Merge branch 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm

Pull ARM updates from Russell King:
 "Included in this update are both some long term fixes and some new
  features.

  Fixes:

   - An integer overflow in the calculation of ELF_ET_DYN_BASE.

   - Avoiding OOMs for high-order IOMMU allocations

   - SMP requires the data cache to be enabled for synchronisation
     primitives to work, so prevent the CPU_DCACHE_DISABLE option being
     visible on SMP builds.

   - A bug going back 10+ years in the noMMU ARM94* CPU support code,
     where it corrupts registers.  Found by folk getting Linux running
     on their cameras.

   - Versatile Express needs an errata workaround enabled for CPU
     hot-unplug to work.

  Features:

   - Clean up module linker by handling out of range relocations
     separately from relocation cases we don't handle.

   - Fix a long term bug in the pci_mmap_page_range() code, which we
     hope won't impact userspace (we hope there's no users of the
     existing broken interface.)

   - Don't map DMA coherent allocations when we don't have a MMU.

   - Drop experimental status for SMP_ON_UP.

   - Warn when DT doesn't specify ePAPR mandatory cache properties.

   - Add documentation concerning how we find the start of physical
     memory for AUTO_ZRELADDR kernels, detailing why we have chosen the
     mask and the implications of changing it.

   - Updates from Ard Biesheuvel to address some issues with large
     kernels (such as allyesconfig) failing to link.

   - Allow hibernation to work on modern (ARMv7) CPUs - this appears to
     have never worked in the past on these CPUs.

   - Enable IRQ_SHOW_LEVEL, which changes the /proc/interrupts output
     format (hopefully without userspace breaking...  let's hope that if
     it causes someone a problem, they tell us.)

   - Fix tegra-ahb DT offsets.

   - Rework ARM errata 643719 code (and ARMv7 flush_cache_louis()/
     flush_dcache_all()) code to be more efficient, and enable this
     errata workaround by default for ARMv7+SMP CPUs.  This complements
     the Versatile Express fix above.

   - Rework ARMv7 context code for errata 430973, so that only Cortex A8
     CPUs are impacted by the branch target buffer flush when this
     errata is enabled.  Also update the help text to indicate that all
     r1p* A8 CPUs are impacted.

   - Switch ARM to the generic show_mem() implementation, it conveys all
     the information which we were already reporting.

   - Prevent slow timer sources being used for udelay() - timers running
     at less than 1MHz are not useful for this, and can cause udelay()
     to return immediately, without any wait.  Using such a slow timer
     is silly.

   - VDSO support for 32-bit ARM, mainly for gettimeofday() using the
     ARM architected timer.

   - Perf support for Scorpion performance monitoring units"

vdso semantic conflict fixed up as per linux-next.

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: (52 commits)
  ARM: update errata 430973 documentation to cover Cortex A8 r1p*
  ARM: ensure delay timer has sufficient accuracy for delays
  ARM: switch to use the generic show_mem() implementation
  ARM: proc-v7: avoid errata 430973 workaround for non-Cortex A8 CPUs
  ARM: enable ARM errata 643719 workaround by default
  ARM: cache-v7: optimise test for Cortex A9 r0pX devices
  ARM: cache-v7: optimise branches in v7_flush_cache_louis
  ARM: cache-v7: consolidate initialisation of cache level index
  ARM: cache-v7: shift CLIDR to extract appropriate field before masking
  ARM: cache-v7: use movw/movt instructions
  ARM: allow 16-bit instructions in ALT_UP()
  ARM: proc-arm94*.S: fix setup function
  ARM: vexpress: fix CPU hotplug with CT9x4 tile.
  ARM: 8276/1: Make CPU_DCACHE_DISABLE depend on !SMP
  ARM: 8335/1: Documentation: DT bindings: Tegra AHB: document the legacy base address
  ARM: 8334/1: amba: tegra-ahb: detect and correct bogus base address
  ARM: 8333/1: amba: tegra-ahb: fix register offsets in the macros
  ARM: 8339/1: Enable CONFIG_GENERIC_IRQ_SHOW_LEVEL
  ARM: 8338/1: kexec: Relax SMP validation to improve DT compatibility
  ARM: 8337/1: mm: Do not invoke OOM for higher order IOMMU DMA allocations
  ...

1 files changed, 19 insertions, 19 deletions

diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index b966656..a134d8a 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -36,10 +36,10 @@ ENTRY(v7_invalidate_l1)
        mcr     p15, 2, r0, c0, c0, 0
        mrc     p15, 1, r0, c0, c0, 0
 
-       ldr     r1, =0x7fff
+       movw    r1, #0x7fff
        and     r2, r1, r0, lsr #13
 
-       ldr     r1, =0x3ff
+       movw    r1, #0x3ff
 
        and     r3, r1, r0, lsr #3      @ NumWays - 1
        add     r2, r2, #1              @ NumSets
@@ -90,21 +90,20 @@ ENDPROC(v7_flush_icache_all)
 ENTRY(v7_flush_dcache_louis)
 	dmb					@ ensure ordering with previous memory accesses
 	mrc	p15, 1, r0, c0, c0, 1		@ read clidr, r0 = clidr
-	ALT_SMP(ands	r3, r0, #(7 << 21))	@ extract LoUIS from clidr
-	ALT_UP(ands	r3, r0, #(7 << 27))	@ extract LoUU from clidr
+ALT_SMP(mov	r3, r0, lsr #20)		@ move LoUIS into position
+ALT_UP(	mov	r3, r0, lsr #26)		@ move LoUU into position
+	ands	r3, r3, #7 << 1 		@ extract LoU*2 field from clidr
+	bne	start_flush_levels		@ LoU != 0, start flushing
 #ifdef CONFIG_ARM_ERRATA_643719
-	ALT_SMP(mrceq	p15, 0, r2, c0, c0, 0)	@ read main ID register
-	ALT_UP(reteq	lr)			@ LoUU is zero, so nothing to do
-	ldreq	r1, =0x410fc090                 @ ID of ARM Cortex A9 r0p?
-	biceq	r2, r2, #0x0000000f             @ clear minor revision number
-	teqeq	r2, r1                          @ test for errata affected core and if so...
-	orreqs	r3, #(1 << 21)			@   fix LoUIS value (and set flags state to 'ne')
+ALT_SMP(mrc	p15, 0, r2, c0, c0, 0)		@ read main ID register
+ALT_UP(	ret	lr)				@ LoUU is zero, so nothing to do
+	movw	r1, #:lower16:(0x410fc090 >> 4)	@ ID of ARM Cortex A9 r0p?
+	movt	r1, #:upper16:(0x410fc090 >> 4)
+	teq	r1, r2, lsr #4			@ test for errata affected core and if so...
+	moveq	r3, #1 << 1			@   fix LoUIS value
+	beq	start_flush_levels		@   start flushing cache levels
 #endif
-	ALT_SMP(mov	r3, r3, lsr #20)	@ r3 = LoUIS * 2
-	ALT_UP(mov	r3, r3, lsr #26)	@ r3 = LoUU * 2
-	reteq	lr				@ return if level == 0
-	mov	r10, #0				@ r10 (starting level) = 0
-	b	flush_levels			@ start flushing cache levels
+	ret	lr
 ENDPROC(v7_flush_dcache_louis)
 
 /*
@@ -119,9 +118,10 @@ ENDPROC(v7_flush_dcache_louis)
 ENTRY(v7_flush_dcache_all)
 	dmb					@ ensure ordering with previous memory accesses
 	mrc	p15, 1, r0, c0, c0, 1		@ read clidr
-	ands	r3, r0, #0x7000000		@ extract loc from clidr
-	mov	r3, r3, lsr #23			@ left align loc bit field
+	mov	r3, r0, lsr #23			@ move LoC into position
+	ands	r3, r3, #7 << 1			@ extract LoC*2 from clidr
 	beq	finished			@ if loc is 0, then no need to clean
+start_flush_levels:
 	mov	r10, #0				@ start clean at cache level 0
 flush_levels:
 	add	r2, r10, r10, lsr #1		@ work out 3x current cache level
@@ -140,10 +140,10 @@ flush_levels:
 #endif
 	and	r2, r1, #7			@ extract the length of the cache lines
 	add	r2, r2, #4			@ add 4 (line length offset)
-	ldr	r4, =0x3ff
+	movw	r4, #0x3ff
 	ands	r4, r4, r1, lsr #3		@ find maximum number on the way size
 	clz	r5, r4				@ find bit position of way size increment
-	ldr	r7, =0x7fff
+	movw	r7, #0x7fff
 	ands	r7, r7, r1, lsr #13		@ extract max number of the index size
 loop1:
 	mov	r9, r7				@ create working copy of max index