group "brX" */ /* rcu_read_lock()ed by __nf_queue */ - NLA_PUT_BE32(skb, NFQA_IFINDEX_INDEV, - htonl(br_port_get_rcu(indev)->br->dev->ifindex)); + nla_put_be32(skb, NFQA_IFINDEX_INDEV, + htonl(br_port_get_rcu(indev)->br->dev->ifindex))) + goto nla_put_failure; } else { /* Case 2: indev is bridge group, we need to look for * physical device (when called from ipv4) */ - NLA_PUT_BE32(skb, NFQA_IFINDEX_INDEV, - htonl(indev->ifindex)); - if (entskb->nf_bridge && entskb->nf_bridge->physindev) - NLA_PUT_BE32(skb, NFQA_IFINDEX_PHYSINDEV, - htonl(entskb->nf_bridge->physindev->ifindex)); + if (nla_put_be32(skb, NFQA_IFINDEX_INDEV, + htonl(indev->ifindex))) + goto nla_put_failure; + if (entskb->nf_bridge && entskb->nf_bridge->physindev && + nla_put_be32(skb, NFQA_IFINDEX_PHYSINDEV, + htonl(entskb->nf_bridge->physindev->ifindex))) + goto nla_put_failure; } #endif } if (outdev) { #ifndef CONFIG_BRIDGE_NETFILTER - NLA_PUT_BE32(skb, NFQA_IFINDEX_OUTDEV, htonl(outdev->ifindex)); + if (nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, htonl(outdev->ifindex))) + goto nla_put_failure; #else if (entry->pf == PF_BRIDGE) { /* Case 1: outdev is physical output device, we need to * look for bridge group (when called from * netfilter_bridge) */ - NLA_PUT_BE32(skb, NFQA_IFINDEX_PHYSOUTDEV, - htonl(outdev->ifindex)); + if (nla_put_be32(skb, NFQA_IFINDEX_PHYSOUTDEV, + htonl(outdev->ifindex)) || /* this is the bridge group "brX" */ /* rcu_read_lock()ed by __nf_queue */ - NLA_PUT_BE32(skb, NFQA_IFINDEX_OUTDEV, - htonl(br_port_get_rcu(outdev)->br->dev->ifindex)); + nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, + htonl(br_port_get_rcu(outdev)->br->dev->ifindex))) + goto nla_put_failure; } else { /* Case 2: outdev is bridge group, we need to look for * physical output device (when called from ipv4) */ - NLA_PUT_BE32(skb, NFQA_IFINDEX_OUTDEV, - htonl(outdev->ifindex)); - if (entskb->nf_bridge && entskb->nf_bridge->physoutdev) - NLA_PUT_BE32(skb, NFQA_IFINDEX_PHYSOUTDEV, - htonl(entskb->nf_bridge->physoutdev->ifindex)); + if (nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, + htonl(outdev->ifindex))) + goto nla_put_failure; + if (entskb->nf_bridge && entskb->nf_bridge->physoutdev && + nla_put_be32(skb, NFQA_IFINDEX_PHYSOUTDEV, + htonl(entskb->nf_bridge->physoutdev->ifindex))) + goto nla_put_failure; } #endif } - if (entskb->mark) - NLA_PUT_BE32(skb, NFQA_MARK, htonl(entskb->mark)); + if (entskb->mark && + nla_put_be32(skb, NFQA_MARK, htonl(entskb->mark))) + goto nla_put_failure; if (indev && entskb->dev && entskb->mac_header != entskb->network_header) { @@ -347,7 +356,8 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, int len = dev_parse_header(entskb, phw.hw_addr); if (len) { phw.hw_addrlen = htons(len); - NLA_PUT(skb, NFQA_HWADDR, sizeof(phw), &phw); + if (nla_put(skb, NFQA_HWADDR, sizeof(phw), &phw)) + goto nla_put_failure; } } @@ -357,7 +367,8 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, ts.sec = cpu_to_be64(tv.tv_sec); ts.usec = cpu_to_be64(tv.tv_usec); - NLA_PUT(skb, NFQA_TIMESTAMP, sizeof(ts), &ts); + if (nla_put(skb, NFQA_TIMESTAMP, sizeof(ts), &ts)) + goto nla_put_failure; } if (data_len) { @@ -384,8 +395,7 @@ nlmsg_failure: nla_put_failure: if (skb) kfree_skb(skb); - if (net_ratelimit()) - printk(KERN_ERR "nf_queue: error creating packet message\n"); + net_err_ratelimited("nf_queue: error creating packet message\n"); return NULL; } @@ -422,10 +432,8 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) } if (queue->queue_total >= queue->queue_maxlen) { queue->queue_dropped++; - if (net_ratelimit()) - printk(KERN_WARNING "nf_queue: full at %d entries, " - "dropping packets(s).\n", - queue->queue_total); + net_warn_ratelimited("nf_queue: full at %d entries, dropping packets(s)\n", + queue->queue_total); goto err_out_free_nskb; } entry->id = ++queue->id_sequence; diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 0c8e43810ce..a51de9b052b 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -17,7 +17,6 @@ #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_ecache.h> -#include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_conntrack_zones.h> @@ -150,6 +149,17 @@ err1: return ret; } +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT +static void __xt_ct_tg_timeout_put(struct ctnl_timeout *timeout) +{ + typeof(nf_ct_timeout_put_hook) timeout_put; + + timeout_put = rcu_dereference(nf_ct_timeout_put_hook); + if (timeout_put) + timeout_put(timeout); +} +#endif + static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) { struct xt_ct_target_info_v1 *info = par->targinfo; @@ -158,7 +168,9 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) struct nf_conn *ct; int ret = 0; u8 proto; - +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT + struct ctnl_timeout *timeout; +#endif if (info->flags & ~XT_CT_NOTRACK) return -EINVAL; @@ -214,9 +226,8 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) } #ifdef CONFIG_NF_CONNTRACK_TIMEOUT - if (info->timeout) { + if (info->timeout[0]) { typeof(nf_ct_timeout_find_get_hook) timeout_find_get; - struct ctnl_timeout *timeout; struct nf_conn_timeout *timeout_ext; rcu_read_lock(); @@ -245,7 +256,7 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) pr_info("Timeout policy `%s' can only be " "used by L3 protocol number %d\n", info->timeout, timeout->l3num); - goto err4; + goto err5; } /* Make sure the timeout policy matches any existing * protocol tracker, otherwise default to generic. @@ -258,13 +269,13 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) "used by L4 protocol number %d\n", info->timeout, timeout->l4proto->l4proto); - goto err4; + goto err5; } timeout_ext = nf_ct_timeout_ext_add(ct, timeout, - GFP_KERNEL); + GFP_ATOMIC); if (timeout_ext == NULL) { ret = -ENOMEM; - goto err4; + goto err5; } } else { ret = -ENOENT; @@ -281,8 +292,12 @@ out: info->ct = ct; return 0; +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT +err5: + __xt_ct_tg_timeout_put(timeout); err4: rcu_read_unlock(); +#endif err3: nf_conntrack_free(ct); err2: diff --git a/net/netfilter/xt_HMARK.c b/net/netfilter/xt_HMARK.c new file mode 100644 index 00000000000..0a96a43108e --- /dev/null +++ b/net/netfilter/xt_HMARK.c @@ -0,0 +1,362 @@ +/* + * xt_HMARK - Netfilter module to set mark by means of hashing + * + * (C) 2012 by Hans Schillstrom <hans.schillstrom@ericsson.com> + * (C) 2012 by Pablo Neira Ayuso <pablo@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/icmp.h> + +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_HMARK.h> + +#include <net/ip.h> +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include <net/netfilter/nf_conntrack.h> +#endif +#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) +#include <net/ipv6.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#endif + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Hans Schillstrom <hans.schillstrom@ericsson.com>"); +MODULE_DESCRIPTION("Xtables: packet marking using hash calculation"); +MODULE_ALIAS("ipt_HMARK"); +MODULE_ALIAS("ip6t_HMARK"); + +struct hmark_tuple { + u32 src; + u32 dst; + union hmark_ports uports; + uint8_t proto; +}; + +static inline u32 hmark_addr6_mask(const __u32 *addr32, const __u32 *mask) +{ + return (addr32[0] & mask[0]) ^ + (addr32[1] & mask[1]) ^ + (addr32[2] & mask[2]) ^ + (addr32[3] & mask[3]); +} + +static inline u32 +hmark_addr_mask(int l3num, const __u32 *addr32, const __u32 *mask) +{ + switch (l3num) { + case AF_INET: + return *addr32 & *mask; + case AF_INET6: + return hmark_addr6_mask(addr32, mask); + } + return 0; +} + +static int +hmark_ct_set_htuple(const struct sk_buff *skb, struct hmark_tuple *t, + const struct xt_hmark_info *info) +{ +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + struct nf_conntrack_tuple *otuple; + struct nf_conntrack_tuple *rtuple; + + if (ct == NULL || nf_ct_is_untracked(ct)) + return -1; + + otuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; + rtuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; + + t->src = hmark_addr_mask(otuple->src.l3num, otuple->src.u3.all, + info->src_mask.all); + t->dst = hmark_addr_mask(otuple->src.l3num, rtuple->src.u3.all, + info->dst_mask.all); + + if (info->flags & XT_HMARK_FLAG(XT_HMARK_METHOD_L3)) + return 0; + + t->proto = nf_ct_protonum(ct); + if (t->proto != IPPROTO_ICMP) { + t->uports.p16.src = otuple->src.u.all; + t->uports.p16.dst = rtuple->src.u.all; + t->uports.v32 = (t->uports.v32 & info->port_mask.v32) | + info->port_set.v32; + if (t->uports.p16.dst < t->uports.p16.src) + swap(t->uports.p16.dst, t->uports.p16.src); + } + + return 0; +#else + return -1; +#endif +} + +static inline u32 +hmark_hash(struct hmark_tuple *t, const struct xt_hmark_info *info) +{ + u32 hash; + + if (t->dst < t->src) + swap(t->src, t->dst); + + hash = jhash_3words(t->src, t->dst, t->uports.v32, info->hashrnd); + hash = hash ^ (t->proto & info->proto_mask); + + return (((u64)hash * info->hmodulus) >> 32) + info->hoffset; +} + +static void +hmark_set_tuple_ports(const struct sk_buff *skb, unsigned int nhoff, + struct hmark_tuple *t, const struct xt_hmark_info *info) +{ + int protoff; + + protoff = proto_ports_offset(t->proto); + if (protoff < 0) + return; + + nhoff += protoff; + if (skb_copy_bits(skb, nhoff, &t->uports, sizeof(t->uports)) < 0) + return; + + t->uports.v32 = (t->uports.v32 & info->port_mask.v32) | + info->port_set.v32; + + if (t->uports.p16.dst < t->uports.p16.src) + swap(t->uports.p16.dst, t->uports.p16.src); +} + +#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) +static int get_inner6_hdr(const struct sk_buff *skb, int *offset) +{ + struct icmp6hdr *icmp6h, _ih6; + + icmp6h = skb_header_pointer(skb, *offset, sizeof(_ih6), &_ih6); + if (icmp6h == NULL) + return 0; + + if (icmp6h->icmp6_type && icmp6h->icmp6_type < 128) { + *offset += sizeof(struct icmp6hdr); + return 1; + } + return 0; +} + +static int +hmark_pkt_set_htuple_ipv6(const struct sk_buff *skb, struct hmark_tuple *t, + const struct xt_hmark_info *info) +{ + struct ipv6hdr *ip6, _ip6; + int flag = IP6T_FH_F_AUTH; + unsigned int nhoff = 0; + u16 fragoff = 0; + int nexthdr; + + ip6 = (struct ipv6hdr *) (skb->data + skb_network_offset(skb)); + nexthdr = ipv6_find_hdr(skb, &nhoff, -1, &fragoff, &flag); + if (nexthdr < 0) + return 0; + /* No need to check for icmp errors on fragments */ + if ((flag & IP6T_FH_F_FRAG) || (nexthdr != IPPROTO_ICMPV6)) + goto noicmp; + /* Use inner header in case of ICMP errors */ + if (get_inner6_hdr(skb, &nhoff)) { + ip6 = skb_header_pointer(skb, nhoff, sizeof(_ip6), &_ip6); + if (ip6 == NULL) + return -1; + /* If AH present, use SPI like in ESP. */ + flag = IP6T_FH_F_AUTH; + nexthdr = ipv6_find_hdr(skb, &nhoff, -1, &fragoff, &flag); + if (nexthdr < 0) + return -1; + } +noicmp: + t->src = hmark_addr6_mask(ip6->saddr.s6_addr32, info->src_mask.all); + t->dst = hmark_addr6_mask(ip6->daddr.s6_addr32, info->dst_mask.all); + + if (info->flags & XT_HMARK_FLAG(XT_HMARK_METHOD_L3)) + return 0; + + t->proto = nexthdr; + if (t->proto == IPPROTO_ICMPV6) + return 0; + + if (flag & IP6T_FH_F_FRAG) + return 0; + + hmark_set_tuple_ports(skb, nhoff, t, info); + return 0; +} + +static unsigned int +hmark_tg_v6(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct xt_hmark_info *info = par->targinfo; + struct hmark_tuple t; + + memset(&t, 0, sizeof(struct hmark_tuple)); + + if (info->flags & XT_HMARK_FLAG(XT_HMARK_CT)) { + if (hmark_ct_set_htuple(skb, &t, info) < 0) + return XT_CONTINUE; + } else { + if (hmark_pkt_set_htuple_ipv6(skb, &t, info) < 0) + return XT_CONTINUE; + } + + skb->mark = hmark_hash(&t, info); + return XT_CONTINUE; +} +#endif + +static int get_inner_hdr(const struct sk_buff *skb, int iphsz, int *nhoff) +{ + const struct icmphdr *icmph; + struct icmphdr _ih; + + /* Not enough header? */ + icmph = skb_header_pointer(skb, *nhoff + iphsz, sizeof(_ih), &_ih); + if (icmph == NULL || icmph->type > NR_ICMP_TYPES) + return 0; + + /* Error message? */ + if (icmph->type != ICMP_DEST_UNREACH && + icmph->type != ICMP_SOURCE_QUENCH && + icmph->type != ICMP_TIME_EXCEEDED && + icmph->type != ICMP_PARAMETERPROB && + icmph->type != ICMP_REDIRECT) + return 0; + + *nhoff += iphsz + sizeof(_ih); + return 1; +} + +static int +hmark_pkt_set_htuple_ipv4(const struct sk_buff *skb, struct hmark_tuple *t, + const struct xt_hmark_info *info) +{ + struct iphdr *ip, _ip; + int nhoff = skb_network_offset(skb); + + ip = (struct iphdr *) (skb->data + nhoff); + if (ip->protocol == IPPROTO_ICMP) { + /* Use inner header in case of ICMP errors */ + if (get_inner_hdr(skb, ip->ihl * 4, &nhoff)) { + ip = skb_header_pointer(skb, nhoff, sizeof(_ip), &_ip); + if (ip == NULL) + return -1; + } + } + + t->src = (__force u32) ip->saddr; + t->dst = (__force u32) ip->daddr; + + t->src &= info->src_mask.ip; + t->dst &= info->dst_mask.ip; + + if (info->flags & XT_HMARK_FLAG(XT_HMARK_METHOD_L3)) + return 0; + + t->proto = ip->protocol; + + /* ICMP has no ports, skip */ + if (t->proto == IPPROTO_ICMP) + return 0; + + /* follow-up fragments don't contain ports, skip all fragments */ + if (ip->frag_off & htons(IP_MF | IP_OFFSET)) + return 0; + + hmark_set_tuple_ports(skb, (ip->ihl * 4) + nhoff, t, info); + + return 0; +} + +static unsigned int +hmark_tg_v4(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct xt_hmark_info *info = par->targinfo; + struct hmark_tuple t; + + memset(&t, 0, sizeof(struct hmark_tuple)); + + if (info->flags & XT_HMARK_FLAG(XT_HMARK_CT)) { + if (hmark_ct_set_htuple(skb, &t, info) < 0) + return XT_CONTINUE; + } else { + if (hmark_pkt_set_htuple_ipv4(skb, &t, info) < 0) + return XT_CONTINUE; + } + + skb->mark = hmark_hash(&t, info); + return XT_CONTINUE; +} + +static int hmark_tg_check(const struct xt_tgchk_param *par) +{ + const struct xt_hmark_info *info = par->targinfo; + + if (!info->hmodulus) { + pr_info("xt_HMARK: hash modulus can't be zero\n"); + return -EINVAL; + } + if (info->proto_mask && + (info->flags & XT_HMARK_FLAG(XT_HMARK_METHOD_L3))) { + pr_info("xt_HMARK: proto mask must be zero with L3 mode\n"); + return -EINVAL; + } + if (info->flags & XT_HMARK_FLAG(XT_HMARK_SPI_MASK) && + (info->flags & (XT_HMARK_FLAG(XT_HMARK_SPORT_MASK) | + XT_HMARK_FLAG(XT_HMARK_DPORT_MASK)))) { + pr_info("xt_HMARK: spi-mask and port-mask can't be combined\n"); + return -EINVAL; + } + if (info->flags & XT_HMARK_FLAG(XT_HMARK_SPI) && + (info->flags & (XT_HMARK_FLAG(XT_HMARK_SPORT) | + XT_HMARK_FLAG(XT_HMARK_DPORT)))) { + pr_info("xt_HMARK: spi-set and port-set can't be combined\n"); + return -EINVAL; + } + return 0; +} + +static struct xt_target hmark_tg_reg[] __read_mostly = { + { + .name = "HMARK", + .family = NFPROTO_IPV4, + .target = hmark_tg_v4, + .targetsize = sizeof(struct xt_hmark_info), + .checkentry = hmark_tg_check, + .me = THIS_MODULE, + }, +#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) + { + .name = "HMARK", + .family = NFPROTO_IPV6, + .target = hmark_tg_v6, + .targetsize = sizeof(struct xt_hmark_info), + .checkentry = hmark_tg_check, + .me = THIS_MODULE, + }, +#endif +}; + +static int __init hmark_tg_init(void) +{ + return xt_register_targets(hmark_tg_reg, ARRAY_SIZE(hmark_tg_reg)); +} + +static void __exit hmark_tg_exit(void) +{ + xt_unregister_targets(hmark_tg_reg, ARRAY_SIZE(hmark_tg_reg)); +} + +module_init(hmark_tg_init); +module_exit(hmark_tg_exit); diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 190ad37c5cf..71a266de5fb 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -67,15 +67,13 @@ tcpmss_mangle_packet(struct sk_buff *skb, if (info->mss == XT_TCPMSS_CLAMP_PMTU) { if (dst_mtu(skb_dst(skb)) <= minlen) { - if (net_ratelimit()) - pr_err("unknown or invalid path-MTU (%u)\n", - dst_mtu(skb_dst(skb))); + net_err_ratelimited("unknown or invalid path-MTU (%u)\n", + dst_mtu(skb_dst(skb))); return -1; } if (in_mtu <= minlen) { - if (net_ratelimit()) - pr_err("unknown or invalid path-MTU (%u)\n", - in_mtu); + net_err_ratelimited("unknown or invalid path-MTU (%u)\n", + in_mtu); return -1; } newmss = min(dst_mtu(skb_dst(skb)), in_mtu) - minlen; diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index 4d505790283..ee2e5bc5a8c 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -87,7 +87,7 @@ tee_tg4(struct sk_buff *skb, const struct xt_action_param *par) const struct xt_tee_tginfo *info = par->targinfo; struct iphdr *iph; - if (percpu_read(tee_active)) + if (__this_cpu_read(tee_active)) return XT_CONTINUE; /* * Copy the skb, and route the copy. Will later return %XT_CONTINUE for @@ -124,9 +124,9 @@ tee_tg4(struct sk_buff *skb, const struct xt_action_param *par) ip_send_check(iph); if (tee_tg_route4(skb, info)) { - percpu_write(tee_active, true); + __this_cpu_write(tee_active, true); ip_local_out(skb); - percpu_write(tee_active, false); + __this_cpu_write(tee_active, false); } else { kfree_skb(skb); } @@ -168,7 +168,7 @@ tee_tg6(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tee_tginfo *info = par->targinfo; - if (percpu_read(tee_active)) + if (__this_cpu_read(tee_active)) return XT_CONTINUE; skb = pskb_copy(skb, GFP_ATOMIC); if (skb == NULL) @@ -186,9 +186,9 @@ tee_tg6(struct sk_buff *skb, const struct xt_action_param *par) --iph->hop_limit; } if (tee_tg_route6(skb, info)) { - percpu_write(tee_active, true); + __this_cpu_write(tee_active, true); ip6_local_out(skb); - percpu_write(tee_active, false); + __this_cpu_write(tee_active, false); } else { kfree_skb(skb); } diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 35a959a096e..146033a86de 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -282,10 +282,10 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) struct sock *sk; const struct in6_addr *laddr; __be16 lport; - int thoff; + int thoff = 0; int tproto; - tproto = ipv6_find_hdr(skb, &thoff, -1, NULL); + tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL); if (tproto < 0) { pr_debug("unable to find transport header in IPv6 packet, dropping\n"); return NF_DROP; diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index d95f9c963cd..26a668a84aa 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -171,8 +171,7 @@ dsthash_alloc_init(struct xt_hashlimit_htable *ht, if (ht->cfg.max && ht->count >= ht->cfg.max) { /* FIXME: do something. question is what.. */ - if (net_ratelimit()) - pr_err("max count of %u reached\n", ht->cfg.max); + net_err_ratelimited("max count of %u reached\n", ht->cfg.max); ent = NULL; } else ent = kmem_cache_alloc(hashlimit_cachep, GFP_ATOMIC); @@ -388,9 +387,20 @@ static void htable_put(struct xt_hashlimit_htable *hinfo) #define CREDITS_PER_JIFFY POW2_BELOW32(MAX_CPJ) +/* in byte mode, the lowest possible rate is one packet/second. + * credit_cap is used as a counter that tells us how many times we can + * refill the "credits available" counter when it becomes empty. + */ +#define MAX_CPJ_BYTES (0xFFFFFFFF / HZ) +#define CREDITS_PER_JIFFY_BYTES POW2_BELOW32(MAX_CPJ_BYTES) + +static u32 xt_hashlimit_len_to_chunks(u32 len) +{ + return (len >> XT_HASHLIMIT_BYTE_SHIFT) + 1; +} + /* Precision saver. */ -static inline u_int32_t -user2credits(u_int32_t user) +static u32 user2credits(u32 user) { /* If multiplying would overflow... */ if (user > 0xFFFFFFFF / (HZ*CREDITS_PER_JIFFY)) @@ -400,12 +410,53 @@ user2credits(u_int32_t user) return (user * HZ * CREDITS_PER_JIFFY) / XT_HASHLIMIT_SCALE; } -static inline void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now) +static u32 user2credits_byte(u32 user) { - dh->rateinfo.credit += (now - dh->rateinfo.prev) * CREDITS_PER_JIFFY; - if (dh->rateinfo.credit > dh->rateinfo.credit_cap) - dh->rateinfo.credit = dh->rateinfo.credit_cap; + u64 us = user; + us *= HZ * CREDITS_PER_JIFFY_BYTES; + return (u32) (us >> 32); +} + +static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, u32 mode) +{ + unsigned long delta = now - dh->rateinfo.prev; + u32 cap; + + if (delta == 0) + return; + dh->rateinfo.prev = now; + + if (mode & XT_HASHLIMIT_BYTES) { + u32 tmp = dh->rateinfo.credit; + dh->rateinfo.credit += CREDITS_PER_JIFFY_BYTES * delta; + cap = CREDITS_PER_JIFFY_BYTES * HZ; + if (tmp >= dh->rateinfo.credit) {/* overflow */ + dh->rateinfo.credit = cap; + return; + } + } else { + dh->rateinfo.credit += delta * CREDITS_PER_JIFFY; + cap = dh->rateinfo.credit_cap; + } + if (dh->rateinfo.credit > cap) + dh->rateinfo.credit = cap; +} + +static void rateinfo_init(struct dsthash_ent *dh, + struct xt_hashlimit_htable *hinfo) +{ + dh->rateinfo.prev = jiffies; + if (hinfo->cfg.mode & XT_HASHLIMIT_BYTES) { + dh->rateinfo.credit = CREDITS_PER_JIFFY_BYTES * HZ; + dh->rateinfo.cost = user2credits_byte(hinfo->cfg.avg); + dh->rateinfo.credit_cap = hinfo->cfg.burst; + } else { + dh->rateinfo.credit = user2credits(hinfo->cfg.avg * + hinfo->cfg.burst); + dh->rateinfo.cost = user2credits(hinfo->cfg.avg); + dh->rateinfo.credit_cap = dh->rateinfo.credit; + } } static inline __be32 maskl(__be32 a, unsigned int l) @@ -511,6 +562,21 @@ hashlimit_init_dst(const struct xt_hashlimit_htable *hinfo, return 0; } +static u32 hashlimit_byte_cost(unsigned int len, struct dsthash_ent *dh) +{ + u64 tmp = xt_hashlimit_len_to_chunks(len); + tmp = tmp * dh->rateinfo.cost; + + if (unlikely(tmp > CREDITS_PER_JIFFY_BYTES * HZ)) + tmp = CREDITS_PER_JIFFY_BYTES * HZ; + + if (dh->rateinfo.credit < tmp && dh->rateinfo.credit_cap) { + dh->rateinfo.credit_cap--; + dh->rateinfo.credit = CREDITS_PER_JIFFY_BYTES * HZ; + } + return (u32) tmp; +} + static bool hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) { @@ -519,6 +585,7 @@ hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) unsigned long now = jiffies; struct dsthash_ent *dh; struct dsthash_dst dst; + u32 cost; if (hashlimit_init_dst(hinfo, &dst, skb, par->thoff) < 0) goto hotdrop; @@ -532,21 +599,21 @@ hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) goto hotdrop; } dh->expires = jiffies + msecs_to_jiffies(hinfo->cfg.expire); - dh->rateinfo.prev = jiffies; - dh->rateinfo.credit = user2credits(hinfo->cfg.avg * - hinfo->cfg.burst); - dh->rateinfo.credit_cap = user2credits(hinfo->cfg.avg * - hinfo->cfg.burst); - dh->rateinfo.cost = user2credits(hinfo->cfg.avg); + rateinfo_init(dh, hinfo); } else { /* update expiration timeout */ dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire); - rateinfo_recalc(dh, now); + rateinfo_recalc(dh, now, hinfo->cfg.mode); } - if (dh->rateinfo.credit >= dh->rateinfo.cost) { + if (info->cfg.mode & XT_HASHLIMIT_BYTES) + cost = hashlimit_byte_cost(skb->len, dh); + else + cost = dh->rateinfo.cost; + + if (dh->rateinfo.credit >= cost) { /* below the limit */ - dh->rateinfo.credit -= dh->rateinfo.cost; + dh->rateinfo.credit -= cost; spin_unlock(&dh->lock); rcu_read_unlock_bh(); return !(info->cfg.mode & XT_HASHLIMIT_INVERT); @@ -568,14 +635,6 @@ static int hashlimit_mt_check(const struct xt_mtchk_param *par) struct xt_hashlimit_mtinfo1 *info = par->matchinfo; int ret; - /* Check for overflow. */ - if (info->cfg.burst == 0 || - user2credits(info->cfg.avg * info->cfg.burst) < - user2credits(info->cfg.avg)) { - pr_info("overflow, try lower: %u/%u\n", - info->cfg.avg, info->cfg.burst); - return -ERANGE; - } if (info->cfg.gc_interval == 0 || info->cfg.expire == 0) return -EINVAL; if (info->name[sizeof(info->name)-1] != '\0') @@ -588,6 +647,26 @@ static int hashlimit_mt_check(const struct xt_mtchk_param *par) return -EINVAL; } + if (info->cfg.mode & ~XT_HASHLIMIT_ALL) { + pr_info("Unknown mode mask %X, kernel too old?\n", + info->cfg.mode); + return -EINVAL; + } + + /* Check for overflow. */ + if (info->cfg.mode & XT_HASHLIMIT_BYTES) { + if (user2credits_byte(info->cfg.avg) == 0) { + pr_info("overflow, rate too high: %u\n", info->cfg.avg); + return -EINVAL; + } + } else if (info->cfg.burst == 0 || + user2credits(info->cfg.avg * info->cfg.burst) < + user2credits(info->cfg.avg)) { + pr_info("overflow, try lower: %u/%u\n", + info->cfg.avg, info->cfg.burst); + return -ERANGE; + } + mutex_lock(&hashlimit_mutex); info->hinfo = htable_find_get(net, info->name, par->family); if (info->hinfo == NULL) { @@ -680,10 +759,11 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { int res; + const struct xt_hashlimit_htable *ht = s->private; spin_lock(&ent->lock); /* recalculate to show accurate numbers */ - rateinfo_recalc(ent, jiffies); + rateinfo_recalc(ent, jiffies, ht->cfg.mode); switch (family) { case NFPROTO_IPV4: diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c index 32b7a579a03..5c22ce8ab30 100644 --- a/net/netfilter/xt_limit.c +++ b/net/netfilter/xt_limit.c @@ -88,8 +88,7 @@ limit_mt(const struct sk_buff *skb, struct xt_action_param *par) } /* Precision saver. */ -static u_int32_t -user2credits(u_int32_t user) +static u32 user2credits(u32 user) { /* If multiplying would overflow... */ if (user > 0xFFFFFFFF / (HZ*CREDITS_PER_JIFFY)) @@ -123,7 +122,7 @@ static int limit_mt_check(const struct xt_mtchk_param *par) 128. */ priv->prev = jiffies; priv->credit = user2credits(r->avg * r->burst); /* Credits full. */ - r->credit_cap = user2credits(r->avg * r->burst); /* Credits full. */ + r->credit_cap = priv->credit; /* Credits full. */ r->cost = user2credits(r->avg); } return 0; diff --git a/net/netfilter/xt_mac.c b/net/netfilter/xt_mac.c index 8160f6b1435..d5b4fd4f91e 100644 --- a/net/netfilter/xt_mac.c +++ b/net/netfilter/xt_mac.c @@ -36,7 +36,7 @@ static bool mac_mt(const struct sk_buff *skb, struct xt_action_param *par) return false; if (skb_mac_header(skb) + ETH_HLEN > skb->data) return false; - ret = compare_ether_addr(eth_hdr(skb)->h_source, info->srcaddr) == 0; + ret = ether_addr_equal(eth_hdr(skb)->h_source, info->srcaddr); ret ^= info->invert; return ret; } diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index d2ff15a2412..fc0d6dbe5d1 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -314,7 +314,7 @@ static int recent_mt_check(const struct xt_mtchk_param *par) #ifdef CONFIG_PROC_FS struct proc_dir_entry *pde; #endif - unsigned i; + unsigned int i; int ret = -EINVAL; if (unlikely(!hash_rnd_inited)) { diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c index 0ec8138aa47..035960ec5cb 100644 --- a/net/netfilter/xt_set.c +++ b/net/netfilter/xt_set.c @@ -44,6 +44,14 @@ const struct ip_set_adt_opt n = { \ .cmdflags = cfs, \ .timeout = t, \ } +#define ADT_MOPT(n, f, d, fs, cfs, t) \ +struct ip_set_adt_opt n = { \ + .family = f, \ + .dim = d, \ + .flags = fs, \ + .cmdflags = cfs, \ + .timeout = t, \ +} /* Revision 0 interface: backward compatible with netfilter/iptables */ @@ -296,11 +304,14 @@ static unsigned int set_target_v2(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_set_info_target_v2 *info = par->targinfo; - ADT_OPT(add_opt, par->family, info->add_set.dim, - info->add_set.flags, info->flags, info->timeout); + ADT_MOPT(add_opt, par->family, info->add_set.dim, + info->add_set.flags, info->flags, info->timeout); ADT_OPT(del_opt, par->family, info->del_set.dim, info->del_set.flags, 0, UINT_MAX); + /* Normalize to fit into jiffies */ + if (add_opt.timeout > UINT_MAX/MSEC_PER_SEC) + add_opt.timeout = UINT_MAX/MSEC_PER_SEC; if (info->add_set.index != IPSET_INVALID_ID) ip_set_add(info->add_set.index, skb, par, &add_opt); if (info->del_set.index != IPSET_INVALID_ID) diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 72bb07f57f9..9ea482d08cf 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -263,10 +263,10 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) struct sock *sk; struct in6_addr *daddr, *saddr; __be16 dport, sport; - int thoff, tproto; + int thoff = 0, tproto; const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; - tproto = ipv6_find_hdr(skb, &thoff, -1, NULL); + tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL); if (tproto < 0) { pr_debug("unable to find transport header in IPv6 packet, dropping\n"); return NF_DROP; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 32bb75324e7..b3025a603d5 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -104,27 +104,27 @@ static inline int netlink_is_kernel(struct sock *sk) } struct nl_pid_hash { - struct hlist_head *table; - unsigned long rehash_time; + struct hlist_head *table; + unsigned long rehash_time; - unsigned int mask; - unsigned int shift; + unsigned int mask; + unsigned int shift; - unsigned int entries; - unsigned int max_shift; + unsigned int entries; + unsigned int max_shift; - u32 rnd; + u32 rnd; }; struct netlink_table { - struct nl_pid_hash hash; - struct hlist_head mc_list; - struct listeners __rcu *listeners; - unsigned int nl_nonroot; - unsigned int groups; - struct mutex *cb_mutex; - struct module *module; - int registered; + struct nl_pid_hash hash; + struct hlist_head mc_list; + struct listeners __rcu *listeners; + unsigned int nl_nonroot; + unsigned int groups; + struct mutex *cb_mutex; + struct module *module; + int registered; }; static struct netlink_table *nl_table; @@ -132,7 +132,6 @@ static struct netlink_table *nl_table; static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait); static int netlink_dump(struct sock *sk); -static void netlink_destroy_callback(struct netlink_callback *cb); static DEFINE_RWLOCK(nl_table_lock); static atomic_t nl_table_users = ATOMIC_INIT(0); @@ -149,6 +148,18 @@ static inline struct hlist_head *nl_pid_hashfn(struct nl_pid_hash *hash, u32 pid return &hash->table[jhash_1word(pid, hash->rnd) & hash->mask]; } +static void netlink_destroy_callback(struct netlink_callback *cb) +{ + kfree_skb(cb->skb); + kfree(cb); +} + +static void netlink_consume_callback(struct netlink_callback *cb) +{ + consume_skb(cb->skb); + kfree(cb); +} + static void netlink_sock_destruct(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); @@ -414,9 +425,9 @@ static int __netlink_create(struct net *net, struct socket *sock, sock_init_data(sock, sk); nlk = nlk_sk(sk); - if (cb_mutex) + if (cb_mutex) { nlk->cb_mutex = cb_mutex; - else { + } else { nlk->cb_mutex = &nlk->cb_def_mutex; mutex_init(nlk->cb_mutex); } @@ -522,8 +533,9 @@ static int netlink_release(struct socket *sock) nl_table[sk->sk_protocol].module = NULL; nl_table[sk->sk_protocol].registered = 0; } - } else if (nlk->subscriptions) + } else if (nlk->subscriptions) { netlink_update_listeners(sk); + } netlink_table_ungrab(); kfree(nlk->groups); @@ -829,12 +841,19 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, return 0; } -int netlink_sendskb(struct sock *sk, struct sk_buff *skb) +static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb) { int len = skb->len; skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_data_ready(sk, len); + return len; +} + +int netlink_sendskb(struct sock *sk, struct sk_buff *skb) +{ + int len = __netlink_sendskb(sk, skb); + sock_put(sk); return len; } @@ -859,7 +878,7 @@ static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation) struct sk_buff *nskb = skb_clone(skb, allocation); if (!nskb) return skb; - kfree_skb(skb); + consume_skb(skb); skb = nskb; } @@ -889,8 +908,10 @@ static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb) ret = skb->len; skb_set_owner_r(skb, sk); nlk->netlink_rcv(skb); + consume_skb(skb); + } else { + kfree_skb(skb); } - kfree_skb(skb); sock_put(sk); return ret; } @@ -957,8 +978,7 @@ static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb) if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && !test_bit(0, &nlk->state)) { skb_set_owner_r(skb, sk); - skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); + __netlink_sendskb(sk, skb); return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1); } return -1; @@ -1080,8 +1100,8 @@ int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 pid, if (info.delivery_failure) { kfree_skb(info.skb2); return -ENOBUFS; - } else - consume_skb(info.skb2); + } + consume_skb(info.skb2); if (info.delivered) { if (info.congested && (allocation & __GFP_WAIT)) @@ -1234,8 +1254,9 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, nlk->flags |= NETLINK_RECV_NO_ENOBUFS; clear_bit(0, &nlk->state); wake_up_interruptible(&nlk->wait); - } else + } else { nlk->flags &= ~NETLINK_RECV_NO_ENOBUFS; + } err = 0; break; default: @@ -1639,12 +1660,6 @@ void netlink_set_nonroot(int protocol, unsigned int flags) } EXPORT_SYMBOL(netlink_set_nonroot); -static void netlink_destroy_callback(struct netlink_callback *cb) -{ - kfree_skb(cb->skb); - kfree(cb); -} - struct nlmsghdr * __nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len, int flags) { @@ -1698,10 +1713,8 @@ static int netlink_dump(struct sock *sk) if (sk_filter(sk, skb)) kfree_skb(skb); - else { - skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); - } + else + __netlink_sendskb(sk, skb); return 0; } @@ -1715,17 +1728,15 @@ static int netlink_dump(struct sock *sk) if (sk_filter(sk, skb)) kfree_skb(skb); - else { - skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); - } + else + __netlink_sendskb(sk, skb); if (cb->done) cb->done(cb); nlk->cb = NULL; mutex_unlock(nlk->cb_mutex); - netlink_destroy_callback(cb); + netlink_consume_callback(cb); return 0; errout_skb: @@ -1994,11 +2005,11 @@ static void netlink_seq_stop(struct seq_file *seq, void *v) static int netlink_seq_show(struct seq_file *seq, void *v) { - if (v == SEQ_START_TOKEN) + if (v == SEQ_START_TOKEN) { seq_puts(seq, "sk Eth Pid Groups " "Rmem Wmem Dump Locks Drops Inode\n"); - else { + } else { struct sock *s = v; struct netlink_sock *nlk = nlk_sk(s); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 9f40441d7a7..8340ace837f 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -635,11 +635,12 @@ static int ctrl_fill_info(struct genl_family *family, u32 pid, u32 seq, if (hdr == NULL) return -1; - NLA_PUT_STRING(skb, CTRL_ATTR_FAMILY_NAME, family->name); - NLA_PUT_U16(skb, CTRL_ATTR_FAMILY_ID, family->id); - NLA_PUT_U32(skb, CTRL_ATTR_VERSION, family->version); - NLA_PUT_U32(skb, CTRL_ATTR_HDRSIZE, family->hdrsize); - NLA_PUT_U32(skb, CTRL_ATTR_MAXATTR, family->maxattr); + if (nla_put_string(skb, CTRL_ATTR_FAMILY_NAME, family->name) || + nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, family->id) || + nla_put_u32(skb, CTRL_ATTR_VERSION, family->version) || + nla_put_u32(skb, CTRL_ATTR_HDRSIZE, family->hdrsize) || + nla_put_u32(skb, CTRL_ATTR_MAXATTR, family->maxattr)) + goto nla_put_failure; if (!list_empty(&family->ops_list)) { struct nlattr *nla_ops; @@ -657,8 +658,9 @@ static int ctrl_fill_info(struct genl_family *family, u32 pid, u32 seq, if (nest == NULL) goto nla_put_failure; - NLA_PUT_U32(skb, CTRL_ATTR_OP_ID, ops->cmd); - NLA_PUT_U32(skb, CTRL_ATTR_OP_FLAGS, ops->flags); + if (nla_put_u32(skb, CTRL_ATTR_OP_ID, ops->cmd) || + nla_put_u32(skb, CTRL_ATTR_OP_FLAGS, ops->flags)) + goto nla_put_failure; nla_nest_end(skb, nest); } @@ -682,9 +684,10 @@ static int ctrl_fill_info(struct genl_family *family, u32 pid, u32 seq, if (nest == NULL) goto nla_put_failure; - NLA_PUT_U32(skb, CTRL_ATTR_MCAST_GRP_ID, grp->id); - NLA_PUT_STRING(skb, CTRL_ATTR_MCAST_GRP_NAME, - grp->name); + if (nla_put_u32(skb, CTRL_ATTR_MCAST_GRP_ID, grp->id) || + nla_put_string(skb, CTRL_ATTR_MCAST_GRP_NAME, + grp->name)) + goto nla_put_failure; nla_nest_end(skb, nest); } @@ -710,8 +713,9 @@ static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 pid, if (hdr == NULL) return -1; - NLA_PUT_STRING(skb, CTRL_ATTR_FAMILY_NAME, grp->family->name); - NLA_PUT_U16(skb, CTRL_ATTR_FAMILY_ID, grp->family->id); + if (nla_put_string(skb, CTRL_ATTR_FAMILY_NAME, grp->family->name) || + nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, grp->family->id)) + goto nla_put_failure; nla_grps = nla_nest_start(skb, CTRL_ATTR_MCAST_GROUPS); if (nla_grps == NULL) @@ -721,9 +725,10 @@ static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 pid, if (nest == NULL) goto nla_put_failure; - NLA_PUT_U32(skb, CTRL_ATTR_MCAST_GRP_ID, grp->id); - NLA_PUT_STRING(skb, CTRL_ATTR_MCAST_GRP_NAME, - grp->name); + if (nla_put_u32(skb, CTRL_ATTR_MCAST_GRP_ID, grp->id) || + nla_put_string(skb, CTRL_ATTR_MCAST_GRP_NAME, + grp->name)) + goto nla_put_failure; nla_nest_end(skb, nest); nla_nest_end(skb, nla_grps); diff --git a/net/netrom/nr_dev.c b/net/netrom/nr_dev.c index 1c51d7a58f0..743262becd6 100644 --- a/net/netrom/nr_dev.c +++ b/net/netrom/nr_dev.c @@ -97,7 +97,7 @@ static int nr_rebuild_header(struct sk_buff *skb) static int nr_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, - const void *daddr, const void *saddr, unsigned len) + const void *daddr, const void *saddr, unsigned int len) { unsigned char *buff = skb_push(skb, NR_NETWORK_LEN + NR_TRANSPORT_LEN); diff --git a/net/netrom/sysctl_net_netrom.c b/net/netrom/sysctl_net_netrom.c index 1e0fa9e57aa..42f630b9a69 100644 --- a/net/netrom/sysctl_net_netrom.c +++ b/net/netrom/sysctl_net_netrom.c @@ -146,18 +146,12 @@ static ctl_table nr_table[] = { { } }; -static struct ctl_path nr_path[] = { - { .procname = "net", }, - { .procname = "netrom", }, - { } -}; - void __init nr_register_sysctl(void) { - nr_table_header = register_sysctl_paths(nr_path, nr_table); + nr_table_header = register_net_sysctl(&init_net, "net/netrom", nr_table); } void nr_unregister_sysctl(void) { - unregister_sysctl_table(nr_table_header); + unregister_net_sysctl_table(nr_table_header); } diff --git a/net/nfc/Kconfig b/net/nfc/Kconfig index 44c865b86d6..8d8d9bc4b6f 100644 --- a/net/nfc/Kconfig +++ b/net/nfc/Kconfig @@ -14,6 +14,7 @@ menuconfig NFC be called nfc. source "net/nfc/nci/Kconfig" +source "net/nfc/hci/Kconfig" source "net/nfc/llcp/Kconfig" source "drivers/nfc/Kconfig" diff --git a/net/nfc/Makefile b/net/nfc/Makefile index 7b4a6dcfa56..d1a117c2c40 100644 --- a/net/nfc/Makefile +++ b/net/nfc/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_NFC) += nfc.o obj-$(CONFIG_NFC_NCI) += nci/ +obj-$(CONFIG_NFC_HCI) += hci/ nfc-objs := core.o netlink.o af_nfc.o rawsock.o nfc-$(CONFIG_NFC_LLCP) += llcp/llcp.o llcp/commands.o llcp/sock.o diff --git a/net/nfc/core.c b/net/nfc/core.c index 295d129864d..3192c3f589e 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -33,6 +33,8 @@ #define VERSION "0.1" +#define NFC_CHECK_PRES_FREQ_MS 2000 + int nfc_devlist_generation; DEFINE_MUTEX(nfc_devlist_mutex); @@ -95,7 +97,7 @@ int nfc_dev_down(struct nfc_dev *dev) goto error; } - if (dev->polling || dev->remote_activated) { + if (dev->polling || dev->activated_target_idx != NFC_TARGET_IDX_NONE) { rc = -EBUSY; goto error; } @@ -211,6 +213,8 @@ int nfc_dep_link_up(struct nfc_dev *dev, int target_index, u8 comm_mode) } rc = dev->ops->dep_link_up(dev, target_index, comm_mode, gb, gb_len); + if (!rc) + dev->activated_target_idx = target_index; error: device_unlock(&dev->dev); @@ -246,6 +250,7 @@ int nfc_dep_link_down(struct nfc_dev *dev) rc = dev->ops->dep_link_down(dev); if (!rc) { dev->dep_link_up = false; + dev->activated_target_idx = NFC_TARGET_IDX_NONE; nfc_llcp_mac_is_down(dev); nfc_genl_dep_link_down_event(dev); } @@ -289,8 +294,13 @@ int nfc_activate_target(struct nfc_dev *dev, u32 target_idx, u32 protocol) } rc = dev->ops->activate_target(dev, target_idx, protocol); - if (!rc) - dev->remote_activated = true; + if (!rc) { + dev->activated_target_idx = target_idx; + + if (dev->ops->check_presence) + mod_timer(&dev->check_pres_timer, jiffies + + msecs_to_jiffies(NFC_CHECK_PRES_FREQ_MS)); + } error: device_unlock(&dev->dev); @@ -317,8 +327,11 @@ int nfc_deactivate_target(struct nfc_dev *dev, u32 target_idx) goto error; } + if (dev->ops->check_presence) + del_timer_sync(&dev->check_pres_timer); + dev->ops->deactivate_target(dev, target_idx); - dev->remote_activated = false; + dev->activated_target_idx = NFC_TARGET_IDX_NONE; error: device_unlock(&dev->dev); @@ -352,8 +365,27 @@ int nfc_data_exchange(struct nfc_dev *dev, u32 target_idx, struct sk_buff *skb, goto error; } + if (dev->activated_target_idx == NFC_TARGET_IDX_NONE) { + rc = -ENOTCONN; + kfree_skb(skb); + goto error; + } + + if (target_idx != dev->activated_target_idx) { + rc = -EADDRNOTAVAIL; + kfree_skb(skb); + goto error; + } + + if (dev->ops->check_presence) + del_timer_sync(&dev->check_pres_timer); + rc = dev->ops->data_exchange(dev, target_idx, skb, cb, cb_context); + if (!rc && dev->ops->check_presence) + mod_timer(&dev->check_pres_timer, jiffies + + msecs_to_jiffies(NFC_CHECK_PRES_FREQ_MS)); + error: device_unlock(&dev->dev); return rc; @@ -428,10 +460,15 @@ EXPORT_SYMBOL(nfc_alloc_recv_skb); int nfc_targets_found(struct nfc_dev *dev, struct nfc_target *targets, int n_targets) { + int i; + pr_debug("dev_name=%s n_targets=%d\n", dev_name(&dev->dev), n_targets); dev->polling = false; + for (i = 0; i < n_targets; i++) + targets[i].idx = dev->target_next_idx++; + spin_lock_bh(&dev->targets_lock); dev->targets_generation++; @@ -455,17 +492,92 @@ int nfc_targets_found(struct nfc_dev *dev, } EXPORT_SYMBOL(nfc_targets_found); +int nfc_target_lost(struct nfc_dev *dev, u32 target_idx) +{ + struct nfc_target *tg; + int i; + + pr_debug("dev_name %s n_target %d\n", dev_name(&dev->dev), target_idx); + + spin_lock_bh(&dev->targets_lock); + + for (i = 0; i < dev->n_targets; i++) { + tg = &dev->targets[i]; + if (tg->idx == target_idx) + break; + } + + if (i == dev->n_targets) { + spin_unlock_bh(&dev->targets_lock); + return -EINVAL; + } + + dev->targets_generation++; + dev->n_targets--; + dev->activated_target_idx = NFC_TARGET_IDX_NONE; + + if (dev->n_targets) { + memcpy(&dev->targets[i], &dev->targets[i + 1], + (dev->n_targets - i) * sizeof(struct nfc_target)); + } else { + kfree(dev->targets); + dev->targets = NULL; + } + + spin_unlock_bh(&dev->targets_lock); + + nfc_genl_target_lost(dev, target_idx); + + return 0; +} +EXPORT_SYMBOL(nfc_target_lost); + static void nfc_release(struct device *d) { struct nfc_dev *dev = to_nfc_dev(d); pr_debug("dev_name=%s\n", dev_name(&dev->dev)); + if (dev->ops->check_presence) { + del_timer_sync(&dev->check_pres_timer); + destroy_workqueue(dev->check_pres_wq); + } + nfc_genl_data_exit(&dev->genl_data); kfree(dev->targets); kfree(dev); } +static void nfc_check_pres_work(struct work_struct *work) +{ + struct nfc_dev *dev = container_of(work, struct nfc_dev, + check_pres_work); + int rc; + + device_lock(&dev->dev); + + if (dev->activated_target_idx != NFC_TARGET_IDX_NONE && + timer_pending(&dev->check_pres_timer) == 0) { + rc = dev->ops->check_presence(dev, dev->activated_target_idx); + if (!rc) { + mod_timer(&dev->check_pres_timer, jiffies + + msecs_to_jiffies(NFC_CHECK_PRES_FREQ_MS)); + } else { + nfc_target_lost(dev, dev->activated_target_idx); + dev->activated_target_idx = NFC_TARGET_IDX_NONE; + } + } + + device_unlock(&dev->dev); +} + +static void nfc_check_pres_timeout(unsigned long data) +{ + struct nfc_dev *dev = (struct nfc_dev *)data; + + queue_work(dev->check_pres_wq, &dev->check_pres_work); +} + struct class nfc_class = { .name = "nfc", .dev_release = nfc_release, @@ -475,12 +587,12 @@ EXPORT_SYMBOL(nfc_class); static int match_idx(struct device *d, void *data) { struct nfc_dev *dev = to_nfc_dev(d); - unsigned *idx = data; + unsigned int *idx = data; return dev->idx == *idx; } -struct nfc_dev *nfc_get_device(unsigned idx) +struct nfc_dev *nfc_get_device(unsigned int idx) { struct device *d; @@ -531,6 +643,26 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, /* first generation must not be 0 */ dev->targets_generation = 1; + dev->activated_target_idx = NFC_TARGET_IDX_NONE; + + if (ops->check_presence) { + char name[32]; + init_timer(&dev->check_pres_timer); + dev->check_pres_timer.data = (unsigned long)dev; + dev->check_pres_timer.function = nfc_check_pres_timeout; + + INIT_WORK(&dev->check_pres_work, nfc_check_pres_work); + snprintf(name, sizeof(name), "nfc%d_check_pres_wq", dev->idx); + dev->check_pres_wq = alloc_workqueue(name, WQ_NON_REENTRANT | + WQ_UNBOUND | + WQ_MEM_RECLAIM, 1); + if (dev->check_pres_wq == NULL) { + kfree(dev); + return NULL; + } + } + + return dev; } EXPORT_SYMBOL(nfc_allocate_device); diff --git a/net/nfc/hci/Kconfig b/net/nfc/hci/Kconfig new file mode 100644 index 00000000000..17213a6362b --- /dev/null +++ b/net/nfc/hci/Kconfig @@ -0,0 +1,16 @@ +config NFC_HCI + depends on NFC + tristate "NFC HCI implementation" + default n + help + Say Y here if you want to build support for a kernel NFC HCI + implementation. This is mostly needed for devices that only process + HCI frames, like for example the NXP pn544. + +config NFC_SHDLC + depends on NFC_HCI + bool "SHDLC link layer for HCI based NFC drivers" + default n + ---help--- + Say yes if you use an NFC HCI driver that requires SHDLC link layer. + If unsure, say N here. diff --git a/net/nfc/hci/Makefile b/net/nfc/hci/Makefile new file mode 100644 index 00000000000..f9c44b2fb06 --- /dev/null +++ b/net/nfc/hci/Makefile @@ -0,0 +1,8 @@ +# +# Makefile for the Linux NFC HCI layer. +# + +obj-$(CONFIG_NFC_HCI) += hci.o + +hci-y := core.o hcp.o command.o +hci-$(CONFIG_NFC_SHDLC) += shdlc.o diff --git a/net/nfc/hci/command.c b/net/nfc/hci/command.c new file mode 100644 index 00000000000..8729abf5f18 --- /dev/null +++ b/net/nfc/hci/command.c @@ -0,0 +1,354 @@ +/* + * Copyright (C) 2012 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the + * Free Software Foundation, Inc., + * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + */ + +#define pr_fmt(fmt) "hci: %s: " fmt, __func__ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/module.h> + +#include <net/nfc/hci.h> + +#include "hci.h" + +static int nfc_hci_result_to_errno(u8 result) +{ + switch (result) { + case NFC_HCI_ANY_OK: + return 0; + case NFC_HCI_ANY_E_TIMEOUT: + return -ETIMEDOUT; + default: + return -1; + } +} + +static void nfc_hci_execute_cb(struct nfc_hci_dev *hdev, u8 result, + struct sk_buff *skb, void *cb_data) +{ + struct hcp_exec_waiter *hcp_ew = (struct hcp_exec_waiter *)cb_data; + + pr_debug("HCI Cmd completed with HCI result=%d\n", result); + + hcp_ew->exec_result = nfc_hci_result_to_errno(result); + if (hcp_ew->exec_result == 0) + hcp_ew->result_skb = skb; + else + kfree_skb(skb); + hcp_ew->exec_complete = true; + + wake_up(hcp_ew->wq); +} + +static int nfc_hci_execute_cmd(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd, + const u8 *param, size_t param_len, + struct sk_buff **skb) +{ + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(ew_wq); + struct hcp_exec_waiter hcp_ew; + hcp_ew.wq = &ew_wq; + hcp_ew.exec_complete = false; + hcp_ew.result_skb = NULL; + + pr_debug("through pipe=%d, cmd=%d, plen=%zd\n", pipe, cmd, param_len); + + /* TODO: Define hci cmd execution delay. Should it be the same + * for all commands? + */ + hcp_ew.exec_result = nfc_hci_hcp_message_tx(hdev, pipe, + NFC_HCI_HCP_COMMAND, cmd, + param, param_len, + nfc_hci_execute_cb, &hcp_ew, + 3000); + if (hcp_ew.exec_result < 0) + return hcp_ew.exec_result; + + wait_event(ew_wq, hcp_ew.exec_complete == true); + + if (hcp_ew.exec_result == 0) { + if (skb) + *skb = hcp_ew.result_skb; + else + kfree_skb(hcp_ew.result_skb); + } + + return hcp_ew.exec_result; +} + +int nfc_hci_send_event(struct nfc_hci_dev *hdev, u8 gate, u8 event, + const u8 *param, size_t param_len) +{ + u8 pipe; + + pr_debug("%d to gate %d\n", event, gate); + + pipe = hdev->gate2pipe[gate]; + if (pipe == NFC_HCI_INVALID_PIPE) + return -EADDRNOTAVAIL; + + return nfc_hci_hcp_message_tx(hdev, pipe, NFC_HCI_HCP_EVENT, event, + param, param_len, NULL, NULL, 0); +} +EXPORT_SYMBOL(nfc_hci_send_event); + +int nfc_hci_send_response(struct nfc_hci_dev *hdev, u8 gate, u8 response, + const u8 *param, size_t param_len) +{ + u8 pipe; + + pr_debug("\n"); + + pipe = hdev->gate2pipe[gate]; + if (pipe == NFC_HCI_INVALID_PIPE) + return -EADDRNOTAVAIL; + + return nfc_hci_hcp_message_tx(hdev, pipe, NFC_HCI_HCP_RESPONSE, + response, param, param_len, NULL, NULL, + 0); +} +EXPORT_SYMBOL(nfc_hci_send_response); + +/* + * Execute an hci command sent to gate. + * skb will contain response data if success. skb can be NULL if you are not + * interested by the response. + */ +int nfc_hci_send_cmd(struct nfc_hci_dev *hdev, u8 gate, u8 cmd, + const u8 *param, size_t param_len, struct sk_buff **skb) +{ + u8 pipe; + + pr_debug("\n"); + + pipe = hdev->gate2pipe[gate]; + if (pipe == NFC_HCI_INVALID_PIPE) + return -EADDRNOTAVAIL; + + return nfc_hci_execute_cmd(hdev, pipe, cmd, param, param_len, skb); +} +EXPORT_SYMBOL(nfc_hci_send_cmd); + +int nfc_hci_set_param(struct nfc_hci_dev *hdev, u8 gate, u8 idx, + const u8 *param, size_t param_len) +{ + int r; + u8 *tmp; + + /* TODO ELa: reg idx must be inserted before param, but we don't want + * to ask the caller to do it to keep a simpler API. + * For now, just create a new temporary param buffer. This is far from + * optimal though, and the plan is to modify APIs to pass idx down to + * nfc_hci_hcp_message_tx where the frame is actually built, thereby + * eliminating the need for the temp allocation-copy here. + */ + + pr_debug("idx=%d to gate %d\n", idx, gate); + + tmp = kmalloc(1 + param_len, GFP_KERNEL); + if (tmp == NULL) + return -ENOMEM; + + *tmp = idx; + memcpy(tmp + 1, param, param_len); + + r = nfc_hci_send_cmd(hdev, gate, NFC_HCI_ANY_SET_PARAMETER, + tmp, param_len + 1, NULL); + + kfree(tmp); + + return r; +} +EXPORT_SYMBOL(nfc_hci_set_param); + +int nfc_hci_get_param(struct nfc_hci_dev *hdev, u8 gate, u8 idx, + struct sk_buff **skb) +{ + pr_debug("gate=%d regidx=%d\n", gate, idx); + + return nfc_hci_send_cmd(hdev, gate, NFC_HCI_ANY_GET_PARAMETER, + &idx, 1, skb); +} +EXPORT_SYMBOL(nfc_hci_get_param); + +static int nfc_hci_open_pipe(struct nfc_hci_dev *hdev, u8 pipe) +{ + struct sk_buff *skb; + int r; + + pr_debug("pipe=%d\n", pipe); + + r = nfc_hci_execute_cmd(hdev, pipe, NFC_HCI_ANY_OPEN_PIPE, + NULL, 0, &skb); + if (r == 0) { + /* dest host other than host controller will send + * number of pipes already open on this gate before + * execution. The number can be found in skb->data[0] + */ + kfree_skb(skb); + } + + return r; +} + +static int nfc_hci_close_pipe(struct nfc_hci_dev *hdev, u8 pipe) +{ + pr_debug("\n"); + + return nfc_hci_execute_cmd(hdev, pipe, NFC_HCI_ANY_CLOSE_PIPE, + NULL, 0, NULL); +} + +static u8 nfc_hci_create_pipe(struct nfc_hci_dev *hdev, u8 dest_host, + u8 dest_gate, int *result) +{ + struct sk_buff *skb; + struct hci_create_pipe_params params; + struct hci_create_pipe_resp *resp; + u8 pipe; + + pr_debug("gate=%d\n", dest_gate); + + params.src_gate = NFC_HCI_ADMIN_GATE; + params.dest_host = dest_host; + params.dest_gate = dest_gate; + + *result = nfc_hci_execute_cmd(hdev, NFC_HCI_ADMIN_PIPE, + NFC_HCI_ADM_CREATE_PIPE, + (u8 *) ¶ms, sizeof(params), &skb); + if (*result == 0) { + resp = (struct hci_create_pipe_resp *)skb->data; + pipe = resp->pipe; + kfree_skb(skb); + + pr_debug("pipe created=%d\n", pipe); + + return pipe; + } else + return NFC_HCI_INVALID_PIPE; +} + +static int nfc_hci_delete_pipe(struct nfc_hci_dev *hdev, u8 pipe) +{ + pr_debug("\n"); + + return nfc_hci_execute_cmd(hdev, NFC_HCI_ADMIN_PIPE, + NFC_HCI_ADM_DELETE_PIPE, &pipe, 1, NULL); +} + +static int nfc_hci_clear_all_pipes(struct nfc_hci_dev *hdev) +{ + int r; + + u8 param[2]; + + /* TODO: Find out what the identity reference data is + * and fill param with it. HCI spec 6.1.3.5 */ + + pr_debug("\n"); + + r = nfc_hci_execute_cmd(hdev, NFC_HCI_ADMIN_PIPE, + NFC_HCI_ADM_CLEAR_ALL_PIPE, param, 2, NULL); + + return 0; +} + +int nfc_hci_disconnect_gate(struct nfc_hci_dev *hdev, u8 gate) +{ + int r; + u8 pipe = hdev->gate2pipe[gate]; + + pr_debug("\n"); + + if (pipe == NFC_HCI_INVALID_PIPE) + return -EADDRNOTAVAIL; + + r = nfc_hci_close_pipe(hdev, pipe); + if (r < 0) + return r; + + if (pipe != NFC_HCI_LINK_MGMT_PIPE && pipe != NFC_HCI_ADMIN_PIPE) { + r = nfc_hci_delete_pipe(hdev, pipe); + if (r < 0) + return r; + } + + hdev->gate2pipe[gate] = NFC_HCI_INVALID_PIPE; + + return 0; +} +EXPORT_SYMBOL(nfc_hci_disconnect_gate); + +int nfc_hci_disconnect_all_gates(struct nfc_hci_dev *hdev) +{ + int r; + + pr_debug("\n"); + + r = nfc_hci_clear_all_pipes(hdev); + if (r < 0) + return r; + + memset(hdev->gate2pipe, NFC_HCI_INVALID_PIPE, sizeof(hdev->gate2pipe)); + + return 0; +} +EXPORT_SYMBOL(nfc_hci_disconnect_all_gates); + +int nfc_hci_connect_gate(struct nfc_hci_dev *hdev, u8 dest_host, u8 dest_gate) +{ + u8 pipe = NFC_HCI_INVALID_PIPE; + bool pipe_created = false; + int r; + + pr_debug("\n"); + + if (hdev->gate2pipe[dest_gate] != NFC_HCI_INVALID_PIPE) + return -EADDRINUSE; + + switch (dest_gate) { + case NFC_HCI_LINK_MGMT_GATE: + pipe = NFC_HCI_LINK_MGMT_PIPE; + break; + case NFC_HCI_ADMIN_GATE: + pipe = NFC_HCI_ADMIN_PIPE; + break; + default: + pipe = nfc_hci_create_pipe(hdev, dest_host, dest_gate, &r); + if (pipe == NFC_HCI_INVALID_PIPE) + return r; + pipe_created = true; + break; + } + + r = nfc_hci_open_pipe(hdev, pipe); + if (r < 0) { + if (pipe_created) + if (nfc_hci_delete_pipe(hdev, pipe) < 0) { + /* TODO: Cannot clean by deleting pipe... + * -> inconsistent state */ + } + return r; + } + + hdev->gate2pipe[dest_gate] = pipe; + + return 0; +} +EXPORT_SYMBOL(nfc_hci_connect_gate); diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c new file mode 100644 index 00000000000..86fd00d5a09 --- /dev/null +++ b/net/nfc/hci/core.c @@ -0,0 +1,830 @@ +/* + * Copyright (C) 2012 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the + * Free Software Foundation, Inc., + * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + */ + +#define pr_fmt(fmt) "hci: %s: " fmt, __func__ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/nfc.h> + +#include <net/nfc/nfc.h> +#include <net/nfc/hci.h> + +#include "hci.h" + +/* Largest headroom needed for outgoing HCI commands */ +#define HCI_CMDS_HEADROOM 1 + +static void nfc_hci_msg_tx_work(struct work_struct *work) +{ + struct nfc_hci_dev *hdev = container_of(work, struct nfc_hci_dev, + msg_tx_work); + struct hci_msg *msg; + struct sk_buff *skb; + int r = 0; + + mutex_lock(&hdev->msg_tx_mutex); + + if (hdev->cmd_pending_msg) { + if (timer_pending(&hdev->cmd_timer) == 0) { + if (hdev->cmd_pending_msg->cb) + hdev->cmd_pending_msg->cb(hdev, + NFC_HCI_ANY_E_TIMEOUT, + NULL, + hdev-> + cmd_pending_msg-> + cb_context); + kfree(hdev->cmd_pending_msg); + hdev->cmd_pending_msg = NULL; + } else + goto exit; + } + +next_msg: + if (list_empty(&hdev->msg_tx_queue)) + goto exit; + + msg = list_first_entry(&hdev->msg_tx_queue, struct hci_msg, msg_l); + list_del(&msg->msg_l); + + pr_debug("msg_tx_queue has a cmd to send\n"); + while ((skb = skb_dequeue(&msg->msg_frags)) != NULL) { + r = hdev->ops->xmit(hdev, skb); + if (r < 0) { + kfree_skb(skb); + skb_queue_purge(&msg->msg_frags); + if (msg->cb) + msg->cb(hdev, NFC_HCI_ANY_E_NOK, NULL, + msg->cb_context); + kfree(msg); + break; + } + } + + if (r) + goto next_msg; + + if (msg->wait_response == false) { + kfree(msg); + goto next_msg; + } + + hdev->cmd_pending_msg = msg; + mod_timer(&hdev->cmd_timer, jiffies + + msecs_to_jiffies(hdev->cmd_pending_msg->completion_delay)); + +exit: + mutex_unlock(&hdev->msg_tx_mutex); +} + +static void nfc_hci_msg_rx_work(struct work_struct *work) +{ + struct nfc_hci_dev *hdev = container_of(work, struct nfc_hci_dev, + msg_rx_work); + struct sk_buff *skb; + struct hcp_message *message; + u8 pipe; + u8 type; + u8 instruction; + + while ((skb = skb_dequeue(&hdev->msg_rx_queue)) != NULL) { + pipe = skb->data[0]; + skb_pull(skb, NFC_HCI_HCP_PACKET_HEADER_LEN); + message = (struct hcp_message *)skb->data; + type = HCP_MSG_GET_TYPE(message->header); + instruction = HCP_MSG_GET_CMD(message->header); + skb_pull(skb, NFC_HCI_HCP_MESSAGE_HEADER_LEN); + + nfc_hci_hcp_message_rx(hdev, pipe, type, instruction, skb); + } +} + +void nfc_hci_resp_received(struct nfc_hci_dev *hdev, u8 result, + struct sk_buff *skb) +{ + mutex_lock(&hdev->msg_tx_mutex); + + if (hdev->cmd_pending_msg == NULL) { + kfree_skb(skb); + goto exit; + } + + del_timer_sync(&hdev->cmd_timer); + + if (hdev->cmd_pending_msg->cb) + hdev->cmd_pending_msg->cb(hdev, result, skb, + hdev->cmd_pending_msg->cb_context); + else + kfree_skb(skb); + + kfree(hdev->cmd_pending_msg); + hdev->cmd_pending_msg = NULL; + + queue_work(hdev->msg_tx_wq, &hdev->msg_tx_work); + +exit: + mutex_unlock(&hdev->msg_tx_mutex); +} + +void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd, + struct sk_buff *skb) +{ + kfree_skb(skb); +} + +static u32 nfc_hci_sak_to_protocol(u8 sak) +{ + switch (NFC_HCI_TYPE_A_SEL_PROT(sak)) { + case NFC_HCI_TYPE_A_SEL_PROT_MIFARE: + return NFC_PROTO_MIFARE_MASK; + case NFC_HCI_TYPE_A_SEL_PROT_ISO14443: + return NFC_PROTO_ISO14443_MASK; + case NFC_HCI_TYPE_A_SEL_PROT_DEP: + return NFC_PROTO_NFC_DEP_MASK; + case NFC_HCI_TYPE_A_SEL_PROT_ISO14443_DEP: + return NFC_PROTO_ISO14443_MASK | NFC_PROTO_NFC_DEP_MASK; + default: + return 0xffffffff; + } +} + +static int nfc_hci_target_discovered(struct nfc_hci_dev *hdev, u8 gate) +{ + struct nfc_target *targets; + struct sk_buff *atqa_skb = NULL; + struct sk_buff *sak_skb = NULL; + int r; + + pr_debug("from gate %d\n", gate); + + targets = kzalloc(sizeof(struct nfc_target), GFP_KERNEL); + if (targets == NULL) + return -ENOMEM; + + switch (gate) { + case NFC_HCI_RF_READER_A_GATE: + r = nfc_hci_get_param(hdev, NFC_HCI_RF_READER_A_GATE, + NFC_HCI_RF_READER_A_ATQA, &atqa_skb); + if (r < 0) + goto exit; + + r = nfc_hci_get_param(hdev, NFC_HCI_RF_READER_A_GATE, + NFC_HCI_RF_READER_A_SAK, &sak_skb); + if (r < 0) + goto exit; + + if (atqa_skb->len != 2 || sak_skb->len != 1) { + r = -EPROTO; + goto exit; + } + + targets->supported_protocols = + nfc_hci_sak_to_protocol(sak_skb->data[0]); + if (targets->supported_protocols == 0xffffffff) { + r = -EPROTO; + goto exit; + } + + targets->sens_res = be16_to_cpu(*(u16 *)atqa_skb->data); + targets->sel_res = sak_skb->data[0]; + + if (hdev->ops->complete_target_discovered) { + r = hdev->ops->complete_target_discovered(hdev, gate, + targets); + if (r < 0) + goto exit; + } + break; + case NFC_HCI_RF_READER_B_GATE: + targets->supported_protocols = NFC_PROTO_ISO14443_MASK; + break; + default: + if (hdev->ops->target_from_gate) + r = hdev->ops->target_from_gate(hdev, gate, targets); + else + r = -EPROTO; + if (r < 0) + goto exit; + + if (hdev->ops->complete_target_discovered) { + r = hdev->ops->complete_target_discovered(hdev, gate, + targets); + if (r < 0) + goto exit; + } + break; + } + + targets->hci_reader_gate = gate; + + r = nfc_targets_found(hdev->ndev, targets, 1); + if (r < 0) + goto exit; + + kfree(hdev->targets); + hdev->targets = targets; + targets = NULL; + hdev->target_count = 1; + +exit: + kfree(targets); + kfree_skb(atqa_skb); + kfree_skb(sak_skb); + + return r; +} + +void nfc_hci_event_received(struct nfc_hci_dev *hdev, u8 pipe, u8 event, + struct sk_buff *skb) +{ + int r = 0; + + switch (event) { + case NFC_HCI_EVT_TARGET_DISCOVERED: + if (hdev->poll_started == false) { + r = -EPROTO; + goto exit; + } + + if (skb->len < 1) { /* no status data? */ + r = -EPROTO; + goto exit; + } + + if (skb->data[0] == 3) { + /* TODO: Multiple targets in field, none activated + * poll is supposedly stopped, but there is no + * single target to activate, so nothing to report + * up. + * if we need to restart poll, we must save the + * protocols from the initial poll and reuse here. + */ + } + + if (skb->data[0] != 0) { + r = -EPROTO; + goto exit; + } + + r = nfc_hci_target_discovered(hdev, + nfc_hci_pipe2gate(hdev, pipe)); + break; + default: + /* TODO: Unknown events are hardware specific + * pass them to the driver (needs a new hci_ops) */ + break; + } + +exit: + kfree_skb(skb); + + if (r) { + /* TODO: There was an error dispatching the event, + * how to propagate up to nfc core? + */ + } +} + +static void nfc_hci_cmd_timeout(unsigned long data) +{ + struct nfc_hci_dev *hdev = (struct nfc_hci_dev *)data; + + queue_work(hdev->msg_tx_wq, &hdev->msg_tx_work); +} + +static int hci_dev_connect_gates(struct nfc_hci_dev *hdev, u8 gate_count, + u8 gates[]) +{ + int r; + u8 *p = gates; + while (gate_count--) { + r = nfc_hci_connect_gate(hdev, NFC_HCI_HOST_CONTROLLER_ID, *p); + if (r < 0) + return r; + p++; + } + + return 0; +} + +static int hci_dev_session_init(struct nfc_hci_dev *hdev) +{ + struct sk_buff *skb = NULL; + int r; + u8 hci_gates[] = { /* NFC_HCI_ADMIN_GATE MUST be first */ + NFC_HCI_ADMIN_GATE, NFC_HCI_LOOPBACK_GATE, + NFC_HCI_ID_MGMT_GATE, NFC_HCI_LINK_MGMT_GATE, + NFC_HCI_RF_READER_B_GATE, NFC_HCI_RF_READER_A_GATE + }; + + r = nfc_hci_connect_gate(hdev, NFC_HCI_HOST_CONTROLLER_ID, + NFC_HCI_ADMIN_GATE); + if (r < 0) + goto exit; + + r = nfc_hci_get_param(hdev, NFC_HCI_ADMIN_GATE, + NFC_HCI_ADMIN_SESSION_IDENTITY, &skb); + if (r < 0) + goto disconnect_all; + + if (skb->len && skb->len == strlen(hdev->init_data.session_id)) + if (memcmp(hdev->init_data.session_id, skb->data, + skb->len) == 0) { + /* TODO ELa: restore gate<->pipe table from + * some TBD location. + * note: it doesn't seem possible to get the chip + * currently open gate/pipe table. + * It is only possible to obtain the supported + * gate list. + */ + + /* goto exit + * For now, always do a full initialization */ + } + + r = nfc_hci_disconnect_all_gates(hdev); + if (r < 0) + goto exit; + + r = hci_dev_connect_gates(hdev, sizeof(hci_gates), hci_gates); + if (r < 0) + goto disconnect_all; + + r = hci_dev_connect_gates(hdev, hdev->init_data.gate_count, + hdev->init_data.gates); + if (r < 0) + goto disconnect_all; + + r = nfc_hci_set_param(hdev, NFC_HCI_ADMIN_GATE, + NFC_HCI_ADMIN_SESSION_IDENTITY, + hdev->init_data.session_id, + strlen(hdev->init_data.session_id)); + if (r == 0) + goto exit; + +disconnect_all: + nfc_hci_disconnect_all_gates(hdev); + +exit: + if (skb) + kfree_skb(skb); + + return r; +} + +static int hci_dev_version(struct nfc_hci_dev *hdev) +{ + int r; + struct sk_buff *skb; + + r = nfc_hci_get_param(hdev, NFC_HCI_ID_MGMT_GATE, + NFC_HCI_ID_MGMT_VERSION_SW, &skb); + if (r < 0) + return r; + + if (skb->len != 3) { + kfree_skb(skb); + return -EINVAL; + } + + hdev->sw_romlib = (skb->data[0] & 0xf0) >> 4; + hdev->sw_patch = skb->data[0] & 0x0f; + hdev->sw_flashlib_major = skb->data[1]; + hdev->sw_flashlib_minor = skb->data[2]; + + kfree_skb(skb); + + r = nfc_hci_get_param(hdev, NFC_HCI_ID_MGMT_GATE, + NFC_HCI_ID_MGMT_VERSION_HW, &skb); + if (r < 0) + return r; + + if (skb->len != 3) { + kfree_skb(skb); + return -EINVAL; + } + + hdev->hw_derivative = (skb->data[0] & 0xe0) >> 5; + hdev->hw_version = skb->data[0] & 0x1f; + hdev->hw_mpw = (skb->data[1] & 0xc0) >> 6; + hdev->hw_software = skb->data[1] & 0x3f; + hdev->hw_bsid = skb->data[2]; + + kfree_skb(skb); + + pr_info("SOFTWARE INFO:\n"); + pr_info("RomLib : %d\n", hdev->sw_romlib); + pr_info("Patch : %d\n", hdev->sw_patch); + pr_info("FlashLib Major : %d\n", hdev->sw_flashlib_major); + pr_info("FlashLib Minor : %d\n", hdev->sw_flashlib_minor); + pr_info("HARDWARE INFO:\n"); + pr_info("Derivative : %d\n", hdev->hw_derivative); + pr_info("HW Version : %d\n", hdev->hw_version); + pr_info("#MPW : %d\n", hdev->hw_mpw); + pr_info("Software : %d\n", hdev->hw_software); + pr_info("BSID Version : %d\n", hdev->hw_bsid); + + return 0; +} + +static int hci_dev_up(struct nfc_dev *nfc_dev) +{ + struct nfc_hci_dev *hdev = nfc_get_drvdata(nfc_dev); + int r = 0; + + if (hdev->ops->open) { + r = hdev->ops->open(hdev); + if (r < 0) + return r; + } + + r = hci_dev_session_init(hdev); + if (r < 0) + goto exit; + + r = nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE, + NFC_HCI_EVT_END_OPERATION, NULL, 0); + if (r < 0) + goto exit; + + if (hdev->ops->hci_ready) { + r = hdev->ops->hci_ready(hdev); + if (r < 0) + goto exit; + } + + r = hci_dev_version(hdev); + if (r < 0) + goto exit; + +exit: + if (r < 0) + if (hdev->ops->close) + hdev->ops->close(hdev); + return r; +} + +static int hci_dev_down(struct nfc_dev *nfc_dev) +{ + struct nfc_hci_dev *hdev = nfc_get_drvdata(nfc_dev); + + if (hdev->ops->close) + hdev->ops->close(hdev); + + memset(hdev->gate2pipe, NFC_HCI_INVALID_PIPE, sizeof(hdev->gate2pipe)); + + return 0; +} + +static int hci_start_poll(struct nfc_dev *nfc_dev, u32 protocols) +{ + struct nfc_hci_dev *hdev = nfc_get_drvdata(nfc_dev); + int r; + + if (hdev->ops->start_poll) + r = hdev->ops->start_poll(hdev, protocols); + else + r = nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE, + NFC_HCI_EVT_READER_REQUESTED, NULL, 0); + if (r == 0) + hdev->poll_started = true; + + return r; +} + +static void hci_stop_poll(struct nfc_dev *nfc_dev) +{ + struct nfc_hci_dev *hdev = nfc_get_drvdata(nfc_dev); + + if (hdev->poll_started) { + nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE, + NFC_HCI_EVT_END_OPERATION, NULL, 0); + hdev->poll_started = false; + } +} + +static struct nfc_target *hci_find_target(struct nfc_hci_dev *hdev, + u32 target_idx) +{ + int i; + if (hdev->poll_started == false || hdev->targets == NULL) + return NULL; + + for (i = 0; i < hdev->target_count; i++) { + if (hdev->targets[i].idx == target_idx) + return &hdev->targets[i]; + } + + return NULL; +} + +static int hci_activate_target(struct nfc_dev *nfc_dev, u32 target_idx, + u32 protocol) +{ + struct nfc_hci_dev *hdev = nfc_get_drvdata(nfc_dev); + + if (hci_find_target(hdev, target_idx) == NULL) + return -ENOMEDIUM; + + return 0; +} + +static void hci_deactivate_target(struct nfc_dev *nfc_dev, u32 target_idx) +{ +} + +static int hci_data_exchange(struct nfc_dev *nfc_dev, u32 target_idx, + struct sk_buff *skb, data_exchange_cb_t cb, + void *cb_context) +{ + struct nfc_hci_dev *hdev = nfc_get_drvdata(nfc_dev); + int r; + struct nfc_target *target; + struct sk_buff *res_skb = NULL; + + pr_debug("target_idx=%d\n", target_idx); + + target = hci_find_target(hdev, target_idx); + if (target == NULL) + return -ENOMEDIUM; + + switch (target->hci_reader_gate) { + case NFC_HCI_RF_READER_A_GATE: + case NFC_HCI_RF_READER_B_GATE: + if (hdev->ops->data_exchange) { + r = hdev->ops->data_exchange(hdev, target, skb, + &res_skb); + if (r <= 0) /* handled */ + break; + } + + *skb_push(skb, 1) = 0; /* CTR, see spec:10.2.2.1 */ + r = nfc_hci_send_cmd(hdev, target->hci_reader_gate, + NFC_HCI_WR_XCHG_DATA, + skb->data, skb->len, &res_skb); + /* + * TODO: Check RF Error indicator to make sure data is valid. + * It seems that HCI cmd can complete without error, but data + * can be invalid if an RF error occured? Ignore for now. + */ + if (r == 0) + skb_trim(res_skb, res_skb->len - 1); /* RF Err ind */ + break; + default: + if (hdev->ops->data_exchange) { + r = hdev->ops->data_exchange(hdev, target, skb, + &res_skb); + if (r == 1) + r = -ENOTSUPP; + } + else + r = -ENOTSUPP; + } + + kfree_skb(skb); + + cb(cb_context, res_skb, r); + + return 0; +} + +struct nfc_ops hci_nfc_ops = { + .dev_up = hci_dev_up, + .dev_down = hci_dev_down, + .start_poll = hci_start_poll, + .stop_poll = hci_stop_poll, + .activate_target = hci_activate_target, + .deactivate_target = hci_deactivate_target, + .data_exchange = hci_data_exchange, +}; + +struct nfc_hci_dev *nfc_hci_allocate_device(struct nfc_hci_ops *ops, + struct nfc_hci_init_data *init_data, + u32 protocols, + int tx_headroom, + int tx_tailroom, + int max_link_payload) +{ + struct nfc_hci_dev *hdev; + + if (ops->xmit == NULL) + return NULL; + + if (protocols == 0) + return NULL; + + hdev = kzalloc(sizeof(struct nfc_hci_dev), GFP_KERNEL); + if (hdev == NULL) + return NULL; + + hdev->ndev = nfc_allocate_device(&hci_nfc_ops, protocols, + tx_headroom + HCI_CMDS_HEADROOM, + tx_tailroom); + if (!hdev->ndev) { + kfree(hdev); + return NULL; + } + + hdev->ops = ops; + hdev->max_data_link_payload = max_link_payload; + hdev->init_data = *init_data; + + nfc_set_drvdata(hdev->ndev, hdev); + + memset(hdev->gate2pipe, NFC_HCI_INVALID_PIPE, sizeof(hdev->gate2pipe)); + + return hdev; +} +EXPORT_SYMBOL(nfc_hci_allocate_device); + +void nfc_hci_free_device(struct nfc_hci_dev *hdev) +{ + nfc_free_device(hdev->ndev); + kfree(hdev); +} +EXPORT_SYMBOL(nfc_hci_free_device); + +int nfc_hci_register_device(struct nfc_hci_dev *hdev) +{ + struct device *dev = &hdev->ndev->dev; + const char *devname = dev_name(dev); + char name[32]; + int r = 0; + + mutex_init(&hdev->msg_tx_mutex); + + INIT_LIST_HEAD(&hdev->msg_tx_queue); + + INIT_WORK(&hdev->msg_tx_work, nfc_hci_msg_tx_work); + snprintf(name, sizeof(name), "%s_hci_msg_tx_wq", devname); + hdev->msg_tx_wq = alloc_workqueue(name, WQ_NON_REENTRANT | WQ_UNBOUND | + WQ_MEM_RECLAIM, 1); + if (hdev->msg_tx_wq == NULL) { + r = -ENOMEM; + goto exit; + } + + init_timer(&hdev->cmd_timer); + hdev->cmd_timer.data = (unsigned long)hdev; + hdev->cmd_timer.function = nfc_hci_cmd_timeout; + + skb_queue_head_init(&hdev->rx_hcp_frags); + + INIT_WORK(&hdev->msg_rx_work, nfc_hci_msg_rx_work); + snprintf(name, sizeof(name), "%s_hci_msg_rx_wq", devname); + hdev->msg_rx_wq = alloc_workqueue(name, WQ_NON_REENTRANT | WQ_UNBOUND | + WQ_MEM_RECLAIM, 1); + if (hdev->msg_rx_wq == NULL) { + r = -ENOMEM; + goto exit; + } + + skb_queue_head_init(&hdev->msg_rx_queue); + + r = nfc_register_device(hdev->ndev); + +exit: + if (r < 0) { + if (hdev->msg_tx_wq) + destroy_workqueue(hdev->msg_tx_wq); + if (hdev->msg_rx_wq) + destroy_workqueue(hdev->msg_rx_wq); + } + + return r; +} +EXPORT_SYMBOL(nfc_hci_register_device); + +void nfc_hci_unregister_device(struct nfc_hci_dev *hdev) +{ + struct hci_msg *msg; + + skb_queue_purge(&hdev->rx_hcp_frags); + skb_queue_purge(&hdev->msg_rx_queue); + + while ((msg = list_first_entry(&hdev->msg_tx_queue, struct hci_msg, + msg_l)) != NULL) { + list_del(&msg->msg_l); + skb_queue_purge(&msg->msg_frags); + kfree(msg); + } + + del_timer_sync(&hdev->cmd_timer); + + nfc_unregister_device(hdev->ndev); + + destroy_workqueue(hdev->msg_tx_wq); + + destroy_workqueue(hdev->msg_rx_wq); +} +EXPORT_SYMBOL(nfc_hci_unregister_device); + +void nfc_hci_set_clientdata(struct nfc_hci_dev *hdev, void *clientdata) +{ + hdev->clientdata = clientdata; +} +EXPORT_SYMBOL(nfc_hci_set_clientdata); + +void *nfc_hci_get_clientdata(struct nfc_hci_dev *hdev) +{ + return hdev->clientdata; +} +EXPORT_SYMBOL(nfc_hci_get_clientdata); + +void nfc_hci_recv_frame(struct nfc_hci_dev *hdev, struct sk_buff *skb) +{ + struct hcp_packet *packet; + u8 type; + u8 instruction; + struct sk_buff *hcp_skb; + u8 pipe; + struct sk_buff *frag_skb; + int msg_len; + + if (skb == NULL) { + /* TODO ELa: lower layer had permanent failure, need to + * propagate that up + */ + + skb_queue_purge(&hdev->rx_hcp_frags); + + return; + } + + packet = (struct hcp_packet *)skb->data; + if ((packet->header & ~NFC_HCI_FRAGMENT) == 0) { + skb_queue_tail(&hdev->rx_hcp_frags, skb); + return; + } + + /* it's the last fragment. Does it need re-aggregation? */ + if (skb_queue_len(&hdev->rx_hcp_frags)) { + pipe = packet->header & NFC_HCI_FRAGMENT; + skb_queue_tail(&hdev->rx_hcp_frags, skb); + + msg_len = 0; + skb_queue_walk(&hdev->rx_hcp_frags, frag_skb) { + msg_len += (frag_skb->len - + NFC_HCI_HCP_PACKET_HEADER_LEN); + } + + hcp_skb = nfc_alloc_recv_skb(NFC_HCI_HCP_PACKET_HEADER_LEN + + msg_len, GFP_KERNEL); + if (hcp_skb == NULL) { + /* TODO ELa: cannot deliver HCP message. How to + * propagate error up? + */ + } + + *skb_put(hcp_skb, NFC_HCI_HCP_PACKET_HEADER_LEN) = pipe; + + skb_queue_walk(&hdev->rx_hcp_frags, frag_skb) { + msg_len = frag_skb->len - NFC_HCI_HCP_PACKET_HEADER_LEN; + memcpy(skb_put(hcp_skb, msg_len), + frag_skb->data + NFC_HCI_HCP_PACKET_HEADER_LEN, + msg_len); + } + + skb_queue_purge(&hdev->rx_hcp_frags); + } else { + packet->header &= NFC_HCI_FRAGMENT; + hcp_skb = skb; + } + + /* if this is a response, dispatch immediately to + * unblock waiting cmd context. Otherwise, enqueue to dispatch + * in separate context where handler can also execute command. + */ + packet = (struct hcp_packet *)hcp_skb->data; + type = HCP_MSG_GET_TYPE(packet->message.header); + if (type == NFC_HCI_HCP_RESPONSE) { + pipe = packet->header; + instruction = HCP_MSG_GET_CMD(packet->message.header); + skb_pull(hcp_skb, NFC_HCI_HCP_PACKET_HEADER_LEN + + NFC_HCI_HCP_MESSAGE_HEADER_LEN); + nfc_hci_hcp_message_rx(hdev, pipe, type, instruction, hcp_skb); + } else { + skb_queue_tail(&hdev->msg_rx_queue, hcp_skb); + queue_work(hdev->msg_rx_wq, &hdev->msg_rx_work); + } +} +EXPORT_SYMBOL(nfc_hci_recv_frame); + +MODULE_LICENSE("GPL"); diff --git a/net/nfc/hci/hci.h b/net/nfc/hci/hci.h new file mode 100644 index 00000000000..45f2fe4fd48 --- /dev/null +++ b/net/nfc/hci/hci.h @@ -0,0 +1,139 @@ +/* + * Copyright (C) 2012 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the + * Free Software Foundation, Inc., + * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + */ + +#ifndef __LOCAL_HCI_H +#define __LOCAL_HCI_H + +struct gate_pipe_map { + u8 gate; + u8 pipe; +}; + +struct hcp_message { + u8 header; /* type -cmd,evt,rsp- + instruction */ + u8 data[]; +} __packed; + +struct hcp_packet { + u8 header; /* cbit+pipe */ + struct hcp_message message; +} __packed; + +/* + * HCI command execution completion callback. + * result will be one of the HCI response codes. + * skb contains the response data and must be disposed. + */ +typedef void (*hci_cmd_cb_t) (struct nfc_hci_dev *hdev, u8 result, + struct sk_buff *skb, void *cb_data); + +struct hcp_exec_waiter { + wait_queue_head_t *wq; + bool exec_complete; + int exec_result; + struct sk_buff *result_skb; +}; + +struct hci_msg { + struct list_head msg_l; + struct sk_buff_head msg_frags; + bool wait_response; + hci_cmd_cb_t cb; + void *cb_context; + unsigned long completion_delay; +}; + +struct hci_create_pipe_params { + u8 src_gate; + u8 dest_host; + u8 dest_gate; +} __packed; + +struct hci_create_pipe_resp { + u8 src_host; + u8 src_gate; + u8 dest_host; + u8 dest_gate; + u8 pipe; +} __packed; + +#define NFC_HCI_FRAGMENT 0x7f + +#define HCP_HEADER(type, instr) ((((type) & 0x03) << 6) | ((instr) & 0x3f)) +#define HCP_MSG_GET_TYPE(header) ((header & 0xc0) >> 6) +#define HCP_MSG_GET_CMD(header) (header & 0x3f) + +int nfc_hci_hcp_message_tx(struct nfc_hci_dev *hdev, u8 pipe, + u8 type, u8 instruction, + const u8 *payload, size_t payload_len, + hci_cmd_cb_t cb, void *cb_data, + unsigned long completion_delay); + +u8 nfc_hci_pipe2gate(struct nfc_hci_dev *hdev, u8 pipe); + +void nfc_hci_hcp_message_rx(struct nfc_hci_dev *hdev, u8 pipe, u8 type, + u8 instruction, struct sk_buff *skb); + +/* HCP headers */ +#define NFC_HCI_HCP_PACKET_HEADER_LEN 1 +#define NFC_HCI_HCP_MESSAGE_HEADER_LEN 1 +#define NFC_HCI_HCP_HEADER_LEN 2 + +/* HCP types */ +#define NFC_HCI_HCP_COMMAND 0x00 +#define NFC_HCI_HCP_EVENT 0x01 +#define NFC_HCI_HCP_RESPONSE 0x02 + +/* Generic commands */ +#define NFC_HCI_ANY_SET_PARAMETER 0x01 +#define NFC_HCI_ANY_GET_PARAMETER 0x02 +#define NFC_HCI_ANY_OPEN_PIPE 0x03 +#define NFC_HCI_ANY_CLOSE_PIPE 0x04 + +/* Reader RF commands */ +#define NFC_HCI_WR_XCHG_DATA 0x10 + +/* Admin commands */ +#define NFC_HCI_ADM_CREATE_PIPE 0x10 +#define NFC_HCI_ADM_DELETE_PIPE 0x11 +#define NFC_HCI_ADM_NOTIFY_PIPE_CREATED 0x12 +#define NFC_HCI_ADM_NOTIFY_PIPE_DELETED 0x13 +#define NFC_HCI_ADM_CLEAR_ALL_PIPE 0x14 +#define NFC_HCI_ADM_NOTIFY_ALL_PIPE_CLEARED 0x15 + +/* Generic responses */ +#define NFC_HCI_ANY_OK 0x00 +#define NFC_HCI_ANY_E_NOT_CONNECTED 0x01 +#define NFC_HCI_ANY_E_CMD_PAR_UNKNOWN 0x02 +#define NFC_HCI_ANY_E_NOK 0x03 +#define NFC_HCI_ANY_E_PIPES_FULL 0x04 +#define NFC_HCI_ANY_E_REG_PAR_UNKNOWN 0x05 +#define NFC_HCI_ANY_E_PIPE_NOT_OPENED 0x06 +#define NFC_HCI_ANY_E_CMD_NOT_SUPPORTED 0x07 +#define NFC_HCI_ANY_E_INHIBITED 0x08 +#define NFC_HCI_ANY_E_TIMEOUT 0x09 +#define NFC_HCI_ANY_E_REG_ACCESS_DENIED 0x0a +#define NFC_HCI_ANY_E_PIPE_ACCESS_DENIED 0x0b + +/* Pipes */ +#define NFC_HCI_INVALID_PIPE 0x80 +#define NFC_HCI_LINK_MGMT_PIPE 0x00 +#define NFC_HCI_ADMIN_PIPE 0x01 + +#endif /* __LOCAL_HCI_H */ diff --git a/net/nfc/hci/hcp.c b/net/nfc/hci/hcp.c new file mode 100644 index 00000000000..7212cf2c578 --- /dev/null +++ b/net/nfc/hci/hcp.c @@ -0,0 +1,156 @@ +/* + * Copyright (C) 2012 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the + * Free Software Foundation, Inc., + * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + */ + +#define pr_fmt(fmt) "hci: %s: " fmt, __func__ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> + +#include <net/nfc/hci.h> + +#include "hci.h" + +/* + * Payload is the HCP message data only. Instruction will be prepended. + * Guarantees that cb will be called upon completion or timeout delay + * counted from the moment the cmd is sent to the transport. + */ +int nfc_hci_hcp_message_tx(struct nfc_hci_dev *hdev, u8 pipe, + u8 type, u8 instruction, + const u8 *payload, size_t payload_len, + hci_cmd_cb_t cb, void *cb_data, + unsigned long completion_delay) +{ + struct nfc_dev *ndev = hdev->ndev; + struct hci_msg *cmd; + const u8 *ptr = payload; + int hci_len, err; + bool firstfrag = true; + + cmd = kzalloc(sizeof(struct hci_msg), GFP_KERNEL); + if (cmd == NULL) + return -ENOMEM; + + INIT_LIST_HEAD(&cmd->msg_l); + skb_queue_head_init(&cmd->msg_frags); + cmd->wait_response = (type == NFC_HCI_HCP_COMMAND) ? true : false; + cmd->cb = cb; + cmd->cb_context = cb_data; + cmd->completion_delay = completion_delay; + + hci_len = payload_len + 1; + while (hci_len > 0) { + struct sk_buff *skb; + int skb_len, data_link_len; + struct hcp_packet *packet; + + if (NFC_HCI_HCP_PACKET_HEADER_LEN + hci_len <= + hdev->max_data_link_payload) + data_link_len = hci_len; + else + data_link_len = hdev->max_data_link_payload - + NFC_HCI_HCP_PACKET_HEADER_LEN; + + skb_len = ndev->tx_headroom + NFC_HCI_HCP_PACKET_HEADER_LEN + + data_link_len + ndev->tx_tailroom; + hci_len -= data_link_len; + + skb = alloc_skb(skb_len, GFP_KERNEL); + if (skb == NULL) { + err = -ENOMEM; + goto out_skb_err; + } + skb_reserve(skb, ndev->tx_headroom); + + skb_put(skb, NFC_HCI_HCP_PACKET_HEADER_LEN + data_link_len); + + /* Only the last fragment will have the cb bit set to 1 */ + packet = (struct hcp_packet *)skb->data; + packet->header = pipe; + if (firstfrag) { + firstfrag = false; + packet->message.header = HCP_HEADER(type, instruction); + if (ptr) { + memcpy(packet->message.data, ptr, + data_link_len - 1); + ptr += data_link_len - 1; + } + } else { + memcpy(&packet->message, ptr, data_link_len); + ptr += data_link_len; + } + + /* This is the last fragment, set the cb bit */ + if (hci_len == 0) + packet->header |= ~NFC_HCI_FRAGMENT; + + skb_queue_tail(&cmd->msg_frags, skb); + } + + mutex_lock(&hdev->msg_tx_mutex); + list_add_tail(&hdev->msg_tx_queue, &cmd->msg_l); + mutex_unlock(&hdev->msg_tx_mutex); + + queue_work(hdev->msg_tx_wq, &hdev->msg_tx_work); + + return 0; + +out_skb_err: + skb_queue_purge(&cmd->msg_frags); + kfree(cmd); + + return err; +} + +u8 nfc_hci_pipe2gate(struct nfc_hci_dev *hdev, u8 pipe) +{ + int gate; + + for (gate = 0; gate < NFC_HCI_MAX_GATES; gate++) + if (hdev->gate2pipe[gate] == pipe) + return gate; + + return 0xff; +} + +/* + * Receive hcp message for pipe, with type and cmd. + * skb contains optional message data only. + */ +void nfc_hci_hcp_message_rx(struct nfc_hci_dev *hdev, u8 pipe, u8 type, + u8 instruction, struct sk_buff *skb) +{ + switch (type) { + case NFC_HCI_HCP_RESPONSE: + nfc_hci_resp_received(hdev, instruction, skb); + break; + case NFC_HCI_HCP_COMMAND: + nfc_hci_cmd_received(hdev, pipe, instruction, skb); + break; + case NFC_HCI_HCP_EVENT: + nfc_hci_event_received(hdev, pipe, instruction, skb); + break; + default: + pr_err("UNKNOWN MSG Type %d, instruction=%d\n", + type, instruction); + kfree_skb(skb); + break; + } +} diff --git a/net/nfc/hci/shdlc.c b/net/nfc/hci/shdlc.c new file mode 100644 index 00000000000..923bdf7c26d --- /dev/null +++ b/net/nfc/hci/shdlc.c @@ -0,0 +1,945 @@ +/* + * Copyright (C) 2012 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the + * Free Software Foundation, Inc., + * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + */ + +#define pr_fmt(fmt) "shdlc: %s: " fmt, __func__ + +#include <linux/sched.h> +#include <linux/export.h> +#include <linux/wait.h> +#include <linux/crc-ccitt.h> +#include <linux/slab.h> +#include <linux/skbuff.h> + +#include <net/nfc/hci.h> +#include <net/nfc/shdlc.h> + +#define SHDLC_LLC_HEAD_ROOM 2 +#define SHDLC_LLC_TAIL_ROOM 2 + +#define SHDLC_MAX_WINDOW 4 +#define SHDLC_SREJ_SUPPORT false + +#define SHDLC_CONTROL_HEAD_MASK 0xe0 +#define SHDLC_CONTROL_HEAD_I 0x80 +#define SHDLC_CONTROL_HEAD_I2 0xa0 +#define SHDLC_CONTROL_HEAD_S 0xc0 +#define SHDLC_CONTROL_HEAD_U 0xe0 + +#define SHDLC_CONTROL_NS_MASK 0x38 +#define SHDLC_CONTROL_NR_MASK 0x07 +#define SHDLC_CONTROL_TYPE_MASK 0x18 + +#define SHDLC_CONTROL_M_MASK 0x1f + +enum sframe_type { + S_FRAME_RR = 0x00, + S_FRAME_REJ = 0x01, + S_FRAME_RNR = 0x02, + S_FRAME_SREJ = 0x03 +}; + +enum uframe_modifier { + U_FRAME_UA = 0x06, + U_FRAME_RSET = 0x19 +}; + +#define SHDLC_CONNECT_VALUE_MS 5 +#define SHDLC_T1_VALUE_MS(w) ((5 * w) / 4) +#define SHDLC_T2_VALUE_MS 300 + +#define SHDLC_DUMP_SKB(info, skb) \ +do { \ + pr_debug("%s:\n", info); \ + print_hex_dump(KERN_DEBUG, "shdlc: ", DUMP_PREFIX_OFFSET, \ + 16, 1, skb->data, skb->len, 0); \ +} while (0) + +/* checks x < y <= z modulo 8 */ +static bool nfc_shdlc_x_lt_y_lteq_z(int x, int y, int z) +{ + if (x < z) + return ((x < y) && (y <= z)) ? true : false; + else + return ((y > x) || (y <= z)) ? true : false; +} + +/* checks x <= y < z modulo 8 */ +static bool nfc_shdlc_x_lteq_y_lt_z(int x, int y, int z) +{ + if (x <= z) + return ((x <= y) && (y < z)) ? true : false; + else /* x > z -> z+8 > x */ + return ((y >= x) || (y < z)) ? true : false; +} + +static struct sk_buff *nfc_shdlc_alloc_skb(struct nfc_shdlc *shdlc, + int payload_len) +{ + struct sk_buff *skb; + + skb = alloc_skb(shdlc->client_headroom + SHDLC_LLC_HEAD_ROOM + + shdlc->client_tailroom + SHDLC_LLC_TAIL_ROOM + + payload_len, GFP_KERNEL); + if (skb) + skb_reserve(skb, shdlc->client_headroom + SHDLC_LLC_HEAD_ROOM); + + return skb; +} + +static void nfc_shdlc_add_len_crc(struct sk_buff *skb) +{ + u16 crc; + int len; + + len = skb->len + 2; + *skb_push(skb, 1) = len; + + crc = crc_ccitt(0xffff, skb->data, skb->len); + crc = ~crc; + *skb_put(skb, 1) = crc & 0xff; + *skb_put(skb, 1) = crc >> 8; +} + +/* immediately sends an S frame. */ +static int nfc_shdlc_send_s_frame(struct nfc_shdlc *shdlc, + enum sframe_type sframe_type, int nr) +{ + int r; + struct sk_buff *skb; + + pr_debug("sframe_type=%d nr=%d\n", sframe_type, nr); + + skb = nfc_shdlc_alloc_skb(shdlc, 0); + if (skb == NULL) + return -ENOMEM; + + *skb_push(skb, 1) = SHDLC_CONTROL_HEAD_S | (sframe_type << 3) | nr; + + nfc_shdlc_add_len_crc(skb); + + r = shdlc->ops->xmit(shdlc, skb); + + kfree_skb(skb); + + return r; +} + +/* immediately sends an U frame. skb may contain optional payload */ +static int nfc_shdlc_send_u_frame(struct nfc_shdlc *shdlc, + struct sk_buff *skb, + enum uframe_modifier uframe_modifier) +{ + int r; + + pr_debug("uframe_modifier=%d\n", uframe_modifier); + + *skb_push(skb, 1) = SHDLC_CONTROL_HEAD_U | uframe_modifier; + + nfc_shdlc_add_len_crc(skb); + + r = shdlc->ops->xmit(shdlc, skb); + + kfree_skb(skb); + + return r; +} + +/* + * Free ack_pending frames until y_nr - 1, and reset t2 according to + * the remaining oldest ack_pending frame sent time + */ +static void nfc_shdlc_reset_t2(struct nfc_shdlc *shdlc, int y_nr) +{ + struct sk_buff *skb; + int dnr = shdlc->dnr; /* MUST initially be < y_nr */ + + pr_debug("release ack pending up to frame %d excluded\n", y_nr); + + while (dnr != y_nr) { + pr_debug("release ack pending frame %d\n", dnr); + + skb = skb_dequeue(&shdlc->ack_pending_q); + kfree_skb(skb); + + dnr = (dnr + 1) % 8; + } + + if (skb_queue_empty(&shdlc->ack_pending_q)) { + if (shdlc->t2_active) { + del_timer_sync(&shdlc->t2_timer); + shdlc->t2_active = false; + + pr_debug + ("All sent frames acked. Stopped T2(retransmit)\n"); + } + } else { + skb = skb_peek(&shdlc->ack_pending_q); + + mod_timer(&shdlc->t2_timer, *(unsigned long *)skb->cb + + msecs_to_jiffies(SHDLC_T2_VALUE_MS)); + shdlc->t2_active = true; + + pr_debug + ("Start T2(retransmit) for remaining unacked sent frames\n"); + } +} + +/* + * Receive validated frames from lower layer. skb contains HCI payload only. + * Handle according to algorithm at spec:10.8.2 + */ +static void nfc_shdlc_rcv_i_frame(struct nfc_shdlc *shdlc, + struct sk_buff *skb, int ns, int nr) +{ + int x_ns = ns; + int y_nr = nr; + + pr_debug("recvd I-frame %d, remote waiting frame %d\n", ns, nr); + + if (shdlc->state != SHDLC_CONNECTED) + goto exit; + + if (x_ns != shdlc->nr) { + nfc_shdlc_send_s_frame(shdlc, S_FRAME_REJ, shdlc->nr); + goto exit; + } + + if (shdlc->t1_active == false) { + shdlc->t1_active = true; + mod_timer(&shdlc->t1_timer, + msecs_to_jiffies(SHDLC_T1_VALUE_MS(shdlc->w))); + pr_debug("(re)Start T1(send ack)\n"); + } + + if (skb->len) { + nfc_hci_recv_frame(shdlc->hdev, skb); + skb = NULL; + } + + shdlc->nr = (shdlc->nr + 1) % 8; + + if (nfc_shdlc_x_lt_y_lteq_z(shdlc->dnr, y_nr, shdlc->ns)) { + nfc_shdlc_reset_t2(shdlc, y_nr); + + shdlc->dnr = y_nr; + } + +exit: + if (skb) + kfree_skb(skb); +} + +static void nfc_shdlc_rcv_ack(struct nfc_shdlc *shdlc, int y_nr) +{ + pr_debug("remote acked up to frame %d excluded\n", y_nr); + + if (nfc_shdlc_x_lt_y_lteq_z(shdlc->dnr, y_nr, shdlc->ns)) { + nfc_shdlc_reset_t2(shdlc, y_nr); + shdlc->dnr = y_nr; + } +} + +static void nfc_shdlc_requeue_ack_pending(struct nfc_shdlc *shdlc) +{ + struct sk_buff *skb; + + pr_debug("ns reset to %d\n", shdlc->dnr); + + while ((skb = skb_dequeue_tail(&shdlc->ack_pending_q))) { + skb_pull(skb, 2); /* remove len+control */ + skb_trim(skb, skb->len - 2); /* remove crc */ + skb_queue_head(&shdlc->send_q, skb); + } + shdlc->ns = shdlc->dnr; +} + +static void nfc_shdlc_rcv_rej(struct nfc_shdlc *shdlc, int y_nr) +{ + struct sk_buff *skb; + + pr_debug("remote asks retransmition from frame %d\n", y_nr); + + if (nfc_shdlc_x_lteq_y_lt_z(shdlc->dnr, y_nr, shdlc->ns)) { + if (shdlc->t2_active) { + del_timer_sync(&shdlc->t2_timer); + shdlc->t2_active = false; + pr_debug("Stopped T2(retransmit)\n"); + } + + if (shdlc->dnr != y_nr) { + while ((shdlc->dnr = ((shdlc->dnr + 1) % 8)) != y_nr) { + skb = skb_dequeue(&shdlc->ack_pending_q); + kfree_skb(skb); + } + } + + nfc_shdlc_requeue_ack_pending(shdlc); + } +} + +/* See spec RR:10.8.3 REJ:10.8.4 */ +static void nfc_shdlc_rcv_s_frame(struct nfc_shdlc *shdlc, + enum sframe_type s_frame_type, int nr) +{ + struct sk_buff *skb; + + if (shdlc->state != SHDLC_CONNECTED) + return; + + switch (s_frame_type) { + case S_FRAME_RR: + nfc_shdlc_rcv_ack(shdlc, nr); + if (shdlc->rnr == true) { /* see SHDLC 10.7.7 */ + shdlc->rnr = false; + if (shdlc->send_q.qlen == 0) { + skb = nfc_shdlc_alloc_skb(shdlc, 0); + if (skb) + skb_queue_tail(&shdlc->send_q, skb); + } + } + break; + case S_FRAME_REJ: + nfc_shdlc_rcv_rej(shdlc, nr); + break; + case S_FRAME_RNR: + nfc_shdlc_rcv_ack(shdlc, nr); + shdlc->rnr = true; + break; + default: + break; + } +} + +static void nfc_shdlc_connect_complete(struct nfc_shdlc *shdlc, int r) +{ + pr_debug("result=%d\n", r); + + del_timer_sync(&shdlc->connect_timer); + + if (r == 0) { + shdlc->ns = 0; + shdlc->nr = 0; + shdlc->dnr = 0; + + shdlc->state = SHDLC_CONNECTED; + } else { + shdlc->state = SHDLC_DISCONNECTED; + + /* + * TODO: Could it be possible that there are pending + * executing commands that are waiting for connect to complete + * before they can be carried? As connect is a blocking + * operation, it would require that the userspace process can + * send commands on the same device from a second thread before + * the device is up. I don't think that is possible, is it? + */ + } + + shdlc->connect_result = r; + + wake_up(shdlc->connect_wq); +} + +static int nfc_shdlc_connect_initiate(struct nfc_shdlc *shdlc) +{ + struct sk_buff *skb; + + pr_debug("\n"); + + skb = nfc_shdlc_alloc_skb(shdlc, 2); + if (skb == NULL) + return -ENOMEM; + + *skb_put(skb, 1) = SHDLC_MAX_WINDOW; + *skb_put(skb, 1) = SHDLC_SREJ_SUPPORT ? 1 : 0; + + return nfc_shdlc_send_u_frame(shdlc, skb, U_FRAME_RSET); +} + +static int nfc_shdlc_connect_send_ua(struct nfc_shdlc *shdlc) +{ + struct sk_buff *skb; + + pr_debug("\n"); + + skb = nfc_shdlc_alloc_skb(shdlc, 0); + if (skb == NULL) + return -ENOMEM; + + return nfc_shdlc_send_u_frame(shdlc, skb, U_FRAME_UA); +} + +static void nfc_shdlc_rcv_u_frame(struct nfc_shdlc *shdlc, + struct sk_buff *skb, + enum uframe_modifier u_frame_modifier) +{ + u8 w = SHDLC_MAX_WINDOW; + bool srej_support = SHDLC_SREJ_SUPPORT; + int r; + + pr_debug("u_frame_modifier=%d\n", u_frame_modifier); + + switch (u_frame_modifier) { + case U_FRAME_RSET: + if (shdlc->state == SHDLC_NEGOCIATING) { + /* we sent RSET, but chip wants to negociate */ + if (skb->len > 0) + w = skb->data[0]; + + if (skb->len > 1) + srej_support = skb->data[1] & 0x01 ? true : + false; + + if ((w <= SHDLC_MAX_WINDOW) && + (SHDLC_SREJ_SUPPORT || (srej_support == false))) { + shdlc->w = w; + shdlc->srej_support = srej_support; + r = nfc_shdlc_connect_send_ua(shdlc); + nfc_shdlc_connect_complete(shdlc, r); + } + } else if (shdlc->state > SHDLC_NEGOCIATING) { + /* + * TODO: Chip wants to reset link + * send ua, empty skb lists, reset counters + * propagate info to HCI layer + */ + } + break; + case U_FRAME_UA: + if ((shdlc->state == SHDLC_CONNECTING && + shdlc->connect_tries > 0) || + (shdlc->state == SHDLC_NEGOCIATING)) + nfc_shdlc_connect_complete(shdlc, 0); + break; + default: + break; + } + + kfree_skb(skb); +} + +static void nfc_shdlc_handle_rcv_queue(struct nfc_shdlc *shdlc) +{ + struct sk_buff *skb; + u8 control; + int nr; + int ns; + enum sframe_type s_frame_type; + enum uframe_modifier u_frame_modifier; + + if (shdlc->rcv_q.qlen) + pr_debug("rcvQlen=%d\n", shdlc->rcv_q.qlen); + + while ((skb = skb_dequeue(&shdlc->rcv_q)) != NULL) { + control = skb->data[0]; + skb_pull(skb, 1); + switch (control & SHDLC_CONTROL_HEAD_MASK) { + case SHDLC_CONTROL_HEAD_I: + case SHDLC_CONTROL_HEAD_I2: + ns = (control & SHDLC_CONTROL_NS_MASK) >> 3; + nr = control & SHDLC_CONTROL_NR_MASK; + nfc_shdlc_rcv_i_frame(shdlc, skb, ns, nr); + break; + case SHDLC_CONTROL_HEAD_S: + s_frame_type = (control & SHDLC_CONTROL_TYPE_MASK) >> 3; + nr = control & SHDLC_CONTROL_NR_MASK; + nfc_shdlc_rcv_s_frame(shdlc, s_frame_type, nr); + kfree_skb(skb); + break; + case SHDLC_CONTROL_HEAD_U: + u_frame_modifier = control & SHDLC_CONTROL_M_MASK; + nfc_shdlc_rcv_u_frame(shdlc, skb, u_frame_modifier); + break; + default: + pr_err("UNKNOWN Control=%d\n", control); + kfree_skb(skb); + break; + } + } +} + +static int nfc_shdlc_w_used(int ns, int dnr) +{ + int unack_count; + + if (dnr <= ns) + unack_count = ns - dnr; + else + unack_count = 8 - dnr + ns; + + return unack_count; +} + +/* Send frames according to algorithm at spec:10.8.1 */ +static void nfc_shdlc_handle_send_queue(struct nfc_shdlc *shdlc) +{ + struct sk_buff *skb; + int r; + unsigned long time_sent; + + if (shdlc->send_q.qlen) + pr_debug + ("sendQlen=%d ns=%d dnr=%d rnr=%s w_room=%d unackQlen=%d\n", + shdlc->send_q.qlen, shdlc->ns, shdlc->dnr, + shdlc->rnr == false ? "false" : "true", + shdlc->w - nfc_shdlc_w_used(shdlc->ns, shdlc->dnr), + shdlc->ack_pending_q.qlen); + + while (shdlc->send_q.qlen && shdlc->ack_pending_q.qlen < shdlc->w && + (shdlc->rnr == false)) { + + if (shdlc->t1_active) { + del_timer_sync(&shdlc->t1_timer); + shdlc->t1_active = false; + pr_debug("Stopped T1(send ack)\n"); + } + + skb = skb_dequeue(&shdlc->send_q); + + *skb_push(skb, 1) = SHDLC_CONTROL_HEAD_I | (shdlc->ns << 3) | + shdlc->nr; + + pr_debug("Sending I-Frame %d, waiting to rcv %d\n", shdlc->ns, + shdlc->nr); + /* SHDLC_DUMP_SKB("shdlc frame written", skb); */ + + nfc_shdlc_add_len_crc(skb); + + r = shdlc->ops->xmit(shdlc, skb); + if (r < 0) { + /* + * TODO: Cannot send, shdlc machine is dead, we + * must propagate the information up to HCI. + */ + shdlc->hard_fault = r; + break; + } + + shdlc->ns = (shdlc->ns + 1) % 8; + + time_sent = jiffies; + *(unsigned long *)skb->cb = time_sent; + + skb_queue_tail(&shdlc->ack_pending_q, skb); + + if (shdlc->t2_active == false) { + shdlc->t2_active = true; + mod_timer(&shdlc->t2_timer, time_sent + + msecs_to_jiffies(SHDLC_T2_VALUE_MS)); + pr_debug("Started T2 (retransmit)\n"); + } + } +} + +static void nfc_shdlc_connect_timeout(unsigned long data) +{ + struct nfc_shdlc *shdlc = (struct nfc_shdlc *)data; + + pr_debug("\n"); + + queue_work(shdlc->sm_wq, &shdlc->sm_work); +} + +static void nfc_shdlc_t1_timeout(unsigned long data) +{ + struct nfc_shdlc *shdlc = (struct nfc_shdlc *)data; + + pr_debug("SoftIRQ: need to send ack\n"); + + queue_work(shdlc->sm_wq, &shdlc->sm_work); +} + +static void nfc_shdlc_t2_timeout(unsigned long data) +{ + struct nfc_shdlc *shdlc = (struct nfc_shdlc *)data; + + pr_debug("SoftIRQ: need to retransmit\n"); + + queue_work(shdlc->sm_wq, &shdlc->sm_work); +} + +static void nfc_shdlc_sm_work(struct work_struct *work) +{ + struct nfc_shdlc *shdlc = container_of(work, struct nfc_shdlc, sm_work); + int r; + + pr_debug("\n"); + + mutex_lock(&shdlc->state_mutex); + + switch (shdlc->state) { + case SHDLC_DISCONNECTED: + skb_queue_purge(&shdlc->rcv_q); + skb_queue_purge(&shdlc->send_q); + skb_queue_purge(&shdlc->ack_pending_q); + break; + case SHDLC_CONNECTING: + if (shdlc->connect_tries++ < 5) + r = nfc_shdlc_connect_initiate(shdlc); + else + r = -ETIME; + if (r < 0) + nfc_shdlc_connect_complete(shdlc, r); + else { + mod_timer(&shdlc->connect_timer, jiffies + + msecs_to_jiffies(SHDLC_CONNECT_VALUE_MS)); + + shdlc->state = SHDLC_NEGOCIATING; + } + break; + case SHDLC_NEGOCIATING: + if (timer_pending(&shdlc->connect_timer) == 0) { + shdlc->state = SHDLC_CONNECTING; + queue_work(shdlc->sm_wq, &shdlc->sm_work); + } + + nfc_shdlc_handle_rcv_queue(shdlc); + break; + case SHDLC_CONNECTED: + nfc_shdlc_handle_rcv_queue(shdlc); + nfc_shdlc_handle_send_queue(shdlc); + + if (shdlc->t1_active && timer_pending(&shdlc->t1_timer) == 0) { + pr_debug + ("Handle T1(send ack) elapsed (T1 now inactive)\n"); + + shdlc->t1_active = false; + r = nfc_shdlc_send_s_frame(shdlc, S_FRAME_RR, + shdlc->nr); + if (r < 0) + shdlc->hard_fault = r; + } + + if (shdlc->t2_active && timer_pending(&shdlc->t2_timer) == 0) { + pr_debug + ("Handle T2(retransmit) elapsed (T2 inactive)\n"); + + shdlc->t2_active = false; + + nfc_shdlc_requeue_ack_pending(shdlc); + nfc_shdlc_handle_send_queue(shdlc); + } + + if (shdlc->hard_fault) { + /* + * TODO: Handle hard_fault that occured during + * this invocation of the shdlc worker + */ + } + break; + default: + break; + } + mutex_unlock(&shdlc->state_mutex); +} + +/* + * Called from syscall context to establish shdlc link. Sleeps until + * link is ready or failure. + */ +static int nfc_shdlc_connect(struct nfc_shdlc *shdlc) +{ + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(connect_wq); + + pr_debug("\n"); + + mutex_lock(&shdlc->state_mutex); + + shdlc->state = SHDLC_CONNECTING; + shdlc->connect_wq = &connect_wq; + shdlc->connect_tries = 0; + shdlc->connect_result = 1; + + mutex_unlock(&shdlc->state_mutex); + + queue_work(shdlc->sm_wq, &shdlc->sm_work); + + wait_event(connect_wq, shdlc->connect_result != 1); + + return shdlc->connect_result; +} + +static void nfc_shdlc_disconnect(struct nfc_shdlc *shdlc) +{ + pr_debug("\n"); + + mutex_lock(&shdlc->state_mutex); + + shdlc->state = SHDLC_DISCONNECTED; + + mutex_unlock(&shdlc->state_mutex); + + queue_work(shdlc->sm_wq, &shdlc->sm_work); +} + +/* + * Receive an incoming shdlc frame. Frame has already been crc-validated. + * skb contains only LLC header and payload. + * If skb == NULL, it is a notification that the link below is dead. + */ +void nfc_shdlc_recv_frame(struct nfc_shdlc *shdlc, struct sk_buff *skb) +{ + if (skb == NULL) { + pr_err("NULL Frame -> link is dead\n"); + shdlc->hard_fault = -EREMOTEIO; + } else { + SHDLC_DUMP_SKB("incoming frame", skb); + skb_queue_tail(&shdlc->rcv_q, skb); + } + + queue_work(shdlc->sm_wq, &shdlc->sm_work); +} +EXPORT_SYMBOL(nfc_shdlc_recv_frame); + +static int nfc_shdlc_open(struct nfc_hci_dev *hdev) +{ + struct nfc_shdlc *shdlc = nfc_hci_get_clientdata(hdev); + int r; + + pr_debug("\n"); + + if (shdlc->ops->open) { + r = shdlc->ops->open(shdlc); + if (r < 0) + return r; + } + + r = nfc_shdlc_connect(shdlc); + if (r < 0 && shdlc->ops->close) + shdlc->ops->close(shdlc); + + return r; +} + +static void nfc_shdlc_close(struct nfc_hci_dev *hdev) +{ + struct nfc_shdlc *shdlc = nfc_hci_get_clientdata(hdev); + + pr_debug("\n"); + + nfc_shdlc_disconnect(shdlc); + + if (shdlc->ops->close) + shdlc->ops->close(shdlc); +} + +static int nfc_shdlc_hci_ready(struct nfc_hci_dev *hdev) +{ + struct nfc_shdlc *shdlc = nfc_hci_get_clientdata(hdev); + int r = 0; + + pr_debug("\n"); + + if (shdlc->ops->hci_ready) + r = shdlc->ops->hci_ready(shdlc); + + return r; +} + +static int nfc_shdlc_xmit(struct nfc_hci_dev *hdev, struct sk_buff *skb) +{ + struct nfc_shdlc *shdlc = nfc_hci_get_clientdata(hdev); + + SHDLC_DUMP_SKB("queuing HCP packet to shdlc", skb); + + skb_queue_tail(&shdlc->send_q, skb); + + queue_work(shdlc->sm_wq, &shdlc->sm_work); + + return 0; +} + +static int nfc_shdlc_start_poll(struct nfc_hci_dev *hdev, u32 protocols) +{ + struct nfc_shdlc *shdlc = nfc_hci_get_clientdata(hdev); + + pr_debug("\n"); + + if (shdlc->ops->start_poll) + return shdlc->ops->start_poll(shdlc, protocols); + + return 0; +} + +static int nfc_shdlc_target_from_gate(struct nfc_hci_dev *hdev, u8 gate, + struct nfc_target *target) +{ + struct nfc_shdlc *shdlc = nfc_hci_get_clientdata(hdev); + + if (shdlc->ops->target_from_gate) + return shdlc->ops->target_from_gate(shdlc, gate, target); + + return -EPERM; +} + +static int nfc_shdlc_complete_target_discovered(struct nfc_hci_dev *hdev, + u8 gate, + struct nfc_target *target) +{ + struct nfc_shdlc *shdlc = nfc_hci_get_clientdata(hdev); + + pr_debug("\n"); + + if (shdlc->ops->complete_target_discovered) + return shdlc->ops->complete_target_discovered(shdlc, gate, + target); + + return 0; +} + +static int nfc_shdlc_data_exchange(struct nfc_hci_dev *hdev, + struct nfc_target *target, + struct sk_buff *skb, + struct sk_buff **res_skb) +{ + struct nfc_shdlc *shdlc = nfc_hci_get_clientdata(hdev); + + if (shdlc->ops->data_exchange) + return shdlc->ops->data_exchange(shdlc, target, skb, res_skb); + + return -EPERM; +} + +static struct nfc_hci_ops shdlc_ops = { + .open = nfc_shdlc_open, + .close = nfc_shdlc_close, + .hci_ready = nfc_shdlc_hci_ready, + .xmit = nfc_shdlc_xmit, + .start_poll = nfc_shdlc_start_poll, + .target_from_gate = nfc_shdlc_target_from_gate, + .complete_target_discovered = nfc_shdlc_complete_target_discovered, + .data_exchange = nfc_shdlc_data_exchange, +}; + +struct nfc_shdlc *nfc_shdlc_allocate(struct nfc_shdlc_ops *ops, + struct nfc_hci_init_data *init_data, + u32 protocols, + int tx_headroom, int tx_tailroom, + int max_link_payload, const char *devname) +{ + struct nfc_shdlc *shdlc; + int r; + char name[32]; + + if (ops->xmit == NULL) + return NULL; + + shdlc = kzalloc(sizeof(struct nfc_shdlc), GFP_KERNEL); + if (shdlc == NULL) + return NULL; + + mutex_init(&shdlc->state_mutex); + shdlc->ops = ops; + shdlc->state = SHDLC_DISCONNECTED; + + init_timer(&shdlc->connect_timer); + shdlc->connect_timer.data = (unsigned long)shdlc; + shdlc->connect_timer.function = nfc_shdlc_connect_timeout; + + init_timer(&shdlc->t1_timer); + shdlc->t1_timer.data = (unsigned long)shdlc; + shdlc->t1_timer.function = nfc_shdlc_t1_timeout; + + init_timer(&shdlc->t2_timer); + shdlc->t2_timer.data = (unsigned long)shdlc; + shdlc->t2_timer.function = nfc_shdlc_t2_timeout; + + shdlc->w = SHDLC_MAX_WINDOW; + shdlc->srej_support = SHDLC_SREJ_SUPPORT; + + skb_queue_head_init(&shdlc->rcv_q); + skb_queue_head_init(&shdlc->send_q); + skb_queue_head_init(&shdlc->ack_pending_q); + + INIT_WORK(&shdlc->sm_work, nfc_shdlc_sm_work); + snprintf(name, sizeof(name), "%s_shdlc_sm_wq", devname); + shdlc->sm_wq = alloc_workqueue(name, WQ_NON_REENTRANT | WQ_UNBOUND | + WQ_MEM_RECLAIM, 1); + if (shdlc->sm_wq == NULL) + goto err_allocwq; + + shdlc->client_headroom = tx_headroom; + shdlc->client_tailroom = tx_tailroom; + + shdlc->hdev = nfc_hci_allocate_device(&shdlc_ops, init_data, protocols, + tx_headroom + SHDLC_LLC_HEAD_ROOM, + tx_tailroom + SHDLC_LLC_TAIL_ROOM, + max_link_payload); + if (shdlc->hdev == NULL) + goto err_allocdev; + + nfc_hci_set_clientdata(shdlc->hdev, shdlc); + + r = nfc_hci_register_device(shdlc->hdev); + if (r < 0) + goto err_regdev; + + return shdlc; + +err_regdev: + nfc_hci_free_device(shdlc->hdev); + +err_allocdev: + destroy_workqueue(shdlc->sm_wq); + +err_allocwq: + kfree(shdlc); + + return NULL; +} +EXPORT_SYMBOL(nfc_shdlc_allocate); + +void nfc_shdlc_free(struct nfc_shdlc *shdlc) +{ + pr_debug("\n"); + + /* TODO: Check that this cannot be called while still in use */ + + nfc_hci_unregister_device(shdlc->hdev); + nfc_hci_free_device(shdlc->hdev); + + destroy_workqueue(shdlc->sm_wq); + + skb_queue_purge(&shdlc->rcv_q); + skb_queue_purge(&shdlc->send_q); + skb_queue_purge(&shdlc->ack_pending_q); + + kfree(shdlc); +} +EXPORT_SYMBOL(nfc_shdlc_free); + +void nfc_shdlc_set_clientdata(struct nfc_shdlc *shdlc, void *clientdata) +{ + pr_debug("\n"); + + shdlc->clientdata = clientdata; +} +EXPORT_SYMBOL(nfc_shdlc_set_clientdata); + +void *nfc_shdlc_get_clientdata(struct nfc_shdlc *shdlc) +{ + return shdlc->clientdata; +} +EXPORT_SYMBOL(nfc_shdlc_get_clientdata); + +struct nfc_hci_dev *nfc_shdlc_get_hci_dev(struct nfc_shdlc *shdlc) +{ + return shdlc->hdev; +} +EXPORT_SYMBOL(nfc_shdlc_get_hci_dev); diff --git a/net/nfc/llcp/commands.c b/net/nfc/llcp/commands.c index 7b76eb7192f..11a3b7d98dc 100644 --- a/net/nfc/llcp/commands.c +++ b/net/nfc/llcp/commands.c @@ -102,7 +102,7 @@ u8 *nfc_llcp_build_tlv(u8 type, u8 *value, u8 value_length, u8 *tlv_length) length = llcp_tlv_length[type]; if (length == 0 && value_length == 0) return NULL; - else + else if (length == 0) length = value_length; *tlv_length = 2 + length; @@ -248,7 +248,7 @@ int nfc_llcp_disconnect(struct nfc_llcp_sock *sock) skb_reserve(skb, dev->tx_headroom + NFC_HEADER_SIZE); - skb = llcp_add_header(skb, sock->ssap, sock->dsap, LLCP_PDU_DISC); + skb = llcp_add_header(skb, sock->dsap, sock->ssap, LLCP_PDU_DISC); skb_queue_tail(&local->tx_queue, skb); @@ -416,7 +416,7 @@ int nfc_llcp_send_dm(struct nfc_llcp_local *local, u8 ssap, u8 dsap, u8 reason) skb_reserve(skb, dev->tx_headroom + NFC_HEADER_SIZE); - skb = llcp_add_header(skb, ssap, dsap, LLCP_PDU_DM); + skb = llcp_add_header(skb, dsap, ssap, LLCP_PDU_DM); memcpy(skb_put(skb, 1), &reason, 1); @@ -474,7 +474,7 @@ int nfc_llcp_send_i_frame(struct nfc_llcp_sock *sock, while (remaining_len > 0) { - frag_len = min_t(u16, local->remote_miu, remaining_len); + frag_len = min_t(size_t, local->remote_miu, remaining_len); pr_debug("Fragment %zd bytes remaining %zd", frag_len, remaining_len); @@ -497,7 +497,7 @@ int nfc_llcp_send_i_frame(struct nfc_llcp_sock *sock, release_sock(sk); remaining_len -= frag_len; - msg_ptr += len; + msg_ptr += frag_len; } kfree(msg_data); @@ -522,7 +522,7 @@ int nfc_llcp_send_rr(struct nfc_llcp_sock *sock) skb_put(skb, LLCP_SEQUENCE_SIZE); - skb->data[2] = sock->recv_n % 16; + skb->data[2] = sock->recv_n; skb_queue_head(&local->tx_queue, skb); diff --git a/net/nfc/llcp/llcp.c b/net/nfc/llcp/llcp.c index 17a578f641f..92988aa620d 100644 --- a/net/nfc/llcp/llcp.c +++ b/net/nfc/llcp/llcp.c @@ -307,6 +307,8 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local) u8 *gb_cur, *version_tlv, version, version_length; u8 *lto_tlv, lto, lto_length; u8 *wks_tlv, wks_length; + u8 *miux_tlv, miux_length; + __be16 miux; u8 gb_len = 0; version = LLCP_VERSION_11; @@ -316,7 +318,7 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local) /* 1500 ms */ lto = 150; - lto_tlv = nfc_llcp_build_tlv(LLCP_TLV_VERSION, <o, 1, <o_length); + lto_tlv = nfc_llcp_build_tlv(LLCP_TLV_LTO, <o, 1, <o_length); gb_len += lto_length; pr_debug("Local wks 0x%lx\n", local->local_wks); @@ -324,6 +326,11 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local) &wks_length); gb_len += wks_length; + miux = cpu_to_be16(LLCP_MAX_MIUX); + miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0, + &miux_length); + gb_len += miux_length; + gb_len += ARRAY_SIZE(llcp_magic); if (gb_len > NFC_MAX_GT_LEN) { @@ -345,6 +352,9 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local) memcpy(gb_cur, wks_tlv, wks_length); gb_cur += wks_length; + memcpy(gb_cur, miux_tlv, miux_length); + gb_cur += miux_length; + kfree(version_tlv); kfree(lto_tlv); @@ -388,6 +398,9 @@ static void nfc_llcp_tx_work(struct work_struct *work) skb = skb_dequeue(&local->tx_queue); if (skb != NULL) { pr_debug("Sending pending skb\n"); + print_hex_dump(KERN_DEBUG, "LLCP Tx: ", DUMP_PREFIX_OFFSET, + 16, 1, skb->data, skb->len, true); + nfc_data_exchange(local->dev, local->target_idx, skb, nfc_llcp_recv, local); } else { @@ -425,7 +438,7 @@ static u8 nfc_llcp_nr(struct sk_buff *pdu) static void nfc_llcp_set_nrns(struct nfc_llcp_sock *sock, struct sk_buff *pdu) { - pdu->data[2] = (sock->send_n << 4) | (sock->recv_n % 16); + pdu->data[2] = (sock->send_n << 4) | (sock->recv_n); sock->send_n = (sock->send_n + 1) % 16; sock->recv_ack_n = (sock->recv_n - 1) % 16; } @@ -814,6 +827,10 @@ static void nfc_llcp_rx_work(struct work_struct *work) pr_debug("ptype 0x%x dsap 0x%x ssap 0x%x\n", ptype, dsap, ssap); + if (ptype != LLCP_PDU_SYMM) + print_hex_dump(KERN_DEBUG, "LLCP Rx: ", DUMP_PREFIX_OFFSET, + 16, 1, skb->data, skb->len, true); + switch (ptype) { case LLCP_PDU_SYMM: pr_debug("SYMM\n"); diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 9ec065bb9ee..8737c2089fd 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -477,7 +477,7 @@ static int nci_activate_target(struct nfc_dev *nfc_dev, __u32 target_idx, } if (atomic_read(&ndev->state) == NCI_W4_HOST_SELECT) { - param.rf_discovery_id = target->idx; + param.rf_discovery_id = target->logical_idx; if (protocol == NFC_PROTO_JEWEL) param.rf_protocol = NCI_RF_PROTOCOL_T1T; diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c index 2e3dee42196..99e1632e6aa 100644 --- a/net/nfc/nci/ntf.c +++ b/net/nfc/nci/ntf.c @@ -227,7 +227,7 @@ static void nci_add_new_target(struct nci_dev *ndev, for (i = 0; i < ndev->n_targets; i++) { target = &ndev->targets[i]; - if (target->idx == ntf->rf_discovery_id) { + if (target->logical_idx == ntf->rf_discovery_id) { /* This target already exists, add the new protocol */ nci_add_new_protocol(ndev, target, ntf->rf_protocol, ntf->rf_tech_and_mode, @@ -248,10 +248,10 @@ static void nci_add_new_target(struct nci_dev *ndev, ntf->rf_tech_and_mode, &ntf->rf_tech_specific_params); if (!rc) { - target->idx = ntf->rf_discovery_id; + target->logical_idx = ntf->rf_discovery_id; ndev->n_targets++; - pr_debug("target_idx %d, n_targets %d\n", target->idx, + pr_debug("logical idx %d, n_targets %d\n", target->logical_idx, ndev->n_targets); } } @@ -372,10 +372,11 @@ static void nci_target_auto_activated(struct nci_dev *ndev, if (rc) return; - target->idx = ntf->rf_discovery_id; + target->logical_idx = ntf->rf_discovery_id; ndev->n_targets++; - pr_debug("target_idx %d, n_targets %d\n", target->idx, ndev->n_targets); + pr_debug("logical idx %d, n_targets %d\n", + target->logical_idx, ndev->n_targets); nfc_targets_found(ndev->nfc_dev, ndev->targets, ndev->n_targets); } diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 6404052d6c0..f1829f6ae9c 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -63,19 +63,23 @@ static int nfc_genl_send_target(struct sk_buff *msg, struct nfc_target *target, genl_dump_check_consistent(cb, hdr, &nfc_genl_family); - NLA_PUT_U32(msg, NFC_ATTR_TARGET_INDEX, target->idx); - NLA_PUT_U32(msg, NFC_ATTR_PROTOCOLS, target->supported_protocols); - NLA_PUT_U16(msg, NFC_ATTR_TARGET_SENS_RES, target->sens_res); - NLA_PUT_U8(msg, NFC_ATTR_TARGET_SEL_RES, target->sel_res); - if (target->nfcid1_len > 0) - NLA_PUT(msg, NFC_ATTR_TARGET_NFCID1, target->nfcid1_len, - target->nfcid1); - if (target->sensb_res_len > 0) - NLA_PUT(msg, NFC_ATTR_TARGET_SENSB_RES, target->sensb_res_len, - target->sensb_res); - if (target->sensf_res_len > 0) - NLA_PUT(msg, NFC_ATTR_TARGET_SENSF_RES, target->sensf_res_len, - target->sensf_res); + if (nla_put_u32(msg, NFC_ATTR_TARGET_INDEX, target->idx) || + nla_put_u32(msg, NFC_ATTR_PROTOCOLS, target->supported_protocols) || + nla_put_u16(msg, NFC_ATTR_TARGET_SENS_RES, target->sens_res) || + nla_put_u8(msg, NFC_ATTR_TARGET_SEL_RES, target->sel_res)) + goto nla_put_failure; + if (target->nfcid1_len > 0 && + nla_put(msg, NFC_ATTR_TARGET_NFCID1, target->nfcid1_len, + target->nfcid1)) + goto nla_put_failure; + if (target->sensb_res_len > 0 && + nla_put(msg, NFC_ATTR_TARGET_SENSB_RES, target->sensb_res_len, + target->sensb_res)) + goto nla_put_failure; + if (target->sensf_res_len > 0 && + nla_put(msg, NFC_ATTR_TARGET_SENSF_RES, target->sensf_res_len, + target->sensf_res)) + goto nla_put_failure; return genlmsg_end(msg, hdr); @@ -170,7 +174,8 @@ int nfc_genl_targets_found(struct nfc_dev *dev) if (!hdr) goto free_msg; - NLA_PUT_U32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx); + if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -183,6 +188,37 @@ free_msg: return -EMSGSIZE; } +int nfc_genl_target_lost(struct nfc_dev *dev, u32 target_idx) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, + NFC_EVENT_TARGET_LOST); + if (!hdr) + goto free_msg; + + if (nla_put_string(msg, NFC_ATTR_DEVICE_NAME, nfc_device_name(dev)) || + nla_put_u32(msg, NFC_ATTR_TARGET_INDEX, target_idx)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_KERNEL); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return -EMSGSIZE; +} + int nfc_genl_device_added(struct nfc_dev *dev) { struct sk_buff *msg; @@ -197,10 +233,11 @@ int nfc_genl_device_added(struct nfc_dev *dev) if (!hdr) goto free_msg; - NLA_PUT_STRING(msg, NFC_ATTR_DEVICE_NAME, nfc_device_name(dev)); - NLA_PUT_U32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx); - NLA_PUT_U32(msg, NFC_ATTR_PROTOCOLS, dev->supported_protocols); - NLA_PUT_U8(msg, NFC_ATTR_DEVICE_POWERED, dev->dev_up); + if (nla_put_string(msg, NFC_ATTR_DEVICE_NAME, nfc_device_name(dev)) || + nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) || + nla_put_u32(msg, NFC_ATTR_PROTOCOLS, dev->supported_protocols) || + nla_put_u8(msg, NFC_ATTR_DEVICE_POWERED, dev->dev_up)) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -229,7 +266,8 @@ int nfc_genl_device_removed(struct nfc_dev *dev) if (!hdr) goto free_msg; - NLA_PUT_U32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx); + if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -259,10 +297,11 @@ static int nfc_genl_send_device(struct sk_buff *msg, struct nfc_dev *dev, if (cb) genl_dump_check_consistent(cb, hdr, &nfc_genl_family); - NLA_PUT_STRING(msg, NFC_ATTR_DEVICE_NAME, nfc_device_name(dev)); - NLA_PUT_U32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx); - NLA_PUT_U32(msg, NFC_ATTR_PROTOCOLS, dev->supported_protocols); - NLA_PUT_U8(msg, NFC_ATTR_DEVICE_POWERED, dev->dev_up); + if (nla_put_string(msg, NFC_ATTR_DEVICE_NAME, nfc_device_name(dev)) || + nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) || + nla_put_u32(msg, NFC_ATTR_PROTOCOLS, dev->supported_protocols) || + nla_put_u8(msg, NFC_ATTR_DEVICE_POWERED, dev->dev_up)) + goto nla_put_failure; return genlmsg_end(msg, hdr); @@ -339,11 +378,14 @@ int nfc_genl_dep_link_up_event(struct nfc_dev *dev, u32 target_idx, if (!hdr) goto free_msg; - NLA_PUT_U32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx); - if (rf_mode == NFC_RF_INITIATOR) - NLA_PUT_U32(msg, NFC_ATTR_TARGET_INDEX, target_idx); - NLA_PUT_U8(msg, NFC_ATTR_COMM_MODE, comm_mode); - NLA_PUT_U8(msg, NFC_ATTR_RF_MODE, rf_mode); + if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) + goto nla_put_failure; + if (rf_mode == NFC_RF_INITIATOR && + nla_put_u32(msg, NFC_ATTR_TARGET_INDEX, target_idx)) + goto nla_put_failure; + if (nla_put_u8(msg, NFC_ATTR_COMM_MODE, comm_mode) || + nla_put_u8(msg, NFC_ATTR_RF_MODE, rf_mode)) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -376,7 +418,8 @@ int nfc_genl_dep_link_down_event(struct nfc_dev *dev) if (!hdr) goto free_msg; - NLA_PUT_U32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx); + if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) + goto nla_put_failure; genlmsg_end(msg, hdr); diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h index ec8794c1099..7d589a81942 100644 --- a/net/nfc/nfc.h +++ b/net/nfc/nfc.h @@ -119,6 +119,7 @@ void nfc_genl_data_init(struct nfc_genl_data *genl_data); void nfc_genl_data_exit(struct nfc_genl_data *genl_data); int nfc_genl_targets_found(struct nfc_dev *dev); +int nfc_genl_target_lost(struct nfc_dev *dev, u32 target_idx); int nfc_genl_device_added(struct nfc_dev *dev); int nfc_genl_device_removed(struct nfc_dev *dev); @@ -127,7 +128,7 @@ int nfc_genl_dep_link_up_event(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode); int nfc_genl_dep_link_down_event(struct nfc_dev *dev); -struct nfc_dev *nfc_get_device(unsigned idx); +struct nfc_dev *nfc_get_device(unsigned int idx); static inline void nfc_put_device(struct nfc_dev *dev) { diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 5a839ceb2e8..ec1134c9e07 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -92,6 +92,12 @@ static int rawsock_connect(struct socket *sock, struct sockaddr *_addr, goto error; } + if (addr->target_idx > dev->target_next_idx - 1 || + addr->target_idx < dev->target_next_idx - dev->n_targets) { + rc = -EINVAL; + goto error; + } + rc = nfc_activate_target(dev, addr->target_idx, addr->nfc_protocol); if (rc) goto put_dev; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index e44e631ea95..2c74daa5aca 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -321,7 +321,7 @@ static int queue_userspace_packet(int dp_ifindex, struct sk_buff *skb, return -ENOMEM; nskb = __vlan_put_tag(nskb, vlan_tx_tag_get(nskb)); - if (!skb) + if (!nskb) return -ENOMEM; nskb->vlan_tci = 0; @@ -421,6 +421,19 @@ static int validate_sample(const struct nlattr *attr, return validate_actions(actions, key, depth + 1); } +static int validate_tp_port(const struct sw_flow_key *flow_key) +{ + if (flow_key->eth.type == htons(ETH_P_IP)) { + if (flow_key->ipv4.tp.src && flow_key->ipv4.tp.dst) + return 0; + } else if (flow_key->eth.type == htons(ETH_P_IPV6)) { + if (flow_key->ipv6.tp.src && flow_key->ipv6.tp.dst) + return 0; + } + + return -EINVAL; +} + static int validate_set(const struct nlattr *a, const struct sw_flow_key *flow_key) { @@ -462,18 +475,13 @@ static int validate_set(const struct nlattr *a, if (flow_key->ip.proto != IPPROTO_TCP) return -EINVAL; - if (!flow_key->ipv4.tp.src || !flow_key->ipv4.tp.dst) - return -EINVAL; - - break; + return validate_tp_port(flow_key); case OVS_KEY_ATTR_UDP: if (flow_key->ip.proto != IPPROTO_UDP) return -EINVAL; - if (!flow_key->ipv4.tp.src || !flow_key->ipv4.tp.dst) - return -EINVAL; - break; + return validate_tp_port(flow_key); default: return -EINVAL; @@ -778,15 +786,18 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, tcp_flags = flow->tcp_flags; spin_unlock_bh(&flow->lock); - if (used) - NLA_PUT_U64(skb, OVS_FLOW_ATTR_USED, ovs_flow_used_time(used)); + if (used && + nla_put_u64(skb, OVS_FLOW_ATTR_USED, ovs_flow_used_time(used))) + goto nla_put_failure; - if (stats.n_packets) - NLA_PUT(skb, OVS_FLOW_ATTR_STATS, - sizeof(struct ovs_flow_stats), &stats); + if (stats.n_packets && + nla_put(skb, OVS_FLOW_ATTR_STATS, + sizeof(struct ovs_flow_stats), &stats)) + goto nla_put_failure; - if (tcp_flags) - NLA_PUT_U8(skb, OVS_FLOW_ATTR_TCP_FLAGS, tcp_flags); + if (tcp_flags && + nla_put_u8(skb, OVS_FLOW_ATTR_TCP_FLAGS, tcp_flags)) + goto nla_put_failure; /* If OVS_FLOW_ATTR_ACTIONS doesn't fit, skip dumping the actions if * this is the first flow to be dumped into 'skb'. This is unusual for @@ -1168,7 +1179,8 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, goto nla_put_failure; get_dp_stats(dp, &dp_stats); - NLA_PUT(skb, OVS_DP_ATTR_STATS, sizeof(struct ovs_dp_stats), &dp_stats); + if (nla_put(skb, OVS_DP_ATTR_STATS, sizeof(struct ovs_dp_stats), &dp_stats)) + goto nla_put_failure; return genlmsg_end(skb, ovs_header); @@ -1468,14 +1480,16 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, ovs_header->dp_ifindex = get_dpifindex(vport->dp); - NLA_PUT_U32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no); - NLA_PUT_U32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type); - NLA_PUT_STRING(skb, OVS_VPORT_ATTR_NAME, vport->ops->get_name(vport)); - NLA_PUT_U32(skb, OVS_VPORT_ATTR_UPCALL_PID, vport->upcall_pid); + if (nla_put_u32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no) || + nla_put_u32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type) || + nla_put_string(skb, OVS_VPORT_ATTR_NAME, vport->ops->get_name(vport)) || + nla_put_u32(skb, OVS_VPORT_ATTR_UPCALL_PID, vport->upcall_pid)) + goto nla_put_failure; ovs_vport_get_stats(vport, &vport_stats); - NLA_PUT(skb, OVS_VPORT_ATTR_STATS, sizeof(struct ovs_vport_stats), - &vport_stats); + if (nla_put(skb, OVS_VPORT_ATTR_STATS, sizeof(struct ovs_vport_stats), + &vport_stats)) + goto nla_put_failure; err = ovs_vport_get_options(vport, skb); if (err == -EMSGSIZE) @@ -1641,10 +1655,9 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq, OVS_VPORT_CMD_NEW); if (IS_ERR(reply)) { - err = PTR_ERR(reply); netlink_set_err(init_net.genl_sock, 0, - ovs_dp_vport_multicast_group.id, err); - return 0; + ovs_dp_vport_multicast_group.id, PTR_ERR(reply)); + goto exit_unlock; } genl_notify(reply, genl_info_net(info), info->snd_pid, diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 1252c3081ef..6d4d8097cf9 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -183,7 +183,8 @@ void ovs_flow_used(struct sw_flow *flow, struct sk_buff *skb) u8 tcp_flags = 0; if (flow->key.eth.type == htons(ETH_P_IP) && - flow->key.ip.proto == IPPROTO_TCP) { + flow->key.ip.proto == IPPROTO_TCP && + likely(skb->len >= skb_transport_offset(skb) + sizeof(struct tcphdr))) { u8 *tcp = (u8 *)tcp_hdr(skb); tcp_flags = *(tcp + TCP_FLAGS_OFFSET) & TCP_FLAG_MASK; } @@ -1174,11 +1175,13 @@ int ovs_flow_to_nlattrs(const struct sw_flow_key *swkey, struct sk_buff *skb) struct ovs_key_ethernet *eth_key; struct nlattr *nla, *encap; - if (swkey->phy.priority) - NLA_PUT_U32(skb, OVS_KEY_ATTR_PRIORITY, swkey->phy.priority); + if (swkey->phy.priority && + nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, swkey->phy.priority)) + goto nla_put_failure; - if (swkey->phy.in_port != USHRT_MAX) - NLA_PUT_U32(skb, OVS_KEY_ATTR_IN_PORT, swkey->phy.in_port); + if (swkey->phy.in_port != USHRT_MAX && + nla_put_u32(skb, OVS_KEY_ATTR_IN_PORT, swkey->phy.in_port)) + goto nla_put_failure; nla = nla_reserve(skb, OVS_KEY_ATTR_ETHERNET, sizeof(*eth_key)); if (!nla) @@ -1188,8 +1191,9 @@ int ovs_flow_to_nlattrs(const struct sw_flow_key *swkey, struct sk_buff *skb) memcpy(eth_key->eth_dst, swkey->eth.dst, ETH_ALEN); if (swkey->eth.tci || swkey->eth.type == htons(ETH_P_8021Q)) { - NLA_PUT_BE16(skb, OVS_KEY_ATTR_ETHERTYPE, htons(ETH_P_8021Q)); - NLA_PUT_BE16(skb, OVS_KEY_ATTR_VLAN, swkey->eth.tci); + if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, htons(ETH_P_8021Q)) || + nla_put_be16(skb, OVS_KEY_ATTR_VLAN, swkey->eth.tci)) + goto nla_put_failure; encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP); if (!swkey->eth.tci) goto unencap; @@ -1200,7 +1204,8 @@ int ovs_flow_to_nlattrs(const struct sw_flow_key *swkey, struct sk_buff *skb) if (swkey->eth.type == htons(ETH_P_802_2)) goto unencap; - NLA_PUT_BE16(skb, OVS_KEY_ATTR_ETHERTYPE, swkey->eth.type); + if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, swkey->eth.type)) + goto nla_put_failure; if (swkey->eth.type == htons(ETH_P_IP)) { struct ovs_key_ipv4 *ipv4_key; diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index c1068aed03d..3fd6c0d88e1 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -140,9 +140,9 @@ int ovs_netdev_get_ifindex(const struct vport *vport) return netdev_vport->dev->ifindex; } -static unsigned packet_length(const struct sk_buff *skb) +static unsigned int packet_length(const struct sk_buff *skb) { - unsigned length = skb->len - ETH_HLEN; + unsigned int length = skb->len - ETH_HLEN; if (skb->protocol == htons(ETH_P_8021Q)) length -= VLAN_HLEN; @@ -157,9 +157,9 @@ static int netdev_send(struct vport *vport, struct sk_buff *skb) int len; if (unlikely(packet_length(skb) > mtu && !skb_is_gso(skb))) { - if (net_ratelimit()) - pr_warn("%s: dropped over-mtu packet: %d > %d\n", - ovs_dp_name(vport->dp), packet_length(skb), mtu); + net_warn_ratelimited("%s: dropped over-mtu packet: %d > %d\n", + ovs_dp_name(vport->dp), + packet_length(skb), mtu); goto error; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 4f2c0df7956..0f661745df0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1654,7 +1654,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, skb->data = skb_head; skb->len = skb_len; } - kfree_skb(skb); + consume_skb(skb); skb = nskb; } @@ -1764,7 +1764,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, macoff = netoff = TPACKET_ALIGN(po->tp_hdrlen) + 16 + po->tp_reserve; } else { - unsigned maclen = skb_network_offset(skb); + unsigned int maclen = skb_network_offset(skb); netoff = TPACKET_ALIGN(po->tp_hdrlen + (maclen < 16 ? 16 : maclen)) + po->tp_reserve; @@ -3224,10 +3224,10 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { int len; - int val; + int val, lv = sizeof(val); struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); - void *data; + void *data = &val; struct tpacket_stats st; union tpacket_stats_u st_u; @@ -3242,21 +3242,17 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, switch (optname) { case PACKET_STATISTICS: - if (po->tp_version == TPACKET_V3) { - len = sizeof(struct tpacket_stats_v3); - } else { - if (len > sizeof(struct tpacket_stats)) - len = sizeof(struct tpacket_stats); - } spin_lock_bh(&sk->sk_receive_queue.lock); if (po->tp_version == TPACKET_V3) { + lv = sizeof(struct tpacket_stats_v3); memcpy(&st_u.stats3, &po->stats, - sizeof(struct tpacket_stats)); + sizeof(struct tpacket_stats)); st_u.stats3.tp_freeze_q_cnt = - po->stats_u.stats3.tp_freeze_q_cnt; + po->stats_u.stats3.tp_freeze_q_cnt; st_u.stats3.tp_packets += po->stats.tp_drops; data = &st_u.stats3; } else { + lv = sizeof(struct tpacket_stats); st = po->stats; st.tp_packets += st.tp_drops; data = &st; @@ -3265,31 +3261,16 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, spin_unlock_bh(&sk->sk_receive_queue.lock); break; case PACKET_AUXDATA: - if (len > sizeof(int)) - len = sizeof(int); val = po->auxdata; - - data = &val; break; case PACKET_ORIGDEV: - if (len > sizeof(int)) - len = sizeof(int); val = po->origdev; - - data = &val; break; case PACKET_VNET_HDR: - if (len > sizeof(int)) - len = sizeof(int); val = po->has_vnet_hdr; - - data = &val; break; case PACKET_VERSION: - if (len > sizeof(int)) - len = sizeof(int); val = po->tp_version; - data = &val; break; case PACKET_HDRLEN: if (len > sizeof(int)) @@ -3309,39 +3290,28 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, default: return -EINVAL; } - data = &val; break; case PACKET_RESERVE: - if (len > sizeof(unsigned int)) - len = sizeof(unsigned int); val = po->tp_reserve; - data = &val; break; case PACKET_LOSS: - if (len > sizeof(unsigned int)) - len = sizeof(unsigned int); val = po->tp_loss; - data = &val; break; case PACKET_TIMESTAMP: - if (len > sizeof(int)) - len = sizeof(int); val = po->tp_tstamp; - data = &val; break; case PACKET_FANOUT: - if (len > sizeof(int)) - len = sizeof(int); val = (po->fanout ? ((u32)po->fanout->id | ((u32)po->fanout->type << 16)) : 0); - data = &val; break; default: return -ENOPROTOOPT; } + if (len > lv) + len = lv; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, data, len)) diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index d65f699fbf3..779ce4ff92e 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -129,7 +129,7 @@ static const struct net_proto_family phonet_proto_family = { /* Phonet device header operations */ static int pn_header_create(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, - const void *saddr, unsigned len) + const void *saddr, unsigned int len) { u8 *media = skb_push(skb, 1); diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 9f60008740e..9dd4f926f7d 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -273,7 +273,7 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) hdr = pnp_hdr(skb); if (hdr->data[0] != PN_PEP_TYPE_COMMON) { LIMIT_NETDEBUG(KERN_DEBUG"Phonet unknown PEP type: %u\n", - (unsigned)hdr->data[0]); + (unsigned int)hdr->data[0]); return -EOPNOTSUPP; } @@ -305,7 +305,7 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) default: LIMIT_NETDEBUG(KERN_DEBUG"Phonet unknown PEP indication: %u\n", - (unsigned)hdr->data[1]); + (unsigned int)hdr->data[1]); return -EOPNOTSUPP; } if (wake) @@ -478,9 +478,9 @@ static void pipe_destruct(struct sock *sk) skb_queue_purge(&pn->ctrlreq_queue); } -static u8 pipe_negotiate_fc(const u8 *fcs, unsigned n) +static u8 pipe_negotiate_fc(const u8 *fcs, unsigned int n) { - unsigned i; + unsigned int i; u8 final_fc = PN_NO_FLOW_CONTROL; for (i = 0; i < n; i++) { @@ -1130,6 +1130,9 @@ static int pep_sendmsg(struct kiocb *iocb, struct sock *sk, int flags = msg->msg_flags; int err, done; + if (len > USHRT_MAX) + return -EMSGSIZE; + if ((msg->msg_flags & ~(MSG_DONTWAIT|MSG_EOR|MSG_NOSIGNAL| MSG_CMSG_COMPAT)) || !(msg->msg_flags & MSG_EOR)) diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index 9b9a85ecc4c..36f75a9e2c3 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -44,7 +44,7 @@ struct phonet_net { struct phonet_routes routes; }; -int phonet_net_id __read_mostly; +static int phonet_net_id __read_mostly; static struct phonet_net *phonet_pernet(struct net *net) { @@ -268,7 +268,7 @@ static int phonet_device_autoconf(struct net_device *dev) static void phonet_route_autodel(struct net_device *dev) { struct phonet_net *pnn = phonet_pernet(dev_net(dev)); - unsigned i; + unsigned int i; DECLARE_BITMAP(deleted, 64); /* Remove left-over Phonet routes */ @@ -331,23 +331,6 @@ static int __net_init phonet_init_net(struct net *net) static void __net_exit phonet_exit_net(struct net *net) { - struct phonet_net *pnn = phonet_pernet(net); - struct net_device *dev; - unsigned i; - - rtnl_lock(); - for_each_netdev(net, dev) - phonet_device_destroy(dev); - - for (i = 0; i < 64; i++) { - dev = pnn->routes.table[i]; - if (dev) { - rtm_phonet_notify(RTM_DELROUTE, dev, i); - dev_put(dev); - } - } - rtnl_unlock(); - proc_net_remove(net, "phonet"); } @@ -361,7 +344,7 @@ static struct pernet_operations phonet_net_ops = { /* Initialize Phonet devices list */ int __init phonet_device_init(void) { - int err = register_pernet_device(&phonet_net_ops); + int err = register_pernet_subsys(&phonet_net_ops); if (err) return err; @@ -377,7 +360,7 @@ void phonet_device_exit(void) { rtnl_unregister_all(PF_PHONET); unregister_netdevice_notifier(&phonet_device_notifier); - unregister_pernet_device(&phonet_net_ops); + unregister_pernet_subsys(&phonet_net_ops); proc_net_remove(&init_net, "pnresource"); } diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index d61f6761777..cfdf135fcd6 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -116,7 +116,8 @@ static int fill_addr(struct sk_buff *skb, struct net_device *dev, u8 addr, ifm->ifa_flags = IFA_F_PERMANENT; ifm->ifa_scope = RT_SCOPE_LINK; ifm->ifa_index = dev->ifindex; - NLA_PUT_U8(skb, IFA_LOCAL, addr); + if (nla_put_u8(skb, IFA_LOCAL, addr)) + goto nla_put_failure; return nlmsg_end(skb, nlh); nla_put_failure: @@ -183,8 +184,9 @@ static int fill_route(struct sk_buff *skb, struct net_device *dev, u8 dst, rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_type = RTN_UNICAST; rtm->rtm_flags = 0; - NLA_PUT_U8(skb, RTA_DST, dst); - NLA_PUT_U32(skb, RTA_OIF, dev->ifindex); + if (nla_put_u8(skb, RTA_DST, dst) || + nla_put_u32(skb, RTA_OIF, dev->ifindex)) + goto nla_put_failure; return nlmsg_end(skb, nlh); nla_put_failure: diff --git a/net/phonet/socket.c b/net/phonet/socket.c index 4c7eff30dfa..89cfa9ce493 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -58,7 +58,7 @@ static struct { void __init pn_sock_init(void) { - unsigned i; + unsigned int i; for (i = 0; i < PN_HASHSIZE; i++) INIT_HLIST_HEAD(pnsocks.hlist + i); @@ -116,7 +116,7 @@ struct sock *pn_find_sock_by_sa(struct net *net, const struct sockaddr_pn *spn) void pn_deliver_sock_broadcast(struct net *net, struct sk_buff *skb) { struct hlist_head *hlist = pnsocks.hlist; - unsigned h; + unsigned int h; rcu_read_lock(); for (h = 0; h < PN_HASHSIZE; h++) { @@ -545,7 +545,7 @@ static struct sock *pn_sock_get_idx(struct seq_file *seq, loff_t pos) struct hlist_head *hlist = pnsocks.hlist; struct hlist_node *node; struct sock *sknode; - unsigned h; + unsigned int h; for (h = 0; h < PN_HASHSIZE; h++) { sk_for_each_rcu(sknode, node, hlist) { @@ -710,7 +710,7 @@ int pn_sock_unbind_res(struct sock *sk, u8 res) void pn_sock_unbind_all_res(struct sock *sk) { - unsigned res, match = 0; + unsigned int res, match = 0; mutex_lock(&resource_mutex); for (res = 0; res < 256; res++) { @@ -732,7 +732,7 @@ void pn_sock_unbind_all_res(struct sock *sk) static struct sock **pn_res_get_idx(struct seq_file *seq, loff_t pos) { struct net *net = seq_file_net(seq); - unsigned i; + unsigned int i; if (!net_eq(net, &init_net)) return NULL; @@ -750,7 +750,7 @@ static struct sock **pn_res_get_idx(struct seq_file *seq, loff_t pos) static struct sock **pn_res_get_next(struct seq_file *seq, struct sock **sk) { struct net *net = seq_file_net(seq); - unsigned i; + unsigned int i; BUG_ON(!net_eq(net, &init_net)); diff --git a/net/phonet/sysctl.c b/net/phonet/sysctl.c index cea1c7dbdae..696348fd31a 100644 --- a/net/phonet/sysctl.c +++ b/net/phonet/sysctl.c @@ -27,6 +27,10 @@ #include <linux/errno.h> #include <linux/init.h> +#include <net/sock.h> +#include <linux/phonet.h> +#include <net/phonet/phonet.h> + #define DYNAMIC_PORT_MIN 0x40 #define DYNAMIC_PORT_MAX 0x7f @@ -46,7 +50,8 @@ static void set_local_port_range(int range[2]) void phonet_get_local_port_range(int *min, int *max) { - unsigned seq; + unsigned int seq; + do { seq = read_seqbegin(&local_port_range_lock); if (min) @@ -93,19 +98,13 @@ static struct ctl_table phonet_table[] = { { } }; -static struct ctl_path phonet_ctl_path[] = { - { .procname = "net", }, - { .procname = "phonet", }, - { }, -}; - int __init phonet_sysctl_init(void) { - phonet_table_hrd = register_sysctl_paths(phonet_ctl_path, phonet_table); + phonet_table_hrd = register_net_sysctl(&init_net, "net/phonet", phonet_table); return phonet_table_hrd == NULL ? -ENOMEM : 0; } void phonet_sysctl_exit(void) { - unregister_sysctl_table(phonet_table_hrd); + unregister_net_sysctl_table(phonet_table_hrd); } diff --git a/net/rds/ib_sysctl.c b/net/rds/ib_sysctl.c index 1253b006efd..7e643bafb4a 100644 --- a/net/rds/ib_sysctl.c +++ b/net/rds/ib_sysctl.c @@ -106,22 +106,15 @@ static ctl_table rds_ib_sysctl_table[] = { { } }; -static struct ctl_path rds_ib_sysctl_path[] = { - { .procname = "net", }, - { .procname = "rds", }, - { .procname = "ib", }, - { } -}; - void rds_ib_sysctl_exit(void) { if (rds_ib_sysctl_hdr) - unregister_sysctl_table(rds_ib_sysctl_hdr); + unregister_net_sysctl_table(rds_ib_sysctl_hdr); } int rds_ib_sysctl_init(void) { - rds_ib_sysctl_hdr = register_sysctl_paths(rds_ib_sysctl_path, rds_ib_sysctl_table); + rds_ib_sysctl_hdr = register_net_sysctl(&init_net, "net/rds/ib", rds_ib_sysctl_table); if (!rds_ib_sysctl_hdr) return -ENOMEM; return 0; diff --git a/net/rds/iw_sysctl.c b/net/rds/iw_sysctl.c index e2e47176e72..5d5ebd576f3 100644 --- a/net/rds/iw_sysctl.c +++ b/net/rds/iw_sysctl.c @@ -109,22 +109,15 @@ static ctl_table rds_iw_sysctl_table[] = { { } }; -static struct ctl_path rds_iw_sysctl_path[] = { - { .procname = "net", }, - { .procname = "rds", }, - { .procname = "iw", }, - { } -}; - void rds_iw_sysctl_exit(void) { if (rds_iw_sysctl_hdr) - unregister_sysctl_table(rds_iw_sysctl_hdr); + unregister_net_sysctl_table(rds_iw_sysctl_hdr); } int rds_iw_sysctl_init(void) { - rds_iw_sysctl_hdr = register_sysctl_paths(rds_iw_sysctl_path, rds_iw_sysctl_table); + rds_iw_sysctl_hdr = register_net_sysctl(&init_net, "net/rds/iw", rds_iw_sysctl_table); if (!rds_iw_sysctl_hdr) return -ENOMEM; return 0; diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c index 25ad0c77a26..907214b4c4d 100644 --- a/net/rds/sysctl.c +++ b/net/rds/sysctl.c @@ -92,17 +92,10 @@ static ctl_table rds_sysctl_rds_table[] = { { } }; -static struct ctl_path rds_sysctl_path[] = { - { .procname = "net", }, - { .procname = "rds", }, - { } -}; - - void rds_sysctl_exit(void) { if (rds_sysctl_reg_table) - unregister_sysctl_table(rds_sysctl_reg_table); + unregister_net_sysctl_table(rds_sysctl_reg_table); } int rds_sysctl_init(void) @@ -110,7 +103,7 @@ int rds_sysctl_init(void) rds_sysctl_reconnect_min = msecs_to_jiffies(1); rds_sysctl_reconnect_min_jiffies = rds_sysctl_reconnect_min; - rds_sysctl_reg_table = register_sysctl_paths(rds_sysctl_path, rds_sysctl_rds_table); + rds_sysctl_reg_table = register_net_sysctl(&init_net,"net/rds", rds_sysctl_rds_table); if (!rds_sysctl_reg_table) return -ENOMEM; return 0; diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 8b5cc4aa886..72981375f47 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -145,7 +145,7 @@ int rds_tcp_listen_init(void) if (ret < 0) goto out; - sock->sk->sk_reuse = 1; + sock->sk->sk_reuse = SK_CAN_REUSE; rds_tcp_nonagle(sock); write_lock_bh(&sock->sk->sk_callback_lock); diff --git a/net/rose/rose_dev.c b/net/rose/rose_dev.c index 1ab8689726e..28dbdb911b8 100644 --- a/net/rose/rose_dev.c +++ b/net/rose/rose_dev.c @@ -37,7 +37,7 @@ static int rose_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, - const void *daddr, const void *saddr, unsigned len) + const void *daddr, const void *saddr, unsigned int len) { unsigned char *buff = skb_push(skb, ROSE_MIN_LEN + 2); @@ -95,11 +95,11 @@ static int rose_set_mac_address(struct net_device *dev, void *addr) struct sockaddr *sa = addr; int err; - if (!memcpy(dev->dev_addr, sa->sa_data, dev->addr_len)) + if (!memcmp(dev->dev_addr, sa->sa_data, dev->addr_len)) return 0; if (dev->flags & IFF_UP) { - err = rose_add_loopback_node((rose_address *)dev->dev_addr); + err = rose_add_loopback_node((rose_address *)sa->sa_data); if (err) return err; diff --git a/net/rose/rose_subr.c b/net/rose/rose_subr.c index 47f1fdb346b..7ca57741b2f 100644 --- a/net/rose/rose_subr.c +++ b/net/rose/rose_subr.c @@ -399,7 +399,7 @@ int rose_parse_facilities(unsigned char *p, unsigned packet_len, facilities_len = *p++; - if (facilities_len == 0 || (unsigned)facilities_len > packet_len) + if (facilities_len == 0 || (unsigned int)facilities_len > packet_len) return 0; while (facilities_len >= 3 && *p == 0x00) { diff --git a/net/rose/sysctl_net_rose.c b/net/rose/sysctl_net_rose.c index df6d9dac218..94ca9c2ccd6 100644 --- a/net/rose/sysctl_net_rose.c +++ b/net/rose/sysctl_net_rose.c @@ -118,18 +118,12 @@ static ctl_table rose_table[] = { { } }; -static struct ctl_path rose_path[] = { - { .procname = "net", }, - { .procname = "rose", }, - { } -}; - void __init rose_register_sysctl(void) { - rose_table_header = register_sysctl_paths(rose_path, rose_table); + rose_table_header = register_net_sysctl(&init_net, "net/rose", rose_table); } void rose_unregister_sysctl(void) { - unregister_sysctl_table(rose_table_header); + unregister_net_sysctl_table(rose_table_header); } diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 74c064c0dfd..05996d0dd82 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -26,7 +26,7 @@ MODULE_AUTHOR("Red Hat, Inc."); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_RXRPC); -unsigned rxrpc_debug; // = RXRPC_DEBUG_KPROTO; +unsigned int rxrpc_debug; // = RXRPC_DEBUG_KPROTO; module_param_named(debug, rxrpc_debug, uint, S_IWUSR | S_IRUGO); MODULE_PARM_DESC(debug, "RxRPC debugging mask"); @@ -513,7 +513,7 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct rxrpc_sock *rx = rxrpc_sk(sock->sk); - unsigned min_sec_level; + unsigned int min_sec_level; int ret; _enter(",%d,%d,,%d", level, optname, optlen); @@ -555,13 +555,13 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, case RXRPC_MIN_SECURITY_LEVEL: ret = -EINVAL; - if (optlen != sizeof(unsigned)) + if (optlen != sizeof(unsigned int)) goto error; ret = -EISCONN; if (rx->sk.sk_state != RXRPC_UNCONNECTED) goto error; ret = get_user(min_sec_level, - (unsigned __user *) optval); + (unsigned int __user *) optval); if (ret < 0) goto error; ret = -EINVAL; diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/ar-ack.c index c3126e864f3..e4d9cbcff40 100644 --- a/net/rxrpc/ar-ack.c +++ b/net/rxrpc/ar-ack.c @@ -19,7 +19,7 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" -static unsigned rxrpc_ack_defer = 1; +static unsigned int rxrpc_ack_defer = 1; static const char *const rxrpc_acks[] = { "---", "REQ", "DUP", "OOS", "WIN", "MEM", "PNG", "PNR", "DLY", "IDL", @@ -548,11 +548,11 @@ static void rxrpc_zap_tx_window(struct rxrpc_call *call) * process the extra information that may be appended to an ACK packet */ static void rxrpc_extract_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, - unsigned latest, int nAcks) + unsigned int latest, int nAcks) { struct rxrpc_ackinfo ackinfo; struct rxrpc_peer *peer; - unsigned mtu; + unsigned int mtu; if (skb_copy_bits(skb, nAcks + 3, &ackinfo, sizeof(ackinfo)) < 0) { _leave(" [no ackinfo]"); diff --git a/net/rxrpc/ar-call.c b/net/rxrpc/ar-call.c index bf656c230ba..a3bbb360a3f 100644 --- a/net/rxrpc/ar-call.c +++ b/net/rxrpc/ar-call.c @@ -38,8 +38,8 @@ const char *const rxrpc_call_states[] = { struct kmem_cache *rxrpc_call_jar; LIST_HEAD(rxrpc_calls); DEFINE_RWLOCK(rxrpc_call_lock); -static unsigned rxrpc_call_max_lifetime = 60; -static unsigned rxrpc_dead_call_timeout = 2; +static unsigned int rxrpc_call_max_lifetime = 60; +static unsigned int rxrpc_dead_call_timeout = 2; static void rxrpc_destroy_call(struct work_struct *work); static void rxrpc_call_life_expired(unsigned long _call); diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c index 1a2b0633fec..529572f18d1 100644 --- a/net/rxrpc/ar-input.c +++ b/net/rxrpc/ar-input.c @@ -76,7 +76,7 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb, * --ANK */ // ret = -ENOBUFS; // if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= -// (unsigned) sk->sk_rcvbuf) +// (unsigned int) sk->sk_rcvbuf) // goto out; ret = sk_filter(sk, skb); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 8e22bd345e7..a693aca2ae2 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -83,7 +83,7 @@ struct rxrpc_skb_priv { struct rxrpc_call *call; /* call with which associated */ unsigned long resend_at; /* time in jiffies at which to resend */ union { - unsigned offset; /* offset into buffer of next read */ + unsigned int offset; /* offset into buffer of next read */ int remain; /* amount of space remaining for next write */ u32 error; /* network error code */ bool need_resend; /* T if needs resending */ @@ -176,9 +176,9 @@ struct rxrpc_peer { struct list_head error_targets; /* targets for net error distribution */ spinlock_t lock; /* access lock */ atomic_t usage; - unsigned if_mtu; /* interface MTU for this peer */ - unsigned mtu; /* network MTU for this peer */ - unsigned maxdata; /* data size (MTU - hdrsize) */ + unsigned int if_mtu; /* interface MTU for this peer */ + unsigned int mtu; /* network MTU for this peer */ + unsigned int maxdata; /* data size (MTU - hdrsize) */ unsigned short hdrsize; /* header size (IP + UDP + RxRPC) */ int debug_id; /* debug ID for printks */ int net_error; /* network error distributed */ @@ -187,8 +187,8 @@ struct rxrpc_peer { /* calculated RTT cache */ #define RXRPC_RTT_CACHE_SIZE 32 suseconds_t rtt; /* current RTT estimate (in uS) */ - unsigned rtt_point; /* next entry at which to insert */ - unsigned rtt_usage; /* amount of cache actually used */ + unsigned int rtt_point; /* next entry at which to insert */ + unsigned int rtt_usage; /* amount of cache actually used */ suseconds_t rtt_cache[RXRPC_RTT_CACHE_SIZE]; /* calculated RTT cache */ }; @@ -271,7 +271,7 @@ struct rxrpc_connection { } state; int error; /* error code for local abort */ int debug_id; /* debug ID for printks */ - unsigned call_counter; /* call ID counter */ + unsigned int call_counter; /* call ID counter */ atomic_t serial; /* packet serial number counter */ atomic_t hi_serial; /* highest serial number received */ u8 avail_calls; /* number of calls available */ @@ -592,7 +592,7 @@ extern struct rxrpc_transport *rxrpc_find_transport(struct rxrpc_local *, /* * debug tracing */ -extern unsigned rxrpc_debug; +extern unsigned int rxrpc_debug; #define dbgprintk(FMT,...) \ printk("[%-6.6s] "FMT"\n", current->comm ,##__VA_ARGS__) diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c index ae3a035f539..8b1f9f49960 100644 --- a/net/rxrpc/ar-key.c +++ b/net/rxrpc/ar-key.c @@ -82,7 +82,7 @@ static int rxrpc_vet_description_s(const char *desc) * - the caller guarantees we have at least 4 words */ static int rxrpc_instantiate_xdr_rxkad(struct key *key, const __be32 *xdr, - unsigned toklen) + unsigned int toklen) { struct rxrpc_key_token *token, **pptoken; size_t plen; @@ -210,10 +210,10 @@ static void rxrpc_rxk5_free(struct rxk5_key *rxk5) */ static int rxrpc_krb5_decode_principal(struct krb5_principal *princ, const __be32 **_xdr, - unsigned *_toklen) + unsigned int *_toklen) { const __be32 *xdr = *_xdr; - unsigned toklen = *_toklen, n_parts, loop, tmp; + unsigned int toklen = *_toklen, n_parts, loop, tmp; /* there must be at least one name, and at least #names+1 length * words */ @@ -286,10 +286,10 @@ static int rxrpc_krb5_decode_principal(struct krb5_principal *princ, static int rxrpc_krb5_decode_tagged_data(struct krb5_tagged_data *td, size_t max_data_size, const __be32 **_xdr, - unsigned *_toklen) + unsigned int *_toklen) { const __be32 *xdr = *_xdr; - unsigned toklen = *_toklen, len; + unsigned int toklen = *_toklen, len; /* there must be at least one tag and one length word */ if (toklen <= 8) @@ -330,11 +330,11 @@ static int rxrpc_krb5_decode_tagged_array(struct krb5_tagged_data **_td, u8 max_n_elem, size_t max_elem_size, const __be32 **_xdr, - unsigned *_toklen) + unsigned int *_toklen) { struct krb5_tagged_data *td; const __be32 *xdr = *_xdr; - unsigned toklen = *_toklen, n_elem, loop; + unsigned int toklen = *_toklen, n_elem, loop; int ret; /* there must be at least one count */ @@ -380,10 +380,10 @@ static int rxrpc_krb5_decode_tagged_array(struct krb5_tagged_data **_td, * extract a krb5 ticket */ static int rxrpc_krb5_decode_ticket(u8 **_ticket, u16 *_tktlen, - const __be32 **_xdr, unsigned *_toklen) + const __be32 **_xdr, unsigned int *_toklen) { const __be32 *xdr = *_xdr; - unsigned toklen = *_toklen, len; + unsigned int toklen = *_toklen, len; /* there must be at least one length word */ if (toklen <= 4) @@ -419,7 +419,7 @@ static int rxrpc_krb5_decode_ticket(u8 **_ticket, u16 *_tktlen, * - the caller guarantees we have at least 4 words */ static int rxrpc_instantiate_xdr_rxk5(struct key *key, const __be32 *xdr, - unsigned toklen) + unsigned int toklen) { struct rxrpc_key_token *token, **pptoken; struct rxk5_key *rxk5; @@ -549,7 +549,7 @@ static int rxrpc_instantiate_xdr(struct key *key, const void *data, size_t datal { const __be32 *xdr = data, *token; const char *cp; - unsigned len, tmp, loop, ntoken, toklen, sec_ix; + unsigned int len, tmp, loop, ntoken, toklen, sec_ix; int ret; _enter(",{%x,%x,%x,%x},%zu", diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 7635107726c..f226709ebd8 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -31,7 +31,7 @@ #define REALM_SZ 40 /* size of principal's auth domain */ #define SNAME_SZ 40 /* size of service name */ -unsigned rxrpc_debug; +unsigned int rxrpc_debug; module_param_named(debug, rxrpc_debug, uint, S_IWUSR | S_IRUGO); MODULE_PARM_DESC(debug, "rxkad debugging mask"); @@ -207,7 +207,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, struct rxrpc_crypt iv; struct scatterlist sg[16]; struct sk_buff *trailer; - unsigned len; + unsigned int len; u16 check; int nsg; @@ -826,7 +826,7 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn, struct rxrpc_crypt iv, key; struct scatterlist sg[1]; struct in_addr addr; - unsigned life; + unsigned int life; time_t issue, now; bool little_endian; int ret; diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 75b58f81d53..e7a8976bf25 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -250,6 +250,28 @@ config NET_SCH_QFQ If unsure, say N. +config NET_SCH_CODEL + tristate "Controlled Delay AQM (CODEL)" + help + Say Y here if you want to use the Controlled Delay (CODEL) + packet scheduling algorithm. + + To compile this driver as a module, choose M here: the module + will be called sch_codel. + + If unsure, say N. + +config NET_SCH_FQ_CODEL + tristate "Fair Queue Controlled Delay AQM (FQ_CODEL)" + help + Say Y here if you want to use the FQ Controlled Delay (FQ_CODEL) + packet scheduling algorithm. + + To compile this driver as a module, choose M here: the module + will be called sch_fq_codel. + + If unsure, say N. + config NET_SCH_INGRESS tristate "Ingress Qdisc" depends on NET_CLS_ACT diff --git a/net/sched/Makefile b/net/sched/Makefile index 8cdf4e2b51d..5940a1992f0 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -37,6 +37,8 @@ obj-$(CONFIG_NET_SCH_PLUG) += sch_plug.o obj-$(CONFIG_NET_SCH_MQPRIO) += sch_mqprio.o obj-$(CONFIG_NET_SCH_CHOKE) += sch_choke.o obj-$(CONFIG_NET_SCH_QFQ) += sch_qfq.o +obj-$(CONFIG_NET_SCH_CODEL) += sch_codel.o +obj-$(CONFIG_NET_SCH_FQ_CODEL) += sch_fq_codel.o obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 93fdf131bd7..5cfb160df06 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -127,7 +127,8 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a, nest = nla_nest_start(skb, a->order); if (nest == NULL) goto nla_put_failure; - NLA_PUT_STRING(skb, TCA_KIND, a->ops->kind); + if (nla_put_string(skb, TCA_KIND, a->ops->kind)) + goto nla_put_failure; for (i = 0; i < (hinfo->hmask + 1); i++) { p = hinfo->htab[tcf_hash(i, hinfo->hmask)]; @@ -139,7 +140,8 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a, p = s_p; } } - NLA_PUT_U32(skb, TCA_FCNT, n_i); + if (nla_put_u32(skb, TCA_FCNT, n_i)) + goto nla_put_failure; nla_nest_end(skb, nest); return n_i; @@ -437,7 +439,8 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) if (a->ops == NULL || a->ops->dump == NULL) return err; - NLA_PUT_STRING(skb, TCA_KIND, a->ops->kind); + if (nla_put_string(skb, TCA_KIND, a->ops->kind)) + goto nla_put_failure; if (tcf_action_copy_stats(skb, a, 0)) goto nla_put_failure; nest = nla_nest_start(skb, TCA_OPTIONS); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 453a73431ac..2c8ad7c86e4 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -397,7 +397,7 @@ static int tcf_csum_ipv6_hopopts(struct ipv6_opt_hdr *ip6xh, while (len > 1) { switch (xh[off]) { - case IPV6_TLV_PAD0: + case IPV6_TLV_PAD1: optlen = 1; break; case IPV6_TLV_JUMBO: @@ -550,11 +550,13 @@ static int tcf_csum_dump(struct sk_buff *skb, }; struct tcf_t t; - NLA_PUT(skb, TCA_CSUM_PARMS, sizeof(opt), &opt); + if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; t.install = jiffies_to_clock_t(jiffies - p->tcf_tm.install); t.lastuse = jiffies_to_clock_t(jiffies - p->tcf_tm.lastuse); t.expires = jiffies_to_clock_t(p->tcf_tm.expires); - NLA_PUT(skb, TCA_CSUM_TM, sizeof(t), &t); + if (nla_put(skb, TCA_CSUM_TM, sizeof(t), &t)) + goto nla_put_failure; return skb->len; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index b77f5a06a65..f10fb825644 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -162,7 +162,8 @@ static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, int bind, int }; struct tcf_t t; - NLA_PUT(skb, TCA_GACT_PARMS, sizeof(opt), &opt); + if (nla_put(skb, TCA_GACT_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; #ifdef CONFIG_GACT_PROB if (gact->tcfg_ptype) { struct tc_gact_p p_opt = { @@ -171,13 +172,15 @@ static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, int bind, int .ptype = gact->tcfg_ptype, }; - NLA_PUT(skb, TCA_GACT_PROB, sizeof(p_opt), &p_opt); + if (nla_put(skb, TCA_GACT_PROB, sizeof(p_opt), &p_opt)) + goto nla_put_failure; } #endif t.install = jiffies_to_clock_t(jiffies - gact->tcf_tm.install); t.lastuse = jiffies_to_clock_t(jiffies - gact->tcf_tm.lastuse); t.expires = jiffies_to_clock_t(gact->tcf_tm.expires); - NLA_PUT(skb, TCA_GACT_TM, sizeof(t), &t); + if (nla_put(skb, TCA_GACT_TM, sizeof(t), &t)) + goto nla_put_failure; return skb->len; nla_put_failure: diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 60f8f616e8f..60e281ad0f0 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -1,5 +1,5 @@ /* - * net/sched/ipt.c iptables target interface + * net/sched/ipt.c iptables target interface * *TODO: Add other tables. For now we only support the ipv4 table targets * @@ -235,9 +235,8 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, result = TC_ACT_PIPE; break; default: - if (net_ratelimit()) - pr_notice("tc filter: Bogus netfilter code" - " %d assume ACCEPT\n", ret); + net_notice_ratelimited("tc filter: Bogus netfilter code %d assume ACCEPT\n", + ret); result = TC_POLICE_OK; break; } @@ -267,15 +266,17 @@ static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, int c.refcnt = ipt->tcf_refcnt - ref; strcpy(t->u.user.name, ipt->tcfi_t->u.kernel.target->name); - NLA_PUT(skb, TCA_IPT_TARG, ipt->tcfi_t->u.user.target_size, t); - NLA_PUT_U32(skb, TCA_IPT_INDEX, ipt->tcf_index); - NLA_PUT_U32(skb, TCA_IPT_HOOK, ipt->tcfi_hook); - NLA_PUT(skb, TCA_IPT_CNT, sizeof(struct tc_cnt), &c); - NLA_PUT_STRING(skb, TCA_IPT_TABLE, ipt->tcfi_tname); + if (nla_put(skb, TCA_IPT_TARG, ipt->tcfi_t->u.user.target_size, t) || + nla_put_u32(skb, TCA_IPT_INDEX, ipt->tcf_index) || + nla_put_u32(skb, TCA_IPT_HOOK, ipt->tcfi_hook) || + nla_put(skb, TCA_IPT_CNT, sizeof(struct tc_cnt), &c) || + nla_put_string(skb, TCA_IPT_TABLE, ipt->tcfi_tname)) + goto nla_put_failure; tm.install = jiffies_to_clock_t(jiffies - ipt->tcf_tm.install); tm.lastuse = jiffies_to_clock_t(jiffies - ipt->tcf_tm.lastuse); tm.expires = jiffies_to_clock_t(ipt->tcf_tm.expires); - NLA_PUT(skb, TCA_IPT_TM, sizeof (tm), &tm); + if (nla_put(skb, TCA_IPT_TM, sizeof (tm), &tm)) + goto nla_put_failure; kfree(t); return skb->len; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index e051398fdf6..fe81cc18e9e 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -174,9 +174,8 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, } if (!(dev->flags & IFF_UP)) { - if (net_ratelimit()) - pr_notice("tc mirred to Houston: device %s is down\n", - dev->name); + net_notice_ratelimited("tc mirred to Houston: device %s is down\n", + dev->name); goto out; } @@ -227,11 +226,13 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, i }; struct tcf_t t; - NLA_PUT(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt); + if (nla_put(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; t.install = jiffies_to_clock_t(jiffies - m->tcf_tm.install); t.lastuse = jiffies_to_clock_t(jiffies - m->tcf_tm.lastuse); t.expires = jiffies_to_clock_t(m->tcf_tm.expires); - NLA_PUT(skb, TCA_MIRRED_TM, sizeof(t), &t); + if (nla_put(skb, TCA_MIRRED_TM, sizeof(t), &t)) + goto nla_put_failure; return skb->len; nla_put_failure: diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 001d1b35486..b5d029eb44f 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -284,11 +284,13 @@ static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a, }; struct tcf_t t; - NLA_PUT(skb, TCA_NAT_PARMS, sizeof(opt), &opt); + if (nla_put(skb, TCA_NAT_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; t.install = jiffies_to_clock_t(jiffies - p->tcf_tm.install); t.lastuse = jiffies_to_clock_t(jiffies - p->tcf_tm.lastuse); t.expires = jiffies_to_clock_t(p->tcf_tm.expires); - NLA_PUT(skb, TCA_NAT_TM, sizeof(t), &t); + if (nla_put(skb, TCA_NAT_TM, sizeof(t), &t)) + goto nla_put_failure; return skb->len; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 10d3aed8656..26aa2f6ce25 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -215,11 +215,13 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a, opt->refcnt = p->tcf_refcnt - ref; opt->bindcnt = p->tcf_bindcnt - bind; - NLA_PUT(skb, TCA_PEDIT_PARMS, s, opt); + if (nla_put(skb, TCA_PEDIT_PARMS, s, opt)) + goto nla_put_failure; t.install = jiffies_to_clock_t(jiffies - p->tcf_tm.install); t.lastuse = jiffies_to_clock_t(jiffies - p->tcf_tm.lastuse); t.expires = jiffies_to_clock_t(p->tcf_tm.expires); - NLA_PUT(skb, TCA_PEDIT_TM, sizeof(t), &t); + if (nla_put(skb, TCA_PEDIT_TM, sizeof(t), &t)) + goto nla_put_failure; kfree(opt); return skb->len; diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 6fb3f5af0f8..a9de23297d4 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -356,11 +356,14 @@ tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) opt.rate = police->tcfp_R_tab->rate; if (police->tcfp_P_tab) opt.peakrate = police->tcfp_P_tab->rate; - NLA_PUT(skb, TCA_POLICE_TBF, sizeof(opt), &opt); - if (police->tcfp_result) - NLA_PUT_U32(skb, TCA_POLICE_RESULT, police->tcfp_result); - if (police->tcfp_ewma_rate) - NLA_PUT_U32(skb, TCA_POLICE_AVRATE, police->tcfp_ewma_rate); + if (nla_put(skb, TCA_POLICE_TBF, sizeof(opt), &opt)) + goto nla_put_failure; + if (police->tcfp_result && + nla_put_u32(skb, TCA_POLICE_RESULT, police->tcfp_result)) + goto nla_put_failure; + if (police->tcfp_ewma_rate && + nla_put_u32(skb, TCA_POLICE_AVRATE, police->tcfp_ewma_rate)) + goto nla_put_failure; return skb->len; nla_put_failure: diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 73e0a3ab4d5..3922f2a2821 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -172,12 +172,14 @@ static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, }; struct tcf_t t; - NLA_PUT(skb, TCA_DEF_PARMS, sizeof(opt), &opt); - NLA_PUT_STRING(skb, TCA_DEF_DATA, d->tcfd_defdata); + if (nla_put(skb, TCA_DEF_PARMS, sizeof(opt), &opt) || + nla_put_string(skb, TCA_DEF_DATA, d->tcfd_defdata)) + goto nla_put_failure; t.install = jiffies_to_clock_t(jiffies - d->tcf_tm.install); t.lastuse = jiffies_to_clock_t(jiffies - d->tcf_tm.lastuse); t.expires = jiffies_to_clock_t(d->tcf_tm.expires); - NLA_PUT(skb, TCA_DEF_TM, sizeof(t), &t); + if (nla_put(skb, TCA_DEF_TM, sizeof(t), &t)) + goto nla_put_failure; return skb->len; nla_put_failure: diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 35dbbe91027..476e0fac671 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -166,20 +166,25 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, }; struct tcf_t t; - NLA_PUT(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt); - if (d->flags & SKBEDIT_F_PRIORITY) - NLA_PUT(skb, TCA_SKBEDIT_PRIORITY, sizeof(d->priority), - &d->priority); - if (d->flags & SKBEDIT_F_QUEUE_MAPPING) - NLA_PUT(skb, TCA_SKBEDIT_QUEUE_MAPPING, - sizeof(d->queue_mapping), &d->queue_mapping); - if (d->flags & SKBEDIT_F_MARK) - NLA_PUT(skb, TCA_SKBEDIT_MARK, sizeof(d->mark), - &d->mark); + if (nla_put(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + if ((d->flags & SKBEDIT_F_PRIORITY) && + nla_put(skb, TCA_SKBEDIT_PRIORITY, sizeof(d->priority), + &d->priority)) + goto nla_put_failure; + if ((d->flags & SKBEDIT_F_QUEUE_MAPPING) && + nla_put(skb, TCA_SKBEDIT_QUEUE_MAPPING, + sizeof(d->queue_mapping), &d->queue_mapping)) + goto nla_put_failure; + if ((d->flags & SKBEDIT_F_MARK) && + nla_put(skb, TCA_SKBEDIT_MARK, sizeof(d->mark), + &d->mark)) + goto nla_put_failure; t.install = jiffies_to_clock_t(jiffies - d->tcf_tm.install); t.lastuse = jiffies_to_clock_t(jiffies - d->tcf_tm.lastuse); t.expires = jiffies_to_clock_t(d->tcf_tm.expires); - NLA_PUT(skb, TCA_SKBEDIT_TM, sizeof(t), &t); + if (nla_put(skb, TCA_SKBEDIT_TM, sizeof(t), &t)) + goto nla_put_failure; return skb->len; nla_put_failure: diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index a69d44f1dac..f452f696b4b 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -357,7 +357,8 @@ static int tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp, tcm->tcm_ifindex = qdisc_dev(tp->q)->ifindex; tcm->tcm_parent = tp->classid; tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol); - NLA_PUT_STRING(skb, TCA_KIND, tp->ops->kind); + if (nla_put_string(skb, TCA_KIND, tp->ops->kind)) + goto nla_put_failure; tcm->tcm_handle = fh; if (RTM_DELTFILTER != event) { tcm->tcm_handle = 0; diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index ea1f70b5a5f..590960a22a7 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -257,8 +257,9 @@ static int basic_dump(struct tcf_proto *tp, unsigned long fh, if (nest == NULL) goto nla_put_failure; - if (f->res.classid) - NLA_PUT_U32(skb, TCA_BASIC_CLASSID, f->res.classid); + if (f->res.classid && + nla_put_u32(skb, TCA_BASIC_CLASSID, f->res.classid)) + goto nla_put_failure; if (tcf_exts_dump(skb, &f->exts, &basic_ext_map) < 0 || tcf_em_tree_dump(skb, &f->ematches, TCA_BASIC_EMATCHES) < 0) diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 1d8bd0dbcd1..ccd08c8dc6a 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -572,25 +572,32 @@ static int flow_dump(struct tcf_proto *tp, unsigned long fh, if (nest == NULL) goto nla_put_failure; - NLA_PUT_U32(skb, TCA_FLOW_KEYS, f->keymask); - NLA_PUT_U32(skb, TCA_FLOW_MODE, f->mode); + if (nla_put_u32(skb, TCA_FLOW_KEYS, f->keymask) || + nla_put_u32(skb, TCA_FLOW_MODE, f->mode)) + goto nla_put_failure; if (f->mask != ~0 || f->xor != 0) { - NLA_PUT_U32(skb, TCA_FLOW_MASK, f->mask); - NLA_PUT_U32(skb, TCA_FLOW_XOR, f->xor); + if (nla_put_u32(skb, TCA_FLOW_MASK, f->mask) || + nla_put_u32(skb, TCA_FLOW_XOR, f->xor)) + goto nla_put_failure; } - if (f->rshift) - NLA_PUT_U32(skb, TCA_FLOW_RSHIFT, f->rshift); - if (f->addend) - NLA_PUT_U32(skb, TCA_FLOW_ADDEND, f->addend); + if (f->rshift && + nla_put_u32(skb, TCA_FLOW_RSHIFT, f->rshift)) + goto nla_put_failure; + if (f->addend && + nla_put_u32(skb, TCA_FLOW_ADDEND, f->addend)) + goto nla_put_failure; - if (f->divisor) - NLA_PUT_U32(skb, TCA_FLOW_DIVISOR, f->divisor); - if (f->baseclass) - NLA_PUT_U32(skb, TCA_FLOW_BASECLASS, f->baseclass); + if (f->divisor && + nla_put_u32(skb, TCA_FLOW_DIVISOR, f->divisor)) + goto nla_put_failure; + if (f->baseclass && + nla_put_u32(skb, TCA_FLOW_BASECLASS, f->baseclass)) + goto nla_put_failure; - if (f->perturb_period) - NLA_PUT_U32(skb, TCA_FLOW_PERTURB, f->perturb_period / HZ); + if (f->perturb_period && + nla_put_u32(skb, TCA_FLOW_PERTURB, f->perturb_period / HZ)) + goto nla_put_failure; if (tcf_exts_dump(skb, &f->exts, &flow_ext_map) < 0) goto nla_put_failure; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 389af152ec4..8384a479724 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -346,14 +346,17 @@ static int fw_dump(struct tcf_proto *tp, unsigned long fh, if (nest == NULL) goto nla_put_failure; - if (f->res.classid) - NLA_PUT_U32(skb, TCA_FW_CLASSID, f->res.classid); + if (f->res.classid && + nla_put_u32(skb, TCA_FW_CLASSID, f->res.classid)) + goto nla_put_failure; #ifdef CONFIG_NET_CLS_IND - if (strlen(f->indev)) - NLA_PUT_STRING(skb, TCA_FW_INDEV, f->indev); + if (strlen(f->indev) && + nla_put_string(skb, TCA_FW_INDEV, f->indev)) + goto nla_put_failure; #endif /* CONFIG_NET_CLS_IND */ - if (head->mask != 0xFFFFFFFF) - NLA_PUT_U32(skb, TCA_FW_MASK, head->mask); + if (head->mask != 0xFFFFFFFF && + nla_put_u32(skb, TCA_FW_MASK, head->mask)) + goto nla_put_failure; if (tcf_exts_dump(skb, &f->exts, &fw_ext_map) < 0) goto nla_put_failure; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 13ab66e9df5..36fec422740 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -571,17 +571,21 @@ static int route4_dump(struct tcf_proto *tp, unsigned long fh, if (!(f->handle & 0x8000)) { id = f->id & 0xFF; - NLA_PUT_U32(skb, TCA_ROUTE4_TO, id); + if (nla_put_u32(skb, TCA_ROUTE4_TO, id)) + goto nla_put_failure; } if (f->handle & 0x80000000) { - if ((f->handle >> 16) != 0xFFFF) - NLA_PUT_U32(skb, TCA_ROUTE4_IIF, f->iif); + if ((f->handle >> 16) != 0xFFFF && + nla_put_u32(skb, TCA_ROUTE4_IIF, f->iif)) + goto nla_put_failure; } else { id = f->id >> 16; - NLA_PUT_U32(skb, TCA_ROUTE4_FROM, id); + if (nla_put_u32(skb, TCA_ROUTE4_FROM, id)) + goto nla_put_failure; } - if (f->res.classid) - NLA_PUT_U32(skb, TCA_ROUTE4_CLASSID, f->res.classid); + if (f->res.classid && + nla_put_u32(skb, TCA_ROUTE4_CLASSID, f->res.classid)) + goto nla_put_failure; if (tcf_exts_dump(skb, &f->exts, &route_ext_map) < 0) goto nla_put_failure; diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index b01427924f8..18ab93ec8d7 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -615,18 +615,22 @@ static int rsvp_dump(struct tcf_proto *tp, unsigned long fh, if (nest == NULL) goto nla_put_failure; - NLA_PUT(skb, TCA_RSVP_DST, sizeof(s->dst), &s->dst); + if (nla_put(skb, TCA_RSVP_DST, sizeof(s->dst), &s->dst)) + goto nla_put_failure; pinfo.dpi = s->dpi; pinfo.spi = f->spi; pinfo.protocol = s->protocol; pinfo.tunnelid = s->tunnelid; pinfo.tunnelhdr = f->tunnelhdr; pinfo.pad = 0; - NLA_PUT(skb, TCA_RSVP_PINFO, sizeof(pinfo), &pinfo); - if (f->res.classid) - NLA_PUT_U32(skb, TCA_RSVP_CLASSID, f->res.classid); - if (((f->handle >> 8) & 0xFF) != 16) - NLA_PUT(skb, TCA_RSVP_SRC, sizeof(f->src), f->src); + if (nla_put(skb, TCA_RSVP_PINFO, sizeof(pinfo), &pinfo)) + goto nla_put_failure; + if (f->res.classid && + nla_put_u32(skb, TCA_RSVP_CLASSID, f->res.classid)) + goto nla_put_failure; + if (((f->handle >> 8) & 0xFF) != 16 && + nla_put(skb, TCA_RSVP_SRC, sizeof(f->src), f->src)) + goto nla_put_failure; if (tcf_exts_dump(skb, &f->exts, &rsvp_ext_map) < 0) goto nla_put_failure; diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index dbe199234c6..fe29420d0b0 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -438,10 +438,11 @@ static int tcindex_dump(struct tcf_proto *tp, unsigned long fh, if (!fh) { t->tcm_handle = ~0; /* whatever ... */ - NLA_PUT_U32(skb, TCA_TCINDEX_HASH, p->hash); - NLA_PUT_U16(skb, TCA_TCINDEX_MASK, p->mask); - NLA_PUT_U32(skb, TCA_TCINDEX_SHIFT, p->shift); - NLA_PUT_U32(skb, TCA_TCINDEX_FALL_THROUGH, p->fall_through); + if (nla_put_u32(skb, TCA_TCINDEX_HASH, p->hash) || + nla_put_u16(skb, TCA_TCINDEX_MASK, p->mask) || + nla_put_u32(skb, TCA_TCINDEX_SHIFT, p->shift) || + nla_put_u32(skb, TCA_TCINDEX_FALL_THROUGH, p->fall_through)) + goto nla_put_failure; nla_nest_end(skb, nest); } else { if (p->perfect) { @@ -460,8 +461,9 @@ static int tcindex_dump(struct tcf_proto *tp, unsigned long fh, } } pr_debug("handle = %d\n", t->tcm_handle); - if (r->res.class) - NLA_PUT_U32(skb, TCA_TCINDEX_CLASSID, r->res.classid); + if (r->res.class && + nla_put_u32(skb, TCA_TCINDEX_CLASSID, r->res.classid)) + goto nla_put_failure; if (tcf_exts_dump(skb, &r->exts, &tcindex_ext_map) < 0) goto nla_put_failure; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 939b627b479..d45373fb00b 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -234,8 +234,7 @@ out: return -1; deadloop: - if (net_ratelimit()) - pr_warning("cls_u32: dead loop\n"); + net_warn_ratelimited("cls_u32: dead loop\n"); return -1; } @@ -733,36 +732,44 @@ static int u32_dump(struct tcf_proto *tp, unsigned long fh, struct tc_u_hnode *ht = (struct tc_u_hnode *)fh; u32 divisor = ht->divisor + 1; - NLA_PUT_U32(skb, TCA_U32_DIVISOR, divisor); + if (nla_put_u32(skb, TCA_U32_DIVISOR, divisor)) + goto nla_put_failure; } else { - NLA_PUT(skb, TCA_U32_SEL, - sizeof(n->sel) + n->sel.nkeys*sizeof(struct tc_u32_key), - &n->sel); + if (nla_put(skb, TCA_U32_SEL, + sizeof(n->sel) + n->sel.nkeys*sizeof(struct tc_u32_key), + &n->sel)) + goto nla_put_failure; if (n->ht_up) { u32 htid = n->handle & 0xFFFFF000; - NLA_PUT_U32(skb, TCA_U32_HASH, htid); + if (nla_put_u32(skb, TCA_U32_HASH, htid)) + goto nla_put_failure; } - if (n->res.classid) - NLA_PUT_U32(skb, TCA_U32_CLASSID, n->res.classid); - if (n->ht_down) - NLA_PUT_U32(skb, TCA_U32_LINK, n->ht_down->handle); + if (n->res.classid && + nla_put_u32(skb, TCA_U32_CLASSID, n->res.classid)) + goto nla_put_failure; + if (n->ht_down && + nla_put_u32(skb, TCA_U32_LINK, n->ht_down->handle)) + goto nla_put_failure; #ifdef CONFIG_CLS_U32_MARK - if (n->mark.val || n->mark.mask) - NLA_PUT(skb, TCA_U32_MARK, sizeof(n->mark), &n->mark); + if ((n->mark.val || n->mark.mask) && + nla_put(skb, TCA_U32_MARK, sizeof(n->mark), &n->mark)) + goto nla_put_failure; #endif if (tcf_exts_dump(skb, &n->exts, &u32_ext_map) < 0) goto nla_put_failure; #ifdef CONFIG_NET_CLS_IND - if (strlen(n->indev)) - NLA_PUT_STRING(skb, TCA_U32_INDEV, n->indev); + if (strlen(n->indev) && + nla_put_string(skb, TCA_U32_INDEV, n->indev)) + goto nla_put_failure; #endif #ifdef CONFIG_CLS_U32_PERF - NLA_PUT(skb, TCA_U32_PCNT, - sizeof(struct tc_u32_pcnt) + n->sel.nkeys*sizeof(u64), - n->pf); + if (nla_put(skb, TCA_U32_PCNT, + sizeof(struct tc_u32_pcnt) + n->sel.nkeys*sizeof(u64), + n->pf)) + goto nla_put_failure; #endif } diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 1363bf14e61..4790c696cbc 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -585,8 +585,9 @@ static void meta_var_apply_extras(struct meta_value *v, static int meta_var_dump(struct sk_buff *skb, struct meta_value *v, int tlv) { - if (v->val && v->len) - NLA_PUT(skb, tlv, v->len, (void *) v->val); + if (v->val && v->len && + nla_put(skb, tlv, v->len, (void *) v->val)) + goto nla_put_failure; return 0; nla_put_failure: @@ -636,10 +637,13 @@ static void meta_int_apply_extras(struct meta_value *v, static int meta_int_dump(struct sk_buff *skb, struct meta_value *v, int tlv) { - if (v->len == sizeof(unsigned long)) - NLA_PUT(skb, tlv, sizeof(unsigned long), &v->val); - else if (v->len == sizeof(u32)) - NLA_PUT_U32(skb, tlv, v->val); + if (v->len == sizeof(unsigned long)) { + if (nla_put(skb, tlv, sizeof(unsigned long), &v->val)) + goto nla_put_failure; + } else if (v->len == sizeof(u32)) { + if (nla_put_u32(skb, tlv, v->val)) + goto nla_put_failure; + } return 0; @@ -831,7 +835,8 @@ static int em_meta_dump(struct sk_buff *skb, struct tcf_ematch *em) memcpy(&hdr.left, &meta->lvalue.hdr, sizeof(hdr.left)); memcpy(&hdr.right, &meta->rvalue.hdr, sizeof(hdr.right)); - NLA_PUT(skb, TCA_EM_META_HDR, sizeof(hdr), &hdr); + if (nla_put(skb, TCA_EM_META_HDR, sizeof(hdr), &hdr)) + goto nla_put_failure; ops = meta_type_ops(&meta->lvalue); if (ops->dump(skb, &meta->lvalue, TCA_EM_META_LVALUE) < 0 || diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 88d93eb9250..3a633debb6d 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -441,7 +441,8 @@ int tcf_em_tree_dump(struct sk_buff *skb, struct tcf_ematch_tree *tree, int tlv) if (top_start == NULL) goto nla_put_failure; - NLA_PUT(skb, TCA_EMATCH_TREE_HDR, sizeof(tree->hdr), &tree->hdr); + if (nla_put(skb, TCA_EMATCH_TREE_HDR, sizeof(tree->hdr), &tree->hdr)) + goto nla_put_failure; list_start = nla_nest_start(skb, TCA_EMATCH_TREE_LIST); if (list_start == NULL) @@ -457,7 +458,8 @@ int tcf_em_tree_dump(struct sk_buff *skb, struct tcf_ematch_tree *tree, int tlv) .flags = em->flags }; - NLA_PUT(skb, i + 1, sizeof(em_hdr), &em_hdr); + if (nla_put(skb, i + 1, sizeof(em_hdr), &em_hdr)) + goto nla_put_failure; if (em->ops && em->ops->dump) { if (em->ops->dump(skb, em) < 0) @@ -535,9 +537,7 @@ pop_stack: return res; stack_overflow: - if (net_ratelimit()) - pr_warning("tc ematch: local stack overflow," - " increase NET_EMATCH_STACK\n"); + net_warn_ratelimited("tc ematch: local stack overflow, increase NET_EMATCH_STACK\n"); return -1; } EXPORT_SYMBOL(__tcf_em_tree_match); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 3d8981fde30..085ce53d570 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -426,7 +426,8 @@ static int qdisc_dump_stab(struct sk_buff *skb, struct qdisc_size_table *stab) nest = nla_nest_start(skb, TCA_STAB); if (nest == NULL) goto nla_put_failure; - NLA_PUT(skb, TCA_STAB_BASE, sizeof(stab->szopts), &stab->szopts); + if (nla_put(skb, TCA_STAB_BASE, sizeof(stab->szopts), &stab->szopts)) + goto nla_put_failure; nla_nest_end(skb, nest); return skb->len; @@ -1201,7 +1202,8 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, tcm->tcm_parent = clid; tcm->tcm_handle = q->handle; tcm->tcm_info = atomic_read(&q->refcnt); - NLA_PUT_STRING(skb, TCA_KIND, q->ops->id); + if (nla_put_string(skb, TCA_KIND, q->ops->id)) + goto nla_put_failure; if (q->ops->dump && q->ops->dump(q, skb) < 0) goto nla_put_failure; q->qstats.qlen = q->q.qlen; @@ -1505,7 +1507,8 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, tcm->tcm_parent = q->handle; tcm->tcm_handle = q->handle; tcm->tcm_info = 0; - NLA_PUT_STRING(skb, TCA_KIND, q->ops->id); + if (nla_put_string(skb, TCA_KIND, q->ops->id)) + goto nla_put_failure; if (cl_ops->dump && cl_ops->dump(q, cl, skb, tcm) < 0) goto nla_put_failure; @@ -1688,12 +1691,10 @@ reclassify: tp = otp; if (verd++ >= MAX_REC_LOOP) { - if (net_ratelimit()) - pr_notice("%s: packet reclassify loop" - " rule prio %u protocol %02x\n", - tp->q->ops->id, - tp->prio & 0xffff, - ntohs(tp->protocol)); + net_notice_ratelimited("%s: packet reclassify loop rule prio %u protocol %02x\n", + tp->q->ops->id, + tp->prio & 0xffff, + ntohs(tp->protocol)); return TC_ACT_SHOT; } skb->tc_verd = SET_TC_VERD(skb->tc_verd, verd); diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index e25e49061a0..8522a479337 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -423,8 +423,6 @@ drop: __maybe_unused } return ret; } - qdisc_bstats_update(sch, skb); - bstats_update(&flow->bstats, skb); /* * Okay, this may seem weird. We pretend we've dropped the packet if * it goes via ATM. The reason for this is that the outer qdisc @@ -472,6 +470,8 @@ static void sch_atm_dequeue(unsigned long data) if (unlikely(!skb)) break; + qdisc_bstats_update(sch, skb); + bstats_update(&flow->bstats, skb); pr_debug("atm_tc_dequeue: sending on class %p\n", flow); /* remove any LL header somebody else has attached */ skb_pull(skb, skb_network_offset(skb)); @@ -601,7 +601,8 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, if (nest == NULL) goto nla_put_failure; - NLA_PUT(skb, TCA_ATM_HDR, flow->hdr_len, flow->hdr); + if (nla_put(skb, TCA_ATM_HDR, flow->hdr_len, flow->hdr)) + goto nla_put_failure; if (flow->vcc) { struct sockaddr_atmpvc pvc; int state; @@ -610,15 +611,19 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, pvc.sap_addr.itf = flow->vcc->dev ? flow->vcc->dev->number : -1; pvc.sap_addr.vpi = flow->vcc->vpi; pvc.sap_addr.vci = flow->vcc->vci; - NLA_PUT(skb, TCA_ATM_ADDR, sizeof(pvc), &pvc); + if (nla_put(skb, TCA_ATM_ADDR, sizeof(pvc), &pvc)) + goto nla_put_failure; state = ATM_VF2VS(flow->vcc->flags); - NLA_PUT_U32(skb, TCA_ATM_STATE, state); + if (nla_put_u32(skb, TCA_ATM_STATE, state)) + goto nla_put_failure; + } + if (flow->excess) { + if (nla_put_u32(skb, TCA_ATM_EXCESS, flow->classid)) + goto nla_put_failure; + } else { + if (nla_put_u32(skb, TCA_ATM_EXCESS, 0)) + goto nla_put_failure; } - if (flow->excess) - NLA_PUT_U32(skb, TCA_ATM_EXCESS, flow->classid); - else - NLA_PUT_U32(skb, TCA_ATM_EXCESS, 0); - nla_nest_end(skb, nest); return skb->len; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 24d94c097b3..6aabd77d1cf 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1425,7 +1425,8 @@ static int cbq_dump_rate(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); - NLA_PUT(skb, TCA_CBQ_RATE, sizeof(cl->R_tab->rate), &cl->R_tab->rate); + if (nla_put(skb, TCA_CBQ_RATE, sizeof(cl->R_tab->rate), &cl->R_tab->rate)) + goto nla_put_failure; return skb->len; nla_put_failure: @@ -1450,7 +1451,8 @@ static int cbq_dump_lss(struct sk_buff *skb, struct cbq_class *cl) opt.minidle = (u32)(-cl->minidle); opt.offtime = cl->offtime; opt.change = ~0; - NLA_PUT(skb, TCA_CBQ_LSSOPT, sizeof(opt), &opt); + if (nla_put(skb, TCA_CBQ_LSSOPT, sizeof(opt), &opt)) + goto nla_put_failure; return skb->len; nla_put_failure: @@ -1468,7 +1470,8 @@ static int cbq_dump_wrr(struct sk_buff *skb, struct cbq_class *cl) opt.priority = cl->priority + 1; opt.cpriority = cl->cpriority + 1; opt.weight = cl->weight; - NLA_PUT(skb, TCA_CBQ_WRROPT, sizeof(opt), &opt); + if (nla_put(skb, TCA_CBQ_WRROPT, sizeof(opt), &opt)) + goto nla_put_failure; return skb->len; nla_put_failure: @@ -1485,7 +1488,8 @@ static int cbq_dump_ovl(struct sk_buff *skb, struct cbq_class *cl) opt.priority2 = cl->priority2 + 1; opt.pad = 0; opt.penalty = cl->penalty; - NLA_PUT(skb, TCA_CBQ_OVL_STRATEGY, sizeof(opt), &opt); + if (nla_put(skb, TCA_CBQ_OVL_STRATEGY, sizeof(opt), &opt)) + goto nla_put_failure; return skb->len; nla_put_failure: @@ -1502,7 +1506,8 @@ static int cbq_dump_fopt(struct sk_buff *skb, struct cbq_class *cl) opt.split = cl->split ? cl->split->common.classid : 0; opt.defmap = cl->defmap; opt.defchange = ~0; - NLA_PUT(skb, TCA_CBQ_FOPT, sizeof(opt), &opt); + if (nla_put(skb, TCA_CBQ_FOPT, sizeof(opt), &opt)) + goto nla_put_failure; } return skb->len; @@ -1521,7 +1526,8 @@ static int cbq_dump_police(struct sk_buff *skb, struct cbq_class *cl) opt.police = cl->police; opt.__res1 = 0; opt.__res2 = 0; - NLA_PUT(skb, TCA_CBQ_POLICE, sizeof(opt), &opt); + if (nla_put(skb, TCA_CBQ_POLICE, sizeof(opt), &opt)) + goto nla_put_failure; } return skb->len; diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 7e267d7b9c7..cc37dd52ecf 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -332,15 +332,13 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch) } q->stats.pdrop++; - sch->qstats.drops++; - kfree_skb(skb); - return NET_XMIT_DROP; + return qdisc_drop(skb, sch); - congestion_drop: +congestion_drop: qdisc_drop(skb, sch); return NET_XMIT_CN; - other_drop: +other_drop: if (ret & __NET_XMIT_BYPASS) sch->qstats.drops++; kfree_skb(skb); @@ -515,8 +513,9 @@ static int choke_dump(struct Qdisc *sch, struct sk_buff *skb) if (opts == NULL) goto nla_put_failure; - NLA_PUT(skb, TCA_CHOKE_PARMS, sizeof(opt), &opt); - NLA_PUT_U32(skb, TCA_CHOKE_MAX_P, q->parms.max_P); + if (nla_put(skb, TCA_CHOKE_PARMS, sizeof(opt), &opt) || + nla_put_u32(skb, TCA_CHOKE_MAX_P, q->parms.max_P)) + goto nla_put_failure; return nla_nest_end(skb, opts); nla_put_failure: diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c new file mode 100644 index 00000000000..2f9ab17db85 --- /dev/null +++ b/net/sched/sch_codel.c @@ -0,0 +1,276 @@ +/* + * Codel - The Controlled-Delay Active Queue Management algorithm + * + * Copyright (C) 2011-2012 Kathleen Nichols <nichols@pollere.com> + * Copyright (C) 2011-2012 Van Jacobson <van@pollere.net> + * + * Implemented on linux by : + * Copyright (C) 2012 Michael D. Taht <dave.taht@bufferbloat.net> + * Copyright (C) 2012 Eric Dumazet <edumazet@google.com> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions, and the following disclaimer, + * without modification. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. The names of the authors may not be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * Alternatively, provided that this notice is retained in full, this + * software may be distributed under the terms of the GNU General + * Public License ("GPL") version 2, in which case the provisions of the + * GPL apply INSTEAD OF those given above. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH + * DAMAGE. + * + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <linux/prefetch.h> +#include <net/pkt_sched.h> +#include <net/codel.h> + + +#define DEFAULT_CODEL_LIMIT 1000 + +struct codel_sched_data { + struct codel_params params; + struct codel_vars vars; + struct codel_stats stats; + u32 drop_overlimit; +}; + +/* This is the specific function called from codel_dequeue() + * to dequeue a packet from queue. Note: backlog is handled in + * codel, we dont need to reduce it here. + */ +static struct sk_buff *dequeue(struct codel_vars *vars, struct Qdisc *sch) +{ + struct sk_buff *skb = __skb_dequeue(&sch->q); + + prefetch(&skb->end); /* we'll need skb_shinfo() */ + return skb; +} + +static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch) +{ + struct codel_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb; + + skb = codel_dequeue(sch, &q->params, &q->vars, &q->stats, dequeue); + + /* We cant call qdisc_tree_decrease_qlen() if our qlen is 0, + * or HTB crashes. Defer it for next round. + */ + if (q->stats.drop_count && sch->q.qlen) { + qdisc_tree_decrease_qlen(sch, q->stats.drop_count); + q->stats.drop_count = 0; + } + if (skb) + qdisc_bstats_update(sch, skb); + return skb; +} + +static int codel_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch) +{ + struct codel_sched_data *q; + + if (likely(qdisc_qlen(sch) < sch->limit)) { + codel_set_enqueue_time(skb); + return qdisc_enqueue_tail(skb, sch); + } + q = qdisc_priv(sch); + q->drop_overlimit++; + return qdisc_drop(skb, sch); +} + +static const struct nla_policy codel_policy[TCA_CODEL_MAX + 1] = { + [TCA_CODEL_TARGET] = { .type = NLA_U32 }, + [TCA_CODEL_LIMIT] = { .type = NLA_U32 }, + [TCA_CODEL_INTERVAL] = { .type = NLA_U32 }, + [TCA_CODEL_ECN] = { .type = NLA_U32 }, +}; + +static int codel_change(struct Qdisc *sch, struct nlattr *opt) +{ + struct codel_sched_data *q = qdisc_priv(sch); + struct nlattr *tb[TCA_CODEL_MAX + 1]; + unsigned int qlen; + int err; + + if (!opt) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_CODEL_MAX, opt, codel_policy); + if (err < 0) + return err; + + sch_tree_lock(sch); + + if (tb[TCA_CODEL_TARGET]) { + u32 target = nla_get_u32(tb[TCA_CODEL_TARGET]); + + q->params.target = ((u64)target * NSEC_PER_USEC) >> CODEL_SHIFT; + } + + if (tb[TCA_CODEL_INTERVAL]) { + u32 interval = nla_get_u32(tb[TCA_CODEL_INTERVAL]); + + q->params.interval = ((u64)interval * NSEC_PER_USEC) >> CODEL_SHIFT; + } + + if (tb[TCA_CODEL_LIMIT]) + sch->limit = nla_get_u32(tb[TCA_CODEL_LIMIT]); + + if (tb[TCA_CODEL_ECN]) + q->params.ecn = !!nla_get_u32(tb[TCA_CODEL_ECN]); + + qlen = sch->q.qlen; + while (sch->q.qlen > sch->limit) { + struct sk_buff *skb = __skb_dequeue(&sch->q); + + sch->qstats.backlog -= qdisc_pkt_len(skb); + qdisc_drop(skb, sch); + } + qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen); + + sch_tree_unlock(sch); + return 0; +} + +static int codel_init(struct Qdisc *sch, struct nlattr *opt) +{ + struct codel_sched_data *q = qdisc_priv(sch); + + sch->limit = DEFAULT_CODEL_LIMIT; + + codel_params_init(&q->params); + codel_vars_init(&q->vars); + codel_stats_init(&q->stats); + + if (opt) { + int err = codel_change(sch, opt); + + if (err) + return err; + } + + if (sch->limit >= 1) + sch->flags |= TCQ_F_CAN_BYPASS; + else + sch->flags &= ~TCQ_F_CAN_BYPASS; + + return 0; +} + +static int codel_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct codel_sched_data *q = qdisc_priv(sch); + struct nlattr *opts; + + opts = nla_nest_start(skb, TCA_OPTIONS); + if (opts == NULL) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_CODEL_TARGET, + codel_time_to_us(q->params.target)) || + nla_put_u32(skb, TCA_CODEL_LIMIT, + sch->limit) || + nla_put_u32(skb, TCA_CODEL_INTERVAL, + codel_time_to_us(q->params.interval)) || + nla_put_u32(skb, TCA_CODEL_ECN, + q->params.ecn)) + goto nla_put_failure; + + return nla_nest_end(skb, opts); + +nla_put_failure: + nla_nest_cancel(skb, opts); + return -1; +} + +static int codel_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + const struct codel_sched_data *q = qdisc_priv(sch); + struct tc_codel_xstats st = { + .maxpacket = q->stats.maxpacket, + .count = q->vars.count, + .lastcount = q->vars.lastcount, + .drop_overlimit = q->drop_overlimit, + .ldelay = codel_time_to_us(q->vars.ldelay), + .dropping = q->vars.dropping, + .ecn_mark = q->stats.ecn_mark, + }; + + if (q->vars.dropping) { + codel_tdiff_t delta = q->vars.drop_next - codel_get_time(); + + if (delta >= 0) + st.drop_next = codel_time_to_us(delta); + else + st.drop_next = -codel_time_to_us(-delta); + } + + return gnet_stats_copy_app(d, &st, sizeof(st)); +} + +static void codel_reset(struct Qdisc *sch) +{ + struct codel_sched_data *q = qdisc_priv(sch); + + qdisc_reset_queue(sch); + codel_vars_init(&q->vars); +} + +static struct Qdisc_ops codel_qdisc_ops __read_mostly = { + .id = "codel", + .priv_size = sizeof(struct codel_sched_data), + + .enqueue = codel_qdisc_enqueue, + .dequeue = codel_qdisc_dequeue, + .peek = qdisc_peek_dequeued, + .init = codel_init, + .reset = codel_reset, + .change = codel_change, + .dump = codel_dump, + .dump_stats = codel_dump_stats, + .owner = THIS_MODULE, +}; + +static int __init codel_module_init(void) +{ + return register_qdisc(&codel_qdisc_ops); +} + +static void __exit codel_module_exit(void) +{ + unregister_qdisc(&codel_qdisc_ops); +} + +module_init(codel_module_init) +module_exit(codel_module_exit) + +MODULE_DESCRIPTION("Controlled Delay queue discipline"); +MODULE_AUTHOR("Dave Taht"); +MODULE_AUTHOR("Eric Dumazet"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 6b7fe4a84f1..9ce0b4fe23f 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -260,7 +260,8 @@ static int drr_dump_class(struct Qdisc *sch, unsigned long arg, nest = nla_nest_start(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; - NLA_PUT_U32(skb, TCA_DRR_QUANTUM, cl->quantum); + if (nla_put_u32(skb, TCA_DRR_QUANTUM, cl->quantum)) + goto nla_put_failure; return nla_nest_end(skb, nest); nla_put_failure: @@ -375,8 +376,6 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch) cl->deficit = cl->quantum; } - bstats_update(&cl->bstats, skb); - sch->q.qlen++; return err; } @@ -402,6 +401,8 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch) skb = qdisc_dequeue_peeked(cl->qdisc); if (cl->qdisc->q.qlen == 0) list_del(&cl->alist); + + bstats_update(&cl->bstats, skb); qdisc_bstats_update(sch, skb); sch->q.qlen--; return skb; diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 2c790204d04..3886365cc20 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -265,8 +265,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch) return NET_XMIT_SUCCESS; drop: - kfree_skb(skb); - sch->qstats.drops++; + qdisc_drop(skb, sch); return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; } @@ -429,8 +428,9 @@ static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, opts = nla_nest_start(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; - NLA_PUT_U8(skb, TCA_DSMARK_MASK, p->mask[cl - 1]); - NLA_PUT_U8(skb, TCA_DSMARK_VALUE, p->value[cl - 1]); + if (nla_put_u8(skb, TCA_DSMARK_MASK, p->mask[cl - 1]) || + nla_put_u8(skb, TCA_DSMARK_VALUE, p->value[cl - 1])) + goto nla_put_failure; return nla_nest_end(skb, opts); @@ -447,13 +447,16 @@ static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb) opts = nla_nest_start(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; - NLA_PUT_U16(skb, TCA_DSMARK_INDICES, p->indices); + if (nla_put_u16(skb, TCA_DSMARK_INDICES, p->indices)) + goto nla_put_failure; - if (p->default_index != NO_DEFAULT_INDEX) - NLA_PUT_U16(skb, TCA_DSMARK_DEFAULT_INDEX, p->default_index); + if (p->default_index != NO_DEFAULT_INDEX && + nla_put_u16(skb, TCA_DSMARK_DEFAULT_INDEX, p->default_index)) + goto nla_put_failure; - if (p->set_tc_index) - NLA_PUT_FLAG(skb, TCA_DSMARK_SET_TC_INDEX); + if (p->set_tc_index && + nla_put_flag(skb, TCA_DSMARK_SET_TC_INDEX)) + goto nla_put_failure; return nla_nest_end(skb, opts); diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index 66effe2da8e..e15a9eb2908 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -85,7 +85,8 @@ static int fifo_dump(struct Qdisc *sch, struct sk_buff *skb) { struct tc_fifo_qopt opt = { .limit = sch->limit }; - NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); + if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) + goto nla_put_failure; return skb->len; nla_put_failure: diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c new file mode 100644 index 00000000000..9fc1c62ec80 --- /dev/null +++ b/net/sched/sch_fq_codel.c @@ -0,0 +1,626 @@ +/* + * Fair Queue CoDel discipline + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Copyright (C) 2012 Eric Dumazet <edumazet@google.com> + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/jiffies.h> +#include <linux/string.h> +#include <linux/in.h> +#include <linux/errno.h> +#include <linux/init.h> +#include <linux/skbuff.h> +#include <linux/jhash.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <net/netlink.h> +#include <net/pkt_sched.h> +#include <net/flow_keys.h> +#include <net/codel.h> + +/* Fair Queue CoDel. + * + * Principles : + * Packets are classified (internal classifier or external) on flows. + * This is a Stochastic model (as we use a hash, several flows + * might be hashed on same slot) + * Each flow has a CoDel managed queue. + * Flows are linked onto two (Round Robin) lists, + * so that new flows have priority on old ones. + * + * For a given flow, packets are not reordered (CoDel uses a FIFO) + * head drops only. + * ECN capability is on by default. + * Low memory footprint (64 bytes per flow) + */ + +struct fq_codel_flow { + struct sk_buff *head; + struct sk_buff *tail; + struct list_head flowchain; + int deficit; + u32 dropped; /* number of drops (or ECN marks) on this flow */ + struct codel_vars cvars; +}; /* please try to keep this structure <= 64 bytes */ + +struct fq_codel_sched_data { + struct tcf_proto *filter_list; /* optional external classifier */ + struct fq_codel_flow *flows; /* Flows table [flows_cnt] */ + u32 *backlogs; /* backlog table [flows_cnt] */ + u32 flows_cnt; /* number of flows */ + u32 perturbation; /* hash perturbation */ + u32 quantum; /* psched_mtu(qdisc_dev(sch)); */ + struct codel_params cparams; + struct codel_stats cstats; + u32 drop_overlimit; + u32 new_flow_count; + + struct list_head new_flows; /* list of new flows */ + struct list_head old_flows; /* list of old flows */ +}; + +static unsigned int fq_codel_hash(const struct fq_codel_sched_data *q, + const struct sk_buff *skb) +{ + struct flow_keys keys; + unsigned int hash; + + skb_flow_dissect(skb, &keys); + hash = jhash_3words((__force u32)keys.dst, + (__force u32)keys.src ^ keys.ip_proto, + (__force u32)keys.ports, q->perturbation); + return ((u64)hash * q->flows_cnt) >> 32; +} + +static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch, + int *qerr) +{ + struct fq_codel_sched_data *q = qdisc_priv(sch); + struct tcf_result res; + int result; + + if (TC_H_MAJ(skb->priority) == sch->handle && + TC_H_MIN(skb->priority) > 0 && + TC_H_MIN(skb->priority) <= q->flows_cnt) + return TC_H_MIN(skb->priority); + + if (!q->filter_list) + return fq_codel_hash(q, skb) + 1; + + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + result = tc_classify(skb, q->filter_list, &res); + if (result >= 0) { +#ifdef CONFIG_NET_CLS_ACT + switch (result) { + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + case TC_ACT_SHOT: + return 0; + } +#endif + if (TC_H_MIN(res.classid) <= q->flows_cnt) + return TC_H_MIN(res.classid); + } + return 0; +} + +/* helper functions : might be changed when/if skb use a standard list_head */ + +/* remove one skb from head of slot queue */ +static inline struct sk_buff *dequeue_head(struct fq_codel_flow *flow) +{ + struct sk_buff *skb = flow->head; + + flow->head = skb->next; + skb->next = NULL; + return skb; +} + +/* add skb to flow queue (tail add) */ +static inline void flow_queue_add(struct fq_codel_flow *flow, + struct sk_buff *skb) +{ + if (flow->head == NULL) + flow->head = skb; + else + flow->tail->next = skb; + flow->tail = skb; + skb->next = NULL; +} + +static unsigned int fq_codel_drop(struct Qdisc *sch) +{ + struct fq_codel_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb; + unsigned int maxbacklog = 0, idx = 0, i, len; + struct fq_codel_flow *flow; + + /* Queue is full! Find the fat flow and drop packet from it. + * This might sound expensive, but with 1024 flows, we scan + * 4KB of memory, and we dont need to handle a complex tree + * in fast path (packet queue/enqueue) with many cache misses. + */ + for (i = 0; i < q->flows_cnt; i++) { + if (q->backlogs[i] > maxbacklog) { + maxbacklog = q->backlogs[i]; + idx = i; + } + } + flow = &q->flows[idx]; + skb = dequeue_head(flow); + len = qdisc_pkt_len(skb); + q->backlogs[idx] -= len; + kfree_skb(skb); + sch->q.qlen--; + sch->qstats.drops++; + sch->qstats.backlog -= len; + flow->dropped++; + return idx; +} + +static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch) +{ + struct fq_codel_sched_data *q = qdisc_priv(sch); + unsigned int idx; + struct fq_codel_flow *flow; + int uninitialized_var(ret); + + idx = fq_codel_classify(skb, sch, &ret); + if (idx == 0) { + if (ret & __NET_XMIT_BYPASS) + sch->qstats.drops++; + kfree_skb(skb); + return ret; + } + idx--; + + codel_set_enqueue_time(skb); + flow = &q->flows[idx]; + flow_queue_add(flow, skb); + q->backlogs[idx] += qdisc_pkt_len(skb); + sch->qstats.backlog += qdisc_pkt_len(skb); + + if (list_empty(&flow->flowchain)) { + list_add_tail(&flow->flowchain, &q->new_flows); + codel_vars_init(&flow->cvars); + q->new_flow_count++; + flow->deficit = q->quantum; + flow->dropped = 0; + } + if (++sch->q.qlen < sch->limit) + return NET_XMIT_SUCCESS; + + q->drop_overlimit++; + /* Return Congestion Notification only if we dropped a packet + * from this flow. + */ + if (fq_codel_drop(sch) == idx) + return NET_XMIT_CN; + + /* As we dropped a packet, better let upper stack know this */ + qdisc_tree_decrease_qlen(sch, 1); + return NET_XMIT_SUCCESS; +} + +/* This is the specific function called from codel_dequeue() + * to dequeue a packet from queue. Note: backlog is handled in + * codel, we dont need to reduce it here. + */ +static struct sk_buff *dequeue(struct codel_vars *vars, struct Qdisc *sch) +{ + struct fq_codel_sched_data *q = qdisc_priv(sch); + struct fq_codel_flow *flow; + struct sk_buff *skb = NULL; + + flow = container_of(vars, struct fq_codel_flow, cvars); + if (flow->head) { + skb = dequeue_head(flow); + q->backlogs[flow - q->flows] -= qdisc_pkt_len(skb); + sch->q.qlen--; + } + return skb; +} + +static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch) +{ + struct fq_codel_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb; + struct fq_codel_flow *flow; + struct list_head *head; + u32 prev_drop_count, prev_ecn_mark; + +begin: + head = &q->new_flows; + if (list_empty(head)) { + head = &q->old_flows; + if (list_empty(head)) + return NULL; + } + flow = list_first_entry(head, struct fq_codel_flow, flowchain); + + if (flow->deficit <= 0) { + flow->deficit += q->quantum; + list_move_tail(&flow->flowchain, &q->old_flows); + goto begin; + } + + prev_drop_count = q->cstats.drop_count; + prev_ecn_mark = q->cstats.ecn_mark; + + skb = codel_dequeue(sch, &q->cparams, &flow->cvars, &q->cstats, + dequeue); + + flow->dropped += q->cstats.drop_count - prev_drop_count; + flow->dropped += q->cstats.ecn_mark - prev_ecn_mark; + + if (!skb) { + /* force a pass through old_flows to prevent starvation */ + if ((head == &q->new_flows) && !list_empty(&q->old_flows)) + list_move_tail(&flow->flowchain, &q->old_flows); + else + list_del_init(&flow->flowchain); + goto begin; + } + qdisc_bstats_update(sch, skb); + flow->deficit -= qdisc_pkt_len(skb); + /* We cant call qdisc_tree_decrease_qlen() if our qlen is 0, + * or HTB crashes. Defer it for next round. + */ + if (q->cstats.drop_count && sch->q.qlen) { + qdisc_tree_decrease_qlen(sch, q->cstats.drop_count); + q->cstats.drop_count = 0; + } + return skb; +} + +static void fq_codel_reset(struct Qdisc *sch) +{ + struct sk_buff *skb; + + while ((skb = fq_codel_dequeue(sch)) != NULL) + kfree_skb(skb); +} + +static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = { + [TCA_FQ_CODEL_TARGET] = { .type = NLA_U32 }, + [TCA_FQ_CODEL_LIMIT] = { .type = NLA_U32 }, + [TCA_FQ_CODEL_INTERVAL] = { .type = NLA_U32 }, + [TCA_FQ_CODEL_ECN] = { .type = NLA_U32 }, + [TCA_FQ_CODEL_FLOWS] = { .type = NLA_U32 }, + [TCA_FQ_CODEL_QUANTUM] = { .type = NLA_U32 }, +}; + +static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt) +{ + struct fq_codel_sched_data *q = qdisc_priv(sch); + struct nlattr *tb[TCA_FQ_CODEL_MAX + 1]; + int err; + + if (!opt) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_FQ_CODEL_MAX, opt, fq_codel_policy); + if (err < 0) + return err; + if (tb[TCA_FQ_CODEL_FLOWS]) { + if (q->flows) + return -EINVAL; + q->flows_cnt = nla_get_u32(tb[TCA_FQ_CODEL_FLOWS]); + if (!q->flows_cnt || + q->flows_cnt > 65536) + return -EINVAL; + } + sch_tree_lock(sch); + + if (tb[TCA_FQ_CODEL_TARGET]) { + u64 target = nla_get_u32(tb[TCA_FQ_CODEL_TARGET]); + + q->cparams.target = (target * NSEC_PER_USEC) >> CODEL_SHIFT; + } + + if (tb[TCA_FQ_CODEL_INTERVAL]) { + u64 interval = nla_get_u32(tb[TCA_FQ_CODEL_INTERVAL]); + + q->cparams.interval = (interval * NSEC_PER_USEC) >> CODEL_SHIFT; + } + + if (tb[TCA_FQ_CODEL_LIMIT]) + sch->limit = nla_get_u32(tb[TCA_FQ_CODEL_LIMIT]); + + if (tb[TCA_FQ_CODEL_ECN]) + q->cparams.ecn = !!nla_get_u32(tb[TCA_FQ_CODEL_ECN]); + + if (tb[TCA_FQ_CODEL_QUANTUM]) + q->quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM])); + + while (sch->q.qlen > sch->limit) { + struct sk_buff *skb = fq_codel_dequeue(sch); + + kfree_skb(skb); + q->cstats.drop_count++; + } + qdisc_tree_decrease_qlen(sch, q->cstats.drop_count); + q->cstats.drop_count = 0; + + sch_tree_unlock(sch); + return 0; +} + +static void *fq_codel_zalloc(size_t sz) +{ + void *ptr = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN); + + if (!ptr) + ptr = vzalloc(sz); + return ptr; +} + +static void fq_codel_free(void *addr) +{ + if (addr) { + if (is_vmalloc_addr(addr)) + vfree(addr); + else + kfree(addr); + } +} + +static void fq_codel_destroy(struct Qdisc *sch) +{ + struct fq_codel_sched_data *q = qdisc_priv(sch); + + tcf_destroy_chain(&q->filter_list); + fq_codel_free(q->backlogs); + fq_codel_free(q->flows); +} + +static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) +{ + struct fq_codel_sched_data *q = qdisc_priv(sch); + int i; + + sch->limit = 10*1024; + q->flows_cnt = 1024; + q->quantum = psched_mtu(qdisc_dev(sch)); + q->perturbation = net_random(); + INIT_LIST_HEAD(&q->new_flows); + INIT_LIST_HEAD(&q->old_flows); + codel_params_init(&q->cparams); + codel_stats_init(&q->cstats); + q->cparams.ecn = true; + + if (opt) { + int err = fq_codel_change(sch, opt); + if (err) + return err; + } + + if (!q->flows) { + q->flows = fq_codel_zalloc(q->flows_cnt * + sizeof(struct fq_codel_flow)); + if (!q->flows) + return -ENOMEM; + q->backlogs = fq_codel_zalloc(q->flows_cnt * sizeof(u32)); + if (!q->backlogs) { + fq_codel_free(q->flows); + return -ENOMEM; + } + for (i = 0; i < q->flows_cnt; i++) { + struct fq_codel_flow *flow = q->flows + i; + + INIT_LIST_HEAD(&flow->flowchain); + } + } + if (sch->limit >= 1) + sch->flags |= TCQ_F_CAN_BYPASS; + else + sch->flags &= ~TCQ_F_CAN_BYPASS; + return 0; +} + +static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct fq_codel_sched_data *q = qdisc_priv(sch); + struct nlattr *opts; + + opts = nla_nest_start(skb, TCA_OPTIONS); + if (opts == NULL) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_FQ_CODEL_TARGET, + codel_time_to_us(q->cparams.target)) || + nla_put_u32(skb, TCA_FQ_CODEL_LIMIT, + sch->limit) || + nla_put_u32(skb, TCA_FQ_CODEL_INTERVAL, + codel_time_to_us(q->cparams.interval)) || + nla_put_u32(skb, TCA_FQ_CODEL_ECN, + q->cparams.ecn) || + nla_put_u32(skb, TCA_FQ_CODEL_QUANTUM, + q->quantum) || + nla_put_u32(skb, TCA_FQ_CODEL_FLOWS, + q->flows_cnt)) + goto nla_put_failure; + + nla_nest_end(skb, opts); + return skb->len; + +nla_put_failure: + return -1; +} + +static int fq_codel_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct fq_codel_sched_data *q = qdisc_priv(sch); + struct tc_fq_codel_xstats st = { + .type = TCA_FQ_CODEL_XSTATS_QDISC, + }; + struct list_head *pos; + + st.qdisc_stats.maxpacket = q->cstats.maxpacket; + st.qdisc_stats.drop_overlimit = q->drop_overlimit; + st.qdisc_stats.ecn_mark = q->cstats.ecn_mark; + st.qdisc_stats.new_flow_count = q->new_flow_count; + + list_for_each(pos, &q->new_flows) + st.qdisc_stats.new_flows_len++; + + list_for_each(pos, &q->old_flows) + st.qdisc_stats.old_flows_len++; + + return gnet_stats_copy_app(d, &st, sizeof(st)); +} + +static struct Qdisc *fq_codel_leaf(struct Qdisc *sch, unsigned long arg) +{ + return NULL; +} + +static unsigned long fq_codel_get(struct Qdisc *sch, u32 classid) +{ + return 0; +} + +static unsigned long fq_codel_bind(struct Qdisc *sch, unsigned long parent, + u32 classid) +{ + /* we cannot bypass queue discipline anymore */ + sch->flags &= ~TCQ_F_CAN_BYPASS; + return 0; +} + +static void fq_codel_put(struct Qdisc *q, unsigned long cl) +{ +} + +static struct tcf_proto **fq_codel_find_tcf(struct Qdisc *sch, unsigned long cl) +{ + struct fq_codel_sched_data *q = qdisc_priv(sch); + + if (cl) + return NULL; + return &q->filter_list; +} + +static int fq_codel_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + tcm->tcm_handle |= TC_H_MIN(cl); + return 0; +} + +static int fq_codel_dump_class_stats(struct Qdisc *sch, unsigned long cl, + struct gnet_dump *d) +{ + struct fq_codel_sched_data *q = qdisc_priv(sch); + u32 idx = cl - 1; + struct gnet_stats_queue qs = { 0 }; + struct tc_fq_codel_xstats xstats; + + if (idx < q->flows_cnt) { + const struct fq_codel_flow *flow = &q->flows[idx]; + const struct sk_buff *skb = flow->head; + + memset(&xstats, 0, sizeof(xstats)); + xstats.type = TCA_FQ_CODEL_XSTATS_CLASS; + xstats.class_stats.deficit = flow->deficit; + xstats.class_stats.ldelay = + codel_time_to_us(flow->cvars.ldelay); + xstats.class_stats.count = flow->cvars.count; + xstats.class_stats.lastcount = flow->cvars.lastcount; + xstats.class_stats.dropping = flow->cvars.dropping; + if (flow->cvars.dropping) { + codel_tdiff_t delta = flow->cvars.drop_next - + codel_get_time(); + + xstats.class_stats.drop_next = (delta >= 0) ? + codel_time_to_us(delta) : + -codel_time_to_us(-delta); + } + while (skb) { + qs.qlen++; + skb = skb->next; + } + qs.backlog = q->backlogs[idx]; + qs.drops = flow->dropped; + } + if (gnet_stats_copy_queue(d, &qs) < 0) + return -1; + if (idx < q->flows_cnt) + return gnet_stats_copy_app(d, &xstats, sizeof(xstats)); + return 0; +} + +static void fq_codel_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + struct fq_codel_sched_data *q = qdisc_priv(sch); + unsigned int i; + + if (arg->stop) + return; + + for (i = 0; i < q->flows_cnt; i++) { + if (list_empty(&q->flows[i].flowchain) || + arg->count < arg->skip) { + arg->count++; + continue; + } + if (arg->fn(sch, i + 1, arg) < 0) { + arg->stop = 1; + break; + } + arg->count++; + } +} + +static const struct Qdisc_class_ops fq_codel_class_ops = { + .leaf = fq_codel_leaf, + .get = fq_codel_get, + .put = fq_codel_put, + .tcf_chain = fq_codel_find_tcf, + .bind_tcf = fq_codel_bind, + .unbind_tcf = fq_codel_put, + .dump = fq_codel_dump_class, + .dump_stats = fq_codel_dump_class_stats, + .walk = fq_codel_walk, +}; + +static struct Qdisc_ops fq_codel_qdisc_ops __read_mostly = { + .cl_ops = &fq_codel_class_ops, + .id = "fq_codel", + .priv_size = sizeof(struct fq_codel_sched_data), + .enqueue = fq_codel_enqueue, + .dequeue = fq_codel_dequeue, + .peek = qdisc_peek_dequeued, + .drop = fq_codel_drop, + .init = fq_codel_init, + .reset = fq_codel_reset, + .destroy = fq_codel_destroy, + .change = fq_codel_change, + .dump = fq_codel_dump, + .dump_stats = fq_codel_dump_stats, + .owner = THIS_MODULE, +}; + +static int __init fq_codel_module_init(void) +{ + return register_qdisc(&fq_codel_qdisc_ops); +} + +static void __exit fq_codel_module_exit(void) +{ + unregister_qdisc(&fq_codel_qdisc_ops); +} + +module_init(fq_codel_module_init) +module_exit(fq_codel_module_exit) +MODULE_AUTHOR("Eric Dumazet"); +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 67fc573e013..511323e89ce 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -86,9 +86,8 @@ static inline int handle_dev_cpu_collision(struct sk_buff *skb, * deadloop is detected. Return OK to try the next skb. */ kfree_skb(skb); - if (net_ratelimit()) - pr_warning("Dead loop on netdevice %s, fix it urgently!\n", - dev_queue->dev->name); + net_warn_ratelimited("Dead loop on netdevice %s, fix it urgently!\n", + dev_queue->dev->name); ret = qdisc_qlen(q); } else { /* @@ -136,9 +135,9 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, ret = handle_dev_cpu_collision(skb, txq, q); } else { /* Driver returned NETDEV_TX_BUSY - requeue skb */ - if (unlikely (ret != NETDEV_TX_BUSY && net_ratelimit())) - pr_warning("BUG %s code %d qlen %d\n", - dev->name, ret, q->q.qlen); + if (unlikely(ret != NETDEV_TX_BUSY)) + net_warn_ratelimited("BUG %s code %d qlen %d\n", + dev->name, ret, q->q.qlen); ret = dev_requeue_skb(skb, q); } @@ -512,7 +511,8 @@ static int pfifo_fast_dump(struct Qdisc *qdisc, struct sk_buff *skb) struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS }; memcpy(&opt.priomap, prio2band, TC_PRIO_MAX + 1); - NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); + if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) + goto nla_put_failure; return skb->len; nla_put_failure: diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 0b15236be7b..e901583e4ea 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -255,10 +255,8 @@ static struct sk_buff *gred_dequeue(struct Qdisc *sch) u16 dp = tc_index_to_dp(skb); if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { - if (net_ratelimit()) - pr_warning("GRED: Unable to relocate VQ 0x%x " - "after dequeue, screwing up " - "backlog.\n", tc_index_to_dp(skb)); + net_warn_ratelimited("GRED: Unable to relocate VQ 0x%x after dequeue, screwing up backlog\n", + tc_index_to_dp(skb)); } else { q->backlog -= qdisc_pkt_len(skb); @@ -287,10 +285,8 @@ static unsigned int gred_drop(struct Qdisc *sch) u16 dp = tc_index_to_dp(skb); if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { - if (net_ratelimit()) - pr_warning("GRED: Unable to relocate VQ 0x%x " - "while dropping, screwing up " - "backlog.\n", tc_index_to_dp(skb)); + net_warn_ratelimited("GRED: Unable to relocate VQ 0x%x while dropping, screwing up backlog\n", + tc_index_to_dp(skb)); } else { q->backlog -= len; q->stats.other++; @@ -521,14 +517,16 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb) opts = nla_nest_start(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; - NLA_PUT(skb, TCA_GRED_DPS, sizeof(sopt), &sopt); + if (nla_put(skb, TCA_GRED_DPS, sizeof(sopt), &sopt)) + goto nla_put_failure; for (i = 0; i < MAX_DPs; i++) { struct gred_sched_data *q = table->tab[i]; max_p[i] = q ? q->parms.max_P : 0; } - NLA_PUT(skb, TCA_GRED_MAX_P, sizeof(max_p), max_p); + if (nla_put(skb, TCA_GRED_MAX_P, sizeof(max_p), max_p)) + goto nla_put_failure; parms = nla_nest_start(skb, TCA_GRED_PARMS); if (parms == NULL) @@ -565,11 +563,8 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb) opt.packets = q->packetsin; opt.bytesin = q->bytesin; - if (gred_wred_mode(table)) { - q->vars.qidlestart = - table->tab[table->def]->vars.qidlestart; - q->vars.qavg = table->tab[table->def]->vars.qavg; - } + if (gred_wred_mode(table)) + gred_load_wred_set(table, q); opt.qave = red_calc_qavg(&q->parms, &q->vars, q->vars.qavg); diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 9bdca2e011e..6c2ec451054 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1305,7 +1305,8 @@ hfsc_dump_sc(struct sk_buff *skb, int attr, struct internal_sc *sc) tsc.m1 = sm2m(sc->sm1); tsc.d = dx2d(sc->dx); tsc.m2 = sm2m(sc->sm2); - NLA_PUT(skb, attr, sizeof(tsc), &tsc); + if (nla_put(skb, attr, sizeof(tsc), &tsc)) + goto nla_put_failure; return skb->len; @@ -1573,7 +1574,8 @@ hfsc_dump_qdisc(struct Qdisc *sch, struct sk_buff *skb) } qopt.defcls = q->defcls; - NLA_PUT(skb, TCA_OPTIONS, sizeof(qopt), &qopt); + if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt)) + goto nla_put_failure; return skb->len; nla_put_failure: @@ -1607,7 +1609,6 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (cl->qdisc->q.qlen == 1) set_active(cl, qdisc_pkt_len(skb)); - bstats_update(&cl->bstats, skb); sch->q.qlen++; return NET_XMIT_SUCCESS; @@ -1655,6 +1656,7 @@ hfsc_dequeue(struct Qdisc *sch) return NULL; } + bstats_update(&cl->bstats, skb); update_vf(cl, qdisc_pkt_len(skb), cur_time); if (realtime) cl->cl_cumul += qdisc_pkt_len(skb); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 29b942ce9e8..9d75b776131 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -558,9 +558,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch) __skb_queue_tail(&q->direct_queue, skb); q->direct_pkts++; } else { - kfree_skb(skb); - sch->qstats.drops++; - return NET_XMIT_DROP; + return qdisc_drop(skb, sch); } #ifdef CONFIG_NET_CLS_ACT } else if (!cl) { @@ -576,7 +574,6 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch) } return ret; } else { - bstats_update(&cl->bstats, skb); htb_activate(q, cl); } @@ -837,6 +834,7 @@ next: } while (cl != start); if (likely(skb != NULL)) { + bstats_update(&cl->bstats, skb); cl->un.leaf.deficit[level] -= qdisc_pkt_len(skb); if (cl->un.leaf.deficit[level] < 0) { cl->un.leaf.deficit[level] += cl->quantum; @@ -1051,7 +1049,8 @@ static int htb_dump(struct Qdisc *sch, struct sk_buff *skb) nest = nla_nest_start(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; - NLA_PUT(skb, TCA_HTB_INIT, sizeof(gopt), &gopt); + if (nla_put(skb, TCA_HTB_INIT, sizeof(gopt), &gopt)) + goto nla_put_failure; nla_nest_end(skb, nest); spin_unlock_bh(root_lock); @@ -1090,7 +1089,8 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, opt.quantum = cl->quantum; opt.prio = cl->prio; opt.level = cl->level; - NLA_PUT(skb, TCA_HTB_PARMS, sizeof(opt), &opt); + if (nla_put(skb, TCA_HTB_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; nla_nest_end(skb, nest); spin_unlock_bh(root_lock); diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 28de4309233..d1831ca966d 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -247,7 +247,8 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) opt.offset[i] = dev->tc_to_txq[i].offset; } - NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); + if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) + goto nla_put_failure; return skb->len; nla_put_failure: diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 49131d7a744..2a2b096d9a6 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -284,7 +284,8 @@ static int multiq_dump(struct Qdisc *sch, struct sk_buff *skb) opt.bands = q->bands; opt.max_bands = q->max_bands; - NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); + if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) + goto nla_put_failure; return skb->len; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 5da548fa7ae..a2a95aabf9c 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -26,6 +26,7 @@ #include <net/netlink.h> #include <net/pkt_sched.h> +#include <net/inet_ecn.h> #define VERSION "1.3" @@ -78,6 +79,7 @@ struct netem_sched_data { psched_tdiff_t jitter; u32 loss; + u32 ecn; u32 limit; u32 counter; u32 gap; @@ -374,9 +376,12 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) ++count; /* Drop packet? */ - if (loss_event(q)) - --count; - + if (loss_event(q)) { + if (q->ecn && INET_ECN_set_ce(skb)) + sch->qstats.drops++; /* mark packet */ + else + --count; + } if (count == 0) { sch->qstats.drops++; kfree_skb(skb); @@ -408,10 +413,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) { if (!(skb = skb_unshare(skb, GFP_ATOMIC)) || (skb->ip_summed == CHECKSUM_PARTIAL && - skb_checksum_help(skb))) { - sch->qstats.drops++; - return NET_XMIT_DROP; - } + skb_checksum_help(skb))) + return qdisc_drop(skb, sch); skb->data[net_random() % skb_headlen(skb)] ^= 1<<(net_random() % 8); } @@ -706,6 +709,7 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = { [TCA_NETEM_CORRUPT] = { .len = sizeof(struct tc_netem_corrupt) }, [TCA_NETEM_RATE] = { .len = sizeof(struct tc_netem_rate) }, [TCA_NETEM_LOSS] = { .type = NLA_NESTED }, + [TCA_NETEM_ECN] = { .type = NLA_U32 }, }; static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, @@ -776,6 +780,9 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) if (tb[TCA_NETEM_RATE]) get_rate(sch, tb[TCA_NETEM_RATE]); + if (tb[TCA_NETEM_ECN]) + q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]); + q->loss_model = CLG_RANDOM; if (tb[TCA_NETEM_LOSS]) ret = get_loss_clg(sch, tb[TCA_NETEM_LOSS]); @@ -834,7 +841,8 @@ static int dump_loss_model(const struct netem_sched_data *q, .p23 = q->clg.a5, }; - NLA_PUT(skb, NETEM_LOSS_GI, sizeof(gi), &gi); + if (nla_put(skb, NETEM_LOSS_GI, sizeof(gi), &gi)) + goto nla_put_failure; break; } case CLG_GILB_ELL: { @@ -845,7 +853,8 @@ static int dump_loss_model(const struct netem_sched_data *q, .k1 = q->clg.a4, }; - NLA_PUT(skb, NETEM_LOSS_GE, sizeof(ge), &ge); + if (nla_put(skb, NETEM_LOSS_GE, sizeof(ge), &ge)) + goto nla_put_failure; break; } } @@ -874,26 +883,34 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) qopt.loss = q->loss; qopt.gap = q->gap; qopt.duplicate = q->duplicate; - NLA_PUT(skb, TCA_OPTIONS, sizeof(qopt), &qopt); + if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt)) + goto nla_put_failure; cor.delay_corr = q->delay_cor.rho; cor.loss_corr = q->loss_cor.rho; cor.dup_corr = q->dup_cor.rho; - NLA_PUT(skb, TCA_NETEM_CORR, sizeof(cor), &cor); + if (nla_put(skb, TCA_NETEM_CORR, sizeof(cor), &cor)) + goto nla_put_failure; reorder.probability = q->reorder; reorder.correlation = q->reorder_cor.rho; - NLA_PUT(skb, TCA_NETEM_REORDER, sizeof(reorder), &reorder); + if (nla_put(skb, TCA_NETEM_REORDER, sizeof(reorder), &reorder)) + goto nla_put_failure; corrupt.probability = q->corrupt; corrupt.correlation = q->corrupt_cor.rho; - NLA_PUT(skb, TCA_NETEM_CORRUPT, sizeof(corrupt), &corrupt); + if (nla_put(skb, TCA_NETEM_CORRUPT, sizeof(corrupt), &corrupt)) + goto nla_put_failure; rate.rate = q->rate; rate.packet_overhead = q->packet_overhead; rate.cell_size = q->cell_size; rate.cell_overhead = q->cell_overhead; - NLA_PUT(skb, TCA_NETEM_RATE, sizeof(rate), &rate); + if (nla_put(skb, TCA_NETEM_RATE, sizeof(rate), &rate)) + goto nla_put_failure; + + if (q->ecn && nla_put_u32(skb, TCA_NETEM_ECN, q->ecn)) + goto nla_put_failure; if (dump_loss_model(q, skb) != 0) goto nla_put_failure; diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index b5d56a22b1d..79359b69ad8 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -247,7 +247,8 @@ static int prio_dump(struct Qdisc *sch, struct sk_buff *skb) opt.bands = q->bands; memcpy(&opt.priomap, q->prio2band, TC_PRIO_MAX + 1); - NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); + if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) + goto nla_put_failure; return skb->len; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index e68cb440756..9af01f3df18 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -429,8 +429,9 @@ static int qfq_dump_class(struct Qdisc *sch, unsigned long arg, nest = nla_nest_start(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; - NLA_PUT_U32(skb, TCA_QFQ_WEIGHT, ONE_FP/cl->inv_w); - NLA_PUT_U32(skb, TCA_QFQ_LMAX, cl->lmax); + if (nla_put_u32(skb, TCA_QFQ_WEIGHT, ONE_FP/cl->inv_w) || + nla_put_u32(skb, TCA_QFQ_LMAX, cl->lmax)) + goto nla_put_failure; return nla_nest_end(skb, nest); nla_put_failure: diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index a5cc3012cf4..633e32defdc 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -272,8 +272,9 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb) opts = nla_nest_start(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; - NLA_PUT(skb, TCA_RED_PARMS, sizeof(opt), &opt); - NLA_PUT_U32(skb, TCA_RED_MAX_P, q->parms.max_P); + if (nla_put(skb, TCA_RED_PARMS, sizeof(opt), &opt) || + nla_put_u32(skb, TCA_RED_MAX_P, q->parms.max_P)) + goto nla_put_failure; return nla_nest_end(skb, opts); nla_put_failure: diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index d7eea99333e..74305c883bd 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -570,7 +570,8 @@ static int sfb_dump(struct Qdisc *sch, struct sk_buff *skb) sch->qstats.backlog = q->qdisc->qstats.backlog; opts = nla_nest_start(skb, TCA_OPTIONS); - NLA_PUT(skb, TCA_SFB_PARMS, sizeof(opt), &opt); + if (nla_put(skb, TCA_SFB_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; return nla_nest_end(skb, opts); nla_put_failure: diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 02a21abea65..d3a1bc26dbf 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -812,7 +812,8 @@ static int sfq_dump(struct Qdisc *sch, struct sk_buff *skb) memcpy(&opt.stats, &q->stats, sizeof(opt.stats)); opt.flags = q->flags; - NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); + if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) + goto nla_put_failure; return skb->len; diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index b8e156319d7..4b056c15e90 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -359,7 +359,8 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb) memset(&opt.peakrate, 0, sizeof(opt.peakrate)); opt.mtu = q->mtu; opt.buffer = q->buffer; - NLA_PUT(skb, TCA_TBF_PARMS, sizeof(opt), &opt); + if (nla_put(skb, TCA_TBF_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; nla_nest_end(skb, nest); return skb->len; diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 45326599fda..ca0c29695d5 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -88,9 +88,7 @@ teql_enqueue(struct sk_buff *skb, struct Qdisc *sch) return NET_XMIT_SUCCESS; } - kfree_skb(skb); - sch->qstats.drops++; - return NET_XMIT_DROP; + return qdisc_drop(skb, sch); } static struct sk_buff * diff --git a/net/sctp/associola.c b/net/sctp/associola.c index acd2edbc073..5bc9ab161b3 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1408,7 +1408,7 @@ static inline int sctp_peer_needs_update(struct sctp_association *asoc) } /* Increase asoc's rwnd by len and send any window update SACK if needed. */ -void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned len) +void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) { struct sctp_chunk *sack; struct timer_list *timer; @@ -1465,7 +1465,7 @@ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned len) } /* Decrease asoc's rwnd by len. */ -void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned len) +void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) { int rx_count; int over = 0; diff --git a/net/sctp/input.c b/net/sctp/input.c index 80f71af7138..80564fe0302 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -342,7 +342,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) sctp_bh_lock_sock(sk); if (sock_owned_by_user(sk)) { - if (sk_add_backlog(sk, skb)) + if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) sctp_chunk_free(chunk); else backloged = 1; @@ -376,7 +376,7 @@ static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb) struct sctp_ep_common *rcvr = chunk->rcvr; int ret; - ret = sk_add_backlog(sk, skb); + ret = sk_add_backlog(sk, skb, sk->sk_rcvbuf); if (!ret) { /* Hold the assoc/ep while hanging on the backlog queue. * This way, we know structures we need will not disappear diff --git a/net/sctp/output.c b/net/sctp/output.c index 817174eb5f4..f1b7d4bb591 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -377,9 +377,7 @@ int sctp_packet_transmit(struct sctp_packet *packet) */ skb_set_owner_w(nskb, sk); - /* The 'obsolete' field of dst is set to 2 when a dst is freed. */ - if (!dst || (dst->obsolete > 1)) { - dst_release(dst); + if (!sctp_transport_dst_check(tp)) { sctp_transport_route(tp, NULL, sctp_sk(sk)); if (asoc && (asoc->param_flags & SPP_PMTUD_ENABLE)) { sctp_assoc_sync_pmtu(asoc); @@ -663,8 +661,8 @@ static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet, */ if (!sctp_sk(asoc->base.sk)->nodelay && sctp_packet_empty(packet) && inflight && sctp_state(asoc, ESTABLISHED)) { - unsigned max = transport->pathmtu - packet->overhead; - unsigned len = chunk->skb->len + q->out_qlen; + unsigned int max = transport->pathmtu - packet->overhead; + unsigned int len = chunk->skb->len + q->out_qlen; /* Check whether this chunk and all the rest of pending * data will fit or delay in hopes of bundling a full diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index cfeb1d4a1ee..a0fa19f5650 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -1147,7 +1147,7 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_sackhdr *sack) __u32 sack_ctsn, ctsn, tsn; __u32 highest_tsn, highest_new_tsn; __u32 sack_a_rwnd; - unsigned outstanding; + unsigned int outstanding; struct sctp_transport *primary = asoc->peer.primary_path; int count_of_newacks = 0; int gap_ack_blocks; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 1ff51c9d18d..c96d1a81cf4 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -524,7 +524,7 @@ static void sctp_do_8_2_transport_strike(struct sctp_association *asoc, /* Worker routine to handle INIT command failure. */ static void sctp_cmd_init_failed(sctp_cmd_seq_t *commands, struct sctp_association *asoc, - unsigned error) + unsigned int error) { struct sctp_ulpevent *event; @@ -550,7 +550,7 @@ static void sctp_cmd_assoc_failed(sctp_cmd_seq_t *commands, sctp_event_t event_type, sctp_subtype_t subtype, struct sctp_chunk *chunk, - unsigned error) + unsigned int error) { struct sctp_ulpevent *event; @@ -1161,9 +1161,8 @@ static int sctp_side_effects(sctp_event_t event_type, sctp_subtype_t subtype, break; case SCTP_DISPOSITION_VIOLATION: - if (net_ratelimit()) - pr_err("protocol violation state %d chunkid %d\n", - state, subtype.chunk); + net_err_ratelimited("protocol violation state %d chunkid %d\n", + state, subtype.chunk); break; case SCTP_DISPOSITION_NOT_IMPL: diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 891f5db8cc3..9fca1035735 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1129,17 +1129,15 @@ sctp_disposition_t sctp_sf_backbeat_8_3(const struct sctp_endpoint *ep, /* This should never happen, but lets log it if so. */ if (unlikely(!link)) { if (from_addr.sa.sa_family == AF_INET6) { - if (net_ratelimit()) - pr_warn("%s association %p could not find address %pI6\n", - __func__, - asoc, - &from_addr.v6.sin6_addr); + net_warn_ratelimited("%s association %p could not find address %pI6\n", + __func__, + asoc, + &from_addr.v6.sin6_addr); } else { - if (net_ratelimit()) - pr_warn("%s association %p could not find address %pI4\n", - __func__, - asoc, - &from_addr.v4.sin_addr.s_addr); + net_warn_ratelimited("%s association %p could not find address %pI4\n", + __func__, + asoc, + &from_addr.v4.sin_addr.s_addr); } return SCTP_DISPOSITION_DISCARD; } @@ -2410,7 +2408,7 @@ static sctp_disposition_t __sctp_sf_do_9_1_abort(const struct sctp_endpoint *ep, sctp_cmd_seq_t *commands) { struct sctp_chunk *chunk = arg; - unsigned len; + unsigned int len; __be16 error = SCTP_ERROR_NO_ERROR; /* See if we have an error cause code in the chunk. */ @@ -2446,7 +2444,7 @@ sctp_disposition_t sctp_sf_cookie_wait_abort(const struct sctp_endpoint *ep, sctp_cmd_seq_t *commands) { struct sctp_chunk *chunk = arg; - unsigned len; + unsigned int len; __be16 error = SCTP_ERROR_NO_ERROR; if (!sctp_vtag_verify_either(chunk, asoc)) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 06b42b7f5a0..b3b8a8d813e 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4133,9 +4133,10 @@ static int sctp_getsockopt_disable_fragments(struct sock *sk, int len, static int sctp_getsockopt_events(struct sock *sk, int len, char __user *optval, int __user *optlen) { - if (len < sizeof(struct sctp_event_subscribe)) + if (len <= 0) return -EINVAL; - len = sizeof(struct sctp_event_subscribe); + if (len > sizeof(struct sctp_event_subscribe)) + len = sizeof(struct sctp_event_subscribe); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &sctp_sk(sk)->subscribe, len)) @@ -5839,10 +5840,8 @@ SCTP_STATIC int sctp_listen_start(struct sock *sk, int backlog) if (!sctp_sk(sk)->hmac && sctp_hmac_alg) { tfm = crypto_alloc_hash(sctp_hmac_alg, 0, CRYPTO_ALG_ASYNC); if (IS_ERR(tfm)) { - if (net_ratelimit()) { - pr_info("failed to load transform for %s: %ld\n", - sctp_hmac_alg, PTR_ERR(tfm)); - } + net_info_ratelimited("failed to load transform for %s: %ld\n", + sctp_hmac_alg, PTR_ERR(tfm)); return -ENOSYS; } sctp_sk(sk)->hmac = tfm; diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 60ffbd067ff..e5fe639c89e 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -275,22 +275,16 @@ static ctl_table sctp_table[] = { { /* sentinel */ } }; -static struct ctl_path sctp_path[] = { - { .procname = "net", }, - { .procname = "sctp", }, - { } -}; - static struct ctl_table_header * sctp_sysctl_header; /* Sysctl registration. */ void sctp_sysctl_register(void) { - sctp_sysctl_header = register_sysctl_paths(sctp_path, sctp_table); + sctp_sysctl_header = register_net_sysctl(&init_net, "net/sctp", sctp_table); } /* Sysctl deregistration. */ void sctp_sysctl_unregister(void) { - unregister_sysctl_table(sctp_sysctl_header); + unregister_net_sysctl_table(sctp_sysctl_header); } diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 3889330b7b0..b026ba0c699 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -226,23 +226,6 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT; } -/* this is a complete rip-off from __sk_dst_check - * the cookie is always 0 since this is how it's used in the - * pmtu code - */ -static struct dst_entry *sctp_transport_dst_check(struct sctp_transport *t) -{ - struct dst_entry *dst = t->dst; - - if (dst && dst->obsolete && dst->ops->check(dst, 0) == NULL) { - dst_release(t->dst); - t->dst = NULL; - return NULL; - } - - return dst; -} - void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) { struct dst_entry *dst; diff --git a/net/socket.c b/net/socket.c index 484cc6953fc..6e0ccc09b31 100644 --- a/net/socket.c +++ b/net/socket.c @@ -479,7 +479,7 @@ static struct socket *sock_alloc(void) inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); - percpu_add(sockets_in_use, 1); + this_cpu_add(sockets_in_use, 1); return sock; } @@ -522,7 +522,7 @@ void sock_release(struct socket *sock) if (rcu_dereference_protected(sock->wq, 1)->fasync_list) printk(KERN_ERR "sock_release: fasync list not empty!\n"); - percpu_sub(sockets_in_use, 1); + this_cpu_sub(sockets_in_use, 1); if (!sock->file) { iput(SOCK_INODE(sock)); return; @@ -811,9 +811,9 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, sock = file->private_data; - flags = !(file->f_flags & O_NONBLOCK) ? 0 : MSG_DONTWAIT; - if (more) - flags |= MSG_MORE; + flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0; + /* more is a combination of MSG_MORE and MSG_SENDPAGE_NOTLAST */ + flags |= more; return kernel_sendpage(sock, page, offset, size, flags); } @@ -1234,8 +1234,7 @@ int __sock_create(struct net *net, int family, int type, int protocol, */ sock = sock_alloc(); if (!sock) { - if (net_ratelimit()) - printk(KERN_WARNING "socket: no more sockets\n"); + net_warn_ratelimited("socket: no more sockets\n"); return -ENFILE; /* Not exactly a match, but its the closest posix thing */ } @@ -1479,7 +1478,7 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog) sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock) { somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn; - if ((unsigned)backlog > somaxconn) + if ((unsigned int)backlog > somaxconn) backlog = somaxconn; err = security_socket_listen(sock, backlog); @@ -1691,7 +1690,7 @@ SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr, */ SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len, - unsigned, flags, struct sockaddr __user *, addr, + unsigned int, flags, struct sockaddr __user *, addr, int, addr_len) { struct socket *sock; @@ -1738,7 +1737,7 @@ out: */ SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len, - unsigned, flags) + unsigned int, flags) { return sys_sendto(fd, buff, len, flags, NULL, 0); } @@ -1750,7 +1749,7 @@ SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len, */ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, - unsigned, flags, struct sockaddr __user *, addr, + unsigned int, flags, struct sockaddr __user *, addr, int __user *, addr_len) { struct socket *sock; @@ -1795,7 +1794,7 @@ out: */ asmlinkage long sys_recv(int fd, void __user *ubuf, size_t size, - unsigned flags) + unsigned int flags) { return sys_recvfrom(fd, ubuf, size, flags, NULL, NULL); } @@ -1897,7 +1896,7 @@ struct used_address { }; static int __sys_sendmsg(struct socket *sock, struct msghdr __user *msg, - struct msghdr *msg_sys, unsigned flags, + struct msghdr *msg_sys, unsigned int flags, struct used_address *used_address) { struct compat_msghdr __user *msg_compat = @@ -1908,7 +1907,7 @@ static int __sys_sendmsg(struct socket *sock, struct msghdr __user *msg, __attribute__ ((aligned(sizeof(__kernel_size_t)))); /* 20 is size of ipv6_pktinfo */ unsigned char *ctl_buf = ctl; - int err, ctl_len, iov_size, total_len; + int err, ctl_len, total_len; err = -EFAULT; if (MSG_CMSG_COMPAT & flags) { @@ -1917,16 +1916,13 @@ static int __sys_sendmsg(struct socket *sock, struct msghdr __user *msg, } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr))) return -EFAULT; - /* do not move before msg_sys is valid */ - err = -EMSGSIZE; - if (msg_sys->msg_iovlen > UIO_MAXIOV) - goto out; - - /* Check whether to allocate the iovec area */ - err = -ENOMEM; - iov_size = msg_sys->msg_iovlen * sizeof(struct iovec); if (msg_sys->msg_iovlen > UIO_FASTIOV) { - iov = sock_kmalloc(sock->sk, iov_size, GFP_KERNEL); + err = -EMSGSIZE; + if (msg_sys->msg_iovlen > UIO_MAXIOV) + goto out; + err = -ENOMEM; + iov = kmalloc(msg_sys->msg_iovlen * sizeof(struct iovec), + GFP_KERNEL); if (!iov) goto out; } @@ -2005,7 +2001,7 @@ out_freectl: sock_kfree_s(sock->sk, ctl_buf, ctl_len); out_freeiov: if (iov != iovstack) - sock_kfree_s(sock->sk, iov, iov_size); + kfree(iov); out: return err; } @@ -2014,7 +2010,7 @@ out: * BSD sendmsg interface */ -SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned, flags) +SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned int, flags) { int fput_needed, err; struct msghdr msg_sys; @@ -2096,14 +2092,14 @@ SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg, } static int __sys_recvmsg(struct socket *sock, struct msghdr __user *msg, - struct msghdr *msg_sys, unsigned flags, int nosec) + struct msghdr *msg_sys, unsigned int flags, int nosec) { struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *)msg; struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; unsigned long cmsg_ptr; - int err, iov_size, total_len, len; + int err, total_len, len; /* kernel mode address */ struct sockaddr_storage addr; @@ -2118,15 +2114,13 @@ static int __sys_recvmsg(struct socket *sock, struct msghdr __user *msg, } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr))) return -EFAULT; - err = -EMSGSIZE; - if (msg_sys->msg_iovlen > UIO_MAXIOV) - goto out; - - /* Check whether to allocate the iovec area */ - err = -ENOMEM; - iov_size = msg_sys->msg_iovlen * sizeof(struct iovec); if (msg_sys->msg_iovlen > UIO_FASTIOV) { - iov = sock_kmalloc(sock->sk, iov_size, GFP_KERNEL); + err = -EMSGSIZE; + if (msg_sys->msg_iovlen > UIO_MAXIOV) + goto out; + err = -ENOMEM; + iov = kmalloc(msg_sys->msg_iovlen * sizeof(struct iovec), + GFP_KERNEL); if (!iov) goto out; } @@ -2180,7 +2174,7 @@ static int __sys_recvmsg(struct socket *sock, struct msghdr __user *msg, out_freeiov: if (iov != iovstack) - sock_kfree_s(sock->sk, iov, iov_size); + kfree(iov); out: return err; } @@ -2524,6 +2518,12 @@ EXPORT_SYMBOL(sock_unregister); static int __init sock_init(void) { int err; + /* + * Initialize the network sysctl infrastructure. + */ + err = net_sysctl_init(); + if (err) + goto out; /* * Initialize sock SLAB cache. @@ -3223,7 +3223,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, return -ENOIOCTLCMD; } -static long compat_sock_ioctl(struct file *file, unsigned cmd, +static long compat_sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct socket *sock = file->private_data; diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 8eff8c32d1b..d3611f11a8d 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -624,7 +624,7 @@ gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx, ctx->seq_send = ctx->seq_send64; if (ctx->seq_send64 != ctx->seq_send) { dprintk("%s: seq_send64 %lx, seq_send %x overflow?\n", __func__, - (long unsigned)ctx->seq_send64, ctx->seq_send); + (unsigned long)ctx->seq_send64, ctx->seq_send); p = ERR_PTR(-EINVAL); goto out_err; } diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index ca8cad8251c..782bfe1b646 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -242,12 +242,13 @@ EXPORT_SYMBOL_GPL(gss_mech_get_by_pseudoflavor); int gss_mech_list_pseudoflavors(rpc_authflavor_t *array_ptr) { struct gss_api_mech *pos = NULL; - int i = 0; + int j, i = 0; spin_lock(®istered_mechs_lock); list_for_each_entry(pos, ®istered_mechs, gm_list) { - array_ptr[i] = pos->gm_pfs->pseudoflavor; - i++; + for (j=0; j < pos->gm_pf_num; j++) { + array_ptr[i++] = pos->gm_pfs[j].pseudoflavor; + } } spin_unlock(®istered_mechs_lock); return i; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index de0b0f39d9d..47ad2666fdf 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1273,7 +1273,7 @@ static void *c_start(struct seq_file *m, loff_t *pos) __acquires(cd->hash_lock) { loff_t n = *pos; - unsigned hash, entry; + unsigned int hash, entry; struct cache_head *ch; struct cache_detail *cd = ((struct handle*)m->private)->cd; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 67972462a54..7fee13b331d 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -127,9 +127,7 @@ static struct dentry *rpc_setup_pipedir_sb(struct super_block *sb, { static uint32_t clntid; char name[15]; - struct qstr q = { - .name = name, - }; + struct qstr q = { .name = name }; struct dentry *dir, *dentry; int error; @@ -176,16 +174,22 @@ rpc_setup_pipedir(struct rpc_clnt *clnt, const char *dir_name) return 0; } -static int __rpc_pipefs_event(struct rpc_clnt *clnt, unsigned long event, - struct super_block *sb) +static inline int rpc_clnt_skip_event(struct rpc_clnt *clnt, unsigned long event) +{ + if (((event == RPC_PIPEFS_MOUNT) && clnt->cl_dentry) || + ((event == RPC_PIPEFS_UMOUNT) && !clnt->cl_dentry)) + return 1; + return 0; +} + +static int __rpc_clnt_handle_event(struct rpc_clnt *clnt, unsigned long event, + struct super_block *sb) { struct dentry *dentry; int err = 0; switch (event) { case RPC_PIPEFS_MOUNT: - if (clnt->cl_program->pipe_dir_name == NULL) - break; dentry = rpc_setup_pipedir_sb(sb, clnt, clnt->cl_program->pipe_dir_name); BUG_ON(dentry == NULL); @@ -208,6 +212,20 @@ static int __rpc_pipefs_event(struct rpc_clnt *clnt, unsigned long event, return err; } +static int __rpc_pipefs_event(struct rpc_clnt *clnt, unsigned long event, + struct super_block *sb) +{ + int error = 0; + + for (;; clnt = clnt->cl_parent) { + if (!rpc_clnt_skip_event(clnt, event)) + error = __rpc_clnt_handle_event(clnt, event, sb); + if (error || clnt == clnt->cl_parent) + break; + } + return error; +} + static struct rpc_clnt *rpc_get_client_for_event(struct net *net, int event) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); @@ -215,10 +233,12 @@ static struct rpc_clnt *rpc_get_client_for_event(struct net *net, int event) spin_lock(&sn->rpc_client_lock); list_for_each_entry(clnt, &sn->all_clients, cl_clients) { - if (((event == RPC_PIPEFS_MOUNT) && clnt->cl_dentry) || - ((event == RPC_PIPEFS_UMOUNT) && !clnt->cl_dentry)) + if (clnt->cl_program->pipe_dir_name == NULL) + break; + if (rpc_clnt_skip_event(clnt, event)) + continue; + if (atomic_inc_not_zero(&clnt->cl_count) == 0) continue; - atomic_inc(&clnt->cl_count); spin_unlock(&sn->rpc_client_lock); return clnt; } @@ -257,6 +277,14 @@ void rpc_clients_notifier_unregister(void) return rpc_pipefs_notifier_unregister(&rpc_clients_block); } +static void rpc_clnt_set_nodename(struct rpc_clnt *clnt, const char *nodename) +{ + clnt->cl_nodelen = strlen(nodename); + if (clnt->cl_nodelen > UNX_MAXNODENAME) + clnt->cl_nodelen = UNX_MAXNODENAME; + memcpy(clnt->cl_nodename, nodename, clnt->cl_nodelen); +} + static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, struct rpc_xprt *xprt) { const struct rpc_program *program = args->program; @@ -337,10 +365,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru } /* save the nodename */ - clnt->cl_nodelen = strlen(init_utsname()->nodename); - if (clnt->cl_nodelen > UNX_MAXNODENAME) - clnt->cl_nodelen = UNX_MAXNODENAME; - memcpy(clnt->cl_nodename, init_utsname()->nodename, clnt->cl_nodelen); + rpc_clnt_set_nodename(clnt, utsname()->nodename); rpc_register_client(clnt); return clnt; @@ -499,6 +524,7 @@ rpc_clone_client(struct rpc_clnt *clnt) err = rpc_setup_pipedir(new, clnt->cl_program->pipe_dir_name); if (err != 0) goto out_no_path; + rpc_clnt_set_nodename(new, utsname()->nodename); if (new->cl_auth) atomic_inc(&new->cl_auth->au_count); atomic_inc(&clnt->cl_count); diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 0af37fc4681..fd2423991c2 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -1059,12 +1059,9 @@ static const struct rpc_filelist files[] = { struct dentry *rpc_d_lookup_sb(const struct super_block *sb, const unsigned char *dir_name) { - struct qstr dir = { - .name = dir_name, - .len = strlen(dir_name), - .hash = full_name_hash(dir_name, strlen(dir_name)), - }; + struct qstr dir = QSTR_INIT(dir_name, strlen(dir_name)); + dir.hash = full_name_hash(dir.name, dir.len); return d_lookup(sb->s_root, &dir); } EXPORT_SYMBOL_GPL(rpc_d_lookup_sb); @@ -1126,19 +1123,20 @@ rpc_fill_super(struct super_block *sb, void *data, int silent) return -ENOMEM; dprintk("RPC: sending pipefs MOUNT notification for net %p%s\n", net, NET_NAME(net)); + sn->pipefs_sb = sb; err = blocking_notifier_call_chain(&rpc_pipefs_notifier_list, RPC_PIPEFS_MOUNT, sb); if (err) goto err_depopulate; sb->s_fs_info = get_net(net); - sn->pipefs_sb = sb; return 0; err_depopulate: blocking_notifier_call_chain(&rpc_pipefs_notifier_list, RPC_PIPEFS_UMOUNT, sb); + sn->pipefs_sb = NULL; __rpc_depopulate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF); return err; } diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index 8adfc88e793..3d6498af9ad 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -75,20 +75,21 @@ static struct pernet_operations sunrpc_net_ops = { static int __init init_sunrpc(void) { - int err = register_rpc_pipefs(); + int err = rpc_init_mempool(); if (err) goto out; - err = rpc_init_mempool(); - if (err) - goto out2; err = rpcauth_init_module(); if (err) - goto out3; + goto out2; cache_initialize(); err = register_pernet_subsys(&sunrpc_net_ops); if (err) + goto out3; + + err = register_rpc_pipefs(); + if (err) goto out4; #ifdef RPC_DEBUG rpc_register_sysctl(); @@ -98,11 +99,11 @@ init_sunrpc(void) return 0; out4: - rpcauth_remove_module(); + unregister_pernet_subsys(&sunrpc_net_ops); out3: - rpc_destroy_mempool(); + rpcauth_remove_module(); out2: - unregister_rpc_pipefs(); + rpc_destroy_mempool(); out: return err; } diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 4153846984a..017c0117d15 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1041,23 +1041,21 @@ static void svc_unregister(const struct svc_serv *serv, struct net *net) * Printk the given error with the address of the client that caused it. */ static __printf(2, 3) -int svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) +void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) { + struct va_format vaf; va_list args; - int r; char buf[RPC_MAX_ADDRBUFLEN]; - if (!net_ratelimit()) - return 0; + va_start(args, fmt); - printk(KERN_WARNING "svc: %s: ", - svc_print_addr(rqstp, buf, sizeof(buf))); + vaf.fmt = fmt; + vaf.va = &args; - va_start(args, fmt); - r = vprintk(fmt, args); - va_end(args); + net_warn_ratelimited("svc: %s: %pV", + svc_print_addr(rqstp, buf, sizeof(buf)), &vaf); - return r; + va_end(args); } /* diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 4bda09d7e1a..b98ee351491 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -544,14 +544,11 @@ static void svc_check_conn_limits(struct svc_serv *serv) struct svc_xprt *xprt = NULL; spin_lock_bh(&serv->sv_lock); if (!list_empty(&serv->sv_tempsocks)) { - if (net_ratelimit()) { - /* Try to help the admin */ - printk(KERN_NOTICE "%s: too many open " - "connections, consider increasing %s\n", - serv->sv_name, serv->sv_maxconn ? - "the max number of connections." : - "the number of threads."); - } + /* Try to help the admin */ + net_notice_ratelimited("%s: too many open connections, consider increasing the %s\n", + serv->sv_name, serv->sv_maxconn ? + "max number of connections" : + "number of threads"); /* * Always select the oldest connection. It's not fair, * but so is life diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 824d32fb312..a6de09de5d2 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -617,11 +617,8 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) rqstp->rq_prot = IPPROTO_UDP; if (!svc_udp_get_dest_address(rqstp, cmh)) { - if (net_ratelimit()) - printk(KERN_WARNING - "svc: received unknown control message %d/%d; " - "dropping RPC reply datagram\n", - cmh->cmsg_level, cmh->cmsg_type); + net_warn_ratelimited("svc: received unknown control message %d/%d; dropping RPC reply datagram\n", + cmh->cmsg_level, cmh->cmsg_type); skb_free_datagram_locked(svsk->sk_sk, skb); return 0; } @@ -871,18 +868,17 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) if (err == -ENOMEM) printk(KERN_WARNING "%s: no more sockets!\n", serv->sv_name); - else if (err != -EAGAIN && net_ratelimit()) - printk(KERN_WARNING "%s: accept failed (err %d)!\n", - serv->sv_name, -err); + else if (err != -EAGAIN) + net_warn_ratelimited("%s: accept failed (err %d)!\n", + serv->sv_name, -err); return NULL; } set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags); err = kernel_getpeername(newsock, sin, &slen); if (err < 0) { - if (net_ratelimit()) - printk(KERN_WARNING "%s: peername failed (err %d)!\n", - serv->sv_name, -err); + net_warn_ratelimited("%s: peername failed (err %d)!\n", + serv->sv_name, -err); goto failed; /* aborted connection or whatever */ } @@ -1012,19 +1008,15 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp) * bit set in the fragment length header. * But apparently no known nfs clients send fragmented * records. */ - if (net_ratelimit()) - printk(KERN_NOTICE "RPC: multiple fragments " - "per record not supported\n"); + net_notice_ratelimited("RPC: multiple fragments per record not supported\n"); goto err_delete; } svsk->sk_reclen &= RPC_FRAGMENT_SIZE_MASK; dprintk("svc: TCP record, %d bytes\n", svsk->sk_reclen); if (svsk->sk_reclen > serv->sv_max_mesg) { - if (net_ratelimit()) - printk(KERN_NOTICE "RPC: " - "fragment too large: 0x%08lx\n", - (unsigned long)svsk->sk_reclen); + net_notice_ratelimited("RPC: fragment too large: 0x%08lx\n", + (unsigned long)svsk->sk_reclen); goto err_delete; } } @@ -1556,7 +1548,7 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv, (char *)&val, sizeof(val)); if (type == SOCK_STREAM) - sock->sk->sk_reuse = 1; /* allow address reuse */ + sock->sk->sk_reuse = SK_CAN_REUSE; /* allow address reuse */ error = kernel_bind(sock, sin, len); if (error < 0) goto bummer; diff --git a/net/sunrpc/timer.c b/net/sunrpc/timer.c index dd824341c34..08881d0c967 100644 --- a/net/sunrpc/timer.c +++ b/net/sunrpc/timer.c @@ -34,7 +34,7 @@ void rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo) { unsigned long init = 0; - unsigned i; + unsigned int i; rt->timeo = timeo; @@ -57,7 +57,7 @@ EXPORT_SYMBOL_GPL(rpc_init_rtt); * NB: When computing the smoothed RTT and standard deviation, * be careful not to produce negative intermediate results. */ -void rpc_update_rtt(struct rpc_rtt *rt, unsigned timer, long m) +void rpc_update_rtt(struct rpc_rtt *rt, unsigned int timer, long m) { long *srtt, *sdrtt; @@ -106,7 +106,7 @@ EXPORT_SYMBOL_GPL(rpc_update_rtt); * read, write, commit - A+4D * other - timeo */ -unsigned long rpc_calc_rto(struct rpc_rtt *rt, unsigned timer) +unsigned long rpc_calc_rto(struct rpc_rtt *rt, unsigned int timer) { unsigned long res; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index b97a3dd9a60..fddcccfcdf7 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -1204,7 +1204,7 @@ xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data) { int i, ret = 0; - unsigned page_len, thislen, page_offset; + unsigned int page_len, thislen, page_offset; struct scatterlist sg[1]; sg_init_table(sg, 1); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 0cbcd1ab49a..6fe2dcead15 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -783,7 +783,7 @@ static void xprt_update_rtt(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_rtt *rtt = task->tk_client->cl_rtt; - unsigned timer = task->tk_msg.rpc_proc->p_timer; + unsigned int timer = task->tk_msg.rpc_proc->p_timer; long m = usecs_to_jiffies(ktime_to_us(req->rq_rtt)); if (timer) { diff --git a/net/sysctl_net.c b/net/sysctl_net.c index c3e65aebecc..e3a6e37cd1c 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -26,10 +26,6 @@ #include <linux/if_ether.h> #endif -#ifdef CONFIG_TR -#include <linux/if_tr.h> -#endif - static struct ctl_table_set * net_ctl_header_lookup(struct ctl_table_root *root, struct nsproxy *namespaces) { @@ -59,19 +55,6 @@ static struct ctl_table_root net_sysctl_root = { .permissions = net_ctl_permissions, }; -static int net_ctl_ro_header_perms(struct ctl_table_root *root, - struct nsproxy *namespaces, struct ctl_table *table) -{ - if (net_eq(namespaces->net_ns, &init_net)) - return table->mode; - else - return table->mode & ~0222; -} - -static struct ctl_table_root net_sysctl_ro_root = { - .permissions = net_ctl_ro_header_perms, -}; - static int __net_init sysctl_net_init(struct net *net) { setup_sysctl_set(&net->sysctls, &net_sysctl_root, is_seen); @@ -88,34 +71,32 @@ static struct pernet_operations sysctl_pernet_ops = { .exit = sysctl_net_exit, }; -static __init int net_sysctl_init(void) +static struct ctl_table_header *net_header; +__init int net_sysctl_init(void) { - int ret; + static struct ctl_table empty[1]; + int ret = -ENOMEM; + /* Avoid limitations in the sysctl implementation by + * registering "/proc/sys/net" as an empty directory not in a + * network namespace. + */ + net_header = register_sysctl("net", empty); + if (!net_header) + goto out; ret = register_pernet_subsys(&sysctl_pernet_ops); if (ret) goto out; - setup_sysctl_set(&net_sysctl_ro_root.default_set, &net_sysctl_ro_root, NULL); - register_sysctl_root(&net_sysctl_ro_root); register_sysctl_root(&net_sysctl_root); out: return ret; } -subsys_initcall(net_sysctl_init); - -struct ctl_table_header *register_net_sysctl_table(struct net *net, - const struct ctl_path *path, struct ctl_table *table) -{ - return __register_sysctl_paths(&net->sysctls, path, table); -} -EXPORT_SYMBOL_GPL(register_net_sysctl_table); -struct ctl_table_header *register_net_sysctl_rotable(const - struct ctl_path *path, struct ctl_table *table) +struct ctl_table_header *register_net_sysctl(struct net *net, + const char *path, struct ctl_table *table) { - return __register_sysctl_paths(&net_sysctl_ro_root.default_set, - path, table); + return __register_sysctl_table(&net->sysctls, path, table); } -EXPORT_SYMBOL_GPL(register_net_sysctl_rotable); +EXPORT_SYMBOL_GPL(register_net_sysctl); void unregister_net_sysctl_table(struct ctl_table_header *header) { diff --git a/net/tipc/Makefile b/net/tipc/Makefile index 521d24d04ab..6cd55d671d3 100644 --- a/net/tipc/Makefile +++ b/net/tipc/Makefile @@ -9,5 +9,3 @@ tipc-y += addr.o bcast.o bearer.o config.o \ name_distr.o subscr.o name_table.o net.o \ netlink.o node.o node_subscr.o port.o ref.o \ socket.o log.o eth_media.o - -# End of file diff --git a/net/tipc/addr.c b/net/tipc/addr.c index a6fdab33877..357b74b26f9 100644 --- a/net/tipc/addr.c +++ b/net/tipc/addr.c @@ -45,7 +45,6 @@ * * Returns 1 if domain address is valid, otherwise 0 */ - int tipc_addr_domain_valid(u32 addr) { u32 n = tipc_node(addr); @@ -66,7 +65,6 @@ int tipc_addr_domain_valid(u32 addr) * * Returns 1 if address can be used, otherwise 0 */ - int tipc_addr_node_valid(u32 addr) { return tipc_addr_domain_valid(addr) && tipc_node(addr); @@ -86,7 +84,6 @@ int tipc_in_scope(u32 domain, u32 addr) /** * tipc_addr_scope - convert message lookup domain to a 2-bit scope value */ - int tipc_addr_scope(u32 domain) { if (likely(!domain)) diff --git a/net/tipc/addr.h b/net/tipc/addr.h index e4f35afe320..60b00ab93d7 100644 --- a/net/tipc/addr.h +++ b/net/tipc/addr.h @@ -50,18 +50,33 @@ static inline u32 tipc_cluster_mask(u32 addr) return addr & TIPC_CLUSTER_MASK; } -static inline int in_own_cluster(u32 addr) +static inline int in_own_cluster_exact(u32 addr) { return !((addr ^ tipc_own_addr) >> 12); } /** + * in_own_node - test for node inclusion; <0.0.0> always matches + */ +static inline int in_own_node(u32 addr) +{ + return (addr == tipc_own_addr) || !addr; +} + +/** + * in_own_cluster - test for cluster inclusion; <0.0.0> always matches + */ +static inline int in_own_cluster(u32 addr) +{ + return in_own_cluster_exact(addr) || !addr; +} + +/** * addr_domain - convert 2-bit scope value to equivalent message lookup domain * * Needed when address of a named message must be looked up a second time * after a network hop. */ - static inline u32 addr_domain(u32 sc) { if (likely(sc == TIPC_NODE_SCOPE)) diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index e00441a2092..2625f5ebe3e 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -73,7 +73,6 @@ struct tipc_bcbearer_pair { * large local variables within multicast routines. Concurrent access is * prevented through use of the spinlock "bc_lock". */ - struct tipc_bcbearer { struct tipc_bearer bearer; struct tipc_media media; @@ -92,7 +91,6 @@ struct tipc_bcbearer { * * Handles sequence numbering, fragmentation, bundling, etc. */ - struct tipc_bclink { struct tipc_link link; struct tipc_node node; @@ -169,7 +167,6 @@ static void bclink_update_last_sent(struct tipc_node *node, u32 seqno) * * Called with bc_lock locked */ - struct tipc_node *tipc_bclink_retransmit_to(void) { return bclink->retransmit_to; @@ -182,7 +179,6 @@ struct tipc_node *tipc_bclink_retransmit_to(void) * * Called with bc_lock locked */ - static void bclink_retransmit_pkt(u32 after, u32 to) { struct sk_buff *buf; @@ -200,7 +196,6 @@ static void bclink_retransmit_pkt(u32 after, u32 to) * * Node is locked, bc_lock unlocked. */ - void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked) { struct sk_buff *crs; @@ -280,7 +275,6 @@ exit: * * tipc_net_lock and node lock set */ - void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent) { struct sk_buff *buf; @@ -344,7 +338,6 @@ void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent) * * Only tipc_net_lock set. */ - static void bclink_peek_nack(struct tipc_msg *msg) { struct tipc_node *n_ptr = tipc_node_find(msg_destnode(msg)); @@ -365,7 +358,6 @@ static void bclink_peek_nack(struct tipc_msg *msg) /* * tipc_bclink_send_msg - broadcast a packet to all nodes in cluster */ - int tipc_bclink_send_msg(struct sk_buff *buf) { int res; @@ -394,7 +386,6 @@ exit: * * Called with both sending node's lock and bc_lock taken. */ - static void bclink_accept_pkt(struct tipc_node *node, u32 seqno) { bclink_update_last_sent(node, seqno); @@ -420,7 +411,6 @@ static void bclink_accept_pkt(struct tipc_node *node, u32 seqno) * * tipc_net_lock is read_locked, no other locks set */ - void tipc_bclink_recv_pkt(struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); @@ -588,7 +578,6 @@ u32 tipc_bclink_acks_missing(struct tipc_node *n_ptr) * Returns 0 (packet sent successfully) under all circumstances, * since the broadcast link's pseudo-bearer never blocks */ - static int tipc_bcbearer_send(struct sk_buff *buf, struct tipc_bearer *unused1, struct tipc_media_addr *unused2) @@ -601,7 +590,6 @@ static int tipc_bcbearer_send(struct sk_buff *buf, * preparation is skipped for broadcast link protocol messages * since they are sent in an unreliable manner and don't need it */ - if (likely(!msg_non_seq(buf_msg(buf)))) { struct tipc_msg *msg; @@ -618,7 +606,6 @@ static int tipc_bcbearer_send(struct sk_buff *buf, } /* Send buffer over bearers until all targets reached */ - bcbearer->remains = bclink->bcast_nodes; for (bp_index = 0; bp_index < MAX_BEARERS; bp_index++) { @@ -660,7 +647,6 @@ static int tipc_bcbearer_send(struct sk_buff *buf, /** * tipc_bcbearer_sort - create sets of bearer pairs used by broadcast bearer */ - void tipc_bcbearer_sort(void) { struct tipc_bcbearer_pair *bp_temp = bcbearer->bpairs_temp; @@ -671,7 +657,6 @@ void tipc_bcbearer_sort(void) spin_lock_bh(&bc_lock); /* Group bearers by priority (can assume max of two per priority) */ - memset(bp_temp, 0, sizeof(bcbearer->bpairs_temp)); for (b_index = 0; b_index < MAX_BEARERS; b_index++) { @@ -687,7 +672,6 @@ void tipc_bcbearer_sort(void) } /* Create array of bearer pairs for broadcasting */ - bp_curr = bcbearer->bpairs; memset(bcbearer->bpairs, 0, sizeof(bcbearer->bpairs)); @@ -817,7 +801,6 @@ void tipc_bclink_stop(void) /** * tipc_nmap_add - add a node to a node map */ - void tipc_nmap_add(struct tipc_node_map *nm_ptr, u32 node) { int n = tipc_node(node); @@ -833,7 +816,6 @@ void tipc_nmap_add(struct tipc_node_map *nm_ptr, u32 node) /** * tipc_nmap_remove - remove a node from a node map */ - void tipc_nmap_remove(struct tipc_node_map *nm_ptr, u32 node) { int n = tipc_node(node); @@ -852,7 +834,6 @@ void tipc_nmap_remove(struct tipc_node_map *nm_ptr, u32 node) * @nm_b: input node map B * @nm_diff: output node map A-B (i.e. nodes of A that are not in B) */ - static void tipc_nmap_diff(struct tipc_node_map *nm_a, struct tipc_node_map *nm_b, struct tipc_node_map *nm_diff) @@ -878,7 +859,6 @@ static void tipc_nmap_diff(struct tipc_node_map *nm_a, /** * tipc_port_list_add - add a port to a port list, ensuring no duplicates */ - void tipc_port_list_add(struct tipc_port_list *pl_ptr, u32 port) { struct tipc_port_list *item = pl_ptr; @@ -912,7 +892,6 @@ void tipc_port_list_add(struct tipc_port_list *pl_ptr, u32 port) * tipc_port_list_free - free dynamically created entries in port_list chain * */ - void tipc_port_list_free(struct tipc_port_list *pl_ptr) { struct tipc_port_list *item; @@ -923,4 +902,3 @@ void tipc_port_list_free(struct tipc_port_list *pl_ptr) kfree(item); } } - diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index 5571394098f..a93306557e0 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -45,7 +45,6 @@ * @count: # of nodes in set * @map: bitmap of node identifiers that are in the set */ - struct tipc_node_map { u32 count; u32 map[MAX_NODES / WSIZE]; @@ -59,7 +58,6 @@ struct tipc_node_map { * @next: pointer to next entry in list * @ports: array of port references */ - struct tipc_port_list { int count; struct tipc_port_list *next; @@ -77,7 +75,6 @@ void tipc_nmap_remove(struct tipc_node_map *nm_ptr, u32 node); /** * tipc_nmap_equal - test for equality of node maps */ - static inline int tipc_nmap_equal(struct tipc_node_map *nm_a, struct tipc_node_map *nm_b) { return !memcmp(nm_a, nm_b, sizeof(*nm_a)); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 5dfd89c4042..a297e3a2e3e 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -53,7 +53,6 @@ static void bearer_disable(struct tipc_bearer *b_ptr); * * Returns 1 if media name is valid, otherwise 0. */ - static int media_name_valid(const char *name) { u32 len; @@ -67,7 +66,6 @@ static int media_name_valid(const char *name) /** * tipc_media_find - locates specified media object by name */ - struct tipc_media *tipc_media_find(const char *name) { u32 i; @@ -82,7 +80,6 @@ struct tipc_media *tipc_media_find(const char *name) /** * media_find_id - locates specified media object by type identifier */ - static struct tipc_media *media_find_id(u8 type) { u32 i; @@ -99,7 +96,6 @@ static struct tipc_media *media_find_id(u8 type) * * Bearers for this media type must be activated separately at a later stage. */ - int tipc_register_media(struct tipc_media *m_ptr) { int res = -EINVAL; @@ -134,7 +130,6 @@ exit: /** * tipc_media_addr_printf - record media address in print buffer */ - void tipc_media_addr_printf(struct print_buf *pb, struct tipc_media_addr *a) { char addr_str[MAX_ADDR_STR]; @@ -156,7 +151,6 @@ void tipc_media_addr_printf(struct print_buf *pb, struct tipc_media_addr *a) /** * tipc_media_get_names - record names of registered media in buffer */ - struct sk_buff *tipc_media_get_names(void) { struct sk_buff *buf; @@ -183,7 +177,6 @@ struct sk_buff *tipc_media_get_names(void) * * Returns 1 if bearer name is valid, otherwise 0. */ - static int bearer_name_validate(const char *name, struct tipc_bearer_names *name_parts) { @@ -194,7 +187,6 @@ static int bearer_name_validate(const char *name, u32 if_len; /* copy bearer name & ensure length is OK */ - name_copy[TIPC_MAX_BEARER_NAME - 1] = 0; /* need above in case non-Posix strncpy() doesn't pad with nulls */ strncpy(name_copy, name, TIPC_MAX_BEARER_NAME); @@ -202,7 +194,6 @@ static int bearer_name_validate(const char *name, return 0; /* ensure all component parts of bearer name are present */ - media_name = name_copy; if_name = strchr(media_name, ':'); if (if_name == NULL) @@ -212,7 +203,6 @@ static int bearer_name_validate(const char *name, if_len = strlen(if_name) + 1; /* validate component parts of bearer name */ - if ((media_len <= 1) || (media_len > TIPC_MAX_MEDIA_NAME) || (if_len <= 1) || (if_len > TIPC_MAX_IF_NAME) || (strspn(media_name, tipc_alphabet) != (media_len - 1)) || @@ -220,7 +210,6 @@ static int bearer_name_validate(const char *name, return 0; /* return bearer name components, if necessary */ - if (name_parts) { strcpy(name_parts->media_name, media_name); strcpy(name_parts->if_name, if_name); @@ -231,7 +220,6 @@ static int bearer_name_validate(const char *name, /** * tipc_bearer_find - locates bearer object with matching bearer name */ - struct tipc_bearer *tipc_bearer_find(const char *name) { struct tipc_bearer *b_ptr; @@ -247,7 +235,6 @@ struct tipc_bearer *tipc_bearer_find(const char *name) /** * tipc_bearer_find_interface - locates bearer object with matching interface name */ - struct tipc_bearer *tipc_bearer_find_interface(const char *if_name) { struct tipc_bearer *b_ptr; @@ -267,7 +254,6 @@ struct tipc_bearer *tipc_bearer_find_interface(const char *if_name) /** * tipc_bearer_get_names - record names of bearers in buffer */ - struct sk_buff *tipc_bearer_get_names(void) { struct sk_buff *buf; @@ -363,7 +349,6 @@ void tipc_continue(struct tipc_bearer *b_ptr) * the bearer is congested. 'tipc_net_lock' is in read_lock here * bearer.lock is busy */ - static void tipc_bearer_schedule_unlocked(struct tipc_bearer *b_ptr, struct tipc_link *l_ptr) { @@ -377,7 +362,6 @@ static void tipc_bearer_schedule_unlocked(struct tipc_bearer *b_ptr, * the bearer is congested. 'tipc_net_lock' is in read_lock here, * bearer.lock is free */ - void tipc_bearer_schedule(struct tipc_bearer *b_ptr, struct tipc_link *l_ptr) { spin_lock_bh(&b_ptr->lock); @@ -410,7 +394,6 @@ int tipc_bearer_resolve_congestion(struct tipc_bearer *b_ptr, /** * tipc_bearer_congested - determines if bearer is currently congested */ - int tipc_bearer_congested(struct tipc_bearer *b_ptr, struct tipc_link *l_ptr) { if (unlikely(b_ptr->blocked)) @@ -423,7 +406,6 @@ int tipc_bearer_congested(struct tipc_bearer *b_ptr, struct tipc_link *l_ptr) /** * tipc_enable_bearer - enable bearer with the given name */ - int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority) { struct tipc_bearer *b_ptr; @@ -449,7 +431,7 @@ int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority) if (tipc_in_scope(disc_domain, tipc_own_addr)) { disc_domain = tipc_own_addr & TIPC_CLUSTER_MASK; res = 0; /* accept any node in own cluster */ - } else if (in_own_cluster(disc_domain)) + } else if (in_own_cluster_exact(disc_domain)) res = 0; /* accept specified node in own cluster */ } if (res) { @@ -541,7 +523,6 @@ exit: * tipc_block_bearer(): Block the bearer with the given name, * and reset all its links */ - int tipc_block_bearer(const char *name) { struct tipc_bearer *b_ptr = NULL; @@ -573,11 +554,10 @@ int tipc_block_bearer(const char *name) } /** - * bearer_disable - + * bearer_disable * * Note: This routine assumes caller holds tipc_net_lock. */ - static void bearer_disable(struct tipc_bearer *b_ptr) { struct tipc_link *l_ptr; diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index d3eac56b8c2..e3b2be37fb3 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -49,7 +49,6 @@ * - media type identifier located at offset 3 * - remaining bytes vary according to media type */ - #define TIPC_MEDIA_ADDR_SIZE 20 #define TIPC_MEDIA_TYPE_OFFSET 3 @@ -64,7 +63,6 @@ * @media_id: TIPC media type identifier * @broadcast: non-zero if address is a broadcast address */ - struct tipc_media_addr { u8 value[TIPC_MEDIA_ADDR_SIZE]; u8 media_id; @@ -89,7 +87,6 @@ struct tipc_bearer; * @type_id: TIPC media identifier * @name: media name */ - struct tipc_media { int (*send_msg)(struct sk_buff *buf, struct tipc_bearer *b_ptr, @@ -216,7 +213,6 @@ void tipc_bearer_lock_push(struct tipc_bearer *b_ptr); * send routine always returns success -- even if the buffer was not sent -- * and let TIPC's link code deal with the undelivered message. */ - static inline int tipc_bearer_send(struct tipc_bearer *b_ptr, struct sk_buff *buf, struct tipc_media_addr *dest) diff --git a/net/tipc/config.c b/net/tipc/config.c index f76d3b15e4e..c5712a34381 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -131,7 +131,6 @@ static struct sk_buff *tipc_show_stats(void) tipc_printf(&pb, "TIPC version " TIPC_MOD_VER "\n"); /* Use additional tipc_printf()'s to return more info ... */ - str_len = tipc_printbuf_validate(&pb); skb_put(buf, TLV_SPACE(str_len)); TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len); @@ -191,7 +190,6 @@ static struct sk_buff *cfg_set_own_addr(void) * configuration commands can't be received until a local configuration * command to enable the first bearer is received and processed. */ - spin_unlock_bh(&config_lock); tipc_core_start_net(addr); spin_lock_bh(&config_lock); @@ -283,14 +281,12 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area spin_lock_bh(&config_lock); /* Save request and reply details in a well-known location */ - req_tlv_area = request_area; req_tlv_space = request_space; rep_headroom = reply_headroom; /* Check command authorization */ - - if (likely(orig_node == tipc_own_addr)) { + if (likely(in_own_node(orig_node))) { /* command is permitted */ } else if (cmd >= 0x8000) { rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED @@ -310,7 +306,6 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area } /* Call appropriate processing routine */ - switch (cmd) { case TIPC_CMD_NOOP: rep_tlv_buf = tipc_cfg_reply_none(); @@ -433,7 +428,6 @@ static void cfg_named_msg_event(void *userdata, struct sk_buff *rep_buf; /* Validate configuration message header (ignore invalid message) */ - req_hdr = (struct tipc_cfg_msg_hdr *)msg; if ((size < sizeof(*req_hdr)) || (size != TCM_ALIGN(ntohl(req_hdr->tcm_len))) || @@ -443,7 +437,6 @@ static void cfg_named_msg_event(void *userdata, } /* Generate reply for request (if can't, return request) */ - rep_buf = tipc_cfg_do_cmd(orig->node, ntohs(req_hdr->tcm_type), msg + sizeof(*req_hdr), @@ -489,10 +482,23 @@ failed: return res; } +void tipc_cfg_reinit(void) +{ + struct tipc_name_seq seq; + int res; + + seq.type = TIPC_CFG_SRV; + seq.lower = seq.upper = 0; + tipc_withdraw(config_port_ref, TIPC_ZONE_SCOPE, &seq); + + seq.lower = seq.upper = tipc_own_addr; + res = tipc_publish(config_port_ref, TIPC_ZONE_SCOPE, &seq); + if (res) + err("Unable to reinitialize configuration service\n"); +} + void tipc_cfg_stop(void) { - if (config_port_ref) { - tipc_deleteport(config_port_ref); - config_port_ref = 0; - } + tipc_deleteport(config_port_ref); + config_port_ref = 0; } diff --git a/net/tipc/config.h b/net/tipc/config.h index 80da6ebc278..1f252f3fa05 100644 --- a/net/tipc/config.h +++ b/net/tipc/config.h @@ -66,6 +66,7 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, int headroom); int tipc_cfg_init(void); +void tipc_cfg_reinit(void); void tipc_cfg_stop(void); #endif diff --git a/net/tipc/core.c b/net/tipc/core.c index 68eba03e795..f7b95239ebd 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -52,14 +52,12 @@ #endif /* global variables used by multiple sub-systems within TIPC */ - int tipc_random; const char tipc_alphabet[] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_."; /* configurable TIPC parameters */ - u32 tipc_own_addr; int tipc_max_ports; int tipc_max_subscriptions; @@ -77,7 +75,6 @@ int tipc_remote_management; * NOTE: Headroom is reserved to allow prepending of a data link header. * There may also be unrequested tailroom present at the buffer's end. */ - struct sk_buff *tipc_buf_acquire(u32 size) { struct sk_buff *skb; @@ -95,7 +92,6 @@ struct sk_buff *tipc_buf_acquire(u32 size) /** * tipc_core_stop_net - shut down TIPC networking sub-systems */ - static void tipc_core_stop_net(void) { tipc_net_stop(); @@ -105,7 +101,6 @@ static void tipc_core_stop_net(void) /** * start_net - start TIPC networking sub-systems */ - int tipc_core_start_net(unsigned long addr) { int res; @@ -121,7 +116,6 @@ int tipc_core_start_net(unsigned long addr) /** * tipc_core_stop - switch TIPC from SINGLE NODE to NOT RUNNING mode */ - static void tipc_core_stop(void) { tipc_netlink_stop(); @@ -137,7 +131,6 @@ static void tipc_core_stop(void) /** * tipc_core_start - switch TIPC from NOT RUNNING to SINGLE NODE mode */ - static int tipc_core_start(void) { int res; @@ -150,9 +143,9 @@ static int tipc_core_start(void) if (!res) res = tipc_nametbl_init(); if (!res) - res = tipc_k_signal((Handler)tipc_subscr_start, 0); + res = tipc_subscr_start(); if (!res) - res = tipc_k_signal((Handler)tipc_cfg_init, 0); + res = tipc_cfg_init(); if (!res) res = tipc_netlink_start(); if (!res) diff --git a/net/tipc/core.h b/net/tipc/core.h index 13837e0e56b..2a9bb99537b 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -85,7 +85,6 @@ void tipc_printf(struct print_buf *, const char *fmt, ...); /* * TIPC_OUTPUT is the destination print buffer for system messages. */ - #ifndef TIPC_OUTPUT #define TIPC_OUTPUT TIPC_LOG #endif @@ -102,7 +101,6 @@ void tipc_printf(struct print_buf *, const char *fmt, ...); /* * DBG_OUTPUT is the destination print buffer for debug messages. */ - #ifndef DBG_OUTPUT #define DBG_OUTPUT TIPC_LOG #endif @@ -126,13 +124,11 @@ void tipc_msg_dbg(struct print_buf *, struct tipc_msg *, const char *); /* * TIPC-specific error codes */ - #define ELINKCONG EAGAIN /* link congestion <=> resource unavailable */ /* * Global configuration variables */ - extern u32 tipc_own_addr; extern int tipc_max_ports; extern int tipc_max_subscriptions; @@ -143,7 +139,6 @@ extern int tipc_remote_management; /* * Other global variables */ - extern int tipc_random; extern const char tipc_alphabet[]; @@ -151,7 +146,6 @@ extern const char tipc_alphabet[]; /* * Routines available to privileged subsystems */ - extern int tipc_core_start_net(unsigned long); extern int tipc_handler_start(void); extern void tipc_handler_stop(void); @@ -163,7 +157,6 @@ extern void tipc_socket_stop(void); /* * TIPC timer and signal code */ - typedef void (*Handler) (unsigned long); u32 tipc_k_signal(Handler routine, unsigned long argument); @@ -176,7 +169,6 @@ u32 tipc_k_signal(Handler routine, unsigned long argument); * * Timer must be initialized before use (and terminated when no longer needed). */ - static inline void k_init_timer(struct timer_list *timer, Handler routine, unsigned long argument) { @@ -196,7 +188,6 @@ static inline void k_init_timer(struct timer_list *timer, Handler routine, * then an additional jiffy is added to account for the fact that * the starting time may be in the middle of the current jiffy. */ - static inline void k_start_timer(struct timer_list *timer, unsigned long msec) { mod_timer(timer, jiffies + msecs_to_jiffies(msec) + 1); @@ -212,7 +203,6 @@ static inline void k_start_timer(struct timer_list *timer, unsigned long msec) * WARNING: Must not be called when holding locks required by the timer's * timeout routine, otherwise deadlock can occur on SMP systems! */ - static inline void k_cancel_timer(struct timer_list *timer) { del_timer_sync(timer); @@ -229,12 +219,10 @@ static inline void k_cancel_timer(struct timer_list *timer) * (Do not "enhance" this routine to automatically cancel an active timer, * otherwise deadlock can arise when a timeout routine calls k_term_timer.) */ - static inline void k_term_timer(struct timer_list *timer) { } - /* * TIPC message buffer code * @@ -244,7 +232,6 @@ static inline void k_term_timer(struct timer_list *timer) * Note: Headroom should be a multiple of 4 to ensure the TIPC header fields * are word aligned for quicker access */ - #define BUF_HEADROOM LL_MAX_HEADER struct tipc_skb_cb { @@ -253,7 +240,6 @@ struct tipc_skb_cb { #define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0])) - static inline struct tipc_msg *buf_msg(struct sk_buff *skb) { return (struct tipc_msg *)skb->data; diff --git a/net/tipc/discover.c b/net/tipc/discover.c index c630a21b2be..ae054cfe179 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -70,7 +70,6 @@ struct tipc_link_req { * @dest_domain: network domain of node(s) which should respond to message * @b_ptr: ptr to bearer issuing message */ - static struct sk_buff *tipc_disc_init_msg(u32 type, u32 dest_domain, struct tipc_bearer *b_ptr) @@ -96,7 +95,6 @@ static struct sk_buff *tipc_disc_init_msg(u32 type, * @node_addr: duplicated node address * @media_addr: media address advertised by duplicated node */ - static void disc_dupl_alert(struct tipc_bearer *b_ptr, u32 node_addr, struct tipc_media_addr *media_addr) { @@ -117,7 +115,6 @@ static void disc_dupl_alert(struct tipc_bearer *b_ptr, u32 node_addr, * @buf: buffer containing message * @b_ptr: bearer that message arrived on */ - void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr) { struct tipc_node *n_ptr; @@ -221,7 +218,6 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr) * the new media address and reset the link to ensure it starts up * cleanly. */ - if (addr_mismatch) { if (tipc_link_is_up(link)) { disc_dupl_alert(b_ptr, orig, &media_addr); @@ -264,7 +260,6 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr) * Reinitiates discovery process if discovery object has no associated nodes * and is either not currently searching or is searching at a slow rate */ - static void disc_update(struct tipc_link_req *req) { if (!req->num_nodes) { @@ -280,7 +275,6 @@ static void disc_update(struct tipc_link_req *req) * tipc_disc_add_dest - increment set of discovered nodes * @req: ptr to link request structure */ - void tipc_disc_add_dest(struct tipc_link_req *req) { req->num_nodes++; @@ -290,7 +284,6 @@ void tipc_disc_add_dest(struct tipc_link_req *req) * tipc_disc_remove_dest - decrement set of discovered nodes * @req: ptr to link request structure */ - void tipc_disc_remove_dest(struct tipc_link_req *req) { req->num_nodes--; @@ -301,7 +294,6 @@ void tipc_disc_remove_dest(struct tipc_link_req *req) * disc_send_msg - send link setup request message * @req: ptr to link request structure */ - static void disc_send_msg(struct tipc_link_req *req) { if (!req->bearer->blocked) @@ -314,7 +306,6 @@ static void disc_send_msg(struct tipc_link_req *req) * * Called whenever a link setup request timer associated with a bearer expires. */ - static void disc_timeout(struct tipc_link_req *req) { int max_delay; @@ -322,7 +313,6 @@ static void disc_timeout(struct tipc_link_req *req) spin_lock_bh(&req->bearer->lock); /* Stop searching if only desired node has been found */ - if (tipc_node(req->domain) && req->num_nodes) { req->timer_intv = TIPC_LINK_REQ_INACTIVE; goto exit; @@ -335,7 +325,6 @@ static void disc_timeout(struct tipc_link_req *req) * hold at fast polling rate if don't have any associated nodes, * otherwise hold at slow polling rate */ - disc_send_msg(req); req->timer_intv *= 2; @@ -359,7 +348,6 @@ exit: * * Returns 0 if successful, otherwise -errno. */ - int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest, u32 dest_domain) { @@ -391,7 +379,6 @@ int tipc_disc_create(struct tipc_bearer *b_ptr, * tipc_disc_delete - destroy object sending periodic link setup requests * @req: ptr to link request structure */ - void tipc_disc_delete(struct tipc_link_req *req) { k_cancel_timer(&req->timer); @@ -399,4 +386,3 @@ void tipc_disc_delete(struct tipc_link_req *req) kfree_skb(req->buf); kfree(req); } - diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c index 527e3f0e165..90ac9bfa7ab 100644 --- a/net/tipc/eth_media.c +++ b/net/tipc/eth_media.c @@ -48,7 +48,6 @@ * @tipc_packet_type: used in binding TIPC to Ethernet driver * @cleanup: work item used when disabling bearer */ - struct eth_bearer { struct tipc_bearer *bearer; struct net_device *dev; @@ -67,7 +66,6 @@ static struct notifier_block notifier; * Media-dependent "value" field stores MAC address in first 6 bytes * and zeroes out the remaining bytes. */ - static void eth_media_addr_set(struct tipc_media_addr *a, char *mac) { memcpy(a->value, mac, ETH_ALEN); @@ -79,7 +77,6 @@ static void eth_media_addr_set(struct tipc_media_addr *a, char *mac) /** * send_msg - send a TIPC message out over an Ethernet interface */ - static int send_msg(struct sk_buff *buf, struct tipc_bearer *tb_ptr, struct tipc_media_addr *dest) { @@ -115,7 +112,6 @@ static int send_msg(struct sk_buff *buf, struct tipc_bearer *tb_ptr, * ignores packets sent using Ethernet multicast, and traffic sent to other * nodes (which can happen if interface is running in promiscuous mode). */ - static int recv_msg(struct sk_buff *buf, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { @@ -140,7 +136,6 @@ static int recv_msg(struct sk_buff *buf, struct net_device *dev, /** * enable_bearer - attach TIPC bearer to an Ethernet interface */ - static int enable_bearer(struct tipc_bearer *tb_ptr) { struct net_device *dev = NULL; @@ -151,7 +146,6 @@ static int enable_bearer(struct tipc_bearer *tb_ptr) int pending_dev = 0; /* Find unused Ethernet bearer structure */ - while (eb_ptr->dev) { if (!eb_ptr->bearer) pending_dev++; @@ -160,7 +154,6 @@ static int enable_bearer(struct tipc_bearer *tb_ptr) } /* Find device with specified name */ - read_lock(&dev_base_lock); for_each_netdev(&init_net, pdev) { if (!strncmp(pdev->name, driver_name, IFNAMSIZ)) { @@ -174,7 +167,6 @@ static int enable_bearer(struct tipc_bearer *tb_ptr) return -ENODEV; /* Create Ethernet bearer for device */ - eb_ptr->dev = dev; eb_ptr->tipc_packet_type.type = htons(ETH_P_TIPC); eb_ptr->tipc_packet_type.dev = dev; @@ -184,7 +176,6 @@ static int enable_bearer(struct tipc_bearer *tb_ptr) dev_add_pack(&eb_ptr->tipc_packet_type); /* Associate TIPC bearer with Ethernet bearer */ - eb_ptr->bearer = tb_ptr; tb_ptr->usr_handle = (void *)eb_ptr; tb_ptr->mtu = dev->mtu; @@ -198,7 +189,6 @@ static int enable_bearer(struct tipc_bearer *tb_ptr) * * This routine must be invoked from a work queue because it can sleep. */ - static void cleanup_bearer(struct work_struct *work) { struct eth_bearer *eb_ptr = @@ -216,7 +206,6 @@ static void cleanup_bearer(struct work_struct *work) * then get worker thread to complete bearer cleanup. (Can't do cleanup * here because cleanup code needs to sleep and caller holds spinlocks.) */ - static void disable_bearer(struct tipc_bearer *tb_ptr) { struct eth_bearer *eb_ptr = (struct eth_bearer *)tb_ptr->usr_handle; @@ -232,7 +221,6 @@ static void disable_bearer(struct tipc_bearer *tb_ptr) * Change the state of the Ethernet bearer (if any) associated with the * specified device. */ - static int recv_notification(struct notifier_block *nb, unsigned long evt, void *dv) { @@ -281,7 +269,6 @@ static int recv_notification(struct notifier_block *nb, unsigned long evt, /** * eth_addr2str - convert Ethernet address to string */ - static int eth_addr2str(struct tipc_media_addr *a, char *str_buf, int str_size) { if (str_size < 18) /* 18 = strlen("aa:bb:cc:dd:ee:ff\0") */ @@ -294,7 +281,6 @@ static int eth_addr2str(struct tipc_media_addr *a, char *str_buf, int str_size) /** * eth_str2addr - convert string to Ethernet address */ - static int eth_str2addr(struct tipc_media_addr *a, char *str_buf) { char mac[ETH_ALEN]; @@ -314,7 +300,6 @@ static int eth_str2addr(struct tipc_media_addr *a, char *str_buf) /** * eth_str2addr - convert Ethernet address format to message header format */ - static int eth_addr2msg(struct tipc_media_addr *a, char *msg_area) { memset(msg_area, 0, TIPC_MEDIA_ADDR_SIZE); @@ -326,7 +311,6 @@ static int eth_addr2msg(struct tipc_media_addr *a, char *msg_area) /** * eth_str2addr - convert message header address format to Ethernet format */ - static int eth_msg2addr(struct tipc_media_addr *a, char *msg_area) { if (msg_area[TIPC_MEDIA_TYPE_OFFSET] != TIPC_MEDIA_TYPE_ETH) @@ -339,7 +323,6 @@ static int eth_msg2addr(struct tipc_media_addr *a, char *msg_area) /* * Ethernet media registration info */ - static struct tipc_media eth_media_info = { .send_msg = send_msg, .enable_bearer = enable_bearer, @@ -363,7 +346,6 @@ static struct tipc_media eth_media_info = { * Register Ethernet media type with TIPC bearer code. Also register * with OS for notifications about device state changes. */ - int tipc_eth_media_start(void) { int res; @@ -386,7 +368,6 @@ int tipc_eth_media_start(void) /** * tipc_eth_media_stop - deactivate Ethernet bearer support */ - void tipc_eth_media_stop(void) { if (!eth_started) diff --git a/net/tipc/handler.c b/net/tipc/handler.c index 274c98e164b..9c6f22ff1c6 100644 --- a/net/tipc/handler.c +++ b/net/tipc/handler.c @@ -129,4 +129,3 @@ void tipc_handler_stop(void) kmem_cache_destroy(tipc_queue_item_cache); } - diff --git a/net/tipc/link.c b/net/tipc/link.c index b4b9b30167a..7a614f43549 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -45,13 +45,11 @@ /* * Out-of-range value for link session numbers */ - #define INVALID_SESSION 0x10000 /* * Link state events: */ - #define STARTING_EVT 856384768 /* link processing trigger */ #define TRAFFIC_MSG_EVT 560815u /* rx'd ??? */ #define TIMEOUT_EVT 560817u /* link timer expired */ @@ -67,7 +65,6 @@ /* * State value stored in 'exp_msg_count' */ - #define START_CHANGEOVER 100000u /** @@ -77,7 +74,6 @@ * @addr_peer: network address of node at far end * @if_peer: name of interface at far end */ - struct tipc_link_name { u32 addr_local; char if_local[TIPC_MAX_IF_NAME]; @@ -105,7 +101,6 @@ static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf); /* * Simple link routines */ - static unsigned int align(unsigned int i) { return (i + 3) & ~3u; @@ -143,7 +138,6 @@ static u32 link_last_sent(struct tipc_link *l_ptr) /* * Simple non-static link routines (i.e. referenced outside this file) */ - int tipc_link_is_up(struct tipc_link *l_ptr) { if (!l_ptr) @@ -164,7 +158,6 @@ int tipc_link_is_active(struct tipc_link *l_ptr) * * Returns 1 if link name is valid, otherwise 0. */ - static int link_name_validate(const char *name, struct tipc_link_name *name_parts) { @@ -180,7 +173,6 @@ static int link_name_validate(const char *name, u32 if_peer_len; /* copy link name & ensure length is OK */ - name_copy[TIPC_MAX_LINK_NAME - 1] = 0; /* need above in case non-Posix strncpy() doesn't pad with nulls */ strncpy(name_copy, name, TIPC_MAX_LINK_NAME); @@ -188,7 +180,6 @@ static int link_name_validate(const char *name, return 0; /* ensure all component parts of link name are present */ - addr_local = name_copy; if_local = strchr(addr_local, ':'); if (if_local == NULL) @@ -206,7 +197,6 @@ static int link_name_validate(const char *name, if_peer_len = strlen(if_peer) + 1; /* validate component parts of link name */ - if ((sscanf(addr_local, "%u.%u.%u%c", &z_local, &c_local, &n_local, &dummy) != 3) || (sscanf(addr_peer, "%u.%u.%u%c", @@ -220,7 +210,6 @@ static int link_name_validate(const char *name, return 0; /* return link name components, if necessary */ - if (name_parts) { name_parts->addr_local = tipc_addr(z_local, c_local, n_local); strcpy(name_parts->if_local, if_local); @@ -239,13 +228,11 @@ static int link_name_validate(const char *name, * another thread because tipc_link_delete() always cancels the link timer before * tipc_node_delete() is called.) */ - static void link_timeout(struct tipc_link *l_ptr) { tipc_node_lock(l_ptr->owner); /* update counters used in statistical profiling of send traffic */ - l_ptr->stats.accu_queue_sz += l_ptr->out_queue_size; l_ptr->stats.queue_sz_counts++; @@ -278,7 +265,6 @@ static void link_timeout(struct tipc_link *l_ptr) } /* do all other link processing performed on a periodic basis */ - link_check_defragm_bufs(l_ptr); link_state_event(l_ptr, TIMEOUT_EVT); @@ -302,7 +288,6 @@ static void link_set_timer(struct tipc_link *l_ptr, u32 time) * * Returns pointer to link. */ - struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, struct tipc_bearer *b_ptr, const struct tipc_media_addr *media_addr) @@ -383,7 +368,6 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, * This routine must not grab the node lock until after link timer cancellation * to avoid a potential deadlock situation. */ - void tipc_link_delete(struct tipc_link *l_ptr) { if (!l_ptr) { @@ -419,7 +403,6 @@ static void link_start(struct tipc_link *l_ptr) * Schedules port for renewed sending of messages after link congestion * has abated. */ - static int link_schedule_port(struct tipc_link *l_ptr, u32 origport, u32 sz) { struct tipc_port *p_ptr; @@ -476,7 +459,6 @@ exit: * link_release_outqueue - purge link's outbound message queue * @l_ptr: pointer to link */ - static void link_release_outqueue(struct tipc_link *l_ptr) { struct sk_buff *buf = l_ptr->first_out; @@ -495,7 +477,6 @@ static void link_release_outqueue(struct tipc_link *l_ptr) * tipc_link_reset_fragments - purge link's inbound message fragments queue * @l_ptr: pointer to link */ - void tipc_link_reset_fragments(struct tipc_link *l_ptr) { struct sk_buff *buf = l_ptr->defragm_buf; @@ -513,7 +494,6 @@ void tipc_link_reset_fragments(struct tipc_link *l_ptr) * tipc_link_stop - purge all inbound and outbound messages associated with link * @l_ptr: pointer to link */ - void tipc_link_stop(struct tipc_link *l_ptr) { struct sk_buff *buf; @@ -569,7 +549,6 @@ void tipc_link_reset(struct tipc_link *l_ptr) } /* Clean up all queues: */ - link_release_outqueue(l_ptr); kfree_skb(l_ptr->proto_msg_queue); l_ptr->proto_msg_queue = NULL; @@ -611,8 +590,7 @@ static void link_activate(struct tipc_link *l_ptr) * @l_ptr: pointer to link * @event: state machine event to process */ - -static void link_state_event(struct tipc_link *l_ptr, unsigned event) +static void link_state_event(struct tipc_link *l_ptr, unsigned int event) { struct tipc_link *other; u32 cont_intv = l_ptr->continuity_interval; @@ -785,7 +763,6 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned event) * link_bundle_buf(): Append contents of a buffer to * the tail of an existing one. */ - static int link_bundle_buf(struct tipc_link *l_ptr, struct sk_buff *bundler, struct sk_buff *buf) @@ -860,7 +837,6 @@ static void link_add_chain_to_outqueue(struct tipc_link *l_ptr, * inside TIPC when the 'fast path' in tipc_send_buf * has failed, and from link_send() */ - int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); @@ -872,7 +848,6 @@ int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf) u32 max_packet = l_ptr->max_pkt; /* Match msg importance against queue limits: */ - if (unlikely(queue_size >= queue_limit)) { if (imp <= TIPC_CRITICAL_IMPORTANCE) { link_schedule_port(l_ptr, msg_origport(msg), size); @@ -888,12 +863,10 @@ int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf) } /* Fragmentation needed ? */ - if (size > max_packet) return link_send_long_buf(l_ptr, buf); - /* Packet can be queued or sent: */ - + /* Packet can be queued or sent. */ if (likely(!tipc_bearer_congested(l_ptr->b_ptr, l_ptr) && !link_congested(l_ptr))) { link_add_to_outqueue(l_ptr, buf, msg); @@ -907,13 +880,11 @@ int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf) } return dsz; } - /* Congestion: can message be bundled ?: */ - + /* Congestion: can message be bundled ? */ if ((msg_user(msg) != CHANGEOVER_PROTOCOL) && (msg_user(msg) != MSG_FRAGMENTER)) { /* Try adding message to an existing bundle */ - if (l_ptr->next_out && link_bundle_buf(l_ptr, l_ptr->last_out, buf)) { tipc_bearer_resolve_congestion(l_ptr->b_ptr, l_ptr); @@ -921,7 +892,6 @@ int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf) } /* Try creating a new bundle */ - if (size <= max_packet * 2 / 3) { struct sk_buff *bundler = tipc_buf_acquire(max_packet); struct tipc_msg bundler_hdr; @@ -951,7 +921,6 @@ int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf) * not been selected yet, and the the owner node is not locked * Called by TIPC internal users, e.g. the name distributor */ - int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector) { struct tipc_link *l_ptr; @@ -984,7 +953,6 @@ int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector) * small enough not to require fragmentation. * Called without any locks held. */ - void tipc_link_send_names(struct list_head *message_list, u32 dest) { struct tipc_node *n_ptr; @@ -1013,7 +981,6 @@ void tipc_link_send_names(struct list_head *message_list, u32 dest) read_unlock_bh(&tipc_net_lock); /* discard the messages if they couldn't be sent */ - list_for_each_safe(buf, temp_buf, ((struct sk_buff *)message_list)) { list_del((struct list_head *)buf); kfree_skb(buf); @@ -1026,7 +993,6 @@ void tipc_link_send_names(struct list_head *message_list, u32 dest) * inclusive total message length. Very time critical. * Link is locked. Returns user data length. */ - static int link_send_buf_fast(struct tipc_link *l_ptr, struct sk_buff *buf, u32 *used_max_pkt) { @@ -1111,7 +1077,6 @@ again: * Try building message using port's max_pkt hint. * (Must not hold any locks while building message.) */ - res = tipc_msg_build(hdr, msg_sect, num_sect, total_len, sender->max_pkt, !sender->user_port, &buf); @@ -1131,12 +1096,10 @@ exit: } /* Exit if build request was invalid */ - if (unlikely(res < 0)) goto exit; /* Exit if link (or bearer) is congested */ - if (link_congested(l_ptr) || !list_empty(&l_ptr->b_ptr->cong_links)) { res = link_schedule_port(l_ptr, @@ -1148,7 +1111,6 @@ exit: * Message size exceeds max_pkt hint; update hint, * then re-try fast path or fragment the message */ - sender->max_pkt = l_ptr->max_pkt; tipc_node_unlock(node); read_unlock_bh(&tipc_net_lock); @@ -1166,7 +1128,6 @@ exit: read_unlock_bh(&tipc_net_lock); /* Couldn't find a link to the destination node */ - if (buf) return tipc_reject_msg(buf, TIPC_ERR_NO_NODE); if (res >= 0) @@ -1220,15 +1181,13 @@ again: sect_crs = NULL; curr_sect = -1; - /* Prepare reusable fragment header: */ - + /* Prepare reusable fragment header */ tipc_msg_init(&fragm_hdr, MSG_FRAGMENTER, FIRST_FRAGMENT, INT_H_SIZE, msg_destnode(hdr)); msg_set_size(&fragm_hdr, max_pkt); msg_set_fragm_no(&fragm_hdr, 1); - /* Prepare header of first fragment: */ - + /* Prepare header of first fragment */ buf_chain = buf = tipc_buf_acquire(max_pkt); if (!buf) return -ENOMEM; @@ -1237,8 +1196,7 @@ again: hsz = msg_hdr_sz(hdr); skb_copy_to_linear_data_offset(buf, INT_H_SIZE, hdr, hsz); - /* Chop up message: */ - + /* Chop up message */ fragm_crs = INT_H_SIZE + hsz; fragm_rest = fragm_sz - hsz; @@ -1329,7 +1287,6 @@ reject: } /* Append chain of fragments to send queue & send them */ - l_ptr->long_msg_seq_no++; link_add_chain_to_outqueue(l_ptr, buf_chain, l_ptr->long_msg_seq_no); l_ptr->stats.sent_fragments += fragm_no; @@ -1350,7 +1307,6 @@ u32 tipc_link_push_packet(struct tipc_link *l_ptr) /* Step to position where retransmission failed, if any, */ /* consider that buffers may have been released in meantime */ - if (r_q_size && buf) { u32 last = lesser(mod(r_q_head + r_q_size), link_last_sent(l_ptr)); @@ -1365,7 +1321,6 @@ u32 tipc_link_push_packet(struct tipc_link *l_ptr) } /* Continue retransmission now, if there is anything: */ - if (r_q_size && buf) { msg_set_ack(buf_msg(buf), mod(l_ptr->next_in_no - 1)); msg_set_bcast_ack(buf_msg(buf), l_ptr->owner->bclink.last_in); @@ -1381,7 +1336,6 @@ u32 tipc_link_push_packet(struct tipc_link *l_ptr) } /* Send deferred protocol message, if any: */ - buf = l_ptr->proto_msg_queue; if (buf) { msg_set_ack(buf_msg(buf), mod(l_ptr->next_in_no - 1)); @@ -1398,7 +1352,6 @@ u32 tipc_link_push_packet(struct tipc_link *l_ptr) } /* Send one deferred data message, if send window not full: */ - buf = l_ptr->next_out; if (buf) { struct tipc_msg *msg = buf_msg(buf); @@ -1478,16 +1431,12 @@ static void link_retransmit_failure(struct tipc_link *l_ptr, warn("Retransmission failure on link <%s>\n", l_ptr->name); if (l_ptr->addr) { - /* Handle failure on standard link */ - link_print(l_ptr, "Resetting link\n"); tipc_link_reset(l_ptr); } else { - /* Handle failure on broadcast link */ - struct tipc_node *n_ptr; char addr_string[16]; @@ -1536,7 +1485,6 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *buf, return; } else { /* Detect repeated retransmit failures on uncongested bearer */ - if (l_ptr->last_retransmitted == msg_seqno(msg)) { if (++l_ptr->stale_count > 100) { link_retransmit_failure(l_ptr, buf); @@ -1571,7 +1519,6 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *buf, /** * link_insert_deferred_queue - insert deferred messages back into receive chain */ - static struct sk_buff *link_insert_deferred_queue(struct tipc_link *l_ptr, struct sk_buff *buf) { @@ -1602,7 +1549,6 @@ static struct sk_buff *link_insert_deferred_queue(struct tipc_link *l_ptr, * TIPC will ignore the excess, under the assumption that it is optional info * introduced by a later release of the protocol. */ - static int link_recv_buf_validate(struct sk_buff *buf) { static u32 min_data_hdr_size[8] = { @@ -1648,7 +1594,6 @@ static int link_recv_buf_validate(struct sk_buff *buf) * Invoked with no locks held. Bearer pointer must point to a valid bearer * structure (i.e. cannot be NULL), but bearer can be inactive. */ - void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) { read_lock_bh(&tipc_net_lock); @@ -1666,22 +1611,18 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) head = head->next; /* Ensure bearer is still enabled */ - if (unlikely(!b_ptr->active)) goto cont; /* Ensure message is well-formed */ - if (unlikely(!link_recv_buf_validate(buf))) goto cont; /* Ensure message data is a single contiguous unit */ - if (unlikely(skb_linearize(buf))) goto cont; /* Handle arrival of a non-unicast link message */ - msg = buf_msg(buf); if (unlikely(msg_non_seq(msg))) { @@ -1693,20 +1634,17 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) } /* Discard unicast link messages destined for another node */ - if (unlikely(!msg_short(msg) && (msg_destnode(msg) != tipc_own_addr))) goto cont; /* Locate neighboring node that sent message */ - n_ptr = tipc_node_find(msg_prevnode(msg)); if (unlikely(!n_ptr)) goto cont; tipc_node_lock(n_ptr); /* Locate unicast link endpoint that should handle message */ - l_ptr = n_ptr->links[b_ptr->identity]; if (unlikely(!l_ptr)) { tipc_node_unlock(n_ptr); @@ -1714,7 +1652,6 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) } /* Verify that communication with node is currently allowed */ - if ((n_ptr->block_setup & WAIT_PEER_DOWN) && msg_user(msg) == LINK_PROTOCOL && (msg_type(msg) == RESET_MSG || @@ -1728,12 +1665,10 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) } /* Validate message sequence number info */ - seq_no = msg_seqno(msg); ackd = msg_ack(msg); /* Release acked messages */ - if (n_ptr->bclink.supported) tipc_bclink_acknowledge(n_ptr, msg_bcast_ack(msg)); @@ -1752,7 +1687,6 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) } /* Try sending any messages link endpoint has pending */ - if (unlikely(l_ptr->next_out)) tipc_link_push_queue(l_ptr); if (unlikely(!list_empty(&l_ptr->waiting_ports))) @@ -1763,7 +1697,6 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) } /* Now (finally!) process the incoming message */ - protocol_check: if (likely(link_working_working(l_ptr))) { if (likely(seq_no == mod(l_ptr->next_in_no))) { @@ -1859,7 +1792,6 @@ cont: * * Returns increase in queue length (i.e. 0 or 1) */ - u32 tipc_link_defer_pkt(struct sk_buff **head, struct sk_buff **tail, struct sk_buff *buf) { @@ -1908,7 +1840,6 @@ u32 tipc_link_defer_pkt(struct sk_buff **head, struct sk_buff **tail, /* * link_handle_out_of_seq_msg - handle arrival of out-of-sequence packet */ - static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, struct sk_buff *buf) { @@ -1920,14 +1851,12 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, } /* Record OOS packet arrival (force mismatch on next timeout) */ - l_ptr->checkpoint--; /* * Discard packet if a duplicate; otherwise add it to deferred queue * and notify peer of gap as per protocol specification */ - if (less(seq_no, mod(l_ptr->next_in_no))) { l_ptr->stats.duplicates++; kfree_skb(buf); @@ -1957,7 +1886,6 @@ void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, int r_flag; /* Discard any previous message that was deferred due to congestion */ - if (l_ptr->proto_msg_queue) { kfree_skb(l_ptr->proto_msg_queue); l_ptr->proto_msg_queue = NULL; @@ -1967,12 +1895,10 @@ void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, return; /* Abort non-RESET send if communication with node is prohibited */ - if ((l_ptr->owner->block_setup) && (msg_typ != RESET_MSG)) return; /* Create protocol message with "out-of-sequence" sequence number */ - msg_set_type(msg, msg_typ); msg_set_net_plane(msg, l_ptr->b_ptr->net_plane); msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); @@ -2040,14 +1966,12 @@ void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, skb_copy_to_linear_data(buf, msg, sizeof(l_ptr->proto_msg)); /* Defer message if bearer is already congested */ - if (tipc_bearer_congested(l_ptr->b_ptr, l_ptr)) { l_ptr->proto_msg_queue = buf; return; } /* Defer message if attempting to send results in bearer congestion */ - if (!tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr)) { tipc_bearer_schedule(l_ptr->b_ptr, l_ptr); l_ptr->proto_msg_queue = buf; @@ -2056,7 +1980,6 @@ void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, } /* Discard message if it was sent successfully */ - l_ptr->unacked_window = 0; kfree_skb(buf); } @@ -2066,7 +1989,6 @@ void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, * Note that network plane id propagates through the network, and may * change at any time. The node with lowest address rules */ - static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf) { u32 rec_gap = 0; @@ -2079,7 +2001,6 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf) goto exit; /* record unnumbered packet arrival (force mismatch on next timeout) */ - l_ptr->checkpoint--; if (l_ptr->b_ptr->net_plane != msg_net_plane(msg)) @@ -2111,7 +2032,6 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf) /* fall thru' */ case ACTIVATE_MSG: /* Update link settings according other endpoint's values */ - strcpy((strrchr(l_ptr->name, ':') + 1), (char *)msg_data(msg)); msg_tol = msg_link_tolerance(msg); @@ -2133,7 +2053,6 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf) l_ptr->owner->bclink.supportable = (max_pkt_info != 0); /* Synchronize broadcast link info, if not done previously */ - if (!tipc_node_is_up(l_ptr->owner)) { l_ptr->owner->bclink.last_sent = l_ptr->owner->bclink.last_in = @@ -2185,7 +2104,6 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf) } /* Protocol message before retransmits, reduce loss risk */ - if (l_ptr->owner->bclink.supported) tipc_bclink_update_link_state(l_ptr->owner, msg_last_bcast(msg)); @@ -2243,7 +2161,6 @@ static void tipc_link_tunnel(struct tipc_link *l_ptr, * changeover(): Send whole message queue via the remaining link * Owner node is locked. */ - void tipc_link_changeover(struct tipc_link *l_ptr) { u32 msgcount = l_ptr->out_queue_size; @@ -2343,8 +2260,6 @@ void tipc_link_send_duplicate(struct tipc_link *l_ptr, struct tipc_link *tunnel) } } - - /** * buf_extract - extracts embedded TIPC message from another message * @skb: encapsulating message buffer @@ -2353,7 +2268,6 @@ void tipc_link_send_duplicate(struct tipc_link *l_ptr, struct tipc_link *tunnel) * Returns a new message buffer containing an embedded message. The * encapsulating message itself is left unchanged. */ - static struct sk_buff *buf_extract(struct sk_buff *skb, u32 from_pos) { struct tipc_msg *msg = (struct tipc_msg *)(skb->data + from_pos); @@ -2370,7 +2284,6 @@ static struct sk_buff *buf_extract(struct sk_buff *skb, u32 from_pos) * link_recv_changeover_msg(): Receive tunneled packet sent * via other link. Node is locked. Return extracted buffer. */ - static int link_recv_changeover_msg(struct tipc_link **l_ptr, struct sk_buff **buf) { @@ -2405,7 +2318,6 @@ static int link_recv_changeover_msg(struct tipc_link **l_ptr, } /* First original message ?: */ - if (tipc_link_is_up(dest_link)) { info("Resetting link <%s>, changeover initiated by peer\n", dest_link->name); @@ -2420,7 +2332,6 @@ static int link_recv_changeover_msg(struct tipc_link **l_ptr, } /* Receive original message */ - if (dest_link->exp_msg_count == 0) { warn("Link switchover error, " "got too many tunnelled messages\n"); @@ -2469,7 +2380,6 @@ void tipc_link_recv_bundle(struct sk_buff *buf) * Fragmentation/defragmentation: */ - /* * link_send_long_buf: Entry for buffers needing fragmentation. * The buffer is complete, inclusive total message length. @@ -2496,12 +2406,10 @@ static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf) destaddr = msg_destnode(inmsg); /* Prepare reusable fragment header: */ - tipc_msg_init(&fragm_hdr, MSG_FRAGMENTER, FIRST_FRAGMENT, INT_H_SIZE, destaddr); /* Chop up message: */ - while (rest > 0) { struct sk_buff *fragm; @@ -2535,7 +2443,6 @@ static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf) kfree_skb(buf); /* Append chain of fragments to send queue & send them */ - l_ptr->long_msg_seq_no++; link_add_chain_to_outqueue(l_ptr, buf_chain, l_ptr->long_msg_seq_no); l_ptr->stats.sent_fragments += fragm_no; @@ -2551,7 +2458,6 @@ static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf) * help storing these values in unused, available fields in the * pending message. This makes dynamic memory allocation unnecessary. */ - static void set_long_msg_seqno(struct sk_buff *buf, u32 seqno) { msg_set_seqno(buf_msg(buf), seqno); @@ -2603,7 +2509,6 @@ int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, *fb = NULL; /* Is there an incomplete message waiting for this fragment? */ - while (pbuf && ((buf_seqno(pbuf) != long_msg_seq_no) || (msg_orignode(fragm) != msg_orignode(buf_msg(pbuf))))) { prev = pbuf; @@ -2629,7 +2534,6 @@ int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, skb_copy_to_linear_data(pbuf, imsg, msg_data_sz(fragm)); /* Prepare buffer for subsequent fragments. */ - set_long_msg_seqno(pbuf, long_msg_seq_no); set_fragm_size(pbuf, fragm_sz); set_expected_frags(pbuf, exp_fragm_cnt - 1); @@ -2650,7 +2554,6 @@ int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, kfree_skb(fbuf); /* Is message complete? */ - if (exp_frags == 0) { if (prev) prev->next = pbuf->next; @@ -2672,7 +2575,6 @@ int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, * link_check_defragm_bufs - flush stale incoming message fragments * @l_ptr: pointer to link */ - static void link_check_defragm_bufs(struct tipc_link *l_ptr) { struct sk_buff *prev = NULL; @@ -2701,8 +2603,6 @@ static void link_check_defragm_bufs(struct tipc_link *l_ptr) } } - - static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tolerance) { if ((tolerance < TIPC_MIN_LINK_TOL) || (tolerance > TIPC_MAX_LINK_TOL)) @@ -2714,7 +2614,6 @@ static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tolerance) l_ptr->abort_limit = tolerance / (l_ptr->continuity_interval / 4); } - void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window) { /* Data messages from this node, inclusive FIRST_FRAGM */ @@ -2744,7 +2643,6 @@ void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window) * * Returns pointer to link (or 0 if invalid link name). */ - static struct tipc_link *link_find_link(const char *name, struct tipc_node **node) { @@ -2778,7 +2676,6 @@ static struct tipc_link *link_find_link(const char *name, * * Returns 1 if value is within range, 0 if not. */ - static int link_value_is_valid(u16 cmd, u32 new_value) { switch (cmd) { @@ -2794,7 +2691,6 @@ static int link_value_is_valid(u16 cmd, u32 new_value) return 0; } - /** * link_cmd_set_value - change priority/tolerance/window for link/bearer/media * @name - ptr to link, bearer, or media name @@ -2805,7 +2701,6 @@ static int link_value_is_valid(u16 cmd, u32 new_value) * * Returns 0 if value updated and negative value on error. */ - static int link_cmd_set_value(const char *name, u32 new_value, u16 cmd) { struct tipc_node *node; @@ -2910,7 +2805,6 @@ struct sk_buff *tipc_link_cmd_config(const void *req_tlv_area, int req_tlv_space * link_reset_statistics - reset link statistics * @l_ptr: pointer to link */ - static void link_reset_statistics(struct tipc_link *l_ptr) { memset(&l_ptr->stats, 0, sizeof(l_ptr->stats)); @@ -2951,7 +2845,6 @@ struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_ /** * percent - convert count to a percentage of total (rounding up or down) */ - static u32 percent(u32 count, u32 total) { return (count * 100 + (total / 2)) / total; @@ -2965,7 +2858,6 @@ static u32 percent(u32 count, u32 total) * * Returns length of print buffer data string (or 0 if error) */ - static int tipc_link_stats(const char *name, char *buf, const u32 buf_size) { struct print_buf pb; @@ -3087,7 +2979,6 @@ struct sk_buff *tipc_link_cmd_show_stats(const void *req_tlv_area, int req_tlv_s * * If no active link can be found, uses default maximum packet size. */ - u32 tipc_link_get_max_pkt(u32 dest, u32 selector) { struct tipc_node *n_ptr; @@ -3171,4 +3062,3 @@ print_state: tipc_printbuf_validate(buf); info("%s", print_area); } - diff --git a/net/tipc/link.h b/net/tipc/link.h index 73c18c140e1..d6a60a963ce 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -47,13 +47,11 @@ /* * Out-of-range value for link sequence numbers */ - #define INVALID_LINK_SEQ 0x10000 /* * Link states */ - #define WORKING_WORKING 560810u #define WORKING_UNKNOWN 560811u #define RESET_UNKNOWN 560812u @@ -63,7 +61,6 @@ * Starting value for maximum packet size negotiation on unicast links * (unless bearer MTU is less) */ - #define MAX_PKT_DEFAULT 1500 /** @@ -114,7 +111,6 @@ * @defragm_buf: list of partially reassembled inbound message fragments * @stats: collects statistics regarding link activity */ - struct tipc_link { u32 addr; char name[TIPC_MAX_LINK_NAME]; @@ -255,7 +251,6 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, /* * Link sequence number manipulation routines (uses modulo 2**16 arithmetic) */ - static inline u32 buf_seqno(struct sk_buff *buf) { return msg_seqno(buf_msg(buf)); @@ -294,7 +289,6 @@ static inline u32 lesser(u32 left, u32 right) /* * Link status checking routines */ - static inline int link_working_working(struct tipc_link *l_ptr) { return l_ptr->state == WORKING_WORKING; diff --git a/net/tipc/log.c b/net/tipc/log.c index 895c6e530b0..026733f2491 100644 --- a/net/tipc/log.c +++ b/net/tipc/log.c @@ -47,7 +47,6 @@ * * Additional user-defined print buffers are also permitted. */ - static struct print_buf null_buf = { NULL, 0, NULL, 0 }; struct print_buf *const TIPC_NULL = &null_buf; @@ -72,7 +71,6 @@ struct print_buf *const TIPC_LOG = &log_buf; * on the caller to prevent simultaneous use of the print buffer(s) being * manipulated. */ - static char print_string[TIPC_PB_MAX_STR]; static DEFINE_SPINLOCK(print_lock); @@ -97,7 +95,6 @@ static void tipc_printbuf_move(struct print_buf *pb_to, * Note: If the character array is too small (or absent), the print buffer * becomes a null device that discards anything written to it. */ - void tipc_printbuf_init(struct print_buf *pb, char *raw, u32 size) { pb->buf = raw; @@ -117,7 +114,6 @@ void tipc_printbuf_init(struct print_buf *pb, char *raw, u32 size) * tipc_printbuf_reset - reinitialize print buffer to empty state * @pb: pointer to print buffer structure */ - static void tipc_printbuf_reset(struct print_buf *pb) { if (pb->buf) { @@ -133,7 +129,6 @@ static void tipc_printbuf_reset(struct print_buf *pb) * * Returns non-zero if print buffer is empty. */ - static int tipc_printbuf_empty(struct print_buf *pb) { return !pb->buf || (pb->crs == pb->buf); @@ -148,7 +143,6 @@ static int tipc_printbuf_empty(struct print_buf *pb) * * Returns length of print buffer data string (including trailing NUL) */ - int tipc_printbuf_validate(struct print_buf *pb) { char *err = "\n\n*** PRINT BUFFER OVERFLOW ***\n\n"; @@ -182,14 +176,12 @@ int tipc_printbuf_validate(struct print_buf *pb) * Current contents of destination print buffer (if any) are discarded. * Source print buffer becomes empty if a successful move occurs. */ - static void tipc_printbuf_move(struct print_buf *pb_to, struct print_buf *pb_from) { int len; /* Handle the cases where contents can't be moved */ - if (!pb_to->buf) return; @@ -206,7 +198,6 @@ static void tipc_printbuf_move(struct print_buf *pb_to, } /* Copy data from char after cursor to end (if used) */ - len = pb_from->buf + pb_from->size - pb_from->crs - 2; if ((pb_from->buf[pb_from->size - 1] == 0) && (len > 0)) { strcpy(pb_to->buf, pb_from->crs + 1); @@ -215,7 +206,6 @@ static void tipc_printbuf_move(struct print_buf *pb_to, pb_to->crs = pb_to->buf; /* Copy data from start to cursor (always) */ - len = pb_from->crs - pb_from->buf; strcpy(pb_to->crs, pb_from->buf); pb_to->crs += len; @@ -228,7 +218,6 @@ static void tipc_printbuf_move(struct print_buf *pb_to, * @pb: pointer to print buffer * @fmt: formatted info to be printed */ - void tipc_printf(struct print_buf *pb, const char *fmt, ...) { int chars_to_add; @@ -270,7 +259,6 @@ void tipc_printf(struct print_buf *pb, const char *fmt, ...) * tipc_log_resize - change the size of the TIPC log buffer * @log_size: print buffer size to use */ - int tipc_log_resize(int log_size) { int res = 0; @@ -295,7 +283,6 @@ int tipc_log_resize(int log_size) /** * tipc_log_resize_cmd - reconfigure size of TIPC log buffer */ - struct sk_buff *tipc_log_resize_cmd(const void *req_tlv_area, int req_tlv_space) { u32 value; @@ -316,7 +303,6 @@ struct sk_buff *tipc_log_resize_cmd(const void *req_tlv_area, int req_tlv_space) /** * tipc_log_dump - capture TIPC log buffer contents in configuration message */ - struct sk_buff *tipc_log_dump(void) { struct sk_buff *reply; diff --git a/net/tipc/log.h b/net/tipc/log.h index 2248d96238e..d1f5eb967fd 100644 --- a/net/tipc/log.h +++ b/net/tipc/log.h @@ -44,7 +44,6 @@ * @crs: pointer to first unused space in character array (i.e. final NUL) * @echo: echo output to system console if non-zero */ - struct print_buf { char *buf; u32 size; diff --git a/net/tipc/msg.c b/net/tipc/msg.c index e3afe162c0a..deea0d232dc 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -72,7 +72,6 @@ void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, * * Returns message data size or errno */ - int tipc_msg_build(struct tipc_msg *hdr, struct iovec const *msg_sect, u32 num_sect, unsigned int total_len, int max_size, int usrmem, struct sk_buff **buf) @@ -112,7 +111,6 @@ int tipc_msg_build(struct tipc_msg *hdr, struct iovec const *msg_sect, } #ifdef CONFIG_TIPC_DEBUG - void tipc_msg_dbg(struct print_buf *buf, struct tipc_msg *msg, const char *str) { u32 usr = msg_user(msg); @@ -352,5 +350,4 @@ void tipc_msg_dbg(struct print_buf *buf, struct tipc_msg *msg, const char *str) if ((usr == MSG_FRAGMENTER) && (msg_type(msg) == FIRST_FRAGMENT)) tipc_msg_dbg(buf, msg_get_wrapped(msg), " /"); } - #endif diff --git a/net/tipc/msg.h b/net/tipc/msg.h index eba524e34a6..ba2a72beea6 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -44,7 +44,6 @@ * * Note: Some items are also used with TIPC internal message headers */ - #define TIPC_VERSION 2 /* @@ -58,7 +57,6 @@ /* * Payload message types */ - #define TIPC_CONN_MSG 0 #define TIPC_MCAST_MSG 1 #define TIPC_NAMED_MSG 2 @@ -67,7 +65,6 @@ /* * Message header sizes */ - #define SHORT_H_SIZE 24 /* In-cluster basic payload message */ #define BASIC_H_SIZE 32 /* Basic payload message */ #define NAMED_H_SIZE 40 /* Named payload message */ @@ -121,7 +118,6 @@ static inline void msg_swap_words(struct tipc_msg *msg, u32 a, u32 b) /* * Word 0 */ - static inline u32 msg_version(struct tipc_msg *m) { return msg_bits(m, 0, 29, 7); @@ -216,7 +212,6 @@ static inline void msg_set_size(struct tipc_msg *m, u32 sz) /* * Word 1 */ - static inline u32 msg_type(struct tipc_msg *m) { return msg_bits(m, 1, 29, 0x7); @@ -291,7 +286,6 @@ static inline void msg_set_bcast_ack(struct tipc_msg *m, u32 n) /* * Word 2 */ - static inline u32 msg_ack(struct tipc_msg *m) { return msg_bits(m, 2, 16, 0xffff); @@ -315,8 +309,6 @@ static inline void msg_set_seqno(struct tipc_msg *m, u32 n) /* * Words 3-10 */ - - static inline u32 msg_prevnode(struct tipc_msg *m) { return msg_word(m, 3); @@ -434,7 +426,6 @@ static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) return (struct tipc_msg *)msg_data(m); } - /* * Constants and routines used to read and write TIPC internal message headers */ @@ -442,7 +433,6 @@ static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) /* * Internal message users */ - #define BCAST_PROTOCOL 5 #define MSG_BUNDLER 6 #define LINK_PROTOCOL 7 @@ -456,7 +446,6 @@ static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) /* * Connection management protocol message types */ - #define CONN_PROBE 0 #define CONN_PROBE_REPLY 1 #define CONN_ACK 2 @@ -464,14 +453,12 @@ static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) /* * Name distributor message types */ - #define PUBLICATION 0 #define WITHDRAWAL 1 /* * Segmentation message types */ - #define FIRST_FRAGMENT 0 #define FRAGMENT 1 #define LAST_FRAGMENT 2 @@ -479,7 +466,6 @@ static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) /* * Link management protocol message types */ - #define STATE_MSG 0 #define RESET_MSG 1 #define ACTIVATE_MSG 2 @@ -493,7 +479,6 @@ static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) /* * Config protocol message types */ - #define DSC_REQ_MSG 0 #define DSC_RESP_MSG 1 @@ -501,7 +486,6 @@ static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) /* * Word 1 */ - static inline u32 msg_seq_gap(struct tipc_msg *m) { return msg_bits(m, 1, 16, 0x1fff); @@ -526,7 +510,6 @@ static inline void msg_set_node_sig(struct tipc_msg *m, u32 n) /* * Word 2 */ - static inline u32 msg_dest_domain(struct tipc_msg *m) { return msg_word(m, 2); @@ -561,7 +544,6 @@ static inline void msg_set_bcgap_to(struct tipc_msg *m, u32 n) /* * Word 4 */ - static inline u32 msg_last_bcast(struct tipc_msg *m) { return msg_bits(m, 4, 16, 0xffff); @@ -628,7 +610,6 @@ static inline void msg_set_link_selector(struct tipc_msg *m, u32 n) /* * Word 5 */ - static inline u32 msg_session(struct tipc_msg *m) { return msg_bits(m, 5, 16, 0xffff); @@ -697,7 +678,6 @@ static inline char *msg_media_addr(struct tipc_msg *m) /* * Word 9 */ - static inline u32 msg_msgcnt(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff); @@ -744,5 +724,4 @@ void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, int tipc_msg_build(struct tipc_msg *hdr, struct iovec const *msg_sect, u32 num_sect, unsigned int total_len, int max_size, int usrmem, struct sk_buff **buf); - #endif diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index d57da615961..158318e67b0 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -58,7 +58,6 @@ * Note: There is no field that identifies the publishing node because it is * the same for all items contained within a publication message. */ - struct distr_item { __be32 type; __be32 lower; @@ -68,17 +67,41 @@ struct distr_item { }; /** - * List of externally visible publications by this node -- - * that is, all publications having scope > TIPC_NODE_SCOPE. + * struct publ_list - list of publications made by this node + * @list: circular list of publications + * @list_size: number of entries in list */ +struct publ_list { + struct list_head list; + u32 size; +}; + +static struct publ_list publ_zone = { + .list = LIST_HEAD_INIT(publ_zone.list), + .size = 0, +}; + +static struct publ_list publ_cluster = { + .list = LIST_HEAD_INIT(publ_cluster.list), + .size = 0, +}; + +static struct publ_list publ_node = { + .list = LIST_HEAD_INIT(publ_node.list), + .size = 0, +}; + +static struct publ_list *publ_lists[] = { + NULL, + &publ_zone, /* publ_lists[TIPC_ZONE_SCOPE] */ + &publ_cluster, /* publ_lists[TIPC_CLUSTER_SCOPE] */ + &publ_node /* publ_lists[TIPC_NODE_SCOPE] */ +}; -static LIST_HEAD(publ_root); -static u32 publ_cnt; /** * publ_to_item - add publication info to a publication message */ - static void publ_to_item(struct distr_item *i, struct publication *p) { i->type = htonl(p->type); @@ -91,7 +114,6 @@ static void publ_to_item(struct distr_item *i, struct publication *p) /** * named_prepare_buf - allocate & initialize a publication message */ - static struct sk_buff *named_prepare_buf(u32 type, u32 size, u32 dest) { struct sk_buff *buf = tipc_buf_acquire(INT_H_SIZE + size); @@ -126,14 +148,16 @@ static void named_cluster_distribute(struct sk_buff *buf) /** * tipc_named_publish - tell other nodes about a new publication by this node */ - void tipc_named_publish(struct publication *publ) { struct sk_buff *buf; struct distr_item *item; - list_add_tail(&publ->local_list, &publ_root); - publ_cnt++; + list_add_tail(&publ->local_list, &publ_lists[publ->scope]->list); + publ_lists[publ->scope]->size++; + + if (publ->scope == TIPC_NODE_SCOPE) + return; buf = named_prepare_buf(PUBLICATION, ITEM_SIZE, 0); if (!buf) { @@ -149,14 +173,16 @@ void tipc_named_publish(struct publication *publ) /** * tipc_named_withdraw - tell other nodes about a withdrawn publication by this node */ - void tipc_named_withdraw(struct publication *publ) { struct sk_buff *buf; struct distr_item *item; list_del(&publ->local_list); - publ_cnt--; + publ_lists[publ->scope]->size--; + + if (publ->scope == TIPC_NODE_SCOPE) + return; buf = named_prepare_buf(WITHDRAWAL, ITEM_SIZE, 0); if (!buf) { @@ -169,25 +195,51 @@ void tipc_named_withdraw(struct publication *publ) named_cluster_distribute(buf); } +/* + * named_distribute - prepare name info for bulk distribution to another node + */ +static void named_distribute(struct list_head *message_list, u32 node, + struct publ_list *pls, u32 max_item_buf) +{ + struct publication *publ; + struct sk_buff *buf = NULL; + struct distr_item *item = NULL; + u32 left = 0; + u32 rest = pls->size * ITEM_SIZE; + + list_for_each_entry(publ, &pls->list, local_list) { + if (!buf) { + left = (rest <= max_item_buf) ? rest : max_item_buf; + rest -= left; + buf = named_prepare_buf(PUBLICATION, left, node); + if (!buf) { + warn("Bulk publication failure\n"); + return; + } + item = (struct distr_item *)msg_data(buf_msg(buf)); + } + publ_to_item(item, publ); + item++; + left -= ITEM_SIZE; + if (!left) { + list_add_tail((struct list_head *)buf, message_list); + buf = NULL; + } + } +} + /** * tipc_named_node_up - tell specified node about all publications by this node */ - void tipc_named_node_up(unsigned long nodearg) { struct tipc_node *n_ptr; struct tipc_link *l_ptr; - struct publication *publ; - struct distr_item *item = NULL; - struct sk_buff *buf = NULL; struct list_head message_list; u32 node = (u32)nodearg; - u32 left = 0; - u32 rest; u32 max_item_buf = 0; /* compute maximum amount of publication data to send per message */ - read_lock_bh(&tipc_net_lock); n_ptr = tipc_node_find(node); if (n_ptr) { @@ -203,32 +255,11 @@ void tipc_named_node_up(unsigned long nodearg) return; /* create list of publication messages, then send them as a unit */ - INIT_LIST_HEAD(&message_list); read_lock_bh(&tipc_nametbl_lock); - rest = publ_cnt * ITEM_SIZE; - - list_for_each_entry(publ, &publ_root, local_list) { - if (!buf) { - left = (rest <= max_item_buf) ? rest : max_item_buf; - rest -= left; - buf = named_prepare_buf(PUBLICATION, left, node); - if (!buf) { - warn("Bulk publication distribution failure\n"); - goto exit; - } - item = (struct distr_item *)msg_data(buf_msg(buf)); - } - publ_to_item(item, publ); - item++; - left -= ITEM_SIZE; - if (!left) { - list_add_tail((struct list_head *)buf, &message_list); - buf = NULL; - } - } -exit: + named_distribute(&message_list, node, &publ_cluster, max_item_buf); + named_distribute(&message_list, node, &publ_zone, max_item_buf); read_unlock_bh(&tipc_nametbl_lock); tipc_link_send_names(&message_list, (u32)node); @@ -240,7 +271,6 @@ exit: * Invoked for each publication issued by a newly failed node. * Removes publication structure from name table & deletes it. */ - static void named_purge_publ(struct publication *publ) { struct publication *p; @@ -264,7 +294,6 @@ static void named_purge_publ(struct publication *publ) /** * tipc_named_recv - process name table update message sent by another node */ - void tipc_named_recv(struct sk_buff *buf) { struct publication *publ; @@ -316,21 +345,22 @@ void tipc_named_recv(struct sk_buff *buf) } /** - * tipc_named_reinit - re-initialize local publication list + * tipc_named_reinit - re-initialize local publications * * This routine is called whenever TIPC networking is enabled. - * All existing publications by this node that have "cluster" or "zone" scope - * are updated to reflect the node's new network address. + * All name table entries published by this node are updated to reflect + * the node's new network address. */ - void tipc_named_reinit(void) { struct publication *publ; + int scope; write_lock_bh(&tipc_nametbl_lock); - list_for_each_entry(publ, &publ_root, local_list) - publ->node = tipc_own_addr; + for (scope = TIPC_ZONE_SCOPE; scope <= TIPC_NODE_SCOPE; scope++) + list_for_each_entry(publ, &publ_lists[scope]->list, local_list) + publ->node = tipc_own_addr; write_unlock_bh(&tipc_nametbl_lock); } diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index c6a1ae36952..010f24a59da 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -56,7 +56,6 @@ static int tipc_nametbl_size = 1024; /* must be a power of 2 */ * publications of the associated name sequence belong to it. * (The cluster and node lists may be empty.) */ - struct name_info { struct list_head node_list; struct list_head cluster_list; @@ -72,7 +71,6 @@ struct name_info { * @upper: name sequence upper bound * @info: pointer to name sequence publication info */ - struct sub_seq { u32 lower; u32 upper; @@ -90,7 +88,6 @@ struct sub_seq { * @subscriptions: list of subscriptions for this 'type' * @lock: spinlock controlling access to publication lists of all sub-sequences */ - struct name_seq { u32 type; struct sub_seq *sseqs; @@ -107,7 +104,6 @@ struct name_seq { * accessed via hashing on 'type'; name sequence lists are *not* sorted * @local_publ_count: number of publications issued by this node */ - struct name_table { struct hlist_head *types; u32 local_publ_count; @@ -124,7 +120,6 @@ static int hash(int x) /** * publ_create - create a publication structure */ - static struct publication *publ_create(u32 type, u32 lower, u32 upper, u32 scope, u32 node, u32 port_ref, u32 key) @@ -151,7 +146,6 @@ static struct publication *publ_create(u32 type, u32 lower, u32 upper, /** * tipc_subseq_alloc - allocate a specified number of sub-sequence structures */ - static struct sub_seq *tipc_subseq_alloc(u32 cnt) { struct sub_seq *sseq = kcalloc(cnt, sizeof(struct sub_seq), GFP_ATOMIC); @@ -163,7 +157,6 @@ static struct sub_seq *tipc_subseq_alloc(u32 cnt) * * Allocates a single sub-sequence structure and sets it to all 0's. */ - static struct name_seq *tipc_nameseq_create(u32 type, struct hlist_head *seq_head) { struct name_seq *nseq = kzalloc(sizeof(*nseq), GFP_ATOMIC); @@ -186,12 +179,23 @@ static struct name_seq *tipc_nameseq_create(u32 type, struct hlist_head *seq_hea return nseq; } -/** +/* + * nameseq_delete_empty - deletes a name sequence structure if now unused + */ +static void nameseq_delete_empty(struct name_seq *seq) +{ + if (!seq->first_free && list_empty(&seq->subscriptions)) { + hlist_del_init(&seq->ns_list); + kfree(seq->sseqs); + kfree(seq); + } +} + +/* * nameseq_find_subseq - find sub-sequence (if any) matching a name instance * * Very time-critical, so binary searches through sub-sequence array. */ - static struct sub_seq *nameseq_find_subseq(struct name_seq *nseq, u32 instance) { @@ -221,7 +225,6 @@ static struct sub_seq *nameseq_find_subseq(struct name_seq *nseq, * * Note: Similar to binary search code for locating a sub-sequence. */ - static u32 nameseq_locate_subseq(struct name_seq *nseq, u32 instance) { struct sub_seq *sseqs = nseq->sseqs; @@ -242,9 +245,8 @@ static u32 nameseq_locate_subseq(struct name_seq *nseq, u32 instance) } /** - * tipc_nameseq_insert_publ - + * tipc_nameseq_insert_publ */ - static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, u32 type, u32 lower, u32 upper, u32 scope, u32 node, u32 port, u32 key) @@ -260,7 +262,6 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, if (sseq) { /* Lower end overlaps existing entry => need an exact match */ - if ((sseq->lower != lower) || (sseq->upper != upper)) { warn("Cannot publish {%u,%u,%u}, overlap error\n", type, lower, upper); @@ -280,11 +281,9 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, struct sub_seq *freesseq; /* Find where lower end should be inserted */ - inspos = nameseq_locate_subseq(nseq, lower); /* Fail if upper end overlaps into an existing entry */ - if ((inspos < nseq->first_free) && (upper >= nseq->sseqs[inspos].lower)) { warn("Cannot publish {%u,%u,%u}, overlap error\n", @@ -293,7 +292,6 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, } /* Ensure there is space for new sub-sequence */ - if (nseq->first_free == nseq->alloc) { struct sub_seq *sseqs = tipc_subseq_alloc(nseq->alloc * 2); @@ -321,7 +319,6 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, INIT_LIST_HEAD(&info->zone_list); /* Insert new sub-sequence */ - sseq = &nseq->sseqs[inspos]; freesseq = &nseq->sseqs[nseq->first_free]; memmove(sseq + 1, sseq, (freesseq - sseq) * sizeof(*sseq)); @@ -333,8 +330,7 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, created_subseq = 1; } - /* Insert a publication: */ - + /* Insert a publication */ publ = publ_create(type, lower, upper, scope, node, port, key); if (!publ) return NULL; @@ -347,14 +343,12 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, info->cluster_list_size++; } - if (node == tipc_own_addr) { + if (in_own_node(node)) { list_add(&publ->node_list, &info->node_list); info->node_list_size++; } - /* - * Any subscriptions waiting for notification? - */ + /* Any subscriptions waiting for notification? */ list_for_each_entry_safe(s, st, &nseq->subscriptions, nameseq_list) { tipc_subscr_report_overlap(s, publ->lower, @@ -368,7 +362,7 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, } /** - * tipc_nameseq_remove_publ - + * tipc_nameseq_remove_publ * * NOTE: There may be cases where TIPC is asked to remove a publication * that is not in the name table. For example, if another node issues a @@ -378,7 +372,6 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, * A failed withdraw request simply returns a failure indication and lets the * caller issue any error or warning messages associated with such a problem. */ - static struct publication *tipc_nameseq_remove_publ(struct name_seq *nseq, u32 inst, u32 node, u32 ref, u32 key) { @@ -395,7 +388,6 @@ static struct publication *tipc_nameseq_remove_publ(struct name_seq *nseq, u32 i info = sseq->info; /* Locate publication, if it exists */ - list_for_each_entry(publ, &info->zone_list, zone_list) { if ((publ->key == key) && (publ->ref == ref) && (!publ->node || (publ->node == node))) @@ -405,26 +397,22 @@ static struct publication *tipc_nameseq_remove_publ(struct name_seq *nseq, u32 i found: /* Remove publication from zone scope list */ - list_del(&publ->zone_list); info->zone_list_size--; /* Remove publication from cluster scope list, if present */ - if (in_own_cluster(node)) { list_del(&publ->cluster_list); info->cluster_list_size--; } /* Remove publication from node scope list, if present */ - - if (node == tipc_own_addr) { + if (in_own_node(node)) { list_del(&publ->node_list); info->node_list_size--; } /* Contract subseq list if no more publications for that subseq */ - if (list_empty(&info->zone_list)) { kfree(info); free = &nseq->sseqs[nseq->first_free--]; @@ -433,7 +421,6 @@ found: } /* Notify any waiting subscriptions */ - list_for_each_entry_safe(s, st, &nseq->subscriptions, nameseq_list) { tipc_subscr_report_overlap(s, publ->lower, @@ -452,7 +439,6 @@ found: * the prescribed number of events if there is any sub- * sequence overlapping with the requested sequence */ - static void tipc_nameseq_subscribe(struct name_seq *nseq, struct tipc_subscription *s) { @@ -504,9 +490,10 @@ struct publication *tipc_nametbl_insert_publ(u32 type, u32 lower, u32 upper, { struct name_seq *seq = nametbl_find_seq(type); - if (lower > upper) { - warn("Failed to publish illegal {%u,%u,%u}\n", - type, lower, upper); + if ((scope < TIPC_ZONE_SCOPE) || (scope > TIPC_NODE_SCOPE) || + (lower > upper)) { + dbg("Failed to publish illegal {%u,%u,%u} with scope %u\n", + type, lower, upper, scope); return NULL; } @@ -529,12 +516,7 @@ struct publication *tipc_nametbl_remove_publ(u32 type, u32 lower, return NULL; publ = tipc_nameseq_remove_publ(seq, lower, node, ref, key); - - if (!seq->first_free && list_empty(&seq->subscriptions)) { - hlist_del_init(&seq->ns_list); - kfree(seq->sseqs); - kfree(seq); - } + nameseq_delete_empty(seq); return publ; } @@ -551,7 +533,6 @@ struct publication *tipc_nametbl_remove_publ(u32 type, u32 lower, * - if name translation is attempted and fails, sets 'destnode' to 0 * and returns 0 */ - u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode) { struct sub_seq *sseq; @@ -574,7 +555,7 @@ u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode) spin_lock_bh(&seq->lock); info = sseq->info; - /* Closest-First Algorithm: */ + /* Closest-First Algorithm */ if (likely(!*destnode)) { if (!list_empty(&info->node_list)) { publ = list_first_entry(&info->node_list, @@ -597,14 +578,14 @@ u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode) } } - /* Round-Robin Algorithm: */ + /* Round-Robin Algorithm */ else if (*destnode == tipc_own_addr) { if (list_empty(&info->node_list)) goto no_match; publ = list_first_entry(&info->node_list, struct publication, node_list); list_move_tail(&publ->node_list, &info->node_list); - } else if (in_own_cluster(*destnode)) { + } else if (in_own_cluster_exact(*destnode)) { if (list_empty(&info->cluster_list)) goto no_match; publ = list_first_entry(&info->cluster_list, struct publication, @@ -638,7 +619,6 @@ not_found: * * Returns non-zero if any off-node ports overlap */ - int tipc_nametbl_mc_translate(u32 type, u32 lower, u32 upper, u32 limit, struct tipc_port_list *dports) { @@ -682,7 +662,6 @@ exit: /* * tipc_nametbl_publish - add name publication to network name tables */ - struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper, u32 scope, u32 port_ref, u32 key) { @@ -695,11 +674,12 @@ struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper, } write_lock_bh(&tipc_nametbl_lock); - table.local_publ_count++; publ = tipc_nametbl_insert_publ(type, lower, upper, scope, tipc_own_addr, port_ref, key); - if (publ && (scope != TIPC_NODE_SCOPE)) + if (likely(publ)) { + table.local_publ_count++; tipc_named_publish(publ); + } write_unlock_bh(&tipc_nametbl_lock); return publ; } @@ -707,7 +687,6 @@ struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper, /** * tipc_nametbl_withdraw - withdraw name publication from network name tables */ - int tipc_nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key) { struct publication *publ; @@ -716,8 +695,7 @@ int tipc_nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key) publ = tipc_nametbl_remove_publ(type, lower, tipc_own_addr, ref, key); if (likely(publ)) { table.local_publ_count--; - if (publ->scope != TIPC_NODE_SCOPE) - tipc_named_withdraw(publ); + tipc_named_withdraw(publ); write_unlock_bh(&tipc_nametbl_lock); list_del_init(&publ->pport_list); kfree(publ); @@ -733,7 +711,6 @@ int tipc_nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key) /** * tipc_nametbl_subscribe - add a subscription object to the name table */ - void tipc_nametbl_subscribe(struct tipc_subscription *s) { u32 type = s->seq.type; @@ -757,7 +734,6 @@ void tipc_nametbl_subscribe(struct tipc_subscription *s) /** * tipc_nametbl_unsubscribe - remove a subscription object from name table */ - void tipc_nametbl_unsubscribe(struct tipc_subscription *s) { struct name_seq *seq; @@ -768,11 +744,7 @@ void tipc_nametbl_unsubscribe(struct tipc_subscription *s) spin_lock_bh(&seq->lock); list_del_init(&s->nameseq_list); spin_unlock_bh(&seq->lock); - if ((seq->first_free == 0) && list_empty(&seq->subscriptions)) { - hlist_del_init(&seq->ns_list); - kfree(seq->sseqs); - kfree(seq); - } + nameseq_delete_empty(seq); } write_unlock_bh(&tipc_nametbl_lock); } @@ -781,7 +753,6 @@ void tipc_nametbl_unsubscribe(struct tipc_subscription *s) /** * subseq_list: print specified sub-sequence contents into the given buffer */ - static void subseq_list(struct sub_seq *sseq, struct print_buf *buf, u32 depth, u32 index) { @@ -818,7 +789,6 @@ static void subseq_list(struct sub_seq *sseq, struct print_buf *buf, u32 depth, /** * nameseq_list: print specified name sequence contents into the given buffer */ - static void nameseq_list(struct name_seq *seq, struct print_buf *buf, u32 depth, u32 type, u32 lowbound, u32 upbound, u32 index) { @@ -849,7 +819,6 @@ static void nameseq_list(struct name_seq *seq, struct print_buf *buf, u32 depth, /** * nametbl_header - print name table header into the given buffer */ - static void nametbl_header(struct print_buf *buf, u32 depth) { const char *header[] = { @@ -871,7 +840,6 @@ static void nametbl_header(struct print_buf *buf, u32 depth) /** * nametbl_list - print specified name table contents into the given buffer */ - static void nametbl_list(struct print_buf *buf, u32 depth_info, u32 type, u32 lowbound, u32 upbound) { @@ -970,7 +938,6 @@ void tipc_nametbl_stop(void) return; /* Verify name table is empty, then release it */ - write_lock_bh(&tipc_nametbl_lock); for (i = 0; i < tipc_nametbl_size; i++) { if (!hlist_empty(&table.types[i])) @@ -980,4 +947,3 @@ void tipc_nametbl_stop(void) table.types = NULL; write_unlock_bh(&tipc_nametbl_lock); } - diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index 207d59ebf84..71cb4dc712d 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -45,10 +45,8 @@ struct tipc_port_list; /* * TIPC name types reserved for internal TIPC use (both current and planned) */ - #define TIPC_ZM_SRV 3 /* zone master service name type */ - /** * struct publication - info about a published (name or) name sequence * @type: name sequence type @@ -67,7 +65,6 @@ struct tipc_port_list; * * Note that the node list, cluster list, and zone list are circular lists. */ - struct publication { u32 type; u32 lower; diff --git a/net/tipc/net.c b/net/tipc/net.c index d4531b07076..7c236c89cf5 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -175,17 +175,14 @@ int tipc_net_start(u32 addr) { char addr_string[16]; - tipc_subscr_stop(); - tipc_cfg_stop(); - + write_lock_bh(&tipc_net_lock); tipc_own_addr = addr; tipc_named_reinit(); tipc_port_reinit(); - tipc_bclink_init(); + write_unlock_bh(&tipc_net_lock); - tipc_k_signal((Handler)tipc_subscr_start, 0); - tipc_k_signal((Handler)tipc_cfg_init, 0); + tipc_cfg_reinit(); info("Started in network mode\n"); info("Own node address %s, network identity %u\n", diff --git a/net/tipc/node.c b/net/tipc/node.c index a34cabc2c43..d4fd341e6e0 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -58,7 +58,7 @@ static atomic_t tipc_num_links = ATOMIC_INIT(0); * entries has been chosen so that no hash chain exceeds 8 nodes and will * usually be much smaller (typically only a single node). */ -static inline unsigned int tipc_hashfn(u32 addr) +static unsigned int tipc_hashfn(u32 addr) { return addr & (NODE_HTABLE_SIZE - 1); } @@ -66,13 +66,12 @@ static inline unsigned int tipc_hashfn(u32 addr) /* * tipc_node_find - locate specified node object, if it exists */ - struct tipc_node *tipc_node_find(u32 addr) { struct tipc_node *node; struct hlist_node *pos; - if (unlikely(!in_own_cluster(addr))) + if (unlikely(!in_own_cluster_exact(addr))) return NULL; hlist_for_each_entry(node, pos, &node_htable[tipc_hashfn(addr)], hash) { @@ -91,7 +90,6 @@ struct tipc_node *tipc_node_find(u32 addr) * time. (It would be preferable to switch to holding net_lock in write mode, * but this is a non-trivial change.) */ - struct tipc_node *tipc_node_create(u32 addr) { struct tipc_node *n_ptr, *temp_node; @@ -142,13 +140,11 @@ void tipc_node_delete(struct tipc_node *n_ptr) tipc_num_nodes--; } - /** * tipc_node_link_up - handle addition of link * * Link becomes active (alone or shared) or standby, depending on its priority. */ - void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr) { struct tipc_link **active = &n_ptr->active_links[0]; @@ -181,7 +177,6 @@ void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr) /** * node_select_active_links - select active link */ - static void node_select_active_links(struct tipc_node *n_ptr) { struct tipc_link **active = &n_ptr->active_links[0]; @@ -209,7 +204,6 @@ static void node_select_active_links(struct tipc_node *n_ptr) /** * tipc_node_link_down - handle loss of link */ - void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr) { struct tipc_link **active; @@ -300,7 +294,6 @@ static void node_lost_contact(struct tipc_node *n_ptr) tipc_addr_string_fill(addr_string, n_ptr->addr)); /* Flush broadcast link info associated with lost node */ - if (n_ptr->bclink.supported) { while (n_ptr->bclink.deferred_head) { struct sk_buff *buf = n_ptr->bclink.deferred_head; @@ -334,7 +327,6 @@ static void node_lost_contact(struct tipc_node *n_ptr) tipc_nodesub_notify(n_ptr); /* Prevent re-contact with node until cleanup is done */ - n_ptr->block_setup = WAIT_PEER_DOWN | WAIT_NAMES_GONE; tipc_k_signal((Handler)node_name_purge_complete, n_ptr->addr); } @@ -362,7 +354,6 @@ struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space) } /* For now, get space for all other nodes */ - payload_size = TLV_SPACE(sizeof(node_info)) * tipc_num_nodes; if (payload_size > 32768u) { read_unlock_bh(&tipc_net_lock); @@ -376,7 +367,6 @@ struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space) } /* Add TLVs for all nodes in scope */ - list_for_each_entry(n_ptr, &tipc_node_list, list) { if (!tipc_in_scope(domain, n_ptr->addr)) continue; @@ -412,7 +402,6 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space) read_lock_bh(&tipc_net_lock); /* Get space for all unicast links + broadcast link */ - payload_size = TLV_SPACE(sizeof(link_info)) * (atomic_read(&tipc_num_links) + 1); if (payload_size > 32768u) { @@ -427,14 +416,12 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space) } /* Add TLV for broadcast link */ - link_info.dest = htonl(tipc_cluster_mask(tipc_own_addr)); link_info.up = htonl(1); strlcpy(link_info.str, tipc_bclink_name, TIPC_MAX_LINK_NAME); tipc_cfg_append_tlv(buf, TIPC_TLV_LINK_INFO, &link_info, sizeof(link_info)); /* Add TLVs for any other links in scope */ - list_for_each_entry(n_ptr, &tipc_node_list, list) { u32 i; diff --git a/net/tipc/node.h b/net/tipc/node.h index 72561c971d6..cfcaf4d6e48 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -48,7 +48,6 @@ #define INVALID_NODE_SIG 0x10000 /* Flags used to block (re)establishment of contact with a neighboring node */ - #define WAIT_PEER_DOWN 0x0001 /* wait to see that peer's links are down */ #define WAIT_NAMES_GONE 0x0002 /* wait for peer's publications to be purged */ #define WAIT_NODE_DOWN 0x0004 /* wait until peer node is declared down */ @@ -79,7 +78,6 @@ * @deferred_tail: newest OOS b'cast message received from node * @defragm: list of partially reassembled b'cast message fragments from node */ - struct tipc_node { u32 addr; spinlock_t lock; diff --git a/net/tipc/node_subscr.c b/net/tipc/node_subscr.c index c3c2815ae63..7a27344108f 100644 --- a/net/tipc/node_subscr.c +++ b/net/tipc/node_subscr.c @@ -41,11 +41,10 @@ /** * tipc_nodesub_subscribe - create "node down" subscription for specified node */ - void tipc_nodesub_subscribe(struct tipc_node_subscr *node_sub, u32 addr, void *usr_handle, net_ev_handler handle_down) { - if (addr == tipc_own_addr) { + if (in_own_node(addr)) { node_sub->node = NULL; return; } @@ -66,7 +65,6 @@ void tipc_nodesub_subscribe(struct tipc_node_subscr *node_sub, u32 addr, /** * tipc_nodesub_unsubscribe - cancel "node down" subscription (if any) */ - void tipc_nodesub_unsubscribe(struct tipc_node_subscr *node_sub) { if (!node_sub->node) @@ -82,7 +80,6 @@ void tipc_nodesub_unsubscribe(struct tipc_node_subscr *node_sub) * * Note: node is locked by caller */ - void tipc_nodesub_notify(struct tipc_node *node) { struct tipc_node_subscr *ns; diff --git a/net/tipc/node_subscr.h b/net/tipc/node_subscr.h index 4bc2ca0867a..c95d20727de 100644 --- a/net/tipc/node_subscr.h +++ b/net/tipc/node_subscr.h @@ -48,7 +48,6 @@ typedef void (*net_ev_handler) (void *usr_handle); * @usr_handle: argument to pass to routine when node fails * @nodesub_list: adjacent entries in list of subscriptions for the node */ - struct tipc_node_subscr { struct tipc_node *node; net_ev_handler handle_node_down; diff --git a/net/tipc/port.c b/net/tipc/port.c index 94d2904cce6..2ad37a4db37 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -69,10 +69,30 @@ static u32 port_peerport(struct tipc_port *p_ptr) return msg_destport(&p_ptr->phdr); } +/* + * tipc_port_peer_msg - verify message was sent by connected port's peer + * + * Handles cases where the node's network address has changed from + * the default of <0.0.0> to its configured setting. + */ +int tipc_port_peer_msg(struct tipc_port *p_ptr, struct tipc_msg *msg) +{ + u32 peernode; + u32 orignode; + + if (msg_origport(msg) != port_peerport(p_ptr)) + return 0; + + orignode = msg_orignode(msg); + peernode = port_peernode(p_ptr); + return (orignode == peernode) || + (!orignode && (peernode == tipc_own_addr)) || + (!peernode && (orignode == tipc_own_addr)); +} + /** * tipc_multicast - send a multicast message to local and remote destinations */ - int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, u32 num_sect, struct iovec const *msg_sect, unsigned int total_len) @@ -89,7 +109,6 @@ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, return -EINVAL; /* Create multicast message */ - hdr = &oport->phdr; msg_set_type(hdr, TIPC_MCAST_MSG); msg_set_lookup_scope(hdr, TIPC_CLUSTER_SCOPE); @@ -105,12 +124,10 @@ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, return res; /* Figure out where to send multicast message */ - ext_targets = tipc_nametbl_mc_translate(seq->type, seq->lower, seq->upper, TIPC_NODE_SCOPE, &dports); /* Send message to destinations (duplicate it only if necessary) */ - if (ext_targets) { if (dports.count != 0) { ibuf = skb_copy(buf, GFP_ATOMIC); @@ -141,7 +158,6 @@ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, * * If there is no port list, perform a lookup to create one */ - void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp) { struct tipc_msg *msg; @@ -152,7 +168,6 @@ void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp) msg = buf_msg(buf); /* Create destination port list, if one wasn't supplied */ - if (dp == NULL) { tipc_nametbl_mc_translate(msg_nametype(msg), msg_namelower(msg), @@ -163,7 +178,6 @@ void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp) } /* Deliver a copy of message to each destination port */ - if (dp->count != 0) { msg_set_destnode(msg, tipc_own_addr); if (dp->count == 1) { @@ -196,7 +210,6 @@ exit: * * Returns pointer to (locked) TIPC port, or NULL if unable to create it */ - struct tipc_port *tipc_createport_raw(void *usr_handle, u32 (*dispatcher)(struct tipc_port *, struct sk_buff *), void (*wakeup)(struct tipc_port *), @@ -221,18 +234,24 @@ struct tipc_port *tipc_createport_raw(void *usr_handle, p_ptr->usr_handle = usr_handle; p_ptr->max_pkt = MAX_PKT_DEFAULT; p_ptr->ref = ref; - msg = &p_ptr->phdr; - tipc_msg_init(msg, importance, TIPC_NAMED_MSG, NAMED_H_SIZE, 0); - msg_set_origport(msg, ref); INIT_LIST_HEAD(&p_ptr->wait_list); INIT_LIST_HEAD(&p_ptr->subscription.nodesub_list); p_ptr->dispatcher = dispatcher; p_ptr->wakeup = wakeup; p_ptr->user_port = NULL; k_init_timer(&p_ptr->timer, (Handler)port_timeout, ref); - spin_lock_bh(&tipc_port_list_lock); INIT_LIST_HEAD(&p_ptr->publications); INIT_LIST_HEAD(&p_ptr->port_list); + + /* + * Must hold port list lock while initializing message header template + * to ensure a change to node's own network address doesn't result + * in template containing out-dated network address information + */ + spin_lock_bh(&tipc_port_list_lock); + msg = &p_ptr->phdr; + tipc_msg_init(msg, importance, TIPC_NAMED_MSG, NAMED_H_SIZE, 0); + msg_set_origport(msg, ref); list_add_tail(&p_ptr->port_list, &ports); spin_unlock_bh(&tipc_port_list_lock); return p_ptr; @@ -361,7 +380,6 @@ int tipc_reject_msg(struct sk_buff *buf, u32 err) u32 rmsg_sz; /* discard rejected message if it shouldn't be returned to sender */ - if (WARN(!msg_isdata(msg), "attempt to reject message with user=%u", msg_user(msg))) { dump_stack(); @@ -374,7 +392,6 @@ int tipc_reject_msg(struct sk_buff *buf, u32 err) * construct returned message by copying rejected message header and * data (or subset), then updating header fields that need adjusting */ - hdr_sz = msg_hdr_sz(msg); rmsg_sz = hdr_sz + min_t(u32, data_sz, MAX_REJECT_SIZE); @@ -413,9 +430,8 @@ int tipc_reject_msg(struct sk_buff *buf, u32 err) } /* send returned message & dispose of rejected message */ - src_node = msg_prevnode(msg); - if (src_node == tipc_own_addr) + if (in_own_node(src_node)) tipc_port_recv_msg(rbuf); else tipc_link_send(rbuf, src_node, msg_link_selector(rmsg)); @@ -519,25 +535,20 @@ void tipc_port_recv_proto_msg(struct sk_buff *buf) struct tipc_msg *msg = buf_msg(buf); struct tipc_port *p_ptr; struct sk_buff *r_buf = NULL; - u32 orignode = msg_orignode(msg); - u32 origport = msg_origport(msg); u32 destport = msg_destport(msg); int wakeable; /* Validate connection */ - p_ptr = tipc_port_lock(destport); - if (!p_ptr || !p_ptr->connected || - (port_peernode(p_ptr) != orignode) || - (port_peerport(p_ptr) != origport)) { + if (!p_ptr || !p_ptr->connected || !tipc_port_peer_msg(p_ptr, msg)) { r_buf = tipc_buf_acquire(BASIC_H_SIZE); if (r_buf) { msg = buf_msg(r_buf); tipc_msg_init(msg, TIPC_HIGH_IMPORTANCE, TIPC_CONN_MSG, - BASIC_H_SIZE, orignode); + BASIC_H_SIZE, msg_orignode(msg)); msg_set_errcode(msg, TIPC_ERR_NO_PORT); msg_set_origport(msg, destport); - msg_set_destport(msg, origport); + msg_set_destport(msg, msg_origport(msg)); } if (p_ptr) tipc_port_unlock(p_ptr); @@ -545,7 +556,6 @@ void tipc_port_recv_proto_msg(struct sk_buff *buf) } /* Process protocol message sent by peer */ - switch (msg_type(msg)) { case CONN_ACK: wakeable = tipc_port_congested(p_ptr) && p_ptr->congested && @@ -646,8 +656,6 @@ void tipc_port_reinit(void) spin_lock_bh(&tipc_port_list_lock); list_for_each_entry(p_ptr, &ports, port_list) { msg = &p_ptr->phdr; - if (msg_orignode(msg) == tipc_own_addr) - break; msg_set_prevnode(msg, tipc_own_addr); msg_set_orignode(msg, tipc_own_addr); } @@ -659,7 +667,6 @@ void tipc_port_reinit(void) * port_dispatcher_sigh(): Signal handler for messages destinated * to the tipc_port interface. */ - static void port_dispatcher_sigh(void *dummy) { struct sk_buff *buf; @@ -676,6 +683,7 @@ static void port_dispatcher_sigh(void *dummy) struct tipc_name_seq dseq; void *usr_handle; int connected; + int peer_invalid; int published; u32 message_type; @@ -696,6 +704,7 @@ static void port_dispatcher_sigh(void *dummy) up_ptr = p_ptr->user_port; usr_handle = up_ptr->usr_handle; connected = p_ptr->connected; + peer_invalid = connected && !tipc_port_peer_msg(p_ptr, msg); published = p_ptr->published; if (unlikely(msg_errcode(msg))) @@ -705,8 +714,6 @@ static void port_dispatcher_sigh(void *dummy) case TIPC_CONN_MSG:{ tipc_conn_msg_event cb = up_ptr->conn_msg_cb; - u32 peer_port = port_peerport(p_ptr); - u32 peer_node = port_peernode(p_ptr); u32 dsz; tipc_port_unlock(p_ptr); @@ -715,8 +722,7 @@ static void port_dispatcher_sigh(void *dummy) if (unlikely(!connected)) { if (tipc_connect2port(dref, &orig)) goto reject; - } else if ((msg_origport(msg) != peer_port) || - (msg_orignode(msg) != peer_node)) + } else if (peer_invalid) goto reject; dsz = msg_data_sz(msg); if (unlikely(dsz && @@ -768,14 +774,9 @@ err: case TIPC_CONN_MSG:{ tipc_conn_shutdown_event cb = up_ptr->conn_err_cb; - u32 peer_port = port_peerport(p_ptr); - u32 peer_node = port_peernode(p_ptr); tipc_port_unlock(p_ptr); - if (!cb || !connected) - break; - if ((msg_origport(msg) != peer_port) || - (msg_orignode(msg) != peer_node)) + if (!cb || !connected || peer_invalid) break; tipc_disconnect(dref); skb_pull(buf, msg_hdr_sz(msg)); @@ -826,7 +827,6 @@ reject: * port_dispatcher(): Dispatcher for messages destinated * to the tipc_port interface. Called with port locked. */ - static u32 port_dispatcher(struct tipc_port *dummy, struct sk_buff *buf) { buf->next = NULL; @@ -843,10 +843,8 @@ static u32 port_dispatcher(struct tipc_port *dummy, struct sk_buff *buf) } /* - * Wake up port after congestion: Called with port locked, - * + * Wake up port after congestion: Called with port locked */ - static void port_wakeup_sh(unsigned long ref) { struct tipc_port *p_ptr; @@ -892,7 +890,6 @@ void tipc_acknowledge(u32 ref, u32 ack) /* * tipc_createport(): user level call. */ - int tipc_createport(void *usr_handle, unsigned int importance, tipc_msg_err_event error_cb, @@ -901,7 +898,7 @@ int tipc_createport(void *usr_handle, tipc_msg_event msg_cb, tipc_named_msg_event named_msg_cb, tipc_conn_msg_event conn_msg_cb, - tipc_continue_event continue_event_cb,/* May be zero */ + tipc_continue_event continue_event_cb, /* May be zero */ u32 *portref) { struct user_port *up_ptr; @@ -975,10 +972,6 @@ int tipc_publish(u32 ref, unsigned int scope, struct tipc_name_seq const *seq) if (p_ptr->connected) goto exit; - if (seq->lower > seq->upper) - goto exit; - if ((scope < TIPC_ZONE_SCOPE) || (scope > TIPC_NODE_SCOPE)) - goto exit; key = ref + p_ptr->pub_count + 1; if (key == ref) { res = -EADDRINUSE; @@ -1078,7 +1071,6 @@ exit: * * Port must be locked. */ - int tipc_disconnect_port(struct tipc_port *tp_ptr) { int res; @@ -1099,7 +1091,6 @@ int tipc_disconnect_port(struct tipc_port *tp_ptr) * tipc_disconnect(): Disconnect port form peer. * This is a node local operation. */ - int tipc_disconnect(u32 ref) { struct tipc_port *p_ptr; @@ -1134,7 +1125,6 @@ int tipc_shutdown(u32 ref) /** * tipc_port_recv_msg - receive message from lower layer and deliver to port user */ - int tipc_port_recv_msg(struct sk_buff *buf) { struct tipc_port *p_ptr; @@ -1152,17 +1142,6 @@ int tipc_port_recv_msg(struct sk_buff *buf) /* validate destination & pass to port, otherwise reject message */ p_ptr = tipc_port_lock(destport); if (likely(p_ptr)) { - if (likely(p_ptr->connected)) { - if ((unlikely(msg_origport(msg) != - tipc_peer_port(p_ptr))) || - (unlikely(msg_orignode(msg) != - tipc_peer_node(p_ptr))) || - (unlikely(!msg_connected(msg)))) { - err = TIPC_ERR_NO_PORT; - tipc_port_unlock(p_ptr); - goto reject; - } - } err = p_ptr->dispatcher(p_ptr, buf); tipc_port_unlock(p_ptr); if (likely(!err)) @@ -1170,7 +1149,7 @@ int tipc_port_recv_msg(struct sk_buff *buf) } else { err = TIPC_ERR_NO_PORT; } -reject: + return tipc_reject_msg(buf, err); } @@ -1178,7 +1157,6 @@ reject: * tipc_port_recv_sections(): Concatenate and deliver sectioned * message for this node. */ - static int tipc_port_recv_sections(struct tipc_port *sender, unsigned int num_sect, struct iovec const *msg_sect, unsigned int total_len) @@ -1196,7 +1174,6 @@ static int tipc_port_recv_sections(struct tipc_port *sender, unsigned int num_se /** * tipc_send - send message sections on connection */ - int tipc_send(u32 ref, unsigned int num_sect, struct iovec const *msg_sect, unsigned int total_len) { @@ -1211,7 +1188,7 @@ int tipc_send(u32 ref, unsigned int num_sect, struct iovec const *msg_sect, p_ptr->congested = 1; if (!tipc_port_congested(p_ptr)) { destnode = port_peernode(p_ptr); - if (likely(destnode != tipc_own_addr)) + if (likely(!in_own_node(destnode))) res = tipc_link_send_sections_fast(p_ptr, msg_sect, num_sect, total_len, destnode); else @@ -1235,7 +1212,6 @@ int tipc_send(u32 ref, unsigned int num_sect, struct iovec const *msg_sect, /** * tipc_send2name - send message sections to port name */ - int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, unsigned int num_sect, struct iovec const *msg_sect, unsigned int total_len) @@ -1261,13 +1237,17 @@ int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, msg_set_destport(msg, destport); if (likely(destport || destnode)) { - if (likely(destnode == tipc_own_addr)) + if (likely(in_own_node(destnode))) res = tipc_port_recv_sections(p_ptr, num_sect, msg_sect, total_len); - else + else if (tipc_own_addr) res = tipc_link_send_sections_fast(p_ptr, msg_sect, num_sect, total_len, destnode); + else + res = tipc_port_reject_sections(p_ptr, msg, msg_sect, + num_sect, total_len, + TIPC_ERR_NO_NODE); if (likely(res != -ELINKCONG)) { if (res > 0) p_ptr->sent++; @@ -1285,7 +1265,6 @@ int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, /** * tipc_send2port - send message sections to port identity */ - int tipc_send2port(u32 ref, struct tipc_portid const *dest, unsigned int num_sect, struct iovec const *msg_sect, unsigned int total_len) @@ -1305,12 +1284,15 @@ int tipc_send2port(u32 ref, struct tipc_portid const *dest, msg_set_destport(msg, dest->ref); msg_set_hdr_sz(msg, BASIC_H_SIZE); - if (dest->node == tipc_own_addr) + if (in_own_node(dest->node)) res = tipc_port_recv_sections(p_ptr, num_sect, msg_sect, total_len); - else + else if (tipc_own_addr) res = tipc_link_send_sections_fast(p_ptr, msg_sect, num_sect, total_len, dest->node); + else + res = tipc_port_reject_sections(p_ptr, msg, msg_sect, num_sect, + total_len, TIPC_ERR_NO_NODE); if (likely(res != -ELINKCONG)) { if (res > 0) p_ptr->sent++; @@ -1325,7 +1307,6 @@ int tipc_send2port(u32 ref, struct tipc_portid const *dest, /** * tipc_send_buf2port - send message buffer to port identity */ - int tipc_send_buf2port(u32 ref, struct tipc_portid const *dest, struct sk_buff *buf, unsigned int dsz) { @@ -1349,7 +1330,7 @@ int tipc_send_buf2port(u32 ref, struct tipc_portid const *dest, skb_push(buf, BASIC_H_SIZE); skb_copy_to_linear_data(buf, msg, BASIC_H_SIZE); - if (dest->node == tipc_own_addr) + if (in_own_node(dest->node)) res = tipc_port_recv_msg(buf); else res = tipc_send_buf_fast(buf, dest->node); @@ -1362,4 +1343,3 @@ int tipc_send_buf2port(u32 ref, struct tipc_portid const *dest, return dsz; return -ELINKCONG; } - diff --git a/net/tipc/port.h b/net/tipc/port.h index 9b88531e5a6..98cbec9c453 100644 --- a/net/tipc/port.h +++ b/net/tipc/port.h @@ -81,7 +81,6 @@ typedef void (*tipc_continue_event) (void *usr_handle, u32 portref); * @ref: object reference to associated TIPC port * <various callback routines> */ - struct user_port { void *usr_handle; u32 ref; @@ -201,6 +200,7 @@ int tipc_shutdown(u32 ref); * The following routines require that the port be locked on entry */ int tipc_disconnect_port(struct tipc_port *tp_ptr); +int tipc_port_peer_msg(struct tipc_port *p_ptr, struct tipc_msg *msg); /* * TIPC messaging routines @@ -235,7 +235,6 @@ void tipc_port_reinit(void); /** * tipc_port_lock - lock port instance referred to and return its pointer */ - static inline struct tipc_port *tipc_port_lock(u32 ref) { return (struct tipc_port *)tipc_ref_lock(ref); @@ -246,7 +245,6 @@ static inline struct tipc_port *tipc_port_lock(u32 ref) * * Can use pointer instead of tipc_ref_unlock() since port is already locked. */ - static inline void tipc_port_unlock(struct tipc_port *p_ptr) { spin_unlock_bh(p_ptr->lock); @@ -257,16 +255,6 @@ static inline struct tipc_port *tipc_port_deref(u32 ref) return (struct tipc_port *)tipc_ref_deref(ref); } -static inline u32 tipc_peer_port(struct tipc_port *p_ptr) -{ - return msg_destport(&p_ptr->phdr); -} - -static inline u32 tipc_peer_node(struct tipc_port *p_ptr) -{ - return msg_destnode(&p_ptr->phdr); -} - static inline int tipc_port_congested(struct tipc_port *p_ptr) { return (p_ptr->sent - p_ptr->acked) >= (TIPC_FLOW_CONTROL_WIN * 2); diff --git a/net/tipc/ref.c b/net/tipc/ref.c index 9e37b7812c3..5cada0e38e0 100644 --- a/net/tipc/ref.c +++ b/net/tipc/ref.c @@ -43,7 +43,6 @@ * @lock: spinlock controlling access to object * @ref: reference value for object (combines instance & array index info) */ - struct reference { void *object; spinlock_t lock; @@ -60,7 +59,6 @@ struct reference { * @index_mask: bitmask for array index portion of reference values * @start_mask: initial value for instance value portion of reference values */ - struct ref_table { struct reference *entries; u32 capacity; @@ -96,7 +94,6 @@ static DEFINE_RWLOCK(ref_table_lock); /** * tipc_ref_table_init - create reference table for objects */ - int tipc_ref_table_init(u32 requested_size, u32 start) { struct reference *table; @@ -109,7 +106,6 @@ int tipc_ref_table_init(u32 requested_size, u32 start) /* do nothing */ ; /* allocate table & mark all entries as uninitialized */ - table = vzalloc(actual_size * sizeof(struct reference)); if (table == NULL) return -ENOMEM; @@ -128,7 +124,6 @@ int tipc_ref_table_init(u32 requested_size, u32 start) /** * tipc_ref_table_stop - destroy reference table for objects */ - void tipc_ref_table_stop(void) { if (!tipc_ref_table.entries) @@ -149,7 +144,6 @@ void tipc_ref_table_stop(void) * register a partially initialized object, without running the risk that * the object will be accessed before initialization is complete. */ - u32 tipc_ref_acquire(void *object, spinlock_t **lock) { u32 index; @@ -168,7 +162,6 @@ u32 tipc_ref_acquire(void *object, spinlock_t **lock) } /* take a free entry, if available; otherwise initialize a new entry */ - write_lock_bh(&ref_table_lock); if (tipc_ref_table.first_free) { index = tipc_ref_table.first_free; @@ -211,7 +204,6 @@ u32 tipc_ref_acquire(void *object, spinlock_t **lock) * Disallow future references to an object and free up the entry for re-use. * Note: The entry's spin_lock may still be busy after discard */ - void tipc_ref_discard(u32 ref) { struct reference *entry; @@ -242,12 +234,10 @@ void tipc_ref_discard(u32 ref) * mark entry as unused; increment instance part of entry's reference * to invalidate any subsequent references */ - entry->object = NULL; entry->ref = (ref & ~index_mask) + (index_mask + 1); /* append entry to free entry list */ - if (tipc_ref_table.first_free == 0) tipc_ref_table.first_free = index; else @@ -261,7 +251,6 @@ exit: /** * tipc_ref_lock - lock referenced object and return pointer to it */ - void *tipc_ref_lock(u32 ref) { if (likely(tipc_ref_table.entries)) { @@ -283,7 +272,6 @@ void *tipc_ref_lock(u32 ref) /** * tipc_ref_deref - return pointer referenced object (without locking it) */ - void *tipc_ref_deref(u32 ref) { if (likely(tipc_ref_table.entries)) { @@ -296,4 +284,3 @@ void *tipc_ref_deref(u32 ref) } return NULL; } - diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 29e957f6445..5577a447f53 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -123,7 +123,6 @@ static atomic_t tipc_queue_size = ATOMIC_INIT(0); * * Caller must hold socket lock */ - static void advance_rx_queue(struct sock *sk) { kfree_skb(__skb_dequeue(&sk->sk_receive_queue)); @@ -135,7 +134,6 @@ static void advance_rx_queue(struct sock *sk) * * Caller must hold socket lock */ - static void discard_rx_queue(struct sock *sk) { struct sk_buff *buf; @@ -151,7 +149,6 @@ static void discard_rx_queue(struct sock *sk) * * Caller must hold socket lock */ - static void reject_rx_queue(struct sock *sk) { struct sk_buff *buf; @@ -174,7 +171,6 @@ static void reject_rx_queue(struct sock *sk) * * Returns 0 on success, errno otherwise */ - static int tipc_create(struct net *net, struct socket *sock, int protocol, int kern) { @@ -184,7 +180,6 @@ static int tipc_create(struct net *net, struct socket *sock, int protocol, struct tipc_port *tp_ptr; /* Validate arguments */ - if (unlikely(protocol != 0)) return -EPROTONOSUPPORT; @@ -207,13 +202,11 @@ static int tipc_create(struct net *net, struct socket *sock, int protocol, } /* Allocate socket's protocol area */ - sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto); if (sk == NULL) return -ENOMEM; /* Allocate TIPC port for socket to use */ - tp_ptr = tipc_createport_raw(sk, &dispatch, &wakeupdispatch, TIPC_LOW_IMPORTANCE); if (unlikely(!tp_ptr)) { @@ -222,7 +215,6 @@ static int tipc_create(struct net *net, struct socket *sock, int protocol, } /* Finish initializing socket data structures */ - sock->ops = ops; sock->state = state; @@ -258,7 +250,6 @@ static int tipc_create(struct net *net, struct socket *sock, int protocol, * * Returns 0 on success, errno otherwise */ - static int release(struct socket *sock) { struct sock *sk = sock->sk; @@ -270,7 +261,6 @@ static int release(struct socket *sock) * Exit if socket isn't fully initialized (occurs when a failed accept() * releases a pre-allocated child socket that was never used) */ - if (sk == NULL) return 0; @@ -281,7 +271,6 @@ static int release(struct socket *sock) * Reject all unreceived messages, except on an active connection * (which disconnects locally & sends a 'FIN+' to peer) */ - while (sock->state != SS_DISCONNECTING) { buf = __skb_dequeue(&sk->sk_receive_queue); if (buf == NULL) @@ -303,15 +292,12 @@ static int release(struct socket *sock) * Delete TIPC port; this ensures no more messages are queued * (also disconnects an active connection & sends a 'FIN-' to peer) */ - res = tipc_deleteport(tport->ref); /* Discard any remaining (connection-based) messages in receive queue */ - discard_rx_queue(sk); /* Reject any messages that accumulated in backlog queue */ - sock->state = SS_DISCONNECTING; release_sock(sk); @@ -336,7 +322,6 @@ static int release(struct socket *sock) * NOTE: This routine doesn't need to take the socket lock since it doesn't * access any non-constant socket information. */ - static int bind(struct socket *sock, struct sockaddr *uaddr, int uaddr_len) { struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr; @@ -376,7 +361,6 @@ static int bind(struct socket *sock, struct sockaddr *uaddr, int uaddr_len) * accesses socket information that is unchanging (or which changes in * a completely predictable manner). */ - static int get_name(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len, int peer) { @@ -444,7 +428,6 @@ static int get_name(struct socket *sock, struct sockaddr *uaddr, * imply that the operation will succeed, merely that it should be performed * and will not block. */ - static unsigned int poll(struct file *file, struct socket *sock, poll_table *wait) { @@ -482,7 +465,6 @@ static unsigned int poll(struct file *file, struct socket *sock, * * Returns 0 if permission is granted, otherwise errno */ - static int dest_name_check(struct sockaddr_tipc *dest, struct msghdr *m) { struct tipc_cfg_msg_hdr hdr; @@ -518,7 +500,6 @@ static int dest_name_check(struct sockaddr_tipc *dest, struct msghdr *m) * * Returns the number of bytes sent on success, or errno otherwise */ - static int send_msg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t total_len) { @@ -535,7 +516,7 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, (dest->family != AF_TIPC))) return -EINVAL; if ((total_len > TIPC_MAX_USER_MSG_SIZE) || - (m->msg_iovlen > (unsigned)INT_MAX)) + (m->msg_iovlen > (unsigned int)INT_MAX)) return -EMSGSIZE; if (iocb) @@ -562,7 +543,6 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, } /* Abort any pending connection attempts (very unlikely) */ - reject_rx_queue(sk); } @@ -631,7 +611,6 @@ exit: * * Returns the number of bytes sent on success, or errno otherwise */ - static int send_packet(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t total_len) { @@ -642,12 +621,11 @@ static int send_packet(struct kiocb *iocb, struct socket *sock, int res; /* Handle implied connection establishment */ - if (unlikely(dest)) return send_msg(iocb, sock, m, total_len); if ((total_len > TIPC_MAX_USER_MSG_SIZE) || - (m->msg_iovlen > (unsigned)INT_MAX)) + (m->msg_iovlen > (unsigned int)INT_MAX)) return -EMSGSIZE; if (iocb) @@ -695,7 +673,6 @@ static int send_packet(struct kiocb *iocb, struct socket *sock, * Returns the number of bytes sent on success (or partial success), * or errno if no data sent */ - static int send_stream(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t total_len) { @@ -715,7 +692,6 @@ static int send_stream(struct kiocb *iocb, struct socket *sock, lock_sock(sk); /* Handle special cases where there is no connection */ - if (unlikely(sock->state != SS_CONNECTED)) { if (sock->state == SS_UNCONNECTED) { res = send_packet(NULL, sock, m, total_len); @@ -734,8 +710,8 @@ static int send_stream(struct kiocb *iocb, struct socket *sock, goto exit; } - if ((total_len > (unsigned)INT_MAX) || - (m->msg_iovlen > (unsigned)INT_MAX)) { + if ((total_len > (unsigned int)INT_MAX) || + (m->msg_iovlen > (unsigned int)INT_MAX)) { res = -EMSGSIZE; goto exit; } @@ -747,7 +723,6 @@ static int send_stream(struct kiocb *iocb, struct socket *sock, * (i.e. one large iovec entry), but could be improved to pass sets * of small iovec entries into send_packet(). */ - curr_iov = m->msg_iov; curr_iovlen = m->msg_iovlen; my_msg.msg_iov = &my_iov; @@ -796,7 +771,6 @@ exit: * * Returns 0 on success, errno otherwise */ - static int auto_connect(struct socket *sock, struct tipc_msg *msg) { struct tipc_sock *tsock = tipc_sk(sock->sk); @@ -821,7 +795,6 @@ static int auto_connect(struct socket *sock, struct tipc_msg *msg) * * Note: Address is not captured if not requested by receiver. */ - static void set_orig_addr(struct msghdr *m, struct tipc_msg *msg) { struct sockaddr_tipc *addr = (struct sockaddr_tipc *)m->msg_name; @@ -847,7 +820,6 @@ static void set_orig_addr(struct msghdr *m, struct tipc_msg *msg) * * Returns 0 if successful, otherwise errno */ - static int anc_data_recv(struct msghdr *m, struct tipc_msg *msg, struct tipc_port *tport) { @@ -861,7 +833,6 @@ static int anc_data_recv(struct msghdr *m, struct tipc_msg *msg, return 0; /* Optionally capture errored message object(s) */ - err = msg ? msg_errcode(msg) : 0; if (unlikely(err)) { anc_data[0] = err; @@ -878,7 +849,6 @@ static int anc_data_recv(struct msghdr *m, struct tipc_msg *msg, } /* Optionally capture message destination object */ - dest_type = msg ? msg_type(msg) : TIPC_DIRECT_MSG; switch (dest_type) { case TIPC_NAMED_MSG: @@ -923,7 +893,6 @@ static int anc_data_recv(struct msghdr *m, struct tipc_msg *msg, * * Returns size of returned message data, errno otherwise */ - static int recv_msg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t buf_len, int flags) { @@ -937,7 +906,6 @@ static int recv_msg(struct kiocb *iocb, struct socket *sock, int res; /* Catch invalid receive requests */ - if (unlikely(!buf_len)) return -EINVAL; @@ -952,7 +920,6 @@ static int recv_msg(struct kiocb *iocb, struct socket *sock, restart: /* Look for a message in receive queue; wait if necessary */ - while (skb_queue_empty(&sk->sk_receive_queue)) { if (sock->state == SS_DISCONNECTING) { res = -ENOTCONN; @@ -970,14 +937,12 @@ restart: } /* Look at first message in receive queue */ - buf = skb_peek(&sk->sk_receive_queue); msg = buf_msg(buf); sz = msg_data_sz(msg); err = msg_errcode(msg); /* Complete connection setup for an implied connect */ - if (unlikely(sock->state == SS_CONNECTING)) { res = auto_connect(sock, msg); if (res) @@ -985,24 +950,20 @@ restart: } /* Discard an empty non-errored message & try again */ - if ((!sz) && (!err)) { advance_rx_queue(sk); goto restart; } /* Capture sender's address (optional) */ - set_orig_addr(m, msg); /* Capture ancillary data (optional) */ - res = anc_data_recv(m, msg, tport); if (res) goto exit; /* Capture message data (if valid) & compute return value (always) */ - if (!err) { if (unlikely(buf_len < sz)) { sz = buf_len; @@ -1022,7 +983,6 @@ restart: } /* Consume received message (optional) */ - if (likely(!(flags & MSG_PEEK))) { if ((sock->state != SS_READY) && (++tport->conn_unacked >= TIPC_FLOW_CONTROL_WIN)) @@ -1046,7 +1006,6 @@ exit: * * Returns size of returned message data, errno otherwise */ - static int recv_stream(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t buf_len, int flags) { @@ -1062,7 +1021,6 @@ static int recv_stream(struct kiocb *iocb, struct socket *sock, int res = 0; /* Catch invalid receive attempts */ - if (unlikely(!buf_len)) return -EINVAL; @@ -1076,10 +1034,9 @@ static int recv_stream(struct kiocb *iocb, struct socket *sock, target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len); timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); -restart: +restart: /* Look for a message in receive queue; wait if necessary */ - while (skb_queue_empty(&sk->sk_receive_queue)) { if (sock->state == SS_DISCONNECTING) { res = -ENOTCONN; @@ -1097,21 +1054,18 @@ restart: } /* Look at first message in receive queue */ - buf = skb_peek(&sk->sk_receive_queue); msg = buf_msg(buf); sz = msg_data_sz(msg); err = msg_errcode(msg); /* Discard an empty non-errored message & try again */ - if ((!sz) && (!err)) { advance_rx_queue(sk); goto restart; } /* Optionally capture sender's address & ancillary data of first msg */ - if (sz_copied == 0) { set_orig_addr(m, msg); res = anc_data_recv(m, msg, tport); @@ -1120,7 +1074,6 @@ restart: } /* Capture message data (if valid) & compute return value (always) */ - if (!err) { u32 offset = (u32)(unsigned long)(TIPC_SKB_CB(buf)->handle); @@ -1152,7 +1105,6 @@ restart: } /* Consume received message (optional) */ - if (likely(!(flags & MSG_PEEK))) { if (unlikely(++tport->conn_unacked >= TIPC_FLOW_CONTROL_WIN)) tipc_acknowledge(tport->ref, tport->conn_unacked); @@ -1160,7 +1112,6 @@ restart: } /* Loop around if more data is required */ - if ((sz_copied < buf_len) && /* didn't get all requested data */ (!skb_queue_empty(&sk->sk_receive_queue) || (sz_copied < target)) && /* and more is ready or required */ @@ -1181,7 +1132,6 @@ exit: * * Returns 1 if queue is unable to accept message, 0 otherwise */ - static int rx_queue_full(struct tipc_msg *msg, u32 queue_size, u32 base) { u32 threshold; @@ -1214,7 +1164,6 @@ static int rx_queue_full(struct tipc_msg *msg, u32 queue_size, u32 base) * * Returns TIPC error status code (TIPC_OK if message is not to be rejected) */ - static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) { struct socket *sock = sk->sk_socket; @@ -1222,12 +1171,8 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) u32 recv_q_len; /* Reject message if it is wrong sort of message for socket */ - - /* - * WOULD IT BE BETTER TO JUST DISCARD THESE MESSAGES INSTEAD? - * "NO PORT" ISN'T REALLY THE RIGHT ERROR CODE, AND THERE MAY - * BE SECURITY IMPLICATIONS INHERENT IN REJECTING INVALID TRAFFIC - */ + if (msg_type(msg) > TIPC_DIRECT_MSG) + return TIPC_ERR_NO_PORT; if (sock->state == SS_READY) { if (msg_connected(msg)) @@ -1236,7 +1181,8 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) if (msg_mcast(msg)) return TIPC_ERR_NO_PORT; if (sock->state == SS_CONNECTED) { - if (!msg_connected(msg)) + if (!msg_connected(msg) || + !tipc_port_peer_msg(tipc_sk_port(sk), msg)) return TIPC_ERR_NO_PORT; } else if (sock->state == SS_CONNECTING) { if (!msg_connected(msg) && (msg_errcode(msg) == 0)) @@ -1253,7 +1199,6 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) } /* Reject message if there isn't room to queue it */ - recv_q_len = (u32)atomic_read(&tipc_queue_size); if (unlikely(recv_q_len >= OVERLOAD_LIMIT_BASE)) { if (rx_queue_full(msg, recv_q_len, OVERLOAD_LIMIT_BASE)) @@ -1266,13 +1211,11 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) } /* Enqueue message (finally!) */ - TIPC_SKB_CB(buf)->handle = 0; atomic_inc(&tipc_queue_size); __skb_queue_tail(&sk->sk_receive_queue, buf); /* Initiate connection termination for an incoming 'FIN' */ - if (unlikely(msg_errcode(msg) && (sock->state == SS_CONNECTED))) { sock->state = SS_DISCONNECTING; tipc_disconnect_port(tipc_sk_port(sk)); @@ -1292,7 +1235,6 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) * * Returns 0 */ - static int backlog_rcv(struct sock *sk, struct sk_buff *buf) { u32 res; @@ -1312,7 +1254,6 @@ static int backlog_rcv(struct sock *sk, struct sk_buff *buf) * * Returns TIPC error status code (TIPC_OK if message is not to be rejected) */ - static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf) { struct sock *sk = (struct sock *)tport->usr_handle; @@ -1324,12 +1265,11 @@ static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf) * This code is based on sk_receive_skb(), but must be distinct from it * since a TIPC-specific filter/reject mechanism is utilized */ - bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { res = filter_rcv(sk, buf); } else { - if (sk_add_backlog(sk, buf)) + if (sk_add_backlog(sk, buf, sk->sk_rcvbuf)) res = TIPC_ERR_OVERLOAD; else res = TIPC_OK; @@ -1345,7 +1285,6 @@ static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf) * * Called with port lock already taken. */ - static void wakeupdispatch(struct tipc_port *tport) { struct sock *sk = (struct sock *)tport->usr_handle; @@ -1363,7 +1302,6 @@ static void wakeupdispatch(struct tipc_port *tport) * * Returns 0 on success, errno otherwise */ - static int connect(struct socket *sock, struct sockaddr *dest, int destlen, int flags) { @@ -1378,21 +1316,18 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, lock_sock(sk); /* For now, TIPC does not allow use of connect() with DGRAM/RDM types */ - if (sock->state == SS_READY) { res = -EOPNOTSUPP; goto exit; } /* For now, TIPC does not support the non-blocking form of connect() */ - if (flags & O_NONBLOCK) { res = -EOPNOTSUPP; goto exit; } /* Issue Posix-compliant error code if socket is in the wrong state */ - if (sock->state == SS_LISTENING) { res = -EOPNOTSUPP; goto exit; @@ -1412,18 +1347,15 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, * Note: send_msg() validates the rest of the address fields, * so there's no need to do it here */ - if (dst->addrtype == TIPC_ADDR_MCAST) { res = -EINVAL; goto exit; } /* Reject any messages already in receive queue (very unlikely) */ - reject_rx_queue(sk); /* Send a 'SYN-' to destination */ - m.msg_name = dest; m.msg_namelen = destlen; res = send_msg(NULL, sock, &m, 0); @@ -1431,7 +1363,6 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, goto exit; /* Wait until an 'ACK' or 'RST' arrives, or a timeout occurs */ - timeout = tipc_sk(sk)->conn_timeout; release_sock(sk); res = wait_event_interruptible_timeout(*sk_sleep(sk), @@ -1476,7 +1407,6 @@ exit: * * Returns 0 on success, errno otherwise */ - static int listen(struct socket *sock, int len) { struct sock *sk = sock->sk; @@ -1503,7 +1433,6 @@ static int listen(struct socket *sock, int len) * * Returns 0 on success, errno otherwise */ - static int accept(struct socket *sock, struct socket *new_sock, int flags) { struct sock *sk = sock->sk; @@ -1546,11 +1475,9 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags) * Reject any stray messages received by new socket * before the socket lock was taken (very, very unlikely) */ - reject_rx_queue(new_sk); /* Connect new socket to it's peer */ - new_tsock->peer_name.ref = msg_origport(msg); new_tsock->peer_name.node = msg_orignode(msg); tipc_connect2port(new_ref, &new_tsock->peer_name); @@ -1566,7 +1493,6 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags) * Respond to 'SYN-' by discarding it & returning 'ACK'-. * Respond to 'SYN+' by queuing it on new socket. */ - if (!msg_data_sz(msg)) { struct msghdr m = {NULL,}; @@ -1592,7 +1518,6 @@ exit: * * Returns 0 on success, errno otherwise */ - static int shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; @@ -1609,8 +1534,8 @@ static int shutdown(struct socket *sock, int how) case SS_CONNECTING: case SS_CONNECTED: - /* Disconnect and send a 'FIN+' or 'FIN-' message to peer */ restart: + /* Disconnect and send a 'FIN+' or 'FIN-' message to peer */ buf = __skb_dequeue(&sk->sk_receive_queue); if (buf) { atomic_dec(&tipc_queue_size); @@ -1631,7 +1556,6 @@ restart: case SS_DISCONNECTING: /* Discard any unreceived messages; wake up sleeping tasks */ - discard_rx_queue(sk); if (waitqueue_active(sk_sleep(sk))) wake_up_interruptible(sk_sleep(sk)); @@ -1659,7 +1583,6 @@ restart: * * Returns 0 on success, errno otherwise */ - static int setsockopt(struct socket *sock, int lvl, int opt, char __user *ov, unsigned int ol) { @@ -1719,7 +1642,6 @@ static int setsockopt(struct socket *sock, * * Returns 0 on success, errno otherwise */ - static int getsockopt(struct socket *sock, int lvl, int opt, char __user *ov, int __user *ol) { @@ -1780,7 +1702,6 @@ static int getsockopt(struct socket *sock, /** * Protocol switches for the various types of TIPC sockets */ - static const struct proto_ops msg_ops = { .owner = THIS_MODULE, .family = AF_TIPC, @@ -1886,7 +1807,6 @@ int tipc_socket_init(void) /** * tipc_socket_stop - stop TIPC socket interface */ - void tipc_socket_stop(void) { if (!sockets_enabled) @@ -1896,4 +1816,3 @@ void tipc_socket_stop(void) sock_unregister(tipc_family_ops.family); proto_unregister(&tipc_proto); } - diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index b2964e9895d..f976e9cd6a7 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -46,7 +46,6 @@ * @subscriber_list: adjacent subscribers in top. server's list of subscribers * @subscription_list: list of subscription objects for this subscriber */ - struct tipc_subscriber { u32 port_ref; spinlock_t *lock; @@ -56,13 +55,11 @@ struct tipc_subscriber { /** * struct top_srv - TIPC network topology subscription service - * @user_ref: TIPC userid of subscription service * @setup_port: reference to TIPC port that handles subscription requests * @subscription_count: number of active subscriptions (not subscribers!) * @subscriber_list: list of ports subscribing to service * @lock: spinlock govering access to subscriber list */ - struct top_srv { u32 setup_port; atomic_t subscription_count; @@ -79,7 +76,6 @@ static struct top_srv topsrv; * * Returns converted value */ - static u32 htohl(u32 in, int swap) { return swap ? swab32(in) : in; @@ -91,7 +87,6 @@ static u32 htohl(u32 in, int swap) * Note: Must not hold subscriber's server port lock, since tipc_send() will * try to take the lock if the message is rejected and returned! */ - static void subscr_send_event(struct tipc_subscription *sub, u32 found_lower, u32 found_upper, @@ -117,7 +112,6 @@ static void subscr_send_event(struct tipc_subscription *sub, * * Returns 1 if there is overlap, otherwise 0. */ - int tipc_subscr_overlap(struct tipc_subscription *sub, u32 found_lower, u32 found_upper) @@ -137,7 +131,6 @@ int tipc_subscr_overlap(struct tipc_subscription *sub, * * Protected by nameseq.lock in name_table.c */ - void tipc_subscr_report_overlap(struct tipc_subscription *sub, u32 found_lower, u32 found_upper, @@ -157,43 +150,35 @@ void tipc_subscr_report_overlap(struct tipc_subscription *sub, /** * subscr_timeout - subscription timeout has occurred */ - static void subscr_timeout(struct tipc_subscription *sub) { struct tipc_port *server_port; /* Validate server port reference (in case subscriber is terminating) */ - server_port = tipc_port_lock(sub->server_ref); if (server_port == NULL) return; /* Validate timeout (in case subscription is being cancelled) */ - if (sub->timeout == TIPC_WAIT_FOREVER) { tipc_port_unlock(server_port); return; } /* Unlink subscription from name table */ - tipc_nametbl_unsubscribe(sub); /* Unlink subscription from subscriber */ - list_del(&sub->subscription_list); /* Release subscriber's server port */ - tipc_port_unlock(server_port); /* Notify subscriber of timeout */ - subscr_send_event(sub, sub->evt.s.seq.lower, sub->evt.s.seq.upper, TIPC_SUBSCR_TIMEOUT, 0, 0); /* Now destroy subscription */ - k_term_timer(&sub->timer); kfree(sub); atomic_dec(&topsrv.subscription_count); @@ -204,7 +189,6 @@ static void subscr_timeout(struct tipc_subscription *sub) * * Called with subscriber port locked. */ - static void subscr_del(struct tipc_subscription *sub) { tipc_nametbl_unsubscribe(sub); @@ -223,7 +207,6 @@ static void subscr_del(struct tipc_subscription *sub) * a new object reference in the interim that uses this lock; this routine will * simply wait for it to be released, then claim it.) */ - static void subscr_terminate(struct tipc_subscriber *subscriber) { u32 port_ref; @@ -231,18 +214,15 @@ static void subscr_terminate(struct tipc_subscriber *subscriber) struct tipc_subscription *sub_temp; /* Invalidate subscriber reference */ - port_ref = subscriber->port_ref; subscriber->port_ref = 0; spin_unlock_bh(subscriber->lock); /* Sever connection to subscriber */ - tipc_shutdown(port_ref); tipc_deleteport(port_ref); /* Destroy any existing subscriptions for subscriber */ - list_for_each_entry_safe(sub, sub_temp, &subscriber->subscription_list, subscription_list) { if (sub->timeout != TIPC_WAIT_FOREVER) { @@ -253,17 +233,14 @@ static void subscr_terminate(struct tipc_subscriber *subscriber) } /* Remove subscriber from topology server's subscriber list */ - spin_lock_bh(&topsrv.lock); list_del(&subscriber->subscriber_list); spin_unlock_bh(&topsrv.lock); /* Reclaim subscriber lock */ - spin_lock_bh(subscriber->lock); /* Now destroy subscriber */ - kfree(subscriber); } @@ -276,7 +253,6 @@ static void subscr_terminate(struct tipc_subscriber *subscriber) * * Note that fields of 's' use subscriber's endianness! */ - static void subscr_cancel(struct tipc_subscr *s, struct tipc_subscriber *subscriber) { @@ -285,7 +261,6 @@ static void subscr_cancel(struct tipc_subscr *s, int found = 0; /* Find first matching subscription, exit if not found */ - list_for_each_entry_safe(sub, sub_temp, &subscriber->subscription_list, subscription_list) { if (!memcmp(s, &sub->evt.s, sizeof(struct tipc_subscr))) { @@ -297,7 +272,6 @@ static void subscr_cancel(struct tipc_subscr *s, return; /* Cancel subscription timer (if used), then delete subscription */ - if (sub->timeout != TIPC_WAIT_FOREVER) { sub->timeout = TIPC_WAIT_FOREVER; spin_unlock_bh(subscriber->lock); @@ -313,7 +287,6 @@ static void subscr_cancel(struct tipc_subscr *s, * * Called with subscriber port locked. */ - static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s, struct tipc_subscriber *subscriber) { @@ -321,11 +294,9 @@ static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s, int swap; /* Determine subscriber's endianness */ - swap = !(s->filter & (TIPC_SUB_PORTS | TIPC_SUB_SERVICE)); /* Detect & process a subscription cancellation request */ - if (s->filter & htohl(TIPC_SUB_CANCEL, swap)) { s->filter &= ~htohl(TIPC_SUB_CANCEL, swap); subscr_cancel(s, subscriber); @@ -333,7 +304,6 @@ static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s, } /* Refuse subscription if global limit exceeded */ - if (atomic_read(&topsrv.subscription_count) >= tipc_max_subscriptions) { warn("Subscription rejected, subscription limit reached (%u)\n", tipc_max_subscriptions); @@ -342,7 +312,6 @@ static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s, } /* Allocate subscription object */ - sub = kmalloc(sizeof(*sub), GFP_ATOMIC); if (!sub) { warn("Subscription rejected, no memory\n"); @@ -351,7 +320,6 @@ static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s, } /* Initialize subscription object */ - sub->seq.type = htohl(s->seq.type, swap); sub->seq.lower = htohl(s->seq.lower, swap); sub->seq.upper = htohl(s->seq.upper, swap); @@ -385,7 +353,6 @@ static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s, * * Called with subscriber's server port unlocked. */ - static void subscr_conn_shutdown_event(void *usr_handle, u32 port_ref, struct sk_buff **buf, @@ -409,7 +376,6 @@ static void subscr_conn_shutdown_event(void *usr_handle, * * Called with subscriber's server port unlocked. */ - static void subscr_conn_msg_event(void *usr_handle, u32 port_ref, struct sk_buff **buf, @@ -424,7 +390,6 @@ static void subscr_conn_msg_event(void *usr_handle, * Lock subscriber's server port (& make a local copy of lock pointer, * in case subscriber is deleted while processing subscription request) */ - if (tipc_port_lock(port_ref) == NULL) return; @@ -452,7 +417,6 @@ static void subscr_conn_msg_event(void *usr_handle, * timeout code cannot delete the subscription, * so the subscription object is still protected. */ - tipc_nametbl_subscribe(sub); } } @@ -461,7 +425,6 @@ static void subscr_conn_msg_event(void *usr_handle, /** * subscr_named_msg_event - handle request to establish a new subscriber */ - static void subscr_named_msg_event(void *usr_handle, u32 port_ref, struct sk_buff **buf, @@ -475,7 +438,6 @@ static void subscr_named_msg_event(void *usr_handle, u32 server_port_ref; /* Create subscriber object */ - subscriber = kzalloc(sizeof(struct tipc_subscriber), GFP_ATOMIC); if (subscriber == NULL) { warn("Subscriber rejected, no memory\n"); @@ -485,7 +447,6 @@ static void subscr_named_msg_event(void *usr_handle, INIT_LIST_HEAD(&subscriber->subscriber_list); /* Create server port & establish connection to subscriber */ - tipc_createport(subscriber, importance, NULL, @@ -504,26 +465,21 @@ static void subscr_named_msg_event(void *usr_handle, tipc_connect2port(subscriber->port_ref, orig); /* Lock server port (& save lock address for future use) */ - subscriber->lock = tipc_port_lock(subscriber->port_ref)->lock; /* Add subscriber to topology server's subscriber list */ - spin_lock_bh(&topsrv.lock); list_add(&subscriber->subscriber_list, &topsrv.subscriber_list); spin_unlock_bh(&topsrv.lock); /* Unlock server port */ - server_port_ref = subscriber->port_ref; spin_unlock_bh(subscriber->lock); /* Send an ACK- to complete connection handshaking */ - tipc_send(server_port_ref, 0, NULL, 0); /* Handle optional subscription request */ - if (size != 0) { subscr_conn_msg_event(subscriber, server_port_ref, buf, data, size); @@ -535,7 +491,6 @@ int tipc_subscr_start(void) struct tipc_name_seq seq = {TIPC_TOP_SRV, TIPC_TOP_SRV, TIPC_TOP_SRV}; int res; - memset(&topsrv, 0, sizeof(topsrv)); spin_lock_init(&topsrv.lock); INIT_LIST_HEAD(&topsrv.subscriber_list); diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h index ef6529c8456..218d2e07f0c 100644 --- a/net/tipc/subscr.h +++ b/net/tipc/subscr.h @@ -51,7 +51,6 @@ struct tipc_subscription; * @swap: indicates if subscriber uses opposite endianness in its messages * @evt: template for events generated by subscription */ - struct tipc_subscription { struct tipc_name_seq seq; u32 timeout; @@ -80,5 +79,4 @@ int tipc_subscr_start(void); void tipc_subscr_stop(void); - #endif diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index d510353ef43..641f2e47f16 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -149,9 +149,10 @@ static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb) * each socket state is protected by separate spin lock. */ -static inline unsigned unix_hash_fold(__wsum n) +static inline unsigned int unix_hash_fold(__wsum n) { - unsigned hash = (__force unsigned)n; + unsigned int hash = (__force unsigned int)n; + hash ^= hash>>16; hash ^= hash>>8; return hash&(UNIX_HASH_SIZE-1); @@ -200,7 +201,7 @@ static inline void unix_release_addr(struct unix_address *addr) * - if started by zero, it is abstract name. */ -static int unix_mkname(struct sockaddr_un *sunaddr, int len, unsigned *hashp) +static int unix_mkname(struct sockaddr_un *sunaddr, int len, unsigned int *hashp) { if (len <= sizeof(short) || len > sizeof(*sunaddr)) return -EINVAL; @@ -250,7 +251,7 @@ static inline void unix_insert_socket(struct hlist_head *list, struct sock *sk) static struct sock *__unix_find_socket_byname(struct net *net, struct sockaddr_un *sunname, - int len, int type, unsigned hash) + int len, int type, unsigned int hash) { struct sock *s; struct hlist_node *node; @@ -273,7 +274,7 @@ found: static inline struct sock *unix_find_socket_byname(struct net *net, struct sockaddr_un *sunname, int len, int type, - unsigned hash) + unsigned int hash) { struct sock *s; @@ -760,7 +761,7 @@ out: mutex_unlock(&u->readlock); static struct sock *unix_find_other(struct net *net, struct sockaddr_un *sunname, int len, - int type, unsigned hash, int *error) + int type, unsigned int hash, int *error) { struct sock *u; struct path path; @@ -824,7 +825,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct dentry *dentry = NULL; struct path path; int err; - unsigned hash; + unsigned int hash; struct unix_address *addr; struct hlist_head *list; @@ -964,7 +965,7 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, struct net *net = sock_net(sk); struct sockaddr_un *sunaddr = (struct sockaddr_un *)addr; struct sock *other; - unsigned hash; + unsigned int hash; int err; if (addr->sa_family != AF_UNSPEC) { @@ -1062,7 +1063,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, struct sock *newsk = NULL; struct sock *other = NULL; struct sk_buff *skb = NULL; - unsigned hash; + unsigned int hash; int st; int err; long timeo; @@ -1437,11 +1438,12 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, struct sock *other = NULL; int namelen = 0; /* fake GCC */ int err; - unsigned hash; + unsigned int hash; struct sk_buff *skb; long timeo; struct scm_cookie tmp_scm; int max_level; + int data_len = 0; if (NULL == siocb->scm) siocb->scm = &tmp_scm; @@ -1475,7 +1477,13 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, if (len > sk->sk_sndbuf - 32) goto out; - skb = sock_alloc_send_skb(sk, len, msg->msg_flags&MSG_DONTWAIT, &err); + if (len > SKB_MAX_ALLOC) + data_len = min_t(size_t, + len - SKB_MAX_ALLOC, + MAX_SKB_FRAGS * PAGE_SIZE); + + skb = sock_alloc_send_pskb(sk, len - data_len, data_len, + msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) goto out; @@ -1485,8 +1493,10 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, max_level = err + 1; unix_get_secdata(siocb->scm, skb); - skb_reset_transport_header(skb); - err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len); + skb_put(skb, len - data_len); + skb->data_len = data_len; + skb->len = len; + err = skb_copy_datagram_from_iovec(skb, 0, msg->msg_iov, 0, len); if (err) goto out_free; diff --git a/net/unix/diag.c b/net/unix/diag.c index f0486ae9ebe..47d3002737f 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -310,7 +310,7 @@ static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) return unix_diag_get_exact(skb, h, (struct unix_diag_req *)NLMSG_DATA(h)); } -static struct sock_diag_handler unix_diag_handler = { +static const struct sock_diag_handler unix_diag_handler = { .family = AF_UNIX, .dump = unix_diag_handler_dump, }; diff --git a/net/unix/sysctl_net_unix.c b/net/unix/sysctl_net_unix.c index 397cffebb3b..b34b5b9792f 100644 --- a/net/unix/sysctl_net_unix.c +++ b/net/unix/sysctl_net_unix.c @@ -26,12 +26,6 @@ static ctl_table unix_table[] = { { } }; -static struct ctl_path unix_path[] = { - { .procname = "net", }, - { .procname = "unix", }, - { }, -}; - int __net_init unix_sysctl_register(struct net *net) { struct ctl_table *table; @@ -41,7 +35,7 @@ int __net_init unix_sysctl_register(struct net *net) goto err_alloc; table[0].data = &net->unx.sysctl_max_dgram_qlen; - net->unx.ctl = register_net_sysctl_table(net, unix_path, table); + net->unx.ctl = register_net_sysctl(net, "net/unix", table); if (net->unx.ctl == NULL) goto err_reg; @@ -58,6 +52,6 @@ void unix_sysctl_unregister(struct net *net) struct ctl_table *table; table = net->unx.ctl->ctl_table_arg; - unregister_sysctl_table(net->unx.ctl); + unregister_net_sysctl_table(net->unx.ctl); kfree(table); } diff --git a/net/wimax/stack.c b/net/wimax/stack.c index 3c65eae701c..a6470ac3949 100644 --- a/net/wimax/stack.c +++ b/net/wimax/stack.c @@ -187,7 +187,7 @@ out: static void __check_new_state(enum wimax_st old_state, enum wimax_st new_state, - unsigned allowed_states_bm) + unsigned int allowed_states_bm) { if (WARN_ON(((1 << new_state) & allowed_states_bm) == 0)) { printk(KERN_ERR "SW BUG! Forbidden state change %u -> %u\n", @@ -425,7 +425,8 @@ static size_t wimax_addr_scnprint(char *addr_str, size_t addr_str_size, unsigned char *addr, size_t addr_len) { - unsigned cnt, total; + unsigned int cnt, total; + for (total = cnt = 0; cnt < addr_len; cnt++) total += scnprintf(addr_str + total, addr_str_size - total, "%02x%c", addr[cnt], diff --git a/net/wireless/core.c b/net/wireless/core.c index ccdfed89765..39f2538a46f 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -422,10 +422,6 @@ static int wiphy_verify_combinations(struct wiphy *wiphy) const struct ieee80211_iface_combination *c; int i, j; - /* If we have combinations enforce them */ - if (wiphy->n_iface_combinations) - wiphy->flags |= WIPHY_FLAG_ENFORCE_COMBINATIONS; - for (i = 0; i < wiphy->n_iface_combinations; i++) { u32 cnt = 0; u16 all_iftypes = 0; @@ -708,6 +704,10 @@ void wiphy_unregister(struct wiphy *wiphy) flush_work(&rdev->scan_done_wk); cancel_work_sync(&rdev->conn_work); flush_work(&rdev->event_work); + + if (rdev->wowlan && rdev->ops->set_wakeup) + rdev->ops->set_wakeup(&rdev->wiphy, false); + cfg80211_rdev_free_wowlan(rdev); } EXPORT_SYMBOL(wiphy_unregister); @@ -720,7 +720,6 @@ void cfg80211_dev_free(struct cfg80211_registered_device *rdev) mutex_destroy(&rdev->sched_scan_mtx); list_for_each_entry_safe(scan, tmp, &rdev->bss_list, list) cfg80211_put_bss(&scan->pub); - cfg80211_rdev_free_wowlan(rdev); kfree(rdev); } diff --git a/net/wireless/debugfs.c b/net/wireless/debugfs.c index 39765bcfb47..920cabe0461 100644 --- a/net/wireless/debugfs.c +++ b/net/wireless/debugfs.c @@ -13,12 +13,6 @@ #include "core.h" #include "debugfs.h" -static int cfg80211_open_file_generic(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - #define DEBUGFS_READONLY_FILE(name, buflen, fmt, value...) \ static ssize_t name## _read(struct file *file, char __user *userbuf, \ size_t count, loff_t *ppos) \ @@ -33,7 +27,7 @@ static ssize_t name## _read(struct file *file, char __user *userbuf, \ \ static const struct file_operations name## _ops = { \ .read = name## _read, \ - .open = cfg80211_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; @@ -102,7 +96,7 @@ static ssize_t ht40allow_map_read(struct file *file, static const struct file_operations ht40allow_map_ops = { .read = ht40allow_map_read, - .open = cfg80211_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; diff --git a/net/wireless/ethtool.c b/net/wireless/ethtool.c index 9bde4d1d3e9..7eecdf40cf8 100644 --- a/net/wireless/ethtool.c +++ b/net/wireless/ethtool.c @@ -68,6 +68,32 @@ static int cfg80211_set_ringparam(struct net_device *dev, return -ENOTSUPP; } +static int cfg80211_get_sset_count(struct net_device *dev, int sset) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + if (rdev->ops->get_et_sset_count) + return rdev->ops->get_et_sset_count(wdev->wiphy, dev, sset); + return -EOPNOTSUPP; +} + +static void cfg80211_get_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + if (rdev->ops->get_et_stats) + rdev->ops->get_et_stats(wdev->wiphy, dev, stats, data); +} + +static void cfg80211_get_strings(struct net_device *dev, u32 sset, u8 *data) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + if (rdev->ops->get_et_strings) + rdev->ops->get_et_strings(wdev->wiphy, dev, sset, data); +} + const struct ethtool_ops cfg80211_ethtool_ops = { .get_drvinfo = cfg80211_get_drvinfo, .get_regs_len = cfg80211_get_regs_len, @@ -75,4 +101,7 @@ const struct ethtool_ops cfg80211_ethtool_ops = { .get_link = ethtool_op_get_link, .get_ringparam = cfg80211_get_ringparam, .set_ringparam = cfg80211_set_ringparam, + .get_strings = cfg80211_get_strings, + .get_ethtool_stats = cfg80211_get_stats, + .get_sset_count = cfg80211_get_sset_count, }; diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index 30f20fe4a5f..d2a19b0ff71 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -473,7 +473,7 @@ int cfg80211_ibss_wext_siwap(struct net_device *dev, /* fixed already - and no change */ if (wdev->wext.ibss.bssid && bssid && - compare_ether_addr(bssid, wdev->wext.ibss.bssid) == 0) + ether_addr_equal(bssid, wdev->wext.ibss.bssid)) return 0; wdev_lock(wdev); diff --git a/net/wireless/lib80211_crypt_ccmp.c b/net/wireless/lib80211_crypt_ccmp.c index 755738d26bb..1526c211db6 100644 --- a/net/wireless/lib80211_crypt_ccmp.c +++ b/net/wireless/lib80211_crypt_ccmp.c @@ -304,10 +304,8 @@ static int lib80211_ccmp_decrypt(struct sk_buff *skb, int hdr_len, void *priv) pos = skb->data + hdr_len; keyidx = pos[3]; if (!(keyidx & (1 << 5))) { - if (net_ratelimit()) { - printk(KERN_DEBUG "CCMP: received packet without ExtIV" - " flag from %pM\n", hdr->addr2); - } + net_dbg_ratelimited("CCMP: received packet without ExtIV flag from %pM\n", + hdr->addr2); key->dot11RSNAStatsCCMPFormatErrors++; return -2; } @@ -318,11 +316,8 @@ static int lib80211_ccmp_decrypt(struct sk_buff *skb, int hdr_len, void *priv) return -6; } if (!key->key_set) { - if (net_ratelimit()) { - printk(KERN_DEBUG "CCMP: received packet from %pM" - " with keyid=%d that does not have a configured" - " key\n", hdr->addr2, keyidx); - } + net_dbg_ratelimited("CCMP: received packet from %pM with keyid=%d that does not have a configured key\n", + hdr->addr2, keyidx); return -3; } @@ -336,15 +331,11 @@ static int lib80211_ccmp_decrypt(struct sk_buff *skb, int hdr_len, void *priv) if (ccmp_replay_check(pn, key->rx_pn)) { #ifdef CONFIG_LIB80211_DEBUG - if (net_ratelimit()) { - printk(KERN_DEBUG "CCMP: replay detected: STA=%pM " - "previous PN %02x%02x%02x%02x%02x%02x " - "received PN %02x%02x%02x%02x%02x%02x\n", - hdr->addr2, - key->rx_pn[0], key->rx_pn[1], key->rx_pn[2], - key->rx_pn[3], key->rx_pn[4], key->rx_pn[5], - pn[0], pn[1], pn[2], pn[3], pn[4], pn[5]); - } + net_dbg_ratelimited("CCMP: replay detected: STA=%pM previous PN %02x%02x%02x%02x%02x%02x received PN %02x%02x%02x%02x%02x%02x\n", + hdr->addr2, + key->rx_pn[0], key->rx_pn[1], key->rx_pn[2], + key->rx_pn[3], key->rx_pn[4], key->rx_pn[5], + pn[0], pn[1], pn[2], pn[3], pn[4], pn[5]); #endif key->dot11RSNAStatsCCMPReplays++; return -4; @@ -370,10 +361,8 @@ static int lib80211_ccmp_decrypt(struct sk_buff *skb, int hdr_len, void *priv) } if (memcmp(mic, a, CCMP_MIC_LEN) != 0) { - if (net_ratelimit()) { - printk(KERN_DEBUG "CCMP: decrypt failed: STA=" - "%pM\n", hdr->addr2); - } + net_dbg_ratelimited("CCMP: decrypt failed: STA=%pM\n", + hdr->addr2); key->dot11RSNAStatsCCMPDecryptErrors++; return -5; } diff --git a/net/wireless/lib80211_crypt_tkip.c b/net/wireless/lib80211_crypt_tkip.c index 38734846c19..d475cfc8568 100644 --- a/net/wireless/lib80211_crypt_tkip.c +++ b/net/wireless/lib80211_crypt_tkip.c @@ -360,12 +360,9 @@ static int lib80211_tkip_encrypt(struct sk_buff *skb, int hdr_len, void *priv) struct scatterlist sg; if (tkey->flags & IEEE80211_CRYPTO_TKIP_COUNTERMEASURES) { - if (net_ratelimit()) { - struct ieee80211_hdr *hdr = - (struct ieee80211_hdr *)skb->data; - printk(KERN_DEBUG ": TKIP countermeasures: dropped " - "TX packet to %pM\n", hdr->addr1); - } + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + net_dbg_ratelimited("TKIP countermeasures: dropped TX packet to %pM\n", + hdr->addr1); return -1; } @@ -420,10 +417,8 @@ static int lib80211_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv) hdr = (struct ieee80211_hdr *)skb->data; if (tkey->flags & IEEE80211_CRYPTO_TKIP_COUNTERMEASURES) { - if (net_ratelimit()) { - printk(KERN_DEBUG ": TKIP countermeasures: dropped " - "received packet from %pM\n", hdr->addr2); - } + net_dbg_ratelimited("TKIP countermeasures: dropped received packet from %pM\n", + hdr->addr2); return -1; } @@ -433,10 +428,8 @@ static int lib80211_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv) pos = skb->data + hdr_len; keyidx = pos[3]; if (!(keyidx & (1 << 5))) { - if (net_ratelimit()) { - printk(KERN_DEBUG "TKIP: received packet without ExtIV" - " flag from %pM\n", hdr->addr2); - } + net_dbg_ratelimited("TKIP: received packet without ExtIV flag from %pM\n", + hdr->addr2); return -2; } keyidx >>= 6; @@ -446,11 +439,8 @@ static int lib80211_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv) return -6; } if (!tkey->key_set) { - if (net_ratelimit()) { - printk(KERN_DEBUG "TKIP: received packet from %pM" - " with keyid=%d that does not have a configured" - " key\n", hdr->addr2, keyidx); - } + net_dbg_ratelimited("TKIP: received packet from %pM with keyid=%d that does not have a configured key\n", + hdr->addr2, keyidx); return -3; } iv16 = (pos[0] << 8) | pos[2]; @@ -459,12 +449,9 @@ static int lib80211_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv) if (tkip_replay_check(iv32, iv16, tkey->rx_iv32, tkey->rx_iv16)) { #ifdef CONFIG_LIB80211_DEBUG - if (net_ratelimit()) { - printk(KERN_DEBUG "TKIP: replay detected: STA=%pM" - " previous TSC %08x%04x received TSC " - "%08x%04x\n", hdr->addr2, - tkey->rx_iv32, tkey->rx_iv16, iv32, iv16); - } + net_dbg_ratelimited("TKIP: replay detected: STA=%pM previous TSC %08x%04x received TSC %08x%04x\n", + hdr->addr2, tkey->rx_iv32, tkey->rx_iv16, + iv32, iv16); #endif tkey->dot11RSNAStatsTKIPReplays++; return -4; @@ -481,11 +468,8 @@ static int lib80211_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv) crypto_blkcipher_setkey(tkey->rx_tfm_arc4, rc4key, 16); sg_init_one(&sg, pos, plen + 4); if (crypto_blkcipher_decrypt(&desc, &sg, &sg, plen + 4)) { - if (net_ratelimit()) { - printk(KERN_DEBUG ": TKIP: failed to decrypt " - "received packet from %pM\n", - hdr->addr2); - } + net_dbg_ratelimited("TKIP: failed to decrypt received packet from %pM\n", + hdr->addr2); return -7; } @@ -501,10 +485,8 @@ static int lib80211_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv) tkey->rx_phase1_done = 0; } #ifdef CONFIG_LIB80211_DEBUG - if (net_ratelimit()) { - printk(KERN_DEBUG "TKIP: ICV error detected: STA=" - "%pM\n", hdr->addr2); - } + net_dbg_ratelimited("TKIP: ICV error detected: STA=%pM\n", + hdr->addr2); #endif tkey->dot11RSNAStatsTKIPICVErrors++; return -5; diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index ba21ab22187..2749cb86b46 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -38,6 +38,7 @@ #define MESH_MAX_PREQ_RETRIES 4 +#define MESH_SYNC_NEIGHBOR_OFFSET_MAX 50 const struct mesh_config default_mesh_config = { .dot11MeshRetryTimeout = MESH_RET_T, @@ -48,6 +49,7 @@ const struct mesh_config default_mesh_config = { .element_ttl = MESH_DEFAULT_ELEMENT_TTL, .auto_open_plinks = true, .dot11MeshMaxPeerLinks = MESH_MAX_ESTAB_PLINKS, + .dot11MeshNbrOffsetMaxNeighbor = MESH_SYNC_NEIGHBOR_OFFSET_MAX, .dot11MeshHWMPactivePathTimeout = MESH_PATH_TIMEOUT, .dot11MeshHWMPpreqMinInterval = MESH_PREQ_MIN_INT, .dot11MeshHWMPperrMinInterval = MESH_PERR_MIN_INT, @@ -59,9 +61,11 @@ const struct mesh_config default_mesh_config = { .dot11MeshGateAnnouncementProtocol = false, .dot11MeshForwarding = true, .rssi_threshold = MESH_RSSI_THRESHOLD, + .ht_opmode = IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED, }; const struct mesh_setup default_mesh_setup = { + .sync_method = IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET, .path_sel_proto = IEEE80211_PATH_PROTOCOL_HWMP, .path_metric = IEEE80211_PATH_METRIC_AIRTIME, .ie = NULL, diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index f5a7ac3a093..eb90988bbd3 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -6,6 +6,7 @@ #include <linux/kernel.h> #include <linux/module.h> +#include <linux/etherdevice.h> #include <linux/netdevice.h> #include <linux/nl80211.h> #include <linux/slab.h> @@ -100,7 +101,7 @@ void __cfg80211_send_deauth(struct net_device *dev, ASSERT_WDEV_LOCK(wdev); if (wdev->current_bss && - memcmp(wdev->current_bss->pub.bssid, bssid, ETH_ALEN) == 0) { + ether_addr_equal(wdev->current_bss->pub.bssid, bssid)) { cfg80211_unhold_bss(wdev->current_bss); cfg80211_put_bss(&wdev->current_bss->pub); wdev->current_bss = NULL; @@ -115,7 +116,7 @@ void __cfg80211_send_deauth(struct net_device *dev, reason_code = le16_to_cpu(mgmt->u.deauth.reason_code); - from_ap = memcmp(mgmt->sa, dev->dev_addr, ETH_ALEN) != 0; + from_ap = !ether_addr_equal(mgmt->sa, dev->dev_addr); __cfg80211_disconnected(dev, NULL, 0, reason_code, from_ap); } else if (wdev->sme_state == CFG80211_SME_CONNECTING) { __cfg80211_connect_result(dev, mgmt->bssid, NULL, 0, NULL, 0, @@ -154,7 +155,7 @@ void __cfg80211_send_disassoc(struct net_device *dev, return; if (wdev->current_bss && - memcmp(wdev->current_bss->pub.bssid, bssid, ETH_ALEN) == 0) { + ether_addr_equal(wdev->current_bss->pub.bssid, bssid)) { cfg80211_sme_disassoc(dev, wdev->current_bss); cfg80211_unhold_bss(wdev->current_bss); cfg80211_put_bss(&wdev->current_bss->pub); @@ -165,7 +166,7 @@ void __cfg80211_send_disassoc(struct net_device *dev, reason_code = le16_to_cpu(mgmt->u.disassoc.reason_code); - from_ap = memcmp(mgmt->sa, dev->dev_addr, ETH_ALEN) != 0; + from_ap = !ether_addr_equal(mgmt->sa, dev->dev_addr); __cfg80211_disconnected(dev, NULL, 0, reason_code, from_ap); } EXPORT_SYMBOL(__cfg80211_send_disassoc); @@ -285,7 +286,7 @@ int __cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, return -EINVAL; if (wdev->current_bss && - memcmp(bssid, wdev->current_bss->pub.bssid, ETH_ALEN) == 0) + ether_addr_equal(bssid, wdev->current_bss->pub.bssid)) return -EALREADY; memset(&req, 0, sizeof(req)); @@ -362,7 +363,7 @@ int __cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, memset(&req, 0, sizeof(req)); if (wdev->current_bss && prev_bssid && - memcmp(wdev->current_bss->pub.bssid, prev_bssid, ETH_ALEN) == 0) { + ether_addr_equal(wdev->current_bss->pub.bssid, prev_bssid)) { /* * Trying to reassociate: Allow this to proceed and let the old * association to be dropped when the new one is completed. @@ -446,7 +447,7 @@ int __cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, if (local_state_change) { if (wdev->current_bss && - memcmp(wdev->current_bss->pub.bssid, bssid, ETH_ALEN) == 0) { + ether_addr_equal(wdev->current_bss->pub.bssid, bssid)) { cfg80211_unhold_bss(wdev->current_bss); cfg80211_put_bss(&wdev->current_bss->pub); wdev->current_bss = NULL; @@ -495,7 +496,7 @@ static int __cfg80211_mlme_disassoc(struct cfg80211_registered_device *rdev, req.local_state_change = local_state_change; req.ie = ie; req.ie_len = ie_len; - if (memcmp(wdev->current_bss->pub.bssid, bssid, ETH_ALEN) == 0) + if (ether_addr_equal(wdev->current_bss->pub.bssid, bssid)) req.bss = &wdev->current_bss->pub; else return -ENOTCONN; @@ -758,8 +759,8 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, break; } - if (memcmp(wdev->current_bss->pub.bssid, - mgmt->bssid, ETH_ALEN)) { + if (!ether_addr_equal(wdev->current_bss->pub.bssid, + mgmt->bssid)) { err = -ENOTCONN; break; } @@ -772,8 +773,8 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, break; /* for station, check that DA is the AP */ - if (memcmp(wdev->current_bss->pub.bssid, - mgmt->da, ETH_ALEN)) { + if (!ether_addr_equal(wdev->current_bss->pub.bssid, + mgmt->da)) { err = -ENOTCONN; break; } @@ -781,11 +782,11 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_AP_VLAN: - if (memcmp(mgmt->bssid, dev->dev_addr, ETH_ALEN)) + if (!ether_addr_equal(mgmt->bssid, dev->dev_addr)) err = -EINVAL; break; case NL80211_IFTYPE_MESH_POINT: - if (memcmp(mgmt->sa, mgmt->bssid, ETH_ALEN)) { + if (!ether_addr_equal(mgmt->sa, mgmt->bssid)) { err = -EINVAL; break; } @@ -804,7 +805,7 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, return err; } - if (memcmp(mgmt->sa, dev->dev_addr, ETH_ALEN) != 0) + if (!ether_addr_equal(mgmt->sa, dev->dev_addr)) return -EINVAL; /* Transmit the Action frame as requested by user space */ @@ -928,6 +929,33 @@ void cfg80211_pmksa_candidate_notify(struct net_device *dev, int index, } EXPORT_SYMBOL(cfg80211_pmksa_candidate_notify); +void cfg80211_ch_switch_notify(struct net_device *dev, int freq, + enum nl80211_channel_type type) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + struct ieee80211_channel *chan; + + wdev_lock(wdev); + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_AP && + wdev->iftype != NL80211_IFTYPE_P2P_GO)) + goto out; + + chan = rdev_freq_to_chan(rdev, freq, type); + if (WARN_ON(!chan)) + goto out; + + wdev->channel = chan; + + nl80211_ch_switch_notify(rdev, dev, freq, type, GFP_KERNEL); +out: + wdev_unlock(wdev); + return; +} +EXPORT_SYMBOL(cfg80211_ch_switch_notify); + bool cfg80211_rx_spurious_frame(struct net_device *dev, const u8 *addr, gfp_t gfp) { diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 4c1eb9472dd..b67b1114e25 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -356,20 +356,26 @@ static inline void *nl80211hdr_put(struct sk_buff *skb, u32 pid, u32 seq, static int nl80211_msg_put_channel(struct sk_buff *msg, struct ieee80211_channel *chan) { - NLA_PUT_U32(msg, NL80211_FREQUENCY_ATTR_FREQ, - chan->center_freq); + if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_FREQ, + chan->center_freq)) + goto nla_put_failure; - if (chan->flags & IEEE80211_CHAN_DISABLED) - NLA_PUT_FLAG(msg, NL80211_FREQUENCY_ATTR_DISABLED); - if (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN) - NLA_PUT_FLAG(msg, NL80211_FREQUENCY_ATTR_PASSIVE_SCAN); - if (chan->flags & IEEE80211_CHAN_NO_IBSS) - NLA_PUT_FLAG(msg, NL80211_FREQUENCY_ATTR_NO_IBSS); - if (chan->flags & IEEE80211_CHAN_RADAR) - NLA_PUT_FLAG(msg, NL80211_FREQUENCY_ATTR_RADAR); + if ((chan->flags & IEEE80211_CHAN_DISABLED) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_DISABLED)) + goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_PASSIVE_SCAN) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_PASSIVE_SCAN)) + goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_NO_IBSS) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_IBSS)) + goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_RADAR) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_RADAR)) + goto nla_put_failure; - NLA_PUT_U32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER, - DBM_TO_MBM(chan->max_power)); + if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER, + DBM_TO_MBM(chan->max_power))) + goto nla_put_failure; return 0; @@ -621,8 +627,8 @@ static int nl80211_put_iftypes(struct sk_buff *msg, u32 attr, u16 ifmodes) i = 0; while (ifmodes) { - if (ifmodes & 1) - NLA_PUT_FLAG(msg, i); + if ((ifmodes & 1) && nla_put_flag(msg, i)) + goto nla_put_failure; ifmodes >>= 1; i++; } @@ -665,8 +671,9 @@ static int nl80211_put_iface_combinations(struct wiphy *wiphy, nl_limit = nla_nest_start(msg, j + 1); if (!nl_limit) goto nla_put_failure; - NLA_PUT_U32(msg, NL80211_IFACE_LIMIT_MAX, - c->limits[j].max); + if (nla_put_u32(msg, NL80211_IFACE_LIMIT_MAX, + c->limits[j].max)) + goto nla_put_failure; if (nl80211_put_iftypes(msg, NL80211_IFACE_LIMIT_TYPES, c->limits[j].types)) goto nla_put_failure; @@ -675,13 +682,14 @@ static int nl80211_put_iface_combinations(struct wiphy *wiphy, nla_nest_end(msg, nl_limits); - if (c->beacon_int_infra_match) - NLA_PUT_FLAG(msg, - NL80211_IFACE_COMB_STA_AP_BI_MATCH); - NLA_PUT_U32(msg, NL80211_IFACE_COMB_NUM_CHANNELS, - c->num_different_channels); - NLA_PUT_U32(msg, NL80211_IFACE_COMB_MAXNUM, - c->max_interfaces); + if (c->beacon_int_infra_match && + nla_put_flag(msg, NL80211_IFACE_COMB_STA_AP_BI_MATCH)) + goto nla_put_failure; + if (nla_put_u32(msg, NL80211_IFACE_COMB_NUM_CHANNELS, + c->num_different_channels) || + nla_put_u32(msg, NL80211_IFACE_COMB_MAXNUM, + c->max_interfaces)) + goto nla_put_failure; nla_nest_end(msg, nl_combi); } @@ -712,64 +720,74 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, if (!hdr) return -1; - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, dev->wiphy_idx); - NLA_PUT_STRING(msg, NL80211_ATTR_WIPHY_NAME, wiphy_name(&dev->wiphy)); - - NLA_PUT_U32(msg, NL80211_ATTR_GENERATION, - cfg80211_rdev_list_generation); - - NLA_PUT_U8(msg, NL80211_ATTR_WIPHY_RETRY_SHORT, - dev->wiphy.retry_short); - NLA_PUT_U8(msg, NL80211_ATTR_WIPHY_RETRY_LONG, - dev->wiphy.retry_long); - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY_FRAG_THRESHOLD, - dev->wiphy.frag_threshold); - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY_RTS_THRESHOLD, - dev->wiphy.rts_threshold); - NLA_PUT_U8(msg, NL80211_ATTR_WIPHY_COVERAGE_CLASS, - dev->wiphy.coverage_class); - NLA_PUT_U8(msg, NL80211_ATTR_MAX_NUM_SCAN_SSIDS, - dev->wiphy.max_scan_ssids); - NLA_PUT_U8(msg, NL80211_ATTR_MAX_NUM_SCHED_SCAN_SSIDS, - dev->wiphy.max_sched_scan_ssids); - NLA_PUT_U16(msg, NL80211_ATTR_MAX_SCAN_IE_LEN, - dev->wiphy.max_scan_ie_len); - NLA_PUT_U16(msg, NL80211_ATTR_MAX_SCHED_SCAN_IE_LEN, - dev->wiphy.max_sched_scan_ie_len); - NLA_PUT_U8(msg, NL80211_ATTR_MAX_MATCH_SETS, - dev->wiphy.max_match_sets); - - if (dev->wiphy.flags & WIPHY_FLAG_IBSS_RSN) - NLA_PUT_FLAG(msg, NL80211_ATTR_SUPPORT_IBSS_RSN); - if (dev->wiphy.flags & WIPHY_FLAG_MESH_AUTH) - NLA_PUT_FLAG(msg, NL80211_ATTR_SUPPORT_MESH_AUTH); - if (dev->wiphy.flags & WIPHY_FLAG_AP_UAPSD) - NLA_PUT_FLAG(msg, NL80211_ATTR_SUPPORT_AP_UAPSD); - if (dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_FW_ROAM) - NLA_PUT_FLAG(msg, NL80211_ATTR_ROAM_SUPPORT); - if (dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) - NLA_PUT_FLAG(msg, NL80211_ATTR_TDLS_SUPPORT); - if (dev->wiphy.flags & WIPHY_FLAG_TDLS_EXTERNAL_SETUP) - NLA_PUT_FLAG(msg, NL80211_ATTR_TDLS_EXTERNAL_SETUP); - - NLA_PUT(msg, NL80211_ATTR_CIPHER_SUITES, - sizeof(u32) * dev->wiphy.n_cipher_suites, - dev->wiphy.cipher_suites); - - NLA_PUT_U8(msg, NL80211_ATTR_MAX_NUM_PMKIDS, - dev->wiphy.max_num_pmkids); - - if (dev->wiphy.flags & WIPHY_FLAG_CONTROL_PORT_PROTOCOL) - NLA_PUT_FLAG(msg, NL80211_ATTR_CONTROL_PORT_ETHERTYPE); - - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY_ANTENNA_AVAIL_TX, - dev->wiphy.available_antennas_tx); - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY_ANTENNA_AVAIL_RX, - dev->wiphy.available_antennas_rx); - - if (dev->wiphy.flags & WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD) - NLA_PUT_U32(msg, NL80211_ATTR_PROBE_RESP_OFFLOAD, - dev->wiphy.probe_resp_offload); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, dev->wiphy_idx) || + nla_put_string(msg, NL80211_ATTR_WIPHY_NAME, wiphy_name(&dev->wiphy)) || + nla_put_u32(msg, NL80211_ATTR_GENERATION, + cfg80211_rdev_list_generation) || + nla_put_u8(msg, NL80211_ATTR_WIPHY_RETRY_SHORT, + dev->wiphy.retry_short) || + nla_put_u8(msg, NL80211_ATTR_WIPHY_RETRY_LONG, + dev->wiphy.retry_long) || + nla_put_u32(msg, NL80211_ATTR_WIPHY_FRAG_THRESHOLD, + dev->wiphy.frag_threshold) || + nla_put_u32(msg, NL80211_ATTR_WIPHY_RTS_THRESHOLD, + dev->wiphy.rts_threshold) || + nla_put_u8(msg, NL80211_ATTR_WIPHY_COVERAGE_CLASS, + dev->wiphy.coverage_class) || + nla_put_u8(msg, NL80211_ATTR_MAX_NUM_SCAN_SSIDS, + dev->wiphy.max_scan_ssids) || + nla_put_u8(msg, NL80211_ATTR_MAX_NUM_SCHED_SCAN_SSIDS, + dev->wiphy.max_sched_scan_ssids) || + nla_put_u16(msg, NL80211_ATTR_MAX_SCAN_IE_LEN, + dev->wiphy.max_scan_ie_len) || + nla_put_u16(msg, NL80211_ATTR_MAX_SCHED_SCAN_IE_LEN, + dev->wiphy.max_sched_scan_ie_len) || + nla_put_u8(msg, NL80211_ATTR_MAX_MATCH_SETS, + dev->wiphy.max_match_sets)) + goto nla_put_failure; + + if ((dev->wiphy.flags & WIPHY_FLAG_IBSS_RSN) && + nla_put_flag(msg, NL80211_ATTR_SUPPORT_IBSS_RSN)) + goto nla_put_failure; + if ((dev->wiphy.flags & WIPHY_FLAG_MESH_AUTH) && + nla_put_flag(msg, NL80211_ATTR_SUPPORT_MESH_AUTH)) + goto nla_put_failure; + if ((dev->wiphy.flags & WIPHY_FLAG_AP_UAPSD) && + nla_put_flag(msg, NL80211_ATTR_SUPPORT_AP_UAPSD)) + goto nla_put_failure; + if ((dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_FW_ROAM) && + nla_put_flag(msg, NL80211_ATTR_ROAM_SUPPORT)) + goto nla_put_failure; + if ((dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) && + nla_put_flag(msg, NL80211_ATTR_TDLS_SUPPORT)) + goto nla_put_failure; + if ((dev->wiphy.flags & WIPHY_FLAG_TDLS_EXTERNAL_SETUP) && + nla_put_flag(msg, NL80211_ATTR_TDLS_EXTERNAL_SETUP)) + goto nla_put_failure; + + if (nla_put(msg, NL80211_ATTR_CIPHER_SUITES, + sizeof(u32) * dev->wiphy.n_cipher_suites, + dev->wiphy.cipher_suites)) + goto nla_put_failure; + + if (nla_put_u8(msg, NL80211_ATTR_MAX_NUM_PMKIDS, + dev->wiphy.max_num_pmkids)) + goto nla_put_failure; + + if ((dev->wiphy.flags & WIPHY_FLAG_CONTROL_PORT_PROTOCOL) && + nla_put_flag(msg, NL80211_ATTR_CONTROL_PORT_ETHERTYPE)) + goto nla_put_failure; + + if (nla_put_u32(msg, NL80211_ATTR_WIPHY_ANTENNA_AVAIL_TX, + dev->wiphy.available_antennas_tx) || + nla_put_u32(msg, NL80211_ATTR_WIPHY_ANTENNA_AVAIL_RX, + dev->wiphy.available_antennas_rx)) + goto nla_put_failure; + + if ((dev->wiphy.flags & WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD) && + nla_put_u32(msg, NL80211_ATTR_PROBE_RESP_OFFLOAD, + dev->wiphy.probe_resp_offload)) + goto nla_put_failure; if ((dev->wiphy.available_antennas_tx || dev->wiphy.available_antennas_rx) && dev->ops->get_antenna) { @@ -777,8 +795,11 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, int res; res = dev->ops->get_antenna(&dev->wiphy, &tx_ant, &rx_ant); if (!res) { - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY_ANTENNA_TX, tx_ant); - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY_ANTENNA_RX, rx_ant); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY_ANTENNA_TX, + tx_ant) || + nla_put_u32(msg, NL80211_ATTR_WIPHY_ANTENNA_RX, + rx_ant)) + goto nla_put_failure; } } @@ -799,17 +820,17 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, goto nla_put_failure; /* add HT info */ - if (dev->wiphy.bands[band]->ht_cap.ht_supported) { - NLA_PUT(msg, NL80211_BAND_ATTR_HT_MCS_SET, - sizeof(dev->wiphy.bands[band]->ht_cap.mcs), - &dev->wiphy.bands[band]->ht_cap.mcs); - NLA_PUT_U16(msg, NL80211_BAND_ATTR_HT_CAPA, - dev->wiphy.bands[band]->ht_cap.cap); - NLA_PUT_U8(msg, NL80211_BAND_ATTR_HT_AMPDU_FACTOR, - dev->wiphy.bands[band]->ht_cap.ampdu_factor); - NLA_PUT_U8(msg, NL80211_BAND_ATTR_HT_AMPDU_DENSITY, - dev->wiphy.bands[band]->ht_cap.ampdu_density); - } + if (dev->wiphy.bands[band]->ht_cap.ht_supported && + (nla_put(msg, NL80211_BAND_ATTR_HT_MCS_SET, + sizeof(dev->wiphy.bands[band]->ht_cap.mcs), + &dev->wiphy.bands[band]->ht_cap.mcs) || + nla_put_u16(msg, NL80211_BAND_ATTR_HT_CAPA, + dev->wiphy.bands[band]->ht_cap.cap) || + nla_put_u8(msg, NL80211_BAND_ATTR_HT_AMPDU_FACTOR, + dev->wiphy.bands[band]->ht_cap.ampdu_factor) || + nla_put_u8(msg, NL80211_BAND_ATTR_HT_AMPDU_DENSITY, + dev->wiphy.bands[band]->ht_cap.ampdu_density))) + goto nla_put_failure; /* add frequencies */ nl_freqs = nla_nest_start(msg, NL80211_BAND_ATTR_FREQS); @@ -842,11 +863,13 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, goto nla_put_failure; rate = &dev->wiphy.bands[band]->bitrates[i]; - NLA_PUT_U32(msg, NL80211_BITRATE_ATTR_RATE, - rate->bitrate); - if (rate->flags & IEEE80211_RATE_SHORT_PREAMBLE) - NLA_PUT_FLAG(msg, - NL80211_BITRATE_ATTR_2GHZ_SHORTPREAMBLE); + if (nla_put_u32(msg, NL80211_BITRATE_ATTR_RATE, + rate->bitrate)) + goto nla_put_failure; + if ((rate->flags & IEEE80211_RATE_SHORT_PREAMBLE) && + nla_put_flag(msg, + NL80211_BITRATE_ATTR_2GHZ_SHORTPREAMBLE)) + goto nla_put_failure; nla_nest_end(msg, nl_rate); } @@ -866,7 +889,8 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, do { \ if (dev->ops->op) { \ i++; \ - NLA_PUT_U32(msg, i, NL80211_CMD_ ## n); \ + if (nla_put_u32(msg, i, NL80211_CMD_ ## n)) \ + goto nla_put_failure; \ } \ } while (0) @@ -894,7 +918,8 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, CMD(mgmt_tx_cancel_wait, FRAME_WAIT_CANCEL); if (dev->wiphy.flags & WIPHY_FLAG_NETNS_OK) { i++; - NLA_PUT_U32(msg, i, NL80211_CMD_SET_WIPHY_NETNS); + if (nla_put_u32(msg, i, NL80211_CMD_SET_WIPHY_NETNS)) + goto nla_put_failure; } CMD(set_channel, SET_CHANNEL); CMD(set_wds_peer, SET_WDS_PEER); @@ -908,7 +933,8 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, CMD(set_noack_map, SET_NOACK_MAP); if (dev->wiphy.flags & WIPHY_FLAG_REPORTS_OBSS) { i++; - NLA_PUT_U32(msg, i, NL80211_CMD_REGISTER_BEACONS); + if (nla_put_u32(msg, i, NL80211_CMD_REGISTER_BEACONS)) + goto nla_put_failure; } #ifdef CONFIG_NL80211_TESTMODE @@ -919,23 +945,27 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, if (dev->ops->connect || dev->ops->auth) { i++; - NLA_PUT_U32(msg, i, NL80211_CMD_CONNECT); + if (nla_put_u32(msg, i, NL80211_CMD_CONNECT)) + goto nla_put_failure; } if (dev->ops->disconnect || dev->ops->deauth) { i++; - NLA_PUT_U32(msg, i, NL80211_CMD_DISCONNECT); + if (nla_put_u32(msg, i, NL80211_CMD_DISCONNECT)) + goto nla_put_failure; } nla_nest_end(msg, nl_cmds); if (dev->ops->remain_on_channel && - dev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL) - NLA_PUT_U32(msg, NL80211_ATTR_MAX_REMAIN_ON_CHANNEL_DURATION, - dev->wiphy.max_remain_on_channel_duration); + (dev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL) && + nla_put_u32(msg, NL80211_ATTR_MAX_REMAIN_ON_CHANNEL_DURATION, + dev->wiphy.max_remain_on_channel_duration)) + goto nla_put_failure; - if (dev->wiphy.flags & WIPHY_FLAG_OFFCHAN_TX) - NLA_PUT_FLAG(msg, NL80211_ATTR_OFFCHANNEL_TX_OK); + if ((dev->wiphy.flags & WIPHY_FLAG_OFFCHAN_TX) && + nla_put_flag(msg, NL80211_ATTR_OFFCHANNEL_TX_OK)) + goto nla_put_failure; if (mgmt_stypes) { u16 stypes; @@ -953,9 +983,10 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, i = 0; stypes = mgmt_stypes[ift].tx; while (stypes) { - if (stypes & 1) - NLA_PUT_U16(msg, NL80211_ATTR_FRAME_TYPE, - (i << 4) | IEEE80211_FTYPE_MGMT); + if ((stypes & 1) && + nla_put_u16(msg, NL80211_ATTR_FRAME_TYPE, + (i << 4) | IEEE80211_FTYPE_MGMT)) + goto nla_put_failure; stypes >>= 1; i++; } @@ -975,9 +1006,10 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, i = 0; stypes = mgmt_stypes[ift].rx; while (stypes) { - if (stypes & 1) - NLA_PUT_U16(msg, NL80211_ATTR_FRAME_TYPE, - (i << 4) | IEEE80211_FTYPE_MGMT); + if ((stypes & 1) && + nla_put_u16(msg, NL80211_ATTR_FRAME_TYPE, + (i << 4) | IEEE80211_FTYPE_MGMT)) + goto nla_put_failure; stypes >>= 1; i++; } @@ -994,22 +1026,23 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, if (!nl_wowlan) goto nla_put_failure; - if (dev->wiphy.wowlan.flags & WIPHY_WOWLAN_ANY) - NLA_PUT_FLAG(msg, NL80211_WOWLAN_TRIG_ANY); - if (dev->wiphy.wowlan.flags & WIPHY_WOWLAN_DISCONNECT) - NLA_PUT_FLAG(msg, NL80211_WOWLAN_TRIG_DISCONNECT); - if (dev->wiphy.wowlan.flags & WIPHY_WOWLAN_MAGIC_PKT) - NLA_PUT_FLAG(msg, NL80211_WOWLAN_TRIG_MAGIC_PKT); - if (dev->wiphy.wowlan.flags & WIPHY_WOWLAN_SUPPORTS_GTK_REKEY) - NLA_PUT_FLAG(msg, NL80211_WOWLAN_TRIG_GTK_REKEY_SUPPORTED); - if (dev->wiphy.wowlan.flags & WIPHY_WOWLAN_GTK_REKEY_FAILURE) - NLA_PUT_FLAG(msg, NL80211_WOWLAN_TRIG_GTK_REKEY_FAILURE); - if (dev->wiphy.wowlan.flags & WIPHY_WOWLAN_EAP_IDENTITY_REQ) - NLA_PUT_FLAG(msg, NL80211_WOWLAN_TRIG_EAP_IDENT_REQUEST); - if (dev->wiphy.wowlan.flags & WIPHY_WOWLAN_4WAY_HANDSHAKE) - NLA_PUT_FLAG(msg, NL80211_WOWLAN_TRIG_4WAY_HANDSHAKE); - if (dev->wiphy.wowlan.flags & WIPHY_WOWLAN_RFKILL_RELEASE) - NLA_PUT_FLAG(msg, NL80211_WOWLAN_TRIG_RFKILL_RELEASE); + if (((dev->wiphy.wowlan.flags & WIPHY_WOWLAN_ANY) && + nla_put_flag(msg, NL80211_WOWLAN_TRIG_ANY)) || + ((dev->wiphy.wowlan.flags & WIPHY_WOWLAN_DISCONNECT) && + nla_put_flag(msg, NL80211_WOWLAN_TRIG_DISCONNECT)) || + ((dev->wiphy.wowlan.flags & WIPHY_WOWLAN_MAGIC_PKT) && + nla_put_flag(msg, NL80211_WOWLAN_TRIG_MAGIC_PKT)) || + ((dev->wiphy.wowlan.flags & WIPHY_WOWLAN_SUPPORTS_GTK_REKEY) && + nla_put_flag(msg, NL80211_WOWLAN_TRIG_GTK_REKEY_SUPPORTED)) || + ((dev->wiphy.wowlan.flags & WIPHY_WOWLAN_GTK_REKEY_FAILURE) && + nla_put_flag(msg, NL80211_WOWLAN_TRIG_GTK_REKEY_FAILURE)) || + ((dev->wiphy.wowlan.flags & WIPHY_WOWLAN_EAP_IDENTITY_REQ) && + nla_put_flag(msg, NL80211_WOWLAN_TRIG_EAP_IDENT_REQUEST)) || + ((dev->wiphy.wowlan.flags & WIPHY_WOWLAN_4WAY_HANDSHAKE) && + nla_put_flag(msg, NL80211_WOWLAN_TRIG_4WAY_HANDSHAKE)) || + ((dev->wiphy.wowlan.flags & WIPHY_WOWLAN_RFKILL_RELEASE) && + nla_put_flag(msg, NL80211_WOWLAN_TRIG_RFKILL_RELEASE))) + goto nla_put_failure; if (dev->wiphy.wowlan.n_patterns) { struct nl80211_wowlan_pattern_support pat = { .max_patterns = dev->wiphy.wowlan.n_patterns, @@ -1018,8 +1051,9 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, .max_pattern_len = dev->wiphy.wowlan.pattern_max_len, }; - NLA_PUT(msg, NL80211_WOWLAN_TRIG_PKT_PATTERN, - sizeof(pat), &pat); + if (nla_put(msg, NL80211_WOWLAN_TRIG_PKT_PATTERN, + sizeof(pat), &pat)) + goto nla_put_failure; } nla_nest_end(msg, nl_wowlan); @@ -1032,16 +1066,20 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, if (nl80211_put_iface_combinations(&dev->wiphy, msg)) goto nla_put_failure; - if (dev->wiphy.flags & WIPHY_FLAG_HAVE_AP_SME) - NLA_PUT_U32(msg, NL80211_ATTR_DEVICE_AP_SME, - dev->wiphy.ap_sme_capa); + if ((dev->wiphy.flags & WIPHY_FLAG_HAVE_AP_SME) && + nla_put_u32(msg, NL80211_ATTR_DEVICE_AP_SME, + dev->wiphy.ap_sme_capa)) + goto nla_put_failure; - NLA_PUT_U32(msg, NL80211_ATTR_FEATURE_FLAGS, dev->wiphy.features); + if (nla_put_u32(msg, NL80211_ATTR_FEATURE_FLAGS, + dev->wiphy.features)) + goto nla_put_failure; - if (dev->wiphy.ht_capa_mod_mask) - NLA_PUT(msg, NL80211_ATTR_HT_CAPABILITY_MASK, - sizeof(*dev->wiphy.ht_capa_mod_mask), - dev->wiphy.ht_capa_mod_mask); + if (dev->wiphy.ht_capa_mod_mask && + nla_put(msg, NL80211_ATTR_HT_CAPABILITY_MASK, + sizeof(*dev->wiphy.ht_capa_mod_mask), + dev->wiphy.ht_capa_mod_mask)) + goto nla_put_failure; return genlmsg_end(msg, hdr); @@ -1104,17 +1142,20 @@ static const struct nla_policy txq_params_policy[NL80211_TXQ_ATTR_MAX + 1] = { static int parse_txq_params(struct nlattr *tb[], struct ieee80211_txq_params *txq_params) { - if (!tb[NL80211_TXQ_ATTR_QUEUE] || !tb[NL80211_TXQ_ATTR_TXOP] || + if (!tb[NL80211_TXQ_ATTR_AC] || !tb[NL80211_TXQ_ATTR_TXOP] || !tb[NL80211_TXQ_ATTR_CWMIN] || !tb[NL80211_TXQ_ATTR_CWMAX] || !tb[NL80211_TXQ_ATTR_AIFS]) return -EINVAL; - txq_params->queue = nla_get_u8(tb[NL80211_TXQ_ATTR_QUEUE]); + txq_params->ac = nla_get_u8(tb[NL80211_TXQ_ATTR_AC]); txq_params->txop = nla_get_u16(tb[NL80211_TXQ_ATTR_TXOP]); txq_params->cwmin = nla_get_u16(tb[NL80211_TXQ_ATTR_CWMIN]); txq_params->cwmax = nla_get_u16(tb[NL80211_TXQ_ATTR_CWMAX]); txq_params->aifs = nla_get_u8(tb[NL80211_TXQ_ATTR_AIFS]); + if (txq_params->ac >= NL80211_NUM_ACS) + return -EINVAL; + return 0; } @@ -1294,6 +1335,11 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) goto bad_res; } + if (!netif_running(netdev)) { + result = -ENETDOWN; + goto bad_res; + } + nla_for_each_nested(nl_txq_params, info->attrs[NL80211_ATTR_WIPHY_TXQ_PARAMS], rem_txq_params) { @@ -1484,14 +1530,28 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 pid, u32 seq, int flags, if (!hdr) return -1; - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, dev->ifindex); - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_STRING(msg, NL80211_ATTR_IFNAME, dev->name); - NLA_PUT_U32(msg, NL80211_ATTR_IFTYPE, dev->ieee80211_ptr->iftype); + if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || + nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_string(msg, NL80211_ATTR_IFNAME, dev->name) || + nla_put_u32(msg, NL80211_ATTR_IFTYPE, + dev->ieee80211_ptr->iftype) || + nla_put_u32(msg, NL80211_ATTR_GENERATION, + rdev->devlist_generation ^ + (cfg80211_rdev_list_generation << 2))) + goto nla_put_failure; - NLA_PUT_U32(msg, NL80211_ATTR_GENERATION, - rdev->devlist_generation ^ - (cfg80211_rdev_list_generation << 2)); + if (rdev->ops->get_channel) { + struct ieee80211_channel *chan; + enum nl80211_channel_type channel_type; + + chan = rdev->ops->get_channel(&rdev->wiphy, &channel_type); + if (chan && + (nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, + chan->center_freq) || + nla_put_u32(msg, NL80211_ATTR_WIPHY_CHANNEL_TYPE, + channel_type))) + goto nla_put_failure; + } return genlmsg_end(msg, hdr); @@ -1789,35 +1849,34 @@ static void get_key_callback(void *c, struct key_params *params) struct nlattr *key; struct get_key_cookie *cookie = c; - if (params->key) - NLA_PUT(cookie->msg, NL80211_ATTR_KEY_DATA, - params->key_len, params->key); - - if (params->seq) - NLA_PUT(cookie->msg, NL80211_ATTR_KEY_SEQ, - params->seq_len, params->seq); - - if (params->cipher) - NLA_PUT_U32(cookie->msg, NL80211_ATTR_KEY_CIPHER, - params->cipher); + if ((params->key && + nla_put(cookie->msg, NL80211_ATTR_KEY_DATA, + params->key_len, params->key)) || + (params->seq && + nla_put(cookie->msg, NL80211_ATTR_KEY_SEQ, + params->seq_len, params->seq)) || + (params->cipher && + nla_put_u32(cookie->msg, NL80211_ATTR_KEY_CIPHER, + params->cipher))) + goto nla_put_failure; key = nla_nest_start(cookie->msg, NL80211_ATTR_KEY); if (!key) goto nla_put_failure; - if (params->key) - NLA_PUT(cookie->msg, NL80211_KEY_DATA, - params->key_len, params->key); - - if (params->seq) - NLA_PUT(cookie->msg, NL80211_KEY_SEQ, - params->seq_len, params->seq); - - if (params->cipher) - NLA_PUT_U32(cookie->msg, NL80211_KEY_CIPHER, - params->cipher); + if ((params->key && + nla_put(cookie->msg, NL80211_KEY_DATA, + params->key_len, params->key)) || + (params->seq && + nla_put(cookie->msg, NL80211_KEY_SEQ, + params->seq_len, params->seq)) || + (params->cipher && + nla_put_u32(cookie->msg, NL80211_KEY_CIPHER, + params->cipher))) + goto nla_put_failure; - NLA_PUT_U8(cookie->msg, NL80211_ATTR_KEY_IDX, cookie->idx); + if (nla_put_u8(cookie->msg, NL80211_ATTR_KEY_IDX, cookie->idx)) + goto nla_put_failure; nla_nest_end(cookie->msg, key); @@ -1875,10 +1934,12 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) cookie.msg = msg; cookie.idx = key_idx; - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, dev->ifindex); - NLA_PUT_U8(msg, NL80211_ATTR_KEY_IDX, key_idx); - if (mac_addr) - NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr); + if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || + nla_put_u8(msg, NL80211_ATTR_KEY_IDX, key_idx)) + goto nla_put_failure; + if (mac_addr && + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr)) + goto nla_put_failure; if (pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) @@ -2368,15 +2429,15 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, /* cfg80211_calculate_bitrate will return 0 for mcs >= 32 */ bitrate = cfg80211_calculate_bitrate(info); - if (bitrate > 0) - NLA_PUT_U16(msg, NL80211_RATE_INFO_BITRATE, bitrate); - - if (info->flags & RATE_INFO_FLAGS_MCS) - NLA_PUT_U8(msg, NL80211_RATE_INFO_MCS, info->mcs); - if (info->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH) - NLA_PUT_FLAG(msg, NL80211_RATE_INFO_40_MHZ_WIDTH); - if (info->flags & RATE_INFO_FLAGS_SHORT_GI) - NLA_PUT_FLAG(msg, NL80211_RATE_INFO_SHORT_GI); + if ((bitrate > 0 && + nla_put_u16(msg, NL80211_RATE_INFO_BITRATE, bitrate)) || + ((info->flags & RATE_INFO_FLAGS_MCS) && + nla_put_u8(msg, NL80211_RATE_INFO_MCS, info->mcs)) || + ((info->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH) && + nla_put_flag(msg, NL80211_RATE_INFO_40_MHZ_WIDTH)) || + ((info->flags & RATE_INFO_FLAGS_SHORT_GI) && + nla_put_flag(msg, NL80211_RATE_INFO_SHORT_GI))) + goto nla_put_failure; nla_nest_end(msg, rate); return true; @@ -2386,7 +2447,9 @@ nla_put_failure: } static int nl80211_send_station(struct sk_buff *msg, u32 pid, u32 seq, - int flags, struct net_device *dev, + int flags, + struct cfg80211_registered_device *rdev, + struct net_device *dev, const u8 *mac_addr, struct station_info *sinfo) { void *hdr; @@ -2396,41 +2459,54 @@ static int nl80211_send_station(struct sk_buff *msg, u32 pid, u32 seq, if (!hdr) return -1; - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, dev->ifindex); - NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr); - - NLA_PUT_U32(msg, NL80211_ATTR_GENERATION, sinfo->generation); + if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr) || + nla_put_u32(msg, NL80211_ATTR_GENERATION, sinfo->generation)) + goto nla_put_failure; sinfoattr = nla_nest_start(msg, NL80211_ATTR_STA_INFO); if (!sinfoattr) goto nla_put_failure; - if (sinfo->filled & STATION_INFO_CONNECTED_TIME) - NLA_PUT_U32(msg, NL80211_STA_INFO_CONNECTED_TIME, - sinfo->connected_time); - if (sinfo->filled & STATION_INFO_INACTIVE_TIME) - NLA_PUT_U32(msg, NL80211_STA_INFO_INACTIVE_TIME, - sinfo->inactive_time); - if (sinfo->filled & STATION_INFO_RX_BYTES) - NLA_PUT_U32(msg, NL80211_STA_INFO_RX_BYTES, - sinfo->rx_bytes); - if (sinfo->filled & STATION_INFO_TX_BYTES) - NLA_PUT_U32(msg, NL80211_STA_INFO_TX_BYTES, - sinfo->tx_bytes); - if (sinfo->filled & STATION_INFO_LLID) - NLA_PUT_U16(msg, NL80211_STA_INFO_LLID, - sinfo->llid); - if (sinfo->filled & STATION_INFO_PLID) - NLA_PUT_U16(msg, NL80211_STA_INFO_PLID, - sinfo->plid); - if (sinfo->filled & STATION_INFO_PLINK_STATE) - NLA_PUT_U8(msg, NL80211_STA_INFO_PLINK_STATE, - sinfo->plink_state); - if (sinfo->filled & STATION_INFO_SIGNAL) - NLA_PUT_U8(msg, NL80211_STA_INFO_SIGNAL, - sinfo->signal); - if (sinfo->filled & STATION_INFO_SIGNAL_AVG) - NLA_PUT_U8(msg, NL80211_STA_INFO_SIGNAL_AVG, - sinfo->signal_avg); + if ((sinfo->filled & STATION_INFO_CONNECTED_TIME) && + nla_put_u32(msg, NL80211_STA_INFO_CONNECTED_TIME, + sinfo->connected_time)) + goto nla_put_failure; + if ((sinfo->filled & STATION_INFO_INACTIVE_TIME) && + nla_put_u32(msg, NL80211_STA_INFO_INACTIVE_TIME, + sinfo->inactive_time)) + goto nla_put_failure; + if ((sinfo->filled & STATION_INFO_RX_BYTES) && + nla_put_u32(msg, NL80211_STA_INFO_RX_BYTES, + sinfo->rx_bytes)) + goto nla_put_failure; + if ((sinfo->filled & STATION_INFO_TX_BYTES) && + nla_put_u32(msg, NL80211_STA_INFO_TX_BYTES, + sinfo->tx_bytes)) + goto nla_put_failure; + if ((sinfo->filled & STATION_INFO_LLID) && + nla_put_u16(msg, NL80211_STA_INFO_LLID, sinfo->llid)) + goto nla_put_failure; + if ((sinfo->filled & STATION_INFO_PLID) && + nla_put_u16(msg, NL80211_STA_INFO_PLID, sinfo->plid)) + goto nla_put_failure; + if ((sinfo->filled & STATION_INFO_PLINK_STATE) && + nla_put_u8(msg, NL80211_STA_INFO_PLINK_STATE, + sinfo->plink_state)) + goto nla_put_failure; + switch (rdev->wiphy.signal_type) { + case CFG80211_SIGNAL_TYPE_MBM: + if ((sinfo->filled & STATION_INFO_SIGNAL) && + nla_put_u8(msg, NL80211_STA_INFO_SIGNAL, + sinfo->signal)) + goto nla_put_failure; + if ((sinfo->filled & STATION_INFO_SIGNAL_AVG) && + nla_put_u8(msg, NL80211_STA_INFO_SIGNAL_AVG, + sinfo->signal_avg)) + goto nla_put_failure; + break; + default: + break; + } if (sinfo->filled & STATION_INFO_TX_BITRATE) { if (!nl80211_put_sta_rate(msg, &sinfo->txrate, NL80211_STA_INFO_TX_BITRATE)) @@ -2441,49 +2517,60 @@ static int nl80211_send_station(struct sk_buff *msg, u32 pid, u32 seq, NL80211_STA_INFO_RX_BITRATE)) goto nla_put_failure; } - if (sinfo->filled & STATION_INFO_RX_PACKETS) - NLA_PUT_U32(msg, NL80211_STA_INFO_RX_PACKETS, - sinfo->rx_packets); - if (sinfo->filled & STATION_INFO_TX_PACKETS) - NLA_PUT_U32(msg, NL80211_STA_INFO_TX_PACKETS, - sinfo->tx_packets); - if (sinfo->filled & STATION_INFO_TX_RETRIES) - NLA_PUT_U32(msg, NL80211_STA_INFO_TX_RETRIES, - sinfo->tx_retries); - if (sinfo->filled & STATION_INFO_TX_FAILED) - NLA_PUT_U32(msg, NL80211_STA_INFO_TX_FAILED, - sinfo->tx_failed); - if (sinfo->filled & STATION_INFO_BEACON_LOSS_COUNT) - NLA_PUT_U32(msg, NL80211_STA_INFO_BEACON_LOSS, - sinfo->beacon_loss_count); + if ((sinfo->filled & STATION_INFO_RX_PACKETS) && + nla_put_u32(msg, NL80211_STA_INFO_RX_PACKETS, + sinfo->rx_packets)) + goto nla_put_failure; + if ((sinfo->filled & STATION_INFO_TX_PACKETS) && + nla_put_u32(msg, NL80211_STA_INFO_TX_PACKETS, + sinfo->tx_packets)) + goto nla_put_failure; + if ((sinfo->filled & STATION_INFO_TX_RETRIES) && + nla_put_u32(msg, NL80211_STA_INFO_TX_RETRIES, + sinfo->tx_retries)) + goto nla_put_failure; + if ((sinfo->filled & STATION_INFO_TX_FAILED) && + nla_put_u32(msg, NL80211_STA_INFO_TX_FAILED, + sinfo->tx_failed)) + goto nla_put_failure; + if ((sinfo->filled & STATION_INFO_BEACON_LOSS_COUNT) && + nla_put_u32(msg, NL80211_STA_INFO_BEACON_LOSS, + sinfo->beacon_loss_count)) + goto nla_put_failure; if (sinfo->filled & STATION_INFO_BSS_PARAM) { bss_param = nla_nest_start(msg, NL80211_STA_INFO_BSS_PARAM); if (!bss_param) goto nla_put_failure; - if (sinfo->bss_param.flags & BSS_PARAM_FLAGS_CTS_PROT) - NLA_PUT_FLAG(msg, NL80211_STA_BSS_PARAM_CTS_PROT); - if (sinfo->bss_param.flags & BSS_PARAM_FLAGS_SHORT_PREAMBLE) - NLA_PUT_FLAG(msg, NL80211_STA_BSS_PARAM_SHORT_PREAMBLE); - if (sinfo->bss_param.flags & BSS_PARAM_FLAGS_SHORT_SLOT_TIME) - NLA_PUT_FLAG(msg, - NL80211_STA_BSS_PARAM_SHORT_SLOT_TIME); - NLA_PUT_U8(msg, NL80211_STA_BSS_PARAM_DTIM_PERIOD, - sinfo->bss_param.dtim_period); - NLA_PUT_U16(msg, NL80211_STA_BSS_PARAM_BEACON_INTERVAL, - sinfo->bss_param.beacon_interval); + if (((sinfo->bss_param.flags & BSS_PARAM_FLAGS_CTS_PROT) && + nla_put_flag(msg, NL80211_STA_BSS_PARAM_CTS_PROT)) || + ((sinfo->bss_param.flags & BSS_PARAM_FLAGS_SHORT_PREAMBLE) && + nla_put_flag(msg, NL80211_STA_BSS_PARAM_SHORT_PREAMBLE)) || + ((sinfo->bss_param.flags & BSS_PARAM_FLAGS_SHORT_SLOT_TIME) && + nla_put_flag(msg, NL80211_STA_BSS_PARAM_SHORT_SLOT_TIME)) || + nla_put_u8(msg, NL80211_STA_BSS_PARAM_DTIM_PERIOD, + sinfo->bss_param.dtim_period) || + nla_put_u16(msg, NL80211_STA_BSS_PARAM_BEACON_INTERVAL, + sinfo->bss_param.beacon_interval)) + goto nla_put_failure; nla_nest_end(msg, bss_param); } - if (sinfo->filled & STATION_INFO_STA_FLAGS) - NLA_PUT(msg, NL80211_STA_INFO_STA_FLAGS, - sizeof(struct nl80211_sta_flag_update), - &sinfo->sta_flags); + if ((sinfo->filled & STATION_INFO_STA_FLAGS) && + nla_put(msg, NL80211_STA_INFO_STA_FLAGS, + sizeof(struct nl80211_sta_flag_update), + &sinfo->sta_flags)) + goto nla_put_failure; + if ((sinfo->filled & STATION_INFO_T_OFFSET) && + nla_put_u64(msg, NL80211_STA_INFO_T_OFFSET, + sinfo->t_offset)) + goto nla_put_failure; nla_nest_end(msg, sinfoattr); - if (sinfo->filled & STATION_INFO_ASSOC_REQ_IES) - NLA_PUT(msg, NL80211_ATTR_IE, sinfo->assoc_req_ies_len, - sinfo->assoc_req_ies); + if ((sinfo->filled & STATION_INFO_ASSOC_REQ_IES) && + nla_put(msg, NL80211_ATTR_IE, sinfo->assoc_req_ies_len, + sinfo->assoc_req_ies)) + goto nla_put_failure; return genlmsg_end(msg, hdr); @@ -2523,7 +2610,7 @@ static int nl80211_dump_station(struct sk_buff *skb, if (nl80211_send_station(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - netdev, mac_addr, + dev, netdev, mac_addr, &sinfo) < 0) goto out; @@ -2568,7 +2655,7 @@ static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; if (nl80211_send_station(msg, info->snd_pid, info->snd_seq, 0, - dev, mac_addr, &sinfo) < 0) { + rdev, dev, mac_addr, &sinfo) < 0) { nlmsg_free(msg); return -ENOBUFS; } @@ -2905,36 +2992,37 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 pid, u32 seq, if (!hdr) return -1; - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, dev->ifindex); - NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, dst); - NLA_PUT(msg, NL80211_ATTR_MPATH_NEXT_HOP, ETH_ALEN, next_hop); - - NLA_PUT_U32(msg, NL80211_ATTR_GENERATION, pinfo->generation); + if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, dst) || + nla_put(msg, NL80211_ATTR_MPATH_NEXT_HOP, ETH_ALEN, next_hop) || + nla_put_u32(msg, NL80211_ATTR_GENERATION, pinfo->generation)) + goto nla_put_failure; pinfoattr = nla_nest_start(msg, NL80211_ATTR_MPATH_INFO); if (!pinfoattr) goto nla_put_failure; - if (pinfo->filled & MPATH_INFO_FRAME_QLEN) - NLA_PUT_U32(msg, NL80211_MPATH_INFO_FRAME_QLEN, - pinfo->frame_qlen); - if (pinfo->filled & MPATH_INFO_SN) - NLA_PUT_U32(msg, NL80211_MPATH_INFO_SN, - pinfo->sn); - if (pinfo->filled & MPATH_INFO_METRIC) - NLA_PUT_U32(msg, NL80211_MPATH_INFO_METRIC, - pinfo->metric); - if (pinfo->filled & MPATH_INFO_EXPTIME) - NLA_PUT_U32(msg, NL80211_MPATH_INFO_EXPTIME, - pinfo->exptime); - if (pinfo->filled & MPATH_INFO_FLAGS) - NLA_PUT_U8(msg, NL80211_MPATH_INFO_FLAGS, - pinfo->flags); - if (pinfo->filled & MPATH_INFO_DISCOVERY_TIMEOUT) - NLA_PUT_U32(msg, NL80211_MPATH_INFO_DISCOVERY_TIMEOUT, - pinfo->discovery_timeout); - if (pinfo->filled & MPATH_INFO_DISCOVERY_RETRIES) - NLA_PUT_U8(msg, NL80211_MPATH_INFO_DISCOVERY_RETRIES, - pinfo->discovery_retries); + if ((pinfo->filled & MPATH_INFO_FRAME_QLEN) && + nla_put_u32(msg, NL80211_MPATH_INFO_FRAME_QLEN, + pinfo->frame_qlen)) + goto nla_put_failure; + if (((pinfo->filled & MPATH_INFO_SN) && + nla_put_u32(msg, NL80211_MPATH_INFO_SN, pinfo->sn)) || + ((pinfo->filled & MPATH_INFO_METRIC) && + nla_put_u32(msg, NL80211_MPATH_INFO_METRIC, + pinfo->metric)) || + ((pinfo->filled & MPATH_INFO_EXPTIME) && + nla_put_u32(msg, NL80211_MPATH_INFO_EXPTIME, + pinfo->exptime)) || + ((pinfo->filled & MPATH_INFO_FLAGS) && + nla_put_u8(msg, NL80211_MPATH_INFO_FLAGS, + pinfo->flags)) || + ((pinfo->filled & MPATH_INFO_DISCOVERY_TIMEOUT) && + nla_put_u32(msg, NL80211_MPATH_INFO_DISCOVERY_TIMEOUT, + pinfo->discovery_timeout)) || + ((pinfo->filled & MPATH_INFO_DISCOVERY_RETRIES) && + nla_put_u8(msg, NL80211_MPATH_INFO_DISCOVERY_RETRIES, + pinfo->discovery_retries))) + goto nla_put_failure; nla_nest_end(msg, pinfoattr); @@ -3260,47 +3348,52 @@ static int nl80211_get_mesh_config(struct sk_buff *skb, pinfoattr = nla_nest_start(msg, NL80211_ATTR_MESH_CONFIG); if (!pinfoattr) goto nla_put_failure; - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, dev->ifindex); - NLA_PUT_U16(msg, NL80211_MESHCONF_RETRY_TIMEOUT, - cur_params.dot11MeshRetryTimeout); - NLA_PUT_U16(msg, NL80211_MESHCONF_CONFIRM_TIMEOUT, - cur_params.dot11MeshConfirmTimeout); - NLA_PUT_U16(msg, NL80211_MESHCONF_HOLDING_TIMEOUT, - cur_params.dot11MeshHoldingTimeout); - NLA_PUT_U16(msg, NL80211_MESHCONF_MAX_PEER_LINKS, - cur_params.dot11MeshMaxPeerLinks); - NLA_PUT_U8(msg, NL80211_MESHCONF_MAX_RETRIES, - cur_params.dot11MeshMaxRetries); - NLA_PUT_U8(msg, NL80211_MESHCONF_TTL, - cur_params.dot11MeshTTL); - NLA_PUT_U8(msg, NL80211_MESHCONF_ELEMENT_TTL, - cur_params.element_ttl); - NLA_PUT_U8(msg, NL80211_MESHCONF_AUTO_OPEN_PLINKS, - cur_params.auto_open_plinks); - NLA_PUT_U8(msg, NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES, - cur_params.dot11MeshHWMPmaxPREQretries); - NLA_PUT_U32(msg, NL80211_MESHCONF_PATH_REFRESH_TIME, - cur_params.path_refresh_time); - NLA_PUT_U16(msg, NL80211_MESHCONF_MIN_DISCOVERY_TIMEOUT, - cur_params.min_discovery_timeout); - NLA_PUT_U32(msg, NL80211_MESHCONF_HWMP_ACTIVE_PATH_TIMEOUT, - cur_params.dot11MeshHWMPactivePathTimeout); - NLA_PUT_U16(msg, NL80211_MESHCONF_HWMP_PREQ_MIN_INTERVAL, - cur_params.dot11MeshHWMPpreqMinInterval); - NLA_PUT_U16(msg, NL80211_MESHCONF_HWMP_PERR_MIN_INTERVAL, - cur_params.dot11MeshHWMPperrMinInterval); - NLA_PUT_U16(msg, NL80211_MESHCONF_HWMP_NET_DIAM_TRVS_TIME, - cur_params.dot11MeshHWMPnetDiameterTraversalTime); - NLA_PUT_U8(msg, NL80211_MESHCONF_HWMP_ROOTMODE, - cur_params.dot11MeshHWMPRootMode); - NLA_PUT_U16(msg, NL80211_MESHCONF_HWMP_RANN_INTERVAL, - cur_params.dot11MeshHWMPRannInterval); - NLA_PUT_U8(msg, NL80211_MESHCONF_GATE_ANNOUNCEMENTS, - cur_params.dot11MeshGateAnnouncementProtocol); - NLA_PUT_U8(msg, NL80211_MESHCONF_FORWARDING, - cur_params.dot11MeshForwarding); - NLA_PUT_U32(msg, NL80211_MESHCONF_RSSI_THRESHOLD, - cur_params.rssi_threshold); + if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || + nla_put_u16(msg, NL80211_MESHCONF_RETRY_TIMEOUT, + cur_params.dot11MeshRetryTimeout) || + nla_put_u16(msg, NL80211_MESHCONF_CONFIRM_TIMEOUT, + cur_params.dot11MeshConfirmTimeout) || + nla_put_u16(msg, NL80211_MESHCONF_HOLDING_TIMEOUT, + cur_params.dot11MeshHoldingTimeout) || + nla_put_u16(msg, NL80211_MESHCONF_MAX_PEER_LINKS, + cur_params.dot11MeshMaxPeerLinks) || + nla_put_u8(msg, NL80211_MESHCONF_MAX_RETRIES, + cur_params.dot11MeshMaxRetries) || + nla_put_u8(msg, NL80211_MESHCONF_TTL, + cur_params.dot11MeshTTL) || + nla_put_u8(msg, NL80211_MESHCONF_ELEMENT_TTL, + cur_params.element_ttl) || + nla_put_u8(msg, NL80211_MESHCONF_AUTO_OPEN_PLINKS, + cur_params.auto_open_plinks) || + nla_put_u32(msg, NL80211_MESHCONF_SYNC_OFFSET_MAX_NEIGHBOR, + cur_params.dot11MeshNbrOffsetMaxNeighbor) || + nla_put_u8(msg, NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES, + cur_params.dot11MeshHWMPmaxPREQretries) || + nla_put_u32(msg, NL80211_MESHCONF_PATH_REFRESH_TIME, + cur_params.path_refresh_time) || + nla_put_u16(msg, NL80211_MESHCONF_MIN_DISCOVERY_TIMEOUT, + cur_params.min_discovery_timeout) || + nla_put_u32(msg, NL80211_MESHCONF_HWMP_ACTIVE_PATH_TIMEOUT, + cur_params.dot11MeshHWMPactivePathTimeout) || + nla_put_u16(msg, NL80211_MESHCONF_HWMP_PREQ_MIN_INTERVAL, + cur_params.dot11MeshHWMPpreqMinInterval) || + nla_put_u16(msg, NL80211_MESHCONF_HWMP_PERR_MIN_INTERVAL, + cur_params.dot11MeshHWMPperrMinInterval) || + nla_put_u16(msg, NL80211_MESHCONF_HWMP_NET_DIAM_TRVS_TIME, + cur_params.dot11MeshHWMPnetDiameterTraversalTime) || + nla_put_u8(msg, NL80211_MESHCONF_HWMP_ROOTMODE, + cur_params.dot11MeshHWMPRootMode) || + nla_put_u16(msg, NL80211_MESHCONF_HWMP_RANN_INTERVAL, + cur_params.dot11MeshHWMPRannInterval) || + nla_put_u8(msg, NL80211_MESHCONF_GATE_ANNOUNCEMENTS, + cur_params.dot11MeshGateAnnouncementProtocol) || + nla_put_u8(msg, NL80211_MESHCONF_FORWARDING, + cur_params.dot11MeshForwarding) || + nla_put_u32(msg, NL80211_MESHCONF_RSSI_THRESHOLD, + cur_params.rssi_threshold) || + nla_put_u32(msg, NL80211_MESHCONF_HT_OPMODE, + cur_params.ht_opmode)) + goto nla_put_failure; nla_nest_end(msg, pinfoattr); genlmsg_end(msg, hdr); return genlmsg_reply(msg, info); @@ -3321,6 +3414,7 @@ static const struct nla_policy nl80211_meshconf_params_policy[NL80211_MESHCONF_A [NL80211_MESHCONF_TTL] = { .type = NLA_U8 }, [NL80211_MESHCONF_ELEMENT_TTL] = { .type = NLA_U8 }, [NL80211_MESHCONF_AUTO_OPEN_PLINKS] = { .type = NLA_U8 }, + [NL80211_MESHCONF_SYNC_OFFSET_MAX_NEIGHBOR] = { .type = NLA_U32 }, [NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES] = { .type = NLA_U8 }, [NL80211_MESHCONF_PATH_REFRESH_TIME] = { .type = NLA_U32 }, @@ -3334,10 +3428,12 @@ static const struct nla_policy nl80211_meshconf_params_policy[NL80211_MESHCONF_A [NL80211_MESHCONF_GATE_ANNOUNCEMENTS] = { .type = NLA_U8 }, [NL80211_MESHCONF_FORWARDING] = { .type = NLA_U8 }, [NL80211_MESHCONF_RSSI_THRESHOLD] = { .type = NLA_U32}, + [NL80211_MESHCONF_HT_OPMODE] = { .type = NLA_U16}, }; static const struct nla_policy nl80211_mesh_setup_params_policy[NL80211_MESH_SETUP_ATTR_MAX+1] = { + [NL80211_MESH_SETUP_ENABLE_VENDOR_SYNC] = { .type = NLA_U8 }, [NL80211_MESH_SETUP_ENABLE_VENDOR_PATH_SEL] = { .type = NLA_U8 }, [NL80211_MESH_SETUP_ENABLE_VENDOR_METRIC] = { .type = NLA_U8 }, [NL80211_MESH_SETUP_USERSPACE_AUTH] = { .type = NLA_FLAG }, @@ -3390,6 +3486,9 @@ do {\ mask, NL80211_MESHCONF_ELEMENT_TTL, nla_get_u8); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, auto_open_plinks, mask, NL80211_MESHCONF_AUTO_OPEN_PLINKS, nla_get_u8); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshNbrOffsetMaxNeighbor, + mask, NL80211_MESHCONF_SYNC_OFFSET_MAX_NEIGHBOR, + nla_get_u32); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPmaxPREQretries, mask, NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES, nla_get_u8); @@ -3427,6 +3526,8 @@ do {\ mask, NL80211_MESHCONF_FORWARDING, nla_get_u8); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, rssi_threshold, mask, NL80211_MESHCONF_RSSI_THRESHOLD, nla_get_u32); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, ht_opmode, + mask, NL80211_MESHCONF_HT_OPMODE, nla_get_u16); if (mask_out) *mask_out = mask; @@ -3447,6 +3548,12 @@ static int nl80211_parse_mesh_setup(struct genl_info *info, nl80211_mesh_setup_params_policy)) return -EINVAL; + if (tb[NL80211_MESH_SETUP_ENABLE_VENDOR_SYNC]) + setup->sync_method = + (nla_get_u8(tb[NL80211_MESH_SETUP_ENABLE_VENDOR_SYNC])) ? + IEEE80211_SYNC_METHOD_VENDOR : + IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET; + if (tb[NL80211_MESH_SETUP_ENABLE_VENDOR_PATH_SEL]) setup->path_sel_proto = (nla_get_u8(tb[NL80211_MESH_SETUP_ENABLE_VENDOR_PATH_SEL])) ? @@ -3531,11 +3638,12 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) if (!hdr) goto put_failure; - NLA_PUT_STRING(msg, NL80211_ATTR_REG_ALPHA2, - cfg80211_regdomain->alpha2); - if (cfg80211_regdomain->dfs_region) - NLA_PUT_U8(msg, NL80211_ATTR_DFS_REGION, - cfg80211_regdomain->dfs_region); + if (nla_put_string(msg, NL80211_ATTR_REG_ALPHA2, + cfg80211_regdomain->alpha2) || + (cfg80211_regdomain->dfs_region && + nla_put_u8(msg, NL80211_ATTR_DFS_REGION, + cfg80211_regdomain->dfs_region))) + goto nla_put_failure; nl_reg_rules = nla_nest_start(msg, NL80211_ATTR_REG_RULES); if (!nl_reg_rules) @@ -3555,18 +3663,19 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) if (!nl_reg_rule) goto nla_put_failure; - NLA_PUT_U32(msg, NL80211_ATTR_REG_RULE_FLAGS, - reg_rule->flags); - NLA_PUT_U32(msg, NL80211_ATTR_FREQ_RANGE_START, - freq_range->start_freq_khz); - NLA_PUT_U32(msg, NL80211_ATTR_FREQ_RANGE_END, - freq_range->end_freq_khz); - NLA_PUT_U32(msg, NL80211_ATTR_FREQ_RANGE_MAX_BW, - freq_range->max_bandwidth_khz); - NLA_PUT_U32(msg, NL80211_ATTR_POWER_RULE_MAX_ANT_GAIN, - power_rule->max_antenna_gain); - NLA_PUT_U32(msg, NL80211_ATTR_POWER_RULE_MAX_EIRP, - power_rule->max_eirp); + if (nla_put_u32(msg, NL80211_ATTR_REG_RULE_FLAGS, + reg_rule->flags) || + nla_put_u32(msg, NL80211_ATTR_FREQ_RANGE_START, + freq_range->start_freq_khz) || + nla_put_u32(msg, NL80211_ATTR_FREQ_RANGE_END, + freq_range->end_freq_khz) || + nla_put_u32(msg, NL80211_ATTR_FREQ_RANGE_MAX_BW, + freq_range->max_bandwidth_khz) || + nla_put_u32(msg, NL80211_ATTR_POWER_RULE_MAX_ANT_GAIN, + power_rule->max_antenna_gain) || + nla_put_u32(msg, NL80211_ATTR_POWER_RULE_MAX_EIRP, + power_rule->max_eirp)) + goto nla_put_failure; nla_nest_end(msg, nl_reg_rule); } @@ -4137,37 +4246,44 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, genl_dump_check_consistent(cb, hdr, &nl80211_fam); - NLA_PUT_U32(msg, NL80211_ATTR_GENERATION, rdev->bss_generation); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, wdev->netdev->ifindex); + if (nla_put_u32(msg, NL80211_ATTR_GENERATION, rdev->bss_generation) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, wdev->netdev->ifindex)) + goto nla_put_failure; bss = nla_nest_start(msg, NL80211_ATTR_BSS); if (!bss) goto nla_put_failure; - if (!is_zero_ether_addr(res->bssid)) - NLA_PUT(msg, NL80211_BSS_BSSID, ETH_ALEN, res->bssid); - if (res->information_elements && res->len_information_elements) - NLA_PUT(msg, NL80211_BSS_INFORMATION_ELEMENTS, - res->len_information_elements, - res->information_elements); - if (res->beacon_ies && res->len_beacon_ies && - res->beacon_ies != res->information_elements) - NLA_PUT(msg, NL80211_BSS_BEACON_IES, - res->len_beacon_ies, res->beacon_ies); - if (res->tsf) - NLA_PUT_U64(msg, NL80211_BSS_TSF, res->tsf); - if (res->beacon_interval) - NLA_PUT_U16(msg, NL80211_BSS_BEACON_INTERVAL, res->beacon_interval); - NLA_PUT_U16(msg, NL80211_BSS_CAPABILITY, res->capability); - NLA_PUT_U32(msg, NL80211_BSS_FREQUENCY, res->channel->center_freq); - NLA_PUT_U32(msg, NL80211_BSS_SEEN_MS_AGO, - jiffies_to_msecs(jiffies - intbss->ts)); + if ((!is_zero_ether_addr(res->bssid) && + nla_put(msg, NL80211_BSS_BSSID, ETH_ALEN, res->bssid)) || + (res->information_elements && res->len_information_elements && + nla_put(msg, NL80211_BSS_INFORMATION_ELEMENTS, + res->len_information_elements, + res->information_elements)) || + (res->beacon_ies && res->len_beacon_ies && + res->beacon_ies != res->information_elements && + nla_put(msg, NL80211_BSS_BEACON_IES, + res->len_beacon_ies, res->beacon_ies))) + goto nla_put_failure; + if (res->tsf && + nla_put_u64(msg, NL80211_BSS_TSF, res->tsf)) + goto nla_put_failure; + if (res->beacon_interval && + nla_put_u16(msg, NL80211_BSS_BEACON_INTERVAL, res->beacon_interval)) + goto nla_put_failure; + if (nla_put_u16(msg, NL80211_BSS_CAPABILITY, res->capability) || + nla_put_u32(msg, NL80211_BSS_FREQUENCY, res->channel->center_freq) || + nla_put_u32(msg, NL80211_BSS_SEEN_MS_AGO, + jiffies_to_msecs(jiffies - intbss->ts))) + goto nla_put_failure; switch (rdev->wiphy.signal_type) { case CFG80211_SIGNAL_TYPE_MBM: - NLA_PUT_U32(msg, NL80211_BSS_SIGNAL_MBM, res->signal); + if (nla_put_u32(msg, NL80211_BSS_SIGNAL_MBM, res->signal)) + goto nla_put_failure; break; case CFG80211_SIGNAL_TYPE_UNSPEC: - NLA_PUT_U8(msg, NL80211_BSS_SIGNAL_UNSPEC, res->signal); + if (nla_put_u8(msg, NL80211_BSS_SIGNAL_UNSPEC, res->signal)) + goto nla_put_failure; break; default: break; @@ -4176,14 +4292,16 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, switch (wdev->iftype) { case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_STATION: - if (intbss == wdev->current_bss) - NLA_PUT_U32(msg, NL80211_BSS_STATUS, - NL80211_BSS_STATUS_ASSOCIATED); + if (intbss == wdev->current_bss && + nla_put_u32(msg, NL80211_BSS_STATUS, + NL80211_BSS_STATUS_ASSOCIATED)) + goto nla_put_failure; break; case NL80211_IFTYPE_ADHOC: - if (intbss == wdev->current_bss) - NLA_PUT_U32(msg, NL80211_BSS_STATUS, - NL80211_BSS_STATUS_IBSS_JOINED); + if (intbss == wdev->current_bss && + nla_put_u32(msg, NL80211_BSS_STATUS, + NL80211_BSS_STATUS_IBSS_JOINED)) + goto nla_put_failure; break; default: break; @@ -4252,34 +4370,43 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 pid, u32 seq, if (!hdr) return -ENOMEM; - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, dev->ifindex); + if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex)) + goto nla_put_failure; infoattr = nla_nest_start(msg, NL80211_ATTR_SURVEY_INFO); if (!infoattr) goto nla_put_failure; - NLA_PUT_U32(msg, NL80211_SURVEY_INFO_FREQUENCY, - survey->channel->center_freq); - if (survey->filled & SURVEY_INFO_NOISE_DBM) - NLA_PUT_U8(msg, NL80211_SURVEY_INFO_NOISE, - survey->noise); - if (survey->filled & SURVEY_INFO_IN_USE) - NLA_PUT_FLAG(msg, NL80211_SURVEY_INFO_IN_USE); - if (survey->filled & SURVEY_INFO_CHANNEL_TIME) - NLA_PUT_U64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME, - survey->channel_time); - if (survey->filled & SURVEY_INFO_CHANNEL_TIME_BUSY) - NLA_PUT_U64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_BUSY, - survey->channel_time_busy); - if (survey->filled & SURVEY_INFO_CHANNEL_TIME_EXT_BUSY) - NLA_PUT_U64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_EXT_BUSY, - survey->channel_time_ext_busy); - if (survey->filled & SURVEY_INFO_CHANNEL_TIME_RX) - NLA_PUT_U64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_RX, - survey->channel_time_rx); - if (survey->filled & SURVEY_INFO_CHANNEL_TIME_TX) - NLA_PUT_U64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_TX, - survey->channel_time_tx); + if (nla_put_u32(msg, NL80211_SURVEY_INFO_FREQUENCY, + survey->channel->center_freq)) + goto nla_put_failure; + + if ((survey->filled & SURVEY_INFO_NOISE_DBM) && + nla_put_u8(msg, NL80211_SURVEY_INFO_NOISE, survey->noise)) + goto nla_put_failure; + if ((survey->filled & SURVEY_INFO_IN_USE) && + nla_put_flag(msg, NL80211_SURVEY_INFO_IN_USE)) + goto nla_put_failure; + if ((survey->filled & SURVEY_INFO_CHANNEL_TIME) && + nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME, + survey->channel_time)) + goto nla_put_failure; + if ((survey->filled & SURVEY_INFO_CHANNEL_TIME_BUSY) && + nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_BUSY, + survey->channel_time_busy)) + goto nla_put_failure; + if ((survey->filled & SURVEY_INFO_CHANNEL_TIME_EXT_BUSY) && + nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_EXT_BUSY, + survey->channel_time_ext_busy)) + goto nla_put_failure; + if ((survey->filled & SURVEY_INFO_CHANNEL_TIME_RX) && + nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_RX, + survey->channel_time_rx)) + goto nla_put_failure; + if ((survey->filled & SURVEY_INFO_CHANNEL_TIME_TX) && + nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_TX, + survey->channel_time_tx)) + goto nla_put_failure; nla_nest_end(msg, infoattr); @@ -4960,7 +5087,7 @@ static int nl80211_testmode_dump(struct sk_buff *skb, NL80211_CMD_TESTMODE); struct nlattr *tmdata; - if (nla_put_u32(skb, NL80211_ATTR_WIPHY, phy_idx) < 0) { + if (nla_put_u32(skb, NL80211_ATTR_WIPHY, phy_idx)) { genlmsg_cancel(skb, hdr); break; } @@ -5011,7 +5138,8 @@ __cfg80211_testmode_alloc_skb(struct cfg80211_registered_device *rdev, return NULL; } - NLA_PUT_U32(skb, NL80211_ATTR_WIPHY, rdev->wiphy_idx); + if (nla_put_u32(skb, NL80211_ATTR_WIPHY, rdev->wiphy_idx)) + goto nla_put_failure; data = nla_nest_start(skb, NL80211_ATTR_TESTDATA); ((void **)skb->cb)[0] = rdev; @@ -5390,7 +5518,8 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, if (err) goto free_msg; - NLA_PUT_U64(msg, NL80211_ATTR_COOKIE, cookie); + if (nla_put_u64(msg, NL80211_ATTR_COOKIE, cookie)) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -5532,6 +5661,9 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, sband, nla_data(tb[NL80211_TXRATE_LEGACY]), nla_len(tb[NL80211_TXRATE_LEGACY])); + if ((mask.control[band].legacy == 0) && + nla_len(tb[NL80211_TXRATE_LEGACY])) + return -EINVAL; } if (tb[NL80211_TXRATE_MCS]) { if (!ht_rateset_to_mask( @@ -5677,7 +5809,8 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) goto free_msg; if (msg) { - NLA_PUT_U64(msg, NL80211_ATTR_COOKIE, cookie); + if (nla_put_u64(msg, NL80211_ATTR_COOKIE, cookie)) + goto nla_put_failure; genlmsg_end(msg, hdr); return genlmsg_reply(msg, info); @@ -5782,7 +5915,8 @@ static int nl80211_get_power_save(struct sk_buff *skb, struct genl_info *info) else ps_state = NL80211_PS_DISABLED; - NLA_PUT_U32(msg, NL80211_ATTR_PS_STATE, ps_state); + if (nla_put_u32(msg, NL80211_ATTR_PS_STATE, ps_state)) + goto nla_put_failure; genlmsg_end(msg, hdr); return genlmsg_reply(msg, info); @@ -5929,20 +6063,21 @@ static int nl80211_get_wowlan(struct sk_buff *skb, struct genl_info *info) if (!nl_wowlan) goto nla_put_failure; - if (rdev->wowlan->any) - NLA_PUT_FLAG(msg, NL80211_WOWLAN_TRIG_ANY); - if (rdev->wowlan->disconnect) - NLA_PUT_FLAG(msg, NL80211_WOWLAN_TRIG_DISCONNECT); - if (rdev->wowlan->magic_pkt) - NLA_PUT_FLAG(msg, NL80211_WOWLAN_TRIG_MAGIC_PKT); - if (rdev->wowlan->gtk_rekey_failure) - NLA_PUT_FLAG(msg, NL80211_WOWLAN_TRIG_GTK_REKEY_FAILURE); - if (rdev->wowlan->eap_identity_req) - NLA_PUT_FLAG(msg, NL80211_WOWLAN_TRIG_EAP_IDENT_REQUEST); - if (rdev->wowlan->four_way_handshake) - NLA_PUT_FLAG(msg, NL80211_WOWLAN_TRIG_4WAY_HANDSHAKE); - if (rdev->wowlan->rfkill_release) - NLA_PUT_FLAG(msg, NL80211_WOWLAN_TRIG_RFKILL_RELEASE); + if ((rdev->wowlan->any && + nla_put_flag(msg, NL80211_WOWLAN_TRIG_ANY)) || + (rdev->wowlan->disconnect && + nla_put_flag(msg, NL80211_WOWLAN_TRIG_DISCONNECT)) || + (rdev->wowlan->magic_pkt && + nla_put_flag(msg, NL80211_WOWLAN_TRIG_MAGIC_PKT)) || + (rdev->wowlan->gtk_rekey_failure && + nla_put_flag(msg, NL80211_WOWLAN_TRIG_GTK_REKEY_FAILURE)) || + (rdev->wowlan->eap_identity_req && + nla_put_flag(msg, NL80211_WOWLAN_TRIG_EAP_IDENT_REQUEST)) || + (rdev->wowlan->four_way_handshake && + nla_put_flag(msg, NL80211_WOWLAN_TRIG_4WAY_HANDSHAKE)) || + (rdev->wowlan->rfkill_release && + nla_put_flag(msg, NL80211_WOWLAN_TRIG_RFKILL_RELEASE))) + goto nla_put_failure; if (rdev->wowlan->n_patterns) { struct nlattr *nl_pats, *nl_pat; int i, pat_len; @@ -5957,12 +6092,13 @@ static int nl80211_get_wowlan(struct sk_buff *skb, struct genl_info *info) if (!nl_pat) goto nla_put_failure; pat_len = rdev->wowlan->patterns[i].pattern_len; - NLA_PUT(msg, NL80211_WOWLAN_PKTPAT_MASK, - DIV_ROUND_UP(pat_len, 8), - rdev->wowlan->patterns[i].mask); - NLA_PUT(msg, NL80211_WOWLAN_PKTPAT_PATTERN, - pat_len, - rdev->wowlan->patterns[i].pattern); + if (nla_put(msg, NL80211_WOWLAN_PKTPAT_MASK, + DIV_ROUND_UP(pat_len, 8), + rdev->wowlan->patterns[i].mask) || + nla_put(msg, NL80211_WOWLAN_PKTPAT_PATTERN, + pat_len, + rdev->wowlan->patterns[i].pattern)) + goto nla_put_failure; nla_nest_end(msg, nl_pat); } nla_nest_end(msg, nl_pats); @@ -5987,6 +6123,7 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) struct cfg80211_wowlan new_triggers = {}; struct wiphy_wowlan_support *wowlan = &rdev->wiphy.wowlan; int err, i; + bool prev_enabled = rdev->wowlan; if (!rdev->wiphy.wowlan.flags && !rdev->wiphy.wowlan.n_patterns) return -EOPNOTSUPP; @@ -6119,6 +6256,9 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) rdev->wowlan = NULL; } + if (rdev->ops->set_wakeup && prev_enabled != !!rdev->wowlan) + rdev->ops->set_wakeup(&rdev->wiphy, rdev->wowlan); + return 0; error: for (i = 0; i < new_triggers.n_patterns; i++) @@ -6235,7 +6375,8 @@ static int nl80211_probe_client(struct sk_buff *skb, if (err) goto free_msg; - NLA_PUT_U64(msg, NL80211_ATTR_COOKIE, cookie); + if (nla_put_u64(msg, NL80211_ATTR_COOKIE, cookie)) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -6376,7 +6517,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_get_key, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6408,7 +6549,7 @@ static struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .doit = nl80211_set_beacon, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6416,7 +6557,7 @@ static struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .doit = nl80211_start_ap, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6424,7 +6565,7 @@ static struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .doit = nl80211_stop_ap, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6440,7 +6581,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_set_station, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6456,7 +6597,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_del_station, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6489,7 +6630,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_del_mpath, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6497,7 +6638,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_set_bss, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6523,7 +6664,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_get_mesh_config, .policy = nl80211_policy, /* can be retrieved by unprivileged users */ - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6656,7 +6797,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_setdel_pmksa, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6664,7 +6805,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_setdel_pmksa, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6672,7 +6813,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_flush_pmksa, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6832,7 +6973,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_probe_client, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6903,19 +7044,24 @@ static int nl80211_add_scan_req(struct sk_buff *msg, nest = nla_nest_start(msg, NL80211_ATTR_SCAN_SSIDS); if (!nest) goto nla_put_failure; - for (i = 0; i < req->n_ssids; i++) - NLA_PUT(msg, i, req->ssids[i].ssid_len, req->ssids[i].ssid); + for (i = 0; i < req->n_ssids; i++) { + if (nla_put(msg, i, req->ssids[i].ssid_len, req->ssids[i].ssid)) + goto nla_put_failure; + } nla_nest_end(msg, nest); nest = nla_nest_start(msg, NL80211_ATTR_SCAN_FREQUENCIES); if (!nest) goto nla_put_failure; - for (i = 0; i < req->n_channels; i++) - NLA_PUT_U32(msg, i, req->channels[i]->center_freq); + for (i = 0; i < req->n_channels; i++) { + if (nla_put_u32(msg, i, req->channels[i]->center_freq)) + goto nla_put_failure; + } nla_nest_end(msg, nest); - if (req->ie) - NLA_PUT(msg, NL80211_ATTR_IE, req->ie_len, req->ie); + if (req->ie && + nla_put(msg, NL80211_ATTR_IE, req->ie_len, req->ie)) + goto nla_put_failure; return 0; nla_put_failure: @@ -6934,8 +7080,9 @@ static int nl80211_send_scan_msg(struct sk_buff *msg, if (!hdr) return -1; - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex)) + goto nla_put_failure; /* ignore errors and send incomplete event anyway */ nl80211_add_scan_req(msg, rdev); @@ -6959,8 +7106,9 @@ nl80211_send_sched_scan_msg(struct sk_buff *msg, if (!hdr) return -1; - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex)) + goto nla_put_failure; return genlmsg_end(msg, hdr); @@ -7083,26 +7231,33 @@ void nl80211_send_reg_change_event(struct regulatory_request *request) } /* Userspace can always count this one always being set */ - NLA_PUT_U8(msg, NL80211_ATTR_REG_INITIATOR, request->initiator); - - if (request->alpha2[0] == '0' && request->alpha2[1] == '0') - NLA_PUT_U8(msg, NL80211_ATTR_REG_TYPE, - NL80211_REGDOM_TYPE_WORLD); - else if (request->alpha2[0] == '9' && request->alpha2[1] == '9') - NLA_PUT_U8(msg, NL80211_ATTR_REG_TYPE, - NL80211_REGDOM_TYPE_CUSTOM_WORLD); - else if ((request->alpha2[0] == '9' && request->alpha2[1] == '8') || - request->intersect) - NLA_PUT_U8(msg, NL80211_ATTR_REG_TYPE, - NL80211_REGDOM_TYPE_INTERSECTION); - else { - NLA_PUT_U8(msg, NL80211_ATTR_REG_TYPE, - NL80211_REGDOM_TYPE_COUNTRY); - NLA_PUT_STRING(msg, NL80211_ATTR_REG_ALPHA2, request->alpha2); - } - - if (wiphy_idx_valid(request->wiphy_idx)) - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, request->wiphy_idx); + if (nla_put_u8(msg, NL80211_ATTR_REG_INITIATOR, request->initiator)) + goto nla_put_failure; + + if (request->alpha2[0] == '0' && request->alpha2[1] == '0') { + if (nla_put_u8(msg, NL80211_ATTR_REG_TYPE, + NL80211_REGDOM_TYPE_WORLD)) + goto nla_put_failure; + } else if (request->alpha2[0] == '9' && request->alpha2[1] == '9') { + if (nla_put_u8(msg, NL80211_ATTR_REG_TYPE, + NL80211_REGDOM_TYPE_CUSTOM_WORLD)) + goto nla_put_failure; + } else if ((request->alpha2[0] == '9' && request->alpha2[1] == '8') || + request->intersect) { + if (nla_put_u8(msg, NL80211_ATTR_REG_TYPE, + NL80211_REGDOM_TYPE_INTERSECTION)) + goto nla_put_failure; + } else { + if (nla_put_u8(msg, NL80211_ATTR_REG_TYPE, + NL80211_REGDOM_TYPE_COUNTRY) || + nla_put_string(msg, NL80211_ATTR_REG_ALPHA2, + request->alpha2)) + goto nla_put_failure; + } + + if (wiphy_idx_valid(request->wiphy_idx) && + nla_put_u32(msg, NL80211_ATTR_WIPHY, request->wiphy_idx)) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -7136,9 +7291,10 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev, return; } - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); - NLA_PUT(msg, NL80211_ATTR_FRAME, len, buf); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + nla_put(msg, NL80211_ATTR_FRAME, len, buf)) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -7216,10 +7372,11 @@ static void nl80211_send_mlme_timeout(struct cfg80211_registered_device *rdev, return; } - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); - NLA_PUT_FLAG(msg, NL80211_ATTR_TIMED_OUT); - NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, addr); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + nla_put_flag(msg, NL80211_ATTR_TIMED_OUT) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr)) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -7267,15 +7424,15 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, return; } - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); - if (bssid) - NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid); - NLA_PUT_U16(msg, NL80211_ATTR_STATUS_CODE, status); - if (req_ie) - NLA_PUT(msg, NL80211_ATTR_REQ_IE, req_ie_len, req_ie); - if (resp_ie) - NLA_PUT(msg, NL80211_ATTR_RESP_IE, resp_ie_len, resp_ie); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + (bssid && nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid)) || + nla_put_u16(msg, NL80211_ATTR_STATUS_CODE, status) || + (req_ie && + nla_put(msg, NL80211_ATTR_REQ_IE, req_ie_len, req_ie)) || + (resp_ie && + nla_put(msg, NL80211_ATTR_RESP_IE, resp_ie_len, resp_ie))) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -7307,13 +7464,14 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, return; } - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); - NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid); - if (req_ie) - NLA_PUT(msg, NL80211_ATTR_REQ_IE, req_ie_len, req_ie); - if (resp_ie) - NLA_PUT(msg, NL80211_ATTR_RESP_IE, resp_ie_len, resp_ie); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid) || + (req_ie && + nla_put(msg, NL80211_ATTR_REQ_IE, req_ie_len, req_ie)) || + (resp_ie && + nla_put(msg, NL80211_ATTR_RESP_IE, resp_ie_len, resp_ie))) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -7344,14 +7502,14 @@ void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, return; } - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); - if (from_ap && reason) - NLA_PUT_U16(msg, NL80211_ATTR_REASON_CODE, reason); - if (from_ap) - NLA_PUT_FLAG(msg, NL80211_ATTR_DISCONNECTED_BY_AP); - if (ie) - NLA_PUT(msg, NL80211_ATTR_IE, ie_len, ie); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + (from_ap && reason && + nla_put_u16(msg, NL80211_ATTR_REASON_CODE, reason)) || + (from_ap && + nla_put_flag(msg, NL80211_ATTR_DISCONNECTED_BY_AP)) || + (ie && nla_put(msg, NL80211_ATTR_IE, ie_len, ie))) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -7382,9 +7540,10 @@ void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev, return; } - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); - NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid)) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -7415,11 +7574,12 @@ void nl80211_send_new_peer_candidate(struct cfg80211_registered_device *rdev, return; } - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); - NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, macaddr); - if (ie_len && ie) - NLA_PUT(msg, NL80211_ATTR_IE, ie_len , ie); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, macaddr) || + (ie_len && ie && + nla_put(msg, NL80211_ATTR_IE, ie_len , ie))) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -7450,15 +7610,14 @@ void nl80211_michael_mic_failure(struct cfg80211_registered_device *rdev, return; } - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); - if (addr) - NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, addr); - NLA_PUT_U32(msg, NL80211_ATTR_KEY_TYPE, key_type); - if (key_id != -1) - NLA_PUT_U8(msg, NL80211_ATTR_KEY_IDX, key_id); - if (tsc) - NLA_PUT(msg, NL80211_ATTR_KEY_SEQ, 6, tsc); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + (addr && nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr)) || + nla_put_u32(msg, NL80211_ATTR_KEY_TYPE, key_type) || + (key_id != -1 && + nla_put_u8(msg, NL80211_ATTR_KEY_IDX, key_id)) || + (tsc && nla_put(msg, NL80211_ATTR_KEY_SEQ, 6, tsc))) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -7493,7 +7652,8 @@ void nl80211_send_beacon_hint_event(struct wiphy *wiphy, * Since we are applying the beacon hint to a wiphy we know its * wiphy_idx is valid */ - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, get_wiphy_idx(wiphy)); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, get_wiphy_idx(wiphy))) + goto nla_put_failure; /* Before */ nl_freq = nla_nest_start(msg, NL80211_ATTR_FREQ_BEFORE); @@ -7545,14 +7705,16 @@ static void nl80211_send_remain_on_chan_event( return; } - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY_FREQ, chan->center_freq); - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY_CHANNEL_TYPE, channel_type); - NLA_PUT_U64(msg, NL80211_ATTR_COOKIE, cookie); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, chan->center_freq) || + nla_put_u32(msg, NL80211_ATTR_WIPHY_CHANNEL_TYPE, channel_type) || + nla_put_u64(msg, NL80211_ATTR_COOKIE, cookie)) + goto nla_put_failure; - if (cmd == NL80211_CMD_REMAIN_ON_CHANNEL) - NLA_PUT_U32(msg, NL80211_ATTR_DURATION, duration); + if (cmd == NL80211_CMD_REMAIN_ON_CHANNEL && + nla_put_u32(msg, NL80211_ATTR_DURATION, duration)) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -7596,7 +7758,8 @@ void nl80211_send_sta_event(struct cfg80211_registered_device *rdev, if (!msg) return; - if (nl80211_send_station(msg, 0, 0, 0, dev, mac_addr, sinfo) < 0) { + if (nl80211_send_station(msg, 0, 0, 0, + rdev, dev, mac_addr, sinfo) < 0) { nlmsg_free(msg); return; } @@ -7622,8 +7785,9 @@ void nl80211_send_sta_del_event(struct cfg80211_registered_device *rdev, return; } - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, dev->ifindex); - NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr); + if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr)) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -7659,9 +7823,10 @@ static bool __nl80211_unexpected_frame(struct net_device *dev, u8 cmd, return true; } - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, dev->ifindex); - NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, addr); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr)) + goto nla_put_failure; err = genlmsg_end(msg, hdr); if (err < 0) { @@ -7710,12 +7875,13 @@ int nl80211_send_mgmt(struct cfg80211_registered_device *rdev, return -ENOMEM; } - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY_FREQ, freq); - if (sig_dbm) - NLA_PUT_U32(msg, NL80211_ATTR_RX_SIGNAL_DBM, sig_dbm); - NLA_PUT(msg, NL80211_ATTR_FRAME, len, buf); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, freq) || + (sig_dbm && + nla_put_u32(msg, NL80211_ATTR_RX_SIGNAL_DBM, sig_dbm)) || + nla_put(msg, NL80211_ATTR_FRAME, len, buf)) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -7745,12 +7911,12 @@ void nl80211_send_mgmt_tx_status(struct cfg80211_registered_device *rdev, return; } - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); - NLA_PUT(msg, NL80211_ATTR_FRAME, len, buf); - NLA_PUT_U64(msg, NL80211_ATTR_COOKIE, cookie); - if (ack) - NLA_PUT_FLAG(msg, NL80211_ATTR_ACK); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + nla_put(msg, NL80211_ATTR_FRAME, len, buf) || + nla_put_u64(msg, NL80211_ATTR_COOKIE, cookie) || + (ack && nla_put_flag(msg, NL80211_ATTR_ACK))) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -7782,15 +7948,17 @@ nl80211_send_cqm_rssi_notify(struct cfg80211_registered_device *rdev, return; } - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex)) + goto nla_put_failure; pinfoattr = nla_nest_start(msg, NL80211_ATTR_CQM); if (!pinfoattr) goto nla_put_failure; - NLA_PUT_U32(msg, NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT, - rssi_event); + if (nla_put_u32(msg, NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT, + rssi_event)) + goto nla_put_failure; nla_nest_end(msg, pinfoattr); @@ -7823,16 +7991,18 @@ void nl80211_gtk_rekey_notify(struct cfg80211_registered_device *rdev, return; } - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); - NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid)) + goto nla_put_failure; rekey_attr = nla_nest_start(msg, NL80211_ATTR_REKEY_DATA); if (!rekey_attr) goto nla_put_failure; - NLA_PUT(msg, NL80211_REKEY_DATA_REPLAY_CTR, - NL80211_REPLAY_CTR_LEN, replay_ctr); + if (nla_put(msg, NL80211_REKEY_DATA_REPLAY_CTR, + NL80211_REPLAY_CTR_LEN, replay_ctr)) + goto nla_put_failure; nla_nest_end(msg, rekey_attr); @@ -7865,17 +8035,19 @@ void nl80211_pmksa_candidate_notify(struct cfg80211_registered_device *rdev, return; } - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex)) + goto nla_put_failure; attr = nla_nest_start(msg, NL80211_ATTR_PMKSA_CANDIDATE); if (!attr) goto nla_put_failure; - NLA_PUT_U32(msg, NL80211_PMKSA_CANDIDATE_INDEX, index); - NLA_PUT(msg, NL80211_PMKSA_CANDIDATE_BSSID, ETH_ALEN, bssid); - if (preauth) - NLA_PUT_FLAG(msg, NL80211_PMKSA_CANDIDATE_PREAUTH); + if (nla_put_u32(msg, NL80211_PMKSA_CANDIDATE_INDEX, index) || + nla_put(msg, NL80211_PMKSA_CANDIDATE_BSSID, ETH_ALEN, bssid) || + (preauth && + nla_put_flag(msg, NL80211_PMKSA_CANDIDATE_PREAUTH))) + goto nla_put_failure; nla_nest_end(msg, attr); @@ -7890,6 +8062,39 @@ void nl80211_pmksa_candidate_notify(struct cfg80211_registered_device *rdev, nlmsg_free(msg); } +void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev, + struct net_device *netdev, int freq, + enum nl80211_channel_type type, gfp_t gfp) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_CH_SWITCH_NOTIFY); + if (!hdr) { + nlmsg_free(msg); + return; + } + + if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, freq) || + nla_put_u32(msg, NL80211_ATTR_WIPHY_CHANNEL_TYPE, type)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_mlme_mcgrp.id, gfp); + return; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); +} + void nl80211_send_cqm_pktloss_notify(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *peer, @@ -7909,15 +8114,17 @@ nl80211_send_cqm_pktloss_notify(struct cfg80211_registered_device *rdev, return; } - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); - NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, peer); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, peer)) + goto nla_put_failure; pinfoattr = nla_nest_start(msg, NL80211_ATTR_CQM); if (!pinfoattr) goto nla_put_failure; - NLA_PUT_U32(msg, NL80211_ATTR_CQM_PKT_LOSS_EVENT, num_packets); + if (nla_put_u32(msg, NL80211_ATTR_CQM_PKT_LOSS_EVENT, num_packets)) + goto nla_put_failure; nla_nest_end(msg, pinfoattr); @@ -7951,12 +8158,12 @@ void cfg80211_probe_status(struct net_device *dev, const u8 *addr, return; } - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, dev->ifindex); - NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, addr); - NLA_PUT_U64(msg, NL80211_ATTR_COOKIE, cookie); - if (acked) - NLA_PUT_FLAG(msg, NL80211_ATTR_ACK); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr) || + nla_put_u64(msg, NL80211_ATTR_COOKIE, cookie) || + (acked && nla_put_flag(msg, NL80211_ATTR_ACK))) + goto nla_put_failure; err = genlmsg_end(msg, hdr); if (err < 0) { @@ -7996,12 +8203,13 @@ void cfg80211_report_obss_beacon(struct wiphy *wiphy, return; } - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); - if (freq) - NLA_PUT_U32(msg, NL80211_ATTR_WIPHY_FREQ, freq); - if (sig_dbm) - NLA_PUT_U32(msg, NL80211_ATTR_RX_SIGNAL_DBM, sig_dbm); - NLA_PUT(msg, NL80211_ATTR_FRAME, len, frame); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + (freq && + nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, freq)) || + (sig_dbm && + nla_put_u32(msg, NL80211_ATTR_RX_SIGNAL_DBM, sig_dbm)) || + nla_put(msg, NL80211_ATTR_FRAME, len, frame)) + goto nla_put_failure; genlmsg_end(msg, hdr); diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 4ffe50df9f3..01a1122c3b3 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -118,6 +118,10 @@ void nl80211_pmksa_candidate_notify(struct cfg80211_registered_device *rdev, struct net_device *netdev, int index, const u8 *bssid, bool preauth, gfp_t gfp); +void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev, + struct net_device *dev, int freq, + enum nl80211_channel_type type, gfp_t gfp); + bool nl80211_unexpected_frame(struct net_device *dev, const u8 *addr, gfp_t gfp); bool nl80211_unexpected_4addr_frame(struct net_device *dev, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index e9a0ac83b84..15f347477a9 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -388,7 +388,15 @@ static void reg_regdb_query(const char *alpha2) schedule_work(®_regdb_work); } + +/* Feel free to add any other sanity checks here */ +static void reg_regdb_size_check(void) +{ + /* We should ideally BUILD_BUG_ON() but then random builds would fail */ + WARN_ONCE(!reg_regdb_size, "db.txt is empty, you should update it..."); +} #else +static inline void reg_regdb_size_check(void) {} static inline void reg_regdb_query(const char *alpha2) {} #endif /* CONFIG_CFG80211_INTERNAL_REGDB */ @@ -2322,6 +2330,8 @@ int __init regulatory_init(void) spin_lock_init(®_requests_lock); spin_lock_init(®_pending_beacons_lock); + reg_regdb_size_check(); + cfg80211_regdomain = cfg80211_world_regdom; user_alpha2[0] = '9'; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 70faadf16a3..af2b1caa37f 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -18,7 +18,7 @@ #include "nl80211.h" #include "wext-compat.h" -#define IEEE80211_SCAN_RESULT_EXPIRE (15 * HZ) +#define IEEE80211_SCAN_RESULT_EXPIRE (30 * HZ) void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak) { @@ -281,7 +281,7 @@ static bool is_bss(struct cfg80211_bss *a, { const u8 *ssidie; - if (bssid && compare_ether_addr(a->bssid, bssid)) + if (bssid && !ether_addr_equal(a->bssid, bssid)) return false; if (!ssid) @@ -378,7 +378,11 @@ static int cmp_bss_core(struct cfg80211_bss *a, b->len_information_elements); } - return memcmp(a->bssid, b->bssid, ETH_ALEN); + /* + * we can't use compare_ether_addr here since we need a < > operator. + * The binary return value of compare_ether_addr isn't enough + */ + return memcmp(a->bssid, b->bssid, sizeof(a->bssid)); } static int cmp_bss(struct cfg80211_bss *a, diff --git a/net/wireless/util.c b/net/wireless/util.c index 1b7a08df933..1cd255892a4 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -370,7 +370,7 @@ int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, iftype != NL80211_IFTYPE_P2P_CLIENT && iftype != NL80211_IFTYPE_MESH_POINT) || (is_multicast_ether_addr(dst) && - !compare_ether_addr(src, addr))) + ether_addr_equal(src, addr))) return -1; if (iftype == NL80211_IFTYPE_MESH_POINT) { struct ieee80211s_hdr *meshdr = @@ -398,9 +398,9 @@ int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, payload = skb->data + hdrlen; ethertype = (payload[6] << 8) | payload[7]; - if (likely((compare_ether_addr(payload, rfc1042_header) == 0 && + if (likely((ether_addr_equal(payload, rfc1042_header) && ethertype != ETH_P_AARP && ethertype != ETH_P_IPX) || - compare_ether_addr(payload, bridge_tunnel_header) == 0)) { + ether_addr_equal(payload, bridge_tunnel_header))) { /* remove RFC1042 or Bridge-Tunnel encapsulation and * replace EtherType */ skb_pull(skb, hdrlen + 6); @@ -609,10 +609,9 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, payload = frame->data; ethertype = (payload[6] << 8) | payload[7]; - if (likely((compare_ether_addr(payload, rfc1042_header) == 0 && + if (likely((ether_addr_equal(payload, rfc1042_header) && ethertype != ETH_P_AARP && ethertype != ETH_P_IPX) || - compare_ether_addr(payload, - bridge_tunnel_header) == 0)) { + ether_addr_equal(payload, bridge_tunnel_header))) { /* remove RFC1042 or Bridge-Tunnel * encapsulation and replace EtherType */ skb_pull(frame, 6); @@ -946,13 +945,6 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, if (rdev->wiphy.software_iftypes & BIT(iftype)) return 0; - /* - * Drivers will gradually all set this flag, until all - * have it we only enforce for those that set it. - */ - if (!(rdev->wiphy.flags & WIPHY_FLAG_ENFORCE_COMBINATIONS)) - return 0; - memset(num, 0, sizeof(num)); num[iftype] = 1; @@ -972,6 +964,9 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, } mutex_unlock(&rdev->devlist_mtx); + if (total == 1) + return 0; + for (i = 0; i < rdev->wiphy.n_iface_combinations; i++) { const struct ieee80211_iface_combination *c; struct ieee80211_iface_limit *limits; @@ -989,7 +984,7 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, if (rdev->wiphy.software_iftypes & BIT(iftype)) continue; for (j = 0; j < c->n_limits; j++) { - if (!(limits[j].types & iftype)) + if (!(limits[j].types & BIT(iftype))) continue; if (limits[j].max < num[iftype]) goto cont; diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 3c24eb97e9d..6a6181a673c 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -821,6 +821,7 @@ static int cfg80211_wext_giwfreq(struct net_device *dev, struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); struct ieee80211_channel *chan; + enum nl80211_channel_type channel_type; switch (wdev->iftype) { case NL80211_IFTYPE_STATION: @@ -831,7 +832,7 @@ static int cfg80211_wext_giwfreq(struct net_device *dev, if (!rdev->ops->get_channel) return -EINVAL; - chan = rdev->ops->get_channel(wdev->wiphy); + chan = rdev->ops->get_channel(wdev->wiphy, &channel_type); if (!chan) return -EINVAL; freq->m = chan->center_freq; diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index 0af7f54e4f6..b0eb7aa49b6 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -256,7 +256,7 @@ static const struct iw_ioctl_description standard_ioctl[] = { .max_tokens = sizeof(struct iw_pmksa), }, }; -static const unsigned standard_ioctl_num = ARRAY_SIZE(standard_ioctl); +static const unsigned int standard_ioctl_num = ARRAY_SIZE(standard_ioctl); /* * Meta-data about all the additional standard Wireless Extension events @@ -306,7 +306,7 @@ static const struct iw_ioctl_description standard_event[] = { .max_tokens = sizeof(struct iw_pmkid_cand), }, }; -static const unsigned standard_event_num = ARRAY_SIZE(standard_event); +static const unsigned int standard_event_num = ARRAY_SIZE(standard_event); /* Size (in bytes) of various events */ static const int event_type_size[] = { @@ -402,7 +402,8 @@ static struct nlmsghdr *rtnetlink_ifinfo_prep(struct net_device *dev, r->ifi_flags = dev_get_flags(dev); r->ifi_change = 0; /* Wireless changes don't affect those flags */ - NLA_PUT_STRING(skb, IFLA_IFNAME, dev->name); + if (nla_put_string(skb, IFLA_IFNAME, dev->name)) + goto nla_put_failure; return nlh; nla_put_failure: @@ -428,7 +429,7 @@ void wireless_send_event(struct net_device * dev, int hdr_len; /* Size of the event header */ int wrqu_off = 0; /* Offset in wrqu */ /* Don't "optimise" the following variable, it will crash */ - unsigned cmd_index; /* *MUST* be unsigned */ + unsigned int cmd_index; /* *MUST* be unsigned */ struct sk_buff *skb; struct nlmsghdr *nlh; struct nlattr *nla; @@ -780,8 +781,10 @@ static int ioctl_standard_iw_point(struct iw_point *iwp, unsigned int cmd, if (cmd == SIOCSIWENCODEEXT) { struct iw_encode_ext *ee = (void *) extra; - if (iwp->length < sizeof(*ee) + ee->key_len) - return -EFAULT; + if (iwp->length < sizeof(*ee) + ee->key_len) { + err = -EFAULT; + goto out; + } } } diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index 7c01c2f3b6c..7decbd357d5 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -276,7 +276,7 @@ int cfg80211_mgd_wext_siwap(struct net_device *dev, /* fixed already - and no change */ if (wdev->wext.connect.bssid && bssid && - compare_ether_addr(bssid, wdev->wext.connect.bssid) == 0) + ether_addr_equal(bssid, wdev->wext.connect.bssid)) goto out; err = __cfg80211_disconnect(rdev, dev, diff --git a/net/wireless/wext-spy.c b/net/wireless/wext-spy.c index 5d643a548fe..33bef22e44e 100644 --- a/net/wireless/wext-spy.c +++ b/net/wireless/wext-spy.c @@ -203,7 +203,7 @@ void wireless_spy_update(struct net_device * dev, /* Update all records that match */ for (i = 0; i < spydata->spy_number; i++) - if (!compare_ether_addr(address, spydata->spy_address[i])) { + if (ether_addr_equal(address, spydata->spy_address[i])) { memcpy(&(spydata->spy_stat[i]), wstats, sizeof(struct iw_quality)); match = i; diff --git a/net/x25/sysctl_net_x25.c b/net/x25/sysctl_net_x25.c index d2efd29f434..43239527a20 100644 --- a/net/x25/sysctl_net_x25.c +++ b/net/x25/sysctl_net_x25.c @@ -73,18 +73,12 @@ static struct ctl_table x25_table[] = { { 0, }, }; -static struct ctl_path x25_path[] = { - { .procname = "net", }, - { .procname = "x25", }, - { } -}; - void __init x25_register_sysctl(void) { - x25_table_header = register_sysctl_paths(x25_path, x25_table); + x25_table_header = register_net_sysctl(&init_net, "net/x25", x25_table); } void x25_unregister_sysctl(void) { - unregister_sysctl_table(x25_table_header); + unregister_net_sysctl_table(x25_table_header); } diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c index f0ce862d1f4..a8a236338e6 100644 --- a/net/x25/x25_dev.c +++ b/net/x25/x25_dev.c @@ -58,7 +58,7 @@ static int x25_receive_data(struct sk_buff *skb, struct x25_neigh *nb) if (!sock_owned_by_user(sk)) { queued = x25_process_rx_frame(sk, skb); } else { - queued = !sk_add_backlog(sk, skb); + queued = !sk_add_backlog(sk, skb, sk->sk_rcvbuf); } bh_unlock_sock(sk); sock_put(sk); diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c index 36384a1fa9f..66c638730c7 100644 --- a/net/x25/x25_facilities.c +++ b/net/x25/x25_facilities.c @@ -231,7 +231,7 @@ int x25_create_facilities(unsigned char *buffer, } if (dte_facs->calling_len && (facil_mask & X25_MASK_CALLING_AE)) { - unsigned bytecount = (dte_facs->calling_len + 1) >> 1; + unsigned int bytecount = (dte_facs->calling_len + 1) >> 1; *p++ = X25_FAC_CALLING_AE; *p++ = 1 + bytecount; *p++ = dte_facs->calling_len; @@ -240,7 +240,7 @@ int x25_create_facilities(unsigned char *buffer, } if (dte_facs->called_len && (facil_mask & X25_MASK_CALLED_AE)) { - unsigned bytecount = (dte_facs->called_len % 2) ? + unsigned int bytecount = (dte_facs->called_len % 2) ? dte_facs->called_len / 2 + 1 : dte_facs->called_len / 2; *p++ = X25_FAC_CALLED_AE; diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig index 6d081674515..ce90b8d9236 100644 --- a/net/xfrm/Kconfig +++ b/net/xfrm/Kconfig @@ -3,12 +3,17 @@ # config XFRM bool - select CRYPTO depends on NET +config XFRM_ALGO + tristate + select XFRM + select CRYPTO + config XFRM_USER tristate "Transformation user configuration interface" - depends on INET && XFRM + depends on INET + select XFRM_ALGO ---help--- Support for Transformation(XFRM) user configuration interface like IPsec used by native Linux tools. @@ -48,13 +53,13 @@ config XFRM_STATISTICS config XFRM_IPCOMP tristate - select XFRM + select XFRM_ALGO select CRYPTO select CRYPTO_DEFLATE config NET_KEY tristate "PF_KEY sockets" - select XFRM + select XFRM_ALGO ---help--- PF_KEYv2 socket family, compatible to KAME ones. They are required if you are going to use IPsec tools ported diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index aa429eefe91..c0e961983f1 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -3,8 +3,9 @@ # obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \ - xfrm_input.o xfrm_output.o xfrm_algo.o \ + xfrm_input.o xfrm_output.o \ xfrm_sysctl.o xfrm_replay.o obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o +obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o obj-$(CONFIG_XFRM_USER) += xfrm_user.o obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index 791ab2e77f3..4ce2d93162c 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -15,9 +15,6 @@ #include <linux/crypto.h> #include <linux/scatterlist.h> #include <net/xfrm.h> -#if defined(CONFIG_INET_AH) || defined(CONFIG_INET_AH_MODULE) || defined(CONFIG_INET6_AH) || defined(CONFIG_INET6_AH_MODULE) -#include <net/ah.h> -#endif #if defined(CONFIG_INET_ESP) || defined(CONFIG_INET_ESP_MODULE) || defined(CONFIG_INET6_ESP) || defined(CONFIG_INET6_ESP_MODULE) #include <net/esp.h> #endif @@ -752,3 +749,5 @@ void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len) } EXPORT_SYMBOL_GPL(pskb_put); #endif + +MODULE_LICENSE("GPL"); diff --git a/net/xfrm/xfrm_hash.h b/net/xfrm/xfrm_hash.h index 7199d78b2aa..716502ada53 100644 --- a/net/xfrm/xfrm_hash.h +++ b/net/xfrm/xfrm_hash.h @@ -45,10 +45,10 @@ static inline unsigned int __xfrm_dst_hash(const xfrm_address_t *daddr, return (h ^ (h >> 16)) & hmask; } -static inline unsigned __xfrm_src_hash(const xfrm_address_t *daddr, - const xfrm_address_t *saddr, - unsigned short family, - unsigned int hmask) +static inline unsigned int __xfrm_src_hash(const xfrm_address_t *daddr, + const xfrm_address_t *saddr, + unsigned short family, + unsigned int hmask) { unsigned int h = family; switch (family) { diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 7661576b6f4..c53e8f42aa7 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -26,6 +26,7 @@ #include <linux/cache.h> #include <linux/audit.h> #include <net/dst.h> +#include <net/flow.h> #include <net/xfrm.h> #include <net/ip.h> #ifdef CONFIG_XFRM_STATISTICS @@ -56,7 +57,7 @@ static int xfrm_bundle_ok(struct xfrm_dst *xdst); static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, int dir); -static inline int +static inline bool __xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi4 *fl4 = &fl->u.ip4; @@ -69,7 +70,7 @@ __xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl) (fl4->flowi4_oif == sel->ifindex || !sel->ifindex); } -static inline int +static inline bool __xfrm6_selector_match(const struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi6 *fl6 = &fl->u.ip6; @@ -82,8 +83,8 @@ __xfrm6_selector_match(const struct xfrm_selector *sel, const struct flowi *fl) (fl6->flowi6_oif == sel->ifindex || !sel->ifindex); } -int xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl, - unsigned short family) +bool xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl, + unsigned short family) { switch (family) { case AF_INET: @@ -91,7 +92,7 @@ int xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl, case AF_INET6: return __xfrm6_selector_match(sel, fl); } - return 0; + return false; } static inline struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, @@ -877,7 +878,8 @@ static int xfrm_policy_match(const struct xfrm_policy *pol, u8 type, u16 family, int dir) { const struct xfrm_selector *sel = &pol->selector; - int match, ret = -ESRCH; + int ret = -ESRCH; + bool match; if (pol->family != family || (fl->flowi_mark & pol->mark.m) != pol->mark.v || @@ -1006,8 +1008,8 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, read_lock_bh(&xfrm_policy_lock); if ((pol = sk->sk_policy[dir]) != NULL) { - int match = xfrm_selector_match(&pol->selector, fl, - sk->sk_family); + bool match = xfrm_selector_match(&pol->selector, fl, + sk->sk_family); int err = 0; if (match) { @@ -2767,8 +2769,8 @@ EXPORT_SYMBOL_GPL(xfrm_audit_policy_delete); #endif #ifdef CONFIG_XFRM_MIGRATE -static int xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp, - const struct xfrm_selector *sel_tgt) +static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp, + const struct xfrm_selector *sel_tgt) { if (sel_cmp->proto == IPSEC_ULPROTO_ANY) { if (sel_tgt->family == sel_cmp->family && @@ -2778,14 +2780,14 @@ static int xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp, sel_cmp->family) == 0 && sel_tgt->prefixlen_d == sel_cmp->prefixlen_d && sel_tgt->prefixlen_s == sel_cmp->prefixlen_s) { - return 1; + return true; } } else { if (memcmp(sel_tgt, sel_cmp, sizeof(*sel_tgt)) == 0) { - return 1; + return true; } } - return 0; + return false; } static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector *sel, diff --git a/net/xfrm/xfrm_sysctl.c b/net/xfrm/xfrm_sysctl.c index 05640bc9594..380976f74c4 100644 --- a/net/xfrm/xfrm_sysctl.c +++ b/net/xfrm/xfrm_sysctl.c @@ -54,7 +54,7 @@ int __net_init xfrm_sysctl_init(struct net *net) table[2].data = &net->xfrm.sysctl_larval_drop; table[3].data = &net->xfrm.sysctl_acq_expires; - net->xfrm.sysctl_hdr = register_net_sysctl_table(net, net_core_path, table); + net->xfrm.sysctl_hdr = register_net_sysctl(net, "net/core", table); if (!net->xfrm.sysctl_hdr) goto out_register; return 0; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 7128dde0fe1..44293b3fd6a 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -756,40 +756,50 @@ static int copy_to_user_state_extra(struct xfrm_state *x, { copy_to_user_state(x, p); - if (x->coaddr) - NLA_PUT(skb, XFRMA_COADDR, sizeof(*x->coaddr), x->coaddr); + if (x->coaddr && + nla_put(skb, XFRMA_COADDR, sizeof(*x->coaddr), x->coaddr)) + goto nla_put_failure; - if (x->lastused) - NLA_PUT_U64(skb, XFRMA_LASTUSED, x->lastused); + if (x->lastused && + nla_put_u64(skb, XFRMA_LASTUSED, x->lastused)) + goto nla_put_failure; - if (x->aead) - NLA_PUT(skb, XFRMA_ALG_AEAD, aead_len(x->aead), x->aead); - if (x->aalg) { - if (copy_to_user_auth(x->aalg, skb)) - goto nla_put_failure; + if (x->aead && + nla_put(skb, XFRMA_ALG_AEAD, aead_len(x->aead), x->aead)) + goto nla_put_failure; - NLA_PUT(skb, XFRMA_ALG_AUTH_TRUNC, - xfrm_alg_auth_len(x->aalg), x->aalg); - } - if (x->ealg) - NLA_PUT(skb, XFRMA_ALG_CRYPT, xfrm_alg_len(x->ealg), x->ealg); - if (x->calg) - NLA_PUT(skb, XFRMA_ALG_COMP, sizeof(*(x->calg)), x->calg); + if (x->aalg && + (copy_to_user_auth(x->aalg, skb) || + nla_put(skb, XFRMA_ALG_AUTH_TRUNC, + xfrm_alg_auth_len(x->aalg), x->aalg))) + goto nla_put_failure; - if (x->encap) - NLA_PUT(skb, XFRMA_ENCAP, sizeof(*x->encap), x->encap); + if (x->ealg && + nla_put(skb, XFRMA_ALG_CRYPT, xfrm_alg_len(x->ealg), x->ealg)) + goto nla_put_failure; - if (x->tfcpad) - NLA_PUT_U32(skb, XFRMA_TFCPAD, x->tfcpad); + if (x->calg && + nla_put(skb, XFRMA_ALG_COMP, sizeof(*(x->calg)), x->calg)) + goto nla_put_failure; + + if (x->encap && + nla_put(skb, XFRMA_ENCAP, sizeof(*x->encap), x->encap)) + goto nla_put_failure; + + if (x->tfcpad && + nla_put_u32(skb, XFRMA_TFCPAD, x->tfcpad)) + goto nla_put_failure; if (xfrm_mark_put(skb, &x->mark)) goto nla_put_failure; - if (x->replay_esn) - NLA_PUT(skb, XFRMA_REPLAY_ESN_VAL, - xfrm_replay_state_esn_len(x->replay_esn), x->replay_esn); + if (x->replay_esn && + nla_put(skb, XFRMA_REPLAY_ESN_VAL, + xfrm_replay_state_esn_len(x->replay_esn), + x->replay_esn)) + goto nla_put_failure; - if (x->security && copy_sec_ctx(x->security, skb) < 0) + if (x->security && copy_sec_ctx(x->security, skb)) goto nla_put_failure; return 0; @@ -912,8 +922,9 @@ static int build_spdinfo(struct sk_buff *skb, struct net *net, sph.spdhcnt = si.spdhcnt; sph.spdhmcnt = si.spdhmcnt; - NLA_PUT(skb, XFRMA_SPD_INFO, sizeof(spc), &spc); - NLA_PUT(skb, XFRMA_SPD_HINFO, sizeof(sph), &sph); + if (nla_put(skb, XFRMA_SPD_INFO, sizeof(spc), &spc) || + nla_put(skb, XFRMA_SPD_HINFO, sizeof(sph), &sph)) + goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -967,8 +978,9 @@ static int build_sadinfo(struct sk_buff *skb, struct net *net, sh.sadhmcnt = si.sadhmcnt; sh.sadhcnt = si.sadhcnt; - NLA_PUT_U32(skb, XFRMA_SAD_CNT, si.sadcnt); - NLA_PUT(skb, XFRMA_SAD_HINFO, sizeof(sh), &sh); + if (nla_put_u32(skb, XFRMA_SAD_CNT, si.sadcnt) || + nla_put(skb, XFRMA_SAD_HINFO, sizeof(sh), &sh)) + goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -1690,21 +1702,27 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct id->reqid = x->props.reqid; id->flags = c->data.aevent; - if (x->replay_esn) - NLA_PUT(skb, XFRMA_REPLAY_ESN_VAL, - xfrm_replay_state_esn_len(x->replay_esn), - x->replay_esn); - else - NLA_PUT(skb, XFRMA_REPLAY_VAL, sizeof(x->replay), &x->replay); - - NLA_PUT(skb, XFRMA_LTIME_VAL, sizeof(x->curlft), &x->curlft); + if (x->replay_esn) { + if (nla_put(skb, XFRMA_REPLAY_ESN_VAL, + xfrm_replay_state_esn_len(x->replay_esn), + x->replay_esn)) + goto nla_put_failure; + } else { + if (nla_put(skb, XFRMA_REPLAY_VAL, sizeof(x->replay), + &x->replay)) + goto nla_put_failure; + } + if (nla_put(skb, XFRMA_LTIME_VAL, sizeof(x->curlft), &x->curlft)) + goto nla_put_failure; - if (id->flags & XFRM_AE_RTHR) - NLA_PUT_U32(skb, XFRMA_REPLAY_THRESH, x->replay_maxdiff); + if ((id->flags & XFRM_AE_RTHR) && + nla_put_u32(skb, XFRMA_REPLAY_THRESH, x->replay_maxdiff)) + goto nla_put_failure; - if (id->flags & XFRM_AE_ETHR) - NLA_PUT_U32(skb, XFRMA_ETIMER_THRESH, - x->replay_maxage * 10 / HZ); + if ((id->flags & XFRM_AE_ETHR) && + nla_put_u32(skb, XFRMA_ETIMER_THRESH, + x->replay_maxage * 10 / HZ)) + goto nla_put_failure; if (xfrm_mark_put(skb, &x->mark)) goto nla_put_failure; @@ -2835,8 +2853,9 @@ static int build_report(struct sk_buff *skb, u8 proto, ur->proto = proto; memcpy(&ur->sel, sel, sizeof(ur->sel)); - if (addr) - NLA_PUT(skb, XFRMA_COADDR, sizeof(*addr), addr); + if (addr && + nla_put(skb, XFRMA_COADDR, sizeof(*addr), addr)) + goto nla_put_failure; return nlmsg_end(skb, nlh); |