1 files changed, 260 insertions, 398 deletions

diff --git a/security/selinux/avc.c b/security/selinux/avc.c
index 187964e88af..a18f1fa6440 100644
--- a/security/selinux/avc.c
+++ b/security/selinux/avc.c
@@ -2,16 +2,16 @@
  * Implementation of the kernel access vector cache (AVC).
  *
  * Authors:  Stephen Smalley, <sds@epoch.ncsc.mil>
- *           James Morris <jmorris@redhat.com>
+ *	     James Morris <jmorris@redhat.com>
  *
  * Update:   KaiGai, Kohei <kaigai@ak.jp.nec.com>
- *     Replaced the avc_lock spinlock by RCU.
+ *	Replaced the avc_lock spinlock by RCU.
  *
  * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com>
  *
  *	This program is free software; you can redistribute it and/or modify
  *	it under the terms of the GNU General Public License version 2,
- *      as published by the Free Software Foundation.
+ *	as published by the Free Software Foundation.
  */
 #include <linux/types.h>
 #include <linux/stddef.h>
@@ -31,52 +31,14 @@
 #include <net/ipv6.h>
 #include "avc.h"
 #include "avc_ss.h"
-
-static const struct av_perm_to_string av_perm_to_string[] = {
-#define S_(c, v, s) { c, v, s },
-#include "av_perm_to_string.h"
-#undef S_
-};
-
-static const char *class_to_string[] = {
-#define S_(s) s,
-#include "class_to_string.h"
-#undef S_
-};
-
-#define TB_(s) static const char * s [] = {
-#define TE_(s) };
-#define S_(s) s,
-#include "common_perm_to_string.h"
-#undef TB_
-#undef TE_
-#undef S_
-
-static const struct av_inherit av_inherit[] = {
-#define S_(c, i, b) { c, common_##i##_perm_to_string, b },
-#include "av_inherit.h"
-#undef S_
-};
-
-const struct selinux_class_perm selinux_class_perm = {
-	av_perm_to_string,
-	ARRAY_SIZE(av_perm_to_string),
-	class_to_string,
-	ARRAY_SIZE(class_to_string),
-	av_inherit,
-	ARRAY_SIZE(av_inherit)
-};
+#include "classmap.h"
 
 #define AVC_CACHE_SLOTS			512
 #define AVC_DEF_CACHE_THRESHOLD		512
 #define AVC_CACHE_RECLAIM		16
 
 #ifdef CONFIG_SECURITY_SELINUX_AVC_STATS
-#define avc_cache_stats_incr(field) 				\
-do {								\
-	per_cpu(avc_cache_stats, get_cpu()).field++;		\
-	put_cpu();						\
-} while (0)
+#define avc_cache_stats_incr(field)	this_cpu_inc(avc_cache_stats.field)
 #else
 #define avc_cache_stats_incr(field)	do {} while (0)
 #endif
@@ -86,17 +48,16 @@ struct avc_entry {
 	u32			tsid;
 	u16			tclass;
 	struct av_decision	avd;
-	atomic_t		used;	/* used recently */
 };
 
 struct avc_node {
 	struct avc_entry	ae;
-	struct list_head	list;
-	struct rcu_head         rhead;
+	struct hlist_node	list; /* anchored in avc_cache->slots[i] */
+	struct rcu_head		rhead;
 };
 
 struct avc_cache {
-	struct list_head	slots[AVC_CACHE_SLOTS];
+	struct hlist_head	slots[AVC_CACHE_SLOTS]; /* head for avc_node->list */
 	spinlock_t		slots_lock[AVC_CACHE_SLOTS]; /* lock for writes */
 	atomic_t		lru_hint;	/* LRU hint for reclaim scan */
 	atomic_t		active_nodes;
@@ -104,14 +65,8 @@ struct avc_cache {
 };
 
 struct avc_callback_node {
-	int (*callback) (u32 event, u32 ssid, u32 tsid,
-	                 u16 tclass, u32 perms,
-	                 u32 *out_retained);
+	int (*callback) (u32 event);
 	u32 events;
-	u32 ssid;
-	u32 tsid;
-	u16 tclass;
-	u32 perms;
 	struct avc_callback_node *next;
 };
 
@@ -138,52 +93,28 @@ static inline int avc_hash(u32 ssid, u32 tsid, u16 tclass)
  */
 static void avc_dump_av(struct audit_buffer *ab, u16 tclass, u32 av)
 {
-	const char **common_pts = NULL;
-	u32 common_base = 0;
-	int i, i2, perm;
+	const char **perms;
+	int i, perm;
 
 	if (av == 0) {
 		audit_log_format(ab, " null");
 		return;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(av_inherit); i++) {
-		if (av_inherit[i].tclass == tclass) {
-			common_pts = av_inherit[i].common_pts;
-			common_base = av_inherit[i].common_base;
-			break;
-		}
-	}
+	perms = secclass_map[tclass-1].perms;
 
 	audit_log_format(ab, " {");
 	i = 0;
 	perm = 1;
-	while (perm < common_base) {
-		if (perm & av) {
-			audit_log_format(ab, " %s", common_pts[i]);
+	while (i < (sizeof(av) * 8)) {
+		if ((perm & av) && perms[i]) {
+			audit_log_format(ab, " %s", perms[i]);
 			av &= ~perm;
 		}
 		i++;
 		perm <<= 1;
 	}
 
-	while (i < sizeof(av) * 8) {
-		if (perm & av) {
-			for (i2 = 0; i2 < ARRAY_SIZE(av_perm_to_string); i2++) {
-				if ((av_perm_to_string[i2].tclass == tclass) &&
-				    (av_perm_to_string[i2].value == perm))
-					break;
-			}
-			if (i2 < ARRAY_SIZE(av_perm_to_string)) {
-				audit_log_format(ab, " %s",
-						 av_perm_to_string[i2].name);
-				av &= ~perm;
-			}
-		}
-		i++;
-		perm <<= 1;
-	}
-
 	if (av)
 		audit_log_format(ab, " 0x%x", av);
 
@@ -202,7 +133,7 @@ static void avc_dump_query(struct audit_buffer *ab, u32 ssid, u32 tsid, u16 tcla
 	char *scontext;
 	u32 scontext_len;
 
- 	rc = security_sid_to_context(ssid, &scontext, &scontext_len);
+	rc = security_sid_to_context(ssid, &scontext, &scontext_len);
 	if (rc)
 		audit_log_format(ab, "ssid=%d", ssid);
 	else {
@@ -218,8 +149,8 @@ static void avc_dump_query(struct audit_buffer *ab, u32 ssid, u32 tsid, u16 tcla
 		kfree(scontext);
 	}
 
-	BUG_ON(tclass >= ARRAY_SIZE(class_to_string) || !class_to_string[tclass]);
-	audit_log_format(ab, " tclass=%s", class_to_string[tclass]);
+	BUG_ON(tclass >= ARRAY_SIZE(secclass_map));
+	audit_log_format(ab, " tclass=%s", secclass_map[tclass-1].name);
 }
 
 /**
@@ -232,7 +163,7 @@ void __init avc_init(void)
 	int i;
 
 	for (i = 0; i < AVC_CACHE_SLOTS; i++) {
-		INIT_LIST_HEAD(&avc_cache.slots[i]);
+		INIT_HLIST_HEAD(&avc_cache.slots[i]);
 		spin_lock_init(&avc_cache.slots_lock[i]);
 	}
 	atomic_set(&avc_cache.active_nodes, 0);
@@ -248,16 +179,18 @@ int avc_get_hash_stats(char *page)
 {
 	int i, chain_len, max_chain_len, slots_used;
 	struct avc_node *node;
+	struct hlist_head *head;
 
 	rcu_read_lock();
 
 	slots_used = 0;
 	max_chain_len = 0;
 	for (i = 0; i < AVC_CACHE_SLOTS; i++) {
-		if (!list_empty(&avc_cache.slots[i])) {
+		head = &avc_cache.slots[i];
+		if (!hlist_empty(head)) {
 			slots_used++;
 			chain_len = 0;
-			list_for_each_entry_rcu(node, &avc_cache.slots[i], list)
+			hlist_for_each_entry_rcu(node, head, list)
 				chain_len++;
 			if (chain_len > max_chain_len)
 				max_chain_len = chain_len;
@@ -281,7 +214,7 @@ static void avc_node_free(struct rcu_head *rhead)
 
 static void avc_node_delete(struct avc_node *node)
 {
-	list_del_rcu(&node->list);
+	hlist_del_rcu(&node->list);
 	call_rcu(&node->rhead, avc_node_free);
 	atomic_dec(&avc_cache.active_nodes);
 }
@@ -295,7 +228,7 @@ static void avc_node_kill(struct avc_node *node)
 
 static void avc_node_replace(struct avc_node *new, struct avc_node *old)
 {
-	list_replace_rcu(&old->list, &new->list);
+	hlist_replace_rcu(&old->list, &new->list);
 	call_rcu(&old->rhead, avc_node_free);
 	atomic_dec(&avc_cache.active_nodes);
 }
@@ -305,26 +238,30 @@ static inline int avc_reclaim_node(void)
 	struct avc_node *node;
 	int hvalue, try, ecx;
 	unsigned long flags;
+	struct hlist_head *head;
+	spinlock_t *lock;
 
-	for (try = 0, ecx = 0; try < AVC_CACHE_SLOTS; try++ ) {
+	for (try = 0, ecx = 0; try < AVC_CACHE_SLOTS; try++) {
 		hvalue = atomic_inc_return(&avc_cache.lru_hint) & (AVC_CACHE_SLOTS - 1);
+		head = &avc_cache.slots[hvalue];
+		lock = &avc_cache.slots_lock[hvalue];
 
-		if (!spin_trylock_irqsave(&avc_cache.slots_lock[hvalue], flags))
+		if (!spin_trylock_irqsave(lock, flags))
 			continue;
 
-		list_for_each_entry(node, &avc_cache.slots[hvalue], list) {
-			if (atomic_dec_and_test(&node->ae.used)) {
-				/* Recently Unused */
-				avc_node_delete(node);
-				avc_cache_stats_incr(reclaims);
-				ecx++;
-				if (ecx >= AVC_CACHE_RECLAIM) {
-					spin_unlock_irqrestore(&avc_cache.slots_lock[hvalue], flags);
-					goto out;
-				}
+		rcu_read_lock();
+		hlist_for_each_entry(node, head, list) {
+			avc_node_delete(node);
+			avc_cache_stats_incr(reclaims);
+			ecx++;
+			if (ecx >= AVC_CACHE_RECLAIM) {
+				rcu_read_unlock();
+				spin_unlock_irqrestore(lock, flags);
+				goto out;
 			}
 		}
-		spin_unlock_irqrestore(&avc_cache.slots_lock[hvalue], flags);
+		rcu_read_unlock();
+		spin_unlock_irqrestore(lock, flags);
 	}
 out:
 	return ecx;
@@ -334,13 +271,11 @@ static struct avc_node *avc_alloc_node(void)
 {
 	struct avc_node *node;
 
-	node = kmem_cache_zalloc(avc_node_cachep, GFP_ATOMIC);
+	node = kmem_cache_zalloc(avc_node_cachep, GFP_ATOMIC|__GFP_NOMEMALLOC);
 	if (!node)
 		goto out;
 
-	INIT_RCU_HEAD(&node->rhead);
-	INIT_LIST_HEAD(&node->list);
-	atomic_set(&node->ae.used, 1);
+	INIT_HLIST_NODE(&node->list);
 	avc_cache_stats_incr(allocations);
 
 	if (atomic_inc_return(&avc_cache.active_nodes) > avc_cache_threshold)
@@ -350,21 +285,23 @@ out:
 	return node;
 }
 
-static void avc_node_populate(struct avc_node *node, u32 ssid, u32 tsid, u16 tclass, struct avc_entry *ae)
+static void avc_node_populate(struct avc_node *node, u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd)
 {
 	node->ae.ssid = ssid;
 	node->ae.tsid = tsid;
 	node->ae.tclass = tclass;
-	memcpy(&node->ae.avd, &ae->avd, sizeof(node->ae.avd));
+	memcpy(&node->ae.avd, avd, sizeof(node->ae.avd));
 }
 
 static inline struct avc_node *avc_search_node(u32 ssid, u32 tsid, u16 tclass)
 {
 	struct avc_node *node, *ret = NULL;
 	int hvalue;
+	struct hlist_head *head;
 
 	hvalue = avc_hash(ssid, tsid, tclass);
-	list_for_each_entry_rcu(node, &avc_cache.slots[hvalue], list) {
+	head = &avc_cache.slots[hvalue];
+	hlist_for_each_entry_rcu(node, head, list) {
 		if (ssid == node->ae.ssid &&
 		    tclass == node->ae.tclass &&
 		    tsid == node->ae.tsid) {
@@ -373,15 +310,6 @@ static inline struct avc_node *avc_search_node(u32 ssid, u32 tsid, u16 tclass)
 		}
 	}
 
-	if (ret == NULL) {
-		/* cache miss */
-		goto out;
-	}
-
-	/* cache hit */
-	if (atomic_read(&ret->ae.used) != 1)
-		atomic_set(&ret->ae.used, 1);
-out:
 	return ret;
 }
 
@@ -390,31 +318,25 @@ out:
  * @ssid: source security identifier
  * @tsid: target security identifier
  * @tclass: target security class
- * @requested: requested permissions, interpreted based on @tclass
  *
  * Look up an AVC entry that is valid for the
- * @requested permissions between the SID pair
  * (@ssid, @tsid), interpreting the permissions
  * based on @tclass.  If a valid AVC entry exists,
- * then this function return the avc_node.
+ * then this function returns the avc_node.
  * Otherwise, this function returns NULL.
  */
-static struct avc_node *avc_lookup(u32 ssid, u32 tsid, u16 tclass, u32 requested)
+static struct avc_node *avc_lookup(u32 ssid, u32 tsid, u16 tclass)
 {
 	struct avc_node *node;
 
 	avc_cache_stats_incr(lookups);
 	node = avc_search_node(ssid, tsid, tclass);
 
-	if (node && ((node->ae.avd.decided & requested) == requested)) {
-		avc_cache_stats_incr(hits);
-		goto out;
-	}
+	if (node)
+		return node;
 
-	node = NULL;
 	avc_cache_stats_incr(misses);
-out:
-	return node;
+	return NULL;
 }
 
 static int avc_latest_notif_update(int seqno, int is_insert)
@@ -426,7 +348,7 @@ static int avc_latest_notif_update(int seqno, int is_insert)
 	spin_lock_irqsave(&notif_lock, flag);
 	if (is_insert) {
 		if (seqno < avc_cache.latest_notif) {
-			printk(KERN_WARNING "avc:  seqno %d < latest_notif %d\n",
+			printk(KERN_WARNING "SELinux: avc:  seqno %d < latest_notif %d\n",
 			       seqno, avc_cache.latest_notif);
 			ret = -EAGAIN;
 		}
@@ -444,273 +366,144 @@ static int avc_latest_notif_update(int seqno, int is_insert)
  * @ssid: source security identifier
  * @tsid: target security identifier
  * @tclass: target security class
- * @ae: AVC entry
+ * @avd: resulting av decision
  *
  * Insert an AVC entry for the SID pair
  * (@ssid, @tsid) and class @tclass.
  * The access vectors and the sequence number are
  * normally provided by the security server in
  * response to a security_compute_av() call.  If the
- * sequence number @ae->avd.seqno is not less than the latest
+ * sequence number @avd->seqno is not less than the latest
  * revocation notification, then the function copies
  * the access vectors into a cache entry, returns
  * avc_node inserted. Otherwise, this function returns NULL.
  */
-static struct avc_node *avc_insert(u32 ssid, u32 tsid, u16 tclass, struct avc_entry *ae)
+static struct avc_node *avc_insert(u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd)
 {
 	struct avc_node *pos, *node = NULL;
 	int hvalue;
 	unsigned long flag;
 
-	if (avc_latest_notif_update(ae->avd.seqno, 1))
+	if (avc_latest_notif_update(avd->seqno, 1))
 		goto out;
 
 	node = avc_alloc_node();
 	if (node) {
+		struct hlist_head *head;
+		spinlock_t *lock;
+
 		hvalue = avc_hash(ssid, tsid, tclass);
-		avc_node_populate(node, ssid, tsid, tclass, ae);
+		avc_node_populate(node, ssid, tsid, tclass, avd);
+
+		head = &avc_cache.slots[hvalue];
+		lock = &avc_cache.slots_lock[hvalue];
 
-		spin_lock_irqsave(&avc_cache.slots_lock[hvalue], flag);
-		list_for_each_entry(pos, &avc_cache.slots[hvalue], list) {
+		spin_lock_irqsave(lock, flag);
+		hlist_for_each_entry(pos, head, list) {
 			if (pos->ae.ssid == ssid &&
 			    pos->ae.tsid == tsid &&
 			    pos->ae.tclass == tclass) {
-			    	avc_node_replace(node, pos);
+				avc_node_replace(node, pos);
 				goto found;
 			}
 		}
-		list_add_rcu(&node->list, &avc_cache.slots[hvalue]);
+		hlist_add_head_rcu(&node->list, head);
 found:
-		spin_unlock_irqrestore(&avc_cache.slots_lock[hvalue], flag);
+		spin_unlock_irqrestore(lock, flag);
 	}
 out:
 	return node;
 }
 
-static inline void avc_print_ipv6_addr(struct audit_buffer *ab,
-				       struct in6_addr *addr, __be16 port,
-				       char *name1, char *name2)
-{
-	if (!ipv6_addr_any(addr))
-		audit_log_format(ab, " %s=" NIP6_FMT, name1, NIP6(*addr));
-	if (port)
-		audit_log_format(ab, " %s=%d", name2, ntohs(port));
-}
-
-static inline void avc_print_ipv4_addr(struct audit_buffer *ab, __be32 addr,
-				       __be16 port, char *name1, char *name2)
+/**
+ * avc_audit_pre_callback - SELinux specific information
+ * will be called by generic audit code
+ * @ab: the audit buffer
+ * @a: audit_data
+ */
+static void avc_audit_pre_callback(struct audit_buffer *ab, void *a)
 {
-	if (addr)
-		audit_log_format(ab, " %s=" NIPQUAD_FMT, name1, NIPQUAD(addr));
-	if (port)
-		audit_log_format(ab, " %s=%d", name2, ntohs(port));
+	struct common_audit_data *ad = a;
+	audit_log_format(ab, "avc:  %s ",
+			 ad->selinux_audit_data->denied ? "denied" : "granted");
+	avc_dump_av(ab, ad->selinux_audit_data->tclass,
+			ad->selinux_audit_data->audited);
+	audit_log_format(ab, " for ");
 }
 
 /**
- * avc_audit - Audit the granting or denial of permissions.
- * @ssid: source security identifier
- * @tsid: target security identifier
- * @tclass: target security class
- * @requested: requested permissions
- * @avd: access vector decisions
- * @result: result from avc_has_perm_noaudit
- * @a:  auxiliary audit data
- *
- * Audit the granting or denial of permissions in accordance
- * with the policy.  This function is typically called by
- * avc_has_perm() after a permission check, but can also be
- * called directly by callers who use avc_has_perm_noaudit()
- * in order to separate the permission check from the auditing.
- * For example, this separation is useful when the permission check must
- * be performed under a lock, to allow the lock to be released
- * before calling the auditing code.
+ * avc_audit_post_callback - SELinux specific information
+ * will be called by generic audit code
+ * @ab: the audit buffer
+ * @a: audit_data
  */
-void avc_audit(u32 ssid, u32 tsid,
-               u16 tclass, u32 requested,
-               struct av_decision *avd, int result, struct avc_audit_data *a)
+static void avc_audit_post_callback(struct audit_buffer *ab, void *a)
 {
-	struct task_struct *tsk = current;
-	struct inode *inode = NULL;
-	u32 denied, audited;
-	struct audit_buffer *ab;
-
-	denied = requested & ~avd->allowed;
-	if (denied) {
-		audited = denied;
-		if (!(audited & avd->auditdeny))
-			return;
-	} else if (result) {
-		audited = denied = requested;
-        } else {
-		audited = requested;
-		if (!(audited & avd->auditallow))
-			return;
+	struct common_audit_data *ad = a;
+	audit_log_format(ab, " ");
+	avc_dump_query(ab, ad->selinux_audit_data->ssid,
+			   ad->selinux_audit_data->tsid,
+			   ad->selinux_audit_data->tclass);
+	if (ad->selinux_audit_data->denied) {
+		audit_log_format(ab, " permissive=%u",
+				 ad->selinux_audit_data->result ? 0 : 1);
 	}
+}
 
-	ab = audit_log_start(current->audit_context, GFP_ATOMIC, AUDIT_AVC);
-	if (!ab)
-		return;		/* audit_panic has been called */
-	audit_log_format(ab, "avc:  %s ", denied ? "denied" : "granted");
-	avc_dump_av(ab, tclass,audited);
-	audit_log_format(ab, " for ");
-	if (a && a->tsk)
-		tsk = a->tsk;
-	if (tsk && tsk->pid) {
-		audit_log_format(ab, " pid=%d comm=", tsk->pid);
-		audit_log_untrustedstring(ab, tsk->comm);
-	}
-	if (a) {
-		switch (a->type) {
-		case AVC_AUDIT_DATA_IPC:
-			audit_log_format(ab, " key=%d", a->u.ipc_id);
-			break;
-		case AVC_AUDIT_DATA_CAP:
-			audit_log_format(ab, " capability=%d", a->u.cap);
-			break;
-		case AVC_AUDIT_DATA_FS:
-			if (a->u.fs.path.dentry) {
-				struct dentry *dentry = a->u.fs.path.dentry;
-				if (a->u.fs.path.mnt) {
-					audit_log_d_path(ab, "path=",
-							 &a->u.fs.path);
-				} else {
-					audit_log_format(ab, " name=");
-					audit_log_untrustedstring(ab, dentry->d_name.name);
-				}
-				inode = dentry->d_inode;
-			} else if (a->u.fs.inode) {
-				struct dentry *dentry;
-				inode = a->u.fs.inode;
-				dentry = d_find_alias(inode);
-				if (dentry) {
-					audit_log_format(ab, " name=");
-					audit_log_untrustedstring(ab, dentry->d_name.name);
-					dput(dentry);
-				}
-			}
-			if (inode)
-				audit_log_format(ab, " dev=%s ino=%lu",
-						 inode->i_sb->s_id,
-						 inode->i_ino);
-			break;
-		case AVC_AUDIT_DATA_NET:
-			if (a->u.net.sk) {
-				struct sock *sk = a->u.net.sk;
-				struct unix_sock *u;
-				int len = 0;
-				char *p = NULL;
-
-				switch (sk->sk_family) {
-				case AF_INET: {
-					struct inet_sock *inet = inet_sk(sk);
-
-					avc_print_ipv4_addr(ab, inet->rcv_saddr,
-							    inet->sport,
-							    "laddr", "lport");
-					avc_print_ipv4_addr(ab, inet->daddr,
-							    inet->dport,
-							    "faddr", "fport");
-					break;
-				}
-				case AF_INET6: {
-					struct inet_sock *inet = inet_sk(sk);
-					struct ipv6_pinfo *inet6 = inet6_sk(sk);
-
-					avc_print_ipv6_addr(ab, &inet6->rcv_saddr,
-							    inet->sport,
-							    "laddr", "lport");
-					avc_print_ipv6_addr(ab, &inet6->daddr,
-							    inet->dport,
-							    "faddr", "fport");
-					break;
-				}
-				case AF_UNIX:
-					u = unix_sk(sk);
-					if (u->dentry) {
-						struct path path = {
-							.dentry = u->dentry,
-							.mnt = u->mnt
-						};
-						audit_log_d_path(ab, "path=",
-								 &path);
-						break;
-					}
-					if (!u->addr)
-						break;
-					len = u->addr->len-sizeof(short);
-					p = &u->addr->name->sun_path[0];
-					audit_log_format(ab, " path=");
-					if (*p)
-						audit_log_untrustedstring(ab, p);
-					else
-						audit_log_hex(ab, p, len);
-					break;
-				}
-			}
-			
-			switch (a->u.net.family) {
-			case AF_INET:
-				avc_print_ipv4_addr(ab, a->u.net.v4info.saddr,
-						    a->u.net.sport,
-						    "saddr", "src");
-				avc_print_ipv4_addr(ab, a->u.net.v4info.daddr,
-						    a->u.net.dport,
-						    "daddr", "dest");
-				break;
-			case AF_INET6:
-				avc_print_ipv6_addr(ab, &a->u.net.v6info.saddr,
-						    a->u.net.sport,
-						    "saddr", "src");
-				avc_print_ipv6_addr(ab, &a->u.net.v6info.daddr,
-						    a->u.net.dport,
-						    "daddr", "dest");
-				break;
-			}
-			if (a->u.net.netif > 0) {
-				struct net_device *dev;
-
-				/* NOTE: we always use init's namespace */
-				dev = dev_get_by_index(&init_net,
-						       a->u.net.netif);
-				if (dev) {
-					audit_log_format(ab, " netif=%s",
-							 dev->name);
-					dev_put(dev);
-				}
-			}
-			break;
-		}
+/* This is the slow part of avc audit with big stack footprint */
+noinline int slow_avc_audit(u32 ssid, u32 tsid, u16 tclass,
+		u32 requested, u32 audited, u32 denied, int result,
+		struct common_audit_data *a,
+		unsigned flags)
+{
+	struct common_audit_data stack_data;
+	struct selinux_audit_data sad;
+
+	if (!a) {
+		a = &stack_data;
+		a->type = LSM_AUDIT_DATA_NONE;
 	}
-	audit_log_format(ab, " ");
-	avc_dump_query(ab, ssid, tsid, tclass);
-	audit_log_end(ab);
+
+	/*
+	 * When in a RCU walk do the audit on the RCU retry.  This is because
+	 * the collection of the dname in an inode audit message is not RCU
+	 * safe.  Note this may drop some audits when the situation changes
+	 * during retry. However this is logically just as if the operation
+	 * happened a little later.
+	 */
+	if ((a->type == LSM_AUDIT_DATA_INODE) &&
+	    (flags & MAY_NOT_BLOCK))
+		return -ECHILD;
+
+	sad.tclass = tclass;
+	sad.requested = requested;
+	sad.ssid = ssid;
+	sad.tsid = tsid;
+	sad.audited = audited;
+	sad.denied = denied;
+	sad.result = result;
+
+	a->selinux_audit_data = &sad;
+
+	common_lsm_audit(a, avc_audit_pre_callback, avc_audit_post_callback);
+	return 0;
 }
 
 /**
  * avc_add_callback - Register a callback for security events.
  * @callback: callback function
  * @events: security events
- * @ssid: source security identifier or %SECSID_WILD
- * @tsid: target security identifier or %SECSID_WILD
- * @tclass: target security class
- * @perms: permissions
  *
- * Register a callback function for events in the set @events
- * related to the SID pair (@ssid, @tsid) and
- * and the permissions @perms, interpreting
- * @perms based on @tclass.  Returns %0 on success or
- * -%ENOMEM if insufficient memory exists to add the callback.
+ * Register a callback function for events in the set @events.
+ * Returns %0 on success or -%ENOMEM if insufficient memory
+ * exists to add the callback.
  */
-int avc_add_callback(int (*callback)(u32 event, u32 ssid, u32 tsid,
-                                     u16 tclass, u32 perms,
-                                     u32 *out_retained),
-                     u32 events, u32 ssid, u32 tsid,
-                     u16 tclass, u32 perms)
+int __init avc_add_callback(int (*callback)(u32 event), u32 events)
 {
 	struct avc_callback_node *c;
 	int rc = 0;
 
-	c = kmalloc(sizeof(*c), GFP_ATOMIC);
+	c = kmalloc(sizeof(*c), GFP_KERNEL);
 	if (!c) {
 		rc = -ENOMEM;
 		goto out;
@@ -718,9 +511,6 @@ int avc_add_callback(int (*callback)(u32 event, u32 ssid, u32 tsid,
 
 	c->callback = callback;
 	c->events = events;
-	c->ssid = ssid;
-	c->tsid = tsid;
-	c->perms = perms;
 	c->next = avc_callbacks;
 	avc_callbacks = c;
 out:
@@ -737,17 +527,21 @@ static inline int avc_sidcmp(u32 x, u32 y)
  * @event : Updating event
  * @perms : Permission mask bits
  * @ssid,@tsid,@tclass : identifier of an AVC entry
+ * @seqno : sequence number when decision was made
  *
  * if a valid AVC entry doesn't exist,this function returns -ENOENT.
  * if kmalloc() called internal returns NULL, this function returns -ENOMEM.
- * otherwise, this function update the AVC entry. The original AVC-entry object
+ * otherwise, this function updates the AVC entry. The original AVC-entry object
  * will release later by RCU.
  */
-static int avc_update_node(u32 event, u32 perms, u32 ssid, u32 tsid, u16 tclass)
+static int avc_update_node(u32 event, u32 perms, u32 ssid, u32 tsid, u16 tclass,
+			   u32 seqno)
 {
 	int hvalue, rc = 0;
 	unsigned long flag;
 	struct avc_node *pos, *node, *orig = NULL;
+	struct hlist_head *head;
+	spinlock_t *lock;
 
 	node = avc_alloc_node();
 	if (!node) {
@@ -757,12 +551,17 @@ static int avc_update_node(u32 event, u32 perms, u32 ssid, u32 tsid, u16 tclass)
 
 	/* Lock the target slot */
 	hvalue = avc_hash(ssid, tsid, tclass);
-	spin_lock_irqsave(&avc_cache.slots_lock[hvalue], flag);
 
-	list_for_each_entry(pos, &avc_cache.slots[hvalue], list){
-		if ( ssid==pos->ae.ssid &&
-		     tsid==pos->ae.tsid &&
-		     tclass==pos->ae.tclass ){
+	head = &avc_cache.slots[hvalue];
+	lock = &avc_cache.slots_lock[hvalue];
+
+	spin_lock_irqsave(lock, flag);
+
+	hlist_for_each_entry(pos, head, list) {
+		if (ssid == pos->ae.ssid &&
+		    tsid == pos->ae.tsid &&
+		    tclass == pos->ae.tclass &&
+		    seqno == pos->ae.avd.seqno){
 			orig = pos;
 			break;
 		}
@@ -778,7 +577,7 @@ static int avc_update_node(u32 event, u32 perms, u32 ssid, u32 tsid, u16 tclass)
 	 * Copy and replace original node.
 	 */
 
-	avc_node_populate(node, ssid, tsid, tclass, &orig->ae);
+	avc_node_populate(node, ssid, tsid, tclass, &orig->ae.avd);
 
 	switch (event) {
 	case AVC_CALLBACK_GRANT:
@@ -803,33 +602,53 @@ static int avc_update_node(u32 event, u32 perms, u32 ssid, u32 tsid, u16 tclass)
 	}
 	avc_node_replace(node, orig);
 out_unlock:
-	spin_unlock_irqrestore(&avc_cache.slots_lock[hvalue], flag);
+	spin_unlock_irqrestore(lock, flag);
 out:
 	return rc;
 }
 
 /**
- * avc_ss_reset - Flush the cache and revalidate migrated permissions.
- * @seqno: policy sequence number
+ * avc_flush - Flush the cache
  */
-int avc_ss_reset(u32 seqno)
+static void avc_flush(void)
 {
-	struct avc_callback_node *c;
-	int i, rc = 0, tmprc;
-	unsigned long flag;
+	struct hlist_head *head;
 	struct avc_node *node;
+	spinlock_t *lock;
+	unsigned long flag;
+	int i;
 
 	for (i = 0; i < AVC_CACHE_SLOTS; i++) {
-		spin_lock_irqsave(&avc_cache.slots_lock[i], flag);
-		list_for_each_entry(node, &avc_cache.slots[i], list)
+		head = &avc_cache.slots[i];
+		lock = &avc_cache.slots_lock[i];
+
+		spin_lock_irqsave(lock, flag);
+		/*
+		 * With preemptable RCU, the outer spinlock does not
+		 * prevent RCU grace periods from ending.
+		 */
+		rcu_read_lock();
+		hlist_for_each_entry(node, head, list)
 			avc_node_delete(node);
-		spin_unlock_irqrestore(&avc_cache.slots_lock[i], flag);
+		rcu_read_unlock();
+		spin_unlock_irqrestore(lock, flag);
 	}
+}
+
+/**
+ * avc_ss_reset - Flush the cache and revalidate migrated permissions.
+ * @seqno: policy sequence number
+ */
+int avc_ss_reset(u32 seqno)
+{
+	struct avc_callback_node *c;
+	int rc = 0, tmprc;
+
+	avc_flush();
 
 	for (c = avc_callbacks; c; c = c->next) {
 		if (c->events & AVC_CALLBACK_RESET) {
-			tmprc = c->callback(AVC_CALLBACK_RESET,
-			                    0, 0, 0, 0, NULL);
+			tmprc = c->callback(AVC_CALLBACK_RESET);
 			/* save the first error encountered for the return
 			   value and continue processing the callbacks */
 			if (!rc)
@@ -841,6 +660,41 @@ int avc_ss_reset(u32 seqno)
 	return rc;
 }
 
+/*
+ * Slow-path helper function for avc_has_perm_noaudit,
+ * when the avc_node lookup fails. We get called with
+ * the RCU read lock held, and need to return with it
+ * still held, but drop if for the security compute.
+ *
+ * Don't inline this, since it's the slow-path and just
+ * results in a bigger stack frame.
+ */
+static noinline struct avc_node *avc_compute_av(u32 ssid, u32 tsid,
+			 u16 tclass, struct av_decision *avd)
+{
+	rcu_read_unlock();
+	security_compute_av(ssid, tsid, tclass, avd);
+	rcu_read_lock();
+	return avc_insert(ssid, tsid, tclass, avd);
+}
+
+static noinline int avc_denied(u32 ssid, u32 tsid,
+			 u16 tclass, u32 requested,
+			 unsigned flags,
+			 struct av_decision *avd)
+{
+	if (flags & AVC_STRICT)
+		return -EACCES;
+
+	if (selinux_enforcing && !(avd->flags & AVD_FLAGS_PERMISSIVE))
+		return -EACCES;
+
+	avc_update_node(AVC_CALLBACK_GRANT, requested, ssid,
+				tsid, tclass, avd->seqno);
+	return 0;
+}
+
+
 /**
  * avc_has_perm_noaudit - Check permissions but perform no auditing.
  * @ssid: source security identifier
@@ -861,46 +715,32 @@ int avc_ss_reset(u32 seqno)
  * auditing, e.g. in cases where a lock must be held for the check but
  * should be released for the auditing.
  */
-int avc_has_perm_noaudit(u32 ssid, u32 tsid,
+inline int avc_has_perm_noaudit(u32 ssid, u32 tsid,
 			 u16 tclass, u32 requested,
 			 unsigned flags,
 			 struct av_decision *avd)
 {
 	struct avc_node *node;
-	struct avc_entry entry, *p_ae;
 	int rc = 0;
 	u32 denied;
 
+	BUG_ON(!requested);
+
 	rcu_read_lock();
 
-	node = avc_lookup(ssid, tsid, tclass, requested);
-	if (!node) {
-		rcu_read_unlock();
-		rc = security_compute_av(ssid,tsid,tclass,requested,&entry.avd);
-		if (rc)
-			goto out;
-		rcu_read_lock();
-		node = avc_insert(ssid,tsid,tclass,&entry);
+	node = avc_lookup(ssid, tsid, tclass);
+	if (unlikely(!node)) {
+		node = avc_compute_av(ssid, tsid, tclass, avd);
+	} else {
+		memcpy(avd, &node->ae.avd, sizeof(*avd));
+		avd = &node->ae.avd;
 	}
 
-	p_ae = node ? &node->ae : &entry;
-
-	if (avd)
-		memcpy(avd, &p_ae->avd, sizeof(*avd));
-
-	denied = requested & ~(p_ae->avd.allowed);
-
-	if (!requested || denied) {
-		if (selinux_enforcing || (flags & AVC_STRICT))
-			rc = -EACCES;
-		else
-			if (node)
-				avc_update_node(AVC_CALLBACK_GRANT,requested,
-						ssid,tsid,tclass);
-	}
+	denied = requested & ~(avd->allowed);
+	if (unlikely(denied))
+		rc = avc_denied(ssid, tsid, tclass, requested, flags, avd);
 
 	rcu_read_unlock();
-out:
 	return rc;
 }
 
@@ -921,13 +761,16 @@ out:
  * another -errno upon other errors.
  */
 int avc_has_perm(u32 ssid, u32 tsid, u16 tclass,
-                 u32 requested, struct avc_audit_data *auditdata)
+		 u32 requested, struct common_audit_data *auditdata)
 {
 	struct av_decision avd;
-	int rc;
+	int rc, rc2;
 
 	rc = avc_has_perm_noaudit(ssid, tsid, tclass, requested, 0, &avd);
-	avc_audit(ssid, tsid, tclass, requested, &avd, rc, auditdata);
+
+	rc2 = avc_audit(ssid, tsid, tclass, requested, &avd, rc, auditdata);
+	if (rc2)
+		return rc2;
 	return rc;
 }
 
@@ -935,3 +778,22 @@ u32 avc_policy_seqno(void)
 {
 	return avc_cache.latest_notif;
 }
+
+void avc_disable(void)
+{
+	/*
+	 * If you are looking at this because you have realized that we are
+	 * not destroying the avc_node_cachep it might be easy to fix, but
+	 * I don't know the memory barrier semantics well enough to know.  It's
+	 * possible that some other task dereferenced security_ops when
+	 * it still pointed to selinux operations.  If that is the case it's
+	 * possible that it is about to use the avc and is about to need the
+	 * avc_node_cachep.  I know I could wrap the security.c security_ops call
+	 * in an rcu_lock, but seriously, it's not worth it.  Instead I just flush
+	 * the cache and get that memory back.
+	 */
+	if (avc_node_cachep) {
+		avc_flush();
+		/* kmem_cache_destroy(avc_node_cachep); */
+	}
+}