Merge tag 'random-6.12-rc1-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/crng/random

Pull random number generator updates from Jason Donenfeld:
 "Originally I'd planned on sending each of the vDSO getrandom()
  architecture ports to their respective arch trees. But as we started
  to work on this, we found lots of interesting issues in the shared
  code and infrastructure, the fixes for which the various archs needed
  to base their work.

  So in the end, this turned into a nice collaborative effort fixing up
  issues and porting to 5 new architectures -- arm64, powerpc64,
  powerpc32, s390x, and loongarch64 -- with everybody pitching in and
  commenting on each other's code. It was a fun development cycle.

  This contains:

   - Numerous fixups to the vDSO selftest infrastructure, getting it
     running successfully on more platforms, and fixing bugs in it.

   - Additions to the vDSO getrandom & chacha selftests. Basically every
     time manual review unearthed a bug in a revision of an arch patch,
     or an ambiguity, the tests were augmented.

     By the time the last arch was submitted for review, s390x, v1 of
     the series was essentially fine right out of the gate.

   - Fixes to the the generic C implementation of vDSO getrandom, to
     build and run successfully on all archs, decoupling it from
     assumptions we had (unintentionally) made on x86_64 that didn't
     carry through to the other architectures.

   - Port of vDSO getrandom to LoongArch64, from Xi Ruoyao and acked by
     Huacai Chen.

   - Port of vDSO getrandom to ARM64, from Adhemerval Zanella and acked
     by Will Deacon.

   - Port of vDSO getrandom to PowerPC, in both 32-bit and 64-bit
     varieties, from Christophe Leroy and acked by Michael Ellerman.

   - Port of vDSO getrandom to S390X from Heiko Carstens, the arch
     maintainer.

  While it'd be natural for there to be things to fix up over the course
  of the development cycle, these patches got a decent amount of review
  from a fairly diverse crew of folks on the mailing lists, and, for the
  most part, they've been cooking in linux-next, which has been helpful
  for ironing out build issues.

  In terms of architectures, I think that mostly takes care of the
  important 64-bit archs with hardware still being produced and running
  production loads in settings where vDSO getrandom is likely to help.

  Arguably there's still RISC-V left, and we'll see for 6.13 whether
  they find it useful and submit a port"

* tag 'random-6.12-rc1-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/crng/random: (47 commits)
  selftests: vDSO: check cpu caps before running chacha test
  s390/vdso: Wire up getrandom() vdso implementation
  s390/vdso: Move vdso symbol handling to separate header file
  s390/vdso: Allow alternatives in vdso code
  s390/module: Provide find_section() helper
  s390/facility: Let test_facility() generate static branch if possible
  s390/alternatives: Remove ALT_FACILITY_EARLY
  s390/facility: Disable compile time optimization for decompressor code
  selftests: vDSO: fix vdso_config for s390
  selftests: vDSO: fix ELF hash table entry size for s390x
  powerpc/vdso: Wire up getrandom() vDSO implementation on VDSO64
  powerpc/vdso: Wire up getrandom() vDSO implementation on VDSO32
  powerpc/vdso: Refactor CFLAGS for CVDSO build
  powerpc/vdso32: Add crtsavres
  mm: Define VM_DROPPABLE for powerpc/32
  powerpc/vdso: Fix VDSO data access when running in a non-root time namespace
  selftests: vDSO: don't include generated headers for chacha test
  arm64: vDSO: Wire up getrandom() vDSO implementation
  arm64: alternative: make alternative_has_cap_likely() VDSO compatible
  selftests: vDSO: also test counter in vdso_test_chacha
  ...

21 files changed, 322 insertions, 99 deletions

diff --git a/tools/arch/arm64/vdso b/tools/arch/arm64/vdso
new file mode 120000
index 000000000000..233c7a26f6e5
--- /dev/null
+++ b/tools/arch/arm64/vdso
@@ -0,0 +1 @@
+../../../arch/arm64/kernel/vdso
\ No newline at end of file
diff --git a/tools/arch/loongarch/vdso b/tools/arch/loongarch/vdso
new file mode 120000
index 000000000000..ebda43a82db7
--- /dev/null
+++ b/tools/arch/loongarch/vdso
@@ -0,0 +1 @@
+../../../arch/loongarch/vdso
\ No newline at end of file
diff --git a/tools/arch/powerpc/vdso b/tools/arch/powerpc/vdso
new file mode 120000
index 000000000000..4e676d1d1cb4
--- /dev/null
+++ b/tools/arch/powerpc/vdso
@@ -0,0 +1 @@
+../../../arch/powerpc/kernel/vdso
\ No newline at end of file
diff --git a/tools/arch/s390/vdso b/tools/arch/s390/vdso
new file mode 120000
index 000000000000..6cf4c1cebdcd
--- /dev/null
+++ b/tools/arch/s390/vdso
@@ -0,0 +1 @@
+../../../arch/s390/kernel/vdso64
\ No newline at end of file
diff --git a/tools/arch/x86/vdso b/tools/arch/x86/vdso
new file mode 120000
index 000000000000..7eb962fd3454
--- /dev/null
+++ b/tools/arch/x86/vdso
@@ -0,0 +1 @@
+../../../arch/x86/entry/vdso/
\ No newline at end of file
diff --git a/tools/include/asm/alternative.h b/tools/include/asm/alternative.h
index 7ce02a223732..8e548ac8f740 100644
--- a/tools/include/asm/alternative.h
+++ b/tools/include/asm/alternative.h
@@ -2,8 +2,18 @@
 #ifndef _TOOLS_ASM_ALTERNATIVE_ASM_H
 #define _TOOLS_ASM_ALTERNATIVE_ASM_H
 
+#if defined(__s390x__)
+#ifdef __ASSEMBLY__
+.macro ALTERNATIVE oldinstr, newinstr, feature
+	\oldinstr
+.endm
+#endif
+#else
+
 /* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */
 
 #define ALTERNATIVE #
 
 #endif
+
+#endif
diff --git a/tools/include/generated/asm-offsets.h b/tools/include/generated/asm-offsets.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/include/generated/asm-offsets.h
diff --git a/tools/include/generated/asm/cpucap-defs.h b/tools/include/generated/asm/cpucap-defs.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/include/generated/asm/cpucap-defs.h
diff --git a/tools/include/generated/asm/sysreg-defs.h b/tools/include/generated/asm/sysreg-defs.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/include/generated/asm/sysreg-defs.h
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 6f7f22ac9da5..4366da278033 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -2,6 +2,8 @@
 #ifndef _TOOLS_LINUX_COMPILER_H_
 #define _TOOLS_LINUX_COMPILER_H_
 
+#ifndef __ASSEMBLY__
+
 #include <linux/compiler_types.h>
 
 #ifndef __compiletime_error
@@ -224,4 +226,6 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 	__asm__ ("" : "=r" (var) : "0" (var))
 #endif
 
+#endif /* __ASSEMBLY__ */
+
 #endif /* _TOOLS_LINUX_COMPILER_H */
diff --git a/tools/include/linux/linkage.h b/tools/include/linux/linkage.h
index bc763d500262..a48ff086899c 100644
--- a/tools/include/linux/linkage.h
+++ b/tools/include/linux/linkage.h
@@ -1,4 +1,8 @@
 #ifndef _TOOLS_INCLUDE_LINUX_LINKAGE_H
 #define _TOOLS_INCLUDE_LINUX_LINKAGE_H
 
+#define SYM_FUNC_START(x) .globl x; x:
+
+#define SYM_FUNC_END(x)
+
 #endif /* _TOOLS_INCLUDE_LINUX_LINKAGE_H */
diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile
index 3de8e7e052ae..af9cedbf5357 100644
--- a/tools/testing/selftests/vDSO/Makefile
+++ b/tools/testing/selftests/vDSO/Makefile
@@ -1,7 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-uname_M := $(shell uname -m 2>/dev/null || echo not)
-ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
-SODIUM := $(shell pkg-config --libs libsodium 2>/dev/null)
+include ../../../scripts/Makefile.arch
 
 TEST_GEN_PROGS := vdso_test_gettimeofday
 TEST_GEN_PROGS += vdso_test_getcpu
@@ -11,14 +9,12 @@ ifeq ($(ARCH),$(filter $(ARCH),x86 x86_64))
 TEST_GEN_PROGS += vdso_standalone_test_x86
 endif
 TEST_GEN_PROGS += vdso_test_correctness
-ifeq ($(uname_M),x86_64)
+ifeq ($(ARCH)$(CONFIG_X86_32),$(filter $(ARCH)$(CONFIG_X86_32),x86 x86_64 loongarch arm64 powerpc s390))
 TEST_GEN_PROGS += vdso_test_getrandom
-ifneq ($(SODIUM),)
 TEST_GEN_PROGS += vdso_test_chacha
 endif
-endif
 
-CFLAGS := -std=gnu99
+CFLAGS := -std=gnu99 -O2
 
 ifeq ($(CONFIG_X86_32),y)
 LDLIBS += -lgcc_s
@@ -38,11 +34,12 @@ $(OUTPUT)/vdso_test_correctness: LDFLAGS += -ldl
 
 $(OUTPUT)/vdso_test_getrandom: parse_vdso.c
 $(OUTPUT)/vdso_test_getrandom: CFLAGS += -isystem $(top_srcdir)/tools/include \
+                                         $(KHDR_INCLUDES) \
                                          -isystem $(top_srcdir)/include/uapi
 
-$(OUTPUT)/vdso_test_chacha: $(top_srcdir)/arch/$(ARCH)/entry/vdso/vgetrandom-chacha.S
+$(OUTPUT)/vdso_test_chacha: $(top_srcdir)/tools/arch/$(SRCARCH)/vdso/vgetrandom-chacha.S
 $(OUTPUT)/vdso_test_chacha: CFLAGS += -idirafter $(top_srcdir)/tools/include \
-                                      -isystem $(top_srcdir)/arch/$(ARCH)/include \
-                                      -isystem $(top_srcdir)/include \
-                                      -D__ASSEMBLY__ -DBULID_VDSO -DCONFIG_FUNCTION_ALIGNMENT=0 \
-                                      -Wa,--noexecstack $(SODIUM)
+                                      -idirafter $(top_srcdir)/tools/include/generated \
+                                      -idirafter $(top_srcdir)/arch/$(SRCARCH)/include \
+                                      -idirafter $(top_srcdir)/include \
+                                      -D__ASSEMBLY__ -Wa,--noexecstack
diff --git a/tools/testing/selftests/vDSO/parse_vdso.c b/tools/testing/selftests/vDSO/parse_vdso.c
index 4ae417372e9e..7dd5668ea8a6 100644
--- a/tools/testing/selftests/vDSO/parse_vdso.c
+++ b/tools/testing/selftests/vDSO/parse_vdso.c
@@ -36,6 +36,12 @@
 #define ELF_BITS_XFORM(bits, x) ELF_BITS_XFORM2(bits, x)
 #define ELF(x) ELF_BITS_XFORM(ELF_BITS, x)
 
+#ifdef __s390x__
+#define ELF_HASH_ENTRY ELF(Xword)
+#else
+#define ELF_HASH_ENTRY ELF(Word)
+#endif
+
 static struct vdso_info
 {
 	bool valid;
@@ -47,8 +53,8 @@ static struct vdso_info
 	/* Symbol table */
 	ELF(Sym) *symtab;
 	const char *symstrings;
-	ELF(Word) *bucket, *chain;
-	ELF(Word) nbucket, nchain;
+	ELF_HASH_ENTRY *bucket, *chain;
+	ELF_HASH_ENTRY nbucket, nchain;
 
 	/* Version table */
 	ELF(Versym) *versym;
@@ -115,7 +121,7 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base)
 	/*
 	 * Fish out the useful bits of the dynamic table.
 	 */
-	ELF(Word) *hash = 0;
+	ELF_HASH_ENTRY *hash = 0;
 	vdso_info.symstrings = 0;
 	vdso_info.symtab = 0;
 	vdso_info.versym = 0;
@@ -133,7 +139,7 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base)
 				 + vdso_info.load_offset);
 			break;
 		case DT_HASH:
-			hash = (ELF(Word) *)
+			hash = (ELF_HASH_ENTRY *)
 				((uintptr_t)dyn[i].d_un.d_ptr
 				 + vdso_info.load_offset);
 			break;
@@ -216,7 +222,8 @@ void *vdso_sym(const char *version, const char *name)
 		ELF(Sym) *sym = &vdso_info.symtab[chain];
 
 		/* Check for a defined global or weak function w/ right name. */
-		if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC)
+		if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC &&
+		    ELF64_ST_TYPE(sym->st_info) != STT_NOTYPE)
 			continue;
 		if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL &&
 		    ELF64_ST_BIND(sym->st_info) != STB_WEAK)
diff --git a/tools/testing/selftests/vDSO/vdso_call.h b/tools/testing/selftests/vDSO/vdso_call.h
new file mode 100644
index 000000000000..bb237d771051
--- /dev/null
+++ b/tools/testing/selftests/vDSO/vdso_call.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Macro to call vDSO functions
+ *
+ * Copyright (C) 2024 Christophe Leroy <christophe.leroy@csgroup.eu>, CS GROUP France
+ */
+#ifndef __VDSO_CALL_H__
+#define __VDSO_CALL_H__
+
+#ifdef __powerpc__
+
+#define LOADARGS_1(fn, __arg1) do {					\
+	_r0 = fn;							\
+	_r3 = (long)__arg1;						\
+} while (0)
+
+#define LOADARGS_2(fn, __arg1, __arg2) do {				\
+	_r0 = fn;							\
+	_r3 = (long)__arg1;						\
+	_r4 = (long)__arg2;						\
+} while (0)
+
+#define LOADARGS_3(fn, __arg1, __arg2, __arg3) do {			\
+	_r0 = fn;							\
+	_r3 = (long)__arg1;						\
+	_r4 = (long)__arg2;						\
+	_r5 = (long)__arg3;						\
+} while (0)
+
+#define LOADARGS_5(fn, __arg1, __arg2, __arg3, __arg4, __arg5) do {	\
+	_r0 = fn;							\
+	_r3 = (long)__arg1;						\
+	_r4 = (long)__arg2;						\
+	_r5 = (long)__arg3;						\
+	_r6 = (long)__arg4;						\
+	_r7 = (long)__arg5;						\
+} while (0)
+
+#define VDSO_CALL(fn, nr, args...) ({					\
+	register void *_r0 asm ("r0");					\
+	register long _r3 asm ("r3");					\
+	register long _r4 asm ("r4");					\
+	register long _r5 asm ("r5");					\
+	register long _r6 asm ("r6");					\
+	register long _r7 asm ("r7");					\
+	register long _r8 asm ("r8");					\
+	register long _rval asm ("r3");					\
+									\
+	LOADARGS_##nr(fn, args);					\
+									\
+	asm volatile(							\
+		"	mtctr %0\n"					\
+		"	bctrl\n"					\
+		"	bns+	1f\n"					\
+		"	neg	3, 3\n"					\
+		"1:"							\
+		: "+r" (_r0), "=r" (_r3), "+r" (_r4), "+r" (_r5),	\
+		  "+r" (_r6), "+r" (_r7), "+r" (_r8)			\
+		: "r" (_rval)						\
+		: "r9", "r10", "r11", "r12", "cr0", "cr1", "cr5",	\
+		  "cr6", "cr7", "xer", "lr", "ctr", "memory"		\
+	);								\
+	_rval;								\
+})
+
+#else
+#define VDSO_CALL(fn, nr, args...)	fn(args)
+#endif
+
+#endif
diff --git a/tools/testing/selftests/vDSO/vdso_config.h b/tools/testing/selftests/vDSO/vdso_config.h
index 7b543e7f04d7..722260f97561 100644
--- a/tools/testing/selftests/vDSO/vdso_config.h
+++ b/tools/testing/selftests/vDSO/vdso_config.h
@@ -18,18 +18,18 @@
 #elif defined(__aarch64__)
 #define VDSO_VERSION		3
 #define VDSO_NAMES		0
-#elif defined(__powerpc__)
+#elif defined(__powerpc64__)
 #define VDSO_VERSION		1
 #define VDSO_NAMES		0
-#define VDSO_32BIT		1
-#elif defined(__powerpc64__)
+#elif defined(__powerpc__)
 #define VDSO_VERSION		1
 #define VDSO_NAMES		0
-#elif defined (__s390__)
+#define VDSO_32BIT		1
+#elif defined (__s390__) && !defined(__s390x__)
 #define VDSO_VERSION		2
 #define VDSO_NAMES		0
 #define VDSO_32BIT		1
-#elif defined (__s390X__)
+#elif defined (__s390x__)
 #define VDSO_VERSION		2
 #define VDSO_NAMES		0
 #elif defined(__mips__)
@@ -68,16 +68,15 @@ static const char *versions[7] = {
 	"LINUX_5.10"
 };
 
-static const char *names[2][6] = {
+static const char *names[2][7] = {
 	{
 		"__kernel_gettimeofday",
 		"__kernel_clock_gettime",
 		"__kernel_time",
 		"__kernel_clock_getres",
 		"__kernel_getcpu",
-#if defined(VDSO_32BIT)
 		"__kernel_clock_gettime64",
-#endif
+		"__kernel_getrandom",
 	},
 	{
 		"__vdso_gettimeofday",
@@ -85,9 +84,8 @@ static const char *names[2][6] = {
 		"__vdso_time",
 		"__vdso_clock_getres",
 		"__vdso_getcpu",
-#if defined(VDSO_32BIT)
 		"__vdso_clock_gettime64",
-#endif
+		"__vdso_getrandom",
 	},
 };
 
diff --git a/tools/testing/selftests/vDSO/vdso_test_abi.c b/tools/testing/selftests/vDSO/vdso_test_abi.c
index 96d32fd65b42..a54424e2336f 100644
--- a/tools/testing/selftests/vDSO/vdso_test_abi.c
+++ b/tools/testing/selftests/vDSO/vdso_test_abi.c
@@ -20,10 +20,8 @@
 
 #include "../kselftest.h"
 #include "vdso_config.h"
-
-extern void *vdso_sym(const char *version, const char *name);
-extern void vdso_init_from_sysinfo_ehdr(uintptr_t base);
-extern void vdso_init_from_auxv(void *auxv);
+#include "vdso_call.h"
+#include "parse_vdso.h"
 
 static const char *version;
 static const char **name;
@@ -61,7 +59,7 @@ static void vdso_test_gettimeofday(void)
 	}
 
 	struct timeval tv;
-	long ret = vdso_gettimeofday(&tv, 0);
+	long ret = VDSO_CALL(vdso_gettimeofday, 2, &tv, 0);
 
 	if (ret == 0) {
 		ksft_print_msg("The time is %lld.%06lld\n",
@@ -86,7 +84,7 @@ static void vdso_test_clock_gettime(clockid_t clk_id)
 	}
 
 	struct timespec ts;
-	long ret = vdso_clock_gettime(clk_id, &ts);
+	long ret = VDSO_CALL(vdso_clock_gettime, 2, clk_id, &ts);
 
 	if (ret == 0) {
 		ksft_print_msg("The time is %lld.%06lld\n",
@@ -111,7 +109,7 @@ static void vdso_test_time(void)
 		return;
 	}
 
-	long ret = vdso_time(NULL);
+	long ret = VDSO_CALL(vdso_time, 1, NULL);
 
 	if (ret > 0) {
 		ksft_print_msg("The time in hours since January 1, 1970 is %lld\n",
@@ -138,7 +136,7 @@ static void vdso_test_clock_getres(clockid_t clk_id)
 	}
 
 	struct timespec ts, sys_ts;
-	long ret = vdso_clock_getres(clk_id, &ts);
+	long ret = VDSO_CALL(vdso_clock_getres, 2, clk_id, &ts);
 
 	if (ret == 0) {
 		ksft_print_msg("The vdso resolution is %lld %lld\n",
diff --git a/tools/testing/selftests/vDSO/vdso_test_chacha.c b/tools/testing/selftests/vDSO/vdso_test_chacha.c
index e38f44e5f803..b1ea532c5996 100644
--- a/tools/testing/selftests/vDSO/vdso_test_chacha.c
+++ b/tools/testing/selftests/vDSO/vdso_test_chacha.c
@@ -3,23 +3,90 @@
  * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
  */
 
-#include <sodium/crypto_stream_chacha20.h>
+#include <tools/le_byteshift.h>
 #include <sys/random.h>
+#include <sys/auxv.h>
 #include <string.h>
 #include <stdint.h>
+#include <stdbool.h>
 #include "../kselftest.h"
 
-extern void __arch_chacha20_blocks_nostack(uint8_t *dst_bytes, const uint8_t *key, uint32_t *counter, size_t nblocks);
+#if defined(__aarch64__)
+static bool cpu_has_capabilities(void)
+{
+	return getauxval(AT_HWCAP) & HWCAP_ASIMD;
+}
+#elif defined(__s390x__)
+static bool cpu_has_capabilities(void)
+{
+	return getauxval(AT_HWCAP) & HWCAP_S390_VXRS;
+}
+#else
+static bool cpu_has_capabilities(void)
+{
+	return true;
+}
+#endif
+
+static uint32_t rol32(uint32_t word, unsigned int shift)
+{
+	return (word << (shift & 31)) | (word >> ((-shift) & 31));
+}
+
+static void reference_chacha20_blocks(uint8_t *dst_bytes, const uint32_t *key, uint32_t *counter, size_t nblocks)
+{
+	uint32_t s[16] = {
+		0x61707865U, 0x3320646eU, 0x79622d32U, 0x6b206574U,
+		key[0], key[1], key[2], key[3], key[4], key[5], key[6], key[7],
+		counter[0], counter[1], 0, 0
+	};
+
+	while (nblocks--) {
+		uint32_t x[16];
+		memcpy(x, s, sizeof(x));
+		for (unsigned int r = 0; r < 20; r += 2) {
+		#define QR(a, b, c, d) ( \
+			x[a] += x[b], \
+			x[d] = rol32(x[d] ^ x[a], 16), \
+			x[c] += x[d], \
+			x[b] = rol32(x[b] ^ x[c], 12), \
+			x[a] += x[b], \
+			x[d] = rol32(x[d] ^ x[a], 8), \
+			x[c] += x[d], \
+			x[b] = rol32(x[b] ^ x[c], 7))
+
+			QR(0, 4, 8, 12);
+			QR(1, 5, 9, 13);
+			QR(2, 6, 10, 14);
+			QR(3, 7, 11, 15);
+			QR(0, 5, 10, 15);
+			QR(1, 6, 11, 12);
+			QR(2, 7, 8, 13);
+			QR(3, 4, 9, 14);
+		}
+		for (unsigned int i = 0; i < 16; ++i, dst_bytes += sizeof(uint32_t))
+			put_unaligned_le32(x[i] + s[i], dst_bytes);
+		if (!++s[12])
+			++s[13];
+	}
+	counter[0] = s[12];
+	counter[1] = s[13];
+}
+
+typedef uint8_t u8;
+typedef uint32_t u32;
+typedef uint64_t u64;
+#include <vdso/getrandom.h>
 
 int main(int argc, char *argv[])
 {
 	enum { TRIALS = 1000, BLOCKS = 128, BLOCK_SIZE = 64 };
-	static const uint8_t nonce[8] = { 0 };
-	uint32_t counter[2];
-	uint8_t key[32];
+	uint32_t key[8], counter1[2], counter2[2];
 	uint8_t output1[BLOCK_SIZE * BLOCKS], output2[BLOCK_SIZE * BLOCKS];
 
 	ksft_print_header();
+	if (!cpu_has_capabilities())
+		ksft_exit_skip("Required CPU capabilities missing\n");
 	ksft_set_plan(1);
 
 	for (unsigned int trial = 0; trial < TRIALS; ++trial) {
@@ -27,17 +94,33 @@ int main(int argc, char *argv[])
 			printf("getrandom() failed!\n");
 			return KSFT_SKIP;
 		}
-		crypto_stream_chacha20(output1, sizeof(output1), nonce, key);
+		memset(counter1, 0, sizeof(counter1));
+		reference_chacha20_blocks(output1, key, counter1, BLOCKS);
 		for (unsigned int split = 0; split < BLOCKS; ++split) {
 			memset(output2, 'X', sizeof(output2));
-			memset(counter, 0, sizeof(counter));
+			memset(counter2, 0, sizeof(counter2));
 			if (split)
-				__arch_chacha20_blocks_nostack(output2, key, counter, split);
-			__arch_chacha20_blocks_nostack(output2 + split * BLOCK_SIZE, key, counter, BLOCKS - split);
-			if (memcmp(output1, output2, sizeof(output1)))
+				__arch_chacha20_blocks_nostack(output2, key, counter2, split);
+			__arch_chacha20_blocks_nostack(output2 + split * BLOCK_SIZE, key, counter2, BLOCKS - split);
+			if (memcmp(output1, output2, sizeof(output1)) || memcmp(counter1, counter2, sizeof(counter1)))
 				return KSFT_FAIL;
 		}
 	}
+	memset(counter1, 0, sizeof(counter1));
+	counter1[0] = (uint32_t)-BLOCKS + 2;
+	memset(counter2, 0, sizeof(counter2));
+	counter2[0] = (uint32_t)-BLOCKS + 2;
+
+	reference_chacha20_blocks(output1, key, counter1, BLOCKS);
+	__arch_chacha20_blocks_nostack(output2, key, counter2, BLOCKS);
+	if (memcmp(output1, output2, sizeof(output1)) || memcmp(counter1, counter2, sizeof(counter1)))
+		return KSFT_FAIL;
+
+	reference_chacha20_blocks(output1, key, counter1, BLOCKS);
+	__arch_chacha20_blocks_nostack(output2, key, counter2, BLOCKS);
+	if (memcmp(output1, output2, sizeof(output1)) || memcmp(counter1, counter2, sizeof(counter1)))
+		return KSFT_FAIL;
+
 	ksft_test_result_pass("chacha: PASS\n");
 	return KSFT_PASS;
 }
diff --git a/tools/testing/selftests/vDSO/vdso_test_correctness.c b/tools/testing/selftests/vDSO/vdso_test_correctness.c
index e691a3cf1491..5fb97ad67eea 100644
--- a/tools/testing/selftests/vDSO/vdso_test_correctness.c
+++ b/tools/testing/selftests/vDSO/vdso_test_correctness.c
@@ -20,6 +20,7 @@
 #include <limits.h>
 
 #include "vdso_config.h"
+#include "vdso_call.h"
 #include "../kselftest.h"
 
 static const char **name;
@@ -114,6 +115,12 @@ static void fill_function_pointers()
 	if (!vdso)
 		vdso = dlopen("linux-gate.so.1",
 			      RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD);
+	if (!vdso)
+		vdso = dlopen("linux-vdso32.so.1",
+			      RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD);
+	if (!vdso)
+		vdso = dlopen("linux-vdso64.so.1",
+			      RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD);
 	if (!vdso) {
 		printf("[WARN]\tfailed to find vDSO\n");
 		return;
@@ -180,7 +187,7 @@ static void test_getcpu(void)
 
 		ret_sys = sys_getcpu(&cpu_sys, &node_sys, 0);
 		if (vdso_getcpu)
-			ret_vdso = vdso_getcpu(&cpu_vdso, &node_vdso, 0);
+			ret_vdso = VDSO_CALL(vdso_getcpu, 3, &cpu_vdso, &node_vdso, 0);
 		if (vgetcpu)
 			ret_vsys = vgetcpu(&cpu_vsys, &node_vsys, 0);
 
@@ -263,7 +270,7 @@ static void test_one_clock_gettime(int clock, const char *name)
 
 	if (sys_clock_gettime(clock, &start) < 0) {
 		if (errno == EINVAL) {
-			vdso_ret = vdso_clock_gettime(clock, &vdso);
+			vdso_ret = VDSO_CALL(vdso_clock_gettime, 2, clock, &vdso);
 			if (vdso_ret == -EINVAL) {
 				printf("[OK]\tNo such clock.\n");
 			} else {
@@ -276,7 +283,7 @@ static void test_one_clock_gettime(int clock, const char *name)
 		return;
 	}
 
-	vdso_ret = vdso_clock_gettime(clock, &vdso);
+	vdso_ret = VDSO_CALL(vdso_clock_gettime, 2, clock, &vdso);
 	end_ret = sys_clock_gettime(clock, &end);
 
 	if (vdso_ret != 0 || end_ret != 0) {
@@ -325,7 +332,7 @@ static void test_one_clock_gettime64(int clock, const char *name)
 
 	if (sys_clock_gettime64(clock, &start) < 0) {
 		if (errno == EINVAL) {
-			vdso_ret = vdso_clock_gettime64(clock, &vdso);
+			vdso_ret = VDSO_CALL(vdso_clock_gettime64, 2, clock, &vdso);
 			if (vdso_ret == -EINVAL) {
 				printf("[OK]\tNo such clock.\n");
 			} else {
@@ -338,7 +345,7 @@ static void test_one_clock_gettime64(int clock, const char *name)
 		return;
 	}
 
-	vdso_ret = vdso_clock_gettime64(clock, &vdso);
+	vdso_ret = VDSO_CALL(vdso_clock_gettime64, 2, clock, &vdso);
 	end_ret = sys_clock_gettime64(clock, &end);
 
 	if (vdso_ret != 0 || end_ret != 0) {
@@ -395,7 +402,7 @@ static void test_gettimeofday(void)
 		return;
 	}
 
-	vdso_ret = vdso_gettimeofday(&vdso, &vdso_tz);
+	vdso_ret = VDSO_CALL(vdso_gettimeofday, 2, &vdso, &vdso_tz);
 	end_ret = sys_gettimeofday(&end, NULL);
 
 	if (vdso_ret != 0 || end_ret != 0) {
@@ -425,7 +432,7 @@ static void test_gettimeofday(void)
 	}
 
 	/* And make sure that passing NULL for tz doesn't crash. */
-	vdso_gettimeofday(&vdso, NULL);
+	VDSO_CALL(vdso_gettimeofday, 2, &vdso, NULL);
 }
 
 int main(int argc, char **argv)
diff --git a/tools/testing/selftests/vDSO/vdso_test_getcpu.c b/tools/testing/selftests/vDSO/vdso_test_getcpu.c
index b758f68c6c9c..cdeaed45fb26 100644
--- a/tools/testing/selftests/vDSO/vdso_test_getcpu.c
+++ b/tools/testing/selftests/vDSO/vdso_test_getcpu.c
@@ -14,6 +14,7 @@
 #include "../kselftest.h"
 #include "parse_vdso.h"
 #include "vdso_config.h"
+#include "vdso_call.h"
 
 struct getcpu_cache;
 typedef long (*getcpu_t)(unsigned int *, unsigned int *,
@@ -42,7 +43,7 @@ int main(int argc, char **argv)
 		return KSFT_SKIP;
 	}
 
-	ret = get_cpu(&cpu, &node, 0);
+	ret = VDSO_CALL(get_cpu, 3, &cpu, &node, 0);
 	if (ret == 0) {
 		printf("Running on CPU %u node %u\n", cpu, node);
 	} else {
diff --git a/tools/testing/selftests/vDSO/vdso_test_getrandom.c b/tools/testing/selftests/vDSO/vdso_test_getrandom.c
index 05122425a873..72a1d9b43a84 100644
--- a/tools/testing/selftests/vDSO/vdso_test_getrandom.c
+++ b/tools/testing/selftests/vDSO/vdso_test_getrandom.c
@@ -16,11 +16,17 @@
 #include <sys/mman.h>
 #include <sys/random.h>
 #include <sys/syscall.h>
+#include <sys/ptrace.h>
+#include <sys/wait.h>
 #include <sys/types.h>
 #include <linux/random.h>
+#include <linux/compiler.h>
+#include <linux/ptrace.h>
 
 #include "../kselftest.h"
 #include "parse_vdso.h"
+#include "vdso_config.h"
+#include "vdso_call.h"
 
 #ifndef timespecsub
 #define	timespecsub(tsp, usp, vsp)					\
@@ -38,50 +44,43 @@ static struct {
 	pthread_mutex_t lock;
 	void **states;
 	size_t len, cap;
-} grnd_allocator = {
-	.lock = PTHREAD_MUTEX_INITIALIZER
-};
-
-static struct {
 	ssize_t(*fn)(void *, size_t, unsigned long, void *, size_t);
-	pthread_key_t key;
-	pthread_once_t initialized;
 	struct vgetrandom_opaque_params params;
-} grnd_ctx = {
-	.initialized = PTHREAD_ONCE_INIT
+} vgrnd = {
+	.lock = PTHREAD_MUTEX_INITIALIZER
 };
 
 static void *vgetrandom_get_state(void)
 {
 	void *state = NULL;
 
-	pthread_mutex_lock(&grnd_allocator.lock);
-	if (!grnd_allocator.len) {
+	pthread_mutex_lock(&vgrnd.lock);
+	if (!vgrnd.len) {
 		size_t page_size = getpagesize();
 		size_t new_cap;
 		size_t alloc_size, num = sysconf(_SC_NPROCESSORS_ONLN); /* Just a decent heuristic. */
 		void *new_block, *new_states;
 
-		alloc_size = (num * grnd_ctx.params.size_of_opaque_state + page_size - 1) & (~(page_size - 1));
-		num = (page_size / grnd_ctx.params.size_of_opaque_state) * (alloc_size / page_size);
-		new_block = mmap(0, alloc_size, grnd_ctx.params.mmap_prot, grnd_ctx.params.mmap_flags, -1, 0);
+		alloc_size = (num * vgrnd.params.size_of_opaque_state + page_size - 1) & (~(page_size - 1));
+		num = (page_size / vgrnd.params.size_of_opaque_state) * (alloc_size / page_size);
+		new_block = mmap(0, alloc_size, vgrnd.params.mmap_prot, vgrnd.params.mmap_flags, -1, 0);
 		if (new_block == MAP_FAILED)
 			goto out;
 
-		new_cap = grnd_allocator.cap + num;
-		new_states = reallocarray(grnd_allocator.states, new_cap, sizeof(*grnd_allocator.states));
+		new_cap = vgrnd.cap + num;
+		new_states = reallocarray(vgrnd.states, new_cap, sizeof(*vgrnd.states));
 		if (!new_states)
 			goto unmap;
-		grnd_allocator.cap = new_cap;
-		grnd_allocator.states = new_states;
+		vgrnd.cap = new_cap;
+		vgrnd.states = new_states;
 
 		for (size_t i = 0; i < num; ++i) {
-			if (((uintptr_t)new_block & (page_size - 1)) + grnd_ctx.params.size_of_opaque_state > page_size)
+			if (((uintptr_t)new_block & (page_size - 1)) + vgrnd.params.size_of_opaque_state > page_size)
 				new_block = (void *)(((uintptr_t)new_block + page_size - 1) & (~(page_size - 1)));
-			grnd_allocator.states[i] = new_block;
-			new_block += grnd_ctx.params.size_of_opaque_state;
+			vgrnd.states[i] = new_block;
+			new_block += vgrnd.params.size_of_opaque_state;
 		}
-		grnd_allocator.len = num;
+		vgrnd.len = num;
 		goto success;
 
 	unmap:
@@ -89,10 +88,10 @@ static void *vgetrandom_get_state(void)
 		goto out;
 	}
 success:
-	state = grnd_allocator.states[--grnd_allocator.len];
+	state = vgrnd.states[--vgrnd.len];
 
 out:
-	pthread_mutex_unlock(&grnd_allocator.lock);
+	pthread_mutex_unlock(&vgrnd.lock);
 	return state;
 }
 
@@ -100,27 +99,33 @@ static void vgetrandom_put_state(void *state)
 {
 	if (!state)
 		return;
-	pthread_mutex_lock(&grnd_allocator.lock);
-	grnd_allocator.states[grnd_allocator.len++] = state;
-	pthread_mutex_unlock(&grnd_allocator.lock);
+	pthread_mutex_lock(&vgrnd.lock);
+	vgrnd.states[vgrnd.len++] = state;
+	pthread_mutex_unlock(&vgrnd.lock);
 }
 
 static void vgetrandom_init(void)
 {
-	if (pthread_key_create(&grnd_ctx.key, vgetrandom_put_state) != 0)
-		return;
+	const char *version = versions[VDSO_VERSION];
+	const char *name = names[VDSO_NAMES][6];
 	unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR);
+	size_t ret;
+
 	if (!sysinfo_ehdr) {
 		printf("AT_SYSINFO_EHDR is not present!\n");
 		exit(KSFT_SKIP);
 	}
 	vdso_init_from_sysinfo_ehdr(sysinfo_ehdr);
-	grnd_ctx.fn = (__typeof__(grnd_ctx.fn))vdso_sym("LINUX_2.6", "__vdso_getrandom");
-	if (!grnd_ctx.fn) {
-		printf("__vdso_getrandom is missing!\n");
+	vgrnd.fn = (__typeof__(vgrnd.fn))vdso_sym(version, name);
+	if (!vgrnd.fn) {
+		printf("%s is missing!\n", name);
 		exit(KSFT_FAIL);
 	}
-	if (grnd_ctx.fn(NULL, 0, 0, &grnd_ctx.params, ~0UL) != 0) {
+	ret = VDSO_CALL(vgrnd.fn, 5, NULL, 0, 0, &vgrnd.params, ~0UL);
+	if (ret == -ENOSYS) {
+		printf("unsupported architecture\n");
+		exit(KSFT_SKIP);
+	} else if (ret) {
 		printf("failed to fetch vgetrandom params!\n");
 		exit(KSFT_FAIL);
 	}
@@ -128,27 +133,21 @@ static void vgetrandom_init(void)
 
 static ssize_t vgetrandom(void *buf, size_t len, unsigned long flags)
 {
-	void *state;
+	static __thread void *state;
 
-	pthread_once(&grnd_ctx.initialized, vgetrandom_init);
-	state = pthread_getspecific(grnd_ctx.key);
 	if (!state) {
 		state = vgetrandom_get_state();
-		if (pthread_setspecific(grnd_ctx.key, state) != 0) {
-			vgetrandom_put_state(state);
-			state = NULL;
-		}
 		if (!state) {
 			printf("vgetrandom_get_state failed!\n");
 			exit(KSFT_FAIL);
 		}
 	}
-	return grnd_ctx.fn(buf, len, flags, state, grnd_ctx.params.size_of_opaque_state);
+	return VDSO_CALL(vgrnd.fn, 5, buf, len, flags, state, vgrnd.params.size_of_opaque_state);
 }
 
 enum { TRIALS = 25000000, THREADS = 256 };
 
-static void *test_vdso_getrandom(void *)
+static void *test_vdso_getrandom(void *ctx)
 {
 	for (size_t i = 0; i < TRIALS; ++i) {
 		unsigned int val;
@@ -158,7 +157,7 @@ static void *test_vdso_getrandom(void *)
 	return NULL;
 }
 
-static void *test_libc_getrandom(void *)
+static void *test_libc_getrandom(void *ctx)
 {
 	for (size_t i = 0; i < TRIALS; ++i) {
 		unsigned int val;
@@ -168,7 +167,7 @@ static void *test_libc_getrandom(void *)
 	return NULL;
 }
 
-static void *test_syscall_getrandom(void *)
+static void *test_syscall_getrandom(void *ctx)
 {
 	for (size_t i = 0; i < TRIALS; ++i) {
 		unsigned int val;
@@ -244,9 +243,10 @@ static void fill(void)
 static void kselftest(void)
 {
 	uint8_t weird_size[1263];
+	pid_t child;
 
 	ksft_print_header();
-	ksft_set_plan(1);
+	ksft_set_plan(2);
 
 	for (size_t i = 0; i < 1000; ++i) {
 		ssize_t ret = vgetrandom(weird_size, sizeof(weird_size), 0);
@@ -255,6 +255,42 @@ static void kselftest(void)
 	}
 
 	ksft_test_result_pass("getrandom: PASS\n");
+
+	unshare(CLONE_NEWUSER);
+	assert(unshare(CLONE_NEWTIME) == 0);
+	child = fork();
+	assert(child >= 0);
+	if (!child) {
+		vgetrandom_init();
+		child = getpid();
+		assert(ptrace(PTRACE_TRACEME, 0, NULL, NULL) == 0);
+		assert(kill(child, SIGSTOP) == 0);
+		assert(vgetrandom(weird_size, sizeof(weird_size), 0) == sizeof(weird_size));
+		_exit(0);
+	}
+	for (;;) {
+		struct ptrace_syscall_info info = { 0 };
+		int status, ret;
+		assert(waitpid(child, &status, 0) >= 0);
+		if (WIFEXITED(status)) {
+			if (WEXITSTATUS(status) != 0)
+				exit(KSFT_FAIL);
+			break;
+		}
+		assert(WIFSTOPPED(status));
+		if (WSTOPSIG(status) == SIGSTOP)
+			assert(ptrace(PTRACE_SETOPTIONS, child, 0, PTRACE_O_TRACESYSGOOD) == 0);
+		else if (WSTOPSIG(status) == (SIGTRAP | 0x80)) {
+			assert(ptrace(PTRACE_GET_SYSCALL_INFO, child, sizeof(info), &info) > 0);
+			if (info.op == PTRACE_SYSCALL_INFO_ENTRY && info.entry.nr == __NR_getrandom &&
+			    info.entry.args[0] == (uintptr_t)weird_size && info.entry.args[1] == sizeof(weird_size))
+				exit(KSFT_FAIL);
+		}
+		assert(ptrace(PTRACE_SYSCALL, child, 0, 0) == 0);
+	}
+
+	ksft_test_result_pass("getrandom timens: PASS\n");
+
 	exit(KSFT_PASS);
 }
 
@@ -265,6 +301,8 @@ static void usage(const char *argv0)
 
 int main(int argc, char *argv[])
 {
+	vgetrandom_init();
+
 	if (argc == 1) {
 		kselftest();
 		return 0;
diff --git a/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c b/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c
index ee4f1ca56a71..e31b18ffae33 100644
--- a/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c
+++ b/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c
@@ -19,6 +19,7 @@
 #include "../kselftest.h"
 #include "parse_vdso.h"
 #include "vdso_config.h"
+#include "vdso_call.h"
 
 int main(int argc, char **argv)
 {
@@ -43,7 +44,7 @@ int main(int argc, char **argv)
 	}
 
 	struct timeval tv;
-	long ret = gtod(&tv, 0);
+	long ret = VDSO_CALL(gtod, 2, &tv, 0);
 
 	if (ret == 0) {
 		printf("The time is %lld.%06lld\n",