| Message ID | patch-4.thread-aa7b8d.git-aa7b8dbf236f.your-ad-here.call-01533557518-ext-9465@work.hours (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | ftrace build improvements | expand |
On Mon, Aug 06, 2018 at 03:17:47PM +0200, Vasily Gorbik wrote: > Utilize -mfentry and -mnop-mcount gcc options together with > -mrecord-mcount to get compiler generated calls to the profiling functions > as nops which are compatible with current -mhotpatch=0,3 approach. At the > same time -mrecord-mcount enables __mcount_loc section generation by > the compiler which allows to avoid using scripts/recordmcount.pl script. > > Signed-off-by: Vasily Gorbik <gor@linux.ibm.com> > --- > arch/s390/Kconfig | 2 ++ > arch/s390/Makefile | 16 +++++++++------- > arch/s390/include/asm/ftrace.h | 6 +++--- > arch/s390/kernel/ftrace.c | 2 +- > arch/s390/kernel/mcount.S | 2 +- > 5 files changed, 16 insertions(+), 12 deletions(-) Do you have numbers which tell how much this reduces the compile time of the kernel on s390? I assume this change makes quite some difference. Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com> -- To unsubscribe from this list: send the line "unsubscribe linux-kbuild" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Tue, Aug 07, 2018 at 07:30:17AM +0200, Heiko Carstens wrote: > On Mon, Aug 06, 2018 at 03:17:47PM +0200, Vasily Gorbik wrote: > > Utilize -mfentry and -mnop-mcount gcc options together with > > -mrecord-mcount to get compiler generated calls to the profiling functions > > as nops which are compatible with current -mhotpatch=0,3 approach. At the > > same time -mrecord-mcount enables __mcount_loc section generation by > > the compiler which allows to avoid using scripts/recordmcount.pl script. > > > > Signed-off-by: Vasily Gorbik <gor@linux.ibm.com> > > --- > > arch/s390/Kconfig | 2 ++ > > arch/s390/Makefile | 16 +++++++++------- > > arch/s390/include/asm/ftrace.h | 6 +++--- > > arch/s390/kernel/ftrace.c | 2 +- > > arch/s390/kernel/mcount.S | 2 +- > > 5 files changed, 16 insertions(+), 12 deletions(-) > > Do you have numbers which tell how much this reduces the compile time of > the kernel on s390? I assume this change makes quite some difference. > Very roughly, best time across several runs. With -j24 on 24 core lpar with -mfentry -mrecord-mcount etc real 0m54.748s user 12m32.041s sys 1m17.778s vs -mhotpatch=0,3 + scripts/recordmcount.pl: real 0m56.752s user 12m52.386s sys 1m35.873s -- To unsubscribe from this list: send the line "unsubscribe linux-kbuild" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 8a1863d9ed53..71c2d9de379f 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -136,6 +136,7 @@ config S390 select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EFFICIENT_UNALIGNED_ACCESS + select HAVE_FENTRY select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER @@ -157,6 +158,7 @@ config S390 select HAVE_MEMBLOCK_NODE_MAP select HAVE_MEMBLOCK_PHYS_MAP select HAVE_MOD_ARCH_SPECIFIC + select HAVE_NOP_MCOUNT select HAVE_OPROFILE select HAVE_PERF_EVENTS select HAVE_REGS_AND_STACK_ACCESS_API diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 68a690442be0..8498babb5dad 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -86,13 +86,15 @@ ifdef CONFIG_EXPOLINE endif ifdef CONFIG_FUNCTION_TRACER -# make use of hotpatch feature if the compiler supports it -cc_hotpatch := -mhotpatch=0,3 -ifeq ($(call cc-option-yn,$(cc_hotpatch)),y) -CC_FLAGS_FTRACE := $(cc_hotpatch) -KBUILD_AFLAGS += -DCC_USING_HOTPATCH -KBUILD_CFLAGS += -DCC_USING_HOTPATCH -endif + ifeq ($(call cc-option-yn,-mfentry -mnop-mcount),n) + # make use of hotpatch feature if the compiler supports it + cc_hotpatch := -mhotpatch=0,3 + ifeq ($(call cc-option-yn,$(cc_hotpatch)),y) + CC_FLAGS_FTRACE := $(cc_hotpatch) + KBUILD_AFLAGS += -DCC_USING_HOTPATCH + KBUILD_CFLAGS += -DCC_USING_HOTPATCH + endif + endif endif # Test CFI features of binutils diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index cfccc0edd00d..8ea270fdc7fb 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -4,7 +4,7 @@ #define ARCH_SUPPORTS_FTRACE_OPS 1 -#ifdef CC_USING_HOTPATCH +#if defined(CC_USING_HOTPATCH) || defined(CC_USING_NOP_MCOUNT) #define MCOUNT_INSN_SIZE 6 #else #define MCOUNT_INSN_SIZE 24 @@ -42,7 +42,7 @@ struct ftrace_insn { static inline void ftrace_generate_nop_insn(struct ftrace_insn *insn) { #ifdef CONFIG_FUNCTION_TRACER -#ifdef CC_USING_HOTPATCH +#if defined(CC_USING_HOTPATCH) || defined(CC_USING_NOP_MCOUNT) /* brcl 0,0 */ insn->opc = 0xc004; insn->disp = 0; @@ -57,7 +57,7 @@ static inline void ftrace_generate_nop_insn(struct ftrace_insn *insn) static inline int is_ftrace_nop(struct ftrace_insn *insn) { #ifdef CONFIG_FUNCTION_TRACER -#ifdef CC_USING_HOTPATCH +#if defined(CC_USING_HOTPATCH) || defined(CC_USING_NOP_MCOUNT) if (insn->disp == 0) return 1; #else diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index dc76d813e420..84be7f02d0c2 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -61,7 +61,7 @@ unsigned long ftrace_plt; static inline void ftrace_generate_orig_insn(struct ftrace_insn *insn) { -#ifdef CC_USING_HOTPATCH +#if defined(CC_USING_HOTPATCH) || defined(CC_USING_NOP_MCOUNT) /* brcl 0,0 */ insn->opc = 0xc004; insn->disp = 0; diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 27110f3294ed..e93fbf02490c 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -35,7 +35,7 @@ ENTRY(ftrace_caller) .globl ftrace_regs_caller .set ftrace_regs_caller,ftrace_caller lgr %r1,%r15 -#ifndef CC_USING_HOTPATCH +#if !(defined(CC_USING_HOTPATCH) || defined(CC_USING_NOP_MCOUNT)) aghi %r0,MCOUNT_RETURN_FIXUP #endif aghi %r15,-STACK_FRAME_SIZE
Utilize -mfentry and -mnop-mcount gcc options together with -mrecord-mcount to get compiler generated calls to the profiling functions as nops which are compatible with current -mhotpatch=0,3 approach. At the same time -mrecord-mcount enables __mcount_loc section generation by the compiler which allows to avoid using scripts/recordmcount.pl script. Signed-off-by: Vasily Gorbik <gor@linux.ibm.com> --- arch/s390/Kconfig | 2 ++ arch/s390/Makefile | 16 +++++++++------- arch/s390/include/asm/ftrace.h | 6 +++--- arch/s390/kernel/ftrace.c | 2 +- arch/s390/kernel/mcount.S | 2 +- 5 files changed, 16 insertions(+), 12 deletions(-)