Merge tag 'random_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/random

Pull random driver updates from Ted Ts'o:
 "A number of improvements for the /dev/random driver; the most
  important is the use of a ChaCha20-based CRNG for /dev/urandom, which
  is faster, more efficient, and easier to make scalable for
  silly/abusive userspace programs that want to read from /dev/urandom
  in a tight loop on NUMA systems.

  This set of patches also improves entropy gathering on VM's running on
  Microsoft Azure, and will take advantage of a hw random number
  generator (if present) to initialize the /dev/urandom pool"

(It turns out that the random tree hadn't been in linux-next this time
around, because it had been dropped earlier as being too quiet.  Oh
well).

* tag 'random_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/random:
  random: strengthen input validation for RNDADDTOENTCNT
  random: add backtracking protection to the CRNG
  random: make /dev/urandom scalable for silly userspace programs
  random: replace non-blocking pool with a Chacha20-based CRNG
  random: properly align get_random_int_hash
  random: add interrupt callback to VMBus IRQ handler
  random: print a warning for the first ten uninitialized random users
  random: initialize the non-blocking pool via add_hwgenerator_randomness()

crypto/chacha20_generic.c

@@ -15,72 +15,11 @@
 #include <linux/module.h>
 #include <crypto/chacha20.h>
 
-static inline u32 rotl32(u32 v, u8 n)
-{
-	return (v << n) | (v >> (sizeof(v) * 8 - n));
-}
-
 static inline u32 le32_to_cpuvp(const void *p)
 {
 	return le32_to_cpup(p);
 }
 
-static void chacha20_block(u32 *state, void *stream)
-{
-	u32 x[16], *out = stream;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(x); i++)
-		x[i] = state[i];
-
-	for (i = 0; i < 20; i += 2) {
-		x[0]  += x[4];    x[12] = rotl32(x[12] ^ x[0],  16);
-		x[1]  += x[5];    x[13] = rotl32(x[13] ^ x[1],  16);
-		x[2]  += x[6];    x[14] = rotl32(x[14] ^ x[2],  16);
-		x[3]  += x[7];    x[15] = rotl32(x[15] ^ x[3],  16);
-
-		x[8]  += x[12];   x[4]  = rotl32(x[4]  ^ x[8],  12);
-		x[9]  += x[13];   x[5]  = rotl32(x[5]  ^ x[9],  12);
-		x[10] += x[14];   x[6]  = rotl32(x[6]  ^ x[10], 12);
-		x[11] += x[15];   x[7]  = rotl32(x[7]  ^ x[11], 12);
-
-		x[0]  += x[4];    x[12] = rotl32(x[12] ^ x[0],   8);
-		x[1]  += x[5];    x[13] = rotl32(x[13] ^ x[1],   8);
-		x[2]  += x[6];    x[14] = rotl32(x[14] ^ x[2],   8);
-		x[3]  += x[7];    x[15] = rotl32(x[15] ^ x[3],   8);
-
-		x[8]  += x[12];   x[4]  = rotl32(x[4]  ^ x[8],   7);
-		x[9]  += x[13];   x[5]  = rotl32(x[5]  ^ x[9],   7);
-		x[10] += x[14];   x[6]  = rotl32(x[6]  ^ x[10],  7);
-		x[11] += x[15];   x[7]  = rotl32(x[7]  ^ x[11],  7);
-
-		x[0]  += x[5];    x[15] = rotl32(x[15] ^ x[0],  16);
-		x[1]  += x[6];    x[12] = rotl32(x[12] ^ x[1],  16);
-		x[2]  += x[7];    x[13] = rotl32(x[13] ^ x[2],  16);
-		x[3]  += x[4];    x[14] = rotl32(x[14] ^ x[3],  16);
-
-		x[10] += x[15];   x[5]  = rotl32(x[5]  ^ x[10], 12);
-		x[11] += x[12];   x[6]  = rotl32(x[6]  ^ x[11], 12);
-		x[8]  += x[13];   x[7]  = rotl32(x[7]  ^ x[8],  12);
-		x[9]  += x[14];   x[4]  = rotl32(x[4]  ^ x[9],  12);
-
-		x[0]  += x[5];    x[15] = rotl32(x[15] ^ x[0],   8);
-		x[1]  += x[6];    x[12] = rotl32(x[12] ^ x[1],   8);
-		x[2]  += x[7];    x[13] = rotl32(x[13] ^ x[2],   8);
-		x[3]  += x[4];    x[14] = rotl32(x[14] ^ x[3],   8);
-
-		x[10] += x[15];   x[5]  = rotl32(x[5]  ^ x[10],  7);
-		x[11] += x[12];   x[6]  = rotl32(x[6]  ^ x[11],  7);
-		x[8]  += x[13];   x[7]  = rotl32(x[7]  ^ x[8],   7);
-		x[9]  += x[14];   x[4]  = rotl32(x[4]  ^ x[9],   7);
-	}
-
-	for (i = 0; i < ARRAY_SIZE(x); i++)
-		out[i] = cpu_to_le32(x[i] + state[i]);
-
-	state[12]++;
-}
-
 static void chacha20_docrypt(u32 *state, u8 *dst, const u8 *src,
 			     unsigned int bytes)
 {

drivers/hv/vmbus_drv.c

@@ -42,6 +42,7 @@
 #include <linux/screen_info.h>
 #include <linux/kdebug.h>
 #include <linux/efi.h>
+#include <linux/random.h>
 #include "hyperv_vmbus.h"
 
 static struct acpi_device  *hv_acpi_dev;
@@ -806,6 +807,8 @@ static void vmbus_isr(void)
 		else
 			tasklet_schedule(hv_context.msg_dpc[cpu]);
 	}
+
+	add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0);
 }
 
 

include/crypto/chacha20.h

@@ -16,6 +16,7 @@ struct chacha20_ctx {
 	u32 key[8];
 };
 
+void chacha20_block(u32 *state, void *stream);
 void crypto_chacha20_init(u32 *state, struct chacha20_ctx *ctx, u8 *iv);
 int crypto_chacha20_setkey(struct crypto_tfm *tfm, const u8 *key,
 			   unsigned int keysize);

lib/Makefile

@@ -19,7 +19,7 @@ KCOV_INSTRUMENT_dynamic_debug.o := n
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o dump_stack.o timerqueue.o\
 	 idr.o int_sqrt.o extable.o \
-	 sha1.o md5.o irq_regs.o argv_split.o \
+	 sha1.o chacha20.o md5.o irq_regs.o argv_split.o \
 	 flex_proportions.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
 	 earlycpio.o seq_buf.o nmi_backtrace.o nodemask.o

lib/chacha20.c

+/*
+ * ChaCha20 256-bit cipher algorithm, RFC7539
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/bitops.h>
+#include <linux/cryptohash.h>
+#include <asm/unaligned.h>
+#include <crypto/chacha20.h>
+
+static inline u32 rotl32(u32 v, u8 n)
+{
+	return (v << n) | (v >> (sizeof(v) * 8 - n));
+}
+
+extern void chacha20_block(u32 *state, void *stream)
+{
+	u32 x[16], *out = stream;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(x); i++)
+		x[i] = state[i];
+
+	for (i = 0; i < 20; i += 2) {
+		x[0]  += x[4];    x[12] = rotl32(x[12] ^ x[0],  16);
+		x[1]  += x[5];    x[13] = rotl32(x[13] ^ x[1],  16);
+		x[2]  += x[6];    x[14] = rotl32(x[14] ^ x[2],  16);
+		x[3]  += x[7];    x[15] = rotl32(x[15] ^ x[3],  16);
+
+		x[8]  += x[12];   x[4]  = rotl32(x[4]  ^ x[8],  12);
+		x[9]  += x[13];   x[5]  = rotl32(x[5]  ^ x[9],  12);
+		x[10] += x[14];   x[6]  = rotl32(x[6]  ^ x[10], 12);
+		x[11] += x[15];   x[7]  = rotl32(x[7]  ^ x[11], 12);
+
+		x[0]  += x[4];    x[12] = rotl32(x[12] ^ x[0],   8);
+		x[1]  += x[5];    x[13] = rotl32(x[13] ^ x[1],   8);
+		x[2]  += x[6];    x[14] = rotl32(x[14] ^ x[2],   8);
+		x[3]  += x[7];    x[15] = rotl32(x[15] ^ x[3],   8);
+
+		x[8]  += x[12];   x[4]  = rotl32(x[4]  ^ x[8],   7);
+		x[9]  += x[13];   x[5]  = rotl32(x[5]  ^ x[9],   7);
+		x[10] += x[14];   x[6]  = rotl32(x[6]  ^ x[10],  7);
+		x[11] += x[15];   x[7]  = rotl32(x[7]  ^ x[11],  7);
+
+		x[0]  += x[5];    x[15] = rotl32(x[15] ^ x[0],  16);
+		x[1]  += x[6];    x[12] = rotl32(x[12] ^ x[1],  16);
+		x[2]  += x[7];    x[13] = rotl32(x[13] ^ x[2],  16);
+		x[3]  += x[4];    x[14] = rotl32(x[14] ^ x[3],  16);
+
+		x[10] += x[15];   x[5]  = rotl32(x[5]  ^ x[10], 12);
+		x[11] += x[12];   x[6]  = rotl32(x[6]  ^ x[11], 12);
+		x[8]  += x[13];   x[7]  = rotl32(x[7]  ^ x[8],  12);
+		x[9]  += x[14];   x[4]  = rotl32(x[4]  ^ x[9],  12);
+
+		x[0]  += x[5];    x[15] = rotl32(x[15] ^ x[0],   8);
+		x[1]  += x[6];    x[12] = rotl32(x[12] ^ x[1],   8);
+		x[2]  += x[7];    x[13] = rotl32(x[13] ^ x[2],   8);
+		x[3]  += x[4];    x[14] = rotl32(x[14] ^ x[3],   8);
+
+		x[10] += x[15];   x[5]  = rotl32(x[5]  ^ x[10],  7);
+		x[11] += x[12];   x[6]  = rotl32(x[6]  ^ x[11],  7);
+		x[8]  += x[13];   x[7]  = rotl32(x[7]  ^ x[8],   7);
+		x[9]  += x[14];   x[4]  = rotl32(x[4]  ^ x[9],   7);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(x); i++)
+		out[i] = cpu_to_le32(x[i] + state[i]);
+
+	state[12]++;
+}
+EXPORT_SYMBOL(chacha20_block);