perf script: Add capstone support for '-F +brstackdisasm'

Support capstone output for the '-F +brstackinsn' branch dump.

The new output is enabled with the new field 'brstackdisasm'.

This was possible before with --xed, but now also allow it for users
that don't have xed using the builtin capstone support.

Before:

perf record -b emacs -Q --batch '()'
perf script -F +brstackinsn
...
emacs 55778 1814366.755945: 151564 cycles:P: 7f0ab2d17192 intel_check_word.constprop.0+0x162 (/usr/lib64/ld-linux-x86-64.s> intel_check_word.constprop.0+237:
00007f0ab2d1711d insn: 75 e6 # PRED 3 cycles [3]
00007f0ab2d17105 insn: 73 51
00007f0ab2d17107 insn: 48 89 c1
00007f0ab2d1710a insn: 48 39 ca
00007f0ab2d1710d insn: 73 96
00007f0ab2d1710f insn: 48 8d 04 11
00007f0ab2d17113 insn: 48 d1 e8
00007f0ab2d17116 insn: 49 8d 34 c1
00007f0ab2d1711a insn: 44 3a 06
00007f0ab2d1711d insn: 75 e6 # PRED 3 cycles [6] 3.00 IPC
00007f0ab2d17105 insn: 73 51 # PRED 1 cycles [7] 1.00 IPC
00007f0ab2d17158 insn: 48 8d 50 01
00007f0ab2d1715c insn: eb 92 # PRED 1 cycles [8] 2.00 IPC
00007f0ab2d170f0 insn: 48 39 ca
00007f0ab2d170f3 insn: 73 b0 # PRED 1 cycles [9] 2.00 IPC

After (perf must be compiled with capstone):

perf script -F +brstackdisasm

...
emacs 55778 1814366.755945: 151564 cycles:P: 7f0ab2d17192 intel_check_word.constprop.0+0x162 (/usr/lib64/ld-linux-x86-64.s> intel_check_word.constprop.0+237:
00007f0ab2d1711d jne intel_check_word.constprop.0+0xd5 # PRED 3 cycles [3]
00007f0ab2d17105 jae intel_check_word.constprop.0+0x128
00007f0ab2d17107 movq %rax, %rcx
00007f0ab2d1710a cmpq %rcx, %rdx
00007f0ab2d1710d jae intel_check_word.constprop.0+0x75
00007f0ab2d1710f leaq (%rcx, %rdx), %rax
00007f0ab2d17113 shrq $1, %rax
00007f0ab2d17116 leaq (%r9, %rax, 8), %rsi
00007f0ab2d1711a cmpb (%rsi), %r8b
00007f0ab2d1711d jne intel_check_word.constprop.0+0xd5 # PRED 3 cycles [6] 3.00 IPC
00007f0ab2d17105 jae intel_check_word.constprop.0+0x128 # PRED 1 cycles [7] 1.00 IPC
00007f0ab2d17158 leaq 1(%rax), %rdx
00007f0ab2d1715c jmp intel_check_word.constprop.0+0xc0 # PRED 1 cycles [8] 2.00 IPC
00007f0ab2d170f0 cmpq %rcx, %rdx
00007f0ab2d170f3 jae intel_check_word.constprop.0+0x75 # PRED 1 cycles [9] 2.00 IPC

Reviewed-by: Adrian Hunter <[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/Documentation/perf-script.txt

···
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, dsoff, addr, symoff,
         srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output,
-        brstackinsn, brstackinsnlen, brstackoff, callindent, insn, disasm,
+        brstackinsn, brstackinsnlen, brstackdisasm, brstackoff, callindent, insn, disasm,
         insnlen, synth, phys_addr, metric, misc, srccode, ipc, data_page_size,
-        code_page_size, ins_lat, machine_pid, vcpu, cgroup, retire_lat.
+        code_page_size, ins_lat, machine_pid, vcpu, cgroup, retire_lat,
 
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
···
 	Use brstackinsnlen to print the brstackinsn lenght. For example, you
 	can’t know the next sequential instruction after an unconditional branch unless
 	you calculate that based on its length.
+
+	brstackdisasm acts like brstackinsn, but will print disassembled instructions if
+	perf is built with the capstone library.
 
 	The brstackoff field will print an offset into a specific dso/binary.
 

tools/perf/builtin-script.c

···
 	PERF_OUTPUT_RETIRE_LAT      = 1ULL << 40,
 	PERF_OUTPUT_DSOFF           = 1ULL << 41,
 	PERF_OUTPUT_DISASM          = 1ULL << 42,
+	PERF_OUTPUT_BRSTACKDISASM   = 1ULL << 43,
 };
 
 struct perf_script {
···
 	{.str = "vcpu", .field = PERF_OUTPUT_VCPU},
 	{.str = "cgroup", .field = PERF_OUTPUT_CGROUP},
 	{.str = "retire_lat", .field = PERF_OUTPUT_RETIRE_LAT},
+	{.str = "brstackdisasm", .field = PERF_OUTPUT_BRSTACKDISASM},
 };
 
 enum {
···
 		       "selected. Hence, no address to lookup the source line number.\n");
 		return -EINVAL;
 	}
-	if ((PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN)) && !allow_user_set &&
+	if ((PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN) || PRINT_FIELD(BRSTACKDISASM))
+	    && !allow_user_set &&
 	    !(evlist__combined_branch_type(session->evlist) & PERF_SAMPLE_BRANCH_ANY)) {
 		pr_err("Display of branch stack assembler requested, but non all-branch filter set\n"
 		       "Hint: run 'perf record -b ...'\n");
···
 	return ret;
 }
 
+static const char *any_dump_insn(struct perf_event_attr *attr __maybe_unused,
+			struct perf_insn *x, uint64_t ip,
+			u8 *inbuf, int inlen, int *lenp)
+{
+#ifdef HAVE_LIBCAPSTONE_SUPPORT
+	if (PRINT_FIELD(BRSTACKDISASM)) {
+		const char *p = cs_dump_insn(x, ip, inbuf, inlen, lenp);
+		if (p)
+			return p;
+	}
+#endif
+	return dump_insn(x, ip, inbuf, inlen, lenp);
+}
+
 static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
 			    struct perf_insn *x, u8 *inbuf, int len,
 			    int insn, FILE *fp, int *total_cycles,
···
 {
 	int ilen = 0;
 	int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t", ip,
-			      dump_insn(x, ip, inbuf, len, &ilen));
+			      any_dump_insn(attr, x, ip, inbuf, len, &ilen));
 
 	if (PRINT_FIELD(BRSTACKINSNLEN))
 		printed += fprintf(fp, "ilen: %d\t", ilen);
···
 		nr = max_blocks + 1;
 
 	x.thread = thread;
+	x.machine = machine;
 	x.cpu = sample->cpu;
 
 	printed += fprintf(fp, "%c", '\n');
···
 			} else {
 				ilen = 0;
 				printed += fprintf(fp, "\t%016" PRIx64 "\t%s", ip,
-						   dump_insn(&x, ip, buffer + off, len - off, &ilen));
+						   any_dump_insn(attr, &x, ip, buffer + off, len - off, &ilen));
 				if (PRINT_FIELD(BRSTACKINSNLEN))
 					printed += fprintf(fp, "\tilen: %d", ilen);
 				printed += fprintf(fp, "\n");
···
 			goto out;
 		ilen = 0;
 		printed += fprintf(fp, "\t%016" PRIx64 "\t%s", sample->ip,
-			dump_insn(&x, sample->ip, buffer, len, &ilen));
+			any_dump_insn(attr, &x, sample->ip, buffer, len, &ilen));
 		if (PRINT_FIELD(BRSTACKINSNLEN))
 			printed += fprintf(fp, "\tilen: %d", ilen);
 		printed += fprintf(fp, "\n");
···
 	for (off = 0; off <= end - start; off += ilen) {
 		ilen = 0;
 		printed += fprintf(fp, "\t%016" PRIx64 "\t%s", start + off,
-				   dump_insn(&x, start + off, buffer + off, len - off, &ilen));
+				   any_dump_insn(attr, &x, start + off, buffer + off, len - off, &ilen));
 		if (PRINT_FIELD(BRSTACKINSNLEN))
 			printed += fprintf(fp, "\tilen: %d", ilen);
 		printed += fprintf(fp, "\n");
···
 		printed += fprintf(fp, "\t\t");
 		printed += sample__fprintf_insn_asm(sample, thread, machine, fp, al);
 	}
-	if (PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN))
+	if (PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN) || PRINT_FIELD(BRSTACKDISASM))
 		printed += perf_sample__fprintf_brstackinsn(sample, thread, attr, machine, fp);
 
 	return printed;
···
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,dsoff,"
 		     "addr,symoff,srcline,period,iregs,uregs,brstack,"
 		     "brstacksym,flags,data_src,weight,bpf-output,brstackinsn,"
-		     "brstackinsnlen,brstackoff,callindent,insn,disasm,insnlen,synth,"
+		     "brstackinsnlen,brstackdisasm,brstackoff,callindent,insn,disasm,insnlen,synth,"
 		     "phys_addr,metric,misc,srccode,ipc,tod,data_page_size,"
 		     "code_page_size,ins_lat,machine_pid,vcpu,cgroup,retire_lat",
 		     parse_output_fields),

tools/perf/util/dump-insn.h

···
 struct perf_insn {
 	/* Initialized by callers: */
 	struct thread *thread;
+	struct machine *machine;
 	u8	      cpumode;
 	bool	      is64bit;
 	int	      cpu;

tools/perf/util/print_insn.c

···
 #include "machine.h"
 #include "thread.h"
 #include "print_insn.h"
+#include "dump-insn.h"
 #include "map.h"
 #include "dso.h"
 
···
 	}
 
 	return 0;
+}
+
+static void dump_insn_x86(struct thread *thread, cs_insn *insn, struct perf_insn *x)
+{
+	struct addr_location al;
+	bool printed = false;
+
+	if (insn->detail && insn->detail->x86.op_count == 1) {
+		cs_x86_op *op = &insn->detail->x86.operands[0];
+
+		addr_location__init(&al);
+		if (op->type == X86_OP_IMM &&
+		    thread__find_symbol(thread, x->cpumode, op->imm, &al) &&
+		    al.sym &&
+		    al.addr < al.sym->end) {
+			snprintf(x->out, sizeof(x->out), "%s %s+%#" PRIx64 " [%#" PRIx64 "]", insn[0].mnemonic,
+					al.sym->name, al.addr - al.sym->start, op->imm);
+			printed = true;
+		}
+		addr_location__exit(&al);
+	}
+
+	if (!printed)
+		snprintf(x->out, sizeof(x->out), "%s %s", insn[0].mnemonic, insn[0].op_str);
+}
+
+const char *cs_dump_insn(struct perf_insn *x, uint64_t ip,
+			 u8 *inbuf, int inlen, int *lenp)
+{
+	int ret;
+	int count;
+	cs_insn *insn;
+	csh cs_handle;
+
+	ret = capstone_init(x->machine, &cs_handle, x->is64bit);
+	if (ret < 0)
+		return NULL;
+
+	count = cs_disasm(cs_handle, (uint8_t *)inbuf, inlen, ip, 1, &insn);
+	if (count > 0) {
+		if (machine__normalized_is(x->machine, "x86"))
+			dump_insn_x86(x->thread, &insn[0], x);
+		else
+			snprintf(x->out, sizeof(x->out), "%s %s",
+					insn[0].mnemonic, insn[0].op_str);
+		*lenp = insn->size;
+		cs_free(insn, count);
+	} else {
+		return NULL;
+	}
+	return x->out;
 }
 
 static size_t print_insn_x86(struct perf_sample *sample, struct thread *thread,

tools/perf/util/print_insn.h

···
 struct perf_sample;
 struct thread;
 struct machine;
+struct perf_insn;
 
 size_t sample__fprintf_insn_asm(struct perf_sample *sample, struct thread *thread,
 				struct machine *machine, FILE *fp, struct addr_location *al);
 size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp);
+const char *cs_dump_insn(struct perf_insn *x, uint64_t ip,
+                         u8 *inbuf, int inlen, int *lenp);
 
 #endif /* PERF_PRINT_INSN_H */