random: clamp credited irq bits to maximum mixed

[mirror_ubuntu-jammy-kernel.git] / drivers / char / random.c

// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
/*
 * Copyright (C) 2017-2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
 * Copyright Matt Mackall <mpm@selenic.com>, 2003, 2004, 2005
 * Copyright Theodore Ts'o, 1994, 1995, 1996, 1997, 1998, 1999. All rights reserved.
 *
 * This driver produces cryptographically secure pseudorandom data. It is divided
 * into roughly six sections, each with a section header:
 *
 *   - Initialization and readiness waiting.
 *   - Fast key erasure RNG, the "crng".
 *   - Entropy accumulation and extraction routines.
 *   - Entropy collection routines.
 *   - Userspace reader/writer interfaces.
 *   - Sysctl interface.
 *
 * The high level overview is that there is one input pool, into which
 * various pieces of data are hashed. Prior to initialization, some of that
 * data is then "credited" as having a certain number of bits of entropy.
 * When enough bits of entropy are available, the hash is finalized and
 * handed as a key to a stream cipher that expands it indefinitely for
 * various consumers. This key is periodically refreshed as the various
 * entropy collectors, described below, add data to the input pool.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/utsname.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/major.h>
#include <linux/string.h>
#include <linux/fcntl.h>
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/poll.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/genhd.h>
#include <linux/interrupt.h>
#include <linux/mm.h>
#include <linux/nodemask.h>
#include <linux/spinlock.h>
#include <linux/kthread.h>
#include <linux/percpu.h>
#include <linux/ptrace.h>
#include <linux/workqueue.h>
#include <linux/irq.h>
#include <linux/ratelimit.h>
#include <linux/syscalls.h>
#include <linux/completion.h>
#include <linux/uuid.h>
#include <linux/uaccess.h>
#include <linux/siphash.h>
#include <linux/uio.h>
#include <crypto/chacha.h>
#include <crypto/blake2s.h>
#include <asm/processor.h>
#include <asm/irq.h>
#include <asm/irq_regs.h>
#include <asm/io.h>

/*********************************************************************
 *
 * Initialization and readiness waiting.
 *
 * Much of the RNG infrastructure is devoted to various dependencies
 * being able to wait until the RNG has collected enough entropy and
 * is ready for safe consumption.
 *
 *********************************************************************/

/*
 * crng_init is protected by base_crng->lock, and only increases
 * its value (from empty->early->ready).
 */
static enum {
        CRNG_EMPTY = 0, /* Little to no entropy collected */
        CRNG_EARLY = 1, /* At least POOL_EARLY_BITS collected */
        CRNG_READY = 2  /* Fully initialized with POOL_READY_BITS collected */
} crng_init __read_mostly = CRNG_EMPTY;
#define crng_ready() (likely(crng_init >= CRNG_READY))
/* Various types of waiters for crng_init->CRNG_READY transition. */
static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait);
static struct fasync_struct *fasync;
static DEFINE_SPINLOCK(random_ready_chain_lock);
static RAW_NOTIFIER_HEAD(random_ready_chain);

/* Control how we warn userspace. */
static struct ratelimit_state urandom_warning =
        RATELIMIT_STATE_INIT_FLAGS("urandom_warning", HZ, 3, RATELIMIT_MSG_ON_RELEASE);
static int ratelimit_disable __read_mostly =
        IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM);
module_param_named(ratelimit_disable, ratelimit_disable, int, 0644);
MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression");

/*
 * Returns whether or not the input pool has been seeded and thus guaranteed
 * to supply cryptographically secure random numbers. This applies to: the
 * /dev/urandom device, the get_random_bytes function, and the get_random_{u32,
 * ,u64,int,long} family of functions.
 *
 * Returns: true if the input pool has been seeded.
 *          false if the input pool has not been seeded.
 */
bool rng_is_initialized(void)
{
        return crng_ready();
}
EXPORT_SYMBOL(rng_is_initialized);

/* Used by wait_for_random_bytes(), and considered an entropy collector, below. */
static void try_to_generate_entropy(void);

/*
 * Wait for the input pool to be seeded and thus guaranteed to supply
 * cryptographically secure random numbers. This applies to: the /dev/urandom
 * device, the get_random_bytes function, and the get_random_{u32,u64,int,long}
 * family of functions. Using any of these functions without first calling
 * this function forfeits the guarantee of security.
 *
 * Returns: 0 if the input pool has been seeded.
 *          -ERESTARTSYS if the function was interrupted by a signal.
 */
int wait_for_random_bytes(void)
{
        while (!crng_ready()) {
                int ret;

                try_to_generate_entropy();
                ret = wait_event_interruptible_timeout(crng_init_wait, crng_ready(), HZ);
                if (ret)
                        return ret > 0 ? 0 : ret;
        }
        return 0;
}
EXPORT_SYMBOL(wait_for_random_bytes);

/*
 * Add a callback function that will be invoked when the input
 * pool is initialised.
 *
 * returns: 0 if callback is successfully added
 *          -EALREADY if pool is already initialised (callback not called)
 */
int __cold register_random_ready_notifier(struct notifier_block *nb)
{
        unsigned long flags;
        int ret = -EALREADY;

        if (crng_ready())
                return ret;

        spin_lock_irqsave(&random_ready_chain_lock, flags);
        if (!crng_ready())
                ret = raw_notifier_chain_register(&random_ready_chain, nb);
        spin_unlock_irqrestore(&random_ready_chain_lock, flags);
        return ret;
}

/*
 * Delete a previously registered readiness callback function.
 */
int __cold unregister_random_ready_notifier(struct notifier_block *nb)
{
        unsigned long flags;
        int ret;

        spin_lock_irqsave(&random_ready_chain_lock, flags);
        ret = raw_notifier_chain_unregister(&random_ready_chain, nb);
        spin_unlock_irqrestore(&random_ready_chain_lock, flags);
        return ret;
}

static void __cold process_random_ready_list(void)
{
        unsigned long flags;

        spin_lock_irqsave(&random_ready_chain_lock, flags);
        raw_notifier_call_chain(&random_ready_chain, 0, NULL);
        spin_unlock_irqrestore(&random_ready_chain_lock, flags);
}

#define warn_unseeded_randomness() \
        if (IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM) && !crng_ready()) \
                printk_deferred(KERN_NOTICE "random: %s called from %pS with crng_init=%d\n", \
                                __func__, (void *)_RET_IP_, crng_init)


/*********************************************************************
 *
 * Fast key erasure RNG, the "crng".
 *
 * 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 len)
 *      u32 get_random_u32()
 *      u64 get_random_u64()
 *      unsigned int get_random_int()
 *      unsigned long get_random_long()
 *
 * 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 u32, u64, int, and long family of
 * functions may be higher performance for one-off random integers,
 * because they do a bit of buffering and do not invoke reseeding
 * until the buffer is emptied.
 *
 *********************************************************************/

enum {
        CRNG_RESEED_START_INTERVAL = HZ,
        CRNG_RESEED_INTERVAL = 60 * HZ
};

static struct {
        u8 key[CHACHA_KEY_SIZE] __aligned(__alignof__(long));
        unsigned long birth;
        unsigned long generation;
        spinlock_t lock;
} base_crng = {
        .lock = __SPIN_LOCK_UNLOCKED(base_crng.lock)
};

struct crng {
        u8 key[CHACHA_KEY_SIZE];
        unsigned long generation;
        local_lock_t lock;
};

static DEFINE_PER_CPU(struct crng, crngs) = {
        .generation = ULONG_MAX,
        .lock = INIT_LOCAL_LOCK(crngs.lock),
};

/* Used by crng_reseed() and crng_make_state() to extract a new seed from the input pool. */
static void extract_entropy(void *buf, size_t len);

/* This extracts a new crng key from the input pool. */
static void crng_reseed(void)
{
        unsigned long flags;
        unsigned long next_gen;
        u8 key[CHACHA_KEY_SIZE];

        extract_entropy(key, sizeof(key));

        /*
         * We copy the new key into the base_crng, overwriting the old one,
         * and update the generation counter. We avoid hitting ULONG_MAX,
         * because the per-cpu crngs are initialized to ULONG_MAX, so this
         * forces new CPUs that come online to always initialize.
         */
        spin_lock_irqsave(&base_crng.lock, flags);
        memcpy(base_crng.key, key, sizeof(base_crng.key));
        next_gen = base_crng.generation + 1;
        if (next_gen == ULONG_MAX)
                ++next_gen;
        WRITE_ONCE(base_crng.generation, next_gen);
        WRITE_ONCE(base_crng.birth, jiffies);
        if (!crng_ready())
                crng_init = CRNG_READY;
        spin_unlock_irqrestore(&base_crng.lock, flags);
        memzero_explicit(key, sizeof(key));
}

/*
 * 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.
 *
 * The returned ChaCha state contains within it a copy of the old
 * key value, at index 4, so the state should always be zeroed out
 * immediately after using in order to maintain forward secrecy.
 * If the state cannot be erased in a timely manner, then it is
 * safer to set the random_data parameter to &chacha_state[4] so
 * that this function overwrites it before returning.
 */
static void crng_fast_key_erasure(u8 key[CHACHA_KEY_SIZE],
                                  u32 chacha_state[CHACHA_STATE_WORDS],
                                  u8 *random_data, size_t random_data_len)
{
        u8 first_block[CHACHA_BLOCK_SIZE];

        BUG_ON(random_data_len > 32);

        chacha_init_consts(chacha_state);
        memcpy(&chacha_state[4], key, CHACHA_KEY_SIZE);
        memset(&chacha_state[12], 0, sizeof(u32) * 4);
        chacha20_block(chacha_state, first_block);

        memcpy(key, first_block, CHACHA_KEY_SIZE);
        memcpy(random_data, first_block + CHACHA_KEY_SIZE, random_data_len);
        memzero_explicit(first_block, sizeof(first_block));
}

/*
 * Return whether the crng seed is considered to be sufficiently old
 * that a reseeding is needed. This happens if the last reseeding
 * was CRNG_RESEED_INTERVAL ago, or during early boot, at an interval
 * proportional to the uptime.
 */
static bool crng_has_old_seed(void)
{
        static bool early_boot = true;
        unsigned long interval = CRNG_RESEED_INTERVAL;

        if (unlikely(READ_ONCE(early_boot))) {
                time64_t uptime = ktime_get_seconds();
                if (uptime >= CRNG_RESEED_INTERVAL / HZ * 2)
                        WRITE_ONCE(early_boot, false);
                else
                        interval = max_t(unsigned int, CRNG_RESEED_START_INTERVAL,
                                         (unsigned int)uptime / 2 * HZ);
        }
        return time_is_before_jiffies(READ_ONCE(base_crng.birth) + interval);
}

/*
 * This function returns a ChaCha state that you may use for generating
 * random data. It also returns up to 32 bytes on its own of random data
 * that may be used; random_data_len may not be greater than 32.
 */
static void crng_make_state(u32 chacha_state[CHACHA_STATE_WORDS],
                            u8 *random_data, size_t random_data_len)
{
        unsigned long flags;
        struct crng *crng;

        BUG_ON(random_data_len > 32);

        /*
         * For the fast path, we check whether we're ready, unlocked first, and
         * then re-check once locked later. In the case where we're really not
         * ready, we do fast key erasure with the base_crng directly, extracting
         * when crng_init is CRNG_EMPTY.
         */
        if (!crng_ready()) {
                bool ready;

                spin_lock_irqsave(&base_crng.lock, flags);
                ready = crng_ready();
                if (!ready) {
                        if (crng_init == CRNG_EMPTY)
                                extract_entropy(base_crng.key, sizeof(base_crng.key));
                        crng_fast_key_erasure(base_crng.key, chacha_state,
                                              random_data, random_data_len);
                }
                spin_unlock_irqrestore(&base_crng.lock, flags);
                if (!ready)
                        return;
        }

        /*
         * If the base_crng is old enough, we reseed, which in turn bumps the
         * generation counter that we check below.
         */
        if (unlikely(crng_has_old_seed()))
                crng_reseed();

        local_lock_irqsave(&crngs.lock, flags);
        crng = raw_cpu_ptr(&crngs);

        /*
         * If our per-cpu crng is older than the base_crng, then it means
         * somebody reseeded the base_crng. In that case, we do fast key
         * erasure on the base_crng, and use its output as the new key
         * for our per-cpu crng. This brings us up to date with base_crng.
         */
        if (unlikely(crng->generation != READ_ONCE(base_crng.generation))) {
                spin_lock(&base_crng.lock);
                crng_fast_key_erasure(base_crng.key, chacha_state,
                                      crng->key, sizeof(crng->key));
                crng->generation = base_crng.generation;
                spin_unlock(&base_crng.lock);
        }

        /*
         * Finally, when we've made it this far, our per-cpu crng has an up
         * to date key, and we can do fast key erasure with it to produce
         * some random data and a ChaCha state for the caller. All other
         * branches of this function are "unlikely", so most of the time we
         * should wind up here immediately.
         */
        crng_fast_key_erasure(crng->key, chacha_state, random_data, random_data_len);
        local_unlock_irqrestore(&crngs.lock, flags);
}

static void _get_random_bytes(void *buf, size_t len)
{
        u32 chacha_state[CHACHA_STATE_WORDS];
        u8 tmp[CHACHA_BLOCK_SIZE];
        size_t first_block_len;

        if (!len)
                return;

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

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

                chacha20_block(chacha_state, buf);
                if (unlikely(chacha_state[12] == 0))
                        ++chacha_state[13];
                len -= 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 len)
{
        warn_unseeded_randomness();
        _get_random_bytes(buf, len);
}
EXPORT_SYMBOL(get_random_bytes);

static ssize_t get_random_bytes_user(struct iov_iter *iter)
{
        u32 chacha_state[CHACHA_STATE_WORDS];
        u8 block[CHACHA_BLOCK_SIZE];
        size_t ret = 0, copied;

        if (unlikely(!iov_iter_count(iter)))
                return 0;

        /*
         * Immediately overwrite the ChaCha key at index 4 with random
         * bytes, in case userspace causes copy_to_iter() below to sleep
         * forever, so that we still retain forward secrecy in that case.
         */
        crng_make_state(chacha_state, (u8 *)&chacha_state[4], CHACHA_KEY_SIZE);
        /*
         * However, if we're doing a read of len <= 32, we don't need to
         * use chacha_state after, so we can simply return those bytes to
         * the user directly.
         */
        if (iov_iter_count(iter) <= CHACHA_KEY_SIZE) {
                ret = copy_to_iter(&chacha_state[4], CHACHA_KEY_SIZE, iter);
                goto out_zero_chacha;
        }

        for (;;) {
                chacha20_block(chacha_state, block);
                if (unlikely(chacha_state[12] == 0))
                        ++chacha_state[13];

                copied = copy_to_iter(block, sizeof(block), iter);
                ret += copied;
                if (!iov_iter_count(iter) || copied != sizeof(block))
                        break;

                BUILD_BUG_ON(PAGE_SIZE % sizeof(block) != 0);
                if (ret % PAGE_SIZE == 0) {
                        if (signal_pending(current))
                                break;
                        cond_resched();
                }
        }

        memzero_explicit(block, sizeof(block));
out_zero_chacha:
        memzero_explicit(chacha_state, sizeof(chacha_state));
        return ret ? ret : -EFAULT;
}

/*
 * 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.
 */

#define DEFINE_BATCHED_ENTROPY(type)                                            \
struct batch_ ##type {                                                          \
        /*                                                                      \
         * 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.               \
         */                                                                     \
        type entropy[CHACHA_BLOCK_SIZE * 3 / (2 * sizeof(type))];               \
        local_lock_t lock;                                                      \
        unsigned long generation;                                               \
        unsigned int position;                                                  \
};                                                                              \
                                                                                \
static DEFINE_PER_CPU(struct batch_ ##type, batched_entropy_ ##type) = {        \
        .lock = INIT_LOCAL_LOCK(batched_entropy_ ##type.lock),                  \
        .position = UINT_MAX                                                    \
};                                                                              \
                                                                                \
type get_random_ ##type(void)                                                   \
{                                                                               \
        type ret;                                                               \
        unsigned long flags;                                                    \
        struct batch_ ##type *batch;                                            \
        unsigned long next_gen;                                                 \
                                                                                \
        warn_unseeded_randomness();                                             \
                                                                                \
        if  (!crng_ready()) {                                                   \
                _get_random_bytes(&ret, sizeof(ret));                           \
                return ret;                                                     \
        }                                                                       \
                                                                                \
        local_lock_irqsave(&batched_entropy_ ##type.lock, flags);               \
        batch = raw_cpu_ptr(&batched_entropy_##type);                           \
                                                                                \
        next_gen = READ_ONCE(base_crng.generation);                             \
        if (batch->position >= ARRAY_SIZE(batch->entropy) ||                    \
            next_gen != batch->generation) {                                    \
                _get_random_bytes(batch->entropy, sizeof(batch->entropy));      \
                batch->position = 0;                                            \
                batch->generation = next_gen;                                   \
        }                                                                       \
                                                                                \
        ret = batch->entropy[batch->position];                                  \
        batch->entropy[batch->position] = 0;                                    \
        ++batch->position;                                                      \
        local_unlock_irqrestore(&batched_entropy_ ##type.lock, flags);          \
        return ret;                                                             \
}                                                                               \
EXPORT_SYMBOL(get_random_ ##type);

DEFINE_BATCHED_ENTROPY(u64)
DEFINE_BATCHED_ENTROPY(u32)

#ifdef CONFIG_SMP
/*
 * This function is called when the CPU is coming up, with entry
 * CPUHP_RANDOM_PREPARE, which comes before CPUHP_WORKQUEUE_PREP.
 */
int __cold random_prepare_cpu(unsigned int cpu)
{
        /*
         * When the cpu comes back online, immediately invalidate both
         * the per-cpu crng and all batches, so that we serve fresh
         * randomness.
         */
        per_cpu_ptr(&crngs, cpu)->generation = ULONG_MAX;
        per_cpu_ptr(&batched_entropy_u32, cpu)->position = UINT_MAX;
        per_cpu_ptr(&batched_entropy_u64, cpu)->position = UINT_MAX;
        return 0;
}
#endif

/*
 * 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 len)
{
        size_t left = len;
        u8 *p = buf;

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

                if (!arch_get_random_long(&v))
                        break;

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

        return len - left;
}
EXPORT_SYMBOL(get_random_bytes_arch);


/**********************************************************************
 *
 * Entropy accumulation and extraction routines.
 *
 * Callers may add entropy via:
 *
 *     static void mix_pool_bytes(const void *buf, size_t len)
 *
 * After which, if added entropy should be credited:
 *
 *     static void credit_init_bits(size_t bits)
 *
 * Finally, extract entropy via:
 *
 *     static void extract_entropy(void *buf, size_t len)
 *
 **********************************************************************/

enum {
        POOL_BITS = BLAKE2S_HASH_SIZE * 8,
        POOL_READY_BITS = POOL_BITS, /* When crng_init->CRNG_READY */
        POOL_EARLY_BITS = POOL_READY_BITS / 2 /* When crng_init->CRNG_EARLY */
};

static struct {
        struct blake2s_state hash;
        spinlock_t lock;
        unsigned int init_bits;
} 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 _mix_pool_bytes(const void *buf, size_t len)
{
        blake2s_update(&input_pool.hash, buf, len);
}

/*
 * This function adds bytes into the input pool. It does not
 * update the initialization bit counter; the caller should call
 * credit_init_bits if this is appropriate.
 */
static void mix_pool_bytes(const void *buf, size_t len)
{
        unsigned long flags;

        spin_lock_irqsave(&input_pool.lock, flags);
        _mix_pool_bytes(buf, len);
        spin_unlock_irqrestore(&input_pool.lock, flags);
}

/*
 * This is an HKDF-like construction for using the hashed collected entropy
 * as a PRF key, that's then expanded block-by-block.
 */
static void extract_entropy(void *buf, size_t len)
{
        unsigned long flags;
        u8 seed[BLAKE2S_HASH_SIZE], next_key[BLAKE2S_HASH_SIZE];
        struct {
                unsigned long rdseed[32 / sizeof(long)];
                size_t counter;
        } block;
        size_t i;

        for (i = 0; i < ARRAY_SIZE(block.rdseed); ++i) {
                if (!arch_get_random_seed_long(&block.rdseed[i]) &&
                    !arch_get_random_long(&block.rdseed[i]))
                        block.rdseed[i] = random_get_entropy();
        }

        spin_lock_irqsave(&input_pool.lock, flags);

        /* seed = HASHPRF(last_key, entropy_input) */
        blake2s_final(&input_pool.hash, seed);

        /* next_key = HASHPRF(seed, RDSEED || 0) */
        block.counter = 0;
        blake2s(next_key, (u8 *)&block, seed, sizeof(next_key), sizeof(block), sizeof(seed));
        blake2s_init_key(&input_pool.hash, BLAKE2S_HASH_SIZE, next_key, sizeof(next_key));

        spin_unlock_irqrestore(&input_pool.lock, flags);
        memzero_explicit(next_key, sizeof(next_key));

        while (len) {
                i = min_t(size_t, len, BLAKE2S_HASH_SIZE);
                /* output = HASHPRF(seed, RDSEED || ++counter) */
                ++block.counter;
                blake2s(buf, (u8 *)&block, seed, i, sizeof(block), sizeof(seed));
                len -= i;
                buf += i;
        }

        memzero_explicit(seed, sizeof(seed));
        memzero_explicit(&block, sizeof(block));
}

#define credit_init_bits(bits) if (!crng_ready()) _credit_init_bits(bits)

static void __cold _credit_init_bits(size_t bits)
{
        unsigned int new, orig, add;
        unsigned long flags;

        if (!bits)
                return;

        add = min_t(size_t, bits, POOL_BITS);

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

        if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) {
                crng_reseed(); /* Sets crng_init to CRNG_READY under base_crng.lock. */
                process_random_ready_list();
                wake_up_interruptible(&crng_init_wait);
                kill_fasync(&fasync, SIGIO, POLL_IN);
                pr_notice("crng init done\n");
                if (urandom_warning.missed)
                        pr_notice("%d urandom warning(s) missed due to ratelimiting\n",
                                  urandom_warning.missed);
        } else if (orig < POOL_EARLY_BITS && new >= POOL_EARLY_BITS) {
                spin_lock_irqsave(&base_crng.lock, flags);
                /* Check if crng_init is CRNG_EMPTY, to avoid race with crng_reseed(). */
                if (crng_init == CRNG_EMPTY) {
                        extract_entropy(base_crng.key, sizeof(base_crng.key));
                        crng_init = CRNG_EARLY;
                }
                spin_unlock_irqrestore(&base_crng.lock, flags);
        }
}


/**********************************************************************
 *
 * Entropy collection routines.
 *
 * The following exported functions are used for pushing entropy into
 * the above entropy accumulation routines:
 *
 *      void add_device_randomness(const void *buf, size_t len);
 *      void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy);
 *      void add_bootloader_randomness(const void *buf, size_t len);
 *      void add_interrupt_randomness(int irq);
 *      void add_input_randomness(unsigned int type, unsigned int code, unsigned int value);
 *      void add_disk_randomness(struct gendisk *disk);
 *
 * add_device_randomness() adds data to the input pool that
 * is likely to differ between two devices (or possibly even per boot).
 * This would be things like MAC addresses or serial numbers, or the
 * read-out of the RTC. This does *not* credit any actual entropy to
 * the pool, but it initializes the pool to different values for devices
 * that might otherwise be identical and have very little entropy
 * available to them (particularly common in the embedded world).
 *
 * add_hwgenerator_randomness() is for true hardware RNGs, and will credit
 * entropy as specified by the caller. If the entropy pool is full it will
 * block until more entropy is needed.
 *
 * add_bootloader_randomness() is called by bootloader drivers, such as EFI
 * and device tree, and credits its input depending on whether or not the
 * configuration option CONFIG_RANDOM_TRUST_BOOTLOADER is set.
 *
 * add_interrupt_randomness() uses the interrupt timing as random
 * inputs to the entropy pool. Using the cycle counters and the irq source
 * as inputs, it feeds the input pool roughly once a second or after 64
 * interrupts, crediting 1 bit of entropy for whichever comes first.
 *
 * add_input_randomness() uses the input layer interrupt timing, as well
 * as the event type information from the hardware.
 *
 * add_disk_randomness() uses what amounts to the seek time of block
 * layer request events, on a per-disk_devt basis, as input to the
 * entropy pool. Note that high-speed solid state drives with very low
 * seek times do not make for good sources of entropy, as their seek
 * times are usually fairly consistent.
 *
 * The last two routines try to estimate how many bits of entropy
 * to credit. They do this by keeping track of the first and second
 * order deltas of the event timings.
 *
 **********************************************************************/

static bool trust_cpu __initdata = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU);
static bool trust_bootloader __initdata = IS_ENABLED(CONFIG_RANDOM_TRUST_BOOTLOADER);
static int __init parse_trust_cpu(char *arg)
{
        return kstrtobool(arg, &trust_cpu);
}
static int __init parse_trust_bootloader(char *arg)
{
        return kstrtobool(arg, &trust_bootloader);
}
early_param("random.trust_cpu", parse_trust_cpu);
early_param("random.trust_bootloader", parse_trust_bootloader);

/*
 * The first collection of entropy occurs at system boot while interrupts
 * are still turned off. Here we push in latent entropy, RDSEED, a timestamp,
 * utsname(), and the command line. Depending on the above configuration knob,
 * RDSEED may be considered sufficient for initialization. Note that much
 * earlier setup may already have pushed entropy into the input pool by the
 * time we get here.
 */
int __init random_init(const char *command_line)
{
        ktime_t now = ktime_get_real();
        unsigned int i, arch_bits;
        unsigned long entropy;

#if defined(LATENT_ENTROPY_PLUGIN)
        static const u8 compiletime_seed[BLAKE2S_BLOCK_SIZE] __initconst __latent_entropy;
        _mix_pool_bytes(compiletime_seed, sizeof(compiletime_seed));
#endif

        for (i = 0, arch_bits = BLAKE2S_BLOCK_SIZE * 8;
             i < BLAKE2S_BLOCK_SIZE; i += sizeof(entropy)) {
                if (!arch_get_random_seed_long_early(&entropy) &&
                    !arch_get_random_long_early(&entropy)) {
                        entropy = random_get_entropy();
                        arch_bits -= sizeof(entropy) * 8;
                }
                _mix_pool_bytes(&entropy, sizeof(entropy));
        }
        _mix_pool_bytes(&now, sizeof(now));
        _mix_pool_bytes(utsname(), sizeof(*(utsname())));
        _mix_pool_bytes(command_line, strlen(command_line));
        add_latent_entropy();

        if (crng_ready())
                crng_reseed();
        else if (trust_cpu)
                _credit_init_bits(arch_bits);

        return 0;
}

/*
 * 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 entropy pool having similar initial state across largely
 * identical devices.
 */
void add_device_randomness(const void *buf, size_t len)
{
        unsigned long entropy = random_get_entropy();
        unsigned long flags;

        spin_lock_irqsave(&input_pool.lock, flags);
        _mix_pool_bytes(&entropy, sizeof(entropy));
        _mix_pool_bytes(buf, len);
        spin_unlock_irqrestore(&input_pool.lock, flags);
}
EXPORT_SYMBOL(add_device_randomness);

/*
 * 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 void *buf, size_t len, size_t entropy)
{
        mix_pool_bytes(buf, len);
        credit_init_bits(entropy);

        /*
         * Throttle writing to once every CRNG_RESEED_INTERVAL, unless
         * we're not yet initialized.
         */
        if (!kthread_should_stop() && crng_ready())
                schedule_timeout_interruptible(CRNG_RESEED_INTERVAL);
}
EXPORT_SYMBOL_GPL(add_hwgenerator_randomness);

/*
 * Handle random seed passed by bootloader, and credit it if
 * CONFIG_RANDOM_TRUST_BOOTLOADER is set.
 */
void __init add_bootloader_randomness(const void *buf, size_t len)
{
        mix_pool_bytes(buf, len);
        if (trust_bootloader)
                credit_init_bits(len * 8);
}

struct fast_pool {
        struct work_struct mix;
        unsigned long pool[4];
        unsigned long last;
        unsigned int count;
};

static DEFINE_PER_CPU(struct fast_pool, irq_randomness) = {
#ifdef CONFIG_64BIT
#define FASTMIX_PERM SIPHASH_PERMUTATION
        .pool = { SIPHASH_CONST_0, SIPHASH_CONST_1, SIPHASH_CONST_2, SIPHASH_CONST_3 }
#else
#define FASTMIX_PERM HSIPHASH_PERMUTATION
        .pool = { HSIPHASH_CONST_0, HSIPHASH_CONST_1, HSIPHASH_CONST_2, HSIPHASH_CONST_3 }
#endif
};

/*
 * This is [Half]SipHash-1-x, starting from an empty key. Because
 * the key is fixed, it assumes that its inputs are non-malicious,
 * and therefore this has no security on its own. s represents the
 * four-word SipHash state, while v represents a two-word input.
 */
static void fast_mix(unsigned long s[4], unsigned long v1, unsigned long v2)
{
        s[3] ^= v1;
        FASTMIX_PERM(s[0], s[1], s[2], s[3]);
        s[0] ^= v1;
        s[3] ^= v2;
        FASTMIX_PERM(s[0], s[1], s[2], s[3]);
        s[0] ^= v2;
}

#ifdef CONFIG_SMP
/*
 * This function is called when the CPU has just come online, with
 * entry CPUHP_AP_RANDOM_ONLINE, just after CPUHP_AP_WORKQUEUE_ONLINE.
 */
int __cold random_online_cpu(unsigned int cpu)
{
        /*
         * During CPU shutdown and before CPU onlining, add_interrupt_
         * randomness() may schedule mix_interrupt_randomness(), and
         * set the MIX_INFLIGHT flag. However, because the worker can
         * be scheduled on a different CPU during this period, that
         * flag will never be cleared. For that reason, we zero out
         * the flag here, which runs just after workqueues are onlined
         * for the CPU again. This also has the effect of setting the
         * irq randomness count to zero so that new accumulated irqs
         * are fresh.
         */
        per_cpu_ptr(&irq_randomness, cpu)->count = 0;
        return 0;
}
#endif

static void mix_interrupt_randomness(struct work_struct *work)
{
        struct fast_pool *fast_pool = container_of(work, struct fast_pool, mix);
        /*
         * The size of the copied stack pool is explicitly 2 longs so that we
         * only ever ingest half of the siphash output each time, retaining
         * the other half as the next "key" that carries over. The entropy is
         * supposed to be sufficiently dispersed between bits so on average
         * we don't wind up "losing" some.
         */
        unsigned long pool[2];
        unsigned int count;

        /* Check to see if we're running on the wrong CPU due to hotplug. */
        local_irq_disable();
        if (fast_pool != this_cpu_ptr(&irq_randomness)) {
                local_irq_enable();
                return;
        }

        /*
         * Copy the pool to the stack so that the mixer always has a
         * consistent view, before we reenable irqs again.
         */
        memcpy(pool, fast_pool->pool, sizeof(pool));
        count = fast_pool->count;
        fast_pool->count = 0;
        fast_pool->last = jiffies;
        local_irq_enable();

        mix_pool_bytes(pool, sizeof(pool));
        credit_init_bits(clamp_t(unsigned int, (count & U16_MAX) / 64, 1, sizeof(pool) * 8));

        memzero_explicit(pool, sizeof(pool));
}

void add_interrupt_randomness(int irq)
{
        enum { MIX_INFLIGHT = 1U << 31 };
        unsigned long entropy = random_get_entropy();
        struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness);
        struct pt_regs *regs = get_irq_regs();
        unsigned int new_count;

        fast_mix(fast_pool->pool, entropy,
                 (regs ? instruction_pointer(regs) : _RET_IP_) ^ swab(irq));
        new_count = ++fast_pool->count;

        if (new_count & MIX_INFLIGHT)
                return;

        if (new_count < 1024 && !time_is_before_jiffies(fast_pool->last + HZ))
                return;

        if (unlikely(!fast_pool->mix.func))
                INIT_WORK(&fast_pool->mix, mix_interrupt_randomness);
        fast_pool->count |= MIX_INFLIGHT;
        queue_work_on(raw_smp_processor_id(), system_highpri_wq, &fast_pool->mix);
}
EXPORT_SYMBOL_GPL(add_interrupt_randomness);

/* There is one of these per entropy source */
struct timer_rand_state {
        unsigned long last_time;
        long last_delta, last_delta2;
};

/*
 * This function adds entropy to the entropy "pool" by using timing
 * delays. It uses the timer_rand_state structure to make an estimate
 * of how many bits of entropy this call has added to the pool. The
 * value "num" is also added to the pool; it should somehow describe
 * the type of event that just happened.
 */
static void add_timer_randomness(struct timer_rand_state *state, unsigned int num)
{
        unsigned long entropy = random_get_entropy(), now = jiffies, flags;
        long delta, delta2, delta3;
        unsigned int bits;

        /*
         * If we're in a hard IRQ, add_interrupt_randomness() will be called
         * sometime after, so mix into the fast pool.
         */
        if (in_hardirq()) {
                fast_mix(this_cpu_ptr(&irq_randomness)->pool, entropy, num);
        } else {
                spin_lock_irqsave(&input_pool.lock, flags);
                _mix_pool_bytes(&entropy, sizeof(entropy));
                _mix_pool_bytes(&num, sizeof(num));
                spin_unlock_irqrestore(&input_pool.lock, flags);
        }

        if (crng_ready())
                return;

        /*
         * Calculate number of bits of randomness we probably added.
         * We take into account the first, second and third-order deltas
         * in order to make our estimate.
         */
        delta = now - READ_ONCE(state->last_time);
        WRITE_ONCE(state->last_time, now);

        delta2 = delta - READ_ONCE(state->last_delta);
        WRITE_ONCE(state->last_delta, delta);

        delta3 = delta2 - READ_ONCE(state->last_delta2);
        WRITE_ONCE(state->last_delta2, delta2);

        if (delta < 0)
                delta = -delta;
        if (delta2 < 0)
                delta2 = -delta2;
        if (delta3 < 0)
                delta3 = -delta3;
        if (delta > delta2)
                delta = delta2;
        if (delta > delta3)
                delta = delta3;

        /*
         * delta is now minimum absolute delta. Round down by 1 bit
         * on general principles, and limit entropy estimate to 11 bits.
         */
        bits = min(fls(delta >> 1), 11);

        /*
         * As mentioned above, if we're in a hard IRQ, add_interrupt_randomness()
         * will run after this, which uses a different crediting scheme of 1 bit
         * per every 64 interrupts. In order to let that function do accounting
         * close to the one in this function, we credit a full 64/64 bit per bit,
         * and then subtract one to account for the extra one added.
         */
        if (in_hardirq())
                this_cpu_ptr(&irq_randomness)->count += max(1u, bits * 64) - 1;
        else
                _credit_init_bits(bits);
}

void add_input_randomness(unsigned int type, unsigned int code, unsigned int value)
{
        static unsigned char last_value;
        static struct timer_rand_state input_timer_state = { INITIAL_JIFFIES };

        /* Ignore autorepeat and the like. */
        if (value == last_value)
                return;

        last_value = value;
        add_timer_randomness(&input_timer_state,
                             (type << 4) ^ code ^ (code >> 4) ^ value);
}
EXPORT_SYMBOL_GPL(add_input_randomness);

#ifdef CONFIG_BLOCK
void add_disk_randomness(struct gendisk *disk)
{
        if (!disk || !disk->random)
                return;
        /* First major is 1, so we get >= 0x200 here. */
        add_timer_randomness(disk->random, 0x100 + disk_devt(disk));
}
EXPORT_SYMBOL_GPL(add_disk_randomness);

void __cold rand_initialize_disk(struct gendisk *disk)
{
        struct timer_rand_state *state;

        /*
         * If kzalloc returns null, we just won't use that entropy
         * source.
         */
        state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL);
        if (state) {
                state->last_time = INITIAL_JIFFIES;
                disk->random = state;
        }
}
#endif

/*
 * 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
 * CPU, the timer activity will be touching the stack of the CPU that is
 * generating entropy..
 *
 * Note that we don't re-arm the timer in the timer itself - we are
 * happy to be scheduled away, since that just makes the load more
 * complex, but we do not want the timer to keep ticking unless the
 * entropy loop is running.
 *
 * So the re-arming always happens in the entropy loop itself.
 */
static void __cold entropy_timer(struct timer_list *t)
{
        credit_init_bits(1);
}

/*
 * If we have an actual cycle counter, see if we can
 * generate enough entropy with timing noise
 */
static void __cold try_to_generate_entropy(void)
{
        struct {
                unsigned long entropy;
                struct timer_list timer;
        } stack;

        stack.entropy = random_get_entropy();

        /* Slow counter - or none. Don't even bother */
        if (stack.entropy == random_get_entropy())
                return;

        timer_setup_on_stack(&stack.timer, entropy_timer, 0);
        while (!crng_ready() && !signal_pending(current)) {
                if (!timer_pending(&stack.timer))
                        mod_timer(&stack.timer, jiffies + 1);
                mix_pool_bytes(&stack.entropy, sizeof(stack.entropy));
                schedule();
                stack.entropy = random_get_entropy();
        }

        del_timer_sync(&stack.timer);
        destroy_timer_on_stack(&stack.timer);
        mix_pool_bytes(&stack.entropy, sizeof(stack.entropy));
}


/**********************************************************************
 *
 * Userspace reader/writer interfaces.
 *
 * getrandom(2) is the primary modern interface into the RNG and should
 * be used in preference to anything else.
 *
 * Reading from /dev/random has the same functionality as calling
 * getrandom(2) with flags=0. In earlier versions, however, it had
 * vastly different semantics and should therefore be avoided, to
 * prevent backwards compatibility issues.
 *
 * Reading from /dev/urandom has the same functionality as calling
 * getrandom(2) with flags=GRND_INSECURE. Because it does not block
 * waiting for the RNG to be ready, it should not be used.
 *
 * Writing to either /dev/random or /dev/urandom adds entropy to
 * the input pool but does not credit it.
 *
 * Polling on /dev/random indicates when the RNG is initialized, on
 * the read side, and when it wants new entropy, on the write side.
 *
 * Both /dev/random and /dev/urandom have the same set of ioctls for
 * adding entropy, getting the entropy count, zeroing the count, and
 * reseeding the crng.
 *
 **********************************************************************/

SYSCALL_DEFINE3(getrandom, char __user *, ubuf, size_t, len, unsigned int, flags)
{
        struct iov_iter iter;
        struct iovec iov;
        int ret;

        if (flags & ~(GRND_NONBLOCK | GRND_RANDOM | GRND_INSECURE))
                return -EINVAL;

        /*
         * Requesting insecure and blocking randomness at the same time makes
         * no sense.
         */
        if ((flags & (GRND_INSECURE | GRND_RANDOM)) == (GRND_INSECURE | GRND_RANDOM))
                return -EINVAL;

        if (!crng_ready() && !(flags & GRND_INSECURE)) {
                if (flags & GRND_NONBLOCK)
                        return -EAGAIN;
                ret = wait_for_random_bytes();
                if (unlikely(ret))
                        return ret;
        }

        ret = import_single_range(READ, ubuf, len, &iov, &iter);
        if (unlikely(ret))
                return ret;
        return get_random_bytes_user(&iter);
}

static __poll_t random_poll(struct file *file, poll_table *wait)
{
        poll_wait(file, &crng_init_wait, wait);
        return crng_ready() ? EPOLLIN | EPOLLRDNORM : EPOLLOUT | EPOLLWRNORM;
}

static ssize_t write_pool_user(struct iov_iter *iter)
{
        u8 block[BLAKE2S_BLOCK_SIZE];
        ssize_t ret = 0;
        size_t copied;

        if (unlikely(!iov_iter_count(iter)))
                return 0;

        for (;;) {
                copied = copy_from_iter(block, sizeof(block), iter);
                ret += copied;
                mix_pool_bytes(block, copied);
                if (!iov_iter_count(iter) || copied != sizeof(block))
                        break;

                BUILD_BUG_ON(PAGE_SIZE % sizeof(block) != 0);
                if (ret % PAGE_SIZE == 0) {
                        if (signal_pending(current))
                                break;
                        cond_resched();
                }
        }

        memzero_explicit(block, sizeof(block));
        return ret ? ret : -EFAULT;
}

static ssize_t random_write_iter(struct kiocb *kiocb, struct iov_iter *iter)
{
        return write_pool_user(iter);
}

static ssize_t urandom_read_iter(struct kiocb *kiocb, struct iov_iter *iter)
{
        static int maxwarn = 10;

        if (!crng_ready()) {
                if (!ratelimit_disable && maxwarn <= 0)
                        ++urandom_warning.missed;
                else if (ratelimit_disable || __ratelimit(&urandom_warning)) {
                        --maxwarn;
                        pr_notice("%s: uninitialized urandom read (%zu bytes read)\n",
                                  current->comm, iov_iter_count(iter));
                }
        }

        return get_random_bytes_user(iter);
}

static ssize_t random_read_iter(struct kiocb *kiocb, struct iov_iter *iter)
{
        int ret;

        if (!crng_ready() &&
            ((kiocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) ||
             (kiocb->ki_filp->f_flags & O_NONBLOCK)))
                return -EAGAIN;

        ret = wait_for_random_bytes();
        if (ret != 0)
                return ret;
        return get_random_bytes_user(iter);
}

static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
{
        int __user *p = (int __user *)arg;
        int ent_count;

        switch (cmd) {
        case RNDGETENTCNT:
                /* Inherently racy, no point locking. */
                if (put_user(input_pool.init_bits, p))
                        return -EFAULT;
                return 0;
        case RNDADDTOENTCNT:
                if (!capable(CAP_SYS_ADMIN))
                        return -EPERM;
                if (get_user(ent_count, p))
                        return -EFAULT;
                if (ent_count < 0)
                        return -EINVAL;
                credit_init_bits(ent_count);
                return 0;
        case RNDADDENTROPY: {
                struct iov_iter iter;
                struct iovec iov;
                ssize_t ret;
                int len;

                if (!capable(CAP_SYS_ADMIN))
                        return -EPERM;
                if (get_user(ent_count, p++))
                        return -EFAULT;
                if (ent_count < 0)
                        return -EINVAL;
                if (get_user(len, p++))
                        return -EFAULT;
                ret = import_single_range(WRITE, p, len, &iov, &iter);
                if (unlikely(ret))
                        return ret;
                ret = write_pool_user(&iter);
                if (unlikely(ret < 0))
                        return ret;
                /* Since we're crediting, enforce that it was all written into the pool. */
                if (unlikely(ret != len))
                        return -EFAULT;
                credit_init_bits(ent_count);
                return 0;
        }
        case RNDZAPENTCNT:
        case RNDCLEARPOOL:
                /* No longer has any effect. */
                if (!capable(CAP_SYS_ADMIN))
                        return -EPERM;
                return 0;
        case RNDRESEEDCRNG:
                if (!capable(CAP_SYS_ADMIN))
                        return -EPERM;
                if (!crng_ready())
                        return -ENODATA;
                crng_reseed();
                return 0;
        default:
                return -EINVAL;
        }
}

static int random_fasync(int fd, struct file *filp, int on)
{
        return fasync_helper(fd, filp, on, &fasync);
}

const struct file_operations random_fops = {
        .read_iter = random_read_iter,
        .write_iter = random_write_iter,
        .poll = random_poll,
        .unlocked_ioctl = random_ioctl,
        .compat_ioctl = compat_ptr_ioctl,
        .fasync = random_fasync,
        .llseek = noop_llseek,
        .splice_read = generic_file_splice_read,
        .splice_write = iter_file_splice_write,
};

const struct file_operations urandom_fops = {
        .read_iter = urandom_read_iter,
        .write_iter = random_write_iter,
        .unlocked_ioctl = random_ioctl,
        .compat_ioctl = compat_ptr_ioctl,
        .fasync = random_fasync,
        .llseek = noop_llseek,
        .splice_read = generic_file_splice_read,
        .splice_write = iter_file_splice_write,
};


/********************************************************************
 *
 * Sysctl interface.
 *
 * These are partly unused legacy knobs with dummy values to not break
 * userspace and partly still useful things. They are usually accessible
 * in /proc/sys/kernel/random/ and are as follows:
 *
 * - boot_id - a UUID representing the current boot.
 *
 * - uuid - a random UUID, different each time the file is read.
 *
 * - poolsize - the number of bits of entropy that the input pool can
 *   hold, tied to the POOL_BITS constant.
 *
 * - entropy_avail - the number of bits of entropy currently in the
 *   input pool. Always <= poolsize.
 *
 * - write_wakeup_threshold - the amount of entropy in the input pool
 *   below which write polls to /dev/random will unblock, requesting
 *   more entropy, tied to the POOL_READY_BITS constant. It is writable
 *   to avoid breaking old userspaces, but writing to it does not
 *   change any behavior of the RNG.
 *
 * - urandom_min_reseed_secs - fixed to the value CRNG_RESEED_INTERVAL.
 *   It is writable to avoid breaking old userspaces, but writing
 *   to it does not change any behavior of the RNG.
 *
 ********************************************************************/

#ifdef CONFIG_SYSCTL

#include <linux/sysctl.h>

static int sysctl_random_min_urandom_seed = CRNG_RESEED_INTERVAL / HZ;
static int sysctl_random_write_wakeup_bits = POOL_READY_BITS;
static int sysctl_poolsize = POOL_BITS;
static u8 sysctl_bootid[UUID_SIZE];

/*
 * This function is used to return both the bootid UUID, and random
 * UUID. The difference is in whether table->data is NULL; if it is,
 * then a new UUID is generated and returned to the user.
 */
static int proc_do_uuid(struct ctl_table *table, int write, void *buf,
                        size_t *lenp, loff_t *ppos)
{
        u8 tmp_uuid[UUID_SIZE], *uuid;
        char uuid_string[UUID_STRING_LEN + 1];
        struct ctl_table fake_table = {
                .data = uuid_string,
                .maxlen = UUID_STRING_LEN
        };

        if (write)
                return -EPERM;

        uuid = table->data;
        if (!uuid) {
                uuid = tmp_uuid;
                generate_random_uuid(uuid);
        } else {
                static DEFINE_SPINLOCK(bootid_spinlock);

                spin_lock(&bootid_spinlock);
                if (!uuid[8])
                        generate_random_uuid(uuid);
                spin_unlock(&bootid_spinlock);
        }

        snprintf(uuid_string, sizeof(uuid_string), "%pU", uuid);
        return proc_dostring(&fake_table, 0, buf, lenp, ppos);
}

/* The same as proc_dointvec, but writes don't change anything. */
static int proc_do_rointvec(struct ctl_table *table, int write, void *buf,
                            size_t *lenp, loff_t *ppos)
{
        return write ? 0 : proc_dointvec(table, 0, buf, lenp, ppos);
}

extern struct ctl_table random_table[];
struct ctl_table random_table[] = {
        {
                .procname       = "poolsize",
                .data           = &sysctl_poolsize,
                .maxlen         = sizeof(int),
                .mode           = 0444,
                .proc_handler   = proc_dointvec,
        },
        {
                .procname       = "entropy_avail",
                .data           = &input_pool.init_bits,
                .maxlen         = sizeof(int),
                .mode           = 0444,
                .proc_handler   = proc_dointvec,
        },
        {
                .procname       = "write_wakeup_threshold",
                .data           = &sysctl_random_write_wakeup_bits,
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_do_rointvec,
        },
        {
                .procname       = "urandom_min_reseed_secs",
                .data           = &sysctl_random_min_urandom_seed,
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_do_rointvec,
        },
        {
                .procname       = "boot_id",
                .data           = &sysctl_bootid,
                .mode           = 0444,
                .proc_handler   = proc_do_uuid,
        },
        {
                .procname       = "uuid",
                .mode           = 0444,
                .proc_handler   = proc_do_uuid,
        },
        { }
};
#endif  /* CONFIG_SYSCTL */