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>

arch/arm/Kconfig

@@ -1191,6 +1191,19 @@ config SMP
 
 	  If you don't know what to do here, say N.
 
+config SMP_ON_UP
+	bool "Allow booting SMP kernel on uniprocessor systems (EXPERIMENTAL)"
+	depends on EXPERIMENTAL
+	depends on SMP && !XIP && !THUMB2_KERNEL
+	default y
+	help
+	  SMP kernels contain instructions which fail on non-SMP processors.
+	  Enabling this option allows the kernel to modify itself to make
+	  these instructions safe.  Disabling it allows about 1K of space
+	  savings.
+
+	  If you don't know what to do here, say Y.
+
 config HAVE_ARM_SCU
 	bool
 	depends on SMP

arch/arm/include/asm/assembler.h

@@ -154,16 +154,39 @@
 	.long	9999b,9001f;			\
 	.popsection
 
+#ifdef CONFIG_SMP
+#define ALT_SMP(instr...)					\
+9998:	instr
+#define ALT_UP(instr...)					\
+	.pushsection ".alt.smp.init", "a"			;\
+	.long	9998b						;\
+	instr							;\
+	.popsection
+#define ALT_UP_B(label)					\
+	.equ	up_b_offset, label - 9998b			;\
+	.pushsection ".alt.smp.init", "a"			;\
+	.long	9998b						;\
+	b	. + up_b_offset					;\
+	.popsection
+#else
+#define ALT_SMP(instr...)
+#define ALT_UP(instr...) instr
+#define ALT_UP_B(label) b label
+#endif
+
 /*
  * SMP data memory barrier
  */
 	.macro	smp_dmb
 #ifdef CONFIG_SMP
 #if __LINUX_ARM_ARCH__ >= 7
-	dmb
+	ALT_SMP(dmb)
 #elif __LINUX_ARM_ARCH__ == 6
-	mcr	p15, 0, r0, c7, c10, 5	@ dmb
+	ALT_SMP(mcr	p15, 0, r0, c7, c10, 5)	@ dmb
+#else
+#error Incompatible SMP platform
 #endif
+	ALT_UP(nop)
 #endif
 	.endm
 

arch/arm/include/asm/smp_mpidr.h

@@ -4,7 +4,12 @@
 #define hard_smp_processor_id()						\
 	({								\
 		unsigned int cpunum;					\
-		__asm__("mrc p15, 0, %0, c0, c0, 5\n"			\
+		__asm__("\n"						\
+			"1:	mrc p15, 0, %0, c0, c0, 5\n"		\
+			"	.pushsection \".alt.smp.init\", \"a\"\n"\
+			"	.long	1b\n"				\
+			"	mov	%0, #0\n"			\
+			"	.popsection"				\
 			: "=r" (cpunum));				\
 		cpunum &= 0x0F;						\
 	})

arch/arm/include/asm/smp_plat.h

@@ -18,4 +18,19 @@ static inline int cache_ops_need_broadcast(void)
 	return ((read_cpuid_ext(CPUID_EXT_MMFR3) >> 12) & 0xf) < 1;
 }
 
+/*
+ * Return true if we are running on a SMP platform
+ */
+static inline bool is_smp(void)
+{
+#ifndef CONFIG_SMP
+	return false;
+#elif defined(CONFIG_SMP_ON_UP)
+	extern unsigned int smp_on_up;
+	return !!smp_on_up;
+#else
+	return true;
+#endif
+}
+
 #endif

arch/arm/include/asm/tlbflush.h

@@ -70,6 +70,10 @@
 #undef _TLB
 #undef MULTI_TLB
 
+#ifdef CONFIG_SMP_ON_UP
+#define MULTI_TLB 1
+#endif
+
 #define v3_tlb_flags	(TLB_V3_FULL | TLB_V3_PAGE)
 
 #ifdef CONFIG_CPU_TLB_V3
@@ -185,17 +189,23 @@
 # define v6wbi_always_flags	(-1UL)
 #endif
 
-#ifdef CONFIG_SMP
-#define v7wbi_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_V7_IS_BTB | \
+#define v7wbi_tlb_flags_smp	(TLB_WB | TLB_DCLEAN | TLB_V7_IS_BTB | \
 			 TLB_V7_UIS_FULL | TLB_V7_UIS_PAGE | TLB_V7_UIS_ASID)
-#else
-#define v7wbi_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_BTB | \
+#define v7wbi_tlb_flags_up	(TLB_WB | TLB_DCLEAN | TLB_BTB | \
 			 TLB_V6_U_FULL | TLB_V6_U_PAGE | TLB_V6_U_ASID)
-#endif
 
 #ifdef CONFIG_CPU_TLB_V7
-# define v7wbi_possible_flags	v7wbi_tlb_flags
-# define v7wbi_always_flags	v7wbi_tlb_flags
+
+# ifdef CONFIG_SMP_ON_UP
+#  define v7wbi_possible_flags	(v7wbi_tlb_flags_smp | v7wbi_tlb_flags_up)
+#  define v7wbi_always_flags	(v7wbi_tlb_flags_smp & v7wbi_tlb_flags_up)
+# elif defined(CONFIG_SMP)
+#  define v7wbi_possible_flags	v7wbi_tlb_flags_smp
+#  define v7wbi_always_flags	v7wbi_tlb_flags_smp
+# else
+#  define v7wbi_possible_flags	v7wbi_tlb_flags_up
+#  define v7wbi_always_flags	v7wbi_tlb_flags_up
+# endif
 # ifdef _TLB
 #  define MULTI_TLB 1
 # else

arch/arm/kernel/entry-armv.S

@@ -46,7 +46,8 @@
 	 * this macro assumes that irqstat (r6) and base (r5) are
 	 * preserved from get_irqnr_and_base above
 	 */
-	test_for_ipi r0, r6, r5, lr
+	ALT_SMP(test_for_ipi r0, r6, r5, lr)
+	ALT_UP_B(9997f)
 	movne	r0, sp
 	adrne	lr, BSYM(1b)
 	bne	do_IPI
@@ -57,6 +58,7 @@
 	adrne	lr, BSYM(1b)
 	bne	do_local_timer
 #endif
+9997:
 #endif
 
 	.endm
@@ -965,11 +967,8 @@ kuser_cmpxchg_fixup:
 	beq	1b
 	rsbs	r0, r3, #0
 	/* beware -- each __kuser slot must be 8 instructions max */
-#ifdef CONFIG_SMP
-	b	__kuser_memory_barrier
-#else
-	usr_ret	lr
-#endif
+	ALT_SMP(b	__kuser_memory_barrier)
+	ALT_UP(usr_ret	lr)
 
 #endif
 

arch/arm/kernel/head.S

@@ -86,6 +86,9 @@ ENTRY(stext)
 	movs	r8, r5				@ invalid machine (r5=0)?
 	beq	__error_a			@ yes, error 'a'
 	bl	__vet_atags
+#ifdef CONFIG_SMP_ON_UP
+	bl	__fixup_smp
+#endif
 	bl	__create_page_tables
 
 	/*
@@ -333,4 +336,51 @@ __create_page_tables:
 ENDPROC(__create_page_tables)
 	.ltorg
 
+#ifdef CONFIG_SMP_ON_UP
+__fixup_smp:
+	mov	r7, #0x00070000
+	orr	r6, r7, #0xff000000	@ mask 0xff070000
+	orr	r7, r7, #0x41000000	@ val 0x41070000
+	and	r0, r9, r6
+	teq	r0, r7			@ ARM CPU and ARMv6/v7?
+	bne	__fixup_smp_on_up	@ no, assume UP
+
+	orr	r6, r6, #0x0000ff00
+	orr	r6, r6, #0x000000f0	@ mask 0xff07fff0
+	orr	r7, r7, #0x0000b000
+	orr	r7, r7, #0x00000020	@ val 0x4107b020
+	and	r0, r9, r6
+	teq	r0, r7			@ ARM 11MPCore?
+	moveq	pc, lr			@ yes, assume SMP
+
+	mrc	p15, 0, r0, c0, c0, 5	@ read MPIDR
+	tst	r0, #1 << 31
+	movne	pc, lr			@ bit 31 => SMP
+
+__fixup_smp_on_up:
+	adr	r0, 1f
+	ldmia	r0, {r3, r6, r7}
+	sub	r3, r0, r3
+	add	r6, r6, r3
+	add	r7, r7, r3
+2:	cmp	r6, r7
+	ldmia	r6!, {r0, r4}
+	strlo	r4, [r0, r3]
+	blo	2b
+	mov	pc, lr
+ENDPROC(__fixup_smp)
+
+1:	.word	.
+	.word	__smpalt_begin
+	.word	__smpalt_end
+
+	.pushsection .data
+	.globl	smp_on_up
+smp_on_up:
+	ALT_SMP(.long	1)
+	ALT_UP(.long	0)
+	.popsection
+
+#endif
+
 #include "head-common.S"

arch/arm/kernel/setup.c

@@ -36,6 +36,7 @@
 #include <asm/procinfo.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
+#include <asm/smp_plat.h>
 #include <asm/mach-types.h>
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
@@ -825,7 +826,8 @@ void __init setup_arch(char **cmdline_p)
 	request_standard_resources(&meminfo, mdesc);
 
 #ifdef CONFIG_SMP
-	smp_init_cpus();
+	if (is_smp())
+		smp_init_cpus();
 #endif
 	reserve_crashkernel();
 

arch/arm/kernel/vmlinux.lds.S

@@ -40,6 +40,11 @@ SECTIONS
 		__tagtable_begin = .;
 			*(.taglist.init)
 		__tagtable_end = .;
+#ifdef CONFIG_SMP_ON_UP
+		__smpalt_begin = .;
+			*(.alt.smp.init)
+		__smpalt_end = .;
+#endif
 
 		INIT_SETUP(16)
 
@@ -237,6 +242,12 @@ SECTIONS
 
 	/* Default discards */
 	DISCARDS
+
+#ifndef CONFIG_SMP_ON_UP
+	/DISCARD/ : {
+		*(.alt.smp.init)
+	}
+#endif
 }
 
 /*

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

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",