selftests/bpf: Add a cpuv4 test runner for cpu=v4 testing

Similar to no-alu32 runner, if clang compiler supports -mcpu=v4,
a cpuv4 runner is created to test bpf programs compiled with
-mcpu=v4.

The following are some num-of-insn statistics for each newer
instructions based on existing selftests, excluding subsequent
cpuv4 insn specific tests.

   insn pattern                # of instructions
   reg = (s8)reg               4
   reg = (s16)reg              4
   reg = (s32)reg              144
   reg = *(s8 *)(reg + off)    13
   reg = *(s16 *)(reg + off)   14
   reg = *(s32 *)(reg + off)   15215
   reg = bswap16 reg           142
   reg = bswap32 reg           38
   reg = bswap64 reg           14
   reg s/= reg                 0
   reg s%= reg                 0
   gotol <offset>              58

Note that in llvm -mcpu=v4 implementation, the compiler is a little
bit conservative about generating 'gotol' insn (32-bit branch offset)
as it didn't precise count the number of insns (e.g., some insns are
debug insns, etc.). Compared to old 'goto' insn, newer 'gotol' insn
should have comparable verification states to 'goto' insn.

With current patch set, all selftests passed with -mcpu=v4
when running test_progs-cpuv4 binary. The -mcpu=v3 and -mcpu=v2 run
are also successful.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728011250.3718252-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

2 files changed, 26 insertions, 4 deletions

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 116fecf80ca1..110518ba4804 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -13,6 +13,7 @@ test_dev_cgroup
 /test_progs
 /test_progs-no_alu32
 /test_progs-bpf_gcc
+/test_progs-cpuv4
 test_verifier_log
 feature
 test_sock
@@ -36,6 +37,7 @@ test_cpp
 *.lskel.h
 /no_alu32
 /bpf_gcc
+/cpuv4
 /host-tools
 /tools
 /runqslower
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 882be03b179f..6a45719a8d47 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -33,9 +33,13 @@ CFLAGS += -g -O0 -rdynamic -Wall -Werror $(GENFLAGS) $(SAN_CFLAGS)	\
 LDFLAGS += $(SAN_LDFLAGS)
 LDLIBS += -lelf -lz -lrt -lpthread
 
-# Silence some warnings when compiled with clang
 ifneq ($(LLVM),)
+# Silence some warnings when compiled with clang
 CFLAGS += -Wno-unused-command-line-argument
+# Check whether cpu=v4 is supported or not by clang
+ifneq ($(shell $(CLANG) --target=bpf -mcpu=help 2>&1 | grep 'v4'),)
+CLANG_CPUV4 := 1
+endif
 endif
 
 # Order correspond to 'make run_tests' order
@@ -51,6 +55,10 @@ ifneq ($(BPF_GCC),)
 TEST_GEN_PROGS += test_progs-bpf_gcc
 endif
 
+ifneq ($(CLANG_CPUV4),)
+TEST_GEN_PROGS += test_progs-cpuv4
+endif
+
 TEST_GEN_FILES = test_lwt_ip_encap.bpf.o test_tc_edt.bpf.o
 TEST_FILES = xsk_prereqs.sh $(wildcard progs/btf_dump_test_case_*.c)
 
@@ -383,6 +391,11 @@ define CLANG_NOALU32_BPF_BUILD_RULE
 	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
 	$(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v2 -o $2
 endef
+# Similar to CLANG_BPF_BUILD_RULE, but with cpu-v4
+define CLANG_CPUV4_BPF_BUILD_RULE
+	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
+	$(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v4 -o $2
+endef
 # Build BPF object using GCC
 define GCC_BPF_BUILD_RULE
 	$(call msg,GCC-BPF,$(TRUNNER_BINARY),$2)
@@ -425,7 +438,7 @@ LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(ske
 # $eval()) and pass control to DEFINE_TEST_RUNNER_RULES.
 # Parameters:
 # $1 - test runner base binary name (e.g., test_progs)
-# $2 - test runner extra "flavor" (e.g., no_alu32, gcc-bpf, etc)
+# $2 - test runner extra "flavor" (e.g., no_alu32, cpuv4, gcc-bpf, etc)
 define DEFINE_TEST_RUNNER
 
 TRUNNER_OUTPUT := $(OUTPUT)$(if $2,/)$2
@@ -453,7 +466,7 @@ endef
 # Using TRUNNER_XXX variables, provided by callers of DEFINE_TEST_RUNNER and
 # set up by DEFINE_TEST_RUNNER itself, create test runner build rules with:
 # $1 - test runner base binary name (e.g., test_progs)
-# $2 - test runner extra "flavor" (e.g., no_alu32, gcc-bpf, etc)
+# $2 - test runner extra "flavor" (e.g., no_alu32, cpuv4, gcc-bpf, etc)
 define DEFINE_TEST_RUNNER_RULES
 
 ifeq ($($(TRUNNER_OUTPUT)-dir),)
@@ -584,6 +597,13 @@ TRUNNER_BPF_BUILD_RULE := CLANG_NOALU32_BPF_BUILD_RULE
 TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS)
 $(eval $(call DEFINE_TEST_RUNNER,test_progs,no_alu32))
 
+# Define test_progs-cpuv4 test runner.
+ifneq ($(CLANG_CPUV4),)
+TRUNNER_BPF_BUILD_RULE := CLANG_CPUV4_BPF_BUILD_RULE
+TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS)
+$(eval $(call DEFINE_TEST_RUNNER,test_progs,cpuv4))
+endif
+
 # Define test_progs BPF-GCC-flavored test runner.
 ifneq ($(BPF_GCC),)
 TRUNNER_BPF_BUILD_RULE := GCC_BPF_BUILD_RULE
@@ -681,7 +701,7 @@ EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR)	\
 	prog_tests/tests.h map_tests/tests.h verifier/tests.h		\
 	feature bpftool							\
 	$(addprefix $(OUTPUT)/,*.o *.skel.h *.lskel.h *.subskel.h	\
-			       no_alu32 bpf_gcc bpf_testmod.ko		\
+			       no_alu32 cpuv4 bpf_gcc bpf_testmod.ko	\
 			       liburandom_read.so)
 
 .PHONY: docs docs-clean