@@ -270,6 +270,7 @@ config X86
select HAVE_UNSTABLE_SCHED_CLOCK
select HAVE_USER_RETURN_NOTIFIER
select HAVE_GENERIC_VDSO
+ select HAVE_VDSO_GETRANDOM if X86_64
select HOTPLUG_SMT if SMP
select IRQ_FORCED_THREADING
select NEED_PER_CPU_EMBED_FIRST_CHUNK
@@ -27,7 +27,7 @@ VDSO32-$(CONFIG_X86_32) := y
VDSO32-$(CONFIG_IA32_EMULATION) := y
# 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
vobjs-$(CONFIG_X86_SGX) += vsgx.o
@@ -104,6 +104,7 @@ CFLAGS_REMOVE_vclock_gettime.o = -pg
CFLAGS_REMOVE_vdso32/vclock_gettime.o = -pg
CFLAGS_REMOVE_vgetcpu.o = -pg
CFLAGS_REMOVE_vsgx.o = -pg
+CFLAGS_REMOVE_vgetrandom.o = -pg
#
# X32 processes use x32 vDSO to access 64bit kernel data.
@@ -28,6 +28,8 @@ VERSION {
clock_getres;
__vdso_clock_getres;
__vdso_sgx_enter_enclave;
+ getrandom;
+ __vdso_getrandom;
local: *;
};
}
new file mode 100644
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <linux/linkage.h>
+#include <asm/frame.h>
+
+.section .rodata.cst16.CONSTANTS, "aM", @progbits, 16
+.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(chacha20_blocks_nostack)
+ FRAME_BEGIN
+
+#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 = "expand 32-byte k" */
+ movaps CONSTANTS(%rip),copy0
+ /* copy1,copy2 = key */
+ movdqu 0x00(key),copy1
+ movdqu 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 = shuffle32(state1, MASK(0, 3, 2, 1)) */
+ pshufd $0x39,state1,state1
+ /* state2 = shuffle32(state2, MASK(1, 0, 3, 2)) */
+ pshufd $0x4e,state2,state2
+ /* state3 = shuffle32(state3, MASK(2, 1, 0, 3)) */
+ 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 = shuffle32(state1, MASK(2, 1, 0, 3)) */
+ pshufd $0x93,state1,state1
+ /* state2 = shuffle32(state2, MASK(1, 0, 3, 2)) */
+ pshufd $0x4e,state2,state2
+ /* state3 = shuffle32(state3, MASK(0, 3, 2, 1)) */
+ pshufd $0x39,state3,state3
+
+ decb i
+ jnz .Lpermute
+
+ /* output0 = state0 + copy0 */
+ paddd copy0,state0
+ movdqu state0,0x00(output)
+ /* output1 = state1 + copy1 */
+ paddd copy1,state1
+ movdqu state1,0x10(output)
+ /* output2 = state2 + copy2 */
+ paddd copy2,state2
+ movdqu state2,0x20(output)
+ /* output3 = state3 + copy3 */
+ paddd copy3,state3
+ movdqu 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 all the regs, in case nothing uses these again. */
+ pxor state0,state0
+ pxor state1,state1
+ pxor state2,state2
+ pxor state3,state3
+ pxor copy0,copy0
+ pxor copy1,copy1
+ pxor copy2,copy2
+ pxor copy3,copy3
+ pxor temp,temp
+
+ FRAME_END
+ RET
+SYM_FUNC_END(chacha20_blocks_nostack)
new file mode 100644
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+#include "../../../../lib/vdso/getrandom.c"
+
+ssize_t __vdso_getrandom(void *buffer, size_t len, unsigned int flags, void *state);
+
+ssize_t __vdso_getrandom(void *buffer, size_t len, unsigned int flags, void *state)
+{
+ return __cvdso_getrandom(buffer, len, flags, state);
+}
+
+ssize_t getrandom(void *, size_t, unsigned int, void *)
+ __attribute__((weak, alias("__vdso_getrandom")));
new file mode 100644
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2022 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>
+
+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 (__vdso_data->clock_mode == VDSO_CLOCKMODE_TIMENS)
+ return (void *)&__vdso_rng_data +
+ ((void *)&__timens_vdso_data - (void *)&__vdso_data);
+ return &__vdso_rng_data;
+}
+
+/*
+ * Generates a given positive number of block of ChaCha20 output with nonce=0,
+ * and does not write to any stack or memory outside of the parameters passed
+ * to it. This way, we don't need to worry about stack data leaking into forked
+ * child processes.
+ */
+static __always_inline void __arch_chacha20_blocks_nostack(u8 *dst_bytes, const u32 *key, u32 *counter, size_t nblocks)
+{
+ extern void chacha20_blocks_nostack(u8 *dst_bytes, const u32 *key, u32 *counter, size_t nblocks);
+ return chacha20_blocks_nostack(dst_bytes, key, counter, nblocks);
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_GETRANDOM_H */
@@ -11,6 +11,8 @@
#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.
*/
@@ -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
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. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> --- 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 | 181 ++++++++++++++++++++++++ arch/x86/entry/vdso/vgetrandom.c | 18 +++ arch/x86/include/asm/vdso/getrandom.h | 49 +++++++ arch/x86/include/asm/vdso/vsyscall.h | 2 + arch/x86/include/asm/vvar.h | 16 +++ 8 files changed, 271 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