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

Pull arm64 and cross-arch updates from Catalin Marinas:
 "Here's a slightly wider-spread set of updates for 5.9.

  Going outside the usual arch/arm64/ area is the removal of
  read_barrier_depends() series from Will and the MSI/IOMMU ID
  translation series from Lorenzo.

  The notable arm64 updates include ARMv8.4 TLBI range operations and
  translation level hint, time namespace support, and perf.

  Summary:

   - Removal of the tremendously unpopular read_barrier_depends()
     barrier, which is a NOP on all architectures apart from Alpha, in
     favour of allowing architectures to override READ_ONCE() and do
     whatever dance they need to do to ensure address dependencies
     provide LOAD -> LOAD/STORE ordering.

     This work also offers a potential solution if compilers are shown
     to convert LOAD -> LOAD address dependencies into control
     dependencies (e.g. under LTO), as weakly ordered architectures will
     effectively be able to upgrade READ_ONCE() to smp_load_acquire().
     The latter case is not used yet, but will be discussed further at
     LPC.

   - Make the MSI/IOMMU input/output ID translation PCI agnostic,
     augment the MSI/IOMMU ACPI/OF ID mapping APIs to accept an input ID
     bus-specific parameter and apply the resulting changes to the
     device ID space provided by the Freescale FSL bus.

   - arm64 support for TLBI range operations and translation table level
     hints (part of the ARMv8.4 architecture version).

   - Time namespace support for arm64.

   - Export the virtual and physical address sizes in vmcoreinfo for
     makedumpfile and crash utilities.

   - CPU feature handling cleanups and checks for programmer errors
     (overlapping bit-fields).

   - ACPI updates for arm64: disallow AML accesses to EFI code regions
     and kernel memory.

   - perf updates for arm64.

   - Miscellaneous fixes and cleanups, most notably PLT counting
     optimisation for module loading, recordmcount fix to ignore
     relocations other than R_AARCH64_CALL26, CMA areas reserved for
     gigantic pages on 16K and 64K configurations.

   - Trivial typos, duplicate words"

Link: http://lkml.kernel.org/r/20200710165203.31284-1-will@kernel.org
Link: http://lkml.kernel.org/r/20200619082013.13661-1-lorenzo.pieralisi@arm.com

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (82 commits)
  arm64: use IRQ_STACK_SIZE instead of THREAD_SIZE for irq stack
  arm64/mm: save memory access in check_and_switch_context() fast switch path
  arm64: sigcontext.h: delete duplicated word
  arm64: ptrace.h: delete duplicated word
  arm64: pgtable-hwdef.h: delete duplicated words
  bus: fsl-mc: Add ACPI support for fsl-mc
  bus/fsl-mc: Refactor the MSI domain creation in the DPRC driver
  of/irq: Make of_msi_map_rid() PCI bus agnostic
  of/irq: make of_msi_map_get_device_domain() bus agnostic
  dt-bindings: arm: fsl: Add msi-map device-tree binding for fsl-mc bus
  of/device: Add input id to of_dma_configure()
  of/iommu: Make of_map_rid() PCI agnostic
  ACPI/IORT: Add an input ID to acpi_dma_configure()
  ACPI/IORT: Remove useless PCI bus walk
  ACPI/IORT: Make iort_msi_map_rid() PCI agnostic
  ACPI/IORT: Make iort_get_device_domain IRQ domain agnostic
  ACPI/IORT: Make iort_match_node_callback walk the ACPI namespace for NC
  arm64: enable time namespace support
  arm64/vdso: Restrict splitting VVAR VMA
  arm64/vdso: Handle faults on timens page
  ...

44 files changed, 961 insertions, 257 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 66dc41fd49f2..73aee7290cdf 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -118,6 +118,7 @@ config ARM64
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_GETTIMEOFDAY
+	select GENERIC_VDSO_TIME_NS
 	select HANDLE_DOMAIN_IRQ
 	select HARDIRQS_SW_RESEND
 	select HAVE_PCI
@@ -1327,6 +1328,8 @@ config SWP_EMULATION
 	  ARMv8 obsoletes the use of A32 SWP/SWPB instructions such that
 	  they are always undefined. Say Y here to enable software
 	  emulation of these instructions for userspace using LDXR/STXR.
+	  This feature can be controlled at runtime with the abi.swp
+	  sysctl which is disabled by default.
 
 	  In some older versions of glibc [<=2.8] SWP is used during futex
 	  trylock() operations with the assumption that the code will not
@@ -1353,7 +1356,8 @@ config CP15_BARRIER_EMULATION
 	  Say Y here to enable software emulation of these
 	  instructions for AArch32 userspace code. When this option is
 	  enabled, CP15 barrier usage is traced which can help
-	  identify software that needs updating.
+	  identify software that needs updating. This feature can be
+	  controlled at runtime with the abi.cp15_barrier sysctl.
 
 	  If unsure, say Y
 
@@ -1364,7 +1368,8 @@ config SETEND_EMULATION
 	  AArch32 EL0, and is deprecated in ARMv8.
 
 	  Say Y here to enable software emulation of the instruction
-	  for AArch32 userspace code.
+	  for AArch32 userspace code. This feature can be controlled
+	  at runtime with the abi.setend sysctl.
 
 	  Note: All the cpus on the system must have mixed endian support at EL0
 	  for this feature to be enabled. If a new CPU - which doesn't support mixed
@@ -1596,6 +1601,20 @@ config ARM64_AMU_EXTN
 	  correctly reflect reality. Most commonly, the value read will be 0,
 	  indicating that the counter is not enabled.
 
+config AS_HAS_ARMV8_4
+	def_bool $(cc-option,-Wa$(comma)-march=armv8.4-a)
+
+config ARM64_TLB_RANGE
+	bool "Enable support for tlbi range feature"
+	default y
+	depends on AS_HAS_ARMV8_4
+	help
+	  ARMv8.4-TLBI provides TLBI invalidation instruction that apply to a
+	  range of input addresses.
+
+	  The feature introduces new assembly instructions, and they were
+	  support when binutils >= 2.30.
+
 endmenu
 
 menu "ARMv8.5 architectural features"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 70f5905954dd..55bc8546d9c7 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -82,11 +82,18 @@ endif
 # compiler to generate them and consequently to break the single image contract
 # we pass it only to the assembler. This option is utilized only in case of non
 # integrated assemblers.
+ifneq ($(CONFIG_AS_HAS_ARMV8_4), y)
 branch-prot-flags-$(CONFIG_AS_HAS_PAC) += -Wa,-march=armv8.3-a
 endif
+endif
 
 KBUILD_CFLAGS += $(branch-prot-flags-y)
 
+ifeq ($(CONFIG_AS_HAS_ARMV8_4), y)
+# make sure to pass the newest target architecture to -march.
+KBUILD_CFLAGS	+= -Wa,-march=armv8.4-a
+endif
+
 ifeq ($(CONFIG_SHADOW_CALL_STACK), y)
 KBUILD_CFLAGS	+= -ffixed-x18
 endif
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 2ca7ba69c318..39273b5c14be 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -66,6 +66,7 @@ CONFIG_SCHED_SMT=y
 CONFIG_NUMA=y
 CONFIG_SECCOMP=y
 CONFIG_KEXEC=y
+CONFIG_KEXEC_FILE=y
 CONFIG_CRASH_DUMP=y
 CONFIG_XEN=y
 CONFIG_COMPAT=y
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index a45366c3909b..bd68e1b7f29f 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -47,20 +47,7 @@
 pgprot_t __acpi_get_mem_attribute(phys_addr_t addr);
 
 /* ACPI table mapping after acpi_permanent_mmap is set */
-static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys,
-					    acpi_size size)
-{
-	/* For normal memory we already have a cacheable mapping. */
-	if (memblock_is_map_memory(phys))
-		return (void __iomem *)__phys_to_virt(phys);
-
-	/*
-	 * We should still honor the memory's attribute here because
-	 * crash dump kernel possibly excludes some ACPI (reclaim)
-	 * regions from memblock list.
-	 */
-	return __ioremap(phys, size, __acpi_get_mem_attribute(phys));
-}
+void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size);
 #define acpi_os_ioremap acpi_os_ioremap
 
 typedef u64 phys_cpuid_t;
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index d7b3bb0cb180..07b643a70710 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -62,7 +62,9 @@
 #define ARM64_HAS_GENERIC_AUTH			52
 #define ARM64_HAS_32BIT_EL1			53
 #define ARM64_BTI				54
+#define ARM64_HAS_ARMv8_4_TTL			55
+#define ARM64_HAS_TLB_RANGE			56
 
-#define ARM64_NCAPS				55
+#define ARM64_NCAPS				57
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index f7c3d1ff091d..89b4f0142c28 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -692,6 +692,12 @@ static inline bool system_supports_bti(void)
 	return IS_ENABLED(CONFIG_ARM64_BTI) && cpus_have_const_cap(ARM64_BTI);
 }
 
+static inline bool system_supports_tlb_range(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_TLB_RANGE) &&
+		cpus_have_const_cap(ARM64_HAS_TLB_RANGE);
+}
+
 #define ARM64_BP_HARDEN_UNKNOWN		-1
 #define ARM64_BP_HARDEN_WA_NEEDED	0
 #define ARM64_BP_HARDEN_NOT_REQUIRED	1
@@ -774,6 +780,7 @@ static inline unsigned int get_vmid_bits(u64 mmfr1)
 }
 
 u32 get_kvm_ipa_limit(void);
+void dump_cpu_features(void);
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 94ba0c5bced2..5abf91e3494c 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -49,6 +49,8 @@ extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
 				 pte_t *ptep, pte_t pte, unsigned long sz);
 #define set_huge_swap_pte_at set_huge_swap_pte_at
 
+void __init arm64_hugetlb_cma_reserve(void);
+
 #include <asm-generic/hugetlb.h>
 
 #endif /* __ASM_HUGETLB_H */
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index d683bcbf1e7c..22f73fe09030 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -95,6 +95,7 @@
 #define KERNEL_HWCAP_DGH		__khwcap2_feature(DGH)
 #define KERNEL_HWCAP_RNG		__khwcap2_feature(RNG)
 #define KERNEL_HWCAP_BTI		__khwcap2_feature(BTI)
+/* reserved for KERNEL_HWCAP_MTE	__khwcap2_feature(MTE) */
 
 /*
  * This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index 3bf626f6fe0c..329fb15f6bac 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -8,7 +8,7 @@
 #ifndef __ASM_KERNEL_PGTABLE_H
 #define __ASM_KERNEL_PGTABLE_H
 
-#include <linux/pgtable.h>
+#include <asm/pgtable-hwdef.h>
 #include <asm/sparsemem.h>
 
 /*
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index a1871bb32bb1..afa722504bfd 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -10,11 +10,8 @@
 #ifndef __ASM_MEMORY_H
 #define __ASM_MEMORY_H
 
-#include <linux/compiler.h>
 #include <linux/const.h>
 #include <linux/sizes.h>
-#include <linux/types.h>
-#include <asm/bug.h>
 #include <asm/page-def.h>
 
 /*
@@ -157,11 +154,15 @@
 #endif
 
 #ifndef __ASSEMBLY__
-extern u64			vabits_actual;
-#define PAGE_END		(_PAGE_END(vabits_actual))
 
 #include <linux/bitops.h>
+#include <linux/compiler.h>
 #include <linux/mmdebug.h>
+#include <linux/types.h>
+#include <asm/bug.h>
+
+extern u64			vabits_actual;
+#define PAGE_END		(_PAGE_END(vabits_actual))
 
 extern s64			physvirt_offset;
 extern s64			memstart_addr;
@@ -322,6 +323,7 @@ static inline void *phys_to_virt(phys_addr_t x)
 	__is_lm_address(__addr) && pfn_valid(virt_to_pfn(__addr));	\
 })
 
+void dump_mem_limit(void);
 #endif /* !ASSEMBLY */
 
 /*
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index b0bd9b55594c..f2d7537d6f83 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -175,7 +175,7 @@ static inline void cpu_replace_ttbr1(pgd_t *pgdp)
  * take CPU migration into account.
  */
 #define destroy_context(mm)		do { } while(0)
-void check_and_switch_context(struct mm_struct *mm, unsigned int cpu);
+void check_and_switch_context(struct mm_struct *mm);
 
 #define init_new_context(tsk,mm)	({ atomic64_set(&(mm)->context.id, 0); 0; })
 
@@ -214,8 +214,6 @@ enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 
 static inline void __switch_mm(struct mm_struct *next)
 {
-	unsigned int cpu = smp_processor_id();
-
 	/*
 	 * init_mm.pgd does not contain any user mappings and it is always
 	 * active for kernel addresses in TTBR1. Just set the reserved TTBR0.
@@ -225,7 +223,7 @@ static inline void __switch_mm(struct mm_struct *next)
 		return;
 	}
 
-	check_and_switch_context(next, cpu);
+	check_and_switch_context(next);
 }
 
 static inline void
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index e7765b62c712..2c2d7dbe8a02 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -72,6 +72,13 @@
 #define ARMV8_PMUV3_PERFCTR_LL_CACHE_RD				0x36
 #define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD			0x37
 #define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD			0x38
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_LMISS_RD			0x39
+#define ARMV8_PMUV3_PERFCTR_OP_RETIRED				0x3A
+#define ARMV8_PMUV3_PERFCTR_OP_SPEC				0x3B
+#define ARMV8_PMUV3_PERFCTR_STALL				0x3C
+#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND			0x3D
+#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND			0x3E
+#define ARMV8_PMUV3_PERFCTR_STALL_SLOT				0x3F
 
 /* Statistical profiling extension microarchitectural events */
 #define	ARMV8_SPE_PERFCTR_SAMPLE_POP				0x4000
@@ -79,6 +86,26 @@
 #define	ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE			0x4002
 #define	ARMV8_SPE_PERFCTR_SAMPLE_COLLISION			0x4003
 
+/* AMUv1 architecture events */
+#define	ARMV8_AMU_PERFCTR_CNT_CYCLES				0x4004
+#define	ARMV8_AMU_PERFCTR_STALL_BACKEND_MEM			0x4005
+
+/* long-latency read miss events */
+#define	ARMV8_PMUV3_PERFCTR_L1I_CACHE_LMISS			0x4006
+#define	ARMV8_PMUV3_PERFCTR_L2D_CACHE_LMISS_RD			0x4009
+#define	ARMV8_PMUV3_PERFCTR_L2I_CACHE_LMISS			0x400A
+#define	ARMV8_PMUV3_PERFCTR_L3D_CACHE_LMISS_RD			0x400B
+
+/* additional latency from alignment events */
+#define	ARMV8_PMUV3_PERFCTR_LDST_ALIGN_LAT			0x4020
+#define	ARMV8_PMUV3_PERFCTR_LD_ALIGN_LAT			0x4021
+#define	ARMV8_PMUV3_PERFCTR_ST_ALIGN_LAT			0x4022
+
+/* Armv8.5 Memory Tagging Extension events */
+#define	ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED			0x4024
+#define	ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_RD			0x4025
+#define	ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_WR			0x4026
+
 /* ARMv8 recommended implementation defined event types */
 #define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD			0x40
 #define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR			0x41
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 9c91a8f93a0e..d400a4d9aee2 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -29,7 +29,7 @@
  * Size mapped by an entry at level n ( 0 <= n <= 3)
  * We map (PAGE_SHIFT - 3) at all translation levels and PAGE_SHIFT bits
  * in the final page. The maximum number of translation levels supported by
- * the architecture is 4. Hence, starting at at level n, we have further
+ * the architecture is 4. Hence, starting at level n, we have further
  * ((4 - n) - 1) levels of translation excluding the offset within the page.
  * So, the total number of bits mapped by an entry at level n is :
  *
@@ -82,23 +82,23 @@
  * Contiguous page definitions.
  */
 #ifdef CONFIG_ARM64_64K_PAGES
-#define CONT_PTE_SHIFT		5
-#define CONT_PMD_SHIFT		5
+#define CONT_PTE_SHIFT		(5 + PAGE_SHIFT)
+#define CONT_PMD_SHIFT		(5 + PMD_SHIFT)
 #elif defined(CONFIG_ARM64_16K_PAGES)
-#define CONT_PTE_SHIFT		7
-#define CONT_PMD_SHIFT		5
+#define CONT_PTE_SHIFT		(7 + PAGE_SHIFT)
+#define CONT_PMD_SHIFT		(5 + PMD_SHIFT)
 #else
-#define CONT_PTE_SHIFT		4
-#define CONT_PMD_SHIFT		4
+#define CONT_PTE_SHIFT		(4 + PAGE_SHIFT)
+#define CONT_PMD_SHIFT		(4 + PMD_SHIFT)
 #endif
 
-#define CONT_PTES		(1 << CONT_PTE_SHIFT)
+#define CONT_PTES		(1 << (CONT_PTE_SHIFT - PAGE_SHIFT))
 #define CONT_PTE_SIZE		(CONT_PTES * PAGE_SIZE)
 #define CONT_PTE_MASK		(~(CONT_PTE_SIZE - 1))
-#define CONT_PMDS		(1 << CONT_PMD_SHIFT)
+#define CONT_PMDS		(1 << (CONT_PMD_SHIFT - PMD_SHIFT))
 #define CONT_PMD_SIZE		(CONT_PMDS * PMD_SIZE)
 #define CONT_PMD_MASK		(~(CONT_PMD_SIZE - 1))
-/* the the numerical offset of the PTE within a range of CONT_PTES */
+/* the numerical offset of the PTE within a range of CONT_PTES */
 #define CONT_RANGE_OFFSET(addr) (((addr)>>PAGE_SHIFT)&(CONT_PTES-1))
 
 /*
@@ -178,10 +178,12 @@
 #define PTE_S2_RDONLY		(_AT(pteval_t, 1) << 6)   /* HAP[2:1] */
 #define PTE_S2_RDWR		(_AT(pteval_t, 3) << 6)   /* HAP[2:1] */
 #define PTE_S2_XN		(_AT(pteval_t, 2) << 53)  /* XN[1:0] */
+#define PTE_S2_SW_RESVD		(_AT(pteval_t, 15) << 55) /* Reserved for SW */
 
 #define PMD_S2_RDONLY		(_AT(pmdval_t, 1) << 6)   /* HAP[2:1] */
 #define PMD_S2_RDWR		(_AT(pmdval_t, 3) << 6)   /* HAP[2:1] */
 #define PMD_S2_XN		(_AT(pmdval_t, 2) << 53)  /* XN[1:0] */
+#define PMD_S2_SW_RESVD		(_AT(pmdval_t, 15) << 55) /* Reserved for SW */
 
 #define PUD_S2_RDONLY		(_AT(pudval_t, 1) << 6)   /* HAP[2:1] */
 #define PUD_S2_RDWR		(_AT(pudval_t, 3) << 6)   /* HAP[2:1] */
@@ -216,6 +218,7 @@
 #define TCR_TxSZ(x)		(TCR_T0SZ(x) | TCR_T1SZ(x))
 #define TCR_TxSZ_WIDTH		6
 #define TCR_T0SZ_MASK		(((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T0SZ_OFFSET)
+#define TCR_T1SZ_MASK		(((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T1SZ_OFFSET)
 
 #define TCR_EPD0_SHIFT		7
 #define TCR_EPD0_MASK		(UL(1) << TCR_EPD0_SHIFT)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 758e2d1577d0..d5d3fbe73953 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -40,6 +40,16 @@ extern void __pmd_error(const char *file, int line, unsigned long val);
 extern void __pud_error(const char *file, int line, unsigned long val);
 extern void __pgd_error(const char *file, int line, unsigned long val);
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
+
+/* Set stride and tlb_level in flush_*_tlb_range */
+#define flush_pmd_tlb_range(vma, addr, end)	\
+	__flush_tlb_range(vma, addr, end, PMD_SIZE, false, 2)
+#define flush_pud_tlb_range(vma, addr, end)	\
+	__flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1)
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 953b6a1ce549..966ed30ed5f7 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -27,7 +27,7 @@
  *
  * Some code sections either automatically switch back to PSR.I or explicitly
  * require to not use priority masking. If bit GIC_PRIO_PSR_I_SET is included
- * in the  the priority mask, it indicates that PSR.I should be set and
+ * in the priority mask, it indicates that PSR.I should be set and
  * interrupt disabling temporarily does not rely on IRQ priorities.
  */
 #define GIC_PRIO_IRQON			0xe0
diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h
index b767904f28b1..996bf98f0cab 100644
--- a/arch/arm64/include/asm/stage2_pgtable.h
+++ b/arch/arm64/include/asm/stage2_pgtable.h
@@ -256,4 +256,13 @@ stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
 	return (boundary - 1 < end - 1) ? boundary : end;
 }
 
+/*
+ * Level values for the ARMv8.4-TTL extension, mapping PUD/PMD/PTE and
+ * the architectural page-table level.
+ */
+#define S2_NO_LEVEL_HINT	0
+#define S2_PUD_LEVEL		1
+#define S2_PMD_LEVEL		2
+#define S2_PTE_LEVEL		3
+
 #endif	/* __ARM64_S2_PGTABLE_H_ */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 463175f80341..554a7e8ecb07 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -421,9 +421,9 @@
  */
 
 #define SYS_AMEVCNTR0_EL0(n)		SYS_AM_EL0(4 + ((n) >> 3), (n) & 7)
-#define SYS_AMEVTYPE0_EL0(n)		SYS_AM_EL0(6 + ((n) >> 3), (n) & 7)
+#define SYS_AMEVTYPER0_EL0(n)		SYS_AM_EL0(6 + ((n) >> 3), (n) & 7)
 #define SYS_AMEVCNTR1_EL0(n)		SYS_AM_EL0(12 + ((n) >> 3), (n) & 7)
-#define SYS_AMEVTYPE1_EL0(n)		SYS_AM_EL0(14 + ((n) >> 3), (n) & 7)
+#define SYS_AMEVTYPER1_EL0(n)		SYS_AM_EL0(14 + ((n) >> 3), (n) & 7)
 
 /* AMU v1: Fixed (architecturally defined) activity monitors */
 #define SYS_AMEVCNTR0_CORE_EL0		SYS_AMEVCNTR0_EL0(0)
@@ -617,6 +617,9 @@
 #define ID_AA64ISAR0_SHA1_SHIFT		8
 #define ID_AA64ISAR0_AES_SHIFT		4
 
+#define ID_AA64ISAR0_TLB_RANGE_NI	0x0
+#define ID_AA64ISAR0_TLB_RANGE		0x2
+
 /* id_aa64isar1 */
 #define ID_AA64ISAR1_I8MM_SHIFT		52
 #define ID_AA64ISAR1_DGH_SHIFT		48
@@ -706,6 +709,9 @@
 #define ID_AA64ZFR0_SVEVER_SVE2		0x1
 
 /* id_aa64mmfr0 */
+#define ID_AA64MMFR0_ECV_SHIFT		60
+#define ID_AA64MMFR0_FGT_SHIFT		56
+#define ID_AA64MMFR0_EXS_SHIFT		44
 #define ID_AA64MMFR0_TGRAN4_2_SHIFT	40
 #define ID_AA64MMFR0_TGRAN64_2_SHIFT	36
 #define ID_AA64MMFR0_TGRAN16_2_SHIFT	32
@@ -734,6 +740,10 @@
 #endif
 
 /* id_aa64mmfr1 */
+#define ID_AA64MMFR1_ETS_SHIFT		36
+#define ID_AA64MMFR1_TWED_SHIFT		32
+#define ID_AA64MMFR1_XNX_SHIFT		28
+#define ID_AA64MMFR1_SPECSEI_SHIFT	24
 #define ID_AA64MMFR1_PAN_SHIFT		20
 #define ID_AA64MMFR1_LOR_SHIFT		16
 #define ID_AA64MMFR1_HPD_SHIFT		12
@@ -746,8 +756,15 @@
 
 /* id_aa64mmfr2 */
 #define ID_AA64MMFR2_E0PD_SHIFT		60
+#define ID_AA64MMFR2_EVT_SHIFT		56
+#define ID_AA64MMFR2_BBM_SHIFT		52
+#define ID_AA64MMFR2_TTL_SHIFT		48
 #define ID_AA64MMFR2_FWB_SHIFT		40
+#define ID_AA64MMFR2_IDS_SHIFT		36
 #define ID_AA64MMFR2_AT_SHIFT		32
+#define ID_AA64MMFR2_ST_SHIFT		28
+#define ID_AA64MMFR2_NV_SHIFT		24
+#define ID_AA64MMFR2_CCIDX_SHIFT	20
 #define ID_AA64MMFR2_LVA_SHIFT		16
 #define ID_AA64MMFR2_IESB_SHIFT		12
 #define ID_AA64MMFR2_LSM_SHIFT		8
@@ -755,6 +772,7 @@
 #define ID_AA64MMFR2_CNP_SHIFT		0
 
 /* id_aa64dfr0 */
+#define ID_AA64DFR0_DOUBLELOCK_SHIFT	36
 #define ID_AA64DFR0_PMSVER_SHIFT	32
 #define ID_AA64DFR0_CTX_CMPS_SHIFT	28
 #define ID_AA64DFR0_WRPS_SHIFT		20
@@ -807,18 +825,40 @@
 #define ID_ISAR6_DP_SHIFT		4
 #define ID_ISAR6_JSCVT_SHIFT		0
 
+#define ID_MMFR0_INNERSHR_SHIFT		28
+#define ID_MMFR0_FCSE_SHIFT		24
+#define ID_MMFR0_AUXREG_SHIFT		20
+#define ID_MMFR0_TCM_SHIFT		16
+#define ID_MMFR0_SHARELVL_SHIFT		12
+#define ID_MMFR0_OUTERSHR_SHIFT		8
+#define ID_MMFR0_PMSA_SHIFT		4
+#define ID_MMFR0_VMSA_SHIFT		0
+
 #define ID_MMFR4_EVT_SHIFT		28
 #define ID_MMFR4_CCIDX_SHIFT		24
 #define ID_MMFR4_LSM_SHIFT		20
 #define ID_MMFR4_HPDS_SHIFT		16
 #define ID_MMFR4_CNP_SHIFT		12
 #define ID_MMFR4_XNX_SHIFT		8
+#define ID_MMFR4_AC2_SHIFT		4
 #define ID_MMFR4_SPECSEI_SHIFT		0
 
 #define ID_MMFR5_ETS_SHIFT		0
 
 #define ID_PFR0_DIT_SHIFT		24
 #define ID_PFR0_CSV2_SHIFT		16
+#define ID_PFR0_STATE3_SHIFT		12
+#define ID_PFR0_STATE2_SHIFT		8
+#define ID_PFR0_STATE1_SHIFT		4
+#define ID_PFR0_STATE0_SHIFT		0
+
+#define ID_DFR0_PERFMON_SHIFT		24
+#define ID_DFR0_MPROFDBG_SHIFT		20
+#define ID_DFR0_MMAPTRC_SHIFT		16
+#define ID_DFR0_COPTRC_SHIFT		12
+#define ID_DFR0_MMAPDBG_SHIFT		8
+#define ID_DFR0_COPSDBG_SHIFT		4
+#define ID_DFR0_COPDBG_SHIFT		0
 
 #define ID_PFR2_SSBS_SHIFT		4
 #define ID_PFR2_CSV3_SHIFT		0
@@ -861,6 +901,11 @@
 #define ID_AA64MMFR0_TGRAN_SUPPORTED	ID_AA64MMFR0_TGRAN64_SUPPORTED
 #endif
 
+#define MVFR2_FPMISC_SHIFT		4
+#define MVFR2_SIMDMISC_SHIFT		0
+
+#define DCZID_DZP_SHIFT			4
+#define DCZID_BS_SHIFT			0
 
 /*
  * The ZCR_ELx_LEN_* definitions intentionally include bits [8:4] which
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index b76df828e6b7..61c97d3b58c7 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -21,11 +21,37 @@ static void tlb_flush(struct mmu_gather *tlb);
 
 #include <asm-generic/tlb.h>
 
+/*
+ * get the tlbi levels in arm64.  Default value is 0 if more than one
+ * of cleared_* is set or neither is set.
+ * Arm64 doesn't support p4ds now.
+ */
+static inline int tlb_get_level(struct mmu_gather *tlb)
+{
+	if (tlb->cleared_ptes && !(tlb->cleared_pmds ||
+				   tlb->cleared_puds ||
+				   tlb->cleared_p4ds))
+		return 3;
+
+	if (tlb->cleared_pmds && !(tlb->cleared_ptes ||
+				   tlb->cleared_puds ||
+				   tlb->cleared_p4ds))
+		return 2;
+
+	if (tlb->cleared_puds && !(tlb->cleared_ptes ||
+				   tlb->cleared_pmds ||
+				   tlb->cleared_p4ds))
+		return 1;
+
+	return 0;
+}
+
 static inline void tlb_flush(struct mmu_gather *tlb)
 {</