gh-101282: Apply BOLT optimizations to libpython for shared builds (#104709)

Apply BOLT optimizations to libpython for shared builds. Most of the C
code is in libpython so it is critical to apply BOLT there fully realize
BOLT benefits.

This change also reworks how BOLT instrumentation is applied. It
effectively removes the readelf based logic added in gh-101525 and
replaces it with a mechanism that saves a copy of the pre-bolt binary
and restores that copy when necessary. This allows us to perform BOLT
optimizations without having to manually delete the output binary to
force a new bolt run.

Also:
- add a clean-bolt target for purging BOLT files and hook that up to the
  clean target
- .gitignore BOLT related files

Before and after this refactor, `make` will no-op after a previous run.
Both versions should also share common make DAG deficiencies where
targets fail to trigger as often as they need to or can trigger
prematurely in certain scenarios. e.g. after this change you may need to
`rm profile-bolt-stamp` to force a BOLT run because there aren't
appropriate non-phony targets for BOLT's make target to depend on.

To make it easier to iterate on custom BOLT settings, the flags to pass
to instrumentation and application are now defined in configure and can
be overridden by passing BOLT_INSTRUMENT_FLAGS and BOLT_APPLY_FLAGS.

1 files changed, 50 insertions, 15 deletions

diff --git a/Makefile.pre.in b/Makefile.pre.in
index da3a8f6..eb79c9c 100644
--- a/Makefile.pre.in
+++ b/Makefile.pre.in
@@ -672,21 +672,55 @@ profile-opt: profile-run-stamp
 	-rm -f profile-clean-stamp
 	$(MAKE) @DEF_MAKE_RULE@ CFLAGS_NODIST="$(CFLAGS_NODIST) $(PGO_PROF_USE_FLAG)" LDFLAGS_NODIST="$(LDFLAGS_NODIST)"
 
-.PHONY: bolt-opt
-bolt-opt: @PREBOLT_RULE@
+# List of binaries that BOLT runs on.
+BOLT_BINARIES := @BOLT_BINARIES@
+
+BOLT_INSTRUMENT_FLAGS := @BOLT_INSTRUMENT_FLAGS@
+BOLT_APPLY_FLAGS := @BOLT_APPLY_FLAGS@
+
+.PHONY: clean-bolt
+clean-bolt:
+	# Profile data.
 	rm -f *.fdata
-	@if $(READELF) -p .note.bolt_info $(BUILDPYTHON) | grep BOLT > /dev/null; then\
-		echo "skip: $(BUILDPYTHON) is already BOLTed."; \
-	else \
-		@LLVM_BOLT@ ./$(BUILDPYTHON) -instrument -instrumentation-file-append-pid -instrumentation-file=$(abspath $(BUILDPYTHON).bolt) -o $(BUILDPYTHON).bolt_inst; \
-		./$(BUILDPYTHON).bolt_inst $(PROFILE_TASK) || true; \
-		@MERGE_FDATA@ $(BUILDPYTHON).*.fdata > $(BUILDPYTHON).fdata; \
-		@LLVM_BOLT@ ./$(BUILDPYTHON) -o $(BUILDPYTHON).bolt -data=$(BUILDPYTHON).fdata -update-debug-sections -reorder-blocks=ext-tsp -reorder-functions=hfsort+ -split-functions -icf=1 -inline-all -split-eh -reorder-functions-use-hot-size -peepholes=none -jump-tables=aggressive -inline-ap -indirect-call-promotion=all -dyno-stats -use-gnu-stack -frame-opt=hot; \
-		rm -f *.fdata; \
-		rm -f $(BUILDPYTHON).bolt_inst; \
-		mv $(BUILDPYTHON).bolt $(BUILDPYTHON); \
-	fi
+	# Pristine binaries before BOLT optimization.
+	rm -f *.prebolt
+	# BOLT instrumented binaries.
+	rm -f *.bolt_inst
+
+profile-bolt-stamp: $(BUILDPYTHON)
+	# Ensure a pristine, pre-BOLT copy of the binary and no profile data from last run.
+	for bin in $(BOLT_BINARIES); do \
+	  prebolt="$${bin}.prebolt"; \
+	  if [ -e "$${prebolt}" ]; then \
+	    echo "Restoring pre-BOLT binary $${prebolt}"; \
+	    mv "$${bin}.prebolt" "$${bin}"; \
+	  fi; \
+	  cp "$${bin}" "$${prebolt}"; \
+	  rm -f $${bin}.bolt.*.fdata $${bin}.fdata; \
+	done
+	# Instrument each binary.
+	for bin in $(BOLT_BINARIES); do \
+	  @LLVM_BOLT@ "$${bin}" -instrument -instrumentation-file-append-pid -instrumentation-file=$(abspath $${bin}.bolt) -o $${bin}.bolt_inst $(BOLT_INSTRUMENT_FLAGS); \
+	  mv "$${bin}.bolt_inst" "$${bin}"; \
+	done
+	# Run instrumented binaries to collect data.
+	$(RUNSHARED) ./$(BUILDPYTHON) $(PROFILE_TASK) || true
+	# Merge all the data files together.
+	for bin in $(BOLT_BINARIES); do \
+	  @MERGE_FDATA@ $${bin}.*.fdata > "$${bin}.fdata"; \
+	  rm -f $${bin}.*.fdata; \
+	done
+	# Run bolt against the merged data to produce an optimized binary.
+	for bin in $(BOLT_BINARIES); do \
+	  @LLVM_BOLT@ "$${bin}.prebolt" -o "$${bin}.bolt" -data="$${bin}.fdata" $(BOLT_APPLY_FLAGS); \
+	  mv "$${bin}.bolt" "$${bin}"; \
+	done
+	touch $@
 
+.PHONY: bolt-opt
+bolt-opt:
+	$(MAKE) @PREBOLT_RULE@
+	$(MAKE) profile-bolt-stamp
 
 # Compile and run with gcov
 .PHONY: coverage
@@ -2623,10 +2657,11 @@ profile-removal:
 	rm -f $(COVERAGE_INFO)
 	rm -rf $(COVERAGE_REPORT)
 	rm -f profile-run-stamp
+	rm -f profile-bolt-stamp
 
 .PHONY: clean
-clean: clean-retain-profile
-	@if test @DEF_MAKE_ALL_RULE@ = profile-opt; then \
+clean: clean-retain-profile clean-bolt
+	@if test @DEF_MAKE_ALL_RULE@ = profile-opt -o @DEF_MAKE_ALL_RULE@ = bolt-opt; then \
 		rm -f profile-gen-stamp profile-clean-stamp; \
 		$(MAKE) profile-removal; \
 	fi