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

Pull arm64 updates from Catalin Marinas:
 "The biggest part is the virtual CPU hotplug that touches ACPI,
  irqchip. We also have some GICv3 optimisation for pseudo-NMIs that has
  been queued via the arm64 tree. Otherwise the usual perf updates,
  kselftest, various small cleanups.

  Core:

   - Virtual CPU hotplug support for arm64 ACPI systems

   - cpufeature infrastructure cleanups and making the FEAT_ECBHB ID
     bits visible to guests

   - CPU errata: expand the speculative SSBS workaround to more CPUs

   - GICv3, use compile-time PMR values: optimise the way regular IRQs
     are masked/unmasked when GICv3 pseudo-NMIs are used, removing the
     need for a static key in fast paths by using a priority value
     chosen dynamically at boot time

  ACPI:

   - 'acpi=nospcr' option to disable SPCR as default console for arm64

   - Move some ACPI code (cpuidle, FFH) to drivers/acpi/arm64/

  Perf updates:

   - Rework of the IMX PMU driver to enable support for I.MX95

   - Enable support for tertiary match groups in the CMN PMU driver

   - Initial refactoring of the CPU PMU code to prepare for the fixed
     instruction counter introduced by Arm v9.4

   - Add missing PMU driver MODULE_DESCRIPTION() strings

   - Hook up DT compatibles for recent CPU PMUs

  Kselftest updates:

   - Kernel mode NEON fp-stress

   - Cleanups, spelling mistakes

  Miscellaneous:

   - arm64 Documentation update with a minor clarification on TBI

   - Fix missing IPI statistics

   - Implement raw_smp_processor_id() using thread_info rather than a
     per-CPU variable (better code generation)

   - Make MTE checking of in-kernel asynchronous tag faults conditional
     on KASAN being enabled

   - Minor cleanups, typos"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (69 commits)
  selftests: arm64: tags: remove the result script
  selftests: arm64: tags_test: conform test to TAP output
  perf: add missing MODULE_DESCRIPTION() macros
  arm64: smp: Fix missing IPI statistics
  irqchip/gic-v3: Fix 'broken_rdists' unused warning when !SMP and !ACPI
  ACPI: Add acpi=nospcr to disable ACPI SPCR as default console on ARM64
  Documentation: arm64: Update memory.rst for TBI
  arm64/cpufeature: Replace custom macros with fields from ID_AA64PFR0_EL1
  KVM: arm64: Replace custom macros with fields from ID_AA64PFR0_EL1
  perf: arm_pmuv3: Include asm/arm_pmuv3.h from linux/perf/arm_pmuv3.h
  perf: arm_v6/7_pmu: Drop non-DT probe support
  perf/arm: Move 32-bit PMU drivers to drivers/perf/
  perf: arm_pmuv3: Drop unnecessary IS_ENABLED(CONFIG_ARM64) check
  perf: arm_pmuv3: Avoid assigning fixed cycle counter with threshold
  arm64: Kconfig: Fix dependencies to enable ACPI_HOTPLUG_CPU
  perf: imx_perf: add support for i.MX95 platform
  perf: imx_perf: fix counter start and config sequence
  perf: imx_perf: refactor driver for imx93
  perf: imx_perf: let the driver manage the counter usage rather the user
  perf: imx_perf: add macro definitions for parsing config attr
  ...

8 files changed, 350 insertions, 27 deletions

diff --git a/tools/testing/selftests/arm64/abi/ptrace.c b/tools/testing/selftests/arm64/abi/ptrace.c
index abe4d58d731d..4c941270d8de 100644
--- a/tools/testing/selftests/arm64/abi/ptrace.c
+++ b/tools/testing/selftests/arm64/abi/ptrace.c
@@ -47,7 +47,7 @@ static void test_tpidr(pid_t child)
 
 	/* ...write a new value.. */
 	write_iov.iov_len = sizeof(uint64_t);
-	write_val[0] = read_val[0]++;
+	write_val[0] = read_val[0] + 1;
 	ret = ptrace(PTRACE_SETREGSET, child, NT_ARM_TLS, &write_iov);
 	ksft_test_result(ret == 0, "write_tpidr_one\n");
 
diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore
index 00e52c966281..8362e7ec35ad 100644
--- a/tools/testing/selftests/arm64/fp/.gitignore
+++ b/tools/testing/selftests/arm64/fp/.gitignore
@@ -2,6 +2,7 @@ fp-pidbench
 fp-ptrace
 fp-stress
 fpsimd-test
+kernel-test
 rdvl-sme
 rdvl-sve
 sve-probe-vls
diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile
index 55d4f00d9e8e..d171021e4cdd 100644
--- a/tools/testing/selftests/arm64/fp/Makefile
+++ b/tools/testing/selftests/arm64/fp/Makefile
@@ -12,6 +12,7 @@ TEST_GEN_PROGS := \
 	vec-syscfg \
 	za-fork za-ptrace
 TEST_GEN_PROGS_EXTENDED := fp-pidbench fpsimd-test \
+	kernel-test \
 	rdvl-sme rdvl-sve \
 	sve-test \
 	ssve-test \
diff --git a/tools/testing/selftests/arm64/fp/fp-stress.c b/tools/testing/selftests/arm64/fp/fp-stress.c
index dd31647b00a2..faac24bdefeb 100644
--- a/tools/testing/selftests/arm64/fp/fp-stress.c
+++ b/tools/testing/selftests/arm64/fp/fp-stress.c
@@ -319,6 +319,19 @@ static void start_fpsimd(struct child_data *child, int cpu, int copy)
 	ksft_print_msg("Started %s\n", child->name);
 }
 
+static void start_kernel(struct child_data *child, int cpu, int copy)
+{
+	int ret;
+
+	ret = asprintf(&child->name, "KERNEL-%d-%d", cpu, copy);
+	if (ret == -1)
+		ksft_exit_fail_msg("asprintf() failed\n");
+
+	child_start(child, "./kernel-test");
+
+	ksft_print_msg("Started %s\n", child->name);
+}
+
 static void start_sve(struct child_data *child, int vl, int cpu)
 {
 	int ret;
@@ -438,7 +451,7 @@ int main(int argc, char **argv)
 	int ret;
 	int timeout = 10;
 	int cpus, i, j, c;
-	int sve_vl_count, sme_vl_count, fpsimd_per_cpu;
+	int sve_vl_count, sme_vl_count;
 	bool all_children_started = false;
 	int seen_children;
 	int sve_vls[MAX_VLS], sme_vls[MAX_VLS];
@@ -482,12 +495,7 @@ int main(int argc, char **argv)
 		have_sme2 = false;
 	}
 
-	/* Force context switching if we only have FPSIMD */
-	if (!sve_vl_count && !sme_vl_count)
-		fpsimd_per_cpu = 2;
-	else
-		fpsimd_per_cpu = 1;
-	tests += cpus * fpsimd_per_cpu;
+	tests += cpus * 2;
 
 	ksft_print_header();
 	ksft_set_plan(tests);
@@ -542,8 +550,8 @@ int main(int argc, char **argv)
 				   tests);
 
 	for (i = 0; i < cpus; i++) {
-		for (j = 0; j < fpsimd_per_cpu; j++)
-			start_fpsimd(&children[num_children++], i, j);
+		start_fpsimd(&children[num_children++], i, 0);
+		start_kernel(&children[num_children++], i, 0);
 
 		for (j = 0; j < sve_vl_count; j++)
 			start_sve(&children[num_children++], sve_vls[j], i);
diff --git a/tools/testing/selftests/arm64/fp/kernel-test.c b/tools/testing/selftests/arm64/fp/kernel-test.c
new file mode 100644
index 000000000000..e8da3b4cbd23
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/kernel-test.c
@@ -0,0 +1,324 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024 ARM Limited.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <signal.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <sys/socket.h>
+
+#include <linux/kernel.h>
+#include <linux/if_alg.h>
+
+#define DATA_SIZE (16 * 4096)
+
+static int base, sock;
+
+static int digest_len;
+static char *ref;
+static char *digest;
+static char *alg_name;
+
+static struct iovec data_iov;
+static int zerocopy[2];
+static int sigs;
+static int iter;
+
+static void handle_exit_signal(int sig, siginfo_t *info, void *context)
+{
+	printf("Terminated by signal %d, iterations=%d, signals=%d\n",
+	       sig, iter, sigs);
+	exit(0);
+}
+
+static void handle_kick_signal(int sig, siginfo_t *info, void *context)
+{
+	sigs++;
+}
+
+static char *drivers[] = {
+	"crct10dif-arm64-ce",
+	/* "crct10dif-arm64-neon", - Same priority as generic */
+	"sha1-ce",
+	"sha224-arm64",
+	"sha224-arm64-neon",
+	"sha224-ce",
+	"sha256-arm64",
+	"sha256-arm64-neon",
+	"sha256-ce",
+	"sha384-ce",
+	"sha512-ce",
+	"sha3-224-ce",
+	"sha3-256-ce",
+	"sha3-384-ce",
+	"sha3-512-ce",
+	"sm3-ce",
+	"sm3-neon",
+};
+
+static bool create_socket(void)
+{
+	FILE *proc;
+	struct sockaddr_alg addr;
+	char buf[1024];
+	char *c, *driver_name;
+	bool is_shash, match;
+	int ret, i;
+
+	ret = socket(AF_ALG, SOCK_SEQPACKET, 0);
+	if (ret < 0) {
+		if (errno == EAFNOSUPPORT) {
+			printf("AF_ALG not supported\n");
+			return false;
+		}
+
+		printf("Failed to create AF_ALG socket: %s (%d)\n",
+		       strerror(errno), errno);
+		return false;
+	}
+	base = ret;
+
+	memset(&addr, 0, sizeof(addr));
+	addr.salg_family = AF_ALG;
+	strncpy((char *)addr.salg_type, "hash", sizeof(addr.salg_type));
+
+	proc = fopen("/proc/crypto", "r");
+	if (!proc) {
+		printf("Unable to open /proc/crypto\n");
+		return false;
+	}
+
+	driver_name = NULL;
+	is_shash = false;
+	match = false;
+
+	/* Look through /proc/crypto for a driver with kernel mode FP usage */
+	while (!match) {
+		c = fgets(buf, sizeof(buf), proc);
+		if (!c) {
+			if (feof(proc)) {
+				printf("Nothing found in /proc/crypto\n");
+				return false;
+			}
+			continue;
+		}
+
+		/* Algorithm descriptions are separated by a blank line */
+		if (*c == '\n') {
+			if (is_shash && driver_name) {
+				for (i = 0; i < ARRAY_SIZE(drivers); i++) {
+					if (strcmp(drivers[i],
+						   driver_name) == 0) {
+						match = true;
+					}
+				}
+			}
+
+			if (!match) {
+				digest_len = 0;
+
+				free(driver_name);
+				driver_name = NULL;
+
+				free(alg_name);
+				alg_name = NULL;
+
+				is_shash = false;
+			}
+			continue;
+		}
+
+		/* Remove trailing newline */
+		c = strchr(buf, '\n');
+		if (c)
+			*c = '\0';
+
+		/* Find the field/value separator and start of the value */
+		c = strchr(buf, ':');
+		if (!c)
+			continue;
+		c += 2;
+
+		if (strncmp(buf, "digestsize", strlen("digestsize")) == 0)
+			sscanf(c, "%d", &digest_len);
+
+		if (strncmp(buf, "name", strlen("name")) == 0)
+			alg_name = strdup(c);
+
+		if (strncmp(buf, "driver", strlen("driver")) == 0)
+			driver_name = strdup(c);
+
+		if (strncmp(buf, "type", strlen("type")) == 0)
+			if (strncmp(c, "shash", strlen("shash")) == 0)
+				is_shash = true;
+	}
+
+	strncpy((char *)addr.salg_name, alg_name,
+		sizeof(addr.salg_name) - 1);
+
+	ret = bind(base, (struct sockaddr *)&addr, sizeof(addr));
+	if (ret < 0) {
+		printf("Failed to bind %s: %s (%d)\n",
+		       addr.salg_name, strerror(errno), errno);
+		return false;
+	}
+
+	ret = accept(base, NULL, 0);
+	if (ret < 0) {
+		printf("Failed to accept %s: %s (%d)\n",
+		       addr.salg_name, strerror(errno), errno);
+		return false;
+	}
+
+	sock = ret;
+
+	ret = pipe(zerocopy);
+	if (ret != 0) {
+		printf("Failed to create zerocopy pipe: %s (%d)\n",
+		       strerror(errno), errno);
+		return false;
+	}
+
+	ref = malloc(digest_len);
+	if (!ref) {
+		printf("Failed to allocated %d byte reference\n", digest_len);
+		return false;
+	}
+
+	digest = malloc(digest_len);
+	if (!digest) {
+		printf("Failed to allocated %d byte digest\n", digest_len);
+		return false;
+	}
+
+	return true;
+}
+
+static bool compute_digest(void *buf)
+{
+	struct iovec iov;
+	int ret, wrote;
+
+	iov = data_iov;
+	while (iov.iov_len) {
+		ret = vmsplice(zerocopy[1], &iov, 1, SPLICE_F_GIFT);
+		if (ret < 0) {
+			printf("Failed to send buffer: %s (%d)\n",
+			       strerror(errno), errno);
+			return false;
+		}
+
+		wrote = ret;
+		ret = splice(zerocopy[0], NULL, sock, NULL, wrote, 0);
+		if (ret < 0) {
+			printf("Failed to splice buffer: %s (%d)\n",
+			       strerror(errno), errno);
+		} else if (ret != wrote) {
+			printf("Short splice: %d < %d\n", ret, wrote);
+		}
+
+		iov.iov_len -= wrote;
+		iov.iov_base += wrote;
+	}
+
+reread:
+	ret = recv(sock, buf, digest_len, 0);
+	if (ret == 0) {
+		printf("No digest returned\n");
+		return false;
+	}
+	if (ret != digest_len) {
+		if (errno == -EAGAIN)
+			goto reread;
+		printf("Failed to get digest: %s (%d)\n",
+		       strerror(errno), errno);
+		return false;
+	}
+
+	return true;
+}
+
+int main(void)
+{
+	char *data;
+	struct sigaction sa;
+	int ret;
+
+	/* Ensure we have unbuffered output */
+	setvbuf(stdout, NULL, _IOLBF, 0);
+
+	/* The parent will communicate with us via signals */
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handle_exit_signal;
+	sa.sa_flags = SA_RESTART | SA_SIGINFO;
+	sigemptyset(&sa.sa_mask);
+	ret = sigaction(SIGTERM, &sa, NULL);
+	if (ret < 0)
+		printf("Failed to install SIGTERM handler: %s (%d)\n",
+		       strerror(errno), errno);
+
+	sa.sa_sigaction = handle_kick_signal;
+	ret = sigaction(SIGUSR2, &sa, NULL);
+	if (ret < 0)
+		printf("Failed to install SIGUSR2 handler: %s (%d)\n",
+		       strerror(errno), errno);
+
+	data = malloc(DATA_SIZE);
+	if (!data) {
+		printf("Failed to allocate data buffer\n");
+		return EXIT_FAILURE;
+	}
+	memset(data, 0, DATA_SIZE);
+
+	data_iov.iov_base = data;
+	data_iov.iov_len = DATA_SIZE;
+
+	/*
+	 * If we can't create a socket assume it's a lack of system
+	 * support and fall back to a basic FPSIMD test for the
+	 * benefit of fp-stress.
+	 */
+	if (!create_socket()) {
+		execl("./fpsimd-test", "./fpsimd-test", NULL);
+		printf("Failed to fall back to fspimd-test: %d (%s)\n",
+			errno, strerror(errno));
+		return EXIT_FAILURE;
+	}
+
+	/*
+	 * Compute a reference digest we hope is repeatable, we do
+	 * this at runtime partly to make it easier to play with
+	 * parameters.
+	 */
+	if (!compute_digest(ref)) {
+		printf("Failed to compute reference digest\n");
+		return EXIT_FAILURE;
+	}
+
+	printf("AF_ALG using %s\n", alg_name);
+
+	while (true) {
+		if (!compute_digest(digest)) {
+			printf("Failed to compute digest, iter=%d\n", iter);
+			return EXIT_FAILURE;
+		}
+
+		if (memcmp(ref, digest, digest_len) != 0) {
+			printf("Digest mismatch, iter=%d\n", iter);
+			return EXIT_FAILURE;
+		}
+
+		iter++;
+	}
+
+	return EXIT_FAILURE;
+}
diff --git a/tools/testing/selftests/arm64/tags/Makefile b/tools/testing/selftests/arm64/tags/Makefile
index 6d29cfde43a2..0a77f35295fb 100644
--- a/tools/testing/selftests/arm64/tags/Makefile
+++ b/tools/testing/selftests/arm64/tags/Makefile
@@ -2,6 +2,5 @@
 
 CFLAGS += $(KHDR_INCLUDES)
 TEST_GEN_PROGS := tags_test
-TEST_PROGS := run_tags_test.sh
 
 include ../../lib.mk
diff --git a/tools/testing/selftests/arm64/tags/run_tags_test.sh b/tools/testing/selftests/arm64/tags/run_tags_test.sh
deleted file mode 100755
index 745f11379930..000000000000
--- a/tools/testing/selftests/arm64/tags/run_tags_test.sh
+++ /dev/null
@@ -1,12 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-
-echo "--------------------"
-echo "running tags test"
-echo "--------------------"
-./tags_test
-if [ $? -ne 0 ]; then
-	echo "[FAIL]"
-else
-	echo "[PASS]"
-fi
diff --git a/tools/testing/selftests/arm64/tags/tags_test.c b/tools/testing/selftests/arm64/tags/tags_test.c
index 955f87c1170d..8ae26e496c89 100644
--- a/tools/testing/selftests/arm64/tags/tags_test.c
+++ b/tools/testing/selftests/arm64/tags/tags_test.c
@@ -17,19 +17,21 @@ int main(void)
 	static int tbi_enabled = 0;
 	unsigned long tag = 0;
 	struct utsname *ptr;
-	int err;
+
+	ksft_print_header();
+	ksft_set_plan(1);
 
 	if (prctl(PR_SET_TAGGED_ADDR_CTRL, PR_TAGGED_ADDR_ENABLE, 0, 0, 0) == 0)
 		tbi_enabled = 1;
 	ptr = (struct utsname *)malloc(sizeof(*ptr));
 	if (!ptr)
-		ksft_exit_fail_msg("Failed to allocate utsname buffer\n");
+		ksft_exit_fail_perror("Failed to allocate utsname buffer");
 
 	if (tbi_enabled)
 		tag = 0x42;
 	ptr = (struct utsname *)SET_TAG(ptr, tag);
-	err = uname(ptr);
+	ksft_test_result(!uname(ptr), "Syscall successful with tagged address\n");
 	free(ptr);
 
-	return err;
+	ksft_finished();
 }