Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit a8786d54 authored by Jason A. Donenfeld's avatar Jason A. Donenfeld Committed by Greg Kroah-Hartman
Browse files

random: group crng functions



commit 3655adc7089da4f8ca74cec8fcef73ea5101430e upstream.

This pulls all of the crng-focused functions into the second labeled
section.

No functional changes.

Cc: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: default avatarDominik Brodowski <linux@dominikbrodowski.net>
Reviewed-by: default avatarEric Biggers <ebiggers@google.com>
Signed-off-by: default avatarJason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: default avatarGreg Kroah-Hartman <gregkh@linuxfoundation.org>
parent c12dfec1
Loading
Loading
Loading
Loading
+442 −414
Original line number Diff line number Diff line
@@ -380,122 +380,27 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller, void
}


enum {
	POOL_BITS = BLAKE2S_HASH_SIZE * 8,
	POOL_MIN_BITS = POOL_BITS /* No point in settling for less. */
};

/*
 * Static global variables
 */
static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);

static int crng_init_cnt = 0;

/**********************************************************************
/*********************************************************************
 *
 * OS independent entropy store.   Here are the functions which handle
 * storing entropy in an entropy pool.
 * Fast key erasure RNG, the "crng".
 *
 **********************************************************************/

static struct {
	struct blake2s_state hash;
	spinlock_t lock;
	unsigned int entropy_count;
} input_pool = {
	.hash.h = { BLAKE2S_IV0 ^ (0x01010000 | BLAKE2S_HASH_SIZE),
		    BLAKE2S_IV1, BLAKE2S_IV2, BLAKE2S_IV3, BLAKE2S_IV4,
		    BLAKE2S_IV5, BLAKE2S_IV6, BLAKE2S_IV7 },
	.hash.outlen = BLAKE2S_HASH_SIZE,
	.lock = __SPIN_LOCK_UNLOCKED(input_pool.lock),
};

static void extract_entropy(void *buf, size_t nbytes);
static bool drain_entropy(void *buf, size_t nbytes);

static void crng_reseed(void);

/*
 * This function adds bytes into the entropy "pool".  It does not
 * update the entropy estimate.  The caller should call
 * credit_entropy_bits if this is appropriate.
 */
static void _mix_pool_bytes(const void *in, size_t nbytes)
{
	blake2s_update(&input_pool.hash, in, nbytes);
}

static void mix_pool_bytes(const void *in, size_t nbytes)
{
	unsigned long flags;

	spin_lock_irqsave(&input_pool.lock, flags);
	_mix_pool_bytes(in, nbytes);
	spin_unlock_irqrestore(&input_pool.lock, flags);
}

struct fast_pool {
	union {
		u32 pool32[4];
		u64 pool64[2];
	};
	unsigned long last;
	u16 reg_idx;
	u8 count;
};

/*
 * This is a fast mixing routine used by the interrupt randomness
 * 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(u32 pool[4])
{
	u32 a = pool[0],	b = pool[1];
	u32 c = pool[2],	d = pool[3];

	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;

	pool[0] = a;  pool[1] = b;
	pool[2] = c;  pool[3] = d;
}

static void credit_entropy_bits(size_t nbits)
{
	unsigned int entropy_count, orig, add;

	if (!nbits)
		return;

	add = min_t(size_t, nbits, POOL_BITS);

	do {
		orig = READ_ONCE(input_pool.entropy_count);
		entropy_count = min_t(unsigned int, POOL_BITS, orig + add);
	} while (cmpxchg(&input_pool.entropy_count, orig, entropy_count) != orig);

	if (crng_init < 2 && entropy_count >= POOL_MIN_BITS)
		crng_reseed();
}

/*********************************************************************
 * These functions expand entropy from the entropy extractor into
 * long streams for external consumption using the "fast key erasure"
 * RNG described at <https://blog.cr.yp.to/20170723-random.html>.
 *
 * There are a few exported interfaces for use by other drivers:
 *
 *	void get_random_bytes(void *buf, size_t nbytes)
 *	u32 get_random_u32()
 *	u64 get_random_u64()
 *	unsigned int get_random_int()
 *	unsigned long get_random_long()
 *
 * CRNG using CHACHA20
 * These interfaces will return the requested number of random bytes
 * into the given buffer or as a return value. This is equivalent to
 * a read from /dev/urandom. The integer family of functions may be
 * higher performance for one-off random integers, because they do a
 * bit of buffering.
 *
 *********************************************************************/

@@ -522,70 +427,14 @@ static DEFINE_PER_CPU(struct crng, crngs) = {
	.generation = ULONG_MAX
};

/*
 * crng_fast_load() can be called by code in the interrupt service
 * path.  So we can't afford to dilly-dally. Returns the number of
 * bytes processed from cp.
 */
static size_t crng_fast_load(const void *cp, size_t len)
{
	unsigned long flags;
	const u8 *src = (const u8 *)cp;
	size_t ret = 0;

	if (!spin_trylock_irqsave(&base_crng.lock, flags))
		return 0;
	if (crng_init != 0) {
		spin_unlock_irqrestore(&base_crng.lock, flags);
		return 0;
	}
	while (len > 0 && crng_init_cnt < CRNG_INIT_CNT_THRESH) {
		base_crng.key[crng_init_cnt % sizeof(base_crng.key)] ^= *src;
		src++; crng_init_cnt++; len--; ret++;
	}
	if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) {
		++base_crng.generation;
		crng_init = 1;
	}
	spin_unlock_irqrestore(&base_crng.lock, flags);
	if (crng_init == 1)
		pr_notice("fast init done\n");
	return ret;
}
/* Used by crng_reseed() to extract a new seed from the input pool. */
static bool drain_entropy(void *buf, size_t nbytes);

/*
 * crng_slow_load() is called by add_device_randomness, which has two
 * attributes.  (1) We can't trust the buffer passed to it is
 * guaranteed to be unpredictable (so it might not have any entropy at
 * all), and (2) it doesn't have the performance constraints of
 * crng_fast_load().
 *
 * So, we simply hash the contents in with the current key. Finally,
 * we do *not* advance crng_init_cnt since buffer we may get may be
 * something like a fixed DMI table (for example), which might very
 * well be unique to the machine, but is otherwise unvarying.
 * This extracts a new crng key from the input pool, but only if there is a
 * sufficient amount of entropy available, in order to mitigate bruteforcing
 * of newly added bits.
 */
static void crng_slow_load(const void *cp, size_t len)
{
	unsigned long flags;
	struct blake2s_state hash;

	blake2s_init(&hash, sizeof(base_crng.key));

	if (!spin_trylock_irqsave(&base_crng.lock, flags))
		return;
	if (crng_init != 0) {
		spin_unlock_irqrestore(&base_crng.lock, flags);
		return;
	}

	blake2s_update(&hash, base_crng.key, sizeof(base_crng.key));
	blake2s_update(&hash, cp, len);
	blake2s_final(&hash, base_crng.key);

	spin_unlock_irqrestore(&base_crng.lock, flags);
}

static void crng_reseed(void)
{
	unsigned long flags;
@@ -635,13 +484,11 @@ static void crng_reseed(void)
}

/*
 * The general form here is based on a "fast key erasure RNG" from
 * <https://blog.cr.yp.to/20170723-random.html>. It generates a ChaCha
 * block using the provided key, and then immediately overwites that
 * key with half the block. It returns the resultant ChaCha state to the
 * user, along with the second half of the block containing 32 bytes of
 * random data that may be used; random_data_len may not be greater than
 * 32.
 * This generates a ChaCha block using the provided key, and then
 * immediately overwites that key with half the block. It returns
 * the resultant ChaCha state to the user, along with the second
 * half of the block containing 32 bytes of random data that may
 * be used; random_data_len may not be greater than 32.
 */
static void crng_fast_key_erasure(u8 key[CHACHA_KEY_SIZE],
				  u32 chacha_state[CHACHA_BLOCK_SIZE / sizeof(u32)],
@@ -728,51 +575,430 @@ static void crng_make_state(u32 chacha_state[CHACHA_BLOCK_SIZE / sizeof(u32)],
	local_irq_restore(flags);
}

static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes)
/*
 * This function is for crng_init == 0 only.
 *
 * crng_fast_load() can be called by code in the interrupt service
 * path.  So we can't afford to dilly-dally. Returns the number of
 * bytes processed from cp.
 */
static size_t crng_fast_load(const void *cp, size_t len)
{
	static int crng_init_cnt = 0;
	unsigned long flags;
	const u8 *src = (const u8 *)cp;
	size_t ret = 0;

	if (!spin_trylock_irqsave(&base_crng.lock, flags))
		return 0;
	if (crng_init != 0) {
		spin_unlock_irqrestore(&base_crng.lock, flags);
		return 0;
	}
	while (len > 0 && crng_init_cnt < CRNG_INIT_CNT_THRESH) {
		base_crng.key[crng_init_cnt % sizeof(base_crng.key)] ^= *src;
		src++; crng_init_cnt++; len--; ret++;
	}
	if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) {
		++base_crng.generation;
		crng_init = 1;
	}
	spin_unlock_irqrestore(&base_crng.lock, flags);
	if (crng_init == 1)
		pr_notice("fast init done\n");
	return ret;
}

/*
 * This function is for crng_init == 0 only.
 *
 * crng_slow_load() is called by add_device_randomness, which has two
 * attributes.  (1) We can't trust the buffer passed to it is
 * guaranteed to be unpredictable (so it might not have any entropy at
 * all), and (2) it doesn't have the performance constraints of
 * crng_fast_load().
 *
 * So, we simply hash the contents in with the current key. Finally,
 * we do *not* advance crng_init_cnt since buffer we may get may be
 * something like a fixed DMI table (for example), which might very
 * well be unique to the machine, but is otherwise unvarying.
 */
static void crng_slow_load(const void *cp, size_t len)
{
	unsigned long flags;
	struct blake2s_state hash;

	blake2s_init(&hash, sizeof(base_crng.key));

	if (!spin_trylock_irqsave(&base_crng.lock, flags))
		return;
	if (crng_init != 0) {
		spin_unlock_irqrestore(&base_crng.lock, flags);
		return;
	}

	blake2s_update(&hash, base_crng.key, sizeof(base_crng.key));
	blake2s_update(&hash, cp, len);
	blake2s_final(&hash, base_crng.key);

	spin_unlock_irqrestore(&base_crng.lock, flags);
}

static void _get_random_bytes(void *buf, size_t nbytes)
{
	bool large_request = nbytes > 256;
	ssize_t ret = 0;
	size_t len;
	u32 chacha_state[CHACHA_BLOCK_SIZE / sizeof(u32)];
	u8 output[CHACHA_BLOCK_SIZE];
	u8 tmp[CHACHA_BLOCK_SIZE];
	size_t len;

	if (!nbytes)
		return;

	len = min_t(size_t, 32, nbytes);
	crng_make_state(chacha_state, buf, len);
	nbytes -= len;
	buf += len;

	while (nbytes) {
		if (nbytes < CHACHA_BLOCK_SIZE) {
			chacha20_block(chacha_state, tmp);
			memcpy(buf, tmp, nbytes);
			memzero_explicit(tmp, sizeof(tmp));
			break;
		}

		chacha20_block(chacha_state, buf);
		if (unlikely(chacha_state[12] == 0))
			++chacha_state[13];
		nbytes -= CHACHA_BLOCK_SIZE;
		buf += CHACHA_BLOCK_SIZE;
	}

	memzero_explicit(chacha_state, sizeof(chacha_state));
}

/*
 * 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 rely on the hardware random
 * number generator.  For random bytes direct from the hardware RNG
 * (when available), use get_random_bytes_arch(). In order to ensure
 * that the randomness provided by this function is okay, the function
 * wait_for_random_bytes() should be called and return 0 at least once
 * at any point prior.
 */
void get_random_bytes(void *buf, size_t nbytes)
{
	static void *previous;

	warn_unseeded_randomness(&previous);
	_get_random_bytes(buf, nbytes);
}
EXPORT_SYMBOL(get_random_bytes);

static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes)
{
	bool large_request = nbytes > 256;
	ssize_t ret = 0;
	size_t len;
	u32 chacha_state[CHACHA_BLOCK_SIZE / sizeof(u32)];
	u8 output[CHACHA_BLOCK_SIZE];

	if (!nbytes)
		return 0;

	len = min_t(size_t, 32, nbytes);
	crng_make_state(chacha_state, output, len);

	if (copy_to_user(buf, output, len))
		return -EFAULT;
	nbytes -= len;
	buf += len;
	ret += len;

	while (nbytes) {
		if (large_request && need_resched()) {
			if (signal_pending(current))
				break;
			schedule();
		}

		chacha20_block(chacha_state, output);
		if (unlikely(chacha_state[12] == 0))
			++chacha_state[13];

		len = min_t(size_t, nbytes, CHACHA_BLOCK_SIZE);
		if (copy_to_user(buf, output, len)) {
			ret = -EFAULT;
			break;
		}

		nbytes -= len;
		buf += len;
		ret += len;
	}

	memzero_explicit(chacha_state, sizeof(chacha_state));
	memzero_explicit(output, sizeof(output));
	return ret;
}

/*
 * Batched entropy returns random integers. The quality of the random
 * number is good as /dev/urandom. In order to ensure that the randomness
 * provided by this function is okay, the function wait_for_random_bytes()
 * should be called and return 0 at least once at any point prior.
 */
struct batched_entropy {
	union {
		/*
		 * We make this 1.5x a ChaCha block, so that we get the
		 * remaining 32 bytes from fast key erasure, plus one full
		 * block from the detached ChaCha state. We can increase
		 * the size of this later if needed so long as we keep the
		 * formula of (integer_blocks + 0.5) * CHACHA_BLOCK_SIZE.
		 */
		u64 entropy_u64[CHACHA_BLOCK_SIZE * 3 / (2 * sizeof(u64))];
		u32 entropy_u32[CHACHA_BLOCK_SIZE * 3 / (2 * sizeof(u32))];
	};
	unsigned long generation;
	unsigned int position;
};


static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64) = {
	.position = UINT_MAX
};

u64 get_random_u64(void)
{
	u64 ret;
	unsigned long flags;
	struct batched_entropy *batch;
	static void *previous;
	unsigned long next_gen;

	warn_unseeded_randomness(&previous);

	local_irq_save(flags);
	batch = raw_cpu_ptr(&batched_entropy_u64);

	next_gen = READ_ONCE(base_crng.generation);
	if (batch->position >= ARRAY_SIZE(batch->entropy_u64) ||
	    next_gen != batch->generation) {
		_get_random_bytes(batch->entropy_u64, sizeof(batch->entropy_u64));
		batch->position = 0;
		batch->generation = next_gen;
	}

	ret = batch->entropy_u64[batch->position];
	batch->entropy_u64[batch->position] = 0;
	++batch->position;
	local_irq_restore(flags);
	return ret;
}
EXPORT_SYMBOL(get_random_u64);

static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32) = {
	.position = UINT_MAX
};

u32 get_random_u32(void)
{
	u32 ret;
	unsigned long flags;
	struct batched_entropy *batch;
	static void *previous;
	unsigned long next_gen;

	warn_unseeded_randomness(&previous);

	local_irq_save(flags);
	batch = raw_cpu_ptr(&batched_entropy_u32);

	next_gen = READ_ONCE(base_crng.generation);
	if (batch->position >= ARRAY_SIZE(batch->entropy_u32) ||
	    next_gen != batch->generation) {
		_get_random_bytes(batch->entropy_u32, sizeof(batch->entropy_u32));
		batch->position = 0;
		batch->generation = next_gen;
	}

	ret = batch->entropy_u32[batch->position];
	batch->entropy_u32[batch->position] = 0;
	++batch->position;
	local_irq_restore(flags);
	return ret;
}
EXPORT_SYMBOL(get_random_u32);

/**
 * randomize_page - Generate a random, page aligned address
 * @start:	The smallest acceptable address the caller will take.
 * @range:	The size of the area, starting at @start, within which the
 *		random address must fall.
 *
 * If @start + @range would overflow, @range is capped.
 *
 * NOTE: Historical use of randomize_range, which this replaces, presumed that
 * @start was already page aligned.  We now align it regardless.
 *
 * Return: A page aligned address within [start, start + range).  On error,
 * @start is returned.
 */
unsigned long randomize_page(unsigned long start, unsigned long range)
{
	if (!PAGE_ALIGNED(start)) {
		range -= PAGE_ALIGN(start) - start;
		start = PAGE_ALIGN(start);
	}

	if (start > ULONG_MAX - range)
		range = ULONG_MAX - start;

	range >>= PAGE_SHIFT;

	if (range == 0)
		return start;

	return start + (get_random_long() % range << PAGE_SHIFT);
}

/*
 * This function will use the architecture-specific hardware random
 * number generator if it is available. It is not recommended for
 * use. Use get_random_bytes() instead. It returns the number of
 * bytes filled in.
 */
size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes)
{
	size_t left = nbytes;
	u8 *p = buf;

	while (left) {
		unsigned long v;
		size_t chunk = min_t(size_t, left, sizeof(unsigned long));

		if (!arch_get_random_long(&v))
			break;

		memcpy(p, &v, chunk);
		p += chunk;
		left -= chunk;
	}

	return nbytes - left;
}
EXPORT_SYMBOL(get_random_bytes_arch);

enum {
	POOL_BITS = BLAKE2S_HASH_SIZE * 8,
	POOL_MIN_BITS = POOL_BITS /* No point in settling for less. */
};

/*
 * Static global variables
 */
static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);

/**********************************************************************
 *
 * OS independent entropy store.   Here are the functions which handle
 * storing entropy in an entropy pool.
 *
 **********************************************************************/

static struct {
	struct blake2s_state hash;
	spinlock_t lock;
	unsigned int entropy_count;
} input_pool = {
	.hash.h = { BLAKE2S_IV0 ^ (0x01010000 | BLAKE2S_HASH_SIZE),
		    BLAKE2S_IV1, BLAKE2S_IV2, BLAKE2S_IV3, BLAKE2S_IV4,
		    BLAKE2S_IV5, BLAKE2S_IV6, BLAKE2S_IV7 },
	.hash.outlen = BLAKE2S_HASH_SIZE,
	.lock = __SPIN_LOCK_UNLOCKED(input_pool.lock),
};

static void extract_entropy(void *buf, size_t nbytes);
static bool drain_entropy(void *buf, size_t nbytes);

static void crng_reseed(void);

/*
 * This function adds bytes into the entropy "pool".  It does not
 * update the entropy estimate.  The caller should call
 * credit_entropy_bits if this is appropriate.
 */
static void _mix_pool_bytes(const void *in, size_t nbytes)
{
	blake2s_update(&input_pool.hash, in, nbytes);
}

static void mix_pool_bytes(const void *in, size_t nbytes)
{
	unsigned long flags;

	spin_lock_irqsave(&input_pool.lock, flags);
	_mix_pool_bytes(in, nbytes);
	spin_unlock_irqrestore(&input_pool.lock, flags);
}

struct fast_pool {
	union {
		u32 pool32[4];
		u64 pool64[2];
	};
	unsigned long last;
	u16 reg_idx;
	u8 count;
};

/*
 * This is a fast mixing routine used by the interrupt randomness
 * 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(u32 pool[4])
{
	u32 a = pool[0],	b = pool[1];
	u32 c = pool[2],	d = pool[3];

	if (!nbytes)
		return 0;
	a += b;			c += d;
	b = rol32(b, 6);	d = rol32(d, 27);
	d ^= a;			b ^= c;

	len = min_t(size_t, 32, nbytes);
	crng_make_state(chacha_state, output, len);
	a += b;			c += d;
	b = rol32(b, 16);	d = rol32(d, 14);
	d ^= a;			b ^= c;

	if (copy_to_user(buf, output, len))
		return -EFAULT;
	nbytes -= len;
	buf += len;
	ret += len;
	a += b;			c += d;
	b = rol32(b, 6);	d = rol32(d, 27);
	d ^= a;			b ^= c;

	while (nbytes) {
		if (large_request && need_resched()) {
			if (signal_pending(current))
				break;
			schedule();
	a += b;			c += d;
	b = rol32(b, 16);	d = rol32(d, 14);
	d ^= a;			b ^= c;

	pool[0] = a;  pool[1] = b;
	pool[2] = c;  pool[3] = d;
}

		chacha20_block(chacha_state, output);
		if (unlikely(chacha_state[12] == 0))
			++chacha_state[13];
static void credit_entropy_bits(size_t nbits)
{
	unsigned int entropy_count, orig, add;

		len = min_t(size_t, nbytes, CHACHA_BLOCK_SIZE);
		if (copy_to_user(buf, output, len)) {
			ret = -EFAULT;
			break;
		}
	if (!nbits)
		return;

		nbytes -= len;
		buf += len;
		ret += len;
	}
	add = min_t(size_t, nbits, POOL_BITS);

	memzero_explicit(chacha_state, sizeof(chacha_state));
	memzero_explicit(output, sizeof(output));
	return ret;
	do {
		orig = READ_ONCE(input_pool.entropy_count);
		entropy_count = min_t(unsigned int, POOL_BITS, orig + add);
	} while (cmpxchg(&input_pool.entropy_count, orig, entropy_count) != orig);

	if (crng_init < 2 && entropy_count >= POOL_MIN_BITS)
		crng_reseed();
}

/*********************************************************************
@@ -1042,57 +1268,6 @@ static bool drain_entropy(void *buf, size_t nbytes)
	return true;
}

/*
 * 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 rely on the hardware random
 * number generator.  For random bytes direct from the hardware RNG
 * (when available), use get_random_bytes_arch(). In order to ensure
 * that the randomness provided by this function is okay, the function
 * wait_for_random_bytes() should be called and return 0 at least once
 * at any point prior.
 */
static void _get_random_bytes(void *buf, size_t nbytes)
{
	u32 chacha_state[CHACHA_BLOCK_SIZE / sizeof(u32)];
	u8 tmp[CHACHA_BLOCK_SIZE];
	size_t len;

	if (!nbytes)
		return;

	len = min_t(size_t, 32, nbytes);
	crng_make_state(chacha_state, buf, len);
	nbytes -= len;
	buf += len;

	while (nbytes) {
		if (nbytes < CHACHA_BLOCK_SIZE) {
			chacha20_block(chacha_state, tmp);
			memcpy(buf, tmp, nbytes);
			memzero_explicit(tmp, sizeof(tmp));
			break;
		}

		chacha20_block(chacha_state, buf);
		if (unlikely(chacha_state[12] == 0))
			++chacha_state[13];
		nbytes -= CHACHA_BLOCK_SIZE;
		buf += CHACHA_BLOCK_SIZE;
	}

	memzero_explicit(chacha_state, sizeof(chacha_state));
}

void get_random_bytes(void *buf, size_t nbytes)
{
	static void *previous;

	warn_unseeded_randomness(&previous);
	_get_random_bytes(buf, nbytes);
}
EXPORT_SYMBOL(get_random_bytes);

/*
 * Each time the timer fires, we expect that we got an unpredictable
 * jump in the cycle counter. Even if the timer is running on another
@@ -1142,33 +1317,6 @@ static void try_to_generate_entropy(void)
	mix_pool_bytes(&stack.now, sizeof(stack.now));
}

/*
 * This function will use the architecture-specific hardware random
 * number generator if it is available. It is not recommended for
 * use. Use get_random_bytes() instead. It returns the number of
 * bytes filled in.
 */
size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes)
{
	size_t left = nbytes;
	u8 *p = buf;

	while (left) {
		unsigned long v;
		size_t chunk = min_t(size_t, left, sizeof(unsigned long));

		if (!arch_get_random_long(&v))
			break;

		memcpy(p, &v, chunk);
		p += chunk;
		left -= chunk;
	}

	return nbytes - left;
}
EXPORT_SYMBOL(get_random_bytes_arch);

static bool trust_cpu __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU);
static int __init parse_trust_cpu(char *arg)
{
@@ -1521,126 +1669,6 @@ struct ctl_table random_table[] = {
};
#endif	/* CONFIG_SYSCTL */

struct batched_entropy {
	union {
		/*
		 * We make this 1.5x a ChaCha block, so that we get the
		 * remaining 32 bytes from fast key erasure, plus one full
		 * block from the detached ChaCha state. We can increase
		 * the size of this later if needed so long as we keep the
		 * formula of (integer_blocks + 0.5) * CHACHA_BLOCK_SIZE.
		 */
		u64 entropy_u64[CHACHA_BLOCK_SIZE * 3 / (2 * sizeof(u64))];
		u32 entropy_u32[CHACHA_BLOCK_SIZE * 3 / (2 * sizeof(u32))];
	};
	unsigned long generation;
	unsigned int position;
};

/*
 * Get a random word for internal kernel use only. The quality of the random
 * number is good as /dev/urandom. In order to ensure that the randomness
 * provided by this function is okay, the function wait_for_random_bytes()
 * should be called and return 0 at least once at any point prior.
 */
static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64) = {
	.position = UINT_MAX
};

u64 get_random_u64(void)
{
	u64 ret;
	unsigned long flags;
	struct batched_entropy *batch;
	static void *previous;
	unsigned long next_gen;

	warn_unseeded_randomness(&previous);

	local_irq_save(flags);
	batch = raw_cpu_ptr(&batched_entropy_u64);

	next_gen = READ_ONCE(base_crng.generation);
	if (batch->position >= ARRAY_SIZE(batch->entropy_u64) ||
	    next_gen != batch->generation) {
		_get_random_bytes(batch->entropy_u64, sizeof(batch->entropy_u64));
		batch->position = 0;
		batch->generation = next_gen;
	}

	ret = batch->entropy_u64[batch->position];
	batch->entropy_u64[batch->position] = 0;
	++batch->position;
	local_irq_restore(flags);
	return ret;
}
EXPORT_SYMBOL(get_random_u64);

static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32) = {
	.position = UINT_MAX
};

u32 get_random_u32(void)
{
	u32 ret;
	unsigned long flags;
	struct batched_entropy *batch;
	static void *previous;
	unsigned long next_gen;

	warn_unseeded_randomness(&previous);

	local_irq_save(flags);
	batch = raw_cpu_ptr(&batched_entropy_u32);

	next_gen = READ_ONCE(base_crng.generation);
	if (batch->position >= ARRAY_SIZE(batch->entropy_u32) ||
	    next_gen != batch->generation) {
		_get_random_bytes(batch->entropy_u32, sizeof(batch->entropy_u32));
		batch->position = 0;
		batch->generation = next_gen;
	}

	ret = batch->entropy_u32[batch->position];
	batch->entropy_u32[batch->position] = 0;
	++batch->position;
	local_irq_restore(flags);
	return ret;
}
EXPORT_SYMBOL(get_random_u32);

/**
 * randomize_page - Generate a random, page aligned address
 * @start:	The smallest acceptable address the caller will take.
 * @range:	The size of the area, starting at @start, within which the
 *		random address must fall.
 *
 * If @start + @range would overflow, @range is capped.
 *
 * NOTE: Historical use of randomize_range, which this replaces, presumed that
 * @start was already page aligned.  We now align it regardless.
 *
 * Return: A page aligned address within [start, start + range).  On error,
 * @start is returned.
 */
unsigned long randomize_page(unsigned long start, unsigned long range)
{
	if (!PAGE_ALIGNED(start)) {
		range -= PAGE_ALIGN(start) - start;
		start = PAGE_ALIGN(start);
	}

	if (start > ULONG_MAX - range)
		range = ULONG_MAX - start;

	range >>= PAGE_SHIFT;

	if (range == 0)
		return start;

	return start + (get_random_long() % range << PAGE_SHIFT);
}

/* 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.