diff options
Diffstat (limited to 'net/netfilter/x_tables.c')
| -rw-r--r-- | net/netfilter/x_tables.c | 813 |
1 files changed, 592 insertions, 221 deletions
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index a6792089fcf..227aa11e840 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -2,6 +2,7 @@ * x_tables core - Backend for {ip,ip6,arp}_tables * * Copyright (C) 2006-2006 Harald Welte <laforge@netfilter.org> + * Copyright (C) 2006-2012 Patrick McHardy <kaber@trash.net> * * Based on existing ip_tables code which is * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling @@ -12,8 +13,9 @@ * published by the Free Software Foundation. * */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> +#include <linux/module.h> #include <linux/socket.h> #include <linux/net.h> #include <linux/proc_fs.h> @@ -22,22 +24,25 @@ #include <linux/vmalloc.h> #include <linux/mutex.h> #include <linux/mm.h> +#include <linux/slab.h> +#include <linux/audit.h> #include <net/net_namespace.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_arp.h> - +#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter_arp/arp_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); -MODULE_DESCRIPTION("[ip,ip6,arp]_tables backend module"); +MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module"); #define SMP_ALIGN(x) (((x) + SMP_CACHE_BYTES-1) & ~(SMP_CACHE_BYTES-1)) struct compat_delta { - struct compat_delta *next; - unsigned int offset; - short delta; + unsigned int offset; /* offset in kernel */ + int delta; /* delta in 32bit user land */ }; struct xt_af { @@ -46,29 +51,31 @@ struct xt_af { struct list_head target; #ifdef CONFIG_COMPAT struct mutex compat_mutex; - struct compat_delta *compat_offsets; + struct compat_delta *compat_tab; + unsigned int number; /* number of slots in compat_tab[] */ + unsigned int cur; /* number of used slots in compat_tab[] */ #endif }; static struct xt_af *xt; -#ifdef DEBUG_IP_FIREWALL_USER -#define duprintf(format, args...) printk(format , ## args) -#else -#define duprintf(format, args...) -#endif - -static const char *xt_prefix[NPROTO] = { - [AF_INET] = "ip", - [AF_INET6] = "ip6", - [NF_ARP] = "arp", +static const char *const xt_prefix[NFPROTO_NUMPROTO] = { + [NFPROTO_UNSPEC] = "x", + [NFPROTO_IPV4] = "ip", + [NFPROTO_ARP] = "arp", + [NFPROTO_BRIDGE] = "eb", + [NFPROTO_IPV6] = "ip6", }; +/* Allow this many total (re)entries. */ +static const unsigned int xt_jumpstack_multiplier = 2; + /* Registration hooks for targets. */ int xt_register_target(struct xt_target *target) { - int ret, af = target->family; + u_int8_t af = target->family; + int ret; ret = mutex_lock_interruptible(&xt[af].mutex); if (ret != 0) @@ -82,7 +89,7 @@ EXPORT_SYMBOL(xt_register_target); void xt_unregister_target(struct xt_target *target) { - int af = target->family; + u_int8_t af = target->family; mutex_lock(&xt[af].mutex); list_del(&target->list); @@ -113,17 +120,16 @@ EXPORT_SYMBOL(xt_register_targets); void xt_unregister_targets(struct xt_target *target, unsigned int n) { - unsigned int i; - - for (i = 0; i < n; i++) - xt_unregister_target(&target[i]); + while (n-- > 0) + xt_unregister_target(&target[n]); } EXPORT_SYMBOL(xt_unregister_targets); int xt_register_match(struct xt_match *match) { - int ret, af = match->family; + u_int8_t af = match->family; + int ret; ret = mutex_lock_interruptible(&xt[af].mutex); if (ret != 0) @@ -139,7 +145,7 @@ EXPORT_SYMBOL(xt_register_match); void xt_unregister_match(struct xt_match *match) { - int af = match->family; + u_int8_t af = match->family; mutex_lock(&xt[af].mutex); list_del(&match->list); @@ -170,10 +176,8 @@ EXPORT_SYMBOL(xt_register_matches); void xt_unregister_matches(struct xt_match *match, unsigned int n) { - unsigned int i; - - for (i = 0; i < n; i++) - xt_unregister_match(&match[i]); + while (n-- > 0) + xt_unregister_match(&match[n]); } EXPORT_SYMBOL(xt_unregister_matches); @@ -181,14 +185,14 @@ EXPORT_SYMBOL(xt_unregister_matches); /* * These are weird, but module loading must not be done with mutex * held (since they will register), and we have to have a single - * function to use try_then_request_module(). + * function to use. */ /* Find match, grabs ref. Returns ERR_PTR() on error. */ -struct xt_match *xt_find_match(int af, const char *name, u8 revision) +struct xt_match *xt_find_match(u8 af, const char *name, u8 revision) { struct xt_match *m; - int err = 0; + int err = -ENOENT; if (mutex_lock_interruptible(&xt[af].mutex) != 0) return ERR_PTR(-EINTR); @@ -205,15 +209,35 @@ struct xt_match *xt_find_match(int af, const char *name, u8 revision) } } mutex_unlock(&xt[af].mutex); + + if (af != NFPROTO_UNSPEC) + /* Try searching again in the family-independent list */ + return xt_find_match(NFPROTO_UNSPEC, name, revision); + return ERR_PTR(err); } EXPORT_SYMBOL(xt_find_match); +struct xt_match * +xt_request_find_match(uint8_t nfproto, const char *name, uint8_t revision) +{ + struct xt_match *match; + + match = xt_find_match(nfproto, name, revision); + if (IS_ERR(match)) { + request_module("%st_%s", xt_prefix[nfproto], name); + match = xt_find_match(nfproto, name, revision); + } + + return match; +} +EXPORT_SYMBOL_GPL(xt_request_find_match); + /* Find target, grabs ref. Returns ERR_PTR() on error. */ -struct xt_target *xt_find_target(int af, const char *name, u8 revision) +struct xt_target *xt_find_target(u8 af, const char *name, u8 revision) { struct xt_target *t; - int err = 0; + int err = -ENOENT; if (mutex_lock_interruptible(&xt[af].mutex) != 0) return ERR_PTR(-EINTR); @@ -230,25 +254,32 @@ struct xt_target *xt_find_target(int af, const char *name, u8 revision) } } mutex_unlock(&xt[af].mutex); + + if (af != NFPROTO_UNSPEC) + /* Try searching again in the family-independent list */ + return xt_find_target(NFPROTO_UNSPEC, name, revision); + return ERR_PTR(err); } EXPORT_SYMBOL(xt_find_target); -struct xt_target *xt_request_find_target(int af, const char *name, u8 revision) +struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision) { struct xt_target *target; - target = try_then_request_module(xt_find_target(af, name, revision), - "%st_%s", xt_prefix[af], name); - if (IS_ERR(target) || !target) - return NULL; + target = xt_find_target(af, name, revision); + if (IS_ERR(target)) { + request_module("%st_%s", xt_prefix[af], name); + target = xt_find_target(af, name, revision); + } + return target; } EXPORT_SYMBOL_GPL(xt_request_find_target); -static int match_revfn(int af, const char *name, u8 revision, int *bestp) +static int match_revfn(u8 af, const char *name, u8 revision, int *bestp) { - struct xt_match *m; + const struct xt_match *m; int have_rev = 0; list_for_each_entry(m, &xt[af].match, list) { @@ -259,12 +290,16 @@ static int match_revfn(int af, const char *name, u8 revision, int *bestp) have_rev = 1; } } + + if (af != NFPROTO_UNSPEC && !have_rev) + return match_revfn(NFPROTO_UNSPEC, name, revision, bestp); + return have_rev; } -static int target_revfn(int af, const char *name, u8 revision, int *bestp) +static int target_revfn(u8 af, const char *name, u8 revision, int *bestp) { - struct xt_target *t; + const struct xt_target *t; int have_rev = 0; list_for_each_entry(t, &xt[af].target, list) { @@ -275,11 +310,15 @@ static int target_revfn(int af, const char *name, u8 revision, int *bestp) have_rev = 1; } } + + if (af != NFPROTO_UNSPEC && !have_rev) + return target_revfn(NFPROTO_UNSPEC, name, revision, bestp); + return have_rev; } /* Returns true or false (if no such extension at all) */ -int xt_find_revision(int af, const char *name, u8 revision, int target, +int xt_find_revision(u8 af, const char *name, u8 revision, int target, int *err) { int have_rev, best = -1; @@ -307,85 +346,158 @@ int xt_find_revision(int af, const char *name, u8 revision, int target, } EXPORT_SYMBOL_GPL(xt_find_revision); -int xt_check_match(const struct xt_match *match, unsigned short family, - unsigned int size, const char *table, unsigned int hook_mask, - unsigned short proto, int inv_proto) +static char * +textify_hooks(char *buf, size_t size, unsigned int mask, uint8_t nfproto) { - if (XT_ALIGN(match->matchsize) != size) { - printk("%s_tables: %s match: invalid size %Zu != %u\n", - xt_prefix[family], match->name, - XT_ALIGN(match->matchsize), size); + static const char *const inetbr_names[] = { + "PREROUTING", "INPUT", "FORWARD", + "OUTPUT", "POSTROUTING", "BROUTING", + }; + static const char *const arp_names[] = { + "INPUT", "FORWARD", "OUTPUT", + }; + const char *const *names; + unsigned int i, max; + char *p = buf; + bool np = false; + int res; + + names = (nfproto == NFPROTO_ARP) ? arp_names : inetbr_names; + max = (nfproto == NFPROTO_ARP) ? ARRAY_SIZE(arp_names) : + ARRAY_SIZE(inetbr_names); + *p = '\0'; + for (i = 0; i < max; ++i) { + if (!(mask & (1 << i))) + continue; + res = snprintf(p, size, "%s%s", np ? "/" : "", names[i]); + if (res > 0) { + size -= res; + p += res; + } + np = true; + } + + return buf; +} + +int xt_check_match(struct xt_mtchk_param *par, + unsigned int size, u_int8_t proto, bool inv_proto) +{ + int ret; + + if (XT_ALIGN(par->match->matchsize) != size && + par->match->matchsize != -1) { + /* + * ebt_among is exempt from centralized matchsize checking + * because it uses a dynamic-size data set. + */ + pr_err("%s_tables: %s.%u match: invalid size " + "%u (kernel) != (user) %u\n", + xt_prefix[par->family], par->match->name, + par->match->revision, + XT_ALIGN(par->match->matchsize), size); return -EINVAL; } - if (match->table && strcmp(match->table, table)) { - printk("%s_tables: %s match: only valid in %s table, not %s\n", - xt_prefix[family], match->name, match->table, table); + if (par->match->table != NULL && + strcmp(par->match->table, par->table) != 0) { + pr_err("%s_tables: %s match: only valid in %s table, not %s\n", + xt_prefix[par->family], par->match->name, + par->match->table, par->table); return -EINVAL; } - if (match->hooks && (hook_mask & ~match->hooks) != 0) { - printk("%s_tables: %s match: bad hook_mask %u/%u\n", - xt_prefix[family], match->name, hook_mask, match->hooks); + if (par->match->hooks && (par->hook_mask & ~par->match->hooks) != 0) { + char used[64], allow[64]; + + pr_err("%s_tables: %s match: used from hooks %s, but only " + "valid from %s\n", + xt_prefix[par->family], par->match->name, + textify_hooks(used, sizeof(used), par->hook_mask, + par->family), + textify_hooks(allow, sizeof(allow), par->match->hooks, + par->family)); return -EINVAL; } - if (match->proto && (match->proto != proto || inv_proto)) { - printk("%s_tables: %s match: only valid for protocol %u\n", - xt_prefix[family], match->name, match->proto); + if (par->match->proto && (par->match->proto != proto || inv_proto)) { + pr_err("%s_tables: %s match: only valid for protocol %u\n", + xt_prefix[par->family], par->match->name, + par->match->proto); return -EINVAL; } + if (par->match->checkentry != NULL) { + ret = par->match->checkentry(par); + if (ret < 0) + return ret; + else if (ret > 0) + /* Flag up potential errors. */ + return -EIO; + } return 0; } EXPORT_SYMBOL_GPL(xt_check_match); #ifdef CONFIG_COMPAT -int xt_compat_add_offset(int af, unsigned int offset, short delta) +int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta) { - struct compat_delta *tmp; - - tmp = kmalloc(sizeof(struct compat_delta), GFP_KERNEL); - if (!tmp) - return -ENOMEM; + struct xt_af *xp = &xt[af]; + + if (!xp->compat_tab) { + if (!xp->number) + return -EINVAL; + xp->compat_tab = vmalloc(sizeof(struct compat_delta) * xp->number); + if (!xp->compat_tab) + return -ENOMEM; + xp->cur = 0; + } - tmp->offset = offset; - tmp->delta = delta; + if (xp->cur >= xp->number) + return -EINVAL; - if (xt[af].compat_offsets) { - tmp->next = xt[af].compat_offsets->next; - xt[af].compat_offsets->next = tmp; - } else { - xt[af].compat_offsets = tmp; - tmp->next = NULL; - } + if (xp->cur) + delta += xp->compat_tab[xp->cur - 1].delta; + xp->compat_tab[xp->cur].offset = offset; + xp->compat_tab[xp->cur].delta = delta; + xp->cur++; return 0; } EXPORT_SYMBOL_GPL(xt_compat_add_offset); -void xt_compat_flush_offsets(int af) +void xt_compat_flush_offsets(u_int8_t af) { - struct compat_delta *tmp, *next; - - if (xt[af].compat_offsets) { - for (tmp = xt[af].compat_offsets; tmp; tmp = next) { - next = tmp->next; - kfree(tmp); - } - xt[af].compat_offsets = NULL; + if (xt[af].compat_tab) { + vfree(xt[af].compat_tab); + xt[af].compat_tab = NULL; + xt[af].number = 0; + xt[af].cur = 0; } } EXPORT_SYMBOL_GPL(xt_compat_flush_offsets); -short xt_compat_calc_jump(int af, unsigned int offset) +int xt_compat_calc_jump(u_int8_t af, unsigned int offset) { - struct compat_delta *tmp; - short delta; - - for (tmp = xt[af].compat_offsets, delta = 0; tmp; tmp = tmp->next) - if (tmp->offset < offset) - delta += tmp->delta; - return delta; + struct compat_delta *tmp = xt[af].compat_tab; + int mid, left = 0, right = xt[af].cur - 1; + + while (left <= right) { + mid = (left + right) >> 1; + if (offset > tmp[mid].offset) + left = mid + 1; + else if (offset < tmp[mid].offset) + right = mid - 1; + else + return mid ? tmp[mid - 1].delta : 0; + } + return left ? tmp[left - 1].delta : 0; } EXPORT_SYMBOL_GPL(xt_compat_calc_jump); -int xt_compat_match_offset(struct xt_match *match) +void xt_compat_init_offsets(u_int8_t af, unsigned int number) +{ + xt[af].number = number; + xt[af].cur = 0; +} +EXPORT_SYMBOL(xt_compat_init_offsets); + +int xt_compat_match_offset(const struct xt_match *match) { u_int16_t csize = match->compatsize ? : match->matchsize; return XT_ALIGN(match->matchsize) - COMPAT_XT_ALIGN(csize); @@ -395,7 +507,7 @@ EXPORT_SYMBOL_GPL(xt_compat_match_offset); int xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, unsigned int *size) { - struct xt_match *match = m->u.kernel.match; + const struct xt_match *match = m->u.kernel.match; struct compat_xt_entry_match *cm = (struct compat_xt_entry_match *)m; int pad, off = xt_compat_match_offset(match); u_int16_t msize = cm->u.user.match_size; @@ -419,10 +531,10 @@ int xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, } EXPORT_SYMBOL_GPL(xt_compat_match_from_user); -int xt_compat_match_to_user(struct xt_entry_match *m, void __user **dstptr, - unsigned int *size) +int xt_compat_match_to_user(const struct xt_entry_match *m, + void __user **dstptr, unsigned int *size) { - struct xt_match *match = m->u.kernel.match; + const struct xt_match *match = m->u.kernel.match; struct compat_xt_entry_match __user *cm = *dstptr; int off = xt_compat_match_offset(match); u_int16_t msize = m->u.user.match_size - off; @@ -448,38 +560,58 @@ int xt_compat_match_to_user(struct xt_entry_match *m, void __user **dstptr, EXPORT_SYMBOL_GPL(xt_compat_match_to_user); #endif /* CONFIG_COMPAT */ -int xt_check_target(const struct xt_target *target, unsigned short family, - unsigned int size, const char *table, unsigned int hook_mask, - unsigned short proto, int inv_proto) +int xt_check_target(struct xt_tgchk_param *par, + unsigned int size, u_int8_t proto, bool inv_proto) { - if (XT_ALIGN(target->targetsize) != size) { - printk("%s_tables: %s target: invalid size %Zu != %u\n", - xt_prefix[family], target->name, - XT_ALIGN(target->targetsize), size); + int ret; + + if (XT_ALIGN(par->target->targetsize) != size) { + pr_err("%s_tables: %s.%u target: invalid size " + "%u (kernel) != (user) %u\n", + xt_prefix[par->family], par->target->name, + par->target->revision, + XT_ALIGN(par->target->targetsize), size); return -EINVAL; } - if (target->table && strcmp(target->table, table)) { - printk("%s_tables: %s target: only valid in %s table, not %s\n", - xt_prefix[family], target->name, target->table, table); + if (par->target->table != NULL && + strcmp(par->target->table, par->table) != 0) { + pr_err("%s_tables: %s target: only valid in %s table, not %s\n", + xt_prefix[par->family], par->target->name, + par->target->table, par->table); return -EINVAL; } - if (target->hooks && (hook_mask & ~target->hooks) != 0) { - printk("%s_tables: %s target: bad hook_mask %u/%u\n", - xt_prefix[family], target->name, hook_mask, - target->hooks); + if (par->target->hooks && (par->hook_mask & ~par->target->hooks) != 0) { + char used[64], allow[64]; + + pr_err("%s_tables: %s target: used from hooks %s, but only " + "usable from %s\n", + xt_prefix[par->family], par->target->name, + textify_hooks(used, sizeof(used), par->hook_mask, + par->family), + textify_hooks(allow, sizeof(allow), par->target->hooks, + par->family)); return -EINVAL; } - if (target->proto && (target->proto != proto || inv_proto)) { - printk("%s_tables: %s target: only valid for protocol %u\n", - xt_prefix[family], target->name, target->proto); + if (par->target->proto && (par->target->proto != proto || inv_proto)) { + pr_err("%s_tables: %s target: only valid for protocol %u\n", + xt_prefix[par->family], par->target->name, + par->target->proto); return -EINVAL; } + if (par->target->checkentry != NULL) { + ret = par->target->checkentry(par); + if (ret < 0) + return ret; + else if (ret > 0) + /* Flag up potential errors. */ + return -EIO; + } return 0; } EXPORT_SYMBOL_GPL(xt_check_target); #ifdef CONFIG_COMPAT -int xt_compat_target_offset(struct xt_target *target) +int xt_compat_target_offset(const struct xt_target *target) { u_int16_t csize = target->compatsize ? : target->targetsize; return XT_ALIGN(target->targetsize) - COMPAT_XT_ALIGN(csize); @@ -489,7 +621,7 @@ EXPORT_SYMBOL_GPL(xt_compat_target_offset); void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, unsigned int *size) { - struct xt_target *target = t->u.kernel.target; + const struct xt_target *target = t->u.kernel.target; struct compat_xt_entry_target *ct = (struct compat_xt_entry_target *)t; int pad, off = xt_compat_target_offset(target); u_int16_t tsize = ct->u.user.target_size; @@ -512,10 +644,10 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, } EXPORT_SYMBOL_GPL(xt_compat_target_from_user); -int xt_compat_target_to_user(struct xt_entry_target *t, void __user **dstptr, - unsigned int *size) +int xt_compat_target_to_user(const struct xt_entry_target *t, + void __user **dstptr, unsigned int *size) { - struct xt_target *target = t->u.kernel.target; + const struct xt_target *target = t->u.kernel.target; struct compat_xt_entry_target __user *ct = *dstptr; int off = xt_compat_target_offset(target); u_int16_t tsize = t->u.user.target_size - off; @@ -547,7 +679,7 @@ struct xt_table_info *xt_alloc_table_info(unsigned int size) int cpu; /* Pedantry: prevent them from hitting BUG() in vmalloc.c --RR */ - if ((SMP_ALIGN(size) >> PAGE_SHIFT) + 2 > num_physpages) + if ((SMP_ALIGN(size) >> PAGE_SHIFT) + 2 > totalram_pages) return NULL; newinfo = kzalloc(XT_TABLE_INFO_SZ, GFP_KERNEL); @@ -585,12 +717,31 @@ void xt_free_table_info(struct xt_table_info *info) else vfree(info->entries[cpu]); } + + if (info->jumpstack != NULL) { + if (sizeof(void *) * info->stacksize > PAGE_SIZE) { + for_each_possible_cpu(cpu) + vfree(info->jumpstack[cpu]); + } else { + for_each_possible_cpu(cpu) + kfree(info->jumpstack[cpu]); + } + } + + if (sizeof(void **) * nr_cpu_ids > PAGE_SIZE) + vfree(info->jumpstack); + else + kfree(info->jumpstack); + + free_percpu(info->stackptr); + kfree(info); } EXPORT_SYMBOL(xt_free_table_info); /* Find table by name, grabs mutex & ref. Returns ERR_PTR() on error. */ -struct xt_table *xt_find_table_lock(struct net *net, int af, const char *name) +struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, + const char *name) { struct xt_table *t; @@ -612,57 +763,134 @@ void xt_table_unlock(struct xt_table *table) EXPORT_SYMBOL_GPL(xt_table_unlock); #ifdef CONFIG_COMPAT -void xt_compat_lock(int af) +void xt_compat_lock(u_int8_t af) { mutex_lock(&xt[af].compat_mutex); } EXPORT_SYMBOL_GPL(xt_compat_lock); -void xt_compat_unlock(int af) +void xt_compat_unlock(u_int8_t af) { mutex_unlock(&xt[af].compat_mutex); } EXPORT_SYMBOL_GPL(xt_compat_unlock); #endif +DEFINE_PER_CPU(seqcount_t, xt_recseq); +EXPORT_PER_CPU_SYMBOL_GPL(xt_recseq); + +static int xt_jumpstack_alloc(struct xt_table_info *i) +{ + unsigned int size; + int cpu; + + i->stackptr = alloc_percpu(unsigned int); + if (i->stackptr == NULL) + return -ENOMEM; + + size = sizeof(void **) * nr_cpu_ids; + if (size > PAGE_SIZE) + i->jumpstack = vzalloc(size); + else + i->jumpstack = kzalloc(size, GFP_KERNEL); + if (i->jumpstack == NULL) + return -ENOMEM; + + i->stacksize *= xt_jumpstack_multiplier; + size = sizeof(void *) * i->stacksize; + for_each_possible_cpu(cpu) { + if (size > PAGE_SIZE) + i->jumpstack[cpu] = vmalloc_node(size, + cpu_to_node(cpu)); + else + i->jumpstack[cpu] = kmalloc_node(size, + GFP_KERNEL, cpu_to_node(cpu)); + if (i->jumpstack[cpu] == NULL) + /* + * Freeing will be done later on by the callers. The + * chain is: xt_replace_table -> __do_replace -> + * do_replace -> xt_free_table_info. + */ + return -ENOMEM; + } + + return 0; +} + struct xt_table_info * xt_replace_table(struct xt_table *table, unsigned int num_counters, struct xt_table_info *newinfo, int *error) { - struct xt_table_info *oldinfo, *private; + struct xt_table_info *private; + int ret; + + ret = xt_jumpstack_alloc(newinfo); + if (ret < 0) { + *error = ret; + return NULL; + } /* Do the substitution. */ - write_lock_bh(&table->lock); + local_bh_disable(); private = table->private; + /* Check inside lock: is the old number correct? */ if (num_counters != private->number) { - duprintf("num_counters != table->private->number (%u/%u)\n", + pr_debug("num_counters != table->private->number (%u/%u)\n", num_counters, private->number); - write_unlock_bh(&table->lock); + local_bh_enable(); *error = -EAGAIN; return NULL; } - oldinfo = private; + + newinfo->initial_entries = private->initial_entries; + /* + * Ensure contents of newinfo are visible before assigning to + * private. + */ + smp_wmb(); table->private = newinfo; - newinfo->initial_entries = oldinfo->initial_entries; - write_unlock_bh(&table->lock); - return oldinfo; + /* + * Even though table entries have now been swapped, other CPU's + * may still be using the old entries. This is okay, because + * resynchronization happens because of the locking done + * during the get_counters() routine. + */ + local_bh_enable(); + +#ifdef CONFIG_AUDIT + if (audit_enabled) { + struct audit_buffer *ab; + + ab = audit_log_start(current->audit_context, GFP_KERNEL, + AUDIT_NETFILTER_CFG); + if (ab) { + audit_log_format(ab, "table=%s family=%u entries=%u", + table->name, table->af, + private->number); + audit_log_end(ab); + } + } +#endif + + return private; } EXPORT_SYMBOL_GPL(xt_replace_table); -struct xt_table *xt_register_table(struct net *net, struct xt_table *table, +struct xt_table *xt_register_table(struct net *net, + const struct xt_table *input_table, struct xt_table_info *bootstrap, struct xt_table_info *newinfo) { int ret; struct xt_table_info *private; - struct xt_table *t; + struct xt_table *t, *table; /* Don't add one object to multiple lists. */ - table = kmemdup(table, sizeof(struct xt_table), GFP_KERNEL); + table = kmemdup(input_table, sizeof(struct xt_table), GFP_KERNEL); if (!table) { ret = -ENOMEM; goto out; @@ -682,12 +910,12 @@ struct xt_table *xt_register_table(struct net *net, struct xt_table *table, /* Simplifies replace_table code. */ table->private = bootstrap; - rwlock_init(&table->lock); + if (!xt_replace_table(table, 0, newinfo, &ret)) goto unlock; private = table->private; - duprintf("table->private->number = %u\n", private->number); + pr_debug("table->private->number = %u\n", private->number); /* save number of initial entries */ private->initial_entries = private->number; @@ -722,13 +950,13 @@ EXPORT_SYMBOL_GPL(xt_unregister_table); #ifdef CONFIG_PROC_FS struct xt_names_priv { struct seq_net_private p; - int af; + u_int8_t af; }; static void *xt_table_seq_start(struct seq_file *seq, loff_t *pos) { struct xt_names_priv *priv = seq->private; - struct net *net = priv->p.net; - int af = priv->af; + struct net *net = seq_file_net(seq); + u_int8_t af = priv->af; mutex_lock(&xt[af].mutex); return seq_list_start(&net->xt.tables[af], *pos); @@ -737,8 +965,8 @@ static void *xt_table_seq_start(struct seq_file *seq, loff_t *pos) static void *xt_table_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct xt_names_priv *priv = seq->private; - struct net *net = priv->p.net; - int af = priv->af; + struct net *net = seq_file_net(seq); + u_int8_t af = priv->af; return seq_list_next(v, &net->xt.tables[af], pos); } @@ -746,7 +974,7 @@ static void *xt_table_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void xt_table_seq_stop(struct seq_file *seq, void *v) { struct xt_names_priv *priv = seq->private; - int af = priv->af; + u_int8_t af = priv->af; mutex_unlock(&xt[af].mutex); } @@ -777,7 +1005,7 @@ static int xt_table_open(struct inode *inode, struct file *file) sizeof(struct xt_names_priv)); if (!ret) { priv = ((struct seq_file *)file->private_data)->private; - priv->af = (unsigned long)PDE(inode)->data; + priv->af = (unsigned long)PDE_DATA(inode); } return ret; } @@ -787,62 +1015,146 @@ static const struct file_operations xt_table_ops = { .open = xt_table_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; -static void *xt_match_seq_start(struct seq_file *seq, loff_t *pos) +/* + * Traverse state for ip{,6}_{tables,matches} for helping crossing + * the multi-AF mutexes. + */ +struct nf_mttg_trav { + struct list_head *head, *curr; + uint8_t class, nfproto; +}; + +enum { + MTTG_TRAV_INIT, + MTTG_TRAV_NFP_UNSPEC, + MTTG_TRAV_NFP_SPEC, + MTTG_TRAV_DONE, +}; + +static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos, + bool is_target) { - struct proc_dir_entry *pde = (struct proc_dir_entry *)seq->private; - u_int16_t af = (unsigned long)pde->data; + static const uint8_t next_class[] = { + [MTTG_TRAV_NFP_UNSPEC] = MTTG_TRAV_NFP_SPEC, + [MTTG_TRAV_NFP_SPEC] = MTTG_TRAV_DONE, + }; + struct nf_mttg_trav *trav = seq->private; + + switch (trav->class) { + case MTTG_TRAV_INIT: + trav->class = MTTG_TRAV_NFP_UNSPEC; + mutex_lock(&xt[NFPROTO_UNSPEC].mutex); + trav->head = trav->curr = is_target ? + &xt[NFPROTO_UNSPEC].target : &xt[NFPROTO_UNSPEC].match; + break; + case MTTG_TRAV_NFP_UNSPEC: + trav->curr = trav->curr->next; + if (trav->curr != trav->head) + break; + mutex_unlock(&xt[NFPROTO_UNSPEC].mutex); + mutex_lock(&xt[trav->nfproto].mutex); + trav->head = trav->curr = is_target ? + &xt[trav->nfproto].target : &xt[trav->nfproto].match; + trav->class = next_class[trav->class]; + break; + case MTTG_TRAV_NFP_SPEC: + trav->curr = trav->curr->next; + if (trav->curr != trav->head) + break; + /* fallthru, _stop will unlock */ + default: + return NULL; + } - mutex_lock(&xt[af].mutex); - return seq_list_start(&xt[af].match, *pos); + if (ppos != NULL) + ++*ppos; + return trav; } -static void *xt_match_seq_next(struct seq_file *seq, void *v, loff_t *pos) +static void *xt_mttg_seq_start(struct seq_file *seq, loff_t *pos, + bool is_target) { - struct proc_dir_entry *pde = (struct proc_dir_entry *)seq->private; - u_int16_t af = (unsigned long)pde->data; + struct nf_mttg_trav *trav = seq->private; + unsigned int j; - return seq_list_next(v, &xt[af].match, pos); + trav->class = MTTG_TRAV_INIT; + for (j = 0; j < *pos; ++j) + if (xt_mttg_seq_next(seq, NULL, NULL, is_target) == NULL) + return NULL; + return trav; } -static void xt_match_seq_stop(struct seq_file *seq, void *v) +static void xt_mttg_seq_stop(struct seq_file *seq, void *v) { - struct proc_dir_entry *pde = seq->private; - u_int16_t af = (unsigned long)pde->data; + struct nf_mttg_trav *trav = seq->private; + + switch (trav->class) { + case MTTG_TRAV_NFP_UNSPEC: + mutex_unlock(&xt[NFPROTO_UNSPEC].mutex); + break; + case MTTG_TRAV_NFP_SPEC: + mutex_unlock(&xt[trav->nfproto].mutex); + break; + } +} - mutex_unlock(&xt[af].mutex); +static void *xt_match_seq_start(struct seq_file *seq, loff_t *pos) +{ + return xt_mttg_seq_start(seq, pos, false); } -static int xt_match_seq_show(struct seq_file *seq, void *v) +static void *xt_match_seq_next(struct seq_file *seq, void *v, loff_t *ppos) { - struct xt_match *match = list_entry(v, struct xt_match, list); + return xt_mttg_seq_next(seq, v, ppos, false); +} - if (strlen(match->name)) - return seq_printf(seq, "%s\n", match->name); - else - return 0; +static int xt_match_seq_show(struct seq_file *seq, void *v) +{ + const struct nf_mttg_trav *trav = seq->private; + const struct xt_match *match; + + switch (trav->class) { + case MTTG_TRAV_NFP_UNSPEC: + case MTTG_TRAV_NFP_SPEC: + if (trav->curr == trav->head) + return 0; + match = list_entry(trav->curr, struct xt_match, list); + return (*match->name == '\0') ? 0 : + seq_printf(seq, "%s\n", match->name); + } + return 0; } static const struct seq_operations xt_match_seq_ops = { .start = xt_match_seq_start, .next = xt_match_seq_next, - .stop = xt_match_seq_stop, + .stop = xt_mttg_seq_stop, .show = xt_match_seq_show, }; static int xt_match_open(struct inode *inode, struct file *file) { + struct seq_file *seq; + struct nf_mttg_trav *trav; int ret; - ret = seq_open(file, &xt_match_seq_ops); - if (!ret) { - struct seq_file *seq = file->private_data; + trav = kmalloc(sizeof(*trav), GFP_KERNEL); + if (trav == NULL) + return -ENOMEM; - seq->private = PDE(inode); + ret = seq_open(file, &xt_match_seq_ops); + if (ret < 0) { + kfree(trav); + return ret; } - return ret; + + seq = file->private_data; + seq->private = trav; + trav->nfproto = (unsigned long)PDE_DATA(inode); + return 0; } static const struct file_operations xt_match_ops = { @@ -850,62 +1162,63 @@ static const struct file_operations xt_match_ops = { .open = xt_match_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_private, }; static void *xt_target_seq_start(struct seq_file *seq, loff_t *pos) { - struct proc_dir_entry *pde = (struct proc_dir_entry *)seq->private; - u_int16_t af = (unsigned long)pde->data; - - mutex_lock(&xt[af].mutex); - return seq_list_start(&xt[af].target, *pos); + return xt_mttg_seq_start(seq, pos, true); } -static void *xt_target_seq_next(struct seq_file *seq, void *v, loff_t *pos) +static void *xt_target_seq_next(struct seq_file *seq, void *v, loff_t *ppos) { - struct proc_dir_entry *pde = (struct proc_dir_entry *)seq->private; - u_int16_t af = (unsigned long)pde->data; - - return seq_list_next(v, &xt[af].target, pos); -} - -static void xt_target_seq_stop(struct seq_file *seq, void *v) -{ - struct proc_dir_entry *pde = seq->private; - u_int16_t af = (unsigned long)pde->data; - - mutex_unlock(&xt[af].mutex); + return xt_mttg_seq_next(seq, v, ppos, true); } static int xt_target_seq_show(struct seq_file *seq, void *v) { - struct xt_target *target = list_entry(v, struct xt_target, list); - - if (strlen(target->name)) - return seq_printf(seq, "%s\n", target->name); - else - return 0; + const struct nf_mttg_trav *trav = seq->private; + const struct xt_target *target; + + switch (trav->class) { + case MTTG_TRAV_NFP_UNSPEC: + case MTTG_TRAV_NFP_SPEC: + if (trav->curr == trav->head) + return 0; + target = list_entry(trav->curr, struct xt_target, list); + return (*target->name == '\0') ? 0 : + seq_printf(seq, "%s\n", target->name); + } + return 0; } static const struct seq_operations xt_target_seq_ops = { .start = xt_target_seq_start, .next = xt_target_seq_next, - .stop = xt_target_seq_stop, + .stop = xt_mttg_seq_stop, .show = xt_target_seq_show, }; static int xt_target_open(struct inode *inode, struct file *file) { + struct seq_file *seq; + struct nf_mttg_trav *trav; int ret; - ret = seq_open(file, &xt_target_seq_ops); - if (!ret) { - struct seq_file *seq = file->private_data; + trav = kmalloc(sizeof(*trav), GFP_KERNEL); + if (trav == NULL) + return -ENOMEM; - seq->private = PDE(inode); + ret = seq_open(file, &xt_target_seq_ops); + if (ret < 0) { + kfree(trav); + return ret; } - return ret; + + seq = file->private_data; + seq->private = trav; + trav->nfproto = (unsigned long)PDE_DATA(inode); + return 0; } static const struct file_operations xt_target_ops = { @@ -913,7 +1226,7 @@ static const struct file_operations xt_target_ops = { .open = xt_target_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_private, }; #define FORMAT_TABLES "_tables_names" @@ -922,39 +1235,92 @@ static const struct file_operations xt_target_ops = { #endif /* CONFIG_PROC_FS */ -int xt_proto_init(struct net *net, int af) +/** + * xt_hook_link - set up hooks for a new table + * @table: table with metadata needed to set up hooks + * @fn: Hook function + * + * This function will take care of creating and registering the necessary + * Netfilter hooks for XT tables. + */ +struct nf_hook_ops *xt_hook_link(const struct xt_table *table, nf_hookfn *fn) +{ + unsigned int hook_mask = table->valid_hooks; + uint8_t i, num_hooks = hweight32(hook_mask); + uint8_t hooknum; + struct nf_hook_ops *ops; + int ret; + + ops = kmalloc(sizeof(*ops) * num_hooks, GFP_KERNEL); + if (ops == NULL) + return ERR_PTR(-ENOMEM); + + for (i = 0, hooknum = 0; i < num_hooks && hook_mask != 0; + hook_mask >>= 1, ++hooknum) { + if (!(hook_mask & 1)) + continue; + ops[i].hook = fn; + ops[i].owner = table->me; + ops[i].pf = table->af; + ops[i].hooknum = hooknum; + ops[i].priority = table->priority; + ++i; + } + + ret = nf_register_hooks(ops, num_hooks); + if (ret < 0) { + kfree(ops); + return ERR_PTR(ret); + } + + return ops; +} +EXPORT_SYMBOL_GPL(xt_hook_link); + +/** + * xt_hook_unlink - remove hooks for a table + * @ops: nf_hook_ops array as returned by nf_hook_link + * @hook_mask: the very same mask that was passed to nf_hook_link + */ +void xt_hook_unlink(const struct xt_table *table, struct nf_hook_ops *ops) +{ + nf_unregister_hooks(ops, hweight32(table->valid_hooks)); + kfree(ops); +} +EXPORT_SYMBOL_GPL(xt_hook_unlink); + +int xt_proto_init(struct net *net, u_int8_t af) { #ifdef CONFIG_PROC_FS char buf[XT_FUNCTION_MAXNAMELEN]; struct proc_dir_entry *proc; #endif - if (af >= NPROTO) + if (af >= ARRAY_SIZE(xt_prefix)) return -EINVAL; #ifdef CONFIG_PROC_FS strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); - proc = proc_net_fops_create(net, buf, 0440, &xt_table_ops); + proc = proc_create_data(buf, 0440, net->proc_net, &xt_table_ops, + (void *)(unsigned long)af); if (!proc) goto out; - proc->data = (void *)(unsigned long)af; - strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); - proc = proc_net_fops_create(net, buf, 0440, &xt_match_ops); + proc = proc_create_data(buf, 0440, net->proc_net, &xt_match_ops, + (void *)(unsigned long)af); if (!proc) goto out_remove_tables; - proc->data = (void *)(unsigned long)af; strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TARGETS, sizeof(buf)); - proc = proc_net_fops_create(net, buf, 0440, &xt_target_ops); + proc = proc_create_data(buf, 0440, net->proc_net, &xt_target_ops, + (void *)(unsigned long)af); if (!proc) goto out_remove_matches; - proc->data = (void *)(unsigned long)af; #endif return 0; @@ -963,34 +1329,34 @@ int xt_proto_init(struct net *net, int af) out_remove_matches: strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); - proc_net_remove(net, buf); + remove_proc_entry(buf, net->proc_net); out_remove_tables: strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); - proc_net_remove(net, buf); + remove_proc_entry(buf, net->proc_net); out: return -1; #endif } EXPORT_SYMBOL_GPL(xt_proto_init); -void xt_proto_fini(struct net *net, int af) +void xt_proto_fini(struct net *net, u_int8_t af) { #ifdef CONFIG_PROC_FS char buf[XT_FUNCTION_MAXNAMELEN]; strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); - proc_net_remove(net, buf); + remove_proc_entry(buf, net->proc_net); strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TARGETS, sizeof(buf)); - proc_net_remove(net, buf); + remove_proc_entry(buf, net->proc_net); strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); - proc_net_remove(net, buf); + remove_proc_entry(buf, net->proc_net); #endif /*CONFIG_PROC_FS*/ } EXPORT_SYMBOL_GPL(xt_proto_fini); @@ -999,7 +1365,7 @@ static int __net_init xt_net_init(struct net *net) { int i; - for (i = 0; i < NPROTO; i++) + for (i = 0; i < NFPROTO_NUMPROTO; i++) INIT_LIST_HEAD(&net->xt.tables[i]); return 0; } @@ -1010,17 +1376,22 @@ static struct pernet_operations xt_net_ops = { static int __init xt_init(void) { - int i, rv; + unsigned int i; + int rv; + + for_each_possible_cpu(i) { + seqcount_init(&per_cpu(xt_recseq, i)); + } - xt = kmalloc(sizeof(struct xt_af) * NPROTO, GFP_KERNEL); + xt = kmalloc(sizeof(struct xt_af) * NFPROTO_NUMPROTO, GFP_KERNEL); if (!xt) return -ENOMEM; - for (i = 0; i < NPROTO; i++) { + for (i = 0; i < NFPROTO_NUMPROTO; i++) { mutex_init(&xt[i].mutex); #ifdef CONFIG_COMPAT mutex_init(&xt[i].compat_mutex); - xt[i].compat_offsets = NULL; + xt[i].compat_tab = NULL; #endif INIT_LIST_HEAD(&xt[i].target); INIT_LIST_HEAD(&xt[i].match); |