selinux: overhaul sidtab to fix bug and improve performance

Before this patch, during a policy reload the sidtab would become frozen
and trying to map a new context to SID would be unable to add a new
entry to sidtab and fail with -ENOMEM.

Such failures are usually propagated into userspace, which has no way of
distignuishing them from actual allocation failures and thus doesn't
handle them gracefully. Such situation can be triggered e.g. by the
following reproducer:

    while true; do load_policy; echo -n .; sleep 0.1; done &
    for (( i = 0; i < 1024; i++ )); do
        runcon -l s0:c$i echo -n x || break
        # or:
        # chcon -l s0:c$i <some_file> || break
    done

This patch overhauls the sidtab so it doesn't need to be frozen during
policy reload, thus solving the above problem.

The new SID table leverages the fact that SIDs are allocated
sequentially and are never invalidated and stores them in linear buckets
indexed by a tree structure. This brings several advantages:
  1. Fast SID -> context lookup - this lookup can now be done in
     logarithmic time complexity (usually in less than 4 array lookups)
     and can still be done safely without locking.
  2. No need to re-search the whole table on reverse lookup miss - after
     acquiring the spinlock only the newly added entries need to be
     searched, which means that reverse lookups that end up inserting a
     new entry are now about twice as fast.
  3. No need to freeze sidtab during policy reload - it is now possible
     to handle insertion of new entries even during sidtab conversion.

The tree structure of the new sidtab is able to grow automatically to up
to about 2^31 entries (at which point it should not have more than about
4 tree levels). The old sidtab had a theoretical capacity of almost 2^32
entries, but half of that is still more than enough since by that point
the reverse table lookups would become unusably slow anyway...

The number of entries per tree node is selected automatically so that
each node fits into a single page, which should be the easiest size for
kmalloc() to handle.

Note that the cache for reverse lookup is preserved with equivalent
logic. The only difference is that instead of storing pointers to the
hash table nodes it stores just the indices of the cached entries.

The new cache ensures that the indices are loaded/stored atomically, but
it still has the drawback that concurrent cache updates may mess up the
contents of the cache. Such situation however only reduces its
effectivity, not the correctness of lookups.

Tested by selinux-testsuite and thoroughly tortured by this simple
stress test:
```
function rand_cat() {
	echo $(( $RANDOM % 1024 ))
}

function do_work() {
	while true; do
		echo -n "system_u:system_r:kernel_t:s0:c$(rand_cat),c$(rand_cat)" \
			>/sys/fs/selinux/context 2>/dev/null || true
	done
}

do_work >/dev/null &
do_work >/dev/null &
do_work >/dev/null &

while load_policy; do echo -n .; sleep 0.1; done

kill %1
kill %2
kill %3
```

Link: https://github.com/SELinuxProject/selinux-kernel/issues/38

Reported-by: Orion Poplawski <orion@nwra.com>
Reported-by: Li Kun <hw.likun@huawei.com>
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Reviewed-by: Stephen Smalley <sds@tycho.nsa.gov>
[PM: most of sidtab.c merged by hand due to conflicts]
[PM: checkpatch fixes in mls.c, services.c, sidtab.c]
Signed-off-by: Paul Moore <paul@paul-moore.com>

1 files changed, 58 insertions, 22 deletions

diff --git a/security/selinux/ss/sidtab.h b/security/selinux/ss/sidtab.h
index e657ae6bf996..bbd5c0d1f3bd 100644
--- a/security/selinux/ss/sidtab.h
+++ b/security/selinux/ss/sidtab.h
@@ -1,41 +1,82 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
- * A security identifier table (sidtab) is a hash table
+ * A security identifier table (sidtab) is a lookup table
  * of security context structures indexed by SID value.
  *
- * Author : Stephen Smalley, <sds@tycho.nsa.gov>
+ * Original author: Stephen Smalley, <sds@tycho.nsa.gov>
+ * Author: Ondrej Mosnacek, <omosnacek@gmail.com>
+ *
+ * Copyright (C) 2018 Red Hat, Inc.
  */
 #ifndef _SS_SIDTAB_H_
 #define _SS_SIDTAB_H_
 
+#include <linux/spinlock_types.h>
+#include <linux/log2.h>
+
 #include "context.h"
 
-struct sidtab_node {
-	u32 sid;		/* security identifier */
-	struct context context;	/* security context structure */
-	struct sidtab_node *next;
+struct sidtab_entry_leaf {
+	struct context context;
+};
+
+struct sidtab_node_inner;
+struct sidtab_node_leaf;
+
+union sidtab_entry_inner {
+	struct sidtab_node_inner *ptr_inner;
+	struct sidtab_node_leaf  *ptr_leaf;
 };
 
-#define SIDTAB_HASH_BITS 7
-#define SIDTAB_HASH_BUCKETS (1 << SIDTAB_HASH_BITS)
-#define SIDTAB_HASH_MASK (SIDTAB_HASH_BUCKETS-1)
+/* align node size to page boundary */
+#define SIDTAB_NODE_ALLOC_SHIFT PAGE_SHIFT
+#define SIDTAB_NODE_ALLOC_SIZE  PAGE_SIZE
+
+#define size_to_shift(size) ((size) == 1 ? 1 : (const_ilog2((size) - 1) + 1))
+
+#define SIDTAB_INNER_SHIFT \
+	(SIDTAB_NODE_ALLOC_SHIFT - size_to_shift(sizeof(union sidtab_entry_inner)))
+#define SIDTAB_INNER_ENTRIES ((size_t)1 << SIDTAB_INNER_SHIFT)
+#define SIDTAB_LEAF_ENTRIES \
+	(SIDTAB_NODE_ALLOC_SIZE / sizeof(struct sidtab_entry_leaf))
 
-#define SIDTAB_SIZE SIDTAB_HASH_BUCKETS
+#define SIDTAB_MAX_BITS 31 /* limited to INT_MAX due to atomic_t range */
+#define SIDTAB_MAX (((u32)1 << SIDTAB_MAX_BITS) - 1)
+/* ensure enough tree levels for SIDTAB_MAX entries */
+#define SIDTAB_MAX_LEVEL \
+	DIV_ROUND_UP(SIDTAB_MAX_BITS - size_to_shift(SIDTAB_LEAF_ENTRIES), \
+		     SIDTAB_INNER_SHIFT)
+
+struct sidtab_node_leaf {
+	struct sidtab_entry_leaf entries[SIDTAB_LEAF_ENTRIES];
+};
+
+struct sidtab_node_inner {
+	union sidtab_entry_inner entries[SIDTAB_INNER_ENTRIES];
+};
 
 struct sidtab_isid_entry {
 	int set;
 	struct context context;
 };
 
+struct sidtab_convert_params {
+	int (*func)(struct context *oldc, struct context *newc, void *args);
+	void *args;
+	struct sidtab *target;
+};
+
+#define SIDTAB_RCACHE_SIZE 3
+
 struct sidtab {
-	struct sidtab_node **htable;
-	unsigned int nel;	/* number of elements */
-	unsigned int next_sid;	/* next SID to allocate */
-	unsigned char shutdown;
-#define SIDTAB_CACHE_LEN	3
-	struct sidtab_node *cache[SIDTAB_CACHE_LEN];
+	union sidtab_entry_inner roots[SIDTAB_MAX_LEVEL + 1];
+	atomic_t count;
+	struct sidtab_convert_params *convert;
 	spinlock_t lock;
 
+	/* reverse lookup cache */
+	atomic_t rcache[SIDTAB_RCACHE_SIZE];
+
 	/* index == SID - 1 (no entry for SECSID_NULL) */
 	struct sidtab_isid_entry isids[SECINITSID_NUM];
 };
@@ -45,15 +86,10 @@ int sidtab_set_initial(struct sidtab *s, u32 sid, struct context *context);
 struct context *sidtab_search(struct sidtab *s, u32 sid);
 struct context *sidtab_search_force(struct sidtab *s, u32 sid);
 
-int sidtab_convert(struct sidtab *s, struct sidtab *news,
-		   int (*apply)(u32 sid,
-				struct context *context,
-				void *args),
-		   void *args);
+int sidtab_convert(struct sidtab *s, struct sidtab_convert_params *params);
 
 int sidtab_context_to_sid(struct sidtab *s, struct context *context, u32 *sid);
 
-void sidtab_hash_eval(struct sidtab *h, char *tag);
 void sidtab_destroy(struct sidtab *s);
 
 #endif	/* _SS_SIDTAB_H_ */