ARM: 6516/1: Allow SMP_ON_UP to work with Thumb-2 kernels.

* __fixup_smp_on_up has been modified with support for the
    THUMB2_KERNEL case.  For THUMB2_KERNEL only, fixups are split
    into halfwords in case of misalignment, since we can't rely on
    unaligned accesses working before turning the MMU on.

    No attempt is made to optimise the aligned case, since the
    number of fixups is typically small, and it seems best to keep
    the code as simple as possible.

  * Add a rotate in the fixup_smp code in order to support
    CPU_BIG_ENDIAN, as suggested by Nicolas Pitre.

  * Add an assembly-time sanity-check to ALT_UP() to ensure that
    the content really is the right size (4 bytes).

    (No check is done for ALT_SMP().  Possibly, this could be fixed
    by splitting the two uses ot ALT_SMP() (ALT_SMP...SMP_UP versus
    ALT_SMP...SMP_UP_B) into two macros.  In the first case,
    ALT_SMP needs to expand to >= 4 bytes, not == 4.)

  * smp_mpidr.h (which implements ALT_SMP()/ALT_UP() manually due
    to macro limitations) has not been modified: the affected
    instruction (mov) has no 16-bit encoding, so the correct
    instruction size is satisfied in this case.

  * A "mode" parameter has been added to smp_dmb:

    smp_dmb arm @ assumes 4-byte instructions (for ARM code, e.g. kuser)
    smp_dmb     @ uses W() to ensure 4-byte instructions for ALT_SMP()

    This avoids assembly failures due to use of W() inside smp_dmb,
    when assembling pure-ARM code in the vectors page.

    There might be a better way to achieve this.

  * Kconfig: make SMP_ON_UP depend on
    (!THUMB2_KERNEL || !BIG_ENDIAN) i.e., THUMB2_KERNEL is now
    supported, but only if !BIG_ENDIAN (The fixup code for Thumb-2
    currently assumes little-endian order.)

Tested using a single generic realview kernel on:
	ARM RealView PB-A8 (CONFIG_THUMB2_KERNEL={n,y})
	ARM RealView PBX-A9 (SMP)

Signed-off-by: Dave Martin <dave.martin@linaro.org>
Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

arch/arm/Kconfig

@@ -1229,7 +1229,7 @@ config SMP
 config SMP_ON_UP
 	bool "Allow booting SMP kernel on uniprocessor systems (EXPERIMENTAL)"
 	depends on EXPERIMENTAL
-	depends on SMP && !XIP && !THUMB2_KERNEL
+	depends on SMP && !XIP
 	default y
 	help
 	  SMP kernels contain instructions which fail on non-SMP processors.

arch/arm/include/asm/assembler.h

@@ -157,16 +157,24 @@
 #ifdef CONFIG_SMP
 #define ALT_SMP(instr...)					\
 9998:	instr
+/*
+ * Note: if you get assembler errors from ALT_UP() when building with
+ * CONFIG_THUMB2_KERNEL, you almost certainly need to use
+ * ALT_SMP( W(instr) ... )
+ */
 #define ALT_UP(instr...)					\
 	.pushsection ".alt.smp.init", "a"			;\
 	.long	9998b						;\
-	instr							;\
+9997:	instr							;\
+	.if . - 9997b != 4					;\
+		.error "ALT_UP() content must assemble to exactly 4 bytes";\
+	.endif							;\
 	.popsection
 #define ALT_UP_B(label)					\
 	.equ	up_b_offset, label - 9998b			;\
 	.pushsection ".alt.smp.init", "a"			;\
 	.long	9998b						;\
-	b	. + up_b_offset					;\
+	W(b)	. + up_b_offset					;\
 	.popsection
 #else
 #define ALT_SMP(instr...)
@@ -177,16 +185,24 @@
 /*
  * SMP data memory barrier
  */
-	.macro	smp_dmb
+	.macro	smp_dmb mode
 #ifdef CONFIG_SMP
 #if __LINUX_ARM_ARCH__ >= 7
+	.ifeqs "\mode","arm"
 	ALT_SMP(dmb)
+	.else
+	ALT_SMP(W(dmb))
+	.endif
 #elif __LINUX_ARM_ARCH__ == 6
 	ALT_SMP(mcr	p15, 0, r0, c7, c10, 5)	@ dmb
 #else
 #error Incompatible SMP platform
 #endif
+	.ifeqs "\mode","arm"
 	ALT_UP(nop)
+	.else
+	ALT_UP(W(nop))
+	.endif
 #endif
 	.endm
 

arch/arm/kernel/entry-armv.S

@@ -842,7 +842,7 @@ __kuser_helper_start:
  */
 
 __kuser_memory_barrier:				@ 0xffff0fa0
-	smp_dmb
+	smp_dmb	arm
 	usr_ret	lr
 
 	.align	5
@@ -959,7 +959,7 @@ kuser_cmpxchg_fixup:
 
 #else
 
-	smp_dmb
+	smp_dmb	arm
 1:	ldrex	r3, [r2]
 	subs	r3, r3, r0
 	strexeq	r3, r1, [r2]

arch/arm/kernel/head.S

@@ -412,10 +412,17 @@ __fixup_smp_on_up:
 	add	r4, r4, r3
 	add	r5, r5, r3
 2:	cmp	r4, r5
+	movhs	pc, lr
 	ldmia	r4!, {r0, r6}
-	strlo	r6, [r0, r3]
-	blo	2b
-	mov	pc, lr
+ 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
 ENDPROC(__fixup_smp)
 
 1:	.word	.