treewide: use prandom_u32_max() when possible, part 2

Rather than incurring a division or requesting too many random bytes for
the given range, use the prandom_u32_max() function, which only takes
the minimum required bytes from the RNG and avoids divisions. This was
done by hand, covering things that coccinelle could not do on its own.
Reviewed-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: NKees Cook <keescook@chromium.org>
Reviewed-by: NYury Norov <yury.norov@gmail.com>
Reviewed-by: Jan Kara <jack@suse.cz> # for ext2, ext4, and sbitmap
Acked-by: NJakub Kicinski <kuba@kernel.org>
Signed-off-by: NJason A. Donenfeld <Jason@zx2c4.com>

fs/ext2/ialloc.c

@@ -277,8 +277,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
 		int best_ndir = inodes_per_group;
 		int best_group = -1;
 
-		group = prandom_u32();
-		parent_group = (unsigned)group % ngroups;
+		parent_group = prandom_u32_max(ngroups);
 		for (i = 0; i < ngroups; i++) {
 			group = (parent_group + i) % ngroups;
 			desc = ext2_get_group_desc (sb, group, NULL);

fs/ext4/ialloc.c

@@ -463,10 +463,9 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 			hinfo.hash_version = DX_HASH_HALF_MD4;
 			hinfo.seed = sbi->s_hash_seed;
 			ext4fs_dirhash(parent, qstr->name, qstr->len, &hinfo);
-			grp = hinfo.hash;
+			parent_group = hinfo.hash % ngroups;
 		} else
-			grp = prandom_u32();
-		parent_group = (unsigned)grp % ngroups;
+			parent_group = prandom_u32_max(ngroups);
 		for (i = 0; i < ngroups; i++) {
 			g = (parent_group + i) % ngroups;
 			get_orlov_stats(sb, g, flex_size, &stats);

lib/sbitmap.c

@@ -21,7 +21,7 @@ static int init_alloc_hint(struct sbitmap *sb, gfp_t flags)
 		int i;
 
 		for_each_possible_cpu(i)
-			*per_cpu_ptr(sb->alloc_hint, i) = prandom_u32() % depth;
+			*per_cpu_ptr(sb->alloc_hint, i) = prandom_u32_max(depth);
 	}
 	return 0;
 }

lib/test_vmalloc.c

@@ -151,9 +151,7 @@ static int random_size_alloc_test(void)
 	int i;
 
 	for (i = 0; i < test_loop_count; i++) {
-		n = prandom_u32();
-		n = (n % 100) + 1;
-
+		n = prandom_u32_max(100) + 1;
 		p = vmalloc(n * PAGE_SIZE);
 
 		if (!p)
@@ -293,16 +291,12 @@ pcpu_alloc_test(void)
 		return -1;
 
 	for (i = 0; i < 35000; i++) {
-		unsigned int r;
-
-		r = prandom_u32();
-		size = (r % (PAGE_SIZE / 4)) + 1;
+		size = prandom_u32_max(PAGE_SIZE / 4) + 1;
 
 		/*
 		 * Maximum PAGE_SIZE
 		 */
-		r = prandom_u32();
-		align = 1 << ((r % 11) + 1);
+		align = 1 << (prandom_u32_max(11) + 1);
 
 		pcpu[i] = __alloc_percpu(size, align);
 		if (!pcpu[i])
@@ -393,14 +387,11 @@ static struct test_driver {
 
 static void shuffle_array(int *arr, int n)
 {
-	unsigned int rnd;
 	int i, j;
 
 	for (i = n - 1; i > 0; i--)  {
-		rnd = prandom_u32();
-
 		/* Cut the range. */
-		j = rnd % i;
+		j = prandom_u32_max(i);
 
 		/* Swap indexes. */
 		swap(arr[i], arr[j]);