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

Pull ARM updates from Russell King:
 "Included in this series are:

   1. BE8 (modern big endian) changes for ARM from Ben Dooks
   2. big.Little support from Nicolas Pitre and Dave Martin
   3. support for LPAE systems with all system memory above 4GB
   4. Perf updates from Will Deacon
   5. Additional prefetching and other performance improvements from Will.
   6. Neon-optimised AES implementation fro Ard.
   7. A number of smaller fixes scattered around the place.

  There is a rather horrid merge conflict in tools/perf - I was never
  notified of the conflict because it originally occurred between Will's
  tree and other stuff.  Consequently I have a resolution which Will
  forwarded me, which I'll forward on immediately after sending this
  mail.

  The other notable thing is I'm expecting some build breakage in the
  crypto stuff on ARM only with Ard's AES patches.  These were merged
  into a stable git branch which others had already pulled, so there's
  little I can do about this.  The problem is caused because these
  patches have a dependency on some code in the crypto git tree - I
  tried requesting a branch I can pull to resolve these, and all I got
  each time from the crypto people was "we'll revert our patches then"
  which would only make things worse since I still don't have the
  dependent patches.  I've no idea what's going on there or how to
  resolve that, and since I can't split these patches from the rest of
  this pull request, I'm rather stuck with pushing this as-is or
  reverting Ard's patches.

  Since it should "come out in the wash" I've left them in - the only
  build problems they seem to cause at the moment are with randconfigs,
  and since it's a new feature anyway.  However, if by -rc1 the
  dependencies aren't in, I think it'd be best to revert Ard's patches"

I resolved the perf conflict roughly as per the patch sent by Russell,
but there may be some differences.  Any errors are likely mine.  Let's
see how the crypto issues work out..

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (110 commits)
  ARM: 7868/1: arm/arm64: remove atomic_clear_mask() in "include/asm/atomic.h"
  ARM: 7867/1: include: asm: use 'int' instead of 'unsigned long' for 'oldval' in atomic_cmpxchg().
  ARM: 7866/1: include: asm: use 'long long' instead of 'u64' within atomic.h
  ARM: 7871/1: amba: Extend number of IRQS
  ARM: 7887/1: Don't smp_cross_call() on UP devices in arch_irq_work_raise()
  ARM: 7872/1: Support arch_irq_work_raise() via self IPIs
  ARM: 7880/1: Clear the IT state independent of the Thumb-2 mode
  ARM: 7878/1: nommu: Implement dummy early_paging_init()
  ARM: 7876/1: clear Thumb-2 IT state on exception handling
  ARM: 7874/2: bL_switcher: Remove cpu_hotplug_driver_{lock,unlock}()
  ARM: footbridge: fix build warnings for netwinder
  ARM: 7873/1: vfp: clear vfp_current_hw_state for dying cpu
  ARM: fix misplaced arch_virt_to_idmap()
  ARM: 7848/1: mcpm: Implement cpu_kill() to synchronise on powerdown
  ARM: 7847/1: mcpm: Factor out logical-to-physical CPU translation
  ARM: 7869/1: remove unused XSCALE_PMU Kconfig param
  ARM: 7864/1: Handle 64-bit memory in case of 32-bit phys_addr_t
  ARM: 7863/1: Let arm_add_memory() always use 64-bit arguments
  ARM: 7862/1: pcpu: replace __get_cpu_var_uses
  ARM: 7861/1: cacheflush: consolidate single-CPU ARMv7 cache disabling code
  ...

1 files changed, 34 insertions, 23 deletions

diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index c9dfff3b8008..45e478157278 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -24,6 +24,7 @@
 #include <asm/sections.h>
 #include <asm/smp_plat.h>
 #include <asm/unwind.h>
+#include <asm/opcodes.h>
 
 #ifdef CONFIG_XIP_KERNEL
 /*
@@ -60,6 +61,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
                 Elf32_Sym *sym;
                 const char *symname;
                 s32 offset;
+                u32 tmp;
 #ifdef CONFIG_THUMB2_KERNEL
                 u32 upper, lower, sign, j1, j2;
 #endif
@@ -95,7 +97,8 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
                 case R_ARM_PC24:
                 case R_ARM_CALL:
                 case R_ARM_JUMP24:
-                        offset = (*(u32 *)loc & 0x00ffffff) << 2;
+                        offset = __mem_to_opcode_arm(*(u32 *)loc);
+                        offset = (offset & 0x00ffffff) << 2;
                         if (offset & 0x02000000)
                                 offset -= 0x04000000;
 
@@ -111,9 +114,10 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
                         }
 
                         offset >>= 2;
+                        offset &= 0x00ffffff;
 
-                        *(u32 *)loc &= 0xff000000;
-                        *(u32 *)loc |= offset & 0x00ffffff;
+                        *(u32 *)loc &= __opcode_to_mem_arm(0xff000000);
+                        *(u32 *)loc |= __opcode_to_mem_arm(offset);
                         break;
 
                case R_ARM_V4BX:
@@ -121,8 +125,8 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
                         * other bits to re-code instruction as
                         * MOV PC,Rm.
                         */
-                       *(u32 *)loc &= 0xf000000f;
-                       *(u32 *)loc |= 0x01a0f000;
+                       *(u32 *)loc &= __opcode_to_mem_arm(0xf000000f);
+                       *(u32 *)loc |= __opcode_to_mem_arm(0x01a0f000);
                        break;
 
                 case R_ARM_PREL31:
@@ -132,7 +136,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 
                 case R_ARM_MOVW_ABS_NC:
                 case R_ARM_MOVT_ABS:
-                        offset = *(u32 *)loc;
+                        offset = tmp = __mem_to_opcode_arm(*(u32 *)loc);
                         offset = ((offset & 0xf0000) >> 4) | (offset & 0xfff);
                         offset = (offset ^ 0x8000) - 0x8000;
 
@@ -140,16 +144,18 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
                         if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_ABS)
                                 offset >>= 16;
 
-                        *(u32 *)loc &= 0xfff0f000;
-                        *(u32 *)loc |= ((offset & 0xf000) << 4) |
-                                        (offset & 0x0fff);
+                        tmp &= 0xfff0f000;
+                        tmp |= ((offset & 0xf000) << 4) |
+                                (offset & 0x0fff);
+
+                        *(u32 *)loc = __opcode_to_mem_arm(tmp);
                         break;
 
 #ifdef CONFIG_THUMB2_KERNEL
                 case R_ARM_THM_CALL:
                 case R_ARM_THM_JUMP24:
-                        upper = *(u16 *)loc;
-                        lower = *(u16 *)(loc + 2);
+                        upper = __mem_to_opcode_thumb16(*(u16 *)loc);
+                        lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2));
 
                         /*
                          * 25 bit signed address range (Thumb-2 BL and B.W
@@ -198,17 +204,20 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
                         sign = (offset >> 24) & 1;
                         j1 = sign ^ (~(offset >> 23) & 1);
                         j2 = sign ^ (~(offset >> 22) & 1);
-                        *(u16 *)loc = (u16)((upper & 0xf800) | (sign << 10) |
+                        upper = (u16)((upper & 0xf800) | (sign << 10) |
                                             ((offset >> 12) & 0x03ff));
-                        *(u16 *)(loc + 2) = (u16)((lower & 0xd000) |
-                                                  (j1 << 13) | (j2 << 11) |
-                                                  ((offset >> 1) & 0x07ff));
+                        lower = (u16)((lower & 0xd000) |
+                                      (j1 << 13) | (j2 << 11) |
+                                      ((offset >> 1) & 0x07ff));
+
+                        *(u16 *)loc = __opcode_to_mem_thumb16(upper);
+                        *(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower);
                         break;
 
                 case R_ARM_THM_MOVW_ABS_NC:
                 case R_ARM_THM_MOVT_ABS:
-                        upper = *(u16 *)loc;
-                        lower = *(u16 *)(loc + 2);
+                        upper = __mem_to_opcode_thumb16(*(u16 *)loc);
+                        lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2));
 
                         /*
                          * MOVT/MOVW instructions encoding in Thumb-2:
@@ -229,12 +238,14 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
                         if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_ABS)
                                 offset >>= 16;
 
-                        *(u16 *)loc = (u16)((upper & 0xfbf0) |
-                                            ((offset & 0xf000) >> 12) |
-                                            ((offset & 0x0800) >> 1));
-                        *(u16 *)(loc + 2) = (u16)((lower & 0x8f00) |
-                                                  ((offset & 0x0700) << 4) |
-                                                  (offset & 0x00ff));
+                        upper = (u16)((upper & 0xfbf0) |
+                                      ((offset & 0xf000) >> 12) |
+                                      ((offset & 0x0800) >> 1));
+                        lower = (u16)((lower & 0x8f00) |
+                                      ((offset & 0x0700) << 4) |
+                                      (offset & 0x00ff));
+                        *(u16 *)loc = __opcode_to_mem_thumb16(upper);
+                        *(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower);
                         break;
 #endif