diff options
37 files changed, 1121 insertions, 18 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 07f753f039d2..644fc7b545e0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -19057,7 +19057,13 @@ S: Maintained 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: include/linux/random.h +F: include/uapi/linux/random.h F: drivers/virt/vmgenid.c +F: include/vdso/getrandom.h +F: lib/vdso/getrandom.c +F: arch/x86/entry/vdso/vgetrandom* +F: arch/x86/include/asm/vdso/getrandom* RAPIDIO SUBSYSTEM M: Matt Porter <mporter@kernel.crashing.org> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cbe5fac4b9dd..007bab9f2a0e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -287,6 +287,7 @@ config X86 select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_USER_RETURN_NOTIFIER select HAVE_GENERIC_VDSO + select VDSO_GETRANDOM if X86_64 select HOTPLUG_PARALLEL if SMP && X86_64 select HOTPLUG_SMT if SMP select HOTPLUG_SPLIT_STARTUP if SMP && X86_32 diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 215a1b202a91..c9216ac4fb1e 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -7,7 +7,7 @@ include $(srctree)/lib/vdso/Makefile # Files to link into the vDSO: -vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o +vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o vgetrandom.o vgetrandom-chacha.o vobjs32-y := vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o vobjs32-y += vdso32/vclock_gettime.o vdso32/vgetcpu.o vobjs-$(CONFIG_X86_SGX) += vsgx.o @@ -73,6 +73,7 @@ CFLAGS_REMOVE_vdso32/vclock_gettime.o = -pg CFLAGS_REMOVE_vgetcpu.o = -pg CFLAGS_REMOVE_vdso32/vgetcpu.o = -pg CFLAGS_REMOVE_vsgx.o = -pg +CFLAGS_REMOVE_vgetrandom.o = -pg # # X32 processes use x32 vDSO to access 64bit kernel data. diff --git a/arch/x86/entry/vdso/vdso.lds.S b/arch/x86/entry/vdso/vdso.lds.S index e8c60ae7a7c8..0bab5f4af6d1 100644 --- a/arch/x86/entry/vdso/vdso.lds.S +++ b/arch/x86/entry/vdso/vdso.lds.S @@ -30,6 +30,8 @@ VERSION { #ifdef CONFIG_X86_SGX __vdso_sgx_enter_enclave; #endif + getrandom; + __vdso_getrandom; local: *; }; } diff --git a/arch/x86/entry/vdso/vgetrandom-chacha.S b/arch/x86/entry/vdso/vgetrandom-chacha.S new file mode 100644 index 000000000000..bcba5639b8ee --- /dev/null +++ b/arch/x86/entry/vdso/vgetrandom-chacha.S @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + */ + +#include <linux/linkage.h> +#include <asm/frame.h> + +.section .rodata, "a" +.align 16 +CONSTANTS: .octa 0x6b20657479622d323320646e61707865 +.text + +/* + * Very basic SSE2 implementation of ChaCha20. Produces a given positive number + * of blocks of output with a nonce of 0, taking an input key and 8-byte + * counter. Importantly does not spill to the stack. Its arguments are: + * + * rdi: output bytes + * rsi: 32-byte key input + * rdx: 8-byte counter input/output + * rcx: number of 64-byte blocks to write to output + */ +SYM_FUNC_START(__arch_chacha20_blocks_nostack) + +.set output, %rdi +.set key, %rsi +.set counter, %rdx +.set nblocks, %rcx +.set i, %al +/* xmm registers are *not* callee-save. */ +.set temp, %xmm0 +.set state0, %xmm1 +.set state1, %xmm2 +.set state2, %xmm3 +.set state3, %xmm4 +.set copy0, %xmm5 +.set copy1, %xmm6 +.set copy2, %xmm7 +.set copy3, %xmm8 +.set one, %xmm9 + + /* copy0 = "expand 32-byte k" */ + movaps CONSTANTS(%rip),copy0 + /* copy1,copy2 = key */ + movups 0x00(key),copy1 + movups 0x10(key),copy2 + /* copy3 = counter || zero nonce */ + movq 0x00(counter),copy3 + /* one = 1 || 0 */ + movq $1,%rax + movq %rax,one + +.Lblock: + /* state0,state1,state2,state3 = copy0,copy1,copy2,copy3 */ + movdqa copy0,state0 + movdqa copy1,state1 + movdqa copy2,state2 + movdqa copy3,state3 + + movb $10,i +.Lpermute: + /* state0 += state1, state3 = rotl32(state3 ^ state0, 16) */ + paddd state1,state0 + pxor state0,state3 + movdqa state3,temp + pslld $16,temp + psrld $16,state3 + por temp,state3 + + /* state2 += state3, state1 = rotl32(state1 ^ state2, 12) */ + paddd state3,state2 + pxor state2,state1 + movdqa state1,temp + pslld $12,temp + psrld $20,state1 + por temp,state1 + + /* state0 += state1, state3 = rotl32(state3 ^ state0, 8) */ + paddd state1,state0 + pxor state0,state3 + movdqa state3,temp + pslld $8,temp + psrld $24,state3 + por temp,state3 + + /* state2 += state3, state1 = rotl32(state1 ^ state2, 7) */ + paddd state3,state2 + pxor state2,state1 + movdqa state1,temp + pslld $7,temp + psrld $25,state1 + por temp,state1 + + /* state1[0,1,2,3] = state1[1,2,3,0] */ + pshufd $0x39,state1,state1 + /* state2[0,1,2,3] = state2[2,3,0,1] */ + pshufd $0x4e,state2,state2 + /* state3[0,1,2,3] = state3[3,0,1,2] */ + pshufd $0x93,state3,state3 + + /* state0 += state1, state3 = rotl32(state3 ^ state0, 16) */ + paddd state1,state0 + pxor state0,state3 + movdqa state3,temp + pslld $16,temp + psrld $16,state3 + por temp,state3 + + /* state2 += state3, state1 = rotl32(state1 ^ state2, 12) */ + paddd state3,state2 + pxor state2,state1 + movdqa state1,temp + pslld $12,temp + psrld $20,state1 + por temp,state1 + + /* state0 += state1, state3 = rotl32(state3 ^ state0, 8) */ + paddd state1,state0 + pxor state0,state3 + movdqa state3,temp + pslld $8,temp + psrld $24,state3 + por temp,state3 + + /* state2 += state3, state1 = rotl32(state1 ^ state2, 7) */ + paddd state3,state2 + pxor state2,state1 + movdqa state1,temp + pslld $7,temp + psrld $25,state1 + por temp,state1 + + /* state1[0,1,2,3] = state1[3,0,1,2] */ + pshufd $0x93,state1,state1 + /* state2[0,1,2,3] = state2[2,3,0,1] */ + pshufd $0x4e,state2,state2 + /* state3[0,1,2,3] = state3[1,2,3,0] */ + pshufd $0x39,state3,state3 + + decb i + jnz .Lpermute + + /* output0 = state0 + copy0 */ + paddd copy0,state0 + movups state0,0x00(output) + /* output1 = state1 + copy1 */ + paddd copy1,state1 + movups state1,0x10(output) + /* output2 = state2 + copy2 */ + paddd copy2,state2 + movups state2,0x20(output) + /* output3 = state3 + copy3 */ + paddd copy3,state3 + movups state3,0x30(output) + + /* ++copy3.counter */ + paddq one,copy3 + + /* output += 64, --nblocks */ + addq $64,output + decq nblocks + jnz .Lblock + + /* counter = copy3.counter */ + movq copy3,0x00(counter) + + /* Zero out the potentially sensitive regs, in case nothing uses these again. */ + pxor state0,state0 + pxor state1,state1 + pxor state2,state2 + pxor state3,state3 + pxor copy1,copy1 + pxor copy2,copy2 + pxor temp,temp + + ret +SYM_FUNC_END(__arch_chacha20_blocks_nostack) diff --git a/arch/x86/entry/vdso/vgetrandom.c b/arch/x86/entry/vdso/vgetrandom.c new file mode 100644 index 000000000000..52d3c7faae2e --- /dev/null +++ b/arch/x86/entry/vdso/vgetrandom.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + */ +#include <linux/types.h> + +#include "../../../../lib/vdso/getrandom.c" + +ssize_t __vdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len); + +ssize_t __vdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len) +{ + return __cvdso_getrandom(buffer, len, flags, opaque_state, opaque_len); +} + +ssize_t getrandom(void *, size_t, unsigned int, void *, size_t) + __attribute__((weak, alias("__vdso_getrandom"))); diff --git a/arch/x86/include/asm/vdso/getrandom.h b/arch/x86/include/asm/vdso/getrandom.h new file mode 100644 index 000000000000..b96e674cafde --- /dev/null +++ b/arch/x86/include/asm/vdso/getrandom.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + */ +#ifndef __ASM_VDSO_GETRANDOM_H +#define __ASM_VDSO_GETRANDOM_H + +#ifndef __ASSEMBLY__ + +#include <asm/unistd.h> +#include <asm/vvar.h> + +/** + * getrandom_syscall - Invoke the getrandom() syscall. + * @buffer: Destination buffer to fill with random bytes. + * @len: Size of @buffer in bytes. + * @flags: Zero or more GRND_* flags. + * Returns: The number of random bytes written to @buffer, or a negative value indicating an error. + */ +static __always_inline ssize_t getrandom_syscall(void *buffer, size_t len, unsigned int flags) +{ + long ret; + + asm ("syscall" : "=a" (ret) : + "0" (__NR_getrandom), "D" (buffer), "S" (len), "d" (flags) : + "rcx", "r11", "memory"); + + return ret; +} + +#define __vdso_rng_data (VVAR(_vdso_rng_data)) + +static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void) +{ + if (IS_ENABLED(CONFIG_TIME_NS) && __vdso_data->clock_mode == VDSO_CLOCKMODE_TIMENS) + return (void *)&__vdso_rng_data + ((void *)&__timens_vdso_data - (void *)&__vdso_data); + return &__vdso_rng_data; +} + +/** + * __arch_chacha20_blocks_nostack - Generate ChaCha20 stream without using the stack. + * @dst_bytes: Destination buffer to hold @nblocks * 64 bytes of output. + * @key: 32-byte input key. + * @counter: 8-byte counter, read on input and updated on return. + * @nblocks: Number of blocks to generate. + * + * Generates a given positive number of blocks of ChaCha20 output with nonce=0, and does not write + * to any stack or memory outside of the parameters passed to it, in order to mitigate stack data + * leaking into forked child processes. + */ +extern void __arch_chacha20_blocks_nostack(u8 *dst_bytes, const u32 *key, u32 *counter, size_t nblocks); + +#endif /* !__ASSEMBLY__ */ + +#endif /* __ASM_VDSO_GETRANDOM_H */ diff --git a/arch/x86/include/asm/vdso/vsyscall.h b/arch/x86/include/asm/vdso/vsyscall.h index 93226281b450..972415a8be31 100644 --- a/arch/x86/include/asm/vdso/vsyscall.h +++ b/arch/x86/include/asm/vdso/vsyscall.h @@ -10,6 +10,8 @@ #include <asm/vvar.h> DEFINE_VVAR(struct vdso_data, _vdso_data); +DEFINE_VVAR_SINGLE(struct vdso_rng_data, _vdso_rng_data); + /* * Update the vDSO data page to keep in sync with kernel timekeeping. */ diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h index 183e98e49ab9..9d9af37f7cab 100644 --- a/arch/x86/include/asm/vvar.h +++ b/arch/x86/include/asm/vvar.h @@ -26,6 +26,8 @@ */ #define DECLARE_VVAR(offset, type, name) \ EMIT_VVAR(name, offset) +#define DECLARE_VVAR_SINGLE(offset, type, name) \ + EMIT_VVAR(name, offset) #else @@ -37,6 +39,10 @@ extern char __vvar_page; extern type timens_ ## name[CS_BASES] \ __attribute__((visibility("hidden"))); \ +#define DECLARE_VVAR_SINGLE(offset, type, name) \ + extern type vvar_ ## name \ + __attribute__((visibility("hidden"))); \ + #define VVAR(name) (vvar_ ## name) #define TIMENS(name) (timens_ ## name) @@ -44,12 +50,22 @@ extern char __vvar_page; type name[CS_BASES] \ __attribute__((section(".vvar_" #name), aligned(16))) __visible +#define DEFINE_VVAR_SINGLE(type, name) \ + type name \ + __attribute__((section(".vvar_" #name), aligned(16))) __visible + #endif /* DECLARE_VVAR(offset, type, name) */ DECLARE_VVAR(128, struct vdso_data, _vdso_data) +#if !defined(_SINGLE_DATA) +#define _SINGLE_DATA +DECLARE_VVAR_SINGLE(640, struct vdso_rng_data, _vdso_rng_data) +#endif + #undef DECLARE_VVAR +#undef DECLARE_VVAR_SINGLE #endif 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 <Jason@zx2c4.com>. All Rights Reserved. + * Copyright (C) 2017-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * Copyright Matt Mackall <mpm@selenic.com>, 2003, 2004, 2005 * Copyright Theodore Ts'o, 1994, 1995, 1996, 1997, 1998, 1999. All rights reserved. * @@ -56,6 +56,10 @@ #include <linux/sched/isolation.h> #include <crypto/chacha.h> #include <crypto/blake2s.h> +#ifdef CONFIG_VDSO_GETRANDOM +#include <vdso/getrandom.h> +#include <vdso/datapage.h> +#endif #include <asm/archrandom.h> #include <asm/processor.h> #include <asm/irq.h> @@ -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/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 775a2e8d600c..5f171ad7b436 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -988,6 +988,7 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_SHADOW_STACK)] = "ss", #endif #ifdef CONFIG_64BIT + [ilog2(VM_DROPPABLE)] = "dp", [ilog2(VM_SEALED)] = "sl", #endif }; diff --git a/include/linux/mm.h b/include/linux/mm.h index 7d044e737dba..aa4fccb2a693 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -407,6 +407,13 @@ extern unsigned int kobjsize(const void *objp); #endif #ifdef CONFIG_64BIT +#define VM_DROPPABLE_BIT 40 +#define VM_DROPPABLE BIT(VM_DROPPABLE_BIT) +#else +#define VM_DROPPABLE VM_NONE +#endif + +#ifdef CONFIG_64BIT /* VM is sealed, in vm_flags */ #define VM_SEALED _BITUL(63) #endif diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 05d59f74fc88..a12bcf042551 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -218,6 +218,9 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, { vm_flags &= __VM_UFFD_FLAGS; + if (vm_flags & VM_DROPPABLE) + return false; + if ((vm_flags & VM_UFFD_MINOR) && (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma))) return false; diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index e46d6e82765e..b63d211bd141 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -165,6 +165,12 @@ IF_HAVE_PG_ARCH_X(arch_3) # define IF_HAVE_UFFD_MINOR(flag, name) #endif +#ifdef CONFIG_64BIT +# define IF_HAVE_VM_DROPPABLE(flag, name) {flag, name}, +#else +# define IF_HAVE_VM_DROPPABLE(flag, name) +#endif + #define __def_vmaflag_names \ {VM_READ, "read" }, \ {VM_WRITE, "write" }, \ @@ -197,6 +203,7 @@ IF_HAVE_VM_SOFTDIRTY(VM_SOFTDIRTY, "softdirty" ) \ {VM_MIXEDMAP, "mixedmap" }, \ {VM_HUGEPAGE, "hugepage" }, \ {VM_NOHUGEPAGE, "nohugepage" }, \ +IF_HAVE_VM_DROPPABLE(VM_DROPPABLE, "droppable" ) \ {VM_MERGEABLE, "mergeable" } \ #define show_vma_flags(flags) \ diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h index a246e11988d5..e89d00528f2f 100644 --- a/include/uapi/linux/mman.h +++ b/include/uapi/linux/mman.h @@ -17,6 +17,7 @@ #define MAP_SHARED 0x01 /* Share changes */ #define MAP_PRIVATE 0x02 /* Changes are private */ #define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ +#define MAP_DROPPABLE 0x08 /* Zero memory under memory pressure. */ /* * Huge page size encoding when MAP_HUGETLB is specified, and a huge page diff --git a/include/uapi/linux/random.h b/include/uapi/linux/random.h index e744c23582eb..1dd047ec98a1 100644 --- a/include/uapi/linux/random.h +++ b/include/uapi/linux/random.h @@ -20,7 +20,7 @@ /* Add to (or subtract from) the entropy count. (Superuser only.) */ #define RNDADDTOENTCNT _IOW( 'R', 0x01, int ) -/* Get the contents of the entropy pool. (Superuser only.) */ +/* Get the contents of the entropy pool. (Superuser only.) (Removed in 2.6.9-rc2.) */ #define RNDGETPOOL _IOR( 'R', 0x02, int [2] ) /* @@ -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 7647e0946f50..b85f24cac3f5 100644 --- a/include/vdso/datapage.h +++ b/include/vdso/datapage.h @@ -117,6 +117,16 @@ 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 @@ -128,6 +138,7 @@ 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 <Jason@zx2c4.com>. All Rights Reserved. + */ + +#ifndef _VDSO_GETRANDOM_H +#define _VDSO_GETRANDOM_H + +#include <linux/types.h> + +#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 <Jason@zx2c4.com>. All Rights Reserved. + */ + +#include <linux/cache.h> +#include <linux/kernel.h> +#include <linux/time64.h> +#include <vdso/datapage.h> +#include <vdso/getrandom.h> +#include <asm/vdso/getrandom.h> +#include <asm/vdso/vsyscall.h> +#include <asm/unaligned.h> +#include <uapi/linux/mman.h> + +#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 t |