diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/Makefile | 1 | ||||
-rw-r--r-- | net/core/datagram.c | 60 | ||||
-rw-r--r-- | net/core/dev.c | 328 | ||||
-rw-r--r-- | net/core/dev_mcast.c | 2 | ||||
-rw-r--r-- | net/core/ethtool.c | 4 | ||||
-rw-r--r-- | net/core/fib_rules.c | 161 | ||||
-rw-r--r-- | net/core/filter.c | 6 | ||||
-rw-r--r-- | net/core/gen_stats.c | 4 | ||||
-rw-r--r-- | net/core/link_watch.c | 2 | ||||
-rw-r--r-- | net/core/neighbour.c | 34 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 4 | ||||
-rw-r--r-- | net/core/netpoll.c | 23 | ||||
-rw-r--r-- | net/core/pktgen.c | 299 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 298 | ||||
-rw-r--r-- | net/core/skbuff.c | 467 | ||||
-rw-r--r-- | net/core/sock.c | 775 | ||||
-rw-r--r-- | net/core/sysctl_net_core.c | 8 | ||||
-rw-r--r-- | net/core/user_dma.c | 25 | ||||
-rw-r--r-- | net/core/utils.c | 6 | ||||
-rw-r--r-- | net/core/wireless.c | 2371 |
20 files changed, 1506 insertions, 3372 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index 73272d506e93..4751613e1b59 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -13,7 +13,6 @@ obj-y += dev.o ethtool.o dev_mcast.o dst.o netevent.o \ obj-$(CONFIG_XFRM) += flow.o obj-$(CONFIG_SYSFS) += net-sysfs.o obj-$(CONFIG_NET_PKTGEN) += pktgen.o -obj-$(CONFIG_WIRELESS_EXT) += wireless.o obj-$(CONFIG_NETPOLL) += netpoll.o obj-$(CONFIG_NET_DMA) += user_dma.o obj-$(CONFIG_FIB_RULES) += fib_rules.o diff --git a/net/core/datagram.c b/net/core/datagram.c index 186212b5b7da..e1afa7679445 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -247,8 +247,8 @@ EXPORT_SYMBOL(skb_kill_datagram); int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, struct iovec *to, int len) { - int start = skb_headlen(skb); - int i, copy = start - offset; + int end = skb_headlen(skb); + int i, copy = end - offset; /* Copy header. */ if (copy > 0) { @@ -263,11 +263,9 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, /* Copy paged appendix. Hmm... why does this look so complicated? */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - int end; + BUG_TRAP(len >= 0); - BUG_TRAP(start <= offset + len); - - end = start + skb_shinfo(skb)->frags[i].size; + end = offset + skb_shinfo(skb)->frags[i].size; if ((copy = end - offset) > 0) { int err; u8 *vaddr; @@ -277,8 +275,8 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, if (copy > len) copy = len; vaddr = kmap(page); - err = memcpy_toiovec(to, vaddr + frag->page_offset + - offset - start, copy); + err = memcpy_toiovec(to, vaddr + frag->page_offset, + copy); kunmap(page); if (err) goto fault; @@ -286,30 +284,24 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, return 0; offset += copy; } - start = end; } if (skb_shinfo(skb)->frag_list) { struct sk_buff *list = skb_shinfo(skb)->frag_list; for (; list; list = list->next) { - int end; - - BUG_TRAP(start <= offset + len); + BUG_TRAP(len >= 0); - end = start + list->len; + end = offset + list->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; - if (skb_copy_datagram_iovec(list, - offset - start, - to, copy)) + if (skb_copy_datagram_iovec(list, 0, to, copy)) goto fault; if ((len -= copy) == 0) return 0; offset += copy; } - start = end; } } if (!len) @@ -323,9 +315,9 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, u8 __user *to, int len, __wsum *csump) { - int start = skb_headlen(skb); + int end = skb_headlen(skb); int pos = 0; - int i, copy = start - offset; + int i, copy = end - offset; /* Copy header. */ if (copy > 0) { @@ -344,11 +336,9 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - int end; - - BUG_TRAP(start <= offset + len); + BUG_TRAP(len >= 0); - end = start + skb_shinfo(skb)->frags[i].size; + end = offset + skb_shinfo(skb)->frags[i].size; if ((copy = end - offset) > 0) { __wsum csum2; int err = 0; @@ -360,8 +350,7 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, copy = len; vaddr = kmap(page); csum2 = csum_and_copy_to_user(vaddr + - frag->page_offset + - offset - start, + frag->page_offset, to, copy, 0, &err); kunmap(page); if (err) @@ -373,24 +362,20 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, to += copy; pos += copy; } - start = end; } if (skb_shinfo(skb)->frag_list) { struct sk_buff *list = skb_shinfo(skb)->frag_list; for (; list; list=list->next) { - int end; + BUG_TRAP(len >= 0); - BUG_TRAP(start <= offset + len); - - end = start + list->len; + end = offset + list->len; if ((copy = end - offset) > 0) { __wsum csum2 = 0; if (copy > len) copy = len; - if (skb_copy_and_csum_datagram(list, - offset - start, + if (skb_copy_and_csum_datagram(list, 0, to, copy, &csum2)) goto fault; @@ -401,7 +386,6 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, to += copy; pos += copy; } - start = end; } } if (!len) @@ -411,11 +395,11 @@ fault: return -EFAULT; } -__sum16 __skb_checksum_complete(struct sk_buff *skb) +__sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len) { __sum16 sum; - sum = csum_fold(skb_checksum(skb, 0, skb->len, skb->csum)); + sum = csum_fold(skb_checksum(skb, 0, len, skb->csum)); if (likely(!sum)) { if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) netdev_rx_csum_fault(skb->dev); @@ -423,6 +407,12 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb) } return sum; } +EXPORT_SYMBOL(__skb_checksum_complete_head); + +__sum16 __skb_checksum_complete(struct sk_buff *skb) +{ + return __skb_checksum_complete_head(skb, skb->len); +} EXPORT_SYMBOL(__skb_checksum_complete); /** diff --git a/net/core/dev.c b/net/core/dev.c index 4dc93cc4d5b7..d5e42d13bd67 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -109,7 +109,7 @@ #include <linux/netpoll.h> #include <linux/rcupdate.h> #include <linux/delay.h> -#include <linux/wireless.h> +#include <net/wext.h> #include <net/iw_handler.h> #include <asm/current.h> #include <linux/audit.h> @@ -146,8 +146,8 @@ */ static DEFINE_SPINLOCK(ptype_lock); -static struct list_head ptype_base[16]; /* 16 way hashed list */ -static struct list_head ptype_all; /* Taps */ +static struct list_head ptype_base[16] __read_mostly; /* 16 way hashed list */ +static struct list_head ptype_all __read_mostly; /* Taps */ #ifdef CONFIG_NET_DMA static struct dma_client *net_dma_client; @@ -226,12 +226,6 @@ extern void netdev_unregister_sysfs(struct net_device *); *******************************************************************************/ /* - * For efficiency - */ - -static int netdev_nit; - -/* * Add a protocol ID to the list. Now that the input handler is * smarter we can dispense with all the messy stuff that used to be * here. @@ -265,10 +259,9 @@ void dev_add_pack(struct packet_type *pt) int hash; spin_lock_bh(&ptype_lock); - if (pt->type == htons(ETH_P_ALL)) { - netdev_nit++; + if (pt->type == htons(ETH_P_ALL)) list_add_rcu(&pt->list, &ptype_all); - } else { + else { hash = ntohs(pt->type) & 15; list_add_rcu(&pt->list, &ptype_base[hash]); } @@ -295,10 +288,9 @@ void __dev_remove_pack(struct packet_type *pt) spin_lock_bh(&ptype_lock); - if (pt->type == htons(ETH_P_ALL)) { - netdev_nit--; + if (pt->type == htons(ETH_P_ALL)) head = &ptype_all; - } else + else head = &ptype_base[ntohs(pt->type) & 15]; list_for_each_entry(pt1, head, list) { @@ -817,7 +809,6 @@ static int default_rebuild_header(struct sk_buff *skb) return 1; } - /** * dev_open - prepare an interface for use. * @dev: device to open @@ -1031,23 +1022,12 @@ void net_disable_timestamp(void) atomic_dec(&netstamp_needed); } -void __net_timestamp(struct sk_buff *skb) -{ - struct timeval tv; - - do_gettimeofday(&tv); - skb_set_timestamp(skb, &tv); -} -EXPORT_SYMBOL(__net_timestamp); - static inline void net_timestamp(struct sk_buff *skb) { if (atomic_read(&netstamp_needed)) __net_timestamp(skb); - else { - skb->tstamp.off_sec = 0; - skb->tstamp.off_usec = 0; - } + else + skb->tstamp.tv64 = 0; } /* @@ -1077,18 +1057,18 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) set by sender, so that the second statement is just protection against buggy protocols. */ - skb2->mac.raw = skb2->data; + skb_reset_mac_header(skb2); - if (skb2->nh.raw < skb2->data || - skb2->nh.raw > skb2->tail) { + if (skb_network_header(skb2) < skb2->data || + skb2->network_header > skb2->tail) { if (net_ratelimit()) printk(KERN_CRIT "protocol %04x is " "buggy, dev %s\n", skb2->protocol, dev->name); - skb2->nh.raw = skb2->data; + skb_reset_network_header(skb2); } - skb2->h.raw = skb2->nh.raw; + skb2->transport_header = skb2->network_header; skb2->pkt_type = PACKET_OUTGOING; ptype->func(skb2, skb->dev, ptype, skb->dev); } @@ -1167,7 +1147,7 @@ EXPORT_SYMBOL(netif_device_attach); int skb_checksum_help(struct sk_buff *skb) { __wsum csum; - int ret = 0, offset = skb->h.raw - skb->data; + int ret = 0, offset; if (skb->ip_summed == CHECKSUM_COMPLETE) goto out_set_summed; @@ -1183,15 +1163,16 @@ int skb_checksum_help(struct sk_buff *skb) goto out; } + offset = skb->csum_start - skb_headroom(skb); BUG_ON(offset > (int)skb->len); csum = skb_checksum(skb, offset, skb->len-offset, 0); - offset = skb->tail - skb->h.raw; + offset = skb_headlen(skb) - offset; BUG_ON(offset <= 0); BUG_ON(skb->csum_offset + 2 > offset); - *(__sum16*)(skb->h.raw + skb->csum_offset) = csum_fold(csum); - + *(__sum16 *)(skb->head + skb->csum_start + skb->csum_offset) = + csum_fold(csum); out_set_summed: skb->ip_summed = CHECKSUM_NONE; out: @@ -1217,11 +1198,11 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) BUG_ON(skb_shinfo(skb)->frag_list); - skb->mac.raw = skb->data; - skb->mac_len = skb->nh.raw - skb->data; + skb_reset_mac_header(skb); + skb->mac_len = skb->network_header - skb->mac_header; __skb_pull(skb, skb->mac_len); - if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { + if (WARN_ON(skb->ip_summed != CHECKSUM_PARTIAL)) { if (skb_header_cloned(skb) && (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) return ERR_PTR(err); @@ -1235,7 +1216,8 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) segs = ERR_PTR(err); if (err || skb_gso_ok(skb, features)) break; - __skb_push(skb, skb->data - skb->nh.raw); + __skb_push(skb, (skb->data - + skb_network_header(skb))); } segs = ptype->gso_segment(skb, features); break; @@ -1243,7 +1225,7 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) } rcu_read_unlock(); - __skb_push(skb, skb->data - skb->mac.raw); + __skb_push(skb, skb->data - skb_mac_header(skb)); return segs; } @@ -1340,7 +1322,7 @@ static int dev_gso_segment(struct sk_buff *skb) int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) { if (likely(!skb->next)) { - if (netdev_nit) + if (!list_empty(&ptype_all)) dev_queue_xmit_nit(skb, dev); if (netif_needs_gso(dev, skb)) { @@ -1442,12 +1424,16 @@ int dev_queue_xmit(struct sk_buff *skb) /* If packet is not checksummed and device does not support * checksumming for this protocol, complete checksumming here. */ - if (skb->ip_summed == CHECKSUM_PARTIAL && - (!(dev->features & NETIF_F_GEN_CSUM) && - (!(dev->features & NETIF_F_IP_CSUM) || - skb->protocol != htons(ETH_P_IP)))) - if (skb_checksum_help(skb)) - goto out_kfree_skb; + if (skb->ip_summed == CHECKSUM_PARTIAL) { + skb_set_transport_header(skb, skb->csum_start - + skb_headroom(skb)); + + if (!(dev->features & NETIF_F_GEN_CSUM) && + (!(dev->features & NETIF_F_IP_CSUM) || + skb->protocol != htons(ETH_P_IP))) + if (skb_checksum_help(skb)) + goto out_kfree_skb; + } gso: spin_lock_prefetch(&dev->queue_lock); @@ -1543,9 +1529,9 @@ out: Receiver routines =======================================================================*/ -int netdev_max_backlog = 1000; -int netdev_budget = 300; -int weight_p = 64; /* old backlog weight */ +int netdev_max_backlog __read_mostly = 1000; +int netdev_budget __read_mostly = 300; +int weight_p __read_mostly = 64; /* old backlog weight */ DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, }; @@ -1577,7 +1563,7 @@ int netif_rx(struct sk_buff *skb) if (netpoll_rx(skb)) return NET_RX_DROP; - if (!skb->tstamp.off_sec) + if (!skb->tstamp.tv64) net_timestamp(skb); /* @@ -1684,40 +1670,46 @@ static void net_tx_action(struct softirq_action *h) } } -static __inline__ int deliver_skb(struct sk_buff *skb, - struct packet_type *pt_prev, - struct net_device *orig_dev) +static inline int deliver_skb(struct sk_buff *skb, + struct packet_type *pt_prev, + struct net_device *orig_dev) { atomic_inc(&skb->users); return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } #if defined(CONFIG_BRIDGE) || defined (CONFIG_BRIDGE_MODULE) -int (*br_handle_frame_hook)(struct net_bridge_port *p, struct sk_buff **pskb); +/* These hooks defined here for ATM */ struct net_bridge; struct net_bridge_fdb_entry *(*br_fdb_get_hook)(struct net_bridge *br, unsigned char *addr); -void (*br_fdb_put_hook)(struct net_bridge_fdb_entry *ent); +void (*br_fdb_put_hook)(struct net_bridge_fdb_entry *ent) __read_mostly; -static __inline__ int handle_bridge(struct sk_buff **pskb, - struct packet_type **pt_prev, int *ret, - struct net_device *orig_dev) +/* + * If bridge module is loaded call bridging hook. + * returns NULL if packet was consumed. + */ +struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p, + struct sk_buff *skb) __read_mostly; +static inline struct sk_buff *handle_bridge(struct sk_buff *skb, + struct packet_type **pt_prev, int *ret, + struct net_device *orig_dev) { struct net_bridge_port *port; - if ((*pskb)->pkt_type == PACKET_LOOPBACK || - (port = rcu_dereference((*pskb)->dev->br_port)) == NULL) - return 0; + if (skb->pkt_type == PACKET_LOOPBACK || + (port = rcu_dereference(skb->dev->br_port)) == NULL) + return skb; if (*pt_prev) { - *ret = deliver_skb(*pskb, *pt_prev, orig_dev); + *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; } - return br_handle_frame_hook(port, pskb); + return br_handle_frame_hook(port, skb); } #else -#define handle_bridge(skb, pt_prev, ret, orig_dev) (0) +#define handle_bridge(skb, pt_prev, ret, orig_dev) (skb) #endif #ifdef CONFIG_NET_CLS_ACT @@ -1747,10 +1739,10 @@ static int ing_filter(struct sk_buff *skb) skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_INGRESS); - spin_lock(&dev->queue_lock); + spin_lock(&dev->ingress_lock); if ((q = dev->qdisc_ingress) != NULL) result = q->enqueue(skb, q); - spin_unlock(&dev->queue_lock); + spin_unlock(&dev->ingress_lock); } @@ -1769,7 +1761,7 @@ int netif_receive_skb(struct sk_buff *skb) if (skb->dev->poll && netpoll_rx(skb)) return NET_RX_DROP; - if (!skb->tstamp.off_sec) + if (!skb->tstamp.tv64) net_timestamp(skb); if (!skb->iif) @@ -1782,8 +1774,9 @@ int netif_receive_skb(struct sk_buff *skb) __get_cpu_var(netdev_rx_stat).total++; - skb->h.raw = skb->nh.raw = skb->data; - skb->mac_len = skb->nh.raw - skb->mac.raw; + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + skb->mac_len = skb->network_header - skb->mac_header; pt_prev = NULL; @@ -1823,7 +1816,8 @@ int netif_receive_skb(struct sk_buff *skb) ncls: #endif - if (handle_bridge(&skb, &pt_prev, &ret, orig_dev)) + skb = handle_bridge(skb, &pt_prev, &ret, orig_dev); + if (!skb) goto out; type = skb->protocol; @@ -2076,7 +2070,7 @@ static int dev_ifconf(char __user *arg) * This is invoked by the /proc filesystem handler to display a device * in detail. */ -static __inline__ struct net_device *dev_get_idx(loff_t pos) +static struct net_device *dev_get_idx(loff_t pos) { struct net_device *dev; loff_t i; @@ -2105,9 +2099,9 @@ void dev_seq_stop(struct seq_file *seq, void *v) static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) { - if (dev->get_stats) { - struct net_device_stats *stats = dev->get_stats(dev); + struct net_device_stats *stats = dev->get_stats(dev); + if (stats) { seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu " "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n", dev->name, stats->rx_bytes, stats->rx_packets, @@ -2185,7 +2179,7 @@ static int softnet_seq_show(struct seq_file *seq, void *v) return 0; } -static struct seq_operations dev_seq_ops = { +static const struct seq_operations dev_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, @@ -2205,7 +2199,7 @@ static const struct file_operations dev_seq_fops = { .release = seq_release, }; -static struct seq_operations softnet_seq_ops = { +static const struct seq_operations softnet_seq_ops = { .start = softnet_seq_start, .next = softnet_seq_next, .stop = softnet_seq_stop, @@ -2225,12 +2219,135 @@ static const struct file_operations softnet_seq_fops = { .release = seq_release, }; -#ifdef CONFIG_WIRELESS_EXT -extern int wireless_proc_init(void); -#else -#define wireless_proc_init() 0 +static void *ptype_get_idx(loff_t pos) +{ + struct packet_type *pt = NULL; + loff_t i = 0; + int t; + + list_for_each_entry_rcu(pt, &ptype_all, list) { + if (i == pos) + return pt; + ++i; + } + + for (t = 0; t < 16; t++) { + list_for_each_entry_rcu(pt, &ptype_base[t], list) { + if (i == pos) + return pt; + ++i; + } + } + return NULL; +} + +static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) +{ + rcu_read_lock(); + return *pos ? ptype_get_idx(*pos - 1) : SEQ_START_TOKEN; +} + +static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct packet_type *pt; + struct list_head *nxt; + int hash; + + ++*pos; + if (v == SEQ_START_TOKEN) + return ptype_get_idx(0); + + pt = v; + nxt = pt->list.next; + if (pt->type == htons(ETH_P_ALL)) { + if (nxt != &ptype_all) + goto found; + hash = 0; + nxt = ptype_base[0].next; + } else + hash = ntohs(pt->type) & 15; + + while (nxt == &ptype_base[hash]) { + if (++hash >= 16) + return NULL; + nxt = ptype_base[hash].next; + } +found: + return list_entry(nxt, struct packet_type, list); +} + +static void ptype_seq_stop(struct seq_file *seq, void *v) +{ + rcu_read_unlock(); +} + +static void ptype_seq_decode(struct seq_file *seq, void *sym) +{ +#ifdef CONFIG_KALLSYMS + unsigned long offset = 0, symsize; + const char *symname; + char *modname; + char namebuf[128]; + + symname = kallsyms_lookup((unsigned long)sym, &symsize, &offset, + &modname, namebuf); + + if (symname) { + char *delim = ":"; + + if (!modname) + modname = delim = ""; + seq_printf(seq, "%s%s%s%s+0x%lx", delim, modname, delim, + symname, offset); + return; + } #endif + seq_printf(seq, "[%p]", sym); +} + +static int ptype_seq_show(struct seq_file *seq, void *v) +{ + struct packet_type *pt = v; + + if (v == SEQ_START_TOKEN) + seq_puts(seq, "Type Device Function\n"); + else { + if (pt->type == htons(ETH_P_ALL)) + seq_puts(seq, "ALL "); + else + seq_printf(seq, "%04x", ntohs(pt->type)); + + seq_printf(seq, " %-8s ", + pt->dev ? pt->dev->name : ""); + ptype_seq_decode(seq, pt->func); + seq_putc(seq, '\n'); + } + + return 0; +} + +static const struct seq_operations ptype_seq_ops = { + .start = ptype_seq_start, + .next = ptype_seq_next, + .stop = ptype_seq_stop, + .show = ptype_seq_show, +}; + +static int ptype_seq_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &ptype_seq_ops); +} + +static const struct file_operations ptype_seq_fops = { + .owner = THIS_MODULE, + .open = ptype_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + + static int __init dev_proc_init(void) { int rc = -ENOMEM; @@ -2239,13 +2356,18 @@ static int __init dev_proc_init(void) goto out; if (!proc_net_fops_create("softnet_stat", S_IRUGO, &softnet_seq_fops)) goto out_dev; - if (wireless_proc_init()) + if (!proc_net_fops_create("ptype", S_IRUGO, &ptype_seq_fops)) + goto out_dev2; + + if (wext_proc_init()) goto out_softnet; rc = 0; out: return rc; out_softnet: proc_net_remove("softnet_stat"); +out_dev2: + proc_net_remove("ptype"); out_dev: proc_net_remove("dev"); goto out; @@ -2795,29 +2917,9 @@ int dev_ioctl(unsigned int cmd, void __user *arg) ret = -EFAULT; return ret; } -#ifdef CONFIG_WIRELESS_EXT /* Take care of Wireless Extensions */ - if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) { - /* If command is `set a parameter', or - * `get the encoding parameters', check if - * the user has the right to do it */ - if (IW_IS_SET(cmd) || cmd == SIOCGIWENCODE - || cmd == SIOCGIWENCODEEXT) { - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - } - dev_load(ifr.ifr_name); - rtnl_lock(); - /* Follow me in net/core/wireless.c */ - ret = wireless_process_ioctl(&ifr, cmd); - rtnl_unlock(); - if (IW_IS_GET(cmd) && - copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - return ret; - } -#endif /* CONFIG_WIRELESS_EXT */ + if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) + return wext_handle_ioctl(&ifr, cmd, arg); return -EINVAL; } } @@ -2847,7 +2949,7 @@ static int dev_boot_phase = 1; static DEFINE_SPINLOCK(net_todo_list_lock); static struct list_head net_todo_list = LIST_HEAD_INIT(net_todo_list); -static inline void net_set_todo(struct net_device *dev) +static void net_set_todo(struct net_device *dev) { spin_lock(&net_todo_list_lock); list_add_tail(&dev->todo_list, &net_todo_list); @@ -2888,9 +2990,7 @@ int register_netdevice(struct net_device *dev) spin_lock_init(&dev->queue_lock); spin_lock_init(&dev->_xmit_lock); dev->xmit_lock_owner = -1; -#ifdef CONFIG_NET_CLS_ACT spin_lock_init(&dev->ingress_lock); -#endif dev->iflink = -1; @@ -3002,7 +3102,7 @@ out: * chain. 0 is returned on success. A negative errno code is returned * on a failure to set up the device, or if the name is a duplicate. * - * This is a wrapper around register_netdev that takes the rtnl semaphore + * This is a wrapper around register_netdevice that takes the rtnl semaphore * and expands the device name if you passed a format string to * alloc_netdev. */ @@ -3157,6 +3257,13 @@ out: mutex_unlock(&net_todo_run_mutex); } +static struct net_device_stats *maybe_internal_stats(struct net_device *dev) +{ + if (dev->features & NETIF_F_INTERNAL_STATS) + return &dev->stats; + return NULL; +} + /** * alloc_netdev - allocate network device * @sizeof_priv: size of private data to allocate space for @@ -3192,6 +3299,7 @@ struct net_device *alloc_netdev(int sizeof_priv, const char *name, if (sizeof_priv) dev->priv = netdev_priv(dev); + dev->get_stats = maybe_internal_stats; setup(dev); strcpy(dev->name, name); return dev; diff --git a/net/core/dev_mcast.c b/net/core/dev_mcast.c index 56b310c0c860..7d57bf77f3a3 100644 --- a/net/core/dev_mcast.c +++ b/net/core/dev_mcast.c @@ -264,7 +264,7 @@ static int dev_mc_seq_show(struct seq_file *seq, void *v) return 0; } -static struct seq_operations dev_mc_seq_ops = { +static const struct seq_operations dev_mc_seq_ops = { .start = dev_mc_seq_start, .next = dev_mc_seq_next, .stop = dev_mc_seq_stop, diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 6168edd137dd..8d5e5a09b576 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -836,7 +836,7 @@ int dev_ethtool(struct ifreq *ifr) return -EPERM; } - if(dev->ethtool_ops->begin) + if (dev->ethtool_ops->begin) if ((rc = dev->ethtool_ops->begin(dev)) < 0) return rc; @@ -952,7 +952,7 @@ int dev_ethtool(struct ifreq *ifr) rc = -EOPNOTSUPP; } - if(dev->ethtool_ops->complete) + if (dev->ethtool_ops->complete) dev->ethtool_ops->complete(dev); if (old_features != dev->features) diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 7174ced75efc..8c5474e16683 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -44,6 +44,12 @@ static void rules_ops_put(struct fib_rules_ops *ops) module_put(ops->owner); } +static void flush_route_cache(struct fib_rules_ops *ops) +{ + if (ops->flush_cache) + ops->flush_cache(); +} + int fib_rules_register(struct fib_rules_ops *ops) { int err = -EEXIST; @@ -132,10 +138,25 @@ int fib_rules_lookup(struct fib_rules_ops *ops, struct flowi *fl, rcu_read_lock(); list_for_each_entry_rcu(rule, ops->rules_list, list) { +jumped: if (!fib_rule_match(rule, ops, fl, flags)) continue; - err = ops->action(rule, fl, flags, arg); + if (rule->action == FR_ACT_GOTO) { + struct fib_rule *target; + + target = rcu_dereference(rule->ctarget); + if (target == NULL) { + continue; + } else { + rule = target; + goto jumped; + } + } else if (rule->action == FR_ACT_NOP) + continue; + else + err = ops->action(rule, fl, flags, arg); + if (err != -EAGAIN) { fib_rule_get(rule); arg->rule = rule; @@ -174,13 +195,13 @@ errout: return err; } -int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rules_ops *ops = NULL; struct fib_rule *rule, *r, *last = NULL; struct nlattr *tb[FRA_MAX+1]; - int err = -EINVAL; + int err = -EINVAL, unresolved = 0; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) goto errout; @@ -237,6 +258,28 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (!rule->pref && ops->default_pref) rule->pref = ops->default_pref(); + err = -EINVAL; + if (tb[FRA_GOTO]) { + if (rule->action != FR_ACT_GOTO) + goto errout_free; + + rule->target = nla_get_u32(tb[FRA_GOTO]); + /* Backward jumps are prohibited to avoid endless loops */ + if (rule->target <= rule->pref) + goto errout_free; + + list_for_each_entry(r, ops->rules_list, list) { + if (r->pref == rule->target) { + rule->ctarget = r; + break; + } + } + + if (rule->ctarget == NULL) + unresolved = 1; + } else if (rule->action == FR_ACT_GOTO) + goto errout_free; + err = ops->configure(rule, skb, nlh, frh, tb); if (err < 0) goto errout_free; @@ -249,12 +292,35 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) fib_rule_get(rule); + if (ops->unresolved_rules) { + /* + * There are unresolved goto rules in the list, check if + * any of them are pointing to this new rule. + */ + list_for_each_entry(r, ops->rules_list, list) { + if (r->action == FR_ACT_GOTO && + r->target == rule->pref) { + BUG_ON(r->ctarget != NULL); + rcu_assign_pointer(r->ctarget, rule); + if (--ops->unresolved_rules == 0) + break; + } + } + } + + if (rule->action == FR_ACT_GOTO) + ops->nr_goto_rules++; + + if (unresolved) + ops->unresolved_rules++; + if (last) list_add_rcu(&rule->list, &last->list); else list_add_rcu(&rule->list, ops->rules_list); notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).pid); + flush_route_cache(ops); rules_ops_put(ops); return 0; @@ -265,11 +331,11 @@ errout: return err; } -int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rules_ops *ops = NULL; - struct fib_rule *rule; + struct fib_rule *rule, *tmp; struct nlattr *tb[FRA_MAX+1]; int err = -EINVAL; @@ -322,10 +388,30 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) } list_del_rcu(&rule->list); + + if (rule->action == FR_ACT_GOTO) + ops->nr_goto_rules--; + + /* + * Check if this rule is a target to any of them. If so, + * disable them. As this operation is eventually very + * expensive, it is only performed if goto rules have + * actually been added. + */ + if (ops->nr_goto_rules > 0) { + list_for_each_entry(tmp, ops->rules_list, list) { + if (tmp->ctarget == rule) { + rcu_assign_pointer(tmp->ctarget, NULL); + ops->unresolved_rules++; + } + } + } + synchronize_rcu(); notify_rule_change(RTM_DELRULE, rule, ops, nlh, NETLINK_CB(skb).pid); fib_rule_put(rule); + flush_route_cache(ops); rules_ops_put(ops); return 0; } @@ -371,9 +457,16 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh->action = rule->action; frh->flags = rule->flags; - if (rule->ifname[0]) + if (rule->action == FR_ACT_GOTO && rule->ctarget == NULL) + frh->flags |= FIB_RULE_UNRESOLVED; + + if (rule->ifname[0]) { NLA_PUT_STRING(skb, FRA_IFNAME, rule->ifname); + if (rule->ifindex == -1) + frh->flags |= FIB_RULE_DEV_DETACHED; + } + if (rule->pref) NLA_PUT_U32(skb, FRA_PRIORITY, rule->pref); @@ -383,6 +476,9 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, 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 (ops->fill(rule, skb, nlh, frh) < 0) goto nla_put_failure; @@ -393,19 +489,14 @@ nla_put_failure: return -EMSGSIZE; } -int fib_rules_dump(struct sk_buff *skb, struct netlink_callback *cb, int family) +static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb, + struct fib_rules_ops *ops) { int idx = 0; struct fib_rule *rule; - struct fib_rules_ops *ops; - - ops = lookup_rules_ops(family); - if (ops == NULL) - return -EAFNOSUPPORT; - rcu_read_lock(); - list_for_each_entry_rcu(rule, ops->rules_list, list) { - if (idx < cb->args[0]) + list_for_each_entry(rule, ops->rules_list, list) { + if (idx < cb->args[1]) goto skip; if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).pid, @@ -415,14 +506,44 @@ int fib_rules_dump(struct sk_buff *skb, struct netlink_callback *cb, int family) skip: idx++; } - rcu_read_unlock(); - cb->args[0] = idx; + cb->args[1] = idx; rules_ops_put(ops); return skb->len; } -EXPORT_SYMBOL_GPL(fib_rules_dump); +static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct fib_rules_ops *ops; + int idx = 0, family; + + family = rtnl_msg_family(cb->nlh); + if (family != AF_UNSPEC) { + /* Protocol specific dump request */ + ops = lookup_rules_ops(family); + if (ops == NULL) + return -EAFNOSUPPORT; + + return dump_rules(skb, cb, ops); + } + + rcu_read_lock(); + list_for_each_entry_rcu(ops, &rules_ops, list) { + if (idx < cb->args[0] || !try_module_get(ops->owner)) + goto skip; + + if (dump_rules(skb, cb, ops) < 0) + break; + + cb->args[1] = 0; + skip: + idx++; + } + rcu_read_unlock(); + cb->args[0] = idx; + + return skb->len; +} static void notify_rule_change(int event, struct fib_rule *rule, struct fib_rules_ops *ops, struct nlmsghdr *nlh, @@ -501,6 +622,10 @@ static struct notifier_block fib_rules_notifier = { static int __init fib_rules_init(void) { + rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL); + rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL); + rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule); + return register_netdevice_notifier(&fib_rules_notifier); } diff --git a/net/core/filter.c b/net/core/filter.c index 8d185a089c53..bd903aaf7aa7 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -42,11 +42,11 @@ static void *__load_pointer(struct sk_buff *skb, int k) u8 *ptr = NULL; if (k >= SKF_NET_OFF) - ptr = skb->nh.raw + k - SKF_NET_OFF; + ptr = skb_network_header(skb) + k - SKF_NET_OFF; else if (k >= SKF_LL_OFF) - ptr = skb->mac.raw + k - SKF_LL_OFF; + ptr = skb_mac_header(skb) + k - SKF_LL_OFF; - if (ptr >= skb->head && ptr < skb->tail) + if (ptr >= skb->head && ptr < skb_tail_pointer(skb)) return ptr; return NULL; } diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index 259473d0559d..bcc25591d8ac 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -61,7 +61,7 @@ gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type, spin_lock_bh(lock); d->lock = lock; if (type) - d->tail = (struct rtattr *) skb->tail; + d->tail = (struct rtattr *)skb_tail_pointer(skb); d->skb = skb; d->compat_tc_stats = tc_stats_type; d->compat_xstats = xstats_type; @@ -212,7 +212,7 @@ int gnet_stats_finish_copy(struct gnet_dump *d) { if (d->tail) - d->tail->rta_len = d->skb->tail - (u8 *) d->tail; + d->tail->rta_len = skb_tail_pointer(d->skb) - (u8 *)d->tail; if (d->compat_tc_stats) if (gnet_stats_copy(d, d->compat_tc_stats, &d->tc_stats, diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 8b45c9d3b249..e3c26a9ccad6 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -79,7 +79,7 @@ static void rfc2863_policy(struct net_device *dev) case IF_LINK_MODE_DEFAULT: default: break; - }; + } dev->operstate = operstate; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 841e3f32cab1..6f3bb73053c2 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1125,7 +1125,7 @@ int neigh_compat_output(struct sk_buff *skb) { struct net_device *dev = skb->dev; - __skb_pull(skb, skb->nh.raw - skb->data); + __skb_pull(skb, skb_network_offset(skb)); if (dev->hard_header && dev->hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL, @@ -1147,7 +1147,7 @@ int neigh_resolve_output(struct sk_buff *skb) if (!dst || !(neigh = dst->neighbour)) goto discard; - __skb_pull(skb, skb->nh.raw - skb->data); + __skb_pull(skb, skb_network_offset(skb)); if (!neigh_event_send(neigh, skb)) { int err; @@ -1190,7 +1190,7 @@ int neigh_connected_output(struct sk_buff *skb) struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; - __skb_pull(skb, skb->nh.raw - skb->data); + __skb_pull(skb, skb_network_offset(skb)); read_lock_bh(&neigh->lock); err = dev->hard_header(skb, dev, ntohs(skb->protocol), @@ -1441,7 +1441,7 @@ int neigh_table_clear(struct neigh_table *tbl) return 0; } -int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct ndmsg *ndm; struct nlattr *dst_attr; @@ -1506,7 +1506,7 @@ out: return err; } -int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct ndmsg *ndm; struct nlattr *tb[NDA_MAX+1]; @@ -1786,7 +1786,7 @@ static struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] __read_mostly = { [NDTPA_LOCKTIME] = { .type = NLA_U64 }, }; -int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct neigh_table *tbl; struct ndtmsg *ndtmsg; @@ -1910,7 +1910,7 @@ errout: return err; } -int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) +static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) { int family, tidx, nidx = 0; int tbl_skip = cb->args[0]; @@ -2034,7 +2034,7 @@ out: return rc; } -int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) +static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) { struct neigh_table *tbl; int t, family, s_t; @@ -2393,7 +2393,7 @@ static int neigh_stat_seq_show(struct seq_file *seq, void *v) return 0; } -static struct seq_operations neigh_stat_seq_ops = { +static const struct seq_operations neigh_stat_seq_ops = { .start = neigh_stat_seq_start, .next = neigh_stat_seq_next, .stop = neigh_stat_seq_stop, @@ -2746,14 +2746,26 @@ void neigh_sysctl_unregister(struct neigh_parms *p) #endif /* CONFIG_SYSCTL */ +static int __init neigh_init(void) +{ + rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL); + rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL); + rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info); + + rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info); + rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL); + + return 0; +} + +subsys_initcall(neigh_init); + EXPORT_SYMBOL(__neigh_event_send); EXPORT_SYMBOL(neigh_changeaddr); EXPORT_SYMBOL(neigh_compat_output); EXPORT_SYMBOL(neigh_connected_output); EXPORT_SYMBOL(neigh_create); -EXPORT_SYMBOL(neigh_delete); EXPORT_SYMBOL(neigh_destroy); -EXPORT_SYMBOL(neigh_dump_info); EXPORT_SYMBOL(neigh_event_ns); EXPORT_SYMBOL(neigh_ifdown); EXPORT_SYMBOL(neigh_lookup); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 4cbb1290a6a3..221a64ab64f7 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -352,8 +352,8 @@ static ssize_t wireless_show(struct device *d, char *buf, read_lock(&dev_base_lock); if (dev_isalive(dev)) { - if(dev->wireless_handlers && - dev->wireless_handlers->get_wireless_stats) + if (dev->wireless_handlers && + dev->wireless_handlers->get_wireless_stats) iw = dev->wireless_handlers->get_wireless_stats(dev); if (iw != NULL) ret = (*format)(iw, buf); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 4581ece48bb2..b316435b0e2a 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -86,7 +86,7 @@ static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh, { __wsum psum; - if (uh->check == 0 || skb->ip_summed == CHECKSUM_UNNECESSARY) + if (uh->check == 0 || skb_csum_unnecessary(skb)) return 0; psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0); @@ -293,10 +293,12 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) if (!skb) return; - memcpy(skb->data, msg, len); + skb_copy_to_linear_data(skb, msg, len); skb->len += len; - skb->h.uh = udph = (struct udphdr *) skb_push(skb, sizeof(*udph)); + skb_push(skb, sizeof(*udph)); + skb_reset_transport_header(skb); + udph = udp_hdr(skb); udph->source = htons(np->local_port); udph->dest = htons(np->remote_port); udph->len = htons(udp_len); @@ -308,7 +310,9 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) if (udph->check == 0) udph->check = CSUM_MANGLED_0; - skb->nh.iph = iph = (struct iphdr *)skb_push(skb, sizeof(*iph)); + skb_push(skb, sizeof(*iph)); + skb_reset_network_header(skb); + iph = ip_hdr(skb); /* iph->version = 4; iph->ihl = 5; */ put_unaligned(0x45, (unsigned char *)iph); @@ -324,7 +328,7 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); - skb->mac.raw = skb->data; + skb_reset_mac_header(skb); skb->protocol = eth->h_proto = htons(ETH_P_IP); memcpy(eth->h_source, np->local_mac, 6); memcpy(eth->h_dest, np->remote_mac, 6); @@ -359,8 +363,9 @@ static void arp_reply(struct sk_buff *skb) (2 * sizeof(u32))))) return; - skb->h.raw = skb->nh.raw = skb->data; - arp = skb->nh.arph; + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + arp = arp_hdr(skb); if ((arp->ar_hrd != htons(ARPHRD_ETHER) && arp->ar_hrd != htons(ARPHRD_IEEE802)) || @@ -389,7 +394,7 @@ static void arp_reply(struct sk_buff *skb) if (!send_skb) return; - send_skb->nh.raw = send_skb->data; + skb_reset_network_header(send_skb); arp = (struct arphdr *) skb_put(send_skb, size); send_skb->dev = skb->dev; send_skb->protocol = htons(ETH_P_ARP); @@ -443,7 +448,7 @@ int __netpoll_rx(struct sk_buff *skb) goto out; /* check if netpoll clients need ARP */ - if (skb->protocol == __constant_htons(ETH_P_ARP) && + if (skb->protocol == htons(ETH_P_ARP) && atomic_read(&trapped)) { skb_queue_tail(&npi->arp_tx, skb); return 1; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 4b01496dc33d..b92a322872a8 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -164,14 +164,11 @@ #define VERSION "pktgen v2.68: Packet Generator for packet performance testing.\n" -/* #define PG_DEBUG(a) a */ -#define PG_DEBUG(a) - /* The buckets are exponential in 'width' */ #define LAT_BUCKETS_MAX 32 #define IP_NAME_SZ 32 #define MAX_MPLS_LABELS 16 /* This is the max label stack depth */ -#define MPLS_STACK_BOTTOM __constant_htonl(0x00000100) +#define MPLS_STACK_BOTTOM htonl(0x00000100) /* Device flag bits */ #define F_IPSRC_RND (1<<0) /* IP-Src Random */ @@ -214,15 +211,11 @@ struct flow_state { }; struct pktgen_dev { - /* * Try to keep frequent/infrequent used vars. separated. */ - - char ifname[IFNAMSIZ]; - char result[512]; - - struct pktgen_thread *pg_thread; /* the owner */ + struct proc_dir_entry *entry; /* proc file */ + struct pktgen_thread *pg_thread;/* the owner */ struct list_head list; /* Used for chaining in the thread's run-queue */ int running; /* if this changes to false, the test will stop */ @@ -349,6 +342,8 @@ struct pktgen_dev { unsigned cflows; /* Concurrent flows (config) */ unsigned lflow; /* Flow length (config) */ unsigned nflows; /* accumulated flows (stats) */ + + char result[512]; }; struct pktgen_hdr { @@ -468,17 +463,6 @@ static inline __u64 pg_div64(__u64 n, __u64 base) return tmp; } -static inline u32 pktgen_random(void) -{ -#if 0 - __u32 n; - get_random_bytes(&n, 4); - return n; -#else - return net_random(); -#endif -} - static inline __u64 getCurMs(void) { struct timeval tv; @@ -512,7 +496,7 @@ static void pktgen_stop_all_threads_ifs(void); static int pktgen_stop_device(struct pktgen_dev *pkt_dev); static void pktgen_stop(struct pktgen_thread *t); static void pktgen_clear_counters(struct pktgen_dev *pkt_dev); -static int pktgen_mark_device(const char *ifname); + static unsigned int scan_ip6(const char *s, char ip[16]); static unsigned int fmt_ip6(char *s, const char ip[16]); @@ -606,7 +590,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v) " frags: %d delay: %u clone_skb: %d ifname: %s\n", pkt_dev->nfrags, 1000 * pkt_dev->delay_us + pkt_dev->delay_ns, - pkt_dev->clone_skb, pkt_dev->ifname); + pkt_dev->clone_skb, pkt_dev->odev->name); seq_printf(seq, " flows: %u flowlen: %u\n", pkt_dev->cflows, pkt_dev->lflow); @@ -661,7 +645,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->nr_labels) { unsigned i; seq_printf(seq, " mpls: "); - for(i = 0; i < pkt_dev->nr_labels; i++) + for (i = 0; i < pkt_dev->nr_labels; i++) seq_printf(seq, "%08x%s", ntohl(pkt_dev->labels[i]), i == pkt_dev->nr_labels-1 ? "\n" : ", "); } @@ -766,7 +750,7 @@ static int hex32_arg(const char __user *user_buffer, unsigned long maxlen, __u32 int i = 0; *num = 0; - for(; i < maxlen; i++) { + for (; i < maxlen; i++) { char c; *num <<= 4; if (get_user(c, &user_buffer[i])) @@ -802,7 +786,7 @@ static int count_trail_chars(const char __user * user_buffer, break; default: goto done; - }; + } } done: return i; @@ -845,7 +829,7 @@ static int strn_len(const char __user * user_buffer, unsigned int maxlen) break; default: break; - }; + } } done_str: return i; @@ -874,7 +858,7 @@ static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev) n++; if (n >= MAX_MPLS_LABELS) return -E2BIG; - } while(c == ','); + } while (c == ','); pkt_dev->nr_labels = n; return i; @@ -1503,7 +1487,7 @@ static ssize_t pktgen_if_write(struct file *file, if (len < 0) { return len; } i += len; offset = sprintf(pg_result, "OK: mpls="); - for(n = 0; n < pkt_dev->nr_labels; n++) + for (n = 0; n < pkt_dev->nr_labels; n++) offset += sprintf(pg_result + offset, "%08x%s", ntohl(pkt_dev->labels[n]), n == pkt_dev->nr_labels-1 ? "" : ","); @@ -1697,13 +1681,13 @@ static int pktgen_thread_show(struct seq_file *seq, void *v) if_lock(t); list_for_each_entry(pkt_dev, &t->if_list, list) if (pkt_dev->running) - seq_printf(seq, "%s ", pkt_dev->ifname); + seq_printf(seq, "%s ", pkt_dev->odev->name); seq_printf(seq, "\nStopped: "); list_for_each_entry(pkt_dev, &t->if_list, list) if (!pkt_dev->running) - seq_printf(seq, "%s ", pkt_dev->ifname); + seq_printf(seq, "%s ", pkt_dev->odev->name); if (t->result[0]) seq_printf(seq, "\nResult: %s\n", t->result); @@ -1849,16 +1833,14 @@ static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove) /* * mark a device for removal */ -static int pktgen_mark_device(const char *ifname) +static void pktgen_mark_device(const char *ifname) { struct pktgen_dev *pkt_dev = NULL; const int max_tries = 10, msec_per_try = 125; int i = 0; - int ret = 0; mutex_lock(&pktgen_thread_lock); - PG_DEBUG(printk("pktgen: pktgen_mark_device marking %s for removal\n", - ifname)); + pr_debug("pktgen: pktgen_mark_device marking %s for removal\n", ifname); while (1) { @@ -1867,8 +1849,8 @@ static int pktgen_mark_device(const char *ifname) break; /* success */ mutex_unlock(&pktgen_thread_lock); - PG_DEBUG(printk("pktgen: pktgen_mark_device waiting for %s " - "to disappear....\n", ifname)); + pr_debug("pktgen: pktgen_mark_device waiting for %s " + "to disappear....\n", ifname); schedule_timeout_interruptible(msecs_to_jiffies(msec_per_try)); mutex_lock(&pktgen_thread_lock); @@ -1876,79 +1858,91 @@ static int pktgen_mark_device(const char *ifname) printk("pktgen_mark_device: timed out after waiting " "%d msec for device %s to be removed\n", msec_per_try * i, ifname); - ret = 1; break; } } mutex_unlock(&pktgen_thread_lock); +} - return ret; +static void pktgen_change_name(struct net_device *dev) +{ + struct pktgen_thread *t; + + list_for_each_entry(t, &pktgen_threads, th_list) { + struct pktgen_dev *pkt_dev; + + list_for_each_entry(pkt_dev, &t->if_list, list) { + if (pkt_dev->odev != dev) + continue; + + remove_proc_entry(pkt_dev->entry->name, pg_proc_dir); + + pkt_dev->entry = create_proc_entry(dev->name, 0600, + pg_proc_dir); + if (!pkt_dev->entry) + printk(KERN_ERR "pktgen: can't move proc " + " entry for '%s'\n", dev->name); + break; + } + } } static int pktgen_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = (struct net_device *)(ptr); + struct net_device *dev = ptr; /* It is OK that we do not hold the group lock right now, * as we run under the RTNL lock. */ switch (event) { - case NETDEV_CHANGEADDR: - case NETDEV_GOING_DOWN: - case NETDEV_DOWN: - case NETDEV_UP: - /* Ignore for now */ + case NETDEV_CHANGENAME: + pktgen_change_name(dev); break; case NETDEV_UNREGISTER: pktgen_mark_device(dev->name); break; - }; + } return NOTIFY_DONE; } /* Associate pktgen_dev with a device. */ -static struct net_device *pktgen_setup_dev(struct pktgen_dev *pkt_dev) +static int pktgen_setup_dev(struct pktgen_dev *pkt_dev, const char *ifname) { struct net_device *odev; + int err; /* Clean old setups */ - if (pkt_dev->odev) { dev_put(pkt_dev->odev); pkt_dev->odev = NULL; } - odev = dev_get_by_name(pkt_dev->ifname); - + odev = dev_get_by_name(ifname); if (!odev) { - printk("pktgen: no such netdevice: \"%s\"\n", pkt_dev->ifname); - goto out; + printk("pktgen: no such netdevice: \"%s\"\n", ifname); + return -ENODEV; } + if (odev->type != ARPHRD_ETHER) { - printk("pktgen: not an ethernet device: \"%s\"\n", - pkt_dev->ifname); - goto out_put; - } - if (!netif_running(odev)) { - printk("pktgen: device is down: \"%s\"\n", pkt_dev->ifname); - goto out_put; + printk("pktgen: not an ethernet device: \"%s\"\n", ifname); + err = -EINVAL; + } else if (!netif_running(odev)) { + printk("pktgen: device is down: \"%s\"\n", ifname); + err = -ENETDOWN; + } else { + pkt_dev->odev = odev; + return 0; } - pkt_dev->odev = odev; - return pkt_dev->odev; - -out_put: dev_put(odev); -out: - return NULL; - + return err; } /* Read pkt_dev from the interface and set up internal pktgen_dev @@ -1956,10 +1950,6 @@ out: */ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) { - /* Try once more, just in case it works now. */ - if (!pkt_dev->odev) - pktgen_setup_dev(pkt_dev); - if (!pkt_dev->odev) { printk("pktgen: ERROR: pkt_dev->odev == NULL in setup_inject.\n"); sprintf(pkt_dev->result, @@ -2096,7 +2086,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) int flow = 0; if (pkt_dev->cflows) { - flow = pktgen_random() % pkt_dev->cflows; + flow = random32() % pkt_dev->cflows; if (pkt_dev->flows[flow].count > pkt_dev->lflow) pkt_dev->flows[flow].count = 0; @@ -2108,7 +2098,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) __u32 tmp; if (pkt_dev->flags & F_MACSRC_RND) - mc = pktgen_random() % (pkt_dev->src_mac_count); + mc = random32() % pkt_dev->src_mac_count; else { mc = pkt_dev->cur_src_mac_offset++; if (pkt_dev->cur_src_mac_offset > @@ -2134,7 +2124,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) __u32 tmp; if (pkt_dev->flags & F_MACDST_RND) - mc = pktgen_random() % (pkt_dev->dst_mac_count); + mc = random32() % pkt_dev->dst_mac_count; else { mc = pkt_dev->cur_dst_mac_offset++; @@ -2158,27 +2148,26 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) if (pkt_dev->flags & F_MPLS_RND) { unsigned i; - for(i = 0; i < pkt_dev->nr_labels; 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 | - ((__force __be32)pktgen_random() & + ((__force __be32)random32() & htonl(0x000fffff)); } if ((pkt_dev->flags & F_VID_RND) && (pkt_dev->vlan_id != 0xffff)) { - pkt_dev->vlan_id = pktgen_random() % 4096; + pkt_dev->vlan_id = random32() & (4096-1); } if ((pkt_dev->flags & F_SVID_RND) && (pkt_dev->svlan_id != 0xffff)) { - pkt_dev->svlan_id = pktgen_random() % 4096; + pkt_dev->svlan_id = random32() & (4096 - 1); } if (pkt_dev->udp_src_min < pkt_dev->udp_src_max) { if (pkt_dev->flags & F_UDPSRC_RND) - pkt_dev->cur_udp_src = - ((pktgen_random() % - (pkt_dev->udp_src_max - pkt_dev->udp_src_min)) + - pkt_dev->udp_src_min); + pkt_dev->cur_udp_src = random32() % + (pkt_dev->udp_src_max - pkt_dev->udp_src_min) + + pkt_dev->udp_src_min; else { pkt_dev->cur_udp_src++; @@ -2189,10 +2178,9 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) if (pkt_dev->udp_dst_min < pkt_dev->udp_dst_max) { if (pkt_dev->flags & F_UDPDST_RND) { - pkt_dev->cur_udp_dst = - ((pktgen_random() % - (pkt_dev->udp_dst_max - pkt_dev->udp_dst_min)) + - pkt_dev->udp_dst_min); + pkt_dev->cur_udp_dst = random32() % + (pkt_dev->udp_dst_max - pkt_dev->udp_dst_min) + + pkt_dev->udp_dst_min; } else { pkt_dev->cur_udp_dst++; if (pkt_dev->cur_udp_dst >= pkt_dev->udp_dst_max) @@ -2207,7 +2195,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) saddr_max))) { __u32 t; if (pkt_dev->flags & F_IPSRC_RND) - t = ((pktgen_random() % (imx - imn)) + imn); + t = random32() % (imx - imn) + imn; else { t = ntohl(pkt_dev->cur_saddr); t++; @@ -2228,14 +2216,13 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) __be32 s; if (pkt_dev->flags & F_IPDST_RND) { - t = pktgen_random() % (imx - imn) + imn; + t = random32() % (imx - imn) + imn; s = htonl(t); while (LOOPBACK(s) || MULTICAST(s) || BADCLASS(s) || ZERONET(s) || LOCAL_MCAST(s)) { - t = (pktgen_random() % - (imx - imn)) + imn; + t = random32() % (imx - imn) + imn; s = htonl(t); } pkt_dev->cur_daddr = s; @@ -2267,7 +2254,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) for (i = 0; i < 4; i++) { pkt_dev->cur_in6_daddr.s6_addr32[i] = - (((__force __be32)pktgen_random() | + (((__force __be32)random32() | pkt_dev->min_in6_daddr.s6_addr32[i]) & pkt_dev->max_in6_daddr.s6_addr32[i]); } @@ -2277,9 +2264,9 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) if (pkt_dev->min_pkt_size < pkt_dev->max_pkt_size) { __u32 t; if (pkt_dev->flags & F_TXSIZE_RND) { - t = ((pktgen_random() % - (pkt_dev->max_pkt_size - pkt_dev->min_pkt_size)) - + pkt_dev->min_pkt_size); + t = random32() % + (pkt_dev->max_pkt_size - pkt_dev->min_pkt_size) + + pkt_dev->min_pkt_size; } else { t = pkt_dev->cur_pkt_size + 1; if (t > pkt_dev->max_pkt_size) @@ -2294,7 +2281,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) static void mpls_push(__be32 *mpls, struct pktgen_dev *pkt_dev) { unsigned i; - for(i = 0; i < pkt_dev->nr_labels; i++) { + for (i = 0; i < pkt_dev->nr_labels; i++) { *mpls++ = pkt_dev->labels[i] & ~MPLS_STACK_BOTTOM; } mpls--; @@ -2316,7 +2303,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, int datalen, iplen; struct iphdr *iph; struct pktgen_hdr *pgh = NULL; - __be16 protocol = __constant_htons(ETH_P_IP); + __be16 protocol = htons(ETH_P_IP); __be32 *mpls; __be16 *vlan_tci = NULL; /* Encapsulates priority and VLAN ID */ __be16 *vlan_encapsulated_proto = NULL; /* packet type ID field (or len) for VLAN tag */ @@ -2325,10 +2312,10 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, if (pkt_dev->nr_labels) - protocol = __constant_htons(ETH_P_MPLS_UC); + protocol = htons(ETH_P_MPLS_UC); if (pkt_dev->vlan_id != 0xffff) - protocol = __constant_htons(ETH_P_8021Q); + protocol = htons(ETH_P_8021Q); /* Update any of the values, used when we're incrementing various * fields. @@ -2354,24 +2341,28 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, mpls_push(mpls, pkt_dev); if (pkt_dev->vlan_id != 0xffff) { - if(pkt_dev->svlan_id != 0xffff) { + if (pkt_dev->svlan_id != 0xffff) { svlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); *svlan_tci = build_tci(pkt_dev->svlan_id, pkt_dev->svlan_cfi, pkt_dev->svlan_p); svlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); - *svlan_encapsulated_proto = __constant_htons(ETH_P_8021Q); + *svlan_encapsulated_proto = htons(ETH_P_8021Q); } vlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); *vlan_tci = build_tci(pkt_dev->vlan_id, pkt_dev->vlan_cfi, pkt_dev->vlan_p); vlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); - *vlan_encapsulated_proto = __constant_htons(ETH_P_IP); + *vlan_encapsulated_proto = htons(ETH_P_IP); } - iph = (struct iphdr *)skb_put(skb, sizeof(struct iphdr)); - udph = (struct udphdr *)skb_put(skb, sizeof(struct udphdr)); + skb->network_header = skb->tail; + skb->transport_header = skb->network_header + sizeof(struct iphdr); + skb_put(skb, sizeof(struct iphdr) + sizeof(struct udphdr)); + + iph = ip_hdr(skb); + udph = udp_hdr(skb); memcpy(eth, pkt_dev->hh, 12); *(__be16 *) & eth[12] = protocol; @@ -2400,12 +2391,11 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, iph->check = 0; iph->check = ip_fast_csum((void *)iph, iph->ihl); skb->protocol = protocol; - skb->mac.raw = ((u8 *) iph) - 14 - pkt_dev->nr_labels*sizeof(u32) - - VLAN_TAG_SIZE(pkt_dev) - SVLAN_TAG_SIZE(pkt_dev); + skb->mac_header = (skb->network_header - ETH_HLEN - + pkt_dev->nr_labels * sizeof(u32) - + VLAN_TAG_SIZE(pkt_dev) - SVLAN_TAG_SIZE(pkt_dev)); skb->dev = odev; skb->pkt_type = PACKET_HOST; - skb->nh.iph = iph; - skb->h.uh = udph; if (pkt_dev->nfrags <= 0) pgh = (struct pktgen_hdr *)skb_put(skb, datalen); @@ -2654,7 +2644,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, int datalen; struct ipv6hdr *iph; struct pktgen_hdr *pgh = NULL; - __be16 protocol = __constant_htons(ETH_P_IPV6); + __be16 protocol = htons(ETH_P_IPV6); __be32 *mpls; __be16 *vlan_tci = NULL; /* Encapsulates priority and VLAN ID */ __be16 *vlan_encapsulated_proto = NULL; /* packet type ID field (or len) for VLAN tag */ @@ -2662,10 +2652,10 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, __be16 *svlan_encapsulated_proto = NULL; /* packet type ID field (or len) for SVLAN tag */ if (pkt_dev->nr_labels) - protocol = __constant_htons(ETH_P_MPLS_UC); + protocol = htons(ETH_P_MPLS_UC); if (pkt_dev->vlan_id != 0xffff) - protocol = __constant_htons(ETH_P_8021Q); + protocol = htons(ETH_P_8021Q); /* Update any of the values, used when we're incrementing various * fields. @@ -2690,24 +2680,28 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, mpls_push(mpls, pkt_dev); if (pkt_dev->vlan_id != 0xffff) { - if(pkt_dev->svlan_id != 0xffff) { + if (pkt_dev->svlan_id != 0xffff) { svlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); *svlan_tci = build_tci(pkt_dev->svlan_id, pkt_dev->svlan_cfi, pkt_dev->svlan_p); svlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); - *svlan_encapsulated_proto = __constant_htons(ETH_P_8021Q); + *svlan_encapsulated_proto = htons(ETH_P_8021Q); } vlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); *vlan_tci = build_tci(pkt_dev->vlan_id, pkt_dev->vlan_cfi, pkt_dev->vlan_p); vlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); - *vlan_encapsulated_proto = __constant_htons(ETH_P_IPV6); + *vlan_encapsulated_proto = htons(ETH_P_IPV6); } - iph = (struct ipv6hdr *)skb_put(skb, sizeof(struct ipv6hdr)); - udph = (struct udphdr *)skb_put(skb, sizeof(struct udphdr)); + skb->network_header = skb->tail; + skb->transport_header = skb->network_header + sizeof(struct ipv6hdr); + skb_put(skb, sizeof(struct ipv6hdr) + sizeof(struct udphdr)); + + iph = ipv6_hdr(skb); + udph = udp_hdr(skb); memcpy(eth, pkt_dev->hh, 12); *(__be16 *) & eth[12] = protocol; @@ -2729,7 +2723,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, udph->len = htons(datalen + sizeof(struct udphdr)); udph->check = 0; /* No checksum */ - *(__be32 *) iph = __constant_htonl(0x60000000); /* Version + flow */ + *(__be32 *) iph = htonl(0x60000000); /* Version + flow */ if (pkt_dev->traffic_class) { /* Version + traffic class + flow (0) */ @@ -2744,13 +2738,12 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, ipv6_addr_copy(&iph->daddr, &pkt_dev->cur_in6_daddr); ipv6_addr_copy(&iph->saddr, &pkt_dev->cur_in6_saddr); - skb->mac.raw = ((u8 *) iph) - 14 - pkt_dev->nr_labels*sizeof(u32) - - VLAN_TAG_SIZE(pkt_dev) - SVLAN_TAG_SIZE(pkt_dev); + skb->mac_header = (skb->network_header - ETH_HLEN - + pkt_dev->nr_labels * sizeof(u32) - + VLAN_TAG_SIZE(pkt_dev) - SVLAN_TAG_SIZE(pkt_dev)); skb->protocol = protocol; skb->dev = odev; skb->pkt_type = PACKET_HOST; - skb->nh.ipv6h = iph; - skb->h.uh = udph; if (pkt_dev->nfrags <= 0) pgh = (struct pktgen_hdr *)skb_put(skb, datalen); @@ -2848,7 +2841,7 @@ static void pktgen_run(struct pktgen_thread *t) struct pktgen_dev *pkt_dev; int started = 0; - PG_DEBUG(printk("pktgen: entering pktgen_run. %p\n", t)); + pr_debug("pktgen: entering pktgen_run. %p\n", t); if_lock(t); list_for_each_entry(pkt_dev, &t->if_list, list) { @@ -2880,7 +2873,7 @@ static void pktgen_stop_all_threads_ifs(void) { struct pktgen_thread *t; - PG_DEBUG(printk("pktgen: entering pktgen_stop_all_threads_ifs.\n")); + pr_debug("pktgen: entering pktgen_stop_all_threads_ifs.\n"); mutex_lock(&pktgen_thread_lock); @@ -2948,7 +2941,7 @@ static void pktgen_run_all_threads(void) { struct pktgen_thread *t; - PG_DEBUG(printk("pktgen: entering pktgen_run_all_threads.\n")); + pr_debug("pktgen: entering pktgen_run_all_threads.\n"); mutex_lock(&pktgen_thread_lock); @@ -3006,7 +2999,7 @@ static int pktgen_stop_device(struct pktgen_dev *pkt_dev) if (!pkt_dev->running) { printk("pktgen: interface: %s is already stopped\n", - pkt_dev->ifname); + pkt_dev->odev->name); return -EINVAL; } @@ -3040,7 +3033,7 @@ static void pktgen_stop(struct pktgen_thread *t) { struct pktgen_dev *pkt_dev; - PG_DEBUG(printk("pktgen: entering pktgen_stop\n")); + pr_debug("pktgen: entering pktgen_stop\n"); if_lock(t); @@ -3064,7 +3057,7 @@ static void pktgen_rem_one_if(struct pktgen_thread *t) struct list_head *q, *n; struct pktgen_dev *cur; - PG_DEBUG(printk("pktgen: entering pktgen_rem_one_if\n")); + pr_debug("pktgen: entering pktgen_rem_one_if\n"); if_lock(t); @@ -3093,7 +3086,7 @@ static void pktgen_rem_all_ifs(struct pktgen_thread *t) /* Remove all devices, free mem */ - PG_DEBUG(printk("pktgen: entering pktgen_rem_all_ifs\n")); + pr_debug("pktgen: entering pktgen_rem_all_ifs\n"); if_lock(t); list_for_each_safe(q, n, &t->if_list) { @@ -3276,7 +3269,7 @@ static int pktgen_thread_worker(void *arg) t->pid = current->pid; - PG_DEBUG(printk("pktgen: starting pktgen/%d: pid=%d\n", cpu, current->pid)); + pr_debug("pktgen: starting pktgen/%d: pid=%d\n", cpu, current->pid); max_before_softirq = t->max_before_softirq; @@ -3339,13 +3332,13 @@ static int pktgen_thread_worker(void *arg) set_current_state(TASK_INTERRUPTIBLE); } - PG_DEBUG(printk("pktgen: %s stopping all device\n", t->tsk->comm)); + pr_debug("pktgen: %s stopping all device\n", t->tsk->comm); pktgen_stop(t); - PG_DEBUG(printk("pktgen: %s removing all device\n", t->tsk->comm)); + pr_debug("pktgen: %s removing all device\n", t->tsk->comm); pktgen_rem_all_ifs(t); - PG_DEBUG(printk("pktgen: %s removing thread.\n", t->tsk->comm)); + pr_debug("pktgen: %s removing thread.\n", t->tsk->comm); pktgen_rem_thread(t); return 0; @@ -3358,13 +3351,13 @@ static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, if_lock(t); list_for_each_entry(p, &t->if_list, list) - if (strncmp(p->ifname, ifname, IFNAMSIZ) == 0) { + if (strncmp(p->odev->name, ifname, IFNAMSIZ) == 0) { pkt_dev = p; break; } if_unlock(t); - PG_DEBUG(printk("pktgen: find_dev(%s) returning %p\n", ifname, pkt_dev)); + pr_debug("pktgen: find_dev(%s) returning %p\n", ifname, pkt_dev); return pkt_dev; } @@ -3399,7 +3392,7 @@ out: static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) { struct pktgen_dev *pkt_dev; - struct proc_dir_entry *pe; + int err; /* We don't allow a device to be on several threads */ @@ -3441,29 +3434,28 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->svlan_cfi = 0; pkt_dev->svlan_id = 0xffff; - strncpy(pkt_dev->ifname, ifname, IFNAMSIZ); + err = pktgen_setup_dev(pkt_dev, ifname); + if (err) + goto out1; - if (!pktgen_setup_dev(pkt_dev)) { - printk("pktgen: ERROR: pktgen_setup_dev failed.\n"); - if (pkt_dev->flows) - vfree(pkt_dev->flows); - kfree(pkt_dev); - return -ENODEV; - } - - pe = create_proc_entry(ifname, 0600, pg_proc_dir); - if (!pe) { + pkt_dev->entry = create_proc_entry(ifname, 0600, pg_proc_dir); + if (!pkt_dev->entry) { printk("pktgen: cannot create %s/%s procfs entry.\n", PG_PROC_DIR, ifname); - if (pkt_dev->flows) - vfree(pkt_dev->flows); - kfree(pkt_dev); - return -EINVAL; + err = -EINVAL; + goto out2; } - pe->proc_fops = &pktgen_if_fops; - pe->data = pkt_dev; + pkt_dev->entry->proc_fops = &pktgen_if_fops; + pkt_dev->entry->data = pkt_dev; return add_dev_to_thread(t, pkt_dev); +out2: + dev_put(pkt_dev->odev); +out1: + if (pkt_dev->flows) + vfree(pkt_dev->flows); + kfree(pkt_dev); + return err; } static int __init pktgen_create_thread(int cpu) @@ -3533,7 +3525,7 @@ static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *pkt_dev) { - PG_DEBUG(printk("pktgen: remove_device pkt_dev=%p\n", pkt_dev)); + pr_debug("pktgen: remove_device pkt_dev=%p\n", pkt_dev); if (pkt_dev->running) { printk("pktgen:WARNING: trying to remove a running interface, stopping it now.\n"); @@ -3551,9 +3543,8 @@ static int pktgen_remove_device(struct pktgen_thread *t, _rem_dev_from_if_list(t, pkt_dev); - /* Clean up proc file system */ - - remove_proc_entry(pkt_dev->ifname, pg_proc_dir); + if (pkt_dev->entry) + remove_proc_entry(pkt_dev->entry->name, pg_proc_dir); if (pkt_dev->flows) vfree(pkt_dev->flows); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 33ea8eac7fe0..cec111109155 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -50,11 +50,13 @@ #include <net/sock.h> #include <net/pkt_sched.h> #include <net/fib_rules.h> -#include <net/netlink.h> -#ifdef CONFIG_NET_WIRELESS_RTNETLINK -#include <linux/wireless.h> -#include <net/iw_handler.h> -#endif /* CONFIG_NET_WIRELESS_RTNETLINK */ +#include <net/rtnetlink.h> + +struct rtnl_link +{ + rtnl_doit_func doit; + rtnl_dumpit_func dumpit; +}; static DEFINE_MUTEX(rtnl_mutex); static struct sock *rtnl; @@ -95,7 +97,151 @@ int rtattr_parse(struct rtattr *tb[], int maxattr, struct rtattr *rta, int len) return 0; } -struct rtnetlink_link * rtnetlink_links[NPROTO]; +static struct rtnl_link *rtnl_msg_handlers[NPROTO]; + +static inline int rtm_msgindex(int msgtype) +{ + int msgindex = msgtype - RTM_BASE; + + /* + * msgindex < 0 implies someone tried to register a netlink + * control code. msgindex >= RTM_NR_MSGTYPES may indicate that + * the message type has not been added to linux/rtnetlink.h + */ + BUG_ON(msgindex < 0 || msgindex >= RTM_NR_MSGTYPES); + + return msgindex; +} + +static rtnl_doit_func rtnl_get_doit(int protocol, int msgindex) +{ + struct rtnl_link *tab; + + tab = rtnl_msg_handlers[protocol]; + if (tab == NULL || tab[msgindex].doit == NULL) + tab = rtnl_msg_handlers[PF_UNSPEC]; + + return tab ? tab[msgindex].doit : NULL; +} + +static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex) +{ + struct rtnl_link *tab; + + tab = rtnl_msg_handlers[protocol]; + if (tab == NULL || tab[msgindex].dumpit == NULL) + tab = rtnl_msg_handlers[PF_UNSPEC]; + + return tab ? tab[msgindex].dumpit : NULL; +} + +/** + * __rtnl_register - Register a rtnetlink message type + * @protocol: Protocol family or PF_UNSPEC + * @msgtype: rtnetlink message type + * @doit: Function pointer called for each request message + * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message + * + * Registers the specified function pointers (at least one of them has + * to be non-NULL) to be called whenever a request message for the + * specified protocol family and message type is received. + * + * The special protocol family PF_UNSPEC may be used to define fallback + * function pointers for the case when no entry for the specific protocol + * family exists. + * + * Returns 0 on success or a negative error code. + */ +int __rtnl_register(int protocol, int msgtype, + rtnl_doit_func doit, rtnl_dumpit_func dumpit) +{ + struct rtnl_link *tab; + int msgindex; + + BUG_ON(protocol < 0 || protocol >= NPROTO); + msgindex = rtm_msgindex(msgtype); + + tab = rtnl_msg_handlers[protocol]; + if (tab == NULL) { + tab = kcalloc(RTM_NR_MSGTYPES, sizeof(*tab), GFP_KERNEL); + if (tab == NULL) + return -ENOBUFS; + + rtnl_msg_handlers[protocol] = tab; + } + + if (doit) + tab[msgindex].doit = doit; + + if (dumpit) + tab[msgindex].dumpit = dumpit; + + return 0; +} + +EXPORT_SYMBOL_GPL(__rtnl_register); + +/** + * rtnl_register - Register a rtnetlink message type + * + * Identical to __rtnl_register() but panics on failure. This is useful + * as failure of this function is very unlikely, it can only happen due + * to lack of memory when allocating the chain to store all message + * handlers for a protocol. Meant for use in init functions where lack + * of memory implies no sense in continueing. + */ +void rtnl_register(int protocol, int msgtype, + rtnl_doit_func doit, rtnl_dumpit_func dumpit) +{ + if (__rtnl_register(protocol, msgtype, doit, dumpit) < 0) + panic("Unable to register rtnetlink message handler, " + "protocol = %d, message type = %d\n", + protocol, msgtype); +} + +EXPORT_SYMBOL_GPL(rtnl_register); + +/** + * rtnl_unregister - Unregister a rtnetlink message type + * @protocol: Protocol family or PF_UNSPEC + * @msgtype: rtnetlink message type + * + * Returns 0 on success or a negative error code. + */ +int rtnl_unregister(int protocol, int msgtype) +{ + int msgindex; + + BUG_ON(protocol < 0 || protocol >= NPROTO); + msgindex = rtm_msgindex(msgtype); + + if (rtnl_msg_handlers[protocol] == NULL) + return -ENOENT; + + rtnl_msg_handlers[protocol][msgindex].doit = NULL; + rtnl_msg_handlers[protocol][msgindex].dumpit = NULL; + + return 0; +} + +EXPORT_SYMBOL_GPL(rtnl_unregister); + +/** + * rtnl_unregister_all - Unregister all rtnetlink message type of a protocol + * @protocol : Protocol family or PF_UNSPEC + * + * Identical to calling rtnl_unregster() for all registered message types + * of a certain protocol family. + */ +void rtnl_unregister_all(int protocol) +{ + BUG_ON(protocol < 0 || protocol >= NPROTO); + + kfree(rtnl_msg_handlers[protocol]); + rtnl_msg_handlers[protocol] = NULL; +} + +EXPORT_SYMBOL_GPL(rtnl_unregister_all); static const int rtm_min[RTM_NR_FAMILIES] = { @@ -249,7 +395,7 @@ static void set_operstate(struct net_device *dev, unsigned char transition) operstate == IF_OPER_UNKNOWN) operstate = IF_OPER_DORMANT; break; - }; + } if (dev->operstate != operstate) { write_lock_bh(&dev_base_lock); @@ -393,7 +539,6 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) int s_idx = cb->args[0]; struct net_device *dev; - read_lock(&dev_base_lock); for (dev=dev_base, idx=0; dev; dev = dev->next, idx++) { if (idx < s_idx) continue; @@ -402,7 +547,6 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) cb->nlh->nlmsg_seq, 0, NLM_F_MULTI) <= 0) break; } - read_unlock(&dev_base_lock); cb->args[0] = idx; return skb->len; @@ -536,17 +680,6 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) modified = 1; } -#ifdef CONFIG_NET_WIRELESS_RTNETLINK - if (tb[IFLA_WIRELESS]) { - /* Call Wireless Extensions. - * Various stuff checked in there... */ - err = wireless_rtnetlink_set(dev, nla_data(tb[IFLA_WIRELESS]), - nla_len(tb[IFLA_WIRELESS])); - if (err < 0) - goto errout_dev; - } -#endif /* CONFIG_NET_WIRELESS_RTNETLINK */ - if (tb[IFLA_BROADCAST]) { nla_memcpy(dev->broadcast, tb[IFLA_BROADCAST], dev->addr_len); send_addr_notify = 1; @@ -610,22 +743,6 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) } else return -EINVAL; - -#ifdef CONFIG_NET_WIRELESS_RTNETLINK - if (tb[IFLA_WIRELESS]) { - /* Call Wireless Extensions. We need to know the size before - * we can alloc. Various stuff checked in there... */ - err = wireless_rtnetlink_get(dev, nla_data(tb[IFLA_WIRELESS]), - nla_len(tb[IFLA_WIRELESS]), - &iw_buf, &iw_buf_len); - if (err < 0) - goto errout; - - /* Payload is at an offset in buffer */ - iw = iw_buf + IW_EV_POINT_OFF; - } -#endif /* CONFIG_NET_WIRELESS_RTNETLINK */ - nskb = nlmsg_new(if_nlmsg_size(iw_buf_len), GFP_KERNEL); if (nskb == NULL) { err = -ENOBUFS; @@ -659,12 +776,12 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) int type = cb->nlh->nlmsg_type-RTM_BASE; if (idx < s_idx || idx == PF_PACKET) continue; - if (rtnetlink_links[idx] == NULL || - rtnetlink_links[idx][type].dumpit == NULL) + if (rtnl_msg_handlers[idx] == NULL || + rtnl_msg_handlers[idx][type].dumpit == NULL) continue; if (idx > s_idx) memset(&cb->args[0], 0, sizeof(cb->args)); - if (rtnetlink_links[idx][type].dumpit(skb, cb)) + if (rtnl_msg_handlers[idx][type].dumpit(skb, cb)) break; } cb->family = idx; @@ -700,30 +817,18 @@ static int rtattr_max; /* Process one rtnetlink message. */ -static __inline__ int -rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, int *errp) +static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { - struct rtnetlink_link *link; - struct rtnetlink_link *link_tab; + rtnl_doit_func doit; int sz_idx, kind; int min_len; int family; int type; int err; - /* Only requests are handled by kernel now */ - if (!(nlh->nlmsg_flags&NLM_F_REQUEST)) - return 0; - type = nlh->nlmsg_type; - - /* A control message: ignore them */ - if (type < RTM_BASE) - return 0; - - /* Unknown message: reply with EINVAL */ if (type > RTM_MAX) - goto err_inval; + return -EOPNOTSUPP; type -= RTM_BASE; @@ -732,45 +837,33 @@ rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, int *errp) return 0; family = ((struct rtgenmsg*)NLMSG_DATA(nlh))->rtgen_family; - if (family >= NPROTO) { - *errp = -EAFNOSUPPORT; - return -1; - } - - link_tab = rtnetlink_links[family]; - if (link_tab == NULL) - link_tab = rtnetlink_links[PF_UNSPEC]; - link = &link_tab[type]; + if (family >= NPROTO) + return -EAFNOSUPPORT; sz_idx = type>>2; kind = type&3; - if (kind != 2 && security_netlink_recv(skb, CAP_NET_ADMIN)) { - *errp = -EPERM; - return -1; - } + if (kind != 2 && security_netlink_recv(skb, CAP_NET_ADMIN)) + return -EPERM; if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { - if (link->dumpit == NULL) - link = &(rtnetlink_links[PF_UNSPEC][type]); - - if (link->dumpit == NULL) - goto err_inval; + rtnl_dumpit_func dumpit; - if ((*errp = netlink_dump_start(rtnl, skb, nlh, - link->dumpit, NULL)) != 0) { - return -1; - } + dumpit = rtnl_get_dumpit(family, type); + if (dumpit == NULL) + return -EOPNOTSUPP; - netlink_queue_skip(nlh, skb); - return -1; + __rtnl_unlock(); + err = netlink_dump_start(rtnl, skb, nlh, dumpit, NULL); + rtnl_lock(); + return err; } memset(rta_buf, 0, (rtattr_max * sizeof(struct rtattr *))); min_len = rtm_min[sz_idx]; if (nlh->nlmsg_len < min_len) - goto err_inval; + return -EINVAL; if (nlh->nlmsg_len > min_len) { int attrlen = nlh->nlmsg_len - NLMSG_ALIGN(min_len); @@ -780,25 +873,18 @@ rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, int *errp) unsigned flavor = attr->rta_type; if (flavor) { if (flavor > rta_max[sz_idx]) - goto err_inval; + return -EINVAL; rta_buf[flavor-1] = attr; } attr = RTA_NEXT(attr, attrlen); } } - if (link->doit == NULL) - link = &(rtnetlink_links[PF_UNSPEC][type]); - if (link->doit == NULL) - goto err_inval; - err = link->doit(skb, nlh, (void *)&rta_buf[0]); + doit = rtnl_get_doit(family, type); + if (doit == NULL) + return -EOPNOTSUPP; - *errp = err; - return err; - -err_inval: - *errp = -EINVAL; - return -1; + return doit(skb, nlh, (void *)&rta_buf[0]); } static void rtnetlink_rcv(struct sock *sk, int len) @@ -814,25 +900,6 @@ static void rtnetlink_rcv(struct sock *sk, int len) } while (qlen); } -static struct rtnetlink_link link_rtnetlink_table[RTM_NR_MSGTYPES] = -{ - [RTM_GETLINK - RTM_BASE] = { .doit = rtnl_getlink, - .dumpit = rtnl_dump_ifinfo }, - [RTM_SETLINK - RTM_BASE] = { .doit = rtnl_setlink }, - [RTM_GETADDR - RTM_BASE] = { .dumpit = rtnl_dump_all }, - [RTM_GETROUTE - RTM_BASE] = { .dumpit = rtnl_dump_all }, - [RTM_NEWNEIGH - RTM_BASE] = { .doit = neigh_add }, - [RTM_DELNEIGH - RTM_BASE] = { .doit = neigh_delete }, - [RTM_GETNEIGH - RTM_BASE] = { .dumpit = neigh_dump_info }, -#ifdef CONFIG_FIB_RULES - [RTM_NEWRULE - RTM_BASE] = { .doit = fib_nl_newrule }, - [RTM_DELRULE - RTM_BASE] = { .doit = fib_nl_delrule }, -#endif - [RTM_GETRULE - RTM_BASE] = { .dumpit = rtnl_dump_all }, - [RTM_GETNEIGHTBL - RTM_BASE] = { .dumpit = neightbl_dump_info }, - [RTM_SETNEIGHTBL - RTM_BASE] = { .doit = neightbl_set }, -}; - static int rtnetlink_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = ptr; @@ -874,19 +941,22 @@ void __init rtnetlink_init(void) panic("rtnetlink_init: cannot allocate rta_buf\n"); rtnl = netlink_kernel_create(NETLINK_ROUTE, RTNLGRP_MAX, rtnetlink_rcv, - THIS_MODULE); + &rtnl_mutex, THIS_MODULE); if (rtnl == NULL) panic("rtnetlink_init: cannot initialize rtnetlink\n"); netlink_set_nonroot(NETLINK_ROUTE, NL_NONROOT_RECV); register_netdevice_notifier(&rtnetlink_dev_notifier); - rtnetlink_links[PF_UNSPEC] = link_rtnetlink_table; - rtnetlink_links[PF_PACKET] = link_rtnetlink_table; + + rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink, rtnl_dump_ifinfo); + rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL); + + rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all); + rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all); } EXPORT_SYMBOL(__rta_fill); EXPORT_SYMBOL(rtattr_strlcpy); EXPORT_SYMBOL(rtattr_parse); -EXPORT_SYMBOL(rtnetlink_links); EXPORT_SYMBOL(rtnetlink_put_metrics); EXPORT_SYMBOL(rtnl_lock); EXPORT_SYMBOL(rtnl_trylock); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 336958fbbcb2..32f087b5233e 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -55,6 +55,7 @@ #include <linux/cache.h> #include <linux/rtnetlink.h> #include <linux/init.h> +#include <linux/scatterlist.h> #include <net/protocol.h> #include <net/dst.h> @@ -87,8 +88,9 @@ static struct kmem_cache *skbuff_fclone_cache __read_mostly; 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:%p end:%p dev:%s\n", - here, skb->len, sz, skb->head, skb->data, skb->tail, skb->end, + "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>"); BUG(); } @@ -105,8 +107,9 @@ void skb_over_panic(struct sk_buff *skb, int sz, void *here) 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:%p end:%p dev:%s\n", - here, skb->len, sz, skb->head, skb->data, skb->tail, skb->end, + "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>"); BUG(); } @@ -155,20 +158,22 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, if (!skb) goto out; - /* Get the DATA. Size must match skb_add_mtu(). */ size = SKB_DATA_ALIGN(size); data = kmalloc_node_track_caller(size + sizeof(struct skb_shared_info), gfp_mask, node); if (!data) goto nodata; - memset(skb, 0, offsetof(struct sk_buff, truesize)); + /* + * See comment in sk_buff definition, just before the 'tail' member + */ + memset(skb, 0, offsetof(struct sk_buff, tail)); skb->truesize = size + sizeof(struct sk_buff); atomic_set(&skb->users, 1); skb->head = data; skb->data = data; - skb->tail = data; - skb->end = data + size; + skb_reset_tail_pointer(skb); + skb->end = skb->tail + size; /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); atomic_set(&shinfo->dataref, 1); @@ -299,7 +304,7 @@ void kfree_skbmem(struct sk_buff *skb) if (atomic_dec_and_test(fclone_ref)) kmem_cache_free(skbuff_fclone_cache, other); break; - }; + } } /** @@ -321,15 +326,13 @@ void __kfree_skb(struct sk_buff *skb) WARN_ON(in_irq()); skb->destructor(skb); } -#ifdef CONFIG_NETFILTER - nf_conntrack_put(skb->nfct); #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) + nf_conntrack_put(skb->nfct); nf_conntrack_put_reasm(skb->nfct_reasm); #endif #ifdef CONFIG_BRIDGE_NETFILTER nf_bridge_put(skb->nf_bridge); #endif -#endif /* XXX: IS this still necessary? - JHS */ #ifdef CONFIG_NET_SCHED skb->tc_index = 0; @@ -396,9 +399,9 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) n->sk = NULL; C(tstamp); C(dev); - C(h); - C(nh); - C(mac); + C(transport_header); + C(network_header); + C(mac_header); C(dst); dst_clone(skb->dst); C(sp); @@ -422,19 +425,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) C(protocol); n->destructor = NULL; C(mark); -#ifdef CONFIG_NETFILTER - C(nfct); - nf_conntrack_get(skb->nfct); - C(nfctinfo); -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) - C(nfct_reasm); - nf_conntrack_get_reasm(skb->nfct_reasm); -#endif -#ifdef CONFIG_BRIDGE_NETFILTER - C(nf_bridge); - nf_bridge_get(skb->nf_bridge); -#endif -#endif /*CONFIG_NETFILTER*/ + __nf_copy(n, skb); #ifdef CONFIG_NET_SCHED C(tc_index); #ifdef CONFIG_NET_CLS_ACT @@ -460,11 +451,12 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) { +#ifndef NET_SKBUFF_DATA_USES_OFFSET /* * Shift between the two data areas in bytes */ unsigned long offset = new->data - old->data; - +#endif new->sk = NULL; new->dev = old->dev; new->priority = old->priority; @@ -473,9 +465,15 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) #ifdef CONFIG_INET new->sp = secpath_get(old->sp); #endif - new->h.raw = old->h.raw + offset; - new->nh.raw = old->nh.raw + offset; - new->mac.raw = old->mac.raw + offset; + new->transport_header = old->transport_header; + new->network_header = old->network_header; + new->mac_header = old->mac_header; +#ifndef NET_SKBUFF_DATA_USES_OFFSET + /* {transport,network,mac}_header are relative to skb->head */ + new->transport_header += offset; + new->network_header += offset; + new->mac_header += offset; +#endif memcpy(new->cb, old->cb, sizeof(old->cb)); new->local_df = old->local_df; new->fclone = SKB_FCLONE_UNAVAILABLE; @@ -483,22 +481,10 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->tstamp = old->tstamp; new->destructor = NULL; new->mark = old->mark; -#ifdef CONFIG_NETFILTER - new->nfct = old->nfct; - nf_conntrack_get(old->nfct); - new->nfctinfo = old->nfctinfo; -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) - new->nfct_reasm = old->nfct_reasm; - nf_conntrack_get_reasm(old->nfct_reasm); -#endif + __nf_copy(new, old); #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) new->ipvs_property = old->ipvs_property; #endif -#ifdef CONFIG_BRIDGE_NETFILTER - new->nf_bridge = old->nf_bridge; - nf_bridge_get(old->nf_bridge); -#endif -#endif #ifdef CONFIG_NET_SCHED #ifdef CONFIG_NET_CLS_ACT new->tc_verd = old->tc_verd; @@ -535,8 +521,12 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) /* * Allocate the copy buffer */ - struct sk_buff *n = alloc_skb(skb->end - skb->head + skb->data_len, - gfp_mask); + struct sk_buff *n; +#ifdef NET_SKBUFF_DATA_USES_OFFSET + n = alloc_skb(skb->end + skb->data_len, gfp_mask); +#else + n = alloc_skb(skb->end - skb->head + skb->data_len, gfp_mask); +#endif if (!n) return NULL; @@ -573,8 +563,12 @@ struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) /* * Allocate the copy buffer */ - struct sk_buff *n = alloc_skb(skb->end - skb->head, gfp_mask); - + struct sk_buff *n; +#ifdef NET_SKBUFF_DATA_USES_OFFSET + n = alloc_skb(skb->end, gfp_mask); +#else + n = alloc_skb(skb->end - skb->head, gfp_mask); +#endif if (!n) goto out; @@ -583,7 +577,7 @@ struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) /* Set the tail pointer and length */ skb_put(n, skb_headlen(skb)); /* Copy the bytes */ - memcpy(n->data, skb->data, n->len); + skb_copy_from_linear_data(skb, n->data, n->len); n->csum = skb->csum; n->ip_summed = skb->ip_summed; @@ -632,7 +626,11 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, { int i; u8 *data; +#ifdef NET_SKBUFF_DATA_USES_OFFSET + int size = nhead + skb->end + ntail; +#else int size = nhead + (skb->end - skb->head) + ntail; +#endif long off; if (skb_shared(skb)) @@ -646,8 +644,14 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, /* Copy only real data... and, alas, header. This should be * optimized for the cases when header is void. */ - memcpy(data + nhead, skb->head, skb->tail - skb->head); - memcpy(data + size, skb->end, sizeof(struct skb_shared_info)); + memcpy(data + nhead, skb->head, +#ifdef NET_SKBUFF_DATA_USES_OFFSET + skb->tail); +#else + skb->tail - skb->head); +#endif + memcpy(data + size, skb_end_pointer(skb), + sizeof(struct skb_shared_info)); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) get_page(skb_shinfo(skb)->frags[i].page); @@ -660,12 +664,18 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, off = (data + nhead) - skb->head; skb->head = data; - skb->end = data + size; skb->data += off; - skb->tail += off; - skb->mac.raw += off; - skb->h.raw += off; - skb->nh.raw += off; +#ifdef NET_SKBUFF_DATA_USES_OFFSET + skb->end = size; + off = nhead; +#else + skb->end = skb->head + size; +#endif + /* {transport,network,mac}_header and tail are relative to skb->head */ + skb->tail += off; + skb->transport_header += off; + skb->network_header += off; + skb->mac_header += off; skb->cloned = 0; skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); @@ -726,7 +736,9 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, */ struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom, gfp_mask); + int oldheadroom = skb_headroom(skb); int head_copy_len, head_copy_off; + int off = 0; if (!n) return NULL; @@ -736,7 +748,7 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, /* Set the tail pointer and length */ skb_put(n, skb->len); - head_copy_len = skb_headroom(skb); + head_copy_len = oldheadroom; head_copy_off = 0; if (newheadroom <= head_copy_len) head_copy_len = newheadroom; @@ -750,6 +762,13 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, copy_skb_header(n, skb); +#ifdef NET_SKBUFF_DATA_USES_OFFSET + off = newheadroom - oldheadroom; +#endif + n->transport_header += off; + n->network_header += off; + n->mac_header += off; + return n; } @@ -877,7 +896,7 @@ done: } else { skb->len = len; skb->data_len = 0; - skb->tail = skb->data + len; + skb_set_tail_pointer(skb, len); } return 0; @@ -922,7 +941,7 @@ unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta) return NULL; } - if (skb_copy_bits(skb, skb_headlen(skb), skb->tail, delta)) + if (skb_copy_bits(skb, skb_headlen(skb), skb_tail_pointer(skb), delta)) BUG(); /* Optimization: no fragments, no reasons to preestimate @@ -1018,7 +1037,7 @@ pull_pages: skb->tail += delta; skb->data_len -= delta; - return skb->tail; + return skb_tail_pointer(skb); } /* Copy some data bits from skb to kernel buffer. */ @@ -1026,16 +1045,16 @@ pull_pages: int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) { int i, copy; - int start = skb_headlen(skb); + int end = skb_headlen(skb); if (offset > (int)skb->len - len) goto fault; /* Copy header. */ - if ((copy = start - offset) > 0) { + if ((copy = end - offset) > 0) { if (copy > len) copy = len; - memcpy(to, skb->data + offset, copy); + skb_copy_from_linear_data_offset(skb, offset, to, copy); if ((len -= copy) == 0) return 0; offset += copy; @@ -1043,11 +1062,9 @@ 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; + BUG_TRAP(len >= 0); - BUG_TRAP(start <= offset + len); - - end = start + skb_shinfo(skb)->frags[i].size; + end = offset + skb_shinfo(skb)->frags[i].size; if ((copy = end - offset) > 0) { u8 *vaddr; @@ -1056,8 +1073,8 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]); memcpy(to, - vaddr + skb_shinfo(skb)->frags[i].page_offset+ - offset - start, copy); + vaddr + skb_shinfo(skb)->frags[i].page_offset, + copy); kunmap_skb_frag(vaddr); if ((len -= copy) == 0) @@ -1065,30 +1082,25 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) offset += copy; to += copy; } - start = end; } if (skb_shinfo(skb)->frag_list) { struct sk_buff *list = skb_shinfo(skb)->frag_list; for (; list; list = list->next) { - int end; - - BUG_TRAP(start <= offset + len); + BUG_TRAP(len >= 0); - end = start + list->len; + end = offset + list->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; - if (skb_copy_bits(list, offset - start, - to, copy)) + if (skb_copy_bits(list, 0, to, copy)) goto fault; if ((len -= copy) == 0) return 0; offset += copy; to += copy; } - start = end; } } if (!len) @@ -1110,18 +1122,18 @@ fault: * traversing fragment lists and such. */ -int skb_store_bits(const struct sk_buff *skb, int offset, void *from, int len) +int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) { int i, copy; - int start = skb_headlen(skb); + int end = skb_headlen(skb); if (offset > (int)skb->len - len) goto fault; - if ((copy = start - offset) > 0) { + if ((copy = end - offset) > 0) { if (copy > len) copy = len; - memcpy(skb->data + offset, from, copy); + skb_copy_to_linear_data_offset(skb, offset, from, copy); if ((len -= copy) == 0) return 0; offset += copy; @@ -1130,11 +1142,9 @@ int skb_store_bits(const struct sk_buff *skb, int offset, void *from, int len) for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - int end; + BUG_TRAP(len >= 0); - BUG_TRAP(start <= offset + len); - - end = start + frag->size; + end = offset + frag->size; if ((copy = end - offset) > 0) { u8 *vaddr; @@ -1142,8 +1152,7 @@ int skb_store_bits(const struct sk_buff *skb, int offset, void *from, int len) copy = len; vaddr = kmap_skb_frag(frag); - memcpy(vaddr + frag->page_offset + offset - start, - from, copy); + memcpy(vaddr + frag->page_offset, from, copy); kunmap_skb_frag(vaddr); if ((len -= copy) == 0) @@ -1151,30 +1160,25 @@ int skb_store_bits(const struct sk_buff *skb, int offset, void *from, int len) offset += copy; from += copy; } - start = end; } if (skb_shinfo(skb)->frag_list) { struct sk_buff *list = skb_shinfo(skb)->frag_list; for (; list; list = list->next) { - int end; - - BUG_TRAP(start <= offset + len); + BUG_TRAP(len >= 0); - end = start + list->len; + end = offset + list->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; - if (skb_store_bits(list, offset - start, - from, copy)) + if (skb_store_bits(list, 0, from, copy)) goto fault; if ((len -= copy) == 0) return 0; offset += copy; from += copy; } - start = end; } } if (!len) @@ -1191,8 +1195,8 @@ EXPORT_SYMBOL(skb_store_bits); __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum) { - int start = skb_headlen(skb); - int i, copy = start - offset; + int end = skb_headlen(skb); + int i, copy = end - offset; int pos = 0; /* Checksum header. */ @@ -1207,11 +1211,9 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - int end; + BUG_TRAP(len >= 0); - BUG_TRAP(start <= offset + len); - - end = start + skb_shinfo(skb)->frags[i].size; + end = offset + skb_shinfo(skb)->frags[i].size; if ((copy = end - offset) > 0) { __wsum csum2; u8 *vaddr; @@ -1220,8 +1222,8 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, if (copy > len) copy = len; vaddr = kmap_skb_frag(frag); - csum2 = csum_partial(vaddr + frag->page_offset + - offset - start, copy, 0); + csum2 = csum_partial(vaddr + frag->page_offset, + copy, 0); kunmap_skb_frag(vaddr); csum = csum_block_add(csum, csum2, pos); if (!(len -= copy)) @@ -1229,31 +1231,26 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, offset += copy; pos += copy; } - start = end; } if (skb_shinfo(skb)->frag_list) { struct sk_buff *list = skb_shinfo(skb)->frag_list; for (; list; list = list->next) { - int end; - - BUG_TRAP(start <= offset + len); + BUG_TRAP(len >= 0); - end = start + list->len; + end = offset + list->len; if ((copy = end - offset) > 0) { __wsum csum2; if (copy > len) copy = len; - csum2 = skb_checksum(list, offset - start, - copy, 0); + csum2 = skb_checksum(list, 0, copy, 0); csum = csum_block_add(csum, csum2, pos); if ((len -= copy) == 0) return csum; offset += copy; pos += copy; } - start = end; } } BUG_ON(len); @@ -1266,8 +1263,8 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len, __wsum csum) { - int start = skb_headlen(skb); - int i, copy = start - offset; + int end = skb_headlen(skb); + int i, copy = end - offset; int pos = 0; /* Copy header. */ @@ -1284,11 +1281,9 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - int end; + BUG_TRAP(len >= 0); - BUG_TRAP(start <= offset + len); - - end = start + skb_shinfo(skb)->frags[i].size; + end = offset + skb_shinfo(skb)->frags[i].size; if ((copy = end - offset) > 0) { __wsum csum2; u8 *vaddr; @@ -1298,9 +1293,8 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, copy = len; vaddr = kmap_skb_frag(frag); csum2 = csum_partial_copy_nocheck(vaddr + - frag->page_offset + - offset - start, to, - copy, 0); + frag->page_offset, + to, copy, 0); kunmap_skb_frag(vaddr); csum = csum_block_add(csum, csum2, pos); if (!(len -= copy)) @@ -1309,7 +1303,6 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, to += copy; pos += copy; } - start = end; } if (skb_shinfo(skb)->frag_list) { @@ -1317,16 +1310,13 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, for (; list; list = list->next) { __wsum csum2; - int end; - - BUG_TRAP(start <= offset + len); + BUG_TRAP(len >= 0); - end = start + list->len; + end = offset + list->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; - csum2 = skb_copy_and_csum_bits(list, - offset - start, + csum2 = skb_copy_and_csum_bits(list, 0, to, copy, 0); csum = csum_block_add(csum, csum2, pos); if ((len -= copy) == 0) @@ -1335,7 +1325,6 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, to += copy; pos += copy; } - start = end; } } BUG_ON(len); @@ -1348,13 +1337,13 @@ void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) long csstart; if (skb->ip_summed == CHECKSUM_PARTIAL) - csstart = skb->h.raw - skb->data; + csstart = skb->csum_start - skb_headroom(skb); else csstart = skb_headlen(skb); BUG_ON(csstart > skb_headlen(skb)); - memcpy(to, skb->data, csstart); + skb_copy_from_linear_data(skb, to, csstart); csum = 0; if (csstart != skb->len) @@ -1522,27 +1511,14 @@ void skb_insert(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head spin_unlock_irqrestore(&list->lock, flags); } -#if 0 -/* - * Tune the memory allocator for a new MTU size. - */ -void skb_add_mtu(int mtu) -{ - /* Must match allocation in alloc_skb */ - mtu = SKB_DATA_ALIGN(mtu) + sizeof(struct skb_shared_info); - - kmem_add_cache_size(mtu); -} -#endif - static inline void skb_split_inside_header(struct sk_buff *skb, struct sk_buff* skb1, const u32 len, const int pos) { int i; - memcpy(skb_put(skb1, pos - len), skb->data + len, pos - len); - + skb_copy_from_linear_data_offset(skb, len, skb_put(skb1, pos - len), + pos - len); /* And move data appendix as is. */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_shinfo(skb1)->frags[i] = skb_shinfo(skb)->frags[i]; @@ -1553,7 +1529,7 @@ static inline void skb_split_inside_header(struct sk_buff *skb, skb1->len += skb1->data_len; skb->data_len = 0; skb->len = len; - skb->tail = skb->data + len; + skb_set_tail_pointer(skb, len); } static inline void skb_split_no_header(struct sk_buff *skb, @@ -1878,7 +1854,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; unsigned int mss = skb_shinfo(skb)->gso_size; - unsigned int doffset = skb->data - skb->mac.raw; + unsigned int doffset = skb->data - skb_mac_header(skb); unsigned int offset = doffset; unsigned int headroom; unsigned int len; @@ -1928,11 +1904,12 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) nskb->mac_len = skb->mac_len; skb_reserve(nskb, headroom); - nskb->mac.raw = nskb->data; - nskb->nh.raw = nskb->data + skb->mac_len; - nskb->h.raw = nskb->nh.raw + (skb->h.raw - skb->nh.raw); - memcpy(skb_put(nskb, doffset), skb->data, doffset); - + skb_reset_mac_header(nskb); + skb_set_network_header(nskb, skb->mac_len); + nskb->transport_header = (nskb->network_header + + skb_network_header_len(skb)); + skb_copy_from_linear_data(skb, skb_put(nskb, doffset), + doffset); if (!sg) { nskb->csum = skb_copy_and_csum_bits(skb, offset, skb_put(nskb, len), @@ -1945,7 +1922,8 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) nskb->ip_summed = CHECKSUM_PARTIAL; nskb->csum = skb->csum; - memcpy(skb_put(nskb, hsize), skb->data + offset, hsize); + skb_copy_from_linear_data_offset(skb, offset, + skb_put(nskb, hsize), hsize); while (pos < offset + len) { BUG_ON(i >= nfrags); @@ -2005,6 +1983,184 @@ void __init skb_init(void) NULL, NULL); } +/** + * skb_to_sgvec - Fill a scatter-gather list from a socket buffer + * @skb: Socket buffer containing the buffers to be mapped + * @sg: The scatter-gather list to map into + * @offset: The offset into the buffer's contents to start mapping + * @len: Length of buffer space to be mapped + * + * Fill the specified scatter-gather list with mappings/pointers into a + * region of the buffer space attached to a socket buffer. + */ +int +skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) +{ + int end = skb_headlen(skb); + int i, copy = end - offset; + int elt = 0; + + if (copy > 0) { + if (copy > len) + copy = len; + sg[elt].page = virt_to_page(skb->data + offset); + sg[elt].offset = (unsigned long)(skb->data + offset) % PAGE_SIZE; + sg[elt].length = copy; + elt++; + if ((len -= copy) == 0) + return elt; + offset += copy; + } + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + BUG_TRAP(len >= 0); + + end = offset + skb_shinfo(skb)->frags[i].size; + if ((copy = end - offset) > 0) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + if (copy > len) + copy = len; + sg[elt].page = frag->page; + sg[elt].offset = frag->page_offset; + sg[elt].length = copy; + elt++; + if (!(len -= copy)) + return elt; + offset += copy; + } + } + + if (skb_shinfo(skb)->frag_list) { + struct sk_buff *list = skb_shinfo(skb)->frag_list; + + for (; list; list = list->next) { + BUG_TRAP(len >= 0); + + end = offset + list->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + elt += skb_to_sgvec(list, sg+elt, 0, copy); + if ((len -= copy) == 0) + return elt; + offset += copy; + } + } + } + BUG_ON(len); + return elt; +} + +/** + * skb_cow_data - Check that a socket buffer's data buffers are writable + * @skb: The socket buffer to check. + * @tailbits: Amount of trailing space to be added + * @trailer: Returned pointer to the skb where the @tailbits space begins + * + * Make sure that the data buffers attached to a socket buffer are + * writable. If they are not, private copies are made of the data buffers + * and the socket buffer is set to use these instead. + * + * If @tailbits is given, make sure that there is space to write @tailbits + * bytes of data beyond current end of socket buffer. @trailer will be + * set to point to the skb in which this space begins. + * + * The number of scatterlist elements required to completely map the + * COW'd and extended socket buffer will be returned. + */ +int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) +{ + int copyflag; + int elt; + struct sk_buff *skb1, **skb_p; + + /* If skb is cloned or its head is paged, reallocate + * head pulling out all the pages (pages are considered not writable + * at the moment even if they are anonymous). + */ + if ((skb_cloned(skb) || skb_shinfo(skb)->nr_frags) && + __pskb_pull_tail(skb, skb_pagelen(skb)-skb_headlen(skb)) == NULL) + return -ENOMEM; + + /* Easy case. Most of packets will go this way. */ + if (!skb_shinfo(skb)->frag_list) { + /* A little of trouble, not enough of space for trailer. + * This should not happen, when stack is tuned to generate + * good frames. OK, on miss we reallocate and reserve even more + * space, 128 bytes is fair. */ + + if (skb_tailroom(skb) < tailbits && + pskb_expand_head(skb, 0, tailbits-skb_tailroom(skb)+128, GFP_ATOMIC)) + return -ENOMEM; + + /* Voila! */ + *trailer = skb; + return 1; + } + + /* Misery. We are in troubles, going to mincer fragments... */ + + elt = 1; + skb_p = &skb_shinfo(skb)->frag_list; + copyflag = 0; + + while ((skb1 = *skb_p) != NULL) { + int ntail = 0; + + /* The fragment is partially pulled by someone, + * this can happen on input. Copy it and everything + * after it. */ + + if (skb_shared(skb1)) + copyflag = 1; + + /* If the skb is the last, worry about trailer. */ + + if (skb1->next == NULL && tailbits) { + if (skb_shinfo(skb1)->nr_frags || + skb_shinfo(skb1)->frag_list || + skb_tailroom(skb1) < tailbits) + ntail = tailbits + 128; + } + + if (copyflag || + skb_cloned(skb1) || + ntail || + skb_shinfo(skb1)->nr_frags || + skb_shinfo(skb1)->frag_list) { + struct sk_buff *skb2; + + /* Fuck, we are miserable poor guys... */ + if (ntail == 0) + skb2 = skb_copy(skb1, GFP_ATOMIC); + else + skb2 = skb_copy_expand(skb1, + skb_headroom(skb1), + ntail, + GFP_ATOMIC); + if (unlikely(skb2 == NULL)) + return -ENOMEM; + + if (skb1->sk) + skb_set_owner_w(skb2, skb1->sk); + + /* Looking around. Are we still alive? + * OK, link new skb, drop old one */ + + skb2->next = skb1->next; + *skb_p = skb2; + kfree_skb(skb1); + skb1 = skb2; + } + elt++; + *trailer = skb1; + skb_p = &skb1->next; + } + + return elt; +} + EXPORT_SYMBOL(___pskb_trim); EXPORT_SYMBOL(__kfree_skb); EXPORT_SYMBOL(kfree_skb); @@ -2039,3 +2195,6 @@ EXPORT_SYMBOL(skb_seq_read); EXPORT_SYMBOL(skb_abort_seq_read); EXPORT_SYMBOL(skb_find_text); EXPORT_SYMBOL(skb_append_datato_frags); + +EXPORT_SYMBOL_GPL(skb_to_sgvec); +EXPORT_SYMBOL_GPL(skb_cow_data); diff --git a/net/core/sock.c b/net/core/sock.c index 27c4f62382bd..22183c2ef284 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -154,7 +154,8 @@ static const char *af_family_key_strings[AF_MAX+1] = { "sk_lock-21" , "sk_lock-AF_SNA" , "sk_lock-AF_IRDA" , "sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE" , "sk_lock-AF_LLC" , "sk_lock-27" , "sk_lock-28" , "sk_lock-29" , - "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-AF_MAX" + "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" , + "sk_lock-AF_RXRPC" , "sk_lock-AF_MAX" }; static const char *af_family_slock_key_strings[AF_MAX+1] = { "slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" , @@ -167,7 +168,8 @@ static const char *af_family_slock_key_strings[AF_MAX+1] = { "slock-21" , "slock-AF_SNA" , "slock-AF_IRDA" , "slock-AF_PPPOX" , "slock-AF_WANPIPE" , "slock-AF_LLC" , "slock-27" , "slock-28" , "slock-29" , - "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_MAX" + "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" , + "slock-AF_RXRPC" , "slock-AF_MAX" }; #endif @@ -361,8 +363,8 @@ int sock_setsockopt(struct socket *sock, int level, int optname, } #endif - if(optlen<sizeof(int)) - return(-EINVAL); + if (optlen < sizeof(int)) + return -EINVAL; if (get_user(val, (int __user *)optval)) return -EFAULT; @@ -371,265 +373,270 @@ int sock_setsockopt(struct socket *sock, int level, int optname, lock_sock(sk); - switch(optname) - { - case SO_DEBUG: - if(val && !capable(CAP_NET_ADMIN)) - { - ret = -EACCES; - } - else if (valbool) - sock_set_flag(sk, SOCK_DBG); - else - sock_reset_flag(sk, SOCK_DBG); - break; - case SO_REUSEADDR: - sk->sk_reuse = valbool; - break; - case SO_TYPE: - case SO_ERROR: - ret = -ENOPROTOOPT; - break; - case SO_DONTROUTE: - if (valbool) - sock_set_flag(sk, SOCK_LOCALROUTE); - else - sock_reset_flag(sk, SOCK_LOCALROUTE); - break; - case SO_BROADCAST: - sock_valbool_flag(sk, SOCK_BROADCAST, valbool); - 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; + switch(optname) { + case SO_DEBUG: + if (val && !capable(CAP_NET_ADMIN)) { + ret = -EACCES; + } + else if (valbool) + sock_set_flag(sk, SOCK_DBG); + else + sock_reset_flag(sk, SOCK_DBG); + break; + case SO_REUSEADDR: + sk->sk_reuse = valbool; + break; + case SO_TYPE: + case SO_ERROR: + ret = -ENOPROTOOPT; + break; + case SO_DONTROUTE: + if (valbool) + sock_set_flag(sk, SOCK_LOCALROUTE); + else + sock_reset_flag(sk, SOCK_LOCALROUTE); + break; + case SO_BROADCAST: + sock_valbool_flag(sk, SOCK_BROADCAST, valbool); + 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; 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; + 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_write_space(sk); - break; + /* + * Wake up sending tasks if we + * upped the value. + */ + sk->sk_write_space(sk); + break; - case SO_SNDBUFFORCE: - if (!capable(CAP_NET_ADMIN)) { - ret = -EPERM; - break; - } - goto set_sndbuf; + case SO_SNDBUFFORCE: + if (!capable(CAP_NET_ADMIN)) { + ret = -EPERM; + break; + } + goto 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 */ + 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; + if (val > sysctl_rmem_max) + val = sysctl_rmem_max; set_rcvbuf: - sk->sk_userlocks |= SOCK_RCVBUF_LOCK; - /* - * We double it on the way in to account for - * "struct sk_buff" etc. overhead. Applications - * assume that the SO_RCVBUF setting they make will - * allow that much actual data to be received on that - * socket. - * - * Applications are unaware that "struct sk_buff" and - * other overheads allocate from the receive buffer - * during socket buffer allocation. - * - * And after considering the possible alternatives, - * 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_userlocks |= SOCK_RCVBUF_LOCK; + /* + * We double it on the way in to account for + * "struct sk_buff" etc. overhead. Applications + * assume that the SO_RCVBUF setting they make will + * allow that much actual data to be received on that + * socket. + * + * Applications are unaware that "struct sk_buff" and + * other overheads allocate from the receive buffer + * during socket buffer allocation. + * + * And after considering the possible alternatives, + * 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; + break; + + case SO_RCVBUFFORCE: + if (!capable(CAP_NET_ADMIN)) { + ret = -EPERM; break; + } + goto set_rcvbuf; - case SO_RCVBUFFORCE: - if (!capable(CAP_NET_ADMIN)) { - ret = -EPERM; - break; - } - goto set_rcvbuf; - - case SO_KEEPALIVE: + case SO_KEEPALIVE: #ifdef CONFIG_INET - if (sk->sk_protocol == IPPROTO_TCP) - tcp_set_keepalive(sk, valbool); + if (sk->sk_protocol == IPPROTO_TCP) + tcp_set_keepalive(sk, valbool); #endif - sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); - break; - - case SO_OOBINLINE: - sock_valbool_flag(sk, SOCK_URGINLINE, valbool); + sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); + break; + + case SO_OOBINLINE: + sock_valbool_flag(sk, SOCK_URGINLINE, valbool); + break; + + case SO_NO_CHECK: + sk->sk_no_check = valbool; + break; + + case SO_PRIORITY: + if ((val >= 0 && val <= 6) || capable(CAP_NET_ADMIN)) + sk->sk_priority = val; + else + ret = -EPERM; + break; + + case SO_LINGER: + if (optlen < sizeof(ling)) { + ret = -EINVAL; /* 1003.1g */ break; - - case SO_NO_CHECK: - sk->sk_no_check = valbool; - break; - - case SO_PRIORITY: - if ((val >= 0 && val <= 6) || capable(CAP_NET_ADMIN)) - sk->sk_priority = val; - else - ret = -EPERM; + } + if (copy_from_user(&ling,optval,sizeof(ling))) { + ret = -EFAULT; break; - - case SO_LINGER: - if(optlen<sizeof(ling)) { - ret = -EINVAL; /* 1003.1g */ - break; - } - if (copy_from_user(&ling,optval,sizeof(ling))) { - ret = -EFAULT; - break; - } - if (!ling.l_onoff) - sock_reset_flag(sk, SOCK_LINGER); - else { + } + if (!ling.l_onoff) + sock_reset_flag(sk, SOCK_LINGER); + else { #if (BITS_PER_LONG == 32) - if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ) - sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT; - else + if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ) + sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT; + else #endif - sk->sk_lingertime = (unsigned int)ling.l_linger * HZ; - sock_set_flag(sk, SOCK_LINGER); - } - break; - - case SO_BSDCOMPAT: - sock_warn_obsolete_bsdism("setsockopt"); - break; - - case SO_PASSCRED: - if (valbool) - set_bit(SOCK_PASSCRED, &sock->flags); + sk->sk_lingertime = (unsigned int)ling.l_linger * HZ; + sock_set_flag(sk, SOCK_LINGER); + } + break; + + case SO_BSDCOMPAT: + sock_warn_obsolete_bsdism("setsockopt"); + break; + + case SO_PASSCRED: + if (valbool) + set_bit(SOCK_PASSCRED, &sock->flags); + else + clear_bit(SOCK_PASSCRED, &sock->flags); + break; + + case SO_TIMESTAMP: + case SO_TIMESTAMPNS: + if (valbool) { + if (optname == SO_TIMESTAMP) + sock_reset_flag(sk, SOCK_RCVTSTAMPNS); else - clear_bit(SOCK_PASSCRED, &sock->flags); - break; + sock_set_flag(sk, SOCK_RCVTSTAMPNS); + sock_set_flag(sk, SOCK_RCVTSTAMP); + sock_enable_timestamp(sk); + } else { + sock_reset_flag(sk, SOCK_RCVTSTAMP); + sock_reset_flag(sk, SOCK_RCVTSTAMPNS); + } + break; - case SO_TIMESTAMP: - if (valbool) { - sock_set_flag(sk, SOCK_RCVTSTAMP); - sock_enable_timestamp(sk); - } else - sock_reset_flag(sk, SOCK_RCVTSTAMP); - break; + case SO_RCVLOWAT: + if (val < 0) + val = INT_MAX; + sk->sk_rcvlowat = val ? : 1; + break; - case SO_RCVLOWAT: - if (val < 0) - val = INT_MAX; - sk->sk_rcvlowat = val ? : 1; - break; + case SO_RCVTIMEO: + ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen); + break; - case SO_RCVTIMEO: - ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen); - break; + case SO_SNDTIMEO: + ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen); + break; - case SO_SNDTIMEO: - ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen); +#ifdef CONFIG_NETDEVICES + case SO_BINDTODEVICE: + { + char devname[IFNAMSIZ]; + + /* Sorry... */ + if (!capable(CAP_NET_RAW)) { + ret = -EPERM; break; + } -#ifdef CONFIG_NETDEVICES - case SO_BINDTODEVICE: - { - char devname[IFNAMSIZ]; + /* Bind this socket to a particular device like "eth0", + * as specified in the passed interface name. If the + * name is "" or the option length is zero the socket + * is not bound. + */ - /* Sorry... */ - if (!capable(CAP_NET_RAW)) { - ret = -EPERM; + if (!valbool) { + sk->sk_bound_dev_if = 0; + } else { + if (optlen > IFNAMSIZ - 1) + optlen = IFNAMSIZ - 1; + memset(devname, 0, sizeof(devname)); + if (copy_from_user(devname, optval, optlen)) { + ret = -EFAULT; break; } - /* Bind this socket to a particular device like "eth0", - * as specified in the passed interface name. If the - * name is "" or the option length is zero the socket - * is not bound. - */ + /* Remove any cached route for this socket. */ + sk_dst_reset(sk); - if (!valbool) { + if (devname[0] == '\0') { sk->sk_bound_dev_if = 0; } else { - if (optlen > IFNAMSIZ - 1) - optlen = IFNAMSIZ - 1; - memset(devname, 0, sizeof(devname)); - if (copy_from_user(devname, optval, optlen)) { - ret = -EFAULT; + struct net_device *dev = dev_get_by_name(devname); + if (!dev) { + ret = -ENODEV; break; } - - /* Remove any cached route for this socket. */ - sk_dst_reset(sk); - - if (devname[0] == '\0') { - sk->sk_bound_dev_if = 0; - } else { - struct net_device *dev = dev_get_by_name(devname); - if (!dev) { - ret = -ENODEV; - break; - } - sk->sk_bound_dev_if = dev->ifindex; - dev_put(dev); - } + sk->sk_bound_dev_if = dev->ifindex; + dev_put(dev); } - break; } + break; + } #endif - case SO_ATTACH_FILTER: - ret = -EINVAL; - if (optlen == sizeof(struct sock_fprog)) { - struct sock_fprog fprog; + case SO_ATTACH_FILTER: + ret = -EINVAL; + if (optlen == sizeof(struct sock_fprog)) { + struct sock_fprog fprog; - ret = -EFAULT; - if (copy_from_user(&fprog, optval, sizeof(fprog))) - break; - - ret = sk_attach_filter(&fprog, sk); - } - break; - - case SO_DETACH_FILTER: - rcu_read_lock_bh(); - filter = rcu_dereference(sk->sk_filter); - if (filter) { - rcu_assign_pointer(sk->sk_filter, NULL); - sk_filter_release(sk, filter); - rcu_read_unlock_bh(); + ret = -EFAULT; + if (copy_from_user(&fprog, optval, sizeof(fprog))) break; - } + + ret = sk_attach_filter(&fprog, sk); + } + break; + + case SO_DETACH_FILTER: + rcu_read_lock_bh(); + filter = rcu_dereference(sk->sk_filter); + if (filter) { + rcu_assign_pointer(sk->sk_filter, NULL); + sk_filter_release(sk, filter); rcu_read_unlock_bh(); - ret = -ENONET; break; + } + rcu_read_unlock_bh(); + ret = -ENONET; + break; - case SO_PASSSEC: - if (valbool) - set_bit(SOCK_PASSSEC, &sock->flags); - else - clear_bit(SOCK_PASSSEC, &sock->flags); - break; + case SO_PASSSEC: + if (valbool) + set_bit(SOCK_PASSSEC, &sock->flags); + else + clear_bit(SOCK_PASSSEC, &sock->flags); + break; /* We implement the SO_SNDLOWAT etc to not be settable (1003.1g 5.3) */ - default: - ret = -ENOPROTOOPT; - break; + default: + ret = -ENOPROTOOPT; + break; } release_sock(sk); return ret; @@ -641,8 +648,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, { struct sock *sk = sock->sk; - union - { + union { int val; struct linger ling; struct timeval tm; @@ -651,148 +657,153 @@ int sock_getsockopt(struct socket *sock, int level, int optname, unsigned int lv = sizeof(int); int len; - if(get_user(len,optlen)) + if (get_user(len, optlen)) return -EFAULT; - if(len < 0) + if (len < 0) return -EINVAL; - switch(optname) - { - case SO_DEBUG: - v.val = sock_flag(sk, SOCK_DBG); - break; - - case SO_DONTROUTE: - v.val = sock_flag(sk, SOCK_LOCALROUTE); - break; - - case SO_BROADCAST: - v.val = !!sock_flag(sk, SOCK_BROADCAST); - break; - - case SO_SNDBUF: - v.val = sk->sk_sndbuf; - break; - - case SO_RCVBUF: - v.val = sk->sk_rcvbuf; - break; - - case SO_REUSEADDR: - v.val = sk->sk_reuse; - break; - - case SO_KEEPALIVE: - v.val = !!sock_flag(sk, SOCK_KEEPOPEN); - break; - - case SO_TYPE: - v.val = sk->sk_type; - break; - - case SO_ERROR: - v.val = -sock_error(sk); - if(v.val==0) - v.val = xchg(&sk->sk_err_soft, 0); - break; - - case SO_OOBINLINE: - v.val = !!sock_flag(sk, SOCK_URGINLINE); - break; - - case SO_NO_CHECK: - v.val = sk->sk_no_check; - break; - - case SO_PRIORITY: - v.val = sk->sk_priority; - break; - - case SO_LINGER: - lv = sizeof(v.ling); - v.ling.l_onoff = !!sock_flag(sk, SOCK_LINGER); - v.ling.l_linger = sk->sk_lingertime / HZ; - break; - - case SO_BSDCOMPAT: - sock_warn_obsolete_bsdism("getsockopt"); - break; - - case SO_TIMESTAMP: - v.val = sock_flag(sk, SOCK_RCVTSTAMP); - break; + switch(optname) { + case SO_DEBUG: + v.val = sock_flag(sk, SOCK_DBG); + break; + + case SO_DONTROUTE: + v.val = sock_flag(sk, SOCK_LOCALROUTE); + break; + + case SO_BROADCAST: + v.val = !!sock_flag(sk, SOCK_BROADCAST); + break; + + case SO_SNDBUF: + v.val = sk->sk_sndbuf; + break; + + case SO_RCVBUF: + v.val = sk->sk_rcvbuf; + break; + + case SO_REUSEADDR: + v.val = sk->sk_reuse; + break; + + case SO_KEEPALIVE: + v.val = !!sock_flag(sk, SOCK_KEEPOPEN); + break; + + case SO_TYPE: + v.val = sk->sk_type; + break; + + case SO_ERROR: + v.val = -sock_error(sk); + if (v.val==0) + v.val = xchg(&sk->sk_err_soft, 0); + break; + + case SO_OOBINLINE: + v.val = !!sock_flag(sk, SOCK_URGINLINE); + break; + + case SO_NO_CHECK: + v.val = sk->sk_no_check; + break; + + case SO_PRIORITY: + v.val = sk->sk_priority; + break; + + case SO_LINGER: + lv = sizeof(v.ling); + v.ling.l_onoff = !!sock_flag(sk, SOCK_LINGER); + v.ling.l_linger = sk->sk_lingertime / HZ; + break; + + case SO_BSDCOMPAT: + sock_warn_obsolete_bsdism("getsockopt"); + break; + + case SO_TIMESTAMP: + v.val = sock_flag(sk, SOCK_RCVTSTAMP) && + !sock_flag(sk, SOCK_RCVTSTAMPNS); + break; + + case SO_TIMESTAMPNS: + v.val = sock_flag(sk, SOCK_RCVTSTAMPNS); + break; + + case SO_RCVTIMEO: + lv=sizeof(struct timeval); + if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) { + v.tm.tv_sec = 0; + v.tm.tv_usec = 0; + } else { + v.tm.tv_sec = sk->sk_rcvtimeo / HZ; + v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * 1000000) / HZ; + } + break; + + case SO_SNDTIMEO: + lv=sizeof(struct timeval); + if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) { + v.tm.tv_sec = 0; + v.tm.tv_usec = 0; + } else { + v.tm.tv_sec = sk->sk_sndtimeo / HZ; + v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * 1000000) / HZ; + } + break; - case SO_RCVTIMEO: - lv=sizeof(struct timeval); - if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) { - v.tm.tv_sec = 0; - v.tm.tv_usec = 0; - } else { - v.tm.tv_sec = sk->sk_rcvtimeo / HZ; - v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * 1000000) / HZ; - } - break; + case SO_RCVLOWAT: + v.val = sk->sk_rcvlowat; + break; - case SO_SNDTIMEO: - lv=sizeof(struct timeval); - if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) { - v.tm.tv_sec = 0; - v.tm.tv_usec = 0; - } else { - v.tm.tv_sec = sk->sk_sndtimeo / HZ; - v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * 1000000) / HZ; - } - break; + case SO_SNDLOWAT: + v.val=1; + break; - case SO_RCVLOWAT: - v.val = sk->sk_rcvlowat; - break; + case SO_PASSCRED: + v.val = test_bit(SOCK_PASSCRED, &sock->flags) ? 1 : 0; + break; - case SO_SNDLOWAT: - v.val=1; - break; + case SO_PEERCRED: + if (len > sizeof(sk->sk_peercred)) + len = sizeof(sk->sk_peercred); + if (copy_to_user(optval, &sk->sk_peercred, len)) + return -EFAULT; + goto lenout; - case SO_PASSCRED: - v.val = test_bit(SOCK_PASSCRED, &sock->flags) ? 1 : 0; - break; - - case SO_PEERCRED: - if (len > sizeof(sk->sk_peercred)) - len = sizeof(sk->sk_peercred); - if (copy_to_user(optval, &sk->sk_peercred, len)) - return -EFAULT; - goto lenout; - - case SO_PEERNAME: - { - char address[128]; - - if (sock->ops->getname(sock, (struct sockaddr *)address, &lv, 2)) - return -ENOTCONN; - if (lv < len) - return -EINVAL; - if (copy_to_user(optval, address, len)) - return -EFAULT; - goto lenout; - } + case SO_PEERNAME: + { + char address[128]; + + if (sock->ops->getname(sock, (struct sockaddr *)address, &lv, 2)) + return -ENOTCONN; + if (lv < len) + return -EINVAL; + if (copy_to_user(optval, address, len)) + return -EFAULT; + goto lenout; + } - /* Dubious BSD thing... Probably nobody even uses it, but - * the UNIX standard wants it for whatever reason... -DaveM - */ - case SO_ACCEPTCONN: - v.val = sk->sk_state == TCP_LISTEN; - break; + /* Dubious BSD thing... Probably nobody even uses it, but + * the UNIX standard wants it for whatever reason... -DaveM + */ + case SO_ACCEPTCONN: + v.val = sk->sk_state == TCP_LISTEN; + break; - case SO_PASSSEC: - v.val = test_bit(SOCK_PASSSEC, &sock->flags) ? 1 : 0; - break; + case SO_PASSSEC: + v.val = test_bit(SOCK_PASSSEC, &sock->flags) ? 1 : 0; + break; - case SO_PEERSEC: - return security_socket_getpeersec_stream(sock, optval, optlen, len); + case SO_PEERSEC: + return security_socket_getpeersec_stream(sock, optval, optlen, len); - default: - return(-ENOPROTOOPT); + default: + return -ENOPROTOOPT; } + if (len > lv) len = lv; if (copy_to_user(optval, &v, len)) @@ -904,6 +915,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) sk_node_init(&newsk->sk_node); sock_lock_init(newsk); bh_lock_sock(newsk); + newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; atomic_set(&newsk->sk_rmem_alloc, 0); atomic_set(&newsk->sk_wmem_alloc, 0); @@ -923,7 +935,6 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) newsk->sk_wmem_queued = 0; newsk->sk_forward_alloc = 0; newsk->sk_send_head = NULL; - newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; sock_reset_flag(newsk, SOCK_DONE); @@ -970,6 +981,21 @@ out: EXPORT_SYMBOL_GPL(sk_clone); +void sk_setup_caps(struct sock *sk, struct dst_entry *dst) +{ + __sk_dst_set(sk, dst); + sk->sk_route_caps = dst->dev->features; + if (sk->sk_route_caps & NETIF_F_GSO) + sk->sk_route_caps |= NETIF_F_GSO_MASK; + if (sk_can_gso(sk)) { + if (dst->header_len) + sk->sk_route_caps &= ~NETIF_F_GSO_MASK; + else + sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; + } +} +EXPORT_SYMBOL_GPL(sk_setup_caps); + void __init sk_init(void) { if (num_physpages <= 4096) { @@ -1220,13 +1246,13 @@ static void __lock_sock(struct sock *sk) { DEFINE_WAIT(wait); - for(;;) { + for (;;) { prepare_to_wait_exclusive(&sk->sk_lock.wq, &wait, TASK_UNINTERRUPTIBLE); spin_unlock_bh(&sk->sk_lock.slock); schedule(); spin_lock_bh(&sk->sk_lock.slock); - if(!sock_owned_by_user(sk)) + if (!sock_owned_by_user(sk)) break; } finish_wait(&sk->sk_lock.wq, &wait); @@ -1258,7 +1284,7 @@ static void __release_sock(struct sock *sk) } while (skb != NULL); bh_lock_sock(sk); - } while((skb = sk->sk_backlog.head) != NULL); + } while ((skb = sk->sk_backlog.head) != NULL); } /** @@ -1420,7 +1446,7 @@ static void sock_def_write_space(struct sock *sk) /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ - if((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { + if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) wake_up_interruptible(sk->sk_sleep); @@ -1482,8 +1508,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sock_set_flag(sk, SOCK_ZAPPED); - if(sock) - { + if (sock) { sk->sk_type = sock->type; sk->sk_sleep = &sock->wait; sock->sk = sk; @@ -1512,8 +1537,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; - sk->sk_stamp.tv_sec = -1L; - sk->sk_stamp.tv_usec = -1L; + sk->sk_stamp = ktime_set(-1L, -1L); atomic_set(&sk->sk_refcnt, 1); } @@ -1554,17 +1578,36 @@ EXPORT_SYMBOL(release_sock); int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp) { + struct timeval tv; if (!sock_flag(sk, SOCK_TIMESTAMP)) sock_enable_timestamp(sk); - if (sk->sk_stamp.tv_sec == -1) + tv = ktime_to_timeval(sk->sk_stamp); + if (tv.tv_sec == -1) return -ENOENT; - if (sk->sk_stamp.tv_sec == 0) - do_gettimeofday(&sk->sk_stamp); - return copy_to_user(userstamp, &sk->sk_stamp, sizeof(struct timeval)) ? - -EFAULT : 0; + if (tv.tv_sec == 0) { + sk->sk_stamp = ktime_get_real(); + tv = ktime_to_timeval(sk->sk_stamp); + } + return copy_to_user(userstamp, &tv, sizeof(tv)) ? -EFAULT : 0; } EXPORT_SYMBOL(sock_get_timestamp); +int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp) +{ + struct timespec ts; + if (!sock_flag(sk, SOCK_TIMESTAMP)) + sock_enable_timestamp(sk); + ts = ktime_to_timespec(sk->sk_stamp); + if (ts.tv_sec == -1) + return -ENOENT; + if (ts.tv_sec == 0) { + sk->sk_stamp = ktime_get_real(); + ts = ktime_to_timespec(sk->sk_stamp); + } + return copy_to_user(userstamp, &ts, sizeof(ts)) ? -EFAULT : 0; +} +EXPORT_SYMBOL(sock_get_timestampns); + void sock_enable_timestamp(struct sock *sk) { if (!sock_flag(sk, SOCK_TIMESTAMP)) { @@ -1899,7 +1942,7 @@ static int proto_seq_show(struct seq_file *seq, void *v) return 0; } -static struct seq_operations proto_seq_ops = { +static const struct seq_operations proto_seq_ops = { .start = proto_seq_start, .next = proto_seq_next, .stop = proto_seq_stop, diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 1e75b1585460..b29712033dd4 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -136,6 +136,14 @@ ctl_table core_table[] = { .mode = 0644, .proc_handler = &proc_dointvec }, + { + .ctl_name = NET_CORE_WARNINGS, + .procname = "warnings", + .data = &net_msg_warn, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec + }, { .ctl_name = 0 } }; diff --git a/net/core/user_dma.c b/net/core/user_dma.c index 0ad1cd57bc39..89241cdeea3f 100644 --- a/net/core/user_dma.c +++ b/net/core/user_dma.c @@ -49,8 +49,8 @@ int dma_skb_copy_datagram_iovec(struct dma_chan *chan, struct sk_buff *skb, int offset, struct iovec *to, size_t len, struct dma_pinned_list *pinned_list) { - int start = skb_headlen(skb); - int i, copy = start - offset; + int end = skb_headlen(skb); + int i, copy = end - offset; dma_cookie_t cookie = 0; /* Copy header. */ @@ -69,11 +69,9 @@ int dma_skb_copy_datagram_iovec(struct dma_chan *chan, /* Copy paged appendix. Hmm... why does this look so complicated? */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - int end; + BUG_TRAP(len >= 0); - BUG_TRAP(start <= offset + len); - - end = start + skb_shinfo(skb)->frags[i].size; + end = offset + skb_shinfo(skb)->frags[i].size; copy = end - offset; if ((copy = end - offset) > 0) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; @@ -82,8 +80,8 @@ int dma_skb_copy_datagram_iovec(struct dma_chan *chan, if (copy > len) copy = len; - cookie = dma_memcpy_pg_to_iovec(chan, to, pinned_list, page, - frag->page_offset + offset - start, copy); + cookie = dma_memcpy_pg_to_iovec(chan, to, pinned_list, + page, frag->page_offset, copy); if (cookie < 0) goto fault; len -= copy; @@ -91,25 +89,21 @@ int dma_skb_copy_datagram_iovec(struct dma_chan *chan, goto end; offset += copy; } - start = end; } if (skb_shinfo(skb)->frag_list) { struct sk_buff *list = skb_shinfo(skb)->frag_list; for (; list; list = list->next) { - int end; - - BUG_TRAP(start <= offset + len); + BUG_TRAP(len >= 0); - end = start + list->len; + end = offset + list->len; copy = end - offset; if (copy > 0) { if (copy > len) copy = len; cookie = dma_skb_copy_datagram_iovec(chan, list, - offset - start, to, copy, - pinned_list); + 0, to, copy, pinned_list); if (cookie < 0) goto fault; len -= copy; @@ -117,7 +111,6 @@ int dma_skb_copy_datagram_iovec(struct dma_chan *chan, goto end; offset += copy; } - start = end; } } diff --git a/net/core/utils.c b/net/core/utils.c index 07236c17fab9..adecfd281ae9 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -30,8 +30,10 @@ #include <asm/system.h> #include <asm/uaccess.h> -int net_msg_cost = 5*HZ; -int net_msg_burst = 10; +int net_msg_cost __read_mostly = 5*HZ; +int net_msg_burst __read_mostly = 10; +int net_msg_warn __read_mostly = 1; +EXPORT_SYMBOL(net_msg_warn); /* * All net warning printk()s should be guarded by this function. diff --git a/net/core/wireless.c b/net/core/wireless.c deleted file mode 100644 index b07fe270a508..000000000000 --- a/net/core/wireless.c +++ /dev/null @@ -1,2371 +0,0 @@ -/* - * This file implement the Wireless Extensions APIs. - * - * Authors : Jean Tourrilhes - HPL - <jt@hpl.hp.com> - * Copyright (c) 1997-2007 Jean Tourrilhes, All Rights Reserved. - * - * (As all part of the Linux kernel, this file is GPL) - */ - -/************************** DOCUMENTATION **************************/ -/* - * API definition : - * -------------- - * See <linux/wireless.h> for details of the APIs and the rest. - * - * History : - * ------- - * - * v1 - 5.12.01 - Jean II - * o Created this file. - * - * v2 - 13.12.01 - Jean II - * o Move /proc/net/wireless stuff from net/core/dev.c to here - * o Make Wireless Extension IOCTLs go through here - * o Added iw_handler handling ;-) - * o Added standard ioctl description - * o Initial dumb commit strategy based on orinoco.c - * - * v3 - 19.12.01 - Jean II - * o Make sure we don't go out of standard_ioctl[] in ioctl_standard_call - * o Add event dispatcher function - * o Add event description - * o Propagate events as rtnetlink IFLA_WIRELESS option - * o Generate event on selected SET requests - * - * v4 - 18.04.02 - Jean II - * o Fix stupid off by one in iw_ioctl_description : IW_ESSID_MAX_SIZE + 1 - * - * v5 - 21.06.02 - Jean II - * o Add IW_PRIV_TYPE_ADDR in priv_type_size (+cleanup) - * o Reshuffle IW_HEADER_TYPE_XXX to map IW_PRIV_TYPE_XXX changes - * o Add IWEVCUSTOM for driver specific event/scanning token - * o Turn on WE_STRICT_WRITE by default + kernel warning - * o Fix WE_STRICT_WRITE in ioctl_export_private() (32 => iw_num) - * o Fix off-by-one in test (extra_size <= IFNAMSIZ) - * - * v6 - 9.01.03 - Jean II - * o Add common spy support : iw_handler_set_spy(), wireless_spy_update() - * o Add enhanced spy support : iw_handler_set_thrspy() and event. - * o Add WIRELESS_EXT version display in /proc/net/wireless - * - * v6 - 18.06.04 - Jean II - * o Change get_spydata() method for added safety - * o Remove spy #ifdef, they are always on -> cleaner code - * o Allow any size GET request if user specifies length > max - * and if request has IW_DESCR_FLAG_NOMAX flag or is SIOCGIWPRIV - * o Start migrating get_wireless_stats to struct iw_handler_def - * o Add wmb() in iw_handler_set_spy() for non-coherent archs/cpus - * Based on patch from Pavel Roskin <proski@gnu.org> : - * o Fix kernel data leak to user space in private handler handling - * - * v7 - 18.3.05 - Jean II - * o Remove (struct iw_point *)->pointer from events and streams - * o Remove spy_offset from struct iw_handler_def - * o Start deprecating dev->get_wireless_stats, output a warning - * o If IW_QUAL_DBM is set, show dBm values in /proc/net/wireless - * o Don't loose INVALID/DBM flags when clearing UPDATED flags (iwstats) - * - * v8 - 17.02.06 - Jean II - * o RtNetlink requests support (SET/GET) - * - * v8b - 03.08.06 - Herbert Xu - * o Fix Wireless Event locking issues. - * - * v9 - 14.3.06 - Jean II - * o Change length in ESSID and NICK to strlen() instead of strlen()+1 - * o Make standard_ioctl_num and standard_event_num unsigned - * o Remove (struct net_device *)->get_wireless_stats() - * - * v10 - 16.3.07 - Jean II - * o Prevent leaking of kernel space in stream on 64 bits. - */ - -/***************************** INCLUDES *****************************/ - -#include <linux/module.h> -#include <linux/types.h> /* off_t */ -#include <linux/netdevice.h> /* struct ifreq, dev_get_by_name() */ -#include <linux/proc_fs.h> -#include <linux/rtnetlink.h> /* rtnetlink stuff */ -#include <linux/seq_file.h> -#include <linux/init.h> /* for __init */ -#include <linux/if_arp.h> /* ARPHRD_ETHER */ -#include <linux/etherdevice.h> /* compare_ether_addr */ -#include <linux/interrupt.h> - -#include <linux/wireless.h> /* Pretty obvious */ -#include <net/iw_handler.h> /* New driver API */ -#include <net/netlink.h> - -#include <asm/uaccess.h> /* copy_to_user() */ - -/**************************** CONSTANTS ****************************/ - -/* Debugging stuff */ -#undef WE_IOCTL_DEBUG /* Debug IOCTL API */ -#undef WE_RTNETLINK_DEBUG /* Debug RtNetlink API */ -#undef WE_EVENT_DEBUG /* Debug Event dispatcher */ -#undef WE_SPY_DEBUG /* Debug enhanced spy support */ - -/* Options */ -//CONFIG_NET_WIRELESS_RTNETLINK /* Wireless requests over RtNetlink */ -#define WE_EVENT_RTNETLINK /* Propagate events using RtNetlink */ -#define WE_SET_EVENT /* Generate an event on some set commands */ - -/************************* GLOBAL VARIABLES *************************/ -/* - * You should not use global variables, because of re-entrancy. - * On our case, it's only const, so it's OK... - */ -/* - * Meta-data about all the standard Wireless Extension request we - * know about. - */ -static const struct iw_ioctl_description standard_ioctl[] = { - [SIOCSIWCOMMIT - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_NULL, - }, - [SIOCGIWNAME - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_CHAR, - .flags = IW_DESCR_FLAG_DUMP, - }, - [SIOCSIWNWID - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - .flags = IW_DESCR_FLAG_EVENT, - }, - [SIOCGIWNWID - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - .flags = IW_DESCR_FLAG_DUMP, - }, - [SIOCSIWFREQ - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_FREQ, - .flags = IW_DESCR_FLAG_EVENT, - }, - [SIOCGIWFREQ - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_FREQ, - .flags = IW_DESCR_FLAG_DUMP, - }, - [SIOCSIWMODE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_UINT, - .flags = IW_DESCR_FLAG_EVENT, - }, - [SIOCGIWMODE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_UINT, - .flags = IW_DESCR_FLAG_DUMP, - }, - [SIOCSIWSENS - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCGIWSENS - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCSIWRANGE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_NULL, - }, - [SIOCGIWRANGE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = sizeof(struct iw_range), - .flags = IW_DESCR_FLAG_DUMP, - }, - [SIOCSIWPRIV - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_NULL, - }, - [SIOCGIWPRIV - SIOCIWFIRST] = { /* (handled directly by us) */ - .header_type = IW_HEADER_TYPE_POINT, - .token_size = sizeof(struct iw_priv_args), - .max_tokens = 16, - .flags = IW_DESCR_FLAG_NOMAX, - }, - [SIOCSIWSTATS - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_NULL, - }, - [SIOCGIWSTATS - SIOCIWFIRST] = { /* (handled directly by us) */ - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = sizeof(struct iw_statistics), - .flags = IW_DESCR_FLAG_DUMP, - }, - [SIOCSIWSPY - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = sizeof(struct sockaddr), - .max_tokens = IW_MAX_SPY, - }, - [SIOCGIWSPY - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = sizeof(struct sockaddr) + - sizeof(struct iw_quality), - .max_tokens = IW_MAX_SPY, - }, - [SIOCSIWTHRSPY - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = sizeof(struct iw_thrspy), - .min_tokens = 1, - .max_tokens = 1, - }, - [SIOCGIWTHRSPY - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = sizeof(struct iw_thrspy), - .min_tokens = 1, - .max_tokens = 1, - }, - [SIOCSIWAP - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_ADDR, - }, - [SIOCGIWAP - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_ADDR, - .flags = IW_DESCR_FLAG_DUMP, - }, - [SIOCSIWMLME - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .min_tokens = sizeof(struct iw_mlme), - .max_tokens = sizeof(struct iw_mlme), - }, - [SIOCGIWAPLIST - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = sizeof(struct sockaddr) + - sizeof(struct iw_quality), - .max_tokens = IW_MAX_AP, - .flags = IW_DESCR_FLAG_NOMAX, - }, - [SIOCSIWSCAN - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .min_tokens = 0, - .max_tokens = sizeof(struct iw_scan_req), - }, - [SIOCGIWSCAN - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_SCAN_MAX_DATA, - .flags = IW_DESCR_FLAG_NOMAX, - }, - [SIOCSIWESSID - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_ESSID_MAX_SIZE, - .flags = IW_DESCR_FLAG_EVENT, - }, - [SIOCGIWESSID - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_ESSID_MAX_SIZE, - .flags = IW_DESCR_FLAG_DUMP, - }, - [SIOCSIWNICKN - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_ESSID_MAX_SIZE, - }, - [SIOCGIWNICKN - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_ESSID_MAX_SIZE, - }, - [SIOCSIWRATE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCGIWRATE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCSIWRTS - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCGIWRTS - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCSIWFRAG - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCGIWFRAG - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCSIWTXPOW - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCGIWTXPOW - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCSIWRETRY - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCGIWRETRY - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCSIWENCODE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_ENCODING_TOKEN_MAX, - .flags = IW_DESCR_FLAG_EVENT | IW_DESCR_FLAG_RESTRICT, - }, - [SIOCGIWENCODE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_ENCODING_TOKEN_MAX, - .flags = IW_DESCR_FLAG_DUMP | IW_DESCR_FLAG_RESTRICT, - }, - [SIOCSIWPOWER - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCGIWPOWER - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCSIWGENIE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_GENERIC_IE_MAX, - }, - [SIOCGIWGENIE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_GENERIC_IE_MAX, - }, - [SIOCSIWAUTH - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCGIWAUTH - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCSIWENCODEEXT - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .min_tokens = sizeof(struct iw_encode_ext), - .max_tokens = sizeof(struct iw_encode_ext) + - IW_ENCODING_TOKEN_MAX, - }, - [SIOCGIWENCODEEXT - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .min_tokens = sizeof(struct iw_encode_ext), - .max_tokens = sizeof(struct iw_encode_ext) + - IW_ENCODING_TOKEN_MAX, - }, - [SIOCSIWPMKSA - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .min_tokens = sizeof(struct iw_pmksa), - .max_tokens = sizeof(struct iw_pmksa), - }, -}; -static const unsigned standard_ioctl_num = (sizeof(standard_ioctl) / - sizeof(struct iw_ioctl_description)); - -/* - * Meta-data about all the additional standard Wireless Extension events - * we know about. - */ -static const struct iw_ioctl_description standard_event[] = { - [IWEVTXDROP - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_ADDR, - }, - [IWEVQUAL - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_QUAL, - }, - [IWEVCUSTOM - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_CUSTOM_MAX, - }, - [IWEVREGISTERED - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_ADDR, - }, - [IWEVEXPIRED - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_ADDR, - }, - [IWEVGENIE - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_GENERIC_IE_MAX, - }, - [IWEVMICHAELMICFAILURE - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = sizeof(struct iw_michaelmicfailure), - }, - [IWEVASSOCREQIE - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_GENERIC_IE_MAX, - }, - [IWEVASSOCRESPIE - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_GENERIC_IE_MAX, - }, - [IWEVPMKIDCAND - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = sizeof(struct iw_pmkid_cand), - }, -}; -static const unsigned standard_event_num = (sizeof(standard_event) / - sizeof(struct iw_ioctl_description)); - -/* Size (in bytes) of the various private data types */ -static const char iw_priv_type_size[] = { - 0, /* IW_PRIV_TYPE_NONE */ - 1, /* IW_PRIV_TYPE_BYTE */ - 1, /* IW_PRIV_TYPE_CHAR */ - 0, /* Not defined */ - sizeof(__u32), /* IW_PRIV_TYPE_INT */ - sizeof(struct iw_freq), /* IW_PRIV_TYPE_FLOAT */ - sizeof(struct sockaddr), /* IW_PRIV_TYPE_ADDR */ - 0, /* Not defined */ -}; - -/* Size (in bytes) of various events */ -static const int event_type_size[] = { - IW_EV_LCP_LEN, /* IW_HEADER_TYPE_NULL */ - 0, - IW_EV_CHAR_LEN, /* IW_HEADER_TYPE_CHAR */ - 0, - IW_EV_UINT_LEN, /* IW_HEADER_TYPE_UINT */ - IW_EV_FREQ_LEN, /* IW_HEADER_TYPE_FREQ */ - IW_EV_ADDR_LEN, /* IW_HEADER_TYPE_ADDR */ - 0, - IW_EV_POINT_LEN, /* Without variable payload */ - IW_EV_PARAM_LEN, /* IW_HEADER_TYPE_PARAM */ - IW_EV_QUAL_LEN, /* IW_HEADER_TYPE_QUAL */ -}; - -/* Size (in bytes) of various events, as packed */ -static const int event_type_pk_size[] = { - IW_EV_LCP_PK_LEN, /* IW_HEADER_TYPE_NULL */ - 0, - IW_EV_CHAR_PK_LEN, /* IW_HEADER_TYPE_CHAR */ - 0, - IW_EV_UINT_PK_LEN, /* IW_HEADER_TYPE_UINT */ - IW_EV_FREQ_PK_LEN, /* IW_HEADER_TYPE_FREQ */ - IW_EV_ADDR_PK_LEN, /* IW_HEADER_TYPE_ADDR */ - 0, - IW_EV_POINT_PK_LEN, /* Without variable payload */ - IW_EV_PARAM_PK_LEN, /* IW_HEADER_TYPE_PARAM */ - IW_EV_QUAL_PK_LEN, /* IW_HEADER_TYPE_QUAL */ -}; - -/************************ COMMON SUBROUTINES ************************/ -/* - * Stuff that may be used in various place or doesn't fit in one - * of the section below. - */ - -/* ---------------------------------------------------------------- */ -/* - * Return the driver handler associated with a specific Wireless Extension. - * Called from various place, so make sure it remains efficient. - */ -static inline iw_handler get_handler(struct net_device *dev, - unsigned int cmd) -{ - /* Don't "optimise" the following variable, it will crash */ - unsigned int index; /* *MUST* be unsigned */ - - /* Check if we have some wireless handlers defined */ - if(dev->wireless_handlers == NULL) - return NULL; - - /* Try as a standard command */ - index = cmd - SIOCIWFIRST; - if(index < dev->wireless_handlers->num_standard) - return dev->wireless_handlers->standard[index]; - - /* Try as a private command */ - index = cmd - SIOCIWFIRSTPRIV; - if(index < dev->wireless_handlers->num_private) - return dev->wireless_handlers->private[index]; - - /* Not found */ - return NULL; -} - -/* ---------------------------------------------------------------- */ -/* - * Get statistics out of the driver - */ -static inline struct iw_statistics *get_wireless_stats(struct net_device *dev) -{ - /* New location */ - if((dev->wireless_handlers != NULL) && - (dev->wireless_handlers->get_wireless_stats != NULL)) - return dev->wireless_handlers->get_wireless_stats(dev); - - /* Not found */ - return (struct iw_statistics *) NULL; -} - -/* ---------------------------------------------------------------- */ -/* - * Call the commit handler in the driver - * (if exist and if conditions are right) - * - * Note : our current commit strategy is currently pretty dumb, - * but we will be able to improve on that... - * The goal is to try to agreagate as many changes as possible - * before doing the commit. Drivers that will define a commit handler - * are usually those that need a reset after changing parameters, so - * we want to minimise the number of reset. - * A cool idea is to use a timer : at each "set" command, we re-set the - * timer, when the timer eventually fires, we call the driver. - * Hopefully, more on that later. - * - * Also, I'm waiting to see how many people will complain about the - * netif_running(dev) test. I'm open on that one... - * Hopefully, the driver will remember to do a commit in "open()" ;-) - */ -static inline int call_commit_handler(struct net_device * dev) -{ - if((netif_running(dev)) && - (dev->wireless_handlers->standard[0] != NULL)) { - /* Call the commit handler on the driver */ - return dev->wireless_handlers->standard[0](dev, NULL, - NULL, NULL); - } else - return 0; /* Command completed successfully */ -} - -/* ---------------------------------------------------------------- */ -/* - * Calculate size of private arguments - */ -static inline int get_priv_size(__u16 args) -{ - int num = args & IW_PRIV_SIZE_MASK; - int type = (args & IW_PRIV_TYPE_MASK) >> 12; - - return num * iw_priv_type_size[type]; -} - -/* ---------------------------------------------------------------- */ -/* - * Re-calculate the size of private arguments - */ -static inline int adjust_priv_size(__u16 args, - union iwreq_data * wrqu) -{ - int num = wrqu->data.length; - int max = args & IW_PRIV_SIZE_MASK; - int type = (args & IW_PRIV_TYPE_MASK) >> 12; - - /* Make sure the driver doesn't goof up */ - if (max < num) - num = max; - - return num * iw_priv_type_size[type]; -} - -/* ---------------------------------------------------------------- */ -/* - * Standard Wireless Handler : get wireless stats - * Allow programatic access to /proc/net/wireless even if /proc - * doesn't exist... Also more efficient... - */ -static int iw_handler_get_iwstats(struct net_device * dev, - struct iw_request_info * info, - union iwreq_data * wrqu, - char * extra) -{ - /* Get stats from the driver */ - struct iw_statistics *stats; - - stats = get_wireless_stats(dev); - if (stats != (struct iw_statistics *) NULL) { - - /* Copy statistics to extra */ - memcpy(extra, stats, sizeof(struct iw_statistics)); - wrqu->data.length = sizeof(struct iw_statistics); - - /* Check if we need to clear the updated flag */ - if(wrqu->data.flags != 0) - stats->qual.updated &= ~IW_QUAL_ALL_UPDATED; - return 0; - } else - return -EOPNOTSUPP; -} - -/* ---------------------------------------------------------------- */ -/* - * Standard Wireless Handler : get iwpriv definitions - * Export the driver private handler definition - * They will be picked up by tools like iwpriv... - */ -static int iw_handler_get_private(struct net_device * dev, - struct iw_request_info * info, - union iwreq_data * wrqu, - char * extra) -{ - /* Check if the driver has something to export */ - if((dev->wireless_handlers->num_private_args == 0) || - (dev->wireless_handlers->private_args == NULL)) - return -EOPNOTSUPP; - - /* Check if there is enough buffer up there */ - if(wrqu->data.length < dev->wireless_handlers->num_private_args) { - /* User space can't know in advance how large the buffer - * needs to be. Give it a hint, so that we can support - * any size buffer we want somewhat efficiently... */ - wrqu->data.length = dev->wireless_handlers->num_private_args; - return -E2BIG; - } - - /* Set the number of available ioctls. */ - wrqu->data.length = dev->wireless_handlers->num_private_args; - - /* Copy structure to the user buffer. */ - memcpy(extra, dev->wireless_handlers->private_args, - sizeof(struct iw_priv_args) * wrqu->data.length); - - return 0; -} - - -/******************** /proc/net/wireless SUPPORT ********************/ -/* - * The /proc/net/wireless file is a human readable user-space interface - * exporting various wireless specific statistics from the wireless devices. - * This is the most popular part of the Wireless Extensions ;-) - * - * This interface is a pure clone of /proc/net/dev (in net/core/dev.c). - * The content of the file is basically the content of "struct iw_statistics". - */ - -#ifdef CONFIG_PROC_FS - -/* ---------------------------------------------------------------- */ -/* - * Print one entry (line) of /proc/net/wireless - */ -static __inline__ void wireless_seq_printf_stats(struct seq_file *seq, - struct net_device *dev) -{ - /* Get stats from the driver */ - struct iw_statistics *stats = get_wireless_stats(dev); - - if (stats) { - seq_printf(seq, "%6s: %04x %3d%c %3d%c %3d%c %6d %6d %6d " - "%6d %6d %6d\n", - dev->name, stats->status, stats->qual.qual, - stats->qual.updated & IW_QUAL_QUAL_UPDATED - ? '.' : ' ', - ((__s32) stats->qual.level) - - ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), - stats->qual.updated & IW_QUAL_LEVEL_UPDATED - ? '.' : ' ', - ((__s32) stats->qual.noise) - - ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), - stats->qual.updated & IW_QUAL_NOISE_UPDATED - ? '.' : ' ', - stats->discard.nwid, stats->discard.code, - stats->discard.fragment, stats->discard.retries, - stats->discard.misc, stats->miss.beacon); - stats->qual.updated &= ~IW_QUAL_ALL_UPDATED; - } -} - -/* ---------------------------------------------------------------- */ -/* - * Print info for /proc/net/wireless (print all entries) - */ -static int wireless_seq_show(struct seq_file *seq, void *v) -{ - if (v == SEQ_START_TOKEN) - seq_printf(seq, "Inter-| sta-| Quality | Discarded " - "packets | Missed | WE\n" - " face | tus | link level noise | nwid " - "crypt frag retry misc | beacon | %d\n", - WIRELESS_EXT); - else - wireless_seq_printf_stats(seq, v); - return 0; -} - -static struct seq_operations wireless_seq_ops = { - .start = dev_seq_start, - .next = dev_seq_next, - .stop = dev_seq_stop, - .show = wireless_seq_show, -}; - -static int wireless_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &wireless_seq_ops); -} - -static const struct file_operations wireless_seq_fops = { - .owner = THIS_MODULE, - .open = wireless_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -int __init wireless_proc_init(void) -{ - /* Create /proc/net/wireless entry */ - if (!proc_net_fops_create("wireless", S_IRUGO, &wireless_seq_fops)) - return -ENOMEM; - - return 0; -} -#endif /* CONFIG_PROC_FS */ - -/************************** IOCTL SUPPORT **************************/ -/* - * The original user space API to configure all those Wireless Extensions - * is through IOCTLs. - * In there, we check if we need to call the new driver API (iw_handler) - * or just call the driver ioctl handler. - */ - -/* ---------------------------------------------------------------- */ -/* - * Wrapper to call a standard Wireless Extension handler. - * We do various checks and also take care of moving data between - * user space and kernel space. - */ -static int ioctl_standard_call(struct net_device * dev, - struct ifreq * ifr, - unsigned int cmd, - iw_handler handler) -{ - struct iwreq * iwr = (struct iwreq *) ifr; - const struct iw_ioctl_description * descr; - struct iw_request_info info; - int ret = -EINVAL; - - /* Get the description of the IOCTL */ - if((cmd - SIOCIWFIRST) >= standard_ioctl_num) - return -EOPNOTSUPP; - descr = &(standard_ioctl[cmd - SIOCIWFIRST]); - -#ifdef WE_IOCTL_DEBUG - printk(KERN_DEBUG "%s (WE) : Found standard handler for 0x%04X\n", - ifr->ifr_name, cmd); - printk(KERN_DEBUG "%s (WE) : Header type : %d, Token type : %d, size : %d, token : %d\n", dev->name, descr->header_type, descr->token_type, descr->token_size, descr->max_tokens); -#endif /* WE_IOCTL_DEBUG */ - - /* Prepare the call */ - info.cmd = cmd; - info.flags = 0; - - /* Check if we have a pointer to user space data or not */ - if(descr->header_type != IW_HEADER_TYPE_POINT) { - - /* No extra arguments. Trivial to handle */ - ret = handler(dev, &info, &(iwr->u), NULL); - -#ifdef WE_SET_EVENT - /* Generate an event to notify listeners of the change */ - if((descr->flags & IW_DESCR_FLAG_EVENT) && - ((ret == 0) || (ret == -EIWCOMMIT))) - wireless_send_event(dev, cmd, &(iwr->u), NULL); -#endif /* WE_SET_EVENT */ - } else { - char * extra; - int extra_size; - int user_length = 0; - int err; - int essid_compat = 0; - - /* Calculate space needed by arguments. Always allocate - * for max space. Easier, and won't last long... */ - extra_size = descr->max_tokens * descr->token_size; - - /* Check need for ESSID compatibility for WE < 21 */ - switch (cmd) { - case SIOCSIWESSID: - case SIOCGIWESSID: - case SIOCSIWNICKN: - case SIOCGIWNICKN: - if (iwr->u.data.length == descr->max_tokens + 1) - essid_compat = 1; - else if (IW_IS_SET(cmd) && (iwr->u.data.length != 0)) { - char essid[IW_ESSID_MAX_SIZE + 1]; - - err = copy_from_user(essid, iwr->u.data.pointer, - iwr->u.data.length * - descr->token_size); - if (err) - return -EFAULT; - - if (essid[iwr->u.data.length - 1] == '\0') - essid_compat = 1; - } - break; - default: - break; - } - - iwr->u.data.length -= essid_compat; - - /* Check what user space is giving us */ - if(IW_IS_SET(cmd)) { - /* Check NULL pointer */ - if((iwr->u.data.pointer == NULL) && - (iwr->u.data.length != 0)) - return -EFAULT; - /* Check if number of token fits within bounds */ - if(iwr->u.data.length > descr->max_tokens) - return -E2BIG; - if(iwr->u.data.length < descr->min_tokens) - return -EINVAL; - } else { - /* Check NULL pointer */ - if(iwr->u.data.pointer == NULL) - return -EFAULT; - /* Save user space buffer size for checking */ - user_length = iwr->u.data.length; - - /* Don't check if user_length > max to allow forward - * compatibility. The test user_length < min is - * implied by the test at the end. */ - - /* Support for very large requests */ - if((descr->flags & IW_DESCR_FLAG_NOMAX) && - (user_length > descr->max_tokens)) { - /* Allow userspace to GET more than max so - * we can support any size GET requests. - * There is still a limit : -ENOMEM. */ - extra_size = user_length * descr->token_size; - /* Note : user_length is originally a __u16, - * and token_size is controlled by us, - * so extra_size won't get negative and - * won't overflow... */ - } - } - -#ifdef WE_IOCTL_DEBUG - printk(KERN_DEBUG "%s (WE) : Malloc %d bytes\n", - dev->name, extra_size); -#endif /* WE_IOCTL_DEBUG */ - - /* Create the kernel buffer */ - /* kzalloc ensures NULL-termination for essid_compat */ - extra = kzalloc(extra_size, GFP_KERNEL); - if (extra == NULL) { - return -ENOMEM; - } - - /* If it is a SET, get all the extra data in here */ - if(IW_IS_SET(cmd) && (iwr->u.data.length != 0)) { - err = copy_from_user(extra, iwr->u.data.pointer, - iwr->u.data.length * - descr->token_size); - if (err) { - kfree(extra); - return -EFAULT; - } -#ifdef WE_IOCTL_DEBUG - printk(KERN_DEBUG "%s (WE) : Got %d bytes\n", - dev->name, - iwr->u.data.length * descr->token_size); -#endif /* WE_IOCTL_DEBUG */ - } - - /* Call the handler */ - ret = handler(dev, &info, &(iwr->u), extra); - - iwr->u.data.length += essid_compat; - - /* If we have something to return to the user */ - if (!ret && IW_IS_GET(cmd)) { - /* Check if there is enough buffer up there */ - if(user_length < iwr->u.data.length) { - kfree(extra); - return -E2BIG; - } - - err = copy_to_user(iwr->u.data.pointer, extra, - iwr->u.data.length * - descr->token_size); - if (err) - ret = -EFAULT; -#ifdef WE_IOCTL_DEBUG - printk(KERN_DEBUG "%s (WE) : Wrote %d bytes\n", - dev->name, - iwr->u.data.length * descr->token_size); -#endif /* WE_IOCTL_DEBUG */ - } - -#ifdef WE_SET_EVENT - /* Generate an event to notify listeners of the change */ - if((descr->flags & IW_DESCR_FLAG_EVENT) && - ((ret == 0) || (ret == -EIWCOMMIT))) { - if(descr->flags & IW_DESCR_FLAG_RESTRICT) - /* If the event is restricted, don't - * export the payload */ - wireless_send_event(dev, cmd, &(iwr->u), NULL); - else - wireless_send_event(dev, cmd, &(iwr->u), - extra); - } -#endif /* WE_SET_EVENT */ - - /* Cleanup - I told you it wasn't that long ;-) */ - kfree(extra); - } - - /* Call commit handler if needed and defined */ - if(ret == -EIWCOMMIT) - ret = call_commit_handler(dev); - - /* Here, we will generate the appropriate event if needed */ - - return ret; -} - -/* ---------------------------------------------------------------- */ -/* - * Wrapper to call a private Wireless Extension handler. - * We do various checks and also take care of moving data between - * user space and kernel space. - * It's not as nice and slimline as the standard wrapper. The cause - * is struct iw_priv_args, which was not really designed for the - * job we are going here. - * - * IMPORTANT : This function prevent to set and get data on the same - * IOCTL and enforce the SET/GET convention. Not doing it would be - * far too hairy... - * If you need to set and get data at the same time, please don't use - * a iw_handler but process it in your ioctl handler (i.e. use the - * old driver API). - */ -static inline int ioctl_private_call(struct net_device * dev, - struct ifreq * ifr, - unsigned int cmd, - iw_handler handler) -{ - struct iwreq * iwr = (struct iwreq *) ifr; - const struct iw_priv_args * descr = NULL; - struct iw_request_info info; - int extra_size = 0; - int i; - int ret = -EINVAL; - - /* Get the description of the IOCTL */ - for(i = 0; i < dev->wireless_handlers->num_private_args; i++) - if(cmd == dev->wireless_handlers->private_args[i].cmd) { - descr = &(dev->wireless_handlers->private_args[i]); - break; - } - -#ifdef WE_IOCTL_DEBUG - printk(KERN_DEBUG "%s (WE) : Found private handler for 0x%04X\n", - ifr->ifr_name, cmd); - if(descr) { - printk(KERN_DEBUG "%s (WE) : Name %s, set %X, get %X\n", - dev->name, descr->name, - descr->set_args, descr->get_args); - } -#endif /* WE_IOCTL_DEBUG */ - - /* Compute the size of the set/get arguments */ - if(descr != NULL) { - if(IW_IS_SET(cmd)) { - int offset = 0; /* For sub-ioctls */ - /* Check for sub-ioctl handler */ - if(descr->name[0] == '\0') - /* Reserve one int for sub-ioctl index */ - offset = sizeof(__u32); - - /* Size of set arguments */ - extra_size = get_priv_size(descr->set_args); - - /* Does it fits in iwr ? */ - if((descr->set_args & IW_PRIV_SIZE_FIXED) && - ((extra_size + offset) <= IFNAMSIZ)) - extra_size = 0; - } else { - /* Size of get arguments */ - extra_size = get_priv_size(descr->get_args); - - /* Does it fits in iwr ? */ - if((descr->get_args & IW_PRIV_SIZE_FIXED) && - (extra_size <= IFNAMSIZ)) - extra_size = 0; - } - } - - /* Prepare the call */ - info.cmd = cmd; - info.flags = 0; - - /* Check if we have a pointer to user space data or not. */ - if(extra_size == 0) { - /* No extra arguments. Trivial to handle */ - ret = handler(dev, &info, &(iwr->u), (char *) &(iwr->u)); - } else { - char * extra; - int err; - - /* Check what user space is giving us */ - if(IW_IS_SET(cmd)) { - /* Check NULL pointer */ - if((iwr->u.data.pointer == NULL) && - (iwr->u.data.length != 0)) - return -EFAULT; - - /* Does it fits within bounds ? */ - if(iwr->u.data.length > (descr->set_args & - IW_PRIV_SIZE_MASK)) - return -E2BIG; - } else { - /* Check NULL pointer */ - if(iwr->u.data.pointer == NULL) - return -EFAULT; - } - -#ifdef WE_IOCTL_DEBUG - printk(KERN_DEBUG "%s (WE) : Malloc %d bytes\n", - dev->name, extra_size); -#endif /* WE_IOCTL_DEBUG */ - - /* Always allocate for max space. Easier, and won't last - * long... */ - extra = kmalloc(extra_size, GFP_KERNEL); - if (extra == NULL) { - return -ENOMEM; - } - - /* If it is a SET, get all the extra data in here */ - if(IW_IS_SET(cmd) && (iwr->u.data.length != 0)) { - err = copy_from_user(extra, iwr->u.data.pointer, - extra_size); - if (err) { - kfree(extra); - return -EFAULT; - } -#ifdef WE_IOCTL_DEBUG - printk(KERN_DEBUG "%s (WE) : Got %d elem\n", - dev->name, iwr->u.data.length); -#endif /* WE_IOCTL_DEBUG */ - } - - /* Call the handler */ - ret = handler(dev, &info, &(iwr->u), extra); - - /* If we have something to return to the user */ - if (!ret && IW_IS_GET(cmd)) { - - /* Adjust for the actual length if it's variable, - * avoid leaking kernel bits outside. */ - if (!(descr->get_args & IW_PRIV_SIZE_FIXED)) { - extra_size = adjust_priv_size(descr->get_args, - &(iwr->u)); - } - - err = copy_to_user(iwr->u.data.pointer, extra, - extra_size); - if (err) - ret = -EFAULT; -#ifdef WE_IOCTL_DEBUG - printk(KERN_DEBUG "%s (WE) : Wrote %d elem\n", - dev->name, iwr->u.data.length); -#endif /* WE_IOCTL_DEBUG */ - } - - /* Cleanup - I told you it wasn't that long ;-) */ - kfree(extra); - } - - - /* Call commit handler if needed and defined */ - if(ret == -EIWCOMMIT) - ret = call_commit_handler(dev); - - return ret; -} - -/* ---------------------------------------------------------------- */ -/* - * Main IOCTl dispatcher. Called from the main networking code - * (dev_ioctl() in net/core/dev.c). - * Check the type of IOCTL and call the appropriate wrapper... - */ -int wireless_process_ioctl(struct ifreq *ifr, unsigned int cmd) -{ - struct net_device *dev; - iw_handler handler; - - /* Permissions are already checked in dev_ioctl() before calling us. - * The copy_to/from_user() of ifr is also dealt with in there */ - - /* Make sure the device exist */ - if ((dev = __dev_get_by_name(ifr->ifr_name)) == NULL) - return -ENODEV; - - /* A bunch of special cases, then the generic case... - * Note that 'cmd' is already filtered in dev_ioctl() with - * (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) */ - switch(cmd) - { - case SIOCGIWSTATS: - /* Get Wireless Stats */ - return ioctl_standard_call(dev, - ifr, - cmd, - &iw_handler_get_iwstats); - - case SIOCGIWPRIV: - /* Check if we have some wireless handlers defined */ - if(dev->wireless_handlers != NULL) { - /* We export to user space the definition of - * the private handler ourselves */ - return ioctl_standard_call(dev, - ifr, - cmd, - &iw_handler_get_private); - } - // ## Fall-through for old API ## - default: - /* Generic IOCTL */ - /* Basic check */ - if (!netif_device_present(dev)) - return -ENODEV; - /* New driver API : try to find the handler */ - handler = get_handler(dev, cmd); - if(handler != NULL) { - /* Standard and private are not the same */ - if(cmd < SIOCIWFIRSTPRIV) - return ioctl_standard_call(dev, - ifr, - cmd, - handler); - else - return ioctl_private_call(dev, - ifr, - cmd, - handler); - } - /* Old driver API : call driver ioctl handler */ - if (dev->do_ioctl) { - return dev->do_ioctl(dev, ifr, cmd); - } - return -EOPNOTSUPP; - } - /* Not reached */ - return -EINVAL; -} - -/********************** RTNETLINK REQUEST API **********************/ -/* - * The alternate user space API to configure all those Wireless Extensions - * is through RtNetlink. - * This API support only the new driver API (iw_handler). - * - * This RtNetlink API use the same query/reply model as the ioctl API. - * Maximum effort has been done to fit in the RtNetlink model, and - * we support both RtNetlink Set and RtNelink Get operations. - * On the other hand, we don't offer Dump operations because of the - * following reasons : - * o Large number of parameters, most optional - * o Large size of some parameters (> 100 bytes) - * o Each parameters need to be extracted from hardware - * o Scan requests can take seconds and disable network activity. - * Because of this high cost/overhead, we want to return only the - * parameters the user application is really interested in. - * We could offer partial Dump using the IW_DESCR_FLAG_DUMP flag. - * - * The API uses the standard RtNetlink socket. When the RtNetlink code - * find a IFLA_WIRELESS field in a RtNetlink SET_LINK request, - * it calls here. - */ - -#ifdef CONFIG_NET_WIRELESS_RTNETLINK -/* ---------------------------------------------------------------- */ -/* - * Wrapper to call a standard Wireless Extension GET handler. - * We do various checks and call the handler with the proper args. - */ -static int rtnetlink_standard_get(struct net_device * dev, - struct iw_event * request, - int request_len, - iw_handler handler, - char ** p_buf, - int * p_len) -{ - const struct iw_ioctl_description * descr = NULL; - unsigned int cmd; - union iwreq_data * wrqu; - int hdr_len; - struct iw_request_info info; - char * buffer = NULL; - int buffer_size = 0; - int ret = -EINVAL; - - /* Get the description of the Request */ - cmd = request->cmd; - if((cmd - SIOCIWFIRST) >= standard_ioctl_num) - return -EOPNOTSUPP; - descr = &(standard_ioctl[cmd - SIOCIWFIRST]); - -#ifdef WE_RTNETLINK_DEBUG - printk(KERN_DEBUG "%s (WE.r) : Found standard handler for 0x%04X\n", - dev->name, cmd); - printk(KERN_DEBUG "%s (WE.r) : Header type : %d, Token type : %d, size : %d, token : %d\n", dev->name, descr->header_type, descr->token_type, descr->token_size, descr->max_tokens); -#endif /* WE_RTNETLINK_DEBUG */ - - /* Check if wrqu is complete */ - hdr_len = event_type_size[descr->header_type]; - if(request_len < hdr_len) { -#ifdef WE_RTNETLINK_DEBUG - printk(KERN_DEBUG - "%s (WE.r) : Wireless request too short (%d)\n", - dev->name, request_len); -#endif /* WE_RTNETLINK_DEBUG */ - return -EINVAL; - } - - /* Prepare the call */ - info.cmd = cmd; - info.flags = 0; - - /* Check if we have extra data in the reply or not */ - if(descr->header_type != IW_HEADER_TYPE_POINT) { - - /* Create the kernel buffer that we will return. - * It's at an offset to match the TYPE_POINT case... */ - buffer_size = request_len + IW_EV_POINT_OFF; - buffer = kmalloc(buffer_size, GFP_KERNEL); - if (buffer == NULL) { - return -ENOMEM; - } - /* Copy event data */ - memcpy(buffer + IW_EV_POINT_OFF, request, request_len); - /* Use our own copy of wrqu */ - wrqu = (union iwreq_data *) (buffer + IW_EV_POINT_OFF - + IW_EV_LCP_PK_LEN); - - /* No extra arguments. Trivial to handle */ - ret = handler(dev, &info, wrqu, NULL); - - } else { - union iwreq_data wrqu_point; - char * extra = NULL; - int extra_size = 0; - - /* Get a temp copy of wrqu (skip pointer) */ - memcpy(((char *) &wrqu_point) + IW_EV_POINT_OFF, - ((char *) request) + IW_EV_LCP_PK_LEN, - IW_EV_POINT_LEN - IW_EV_LCP_PK_LEN); - - /* Calculate space needed by arguments. Always allocate - * for max space. Easier, and won't last long... */ - extra_size = descr->max_tokens * descr->token_size; - /* Support for very large requests */ - if((descr->flags & IW_DESCR_FLAG_NOMAX) && - (wrqu_point.data.length > descr->max_tokens)) - extra_size = (wrqu_point.data.length - * descr->token_size); - buffer_size = extra_size + IW_EV_POINT_PK_LEN + IW_EV_POINT_OFF; -#ifdef WE_RTNETLINK_DEBUG - printk(KERN_DEBUG "%s (WE.r) : Malloc %d bytes (%d bytes)\n", - dev->name, extra_size, buffer_size); -#endif /* WE_RTNETLINK_DEBUG */ - - /* Create the kernel buffer that we will return */ - buffer = kmalloc(buffer_size, GFP_KERNEL); - if (buffer == NULL) { - return -ENOMEM; - } - - /* Put wrqu in the right place (just before extra). - * Leave space for IWE header and dummy pointer... - * Note that IW_EV_LCP_PK_LEN==4 bytes, so it's still aligned. - */ - memcpy(buffer + IW_EV_LCP_PK_LEN + IW_EV_POINT_OFF, - ((char *) &wrqu_point) + IW_EV_POINT_OFF, - IW_EV_POINT_PK_LEN - IW_EV_LCP_PK_LEN); - wrqu = (union iwreq_data *) (buffer + IW_EV_LCP_PK_LEN); - - /* Extra comes logically after that. Offset +12 bytes. */ - extra = buffer + IW_EV_POINT_OFF + IW_EV_POINT_PK_LEN; - - /* Call the handler */ - ret = handler(dev, &info, wrqu, extra); - - /* Calculate real returned length */ - extra_size = (wrqu->data.length * descr->token_size); - /* Re-adjust reply size */ - request->len = extra_size + IW_EV_POINT_PK_LEN; - - /* Put the iwe header where it should, i.e. scrap the - * dummy pointer. */ - memcpy(buffer + IW_EV_POINT_OFF, request, IW_EV_LCP_PK_LEN); - -#ifdef WE_RTNETLINK_DEBUG - printk(KERN_DEBUG "%s (WE.r) : Reply 0x%04X, hdr_len %d, tokens %d, extra_size %d, buffer_size %d\n", dev->name, cmd, hdr_len, wrqu->data.length, extra_size, buffer_size); -#endif /* WE_RTNETLINK_DEBUG */ - - /* Check if there is enough buffer up there */ - if(wrqu_point.data.length < wrqu->data.length) - ret = -E2BIG; - } - - /* Return the buffer to the caller */ - if (!ret) { - *p_buf = buffer; - *p_len = request->len; - } else { - /* Cleanup */ - if(buffer) - kfree(buffer); - } - - return ret; -} - -/* ---------------------------------------------------------------- */ -/* - * Wrapper to call a standard Wireless Extension SET handler. - * We do various checks and call the handler with the proper args. - */ -static inline int rtnetlink_standard_set(struct net_device * dev, - struct iw_event * request, - int request_len, - iw_handler handler) -{ - const struct iw_ioctl_description * descr = NULL; - unsigned int cmd; - union iwreq_data * wrqu; - union iwreq_data wrqu_point; - int hdr_len; - char * extra = NULL; - int extra_size = 0; - struct iw_request_info info; - int ret = -EINVAL; - - /* Get the description of the Request */ - cmd = request->cmd; - if((cmd - SIOCIWFIRST) >= standard_ioctl_num) - return -EOPNOTSUPP; - descr = &(standard_ioctl[cmd - SIOCIWFIRST]); - -#ifdef WE_RTNETLINK_DEBUG - printk(KERN_DEBUG "%s (WE.r) : Found standard SET handler for 0x%04X\n", - dev->name, cmd); - printk(KERN_DEBUG "%s (WE.r) : Header type : %d, Token type : %d, size : %d, token : %d\n", dev->name, descr->header_type, descr->token_type, descr->token_size, descr->max_tokens); -#endif /* WE_RTNETLINK_DEBUG */ - - /* Extract fixed header from request. This is properly aligned. */ - wrqu = (union iwreq_data *) (((char *) request) + IW_EV_LCP_PK_LEN); - - /* Check if wrqu is complete */ - hdr_len = event_type_pk_size[descr->header_type]; - if(request_len < hdr_len) { -#ifdef WE_RTNETLINK_DEBUG - printk(KERN_DEBUG - "%s (WE.r) : Wireless request too short (%d)\n", - dev->name, request_len); -#endif /* WE_RTNETLINK_DEBUG */ - return -EINVAL; - } - - /* Prepare the call */ - info.cmd = cmd; - info.flags = 0; - - /* Check if we have extra data in the request or not */ - if(descr->header_type != IW_HEADER_TYPE_POINT) { - - /* No extra arguments. Trivial to handle */ - ret = handler(dev, &info, wrqu, NULL); - - } else { - int extra_len; - - /* Put wrqu in the right place (skip pointer) */ - memcpy(((char *) &wrqu_point) + IW_EV_POINT_OFF, - wrqu, IW_EV_POINT_PK_LEN - IW_EV_LCP_PK_LEN); - /* Don't forget about the event code... */ - wrqu = &wrqu_point; - - /* Check if number of token fits within bounds */ - if(wrqu_point.data.length > descr->max_tokens) - return -E2BIG; - if(wrqu_point.data.length < descr->min_tokens) - return -EINVAL; - - /* Real length of payload */ - extra_len = wrqu_point.data.length * descr->token_size; - - /* Check if request is self consistent */ - if((request_len - hdr_len) < extra_len) { -#ifdef WE_RTNETLINK_DEBUG - printk(KERN_DEBUG "%s (WE.r) : Wireless request data too short (%d)\n", - dev->name, extra_size); -#endif /* WE_RTNETLINK_DEBUG */ - return -EINVAL; - } - -#ifdef WE_RTNETLINK_DEBUG - printk(KERN_DEBUG "%s (WE.r) : Malloc %d bytes\n", - dev->name, extra_size); -#endif /* WE_RTNETLINK_DEBUG */ - - /* Always allocate for max space. Easier, and won't last - * long... */ - extra_size = descr->max_tokens * descr->token_size; - extra = kmalloc(extra_size, GFP_KERNEL); - if (extra == NULL) - return -ENOMEM; - - /* Copy extra in aligned buffer */ - memcpy(extra, ((char *) request) + hdr_len, extra_len); - - /* Call the handler */ - ret = handler(dev, &info, &wrqu_point, extra); - } - -#ifdef WE_SET_EVENT - /* Generate an event to notify listeners of the change */ - if((descr->flags & IW_DESCR_FLAG_EVENT) && - ((ret == 0) || (ret == -EIWCOMMIT))) { - if(descr->flags & IW_DESCR_FLAG_RESTRICT) - /* If the event is restricted, don't - * export the payload */ - wireless_send_event(dev, cmd, wrqu, NULL); - else - wireless_send_event(dev, cmd, wrqu, extra); - } -#endif /* WE_SET_EVENT */ - - /* Cleanup - I told you it wasn't that long ;-) */ - if(extra) - kfree(extra); - - /* Call commit handler if needed and defined */ - if(ret == -EIWCOMMIT) - ret = call_commit_handler(dev); - - return ret; -} - -/* ---------------------------------------------------------------- */ -/* - * Wrapper to call a private Wireless Extension GET handler. - * Same as above... - * It's not as nice and slimline as the standard wrapper. The cause - * is struct iw_priv_args, which was not really designed for the - * job we are going here. - * - * IMPORTANT : This function prevent to set and get data on the same - * IOCTL and enforce the SET/GET convention. Not doing it would be - * far too hairy... - * If you need to set and get data at the same time, please don't use - * a iw_handler but process it in your ioctl handler (i.e. use the - * old driver API). - */ -static inline int rtnetlink_private_get(struct net_device * dev, - struct iw_event * request, - int request_len, - iw_handler handler, - char ** p_buf, - int * p_len) -{ - const struct iw_priv_args * descr = NULL; - unsigned int cmd; - union iwreq_data * wrqu; - int hdr_len; - struct iw_request_info info; - int extra_size = 0; - int i; - char * buffer = NULL; - int buffer_size = 0; - int ret = -EINVAL; - - /* Get the description of the Request */ - cmd = request->cmd; - for(i = 0; i < dev->wireless_handlers->num_private_args; i++) - if(cmd == dev->wireless_handlers->private_args[i].cmd) { - descr = &(dev->wireless_handlers->private_args[i]); - break; - } - if(descr == NULL) - return -EOPNOTSUPP; - -#ifdef WE_RTNETLINK_DEBUG - printk(KERN_DEBUG "%s (WE.r) : Found private handler for 0x%04X\n", - dev->name, cmd); - printk(KERN_DEBUG "%s (WE.r) : Name %s, set %X, get %X\n", - dev->name, descr->name, descr->set_args, descr->get_args); -#endif /* WE_RTNETLINK_DEBUG */ - - /* Compute the max size of the get arguments */ - extra_size = get_priv_size(descr->get_args); - - /* Does it fits in wrqu ? */ - if((descr->get_args & IW_PRIV_SIZE_FIXED) && - (extra_size <= IFNAMSIZ)) { - hdr_len = extra_size; - extra_size = 0; - } else { - hdr_len = IW_EV_POINT_PK_LEN; - } - - /* Check if wrqu is complete */ - if(request_len < hdr_len) { -#ifdef WE_RTNETLINK_DEBUG - printk(KERN_DEBUG - "%s (WE.r) : Wireless request too short (%d)\n", - dev->name, request_len); -#endif /* WE_RTNETLINK_DEBUG */ - return -EINVAL; - } - - /* Prepare the call */ - info.cmd = cmd; - info.flags = 0; - - /* Check if we have a pointer to user space data or not. */ - if(extra_size == 0) { - - /* Create the kernel buffer that we will return. - * It's at an offset to match the TYPE_POINT case... */ - buffer_size = request_len + IW_EV_POINT_OFF; - buffer = kmalloc(buffer_size, GFP_KERNEL); - if (buffer == NULL) { - return -ENOMEM; - } - /* Copy event data */ - memcpy(buffer + IW_EV_POINT_OFF, request, request_len); - /* Use our own copy of wrqu */ - wrqu = (union iwreq_data *) (buffer + IW_EV_POINT_OFF - + IW_EV_LCP_PK_LEN); - - /* No extra arguments. Trivial to handle */ - ret = handler(dev, &info, wrqu, (char *) wrqu); - - } else { - char * extra; - - /* Buffer for full reply */ - buffer_size = extra_size + IW_EV_POINT_PK_LEN + IW_EV_POINT_OFF; - -#ifdef WE_RTNETLINK_DEBUG - printk(KERN_DEBUG "%s (WE.r) : Malloc %d bytes (%d bytes)\n", - dev->name, extra_size, buffer_size); -#endif /* WE_RTNETLINK_DEBUG */ - - /* Create the kernel buffer that we will return */ - buffer = kmalloc(buffer_size, GFP_KERNEL); - if (buffer == NULL) { - return -ENOMEM; - } - - /* Put wrqu in the right place (just before extra). - * Leave space for IWE header and dummy pointer... - * Note that IW_EV_LCP_PK_LEN==4 bytes, so it's still aligned. - */ - memcpy(buffer + IW_EV_LCP_PK_LEN + IW_EV_POINT_OFF, - ((char *) request) + IW_EV_LCP_PK_LEN, - IW_EV_POINT_PK_LEN - IW_EV_LCP_PK_LEN); - wrqu = (union iwreq_data *) (buffer + IW_EV_LCP_PK_LEN); - - /* Extra comes logically after that. Offset +12 bytes. */ - extra = buffer + IW_EV_POINT_OFF + IW_EV_POINT_PK_LEN; - - /* Call the handler */ - ret = handler(dev, &info, wrqu, extra); - - /* Adjust for the actual length if it's variable, - * avoid leaking kernel bits outside. */ - if (!(descr->get_args & IW_PRIV_SIZE_FIXED)) - extra_size = adjust_priv_size(descr->get_args, wrqu); - /* Re-adjust reply size */ - request->len = extra_size + IW_EV_POINT_PK_LEN; - - /* Put the iwe header where it should, i.e. scrap the - * dummy pointer. */ - memcpy(buffer + IW_EV_POINT_OFF, request, IW_EV_LCP_PK_LEN); - -#ifdef WE_RTNETLINK_DEBUG - printk(KERN_DEBUG "%s (WE.r) : Reply 0x%04X, hdr_len %d, tokens %d, extra_size %d, buffer_size %d\n", dev->name, cmd, hdr_len, wrqu->data.length, extra_size, buffer_size); -#endif /* WE_RTNETLINK_DEBUG */ - } - - /* Return the buffer to the caller */ - if (!ret) { - *p_buf = buffer; - *p_len = request->len; - } else { - /* Cleanup */ - if(buffer) - kfree(buffer); - } - - return ret; -} - -/* ---------------------------------------------------------------- */ -/* - * Wrapper to call a private Wireless Extension SET handler. - * Same as above... - * It's not as nice and slimline as the standard wrapper. The cause - * is struct iw_priv_args, which was not really designed for the - * job we are going here. - * - * IMPORTANT : This function prevent to set and get data on the same - * IOCTL and enforce the SET/GET convention. Not doing it would be - * far too hairy... - * If you need to set and get data at the same time, please don't use - * a iw_handler but process it in your ioctl handler (i.e. use the - * old driver API). - */ -static inline int rtnetlink_private_set(struct net_device * dev, - struct iw_event * request, - int request_len, - iw_handler handler) -{ - const struct iw_priv_args * descr = NULL; - unsigned int cmd; - union iwreq_data * wrqu; - union iwreq_data wrqu_point; - int hdr_len; - char * extra = NULL; - int extra_size = 0; - int offset = 0; /* For sub-ioctls */ - struct iw_request_info info; - int i; - int ret = -EINVAL; - - /* Get the description of the Request */ - cmd = request->cmd; - for(i = 0; i < dev->wireless_handlers->num_private_args; i++) - if(cmd == dev->wireless_handlers->private_args[i].cmd) { - descr = &(dev->wireless_handlers->private_args[i]); - break; - } - if(descr == NULL) - return -EOPNOTSUPP; - -#ifdef WE_RTNETLINK_DEBUG - printk(KERN_DEBUG "%s (WE.r) : Found private handler for 0x%04X\n", - ifr->ifr_name, cmd); - printk(KERN_DEBUG "%s (WE.r) : Name %s, set %X, get %X\n", - dev->name, descr->name, descr->set_args, descr->get_args); -#endif /* WE_RTNETLINK_DEBUG */ - - /* Compute the size of the set arguments */ - /* Check for sub-ioctl handler */ - if(descr->name[0] == '\0') - /* Reserve one int for sub-ioctl index */ - offset = sizeof(__u32); - - /* Size of set arguments */ - extra_size = get_priv_size(descr->set_args); - - /* Does it fits in wrqu ? */ - if((descr->set_args & IW_PRIV_SIZE_FIXED) && - (extra_size <= IFNAMSIZ)) { - hdr_len = IW_EV_LCP_PK_LEN + extra_size; - extra_size = 0; - } else { - hdr_len = IW_EV_POINT_PK_LEN; - } - - /* Extract fixed header from request. This is properly aligned. */ - wrqu = (union iwreq_data *) (((char *) request) + IW_EV_LCP_PK_LEN); - - /* Check if wrqu is complete */ - if(request_len < hdr_len) { -#ifdef WE_RTNETLINK_DEBUG - printk(KERN_DEBUG - "%s (WE.r) : Wireless request too short (%d)\n", - dev->name, request_len); -#endif /* WE_RTNETLINK_DEBUG */ - return -EINVAL; - } - - /* Prepare the call */ - info.cmd = cmd; - info.flags = 0; - - /* Check if we have a pointer to user space data or not. */ - if(extra_size == 0) { - - /* No extra arguments. Trivial to handle */ - ret = handler(dev, &info, wrqu, (char *) wrqu); - - } else { - int extra_len; - - /* Put wrqu in the right place (skip pointer) */ - memcpy(((char *) &wrqu_point) + IW_EV_POINT_OFF, - wrqu, IW_EV_POINT_PK_LEN - IW_EV_LCP_PK_LEN); - - /* Does it fits within bounds ? */ - if(wrqu_point.data.length > (descr->set_args & - IW_PRIV_SIZE_MASK)) - return -E2BIG; - - /* Real length of payload */ - extra_len = adjust_priv_size(descr->set_args, &wrqu_point); - - /* Check if request is self consistent */ - if((request_len - hdr_len) < extra_len) { -#ifdef WE_RTNETLINK_DEBUG - printk(KERN_DEBUG "%s (WE.r) : Wireless request data too short (%d)\n", - dev->name, extra_size); -#endif /* WE_RTNETLINK_DEBUG */ - return -EINVAL; - } - -#ifdef WE_RTNETLINK_DEBUG - printk(KERN_DEBUG "%s (WE.r) : Malloc %d bytes\n", - dev->name, extra_size); -#endif /* WE_RTNETLINK_DEBUG */ - - /* Always allocate for max space. Easier, and won't last - * long... */ - extra = kmalloc(extra_size, GFP_KERNEL); - if (extra == NULL) - return -ENOMEM; - - /* Copy extra in aligned buffer */ - memcpy(extra, ((char *) request) + hdr_len, extra_len); - - /* Call the handler */ - ret = handler(dev, &info, &wrqu_point, extra); - - /* Cleanup - I told you it wasn't that long ;-) */ - kfree(extra); - } - - /* Call commit handler if needed and defined */ - if(ret == -EIWCOMMIT) - ret = call_commit_handler(dev); - - return ret; -} - -/* ---------------------------------------------------------------- */ -/* - * Main RtNetlink dispatcher. Called from the main networking code - * (do_getlink() in net/core/rtnetlink.c). - * Check the type of Request and call the appropriate wrapper... - */ -int wireless_rtnetlink_get(struct net_device * dev, - char * data, - int len, - char ** p_buf, - int * p_len) -{ - struct iw_event * request = (struct iw_event *) data; - iw_handler handler; - - /* Check length */ - if(len < IW_EV_LCP_PK_LEN) { - printk(KERN_DEBUG "%s (WE.r) : RtNetlink request too short (%d)\n", - dev->name, len); - return -EINVAL; - } - - /* ReCheck length (len may have padding) */ - if(request->len > len) { - printk(KERN_DEBUG "%s (WE.r) : RtNetlink request len invalid (%d-%d)\n", - dev->name, request->len, len); - return -EINVAL; - } - - /* Only accept GET requests in here */ - if(!IW_IS_GET(request->cmd)) - return -EOPNOTSUPP; - - /* If command is `get the encoding parameters', check if - * the user has the right to do it */ - if (request->cmd == SIOCGIWENCODE || - request->cmd == SIOCGIWENCODEEXT) { - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - } - - /* Special cases */ - if(request->cmd == SIOCGIWSTATS) - /* Get Wireless Stats */ - return rtnetlink_standard_get(dev, - request, - request->len, - &iw_handler_get_iwstats, - p_buf, p_len); - if(request->cmd == SIOCGIWPRIV) { - /* Check if we have some wireless handlers defined */ - if(dev->wireless_handlers == NULL) - return -EOPNOTSUPP; - /* Get Wireless Stats */ - return rtnetlink_standard_get(dev, - request, - request->len, - &iw_handler_get_private, - p_buf, p_len); - } - - /* Basic check */ - if (!netif_device_present(dev)) - return -ENODEV; - - /* Try to find the handler */ - handler = get_handler(dev, request->cmd); - if(handler != NULL) { - /* Standard and private are not the same */ - if(request->cmd < SIOCIWFIRSTPRIV) - return rtnetlink_standard_get(dev, - request, - request->len, - handler, - p_buf, p_len); - else - return rtnetlink_private_get(dev, - request, - request->len, - handler, - p_buf, p_len); - } - - return -EOPNOTSUPP; -} - -/* ---------------------------------------------------------------- */ -/* - * Main RtNetlink dispatcher. Called from the main networking code - * (do_setlink() in net/core/rtnetlink.c). - * Check the type of Request and call the appropriate wrapper... - */ -int wireless_rtnetlink_set(struct net_device * dev, - char * data, - int len) -{ - struct iw_event * request = (struct iw_event *) data; - iw_handler handler; - - /* Check length */ - if(len < IW_EV_LCP_PK_LEN) { - printk(KERN_DEBUG "%s (WE.r) : RtNetlink request too short (%d)\n", - dev->name, len); - return -EINVAL; - } - - /* ReCheck length (len may have padding) */ - if(request->len > len) { - printk(KERN_DEBUG "%s (WE.r) : RtNetlink request len invalid (%d-%d)\n", - dev->name, request->len, len); - return -EINVAL; - } - - /* Only accept SET requests in here */ - if(!IW_IS_SET(request->cmd)) - return -EOPNOTSUPP; - - /* Basic check */ - if (!netif_device_present(dev)) - return -ENODEV; - - /* New driver API : try to find the handler */ - handler = get_handler(dev, request->cmd); - if(handler != NULL) { - /* Standard and private are not the same */ - if(request->cmd < SIOCIWFIRSTPRIV) - return rtnetlink_standard_set(dev, - request, - request->len, - handler); - else - return rtnetlink_private_set(dev, - request, - request->len, - handler); - } - - return -EOPNOTSUPP; -} -#endif /* CONFIG_NET_WIRELESS_RTNETLINK */ - - -/************************* EVENT PROCESSING *************************/ -/* - * Process events generated by the wireless layer or the driver. - * Most often, the event will be propagated through rtnetlink - */ - -#ifdef WE_EVENT_RTNETLINK -/* ---------------------------------------------------------------- */ -/* - * Locking... - * ---------- - * - * Thanks to Herbert Xu <herbert@gondor.apana.org.au> for fixing - * the locking issue in here and implementing this code ! - * - * The issue : wireless_send_event() is often called in interrupt context, - * while the Netlink layer can never be called in interrupt context. - * The fully formed RtNetlink events are queued, and then a tasklet is run - * to feed those to Netlink. - * The skb_queue is interrupt safe, and its lock is not held while calling - * Netlink, so there is no possibility of dealock. - * Jean II - */ - -static struct sk_buff_head wireless_nlevent_queue; - -static int __init wireless_nlevent_init(void) -{ - skb_queue_head_init(&wireless_nlevent_queue); - return 0; -} - -subsys_initcall(wireless_nlevent_init); - -static void wireless_nlevent_process(unsigned long data) -{ - struct sk_buff *skb; - - while ((skb = skb_dequeue(&wireless_nlevent_queue))) - rtnl_notify(skb, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); -} - -static DECLARE_TASKLET(wireless_nlevent_tasklet, wireless_nlevent_process, 0); - -/* ---------------------------------------------------------------- */ -/* - * Fill a rtnetlink message with our event data. - * Note that we propage only the specified event and don't dump the - * current wireless config. Dumping the wireless config is far too - * expensive (for each parameter, the driver need to query the hardware). - */ -static inline int rtnetlink_fill_iwinfo(struct sk_buff * skb, - struct net_device * dev, - int type, - char * event, - int event_len) -{ - struct ifinfomsg *r; - struct nlmsghdr *nlh; - unsigned char *b = skb->tail; - - nlh = NLMSG_PUT(skb, 0, 0, type, sizeof(*r)); - r = NLMSG_DATA(nlh); - r->ifi_family = AF_UNSPEC; - r->__ifi_pad = 0; - r->ifi_type = dev->type; - r->ifi_index = dev->ifindex; - r->ifi_flags = dev_get_flags(dev); - r->ifi_change = 0; /* Wireless changes don't affect those flags */ - - /* Add the wireless events in the netlink packet */ - RTA_PUT(skb, IFLA_WIRELESS, event_len, event); - - nlh->nlmsg_len = skb->tail - b; - return skb->len; - -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; -} - -/* ---------------------------------------------------------------- */ -/* - * Create and broadcast and send it on the standard rtnetlink socket - * This is a pure clone rtmsg_ifinfo() in net/core/rtnetlink.c - * Andrzej Krzysztofowicz mandated that I used a IFLA_XXX field - * within a RTM_NEWLINK event. - */ -static inline void rtmsg_iwinfo(struct net_device * dev, - char * event, - int event_len) -{ - struct sk_buff *skb; - int size = NLMSG_GOODSIZE; - - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) - return; - - if (rtnetlink_fill_iwinfo(skb, dev, RTM_NEWLINK, - event, event_len) < 0) { - kfree_skb(skb); - return; - } - NETLINK_CB(skb).dst_group = RTNLGRP_LINK; - skb_queue_tail(&wireless_nlevent_queue, skb); - tasklet_schedule(&wireless_nlevent_tasklet); -} - -#endif /* WE_EVENT_RTNETLINK */ - -/* ---------------------------------------------------------------- */ -/* - * Main event dispatcher. Called from other parts and drivers. - * Send the event on the appropriate channels. - * May be called from interrupt context. - */ -void wireless_send_event(struct net_device * dev, - unsigned int cmd, - union iwreq_data * wrqu, - char * extra) -{ - const struct iw_ioctl_description * descr = NULL; - int extra_len = 0; - struct iw_event *event; /* Mallocated whole event */ - int event_len; /* Its size */ - 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 */ - - /* Get the description of the Event */ - if(cmd <= SIOCIWLAST) { - cmd_index = cmd - SIOCIWFIRST; - if(cmd_index < standard_ioctl_num) - descr = &(standard_ioctl[cmd_index]); - } else { - cmd_index = cmd - IWEVFIRST; - if(cmd_index < standard_event_num) - descr = &(standard_event[cmd_index]); - } - /* Don't accept unknown events */ - if(descr == NULL) { - /* Note : we don't return an error to the driver, because - * the driver would not know what to do about it. It can't - * return an error to the user, because the event is not - * initiated by a user request. - * The best the driver could do is to log an error message. - * We will do it ourselves instead... - */ - printk(KERN_ERR "%s (WE) : Invalid/Unknown Wireless Event (0x%04X)\n", - dev->name, cmd); - return; - } -#ifdef WE_EVENT_DEBUG - printk(KERN_DEBUG "%s (WE) : Got event 0x%04X\n", - dev->name, cmd); - printk(KERN_DEBUG "%s (WE) : Header type : %d, Token type : %d, size : %d, token : %d\n", dev->name, descr->header_type, descr->token_type, descr->token_size, descr->max_tokens); -#endif /* WE_EVENT_DEBUG */ - - /* Check extra parameters and set extra_len */ - if(descr->header_type == IW_HEADER_TYPE_POINT) { - /* Check if number of token fits within bounds */ - if(wrqu->data.length > descr->max_tokens) { - printk(KERN_ERR "%s (WE) : Wireless Event too big (%d)\n", dev->name, wrqu->data.length); - return; - } - if(wrqu->data.length < descr->min_tokens) { - printk(KERN_ERR "%s (WE) : Wireless Event too small (%d)\n", dev->name, wrqu->data.length); - return; - } - /* Calculate extra_len - extra is NULL for restricted events */ - if(extra != NULL) - extra_len = wrqu->data.length * descr->token_size; - /* Always at an offset in wrqu */ - wrqu_off = IW_EV_POINT_OFF; -#ifdef WE_EVENT_DEBUG - printk(KERN_DEBUG "%s (WE) : Event 0x%04X, tokens %d, extra_len %d\n", dev->name, cmd, wrqu->data.length, extra_len); -#endif /* WE_EVENT_DEBUG */ - } - - /* Total length of the event */ - hdr_len = event_type_size[descr->header_type]; - event_len = hdr_len + extra_len; - -#ifdef WE_EVENT_DEBUG - printk(KERN_DEBUG "%s (WE) : Event 0x%04X, hdr_len %d, wrqu_off %d, event_len %d\n", dev->name, cmd, hdr_len, wrqu_off, event_len); -#endif /* WE_EVENT_DEBUG */ - - /* Create temporary buffer to hold the event */ - event = kmalloc(event_len, GFP_ATOMIC); - if(event == NULL) - return; - - /* Fill event */ - event->len = event_len; - event->cmd = cmd; - memcpy(&event->u, ((char *) wrqu) + wrqu_off, hdr_len - IW_EV_LCP_LEN); - if(extra != NULL) - memcpy(((char *) event) + hdr_len, extra, extra_len); - -#ifdef WE_EVENT_RTNETLINK - /* Send via the RtNetlink event channel */ - rtmsg_iwinfo(dev, (char *) event, event_len); -#endif /* WE_EVENT_RTNETLINK */ - - /* Cleanup */ - kfree(event); - - return; /* Always success, I guess ;-) */ -} - -/********************** ENHANCED IWSPY SUPPORT **********************/ -/* - * In the old days, the driver was handling spy support all by itself. - * Now, the driver can delegate this task to Wireless Extensions. - * It needs to use those standard spy iw_handler in struct iw_handler_def, - * push data to us via wireless_spy_update() and include struct iw_spy_data - * in its private part (and export it in net_device->wireless_data->spy_data). - * One of the main advantage of centralising spy support here is that - * it becomes much easier to improve and extend it without having to touch - * the drivers. One example is the addition of the Spy-Threshold events. - */ - -/* ---------------------------------------------------------------- */ -/* - * Return the pointer to the spy data in the driver. - * Because this is called on the Rx path via wireless_spy_update(), - * we want it to be efficient... - */ -static inline struct iw_spy_data * get_spydata(struct net_device *dev) -{ - /* This is the new way */ - if(dev->wireless_data) - return(dev->wireless_data->spy_data); - return NULL; -} - -/*------------------------------------------------------------------*/ -/* - * Standard Wireless Handler : set Spy List - */ -int iw_handler_set_spy(struct net_device * dev, - struct iw_request_info * info, - union iwreq_data * wrqu, - char * extra) -{ - struct iw_spy_data * spydata = get_spydata(dev); - struct sockaddr * address = (struct sockaddr *) extra; - - /* Make sure driver is not buggy or using the old API */ - if(!spydata) - return -EOPNOTSUPP; - - /* Disable spy collection while we copy the addresses. - * While we copy addresses, any call to wireless_spy_update() - * will NOP. This is OK, as anyway the addresses are changing. */ - spydata->spy_number = 0; - - /* We want to operate without locking, because wireless_spy_update() - * most likely will happen in the interrupt handler, and therefore - * have its own locking constraints and needs performance. - * The rtnl_lock() make sure we don't race with the other iw_handlers. - * This make sure wireless_spy_update() "see" that the spy list - * is temporarily disabled. */ - smp_wmb(); - - /* Are there are addresses to copy? */ - if(wrqu->data.length > 0) { - int i; - - /* Copy addresses */ - for(i = 0; i < wrqu->data.length; i++) - memcpy(spydata->spy_address[i], address[i].sa_data, - ETH_ALEN); - /* Reset stats */ - memset(spydata->spy_stat, 0, - sizeof(struct iw_quality) * IW_MAX_SPY); - -#ifdef WE_SPY_DEBUG - printk(KERN_DEBUG "iw_handler_set_spy() : wireless_data %p, spydata %p, num %d\n", dev->wireless_data, spydata, wrqu->data.length); - for (i = 0; i < wrqu->data.length; i++) - printk(KERN_DEBUG - "%02X:%02X:%02X:%02X:%02X:%02X \n", - spydata->spy_address[i][0], - spydata->spy_address[i][1], - spydata->spy_address[i][2], - spydata->spy_address[i][3], - spydata->spy_address[i][4], - spydata->spy_address[i][5]); -#endif /* WE_SPY_DEBUG */ - } - - /* Make sure above is updated before re-enabling */ - smp_wmb(); - - /* Enable addresses */ - spydata->spy_number = wrqu->data.length; - - return 0; -} - -/*------------------------------------------------------------------*/ -/* - * Standard Wireless Handler : get Spy List - */ -int iw_handler_get_spy(struct net_device * dev, - struct iw_request_info * info, - union iwreq_data * wrqu, - char * extra) -{ - struct iw_spy_data * spydata = get_spydata(dev); - struct sockaddr * address = (struct sockaddr *) extra; - int i; - - /* Make sure driver is not buggy or using the old API */ - if(!spydata) - return -EOPNOTSUPP; - - wrqu->data.length = spydata->spy_number; - - /* Copy addresses. */ - for(i = 0; i < spydata->spy_number; i++) { - memcpy(address[i].sa_data, spydata->spy_address[i], ETH_ALEN); - address[i].sa_family = AF_UNIX; - } - /* Copy stats to the user buffer (just after). */ - if(spydata->spy_number > 0) - memcpy(extra + (sizeof(struct sockaddr) *spydata->spy_number), - spydata->spy_stat, - sizeof(struct iw_quality) * spydata->spy_number); - /* Reset updated flags. */ - for(i = 0; i < spydata->spy_number; i++) - spydata->spy_stat[i].updated &= ~IW_QUAL_ALL_UPDATED; - return 0; -} - -/*------------------------------------------------------------------*/ -/* - * Standard Wireless Handler : set spy threshold - */ -int iw_handler_set_thrspy(struct net_device * dev, - struct iw_request_info *info, - union iwreq_data * wrqu, - char * extra) -{ - struct iw_spy_data * spydata = get_spydata(dev); - struct iw_thrspy * threshold = (struct iw_thrspy *) extra; - - /* Make sure driver is not buggy or using the old API */ - if(!spydata) - return -EOPNOTSUPP; - - /* Just do it */ - memcpy(&(spydata->spy_thr_low), &(threshold->low), - 2 * sizeof(struct iw_quality)); - - /* Clear flag */ - memset(spydata->spy_thr_under, '\0', sizeof(spydata->spy_thr_under)); - -#ifdef WE_SPY_DEBUG - printk(KERN_DEBUG "iw_handler_set_thrspy() : low %d ; high %d\n", spydata->spy_thr_low.level, spydata->spy_thr_high.level); -#endif /* WE_SPY_DEBUG */ - - return 0; -} - -/*------------------------------------------------------------------*/ -/* - * Standard Wireless Handler : get spy threshold - */ -int iw_handler_get_thrspy(struct net_device * dev, - struct iw_request_info *info, - union iwreq_data * wrqu, - char * extra) -{ - struct iw_spy_data * spydata = get_spydata(dev); - struct iw_thrspy * threshold = (struct iw_thrspy *) extra; - - /* Make sure driver is not buggy or using the old API */ - if(!spydata) - return -EOPNOTSUPP; - - /* Just do it */ - memcpy(&(threshold->low), &(spydata->spy_thr_low), - 2 * sizeof(struct iw_quality)); - - return 0; -} - -/*------------------------------------------------------------------*/ -/* - * Prepare and send a Spy Threshold event - */ -static void iw_send_thrspy_event(struct net_device * dev, - struct iw_spy_data * spydata, - unsigned char * address, - struct iw_quality * wstats) -{ - union iwreq_data wrqu; - struct iw_thrspy threshold; - - /* Init */ - wrqu.data.length = 1; - wrqu.data.flags = 0; - /* Copy address */ - memcpy(threshold.addr.sa_data, address, ETH_ALEN); - threshold.addr.sa_family = ARPHRD_ETHER; - /* Copy stats */ - memcpy(&(threshold.qual), wstats, sizeof(struct iw_quality)); - /* Copy also thresholds */ - memcpy(&(threshold.low), &(spydata->spy_thr_low), - 2 * sizeof(struct iw_quality)); - -#ifdef WE_SPY_DEBUG - printk(KERN_DEBUG "iw_send_thrspy_event() : address %02X:%02X:%02X:%02X:%02X:%02X, level %d, up = %d\n", - threshold.addr.sa_data[0], - threshold.addr.sa_data[1], - threshold.addr.sa_data[2], - threshold.addr.sa_data[3], - threshold.addr.sa_data[4], - threshold.addr.sa_data[5], threshold.qual.level); -#endif /* WE_SPY_DEBUG */ - - /* Send event to user space */ - wireless_send_event(dev, SIOCGIWTHRSPY, &wrqu, (char *) &threshold); -} - -/* ---------------------------------------------------------------- */ -/* - * Call for the driver to update the spy data. - * For now, the spy data is a simple array. As the size of the array is - * small, this is good enough. If we wanted to support larger number of - * spy addresses, we should use something more efficient... - */ -void wireless_spy_update(struct net_device * dev, - unsigned char * address, - struct iw_quality * wstats) -{ - struct iw_spy_data * spydata = get_spydata(dev); - int i; - int match = -1; - - /* Make sure driver is not buggy or using the old API */ - if(!spydata) - return; - -#ifdef WE_SPY_DEBUG - printk(KERN_DEBUG "wireless_spy_update() : wireless_data %p, spydata %p, address %02X:%02X:%02X:%02X:%02X:%02X\n", dev->wireless_data, spydata, address[0], address[1], address[2], address[3], address[4], address[5]); -#endif /* WE_SPY_DEBUG */ - - /* Update all records that match */ - for(i = 0; i < spydata->spy_number; i++) - if(!compare_ether_addr(address, spydata->spy_address[i])) { - memcpy(&(spydata->spy_stat[i]), wstats, - sizeof(struct iw_quality)); - match = i; - } - - /* Generate an event if we cross the spy threshold. - * To avoid event storms, we have a simple hysteresis : we generate - * event only when we go under the low threshold or above the - * high threshold. */ - if(match >= 0) { - if(spydata->spy_thr_under[match]) { - if(wstats->level > spydata->spy_thr_high.level) { - spydata->spy_thr_under[match] = 0; - iw_send_thrspy_event(dev, spydata, - address, wstats); - } - } else { - if(wstats->level < spydata->spy_thr_low.level) { - spydata->spy_thr_under[match] = 1; - iw_send_thrspy_event(dev, spydata, - address, wstats); - } - } - } -} - -EXPORT_SYMBOL(iw_handler_get_spy); -EXPORT_SYMBOL(iw_handler_get_thrspy); -EXPORT_SYMBOL(iw_handler_set_spy); -EXPORT_SYMBOL(iw_handler_set_thrspy); -EXPORT_SYMBOL(wireless_send_event); -EXPORT_SYMBOL(wireless_spy_update); |