diff --git a/MAINTAINERS b/MAINTAINERS index 2a4d4b3a9b40..7edb30b4abf0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18745,6 +18745,8 @@ T: git https://git.kernel.org/pub/scm/linux/kernel/git/crng/random.git F: Documentation/devicetree/bindings/rng/microsoft,vmgenid.yaml F: drivers/char/random.c F: drivers/virt/vmgenid.c +F: include/vdso/getrandom.h +F: lib/vdso/getrandom.c RAPIDIO SUBSYSTEM M: Matt Porter diff --git a/drivers/char/random.c b/drivers/char/random.c index 2597cb43f438..b02a12436750 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* - * Copyright (C) 2017-2022 Jason A. Donenfeld . All Rights Reserved. + * Copyright (C) 2017-2024 Jason A. Donenfeld . All Rights Reserved. * Copyright Matt Mackall , 2003, 2004, 2005 * Copyright Theodore Ts'o, 1994, 1995, 1996, 1997, 1998, 1999. All rights reserved. * @@ -56,6 +56,10 @@ #include #include #include +#ifdef CONFIG_VDSO_GETRANDOM +#include +#include +#endif #include #include #include @@ -271,6 +275,15 @@ static void crng_reseed(struct work_struct *work) if (next_gen == ULONG_MAX) ++next_gen; WRITE_ONCE(base_crng.generation, next_gen); +#ifdef CONFIG_VDSO_GETRANDOM + /* base_crng.generation's invalid value is ULONG_MAX, while + * _vdso_rng_data.generation's invalid value is 0, so add one to the + * former to arrive at the latter. Use smp_store_release so that this + * is ordered with the write above to base_crng.generation. Pairs with + * the smp_rmb() before the syscall in the vDSO code. + */ + smp_store_release(&_vdso_rng_data.generation, next_gen + 1); +#endif if (!static_branch_likely(&crng_is_ready)) crng_init = CRNG_READY; spin_unlock_irqrestore(&base_crng.lock, flags); @@ -721,6 +734,9 @@ static void __cold _credit_init_bits(size_t bits) if (static_key_initialized && system_unbound_wq) queue_work(system_unbound_wq, &set_ready); atomic_notifier_call_chain(&random_ready_notifier, 0, NULL); +#ifdef CONFIG_VDSO_GETRANDOM + WRITE_ONCE(_vdso_rng_data.is_ready, true); +#endif wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); pr_notice("crng init done\n"); diff --git a/include/uapi/linux/random.h b/include/uapi/linux/random.h index e744c23582eb..2a3fe4c2cdc9 100644 --- a/include/uapi/linux/random.h +++ b/include/uapi/linux/random.h @@ -55,4 +55,19 @@ struct rand_pool_info { #define GRND_RANDOM 0x0002 #define GRND_INSECURE 0x0004 +/** + * struct vgetrandom_opaque_params - arguments for allocating memory for vgetrandom + * + * @size_per_opaque_state: Size of each state that is to be passed to vgetrandom(). + * @mmap_prot: Value of the prot argument in mmap(2). + * @mmap_flags: Value of the flags argument in mmap(2). + * @reserved: Reserved for future use. + */ +struct vgetrandom_opaque_params { + __u32 size_of_opaque_state; + __u32 mmap_prot; + __u32 mmap_flags; + __u32 reserved[13]; +}; + #endif /* _UAPI_LINUX_RANDOM_H */ diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h index d04d394db064..05e5787beb73 100644 --- a/include/vdso/datapage.h +++ b/include/vdso/datapage.h @@ -113,6 +113,16 @@ struct vdso_data { struct arch_vdso_data arch_data; }; +/** + * struct vdso_rng_data - vdso RNG state information + * @generation: counter representing the number of RNG reseeds + * @is_ready: boolean signaling whether the RNG is initialized + */ +struct vdso_rng_data { + u64 generation; + u8 is_ready; +}; + /* * We use the hidden visibility to prevent the compiler from generating a GOT * relocation. Not only is going through a GOT useless (the entry couldn't and @@ -124,6 +134,7 @@ struct vdso_data { */ extern struct vdso_data _vdso_data[CS_BASES] __attribute__((visibility("hidden"))); extern struct vdso_data _timens_data[CS_BASES] __attribute__((visibility("hidden"))); +extern struct vdso_rng_data _vdso_rng_data __attribute__((visibility("hidden"))); /** * union vdso_data_store - Generic vDSO data page diff --git a/include/vdso/getrandom.h b/include/vdso/getrandom.h new file mode 100644 index 000000000000..a8b7c14b0ae0 --- /dev/null +++ b/include/vdso/getrandom.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022-2024 Jason A. Donenfeld . All Rights Reserved. + */ + +#ifndef _VDSO_GETRANDOM_H +#define _VDSO_GETRANDOM_H + +#include + +#define CHACHA_KEY_SIZE 32 +#define CHACHA_BLOCK_SIZE 64 + +/** + * struct vgetrandom_state - State used by vDSO getrandom(). + * + * @batch: One and a half ChaCha20 blocks of buffered RNG output. + * + * @key: Key to be used for generating next batch. + * + * @batch_key: Union of the prior two members, which is exactly two full + * ChaCha20 blocks in size, so that @batch and @key can be filled + * together. + * + * @generation: Snapshot of @rng_info->generation in the vDSO data page at + * the time @key was generated. + * + * @pos: Offset into @batch of the next available random byte. + * + * @in_use: Reentrancy guard for reusing a state within the same thread + * due to signal handlers. + */ +struct vgetrandom_state { + union { + struct { + u8 batch[CHACHA_BLOCK_SIZE * 3 / 2]; + u32 key[CHACHA_KEY_SIZE / sizeof(u32)]; + }; + u8 batch_key[CHACHA_BLOCK_SIZE * 2]; + }; + u64 generation; + u8 pos; + bool in_use; +}; + +#endif /* _VDSO_GETRANDOM_H */ diff --git a/lib/vdso/Kconfig b/lib/vdso/Kconfig index c46c2300517c..82fe827af542 100644 --- a/lib/vdso/Kconfig +++ b/lib/vdso/Kconfig @@ -38,3 +38,8 @@ config GENERIC_VDSO_OVERFLOW_PROTECT in the hotpath. endif + +config VDSO_GETRANDOM + bool + help + Selected by architectures that support vDSO getrandom(). diff --git a/lib/vdso/getrandom.c b/lib/vdso/getrandom.c new file mode 100644 index 000000000000..b230f0b10832 --- /dev/null +++ b/lib/vdso/getrandom.c @@ -0,0 +1,251 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024 Jason A. Donenfeld . All Rights Reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define MEMCPY_AND_ZERO_SRC(type, dst, src, len) do { \ + while (len >= sizeof(type)) { \ + __put_unaligned_t(type, __get_unaligned_t(type, src), dst); \ + __put_unaligned_t(type, 0, src); \ + dst += sizeof(type); \ + src += sizeof(type); \ + len -= sizeof(type); \ + } \ +} while (0) + +static void memcpy_and_zero_src(void *dst, void *src, size_t len) +{ + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) { + if (IS_ENABLED(CONFIG_64BIT)) + MEMCPY_AND_ZERO_SRC(u64, dst, src, len); + MEMCPY_AND_ZERO_SRC(u32, dst, src, len); + MEMCPY_AND_ZERO_SRC(u16, dst, src, len); + } + MEMCPY_AND_ZERO_SRC(u8, dst, src, len); +} + +/** + * __cvdso_getrandom_data - Generic vDSO implementation of getrandom() syscall. + * @rng_info: Describes state of kernel RNG, memory shared with kernel. + * @buffer: Destination buffer to fill with random bytes. + * @len: Size of @buffer in bytes. + * @flags: Zero or more GRND_* flags. + * @opaque_state: Pointer to an opaque state area. + * @opaque_len: Length of opaque state area. + * + * This implements a "fast key erasure" RNG using ChaCha20, in the same way that the kernel's + * getrandom() syscall does. It periodically reseeds its key from the kernel's RNG, at the same + * schedule that the kernel's RNG is reseeded. If the kernel's RNG is not ready, then this always + * calls into the syscall. + * + * If @buffer, @len, and @flags are 0, and @opaque_len is ~0UL, then @opaque_state is populated + * with a struct vgetrandom_opaque_params and the function returns 0; if it does not return 0, + * this function should not be used. + * + * @opaque_state *must* be allocated by calling mmap(2) using the mmap_prot and mmap_flags fields + * from the struct vgetrandom_opaque_params, and states must not straddle pages. Unless external + * locking is used, one state must be allocated per thread, as it is not safe to call this function + * concurrently with the same @opaque_state. However, it is safe to call this using the same + * @opaque_state that is shared between main code and signal handling code, within the same thread. + * + * Returns: The number of random bytes written to @buffer, or a negative value indicating an error. + */ +static __always_inline ssize_t +__cvdso_getrandom_data(const struct vdso_rng_data *rng_info, void *buffer, size_t len, + unsigned int flags, void *opaque_state, size_t opaque_len) +{ + ssize_t ret = min_t(size_t, INT_MAX & PAGE_MASK /* = MAX_RW_COUNT */, len); + struct vgetrandom_state *state = opaque_state; + size_t batch_len, nblocks, orig_len = len; + bool in_use, have_retried = false; + unsigned long current_generation; + void *orig_buffer = buffer; + u32 counter[2] = { 0 }; + + if (unlikely(opaque_len == ~0UL && !buffer && !len && !flags)) { + *(struct vgetrandom_opaque_params *)opaque_state = (struct vgetrandom_opaque_params) { + .size_of_opaque_state = sizeof(*state), + .mmap_prot = PROT_READ | PROT_WRITE, + .mmap_flags = MAP_DROPPABLE | MAP_ANONYMOUS + }; + return 0; + } + + /* The state must not straddle a page, since pages can be zeroed at any time. */ + if (unlikely(((unsigned long)opaque_state & ~PAGE_MASK) + sizeof(*state) > PAGE_SIZE)) + return -EFAULT; + + /* If the caller passes the wrong size, which might happen due to CRIU, fallback. */ + if (unlikely(opaque_len != sizeof(*state))) + goto fallback_syscall; + + /* + * If the kernel's RNG is not yet ready, then it's not possible to provide random bytes from + * userspace, because A) the various @flags require this to block, or not, depending on + * various factors unavailable to userspace, and B) the kernel's behavior before the RNG is + * ready is to reseed from the entropy pool at every invocation. + */ + if (unlikely(!READ_ONCE(rng_info->is_ready))) + goto fallback_syscall; + + /* + * This condition is checked after @rng_info->is_ready, because before the kernel's RNG is + * initialized, the @flags parameter may require this to block or return an error, even when + * len is zero. + */ + if (unlikely(!len)) + return 0; + + /* + * @state->in_use is basic reentrancy protection against this running in a signal handler + * with the same @opaque_state, but obviously not atomic wrt multiple CPUs or more than one + * level of reentrancy. If a signal interrupts this after reading @state->in_use, but before + * writing @state->in_use, there is still no race, because the signal handler will run to + * its completion before returning execution. + */ + in_use = READ_ONCE(state->in_use); + if (unlikely(in_use)) + /* The syscall simply fills the buffer and does not touch @state, so fallback. */ + goto fallback_syscall; + WRITE_ONCE(state->in_use, true); + +retry_generation: + /* + * @rng_info->generation must always be read here, as it serializes @state->key with the + * kernel's RNG reseeding schedule. + */ + current_generation = READ_ONCE(rng_info->generation); + + /* + * If @state->generation doesn't match the kernel RNG's generation, then it means the + * kernel's RNG has reseeded, and so @state->key is reseeded as well. + */ + if (unlikely(state->generation != current_generation)) { + /* + * Write the generation before filling the key, in case of fork. If there is a fork + * just after this line, the parent and child will get different random bytes from + * the syscall, which is good. However, were this line to occur after the getrandom + * syscall, then both child and parent could have the same bytes and the same + * generation counter, so the fork would not be detected. Therefore, write + * @state->generation before the call to the getrandom syscall. + */ + WRITE_ONCE(state->generation, current_generation); + + /* + * Prevent the syscall from being reordered wrt current_generation. Pairs with the + * smp_store_release(&_vdso_rng_data.generation) in random.c. + */ + smp_rmb(); + + /* Reseed @state->key using fresh bytes from the kernel. */ + if (getrandom_syscall(state->key, sizeof(state->key), 0) != sizeof(state->key)) { + /* + * If the syscall failed to refresh the key, then @state->key is now + * invalid, so invalidate the generation so that it is not used again, and + * fallback to using the syscall entirely. + */ + WRITE_ONCE(state->generation, 0); + + /* + * Set @state->in_use to false only after the last write to @state in the + * line above. + */ + WRITE_ONCE(state->in_use, false); + + goto fallback_syscall; + } + + /* + * Set @state->pos to beyond the end of the batch, so that the batch is refilled + * using the new key. + */ + state->pos = sizeof(state->batch); + } + + /* Set len to the total amount of bytes that this function is allowed to read, ret. */ + len = ret; +more_batch: + /* + * First use bytes out of @state->batch, which may have been filled by the last call to this + * function. + */ + batch_len = min_t(size_t, sizeof(state->batch) - state->pos, len); + if (batch_len) { + /* Zeroing at the same time as memcpying helps preserve forward secrecy. */ + memcpy_and_zero_src(buffer, state->batch + state->pos, batch_len); + state->pos += batch_len; + buffer += batch_len; + len -= batch_len; + } + + if (!len) { + /* Prevent the loop from being reordered wrt ->generation. */ + barrier(); + + /* + * Since @rng_info->generation will never be 0, re-read @state->generation, rather + * than using the local current_generation variable, to learn whether a fork + * occurred or if @state was zeroed due to memory pressure. Primarily, though, this + * indicates whether the kernel's RNG has reseeded, in which case generate a new key + * and start over. + */ + if (unlikely(READ_ONCE(state->generation) != READ_ONCE(rng_info->generation))) { + /* + * Prevent this from looping forever in case of low memory or racing with a + * user force-reseeding the kernel's RNG using the ioctl. + */ + if (have_retried) { + WRITE_ONCE(state->in_use, false); + goto fallback_syscall; + } + + have_retried = true; + buffer = orig_buffer; + goto retry_generation; + } + + /* + * Set @state->in_use to false only when there will be no more reads or writes of + * @state. + */ + WRITE_ONCE(state->in_use, false); + return ret; + } + + /* Generate blocks of RNG output directly into @buffer while there's enough room left. */ + nblocks = len / CHACHA_BLOCK_SIZE; + if (nblocks) { + __arch_chacha20_blocks_nostack(buffer, state->key, counter, nblocks); + buffer += nblocks * CHACHA_BLOCK_SIZE; + len -= nblocks * CHACHA_BLOCK_SIZE; + } + + BUILD_BUG_ON(sizeof(state->batch_key) % CHACHA_BLOCK_SIZE != 0); + + /* Refill the batch and overwrite the key, in order to preserve forward secrecy. */ + __arch_chacha20_blocks_nostack(state->batch_key, state->key, counter, + sizeof(state->batch_key) / CHACHA_BLOCK_SIZE); + + /* Since the batch was just refilled, set the position back to 0 to indicate a full batch. */ + state->pos = 0; + goto more_batch; + +fallback_syscall: + return getrandom_syscall(orig_buffer, orig_len, flags); +} + +static __always_inline ssize_t +__cvdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len) +{ + return __cvdso_getrandom_data(__arch_get_vdso_rng_data(), buffer, len, flags, opaque_state, opaque_len); +}