perf script: Support 32bit code under 64bit OS with capstone

Use the DSO to resolve whether an IP is 32bit or 64bit and use that to
configure capstone to the correct mode. This allows to correctly
disassemble 32bit code under a 64bit OS.

% cat > loop.c
volatile int var;
int main(void)
{
int i;
for (i = 0; i < 100000; i++)
var++;
}
% gcc -m32 -o loop loop.c
% perf record -e cycles:u ./loop
% perf script -F +disasm
loop 82665 1833176.618023: 1 cycles:u: f7eed500 _start+0x0 (/usr/lib/ld-linux.so.2) movl %esp, %eax
loop 82665 1833176.618029: 1 cycles:u: f7eed500 _start+0x0 (/usr/lib/ld-linux.so.2) movl %esp, %eax
loop 82665 1833176.618031: 7 cycles:u: f7eed500 _start+0x0 (/usr/lib/ld-linux.so.2) movl %esp, %eax
loop 82665 1833176.618034: 91 cycles:u: f7eed500 _start+0x0 (/usr/lib/ld-linux.so.2) movl %esp, %eax
loop 82665 1833176.618036: 1242 cycles:u: f7eed500 _start+0x0 (/usr/lib/ld-linux.so.2) movl %esp, %eax

Reviewed-by: Adrian Hunter <[e-mail]>
Acked-by: Thomas Richter <[e-mail]>
Signed-off-by: Andi Kleen <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/builtin-script.c

···
 static int perf_sample__fprintf_insn(struct perf_sample *sample,
 				     struct perf_event_attr *attr,
 				     struct thread *thread,
-				     struct machine *machine, FILE *fp)
+				     struct machine *machine, FILE *fp,
+				     struct addr_location *al)
 {
 	int printed = 0;
 
···
 	}
 	if (PRINT_FIELD(DISASM) && sample->insn_len) {
 		printed += fprintf(fp, "\t\t");
-		printed += sample__fprintf_insn_asm(sample, thread, machine, fp);
+		printed += sample__fprintf_insn_asm(sample, thread, machine, fp, al);
 	}
 	if (PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN))
 		printed += perf_sample__fprintf_brstackinsn(sample, thread, attr, machine, fp);
···
 	if (print_srcline_last)
 		printed += map__fprintf_srcline(al->map, al->addr, "\n  ", fp);
 
-	printed += perf_sample__fprintf_insn(sample, attr, thread, machine, fp);
+	printed += perf_sample__fprintf_insn(sample, attr, thread, machine, fp, al);
 	printed += fprintf(fp, "\n");
 	if (PRINT_FIELD(SRCCODE)) {
 		int ret = map__fprintf_srccode(al->map, al->addr, stdout,
···
 
 	if (evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		perf_sample__fprintf_bpf_output(sample, fp);
-	perf_sample__fprintf_insn(sample, attr, thread, machine, fp);
+	perf_sample__fprintf_insn(sample, attr, thread, machine, fp, al);
 
 	if (PRINT_FIELD(PHYS_ADDR))
 		fprintf(fp, "%16" PRIx64, sample->phys_addr);

tools/perf/util/print_insn.c

···
 #include "machine.h"
 #include "thread.h"
 #include "print_insn.h"
+#include "map.h"
+#include "dso.h"
 
 size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp)
 {
···
 #ifdef HAVE_LIBCAPSTONE_SUPPORT
 #include <capstone/capstone.h>
 
-static int capstone_init(struct machine *machine, csh *cs_handle)
+static int capstone_init(struct machine *machine, csh *cs_handle, bool is64)
 {
 	cs_arch arch;
 	cs_mode mode;
 
-	if (machine__is(machine, "x86_64")) {
+	if (machine__is(machine, "x86_64") && is64) {
 		arch = CS_ARCH_X86;
 		mode = CS_MODE_64;
 	} else if (machine__normalized_is(machine, "x86")) {
···
 	return printed;
 }
 
+static bool is64bitip(struct machine *machine, struct addr_location *al)
+{
+	const struct dso *dso = al->map ? map__dso(al->map) : NULL;
+
+	if (dso)
+		return dso->is_64_bit;
+
+	return machine__is(machine, "x86_64") ||
+		machine__normalized_is(machine, "arm64") ||
+		machine__normalized_is(machine, "s390");
+}
+
 size_t sample__fprintf_insn_asm(struct perf_sample *sample, struct thread *thread,
-				struct machine *machine, FILE *fp)
+				struct machine *machine, FILE *fp,
+				struct addr_location *al)
 {
 	csh cs_handle;
 	cs_insn *insn;
 	size_t count;
 	size_t printed = 0;
 	int ret;
+	bool is64bit = is64bitip(machine, al);
 
 	/* TODO: Try to initiate capstone only once but need a proper place. */
-	ret = capstone_init(machine, &cs_handle);
+	ret = capstone_init(machine, &cs_handle, is64bit);
 	if (ret < 0) {
 		/* fallback */
 		return sample__fprintf_insn_raw(sample, fp);
···
 size_t sample__fprintf_insn_asm(struct perf_sample *sample __maybe_unused,
 				struct thread *thread __maybe_unused,
 				struct machine *machine __maybe_unused,
-				FILE *fp __maybe_unused)
+				FILE *fp __maybe_unused,
+				struct addr_location *al __maybe_unused)
 {
 	return 0;
 }

tools/perf/util/print_insn.h

···
 struct machine;
 
 size_t sample__fprintf_insn_asm(struct perf_sample *sample, struct thread *thread,
-				struct machine *machine, FILE *fp);
+				struct machine *machine, FILE *fp, struct addr_location *al);
 size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp);
 
 #endif /* PERF_PRINT_INSN_H */