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
  ...

arch/arm64/mm/proc.S

@@ -30,7 +30,9 @@
 
 #ifdef CONFIG_ARM64_64K_PAGES
 #define TCR_TG_FLAGS	TCR_TG0_64K | TCR_TG1_64K
-#else
+#elif defined(CONFIG_ARM64_16K_PAGES)
+#define TCR_TG_FLAGS	TCR_TG0_16K | TCR_TG1_16K
+#else /* CONFIG_ARM64_4K_PAGES */
 #define TCR_TG_FLAGS	TCR_TG0_4K | TCR_TG1_4K
 #endif
 
@@ -130,7 +132,7 @@ ENDPROC(cpu_do_resume)
  *	- pgd_phys - physical address of new TTB
  */
 ENTRY(cpu_do_switch_mm)
-	mmid	w1, x1				// get mm->context.id
+	mmid	x1, x1				// get mm->context.id
 	bfi	x0, x1, #48, #16		// set the ASID
 	msr	ttbr0_el1, x0			// set TTBR0
 	isb
@@ -146,8 +148,8 @@ ENDPROC(cpu_do_switch_mm)
  *	value of the SCTLR_EL1 register.
  */
 ENTRY(__cpu_setup)
-	tlbi	vmalle1is			// invalidate I + D TLBs
-	dsb	ish
+	tlbi	vmalle1				// Invalidate local TLB
+	dsb	nsh
 
 	mov	x0, #3 << 20
 	msr	cpacr_el1, x0			// Enable FP/ASIMD