Merge branch 'lineage-19.1' of https://github.com/TARKZiM/android_kernel_htc_msm8974 into HEAD

Change-Id: Ic4f5c822d9c66c2100597d772eff5eadd1ddb083

15 files changed, 1209 insertions, 415 deletions

diff --git a/crypto/Kconfig b/crypto/Kconfig
index 84ac643c9bd..b0aae164868 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -833,6 +833,19 @@ config CRYPTO_SALSA20_X86_64
 	  The Salsa20 stream cipher algorithm is designed by Daniel J.
 	  Bernstein <djb@cr.yp.to>. See <http://cr.yp.to/snuffle.html>
 
+config CRYPTO_CHACHA20
+	tristate "ChaCha20 cipher algorithm"
+	select CRYPTO_BLKCIPHER
+	help
+	  ChaCha20 cipher algorithm, RFC7539.
+
+	  ChaCha20 is a 256-bit high-speed stream cipher designed by Daniel J.
+	  Bernstein and further specified in RFC7539 for use in IETF protocols.
+	  This is the portable C implementation of ChaCha20.
+
+	  See also:
+	  <http://cr.yp.to/chacha/chacha-20080128.pdf>
+
 config CRYPTO_SEED
 	tristate "SEED cipher algorithm"
 	select CRYPTO_ALGAPI
diff --git a/crypto/Makefile b/crypto/Makefile
index 93c9fc6604e..8418e2849cc 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -76,6 +76,7 @@ obj-$(CONFIG_CRYPTO_KHAZAD) += khazad.o
 obj-$(CONFIG_CRYPTO_ANUBIS) += anubis.o
 obj-$(CONFIG_CRYPTO_SEED) += seed.o
 obj-$(CONFIG_CRYPTO_SALSA20) += salsa20_generic.o
+obj-$(CONFIG_CRYPTO_CHACHA20) += chacha20_generic.o
 obj-$(CONFIG_CRYPTO_DEFLATE) += deflate.o
 obj-$(CONFIG_CRYPTO_ZLIB) += zlib.o
 obj-$(CONFIG_CRYPTO_MICHAEL_MIC) += michael_mic.o
diff --git a/crypto/chacha20_generic.c b/crypto/chacha20_generic.c
new file mode 100644
index 00000000000..1cab83146e3
--- /dev/null
+++ b/crypto/chacha20_generic.c
@@ -0,0 +1,151 @@
+/*
+ * 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 <crypto/algapi.h>
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <crypto/chacha20.h>
+
+static inline u32 le32_to_cpuvp(const void *p)
+{
+	return le32_to_cpup(p);
+}
+
+static void chacha20_docrypt(u32 *state, u8 *dst, const u8 *src,
+			     unsigned int bytes)
+{
+	u8 stream[CHACHA20_BLOCK_SIZE];
+
+	if (dst != src)
+		memcpy(dst, src, bytes);
+
+	while (bytes >= CHACHA20_BLOCK_SIZE) {
+		chacha20_block(state, stream);
+		crypto_xor(dst, stream, CHACHA20_BLOCK_SIZE);
+		bytes -= CHACHA20_BLOCK_SIZE;
+		dst += CHACHA20_BLOCK_SIZE;
+	}
+	if (bytes) {
+		chacha20_block(state, stream);
+		crypto_xor(dst, stream, bytes);
+	}
+}
+
+void crypto_chacha20_init(u32 *state, struct chacha20_ctx *ctx, u8 *iv)
+{
+	static const char constant[16] = "expand 32-byte k";
+
+	state[0]  = le32_to_cpuvp(constant +  0);
+	state[1]  = le32_to_cpuvp(constant +  4);
+	state[2]  = le32_to_cpuvp(constant +  8);
+	state[3]  = le32_to_cpuvp(constant + 12);
+	state[4]  = ctx->key[0];
+	state[5]  = ctx->key[1];
+	state[6]  = ctx->key[2];
+	state[7]  = ctx->key[3];
+	state[8]  = ctx->key[4];
+	state[9]  = ctx->key[5];
+	state[10] = ctx->key[6];
+	state[11] = ctx->key[7];
+	state[12] = le32_to_cpuvp(iv +  0);
+	state[13] = le32_to_cpuvp(iv +  4);
+	state[14] = le32_to_cpuvp(iv +  8);
+	state[15] = le32_to_cpuvp(iv + 12);
+}
+EXPORT_SYMBOL_GPL(crypto_chacha20_init);
+
+int crypto_chacha20_setkey(struct crypto_tfm *tfm, const u8 *key,
+			   unsigned int keysize)
+{
+	struct chacha20_ctx *ctx = crypto_tfm_ctx(tfm);
+	int i;
+
+	if (keysize != CHACHA20_KEY_SIZE)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(ctx->key); i++)
+		ctx->key[i] = le32_to_cpuvp(key + i * sizeof(u32));
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_chacha20_setkey);
+
+int crypto_chacha20_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+			  struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+	u32 state[16];
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt_block(desc, &walk, CHACHA20_BLOCK_SIZE);
+
+	crypto_chacha20_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv);
+
+	while (walk.nbytes >= CHACHA20_BLOCK_SIZE) {
+		chacha20_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr,
+				 rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE));
+		err = blkcipher_walk_done(desc, &walk,
+					  walk.nbytes % CHACHA20_BLOCK_SIZE);
+	}
+
+	if (walk.nbytes) {
+		chacha20_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr,
+				 walk.nbytes);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(crypto_chacha20_crypt);
+
+static struct crypto_alg alg = {
+	.cra_name		= "chacha20",
+	.cra_driver_name	= "chacha20-generic",
+	.cra_priority		= 100,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_ctxsize		= sizeof(struct chacha20_ctx),
+	.cra_alignmask		= sizeof(u32) - 1,
+	.cra_module		= THIS_MODULE,
+	.cra_u			= {
+		.blkcipher = {
+			.min_keysize	= CHACHA20_KEY_SIZE,
+			.max_keysize	= CHACHA20_KEY_SIZE,
+			.ivsize		= CHACHA20_IV_SIZE,
+			.geniv		= "seqiv",
+			.setkey		= crypto_chacha20_setkey,
+			.encrypt	= crypto_chacha20_crypt,
+			.decrypt	= crypto_chacha20_crypt,
+		},
+	},
+};
+
+static int __init chacha20_generic_mod_init(void)
+{
+	return crypto_register_alg(&alg);
+}
+
+static void __exit chacha20_generic_mod_fini(void)
+{
+	crypto_unregister_alg(&alg);
+}
+
+module_init(chacha20_generic_mod_init);
+module_exit(chacha20_generic_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
+MODULE_DESCRIPTION("chacha20 cipher algorithm");
+MODULE_ALIAS_CRYPTO("chacha20");
+MODULE_ALIAS_CRYPTO("chacha20-generic");
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index 69ae5972713..116e4263a74 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -37,10 +37,11 @@
 #include <linux/kernel.h>
 #include <linux/fs.h>
 #include <linux/sched.h>
-#include <linux/init.h>
 #include <linux/miscdevice.h>
+#include <linux/kthread.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
+#include <linux/random.h>
 #include <asm/uaccess.h>
 
 
@@ -50,21 +51,52 @@
 
 
 static struct hwrng *current_rng;
+static struct task_struct *hwrng_fill;
 static LIST_HEAD(rng_list);
 static DEFINE_MUTEX(rng_mutex);
 static int data_avail;
-static u8 *rng_buffer;
+static u8 *rng_buffer, *rng_fillbuf;
+static unsigned short current_quality = 700; /* an arbitrary 70% */
+
+module_param(current_quality, ushort, 0644);
+MODULE_PARM_DESC(current_quality,
+		 "current hwrng entropy estimation per mill");
+
+static void start_khwrngd(void);
+
+static inline int rng_get_data(struct hwrng *rng, u8 *buffer, size_t size,
+			       int wait);
 
 static size_t rng_buffer_size(void)
 {
 	return SMP_CACHE_BYTES < 32 ? 32 : SMP_CACHE_BYTES;
 }
 
+static void add_early_randomness(struct hwrng *rng)
+{
+	int bytes_read;
+	size_t size = min_t(size_t, 16, rng_buffer_size());
+
+	bytes_read = rng_get_data(rng, rng_buffer, size, 1);
+	if (bytes_read > 0)
+		add_device_randomness(rng_buffer, bytes_read);
+}
+
 static inline int hwrng_init(struct hwrng *rng)
 {
-	if (!rng->init)
-		return 0;
-	return rng->init(rng);
+	if (rng->init) {
+		int ret;
+
+		ret =  rng->init(rng);
+		if (ret)
+			return ret;
+	}
+	add_early_randomness(rng);
+
+	if (current_quality > 0 && !hwrng_fill)
+		start_khwrngd();
+
+	return 0;
 }
 
 static inline void hwrng_cleanup(struct hwrng *rng)
@@ -300,9 +332,38 @@ err_misc_dereg:
 	goto out;
 }
 
+static int hwrng_fillfn(void *unused)
+{
+	long rc;
+
+	while (!kthread_should_stop()) {
+		if (!current_rng)
+			break;
+		rc = rng_get_data(current_rng, rng_fillbuf,
+				  rng_buffer_size(), 1);
+		if (rc <= 0) {
+			pr_warn("hwrng: no data available\n");
+			msleep_interruptible(10000);
+			continue;
+		}
+		add_hwgenerator_randomness((void *)rng_fillbuf, rc,
+					   rc * current_quality * 8 >> 10);
+	}
+	hwrng_fill = NULL;
+	return 0;
+}
+
+static void start_khwrngd(void)
+{
+	hwrng_fill = kthread_run(hwrng_fillfn, NULL, "hwrng");
+	if (IS_ERR(hwrng_fill)) {
+		pr_err("hwrng_fill thread creation failed");
+		hwrng_fill = NULL;
+	}
+}
+
 int hwrng_register(struct hwrng *rng)
 {
-	int must_register_misc;
 	int err = -EINVAL;
 	struct hwrng *old_rng, *tmp;
 
@@ -319,6 +380,13 @@ int hwrng_register(struct hwrng *rng)
 		if (!rng_buffer)
 			goto out_unlock;
 	}
+	if (!rng_fillbuf) {
+		rng_fillbuf = kmalloc(rng_buffer_size(), GFP_KERNEL);
+		if (!rng_fillbuf) {
+			kfree(rng_buffer);
+			goto out_unlock;
+		}
+	}
 
 	/* Must not register two RNGs with the same name. */
 	err = -EEXIST;
@@ -327,7 +395,6 @@ int hwrng_register(struct hwrng *rng)
 			goto out_unlock;
 	}
 
-	must_register_misc = (current_rng == NULL);
 	old_rng = current_rng;
 	if (!old_rng) {
 		err = hwrng_init(rng);
@@ -336,18 +403,28 @@ int hwrng_register(struct hwrng *rng)
 		current_rng = rng;
 	}
 	err = 0;
-	if (must_register_misc) {
+	if (!old_rng) {
 		err = register_miscdev();
 		if (err) {
-			if (!old_rng) {
-				hwrng_cleanup(rng);
-				current_rng = NULL;
-			}
+			hwrng_cleanup(rng);
+			current_rng = NULL;
 			goto out_unlock;
 		}
 	}
 	INIT_LIST_HEAD(&rng->list);
 	list_add_tail(&rng->list, &rng_list);
+
+	if (old_rng && !rng->init) {
+		/*
+		 * Use a new device's input to add some randomness to
+		 * the system.  If this rng device isn't going to be
+		 * used right away, its init function hasn't been
+		 * called yet; so only use the randomness from devices
+		 * that don't need an init callback.
+		 */
+		add_early_randomness(rng);
+	}
+
 out_unlock:
 	mutex_unlock(&rng_mutex);
 out:
@@ -373,13 +450,26 @@ void hwrng_unregister(struct hwrng *rng)
 				current_rng = NULL;
 		}
 	}
-	if (list_empty(&rng_list))
+	if (list_empty(&rng_list)) {
 		unregister_miscdev();
+		if (hwrng_fill)
+			kthread_stop(hwrng_fill);
+	}
 
 	mutex_unlock(&rng_mutex);
 }
 EXPORT_SYMBOL_GPL(hwrng_unregister);
 
+static void __exit hwrng_exit(void)
+{
+	mutex_lock(&rng_mutex);
+	BUG_ON(current_rng);
+	kfree(rng_buffer);
+	kfree(rng_fillbuf);
+	mutex_unlock(&rng_mutex);
+}
+
+module_exit(hwrng_exit);
 
 MODULE_DESCRIPTION("H/W Random Number Generator (RNG) driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/char/hw_random/msm_rng.c b/drivers/char/hw_random/msm_rng.c
index b13de3a4ef8..9b532b82f09 100644
--- a/drivers/char/hw_random/msm_rng.c
+++ b/drivers/char/hw_random/msm_rng.c
@@ -28,6 +28,7 @@
 #include <linux/qrng.h>
 #include <linux/fs.h>
 #include <linux/cdev.h>
+#include <linux/delay.h>
 
 #include <linux/platform_data/qcom_crypto_device.h>
 
@@ -113,24 +114,41 @@ int msm_rng_direct_read(struct msm_rng_device *msm_rng_dev, void *data)
 	struct platform_device *pdev;
 	void __iomem *base;
 	size_t currsize = 0;
-	unsigned long val;
-	unsigned long *retdata = data;
+	u32 val;
+	u32 *retdata = data;
 	int ret;
+	int failed = 0;
 
 	pdev = msm_rng_dev->pdev;
 	base = msm_rng_dev->base;
 
+	mutex_lock(&msm_rng_dev->rng_lock);
+
+	if (msm_rng_dev->qrng_perf_client) {
+		ret = msm_bus_scale_client_update_request(
+				msm_rng_dev->qrng_perf_client, 1);
+		if (ret)
+			pr_err("bus_scale_client_update_req failed!\n");
+	}
 	/* enable PRNG clock */
 	ret = clk_prepare_enable(msm_rng_dev->prng_clk);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to enable clock in callback\n");
-		return 0;
+		goto err;
 	}
 	/* read random data from h/w */
 	do {
 		/* check status bit if data is available */
-		if (!(readl_relaxed(base + PRNG_STATUS_OFFSET) & 0x00000001))
-			break;	/* no data to read so just bail */
+		while (!(readl_relaxed(base + PRNG_STATUS_OFFSET)
+					& 0x00000001)) {
+			if (failed == 10) {
+				pr_err("Data not available after retry\n");
+				break;
+			}
+			pr_err("msm_rng:Data not available!\n");
+			msleep_interruptible(10);
+			failed++;
+		}
 
 		/* read FIFO */
 		val = readl_relaxed(base + PRNG_DATA_OUT_OFFSET);
@@ -145,10 +163,17 @@ int msm_rng_direct_read(struct msm_rng_device *msm_rng_dev, void *data)
 
 	/* vote to turn off clock */
 	clk_disable_unprepare(msm_rng_dev->prng_clk);
+err:
+	if (msm_rng_dev->qrng_perf_client) {
+		ret = msm_bus_scale_client_update_request(
+				msm_rng_dev->qrng_perf_client, 0);
+		if (ret)
+			pr_err("bus_scale_client_update_req failed!\n");
+	}
+	mutex_unlock(&msm_rng_dev->rng_lock);
 
 	val = 0L;
 	return currsize;
-
 }
 
 static int msm_rng_drbg_read(struct hwrng *rng,
@@ -157,47 +182,57 @@ static int msm_rng_drbg_read(struct hwrng *rng,
 	struct msm_rng_device *msm_rng_dev;
 	struct platform_device *pdev;
 	void __iomem *base;
-	size_t maxsize;
 	size_t currsize = 0;
-	unsigned long val;
-	unsigned long *retdata = data;
+	u32 val;
+	u32 *retdata = data;
 	int ret, ret1;
+	int failed = 0;
 
 	msm_rng_dev = (struct msm_rng_device *)rng->priv;
 	pdev = msm_rng_dev->pdev;
 	base = msm_rng_dev->base;
 
-
-	down(&msm_rng_dev->drbg_sem);
-
-	/* calculate max size bytes to transfer back to caller */
-	maxsize = min_t(size_t, MAX_HW_FIFO_SIZE, max);
-
 	/* no room for word data */
-	if (maxsize < 4)
+	if (max < 4)
 		return 0;
 
+	mutex_lock(&msm_rng_dev->rng_lock);
+
 	/* read random data from CTR-AES based DRBG */
 	if (FIPS140_DRBG_ENABLED == msm_rng_dev->fips140_drbg_enabled) {
-		ret1 = fips_drbg_gen(msm_rng_dev->drbg_ctx, data, maxsize);
+		ret1 = fips_drbg_gen(msm_rng_dev->drbg_ctx, data, max);
 		if (FIPS140_PRNG_ERR == ret1)
 			panic("random number generator generator error.\n");
 	} else
 		ret1 = 1;
 
+	if (msm_rng_dev->qrng_perf_client) {
+		ret = msm_bus_scale_client_update_request(
+				msm_rng_dev->qrng_perf_client, 1);
+		if (ret)
+			pr_err("bus_scale_client_update_req failed!\n");
+	}
+
 	/* read random data from h/w */
 	/* enable PRNG clock */
 	ret = clk_prepare_enable(msm_rng_dev->prng_clk);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to enable clock in callback\n");
-		up(&msm_rng_dev->drbg_sem);
-		return 0;
+		goto err;
 	}
 	/* read random data from h/w */
 	do {
 		/* check status bit if data is available */
-		if (!(readl_relaxed(base + PRNG_STATUS_OFFSET) & 0x00000001))
-			break;	/* no data to read so just bail */
+		while (!(readl_relaxed(base + PRNG_STATUS_OFFSET)
+				& 0x00000001)) {
+			if (failed == 10) {
+				pr_err("Data not available after retry\n");
+				break;
+			}
+			pr_err("msm_rng:Data not available!\n");
+			msleep_interruptible(10);
+			failed++;
+		}
 
 		/* read FIFO */
 		val = readl_relaxed(base + PRNG_DATA_OUT_OFFSET);
@@ -210,13 +245,20 @@ static int msm_rng_drbg_read(struct hwrng *rng,
 		currsize += 4;
 
 		/* make sure we stay on 32bit boundary */
-		if ((maxsize - currsize) < 4)
+		if ((max - currsize) < 4)
 			break;
-	} while (currsize < maxsize);
+	} while (currsize < max);
 	/* vote to turn off clock */
 	clk_disable_unprepare(msm_rng_dev->prng_clk);
+err:
+	if (msm_rng_dev->qrng_perf_client) {
+		ret = msm_bus_scale_client_update_request(
+				msm_rng_dev->qrng_perf_client, 0);
+		if (ret)
+			pr_err("bus_scale_client_update_req failed!\n");
+	}
 
-	up(&msm_rng_dev->drbg_sem);
+	mutex_unlock(&msm_rng_dev->rng_lock);
 
 	return currsize;
 }
@@ -370,6 +412,14 @@ static int __devinit msm_rng_enable_hw(struct msm_rng_device *msm_rng_dev)
 		mb();
 	}
 	clk_disable_unprepare(msm_rng_dev->prng_clk);
+
+	if (msm_rng_dev->qrng_perf_client) {
+		ret = msm_bus_scale_client_update_request(
+				msm_rng_dev->qrng_perf_client, 0);
+		if (ret)
+			pr_err("bus_scale_client_update_req failed!\n");
+	}
+
 	return 0;
 }
 
@@ -468,6 +518,8 @@ static int __devinit msm_rng_probe(struct platform_device *pdev)
 	if (error)
 		goto rollback_clk;
 
+	mutex_init(&msm_rng_dev->rng_lock);
+
 	/* register with hwrng framework */
 	msm_rng.priv = (unsigned long) msm_rng_dev;
 	error = hwrng_register(&msm_rng);
@@ -493,8 +545,6 @@ static int __devinit msm_rng_probe(struct platform_device *pdev)
 	}
 	cdev_init(&msm_rng_cdev, &msm_rng_fops);
 
-	sema_init(&msm_rng_dev->drbg_sem, 1);
-
 	_first_msm_drbg_init(msm_rng_dev);
 
 	return error;
diff --git a/drivers/char/hw_random/msm_rng.h b/drivers/char/hw_random/msm_rng.h
index b79ba46e77d..d3a2e833995 100644
--- a/drivers/char/hw_random/msm_rng.h
+++ b/drivers/char/hw_random/msm_rng.h
@@ -31,7 +31,7 @@ struct msm_rng_device {
 	void __iomem *base;
 	struct clk *prng_clk;
 	uint32_t qrng_perf_client;
-	struct  semaphore drbg_sem;
+	struct mutex rng_lock;
 	struct fips_drbg_ctx_s *drbg_ctx;
 	int    fips140_drbg_enabled;
 };
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 746b03dfbc3..58ee4445b7a 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -250,17 +250,16 @@
 #include <linux/interrupt.h>
 #include <linux/mm.h>
 #include <linux/spinlock.h>
+#include <linux/kthread.h>
 #include <linux/percpu.h>
 #include <linux/cryptohash.h>
 #include <linux/fips.h>
 #include <linux/ptrace.h>
 #include <linux/kmemcheck.h>
+#include <linux/irq.h>
 #include <linux/syscalls.h>
 #include <linux/completion.h>
-
-#ifdef CONFIG_GENERIC_HARDIRQS
-# include <linux/irq.h>
-#endif
+#include <crypto/chacha20.h>
 
 #include <asm/processor.h>
 #include <asm/uaccess.h>
@@ -271,129 +270,137 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/random.h>
 
+/* #define ADD_INTERRUPT_BENCH */
+
 /*
  * Configuration information
  */
-#define INPUT_POOL_WORDS 128
-#define OUTPUT_POOL_WORDS 32
+#define INPUT_POOL_SHIFT	12
+#define INPUT_POOL_WORDS	(1 << (INPUT_POOL_SHIFT-5))
+#define OUTPUT_POOL_SHIFT	10
+#define OUTPUT_POOL_WORDS	(1 << (OUTPUT_POOL_SHIFT-5))
 #define SEC_XFER_SIZE 512
 #define EXTRACT_SIZE 10
 
+#define DEBUG_RANDOM_BOOT 0
+
 #define LONGS(x) (((x) + sizeof(unsigned long) - 1)/sizeof(unsigned long))
 
 /*
+ * To allow fractional bits to be tracked, the entropy_count field is
+ * denominated in units of 1/8th bits.
+ *
+ * 2*(ENTROPY_SHIFT + log2(poolbits)) must <= 31, or the multiply in
+ * credit_entropy_bits() needs to be 64 bits wide.
+ */
+#define ENTROPY_SHIFT 3
+#define ENTROPY_BITS(r) ((r)->entropy_count >> ENTROPY_SHIFT)
+
+/*
  * The minimum number of bits of entropy before we wake up a read on
  * /dev/random.  Should be enough to do a significant reseed.
  */
-static int random_read_wakeup_thresh = 64;
+static int random_read_wakeup_bits = 64;
 
 /*
  * If the entropy count falls under this number of bits, then we
  * should wake up processes which are selecting or polling on write
  * access to /dev/random.
  */
-static int random_write_wakeup_thresh = 128;
+static int random_write_wakeup_bits = 28 * OUTPUT_POOL_WORDS;
 
 /*
- * When the input pool goes over trickle_thresh, start dropping most
- * samples to avoid wasting CPU time and reduce lock contention.
+ * The minimum number of seconds between urandom pool reseeding.  We
+ * do this to limit the amount of entropy that can be drained from the
+ * input pool even if there are heavy demands on /dev/urandom.
  */
-
-static int trickle_thresh __read_mostly = INPUT_POOL_WORDS * 28;
-
-static DEFINE_PER_CPU(int, trickle_count);
+static int random_min_urandom_seed = 60;
 
 /*
- * A pool of size .poolwords is stirred with a primitive polynomial
- * of degree .poolwords over GF(2).  The taps for various sizes are
- * defined below.  They are chosen to be evenly spaced (minimum RMS
- * distance from evenly spaced; the numbers in the comments are a
- * scaled squared error sum) except for the last tap, which is 1 to
- * get the twisting happening as fast as possible.
+ * Originally, we used a primitive polynomial of degree .poolwords
+ * over GF(2).  The taps for various sizes are defined below.  They
+ * were chosen to be evenly spaced except for the last tap, which is 1
+ * to get the twisting happening as fast as possible.
+ *
+ * For the purposes of better mixing, we use the CRC-32 polynomial as
+ * well to make a (modified) twisted Generalized Feedback Shift
+ * Register.  (See M. Matsumoto & Y. Kurita, 1992.  Twisted GFSR
+ * generators.  ACM Transactions on Modeling and Computer Simulation
+ * 2(3):179-194.  Also see M. Matsumoto & Y. Kurita, 1994.  Twisted
+ * GFSR generators II.  ACM Transactions on Modeling and Computer
+ * Simulation 4:254-266)
+ *
+ * Thanks to Colin Plumb for suggesting this.
+ *
+ * The mixing operation is much less sensitive than the output hash,
+ * where we use SHA-1.  All that we want of mixing operation is that
+ * it be a good non-cryptographic hash; i.e. it not produce collisions
+ * when fed "random" data of the sort we expect to see.  As long as
+ * the pool state differs for different inputs, we have preserved the
+ * input entropy and done a good job.  The fact that an intelligent
+ * attacker can construct inputs that will produce controlled
+ * alterations to the pool's state is not important because we don't
+ * consider such inputs to contribute any randomness.  The only
+ * property we need with respect to them is that the attacker can't
+ * increase his/her knowledge of the pool's state.  Since all
+ * additions are reversible (knowing the final state and the input,
+ * you can reconstruct the initial state), if an attacker has any
+ * uncertainty about the initial state, he/she can only shuffle that
+ * uncertainty about, but never cause any collisions (which would
+ * decrease the uncertainty).
+ *
+ * Our mixing functions were analyzed by Lacharme, Roeck, Strubel, and
+ * Videau in their paper, "The Linux Pseudorandom Number Generator
+ * Revisited" (see: http://eprint.iacr.org/2012/251.pdf).  In their
+ * paper, they point out that we are not using a true Twisted GFSR,
+ * since Matsumoto & Kurita used a trinomial feedback polynomial (that
+ * is, with only three taps, instead of the six that we are using).
+ * As a result, the resulting polynomial is neither primitive nor
+ * irreducible, and hence does not have a maximal period over
+ * GF(2**32).  They suggest a slight change to the generator
+ * polynomial which improves the resulting TGFSR polynomial to be
+ * irreducible, which we have made here.
  */
 static struct poolinfo {
-	int poolwords;
+	int poolbitshift, poolwords, poolbytes, poolbits, poolfracbits;
+#define S(x) ilog2(x)+5, (x), (x)*4, (x)*32, (x) << (ENTROPY_SHIFT+5)
 	int tap1, tap2, tap3, tap4, tap5;
 } poolinfo_table[] = {
-	/* x^128 + x^103 + x^76 + x^51 +x^25 + x + 1 -- 105 */
-	{ 128,	103,	76,	51,	25,	1 },
-	/* x^32 + x^26 + x^20 + x^14 + x^7 + x + 1 -- 15 */
-	{ 32,	26,	20,	14,	7,	1 },
+	/* was: x^128 + x^103 + x^76 + x^51 +x^25 + x + 1 */
+	/* x^128 + x^104 + x^76 + x^51 +x^25 + x + 1 */
+	{ S(128),	104,	76,	51,	25,	1 },
+	/* was: x^32 + x^26 + x^20 + x^14 + x^7 + x + 1 */
+	/* x^32 + x^26 + x^19 + x^14 + x^7 + x + 1 */
+	{ S(32),	26,	19,	14,	7,	1 },
 #if 0
 	/* x^2048 + x^1638 + x^1231 + x^819 + x^411 + x + 1  -- 115 */
-	{ 2048,	1638,	1231,	819,	411,	1 },
+	{ S(2048),	1638,	1231,	819,	411,	1 },
 
 	/* x^1024 + x^817 + x^615 + x^412 + x^204 + x + 1 -- 290 */
-	{ 1024,	817,	615,	412,	204,	1 },
+	{ S(1024),	817,	615,	412,	204,	1 },
 
 	/* x^1024 + x^819 + x^616 + x^410 + x^207 + x^2 + 1 -- 115 */
-	{ 1024,	819,	616,	410,	207,	2 },
+	{ S(1024),	819,	616,	410,	207,	2 },
 
 	/* x^512 + x^411 + x^308 + x^208 + x^104 + x + 1 -- 225 */
-	{ 512,	411,	308,	208,	104,	1 },
+	{ S(512),	411,	308,	208,	104,	1 },
 
 	/* x^512 + x^409 + x^307 + x^206 + x^102 + x^2 + 1 -- 95 */
-	{ 512,	409,	307,	206,	102,	2 },
+	{ S(512),	409,	307,	206,	102,	2 },
 	/* x^512 + x^409 + x^309 + x^205 + x^103 + x^2 + 1 -- 95 */
-	{ 512,	409,	309,	205,	103,	2 },
+	{ S(512),	409,	309,	205,	103,	2 },
 
 	/* x^256 + x^205 + x^155 + x^101 + x^52 + x + 1 -- 125 */
-	{ 256,	205,	155,	101,	52,	1 },
+	{ S(256),	205,	155,	101,	52,	1 },
 
 	/* x^128 + x^103 + x^78 + x^51 + x^27 + x^2 + 1 -- 70 */
-	{ 128,	103,	78,	51,	27,	2 },
+	{ S(128),	103,	78,	51,	27,	2 },
 
 	/* x^64 + x^52 + x^39 + x^26 + x^14 + x + 1 -- 15 */
-	{ 64,	52,	39,	26,	14,	1 },
+	{ S(64),	52,	39,	26,	14,	1 },
 #endif
 };
 
-#define POOLBITS	poolwords*32
-#define POOLBYTES	poolwords*4
-
-/*
- * For the purposes of better mixing, we use the CRC-32 polynomial as
- * well to make a twisted Generalized Feedback Shift Reigster
- *
- * (See M. Matsumoto & Y. Kurita, 1992.  Twisted GFSR generators.  ACM
- * Transactions on Modeling and Computer Simulation 2(3):179-194.
- * Also see M. Matsumoto & Y. Kurita, 1994.  Twisted GFSR generators
- * II.  ACM Transactions on Mdeling and Computer Simulation 4:254-266)
- *
- * Thanks to Colin Plumb for suggesting this.
- *
- * We have not analyzed the resultant polynomial to prove it primitive;
- * in fact it almost certainly isn't.  Nonetheless, the irreducible factors
- * of a random large-degree polynomial over GF(2) are more than large enough
- * that periodicity is not a concern.
- *
- * The input hash is much less sensitive than the output hash.  All
- * that we want of it is that it be a good non-cryptographic hash;
- * i.e. it not produce collisions when fed "random" data of the sort
- * we expect to see.  As long as the pool state differs for different
- * inputs, we have preserved the input entropy and done a good job.
- * The fact that an intelligent attacker can construct inputs that
- * will produce controlled alterations to the pool's state is not
- * important because we don't consider such inputs to contribute any
- * randomness.  The only property we need with respect to them is that
- * the attacker can't increase his/her knowledge of the pool's state.
- * Since all additions are reversible (knowing the final state and the
- * input, you can reconstruct the initial state), if an attacker has
- * any uncertainty about the initial state, he/she can only shuffle
- * that uncertainty about, but never cause any collisions (which would
- * decrease the uncertainty).
- *
- * The chosen system lets the state of the pool be (essentially) the input
- * modulo the generator polymnomial.  Now, for random primitive polynomials,
- * this is a universal class of hash functions, meaning that the chance
- * of a collision is limited by the attacker's knowledge of the generator
- * polynomail, so if it is chosen at random, an attacker can never force
- * a collision.  Here, we use a fixed polynomial, but we *can* assume that
- * ###--> it is unknown to the processes generating the input entropy. <-###
- * Because of this important property, this is a good, collision-resistant
- * hash; hash collisions will occur no more often than chance.
- */
-
 /*
  * Static global variables
  */
@@ -402,20 +409,29 @@ static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
 static DECLARE_WAIT_QUEUE_HEAD(urandom_init_wait);
 static struct fasync_struct *fasync;
 
-#if 0
-static bool debug;
-module_param(debug, bool, 0644);
-#define DEBUG_ENT(fmt, arg...) do { \
-	if (debug) \
-		printk(KERN_DEBUG "random %04d %04d %04d: " \
-		fmt,\
-		input_pool.entropy_count,\
-		blocking_pool.entropy_count,\
-		nonblocking_pool.entropy_count,\
-		## arg); } while (0)
-#else
-#define DEBUG_ENT(fmt, arg...) do {} while (0)
-#endif
+struct crng_state {
+	__u32		state[16];
+	unsigned long	init_time;
+	spinlock_t	lock;
+};
+
+struct crng_state primary_crng = {
+	.lock = __SPIN_LOCK_UNLOCKED(primary_crng.lock),
+};
+
+/*
+ * crng_init =  0 --> Uninitialized
+ *		1 --> Initialized
+ *		2 --> Initialized from input_pool
+ *
+ * crng_init is protected by primary_crng->lock, and only increases
+ * its value (from 0->1->2).
+ */
+static int crng_init = 0;
+#define crng_ready() (likely(crng_init > 0))
+static int crng_init_cnt = 0;
+#define CRNG_INIT_CNT_THRESH (2*CHACHA20_KEY_SIZE)
+static void extract_crng(__u8 out[CHACHA20_BLOCK_SIZE]);
 
 /**********************************************************************
  *
@@ -427,31 +443,37 @@ module_param(debug, bool, 0644);
 struct entropy_store;
 struct entropy_store {
 	/* read-only data: */
-	struct poolinfo *poolinfo;
+	const struct poolinfo *poolinfo;
 	__u32 *pool;
 	const char *name;
 	struct entropy_store *pull;
-	int limit;
 
 	/* read-write data: */
+	unsigned long last_pulled;
 	spinlock_t lock;
-	unsigned add_ptr;
-	unsigned input_rotate;
+	unsigned short add_ptr;
+	unsigned short input_rotate;
 	int entropy_count;
 	int entropy_total;
 	unsigned int initialized:1;
+	unsigned int limit:1;
+	unsigned int last_data_init:1;
 	__u8 last_data[EXTRACT_SIZE];
 };
 
+static ssize_t extract_entropy(struct entropy_store *r, void *buf,
+			       size_t nbytes, int min, int rsvd);
+static ssize_t _extract_entropy(struct entropy_store *r, void *buf,
+				size_t nbytes, int fips);
+static void crng_reseed(struct crng_state *crng, struct entropy_store *r);
 static __u32 input_pool_data[INPUT_POOL_WORDS];
 static __u32 blocking_pool_data[OUTPUT_POOL_WORDS];
-static __u32 nonblocking_pool_data[OUTPUT_POOL_WORDS];
 
 static struct entropy_store input_pool = {
 	.poolinfo = &poolinfo_table[0],
 	.name = "input",
 	.limit = 1,
-	.lock = __SPIN_LOCK_UNLOCKED(&input_pool.lock),
+	.lock = __SPIN_LOCK_UNLOCKED(input_pool.lock),
 	.pool = input_pool_data
 };
 
@@ -460,18 +482,10 @@ static struct entropy_store blocking_pool = {
 	.name = "blocking",
 	.limit = 1,
 	.pull = &input_pool,
-	.lock = __SPIN_LOCK_UNLOCKED(&blocking_pool.lock),
+	.lock = __SPIN_LOCK_UNLOCKED(blocking_pool.lock),
 	.pool = blocking_pool_data
 };
 
-static struct entropy_store nonblocking_pool = {
-	.poolinfo = &poolinfo_table[1],
-	.name = "nonblocking",
-	.pull = &input_pool,
-	.lock = __SPIN_LOCK_UNLOCKED(&nonblocking_pool.lock),
-	.pool = nonblocking_pool_data
-};
-
 static __u32 const twist_table[8] = {
 	0x00000000, 0x3b6e20c8, 0x76dc4190, 0x4db26158,
 	0xedb88320, 0xd6d6a3e8, 0x9b64c2b0, 0xa00ae278 };
@@ -487,9 +501,9 @@ static __u32 const twist_table[8] = {
  * the entropy is concentrated in the low-order bits.
  */
 static void _mix_pool_bytes(struct entropy_store *r, const void *in,
-			    int nbytes, __u8 out[64])
+			    int nbytes)
 {
-	unsigned long i, j, tap1, tap2, tap3, tap4, tap5;
+	unsigned long i, tap1, tap2, tap3, tap4, tap5;
 	int input_rotate;
 	int wordmask = r->poolinfo->poolwords - 1;
 	const char *bytes = in;
@@ -501,13 +515,12 @@ static void _mix_pool_bytes(struct entropy_store *r, const void *in,
 	tap4 = r->poolinfo->tap4;
 	tap5 = r->poolinfo->tap5;
 
-	smp_rmb();
-	input_rotate = ACCESS_ONCE(r->input_rotate);
-	i = ACCESS_ONCE(r->add_ptr);
+	input_rotate = r->input_rotate;
+	i = r->add_ptr;
 
 	/* mix one byte at a time to simplify size handling and churn faster */
 	while (nbytes--) {
-		w = rol32(*bytes++, input_rotate & 31);
+		w = rol32(*bytes++, input_rotate);
 		i = (i - 1) & wordmask;
 
 		/* XOR in the various taps */
@@ -527,42 +540,36 @@ static void _mix_pool_bytes(struct entropy_store *r, const void *in,
 		 * rotation, so that successive passes spread the
 		 * input bits across the pool evenly.
 		 */
-		input_rotate += i ? 7 : 14;
+		input_rotate = (input_rotate + (i ? 7 : 14)) & 31;
 	}
 
-	ACCESS_ONCE(r->input_rotate) = input_rotate;
-	ACCESS_ONCE(r->add_ptr) = i;
-	smp_wmb();
-
-	if (out)
-		for (j = 0; j < 16; j++)
-			((__u32 *)out)[j] = r->pool[(i - j) & wordmask];
+	r->input_rotate = input_rotate;
+	r->add_ptr = i;
 }
 
 static void __mix_pool_bytes(struct entropy_store *r, const void *in,
-			     int nbytes, __u8 out[64])
+			     int nbytes)
 {
 	trace_mix_pool_bytes_nolock(r->name, nbytes, _RET_IP_);
-	_mix_pool_bytes(r, in, nbytes, out);
+	_mix_pool_bytes(r, in, nbytes);
 }
 
 static void mix_pool_bytes(struct entropy_store *r, const void *in,
-			   int nbytes, __u8 out[64])
+			   int nbytes)
 {
 	unsigned long flags;
 
 	trace_mix_pool_bytes(r->name, nbytes, _RET_IP_);
 	spin_lock_irqsave(&r->lock, flags);
-	_mix_pool_bytes(r, in, nbytes, out);
+	_mix_pool_bytes(r, in, nbytes);
 	spin_unlock_irqrestore(&r->lock, flags);
 }
 
 struct fast_pool {
 	__u32		pool[4];
 	unsigned long	last;
-	unsigned short	count;
-	unsigned char	rotate;
-	unsigned char	last_timer_intr;
+	unsigned short	reg_idx;
+	unsigned char	count;
 };
 
 /*
@@ -570,43 +577,94 @@ struct fast_pool {
  * collector.  It's hardcoded for an 128 bit pool and assumes that any
  * locks that might be needed are taken by the caller.
  */
-static void fast_mix(struct fast_pool *f, const void *in, int nbytes)
+static void fast_mix(struct fast_pool *f)
 {
-	const char	*bytes = in;
-	__u32		w;
-	unsigned	i = f->count;
-	unsigned	input_rotate = f->rotate;
+	__u32 a = f->pool[0],	b = f->pool[1];
+	__u32 c = f->pool[2],	d = f->pool[3];
 
-	while (nbytes--) {
-		w = rol32(*bytes++, input_rotate & 31) ^ f->pool[i & 3] ^
-			f->pool[(i + 1) & 3];
-		f->pool[i & 3] = (w >> 3) ^ twist_table[w & 7];
-		input_rotate += (i++ & 3) ? 7 : 14;
-	}
-	f->count = i;
-	f->rotate = input_rotate;
+	a += b;			c += d;
+	b = rol32(b, 6);	d = rol32(d, 27);
+	d ^= a;			b ^= c;
+
+	a += b;			c += d;
+	b = rol32(b, 16);	d = rol32(d, 14);
+	d ^= a;			b ^= c;
+
+	a += b;			c += d;
+	b = rol32(b, 6);	d = rol32(d, 27);
+	d ^= a;			b ^= c;
+
+	a += b;			c += d;
+	b = rol32(b, 16);	d = rol32(d, 14);
+	d ^= a;			b ^= c;
+
+	f->pool[0] = a;  f->pool[1] = b;
+	f->pool[2] = c;  f->pool[3] = d;
+	f->count++;
 }
 
 /*
- * Credit (or debit) the entropy store with n bits of entropy
+ * Credit (or debit) the entropy store with n bits of entropy.
+ * Use credit_entropy_bits_safe() if the value comes from userspace
+ * or otherwise should be checked for extreme values.
  */
 static void credit_entropy_bits(struct entropy_store *r, int nbits)
 {
 	int entropy_count, orig;
+	const int pool_size = r->poolinfo->poolfracbits;
+	int nfrac = nbits << ENTROPY_SHIFT;
 
 	if (!nbits)
 		return;
 
-	DEBUG_ENT("added %d entropy credits to %s\n", nbits, r->name);
 retry:
 	entropy_count = orig = ACCESS_ONCE(r->entropy_count);
-	entropy_count += nbits;
+	if (nfrac < 0) {
+		/* Debit */
+		entropy_count += nfrac;
+	} else {
+		/*
+		 * Credit: we have to account for the possibility of
+		 * overwriting already present entropy.	 Even in the
+		 * ideal case of pure Shannon entropy, new contributions
+		 * approach the full value asymptotically:
+		 *
+		 * entropy <- entropy + (pool_size - entropy) *
+		 *	(1 - exp(-add_entropy/pool_size))
+		 *
+		 * For add_entropy <= pool_size/2 then
+		 * (1 - exp(-add_entropy/pool_size)) >=
+		 *    (add_entropy/pool_size)*0.7869...
+		 * so we can approximate the exponential with
+		 * 3/4*add_entropy/pool_size and still be on the
+		 * safe side by adding at most pool_size/2 at a time.
+		 *
+		 * The use of pool_size-2 in the while statement is to
+		 * prevent rounding artifacts from making the loop
+		 * arbitrarily long; this limits the loop to log2(pool_size)*2
+		 * turns no matter how large nbits is.
+		 */
+		int pnfrac = nfrac;
+		const int s = r->poolinfo->poolbitshift + ENTROPY_SHIFT + 2;
+		/* The +2 corresponds to the /4 in the denominator */
+
+		do {
+			unsigned int anfrac = min(pnfrac, pool_size/2);
+			unsigned int add =
+				((pool_size - entropy_count)*anfrac*3) >> s;
+
+			entropy_count += add;
+			pnfrac -= anfrac;
+		} while (unlikely(entropy_count < pool_size-2 && pnfrac));
+	}
 
-	if (entropy_count < 0) {
-		DEBUG_ENT("negative entropy/overflow\n");
+	if (unlikely(entropy_count < 0)) {
+		pr_warn("random: negative entropy/overflow: pool %s count %d\n",
+			r->name, entropy_count);
+		WARN_ON(1);
 		entropy_count = 0;
-	} else if (entropy_count > r->poolinfo->POOLBITS)
-		entropy_count = r->poolinfo->POOLBITS;
+	} else if (entropy_count > pool_size)
+		entropy_count = pool_size;
 	if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
 		goto retry;
 
@@ -614,21 +672,177 @@ retry:
 	if (!r->initialized && r->entropy_total > 128) {
 		r->initialized = 1;
 		r->entropy_total = 0;
-		if (r == &nonblocking_pool) {
-			prandom_reseed_late();
-			wake_up_all(&urandom_init_wait);
-			pr_notice("random: %s pool is initialized\n", r->name);
+	}
+
+	if (r == &input_pool) {
+		int entropy_bits = entropy_count >> ENTROPY_SHIFT;
+
+		if (crng_init < 2 && entropy_bits >= 128) {
+			crng_reseed(&primary_crng, r);
+			entropy_bits = r->entropy_count >> ENTROPY_SHIFT;
+		}
+
+		/* should we wake readers? */
+		if (entropy_bits >= random_read_wakeup_bits) {
+			wake_up_interruptible(&random_read_wait);
+			kill_fasync(&fasync, SIGIO, POLL_IN);
 		}
 	}
+}
+
+static void credit_entropy_bits_safe(struct entropy_store *r, int nbits)
+{
+	const int nbits_max = (int)(~0U >> (ENTROPY_SHIFT + 1));
+
+	/* Cap the value to avoid overflows */
+	nbits = min(nbits,  nbits_max);
+	nbits = max(nbits, -nbits_max);
+
+	credit_entropy_bits(r, nbits);
+}
+
+/*********************************************************************
+ *
+ * CRNG using CHACHA20
+ *
+ *********************************************************************/
+
+#define CRNG_RESEED_INTERVAL (300*HZ)
+
+static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait);
+
+static void crng_initialize(struct crng_state *crng)
+{
+	int		i;
+	unsigned long	rv;
+
+	memcpy(&crng->state[0], "expand 32-byte k", 16);
+	if (crng == &primary_crng)
+		_extract_entropy(&input_pool, &crng->state[4],
+				 sizeof(__u32) * 12, 0);
+	else
+		get_random_bytes(&crng->state[4], sizeof(__u32) * 12);
+	for (i = 4; i < 16; i++) {
+		if (!arch_get_random_seed_long(&rv) &&
+		    !arch_get_random_long(&rv))
+			rv = random_get_entropy();
+		crng->state[i] ^= rv;
+	}
+	crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1;
+}
 
-	trace_credit_entropy_bits(r->name, nbits, entropy_count,
-				  r->entropy_total, _RET_IP_);
+static int crng_fast_load(const char *cp, size_t len)
+{
+	unsigned long flags;
+	char *p;
 
-	/* should we wake readers? */
-	if (r == &input_pool && entropy_count >= random_read_wakeup_thresh) {
-		wake_up_interruptible(&random_read_wait);
-		kill_fasync(&fasync, SIGIO, POLL_IN);
+	if (!spin_trylock_irqsave(&primary_crng.lock, flags))
+		return 0;
+	if (crng_ready()) {
+		spin_unlock_irqrestore(&primary_crng.lock, flags);
+		return 0;
+	}
+	p = (unsigned char *) &primary_crng.state[4];
+	while (len > 0 && crng_init_cnt < CRNG_INIT_CNT_THRESH) {
+		p[crng_init_cnt % CHACHA20_KEY_SIZE] ^= *cp;
+		cp++; crng_init_cnt++; len--;
+	}
+	if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) {
+		crng_init = 1;
+		wake_up_interruptible(&crng_init_wait);
+		pr_notice("random: fast init done\n");
 	}
+	spin_unlock_irqrestore(&primary_crng.lock, flags);
+	return 1;
+}
+
+static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
+{
+	unsigned long	flags;
+	int		i, num;
+	union {
+		__u8	block[CHACHA20_BLOCK_SIZE];
+		__u32	key[8];
+	} buf;
+
+	if (r) {
+		num = extract_entropy(r, &buf, 32, 16, 0);
+		if (num == 0)
+			return;
+	} else
+		extract_crng(buf.block);
+	spin_lock_irqsave(&primary_crng.lock, flags);
+	for (i = 0; i < 8; i++) {
+		unsigned long	rv;
+		if (!arch_get_random_seed_long(&rv) &&
+		    !arch_get_random_long(&rv))
+			rv = random_get_entropy();
+		crng->state[i+4] ^= buf.key[i] ^ rv;
+	}
+	memzero_explicit(&buf, sizeof(buf));
+	crng->init_time = jiffies;
+	if (crng == &primary_crng && crng_init < 2) {
+		crng_init = 2;
+		wake_up_interruptible(&crng_init_wait);
+		pr_notice("random: crng init done\n");
+	}
+	spin_unlock_irqrestore(&primary_crng.lock, flags);
+}
+
+static inline void crng_wait_ready(void)
+{
+	wait_event_interruptible(crng_init_wait, crng_ready());
+}
+
+static void extract_crng(__u8 out[CHACHA20_BLOCK_SIZE])
+{
+	unsigned long v, flags;
+	struct crng_state *crng = &primary_crng;
+
+	if (crng_init > 1 &&
+	    time_after(jiffies, crng->init_time + CRNG_RESEED_INTERVAL))
+		crng_reseed(crng, &input_pool);
+	spin_lock_irqsave(&crng->lock, flags);
+	if (arch_get_random_long(&v))
+		crng->state[14] ^= v;
+	chacha20_block(&crng->state[0], out);
+	if (crng->state[12] == 0)
+		crng->state[13]++;
+	spin_unlock_irqrestore(&crng->lock, flags);
+}
+
+static ssize_t extract_crng_user(void __user *buf, size_t nbytes)
+{
+	ssize_t ret = 0, i;
+	__u8 tmp[CHACHA20_BLOCK_SIZE];
+	int large_request = (nbytes > 256);
+
+	while (nbytes) {
+		if (large_request && need_resched()) {
+			if (signal_pending(current)) {
+				if (ret == 0)
+					ret = -ERESTARTSYS;
+				break;
+			}
+			schedule();
+		}
+
+		extract_crng(tmp);
+		i = min_t(int, nbytes, CHACHA20_BLOCK_SIZE);
+		if (copy_to_user(buf, tmp, i)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		nbytes -= i;
+		buf += i;
+		ret += i;
+	}
+
+	/* Wipe data just written to memory */
+	memzero_explicit(tmp, sizeof(tmp));
+
+	return ret;
 }
 
 /*********************************************************************
@@ -644,26 +858,29 @@ struct timer_rand_state {
 	unsigned dont_count_entropy:1;
 };
 
+#define INIT_TIMER_RAND_STATE { INITIAL_JIFFIES, };
+
 /*
- * Add device- or boot-specific data to the input and nonblocking
- * pools to help initialize them to unique values.
+ * Add device- or boot-specific data to the input pool to help
+ * initialize it.
  *
- * None of this adds any entropy, it is meant to avoid the
- * problem of the nonblocking pool having similar initial state
- * across largely identical devices.
+ * None of this adds any entropy; it is meant to avoid the problem of
+ * the entropy pool having similar initial state across largely
+ * identical devices.
  */
 void add_device_randomness(const void *buf, unsigned int size)
 {
-	unsigned long time = get_cycles() ^ jiffies;
+	unsigned long time = random_get_entropy() ^ jiffies;
+	unsigned long flags;
 
-	mix_pool_bytes(&input_pool, buf, size, NULL);
-	mix_pool_bytes(&input_pool, &time, sizeof(time), NULL);
-	mix_pool_bytes(&nonblocking_pool, buf, size, NULL);
-	mix_pool_bytes(&nonblocking_pool, &time, sizeof(time), NULL);
+	spin_lock_irqsave(&input_pool.lock, flags);
+	_mix_pool_bytes(&input_pool, buf, size);
+	_mix_pool_bytes(&input_pool, &time, sizeof(time));
+	spin_unlock_irqrestore(&input_pool.lock, flags);
 }
 EXPORT_SYMBOL(add_device_randomness);
 
-static struct timer_rand_state input_timer_state;
+static struct timer_rand_state input_timer_state = INIT_TIMER_RAND_STATE;
 
 /*
  * This function adds entropy to the entropy "pool" by using timing
@@ -677,6 +894,7 @@ static struct timer_rand_state input_timer_state;
  */
 static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 {
+	struct entropy_store	*r;
 	struct {
 		long jiffies;
 		unsigned cycles;
@@ -685,15 +903,12 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 	long delta, delta2, delta3;
 
 	preempt_disable();
-	/* if over the trickle threshold, use only 1 in 4096 samples */
-	if (input_pool.entropy_count > trickle_thresh &&
-	    ((__this_cpu_inc_return(trickle_count) - 1) & 0xfff))
-		goto out;
 
 	sample.jiffies = jiffies;
-	sample.cycles = get_cycles();
+	sample.cycles = random_get_entropy();
 	sample.num = num;
-	mix_pool_bytes(&input_pool, &sample, sizeof(sample), NULL);
+	r = &input_pool;
+	mix_pool_bytes(r, &sample, sizeof(sample));
 
 	/*
 	 * Calculate number of bits of randomness we probably added.
@@ -727,13 +942,10 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 		 * Round down by 1 bit on general principles,
 		 * and limit entropy entimate to 12 bits.
 		 */
-		credit_entropy_bits(&input_pool,
-				    min_t(int, fls(delta>>1), 11));
+		credit_entropy_bits(r, min_t(int, fls(delta>>1), 11));
 	}
-out:
 	preempt_enable();
 }
-
 void add_input_randomness(unsigned int type, unsigned int code,
 				 unsigned int value)
 {
@@ -743,7 +955,6 @@ void add_input_randomness(unsigned int type, unsigned int code,
 	if (value == last_value)
 		return;
 
-	DEBUG_ENT("input event\n");
 	last_value = value;
 	add_timer_randomness(&input_timer_state,
 			     (type << 4) ^ code ^ (code >> 4) ^ value);
@@ -752,47 +963,103 @@ EXPORT_SYMBOL_GPL(add_input_randomness);
 
 static DEFINE_PER_CPU(struct fast_pool, irq_randomness);
 
+#ifdef ADD_INTERRUPT_BENCH
+static unsigned long avg_cycles, avg_deviation;
+
+#define AVG_SHIFT 8     /* Exponential average factor k=1/256 */
+#define FIXED_1_2 (1 << (AVG_SHIFT-1))
+
+static void add_interrupt_bench(cycles_t start)
+{
+        long delta = random_get_entropy() - start;
+
+        /* Use a weighted moving average */
+        delta = delta - ((avg_cycles + FIXED_1_2) >> AVG_SHIFT);
+        avg_cycles += delta;
+        /* And average deviation */
+        delta = abs(delta) - ((avg_deviation + FIXED_1_2) >> AVG_SHIFT);
+        avg_deviation += delta;
+}
+#else
+#define add_interrupt_bench(x)
+#endif
+
+static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs)
+{
+	__u32 *ptr = (__u32 *) regs;
+
+	if (regs == NULL)
+		return 0;
+	if (f->reg_idx >= sizeof(struct pt_regs) / sizeof(__u32))
+		f->reg_idx = 0;
+	return *(ptr + f->reg_idx++);
+}
+
 void add_interrupt_randomness(int irq, int irq_flags)
 {
 	struct entropy_store	*r;
-	struct fast_pool	*fast_pool = &__get_cpu_var(irq_randomness);
+	struct fast_pool	*fast_pool = this_cpu_ptr(&irq_randomness);
 	struct pt_regs		*regs = get_irq_regs();
 	unsigned long		now = jiffies;
-	__u32			input[4], cycles = get_cycles();
-
-	input[0] = cycles ^ jiffies;
-	input[1] = irq;
-	if (regs) {
-		__u64 ip = instruction_pointer(regs);
-		input[2] = ip;
-		input[3] = ip >> 32;
+	cycles_t		cycles = random_get_entropy();
+	__u32			c_high, j_high;
+	__u64			ip;
+	unsigned long		seed;
+	int			credit = 0;
+
+	if (cycles == 0)
+		cycles = get_reg(fast_pool, regs);
+	c_high = (sizeof(cycles) > 4) ? cycles >> 32 : 0;
+	j_high = (sizeof(now) > 4) ? now >> 32 : 0;
+	fast_pool->pool[0] ^= cycles ^ j_high ^ irq;
+	fast_pool->pool[1] ^= now ^ c_high;
+	ip = regs ? instruction_pointer(regs) : _RET_IP_;
+	fast_pool->pool[2] ^= ip;
+	fast_pool->pool[3] ^= (sizeof(ip) > 4) ? ip >> 32 :
+		get_reg(fast_pool, regs);
+
+	fast_mix(fast_pool);
+	add_interrupt_bench(cycles);
+
+	if (!crng_ready()) {
+		if ((fast_pool->count >= 64) &&
+		    crng_fast_load((char *) fast_pool->pool,
+				   sizeof(fast_pool->pool))) {
+			fast_pool->count = 0;
+			fast_pool->last = now;
+		}
+		return;
 	}
 
-	fast_mix(fast_pool, input, sizeof(input));
-
-	if ((fast_pool->count & 1023) &&
+	if ((fast_pool->count < 64) &&
 	    !time_after(now, fast_pool->last + HZ))
 		return;
 
+	r = &input_pool;
+	if (!spin_trylock(&r->lock))
+		return;
+
 	fast_pool->last = now;
+	__mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool));
 
-	r = nonblocking_pool.initialized ? &input_pool : &nonblocking_pool;
-	__mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool), NULL);
 	/*
-	 * If we don't have a valid cycle counter, and we see
-	 * back-to-back timer interrupts, then skip giving credit for
-	 * any entropy.
+	 * If we have architectural seed generator, produce a seed and
+	 * add it to the pool.  For the sake of paranoia don't let the
+	 * architectural seed generator dominate the input from the
+	 * interrupt noise.
 	 */
-	if (cycles == 0) {
-		if (irq_flags & __IRQF_TIMER) {
-			if (fast_pool->last_timer_intr)
-				return;
-			fast_pool->last_timer_intr = 1;
-		} else
-			fast_pool->last_timer_intr = 0;
+	if (arch_get_random_seed_long(&seed)) {
+		__mix_pool_bytes(r, &seed, sizeof(seed));
+		credit = 1;
 	}
-	credit_entropy_bits(r, 1);
+	spin_unlock(&r->lock);
+
+	fast_pool->count = 0;
+
+	/* award one bit for the contents of the fast pool */
+	credit_entropy_bits(r, credit + 1);
 }
+EXPORT_SYMBOL_GPL(add_interrupt_randomness);
 
 #ifdef CONFIG_BLOCK
 void add_disk_randomness(struct gendisk *disk)
@@ -800,11 +1067,9 @@ void add_disk_randomness(struct gendisk *disk)
 	if (!disk || !disk->random)
 		return;
 	/* first major is 1, so we get >= 0x200 here */
-	DEBUG_ENT("disk event %d:%d\n",
-		  MAJOR(disk_devt(disk)), MINOR(disk_devt(disk)));
-
 	add_timer_randomness(disk->random, 0x100 + disk_devt(disk));
 }
+EXPORT_SYMBOL_GPL(add_disk_randomness);
 #endif
 
 /*********************************************************************
@@ -813,38 +1078,48 @@ void add_disk_randomness(struct gendisk *disk)
  *
  *********************************************************************/
 
-static ssize_t extract_entropy(struct entropy_store *r, void *buf,
-			       size_t nbytes, int min, int rsvd);
-
 /*
  * This utility inline function is responsible for transferring entropy
  * from the primary pool to the secondary extraction pool. We make
  * sure we pull enough for a 'catastrophic reseed'.
  */
+static void _xfer_secondary_pool(struct entropy_store *r, size_t nbytes);
 static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
 {
-	__u32	tmp[OUTPUT_POOL_WORDS];
+	if (!r->pull ||
+	    r->entropy_count >= (nbytes << (ENTROPY_SHIFT + 3)) ||
+	    r->entropy_count > r->poolinfo->poolfracbits)
+		return;
+
+	if (r->limit == 0 && random_min_urandom_seed) {
+		unsigned long now = jiffies;
 
-	if (r->pull && r->entropy_count < nbytes * 8 &&
-	    r->entropy_count < r->poolinfo->POOLBITS) {
-		/* If we're limited, always leave two wakeup worth's BITS */
-		int rsvd = r->limit ? 0 : random_read_wakeup_thresh/4;
-		int bytes = nbytes;
-
-		/* pull at least as many as BYTES as wakeup BITS */
-		bytes = max_t(int, bytes, random_read_wakeup_thresh / 8);
-		/* but never more than the buffer size */
-		bytes = min_t(int, bytes, sizeof(tmp));
-
-		DEBUG_ENT("going to reseed %s with %d bits "
-			  "(%d of %d requested)\n",
-			  r->name, bytes * 8, nbytes * 8, r->entropy_count);
-
-		bytes = extract_entropy(r->pull, tmp, bytes,
-					random_read_wakeup_thresh / 8, rsvd);
-		mix_pool_bytes(r, tmp, bytes, NULL);
-		credit_entropy_bits(r, bytes*8);
+		if (time_before(now,
+				r->last_pulled + random_min_urandom_seed * HZ))
+			return;
+		r->last_pulled = now;
 	}
+
+	_xfer_secondary_pool(r, nbytes);
+}
+
+static void _xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
+{
+	__u32	tmp[OUTPUT_POOL_WORDS];
+
+	/* For /dev/random's pool, always leave two wakeups' worth */
+	int rsvd_bytes = r->limit ? 0 : random_read_wakeup_bits / 4;
+	int bytes = nbytes;
+
+	/* pull at least as much as a wakeup */
+	bytes = max_t(int, bytes, random_read_wakeup_bits / 8);
+	/* but never more than the buffer size */
+	bytes = min_t(int, bytes, sizeof(tmp));
+
+	bytes = extract_entropy(r->pull, tmp, bytes,
+				random_read_wakeup_bits / 8, rsvd_bytes);
+	mix_pool_bytes(r, tmp, bytes);
+	credit_entropy_bits(r, bytes*8);
 }
 
 /*
@@ -859,66 +1134,86 @@ static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
  * Note: extract_entropy() assumes that .poolwords is a multiple of 16 words.
  */
 
+/*
+ * This function decides how many bytes to actually take from the
+ * given pool, and also debits the entropy count accordingly.
+ */
 static size_t account(struct entropy_store *r, size_t nbytes, int min,
 		      int reserved)
 {
-	unsigned long flags;
-
-	/* Hold lock while accounting */
-	spin_lock_irqsave(&r->lock, flags);
+	int entropy_count, orig;
+	size_t ibytes, nfrac;
 
-	BUG_ON(r->entropy_count > r->poolinfo->POOLBITS);
-	DEBUG_ENT("trying to extract %d bits from %s\n",
-		  nbytes * 8, r->name);
+	BUG_ON(r->entropy_count > r->poolinfo->poolfracbits);
 
 	/* Can we pull enough? */
-	if (r->entropy_count / 8 < min + reserved) {
-		nbytes = 0;
-	} else {
-		int entropy_count, orig;
 retry:
 		entropy_count = orig = ACCESS_ONCE(r->entropy_count);
+	ibytes = nbytes;
 		/* If limited, never pull more than available */
-		if (r->limit && nbytes + reserved >= entropy_count / 8)
-			nbytes = entropy_count/8 - reserved;
-
-		if (entropy_count / 8 >= nbytes + reserved) {
-			entropy_count -= nbytes*8;
-			if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
-				goto retry;
-		} else {
-			entropy_count = reserved;
-			if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
-				goto retry;
-		}
+	if (r->limit) {
+		int have_bytes = entropy_count >> (ENTROPY_SHIFT + 3);
 
-		if (entropy_count < random_write_wakeup_thresh) {
-			wake_up_interruptible(&random_write_wait);
-			kill_fasync(&fasync, SIGIO, POLL_OUT);
+		if ((have_bytes -= reserved) < 0)
+			have_bytes = 0;
+		ibytes = min_t(size_t, ibytes, have_bytes);
 		}
+	if (ibytes < min)
+		ibytes = 0;
+
+	if (unlikely(entropy_count < 0)) {
+		pr_warn("random: negative entropy count: pool %s count %d\n",
+			r->name, entropy_count);
+		WARN_ON(1);
+		entropy_count = 0;
 	}
+	nfrac = ibytes << (ENTROPY_SHIFT + 3);
+	if ((size_t) entropy_count > nfrac)
+		entropy_count -= nfrac;
+	else
+		entropy_count = 0;
 
-	DEBUG_ENT("debiting %d entropy credits from %s%s\n",
-		  nbytes * 8, r->name, r->limit ? "" : " (unlimited)");
+	if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
+		goto retry;
 
-	spin_unlock_irqrestore(&r->lock, flags);
+	if (ibytes &&
+	    (r->entropy_count >> ENTROPY_SHIFT) < random_write_wakeup_bits) {
+		wake_up_interruptible(&random_write_wait);
+		kill_fasync(&fasync, SIGIO, POLL_OUT);
+	}
 
-	return nbytes;
+	return ibytes;
 }
 
+/*
+ * This function does the actual extraction for extract_entropy and
+ * extract_entropy_user.
+ *
+ * Note: we assume that .poolwords is a multiple of 16 words.
+ */
 static void extract_buf(struct entropy_store *r, __u8 *out)
 {
 	int i;
 	union {
 		__u32 w[5];
-		unsigned long l[LONGS(EXTRACT_SIZE)];
+		unsigned long l[LONGS(20)];
 	} hash;
 	__u32 workspace[SHA_WORKSPACE_WORDS];
-	__u8 extract[64];
 	unsigned long flags;
 
-	/* Generate a hash across the pool, 16 words (512 bits) at a time */
+	/*
+	 * If we have an architectural hardware random number
+	 * generator, use it for SHA's initial vector
+	 */
 	sha_init(hash.w);
+	for (i = 0; i < LONGS(20); i++) {
+		unsigned long v;
+		if (!arch_get_random_long(&v))
+			break;
+		hash.l[i] = v;
+	}
+
+	/* Generate a hash across the pool, 16 words (512 bits) at a time */
 	spin_lock_irqsave(&r->lock, flags);
 	for (i = 0; i < r->poolinfo->poolwords; i += 16)
 		sha_transform(hash.w, (__u8 *)(r->pool + i), workspace);
@@ -932,15 +1227,9 @@ static void extract_buf(struct entropy_store *r, __u8 *out)
 	 * brute-forcing the feedback as hard as brute-forcing the
 	 * hash.
 	 */
-	__mix_pool_bytes(r, hash.w, sizeof(hash.w), extract);
+	__mix_pool_bytes(r, hash.w, sizeof(hash.w));
 	spin_unlock_irqrestore(&r->lock, flags);
 
-	/*
-	 * To avoid duplicates, we atomically extract a portion of the
-	 * pool while mixing, and hash one final time.
-	 */
-	sha_transform(hash.w, extract, workspace);
-	memzero_explicit(extract, sizeof(extract));
 	memzero_explicit(workspace, sizeof(workspace));
 
 	/*
@@ -952,37 +1241,21 @@ static void extract_buf(struct entropy_store *r, __u8 *out)
 	hash.w[1] ^= hash.w[4];
 	hash.w[2] ^= rol32(hash.w[2], 16);
 
-	/*
-	 * If we have a architectural hardware random number
-	 * generator, mix that in, too.
-	 */
-	for (i = 0; i < LONGS(EXTRACT_SIZE); i++) {
-		unsigned long v;
-		if (!arch_get_random_long(&v))
-			break;
-		hash.l[i] ^= v;
-	}
-
 	memcpy(out, &hash, EXTRACT_SIZE);
 	memzero_explicit(&hash, sizeof(hash));
 }
 
-static ssize_t extract_entropy(struct entropy_store *r, void *buf,
-				 size_t nbytes, int min, int reserved)
+static ssize_t _extract_entropy(struct entropy_store *r, void *buf,
+				size_t nbytes, int fips)
 {
 	ssize_t ret = 0, i;
 	__u8 tmp[EXTRACT_SIZE];
-
-	trace_extract_entropy(r->name, nbytes, r->entropy_count, _RET_IP_);
-	xfer_secondary_pool(r, nbytes);
-	nbytes = account(r, nbytes, min, reserved);
+	unsigned long flags;
 
 	while (nbytes) {
 		extract_buf(r, tmp);
 
-		if (fips_enabled) {
-			unsigned long flags;
-
+		if (fips) {
 			spin_lock_irqsave(&r->lock, flags);
 			if (!memcmp(tmp, r->last_data, EXTRACT_SIZE))
 				panic("Hardware RNG duplicated output!\n");
@@ -1002,6 +1275,48 @@ static ssize_t extract_entropy(struct entropy_store *r, void *buf,
 	return ret;
 }
 
+/*
+ * This function extracts randomness from the "entropy pool", and
+ * returns it in a buffer.
+ *
+ * The min parameter specifies the minimum amount we can pull before
+ * failing to avoid races that defeat catastrophic reseeding while the
+ * reserved parameter indicates how much entropy we must leave in the
+ * pool after each pull to avoid starving other readers.
+ */
+static ssize_t extract_entropy(struct entropy_store *r, void *buf,
+				 size_t nbytes, int min, int reserved)
+{
+	__u8 tmp[EXTRACT_SIZE];
+	unsigned long flags;
+
+	/* if last_data isn't primed, we need EXTRACT_SIZE extra bytes */
+	if (fips_enabled) {
+		spin_lock_irqsave(&r->lock, flags);
+		if (!r->last_data_init) {
+			r->last_data_init = 1;
+			spin_unlock_irqrestore(&r->lock, flags);
+			trace_extract_entropy(r->name, EXTRACT_SIZE,
+					      ENTROPY_BITS(r), _RET_IP_);
+			xfer_secondary_pool(r, EXTRACT_SIZE);
+			extract_buf(r, tmp);
+			spin_lock_irqsave(&r->lock, flags);
+			memcpy(r->last_data, tmp, EXTRACT_SIZE);
+		}
+		spin_unlock_irqrestore(&r->lock, flags);
+	}
+
+	trace_extract_entropy(r->name, nbytes, ENTROPY_BITS(r), _RET_IP_);
+	xfer_secondary_pool(r, nbytes);
+	nbytes = account(r, nbytes, min, reserved);
+
+	return _extract_entropy(r, buf, nbytes, fips_enabled);
+}
+
+/*
+ * This function extracts randomness from the "entropy pool", and
+ * returns it in a userspace buffer.
+ */
 static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf,
 				    size_t nbytes)
 {
@@ -1009,7 +1324,7 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf,
 	__u8 tmp[EXTRACT_SIZE];
 	int large_request = (nbytes > 256);
 
-	trace_extract_entropy_user(r->name, nbytes, r->entropy_count, _RET_IP_);
+	trace_extract_entropy_user(r->name, nbytes, ENTROPY_BITS(r), _RET_IP_);
 	xfer_secondary_pool(r, nbytes);
 	nbytes = account(r, nbytes, 0, 0);
 
@@ -1044,12 +1359,32 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf,
 /*
  * This function is the exported kernel interface.  It returns some
  * number of good random numbers, suitable for key generation, seeding
- * TCP sequence numbers, etc.  It does not use the hw random number
- * generator, if available; use get_random_bytes_arch() for that.
+ * TCP sequence numbers, etc.  It does not rely on the hardware random
+ * number generator.  For random bytes direct from the hardware RNG
+ * (when available), use get_random_bytes_arch().
  */
 void get_random_bytes(void *buf, int nbytes)
 {
-	extract_entropy(&nonblocking_pool, buf, nbytes, 0, 0);
+	__u8 tmp[CHACHA20_BLOCK_SIZE];
+
+#if DEBUG_RANDOM_BOOT > 0
+	if (!crng_ready())
+		printk(KERN_NOTICE "random: %pF get_random_bytes called "
+		       "with crng_init = %d\n", (void *) _RET_IP_, crng_init);
+#endif
+	trace_get_random_bytes(nbytes, _RET_IP_);
+
+	while (nbytes >= CHACHA20_BLOCK_SIZE) {
+		extract_crng(buf);
+		buf += CHACHA20_BLOCK_SIZE;
+		nbytes -= CHACHA20_BLOCK_SIZE;
+	}
+
+	if (nbytes > 0) {
+		extract_crng(tmp);
+		memcpy(buf, tmp, nbytes);
+		memzero_explicit(tmp, nbytes);
+	}
 }
 EXPORT_SYMBOL(get_random_bytes);
 
@@ -1081,7 +1416,7 @@ void get_random_bytes_arch(void *buf, int nbytes)
 	}
 
 	if (nbytes)
-		extract_entropy(&nonblocking_pool, p, nbytes, 0, 0);
+		get_random_bytes(p, nbytes);
 }
 EXPORT_SYMBOL(get_random_bytes_arch);
 
@@ -1101,15 +1436,15 @@ static void init_std_data(struct entropy_store *r)
 	ktime_t now = ktime_get_real();
 	unsigned long rv;
 
-	r->entropy_count = 0;
-	r->entropy_total = 0;
-	mix_pool_bytes(r, &now, sizeof(now), NULL);
-	for (i = r->poolinfo->POOLBYTES; i > 0; i -= sizeof(rv)) {
-		if (!arch_get_random_long(&rv))
-			break;
-		mix_pool_bytes(r, &rv, sizeof(rv), NULL);
+	r->last_pulled = jiffies;
+	mix_pool_bytes(r, &now, sizeof(now));
+	for (i = r->poolinfo->poolbytes; i > 0; i -= sizeof(rv)) {
+		if (!arch_get_random_seed_long(&rv) &&
+		    !arch_get_random_long(&rv))
+			rv = random_get_entropy();
+		mix_pool_bytes(r, &rv, sizeof(rv));
 	}
-	mix_pool_bytes(r, utsname(), sizeof(*(utsname())), NULL);
+	mix_pool_bytes(r, utsname(), sizeof(*(utsname())));
 }
 
 /*
@@ -1126,10 +1461,10 @@ static int rand_initialize(void)
 {
 	init_std_data(&input_pool);
 	init_std_data(&blocking_pool);
-	init_std_data(&nonblocking_pool);
+	crng_initialize(&primary_crng);
 	return 0;
 }
-module_init(rand_initialize);
+early_initcall(rand_initialize);
 
 #ifdef CONFIG_BLOCK
 void rand_initialize_disk(struct gendisk *disk)
@@ -1141,65 +1476,40 @@ void rand_initialize_disk(struct gendisk *disk)
 	 * source.
 	 */
 	state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL);
-	if (state)
+	if (state) {
+		state->last_time = INITIAL_JIFFIES;
 		disk->random = state;
+	}
 }
 #endif
 
 static ssize_t
 _random_read(int nonblock, char __user *buf, size_t nbytes)
 {
-	ssize_t n, retval = 0, count = 0;
+	ssize_t n;
 
 	if (nbytes == 0)
 		return 0;
 
-	while (nbytes > 0) {
-		n = nbytes;
-		if (n > SEC_XFER_SIZE)
-			n = SEC_XFER_SIZE;
-
-		DEBUG_ENT("reading %d bits\n", n*8);
+	nbytes = min_t(size_t, nbytes, SEC_XFER_SIZE);
+	while (1) {
+		n = extract_entropy_user(&blocking_pool, buf, nbytes);
+		if (n < 0)
+			return n;
 
-		n = extract_entropy_user(&blocking_pool, buf, n);
+		if (n > 0)
+			return n;
 
-		DEBUG_ENT("read got %d bits (%d still needed)\n",
-			  n*8, (nbytes-n)*8);
-
-		if (n == 0) {
-			if (nonblock) {
-				retval = -EAGAIN;
-				break;
-			}
-
-			DEBUG_ENT("sleeping?\n");
+		/* Pool is (near) empty.  Maybe wait and retry. */
+		if (nonblock)
+			return -EAGAIN;
 
 			wait_event_interruptible(random_read_wait,
-				input_pool.entropy_count >=
-						 random_read_wakeup_thresh);
-
-			DEBUG_ENT("awake\n");
-
-			if (signal_pending(current)) {
-				retval = -ERESTARTSYS;
-				break;
-			}
-
-			continue;
-		}
-
-		if (n < 0) {
-			retval = n;
-			break;
-		}
-		count += n;
-		buf += n;
-		nbytes -= n;
-		break;		/* This break makes the device work */
-				/* like a named pipe */
+			ENTROPY_BITS(&input_pool) >=
+			random_read_wakeup_bits);
+		if (signal_pending(current))
+			return -ERESTARTSYS;
 	}
-
-	return (count ? count : retval);
 }
 
 static ssize_t
@@ -1211,7 +1521,22 @@ random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 static ssize_t
 urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 {
-	return extract_entropy_user(&nonblocking_pool, buf, nbytes);
+	unsigned long flags;
+	static int maxwarn = 10;
+	int ret;
+
+	if (!crng_ready() && maxwarn > 0) {
+		maxwarn--;
+		printk(KERN_NOTICE "random: %s: uninitialized urandom read "
+		       "(%zd bytes read)\n",
+		       current->comm, nbytes);
+		spin_lock_irqsave(&primary_crng.lock, flags);
+		crng_init_cnt = 0;
+		spin_unlock_irqrestore(&primary_crng.lock, flags);
+	}
+	nbytes = min_t(size_t, nbytes, INT_MAX >> (ENTROPY_SHIFT + 3));
+	ret = extract_crng_user(buf, nbytes);
+	return ret;
 }
 
 static unsigned int
@@ -1222,9 +1547,9 @@ random_poll(struct file *file, poll_table * wait)
 	poll_wait(file, &random_read_wait, wait);
 	poll_wait(file, &random_write_wait, wait);
 	mask = 0;
-	if (input_pool.entropy_count >= random_read_wakeup_thresh)
+	if (ENTROPY_BITS(&input_pool) >= random_read_wakeup_bits)
 		mask |= POLLIN | POLLRDNORM;
-	if (input_pool.entropy_count < random_write_wakeup_thresh)
+	if (ENTROPY_BITS(&input_pool) < random_write_wakeup_bits)
 		mask |= POLLOUT | POLLWRNORM;
 	return mask;
 }
@@ -1252,7 +1577,7 @@ write_pool(struct entropy_store *r, const char __user *buffer, size_t count)
 		count -= bytes;
 		p += bytes;
 
-		mix_pool_bytes(r, buf, bytes, NULL);
+		mix_pool_bytes(r, buf, bytes);
 		cond_resched();
 	}
 
@@ -1264,10 +1589,7 @@ static ssize_t random_write(struct file *file, const char __user *buffer,
 {
 	size_t ret;
 
-	ret = write_pool(&blocking_pool, buffer, count);
-	if (ret)
-		return ret;
-	ret = write_pool(&nonblocking_pool, buffer, count);
+	ret = write_pool(&input_pool, buffer, count);
 	if (ret)
 		return ret;
 
@@ -1283,7 +1605,8 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 	switch (cmd) {
 	case RNDGETENTCNT:
 		/* inherently racy, no point locking */
-		if (put_user(input_pool.entropy_count, p))
+		ent_count = ENTROPY_BITS(&input_pool);
+		if (put_user(ent_count, p))
 			return -EFAULT;
 		return 0;
 	case RNDADDTOENTCNT:
@@ -1291,7 +1614,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 			return -EPERM;
 		if (get_user(ent_count, p))
 			return -EFAULT;
-		credit_entropy_bits(&input_pool, ent_count);
+		credit_entropy_bits_safe(&input_pool, ent_count);
 		return 0;
 	case RNDADDENTROPY:
 		if (!capable(CAP_SYS_ADMIN))
@@ -1306,14 +1629,18 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 				    size);
 		if (retval < 0)
 			return retval;
-		credit_entropy_bits(&input_pool, ent_count);
+		credit_entropy_bits_safe(&input_pool, ent_count);
 		return 0;
 	case RNDZAPENTCNT:
 	case RNDCLEARPOOL:
-		/* Clear the entropy pool counters. */
+		/*
+		 * Clear the entropy pool counters. We no longer clear
+		 * the entropy pool, as that's silly.
+		 */
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
-		rand_initialize();
+		input_pool.entropy_count = 0;
+		blocking_pool.entropy_count = 0;
 		return 0;
 	default:
 		return -EINVAL;
@@ -1354,11 +1681,10 @@ SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count,
 	if (flags & GRND_RANDOM)
 		return _random_read(flags & GRND_NONBLOCK, buf, count);
 
-	if (unlikely(nonblocking_pool.initialized == 0)) {
+	if (!crng_ready()) {
 		if (flags & GRND_NONBLOCK)
 			return -EAGAIN;
-		wait_event_interruptible(urandom_init_wait,
-					 nonblocking_pool.initialized);
+		crng_wait_ready();
 		if (signal_pending(current))
 			return -ERESTARTSYS;
 	}
@@ -1396,7 +1722,7 @@ EXPORT_SYMBOL(generate_random_uuid);
 #include <linux/sysctl.h>
 
 static int min_read_thresh = 8, min_write_thresh;
-static int max_read_thresh = INPUT_POOL_WORDS * 32;
+static int max_read_thresh = OUTPUT_POOL_WORDS * 32;
 static int max_write_thresh = INPUT_POOL_WORDS * 32;
 static char sysctl_bootid[16];
 
@@ -1454,7 +1780,7 @@ ctl_table random_table[] = {
 	},
 	{
 		.procname	= "read_wakeup_threshold",
-		.data		= &random_read_wakeup_thresh,
+		.data		= &random_read_wakeup_bits,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
@@ -1463,7 +1789,7 @@ ctl_table random_table[] = {
 	},
 	{
 		.procname	= "write_wakeup_threshold",
-		.data		= &random_write_wakeup_thresh,
+		.data		= &random_write_wakeup_bits,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
@@ -1511,13 +1837,14 @@ unsigned int get_random_int(void)
 
 	hash = get_cpu_var(get_random_int_hash);
 
-	hash[0] += current->pid + jiffies + get_cycles();
+	hash[0] += current->pid + jiffies + random_get_entropy();
 	md5_transform(hash, random_int_secret);
 	ret = hash[0];
 	put_cpu_var(get_random_int_hash);
 
 	return ret;
 }
+EXPORT_SYMBOL(get_random_int);
 
 /*
  * Same as get_random_int(), but returns unsigned long.
@@ -1529,7 +1856,7 @@ unsigned long get_random_long(void)
 
 	hash = get_cpu_var(get_random_int_hash);
 
-	hash[0] += current->pid + jiffies + get_cycles();
+	hash[0] += current->pid + jiffies + random_get_entropy();
 	md5_transform(hash, random_int_secret);
 	ret = *(unsigned long *)hash;
 	put_cpu_var(get_random_int_hash);
@@ -1556,3 +1883,28 @@ randomize_range(unsigned long start, unsigned long end, unsigned long len)
 		return 0;
 	return PAGE_ALIGN(get_random_int() % range + start);
 }
+
+/* Interface for in-kernel drivers of true hardware RNGs.
+ * Those devices may produce endless random bits and will be throttled
+ * when our pool is full.
+ */
+void add_hwgenerator_randomness(const char *buffer, size_t count,
+				size_t entropy)
+{
+	struct entropy_store *poolp = &input_pool;
+
+	if (!crng_ready()) {
+		crng_fast_load(buffer, count);
+		return;
+	}
+
+	/* Suspend writing if we're above the trickle threshold.
+	 * We'll be woken up again once below random_write_wakeup_bits,
+	 * or when the calling thread is about to terminate.
+	 */
+	wait_event_interruptible(random_write_wait, kthread_should_stop() ||
+			ENTROPY_BITS(&input_pool) <= random_write_wakeup_bits);
+	mix_pool_bytes(poolp, buffer, count);
+	credit_entropy_bits(poolp, entropy);
+}
+EXPORT_SYMBOL_GPL(add_hwgenerator_randomness);
diff --git a/fs/file.c b/fs/file.c
index 60d96cfaeab..492767a358e 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -514,7 +514,7 @@ struct files_struct init_files = {
 		.open_fds	= init_files.open_fds_init,
 		.user		= &init_files.user_array[0],
 	},
-	.file_lock	= __SPIN_LOCK_UNLOCKED(init_task.file_lock),
+	.file_lock	= __SPIN_LOCK_UNLOCKED(init_files.file_lock),
 };
 
 /*
diff --git a/include/crypto/chacha20.h b/include/crypto/chacha20.h
new file mode 100644
index 00000000000..20d20f681a7
--- /dev/null
+++ b/include/crypto/chacha20.h
@@ -0,0 +1,26 @@
+/*
+ * Common values for the ChaCha20 algorithm
+ */
+
+#ifndef _CRYPTO_CHACHA20_H
+#define _CRYPTO_CHACHA20_H
+
+#include <linux/types.h>
+#include <linux/crypto.h>
+
+#define CHACHA20_IV_SIZE	16
+#define CHACHA20_KEY_SIZE	32
+#define CHACHA20_BLOCK_SIZE	64
+
+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);
+int crypto_chacha20_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+			  struct scatterlist *src, unsigned int nbytes);
+
+#endif
diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h
index b4b0eef5fdd..3f075ff0041 100644
--- a/include/linux/hw_random.h
+++ b/include/linux/hw_random.h
@@ -47,5 +47,7 @@ struct hwrng {
 extern int hwrng_register(struct hwrng *rng);
 /** Unregister a Hardware Random Number Generator driver. */
 extern void hwrng_unregister(struct hwrng *rng);
+/** Feed random bits into the pool. */
+extern void add_hwgenerator_randomness(const char *buffer, size_t count, size_t entropy);
 
 #endif /* LINUX_HWRANDOM_H_ */
diff --git a/include/linux/idr.h b/include/linux/idr.h
index 52a9da29529..dffed8f9b07 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -136,7 +136,7 @@ struct ida {
 	struct ida_bitmap	*free_bitmap;
 };
 
-#define IDA_INIT(name)		{ .idr = IDR_INIT(name), .free_bitmap = NULL, }
+#define IDA_INIT(name)		{ .idr = IDR_INIT((name).idr), .free_bitmap = NULL, }
 #define DEFINE_IDA(name)	struct ida name = IDA_INIT(name)
 
 int ida_pre_get(struct ida *ida, gfp_t gfp_mask);
diff --git a/include/linux/random.h b/include/linux/random.h
index f604f194bbf..d23daedadfe 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -123,6 +123,22 @@ static inline int arch_get_random_int(unsigned int *v)
 {
 	return 0;
 }
+static inline int arch_has_random(void)
+{
+	return 0;
+}
+static inline int arch_get_random_seed_long(unsigned long *v)
+{
+	return 0;
+}
+static inline int arch_get_random_seed_int(unsigned int *v)
+{
+	return 0;
+}
+static inline int arch_has_random_seed(void)
+{
+	return 0;
+}
 #endif
 
 #endif /* __KERNEL___ */
diff --git a/include/linux/timex.h b/include/linux/timex.h
index 99bc88b1fc0..a647f366189 100644
--- a/include/linux/timex.h
+++ b/include/linux/timex.h
@@ -173,6 +173,20 @@ struct timex {
 
 #include <asm/timex.h>
 
+#ifndef random_get_entropy
+/*
+ * The random_get_entropy() function is used by the /dev/random driver
+ * in order to extract entropy via the relative unpredictability of
+ * when an interrupt takes places versus a high speed, fine-grained
+ * timing source or cycle counter.  Since it will be occurred on every
+ * single interrupt, it must have a very low cost/overhead.
+ *
+ * By default we use get_cycles() for this purpose, but individual
+ * architectures may override this in their asm/timex.h header file.
+ */
+#define random_get_entropy()	get_cycles()
+#endif
+
 /*
  * SHIFT_PLL is used as a dampening factor to define how much we
  * adjust the frequency correction for a given offset in PLL mode.
diff --git a/lib/Makefile b/lib/Makefile
index c9526d2fe7b..8218680c4e2 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -10,7 +10,7 @@ endif
 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 prio_tree.o \
-	 sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
+	 sha1.o chacha20.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
 	 proportions.o prio_heap.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o memory_alloc.o
 
diff --git a/lib/chacha20.c b/lib/chacha20.c
new file mode 100644
index 00000000000..250ceed9ec9
--- /dev/null
+++ b/lib/chacha20.c
@@ -0,0 +1,79 @@
+/*
+ * 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);