Merge aladin.rdu.redhat.com:/usr/local/home/dledford/bk/linus-2.5

into aladin.rdu.redhat.com:/usr/src/2.5

arch/i386/kernel/entry.S

@@ -66,7 +66,9 @@ OLDESP		= 0x34
 OLDSS		= 0x38
 
 CF_MASK		= 0x00000001
+TF_MASK		= 0x00000100
 IF_MASK		= 0x00000200
+DF_MASK		= 0x00000400 
 NT_MASK		= 0x00004000
 VM_MASK		= 0x00020000
 
@@ -134,6 +136,17 @@ ENTRY(lcall7)
 	movl %eax,EFLAGS(%esp)	#
 	movl %edx,EIP(%esp)	# Now we move them to their "normal" places
 	movl %ecx,CS(%esp)	#
+
+	#
+	# Call gates don't clear TF and NT in eflags like
+	# traps do, so we need to do it ourselves.
+	# %eax already contains eflags (but it may have
+	# DF set, clear that also)
+	#
+	andl $~(DF_MASK | TF_MASK | NT_MASK),%eax
+	pushl %eax
+	popfl
+
 	movl %esp, %ebx
 	pushl %ebx
 	andl $-8192, %ebx	# GET_THREAD_INFO
@@ -156,6 +169,17 @@ ENTRY(lcall27)
 	movl %eax,EFLAGS(%esp)	#
 	movl %edx,EIP(%esp)	# Now we move them to their "normal" places
 	movl %ecx,CS(%esp)	#
+
+	#
+	# Call gates don't clear TF and NT in eflags like
+	# traps do, so we need to do it ourselves.
+	# %eax already contains eflags (but it may have
+	# DF set, clear that also)
+	#
+	andl $~(DF_MASK | TF_MASK | NT_MASK),%eax
+	pushl %eax
+	popfl
+
 	movl %esp, %ebx
 	pushl %ebx
 	andl $-8192, %ebx	# GET_THREAD_INFO

arch/sparc/kernel/module.c

@@ -90,7 +90,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 			       me->name, strtab + sym->st_name);
 			return -ENOENT;
 		}
-		v += rel->r_addend;
+		v += rel[i].r_addend;
 
 		switch (ELF32_R_TYPE(rel[i].r_info)) {
 		case R_SPARC_32:
@@ -126,7 +126,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 			       me->name,
 			       (int) (ELF32_R_TYPE(rel[i].r_info) & 0xff));
 			return -ENOEXEC;
-		}
+		};
 	}
 	return 0;
 }

arch/sparc64/kernel/module.c

@@ -10,6 +10,113 @@
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
 #include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+
+static struct vm_struct * modvmlist = NULL;
+
+static void module_unmap(void * addr)
+{
+	struct vm_struct **p, *tmp;
+	int i;
+
+	if (!addr)
+		return;
+	if ((PAGE_SIZE-1) & (unsigned long) addr) {
+		printk("Trying to unmap module with bad address (%p)\n", addr);
+		return;
+	}
+
+	for (p = &modvmlist ; (tmp = *p) ; p = &tmp->next) {
+		if (tmp->addr == addr) {
+			*p = tmp->next;
+			goto found;
+		}
+	}
+	printk("Trying to unmap nonexistent module vm area (%p)\n", addr);
+	return;
+
+found:
+	unmap_vm_area(tmp);
+	
+	for (i = 0; i < tmp->nr_pages; i++) {
+		if (unlikely(!tmp->pages[i]))
+			BUG();
+		__free_page(tmp->pages[i]);
+	}
+
+	kfree(tmp->pages);
+	kfree(tmp);
+}
+
+
+static void *module_map(unsigned long size)
+{
+	struct vm_struct **p, *tmp, *area;
+	struct page **pages;
+	void * addr;
+	unsigned int nr_pages, array_size, i;
+
+	size = PAGE_ALIGN(size);
+	if (!size || size > MODULES_LEN)
+		return NULL;
+		
+	addr = (void *) MODULES_VADDR;
+	for (p = &modvmlist; (tmp = *p) ; p = &tmp->next) {
+		if (size + (unsigned long) addr < (unsigned long) tmp->addr)
+			break;
+		addr = (void *) (tmp->size + (unsigned long) tmp->addr);
+	}
+	if ((unsigned long) addr + size >= MODULES_END)
+		return NULL;
+	
+	area = (struct vm_struct *) kmalloc(sizeof(*area), GFP_KERNEL);
+	if (!area)
+		return NULL;
+	area->size = size + PAGE_SIZE;
+	area->addr = addr;
+	area->next = *p;
+	area->pages = NULL;
+	area->nr_pages = 0;
+	area->phys_addr = 0;
+	*p = area;
+
+	nr_pages = size >> PAGE_SHIFT;
+	array_size = (nr_pages * sizeof(struct page *));
+
+	area->nr_pages = nr_pages;
+	area->pages = pages = kmalloc(array_size, GFP_KERNEL);
+	if (!area->pages)
+		goto fail;
+
+	memset(area->pages, 0, array_size);
+
+	for (i = 0; i < area->nr_pages; i++) {
+		area->pages[i] = alloc_page(GFP_KERNEL);
+		if (unlikely(!area->pages[i]))
+			goto fail;
+	}
+	
+	if (map_vm_area(area, PAGE_KERNEL, &pages)) {
+		unmap_vm_area(area);
+		goto fail;
+	}
+
+	return area->addr;
+
+fail:
+	if (area->pages) {
+		for (i = 0; i < area->nr_pages; i++) {
+			if (area->pages[i])
+				__free_page(area->pages[i]);
+		}
+		kfree(area->pages);
+	}
+	kfree(area);
+
+	return NULL;
+}
 
 static void *alloc_and_zero(unsigned long size)
 {
@@ -19,7 +126,7 @@ static void *alloc_and_zero(unsigned long size)
 	if (size == 0)
 		return NULL;
 
-	ret = vmalloc(size);
+	ret = module_map(size);
 	if (!ret)
 		ret = ERR_PTR(-ENOMEM);
 	else
@@ -31,7 +138,7 @@ static void *alloc_and_zero(unsigned long size)
 /* Free memory returned from module_core_alloc/module_init_alloc */
 void module_free(struct module *mod, void *module_region)
 {
-	vfree(module_region);
+	module_unmap(module_region);
 	/* FIXME: If module_region == mod->init_region, trim exception
            table entries. */
 }
@@ -82,6 +189,9 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		location = (u8 *)sechdrs[sechdrs[relsec].sh_info].sh_offset
 			+ rel[i].r_offset;
 		loc32 = (u32 *) location;
+
+		BUG_ON(((u64)location >> (u64)32) != (u64)0);
+
 		/* This is the symbol it is referring to */
 		sym = (Elf64_Sym *)sechdrs[symindex].sh_offset
 			+ ELF64_R_SYM(rel[i].r_info);
@@ -90,7 +200,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			       me->name, strtab + sym->st_name);
 			return -ENOENT;
 		}
-		v += rel->r_addend;
+		v += rel[i].r_addend;
 
 		switch (ELF64_R_TYPE(rel[i].r_info) & 0xff) {
 		case R_SPARC_64:
@@ -137,7 +247,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			       me->name,
 			       (int) (ELF64_R_TYPE(rel[i].r_info) & 0xff));
 			return -ENOEXEC;
-		}
+		};
 	}
 	return 0;
 }

arch/sparc64/kernel/sys_sparc32.c

@@ -3113,24 +3113,18 @@ asmlinkage int sparc32_execve(struct pt_regs *regs)
 
 #ifdef CONFIG_MODULES
 
-extern asmlinkage long sys_init_module(const char *name_user,
-				       struct module *mod_user);
+extern asmlinkage long sys_init_module(void *, unsigned long, const char *);
 
-/* Hey, when you're trying to init module, take time and prepare us a nice
- * 64bit module structure, even if from 32bit modutils... Why to pollute
- * kernel... :))
- */
-asmlinkage int sys32_init_module(const char *name_user,
-				 struct module *mod_user)
+asmlinkage int sys32_init_module(void *umod, u32 len, const char *uargs)
 {
-	return sys_init_module(name_user, mod_user);
+	return sys_init_module(umod, len, uargs);
 }
 
-extern asmlinkage long sys_delete_module(const char *name_user);
+extern asmlinkage long sys_delete_module(const char *, unsigned int);
 
-asmlinkage int sys32_delete_module(const char *name_user)
+asmlinkage int sys32_delete_module(const char *name_user, unsigned int flags)
 {
-	return sys_delete_module(name_user);
+	return sys_delete_module(name_user, flags);
 }
 
 #else /* CONFIG_MODULES */

crypto/api.c

@@ -263,8 +263,7 @@ static int c_show(struct seq_file *m, void *p)
 	struct crypto_alg *alg = (struct crypto_alg *)p;
 	
 	seq_printf(m, "name         : %s\n", alg->cra_name);
-	seq_printf(m, "module       : %s\n", alg->cra_module ?
-					alg->cra_module->name : "[static]");
+	seq_printf(m, "module       : %s\n", module_name(alg->cra_module));
 	seq_printf(m, "blocksize    : %u\n", alg->cra_blocksize);
 	
 	switch (alg->cra_flags & CRYPTO_ALG_TYPE_MASK) {

include/linux/in.h

@@ -70,6 +70,7 @@ struct in_addr {
 #define IP_MTU		14
 #define IP_FREEBIND	15
 #define IP_IPSEC_POLICY	16
+#define IP_XFRM_POLICY	17
 
 /* BSD compatibility */
 #define IP_RECVRETOPTS	IP_RETOPTS

include/linux/module.h

@@ -242,6 +242,13 @@ static inline void module_put(struct module *module)
 
 #endif /* CONFIG_MODULE_UNLOAD */
 
+/* This is a #define so the string doesn't get put in every .o file */
+#define module_name(mod)			\
+({						\
+	struct module *__mod = (mod);		\
+	__mod ? __mod->name : "kernel";		\
+})
+
 #define __unsafe(mod)							     \
 do {									     \
 	if (mod && !(mod)->unsafe) {					     \
@@ -265,6 +272,8 @@ do {									     \
 #define try_module_get(module) 1
 #define module_put(module) do { } while(0)
 
+#define module_name(mod) "kernel"
+
 #define __unsafe(mod)
 #endif /* CONFIG_MODULES */
 

include/linux/udp.h

@@ -57,7 +57,4 @@ struct udp_sock {
 
 #define udp_sk(__sk) (&((struct udp_sock *)__sk)->udp)
 
-extern int udp_proc_init(void);
-extern void udp_proc_exit(void);
-
 #endif	/* _LINUX_UDP_H */

include/linux/xfrm.h

@@ -91,6 +91,22 @@ struct xfrm_stats {
 	__u32	integrity_failed;
 };
 
+enum
+{
+	XFRM_POLICY_IN	= 0,
+	XFRM_POLICY_OUT	= 1,
+	XFRM_POLICY_FWD	= 2,
+	XFRM_POLICY_MAX	= 3
+};
+
+enum
+{
+	XFRM_SHARE_ANY,		/* No limitations */
+	XFRM_SHARE_SESSION,	/* For this session only */
+	XFRM_SHARE_USER,	/* For this user only */
+	XFRM_SHARE_UNIQUE	/* Use once */
+};
+
 /* Netlink configuration messages.  */
 #define XFRM_MSG_BASE		0x10
 
@@ -104,8 +120,9 @@ struct xfrm_stats {
 
 #define XFRM_MSG_ALLOCSPI	(RTM_BASE + 6)
 #define XFRM_MSG_ACQUIRE	(RTM_BASE + 7)
+#define XFRM_MSG_EXPIRE		(RTM_BASE + 8)
 
-#define XFRM_MSG_MAX		(XFRM_MSG_ACQUIRE+1)
+#define XFRM_MSG_MAX		(XFRM_MSG_EXPIRE+1)
 
 struct xfrm_user_tmpl {
 	struct xfrm_id		id;
@@ -113,6 +130,7 @@ struct xfrm_user_tmpl {
 	__u16			reqid;
 	__u8			mode;
 	__u8			share;
+	__u8			optional;
 	__u32			aalgos;
 	__u32			ealgos;
 	__u32			calgos;
@@ -135,9 +153,9 @@ struct xfrm_usersa_info {
 	struct xfrm_lifetime_cfg	lft;
 	struct xfrm_lifetime_cur	curlft;
 	struct xfrm_stats		stats;
+	__u32				seq;
 	__u16				family;
 	__u16				reqid;
-	__u8				sa_type;
 	__u8				mode; /* 0=transport,1=tunnel */
 	__u8				replay_window;
 };
@@ -148,15 +166,26 @@ struct xfrm_usersa_id {
 	__u8				proto;
 };
 
+struct xfrm_userspi_info {
+	struct xfrm_usersa_info		info;
+	u32				min;
+	u32				max;
+};
+
 struct xfrm_userpolicy_info {
 	struct xfrm_selector		sel;
-	struct xfrm_id			id;
 	struct xfrm_lifetime_cfg	lft;
 	struct xfrm_lifetime_cur	curlft;
+	__u32				priority;
 	__u32				index;
 	__u16				family;
 	__u8				dir;
 	__u8				action;
+#define XFRM_POLICY_ALLOW	0
+#define XFRM_POLICY_BLOCK	1
+	__u8				flags;
+#define XFRM_POLICY_LOCALOK	1	/* Allow user to override global policy */
+	__u8				share;
 };
 
 struct xfrm_userpolicy_id {
@@ -165,4 +194,22 @@ struct xfrm_userpolicy_id {
 	__u8				dir;
 };
 
+struct xfrm_user_acquire {
+	struct xfrm_id			id;
+	xfrm_address_t			saddr;
+	struct xfrm_userpolicy_info	policy;
+	__u32				aalgos;
+	__u32				ealgos;
+	__u32				calgos;
+	__u32				seq;
+};
+
+struct xfrm_user_expire {
+	struct xfrm_usersa_info		state;
+	__u8				hard;
+};
+
+#define XFRMGRP_ACQUIRE		1
+#define XFRMGRP_EXPIRE		2
+
 #endif /* _LINUX_XFRM_H */

include/net/ip_fib.h

@@ -276,7 +276,4 @@ static inline void fib_res_put(struct fib_result *res)
 #endif
 }
 
-extern int fib_proc_init(void);
-extern void fib_proc_exit(void);
-
 #endif  /* _NET_FIB_H */

include/net/udp.h

@@ -76,6 +76,4 @@ extern struct udp_mib udp_statistics[NR_CPUS*2];
 #define UDP_INC_STATS_BH(field)		SNMP_INC_STATS_BH(udp_statistics, field)
 #define UDP_INC_STATS_USER(field) 	SNMP_INC_STATS_USER(udp_statistics, field)
 
-extern int udp_proc_init(void);
-
 #endif	/* _UDP_H */

include/net/xfrm.h

@@ -96,6 +96,7 @@ struct xfrm_state
 		u8		replay_window;
 		u8		aalgo, ealgo, calgo;
 		u16		reqid;
+		u16		family;
 		xfrm_address_t	saddr;
 		int		header_len;
 		int		trailer_len;
@@ -187,22 +188,6 @@ struct xfrm_tmpl
 
 #define XFRM_MAX_DEPTH		3
 
-enum
-{
-	XFRM_SHARE_ANY,		/* No limitations */
-	XFRM_SHARE_SESSION,	/* For this session only */
-	XFRM_SHARE_USER,	/* For this user only */
-	XFRM_SHARE_UNIQUE	/* Use once */
-};
-
-enum
-{
-	XFRM_POLICY_IN	= 0,
-	XFRM_POLICY_OUT	= 1,
-	XFRM_POLICY_FWD	= 2,
-	XFRM_POLICY_MAX	= 3
-};
-
 struct xfrm_policy
 {
 	struct xfrm_policy	*next;
@@ -217,11 +202,9 @@ struct xfrm_policy
 	struct xfrm_lifetime_cfg lft;
 	struct xfrm_lifetime_cur curlft;
 	struct dst_entry       *bundles;
+	__u16			family;
 	__u8			action;
-#define XFRM_POLICY_ALLOW	0
-#define XFRM_POLICY_BLOCK	1
 	__u8			flags;
-#define XFRM_POLICY_LOCALOK	1	/* Allow user to override global policy */
 	__u8			dead;
 	__u8			xfrm_nr;
 	struct xfrm_tmpl       	xfrm_vec[XFRM_MAX_DEPTH];
@@ -390,7 +373,7 @@ struct xfrm_policy *xfrm_policy_delete(int dir, struct xfrm_selector *sel);
 struct xfrm_policy *xfrm_policy_byid(int dir, u32 id, int delete);
 void xfrm_policy_flush(void);
 void xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi);
-struct xfrm_state * xfrm_find_acq(u8 mode, u16 reqid, u8 proto, u32 daddr, u32 saddr);
+struct xfrm_state * xfrm_find_acq(u8 mode, u16 reqid, u8 proto, u32 daddr, u32 saddr, int create);
 extern void xfrm_policy_flush(void);
 extern void xfrm_policy_kill(struct xfrm_policy *);
 extern int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol);

kernel/exec_domain.c

@@ -210,13 +210,8 @@ get_exec_domain_list(char *page)
 	read_lock(&exec_domains_lock);
 	for (ep = exec_domains; ep && len < PAGE_SIZE - 80; ep = ep->next)
 		len += sprintf(page + len, "%d-%d\t%-16s\t[%s]\n",
-			ep->pers_low, ep->pers_high, ep->name,
-#ifdef CONFIG_MODULES
-			ep->module ? ep->module->name : "kernel"
-#else
-			"kernel"
-#endif
-			);
+			       ep->pers_low, ep->pers_high, ep->name,
+			       module_name(ep->module));
 	read_unlock(&exec_domains_lock);
 	return (len);
 }

net/802/tr.c

@@ -541,10 +541,10 @@ static int rif_get_info(char *buffer,char **start, off_t offset, int length)
 
 static int __init rif_init(void)
 {
+	init_timer(&rif_timer);
 	rif_timer.expires  = RIF_TIMEOUT;
 	rif_timer.data     = 0L;
 	rif_timer.function = rif_check_expire;
-	init_timer(&rif_timer);
 	add_timer(&rif_timer);
 
 	proc_net_create("tr_rif",0,rif_get_info);

net/atm/mpc.c

@@ -104,7 +104,7 @@ extern void mpc_proc_clean(void);
 
 struct mpoa_client *mpcs = NULL; /* FIXME */
 static struct atm_mpoa_qos *qos_head = NULL;
-static struct timer_list mpc_timer;
+static struct timer_list mpc_timer = TIMER_INITIALIZER(NULL, 0, 0);
 
 
 static struct mpoa_client *find_mpc_by_itfnum(int itf)

net/core/neighbour.c

@@ -1151,8 +1151,8 @@ void neigh_table_init(struct neigh_table *tbl)
 	tasklet_init(&tbl->gc_task, SMP_TIMER_NAME(neigh_periodic_timer),
 		     (unsigned long)tbl);
 #endif
-	init_timer(&tbl->gc_timer);
 	tbl->lock	       = RW_LOCK_UNLOCKED;
+	init_timer(&tbl->gc_timer);
 	tbl->gc_timer.data     = (unsigned long)tbl;
 	tbl->gc_timer.function = neigh_periodic_timer;
 	tbl->gc_timer.expires  = now + tbl->gc_interval +

net/ipv4/Kconfig

@@ -362,5 +362,13 @@ config INET_ESP
 
 	  If unsure, say Y.
 
+config XFRM_USER
+	tristate "IP: IPsec user configuration interface"
+	---help---
+	  Support for IPsec user configuration interface used
+	  by native Linux tools.
+
+	  If unsure, say Y.
+
 source "net/ipv4/netfilter/Kconfig"
 

net/ipv4/Makefile

@@ -20,6 +20,7 @@ obj-$(CONFIG_INET_AH) += ah.o
 obj-$(CONFIG_INET_ESP) += esp.o
 obj-$(CONFIG_IP_PNP) += ipconfig.o
 obj-$(CONFIG_NETFILTER)	+= netfilter/
+obj-$(CONFIG_XFRM_USER) += xfrm_user.o
 
 obj-y += xfrm_policy.o xfrm_state.o xfrm_input.o
 

net/ipv4/af_inet.c

@@ -1160,16 +1160,20 @@ module_init(inet_init);
 /* ------------------------------------------------------------------------ */
 
 #ifdef CONFIG_PROC_FS
-
-extern int ip_misc_proc_init(void);
-extern int raw_get_info(char *, char **, off_t, int);
-extern int tcp_get_info(char *, char **, off_t, int);
+extern int  fib_proc_init(void);
+extern void fib_proc_exit(void);
+extern int  ip_misc_proc_init(void);
+extern int  raw_proc_init(void);
+extern void raw_proc_exit(void);
+extern int  tcp_get_info(char *buffer, char **start, off_t offset, int length);
+extern int  udp_proc_init(void);
+extern void udp_proc_exit(void);
 
 int __init ipv4_proc_init(void)
 {
 	int rc = 0;
 
-	if (!proc_net_create("raw", 0, raw_get_info))
+	if (raw_proc_init())
 		goto out_raw;
 	if (!proc_net_create("tcp", 0, tcp_get_info))
 		goto out_tcp;
@@ -1188,7 +1192,7 @@ int __init ipv4_proc_init(void)
 out_udp:
 	proc_net_remove("tcp");
 out_tcp:
-	proc_net_remove("raw");
+	raw_proc_exit();
 out_raw:
 	rc = -ENOMEM;
 	goto out;

net/ipv4/ah.c

@@ -189,7 +189,7 @@ int ah_output(struct sk_buff *skb)
 		top_iph->saddr = x->props.saddr.xfrm4_addr;
 		top_iph->daddr = x->id.daddr.xfrm4_addr;
 		ah = (struct ip_auth_hdr*)(top_iph+1);
-		ah->nexthdr = IPPROTO_IP;
+		ah->nexthdr = IPPROTO_IPIP;
 	} else {
 		memcpy(&tmp_iph, skb->data, iph->ihl*4);
 		top_iph = (struct iphdr*)skb_push(skb, x->props.header_len);

net/ipv4/esp.c

@@ -190,11 +190,10 @@ esp_hmac_digest(struct esp_data *esp, struct sk_buff *skb, int offset,
 	struct crypto_tfm *tfm = esp->auth.tfm;
 	char *digest = esp->auth.work_digest;
 
-	memset(auth_data, 0, esp->auth.authlen);
  	crypto_hmac_init(tfm, esp->auth.key, &esp->auth.key_len);
 	skb_digest_walk(skb, tfm, offset, len);
 	crypto_hmac_final(tfm, esp->auth.key, &esp->auth.key_len, digest);
-	memcpy(auth_data, digest, crypto_tfm_alg_digestsize(tfm));
+	memcpy(auth_data, digest, esp->auth.authlen);
 }
 
 /* Check that skb data bits are writable. If they are not, copy data
@@ -370,7 +369,7 @@ int esp_output(struct sk_buff *skb)
 	if (x->props.mode) {
 		top_iph = (struct iphdr*)skb_push(skb, x->props.header_len);
 		esph = (struct ip_esp_hdr*)(top_iph+1);
-		*(u8*)(trailer->tail - 1) = IPPROTO_IP;
+		*(u8*)(trailer->tail - 1) = IPPROTO_IPIP;
 		top_iph->ihl = 5;
 		top_iph->version = 4;
 		top_iph->tos = iph->tos;	/* DS disclosed */
@@ -463,16 +462,16 @@ int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 
 	/* If integrity check is required, do this. */
 	if (esp->auth.authlen) {
-		int icvsize = crypto_tfm_alg_digestsize(esp->auth.tfm);
-		u8 sum[icvsize];
-		u8 sum1[icvsize];
+		u8 sum[esp->auth.authlen];
+		u8 sum1[esp->auth.authlen];
 
 		esp->auth.digest(esp, skb, 0, skb->len-esp->auth.authlen, sum);
 
-		if (skb_copy_bits(skb, skb->len-esp->auth.authlen, sum1, icvsize))
+		if (skb_copy_bits(skb, skb->len-esp->auth.authlen, sum1, 
+				esp->auth.authlen))
 			BUG();
 
-		if (unlikely(memcmp(sum, sum1, icvsize))) {
+		if (unlikely(memcmp(sum, sum1, esp->auth.authlen))) {
 			x->stats.integrity_failed++;
 			goto out;
 		}
@@ -605,14 +604,20 @@ int esp_init_state(struct xfrm_state *x, void *args)
 	memset(esp, 0, sizeof(*esp));
 
 	if (x->aalg) {
+		int digestsize;
+
 		esp->auth.key = x->aalg->alg_key;
 		esp->auth.key_len = (x->aalg->alg_key_len+7)/8;
 		esp->auth.tfm = crypto_alloc_tfm(x->aalg->alg_name, 0);
 		if (esp->auth.tfm == NULL)
 			goto error;
 		esp->auth.digest = esp_hmac_digest;
-		esp->auth.authlen = crypto_tfm_alg_digestsize(esp->auth.tfm);
-		esp->auth.work_digest = kmalloc(esp->auth.authlen, GFP_KERNEL);
+		digestsize = crypto_tfm_alg_digestsize(esp->auth.tfm);
+		/* XXX RFC2403 and RFC 2404 truncate auth to 96 bit */
+		esp->auth.authlen = 12;
+		if (esp->auth.authlen > digestsize) /* XXX */
+			BUG();
+		esp->auth.work_digest = kmalloc(digestsize, GFP_KERNEL);
 		if (!esp->auth.work_digest)
 			goto error;
 	}

net/ipv4/fib_hash.c

@@ -1092,16 +1092,4 @@ void __init fib_proc_exit(void)
 {
 	remove_proc_entry("route", proc_net);
 }
-
-#else /* CONFIG_PROC_FS */
-
-int __init fib_proc_init(void)
-{
-	return 0;
-}
-
-void __init fib_proc_exit(void)
-{
-	return 0;
-}
 #endif /* CONFIG_PROC_FS */

net/ipv4/ip_sockglue.c

@@ -626,6 +626,7 @@ int ip_setsockopt(struct sock *sk, int level, int optname, char *optval, int opt
 	                break;			
  
 		case IP_IPSEC_POLICY:
+		case IP_XFRM_POLICY:
 			err = xfrm_user_policy(sk, optname, optval, optlen);
 			break;
 

net/ipv4/netfilter/ip_nat_helper.c

@@ -361,8 +361,6 @@ helper_cmp(const struct ip_nat_helper *helper,
 	return ip_ct_tuple_mask_cmp(tuple, &helper->tuple, &helper->mask);
 }
 
-#define MODULE_MAX_NAMELEN		32
-
 int ip_nat_helper_register(struct ip_nat_helper *me)
 {
 	int ret = 0;
@@ -374,14 +372,13 @@ int ip_nat_helper_register(struct ip_nat_helper *me)
 		    && ct_helper->me) {
 			__MOD_INC_USE_COUNT(ct_helper->me);
 		} else {
-#ifdef CONFIG_MODULES
 			/* We are a NAT helper for protocol X.  If we need
 			 * respective conntrack helper for protoccol X, compute
 			 * conntrack helper name and try to load module */
-			char name[MODULE_MAX_NAMELEN];
-			const char *tmp = me->me->name;
+			char name[MODULE_NAME_LEN];
+			const char *tmp = module_name(me->me);
 			
-			if (strlen(tmp) + 6 > MODULE_MAX_NAMELEN) {
+			if (strlen(tmp) + 6 > MODULE_NAME_LEN) {
 				printk("%s: unable to "
 				       "compute conntrack helper name "
 				       "from %s\n", __FUNCTION__, tmp);
@@ -403,7 +400,6 @@ int ip_nat_helper_register(struct ip_nat_helper *me)
 			       "because kernel was compiled without kernel "
 			       "module loader support\n", name);
 			return -EBUSY;
-#endif
 #endif
 		}
 	}

net/ipv4/proc.c

@@ -23,30 +23,21 @@
  *		Alan Cox	:	Handle dead sockets properly.
  *	Gerhard Koerting	:	Show both timers
  *		Alan Cox	:	Allow inode to be NULL (kernel socket)
- *	Andi Kleen		:	Add support for open_requests and 
+ *	Andi Kleen		:	Add support for open_requests and
  *					split functions for more readibility.
  *	Andi Kleen		:	Add support for /proc/net/netstat
+ *	Arnaldo C. Melo		:	Convert to seq_file
  *
  *		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.
  */
-#include <asm/system.h>
-#include <linux/sched.h>
-#include <linux/socket.h>
-#include <linux/net.h>
-#include <linux/un.h>
-#include <linux/in.h>
-#include <linux/param.h>
-#include <linux/inet.h>
-#include <linux/netdevice.h>
-#include <net/ip.h>
+#include <linux/types.h>
 #include <net/icmp.h>
 #include <net/protocol.h>
 #include <net/tcp.h>
 #include <net/udp.h>
-#include <linux/skbuff.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <net/sock.h>
@@ -57,7 +48,7 @@ static int fold_prot_inuse(struct proto *proto)
 	int res = 0;
 	int cpu;
 
-	for (cpu=0; cpu<NR_CPUS; cpu++)
+	for (cpu = 0; cpu < NR_CPUS; cpu++)
 		res += proto->stats[cpu].inuse;
 
 	return res;
@@ -66,38 +57,35 @@ static int fold_prot_inuse(struct proto *proto)
 /*
  *	Report socket allocation statistics [mea@utu.fi]
  */
-int afinet_get_info(char *buffer, char **start, off_t offset, int length)
+static int sockstat_seq_show(struct seq_file *seq, void *v)
 {
-	/* From  net/socket.c  */
-	extern int socket_get_info(char *, char **, off_t, int);
-
-	int len  = socket_get_info(buffer,start,offset,length);
-
-	len += sprintf(buffer+len,"TCP: inuse %d orphan %d tw %d alloc %d mem %d\n",
-		       fold_prot_inuse(&tcp_prot),
-		       atomic_read(&tcp_orphan_count), tcp_tw_count,
-		       atomic_read(&tcp_sockets_allocated),
-		       atomic_read(&tcp_memory_allocated));
-	len += sprintf(buffer+len,"UDP: inuse %d\n",
-		       fold_prot_inuse(&udp_prot));
-	len += sprintf(buffer+len,"RAW: inuse %d\n",
-		       fold_prot_inuse(&raw_prot));
-	len += sprintf(buffer+len, "FRAG: inuse %d memory %d\n",
-		       ip_frag_nqueues, atomic_read(&ip_frag_mem));
-	if (offset >= len)
-	{
-		*start = buffer;
-		return 0;
-	}
-	*start = buffer + offset;
-	len -= offset;
-	if (len > length)
-		len = length;
-	if (len < 0)
-		len = 0;
-	return len;
+	/* From net/socket.c */
+	extern void socket_seq_show(struct seq_file *seq);
+
+	socket_seq_show(seq);
+	seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %d\n",
+		   fold_prot_inuse(&tcp_prot), atomic_read(&tcp_orphan_count),
+		   tcp_tw_count, atomic_read(&tcp_sockets_allocated),
+		   atomic_read(&tcp_memory_allocated));
+	seq_printf(seq, "UDP: inuse %d\n", fold_prot_inuse(&udp_prot));
+	seq_printf(seq, "RAW: inuse %d\n", fold_prot_inuse(&raw_prot));
+	seq_printf(seq,  "FRAG: inuse %d memory %d\n", ip_frag_nqueues,
+		   atomic_read(&ip_frag_mem));
+	return 0;
+}
+
+static int sockstat_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, sockstat_seq_show, NULL);
 }
 
+static struct file_operations sockstat_seq_fops = {
+	.open	 = sockstat_seq_open,
+	.read	 = seq_read,
+	.llseek	 = seq_lseek,
+	.release = single_release,
+};
+
 static unsigned long fold_field(unsigned long *begin, int sz, int nr)
 {
 	unsigned long res = 0;
@@ -105,63 +93,84 @@ static unsigned long fold_field(unsigned long *begin, int sz, int nr)
 
 	sz /= sizeof(unsigned long);
 
-	for (i=0; i<NR_CPUS; i++) {
-		res += begin[2*i*sz + nr];
-		res += begin[(2*i+1)*sz + nr];
+	for (i = 0; i < NR_CPUS; i++) {
+		res += begin[2 * i * sz + nr];
+		res += begin[(2 * i + 1) * sz + nr];
 	}
 	return res;
 }
 
-/* 
+/*
  *	Called from the PROCfs module. This outputs /proc/net/snmp.
  */
- 
-int snmp_get_info(char *buffer, char **start, off_t offset, int length)
+static int snmp_seq_show(struct seq_file *seq, void *v)
 {
 	extern int sysctl_ip_default_ttl;
-	int len, i;
-
-	len = sprintf (buffer,
-		"Ip: Forwarding DefaultTTL InReceives InHdrErrors InAddrErrors ForwDatagrams InUnknownProtos InDiscards InDelivers OutRequests OutDiscards OutNoRoutes ReasmTimeout ReasmReqds ReasmOKs ReasmFails FragOKs FragFails FragCreates\n"
-		"Ip: %d %d", ipv4_devconf.forwarding ? 1 : 2, sysctl_ip_default_ttl);
-	for (i=0; i<offsetof(struct ip_mib, __pad)/sizeof(unsigned long); i++)
-		len += sprintf(buffer+len, " %lu", fold_field((unsigned long*)ip_statistics, sizeof(struct ip_mib), i));
-
-	len += sprintf (buffer + len,
-		"\nIcmp: InMsgs InErrors InDestUnreachs InTimeExcds InParmProbs InSrcQuenchs InRedirects InEchos InEchoReps InTimestamps InTimestampReps InAddrMasks InAddrMaskReps OutMsgs OutErrors OutDestUnreachs OutTimeExcds OutParmProbs OutSrcQuenchs OutRedirects OutEchos OutEchoReps OutTimestamps OutTimestampReps OutAddrMasks OutAddrMaskReps\n"
-		  "Icmp:");
-	for (i=0; i<offsetof(struct icmp_mib, dummy)/sizeof(unsigned long); i++)
-		len += sprintf(buffer+len, " %lu", fold_field((unsigned long*)icmp_statistics, sizeof(struct icmp_mib), i));
-
-	len += sprintf (buffer + len,
-		"\nTcp: RtoAlgorithm RtoMin RtoMax MaxConn ActiveOpens PassiveOpens AttemptFails EstabResets CurrEstab InSegs OutSegs RetransSegs InErrs OutRsts\n"
-		  "Tcp:");
-	for (i=0; i<offsetof(struct tcp_mib, __pad)/sizeof(unsigned long); i++)
-		len += sprintf(buffer+len, " %lu", fold_field((unsigned long*)tcp_statistics, sizeof(struct tcp_mib), i));
-
-	len += sprintf (buffer + len,
-		"\nUdp: InDatagrams NoPorts InErrors OutDatagrams\n"
-		  "Udp:");
-	for (i=0; i<offsetof(struct udp_mib, __pad)/sizeof(unsigned long); i++)
-		len += sprintf(buffer+len, " %lu", fold_field((unsigned long*)udp_statistics, sizeof(struct udp_mib), i));
-
-	len += sprintf (buffer + len, "\n");
-
-	if (offset >= len)
-	{
-		*start = buffer;
-		return 0;
-	}
-	*start = buffer + offset;
-	len -= offset;
-	if (len > length)
-		len = length;
-	if (len < 0)
-		len = 0; 
-	return len;
+	int i;
+
+	seq_printf(seq, "Ip: Forwarding DefaultTTL InReceives InHdrErrors "
+			"InAddrErrors ForwDatagrams InUnknownProtos "
+			"InDiscards InDelivers OutRequests OutDiscards "
+			"OutNoRoutes ReasmTimeout ReasmReqds ReasmOKs "
+			"ReasmFails FragOKs FragFails FragCreates\nIp: %d %d",
+			ipv4_devconf.forwarding ? 1 : 2, sysctl_ip_default_ttl);
+
+	for (i = 0;
+	     i < offsetof(struct ip_mib, __pad) / sizeof(unsigned long); i++)
+		seq_printf(seq, " %lu",
+			   fold_field((unsigned long *)ip_statistics,
+				      sizeof(struct ip_mib), i));
+
+	seq_printf(seq, "\nIcmp: InMsgs InErrors InDestUnreachs InTimeExcds "
+			"InParmProbs InSrcQuenchs InRedirects InEchos "
+			"InEchoReps InTimestamps InTimestampReps InAddrMasks "
+			"InAddrMaskReps OutMsgs OutErrors OutDestUnreachs "
+			"OutTimeExcds OutParmProbs OutSrcQuenchs OutRedirects "
+			"OutEchos OutEchoReps OutTimestamps OutTimestampReps "
+			"OutAddrMasks OutAddrMaskReps\nIcmp:");
+
+	for (i = 0;
+	     i < offsetof(struct icmp_mib, dummy) / sizeof(unsigned long); i++)
+		seq_printf(seq, " %lu",
+			   fold_field((unsigned long *)icmp_statistics,
+				      sizeof(struct icmp_mib), i));
+
+	seq_printf(seq, "\nTcp: RtoAlgorithm RtoMin RtoMax MaxConn ActiveOpens "
+			"PassiveOpens AttemptFails EstabResets CurrEstab "
+			"InSegs OutSegs RetransSegs InErrs OutRsts\nTcp:");
+
+	for (i = 0;
+	     i < offsetof(struct tcp_mib, __pad) / sizeof(unsigned long); i++)
+		seq_printf(seq, " %lu",
+			   fold_field((unsigned long *)tcp_statistics,
+				      sizeof(struct tcp_mib), i));
+
+	seq_printf(seq, "\nUdp: InDatagrams NoPorts InErrors OutDatagrams\n"
+			"Udp:");
+
+	for (i = 0;
+	     i < offsetof(struct udp_mib, __pad) / sizeof(unsigned long); i++)
+		seq_printf(seq, " %lu",
+			   fold_field((unsigned long *)udp_statistics,
+				      sizeof(struct udp_mib), i));
+
+	seq_putc(seq, '\n');
+	return 0;
+}
+
+static int snmp_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, snmp_seq_show, NULL);
 }
 
-/* 
+static struct file_operations snmp_seq_fops = {
+	.open	 = snmp_seq_open,
+	.read	 = seq_read,
+	.llseek	 = seq_lseek,
+	.release = single_release,
+};
+
+/*
  *	Output /proc/net/netstat
  */
 static int netstat_seq_show(struct seq_file *seq, void *v)
@@ -181,7 +190,8 @@ static int netstat_seq_show(struct seq_file *seq, void *v)
 		      " TCPPureAcks TCPHPAcks"
 		      " TCPRenoRecovery TCPSackRecovery"
 		      " TCPSACKReneging"
-		      " TCPFACKReorder TCPSACKReorder TCPRenoReorder TCPTSReorder"
+		      " TCPFACKReorder TCPSACKReorder TCPRenoReorder"
+		      " TCPTSReorder"
 		      " TCPFullUndo TCPPartialUndo TCPDSACKUndo TCPLossUndo"
 		      " TCPLoss TCPLostRetransmit"
 		      " TCPRenoFailures TCPSackFailures TCPLossFailures"
@@ -189,14 +199,14 @@ static int netstat_seq_show(struct seq_file *seq, void *v)
 		      " TCPTimeouts"
 		      " TCPRenoRecoveryFail TCPSackRecoveryFail"
 		      " TCPSchedulerFailed TCPRcvCollapsed"
-		      " TCPDSACKOldSent TCPDSACKOfoSent TCPDSACKRecv TCPDSACKOfoRecv"
+		      " TCPDSACKOldSent TCPDSACKOfoSent TCPDSACKRecv"
+		      " TCPDSACKOfoRecv"
 		      " TCPAbortOnSyn TCPAbortOnData TCPAbortOnClose"
 		      " TCPAbortOnMemory TCPAbortOnTimeout TCPAbortOnLinger"
 		      " TCPAbortFailed TCPMemoryPressures\n"
 		      "TcpExt:");
 	for (i = 0;
-	     i < offsetof(struct linux_mib, __pad) / sizeof(unsigned long);
-	     i++)
+	     i < offsetof(struct linux_mib, __pad) / sizeof(unsigned long); i++)
 		seq_printf(seq, " %lu",
 			   fold_field((unsigned long *)net_statistics,
 				      sizeof(struct linux_mib), i));
@@ -219,20 +229,26 @@ static struct file_operations netstat_seq_fops = {
 int __init ip_misc_proc_init(void)
 {
 	int rc = 0;
-	struct proc_dir_entry *p = create_proc_entry("netstat", S_IRUGO, proc_net);
+	struct proc_dir_entry *p;
 
+	p = create_proc_entry("netstat", S_IRUGO, proc_net);
 	if (!p)
 		goto out_netstat;
 	p->proc_fops = &netstat_seq_fops;
 
-	if (!proc_net_create("snmp", 0, snmp_get_info))
+	p = create_proc_entry("snmp", S_IRUGO, proc_net);
+	if (!p)
 		goto out_snmp;
-	if (!proc_net_create("sockstat", 0, afinet_get_info))
+	p->proc_fops = &snmp_seq_fops;
+
+	p = create_proc_entry("sockstat", S_IRUGO, proc_net);
+	if (!p)
 		goto out_sockstat;
+	p->proc_fops = &sockstat_seq_fops;
 out:
 	return rc;
 out_sockstat:
-	proc_net_remove("snmp");
+	remove_proc_entry("snmp", proc_net);
 out_snmp:
 	remove_proc_entry("netstat", proc_net);
 out_netstat:

net/ipv4/raw.c

@@ -40,31 +40,42 @@
  */
  
 #include <linux/config.h> 
-#include <asm/system.h>
+#include <asm/atomic.h>
+#include <asm/byteorder.h>
+#include <asm/current.h>
 #include <asm/uaccess.h>
 #include <asm/ioctls.h>
 #include <linux/types.h>
-#include <linux/sched.h>
+#include <linux/stddef.h>
+#include <linux/slab.h>
 #include <linux/errno.h>
-#include <linux/timer.h>
-#include <linux/mm.h>
+#include <linux/aio.h>
 #include <linux/kernel.h>
-#include <linux/fcntl.h>
+#include <linux/spinlock.h>
+#include <linux/sockios.h>
 #include <linux/socket.h>
 #include <linux/in.h>
-#include <linux/inet.h>
 #include <linux/netdevice.h>
-#include <linux/mroute.h>
-#include <net/tcp.h>
-#include <net/protocol.h>
+#include <linux/in_route.h>
+#include <linux/route.h>
+#include <linux/tcp.h>
 #include <linux/skbuff.h>
+#include <net/dst.h>
 #include <net/sock.h>
+#include <linux/gfp.h>
+#include <linux/ip.h>
+#include <net/ip.h>
 #include <net/icmp.h>
 #include <net/udp.h>
 #include <net/raw.h>
+#include <net/snmp.h>
 #include <net/inet_common.h>
 #include <net/checksum.h>
 #include <net/xfrm.h>
+#include <linux/rtnetlink.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/netfilter.h>
 #include <linux/netfilter_ipv4.h>
 
 struct sock *raw_v4_htable[RAWV4_HTABLE_SIZE];
@@ -656,7 +667,95 @@ static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg)
 	}
 }
 
-static void get_raw_sock(struct sock *sp, char *tmpbuf, int i)
+struct proto raw_prot = {
+	.name =		"RAW",
+	.close =	raw_close,
+	.connect =	udp_connect,
+	.disconnect =	udp_disconnect,
+	.ioctl =	raw_ioctl,
+	.init =		raw_init,
+	.setsockopt =	raw_setsockopt,
+	.getsockopt =	raw_getsockopt,
+	.sendmsg =	raw_sendmsg,
+	.recvmsg =	raw_recvmsg,
+	.bind =		raw_bind,
+	.backlog_rcv =	raw_rcv_skb,
+	.hash =		raw_v4_hash,
+	.unhash =	raw_v4_unhash,
+};
+
+#ifdef CONFIG_PROC_FS
+struct raw_iter_state {
+	int bucket;
+};
+
+#define raw_seq_private(seq) ((struct raw_iter_state *)&seq->private)
+
+static struct sock *raw_get_first(struct seq_file *seq)
+{
+	struct sock *sk = NULL;
+	struct raw_iter_state* state = raw_seq_private(seq);
+
+	for (state->bucket = 0; state->bucket < RAWV4_HTABLE_SIZE; ++state->bucket) {
+		sk = raw_v4_htable[state->bucket];
+		while (sk && sk->family != PF_INET)
+			sk = sk->next;
+		if (sk)
+			break;
+	}
+	return sk;
+}
+
+static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk)
+{
+	struct raw_iter_state* state = raw_seq_private(seq);
+
+	do {
+		sk = sk->next;
+try_again:
+	} while (sk && sk->family != PF_INET);
+
+	if (!sk && ++state->bucket < RAWV4_HTABLE_SIZE) {
+		sk = raw_v4_htable[state->bucket];
+		goto try_again;
+	}
+	return sk;
+}
+
+static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos)
+{
+	struct sock *sk = raw_get_first(seq);
+
+	if (sk)
+		while (pos && (sk = raw_get_next(seq, sk)) != NULL)
+			--pos;
+	return pos ? NULL : sk;
+}
+
+static void *raw_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	read_lock(&raw_v4_lock);
+	return *pos ? raw_get_idx(seq, *pos) : (void *)1;
+}
+
+static void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct sock *sk;
+
+	if (v == (void *)1)
+		sk = raw_get_first(seq);
+	else
+		sk = raw_get_next(seq, v);
+	++*pos;
+	return sk;
+}
+
+static void raw_seq_stop(struct seq_file *seq, void *v)
+{
+	read_unlock(&raw_v4_lock);
+}
+
+static __inline__ char *get_raw_sock(struct sock *sp, char *tmpbuf, int i)
 {
 	struct inet_opt *inet = inet_sk(sp);
 	unsigned int dest = inet->daddr,
@@ -668,65 +767,63 @@ static void get_raw_sock(struct sock *sp, char *tmpbuf, int i)
 		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p",
 		i, src, srcp, dest, destp, sp->state, 
 		atomic_read(&sp->wmem_alloc), atomic_read(&sp->rmem_alloc),
-		0, 0L, 0,
-		sock_i_uid(sp), 0,
-		sock_i_ino(sp),
+		0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp),
 		atomic_read(&sp->refcnt), sp);
+	return tmpbuf;
 }
 
-int raw_get_info(char *buffer, char **start, off_t offset, int length)
+static int raw_seq_show(struct seq_file *seq, void *v)
 {
-	int len = 0, num = 0, i;
-	off_t pos = 128;
-	off_t begin;
 	char tmpbuf[129];
 
-	if (offset < 128) 
-		len += sprintf(buffer, "%-127s\n",
+	if (v == (void *)1)
+		seq_printf(seq, "%-127s\n",
 			       "  sl  local_address rem_address   st tx_queue "
 			       "rx_queue tr tm->when retrnsmt   uid  timeout "
 			       "inode");
-	read_lock(&raw_v4_lock);
-	for (i = 0; i < RAWV4_HTABLE_SIZE; i++) {
-		struct sock *sk;
-
-		for (sk = raw_v4_htable[i]; sk; sk = sk->next, num++) {
-			if (sk->family != PF_INET)
-				continue;
-			pos += 128;
-			if (pos <= offset)
-				continue;
-			get_raw_sock(sk, tmpbuf, i);
-			len += sprintf(buffer + len, "%-127s\n", tmpbuf);
-			if (len >= length)
-				goto out;
-		}
+	else {
+		struct raw_iter_state *state = raw_seq_private(seq);
+
+		seq_printf(seq, "%-127s\n",
+			   get_raw_sock(v, tmpbuf, state->bucket));
 	}
-out:
-	read_unlock(&raw_v4_lock);
-	begin = len - (pos - offset);
-	*start = buffer + begin;
-	len -= begin;
-	if (len > length)
-		len = length;
-	if (len < 0)
-		len = 0; 
-	return len;
+	return 0;
 }
 
-struct proto raw_prot = {
-	.name =		"RAW",
-	.close =	raw_close,
-	.connect =	udp_connect,
-	.disconnect =	udp_disconnect,
-	.ioctl =	raw_ioctl,
-	.init =		raw_init,
-	.setsockopt =	raw_setsockopt,
-	.getsockopt =	raw_getsockopt,
-	.sendmsg =	raw_sendmsg,
-	.recvmsg =	raw_recvmsg,
-	.bind =		raw_bind,
-	.backlog_rcv =	raw_rcv_skb,
-	.hash =		raw_v4_hash,
-	.unhash =	raw_v4_unhash,
+static struct seq_operations raw_seq_ops = {
+	.start = raw_seq_start,
+	.next  = raw_seq_next,
+	.stop  = raw_seq_stop,
+	.show  = raw_seq_show,
+};
+
+static int raw_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &raw_seq_ops);
+}
+
+static struct file_operations raw_seq_fops = {
+	.open	 = raw_seq_open,
+	.read	 = seq_read,
+	.llseek	 = seq_lseek,
+	.release = seq_release,
 };
+
+int __init raw_proc_init(void)
+{
+	struct proc_dir_entry *p;
+	int rc = 0;
+
+	p = create_proc_entry("raw", S_IRUGO, proc_net);
+	if (p)
+		p->proc_fops = &raw_seq_fops;
+	else
+		rc = -ENOMEM;
+	return rc;
+}
+
+void __init raw_proc_exit(void)
+{
+	remove_proc_entry("raw", proc_net);
+}
+#endif /* CONFIG_PROC_FS */

net/ipv4/udp.c

@@ -944,7 +944,7 @@ static int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
 	/*
 	 *	Charge it to the socket, dropping if the queue is full.
 	 */
-	if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb)) {
+	if (!xfrm_policy_check(sk, XFRM_POLICY_IN, skb)) {
 		kfree_skb(skb);
 		return -1;
 	}
@@ -1377,16 +1377,4 @@ void __init udp_proc_exit(void)
 {
 	remove_proc_entry("udp", proc_net);
 }
-
-#else /* CONFIG_PROC_FS */
-
-int __init udp_proc_init(void)
-{
-	return 0;
-}
-
-void __init udp_proc_exit(void)
-{
-	return 0;
-}
 #endif /* CONFIG_PROC_FS */

net/ipv4/xfrm_input.c

@@ -91,7 +91,7 @@ int xfrm4_rcv(struct sk_buff *skb)
 		iph = skb->nh.iph;
 
 		if (x->props.mode) {
-			if (iph->protocol != IPPROTO_IP)
+			if (iph->protocol != IPPROTO_IPIP)
 				goto drop;
 			skb->nh.raw = skb->data;
 			iph = skb->nh.iph;

net/ipv4/xfrm_state.c

@@ -386,7 +386,7 @@ xfrm_state_lookup(u32 daddr, u32 spi, u8 proto)
 }
 
 struct xfrm_state *
-xfrm_find_acq(u8 mode, u16 reqid, u8 proto, u32 daddr, u32 saddr)
+xfrm_find_acq(u8 mode, u16 reqid, u8 proto, u32 daddr, u32 saddr, int create)
 {
 	struct xfrm_state *x, *x0;
 	unsigned h = ntohl(daddr);
@@ -400,10 +400,11 @@ xfrm_find_acq(u8 mode, u16 reqid, u8 proto, u32 daddr, u32 saddr)
 		    mode == x->props.mode &&
 		    proto == x->id.proto &&
 		    saddr == x->props.saddr.xfrm4_addr &&
-		    reqid == x->props.reqid) {
+		    reqid == x->props.reqid &&
+		    x->km.state == XFRM_STATE_ACQ) {
 			    if (!x0)
 				    x0 = x;
-			    if (x->km.state != XFRM_STATE_ACQ)
+			    if (x->id.spi)
 				    continue;
 			    x0 = x;
 			    break;
@@ -411,7 +412,7 @@ xfrm_find_acq(u8 mode, u16 reqid, u8 proto, u32 daddr, u32 saddr)
 	}
 	if (x0) {
 		atomic_inc(&x0->refcnt);
-	} else if ((x0 = xfrm_state_alloc()) != NULL) {
+	} else if (create && (x0 = xfrm_state_alloc()) != NULL) {
 		x0->sel.daddr.xfrm4_addr = daddr;
 		x0->sel.daddr.xfrm4_mask = ~0;
 		x0->sel.saddr.xfrm4_addr = saddr;

net/ipv4/xfrm_user.c

+/* xfrm_user.c: User interface to configure xfrm engine.
+ *
+ * Copyright (C) 2002 David S. Miller (davem@redhat.com)
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/socket.h>
+#include <linux/string.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <linux/pfkeyv2.h>
+#include <linux/ipsec.h>
+#include <linux/init.h>
+#include <net/sock.h>
+#include <net/xfrm.h>
+
+static struct sock *xfrm_nl;
+
+static int verify_one_alg(struct rtattr **xfrma, enum xfrm_attr_type_t type)
+{
+	struct rtattr *rt = xfrma[type];
+	struct xfrm_algo *algp;
+
+	if (!rt)
+		return 0;
+
+	if ((rt->rta_len - sizeof(*rt)) < sizeof(*algp))
+		return -EINVAL;
+
+	algp = RTA_DATA(rt);
+	switch (type) {
+	case XFRMA_ALG_AUTH:
+	case XFRMA_ALG_CRYPT:
+		if (!algp->alg_key_len)
+			return -EINVAL;
+		break;
+
+	case XFRMA_ALG_COMP:
+		/* Zero length keys are legal.  */
+		break;
+
+	default:
+		return -EINVAL;
+	};
+
+	algp->alg_name[CRYPTO_MAX_ALG_NAME - 1] = '\0';
+	return 0;
+}
+
+static int verify_newsa_info(struct xfrm_usersa_info *p,
+			     struct rtattr **xfrma)
+{
+	int err;
+
+	err = -EINVAL;
+	switch (p->family) {
+	case AF_INET:
+		break;
+
+	case AF_INET6: /* XXX */
+		err = -EAFNOSUPPORT;
+
+		/* fallthru */
+	default:
+		goto out;
+	};
+
+	err = -EINVAL;
+	switch (p->id.proto) {
+	case IPPROTO_AH:
+		if (!xfrma[XFRMA_ALG_AUTH]	||
+		    xfrma[XFRMA_ALG_CRYPT]	||
+		    xfrma[XFRMA_ALG_COMP])
+			goto out;
+		break;
+
+	case IPPROTO_ESP:
+		if ((!xfrma[XFRMA_ALG_AUTH] &&
+		     !xfrma[XFRMA_ALG_CRYPT])	||
+		    xfrma[XFRMA_ALG_COMP])
+			goto out;
+		break;
+
+	case IPPROTO_COMP:
+		if (!xfrma[XFRMA_ALG_COMP]	||
+		    xfrma[XFRMA_ALG_AUTH]	||
+		    xfrma[XFRMA_ALG_CRYPT])
+			goto out;
+		break;
+
+	default:
+		goto out;
+	};
+
+	if ((err = verify_one_alg(xfrma, XFRMA_ALG_AUTH)))
+		goto out;
+	if ((err = verify_one_alg(xfrma, XFRMA_ALG_CRYPT)))
+		goto out;
+	if ((err = verify_one_alg(xfrma, XFRMA_ALG_COMP)))
+		goto out;
+
+	err = -EINVAL;
+	switch (p->mode) {
+	case 0:
+	case 1:
+		break;
+
+	default:
+		goto out;
+	};
+
+	err = 0;
+
+out:
+	return err;
+}
+
+static int attach_one_algo(struct xfrm_algo **algpp, struct rtattr *u_arg)
+{
+	struct rtattr *rta = u_arg;
+	struct xfrm_algo *p, *ualg;
+
+	if (!rta)
+		return 0;
+
+	ualg = RTA_DATA(rta);
+	p = kmalloc(sizeof(*ualg) + ualg->alg_key_len, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	memcpy(p, ualg, sizeof(*ualg) + ualg->alg_key_len);
+	*algpp = p;
+	return 0;
+}
+
+static void copy_from_user_state(struct xfrm_state *x, struct xfrm_usersa_info *p)
+{
+	memcpy(&x->id, &p->id, sizeof(x->id));
+	memcpy(&x->sel, &p->sel, sizeof(x->sel));
+	memcpy(&x->lft, &p->lft, sizeof(x->lft));
+	x->props.mode = p->mode;
+	x->props.replay_window = p->replay_window;
+	x->props.reqid = p->reqid;
+	x->props.family = p->family;
+	x->props.saddr = x->sel.saddr;
+}
+
+static struct xfrm_state *xfrm_state_construct(struct xfrm_usersa_info *p,
+					       struct rtattr **xfrma,
+					       int *errp)
+{
+	struct xfrm_state *x = xfrm_state_alloc();
+	int err = -ENOMEM;
+
+	if (!x)
+		goto error_no_put;
+
+	copy_from_user_state(x, p);
+
+	if ((err = attach_one_algo(&x->aalg, xfrma[XFRMA_ALG_AUTH])))
+		goto error;
+	if ((err = attach_one_algo(&x->ealg, xfrma[XFRMA_ALG_CRYPT])))
+		goto error;
+	if ((err = attach_one_algo(&x->calg, xfrma[XFRMA_ALG_COMP])))
+		goto error;
+
+	err = -ENOENT;
+	x->type = xfrm_get_type(x->id.proto);
+	if (x->type == NULL)
+		goto error;
+
+	err = x->type->init_state(x, NULL);
+	if (err)
+		goto error;
+
+	x->curlft.add_time = (unsigned long) xtime.tv_sec;
+	x->km.state = XFRM_STATE_VALID;
+	x->km.seq = p->seq;
+
+	return x;
+
+error:
+	xfrm_state_put(x);
+error_no_put:
+	*errp = err;
+	return NULL;
+}
+
+static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
+{
+	struct xfrm_usersa_info *p = NLMSG_DATA(nlh);
+	struct xfrm_state *x, *x1;
+	int err;
+
+	err = verify_newsa_info(p, (struct rtattr **) xfrma);
+	if (err)
+		return err;
+
+	x = xfrm_state_construct(p, (struct rtattr **) xfrma, &err);
+	if (!x)
+		return err;
+
+	x1 = xfrm_state_lookup(x->props.saddr.xfrm4_addr,
+			       x->id.spi, x->id.proto);
+	if (x1) {
+		xfrm_state_put(x);
+		xfrm_state_put(x1);
+		return -EEXIST;
+	}
+
+	xfrm_state_insert(x);
+
+	return 0;
+}
+
+static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
+{
+	struct xfrm_state *x;
+	struct xfrm_usersa_id *p = NLMSG_DATA(nlh);
+
+	x = xfrm_state_lookup(p->saddr.xfrm4_addr, p->spi, p->proto);
+	if (x == NULL)
+		return -ESRCH;
+
+	xfrm_state_delete(x);
+	xfrm_state_put(x);
+
+	return 0;
+}
+
+static void copy_to_user_state(struct xfrm_state *x, struct xfrm_usersa_info *p)
+{
+	memcpy(&p->id, &x->id, sizeof(p->id));
+	memcpy(&p->sel, &x->sel, sizeof(p->sel));
+	memcpy(&p->lft, &x->lft, sizeof(p->lft));
+	memcpy(&p->curlft, &x->curlft, sizeof(p->curlft));
+	memcpy(&p->stats, &x->stats, sizeof(p->stats));
+	p->mode = x->props.mode;
+	p->replay_window = x->props.replay_window;
+	p->reqid = x->props.reqid;
+	p->family = x->props.family;
+	p->seq = x->km.seq;
+}
+
+struct xfrm_dump_info {
+	struct sk_buff *in_skb;
+	struct sk_buff *out_skb;
+	u32 nlmsg_seq;
+	int start_idx;
+	int this_idx;
+};
+
+static int dump_one_state(struct xfrm_state *x, int count, void *ptr)
+{
+	struct xfrm_dump_info *sp = ptr;
+	struct sk_buff *in_skb = sp->in_skb;
+	struct sk_buff *skb = sp->out_skb;
+	struct xfrm_usersa_info *p;
+	struct nlmsghdr *nlh;
+	unsigned char *b = skb->tail;
+
+	if (sp->this_idx < sp->start_idx)
+		goto out;
+
+	nlh = NLMSG_PUT(skb, NETLINK_CB(in_skb).pid,
+			sp->nlmsg_seq,
+			XFRM_MSG_NEWSA, sizeof(*p));
+	nlh->nlmsg_flags = 0;
+
+	p = NLMSG_DATA(nlh);
+	copy_to_user_state(x, p);
+
+	if (x->aalg)
+		RTA_PUT(skb, XFRMA_ALG_AUTH, sizeof(*(x->aalg)), x->aalg);
+	if (x->ealg)
+		RTA_PUT(skb, XFRMA_ALG_CRYPT, sizeof(*(x->ealg)), x->ealg);
+	if (x->calg)
+		RTA_PUT(skb, XFRMA_ALG_COMP, sizeof(*(x->calg)), x->calg);
+
+	nlh->nlmsg_len = skb->tail - b;
+out:
+	sp->this_idx++;
+	return 0;
+
+nlmsg_failure:
+rtattr_failure:
+	skb_trim(skb, b - skb->data);
+	return -1;
+}
+
+static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct xfrm_dump_info info;
+
+	info.in_skb = cb->skb;
+	info.out_skb = skb;
+	info.nlmsg_seq = cb->nlh->nlmsg_seq;
+	info.this_idx = 0;
+	info.start_idx = cb->args[0];
+	(void) xfrm_state_walk(IPSEC_PROTO_ANY, dump_one_state, &info);
+	cb->args[0] = info.this_idx;
+
+	return skb->len;
+}
+
+static struct sk_buff *xfrm_state_netlink(struct sk_buff *in_skb,
+					  struct xfrm_state *x, u32 seq)
+{
+	struct xfrm_dump_info info;
+	struct sk_buff *skb;
+
+	skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC);
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid;
+	info.in_skb = in_skb;
+	info.out_skb = skb;
+	info.nlmsg_seq = seq;
+	info.this_idx = info.start_idx = 0;
+
+	if (dump_one_state(x, 0, &info)) {
+		kfree_skb(skb);
+		return NULL;
+	}
+
+	return skb;
+}
+
+static int xfrm_get_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
+{
+	struct xfrm_usersa_id *p = NLMSG_DATA(nlh);
+	struct xfrm_state *x;
+	struct sk_buff *resp_skb;
+	int err;
+
+	x = xfrm_state_lookup(p->saddr.xfrm4_addr, p->spi, p->proto);
+	err = -ESRCH;
+	if (x == NULL)
+		goto out_noput;
+
+	resp_skb = xfrm_state_netlink(skb, x, nlh->nlmsg_seq);
+	if (IS_ERR(resp_skb)) {
+		err = PTR_ERR(resp_skb);
+	} else {
+		err = netlink_unicast(xfrm_nl, resp_skb,
+				      NETLINK_CB(skb).pid, MSG_DONTWAIT);
+	}
+	xfrm_state_put(x);
+out_noput:
+	return err;
+}
+
+static int verify_userspi_info(struct xfrm_userspi_info *p)
+{
+	switch (p->info.id.proto) {
+	case IPPROTO_AH:
+	case IPPROTO_ESP:
+		break;
+
+	case IPPROTO_COMP:
+		/* IPCOMP spi is 16-bits. */
+		if (p->min >= 0x10000 ||
+		    p->max >= 0x10000)
+			return -EINVAL;
+
+	default:
+		return -EINVAL;
+	};
+
+	if (p->min > p->max)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
+{
+	struct xfrm_state *x;
+	struct xfrm_userspi_info *p;
+	struct sk_buff *resp_skb;
+	int err;
+
+	p = NLMSG_DATA(nlh);
+	err = verify_userspi_info(p);
+	if (err)
+		goto out_noput;
+	x = xfrm_find_acq(p->info.mode, p->info.reqid, p->info.id.proto,
+			  p->info.sel.daddr.xfrm4_addr,
+			  p->info.sel.saddr.xfrm4_addr, 1);
+	err = -ENOENT;
+	if (x == NULL)
+		goto out_noput;
+
+	resp_skb = ERR_PTR(-ENOENT);
+
+	spin_lock_bh(&x->lock);
+	if (x->km.state != XFRM_STATE_DEAD) {
+		xfrm_alloc_spi(x, p->min, p->max);
+		if (x->id.spi)
+			resp_skb = xfrm_state_netlink(skb, x, nlh->nlmsg_seq);
+	}
+	spin_unlock_bh(&x->lock);
+
+	if (IS_ERR(resp_skb)) {
+		err = PTR_ERR(resp_skb);
+		goto out;
+	}
+
+	err = netlink_unicast(xfrm_nl, resp_skb,
+			      NETLINK_CB(skb).pid, MSG_DONTWAIT);
+
+out:
+	xfrm_state_put(x);
+out_noput:
+	return err;
+}
+
+static int verify_policy_dir(__u8 dir)
+{
+	switch (dir) {
+	case XFRM_POLICY_IN:
+	case XFRM_POLICY_OUT:
+	case XFRM_POLICY_FWD:
+		break;
+
+	default:
+		return -EINVAL;
+	};
+
+	return 0;
+}
+
+static int verify_newpolicy_info(struct xfrm_userpolicy_info *p)
+{
+	switch (p->share) {
+	case XFRM_SHARE_ANY:
+	case XFRM_SHARE_SESSION:
+	case XFRM_SHARE_USER:
+	case XFRM_SHARE_UNIQUE:
+		break;
+
+	default:
+		return -EINVAL;
+	};
+
+	switch (p->action) {
+	case XFRM_POLICY_ALLOW:
+	case XFRM_POLICY_BLOCK:
+		break;
+
+	default:
+		return -EINVAL;
+	};
+
+	return verify_policy_dir(p->dir);
+}
+
+static void copy_templates(struct xfrm_policy *xp, struct xfrm_user_tmpl *ut,
+			   int nr)
+{
+	int i;
+
+	xp->xfrm_nr = nr;
+	for (i = 0; i < nr; i++, ut++) {
+		struct xfrm_tmpl *t = &xp->xfrm_vec[i];
+
+		memcpy(&t->id, &ut->id, sizeof(struct xfrm_id));
+		memcpy(&t->saddr, &ut->saddr,
+		       sizeof(xfrm_address_t));
+		t->reqid = ut->reqid;
+		t->mode = ut->mode;
+		t->share = ut->share;
+		t->optional = ut->optional;
+		t->aalgos = ut->aalgos;
+		t->ealgos = ut->ealgos;
+		t->calgos = ut->calgos;
+	}
+}
+
+static int copy_user_tmpl(struct xfrm_policy *pol, struct rtattr **xfrma)
+{
+	struct rtattr *rt = xfrma[XFRMA_TMPL];
+	struct xfrm_user_tmpl *utmpl;
+	int nr;
+
+	if (!rt) {
+		pol->xfrm_nr = 0;
+	} else {
+		nr = (rt->rta_len - sizeof(*rt)) / sizeof(*utmpl);
+
+		if (nr > XFRM_MAX_DEPTH)
+			return -EINVAL;
+
+		copy_templates(pol, RTA_DATA(rt), nr);
+	}
+	return 0;
+}
+
+static void copy_from_user_policy(struct xfrm_policy *xp, struct xfrm_userpolicy_info *p)
+{
+	xp->priority = p->priority;
+	xp->index = p->index;
+	memcpy(&xp->selector, &p->sel, sizeof(xp->selector));
+	memcpy(&xp->lft, &p->lft, sizeof(xp->lft));
+	xp->action = p->action;
+	xp->flags = p->flags;
+	xp->family = p->family;
+	/* XXX xp->share = p->share; */
+}
+
+static void copy_to_user_policy(struct xfrm_policy *xp, struct xfrm_userpolicy_info *p, int dir)
+{
+	memcpy(&p->sel, &xp->selector, sizeof(p->sel));
+	memcpy(&p->lft, &xp->lft, sizeof(p->lft));
+	memcpy(&p->curlft, &xp->curlft, sizeof(p->curlft));
+	p->priority = xp->priority;
+	p->index = xp->index;
+	p->family = xp->family;
+	p->dir = dir;
+	p->action = xp->action;
+	p->flags = xp->flags;
+	p->share = XFRM_SHARE_ANY; /* XXX xp->share */
+}
+
+static struct xfrm_policy *xfrm_policy_construct(struct xfrm_userpolicy_info *p, struct rtattr **xfrma, int *errp)
+{
+	struct xfrm_policy *xp = xfrm_policy_alloc(GFP_KERNEL);
+	int err;
+
+	if (!xp) {
+		*errp = -ENOMEM;
+		return NULL;
+	}
+
+	copy_from_user_policy(xp, p);
+	err = copy_user_tmpl(xp, xfrma);
+	if (err) {
+		*errp = err;
+		kfree(xp);
+		xp = NULL;
+	}
+
+	return xp;
+}
+
+static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
+{
+	struct xfrm_userpolicy_info *p = NLMSG_DATA(nlh);
+	struct xfrm_policy *xp;
+	int err;
+
+	err = verify_newpolicy_info(p);
+	if (err)
+		return err;
+
+	xp = xfrm_policy_construct(p, (struct rtattr **) xfrma, &err);
+	if (!xp)
+		return err;
+
+	err = xfrm_policy_insert(p->dir, xp, 1);
+	if (err) {
+		kfree(xp);
+		return err;
+	}
+
+	xfrm_pol_put(xp);
+
+	return 0;
+}
+
+static int xfrm_del_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
+{
+	struct xfrm_policy *xp;
+	struct xfrm_userpolicy_id *p;
+	int err;
+
+	p = NLMSG_DATA(nlh);
+
+	err = verify_policy_dir(p->dir);
+	if (err)
+		return err;
+
+	xp = xfrm_policy_delete(p->dir, &p->sel);
+	if (xp == NULL)
+		return -ENOENT;
+	xfrm_policy_kill(xp);
+	xfrm_pol_put(xp);
+	return 0;
+}
+
+static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr)
+{
+	struct xfrm_dump_info *sp = ptr;
+	struct xfrm_userpolicy_info *p;
+	struct sk_buff *in_skb = sp->in_skb;
+	struct sk_buff *skb = sp->out_skb;
+	struct nlmsghdr *nlh;
+	unsigned char *b = skb->tail;
+
+	if (sp->this_idx < sp->start_idx)
+		goto out;
+
+	nlh = NLMSG_PUT(skb, NETLINK_CB(in_skb).pid,
+			sp->nlmsg_seq,
+			XFRM_MSG_NEWPOLICY, sizeof(*p));
+	p = NLMSG_DATA(nlh);
+	nlh->nlmsg_flags = 0;
+
+	copy_to_user_policy(xp, p, dir);
+
+	if (xp->xfrm_nr) {
+		struct xfrm_user_tmpl vec[XFRM_MAX_DEPTH];
+		int i;
+
+		for (i = 0; i < xp->xfrm_nr; i++) {
+			struct xfrm_user_tmpl *up = &vec[i];
+			struct xfrm_tmpl *kp = &xp->xfrm_vec[i];
+
+			memcpy(&up->id, &kp->id, sizeof(up->id));
+			memcpy(&up->saddr, &kp->saddr, sizeof(up->saddr));
+			up->reqid = kp->reqid;
+			up->mode = kp->mode;
+			up->share = kp->share;
+			up->optional = kp->optional;
+			up->aalgos = kp->aalgos;
+			up->ealgos = kp->ealgos;
+			up->calgos = kp->calgos;
+		}
+		RTA_PUT(skb, XFRMA_TMPL,
+			(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr),
+			vec);
+	}
+
+	nlh->nlmsg_len = skb->tail - b;
+out:
+	sp->this_idx++;
+	return 0;
+
+nlmsg_failure:
+rtattr_failure:
+	skb_trim(skb, b - skb->data);
+	return -1;
+}
+
+static int xfrm_dump_policy(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct xfrm_dump_info info;
+
+	info.in_skb = cb->skb;
+	info.out_skb = skb;
+	info.nlmsg_seq = cb->nlh->nlmsg_seq;
+	info.start_idx = cb->args[0];
+	(void) xfrm_policy_walk(dump_one_policy, &info);
+	cb->args[0] = info.this_idx;
+
+	return skb->len;
+}
+
+static struct sk_buff *xfrm_policy_netlink(struct sk_buff *in_skb,
+					  struct xfrm_policy *xp,
+					  int dir, u32 seq)
+{
+	struct xfrm_dump_info info;
+	struct sk_buff *skb;
+
+	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid;
+	info.in_skb = in_skb;
+	info.out_skb = skb;
+	info.nlmsg_seq = seq;
+	info.this_idx = info.start_idx = 0;
+
+	if (dump_one_policy(xp, dir, 0, &info) < 0) {
+		kfree_skb(skb);
+		return NULL;
+	}
+
+	return skb;
+}
+
+static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
+{
+	struct xfrm_policy *xp;
+	struct xfrm_userpolicy_id *p;
+	struct sk_buff *resp_skb;
+	int err;
+
+	p = NLMSG_DATA(nlh);
+	xp = xfrm_policy_byid(p->dir, p->index, 0);
+	if (xp == NULL)
+		return -ENOENT;
+
+	resp_skb = xfrm_policy_netlink(skb, xp, p->dir, nlh->nlmsg_seq);
+	if (IS_ERR(resp_skb)) {
+		err = PTR_ERR(resp_skb);
+	} else {
+		err = netlink_unicast(xfrm_nl, resp_skb,
+				      NETLINK_CB(skb).pid, MSG_DONTWAIT);
+	}
+
+	xfrm_pol_put(xp);
+
+	return err;
+}
+
+static const int xfrm_msg_min[(XFRM_MSG_MAX + 1 - XFRM_MSG_BASE)] = {
+	NLMSG_LENGTH(sizeof(struct xfrm_usersa_info)),	/* NEW SA */
+	NLMSG_LENGTH(sizeof(struct xfrm_usersa_id)),	/* DEL SA */
+	NLMSG_LENGTH(sizeof(struct xfrm_usersa_id)),	/* GET SA */
+	NLMSG_LENGTH(sizeof(struct xfrm_userpolicy_info)),/* NEW POLICY */
+	NLMSG_LENGTH(sizeof(struct xfrm_userpolicy_id)),  /* DEL POLICY */
+	NLMSG_LENGTH(sizeof(struct xfrm_userpolicy_id)),  /* GET POLICY */
+	NLMSG_LENGTH(sizeof(struct xfrm_userspi_info)),	/* ALLOC SPI */
+	NLMSG_LENGTH(sizeof(struct xfrm_user_acquire)),	/* ACQUIRE */
+	NLMSG_LENGTH(sizeof(struct xfrm_user_expire)),	/* EXPIRE */
+};
+
+static struct xfrm_link {
+	int (*doit)(struct sk_buff *, struct nlmsghdr *, void **);
+	int (*dump)(struct sk_buff *, struct netlink_callback *);
+} xfrm_dispatch[] = {
+	{	.doit	=	xfrm_add_sa, 		},
+	{	.doit	=	xfrm_del_sa, 		},
+	{
+		.doit	=	xfrm_get_sa,
+		.dump	=	xfrm_dump_sa,
+	},
+	{	.doit	=	xfrm_add_policy 	},
+	{	.doit	=	xfrm_del_policy 	},
+	{
+		.doit	=	xfrm_get_policy,
+		.dump	=	xfrm_dump_policy,
+	},
+	{	.doit	=	xfrm_alloc_userspi	},
+};
+
+static int xfrm_done(struct netlink_callback *cb)
+{
+	return 0;
+}
+
+static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, int *errp)
+{
+	struct rtattr *xfrma[XFRMA_MAX];
+	struct xfrm_link *link;
+	int type, min_len, kind;
+
+	if (!(nlh->nlmsg_flags & NLM_F_REQUEST))
+		return 0;
+
+	type = nlh->nlmsg_type;
+
+	/* A control message: ignore them */
+	if (type < XFRM_MSG_BASE)
+		return 0;
+
+	/* Unknown message: reply with EINVAL */
+	if (type > XFRM_MSG_MAX)
+		goto err_einval;
+
+	type -= XFRM_MSG_BASE;
+	kind = (type & 3);
+	link = &xfrm_dispatch[type];
+
+	/* All operations require privileges, even GET */
+	if (!cap_raised(NETLINK_CB(skb).eff_cap, CAP_NET_ADMIN)) {
+		*errp = -EPERM;
+		return -1;
+	}
+
+	if (kind == 2 && (nlh->nlmsg_flags & NLM_F_DUMP)) {
+		u32 rlen;
+
+		if (link->dump == NULL)
+			goto err_einval;
+
+		if ((*errp = netlink_dump_start(xfrm_nl, skb, nlh,
+						link->dump,
+						xfrm_done)) != 0) {
+			return -1;
+		}
+		rlen = NLMSG_ALIGN(nlh->nlmsg_len);
+		if (rlen > skb->len)
+			rlen = skb->len;
+		skb_pull(skb, rlen);
+		return -1;
+	}
+
+	memset(xfrma, 0, sizeof(xfrma));
+
+	if (nlh->nlmsg_len < (min_len = xfrm_msg_min[type]))
+		goto err_einval;
+
+	if (nlh->nlmsg_len > min_len) {
+		int attrlen = nlh->nlmsg_len - NLMSG_ALIGN(min_len);
+		struct rtattr *attr = (void *) nlh + NLMSG_ALIGN(min_len);
+
+		while (RTA_OK(attr, attrlen)) {
+			unsigned short flavor = attr->rta_type;
+			if (flavor) {
+				if (flavor > XFRMA_MAX)
+					goto err_einval;
+				xfrma[flavor - 1] = attr;
+			}
+			attr = RTA_NEXT(attr, attrlen);
+		}
+	}
+
+	if (link->doit == NULL)
+		goto err_einval;
+	*errp = link->doit(skb, nlh, (void **) &xfrma);
+
+	return *errp;
+
+err_einval:
+	*errp = -EINVAL;
+	return -1;
+}
+
+static int xfrm_user_rcv_skb(struct sk_buff *skb)
+{
+	int err;
+	struct nlmsghdr *nlh;
+
+	while (skb->len >= NLMSG_SPACE(0)) {
+		u32 rlen;
+
+		nlh = (struct nlmsghdr *) skb->data;
+		if (nlh->nlmsg_len < sizeof(*nlh) ||
+		    skb->len < nlh->nlmsg_len)
+			return 0;
+		rlen = NLMSG_ALIGN(nlh->nlmsg_len);
+		if (rlen > skb->len)
+			rlen = skb->len;
+		if (xfrm_user_rcv_msg(skb, nlh, &err)) {
+			if (err == 0)
+				return -1;
+			netlink_ack(skb, nlh, err);
+		} else if (nlh->nlmsg_flags & NLM_F_ACK)
+			netlink_ack(skb, nlh, 0);
+		skb_pull(skb, rlen);
+	}
+
+	return 0;
+}
+
+static void xfrm_netlink_rcv(struct sock *sk, int len)
+{
+	do {
+		struct sk_buff *skb;
+
+		down(&xfrm_cfg_sem);
+
+		while ((skb = skb_dequeue(&sk->receive_queue)) != NULL) {
+			if (xfrm_user_rcv_skb(skb)) {
+				if (skb->len)
+					skb_queue_head(&sk->receive_queue, skb);
+				else
+					kfree_skb(skb);
+				break;
+			}
+			kfree_skb(skb);
+		}
+
+		up(&xfrm_cfg_sem);
+
+	} while (xfrm_nl && xfrm_nl->receive_queue.qlen);
+}
+
+static int build_expire(struct sk_buff *skb, struct xfrm_state *x, int hard)
+{
+	struct xfrm_user_expire *ue;
+	struct nlmsghdr *nlh;
+	unsigned char *b = skb->tail;
+
+	nlh = NLMSG_PUT(skb, 0, 0, XFRM_MSG_EXPIRE,
+			sizeof(*ue));
+	ue = NLMSG_DATA(nlh);
+	nlh->nlmsg_flags = 0;
+
+	copy_to_user_state(x, &ue->state);
+	ue->hard = (hard != 0) ? 1 : 0;
+
+	nlh->nlmsg_len = skb->tail - b;
+	return skb->len;
+
+nlmsg_failure:
+	skb_trim(skb, b - skb->data);
+	return -1;
+}
+
+static int xfrm_send_notify(struct xfrm_state *x, int hard)
+{
+	struct sk_buff *skb;
+
+	skb = alloc_skb(sizeof(struct xfrm_user_expire) + 16, GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+
+	if (build_expire(skb, x, hard) < 0)
+		BUG();
+
+	NETLINK_CB(skb).dst_groups = XFRMGRP_EXPIRE;
+	netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_EXPIRE, GFP_ATOMIC);
+
+	return 0;
+}
+
+/* XXX Make this xfrm_state.c:xfrm_get_acqseq() */
+static u32 get_acqseq(void)
+{
+	u32 res;
+	static u32 acqseq;
+	static spinlock_t acqseq_lock = SPIN_LOCK_UNLOCKED;
+
+	spin_lock_bh(&acqseq_lock);
+	res = (++acqseq ? : ++acqseq);
+	spin_unlock_bh(&acqseq_lock);
+	return res;
+}
+
+static int build_acquire(struct sk_buff *skb, struct xfrm_state *x,
+			 struct xfrm_tmpl *xt, struct xfrm_policy *xp,
+			 int dir)
+{
+	struct xfrm_user_acquire *ua;
+	struct nlmsghdr *nlh;
+	unsigned char *b = skb->tail;
+	__u32 seq = get_acqseq();
+
+	nlh = NLMSG_PUT(skb, 0, 0, XFRM_MSG_ACQUIRE,
+			sizeof(*ua));
+	ua = NLMSG_DATA(nlh);
+	nlh->nlmsg_flags = 0;
+
+	memcpy(&ua->id, &x->id, sizeof(ua->id));
+	memcpy(&ua->saddr, &x->props.saddr, sizeof(ua->saddr));
+	copy_to_user_policy(xp, &ua->policy, dir);
+	ua->aalgos = xt->aalgos;
+	ua->ealgos = xt->ealgos;
+	ua->calgos = xt->calgos;
+	ua->seq = x->km.seq = seq;
+
+	nlh->nlmsg_len = skb->tail - b;
+	return skb->len;
+
+nlmsg_failure:
+	skb_trim(skb, b - skb->data);
+	return -1;
+}
+
+static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt,
+			     struct xfrm_policy *xp, int dir)
+{
+	struct sk_buff *skb;
+
+	skb = alloc_skb(sizeof(struct xfrm_user_acquire) + 16, GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+
+	if (build_acquire(skb, x, xt, xp, dir) < 0)
+		BUG();
+
+	NETLINK_CB(skb).dst_groups = XFRMGRP_ACQUIRE;
+	netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_ACQUIRE, GFP_ATOMIC);
+
+	return 0;
+}
+
+/* User gives us xfrm_user_policy_info followed by an array of 0
+ * or more templates.
+ */
+struct xfrm_policy *xfrm_compile_policy(int opt, u8 *data, int len, int *dir)
+{
+	struct xfrm_userpolicy_info *p = (struct xfrm_userpolicy_info *)data;
+	struct xfrm_user_tmpl *ut = (struct xfrm_user_tmpl *) (p + 1);
+	struct xfrm_policy *xp;
+	int nr;
+
+	if (opt != IP_XFRM_POLICY) {
+		*dir = -EOPNOTSUPP;
+		return NULL;
+	}
+	*dir = -EINVAL;
+
+	if (len < sizeof(*p) ||
+	    verify_newpolicy_info(p))
+		return NULL;
+
+	nr = ((len - sizeof(*p)) / sizeof(*ut));
+	if (nr > XFRM_MAX_DEPTH)
+		return NULL;
+
+	xp = xfrm_policy_alloc(GFP_KERNEL);
+	if (xp == NULL) {
+		*dir = -ENOBUFS;
+		return NULL;
+	}
+
+	copy_from_user_policy(xp, p);
+	copy_templates(xp, ut, nr);
+
+	*dir = p->dir;
+
+	return xp;
+}
+
+static struct xfrm_mgr netlink_mgr = {
+	.id		= "netlink",
+	.notify		= xfrm_send_notify,
+	.acquire	= xfrm_send_acquire,
+	.compile_policy	= xfrm_compile_policy,
+};
+
+static int __init xfrm_user_init(void)
+{
+	printk(KERN_INFO "Initializing IPsec netlink socket\n");
+
+	xfrm_nl = netlink_kernel_create(NETLINK_XFRM, xfrm_netlink_rcv);
+	if (xfrm_nl == NULL)
+		panic("xfrm_user_init: cannot initialize xfrm_nl\n");
+
+
+	xfrm_register_km(&netlink_mgr);
+
+	return 0;
+}
+
+static void __exit xfrm_user_exit(void)
+{
+	xfrm_unregister_km(&netlink_mgr);
+	sock_release(xfrm_nl->socket);
+}
+
+module_init(xfrm_user_init);
+module_exit(xfrm_user_exit);

net/ipv6/mcast.c

@@ -296,6 +296,7 @@ int ipv6_dev_mc_inc(struct net_device *dev, struct in6_addr *addr)
 	}
 
 	memset(mc, 0, sizeof(struct ifmcaddr6));
+	init_timer(&mc->mca_timer);
 	mc->mca_timer.function = igmp6_timer_handler;
 	mc->mca_timer.data = (unsigned long) mc;
 

net/irda/af_irda.c

@@ -2364,6 +2364,7 @@ static int irda_getsockopt(struct socket *sock, int level, int optname,
 
 			/* Set watchdog timer to expire in <val> ms. */
 			self->errno = 0;
+			init_timer(&self->watchdog);
 			self->watchdog.function = irda_discovery_timeout;
 			self->watchdog.data = (unsigned long) self;
 			self->watchdog.expires = jiffies + (val * HZ/1000);

net/key/af_key.c

@@ -528,8 +528,7 @@ static struct  xfrm_state *pfkey_xfrm_state_lookup(struct sadb_msg *hdr, void **
 
 	switch (((struct sockaddr *)(addr + 1))->sa_family) {
 	case AF_INET:
-		x = xfrm_state_lookup(
-				      ((struct sockaddr_in*)(addr + 1))->sin_addr.s_addr,
+		x = xfrm_state_lookup(((struct sockaddr_in*)(addr + 1))->sin_addr.s_addr,
 				      sa->sadb_sa_spi, proto);
 		break;
 	case AF_INET6:
@@ -1043,7 +1042,7 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h
 	daddr = (struct sockaddr_in*)(addr + 1);
 
 	x = xfrm_find_acq(mode, reqid, proto, daddr->sin_addr.s_addr,
-			  saddr->sin_addr.s_addr);
+			  saddr->sin_addr.s_addr, 1);
 	if (x == NULL)
 		return -ENOENT;
 
@@ -1122,7 +1121,17 @@ static int pfkey_add(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr,
 
 	/* XXX there is race condition */
 	x1 = pfkey_xfrm_state_lookup(hdr, ext_hdrs);
-	if (x1 && hdr->sadb_msg_type == SADB_ADD) {
+	if (!x1) {
+		x1 = xfrm_find_acq(x->props.mode, x->props.reqid, x->id.proto,
+				   x->id.daddr.xfrm4_addr,
+				   x->props.saddr.xfrm4_addr, 0);
+		if (x1 && x1->id.spi != x->id.spi && x1->id.spi) {
+			xfrm_state_put(x1);
+			x1 = NULL;
+		}
+	}
+
+	if (x1 && x1->id.spi && hdr->sadb_msg_type == SADB_ADD) {
 		x->km.state = XFRM_STATE_DEAD;
 		xfrm_state_put(x);
 		xfrm_state_put(x1);
@@ -1131,7 +1140,7 @@ static int pfkey_add(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr,
 
 	xfrm_state_insert(x);
 
-	if (x1 && hdr->sadb_msg_type != SADB_ADD) {
+	if (x1) {
 		xfrm_state_delete(x1);
 		xfrm_state_put(x1);
 	}
@@ -1225,7 +1234,7 @@ static struct sk_buff *compose_sadb_supported(struct sadb_msg *orig, int allocat
 		esp_len += sizeof(struct sadb_supported);
 	len = esp_len + ah_len + sizeof(struct sadb_msg);
 
-	skb = alloc_skb(allocation, len + 16);
+	skb = alloc_skb(len + 16, allocation);
 	if (!skb)
 		goto out_put_algs;
 
@@ -2156,7 +2165,7 @@ static struct xfrm_policy *pfkey_compile_policy(int opt, u8 *data, int len, int
 	    (!pol->sadb_x_policy_dir || pol->sadb_x_policy_dir > IPSEC_DIR_OUTBOUND))
 		return NULL;
 
-	xp = xfrm_policy_alloc(GFP_KERNEL);
+	xp = xfrm_policy_alloc(GFP_ATOMIC);
 	if (xp == NULL) {
 		*dir = -ENOBUFS;
 		return NULL;

net/llc/llc_main.c

@@ -181,18 +181,22 @@ int llc_sk_init(struct sock* sk)
 	llc->inc_cntr = llc->dec_cntr = 2;
 	llc->dec_step = llc->connect_step = 1;
 
+	init_timer(&llc->ack_timer);
 	llc->ack_timer.expire	      = LLC_ACK_TIME;
 	llc->ack_timer.timer.data     = (unsigned long)sk;
 	llc->ack_timer.timer.function = llc_conn_ack_tmr_cb;
 
+	init_timer(&llc->pf_cycle_timer);
 	llc->pf_cycle_timer.expire	   = LLC_P_TIME;
 	llc->pf_cycle_timer.timer.data     = (unsigned long)sk;
 	llc->pf_cycle_timer.timer.function = llc_conn_pf_cycle_tmr_cb;
 
+	init_timer(&llc->rej_sent_timer);
 	llc->rej_sent_timer.expire	   = LLC_REJ_TIME;
 	llc->rej_sent_timer.timer.data     = (unsigned long)sk;
 	llc->rej_sent_timer.timer.function = llc_conn_rej_tmr_cb;
 
+	init_timer(&llc->busy_state_timer);
 	llc->busy_state_timer.expire	     = LLC_BUSY_TIME;
 	llc->busy_state_timer.timer.data     = (unsigned long)sk;
 	llc->busy_state_timer.timer.function = llc_conn_busy_tmr_cb;
@@ -552,6 +556,7 @@ static int __init llc_init(void)
 	skb_queue_head_init(&llc_main_station.mac_pdu_q);
 	skb_queue_head_init(&llc_main_station.ev_q.list);
 	spin_lock_init(&llc_main_station.ev_q.lock);
+	init_timer(&llc_main_station.ack_timer);
 	llc_main_station.ack_timer.data     = (unsigned long)&llc_main_station;
 	llc_main_station.ack_timer.function = llc_station_ack_tmr_cb;
 

net/sched/sch_sfq.c

@@ -411,9 +411,9 @@ static int sfq_init(struct Qdisc *sch, struct rtattr *opt)
 	struct sfq_sched_data *q = (struct sfq_sched_data *)sch->data;
 	int i;
 
+	init_timer(&q->perturb_timer);
 	q->perturb_timer.data = (unsigned long)sch;
 	q->perturb_timer.function = sfq_perturbation;
-	init_timer(&q->perturb_timer);
 
 	for (i=0; i<SFQ_HASH_DIVISOR; i++)
 		q->ht[i] = SFQ_DEPTH;

net/socket.c

@@ -66,6 +66,7 @@
 #include <linux/interrupt.h>
 #include <linux/netdevice.h>
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/wanrouter.h>
 #include <linux/netlink.h>
 #include <linux/rtnetlink.h>
@@ -1839,29 +1840,19 @@ void __init sock_init(void)
 #endif
 }
 
-int socket_get_info(char *buffer, char **start, off_t offset, int length)
+#ifdef CONFIG_PROC_FS
+void socket_seq_show(struct seq_file *seq)
 {
-	int len, cpu;
+	int cpu;
 	int counter = 0;
 
-	for (cpu=0; cpu<NR_CPUS; cpu++)
+	for (cpu = 0; cpu < NR_CPUS; cpu++)
 		counter += sockets_in_use[cpu].counter;
 
 	/* It can be negative, by the way. 8) */
 	if (counter < 0)
 		counter = 0;
 
-	len = sprintf(buffer, "sockets: used %d\n", counter);
-	if (offset >= len)
-	{
-		*start = buffer;
-		return 0;
-	}
-	*start = buffer + offset;
-	len -= offset;
-	if (len > length)
-		len = length;
-	if (len < 0)
-		len = 0;
-	return len;
+	seq_printf(seq, "sockets: used %d\n", counter);
 }
+#endif /* CONFIG_PROC_FS */