perf disasm: Allow configuring what disassemblers to use

The perf tools annotation code used for a long time parsing the output
of binutils's objdump (or its reimplementations, like llvm's) to then
parse and augment it with samples, allow navigation, etc.

More recently disassemblers from the capstone and llvm (libraries, not
parsing the output of tools using those libraries to mimic binutils's
objdump output) were introduced.

So when all those methods are available, there is a static preference
for a series of attempts of disassembling a binary, with the 'llvm,
capstone, objdump' sequence being hard coded.

This patch allows users to change that sequence, specifying via a 'perf
config' 'annotate.disassemblers' entry which and in what order
disassemblers should be attempted.

As alluded to in the comments in the source code of this series, this
flexibility is useful for users and developers alike, elliminating the
requirement to rebuild the tool with some specific set of libraries to
see how the output of disassembling would be for one of these methods.

  root@x1:~# rm -f ~/.perfconfig
  root@x1:~# perf annotate -v --stdio2 update_load_avg
  <SNIP>
  symbol__disassemble:
    filename=/usr/lib/debug/lib/modules/6.11.4-201.fc40.x86_64/vmlinux,
    sym=update_load_avg, start=0xffffffffb6148fe0, en>
  annotating [0x6ff7170]
    /usr/lib/debug/lib/modules/6.11.4-201.fc40.x86_64/vmlinux :
    [0x7407ca0] update_load_avg
  Disassembled with llvm
  annotate.disassemblers=llvm,capstone,objdump
  Samples: 66  of event 'cpu_atom/cycles/P', 10000 Hz,
	Event count (approx.): 5185444, [percent: local period]
  update_load_avg()
    /usr/lib/debug/lib/modules/6.11.4-201.fc40.x86_64/vmlinux
  Percent       0xffffffff81148fe0 <update_load_avg>:
     1.61         pushq   %r15
                  pushq   %r14
     1.00         pushq   %r13
                  movl    %edx,%r13d
     1.90         pushq   %r12
                  pushq   %rbp
                  movq    %rsi,%rbp
                  pushq   %rbx
                  movq    %rdi,%rbx
                  subq    $0x18,%rsp
    15.14         movl    0x1a4(%rdi),%eax

  root@x1:~# perf config annotate.disassemblers=capstone
  root@x1:~# cat ~/.perfconfig
  # this file is auto-generated.
  [annotate]
	  disassemblers = capstone
  root@x1:~#
  root@x1:~# perf annotate -v --stdio2 update_load_avg
  <SNIP>
  Disassembled with capstone
  annotate.disassemblers=capstone
  Samples: 66  of event 'cpu_atom/cycles/P', 10000 Hz,
  Event count (approx.): 5185444, [percent: local period]
  update_load_avg()
  /usr/lib/debug/lib/modules/6.11.4-201.fc40.x86_64/vmlinux
  Percent       0xffffffff81148fe0 <update_load_avg>:
     1.61         pushq   %r15
                  pushq   %r14
     1.00         pushq   %r13
                  movl    %edx,%r13d
     1.90         pushq   %r12
                  pushq   %rbp
                  movq    %rsi,%rbp
                  pushq   %rbx
                  movq    %rdi,%rbx
                  subq    $0x18,%rsp
    15.14         movl    0x1a4(%rdi),%eax
  root@x1:~# perf config annotate.disassemblers=objdump,capstone
  root@x1:~# perf config annotate.disassemblers
  annotate.disassemblers=objdump,capstone
  root@x1:~# cat ~/.perfconfig
  # this file is auto-generated.
  [annotate]
	  disassemblers = objdump,capstone
  root@x1:~# perf annotate -v --stdio2 update_load_avg
  Executing: objdump  --start-address=0xffffffff81148fe0 \
		      --stop-address=0xffffffff811497aa  \
		      -d --no-show-raw-insn -S -C "$1"
  Disassembled with objdump
  annotate.disassemblers=objdump,capstone
  Samples: 66  of event 'cpu_atom/cycles/P', 10000 Hz,
  Event count (approx.): 5185444, [percent: local period]
  update_load_avg()
  /usr/lib/debug/lib/modules/6.11.4-201.fc40.x86_64/vmlinux
  Percent

                Disassembly of section .text:

                ffffffff81148fe0 <update_load_avg>:
                #define DO_ATTACH       0x4

                ffffffff81148fe0 <update_load_avg>:
                #define DO_ATTACH       0x4
                #define DO_DETACH       0x8

                /* Update task and its cfs_rq load average */
                static inline void update_load_avg(struct cfs_rq *cfs_rq,
						   struct sched_entity *se,
						   int flags)
                {
     1.61         push   %r15
                  push   %r14
     1.00         push   %r13
                  mov    %edx,%r13d
     1.90         push   %r12
                  push   %rbp
                  mov    %rsi,%rbp
                  push   %rbx
                  mov    %rdi,%rbx
                  sub    $0x18,%rsp
                }

                /* rq->task_clock normalized against any time
		   this cfs_rq has spent throttled */
                static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq)
                {
                if (unlikely(cfs_rq->throttle_count))
    15.14         mov    0x1a4(%rdi),%eax
  root@x1:~#

After adding a way to select the disassembler from the command line a
'perf test' comparing the output of the various diassemblers should be
introduced, to test these codebases.

Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Link: https://lore.kernel.org/r/20241111151734.1018476-4-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 6 insertions, 0 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index b1d98da79be8..32e15c9f53f3 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2116,6 +2116,12 @@ static int annotation__config(const char *var, const char *value, void *data)
 			opt->offset_level = ANNOTATION__MAX_OFFSET_LEVEL;
 		else if (opt->offset_level < ANNOTATION__MIN_OFFSET_LEVEL)
 			opt->offset_level = ANNOTATION__MIN_OFFSET_LEVEL;
+	} else if (!strcmp(var, "annotate.disassemblers")) {
+		opt->disassemblers_str = strdup(value);
+		if (!opt->disassemblers_str) {
+			pr_err("Not enough memory for annotate.disassemblers\n");
+			return -1;
+		}
 	} else if (!strcmp(var, "annotate.hide_src_code")) {
 		opt->hide_src_code = perf_config_bool("hide_src_code", value);
 	} else if (!strcmp(var, "annotate.jump_arrows")) {