Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:

 - "genirq: Introduce generic irq migration for cpu hotunplugged" patch
   merged from tip/irq/for-arm to allow the arm64-specific part to be
   upstreamed via the arm64 tree

 - CPU feature detection reworked to cope with heterogeneous systems
   where CPUs may not have exactly the same features.  The features
   reported by the kernel via internal data structures or ELF_HWCAP are
   delayed until all the CPUs are up (and before user space starts)

 - Support for 16KB pages, with the additional bonus of a 36-bit VA
   space, though the latter only depending on EXPERT

 - Implement native {relaxed, acquire, release} atomics for arm64

 - New ASID allocation algorithm which avoids IPI on roll-over, together
   with TLB invalidation optimisations (using local vs global where
   feasible)

 - KASan support for arm64

 - EFI_STUB clean-up and isolation for the kernel proper (required by
   KASan)

 - copy_{to,from,in}_user optimisations (sharing the memcpy template)

 - perf: moving arm64 to the arm32/64 shared PMU framework

 - L1_CACHE_BYTES increased to 128 to accommodate Cavium hardware

 - Support for the contiguous PTE hint on kernel mapping (16 consecutive
   entries may be able to use a single TLB entry)

 - Generic CONFIG_HZ now used on arm64

 - defconfig updates

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (91 commits)
  arm64/efi: fix libstub build under CONFIG_MODVERSIONS
  ARM64: Enable multi-core scheduler support by default
  arm64/efi: move arm64 specific stub C code to libstub
  arm64: page-align sections for DEBUG_RODATA
  arm64: Fix build with CONFIG_ZONE_DMA=n
  arm64: Fix compat register mappings
  arm64: Increase the max granular size
  arm64: remove bogus TASK_SIZE_64 check
  arm64: make Timer Interrupt Frequency selectable
  arm64/mm: use PAGE_ALIGNED instead of IS_ALIGNED
  arm64: cachetype: fix definitions of ICACHEF_* flags
  arm64: cpufeature: declare enable_cpu_capabilities as static
  genirq: Make the cpuhotplug migration code less noisy
  arm64: Constify hwcap name string arrays
  arm64/kvm: Make use of the system wide safe values
  arm64/debug: Make use of the system wide safe value
  arm64: Move FP/ASIMD hwcap handling to common code
  arm64/HWCAP: Use system wide safe values
  arm64/capabilities: Make use of system wide safe value
  arm64: Delay cpu feature capability checks
  ...

1 files changed, 44 insertions, 34 deletions

diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index 1be9ef27be97..4699cd74f87e 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -18,6 +18,7 @@
 
 #include <asm/alternative.h>
 #include <asm/assembler.h>
+#include <asm/cache.h>
 #include <asm/cpufeature.h>
 #include <asm/sysreg.h>
 
@@ -31,49 +32,58 @@
  * Returns:
  *	x0 - bytes not copied
  */
+
+	.macro ldrb1 ptr, regB, val
+	USER(9998f, ldrb  \ptr, [\regB], \val)
+	.endm
+
+	.macro strb1 ptr, regB, val
+	strb \ptr, [\regB], \val
+	.endm
+
+	.macro ldrh1 ptr, regB, val
+	USER(9998f, ldrh  \ptr, [\regB], \val)
+	.endm
+
+	.macro strh1 ptr, regB, val
+	strh \ptr, [\regB], \val
+	.endm
+
+	.macro ldr1 ptr, regB, val
+	USER(9998f, ldr \ptr, [\regB], \val)
+	.endm
+
+	.macro str1 ptr, regB, val
+	str \ptr, [\regB], \val
+	.endm
+
+	.macro ldp1 ptr, regB, regC, val
+	USER(9998f, ldp \ptr, \regB, [\regC], \val)
+	.endm
+
+	.macro stp1 ptr, regB, regC, val
+	stp \ptr, \regB, [\regC], \val
+	.endm
+
+end	.req	x5
 ENTRY(__copy_from_user)
 ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \
 	    CONFIG_ARM64_PAN)
-	add	x5, x1, x2			// upper user buffer boundary
-	subs	x2, x2, #16
-	b.mi	1f
-0:
-USER(9f, ldp	x3, x4, [x1], #16)
-	subs	x2, x2, #16
-	stp	x3, x4, [x0], #16
-	b.pl	0b
-1:	adds	x2, x2, #8
-	b.mi	2f
-USER(9f, ldr	x3, [x1], #8	)
-	sub	x2, x2, #8
-	str	x3, [x0], #8
-2:	adds	x2, x2, #4
-	b.mi	3f
-USER(9f, ldr	w3, [x1], #4	)
-	sub	x2, x2, #4
-	str	w3, [x0], #4
-3:	adds	x2, x2, #2
-	b.mi	4f
-USER(9f, ldrh	w3, [x1], #2	)
-	sub	x2, x2, #2
-	strh	w3, [x0], #2
-4:	adds	x2, x2, #1
-	b.mi	5f
-USER(9f, ldrb	w3, [x1]	)
-	strb	w3, [x0]
-5:	mov	x0, #0
+	add	end, x0, x2
+#include "copy_template.S"
 ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \
 	    CONFIG_ARM64_PAN)
+	mov	x0, #0				// Nothing to copy
 	ret
 ENDPROC(__copy_from_user)
 
 	.section .fixup,"ax"
 	.align	2
-9:	sub	x2, x5, x1
-	mov	x3, x2
-10:	strb	wzr, [x0], #1			// zero remaining buffer space
-	subs	x3, x3, #1
-	b.ne	10b
-	mov	x0, x2				// bytes not copied
+9998:
+	sub	x0, end, dst
+9999:
+	strb	wzr, [dst], #1			// zero remaining buffer space
+	cmp	dst, end
+	b.lo	9999b
 	ret
 	.previous