x86: vdso: Wire up getrandom() vDSO implementation

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.

Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Samuel Neves <sneves@dei.uc.pt> # for vgetrandom-chacha.S
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

3 files changed, 73 insertions, 0 deletions

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 be199a9b2676..71c56586a22f 100644
--- a/arch/x86/include/asm/vdso/vsyscall.h
+++ b/arch/x86/include/asm/vdso/vsyscall.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.
  */
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