[PATCH 1/5] powerpc: consolidate feature fixup code

[PATCH 1/5] powerpc: consolidate feature fixup code

[Benjamin Herrenschmidt]

There are currently two versions of the functions for applying the
feature fixups, one for CPU features and one for firmware features. In
addition, they are both in assembly and with separate implementations
for 32 and 64 bits. identify_cpu() is also implemented in assembly and
separately for 32 and 64 bits.

This patch replaces them with a pair of C functions. The call sites are
slightly moved on ppc64 as well to be called from C instead of from
assembly, though it's a very small change, and thus shouldn't cause any
problem.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>


Index: linux-cell/arch/powerpc/kernel/head_64.S
===================================================================
--- linux-cell.orig/arch/powerpc/kernel/head_64.S	2006-10-13 16:04:10.000000000 +1000
+++ linux-cell/arch/powerpc/kernel/head_64.S	2006-10-13 16:43:05.000000000 +1000
@@ -1580,11 +1580,6 @@ _STATIC(__start_initialization_iSeries)
 	li	r0,0
 	stdu	r0,-STACK_FRAME_OVERHEAD(r1)
 
-	LOAD_REG_IMMEDIATE(r3,cpu_specs)
-	LOAD_REG_IMMEDIATE(r4,cur_cpu_spec)
-	li	r5,0
-	bl	.identify_cpu
-
 	LOAD_REG_IMMEDIATE(r2,__toc_start)
 	addi	r2,r2,0x4000
 	addi	r2,r2,0x4000
@@ -1964,13 +1959,6 @@ _STATIC(start_here_multiplatform)
 	addi	r2,r2,0x4000
 	add	r2,r2,r26
 
-	LOAD_REG_IMMEDIATE(r3, cpu_specs)
-	add	r3,r3,r26
-	LOAD_REG_IMMEDIATE(r4,cur_cpu_spec)
-	add	r4,r4,r26
-	mr	r5,r26
-	bl	.identify_cpu
-
 	/* Do very early kernel initializations, including initial hash table,
 	 * stab and slb setup before we turn on relocation.	*/
 
@@ -2000,13 +1988,6 @@ _STATIC(start_here_common)
 	li	r0,0
 	stdu	r0,-STACK_FRAME_OVERHEAD(r1)
 
-	/* Apply the CPUs-specific fixups (nop out sections not relevant
-	 * to this CPU
-	 */
-	li	r3,0
-	bl	.do_cpu_ftr_fixups
-	bl	.do_fw_ftr_fixups
-
 	/* ptr to current */
 	LOAD_REG_IMMEDIATE(r4, init_task)
 	std	r4,PACACURRENT(r13)
Index: linux-cell/arch/powerpc/kernel/misc_64.S
===================================================================
--- linux-cell.orig/arch/powerpc/kernel/misc_64.S	2006-10-13 16:04:10.000000000 +1000
+++ linux-cell/arch/powerpc/kernel/misc_64.S	2006-10-13 16:40:14.000000000 +1000
@@ -246,130 +246,6 @@ _GLOBAL(__flush_dcache_icache)
 	isync
 	blr
 
-/*
- * identify_cpu and calls setup_cpu
- * In:	r3 = base of the cpu_specs array
- *	r4 = address of cur_cpu_spec
- *	r5 = relocation offset
- */
-_GLOBAL(identify_cpu)
-	mfpvr	r7
-1:
-	lwz	r8,CPU_SPEC_PVR_MASK(r3)
-	and	r8,r8,r7
-	lwz	r9,CPU_SPEC_PVR_VALUE(r3)
-	cmplw	0,r9,r8
-	beq	1f
-	addi	r3,r3,CPU_SPEC_ENTRY_SIZE
-	b	1b
-1:
-	sub	r0,r3,r5
-	std	r0,0(r4)
-	ld	r4,CPU_SPEC_SETUP(r3)
-	cmpdi	0,r4,0
-	add	r4,r4,r5
-	beqlr
-	ld	r4,0(r4)
-	add	r4,r4,r5
-	mtctr	r4
-	/* Calling convention for cpu setup is r3=offset, r4=cur_cpu_spec */
-	mr	r4,r3
-	mr	r3,r5
-	bctr
-
-/*
- * do_cpu_ftr_fixups - goes through the list of CPU feature fixups
- * and writes nop's over sections of code that don't apply for this cpu.
- * r3 = data offset (not changed)
- */
-_GLOBAL(do_cpu_ftr_fixups)
-	/* Get CPU 0 features */
-	LOAD_REG_IMMEDIATE(r6,cur_cpu_spec)
-	sub	r6,r6,r3
-	ld	r4,0(r6)
-	sub	r4,r4,r3
-	ld	r4,CPU_SPEC_FEATURES(r4)
-	/* Get the fixup table */
-	LOAD_REG_IMMEDIATE(r6,__start___ftr_fixup)
-	sub	r6,r6,r3
-	LOAD_REG_IMMEDIATE(r7,__stop___ftr_fixup)
-	sub	r7,r7,r3
-	/* Do the fixup */
-1:	cmpld	r6,r7
-	bgelr
-	addi	r6,r6,32
-	ld	r8,-32(r6)	/* mask */
-	and	r8,r8,r4
-	ld	r9,-24(r6)	/* value */
-	cmpld	r8,r9
-	beq	1b
-	ld	r8,-16(r6)	/* section begin */
-	ld	r9,-8(r6)	/* section end */
-	subf.	r9,r8,r9
-	beq	1b
-	/* write nops over the section of code */
-	/* todo: if large section, add a branch at the start of it */
-	srwi	r9,r9,2
-	mtctr	r9
-	sub	r8,r8,r3
-	lis	r0,0x60000000@h	/* nop */
-3:	stw	r0,0(r8)
-	andi.	r10,r4,CPU_FTR_SPLIT_ID_CACHE@l
-	beq	2f
-	dcbst	0,r8		/* suboptimal, but simpler */
-	sync
-	icbi	0,r8
-2:	addi	r8,r8,4
-	bdnz	3b
-	sync			/* additional sync needed on g4 */
-	isync
-	b	1b
-
-/*
- * do_fw_ftr_fixups - goes through the list of firmware feature fixups
- * and writes nop's over sections of code that don't apply for this firmware.
- * r3 = data offset (not changed)
- */
-_GLOBAL(do_fw_ftr_fixups)
-	/* Get firmware features */
-	LOAD_REG_IMMEDIATE(r6,powerpc_firmware_features)
-	sub	r6,r6,r3
-	ld	r4,0(r6)
-	/* Get the fixup table */
-	LOAD_REG_IMMEDIATE(r6,__start___fw_ftr_fixup)
-	sub	r6,r6,r3
-	LOAD_REG_IMMEDIATE(r7,__stop___fw_ftr_fixup)
-	sub	r7,r7,r3
-	/* Do the fixup */
-1:	cmpld	r6,r7
-	bgelr
-	addi	r6,r6,32
-	ld	r8,-32(r6)	/* mask */
-	and	r8,r8,r4
-	ld	r9,-24(r6)	/* value */
-	cmpld	r8,r9
-	beq	1b
-	ld	r8,-16(r6)	/* section begin */
-	ld	r9,-8(r6)	/* section end */
-	subf.	r9,r8,r9
-	beq	1b
-	/* write nops over the section of code */
-	/* todo: if large section, add a branch at the start of it */
-	srwi	r9,r9,2
-	mtctr	r9
-	sub	r8,r8,r3
-	lis	r0,0x60000000@h	/* nop */
-3:	stw	r0,0(r8)
-BEGIN_FTR_SECTION
-	dcbst	0,r8		/* suboptimal, but simpler */
-	sync
-	icbi	0,r8
-END_FTR_SECTION_IFSET(CPU_FTR_SPLIT_ID_CACHE)
-	addi	r8,r8,4
-	bdnz	3b
-	sync			/* additional sync needed on g4 */
-	isync
-	b	1b
 
 #if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE)
 /*
Index: linux-cell/arch/powerpc/kernel/setup-common.c
===================================================================
--- linux-cell.orig/arch/powerpc/kernel/setup-common.c	2006-10-13 16:04:10.000000000 +1000
+++ linux-cell/arch/powerpc/kernel/setup-common.c	2006-10-13 16:39:03.000000000 +1000
@@ -520,3 +520,39 @@ void __init setup_panic(void)
 {
 	atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block);
 }
+
+void do_feature_fixups(unsigned long offset, unsigned long value,
+		       void *fixup_start, void *fixup_end)
+{
+	struct fixup_entry {
+		unsigned long	mask;
+		unsigned long	value;
+		unsigned int	*start;
+		unsigned int	*end;
+	} *fcur, *fend;
+
+	fcur = fixup_start;
+	fend = fixup_end;
+
+	for (; fcur < fend; fcur++) {
+		unsigned int *pstart, *pend, *p;
+
+		if ((value & fcur->mask) == fcur->value)
+			continue;
+
+		/* These PTRRELOCs will disappear once the new scheme for
+		 * modules and vdso is implemented
+		 */
+		pstart = PTRRELOC(fcur->start);
+		pend = PTRRELOC(fcur->end);
+
+		for (p = pstart; p < pend; p++) {
+			*p = 0x60000000u;
+			asm volatile ("dcbst 0, %0" : : "r" (p));
+		}
+		asm volatile ("sync" : : : "memory");
+		for (p = pstart; p < pend; p++)
+			asm volatile ("icbi 0,%0" : : "r" (p));
+		asm volatile ("sync; isync" : : : "memory");
+	}
+}
Index: linux-cell/arch/powerpc/kernel/setup.h
===================================================================
--- linux-cell.orig/arch/powerpc/kernel/setup.h	2006-10-13 16:04:10.000000000 +1000
+++ linux-cell/arch/powerpc/kernel/setup.h	2006-10-13 16:06:24.000000000 +1000
@@ -1,9 +1,12 @@
 #ifndef _POWERPC_KERNEL_SETUP_H
 #define _POWERPC_KERNEL_SETUP_H
 
-void check_for_initrd(void);
-void do_init_bootmem(void);
-void setup_panic(void);
+extern void check_for_initrd(void);
+extern void do_init_bootmem(void);
+extern void setup_panic(void);
+extern void do_feature_fixups(unsigned long offset, unsigned long value,
+			      void *fixup_start, void *fixup_end);
+
 extern int do_early_xmon;
 
 #endif /* _POWERPC_KERNEL_SETUP_H */
Index: linux-cell/arch/powerpc/kernel/setup_32.c
===================================================================
--- linux-cell.orig/arch/powerpc/kernel/setup_32.c	2006-10-13 16:04:10.000000000 +1000
+++ linux-cell/arch/powerpc/kernel/setup_32.c	2006-10-13 16:38:21.000000000 +1000
@@ -90,7 +90,9 @@ int ucache_bsize;
  */
 unsigned long __init early_init(unsigned long dt_ptr)
 {
+	extern unsigned int __start___ftr_fixup, __stop___ftr_fixup;
 	unsigned long offset = reloc_offset();
+	struct cpu_spec *spec;
 
 	/* First zero the BSS -- use memset_io, some platforms don't have
 	 * caches on yet */
@@ -100,8 +102,11 @@ unsigned long __init early_init(unsigned
 	 * Identify the CPU type and fix up code sections
 	 * that depend on which cpu we have.
 	 */
-	identify_cpu(offset, 0);
-	do_cpu_ftr_fixups(offset);
+	spec = identify_cpu(offset);
+
+	do_feature_fixups(offset, spec->cpu_features,
+			  PTRRELOC(&__start___ftr_fixup),
+			  PTRRELOC(&__stop___ftr_fixup));
 
 	return KERNELBASE + offset;
 }
Index: linux-cell/arch/powerpc/kernel/setup_64.c
===================================================================
--- linux-cell.orig/arch/powerpc/kernel/setup_64.c	2006-10-13 16:04:10.000000000 +1000
+++ linux-cell/arch/powerpc/kernel/setup_64.c	2006-10-13 16:42:44.000000000 +1000
@@ -170,6 +170,9 @@ void __init setup_paca(int cpu)
 
 void __init early_setup(unsigned long dt_ptr)
 {
+	/* Identify CPU type */
+	identify_cpu(0);
+
 	/* Assume we're on cpu 0 for now. Don't write to the paca yet! */
 	setup_paca(0);
 
@@ -346,8 +349,19 @@ static void __init initialize_cache_info
  */
 void __init setup_system(void)
 {
+	extern unsigned int __start___ftr_fixup, __stop___ftr_fixup;
+	extern unsigned int __start___fw_ftr_fixup, __stop___fw_ftr_fixup;
+
 	DBG(" -> setup_system()\n");
 
+	/* Apply the CPUs-specific and firmware specific fixups to kernel
+	 * text (nop out sections not relevant to this CPU or this firmware)
+	 */
+	do_feature_fixups(0, cur_cpu_spec->cpu_features,
+			  &__start___ftr_fixup, &__stop___ftr_fixup);
+	do_feature_fixups(0, powerpc_firmware_features,
+			  &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup);
+
 	/*
 	 * Unflatten the device-tree passed by prom_init or kexec
 	 */
Index: linux-cell/arch/powerpc/kernel/cputable.c
===================================================================
--- linux-cell.orig/arch/powerpc/kernel/cputable.c	2006-10-06 13:47:54.000000000 +1000
+++ linux-cell/arch/powerpc/kernel/cputable.c	2006-10-13 16:47:31.000000000 +1000
@@ -73,7 +73,7 @@ extern void __restore_cpu_ppc970(void);
 #define PPC_FEATURE_SPE_COMP	0
 #endif
 
-struct cpu_spec	cpu_specs[] = {
+static struct cpu_spec cpu_specs[] = {
 #ifdef CONFIG_PPC64
 	{	/* Power3 */
 		.pvr_mask		= 0xffff0000,
@@ -1152,3 +1152,25 @@ struct cpu_spec	cpu_specs[] = {
 #endif /* !CLASSIC_PPC */
 #endif /* CONFIG_PPC32 */
 };
+
+struct cpu_spec *identify_cpu(unsigned long offset)
+{
+	struct cpu_spec *s = cpu_specs;
+	struct cpu_spec **cur = &cur_cpu_spec;
+	unsigned int pvr = mfspr(SPRN_PVR);
+	int i;
+
+	s = PTRRELOC(s);
+	cur = PTRRELOC(cur);
+
+	if (*cur != NULL)
+		return PTRRELOC(*cur);
+
+	for (i = 0; i < ARRAY_SIZE(cpu_specs); i++,s++)
+		if ((pvr & s->pvr_mask) == s->pvr_value) {
+			*cur = cpu_specs + i;
+			return s;
+		}
+	BUG();
+	return NULL;
+}
Index: linux-cell/arch/powerpc/kernel/misc_32.S
===================================================================
--- linux-cell.orig/arch/powerpc/kernel/misc_32.S	2006-10-06 13:47:54.000000000 +1000
+++ linux-cell/arch/powerpc/kernel/misc_32.S	2006-10-13 16:26:43.000000000 +1000
@@ -102,80 +102,6 @@ _GLOBAL(reloc_got2)
 	blr
 
 /*
- * identify_cpu,
- * called with r3 = data offset and r4 = CPU number
- * doesn't change r3
- */
-_GLOBAL(identify_cpu)
-	addis	r8,r3,cpu_specs@ha
-	addi	r8,r8,cpu_specs@l
-	mfpvr	r7
-1:
-	lwz	r5,CPU_SPEC_PVR_MASK(r8)
-	and	r5,r5,r7
-	lwz	r6,CPU_SPEC_PVR_VALUE(r8)
-	cmplw	0,r6,r5
-	beq	1f
-	addi	r8,r8,CPU_SPEC_ENTRY_SIZE
-	b	1b
-1:
-	addis	r6,r3,cur_cpu_spec@ha
-	addi	r6,r6,cur_cpu_spec@l
-	sub	r8,r8,r3
-	stw	r8,0(r6)
-	blr
-
-/*
- * do_cpu_ftr_fixups - goes through the list of CPU feature fixups
- * and writes nop's over sections of code that don't apply for this cpu.
- * r3 = data offset (not changed)
- */
-_GLOBAL(do_cpu_ftr_fixups)
-	/* Get CPU 0 features */
-	addis	r6,r3,cur_cpu_spec@ha
-	addi	r6,r6,cur_cpu_spec@l
-	lwz	r4,0(r6)
-	add	r4,r4,r3
-	lwz	r4,CPU_SPEC_FEATURES(r4)
-
-	/* Get the fixup table */
-	addis	r6,r3,__start___ftr_fixup@ha
-	addi	r6,r6,__start___ftr_fixup@l
-	addis	r7,r3,__stop___ftr_fixup@ha
-	addi	r7,r7,__stop___ftr_fixup@l
-
-	/* Do the fixup */
-1:	cmplw	0,r6,r7
-	bgelr
-	addi	r6,r6,16
-	lwz	r8,-16(r6)	/* mask */
-	and	r8,r8,r4
-	lwz	r9,-12(r6)	/* value */
-	cmplw	0,r8,r9
-	beq	1b
-	lwz	r8,-8(r6)	/* section begin */
-	lwz	r9,-4(r6)	/* section end */
-	subf.	r9,r8,r9
-	beq	1b
-	/* write nops over the section of code */
-	/* todo: if large section, add a branch at the start of it */
-	srwi	r9,r9,2
-	mtctr	r9
-	add	r8,r8,r3
-	lis	r0,0x60000000@h	/* nop */
-3:	stw	r0,0(r8)
-	andi.	r10,r4,CPU_FTR_SPLIT_ID_CACHE@l
-	beq	2f
-	dcbst	0,r8		/* suboptimal, but simpler */
-	sync
-	icbi	0,r8
-2:	addi	r8,r8,4
-	bdnz	3b
-	sync			/* additional sync needed on g4 */
-	isync
-	b	1b
-
-/*
  * call_setup_cpu - call the setup_cpu function for this cpu
  * r3 = data offset, r24 = cpu number
  *
Index: linux-cell/include/asm-powerpc/cputable.h
===================================================================
--- linux-cell.orig/include/asm-powerpc/cputable.h	2006-10-13 16:00:28.000000000 +1000
+++ linux-cell/include/asm-powerpc/cputable.h	2006-10-13 16:19:51.000000000 +1000
@@ -89,8 +89,7 @@ struct cpu_spec {
 
 extern struct cpu_spec		*cur_cpu_spec;
 
-extern void identify_cpu(unsigned long offset, unsigned long cpu);
-extern void do_cpu_ftr_fixups(unsigned long offset);
+extern struct cpu_spec *identify_cpu(unsigned long offset);
 
 #endif /* __ASSEMBLY__ */
 
Index: linux-cell/include/asm-powerpc/system.h
===================================================================
--- linux-cell.orig/include/asm-powerpc/system.h	2006-10-06 13:48:24.000000000 +1000
+++ linux-cell/include/asm-powerpc/system.h	2006-10-13 16:24:45.000000000 +1000
@@ -378,7 +378,11 @@ extern unsigned long reloc_offset(void);
 extern unsigned long add_reloc_offset(unsigned long);
 extern void reloc_got2(unsigned long);
 
+#ifdef CONFIG_PPC64
+#define PTRRELOC(x)	x
+#else
 #define PTRRELOC(x)	((typeof(x)) add_reloc_offset((unsigned long)(x)))
+#endif
 
 static inline void create_instruction(unsigned long addr, unsigned int instr)
 {
Index: linux-cell/arch/powerpc/platforms/iseries/setup.c
===================================================================
--- linux-cell.orig/arch/powerpc/platforms/iseries/setup.c	2006-10-06 13:47:54.000000000 +1000
+++ linux-cell/arch/powerpc/platforms/iseries/setup.c	2006-10-13 16:49:14.000000000 +1000
@@ -694,6 +694,11 @@ void * __init iSeries_early_setup(void)
 {
 	unsigned long phys_mem_size;
 
+	/* Identify CPU type. This is done again by the common code later
+	 * on but calling this function multiple times is fine.
+	 */
+	identify_cpu(0);
+
 	powerpc_firmware_features |= FW_FEATURE_ISERIES;
 	powerpc_firmware_features |= FW_FEATURE_LPAR;
 

Re: [PATCH 1/5] powerpc: consolidate feature fixup code

[Olof Johansson]

On Fri, 13 Oct 2006 18:04:22 +1000 Benjamin Herrenschmidt <benh@kernel.crashing.org> wrote:

> There are currently two versions of the functions for applying the
> feature fixups, one for CPU features and one for firmware features. In
> addition, they are both in assembly and with separate implementations
> for 32 and 64 bits. identify_cpu() is also implemented in assembly and
> separately for 32 and 64 bits.
> 
> This patch replaces them with a pair of C functions. The call sites are
> slightly moved on ppc64 as well to be called from C instead of from
> assembly, though it's a very small change, and thus shouldn't cause any
> problem.
> 
> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> 
> 
> Index: linux-cell/arch/powerpc/kernel/head_64.S
> ===================================================================
> --- linux-cell.orig/arch/powerpc/kernel/head_64.S	2006-10-13 16:04:10.000000000 +1000
> +++ linux-cell/arch/powerpc/kernel/head_64.S	2006-10-13 16:43:05.000000000 +1000
> @@ -1580,11 +1580,6 @@ _STATIC(__start_initialization_iSeries)
>  	li	r0,0
>  	stdu	r0,-STACK_FRAME_OVERHEAD(r1)
>  
> -	LOAD_REG_IMMEDIATE(r3,cpu_specs)
> -	LOAD_REG_IMMEDIATE(r4,cur_cpu_spec)
> -	li	r5,0
> -	bl	.identify_cpu
> -
>  	LOAD_REG_IMMEDIATE(r2,__toc_start)
>  	addi	r2,r2,0x4000
>  	addi	r2,r2,0x4000
> @@ -1964,13 +1959,6 @@ _STATIC(start_here_multiplatform)
>  	addi	r2,r2,0x4000
>  	add	r2,r2,r26
>  
> -	LOAD_REG_IMMEDIATE(r3, cpu_specs)
> -	add	r3,r3,r26
> -	LOAD_REG_IMMEDIATE(r4,cur_cpu_spec)
> -	add	r4,r4,r26
> -	mr	r5,r26
> -	bl	.identify_cpu
> -
>  	/* Do very early kernel initializations, including initial hash table,
>  	 * stab and slb setup before we turn on relocation.	*/
>  
> @@ -2000,13 +1988,6 @@ _STATIC(start_here_common)
>  	li	r0,0
>  	stdu	r0,-STACK_FRAME_OVERHEAD(r1)
>  
> -	/* Apply the CPUs-specific fixups (nop out sections not relevant
> -	 * to this CPU
> -	 */
> -	li	r3,0
> -	bl	.do_cpu_ftr_fixups
> -	bl	.do_fw_ftr_fixups
> -
>  	/* ptr to current */
>  	LOAD_REG_IMMEDIATE(r4, init_task)
>  	std	r4,PACACURRENT(r13)
> Index: linux-cell/arch/powerpc/kernel/misc_64.S
> ===================================================================
> --- linux-cell.orig/arch/powerpc/kernel/misc_64.S	2006-10-13 16:04:10.000000000 +1000
> +++ linux-cell/arch/powerpc/kernel/misc_64.S	2006-10-13 16:40:14.000000000 +1000
> @@ -246,130 +246,6 @@ _GLOBAL(__flush_dcache_icache)
>  	isync
>  	blr
>  
> -/*
> - * identify_cpu and calls setup_cpu
> - * In:	r3 = base of the cpu_specs array
> - *	r4 = address of cur_cpu_spec
> - *	r5 = relocation offset
> - */
> -_GLOBAL(identify_cpu)
> -	mfpvr	r7
> -1:
> -	lwz	r8,CPU_SPEC_PVR_MASK(r3)
> -	and	r8,r8,r7
> -	lwz	r9,CPU_SPEC_PVR_VALUE(r3)
> -	cmplw	0,r9,r8
> -	beq	1f
> -	addi	r3,r3,CPU_SPEC_ENTRY_SIZE
> -	b	1b
> -1:
> -	sub	r0,r3,r5
> -	std	r0,0(r4)
> -	ld	r4,CPU_SPEC_SETUP(r3)
> -	cmpdi	0,r4,0
> -	add	r4,r4,r5
> -	beqlr
> -	ld	r4,0(r4)
> -	add	r4,r4,r5
> -	mtctr	r4
> -	/* Calling convention for cpu setup is r3=offset, r4=cur_cpu_spec */
> -	mr	r4,r3
> -	mr	r3,r5
> -	bctr
> -
> -/*
> - * do_cpu_ftr_fixups - goes through the list of CPU feature fixups
> - * and writes nop's over sections of code that don't apply for this cpu.
> - * r3 = data offset (not changed)
> - */
> -_GLOBAL(do_cpu_ftr_fixups)
> -	/* Get CPU 0 features */
> -	LOAD_REG_IMMEDIATE(r6,cur_cpu_spec)
> -	sub	r6,r6,r3
> -	ld	r4,0(r6)
> -	sub	r4,r4,r3
> -	ld	r4,CPU_SPEC_FEATURES(r4)
> -	/* Get the fixup table */
> -	LOAD_REG_IMMEDIATE(r6,__start___ftr_fixup)
> -	sub	r6,r6,r3
> -	LOAD_REG_IMMEDIATE(r7,__stop___ftr_fixup)
> -	sub	r7,r7,r3
> -	/* Do the fixup */
> -1:	cmpld	r6,r7
> -	bgelr
> -	addi	r6,r6,32
> -	ld	r8,-32(r6)	/* mask */
> -	and	r8,r8,r4
> -	ld	r9,-24(r6)	/* value */
> -	cmpld	r8,r9
> -	beq	1b
> -	ld	r8,-16(r6)	/* section begin */
> -	ld	r9,-8(r6)	/* section end */
> -	subf.	r9,r8,r9
> -	beq	1b
> -	/* write nops over the section of code */
> -	/* todo: if large section, add a branch at the start of it */
> -	srwi	r9,r9,2
> -	mtctr	r9
> -	sub	r8,r8,r3
> -	lis	r0,0x60000000@h	/* nop */
> -3:	stw	r0,0(r8)
> -	andi.	r10,r4,CPU_FTR_SPLIT_ID_CACHE@l
> -	beq	2f
> -	dcbst	0,r8		/* suboptimal, but simpler */
> -	sync
> -	icbi	0,r8
> -2:	addi	r8,r8,4
> -	bdnz	3b
> -	sync			/* additional sync needed on g4 */
> -	isync
> -	b	1b
> -
> -/*
> - * do_fw_ftr_fixups - goes through the list of firmware feature fixups
> - * and writes nop's over sections of code that don't apply for this firmware.
> - * r3 = data offset (not changed)
> - */
> -_GLOBAL(do_fw_ftr_fixups)
> -	/* Get firmware features */
> -	LOAD_REG_IMMEDIATE(r6,powerpc_firmware_features)
> -	sub	r6,r6,r3
> -	ld	r4,0(r6)
> -	/* Get the fixup table */
> -	LOAD_REG_IMMEDIATE(r6,__start___fw_ftr_fixup)
> -	sub	r6,r6,r3
> -	LOAD_REG_IMMEDIATE(r7,__stop___fw_ftr_fixup)
> -	sub	r7,r7,r3
> -	/* Do the fixup */
> -1:	cmpld	r6,r7
> -	bgelr
> -	addi	r6,r6,32
> -	ld	r8,-32(r6)	/* mask */
> -	and	r8,r8,r4
> -	ld	r9,-24(r6)	/* value */
> -	cmpld	r8,r9
> -	beq	1b
> -	ld	r8,-16(r6)	/* section begin */
> -	ld	r9,-8(r6)	/* section end */
> -	subf.	r9,r8,r9
> -	beq	1b
> -	/* write nops over the section of code */
> -	/* todo: if large section, add a branch at the start of it */
> -	srwi	r9,r9,2
> -	mtctr	r9
> -	sub	r8,r8,r3
> -	lis	r0,0x60000000@h	/* nop */
> -3:	stw	r0,0(r8)
> -BEGIN_FTR_SECTION
> -	dcbst	0,r8		/* suboptimal, but simpler */
> -	sync
> -	icbi	0,r8
> -END_FTR_SECTION_IFSET(CPU_FTR_SPLIT_ID_CACHE)
> -	addi	r8,r8,4
> -	bdnz	3b
> -	sync			/* additional sync needed on g4 */
> -	isync
> -	b	1b
>  
>  #if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE)
>  /*
> Index: linux-cell/arch/powerpc/kernel/setup-common.c
> ===================================================================
> --- linux-cell.orig/arch/powerpc/kernel/setup-common.c	2006-10-13 16:04:10.000000000 +1000
> +++ linux-cell/arch/powerpc/kernel/setup-common.c	2006-10-13 16:39:03.000000000 +1000
> @@ -520,3 +520,39 @@ void __init setup_panic(void)
>  {
>  	atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block);
>  }
> +
> +void do_feature_fixups(unsigned long offset, unsigned long value,
> +		       void *fixup_start, void *fixup_end)
> +{
> +	struct fixup_entry {
> +		unsigned long	mask;
> +		unsigned long	value;
> +		unsigned int	*start;
> +		unsigned int	*end;
> +	} *fcur, *fend;
> +
> +	fcur = fixup_start;
> +	fend = fixup_end;
> +
> +	for (; fcur < fend; fcur++) {
> +		unsigned int *pstart, *pend, *p;
> +
> +		if ((value & fcur->mask) == fcur->value)
> +			continue;
> +
> +		/* These PTRRELOCs will disappear once the new scheme for
> +		 * modules and vdso is implemented
> +		 */
> +		pstart = PTRRELOC(fcur->start);
> +		pend = PTRRELOC(fcur->end);
> +
> +		for (p = pstart; p < pend; p++) {
> +			*p = 0x60000000u;
> +			asm volatile ("dcbst 0, %0" : : "r" (p));
> +		}
> +		asm volatile ("sync" : : : "memory");
> +		for (p = pstart; p < pend; p++)
> +			asm volatile ("icbi 0,%0" : : "r" (p));
> +		asm volatile ("sync; isync" : : : "memory");

You can advance the pointer with L1_CACHE_BYTES/sizeof(int) per
iteration in the second loop here.

> +	}
> +}
> Index: linux-cell/arch/powerpc/kernel/setup.h
> ===================================================================
> --- linux-cell.orig/arch/powerpc/kernel/setup.h	2006-10-13 16:04:10.000000000 +1000
> +++ linux-cell/arch/powerpc/kernel/setup.h	2006-10-13 16:06:24.000000000 +1000
> @@ -1,9 +1,12 @@
>  #ifndef _POWERPC_KERNEL_SETUP_H
>  #define _POWERPC_KERNEL_SETUP_H
>  
> -void check_for_initrd(void);
> -void do_init_bootmem(void);
> -void setup_panic(void);
> +extern void check_for_initrd(void);
> +extern void do_init_bootmem(void);
> +extern void setup_panic(void);
> +extern void do_feature_fixups(unsigned long offset, unsigned long value,
> +			      void *fixup_start, void *fixup_end);
> +
>  extern int do_early_xmon;
>  
>  #endif /* _POWERPC_KERNEL_SETUP_H */
> Index: linux-cell/arch/powerpc/kernel/setup_32.c
> ===================================================================
> --- linux-cell.orig/arch/powerpc/kernel/setup_32.c	2006-10-13 16:04:10.000000000 +1000
> +++ linux-cell/arch/powerpc/kernel/setup_32.c	2006-10-13 16:38:21.000000000 +1000
> @@ -90,7 +90,9 @@ int ucache_bsize;
>   */
>  unsigned long __init early_init(unsigned long dt_ptr)
>  {
> +	extern unsigned int __start___ftr_fixup, __stop___ftr_fixup;
>  	unsigned long offset = reloc_offset();
> +	struct cpu_spec *spec;
>  
>  	/* First zero the BSS -- use memset_io, some platforms don't have
>  	 * caches on yet */
> @@ -100,8 +102,11 @@ unsigned long __init early_init(unsigned
>  	 * Identify the CPU type and fix up code sections
>  	 * that depend on which cpu we have.
>  	 */
> -	identify_cpu(offset, 0);
> -	do_cpu_ftr_fixups(offset);
> +	spec = identify_cpu(offset);
> +
> +	do_feature_fixups(offset, spec->cpu_features,
> +			  PTRRELOC(&__start___ftr_fixup),
> +			  PTRRELOC(&__stop___ftr_fixup));
>  
>  	return KERNELBASE + offset;
>  }
> Index: linux-cell/arch/powerpc/kernel/setup_64.c
> ===================================================================
> --- linux-cell.orig/arch/powerpc/kernel/setup_64.c	2006-10-13 16:04:10.000000000 +1000
> +++ linux-cell/arch/powerpc/kernel/setup_64.c	2006-10-13 16:42:44.000000000 +1000
> @@ -170,6 +170,9 @@ void __init setup_paca(int cpu)
>  
>  void __init early_setup(unsigned long dt_ptr)
>  {
> +	/* Identify CPU type */
> +	identify_cpu(0);
> +
>  	/* Assume we're on cpu 0 for now. Don't write to the paca yet! */
>  	setup_paca(0);
>  
> @@ -346,8 +349,19 @@ static void __init initialize_cache_info
>   */
>  void __init setup_system(void)
>  {
> +	extern unsigned int __start___ftr_fixup, __stop___ftr_fixup;
> +	extern unsigned int __start___fw_ftr_fixup, __stop___fw_ftr_fixup;
> +
>  	DBG(" -> setup_system()\n");
>  
> +	/* Apply the CPUs-specific and firmware specific fixups to kernel
> +	 * text (nop out sections not relevant to this CPU or this firmware)
> +	 */
> +	do_feature_fixups(0, cur_cpu_spec->cpu_features,
> +			  &__start___ftr_fixup, &__stop___ftr_fixup);
> +	do_feature_fixups(0, powerpc_firmware_features,
> +			  &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup);
> +
>  	/*
>  	 * Unflatten the device-tree passed by prom_init or kexec
>  	 */
> Index: linux-cell/arch/powerpc/kernel/cputable.c
> ===================================================================
> --- linux-cell.orig/arch/powerpc/kernel/cputable.c	2006-10-06 13:47:54.000000000 +1000
> +++ linux-cell/arch/powerpc/kernel/cputable.c	2006-10-13 16:47:31.000000000 +1000
> @@ -73,7 +73,7 @@ extern void __restore_cpu_ppc970(void);
>  #define PPC_FEATURE_SPE_COMP	0
>  #endif
>  
> -struct cpu_spec	cpu_specs[] = {
> +static struct cpu_spec cpu_specs[] = {
>  #ifdef CONFIG_PPC64
>  	{	/* Power3 */
>  		.pvr_mask		= 0xffff0000,
> @@ -1152,3 +1152,25 @@ struct cpu_spec	cpu_specs[] = {
>  #endif /* !CLASSIC_PPC */
>  #endif /* CONFIG_PPC32 */
>  };
> +
> +struct cpu_spec *identify_cpu(unsigned long offset)
> +{
> +	struct cpu_spec *s = cpu_specs;
> +	struct cpu_spec **cur = &cur_cpu_spec;
> +	unsigned int pvr = mfspr(SPRN_PVR);
> +	int i;
> +
> +	s = PTRRELOC(s);
> +	cur = PTRRELOC(cur);
> +
> +	if (*cur != NULL)
> +		return PTRRELOC(*cur);
> +
> +	for (i = 0; i < ARRAY_SIZE(cpu_specs); i++,s++)
> +		if ((pvr & s->pvr_mask) == s->pvr_value) {
> +			*cur = cpu_specs + i;
> +			return s;
> +		}
> +	BUG();
> +	return NULL;
> +}
> Index: linux-cell/arch/powerpc/kernel/misc_32.S
> ===================================================================
> --- linux-cell.orig/arch/powerpc/kernel/misc_32.S	2006-10-06 13:47:54.000000000 +1000
> +++ linux-cell/arch/powerpc/kernel/misc_32.S	2006-10-13 16:26:43.000000000 +1000
> @@ -102,80 +102,6 @@ _GLOBAL(reloc_got2)
>  	blr
>  
>  /*
> - * identify_cpu,
> - * called with r3 = data offset and r4 = CPU number
> - * doesn't change r3
> - */
> -_GLOBAL(identify_cpu)
> -	addis	r8,r3,cpu_specs@ha
> -	addi	r8,r8,cpu_specs@l
> -	mfpvr	r7
> -1:
> -	lwz	r5,CPU_SPEC_PVR_MASK(r8)
> -	and	r5,r5,r7
> -	lwz	r6,CPU_SPEC_PVR_VALUE(r8)
> -	cmplw	0,r6,r5
> -	beq	1f
> -	addi	r8,r8,CPU_SPEC_ENTRY_SIZE
> -	b	1b
> -1:
> -	addis	r6,r3,cur_cpu_spec@ha
> -	addi	r6,r6,cur_cpu_spec@l
> -	sub	r8,r8,r3
> -	stw	r8,0(r6)
> -	blr
> -
> -/*
> - * do_cpu_ftr_fixups - goes through the list of CPU feature fixups
> - * and writes nop's over sections of code that don't apply for this cpu.
> - * r3 = data offset (not changed)
> - */
> -_GLOBAL(do_cpu_ftr_fixups)
> -	/* Get CPU 0 features */
> -	addis	r6,r3,cur_cpu_spec@ha
> -	addi	r6,r6,cur_cpu_spec@l
> -	lwz	r4,0(r6)
> -	add	r4,r4,r3
> -	lwz	r4,CPU_SPEC_FEATURES(r4)
> -
> -	/* Get the fixup table */
> -	addis	r6,r3,__start___ftr_fixup@ha
> -	addi	r6,r6,__start___ftr_fixup@l
> -	addis	r7,r3,__stop___ftr_fixup@ha
> -	addi	r7,r7,__stop___ftr_fixup@l
> -
> -	/* Do the fixup */
> -1:	cmplw	0,r6,r7
> -	bgelr
> -	addi	r6,r6,16
> -	lwz	r8,-16(r6)	/* mask */
> -	and	r8,r8,r4
> -	lwz	r9,-12(r6)	/* value */
> -	cmplw	0,r8,r9
> -	beq	1b
> -	lwz	r8,-8(r6)	/* section begin */
> -	lwz	r9,-4(r6)	/* section end */
> -	subf.	r9,r8,r9
> -	beq	1b
> -	/* write nops over the section of code */
> -	/* todo: if large section, add a branch at the start of it */
> -	srwi	r9,r9,2
> -	mtctr	r9
> -	add	r8,r8,r3
> -	lis	r0,0x60000000@h	/* nop */
> -3:	stw	r0,0(r8)
> -	andi.	r10,r4,CPU_FTR_SPLIT_ID_CACHE@l
> -	beq	2f
> -	dcbst	0,r8		/* suboptimal, but simpler */
> -	sync
> -	icbi	0,r8
> -2:	addi	r8,r8,4
> -	bdnz	3b
> -	sync			/* additional sync needed on g4 */
> -	isync
> -	b	1b
> -
> -/*
>   * call_setup_cpu - call the setup_cpu function for this cpu
>   * r3 = data offset, r24 = cpu number
>   *
> Index: linux-cell/include/asm-powerpc/cputable.h
> ===================================================================
> --- linux-cell.orig/include/asm-powerpc/cputable.h	2006-10-13 16:00:28.000000000 +1000
> +++ linux-cell/include/asm-powerpc/cputable.h	2006-10-13 16:19:51.000000000 +1000
> @@ -89,8 +89,7 @@ struct cpu_spec {
>  
>  extern struct cpu_spec		*cur_cpu_spec;
>  
> -extern void identify_cpu(unsigned long offset, unsigned long cpu);
> -extern void do_cpu_ftr_fixups(unsigned long offset);
> +extern struct cpu_spec *identify_cpu(unsigned long offset);
>  
>  #endif /* __ASSEMBLY__ */
>  
> Index: linux-cell/include/asm-powerpc/system.h
> ===================================================================
> --- linux-cell.orig/include/asm-powerpc/system.h	2006-10-06 13:48:24.000000000 +1000
> +++ linux-cell/include/asm-powerpc/system.h	2006-10-13 16:24:45.000000000 +1000
> @@ -378,7 +378,11 @@ extern unsigned long reloc_offset(void);
>  extern unsigned long add_reloc_offset(unsigned long);
>  extern void reloc_got2(unsigned long);
>  
> +#ifdef CONFIG_PPC64
> +#define PTRRELOC(x)	x
> +#else
>  #define PTRRELOC(x)	((typeof(x)) add_reloc_offset((unsigned long)(x)))
> +#endif
>  
>  static inline void create_instruction(unsigned long addr, unsigned int instr)
>  {
> Index: linux-cell/arch/powerpc/platforms/iseries/setup.c
> ===================================================================
> --- linux-cell.orig/arch/powerpc/platforms/iseries/setup.c	2006-10-06 13:47:54.000000000 +1000
> +++ linux-cell/arch/powerpc/platforms/iseries/setup.c	2006-10-13 16:49:14.000000000 +1000
> @@ -694,6 +694,11 @@ void * __init iSeries_early_setup(void)
>  {
>  	unsigned long phys_mem_size;
>  
> +	/* Identify CPU type. This is done again by the common code later
> +	 * on but calling this function multiple times is fine.
> +	 */
> +	identify_cpu(0);
> +
>  	powerpc_firmware_features |= FW_FEATURE_ISERIES;
>  	powerpc_firmware_features |= FW_FEATURE_LPAR;
>  
> 
> 
> 
> _______________________________________________
> Linuxppc-dev mailing list
> Linuxppc-dev@ozlabs.org
> https://ozlabs.org/mailman/listinfo/linuxppc-dev

Re: [PATCH 1/5] powerpc: consolidate feature fixup code

[Benjamin Herrenschmidt]

> You can advance the pointer with L1_CACHE_BYTES/sizeof(int) per
> iteration in the second loop here.

Yeah, I suppose so. Though I'm not 100% confident we get L1_CACHE_BYTES
on all cpus, for example, PA6T is 64 bytes ;) We could use
cur_cpu_spec->icache_bsize but that would involve ugly RELOC's to get it
right on 32 bits. I decided not to care for now.

Ben.

Re: [PATCH 1/5] powerpc: consolidate feature fixup code

[Stephen Rothwell]

[-- Attachment #1: Type: text/plain, Size: 435 bytes --]

Hi Olof,

On Fri, 13 Oct 2006 11:54:57 -0500 Olof Johansson <olof@lixom.net> wrote:
>
... lots of stuff deleted ...

Could you please trim your replies to just areasonable amount of context,
please. You are not the only one who is at fault here, but yours was the
example that came my way just as I needed to point out the problem.

--
Cheers,
Stephen Rothwell                    sfr@canb.auug.org.au
http://www.canb.auug.org.au/~sfr/

[-- Attachment #2: Type: application/pgp-signature, Size: 189 bytes --]

Re: [PATCH 1/5] powerpc: consolidate feature fixup code

[Olof Johansson]

On Sat, 14 Oct 2006 11:42:59 +1000 Stephen Rothwell <sfr@canb.auug.org.au> wrote:

> Hi Olof,
> 
> On Fri, 13 Oct 2006 11:54:57 -0500 Olof Johansson <olof@lixom.net> wrote:
> >
> ... lots of stuff deleted ...
> 
> Could you please trim your replies to just areasonable amount of context,
> please. You are not the only one who is at fault here, but yours was the
> example that came my way just as I needed to point out the problem.

I normally try to do it, I think I might have been sloppy lately.
Thanks for the reminder.


-Olof

Re: [PATCH 1/5] powerpc: consolidate feature fixup code

[Olof Johansson]

On Sat, 14 Oct 2006 08:36:46 +1000 Benjamin Herrenschmidt <benh@kernel.crashing.org> wrote:

> 
> > You can advance the pointer with L1_CACHE_BYTES/sizeof(int) per
> > iteration in the second loop here.
> 
> Yeah, I suppose so. Though I'm not 100% confident we get L1_CACHE_BYTES
> on all cpus, for example, PA6T is 64 bytes ;) We could use
> cur_cpu_spec->icache_bsize but that would involve ugly RELOC's to get it
> right on 32 bits. I decided not to care for now.

Ugh, yeah, I remember this when I did the patches but forgot about it
now. L1_CACHE_BYTES is used in a number of places, but overall used as
the largest value needed to bump between lines to avoid false sharing.

The other early places seems to have used hardcoded constants. I guess
it's better to just loop over every word like you're already doing. It
still avoids a barrier on every iteration.


-Olof

Re: [PATCH 1/5] powerpc: consolidate feature fixup code

[Olof Johansson]

On Fri, 13 Oct 2006 18:04:22 +1000 Benjamin Herrenschmidt <benh@kernel.crashing.org> wrote:

> There are currently two versions of the functions for applying the
> feature fixups, one for CPU features and one for firmware features. In
> addition, they are both in assembly and with separate implementations
> for 32 and 64 bits. identify_cpu() is also implemented in assembly and
> separately for 32 and 64 bits.
> 
> This patch replaces them with a pair of C functions. The call sites are
> slightly moved on ppc64 as well to be called from C instead of from
> assembly, though it's a very small change, and thus shouldn't cause any
> problem.
> 
> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

Acked-by: Olof Johansson <olof@lixom.net>

Re: [PATCH 1/5] powerpc: consolidate feature fixup code

[Benjamin Herrenschmidt]

On Fri, 2006-10-13 at 18:04 +1000, Benjamin Herrenschmidt wrote:
>  
> Index: linux-cell/include/asm-powerpc/system.h
> ===================================================================
> --- linux-cell.orig/include/asm-powerpc/system.h        2006-10-06 13:48:24.000000000 +1000
> +++ linux-cell/include/asm-powerpc/system.h     2006-10-13 16:24:45.000000000 +1000
> @@ -378,7 +378,11 @@ extern unsigned long reloc_offset(void);
>  extern unsigned long add_reloc_offset(unsigned long);
>  extern void reloc_got2(unsigned long);
>  
> +#ifdef CONFIG_PPC64
> +#define PTRRELOC(x)    x
> +#else
>  #define PTRRELOC(x)    ((typeof(x)) add_reloc_offset((unsigned long)(x)))
> +#endif
>  
>  static inline void create_instruction(unsigned long addr, unsigned int instr)
>  {

And of course that bit of the patch is a stupid "optimisation" that
breaks prom_init.c on ppc64... I'll post a new patch without it and do
more tests (damn, I tested iSeries and figured if it worked there, it
would work everywhere :)

Ben.

[PATCH 1/5] powerpc: consolidate feature fixup code

[Benjamin Herrenschmidt]

There are currently two versions of the functions for applying the
feature fixups, one for CPU features and one for firmware features. In
addition, they are both in assembly and with separate implementations
for 32 and 64 bits. identify_cpu() is also implemented in assembly and
separately for 32 and 64 bits.

This patch replaces them with a pair of C functions. The call sites are
slightly moved on ppc64 as well to be called from C instead of from
assembly, though it's a very small change, and thus shouldn't cause any
problem.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

Index: linux-cell/arch/powerpc/kernel/head_64.S
===================================================================
--- linux-cell.orig/arch/powerpc/kernel/head_64.S	2006-10-13 16:04:10.000000000 +1000
+++ linux-cell/arch/powerpc/kernel/head_64.S	2006-10-13 16:43:05.000000000 +1000
@@ -1580,11 +1580,6 @@ _STATIC(__start_initialization_iSeries)
 	li	r0,0
 	stdu	r0,-STACK_FRAME_OVERHEAD(r1)
 
-	LOAD_REG_IMMEDIATE(r3,cpu_specs)
-	LOAD_REG_IMMEDIATE(r4,cur_cpu_spec)
-	li	r5,0
-	bl	.identify_cpu
-
 	LOAD_REG_IMMEDIATE(r2,__toc_start)
 	addi	r2,r2,0x4000
 	addi	r2,r2,0x4000
@@ -1964,13 +1959,6 @@ _STATIC(start_here_multiplatform)
 	addi	r2,r2,0x4000
 	add	r2,r2,r26
 
-	LOAD_REG_IMMEDIATE(r3, cpu_specs)
-	add	r3,r3,r26
-	LOAD_REG_IMMEDIATE(r4,cur_cpu_spec)
-	add	r4,r4,r26
-	mr	r5,r26
-	bl	.identify_cpu
-
 	/* Do very early kernel initializations, including initial hash table,
 	 * stab and slb setup before we turn on relocation.	*/
 
@@ -2000,13 +1988,6 @@ _STATIC(start_here_common)
 	li	r0,0
 	stdu	r0,-STACK_FRAME_OVERHEAD(r1)
 
-	/* Apply the CPUs-specific fixups (nop out sections not relevant
-	 * to this CPU
-	 */
-	li	r3,0
-	bl	.do_cpu_ftr_fixups
-	bl	.do_fw_ftr_fixups
-
 	/* ptr to current */
 	LOAD_REG_IMMEDIATE(r4, init_task)
 	std	r4,PACACURRENT(r13)
Index: linux-cell/arch/powerpc/kernel/misc_64.S
===================================================================
--- linux-cell.orig/arch/powerpc/kernel/misc_64.S	2006-10-13 16:04:10.000000000 +1000
+++ linux-cell/arch/powerpc/kernel/misc_64.S	2006-10-13 16:40:14.000000000 +1000
@@ -246,130 +246,6 @@ _GLOBAL(__flush_dcache_icache)
 	isync
 	blr
 
-/*
- * identify_cpu and calls setup_cpu
- * In:	r3 = base of the cpu_specs array
- *	r4 = address of cur_cpu_spec
- *	r5 = relocation offset
- */
-_GLOBAL(identify_cpu)
-	mfpvr	r7
-1:
-	lwz	r8,CPU_SPEC_PVR_MASK(r3)
-	and	r8,r8,r7
-	lwz	r9,CPU_SPEC_PVR_VALUE(r3)
-	cmplw	0,r9,r8
-	beq	1f
-	addi	r3,r3,CPU_SPEC_ENTRY_SIZE
-	b	1b
-1:
-	sub	r0,r3,r5
-	std	r0,0(r4)
-	ld	r4,CPU_SPEC_SETUP(r3)
-	cmpdi	0,r4,0
-	add	r4,r4,r5
-	beqlr
-	ld	r4,0(r4)
-	add	r4,r4,r5
-	mtctr	r4
-	/* Calling convention for cpu setup is r3=offset, r4=cur_cpu_spec */
-	mr	r4,r3
-	mr	r3,r5
-	bctr
-
-/*
- * do_cpu_ftr_fixups - goes through the list of CPU feature fixups
- * and writes nop's over sections of code that don't apply for this cpu.
- * r3 = data offset (not changed)
- */
-_GLOBAL(do_cpu_ftr_fixups)
-	/* Get CPU 0 features */
-	LOAD_REG_IMMEDIATE(r6,cur_cpu_spec)
-	sub	r6,r6,r3
-	ld	r4,0(r6)
-	sub	r4,r4,r3
-	ld	r4,CPU_SPEC_FEATURES(r4)
-	/* Get the fixup table */
-	LOAD_REG_IMMEDIATE(r6,__start___ftr_fixup)
-	sub	r6,r6,r3
-	LOAD_REG_IMMEDIATE(r7,__stop___ftr_fixup)
-	sub	r7,r7,r3
-	/* Do the fixup */
-1:	cmpld	r6,r7
-	bgelr
-	addi	r6,r6,32
-	ld	r8,-32(r6)	/* mask */
-	and	r8,r8,r4
-	ld	r9,-24(r6)	/* value */
-	cmpld	r8,r9
-	beq	1b
-	ld	r8,-16(r6)	/* section begin */
-	ld	r9,-8(r6)	/* section end */
-	subf.	r9,r8,r9
-	beq	1b
-	/* write nops over the section of code */
-	/* todo: if large section, add a branch at the start of it */
-	srwi	r9,r9,2
-	mtctr	r9
-	sub	r8,r8,r3
-	lis	r0,0x60000000@h	/* nop */
-3:	stw	r0,0(r8)
-	andi.	r10,r4,CPU_FTR_SPLIT_ID_CACHE@l
-	beq	2f
-	dcbst	0,r8		/* suboptimal, but simpler */
-	sync
-	icbi	0,r8
-2:	addi	r8,r8,4
-	bdnz	3b
-	sync			/* additional sync needed on g4 */
-	isync
-	b	1b
-
-/*
- * do_fw_ftr_fixups - goes through the list of firmware feature fixups
- * and writes nop's over sections of code that don't apply for this firmware.
- * r3 = data offset (not changed)
- */
-_GLOBAL(do_fw_ftr_fixups)
-	/* Get firmware features */
-	LOAD_REG_IMMEDIATE(r6,powerpc_firmware_features)
-	sub	r6,r6,r3
-	ld	r4,0(r6)
-	/* Get the fixup table */
-	LOAD_REG_IMMEDIATE(r6,__start___fw_ftr_fixup)
-	sub	r6,r6,r3
-	LOAD_REG_IMMEDIATE(r7,__stop___fw_ftr_fixup)
-	sub	r7,r7,r3
-	/* Do the fixup */
-1:	cmpld	r6,r7
-	bgelr
-	addi	r6,r6,32
-	ld	r8,-32(r6)	/* mask */
-	and	r8,r8,r4
-	ld	r9,-24(r6)	/* value */
-	cmpld	r8,r9
-	beq	1b
-	ld	r8,-16(r6)	/* section begin */
-	ld	r9,-8(r6)	/* section end */
-	subf.	r9,r8,r9
-	beq	1b
-	/* write nops over the section of code */
-	/* todo: if large section, add a branch at the start of it */
-	srwi	r9,r9,2
-	mtctr	r9
-	sub	r8,r8,r3
-	lis	r0,0x60000000@h	/* nop */
-3:	stw	r0,0(r8)
-BEGIN_FTR_SECTION
-	dcbst	0,r8		/* suboptimal, but simpler */
-	sync
-	icbi	0,r8
-END_FTR_SECTION_IFSET(CPU_FTR_SPLIT_ID_CACHE)
-	addi	r8,r8,4
-	bdnz	3b
-	sync			/* additional sync needed on g4 */
-	isync
-	b	1b
 
 #if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE)
 /*
Index: linux-cell/arch/powerpc/kernel/setup-common.c
===================================================================
--- linux-cell.orig/arch/powerpc/kernel/setup-common.c	2006-10-13 16:04:10.000000000 +1000
+++ linux-cell/arch/powerpc/kernel/setup-common.c	2006-10-13 16:39:03.000000000 +1000
@@ -520,3 +520,39 @@ void __init setup_panic(void)
 {
 	atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block);
 }
+
+void do_feature_fixups(unsigned long offset, unsigned long value,
+		       void *fixup_start, void *fixup_end)
+{
+	struct fixup_entry {
+		unsigned long	mask;
+		unsigned long	value;
+		unsigned int	*start;
+		unsigned int	*end;
+	} *fcur, *fend;
+
+	fcur = fixup_start;
+	fend = fixup_end;
+
+	for (; fcur < fend; fcur++) {
+		unsigned int *pstart, *pend, *p;
+
+		if ((value & fcur->mask) == fcur->value)
+			continue;
+
+		/* These PTRRELOCs will disappear once the new scheme for
+		 * modules and vdso is implemented
+		 */
+		pstart = PTRRELOC(fcur->start);
+		pend = PTRRELOC(fcur->end);
+
+		for (p = pstart; p < pend; p++) {
+			*p = 0x60000000u;
+			asm volatile ("dcbst 0, %0" : : "r" (p));
+		}
+		asm volatile ("sync" : : : "memory");
+		for (p = pstart; p < pend; p++)
+			asm volatile ("icbi 0,%0" : : "r" (p));
+		asm volatile ("sync; isync" : : : "memory");
+	}
+}
Index: linux-cell/arch/powerpc/kernel/setup.h
===================================================================
--- linux-cell.orig/arch/powerpc/kernel/setup.h	2006-10-13 16:04:10.000000000 +1000
+++ linux-cell/arch/powerpc/kernel/setup.h	2006-10-13 16:06:24.000000000 +1000
@@ -1,9 +1,12 @@
 #ifndef _POWERPC_KERNEL_SETUP_H
 #define _POWERPC_KERNEL_SETUP_H
 
-void check_for_initrd(void);
-void do_init_bootmem(void);
-void setup_panic(void);
+extern void check_for_initrd(void);
+extern void do_init_bootmem(void);
+extern void setup_panic(void);
+extern void do_feature_fixups(unsigned long offset, unsigned long value,
+			      void *fixup_start, void *fixup_end);
+
 extern int do_early_xmon;
 
 #endif /* _POWERPC_KERNEL_SETUP_H */
Index: linux-cell/arch/powerpc/kernel/setup_32.c
===================================================================
--- linux-cell.orig/arch/powerpc/kernel/setup_32.c	2006-10-13 16:04:10.000000000 +1000
+++ linux-cell/arch/powerpc/kernel/setup_32.c	2006-10-13 16:38:21.000000000 +1000
@@ -90,7 +90,9 @@ int ucache_bsize;
  */
 unsigned long __init early_init(unsigned long dt_ptr)
 {
+	extern unsigned int __start___ftr_fixup, __stop___ftr_fixup;
 	unsigned long offset = reloc_offset();
+	struct cpu_spec *spec;
 
 	/* First zero the BSS -- use memset_io, some platforms don't have
 	 * caches on yet */
@@ -100,8 +102,11 @@ unsigned long __init early_init(unsigned
 	 * Identify the CPU type and fix up code sections
 	 * that depend on which cpu we have.
 	 */
-	identify_cpu(offset, 0);
-	do_cpu_ftr_fixups(offset);
+	spec = identify_cpu(offset);
+
+	do_feature_fixups(offset, spec->cpu_features,
+			  PTRRELOC(&__start___ftr_fixup),
+			  PTRRELOC(&__stop___ftr_fixup));
 
 	return KERNELBASE + offset;
 }
Index: linux-cell/arch/powerpc/kernel/setup_64.c
===================================================================
--- linux-cell.orig/arch/powerpc/kernel/setup_64.c	2006-10-13 16:04:10.000000000 +1000
+++ linux-cell/arch/powerpc/kernel/setup_64.c	2006-10-13 16:42:44.000000000 +1000
@@ -170,6 +170,9 @@ void __init setup_paca(int cpu)
 
 void __init early_setup(unsigned long dt_ptr)
 {
+	/* Identify CPU type */
+	identify_cpu(0);
+
 	/* Assume we're on cpu 0 for now. Don't write to the paca yet! */
 	setup_paca(0);
 
@@ -346,8 +349,19 @@ static void __init initialize_cache_info
  */
 void __init setup_system(void)
 {
+	extern unsigned int __start___ftr_fixup, __stop___ftr_fixup;
+	extern unsigned int __start___fw_ftr_fixup, __stop___fw_ftr_fixup;
+
 	DBG(" -> setup_system()\n");
 
+	/* Apply the CPUs-specific and firmware specific fixups to kernel
+	 * text (nop out sections not relevant to this CPU or this firmware)
+	 */
+	do_feature_fixups(0, cur_cpu_spec->cpu_features,
+			  &__start___ftr_fixup, &__stop___ftr_fixup);
+	do_feature_fixups(0, powerpc_firmware_features,
+			  &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup);
+
 	/*
 	 * Unflatten the device-tree passed by prom_init or kexec
 	 */
Index: linux-cell/arch/powerpc/kernel/cputable.c
===================================================================
--- linux-cell.orig/arch/powerpc/kernel/cputable.c	2006-10-06 13:47:54.000000000 +1000
+++ linux-cell/arch/powerpc/kernel/cputable.c	2006-10-13 16:47:31.000000000 +1000
@@ -73,7 +73,7 @@ extern void __restore_cpu_ppc970(void);
 #define PPC_FEATURE_SPE_COMP	0
 #endif
 
-struct cpu_spec	cpu_specs[] = {
+static struct cpu_spec cpu_specs[] = {
 #ifdef CONFIG_PPC64
 	{	/* Power3 */
 		.pvr_mask		= 0xffff0000,
@@ -1152,3 +1152,25 @@ struct cpu_spec	cpu_specs[] = {
 #endif /* !CLASSIC_PPC */
 #endif /* CONFIG_PPC32 */
 };
+
+struct cpu_spec *identify_cpu(unsigned long offset)
+{
+	struct cpu_spec *s = cpu_specs;
+	struct cpu_spec **cur = &cur_cpu_spec;
+	unsigned int pvr = mfspr(SPRN_PVR);
+	int i;
+
+	s = PTRRELOC(s);
+	cur = PTRRELOC(cur);
+
+	if (*cur != NULL)
+		return PTRRELOC(*cur);
+
+	for (i = 0; i < ARRAY_SIZE(cpu_specs); i++,s++)
+		if ((pvr & s->pvr_mask) == s->pvr_value) {
+			*cur = cpu_specs + i;
+			return s;
+		}
+	BUG();
+	return NULL;
+}
Index: linux-cell/arch/powerpc/kernel/misc_32.S
===================================================================
--- linux-cell.orig/arch/powerpc/kernel/misc_32.S	2006-10-06 13:47:54.000000000 +1000
+++ linux-cell/arch/powerpc/kernel/misc_32.S	2006-10-13 16:26:43.000000000 +1000
@@ -102,80 +102,6 @@ _GLOBAL(reloc_got2)
 	blr
 
 /*
- * identify_cpu,
- * called with r3 = data offset and r4 = CPU number
- * doesn't change r3
- */
-_GLOBAL(identify_cpu)
-	addis	r8,r3,cpu_specs@ha
-	addi	r8,r8,cpu_specs@l
-	mfpvr	r7
-1:
-	lwz	r5,CPU_SPEC_PVR_MASK(r8)
-	and	r5,r5,r7
-	lwz	r6,CPU_SPEC_PVR_VALUE(r8)
-	cmplw	0,r6,r5
-	beq	1f
-	addi	r8,r8,CPU_SPEC_ENTRY_SIZE
-	b	1b
-1:
-	addis	r6,r3,cur_cpu_spec@ha
-	addi	r6,r6,cur_cpu_spec@l
-	sub	r8,r8,r3
-	stw	r8,0(r6)
-	blr
-
-/*
- * do_cpu_ftr_fixups - goes through the list of CPU feature fixups
- * and writes nop's over sections of code that don't apply for this cpu.
- * r3 = data offset (not changed)
- */
-_GLOBAL(do_cpu_ftr_fixups)
-	/* Get CPU 0 features */
-	addis	r6,r3,cur_cpu_spec@ha
-	addi	r6,r6,cur_cpu_spec@l
-	lwz	r4,0(r6)
-	add	r4,r4,r3
-	lwz	r4,CPU_SPEC_FEATURES(r4)
-
-	/* Get the fixup table */
-	addis	r6,r3,__start___ftr_fixup@ha
-	addi	r6,r6,__start___ftr_fixup@l
-	addis	r7,r3,__stop___ftr_fixup@ha
-	addi	r7,r7,__stop___ftr_fixup@l
-
-	/* Do the fixup */
-1:	cmplw	0,r6,r7
-	bgelr
-	addi	r6,r6,16
-	lwz	r8,-16(r6)	/* mask */
-	and	r8,r8,r4
-	lwz	r9,-12(r6)	/* value */
-	cmplw	0,r8,r9
-	beq	1b
-	lwz	r8,-8(r6)	/* section begin */
-	lwz	r9,-4(r6)	/* section end */
-	subf.	r9,r8,r9
-	beq	1b
-	/* write nops over the section of code */
-	/* todo: if large section, add a branch at the start of it */
-	srwi	r9,r9,2
-	mtctr	r9
-	add	r8,r8,r3
-	lis	r0,0x60000000@h	/* nop */
-3:	stw	r0,0(r8)
-	andi.	r10,r4,CPU_FTR_SPLIT_ID_CACHE@l
-	beq	2f
-	dcbst	0,r8		/* suboptimal, but simpler */
-	sync
-	icbi	0,r8
-2:	addi	r8,r8,4
-	bdnz	3b
-	sync			/* additional sync needed on g4 */
-	isync
-	b	1b
-
-/*
  * call_setup_cpu - call the setup_cpu function for this cpu
  * r3 = data offset, r24 = cpu number
  *
Index: linux-cell/include/asm-powerpc/cputable.h
===================================================================
--- linux-cell.orig/include/asm-powerpc/cputable.h	2006-10-13 16:00:28.000000000 +1000
+++ linux-cell/include/asm-powerpc/cputable.h	2006-10-13 16:19:51.000000000 +1000
@@ -89,8 +89,7 @@ struct cpu_spec {
 
 extern struct cpu_spec		*cur_cpu_spec;
 
-extern void identify_cpu(unsigned long offset, unsigned long cpu);
-extern void do_cpu_ftr_fixups(unsigned long offset);
+extern struct cpu_spec *identify_cpu(unsigned long offset);
 
 #endif /* __ASSEMBLY__ */
 
Index: linux-cell/arch/powerpc/platforms/iseries/setup.c
===================================================================
--- linux-cell.orig/arch/powerpc/platforms/iseries/setup.c	2006-10-06 13:47:54.000000000 +1000
+++ linux-cell/arch/powerpc/platforms/iseries/setup.c	2006-10-13 16:49:14.000000000 +1000
@@ -694,6 +694,11 @@ void * __init iSeries_early_setup(void)
 {
 	unsigned long phys_mem_size;
 
+	/* Identify CPU type. This is done again by the common code later
+	 * on but calling this function multiple times is fine.
+	 */
+	identify_cpu(0);
+
 	powerpc_firmware_features |= FW_FEATURE_ISERIES;
 	powerpc_firmware_features |= FW_FEATURE_LPAR;
 

Re: [PATCH 1/5] powerpc: consolidate feature fixup code

[Olof Johansson]

On Fri, 20 Oct 2006 11:47:15 +1000 Benjamin Herrenschmidt <benh@kernel.crashing.org> wrote:

> There are currently two versions of the functions for applying the
> feature fixups, one for CPU features and one for firmware features. In
> addition, they are both in assembly and with separate implementations
> for 32 and 64 bits. identify_cpu() is also implemented in assembly and
> separately for 32 and 64 bits.
> 
> This patch replaces them with a pair of C functions. The call sites are
> slightly moved on ppc64 as well to be called from C instead of from
> assembly, though it's a very small change, and thus shouldn't cause any
> problem.
> 
> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

Acked-by: Olof Johansson <olof@lixom.net>

Re: [PATCH 1/5] powerpc: consolidate feature fixup code

[Paul Mackerras]

Benjamin Herrenschmidt writes:

> There are currently two versions of the functions for applying the
> feature fixups, one for CPU features and one for firmware features. In
> addition, they are both in assembly and with separate implementations
> for 32 and 64 bits. identify_cpu() is also implemented in assembly and
> separately for 32 and 64 bits.
> 
> This patch replaces them with a pair of C functions. The call sites are
> slightly moved on ppc64 as well to be called from C instead of from
> assembly, though it's a very small change, and thus shouldn't cause any
> problem.

Unfortunately this:

> Index: linux-cell/include/asm-powerpc/cputable.h
> ===================================================================
> --- linux-cell.orig/include/asm-powerpc/cputable.h	2006-10-13 16:00:28.000000000 +1000
> +++ linux-cell/include/asm-powerpc/cputable.h	2006-10-13 16:19:51.000000000 +1000
> @@ -89,8 +89,7 @@ struct cpu_spec {
>  
>  extern struct cpu_spec		*cur_cpu_spec;
>  
> -extern void identify_cpu(unsigned long offset, unsigned long cpu);
> -extern void do_cpu_ftr_fixups(unsigned long offset);
> +extern struct cpu_spec *identify_cpu(unsigned long offset);

... breaks the ARCH=ppc build.

Paul.

Re: [PATCH 1/5] powerpc: consolidate feature fixup code

[Benjamin Herrenschmidt]

> > Index: linux-cell/include/asm-powerpc/cputable.h
> > ===================================================================
> > --- linux-cell.orig/include/asm-powerpc/cputable.h	2006-10-13 16:00:28.000000000 +1000
> > +++ linux-cell/include/asm-powerpc/cputable.h	2006-10-13 16:19:51.000000000 +1000
> > @@ -89,8 +89,7 @@ struct cpu_spec {
> >  
> >  extern struct cpu_spec		*cur_cpu_spec;
> >  
> > -extern void identify_cpu(unsigned long offset, unsigned long cpu);
> > -extern void do_cpu_ftr_fixups(unsigned long offset);
> > +extern struct cpu_spec *identify_cpu(unsigned long offset);
> 
> ... breaks the ARCH=ppc build.

Gack... I though I tested, I must have screwed up. Should be easy enough
to fix though. I'll have a look.

Ben.