selinux: sidtab reverse lookup hash table

This replaces the reverse table lookup and reverse cache with a
hashtable which improves cache-miss reverse-lookup times from
O(n) to O(1)* and maintains the same performance as a reverse
cache hit.

This reduces the time needed to add a new sidtab entry from ~500us
to 5us on a Pixel 3 when there are ~10,000 sidtab entries.

The implementation uses the kernel's generic hashtable API,
It uses the context's string represtation as the hash source,
and the kernels generic string hashing algorithm full_name_hash()
to reduce the string to a 32 bit value.

This change also maintains the improvement introduced in
commit ee1a84fd ("selinux: overhaul sidtab to fix bug and improve
performance") which removed the need to keep the current sidtab
locked during policy reload. It does however introduce periodic
locking of the target sidtab while converting the hashtable. Sidtab
entries are never modified or removed, so the context struct stored
in the sid_to_context tree can also be used for the context_to_sid
hashtable to reduce memory usage.

This bug was reported by:
- On the selinux bug tracker.
  BUG: kernel softlockup due to too many SIDs/contexts #37
  https://github.com/SELinuxProject/selinux-kernel/issues/37
- Jovana Knezevic on Android's bugtracker.
  Bug: 140252993
  "During multi-user performance testing, we create and remove users
  many times. selinux_android_restorecon_pkgdir goes from 1ms to over
  20ms after about 200 user creations and removals. Accumulated over
  ~280 packages, that adds a significant time to user creation,
  making perf benchmarks unreliable."

* Hashtable lookup is only O(1) when n < the number of buckets.
Signed-off-by: Jeff Vander Stoep <jeffv@google.com>
Reported-by: Stephen Smalley <sds@tycho.nsa.gov>
Reported-by: Jovana Knezevic <jovanak@google.com>
Reviewed-by: Stephen Smalley <sds@tycho.nsa.gov>
Tested-by: Stephen Smalley <sds@tycho.nsa.gov>
[PM: subj tweak, removed changelog from patch description]
Signed-off-by: Paul Moore <paul@paul-moore.com>

security/selinux/Kconfig

@@ -85,3 +85,15 @@ config SECURITY_SELINUX_CHECKREQPROT_VALUE
 	  via /selinux/checkreqprot if authorized by policy.
 
 	  If you are unsure how to answer this question, answer 0.
+
+config SECURITY_SELINUX_SIDTAB_HASH_BITS
+	int "NSA SELinux sidtab hashtable size"
+	depends on SECURITY_SELINUX
+	range 8 13
+	default 9
+	help
+	  This option sets the number of buckets used in the sidtab hashtable
+	  to 2^SECURITY_SELINUX_SIDTAB_HASH_BITS buckets. The number of hash
+	  collisions may be viewed at /sys/fs/selinux/ss/sidtab_hash_stats. If
+	  chain lengths are high (e.g. > 20) then selecting a higher value here
+	  will ensure that lookups times are short and stable.

security/selinux/include/security.h

@@ -395,5 +395,6 @@ extern int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm);
 extern void avtab_cache_init(void);
 extern void ebitmap_cache_init(void);
 extern void hashtab_cache_init(void);
+extern int security_sidtab_hash_stats(struct selinux_state *state, char *page);
 
 #endif /* _SELINUX_SECURITY_H_ */

security/selinux/selinuxfs.c

@@ -1482,6 +1482,32 @@ static ssize_t sel_read_avc_hash_stats(struct file *filp, char __user *buf,
 	return length;
 }
 
+static ssize_t sel_read_sidtab_hash_stats(struct file *filp, char __user *buf,
+					size_t count, loff_t *ppos)
+{
+	struct selinux_fs_info *fsi = file_inode(filp)->i_sb->s_fs_info;
+	struct selinux_state *state = fsi->state;
+	char *page;
+	ssize_t length;
+
+	page = (char *)__get_free_page(GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+
+	length = security_sidtab_hash_stats(state, page);
+	if (length >= 0)
+		length = simple_read_from_buffer(buf, count, ppos, page,
+						length);
+	free_page((unsigned long)page);
+
+	return length;
+}
+
+static const struct file_operations sel_sidtab_hash_stats_ops = {
+	.read		= sel_read_sidtab_hash_stats,
+	.llseek		= generic_file_llseek,
+};
+
 static const struct file_operations sel_avc_cache_threshold_ops = {
 	.read		= sel_read_avc_cache_threshold,
 	.write		= sel_write_avc_cache_threshold,
@@ -1599,6 +1625,37 @@ static int sel_make_avc_files(struct dentry *dir)
 	return 0;
 }
 
+static int sel_make_ss_files(struct dentry *dir)
+{
+	struct super_block *sb = dir->d_sb;
+	struct selinux_fs_info *fsi = sb->s_fs_info;
+	int i;
+	static struct tree_descr files[] = {
+		{ "sidtab_hash_stats", &sel_sidtab_hash_stats_ops, S_IRUGO },
+	};
+
+	for (i = 0; i < ARRAY_SIZE(files); i++) {
+		struct inode *inode;
+		struct dentry *dentry;
+
+		dentry = d_alloc_name(dir, files[i].name);
+		if (!dentry)
+			return -ENOMEM;
+
+		inode = sel_make_inode(dir->d_sb, S_IFREG|files[i].mode);
+		if (!inode) {
+			dput(dentry);
+			return -ENOMEM;
+		}
+
+		inode->i_fop = files[i].ops;
+		inode->i_ino = ++fsi->last_ino;
+		d_add(dentry, inode);
+	}
+
+	return 0;
+}
+
 static ssize_t sel_read_initcon(struct file *file, char __user *buf,
 				size_t count, loff_t *ppos)
 {
@@ -1963,6 +2020,14 @@ static int sel_fill_super(struct super_block *sb, struct fs_context *fc)
 	}
 
 	ret = sel_make_avc_files(dentry);
+
+	dentry = sel_make_dir(sb->s_root, "ss", &fsi->last_ino);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto err;
+	}
+
+	ret = sel_make_ss_files(dentry);
 	if (ret)
 		goto err;
 

security/selinux/ss/context.h

@@ -31,6 +31,7 @@ struct context {
 	u32 len;        /* length of string in bytes */
 	struct mls_range range;
 	char *str;	/* string representation if context cannot be mapped. */
+	u32 hash;	/* a hash of the string representation */
 };
 
 static inline void mls_context_init(struct context *c)
@@ -168,12 +169,13 @@ static inline int context_cpy(struct context *dst, struct context *src)
 		kfree(dst->str);
 		return rc;
 	}
+	dst->hash = src->hash;
 	return 0;
 }
 
 static inline void context_destroy(struct context *c)
 {
-	c->user = c->role = c->type = 0;
+	c->user = c->role = c->type = c->hash = 0;
 	kfree(c->str);
 	c->str = NULL;
 	c->len = 0;
@@ -182,6 +184,8 @@ static inline void context_destroy(struct context *c)
 
 static inline int context_cmp(struct context *c1, struct context *c2)
 {
+	if (c1->hash && c2->hash && (c1->hash != c2->hash))
+		return 0;
 	if (c1->len && c2->len)
 		return (c1->len == c2->len && !strcmp(c1->str, c2->str));
 	if (c1->len || c2->len)
@@ -192,5 +196,10 @@ static inline int context_cmp(struct context *c1, struct context *c2)
 		mls_context_cmp(c1, c2));
 }
 
+static inline unsigned int context_compute_hash(const char *s)
+{
+	return full_name_hash(NULL, s, strlen(s));
+}
+
 #endif	/* _SS_CONTEXT_H_ */
 

security/selinux/ss/policydb.c

@@ -878,6 +878,11 @@ int policydb_load_isids(struct policydb *p, struct sidtab *s)
 			sidtab_destroy(s);
 			goto out;
 		}
+		rc = context_add_hash(p, &c->context[0]);
+		if (rc) {
+			sidtab_destroy(s);
+			goto out;
+		}
 
 		rc = sidtab_set_initial(s, c->sid[0], &c->context[0]);
 		if (rc) {

security/selinux/ss/services.c

@@ -1257,6 +1257,17 @@ static int context_struct_to_string(struct policydb *p,
 
 #include "initial_sid_to_string.h"
 
+int security_sidtab_hash_stats(struct selinux_state *state, char *page)
+{
+	int rc;
+
+	read_lock(&state->ss->policy_rwlock);
+	rc = sidtab_hash_stats(state->ss->sidtab, page);
+	read_unlock(&state->ss->policy_rwlock);
+
+	return rc;
+}
+
 const char *security_get_initial_sid_context(u32 sid)
 {
 	if (unlikely(sid > SECINITSID_NUM))
@@ -1449,6 +1460,42 @@ static int string_to_context_struct(struct policydb *pol,
 	return rc;
 }
 
+int context_add_hash(struct policydb *policydb,
+		     struct context *context)
+{
+	int rc;
+	char *str;
+	int len;
+
+	if (context->str) {
+		context->hash = context_compute_hash(context->str);
+	} else {
+		rc = context_struct_to_string(policydb, context,
+					      &str, &len);
+		if (rc)
+			return rc;
+		context->hash = context_compute_hash(str);
+		kfree(str);
+	}
+	return 0;
+}
+
+static int context_struct_to_sid(struct selinux_state *state,
+				 struct context *context, u32 *sid)
+{
+	int rc;
+	struct sidtab *sidtab = state->ss->sidtab;
+	struct policydb *policydb = &state->ss->policydb;
+
+	if (!context->hash) {
+		rc = context_add_hash(policydb, context);
+		if (rc)
+			return rc;
+	}
+
+	return sidtab_context_to_sid(sidtab, context, sid);
+}
+
 static int security_context_to_sid_core(struct selinux_state *state,
 					const char *scontext, u32 scontext_len,
 					u32 *sid, u32 def_sid, gfp_t gfp_flags,
@@ -1501,7 +1548,7 @@ static int security_context_to_sid_core(struct selinux_state *state,
 		str = NULL;
 	} else if (rc)
 		goto out_unlock;
-	rc = sidtab_context_to_sid(sidtab, &context, sid);
+	rc = context_struct_to_sid(state, &context, sid);
 	context_destroy(&context);
 out_unlock:
 	read_unlock(&state->ss->policy_rwlock);
@@ -1805,7 +1852,7 @@ static int security_compute_sid(struct selinux_state *state,
 			goto out_unlock;
 	}
 	/* Obtain the sid for the context. */
-	rc = sidtab_context_to_sid(sidtab, &newcontext, out_sid);
+	rc = context_struct_to_sid(state, &newcontext, out_sid);
 out_unlock:
 	read_unlock(&state->ss->policy_rwlock);
 	context_destroy(&newcontext);
@@ -1957,6 +2004,7 @@ static int convert_context(struct context *oldc, struct context *newc, void *p)
 			context_init(newc);
 			newc->str = s;
 			newc->len = oldc->len;
+			newc->hash = oldc->hash;
 			return 0;
 		}
 		kfree(s);
@@ -2033,6 +2081,10 @@ static int convert_context(struct context *oldc, struct context *newc, void *p)
 			goto bad;
 	}
 
+	rc = context_add_hash(args->newp, newc);
+	if (rc)
+		goto bad;
+
 	return 0;
 bad:
 	/* Map old representation to string and save it. */
@@ -2042,6 +2094,7 @@ static int convert_context(struct context *oldc, struct context *newc, void *p)
 	context_destroy(newc);
 	newc->str = s;
 	newc->len = len;
+	newc->hash = context_compute_hash(s);
 	pr_info("SELinux:  Context %s became invalid (unmapped).\n",
 		newc->str);
 	return 0;
@@ -2280,8 +2333,7 @@ int security_port_sid(struct selinux_state *state,
 
 	if (c) {
 		if (!c->sid[0]) {
-			rc = sidtab_context_to_sid(sidtab,
-						   &c->context[0],
+			rc = context_struct_to_sid(state, &c->context[0],
 						   &c->sid[0]);
 			if (rc)
 				goto out;
@@ -2306,14 +2358,12 @@ int security_ib_pkey_sid(struct selinux_state *state,
 			 u64 subnet_prefix, u16 pkey_num, u32 *out_sid)
 {
 	struct policydb *policydb;
-	struct sidtab *sidtab;
 	struct ocontext *c;
 	int rc = 0;
 
 	read_lock(&state->ss->policy_rwlock);
 
 	policydb = &state->ss->policydb;
-	sidtab = state->ss->sidtab;
 
 	c = policydb->ocontexts[OCON_IBPKEY];
 	while (c) {
@@ -2327,7 +2377,7 @@ int security_ib_pkey_sid(struct selinux_state *state,
 
 	if (c) {
 		if (!c->sid[0]) {
-			rc = sidtab_context_to_sid(sidtab,
+			rc = context_struct_to_sid(state,
 						   &c->context[0],
 						   &c->sid[0]);
 			if (rc)
@@ -2374,8 +2424,7 @@ int security_ib_endport_sid(struct selinux_state *state,
 
 	if (c) {
 		if (!c->sid[0]) {
-			rc = sidtab_context_to_sid(sidtab,
-						   &c->context[0],
+			rc = context_struct_to_sid(state, &c->context[0],
 						   &c->sid[0]);
 			if (rc)
 				goto out;
@@ -2416,13 +2465,11 @@ int security_netif_sid(struct selinux_state *state,
 
 	if (c) {
 		if (!c->sid[0] || !c->sid[1]) {
-			rc = sidtab_context_to_sid(sidtab,
-						  &c->context[0],
+			rc = context_struct_to_sid(state, &c->context[0],
 						   &c->sid[0]);
 			if (rc)
 				goto out;
-			rc = sidtab_context_to_sid(sidtab,
-						   &c->context[1],
+			rc = context_struct_to_sid(state, &c->context[1],
 						   &c->sid[1]);
 			if (rc)
 				goto out;
@@ -2463,14 +2510,12 @@ int security_node_sid(struct selinux_state *state,
 		      u32 *out_sid)
 {
 	struct policydb *policydb;
-	struct sidtab *sidtab;
 	int rc;
 	struct ocontext *c;
 
 	read_lock(&state->ss->policy_rwlock);
 
 	policydb = &state->ss->policydb;
-	sidtab = state->ss->sidtab;
 
 	switch (domain) {
 	case AF_INET: {
@@ -2512,7 +2557,7 @@ int security_node_sid(struct selinux_state *state,
 
 	if (c) {
 		if (!c->sid[0]) {
-			rc = sidtab_context_to_sid(sidtab,
+			rc = context_struct_to_sid(state,
 						   &c->context[0],
 						   &c->sid[0]);
 			if (rc)
@@ -2596,12 +2641,17 @@ int security_get_user_sids(struct selinux_state *state,
 		usercon.role = i + 1;
 		ebitmap_for_each_positive_bit(&role->types, tnode, j) {
 			usercon.type = j + 1;
+			/*
+			 * The same context struct is reused here so the hash
+			 * must be reset.
+			 */
+			usercon.hash = 0;
 
 			if (mls_setup_user_range(policydb, fromcon, user,
 						 &usercon))
 				continue;
 
-			rc = sidtab_context_to_sid(sidtab, &usercon, &sid);
+			rc = context_struct_to_sid(state, &usercon, &sid);
 			if (rc)
 				goto out_unlock;
 			if (mynel < maxnel) {
@@ -2672,7 +2722,6 @@ static inline int __security_genfs_sid(struct selinux_state *state,
 				       u32 *sid)
 {
 	struct policydb *policydb = &state->ss->policydb;
-	struct sidtab *sidtab = state->ss->sidtab;
 	int len;
 	u16 sclass;
 	struct genfs *genfs;
@@ -2707,7 +2756,7 @@ static inline int __security_genfs_sid(struct selinux_state *state,
 		goto out;
 
 	if (!c->sid[0]) {
-		rc = sidtab_context_to_sid(sidtab, &c->context[0], &c->sid[0]);
+		rc = context_struct_to_sid(state, &c->context[0], &c->sid[0]);
 		if (rc)
 			goto out;
 	}
@@ -2770,7 +2819,7 @@ int security_fs_use(struct selinux_state *state, struct super_block *sb)
 	if (c) {
 		sbsec->behavior = c->v.behavior;
 		if (!c->sid[0]) {
-			rc = sidtab_context_to_sid(sidtab, &c->context[0],
+			rc = context_struct_to_sid(state, &c->context[0],
 						   &c->sid[0]);
 			if (rc)
 				goto out;
@@ -3026,8 +3075,7 @@ int security_sid_mls_copy(struct selinux_state *state,
 			goto out_unlock;
 		}
 	}
-
-	rc = sidtab_context_to_sid(sidtab, &newcon, new_sid);
+	rc = context_struct_to_sid(state, &newcon, new_sid);
 out_unlock:
 	read_unlock(&state->ss->policy_rwlock);
 	context_destroy(&newcon);
@@ -3620,7 +3668,7 @@ int security_netlbl_secattr_to_sid(struct selinux_state *state,
 		if (!mls_context_isvalid(policydb, &ctx_new))
 			goto out_free;
 
-		rc = sidtab_context_to_sid(sidtab, &ctx_new, sid);
+		rc = context_struct_to_sid(state, &ctx_new, sid);
 		if (rc)
 			goto out_free;
 

security/selinux/ss/services.h

@@ -8,7 +8,7 @@
 #define _SS_SERVICES_H_
 
 #include "policydb.h"
-#include "sidtab.h"
+#include "context.h"
 
 /* Mapping for a single class */
 struct selinux_mapping {
@@ -39,4 +39,6 @@ void services_compute_xperms_drivers(struct extended_perms *xperms,
 void services_compute_xperms_decision(struct extended_perms_decision *xpermd,
 					struct avtab_node *node);
 
+int context_add_hash(struct policydb *policydb, struct context *context);
+
 #endif	/* _SS_SERVICES_H_ */

security/selinux/ss/sidtab.h

@@ -13,11 +13,14 @@
 
 #include <linux/spinlock_types.h>
 #include <linux/log2.h>
+#include <linux/hashtable.h>
 
 #include "context.h"
 
 struct sidtab_entry_leaf {
+	u32 sid;
 	struct context context;
+	struct hlist_node list;
 };
 
 struct sidtab_node_inner;
@@ -57,7 +60,7 @@ struct sidtab_node_inner {
 
 struct sidtab_isid_entry {
 	int set;
-	struct context context;
+	struct sidtab_entry_leaf leaf;
 };
 
 struct sidtab_convert_params {
@@ -66,7 +69,8 @@ struct sidtab_convert_params {
 	struct sidtab *target;
 };
 
-#define SIDTAB_RCACHE_SIZE 3
+#define SIDTAB_HASH_BITS CONFIG_SECURITY_SELINUX_SIDTAB_HASH_BITS
+#define SIDTAB_HASH_BUCKETS (1 << SIDTAB_HASH_BITS)
 
 struct sidtab {
 	/*
@@ -83,11 +87,11 @@ struct sidtab {
 	struct sidtab_convert_params *convert;
 	spinlock_t lock;
 
-	/* reverse lookup cache - access atomically via {READ|WRITE}_ONCE() */
-	u32 rcache[SIDTAB_RCACHE_SIZE];
-
 	/* index == SID - 1 (no entry for SECSID_NULL) */
 	struct sidtab_isid_entry isids[SECINITSID_NUM];
+
+	/* Hash table for fast reverse context-to-sid lookups. */
+	DECLARE_HASHTABLE(context_to_sid, SIDTAB_HASH_BITS);
 };
 
 int sidtab_init(struct sidtab *s);
@@ -101,6 +105,8 @@ int sidtab_context_to_sid(struct sidtab *s, struct context *context, u32 *sid);
 
 void sidtab_destroy(struct sidtab *s);
 
+int sidtab_hash_stats(struct sidtab *sidtab, char *page);
+
 #endif	/* _SS_SIDTAB_H_ */