[PATCH 4/5] -march=native: REP STOSB

[Alexey Dobriyan <adobriyan@gmail.com>]

If CPU advertises fast REP STOSB, use it.

Inline clear_page() to use only 3 registers across function call
not whole shebang as required by ABI.

Also, tell gcc to use REP STOSB for memset(), this saves terabytes of .text.

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
---
 Makefile                           |  3 +++
 arch/x86/boot/compressed/head_64.S |  4 ++++
 arch/x86/crypto/sha1_ssse3_asm.S   |  7 ++++++-
 arch/x86/include/asm/page_64.h     | 13 +++++++++++++
 arch/x86/lib/Makefile              |  2 ++
 arch/x86/lib/memset_64.S           | 15 +++++++++++++++
 scripts/kconfig/cpuid.c            |  6 +++++-
 scripts/march-native.sh            |  1 +
 8 files changed, 49 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile
index 84abac4c181a..70d91d52ee60 100644
--- a/Makefile
+++ b/Makefile
@@ -593,6 +593,9 @@ endif
 ifdef CONFIG_MARCH_NATIVE_REP_MOVSB
 KBUILD_CFLAGS += -mmemcpy-strategy=rep_byte:-1:align
 endif
+ifdef CONFIG_MARCH_NATIVE_REP_STOSB
+KBUILD_CFLAGS += -mmemset-strategy=rep_byte:-1:align
+endif
 
 ifeq ($(KBUILD_EXTMOD),)
 # Read in dependencies to all Kconfig* files, make sure to run
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 20919b4f3133..a7913f5e18b6 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -447,8 +447,12 @@ relocated:
 	leaq    _bss(%rip), %rdi
 	leaq    _ebss(%rip), %rcx
 	subq	%rdi, %rcx
+#ifdef CONFIG_MARCH_NATIVE_REP_STOSB
+	rep stosb
+#else
 	shrq	$3, %rcx
 	rep	stosq
+#endif
 
 /*
  * Adjust our own GOT
diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S
index 6204bd53528c..ffa41d7a582a 100644
--- a/arch/x86/crypto/sha1_ssse3_asm.S
+++ b/arch/x86/crypto/sha1_ssse3_asm.S
@@ -94,10 +94,15 @@
 	SHA1_PIPELINED_MAIN_BODY
 
 	# cleanup workspace
-	mov	$8, %ecx
 	mov	%rsp, %rdi
 	xor	%rax, %rax
+#ifdef CONFIG_MARCH_NATIVE_REP_STOSB
+	mov	$64, %ecx
+	rep stosb
+#else
+	mov	$8, %ecx
 	rep stosq
+#endif
 
 	mov	%rbp, %rsp		# deallocate workspace
 	pop	%rbp
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index c2353661eaf1..b3d275b07624 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -36,6 +36,18 @@ extern unsigned long __phys_addr_symbol(unsigned long);
 #define pfn_valid(pfn)          ((pfn) < max_pfn)
 #endif
 
+#ifdef CONFIG_MARCH_NATIVE_REP_STOSB
+static __always_inline void clear_page(void *page)
+{
+	uint32_t len = PAGE_SIZE;
+	asm volatile (
+		"rep stosb"
+		: "+D" (page), "+c" (len)
+		: "a" (0)
+		: "memory"
+	);
+}
+#else
 void clear_page_orig(void *page);
 void clear_page_rep(void *page);
 void clear_page_erms(void *page);
@@ -49,6 +61,7 @@ static inline void clear_page(void *page)
 			   "0" (page)
 			   : "memory", "rax", "rcx");
 }
+#endif
 
 #ifdef CONFIG_MARCH_NATIVE_REP_MOVSB
 static __always_inline void copy_page(void *to, void *from)
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 8f9460bef2ec..6cb356408ebb 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -45,7 +45,9 @@ endif
 else
         obj-y += iomap_copy_64.o
         lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
+ifneq ($(CONFIG_MARCH_NATIVE_REP_STOSB),y)
         lib-y += clear_page_64.o
+endif
 ifneq ($(CONFIG_MARCH_NATIVE_REP_MOVSB),y)
 	lib-y += copy_page_64.o
 endif
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 9bc861c71e75..7786d1a65423 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -8,6 +8,20 @@
 
 .weak memset
 
+#ifdef CONFIG_MARCH_NATIVE_REP_STOSB
+ENTRY(memset)
+ENTRY(__memset)
+	mov	%esi, %eax
+	mov	%rdi, %rsi
+	mov	%rdx, %rcx
+	rep stosb
+	mov	%rsi, %rax
+	ret
+ENDPROC(memset)
+ENDPROC(__memset)
+EXPORT_SYMBOL(memset)
+EXPORT_SYMBOL(__memset)
+#else
 /*
  * ISO C memset - set a memory block to a byte value. This function uses fast
  * string to get better performance than the original function. The code is
@@ -140,3 +154,4 @@ ENTRY(memset_orig)
 	jmp .Lafter_bad_alignment
 .Lfinal:
 ENDPROC(memset_orig)
+#endif
diff --git a/scripts/kconfig/cpuid.c b/scripts/kconfig/cpuid.c
index 4947f47e7728..ecb285183581 100644
--- a/scripts/kconfig/cpuid.c
+++ b/scripts/kconfig/cpuid.c
@@ -44,6 +44,7 @@ static inline void cpuid2(uint32_t eax0, uint32_t ecx0, uint32_t *eax, uint32_t
 
 static bool popcnt	= false;
 static bool rep_movsb	= false;
+static bool rep_stosb	= false;
 
 static uint32_t eax0_max;
 
@@ -62,8 +63,10 @@ static void intel(void)
 		cpuid2(7, 0, &eax, &ecx, &edx, &ebx);
 //		printf("%08x %08x %08x %08x\n", eax, ecx, edx, ebx);
 
-		if (ebx & (1 << 9))
+		if (ebx & (1 << 9)) {
 			rep_movsb = true;
+			rep_stosb = true;
+		}
 	}
 }
 
@@ -85,6 +88,7 @@ int main(int argc, char *argv[])
 #define _(x)	if (streq(opt, #x)) return x ? EXIT_SUCCESS : EXIT_FAILURE
 	_(popcnt);
 	_(rep_movsb);
+	_(rep_stosb);
 #undef _
 
 	return EXIT_FAILURE;
diff --git a/scripts/march-native.sh b/scripts/march-native.sh
index eb52c20c56b4..d3adf0edb2be 100755
--- a/scripts/march-native.sh
+++ b/scripts/march-native.sh
@@ -32,6 +32,7 @@ option() {
 if test -x "$CPUID"; then
 	"$CPUID" popcnt		&& option "CONFIG_MARCH_NATIVE_POPCNT"
 	"$CPUID" rep_movsb	&& option "CONFIG_MARCH_NATIVE_REP_MOVSB"
+	"$CPUID" rep_stosb	&& option "CONFIG_MARCH_NATIVE_REP_STOSB"
 fi
 
 if test ! -f "$AUTOCONF1" -o ! -f "$AUTOCONF2"; then
-- 
2.13.6