diff options
Diffstat (limited to 'drivers/char/random.c')
| -rw-r--r-- | drivers/char/random.c | 2511 |
1 files changed, 1361 insertions, 1150 deletions
diff --git a/drivers/char/random.c b/drivers/char/random.c index 0d91fe52f3f5..bab03c7c4194 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1,239 +1,29 @@ +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* - * random.c -- A strong random number generator - * + * Copyright (C) 2017-2024 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. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, and the entire permission notice in its entirety, - * including the disclaimer of warranties. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. The name of the author may not be used to endorse or promote - * products derived from this software without specific prior - * written permission. - * - * ALTERNATIVELY, this product may be distributed under the terms of - * the GNU General Public License, in which case the provisions of the GPL are - * required INSTEAD OF the above restrictions. (This clause is - * necessary due to a potential bad interaction between the GPL and - * the restrictions contained in a BSD-style copyright.) - * - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES - * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE, ALL OF - * WHICH ARE HEREBY DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT - * OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR - * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF - * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE - * USE OF THIS SOFTWARE, EVEN IF NOT ADVISED OF THE POSSIBILITY OF SUCH - * DAMAGE. + * 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. */ -/* - * (now, with legal B.S. out of the way.....) - * - * This routine gathers environmental noise from device drivers, etc., - * and returns good random numbers, suitable for cryptographic use. - * Besides the obvious cryptographic uses, these numbers are also good - * for seeding TCP sequence numbers, and other places where it is - * desirable to have numbers which are not only random, but hard to - * predict by an attacker. - * - * Theory of operation - * =================== - * - * Computers are very predictable devices. Hence it is extremely hard - * to produce truly random numbers on a computer --- as opposed to - * pseudo-random numbers, which can easily generated by using a - * algorithm. Unfortunately, it is very easy for attackers to guess - * the sequence of pseudo-random number generators, and for some - * applications this is not acceptable. So instead, we must try to - * gather "environmental noise" from the computer's environment, which - * must be hard for outside attackers to observe, and use that to - * generate random numbers. In a Unix environment, this is best done - * from inside the kernel. - * - * Sources of randomness from the environment include inter-keyboard - * timings, inter-interrupt timings from some interrupts, and other - * events which are both (a) non-deterministic and (b) hard for an - * outside observer to measure. Randomness from these sources are - * added to an "entropy pool", which is mixed using a CRC-like function. - * This is not cryptographically strong, but it is adequate assuming - * the randomness is not chosen maliciously, and it is fast enough that - * the overhead of doing it on every interrupt is very reasonable. - * As random bytes are mixed into the entropy pool, the routines keep - * 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 - * 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 - * 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 - * bits of "true randomness" are contained in the entropy pool as it - * outputs random numbers. - * - * 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 - * not believed to be feasible, but there is a remote possibility. - * Nonetheless, these numbers should be useful for the vast majority - * of purposes. - * - * Exported interfaces ---- output - * =============================== - * - * There are three exported interfaces; the first is one designed to - * be used from within the kernel: - * - * void get_random_bytes(void *buf, int nbytes); - * - * This interface will return the requested number of random bytes, - * and place it in the requested buffer. - * - * The two other interfaces are two character devices /dev/random and - * /dev/urandom. /dev/random is suitable for use when very high - * quality randomness is desired (for example, for key generation or - * one-time pads), as it will only return a maximum of the number of - * bits of randomness (as estimated by the random number generator) - * contained in the entropy pool. - * - * The /dev/urandom device does not have this limit, and will return - * as many bytes as are requested. As more and more random bytes are - * requested without giving time for the entropy pool to recharge, - * this will result in random numbers that are merely cryptographically - * strong. For many applications, however, this is acceptable. - * - * Exported interfaces ---- input - * ============================== - * - * The current exported interfaces for gathering environmental noise - * from the devices are: - * - * 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_disk_randomness(struct gendisk *disk); - * - * add_device_randomness() is for adding data to the random 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* add 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_input_randomness() uses the input layer interrupt timing, as well as - * the event type information from the hardware. - * - * 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 randomness roughly once a second. - * - * 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. - * - * All of these routines try to estimate how many bits of randomness a - * particular randomness source. They do this by keeping track of the - * first and second order deltas of the event timings. - * - * Ensuring unpredictability at system startup - * ============================================ - * - * When any operating system starts up, it will go through a sequence - * of actions that are fairly predictable by an adversary, especially - * if the start-up does not involve interaction with a human operator. - * This reduces the actual number of bits of unpredictability in the - * entropy pool below the value in entropy_count. In order to - * counteract this effect, it helps to carry information in the - * entropy pool across shut-downs and start-ups. To do this, put the - * following lines an appropriate script which is run during the boot - * sequence: - * - * echo "Initializing random number generator..." - * random_seed=/var/run/random-seed - * # Carry a random seed from start-up to start-up - * # Load and then save the whole entropy pool - * if [ -f $random_seed ]; then - * cat $random_seed >/dev/urandom - * else - * touch $random_seed - * fi - * chmod 600 $random_seed - * dd if=/dev/urandom of=$random_seed count=1 bs=512 - * - * and the following lines in an appropriate script which is run as - * the system is shutdown: - * - * # Carry a random seed from shut-down to start-up - * # Save the whole entropy pool - * echo "Saving random seed..." - * random_seed=/var/run/random-seed - * touch $random_seed - * chmod 600 $random_seed - * dd if=/dev/urandom of=$random_seed count=1 bs=512 - * - * For example, on most modern systems using the System V init - * scripts, such code fragments would be found in - * /etc/rc.d/init.d/random. On older Linux systems, the correct script - * location might be in /etc/rcb.d/rc.local or /etc/rc.d/rc.0. - * - * Effectively, these commands cause the contents of the entropy pool - * to be saved at shut-down time and reloaded into the entropy pool at - * start-up. (The 'dd' in the addition to the bootup script is to - * make sure that /etc/random-seed is different for every start-up, - * even if the system crashes without executing rc.0.) Even with - * complete knowledge of the start-up activities, predicting the state - * of the entropy pool requires knowledge of the previous history of - * the system. - * - * Configuring the /dev/random driver under Linux - * ============================================== - * - * The /dev/random driver under Linux uses minor numbers 8 and 9 of - * the /dev/mem major number (#1). So if your system does not have - * /dev/random and /dev/urandom created already, they can be created - * by using the commands: - * - * mknod /dev/random c 1 8 - * mknod /dev/urandom c 1 9 - * - * Acknowledgements: - * ================= - * - * Ideas for constructing this random number generator were derived - * from Pretty Good Privacy's random number generator, and from private - * discussions with Phil Karn. Colin Plumb provided a faster random - * number generator, which speed up the mixing function of the entropy - * pool, taken from PGPfone. Dale Worley has also contributed many - * useful ideas and suggestions to improve this driver. - * - * Any flaws in the design are solely my responsibility, and should - * not be attributed to the Phil, Colin, or any of authors of PGP. - * - * Further background information on this topic may be obtained from - * RFC 1750, "Randomness Recommendations for Security", by Donald - * Eastlake, Steve Crocker, and Jeff Schiller. - */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/utsname.h> #include <linux/module.h> @@ -246,901 +36,1211 @@ #include <linux/poll.h> #include <linux/init.h> #include <linux/fs.h> -#include <linux/genhd.h> +#include <linux/blkdev.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/cryptohash.h> -#include <linux/fips.h> #include <linux/ptrace.h> -#include <linux/kmemcheck.h> - -#ifdef CONFIG_GENERIC_HARDIRQS -# include <linux/irq.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/suspend.h> +#include <linux/siphash.h> +#include <linux/sched/isolation.h> +#include <crypto/chacha.h> +#include <crypto/blake2s.h> +#ifdef CONFIG_VDSO_GETRANDOM +#include <vdso/getrandom.h> +#include <vdso/datapage.h> +#include <vdso/vsyscall.h> #endif - +#include <asm/archrandom.h> #include <asm/processor.h> -#include <asm/uaccess.h> #include <asm/irq.h> #include <asm/irq_regs.h> #include <asm/io.h> -#define CREATE_TRACE_POINTS -#include <trace/events/random.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. + * + *********************************************************************/ /* - * Configuration information + * crng_init is protected by base_crng->lock, and only increases + * its value (from empty->early->ready). */ -#define INPUT_POOL_WORDS 128 -#define OUTPUT_POOL_WORDS 32 -#define SEC_XFER_SIZE 512 -#define EXTRACT_SIZE 10 +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; +static DEFINE_STATIC_KEY_FALSE(crng_is_ready); +#define crng_ready() (static_branch_likely(&crng_is_ready) || 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 ATOMIC_NOTIFIER_HEAD(random_ready_notifier); -#define LONGS(x) (((x) + sizeof(unsigned long) - 1)/sizeof(unsigned long)) +/* 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"); /* - * The minimum number of bits of entropy before we wake up a read on - * /dev/random. Should be enough to do a significant reseed. + * 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_{u8, + * u16,u32,u64,long} family of functions. + * + * Returns: true if the input pool has been seeded. + * false if the input pool has not been seeded. */ -static int random_read_wakeup_thresh = 64; +bool rng_is_initialized(void) +{ + return crng_ready(); +} +EXPORT_SYMBOL(rng_is_initialized); -/* - * If the entropy count falls under this number of bits, then we - * should wake up processes which are selecting or polling on write - * access to /dev/random. - */ -static int random_write_wakeup_thresh = 128; +static void __cold crng_set_ready(struct work_struct *work) +{ + static_branch_enable(&crng_is_ready); +} + +/* Used by wait_for_random_bytes(), and considered an entropy collector, below. */ +static void try_to_generate_entropy(void); /* - * When the input pool goes over trickle_thresh, start dropping most - * samples to avoid wasting CPU time and reduce lock contention. + * 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_{u8,u16,u32,u64, + * 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; -static int trickle_thresh __read_mostly = INPUT_POOL_WORDS * 28; - -static DEFINE_PER_CPU(int, trickle_count); + 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); /* - * A pool of size .poolwords is stirred with a primitive polynomial - * of degree .poolwords over GF(2). The taps for various sizes are - * defined below. They are chosen to be evenly spaced (minimum RMS - * distance from evenly spaced; the numbers in the comments are a - * scaled squared error sum) except for the last tap, which is 1 to - * get the twisting happening as fast as possible. + * Add a callback function that will be invoked when the crng is initialised, + * or immediately if it already has been. Only use this is you are absolutely + * sure it is required. Most users should instead be able to test + * `rng_is_initialized()` on demand, or make use of `get_random_bytes_wait()`. */ -static struct poolinfo { - int poolwords; - int tap1, tap2, tap3, tap4, tap5; -} poolinfo_table[] = { - /* x^128 + x^103 + x^76 + x^51 +x^25 + x + 1 -- 105 */ - { 128, 103, 76, 51, 25, 1 }, - /* x^32 + x^26 + x^20 + x^14 + x^7 + x + 1 -- 15 */ - { 32, 26, 20, 14, 7, 1 }, -#if 0 - /* x^2048 + x^1638 + x^1231 + x^819 + x^411 + x + 1 -- 115 */ - { 2048, 1638, 1231, 819, 411, 1 }, - - /* x^1024 + x^817 + x^615 + x^412 + x^204 + x + 1 -- 290 */ - { 1024, 817, 615, 412, 204, 1 }, - - /* x^1024 + x^819 + x^616 + x^410 + x^207 + x^2 + 1 -- 115 */ - { 1024, 819, 616, 410, 207, 2 }, - - /* x^512 + x^411 + x^308 + x^208 + x^104 + x + 1 -- 225 */ - { 512, 411, 308, 208, 104, 1 }, - - /* x^512 + x^409 + x^307 + x^206 + x^102 + x^2 + 1 -- 95 */ - { 512, 409, 307, 206, 102, 2 }, - /* x^512 + x^409 + x^309 + x^205 + x^103 + x^2 + 1 -- 95 */ - { 512, 409, 309, 205, 103, 2 }, - - /* x^256 + x^205 + x^155 + x^101 + x^52 + x + 1 -- 125 */ - { 256, 205, 155, 101, 52, 1 }, - - /* x^128 + x^103 + x^78 + x^51 + x^27 + x^2 + 1 -- 70 */ - { 128, 103, 78, 51, 27, 2 }, - - /* x^64 + x^52 + x^39 + x^26 + x^14 + x + 1 -- 15 */ - { 64, 52, 39, 26, 14, 1 }, -#endif -}; +int __cold execute_with_initialized_rng(struct notifier_block *nb) +{ + unsigned long flags; + int ret = 0; + + spin_lock_irqsave(&random_ready_notifier.lock, flags); + if (crng_ready()) + nb->notifier_call(nb, 0, NULL); + else + ret = raw_notifier_chain_register((struct raw_notifier_head *)&random_ready_notifier.head, nb); + spin_unlock_irqrestore(&random_ready_notifier.lock, flags); + return ret; +} -#define POOLBITS poolwords*32 -#define POOLBYTES poolwords*4 +#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) -/* - * For the purposes of better mixing, we use the CRC-32 polynomial as - * well to make a twisted Generalized Feedback Shift Reigster - * - * (See M. Matsumoto & Y. Kurita, 1992. Twisted GFSR generators. ACM - * Transactions on Modeling and Computer Simulation 2(3):179-194. - * Also see M. Matsumoto & Y. Kurita, 1994. Twisted GFSR generators - * II. ACM Transactions on Mdeling and Computer Simulation 4:254-266) + +/********************************************************************* * - * Thanks to Colin Plumb for suggesting this. + * Fast key erasure RNG, the "crng". * - * We have not analyzed the resultant polynomial to prove it primitive; - * in fact it almost certainly isn't. Nonetheless, the irreducible factors - * of a random large-degree polynomial over GF(2) are more than large enough - * that periodicity is not a concern. + * 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>. * - * The input hash is much less sensitive than the output hash. All - * that we want of it is that it be a good non-cryptographic hash; - * i.e. it not produce collisions when fed "random" data of the sort - * we expect to see. As long as the pool state differs for different - * inputs, we have preserved the input entropy and done a good job. - * The fact that an intelligent attacker can construct inputs that - * will produce controlled alterations to the pool's state is not - * important because we don't consider such inputs to contribute any - * randomness. The only property we need with respect to them is that - * the attacker can't increase his/her knowledge of the pool's state. - * Since all additions are reversible (knowing the final state and the - * input, you can reconstruct the initial state), if an attacker has - * any uncertainty about the initial state, he/she can only shuffle - * that uncertainty about, but never cause any collisions (which would - * decrease the uncertainty). + * There are a few exported interfaces for use by other drivers: * - * The chosen system lets the state of the pool be (essentially) the input - * modulo the generator polymnomial. Now, for random primitive polynomials, - * this is a universal class of hash functions, meaning that the chance - * of a collision is limited by the attacker's knowledge of the generator - * polynomail, so if it is chosen at random, an attacker can never force - * a collision. Here, we use a fixed polynomial, but we *can* assume that - * ###--> it is unknown to the processes generating the input entropy. <-### - * Because of this important property, this is a good, collision-resistant - * hash; hash collisions will occur no more often than chance. - */ - -/* - * Static global variables - */ -static DECLARE_WAIT_QUEUE_HEAD(random_read_wait); -static DECLARE_WAIT_QUEUE_HEAD(random_write_wait); -static struct fasync_struct *fasync; - -static bool debug; -module_param(debug, bool, 0644); -#define DEBUG_ENT(fmt, arg...) do { \ - if (debug) \ - printk(KERN_DEBUG "random %04d %04d %04d: " \ - fmt,\ - input_pool.entropy_count,\ - blocking_pool.entropy_count,\ - nonblocking_pool.entropy_count,\ - ## arg); } while (0) - -/********************************************************************** + * void get_random_bytes(void *buf, size_t len) + * u8 get_random_u8() + * u16 get_random_u16() + * u32 get_random_u32() + * u32 get_random_u32_below(u32 ceil) + * u32 get_random_u32_above(u32 floor) + * u32 get_random_u32_inclusive(u32 floor, u32 ceil) + * u64 get_random_u64() + * unsigned long get_random_long() * - * OS independent entropy store. Here are the functions which handle - * storing entropy in an entropy pool. + * 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 u8, u16, u32, u64, 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. * - **********************************************************************/ - -struct entropy_store; -struct entropy_store { - /* read-only data: */ - struct poolinfo *poolinfo; - __u32 *pool; - const char *name; - struct entropy_store *pull; - int limit; + *********************************************************************/ - /* read-write data: */ - spinlock_t lock; - unsigned add_ptr; - unsigned input_rotate; - int entropy_count; - int entropy_total; - unsigned int initialized:1; - bool last_data_init; - __u8 last_data[EXTRACT_SIZE]; +enum { + CRNG_RESEED_START_INTERVAL = HZ, + CRNG_RESEED_INTERVAL = 60 * HZ }; -static __u32 input_pool_data[INPUT_POOL_WORDS]; -static __u32 blocking_pool_data[OUTPUT_POOL_WORDS]; -static __u32 nonblocking_pool_data[OUTPUT_POOL_WORDS]; - -static struct entropy_store input_pool = { - .poolinfo = &poolinfo_table[0], - .name = "input", - .limit = 1, - .lock = __SPIN_LOCK_UNLOCKED(input_pool.lock), - .pool = input_pool_data +static struct { + u8 key[CHACHA_KEY_SIZE] __aligned(__alignof__(long)); + unsigned long generation; + spinlock_t lock; +} base_crng = { + .lock = __SPIN_LOCK_UNLOCKED(base_crng.lock) }; -static struct entropy_store blocking_pool = { - .poolinfo = &poolinfo_table[1], - .name = "blocking", - .limit = 1, - .pull = &input_pool, - .lock = __SPIN_LOCK_UNLOCKED(blocking_pool.lock), - .pool = blocking_pool_data +struct crng { + u8 key[CHACHA_KEY_SIZE]; + unsigned long generation; + local_lock_t lock; }; -static struct entropy_store nonblocking_pool = { - .poolinfo = &poolinfo_table[1], - .name = "nonblocking", - .pull = &input_pool, - .lock = __SPIN_LOCK_UNLOCKED(nonblocking_pool.lock), - .pool = nonblocking_pool_data +static DEFINE_PER_CPU(struct crng, crngs) = { + .generation = ULONG_MAX, + .lock = INIT_LOCAL_LOCK(crngs.lock), }; -static __u32 const twist_table[8] = { - 0x00000000, 0x3b6e20c8, 0x76dc4190, 0x4db26158, - 0xedb88320, 0xd6d6a3e8, 0x9b64c2b0, 0xa00ae278 }; - /* - * 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. - * - * The pool is stirred with a primitive polynomial of the appropriate - * degree, and then twisted. We twist by three bits at a time because - * it's cheap to do so and helps slightly in the expected case where - * the entropy is concentrated in the low-order bits. + * Return the interval until the next reseeding, which is normally + * CRNG_RESEED_INTERVAL, but during early boot, it is at an interval + * proportional to the uptime. */ -static void _mix_pool_bytes(struct entropy_store *r, const void *in, - int nbytes, __u8 out[64]) +static unsigned int crng_reseed_interval(void) { - unsigned long i, j, tap1, tap2, tap3, tap4, tap5; - int input_rotate; - int wordmask = r->poolinfo->poolwords - 1; - const char *bytes = in; - __u32 w; - - tap1 = r->poolinfo->tap1; - tap2 = r->poolinfo->tap2; - tap3 = r->poolinfo->tap3; - tap4 = r->poolinfo->tap4; - tap5 = r->poolinfo->tap5; - - smp_rmb(); - input_rotate = ACCESS_ONCE(r->input_rotate); - i = ACCESS_ONCE(r->add_ptr); - - /* mix one byte at a time to simplify size handling and churn faster */ - while (nbytes--) { - w = rol32(*bytes++, input_rotate & 31); - i = (i - 1) & wordmask; - - /* XOR in the various taps */ - w ^= r->pool[i]; - w ^= r->pool[(i + tap1) & wordmask]; - w ^= r->pool[(i + tap2) & wordmask]; - w ^= r->pool[(i + tap3) & wordmask]; - w ^= r->pool[(i + tap4) & wordmask]; - w ^= r->pool[(i + tap5) & wordmask]; - - /* Mix the result back in with a twist */ - r->pool[i] = (w >> 3) ^ twist_table[w & 7]; - - /* - * Normally, we add 7 bits of rotation to the pool. - * At the beginning of the pool, add an extra 7 bits - * rotation, so that successive passes spread the - * input bits across the pool evenly. - */ - input_rotate += i ? 7 : 14; + static bool early_boot = true; + + 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 + return max_t(unsigned int, CRNG_RESEED_START_INTERVAL, + (unsigned int)uptime / 2 * HZ); } - - ACCESS_ONCE(r->input_rotate) = input_rotate; - ACCESS_ONCE(r->add_ptr) = i; - smp_wmb(); - - if (out) - for (j = 0; j < 16; j++) - ((__u32 *)out)[j] = r->pool[(i - j) & wordmask]; + return CRNG_RESEED_INTERVAL; } -static void __mix_pool_bytes(struct entropy_store *r, const void *in, - int nbytes, __u8 out[64]) -{ - trace_mix_pool_bytes_nolock(r->name, nbytes, _RET_IP_); - _mix_pool_bytes(r, in, nbytes, out); -} +/* 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); -static void mix_pool_bytes(struct entropy_store *r, const void *in, - int nbytes, __u8 out[64]) +/* This extracts a new crng key from the input pool. */ +static void crng_reseed(struct work_struct *work) { + static DECLARE_DELAYED_WORK(next_reseed, crng_reseed); unsigned long flags; + unsigned long next_gen; + u8 key[CHACHA_KEY_SIZE]; - trace_mix_pool_bytes(r->name, nbytes, _RET_IP_); - spin_lock_irqsave(&r->lock, flags); - _mix_pool_bytes(r, in, nbytes, out); - spin_unlock_irqrestore(&r->lock, flags); -} + /* Immediately schedule the next reseeding, so that it fires sooner rather than later. */ + if (likely(system_dfl_wq)) + queue_delayed_work(system_dfl_wq, &next_reseed, crng_reseed_interval()); -struct fast_pool { - __u32 pool[4]; - unsigned long last; - unsigned short count; - unsigned char rotate; - unsigned char last_timer_intr; -}; + 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); +#ifdef CONFIG_VDSO_GETRANDOM + /* base_crng.generation's invalid value is ULONG_MAX, while + * vdso_k_rng_data->generation's invalid value is 0, so add one to the + * former to arrive at the latter. Use smp_store_release so that this + * is ordered with the write above to base_crng.generation. Pairs with + * the smp_rmb() before the syscall in the vDSO code. + * + * Cast to unsigned long for 32-bit architectures, since atomic 64-bit + * operations are not supported on those architectures. This is safe + * because base_crng.generation is a 32-bit value. On big-endian + * architectures it will be stored in the upper 32 bits, but that's okay + * because the vDSO side only checks whether the value changed, without + * actually using or interpreting the value. + */ + smp_store_release((unsigned long *)&vdso_k_rng_data->generation, next_gen + 1); +#endif + if (!static_branch_likely(&crng_is_ready)) + crng_init = CRNG_READY; + spin_unlock_irqrestore(&base_crng.lock, flags); + memzero_explicit(key, sizeof(key)); +} /* - * 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. + * This generates a ChaCha block using the provided key, and then + * immediately overwrites 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->x[4] + * so that this function overwrites it before returning. */ -static void fast_mix(struct fast_pool *f, const void *in, int nbytes) +static void crng_fast_key_erasure(u8 key[CHACHA_KEY_SIZE], + struct chacha_state *chacha_state, + u8 *random_data, size_t random_data_len) { - const char *bytes = in; - __u32 w; - unsigned i = f->count; - unsigned input_rotate = f->rotate; - - while (nbytes--) { - w = rol32(*bytes++, input_rotate & 31) ^ f->pool[i & 3] ^ - f->pool[(i + 1) & 3]; - f->pool[i & 3] = (w >> 3) ^ twist_table[w & 7]; - input_rotate += (i++ & 3) ? 7 : 14; - } - f->count = i; - f->rotate = input_rotate; + u8 first_block[CHACHA_BLOCK_SIZE]; + + BUG_ON(random_data_len > 32); + + chacha_init_consts(chacha_state); + memcpy(&chacha_state->x[4], key, CHACHA_KEY_SIZE); + memset(&chacha_state->x[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)); } /* - * Credit (or debit) the entropy store with n bits of entropy + * 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 credit_entropy_bits(struct entropy_store *r, int nbits) +static void crng_make_state(struct chacha_state *chacha_state, + u8 *random_data, size_t random_data_len) { - int entropy_count, orig; + unsigned long flags; + struct crng *crng; - if (!nbits) - return; + BUG_ON(random_data_len > 32); - DEBUG_ENT("added %d entropy credits to %s\n", nbits, r->name); -retry: - entropy_count = orig = ACCESS_ONCE(r->entropy_count); - entropy_count += nbits; - - if (entropy_count < 0) { - DEBUG_ENT("negative entropy/overflow\n"); - entropy_count = 0; - } else if (entropy_count > r->poolinfo->POOLBITS) - entropy_count = r->poolinfo->POOLBITS; - if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig) - goto retry; - - if (!r->initialized && nbits > 0) { - r->entropy_total += nbits; - if (r->entropy_total > 128) - r->initialized = 1; + /* + * 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; } - trace_credit_entropy_bits(r->name, nbits, entropy_count, - r->entropy_total, _RET_IP_); + local_lock_irqsave(&crngs.lock, flags); + crng = raw_cpu_ptr(&crngs); - /* should we wake readers? */ - if (r == &input_pool && entropy_count >= random_read_wakeup_thresh) { - wake_up_interruptible(&random_read_wait); - kill_fasync(&fasync, SIGIO, POLL_IN); + /* + * If 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); } -/********************************************************************* - * - * Entropy input management - * - *********************************************************************/ +static void _get_random_bytes(void *buf, size_t len) +{ + struct chacha_state chacha_state; + u8 tmp[CHACHA_BLOCK_SIZE]; + size_t first_block_len; -/* There is one of these per entropy source */ -struct timer_rand_state { - cycles_t last_time; - long last_delta, last_delta2; - unsigned dont_count_entropy:1; -}; + if (!len) + return; -/* - * Add device- or boot-specific data to the input and nonblocking - * pools to help initialize them to unique values. - * - * None of this adds any entropy, it is meant to avoid the - * problem of the nonblocking pool having similar initial state - * across largely identical devices. - */ -void add_device_randomness(const void *buf, unsigned int size) -{ - unsigned long time = get_cycles() ^ jiffies; + 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; - mix_pool_bytes(&input_pool, buf, size, NULL); - mix_pool_bytes(&input_pool, &time, sizeof(time), NULL); - mix_pool_bytes(&nonblocking_pool, buf, size, NULL); - mix_pool_bytes(&nonblocking_pool, &time, sizeof(time), NULL); -} -EXPORT_SYMBOL(add_device_randomness); + while (len) { + if (len < CHACHA_BLOCK_SIZE) { + chacha20_block(&chacha_state, tmp); + memcpy(buf, tmp, len); + memzero_explicit(tmp, sizeof(tmp)); + break; + } -static struct timer_rand_state input_timer_state; + chacha20_block(&chacha_state, buf); + if (unlikely(chacha_state.x[12] == 0)) + ++chacha_state.x[13]; + len -= CHACHA_BLOCK_SIZE; + buf += CHACHA_BLOCK_SIZE; + } + + chacha_zeroize_state(&chacha_state); +} /* - * 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 number "num" is also added to the pool - it should somehow describe - * the type of event which just happened. This is currently 0-255 for - * keyboard scan codes, and 256 upwards for interrupts. - * + * This returns random bytes in arbitrary quantities. The quality of the + * random bytes is as 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 void add_timer_randomness(struct timer_rand_state *state, unsigned num) +void get_random_bytes(void *buf, size_t len) { - struct { - long jiffies; - unsigned cycles; - unsigned num; - } sample; - long delta, delta2, delta3; + warn_unseeded_randomness(); + _get_random_bytes(buf, len); +} +EXPORT_SYMBOL(get_random_bytes); - preempt_disable(); - /* if over the trickle threshold, use only 1 in 4096 samples */ - if (input_pool.entropy_count > trickle_thresh && - ((__this_cpu_inc_return(trickle_count) - 1) & 0xfff)) - goto out; +static ssize_t get_random_bytes_user(struct iov_iter *iter) +{ + struct chacha_state chacha_state; + u8 block[CHACHA_BLOCK_SIZE]; + size_t ret = 0, copied; - sample.jiffies = jiffies; - sample.cycles = get_cycles(); - sample.num = num; - mix_pool_bytes(&input_pool, &sample, sizeof(sample), NULL); + if (unlikely(!iov_iter_count(iter))) + return 0; /* - * 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. + * 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.x[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.x[4], CHACHA_KEY_SIZE, iter); + goto out_zero_chacha; + } - if (!state->dont_count_entropy) { - delta = sample.jiffies - state->last_time; - state->last_time = sample.jiffies; + for (;;) { + chacha20_block(&chacha_state, block); + if (unlikely(chacha_state.x[12] == 0)) + ++chacha_state.x[13]; - delta2 = delta - state->last_delta; - state->last_delta = delta; + copied = copy_to_iter(block, sizeof(block), iter); + ret += copied; + if (!iov_iter_count(iter) || copied != sizeof(block)) + break; - delta3 = delta2 - state->last_delta2; - state->last_delta2 = delta2; + BUILD_BUG_ON(PAGE_SIZE % sizeof(block) != 0); + if (ret % PAGE_SIZE == 0) { + if (signal_pending(current)) + break; + cond_resched(); + } + } - 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; + memzero_explicit(block, sizeof(block)); +out_zero_chacha: + chacha_zeroize_state(&chacha_state); + return ret ? ret : -EFAULT; +} - /* - * delta is now minimum absolute delta. - * Round down by 1 bit on general principles, - * and limit entropy entimate to 12 bits. - */ - credit_entropy_bits(&input_pool, - min_t(int, fls(delta>>1), 11)); +/* + * Batched entropy returns random integers. The quality of the random + * number is as 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(u8) +DEFINE_BATCHED_ENTROPY(u16) +DEFINE_BATCHED_ENTROPY(u32) +DEFINE_BATCHED_ENTROPY(u64) + +u32 __get_random_u32_below(u32 ceil) +{ + /* + * This is the slow path for variable ceil. It is still fast, most of + * the time, by doing traditional reciprocal multiplication and + * opportunistically comparing the lower half to ceil itself, before + * falling back to computing a larger bound, and then rejecting samples + * whose lower half would indicate a range indivisible by ceil. The use + * of `-ceil % ceil` is analogous to `2^32 % ceil`, but is computable + * in 32-bits. + */ + u32 rand = get_random_u32(); + u64 mult; + + /* + * This function is technically undefined for ceil == 0, and in fact + * for the non-underscored constant version in the header, we build bug + * on that. But for the non-constant case, it's convenient to have that + * evaluate to being a straight call to get_random_u32(), so that + * get_random_u32_inclusive() can work over its whole range without + * undefined behavior. + */ + if (unlikely(!ceil)) + return rand; + + mult = (u64)ceil * rand; + if (unlikely((u32)mult < ceil)) { + u32 bound = -ceil % ceil; + while (unlikely((u32)mult < bound)) + mult = (u64)ceil * get_random_u32(); } -out: - preempt_enable(); + return mult >> 32; } +EXPORT_SYMBOL(__get_random_u32_below); -void add_input_randomness(unsigned int type, unsigned int code, - unsigned int value) +#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) { - static unsigned char last_value; + /* + * 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_u8, cpu)->position = UINT_MAX; + per_cpu_ptr(&batched_entropy_u16, cpu)->position = UINT_MAX; + per_cpu_ptr(&batched_entropy_u32, cpu)->position = UINT_MAX; + per_cpu_ptr(&batched_entropy_u64, cpu)->position = UINT_MAX; + return 0; +} +#endif - /* ignore autorepeat and the like */ - if (value == last_value) - return; - DEBUG_ENT("input event\n"); - last_value = value; - add_timer_randomness(&input_timer_state, - (type << 4) ^ code ^ (code >> 4) ^ value); +/********************************************************************** + * + * 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_ctx 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); } -EXPORT_SYMBOL_GPL(add_input_randomness); -static DEFINE_PER_CPU(struct fast_pool, irq_randomness); +/* + * 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); +} -void add_interrupt_randomness(int irq, int irq_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) { - struct entropy_store *r; - struct fast_pool *fast_pool = &__get_cpu_var(irq_randomness); - struct pt_regs *regs = get_irq_regs(); - unsigned long now = jiffies; - __u32 input[4], cycles = get_cycles(); - - input[0] = cycles ^ jiffies; - input[1] = irq; - if (regs) { - __u64 ip = instruction_pointer(regs); - input[2] = ip; - input[3] = ip >> 32; + 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, longs; + + for (i = 0; i < ARRAY_SIZE(block.rdseed);) { + longs = arch_get_random_seed_longs(&block.rdseed[i], ARRAY_SIZE(block.rdseed) - i); + if (longs) { + i += longs; + continue; + } + longs = arch_get_random_longs(&block.rdseed[i], ARRAY_SIZE(block.rdseed) - i); + if (longs) { + i += longs; + continue; + } + block.rdseed[i++] = random_get_entropy(); } - fast_mix(fast_pool, input, sizeof(input)); + spin_lock_irqsave(&input_pool.lock, flags); - if ((fast_pool->count & 1023) && - !time_after(now, fast_pool->last + HZ)) - return; + /* seed = HASHPRF(last_key, entropy_input) */ + blake2s_final(&input_pool.hash, seed); - fast_pool->last = now; + /* next_key = HASHPRF(seed, RDSEED || 0) */ + block.counter = 0; + blake2s(seed, sizeof(seed), (const u8 *)&block, sizeof(block), next_key, sizeof(next_key)); + blake2s_init_key(&input_pool.hash, BLAKE2S_HASH_SIZE, next_key, sizeof(next_key)); - r = nonblocking_pool.initialized ? &input_pool : &nonblocking_pool; - __mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool), NULL); - /* - * If we don't have a valid cycle counter, and we see - * back-to-back timer interrupts, then skip giving credit for - * any entropy. - */ - if (cycles == 0) { - if (irq_flags & __IRQF_TIMER) { - if (fast_pool->last_timer_intr) - return; - fast_pool->last_timer_intr = 1; - } else - fast_pool->last_timer_intr = 0; + 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(seed, sizeof(seed), (const u8 *)&block, sizeof(block), buf, i); + len -= i; + buf += i; } - credit_entropy_bits(r, 1); + + memzero_explicit(seed, sizeof(seed)); + memzero_explicit(&block, sizeof(block)); } -#ifdef CONFIG_BLOCK -void add_disk_randomness(struct gendisk *disk) +#define credit_init_bits(bits) if (!crng_ready()) _credit_init_bits(bits) + +static void __cold _credit_init_bits(size_t bits) { - if (!disk || !disk->random) + static DECLARE_WORK(set_ready, crng_set_ready); + unsigned int new, orig, add; + unsigned long flags; + int m; + + if (!bits) return; - /* first major is 1, so we get >= 0x200 here */ - DEBUG_ENT("disk event %d:%d\n", - MAJOR(disk_devt(disk)), MINOR(disk_devt(disk))); - add_timer_randomness(disk->random, 0x100 + disk_devt(disk)); -} + add = min_t(size_t, bits, POOL_BITS); + + orig = READ_ONCE(input_pool.init_bits); + do { + new = min_t(unsigned int, POOL_BITS, orig + add); + } while (!try_cmpxchg(&input_pool.init_bits, &orig, new)); + + if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) { + crng_reseed(NULL); /* Sets crng_init to CRNG_READY under base_crng.lock. */ + if (system_dfl_wq) + queue_work(system_dfl_wq, &set_ready); + atomic_notifier_call_chain(&random_ready_notifier, 0, NULL); +#ifdef CONFIG_VDSO_GETRANDOM + WRITE_ONCE(vdso_k_rng_data->is_ready, true); #endif + wake_up_interruptible(&crng_init_wait); + kill_fasync(&fasync, SIGIO, POLL_IN); + pr_notice("crng init done\n"); + m = ratelimit_state_get_miss(&urandom_warning); + if (m) + pr_notice("%d urandom warning(s) missed due to ratelimiting\n", m); + } 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 extraction routines + * 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, bool sleep_after); + * void add_bootloader_randomness(const void *buf, size_t len); + * void add_vmfork_randomness(const void *unique_vm_id, 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 + * command line option 'random.trust_bootloader' is set. + * + * add_vmfork_randomness() adds a unique (but not necessarily secret) ID + * representing the current instance of a VM to the pool, without crediting, + * and then force-reseeds the crng so that it takes effect immediately. + * + * 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 ssize_t extract_entropy(struct entropy_store *r, void *buf, - size_t nbytes, int min, int rsvd); +static bool trust_cpu __initdata = true; +static bool trust_bootloader __initdata = true; +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); -/* - * This utility inline function is responsible for transferring entropy - * from the primary pool to the secondary extraction pool. We make - * sure we pull enough for a 'catastrophic reseed'. - */ -static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes) +static int random_pm_notification(struct notifier_block *nb, unsigned long action, void *data) { - __u32 tmp[OUTPUT_POOL_WORDS]; - - if (r->pull && r->entropy_count < nbytes * 8 && - r->entropy_count < r->poolinfo->POOLBITS) { - /* If we're limited, always leave two wakeup worth's BITS */ - int rsvd = r->limit ? 0 : random_read_wakeup_thresh/4; - int bytes = nbytes; - - /* pull at least as many as BYTES as wakeup BITS */ - bytes = max_t(int, bytes, random_read_wakeup_thresh / 8); - /* but never more than the buffer size */ - bytes = min_t(int, bytes, sizeof(tmp)); - - DEBUG_ENT("going to reseed %s with %d bits " - "(%zu of %d requested)\n", - r->name, bytes * 8, nbytes * 8, r->entropy_count); - - bytes = extract_entropy(r->pull, tmp, bytes, - random_read_wakeup_thresh / 8, rsvd); - mix_pool_bytes(r, tmp, bytes, NULL); - credit_entropy_bits(r, bytes*8); + unsigned long flags, entropy = random_get_entropy(); + + /* + * Encode a representation of how long the system has been suspended, + * in a way that is distinct from prior system suspends. + */ + ktime_t stamps[] = { ktime_get(), ktime_get_boottime(), ktime_get_real() }; + + spin_lock_irqsave(&input_pool.lock, flags); + _mix_pool_bytes(&action, sizeof(action)); + _mix_pool_bytes(stamps, sizeof(stamps)); + _mix_pool_bytes(&entropy, sizeof(entropy)); + spin_unlock_irqrestore(&input_pool.lock, flags); + + if (crng_ready() && (action == PM_RESTORE_PREPARE || + (action == PM_POST_SUSPEND && !IS_ENABLED(CONFIG_PM_AUTOSLEEP) && + !IS_ENABLED(CONFIG_PM_USERSPACE_AUTOSLEEP)))) { + crng_reseed(NULL); + pr_notice("crng reseeded on system resumption\n"); } + return 0; } +static struct notifier_block pm_notifier = { .notifier_call = random_pm_notification }; + /* - * These functions extracts randomness from the "entropy pool", and - * returns it in a buffer. - * - * The min parameter specifies the minimum amount we can pull before - * failing to avoid races that defeat catastrophic reseeding while the - * reserved parameter indicates how much entropy we must leave in the - * pool after each pull to avoid starving other readers. - * - * Note: extract_entropy() assumes that .poolwords is a multiple of 16 words. + * This is called extremely early, before time keeping functionality is + * available, but arch randomness is. Interrupts are not yet enabled. */ - -static size_t account(struct entropy_store *r, size_t nbytes, int min, - int reserved) +void __init random_init_early(const char *command_line) { - unsigned long flags; - int wakeup_write = 0; + unsigned long entropy[BLAKE2S_BLOCK_SIZE / sizeof(long)]; + size_t i, longs, arch_bits; - /* Hold lock while accounting */ - spin_lock_irqsave(&r->lock, flags); - - BUG_ON(r->entropy_count > r->poolinfo->POOLBITS); - DEBUG_ENT("trying to extract %zu bits from %s\n", - nbytes * 8, r->name); +#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 - /* Can we pull enough? */ - if (r->entropy_count / 8 < min + reserved) { - nbytes = 0; - } else { - int entropy_count, orig; -retry: - entropy_count = orig = ACCESS_ONCE(r->entropy_count); - /* If limited, never pull more than available */ - if (r->limit && nbytes + reserved >= entropy_count / 8) - nbytes = entropy_count/8 - reserved; - - if (entropy_count / 8 >= nbytes + reserved) { - entropy_count -= nbytes*8; - if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig) - goto retry; - } else { - entropy_count = reserved; - if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig) - goto retry; + for (i = 0, arch_bits = sizeof(entropy) * 8; i < ARRAY_SIZE(entropy);) { + longs = arch_get_random_seed_longs(entropy, ARRAY_SIZE(entropy) - i); + if (longs) { + _mix_pool_bytes(entropy, sizeof(*entropy) * longs); + i += longs; + continue; } - - if (entropy_count < random_write_wakeup_thresh) - wakeup_write = 1; + longs = arch_get_random_longs(entropy, ARRAY_SIZE(entropy) - i); + if (longs) { + _mix_pool_bytes(entropy, sizeof(*entropy) * longs); + i += longs; + continue; + } + arch_bits -= sizeof(*entropy) * 8; + ++i; } - DEBUG_ENT("debiting %zu entropy credits from %s%s\n", - nbytes * 8, r->name, r->limit ? "" : " (unlimited)"); + _mix_pool_bytes(init_utsname(), sizeof(*(init_utsname()))); + _mix_pool_bytes(command_line, strlen(command_line)); - spin_unlock_irqrestore(&r->lock, flags); - - if (wakeup_write) { - wake_up_interruptible(&random_write_wait); - kill_fasync(&fasync, SIGIO, POLL_OUT); - } - - return nbytes; + /* Reseed if already seeded by earlier phases. */ + if (crng_ready()) + crng_reseed(NULL); + else if (trust_cpu) + _credit_init_bits(arch_bits); } -static void extract_buf(struct entropy_store *r, __u8 *out) +/* + * This is called a little bit after the prior function, and now there is + * access to timestamps counters. Interrupts are not yet enabled. + */ +void __init random_init(void) { - int i; - union { - __u32 w[5]; - unsigned long l[LONGS(EXTRACT_SIZE)]; - } hash; - __u32 workspace[SHA_WORKSPACE_WORDS]; - __u8 extract[64]; - unsigned long flags; + unsigned long entropy = random_get_entropy(); + ktime_t now = ktime_get_real(); - /* Generate a hash across the pool, 16 words (512 bits) at a time */ - sha_init(hash.w); - spin_lock_irqsave(&r->lock, flags); - for (i = 0; i < r->poolinfo->poolwords; i += 16) - sha_transform(hash.w, (__u8 *)(r->pool + i), workspace); + _mix_pool_bytes(&now, sizeof(now)); + _mix_pool_bytes(&entropy, sizeof(entropy)); + add_latent_entropy(); /* - * 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 - * brute-forcing the feedback as hard as brute-forcing the - * hash. + * If we were initialized by the cpu or bootloader before workqueues + * are initialized, then we should enable the static branch here. */ - __mix_pool_bytes(r, hash.w, sizeof(hash.w), extract); - spin_unlock_irqrestore(&r->lock, flags); + if (!static_branch_likely(&crng_is_ready) && crng_init >= CRNG_READY) + crng_set_ready(NULL); - /* - * To avoid duplicates, we atomically extract a portion of the - * pool while mixing, and hash one final time. - */ - sha_transform(hash.w, extract, workspace); - memset(extract, 0, sizeof(extract)); - memset(workspace, 0, sizeof(workspace)); + /* Reseed if already seeded by earlier phases. */ + if (crng_ready()) + crng_reseed(NULL); - /* - * 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. - */ - hash.w[0] ^= hash.w[3]; - hash.w[1] ^= hash.w[4]; - hash.w[2] ^= rol32(hash.w[2], 16); + WARN_ON(register_pm_notifier(&pm_notifier)); - /* - * If we have a architectural hardware random number - * generator, mix that in, too. - */ - for (i = 0; i < LONGS(EXTRACT_SIZE); i++) { - unsigned long v; - if (!arch_get_random_long(&v)) - break; - hash.l[i] ^= v; - } - - memcpy(out, &hash, EXTRACT_SIZE); - memset(&hash, 0, sizeof(hash)); + WARN(!entropy, "Missing cycle counter and fallback timer; RNG " + "entropy collection will consequently suffer."); } -static ssize_t extract_entropy(struct entropy_store *r, void *buf, - size_t nbytes, int min, int reserved) +/* + * 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) { - ssize_t ret = 0, i; - __u8 tmp[EXTRACT_SIZE]; + unsigned long entropy = random_get_entropy(); unsigned long flags; - /* if last_data isn't primed, we need EXTRACT_SIZE extra bytes */ - if (fips_enabled) { - spin_lock_irqsave(&r->lock, flags); - if (!r->last_data_init) { - r->last_data_init = true; - spin_unlock_irqrestore(&r->lock, flags); - trace_extract_entropy(r->name, EXTRACT_SIZE, - r->entropy_count, _RET_IP_); - xfer_secondary_pool(r, EXTRACT_SIZE); - extract_buf(r, tmp); - spin_lock_irqsave(&r->lock, flags); - memcpy(r->last_data, tmp, EXTRACT_SIZE); - } - spin_unlock_irqrestore(&r->lock, flags); - } + 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); - trace_extract_entropy(r->name, nbytes, r->entropy_count, _RET_IP_); - xfer_secondary_pool(r, nbytes); - nbytes = account(r, nbytes, min, reserved); +/* + * Interface for in-kernel drivers of true hardware RNGs. Those devices + * may produce endless random bits, so this function will sleep for + * some amount of time after, if the sleep_after parameter is true. + */ +void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy, bool sleep_after) +{ + mix_pool_bytes(buf, len); + credit_init_bits(entropy); - while (nbytes) { - extract_buf(r, tmp); + /* + * Throttle writing to once every reseed interval, unless we're not yet + * initialized or no entropy is credited. + */ + if (sleep_after && !kthread_should_stop() && (crng_ready() || !entropy)) + schedule_timeout_interruptible(crng_reseed_interval()); +} +EXPORT_SYMBOL_GPL(add_hwgenerator_randomness); - if (fips_enabled) { - spin_lock_irqsave(&r->lock, flags); - if (!memcmp(tmp, r->last_data, EXTRACT_SIZE)) - panic("Hardware RNG duplicated output!\n"); - memcpy(r->last_data, tmp, EXTRACT_SIZE); - spin_unlock_irqrestore(&r->lock, flags); - } - i = min_t(int, nbytes, EXTRACT_SIZE); - memcpy(buf, tmp, i); - nbytes -= i; - buf += i; - ret += i; - } +/* + * Handle random seed passed by bootloader, and credit it depending + * on the command line option 'random.trust_bootloader'. + */ +void __init add_bootloader_randomness(const void *buf, size_t len) +{ + mix_pool_bytes(buf, len); + if (trust_bootloader) + credit_init_bits(len * 8); +} - /* Wipe data just returned from memory */ - memset(tmp, 0, sizeof(tmp)); +#if IS_ENABLED(CONFIG_VMGENID) +static BLOCKING_NOTIFIER_HEAD(vmfork_chain); - return ret; +/* + * Handle a new unique VM ID, which is unique, not secret, so we + * don't credit it, but we do immediately force a reseed after so + * that it's used by the crng posthaste. + */ +void __cold add_vmfork_randomness(const void *unique_vm_id, size_t len) +{ + add_device_randomness(unique_vm_id, len); + if (crng_ready()) { + crng_reseed(NULL); + pr_notice("crng reseeded due to virtual machine fork\n"); + } + blocking_notifier_call_chain(&vmfork_chain, 0, NULL); } +#if IS_MODULE(CONFIG_VMGENID) +EXPORT_SYMBOL_GPL(add_vmfork_randomness); +#endif -static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf, - size_t nbytes) +int __cold register_random_vmfork_notifier(struct notifier_block *nb) { - ssize_t ret = 0, i; - __u8 tmp[EXTRACT_SIZE]; - - trace_extract_entropy_user(r->name, nbytes, r->entropy_count, _RET_IP_); - xfer_secondary_pool(r, nbytes); - nbytes = account(r, nbytes, 0, 0); - - while (nbytes) { - if (need_resched()) { - if (signal_pending(current)) { - if (ret == 0) - ret = -ERESTARTSYS; - break; - } - schedule(); - } + return blocking_notifier_chain_register(&vmfork_chain, nb); +} +EXPORT_SYMBOL_GPL(register_random_vmfork_notifier); - extract_buf(r, tmp); - i = min_t(int, nbytes, EXTRACT_SIZE); - if (copy_to_user(buf, tmp, i)) { - ret = -EFAULT; - break; - } +int __cold unregister_random_vmfork_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&vmfork_chain, nb); +} +EXPORT_SYMBOL_GPL(unregister_random_vmfork_notifier); +#endif - nbytes -= i; - buf += i; - ret += i; - } +struct fast_pool { + unsigned long pool[4]; + unsigned long last; + unsigned int count; + struct timer_list mix; +}; - /* Wipe data just returned from memory */ - memset(tmp, 0, sizeof(tmp)); +static void mix_interrupt_randomness(struct timer_list *work); - return ret; -} +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 + .mix = __TIMER_INITIALIZER(mix_interrupt_randomness, 0) +}; /* - * This function is the exported kernel interface. It returns some - * number of good random numbers, suitable for key generation, seeding - * TCP sequence numbers, etc. It does not use the hw random number - * generator, if available; use get_random_bytes_arch() for that. + * 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. */ -void get_random_bytes(void *buf, int nbytes) +static void fast_mix(unsigned long s[4], unsigned long v1, unsigned long v2) { - extract_entropy(&nonblocking_pool, buf, nbytes, 0, 0); + 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; } -EXPORT_SYMBOL(get_random_bytes); +#ifdef CONFIG_SMP /* - * This function will use the architecture-specific hardware random - * number generator if it is available. The arch-specific hw RNG will - * almost certainly be faster than what we can do in software, but it - * is impossible to verify that it is implemented securely (as - * opposed, to, say, the AES encryption of a sequence number using a - * key known by the NSA). So it's useful if we need the speed, but - * only if we're willing to trust the hardware manufacturer not to - * have put in a back door. + * This function is called when the CPU has just come online, with + * entry CPUHP_AP_RANDOM_ONLINE, just after CPUHP_AP_WORKQUEUE_ONLINE. */ -void get_random_bytes_arch(void *buf, int nbytes) +int __cold random_online_cpu(unsigned int cpu) { - char *p = buf; + /* + * 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 - trace_get_random_bytes(nbytes, _RET_IP_); - while (nbytes) { - unsigned long v; - int chunk = min(nbytes, (int)sizeof(unsigned long)); +static void mix_interrupt_randomness(struct timer_list *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; - if (!arch_get_random_long(&v)) - break; - - memcpy(p, &v, chunk); - p += chunk; - nbytes -= chunk; + /* 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; } - if (nbytes) - extract_entropy(&nonblocking_pool, p, nbytes, 0, 0); + /* + * 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; + + fast_pool->count |= MIX_INFLIGHT; + if (!timer_pending(&fast_pool->mix)) { + fast_pool->mix.expires = jiffies; + add_timer_on(&fast_pool->mix, raw_smp_processor_id()); + } } -EXPORT_SYMBOL(get_random_bytes_arch); +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; +}; /* - * init_std_data - initialize pool with system data - * - * @r: pool to initialize - * - * This function clears the pool's entropy count and mixes some system - * data into the pool to prepare it for use. The pool is not cleared - * as that can only decrease the entropy in the pool. + * 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 init_std_data(struct entropy_store *r) +static void add_timer_randomness(struct timer_rand_state *state, unsigned int num) { - int i; - ktime_t now = ktime_get_real(); - unsigned long rv; - - r->entropy_count = 0; - r->entropy_total = 0; - r->last_data_init = false; - mix_pool_bytes(r, &now, sizeof(now), NULL); - for (i = r->poolinfo->POOLBYTES; i > 0; i -= sizeof(rv)) { - if (!arch_get_random_long(&rv)) - break; - mix_pool_bytes(r, &rv, sizeof(rv), NULL); + 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); } - mix_pool_bytes(r, utsname(), sizeof(*(utsname())), NULL); + + 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); } -/* - * Note that setup_arch() may call add_device_randomness() - * long before we get here. This allows seeding of the pools - * with some platform dependent data very early in the boot - * process. But it limits our options here. We must use - * statically allocated structures that already have all - * initializations complete at compile time. We should also - * take care not to overwrite the precious per platform data - * we were given. - */ -static int rand_initialize(void) +void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) { - init_std_data(&input_pool); - init_std_data(&blocking_pool); - init_std_data(&nonblocking_pool); - return 0; + 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); } -module_init(rand_initialize); +EXPORT_SYMBOL_GPL(add_input_randomness); #ifdef CONFIG_BLOCK -void rand_initialize_disk(struct gendisk *disk) +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; @@ -1149,136 +1249,264 @@ void rand_initialize_disk(struct gendisk *disk) * source. */ state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL); - if (state) + if (state) { + state->last_time = INITIAL_JIFFIES; disk->random = state; + } } #endif -static ssize_t -random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) +struct entropy_timer_state { + unsigned long entropy; + struct timer_list timer; + atomic_t samples; + unsigned int samples_per_bit; +}; + +/* + * 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 *timer) { - ssize_t n, retval = 0, count = 0; + struct entropy_timer_state *state = container_of(timer, struct entropy_timer_state, timer); + unsigned long entropy = random_get_entropy(); - if (nbytes == 0) - return 0; + mix_pool_bytes(&entropy, sizeof(entropy)); + if (atomic_inc_return(&state->samples) % state->samples_per_bit == 0) + credit_init_bits(1); +} - while (nbytes > 0) { - n = nbytes; - if (n > SEC_XFER_SIZE) - n = SEC_XFER_SIZE; +/* + * 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) +{ + enum { NUM_TRIAL_SAMPLES = 8192, MAX_SAMPLES_PER_BIT = HZ / 15 }; + u8 stack_bytes[sizeof(struct entropy_timer_state) + SMP_CACHE_BYTES - 1]; + struct entropy_timer_state *stack = PTR_ALIGN((void *)stack_bytes, SMP_CACHE_BYTES); + unsigned int i, num_different = 0; + unsigned long last = random_get_entropy(); + cpumask_var_t timer_cpus; + int cpu = -1; + + for (i = 0; i < NUM_TRIAL_SAMPLES - 1; ++i) { + stack->entropy = random_get_entropy(); + if (stack->entropy != last) + ++num_different; + last = stack->entropy; + } + stack->samples_per_bit = DIV_ROUND_UP(NUM_TRIAL_SAMPLES, num_different + 1); + if (stack->samples_per_bit > MAX_SAMPLES_PER_BIT) + return; - DEBUG_ENT("reading %zu bits\n", n*8); + atomic_set(&stack->samples, 0); + timer_setup_on_stack(&stack->timer, entropy_timer, 0); + if (!alloc_cpumask_var(&timer_cpus, GFP_KERNEL)) + goto out; - n = extract_entropy_user(&blocking_pool, buf, n); + while (!crng_ready() && !signal_pending(current)) { + /* + * Check !timer_pending() and then ensure that any previous callback has finished + * executing by checking timer_delete_sync_try(), before queueing the next one. + */ + if (!timer_pending(&stack->timer) && timer_delete_sync_try(&stack->timer) >= 0) { + unsigned int num_cpus; + + /* + * Preemption must be disabled here, both to read the current CPU number + * and to avoid scheduling a timer on a dead CPU. + */ + preempt_disable(); + + /* Only schedule callbacks on timer CPUs that are online. */ + cpumask_and(timer_cpus, housekeeping_cpumask(HK_TYPE_TIMER), cpu_online_mask); + num_cpus = cpumask_weight(timer_cpus); + /* In very bizarre case of misconfiguration, fallback to all online. */ + if (unlikely(num_cpus == 0)) { + *timer_cpus = *cpu_online_mask; + num_cpus = cpumask_weight(timer_cpus); + } - if (n < 0) { - retval = n; - break; - } + /* Basic CPU round-robin, which avoids the current CPU. */ + do { + cpu = cpumask_next(cpu, timer_cpus); + if (cpu >= nr_cpu_ids) + cpu = cpumask_first(timer_cpus); + } while (cpu == smp_processor_id() && num_cpus > 1); - DEBUG_ENT("read got %zd bits (%zd still needed)\n", - n*8, (nbytes-n)*8); + /* Expiring the timer at `jiffies` means it's the next tick. */ + stack->timer.expires = jiffies; - if (n == 0) { - if (file->f_flags & O_NONBLOCK) { - retval = -EAGAIN; - break; - } + add_timer_on(&stack->timer, cpu); - DEBUG_ENT("sleeping?\n"); + preempt_enable(); + } + mix_pool_bytes(&stack->entropy, sizeof(stack->entropy)); + schedule(); + stack->entropy = random_get_entropy(); + } + mix_pool_bytes(&stack->entropy, sizeof(stack->entropy)); - wait_event_interruptible(random_read_wait, - input_pool.entropy_count >= - random_read_wakeup_thresh); + free_cpumask_var(timer_cpus); +out: + timer_delete_sync(&stack->timer); + timer_destroy_on_stack(&stack->timer); +} - DEBUG_ENT("awake\n"); - if (signal_pending(current)) { - retval = -ERESTARTSYS; - break; - } +/********************************************************************** + * + * 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. + * + **********************************************************************/ - continue; - } +SYSCALL_DEFINE3(getrandom, char __user *, ubuf, size_t, len, unsigned int, flags) +{ + struct iov_iter iter; + int ret; - count += n; - buf += n; - nbytes -= n; - break; /* This break makes the device work */ - /* like a named pipe */ + 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; } - return (count ? count : retval); + ret = import_ubuf(ITER_DEST, ubuf, len, &iter); + if (unlikely(ret)) + return ret; + return get_random_bytes_user(&iter); } -static ssize_t -urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) +static __poll_t random_poll(struct file *file, poll_table *wait) { - return extract_entropy_user(&nonblocking_pool, buf, nbytes); + poll_wait(file, &crng_init_wait, wait); + return crng_ready() ? EPOLLIN | EPOLLRDNORM : EPOLLOUT | EPOLLWRNORM; } -static unsigned int -random_poll(struct file *file, poll_table * wait) +static ssize_t write_pool_user(struct iov_iter *iter) { - unsigned int mask; - - poll_wait(file, &random_read_wait, wait); - poll_wait(file, &random_write_wait, wait); - mask = 0; - if (input_pool.entropy_count >= random_read_wakeup_thresh) - mask |= POLLIN | POLLRDNORM; - if (input_pool.entropy_count < random_write_wakeup_thresh) - mask |= POLLOUT | POLLWRNORM; - return mask; + 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 int -write_pool(struct entropy_store *r, const char __user *buffer, size_t count) +static ssize_t random_write_iter(struct kiocb *kiocb, struct iov_iter *iter) { - size_t bytes; - __u32 buf[16]; - const char __user *p = buffer; - - while (count > 0) { - bytes = min(count, sizeof(buf)); - if (copy_from_user(&buf, p, bytes)) - return -EFAULT; + return write_pool_user(iter); +} - count -= bytes; - p += bytes; +static ssize_t urandom_read_iter(struct kiocb *kiocb, struct iov_iter *iter) +{ + static int maxwarn = 10; - mix_pool_bytes(r, buf, bytes, NULL); - cond_resched(); + /* + * Opportunistically attempt to initialize the RNG on platforms that + * have fast cycle counters, but don't (for now) require it to succeed. + */ + if (!crng_ready()) + try_to_generate_entropy(); + + if (!crng_ready()) { + if (!ratelimit_disable && maxwarn <= 0) + ratelimit_state_inc_miss(&urandom_warning); + 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 0; + return get_random_bytes_user(iter); } -static ssize_t random_write(struct file *file, const char __user *buffer, - size_t count, loff_t *ppos) +static ssize_t random_read_iter(struct kiocb *kiocb, struct iov_iter *iter) { - size_t ret; + int ret; - ret = write_pool(&blocking_pool, buffer, count); - if (ret) - return ret; - ret = write_pool(&nonblocking_pool, buffer, count); - if (ret) - return ret; + if (!crng_ready() && + ((kiocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) || + (kiocb->ki_filp->f_flags & O_NONBLOCK))) + return -EAGAIN; - return (ssize_t)count; + 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 size, ent_count; int __user *p = (int __user *)arg; - int retval; + int ent_count; switch (cmd) { case RNDGETENTCNT: - /* inherently racy, no point locking */ - if (put_user(input_pool.entropy_count, p)) + /* Inherently racy, no point locking. */ + if (put_user(input_pool.init_bits, p)) return -EFAULT; return 0; case RNDADDTOENTCNT: @@ -1286,29 +1514,47 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) return -EPERM; if (get_user(ent_count, p)) return -EFAULT; - credit_entropy_bits(&input_pool, ent_count); + if (ent_count < 0) + return -EINVAL; + credit_init_bits(ent_count); return 0; - case RNDADDENTROPY: + case RNDADDENTROPY: { + struct iov_iter iter; + 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(size, p++)) + if (get_user(len, p++)) + return -EFAULT; + ret = import_ubuf(ITER_SOURCE, p, len, &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; - retval = write_pool(&input_pool, (const char __user *)p, - size); - if (retval < 0) - return retval; - credit_entropy_bits(&input_pool, ent_count); + credit_init_bits(ent_count); return 0; + } case RNDZAPENTCNT: case RNDCLEARPOOL: - /* Clear the entropy pool counters. */ + /* No longer has any effect. */ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + return 0; + case RNDRESEEDCRNG: if (!capable(CAP_SYS_ADMIN)) return -EPERM; - rand_initialize(); + if (!crng_ready()) + return -ENODATA; + crng_reseed(NULL); return 0; default: return -EINVAL; @@ -1321,45 +1567,56 @@ static int random_fasync(int fd, struct file *filp, int on) } const struct file_operations random_fops = { - .read = random_read, - .write = random_write, - .poll = random_poll, + .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 = copy_splice_read, + .splice_write = iter_file_splice_write, }; const struct file_operations urandom_fops = { - .read = urandom_read, - .write = random_write, + .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 = copy_splice_read, + .splice_write = iter_file_splice_write, }; -/*************************************************************** - * Random UUID interface - * - * Used here for a Boot ID, but can be useful for other kernel - * drivers. - ***************************************************************/ - -/* - * Generate random UUID - */ -void generate_random_uuid(unsigned char uuid_out[16]) -{ - get_random_bytes(uuid_out, 16); - /* Set UUID version to 4 --- truly random generation */ - uuid_out[6] = (uuid_out[6] & 0x0F) | 0x40; - /* Set the UUID variant to DCE */ - uuid_out[8] = (uuid_out[8] & 0x3F) | 0x80; -} -EXPORT_SYMBOL(generate_random_uuid); /******************************************************************** * - * Sysctl interface + * 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. * ********************************************************************/ @@ -1367,25 +1624,28 @@ EXPORT_SYMBOL(generate_random_uuid); #include <linux/sysctl.h> -static int min_read_thresh = 8, min_write_thresh; -static int max_read_thresh = INPUT_POOL_WORDS * 32; -static int max_write_thresh = INPUT_POOL_WORDS * 32; -static char sysctl_bootid[16]; +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]; /* - * These functions is used to return both the bootid UUID, and random - * UUID. The difference is in whether table->data is NULL; if it is, + * 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. - * - * If the user accesses this via the proc interface, it will be returned - * as an ASCII string in the standard UUID format. If accesses via the - * sysctl system call, it is returned as 16 bytes of binary data. */ -static int proc_do_uuid(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int proc_do_uuid(const struct ctl_table *table, int write, void *buf, + size_t *lenp, loff_t *ppos) { - struct ctl_table fake_table; - unsigned char buf[64], tmp_uuid[16], *uuid; + 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) { @@ -1400,17 +1660,18 @@ static int proc_do_uuid(struct ctl_table *table, int write, spin_unlock(&bootid_spinlock); } - sprintf(buf, "%pU", uuid); - - fake_table.data = buf; - fake_table.maxlen = sizeof(buf); + snprintf(uuid_string, sizeof(uuid_string), "%pU", uuid); + return proc_dostring(&fake_table, 0, buf, lenp, ppos); +} - return proc_dostring(&fake_table, write, buffer, lenp, ppos); +/* The same as proc_dointvec, but writes don't change anything. */ +static int proc_do_rointvec(const struct ctl_table *table, int write, void *buf, + size_t *lenp, loff_t *ppos) +{ + return write ? 0 : proc_dointvec(table, 0, buf, lenp, ppos); } -static int sysctl_poolsize = INPUT_POOL_WORDS * 32; -extern struct ctl_table random_table[]; -struct ctl_table random_table[] = { +static const struct ctl_table random_table[] = { { .procname = "poolsize", .data = &sysctl_poolsize, @@ -1420,96 +1681,46 @@ struct ctl_table random_table[] = { }, { .procname = "entropy_avail", + .data = &input_pool.init_bits, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, - .data = &input_pool.entropy_count, }, { - .procname = "read_wakeup_threshold", - .data = &random_read_wakeup_thresh, + .procname = "write_wakeup_threshold", + .data = &sysctl_random_write_wakeup_bits, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_read_thresh, - .extra2 = &max_read_thresh, + .proc_handler = proc_do_rointvec, }, { - .procname = "write_wakeup_threshold", - .data = &random_write_wakeup_thresh, + .procname = "urandom_min_reseed_secs", + .data = &sysctl_random_min_urandom_seed, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_write_thresh, - .extra2 = &max_write_thresh, + .proc_handler = proc_do_rointvec, }, { .procname = "boot_id", .data = &sysctl_bootid, - .maxlen = 16, .mode = 0444, .proc_handler = proc_do_uuid, }, { .procname = "uuid", - .maxlen = 16, .mode = 0444, .proc_handler = proc_do_uuid, }, - { } }; -#endif /* CONFIG_SYSCTL */ - -static u32 random_int_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned; - -static int __init random_int_secret_init(void) -{ - get_random_bytes(random_int_secret, sizeof(random_int_secret)); - return 0; -} -late_initcall(random_int_secret_init); /* - * Get a random word for internal kernel use only. Similar to urandom but - * with the goal of minimal entropy pool depletion. As a result, the random - * value is not cryptographically secure but for several uses the cost of - * depleting entropy is too high + * random_init() is called before sysctl_init(), + * so we cannot call register_sysctl_init() in random_init() */ -static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash); -unsigned int get_random_int(void) +static int __init random_sysctls_init(void) { - __u32 *hash; - unsigned int ret; - - if (arch_get_random_int(&ret)) - return ret; - - hash = get_cpu_var(get_random_int_hash); - - hash[0] += current->pid + jiffies + get_cycles(); - md5_transform(hash, random_int_secret); - ret = hash[0]; - put_cpu_var(get_random_int_hash); - - return ret; -} -EXPORT_SYMBOL(get_random_int); - -/* - * randomize_range() returns a start address such that - * - * [...... <range> .....] - * start end - * - * a <range> with size "len" starting at the return value is inside in the - * area defined by [start, end], but is otherwise randomized. - */ -unsigned long -randomize_range(unsigned long start, unsigned long end, unsigned long len) -{ - unsigned long range = end - len - start; - - if (end <= start + len) - return 0; - return PAGE_ALIGN(get_random_int() % range + start); + register_sysctl_init("kernel/random", random_table); + return 0; } +device_initcall(random_sysctls_init); +#endif |