Merge branch 'fixes' of git://git.linaro.org/people/rmk/linux-arm

Pull ARM fixes from Russell King:
 "This fixes various issues found during July"

* 'fixes' of git://git.linaro.org/people/rmk/linux-arm:
  ARM: 7479/1: mm: avoid NULL dereference when flushing gate_vma with VIVT caches
  ARM: Fix undefined instruction exception handling
  ARM: 7480/1: only call smp_send_stop() on SMP
  ARM: 7478/1: errata: extend workaround for erratum #720789
  ARM: 7477/1: vfp: Always save VFP state in vfp_pm_suspend on UP
  ARM: 7476/1: vfp: only clear vfp state for current cpu in vfp_pm_suspend
  ARM: 7468/1: ftrace: Trace function entry before updating index
  ARM: 7467/1: mutex: use generic xchg-based implementation for ARMv6+
  ARM: 7466/1: disable interrupt before spinning endlessly
  ARM: 7465/1: Handle >4GB memory sizes in device tree and mem=size@start option

arch/arm/vfp/entry.S

@@ -7,18 +7,20 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * Basic entry code, called from the kernel's undefined instruction trap.
- *  r0  = faulted instruction
- *  r5  = faulted PC+4
- *  r9  = successful return
- *  r10 = thread_info structure
- *  lr  = failure return
  */
 #include <asm/thread_info.h>
 #include <asm/vfpmacros.h>
 #include "../kernel/entry-header.S"
 
+@ VFP entry point.
+@
+@  r0  = instruction opcode (32-bit ARM or two 16-bit Thumb)
+@  r2  = PC value to resume execution after successful emulation
+@  r9  = normal "successful" return address
+@  r10 = this threads thread_info structure
+@  lr  = unrecognised instruction return address
+@  IRQs disabled.
+@
 ENTRY(do_vfp)
 #ifdef CONFIG_PREEMPT
 	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count

arch/arm/vfp/vfphw.S

@@ -62,13 +62,13 @@
 
 @ VFP hardware support entry point.
 @
-@  r0  = faulted instruction
-@  r2  = faulted PC+4
-@  r9  = successful return
+@  r0  = instruction opcode (32-bit ARM or two 16-bit Thumb)
+@  r2  = PC value to resume execution after successful emulation
+@  r9  = normal "successful" return address
 @  r10 = vfp_state union
 @  r11 = CPU number
-@  lr  = failure return
-
+@  lr  = unrecognised instruction return address
+@  IRQs enabled.
 ENTRY(vfp_support_entry)
 	DBGSTR3	"instr %08x pc %08x state %p", r0, r2, r10
 
@@ -162,9 +162,12 @@ vfp_hw_state_valid:
 					@ exception before retrying branch
 					@ out before setting an FPEXC that
 					@ stops us reading stuff
-	VFPFMXR	FPEXC, r1		@ restore FPEXC last
-	sub	r2, r2, #4
-	str	r2, [sp, #S_PC]		@ retry the instruction
+	VFPFMXR	FPEXC, r1		@ Restore FPEXC last
+	sub	r2, r2, #4		@ Retry current instruction - if Thumb
+	str	r2, [sp, #S_PC]		@ mode it's two 16-bit instructions,
+					@ else it's one 32-bit instruction, so
+					@ always subtract 4 from the following
+					@ instruction address.
 #ifdef CONFIG_PREEMPT
 	get_thread_info	r10
 	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count

arch/arm/vfp/vfpmodule.c

@@ -457,10 +457,16 @@ static int vfp_pm_suspend(void)
 
 		/* disable, just in case */
 		fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN);
+	} else if (vfp_current_hw_state[ti->cpu]) {
+#ifndef CONFIG_SMP
+		fmxr(FPEXC, fpexc | FPEXC_EN);
+		vfp_save_state(vfp_current_hw_state[ti->cpu], fpexc);
+		fmxr(FPEXC, fpexc);
+#endif
 	}
 
 	/* clear any information we had about last context state */
-	memset(vfp_current_hw_state, 0, sizeof(vfp_current_hw_state));
+	vfp_current_hw_state[ti->cpu] = NULL;
 
 	return 0;
 }