Message ID | 20230713060800.392500-1-yhs@fb.com (mailing list archive) |
---|---|
State | Superseded |
Delegated to: | BPF |
Headers | show |
Series | bpf: Support new insns from cpu v4 | expand |
On Wed, Jul 12, 2023 at 11:11 PM Yonghong Song <yhs@fb.com> wrote: > > Similar to no-alu32 runner, 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, excluding naked asm (verifier_*) tests: > insn pattern # of instructions > reg = (s8)reg 4 > reg = (s16)reg 2 > reg = (s32)reg 26 > reg = *(s8 *)(reg + off) 11 > reg = *(s16 *)(reg + off) 14 > reg = *(s32 *)(reg + off) 15214 > reg = bswap16 reg 133 > 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. > > I did not collect verifier stats now since I have not really > started to do proper range bound estimation with these > instructions. > > With current patch set, all selftests passed with -mcpu=v4 > when running test_progs-cpuv4 binary. > > Signed-off-by: Yonghong Song <yhs@fb.com> > --- > tools/testing/selftests/bpf/.gitignore | 2 ++ > tools/testing/selftests/bpf/Makefile | 18 ++++++++++++++---- > 2 files changed, 16 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..4b2cf5d40120 100644 > --- a/tools/testing/selftests/bpf/Makefile > +++ b/tools/testing/selftests/bpf/Makefile > @@ -44,7 +44,7 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test > test_sock test_sockmap get_cgroup_id_user \ > test_cgroup_storage \ > test_tcpnotify_user test_sysctl \ > - test_progs-no_alu32 > + test_progs-no_alu32 test_progs-cpuv4 > > # Also test bpf-gcc, if present > ifneq ($(BPF_GCC),) > @@ -383,6 +383,11 @@ 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 Use --target= (Clang 3.4 preferred form) for new code :) > # Build BPF object using GCC > define GCC_BPF_BUILD_RULE > $(call msg,GCC-BPF,$(TRUNNER_BINARY),$2) > @@ -425,7 +430,7 @@ 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 +458,7 @@ 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 +589,11 @@ 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. > +TRUNNER_BPF_BUILD_RULE := CLANG_CPUV4_BPF_BUILD_RULE > +TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS) > +$(eval $(call DEFINE_TEST_RUNNER,test_progs,cpuv4)) > + > # Define test_progs BPF-GCC-flavored test runner. > ifneq ($(BPF_GCC),) > TRUNNER_BPF_BUILD_RULE := GCC_BPF_BUILD_RULE > @@ -681,7 +691,7 @@ 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 > -- > 2.34.1 >
On 7/12/23 11:18 PM, Fangrui Song wrote: > On Wed, Jul 12, 2023 at 11:11 PM Yonghong Song <yhs@fb.com> wrote: >> >> Similar to no-alu32 runner, 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, excluding naked asm (verifier_*) tests: >> insn pattern # of instructions >> reg = (s8)reg 4 >> reg = (s16)reg 2 >> reg = (s32)reg 26 >> reg = *(s8 *)(reg + off) 11 >> reg = *(s16 *)(reg + off) 14 >> reg = *(s32 *)(reg + off) 15214 >> reg = bswap16 reg 133 >> 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. >> >> I did not collect verifier stats now since I have not really >> started to do proper range bound estimation with these >> instructions. >> >> With current patch set, all selftests passed with -mcpu=v4 >> when running test_progs-cpuv4 binary. >> >> Signed-off-by: Yonghong Song <yhs@fb.com> >> --- >> tools/testing/selftests/bpf/.gitignore | 2 ++ >> tools/testing/selftests/bpf/Makefile | 18 ++++++++++++++---- >> 2 files changed, 16 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..4b2cf5d40120 100644 >> --- a/tools/testing/selftests/bpf/Makefile >> +++ b/tools/testing/selftests/bpf/Makefile >> @@ -44,7 +44,7 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test >> test_sock test_sockmap get_cgroup_id_user \ >> test_cgroup_storage \ >> test_tcpnotify_user test_sysctl \ >> - test_progs-no_alu32 >> + test_progs-no_alu32 test_progs-cpuv4 >> >> # Also test bpf-gcc, if present >> ifneq ($(BPF_GCC),) >> @@ -383,6 +383,11 @@ 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 > > Use --target= (Clang 3.4 preferred form) for new code :) Thanks for reminding me this. Will fix in the next revision. Using '-target bpf' for too long so forgot '--target=bpf' although just learned it a few weeks ago. > >> # Build BPF object using GCC >> define GCC_BPF_BUILD_RULE >> $(call msg,GCC-BPF,$(TRUNNER_BINARY),$2) >> @@ -425,7 +430,7 @@ 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) >> +# $2 - test runner extra "flavor" (e.g., no_alu32, cpuv4, gcc-bpf, etc) >> define DEFINE_TEST_RUNNER [...]
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 116fecf80ca1..110518ba4804 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -13,6 +13,7 @@ test_dev_cgroup /test_progs /test_progs-no_alu32 /test_progs-bpf_gcc +/test_progs-cpuv4 test_verifier_log feature test_sock @@ -36,6 +37,7 @@ test_cpp *.lskel.h /no_alu32 /bpf_gcc +/cpuv4 /host-tools /tools /runqslower diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 882be03b179f..4b2cf5d40120 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -44,7 +44,7 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test test_sock test_sockmap get_cgroup_id_user \ test_cgroup_storage \ test_tcpnotify_user test_sysctl \ - test_progs-no_alu32 + test_progs-no_alu32 test_progs-cpuv4 # Also test bpf-gcc, if present ifneq ($(BPF_GCC),) @@ -383,6 +383,11 @@ 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 +430,7 @@ 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 +458,7 @@ 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 +589,11 @@ 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. +TRUNNER_BPF_BUILD_RULE := CLANG_CPUV4_BPF_BUILD_RULE +TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS) +$(eval $(call DEFINE_TEST_RUNNER,test_progs,cpuv4)) + # Define test_progs BPF-GCC-flavored test runner. ifneq ($(BPF_GCC),) TRUNNER_BPF_BUILD_RULE := GCC_BPF_BUILD_RULE @@ -681,7 +691,7 @@ 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
Similar to no-alu32 runner, 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, excluding naked asm (verifier_*) tests: insn pattern # of instructions reg = (s8)reg 4 reg = (s16)reg 2 reg = (s32)reg 26 reg = *(s8 *)(reg + off) 11 reg = *(s16 *)(reg + off) 14 reg = *(s32 *)(reg + off) 15214 reg = bswap16 reg 133 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. I did not collect verifier stats now since I have not really started to do proper range bound estimation with these instructions. With current patch set, all selftests passed with -mcpu=v4 when running test_progs-cpuv4 binary. Signed-off-by: Yonghong Song <yhs@fb.com> --- tools/testing/selftests/bpf/.gitignore | 2 ++ tools/testing/selftests/bpf/Makefile | 18 ++++++++++++++---- 2 files changed, 16 insertions(+), 4 deletions(-)