powerpc/64s: Set assembler machine type to POWER4

Rather than override the machine type in .S code (which can hide wrong
or ambiguous code generation for the target), set the type to power4
for all assembly.

This also means we need to be careful not to build power4-only code
when we're not building for Book3S, such as the "power7" versions of
copyuser/page/memcpy.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Fix Book3E build, don't build the "power7" variants for non-Book3S]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/Makefile

@@ -245,6 +245,7 @@ endif
 cpu-as-$(CONFIG_4xx)		+= -Wa,-m405
 cpu-as-$(CONFIG_ALTIVEC)	+= $(call as-option,-Wa$(comma)-maltivec)
 cpu-as-$(CONFIG_E200)		+= -Wa,-me200
+cpu-as-$(CONFIG_PPC_BOOK3S_64)	+= -Wa,-mpower4
 
 KBUILD_AFLAGS += $(cpu-as-y)
 KBUILD_CFLAGS += $(cpu-as-y)

arch/powerpc/include/asm/ppc_asm.h

@@ -439,14 +439,11 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 
 /* The following stops all load and store data streams associated with stream
  * ID (ie. streams created explicitly).  The embedded and server mnemonics for
- * dcbt are different so we use machine "power4" here explicitly.
+ * dcbt are different so this must only be used for server.
  */
-#define DCBT_STOP_ALL_STREAM_IDS(scratch)	\
-.machine push ;					\
-.machine "power4" ;				\
-       lis     scratch,0x60000000@h;		\
-       dcbt    0,scratch,0b01010;		\
-.machine pop
+#define DCBT_BOOK3S_STOP_ALL_STREAM_IDS(scratch)	\
+       lis     scratch,0x60000000@h;			\
+       dcbt    0,scratch,0b01010
 
 /*
  * toreal/fromreal/tophys/tovirt macros. 32-bit BookE makes them

arch/powerpc/kernel/entry_64.S

@@ -545,7 +545,7 @@ _GLOBAL(_switch)
 /* Cancel all explict user streams as they will have no use after context
  * switch and will stop the HW from creating streams itself
  */
-	DCBT_STOP_ALL_STREAM_IDS(r6)
+	DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r6)
 #endif
 
 	addi	r6,r4,-THREAD	/* Convert THREAD to 'current' */

arch/powerpc/kernel/exceptions-64s.S

@@ -687,14 +687,11 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 
 	bne	cr4,1f		/* returning to kernel */
 
-.machine	push
-.machine	"power4"
 	mtcrf	0x80,r9
 	mtcrf	0x08,r9		/* MSR[PR] indication is in cr4 */
 	mtcrf	0x04,r9		/* MSR[RI] indication is in cr5 */
 	mtcrf	0x02,r9		/* I/D indication is in cr6 */
 	mtcrf	0x01,r9		/* slb_allocate uses cr0 and cr7 */
-.machine	pop
 
 	RESTORE_CTR(r9, PACA_EXSLB)
 	RESTORE_PPR_PACA(PACA_EXSLB, r9)
@@ -707,14 +704,11 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 	RFI_TO_USER
 	b	.	/* prevent speculative execution */
 1:
-.machine	push
-.machine	"power4"
 	mtcrf	0x80,r9
 	mtcrf	0x08,r9		/* MSR[PR] indication is in cr4 */
 	mtcrf	0x04,r9		/* MSR[RI] indication is in cr5 */
 	mtcrf	0x02,r9		/* I/D indication is in cr6 */
 	mtcrf	0x01,r9		/* slb_allocate uses cr0 and cr7 */
-.machine	pop
 
 	RESTORE_CTR(r9, PACA_EXSLB)
 	RESTORE_PPR_PACA(PACA_EXSLB, r9)
@@ -1524,7 +1518,7 @@ TRAMP_REAL_BEGIN(rfi_flush_fallback)
 	ld	r11,PACA_L1D_FLUSH_SIZE(r13)
 	srdi	r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
 	mtctr	r11
-	DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+	DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
 
 	/* order ld/st prior to dcbt stop all streams with flushing */
 	sync
@@ -1564,7 +1558,7 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback)
 	ld	r11,PACA_L1D_FLUSH_SIZE(r13)
 	srdi	r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
 	mtctr	r11
-	DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+	DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
 
 	/* order ld/st prior to dcbt stop all streams with flushing */
 	sync

arch/powerpc/lib/Makefile

@@ -22,9 +22,11 @@ ifeq ($(call ld-ifversion, -lt, 225000000, y),y)
 extra-$(CONFIG_PPC64)	+= crtsavres.o
 endif
 
+obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \
+			       memcpy_power7.o
+
 obj64-y	+= copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
-	   copyuser_power7.o string_64.o copypage_power7.o memcpy_power7.o \
-	   memcpy_64.o memcmp_64.o pmem.o
+	   string_64.o memcpy_64.o memcmp_64.o pmem.o
 
 obj64-$(CONFIG_SMP)	+= locks.o
 obj64-$(CONFIG_ALTIVEC)	+= vmx-helper.o

arch/powerpc/lib/copypage_64.S

@@ -21,7 +21,9 @@ _GLOBAL_TOC(copy_page)
 BEGIN_FTR_SECTION
 	lis	r5,PAGE_SIZE@h
 FTR_SECTION_ELSE
+#ifdef CONFIG_PPC_BOOK3S_64
 	b	copypage_power7
+#endif
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
 	ori	r5,r5,PAGE_SIZE@l
 BEGIN_FTR_SECTION

arch/powerpc/lib/copypage_power7.S

@@ -42,8 +42,6 @@ _GLOBAL(copypage_power7)
 	lis	r8,0x8000	/* GO=1 */
 	clrldi	r8,r8,32
 
-.machine push
-.machine "power4"
 	/* setup read stream 0  */
 	dcbt	0,r4,0b01000  	/* addr from */
 	dcbt	0,r7,0b01010   /* length and depth from */
@@ -52,7 +50,6 @@ _GLOBAL(copypage_power7)
 	dcbtst	0,r10,0b01010  /* length and depth to */
 	eieio
 	dcbt	0,r8,0b01010	/* all streams GO */
-.machine pop
 
 #ifdef CONFIG_ALTIVEC
 	mflr	r0

arch/powerpc/lib/copyuser_64.S

@@ -20,11 +20,13 @@
 
 	.align	7
 _GLOBAL_TOC(__copy_tofrom_user)
+#ifdef CONFIG_PPC_BOOK3S_64
 BEGIN_FTR_SECTION
 	nop
 FTR_SECTION_ELSE
 	b	__copy_tofrom_user_power7
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
+#endif
 _GLOBAL(__copy_tofrom_user_base)
 	/* first check for a whole page copy on a page boundary */
 	cmpldi	cr1,r5,16

arch/powerpc/lib/copyuser_power7.S

@@ -312,8 +312,6 @@ err1;	stb	r0,0(r3)
 	lis	r8,0x8000	/* GO=1 */
 	clrldi	r8,r8,32
 
-.machine push
-.machine "power4"
 	/* setup read stream 0 */
 	dcbt	0,r6,0b01000   /* addr from */
 	dcbt	0,r7,0b01010   /* length and depth from */
@@ -322,7 +320,6 @@ err1;	stb	r0,0(r3)
 	dcbtst	0,r10,0b01010  /* length and depth to */
 	eieio
 	dcbt	0,r8,0b01010	/* all streams GO */
-.machine pop
 
 	beq	cr1,.Lunwind_stack_nonvmx_copy
 

arch/powerpc/lib/memcpy_64.S

@@ -19,9 +19,11 @@ BEGIN_FTR_SECTION
 	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)	/* save destination pointer for return value */
 #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 */

arch/powerpc/lib/memcpy_power7.S

@@ -259,15 +259,12 @@ _GLOBAL(memcpy_power7)
 	lis	r8,0x8000	/* GO=1 */
 	clrldi	r8,r8,32
 
-.machine push
-.machine "power4"
 	dcbt	0,r6,0b01000
 	dcbt	0,r7,0b01010
 	dcbtst	0,r9,0b01000
 	dcbtst	0,r10,0b01010
 	eieio
 	dcbt	0,r8,0b01010	/* GO */
-.machine pop
 
 	beq	cr1,.Lunwind_stack_nonvmx_copy