perf thread: Add support for reading the e_machine type for a thread

First try to read the e_machine from the dsos associated with the
thread's maps. If live use the executable from /proc/pid/exe and read
the e_machine from the ELF header. On failure use EM_HOST. Change
builtin-trace syscall functions to pass e_machine from the thread
rather than EM_HOST, so that in later patches when syscalltbl can use
the e_machine the system calls are specific to the architecture.

Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Link: https://lore.kernel.org/r/20250319050741.269828-8-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

Author: captain5050

tools/perf/builtin-trace.c

@@ -2731,16 +2731,16 @@ static int trace__sys_enter(struct trace *trace, struct evsel *evsel,
 	int printed = 0;
 	struct thread *thread;
 	int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
-	int augmented_args_size = 0;
+	int augmented_args_size = 0, e_machine;
 	void *augmented_args = NULL;
-	/* TODO: get e_machine from thread. */
-	struct syscall *sc = trace__syscall_info(trace, evsel, EM_HOST, id);
+	struct syscall *sc;
 	struct thread_trace *ttrace;
 
-	if (sc == NULL)
-		return -1;
-
 	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+	e_machine = thread__e_machine(thread, trace->host);
+	sc = trace__syscall_info(trace, evsel, e_machine, id);
+	if (sc == NULL)
+		goto out_put;
 	ttrace = thread__trace(thread, trace);
 	if (ttrace == NULL)
 		goto out_put;
@@ -2808,17 +2808,18 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct evsel *evsel,
 	struct thread_trace *ttrace;
 	struct thread *thread;
 	int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
-	/* TODO: get e_machine from thread. */
-	struct syscall *sc = trace__syscall_info(trace, evsel, EM_HOST, id);
+	struct syscall *sc;
 	char msg[1024];
 	void *args, *augmented_args = NULL;
-	int augmented_args_size;
+	int augmented_args_size, e_machine;
 	size_t printed = 0;
 
-	if (sc == NULL)
-		return -1;
 
 	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+	e_machine = thread__e_machine(thread, trace->host);
+	sc = trace__syscall_info(trace, evsel, e_machine, id);
+	if (sc == NULL)
+		return -1;
 	ttrace = thread__trace(thread, trace);
 	/*
 	 * We need to get ttrace just to make sure it is there when syscall__scnprintf_args()
@@ -2883,15 +2884,15 @@ static int trace__sys_exit(struct trace *trace, struct evsel *evsel,
 	bool duration_calculated = false;
 	struct thread *thread;
 	int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1, callchain_ret = 0, printed = 0;
-	int alignment = trace->args_alignment;
-	/* TODO: get e_machine from thread. */
-	struct syscall *sc = trace__syscall_info(trace, evsel, EM_HOST, id);
+	int alignment = trace->args_alignment, e_machine;
+	struct syscall *sc;
 	struct thread_trace *ttrace;
 
-	if (sc == NULL)
-		return -1;
-
 	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+	e_machine = thread__e_machine(thread, trace->host);
+	sc = trace__syscall_info(trace, evsel, e_machine, id);
+	if (sc == NULL)
+		goto out_put;
 	ttrace = thread__trace(thread, trace);
 	if (ttrace == NULL)
 		goto out_put;
@@ -3238,8 +3239,8 @@ static int trace__event_handler(struct trace *trace, struct evsel *evsel,
 
 	if (evsel == trace->syscalls.events.bpf_output) {
 		int id = perf_evsel__sc_tp_uint(evsel, id, sample);
-		/* TODO: get e_machine from thread. */
-		struct syscall *sc = trace__syscall_info(trace, evsel, EM_HOST, id);
+		int e_machine = thread ? thread__e_machine(thread, trace->host) : EM_HOST;
+		struct syscall *sc = trace__syscall_info(trace, evsel, e_machine, id);
 
 		if (sc) {
 			fprintf(trace->output, "%s(", sc->name);
@@ -4889,6 +4890,7 @@ static size_t trace__fprintf_thread(FILE *fp, struct thread *thread, struct trac
 {
 	size_t printed = 0;
 	struct thread_trace *ttrace = thread__priv(thread);
+	int e_machine = thread__e_machine(thread, trace->host);
 	double ratio;
 
 	if (ttrace == NULL)
@@ -4908,8 +4910,7 @@ static size_t trace__fprintf_thread(FILE *fp, struct thread *thread, struct trac
 	else if (fputc('\n', fp) != EOF)
 		++printed;
 
-	/* TODO: get e_machine from thread. */
-	printed += thread__dump_stats(ttrace, trace, EM_HOST, fp);
+	printed += thread__dump_stats(ttrace, trace, e_machine, fp);
 
 	return printed;
 }

tools/perf/util/thread.c

@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <elf.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
@@ -16,6 +18,7 @@
 #include "symbol.h"
 #include "unwind.h"
 #include "callchain.h"
+#include "dwarf-regs.h"
 
 #include <api/fs/fs.h>
 
@@ -51,6 +54,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 		thread__set_ppid(thread, -1);
 		thread__set_cpu(thread, -1);
 		thread__set_guest_cpu(thread, -1);
+		thread__set_e_machine(thread, EM_NONE);
 		thread__set_lbr_stitch_enable(thread, false);
 		INIT_LIST_HEAD(thread__namespaces_list(thread));
 		INIT_LIST_HEAD(thread__comm_list(thread));
@@ -423,6 +427,82 @@ void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
 	}
 }
 
+static uint16_t read_proc_e_machine_for_pid(pid_t pid)
+{
+	char path[6 /* "/proc/" */ + 11 /* max length of pid */ + 5 /* "/exe\0" */];
+	int fd;
+	uint16_t e_machine = EM_NONE;
+
+	snprintf(path, sizeof(path), "/proc/%d/exe", pid);
+	fd = open(path, O_RDONLY);
+	if (fd >= 0) {
+		_Static_assert(offsetof(Elf32_Ehdr, e_machine) == 18, "Unexpected offset");
+		_Static_assert(offsetof(Elf64_Ehdr, e_machine) == 18, "Unexpected offset");
+		if (pread(fd, &e_machine, sizeof(e_machine), 18) != sizeof(e_machine))
+			e_machine = EM_NONE;
+		close(fd);
+	}
+	return e_machine;
+}
+
+static int thread__e_machine_callback(struct map *map, void *machine)
+{
+	struct dso *dso = map__dso(map);
+
+	_Static_assert(0 == EM_NONE, "Unexpected EM_NONE");
+	if (!dso)
+		return EM_NONE;
+
+	return dso__e_machine(dso, machine);
+}
+
+uint16_t thread__e_machine(struct thread *thread, struct machine *machine)
+{
+	pid_t tid, pid;
+	uint16_t e_machine = RC_CHK_ACCESS(thread)->e_machine;
+
+	if (e_machine != EM_NONE)
+		return e_machine;
+
+	tid = thread__tid(thread);
+	pid = thread__pid(thread);
+	if (pid != tid) {
+		struct thread *parent = machine__findnew_thread(machine, pid, pid);
+
+		if (parent) {
+			e_machine = thread__e_machine(parent, machine);
+			thread__set_e_machine(thread, e_machine);
+			return e_machine;
+		}
+		/* Something went wrong, fallback. */
+	}
+	/* Reading on the PID thread. First try to find from the maps. */
+	e_machine = maps__for_each_map(thread__maps(thread),
+				       thread__e_machine_callback,
+				       machine);
+	if (e_machine == EM_NONE) {
+		/* Maps failed, perhaps we're live with map events disabled. */
+		bool is_live = machine->machines == NULL;
+
+		if (!is_live) {
+			/* Check if the session has a data file. */
+			struct perf_session *session = container_of(machine->machines,
+								    struct perf_session,
+								    machines);
+
+			is_live = !!session->data;
+		}
+		/* Read from /proc/pid/exe if live. */
+		if (is_live)
+			e_machine = read_proc_e_machine_for_pid(pid);
+	}
+	if (e_machine != EM_NONE)
+		thread__set_e_machine(thread, e_machine);
+	else
+		e_machine = EM_HOST;
+	return e_machine;
+}
+
 struct thread *thread__main_thread(struct machine *machine, struct thread *thread)
 {
 	if (thread__pid(thread) == thread__tid(thread))

tools/perf/util/thread.h

@@ -60,7 +60,11 @@ DECLARE_RC_STRUCT(thread) {
 	struct srccode_state	srccode_state;
 	bool			filter;
 	int			filter_entry_depth;
-
+	/**
+	 * @e_machine: The ELF EM_* associated with the thread. EM_NONE if not
+	 * computed.
+	 */
+	uint16_t		e_machine;
 	/* LBR call stack stitch */
 	bool			lbr_stitch_enable;
 	struct lbr_stitch	*lbr_stitch;
@@ -302,6 +306,14 @@ static inline void thread__set_filter_entry_depth(struct thread *thread, int dep
 	RC_CHK_ACCESS(thread)->filter_entry_depth = depth;
 }
 
+uint16_t thread__e_machine(struct thread *thread, struct machine *machine);
+
+static inline void thread__set_e_machine(struct thread *thread, uint16_t e_machine)
+{
+	RC_CHK_ACCESS(thread)->e_machine = e_machine;
+}
+
+
 static inline bool thread__lbr_stitch_enable(const struct thread *thread)
 {
 	return RC_CHK_ACCESS(thread)->lbr_stitch_enable;