treewide: use prandom_u32_max() when possible, part 1

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 mechanically with this coccinelle script:

@basic@
expression E;
type T;
identifier get_random_u32 =~ "get_random_int|prandom_u32|get_random_u32";
typedef u64;
@@
(
- ((T)get_random_u32() % (E))
+ prandom_u32_max(E)
|
- ((T)get_random_u32() & ((E) - 1))
+ prandom_u32_max(E * XXX_MAKE_SURE_E_IS_POW2)
|
- ((u64)(E) * get_random_u32() >> 32)
+ prandom_u32_max(E)
|
- ((T)get_random_u32() & ~PAGE_MASK)
+ prandom_u32_max(PAGE_SIZE)
)

@multi_line@
identifier get_random_u32 =~ "get_random_int|prandom_u32|get_random_u32";
identifier RAND;
expression E;
@@

-       RAND = get_random_u32();
        ... when != RAND
-       RAND %= (E);
+       RAND = prandom_u32_max(E);

// Find a potential literal
@literal_mask@
expression LITERAL;
type T;
identifier get_random_u32 =~ "get_random_int|prandom_u32|get_random_u32";
position p;
@@

        ((T)get_random_u32()@p & (LITERAL))

// Add one to the literal.
@script:python add_one@
literal << literal_mask.LITERAL;
RESULT;
@@

value = None
if literal.startswith('0x'):
        value = int(literal, 16)
elif literal[0] in '123456789':
        value = int(literal, 10)
if value is None:
        print("I don't know how to handle %s" % (literal))
        cocci.include_match(False)
elif value == 2**32 - 1 or value == 2**31 - 1 or value == 2**24 - 1 or value == 2**16 - 1 or value == 2**8 - 1:
        print("Skipping 0x%x for cleanup elsewhere" % (value))
        cocci.include_match(False)
elif value & (value + 1) != 0:
        print("Skipping 0x%x because it's not a power of two minus one" % (value))
        cocci.include_match(False)
elif literal.startswith('0x'):
        coccinelle.RESULT = cocci.make_expr("0x%x" % (value + 1))
else:
        coccinelle.RESULT = cocci.make_expr("%d" % (value + 1))

// Replace the literal mask with the calculated result.
@plus_one@
expression literal_mask.LITERAL;
position literal_mask.p;
expression add_one.RESULT;
identifier FUNC;
@@

-       (FUNC()@p & (LITERAL))
+       prandom_u32_max(RESULT)

@collapse_ret@
type T;
identifier VAR;
expression E;
@@

 {
-       T VAR;
-       VAR = (E);
-       return VAR;
+       return E;
 }

@drop_var@
type T;
identifier VAR;
@@

 {
-       T VAR;
        ... when != VAR
 }

Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Yury Norov <yury.norov@gmail.com>
Reviewed-by: KP Singh <kpsingh@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz> # for ext4 and sbitmap
Reviewed-by: Christoph Böhmwalder <christoph.boehmwalder@linbit.com> # for drbd
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Heiko Carstens <hca@linux.ibm.com> # for s390
Acked-by: Ulf Hansson <ulf.hansson@linaro.org> # for mmc
Acked-by: Darrick J. Wong <djwong@kernel.org> # for xfs
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

kernel/bpf/core.c

@@ -1032,7 +1032,7 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
 	hdr->size = size;
 	hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
 		     PAGE_SIZE - sizeof(*hdr));
-	start = (get_random_int() % hole) & ~(alignment - 1);
+	start = prandom_u32_max(hole) & ~(alignment - 1);
 
 	/* Leave a random number of instructions before BPF code. */
 	*image_ptr = &hdr->image[start];
@@ -1094,7 +1094,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr,
 
 	hole = min_t(unsigned int, size - (proglen + sizeof(*ro_header)),
 		     BPF_PROG_CHUNK_SIZE - sizeof(*ro_header));
-	start = (get_random_int() % hole) & ~(alignment - 1);
+	start = prandom_u32_max(hole) & ~(alignment - 1);
 
 	*image_ptr = &ro_header->image[start];
 	*rw_image = &(*rw_header)->image[start];

kernel/locking/test-ww_mutex.c

@@ -399,7 +399,7 @@ static int *get_random_order(int count)
 		order[n] = n;
 
 	for (n = count - 1; n > 1; n--) {
-		r = get_random_int() % (n + 1);
+		r = prandom_u32_max(n + 1);
 		if (r != n) {
 			tmp = order[n];
 			order[n] = order[r];
@@ -538,7 +538,7 @@ static void stress_one_work(struct work_struct *work)
 {
 	struct stress *stress = container_of(work, typeof(*stress), work);
 	const int nlocks = stress->nlocks;
-	struct ww_mutex *lock = stress->locks + (get_random_int() % nlocks);
+	struct ww_mutex *lock = stress->locks + prandom_u32_max(nlocks);
 	int err;
 
 	do {

kernel/time/clocksource.c

@@ -310,7 +310,7 @@ static void clocksource_verify_choose_cpus(void)
 	 * CPUs that are currently online.
 	 */
 	for (i = 1; i < n; i++) {
-		cpu = prandom_u32() % nr_cpu_ids;
+		cpu = prandom_u32_max(nr_cpu_ids);
 		cpu = cpumask_next(cpu - 1, cpu_online_mask);
 		if (cpu >= nr_cpu_ids)
 			cpu = cpumask_first(cpu_online_mask);