1 files changed, 305 insertions, 73 deletions

diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 1e54e2c86360..c0e2b9d5f0b2 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -1,10 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "cpumap.h"
+#include "dwarf-regs.h"
 #include "debug.h"
 #include "env.h"
 #include "util/header.h"
 #include "util/rwsem.h"
 #include <linux/compiler.h>
+#include <linux/kernel.h>
 #include <linux/ctype.h>
 #include <linux/rbtree.h>
 #include <linux/string.h>
@@ -248,6 +250,8 @@ void perf_env__exit(struct perf_env *env)
 {
 	int i, j;
 
+	mutex_destroy(&env->lock);
+
 	perf_env__purge_bpf(env);
 	perf_env__purge_cgroups(env);
 	zfree(&env->hostname);
@@ -305,19 +309,32 @@ void perf_env__init(struct perf_env *env)
 	init_rwsem(&env->bpf_progs.lock);
 #endif
 	env->kernel_is_64_bit = -1;
+	mutex_init(&env->lock);
 }
 
 static void perf_env__init_kernel_mode(struct perf_env *env)
 {
-	const char *arch = perf_env__raw_arch(env);
+	const char *arch = env->arch;
+
+	if (!arch) {
+		static struct utsname uts = { .machine[0] = '\0', };
 
-	if (!strncmp(arch, "x86_64", 6) || !strncmp(arch, "aarch64", 7) ||
-	    !strncmp(arch, "arm64", 5) || !strncmp(arch, "mips64", 6) ||
-	    !strncmp(arch, "parisc64", 8) || !strncmp(arch, "riscv64", 7) ||
-	    !strncmp(arch, "s390x", 5) || !strncmp(arch, "sparc64", 7))
-		env->kernel_is_64_bit = 1;
-	else
-		env->kernel_is_64_bit = 0;
+		if (uts.machine[0] == '\0')
+			uname(&uts);
+		if (uts.machine[0] != '\0')
+			arch = uts.machine;
+	}
+
+	if (arch) {
+		if (strstr(arch, "64") || strstr(arch, "s390x"))
+			env->kernel_is_64_bit = 1;
+		else
+			env->kernel_is_64_bit = 0;
+		return;
+	}
+
+	/* Fallback if completely unresolvable (assume host-bitness) */
+	env->kernel_is_64_bit = (sizeof(void *) == 8) ? 1 : 0;
 }
 
 int perf_env__kernel_is_64_bit(struct perf_env *env)
@@ -328,6 +345,60 @@ int perf_env__kernel_is_64_bit(struct perf_env *env)
 	return env->kernel_is_64_bit;
 }
 
+bool perf_arch_is_big_endian(const char *arch)
+{
+	if (!arch)
+		return __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__;
+
+	if (str_ends_with(arch, "_be") || !strcmp(arch, "sparc") || !strcmp(arch, "sparc64") ||
+	    !strcmp(arch, "s390") || !strcmp(arch, "s390x") || !strcmp(arch, "powerpc") ||
+	    !strcmp(arch, "ppc") || !strcmp(arch, "ppc64") ||
+	    !strcmp(arch, "mips") || !strcmp(arch, "mips64") || !strcmp(arch, "parisc") ||
+	    !strcmp(arch, "parisc64") || !strcmp(arch, "m68k") ||
+	    !strcmp(arch, "armeb") || !strcmp(arch, "mipseb") || !strcmp(arch, "mips64eb"))
+		return true;
+
+	return false;
+}
+
+const char *perf_env__os_release(struct perf_env *env)
+{
+	struct utsname uts;
+	int ret;
+	const char *release;
+
+	if (!env)
+		return perf_version_string;
+
+	mutex_lock(&env->lock);
+	if (env->os_release) {
+		release = env->os_release;
+		goto out;
+	}
+
+	/*
+	 * If env->arch is set, this is an offline target environment.
+	 * If the os_release is not populated in the file, we do not want
+	 * to poison it with the host's release which would break guest checks.
+	 */
+	if (env->arch) {
+		release = NULL;
+		goto out;
+	}
+
+	/*
+	 * The os_release is being accessed but wasn't initialized from a data
+	 * file, assume this is 'live' mode and use the release from uname. If
+	 * uname or strdup fails then use the current perf tool version.
+	 */
+	ret = uname(&uts);
+	env->os_release = strdup(ret < 0 ? perf_version_string : uts.release);
+	release = env->os_release ?: perf_version_string;
+out:
+	mutex_unlock(&env->lock);
+	return release;
+}
+
 int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
 {
 	int i;
@@ -440,19 +511,6 @@ int perf_env__read_cpuid(struct perf_env *env)
 	return 0;
 }
 
-static int perf_env__read_arch(struct perf_env *env)
-{
-	struct utsname uts;
-
-	if (env->arch)
-		return 0;
-
-	if (!uname(&uts))
-		env->arch = strdup(uts.machine);
-
-	return env->arch ? 0 : -ENOMEM;
-}
-
 static int perf_env__read_nr_cpus_avail(struct perf_env *env)
 {
 	if (env->nr_cpus_avail == 0)
@@ -571,11 +629,6 @@ error:
 	return ret;
 }
 
-const char *perf_env__raw_arch(struct perf_env *env)
-{
-	return env && !perf_env__read_arch(env) ? env->arch : "unknown";
-}
-
 int perf_env__nr_cpus_avail(struct perf_env *env)
 {
 	return env && !perf_env__read_nr_cpus_avail(env) ? env->nr_cpus_avail : 0;
@@ -588,67 +641,244 @@ void cpu_cache_level__free(struct cpu_cache_level *cache)
 	zfree(&cache->size);
 }
 
+struct arch_to_e_machine {
+	const char *prefix;
+	uint16_t e_machine;
+};
+
 /*
- * Return architecture name in a normalized form.
- * The conversion logic comes from the Makefile.
+ * A mapping from an arch prefix string to an ELF machine that can be used in a
+ * bsearch. Some arch prefixes are shared an need additional processing as
+ * marked next to the architecture. The prefixes handle both perf's architecture
+ * naming and those from uname.
  */
-static const char *normalize_arch(char *arch)
-{
-	if (!strcmp(arch, "x86_64"))
-		return "x86";
-	if (arch[0] == 'i' && arch[2] == '8' && arch[3] == '6')
-		return "x86";
-	if (!strcmp(arch, "sun4u") || !strncmp(arch, "sparc", 5))
-		return "sparc";
-	if (!strncmp(arch, "aarch64", 7) || !strncmp(arch, "arm64", 5))
-		return "arm64";
-	if (!strncmp(arch, "arm", 3) || !strcmp(arch, "sa110"))
-		return "arm";
-	if (!strncmp(arch, "s390", 4))
-		return "s390";
-	if (!strncmp(arch, "parisc", 6))
-		return "parisc";
-	if (!strncmp(arch, "powerpc", 7) || !strncmp(arch, "ppc", 3))
-		return "powerpc";
-	if (!strncmp(arch, "mips", 4))
-		return "mips";
-	if (!strncmp(arch, "sh", 2) && isdigit(arch[2]))
-		return "sh";
-	if (!strncmp(arch, "loongarch", 9))
-		return "loongarch";
+static const struct arch_to_e_machine prefix_to_e_machine[] = {
+	{"aarch64", EM_AARCH64},
+	{"alpha", EM_ALPHA},
+	{"arc", EM_ARC},
+	{"arm", EM_ARM}, /* Check also for EM_AARCH64. */
+	{"avr", EM_AVR},  /* Check also for EM_AVR32. */
+	{"bfin", EM_BLACKFIN},
+	{"blackfin", EM_BLACKFIN},
+	{"cris", EM_CRIS},
+	{"csky", EM_CSKY},
+	{"hppa", EM_PARISC},
+	{"i386", EM_386},
+	{"i486", EM_386},
+	{"i586", EM_386},
+	{"i686", EM_386},
+	{"loongarch", EM_LOONGARCH},
+	{"m32r", EM_M32R},
+	{"m68k", EM_68K},
+	{"microblaze", EM_MICROBLAZE},
+	{"mips", EM_MIPS},
+	{"msp430", EM_MSP430},
+	{"parisc", EM_PARISC},
+	{"powerpc", EM_PPC}, /* Check also for EM_PPC64. */
+	{"ppc", EM_PPC}, /* Check also for EM_PPC64. */
+	{"riscv", EM_RISCV},
+	{"s390", EM_S390},
+	{"sa110", EM_ARM},
+	{"sh", EM_SH},
+	{"sparc", EM_SPARC}, /* Check also for EM_SPARCV9. */
+	{"sun4u", EM_SPARC},
+	{"x86", EM_X86_64}, /* Check also for EM_386. */
+	{"xtensa", EM_XTENSA},
+};
+
+static int compare_prefix(const void *key, const void *element)
+{
+	const char *search_key = key;
+	const struct arch_to_e_machine *map_element = element;
+	size_t prefix_len = strlen(map_element->prefix);
 
-	return arch;
+	return strncmp(search_key, map_element->prefix, prefix_len);
 }
 
-const char *perf_env__arch(struct perf_env *env)
+static uint16_t perf_arch_to_e_machine(const char *perf_arch, int is_64_bit)
+{
+	/* Binary search for a matching prefix. */
+	const struct arch_to_e_machine *result;
+
+	if (!perf_arch)
+		return EM_HOST;
+
+	result = bsearch(perf_arch,
+			 prefix_to_e_machine, ARRAY_SIZE(prefix_to_e_machine),
+			 sizeof(prefix_to_e_machine[0]),
+			 compare_prefix);
+
+	if (!result) {
+		pr_debug("Unknown perf arch for ELF machine mapping: %s\n", perf_arch);
+		return EM_NONE;
+	}
+
+	/*
+	 * Handle conflicting prefixes. If the is_64_bit is unknown (-1) then
+	 * assume 64-bit. We can't use perf_env__kernel_is_64_bit as that
+	 * depends on the arch string.
+	 */
+	switch (result->e_machine) {
+	case EM_ARM:
+		return !strcmp(perf_arch, "arm64") || !strcmp(perf_arch, "aarch64")
+			? EM_AARCH64 : EM_ARM;
+	case EM_AVR:
+		return !strcmp(perf_arch, "avr32") ? EM_AVR32 : EM_AVR;
+	case EM_PPC:
+		if (is_64_bit == 1)
+			return EM_PPC64;
+		if (is_64_bit == 0)
+			return EM_PPC;
+		return strstarts(perf_arch, "ppc64") ? EM_PPC64 : EM_PPC;
+	case EM_SPARC:
+		if (is_64_bit == 1)
+			return EM_SPARCV9;
+		if (is_64_bit == 0)
+			return EM_SPARC;
+		return !strcmp(perf_arch, "sparc64") || !strcmp(perf_arch, "sun4u")
+			? EM_SPARCV9 : EM_SPARC;
+	case EM_X86_64:
+		if (is_64_bit == 1)
+			return EM_X86_64;
+		if (is_64_bit == 0)
+			return EM_386;
+		return !strcmp(perf_arch, "x86_64") || !strcmp(perf_arch, "x86")
+			? EM_X86_64 : EM_386;
+	default:
+		return result->e_machine;
+	}
+}
+
+static const char *e_machine_to_perf_arch(uint16_t e_machine)
+{
+	/*
+	 * Table for if either the perf arch string differs from uname or there
+	 * are >1 ELF machine with the prefix.
+	 */
+	static const struct arch_to_e_machine extras[] = {
+		{"arm64", EM_AARCH64},
+		{"avr32", EM_AVR32},
+		{"powerpc", EM_PPC},
+		{"powerpc", EM_PPC64},
+		{"sparc", EM_SPARCV9},
+		{"x86", EM_386},
+		{"x86", EM_X86_64},
+		{"none", EM_NONE},
+	};
+
+	for (size_t i = 0; i < ARRAY_SIZE(extras); i++) {
+		if (extras[i].e_machine == e_machine)
+			return extras[i].prefix;
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(prefix_to_e_machine); i++) {
+		if (prefix_to_e_machine[i].e_machine == e_machine)
+			return prefix_to_e_machine[i].prefix;
+
+	}
+	return "unknown";
+}
+
+uint16_t perf_env__e_machine_nocache(struct perf_env *env, uint32_t *e_flags)
 {
-	char *arch_name;
+	uint16_t e_machine = EM_NONE;
+	const char *arch = NULL;
+	int is_64_bit = -1;
+
+	if (e_flags)
+		*e_flags = 0;
+
+	if (env) {
+		arch = env->arch;
+		is_64_bit = env->kernel_is_64_bit;
+	}
 
-	if (!env || !env->arch) { /* Assume local operation */
+	if (!arch) {
 		static struct utsname uts = { .machine[0] = '\0', };
-		if (uts.machine[0] == '\0' && uname(&uts) < 0)
-			return NULL;
-		arch_name = uts.machine;
-	} else
-		arch_name = env->arch;
 
-	return normalize_arch(arch_name);
+		if (uts.machine[0] == '\0')
+			uname(&uts);
+		if (uts.machine[0] != '\0')
+			arch = uts.machine;
+	}
+
+	e_machine = perf_arch_to_e_machine(arch, is_64_bit);
+
+	if (e_flags)
+		*e_flags = (e_machine == EM_HOST) ? EF_HOST : 0;
+
+	return e_machine;
 }
 
-#if defined(HAVE_LIBTRACEEVENT)
-#include "trace/beauty/arch_errno_names.c"
-#endif
+uint16_t perf_env__e_machine(struct perf_env *env, uint32_t *e_flags)
+{
+	uint16_t e_machine;
+	uint32_t local_e_flags = 0;
+
+	if (env && env->e_machine != EM_NONE) {
+		if (e_flags)
+			*e_flags = env->e_flags;
+
+		return env->e_machine;
+	}
+	e_machine = perf_env__e_machine_nocache(env, &local_e_flags);
+	/*
+	 * Only cache the e_machine in perf_env if env->arch is not NULL.
+	 * If env->arch is NULL, the e_machine is just a fallback to EM_HOST.
+	 * Caching it permanently would prevent dynamic, more accurate
+	 * thread-based session e_machine scanning later in
+	 * perf_session__e_machine().
+	 */
+	if (env && env->arch) {
+		env->e_machine = e_machine;
+		env->e_flags = local_e_flags;
+	}
+	if (e_flags)
+		*e_flags = local_e_flags;
 
-const char *perf_env__arch_strerrno(struct perf_env *env __maybe_unused, int err __maybe_unused)
+	return e_machine;
+}
+
+const char *perf_env__arch(struct perf_env *env)
 {
-#if defined(HAVE_LIBTRACEEVENT)
-	if (env->arch_strerrno == NULL)
-		env->arch_strerrno = arch_syscalls__strerrno_function(perf_env__arch(env));
+	uint16_t e_machine;
+	const char *arch;
 
-	return env->arch_strerrno ? env->arch_strerrno(err) : "no arch specific strerrno function";
-#else
-	return "!HAVE_LIBTRACEEVENT";
-#endif
+	if (!env) {
+		static struct utsname uts = { .machine[0] = '\0', };
+		uint16_t host_e_machine;
+
+		if (uts.machine[0] == '\0')
+			uname(&uts);
+		if (uts.machine[0] != '\0') {
+			host_e_machine = perf_arch_to_e_machine(uts.machine, -1);
+			return e_machine_to_perf_arch(host_e_machine);
+		}
+		return e_machine_to_perf_arch(EM_HOST);
+	}
+
+	/*
+	 * Lazily compute/allocate arch. The e_machine may have been
+	 * read from a data file and so may not be EM_HOST.
+	 */
+	e_machine = perf_env__e_machine(env, /*e_flags=*/NULL);
+	arch = e_machine_to_perf_arch(e_machine);
+
+	if (e_machine == EM_RISCV && perf_env__kernel_is_64_bit(env) == 1)
+		arch = "riscv64";
+	else if (e_machine == EM_MIPS && perf_env__kernel_is_64_bit(env) == 1)
+		arch = "mips64";
+	else if (e_machine == EM_PARISC && perf_env__kernel_is_64_bit(env) == 1)
+		arch = "parisc64";
+
+	return arch;
+}
+
+const char *arch_syscalls__strerrno(uint16_t e_machine, int err);
+
+const char *perf_env__arch_strerrno(uint16_t e_machine, int err)
+{
+	return arch_syscalls__strerrno(e_machine, err);
 }
 
 const char *perf_env__cpuid(struct perf_env *env)
@@ -825,6 +1055,7 @@ bool x86__is_amd_cpu(void)
 	struct perf_env env = { .total_mem = 0, };
 	bool is_amd;
 
+	perf_env__init(&env);
 	perf_env__cpuid(&env);
 	is_amd = perf_env__is_x86_amd_cpu(&env);
 	perf_env__exit(&env);
@@ -847,6 +1078,7 @@ bool x86__is_intel_cpu(void)
 	struct perf_env env = { .total_mem = 0, };
 	bool is_intel;
 
+	perf_env__init(&env);
 	perf_env__cpuid(&env);
 	is_intel = perf_env__is_x86_intel_cpu(&env);
 	perf_env__exit(&env);