Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Will Deacon:
 "There's a little less than normal, probably due to LPC & Christmas/New
  Year meaning that a few series weren't quite ready or reviewed in
  time. It's still useful across the board, despite the only real
  feature being support for the LS64 feature enabling 64-byte atomic
  accesses to endpoints that support it.

  ACPI:
   - Add interrupt signalling support to the AGDI handler
   - Add Catalin and myself to the arm64 ACPI MAINTAINERS entry

  CPU features:
   - Drop Kconfig options for PAN and LSE (these are detected at runtime)
   - Add support for 64-byte single-copy atomic instructions (LS64/LS64V)
   - Reduce MTE overhead when executing in the kernel on Ampere CPUs
   - Ensure POR_EL0 value exposed via ptrace is up-to-date
   - Fix error handling on GCS allocation failure

  CPU frequency:
   - Add CPU hotplug support to the FIE setup in the AMU driver

  Entry code:
   - Minor optimisations and cleanups to the syscall entry path
   - Preparatory rework for moving to the generic syscall entry code

  Hardware errata:
   - Work around Spectre-BHB on TSV110 processors
   - Work around broken CMO propagation on some systems with the SI-L1
     interconnect

  Miscellaneous:
   - Disable branch profiling for arch/arm64/ to avoid issues with
     noinstr
   - Minor fixes and cleanups (kexec + ubsan, WARN_ONCE() instead of
     WARN_ON(), reduction of boolean expression)
   - Fix custom __READ_ONCE() implementation for LTO builds when
     operating on non-atomic types

  Perf and PMUs:
   - Support for CMN-600AE
   - Be stricter about supported hardware in the CMN driver
   - Support for DSU-110 and DSU-120
   - Support for the cycles event in the DSU driver (alongside the
     dedicated cycles counter)
   - Use IRQF_NO_THREAD instead of IRQF_ONESHOT in the cxlpmu driver
   - Use !bitmap_empty() as a faster alternative to bitmap_weight()
   - Fix SPE error handling when failing to resume profiling

  Selftests:
   - Add support for the FORCE_TARGETS option to the arm64 kselftests
   - Avoid nolibc-specific my_syscall() function
   - Add basic test for the LS64 HWCAP
   - Extend fp-pidbench to cover additional workload patterns"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (43 commits)
  perf/arm-cmn: Reject unsupported hardware configurations
  perf: arm_spe: Properly set hw.state on failures
  arm64/gcs: Fix error handling in arch_set_shadow_stack_status()
  arm64: Fix non-atomic __READ_ONCE() with CONFIG_LTO=y
  arm64: poe: fix stale POR_EL0 values for ptrace
  kselftest/arm64: Raise default number of loops in fp-pidbench
  kselftest/arm64: Add a no-SVE loop after SVE in fp-pidbench
  perf/cxlpmu: Replace IRQF_ONESHOT with IRQF_NO_THREAD
  arm64: mte: Set TCMA1 whenever MTE is present in the kernel
  arm64/ptrace: Return early for ptrace_report_syscall_entry() error
  arm64/ptrace: Split report_syscall()
  arm64: Remove unused _TIF_WORK_MASK
  kselftest/arm64: Add missing file in .gitignore
  arm64: errata: Workaround for SI L1 downstream coherency issue
  kselftest/arm64: Add HWCAP test for FEAT_LS64
  arm64: Add support for FEAT_{LS64, LS64_V}
  KVM: arm64: Enable FEAT_{LS64, LS64_V} in the supported guest
  arm64: Provide basic EL2 setup for FEAT_{LS64, LS64_V} usage at EL0/1
  KVM: arm64: Handle DABT caused by LS64* instructions on unsupported memory
  KVM: arm64: Add documentation for KVM_EXIT_ARM_LDST64B
  ...

6 files changed, 76 insertions, 29 deletions

diff --git a/tools/testing/selftests/arm64/Makefile b/tools/testing/selftests/arm64/Makefile
index c4c72ee2ef55..e456f3b62fa1 100644
--- a/tools/testing/selftests/arm64/Makefile
+++ b/tools/testing/selftests/arm64/Makefile
@@ -30,13 +30,15 @@ all:
 	@for DIR in $(ARM64_SUBTARGETS); do				\
 		BUILD_TARGET=$(OUTPUT)/$$DIR;			\
 		mkdir -p $$BUILD_TARGET;			\
-		make OUTPUT=$$BUILD_TARGET -C $$DIR $@;		\
+		make OUTPUT=$$BUILD_TARGET -C $$DIR $@		\
+			$(if $(FORCE_TARGETS),|| exit); \
 	done
 
 install: all
 	@for DIR in $(ARM64_SUBTARGETS); do				\
 		BUILD_TARGET=$(OUTPUT)/$$DIR;			\
-		make OUTPUT=$$BUILD_TARGET -C $$DIR $@;		\
+		make OUTPUT=$$BUILD_TARGET -C $$DIR $@		\
+			$(if $(FORCE_TARGETS),|| exit); \
 	done
 
 run_tests: all
diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c
index c41640f18e4e..9d2df1f3e6bb 100644
--- a/tools/testing/selftests/arm64/abi/hwcap.c
+++ b/tools/testing/selftests/arm64/abi/hwcap.c
@@ -11,6 +11,8 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <linux/auxvec.h>
+#include <linux/compiler.h>
 #include <sys/auxv.h>
 #include <sys/prctl.h>
 #include <asm/hwcap.h>
@@ -595,6 +597,45 @@ static void lrcpc3_sigill(void)
 	              : "=r" (data0), "=r" (data1) : "r" (src) :);
 }
 
+static void ignore_signal(int sig, siginfo_t *info, void *context)
+{
+	ucontext_t *uc = context;
+
+	uc->uc_mcontext.pc += 4;
+}
+
+static void ls64_sigill(void)
+{
+	struct sigaction ign, old;
+	char src[64] __aligned(64) = { 1 };
+
+	/*
+	 * LS64 requires target memory to be Device/Non-cacheable (if
+	 * FEAT_LS64WB not supported) and the completer supports these
+	 * instructions, otherwise we'll receive a SIGBUS. Since we are only
+	 * testing the ABI here, so just ignore the SIGBUS and see if we can
+	 * execute the instructions without receiving a SIGILL. Restore the
+	 * handler of SIGBUS after this test.
+	 */
+	ign.sa_sigaction = ignore_signal;
+	ign.sa_flags = SA_SIGINFO | SA_RESTART;
+	sigemptyset(&ign.sa_mask);
+	sigaction(SIGBUS, &ign, &old);
+
+	register void *xn asm ("x8") = src;
+	register u64 xt_1 asm ("x0");
+
+	/* LD64B x0, [x8] */
+	asm volatile(".inst 0xf83fd100" : "=r" (xt_1) : "r" (xn)
+		     : "x1", "x2", "x3", "x4", "x5", "x6", "x7");
+
+	/* ST64B x0, [x8] */
+	asm volatile(".inst 0xf83f9100" : : "r" (xt_1), "r" (xn)
+		     : "x1", "x2", "x3", "x4", "x5", "x6", "x7");
+
+	sigaction(SIGBUS, &old, NULL);
+}
+
 static const struct hwcap_data {
 	const char *name;
 	unsigned long at_hwcap;
@@ -1134,6 +1175,14 @@ static const struct hwcap_data {
 		.hwcap_bit = HWCAP3_MTE_STORE_ONLY,
 		.cpuinfo = "mtestoreonly",
 	},
+	{
+		.name = "LS64",
+		.at_hwcap = AT_HWCAP3,
+		.hwcap_bit = HWCAP3_LS64,
+		.cpuinfo = "ls64",
+		.sigill_fn = ls64_sigill,
+		.sigill_reliable = true,
+	},
 };
 
 typedef void (*sighandler_fn)(int, siginfo_t *, void *);
diff --git a/tools/testing/selftests/arm64/abi/tpidr2.c b/tools/testing/selftests/arm64/abi/tpidr2.c
index 1703543fb7c7..ce4550fb7224 100644
--- a/tools/testing/selftests/arm64/abi/tpidr2.c
+++ b/tools/testing/selftests/arm64/abi/tpidr2.c
@@ -128,8 +128,7 @@ static int sys_clone(unsigned long clone_flags, unsigned long newsp,
 		     int *parent_tidptr, unsigned long tls,
 		     int *child_tidptr)
 {
-	return my_syscall5(__NR_clone, clone_flags, newsp, parent_tidptr, tls,
-			   child_tidptr);
+	return syscall(__NR_clone, clone_flags, newsp, parent_tidptr, tls, child_tidptr);
 }
 
 #define __STACK_SIZE (8 * 1024 * 1024)
diff --git a/tools/testing/selftests/arm64/fp/fp-pidbench.S b/tools/testing/selftests/arm64/fp/fp-pidbench.S
index 73830f6bc99b..881dfa3b342e 100644
--- a/tools/testing/selftests/arm64/fp/fp-pidbench.S
+++ b/tools/testing/selftests/arm64/fp/fp-pidbench.S
@@ -33,7 +33,7 @@
 function _start
 	puts	"Iterations per test: "
 	mov	x20, #10000
-	lsl	x20, x20, #8
+	lsl	x20, x20, #12
 	mov	x0, x20
 	bl	putdec
 	puts	"\n"
@@ -63,6 +63,10 @@ function _start
 	puts	"SVE used per syscall: "
 	test_loop "rdvl x0, #8"
 
+	// Test non-SVE execution after SVE
+	puts	"No SVE after SVE: "
+	test_loop
+
 	//  And we're done
 out:
 	mov	x0, #0
diff --git a/tools/testing/selftests/arm64/gcs/basic-gcs.c b/tools/testing/selftests/arm64/gcs/basic-gcs.c
index 250977abc398..ae4cce6afe2b 100644
--- a/tools/testing/selftests/arm64/gcs/basic-gcs.c
+++ b/tools/testing/selftests/arm64/gcs/basic-gcs.c
@@ -22,7 +22,7 @@ static size_t page_size = 65536;
 static  __attribute__((noinline)) void valid_gcs_function(void)
 {
 	/* Do something the compiler can't optimise out */
-	my_syscall1(__NR_prctl, PR_SVE_GET_VL);
+	syscall(__NR_prctl, PR_SVE_GET_VL);
 }
 
 static inline int gcs_set_status(unsigned long mode)
@@ -36,12 +36,10 @@ static inline int gcs_set_status(unsigned long mode)
 	 * other 3 values passed in registers to the syscall are zero
 	 * since the kernel validates them.
 	 */
-	ret = my_syscall5(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, mode,
-			  0, 0, 0);
+	ret = syscall(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, mode, 0, 0, 0);
 
 	if (ret == 0) {
-		ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS,
-				  &new_mode, 0, 0, 0);
+		ret = syscall(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, &new_mode, 0, 0, 0);
 		if (ret == 0) {
 			if (new_mode != mode) {
 				ksft_print_msg("Mode set to %lx not %lx\n",
@@ -49,7 +47,7 @@ static inline int gcs_set_status(unsigned long mode)
 				ret = -EINVAL;
 			}
 		} else {
-			ksft_print_msg("Failed to validate mode: %d\n", ret);
+			ksft_print_msg("Failed to validate mode: %d\n", errno);
 		}
 
 		if (enabling != chkfeat_gcs()) {
@@ -69,10 +67,9 @@ static bool read_status(void)
 	unsigned long state;
 	int ret;
 
-	ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS,
-			  &state, 0, 0, 0);
+	ret = syscall(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, &state, 0, 0, 0);
 	if (ret != 0) {
-		ksft_print_msg("Failed to read state: %d\n", ret);
+		ksft_print_msg("Failed to read state: %d\n", errno);
 		return false;
 	}
 
@@ -188,9 +185,8 @@ static bool map_guarded_stack(void)
 	int elem;
 	bool pass = true;
 
-	buf = (void *)my_syscall3(__NR_map_shadow_stack, 0, page_size,
-				  SHADOW_STACK_SET_MARKER |
-				  SHADOW_STACK_SET_TOKEN);
+	buf = (void *)syscall(__NR_map_shadow_stack, 0, page_size,
+			      SHADOW_STACK_SET_MARKER | SHADOW_STACK_SET_TOKEN);
 	if (buf == MAP_FAILED) {
 		ksft_print_msg("Failed to map %lu byte GCS: %d\n",
 			       page_size, errno);
@@ -257,8 +253,7 @@ static bool test_fork(void)
 		valid_gcs_function();
 		get_gcspr();
 
-		ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS,
-				  &child_mode, 0, 0, 0);
+		ret = syscall(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, &child_mode, 0, 0, 0);
 		if (ret == 0 && !(child_mode & PR_SHADOW_STACK_ENABLE)) {
 			ksft_print_msg("GCS not enabled in child\n");
 			ret = -EINVAL;
@@ -321,8 +316,7 @@ static bool test_vfork(void)
 		valid_gcs_function();
 		get_gcspr();
 
-		ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS,
-				  &child_mode, 0, 0, 0);
+		ret = syscall(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, &child_mode, 0, 0, 0);
 		if (ret == 0 && !(child_mode & PR_SHADOW_STACK_ENABLE)) {
 			ksft_print_msg("GCS not enabled in child\n");
 			ret = EXIT_FAILURE;
@@ -390,17 +384,15 @@ int main(void)
 	if (!(getauxval(AT_HWCAP) & HWCAP_GCS))
 		ksft_exit_skip("SKIP GCS not supported\n");
 
-	ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS,
-			  &gcs_mode, 0, 0, 0);
+	ret = syscall(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, &gcs_mode, 0, 0, 0);
 	if (ret != 0)
-		ksft_exit_fail_msg("Failed to read GCS state: %d\n", ret);
+		ksft_exit_fail_msg("Failed to read GCS state: %d\n", errno);
 
 	if (!(gcs_mode & PR_SHADOW_STACK_ENABLE)) {
 		gcs_mode = PR_SHADOW_STACK_ENABLE;
-		ret = my_syscall5(__NR_prctl, PR_SET_SHADOW_STACK_STATUS,
-				  gcs_mode, 0, 0, 0);
+		ret = syscall(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, gcs_mode, 0, 0, 0);
 		if (ret != 0)
-			ksft_exit_fail_msg("Failed to enable GCS: %d\n", ret);
+			ksft_exit_fail_msg("Failed to enable GCS: %d\n", errno);
 	}
 
 	ksft_set_plan(ARRAY_SIZE(tests));
@@ -410,9 +402,9 @@ int main(void)
 	}
 
 	/* One last test: disable GCS, we can do this one time */
-	ret = my_syscall5(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, 0, 0, 0, 0);
+	ret = syscall(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, 0, 0, 0, 0);
 	if (ret != 0)
-		ksft_print_msg("Failed to disable GCS: %d\n", ret);
+		ksft_print_msg("Failed to disable GCS: %d\n", errno);
 
 	ksft_finished();
 
diff --git a/tools/testing/selftests/arm64/mte/.gitignore b/tools/testing/selftests/arm64/mte/.gitignore
index 052d0f9f92b3..f6937f890039 100644
--- a/tools/testing/selftests/arm64/mte/.gitignore
+++ b/tools/testing/selftests/arm64/mte/.gitignore
@@ -6,3 +6,4 @@ check_mmap_options
 check_prctl
 check_ksm_options
 check_user_mem
+check_hugetlb_options