SELinux: improve performance when AVC misses.

* We add ebitmap_for_each_positive_bit() which enables to walk on
  any positive bit on the given ebitmap, to improve its performance
  using common bit-operations defined in linux/bitops.h.
  In the previous version, this logic was implemented using a combination
  of ebitmap_for_each_bit() and ebitmap_node_get_bit(), but is was worse
  in performance aspect.
  This logic is most frequestly used to compute a new AVC entry,
  so this patch can improve SELinux performance when AVC misses are happen.
* struct ebitmap_node is redefined as an array of "unsigned long", to get
  suitable for using find_next_bit() which is fasted than iteration of
  shift and logical operation, and to maximize memory usage allocated
  from general purpose slab.
* Any ebitmap_for_each_bit() are repleced by the new implementation
  in ss/service.c and ss/mls.c. Some of related implementation are
  changed, however, there is no incompatibility with the previous
  version.
* The width of any new line are less or equal than 80-chars.

The following benchmark shows the effect of this patch, when we
access many files which have different security context one after
another. The number is more than /selinux/avc/cache_threshold, so
any access always causes AVC misses.

      selinux-2.6      selinux-2.6-ebitmap
AVG:   22.763 [s]          8.750 [s]
STD:    0.265              0.019
------------------------------------------
1st:   22.558 [s]          8.786 [s]
2nd:   22.458 [s]          8.750 [s]
3rd:   22.478 [s]          8.754 [s]
4th:   22.724 [s]          8.745 [s]
5th:   22.918 [s]          8.748 [s]
6th:   22.905 [s]          8.764 [s]
7th:   23.238 [s]          8.726 [s]
8th:   22.822 [s]          8.729 [s]
Signed-off-by: KaiGai Kohei <kaigai@ak.jp.nec.com>
Acked-by: Stephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: James Morris <jmorris@namei.org>

security/selinux/ss/ebitmap.h

@@ -16,14 +16,16 @@
 
 #include <net/netlabel.h>
 
-#define MAPTYPE u64			/* portion of bitmap in each node */
-#define MAPSIZE (sizeof(MAPTYPE) * 8)	/* number of bits in node bitmap */
-#define MAPBIT  1ULL			/* a bit in the node bitmap */
+#define EBITMAP_UNIT_NUMS	((32 - sizeof(void *) - sizeof(u32))	\
+					/ sizeof(unsigned long))
+#define EBITMAP_UNIT_SIZE	BITS_PER_LONG
+#define EBITMAP_SIZE		(EBITMAP_UNIT_NUMS * EBITMAP_UNIT_SIZE)
+#define EBITMAP_BIT		1ULL
 
 struct ebitmap_node {
-	u32 startbit;		/* starting position in the total bitmap */
-	MAPTYPE map;		/* this node's portion of the bitmap */
 	struct ebitmap_node *next;
+	unsigned long maps[EBITMAP_UNIT_NUMS];
+	u32 startbit;
 };
 
 struct ebitmap {
@@ -34,11 +36,17 @@ struct ebitmap {
 #define ebitmap_length(e) ((e)->highbit)
 #define ebitmap_startbit(e) ((e)->node ? (e)->node->startbit : 0)
 
-static inline unsigned int ebitmap_start(struct ebitmap *e,
+static inline unsigned int ebitmap_start_positive(struct ebitmap *e,
 						  struct ebitmap_node **n)
 {
-	*n = e->node;
-	return ebitmap_startbit(e);
+	unsigned int ofs;
+
+	for (*n = e->node; *n; *n = (*n)->next) {
+		ofs = find_first_bit((*n)->maps, EBITMAP_SIZE);
+		if (ofs < EBITMAP_SIZE)
+			return (*n)->startbit + ofs;
+	}
+	return ebitmap_length(e);
 }
 
 static inline void ebitmap_init(struct ebitmap *e)
@@ -46,28 +54,65 @@ static inline void ebitmap_init(struct ebitmap *e)
 	memset(e, 0, sizeof(*e));
 }
 
-static inline unsigned int ebitmap_next(struct ebitmap_node **n,
+static inline unsigned int ebitmap_next_positive(struct ebitmap *e,
+						 struct ebitmap_node **n,
 						 unsigned int bit)
 {
-	if ((bit == ((*n)->startbit + MAPSIZE - 1)) &&
-	    (*n)->next) {
-		*n = (*n)->next;
-		return (*n)->startbit;
-	}
+	unsigned int ofs;
 
-	return (bit+1);
+	ofs = find_next_bit((*n)->maps, EBITMAP_SIZE, bit - (*n)->startbit + 1);
+	if (ofs < EBITMAP_SIZE)
+		return ofs + (*n)->startbit;
+
+	for (*n = (*n)->next; *n; *n = (*n)->next) {
+		ofs = find_first_bit((*n)->maps, EBITMAP_SIZE);
+		if (ofs < EBITMAP_SIZE)
+			return ofs + (*n)->startbit;
+	}
+	return ebitmap_length(e);
 }
 
-static inline int ebitmap_node_get_bit(struct ebitmap_node * n,
+#define EBITMAP_NODE_INDEX(node, bit)	\
+	(((bit) - (node)->startbit) / EBITMAP_UNIT_SIZE)
+#define EBITMAP_NODE_OFFSET(node, bit)	\
+	(((bit) - (node)->startbit) % EBITMAP_UNIT_SIZE)
+
+static inline int ebitmap_node_get_bit(struct ebitmap_node *n,
 				       unsigned int bit)
 {
-	if (n->map & (MAPBIT << (bit - n->startbit)))
+	unsigned int index = EBITMAP_NODE_INDEX(n, bit);
+	unsigned int ofs = EBITMAP_NODE_OFFSET(n, bit);
+
+	BUG_ON(index >= EBITMAP_UNIT_NUMS);
+	if ((n->maps[index] & (EBITMAP_BIT << ofs)))
 		return 1;
 	return 0;
 }
 
-#define ebitmap_for_each_bit(e, n, bit) \
-	for (bit = ebitmap_start(e, &n); bit < ebitmap_length(e); bit = ebitmap_next(&n, bit)) \
+static inline void ebitmap_node_set_bit(struct ebitmap_node *n,
+					unsigned int bit)
+{
+	unsigned int index = EBITMAP_NODE_INDEX(n, bit);
+	unsigned int ofs = EBITMAP_NODE_OFFSET(n, bit);
+
+	BUG_ON(index >= EBITMAP_UNIT_NUMS);
+	n->maps[index] |= (EBITMAP_BIT << ofs);
+}
+
+static inline void ebitmap_node_clr_bit(struct ebitmap_node *n,
+					unsigned int bit)
+{
+	unsigned int index = EBITMAP_NODE_INDEX(n, bit);
+	unsigned int ofs = EBITMAP_NODE_OFFSET(n, bit);
+
+	BUG_ON(index >= EBITMAP_UNIT_NUMS);
+	n->maps[index] &= ~(EBITMAP_BIT << ofs);
+}
+
+#define ebitmap_for_each_positive_bit(e, n, bit)	\
+	for (bit = ebitmap_start_positive(e, &n);	\
+	     bit < ebitmap_length(e);			\
+	     bit = ebitmap_next_positive(e, &n, bit))	\
 
 int ebitmap_cmp(struct ebitmap *e1, struct ebitmap *e2);
 int ebitmap_cpy(struct ebitmap *dst, struct ebitmap *src);

security/selinux/ss/mls.c

@@ -34,7 +34,9 @@
  */
 int mls_compute_context_len(struct context * context)
 {
-	int i, l, len, range;
+	int i, l, len, head, prev;
+	char *nm;
+	struct ebitmap *e;
 	struct ebitmap_node *node;
 
 	if (!selinux_mls_enabled)
@@ -42,28 +44,30 @@ int mls_compute_context_len(struct context * context)
 
 	len = 1; /* for the beginning ":" */
 	for (l = 0; l < 2; l++) {
-		range = 0;
-		len += strlen(policydb.p_sens_val_to_name[context->range.level[l].sens - 1]);
+		int index_sens = context->range.level[l].sens;
+		len += strlen(policydb.p_sens_val_to_name[index_sens - 1]);
 
-		ebitmap_for_each_bit(&context->range.level[l].cat, node, i) {
-			if (ebitmap_node_get_bit(node, i)) {
-				if (range) {
-					range++;
-					continue;
-				}
-
-				len += strlen(policydb.p_cat_val_to_name[i]) + 1;
-				range++;
-			} else {
-				if (range > 1)
-					len += strlen(policydb.p_cat_val_to_name[i - 1]) + 1;
-				range = 0;
-			}
+		/* categories */
+		head = -2;
+		prev = -2;
+		e = &context->range.level[l].cat;
+		ebitmap_for_each_positive_bit(e, node, i) {
+			if (i - prev > 1) {
+				/* one or more negative bits are skipped */
+				if (head != prev) {
+					nm = policydb.p_cat_val_to_name[prev];
+					len += strlen(nm) + 1;
+				}
+				nm = policydb.p_cat_val_to_name[i];
+				len += strlen(nm) + 1;
+				head = i;
+			}
+			prev = i;
+		}
+		if (prev != head) {
+			nm = policydb.p_cat_val_to_name[prev];
+			len += strlen(nm) + 1;
 		}
-		/* Handle case where last category is the end of range */
-		if (range > 1)
-			len += strlen(policydb.p_cat_val_to_name[i - 1]) + 1;
-
 		if (l == 0) {
 			if (mls_level_eq(&context->range.level[0],
 					 &context->range.level[1]))
@@ -84,8 +88,9 @@ int mls_compute_context_len(struct context * context)
 void mls_sid_to_context(struct context *context,
                         char **scontext)
 {
-	char *scontextp;
-	int i, l, range, wrote_sep;
+	char *scontextp, *nm;
+	int i, l, head, prev;
+	struct ebitmap *e;
 	struct ebitmap_node *node;
 
 	if (!selinux_mls_enabled)
@@ -97,61 +102,54 @@ void mls_sid_to_context(struct context *context,
 	scontextp++;
 
 	for (l = 0; l < 2; l++) {
-		range = 0;
-		wrote_sep = 0;
 		strcpy(scontextp,
 		       policydb.p_sens_val_to_name[context->range.level[l].sens - 1]);
-		scontextp += strlen(policydb.p_sens_val_to_name[context->range.level[l].sens - 1]);
+		scontextp += strlen(scontextp);
 
 		/* categories */
-		ebitmap_for_each_bit(&context->range.level[l].cat, node, i) {
-			if (ebitmap_node_get_bit(node, i)) {
-				if (range) {
-					range++;
-					continue;
-				}
-
-				if (!wrote_sep) {
-					*scontextp++ = ':';
-					wrote_sep = 1;
-				} else
-					*scontextp++ = ',';
-				strcpy(scontextp, policydb.p_cat_val_to_name[i]);
-				scontextp += strlen(policydb.p_cat_val_to_name[i]);
-				range++;
-			} else {
-				if (range > 1) {
-					if (range > 2)
+		head = -2;
+		prev = -2;
+		e = &context->range.level[l].cat;
+		ebitmap_for_each_positive_bit(e, node, i) {
+			if (i - prev > 1) {
+				/* one or more negative bits are skipped */
+				if (prev != head) {
+					if (prev - head > 1)
 						*scontextp++ = '.';
 					else
 						*scontextp++ = ',';
-
-					strcpy(scontextp, policydb.p_cat_val_to_name[i - 1]);
-					scontextp += strlen(policydb.p_cat_val_to_name[i - 1]);
+					nm = policydb.p_cat_val_to_name[prev];
+					strcpy(scontextp, nm);
+					scontextp += strlen(nm);
 				}
-				range = 0;
+				if (prev < 0)
+					*scontextp++ = ':';
+				else
+					*scontextp++ = ',';
+				nm = policydb.p_cat_val_to_name[i];
+				strcpy(scontextp, nm);
+				scontextp += strlen(nm);
+				head = i;
 			}
+			prev = i;
 		}
 
-		/* Handle case where last category is the end of range */
-		if (range > 1) {
-			if (range > 2)
+		if (prev != head) {
+			if (prev - head > 1)
 				*scontextp++ = '.';
 			else
 				*scontextp++ = ',';
-
-			strcpy(scontextp, policydb.p_cat_val_to_name[i - 1]);
-			scontextp += strlen(policydb.p_cat_val_to_name[i - 1]);
+			nm = policydb.p_cat_val_to_name[prev];
+			strcpy(scontextp, nm);
+			scontextp += strlen(nm);
 		}
 
 		if (l == 0) {
 			if (mls_level_eq(&context->range.level[0],
 			                 &context->range.level[1]))
 				break;
-			else {
-				*scontextp = '-';
-				scontextp++;
-			}
+			else
+				*scontextp++ = '-';
 		}
 	}
 
@@ -190,8 +188,7 @@ int mls_context_isvalid(struct policydb *p, struct context *c)
 		if (!levdatum)
 			return 0;
 
-		ebitmap_for_each_bit(&c->range.level[l].cat, node, i) {
-			if (ebitmap_node_get_bit(node, i)) {
+		ebitmap_for_each_positive_bit(&c->range.level[l].cat, node, i) {
 			if (i > p->p_cats.nprim)
 				return 0;
 			if (!ebitmap_get_bit(&levdatum->level->cat, i))
@@ -202,7 +199,6 @@ int mls_context_isvalid(struct policydb *p, struct context *c)
 				return 0;
 		}
 	}
-	}
 
 	if (c->role == OBJECT_R_VAL)
 		return 1;
@@ -485,8 +481,7 @@ int mls_convert_context(struct policydb *oldp,
 		c->range.level[l].sens = levdatum->level->sens;
 
 		ebitmap_init(&bitmap);
-		ebitmap_for_each_bit(&c->range.level[l].cat, node, i) {
-			if (ebitmap_node_get_bit(node, i)) {
+		ebitmap_for_each_positive_bit(&c->range.level[l].cat, node, i) {
 			int rc;
 
 			catdatum = hashtab_search(newp->p_cats.table,
@@ -497,7 +492,6 @@ int mls_convert_context(struct policydb *oldp,
 			if (rc)
 				return rc;
 		}
-		}
 		ebitmap_destroy(&c->range.level[l].cat);
 		c->range.level[l].cat = bitmap;
 	}

security/selinux/ss/services.c

@@ -353,12 +353,8 @@ static int context_struct_compute_av(struct context *scontext,
 	avkey.specified = AVTAB_AV;
 	sattr = &policydb.type_attr_map[scontext->type - 1];
 	tattr = &policydb.type_attr_map[tcontext->type - 1];
-	ebitmap_for_each_bit(sattr, snode, i) {
-		if (!ebitmap_node_get_bit(snode, i))
-			continue;
-		ebitmap_for_each_bit(tattr, tnode, j) {
-			if (!ebitmap_node_get_bit(tnode, j))
-				continue;
+	ebitmap_for_each_positive_bit(sattr, snode, i) {
+		ebitmap_for_each_positive_bit(tattr, tnode, j) {
 			avkey.source_type = i + 1;
 			avkey.target_type = j + 1;
 			for (node = avtab_search_node(&policydb.te_avtab, &avkey);
@@ -1668,14 +1664,10 @@ int security_get_user_sids(u32 fromsid,
 		goto out_unlock;
 	}
 
-	ebitmap_for_each_bit(&user->roles, rnode, i) {
-		if (!ebitmap_node_get_bit(rnode, i))
-			continue;
+	ebitmap_for_each_positive_bit(&user->roles, rnode, i) {
 		role = policydb.role_val_to_struct[i];
 		usercon.role = i+1;
-		ebitmap_for_each_bit(&role->types, tnode, j) {
-			if (!ebitmap_node_get_bit(tnode, j))
-				continue;
+		ebitmap_for_each_positive_bit(&role->types, tnode, j) {
 			usercon.type = j+1;
 
 			if (mls_setup_user_range(fromcon, user, &usercon))