ARM: fixup SMP alternatives in modules

With certain configurations, we inline the unlock functions in modules,
which results in SMP alternatives being created in modules.  We need to
fix those up when loading a module to prevent undefined instruction
faults.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

arch/arm/kernel/head.S

@@ -391,6 +391,7 @@ ENDPROC(__turn_mmu_on)
 
 
 #ifdef CONFIG_SMP_ON_UP
+	__INIT
 __fixup_smp:
 	and	r3, r9, #0x000f0000	@ architecture version
 	teq	r3, #0x000f0000		@ CPU ID supported?
@@ -415,18 +416,7 @@ __fixup_smp_on_up:
 	sub	r3, r0, r3
 	add	r4, r4, r3
 	add	r5, r5, r3
-2:	cmp	r4, r5
-	movhs	pc, lr
-	ldmia	r4!, {r0, r6}
- ARM(	str	r6, [r0, r3]	)
- THUMB(	add	r0, r0, r3	)
-#ifdef __ARMEB__
- THUMB(	mov	r6, r6, ror #16	)	@ Convert word order for big-endian.
-#endif
- THUMB(	strh	r6, [r0], #2	)	@ For Thumb-2, store as two halfwords
- THUMB(	mov	r6, r6, lsr #16	)	@ to be robust against misaligned r3.
- THUMB(	strh	r6, [r0]	)
-	b	2b
+	b	__do_fixup_smp_on_up
 ENDPROC(__fixup_smp)
 
 	.align
@@ -440,7 +430,31 @@ smp_on_up:
 	ALT_SMP(.long	1)
 	ALT_UP(.long	0)
 	.popsection
+#endif
 
+	.text
+__do_fixup_smp_on_up:
+	cmp	r4, r5
+	movhs	pc, lr
+	ldmia	r4!, {r0, r6}
+ ARM(	str	r6, [r0, r3]	)
+ THUMB(	add	r0, r0, r3	)
+#ifdef __ARMEB__
+ THUMB(	mov	r6, r6, ror #16	)	@ Convert word order for big-endian.
 #endif
+ THUMB(	strh	r6, [r0], #2	)	@ For Thumb-2, store as two halfwords
+ THUMB(	mov	r6, r6, lsr #16	)	@ to be robust against misaligned r3.
+ THUMB(	strh	r6, [r0]	)
+	b	__do_fixup_smp_on_up
+ENDPROC(__do_fixup_smp_on_up)
+
+ENTRY(fixup_smp)
+	stmfd	sp!, {r4 - r6, lr}
+	mov	r4, r0
+	add	r5, r0, r1
+	mov	r3, #0
+	bl	__do_fixup_smp_on_up
+	ldmfd	sp!, {r4 - r6, pc}
+ENDPROC(fixup_smp)
 
 #include "head-common.S"

arch/arm/kernel/module.c

@@ -22,6 +22,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/sections.h>
+#include <asm/smp_plat.h>
 #include <asm/unwind.h>
 
 #ifdef CONFIG_XIP_KERNEL
@@ -268,12 +269,28 @@ struct mod_unwind_map {
 	const Elf_Shdr *txt_sec;
 };
 
+static const Elf_Shdr *find_mod_section(const Elf32_Ehdr *hdr,
+	const Elf_Shdr *sechdrs, const char *name)
+{
+	const Elf_Shdr *s, *se;
+	const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+
+	for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++)
+		if (strcmp(name, secstrs + s->sh_name) == 0)
+			return s;
+
+	return NULL;
+}
+
+extern void fixup_smp(const void *, unsigned long);
+
 int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs,
 		    struct module *mod)
 {
+	const Elf_Shdr * __maybe_unused s = NULL;
 #ifdef CONFIG_ARM_UNWIND
 	const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
-	const Elf_Shdr *s, *sechdrs_end = sechdrs + hdr->e_shnum;
+	const Elf_Shdr *sechdrs_end = sechdrs + hdr->e_shnum;
 	struct mod_unwind_map maps[ARM_SEC_MAX];
 	int i;
 
@@ -315,6 +332,9 @@ int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs,
 					         maps[i].txt_sec->sh_addr,
 					         maps[i].txt_sec->sh_size);
 #endif
+	s = find_mod_section(hdr, sechdrs, ".alt.smp.init");
+	if (s && !is_smp())
+		fixup_smp((void *)s->sh_addr, s->sh_size);
 	return 0;
 }