linux/drivers/char/random.c
Theodore Ts'o d848e5f8e1 random: add new ioctl RNDRESEEDCRNG
Add a new ioctl which forces the the crng to be reseeded.

Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
2018-04-14 11:59:31 -04:00

2296 lines
66 KiB
C

/*
* random.c -- A strong random number generator
*
* Copyright (C) 2017 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.
*/
/*
* (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.
*/
#include <linux/utsname.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/major.h>
#include <linux/string.h>
#include <linux/fcntl.h>
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/poll.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/genhd.h>
#include <linux/interrupt.h>
#include <linux/mm.h>
#include <linux/nodemask.h>
#include <linux/spinlock.h>
#include <linux/kthread.h>
#include <linux/percpu.h>
#include <linux/cryptohash.h>
#include <linux/fips.h>
#include <linux/ptrace.h>
#include <linux/workqueue.h>
#include <linux/irq.h>
#include <linux/syscalls.h>
#include <linux/completion.h>
#include <linux/uuid.h>
#include <crypto/chacha20.h>
#include <asm/processor.h>
#include <linux/uaccess.h>
#include <asm/irq.h>
#include <asm/irq_regs.h>
#include <asm/io.h>
#define CREATE_TRACE_POINTS
#include <trace/events/random.h>
/* #define ADD_INTERRUPT_BENCH */
/*
* Configuration information
*/
#define INPUT_POOL_SHIFT 12
#define INPUT_POOL_WORDS (1 << (INPUT_POOL_SHIFT-5))
#define OUTPUT_POOL_SHIFT 10
#define OUTPUT_POOL_WORDS (1 << (OUTPUT_POOL_SHIFT-5))
#define SEC_XFER_SIZE 512
#define EXTRACT_SIZE 10
#define LONGS(x) (((x) + sizeof(unsigned long) - 1)/sizeof(unsigned long))
/*
* To allow fractional bits to be tracked, the entropy_count field is
* denominated in units of 1/8th bits.
*
* 2*(ENTROPY_SHIFT + log2(poolbits)) must <= 31, or the multiply in
* credit_entropy_bits() needs to be 64 bits wide.
*/
#define ENTROPY_SHIFT 3
#define ENTROPY_BITS(r) ((r)->entropy_count >> ENTROPY_SHIFT)
/*
* The minimum number of bits of entropy before we wake up a read on
* /dev/random. Should be enough to do a significant reseed.
*/
static int random_read_wakeup_bits = 64;
/*
* If the entropy count falls under this number of bits, then we
* should wake up processes which are selecting or polling on write
* access to /dev/random.
*/
static int random_write_wakeup_bits = 28 * OUTPUT_POOL_WORDS;
/*
* Originally, we used a primitive polynomial of degree .poolwords
* over GF(2). The taps for various sizes are defined below. They
* were chosen to be evenly spaced except for the last tap, which is 1
* to get the twisting happening as fast as possible.
*
* For the purposes of better mixing, we use the CRC-32 polynomial as
* well to make a (modified) twisted Generalized Feedback Shift
* Register. (See M. Matsumoto & Y. Kurita, 1992. Twisted GFSR
* generators. ACM Transactions on Modeling and Computer Simulation
* 2(3):179-194. Also see M. Matsumoto & Y. Kurita, 1994. Twisted
* GFSR generators II. ACM Transactions on Modeling and Computer
* Simulation 4:254-266)
*
* Thanks to Colin Plumb for suggesting this.
*
* The mixing operation is much less sensitive than the output hash,
* where we use SHA-1. All that we want of mixing operation is that
* it be a good non-cryptographic hash; i.e. it not produce collisions
* when fed "random" data of the sort we expect to see. As long as
* the pool state differs for different inputs, we have preserved the
* input entropy and done a good job. The fact that an intelligent
* attacker can construct inputs that will produce controlled
* alterations to the pool's state is not important because we don't
* consider such inputs to contribute any randomness. The only
* property we need with respect to them is that the attacker can't
* increase his/her knowledge of the pool's state. Since all
* additions are reversible (knowing the final state and the input,
* you can reconstruct the initial state), if an attacker has any
* uncertainty about the initial state, he/she can only shuffle that
* uncertainty about, but never cause any collisions (which would
* decrease the uncertainty).
*
* Our mixing functions were analyzed by Lacharme, Roeck, Strubel, and
* Videau in their paper, "The Linux Pseudorandom Number Generator
* Revisited" (see: http://eprint.iacr.org/2012/251.pdf). In their
* paper, they point out that we are not using a true Twisted GFSR,
* since Matsumoto & Kurita used a trinomial feedback polynomial (that
* is, with only three taps, instead of the six that we are using).
* As a result, the resulting polynomial is neither primitive nor
* irreducible, and hence does not have a maximal period over
* GF(2**32). They suggest a slight change to the generator
* polynomial which improves the resulting TGFSR polynomial to be
* irreducible, which we have made here.
*/
static struct poolinfo {
int poolbitshift, poolwords, poolbytes, poolbits, poolfracbits;
#define S(x) ilog2(x)+5, (x), (x)*4, (x)*32, (x) << (ENTROPY_SHIFT+5)
int tap1, tap2, tap3, tap4, tap5;
} poolinfo_table[] = {
/* was: x^128 + x^103 + x^76 + x^51 +x^25 + x + 1 */
/* x^128 + x^104 + x^76 + x^51 +x^25 + x + 1 */
{ S(128), 104, 76, 51, 25, 1 },
/* was: x^32 + x^26 + x^20 + x^14 + x^7 + x + 1 */
/* x^32 + x^26 + x^19 + x^14 + x^7 + x + 1 */
{ S(32), 26, 19, 14, 7, 1 },
#if 0
/* x^2048 + x^1638 + x^1231 + x^819 + x^411 + x + 1 -- 115 */
{ S(2048), 1638, 1231, 819, 411, 1 },
/* x^1024 + x^817 + x^615 + x^412 + x^204 + x + 1 -- 290 */
{ S(1024), 817, 615, 412, 204, 1 },
/* x^1024 + x^819 + x^616 + x^410 + x^207 + x^2 + 1 -- 115 */
{ S(1024), 819, 616, 410, 207, 2 },
/* x^512 + x^411 + x^308 + x^208 + x^104 + x + 1 -- 225 */
{ S(512), 411, 308, 208, 104, 1 },
/* x^512 + x^409 + x^307 + x^206 + x^102 + x^2 + 1 -- 95 */
{ S(512), 409, 307, 206, 102, 2 },
/* x^512 + x^409 + x^309 + x^205 + x^103 + x^2 + 1 -- 95 */
{ S(512), 409, 309, 205, 103, 2 },
/* x^256 + x^205 + x^155 + x^101 + x^52 + x + 1 -- 125 */
{ S(256), 205, 155, 101, 52, 1 },
/* x^128 + x^103 + x^78 + x^51 + x^27 + x^2 + 1 -- 70 */
{ S(128), 103, 78, 51, 27, 2 },
/* x^64 + x^52 + x^39 + x^26 + x^14 + x + 1 -- 15 */
{ S(64), 52, 39, 26, 14, 1 },
#endif
};
/*
* 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 DEFINE_SPINLOCK(random_ready_list_lock);
static LIST_HEAD(random_ready_list);
struct crng_state {
__u32 state[16];
unsigned long init_time;
spinlock_t lock;
};
struct crng_state primary_crng = {
.lock = __SPIN_LOCK_UNLOCKED(primary_crng.lock),
};
/*
* crng_init = 0 --> Uninitialized
* 1 --> Initialized
* 2 --> Initialized from input_pool
*
* crng_init is protected by primary_crng->lock, and only increases
* its value (from 0->1->2).
*/
static int crng_init = 0;
#define crng_ready() (likely(crng_init > 1))
static int crng_init_cnt = 0;
static unsigned long crng_global_init_time = 0;
#define CRNG_INIT_CNT_THRESH (2*CHACHA20_KEY_SIZE)
static void _extract_crng(struct crng_state *crng,
__u32 out[CHACHA20_BLOCK_WORDS]);
static void _crng_backtrack_protect(struct crng_state *crng,
__u32 tmp[CHACHA20_BLOCK_WORDS], int used);
static void process_random_ready_list(void);
static void _get_random_bytes(void *buf, int nbytes);
/**********************************************************************
*
* OS independent entropy store. Here are the functions which handle
* storing entropy in an entropy pool.
*
**********************************************************************/
struct entropy_store;
struct entropy_store {
/* read-only data: */
const struct poolinfo *poolinfo;
__u32 *pool;
const char *name;
struct entropy_store *pull;
struct work_struct push_work;
/* read-write data: */
unsigned long last_pulled;
spinlock_t lock;
unsigned short add_ptr;
unsigned short input_rotate;
int entropy_count;
int entropy_total;
unsigned int initialized:1;
unsigned int last_data_init:1;
__u8 last_data[EXTRACT_SIZE];
};
static ssize_t extract_entropy(struct entropy_store *r, void *buf,
size_t nbytes, int min, int rsvd);
static ssize_t _extract_entropy(struct entropy_store *r, void *buf,
size_t nbytes, int fips);
static void crng_reseed(struct crng_state *crng, struct entropy_store *r);
static void push_to_pool(struct work_struct *work);
static __u32 input_pool_data[INPUT_POOL_WORDS] __latent_entropy;
static __u32 blocking_pool_data[OUTPUT_POOL_WORDS] __latent_entropy;
static struct entropy_store input_pool = {
.poolinfo = &poolinfo_table[0],
.name = "input",
.lock = __SPIN_LOCK_UNLOCKED(input_pool.lock),
.pool = input_pool_data
};
static struct entropy_store blocking_pool = {
.poolinfo = &poolinfo_table[1],
.name = "blocking",
.pull = &input_pool,
.lock = __SPIN_LOCK_UNLOCKED(blocking_pool.lock),
.pool = blocking_pool_data,
.push_work = __WORK_INITIALIZER(blocking_pool.push_work,
push_to_pool),
};
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.
*/
static void _mix_pool_bytes(struct entropy_store *r, const void *in,
int nbytes)
{
unsigned long i, 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;
input_rotate = r->input_rotate;
i = r->add_ptr;
/* mix one byte at a time to simplify size handling and churn faster */
while (nbytes--) {
w = rol32(*bytes++, input_rotate);
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 = (input_rotate + (i ? 7 : 14)) & 31;
}
r->input_rotate = input_rotate;
r->add_ptr = i;
}
static void __mix_pool_bytes(struct entropy_store *r, const void *in,
int nbytes)
{
trace_mix_pool_bytes_nolock(r->name, nbytes, _RET_IP_);
_mix_pool_bytes(r, in, nbytes);
}
static void mix_pool_bytes(struct entropy_store *r, const void *in,
int nbytes)
{
unsigned long flags;
trace_mix_pool_bytes(r->name, nbytes, _RET_IP_);
spin_lock_irqsave(&r->lock, flags);
_mix_pool_bytes(r, in, nbytes);
spin_unlock_irqrestore(&r->lock, flags);
}
struct fast_pool {
__u32 pool[4];
unsigned long last;
unsigned short reg_idx;
unsigned char count;
};
/*
* This is a fast mixing routine used by the interrupt randomness
* collector. It's hardcoded for an 128 bit pool and assumes that any
* locks that might be needed are taken by the caller.
*/
static void fast_mix(struct fast_pool *f)
{
__u32 a = f->pool[0], b = f->pool[1];
__u32 c = f->pool[2], d = f->pool[3];
a += b; c += d;
b = rol32(b, 6); d = rol32(d, 27);
d ^= a; b ^= c;
a += b; c += d;
b = rol32(b, 16); d = rol32(d, 14);
d ^= a; b ^= c;
a += b; c += d;
b = rol32(b, 6); d = rol32(d, 27);
d ^= a; b ^= c;
a += b; c += d;
b = rol32(b, 16); d = rol32(d, 14);
d ^= a; b ^= c;
f->pool[0] = a; f->pool[1] = b;
f->pool[2] = c; f->pool[3] = d;
f->count++;
}
static void process_random_ready_list(void)
{
unsigned long flags;
struct random_ready_callback *rdy, *tmp;
spin_lock_irqsave(&random_ready_list_lock, flags);
list_for_each_entry_safe(rdy, tmp, &random_ready_list, list) {
struct module *owner = rdy->owner;
list_del_init(&rdy->list);
rdy->func(rdy);
module_put(owner);
}
spin_unlock_irqrestore(&random_ready_list_lock, flags);
}
/*
* Credit (or debit) the entropy store with n bits of entropy.
* Use credit_entropy_bits_safe() if the value comes from userspace
* or otherwise should be checked for extreme values.
*/
static void credit_entropy_bits(struct entropy_store *r, int nbits)
{
int entropy_count, orig;
const int pool_size = r->poolinfo->poolfracbits;
int nfrac = nbits << ENTROPY_SHIFT;
if (!nbits)
return;
retry:
entropy_count = orig = READ_ONCE(r->entropy_count);
if (nfrac < 0) {
/* Debit */
entropy_count += nfrac;
} else {
/*
* Credit: we have to account for the possibility of
* overwriting already present entropy. Even in the
* ideal case of pure Shannon entropy, new contributions
* approach the full value asymptotically:
*
* entropy <- entropy + (pool_size - entropy) *
* (1 - exp(-add_entropy/pool_size))
*
* For add_entropy <= pool_size/2 then
* (1 - exp(-add_entropy/pool_size)) >=
* (add_entropy/pool_size)*0.7869...
* so we can approximate the exponential with
* 3/4*add_entropy/pool_size and still be on the
* safe side by adding at most pool_size/2 at a time.
*
* The use of pool_size-2 in the while statement is to
* prevent rounding artifacts from making the loop
* arbitrarily long; this limits the loop to log2(pool_size)*2
* turns no matter how large nbits is.
*/
int pnfrac = nfrac;
const int s = r->poolinfo->poolbitshift + ENTROPY_SHIFT + 2;
/* The +2 corresponds to the /4 in the denominator */
do {
unsigned int anfrac = min(pnfrac, pool_size/2);
unsigned int add =
((pool_size - entropy_count)*anfrac*3) >> s;
entropy_count += add;
pnfrac -= anfrac;
} while (unlikely(entropy_count < pool_size-2 && pnfrac));
}
if (unlikely(entropy_count < 0)) {
pr_warn("random: negative entropy/overflow: pool %s count %d\n",
r->name, entropy_count);
WARN_ON(1);
entropy_count = 0;
} else if (entropy_count > pool_size)
entropy_count = pool_size;
if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
goto retry;
r->entropy_total += nbits;
if (!r->initialized && r->entropy_total > 128) {
r->initialized = 1;
r->entropy_total = 0;
}
trace_credit_entropy_bits(r->name, nbits,
entropy_count >> ENTROPY_SHIFT,
r->entropy_total, _RET_IP_);
if (r == &input_pool) {
int entropy_bits = entropy_count >> ENTROPY_SHIFT;
if (crng_init < 2 && entropy_bits >= 128) {
crng_reseed(&primary_crng, r);
entropy_bits = r->entropy_count >> ENTROPY_SHIFT;
}
/* should we wake readers? */
if (entropy_bits >= random_read_wakeup_bits &&
wq_has_sleeper(&random_read_wait)) {
wake_up_interruptible(&random_read_wait);
kill_fasync(&fasync, SIGIO, POLL_IN);
}
/* If the input pool is getting full, send some
* entropy to the blocking pool until it is 75% full.
*/
if (entropy_bits > random_write_wakeup_bits &&
r->initialized &&
r->entropy_total >= 2*random_read_wakeup_bits) {
struct entropy_store *other = &blocking_pool;
if (other->entropy_count <=
3 * other->poolinfo->poolfracbits / 4) {
schedule_work(&other->push_work);
r->entropy_total = 0;
}
}
}
}
static int credit_entropy_bits_safe(struct entropy_store *r, int nbits)
{
const int nbits_max = r->poolinfo->poolwords * 32;
if (nbits < 0)
return -EINVAL;
/* Cap the value to avoid overflows */
nbits = min(nbits, nbits_max);
credit_entropy_bits(r, nbits);
return 0;
}
/*********************************************************************
*
* CRNG using CHACHA20
*
*********************************************************************/
#define CRNG_RESEED_INTERVAL (300*HZ)
static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait);
#ifdef CONFIG_NUMA
/*
* Hack to deal with crazy userspace progams when they are all trying
* to access /dev/urandom in parallel. The programs are almost
* certainly doing something terribly wrong, but we'll work around
* their brain damage.
*/
static struct crng_state **crng_node_pool __read_mostly;
#endif
static void invalidate_batched_entropy(void);
static void crng_initialize(struct crng_state *crng)
{
int i;
unsigned long rv;
memcpy(&crng->state[0], "expand 32-byte k", 16);
if (crng == &primary_crng)
_extract_entropy(&input_pool, &crng->state[4],
sizeof(__u32) * 12, 0);
else
_get_random_bytes(&crng->state[4], sizeof(__u32) * 12);
for (i = 4; i < 16; i++) {
if (!arch_get_random_seed_long(&rv) &&
!arch_get_random_long(&rv))
rv = random_get_entropy();
crng->state[i] ^= rv;
}
crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1;
}
#ifdef CONFIG_NUMA
static void numa_crng_init(void)
{
int i;
struct crng_state *crng;
struct crng_state **pool;
pool = kcalloc(nr_node_ids, sizeof(*pool), GFP_KERNEL|__GFP_NOFAIL);
for_each_online_node(i) {
crng = kmalloc_node(sizeof(struct crng_state),
GFP_KERNEL | __GFP_NOFAIL, i);
spin_lock_init(&crng->lock);
crng_initialize(crng);
pool[i] = crng;
}
mb();
if (cmpxchg(&crng_node_pool, NULL, pool)) {
for_each_node(i)
kfree(pool[i]);
kfree(pool);
}
}
#else
static void numa_crng_init(void) {}
#endif
/*
* crng_fast_load() can be called by code in the interrupt service
* path. So we can't afford to dilly-dally.
*/
static int crng_fast_load(const char *cp, size_t len)
{
unsigned long flags;
char *p;
if (!spin_trylock_irqsave(&primary_crng.lock, flags))
return 0;
if (crng_init != 0) {
spin_unlock_irqrestore(&primary_crng.lock, flags);
return 0;
}
p = (unsigned char *) &primary_crng.state[4];
while (len > 0 && crng_init_cnt < CRNG_INIT_CNT_THRESH) {
p[crng_init_cnt % CHACHA20_KEY_SIZE] ^= *cp;
cp++; crng_init_cnt++; len--;
}
spin_unlock_irqrestore(&primary_crng.lock, flags);
if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) {
invalidate_batched_entropy();
crng_init = 1;
wake_up_interruptible(&crng_init_wait);
pr_notice("random: fast init done\n");
}
return 1;
}
/*
* crng_slow_load() is called by add_device_randomness, which has two
* attributes. (1) We can't trust the buffer passed to it is
* guaranteed to be unpredictable (so it might not have any entropy at
* all), and (2) it doesn't have the performance constraints of
* crng_fast_load().
*
* So we do something more comprehensive which is guaranteed to touch
* all of the primary_crng's state, and which uses a LFSR with a
* period of 255 as part of the mixing algorithm. Finally, we do
* *not* advance crng_init_cnt since buffer we may get may be something
* like a fixed DMI table (for example), which might very well be
* unique to the machine, but is otherwise unvarying.
*/
static int crng_slow_load(const char *cp, size_t len)
{
unsigned long flags;
static unsigned char lfsr = 1;
unsigned char tmp;
unsigned i, max = CHACHA20_KEY_SIZE;
const char * src_buf = cp;
char * dest_buf = (char *) &primary_crng.state[4];
if (!spin_trylock_irqsave(&primary_crng.lock, flags))
return 0;
if (crng_init != 0) {
spin_unlock_irqrestore(&primary_crng.lock, flags);
return 0;
}
if (len > max)
max = len;
for (i = 0; i < max ; i++) {
tmp = lfsr;
lfsr >>= 1;
if (tmp & 1)
lfsr ^= 0xE1;
tmp = dest_buf[i % CHACHA20_KEY_SIZE];
dest_buf[i % CHACHA20_KEY_SIZE] ^= src_buf[i % len] ^ lfsr;
lfsr += (tmp << 3) | (tmp >> 5);
}
spin_unlock_irqrestore(&primary_crng.lock, flags);
return 1;
}
static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
{
unsigned long flags;
int i, num;
union {
__u32 block[CHACHA20_BLOCK_WORDS];
__u32 key[8];
} buf;
if (r) {
num = extract_entropy(r, &buf, 32, 16, 0);
if (num == 0)
return;
} else {
_extract_crng(&primary_crng, buf.block);
_crng_backtrack_protect(&primary_crng, buf.block,
CHACHA20_KEY_SIZE);
}
spin_lock_irqsave(&crng->lock, flags);
for (i = 0; i < 8; i++) {
unsigned long rv;
if (!arch_get_random_seed_long(&rv) &&
!arch_get_random_long(&rv))
rv = random_get_entropy();
crng->state[i+4] ^= buf.key[i] ^ rv;
}
memzero_explicit(&buf, sizeof(buf));
crng->init_time = jiffies;
spin_unlock_irqrestore(&crng->lock, flags);
if (crng == &primary_crng && crng_init < 2) {
invalidate_batched_entropy();
numa_crng_init();
crng_init = 2;
process_random_ready_list();
wake_up_interruptible(&crng_init_wait);
pr_notice("random: crng init done\n");
}
}
static void _extract_crng(struct crng_state *crng,
__u32 out[CHACHA20_BLOCK_WORDS])
{
unsigned long v, flags;
if (crng_ready() &&
(time_after(crng_global_init_time, crng->init_time) ||
time_after(jiffies, crng->init_time + CRNG_RESEED_INTERVAL)))
crng_reseed(crng, crng == &primary_crng ? &input_pool : NULL);
spin_lock_irqsave(&crng->lock, flags);
if (arch_get_random_long(&v))
crng->state[14] ^= v;
chacha20_block(&crng->state[0], out);
if (crng->state[12] == 0)
crng->state[13]++;
spin_unlock_irqrestore(&crng->lock, flags);
}
static void extract_crng(__u32 out[CHACHA20_BLOCK_WORDS])
{
struct crng_state *crng = NULL;
#ifdef CONFIG_NUMA
if (crng_node_pool)
crng = crng_node_pool[numa_node_id()];
if (crng == NULL)
#endif
crng = &primary_crng;
_extract_crng(crng, out);
}
/*
* Use the leftover bytes from the CRNG block output (if there is
* enough) to mutate the CRNG key to provide backtracking protection.
*/
static void _crng_backtrack_protect(struct crng_state *crng,
__u32 tmp[CHACHA20_BLOCK_WORDS], int used)
{
unsigned long flags;
__u32 *s, *d;
int i;
used = round_up(used, sizeof(__u32));
if (used + CHACHA20_KEY_SIZE > CHACHA20_BLOCK_SIZE) {
extract_crng(tmp);
used = 0;
}
spin_lock_irqsave(&crng->lock, flags);
s = &tmp[used / sizeof(__u32)];
d = &crng->state[4];
for (i=0; i < 8; i++)
*d++ ^= *s++;
spin_unlock_irqrestore(&crng->lock, flags);
}
static void crng_backtrack_protect(__u32 tmp[CHACHA20_BLOCK_WORDS], int used)
{
struct crng_state *crng = NULL;
#ifdef CONFIG_NUMA
if (crng_node_pool)
crng = crng_node_pool[numa_node_id()];
if (crng == NULL)
#endif
crng = &primary_crng;
_crng_backtrack_protect(crng, tmp, used);
}
static ssize_t extract_crng_user(void __user *buf, size_t nbytes)
{
ssize_t ret = 0, i = CHACHA20_BLOCK_SIZE;
__u32 tmp[CHACHA20_BLOCK_WORDS];
int large_request = (nbytes > 256);
while (nbytes) {
if (large_request && need_resched()) {
if (signal_pending(current)) {
if (ret == 0)
ret = -ERESTARTSYS;
break;
}
schedule();
}
extract_crng(tmp);
i = min_t(int, nbytes, CHACHA20_BLOCK_SIZE);
if (copy_to_user(buf, tmp, i)) {
ret = -EFAULT;
break;
}
nbytes -= i;
buf += i;
ret += i;
}
crng_backtrack_protect(tmp, i);
/* Wipe data just written to memory */
memzero_explicit(tmp, sizeof(tmp));
return ret;
}
/*********************************************************************
*
* Entropy input management
*
*********************************************************************/
/* There is one of these per entropy source */
struct timer_rand_state {
cycles_t last_time;
long last_delta, last_delta2;
};
#define INIT_TIMER_RAND_STATE { INITIAL_JIFFIES, };
/*
* 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, unsigned int size)
{
unsigned long time = random_get_entropy() ^ jiffies;
unsigned long flags;
if (!crng_ready() && size)
crng_slow_load(buf, size);
trace_add_device_randomness(size, _RET_IP_);
spin_lock_irqsave(&input_pool.lock, flags);
_mix_pool_bytes(&input_pool, buf, size);
_mix_pool_bytes(&input_pool, &time, sizeof(time));
spin_unlock_irqrestore(&input_pool.lock, flags);
}
EXPORT_SYMBOL(add_device_randomness);
static struct timer_rand_state input_timer_state = INIT_TIMER_RAND_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.
*
*/
static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
{
struct entropy_store *r;
struct {
long jiffies;
unsigned cycles;
unsigned num;
} sample;
long delta, delta2, delta3;
preempt_disable();
sample.jiffies = jiffies;
sample.cycles = random_get_entropy();
sample.num = num;
r = &input_pool;
mix_pool_bytes(r, &sample, sizeof(sample));
/*
* 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 = sample.jiffies - state->last_time;
state->last_time = sample.jiffies;
delta2 = delta - state->last_delta;
state->last_delta = delta;
delta3 = delta2 - state->last_delta2;
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 entimate to 12 bits.
*/
credit_entropy_bits(r, min_t(int, fls(delta>>1), 11));
preempt_enable();
}
void add_input_randomness(unsigned int type, unsigned int code,
unsigned int value)
{
static unsigned char last_value;
/* 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);
trace_add_input_randomness(ENTROPY_BITS(&input_pool));
}
EXPORT_SYMBOL_GPL(add_input_randomness);
static DEFINE_PER_CPU(struct fast_pool, irq_randomness);
#ifdef ADD_INTERRUPT_BENCH
static unsigned long avg_cycles, avg_deviation;
#define AVG_SHIFT 8 /* Exponential average factor k=1/256 */
#define FIXED_1_2 (1 << (AVG_SHIFT-1))
static void add_interrupt_bench(cycles_t start)
{
long delta = random_get_entropy() - start;
/* Use a weighted moving average */
delta = delta - ((avg_cycles + FIXED_1_2) >> AVG_SHIFT);
avg_cycles += delta;
/* And average deviation */
delta = abs(delta) - ((avg_deviation + FIXED_1_2) >> AVG_SHIFT);
avg_deviation += delta;
}
#else
#define add_interrupt_bench(x)
#endif
static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs)
{
__u32 *ptr = (__u32 *) regs;
unsigned int idx;
if (regs == NULL)
return 0;
idx = READ_ONCE(f->reg_idx);
if (idx >= sizeof(struct pt_regs) / sizeof(__u32))
idx = 0;
ptr += idx++;
WRITE_ONCE(f->reg_idx, idx);
return *ptr;
}
void add_interrupt_randomness(int irq, int irq_flags)
{
struct entropy_store *r;
struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness);
struct pt_regs *regs = get_irq_regs();
unsigned long now = jiffies;
cycles_t cycles = random_get_entropy();
__u32 c_high, j_high;
__u64 ip;
unsigned long seed;
int credit = 0;
if (cycles == 0)
cycles = get_reg(fast_pool, regs);
c_high = (sizeof(cycles) > 4) ? cycles >> 32 : 0;
j_high = (sizeof(now) > 4) ? now >> 32 : 0;
fast_pool->pool[0] ^= cycles ^ j_high ^ irq;
fast_pool->pool[1] ^= now ^ c_high;
ip = regs ? instruction_pointer(regs) : _RET_IP_;
fast_pool->pool[2] ^= ip;
fast_pool->pool[3] ^= (sizeof(ip) > 4) ? ip >> 32 :
get_reg(fast_pool, regs);
fast_mix(fast_pool);
add_interrupt_bench(cycles);
if (unlikely(crng_init == 0)) {
if ((fast_pool->count >= 64) &&
crng_fast_load((char *) fast_pool->pool,
sizeof(fast_pool->pool))) {
fast_pool->count = 0;
fast_pool->last = now;
}
return;
}
if ((fast_pool->count < 64) &&
!time_after(now, fast_pool->last + HZ))
return;
r = &input_pool;
if (!spin_trylock(&r->lock))
return;
fast_pool->last = now;
__mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool));
/*
* If we have architectural seed generator, produce a seed and
* add it to the pool. For the sake of paranoia don't let the
* architectural seed generator dominate the input from the
* interrupt noise.
*/
if (arch_get_random_seed_long(&seed)) {
__mix_pool_bytes(r, &seed, sizeof(seed));
credit = 1;
}
spin_unlock(&r->lock);
fast_pool->count = 0;
/* award one bit for the contents of the fast pool */
credit_entropy_bits(r, credit + 1);
}
EXPORT_SYMBOL_GPL(add_interrupt_randomness);
#ifdef CONFIG_BLOCK
void add_disk_randomness(struct gendisk *disk)
{
if (!disk || !disk->random)
return;
/* first major is 1, so we get >= 0x200 here */
add_timer_randomness(disk->random, 0x100 + disk_devt(disk));
trace_add_disk_randomness(disk_devt(disk), ENTROPY_BITS(&input_pool));
}
EXPORT_SYMBOL_GPL(add_disk_randomness);
#endif
/*********************************************************************
*
* Entropy extraction routines
*
*********************************************************************/
/*
* This utility inline function is responsible for transferring entropy
* from the primary pool to the secondary extraction pool. We make
* sure we pull enough for a 'catastrophic reseed'.
*/
static void _xfer_secondary_pool(struct entropy_store *r, size_t nbytes);
static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
{
if (!r->pull ||
r->entropy_count >= (nbytes << (ENTROPY_SHIFT + 3)) ||
r->entropy_count > r->poolinfo->poolfracbits)
return;
_xfer_secondary_pool(r, nbytes);
}
static void _xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
{
__u32 tmp[OUTPUT_POOL_WORDS];
int bytes = nbytes;
/* pull at least as much as a wakeup */
bytes = max_t(int, bytes, random_read_wakeup_bits / 8);
/* but never more than the buffer size */
bytes = min_t(int, bytes, sizeof(tmp));
trace_xfer_secondary_pool(r->name, bytes * 8, nbytes * 8,
ENTROPY_BITS(r), ENTROPY_BITS(r->pull));
bytes = extract_entropy(r->pull, tmp, bytes,
random_read_wakeup_bits / 8, 0);
mix_pool_bytes(r, tmp, bytes);
credit_entropy_bits(r, bytes*8);
}
/*
* Used as a workqueue function so that when the input pool is getting
* full, we can "spill over" some entropy to the output pools. That
* way the output pools can store some of the excess entropy instead
* of letting it go to waste.
*/
static void push_to_pool(struct work_struct *work)
{
struct entropy_store *r = container_of(work, struct entropy_store,
push_work);
BUG_ON(!r);
_xfer_secondary_pool(r, random_read_wakeup_bits/8);
trace_push_to_pool(r->name, r->entropy_count >> ENTROPY_SHIFT,
r->pull->entropy_count >> ENTROPY_SHIFT);
}
/*
* This function decides how many bytes to actually take from the
* given pool, and also debits the entropy count accordingly.
*/
static size_t account(struct entropy_store *r, size_t nbytes, int min,
int reserved)
{
int entropy_count, orig, have_bytes;
size_t ibytes, nfrac;
BUG_ON(r->entropy_count > r->poolinfo->poolfracbits);
/* Can we pull enough? */
retry:
entropy_count = orig = READ_ONCE(r->entropy_count);
ibytes = nbytes;
/* never pull more than available */
have_bytes = entropy_count >> (ENTROPY_SHIFT + 3);
if ((have_bytes -= reserved) < 0)
have_bytes = 0;
ibytes = min_t(size_t, ibytes, have_bytes);
if (ibytes < min)
ibytes = 0;
if (unlikely(entropy_count < 0)) {
pr_warn("random: negative entropy count: pool %s count %d\n",
r->name, entropy_count);
WARN_ON(1);
entropy_count = 0;
}
nfrac = ibytes << (ENTROPY_SHIFT + 3);
if ((size_t) entropy_count > nfrac)
entropy_count -= nfrac;
else
entropy_count = 0;
if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
goto retry;
trace_debit_entropy(r->name, 8 * ibytes);
if (ibytes &&
(r->entropy_count >> ENTROPY_SHIFT) < random_write_wakeup_bits) {
wake_up_interruptible(&random_write_wait);
kill_fasync(&fasync, SIGIO, POLL_OUT);
}
return ibytes;
}
/*
* This function does the actual extraction for extract_entropy and
* extract_entropy_user.
*
* Note: we assume that .poolwords is a multiple of 16 words.
*/
static void extract_buf(struct entropy_store *r, __u8 *out)
{
int i;
union {
__u32 w[5];
unsigned long l[LONGS(20)];
} hash;
__u32 workspace[SHA_WORKSPACE_WORDS];
unsigned long flags;
/*
* If we have an architectural hardware random number
* generator, use it for SHA's initial vector
*/
sha_init(hash.w);
for (i = 0; i < LONGS(20); i++) {
unsigned long v;
if (!arch_get_random_long(&v))
break;
hash.l[i] = v;
}
/* Generate a hash across the pool, 16 words (512 bits) at a time */
spin_lock_irqsave(&r->lock, flags);
for (i = 0; i < r->poolinfo->poolwords; i += 16)
sha_transform(hash.w, (__u8 *)(r->pool + i), workspace);
/*
* 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.
*/
__mix_pool_bytes(r, hash.w, sizeof(hash.w));
spin_unlock_irqrestore(&r->lock, flags);
memzero_explicit(workspace, sizeof(workspace));
/*
* In case the hash function has some recognizable output
* pattern, we fold it in half. Thus, we always feed back
* twice as much data as we output.
*/
hash.w[0] ^= hash.w[3];
hash.w[1] ^= hash.w[4];
hash.w[2] ^= rol32(hash.w[2], 16);
memcpy(out, &hash, EXTRACT_SIZE);
memzero_explicit(&hash, sizeof(hash));
}
static ssize_t _extract_entropy(struct entropy_store *r, void *buf,
size_t nbytes, int fips)
{
ssize_t ret = 0, i;
__u8 tmp[EXTRACT_SIZE];
unsigned long flags;
while (nbytes) {
extract_buf(r, tmp);
if (fips) {
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;
}
/* Wipe data just returned from memory */
memzero_explicit(tmp, sizeof(tmp));
return ret;
}
/*
* This function extracts randomness from the "entropy pool", and
* returns it in a buffer.
*
* The min parameter specifies the minimum amount we can pull before
* failing to avoid races that defeat catastrophic reseeding while the
* reserved parameter indicates how much entropy we must leave in the
* pool after each pull to avoid starving other readers.
*/
static ssize_t extract_entropy(struct entropy_store *r, void *buf,
size_t nbytes, int min, int reserved)
{
__u8 tmp[EXTRACT_SIZE];
unsigned long flags;
/* if last_data isn't primed, we need EXTRACT_SIZE extra bytes */
if (fips_enabled) {
spin_lock_irqsave(&r->lock, flags);
if (!r->last_data_init) {
r->last_data_init = 1;
spin_unlock_irqrestore(&r->lock, flags);
trace_extract_entropy(r->name, EXTRACT_SIZE,
ENTROPY_BITS(r), _RET_IP_);
xfer_secondary_pool(r, EXTRACT_SIZE);
extract_buf(r, tmp);
spin_lock_irqsave(&r->lock, flags);
memcpy(r->last_data, tmp, EXTRACT_SIZE);
}
spin_unlock_irqrestore(&r->lock, flags);
}
trace_extract_entropy(r->name, nbytes, ENTROPY_BITS(r), _RET_IP_);
xfer_secondary_pool(r, nbytes);
nbytes = account(r, nbytes, min, reserved);
return _extract_entropy(r, buf, nbytes, fips_enabled);
}
/*
* This function extracts randomness from the "entropy pool", and
* returns it in a userspace buffer.
*/
static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf,
size_t nbytes)
{
ssize_t ret = 0, i;
__u8 tmp[EXTRACT_SIZE];
int large_request = (nbytes > 256);
trace_extract_entropy_user(r->name, nbytes, ENTROPY_BITS(r), _RET_IP_);
xfer_secondary_pool(r, nbytes);
nbytes = account(r, nbytes, 0, 0);
while (nbytes) {
if (large_request && need_resched()) {
if (signal_pending(current)) {
if (ret == 0)
ret = -ERESTARTSYS;
break;
}
schedule();
}
extract_buf(r, tmp);
i = min_t(int, nbytes, EXTRACT_SIZE);
if (copy_to_user(buf, tmp, i)) {
ret = -EFAULT;
break;
}
nbytes -= i;
buf += i;
ret += i;
}
/* Wipe data just returned from memory */
memzero_explicit(tmp, sizeof(tmp));
return ret;
}
#define warn_unseeded_randomness(previous) \
_warn_unseeded_randomness(__func__, (void *) _RET_IP_, (previous))
static void _warn_unseeded_randomness(const char *func_name, void *caller,
void **previous)
{
#ifdef CONFIG_WARN_ALL_UNSEEDED_RANDOM
const bool print_once = false;
#else
static bool print_once __read_mostly;
#endif
if (print_once ||
crng_ready() ||
(previous && (caller == READ_ONCE(*previous))))
return;
WRITE_ONCE(*previous, caller);
#ifndef CONFIG_WARN_ALL_UNSEEDED_RANDOM
print_once = true;
#endif
pr_notice("random: %s called from %pS with crng_init=%d\n",
func_name, caller, crng_init);
}
/*
* This function is the exported kernel interface. It returns some
* number of good random numbers, suitable for key generation, seeding
* TCP sequence numbers, etc. It does not rely on the hardware random
* number generator. For random bytes direct from the hardware RNG
* (when available), use get_random_bytes_arch(). In order to ensure
* that the randomness provided by this function is okay, the function
* wait_for_random_bytes() should be called and return 0 at least once
* at any point prior.
*/
static void _get_random_bytes(void *buf, int nbytes)
{
__u32 tmp[CHACHA20_BLOCK_WORDS];
trace_get_random_bytes(nbytes, _RET_IP_);
while (nbytes >= CHACHA20_BLOCK_SIZE) {
extract_crng(buf);
buf += CHACHA20_BLOCK_SIZE;
nbytes -= CHACHA20_BLOCK_SIZE;
}
if (nbytes > 0) {
extract_crng(tmp);
memcpy(buf, tmp, nbytes);
crng_backtrack_protect(tmp, nbytes);
} else
crng_backtrack_protect(tmp, CHACHA20_BLOCK_SIZE);
memzero_explicit(tmp, sizeof(tmp));
}
void get_random_bytes(void *buf, int nbytes)
{
static void *previous;
warn_unseeded_randomness(&previous);
_get_random_bytes(buf, nbytes);
}
EXPORT_SYMBOL(get_random_bytes);
/*
* Wait for the urandom pool to be seeded and thus guaranteed to supply
* cryptographically secure random numbers. This applies to: the /dev/urandom
* device, the get_random_bytes function, and the get_random_{u32,u64,int,long}
* family of functions. Using any of these functions without first calling
* this function forfeits the guarantee of security.
*
* Returns: 0 if the urandom pool has been seeded.
* -ERESTARTSYS if the function was interrupted by a signal.
*/
int wait_for_random_bytes(void)
{
if (likely(crng_ready()))
return 0;
return wait_event_interruptible(crng_init_wait, crng_ready());
}
EXPORT_SYMBOL(wait_for_random_bytes);
/*
* Add a callback function that will be invoked when the nonblocking
* pool is initialised.
*
* returns: 0 if callback is successfully added
* -EALREADY if pool is already initialised (callback not called)
* -ENOENT if module for callback is not alive
*/
int add_random_ready_callback(struct random_ready_callback *rdy)
{
struct module *owner;
unsigned long flags;
int err = -EALREADY;
if (crng_ready())
return err;
owner = rdy->owner;
if (!try_module_get(owner))
return -ENOENT;
spin_lock_irqsave(&random_ready_list_lock, flags);
if (crng_ready())
goto out;
owner = NULL;
list_add(&rdy->list, &random_ready_list);
err = 0;
out:
spin_unlock_irqrestore(&random_ready_list_lock, flags);
module_put(owner);
return err;
}
EXPORT_SYMBOL(add_random_ready_callback);
/*
* Delete a previously registered readiness callback function.
*/
void del_random_ready_callback(struct random_ready_callback *rdy)
{
unsigned long flags;
struct module *owner = NULL;
spin_lock_irqsave(&random_ready_list_lock, flags);
if (!list_empty(&rdy->list)) {
list_del_init(&rdy->list);
owner = rdy->owner;
}
spin_unlock_irqrestore(&random_ready_list_lock, flags);
module_put(owner);
}
EXPORT_SYMBOL(del_random_ready_callback);
/*
* 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.
*/
void get_random_bytes_arch(void *buf, int nbytes)
{
char *p = buf;
trace_get_random_bytes_arch(nbytes, _RET_IP_);
while (nbytes) {
unsigned long v;
int chunk = min(nbytes, (int)sizeof(unsigned long));
if (!arch_get_random_long(&v))
break;
memcpy(p, &v, chunk);
p += chunk;
nbytes -= chunk;
}
if (nbytes)
get_random_bytes(p, nbytes);
}
EXPORT_SYMBOL(get_random_bytes_arch);
/*
* 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.
*/
static void init_std_data(struct entropy_store *r)
{
int i;
ktime_t now = ktime_get_real();
unsigned long rv;
r->last_pulled = jiffies;
mix_pool_bytes(r, &now, sizeof(now));
for (i = r->poolinfo->poolbytes; i > 0; i -= sizeof(rv)) {
if (!arch_get_random_seed_long(&rv) &&
!arch_get_random_long(&rv))
rv = random_get_entropy();
mix_pool_bytes(r, &rv, sizeof(rv));
}
mix_pool_bytes(r, utsname(), sizeof(*(utsname())));
}
/*
* 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)
{
init_std_data(&input_pool);
init_std_data(&blocking_pool);
crng_initialize(&primary_crng);
crng_global_init_time = jiffies;
return 0;
}
early_initcall(rand_initialize);
#ifdef CONFIG_BLOCK
void rand_initialize_disk(struct gendisk *disk)
{
struct timer_rand_state *state;
/*
* If kzalloc returns null, we just won't use that entropy
* source.
*/
state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL);
if (state) {
state->last_time = INITIAL_JIFFIES;
disk->random = state;
}
}
#endif
static ssize_t
_random_read(int nonblock, char __user *buf, size_t nbytes)
{
ssize_t n;
if (nbytes == 0)
return 0;
nbytes = min_t(size_t, nbytes, SEC_XFER_SIZE);
while (1) {
n = extract_entropy_user(&blocking_pool, buf, nbytes);
if (n < 0)
return n;
trace_random_read(n*8, (nbytes-n)*8,
ENTROPY_BITS(&blocking_pool),
ENTROPY_BITS(&input_pool));
if (n > 0)
return n;
/* Pool is (near) empty. Maybe wait and retry. */
if (nonblock)
return -EAGAIN;
wait_event_interruptible(random_read_wait,
ENTROPY_BITS(&input_pool) >=
random_read_wakeup_bits);
if (signal_pending(current))
return -ERESTARTSYS;
}
}
static ssize_t
random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
{
return _random_read(file->f_flags & O_NONBLOCK, buf, nbytes);
}
static ssize_t
urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
{
unsigned long flags;
static int maxwarn = 10;
int ret;
if (!crng_ready() && maxwarn > 0) {
maxwarn--;
printk(KERN_NOTICE "random: %s: uninitialized urandom read "
"(%zd bytes read)\n",
current->comm, nbytes);
spin_lock_irqsave(&primary_crng.lock, flags);
crng_init_cnt = 0;
spin_unlock_irqrestore(&primary_crng.lock, flags);
}
nbytes = min_t(size_t, nbytes, INT_MAX >> (ENTROPY_SHIFT + 3));
ret = extract_crng_user(buf, nbytes);
trace_urandom_read(8 * nbytes, 0, ENTROPY_BITS(&input_pool));
return ret;
}
static __poll_t
random_poll(struct file *file, poll_table * wait)
{
__poll_t mask;
poll_wait(file, &random_read_wait, wait);
poll_wait(file, &random_write_wait, wait);
mask = 0;
if (ENTROPY_BITS(&input_pool) >= random_read_wakeup_bits)
mask |= EPOLLIN | EPOLLRDNORM;
if (ENTROPY_BITS(&input_pool) < random_write_wakeup_bits)
mask |= EPOLLOUT | EPOLLWRNORM;
return mask;
}
static int
write_pool(struct entropy_store *r, const char __user *buffer, size_t count)
{
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;
count -= bytes;
p += bytes;
mix_pool_bytes(r, buf, bytes);
cond_resched();
}
return 0;
}
static ssize_t random_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos)
{
size_t ret;
ret = write_pool(&input_pool, buffer, count);
if (ret)
return ret;
return (ssize_t)count;
}
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;
switch (cmd) {
case RNDGETENTCNT:
/* inherently racy, no point locking */
ent_count = ENTROPY_BITS(&input_pool);
if (put_user(ent_count, p))
return -EFAULT;
return 0;
case RNDADDTOENTCNT:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(ent_count, p))
return -EFAULT;
return credit_entropy_bits_safe(&input_pool, ent_count);
case RNDADDENTROPY:
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++))
return -EFAULT;
retval = write_pool(&input_pool, (const char __user *)p,
size);
if (retval < 0)
return retval;
return credit_entropy_bits_safe(&input_pool, ent_count);
case RNDZAPENTCNT:
case RNDCLEARPOOL:
/*
* Clear the entropy pool counters. We no longer clear
* the entropy pool, as that's silly.
*/
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
input_pool.entropy_count = 0;
blocking_pool.entropy_count = 0;
return 0;
case RNDRESEEDCRNG:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (crng_init < 2)
return -ENODATA;
crng_reseed(&primary_crng, NULL);
crng_global_init_time = jiffies - 1;
return 0;
default:
return -EINVAL;
}
}
static int random_fasync(int fd, struct file *filp, int on)
{
return fasync_helper(fd, filp, on, &fasync);
}
const struct file_operations random_fops = {
.read = random_read,
.write = random_write,
.poll = random_poll,
.unlocked_ioctl = random_ioctl,
.fasync = random_fasync,
.llseek = noop_llseek,
};
const struct file_operations urandom_fops = {
.read = urandom_read,
.write = random_write,
.unlocked_ioctl = random_ioctl,
.fasync = random_fasync,
.llseek = noop_llseek,
};
SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count,
unsigned int, flags)
{
int ret;
if (flags & ~(GRND_NONBLOCK|GRND_RANDOM))
return -EINVAL;
if (count > INT_MAX)
count = INT_MAX;
if (flags & GRND_RANDOM)
return _random_read(flags & GRND_NONBLOCK, buf, count);
if (!crng_ready()) {
if (flags & GRND_NONBLOCK)
return -EAGAIN;
ret = wait_for_random_bytes();
if (unlikely(ret))
return ret;
}
return urandom_read(NULL, buf, count, NULL);
}
/********************************************************************
*
* Sysctl interface
*
********************************************************************/
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
static int min_read_thresh = 8, min_write_thresh;
static int max_read_thresh = OUTPUT_POOL_WORDS * 32;
static int max_write_thresh = INPUT_POOL_WORDS * 32;
static int random_min_urandom_seed = 60;
static char sysctl_bootid[16];
/*
* 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, the UUID will be
* returned as an ASCII string in the standard UUID format; if via the
* sysctl system call, 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)
{
struct ctl_table fake_table;
unsigned char buf[64], tmp_uuid[16], *uuid;
uuid = table->data;
if (!uuid) {
uuid = tmp_uuid;
generate_random_uuid(uuid);
} else {
static DEFINE_SPINLOCK(bootid_spinlock);
spin_lock(&bootid_spinlock);
if (!uuid[8])
generate_random_uuid(uuid);
spin_unlock(&bootid_spinlock);
}
sprintf(buf, "%pU", uuid);
fake_table.data = buf;
fake_table.maxlen = sizeof(buf);
return proc_dostring(&fake_table, write, buffer, lenp, ppos);
}
/*
* Return entropy available scaled to integral bits
*/
static int proc_do_entropy(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table fake_table;
int entropy_count;
entropy_count = *(int *)table->data >> ENTROPY_SHIFT;
fake_table.data = &entropy_count;
fake_table.maxlen = sizeof(entropy_count);
return proc_dointvec(&fake_table, write, buffer, lenp, ppos);
}
static int sysctl_poolsize = INPUT_POOL_WORDS * 32;
extern struct ctl_table random_table[];
struct ctl_table random_table[] = {
{
.procname = "poolsize",
.data = &sysctl_poolsize,
.maxlen = sizeof(int),
.mode = 0444,
.proc_handler = proc_dointvec,
},
{
.procname = "entropy_avail",
.maxlen = sizeof(int),
.mode = 0444,
.proc_handler = proc_do_entropy,
.data = &input_pool.entropy_count,
},
{
.procname = "read_wakeup_threshold",
.data = &random_read_wakeup_bits,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_read_thresh,
.extra2 = &max_read_thresh,
},
{
.procname = "write_wakeup_threshold",
.data = &random_write_wakeup_bits,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_write_thresh,
.extra2 = &max_write_thresh,
},
{
.procname = "urandom_min_reseed_secs",
.data = &random_min_urandom_seed,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.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,
},
#ifdef ADD_INTERRUPT_BENCH
{
.procname = "add_interrupt_avg_cycles",
.data = &avg_cycles,
.maxlen = sizeof(avg_cycles),
.mode = 0444,
.proc_handler = proc_doulongvec_minmax,
},
{
.procname = "add_interrupt_avg_deviation",
.data = &avg_deviation,
.maxlen = sizeof(avg_deviation),
.mode = 0444,
.proc_handler = proc_doulongvec_minmax,
},
#endif
{ }
};
#endif /* CONFIG_SYSCTL */
struct batched_entropy {
union {
u64 entropy_u64[CHACHA20_BLOCK_SIZE / sizeof(u64)];
u32 entropy_u32[CHACHA20_BLOCK_SIZE / sizeof(u32)];
};
unsigned int position;
};
static rwlock_t batched_entropy_reset_lock = __RW_LOCK_UNLOCKED(batched_entropy_reset_lock);
/*
* Get a random word for internal kernel use only. The quality of the random
* number is either as good as RDRAND or as good as /dev/urandom, with the
* goal of being quite fast and not depleting entropy. In order to ensure
* that the randomness provided by this function is okay, the function
* wait_for_random_bytes() should be called and return 0 at least once
* at any point prior.
*/
static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64);
u64 get_random_u64(void)
{
u64 ret;
bool use_lock;
unsigned long flags = 0;
struct batched_entropy *batch;
static void *previous;
#if BITS_PER_LONG == 64
if (arch_get_random_long((unsigned long *)&ret))
return ret;
#else
if (arch_get_random_long((unsigned long *)&ret) &&
arch_get_random_long((unsigned long *)&ret + 1))
return ret;
#endif
warn_unseeded_randomness(&previous);
use_lock = READ_ONCE(crng_init) < 2;
batch = &get_cpu_var(batched_entropy_u64);
if (use_lock)
read_lock_irqsave(&batched_entropy_reset_lock, flags);
if (batch->position % ARRAY_SIZE(batch->entropy_u64) == 0) {
extract_crng((__u32 *)batch->entropy_u64);
batch->position = 0;
}
ret = batch->entropy_u64[batch->position++];
if (use_lock)
read_unlock_irqrestore(&batched_entropy_reset_lock, flags);
put_cpu_var(batched_entropy_u64);
return ret;
}
EXPORT_SYMBOL(get_random_u64);
static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32);
u32 get_random_u32(void)
{
u32 ret;
bool use_lock;
unsigned long flags = 0;
struct batched_entropy *batch;
static void *previous;
if (arch_get_random_int(&ret))
return ret;
warn_unseeded_randomness(&previous);
use_lock = READ_ONCE(crng_init) < 2;
batch = &get_cpu_var(batched_entropy_u32);
if (use_lock)
read_lock_irqsave(&batched_entropy_reset_lock, flags);
if (batch->position % ARRAY_SIZE(batch->entropy_u32) == 0) {
extract_crng(batch->entropy_u32);
batch->position = 0;
}
ret = batch->entropy_u32[batch->position++];
if (use_lock)
read_unlock_irqrestore(&batched_entropy_reset_lock, flags);
put_cpu_var(batched_entropy_u32);
return ret;
}
EXPORT_SYMBOL(get_random_u32);
/* It's important to invalidate all potential batched entropy that might
* be stored before the crng is initialized, which we can do lazily by
* simply resetting the counter to zero so that it's re-extracted on the
* next usage. */
static void invalidate_batched_entropy(void)
{
int cpu;
unsigned long flags;
write_lock_irqsave(&batched_entropy_reset_lock, flags);
for_each_possible_cpu (cpu) {
per_cpu_ptr(&batched_entropy_u32, cpu)->position = 0;
per_cpu_ptr(&batched_entropy_u64, cpu)->position = 0;
}
write_unlock_irqrestore(&batched_entropy_reset_lock, flags);
}
/**
* randomize_page - Generate a random, page aligned address
* @start: The smallest acceptable address the caller will take.
* @range: The size of the area, starting at @start, within which the
* random address must fall.
*
* If @start + @range would overflow, @range is capped.
*
* NOTE: Historical use of randomize_range, which this replaces, presumed that
* @start was already page aligned. We now align it regardless.
*
* Return: A page aligned address within [start, start + range). On error,
* @start is returned.
*/
unsigned long
randomize_page(unsigned long start, unsigned long range)
{
if (!PAGE_ALIGNED(start)) {
range -= PAGE_ALIGN(start) - start;
start = PAGE_ALIGN(start);
}
if (start > ULONG_MAX - range)
range = ULONG_MAX - start;
range >>= PAGE_SHIFT;
if (range == 0)
return start;
return start + (get_random_long() % range << PAGE_SHIFT);
}
/* Interface for in-kernel drivers of true hardware RNGs.
* Those devices may produce endless random bits and will be throttled
* when our pool is full.
*/
void add_hwgenerator_randomness(const char *buffer, size_t count,
size_t entropy)
{
struct entropy_store *poolp = &input_pool;
if (unlikely(crng_init == 0)) {
crng_fast_load(buffer, count);
return;
}
/* Suspend writing if we're above the trickle threshold.
* We'll be woken up again once below random_write_wakeup_thresh,
* or when the calling thread is about to terminate.
*/
wait_event_interruptible(random_write_wait, kthread_should_stop() ||
ENTROPY_BITS(&input_pool) <= random_write_wakeup_bits);
mix_pool_bytes(poolp, buffer, count);
credit_entropy_bits(poolp, entropy);
}
EXPORT_SYMBOL_GPL(add_hwgenerator_randomness);