diff options
Diffstat (limited to 'drivers/char/random.c')
-rw-r--r-- | drivers/char/random.c | 248 |
1 files changed, 132 insertions, 116 deletions
diff --git a/drivers/char/random.c b/drivers/char/random.c index 605969ed0f96..227fb7802738 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1,8 +1,7 @@ /* * random.c -- A strong random number generator * - * Copyright (C) 2017 Jason A. Donenfeld <Jason@zx2c4.com>. All - * Rights Reserved. + * Copyright (C) 2017-2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * * Copyright Matt Mackall <mpm@selenic.com>, 2003, 2004, 2005 * @@ -78,12 +77,12 @@ * an *estimate* of how many bits of randomness have been stored into * the random number generator's internal state. * - * When random bytes are desired, they are obtained by taking the SHA - * hash of the contents of the "entropy pool". The SHA hash avoids + * When random bytes are desired, they are obtained by taking the BLAKE2s + * hash of the contents of the "entropy pool". The BLAKE2s hash avoids * exposing the internal state of the entropy pool. It is believed to * be computationally infeasible to derive any useful information - * about the input of SHA from its output. Even if it is possible to - * analyze SHA in some clever way, as long as the amount of data + * about the input of BLAKE2s from its output. Even if it is possible to + * analyze BLAKE2s in some clever way, as long as the amount of data * returned from the generator is less than the inherent entropy in * the pool, the output data is totally unpredictable. For this * reason, the routine decreases its internal estimate of how many @@ -93,7 +92,7 @@ * If this estimate goes to zero, the routine can still generate * random numbers; however, an attacker may (at least in theory) be * able to infer the future output of the generator from prior - * outputs. This requires successful cryptanalysis of SHA, which is + * outputs. This requires successful cryptanalysis of BLAKE2s, which is * not believed to be feasible, but there is a remote possibility. * Nonetheless, these numbers should be useful for the vast majority * of purposes. @@ -200,8 +199,11 @@ * void add_device_randomness(const void *buf, unsigned int size); * void add_input_randomness(unsigned int type, unsigned int code, * unsigned int value); - * void add_interrupt_randomness(int irq, int irq_flags); + * void add_interrupt_randomness(int irq); * void add_disk_randomness(struct gendisk *disk); + * void add_hwgenerator_randomness(const char *buffer, size_t count, + * size_t entropy); + * void add_bootloader_randomness(const void *buf, unsigned int size); * * add_device_randomness() is for adding data to the random pool that * is likely to differ between two devices (or possibly even per boot). @@ -228,6 +230,14 @@ * particular randomness source. They do this by keeping track of the * first and second order deltas of the event timings. * + * 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 the same as add_hwgenerator_randomness() or + * add_device_randomness(), depending on whether or not the configuration + * option CONFIG_RANDOM_TRUST_BOOTLOADER is set. + * * Ensuring unpredictability at system startup * ============================================ * @@ -336,7 +346,7 @@ #include <linux/completion.h> #include <linux/uuid.h> #include <crypto/chacha.h> -#include <crypto/sha1.h> +#include <crypto/blake2s.h> #include <asm/processor.h> #include <linux/uaccess.h> @@ -356,10 +366,7 @@ #define INPUT_POOL_WORDS (1 << (INPUT_POOL_SHIFT-5)) #define OUTPUT_POOL_SHIFT 10 #define OUTPUT_POOL_WORDS (1 << (OUTPUT_POOL_SHIFT-5)) -#define EXTRACT_SIZE 10 - - -#define LONGS(x) (((x) + sizeof(unsigned long) - 1)/sizeof(unsigned long)) +#define EXTRACT_SIZE (BLAKE2S_HASH_SIZE / 2) /* * To allow fractional bits to be tracked, the entropy_count field is @@ -395,7 +402,7 @@ static int random_write_wakeup_bits = 28 * OUTPUT_POOL_WORDS; * 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 + * where we use BLAKE2s. 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 @@ -450,6 +457,10 @@ struct crng_state { static struct crng_state primary_crng = { .lock = __SPIN_LOCK_UNLOCKED(primary_crng.lock), + .state[0] = CHACHA_CONSTANT_EXPA, + .state[1] = CHACHA_CONSTANT_ND_3, + .state[2] = CHACHA_CONSTANT_2_BY, + .state[3] = CHACHA_CONSTANT_TE_K, }; /* @@ -461,6 +472,7 @@ static struct crng_state primary_crng = { * its value (from 0->1->2). */ static int crng_init = 0; +static bool crng_need_final_init = false; #define crng_ready() (likely(crng_init > 1)) static int crng_init_cnt = 0; static unsigned long crng_global_init_time = 0; @@ -539,7 +551,7 @@ static void _mix_pool_bytes(struct entropy_store *r, const void *in, unsigned long i, tap1, tap2, tap3, tap4, tap5; int input_rotate; int wordmask = r->poolinfo->poolwords - 1; - const char *bytes = in; + const unsigned char *bytes = in; __u32 w; tap1 = r->poolinfo->tap1; @@ -751,7 +763,6 @@ static int credit_entropy_bits_safe(struct entropy_store *r, int nbits) static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait); -#ifdef CONFIG_NUMA /* * Hack to deal with crazy userspace progams when they are all trying * to access /dev/urandom in parallel. The programs are almost @@ -759,7 +770,6 @@ static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait); * their brain damage. */ static struct crng_state **crng_node_pool __read_mostly; -#endif static void invalidate_batched_entropy(void); static void numa_crng_init(void); @@ -807,7 +817,7 @@ static bool __init crng_init_try_arch_early(struct crng_state *crng) return arch_init; } -static void __maybe_unused crng_initialize_secondary(struct crng_state *crng) +static void crng_initialize_secondary(struct crng_state *crng) { chacha_init_consts(crng->state); _get_random_bytes(&crng->state[4], sizeof(__u32) * 12); @@ -817,18 +827,46 @@ static void __maybe_unused crng_initialize_secondary(struct crng_state *crng) static void __init crng_initialize_primary(struct crng_state *crng) { - chacha_init_consts(crng->state); _extract_entropy(&input_pool, &crng->state[4], sizeof(__u32) * 12, 0); - if (crng_init_try_arch_early(crng) && trust_cpu) { + if (crng_init_try_arch_early(crng) && trust_cpu && crng_init < 2) { invalidate_batched_entropy(); numa_crng_init(); crng_init = 2; - pr_notice("crng done (trusting CPU's manufacturer)\n"); + pr_notice("crng init done (trusting CPU's manufacturer)\n"); } crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1; } -#ifdef CONFIG_NUMA +static void crng_finalize_init(struct crng_state *crng) +{ + if (crng != &primary_crng || crng_init >= 2) + return; + if (!system_wq) { + /* We can't call numa_crng_init until we have workqueues, + * so mark this for processing later. */ + crng_need_final_init = true; + return; + } + + invalidate_batched_entropy(); + numa_crng_init(); + crng_init = 2; + process_random_ready_list(); + wake_up_interruptible(&crng_init_wait); + kill_fasync(&fasync, SIGIO, POLL_IN); + pr_notice("crng init done\n"); + if (unseeded_warning.missed) { + pr_notice("%d get_random_xx warning(s) missed due to ratelimiting\n", + unseeded_warning.missed); + unseeded_warning.missed = 0; + } + if (urandom_warning.missed) { + pr_notice("%d urandom warning(s) missed due to ratelimiting\n", + urandom_warning.missed); + urandom_warning.missed = 0; + } +} + static void do_numa_crng_init(struct work_struct *work) { int i; @@ -843,8 +881,8 @@ static void do_numa_crng_init(struct work_struct *work) crng_initialize_secondary(crng); pool[i] = crng; } - mb(); - if (cmpxchg(&crng_node_pool, NULL, pool)) { + /* pairs with READ_ONCE() in select_crng() */ + if (cmpxchg_release(&crng_node_pool, NULL, pool) != NULL) { for_each_node(i) kfree(pool[i]); kfree(pool); @@ -855,20 +893,35 @@ static DECLARE_WORK(numa_crng_init_work, do_numa_crng_init); static void numa_crng_init(void) { - schedule_work(&numa_crng_init_work); + if (IS_ENABLED(CONFIG_NUMA)) + schedule_work(&numa_crng_init_work); +} + +static struct crng_state *select_crng(void) +{ + if (IS_ENABLED(CONFIG_NUMA)) { + struct crng_state **pool; + int nid = numa_node_id(); + + /* pairs with cmpxchg_release() in do_numa_crng_init() */ + pool = READ_ONCE(crng_node_pool); + if (pool && pool[nid]) + return pool[nid]; + } + + return &primary_crng; } -#else -static void numa_crng_init(void) {} -#endif /* * crng_fast_load() can be called by code in the interrupt service - * path. So we can't afford to dilly-dally. + * path. So we can't afford to dilly-dally. Returns the number of + * bytes processed from cp. */ -static int crng_fast_load(const char *cp, size_t len) +static size_t crng_fast_load(const char *cp, size_t len) { unsigned long flags; char *p; + size_t ret = 0; if (!spin_trylock_irqsave(&primary_crng.lock, flags)) return 0; @@ -879,7 +932,7 @@ static int crng_fast_load(const char *cp, size_t len) p = (unsigned char *) &primary_crng.state[4]; while (len > 0 && crng_init_cnt < CRNG_INIT_CNT_THRESH) { p[crng_init_cnt % CHACHA_KEY_SIZE] ^= *cp; - cp++; crng_init_cnt++; len--; + cp++; crng_init_cnt++; len--; ret++; } spin_unlock_irqrestore(&primary_crng.lock, flags); if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) { @@ -887,7 +940,7 @@ static int crng_fast_load(const char *cp, size_t len) crng_init = 1; pr_notice("fast init done\n"); } - return 1; + return ret; } /* @@ -962,41 +1015,24 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r) crng->state[i+4] ^= buf.key[i] ^ rv; } memzero_explicit(&buf, sizeof(buf)); - crng->init_time = jiffies; + WRITE_ONCE(crng->init_time, jiffies); spin_unlock_irqrestore(&crng->lock, flags); - if (crng == &primary_crng && crng_init < 2) { - invalidate_batched_entropy(); - numa_crng_init(); - crng_init = 2; - process_random_ready_list(); - wake_up_interruptible(&crng_init_wait); - kill_fasync(&fasync, SIGIO, POLL_IN); - pr_notice("crng init done\n"); - if (unseeded_warning.missed) { - pr_notice("%d get_random_xx warning(s) missed due to ratelimiting\n", - unseeded_warning.missed); - unseeded_warning.missed = 0; - } - if (urandom_warning.missed) { - pr_notice("%d urandom warning(s) missed due to ratelimiting\n", - urandom_warning.missed); - urandom_warning.missed = 0; - } - } + crng_finalize_init(crng); } static void _extract_crng(struct crng_state *crng, __u8 out[CHACHA_BLOCK_SIZE]) { - unsigned long v, flags; - - if (crng_ready() && - (time_after(crng_global_init_time, crng->init_time) || - time_after(jiffies, crng->init_time + CRNG_RESEED_INTERVAL))) - crng_reseed(crng, crng == &primary_crng ? &input_pool : NULL); + unsigned long flags, init_time; + + if (crng_ready()) { + init_time = READ_ONCE(crng->init_time); + if (time_after(READ_ONCE(crng_global_init_time), init_time) || + time_after(jiffies, init_time + CRNG_RESEED_INTERVAL)) + crng_reseed(crng, crng == &primary_crng ? + &input_pool : NULL); + } 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]++; @@ -1005,15 +1041,7 @@ static void _extract_crng(struct crng_state *crng, static void extract_crng(__u8 out[CHACHA_BLOCK_SIZE]) { - struct crng_state *crng = NULL; - -#ifdef CONFIG_NUMA - if (crng_node_pool) - crng = crng_node_pool[numa_node_id()]; - if (crng == NULL) -#endif - crng = &primary_crng; - _extract_crng(crng, out); + _extract_crng(select_crng(), out); } /* @@ -1042,15 +1070,7 @@ static void _crng_backtrack_protect(struct crng_state *crng, static void crng_backtrack_protect(__u8 tmp[CHACHA_BLOCK_SIZE], int used) { - struct crng_state *crng = NULL; - -#ifdef CONFIG_NUMA - if (crng_node_pool) - crng = crng_node_pool[numa_node_id()]; - if (crng == NULL) -#endif - crng = &primary_crng; - _crng_backtrack_protect(crng, tmp, used); + _crng_backtrack_protect(select_crng(), tmp, used); } static ssize_t extract_crng_user(void __user *buf, size_t nbytes) @@ -1242,7 +1262,7 @@ static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs) return *ptr; } -void add_interrupt_randomness(int irq, int irq_flags) +void add_interrupt_randomness(int irq) { struct entropy_store *r; struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness); @@ -1269,7 +1289,7 @@ void add_interrupt_randomness(int irq, int irq_flags) if (unlikely(crng_init == 0)) { if ((fast_pool->count >= 64) && crng_fast_load((char *) fast_pool->pool, - sizeof(fast_pool->pool))) { + sizeof(fast_pool->pool)) > 0) { fast_pool->count = 0; fast_pool->last = now; } @@ -1368,56 +1388,49 @@ retry: */ static void extract_buf(struct entropy_store *r, __u8 *out) { - int i; - union { - __u32 w[5]; - unsigned long l[LONGS(20)]; - } hash; - __u32 workspace[SHA1_WORKSPACE_WORDS]; + struct blake2s_state state __aligned(__alignof__(unsigned long)); + u8 hash[BLAKE2S_HASH_SIZE]; + unsigned long *salt; unsigned long flags; + blake2s_init(&state, sizeof(hash)); + /* * If we have an architectural hardware random number - * generator, use it for SHA's initial vector + * generator, use it for BLAKE2's salt & personal fields. */ - sha1_init(hash.w); - for (i = 0; i < LONGS(20); i++) { + for (salt = (unsigned long *)&state.h[4]; + salt < (unsigned long *)&state.h[8]; ++salt) { unsigned long v; if (!arch_get_random_long(&v)) break; - hash.l[i] = v; + *salt ^= v; } - /* Generate a hash across the pool, 16 words (512 bits) at a time */ + /* Generate a hash across the pool */ spin_lock_irqsave(&r->lock, flags); - for (i = 0; i < r->poolinfo->poolwords; i += 16) - sha1_transform(hash.w, (__u8 *)(r->pool + i), workspace); + blake2s_update(&state, (const u8 *)r->pool, + r->poolinfo->poolwords * sizeof(*r->pool)); + blake2s_final(&state, hash); /* final zeros out state */ /* * We mix the hash back into the pool to prevent backtracking * attacks (where the attacker knows the state of the pool * plus the current outputs, and attempts to find previous - * ouputs), unless the hash function can be inverted. By - * mixing at least a SHA1 worth of hash data back, we make + * outputs), unless the hash function can be inverted. By + * mixing at least a hash worth of hash data back, we make * brute-forcing the feedback as hard as brute-forcing the * hash. */ - __mix_pool_bytes(r, hash.w, sizeof(hash.w)); + __mix_pool_bytes(r, hash, sizeof(hash)); spin_unlock_irqrestore(&r->lock, flags); - memzero_explicit(workspace, sizeof(workspace)); - - /* - * In case the hash function has some recognizable output - * pattern, we fold it in half. Thus, we always feed back - * twice as much data as we output. + /* Note that EXTRACT_SIZE is half of hash size here, because above + * we've dumped the full length back into mixer. By reducing the + * amount that we emit, we retain a level of forward secrecy. */ - hash.w[0] ^= hash.w[3]; - hash.w[1] ^= hash.w[4]; - hash.w[2] ^= rol32(hash.w[2], 16); - - memcpy(out, &hash, EXTRACT_SIZE); - memzero_explicit(&hash, sizeof(hash)); + memcpy(out, hash, EXTRACT_SIZE); + memzero_explicit(hash, sizeof(hash)); } static ssize_t _extract_entropy(struct entropy_store *r, void *buf, @@ -1775,6 +1788,8 @@ static void __init init_std_data(struct entropy_store *r) int __init rand_initialize(void) { init_std_data(&input_pool); + if (crng_need_final_init) + crng_finalize_init(&primary_crng); crng_initialize_primary(&primary_crng); crng_global_init_time = jiffies; if (ratelimit_disable) { @@ -1816,7 +1831,6 @@ urandom_read_nowarn(struct file *file, char __user *buf, size_t nbytes, static ssize_t urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { - unsigned long flags; static int maxwarn = 10; if (!crng_ready() && maxwarn > 0) { @@ -1824,9 +1838,6 @@ urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) if (__ratelimit(&urandom_warning)) pr_notice("%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); } return urandom_read_nowarn(file, buf, nbytes, ppos); @@ -1949,7 +1960,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) if (crng_init < 2) return -ENODATA; crng_reseed(&primary_crng, &input_pool); - crng_global_init_time = jiffies - 1; + WRITE_ONCE(crng_global_init_time, jiffies - 1); return 0; default: return -EINVAL; @@ -2275,15 +2286,20 @@ void add_hwgenerator_randomness(const char *buffer, size_t count, struct entropy_store *poolp = &input_pool; if (unlikely(crng_init == 0)) { - crng_fast_load(buffer, count); - return; + size_t ret = crng_fast_load(buffer, count); + mix_pool_bytes(poolp, buffer, ret); + count -= ret; + buffer += ret; + if (!count || crng_init == 0) + return; } /* Suspend writing if we're above the trickle threshold. * We'll be woken up again once below random_write_wakeup_thresh, * or when the calling thread is about to terminate. */ - wait_event_interruptible(random_write_wait, kthread_should_stop() || + wait_event_interruptible(random_write_wait, + !system_wq || kthread_should_stop() || ENTROPY_BITS(&input_pool) <= random_write_wakeup_bits); mix_pool_bytes(poolp, buffer, count); credit_entropy_bits(poolp, entropy); |