patch-2.2.7 linux/net/ipv6/ip6_flowlabel.c

• Lines: 621
• Date: Fri Apr 23 18:39:47 1999
• Orig file: v2.2.6/linux/net/ipv6/ip6_flowlabel.c
• Orig date: Wed Dec 31 16:00:00 1969

diff -u --recursive --new-file v2.2.6/linux/net/ipv6/ip6_flowlabel.c linux/net/ipv6/ip6_flowlabel.c
@@ -0,0 +1,620 @@
+/*
+ *	ip6_flowlabel.c		IPv6 flowlabel manager.
+ *
+ *	This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ *
+ *	Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+
+#include <linux/config.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <linux/if_arp.h>
+#include <linux/in6.h>
+#include <linux/route.h>
+#include <linux/proc_fs.h>
+
+#include <net/sock.h>
+
+#include <net/ipv6.h>
+#include <net/ndisc.h>
+#include <net/protocol.h>
+#include <net/ip6_route.h>
+#include <net/addrconf.h>
+#include <net/rawv6.h>
+#include <net/icmp.h>
+#include <net/transp_v6.h>
+
+#include <asm/uaccess.h>
+
+#define FL_MIN_LINGER	6	/* Minimal linger. It is set to 6sec specified
+				   in old IPv6 RFC. Well, it was reasonable value.
+				 */
+#define FL_MAX_LINGER	60	/* Maximal linger timeout */
+
+/* FL hash table */
+
+#define FL_MAX_PER_SOCK	32
+#define FL_MAX_SIZE	4096
+#define FL_HASH_MASK	255
+#define FL_HASH(l)	(ntohl(l)&FL_HASH_MASK)
+
+static atomic_t fl_size = ATOMIC_INIT(0);
+static struct ip6_flowlabel *fl_ht[FL_HASH_MASK+1];
+
+static struct timer_list ip6_fl_gc_timer;
+
+/* FL hash table lock: it protects only of GC */
+
+static atomic_t ip6_fl_lock = ATOMIC_INIT(0);
+
+static __inline__ void fl_lock(void)
+{
+	atomic_inc(&ip6_fl_lock);
+	synchronize_bh();
+}
+
+static __inline__ void fl_unlock(void)
+{
+	atomic_dec(&ip6_fl_lock);
+}
+
+static struct ip6_flowlabel * fl_lookup(u32 label)
+{
+	struct ip6_flowlabel *fl;
+
+	fl_lock();
+	for (fl=fl_ht[FL_HASH(label)]; fl; fl = fl->next) {
+		if (fl->label == label) {
+			atomic_inc(&fl->users);
+			break;
+		}
+	}
+	fl_unlock();
+	return fl;
+}
+
+static void fl_free(struct ip6_flowlabel *fl)
+{
+	if (fl->opt)
+		kfree(fl->opt);
+	kfree(fl);
+}
+
+static void fl_release(struct ip6_flowlabel *fl)
+{
+	fl_lock();
+	fl->lastuse = jiffies;
+	if (atomic_dec_and_test(&fl->users)) {
+		unsigned long ttd = fl->lastuse + fl->linger;
+		if ((long)(ttd - fl->expires) > 0)
+			fl->expires = ttd;
+		ttd = fl->expires;
+		if (fl->opt && fl->share == IPV6_FL_S_EXCL) {
+			struct ipv6_txoptions *opt = fl->opt;
+			fl->opt = NULL;
+			kfree(opt);
+		}
+		if (!del_timer(&ip6_fl_gc_timer) ||
+		    (long)(ip6_fl_gc_timer.expires - ttd) > 0)
+			ip6_fl_gc_timer.expires = ttd;
+		add_timer(&ip6_fl_gc_timer);
+	}
+	fl_unlock();
+}
+
+static void ip6_fl_gc(unsigned long dummy)
+{
+	int i;
+	unsigned long now = jiffies;
+	unsigned long sched = 0;
+
+	if (atomic_read(&ip6_fl_lock)) {
+		ip6_fl_gc_timer.expires = now + HZ/10;
+		add_timer(&ip6_fl_gc_timer);
+		return;
+	}
+
+	for (i=0; i<=FL_HASH_MASK; i++) {
+		struct ip6_flowlabel *fl, **flp;
+		flp = &fl_ht[i];
+		while ((fl=*flp) != NULL) {
+			if (atomic_read(&fl->users) == 0) {
+				unsigned long ttd = fl->lastuse + fl->linger;
+				if ((long)(ttd - fl->expires) > 0)
+					fl->expires = ttd;
+				ttd = fl->expires;
+				if ((long)(now - ttd) >= 0) {
+					*flp = fl->next;
+					fl_free(fl);
+					atomic_dec(&fl_size);
+					continue;
+				}
+				if (!sched || (long)(ttd - sched) < 0)
+					sched = ttd;
+			}
+			flp = &fl->next;
+		}
+	}
+	if (!sched && atomic_read(&fl_size))
+		sched = now + FL_MAX_LINGER;
+	if (sched) {
+		ip6_fl_gc_timer.expires = sched;
+		add_timer(&ip6_fl_gc_timer);
+	}
+}
+
+static int fl_intern(struct ip6_flowlabel *fl, __u32 label)
+{
+	fl->label = label & IPV6_FLOWLABEL_MASK;
+
+	fl_lock();
+	if (label == 0) {
+		for (;;) {
+			fl->label = htonl(net_random())&IPV6_FLOWLABEL_MASK;
+			if (fl->label) {
+				struct ip6_flowlabel *lfl;
+				lfl = fl_lookup(fl->label);
+				if (lfl == NULL)
+					break;
+				fl_release(lfl);
+			}
+		}
+	}
+
+	fl->lastuse = jiffies;
+	fl->next = fl_ht[FL_HASH(fl->label)];
+	fl_ht[FL_HASH(fl->label)] = fl;
+	atomic_inc(&fl_size);
+	fl_unlock();
+	return 0;
+}
+
+
+
+/* Socket flowlabel lists */
+
+struct ip6_flowlabel * fl6_sock_lookup(struct sock *sk, u32 label)
+{
+	struct ipv6_fl_socklist *sfl;
+	struct ipv6_pinfo *np = &sk->net_pinfo.af_inet6;
+
+	label &= IPV6_FLOWLABEL_MASK;
+
+	for (sfl=np->ipv6_fl_list; sfl; sfl = sfl->next) {
+		struct ip6_flowlabel *fl = sfl->fl;
+		if (fl->label == label) {
+			fl->lastuse = jiffies;
+			atomic_inc(&fl->users);
+			return fl;
+		}
+	}
+	return NULL;
+}
+
+void fl6_free_socklist(struct sock *sk)
+{
+	struct ipv6_pinfo *np = &sk->net_pinfo.af_inet6;
+	struct ipv6_fl_socklist *sfl;
+
+	while ((sfl = np->ipv6_fl_list) != NULL) {
+		np->ipv6_fl_list = sfl->next;
+		fl_release(sfl->fl);
+		kfree(sfl);
+	}
+}
+
+/* Service routines */
+
+
+/*
+   It is the only difficult place. flowlabel enforces equal headers
+   before and including routing header, however user may supply options
+   following rthdr.
+ */
+
+struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions * opt_space,
+					 struct ip6_flowlabel * fl,
+					 struct ipv6_txoptions * fopt)
+{
+	struct ipv6_txoptions * fl_opt = fl->opt;
+
+	if (fopt == NULL || fopt->opt_flen == 0)
+		return fl_opt;
+
+	if (fl_opt != NULL) {
+		opt_space->hopopt = fl_opt->hopopt;
+		opt_space->dst0opt = fl_opt->dst0opt;
+		opt_space->srcrt = fl_opt->srcrt;
+		opt_space->opt_nflen = fl_opt->opt_nflen;
+	} else {
+		if (fopt->opt_nflen == 0)
+			return fopt;
+		opt_space->hopopt = NULL;
+		opt_space->dst0opt = NULL;
+		opt_space->srcrt = NULL;
+		opt_space->opt_nflen = 0;
+	}
+	opt_space->dst1opt = fopt->dst1opt;
+	opt_space->auth = fopt->auth;
+	opt_space->opt_flen = fopt->opt_flen;
+	return opt_space;
+}
+
+static __u32 check_linger(__u16 ttl)
+{
+	if (ttl < FL_MIN_LINGER)
+		return FL_MIN_LINGER*HZ;
+	if (ttl > FL_MAX_LINGER && !capable(CAP_NET_ADMIN))
+		return 0;
+	return ttl*HZ;
+}
+
+static int fl6_renew(struct ip6_flowlabel *fl, unsigned linger, unsigned expires)
+{
+	linger = check_linger(linger);
+	if (!linger)
+		return -EPERM;
+	expires = check_linger(expires);
+	if (!expires)
+		return -EPERM;
+	fl->lastuse = jiffies;
+	if (fl->linger < linger)
+		fl->linger = linger;
+	if (expires < fl->linger)
+		expires = fl->linger;
+	if ((long)(fl->expires - (fl->lastuse+expires)) < 0)
+		fl->expires = fl->lastuse + expires;
+	return 0;
+}
+
+static struct ip6_flowlabel *
+fl_create(struct in6_flowlabel_req *freq, char *optval, int optlen, int *err_p)
+{
+	struct ip6_flowlabel *fl;
+	int olen;
+	int addr_type;
+	int err;
+
+	err = -ENOMEM;
+	fl = kmalloc(sizeof(*fl), GFP_KERNEL);
+	if (fl == NULL)
+		goto done;
+	memset(fl, 0, sizeof(*fl));
+
+	olen = optlen - CMSG_ALIGN(sizeof(*freq));
+	if (olen > 0) {
+		struct msghdr msg;
+		struct flowi flowi;
+		int junk;
+
+		err = -ENOMEM;
+		fl->opt = kmalloc(sizeof(*fl->opt) + olen, GFP_KERNEL);
+		if (fl->opt == NULL)
+			goto done;
+
+		memset(fl->opt, 0, sizeof(*fl->opt));
+		fl->opt->tot_len = sizeof(*fl->opt) + olen;
+		err = -EFAULT;
+		if (copy_from_user(fl->opt+1, optval+CMSG_ALIGN(sizeof(*freq)), olen))
+			goto done;
+
+		msg.msg_controllen = olen;
+		msg.msg_control = (void*)(fl->opt+1);
+		flowi.oif = 0;
+
+		err = datagram_send_ctl(&msg, &flowi, fl->opt, &junk);
+		if (err)
+			goto done;
+		err = -EINVAL;
+		if (fl->opt->opt_flen)
+			goto done;
+		if (fl->opt->opt_nflen == 0) {
+			kfree(fl->opt);
+			fl->opt = NULL;
+		}
+	}
+
+	fl->expires = jiffies;
+	err = fl6_renew(fl, freq->flr_linger, freq->flr_expires);
+	if (err)
+		goto done;
+	fl->share = freq->flr_share;
+	addr_type = ipv6_addr_type(&freq->flr_dst);
+	if ((addr_type&IPV6_ADDR_MAPPED)
+	    || addr_type == IPV6_ADDR_ANY)
+		goto done;
+	ipv6_addr_copy(&fl->dst, &freq->flr_dst);
+	atomic_set(&fl->users, 1);
+	switch (fl->share) {
+	case IPV6_FL_S_EXCL:
+	case IPV6_FL_S_ANY:
+		break;
+	case IPV6_FL_S_PROCESS:
+		fl->owner = current->pid;
+		break;
+	case IPV6_FL_S_USER:
+		fl->owner = current->euid;
+		break;
+	default:
+		err = -EINVAL;
+		goto done;
+	}
+	return fl;
+
+done:
+	if (fl)
+		fl_free(fl);
+	*err_p = err;
+	return NULL;
+}
+
+static int mem_check(struct sock *sk)
+{
+	struct ipv6_fl_socklist *sfl;
+	int room = FL_MAX_SIZE - atomic_read(&fl_size);
+	int count = 0;
+
+	if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK)
+		return 0;
+
+	for (sfl = sk->net_pinfo.af_inet6.ipv6_fl_list; sfl; sfl = sfl->next)
+		count++;
+
+	if (room <= 0 ||
+	    ((count >= FL_MAX_PER_SOCK ||
+	     (count > 0 && room < FL_MAX_SIZE/2) || room < FL_MAX_SIZE/4)
+	     && !capable(CAP_NET_ADMIN)))
+		return -ENOBUFS;
+
+	return 0;
+}
+
+static int ipv6_hdr_cmp(struct ipv6_opt_hdr *h1, struct ipv6_opt_hdr *h2)
+{
+	if (h1 == h2)
+		return 0;
+	if (h1 == NULL || h2 == NULL)
+		return 1;
+	if (h1->hdrlen != h2->hdrlen)
+		return 1;
+	return memcmp(h1+1, h2+1, ((h1->hdrlen+1)<<3) - sizeof(*h1));
+}
+
+static int ipv6_opt_cmp(struct ipv6_txoptions *o1, struct ipv6_txoptions *o2)
+{
+	if (o1 == o2)
+		return 0;
+	if (o1 == NULL || o2 == NULL)
+		return 1;
+	if (o1->opt_nflen != o2->opt_nflen)
+		return 1;
+	if (ipv6_hdr_cmp(o1->hopopt, o2->hopopt))
+		return 1;
+	if (ipv6_hdr_cmp(o1->dst0opt, o2->dst0opt))
+		return 1;
+	if (ipv6_hdr_cmp((struct ipv6_opt_hdr *)o1->srcrt, (struct ipv6_opt_hdr *)o2->srcrt))
+		return 1;
+	return 0;
+}
+
+int ipv6_flowlabel_opt(struct sock *sk, char *optval, int optlen)
+{
+	int err;
+	struct ipv6_pinfo *np = &sk->net_pinfo.af_inet6;
+	struct in6_flowlabel_req freq;
+	struct ipv6_fl_socklist *sfl1=NULL;
+	struct ipv6_fl_socklist *sfl, **sflp;
+	struct ip6_flowlabel *fl;
+
+	if (optlen < sizeof(freq))
+		return -EINVAL;
+
+	if (copy_from_user(&freq, optval, sizeof(freq)))
+		return -EFAULT;
+
+	switch (freq.flr_action) {
+	case IPV6_FL_A_PUT:
+		for (sflp = &np->ipv6_fl_list; (sfl=*sflp)!=NULL; sflp = &sfl->next) {
+			if (sfl->fl->label == freq.flr_label) {
+				if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK))
+					np->flow_label &= ~IPV6_FLOWLABEL_MASK;
+				*sflp = sfl->next;
+				synchronize_bh();
+				fl_release(sfl->fl);
+				kfree(sfl);
+				return 0;
+			}
+		}
+		return -ESRCH;
+
+	case IPV6_FL_A_RENEW:
+		for (sfl = np->ipv6_fl_list; sfl; sfl = sfl->next) {
+			if (sfl->fl->label == freq.flr_label)
+				return fl6_renew(sfl->fl, freq.flr_linger, freq.flr_expires);
+		}
+		if (freq.flr_share == IPV6_FL_S_NONE && capable(CAP_NET_ADMIN)) {
+			fl = fl_lookup(freq.flr_label);
+			if (fl) {
+				err = fl6_renew(fl, freq.flr_linger, freq.flr_expires);
+				fl_release(fl);
+				return err;
+			}
+		}
+		return -ESRCH;
+
+	case IPV6_FL_A_GET:
+		if (freq.flr_label & ~IPV6_FLOWLABEL_MASK)
+			return -EINVAL;
+
+		fl = fl_create(&freq, optval, optlen, &err);
+		if (fl == NULL)
+			return err;
+		sfl1 = kmalloc(sizeof(*sfl1), GFP_KERNEL);
+
+		if (freq.flr_label) {
+			struct ip6_flowlabel *fl1 = NULL;
+
+			err = -EEXIST;
+			for (sfl = np->ipv6_fl_list; sfl; sfl = sfl->next) {
+				if (sfl->fl->label == freq.flr_label) {
+					if (freq.flr_flags&IPV6_FL_F_EXCL)
+						goto done;
+					fl1 = sfl->fl;
+					atomic_inc(&fl->users);
+					break;
+				}
+			}
+
+			if (fl1 == NULL)
+				fl1 = fl_lookup(freq.flr_label);
+			if (fl1) {
+				err = -EEXIST;
+				if (freq.flr_flags&IPV6_FL_F_EXCL)
+					goto release;
+				err = -EPERM;
+				if (fl1->share == IPV6_FL_S_EXCL ||
+				    fl1->share != fl->share ||
+				    fl1->owner != fl->owner)
+					goto release;
+
+				err = -EINVAL;
+				if (ipv6_addr_cmp(&fl1->dst, &fl->dst) ||
+				    ipv6_opt_cmp(fl1->opt, fl->opt))
+					goto release;
+
+				err = -ENOMEM;
+				if (sfl1 == NULL)
+					goto release;
+				if (fl->linger > fl1->linger)
+					fl1->linger = fl->linger;
+				if ((long)(fl->expires - fl1->expires) > 0)
+					fl1->expires = fl->expires;
+				sfl1->fl = fl1;
+				sfl1->next = np->ipv6_fl_list;
+				np->ipv6_fl_list = sfl1;
+				synchronize_bh();
+				fl_free(fl);
+				return 0;
+
+release:
+				fl_release(fl1);
+				goto done;
+			}
+		}
+		err = -ENOENT;
+		if (!(freq.flr_flags&IPV6_FL_F_CREATE))
+			goto done;
+
+		err = -ENOMEM;
+		if (sfl1 == NULL || (err = mem_check(sk)) != 0)
+			goto done;
+
+		err = fl_intern(fl, freq.flr_label);
+		if (err)
+			goto done;
+
+		/* Do not check for fault */
+		if (!freq.flr_label)
+			copy_to_user(optval + ((u8*)&freq.flr_label - (u8*)&freq), &fl->label, sizeof(fl->label));
+
+		sfl1->fl = fl;
+		sfl1->next = np->ipv6_fl_list;
+		np->ipv6_fl_list = sfl1;
+		return 0;
+
+	default:
+		return -EINVAL;
+	}
+
+done:
+	if (fl)
+		fl_free(fl);
+	if (sfl1)
+		kfree(sfl1);
+	return err;
+}
+
+#ifdef CONFIG_PROC_FS
+
+
+static int ip6_fl_read_proc(char *buffer, char **start, off_t offset,
+			    int length, int *eof, void *data)
+{
+	off_t pos=0;
+	off_t begin=0;
+	int len=0;
+	int i, k;
+	struct ip6_flowlabel *fl;
+
+	len+= sprintf(buffer,"Label S Owner  Users  Linger Expires  "
+		      "Dst                              Opt\n");
+
+	fl_lock();
+	for (i=0; i<=FL_HASH_MASK; i++) {
+		for (fl = fl_ht[i]; fl; fl = fl->next) {
+			len+=sprintf(buffer+len,"%05X %-1d %-6d %-6d %-6d %-8ld ",
+				     (unsigned)ntohl(fl->label),
+				     fl->share,
+				     (unsigned)fl->owner,
+				     atomic_read(&fl->users),
+				     fl->linger/HZ,
+				     (long)(fl->expires - jiffies)/HZ);
+
+			for (k=0; k<16; k++)
+				len+=sprintf(buffer+len, "%02x", fl->dst.s6_addr[k]);
+			buffer[len++]=' ';
+			len+=sprintf(buffer+len, "%-4d", fl->opt ? fl->opt->opt_nflen : 0);
+			buffer[len++]='\n';
+
+			pos=begin+len;
+			if(pos<offset) {
+				len=0;
+				begin=pos;
+			}
+			if(pos>offset+length)
+				goto done;
+		}
+	}
+	*eof = 1;
+
+done:
+	fl_unlock();
+	*start=buffer+(offset-begin);
+	len-=(offset-begin);
+	if(len>length)
+		len=length;
+	if(len<0)
+		len=0;
+	return len;
+}
+#endif
+
+
+void ip6_flowlabel_init()
+{
+#ifdef CONFIG_PROC_FS
+	struct proc_dir_entry *ent;
+#endif
+
+	init_timer(&ip6_fl_gc_timer);
+	ip6_fl_gc_timer.function = ip6_fl_gc;
+#ifdef CONFIG_PROC_FS
+	ent = create_proc_entry("net/ip6_flowlabel", 0, 0);
+	ent->read_proc = ip6_fl_read_proc;
+#endif
+}
+
+void ip6_flowlabel_cleanup()
+{
+	del_timer(&ip6_fl_gc_timer);
+#ifdef CONFIG_PROC_FS
+	remove_proc_entry("net/ip6_flowlabel", 0);
+#endif
+}