selftests/powerpc/64: Test all paths through copy routines

The hand-coded assembler 64-bit copy routines include feature sections
that select one code path or another depending on which CPU we are
executing on.  The self-tests for these copy routines end up testing
just one path.  This adds a mechanism for selecting any desired code
path at compile time, and makes 2 or 3 versions of each test, each
using a different code path, so as to cover all the possible paths.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
[mpe: Add -mcpu=power4 to CFLAGS for older compilers]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/lib/copyuser_64.S

@@ -12,6 +12,11 @@
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
 
+#ifndef SELFTEST_CASE
+/* 0 == most CPUs, 1 == POWER6, 2 == Cell */
+#define SELFTEST_CASE	0
+#endif
+
 #ifdef __BIG_ENDIAN__
 #define sLd sld		/* Shift towards low-numbered address. */
 #define sHd srd		/* Shift towards high-numbered address. */
@@ -73,6 +78,7 @@ _GLOBAL(__copy_tofrom_user_base)
  * At the time of writing the only CPU that has this combination of bits
  * set is Power6.
  */
+test_feature = (SELFTEST_CASE == 1)
 BEGIN_FTR_SECTION
 	nop
 FTR_SECTION_ELSE
@@ -82,6 +88,7 @@ ALT_FTR_SECTION_END(CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_CP_USE_DCBTZ, \
 .Ldst_aligned:
 	addi	r3,r3,-16
 r3_offset = 16
+test_feature = (SELFTEST_CASE == 0)
 BEGIN_FTR_SECTION
 	andi.	r0,r4,7
 	bne	.Lsrc_unaligned

arch/powerpc/lib/copyuser_power7.S

@@ -19,6 +19,11 @@
  */
 #include <asm/ppc_asm.h>
 
+#ifndef SELFTEST_CASE
+/* 0 == don't use VMX, 1 == use VMX */
+#define SELFTEST_CASE	0
+#endif
+
 #ifdef __BIG_ENDIAN__
 #define LVS(VRT,RA,RB)		lvsl	VRT,RA,RB
 #define VPERM(VRT,VRA,VRB,VRC)	vperm	VRT,VRA,VRB,VRC
@@ -80,7 +85,6 @@
 
 
 _GLOBAL(__copy_tofrom_user_power7)
-#ifdef CONFIG_ALTIVEC
 	cmpldi	r5,16
 	cmpldi	cr1,r5,3328
 
@@ -89,15 +93,12 @@ _GLOBAL(__copy_tofrom_user_power7)
 	std	r5,-STACKFRAMESIZE+STK_REG(R29)(r1)
 
 	blt	.Lshort_copy
-	bge	cr1,.Lvmx_copy
-#else
-	cmpldi	r5,16
 
-	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
-	std	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
-	std	r5,-STACKFRAMESIZE+STK_REG(R29)(r1)
-
-	blt	.Lshort_copy
+#ifdef CONFIG_ALTIVEC
+test_feature = SELFTEST_CASE
+BEGIN_FTR_SECTION
+	bgt	cr1,.Lvmx_copy
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
 
 .Lnonvmx_copy:
@@ -278,8 +279,8 @@ err1;	stb	r0,0(r3)
 	addi	r1,r1,STACKFRAMESIZE
 	b	.Lnonvmx_copy
 
-#ifdef CONFIG_ALTIVEC
 .Lvmx_copy:
+#ifdef CONFIG_ALTIVEC
 	mflr	r0
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)

arch/powerpc/lib/memcpy_64.S

@@ -12,6 +12,11 @@
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
 
+#ifndef SELFTEST_CASE
+/* For big-endian, 0 == most CPUs, 1 == POWER6, 2 == Cell */
+#define SELFTEST_CASE	0
+#endif
+
 	.align	7
 _GLOBAL_TOC(memcpy)
 BEGIN_FTR_SECTION
@@ -22,10 +27,8 @@ BEGIN_FTR_SECTION
 #endif
 FTR_SECTION_ELSE
 #ifdef CONFIG_PPC_BOOK3S_64
-#ifndef SELFTEST
 	b	memcpy_power7
 #endif
-#endif
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
 #ifdef __LITTLE_ENDIAN__
 	/* dumb little-endian memcpy that will get replaced at runtime */
@@ -49,6 +52,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
    cleared.
    At the time of writing the only CPU that has this combination of bits
    set is Power6. */
+test_feature = (SELFTEST_CASE == 1)
 BEGIN_FTR_SECTION
 	nop
 FTR_SECTION_ELSE
@@ -57,6 +61,7 @@ ALT_FTR_SECTION_END(CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_CP_USE_DCBTZ, \
                     CPU_FTR_UNALIGNED_LD_STD)
 .Ldst_aligned:
 	addi	r3,r3,-16
+test_feature = (SELFTEST_CASE == 0)
 BEGIN_FTR_SECTION
 	andi.	r0,r4,7
 	bne	.Lsrc_unaligned

arch/powerpc/lib/memcpy_power7.S

@@ -19,7 +19,10 @@
  */
 #include <asm/ppc_asm.h>
 
-_GLOBAL(memcpy_power7)
+#ifndef SELFTEST_CASE
+/* 0 == don't use VMX, 1 == use VMX */
+#define SELFTEST_CASE	0
+#endif
 
 #ifdef __BIG_ENDIAN__
 #define LVS(VRT,RA,RB)		lvsl	VRT,RA,RB
@@ -29,20 +32,17 @@ _GLOBAL(memcpy_power7)
 #define VPERM(VRT,VRA,VRB,VRC)	vperm	VRT,VRB,VRA,VRC
 #endif
 
-#ifdef CONFIG_ALTIVEC
+_GLOBAL(memcpy_power7)
 	cmpldi	r5,16
 	cmpldi	cr1,r5,4096
-
 	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
-
 	blt	.Lshort_copy
-	bgt	cr1,.Lvmx_copy
-#else
-	cmpldi	r5,16
-
-	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
 
-	blt	.Lshort_copy
+#ifdef CONFIG_ALTIVEC
+test_feature = SELFTEST_CASE
+BEGIN_FTR_SECTION
+	bgt	cr1, .Lvmx_copy
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
 
 .Lnonvmx_copy:
@@ -223,8 +223,8 @@ _GLOBAL(memcpy_power7)
 	addi	r1,r1,STACKFRAMESIZE
 	b	.Lnonvmx_copy
 
-#ifdef CONFIG_ALTIVEC
 .Lvmx_copy:
+#ifdef CONFIG_ALTIVEC
 	mflr	r0
 	std	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
 	std	r5,-STACKFRAMESIZE+STK_REG(R29)(r1)

tools/testing/selftests/powerpc/copyloops/.gitignore

-copyuser_64
-copyuser_power7
-memcpy_64
-memcpy_power7
+copyuser_64_t0
+copyuser_64_t1
+copyuser_64_t2
+copyuser_power7_t0
+copyuser_power7_t1
+memcpy_64_t0
+memcpy_64_t1
+memcpy_64_t2
+memcpy_power7_t0
+memcpy_power7_t1

tools/testing/selftests/powerpc/copyloops/Makefile

@@ -4,18 +4,41 @@ CFLAGS += -m64
 CFLAGS += -I$(CURDIR)
 CFLAGS += -D SELFTEST
 CFLAGS += -maltivec
+CFLAGS += -mcpu=power4
 
 # Use our CFLAGS for the implicit .S rule & set the asm machine type
 ASFLAGS = $(CFLAGS) -Wa,-mpower4
 
-TEST_GEN_PROGS := copyuser_64 copyuser_power7 memcpy_64 memcpy_power7
+TEST_GEN_PROGS := copyuser_64_t0 copyuser_64_t1 copyuser_64_t2 \
+		copyuser_p7_t0 copyuser_p7_t1 \
+		memcpy_64_t0 memcpy_64_t1 memcpy_64_t2 \
+		memcpy_p7_t0 memcpy_p7_t1
+
 EXTRA_SOURCES := validate.c ../harness.c
 
 include ../../lib.mk
 
-$(OUTPUT)/copyuser_64:     CPPFLAGS += -D COPY_LOOP=test___copy_tofrom_user_base
-$(OUTPUT)/copyuser_power7: CPPFLAGS += -D COPY_LOOP=test___copy_tofrom_user_power7
-$(OUTPUT)/memcpy_64:       CPPFLAGS += -D COPY_LOOP=test_memcpy
-$(OUTPUT)/memcpy_power7:   CPPFLAGS += -D COPY_LOOP=test_memcpy_power7
+$(OUTPUT)/copyuser_64_t%:	copyuser_64.S $(EXTRA_SOURCES)
+	$(CC) $(CPPFLAGS) $(CFLAGS) \
+		-D COPY_LOOP=test___copy_tofrom_user_base \
+		-D SELFTEST_CASE=$(subst copyuser_64_t,,$(notdir $@)) \
+		-o $@ $^
+
+$(OUTPUT)/copyuser_p7_t%:	copyuser_power7.S $(EXTRA_SOURCES)
+	$(CC) $(CPPFLAGS) $(CFLAGS) \
+		-D COPY_LOOP=test___copy_tofrom_user_power7 \
+		-D SELFTEST_CASE=$(subst copyuser_p7_t,,$(notdir $@)) \
+		-o $@ $^
+
+# Strictly speaking, we only need the memcpy_64 test cases for big-endian
+$(OUTPUT)/memcpy_64_t%:	memcpy_64.S $(EXTRA_SOURCES)
+	$(CC) $(CPPFLAGS) $(CFLAGS) \
+		-D COPY_LOOP=test_memcpy \
+		-D SELFTEST_CASE=$(subst memcpy_64_t,,$(notdir $@)) \
+		-o $@ $^
 
-$(TEST_GEN_PROGS): $(EXTRA_SOURCES)
+$(OUTPUT)/memcpy_p7_t%:	memcpy_power7.S $(EXTRA_SOURCES)
+	$(CC) $(CPPFLAGS) $(CFLAGS) \
+		-D COPY_LOOP=test_memcpy_power7 \
+		-D SELFTEST_CASE=$(subst memcpy_p7_t,,$(notdir $@)) \
+		-o $@ $^

tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h

@@ -43,17 +43,16 @@ FUNC_START(enter_vmx_ops)
 FUNC_START(exit_vmx_ops)
 	blr
 
-FUNC_START(memcpy_power7)
-	blr
-
-FUNC_START(__copy_tofrom_user_power7)
-	blr
-
 FUNC_START(__copy_tofrom_user_base)
 	blr
 
-#define BEGIN_FTR_SECTION
-#define FTR_SECTION_ELSE
-#define ALT_FTR_SECTION_END_IFCLR(x)
-#define ALT_FTR_SECTION_END(x, y)
-#define END_FTR_SECTION_IFCLR(x)
+#define BEGIN_FTR_SECTION		.if test_feature
+#define FTR_SECTION_ELSE		.else
+#define ALT_FTR_SECTION_END_IFCLR(x)	.endif
+#define ALT_FTR_SECTION_END_IFSET(x)	.endif
+#define ALT_FTR_SECTION_END(x, y)	.endif
+#define END_FTR_SECTION_IFCLR(x)	.endif
+#define END_FTR_SECTION_IFSET(x)	.endif
+
+/* Default to taking the first of any alternative feature sections */
+test_feature = 1