Merge tag 'random-5.18-rc1-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/crng/random

Pull random number generator updates from Jason Donenfeld:
 "There have been a few important changes to the RNG's crypto, but the
  intent for 5.18 has been to shore up the existing design as much as
  possible with modern cryptographic functions and proven constructions,
  rather than actually changing up anything fundamental to the RNG's
  design.

  So it's still the same old RNG at its core as before: it still counts
  entropy bits, and collects from the various sources with the same
  heuristics as before, and so forth. However, the cryptographic
  algorithms that transform that entropic data into safe random numbers
  have been modernized.

  Just as important, if not more, is that the code has been cleaned up
  and re-documented. As one of the first drivers in Linux, going back to
  1.3.30, its general style and organization was showing its age and
  becoming both a maintenance burden and an auditability impediment.

  Hopefully this provides a more solid foundation to build on for the
  future. I encourage you to open up the file in full, and maybe you'll
  remark, "oh, that's what it's doing," and enjoy reading it. That, at
  least, is the eventual goal, which this pull begins working toward.

  Here's a summary of the various patches in this pull:

   - /dev/urandom and /dev/random now do the same thing, per the patch
     we discussed on the list. I think this is worth trying out. If it
     does appear problematic, I've made sure to keep it standalone and
     revertible without any conflicts.

   - Fixes and cleanups for numerous integer type problems, locking
     issues, and general code quality concerns.

   - The input pool's LFSR has been replaced with a cryptographically
     secure hash function, which has security and performance benefits
     alike, and consequently allows us to count entropy bits linearly.

   - The pre-init injection now uses a real hash function too, instead
     of an LFSR or vanilla xor.

   - The interrupt handler's fast_mix() function now uses one round of
     SipHash, rather than the fake crypto that was there before.

   - All additions of RDRAND and RDSEED now go through the input pool's
     hash function, in part to mitigate ridiculous hypothetical CPU
     backdoors, but more so to have a consistent interface for ingesting
     entropy that's easy to analyze, making everything happen one way,
     instead of a potpourri of different ways.

   - The crng now works on per-cpu data, while also being in accordance
     with the actual "fast key erasure RNG" design. This allows us to
     fix several boot-time race complications associated with the prior
     dynamically allocated model, eliminates much locking, and makes our
     backtrack protection more robust.

   - Batched entropy now erases doled out values so that it's backtrack
     resistant.

   - Working closely with Sebastian, the interrupt handler no longer
     needs to take any locks at all, as we punt the
     synchronized/expensive operations to a workqueue. This is
     especially nice for PREEMPT_RT, where taking spinlocks in irq
     context is problematic. It also makes the handler faster for the
     rest of us.

   - Also working with Sebastian, we now do the right thing on CPU
     hotplug, so that we don't use stale entropy or fail to accumulate
     new entropy when CPUs come back online.

   - We handle virtual machines that fork / clone / snapshot, using the
     "vmgenid" ACPI specification for retrieving a unique new RNG seed,
     which we can use to also make WireGuard (and in the future, other
     things) safe across VM forks.

   - Around boot time, we now try to reseed more often if enough entropy
     is available, before settling on the usual 5 minute schedule.

   - Last, but certainly not least, the documentation in the file has
     been updated considerably"

* tag 'random-5.18-rc1-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/crng/random: (60 commits)
  random: check for signal and try earlier when generating entropy
  random: reseed more often immediately after booting
  random: make consistent usage of crng_ready()
  random: use SipHash as interrupt entropy accumulator
  wireguard: device: clear keys on VM fork
  random: provide notifier for VM fork
  random: replace custom notifier chain with standard one
  random: do not export add_vmfork_randomness() unless needed
  virt: vmgenid: notify RNG of VM fork and supply generation ID
  ACPI: allow longer device IDs
  random: add mechanism for VM forks to reinitialize crng
  random: don't let 644 read-only sysctls be written to
  random: give sysctl_random_min_urandom_seed a more sensible value
  random: block in /dev/urandom
  random: do crng pre-init loading in worker rather than irq
  random: unify cycles_t and jiffies usage and types
  random: cleanup UUID handling
  random: only wake up writers after zap if threshold was passed
  random: round-robin registers as ulong, not u32
  random: clear fast pool, crng, and batches in cpuhp bring up
  ...

17 files changed, 1371 insertions, 1959 deletions

diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index d359bcfadd39..5dd660aac0ae 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -1029,23 +1029,17 @@ This is a directory, with the following entries:
 * ``poolsize``: the entropy pool size, in bits;
 
 * ``urandom_min_reseed_secs``: obsolete (used to determine the minimum
-  number of seconds between urandom pool reseeding).
+  number of seconds between urandom pool reseeding). This file is
+  writable for compatibility purposes, but writing to it has no effect
+  on any RNG behavior.
 
 * ``uuid``: a UUID generated every time this is retrieved (this can
   thus be used to generate UUIDs at will);
 
 * ``write_wakeup_threshold``: when the entropy count drops below this
   (as a number of bits), processes waiting to write to ``/dev/random``
-  are woken up.
-
-If ``drivers/char/random.c`` is built with ``ADD_INTERRUPT_BENCH``
-defined, these additional entries are present:
-
-* ``add_interrupt_avg_cycles``: the average number of cycles between
-  interrupts used to feed the pool;
-
-* ``add_interrupt_avg_deviation``: the standard deviation seen on the
-  number of cycles between interrupts used to feed the pool.
+  are woken up. This file is writable for compatibility purposes, but
+  writing to it has no effect on any RNG behavior.
 
 
 randomize_va_space
diff --git a/MAINTAINERS b/MAINTAINERS
index ac4508914b3a..7940c41f65d5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16213,6 +16213,7 @@ M:	Jason A. Donenfeld <Jason@zx2c4.com>
 T:	git https://git.kernel.org/pub/scm/linux/kernel/git/crng/random.git
 S:	Maintained
 F:	drivers/char/random.c
+F:	drivers/virt/vmgenid.c
 
 RAPIDIO SUBSYSTEM
 M:	Matt Porter <mporter@kernel.crashing.org>
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index a3db27916256..cfb085de876b 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -15,6 +15,7 @@
 #include <linux/err.h>
 #include <linux/fs.h>
 #include <linux/hw_random.h>
+#include <linux/random.h>
 #include <linux/kernel.h>
 #include <linux/kthread.h>
 #include <linux/sched/signal.h>
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index cc296f0823bd..9f586025dbe6 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -707,7 +707,7 @@ static const struct memdev {
 	 [5] = { "zero", 0666, &zero_fops, FMODE_NOWAIT },
 	 [7] = { "full", 0666, &full_fops, 0 },
 	 [8] = { "random", 0666, &random_fops, 0 },
-	 [9] = { "urandom", 0666, &urandom_fops, 0 },
+	 [9] = { "urandom", 0666, &random_fops, 0 },
 #ifdef CONFIG_PRINTK
 	[11] = { "kmsg", 0644, &kmsg_fops, 0 },
 #endif
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 3404a91edf29..0bdefada7453 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1,320 +1,28 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
 /*
- * random.c -- A strong random number generator
- *
  * 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.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, and the entire permission notice in its entirety,
- *    including the disclaimer of warranties.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. The name of the author may not be used to endorse or promote
- *    products derived from this software without specific prior
- *    written permission.
- *
- * ALTERNATIVELY, this product may be distributed under the terms of
- * the GNU General Public License, in which case the provisions of the GPL are
- * required INSTEAD OF the above restrictions.  (This clause is
- * necessary due to a potential bad interaction between the GPL and
- * the restrictions contained in a BSD-style copyright.)
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
- * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE, ALL OF
- * WHICH ARE HEREBY DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT
- * OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
- * USE OF THIS SOFTWARE, EVEN IF NOT ADVISED OF THE POSSIBILITY OF SUCH
- * DAMAGE.
- */
-
-/*
- * (now, with legal B.S. out of the way.....)
- *
- * This routine gathers environmental noise from device drivers, etc.,
- * and returns good random numbers, suitable for cryptographic use.
- * Besides the obvious cryptographic uses, these numbers are also good
- * for seeding TCP sequence numbers, and other places where it is
- * desirable to have numbers which are not only random, but hard to
- * predict by an attacker.
- *
- * Theory of operation
- * ===================
- *
- * Computers are very predictable devices.  Hence it is extremely hard
- * to produce truly random numbers on a computer --- as opposed to
- * pseudo-random numbers, which can easily generated by using a
- * algorithm.  Unfortunately, it is very easy for attackers to guess
- * the sequence of pseudo-random number generators, and for some
- * applications this is not acceptable.  So instead, we must try to
- * gather "environmental noise" from the computer's environment, which
- * must be hard for outside attackers to observe, and use that to
- * generate random numbers.  In a Unix environment, this is best done
- * from inside the kernel.
- *
- * Sources of randomness from the environment include inter-keyboard
- * timings, inter-interrupt timings from some interrupts, and other
- * events which are both (a) non-deterministic and (b) hard for an
- * outside observer to measure.  Randomness from these sources are
- * added to an "entropy pool", which is mixed using a CRC-like function.
- * This is not cryptographically strong, but it is adequate assuming
- * the randomness is not chosen maliciously, and it is fast enough that
- * the overhead of doing it on every interrupt is very reasonable.
- * As random bytes are mixed into the entropy pool, the routines keep
- * an *estimate* of how many bits of randomness have been stored into
- * the random number generator's internal state.
- *
- * When random bytes are desired, they are obtained by taking the BLAKE2s
- * hash of the contents of the "entropy pool".  The BLAKE2s hash avoids
- * exposing the internal state of the entropy pool.  It is believed to
- * be computationally infeasible to derive any useful information
- * about the input of BLAKE2s from its output.  Even if it is possible to
- * analyze BLAKE2s in some clever way, as long as the amount of data
- * returned from the generator is less than the inherent entropy in
- * the pool, the output data is totally unpredictable.  For this
- * reason, the routine decreases its internal estimate of how many
- * bits of "true randomness" are contained in the entropy pool as it
- * outputs random numbers.
- *
- * If this estimate goes to zero, the routine can still generate
- * random numbers; however, an attacker may (at least in theory) be
- * able to infer the future output of the generator from prior
- * outputs.  This requires successful cryptanalysis of BLAKE2s, which is
- * not believed to be feasible, but there is a remote possibility.
- * Nonetheless, these numbers should be useful for the vast majority
- * of purposes.
- *
- * 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
- * --------------------------------------
- *
- * The primary kernel interface is
- *
- *	void get_random_bytes(void *buf, int nbytes);
- *
- * This interface will return the requested number of random bytes,
- * and place it in the requested buffer.  This is equivalent to a
- * read from /dev/urandom.
- *
- * For less critical applications, there are the functions:
- *
- *	u32 get_random_u32()
- *	u64 get_random_u64()
- *	unsigned int get_random_int()
- *	unsigned long get_random_long()
- *
- * These are produced by a cryptographic RNG seeded from get_random_bytes,
- * and so do not deplete the entropy pool as much.  These are recommended
- * for most in-kernel operations *if the result is going to be stored in
- * the kernel*.
- *
- * Specifically, the get_random_int() family do not attempt to do
- * "anti-backtracking".  If you capture the state of the kernel (e.g.
- * by snapshotting the VM), you can figure out previous get_random_int()
- * return values.  But if the value is stored in the kernel anyway,
- * this is not a problem.
- *
- * It *is* safe to expose get_random_int() output to attackers (e.g. as
- * network cookies); given outputs 1..n, it's not feasible to predict
- * outputs 0 or n+1.  The only concern is an attacker who breaks into
- * the kernel later; the get_random_int() engine is not reseeded as
- * often as the get_random_bytes() one.
- *
- * get_random_bytes() is needed for keys that need to stay secret after
- * they are erased from the kernel.  For example, any key that will
- * be wrapped and stored encrypted.  And session encryption keys: we'd
- * like to know that after the session is closed and the keys erased,
- * the plaintext is unrecoverable to someone who recorded the ciphertext.
- *
- * But for network ports/cookies, stack canaries, PRNG seeds, address
- * space layout randomization, session *authentication* keys, or other
- * applications where the sensitive data is stored in the kernel in
- * plaintext for as long as it's sensitive, the get_random_int() family
- * is just fine.
- *
- * Consider ASLR.  We want to keep the address space secret from an
- * outside attacker while the process is running, but once the address
- * space is torn down, it's of no use to an attacker any more.  And it's
- * stored in kernel data structures as long as it's alive, so worrying
- * about an attacker's ability to extrapolate it from the get_random_int()
- * CRNG is silly.
- *
- * Even some cryptographic keys are safe to generate with get_random_int().
- * In particular, keys for SipHash are generally fine.  Here, knowledge
- * of the key authorizes you to do something to a kernel object (inject
- * packets to a network connection, or flood a hash table), and the
- * key is stored with the object being protected.  Once it goes away,
- * we no longer care if anyone knows the key.
- *
- * 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, unsigned int 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 char *buffer, size_t count,
- *					size_t entropy);
- *	void add_bootloader_randomness(const void *buf, unsigned int size);
- *
- * add_device_randomness() is for adding data to the random pool that
- * is likely to differ between two devices (or possibly even per boot).
- * 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
- *
- * Acknowledgements:
- * =================
- *
- * Ideas for constructing this random number generator were derived
- * from Pretty Good Privacy's random number generator, and from private
- * discussions with Phil Karn.  Colin Plumb provided a faster random
- * number generator, which speed up the mixing function of the entropy
- * pool, taken from PGPfone.  Dale Worley has also contributed many
- * useful ideas and suggestions to improve this driver.
- *
- * Any flaws in the design are solely my responsibility, and should
- * not be attributed to the Phil, Colin, or any of authors of PGP.
- *
- * Further background information on this topic may be obtained from
- * RFC 1750, "Randomness Recommendations for Security", by Donald
- * Eastlake, Steve Crocker, and Jeff Schiller.
+ * Copyright Theodore Ts'o, 1994, 1995, 1996, 1997, 1998, 1999. All rights reserved.
+ *
+ * This driver produces cryptographically secure pseudorandom data. It is divided
+ * into roughly six sections, each with a section header:
+ *
+ *   - Initialization and readiness waiting.
+ *   - Fast key erasure RNG, the "crng".
+ *   - Entropy accumulation and extraction routines.
+ *   - Entropy collection routines.
+ *   - Userspace reader/writer interfaces.
+ *   - Sysctl interface.
+ *
+ * The high level overview is that there is one input pool, into which
+ * various pieces of data are hashed. Some of that data is then "credited" as
+ * having a certain number of bits of entropy. When enough bits of entropy are
+ * available, the hash is finalized and handed as a key to a stream cipher that
+ * expands it indefinitely for various consumers. This key is periodically
+ * refreshed as the various entropy collectors, described below, add data to the
+ * input pool and credit it. There is currently no Fortuna-like scheduler
+ * involved, which can lead to malicious entropy sources causing a premature
+ * reseed, and the entropy estimates are, at best, conservative guesses.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -344,744 +52,937 @@
 #include <linux/syscalls.h>
 #include <linux/completion.h>
 #include <linux/uuid.h>
+#include <linux/uaccess.h>
 #include <crypto/chacha.h>
 #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>
 
-#define CREATE_TRACE_POINTS
-#include <trace/events/random.h>
-
-/* #define ADD_INTERRUPT_BENCH */
-
-/*
- * If the entropy count falls under this number of bits, then we
- * should wake up processes which are selecting or polling on write
- * access to /dev/random.
- */
-static int random_write_wakeup_bits = 28 * (1 << 5);
-
-/*
- * Originally, we used a primitive polynomial of degree .poolwords
- * over GF(2).  The taps for various sizes are defined below.  They
- * were chosen to be evenly spaced except for the last tap, which is 1
- * to get the twisting happening as fast as possible.
- *
- * For the purposes of better mixing, we use the CRC-32 polynomial as
- * well to make a (modified) twisted Generalized Feedback Shift
- * Register.  (See M. Matsumoto & Y. Kurita, 1992.  Twisted GFSR
- * generators.  ACM Transactions on Modeling and Computer Simulation
- * 2(3):179-194.  Also see M. Matsumoto & Y. Kurita, 1994.  Twisted
- * GFSR generators II.  ACM Transactions on Modeling and Computer
- * Simulation 4:254-266)
+/*********************************************************************
  *
- * Thanks to Colin Plumb for suggesting this.
+ * Initialization and readiness waiting.
  *
- * The mixing operation is much less sensitive than the output hash,
- * where we use BLAKE2s.  All that we want of mixing operation is that
- * it be a good non-cryptographic hash; i.e. it not produce collisions
- * when fed "random" data of the sort we expect to see.  As long as
- * the pool state differs for different inputs, we have preserved the
- * input entropy and done a good job.  The fact that an intelligent
- * attacker can construct inputs that will produce controlled
- * alterations to the pool's state is not important because we don't
- * consider such inputs to contribute any randomness.  The only
- * property we need with respect to them is that the attacker can't
- * increase his/her knowledge of the pool's state.  Since all
- * additions are reversible (knowing the final state and the input,
- * you can reconstruct the initial state), if an attacker has any
- * uncertainty about the initial state, he/she can only shuffle that
- * uncertainty about, but never cause any collisions (which would
- * decrease the uncertainty).
+ * Much of the RNG infrastructure is devoted to various dependencies
+ * being able to wait until the RNG has collected enough entropy and
+ * is ready for safe consumption.
  *
- * Our mixing functions were analyzed by Lacharme, Roeck, Strubel, and
- * Videau in their paper, "The Linux Pseudorandom Number Generator
- * Revisited" (see: http://eprint.iacr.org/2012/251.pdf).  In their
- * paper, they point out that we are not using a true Twisted GFSR,
- * since Matsumoto & Kurita used a trinomial feedback polynomial (that
- * is, with only three taps, instead of the six that we are using).
- * As a result, the resulting polynomial is neither primitive nor
- * irreducible, and hence does not have a maximal period over
- * GF(2**32).  They suggest a slight change to the generator
- * polynomial which improves the resulting TGFSR polynomial to be
- * irreducible, which we have made here.
- */
-enum poolinfo {
-	POOL_WORDS = 128,
-	POOL_WORDMASK = POOL_WORDS - 1,
-	POOL_BYTES = POOL_WORDS * sizeof(u32),
-	POOL_BITS = POOL_BYTES * 8,
-	POOL_BITSHIFT = ilog2(POOL_BITS),
-
-	/* To allow fractional bits to be tracked, the entropy_count field is
-	 * denominated in units of 1/8th bits. */
-	POOL_ENTROPY_SHIFT = 3,
-#define POOL_ENTROPY_BITS() (input_pool.entropy_count >> POOL_ENTROPY_SHIFT)
-	POOL_FRACBITS = POOL_BITS << POOL_ENTROPY_SHIFT,
-
-	/* x^128 + x^104 + x^76 + x^51 +x^25 + x + 1 */
-	POOL_TAP1 = 104,
-	POOL_TAP2 = 76,
-	POOL_TAP3 = 51,
-	POOL_TAP4 = 25,
-	POOL_TAP5 = 1,
-
-	EXTRACT_SIZE = BLAKE2S_HASH_SIZE / 2
-};
-
-/*
- * Static global variables
- */
-static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
-static struct fasync_struct *fasync;
-
-static DEFINE_SPINLOCK(random_ready_list_lock);
-static LIST_HEAD(random_ready_list);
-
-struct crng_state {
-	u32 state[16];
-	unsigned long init_time;
-	spinlock_t lock;
-};
-
-static struct crng_state primary_crng = {
-	.lock = __SPIN_LOCK_UNLOCKED(primary_crng.lock),
-	.state[0] = CHACHA_CONSTANT_EXPA,
-	.state[1] = CHACHA_CONSTANT_ND_3,
-	.state[2] = CHACHA_CONSTANT_2_BY,
-	.state[3] = CHACHA_CONSTANT_TE_K,
-};
+ *********************************************************************/
 
 /*
  * crng_init =  0 --> Uninitialized
  *		1 --> Initialized
  *		2 --> Initialized from input_pool
  *
- * crng_init is protected by primary_crng->lock, and only increases
+ * crng_init is protected by base_crng->lock, and only increases
  * its value (from 0->1->2).
  */
 static int crng_init = 0;
-static bool crng_need_final_init = false;
 #define crng_ready() (likely(crng_init > 1))
-static int crng_init_cnt = 0;
-static unsigned long crng_global_init_time = 0;
-#define CRNG_INIT_CNT_THRESH (2 * CHACHA_KEY_SIZE)
-static void _extract_crng(struct crng_state *crng, u8 out[CHACHA_BLOCK_SIZE]);
-static void _crng_backtrack_protect(struct crng_state *crng,
-				    u8 tmp[CHACHA_BLOCK_SIZE], int used);
-static void process_random_ready_list(void);
-static void _get_random_bytes(void *buf, int nbytes);
+/* Various types of waiters for crng_init->2 transition. */
+static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait);
+static struct fasync_struct *fasync;
+static DEFINE_SPINLOCK(random_ready_chain_lock);
+static RAW_NOTIFIER_HEAD(random_ready_chain);
 
+/* Control how we warn userspace. */
 static struct ratelimit_state 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.
+/*
+ * Returns whether or not the input pool has been seeded and thus guaranteed
+ * to supply cryptographically secure random numbers. This applies to
+ * get_random_bytes() and get_random_{u32,u64,int,long}().
  *
- **********************************************************************/
-
-static u32 input_pool_data[POOL_WORDS] __latent_entropy;
-
-static struct {
-	spinlock_t lock;
-	u16 add_ptr;
-	u16 input_rotate;
-	int entropy_count;
-} input_pool = {
-	.lock = __SPIN_LOCK_UNLOCKED(input_pool.lock),
-};
+ * Returns: true if the input pool has been seeded.
+ *          false if the input pool has not been seeded.
+ */
+bool rng_is_initialized(void)
+{
+	return crng_ready();
+}
+EXPORT_SYMBOL(rng_is_initialized);
 
-static ssize_t extract_entropy(void *buf, size_t nbytes, int min);
-static ssize_t _extract_entropy(void *buf, size_t nbytes);
+/* Used by wait_for_random_bytes(), and considered an entropy collector, below. */
+static void try_to_generate_entropy(void);
 
-static void crng_reseed(struct crng_state *crng, bool use_input_pool);
+/*
+ * Wait for the input pool to be seeded and thus guaranteed to supply
+ * cryptographically secure random numbers. This applies to
+ * get_random_bytes() and get_random_{u32,u64,int,long}(). Using any
+ * of these functions without first calling this function means that
+ * the returned numbers might not be cryptographically secure.
+ *
+ * Returns: 0 if the input pool has been seeded.
+ *          -ERESTARTSYS if the function was interrupted by a signal.
+ */
+int wait_for_random_bytes(void)
+{
+	while (!crng_ready()) {
+		int ret;
 
-static const u32 twist_table[8] = {
-	0x00000000, 0x3b6e20c8, 0x76dc4190, 0x4db26158,
-	0xedb88320, 0xd6d6a3e8, 0x9b64c2b0, 0xa00ae278 };
+		try_to_generate_entropy();
+		ret = wait_event_interruptible_timeout(crng_init_wait, crng_ready(), HZ);
+		if (ret)
+			return ret > 0 ? 0 : ret;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(wait_for_random_bytes);
 
 /*
- * 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.
+ * Add a callback function that will be invoked when the input
+ * pool is initialised.
  *
- * The pool is stirred with a primitive polynomial of the appropriate
- * degree, and then twisted.  We twist by three bits at a time because
- * it's cheap to do so and helps slightly in the expected case where
- * the entropy is concentrated in the low-order bits.
+ * returns: 0 if callback is successfully added
+ *	    -EALREADY if pool is already initialised (callback not called)
  */
-static void _mix_pool_bytes(const void *in, int nbytes)
+int register_random_ready_notifier(struct notifier_block *nb)
 {
-	unsigned long i;
-	int input_rotate;
-	const u8 *bytes = in;
-	u32 w;
-
-	input_rotate = input_pool.input_rotate;
-	i = input_pool.add_ptr;
-
-	/* mix one byte at a time to simplify size handling and churn faster */
-	while (nbytes--) {
-		w = rol32(*bytes++, input_rotate);
-		i = (i - 1) & POOL_WORDMASK;
-
-		/* XOR in the various taps */
-		w ^= input_pool_data[i];
-		w ^= input_pool_data[(i + POOL_TAP1) & POOL_WORDMASK];
-		w ^= input_pool_data[(i + POOL_TAP2) & POOL_WORDMASK];
-		w ^= input_pool_data[(i + POOL_TAP3) & POOL_WORDMASK];
-		w ^= input_pool_data[(i + POOL_TAP4) & POOL_WORDMASK];
-		w ^= input_pool_data[(i + POOL_TAP5) & POOL_WORDMASK];
-
-		/* Mix the result back in with a twist */
-		input_pool_data[i] = (w >> 3) ^ twist_table[w & 7];
+	unsigned long flags;
+	int ret = -EALREADY;
 
-		/*
-		 * Normally, we add 7 bits of rotation to the pool.
-		 * At the beginning of the pool, add an extra 7 bits
-		 * rotation, so that successive passes spread the
-		 * input bits across the pool evenly.
-		 */
-		input_rotate = (input_rotate + (i ? 7 : 14)) & 31;
-	}
+	if (crng_ready())
+		return ret;
 
-	input_pool.input_rotate = input_rotate;
-	input_pool.add_ptr = i;
+	spin_lock_irqsave(&random_ready_chain_lock, flags);
+	if (!crng_ready())
+		ret = raw_notifier_chain_register(&random_ready_chain, nb);
+	spin_unlock_irqrestore(&random_ready_chain_lock, flags);
+	return ret;
 }
 
-static void __mix_pool_bytes(const void *in, int nbytes)
+/*
+ * Delete a previously registered readiness callback function.
+ */
+int unregister_random_ready_notifier(struct notifier_block *nb)
 {
-	trace_mix_pool_bytes_nolock(nbytes, _RET_IP_);
-	_mix_pool_bytes(in, nbytes);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&random_ready_chain_lock, flags);
+	ret = raw_notifier_chain_unregister(&random_ready_chain, nb);
+	spin_unlock_irqrestore(&random_ready_chain_lock, flags);
+	return ret;
 }
 
-static void mix_pool_bytes(const void *in, int nbytes)
+static void process_random_ready_list(void)
 {
 	unsigned long flags;
 
-	trace_mix_pool_bytes(nbytes, _RET_IP_);
-	spin_lock_irqsave(&input_pool.lock, flags);
-	_mix_pool_bytes(in, nbytes);
-	spin_unlock_irqrestore(&input_pool.lock, flags);
+	spin_lock_irqsave(&random_ready_chain_lock, flags);
+	raw_notifier_call_chain(&random_ready_chain, 0, NULL);
+	spin_unlock_irqrestore(&random_ready_chain_lock, flags);
 }
 
-struct fast_pool {
-	u32 pool[4];
-	unsigned long last;
-	u16 reg_idx;
-	u8 count;
-};
+#define warn_unseeded_randomness(previous) \
+	_warn_unseeded_randomness(__func__, (void *)_RET_IP_, (previous))
 
-/*
- * 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)
+static void _warn_unseeded_randomness(const char *func_name, void *caller, void **previous)
 {
-	u32 a = f->pool[0],	b = f->pool[1];
-	u32 c = f->pool[2],	d = f->pool[3];
+#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);
+}
+
 
-	a += b;			c += d;
-	b = rol32(b, 6);	d = rol32(d, 27);
-	d ^= a;			b ^= c;
+/*********************************************************************
+ *
+ * Fast key erasure RNG, the "crng".
+ *
+ * These functions expand entropy from the entropy extractor into
+ * long streams for external consumption using the "fast key erasure"
+ * RNG described at <https://blog.cr.yp.to/20170723-random.html>.
+ *
+ * There are a few exported interfaces for use by other drivers:
+ *
+ *	void get_random_bytes(void *buf, size_t nbytes)
+ *	u32 get_random_u32()
+ *	u64 get_random_u64()
+ *	unsigned int get_random_int()
+ *	unsigned long get_random_long()
+ *
+ * These interfaces will return the requested number of random bytes
+ * into the given buffer or as a return value. The returned numbers are
+ * the same as those of getrandom(0). The integer family of functions may
+ * be higher performance for one-off random integers, because they do a
+ * bit of buffering and do not invoke reseeding.
+ *
+ *********************************************************************/
 
-	a += b;			c += d;
-	b = rol32(b, 16);	d = rol32(d, 14);
-	d ^= a;			b ^= c;
+enum {
+	CRNG_RESEED_INTERVAL = 300 * HZ,
+	CRNG_INIT_CNT_THRESH = 2 * CHACHA_KEY_SIZE
+};
 
-	a += b;			c += d;
-	b = rol32(b, 6);	d = rol32(d, 27);
-	d ^= a;			b ^= c;
+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)
+};
 
-	a += b;			c += d;
-	b = rol32(b, 16);	d = rol32(d, 14);
-	d ^= a;			b ^= c;
+struct crng {
+	u8 key[CHACHA_KEY_SIZE];
+	unsigned long generation;
+	local_lock_t lock;
+};
 
-	f->pool[0] = a;  f->pool[1] = b;
-	f->pool[2] = c;  f->pool[3] = d;
-	f->count++;
-}
+static DEFINE_PER_CPU(struct crng, crngs) = {
+	.generation = ULONG_MAX,
+	.lock = INIT_LOCAL_LOCK(crngs.lock),
+};
 
-static void process_random_ready_list(void)
+/* Used by crng_reseed() to extract a new seed from the input pool. */
+static bool drain_entropy(void *buf, size_t nbytes, bool force);
+
+/*
+ * This extracts a new crng key from the input pool, but only if there is a
+ * sufficient amount of entropy available or force is true, in order to
+ * mitigate bruteforcing of newly added bits.
+ */
+static void crng_reseed(bool force)
 {
 	unsigned long flags;
-	struct random_ready_callback *rdy, *tmp;
+	unsigned long next_gen;
+	u8 key[CHACHA_KEY_SIZE];
+	bool finalize_init = false;
 
-	spin_lock_irqsave(&random_ready_list_lock, flags);
-	list_for_each_entry_safe(rdy, tmp, &random_ready_list, list) {
-		struct module *owner = rdy->owner;
+	/* Only reseed if we can, to prevent brute forcing a small amount of new bits. */
+	if (!drain_entropy(key, sizeof(key), force))
+		return;
 
-		list_del_init(&rdy->list);
-		rdy->func(rdy);
-		module_put(owner);
+	/*
+	 * We copy the new key into the base_crng, overwriting the old one,
+	 * and update the generation counter. We avoid hitting ULONG_MAX,
+	 * because the per-cpu crngs are initialized to ULONG_MAX, so this
+	 * forces new CPUs that come online to always initialize.
+	 */
+	spin_lock_irqsave(&base_crng.lock, flags);
+	memcpy(base_crng.key, key, sizeof(base_crng.key));
+	next_gen = base_crng.generation + 1;
+	if (next_gen == ULONG_MAX)
+		++next_gen;
+	WRITE_ONCE(base_crng.generation, next_gen);
+	WRITE_ONCE(base_crng.birth, jiffies);
+	if (!crng_ready()) {
+		crng_init = 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;
+		}
 	}
-	spin_unlock_irqrestore(&random_ready_list_lock, flags);
 }
 
 /*
- * Credit (or debit) the entropy store with n bits of entropy.
- * Use credit_entropy_bits_safe() if the value comes from userspace
- * or otherwise should be checked for extreme values.
+ * This generates a ChaCha block using the provided key, and then
+ * immediately overwites that key with half the block. It returns
+ * the resultant ChaCha state to the user, along with the second
+ * half of the block containing 32 bytes of random data that may
+ * be used; random_data_len may not be greater than 32.
  */
-static void credit_entropy_bits(int nbits)
+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)
 {
-	int entropy_count, entropy_bits, orig;
-	int nfrac = nbits << POOL_ENTROPY_SHIFT;
+	u8 first_block[CHACHA_BLOCK_SIZE];
 
-	/* Ensure that the multiplication can avoid being 64 bits wide. */
-	BUILD_BUG_ON(2 * (POOL_ENTROPY_SHIFT + POOL_BITSHIFT) > 31);
+	BUG_ON(random_data_len > 32);
 
-	if (!nbits)
-		return;
+	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);
 
-retry:
-	entropy_count = orig = READ_ONCE(input_pool.entropy_count);
-	if (nfrac < 0) {
-		/* Debit */
-		entropy_count += nfrac;
-	} else {
-		/*
-		 * Credit: we have to account for the possibility of
-		 * overwriting already present entropy.	 Even in the
-		 * ideal case of pure Shannon entropy, new contributions
-		 * approach the full value asymptotically:
-		 *
-		 * entropy <- entropy + (pool_size - entropy) *
-		 *	(1 - exp(-add_entropy/pool_size))
-		 *
-		 * For add_entropy <= pool_size/2 then
-		 * (1 - exp(-add_entropy/pool_size)) >=
-		 *    (add_entropy/pool_size)*0.7869...
-		 * so we can approximate the exponential with
-		 * 3/4*add_entropy/pool_size and still be on the
-		 * safe side by adding at most pool_size/2 at a time.
-		 *
-		 * The use of pool_size-2 in the while statement is to
-		 * prevent rounding artifacts from making the loop
-		 * arbitrarily long; this limits the loop to log2(pool_size)*2
-		 * turns no matter how large nbits is.
-		 */
-		int pnfrac = nfrac;
-		const int s = POOL_BITSHIFT + POOL_ENTROPY_SHIFT + 2;
-		/* The +2 corresponds to the /4 in the denominator */
-
-		do {
-			unsigned int anfrac = min(pnfrac, POOL_FRACBITS / 2);
-			unsigned int add =
-				((POOL_FRACBITS - entropy_count) * anfrac * 3) >> s;
-
-			entropy_count += add;
-			pnfrac -= anfrac;
-		} while (unlikely(entropy_count < POOL_FRACBITS - 2 && pnfrac));
-	}
-
-	if (WARN_ON(entropy_count < 0)) {
-		pr_warn("negative entropy/overflow: count %d\n", entropy_count);
-		entropy_count = 0;
-	} else if (entropy_count > POOL_FRACBITS)
-		entropy_count = POOL_FRACBITS;
-	if (cmpxchg(&input_pool.entropy_count, orig, entropy_count) != orig)
-		goto retry;
-
-	trace_credit_entropy_bits(nbits, entropy_count >> POOL_ENTROPY_SHIFT, _RET_IP_);
+	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));
+}
 
-	entropy_bits = entropy_count >> POOL_ENTROPY_SHIFT;
-	if (crng_init < 2 && entropy_bits >= 128)
-		crng_reseed(&primary_crng, true);
+/*
+ * Return whether the crng seed is considered to be sufficiently
+ * old that a reseeding might be attempted. This happens if the last
+ * reseeding was CRNG_RESEED_INTERVAL ago, or during early boot, at
+ * an interval proportional to the uptime.
+ */
+static bool crng_has_old_seed(void)
+{
+	static bool early_boot = true;
+	unsigned long interval = CRNG_RESEED_INTERVAL;
+
+	if (unlikely(READ_ONCE(early_boot))) {
+		time64_t uptime = ktime_get_seconds();
+		if (uptime >= CRNG_RESEED_INTERVAL / HZ * 2)
+			WRITE_ONCE(early_boot, false);
+		else
+			interval = max_t(unsigned int, 5 * HZ,
+					 (unsigned int)uptime / 2 * HZ);
+	}
+	return time_after(jiffies, READ_ONCE(base_crng.birth) + interval);
 }
 
-static int credit_entropy_bits_safe(int nbits)
+/*
+ * This function returns a ChaCha state that you may use for generating
+ * random data. It also returns up to 32 bytes on its own of random data
+ * that may be used; random_data_len may not be greater than 32.
+ */
+static void crng_make_state(u32 chacha_state[CHACHA_STATE_WORDS],
+			    u8 *random_data, size_t random_data_len)
 {
-	if (nbits < 0)
-		return -EINVAL;
+	unsigned long flags;
+	struct crng *crng;
 
-	/* Cap the value to avoid overflows */
-	nbits = min(nbits, POOL_BITS);
+	BUG_ON(random_data_len > 32);
 
-	credit_entropy_bits(nbits);
-	return 0;
-}
+	/*
+	 * 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_pre_init_inject() mutates during early init.
+	 */
+	if (!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;
+	}
 
-/*********************************************************************
- *
- * CRNG using CHACHA20
- *
- *********************************************************************/
+	/*
+	 * If the base_crng is old enough, we try to reseed, which in turn
+	 * bumps the generation counter that we check below.
+	 */
+	if (unlikely(crng_has_old_seed()))
+		crng_reseed(false);
 
-#define CRNG_RESEED_INTERVAL (300 * HZ)
+	local_lock_irqsave(&crngs.lock, flags);
+	crng = raw_cpu_ptr(&crngs);
 
-static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait);
+	/*
+	 * 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);
+}
 
 /*
- * Hack to deal with crazy userspace progams when they are all trying
- * to access /dev/urandom in parallel.  The programs are almost
- * certainly doing something terribly wrong, but we'll work around
- * their brain damage.
+ * This function is for crng_init == 0 only. It loads entropy directly
+ * into the crng's key, without going through the input pool. It is,
+ * generally speaking, not very safe, but we use this only at early
+ * boot time when it's better to have something there rather than
+ * nothing.
+ *
+ * If account is set, then the crng_init_cnt counter is incremented.
+ * This shouldn't be set by functions like add_device_randomness(),
+ * where we can't trust the buffer passed to it is guaranteed to be
+ * unpredictable (so it might not have any entropy at all).
+ *
+ * Returns the number of bytes processed from input, which is bounded
+ * by CRNG_INIT_CNT_THRESH if account is true.
  */
-static struct crng_state **crng_node_pool __read_mostly;
+static size_t crng_pre_init_inject(const void *input, size_t len, bool account)
+{
+	static int crng_init_cnt = 0;
+	struct blake2s_state hash;
+	unsigned long flags;
 
-static void invalidate_batched_entropy(void);
-static void numa_crng_init(void);
+	blake2s_init(&hash, sizeof(base_crng.key));
 
-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);
+	spin_lock_irqsave(&base_crng.lock, flags);
+	if (crng_init != 0) {
+		spin_unlock_irqrestore(&base_crng.lock, flags);
+		return 0;
+	}
 
-static bool crng_init_try_arch(struct crng_state *crng)
-{
-	int i;
-	bool arch_init = true;
-	unsigned long rv;
+	if (account)
+		len = min_t(size_t, len, CRNG_INIT_CNT_THRESH - crng_init_cnt);
 
-	for (i = 4; i < 16; i++) {
-		if (!arch_get_random_seed_long(&rv) &&
-		    !arch_get_random_long(&rv)) {
-			rv = random_get_entropy();
-			arch_init = false;
+	blake2s_update(&hash, base_crng.key, sizeof(base_crng.key));
+	blake2s_update(&hash, input, len);
+	blake2s_final(&hash, base_crng.key);
+
+	if (account) {
+		crng_init_cnt += len;
+		if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) {
+			++base_crng.generation;
+			crng_init = 1;
 		}
-		crng->state[i] ^= rv;
 	}
 
-	return arch_init;
+	spin_unlock_irqrestore(&base_crng.lock, flags);
+
+	if (crng_init == 1)
+		pr_notice("fast init done\n");
+
+	return len;
 }
 
-static bool __init crng_init_try_arch_early(void)
+static void _get_random_bytes(void *buf, size_t nbytes)
 {
-	int i;
-	bool arch_init = true;
-	unsigned long rv;
+	u32 chacha_state[CHACHA_STATE_WORDS];
+	u8 tmp[CHACHA_BLOCK_SIZE];
+	size_t len;
 
-	for (i = 4; i < 16; i++) {
-		if (!arch_get_random_seed_long_early(&rv) &&
-		    !arch_get_random_long_early(&rv)) {
-			rv = random_get_entropy();
-			arch_init = false;
+	if (!nbytes)
+		return;
+
+	len = min_t(size_t, 32, nbytes);
+	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;
 		}
-		primary_crng.state[i] ^= rv;
+
+		chacha20_block(chacha_state, buf);
+		if (unlikely(chacha_state[12] == 0))
+			++chacha_state[13];
+		nbytes -= CHACHA_BLOCK_SIZE;
+		buf += CHACHA_BLOCK_SIZE;
 	}
 
-	return arch_init;
+	memzero_explicit(chacha_state, sizeof(chacha_state));
 }
 
-static void crng_initialize_secondary(struct crng_state *crng)
+/*
+ * This function is the exported kernel interface.  It returns some
+ * number of good random numbers, suitable for key generation, seeding
+ * TCP sequence numbers, etc.  It does not rely on the hardware random
+ * number generator.  For random bytes direct from the hardware RNG
+ * (when available), use get_random_bytes_arch(). In order to ensure
+ * that the randomness provided by this function is okay, the function
+ * wait_for_random_bytes() should be called and return 0 at least once
+ * at any point prior.
+ */
+void get_random_bytes(void *buf, size_t nbytes)
 {
-	chacha_init_consts(crng->state);
-	_get_random_bytes(&crng->state[4], sizeof(u32) * 12);
-	crng_init_try_arch(crng);
-	crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1;
-}
+	static void *previous;
 
-static void __init crng_initialize_primary(void)
-{
-	_extract_entropy(&primary_crng.state[4], sizeof(u32) * 12);
-	if (crng_init_try_arch_early() && trust_cpu && crng_init < 2) {
-		invalidate_batched_entropy();
-		numa_crng_init();
-		crng_init = 2;
-		pr_notice("crng init done (trusting CPU's manufacturer)\n");
-	}
-	primary_crng.init_time = jiffies - CRNG_RESEED_INTERVAL - 1;
+	warn_unseeded_randomness(&previous);
+	_get_random_bytes(buf, nbytes);
 }
+EXPORT_SYMBOL(get_random_bytes);
 
-static void crng_finalize_init(void)
+static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes)
 {
-	if (!system_wq) {
-		/* We can't call numa_crng_init until we have workqueues,
-		 * so mark this for processing later. */
-		crng_need_final_init = true;
-		return;
-	}
+	bool large_request = nbytes > 256;
+	ssize_t ret = 0;
+	size_t len;
+	u32 chacha_state[CHACHA_STATE_WORDS];
+	u8 output[CHACHA_BLOCK_SIZE];
 
-	invalidate_batched_entropy();
-	numa_crng_init();
-	crng_init = 2;
-	crng_need_final_init = false;
-	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;
-	}
-}
+	if (!nbytes)
+		return 0;
 
-static void do_numa_crng_init(struct work_struct *work)
-{
-	int i;
-	struct crng_state *crng;
-	struct crng_state **pool;
-
-	pool = kcalloc(nr_node_ids, sizeof(*pool), GFP_KERNEL | __GFP_NOFAIL);
-	for_each_online_node(i) {
-		crng = kmalloc_node(sizeof(struct crng_state),
-				    GFP_KERNEL | __GFP_NOFAIL, i);
-		spin_lock_init(&crng->lock);
-		crng_initialize_secondary(crng);
-		pool[i] = crng;
-	}
-	/* pairs with READ_ONCE() in select_crng() */
-	if (cmpxchg_release(&crng_node_pool, NULL, pool) != NULL) {
-		for_each_node(i)
-			kfree(pool[i]);
-		kfree(pool);
-	}
-}
+	len = min_t(size_t, 32, nbytes);
+	crng_make_state(chacha_state, output, len);
 
-static DECLARE_WORK(numa_crng_init_work, do_numa_crng_init);
+	if (copy_to_user(buf, output, len))
+		return -EFAULT;
+	nbytes -= len;
+	buf += len;
+	ret += len;
 
-static void numa_crng_init(void)
-{
-	if (IS_ENABLED(CONFIG_NUMA))
-		schedule_work(&numa_crng_init_work);
-}
+	while (nbytes) {
+		if (large_request && need_resched()) {
+			if (signal_pending(current))
+				break;
+			schedule();
+		}
 
-static struct crng_state *select_crng(void)
-{
-	if (IS_ENABLED(CONFIG_NUMA)) {
-		struct crng_state **pool;
-		int nid = numa_node_id();
-
-		/* pairs with cmpxchg_release() in do_numa_crng_init() */
-		pool = READ_ONCE(crng_node_pool);
-		if (pool && pool[nid])
-			return pool[nid];
+		chacha20_block(chacha_state, output);
+		if (unlikely(chacha_state[12] == 0))
+			++chacha_state[13];
+
+		len = min_t(size_t, nbytes, CHACHA_BLOCK_SIZE);
+		if (copy_to_user(buf, output, len)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		nbytes -= len;
+		buf += len;
+		ret += len;
 	}
 
-	return &primary_crng;
+	memzero_explicit(chacha_state, sizeof(chacha_state));
+	memzero_explicit(output, sizeof(output));
+	return ret;
 }
 
 /*
- * 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.
+ * Batched entropy returns random integers. The quality of the random
+ * number is good as /dev/urandom. In order to ensure that the randomness
+ * provided by this function is okay, the function wait_for_random_bytes()
+ * should be called and return 0 at least once at any point prior.
  */
-static size_t crng_fast_load(const u8 *cp, size_t len)
+struct batched_entropy {
+	union {
+		/*
+		 * 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))];
+	};
+	local_lock_t lock;
+	unsigned long generation;
+	unsigned int position;
+};
+
+
+static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64) = {
+	.lock = INIT_LOCAL_LOCK(batched_entropy_u64.lock),
+	.position = UINT_MAX
+};
+
+u64 get_random_u64(void)
 {
+	u64 ret;
 	unsigned long flags;
-	u8 *p;
-	size_t ret = 0;
+	struct batched_entropy *batch;
+	static void *previous;
+	unsigned long next_gen;
 
-	if (!spin_trylock_irqsave(&primary_crng.lock, flags))
-		return 0;
-	if (crng_init != 0) {
-		spin_unlock_irqrestore(&primary_crng.lock, flags);
-		return 0;
-	}
-	p = (u8 *)&primary_crng.state[4];
-	while (len > 0 && crng_init_cnt < CRNG_INIT_CNT_THRESH) {
-		p[crng_init_cnt % CHACHA_KEY_SIZE] ^= *cp;
-		cp++; crng_init_cnt++; len--; ret++;
-	}
-	spin_unlock_irqrestore(&primary_crng.lock, flags);
-	if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) {
-		invalidate_batched_entropy();
-		crng_init = 1;
-		pr_notice("fast init done\n");
+	warn_unseeded_randomness(&previous);
+
+	local_lock_irqsave(&batched_entropy_u64.lock, flags);
+	batch = raw_cpu_ptr(&batched_entropy_u64);
+
+	next_gen = READ_ONCE(base_crng.generation);
+	if (batch->position >= ARRAY_SIZE(batch->entropy_u64) ||
+	    next_gen != batch->generation) {
+		_get_random_bytes(batch->entropy_u64, sizeof(batch->entropy_u64));
+		batch->position = 0;
+		batch->generation = next_gen;
 	}
+
+	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);
 
-/*
- * crng_slow_load() is called by add_device_randomness, which has two
- * attributes.  (1) We can't trust the buffer passed to it is
- * guaranteed to be unpredictable (so it might not have any entropy at
- * all), and (2) it doesn't have the performance constraints of
- * crng_fast_load().
- *
- * So we do something more comprehensive which is guaranteed to touch
- * all of the primary_crng's state, and which uses a LFSR with a
- * period of 255 as part of the mixing algorithm.  Finally, we do
- * *not* advance crng_init_cnt since buffer we may get may be something
- * like a fixed DMI table (for example), which might very well be
- * unique to the machine, but is otherwise unvarying.
- */
-static int crng_slow_load(const u8 *cp, size_t len)
+static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32) = {
+	.lock = INIT_LOCAL_LOCK(batched_entropy_u32.lock),
+	.position = UINT_MAX
+};
+
+u32 get_random_u32(void)
 {
+	u32 ret;
 	unsigned long flags;
-	static u8 lfsr = 1;
-	u8 tmp;
-	unsigned int i, max = CHACHA_KEY_SIZE;
-	const u8 *src_buf = cp;
-	u8 *dest_buf = (u8 *)&primary_crng.state[4];
+	struct batched_entropy *batch;
+	static void *previous;
+	unsigned long next_gen;
 
-	if (!spin_trylock_irqsave(&primary_crng.lock, flags))
-		return 0;
-	if (crng_init != 0) {
-		spin_unlock_irqrestore(&primary_crng.lock, flags);
-		return 0;
-	}
-	if (len > max)
-		max = len;
-
-	for (i = 0; i < max; i++) {
-		tmp = lfsr;
-		lfsr >>= 1;
-		if (tmp & 1)
-			lfsr ^= 0xE1;
-		tmp = dest_buf[i % CHACHA_KEY_SIZE];
-		dest_buf[i % CHACHA_KEY_SIZE] ^= src_buf[i % len] ^ lfsr;
-		lfsr += (tmp << 3) | (tmp >> 5);
+	warn_unseeded_randomness(&previous);
+
+	local_lock_irqsave(&batched_entropy_u32.lock, flags);
+	batch = raw_cpu_ptr(&batched_entropy_u32);
+
+	next_gen = READ_ONCE(base_crng.generation);
+	if (batch->position >= ARRAY_SIZE(batch->entropy_u32) ||
+	    next_gen != batch->generation) {
+		_get_random_bytes(batch->entropy_u32, sizeof(batch->entropy_u32));
+		batch->position = 0;
+		batch->generation = next_gen;
 	}
-	spin_unlock_irqrestore(&primary_crng.lock, flags);
-	return 1;
+
+	ret = batch->entropy_u32[batch->position];
+	batch->entropy_u32[batch->position] = 0;
+	++batch->position;
+	local_unlock_irqrestore(&batched_entropy_u32.lock, flags);
+	return ret;
 }
+EXPORT_SYMBOL(get_random_u32);
 
-static void crng_reseed(struct crng_state *crng, bool use_input_pool)
+#ifdef CONFIG_SMP
+/*
+ * This function is called when the CPU is coming up, with entry
+ * CPUHP_RANDOM_PREPARE, which comes before CPUHP_WORKQUEUE_PREP.
+ */
+int random_prepare_cpu(unsigned int cpu)
 {
-	unsigned long flags;
-	int i, num;
-	union {
-		u8 block[CHACHA_BLOCK_SIZE];
-		u32 key[8];
-	} buf;
+	/*
+	 * When the cpu comes back online, immediately invalidate both
+	 * the per-cpu crng and all batches, so that we serve fresh
+	 * randomness.
+	 */
+	per_cpu_ptr(&crngs, cpu)->generation = ULONG_MAX;
+	per_cpu_ptr(&batched_entropy_u32, cpu)->position = UINT_MAX;
+	per_cpu_ptr(&batched_entropy_u64, cpu)->position = UINT_MAX;
+	return 0;
+}
+#endif
 
-	if (use_input_pool) {
-		num = extract_entropy(&buf, 32, 16);
-		if (num == 0)
-			return;
-	} else {
-		_extract_crng(&primary_crng, buf.block);
-		_crng_backtrack_protect(&primary_crng, buf.block,
-					CHACHA_KEY_SIZE);
-	}
-	spin_lock_irqsave(&crng->lock, flags);
-	for (i = 0; i < 8; i++) {
-		unsigned long rv;
-		if (!arch_get_random_seed_long(&rv) &&
-		    !arch_get_random_long(&rv))
-			rv = random_get_entropy();
-		crng->state[i + 4] ^= buf.key[i] ^ rv;
+/**
+ * randomize_page - Generate a random, page aligned address
+ * @start:	The smallest acceptable address the caller will take.
+ * @range:	The size of the area, starting at @start, within which the
+ *		random address must fall.
+ *
+ * If @start + @range would overflow, @range is capped.
+ *
+ * NOTE: Historical use of randomize_range, which this replaces, presumed that
+ * @start was already page aligned.  We now align it regardless.
+ *
+ * Return: A page aligned address within [start, start + range).  On error,
+ * @start is returned.
+ */
+unsigned long randomize_page(unsigned long start, unsigned long range)
+{
+	if (!PAGE_ALIGNED(start)) {
+		range -= PAGE_ALIGN(start) - start;
+		start = PAGE_ALIGN(start);
 	}
-	memzero_explicit(&buf, sizeof(buf));
-	WRITE_ONCE(crng->init_time, jiffies);
-	spin_unlock_irqrestore(&crng->lock, flags);
-	if (crng == &primary_crng && crng_init < 2)
-		crng_finalize_init();
+
+	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);
 }
 
-static void _extract_crng(struct crng_state *crng, u8 out[CHACHA_BLOCK_SIZE])
+/*
+ * This function will use the architecture-specific hardware random
+ * number generator if it is available. It is not recommended for
+ * use. Use get_random_bytes() instead. It returns the number of
+ * bytes filled in.
+ */
+size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes)
 {
-	unsigned long flags, init_time;
+	size_t left = nbytes;
+	u8 *p = buf;
 
-	if (crng_ready()) {
-		init_time = READ_ONCE(crng->init_time);
-		if (time_after(READ_ONCE(crng_global_init_time), init_time) ||
-		    time_after(jiffies, init_time + CRNG_RESEED_INTERVAL))
-			crng_reseed(crng, crng == &primary_crng);
+	while (left) {
+		unsigned long v;
+		size_t chunk = min_t(size_t, left, sizeof(unsigned long));
+
+		if (!arch_get_random_long(&v))
+			break;
+
+		memcpy(p, &v, chunk);
+		p += chunk;
+		left -= chunk;
 	}
-	spin_lock_irqsave(&crng->lock, flags);
-	chacha20_block(&crng->state[0], out);
-	if (crng->state[12] == 0)
-		crng->state[13]++;
-	spin_unlock_irqrestore(&crng->lock, flags);
+
+	return nbytes - left;
 }
+EXPORT_SYMBOL(get_random_bytes_arch);
+
+
+/**********************************************************************
+ *
+ * Entropy accumulation and extraction routines.
+ *
+ * Callers may add entropy via:
+ *
+ *     static void mix_pool_bytes(const void *in, size_t nbytes)
+ *
+ * After which, if added entropy should be credited:
+ *
+ *     static void credit_entropy_bits(size_t nbits)
+ *
+ * Finally, extract entropy via these two, with the latter one
+ * setting the entropy count to zero and extracting only if there
+ * is POOL_MIN_BITS entropy credited prior or force is true:
+ *
+ *     static void extract_entropy(void *buf, size_t nbytes)
+ *     static bool drain_entropy(void *buf, size_t nbytes, bool force)
+ *
+ **********************************************************************/
+
+enum {
+	POOL_BITS = BLAKE2S_HASH_SIZE * 8,
+	POOL_MIN_BITS = POOL_BITS /* No point in settling for less. */
+};
+
+/* For notifying userspace should write into /dev/random. */
+static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
+
+static struct {
+	struct blake2s_state hash;
+	spinlock_t lock;
+	unsigned int entropy_count;
+} input_pool = {
+	.hash.h = { BLAKE2S_IV0 ^ (0x01010000 | BLAKE2S_HASH_SIZE),
+		    BLAKE2S_IV1, BLAKE2S_IV2, BLAKE2S_IV3, BLAKE2S_IV4,
+		    BLAKE2S_IV5, BLAKE2S_IV6, BLAKE2S_IV7 },
+	.hash.outlen = BLAKE2S_HASH_SIZE,
+	.lock = __SPIN_LOCK_UNLOCKED(input_pool.lock),
+};
 
-static void extract_crng(u8 out[CHACHA_BLOCK_SIZE])
+static void _mix_pool_bytes(const void *in, size_t nbytes)
 {
-	_extract_crng(select_crng(), out);
+	blake2s_update(&input_pool.hash, in, nbytes);
 }
 
 /*
- * Use the leftover bytes from the CRNG block output (if there is
- * enough) to mutate the CRNG key to provide backtracking protection.
+ * 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 _crng_backtrack_protect(struct crng_state *crng,
-				    u8 tmp[CHACHA_BLOCK_SIZE], int used)
+static void mix_pool_bytes(const void *in, size_t nbytes)
 {
 	unsigned long flags;
-	u32 *s, *d;
-	int i;
 
-	used = round_up(used, sizeof(u32));
-	if (used + CHACHA_KEY_SIZE > CHACHA_BLOCK_SIZE) {
-		extract_crng(tmp);
-		used = 0;
-	}
-	spin_lock_irqsave(&crng->lock, flags);
-	s = (u32 *)&tmp[used];
-	d = &crng->state[4];
-	for (i = 0; i < 8; i++)
-		*d++ ^= *s++;
-	spin_unlock_irqrestore(&crng->lock, flags);
+	spin_lock_irqsave(&input_pool.lock, flags);
+	_mix_pool_bytes(in, nbytes);
+	spin_unlock_irqrestore(&input_pool.lock, flags);
 }
 
-static void crng_backtrack_protect(u8 tmp[CHACHA_BLOCK_SIZE], int used)
+static void credit_entropy_bits(size_t nbits)
 {
-	_crng_backtrack_protect(select_crng(), tmp, used);
+	unsigned int entropy_count, orig, add;
+
+	if (!nbits)
+		return;
+
+	add = min_t(size_t, nbits, POOL_BITS);
+
+	do {
+		orig = READ_ONCE(input_pool.entropy_count);
+		entropy_count = min_t(unsigned int, POOL_BITS, orig + add);
+	} while (cmpxchg(&input_pool.entropy_count, orig, entropy_count) != orig);
+
+	if (!crng_ready() && entropy_count >= POOL_MIN_BITS)
+		crng_reseed(false);
 }
 
-static ssize_t extract_crng_user(void __user *buf, size_t nbytes)
+/*
+ * 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)
 {
-	ssize_t ret = 0, i = CHACHA_BLOCK_SIZE;
-	u8 tmp[CHACHA_BLOCK_SIZE] __aligned(4);
-	int large_request = (nbytes > 256);
+	unsigned long flags;
+	u8 seed[BLAKE2S_HASH_SIZE], next_key[BLAKE2S_HASH_SIZE];
+	struct {
+		unsigned long rdseed[32 / sizeof(long)];
+		size_t counter;
+	} block;
+	size_t i;
+
+	for (i = 0; i < ARRAY_SIZE(block.rdseed); ++i) {
+		if (!arch_get_random_seed_long(&block.rdseed[i]) &&
+		    !arch_get_random_long(&block.rdseed[i]))
+			block.rdseed[i] = random_get_entropy();
+	}
 
-	while (nbytes) {
-		if (large_request && need_resched()) {
-			if (signal_pending(current)) {
-				if (ret == 0)
-					ret = -ERESTARTSYS;
-				break;
-			}
-			schedule();
-		}
+	spin_lock_irqsave(&input_pool.lock, flags);
 
-		extract_crng(tmp);
-		i = min_t(int, nbytes, CHACHA_BLOCK_SIZE);
-		if (copy_to_user(buf, tmp, i)) {
-			ret = -EFAULT;
-			break;
-		}
+	/* seed = HASHPRF(last_key, entropy_input) */
+	blake2s_final(&input_pool.hash, seed);
+
+	/* next_key = HASHPRF(seed, RDSEED || 0) */
+	block.counter = 0;
+	blake2s(next_key, (u8 *)&block, seed, sizeof(next_key), sizeof(block), sizeof(seed));
+	blake2s_init_key(&input_pool.hash, BLAKE2S_HASH_SIZE, next_key, sizeof(next_key));
+
+	spin_unlock_irqrestore(&input_pool.lock, flags);
+	memzero_explicit(next_key, sizeof(next_key));
 
+	while (nbytes) {
+		i = min_t(size_t, nbytes, BLAKE2S_HASH_SIZE);
+		/* output = HASHPRF(seed, RDSEED || ++counter) */
+		++block.counter;
+		blake2s(buf, (u8 *)&block, seed, i, sizeof(block), sizeof(seed));
 		nbytes -= i;
 		buf += i;
-		ret += i;
 	}
-	crng_backtrack_protect(tmp, i);
 
-	/* Wipe data just written to memory */
-	memzero_explicit(tmp, sizeof(tmp));
+	memzero_explicit(seed, sizeof(seed));
+	memzero_explicit(&block, sizeof(block));
+}
 
-	return ret;
+/*
+ * First we make sure we have POOL_MIN_BITS of entropy in the pool unless force
+ * is true, and then we set the entropy count to zero (but don't actually touch
+ * any data). Only then can we extract a new key with extract_entropy().
+ */
+static bool drain_entropy(void *buf, size_t nbytes, bool force)
+{
+	unsigned int entropy_count;
+	do {
+		entropy_count = READ_ONCE(input_pool.entropy_count);
+		if (!force && entropy_count < POOL_MIN_BITS)
+			return false;
+	} while (cmpxchg(&input_pool.entropy_count, entropy_count, 0) != entropy_count);
+	extract_entropy(buf, nbytes);
+	wake_up_interruptible(&random_write_wait);
+	kill_fasync(&fasync, SIGIO, POLL_OUT);
+	return true;
 }
 
-/*********************************************************************
+
+/**********************************************************************
  *
- * Entropy input management
+ * Entropy collection routines.
  *
- *********************************************************************/
+ * The following exported functions are used for pushing entropy into
+ * the above entropy accumulation routines:
+ *
+ *	void add_device_randomness(const void *buf, size_t size);
+ *	void add_input_randomness(unsigned int type, unsigned int code,
+ *	                          unsigned int value);
+ *	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);
+ *	void add_vmfork_randomness(const void *unique_vm_id, size_t size);
+ *	void add_interrupt_randomness(int irq);
+ *
+ * add_device_randomness() adds data to the input pool that
+ * is likely to differ between two devices (or possibly even per boot).
+ * This would be things like MAC addresses or serial numbers, or the
+ * read-out of the RTC. This does *not* credit any actual entropy to
+ * the pool, but it initializes the pool to different values for devices
+ * that might otherwise be identical and have very little entropy
+ * available to them (particularly common in the embedded world).
+ *
+ * add_input_randomness() uses the input layer interrupt timing, as well
+ * as the event type information from the hardware.
+ *
+ * add_disk_randomness() uses what amounts to the seek time of block
+ * layer request events, on a per-disk_devt basis, as input to the
+ * entropy pool. Note that high-speed solid state drives with very low
+ * seek times do not make for good sources of entropy, as their seek
+ * times are usually fairly consistent.
+ *
+ * The above two routines try to estimate how many bits of entropy
+ * to credit. They do this by keeping track of the first and second
+ * order deltas of the event timings.
+ *
+ * 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.
+ *
+ * add_vmfork_randomness() adds a unique (but not necessarily secret) ID
+ * representing the current instance of a VM to the pool, without crediting,
+ * and then force-reseeds the crng so that it takes effect immediately.
+ *
+ * add_interrupt_randomness() uses the interrupt timing as random
+ * inputs to the entropy pool. Using the cycle counters and the irq source
+ * as inputs, it feeds the input pool roughly once a second or after 64
+ * interrupts, crediting 1 bit of entropy for whichever comes first.
+ *
+ **********************************************************************/
 
-/* There is one of these per entropy source */
-struct timer_rand_state {
-	cycles_t last_time;
-	long last_delta, last_delta2;
-};
+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);
+
+/*
+ * The first collection of entropy occurs at system boot while interrupts
+ * are still turned off. Here we push in RDSEED, a timestamp, and utsname().
+ * Depending on the above configuration knob, RDSEED may be considered
+ * sufficient for initialization. Note that much earlier setup may already
+ * have pushed entropy into the input pool by the time we get here.
+ */
+int __init 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())));
+
+	extract_entropy(base_crng.key, sizeof(base_crng.key));
+	++base_crng.generation;
 
-#define INIT_TIMER_RAND_STATE { INITIAL_JIFFIES, };
+	if (arch_init && trust_cpu && !crng_ready()) {
+		crng_init = 2;
+		pr_notice("crng init done (trusting CPU's manufacturer)\n");
+	}
+
+	if (ratelimit_disable)
+		unseeded_warning.interval = 0;
+	return 0;
+}
 
 /*
  * Add device- or boot-specific data to the input pool to help
@@ -1091,23 +992,27 @@ struct timer_rand_state {
  * the entropy pool having similar initial state across largely
  * identical devices.
  */
-void add_device_randomness(const void *buf, unsigned int size)
+void add_device_randomness(const void *buf, size_t size)
 {
-	unsigned long time = random_get_entropy() ^ jiffies;
-	unsigned long flags;
+	cycles_t cycles = random_get_entropy();
+	unsigned long flags, now = jiffies;
 
-	if (!crng_ready() && size)
-		crng_slow_load(buf, size);
+	if (crng_init == 0 && size)
+		crng_pre_init_inject(buf, size, false);
 
-	trace_add_device_randomness(size, _RET_IP_);
 	spin_lock_irqsave(&input_pool.lock, flags);
+	_mix_pool_bytes(&cycles, sizeof(cycles));
+	_mix_pool_bytes(&now, sizeof(now));
 	_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;
+/* There is one of these per entropy source */
+struct timer_rand_state {
+	unsigned long last_time;
+	long last_delta, last_delta2;
+};
 
 /*
  * This function adds entropy to the entropy "pool" by using timing
@@ -1117,29 +1022,26 @@ static struct timer_rand_state input_timer_state = INIT_TIMER_RAND_STATE;
  * The number "num" is also added to the pool - it should somehow describe
  * the type of event which just happened.  This is currently 0-255 for
  * keyboard scan codes, and 256 upwards for interrupts.
- *
  */
-static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
+static void add_timer_randomness(struct timer_rand_state *state, unsigned int num)
 {
-	struct {
-		long jiffies;
-		unsigned int cycles;
-		unsigned int num;
-	} sample;
+	cycles_t cycles = random_get_entropy();
+	unsigned long flags, now = jiffies;
 	long delta, delta2, delta3;
 
-	sample.jiffies = jiffies;
-	sample.cycles = random_get_entropy();
-	sample.num = num;
-	mix_pool_bytes(&sample, sizeof(sample));
+	spin_lock_irqsave(&input_pool.lock, flags);
+	_mix_pool_bytes(&cycles, sizeof(cycles));
+	_mix_pool_bytes(&now, sizeof(now));
+	_mix_pool_bytes(&num, sizeof(num));
+	spin_unlock_irqrestore(&input_pool.lock, flags);
 
 	/*
 	 * Calculate number of bits of randomness we probably added.
 	 * We take into account the first, second and third-order deltas
 	 * in order to make our estimate.
 	 */
-	delta = sample.jiffies - READ_ONCE(state->last_time);
-	WRITE_ONCE(state->last_time, sample.jiffies);
+	delta = now - READ_ONCE(state->last_time);
+	WRITE_ONCE(state->last_time, now);
 
 	delta2 = delta - READ_ONCE(state->last_delta);
 	WRITE_ONCE(state->last_delta, delta);
@@ -1163,318 +1065,303 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 	 * Round down by 1 bit on general principles,
 	 * and limit entropy estimate to 12 bits.
 	 */
-	credit_entropy_bits(min_t(int, fls(delta >> 1), 11));
+	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;
+	static struct timer_rand_state input_timer_state = { INITIAL_JIFFIES };
 
-	/* ignore autorepeat and the like */
+	/* Ignore autorepeat and the like. */
 	if (value == last_value)
 		return;
 
 	last_value = value;
 	add_timer_randomness(&input_timer_state,
 			     (type << 4) ^ code ^ (code >> 4) ^ value);
-	trace_add_input_randomness(POOL_ENTROPY_BITS());
 }
 EXPORT_SYMBOL_GPL(add_input_randomness);
 
-static DEFINE_PER_CPU(struct fast_pool, irq_randomness);
-
-#ifdef ADD_INTERRUPT_BENCH
-static unsigned long avg_cycles, avg_deviation;
-
-#define AVG_SHIFT 8 /* Exponential average factor k=1/256 */
-#define FIXED_1_2 (1 << (AVG_SHIFT - 1))
-
-static void add_interrupt_bench(cycles_t start)
+#ifdef CONFIG_BLOCK
+void add_disk_randomness(struct gendisk *disk)
 {
-	long delta = random_get_entropy() - start;
-
-	/* Use a weighted moving average */
-	delta = delta - ((avg_cycles + FIXED_1_2) >> AVG_SHIFT);
-	avg_cycles += delta;
-	/* And average deviation */
-	delta = abs(delta) - ((avg_deviation + FIXED_1_2) >> AVG_SHIFT);
-	avg_deviation += delta;
+	if (!disk || !disk->random)
+		return;
+	/* First major is 1, so we get >= 0x200 here. */
+	add_timer_randomness(disk->random, 0x100 + disk_devt(disk));
 }
-#else
-#define add_interrupt_bench(x)
-#endif
+EXPORT_SYMBOL_GPL(add_disk_randomness);
 
-static u32 get_reg(struct fast_pool *f, struct pt_regs *regs)
+void rand_initialize_disk(struct gendisk *disk)
 {
-	u32 *ptr = (u32 *)regs;
-	unsigned int idx;
+	struct timer_rand_state *state;
 
-	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;
+	/*
+	 * If kzalloc returns null, we just won't use that entropy
+	 * source.
+	 */
+	state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL);
+	if (state) {
+		state->last_time = INITIAL_JIFFIES;
+		disk->random = state;
+	}
 }
+#endif
 
-void add_interrupt_randomness(int irq)
+/*
+ * 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)
 {
-	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);
-	add_interrupt_bench(cycles);
-
 	if (unlikely(crng_init == 0)) {
-		if ((fast_pool->count >= 64) &&
-		    crng_fast_load((u8 *)fast_pool->pool, sizeof(fast_pool->pool)) > 0) {
-			fast_pool->count = 0;
-			fast_pool->last = now;
-		}
-		return;
+		size_t ret = crng_pre_init_inject(buffer, count, true);
+		mix_pool_bytes(buffer, ret);
+		count -= ret;
+		buffer += ret;
+		if (!count || crng_init == 0)
+			return;
 	}
 
-	if ((fast_pool->count < 64) && !time_after(now, fast_pool->last + HZ))
-		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,
+			!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);
 
-	if (!spin_trylock(&input_pool.lock))
-		return;
+/*
+ * 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);
 
-	fast_pool->last = now;
-	__mix_pool_bytes(&fast_pool->pool, sizeof(fast_pool->pool));
-	spin_unlock(&input_pool.lock);
+#if IS_ENABLED(CONFIG_VMGENID)
+static BLOCKING_NOTIFIER_HEAD(vmfork_chain);
 
-	fast_pool->count = 0;
+/*
+ * Handle a new unique VM ID, which is unique, not secret, so we
+ * don't credit it, but we do immediately force a reseed after so
+ * that it's used by the crng posthaste.
+ */
+void add_vmfork_randomness(const void *unique_vm_id, size_t size)
+{
+	add_device_randomness(unique_vm_id, size);
+	if (crng_ready()) {
+		crng_reseed(true);
+		pr_notice("crng reseeded due to virtual machine fork\n");
+	}
+	blocking_notifier_call_chain(&vmfork_chain, 0, NULL);
+}
+#if IS_MODULE(CONFIG_VMGENID)
+EXPORT_SYMBOL_GPL(add_vmfork_randomness);
+#endif
 
-	/* award one bit for the contents of the fast pool */
-	credit_entropy_bits(1);
+int register_random_vmfork_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&vmfork_chain, nb);
 }
-EXPORT_SYMBOL_GPL(add_interrupt_randomness);
+EXPORT_SYMBOL_GPL(register_random_vmfork_notifier);
 
-#ifdef CONFIG_BLOCK
-void add_disk_randomness(struct gendisk *disk)
+int unregister_random_vmfork_notifier(struct notifier_block *nb)
 {
-	if (!disk || !disk->random)
-		return;
-	/* first major is 1, so we get >= 0x200 here */
-	add_timer_randomness(disk->random, 0x100 + disk_devt(disk));
-	trace_add_disk_randomness(disk_devt(disk), POOL_ENTROPY_BITS());
+	return blocking_notifier_chain_unregister(&vmfork_chain, nb);
 }
-EXPORT_SYMBOL_GPL(add_disk_randomness);
+EXPORT_SYMBOL_GPL(unregister_random_vmfork_notifier);
 #endif
 
-/*********************************************************************
- *
- * Entropy extraction routines
- *
- *********************************************************************/
+struct fast_pool {
+	struct work_struct mix;
+	unsigned long pool[4];
+	unsigned long last;
+	unsigned int count;
+	u16 reg_idx;
+};
+
+static DEFINE_PER_CPU(struct fast_pool, irq_randomness) = {
+#ifdef CONFIG_64BIT
+	/* SipHash constants */
+	.pool = { 0x736f6d6570736575UL, 0x646f72616e646f6dUL,
+		  0x6c7967656e657261UL, 0x7465646279746573UL }
+#else
+	/* HalfSipHash constants */
+	.pool = { 0, 0, 0x6c796765U, 0x74656462U }
+#endif
+};
 
 /*
- * This function decides how many bytes to actually take from the
- * given pool, and also debits the entropy count accordingly.
+ * This is [Half]SipHash-1-x, starting from an empty key. Because
+ * the key is fixed, it assumes that its inputs are non-malicious,
+ * and therefore this has no security on its own. s represents the
+ * 128 or 256-bit SipHash state, while v represents a 128-bit input.
  */
-static size_t account(size_t nbytes, int min)
+static void fast_mix(unsigned long s[4], const unsigned long *v)
 {
-	int entropy_count, orig;
-	size_t ibytes, nfrac;
-
-	BUG_ON(input_pool.entropy_count > POOL_FRACBITS);
-
-	/* Can we pull enough? */
-retry:
-	entropy_count = orig = READ_ONCE(input_pool.entropy_count);
-	if (WARN_ON(entropy_count < 0)) {
-		pr_warn("negative entropy count: count %d\n", entropy_count);
-		entropy_count = 0;
-	}
+	size_t i;
 
-	/* never pull more than available */
-	ibytes = min_t(size_t, nbytes, entropy_count >> (POOL_ENTROPY_SHIFT + 3));
-	if (ibytes < min)
-		ibytes = 0;
-	nfrac = ibytes << (POOL_ENTROPY_SHIFT + 3);
-	if ((size_t)entropy_count > nfrac)
-		entropy_count -= nfrac;
-	else
-		entropy_count = 0;
-
-	if (cmpxchg(&input_pool.entropy_count, orig, entropy_count) != orig)
-		goto retry;
-
-	trace_debit_entropy(8 * ibytes);
-	if (ibytes && POOL_ENTROPY_BITS() < random_write_wakeup_bits) {
-		wake_up_interruptible(&random_write_wait);
-		kill_fasync(&fasync, SIGIO, POLL_OUT);
+	for (i = 0; i < 16 / sizeof(long); ++i) {
+		s[3] ^= v[i];
+#ifdef CONFIG_64BIT
+		s[0] += s[1]; s[1] = rol64(s[1], 13); s[1] ^= s[0]; s[0] = rol64(s[0], 32);
+		s[2] += s[3]; s[3] = rol64(s[3], 16); s[3] ^= s[2];
+		s[0] += s[3]; s[3] = rol64(s[3], 21); s[3] ^= s[0];
+		s[2] += s[1]; s[1] = rol64(s[1], 17); s[1] ^= s[2]; s[2] = rol64(s[2], 32);
+#else
+		s[0] += s[1]; s[1] = rol32(s[1],  5); s[1] ^= s[0]; s[0] = rol32(s[0], 16);
+		s[2] += s[3]; s[3] = rol32(s[3],  8); s[3] ^= s[2];
+		s[0] += s[3]; s[3] = rol32(s[3],  7); s[3] ^= s[0];
+		s[2] += s[1]; s[1] = rol32(s[1], 13); s[1] ^= s[2]; s[2] = rol32(s[2], 16);
+#endif
+		s[0] ^= v[i];
 	}
-
-	return ibytes;
 }
 
+#ifdef CONFIG_SMP
 /*
- * This function does the actual extraction for extract_entropy.
- *
- * Note: we assume that .poolwords is a multiple of 16 words.
+ * This function is called when the CPU has just come online, with
+ * entry CPUHP_AP_RANDOM_ONLINE, just after CPUHP_AP_WORKQUEUE_ONLINE.
  */
-static void extract_buf(u8 *out)
+int random_online_cpu(unsigned int cpu)
 {
-	struct blake2s_state state __aligned(__alignof__(unsigned long));
-	u8 hash[BLAKE2S_HASH_SIZE];
-	unsigned long *salt;
-	unsigned long flags;
-
-	blake2s_init(&state, sizeof(hash));
-
 	/*
-	 * If we have an architectural hardware random number
-	 * generator, use it for BLAKE2's salt & personal fields.
+	 * During CPU shutdown and before CPU onlining, add_interrupt_
+	 * randomness() may schedule mix_interrupt_randomness(), and
+	 * set the MIX_INFLIGHT flag. However, because the worker can
+	 * be scheduled on a different CPU during this period, that
+	 * flag will never be cleared. For that reason, we zero out
+	 * the flag here, which runs just after workqueues are onlined
+	 * for the CPU again. This also has the effect of setting the
+	 * irq randomness count to zero so that new accumulated irqs
+	 * are fresh.
 	 */
-	for (salt = (unsigned long *)&state.h[4];
-	     salt < (unsigned long *)&state.h[8]; ++salt) {
-		unsigned long v;
-		if (!arch_get_random_long(&v))
-			break;
-		*salt ^= v;
-	}
-
-	/* Generate a hash across the pool */
-	spin_lock_irqsave(&input_pool.lock, flags);
-	blake2s_update(&state, (const u8 *)input_pool_data, POOL_BYTES);
-	blake2s_final(&state, hash); /* final zeros out state */
+	per_cpu_ptr(&irq_randomness, cpu)->count = 0;
+	return 0;
+}
+#endif
 
-	/*
-	 * We mix the hash back into the pool to prevent backtracking
-	 * attacks (where the attacker knows the state of the pool
-	 * plus the current outputs, and attempts to find previous
-	 * outputs), unless the hash function can be inverted. By
-	 * mixing at least a hash worth of hash data back, we make
-	 * brute-forcing the feedback as hard as brute-forcing the
-	 * hash.
-	 */
-	__mix_pool_bytes(hash, sizeof(hash));
-	spin_unlock_irqrestore(&input_pool.lock, flags);
+static unsigned long get_reg(struct fast_pool *f, struct pt_regs *regs)
+{
+	unsigned long *ptr = (unsigned long *)regs;
+	unsigned int idx;
 
-	/* Note that EXTRACT_SIZE is half of hash size here, because above
-	 * we've dumped the full length back into mixer. By reducing the
-	 * amount that we emit, we retain a level of forward secrecy.
-	 */
-	memcpy(out, hash, EXTRACT_SIZE);
-	memzero_explicit(hash, sizeof(hash));
+	if (regs == NULL)
+		return 0;
+	idx = READ_ONCE(f->reg_idx);
+	if (idx >= sizeof(struct pt_regs) / sizeof(unsigned long))
+		idx = 0;
+	ptr += idx++;
+	WRITE_ONCE(f->reg_idx, idx);
+	return *ptr;
 }
 
-static ssize_t _extract_entropy(void *buf, size_t nbytes)
+static void mix_interrupt_randomness(struct work_struct *work)
 {
-	ssize_t ret = 0, i;
-	u8 tmp[EXTRACT_SIZE];
+	struct fast_pool *fast_pool = container_of(work, struct fast_pool, mix);
+	/*
+	 * The size of the copied stack pool is explicitly 16 bytes so that we
+	 * tax mix_pool_byte()'s compression function the same amount on all
+	 * platforms. This means on 64-bit we copy half the pool into this,
+	 * while on 32-bit we copy all of it. The entropy is supposed to be
+	 * sufficiently dispersed between bits that in the sponge-like
+	 * half case, on average we don't wind up "losing" some.
+	 */
+	u8 pool[16];
 
-	while (nbytes) {
-		extract_buf(tmp);
-		i = min_t(int, nbytes, EXTRACT_SIZE);
-		memcpy(buf, tmp, i);
-		nbytes -= i;
-		buf += i;
-		ret += i;
+	/* Check to see if we're running on the wrong CPU due to hotplug. */
+	local_irq_disable();
+	if (fast_pool != this_cpu_ptr(&irq_randomness)) {
+		local_irq_enable();
+		return;
 	}
 
-	/* Wipe data just returned from memory */
-	memzero_explicit(tmp, sizeof(tmp));
+	/*
+	 * Copy the pool to the stack so that the mixer always has a
+	 * consistent view, before we reenable irqs again.
+	 */
+	memcpy(pool, fast_pool->pool, sizeof(pool));
+	fast_pool->count = 0;
+	fast_pool->last = jiffies;
+	local_irq_enable();
 
-	return ret;
-}
+	if (unlikely(crng_init == 0)) {
+		crng_pre_init_inject(pool, sizeof(pool), true);
+		mix_pool_bytes(pool, sizeof(pool));
+	} else {
+		mix_pool_bytes(pool, sizeof(pool));
+		credit_entropy_bits(1);
+	}
 
-/*
- * This function extracts randomness from the "entropy pool", and
- * returns it in a buffer.
- *
- * The min parameter specifies the minimum amount we can pull before
- * failing to avoid races that defeat catastrophic reseeding.
- */
-static ssize_t extract_entropy(void *buf, size_t nbytes, int min)
-{
-	trace_extract_entropy(nbytes, POOL_ENTROPY_BITS(), _RET_IP_);
-	nbytes = account(nbytes, min);
-	return _extract_entropy(buf, nbytes);
+	memzero_explicit(pool, sizeof(pool));
 }
 
-#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)
+void add_interrupt_randomness(int irq)
 {
-#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);
-}
+	enum { MIX_INFLIGHT = 1U << 31 };
+	cycles_t cycles = random_get_entropy();
+	unsigned long now = jiffies;
+	struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness);
+	struct pt_regs *regs = get_irq_regs();
+	unsigned int new_count;
+	union {
+		u32 u32[4];
+		u64 u64[2];
+		unsigned long longs[16 / sizeof(long)];
+	} irq_data;
 
-/*
- * This function is the exported kernel interface.  It returns some
- * number of good random numbers, suitable for key generation, seeding
- * TCP sequence numbers, etc.  It does not rely on the hardware random
- * number generator.  For random bytes direct from the hardware RNG
- * (when available), use get_random_bytes_arch(). In order to ensure
- * that the randomness provided by this function is okay, the function
- * wait_for_random_bytes() should be called and return 0 at least once
- * at any point prior.
- */
-static void _get_random_bytes(void *buf, int nbytes)
-{
-	u8 tmp[CHACHA_BLOCK_SIZE] __aligned(4);
+	if (cycles == 0)
+		cycles = get_reg(fast_pool, regs);
 
-	trace_get_random_bytes(nbytes, _RET_IP_);
+	if (sizeof(cycles) == 8)
+		irq_data.u64[0] = cycles ^ rol64(now, 32) ^ irq;
+	else {
+		irq_data.u32[0] = cycles ^ irq;
+		irq_data.u32[1] = now;
+	}
 
-	while (nbytes >= CHACHA_BLOCK_SIZE) {
-		extract_crng(buf);
-		buf += CHACHA_BLOCK_SIZE;
-		nbytes -= CHACHA_BLOCK_SIZE;
+	if (sizeof(unsigned long) == 8)
+		irq_data.u64[1] = regs ? instruction_pointer(regs) : _RET_IP_;
+	else {
+		irq_data.u32[2] = regs ? instruction_pointer(regs) : _RET_IP_;
+		irq_data.u32[3] = get_reg(fast_pool, regs);
 	}
 
-	if (nbytes > 0) {
-		extract_crng(tmp);
-		memcpy(buf, tmp, nbytes);
-		crng_backtrack_protect(tmp, nbytes);
-	} else
-		crng_backtrack_protect(tmp, CHACHA_BLOCK_SIZE);
-	memzero_explicit(tmp, sizeof(tmp));
-}
+	fast_mix(fast_pool->pool, irq_data.longs);
+	new_count = ++fast_pool->count;
 
-void get_random_bytes(void *buf, int nbytes)
-{
-	static void *previous;
+	if (new_count & MIX_INFLIGHT)
+		return;
 
-	warn_unseeded_randomness(&previous);
-	_get_random_bytes(buf, nbytes);
+	if (new_count < 64 && (!time_after(now, fast_pool->last + HZ) ||
+			       unlikely(crng_init == 0)))
+		return;
+
+	if (unlikely(!fast_pool->mix.func))
+		INIT_WORK(&fast_pool->mix, mix_interrupt_randomness);
+	fast_pool->count |= MIX_INFLIGHT;
+	queue_work_on(raw_smp_processor_id(), system_highpri_wq, &fast_pool->mix);
 }
-EXPORT_SYMBOL(get_random_bytes);
+EXPORT_SYMBOL_GPL(add_interrupt_randomness);
 
 /*
  * Each time the timer fires, we expect that we got an unpredictable
@@ -1501,264 +1388,81 @@ static void entropy_timer(struct timer_list *t)
 static void try_to_generate_entropy(void)
 {
 	struct {
-		unsigned long now;
+		cycles_t cycles;
 		struct timer_list timer;
 	} stack;
 
-	stack.now = random_get_entropy();
+	stack.cycles = random_get_entropy();
 
 	/* Slow counter - or none. Don't even bother */
-	if (stack.now == random_get_entropy())
+	if (stack.cycles == random_get_entropy())
 		return;
 
 	timer_setup_on_stack(&stack.timer, entropy_timer, 0);
-	while (!crng_ready()) {
+	while (!crng_ready() && !signal_pending(current)) {
 		if (!timer_pending(&stack.timer))
 			mod_timer(&stack.timer, jiffies + 1);
-		mix_pool_bytes(&stack.now, sizeof(stack.now));
+		mix_pool_bytes(&stack.cycles, sizeof(stack.cycles));
 		schedule();
-		stack.now = random_get_entropy();
+		stack.cycles = random_get_entropy();
 	}
 
 	del_timer_sync(&stack.timer);
 	destroy_timer_on_stack(&stack.timer);
-	mix_pool_bytes(&stack.now, sizeof(stack.now));
+	mix_pool_bytes(&stack.cycles, sizeof(stack.cycles));
 }
 
-/*
- * 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;
-
-	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.
+ * Userspace reader/writer interfaces.
  *
- * returns: 0 if callback is successfully added
- *	    -EALREADY if pool is already initialised (callback not called)
- *	    -ENOENT if module for callback is not alive
- */
-int add_random_ready_callback(struct random_ready_callback *rdy)
-{
-	struct module *owner;
-	unsigned long flags;
-	int err = -EALREADY;
-
-	if (crng_ready())
-		return err;
-
-	owner = rdy->owner;
-	if (!try_module_get(owner))
-		return -ENOENT;
-
-	spin_lock_irqsave(&random_ready_list_lock, flags);
-	if (crng_ready())
-		goto out;
-
-	owner = NULL;
-
-	list_add(&rdy->list, &random_ready_list);
-	err = 0;
-
-out:
-	spin_unlock_irqrestore(&random_ready_list_lock, flags);
-
-	module_put(owner);
-
-	return err;
-}
-EXPORT_SYMBOL(add_random_ready_callback);
-
-/*
- * Delete a previously registered readiness callback function.
- */
-void del_random_ready_callback(struct random_ready_callback *rdy)
-{
-	unsigned long flags;
-	struct module *owner = NULL;
-
-	spin_lock_irqsave(&random_ready_list_lock, flags);
-	if (!list_empty(&rdy->list)) {
-		list_del_init(&rdy->list);
-		owner = rdy->owner;
-	}
-	spin_unlock_irqrestore(&random_ready_list_lock, flags);
-
-	module_put(owner);
-}
-EXPORT_SYMBOL(del_random_ready_callback);
-
-/*
- * This function will use the architecture-specific hardware random
- * number generator if it is available.  The arch-specific hw RNG will
- * almost certainly be faster than what we can do in software, but it
- * is impossible to verify that it is implemented securely (as
- * opposed, to, say, the AES encryption of a sequence number using a
- * key known by the NSA).  So it's useful if we need the speed, but
- * only if we're willing to trust the hardware manufacturer not to
- * have put in a back door.
+ * getrandom(2) is the primary modern interface into the RNG and should
+ * be used in preference to anything else.
  *
- * Return number of bytes filled in.
- */
-int __must_check get_random_bytes_arch(void *buf, int nbytes)
-{
-	int left = nbytes;
-	u8 *p = buf;
-
-	trace_get_random_bytes_arch(left, _RET_IP_);
-	while (left) {
-		unsigned long v;
-		int chunk = min_t(int, left, sizeof(unsigned long));
-
-		if (!arch_get_random_long(&v))
-			break;
-
-		memcpy(p, &v, chunk);
-		p += chunk;
-		left -= chunk;
-	}
-
-	return nbytes - left;
-}
-EXPORT_SYMBOL(get_random_bytes_arch);
-
-/*
- * init_std_data - initialize pool with system data
+ * Reading from /dev/random and /dev/urandom both have the same effect
+ * as calling getrandom(2) with flags=0. (In earlier versions, however,
+ * they each had different semantics.)
  *
- * This function clears the pool's entropy count and mixes some system
- * data into the pool to prepare it for use. The pool is not cleared
- * as that can only decrease the entropy in the pool.
- */
-static void __init init_std_data(void)
-{
-	int i;
-	ktime_t now = ktime_get_real();
-	unsigned long rv;
-
-	mix_pool_bytes(&now, sizeof(now));
-	for (i = POOL_BYTES; i > 0; i -= sizeof(rv)) {
-		if (!arch_get_random_seed_long(&rv) &&
-		    !arch_get_random_long(&rv))
-			rv = random_get_entropy();
-		mix_pool_bytes(&rv, sizeof(rv));
-	}
-	mix_pool_bytes(utsname(), sizeof(*(utsname())));
-}
-
-/*
- * Note that setup_arch() may call add_device_randomness()
- * long before we get here. This allows seeding of the pools
- * with some platform dependent data very early in the boot
- * process. But it limits our options here. We must use
- * statically allocated structures that already have all
- * initializations complete at compile time. We should also
- * take care not to overwrite the precious per platform data
- * we were given.
- */
-int __init rand_initialize(void)
-{
-	init_std_data();
-	if (crng_need_final_init)
-		crng_finalize_init();
-	crng_initialize_primary();
-	crng_global_init_time = jiffies;
-	if (ratelimit_disable) {
-		urandom_warning.interval = 0;
-		unseeded_warning.interval = 0;
-	}
-	return 0;
-}
+ * Writing to either /dev/random or /dev/urandom adds entropy to
+ * the input pool but does not credit it.
+ *
+ * Polling on /dev/random or /dev/urandom indicates when the RNG
+ * is initialized, on the read side, and when it wants new entropy,
+ * on the write side.
+ *
+ * Both /dev/random and /dev/urandom have the same set of ioctls for
+ * adding entropy, getting the entropy count, zeroing the count, and
+ * reseeding the crng.
+ *
+ **********************************************************************/
 
-#ifdef CONFIG_BLOCK
-void rand_initialize_disk(struct gendisk *disk)
+SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count, unsigned int,
+		flags)
 {
-	struct timer_rand_state *state;
+	if (flags & ~(GRND_NONBLOCK | GRND_RANDOM | GRND_INSECURE))
+		return -EINVAL;
 
 	/*
-	 * If kzalloc returns null, we just won't use that entropy
-	 * source.
+	 * Requesting insecure and blocking randomness at the same time makes
+	 * no sense.
 	 */
-	state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL);
-	if (state) {
-		state->last_time = INITIAL_JIFFIES;
-		disk->random = state;
-	}
-}
-#endif
-
-static ssize_t urandom_read_nowarn(struct file *file, char __user *buf,
-				   size_t nbytes, loff_t *ppos)
-{
-	int ret;
+	if ((flags & (GRND_INSECURE | GRND_RANDOM)) == (GRND_INSECURE | GRND_RANDOM))
+		return -EINVAL;
 
-	nbytes = min_t(size_t, nbytes, INT_MAX >> (POOL_ENTROPY_SHIFT + 3));
-	ret = extract_crng_user(buf, nbytes);
-	trace_urandom_read(8 * nbytes, 0, POOL_ENTROPY_BITS());
-	return ret;
-}
+	if (count > INT_MAX)
+		count = INT_MAX;
 
-static ssize_t urandom_read(struct file *file, char __user *buf, size_t nbytes,
-			    loff_t *ppos)
-{
-	static int maxwarn = 10;
+	if (!(flags & GRND_INSECURE) && !crng_ready()) {
+		int ret;
 
-	if (!crng_ready() && maxwarn > 0) {
-		maxwarn--;
-		if (__ratelimit(&urandom_warning))
-			pr_notice("%s: uninitialized urandom read (%zd bytes read)\n",
-				  current->comm, nbytes);
+		if (flags & GRND_NONBLOCK)
+			return -EAGAIN;
+		ret = wait_for_random_bytes();
+		if (unlikely(ret))
+			return ret;
 	}
-
-	return urandom_read_nowarn(file, buf, nbytes, ppos);
-}
-
-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 urandom_read_nowarn(file, buf, nbytes, ppos);
+	return get_random_bytes_user(buf, count);
 }
 
 static __poll_t random_poll(struct file *file, poll_table *wait)
@@ -1770,44 +1474,38 @@ static __poll_t random_poll(struct file *file, poll_table *wait)
 	mask = 0;
 	if (crng_ready())
 		mask |= EPOLLIN | EPOLLRDNORM;
-	if (POOL_ENTROPY_BITS() < random_write_wakeup_bits)
+	if (input_pool.entropy_count < POOL_MIN_BITS)
 		mask |= EPOLLOUT | EPOLLWRNORM;
 	return mask;
 }
 
-static int write_pool(const char __user *buffer, size_t count)
+static int write_pool(const char __user *ubuf, size_t count)
 {
-	size_t bytes;
-	u32 t, buf[16];
-	const char __user *p = buffer;
-
-	while (count > 0) {
-		int b, i = 0;
-
-		bytes = min(count, sizeof(buf));
-		if (copy_from_user(&buf, p, bytes))
-			return -EFAULT;
+	size_t len;
+	int ret = 0;
+	u8 block[BLAKE2S_BLOCK_SIZE];
 
-		for (b = bytes; b > 0; b -= sizeof(u32), i++) {
-			if (!arch_get_random_int(&t))
-				break;
-			buf[i] ^= t;
+	while (count) {
+		len = min(count, sizeof(block));
+		if (copy_from_user(block, ubuf, len)) {
+			ret = -EFAULT;
+			goto out;
 		}
-
-		count -= bytes;
-		p += bytes;
-
-		mix_pool_bytes(buf, bytes);
+		count -= len;
+		ubuf += len;
+		mix_pool_bytes(block, len);
 		cond_resched();
 	}
 
-	return 0;
+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)
 {
-	size_t ret;
+	int ret;
 
 	ret = write_pool(buffer, count);
 	if (ret)
@@ -1816,6 +1514,17 @@ static ssize_t random_write(struct file *file, const char __user *buffer,
 	return (ssize_t)count;
 }
 
+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 long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 {
 	int size, ent_count;
@@ -1824,9 +1533,8 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 
 	switch (cmd) {
 	case RNDGETENTCNT:
-		/* inherently racy, no point locking */
-		ent_count = POOL_ENTROPY_BITS();
-		if (put_user(ent_count, p))
+		/* Inherently racy, no point locking. */
+		if (put_user(input_pool.entropy_count, p))
 			return -EFAULT;
 		return 0;
 	case RNDADDTOENTCNT:
@@ -1834,7 +1542,10 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 			return -EPERM;
 		if (get_user(ent_count, p))
 			return -EFAULT;
-		return credit_entropy_bits_safe(ent_count);
+		if (ent_count < 0)
+			return -EINVAL;
+		credit_entropy_bits(ent_count);
+		return 0;
 	case RNDADDENTROPY:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
@@ -1847,7 +1558,8 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 		retval = write_pool((const char __user *)p, size);
 		if (retval < 0)
 			return retval;
-		return credit_entropy_bits_safe(ent_count);
+		credit_entropy_bits(ent_count);
+		return 0;
 	case RNDZAPENTCNT:
 	case RNDCLEARPOOL:
 		/*
@@ -1856,7 +1568,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 		 */
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
-		if (xchg(&input_pool.entropy_count, 0) && random_write_wakeup_bits) {
+		if (xchg(&input_pool.entropy_count, 0) >= POOL_MIN_BITS) {
 			wake_up_interruptible(&random_write_wait);
 			kill_fasync(&fasync, SIGIO, POLL_OUT);
 		}
@@ -1864,10 +1576,9 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 	case RNDRESEEDCRNG:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
-		if (crng_init < 2)
+		if (!crng_ready())
 			return -ENODATA;
-		crng_reseed(&primary_crng, true);
-		WRITE_ONCE(crng_global_init_time, jiffies - 1);
+		crng_reseed(false);
 		return 0;
 	default:
 		return -EINVAL;
@@ -1889,46 +1600,34 @@ const struct file_operations random_fops = {
 	.llseek = noop_llseek,
 };
 
-const struct file_operations urandom_fops = {
-	.read = urandom_read,
-	.write = random_write,
-	.unlocked_ioctl = random_ioctl,
-	.compat_ioctl = compat_ptr_ioctl,
-	.fasync = random_fasync,
-	.llseek = noop_llseek,
-};
-
-SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count, unsigned int,
-		flags)
-{
-	int ret;
-
-	if (flags & ~(GRND_NONBLOCK | GRND_RANDOM | GRND_INSECURE))
-		return -EINVAL;
-
-	/*
-	 * Requesting insecure and blocking randomness at the same time makes
-	 * no sense.
-	 */
-	if ((flags & (GRND_INSECURE | GRND_RANDOM)) == (GRND_INSECURE | GRND_RANDOM))
-		return -EINVAL;
-
-	if (count > INT_MAX)
-		count = INT_MAX;
-
-	if (!(flags & GRND_INSECURE) && !crng_ready()) {
-		if (flags & GRND_NONBLOCK)
-			return -EAGAIN;
-		ret = wait_for_random_bytes();
-		if (unlikely(ret))
-			return ret;
-	}
-	return urandom_read_nowarn(NULL, buf, count, NULL);
-}
 
 /********************************************************************
  *
- * Sysctl interface
+ * Sysctl interface.
+ *
+ * These are partly unused legacy knobs with dummy values to not break
+ * userspace and partly still useful things. They are usually accessible
+ * in /proc/sys/kernel/random/ and are as follows:
+ *
+ * - boot_id - a UUID representing the current boot.
+ *
+ * - uuid - a random UUID, different each time the file is read.
+ *
+ * - poolsize - the number of bits of entropy that the input pool can
+ *   hold, tied to the POOL_BITS constant.
+ *
+ * - entropy_avail - the number of bits of entropy currently in the
+ *   input pool. Always <= poolsize.
+ *
+ * - write_wakeup_threshold - the amount of entropy in the input pool
+ *   below which write polls to /dev/random will unblock, requesting
+ *   more entropy, tied to the POOL_MIN_BITS constant. It is writable
+ *   to avoid breaking old userspaces, but writing to it does not
+ *   change any behavior of the RNG.
+ *
+ * - urandom_min_reseed_secs - fixed to the value CRNG_RESEED_INTERVAL.
+ *   It is writable to avoid breaking old userspaces, but writing
+ *   to it does not change any behavior of the RNG.
  *
  ********************************************************************/
 
@@ -1936,25 +1635,28 @@ SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count, unsigned int,
 
 #include <linux/sysctl.h>
 
-static int min_write_thresh;
-static int max_write_thresh = POOL_BITS;
-static int random_min_urandom_seed = 60;
-static char sysctl_bootid[16];
+static int sysctl_random_min_urandom_seed = CRNG_RESEED_INTERVAL / HZ;
+static int sysctl_random_write_wakeup_bits = POOL_MIN_BITS;
+static int sysctl_poolsize = POOL_BITS;
+static u8 sysctl_bootid[UUID_SIZE];
 
 /*
  * This function is used to return both the bootid UUID, and random
- * UUID.  The difference is in whether table->data is NULL; if it is,
+ * 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;
+	u8 tmp_uuid[UUID_SIZE], *uuid;
+	char uuid_string[UUID_STRING_LEN + 1];
+	struct ctl_table fake_table = {
+		.data = uuid_string,
+		.maxlen = UUID_STRING_LEN
+	};
+
+	if (write)
+		return -EPERM;
 
 	uuid = table->data;
 	if (!uuid) {
@@ -1969,32 +1671,17 @@ static int proc_do_uuid(struct ctl_table *table, int write, void *buffer,
 		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);
+	snprintf(uuid_string, sizeof(uuid_string), "%pU", uuid);
+	return proc_dostring(&fake_table, 0, buffer, lenp, ppos);
 }
 
-/*
- * Return entropy available scaled to integral bits
- */
-static int proc_do_entropy(struct ctl_table *table, int write, void *buffer,
-			   size_t *lenp, loff_t *ppos)
+/* The same as proc_dointvec, but writes don't change anything. */
+static int proc_do_rointvec(struct ctl_table *table, int write, void *buffer,
+			    size_t *lenp, loff_t *ppos)
 {
-	struct ctl_table fake_table;
-	int entropy_count;
-
-	entropy_count = *(int *)table->data >> POOL_ENTROPY_SHIFT;
-
-	fake_table.data = &entropy_count;
-	fake_table.maxlen = sizeof(entropy_count);
-
-	return proc_dointvec(&fake_table, write, buffer, lenp, ppos);
+	return write ? 0 : proc_dointvec(table, 0, buffer, lenp, ppos);
 }
 
-static int sysctl_poolsize = POOL_BITS;
 static struct ctl_table random_table[] = {
 	{
 		.procname	= "poolsize",
@@ -2005,56 +1692,36 @@ static struct ctl_table random_table[] = {
 	},
 	{
 		.procname	= "entropy_avail",
+		.data		= &input_pool.entropy_count,
 		.maxlen		= sizeof(int),
 		.mode		= 0444,
-		.proc_handler	= proc_do_entropy,
-		.data		= &input_pool.entropy_count,
+		.proc_handler	= proc_dointvec,
 	},
 	{
 		.procname	= "write_wakeup_threshold",
-		.data		= &random_write_wakeup_bits,
+		.data		= &sysctl_random_write_wakeup_bits,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &min_write_thresh,
-		.extra2		= &max_write_thresh,
+		.proc_handler	= proc_do_rointvec,
 	},
 	{
 		.procname	= "urandom_min_reseed_secs",
-		.data		= &random_min_urandom_seed,
+		.data		= &sysctl_random_min_urandom_seed,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_do_rointvec,
 	},
 	{
 		.procname	= "boot_id",
 		.data		= &sysctl_bootid,
-		.maxlen		= 16,
 		.mode		= 0444,
 		.proc_handler	= proc_do_uuid,
 	},
 	{
 		.procname	= "uuid",
-		.maxlen		= 16,
 		.mode		= 0444,
 		.proc_handler	= proc_do_uuid,
 	},
-#ifdef ADD_INTERRUPT_BENCH
-	{
-		.procname	= "add_interrupt_avg_cycles",
-		.data		= &avg_cycles,
-		.maxlen		= sizeof(avg_cycles),
-		.mode		= 0444,
-		.proc_handler	= proc_doulongvec_minmax,
-	},
-	{
-		.procname	= "add_interrupt_avg_deviation",
-		.data		= &avg_deviation,
-		.maxlen		= sizeof(avg_deviation),
-		.mode		= 0444,
-		.proc_handler	= proc_doulongvec_minmax,
-	},
-#endif
 	{ }
 };
 
@@ -2068,170 +1735,4 @@ static int __init random_sysctls_init(void)
 	return 0;
 }
 device_initcall(random_sysctls_init);
-#endif	/* CONFIG_SYSCTL */
-
-struct batched_entropy {
-	union {
-		u64 entropy_u64[CHACHA_BLOCK_SIZE / sizeof(u64)];
-		u32 entropy_u32[CHACHA_BLOCK_SIZE / sizeof(u32)];
-	};
-	unsigned int position;
-	spinlock_t batch_lock;
-};
-
-/*
- * Get a random word for internal kernel use only. The quality of the random
- * number is good as /dev/urandom, but there is no backtrack protection, with
- * the goal of being quite fast and not depleting entropy. In order to ensure
- * that the randomness provided by this function is okay, the function
- * wait_for_random_bytes() should be called and return 0 at least once at any
- * point prior.
- */
-static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64) = {
-	.batch_lock = __SPIN_LOCK_UNLOCKED(batched_entropy_u64.lock),
-};
-
-u64 get_random_u64(void)
-{
-	u64 ret;
-	unsigned long flags;
-	struct batched_entropy *batch;
-	static void *previous;
-
-	warn_unseeded_randomness(&previous);
-
-	batch = raw_cpu_ptr(&batched_entropy_u64);
-	spin_lock_irqsave(&batch->batch_lock, flags);
-	if (batch->position % ARRAY_SIZE(batch->entropy_u64) == 0) {
-		extract_crng((u8 *)batch->entropy_u64);
-		batch->position = 0;
-	}
-	ret = batch->entropy_u64[batch->position++];
-	spin_unlock_irqrestore(&batch->batch_lock, flags);
-	return ret;
-}
-EXPORT_SYMBOL(get_random_u64);
-
-static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32) = {
-	.batch_lock = __SPIN_LOCK_UNLOCKED(batched_entropy_u32.lock),
-};
-u32 get_random_u32(void)
-{
-	u32 ret;
-	unsigned long flags;
-	struct batched_entropy *batch;
-	static void *previous;
-
-	warn_unseeded_randomness(&previous);
-
-	batch = raw_cpu_ptr(&batched_entropy_u32);
-	spin_lock_irqsave(&batch->batch_lock, flags);
-	if (batch->position % ARRAY_SIZE(batch->entropy_u32) == 0) {
-		extract_crng((u8 *)batch->entropy_u32);
-		batch->position = 0;
-	}
-	ret = batch->entropy_u32[batch->position++];
-	spin_unlock_irqrestore(&batch->batch_lock, flags);
-	return ret;
-}
-EXPORT_SYMBOL(get_random_u32);
-
-/* It's important to invalidate all potential batched entropy that might
- * be stored before the crng is initialized, which we can do lazily by
- * simply resetting the counter to zero so that it's re-extracted on the
- * next usage. */
-static void invalidate_batched_entropy(void)
-{
-	int cpu;
-	unsigned long flags;
-
-	for_each_possible_cpu(cpu) {
-		struct batched_entropy *batched_entropy;
-
-		batched_entropy = per_cpu_ptr(&batched_entropy_u32, cpu);
-		spin_lock_irqsave(&batched_entropy->batch_lock, flags);
-		batched_entropy->position = 0;
-		spin_unlock(&batched_entropy->batch_lock);
-
-		batched_entropy = per_cpu_ptr(&batched_entropy_u64, cpu);
-		spin_lock(&batched_entropy->batch_lock);
-		batched_entropy->position = 0;
-		spin_unlock_irqrestore(&batched_entropy->batch_lock, flags);
-	}
-}
-
-/**
- * randomize_page - Generate a random, page aligned address
- * @start:	The smallest acceptable address the caller will take.
- * @range:	The size of the area, starting at @start, within which the
- *		random address must fall.
- *
- * If @start + @range would overflow, @range is capped.
- *
- * NOTE: Historical use of randomize_range, which this replaces, presumed that
- * @start was already page aligned.  We now align it regardless.
- *
- * Return: A page aligned address within [start, start + range).  On error,
- * @start is returned.
- */
-unsigned long randomize_page(unsigned long start, unsigned long range)
-{
-	if (!PAGE_ALIGNED(start)) {
-		range -= PAGE_ALIGN(start) - start;
-		start = PAGE_ALIGN(start);
-	}
-
-	if (start > ULONG_MAX - range)
-		range = ULONG_MAX - start;
-
-	range >>= PAGE_SHIFT;
-
-	if (range == 0)
-		return start;
-
-	return start + (get_random_long() % range << PAGE_SHIFT);
-}
-
-/* Interface for in-kernel drivers of true hardware RNGs.
- * Those devices may produce endless random bits and will be throttled
- * when our pool is full.
- */
-void add_hwgenerator_randomness(const char *buffer, size_t count,
-				size_t entropy)
-{
-	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 random_write_wakeup_thresh,
-	 * when the calling thread is about to terminate, or once
-	 * CRNG_RESEED_INTERVAL has lapsed.
-	 */
-	wait_event_interruptible_timeout(random_write_wait,
-			!system_wq || kthread_should_stop() ||
-			POOL_ENTROPY_BITS() <= random_write_wakeup_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, unsigned int 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);
+#endif
diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c
index a46067c38bf5..0fad1331303c 100644
--- a/drivers/net/wireguard/device.c
+++ b/drivers/net/wireguard/device.c
@@ -59,9 +59,7 @@ out:
 	return ret;
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int wg_pm_notification(struct notifier_block *nb, unsigned long action,
-			      void *data)
+static int wg_pm_notification(struct notifier_block *nb, unsigned long action, void *data)
 {
 	struct wg_device *wg;
 	struct wg_peer *peer;
@@ -92,7 +90,24 @@ static int wg_pm_notification(struct notifier_block *nb, unsigned long action,
 }
 
 static struct notifier_block pm_notifier = { .notifier_call = wg_pm_notification };
-#endif
+
+static int wg_vm_notification(struct notifier_block *nb, unsigned long action, void *data)
+{
+	struct wg_device *wg;
+	struct wg_peer *peer;
+
+	rtnl_lock();
+	list_for_each_entry(wg, &device_list, device_list) {
+		mutex_lock(&wg->device_update_lock);
+		list_for_each_entry(peer, &wg->peer_list, peer_list)
+			wg_noise_expire_current_peer_keypairs(peer);
+		mutex_unlock(&wg->device_update_lock);
+	}
+	rtnl_unlock();
+	return 0;
+}
+
+static struct notifier_block vm_notifier = { .notifier_call = wg_vm_notification };
 
 static int wg_stop(struct net_device *dev)
 {
@@ -424,16 +439,18 @@ int __init wg_device_init(void)
 {
 	int ret;
 
-#ifdef CONFIG_PM_SLEEP
 	ret = register_pm_notifier(&pm_notifier);
 	if (ret)
 		return ret;
-#endif
 
-	ret = register_pernet_device(&pernet_ops);
+	ret = register_random_vmfork_notifier(&vm_notifier);
 	if (ret)
 		goto error_pm;
 
+	ret = register_pernet_device(&pernet_ops);
+	if (ret)
+		goto error_vm;
+
 	ret = rtnl_link_register(&link_ops);
 	if (ret)
 		goto error_pernet;
@@ -442,10 +459,10 @@ int __init wg_device_init(void)
 
 error_pernet:
 	unregister_pernet_device(&pernet_ops);
+error_vm:
+	unregister_random_vmfork_notifier(&vm_notifier);
 error_pm:
-#ifdef CONFIG_PM_SLEEP
 	unregister_pm_notifier(&pm_notifier);
-#endif
 	return ret;
 }
 
@@ -453,8 +470,7 @@ void wg_device_uninit(void)
 {
 	rtnl_link_unregister(&link_ops);
 	unregister_pernet_device(&pernet_ops);
-#ifdef CONFIG_PM_SLEEP
+	unregister_random_vmfork_notifier(&vm_notifier);
 	unregister_pm_notifier(&pm_notifier);
-#endif
 	rcu_barrier();
 }
diff --git a/drivers/virt/Kconfig b/drivers/virt/Kconfig
index 8061e8ef449f..121b9293c737 100644
--- a/drivers/virt/Kconfig
+++ b/drivers/virt/Kconfig
@@ -13,6 +13,17 @@ menuconfig VIRT_DRIVERS
 
 if VIRT_DRIVERS
 
+config VMGENID
+	tristate "Virtual Machine Generation ID driver"
+	default y
+	depends on ACPI
+	help
+	  Say Y here to use the hypervisor-provided Virtual Machine Generation ID
+	  to reseed the RNG when the VM is cloned. This is highly recommended if
+	  you intend to do any rollback / cloning / snapshotting of VMs.
+
+	  Prefer Y to M so that this protection is activated very early.
+
 config FSL_HV_MANAGER
 	tristate "Freescale hypervisor management driver"
 	depends on FSL_SOC
diff --git a/drivers/virt/Makefile b/drivers/virt/Makefile
index 3e272ea60cd9..108d0ffcc9aa 100644
--- a/drivers/virt/Makefile
+++ b/drivers/virt/Makefile
@@ -4,6 +4,7 @@
 #
 
 obj-$(CONFIG_FSL_HV_MANAGER)	+= fsl_hypervisor.o
+obj-$(CONFIG_VMGENID)		+= vmgenid.o
 obj-y				+= vboxguest/
 
 obj-$(CONFIG_NITRO_ENCLAVES)	+= nitro_enclaves/
diff --git a/drivers/virt/vmgenid.c b/drivers/virt/vmgenid.c
new file mode 100644
index 000000000000..0ae1a39f2e28
--- /dev/null
+++ b/drivers/virt/vmgenid.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * The "Virtual Machine Generation ID" is exposed via ACPI and changes when a
+ * virtual machine forks or is cloned. This driver exists for shepherding that
+ * information to random.c.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/acpi.h>
+#include <linux/random.h>
+
+ACPI_MODULE_NAME("vmgenid");
+
+enum { VMGENID_SIZE = 16 };
+
+struct vmgenid_state {
+	u8 *next_id;
+	u8 this_id[VMGENID_SIZE];
+};
+
+static int vmgenid_add(struct acpi_device *device)
+{
+	struct acpi_buffer parsed = { ACPI_ALLOCATE_BUFFER };
+	struct vmgenid_state *state;
+	union acpi_object *obj;
+	phys_addr_t phys_addr;
+	acpi_status status;
+	int ret = 0;
+
+	state = devm_kmalloc(&device->dev, sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return -ENOMEM;
+
+	status = acpi_evaluate_object(device->handle, "ADDR", NULL, &parsed);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating ADDR"));
+		return -ENODEV;
+	}
+	obj = parsed.pointer;
+	if (!obj || obj->type != ACPI_TYPE_PACKAGE || obj->package.count != 2 ||
+	    obj->package.elements[0].type != ACPI_TYPE_INTEGER ||
+	    obj->package.elements[1].type != ACPI_TYPE_INTEGER) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	phys_addr = (obj->package.elements[0].integer.value << 0) |
+		    (obj->package.elements[1].integer.value << 32);
+	state->next_id = devm_memremap(&device->dev, phys_addr, VMGENID_SIZE, MEMREMAP_WB);
+	if (IS_ERR(state->next_id)) {
+		ret = PTR_ERR(state->next_id);
+		goto out;
+	}
+
+	memcpy(state->this_id, state->next_id, sizeof(state->this_id));
+	add_device_randomness(state->this_id, sizeof(state->this_id));
+
+	device->driver_data = state;
+
+out:
+	ACPI_FREE(parsed.pointer);
+	return ret;
+}
+
+static void vmgenid_notify(struct acpi_device *device, u32 event)
+{
+	struct vmgenid_state *state = acpi_driver_data(device);
+	u8 old_id[VMGENID_SIZE];
+
+	memcpy(old_id, state->this_id, sizeof(old_id));
+	memcpy(state->this_id, state->next_id, sizeof(state->this_id));
+	if (!memcmp(old_id, state->this_id, sizeof(old_id)))
+		return;
+	add_vmfork_randomness(state->this_id, sizeof(state->this_id));
+}
+
+static const struct acpi_device_id vmgenid_ids[] = {
+	{ "VM_GEN_COUNTER", 0 },
+	{ }
+};
+
+static struct acpi_driver vmgenid_driver = {
+	.name = "vmgenid",
+	.ids = vmgenid_ids,
+	.owner = THIS_MODULE,
+	.ops = {
+		.add = vmgenid_add,
+		.notify = vmgenid_notify
+	}
+};
+
+module_acpi_driver(vmgenid_driver);
+
+MODULE_DEVICE_TABLE(acpi, vmgenid_ids);
+MODULE_DESCRIPTION("Virtual Machine Generation ID");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 2bc550ac8dc7..c7dce7883179 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -100,6 +100,7 @@ enum cpuhp_state {
 	CPUHP_AP_ARM_CACHE_B15_RAC_DEAD,
 	CPUHP_PADATA_DEAD,
 	CPUHP_AP_DTPM_CPU_DEAD,
+	CPUHP_RANDOM_PREPARE,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,
@@ -241,6 +242,7 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_CSKY_ONLINE,
 	CPUHP_AP_WATCHDOG_ONLINE,
 	CPUHP_AP_WORKQUEUE_ONLINE,
+	CPUHP_AP_RANDOM_ONLINE,
 	CPUHP_AP_RCUTREE_ONLINE,
 	CPUHP_AP_BASE_CACHEINFO_ONLINE,
 	CPUHP_AP_ONLINE_DYN,
diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h
index 8e6dd908da21..aa1d4da03538 100644
--- a/include/linux/hw_random.h
+++ b/include/linux/hw_random.h
@@ -60,7 +60,5 @@ extern int devm_hwrng_register(struct device *dev, struct hwrng *rng);
 /** Unregister a Hardware Random Number Generator driver. */
 extern void hwrng_unregister(struct hwrng *rng);
 extern void devm_hwrng_unregister(struct device *dve, struct hwrng *rng);
-/** Feed random bits into the pool. */
-extern void add_hwgenerator_randomness(const char *buffer, size_t count, size_t entropy);
 
 #endif /* LINUX_HWRANDOM_H_ */
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 4bb71979a8fd..5da5d990ff58 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -211,7 +211,7 @@ struct css_device_id {
 	kernel_ulong_t driver_data;
 };
 
-#define ACPI_ID_LEN	9
+#define ACPI_ID_LEN	16
 
 struct acpi_device_id {
 	__u8 id[ACPI_ID_LEN];
diff --git a/include/linux/random.h b/include/linux/random.h
index c45b2693e51f..c0baffe7afb1 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -1,9 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*
- * include/linux/random.h
- *
- * Include file for the random number generator.
- */
+
 #ifndef _LINUX_RANDOM_H
 #define _LINUX_RANDOM_H
 
@@ -14,14 +10,10 @@
 
 #include <uapi/linux/random.h>
 
-struct random_ready_callback {
-	struct list_head list;
-	void (*func)(struct random_ready_callback *rdy);
-	struct module *owner;
-};
+struct notifier_block;
 
-extern void add_device_randomness(const void *, unsigned int);
-extern void add_bootloader_randomness(const void *, unsigned int);
+extern void add_device_randomness(const void *, size_t);
+extern void add_bootloader_randomness(const void *, size_t);
 
 #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__)
 static inline void add_latent_entropy(void)
@@ -36,17 +28,27 @@ static inline void add_latent_entropy(void) {}
 extern void add_input_randomness(unsigned int type, unsigned int code,
 				 unsigned int value) __latent_entropy;
 extern void add_interrupt_randomness(int irq) __latent_entropy;
+extern void add_hwgenerator_randomness(const void *buffer, size_t count,
+				       size_t entropy);
+#if IS_ENABLED(CONFIG_VMGENID)
+extern void add_vmfork_randomness(const void *unique_vm_id, size_t size);
+extern int register_random_vmfork_notifier(struct notifier_block *nb);
+extern int unregister_random_vmfork_notifier(struct notifier_block *nb);
+#else
+static inline int register_random_vmfork_notifier(struct notifier_block *nb) { return 0; }
+static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) { return 0; }
+#endif
 
-extern void get_random_bytes(void *buf, int nbytes);
+extern void get_random_bytes(void *buf, size_t nbytes);
 extern int wait_for_random_bytes(void);
 extern int __init rand_initialize(void);
 extern bool rng_is_initialized(void);
-extern int add_random_ready_callback(struct random_ready_callback *rdy);
-extern void del_random_ready_callback(struct random_ready_callback *rdy);
-extern int __must_check get_random_bytes_arch(void *buf, int nbytes);
+extern int register_random_ready_notifier(struct notifier_block *nb);
+extern int unregister_random_ready_notifier(struct notifier_block *nb);
+extern size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes);
 
 #ifndef MODULE
-extern const struct file_operations random_fops, urandom_fops;
+extern const struct file_operations random_fops;
 #endif
 
 u32 get_random_u32(void);
@@ -87,7 +89,7 @@ static inline unsigned long get_random_canary(void)
 
 /* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes).
  * Returns the result of the call to wait_for_random_bytes. */
-static inline int get_random_bytes_wait(void *buf, int nbytes)
+static inline int get_random_bytes_wait(void *buf, size_t nbytes)
 {
 	int ret = wait_for_random_bytes();
 	get_random_bytes(buf, nbytes);
@@ -158,4 +160,9 @@ static inline bool __init arch_get_random_long_early(unsigned long *v)
 }
 #endif
 
+#ifdef CONFIG_SMP
+extern int random_prepare_cpu(unsigned int cpu);
+extern int random_online_cpu(unsigned int cpu);
+#endif
+
 #endif /* _LINUX_RANDOM_H */
diff --git a/include/trace/events/random.h b/include/trace/events/random.h
deleted file mode 100644
index a2d9aa16a5d7..000000000000
--- a/include/trace/events/random.h
+++ /dev/null
@@ -1,233 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM random
-
-#if !defined(_TRACE_RANDOM_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_RANDOM_H
-
-#include <linux/writeback.h>
-#include <linux/tracepoint.h>
-
-TRACE_EVENT(add_device_randomness,
-	TP_PROTO(int bytes, unsigned long IP),
-
-	TP_ARGS(bytes, IP),
-
-	TP_STRUCT__entry(
-		__field(	  int,	bytes			)
-		__field(unsigned long,	IP			)
-	),
-
-	TP_fast_assign(
-		__entry->bytes		= bytes;
-		__entry->IP		= IP;
-	),
-
-	TP_printk("bytes %d caller %pS",
-		__entry->bytes, (void *)__entry->IP)
-);
-
-DECLARE_EVENT_CLASS(random__mix_pool_bytes,
-	TP_PROTO(int bytes, unsigned long IP),
-
-	TP_ARGS(bytes, IP),
-
-	TP_STRUCT__entry(
-		__field(	  int,	bytes			)
-		__field(unsigned long,	IP			)
-	),
-
-	TP_fast_assign(
-		__entry->bytes		= bytes;
-		__entry->IP		= IP;
-	),
-
-	TP_printk("input pool: bytes %d caller %pS",
-		  __entry->bytes, (void *)__entry->IP)
-);
-
-DEFINE_EVENT(random__mix_pool_bytes, mix_pool_bytes,
-	TP_PROTO(int bytes, unsigned long IP),
-
-	TP_ARGS(bytes, IP)
-);
-
-DEFINE_EVENT(random__mix_pool_bytes, mix_pool_bytes_nolock,
-	TP_PROTO(int bytes, unsigned long IP),
-
-	TP_ARGS(bytes, IP)
-);
-
-TRACE_EVENT(credit_entropy_bits,
-	TP_PROTO(int bits, int entropy_count, unsigned long IP),
-
-	TP_ARGS(bits, entropy_count, IP),
-
-	TP_STRUCT__entry(
-		__field(	  int,	bits			)
-		__field(	  int,	entropy_count		)
-		__field(unsigned long,	IP			)
-	),
-
-	TP_fast_assign(
-		__entry->bits		= bits;
-		__entry->entropy_count	= entropy_count;
-		__entry->IP		= IP;
-	),
-
-	TP_printk("input pool: bits %d entropy_count %d caller %pS",
-		  __entry->bits, __entry->entropy_count, (void *)__entry->IP)
-);
-
-TRACE_EVENT(debit_entropy,
-	TP_PROTO(int debit_bits),
-
-	TP_ARGS( debit_bits),
-
-	TP_STRUCT__entry(
-		__field(	  int,	debit_bits		)
-	),
-
-	TP_fast_assign(
-		__entry->debit_bits	= debit_bits;
-	),
-
-	TP_printk("input pool: debit_bits %d", __entry->debit_bits)
-);
-
-TRACE_EVENT(add_input_randomness,
-	TP_PROTO(int input_bits),
-
-	TP_ARGS(input_bits),
-
-	TP_STRUCT__entry(
-		__field(	  int,	input_bits		)
-	),
-
-	TP_fast_assign(
-		__entry->input_bits	= input_bits;
-	),
-
-	TP_printk("input_pool_bits %d", __entry->input_bits)
-);
-
-TRACE_EVENT(add_disk_randomness,
-	TP_PROTO(dev_t dev, int input_bits),
-
-	TP_ARGS(dev, input_bits),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	  int,	input_bits		)
-	),
-
-	TP_fast_assign(
-		__entry->dev		= dev;
-		__entry->input_bits	= input_bits;
-	),
-
-	TP_printk("dev %d,%d input_pool_bits %d", MAJOR(__entry->dev),
-		  MINOR(__entry->dev), __entry->input_bits)
-);
-
-DECLARE_EVENT_CLASS(random__get_random_bytes,
-	TP_PROTO(int nbytes, unsigned long IP),
-
-	TP_ARGS(nbytes, IP),
-
-	TP_STRUCT__entry(
-		__field(	  int,	nbytes			)
-		__field(unsigned long,	IP			)
-	),
-
-	TP_fast_assign(
-		__entry->nbytes		= nbytes;
-		__entry->IP		= IP;
-	),
-
-	TP_printk("nbytes %d caller %pS", __entry->nbytes, (void *)__entry->IP)
-);
-
-DEFINE_EVENT(random__get_random_bytes, get_random_bytes,
-	TP_PROTO(int nbytes, unsigned long IP),
-
-	TP_ARGS(nbytes, IP)
-);
-
-DEFINE_EVENT(random__get_random_bytes, get_random_bytes_arch,
-	TP_PROTO(int nbytes, unsigned long IP),
-
-	TP_ARGS(nbytes, IP)
-);
-
-DECLARE_EVENT_CLASS(random__extract_entropy,
-	TP_PROTO(int nbytes, int entropy_count, unsigned long IP),
-
-	TP_ARGS(nbytes, entropy_count, IP),
-
-	TP_STRUCT__entry(
-		__field(	  int,	nbytes			)
-		__field(	  int,	entropy_count		)
-		__field(unsigned long,	IP			)
-	),
-
-	TP_fast_assign(
-		__entry->nbytes		= nbytes;
-		__entry->entropy_count	= entropy_count;
-		__entry->IP		= IP;
-	),
-
-	TP_printk("input pool: nbytes %d entropy_count %d caller %pS",
-		  __entry->nbytes, __entry->entropy_count, (void *)__entry->IP)
-);
-
-
-DEFINE_EVENT(random__extract_entropy, extract_entropy,
-	TP_PROTO(int nbytes, int entropy_count, unsigned long IP),
-
-	TP_ARGS(nbytes, entropy_count, IP)
-);
-
-TRACE_EVENT(urandom_read,
-	TP_PROTO(int got_bits, int pool_left, int input_left),
-
-	TP_ARGS(got_bits, pool_left, input_left),
-
-	TP_STRUCT__entry(
-		__field(	  int,	got_bits		)
-		__field(	  int,	pool_left		)
-		__field(	  int,	input_left		)
-	),
-
-	TP_fast_assign(
-		__entry->got_bits	= got_bits;
-		__entry->pool_left	= pool_left;
-		__entry->input_left	= input_left;
-	),
-
-	TP_printk("got_bits %d nonblocking_pool_entropy_left %d "
-		  "input_entropy_left %d", __entry->got_bits,
-		  __entry->pool_left, __entry->input_left)
-);
-
-TRACE_EVENT(prandom_u32,
-
-	TP_PROTO(unsigned int ret),
-
-	TP_ARGS(ret),
-
-	TP_STRUCT__entry(
-		__field(   unsigned int, ret)
-	),
-
-	TP_fast_assign(
-		__entry->ret = ret;
-	),
-
-	TP_printk("ret=%u" , __entry->ret)
-);
-
-#endif /* _TRACE_RANDOM_H */
-
-/* This part must be outside protection */
-#include <trace/define_trace.h>
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 407a2568f35e..238cba15449f 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -34,6 +34,7 @@
 #include <linux/scs.h>
 #include <linux/percpu-rwsem.h>
 #include <linux/cpuset.h>
+#include <linux/random.h>
 
 #include <trace/events/power.h>
 #define CREATE_TRACE_POINTS
@@ -1659,6 +1660,11 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 		.startup.single		= perf_event_init_cpu,
 		.teardown.single	= perf_event_exit_cpu,
 	},
+	[CPUHP_RANDOM_PREPARE] = {
+		.name			= "random:prepare",
+		.startup.single		= random_prepare_cpu,
+		.teardown.single	= NULL,
+	},
 	[CPUHP_WORKQUEUE_PREP] = {
 		.name			= "workqueue:prepare",
 		.startup.single		= workqueue_prepare_cpu,
@@ -1782,6 +1788,11 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 		.startup.single		= workqueue_online_cpu,
 		.teardown.single	= workqueue_offline_cpu,
 	},
+	[CPUHP_AP_RANDOM_ONLINE] = {
+		.name			= "random:online",
+		.startup.single		= random_online_cpu,
+		.teardown.single	= NULL,
+	},
 	[CPUHP_AP_RCUTREE_ONLINE] = {
 		.name			= "RCU/tree:online",
 		.startup.single		= rcutree_online_cpu,
diff --git a/lib/random32.c b/lib/random32.c
index a57a0e18819d..976632003ec6 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -41,7 +41,6 @@
 #include <linux/bitops.h>
 #include <linux/slab.h>
 #include <asm/unaligned.h>
-#include <trace/events/random.h>
 
 /**
  *	prandom_u32_state - seeded pseudo-random number generator.
@@ -387,7 +386,6 @@ u32 prandom_u32(void)
 	struct siprand_state *state = get_cpu_ptr(&net_rand_state);
 	u32 res = siprand_u32(state);
 
-	trace_prandom_u32(res);
 	put_cpu_ptr(&net_rand_state);
 	return res;
 }
@@ -553,9 +551,11 @@ static void prandom_reseed(struct timer_list *unused)
  * To avoid worrying about whether it's safe to delay that interrupt
  * long enough to seed all CPUs, just schedule an immediate timer event.
  */
-static void prandom_timer_start(struct random_ready_callback *unused)
+static int prandom_timer_start(struct notifier_block *nb,
+			       unsigned long action, void *data)
 {
 	mod_timer(&seed_timer, jiffies);
+	return 0;
 }
 
 #ifdef CONFIG_RANDOM32_SELFTEST
@@ -619,13 +619,13 @@ core_initcall(prandom32_state_selftest);
  */
 static int __init prandom_init_late(void)
 {
-	static struct random_ready_callback random_ready = {
-		.func = prandom_timer_start
+	static struct notifier_block random_ready = {
+		.notifier_call = prandom_timer_start
 	};
-	int ret = add_random_ready_callback(&random_ready);
+	int ret = register_random_ready_notifier(&random_ready);
 
 	if (ret == -EALREADY) {
-		prandom_timer_start(&random_ready);
+		prandom_timer_start(&random_ready, 0, NULL);
 		ret = 0;
 	}
 	return ret;
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 3b8129dd374c..36574a806a81 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -757,14 +757,16 @@ static void enable_ptr_key_workfn(struct work_struct *work)
 
 static DECLARE_WORK(enable_ptr_key_work, enable_ptr_key_workfn);
 
-static void fill_random_ptr_key(struct random_ready_callback *unused)
+static int fill_random_ptr_key(struct notifier_block *nb,
+			       unsigned long action, void *data)
 {
 	/* This may be in an interrupt handler. */
 	queue_work(system_unbound_wq, &enable_ptr_key_work);
+	return 0;
 }
 
-static struct random_ready_callback random_ready = {
-	.func = fill_random_ptr_key
+static struct notifier_block random_ready = {
+	.notifier_call = fill_random_ptr_key
 };
 
 static int __init initialize_ptr_random(void)
@@ -778,7 +780,7 @@ static int __init initialize_ptr_random(void)
 		return 0;
 	}
 
-	ret = add_random_ready_callback(&random_ready);
+	ret = register_random_ready_notifier(&random_ready);
 	if (!ret) {
 		return 0;
 	} else if (ret == -EALREADY) {