From nobody Sat May 4 05:59:43 2024 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 44541C4332F for ; Mon, 5 Dec 2022 02:01:21 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231330AbiLECBT (ORCPT ); Sun, 4 Dec 2022 21:01:19 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:48550 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231225AbiLECBJ (ORCPT ); Sun, 4 Dec 2022 21:01:09 -0500 Received: from dfw.source.kernel.org (dfw.source.kernel.org [139.178.84.217]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 697DC12D08; Sun, 4 Dec 2022 18:01:08 -0800 (PST) Received: from smtp.kernel.org (relay.kernel.org [52.25.139.140]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by dfw.source.kernel.org (Postfix) with ESMTPS id F141460F47; Mon, 5 Dec 2022 02:01:07 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id EA5FEC43470; Mon, 5 Dec 2022 02:01:05 +0000 (UTC) Authentication-Results: smtp.kernel.org; dkim=pass (1024-bit key) header.d=zx2c4.com header.i=@zx2c4.com header.b="U+Tmvykj" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=zx2c4.com; s=20210105; t=1670205664; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=sC95Fs6VdfOSr62EmCGQ58mG+yLwaAAnWTHST/cpMww=; b=U+Tmvykjtiy92y6oCKv7B82fZbUTFr1ExylpNlAaheorQwwBwzs8kUtnMAdrWuVRP7Z8/J CdjgLUzshULcbuTmm6CGyRbZO/NIN9FTqcvFEo/qjIz/3spnupwwheQe5pSs+HNI/C0GVG NIAmnyQ6gg7TXP3Fjla/ZeZEGFKEEv8= Received: by mail.zx2c4.com (ZX2C4 Mail Server) with ESMTPSA id e26ae555 (TLSv1.3:TLS_AES_256_GCM_SHA384:256:NO); Mon, 5 Dec 2022 02:01:04 +0000 (UTC) From: "Jason A. Donenfeld" To: linux-kernel@vger.kernel.org, patches@lists.linux.dev, tglx@linutronix.de Cc: "Jason A. Donenfeld" , linux-crypto@vger.kernel.org, linux-api@vger.kernel.org, x86@kernel.org, Greg Kroah-Hartman , Adhemerval Zanella Netto , Carlos O'Donell , Florian Weimer , Arnd Bergmann , Christian Brauner Subject: [PATCH v11 1/4] random: add vgetrandom_alloc() syscall Date: Mon, 5 Dec 2022 03:00:43 +0100 Message-Id: <20221205020046.1876356-2-Jason@zx2c4.com> In-Reply-To: <20221205020046.1876356-1-Jason@zx2c4.com> References: <20221205020046.1876356-1-Jason@zx2c4.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" The vDSO getrandom() works over an opaque per-thread state of an unexported size, which must be marked as MADV_WIPEONFORK and be mlock()'d for proper operation. Over time, the nuances of these allocations may change or grow or even differ based on architectural features. The syscall has the signature: void *vgetrandom_alloc(unsigned int *num, unsigned int *size_per_each, unsigned long addr, unsigned int flags); This takes a hinted number of opaque states in `num`, and returns a pointer to an array of opaque states, the number actually allocated back in `num`, and the size in bytes of each one in `size_per_each`, enabling a libc to slice up the returned array into a state per each thread. (The `flags` and `addr` arguments, as well as the `*size_per_each` input value, are reserved for the future and are forced to be zero zero for now.) Libc is expected to allocate a chunk of these on first use, and then dole them out to threads as they're created, allocating more when needed. The returned address of the first state may be passed to munmap(2) with a length of `num * size_per_each`, in order to deallocate the memory. We very intentionally do *not* leave state allocation for vDSO getrandom() up to userspace itself, but rather provide this new syscall for such allocations. vDSO getrandom() must not store its state in just any old memory address, but rather just ones that the kernel specially allocates for it, leaving the particularities of those allocations up to the kernel. The allocation of states is intended to be integrated into libc's thread management. As an illustrative example, the following code might be used to do the same outside of libc. Though, vgetrandom_alloc() is not expected to be exposed outside of libc, and the pthread usage here is expected to be elided into libc internals. This allocation scheme is very naive and does not shrink; other implementations may choose to be more complex. static void *vgetrandom_alloc(unsigned int *num, unsigned int *size_per_e= ach) { *size_per_each =3D 0; /* Must be zero on input. */ return (void *)syscall(__NR_vgetrandom_alloc, &num, &size_per_each, 0 /* reserved @addr */, 0 /* reserved @flags */); } static struct { pthread_mutex_t lock; void **states; size_t len, cap; } grnd_allocator =3D { .lock =3D PTHREAD_MUTEX_INITIALIZER }; static void *vgetrandom_get_state(void) { void *state =3D NULL; pthread_mutex_lock(&grnd_allocator.lock); if (!grnd_allocator.len) { size_t new_cap; unsigned int num =3D sysconf(_SC_NPROCESSORS_ONLN); /* Could be arbit= rary, just a hint. */ unsigned int size_per_each; void *new_block =3D vgetrandom_alloc(&num, &size_per_each); void *new_states; if (new_block =3D=3D MAP_FAILED) goto out; new_cap =3D grnd_allocator.cap + num; new_states =3D reallocarray(grnd_allocator.states, new_cap, sizeof(*g= rnd_allocator.states)); if (!new_states) { munmap(new_block, num * size_per_each); goto out; } grnd_allocator.cap =3D new_cap; grnd_allocator.states =3D new_states; for (size_t i =3D 0; i < num; ++i) { grnd_allocator.states[i] =3D new_block; new_block +=3D size_per_each; } grnd_allocator.len =3D num; } state =3D grnd_allocator.states[--grnd_allocator.len]; out: pthread_mutex_unlock(&grnd_allocator.lock); return state; } static void vgetrandom_put_state(void *state) { if (!state) return; pthread_mutex_lock(&grnd_allocator.lock); grnd_allocator.states[grnd_allocator.len++] =3D state; pthread_mutex_unlock(&grnd_allocator.lock); } Signed-off-by: Jason A. Donenfeld --- MAINTAINERS | 1 + drivers/char/random.c | 130 +++++++++++++++++++++++++++++++++++++++ include/linux/syscalls.h | 3 + include/vdso/getrandom.h | 16 +++++ kernel/sys_ni.c | 3 + lib/vdso/Kconfig | 5 ++ 6 files changed, 158 insertions(+) create mode 100644 include/vdso/getrandom.h diff --git a/MAINTAINERS b/MAINTAINERS index 256f03904987..3894f947a507 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17287,6 +17287,7 @@ 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 +F: include/vdso/getrandom.h =20 RAPIDIO SUBSYSTEM M: Matt Porter diff --git a/drivers/char/random.c b/drivers/char/random.c index e872acc1238f..21692f7f4ea0 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -8,6 +8,7 @@ * into roughly six sections, each with a section header: * * - Initialization and readiness waiting. + * - vDSO support helpers. * - Fast key erasure RNG, the "crng". * - Entropy accumulation and extraction routines. * - Entropy collection routines. @@ -39,6 +40,7 @@ #include #include #include +#include #include #include #include @@ -56,6 +58,9 @@ #include #include #include +#ifdef CONFIG_VDSO_GETRANDOM +#include +#endif #include #include #include @@ -168,6 +173,131 @@ int __cold execute_with_initialized_rng(struct notifi= er_block *nb) __func__, (void *)_RET_IP_, crng_init) =20 =20 + +/******************************************************************** + * + * vDSO support helpers. + * + * The actual vDSO function is defined over in lib/vdso/getrandom.c, + * but this section contains the kernel-mode helpers to support that. + * + ********************************************************************/ + +#ifdef CONFIG_VDSO_GETRANDOM +/** + * sys_vgetrandom_alloc - Allocate opaque states for use with vDSO getrand= om(). + * + * @num: On input, a pointer to a suggested hint of how many states to + * allocate, and on return the number of states actually allocated. + * + * @size_per_each: On input, must be zero. On return, the size of each sta= te allocated, + * so that the caller can split up the returned allocation into + * individual states. + * + * @addr: Reserved, must be zero. + * + * @flags: Reserved, must be zero. + * + * The getrandom() vDSO function in userspace requires an opaque state, wh= ich + * this function allocates by mapping a certain number of special pages in= to + * the calling process. It takes a hint as to the number of opaque states + * desired, and provides the caller with the number of opaque states actua= lly + * allocated, the size of each one in bytes, and the address of the first + * state, which may be split up into @num states of @size_per_each bytes e= ach, + * by adding @size_per_each to the returned first state @num times. + * + * Returns the address of the first state in the allocation on success, or= a + * negative error value on failure. + * + * The returned address of the first state may be passed to munmap(2) with= a + * length of `(size_t)num * (size_t)size_per_each`, in order to deallocate= the + * memory, after which it is invalid to pass it to vDSO getrandom(). + * + * States allocated by this function must not be dereferenced, written, re= ad, + * or otherwise manipulated. The *only* supported operations are: + * - Splitting up the states in intervals of @size_per_each, no more than + * @num times from the first state. + * - Passing a state to the getrandom() vDSO function's @opaque_state + * parameter, but not passing the same state at the same time to two s= uch + * calls. + * - Passing the first state to munmap(2), as described above. + * All other uses are undefined behavior, which is subject to change or re= moval. + */ +SYSCALL_DEFINE4(vgetrandom_alloc, unsigned int __user *, num, + unsigned int __user *, size_per_each, unsigned long, addr, + unsigned int, flags) +{ + struct mm_struct *mm =3D current->mm; + size_t alloc_size, num_states; + const size_t state_size =3D sizeof(struct vgetrandom_state); + unsigned long pages_addr, populate, mm_flags; + unsigned int num_hint; + int ret; + + /* + * @flags and @addr are currently unused, so in order to reserve them + * for the future, force them to be set to zero by current callers. + */ + if (flags || addr) + return -EINVAL; + + /* + * Also enforce that *size_per_each is zero on input, in case this becomes + * useful later on. + */ + if (get_user(num_hint, size_per_each)) + return -EFAULT; + if (num_hint) + return -EINVAL; + + if (get_user(num_hint, num)) + return -EFAULT; + + num_states =3D clamp_t(size_t, num_hint, 1, (SIZE_MAX & PAGE_MASK) / stat= e_size); + alloc_size =3D PAGE_ALIGN(num_states * state_size); + + if (mmap_write_lock_killable(mm)) + return -EINTR; + mm_flags =3D mm->def_flags; + + mm->def_flags |=3D + /* + * Don't allow state to be written to swap, to preserve forward secrecy. + * This works in conjunction with MAP_LOCKED in do_mmap(), below, which + * actually does the locking (and associated permission check and accoun= ting). + * Here, VM_LOCKONFAULT together with VM_NORESERVE simply make the mlock= ing + * happen the first time it's actually used, the same as when calling + * mlock2(MLOCK_ONFAULT) from userspace. + */ + VM_LOCKONFAULT | VM_NORESERVE | + + /* Don't allow the state to survive forks, to prevent random number re-u= se. */ + VM_WIPEONFORK | + + /* Don't write random state into coredumps. */ + VM_DONTDUMP; + + pages_addr =3D do_mmap(NULL, 0, alloc_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_LOCKED, 0, + &populate, NULL); + + mm->def_flags =3D mm_flags; + mmap_write_unlock(mm); + if (IS_ERR_VALUE(pages_addr)) + return pages_addr; + + ret =3D -EFAULT; + if (put_user(alloc_size / state_size, num) || put_user(state_size, size_p= er_each)) + goto err_unmap; + + return pages_addr; + +err_unmap: + vm_munmap(pages_addr, alloc_size); + return ret; +} +#endif + /********************************************************************* * * Fast key erasure RNG, the "crng". diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a34b0f9a9972..dc13b0715836 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1006,6 +1006,9 @@ asmlinkage long sys_seccomp(unsigned int op, unsigned= int flags, void __user *uargs); asmlinkage long sys_getrandom(char __user *buf, size_t count, unsigned int flags); +asmlinkage long sys_vgetrandom_alloc(unsigned int __user *num, + unsigned int __user *size_per_each, + unsigned long addr, unsigned int flags); asmlinkage long sys_memfd_create(const char __user *uname_ptr, unsigned in= t flags); asmlinkage long sys_bpf(int cmd, union bpf_attr *attr, unsigned int size); asmlinkage long sys_execveat(int dfd, const char __user *filename, diff --git a/include/vdso/getrandom.h b/include/vdso/getrandom.h new file mode 100644 index 000000000000..e3ceb1976386 --- /dev/null +++ b/include/vdso/getrandom.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022 Jason A. Donenfeld . All Rights Res= erved. + */ + +#ifndef _VDSO_GETRANDOM_H +#define _VDSO_GETRANDOM_H + +/** + * struct vgetrandom_state - State used by vDSO getrandom() and allocated = by vgetrandom_alloc(). + * + * Currently empty, as the vDSO getrandom() function has not yet been impl= emented. + */ +struct vgetrandom_state { int placeholder; }; + +#endif /* _VDSO_GETRANDOM_H */ diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 860b2dcf3ac4..f28196cb919b 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -360,6 +360,9 @@ COND_SYSCALL(pkey_free); /* memfd_secret */ COND_SYSCALL(memfd_secret); =20 +/* random */ +COND_SYSCALL(vgetrandom_alloc); + /* * Architecture specific weak syscall entries. */ diff --git a/lib/vdso/Kconfig b/lib/vdso/Kconfig index d883ac299508..3b394fa83f65 100644 --- a/lib/vdso/Kconfig +++ b/lib/vdso/Kconfig @@ -31,3 +31,8 @@ config GENERIC_VDSO_TIME_NS VDSO =20 endif + +config VDSO_GETRANDOM + bool + help + Selected by architectures that support vDSO getrandom(). --=20 2.38.1 From nobody Sat May 4 05:59:43 2024 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 5DC52C4332F for ; Mon, 5 Dec 2022 02:01:48 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231350AbiLECBq (ORCPT ); Sun, 4 Dec 2022 21:01:46 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:48760 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231316AbiLECBT (ORCPT ); Sun, 4 Dec 2022 21:01:19 -0500 Received: from dfw.source.kernel.org (dfw.source.kernel.org [IPv6:2604:1380:4641:c500::1]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 0DFCA13D47; Sun, 4 Dec 2022 18:01:12 -0800 (PST) Received: from smtp.kernel.org (relay.kernel.org [52.25.139.140]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by dfw.source.kernel.org (Postfix) with ESMTPS id 9109E60F33; Mon, 5 Dec 2022 02:01:11 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id 9FD0CC433B5; Mon, 5 Dec 2022 02:01:09 +0000 (UTC) Authentication-Results: smtp.kernel.org; dkim=pass (1024-bit key) header.d=zx2c4.com header.i=@zx2c4.com header.b="W+l+Oh8m" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=zx2c4.com; s=20210105; t=1670205668; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=CK0rq83os5Kee1vE1eU5xWNXgAa+YD3aA3qZAug3YeI=; b=W+l+Oh8mrhtQPIRyjuksEPUBoJ7IID9OYbHxcUfKXF+8qOL+jE9uCwfsUzBlVBN64eh0/s eYexv0pxINUs8q+nKzHeZGC14tjD4Bu/vYfdjQ1/wmHWl1xROGCH2ZhV87GTj9YvcC6VQE 2CMxmU1ZoLfkLSWhp1uLjN3F+wYVbWo= Received: by mail.zx2c4.com (ZX2C4 Mail Server) with ESMTPSA id 6c5ca026 (TLSv1.3:TLS_AES_256_GCM_SHA384:256:NO); Mon, 5 Dec 2022 02:01:08 +0000 (UTC) From: "Jason A. Donenfeld" To: linux-kernel@vger.kernel.org, patches@lists.linux.dev, tglx@linutronix.de Cc: "Jason A. Donenfeld" , linux-crypto@vger.kernel.org, linux-api@vger.kernel.org, x86@kernel.org, Greg Kroah-Hartman , Adhemerval Zanella Netto , Carlos O'Donell , Florian Weimer , Arnd Bergmann , Christian Brauner , Geert Uytterhoeven Subject: [PATCH v11 2/4] arch: allocate vgetrandom_alloc() syscall number Date: Mon, 5 Dec 2022 03:00:44 +0100 Message-Id: <20221205020046.1876356-3-Jason@zx2c4.com> In-Reply-To: <20221205020046.1876356-1-Jason@zx2c4.com> References: <20221205020046.1876356-1-Jason@zx2c4.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Add vgetrandom_alloc() as syscall 451 (or 561 on alpha) by adding it to all of the various syscall.tbl and unistd.h files. Acked-by: Geert Uytterhoeven Signed-off-by: Jason A. Donenfeld --- arch/alpha/kernel/syscalls/syscall.tbl | 1 + arch/arm/tools/syscall.tbl | 1 + arch/arm64/include/asm/unistd.h | 2 +- arch/arm64/include/asm/unistd32.h | 2 ++ arch/ia64/kernel/syscalls/syscall.tbl | 1 + arch/m68k/kernel/syscalls/syscall.tbl | 1 + arch/microblaze/kernel/syscalls/syscall.tbl | 1 + arch/mips/kernel/syscalls/syscall_n32.tbl | 1 + arch/mips/kernel/syscalls/syscall_n64.tbl | 1 + arch/mips/kernel/syscalls/syscall_o32.tbl | 1 + arch/parisc/kernel/syscalls/syscall.tbl | 1 + arch/powerpc/kernel/syscalls/syscall.tbl | 1 + arch/s390/kernel/syscalls/syscall.tbl | 1 + arch/sh/kernel/syscalls/syscall.tbl | 1 + arch/sparc/kernel/syscalls/syscall.tbl | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/xtensa/kernel/syscalls/syscall.tbl | 1 + include/uapi/asm-generic/unistd.h | 5 ++++- tools/include/uapi/asm-generic/unistd.h | 5 ++++- tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl | 1 + tools/perf/arch/powerpc/entry/syscalls/syscall.tbl | 1 + tools/perf/arch/s390/entry/syscalls/syscall.tbl | 1 + tools/perf/arch/x86/entry/syscalls/syscall_64.tbl | 1 + 24 files changed, 31 insertions(+), 3 deletions(-) diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/sys= calls/syscall.tbl index 8ebacf37a8cf..a4bfd7b53d6f 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -490,3 +490,4 @@ 558 common process_mrelease sys_process_mrelease 559 common futex_waitv sys_futex_waitv 560 common set_mempolicy_home_node sys_ni_syscall +561 common vgetrandom_alloc sys_vgetrandom_alloc diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index ac964612d8b0..e10319cc6c3e 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -464,3 +464,4 @@ 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common vgetrandom_alloc sys_vgetrandom_alloc diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unist= d.h index 037feba03a51..64a514f90131 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -39,7 +39,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) =20 -#define __NR_compat_syscalls 451 +#define __NR_compat_syscalls 452 #endif =20 #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/uni= std32.h index 604a2053d006..7285b5a830cc 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -907,6 +907,8 @@ __SYSCALL(__NR_process_mrelease, sys_process_mrelease) __SYSCALL(__NR_futex_waitv, sys_futex_waitv) #define __NR_set_mempolicy_home_node 450 __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) +#define __NR_vgetrandom_alloc 451 +__SYSCALL(__NR_vgetrandom_alloc, sys_vgetrandom_alloc) =20 /* * Please add new compat syscalls above this comment and update diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/sysca= lls/syscall.tbl index 72c929d9902b..5ed9667051fc 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -371,3 +371,4 @@ 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common vgetrandom_alloc sys_vgetrandom_alloc diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/sysca= lls/syscall.tbl index b1f3940bc298..d9e7ea26dd26 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -450,3 +450,4 @@ 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common vgetrandom_alloc sys_vgetrandom_alloc diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/= kernel/syscalls/syscall.tbl index 820145e47350..c109e307a37b 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -456,3 +456,4 @@ 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common vgetrandom_alloc sys_vgetrandom_alloc diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/s= yscalls/syscall_n32.tbl index 253ff994ed2e..6d47d8231f7d 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -389,3 +389,4 @@ 448 n32 process_mrelease sys_process_mrelease 449 n32 futex_waitv sys_futex_waitv 450 n32 set_mempolicy_home_node sys_set_mempolicy_home_node +451 n32 vgetrandom_alloc sys_vgetrandom_alloc diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/s= yscalls/syscall_n64.tbl index 3f1886ad9d80..890e5b51e1fc 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -365,3 +365,4 @@ 448 n64 process_mrelease sys_process_mrelease 449 n64 futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 n64 vgetrandom_alloc sys_vgetrandom_alloc diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/s= yscalls/syscall_o32.tbl index 8f243e35a7b2..de512de148f5 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -438,3 +438,4 @@ 448 o32 process_mrelease sys_process_mrelease 449 o32 futex_waitv sys_futex_waitv 450 o32 set_mempolicy_home_node sys_set_mempolicy_home_node +451 o32 vgetrandom_alloc sys_vgetrandom_alloc diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/s= yscalls/syscall.tbl index 8a99c998da9b..bab1cee627e3 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -448,3 +448,4 @@ 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common vgetrandom_alloc sys_vgetrandom_alloc diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel= /syscalls/syscall.tbl index a0be127475b1..e6c04eda2363 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -537,3 +537,4 @@ 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv 450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node +451 common vgetrandom_alloc sys_vgetrandom_alloc diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/sysca= lls/syscall.tbl index 799147658dee..5b0b2bea46da 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -453,3 +453,4 @@ 448 common process_mrelease sys_process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_me= mpolicy_home_node +451 common vgetrandom_alloc sys_vgetrandom_alloc sys_vgetrandom_alloc diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/= syscall.tbl index 2de85c977f54..631f0bac0e9a 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -453,3 +453,4 @@ 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common vgetrandom_alloc sys_vgetrandom_alloc diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/sys= calls/syscall.tbl index 4398cc6fb68d..b4925978adea 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -496,3 +496,4 @@ 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common vgetrandom_alloc sys_vgetrandom_alloc diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscal= ls/syscall_32.tbl index 320480a8db4f..f5f863a33824 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -455,3 +455,4 @@ 448 i386 process_mrelease sys_process_mrelease 449 i386 futex_waitv sys_futex_waitv 450 i386 set_mempolicy_home_node sys_set_mempolicy_home_node +451 i386 vgetrandom_alloc sys_vgetrandom_alloc diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscal= ls/syscall_64.tbl index c84d12608cd2..0186f173f0e8 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -372,6 +372,7 @@ 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common vgetrandom_alloc sys_vgetrandom_alloc =20 # # Due to a historical design error, certain syscalls are numbered differen= tly diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/s= yscalls/syscall.tbl index 52c94ab5c205..14d63a119cc2 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -421,3 +421,4 @@ 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common vgetrandom_alloc sys_vgetrandom_alloc diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/u= nistd.h index 45fa180cc56a..9d2e299f3e8a 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -886,8 +886,11 @@ __SYSCALL(__NR_futex_waitv, sys_futex_waitv) #define __NR_set_mempolicy_home_node 450 __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) =20 +#define __NR_vgetrandom_alloc 451 +__SYSCALL(__NR_vgetrandom_alloc, sys_vgetrandom_alloc) + #undef __NR_syscalls -#define __NR_syscalls 451 +#define __NR_syscalls 452 =20 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/a= sm-generic/unistd.h index 45fa180cc56a..9d2e299f3e8a 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -886,8 +886,11 @@ __SYSCALL(__NR_futex_waitv, sys_futex_waitv) #define __NR_set_mempolicy_home_node 450 __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) =20 +#define __NR_vgetrandom_alloc 451 +__SYSCALL(__NR_vgetrandom_alloc, sys_vgetrandom_alloc) + #undef __NR_syscalls -#define __NR_syscalls 451 +#define __NR_syscalls 452 =20 /* * 32 bit systems traditionally used different diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/pe= rf/arch/mips/entry/syscalls/syscall_n64.tbl index 3f1886ad9d80..890e5b51e1fc 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -365,3 +365,4 @@ 448 n64 process_mrelease sys_process_mrelease 449 n64 futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 n64 vgetrandom_alloc sys_vgetrandom_alloc diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/per= f/arch/powerpc/entry/syscalls/syscall.tbl index e9e0df4f9a61..d58da67a9766 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -534,3 +534,4 @@ 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv 450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node +451 common vgetrandom_alloc sys_vgetrandom_alloc diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/a= rch/s390/entry/syscalls/syscall.tbl index 799147658dee..5b0b2bea46da 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -453,3 +453,4 @@ 448 common process_mrelease sys_process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_me= mpolicy_home_node +451 common vgetrandom_alloc sys_vgetrandom_alloc sys_vgetrandom_alloc diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf= /arch/x86/entry/syscalls/syscall_64.tbl index c84d12608cd2..0186f173f0e8 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -372,6 +372,7 @@ 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common vgetrandom_alloc sys_vgetrandom_alloc =20 # # Due to a historical design error, certain syscalls are numbered differen= tly --=20 2.38.1 From nobody Sat May 4 05:59:43 2024 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 3B693C4708D for ; Mon, 5 Dec 2022 02:02:06 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231418AbiLECCD (ORCPT ); Sun, 4 Dec 2022 21:02:03 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:49110 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231362AbiLECBk (ORCPT ); Sun, 4 Dec 2022 21:01:40 -0500 Received: from ams.source.kernel.org (ams.source.kernel.org [145.40.68.75]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 9C57713DF4; Sun, 4 Dec 2022 18:01:16 -0800 (PST) Received: from smtp.kernel.org (relay.kernel.org [52.25.139.140]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ams.source.kernel.org (Postfix) with ESMTPS id 1117EB80D49; Mon, 5 Dec 2022 02:01:15 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id 4755BC4347C; Mon, 5 Dec 2022 02:01:12 +0000 (UTC) Authentication-Results: smtp.kernel.org; dkim=pass (1024-bit key) header.d=zx2c4.com header.i=@zx2c4.com header.b="Fr/ttd2d" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=zx2c4.com; s=20210105; t=1670205671; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=Q1XN0PwIhvMV8UkWiroHjNyYuvbngL2sPfCX7Nzm5bE=; b=Fr/ttd2dCfwNG+1fzIzILwCWFAc/uyK2RQWFS24Oempt518iBJC2CVGtj8WKkmDp98tmQI OqUTbLMbY1pq3weEDTBCNrDEklGB7MZdBkQKOIExVdY+SACyRQUw1VuM1/vQWjGyXqg8dE CCI0iFp7VE87+4tL9Yp1eCDTzJXRAU0= Received: by mail.zx2c4.com (ZX2C4 Mail Server) with ESMTPSA id e1de6732 (TLSv1.3:TLS_AES_256_GCM_SHA384:256:NO); Mon, 5 Dec 2022 02:01:11 +0000 (UTC) From: "Jason A. Donenfeld" To: linux-kernel@vger.kernel.org, patches@lists.linux.dev, tglx@linutronix.de Cc: "Jason A. Donenfeld" , linux-crypto@vger.kernel.org, linux-api@vger.kernel.org, x86@kernel.org, Greg Kroah-Hartman , Adhemerval Zanella Netto , Carlos O'Donell , Florian Weimer , Arnd Bergmann , Christian Brauner Subject: [PATCH v11 3/4] random: introduce generic vDSO getrandom() implementation Date: Mon, 5 Dec 2022 03:00:45 +0100 Message-Id: <20221205020046.1876356-4-Jason@zx2c4.com> In-Reply-To: <20221205020046.1876356-1-Jason@zx2c4.com> References: <20221205020046.1876356-1-Jason@zx2c4.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Provide a generic C vDSO getrandom() implementation, which operates on an opaque state returned by vgetrandom_alloc() and produces random bytes the same way as getrandom(). This has a the API signature: ssize_t vgetrandom(void *buffer, size_t len, unsigned int flags, void *op= aque_state); The return value and the first 3 arguments are the same as ordinary getrandom(), while the last argument is a pointer to the opaque allocated state. Were all four arguments passed to the getrandom() syscall, nothing different would happen, and the functions would have the exact same behavior. The actual vDSO RNG algorithm implemented is the same one implemented by drivers/char/random.c, using the same fast-erasure techniques as that. Should the in-kernel implementation change, so too will the vDSO one. It requires an implementation of ChaCha20 that does not use any stack, in order to maintain forward secrecy if a multi-threaded program forks (though this does not account for a similar issue with SA_SIGINFO copying registers to the stack), so this is left as an architecture-specific fill-in. Stack-less ChaCha20 is an easy algorithm to implement on a variety of architectures, so this shouldn't be too onerous. Initially, the state is keyless, and so the first call makes a getrandom() syscall to generate that key, and then uses it for subsequent calls. By keeping track of a generation counter, it knows when its key is invalidated and it should fetch a new one using the syscall. Later, more than just a generation counter might be used. Since MADV_WIPEONFORK is set on the opaque state, the key and related state is wiped during a fork(), so secrets don't roll over into new processes, and the same state doesn't accidentally generate the same random stream. The generation counter, as well, is always >0, so that the 0 counter is a useful indication of a fork() or otherwise uninitialized state. If the kernel RNG is not yet initialized, then the vDSO always calls the syscall, because that behavior cannot be emulated in userspace, but fortunately that state is short lived and only during early boot. If it has been initialized, then there is no need to inspect the `flags` argument, because the behavior does not change post-initialization regardless of the `flags` value. Since the opaque state passed to it is mutated, vDSO getrandom() is not reentrant, when used with the same opaque state, which libc should be mindful of. vgetrandom_alloc() and vDSO getrandom() provide the ability for userspace to generate random bytes quickly and safely, and are intended to be integrated into libc's thread management. As an illustrative example, together with the example code from "random: add vgetrandom_alloc() syscall", the following code might be used to do the same outside of libc. In a libc, only the non-static vgetrandom() function at the end would be exported as part of a getrandom() implementations, and the various pthread-isms are expected to be elided into libc internals. static struct { ssize_t(*fn)(void *buf, size_t len, unsigned long flags, void *state); pthread_key_t key; pthread_once_t initialized; } grnd_ctx =3D { .initialized =3D PTHREAD_ONCE_INIT }; static void vgetrandom_init(void) { if (pthread_key_create(&grnd_ctx.key, vgetrandom_put_state) !=3D 0) return; grnd_ctx.fn =3D vdso_sym("LINUX_2.6", "__vdso_getrandom"); } ssize_t vgetrandom(void *buf, size_t len, unsigned long flags) { void *state; pthread_once(&grnd_ctx.initialized, vgetrandom_init); if (!grnd_ctx.fn) return getrandom(buf, len, flags); state =3D pthread_getspecific(grnd_ctx.key); if (!state) { state =3D vgetrandom_get_state(); if (pthread_setspecific(grnd_ctx.key, state) !=3D 0) { vgetrandom_put_state(state); state =3D NULL; } if (!state) return getrandom(buf, len, flags); } return grnd_ctx.fn(buf, len, flags, state); } Signed-off-by: Jason A. Donenfeld --- MAINTAINERS | 1 + drivers/char/random.c | 7 + include/vdso/datapage.h | 12 + include/vdso/getrandom.h | 32 +- include/vdso/types.h | 35 +++ lib/vdso/getrandom.c | 205 +++++++++++++ tools/testing/selftests/vDSO/.gitignore | 1 + tools/testing/selftests/vDSO/Makefile | 2 + .../selftests/vDSO/vdso_test_getrandom.c | 279 ++++++++++++++++++ 9 files changed, 572 insertions(+), 2 deletions(-) create mode 100644 include/vdso/types.h create mode 100644 lib/vdso/getrandom.c create mode 100644 tools/testing/selftests/vDSO/vdso_test_getrandom.c diff --git a/MAINTAINERS b/MAINTAINERS index 3894f947a507..70dff39fcff9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17288,6 +17288,7 @@ S: Maintained F: drivers/char/random.c F: drivers/virt/vmgenid.c F: include/vdso/getrandom.h +F: lib/vdso/getrandom.c =20 RAPIDIO SUBSYSTEM M: Matt Porter diff --git a/drivers/char/random.c b/drivers/char/random.c index 21692f7f4ea0..caa1893c8096 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -60,6 +60,7 @@ #include #ifdef CONFIG_VDSO_GETRANDOM #include +#include #endif #include #include @@ -400,6 +401,9 @@ static void crng_reseed(struct work_struct *work) if (next_gen =3D=3D ULONG_MAX) ++next_gen; WRITE_ONCE(base_crng.generation, next_gen); +#ifdef CONFIG_VDSO_GETRANDOM + smp_store_release(&_vdso_rng_data.generation, next_gen + 1); +#endif if (!static_branch_likely(&crng_is_ready)) crng_init =3D CRNG_READY; spin_unlock_irqrestore(&base_crng.lock, flags); @@ -850,6 +854,9 @@ static void __cold _credit_init_bits(size_t bits) if (static_key_initialized) execute_in_process_context(crng_set_ready, &set_ready); atomic_notifier_call_chain(&random_ready_notifier, 0, NULL); +#ifdef CONFIG_VDSO_GETRANDOM + smp_store_release(&_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/vdso/datapage.h b/include/vdso/datapage.h index 73eb622e7663..d1f800c1c718 100644 --- a/include/vdso/datapage.h +++ b/include/vdso/datapage.h @@ -18,6 +18,7 @@ #include #include #include +#include =20 #ifdef CONFIG_ARCH_HAS_VDSO_DATA #include @@ -109,6 +110,16 @@ struct vdso_data { struct arch_vdso_data arch_data; }; =20 +/** + * 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 { + vdso_kernel_ulong 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 @@ -120,6 +131,7 @@ struct vdso_data { */ extern struct vdso_data _vdso_data[CS_BASES] __attribute__((visibility("hi= dden"))); extern struct vdso_data _timens_data[CS_BASES] __attribute__((visibility("= hidden"))); +extern struct vdso_rng_data _vdso_rng_data __attribute__((visibility("hidd= en"))); =20 /* * The generic vDSO implementation requires that gettimeofday.h diff --git a/include/vdso/getrandom.h b/include/vdso/getrandom.h index e3ceb1976386..7dc93d5f72dc 100644 --- a/include/vdso/getrandom.h +++ b/include/vdso/getrandom.h @@ -6,11 +6,39 @@ #ifndef _VDSO_GETRANDOM_H #define _VDSO_GETRANDOM_H =20 +#include +#include + /** * struct vgetrandom_state - State used by vDSO getrandom() and allocated = by vgetrandom_alloc(). * - * Currently empty, as the vDSO getrandom() function has not yet been impl= emented. + * @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 { int placeholder; }; +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]; + }; + vdso_kernel_ulong generation; + u8 pos; + bool in_use; +}; =20 #endif /* _VDSO_GETRANDOM_H */ diff --git a/include/vdso/types.h b/include/vdso/types.h new file mode 100644 index 000000000000..ce131463aeff --- /dev/null +++ b/include/vdso/types.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022 Jason A. Donenfeld . All Rights Res= erved. + */ +#ifndef __VDSO_TYPES_H +#define __VDSO_TYPES_H + +#include + +/** + * type vdso_kernel_ulong - unsigned long type that matches kernel's unsig= ned long + * + * Data shared between userspace and the kernel must operate the same way = in both 64-bit code and in + * 32-bit compat code, over the same potentially 64-bit kernel. This type = represents the size of an + * unsigned long as used by kernel code. This isn't necessarily the same a= s an unsigned long as used + * by userspace, however. + * + * +-------------------+-------------------+--------------= ----+-------------------+ + * | 32-bit userspace | 32-bit userspace | 64-bit usersp= ace | 64-bit userspace | + * | unsigned long | vdso_kernel_ulong | unsigned long= | vdso_kernel_ulong | + * +---------------+-------------------+-------------------+--------------= ----+-------------------+ + * | 32-bit kernel | =E2=9C=93 same size | =E2=9C=93 same size = | + * | unsigned long | | | + * +---------------+-------------------+-------------------+--------------= ----+-------------------+ + * | 64-bit kernel | =E2=9C=98 different size! | =E2=9C=93 same size = | =E2=9C=93 same size | =E2=9C=93 same size | + * | unsigned long | | | = | | + * +---------------+-------------------+-------------------+--------------= ----+-------------------+ + */ +#ifdef CONFIG_64BIT +typedef u64 vdso_kernel_ulong; +#else +typedef u32 vdso_kernel_ulong; +#endif + +#endif /* __VDSO_TYPES_H */ diff --git a/lib/vdso/getrandom.c b/lib/vdso/getrandom.c new file mode 100644 index 000000000000..9ca624756432 --- /dev/null +++ b/lib/vdso/getrandom.c @@ -0,0 +1,205 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022 Jason A. Donenfeld . All Rights Res= erved. + */ + +#include +#include +#include +#include +#include +#include +#include + +#define MEMCPY_AND_ZERO_SRC(type, dst, src, len) do { \ + while (len >=3D sizeof(type)) { \ + __put_unaligned_t(type, __get_unaligned_t(type, src), dst); \ + __put_unaligned_t(type, 0, src); \ + dst +=3D sizeof(type); \ + src +=3D sizeof(type); \ + len -=3D 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() sys= call. + * @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. + * + * This implements a "fast key erasure" RNG using ChaCha20, in the same wa= y that the kernel's + * getrandom() syscall does. It periodically reseeds its key from the kern= el'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. + * + * @opaque_state *must* be allocated using the vgetrandom_alloc() syscall.= Unless external locking + * is used, one state must be allocated per thread, as it is not safe to c= all this function + * concurrently with the same @opaque_state. However, it is safe to call t= his 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 va= lue 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) +{ + ssize_t ret =3D min_t(size_t, INT_MAX & PAGE_MASK /* =3D MAX_RW_COUNT */,= len); + struct vgetrandom_state *state =3D opaque_state; + size_t batch_len, nblocks, orig_len =3D len; + unsigned long current_generation; + void *orig_buffer =3D buffer; + u32 counter[2] =3D { 0 }; + bool in_use; + + /* + * If the kernel's RNG is not yet ready, then it's not possible to provid= e 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 th= e 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 CPU= s 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 han= dler will run to + * its completion before returning execution. + */ + in_use =3D READ_ONCE(state->in_use); + if (unlikely(in_use)) + goto fallback_syscall; + WRITE_ONCE(state->in_use, true); + +retry_generation: + /* + * @rng_info->generation must always be read here, as it serializes @stat= e->key with the + * kernel's RNG reseeding schedule. + */ + current_generation =3D 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 !=3D current_generation)) { + /* + * Write the generation before filling the key, in case of fork. If ther= e is a fork + * just after this line, the two forks will get different random bytes f= rom the + * syscall, which is good. However, were this line to occur after the ge= trandom + * syscall, then both child and parent could have the same bytes and the= same + * generation counter, so the fork would not be detected. Therefore, wri= te + * @state->generation before the call to the getrandom syscall. + */ + WRITE_ONCE(state->generation, current_generation); + + /* Reseed @state->key using fresh bytes from the kernel. */ + if (getrandom_syscall(state->key, sizeof(state->key), 0) !=3D sizeof(sta= te->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 t= he + * 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 =3D sizeof(state->batch); + } + + /* Set len to the total amount of bytes that this function is allowed to = read, ret. */ + len =3D ret; +more_batch: + /* + * First use bytes out of @state->batch, which may have been filled by th= e last call to this + * function. + */ + batch_len =3D 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 +=3D batch_len; + buffer +=3D batch_len; + len -=3D batch_len; + } + + if (!len) { + /* + * Since @rng_info->generation will never be 0, re-read @state->generati= on, rather + * than using the local current_generation variable, to learn whether a = fork + * occurred. 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) !=3D READ_ONCE(rng_info->gener= ation))) { + buffer =3D 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 enou= gh room left. */ + nblocks =3D len / CHACHA_BLOCK_SIZE; + if (nblocks) { + __arch_chacha20_blocks_nostack(buffer, state->key, counter, nblocks); + buffer +=3D nblocks * CHACHA_BLOCK_SIZE; + len -=3D nblocks * CHACHA_BLOCK_SIZE; + } + + BUILD_BUG_ON(sizeof(state->batch_key) % CHACHA_BLOCK_SIZE !=3D 0); + + /* Refill the batch and then overwrite the key, in order to preserve forw= ard 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 indic= ate a full batch. */ + state->pos =3D 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 *opaq= ue_state) +{ + return __cvdso_getrandom_data(__arch_get_vdso_rng_data(), buffer, len, fl= ags, opaque_state); +} diff --git a/tools/testing/selftests/vDSO/.gitignore b/tools/testing/selfte= sts/vDSO/.gitignore index a8dc51af5a9c..7dbfdec53f3d 100644 --- a/tools/testing/selftests/vDSO/.gitignore +++ b/tools/testing/selftests/vDSO/.gitignore @@ -6,3 +6,4 @@ vdso_test_correctness vdso_test_gettimeofday vdso_test_getcpu vdso_standalone_test_x86 +vdso_test_getrandom diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftest= s/vDSO/Makefile index d53a4d8008f9..a33b4d200a32 100644 --- a/tools/testing/selftests/vDSO/Makefile +++ b/tools/testing/selftests/vDSO/Makefile @@ -11,6 +11,7 @@ ifeq ($(ARCH),$(filter $(ARCH),x86 x86_64)) TEST_GEN_PROGS +=3D $(OUTPUT)/vdso_standalone_test_x86 endif TEST_GEN_PROGS +=3D $(OUTPUT)/vdso_test_correctness +TEST_GEN_PROGS +=3D $(OUTPUT)/vdso_test_getrandom =20 CFLAGS :=3D -std=3Dgnu99 CFLAGS_vdso_standalone_test_x86 :=3D -nostdlib -fno-asynchronous-unwind-ta= bles -fno-stack-protector @@ -33,3 +34,4 @@ $(OUTPUT)/vdso_test_correctness: vdso_test_correctness.c vdso_test_correctness.c \ -o $@ \ $(LDFLAGS_vdso_test_correctness) +$(OUTPUT)/vdso_test_getrandom: parse_vdso.c diff --git a/tools/testing/selftests/vDSO/vdso_test_getrandom.c b/tools/tes= ting/selftests/vDSO/vdso_test_getrandom.c new file mode 100644 index 000000000000..528674899b8a --- /dev/null +++ b/tools/testing/selftests/vDSO/vdso_test_getrandom.c @@ -0,0 +1,279 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022 Jason A. Donenfeld . All Rights Res= erved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../kselftest.h" +#include "parse_vdso.h" + +#ifndef timespecsub +#define timespecsub(tsp, usp, vsp) \ + do { \ + (vsp)->tv_sec =3D (tsp)->tv_sec - (usp)->tv_sec; \ + (vsp)->tv_nsec =3D (tsp)->tv_nsec - (usp)->tv_nsec; \ + if ((vsp)->tv_nsec < 0) { \ + (vsp)->tv_sec--; \ + (vsp)->tv_nsec +=3D 1000000000L; \ + } \ + } while (0) +#endif + +static void *vgetrandom_alloc(unsigned int *num, unsigned int *size_per_ea= ch) +{ + enum { __NR_vgetrandom_alloc =3D 451 }; + *size_per_each =3D 0; + return (void *)syscall(__NR_vgetrandom_alloc, num, size_per_each, 0, 0); +} + +static struct { + pthread_mutex_t lock; + void **states; + size_t len, cap; +} grnd_allocator =3D { + .lock =3D PTHREAD_MUTEX_INITIALIZER +}; + +static void *vgetrandom_get_state(void) +{ + void *state =3D NULL; + + pthread_mutex_lock(&grnd_allocator.lock); + if (!grnd_allocator.len) { + size_t new_cap; + unsigned int num =3D sysconf(_SC_NPROCESSORS_ONLN); /* Could be arbitrar= y, just a hint. */ + unsigned int size_per_each; + void *new_block =3D vgetrandom_alloc(&num, &size_per_each); + void *new_states; + + if (new_block =3D=3D MAP_FAILED) + goto out; + new_cap =3D grnd_allocator.cap + num; + new_states =3D reallocarray(grnd_allocator.states, new_cap, sizeof(*grnd= _allocator.states)); + if (!new_states) { + munmap(new_block, num * size_per_each); + goto out; + } + grnd_allocator.cap =3D new_cap; + grnd_allocator.states =3D new_states; + + for (size_t i =3D 0; i < num; ++i) { + grnd_allocator.states[i] =3D new_block; + new_block +=3D size_per_each; + } + grnd_allocator.len =3D num; + } + state =3D grnd_allocator.states[--grnd_allocator.len]; + +out: + pthread_mutex_unlock(&grnd_allocator.lock); + return state; +} + +static void vgetrandom_put_state(void *state) +{ + if (!state) + return; + pthread_mutex_lock(&grnd_allocator.lock); + grnd_allocator.states[grnd_allocator.len++] =3D state; + pthread_mutex_unlock(&grnd_allocator.lock); +} + +static struct { + ssize_t(*fn)(void *buf, size_t len, unsigned long flags, void *state); + pthread_key_t key; + pthread_once_t initialized; +} grnd_ctx =3D { + .initialized =3D PTHREAD_ONCE_INIT +}; + +static void vgetrandom_init(void) +{ + if (pthread_key_create(&grnd_ctx.key, vgetrandom_put_state) !=3D 0) + return; + unsigned long sysinfo_ehdr =3D getauxval(AT_SYSINFO_EHDR); + if (!sysinfo_ehdr) { + printf("AT_SYSINFO_EHDR is not present!\n"); + exit(KSFT_SKIP); + } + vdso_init_from_sysinfo_ehdr(sysinfo_ehdr); + grnd_ctx.fn =3D (__typeof__(grnd_ctx.fn))vdso_sym("LINUX_2.6", "__vdso_ge= trandom"); + if (!grnd_ctx.fn) { + printf("__vdso_getrandom is missing!\n"); + exit(KSFT_FAIL); + } +} + +static ssize_t vgetrandom(void *buf, size_t len, unsigned long flags) +{ + void *state; + + pthread_once(&grnd_ctx.initialized, vgetrandom_init); + state =3D pthread_getspecific(grnd_ctx.key); + if (!state) { + state =3D vgetrandom_get_state(); + if (pthread_setspecific(grnd_ctx.key, state) !=3D 0) { + vgetrandom_put_state(state); + state =3D NULL; + } + if (!state) { + printf("vgetrandom_get_state failed!\n"); + exit(KSFT_FAIL); + } + } + return grnd_ctx.fn(buf, len, flags, state); +} + +enum { TRIALS =3D 25000000, THREADS =3D 256 }; + +static void *test_vdso_getrandom(void *) +{ + for (size_t i =3D 0; i < TRIALS; ++i) { + unsigned int val; + ssize_t ret =3D vgetrandom(&val, sizeof(val), 0); + assert(ret =3D=3D sizeof(val)); + } + return NULL; +} + +static void *test_libc_getrandom(void *) +{ + for (size_t i =3D 0; i < TRIALS; ++i) { + unsigned int val; + ssize_t ret =3D getrandom(&val, sizeof(val), 0); + assert(ret =3D=3D sizeof(val)); + } + return NULL; +} + +static void *test_syscall_getrandom(void *) +{ + for (size_t i =3D 0; i < TRIALS; ++i) { + unsigned int val; + ssize_t ret =3D syscall(SYS_getrandom, &val, sizeof(val), 0); + assert(ret =3D=3D sizeof(val)); + } + return NULL; +} + +static void bench_single(void) +{ + struct timespec start, end, diff; + + clock_gettime(CLOCK_MONOTONIC, &start); + test_vdso_getrandom(NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" vdso: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, d= iff.tv_nsec); + + clock_gettime(CLOCK_MONOTONIC, &start); + test_libc_getrandom(NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" libc: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, d= iff.tv_nsec); + + clock_gettime(CLOCK_MONOTONIC, &start); + test_syscall_getrandom(NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf("syscall: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, d= iff.tv_nsec); +} + +static void bench_multi(void) +{ + struct timespec start, end, diff; + pthread_t threads[THREADS]; + + clock_gettime(CLOCK_MONOTONIC, &start); + for (size_t i =3D 0; i < THREADS; ++i) + assert(pthread_create(&threads[i], NULL, test_vdso_getrandom, NULL) =3D= =3D 0); + for (size_t i =3D 0; i < THREADS; ++i) + pthread_join(threads[i], NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" vdso: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, = diff.tv_sec, diff.tv_nsec); + + clock_gettime(CLOCK_MONOTONIC, &start); + for (size_t i =3D 0; i < THREADS; ++i) + assert(pthread_create(&threads[i], NULL, test_libc_getrandom, NULL) =3D= =3D 0); + for (size_t i =3D 0; i < THREADS; ++i) + pthread_join(threads[i], NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" libc: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, = diff.tv_sec, diff.tv_nsec); + + clock_gettime(CLOCK_MONOTONIC, &start); + for (size_t i =3D 0; i < THREADS; ++i) + assert(pthread_create(&threads[i], NULL, test_syscall_getrandom, NULL) = =3D=3D 0); + for (size_t i =3D 0; i < THREADS; ++i) + pthread_join(threads[i], NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" syscall: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREAD= S, diff.tv_sec, diff.tv_nsec); +} + +static void fill(void) +{ + uint8_t weird_size[323929]; + for (;;) + vgetrandom(weird_size, sizeof(weird_size), 0); +} + +static void kselftest(void) +{ + uint8_t weird_size[1263]; + + ksft_print_header(); + ksft_set_plan(1); + + for (size_t i =3D 0; i < 1000; ++i) { + ssize_t ret =3D vgetrandom(weird_size, sizeof(weird_size), 0); + if (ret !=3D sizeof(weird_size)) + exit(KSFT_FAIL); + } + + ksft_test_result_pass("getrandom: PASS\n"); + exit(KSFT_PASS); +} + +static void usage(const char *argv0) +{ + fprintf(stderr, "Usage: %s [bench-single|bench-multi|fill]\n", argv0); +} + +int main(int argc, char *argv[]) +{ + if (argc =3D=3D 1) { + kselftest(); + return 0; + } + + if (argc !=3D 2) { + usage(argv[0]); + return 1; + } + if (!strcmp(argv[1], "bench-single")) + bench_single(); + else if (!strcmp(argv[1], "bench-multi")) + bench_multi(); + else if (!strcmp(argv[1], "fill")) + fill(); + else { + usage(argv[0]); + return 1; + } + return 0; +} --=20 2.38.1 From nobody Sat May 4 05:59:43 2024 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 49219C4332F for ; Mon, 5 Dec 2022 02:02:10 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231424AbiLECCH (ORCPT ); Sun, 4 Dec 2022 21:02:07 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:49218 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231186AbiLECBu (ORCPT ); Sun, 4 Dec 2022 21:01:50 -0500 Received: from ams.source.kernel.org (ams.source.kernel.org [145.40.68.75]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 20A6B13D44; Sun, 4 Dec 2022 18:01:20 -0800 (PST) Received: from smtp.kernel.org (relay.kernel.org [52.25.139.140]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ams.source.kernel.org (Postfix) with ESMTPS id 92051B80D3E; Mon, 5 Dec 2022 02:01:18 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id D98AEC433B5; Mon, 5 Dec 2022 02:01:15 +0000 (UTC) Authentication-Results: smtp.kernel.org; dkim=pass (1024-bit key) header.d=zx2c4.com header.i=@zx2c4.com header.b="lgk30oEz" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=zx2c4.com; s=20210105; t=1670205674; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=Op3OGtpYFefv7wwJNL4oNw4HnNnPVWLlXugIoJjaoeE=; b=lgk30oEzqJwvKqR9H7xC6MOYofPslyR/RCmXAr7q0+hdqpye/IPAvnxm8Hshw5spTX/RXx WO0ySJ0RKoJRuwJojkXr4+Cn72poIp2PEaFfNd7z7lbaI92S1RFU0W0/+9wds2tR7gywMg 84uai49iJxvnMJfdGPhb5DhzwqbudEI= Received: by mail.zx2c4.com (ZX2C4 Mail Server) with ESMTPSA id 6310b718 (TLSv1.3:TLS_AES_256_GCM_SHA384:256:NO); Mon, 5 Dec 2022 02:01:14 +0000 (UTC) From: "Jason A. Donenfeld" To: linux-kernel@vger.kernel.org, patches@lists.linux.dev, tglx@linutronix.de Cc: "Jason A. Donenfeld" , linux-crypto@vger.kernel.org, linux-api@vger.kernel.org, x86@kernel.org, Greg Kroah-Hartman , Adhemerval Zanella Netto , Carlos O'Donell , Florian Weimer , Arnd Bergmann , Christian Brauner , Samuel Neves Subject: [PATCH v11 4/4] x86: vdso: Wire up getrandom() vDSO implementation Date: Mon, 5 Dec 2022 03:00:46 +0100 Message-Id: <20221205020046.1876356-5-Jason@zx2c4.com> In-Reply-To: <20221205020046.1876356-1-Jason@zx2c4.com> References: <20221205020046.1876356-1-Jason@zx2c4.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Hook up the generic vDSO implementation to the x86 vDSO data page. Since the existing vDSO infrastructure is heavily based on the timekeeping functionality, which works over arrays of bases, a new macro is introduced for vvars that are not arrays. The vDSO function requires a ChaCha20 implementation that does not write to the stack, yet can still do an entire ChaCha20 permutation, so provide this using SSE2, since this is userland code that must work on all x86-64 processors. There's a simple test for this code as well. Reviewed-by: Samuel Neves # for vgetrandom-chacha.S Signed-off-by: Jason A. Donenfeld --- arch/x86/Kconfig | 1 + arch/x86/entry/vdso/Makefile | 3 +- arch/x86/entry/vdso/vdso.lds.S | 2 + arch/x86/entry/vdso/vgetrandom-chacha.S | 177 ++++++++++++++++++ arch/x86/entry/vdso/vgetrandom.c | 17 ++ arch/x86/include/asm/vdso/getrandom.h | 55 ++++++ arch/x86/include/asm/vdso/vsyscall.h | 2 + arch/x86/include/asm/vvar.h | 16 ++ tools/testing/selftests/vDSO/.gitignore | 1 + tools/testing/selftests/vDSO/Makefile | 9 + .../testing/selftests/vDSO/vdso_test_chacha.c | 43 +++++ 11 files changed, 325 insertions(+), 1 deletion(-) create mode 100644 arch/x86/entry/vdso/vgetrandom-chacha.S create mode 100644 arch/x86/entry/vdso/vgetrandom.c create mode 100644 arch/x86/include/asm/vdso/getrandom.h create mode 100644 tools/testing/selftests/vDSO/vdso_test_chacha.c diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 67745ceab0db..357148c4a3a4 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -269,6 +269,7 @@ config X86 select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_USER_RETURN_NOTIFIER select HAVE_GENERIC_VDSO + select VDSO_GETRANDOM if X86_64 select HOTPLUG_SMT if SMP select IRQ_FORCED_THREADING select NEED_PER_CPU_EMBED_FIRST_CHUNK diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 3e88b9df8c8f..2de64e52236a 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -27,7 +27,7 @@ VDSO32-$(CONFIG_X86_32) :=3D y VDSO32-$(CONFIG_IA32_EMULATION) :=3D y =20 # files to link into the vdso -vobjs-y :=3D vdso-note.o vclock_gettime.o vgetcpu.o +vobjs-y :=3D vdso-note.o vclock_gettime.o vgetcpu.o vgetrandom.o vgetrando= m-chacha.o vobjs32-y :=3D vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o vobjs32-y +=3D vdso32/vclock_gettime.o vobjs-$(CONFIG_X86_SGX) +=3D vsgx.o @@ -104,6 +104,7 @@ CFLAGS_REMOVE_vclock_gettime.o =3D -pg CFLAGS_REMOVE_vdso32/vclock_gettime.o =3D -pg CFLAGS_REMOVE_vgetcpu.o =3D -pg CFLAGS_REMOVE_vsgx.o =3D -pg +CFLAGS_REMOVE_vgetrandom.o =3D -pg =20 # # 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 4bf48462fca7..1919cc39277e 100644 --- a/arch/x86/entry/vdso/vdso.lds.S +++ b/arch/x86/entry/vdso/vdso.lds.S @@ -28,6 +28,8 @@ VERSION { clock_getres; __vdso_clock_getres; __vdso_sgx_enter_enclave; + 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..91fbb7ac7af4 --- /dev/null +++ b/arch/x86/entry/vdso/vgetrandom-chacha.S @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022 Jason A. Donenfeld . All Rights Res= erved. + */ + +#include +#include + +.section .rodata.cst16.CONSTANTS, "aM", @progbits, 16 +.align 16 +CONSTANTS: .octa 0x6b20657479622d323320646e61707865 +.text + +/* + * Very basic SSE2 implementation of ChaCha20. Produces a given positive n= umber + * 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) + +#define output %rdi +#define key %rsi +#define counter %rdx +#define nblocks %rcx +#define i %al +#define state0 %xmm0 +#define state1 %xmm1 +#define state2 %xmm2 +#define state3 %xmm3 +#define copy0 %xmm4 +#define copy1 %xmm5 +#define copy2 %xmm6 +#define copy3 %xmm7 +#define temp %xmm8 +#define one %xmm9 + + /* copy0 =3D "expand 32-byte k" */ + movaps CONSTANTS(%rip),copy0 + /* copy1,copy2 =3D key */ + movups 0x00(key),copy1 + movups 0x10(key),copy2 + /* copy3 =3D counter || zero nonce */ + movq 0x00(counter),copy3 + /* one =3D 1 || 0 */ + movq $1,%rax + movq %rax,one + +.Lblock: + /* state0,state1,state2,state3 =3D copy0,copy1,copy2,copy3 */ + movdqa copy0,state0 + movdqa copy1,state1 + movdqa copy2,state2 + movdqa copy3,state3 + + movb $10,i +.Lpermute: + /* state0 +=3D state1, state3 =3D rotl32(state3 ^ state0, 16) */ + paddd state1,state0 + pxor state0,state3 + movdqa state3,temp + pslld $16,temp + psrld $16,state3 + por temp,state3 + + /* state2 +=3D state3, state1 =3D rotl32(state1 ^ state2, 12) */ + paddd state3,state2 + pxor state2,state1 + movdqa state1,temp + pslld $12,temp + psrld $20,state1 + por temp,state1 + + /* state0 +=3D state1, state3 =3D rotl32(state3 ^ state0, 8) */ + paddd state1,state0 + pxor state0,state3 + movdqa state3,temp + pslld $8,temp + psrld $24,state3 + por temp,state3 + + /* state2 +=3D state3, state1 =3D 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] =3D state1[0,3,2,1] */ + pshufd $0x39,state1,state1 + /* state2[0,1,2,3] =3D state2[1,0,3,2] */ + pshufd $0x4e,state2,state2 + /* state3[0,1,2,3] =3D state3[2,1,0,3] */ + pshufd $0x93,state3,state3 + + /* state0 +=3D state1, state3 =3D rotl32(state3 ^ state0, 16) */ + paddd state1,state0 + pxor state0,state3 + movdqa state3,temp + pslld $16,temp + psrld $16,state3 + por temp,state3 + + /* state2 +=3D state3, state1 =3D rotl32(state1 ^ state2, 12) */ + paddd state3,state2 + pxor state2,state1 + movdqa state1,temp + pslld $12,temp + psrld $20,state1 + por temp,state1 + + /* state0 +=3D state1, state3 =3D rotl32(state3 ^ state0, 8) */ + paddd state1,state0 + pxor state0,state3 + movdqa state3,temp + pslld $8,temp + psrld $24,state3 + por temp,state3 + + /* state2 +=3D state3, state1 =3D 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] =3D state1[2,1,0,3] */ + pshufd $0x93,state1,state1 + /* state2[0,1,2,3] =3D state2[1,0,3,2] */ + pshufd $0x4e,state2,state2 + /* state3[0,1,2,3] =3D state3[0,3,2,1] */ + pshufd $0x39,state3,state3 + + decb i + jnz .Lpermute + + /* output0 =3D state0 + copy0 */ + paddd copy0,state0 + movups state0,0x00(output) + /* output1 =3D state1 + copy1 */ + paddd copy1,state1 + movups state1,0x10(output) + /* output2 =3D state2 + copy2 */ + paddd copy2,state2 + movups state2,0x20(output) + /* output3 =3D state3 + copy3 */ + paddd copy3,state3 + movups state3,0x30(output) + + /* ++copy3.counter */ + paddq one,copy3 + + /* output +=3D 64, --nblocks */ + addq $64,output + decq nblocks + jnz .Lblock + + /* counter =3D copy3.counter */ + movq copy3,0x00(counter) + + /* Zero out the potentially sensitive regs, in case nothing uses these ag= ain. */ + 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/vgetran= dom.c new file mode 100644 index 000000000000..6045ded5da90 --- /dev/null +++ b/arch/x86/entry/vdso/vgetrandom.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2022 Jason A. Donenfeld . All Rights Res= erved. + */ +#include + +#include "../../../../lib/vdso/getrandom.c" + +ssize_t __vdso_getrandom(void *buffer, size_t len, unsigned int flags, voi= d *state); + +ssize_t __vdso_getrandom(void *buffer, size_t len, unsigned int flags, voi= d *state) +{ + return __cvdso_getrandom(buffer, len, flags, state); +} + +ssize_t getrandom(void *, size_t, unsigned int, void *) + __attribute__((weak, alias("__vdso_getrandom"))); diff --git a/arch/x86/include/asm/vdso/getrandom.h b/arch/x86/include/asm/v= dso/getrandom.h new file mode 100644 index 000000000000..46f99d735ae6 --- /dev/null +++ b/arch/x86/include/asm/vdso/getrandom.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022 Jason A. Donenfeld . All Rights Res= erved. + */ +#ifndef __ASM_VDSO_GETRANDOM_H +#define __ASM_VDSO_GETRANDOM_H + +#ifndef __ASSEMBLY__ + +#include +#include + +/** + * 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 va= lue indicating an error. + */ +static __always_inline ssize_t getrandom_syscall(void *buffer, size_t len,= unsigned int flags) +{ + long ret; + + asm ("syscall" : "=3Da" (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_dat= a(void) +{ + if (__vdso_data->clock_mode =3D=3D 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 non= ce=3D0, 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/vd= so/vsyscall.h index be199a9b2676..71c56586a22f 100644 --- a/arch/x86/include/asm/vdso/vsyscall.h +++ b/arch/x86/include/asm/vdso/vsyscall.h @@ -11,6 +11,8 @@ #include =20 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) =20 #else =20 @@ -37,6 +39,10 @@ extern char __vvar_page; extern type timens_ ## name[CS_BASES] \ __attribute__((visibility("hidden"))); \ =20 +#define DECLARE_VVAR_SINGLE(offset, type, name) \ + extern type vvar_ ## name \ + __attribute__((visibility("hidden"))); \ + #define VVAR(name) (vvar_ ## name) #define TIMENS(name) (timens_ ## name) =20 @@ -44,12 +50,22 @@ extern char __vvar_page; type name[CS_BASES] \ __attribute__((section(".vvar_" #name), aligned(16))) __visible =20 +#define DEFINE_VVAR_SINGLE(type, name) \ + type name \ + __attribute__((section(".vvar_" #name), aligned(16))) __visible + #endif =20 /* DECLARE_VVAR(offset, type, name) */ =20 DECLARE_VVAR(128, struct vdso_data, _vdso_data) =20 +#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 =20 #endif diff --git a/tools/testing/selftests/vDSO/.gitignore b/tools/testing/selfte= sts/vDSO/.gitignore index 7dbfdec53f3d..30d5c8f0e5c7 100644 --- a/tools/testing/selftests/vDSO/.gitignore +++ b/tools/testing/selftests/vDSO/.gitignore @@ -7,3 +7,4 @@ vdso_test_gettimeofday vdso_test_getcpu vdso_standalone_test_x86 vdso_test_getrandom +vdso_test_chacha diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftest= s/vDSO/Makefile index a33b4d200a32..1b9057974693 100644 --- a/tools/testing/selftests/vDSO/Makefile +++ b/tools/testing/selftests/vDSO/Makefile @@ -3,6 +3,7 @@ include ../lib.mk =20 uname_M :=3D $(shell uname -m 2>/dev/null || echo not) ARCH ?=3D $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) +SODIUM :=3D $(shell pkg-config --libs libsodium 2>/dev/null) =20 TEST_GEN_PROGS :=3D $(OUTPUT)/vdso_test_gettimeofday $(OUTPUT)/vdso_test_g= etcpu TEST_GEN_PROGS +=3D $(OUTPUT)/vdso_test_abi @@ -12,9 +13,15 @@ TEST_GEN_PROGS +=3D $(OUTPUT)/vdso_standalone_test_x86 endif TEST_GEN_PROGS +=3D $(OUTPUT)/vdso_test_correctness TEST_GEN_PROGS +=3D $(OUTPUT)/vdso_test_getrandom +ifeq ($(uname_M),x86_64) +ifneq ($(SODIUM),) +TEST_GEN_PROGS +=3D $(OUTPUT)/vdso_test_chacha +endif +endif =20 CFLAGS :=3D -std=3Dgnu99 CFLAGS_vdso_standalone_test_x86 :=3D -nostdlib -fno-asynchronous-unwind-ta= bles -fno-stack-protector +CFLAGS_vdso_test_chacha :=3D $(SODIUM) -idirafter $(top_srcdir)/include -i= dirafter $(top_srcdir)/arch/$(ARCH)/include -D__ASSEMBLY__ -Wa,--noexecstack LDFLAGS_vdso_test_correctness :=3D -ldl ifeq ($(CONFIG_X86_32),y) LDLIBS +=3D -lgcc_s @@ -35,3 +42,5 @@ $(OUTPUT)/vdso_test_correctness: vdso_test_correctness.c -o $@ \ $(LDFLAGS_vdso_test_correctness) $(OUTPUT)/vdso_test_getrandom: parse_vdso.c +$(OUTPUT)/vdso_test_chacha: CFLAGS +=3D $(CFLAGS_vdso_test_chacha) +$(OUTPUT)/vdso_test_chacha: $(top_srcdir)/arch/$(ARCH)/entry/vdso/vgetrand= om-chacha.S diff --git a/tools/testing/selftests/vDSO/vdso_test_chacha.c b/tools/testin= g/selftests/vDSO/vdso_test_chacha.c new file mode 100644 index 000000000000..1c76aeb3de68 --- /dev/null +++ b/tools/testing/selftests/vDSO/vdso_test_chacha.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022 Jason A. Donenfeld . All Rights Res= erved. + */ + +#include +#include +#include +#include +#include "../kselftest.h" + +extern void __arch_chacha20_blocks_nostack(uint8_t *dst_bytes, const uint8= _t *key, uint32_t *counter, size_t nblocks); + +int main(int argc, char *argv[]) +{ + enum { TRIALS =3D 1000, BLOCKS =3D 128, BLOCK_SIZE =3D 64 }; + static const uint8_t nonce[8] =3D { 0 }; + uint32_t counter[2]; + uint8_t key[32]; + uint8_t output1[BLOCK_SIZE * BLOCKS], output2[BLOCK_SIZE * BLOCKS]; + + ksft_print_header(); + ksft_set_plan(1); + + for (unsigned int trial; trial < TRIALS; ++trial) { + if (getrandom(key, sizeof(key), 0) !=3D sizeof(key)) { + printf("getrandom() failed!\n"); + return KSFT_SKIP; + } + crypto_stream_chacha20(output1, sizeof(output1), nonce, key); + for (unsigned int split =3D 0; split < BLOCKS; ++split) { + memset(output2, 'X', sizeof(output2)); + memset(counter, 0, sizeof(counter)); + if (split) + __arch_chacha20_blocks_nostack(output2, key, counter, split); + __arch_chacha20_blocks_nostack(output2 + split * BLOCK_SIZE, key, count= er, BLOCKS - split); + if (memcmp(output1, output2, sizeof(output1))) + return KSFT_FAIL; + } + } + ksft_test_result_pass("chacha: PASS\n"); + return KSFT_PASS; +} --=20 2.38.1