Merge tag 'random-6.1-rc1-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/crng/random

Pull more random number generator updates from Jason Donenfeld:
 "This time with some large scale treewide cleanups.

  The intent of this pull is to clean up the way callers fetch random
  integers. The current rules for doing this right are:

   - If you want a secure or an insecure random u64, use get_random_u64()

   - If you want a secure or an insecure random u32, use get_random_u32()

     The old function prandom_u32() has been deprecated for a while
     now and is just a wrapper around get_random_u32(). Same for
     get_random_int().

   - If you want a secure or an insecure random u16, use get_random_u16()

   - If you want a secure or an insecure random u8, use get_random_u8()

   - If you want secure or insecure random bytes, use get_random_bytes().

     The old function prandom_bytes() has been deprecated for a while
     now and has long been a wrapper around get_random_bytes()

   - If you want a non-uniform random u32, u16, or u8 bounded by a
     certain open interval maximum, use prandom_u32_max()

     I say "non-uniform", because it doesn't do any rejection sampling
     or divisions. Hence, it stays within the prandom_*() namespace, not
     the get_random_*() namespace.

     I'm currently investigating a "uniform" function for 6.2. We'll see
     what comes of that.

  By applying these rules uniformly, we get several benefits:

   - By using prandom_u32_max() with an upper-bound that the compiler
     can prove at compile-time is ≤65536 or ≤256, internally
     get_random_u16() or get_random_u8() is used, which wastes fewer
     batched random bytes, and hence has higher throughput.

   - By using prandom_u32_max() instead of %, when the upper-bound is
     not a constant, division is still avoided, because
     prandom_u32_max() uses a faster multiplication-based trick instead.

   - By using get_random_u16() or get_random_u8() in cases where the
     return value is intended to indeed be a u16 or a u8, we waste fewer
     batched random bytes, and hence have higher throughput.

  This series was originally done by hand while I was on an airplane
  without Internet. Later, Kees and I worked on retroactively figuring
  out what could be done with Coccinelle and what had to be done
  manually, and then we split things up based on that.

  So while this touches a lot of files, the actual amount of code that's
  hand fiddled is comfortably small"

* tag 'random-6.1-rc1-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/crng/random:
  prandom: remove unused functions
  treewide: use get_random_bytes() when possible
  treewide: use get_random_u32() when possible
  treewide: use get_random_{u8,u16}() when possible, part 2
  treewide: use get_random_{u8,u16}() when possible, part 1
  treewide: use prandom_u32_max() when possible, part 2
  treewide: use prandom_u32_max() when possible, part 1

3 files changed, 25 insertions, 26 deletions

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index e93edb810103..3c4786b99907 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -111,7 +111,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh)
 
 unsigned long neigh_rand_reach_time(unsigned long base)
 {
-	return base ? (prandom_u32() % base) + (base >> 1) : 0;
+	return base ? prandom_u32_max(base) + (base >> 1) : 0;
 }
 EXPORT_SYMBOL(neigh_rand_reach_time);
 
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 88906ba6d9a7..c3763056c554 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2324,7 +2324,7 @@ static inline int f_pick(struct pktgen_dev *pkt_dev)
 				pkt_dev->curfl = 0; /*reset */
 		}
 	} else {
-		flow = prandom_u32() % pkt_dev->cflows;
+		flow = prandom_u32_max(pkt_dev->cflows);
 		pkt_dev->curfl = flow;
 
 		if (pkt_dev->flows[flow].count > pkt_dev->lflow) {
@@ -2380,10 +2380,9 @@ static void set_cur_queue_map(struct pktgen_dev *pkt_dev)
 	else if (pkt_dev->queue_map_min <= pkt_dev->queue_map_max) {
 		__u16 t;
 		if (pkt_dev->flags & F_QUEUE_MAP_RND) {
-			t = prandom_u32() %
-				(pkt_dev->queue_map_max -
-				 pkt_dev->queue_map_min + 1)
-				+ pkt_dev->queue_map_min;
+			t = prandom_u32_max(pkt_dev->queue_map_max -
+					    pkt_dev->queue_map_min + 1) +
+			    pkt_dev->queue_map_min;
 		} else {
 			t = pkt_dev->cur_queue_map + 1;
 			if (t > pkt_dev->queue_map_max)
@@ -2412,7 +2411,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
 		__u32 tmp;
 
 		if (pkt_dev->flags & F_MACSRC_RND)
-			mc = prandom_u32() % pkt_dev->src_mac_count;
+			mc = prandom_u32_max(pkt_dev->src_mac_count);
 		else {
 			mc = pkt_dev->cur_src_mac_offset++;
 			if (pkt_dev->cur_src_mac_offset >=
@@ -2438,7 +2437,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
 		__u32 tmp;
 
 		if (pkt_dev->flags & F_MACDST_RND)
-			mc = prandom_u32() % pkt_dev->dst_mac_count;
+			mc = prandom_u32_max(pkt_dev->dst_mac_count);
 
 		else {
 			mc = pkt_dev->cur_dst_mac_offset++;
@@ -2465,23 +2464,23 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
 		for (i = 0; i < pkt_dev->nr_labels; i++)
 			if (pkt_dev->labels[i] & MPLS_STACK_BOTTOM)
 				pkt_dev->labels[i] = MPLS_STACK_BOTTOM |
-					     ((__force __be32)prandom_u32() &
+					     ((__force __be32)get_random_u32() &
 						      htonl(0x000fffff));
 	}
 
 	if ((pkt_dev->flags & F_VID_RND) && (pkt_dev->vlan_id != 0xffff)) {
-		pkt_dev->vlan_id = prandom_u32() & (4096 - 1);
+		pkt_dev->vlan_id = prandom_u32_max(4096);
 	}
 
 	if ((pkt_dev->flags & F_SVID_RND) && (pkt_dev->svlan_id != 0xffff)) {
-		pkt_dev->svlan_id = prandom_u32() & (4096 - 1);
+		pkt_dev->svlan_id = prandom_u32_max(4096);
 	}
 
 	if (pkt_dev->udp_src_min < pkt_dev->udp_src_max) {
 		if (pkt_dev->flags & F_UDPSRC_RND)
-			pkt_dev->cur_udp_src = prandom_u32() %
-				(pkt_dev->udp_src_max - pkt_dev->udp_src_min)
-				+ pkt_dev->udp_src_min;
+			pkt_dev->cur_udp_src = prandom_u32_max(
+				pkt_dev->udp_src_max - pkt_dev->udp_src_min) +
+				pkt_dev->udp_src_min;
 
 		else {
 			pkt_dev->cur_udp_src++;
@@ -2492,9 +2491,9 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
 
 	if (pkt_dev->udp_dst_min < pkt_dev->udp_dst_max) {
 		if (pkt_dev->flags & F_UDPDST_RND) {
-			pkt_dev->cur_udp_dst = prandom_u32() %
-				(pkt_dev->udp_dst_max - pkt_dev->udp_dst_min)
-				+ pkt_dev->udp_dst_min;
+			pkt_dev->cur_udp_dst = prandom_u32_max(
+				pkt_dev->udp_dst_max - pkt_dev->udp_dst_min) +
+				pkt_dev->udp_dst_min;
 		} else {
 			pkt_dev->cur_udp_dst++;
 			if (pkt_dev->cur_udp_dst >= pkt_dev->udp_dst_max)
@@ -2509,7 +2508,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
 		if (imn < imx) {
 			__u32 t;
 			if (pkt_dev->flags & F_IPSRC_RND)
-				t = prandom_u32() % (imx - imn) + imn;
+				t = prandom_u32_max(imx - imn) + imn;
 			else {
 				t = ntohl(pkt_dev->cur_saddr);
 				t++;
@@ -2531,8 +2530,8 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
 				if (pkt_dev->flags & F_IPDST_RND) {
 
 					do {
-						t = prandom_u32() %
-							(imx - imn) + imn;
+						t = prandom_u32_max(imx - imn) +
+						    imn;
 						s = htonl(t);
 					} while (ipv4_is_loopback(s) ||
 						ipv4_is_multicast(s) ||
@@ -2569,7 +2568,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
 
 			for (i = 0; i < 4; i++) {
 				pkt_dev->cur_in6_daddr.s6_addr32[i] =
-				    (((__force __be32)prandom_u32() |
+				    (((__force __be32)get_random_u32() |
 				      pkt_dev->min_in6_daddr.s6_addr32[i]) &
 				     pkt_dev->max_in6_daddr.s6_addr32[i]);
 			}
@@ -2579,9 +2578,9 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
 	if (pkt_dev->min_pkt_size < pkt_dev->max_pkt_size) {
 		__u32 t;
 		if (pkt_dev->flags & F_TXSIZE_RND) {
-			t = prandom_u32() %
-				(pkt_dev->max_pkt_size - pkt_dev->min_pkt_size)
-				+ pkt_dev->min_pkt_size;
+			t = prandom_u32_max(pkt_dev->max_pkt_size -
+					    pkt_dev->min_pkt_size) +
+			    pkt_dev->min_pkt_size;
 		} else {
 			t = pkt_dev->cur_pkt_size + 1;
 			if (t > pkt_dev->max_pkt_size)
@@ -2590,7 +2589,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
 		pkt_dev->cur_pkt_size = t;
 	} else if (pkt_dev->n_imix_entries > 0) {
 		struct imix_pkt *entry;
-		__u32 t = prandom_u32() % IMIX_PRECISION;
+		__u32 t = prandom_u32_max(IMIX_PRECISION);
 		__u8 entry_index = pkt_dev->imix_distribution[t];
 
 		entry = &pkt_dev->imix_entries[entry_index];
diff --git a/net/core/stream.c b/net/core/stream.c
index 1105057ce00a..75fded8495f5 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -123,7 +123,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
 	if (sk_stream_memory_free(sk))
-		current_timeo = vm_wait = (prandom_u32() % (HZ / 5)) + 2;
+		current_timeo = vm_wait = prandom_u32_max(HZ / 5) + 2;
 
 	add_wait_queue(sk_sleep(sk), &wait);