ARM: Allow SMP kernels to boot on UP systems

UP systems do not implement all the instructions that SMP systems have,
so in order to boot a SMP kernel on a UP system, we need to rewrite
parts of the kernel.

Do this using an 'alternatives' scheme, where the kernel code and data
is modified prior to initialization to replace the SMP instructions,
thereby rendering the problematical code ineffectual.  We use the linker
to generate a list of 32-bit word locations and their replacement values,
and run through these replacements when we detect a UP system.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

5 files changed, 92 insertions, 85 deletions

diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 37c8157..e8ea1a0 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -91,11 +91,8 @@ ENTRY(v7_flush_kern_cache_all)
  THUMB(	stmfd	sp!, {r4-r7, r9-r11, lr}	)
 	bl	v7_flush_dcache_all
 	mov	r0, #0
-#ifdef CONFIG_SMP
-	mcr	p15, 0, r0, c7, c1, 0		@ invalidate I-cache inner shareable
-#else
-	mcr	p15, 0, r0, c7, c5, 0		@ I+BTB cache invalidate
-#endif
+	ALT_SMP(mcr	p15, 0, r0, c7, c1, 0)	@ invalidate I-cache inner shareable
+	ALT_UP(mcr	p15, 0, r0, c7, c5, 0)	@ I+BTB cache invalidate
  ARM(	ldmfd	sp!, {r4-r5, r7, r9-r11, lr}	)
  THUMB(	ldmfd	sp!, {r4-r7, r9-r11, lr}	)
 	mov	pc, lr
@@ -171,11 +168,8 @@ ENTRY(v7_coherent_user_range)
 	cmp	r0, r1
 	blo	1b
 	mov	r0, #0
-#ifdef CONFIG_SMP
-	mcr	p15, 0, r0, c7, c1, 6		@ invalidate BTB Inner Shareable
-#else
-	mcr	p15, 0, r0, c7, c5, 6		@ invalidate BTB
-#endif
+	ALT_SMP(mcr	p15, 0, r0, c7, c1, 6)	@ invalidate BTB Inner Shareable
+	ALT_UP(mcr	p15, 0, r0, c7, c5, 6)	@ invalidate BTB
 	dsb
 	isb
 	mov	pc, lr
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 6a3a2d0..e233581 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -310,9 +310,8 @@ static void __init build_mem_type_table(void)
 			cachepolicy = CPOLICY_WRITEBACK;
 		ecc_mask = 0;
 	}
-#ifdef CONFIG_SMP
-	cachepolicy = CPOLICY_WRITEALLOC;
-#endif
+	if (is_smp())
+		cachepolicy = CPOLICY_WRITEALLOC;
 
 	/*
 	 * Strip out features not present on earlier architectures.
@@ -406,13 +405,11 @@ static void __init build_mem_type_table(void)
 	cp = &cache_policies[cachepolicy];
 	vecs_pgprot = kern_pgprot = user_pgprot = cp->pte;
 
-#ifndef CONFIG_SMP
 	/*
 	 * Only use write-through for non-SMP systems
 	 */
-	if (cpu_arch >= CPU_ARCH_ARMv5 && cachepolicy > CPOLICY_WRITETHROUGH)
+	if (!is_smp() && cpu_arch >= CPU_ARCH_ARMv5 && cachepolicy > CPOLICY_WRITETHROUGH)
 		vecs_pgprot = cache_policies[CPOLICY_WRITETHROUGH].pte;
-#endif
 
 	/*
 	 * Enable CPU-specific coherency if supported.
@@ -436,22 +433,23 @@ static void __init build_mem_type_table(void)
 		mem_types[MT_MINICLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
 		mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
 
-#ifdef CONFIG_SMP
-		/*
-		 * Mark memory with the "shared" attribute for SMP systems
-		 */
-		user_pgprot |= L_PTE_SHARED;
-		kern_pgprot |= L_PTE_SHARED;
-		vecs_pgprot |= L_PTE_SHARED;
-		mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_S;
-		mem_types[MT_DEVICE_WC].prot_pte |= L_PTE_SHARED;
-		mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S;
-		mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED;
-		mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
-		mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
-		mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
-		mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
-#endif
+		if (is_smp()) {
+			/*
+			 * Mark memory with the "shared" attribute
+			 * for SMP systems
+			 */
+			user_pgprot |= L_PTE_SHARED;
+			kern_pgprot |= L_PTE_SHARED;
+			vecs_pgprot |= L_PTE_SHARED;
+			mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_S;
+			mem_types[MT_DEVICE_WC].prot_pte |= L_PTE_SHARED;
+			mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S;
+			mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED;
+			mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
+			mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
+			mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
+			mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
+		}
 	}
 
 	/*
@@ -829,8 +827,7 @@ static void __init sanity_check_meminfo(void)
 			 * rather difficult.
 			 */
 			reason = "with VIPT aliasing cache";
-#ifdef CONFIG_SMP
-		} else if (tlb_ops_need_broadcast()) {
+		} else if (is_smp() && tlb_ops_need_broadcast()) {
 			/*
 			 * kmap_high needs to occasionally flush TLB entries,
 			 * however, if the TLB entries need to be broadcast
@@ -840,7 +837,6 @@ static void __init sanity_check_meminfo(void)
 			 *   (must not be called with irqs off)
 			 */
 			reason = "without hardware TLB ops broadcasting";
-#endif
 		}
 		if (reason) {
 			printk(KERN_CRIT "HIGHMEM is not supported %s, ignoring high memory\n",
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 22aac85..b95662d 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -30,13 +30,10 @@
 #define TTB_RGN_WT	(2 << 3)
 #define TTB_RGN_WB	(3 << 3)
 
-#ifndef CONFIG_SMP
-#define TTB_FLAGS	TTB_RGN_WBWA
-#define PMD_FLAGS	PMD_SECT_WB
-#else
-#define TTB_FLAGS	TTB_RGN_WBWA|TTB_S
-#define PMD_FLAGS	PMD_SECT_WBWA|PMD_SECT_S
-#endif
+#define TTB_FLAGS_UP	TTB_RGN_WBWA
+#define PMD_FLAGS_UP	PMD_SECT_WB
+#define TTB_FLAGS_SMP	TTB_RGN_WBWA|TTB_S
+#define PMD_FLAGS_SMP	PMD_SECT_WBWA|PMD_SECT_S
 
 ENTRY(cpu_v6_proc_init)
 	mov	pc, lr
@@ -97,7 +94,8 @@ ENTRY(cpu_v6_switch_mm)
 #ifdef CONFIG_MMU
 	mov	r2, #0
 	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
-	orr	r0, r0, #TTB_FLAGS
+	ALT_SMP(orr	r0, r0, #TTB_FLAGS_SMP)
+	ALT_UP(orr	r0, r0, #TTB_FLAGS_UP)
 	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
 	mcr	p15, 0, r2, c7, c10, 4		@ drain write buffer
 	mcr	p15, 0, r0, c2, c0, 0		@ set TTB 0
@@ -156,9 +154,11 @@ cpu_pj4_name:
  */
 __v6_setup:
 #ifdef CONFIG_SMP
-	mrc	p15, 0, r0, c1, c0, 1		@ Enable SMP/nAMP mode
+	ALT_SMP(mrc	p15, 0, r0, c1, c0, 1)	@ Enable SMP/nAMP mode
+	ALT_UP(nop)
 	orr	r0, r0, #0x20
-	mcr	p15, 0, r0, c1, c0, 1
+	ALT_SMP(mcr	p15, 0, r0, c1, c0, 1)
+	ALT_UP(nop)
 #endif
 
 	mov	r0, #0
@@ -169,7 +169,8 @@ __v6_setup:
 #ifdef CONFIG_MMU
 	mcr	p15, 0, r0, c8, c7, 0		@ invalidate I + D TLBs
 	mcr	p15, 0, r0, c2, c0, 2		@ TTB control register
-	orr	r4, r4, #TTB_FLAGS
+	ALT_SMP(orr	r4, r4, #TTB_FLAGS_SMP)
+	ALT_UP(orr	r4, r4, #TTB_FLAGS_UP)
 	mcr	p15, 0, r4, c2, c0, 1		@ load TTB1
 #endif /* CONFIG_MMU */
 	adr	r5, v6_crval
@@ -225,10 +226,16 @@ cpu_elf_name:
 __v6_proc_info:
 	.long	0x0007b000
 	.long	0x0007f000
-	.long   PMD_TYPE_SECT | \
+	ALT_SMP(.long \
+		PMD_TYPE_SECT | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ | \
+		PMD_FLAGS_SMP)
+	ALT_UP(.long \
+		PMD_TYPE_SECT | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ | \
-		PMD_FLAGS
+		PMD_FLAGS_UP)
 	.long   PMD_TYPE_SECT | \
 		PMD_SECT_XN | \
 		PMD_SECT_AP_WRITE | \
@@ -249,10 +256,16 @@ __v6_proc_info:
 __pj4_v6_proc_info:
 	.long	0x560f5810
 	.long	0xff0ffff0
-	.long   PMD_TYPE_SECT | \
+	ALT_SMP(.long \
+		PMD_TYPE_SECT | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ | \
+		PMD_FLAGS_SMP)
+	ALT_UP(.long \
+		PMD_TYPE_SECT | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ | \
-		PMD_FLAGS
+		PMD_FLAGS_UP)
 	.long   PMD_TYPE_SECT | \
 		PMD_SECT_XN | \
 		PMD_SECT_AP_WRITE | \
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 7563ff0..df422fe 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -30,15 +30,13 @@
 #define TTB_IRGN_WT	((1 << 0) | (0 << 6))
 #define TTB_IRGN_WB	((1 << 0) | (1 << 6))
 
-#ifndef CONFIG_SMP
 /* PTWs cacheable, inner WB not shareable, outer WB not shareable */
-#define TTB_FLAGS	TTB_IRGN_WB|TTB_RGN_OC_WB
-#define PMD_FLAGS	PMD_SECT_WB
-#else
+#define TTB_FLAGS_UP	TTB_IRGN_WB|TTB_RGN_OC_WB
+#define PMD_FLAGS_UP	PMD_SECT_WB
+
 /* PTWs cacheable, inner WBWA shareable, outer WBWA not shareable */
-#define TTB_FLAGS	TTB_IRGN_WBWA|TTB_S|TTB_NOS|TTB_RGN_OC_WBWA
-#define PMD_FLAGS	PMD_SECT_WBWA|PMD_SECT_S
-#endif
+#define TTB_FLAGS_SMP	TTB_IRGN_WBWA|TTB_S|TTB_NOS|TTB_RGN_OC_WBWA
+#define PMD_FLAGS_SMP	PMD_SECT_WBWA|PMD_SECT_S
 
 ENTRY(cpu_v7_proc_init)
 	mov	pc, lr
@@ -105,7 +103,8 @@ ENTRY(cpu_v7_switch_mm)
 #ifdef CONFIG_MMU
 	mov	r2, #0
 	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
-	orr	r0, r0, #TTB_FLAGS
+	ALT_SMP(orr	r0, r0, #TTB_FLAGS_SMP)
+	ALT_UP(orr	r0, r0, #TTB_FLAGS_UP)
 #ifdef CONFIG_ARM_ERRATA_430973
 	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
 #endif
@@ -188,7 +187,8 @@ cpu_v7_name:
  */
 __v7_ca9mp_setup:
 #ifdef CONFIG_SMP
-	mrc	p15, 0, r0, c1, c0, 1
+	ALT_SMP(mrc	p15, 0, r0, c1, c0, 1)
+	ALT_UP(mov	r0, #(1 << 6))		@ fake it for UP
 	tst	r0, #(1 << 6)			@ SMP/nAMP mode enabled?
 	orreq	r0, r0, #(1 << 6) | (1 << 0)	@ Enable SMP/nAMP mode and
 	mcreq	p15, 0, r0, c1, c0, 1		@ TLB ops broadcasting
@@ -262,7 +262,8 @@ __v7_setup:
 #ifdef CONFIG_MMU
 	mcr	p15, 0, r10, c8, c7, 0		@ invalidate I + D TLBs
 	mcr	p15, 0, r10, c2, c0, 2		@ TTB control register
-	orr	r4, r4, #TTB_FLAGS
+	ALT_SMP(orr	r4, r4, #TTB_FLAGS_SMP)
+	ALT_UP(orr	r4, r4, #TTB_FLAGS_UP)
 	mcr	p15, 0, r4, c2, c0, 1		@ load TTB1
 	mov	r10, #0x1f			@ domains 0, 1 = manager
 	mcr	p15, 0, r10, c3, c0, 0		@ load domain access register
@@ -354,10 +355,16 @@ cpu_elf_name:
 __v7_ca9mp_proc_info:
 	.long	0x410fc090		@ Required ID value
 	.long	0xff0ffff0		@ Mask for ID
-	.long   PMD_TYPE_SECT | \
+	ALT_SMP(.long \
+		PMD_TYPE_SECT | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ | \
+		PMD_FLAGS_SMP)
+	ALT_UP(.long \
+		PMD_TYPE_SECT | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ | \
-		PMD_FLAGS
+		PMD_FLAGS_UP)
 	.long   PMD_TYPE_SECT | \
 		PMD_SECT_XN | \
 		PMD_SECT_AP_WRITE | \
@@ -380,10 +387,16 @@ __v7_ca9mp_proc_info:
 __v7_proc_info:
 	.long	0x000f0000		@ Required ID value
 	.long	0x000f0000		@ Mask for ID
-	.long   PMD_TYPE_SECT | \
+	ALT_SMP(.long \
+		PMD_TYPE_SECT | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ | \
+		PMD_FLAGS_SMP)
+	ALT_UP(.long \
+		PMD_TYPE_SECT | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ | \
-		PMD_FLAGS
+		PMD_FLAGS_UP)
 	.long   PMD_TYPE_SECT | \
 		PMD_SECT_XN | \
 		PMD_SECT_AP_WRITE | \
diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S
index f3f288a..53cd5b4 100644
--- a/arch/arm/mm/tlb-v7.S
+++ b/arch/arm/mm/tlb-v7.S
@@ -13,6 +13,7 @@
  */
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/page.h>
 #include <asm/tlbflush.h>
@@ -41,20 +42,15 @@ ENTRY(v7wbi_flush_user_tlb_range)
 	orr	r0, r3, r0, lsl #PAGE_SHIFT	@ Create initial MVA
 	mov	r1, r1, lsl #PAGE_SHIFT
 1:
-#ifdef CONFIG_SMP
-	mcr	p15, 0, r0, c8, c3, 1		@ TLB invalidate U MVA (shareable) 
-#else
-	mcr	p15, 0, r0, c8, c7, 1		@ TLB invalidate U MVA
-#endif
+	ALT_SMP(mcr	p15, 0, r0, c8, c3, 1)	@ TLB invalidate U MVA (shareable)
+	ALT_UP(mcr	p15, 0, r0, c8, c7, 1)	@ TLB invalidate U MVA
+
 	add	r0, r0, #PAGE_SZ
 	cmp	r0, r1
 	blo	1b
 	mov	ip, #0
-#ifdef CONFIG_SMP
-	mcr	p15, 0, ip, c7, c1, 6		@ flush BTAC/BTB Inner Shareable
-#else
-	mcr	p15, 0, ip, c7, c5, 6		@ flush BTAC/BTB
-#endif
+	ALT_SMP(mcr	p15, 0, ip, c7, c1, 6)	@ flush BTAC/BTB Inner Shareable
+	ALT_UP(mcr	p15, 0, ip, c7, c5, 6)	@ flush BTAC/BTB
 	dsb
 	mov	pc, lr
 ENDPROC(v7wbi_flush_user_tlb_range)
@@ -74,20 +70,14 @@ ENTRY(v7wbi_flush_kern_tlb_range)
 	mov	r0, r0, lsl #PAGE_SHIFT
 	mov	r1, r1, lsl #PAGE_SHIFT
 1:
-#ifdef CONFIG_SMP
-	mcr	p15, 0, r0, c8, c3, 1		@ TLB invalidate U MVA (shareable)
-#else
-	mcr	p15, 0, r0, c8, c7, 1		@ TLB invalidate U MVA
-#endif
+	ALT_SMP(mcr	p15, 0, r0, c8, c3, 1)	@ TLB invalidate U MVA (shareable)
+	ALT_UP(mcr	p15, 0, r0, c8, c7, 1)	@ TLB invalidate U MVA
 	add	r0, r0, #PAGE_SZ
 	cmp	r0, r1
 	blo	1b
 	mov	r2, #0
-#ifdef CONFIG_SMP
-	mcr	p15, 0, r2, c7, c1, 6		@ flush BTAC/BTB Inner Shareable
-#else
-	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
-#endif
+	ALT_SMP(mcr	p15, 0, r2, c7, c1, 6)	@ flush BTAC/BTB Inner Shareable
+	ALT_UP(mcr	p15, 0, r2, c7, c5, 6)	@ flush BTAC/BTB
 	dsb
 	isb
 	mov	pc, lr
@@ -99,5 +89,6 @@ ENDPROC(v7wbi_flush_kern_tlb_range)
 ENTRY(v7wbi_tlb_fns)
 	.long	v7wbi_flush_user_tlb_range
 	.long	v7wbi_flush_kern_tlb_range
-	.long	v7wbi_tlb_flags
+	ALT_SMP(.long	v7wbi_tlb_flags_smp)
+	ALT_UP(.long	v7wbi_tlb_flags_up)
 	.size	v7wbi_tlb_fns, . - v7wbi_tlb_fns