OpenCloudOS-Kernel/drivers/char/random.c

1675 lines
46 KiB
C
Raw Normal View History

// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
/*
random: use BLAKE2s instead of SHA1 in extraction This commit addresses one of the lower hanging fruits of the RNG: its usage of SHA1. BLAKE2s is generally faster, and certainly more secure, than SHA1, which has [1] been [2] really [3] very [4] broken [5]. Additionally, the current construction in the RNG doesn't use the full SHA1 function, as specified, and allows overwriting the IV with RDRAND output in an undocumented way, even in the case when RDRAND isn't set to "trusted", which means potential malicious IV choices. And its short length means that keeping only half of it secret when feeding back into the mixer gives us only 2^80 bits of forward secrecy. In other words, not only is the choice of hash function dated, but the use of it isn't really great either. This commit aims to fix both of these issues while also keeping the general structure and semantics as close to the original as possible. Specifically: a) Rather than overwriting the hash IV with RDRAND, we put it into BLAKE2's documented "salt" and "personal" fields, which were specifically created for this type of usage. b) Since this function feeds the full hash result back into the entropy collector, we only return from it half the length of the hash, just as it was done before. This increases the construction's forward secrecy from 2^80 to a much more comfortable 2^128. c) Rather than using the raw "sha1_transform" function alone, we instead use the full proper BLAKE2s function, with finalization. This also has the advantage of supplying 16 bytes at a time rather than SHA1's 10 bytes, which, in addition to having a faster compression function to begin with, means faster extraction in general. On an Intel i7-11850H, this commit makes initial seeding around 131% faster. BLAKE2s itself has the nice property of internally being based on the ChaCha permutation, which the RNG is already using for expansion, so there shouldn't be any issue with newness, funkiness, or surprising CPU behavior, since it's based on something already in use. [1] https://eprint.iacr.org/2005/010.pdf [2] https://www.iacr.org/archive/crypto2005/36210017/36210017.pdf [3] https://eprint.iacr.org/2015/967.pdf [4] https://shattered.io/static/shattered.pdf [5] https://www.usenix.org/system/files/sec20-leurent.pdf Reviewed-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2021-12-21 23:31:27 +08:00
* Copyright (C) 2017-2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
* Copyright Matt Mackall <mpm@selenic.com>, 2003, 2004, 2005
* Copyright Theodore Ts'o, 1994, 1995, 1996, 1997, 1998, 1999. All
* rights reserved.
*/
/*
* Exported interfaces ---- output
* ===============================
*
* There are four exported interfaces; two for use within the kernel,
* and two for use from userspace.
*
* Exported interfaces ---- userspace output
* -----------------------------------------
*
* The userspace 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 ---- kernel output
* --------------------------------------
*
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
* The primary kernel interfaces are:
*
* void get_random_bytes(void *buf, size_t nbytes);
* u32 get_random_u32()
* u64 get_random_u64()
* unsigned int get_random_int()
* unsigned long get_random_long()
*
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
* 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 get_random_{u32,u64,int,long}() family
* of functions may be higher performance for one-off random integers,
* because they do a bit of buffering.
*
* prandom_u32()
* -------------
*
* For even weaker applications, see the pseudorandom generator
* prandom_u32(), prandom_max(), and prandom_bytes(). If the random
* numbers aren't security-critical at all, these are *far* cheaper.
* Useful for self-tests, random error simulation, randomized backoffs,
* and any other application where you trust that nobody is trying to
* maliciously mess with you by guessing the "random" numbers.
*
* Exported interfaces ---- input
* ==============================
*
* The current exported interfaces for gathering environmental noise
* from the devices are:
*
* void add_device_randomness(const void *buf, size_t size);
* void add_input_randomness(unsigned int type, unsigned int code,
* unsigned int value);
* void add_interrupt_randomness(int irq);
* void add_disk_randomness(struct gendisk *disk);
* void add_hwgenerator_randomness(const void *buffer, size_t count,
* size_t entropy);
* void add_bootloader_randomness(const void *buf, size_t size);
*
* add_device_randomness() is for adding data to the random pool that
* is likely to differ between two devices (or possibly even per boot).
* 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.
*
* add_hwgenerator_randomness() is for true hardware RNGs, and will credit
* entropy as specified by the caller. If the entropy pool is full it will
* block until more entropy is needed.
*
* add_bootloader_randomness() is the same as add_hwgenerator_randomness() or
* add_device_randomness(), depending on whether or not the configuration
* option CONFIG_RANDOM_TRUST_BOOTLOADER is set.
*
* Ensuring unpredictability at system startup
* ============================================
*
* 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
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/utsname.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/major.h>
#include <linux/string.h>
#include <linux/fcntl.h>
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/poll.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/genhd.h>
#include <linux/interrupt.h>
2008-07-24 12:28:13 +08:00
#include <linux/mm.h>
#include <linux/nodemask.h>
#include <linux/spinlock.h>
#include <linux/kthread.h>
#include <linux/percpu.h>
#include <linux/ptrace.h>
#include <linux/workqueue.h>
#include <linux/irq.h>
#include <linux/ratelimit.h>
random: introduce getrandom(2) system call The getrandom(2) system call was requested by the LibreSSL Portable developers. It is analoguous to the getentropy(2) system call in OpenBSD. The rationale of this system call is to provide resiliance against file descriptor exhaustion attacks, where the attacker consumes all available file descriptors, forcing the use of the fallback code where /dev/[u]random is not available. Since the fallback code is often not well-tested, it is better to eliminate this potential failure mode entirely. The other feature provided by this new system call is the ability to request randomness from the /dev/urandom entropy pool, but to block until at least 128 bits of entropy has been accumulated in the /dev/urandom entropy pool. Historically, the emphasis in the /dev/urandom development has been to ensure that urandom pool is initialized as quickly as possible after system boot, and preferably before the init scripts start execution. This is because changing /dev/urandom reads to block represents an interface change that could potentially break userspace which is not acceptable. In practice, on most x86 desktop and server systems, in general the entropy pool can be initialized before it is needed (and in modern kernels, we will printk a warning message if not). However, on an embedded system, this may not be the case. And so with this new interface, we can provide the functionality of blocking until the urandom pool has been initialized. Any userspace program which uses this new functionality must take care to assure that if it is used during the boot process, that it will not cause the init scripts or other portions of the system startup to hang indefinitely. SYNOPSIS #include <linux/random.h> int getrandom(void *buf, size_t buflen, unsigned int flags); DESCRIPTION The system call getrandom() fills the buffer pointed to by buf with up to buflen random bytes which can be used to seed user space random number generators (i.e., DRBG's) or for other cryptographic uses. It should not be used for Monte Carlo simulations or other programs/algorithms which are doing probabilistic sampling. If the GRND_RANDOM flags bit is set, then draw from the /dev/random pool instead of the /dev/urandom pool. The /dev/random pool is limited based on the entropy that can be obtained from environmental noise, so if there is insufficient entropy, the requested number of bytes may not be returned. If there is no entropy available at all, getrandom(2) will either block, or return an error with errno set to EAGAIN if the GRND_NONBLOCK bit is set in flags. If the GRND_RANDOM bit is not set, then the /dev/urandom pool will be used. Unlike using read(2) to fetch data from /dev/urandom, if the urandom pool has not been sufficiently initialized, getrandom(2) will block (or return -1 with the errno set to EAGAIN if the GRND_NONBLOCK bit is set in flags). The getentropy(2) system call in OpenBSD can be emulated using the following function: int getentropy(void *buf, size_t buflen) { int ret; if (buflen > 256) goto failure; ret = getrandom(buf, buflen, 0); if (ret < 0) return ret; if (ret == buflen) return 0; failure: errno = EIO; return -1; } RETURN VALUE On success, the number of bytes that was filled in the buf is returned. This may not be all the bytes requested by the caller via buflen if insufficient entropy was present in the /dev/random pool, or if the system call was interrupted by a signal. On error, -1 is returned, and errno is set appropriately. ERRORS EINVAL An invalid flag was passed to getrandom(2) EFAULT buf is outside the accessible address space. EAGAIN The requested entropy was not available, and getentropy(2) would have blocked if the GRND_NONBLOCK flag was not set. EINTR While blocked waiting for entropy, the call was interrupted by a signal handler; see the description of how interrupted read(2) calls on "slow" devices are handled with and without the SA_RESTART flag in the signal(7) man page. NOTES For small requests (buflen <= 256) getrandom(2) will not return EINTR when reading from the urandom pool once the entropy pool has been initialized, and it will return all of the bytes that have been requested. This is the recommended way to use getrandom(2), and is designed for compatibility with OpenBSD's getentropy() system call. However, if you are using GRND_RANDOM, then getrandom(2) may block until the entropy accounting determines that sufficient environmental noise has been gathered such that getrandom(2) will be operating as a NRBG instead of a DRBG for those people who are working in the NIST SP 800-90 regime. Since it may block for a long time, these guarantees do *not* apply. The user may want to interrupt a hanging process using a signal, so blocking until all of the requested bytes are returned would be unfriendly. For this reason, the user of getrandom(2) MUST always check the return value, in case it returns some error, or if fewer bytes than requested was returned. In the case of !GRND_RANDOM and small request, the latter should never happen, but the careful userspace code (and all crypto code should be careful) should check for this anyway! Finally, unless you are doing long-term key generation (and perhaps not even then), you probably shouldn't be using GRND_RANDOM. The cryptographic algorithms used for /dev/urandom are quite conservative, and so should be sufficient for all purposes. The disadvantage of GRND_RANDOM is that it can block, and the increased complexity required to deal with partially fulfilled getrandom(2) requests. Signed-off-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Zach Brown <zab@zabbo.net>
2014-07-17 16:13:05 +08:00
#include <linux/syscalls.h>
#include <linux/completion.h>
#include <linux/uuid.h>
#include <crypto/chacha.h>
random: use BLAKE2s instead of SHA1 in extraction This commit addresses one of the lower hanging fruits of the RNG: its usage of SHA1. BLAKE2s is generally faster, and certainly more secure, than SHA1, which has [1] been [2] really [3] very [4] broken [5]. Additionally, the current construction in the RNG doesn't use the full SHA1 function, as specified, and allows overwriting the IV with RDRAND output in an undocumented way, even in the case when RDRAND isn't set to "trusted", which means potential malicious IV choices. And its short length means that keeping only half of it secret when feeding back into the mixer gives us only 2^80 bits of forward secrecy. In other words, not only is the choice of hash function dated, but the use of it isn't really great either. This commit aims to fix both of these issues while also keeping the general structure and semantics as close to the original as possible. Specifically: a) Rather than overwriting the hash IV with RDRAND, we put it into BLAKE2's documented "salt" and "personal" fields, which were specifically created for this type of usage. b) Since this function feeds the full hash result back into the entropy collector, we only return from it half the length of the hash, just as it was done before. This increases the construction's forward secrecy from 2^80 to a much more comfortable 2^128. c) Rather than using the raw "sha1_transform" function alone, we instead use the full proper BLAKE2s function, with finalization. This also has the advantage of supplying 16 bytes at a time rather than SHA1's 10 bytes, which, in addition to having a faster compression function to begin with, means faster extraction in general. On an Intel i7-11850H, this commit makes initial seeding around 131% faster. BLAKE2s itself has the nice property of internally being based on the ChaCha permutation, which the RNG is already using for expansion, so there shouldn't be any issue with newness, funkiness, or surprising CPU behavior, since it's based on something already in use. [1] https://eprint.iacr.org/2005/010.pdf [2] https://www.iacr.org/archive/crypto2005/36210017/36210017.pdf [3] https://eprint.iacr.org/2015/967.pdf [4] https://shattered.io/static/shattered.pdf [5] https://www.usenix.org/system/files/sec20-leurent.pdf Reviewed-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2021-12-21 23:31:27 +08:00
#include <crypto/blake2s.h>
#include <asm/processor.h>
#include <linux/uaccess.h>
#include <asm/irq.h>
#include <asm/irq_regs.h>
#include <asm/io.h>
random: use linear min-entropy accumulation crediting 30e37ec516ae ("random: account for entropy loss due to overwrites") assumed that adding new entropy to the LFSR pool probabilistically cancelled out old entropy there, so entropy was credited asymptotically, approximating Shannon entropy of independent sources (rather than a stronger min-entropy notion) using 1/8th fractional bits and replacing a constant 2-2/√𝑒 term (~0.786938) with 3/4 (0.75) to slightly underestimate it. This wasn't superb, but it was perhaps better than nothing, so that's what was done. Which entropy specifically was being cancelled out and how much precisely each time is hard to tell, though as I showed with the attack code in my previous commit, a motivated adversary with sufficient information can actually cancel out everything. Since we're no longer using an LFSR for entropy accumulation, this probabilistic cancellation is no longer relevant. Rather, we're now using a computational hash function as the accumulator and we've switched to working in the random oracle model, from which we can now revisit the question of min-entropy accumulation, which is done in detail in <https://eprint.iacr.org/2019/198>. Consider a long input bit string that is built by concatenating various smaller independent input bit strings. Each one of these inputs has a designated min-entropy, which is what we're passing to credit_entropy_bits(h). When we pass the concatenation of these to a random oracle, it means that an adversary trying to receive back the same reply as us would need to become certain about each part of the concatenated bit string we passed in, which means becoming certain about all of those h values. That means we can estimate the accumulation by simply adding up the h values in calls to credit_entropy_bits(h); there's no probabilistic cancellation at play like there was said to be for the LFSR. Incidentally, this is also what other entropy accumulators based on computational hash functions do as well. So this commit replaces credit_entropy_bits(h) with essentially `total = min(POOL_BITS, total + h)`, done with a cmpxchg loop as before. What if we're wrong and the above is nonsense? It's not, but let's assume we don't want the actual _behavior_ of the code to change much. Currently that behavior is not extracting from the input pool until it has 128 bits of entropy in it. With the old algorithm, we'd hit that magic 128 number after roughly 256 calls to credit_entropy_bits(1). So, we can retain more or less the old behavior by waiting to extract from the input pool until it hits 256 bits of entropy using the new code. For people concerned about this change, it means that there's not that much practical behavioral change. And for folks actually trying to model the behavior rigorously, it means that we have an even higher margin against attacks. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-03 20:28:06 +08:00
enum {
random: use computational hash for entropy extraction The current 4096-bit LFSR used for entropy collection had a few desirable attributes for the context in which it was created. For example, the state was huge, which meant that /dev/random would be able to output quite a bit of accumulated entropy before blocking. It was also, in its time, quite fast at accumulating entropy byte-by-byte, which matters given the varying contexts in which mix_pool_bytes() is called. And its diffusion was relatively high, which meant that changes would ripple across several words of state rather quickly. However, it also suffers from a few security vulnerabilities. In particular, inputs learned by an attacker can be undone, but moreover, if the state of the pool leaks, its contents can be controlled and entirely zeroed out. I've demonstrated this attack with this SMT2 script, <https://xn--4db.cc/5o9xO8pb>, which Boolector/CaDiCal solves in a matter of seconds on a single core of my laptop, resulting in little proof of concept C demonstrators such as <https://xn--4db.cc/jCkvvIaH/c>. For basically all recent formal models of RNGs, these attacks represent a significant cryptographic flaw. But how does this manifest practically? If an attacker has access to the system to such a degree that he can learn the internal state of the RNG, arguably there are other lower hanging vulnerabilities -- side-channel, infoleak, or otherwise -- that might have higher priority. On the other hand, seed files are frequently used on systems that have a hard time generating much entropy on their own, and these seed files, being files, often leak or are duplicated and distributed accidentally, or are even seeded over the Internet intentionally, where their contents might be recorded or tampered with. Seen this way, an otherwise quasi-implausible vulnerability is a bit more practical than initially thought. Another aspect of the current mix_pool_bytes() function is that, while its performance was arguably competitive for the time in which it was created, it's no longer considered so. This patch improves performance significantly: on a high-end CPU, an i7-11850H, it improves performance of mix_pool_bytes() by 225%, and on a low-end CPU, a Cortex-A7, it improves performance by 103%. This commit replaces the LFSR of mix_pool_bytes() with a straight- forward cryptographic hash function, BLAKE2s, which is already in use for pool extraction. Universal hashing with a secret seed was considered too, something along the lines of <https://eprint.iacr.org/2013/338>, but the requirement for a secret seed makes for a chicken & egg problem. Instead we go with a formally proven scheme using a computational hash function, described in sections 5.1, 6.4, and B.1.8 of <https://eprint.iacr.org/2019/198>. BLAKE2s outputs 256 bits, which should give us an appropriate amount of min-entropy accumulation, and a wide enough margin of collision resistance against active attacks. mix_pool_bytes() becomes a simple call to blake2s_update(), for accumulation, while the extraction step becomes a blake2s_final() to generate a seed, with which we can then do a HKDF-like or BLAKE2X-like expansion, the first part of which we fold back as an init key for subsequent blake2s_update()s, and the rest we produce to the caller. This then is provided to our CRNG like usual. In that expansion step, we make opportunistic use of 32 bytes of RDRAND output, just as before. We also always reseed the crng with 32 bytes, unconditionally, or not at all, rather than sometimes with 16 as before, as we don't win anything by limiting beyond the 16 byte threshold. Going for a hash function as an entropy collector is a conservative, proven approach. The result of all this is a much simpler and much less bespoke construction than what's there now, which not only plugs a vulnerability but also improves performance considerably. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-01-16 21:23:10 +08:00
POOL_BITS = BLAKE2S_HASH_SIZE * 8,
random: use linear min-entropy accumulation crediting 30e37ec516ae ("random: account for entropy loss due to overwrites") assumed that adding new entropy to the LFSR pool probabilistically cancelled out old entropy there, so entropy was credited asymptotically, approximating Shannon entropy of independent sources (rather than a stronger min-entropy notion) using 1/8th fractional bits and replacing a constant 2-2/√𝑒 term (~0.786938) with 3/4 (0.75) to slightly underestimate it. This wasn't superb, but it was perhaps better than nothing, so that's what was done. Which entropy specifically was being cancelled out and how much precisely each time is hard to tell, though as I showed with the attack code in my previous commit, a motivated adversary with sufficient information can actually cancel out everything. Since we're no longer using an LFSR for entropy accumulation, this probabilistic cancellation is no longer relevant. Rather, we're now using a computational hash function as the accumulator and we've switched to working in the random oracle model, from which we can now revisit the question of min-entropy accumulation, which is done in detail in <https://eprint.iacr.org/2019/198>. Consider a long input bit string that is built by concatenating various smaller independent input bit strings. Each one of these inputs has a designated min-entropy, which is what we're passing to credit_entropy_bits(h). When we pass the concatenation of these to a random oracle, it means that an adversary trying to receive back the same reply as us would need to become certain about each part of the concatenated bit string we passed in, which means becoming certain about all of those h values. That means we can estimate the accumulation by simply adding up the h values in calls to credit_entropy_bits(h); there's no probabilistic cancellation at play like there was said to be for the LFSR. Incidentally, this is also what other entropy accumulators based on computational hash functions do as well. So this commit replaces credit_entropy_bits(h) with essentially `total = min(POOL_BITS, total + h)`, done with a cmpxchg loop as before. What if we're wrong and the above is nonsense? It's not, but let's assume we don't want the actual _behavior_ of the code to change much. Currently that behavior is not extracting from the input pool until it has 128 bits of entropy in it. With the old algorithm, we'd hit that magic 128 number after roughly 256 calls to credit_entropy_bits(1). So, we can retain more or less the old behavior by waiting to extract from the input pool until it hits 256 bits of entropy using the new code. For people concerned about this change, it means that there's not that much practical behavioral change. And for folks actually trying to model the behavior rigorously, it means that we have an even higher margin against attacks. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-03 20:28:06 +08:00
POOL_MIN_BITS = POOL_BITS /* No point in settling for less. */
};
/*
* Static global variables
*/
static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
2008-04-29 16:03:08 +08:00
static struct fasync_struct *fasync;
static DEFINE_SPINLOCK(random_ready_list_lock);
static LIST_HEAD(random_ready_list);
/*
* 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 void process_random_ready_list(void);
static void _get_random_bytes(void *buf, size_t nbytes);
static struct ratelimit_state unseeded_warning =
RATELIMIT_STATE_INIT("warn_unseeded_randomness", HZ, 3);
static struct ratelimit_state urandom_warning =
RATELIMIT_STATE_INIT("warn_urandom_randomness", HZ, 3);
static int ratelimit_disable __read_mostly;
module_param_named(ratelimit_disable, ratelimit_disable, int, 0644);
MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression");
/**********************************************************************
*
* OS independent entropy store. Here are the functions which handle
* storing entropy in an entropy pool.
*
**********************************************************************/
static struct {
random: use computational hash for entropy extraction The current 4096-bit LFSR used for entropy collection had a few desirable attributes for the context in which it was created. For example, the state was huge, which meant that /dev/random would be able to output quite a bit of accumulated entropy before blocking. It was also, in its time, quite fast at accumulating entropy byte-by-byte, which matters given the varying contexts in which mix_pool_bytes() is called. And its diffusion was relatively high, which meant that changes would ripple across several words of state rather quickly. However, it also suffers from a few security vulnerabilities. In particular, inputs learned by an attacker can be undone, but moreover, if the state of the pool leaks, its contents can be controlled and entirely zeroed out. I've demonstrated this attack with this SMT2 script, <https://xn--4db.cc/5o9xO8pb>, which Boolector/CaDiCal solves in a matter of seconds on a single core of my laptop, resulting in little proof of concept C demonstrators such as <https://xn--4db.cc/jCkvvIaH/c>. For basically all recent formal models of RNGs, these attacks represent a significant cryptographic flaw. But how does this manifest practically? If an attacker has access to the system to such a degree that he can learn the internal state of the RNG, arguably there are other lower hanging vulnerabilities -- side-channel, infoleak, or otherwise -- that might have higher priority. On the other hand, seed files are frequently used on systems that have a hard time generating much entropy on their own, and these seed files, being files, often leak or are duplicated and distributed accidentally, or are even seeded over the Internet intentionally, where their contents might be recorded or tampered with. Seen this way, an otherwise quasi-implausible vulnerability is a bit more practical than initially thought. Another aspect of the current mix_pool_bytes() function is that, while its performance was arguably competitive for the time in which it was created, it's no longer considered so. This patch improves performance significantly: on a high-end CPU, an i7-11850H, it improves performance of mix_pool_bytes() by 225%, and on a low-end CPU, a Cortex-A7, it improves performance by 103%. This commit replaces the LFSR of mix_pool_bytes() with a straight- forward cryptographic hash function, BLAKE2s, which is already in use for pool extraction. Universal hashing with a secret seed was considered too, something along the lines of <https://eprint.iacr.org/2013/338>, but the requirement for a secret seed makes for a chicken & egg problem. Instead we go with a formally proven scheme using a computational hash function, described in sections 5.1, 6.4, and B.1.8 of <https://eprint.iacr.org/2019/198>. BLAKE2s outputs 256 bits, which should give us an appropriate amount of min-entropy accumulation, and a wide enough margin of collision resistance against active attacks. mix_pool_bytes() becomes a simple call to blake2s_update(), for accumulation, while the extraction step becomes a blake2s_final() to generate a seed, with which we can then do a HKDF-like or BLAKE2X-like expansion, the first part of which we fold back as an init key for subsequent blake2s_update()s, and the rest we produce to the caller. This then is provided to our CRNG like usual. In that expansion step, we make opportunistic use of 32 bytes of RDRAND output, just as before. We also always reseed the crng with 32 bytes, unconditionally, or not at all, rather than sometimes with 16 as before, as we don't win anything by limiting beyond the 16 byte threshold. Going for a hash function as an entropy collector is a conservative, proven approach. The result of all this is a much simpler and much less bespoke construction than what's there now, which not only plugs a vulnerability but also improves performance considerably. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-01-16 21:23:10 +08:00
struct blake2s_state hash;
spinlock_t lock;
unsigned int entropy_count;
} input_pool = {
random: use computational hash for entropy extraction The current 4096-bit LFSR used for entropy collection had a few desirable attributes for the context in which it was created. For example, the state was huge, which meant that /dev/random would be able to output quite a bit of accumulated entropy before blocking. It was also, in its time, quite fast at accumulating entropy byte-by-byte, which matters given the varying contexts in which mix_pool_bytes() is called. And its diffusion was relatively high, which meant that changes would ripple across several words of state rather quickly. However, it also suffers from a few security vulnerabilities. In particular, inputs learned by an attacker can be undone, but moreover, if the state of the pool leaks, its contents can be controlled and entirely zeroed out. I've demonstrated this attack with this SMT2 script, <https://xn--4db.cc/5o9xO8pb>, which Boolector/CaDiCal solves in a matter of seconds on a single core of my laptop, resulting in little proof of concept C demonstrators such as <https://xn--4db.cc/jCkvvIaH/c>. For basically all recent formal models of RNGs, these attacks represent a significant cryptographic flaw. But how does this manifest practically? If an attacker has access to the system to such a degree that he can learn the internal state of the RNG, arguably there are other lower hanging vulnerabilities -- side-channel, infoleak, or otherwise -- that might have higher priority. On the other hand, seed files are frequently used on systems that have a hard time generating much entropy on their own, and these seed files, being files, often leak or are duplicated and distributed accidentally, or are even seeded over the Internet intentionally, where their contents might be recorded or tampered with. Seen this way, an otherwise quasi-implausible vulnerability is a bit more practical than initially thought. Another aspect of the current mix_pool_bytes() function is that, while its performance was arguably competitive for the time in which it was created, it's no longer considered so. This patch improves performance significantly: on a high-end CPU, an i7-11850H, it improves performance of mix_pool_bytes() by 225%, and on a low-end CPU, a Cortex-A7, it improves performance by 103%. This commit replaces the LFSR of mix_pool_bytes() with a straight- forward cryptographic hash function, BLAKE2s, which is already in use for pool extraction. Universal hashing with a secret seed was considered too, something along the lines of <https://eprint.iacr.org/2013/338>, but the requirement for a secret seed makes for a chicken & egg problem. Instead we go with a formally proven scheme using a computational hash function, described in sections 5.1, 6.4, and B.1.8 of <https://eprint.iacr.org/2019/198>. BLAKE2s outputs 256 bits, which should give us an appropriate amount of min-entropy accumulation, and a wide enough margin of collision resistance against active attacks. mix_pool_bytes() becomes a simple call to blake2s_update(), for accumulation, while the extraction step becomes a blake2s_final() to generate a seed, with which we can then do a HKDF-like or BLAKE2X-like expansion, the first part of which we fold back as an init key for subsequent blake2s_update()s, and the rest we produce to the caller. This then is provided to our CRNG like usual. In that expansion step, we make opportunistic use of 32 bytes of RDRAND output, just as before. We also always reseed the crng with 32 bytes, unconditionally, or not at all, rather than sometimes with 16 as before, as we don't win anything by limiting beyond the 16 byte threshold. Going for a hash function as an entropy collector is a conservative, proven approach. The result of all this is a much simpler and much less bespoke construction than what's there now, which not only plugs a vulnerability but also improves performance considerably. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-01-16 21:23:10 +08:00
.hash.h = { BLAKE2S_IV0 ^ (0x01010000 | BLAKE2S_HASH_SIZE),
BLAKE2S_IV1, BLAKE2S_IV2, BLAKE2S_IV3, BLAKE2S_IV4,
BLAKE2S_IV5, BLAKE2S_IV6, BLAKE2S_IV7 },
.hash.outlen = BLAKE2S_HASH_SIZE,
.lock = __SPIN_LOCK_UNLOCKED(input_pool.lock),
};
static void extract_entropy(void *buf, size_t nbytes);
static void crng_reseed(void);
/*
* This function adds bytes into the entropy "pool". It does not
* update the entropy estimate. The caller should call
* credit_entropy_bits if this is appropriate.
*/
static void _mix_pool_bytes(const void *in, size_t nbytes)
{
random: use computational hash for entropy extraction The current 4096-bit LFSR used for entropy collection had a few desirable attributes for the context in which it was created. For example, the state was huge, which meant that /dev/random would be able to output quite a bit of accumulated entropy before blocking. It was also, in its time, quite fast at accumulating entropy byte-by-byte, which matters given the varying contexts in which mix_pool_bytes() is called. And its diffusion was relatively high, which meant that changes would ripple across several words of state rather quickly. However, it also suffers from a few security vulnerabilities. In particular, inputs learned by an attacker can be undone, but moreover, if the state of the pool leaks, its contents can be controlled and entirely zeroed out. I've demonstrated this attack with this SMT2 script, <https://xn--4db.cc/5o9xO8pb>, which Boolector/CaDiCal solves in a matter of seconds on a single core of my laptop, resulting in little proof of concept C demonstrators such as <https://xn--4db.cc/jCkvvIaH/c>. For basically all recent formal models of RNGs, these attacks represent a significant cryptographic flaw. But how does this manifest practically? If an attacker has access to the system to such a degree that he can learn the internal state of the RNG, arguably there are other lower hanging vulnerabilities -- side-channel, infoleak, or otherwise -- that might have higher priority. On the other hand, seed files are frequently used on systems that have a hard time generating much entropy on their own, and these seed files, being files, often leak or are duplicated and distributed accidentally, or are even seeded over the Internet intentionally, where their contents might be recorded or tampered with. Seen this way, an otherwise quasi-implausible vulnerability is a bit more practical than initially thought. Another aspect of the current mix_pool_bytes() function is that, while its performance was arguably competitive for the time in which it was created, it's no longer considered so. This patch improves performance significantly: on a high-end CPU, an i7-11850H, it improves performance of mix_pool_bytes() by 225%, and on a low-end CPU, a Cortex-A7, it improves performance by 103%. This commit replaces the LFSR of mix_pool_bytes() with a straight- forward cryptographic hash function, BLAKE2s, which is already in use for pool extraction. Universal hashing with a secret seed was considered too, something along the lines of <https://eprint.iacr.org/2013/338>, but the requirement for a secret seed makes for a chicken & egg problem. Instead we go with a formally proven scheme using a computational hash function, described in sections 5.1, 6.4, and B.1.8 of <https://eprint.iacr.org/2019/198>. BLAKE2s outputs 256 bits, which should give us an appropriate amount of min-entropy accumulation, and a wide enough margin of collision resistance against active attacks. mix_pool_bytes() becomes a simple call to blake2s_update(), for accumulation, while the extraction step becomes a blake2s_final() to generate a seed, with which we can then do a HKDF-like or BLAKE2X-like expansion, the first part of which we fold back as an init key for subsequent blake2s_update()s, and the rest we produce to the caller. This then is provided to our CRNG like usual. In that expansion step, we make opportunistic use of 32 bytes of RDRAND output, just as before. We also always reseed the crng with 32 bytes, unconditionally, or not at all, rather than sometimes with 16 as before, as we don't win anything by limiting beyond the 16 byte threshold. Going for a hash function as an entropy collector is a conservative, proven approach. The result of all this is a much simpler and much less bespoke construction than what's there now, which not only plugs a vulnerability but also improves performance considerably. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-01-16 21:23:10 +08:00
blake2s_update(&input_pool.hash, in, nbytes);
}
static void mix_pool_bytes(const void *in, size_t nbytes)
{
unsigned long flags;
spin_lock_irqsave(&input_pool.lock, flags);
_mix_pool_bytes(in, nbytes);
spin_unlock_irqrestore(&input_pool.lock, flags);
}
struct fast_pool {
u32 pool[4];
unsigned long last;
u16 reg_idx;
u8 count;
};
/*
* This is a fast mixing routine used by the interrupt randomness
* collector. It's hardcoded for an 128 bit pool and assumes that any
* locks that might be needed are taken by the caller.
*/
static void fast_mix(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);
}
static void credit_entropy_bits(size_t nbits)
{
unsigned int entropy_count, orig, add;
if (!nbits)
return;
add = min_t(size_t, nbits, POOL_BITS);
random: use linear min-entropy accumulation crediting 30e37ec516ae ("random: account for entropy loss due to overwrites") assumed that adding new entropy to the LFSR pool probabilistically cancelled out old entropy there, so entropy was credited asymptotically, approximating Shannon entropy of independent sources (rather than a stronger min-entropy notion) using 1/8th fractional bits and replacing a constant 2-2/√𝑒 term (~0.786938) with 3/4 (0.75) to slightly underestimate it. This wasn't superb, but it was perhaps better than nothing, so that's what was done. Which entropy specifically was being cancelled out and how much precisely each time is hard to tell, though as I showed with the attack code in my previous commit, a motivated adversary with sufficient information can actually cancel out everything. Since we're no longer using an LFSR for entropy accumulation, this probabilistic cancellation is no longer relevant. Rather, we're now using a computational hash function as the accumulator and we've switched to working in the random oracle model, from which we can now revisit the question of min-entropy accumulation, which is done in detail in <https://eprint.iacr.org/2019/198>. Consider a long input bit string that is built by concatenating various smaller independent input bit strings. Each one of these inputs has a designated min-entropy, which is what we're passing to credit_entropy_bits(h). When we pass the concatenation of these to a random oracle, it means that an adversary trying to receive back the same reply as us would need to become certain about each part of the concatenated bit string we passed in, which means becoming certain about all of those h values. That means we can estimate the accumulation by simply adding up the h values in calls to credit_entropy_bits(h); there's no probabilistic cancellation at play like there was said to be for the LFSR. Incidentally, this is also what other entropy accumulators based on computational hash functions do as well. So this commit replaces credit_entropy_bits(h) with essentially `total = min(POOL_BITS, total + h)`, done with a cmpxchg loop as before. What if we're wrong and the above is nonsense? It's not, but let's assume we don't want the actual _behavior_ of the code to change much. Currently that behavior is not extracting from the input pool until it has 128 bits of entropy in it. With the old algorithm, we'd hit that magic 128 number after roughly 256 calls to credit_entropy_bits(1). So, we can retain more or less the old behavior by waiting to extract from the input pool until it hits 256 bits of entropy using the new code. For people concerned about this change, it means that there's not that much practical behavioral change. And for folks actually trying to model the behavior rigorously, it means that we have an even higher margin against attacks. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-03 20:28:06 +08:00
do {
orig = READ_ONCE(input_pool.entropy_count);
entropy_count = min_t(unsigned int, POOL_BITS, orig + add);
random: use linear min-entropy accumulation crediting 30e37ec516ae ("random: account for entropy loss due to overwrites") assumed that adding new entropy to the LFSR pool probabilistically cancelled out old entropy there, so entropy was credited asymptotically, approximating Shannon entropy of independent sources (rather than a stronger min-entropy notion) using 1/8th fractional bits and replacing a constant 2-2/√𝑒 term (~0.786938) with 3/4 (0.75) to slightly underestimate it. This wasn't superb, but it was perhaps better than nothing, so that's what was done. Which entropy specifically was being cancelled out and how much precisely each time is hard to tell, though as I showed with the attack code in my previous commit, a motivated adversary with sufficient information can actually cancel out everything. Since we're no longer using an LFSR for entropy accumulation, this probabilistic cancellation is no longer relevant. Rather, we're now using a computational hash function as the accumulator and we've switched to working in the random oracle model, from which we can now revisit the question of min-entropy accumulation, which is done in detail in <https://eprint.iacr.org/2019/198>. Consider a long input bit string that is built by concatenating various smaller independent input bit strings. Each one of these inputs has a designated min-entropy, which is what we're passing to credit_entropy_bits(h). When we pass the concatenation of these to a random oracle, it means that an adversary trying to receive back the same reply as us would need to become certain about each part of the concatenated bit string we passed in, which means becoming certain about all of those h values. That means we can estimate the accumulation by simply adding up the h values in calls to credit_entropy_bits(h); there's no probabilistic cancellation at play like there was said to be for the LFSR. Incidentally, this is also what other entropy accumulators based on computational hash functions do as well. So this commit replaces credit_entropy_bits(h) with essentially `total = min(POOL_BITS, total + h)`, done with a cmpxchg loop as before. What if we're wrong and the above is nonsense? It's not, but let's assume we don't want the actual _behavior_ of the code to change much. Currently that behavior is not extracting from the input pool until it has 128 bits of entropy in it. With the old algorithm, we'd hit that magic 128 number after roughly 256 calls to credit_entropy_bits(1). So, we can retain more or less the old behavior by waiting to extract from the input pool until it hits 256 bits of entropy using the new code. For people concerned about this change, it means that there's not that much practical behavioral change. And for folks actually trying to model the behavior rigorously, it means that we have an even higher margin against attacks. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-03 20:28:06 +08:00
} while (cmpxchg(&input_pool.entropy_count, orig, entropy_count) != orig);
random: use linear min-entropy accumulation crediting 30e37ec516ae ("random: account for entropy loss due to overwrites") assumed that adding new entropy to the LFSR pool probabilistically cancelled out old entropy there, so entropy was credited asymptotically, approximating Shannon entropy of independent sources (rather than a stronger min-entropy notion) using 1/8th fractional bits and replacing a constant 2-2/√𝑒 term (~0.786938) with 3/4 (0.75) to slightly underestimate it. This wasn't superb, but it was perhaps better than nothing, so that's what was done. Which entropy specifically was being cancelled out and how much precisely each time is hard to tell, though as I showed with the attack code in my previous commit, a motivated adversary with sufficient information can actually cancel out everything. Since we're no longer using an LFSR for entropy accumulation, this probabilistic cancellation is no longer relevant. Rather, we're now using a computational hash function as the accumulator and we've switched to working in the random oracle model, from which we can now revisit the question of min-entropy accumulation, which is done in detail in <https://eprint.iacr.org/2019/198>. Consider a long input bit string that is built by concatenating various smaller independent input bit strings. Each one of these inputs has a designated min-entropy, which is what we're passing to credit_entropy_bits(h). When we pass the concatenation of these to a random oracle, it means that an adversary trying to receive back the same reply as us would need to become certain about each part of the concatenated bit string we passed in, which means becoming certain about all of those h values. That means we can estimate the accumulation by simply adding up the h values in calls to credit_entropy_bits(h); there's no probabilistic cancellation at play like there was said to be for the LFSR. Incidentally, this is also what other entropy accumulators based on computational hash functions do as well. So this commit replaces credit_entropy_bits(h) with essentially `total = min(POOL_BITS, total + h)`, done with a cmpxchg loop as before. What if we're wrong and the above is nonsense? It's not, but let's assume we don't want the actual _behavior_ of the code to change much. Currently that behavior is not extracting from the input pool until it has 128 bits of entropy in it. With the old algorithm, we'd hit that magic 128 number after roughly 256 calls to credit_entropy_bits(1). So, we can retain more or less the old behavior by waiting to extract from the input pool until it hits 256 bits of entropy using the new code. For people concerned about this change, it means that there's not that much practical behavioral change. And for folks actually trying to model the behavior rigorously, it means that we have an even higher margin against attacks. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-03 20:28:06 +08:00
if (crng_init < 2 && entropy_count >= POOL_MIN_BITS)
crng_reseed();
}
/*********************************************************************
*
* CRNG using CHACHA20
*
*********************************************************************/
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
enum {
CRNG_RESEED_INTERVAL = 300 * HZ,
CRNG_INIT_CNT_THRESH = 2 * CHACHA_KEY_SIZE
};
static struct {
u8 key[CHACHA_KEY_SIZE] __aligned(__alignof__(long));
unsigned long birth;
unsigned long generation;
spinlock_t lock;
} base_crng = {
.lock = __SPIN_LOCK_UNLOCKED(base_crng.lock)
};
struct crng {
u8 key[CHACHA_KEY_SIZE];
unsigned long generation;
local_lock_t lock;
};
static DEFINE_PER_CPU(struct crng, crngs) = {
.generation = ULONG_MAX,
.lock = INIT_LOCAL_LOCK(crngs.lock),
};
static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait);
/*
* crng_fast_load() can be called by code in the interrupt service
* path. So we can't afford to dilly-dally. Returns the number of
* bytes processed from cp.
*/
static size_t crng_fast_load(const void *cp, size_t len)
{
unsigned long flags;
const u8 *src = (const u8 *)cp;
size_t ret = 0;
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
if (!spin_trylock_irqsave(&base_crng.lock, flags))
return 0;
if (crng_init != 0) {
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
spin_unlock_irqrestore(&base_crng.lock, flags);
return 0;
}
while (len > 0 && crng_init_cnt < CRNG_INIT_CNT_THRESH) {
base_crng.key[crng_init_cnt % sizeof(base_crng.key)] ^= *src;
src++; crng_init_cnt++; len--; ret++;
}
if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) {
++base_crng.generation;
crng_init = 1;
}
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
spin_unlock_irqrestore(&base_crng.lock, flags);
if (crng_init == 1)
pr_notice("fast init done\n");
return ret;
}
/*
* crng_slow_load() is called by add_device_randomness, which has two
* attributes. (1) We can't trust the buffer passed to it is
* guaranteed to be unpredictable (so it might not have any entropy at
* all), and (2) it doesn't have the performance constraints of
* crng_fast_load().
*
* So, we simply hash the contents in with the current key. Finally,
* we do *not* advance crng_init_cnt since buffer we may get may be
* something like a fixed DMI table (for example), which might very
* well be unique to the machine, but is otherwise unvarying.
*/
static void crng_slow_load(const void *cp, size_t len)
{
unsigned long flags;
struct blake2s_state hash;
blake2s_init(&hash, sizeof(base_crng.key));
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
if (!spin_trylock_irqsave(&base_crng.lock, flags))
return;
if (crng_init != 0) {
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
spin_unlock_irqrestore(&base_crng.lock, flags);
return;
}
blake2s_update(&hash, base_crng.key, sizeof(base_crng.key));
blake2s_update(&hash, cp, len);
blake2s_final(&hash, base_crng.key);
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
spin_unlock_irqrestore(&base_crng.lock, flags);
}
static void crng_reseed(void)
{
unsigned long flags;
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
int entropy_count;
unsigned long next_gen;
u8 key[CHACHA_KEY_SIZE];
bool finalize_init = false;
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
/*
* First we make sure we have POOL_MIN_BITS of entropy in the pool,
* and then we drain all of it. Only then can we extract a new key.
*/
do {
entropy_count = READ_ONCE(input_pool.entropy_count);
if (entropy_count < POOL_MIN_BITS)
return;
} while (cmpxchg(&input_pool.entropy_count, entropy_count, 0) != entropy_count);
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
extract_entropy(key, sizeof(key));
wake_up_interruptible(&random_write_wait);
kill_fasync(&fasync, SIGIO, POLL_OUT);
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
/*
* We copy the new key into the base_crng, overwriting the old one,
* and update the generation counter. We avoid hitting ULONG_MAX,
* because the per-cpu crngs are initialized to ULONG_MAX, so this
* forces new CPUs that come online to always initialize.
*/
spin_lock_irqsave(&base_crng.lock, flags);
memcpy(base_crng.key, key, sizeof(base_crng.key));
next_gen = base_crng.generation + 1;
if (next_gen == ULONG_MAX)
++next_gen;
WRITE_ONCE(base_crng.generation, next_gen);
WRITE_ONCE(base_crng.birth, jiffies);
if (crng_init < 2) {
crng_init = 2;
finalize_init = true;
}
spin_unlock_irqrestore(&base_crng.lock, flags);
memzero_explicit(key, sizeof(key));
if (finalize_init) {
process_random_ready_list();
wake_up_interruptible(&crng_init_wait);
kill_fasync(&fasync, SIGIO, POLL_IN);
pr_notice("crng init done\n");
if (unseeded_warning.missed) {
pr_notice("%d get_random_xx warning(s) missed due to ratelimiting\n",
unseeded_warning.missed);
unseeded_warning.missed = 0;
}
if (urandom_warning.missed) {
pr_notice("%d urandom warning(s) missed due to ratelimiting\n",
urandom_warning.missed);
urandom_warning.missed = 0;
}
}
}
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
/*
* The general form here is based on a "fast key erasure RNG" from
* <https://blog.cr.yp.to/20170723-random.html>. It generates a ChaCha
* block using the provided key, and then immediately overwites that
* key with half the block. It returns the resultant ChaCha state to the
* user, along with the second half of the block containing 32 bytes of
* random data that may be used; random_data_len may not be greater than
* 32.
*/
static void crng_fast_key_erasure(u8 key[CHACHA_KEY_SIZE],
u32 chacha_state[CHACHA_STATE_WORDS],
u8 *random_data, size_t random_data_len)
{
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
u8 first_block[CHACHA_BLOCK_SIZE];
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
BUG_ON(random_data_len > 32);
chacha_init_consts(chacha_state);
memcpy(&chacha_state[4], key, CHACHA_KEY_SIZE);
memset(&chacha_state[12], 0, sizeof(u32) * 4);
chacha20_block(chacha_state, first_block);
memcpy(key, first_block, CHACHA_KEY_SIZE);
memcpy(random_data, first_block + CHACHA_KEY_SIZE, random_data_len);
memzero_explicit(first_block, sizeof(first_block));
}
/*
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
* 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.
*/
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
static void crng_make_state(u32 chacha_state[CHACHA_STATE_WORDS],
u8 *random_data, size_t random_data_len)
{
unsigned long flags;
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
struct crng *crng;
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
BUG_ON(random_data_len > 32);
/*
* For the fast path, we check whether we're ready, unlocked first, and
* then re-check once locked later. In the case where we're really not
* ready, we do fast key erasure with the base_crng directly, because
* this is what crng_{fast,slow}_load mutate during early init.
*/
if (unlikely(!crng_ready())) {
bool ready;
spin_lock_irqsave(&base_crng.lock, flags);
ready = crng_ready();
if (!ready)
crng_fast_key_erasure(base_crng.key, chacha_state,
random_data, random_data_len);
spin_unlock_irqrestore(&base_crng.lock, flags);
if (!ready)
return;
}
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
/*
* If the base_crng is more than 5 minutes old, we reseed, which
* in turn bumps the generation counter that we check below.
*/
if (unlikely(time_after(jiffies, READ_ONCE(base_crng.birth) + CRNG_RESEED_INTERVAL)))
crng_reseed();
local_lock_irqsave(&crngs.lock, flags);
crng = raw_cpu_ptr(&crngs);
/*
* If our per-cpu crng is older than the base_crng, then it means
* somebody reseeded the base_crng. In that case, we do fast key
* erasure on the base_crng, and use its output as the new key
* for our per-cpu crng. This brings us up to date with base_crng.
*/
if (unlikely(crng->generation != READ_ONCE(base_crng.generation))) {
spin_lock(&base_crng.lock);
crng_fast_key_erasure(base_crng.key, chacha_state,
crng->key, sizeof(crng->key));
crng->generation = base_crng.generation;
spin_unlock(&base_crng.lock);
}
/*
* Finally, when we've made it this far, our per-cpu crng has an up
* to date key, and we can do fast key erasure with it to produce
* some random data and a ChaCha state for the caller. All other
* branches of this function are "unlikely", so most of the time we
* should wind up here immediately.
*/
crng_fast_key_erasure(crng->key, chacha_state, random_data, random_data_len);
local_unlock_irqrestore(&crngs.lock, flags);
}
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes)
{
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
bool large_request = nbytes > 256;
ssize_t ret = 0;
size_t len;
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
u32 chacha_state[CHACHA_STATE_WORDS];
u8 output[CHACHA_BLOCK_SIZE];
if (!nbytes)
return 0;
len = min_t(size_t, 32, nbytes);
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
crng_make_state(chacha_state, output, len);
if (copy_to_user(buf, output, len))
return -EFAULT;
nbytes -= len;
buf += len;
ret += len;
while (nbytes) {
if (large_request && need_resched()) {
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
if (signal_pending(current))
break;
schedule();
}
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
chacha20_block(chacha_state, output);
if (unlikely(chacha_state[12] == 0))
++chacha_state[13];
len = min_t(size_t, nbytes, CHACHA_BLOCK_SIZE);
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
if (copy_to_user(buf, output, len)) {
ret = -EFAULT;
break;
}
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
nbytes -= len;
buf += len;
ret += len;
}
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
memzero_explicit(chacha_state, sizeof(chacha_state));
memzero_explicit(output, sizeof(output));
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, size_t size)
{
unsigned long time = random_get_entropy() ^ jiffies;
unsigned long flags;
if (!crng_ready() && size)
crng_slow_load(buf, size);
spin_lock_irqsave(&input_pool.lock, flags);
_mix_pool_bytes(buf, size);
_mix_pool_bytes(&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 int num)
{
struct {
long jiffies;
unsigned int cycles;
unsigned int num;
} sample;
long delta, delta2, delta3;
sample.jiffies = jiffies;
sample.cycles = random_get_entropy();
sample.num = num;
mix_pool_bytes(&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.
*/
random: fix data races at timer_rand_state Fields in "struct timer_rand_state" could be accessed concurrently. Lockless plain reads and writes result in data races. Fix them by adding pairs of READ|WRITE_ONCE(). The data races were reported by KCSAN, BUG: KCSAN: data-race in add_timer_randomness / add_timer_randomness write to 0xffff9f320a0a01d0 of 8 bytes by interrupt on cpu 22: add_timer_randomness+0x100/0x190 add_timer_randomness at drivers/char/random.c:1152 add_disk_randomness+0x85/0x280 scsi_end_request+0x43a/0x4a0 scsi_io_completion+0xb7/0x7e0 scsi_finish_command+0x1ed/0x2a0 scsi_softirq_done+0x1c9/0x1d0 blk_done_softirq+0x181/0x1d0 __do_softirq+0xd9/0x57c irq_exit+0xa2/0xc0 do_IRQ+0x8b/0x190 ret_from_intr+0x0/0x42 cpuidle_enter_state+0x15e/0x980 cpuidle_enter+0x69/0xc0 call_cpuidle+0x23/0x40 do_idle+0x248/0x280 cpu_startup_entry+0x1d/0x1f start_secondary+0x1b2/0x230 secondary_startup_64+0xb6/0xc0 no locks held by swapper/22/0. irq event stamp: 32871382 _raw_spin_unlock_irqrestore+0x53/0x60 _raw_spin_lock_irqsave+0x21/0x60 _local_bh_enable+0x21/0x30 irq_exit+0xa2/0xc0 read to 0xffff9f320a0a01d0 of 8 bytes by interrupt on cpu 2: add_timer_randomness+0xe8/0x190 add_disk_randomness+0x85/0x280 scsi_end_request+0x43a/0x4a0 scsi_io_completion+0xb7/0x7e0 scsi_finish_command+0x1ed/0x2a0 scsi_softirq_done+0x1c9/0x1d0 blk_done_softirq+0x181/0x1d0 __do_softirq+0xd9/0x57c irq_exit+0xa2/0xc0 do_IRQ+0x8b/0x190 ret_from_intr+0x0/0x42 cpuidle_enter_state+0x15e/0x980 cpuidle_enter+0x69/0xc0 call_cpuidle+0x23/0x40 do_idle+0x248/0x280 cpu_startup_entry+0x1d/0x1f start_secondary+0x1b2/0x230 secondary_startup_64+0xb6/0xc0 no locks held by swapper/2/0. irq event stamp: 37846304 _raw_spin_unlock_irqrestore+0x53/0x60 _raw_spin_lock_irqsave+0x21/0x60 _local_bh_enable+0x21/0x30 irq_exit+0xa2/0xc0 Reported by Kernel Concurrency Sanitizer on: Hardware name: HP ProLiant BL660c Gen9, BIOS I38 10/17/2018 Link: https://lore.kernel.org/r/1582648024-13111-1-git-send-email-cai@lca.pw Signed-off-by: Qian Cai <cai@lca.pw> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2020-02-26 00:27:04 +08:00
delta = sample.jiffies - READ_ONCE(state->last_time);
WRITE_ONCE(state->last_time, sample.jiffies);
random: fix data races at timer_rand_state Fields in "struct timer_rand_state" could be accessed concurrently. Lockless plain reads and writes result in data races. Fix them by adding pairs of READ|WRITE_ONCE(). The data races were reported by KCSAN, BUG: KCSAN: data-race in add_timer_randomness / add_timer_randomness write to 0xffff9f320a0a01d0 of 8 bytes by interrupt on cpu 22: add_timer_randomness+0x100/0x190 add_timer_randomness at drivers/char/random.c:1152 add_disk_randomness+0x85/0x280 scsi_end_request+0x43a/0x4a0 scsi_io_completion+0xb7/0x7e0 scsi_finish_command+0x1ed/0x2a0 scsi_softirq_done+0x1c9/0x1d0 blk_done_softirq+0x181/0x1d0 __do_softirq+0xd9/0x57c irq_exit+0xa2/0xc0 do_IRQ+0x8b/0x190 ret_from_intr+0x0/0x42 cpuidle_enter_state+0x15e/0x980 cpuidle_enter+0x69/0xc0 call_cpuidle+0x23/0x40 do_idle+0x248/0x280 cpu_startup_entry+0x1d/0x1f start_secondary+0x1b2/0x230 secondary_startup_64+0xb6/0xc0 no locks held by swapper/22/0. irq event stamp: 32871382 _raw_spin_unlock_irqrestore+0x53/0x60 _raw_spin_lock_irqsave+0x21/0x60 _local_bh_enable+0x21/0x30 irq_exit+0xa2/0xc0 read to 0xffff9f320a0a01d0 of 8 bytes by interrupt on cpu 2: add_timer_randomness+0xe8/0x190 add_disk_randomness+0x85/0x280 scsi_end_request+0x43a/0x4a0 scsi_io_completion+0xb7/0x7e0 scsi_finish_command+0x1ed/0x2a0 scsi_softirq_done+0x1c9/0x1d0 blk_done_softirq+0x181/0x1d0 __do_softirq+0xd9/0x57c irq_exit+0xa2/0xc0 do_IRQ+0x8b/0x190 ret_from_intr+0x0/0x42 cpuidle_enter_state+0x15e/0x980 cpuidle_enter+0x69/0xc0 call_cpuidle+0x23/0x40 do_idle+0x248/0x280 cpu_startup_entry+0x1d/0x1f start_secondary+0x1b2/0x230 secondary_startup_64+0xb6/0xc0 no locks held by swapper/2/0. irq event stamp: 37846304 _raw_spin_unlock_irqrestore+0x53/0x60 _raw_spin_lock_irqsave+0x21/0x60 _local_bh_enable+0x21/0x30 irq_exit+0xa2/0xc0 Reported by Kernel Concurrency Sanitizer on: Hardware name: HP ProLiant BL660c Gen9, BIOS I38 10/17/2018 Link: https://lore.kernel.org/r/1582648024-13111-1-git-send-email-cai@lca.pw Signed-off-by: Qian Cai <cai@lca.pw> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2020-02-26 00:27:04 +08:00
delta2 = delta - READ_ONCE(state->last_delta);
WRITE_ONCE(state->last_delta, delta);
random: fix data races at timer_rand_state Fields in "struct timer_rand_state" could be accessed concurrently. Lockless plain reads and writes result in data races. Fix them by adding pairs of READ|WRITE_ONCE(). The data races were reported by KCSAN, BUG: KCSAN: data-race in add_timer_randomness / add_timer_randomness write to 0xffff9f320a0a01d0 of 8 bytes by interrupt on cpu 22: add_timer_randomness+0x100/0x190 add_timer_randomness at drivers/char/random.c:1152 add_disk_randomness+0x85/0x280 scsi_end_request+0x43a/0x4a0 scsi_io_completion+0xb7/0x7e0 scsi_finish_command+0x1ed/0x2a0 scsi_softirq_done+0x1c9/0x1d0 blk_done_softirq+0x181/0x1d0 __do_softirq+0xd9/0x57c irq_exit+0xa2/0xc0 do_IRQ+0x8b/0x190 ret_from_intr+0x0/0x42 cpuidle_enter_state+0x15e/0x980 cpuidle_enter+0x69/0xc0 call_cpuidle+0x23/0x40 do_idle+0x248/0x280 cpu_startup_entry+0x1d/0x1f start_secondary+0x1b2/0x230 secondary_startup_64+0xb6/0xc0 no locks held by swapper/22/0. irq event stamp: 32871382 _raw_spin_unlock_irqrestore+0x53/0x60 _raw_spin_lock_irqsave+0x21/0x60 _local_bh_enable+0x21/0x30 irq_exit+0xa2/0xc0 read to 0xffff9f320a0a01d0 of 8 bytes by interrupt on cpu 2: add_timer_randomness+0xe8/0x190 add_disk_randomness+0x85/0x280 scsi_end_request+0x43a/0x4a0 scsi_io_completion+0xb7/0x7e0 scsi_finish_command+0x1ed/0x2a0 scsi_softirq_done+0x1c9/0x1d0 blk_done_softirq+0x181/0x1d0 __do_softirq+0xd9/0x57c irq_exit+0xa2/0xc0 do_IRQ+0x8b/0x190 ret_from_intr+0x0/0x42 cpuidle_enter_state+0x15e/0x980 cpuidle_enter+0x69/0xc0 call_cpuidle+0x23/0x40 do_idle+0x248/0x280 cpu_startup_entry+0x1d/0x1f start_secondary+0x1b2/0x230 secondary_startup_64+0xb6/0xc0 no locks held by swapper/2/0. irq event stamp: 37846304 _raw_spin_unlock_irqrestore+0x53/0x60 _raw_spin_lock_irqsave+0x21/0x60 _local_bh_enable+0x21/0x30 irq_exit+0xa2/0xc0 Reported by Kernel Concurrency Sanitizer on: Hardware name: HP ProLiant BL660c Gen9, BIOS I38 10/17/2018 Link: https://lore.kernel.org/r/1582648024-13111-1-git-send-email-cai@lca.pw Signed-off-by: Qian Cai <cai@lca.pw> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2020-02-26 00:27:04 +08:00
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 12 bits.
*/
credit_entropy_bits(min_t(unsigned int, fls(delta >> 1), 11));
}
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);
}
EXPORT_SYMBOL_GPL(add_input_randomness);
static DEFINE_PER_CPU(struct fast_pool, irq_randomness);
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)
{
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;
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);
if (unlikely(crng_init == 0)) {
if (fast_pool->count >= 64 &&
crng_fast_load(fast_pool->pool, sizeof(fast_pool->pool)) > 0) {
fast_pool->count = 0;
fast_pool->last = now;
if (spin_trylock(&input_pool.lock)) {
_mix_pool_bytes(&fast_pool->pool, sizeof(fast_pool->pool));
spin_unlock(&input_pool.lock);
}
}
return;
}
if ((fast_pool->count < 64) && !time_after(now, fast_pool->last + HZ))
return;
if (!spin_trylock(&input_pool.lock))
return;
fast_pool->last = now;
_mix_pool_bytes(&fast_pool->pool, sizeof(fast_pool->pool));
spin_unlock(&input_pool.lock);
fast_pool->count = 0;
/* award one bit for the contents of the fast pool */
credit_entropy_bits(1);
}
EXPORT_SYMBOL_GPL(add_interrupt_randomness);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#ifdef CONFIG_BLOCK
void add_disk_randomness(struct gendisk *disk)
{
if (!disk || !disk->random)
return;
/* first major is 1, so we get >= 0x200 here */
add_timer_randomness(disk->random, 0x100 + disk_devt(disk));
}
EXPORT_SYMBOL_GPL(add_disk_randomness);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#endif
/*********************************************************************
*
* Entropy extraction routines
*
*********************************************************************/
/*
random: use computational hash for entropy extraction The current 4096-bit LFSR used for entropy collection had a few desirable attributes for the context in which it was created. For example, the state was huge, which meant that /dev/random would be able to output quite a bit of accumulated entropy before blocking. It was also, in its time, quite fast at accumulating entropy byte-by-byte, which matters given the varying contexts in which mix_pool_bytes() is called. And its diffusion was relatively high, which meant that changes would ripple across several words of state rather quickly. However, it also suffers from a few security vulnerabilities. In particular, inputs learned by an attacker can be undone, but moreover, if the state of the pool leaks, its contents can be controlled and entirely zeroed out. I've demonstrated this attack with this SMT2 script, <https://xn--4db.cc/5o9xO8pb>, which Boolector/CaDiCal solves in a matter of seconds on a single core of my laptop, resulting in little proof of concept C demonstrators such as <https://xn--4db.cc/jCkvvIaH/c>. For basically all recent formal models of RNGs, these attacks represent a significant cryptographic flaw. But how does this manifest practically? If an attacker has access to the system to such a degree that he can learn the internal state of the RNG, arguably there are other lower hanging vulnerabilities -- side-channel, infoleak, or otherwise -- that might have higher priority. On the other hand, seed files are frequently used on systems that have a hard time generating much entropy on their own, and these seed files, being files, often leak or are duplicated and distributed accidentally, or are even seeded over the Internet intentionally, where their contents might be recorded or tampered with. Seen this way, an otherwise quasi-implausible vulnerability is a bit more practical than initially thought. Another aspect of the current mix_pool_bytes() function is that, while its performance was arguably competitive for the time in which it was created, it's no longer considered so. This patch improves performance significantly: on a high-end CPU, an i7-11850H, it improves performance of mix_pool_bytes() by 225%, and on a low-end CPU, a Cortex-A7, it improves performance by 103%. This commit replaces the LFSR of mix_pool_bytes() with a straight- forward cryptographic hash function, BLAKE2s, which is already in use for pool extraction. Universal hashing with a secret seed was considered too, something along the lines of <https://eprint.iacr.org/2013/338>, but the requirement for a secret seed makes for a chicken & egg problem. Instead we go with a formally proven scheme using a computational hash function, described in sections 5.1, 6.4, and B.1.8 of <https://eprint.iacr.org/2019/198>. BLAKE2s outputs 256 bits, which should give us an appropriate amount of min-entropy accumulation, and a wide enough margin of collision resistance against active attacks. mix_pool_bytes() becomes a simple call to blake2s_update(), for accumulation, while the extraction step becomes a blake2s_final() to generate a seed, with which we can then do a HKDF-like or BLAKE2X-like expansion, the first part of which we fold back as an init key for subsequent blake2s_update()s, and the rest we produce to the caller. This then is provided to our CRNG like usual. In that expansion step, we make opportunistic use of 32 bytes of RDRAND output, just as before. We also always reseed the crng with 32 bytes, unconditionally, or not at all, rather than sometimes with 16 as before, as we don't win anything by limiting beyond the 16 byte threshold. Going for a hash function as an entropy collector is a conservative, proven approach. The result of all this is a much simpler and much less bespoke construction than what's there now, which not only plugs a vulnerability but also improves performance considerably. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-01-16 21:23:10 +08:00
* 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 nbytes)
{
unsigned long flags;
random: use computational hash for entropy extraction The current 4096-bit LFSR used for entropy collection had a few desirable attributes for the context in which it was created. For example, the state was huge, which meant that /dev/random would be able to output quite a bit of accumulated entropy before blocking. It was also, in its time, quite fast at accumulating entropy byte-by-byte, which matters given the varying contexts in which mix_pool_bytes() is called. And its diffusion was relatively high, which meant that changes would ripple across several words of state rather quickly. However, it also suffers from a few security vulnerabilities. In particular, inputs learned by an attacker can be undone, but moreover, if the state of the pool leaks, its contents can be controlled and entirely zeroed out. I've demonstrated this attack with this SMT2 script, <https://xn--4db.cc/5o9xO8pb>, which Boolector/CaDiCal solves in a matter of seconds on a single core of my laptop, resulting in little proof of concept C demonstrators such as <https://xn--4db.cc/jCkvvIaH/c>. For basically all recent formal models of RNGs, these attacks represent a significant cryptographic flaw. But how does this manifest practically? If an attacker has access to the system to such a degree that he can learn the internal state of the RNG, arguably there are other lower hanging vulnerabilities -- side-channel, infoleak, or otherwise -- that might have higher priority. On the other hand, seed files are frequently used on systems that have a hard time generating much entropy on their own, and these seed files, being files, often leak or are duplicated and distributed accidentally, or are even seeded over the Internet intentionally, where their contents might be recorded or tampered with. Seen this way, an otherwise quasi-implausible vulnerability is a bit more practical than initially thought. Another aspect of the current mix_pool_bytes() function is that, while its performance was arguably competitive for the time in which it was created, it's no longer considered so. This patch improves performance significantly: on a high-end CPU, an i7-11850H, it improves performance of mix_pool_bytes() by 225%, and on a low-end CPU, a Cortex-A7, it improves performance by 103%. This commit replaces the LFSR of mix_pool_bytes() with a straight- forward cryptographic hash function, BLAKE2s, which is already in use for pool extraction. Universal hashing with a secret seed was considered too, something along the lines of <https://eprint.iacr.org/2013/338>, but the requirement for a secret seed makes for a chicken & egg problem. Instead we go with a formally proven scheme using a computational hash function, described in sections 5.1, 6.4, and B.1.8 of <https://eprint.iacr.org/2019/198>. BLAKE2s outputs 256 bits, which should give us an appropriate amount of min-entropy accumulation, and a wide enough margin of collision resistance against active attacks. mix_pool_bytes() becomes a simple call to blake2s_update(), for accumulation, while the extraction step becomes a blake2s_final() to generate a seed, with which we can then do a HKDF-like or BLAKE2X-like expansion, the first part of which we fold back as an init key for subsequent blake2s_update()s, and the rest we produce to the caller. This then is provided to our CRNG like usual. In that expansion step, we make opportunistic use of 32 bytes of RDRAND output, just as before. We also always reseed the crng with 32 bytes, unconditionally, or not at all, rather than sometimes with 16 as before, as we don't win anything by limiting beyond the 16 byte threshold. Going for a hash function as an entropy collector is a conservative, proven approach. The result of all this is a much simpler and much less bespoke construction than what's there now, which not only plugs a vulnerability but also improves performance considerably. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-01-16 21:23:10 +08:00
u8 seed[BLAKE2S_HASH_SIZE], next_key[BLAKE2S_HASH_SIZE];
struct {
random: use RDSEED instead of RDRAND in entropy extraction When /dev/random was directly connected with entropy extraction, without any expansion stage, extract_buf() was called for every 10 bytes of data read from /dev/random. For that reason, RDRAND was used rather than RDSEED. At the same time, crng_reseed() was still only called every 5 minutes, so there RDSEED made sense. Those olden days were also a time when the entropy collector did not use a cryptographic hash function, which meant most bets were off in terms of real preimage resistance. For that reason too it didn't matter _that_ much whether RDSEED was mixed in before or after entropy extraction; both choices were sort of bad. But now we have a cryptographic hash function at work, and with that we get real preimage resistance. We also now only call extract_entropy() every 5 minutes, rather than every 10 bytes. This allows us to do two important things. First, we can switch to using RDSEED in extract_entropy(), as Dominik suggested. Second, we can ensure that RDSEED input always goes into the cryptographic hash function with other things before being used directly. This eliminates a category of attacks in which the CPU knows the current state of the crng and knows that we're going to xor RDSEED into it, and so it computes a malicious RDSEED. By going through our hash function, it would require the CPU to compute a preimage on the fly, which isn't going to happen. Cc: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Dominik Brodowski <linux@dominikbrodowski.net> Suggested-by: Dominik Brodowski <linux@dominikbrodowski.net> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-08 19:18:33 +08:00
unsigned long rdseed[32 / sizeof(long)];
random: use computational hash for entropy extraction The current 4096-bit LFSR used for entropy collection had a few desirable attributes for the context in which it was created. For example, the state was huge, which meant that /dev/random would be able to output quite a bit of accumulated entropy before blocking. It was also, in its time, quite fast at accumulating entropy byte-by-byte, which matters given the varying contexts in which mix_pool_bytes() is called. And its diffusion was relatively high, which meant that changes would ripple across several words of state rather quickly. However, it also suffers from a few security vulnerabilities. In particular, inputs learned by an attacker can be undone, but moreover, if the state of the pool leaks, its contents can be controlled and entirely zeroed out. I've demonstrated this attack with this SMT2 script, <https://xn--4db.cc/5o9xO8pb>, which Boolector/CaDiCal solves in a matter of seconds on a single core of my laptop, resulting in little proof of concept C demonstrators such as <https://xn--4db.cc/jCkvvIaH/c>. For basically all recent formal models of RNGs, these attacks represent a significant cryptographic flaw. But how does this manifest practically? If an attacker has access to the system to such a degree that he can learn the internal state of the RNG, arguably there are other lower hanging vulnerabilities -- side-channel, infoleak, or otherwise -- that might have higher priority. On the other hand, seed files are frequently used on systems that have a hard time generating much entropy on their own, and these seed files, being files, often leak or are duplicated and distributed accidentally, or are even seeded over the Internet intentionally, where their contents might be recorded or tampered with. Seen this way, an otherwise quasi-implausible vulnerability is a bit more practical than initially thought. Another aspect of the current mix_pool_bytes() function is that, while its performance was arguably competitive for the time in which it was created, it's no longer considered so. This patch improves performance significantly: on a high-end CPU, an i7-11850H, it improves performance of mix_pool_bytes() by 225%, and on a low-end CPU, a Cortex-A7, it improves performance by 103%. This commit replaces the LFSR of mix_pool_bytes() with a straight- forward cryptographic hash function, BLAKE2s, which is already in use for pool extraction. Universal hashing with a secret seed was considered too, something along the lines of <https://eprint.iacr.org/2013/338>, but the requirement for a secret seed makes for a chicken & egg problem. Instead we go with a formally proven scheme using a computational hash function, described in sections 5.1, 6.4, and B.1.8 of <https://eprint.iacr.org/2019/198>. BLAKE2s outputs 256 bits, which should give us an appropriate amount of min-entropy accumulation, and a wide enough margin of collision resistance against active attacks. mix_pool_bytes() becomes a simple call to blake2s_update(), for accumulation, while the extraction step becomes a blake2s_final() to generate a seed, with which we can then do a HKDF-like or BLAKE2X-like expansion, the first part of which we fold back as an init key for subsequent blake2s_update()s, and the rest we produce to the caller. This then is provided to our CRNG like usual. In that expansion step, we make opportunistic use of 32 bytes of RDRAND output, just as before. We also always reseed the crng with 32 bytes, unconditionally, or not at all, rather than sometimes with 16 as before, as we don't win anything by limiting beyond the 16 byte threshold. Going for a hash function as an entropy collector is a conservative, proven approach. The result of all this is a much simpler and much less bespoke construction than what's there now, which not only plugs a vulnerability but also improves performance considerably. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-01-16 21:23:10 +08:00
size_t counter;
} block;
size_t i;
random: use RDSEED instead of RDRAND in entropy extraction When /dev/random was directly connected with entropy extraction, without any expansion stage, extract_buf() was called for every 10 bytes of data read from /dev/random. For that reason, RDRAND was used rather than RDSEED. At the same time, crng_reseed() was still only called every 5 minutes, so there RDSEED made sense. Those olden days were also a time when the entropy collector did not use a cryptographic hash function, which meant most bets were off in terms of real preimage resistance. For that reason too it didn't matter _that_ much whether RDSEED was mixed in before or after entropy extraction; both choices were sort of bad. But now we have a cryptographic hash function at work, and with that we get real preimage resistance. We also now only call extract_entropy() every 5 minutes, rather than every 10 bytes. This allows us to do two important things. First, we can switch to using RDSEED in extract_entropy(), as Dominik suggested. Second, we can ensure that RDSEED input always goes into the cryptographic hash function with other things before being used directly. This eliminates a category of attacks in which the CPU knows the current state of the crng and knows that we're going to xor RDSEED into it, and so it computes a malicious RDSEED. By going through our hash function, it would require the CPU to compute a preimage on the fly, which isn't going to happen. Cc: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Dominik Brodowski <linux@dominikbrodowski.net> Suggested-by: Dominik Brodowski <linux@dominikbrodowski.net> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-08 19:18:33 +08:00
for (i = 0; i < ARRAY_SIZE(block.rdseed); ++i) {
if (!arch_get_random_seed_long(&block.rdseed[i]) &&
!arch_get_random_long(&block.rdseed[i]))
block.rdseed[i] = random_get_entropy();
}
spin_lock_irqsave(&input_pool.lock, flags);
random: use computational hash for entropy extraction The current 4096-bit LFSR used for entropy collection had a few desirable attributes for the context in which it was created. For example, the state was huge, which meant that /dev/random would be able to output quite a bit of accumulated entropy before blocking. It was also, in its time, quite fast at accumulating entropy byte-by-byte, which matters given the varying contexts in which mix_pool_bytes() is called. And its diffusion was relatively high, which meant that changes would ripple across several words of state rather quickly. However, it also suffers from a few security vulnerabilities. In particular, inputs learned by an attacker can be undone, but moreover, if the state of the pool leaks, its contents can be controlled and entirely zeroed out. I've demonstrated this attack with this SMT2 script, <https://xn--4db.cc/5o9xO8pb>, which Boolector/CaDiCal solves in a matter of seconds on a single core of my laptop, resulting in little proof of concept C demonstrators such as <https://xn--4db.cc/jCkvvIaH/c>. For basically all recent formal models of RNGs, these attacks represent a significant cryptographic flaw. But how does this manifest practically? If an attacker has access to the system to such a degree that he can learn the internal state of the RNG, arguably there are other lower hanging vulnerabilities -- side-channel, infoleak, or otherwise -- that might have higher priority. On the other hand, seed files are frequently used on systems that have a hard time generating much entropy on their own, and these seed files, being files, often leak or are duplicated and distributed accidentally, or are even seeded over the Internet intentionally, where their contents might be recorded or tampered with. Seen this way, an otherwise quasi-implausible vulnerability is a bit more practical than initially thought. Another aspect of the current mix_pool_bytes() function is that, while its performance was arguably competitive for the time in which it was created, it's no longer considered so. This patch improves performance significantly: on a high-end CPU, an i7-11850H, it improves performance of mix_pool_bytes() by 225%, and on a low-end CPU, a Cortex-A7, it improves performance by 103%. This commit replaces the LFSR of mix_pool_bytes() with a straight- forward cryptographic hash function, BLAKE2s, which is already in use for pool extraction. Universal hashing with a secret seed was considered too, something along the lines of <https://eprint.iacr.org/2013/338>, but the requirement for a secret seed makes for a chicken & egg problem. Instead we go with a formally proven scheme using a computational hash function, described in sections 5.1, 6.4, and B.1.8 of <https://eprint.iacr.org/2019/198>. BLAKE2s outputs 256 bits, which should give us an appropriate amount of min-entropy accumulation, and a wide enough margin of collision resistance against active attacks. mix_pool_bytes() becomes a simple call to blake2s_update(), for accumulation, while the extraction step becomes a blake2s_final() to generate a seed, with which we can then do a HKDF-like or BLAKE2X-like expansion, the first part of which we fold back as an init key for subsequent blake2s_update()s, and the rest we produce to the caller. This then is provided to our CRNG like usual. In that expansion step, we make opportunistic use of 32 bytes of RDRAND output, just as before. We also always reseed the crng with 32 bytes, unconditionally, or not at all, rather than sometimes with 16 as before, as we don't win anything by limiting beyond the 16 byte threshold. Going for a hash function as an entropy collector is a conservative, proven approach. The result of all this is a much simpler and much less bespoke construction than what's there now, which not only plugs a vulnerability but also improves performance considerably. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-01-16 21:23:10 +08:00
/* seed = HASHPRF(last_key, entropy_input) */
blake2s_final(&input_pool.hash, seed);
random: use RDSEED instead of RDRAND in entropy extraction When /dev/random was directly connected with entropy extraction, without any expansion stage, extract_buf() was called for every 10 bytes of data read from /dev/random. For that reason, RDRAND was used rather than RDSEED. At the same time, crng_reseed() was still only called every 5 minutes, so there RDSEED made sense. Those olden days were also a time when the entropy collector did not use a cryptographic hash function, which meant most bets were off in terms of real preimage resistance. For that reason too it didn't matter _that_ much whether RDSEED was mixed in before or after entropy extraction; both choices were sort of bad. But now we have a cryptographic hash function at work, and with that we get real preimage resistance. We also now only call extract_entropy() every 5 minutes, rather than every 10 bytes. This allows us to do two important things. First, we can switch to using RDSEED in extract_entropy(), as Dominik suggested. Second, we can ensure that RDSEED input always goes into the cryptographic hash function with other things before being used directly. This eliminates a category of attacks in which the CPU knows the current state of the crng and knows that we're going to xor RDSEED into it, and so it computes a malicious RDSEED. By going through our hash function, it would require the CPU to compute a preimage on the fly, which isn't going to happen. Cc: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Dominik Brodowski <linux@dominikbrodowski.net> Suggested-by: Dominik Brodowski <linux@dominikbrodowski.net> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-08 19:18:33 +08:00
/* next_key = HASHPRF(seed, RDSEED || 0) */
random: use computational hash for entropy extraction The current 4096-bit LFSR used for entropy collection had a few desirable attributes for the context in which it was created. For example, the state was huge, which meant that /dev/random would be able to output quite a bit of accumulated entropy before blocking. It was also, in its time, quite fast at accumulating entropy byte-by-byte, which matters given the varying contexts in which mix_pool_bytes() is called. And its diffusion was relatively high, which meant that changes would ripple across several words of state rather quickly. However, it also suffers from a few security vulnerabilities. In particular, inputs learned by an attacker can be undone, but moreover, if the state of the pool leaks, its contents can be controlled and entirely zeroed out. I've demonstrated this attack with this SMT2 script, <https://xn--4db.cc/5o9xO8pb>, which Boolector/CaDiCal solves in a matter of seconds on a single core of my laptop, resulting in little proof of concept C demonstrators such as <https://xn--4db.cc/jCkvvIaH/c>. For basically all recent formal models of RNGs, these attacks represent a significant cryptographic flaw. But how does this manifest practically? If an attacker has access to the system to such a degree that he can learn the internal state of the RNG, arguably there are other lower hanging vulnerabilities -- side-channel, infoleak, or otherwise -- that might have higher priority. On the other hand, seed files are frequently used on systems that have a hard time generating much entropy on their own, and these seed files, being files, often leak or are duplicated and distributed accidentally, or are even seeded over the Internet intentionally, where their contents might be recorded or tampered with. Seen this way, an otherwise quasi-implausible vulnerability is a bit more practical than initially thought. Another aspect of the current mix_pool_bytes() function is that, while its performance was arguably competitive for the time in which it was created, it's no longer considered so. This patch improves performance significantly: on a high-end CPU, an i7-11850H, it improves performance of mix_pool_bytes() by 225%, and on a low-end CPU, a Cortex-A7, it improves performance by 103%. This commit replaces the LFSR of mix_pool_bytes() with a straight- forward cryptographic hash function, BLAKE2s, which is already in use for pool extraction. Universal hashing with a secret seed was considered too, something along the lines of <https://eprint.iacr.org/2013/338>, but the requirement for a secret seed makes for a chicken & egg problem. Instead we go with a formally proven scheme using a computational hash function, described in sections 5.1, 6.4, and B.1.8 of <https://eprint.iacr.org/2019/198>. BLAKE2s outputs 256 bits, which should give us an appropriate amount of min-entropy accumulation, and a wide enough margin of collision resistance against active attacks. mix_pool_bytes() becomes a simple call to blake2s_update(), for accumulation, while the extraction step becomes a blake2s_final() to generate a seed, with which we can then do a HKDF-like or BLAKE2X-like expansion, the first part of which we fold back as an init key for subsequent blake2s_update()s, and the rest we produce to the caller. This then is provided to our CRNG like usual. In that expansion step, we make opportunistic use of 32 bytes of RDRAND output, just as before. We also always reseed the crng with 32 bytes, unconditionally, or not at all, rather than sometimes with 16 as before, as we don't win anything by limiting beyond the 16 byte threshold. Going for a hash function as an entropy collector is a conservative, proven approach. The result of all this is a much simpler and much less bespoke construction than what's there now, which not only plugs a vulnerability but also improves performance considerably. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-01-16 21:23:10 +08:00
block.counter = 0;
blake2s(next_key, (u8 *)&block, seed, sizeof(next_key), sizeof(block), sizeof(seed));
blake2s_init_key(&input_pool.hash, BLAKE2S_HASH_SIZE, next_key, sizeof(next_key));
random: use computational hash for entropy extraction The current 4096-bit LFSR used for entropy collection had a few desirable attributes for the context in which it was created. For example, the state was huge, which meant that /dev/random would be able to output quite a bit of accumulated entropy before blocking. It was also, in its time, quite fast at accumulating entropy byte-by-byte, which matters given the varying contexts in which mix_pool_bytes() is called. And its diffusion was relatively high, which meant that changes would ripple across several words of state rather quickly. However, it also suffers from a few security vulnerabilities. In particular, inputs learned by an attacker can be undone, but moreover, if the state of the pool leaks, its contents can be controlled and entirely zeroed out. I've demonstrated this attack with this SMT2 script, <https://xn--4db.cc/5o9xO8pb>, which Boolector/CaDiCal solves in a matter of seconds on a single core of my laptop, resulting in little proof of concept C demonstrators such as <https://xn--4db.cc/jCkvvIaH/c>. For basically all recent formal models of RNGs, these attacks represent a significant cryptographic flaw. But how does this manifest practically? If an attacker has access to the system to such a degree that he can learn the internal state of the RNG, arguably there are other lower hanging vulnerabilities -- side-channel, infoleak, or otherwise -- that might have higher priority. On the other hand, seed files are frequently used on systems that have a hard time generating much entropy on their own, and these seed files, being files, often leak or are duplicated and distributed accidentally, or are even seeded over the Internet intentionally, where their contents might be recorded or tampered with. Seen this way, an otherwise quasi-implausible vulnerability is a bit more practical than initially thought. Another aspect of the current mix_pool_bytes() function is that, while its performance was arguably competitive for the time in which it was created, it's no longer considered so. This patch improves performance significantly: on a high-end CPU, an i7-11850H, it improves performance of mix_pool_bytes() by 225%, and on a low-end CPU, a Cortex-A7, it improves performance by 103%. This commit replaces the LFSR of mix_pool_bytes() with a straight- forward cryptographic hash function, BLAKE2s, which is already in use for pool extraction. Universal hashing with a secret seed was considered too, something along the lines of <https://eprint.iacr.org/2013/338>, but the requirement for a secret seed makes for a chicken & egg problem. Instead we go with a formally proven scheme using a computational hash function, described in sections 5.1, 6.4, and B.1.8 of <https://eprint.iacr.org/2019/198>. BLAKE2s outputs 256 bits, which should give us an appropriate amount of min-entropy accumulation, and a wide enough margin of collision resistance against active attacks. mix_pool_bytes() becomes a simple call to blake2s_update(), for accumulation, while the extraction step becomes a blake2s_final() to generate a seed, with which we can then do a HKDF-like or BLAKE2X-like expansion, the first part of which we fold back as an init key for subsequent blake2s_update()s, and the rest we produce to the caller. This then is provided to our CRNG like usual. In that expansion step, we make opportunistic use of 32 bytes of RDRAND output, just as before. We also always reseed the crng with 32 bytes, unconditionally, or not at all, rather than sometimes with 16 as before, as we don't win anything by limiting beyond the 16 byte threshold. Going for a hash function as an entropy collector is a conservative, proven approach. The result of all this is a much simpler and much less bespoke construction than what's there now, which not only plugs a vulnerability but also improves performance considerably. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-01-16 21:23:10 +08:00
spin_unlock_irqrestore(&input_pool.lock, flags);
memzero_explicit(next_key, sizeof(next_key));
while (nbytes) {
random: use computational hash for entropy extraction The current 4096-bit LFSR used for entropy collection had a few desirable attributes for the context in which it was created. For example, the state was huge, which meant that /dev/random would be able to output quite a bit of accumulated entropy before blocking. It was also, in its time, quite fast at accumulating entropy byte-by-byte, which matters given the varying contexts in which mix_pool_bytes() is called. And its diffusion was relatively high, which meant that changes would ripple across several words of state rather quickly. However, it also suffers from a few security vulnerabilities. In particular, inputs learned by an attacker can be undone, but moreover, if the state of the pool leaks, its contents can be controlled and entirely zeroed out. I've demonstrated this attack with this SMT2 script, <https://xn--4db.cc/5o9xO8pb>, which Boolector/CaDiCal solves in a matter of seconds on a single core of my laptop, resulting in little proof of concept C demonstrators such as <https://xn--4db.cc/jCkvvIaH/c>. For basically all recent formal models of RNGs, these attacks represent a significant cryptographic flaw. But how does this manifest practically? If an attacker has access to the system to such a degree that he can learn the internal state of the RNG, arguably there are other lower hanging vulnerabilities -- side-channel, infoleak, or otherwise -- that might have higher priority. On the other hand, seed files are frequently used on systems that have a hard time generating much entropy on their own, and these seed files, being files, often leak or are duplicated and distributed accidentally, or are even seeded over the Internet intentionally, where their contents might be recorded or tampered with. Seen this way, an otherwise quasi-implausible vulnerability is a bit more practical than initially thought. Another aspect of the current mix_pool_bytes() function is that, while its performance was arguably competitive for the time in which it was created, it's no longer considered so. This patch improves performance significantly: on a high-end CPU, an i7-11850H, it improves performance of mix_pool_bytes() by 225%, and on a low-end CPU, a Cortex-A7, it improves performance by 103%. This commit replaces the LFSR of mix_pool_bytes() with a straight- forward cryptographic hash function, BLAKE2s, which is already in use for pool extraction. Universal hashing with a secret seed was considered too, something along the lines of <https://eprint.iacr.org/2013/338>, but the requirement for a secret seed makes for a chicken & egg problem. Instead we go with a formally proven scheme using a computational hash function, described in sections 5.1, 6.4, and B.1.8 of <https://eprint.iacr.org/2019/198>. BLAKE2s outputs 256 bits, which should give us an appropriate amount of min-entropy accumulation, and a wide enough margin of collision resistance against active attacks. mix_pool_bytes() becomes a simple call to blake2s_update(), for accumulation, while the extraction step becomes a blake2s_final() to generate a seed, with which we can then do a HKDF-like or BLAKE2X-like expansion, the first part of which we fold back as an init key for subsequent blake2s_update()s, and the rest we produce to the caller. This then is provided to our CRNG like usual. In that expansion step, we make opportunistic use of 32 bytes of RDRAND output, just as before. We also always reseed the crng with 32 bytes, unconditionally, or not at all, rather than sometimes with 16 as before, as we don't win anything by limiting beyond the 16 byte threshold. Going for a hash function as an entropy collector is a conservative, proven approach. The result of all this is a much simpler and much less bespoke construction than what's there now, which not only plugs a vulnerability but also improves performance considerably. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-01-16 21:23:10 +08:00
i = min_t(size_t, nbytes, BLAKE2S_HASH_SIZE);
random: use RDSEED instead of RDRAND in entropy extraction When /dev/random was directly connected with entropy extraction, without any expansion stage, extract_buf() was called for every 10 bytes of data read from /dev/random. For that reason, RDRAND was used rather than RDSEED. At the same time, crng_reseed() was still only called every 5 minutes, so there RDSEED made sense. Those olden days were also a time when the entropy collector did not use a cryptographic hash function, which meant most bets were off in terms of real preimage resistance. For that reason too it didn't matter _that_ much whether RDSEED was mixed in before or after entropy extraction; both choices were sort of bad. But now we have a cryptographic hash function at work, and with that we get real preimage resistance. We also now only call extract_entropy() every 5 minutes, rather than every 10 bytes. This allows us to do two important things. First, we can switch to using RDSEED in extract_entropy(), as Dominik suggested. Second, we can ensure that RDSEED input always goes into the cryptographic hash function with other things before being used directly. This eliminates a category of attacks in which the CPU knows the current state of the crng and knows that we're going to xor RDSEED into it, and so it computes a malicious RDSEED. By going through our hash function, it would require the CPU to compute a preimage on the fly, which isn't going to happen. Cc: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Dominik Brodowski <linux@dominikbrodowski.net> Suggested-by: Dominik Brodowski <linux@dominikbrodowski.net> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-08 19:18:33 +08:00
/* output = HASHPRF(seed, RDSEED || ++counter) */
random: use computational hash for entropy extraction The current 4096-bit LFSR used for entropy collection had a few desirable attributes for the context in which it was created. For example, the state was huge, which meant that /dev/random would be able to output quite a bit of accumulated entropy before blocking. It was also, in its time, quite fast at accumulating entropy byte-by-byte, which matters given the varying contexts in which mix_pool_bytes() is called. And its diffusion was relatively high, which meant that changes would ripple across several words of state rather quickly. However, it also suffers from a few security vulnerabilities. In particular, inputs learned by an attacker can be undone, but moreover, if the state of the pool leaks, its contents can be controlled and entirely zeroed out. I've demonstrated this attack with this SMT2 script, <https://xn--4db.cc/5o9xO8pb>, which Boolector/CaDiCal solves in a matter of seconds on a single core of my laptop, resulting in little proof of concept C demonstrators such as <https://xn--4db.cc/jCkvvIaH/c>. For basically all recent formal models of RNGs, these attacks represent a significant cryptographic flaw. But how does this manifest practically? If an attacker has access to the system to such a degree that he can learn the internal state of the RNG, arguably there are other lower hanging vulnerabilities -- side-channel, infoleak, or otherwise -- that might have higher priority. On the other hand, seed files are frequently used on systems that have a hard time generating much entropy on their own, and these seed files, being files, often leak or are duplicated and distributed accidentally, or are even seeded over the Internet intentionally, where their contents might be recorded or tampered with. Seen this way, an otherwise quasi-implausible vulnerability is a bit more practical than initially thought. Another aspect of the current mix_pool_bytes() function is that, while its performance was arguably competitive for the time in which it was created, it's no longer considered so. This patch improves performance significantly: on a high-end CPU, an i7-11850H, it improves performance of mix_pool_bytes() by 225%, and on a low-end CPU, a Cortex-A7, it improves performance by 103%. This commit replaces the LFSR of mix_pool_bytes() with a straight- forward cryptographic hash function, BLAKE2s, which is already in use for pool extraction. Universal hashing with a secret seed was considered too, something along the lines of <https://eprint.iacr.org/2013/338>, but the requirement for a secret seed makes for a chicken & egg problem. Instead we go with a formally proven scheme using a computational hash function, described in sections 5.1, 6.4, and B.1.8 of <https://eprint.iacr.org/2019/198>. BLAKE2s outputs 256 bits, which should give us an appropriate amount of min-entropy accumulation, and a wide enough margin of collision resistance against active attacks. mix_pool_bytes() becomes a simple call to blake2s_update(), for accumulation, while the extraction step becomes a blake2s_final() to generate a seed, with which we can then do a HKDF-like or BLAKE2X-like expansion, the first part of which we fold back as an init key for subsequent blake2s_update()s, and the rest we produce to the caller. This then is provided to our CRNG like usual. In that expansion step, we make opportunistic use of 32 bytes of RDRAND output, just as before. We also always reseed the crng with 32 bytes, unconditionally, or not at all, rather than sometimes with 16 as before, as we don't win anything by limiting beyond the 16 byte threshold. Going for a hash function as an entropy collector is a conservative, proven approach. The result of all this is a much simpler and much less bespoke construction than what's there now, which not only plugs a vulnerability but also improves performance considerably. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-01-16 21:23:10 +08:00
++block.counter;
blake2s(buf, (u8 *)&block, seed, i, sizeof(block), sizeof(seed));
nbytes -= i;
buf += i;
}
random: use computational hash for entropy extraction The current 4096-bit LFSR used for entropy collection had a few desirable attributes for the context in which it was created. For example, the state was huge, which meant that /dev/random would be able to output quite a bit of accumulated entropy before blocking. It was also, in its time, quite fast at accumulating entropy byte-by-byte, which matters given the varying contexts in which mix_pool_bytes() is called. And its diffusion was relatively high, which meant that changes would ripple across several words of state rather quickly. However, it also suffers from a few security vulnerabilities. In particular, inputs learned by an attacker can be undone, but moreover, if the state of the pool leaks, its contents can be controlled and entirely zeroed out. I've demonstrated this attack with this SMT2 script, <https://xn--4db.cc/5o9xO8pb>, which Boolector/CaDiCal solves in a matter of seconds on a single core of my laptop, resulting in little proof of concept C demonstrators such as <https://xn--4db.cc/jCkvvIaH/c>. For basically all recent formal models of RNGs, these attacks represent a significant cryptographic flaw. But how does this manifest practically? If an attacker has access to the system to such a degree that he can learn the internal state of the RNG, arguably there are other lower hanging vulnerabilities -- side-channel, infoleak, or otherwise -- that might have higher priority. On the other hand, seed files are frequently used on systems that have a hard time generating much entropy on their own, and these seed files, being files, often leak or are duplicated and distributed accidentally, or are even seeded over the Internet intentionally, where their contents might be recorded or tampered with. Seen this way, an otherwise quasi-implausible vulnerability is a bit more practical than initially thought. Another aspect of the current mix_pool_bytes() function is that, while its performance was arguably competitive for the time in which it was created, it's no longer considered so. This patch improves performance significantly: on a high-end CPU, an i7-11850H, it improves performance of mix_pool_bytes() by 225%, and on a low-end CPU, a Cortex-A7, it improves performance by 103%. This commit replaces the LFSR of mix_pool_bytes() with a straight- forward cryptographic hash function, BLAKE2s, which is already in use for pool extraction. Universal hashing with a secret seed was considered too, something along the lines of <https://eprint.iacr.org/2013/338>, but the requirement for a secret seed makes for a chicken & egg problem. Instead we go with a formally proven scheme using a computational hash function, described in sections 5.1, 6.4, and B.1.8 of <https://eprint.iacr.org/2019/198>. BLAKE2s outputs 256 bits, which should give us an appropriate amount of min-entropy accumulation, and a wide enough margin of collision resistance against active attacks. mix_pool_bytes() becomes a simple call to blake2s_update(), for accumulation, while the extraction step becomes a blake2s_final() to generate a seed, with which we can then do a HKDF-like or BLAKE2X-like expansion, the first part of which we fold back as an init key for subsequent blake2s_update()s, and the rest we produce to the caller. This then is provided to our CRNG like usual. In that expansion step, we make opportunistic use of 32 bytes of RDRAND output, just as before. We also always reseed the crng with 32 bytes, unconditionally, or not at all, rather than sometimes with 16 as before, as we don't win anything by limiting beyond the 16 byte threshold. Going for a hash function as an entropy collector is a conservative, proven approach. The result of all this is a much simpler and much less bespoke construction than what's there now, which not only plugs a vulnerability but also improves performance considerably. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-01-16 21:23:10 +08:00
memzero_explicit(seed, sizeof(seed));
memzero_explicit(&block, sizeof(block));
}
#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
if (__ratelimit(&unseeded_warning))
printk_deferred(KERN_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
random: add new get_random_bytes_arch() function Create a new function, get_random_bytes_arch() which will use the architecture-specific hardware random number generator if it is present. Change get_random_bytes() to not use the HW RNG, even if it is avaiable. The reason for this is that the hw random number generator is fast (if it is present), but it requires that we trust the hardware manufacturer to have not put in a back door. (For example, an increasing counter encrypted by an AES key known to the NSA.) It's unlikely that Intel (for example) was paid off by the US Government to do this, but it's impossible for them to prove otherwise --- especially since Bull Mountain is documented to use AES as a whitener. Hence, the output of an evil, trojan-horse version of RDRAND is statistically indistinguishable from an RDRAND implemented to the specifications claimed by Intel. Short of using a tunnelling electronic microscope to reverse engineer an Ivy Bridge chip and disassembling and analyzing the CPU microcode, there's no way for us to tell for sure. Since users of get_random_bytes() in the Linux kernel need to be able to support hardware systems where the HW RNG is not present, most time-sensitive users of this interface have already created their own cryptographic RNG interface which uses get_random_bytes() as a seed. So it's much better to use the HW RNG to improve the existing random number generator, by mixing in any entropy returned by the HW RNG into /dev/random's entropy pool, but to always _use_ /dev/random's entropy pool. This way we get almost of the benefits of the HW RNG without any potential liabilities. The only benefits we forgo is the speed/performance enhancements --- and generic kernel code can't depend on depend on get_random_bytes() having the speed of a HW RNG anyway. For those places that really want access to the arch-specific HW RNG, if it is available, we provide get_random_bytes_arch(). Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: stable@vger.kernel.org
2012-07-05 22:35:23 +08:00
* number of good random numbers, suitable for key generation, seeding
* TCP sequence numbers, etc. It does not rely on the hardware random
* number generator. For random bytes direct from the hardware RNG
* (when available), use get_random_bytes_arch(). In order to ensure
* that the randomness provided by this function is okay, the function
* wait_for_random_bytes() should be called and return 0 at least once
* at any point prior.
*/
static void _get_random_bytes(void *buf, size_t nbytes)
random: add new get_random_bytes_arch() function Create a new function, get_random_bytes_arch() which will use the architecture-specific hardware random number generator if it is present. Change get_random_bytes() to not use the HW RNG, even if it is avaiable. The reason for this is that the hw random number generator is fast (if it is present), but it requires that we trust the hardware manufacturer to have not put in a back door. (For example, an increasing counter encrypted by an AES key known to the NSA.) It's unlikely that Intel (for example) was paid off by the US Government to do this, but it's impossible for them to prove otherwise --- especially since Bull Mountain is documented to use AES as a whitener. Hence, the output of an evil, trojan-horse version of RDRAND is statistically indistinguishable from an RDRAND implemented to the specifications claimed by Intel. Short of using a tunnelling electronic microscope to reverse engineer an Ivy Bridge chip and disassembling and analyzing the CPU microcode, there's no way for us to tell for sure. Since users of get_random_bytes() in the Linux kernel need to be able to support hardware systems where the HW RNG is not present, most time-sensitive users of this interface have already created their own cryptographic RNG interface which uses get_random_bytes() as a seed. So it's much better to use the HW RNG to improve the existing random number generator, by mixing in any entropy returned by the HW RNG into /dev/random's entropy pool, but to always _use_ /dev/random's entropy pool. This way we get almost of the benefits of the HW RNG without any potential liabilities. The only benefits we forgo is the speed/performance enhancements --- and generic kernel code can't depend on depend on get_random_bytes() having the speed of a HW RNG anyway. For those places that really want access to the arch-specific HW RNG, if it is available, we provide get_random_bytes_arch(). Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: stable@vger.kernel.org
2012-07-05 22:35:23 +08:00
{
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
u32 chacha_state[CHACHA_STATE_WORDS];
u8 tmp[CHACHA_BLOCK_SIZE];
size_t len;
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
if (!nbytes)
return;
len = min_t(size_t, 32, nbytes);
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
crng_make_state(chacha_state, buf, len);
nbytes -= len;
buf += len;
while (nbytes) {
if (nbytes < CHACHA_BLOCK_SIZE) {
chacha20_block(chacha_state, tmp);
memcpy(buf, tmp, nbytes);
memzero_explicit(tmp, sizeof(tmp));
break;
}
chacha20_block(chacha_state, buf);
if (unlikely(chacha_state[12] == 0))
++chacha_state[13];
nbytes -= CHACHA_BLOCK_SIZE;
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
buf += CHACHA_BLOCK_SIZE;
}
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
memzero_explicit(chacha_state, sizeof(chacha_state));
random: add new get_random_bytes_arch() function Create a new function, get_random_bytes_arch() which will use the architecture-specific hardware random number generator if it is present. Change get_random_bytes() to not use the HW RNG, even if it is avaiable. The reason for this is that the hw random number generator is fast (if it is present), but it requires that we trust the hardware manufacturer to have not put in a back door. (For example, an increasing counter encrypted by an AES key known to the NSA.) It's unlikely that Intel (for example) was paid off by the US Government to do this, but it's impossible for them to prove otherwise --- especially since Bull Mountain is documented to use AES as a whitener. Hence, the output of an evil, trojan-horse version of RDRAND is statistically indistinguishable from an RDRAND implemented to the specifications claimed by Intel. Short of using a tunnelling electronic microscope to reverse engineer an Ivy Bridge chip and disassembling and analyzing the CPU microcode, there's no way for us to tell for sure. Since users of get_random_bytes() in the Linux kernel need to be able to support hardware systems where the HW RNG is not present, most time-sensitive users of this interface have already created their own cryptographic RNG interface which uses get_random_bytes() as a seed. So it's much better to use the HW RNG to improve the existing random number generator, by mixing in any entropy returned by the HW RNG into /dev/random's entropy pool, but to always _use_ /dev/random's entropy pool. This way we get almost of the benefits of the HW RNG without any potential liabilities. The only benefits we forgo is the speed/performance enhancements --- and generic kernel code can't depend on depend on get_random_bytes() having the speed of a HW RNG anyway. For those places that really want access to the arch-specific HW RNG, if it is available, we provide get_random_bytes_arch(). Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: stable@vger.kernel.org
2012-07-05 22:35:23 +08:00
}
void get_random_bytes(void *buf, size_t nbytes)
{
static void *previous;
warn_unseeded_randomness(&previous);
_get_random_bytes(buf, nbytes);
}
random: add new get_random_bytes_arch() function Create a new function, get_random_bytes_arch() which will use the architecture-specific hardware random number generator if it is present. Change get_random_bytes() to not use the HW RNG, even if it is avaiable. The reason for this is that the hw random number generator is fast (if it is present), but it requires that we trust the hardware manufacturer to have not put in a back door. (For example, an increasing counter encrypted by an AES key known to the NSA.) It's unlikely that Intel (for example) was paid off by the US Government to do this, but it's impossible for them to prove otherwise --- especially since Bull Mountain is documented to use AES as a whitener. Hence, the output of an evil, trojan-horse version of RDRAND is statistically indistinguishable from an RDRAND implemented to the specifications claimed by Intel. Short of using a tunnelling electronic microscope to reverse engineer an Ivy Bridge chip and disassembling and analyzing the CPU microcode, there's no way for us to tell for sure. Since users of get_random_bytes() in the Linux kernel need to be able to support hardware systems where the HW RNG is not present, most time-sensitive users of this interface have already created their own cryptographic RNG interface which uses get_random_bytes() as a seed. So it's much better to use the HW RNG to improve the existing random number generator, by mixing in any entropy returned by the HW RNG into /dev/random's entropy pool, but to always _use_ /dev/random's entropy pool. This way we get almost of the benefits of the HW RNG without any potential liabilities. The only benefits we forgo is the speed/performance enhancements --- and generic kernel code can't depend on depend on get_random_bytes() having the speed of a HW RNG anyway. For those places that really want access to the arch-specific HW RNG, if it is available, we provide get_random_bytes_arch(). Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: stable@vger.kernel.org
2012-07-05 22:35:23 +08:00
EXPORT_SYMBOL(get_random_bytes);
random: try to actively add entropy rather than passively wait for it For 5.3 we had to revert a nice ext4 IO pattern improvement, because it caused a bootup regression due to lack of entropy at bootup together with arguably broken user space that was asking for secure random numbers when it really didn't need to. See commit 72dbcf721566 (Revert "ext4: make __ext4_get_inode_loc plug"). This aims to solve the issue by actively generating entropy noise using the CPU cycle counter when waiting for the random number generator to initialize. This only works when you have a high-frequency time stamp counter available, but that's the case on all modern x86 CPU's, and on most other modern CPU's too. What we do is to generate jitter entropy from the CPU cycle counter under a somewhat complex load: calling the scheduler while also guaranteeing a certain amount of timing noise by also triggering a timer. I'm sure we can tweak this, and that people will want to look at other alternatives, but there's been a number of papers written on jitter entropy, and this should really be fairly conservative by crediting one bit of entropy for every timer-induced jump in the cycle counter. Not because the timer itself would be all that unpredictable, but because the interaction between the timer and the loop is going to be. Even if (and perhaps particularly if) the timer actually happens on another CPU, the cacheline interaction between the loop that reads the cycle counter and the timer itself firing is going to add perturbations to the cycle counter values that get mixed into the entropy pool. As Thomas pointed out, with a modern out-of-order CPU, even quite simple loops show a fair amount of hard-to-predict timing variability even in the absense of external interrupts. But this tries to take that further by actually having a fairly complex interaction. This is not going to solve the entropy issue for architectures that have no CPU cycle counter, but it's not clear how (and if) that is solvable, and the hardware in question is largely starting to be irrelevant. And by doing this we can at least avoid some of the even more contentious approaches (like making the entropy waiting time out in order to avoid the possibly unbounded waiting). Cc: Ahmed Darwish <darwish.07@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Nicholas Mc Guire <hofrat@opentech.at> Cc: Andy Lutomirski <luto@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: Willy Tarreau <w@1wt.eu> Cc: Alexander E. Patrakov <patrakov@gmail.com> Cc: Lennart Poettering <mzxreary@0pointer.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-29 07:53:52 +08:00
/*
* 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 entropy_timer(struct timer_list *t)
{
credit_entropy_bits(1);
random: try to actively add entropy rather than passively wait for it For 5.3 we had to revert a nice ext4 IO pattern improvement, because it caused a bootup regression due to lack of entropy at bootup together with arguably broken user space that was asking for secure random numbers when it really didn't need to. See commit 72dbcf721566 (Revert "ext4: make __ext4_get_inode_loc plug"). This aims to solve the issue by actively generating entropy noise using the CPU cycle counter when waiting for the random number generator to initialize. This only works when you have a high-frequency time stamp counter available, but that's the case on all modern x86 CPU's, and on most other modern CPU's too. What we do is to generate jitter entropy from the CPU cycle counter under a somewhat complex load: calling the scheduler while also guaranteeing a certain amount of timing noise by also triggering a timer. I'm sure we can tweak this, and that people will want to look at other alternatives, but there's been a number of papers written on jitter entropy, and this should really be fairly conservative by crediting one bit of entropy for every timer-induced jump in the cycle counter. Not because the timer itself would be all that unpredictable, but because the interaction between the timer and the loop is going to be. Even if (and perhaps particularly if) the timer actually happens on another CPU, the cacheline interaction between the loop that reads the cycle counter and the timer itself firing is going to add perturbations to the cycle counter values that get mixed into the entropy pool. As Thomas pointed out, with a modern out-of-order CPU, even quite simple loops show a fair amount of hard-to-predict timing variability even in the absense of external interrupts. But this tries to take that further by actually having a fairly complex interaction. This is not going to solve the entropy issue for architectures that have no CPU cycle counter, but it's not clear how (and if) that is solvable, and the hardware in question is largely starting to be irrelevant. And by doing this we can at least avoid some of the even more contentious approaches (like making the entropy waiting time out in order to avoid the possibly unbounded waiting). Cc: Ahmed Darwish <darwish.07@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Nicholas Mc Guire <hofrat@opentech.at> Cc: Andy Lutomirski <luto@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: Willy Tarreau <w@1wt.eu> Cc: Alexander E. Patrakov <patrakov@gmail.com> Cc: Lennart Poettering <mzxreary@0pointer.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-29 07:53:52 +08:00
}
/*
* If we have an actual cycle counter, see if we can
* generate enough entropy with timing noise
*/
static void try_to_generate_entropy(void)
{
struct {
unsigned long now;
struct timer_list timer;
} stack;
stack.now = random_get_entropy();
/* Slow counter - or none. Don't even bother */
if (stack.now == random_get_entropy())
return;
timer_setup_on_stack(&stack.timer, entropy_timer, 0);
while (!crng_ready()) {
if (!timer_pending(&stack.timer))
mod_timer(&stack.timer, jiffies + 1);
mix_pool_bytes(&stack.now, sizeof(stack.now));
random: try to actively add entropy rather than passively wait for it For 5.3 we had to revert a nice ext4 IO pattern improvement, because it caused a bootup regression due to lack of entropy at bootup together with arguably broken user space that was asking for secure random numbers when it really didn't need to. See commit 72dbcf721566 (Revert "ext4: make __ext4_get_inode_loc plug"). This aims to solve the issue by actively generating entropy noise using the CPU cycle counter when waiting for the random number generator to initialize. This only works when you have a high-frequency time stamp counter available, but that's the case on all modern x86 CPU's, and on most other modern CPU's too. What we do is to generate jitter entropy from the CPU cycle counter under a somewhat complex load: calling the scheduler while also guaranteeing a certain amount of timing noise by also triggering a timer. I'm sure we can tweak this, and that people will want to look at other alternatives, but there's been a number of papers written on jitter entropy, and this should really be fairly conservative by crediting one bit of entropy for every timer-induced jump in the cycle counter. Not because the timer itself would be all that unpredictable, but because the interaction between the timer and the loop is going to be. Even if (and perhaps particularly if) the timer actually happens on another CPU, the cacheline interaction between the loop that reads the cycle counter and the timer itself firing is going to add perturbations to the cycle counter values that get mixed into the entropy pool. As Thomas pointed out, with a modern out-of-order CPU, even quite simple loops show a fair amount of hard-to-predict timing variability even in the absense of external interrupts. But this tries to take that further by actually having a fairly complex interaction. This is not going to solve the entropy issue for architectures that have no CPU cycle counter, but it's not clear how (and if) that is solvable, and the hardware in question is largely starting to be irrelevant. And by doing this we can at least avoid some of the even more contentious approaches (like making the entropy waiting time out in order to avoid the possibly unbounded waiting). Cc: Ahmed Darwish <darwish.07@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Nicholas Mc Guire <hofrat@opentech.at> Cc: Andy Lutomirski <luto@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: Willy Tarreau <w@1wt.eu> Cc: Alexander E. Patrakov <patrakov@gmail.com> Cc: Lennart Poettering <mzxreary@0pointer.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-29 07:53:52 +08:00
schedule();
stack.now = random_get_entropy();
}
del_timer_sync(&stack.timer);
destroy_timer_on_stack(&stack.timer);
mix_pool_bytes(&stack.now, sizeof(stack.now));
random: try to actively add entropy rather than passively wait for it For 5.3 we had to revert a nice ext4 IO pattern improvement, because it caused a bootup regression due to lack of entropy at bootup together with arguably broken user space that was asking for secure random numbers when it really didn't need to. See commit 72dbcf721566 (Revert "ext4: make __ext4_get_inode_loc plug"). This aims to solve the issue by actively generating entropy noise using the CPU cycle counter when waiting for the random number generator to initialize. This only works when you have a high-frequency time stamp counter available, but that's the case on all modern x86 CPU's, and on most other modern CPU's too. What we do is to generate jitter entropy from the CPU cycle counter under a somewhat complex load: calling the scheduler while also guaranteeing a certain amount of timing noise by also triggering a timer. I'm sure we can tweak this, and that people will want to look at other alternatives, but there's been a number of papers written on jitter entropy, and this should really be fairly conservative by crediting one bit of entropy for every timer-induced jump in the cycle counter. Not because the timer itself would be all that unpredictable, but because the interaction between the timer and the loop is going to be. Even if (and perhaps particularly if) the timer actually happens on another CPU, the cacheline interaction between the loop that reads the cycle counter and the timer itself firing is going to add perturbations to the cycle counter values that get mixed into the entropy pool. As Thomas pointed out, with a modern out-of-order CPU, even quite simple loops show a fair amount of hard-to-predict timing variability even in the absense of external interrupts. But this tries to take that further by actually having a fairly complex interaction. This is not going to solve the entropy issue for architectures that have no CPU cycle counter, but it's not clear how (and if) that is solvable, and the hardware in question is largely starting to be irrelevant. And by doing this we can at least avoid some of the even more contentious approaches (like making the entropy waiting time out in order to avoid the possibly unbounded waiting). Cc: Ahmed Darwish <darwish.07@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Nicholas Mc Guire <hofrat@opentech.at> Cc: Andy Lutomirski <luto@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: Willy Tarreau <w@1wt.eu> Cc: Alexander E. Patrakov <patrakov@gmail.com> Cc: Lennart Poettering <mzxreary@0pointer.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-29 07:53:52 +08:00
}
/*
* 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;
random: try to actively add entropy rather than passively wait for it For 5.3 we had to revert a nice ext4 IO pattern improvement, because it caused a bootup regression due to lack of entropy at bootup together with arguably broken user space that was asking for secure random numbers when it really didn't need to. See commit 72dbcf721566 (Revert "ext4: make __ext4_get_inode_loc plug"). This aims to solve the issue by actively generating entropy noise using the CPU cycle counter when waiting for the random number generator to initialize. This only works when you have a high-frequency time stamp counter available, but that's the case on all modern x86 CPU's, and on most other modern CPU's too. What we do is to generate jitter entropy from the CPU cycle counter under a somewhat complex load: calling the scheduler while also guaranteeing a certain amount of timing noise by also triggering a timer. I'm sure we can tweak this, and that people will want to look at other alternatives, but there's been a number of papers written on jitter entropy, and this should really be fairly conservative by crediting one bit of entropy for every timer-induced jump in the cycle counter. Not because the timer itself would be all that unpredictable, but because the interaction between the timer and the loop is going to be. Even if (and perhaps particularly if) the timer actually happens on another CPU, the cacheline interaction between the loop that reads the cycle counter and the timer itself firing is going to add perturbations to the cycle counter values that get mixed into the entropy pool. As Thomas pointed out, with a modern out-of-order CPU, even quite simple loops show a fair amount of hard-to-predict timing variability even in the absense of external interrupts. But this tries to take that further by actually having a fairly complex interaction. This is not going to solve the entropy issue for architectures that have no CPU cycle counter, but it's not clear how (and if) that is solvable, and the hardware in question is largely starting to be irrelevant. And by doing this we can at least avoid some of the even more contentious approaches (like making the entropy waiting time out in order to avoid the possibly unbounded waiting). Cc: Ahmed Darwish <darwish.07@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Nicholas Mc Guire <hofrat@opentech.at> Cc: Andy Lutomirski <luto@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: Willy Tarreau <w@1wt.eu> Cc: Alexander E. Patrakov <patrakov@gmail.com> Cc: Lennart Poettering <mzxreary@0pointer.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-29 07:53:52 +08:00
do {
int ret;
ret = wait_event_interruptible_timeout(crng_init_wait, crng_ready(), HZ);
if (ret)
return ret > 0 ? 0 : ret;
try_to_generate_entropy();
} while (!crng_ready());
return 0;
}
EXPORT_SYMBOL(wait_for_random_bytes);
/*
* Returns whether or not the urandom pool has been seeded and thus guaranteed
* to supply cryptographically secure random numbers. This applies to: the
* /dev/urandom device, the get_random_bytes function, and the get_random_{u32,
* ,u64,int,long} family of functions.
*
* Returns: true if the urandom pool has been seeded.
* false if the urandom pool has not been seeded.
*/
bool rng_is_initialized(void)
{
return crng_ready();
}
EXPORT_SYMBOL(rng_is_initialized);
/*
* 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);
random: add new get_random_bytes_arch() function Create a new function, get_random_bytes_arch() which will use the architecture-specific hardware random number generator if it is present. Change get_random_bytes() to not use the HW RNG, even if it is avaiable. The reason for this is that the hw random number generator is fast (if it is present), but it requires that we trust the hardware manufacturer to have not put in a back door. (For example, an increasing counter encrypted by an AES key known to the NSA.) It's unlikely that Intel (for example) was paid off by the US Government to do this, but it's impossible for them to prove otherwise --- especially since Bull Mountain is documented to use AES as a whitener. Hence, the output of an evil, trojan-horse version of RDRAND is statistically indistinguishable from an RDRAND implemented to the specifications claimed by Intel. Short of using a tunnelling electronic microscope to reverse engineer an Ivy Bridge chip and disassembling and analyzing the CPU microcode, there's no way for us to tell for sure. Since users of get_random_bytes() in the Linux kernel need to be able to support hardware systems where the HW RNG is not present, most time-sensitive users of this interface have already created their own cryptographic RNG interface which uses get_random_bytes() as a seed. So it's much better to use the HW RNG to improve the existing random number generator, by mixing in any entropy returned by the HW RNG into /dev/random's entropy pool, but to always _use_ /dev/random's entropy pool. This way we get almost of the benefits of the HW RNG without any potential liabilities. The only benefits we forgo is the speed/performance enhancements --- and generic kernel code can't depend on depend on get_random_bytes() having the speed of a HW RNG anyway. For those places that really want access to the arch-specific HW RNG, if it is available, we provide get_random_bytes_arch(). Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: stable@vger.kernel.org
2012-07-05 22:35:23 +08:00
/*
* This function will use the architecture-specific hardware random
* number generator if it is available. It is not recommended for
* use. Use get_random_bytes() instead. It returns the number of
* bytes filled in.
random: add new get_random_bytes_arch() function Create a new function, get_random_bytes_arch() which will use the architecture-specific hardware random number generator if it is present. Change get_random_bytes() to not use the HW RNG, even if it is avaiable. The reason for this is that the hw random number generator is fast (if it is present), but it requires that we trust the hardware manufacturer to have not put in a back door. (For example, an increasing counter encrypted by an AES key known to the NSA.) It's unlikely that Intel (for example) was paid off by the US Government to do this, but it's impossible for them to prove otherwise --- especially since Bull Mountain is documented to use AES as a whitener. Hence, the output of an evil, trojan-horse version of RDRAND is statistically indistinguishable from an RDRAND implemented to the specifications claimed by Intel. Short of using a tunnelling electronic microscope to reverse engineer an Ivy Bridge chip and disassembling and analyzing the CPU microcode, there's no way for us to tell for sure. Since users of get_random_bytes() in the Linux kernel need to be able to support hardware systems where the HW RNG is not present, most time-sensitive users of this interface have already created their own cryptographic RNG interface which uses get_random_bytes() as a seed. So it's much better to use the HW RNG to improve the existing random number generator, by mixing in any entropy returned by the HW RNG into /dev/random's entropy pool, but to always _use_ /dev/random's entropy pool. This way we get almost of the benefits of the HW RNG without any potential liabilities. The only benefits we forgo is the speed/performance enhancements --- and generic kernel code can't depend on depend on get_random_bytes() having the speed of a HW RNG anyway. For those places that really want access to the arch-specific HW RNG, if it is available, we provide get_random_bytes_arch(). Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: stable@vger.kernel.org
2012-07-05 22:35:23 +08:00
*/
size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes)
{
size_t left = nbytes;
u8 *p = buf;
while (left) {
unsigned long v;
size_t chunk = min_t(size_t, left, sizeof(unsigned long));
random: add new get_random_bytes_arch() function Create a new function, get_random_bytes_arch() which will use the architecture-specific hardware random number generator if it is present. Change get_random_bytes() to not use the HW RNG, even if it is avaiable. The reason for this is that the hw random number generator is fast (if it is present), but it requires that we trust the hardware manufacturer to have not put in a back door. (For example, an increasing counter encrypted by an AES key known to the NSA.) It's unlikely that Intel (for example) was paid off by the US Government to do this, but it's impossible for them to prove otherwise --- especially since Bull Mountain is documented to use AES as a whitener. Hence, the output of an evil, trojan-horse version of RDRAND is statistically indistinguishable from an RDRAND implemented to the specifications claimed by Intel. Short of using a tunnelling electronic microscope to reverse engineer an Ivy Bridge chip and disassembling and analyzing the CPU microcode, there's no way for us to tell for sure. Since users of get_random_bytes() in the Linux kernel need to be able to support hardware systems where the HW RNG is not present, most time-sensitive users of this interface have already created their own cryptographic RNG interface which uses get_random_bytes() as a seed. So it's much better to use the HW RNG to improve the existing random number generator, by mixing in any entropy returned by the HW RNG into /dev/random's entropy pool, but to always _use_ /dev/random's entropy pool. This way we get almost of the benefits of the HW RNG without any potential liabilities. The only benefits we forgo is the speed/performance enhancements --- and generic kernel code can't depend on depend on get_random_bytes() having the speed of a HW RNG anyway. For those places that really want access to the arch-specific HW RNG, if it is available, we provide get_random_bytes_arch(). Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: stable@vger.kernel.org
2012-07-05 22:35:23 +08:00
if (!arch_get_random_long(&v))
break;
memcpy(p, &v, chunk);
p += chunk;
left -= chunk;
}
return nbytes - left;
}
random: add new get_random_bytes_arch() function Create a new function, get_random_bytes_arch() which will use the architecture-specific hardware random number generator if it is present. Change get_random_bytes() to not use the HW RNG, even if it is avaiable. The reason for this is that the hw random number generator is fast (if it is present), but it requires that we trust the hardware manufacturer to have not put in a back door. (For example, an increasing counter encrypted by an AES key known to the NSA.) It's unlikely that Intel (for example) was paid off by the US Government to do this, but it's impossible for them to prove otherwise --- especially since Bull Mountain is documented to use AES as a whitener. Hence, the output of an evil, trojan-horse version of RDRAND is statistically indistinguishable from an RDRAND implemented to the specifications claimed by Intel. Short of using a tunnelling electronic microscope to reverse engineer an Ivy Bridge chip and disassembling and analyzing the CPU microcode, there's no way for us to tell for sure. Since users of get_random_bytes() in the Linux kernel need to be able to support hardware systems where the HW RNG is not present, most time-sensitive users of this interface have already created their own cryptographic RNG interface which uses get_random_bytes() as a seed. So it's much better to use the HW RNG to improve the existing random number generator, by mixing in any entropy returned by the HW RNG into /dev/random's entropy pool, but to always _use_ /dev/random's entropy pool. This way we get almost of the benefits of the HW RNG without any potential liabilities. The only benefits we forgo is the speed/performance enhancements --- and generic kernel code can't depend on depend on get_random_bytes() having the speed of a HW RNG anyway. For those places that really want access to the arch-specific HW RNG, if it is available, we provide get_random_bytes_arch(). Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: stable@vger.kernel.org
2012-07-05 22:35:23 +08:00
EXPORT_SYMBOL(get_random_bytes_arch);
static bool trust_cpu __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU);
static int __init parse_trust_cpu(char *arg)
{
return kstrtobool(arg, &trust_cpu);
}
early_param("random.trust_cpu", parse_trust_cpu);
/*
* 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.
*/
int __init rand_initialize(void)
{
size_t i;
ktime_t now = ktime_get_real();
bool arch_init = true;
unsigned long rv;
for (i = 0; i < BLAKE2S_BLOCK_SIZE; i += sizeof(rv)) {
if (!arch_get_random_seed_long_early(&rv) &&
!arch_get_random_long_early(&rv)) {
rv = random_get_entropy();
arch_init = false;
}
mix_pool_bytes(&rv, sizeof(rv));
}
mix_pool_bytes(&now, sizeof(now));
mix_pool_bytes(utsname(), sizeof(*(utsname())));
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
extract_entropy(base_crng.key, sizeof(base_crng.key));
++base_crng.generation;
if (arch_init && trust_cpu && crng_init < 2) {
crng_init = 2;
pr_notice("crng init done (trusting CPU's manufacturer)\n");
}
if (ratelimit_disable) {
urandom_warning.interval = 0;
unseeded_warning.interval = 0;
}
return 0;
}
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#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;
}
}
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#endif
static ssize_t urandom_read(struct file *file, char __user *buf, size_t nbytes,
loff_t *ppos)
{
static int maxwarn = 10;
if (!crng_ready() && maxwarn > 0) {
maxwarn--;
if (__ratelimit(&urandom_warning))
pr_notice("%s: uninitialized urandom read (%zd bytes read)\n",
current->comm, nbytes);
}
return get_random_bytes_user(buf, nbytes);
}
static ssize_t random_read(struct file *file, char __user *buf, size_t nbytes,
loff_t *ppos)
{
int ret;
ret = wait_for_random_bytes();
if (ret != 0)
return ret;
return get_random_bytes_user(buf, nbytes);
}
static __poll_t random_poll(struct file *file, poll_table *wait)
{
__poll_t mask;
poll_wait(file, &crng_init_wait, wait);
poll_wait(file, &random_write_wait, wait);
mask = 0;
if (crng_ready())
mask |= EPOLLIN | EPOLLRDNORM;
if (input_pool.entropy_count < POOL_MIN_BITS)
mask |= EPOLLOUT | EPOLLWRNORM;
return mask;
}
static int write_pool(const char __user *ubuf, size_t count)
{
size_t len;
int ret = 0;
u8 block[BLAKE2S_BLOCK_SIZE];
while (count) {
len = min(count, sizeof(block));
if (copy_from_user(block, ubuf, len)) {
ret = -EFAULT;
goto out;
}
count -= len;
ubuf += len;
mix_pool_bytes(block, len);
cond_resched();
}
out:
memzero_explicit(block, sizeof(block));
return ret;
}
static ssize_t random_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos)
{
int ret;
ret = write_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 */
random: use linear min-entropy accumulation crediting 30e37ec516ae ("random: account for entropy loss due to overwrites") assumed that adding new entropy to the LFSR pool probabilistically cancelled out old entropy there, so entropy was credited asymptotically, approximating Shannon entropy of independent sources (rather than a stronger min-entropy notion) using 1/8th fractional bits and replacing a constant 2-2/√𝑒 term (~0.786938) with 3/4 (0.75) to slightly underestimate it. This wasn't superb, but it was perhaps better than nothing, so that's what was done. Which entropy specifically was being cancelled out and how much precisely each time is hard to tell, though as I showed with the attack code in my previous commit, a motivated adversary with sufficient information can actually cancel out everything. Since we're no longer using an LFSR for entropy accumulation, this probabilistic cancellation is no longer relevant. Rather, we're now using a computational hash function as the accumulator and we've switched to working in the random oracle model, from which we can now revisit the question of min-entropy accumulation, which is done in detail in <https://eprint.iacr.org/2019/198>. Consider a long input bit string that is built by concatenating various smaller independent input bit strings. Each one of these inputs has a designated min-entropy, which is what we're passing to credit_entropy_bits(h). When we pass the concatenation of these to a random oracle, it means that an adversary trying to receive back the same reply as us would need to become certain about each part of the concatenated bit string we passed in, which means becoming certain about all of those h values. That means we can estimate the accumulation by simply adding up the h values in calls to credit_entropy_bits(h); there's no probabilistic cancellation at play like there was said to be for the LFSR. Incidentally, this is also what other entropy accumulators based on computational hash functions do as well. So this commit replaces credit_entropy_bits(h) with essentially `total = min(POOL_BITS, total + h)`, done with a cmpxchg loop as before. What if we're wrong and the above is nonsense? It's not, but let's assume we don't want the actual _behavior_ of the code to change much. Currently that behavior is not extracting from the input pool until it has 128 bits of entropy in it. With the old algorithm, we'd hit that magic 128 number after roughly 256 calls to credit_entropy_bits(1). So, we can retain more or less the old behavior by waiting to extract from the input pool until it hits 256 bits of entropy using the new code. For people concerned about this change, it means that there's not that much practical behavioral change. And for folks actually trying to model the behavior rigorously, it means that we have an even higher margin against attacks. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-03 20:28:06 +08:00
if (put_user(input_pool.entropy_count, p))
return -EFAULT;
return 0;
case RNDADDTOENTCNT:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(ent_count, p))
return -EFAULT;
if (ent_count < 0)
return -EINVAL;
credit_entropy_bits(ent_count);
return 0;
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((const char __user *)p, size);
if (retval < 0)
return retval;
credit_entropy_bits(ent_count);
return 0;
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;
if (xchg(&input_pool.entropy_count, 0)) {
wake_up_interruptible(&random_write_wait);
kill_fasync(&fasync, SIGIO, POLL_OUT);
}
return 0;
case RNDRESEEDCRNG:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (crng_init < 2)
return -ENODATA;
crng_reseed();
return 0;
default:
return -EINVAL;
}
}
2008-04-29 16:03:08 +08:00
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,
.compat_ioctl = compat_ptr_ioctl,
2008-04-29 16:03:08 +08:00
.fasync = random_fasync,
llseek: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Julia Lawall <julia@diku.dk> Cc: Christoph Hellwig <hch@infradead.org>
2010-08-16 00:52:59 +08:00
.llseek = noop_llseek,
};
const struct file_operations urandom_fops = {
.read = urandom_read,
.write = random_write,
.unlocked_ioctl = random_ioctl,
.compat_ioctl = compat_ptr_ioctl,
2008-04-29 16:03:08 +08:00
.fasync = random_fasync,
llseek: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Julia Lawall <julia@diku.dk> Cc: Christoph Hellwig <hch@infradead.org>
2010-08-16 00:52:59 +08:00
.llseek = noop_llseek,
};
SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count, unsigned int,
flags)
random: introduce getrandom(2) system call The getrandom(2) system call was requested by the LibreSSL Portable developers. It is analoguous to the getentropy(2) system call in OpenBSD. The rationale of this system call is to provide resiliance against file descriptor exhaustion attacks, where the attacker consumes all available file descriptors, forcing the use of the fallback code where /dev/[u]random is not available. Since the fallback code is often not well-tested, it is better to eliminate this potential failure mode entirely. The other feature provided by this new system call is the ability to request randomness from the /dev/urandom entropy pool, but to block until at least 128 bits of entropy has been accumulated in the /dev/urandom entropy pool. Historically, the emphasis in the /dev/urandom development has been to ensure that urandom pool is initialized as quickly as possible after system boot, and preferably before the init scripts start execution. This is because changing /dev/urandom reads to block represents an interface change that could potentially break userspace which is not acceptable. In practice, on most x86 desktop and server systems, in general the entropy pool can be initialized before it is needed (and in modern kernels, we will printk a warning message if not). However, on an embedded system, this may not be the case. And so with this new interface, we can provide the functionality of blocking until the urandom pool has been initialized. Any userspace program which uses this new functionality must take care to assure that if it is used during the boot process, that it will not cause the init scripts or other portions of the system startup to hang indefinitely. SYNOPSIS #include <linux/random.h> int getrandom(void *buf, size_t buflen, unsigned int flags); DESCRIPTION The system call getrandom() fills the buffer pointed to by buf with up to buflen random bytes which can be used to seed user space random number generators (i.e., DRBG's) or for other cryptographic uses. It should not be used for Monte Carlo simulations or other programs/algorithms which are doing probabilistic sampling. If the GRND_RANDOM flags bit is set, then draw from the /dev/random pool instead of the /dev/urandom pool. The /dev/random pool is limited based on the entropy that can be obtained from environmental noise, so if there is insufficient entropy, the requested number of bytes may not be returned. If there is no entropy available at all, getrandom(2) will either block, or return an error with errno set to EAGAIN if the GRND_NONBLOCK bit is set in flags. If the GRND_RANDOM bit is not set, then the /dev/urandom pool will be used. Unlike using read(2) to fetch data from /dev/urandom, if the urandom pool has not been sufficiently initialized, getrandom(2) will block (or return -1 with the errno set to EAGAIN if the GRND_NONBLOCK bit is set in flags). The getentropy(2) system call in OpenBSD can be emulated using the following function: int getentropy(void *buf, size_t buflen) { int ret; if (buflen > 256) goto failure; ret = getrandom(buf, buflen, 0); if (ret < 0) return ret; if (ret == buflen) return 0; failure: errno = EIO; return -1; } RETURN VALUE On success, the number of bytes that was filled in the buf is returned. This may not be all the bytes requested by the caller via buflen if insufficient entropy was present in the /dev/random pool, or if the system call was interrupted by a signal. On error, -1 is returned, and errno is set appropriately. ERRORS EINVAL An invalid flag was passed to getrandom(2) EFAULT buf is outside the accessible address space. EAGAIN The requested entropy was not available, and getentropy(2) would have blocked if the GRND_NONBLOCK flag was not set. EINTR While blocked waiting for entropy, the call was interrupted by a signal handler; see the description of how interrupted read(2) calls on "slow" devices are handled with and without the SA_RESTART flag in the signal(7) man page. NOTES For small requests (buflen <= 256) getrandom(2) will not return EINTR when reading from the urandom pool once the entropy pool has been initialized, and it will return all of the bytes that have been requested. This is the recommended way to use getrandom(2), and is designed for compatibility with OpenBSD's getentropy() system call. However, if you are using GRND_RANDOM, then getrandom(2) may block until the entropy accounting determines that sufficient environmental noise has been gathered such that getrandom(2) will be operating as a NRBG instead of a DRBG for those people who are working in the NIST SP 800-90 regime. Since it may block for a long time, these guarantees do *not* apply. The user may want to interrupt a hanging process using a signal, so blocking until all of the requested bytes are returned would be unfriendly. For this reason, the user of getrandom(2) MUST always check the return value, in case it returns some error, or if fewer bytes than requested was returned. In the case of !GRND_RANDOM and small request, the latter should never happen, but the careful userspace code (and all crypto code should be careful) should check for this anyway! Finally, unless you are doing long-term key generation (and perhaps not even then), you probably shouldn't be using GRND_RANDOM. The cryptographic algorithms used for /dev/urandom are quite conservative, and so should be sufficient for all purposes. The disadvantage of GRND_RANDOM is that it can block, and the increased complexity required to deal with partially fulfilled getrandom(2) requests. Signed-off-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Zach Brown <zab@zabbo.net>
2014-07-17 16:13:05 +08:00
{
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))
random: introduce getrandom(2) system call The getrandom(2) system call was requested by the LibreSSL Portable developers. It is analoguous to the getentropy(2) system call in OpenBSD. The rationale of this system call is to provide resiliance against file descriptor exhaustion attacks, where the attacker consumes all available file descriptors, forcing the use of the fallback code where /dev/[u]random is not available. Since the fallback code is often not well-tested, it is better to eliminate this potential failure mode entirely. The other feature provided by this new system call is the ability to request randomness from the /dev/urandom entropy pool, but to block until at least 128 bits of entropy has been accumulated in the /dev/urandom entropy pool. Historically, the emphasis in the /dev/urandom development has been to ensure that urandom pool is initialized as quickly as possible after system boot, and preferably before the init scripts start execution. This is because changing /dev/urandom reads to block represents an interface change that could potentially break userspace which is not acceptable. In practice, on most x86 desktop and server systems, in general the entropy pool can be initialized before it is needed (and in modern kernels, we will printk a warning message if not). However, on an embedded system, this may not be the case. And so with this new interface, we can provide the functionality of blocking until the urandom pool has been initialized. Any userspace program which uses this new functionality must take care to assure that if it is used during the boot process, that it will not cause the init scripts or other portions of the system startup to hang indefinitely. SYNOPSIS #include <linux/random.h> int getrandom(void *buf, size_t buflen, unsigned int flags); DESCRIPTION The system call getrandom() fills the buffer pointed to by buf with up to buflen random bytes which can be used to seed user space random number generators (i.e., DRBG's) or for other cryptographic uses. It should not be used for Monte Carlo simulations or other programs/algorithms which are doing probabilistic sampling. If the GRND_RANDOM flags bit is set, then draw from the /dev/random pool instead of the /dev/urandom pool. The /dev/random pool is limited based on the entropy that can be obtained from environmental noise, so if there is insufficient entropy, the requested number of bytes may not be returned. If there is no entropy available at all, getrandom(2) will either block, or return an error with errno set to EAGAIN if the GRND_NONBLOCK bit is set in flags. If the GRND_RANDOM bit is not set, then the /dev/urandom pool will be used. Unlike using read(2) to fetch data from /dev/urandom, if the urandom pool has not been sufficiently initialized, getrandom(2) will block (or return -1 with the errno set to EAGAIN if the GRND_NONBLOCK bit is set in flags). The getentropy(2) system call in OpenBSD can be emulated using the following function: int getentropy(void *buf, size_t buflen) { int ret; if (buflen > 256) goto failure; ret = getrandom(buf, buflen, 0); if (ret < 0) return ret; if (ret == buflen) return 0; failure: errno = EIO; return -1; } RETURN VALUE On success, the number of bytes that was filled in the buf is returned. This may not be all the bytes requested by the caller via buflen if insufficient entropy was present in the /dev/random pool, or if the system call was interrupted by a signal. On error, -1 is returned, and errno is set appropriately. ERRORS EINVAL An invalid flag was passed to getrandom(2) EFAULT buf is outside the accessible address space. EAGAIN The requested entropy was not available, and getentropy(2) would have blocked if the GRND_NONBLOCK flag was not set. EINTR While blocked waiting for entropy, the call was interrupted by a signal handler; see the description of how interrupted read(2) calls on "slow" devices are handled with and without the SA_RESTART flag in the signal(7) man page. NOTES For small requests (buflen <= 256) getrandom(2) will not return EINTR when reading from the urandom pool once the entropy pool has been initialized, and it will return all of the bytes that have been requested. This is the recommended way to use getrandom(2), and is designed for compatibility with OpenBSD's getentropy() system call. However, if you are using GRND_RANDOM, then getrandom(2) may block until the entropy accounting determines that sufficient environmental noise has been gathered such that getrandom(2) will be operating as a NRBG instead of a DRBG for those people who are working in the NIST SP 800-90 regime. Since it may block for a long time, these guarantees do *not* apply. The user may want to interrupt a hanging process using a signal, so blocking until all of the requested bytes are returned would be unfriendly. For this reason, the user of getrandom(2) MUST always check the return value, in case it returns some error, or if fewer bytes than requested was returned. In the case of !GRND_RANDOM and small request, the latter should never happen, but the careful userspace code (and all crypto code should be careful) should check for this anyway! Finally, unless you are doing long-term key generation (and perhaps not even then), you probably shouldn't be using GRND_RANDOM. The cryptographic algorithms used for /dev/urandom are quite conservative, and so should be sufficient for all purposes. The disadvantage of GRND_RANDOM is that it can block, and the increased complexity required to deal with partially fulfilled getrandom(2) requests. Signed-off-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Zach Brown <zab@zabbo.net>
2014-07-17 16:13:05 +08:00
return -EINVAL;
if (count > INT_MAX)
count = INT_MAX;
if (!(flags & GRND_INSECURE) && !crng_ready()) {
int ret;
random: introduce getrandom(2) system call The getrandom(2) system call was requested by the LibreSSL Portable developers. It is analoguous to the getentropy(2) system call in OpenBSD. The rationale of this system call is to provide resiliance against file descriptor exhaustion attacks, where the attacker consumes all available file descriptors, forcing the use of the fallback code where /dev/[u]random is not available. Since the fallback code is often not well-tested, it is better to eliminate this potential failure mode entirely. The other feature provided by this new system call is the ability to request randomness from the /dev/urandom entropy pool, but to block until at least 128 bits of entropy has been accumulated in the /dev/urandom entropy pool. Historically, the emphasis in the /dev/urandom development has been to ensure that urandom pool is initialized as quickly as possible after system boot, and preferably before the init scripts start execution. This is because changing /dev/urandom reads to block represents an interface change that could potentially break userspace which is not acceptable. In practice, on most x86 desktop and server systems, in general the entropy pool can be initialized before it is needed (and in modern kernels, we will printk a warning message if not). However, on an embedded system, this may not be the case. And so with this new interface, we can provide the functionality of blocking until the urandom pool has been initialized. Any userspace program which uses this new functionality must take care to assure that if it is used during the boot process, that it will not cause the init scripts or other portions of the system startup to hang indefinitely. SYNOPSIS #include <linux/random.h> int getrandom(void *buf, size_t buflen, unsigned int flags); DESCRIPTION The system call getrandom() fills the buffer pointed to by buf with up to buflen random bytes which can be used to seed user space random number generators (i.e., DRBG's) or for other cryptographic uses. It should not be used for Monte Carlo simulations or other programs/algorithms which are doing probabilistic sampling. If the GRND_RANDOM flags bit is set, then draw from the /dev/random pool instead of the /dev/urandom pool. The /dev/random pool is limited based on the entropy that can be obtained from environmental noise, so if there is insufficient entropy, the requested number of bytes may not be returned. If there is no entropy available at all, getrandom(2) will either block, or return an error with errno set to EAGAIN if the GRND_NONBLOCK bit is set in flags. If the GRND_RANDOM bit is not set, then the /dev/urandom pool will be used. Unlike using read(2) to fetch data from /dev/urandom, if the urandom pool has not been sufficiently initialized, getrandom(2) will block (or return -1 with the errno set to EAGAIN if the GRND_NONBLOCK bit is set in flags). The getentropy(2) system call in OpenBSD can be emulated using the following function: int getentropy(void *buf, size_t buflen) { int ret; if (buflen > 256) goto failure; ret = getrandom(buf, buflen, 0); if (ret < 0) return ret; if (ret == buflen) return 0; failure: errno = EIO; return -1; } RETURN VALUE On success, the number of bytes that was filled in the buf is returned. This may not be all the bytes requested by the caller via buflen if insufficient entropy was present in the /dev/random pool, or if the system call was interrupted by a signal. On error, -1 is returned, and errno is set appropriately. ERRORS EINVAL An invalid flag was passed to getrandom(2) EFAULT buf is outside the accessible address space. EAGAIN The requested entropy was not available, and getentropy(2) would have blocked if the GRND_NONBLOCK flag was not set. EINTR While blocked waiting for entropy, the call was interrupted by a signal handler; see the description of how interrupted read(2) calls on "slow" devices are handled with and without the SA_RESTART flag in the signal(7) man page. NOTES For small requests (buflen <= 256) getrandom(2) will not return EINTR when reading from the urandom pool once the entropy pool has been initialized, and it will return all of the bytes that have been requested. This is the recommended way to use getrandom(2), and is designed for compatibility with OpenBSD's getentropy() system call. However, if you are using GRND_RANDOM, then getrandom(2) may block until the entropy accounting determines that sufficient environmental noise has been gathered such that getrandom(2) will be operating as a NRBG instead of a DRBG for those people who are working in the NIST SP 800-90 regime. Since it may block for a long time, these guarantees do *not* apply. The user may want to interrupt a hanging process using a signal, so blocking until all of the requested bytes are returned would be unfriendly. For this reason, the user of getrandom(2) MUST always check the return value, in case it returns some error, or if fewer bytes than requested was returned. In the case of !GRND_RANDOM and small request, the latter should never happen, but the careful userspace code (and all crypto code should be careful) should check for this anyway! Finally, unless you are doing long-term key generation (and perhaps not even then), you probably shouldn't be using GRND_RANDOM. The cryptographic algorithms used for /dev/urandom are quite conservative, and so should be sufficient for all purposes. The disadvantage of GRND_RANDOM is that it can block, and the increased complexity required to deal with partially fulfilled getrandom(2) requests. Signed-off-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Zach Brown <zab@zabbo.net>
2014-07-17 16:13:05 +08:00
if (flags & GRND_NONBLOCK)
return -EAGAIN;
ret = wait_for_random_bytes();
if (unlikely(ret))
return ret;
random: introduce getrandom(2) system call The getrandom(2) system call was requested by the LibreSSL Portable developers. It is analoguous to the getentropy(2) system call in OpenBSD. The rationale of this system call is to provide resiliance against file descriptor exhaustion attacks, where the attacker consumes all available file descriptors, forcing the use of the fallback code where /dev/[u]random is not available. Since the fallback code is often not well-tested, it is better to eliminate this potential failure mode entirely. The other feature provided by this new system call is the ability to request randomness from the /dev/urandom entropy pool, but to block until at least 128 bits of entropy has been accumulated in the /dev/urandom entropy pool. Historically, the emphasis in the /dev/urandom development has been to ensure that urandom pool is initialized as quickly as possible after system boot, and preferably before the init scripts start execution. This is because changing /dev/urandom reads to block represents an interface change that could potentially break userspace which is not acceptable. In practice, on most x86 desktop and server systems, in general the entropy pool can be initialized before it is needed (and in modern kernels, we will printk a warning message if not). However, on an embedded system, this may not be the case. And so with this new interface, we can provide the functionality of blocking until the urandom pool has been initialized. Any userspace program which uses this new functionality must take care to assure that if it is used during the boot process, that it will not cause the init scripts or other portions of the system startup to hang indefinitely. SYNOPSIS #include <linux/random.h> int getrandom(void *buf, size_t buflen, unsigned int flags); DESCRIPTION The system call getrandom() fills the buffer pointed to by buf with up to buflen random bytes which can be used to seed user space random number generators (i.e., DRBG's) or for other cryptographic uses. It should not be used for Monte Carlo simulations or other programs/algorithms which are doing probabilistic sampling. If the GRND_RANDOM flags bit is set, then draw from the /dev/random pool instead of the /dev/urandom pool. The /dev/random pool is limited based on the entropy that can be obtained from environmental noise, so if there is insufficient entropy, the requested number of bytes may not be returned. If there is no entropy available at all, getrandom(2) will either block, or return an error with errno set to EAGAIN if the GRND_NONBLOCK bit is set in flags. If the GRND_RANDOM bit is not set, then the /dev/urandom pool will be used. Unlike using read(2) to fetch data from /dev/urandom, if the urandom pool has not been sufficiently initialized, getrandom(2) will block (or return -1 with the errno set to EAGAIN if the GRND_NONBLOCK bit is set in flags). The getentropy(2) system call in OpenBSD can be emulated using the following function: int getentropy(void *buf, size_t buflen) { int ret; if (buflen > 256) goto failure; ret = getrandom(buf, buflen, 0); if (ret < 0) return ret; if (ret == buflen) return 0; failure: errno = EIO; return -1; } RETURN VALUE On success, the number of bytes that was filled in the buf is returned. This may not be all the bytes requested by the caller via buflen if insufficient entropy was present in the /dev/random pool, or if the system call was interrupted by a signal. On error, -1 is returned, and errno is set appropriately. ERRORS EINVAL An invalid flag was passed to getrandom(2) EFAULT buf is outside the accessible address space. EAGAIN The requested entropy was not available, and getentropy(2) would have blocked if the GRND_NONBLOCK flag was not set. EINTR While blocked waiting for entropy, the call was interrupted by a signal handler; see the description of how interrupted read(2) calls on "slow" devices are handled with and without the SA_RESTART flag in the signal(7) man page. NOTES For small requests (buflen <= 256) getrandom(2) will not return EINTR when reading from the urandom pool once the entropy pool has been initialized, and it will return all of the bytes that have been requested. This is the recommended way to use getrandom(2), and is designed for compatibility with OpenBSD's getentropy() system call. However, if you are using GRND_RANDOM, then getrandom(2) may block until the entropy accounting determines that sufficient environmental noise has been gathered such that getrandom(2) will be operating as a NRBG instead of a DRBG for those people who are working in the NIST SP 800-90 regime. Since it may block for a long time, these guarantees do *not* apply. The user may want to interrupt a hanging process using a signal, so blocking until all of the requested bytes are returned would be unfriendly. For this reason, the user of getrandom(2) MUST always check the return value, in case it returns some error, or if fewer bytes than requested was returned. In the case of !GRND_RANDOM and small request, the latter should never happen, but the careful userspace code (and all crypto code should be careful) should check for this anyway! Finally, unless you are doing long-term key generation (and perhaps not even then), you probably shouldn't be using GRND_RANDOM. The cryptographic algorithms used for /dev/urandom are quite conservative, and so should be sufficient for all purposes. The disadvantage of GRND_RANDOM is that it can block, and the increased complexity required to deal with partially fulfilled getrandom(2) requests. Signed-off-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Zach Brown <zab@zabbo.net>
2014-07-17 16:13:05 +08:00
}
return get_random_bytes_user(buf, count);
random: introduce getrandom(2) system call The getrandom(2) system call was requested by the LibreSSL Portable developers. It is analoguous to the getentropy(2) system call in OpenBSD. The rationale of this system call is to provide resiliance against file descriptor exhaustion attacks, where the attacker consumes all available file descriptors, forcing the use of the fallback code where /dev/[u]random is not available. Since the fallback code is often not well-tested, it is better to eliminate this potential failure mode entirely. The other feature provided by this new system call is the ability to request randomness from the /dev/urandom entropy pool, but to block until at least 128 bits of entropy has been accumulated in the /dev/urandom entropy pool. Historically, the emphasis in the /dev/urandom development has been to ensure that urandom pool is initialized as quickly as possible after system boot, and preferably before the init scripts start execution. This is because changing /dev/urandom reads to block represents an interface change that could potentially break userspace which is not acceptable. In practice, on most x86 desktop and server systems, in general the entropy pool can be initialized before it is needed (and in modern kernels, we will printk a warning message if not). However, on an embedded system, this may not be the case. And so with this new interface, we can provide the functionality of blocking until the urandom pool has been initialized. Any userspace program which uses this new functionality must take care to assure that if it is used during the boot process, that it will not cause the init scripts or other portions of the system startup to hang indefinitely. SYNOPSIS #include <linux/random.h> int getrandom(void *buf, size_t buflen, unsigned int flags); DESCRIPTION The system call getrandom() fills the buffer pointed to by buf with up to buflen random bytes which can be used to seed user space random number generators (i.e., DRBG's) or for other cryptographic uses. It should not be used for Monte Carlo simulations or other programs/algorithms which are doing probabilistic sampling. If the GRND_RANDOM flags bit is set, then draw from the /dev/random pool instead of the /dev/urandom pool. The /dev/random pool is limited based on the entropy that can be obtained from environmental noise, so if there is insufficient entropy, the requested number of bytes may not be returned. If there is no entropy available at all, getrandom(2) will either block, or return an error with errno set to EAGAIN if the GRND_NONBLOCK bit is set in flags. If the GRND_RANDOM bit is not set, then the /dev/urandom pool will be used. Unlike using read(2) to fetch data from /dev/urandom, if the urandom pool has not been sufficiently initialized, getrandom(2) will block (or return -1 with the errno set to EAGAIN if the GRND_NONBLOCK bit is set in flags). The getentropy(2) system call in OpenBSD can be emulated using the following function: int getentropy(void *buf, size_t buflen) { int ret; if (buflen > 256) goto failure; ret = getrandom(buf, buflen, 0); if (ret < 0) return ret; if (ret == buflen) return 0; failure: errno = EIO; return -1; } RETURN VALUE On success, the number of bytes that was filled in the buf is returned. This may not be all the bytes requested by the caller via buflen if insufficient entropy was present in the /dev/random pool, or if the system call was interrupted by a signal. On error, -1 is returned, and errno is set appropriately. ERRORS EINVAL An invalid flag was passed to getrandom(2) EFAULT buf is outside the accessible address space. EAGAIN The requested entropy was not available, and getentropy(2) would have blocked if the GRND_NONBLOCK flag was not set. EINTR While blocked waiting for entropy, the call was interrupted by a signal handler; see the description of how interrupted read(2) calls on "slow" devices are handled with and without the SA_RESTART flag in the signal(7) man page. NOTES For small requests (buflen <= 256) getrandom(2) will not return EINTR when reading from the urandom pool once the entropy pool has been initialized, and it will return all of the bytes that have been requested. This is the recommended way to use getrandom(2), and is designed for compatibility with OpenBSD's getentropy() system call. However, if you are using GRND_RANDOM, then getrandom(2) may block until the entropy accounting determines that sufficient environmental noise has been gathered such that getrandom(2) will be operating as a NRBG instead of a DRBG for those people who are working in the NIST SP 800-90 regime. Since it may block for a long time, these guarantees do *not* apply. The user may want to interrupt a hanging process using a signal, so blocking until all of the requested bytes are returned would be unfriendly. For this reason, the user of getrandom(2) MUST always check the return value, in case it returns some error, or if fewer bytes than requested was returned. In the case of !GRND_RANDOM and small request, the latter should never happen, but the careful userspace code (and all crypto code should be careful) should check for this anyway! Finally, unless you are doing long-term key generation (and perhaps not even then), you probably shouldn't be using GRND_RANDOM. The cryptographic algorithms used for /dev/urandom are quite conservative, and so should be sufficient for all purposes. The disadvantage of GRND_RANDOM is that it can block, and the increased complexity required to deal with partially fulfilled getrandom(2) requests. Signed-off-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Zach Brown <zab@zabbo.net>
2014-07-17 16:13:05 +08:00
}
/********************************************************************
*
* Sysctl interface
*
********************************************************************/
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
static int random_min_urandom_seed = 60;
static int random_write_wakeup_bits = POOL_MIN_BITS;
static int sysctl_poolsize = POOL_BITS;
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 *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);
}
random: move the random sysctl declarations to its own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. So move the random sysctls to their own file and use register_sysctl_init(). [mcgrof@kernel.org: commit log update to justify the move] Link: https://lkml.kernel.org/r/20211124231435.1445213-3-mcgrof@kernel.org Signed-off-by: Xiaoming Ni <nixiaoming@huawei.com> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Amir Goldstein <amir73il@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Antti Palosaari <crope@iki.fi> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Benjamin LaHaise <bcrl@kvack.org> Cc: Clemens Ladisch <clemens@ladisch.de> Cc: David Airlie <airlied@linux.ie> Cc: Douglas Gilbert <dgilbert@interlog.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Iurii Zaikin <yzaikin@google.com> Cc: James E.J. Bottomley <jejb@linux.ibm.com> Cc: Jani Nikula <jani.nikula@intel.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Joel Becker <jlbec@evilplan.org> Cc: John Ogness <john.ogness@linutronix.de> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Joseph Qi <joseph.qi@linux.alibaba.com> Cc: Julia Lawall <julia.lawall@inria.fr> Cc: Kees Cook <keescook@chromium.org> Cc: Lukas Middendorf <kernel@tuxforce.de> Cc: Mark Fasheh <mark@fasheh.com> Cc: Martin K. Petersen <martin.petersen@oracle.com> Cc: Paul Turner <pjt@google.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Phillip Potter <phil@philpotter.co.uk> Cc: Qing Wang <wangqing@vivo.com> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Sebastian Reichel <sre@kernel.org> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Stephen Kitt <steve@sk2.org> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: "Theodore Ts'o" <tytso@mit.edu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-22 14:12:18 +08:00
static struct ctl_table random_table[] = {
{
.procname = "poolsize",
.data = &sysctl_poolsize,
.maxlen = sizeof(int),
.mode = 0444,
.proc_handler = proc_dointvec,
},
{
.procname = "entropy_avail",
random: use linear min-entropy accumulation crediting 30e37ec516ae ("random: account for entropy loss due to overwrites") assumed that adding new entropy to the LFSR pool probabilistically cancelled out old entropy there, so entropy was credited asymptotically, approximating Shannon entropy of independent sources (rather than a stronger min-entropy notion) using 1/8th fractional bits and replacing a constant 2-2/√𝑒 term (~0.786938) with 3/4 (0.75) to slightly underestimate it. This wasn't superb, but it was perhaps better than nothing, so that's what was done. Which entropy specifically was being cancelled out and how much precisely each time is hard to tell, though as I showed with the attack code in my previous commit, a motivated adversary with sufficient information can actually cancel out everything. Since we're no longer using an LFSR for entropy accumulation, this probabilistic cancellation is no longer relevant. Rather, we're now using a computational hash function as the accumulator and we've switched to working in the random oracle model, from which we can now revisit the question of min-entropy accumulation, which is done in detail in <https://eprint.iacr.org/2019/198>. Consider a long input bit string that is built by concatenating various smaller independent input bit strings. Each one of these inputs has a designated min-entropy, which is what we're passing to credit_entropy_bits(h). When we pass the concatenation of these to a random oracle, it means that an adversary trying to receive back the same reply as us would need to become certain about each part of the concatenated bit string we passed in, which means becoming certain about all of those h values. That means we can estimate the accumulation by simply adding up the h values in calls to credit_entropy_bits(h); there's no probabilistic cancellation at play like there was said to be for the LFSR. Incidentally, this is also what other entropy accumulators based on computational hash functions do as well. So this commit replaces credit_entropy_bits(h) with essentially `total = min(POOL_BITS, total + h)`, done with a cmpxchg loop as before. What if we're wrong and the above is nonsense? It's not, but let's assume we don't want the actual _behavior_ of the code to change much. Currently that behavior is not extracting from the input pool until it has 128 bits of entropy in it. With the old algorithm, we'd hit that magic 128 number after roughly 256 calls to credit_entropy_bits(1). So, we can retain more or less the old behavior by waiting to extract from the input pool until it hits 256 bits of entropy using the new code. For people concerned about this change, it means that there's not that much practical behavioral change. And for folks actually trying to model the behavior rigorously, it means that we have an even higher margin against attacks. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-03 20:28:06 +08:00
.data = &input_pool.entropy_count,
.maxlen = sizeof(int),
.mode = 0444,
random: use linear min-entropy accumulation crediting 30e37ec516ae ("random: account for entropy loss due to overwrites") assumed that adding new entropy to the LFSR pool probabilistically cancelled out old entropy there, so entropy was credited asymptotically, approximating Shannon entropy of independent sources (rather than a stronger min-entropy notion) using 1/8th fractional bits and replacing a constant 2-2/√𝑒 term (~0.786938) with 3/4 (0.75) to slightly underestimate it. This wasn't superb, but it was perhaps better than nothing, so that's what was done. Which entropy specifically was being cancelled out and how much precisely each time is hard to tell, though as I showed with the attack code in my previous commit, a motivated adversary with sufficient information can actually cancel out everything. Since we're no longer using an LFSR for entropy accumulation, this probabilistic cancellation is no longer relevant. Rather, we're now using a computational hash function as the accumulator and we've switched to working in the random oracle model, from which we can now revisit the question of min-entropy accumulation, which is done in detail in <https://eprint.iacr.org/2019/198>. Consider a long input bit string that is built by concatenating various smaller independent input bit strings. Each one of these inputs has a designated min-entropy, which is what we're passing to credit_entropy_bits(h). When we pass the concatenation of these to a random oracle, it means that an adversary trying to receive back the same reply as us would need to become certain about each part of the concatenated bit string we passed in, which means becoming certain about all of those h values. That means we can estimate the accumulation by simply adding up the h values in calls to credit_entropy_bits(h); there's no probabilistic cancellation at play like there was said to be for the LFSR. Incidentally, this is also what other entropy accumulators based on computational hash functions do as well. So this commit replaces credit_entropy_bits(h) with essentially `total = min(POOL_BITS, total + h)`, done with a cmpxchg loop as before. What if we're wrong and the above is nonsense? It's not, but let's assume we don't want the actual _behavior_ of the code to change much. Currently that behavior is not extracting from the input pool until it has 128 bits of entropy in it. With the old algorithm, we'd hit that magic 128 number after roughly 256 calls to credit_entropy_bits(1). So, we can retain more or less the old behavior by waiting to extract from the input pool until it hits 256 bits of entropy using the new code. For people concerned about this change, it means that there's not that much practical behavioral change. And for folks actually trying to model the behavior rigorously, it means that we have an even higher margin against attacks. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-03 20:28:06 +08:00
.proc_handler = proc_dointvec,
},
{
.procname = "write_wakeup_threshold",
.data = &random_write_wakeup_bits,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.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,
},
{ }
};
random: move the random sysctl declarations to its own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. So move the random sysctls to their own file and use register_sysctl_init(). [mcgrof@kernel.org: commit log update to justify the move] Link: https://lkml.kernel.org/r/20211124231435.1445213-3-mcgrof@kernel.org Signed-off-by: Xiaoming Ni <nixiaoming@huawei.com> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Amir Goldstein <amir73il@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Antti Palosaari <crope@iki.fi> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Benjamin LaHaise <bcrl@kvack.org> Cc: Clemens Ladisch <clemens@ladisch.de> Cc: David Airlie <airlied@linux.ie> Cc: Douglas Gilbert <dgilbert@interlog.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Iurii Zaikin <yzaikin@google.com> Cc: James E.J. Bottomley <jejb@linux.ibm.com> Cc: Jani Nikula <jani.nikula@intel.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Joel Becker <jlbec@evilplan.org> Cc: John Ogness <john.ogness@linutronix.de> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Joseph Qi <joseph.qi@linux.alibaba.com> Cc: Julia Lawall <julia.lawall@inria.fr> Cc: Kees Cook <keescook@chromium.org> Cc: Lukas Middendorf <kernel@tuxforce.de> Cc: Mark Fasheh <mark@fasheh.com> Cc: Martin K. Petersen <martin.petersen@oracle.com> Cc: Paul Turner <pjt@google.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Phillip Potter <phil@philpotter.co.uk> Cc: Qing Wang <wangqing@vivo.com> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Sebastian Reichel <sre@kernel.org> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Stephen Kitt <steve@sk2.org> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: "Theodore Ts'o" <tytso@mit.edu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-22 14:12:18 +08:00
/*
* rand_initialize() is called before sysctl_init(),
* so we cannot call register_sysctl_init() in rand_initialize()
*/
static int __init random_sysctls_init(void)
{
register_sysctl_init("kernel/random", random_table);
return 0;
}
device_initcall(random_sysctls_init);
#endif /* CONFIG_SYSCTL */
random: use chacha20 for get_random_int/long Now that our crng uses chacha20, we can rely on its speedy characteristics for replacing MD5, while simultaneously achieving a higher security guarantee. Before the idea was to use these functions if you wanted random integers that aren't stupidly insecure but aren't necessarily secure either, a vague gray zone, that hopefully was "good enough" for its users. With chacha20, we can strengthen this claim, since either we're using an rdrand-like instruction, or we're using the same crng as /dev/urandom. And it's faster than what was before. We could have chosen to replace this with a SipHash-derived function, which might be slightly faster, but at the cost of having yet another RNG construction in the kernel. By moving to chacha20, we have a single RNG to analyze and verify, and we also already get good performance improvements on all platforms. Implementation-wise, rather than use a generic buffer for both get_random_int/long and memcpy based on the size needs, we use a specific buffer for 32-bit reads and for 64-bit reads. This way, we're guaranteed to always have aligned accesses on all platforms. While slightly more verbose in C, the assembly this generates is a lot simpler than otherwise. Finally, on 32-bit platforms where longs and ints are the same size, we simply alias get_random_int to get_random_long. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Suggested-by: Theodore Ts'o <tytso@mit.edu> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-07 02:32:01 +08:00
struct batched_entropy {
union {
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
/*
* We make this 1.5x a ChaCha block, so that we get the
* remaining 32 bytes from fast key erasure, plus one full
* block from the detached ChaCha state. We can increase
* the size of this later if needed so long as we keep the
* formula of (integer_blocks + 0.5) * CHACHA_BLOCK_SIZE.
*/
u64 entropy_u64[CHACHA_BLOCK_SIZE * 3 / (2 * sizeof(u64))];
u32 entropy_u32[CHACHA_BLOCK_SIZE * 3 / (2 * sizeof(u32))];
random: use chacha20 for get_random_int/long Now that our crng uses chacha20, we can rely on its speedy characteristics for replacing MD5, while simultaneously achieving a higher security guarantee. Before the idea was to use these functions if you wanted random integers that aren't stupidly insecure but aren't necessarily secure either, a vague gray zone, that hopefully was "good enough" for its users. With chacha20, we can strengthen this claim, since either we're using an rdrand-like instruction, or we're using the same crng as /dev/urandom. And it's faster than what was before. We could have chosen to replace this with a SipHash-derived function, which might be slightly faster, but at the cost of having yet another RNG construction in the kernel. By moving to chacha20, we have a single RNG to analyze and verify, and we also already get good performance improvements on all platforms. Implementation-wise, rather than use a generic buffer for both get_random_int/long and memcpy based on the size needs, we use a specific buffer for 32-bit reads and for 64-bit reads. This way, we're guaranteed to always have aligned accesses on all platforms. While slightly more verbose in C, the assembly this generates is a lot simpler than otherwise. Finally, on 32-bit platforms where longs and ints are the same size, we simply alias get_random_int to get_random_long. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Suggested-by: Theodore Ts'o <tytso@mit.edu> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-07 02:32:01 +08:00
};
local_lock_t lock;
unsigned long generation;
random: use chacha20 for get_random_int/long Now that our crng uses chacha20, we can rely on its speedy characteristics for replacing MD5, while simultaneously achieving a higher security guarantee. Before the idea was to use these functions if you wanted random integers that aren't stupidly insecure but aren't necessarily secure either, a vague gray zone, that hopefully was "good enough" for its users. With chacha20, we can strengthen this claim, since either we're using an rdrand-like instruction, or we're using the same crng as /dev/urandom. And it's faster than what was before. We could have chosen to replace this with a SipHash-derived function, which might be slightly faster, but at the cost of having yet another RNG construction in the kernel. By moving to chacha20, we have a single RNG to analyze and verify, and we also already get good performance improvements on all platforms. Implementation-wise, rather than use a generic buffer for both get_random_int/long and memcpy based on the size needs, we use a specific buffer for 32-bit reads and for 64-bit reads. This way, we're guaranteed to always have aligned accesses on all platforms. While slightly more verbose in C, the assembly this generates is a lot simpler than otherwise. Finally, on 32-bit platforms where longs and ints are the same size, we simply alias get_random_int to get_random_long. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Suggested-by: Theodore Ts'o <tytso@mit.edu> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-07 02:32:01 +08:00
unsigned int position;
};
/*
random: use chacha20 for get_random_int/long Now that our crng uses chacha20, we can rely on its speedy characteristics for replacing MD5, while simultaneously achieving a higher security guarantee. Before the idea was to use these functions if you wanted random integers that aren't stupidly insecure but aren't necessarily secure either, a vague gray zone, that hopefully was "good enough" for its users. With chacha20, we can strengthen this claim, since either we're using an rdrand-like instruction, or we're using the same crng as /dev/urandom. And it's faster than what was before. We could have chosen to replace this with a SipHash-derived function, which might be slightly faster, but at the cost of having yet another RNG construction in the kernel. By moving to chacha20, we have a single RNG to analyze and verify, and we also already get good performance improvements on all platforms. Implementation-wise, rather than use a generic buffer for both get_random_int/long and memcpy based on the size needs, we use a specific buffer for 32-bit reads and for 64-bit reads. This way, we're guaranteed to always have aligned accesses on all platforms. While slightly more verbose in C, the assembly this generates is a lot simpler than otherwise. Finally, on 32-bit platforms where longs and ints are the same size, we simply alias get_random_int to get_random_long. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Suggested-by: Theodore Ts'o <tytso@mit.edu> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-07 02:32:01 +08:00
* Get a random word for internal kernel use only. The quality of the random
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
* number is good as /dev/urandom. In order to ensure that the randomness
* provided by this function is okay, the function wait_for_random_bytes()
* should be called and return 0 at least once at any point prior.
*/
random: add a spinlock_t to struct batched_entropy The per-CPU variable batched_entropy_uXX is protected by get_cpu_var(). This is just a preempt_disable() which ensures that the variable is only from the local CPU. It does not protect against users on the same CPU from another context. It is possible that a preemptible context reads slot 0 and then an interrupt occurs and the same value is read again. The above scenario is confirmed by lockdep if we add a spinlock: | ================================ | WARNING: inconsistent lock state | 5.1.0-rc3+ #42 Not tainted | -------------------------------- | inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. | ksoftirqd/9/56 [HC0[0]:SC1[1]:HE0:SE0] takes: | (____ptrval____) (batched_entropy_u32.lock){+.?.}, at: get_random_u32+0x3e/0xe0 | {SOFTIRQ-ON-W} state was registered at: | _raw_spin_lock+0x2a/0x40 | get_random_u32+0x3e/0xe0 | new_slab+0x15c/0x7b0 | ___slab_alloc+0x492/0x620 | __slab_alloc.isra.73+0x53/0xa0 | kmem_cache_alloc_node+0xaf/0x2a0 | copy_process.part.41+0x1e1/0x2370 | _do_fork+0xdb/0x6d0 | kernel_thread+0x20/0x30 | kthreadd+0x1ba/0x220 | ret_from_fork+0x3a/0x50 … | other info that might help us debug this: | Possible unsafe locking scenario: | | CPU0 | ---- | lock(batched_entropy_u32.lock); | <Interrupt> | lock(batched_entropy_u32.lock); | | *** DEADLOCK *** | | stack backtrace: | Call Trace: … | kmem_cache_alloc_trace+0x20e/0x270 | ipmi_alloc_recv_msg+0x16/0x40 … | __do_softirq+0xec/0x48d | run_ksoftirqd+0x37/0x60 | smpboot_thread_fn+0x191/0x290 | kthread+0xfe/0x130 | ret_from_fork+0x3a/0x50 Add a spinlock_t to the batched_entropy data structure and acquire the lock while accessing it. Acquire the lock with disabled interrupts because this function may be used from interrupt context. Remove the batched_entropy_reset_lock lock. Now that we have a lock for the data scructure, we can access it from a remote CPU. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-04-20 12:09:51 +08:00
static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64) = {
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
.lock = INIT_LOCAL_LOCK(batched_entropy_u64.lock),
.position = UINT_MAX
random: add a spinlock_t to struct batched_entropy The per-CPU variable batched_entropy_uXX is protected by get_cpu_var(). This is just a preempt_disable() which ensures that the variable is only from the local CPU. It does not protect against users on the same CPU from another context. It is possible that a preemptible context reads slot 0 and then an interrupt occurs and the same value is read again. The above scenario is confirmed by lockdep if we add a spinlock: | ================================ | WARNING: inconsistent lock state | 5.1.0-rc3+ #42 Not tainted | -------------------------------- | inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. | ksoftirqd/9/56 [HC0[0]:SC1[1]:HE0:SE0] takes: | (____ptrval____) (batched_entropy_u32.lock){+.?.}, at: get_random_u32+0x3e/0xe0 | {SOFTIRQ-ON-W} state was registered at: | _raw_spin_lock+0x2a/0x40 | get_random_u32+0x3e/0xe0 | new_slab+0x15c/0x7b0 | ___slab_alloc+0x492/0x620 | __slab_alloc.isra.73+0x53/0xa0 | kmem_cache_alloc_node+0xaf/0x2a0 | copy_process.part.41+0x1e1/0x2370 | _do_fork+0xdb/0x6d0 | kernel_thread+0x20/0x30 | kthreadd+0x1ba/0x220 | ret_from_fork+0x3a/0x50 … | other info that might help us debug this: | Possible unsafe locking scenario: | | CPU0 | ---- | lock(batched_entropy_u32.lock); | <Interrupt> | lock(batched_entropy_u32.lock); | | *** DEADLOCK *** | | stack backtrace: | Call Trace: … | kmem_cache_alloc_trace+0x20e/0x270 | ipmi_alloc_recv_msg+0x16/0x40 … | __do_softirq+0xec/0x48d | run_ksoftirqd+0x37/0x60 | smpboot_thread_fn+0x191/0x290 | kthread+0xfe/0x130 | ret_from_fork+0x3a/0x50 Add a spinlock_t to the batched_entropy data structure and acquire the lock while accessing it. Acquire the lock with disabled interrupts because this function may be used from interrupt context. Remove the batched_entropy_reset_lock lock. Now that we have a lock for the data scructure, we can access it from a remote CPU. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-04-20 12:09:51 +08:00
};
u64 get_random_u64(void)
{
u64 ret;
random: add a spinlock_t to struct batched_entropy The per-CPU variable batched_entropy_uXX is protected by get_cpu_var(). This is just a preempt_disable() which ensures that the variable is only from the local CPU. It does not protect against users on the same CPU from another context. It is possible that a preemptible context reads slot 0 and then an interrupt occurs and the same value is read again. The above scenario is confirmed by lockdep if we add a spinlock: | ================================ | WARNING: inconsistent lock state | 5.1.0-rc3+ #42 Not tainted | -------------------------------- | inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. | ksoftirqd/9/56 [HC0[0]:SC1[1]:HE0:SE0] takes: | (____ptrval____) (batched_entropy_u32.lock){+.?.}, at: get_random_u32+0x3e/0xe0 | {SOFTIRQ-ON-W} state was registered at: | _raw_spin_lock+0x2a/0x40 | get_random_u32+0x3e/0xe0 | new_slab+0x15c/0x7b0 | ___slab_alloc+0x492/0x620 | __slab_alloc.isra.73+0x53/0xa0 | kmem_cache_alloc_node+0xaf/0x2a0 | copy_process.part.41+0x1e1/0x2370 | _do_fork+0xdb/0x6d0 | kernel_thread+0x20/0x30 | kthreadd+0x1ba/0x220 | ret_from_fork+0x3a/0x50 … | other info that might help us debug this: | Possible unsafe locking scenario: | | CPU0 | ---- | lock(batched_entropy_u32.lock); | <Interrupt> | lock(batched_entropy_u32.lock); | | *** DEADLOCK *** | | stack backtrace: | Call Trace: … | kmem_cache_alloc_trace+0x20e/0x270 | ipmi_alloc_recv_msg+0x16/0x40 … | __do_softirq+0xec/0x48d | run_ksoftirqd+0x37/0x60 | smpboot_thread_fn+0x191/0x290 | kthread+0xfe/0x130 | ret_from_fork+0x3a/0x50 Add a spinlock_t to the batched_entropy data structure and acquire the lock while accessing it. Acquire the lock with disabled interrupts because this function may be used from interrupt context. Remove the batched_entropy_reset_lock lock. Now that we have a lock for the data scructure, we can access it from a remote CPU. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-04-20 12:09:51 +08:00
unsigned long flags;
random: use chacha20 for get_random_int/long Now that our crng uses chacha20, we can rely on its speedy characteristics for replacing MD5, while simultaneously achieving a higher security guarantee. Before the idea was to use these functions if you wanted random integers that aren't stupidly insecure but aren't necessarily secure either, a vague gray zone, that hopefully was "good enough" for its users. With chacha20, we can strengthen this claim, since either we're using an rdrand-like instruction, or we're using the same crng as /dev/urandom. And it's faster than what was before. We could have chosen to replace this with a SipHash-derived function, which might be slightly faster, but at the cost of having yet another RNG construction in the kernel. By moving to chacha20, we have a single RNG to analyze and verify, and we also already get good performance improvements on all platforms. Implementation-wise, rather than use a generic buffer for both get_random_int/long and memcpy based on the size needs, we use a specific buffer for 32-bit reads and for 64-bit reads. This way, we're guaranteed to always have aligned accesses on all platforms. While slightly more verbose in C, the assembly this generates is a lot simpler than otherwise. Finally, on 32-bit platforms where longs and ints are the same size, we simply alias get_random_int to get_random_long. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Suggested-by: Theodore Ts'o <tytso@mit.edu> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-07 02:32:01 +08:00
struct batched_entropy *batch;
static void *previous;
unsigned long next_gen;
warn_unseeded_randomness(&previous);
local_lock_irqsave(&batched_entropy_u64.lock, flags);
random: add a spinlock_t to struct batched_entropy The per-CPU variable batched_entropy_uXX is protected by get_cpu_var(). This is just a preempt_disable() which ensures that the variable is only from the local CPU. It does not protect against users on the same CPU from another context. It is possible that a preemptible context reads slot 0 and then an interrupt occurs and the same value is read again. The above scenario is confirmed by lockdep if we add a spinlock: | ================================ | WARNING: inconsistent lock state | 5.1.0-rc3+ #42 Not tainted | -------------------------------- | inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. | ksoftirqd/9/56 [HC0[0]:SC1[1]:HE0:SE0] takes: | (____ptrval____) (batched_entropy_u32.lock){+.?.}, at: get_random_u32+0x3e/0xe0 | {SOFTIRQ-ON-W} state was registered at: | _raw_spin_lock+0x2a/0x40 | get_random_u32+0x3e/0xe0 | new_slab+0x15c/0x7b0 | ___slab_alloc+0x492/0x620 | __slab_alloc.isra.73+0x53/0xa0 | kmem_cache_alloc_node+0xaf/0x2a0 | copy_process.part.41+0x1e1/0x2370 | _do_fork+0xdb/0x6d0 | kernel_thread+0x20/0x30 | kthreadd+0x1ba/0x220 | ret_from_fork+0x3a/0x50 … | other info that might help us debug this: | Possible unsafe locking scenario: | | CPU0 | ---- | lock(batched_entropy_u32.lock); | <Interrupt> | lock(batched_entropy_u32.lock); | | *** DEADLOCK *** | | stack backtrace: | Call Trace: … | kmem_cache_alloc_trace+0x20e/0x270 | ipmi_alloc_recv_msg+0x16/0x40 … | __do_softirq+0xec/0x48d | run_ksoftirqd+0x37/0x60 | smpboot_thread_fn+0x191/0x290 | kthread+0xfe/0x130 | ret_from_fork+0x3a/0x50 Add a spinlock_t to the batched_entropy data structure and acquire the lock while accessing it. Acquire the lock with disabled interrupts because this function may be used from interrupt context. Remove the batched_entropy_reset_lock lock. Now that we have a lock for the data scructure, we can access it from a remote CPU. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-04-20 12:09:51 +08:00
batch = raw_cpu_ptr(&batched_entropy_u64);
next_gen = READ_ONCE(base_crng.generation);
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
if (batch->position >= ARRAY_SIZE(batch->entropy_u64) ||
next_gen != batch->generation) {
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
_get_random_bytes(batch->entropy_u64, sizeof(batch->entropy_u64));
random: use chacha20 for get_random_int/long Now that our crng uses chacha20, we can rely on its speedy characteristics for replacing MD5, while simultaneously achieving a higher security guarantee. Before the idea was to use these functions if you wanted random integers that aren't stupidly insecure but aren't necessarily secure either, a vague gray zone, that hopefully was "good enough" for its users. With chacha20, we can strengthen this claim, since either we're using an rdrand-like instruction, or we're using the same crng as /dev/urandom. And it's faster than what was before. We could have chosen to replace this with a SipHash-derived function, which might be slightly faster, but at the cost of having yet another RNG construction in the kernel. By moving to chacha20, we have a single RNG to analyze and verify, and we also already get good performance improvements on all platforms. Implementation-wise, rather than use a generic buffer for both get_random_int/long and memcpy based on the size needs, we use a specific buffer for 32-bit reads and for 64-bit reads. This way, we're guaranteed to always have aligned accesses on all platforms. While slightly more verbose in C, the assembly this generates is a lot simpler than otherwise. Finally, on 32-bit platforms where longs and ints are the same size, we simply alias get_random_int to get_random_long. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Suggested-by: Theodore Ts'o <tytso@mit.edu> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-07 02:32:01 +08:00
batch->position = 0;
batch->generation = next_gen;
random: use chacha20 for get_random_int/long Now that our crng uses chacha20, we can rely on its speedy characteristics for replacing MD5, while simultaneously achieving a higher security guarantee. Before the idea was to use these functions if you wanted random integers that aren't stupidly insecure but aren't necessarily secure either, a vague gray zone, that hopefully was "good enough" for its users. With chacha20, we can strengthen this claim, since either we're using an rdrand-like instruction, or we're using the same crng as /dev/urandom. And it's faster than what was before. We could have chosen to replace this with a SipHash-derived function, which might be slightly faster, but at the cost of having yet another RNG construction in the kernel. By moving to chacha20, we have a single RNG to analyze and verify, and we also already get good performance improvements on all platforms. Implementation-wise, rather than use a generic buffer for both get_random_int/long and memcpy based on the size needs, we use a specific buffer for 32-bit reads and for 64-bit reads. This way, we're guaranteed to always have aligned accesses on all platforms. While slightly more verbose in C, the assembly this generates is a lot simpler than otherwise. Finally, on 32-bit platforms where longs and ints are the same size, we simply alias get_random_int to get_random_long. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Suggested-by: Theodore Ts'o <tytso@mit.edu> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-07 02:32:01 +08:00
}
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
ret = batch->entropy_u64[batch->position];
batch->entropy_u64[batch->position] = 0;
++batch->position;
local_unlock_irqrestore(&batched_entropy_u64.lock, flags);
return ret;
}
EXPORT_SYMBOL(get_random_u64);
random: add a spinlock_t to struct batched_entropy The per-CPU variable batched_entropy_uXX is protected by get_cpu_var(). This is just a preempt_disable() which ensures that the variable is only from the local CPU. It does not protect against users on the same CPU from another context. It is possible that a preemptible context reads slot 0 and then an interrupt occurs and the same value is read again. The above scenario is confirmed by lockdep if we add a spinlock: | ================================ | WARNING: inconsistent lock state | 5.1.0-rc3+ #42 Not tainted | -------------------------------- | inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. | ksoftirqd/9/56 [HC0[0]:SC1[1]:HE0:SE0] takes: | (____ptrval____) (batched_entropy_u32.lock){+.?.}, at: get_random_u32+0x3e/0xe0 | {SOFTIRQ-ON-W} state was registered at: | _raw_spin_lock+0x2a/0x40 | get_random_u32+0x3e/0xe0 | new_slab+0x15c/0x7b0 | ___slab_alloc+0x492/0x620 | __slab_alloc.isra.73+0x53/0xa0 | kmem_cache_alloc_node+0xaf/0x2a0 | copy_process.part.41+0x1e1/0x2370 | _do_fork+0xdb/0x6d0 | kernel_thread+0x20/0x30 | kthreadd+0x1ba/0x220 | ret_from_fork+0x3a/0x50 … | other info that might help us debug this: | Possible unsafe locking scenario: | | CPU0 | ---- | lock(batched_entropy_u32.lock); | <Interrupt> | lock(batched_entropy_u32.lock); | | *** DEADLOCK *** | | stack backtrace: | Call Trace: … | kmem_cache_alloc_trace+0x20e/0x270 | ipmi_alloc_recv_msg+0x16/0x40 … | __do_softirq+0xec/0x48d | run_ksoftirqd+0x37/0x60 | smpboot_thread_fn+0x191/0x290 | kthread+0xfe/0x130 | ret_from_fork+0x3a/0x50 Add a spinlock_t to the batched_entropy data structure and acquire the lock while accessing it. Acquire the lock with disabled interrupts because this function may be used from interrupt context. Remove the batched_entropy_reset_lock lock. Now that we have a lock for the data scructure, we can access it from a remote CPU. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-04-20 12:09:51 +08:00
static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32) = {
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
.lock = INIT_LOCAL_LOCK(batched_entropy_u32.lock),
.position = UINT_MAX
random: add a spinlock_t to struct batched_entropy The per-CPU variable batched_entropy_uXX is protected by get_cpu_var(). This is just a preempt_disable() which ensures that the variable is only from the local CPU. It does not protect against users on the same CPU from another context. It is possible that a preemptible context reads slot 0 and then an interrupt occurs and the same value is read again. The above scenario is confirmed by lockdep if we add a spinlock: | ================================ | WARNING: inconsistent lock state | 5.1.0-rc3+ #42 Not tainted | -------------------------------- | inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. | ksoftirqd/9/56 [HC0[0]:SC1[1]:HE0:SE0] takes: | (____ptrval____) (batched_entropy_u32.lock){+.?.}, at: get_random_u32+0x3e/0xe0 | {SOFTIRQ-ON-W} state was registered at: | _raw_spin_lock+0x2a/0x40 | get_random_u32+0x3e/0xe0 | new_slab+0x15c/0x7b0 | ___slab_alloc+0x492/0x620 | __slab_alloc.isra.73+0x53/0xa0 | kmem_cache_alloc_node+0xaf/0x2a0 | copy_process.part.41+0x1e1/0x2370 | _do_fork+0xdb/0x6d0 | kernel_thread+0x20/0x30 | kthreadd+0x1ba/0x220 | ret_from_fork+0x3a/0x50 … | other info that might help us debug this: | Possible unsafe locking scenario: | | CPU0 | ---- | lock(batched_entropy_u32.lock); | <Interrupt> | lock(batched_entropy_u32.lock); | | *** DEADLOCK *** | | stack backtrace: | Call Trace: … | kmem_cache_alloc_trace+0x20e/0x270 | ipmi_alloc_recv_msg+0x16/0x40 … | __do_softirq+0xec/0x48d | run_ksoftirqd+0x37/0x60 | smpboot_thread_fn+0x191/0x290 | kthread+0xfe/0x130 | ret_from_fork+0x3a/0x50 Add a spinlock_t to the batched_entropy data structure and acquire the lock while accessing it. Acquire the lock with disabled interrupts because this function may be used from interrupt context. Remove the batched_entropy_reset_lock lock. Now that we have a lock for the data scructure, we can access it from a remote CPU. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-04-20 12:09:51 +08:00
};
u32 get_random_u32(void)
random: use chacha20 for get_random_int/long Now that our crng uses chacha20, we can rely on its speedy characteristics for replacing MD5, while simultaneously achieving a higher security guarantee. Before the idea was to use these functions if you wanted random integers that aren't stupidly insecure but aren't necessarily secure either, a vague gray zone, that hopefully was "good enough" for its users. With chacha20, we can strengthen this claim, since either we're using an rdrand-like instruction, or we're using the same crng as /dev/urandom. And it's faster than what was before. We could have chosen to replace this with a SipHash-derived function, which might be slightly faster, but at the cost of having yet another RNG construction in the kernel. By moving to chacha20, we have a single RNG to analyze and verify, and we also already get good performance improvements on all platforms. Implementation-wise, rather than use a generic buffer for both get_random_int/long and memcpy based on the size needs, we use a specific buffer for 32-bit reads and for 64-bit reads. This way, we're guaranteed to always have aligned accesses on all platforms. While slightly more verbose in C, the assembly this generates is a lot simpler than otherwise. Finally, on 32-bit platforms where longs and ints are the same size, we simply alias get_random_int to get_random_long. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Suggested-by: Theodore Ts'o <tytso@mit.edu> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-07 02:32:01 +08:00
{
u32 ret;
random: add a spinlock_t to struct batched_entropy The per-CPU variable batched_entropy_uXX is protected by get_cpu_var(). This is just a preempt_disable() which ensures that the variable is only from the local CPU. It does not protect against users on the same CPU from another context. It is possible that a preemptible context reads slot 0 and then an interrupt occurs and the same value is read again. The above scenario is confirmed by lockdep if we add a spinlock: | ================================ | WARNING: inconsistent lock state | 5.1.0-rc3+ #42 Not tainted | -------------------------------- | inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. | ksoftirqd/9/56 [HC0[0]:SC1[1]:HE0:SE0] takes: | (____ptrval____) (batched_entropy_u32.lock){+.?.}, at: get_random_u32+0x3e/0xe0 | {SOFTIRQ-ON-W} state was registered at: | _raw_spin_lock+0x2a/0x40 | get_random_u32+0x3e/0xe0 | new_slab+0x15c/0x7b0 | ___slab_alloc+0x492/0x620 | __slab_alloc.isra.73+0x53/0xa0 | kmem_cache_alloc_node+0xaf/0x2a0 | copy_process.part.41+0x1e1/0x2370 | _do_fork+0xdb/0x6d0 | kernel_thread+0x20/0x30 | kthreadd+0x1ba/0x220 | ret_from_fork+0x3a/0x50 … | other info that might help us debug this: | Possible unsafe locking scenario: | | CPU0 | ---- | lock(batched_entropy_u32.lock); | <Interrupt> | lock(batched_entropy_u32.lock); | | *** DEADLOCK *** | | stack backtrace: | Call Trace: … | kmem_cache_alloc_trace+0x20e/0x270 | ipmi_alloc_recv_msg+0x16/0x40 … | __do_softirq+0xec/0x48d | run_ksoftirqd+0x37/0x60 | smpboot_thread_fn+0x191/0x290 | kthread+0xfe/0x130 | ret_from_fork+0x3a/0x50 Add a spinlock_t to the batched_entropy data structure and acquire the lock while accessing it. Acquire the lock with disabled interrupts because this function may be used from interrupt context. Remove the batched_entropy_reset_lock lock. Now that we have a lock for the data scructure, we can access it from a remote CPU. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-04-20 12:09:51 +08:00
unsigned long flags;
random: use chacha20 for get_random_int/long Now that our crng uses chacha20, we can rely on its speedy characteristics for replacing MD5, while simultaneously achieving a higher security guarantee. Before the idea was to use these functions if you wanted random integers that aren't stupidly insecure but aren't necessarily secure either, a vague gray zone, that hopefully was "good enough" for its users. With chacha20, we can strengthen this claim, since either we're using an rdrand-like instruction, or we're using the same crng as /dev/urandom. And it's faster than what was before. We could have chosen to replace this with a SipHash-derived function, which might be slightly faster, but at the cost of having yet another RNG construction in the kernel. By moving to chacha20, we have a single RNG to analyze and verify, and we also already get good performance improvements on all platforms. Implementation-wise, rather than use a generic buffer for both get_random_int/long and memcpy based on the size needs, we use a specific buffer for 32-bit reads and for 64-bit reads. This way, we're guaranteed to always have aligned accesses on all platforms. While slightly more verbose in C, the assembly this generates is a lot simpler than otherwise. Finally, on 32-bit platforms where longs and ints are the same size, we simply alias get_random_int to get_random_long. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Suggested-by: Theodore Ts'o <tytso@mit.edu> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-07 02:32:01 +08:00
struct batched_entropy *batch;
static void *previous;
unsigned long next_gen;
drivers: char: random: add get_random_long() Commit d07e22597d1d ("mm: mmap: add new /proc tunable for mmap_base ASLR") added the ability to choose from a range of values to use for entropy count in generating the random offset to the mmap_base address. The maximum value on this range was set to 32 bits for 64-bit x86 systems, but this value could be increased further, requiring more than the 32 bits of randomness provided by get_random_int(), as is already possible for arm64. Add a new function: get_random_long() which more naturally fits with the mmap usage of get_random_int() but operates exactly the same as get_random_int(). Also, fix the shifting constant in mmap_rnd() to be an unsigned long so that values greater than 31 bits generate an appropriate mask without overflow. This is especially important on x86, as its shift instruction uses a 5-bit mask for the shift operand, which meant that any value for mmap_rnd_bits over 31 acts as a no-op and effectively disables mmap_base randomization. Finally, replace calls to get_random_int() with get_random_long() where appropriate. This patch (of 2): Add get_random_long(). Signed-off-by: Daniel Cashman <dcashman@android.com> Acked-by: Kees Cook <keescook@chromium.org> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: David S. Miller <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Nick Kralevich <nnk@google.com> Cc: Jeff Vander Stoep <jeffv@google.com> Cc: Mark Salyzyn <salyzyn@android.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-02-27 07:19:34 +08:00
warn_unseeded_randomness(&previous);
local_lock_irqsave(&batched_entropy_u32.lock, flags);
random: add a spinlock_t to struct batched_entropy The per-CPU variable batched_entropy_uXX is protected by get_cpu_var(). This is just a preempt_disable() which ensures that the variable is only from the local CPU. It does not protect against users on the same CPU from another context. It is possible that a preemptible context reads slot 0 and then an interrupt occurs and the same value is read again. The above scenario is confirmed by lockdep if we add a spinlock: | ================================ | WARNING: inconsistent lock state | 5.1.0-rc3+ #42 Not tainted | -------------------------------- | inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. | ksoftirqd/9/56 [HC0[0]:SC1[1]:HE0:SE0] takes: | (____ptrval____) (batched_entropy_u32.lock){+.?.}, at: get_random_u32+0x3e/0xe0 | {SOFTIRQ-ON-W} state was registered at: | _raw_spin_lock+0x2a/0x40 | get_random_u32+0x3e/0xe0 | new_slab+0x15c/0x7b0 | ___slab_alloc+0x492/0x620 | __slab_alloc.isra.73+0x53/0xa0 | kmem_cache_alloc_node+0xaf/0x2a0 | copy_process.part.41+0x1e1/0x2370 | _do_fork+0xdb/0x6d0 | kernel_thread+0x20/0x30 | kthreadd+0x1ba/0x220 | ret_from_fork+0x3a/0x50 … | other info that might help us debug this: | Possible unsafe locking scenario: | | CPU0 | ---- | lock(batched_entropy_u32.lock); | <Interrupt> | lock(batched_entropy_u32.lock); | | *** DEADLOCK *** | | stack backtrace: | Call Trace: … | kmem_cache_alloc_trace+0x20e/0x270 | ipmi_alloc_recv_msg+0x16/0x40 … | __do_softirq+0xec/0x48d | run_ksoftirqd+0x37/0x60 | smpboot_thread_fn+0x191/0x290 | kthread+0xfe/0x130 | ret_from_fork+0x3a/0x50 Add a spinlock_t to the batched_entropy data structure and acquire the lock while accessing it. Acquire the lock with disabled interrupts because this function may be used from interrupt context. Remove the batched_entropy_reset_lock lock. Now that we have a lock for the data scructure, we can access it from a remote CPU. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-04-20 12:09:51 +08:00
batch = raw_cpu_ptr(&batched_entropy_u32);
next_gen = READ_ONCE(base_crng.generation);
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
if (batch->position >= ARRAY_SIZE(batch->entropy_u32) ||
next_gen != batch->generation) {
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
_get_random_bytes(batch->entropy_u32, sizeof(batch->entropy_u32));
random: use chacha20 for get_random_int/long Now that our crng uses chacha20, we can rely on its speedy characteristics for replacing MD5, while simultaneously achieving a higher security guarantee. Before the idea was to use these functions if you wanted random integers that aren't stupidly insecure but aren't necessarily secure either, a vague gray zone, that hopefully was "good enough" for its users. With chacha20, we can strengthen this claim, since either we're using an rdrand-like instruction, or we're using the same crng as /dev/urandom. And it's faster than what was before. We could have chosen to replace this with a SipHash-derived function, which might be slightly faster, but at the cost of having yet another RNG construction in the kernel. By moving to chacha20, we have a single RNG to analyze and verify, and we also already get good performance improvements on all platforms. Implementation-wise, rather than use a generic buffer for both get_random_int/long and memcpy based on the size needs, we use a specific buffer for 32-bit reads and for 64-bit reads. This way, we're guaranteed to always have aligned accesses on all platforms. While slightly more verbose in C, the assembly this generates is a lot simpler than otherwise. Finally, on 32-bit platforms where longs and ints are the same size, we simply alias get_random_int to get_random_long. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Suggested-by: Theodore Ts'o <tytso@mit.edu> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-07 02:32:01 +08:00
batch->position = 0;
batch->generation = next_gen;
random: use chacha20 for get_random_int/long Now that our crng uses chacha20, we can rely on its speedy characteristics for replacing MD5, while simultaneously achieving a higher security guarantee. Before the idea was to use these functions if you wanted random integers that aren't stupidly insecure but aren't necessarily secure either, a vague gray zone, that hopefully was "good enough" for its users. With chacha20, we can strengthen this claim, since either we're using an rdrand-like instruction, or we're using the same crng as /dev/urandom. And it's faster than what was before. We could have chosen to replace this with a SipHash-derived function, which might be slightly faster, but at the cost of having yet another RNG construction in the kernel. By moving to chacha20, we have a single RNG to analyze and verify, and we also already get good performance improvements on all platforms. Implementation-wise, rather than use a generic buffer for both get_random_int/long and memcpy based on the size needs, we use a specific buffer for 32-bit reads and for 64-bit reads. This way, we're guaranteed to always have aligned accesses on all platforms. While slightly more verbose in C, the assembly this generates is a lot simpler than otherwise. Finally, on 32-bit platforms where longs and ints are the same size, we simply alias get_random_int to get_random_long. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Suggested-by: Theodore Ts'o <tytso@mit.edu> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-07 02:32:01 +08:00
}
random: use simpler fast key erasure flow on per-cpu keys Rather than the clunky NUMA full ChaCha state system we had prior, this commit is closer to the original "fast key erasure RNG" proposal from <https://blog.cr.yp.to/20170723-random.html>, by simply treating ChaCha keys on a per-cpu basis. All entropy is extracted to a base crng key of 32 bytes. This base crng has a birthdate and a generation counter. When we go to take bytes from the crng, we first check if the birthdate is too old; if it is, we reseed per usual. Then we start working on a per-cpu crng. This per-cpu crng makes sure that it has the same generation counter as the base crng. If it doesn't, it does fast key erasure with the base crng key and uses the output as its new per-cpu key, and then updates its local generation counter. Then, using this per-cpu state, we do ordinary fast key erasure. Half of this first block is used to overwrite the per-cpu crng key for the next call -- this is the fast key erasure RNG idea -- and the other half, along with the ChaCha state, is returned to the caller. If the caller desires more than this remaining half, it can generate more ChaCha blocks, unlocked, using the now detached ChaCha state that was just returned. Crypto-wise, this is more or less what we were doing before, but this simply makes it more explicit and ensures that we always have backtrack protection by not playing games with a shared block counter. The flow looks like this: ──extract()──► base_crng.key ◄──memcpy()───┐ │ │ └──chacha()──────┬─► new_base_key └─► crngs[n].key ◄──memcpy()───┐ │ │ └──chacha()───┬─► new_key └─► random_bytes │ └────► There are a few hairy details around early init. Just as was done before, prior to having gathered enough entropy, crng_fast_load() and crng_slow_load() dump bytes directly into the base crng, and when we go to take bytes from the crng, in that case, we're doing fast key erasure with the base crng rather than the fast unlocked per-cpu crngs. This is fine as that's only the state of affairs during very early boot; once the crng initializes we never use these paths again. In the process of all this, the APIs into the crng become a bit simpler: we have get_random_bytes(buf, len) and get_random_bytes_user(buf, len), which both do what you'd expect. All of the details of fast key erasure and per-cpu selection happen only in a very short critical section of crng_make_state(), which selects the right per-cpu key, does the fast key erasure, and returns a local state to the caller's stack. So, we no longer have a need for a separate backtrack function, as this happens all at once here. The API then allows us to extend backtrack protection to batched entropy without really having to do much at all. The result is a bit simpler than before and has fewer foot guns. The init time state machine also gets a lot simpler as we don't need to wait for workqueues to come online and do deferred work. And the multi-core performance should be increased significantly, by virtue of having hardly any locking on the fast path. Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-02-07 22:08:49 +08:00
ret = batch->entropy_u32[batch->position];
batch->entropy_u32[batch->position] = 0;
++batch->position;
local_unlock_irqrestore(&batched_entropy_u32.lock, flags);
drivers: char: random: add get_random_long() Commit d07e22597d1d ("mm: mmap: add new /proc tunable for mmap_base ASLR") added the ability to choose from a range of values to use for entropy count in generating the random offset to the mmap_base address. The maximum value on this range was set to 32 bits for 64-bit x86 systems, but this value could be increased further, requiring more than the 32 bits of randomness provided by get_random_int(), as is already possible for arm64. Add a new function: get_random_long() which more naturally fits with the mmap usage of get_random_int() but operates exactly the same as get_random_int(). Also, fix the shifting constant in mmap_rnd() to be an unsigned long so that values greater than 31 bits generate an appropriate mask without overflow. This is especially important on x86, as its shift instruction uses a 5-bit mask for the shift operand, which meant that any value for mmap_rnd_bits over 31 acts as a no-op and effectively disables mmap_base randomization. Finally, replace calls to get_random_int() with get_random_long() where appropriate. This patch (of 2): Add get_random_long(). Signed-off-by: Daniel Cashman <dcashman@android.com> Acked-by: Kees Cook <keescook@chromium.org> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: David S. Miller <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Nick Kralevich <nnk@google.com> Cc: Jeff Vander Stoep <jeffv@google.com> Cc: Mark Salyzyn <salyzyn@android.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-02-27 07:19:34 +08:00
return ret;
}
EXPORT_SYMBOL(get_random_u32);
drivers: char: random: add get_random_long() Commit d07e22597d1d ("mm: mmap: add new /proc tunable for mmap_base ASLR") added the ability to choose from a range of values to use for entropy count in generating the random offset to the mmap_base address. The maximum value on this range was set to 32 bits for 64-bit x86 systems, but this value could be increased further, requiring more than the 32 bits of randomness provided by get_random_int(), as is already possible for arm64. Add a new function: get_random_long() which more naturally fits with the mmap usage of get_random_int() but operates exactly the same as get_random_int(). Also, fix the shifting constant in mmap_rnd() to be an unsigned long so that values greater than 31 bits generate an appropriate mask without overflow. This is especially important on x86, as its shift instruction uses a 5-bit mask for the shift operand, which meant that any value for mmap_rnd_bits over 31 acts as a no-op and effectively disables mmap_base randomization. Finally, replace calls to get_random_int() with get_random_long() where appropriate. This patch (of 2): Add get_random_long(). Signed-off-by: Daniel Cashman <dcashman@android.com> Acked-by: Kees Cook <keescook@chromium.org> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: David S. Miller <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Nick Kralevich <nnk@google.com> Cc: Jeff Vander Stoep <jeffv@google.com> Cc: Mark Salyzyn <salyzyn@android.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-02-27 07:19:34 +08:00
random: simplify API for random address requests To date, all callers of randomize_range() have set the length to 0, and check for a zero return value. For the current callers, the only way to get zero returned is if end <= start. Since they are all adding a constant to the start address, this is unnecessary. We can remove a bunch of needless checks by simplifying the API to do just what everyone wants, return an address between [start, start + range). While we're here, s/get_random_int/get_random_long/. No current call site is adversely affected by get_random_int(), since all current range requests are < UINT_MAX. However, we should match caller expectations to avoid coming up short (ha!) in the future. All current callers to randomize_range() chose to use the start address if randomize_range() failed. Therefore, we simplify things by just returning the start address on error. randomize_range() will be removed once all callers have been converted over to randomize_addr(). Link: http://lkml.kernel.org/r/20160803233913.32511-2-jason@lakedaemon.net Signed-off-by: Jason Cooper <jason@lakedaemon.net> Acked-by: Kees Cook <keescook@chromium.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: "Roberts, William C" <william.c.roberts@intel.com> Cc: Yann Droneaud <ydroneaud@opteya.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Nick Kralevich <nnk@google.com> Cc: Jeffrey Vander Stoep <jeffv@google.com> Cc: Daniel Cashman <dcashman@android.com> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-12 04:53:52 +08:00
/**
* 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)
random: simplify API for random address requests To date, all callers of randomize_range() have set the length to 0, and check for a zero return value. For the current callers, the only way to get zero returned is if end <= start. Since they are all adding a constant to the start address, this is unnecessary. We can remove a bunch of needless checks by simplifying the API to do just what everyone wants, return an address between [start, start + range). While we're here, s/get_random_int/get_random_long/. No current call site is adversely affected by get_random_int(), since all current range requests are < UINT_MAX. However, we should match caller expectations to avoid coming up short (ha!) in the future. All current callers to randomize_range() chose to use the start address if randomize_range() failed. Therefore, we simplify things by just returning the start address on error. randomize_range() will be removed once all callers have been converted over to randomize_addr(). Link: http://lkml.kernel.org/r/20160803233913.32511-2-jason@lakedaemon.net Signed-off-by: Jason Cooper <jason@lakedaemon.net> Acked-by: Kees Cook <keescook@chromium.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: "Roberts, William C" <william.c.roberts@intel.com> Cc: Yann Droneaud <ydroneaud@opteya.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Nick Kralevich <nnk@google.com> Cc: Jeffrey Vander Stoep <jeffv@google.com> Cc: Daniel Cashman <dcashman@android.com> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-12 04:53:52 +08:00
{
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 void *buffer, size_t count,
size_t entropy)
{
if (unlikely(crng_init == 0)) {
size_t ret = crng_fast_load(buffer, count);
mix_pool_bytes(buffer, ret);
count -= ret;
buffer += ret;
if (!count || crng_init == 0)
return;
}
/* Throttle writing if we're above the trickle threshold.
* We'll be woken up again once below POOL_MIN_BITS, when
* the calling thread is about to terminate, or once
* CRNG_RESEED_INTERVAL has elapsed.
*/
wait_event_interruptible_timeout(random_write_wait,
random: fix crash on multiple early calls to add_bootloader_randomness() Currently, if CONFIG_RANDOM_TRUST_BOOTLOADER is enabled, multiple calls to add_bootloader_randomness() are broken and can cause a NULL pointer dereference, as noted by Ivan T. Ivanov. This is not only a hypothetical problem, as qemu on arm64 may provide bootloader entropy via EFI and via devicetree. On the first call to add_hwgenerator_randomness(), crng_fast_load() is executed, and if the seed is long enough, crng_init will be set to 1. On subsequent calls to add_bootloader_randomness() and then to add_hwgenerator_randomness(), crng_fast_load() will be skipped. Instead, wait_event_interruptible() and then credit_entropy_bits() will be called. If the entropy count for that second seed is large enough, that proceeds to crng_reseed(). However, both wait_event_interruptible() and crng_reseed() depends (at least in numa_crng_init()) on workqueues. Therefore, test whether system_wq is already initialized, which is a sufficient indicator that workqueue_init_early() has progressed far enough. If we wind up hitting the !system_wq case, we later want to do what would have been done there when wqs are up, so set a flag, and do that work later from the rand_initialize() call. Reported-by: Ivan T. Ivanov <iivanov@suse.de> Fixes: 18b915ac6b0a ("efi/random: Treat EFI_RNG_PROTOCOL output as bootloader randomness") Cc: stable@vger.kernel.org Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net> [Jason: added crng_need_done state and related logic.] Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2021-12-30 05:10:03 +08:00
!system_wq || kthread_should_stop() ||
input_pool.entropy_count < POOL_MIN_BITS,
CRNG_RESEED_INTERVAL);
mix_pool_bytes(buffer, count);
credit_entropy_bits(entropy);
}
EXPORT_SYMBOL_GPL(add_hwgenerator_randomness);
/* Handle random seed passed by bootloader.
* If the seed is trustworthy, it would be regarded as hardware RNGs. Otherwise
* it would be regarded as device data.
* The decision is controlled by CONFIG_RANDOM_TRUST_BOOTLOADER.
*/
void add_bootloader_randomness(const void *buf, size_t size)
{
if (IS_ENABLED(CONFIG_RANDOM_TRUST_BOOTLOADER))
add_hwgenerator_randomness(buf, size, size * 8);
else
add_device_randomness(buf, size);
}
EXPORT_SYMBOL_GPL(add_bootloader_randomness);