perf record: Refactor ARM64 leaf caller setup out of arch

Code in tools/perf/arch causes portability issues/opaqueness and LTO
issues due to the use of weak symbols. Move the adding of LR to the
sample_user_regs into arm64-frame-pointer-unwind-support.c conditional
on EM_HOST == EM_AARCH64 (false on all non-ARM64 builds).

This also better encapsulates the use of the sampled registers by
get_leaf_frame_caller_aarch64 and the set up by the new
add_leaf_frame_caller_opts_aarch64, exposing opportunities for possibly
sampling PC and SP to help the unwinder.

Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Shimin Guo <shimin.guo@skydio.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build
index 4e06a08d281ac133cfc76aba27a7492198acd34f..638aa6948ab51725a4d6492c9946f6d4e4d4e7f1 100644 (file)
--- a/tools/perf/arch/arm64/util/Build
+++ b/tools/perf/arch/arm64/util/Build
@@ -5,7 +5,6 @@ perf-util-y += ../../arm/util/pmu.o
 perf-util-y += arm-spe.o
 perf-util-y += header.o
 perf-util-y += hisi-ptt.o
-perf-util-y += machine.o
 perf-util-y += mem-events.o
 perf-util-y += pmu.o
 perf-util-y += tsc.o

diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c
deleted file mode 100644 (file)
index 80fb13c..0000000
--- a/tools/perf/arch/arm64/util/machine.c
+++ /dev/null
@@ -1,12 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include "callchain.h" // prototype of arch__add_leaf_frame_record_opts
-#include "perf_regs.h"
-#include "record.h"
-
-#define SMPL_REG_MASK(b) (1ULL << (b))
-
-void arch__add_leaf_frame_record_opts(struct record_opts *opts)
-{
-       opts->sample_user_regs |= SMPL_REG_MASK(PERF_REG_ARM64_LR);
-}

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4a5eba498c0259d4323140d0be200e80d7c2164a..272bba7f4b9ec7ee32a1debf98eb3a21fe9655c1 100644 (file)
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -14,6 +14,7 @@
 #include "util/parse-events.h"
 #include "util/config.h"
 
+#include "util/arm64-frame-pointer-unwind-support.h"
 #include "util/callchain.h"
 #include "util/cgroup.h"
 #include "util/header.h"
@@ -3230,10 +3231,6 @@ static int record__parse_off_cpu_thresh(const struct option *opt,
        return 0;
 }
 
-void __weak arch__add_leaf_frame_record_opts(struct record_opts *opts __maybe_unused)
-{
-}
-
 static int parse_control_option(const struct option *opt,
                                const char *str,
                                int unset __maybe_unused)
@@ -4319,8 +4316,10 @@ int cmd_record(int argc, const char **argv)
 
        evlist__warn_user_requested_cpus(rec->evlist, rec->opts.target.cpu_list);
 
-       if (callchain_param.enabled && callchain_param.record_mode == CALLCHAIN_FP)
-               arch__add_leaf_frame_record_opts(&rec->opts);
+       if (callchain_param.enabled && callchain_param.record_mode == CALLCHAIN_FP) {
+               if (EM_HOST == EM_AARCH64)
+                       add_leaf_frame_caller_opts_aarch64(&rec->opts);
+       }
 
        err = -ENOMEM;
        if (evlist__create_maps(rec->evlist, &rec->opts.target) < 0) {

diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c
index 858ce2b01812abb9280dc0471089a8ecf8fcc2eb..3af8c7a466e0eecc019bf8b68b5cba96e9180088 100644 (file)
--- a/tools/perf/util/arm64-frame-pointer-unwind-support.c
+++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c
@@ -2,6 +2,7 @@
 #include "arm64-frame-pointer-unwind-support.h"
 #include "callchain.h"
 #include "event.h"
+#include "record.h"
 #include "unwind.h"
 #include <string.h>
 
@@ -16,6 +17,11 @@ struct entries {
 
 #define SMPL_REG_MASK(b) (1ULL << (b))
 
+void add_leaf_frame_caller_opts_aarch64(struct record_opts *opts)
+{
+       opts->sample_user_regs |= SMPL_REG_MASK(PERF_REG_ARM64_LR);
+}
+
 static bool get_leaf_frame_caller_enabled(struct perf_sample *sample)
 {
        struct regs_dump *regs;

diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.h b/tools/perf/util/arm64-frame-pointer-unwind-support.h
index 42d3a45490f50f10c4d6931fac0fe492164d6cfd..ba35b295bfcdda052cb8b8eb637ea5b53e55f3c6 100644 (file)
--- a/tools/perf/util/arm64-frame-pointer-unwind-support.h
+++ b/tools/perf/util/arm64-frame-pointer-unwind-support.h
@@ -5,8 +5,10 @@
 #include <linux/types.h>
 
 struct perf_sample;
+struct record_opts;
 struct thread;
 
+void add_leaf_frame_caller_opts_aarch64(struct record_opts *opts);
 u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thread, int user_idx);
 
 #endif /* __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H */

diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 06d463ccc7a04fc4b0f9f06f1bc18adc10ae14b7..b7702d65ad6043847809f4c92928b816a97ff4e1 100644 (file)
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -277,8 +277,6 @@ static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
 }
 #endif
 
-void arch__add_leaf_frame_record_opts(struct record_opts *opts);
-
 char *callchain_list__sym_name(struct callchain_list *cl,
                               char *bf, size_t bfsize, bool show_dso);
 char *callchain_node__scnprintf_value(struct callchain_node *node,