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

Pull arm64 updates from Catalin Marinas:
 "Nothing major this time around.

  Apart from the usual perf/PMU updates, some page table cleanups, the
  notable features are average CPU frequency based on the AMUv1
  counters, CONFIG_HOTPLUG_SMT and MOPS instructions (memcpy/memset) in
  the uaccess routines.

  Perf and PMUs:

   - Support for the 'Rainier' CPU PMU from Arm

   - Preparatory driver changes and cleanups that pave the way for BRBE
     support

   - Support for partial virtualisation of the Apple-M1 PMU

   - Support for the second event filter in Arm CSPMU designs

   - Minor fixes and cleanups (CMN and DWC PMUs)

   - Enable EL2 requirements for FEAT_PMUv3p9

  Power, CPU topology:

   - Support for AMUv1-based average CPU frequency

   - Run-time SMT control wired up for arm64 (CONFIG_HOTPLUG_SMT). It
     adds a generic topology_is_primary_thread() function overridden by
     x86 and powerpc

  New(ish) features:

   - MOPS (memcpy/memset) support for the uaccess routines

  Security/confidential compute:

   - Fix the DMA address for devices used in Realms with Arm CCA. The
     CCA architecture uses the address bit to differentiate between
     shared and private addresses

   - Spectre-BHB: assume CPUs Linux doesn't know about vulnerable by
     default

  Memory management clean-ups:

   - Drop the P*D_TABLE_BIT definition in preparation for 128-bit PTEs

   - Some minor page table accessor clean-ups

   - PIE/POE (permission indirection/overlay) helpers clean-up

  Kselftests:

   - MTE: skip hugetlb tests if MTE is not supported on such mappings
     and user correct naming for sync/async tag checking modes

  Miscellaneous:

   - Add a PKEY_UNRESTRICTED definition as 0 to uapi (toolchain people
     request)

   - Sysreg updates for new register fields

   - CPU type info for some Qualcomm Kryo cores"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (72 commits)
  arm64: mm: Don't use %pK through printk
  perf/arm_cspmu: Fix missing io.h include
  arm64: errata: Add newer ARM cores to the spectre_bhb_loop_affected() lists
  arm64: cputype: Add MIDR_CORTEX_A76AE
  arm64: errata: Add KRYO 2XX/3XX/4XX silver cores to Spectre BHB safe list
  arm64: errata: Assume that unknown CPUs _are_ vulnerable to Spectre BHB
  arm64: errata: Add QCOM_KRYO_4XX_GOLD to the spectre_bhb_k24_list
  arm64/sysreg: Enforce whole word match for open/close tokens
  arm64/sysreg: Fix unbalanced closing block
  arm64: Kconfig: Enable HOTPLUG_SMT
  arm64: topology: Support SMT control on ACPI based system
  arch_topology: Support SMT control for OF based system
  cpu/SMT: Provide a default topology_is_primary_thread()
  arm64/mm: Define PTDESC_ORDER
  perf/arm_cspmu: Add PMEVFILT2R support
  perf/arm_cspmu: Generalise event filtering
  perf/arm_cspmu: Move register definitons to header
  arm64/kernel: Always use level 2 or higher for early mappings
  arm64/mm: Drop PXD_TABLE_BIT
  arm64/mm: Check pmd_table() in pmd_trans_huge()
  ...

39 files changed, 721 insertions, 247 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index c9fe3e7566a6..f2d724c1dfd2 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -251,6 +251,7 @@ config ARM64
 	select HAVE_KRETPROBES
 	select HAVE_GENERIC_VDSO
 	select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU
+	select HOTPLUG_SMT if HOTPLUG_CPU
 	select IRQ_DOMAIN
 	select IRQ_FORCED_THREADING
 	select KASAN_VMALLOC if KASAN
@@ -324,7 +325,7 @@ config ARCH_MMAP_RND_BITS_MIN
 	default 18
 
 # max bits determined by the following formula:
-#  VA_BITS - PAGE_SHIFT - 3
+#  VA_BITS - PTDESC_TABLE_SHIFT
 config ARCH_MMAP_RND_BITS_MAX
 	default 19 if ARM64_VA_BITS=36
 	default 24 if ARM64_VA_BITS=39
diff --git a/arch/arm64/include/asm/apple_m1_pmu.h b/arch/arm64/include/asm/apple_m1_pmu.h
index 99483b19b99f..02e05d05851f 100644
--- a/arch/arm64/include/asm/apple_m1_pmu.h
+++ b/arch/arm64/include/asm/apple_m1_pmu.h
@@ -37,6 +37,7 @@
 #define PMCR0_PMI_ENABLE_8_9	GENMASK(45, 44)
 
 #define SYS_IMP_APL_PMCR1_EL1	sys_reg(3, 1, 15, 1, 0)
+#define SYS_IMP_APL_PMCR1_EL12	sys_reg(3, 1, 15, 7, 2)
 #define PMCR1_COUNT_A64_EL0_0_7	GENMASK(15, 8)
 #define PMCR1_COUNT_A64_EL1_0_7	GENMASK(23, 16)
 #define PMCR1_COUNT_A64_EL0_8_9	GENMASK(41, 40)
diff --git a/arch/arm64/include/asm/asm-extable.h b/arch/arm64/include/asm/asm-extable.h
index b8a5861dc7b7..292f2687a12e 100644
--- a/arch/arm64/include/asm/asm-extable.h
+++ b/arch/arm64/include/asm/asm-extable.h
@@ -9,7 +9,8 @@
 #define EX_TYPE_BPF			1
 #define EX_TYPE_UACCESS_ERR_ZERO	2
 #define EX_TYPE_KACCESS_ERR_ZERO	3
-#define EX_TYPE_LOAD_UNALIGNED_ZEROPAD	4
+#define EX_TYPE_UACCESS_CPY		4
+#define EX_TYPE_LOAD_UNALIGNED_ZEROPAD	5
 
 /* Data fields for EX_TYPE_UACCESS_ERR_ZERO */
 #define EX_DATA_REG_ERR_SHIFT	0
@@ -23,6 +24,9 @@
 #define EX_DATA_REG_ADDR_SHIFT	5
 #define EX_DATA_REG_ADDR	GENMASK(9, 5)
 
+/* Data fields for EX_TYPE_UACCESS_CPY */
+#define EX_DATA_UACCESS_WRITE	BIT(0)
+
 #ifdef __ASSEMBLY__
 
 #define __ASM_EXTABLE_RAW(insn, fixup, type, data)	\
@@ -69,6 +73,10 @@
 	.endif
 	.endm
 
+	.macro		_asm_extable_uaccess_cpy, insn, fixup, uaccess_is_write
+	__ASM_EXTABLE_RAW(\insn, \fixup, EX_TYPE_UACCESS_CPY, \uaccess_is_write)
+	.endm
+
 #else /* __ASSEMBLY__ */
 
 #include <linux/stringify.h>
diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h
index 5b6efe8abeeb..9148f5a31968 100644
--- a/arch/arm64/include/asm/asm-uaccess.h
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -61,6 +61,10 @@ alternative_else_nop_endif
 9999:	x;					\
 	_asm_extable_uaccess	9999b, l
 
+#define USER_CPY(l, uaccess_is_write, x...)	\
+9999:	x;					\
+	_asm_extable_uaccess_cpy 9999b, l, uaccess_is_write
+
 /*
  * Generate the assembly for LDTR/STTR with exception table entries.
  * This is complicated as there is no post-increment or pair versions of the
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 6f3f4142e214..20284bf34722 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -75,6 +75,7 @@
 #define ARM_CPU_PART_CORTEX_A76		0xD0B
 #define ARM_CPU_PART_NEOVERSE_N1	0xD0C
 #define ARM_CPU_PART_CORTEX_A77		0xD0D
+#define ARM_CPU_PART_CORTEX_A76AE	0xD0E
 #define ARM_CPU_PART_NEOVERSE_V1	0xD40
 #define ARM_CPU_PART_CORTEX_A78		0xD41
 #define ARM_CPU_PART_CORTEX_A78AE	0xD42
@@ -119,6 +120,7 @@
 #define QCOM_CPU_PART_KRYO		0x200
 #define QCOM_CPU_PART_KRYO_2XX_GOLD	0x800
 #define QCOM_CPU_PART_KRYO_2XX_SILVER	0x801
+#define QCOM_CPU_PART_KRYO_3XX_GOLD	0x802
 #define QCOM_CPU_PART_KRYO_3XX_SILVER	0x803
 #define QCOM_CPU_PART_KRYO_4XX_GOLD	0x804
 #define QCOM_CPU_PART_KRYO_4XX_SILVER	0x805
@@ -159,6 +161,7 @@
 #define MIDR_CORTEX_A76	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76)
 #define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1)
 #define MIDR_CORTEX_A77	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77)
+#define MIDR_CORTEX_A76AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76AE)
 #define MIDR_NEOVERSE_V1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1)
 #define MIDR_CORTEX_A78	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78)
 #define MIDR_CORTEX_A78AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
@@ -196,10 +199,21 @@
 #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
 #define MIDR_QCOM_KRYO_2XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_GOLD)
 #define MIDR_QCOM_KRYO_2XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_SILVER)
+#define MIDR_QCOM_KRYO_3XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_GOLD)
 #define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER)
 #define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD)
 #define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER)
 #define MIDR_QCOM_ORYON_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_ORYON_X1)
+
+/*
+ * NOTES:
+ * - Qualcomm Kryo 5XX Prime / Gold ID themselves as MIDR_CORTEX_A77
+ * - Qualcomm Kryo 5XX Silver IDs itself as MIDR_QCOM_KRYO_4XX_SILVER
+ * - Qualcomm Kryo 6XX Prime IDs itself as MIDR_CORTEX_X1
+ * - Qualcomm Kryo 6XX Gold IDs itself as ARM_CPU_PART_CORTEX_A78
+ * - Qualcomm Kryo 6XX Silver IDs itself as MIDR_CORTEX_A55
+ */
+
 #define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER)
 #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
 #define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX)
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index 555c613fd232..ebceaae3c749 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -259,6 +259,30 @@
 .Lskip_fgt_\@:
 .endm
 
+.macro __init_el2_fgt2
+	mrs	x1, id_aa64mmfr0_el1
+	ubfx	x1, x1, #ID_AA64MMFR0_EL1_FGT_SHIFT, #4
+	cmp	x1, #ID_AA64MMFR0_EL1_FGT_FGT2
+	b.lt	.Lskip_fgt2_\@
+
+	mov	x0, xzr
+	mrs	x1, id_aa64dfr0_el1
+	ubfx	x1, x1, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4
+	cmp	x1, #ID_AA64DFR0_EL1_PMUVer_V3P9
+	b.lt	.Lskip_pmuv3p9_\@
+
+	orr	x0, x0, #HDFGRTR2_EL2_nPMICNTR_EL0
+	orr	x0, x0, #HDFGRTR2_EL2_nPMICFILTR_EL0
+	orr	x0, x0, #HDFGRTR2_EL2_nPMUACR_EL1
+.Lskip_pmuv3p9_\@:
+	msr_s   SYS_HDFGRTR2_EL2, x0
+	msr_s   SYS_HDFGWTR2_EL2, x0
+	msr_s   SYS_HFGRTR2_EL2, xzr
+	msr_s   SYS_HFGWTR2_EL2, xzr
+	msr_s   SYS_HFGITR2_EL2, xzr
+.Lskip_fgt2_\@:
+.endm
+
 .macro __init_el2_gcs
 	mrs_s	x1, SYS_ID_AA64PFR1_EL1
 	ubfx	x1, x1, #ID_AA64PFR1_EL1_GCS_SHIFT, #4
@@ -304,6 +328,7 @@
 	__init_el2_nvhe_idregs
 	__init_el2_cptr
 	__init_el2_fgt
+	__init_el2_fgt2
         __init_el2_gcs
 .endm
 
diff --git a/arch/arm64/include/asm/extable.h b/arch/arm64/include/asm/extable.h
index 72b0e71cc3de..9dc39612bdf5 100644
--- a/arch/arm64/include/asm/extable.h
+++ b/arch/arm64/include/asm/extable.h
@@ -33,6 +33,8 @@ do {							\
 	(b)->data = (tmp).data;				\
 } while (0)
 
+bool insn_may_access_user(unsigned long addr, unsigned long esr);
+
 #ifdef CONFIG_BPF_JIT
 bool ex_handler_bpf(const struct exception_table_entry *ex,
 		    struct pt_regs *regs);
@@ -45,5 +47,5 @@ bool ex_handler_bpf(const struct exception_table_entry *ex,
 }
 #endif /* !CONFIG_BPF_JIT */
 
-bool fixup_exception(struct pt_regs *regs);
+bool fixup_exception(struct pt_regs *regs, unsigned long esr);
 #endif
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index f2a84efc3618..564bc09b3e06 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -80,7 +80,6 @@ extern void fpsimd_signal_preserve_current_state(void);
 extern void fpsimd_preserve_current_state(void);
 extern void fpsimd_restore_current_state(void);
 extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
-extern void fpsimd_kvm_prepare(void);
 
 struct cpu_fp_state {
 	struct user_fpsimd_state *st;
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index fd5a08450b12..9e93733523f6 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -45,11 +45,11 @@
 #define SPAN_NR_ENTRIES(vstart, vend, shift) \
 	((((vend) - 1) >> (shift)) - ((vstart) >> (shift)) + 1)
 
-#define EARLY_ENTRIES(vstart, vend, shift, add) \
-	(SPAN_NR_ENTRIES(vstart, vend, shift) + (add))
+#define EARLY_ENTRIES(lvl, vstart, vend) \
+	SPAN_NR_ENTRIES(vstart, vend, SWAPPER_BLOCK_SHIFT + lvl * PTDESC_TABLE_SHIFT)
 
-#define EARLY_LEVEL(lvl, lvls, vstart, vend, add)	\
-	(lvls > lvl ? EARLY_ENTRIES(vstart, vend, SWAPPER_BLOCK_SHIFT + lvl * (PAGE_SHIFT - 3), add) : 0)
+#define EARLY_LEVEL(lvl, lvls, vstart, vend, add) \
+	((lvls) > (lvl) ? EARLY_ENTRIES(lvl, vstart, vend) + (add) : 0)
 
 #define EARLY_PAGES(lvls, vstart, vend, add) (1 	/* PGDIR page */				\
 	+ EARLY_LEVEL(3, (lvls), (vstart), (vend), add) /* each entry needs a next level page table */	\
diff --git a/arch/arm64/include/asm/mem_encrypt.h b/arch/arm64/include/asm/mem_encrypt.h
index f8f78f622dd2..a2a1eeb36d4b 100644
--- a/arch/arm64/include/asm/mem_encrypt.h
+++ b/arch/arm64/include/asm/mem_encrypt.h
@@ -21,4 +21,15 @@ static inline bool force_dma_unencrypted(struct device *dev)
 	return is_realm_world();
 }
 
+/*
+ * For Arm CCA guests, canonical addresses are "encrypted", so no changes
+ * required for dma_addr_encrypted().
+ * The unencrypted DMA buffers must be accessed via the unprotected IPA,
+ * "top IPA bit" set.
+ */
+#define dma_addr_unencrypted(x)		((x) | PROT_NS_SHARED)
+
+/* Clear the "top" IPA bit while converting back */
+#define dma_addr_canonical(x)		((x) & ~PROT_NS_SHARED)
+
 #endif	/* __ASM_MEM_ENCRYPT_H */
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index a9136cc551cc..f3b77deedfa2 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -7,40 +7,46 @@
 
 #include <asm/memory.h>
 
+#define PTDESC_ORDER 3
+
+/* Number of VA bits resolved by a single translation table level */
+#define PTDESC_TABLE_SHIFT	(PAGE_SHIFT - PTDESC_ORDER)
+
 /*
  * Number of page-table levels required to address 'va_bits' wide
  * address, without section mapping. We resolve the top (va_bits - PAGE_SHIFT)
- * bits with (PAGE_SHIFT - 3) bits at each page table level. Hence:
+ * bits with PTDESC_TABLE_SHIFT bits at each page table level. Hence:
  *
- *  levels = DIV_ROUND_UP((va_bits - PAGE_SHIFT), (PAGE_SHIFT - 3))
+ *  levels = DIV_ROUND_UP((va_bits - PAGE_SHIFT), PTDESC_TABLE_SHIFT)
  *
  * where DIV_ROUND_UP(n, d) => (((n) + (d) - 1) / (d))
  *
  * We cannot include linux/kernel.h which defines DIV_ROUND_UP here
  * due to build issues. So we open code DIV_ROUND_UP here:
  *
- *	((((va_bits) - PAGE_SHIFT) + (PAGE_SHIFT - 3) - 1) / (PAGE_SHIFT - 3))
+ *	((((va_bits) - PAGE_SHIFT) + PTDESC_TABLE_SHIFT - 1) / PTDESC_TABLE_SHIFT)
  *
  * which gets simplified as :
  */
-#define ARM64_HW_PGTABLE_LEVELS(va_bits) (((va_bits) - 4) / (PAGE_SHIFT - 3))
+#define ARM64_HW_PGTABLE_LEVELS(va_bits) \
+	(((va_bits) - PTDESC_ORDER - 1) / PTDESC_TABLE_SHIFT)
 
 /*
  * Size mapped by an entry at level n ( -1 <= n <= 3)
- * We map (PAGE_SHIFT - 3) at all translation levels and PAGE_SHIFT bits
+ * We map PTDESC_TABLE_SHIFT at all translation levels and PAGE_SHIFT bits
  * in the final page. The maximum number of translation levels supported by
  * the architecture is 5. 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 :
  *
- *  ((4 - n) - 1) * (PAGE_SHIFT - 3) + PAGE_SHIFT
+ *  ((4 - n) - 1) * PTDESC_TABLE_SHIFT + PAGE_SHIFT
  *
  * Rearranging it a bit we get :
- *   (4 - n) * (PAGE_SHIFT - 3) + 3
+ *   (4 - n) * PTDESC_TABLE_SHIFT + PTDESC_ORDER
  */
-#define ARM64_HW_PGTABLE_LEVEL_SHIFT(n)	((PAGE_SHIFT - 3) * (4 - (n)) + 3)
+#define ARM64_HW_PGTABLE_LEVEL_SHIFT(n)	(PTDESC_TABLE_SHIFT * (4 - (n)) + PTDESC_ORDER)
 
-#define PTRS_PER_PTE		(1 << (PAGE_SHIFT - 3))
+#define PTRS_PER_PTE		(1 << PTDESC_TABLE_SHIFT)
 
 /*
  * PMD_SHIFT determines the size a level 2 page table entry can map.
@@ -49,7 +55,7 @@
 #define PMD_SHIFT		ARM64_HW_PGTABLE_LEVEL_SHIFT(2)
 #define PMD_SIZE		(_AC(1, UL) << PMD_SHIFT)
 #define PMD_MASK		(~(PMD_SIZE-1))
-#define PTRS_PER_PMD		(1 << (PAGE_SHIFT - 3))
+#define PTRS_PER_PMD		(1 << PTDESC_TABLE_SHIFT)
 #endif
 
 /*
@@ -59,14 +65,14 @@
 #define PUD_SHIFT		ARM64_HW_PGTABLE_LEVEL_SHIFT(1)
 #define PUD_SIZE		(_AC(1, UL) << PUD_SHIFT)
 #define PUD_MASK		(~(PUD_SIZE-1))
-#define PTRS_PER_PUD		(1 << (PAGE_SHIFT - 3))
+#define PTRS_PER_PUD		(1 << PTDESC_TABLE_SHIFT)
 #endif
 
 #if CONFIG_PGTABLE_LEVELS > 4
 #define P4D_SHIFT		ARM64_HW_PGTABLE_LEVEL_SHIFT(0)
 #define P4D_SIZE		(_AC(1, UL) << P4D_SHIFT)
 #define P4D_MASK		(~(P4D_SIZE-1))
-#define PTRS_PER_P4D		(1 << (PAGE_SHIFT - 3))
+#define PTRS_PER_P4D		(1 << PTDESC_TABLE_SHIFT)
 #endif
 
 /*
@@ -97,7 +103,6 @@
  * Level -1 descriptor (PGD).
  */
 #define PGD_TYPE_TABLE		(_AT(pgdval_t, 3) << 0)
-#define PGD_TABLE_BIT		(_AT(pgdval_t, 1) << 1)
 #define PGD_TYPE_MASK		(_AT(pgdval_t, 3) << 0)
 #define PGD_TABLE_AF		(_AT(pgdval_t, 1) << 10)	/* Ignored if no FEAT_HAFT */
 #define PGD_TABLE_PXN		(_AT(pgdval_t, 1) << 59)
@@ -107,7 +112,6 @@
  * Level 0 descriptor (P4D).
  */
 #define P4D_TYPE_TABLE		(_AT(p4dval_t, 3) << 0)
-#define P4D_TABLE_BIT		(_AT(p4dval_t, 1) << 1)
 #define P4D_TYPE_MASK		(_AT(p4dval_t, 3) << 0)
 #define P4D_TYPE_SECT		(_AT(p4dval_t, 1) << 0)
 #define P4D_SECT_RDONLY		(_AT(p4dval_t, 1) << 7)		/* AP[2] */
@@ -119,7 +123,6 @@
  * Level 1 descriptor (PUD).
  */
 #define PUD_TYPE_TABLE		(_AT(pudval_t, 3) << 0)
-#define PUD_TABLE_BIT		(_AT(pudval_t, 1) << 1)
 #define PUD_TYPE_MASK		(_AT(pudval_t, 3) << 0)
 #define PUD_TYPE_SECT		(_AT(pudval_t, 1) << 0)
 #define PUD_SECT_RDONLY		(_AT(pudval_t, 1) << 7)		/* AP[2] */
@@ -133,7 +136,6 @@
 #define PMD_TYPE_MASK		(_AT(pmdval_t, 3) << 0)
 #define PMD_TYPE_TABLE		(_AT(pmdval_t, 3) << 0)
 #define PMD_TYPE_SECT		(_AT(pmdval_t, 1) << 0)
-#define PMD_TABLE_BIT		(_AT(pmdval_t, 1) << 1)
 #define PMD_TABLE_AF		(_AT(pmdval_t, 1) << 10)	/* Ignored if no FEAT_HAFT */
 
 /*
@@ -162,7 +164,6 @@
 #define PTE_VALID		(_AT(pteval_t, 1) << 0)
 #define PTE_TYPE_MASK		(_AT(pteval_t, 3) << 0)
 #define PTE_TYPE_PAGE		(_AT(pteval_t, 3) << 0)
-#define PTE_TABLE_BIT		(_AT(pteval_t, 1) << 1)
 #define PTE_USER		(_AT(pteval_t, 1) << 6)		/* AP[1] */
 #define PTE_RDONLY		(_AT(pteval_t, 1) << 7)		/* AP[2] */
 #define PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index a95f1f77bb39..7830d031742e 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -169,25 +169,25 @@ static inline bool __pure lpa2_is_enabled(void)
 #define PAGE_GCS_RO	__pgprot(_PAGE_GCS_RO)
 
 #define PIE_E0	( \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS),           PIE_GCS)  | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS_RO),        PIE_R)   | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_EXECONLY),      PIE_X_O) | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY_EXEC), PIE_RX_O)  | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED_EXEC),   PIE_RWX_O) | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY),      PIE_R_O)   | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED),        PIE_RW_O))
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_GCS),           PIE_GCS)  | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_GCS_RO),        PIE_R)   | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_EXECONLY),      PIE_X_O) | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_READONLY_EXEC), PIE_RX_O)  | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_SHARED_EXEC),   PIE_RWX_O) | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_READONLY),      PIE_R_O)   | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_SHARED),        PIE_RW_O))
 
 #define PIE_E1	( \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS),           PIE_NONE_O) | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS_RO),        PIE_NONE_O) | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_EXECONLY),      PIE_NONE_O) | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY_EXEC), PIE_R)      | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED_EXEC),   PIE_RW)     | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY),      PIE_R)      | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED),        PIE_RW)     | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL_ROX),    PIE_RX)     | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL_EXEC),   PIE_RWX)    | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL_RO),     PIE_R)      | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL),        PIE_RW))
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_GCS),           PIE_NONE_O) | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_GCS_RO),        PIE_NONE_O) | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_EXECONLY),      PIE_NONE_O) | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_READONLY_EXEC), PIE_R)      | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_SHARED_EXEC),   PIE_RW)     | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_READONLY),      PIE_R)      | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_SHARED),        PIE_RW)     | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_KERNEL_ROX),    PIE_RX)     | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_KERNEL_EXEC),   PIE_RWX)    | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_KERNEL_RO),     PIE_R)      | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_KERNEL),        PIE_RW))
 
 #endif /* __ASM_PGTABLE_PROT_H */
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 0b2a2ad1b9e8..84f05f781a70 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -68,10 +68,6 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #define pte_ERROR(e)	\
 	pr_err("%s:%d: bad pte %016llx.\n", __FILE__, __LINE__, pte_val(e))
 
-/*
- * Macros to convert between a physical address and its placement in a
- * page table entry, taking care of 52-bit addresses.
- */
 #ifdef CONFIG_ARM64_PA_BITS_52
 static inline phys_addr_t __pte_to_phys(pte_t pte)
 {
@@ -84,8 +80,15 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
 	return (phys | (phys >> PTE_ADDR_HIGH_SHIFT)) & PHYS_TO_PTE_ADDR_MASK;
 }
 #else
-#define __pte_to_phys(pte)	(pte_val(pte) & PTE_ADDR_LOW)
-#define __phys_to_pte_val(phys)	(phys)
+static inline phys_addr_t __pte_to_phys(pte_t pte)
+{
+	return pte_val(pte) & PTE_ADDR_LOW;
+}
+
+static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
+{
+	return phys;
+}
 #endif
 
 #define pte_pfn(pte)		(__pte_to_phys(pte) >> PAGE_SHIFT)
@@ -483,12 +486,12 @@ static inline pmd_t pte_pmd(pte_t pte)
 
 static inline pgprot_t mk_pud_sect_prot(pgprot_t prot)
 {
-	return __pgprot((pgprot_val(prot) & ~PUD_TABLE_BIT) | PUD_TYPE_SECT);
+	return __pgprot((pgprot_val(prot) & ~PUD_TYPE_MASK) | PUD_TYPE_SECT);
 }
 
 static inline pgprot_t mk_pmd_sect_prot(pgprot_t prot)
 {
-	return __pgprot((pgprot_val(prot) & ~PMD_TABLE_BIT) | PMD_TYPE_SECT);
+	return __pgprot((pgprot_val(prot) & ~PMD_TYPE_MASK) | PMD_TYPE_SECT);
 }
 
 static inline pte_t pte_swp_mkexclusive(pte_t pte)
@@ -548,18 +551,6 @@ static inline int pmd_protnone(pmd_t pmd)
 #endif
 
 #define pmd_present(pmd)	pte_present(pmd_pte(pmd))
-
-/*
- * THP definitions.
- */
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline int pmd_trans_huge(pmd_t pmd)
-{
-	return pmd_val(pmd) && pmd_present(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
-}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
 #define pmd_valid(pmd)		pte_valid(pmd_pte(pmd))
@@ -585,7 +576,18 @@ static inline int pmd_trans_huge(pmd_t pmd)
 
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
 
-#define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
+static inline pmd_t pmd_mkhuge(pmd_t pmd)
+{
+	/*
+	 * It's possible that the pmd is present-invalid on entry
+	 * and in that case it needs to remain present-invalid on
+	 * exit. So ensure the VALID bit does not get modified.
+	 */
+	pmdval_t mask = PMD_TYPE_MASK & ~PTE_VALID;
+	pmdval_t val = PMD_TYPE_SECT & ~PTE_VALID;
+
+	return __pmd((pmd_val(pmd) & ~mask) | val);
+}
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_devmap(pmd)		pte_devmap(pmd_pte(pmd))
@@ -613,7 +615,18 @@ static inline pmd_t pmd_mkspecial(pmd_t pmd)
 #define pud_mkyoung(pud)	pte_pud(pte_mkyoung(pud_pte(pud)))
 #define pud_write(pud)		pte_write(pud_pte(pud))
 
-#define pud_mkhuge(pud)		(__pud(pud_val(pud) & ~PUD_TABLE_BIT))
+static inline pud_t pud_mkhuge(pud_t pud)
+{
+	/*
+	 * It's possible that the pud is present-invalid on entry
+	 * and in that case it needs to remain present-invalid on
+	 * exit. So ensure the VALID bit does not get modified.
+	 */
+	pudval_t mask = PUD_TYPE_MASK & ~PTE_VALID;
+	pudval_t val = PUD_TYPE_SECT & ~PTE_VALID;
+
+	return __pud((pud_val(pud) & ~mask) | val);
+}
 
 #define __pud_to_phys(pud)	__pte_to_phys(pud_pte(pud))
 #define __phys_to_pud_val(phys)	__phys_to_pte_val(phys)
@@ -724,6 +737,18 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 #define pmd_leaf_size(pmd)	(pmd_cont(pmd) ? CONT_PMD_SIZE : PMD_SIZE)
 #define pte_leaf_size(pte)	(pte_cont(pte) ? CONT_PTE_SIZE : PAGE_SIZE)
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline int pmd_trans_huge(pmd_t pmd)
+{
+	/*
+	 * If pmd is present-invalid, pmd_table() won't detect it
+	 * as a table, so force the valid bit for the comparison.
+	 */
+	return pmd_val(pmd) && pmd_present(pmd) &&
+	       !pmd_table(__pmd(pmd_val(pmd) | PTE_VALID));
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 #if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3
 static inline bool pud_sect(pud_t pud) { return false; }
 static inline bool pud_table(pud_t pud) { return true; }
@@ -805,7 +830,8 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 	pr_err("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e))
 
 #define pud_none(pud)		(!pud_val(pud))
-#define pud_bad(pud)		(!pud_table(pud))
+#define pud_bad(pud)		((pud_val(pud) & PUD_TYPE_MASK) != \
+				 PUD_TYPE_TABLE)
 #define pud_present(pud)	pte_present(pud_pte(pud))
 #ifndef __PAGETABLE_PMD_FOLDED
 #define pud_leaf(pud)		(pud_present(pud) && !pud_table(pud))
@@ -896,7 +922,9 @@ static inline bool mm_pud_folded(const struct mm_struct *mm)
 	pr_err("%s:%d: bad pud %016llx.\n", __FILE__, __LINE__, pud_val(e))
 
 #define p4d_none(p4d)		(pgtable_l4_enabled() && !p4d_val(p4d))
-#define p4d_bad(p4d)		(pgtable_l4_enabled() && !(p4d_val(p4d) & P4D_TABLE_BIT))
+#define p4d_bad(p4d)		(pgtable_l4_enabled() && \
+				((p4d_val(p4d) & P4D_TYPE_MASK) != \
+				 P4D_TYPE_TABLE))
 #define p4d_present(p4d)	(!p4d_none(p4d))
 
 static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
@@ -1023,7 +1051,9 @@ static inline bool mm_p4d_folded(const struct mm_struct *mm)
 	pr_err("%s:%d: bad p4d %016llx.\n", __FILE__, __LINE__, p4d_val(e))
 
 #define pgd_none(pgd)		(pgtable_l5_enabled() && !pgd_val(pgd))
-#define pgd_bad(pgd)		(pgtable_l5_enabled() && !(pgd_val(pgd) & PGD_TABLE_BIT))
+#define pgd_bad(pgd)		(pgtable_l5_enabled() && \
+				((pgd_val(pgd) & PGD_TYPE_MASK) != \
+				 PGD_TYPE_TABLE))
 #define pgd_present(pgd)	(!pgd_none(pgd))
 
 static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
diff --git a/arch/arm64/include/asm/por.h b/arch/arm64/include/asm/por.h
index e06e9f473675..d913d5b529e4 100644
--- a/arch/arm64/include/asm/por.h
+++ b/arch/arm64/include/asm/por.h
@@ -6,26 +6,27 @@
 #ifndef _ASM_ARM64_POR_H
 #define _ASM_ARM64_POR_H
 
-#define POR_BITS_PER_PKEY		4
-#define POR_ELx_IDX(por_elx, idx)	(((por_elx) >> ((idx) * POR_BITS_PER_PKEY)) & 0xf)
+#include <asm/sysreg.h>
+
+#define POR_EL0_INIT	POR_ELx_PERM_PREP(0, POE_RWX)
 
 static inline bool por_elx_allows_read(u64 por, u8 pkey)
 {
-	u8 perm = POR_ELx_IDX(por, pkey);
+	u8 perm = POR_ELx_PERM_GET(pkey, por);
 
 	return perm & POE_R;
 }
 
 static inline bool por_elx_allows_write(u64 por, u8 pkey)
 {
-	u8 perm = POR_ELx_IDX(por, pkey);
+	u8 perm = POR_ELx_PERM_GET(pkey, por);
 
 	return perm & POE_W;
 }
 
 static inline bool por_elx_allows_exec(u64 por, u8 pkey)
 {
-	u8 perm = POR_ELx_IDX(por, pkey);
+	u8 perm = POR_ELx_PERM_GET(pkey, por);
 
 	return perm & POE_X;
 }
diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h
index 0c4d9045c31f..f1524cdeacf1 100644
--- a/arch/arm64/include/asm/spectre.h
+++ b/arch/arm64/include/asm/spectre.h
@@ -97,7 +97,6 @@ enum mitigation_state arm64_get_meltdown_state(void);
 
 enum mitigation_state arm64_get_spectre_bhb_state(void);
 bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, int scope);
-u8 spectre_bhb_loop_affected(int scope);
 void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *__unused);
 bool try_emulate_el1_ssbs(struct pt_regs *regs, u32 instr);
 
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 05ea5223d2d5..e3252f8bb465 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -1062,8 +1062,11 @@
 #define PIE_RX		UL(0xa)
 #define PIE_RW		UL(0xc)
 #define PIE_RWX		UL(0xe)
+#define PIE_MASK	UL(0xf)
 
-#define PIRx_ELx_PERM(idx, perm)	((perm) << ((idx) * 4))
+#define PIRx_ELx_BITS_PER_IDX		4
+#define PIRx_ELx_PERM_SHIFT(idx)	((idx) * PIRx_ELx_BITS_PER_IDX)
+#define PIRx_ELx_PERM_PREP(idx, perm)	(((perm) & PIE_MASK) << PIRx_ELx_PERM_SHIFT(idx))
 
 /*
  * Permission Overlay Extension (POE) permission encodings.
@@ -1074,12 +1077,14 @@
 #define POE_RX		UL(0x3)
 #define POE_W		UL(0x4)
 #define POE_RW		UL(0x5)
-#define POE_XW		UL(0x6)
-#define POE_RXW		UL(0x7)
+#define POE_WX		UL(0x6)
+#define POE_RWX		UL(0x7)
 #define POE_MASK	UL(0xf)
 
-/* Initial value for Permission Overlay Extension for EL0 */
-#define POR_EL0_INIT	POE_RXW
+#define POR_ELx_BITS_PER_IDX		4
+#define POR_ELx_PERM_SHIFT(idx)		((idx) * POR_ELx_BITS_PER_IDX)
+#define POR_ELx_PERM_GET(idx, reg)	(((reg) >> POR_ELx_PERM_SHIFT(idx)) & POE_MASK)
+#define POR_ELx_PERM_PREP(idx, perm)	(((perm) & POE_MASK) << POR_ELx_PERM_SHIFT(idx))
 
 /*
  * Definitions for Guarded Control Stack
diff --git a/arch/arm64/kernel/pi/map_range.c b/arch/arm64/kernel/pi/map_range.c
index 2b69e3beeef8..81345f68f9fc 100644
--- a/arch/arm64/kernel/pi/map_range.c
+++ b/arch/arm64/kernel/pi/map_range.c
@@ -31,7 +31,7 @@ void __init map_range(u64 *pte, u64 start, u64 end, u64 pa, pgprot_t prot,
 {
 	u64 cmask = (level == 3) ? CONT_PTE_SIZE - 1 : U64_MAX;
 	pteval_t protval = pgprot_val(prot) & ~PTE_TYPE_MASK;
-	int lshift = (3 - level) * (PAGE_SHIFT - 3);
+	int lshift = (3 - level) * PTDESC_TABLE_SHIFT;
 	u64 lmask = (PAGE_SIZE << lshift) - 1;
 
 	start	&= PAGE_MASK;
@@ -45,12 +45,12 @@ void __init map_range(u64 *pte, u64 start, u64 end, u64 pa, pgprot_t prot,
 	 * clearing the mapping
 	 */
 	if (protval)
-		protval |= (level < 3) ? PMD_TYPE_SECT : PTE_TYPE_PAGE;
+		protval |= (level == 2) ? PMD_TYPE_SECT : PTE_TYPE_PAGE;
 
 	while (start < end) {
 		u64 next = min((start | lmask) + 1, PAGE_ALIGN(end));
 
-		if (level < 3 && (start | next | pa) & lmask) {
+		if (level < 2 || (level == 2 && (start | next | pa) & lmask)) {
 			/*
 			 * This chunk needs a finer grained mapping. Create a
 			 * table mapping if necessary and recurse.
diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c
index da53722f95d4..0f51fd10b4b0 100644
--- a/arch/arm64/kernel/proton-pack.c
+++ b/arch/arm64/kernel/proton-pack.c
@@ -845,52 +845,86 @@ static unsigned long system_bhb_mitigations;
  * This must be called with SCOPE_LOCAL_CPU for each type of CPU, before any
  * SCOPE_SYSTEM call will give the right answer.
  */
-u8 spectre_bhb_loop_affected(int scope)
+static bool is_spectre_bhb_safe(int scope)
+{
+	static const struct midr_range spectre_bhb_safe_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A510),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A520),
+		MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
+		{},
+	};
+	static bool all_safe = true;
+
+	if (scope != SCOPE_LOCAL_CPU)
+		return all_safe;
+
+	if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_safe_list))
+		return true;
+
+	all_safe = false;
+
+	return false;
+}
+
+static u8 spectre_bhb_loop_affected(void)
 {
 	u8 k = 0;
-	static u8 max_bhb_k;
-
-	if (scope == SCOPE_LOCAL_CPU) {
-		static const struct midr_range spectre_bhb_k32_list[] = {
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A78),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_X1),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_X2),
-			MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
-			MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1),
-			{},
-		};
-		static const struct midr_range spectre_bhb_k24_list[] = {
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A76),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A77),
-			MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1),
-			{},
-		};
-		static const struct midr_range spectre_bhb_k11_list[] = {
-			MIDR_ALL_VERSIONS(MIDR_AMPERE1),
-			{},
-		};
-		static const struct midr_range spectre_bhb_k8_list[] = {
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
-			{},
-		};
-
-		if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k32_list))
-			k = 32;
-		else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k24_list))
-			k = 24;
-		else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k11_list))
-			k = 11;
-		else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k8_list))
-			k =  8;
-
-		max_bhb_k = max(max_bhb_k, k);
-	} else {
-		k = max_bhb_k;
-	}
+
+	static const struct midr_range spectre_bhb_k132_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_X3),
+		MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2),
+	};
+	static const struct midr_range spectre_bhb_k38_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A715),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A720),
+	};
+	static const struct midr_range spectre_bhb_k32_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A78),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_X1),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_X2),
+		MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+		MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1),
+		{},
+	};
+	static const struct midr_range spectre_bhb_k24_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A76),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A76AE),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A77),
+		MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_GOLD),
+		{},
+	};
+	static const struct midr_range spectre_bhb_k11_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_AMPERE1),
+		{},
+	};
+	static const struct midr_range spectre_bhb_k8_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
+		{},
+	};
+
+	if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k132_list))
+		k = 132;
+	else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k38_list))
+		k = 38;
+	else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k32_list))
+		k = 32;
+	else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k24_list))
+		k = 24;
+	else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k11_list))
+		k = 11;
+	else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k8_list))
+		k =  8;
 
 	return k;
 }
@@ -916,29 +950,13 @@ static enum mitigation_state spectre_bhb_get_cpu_fw_mitigation_state(void)
 	}
 }
 
-static bool is_spectre_bhb_fw_affected(int scope)
+static bool has_spectre_bhb_fw_mitigation(void)
 {
-	static bool system_affected;
 	enum mitigation_state fw_state;
 	bool has_smccc = arm_smccc_1_1_get_conduit() != SMCCC_CONDUIT_NONE;
-	static const struct midr_range spectre_bhb_firmware_mitigated_list[] = {
-		MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
-		MIDR_ALL_VERSIONS(MIDR_CORTEX_A75),
-		{},
-	};
-	bool cpu_in_list = is_midr_in_range_list(read_cpuid_id(),
-					 spectre_bhb_firmware_mitigated_list);
-
-	if (scope != SCOPE_LOCAL_CPU)
-		return system_affected;
 
 	fw_state = spectre_bhb_get_cpu_fw_mitigation_state();
-	if (cpu_in_list || (has_smccc && fw_state == SPECTRE_MITIGATED)) {
-		system_affected = true;
-		return true;
-	}
-
-	return false;
+	return has_smccc && fw_state == SPECTRE_MITIGATED;
 }
 
 static bool supports_ecbhb(int scope)
@@ -954,6 +972,8 @@ static bool supports_ecbhb(int scope)
 						    ID_AA64MMFR1_EL1_ECBHB_SHIFT);
 }
 
+static u8 max_bhb_k;
+
 bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry,
 			     int scope)
 {
@@ -962,16 +982,18 @@ bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry,
 	if (supports_csv2p3(scope))
 		return false;
 
-	if (supports_clearbhb(scope))
-		return true;
-
-	if (spectre_bhb_loop_affected(scope))
-		return true;
+	if (is_spectre_bhb_safe(scope))
+		return false;
 
-	if (is_spectre_bhb_fw_affected(scope))
-		return true;
+	/*
+	 * At this point the core isn't known to be "safe" so we're going to
+	 * assume it's vulnerable. We still need to update `max_bhb_k` though,
+	 * but only if we aren't mitigating with clearbhb though.
+	 */
+	if (scope == SCOPE_LOCAL_CPU && !supports_clearbhb(SCOPE_LOCAL_CPU))
+		max_bhb_k = max(max_bhb_k, spectre_bhb_loop_affected());
 
-	return false;
+	return true;
 }
 
 static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot)
@@ -1002,7 +1024,7 @@ early_param("nospectre_bhb", parse_spectre_bhb_param);
 void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry)
 {
 	bp_hardening_cb_t cpu_cb;
-	enum mitigation_state fw_state, state = SPECTRE_VULNERABLE;
+	enum mitigation_state state = SPECTRE_VULNERABLE;
 	struct bp_hardening_data *data = this_cpu_ptr(&bp_hardening_data);
 
 	if (!is_spectre_bhb_affected(entry, SCOPE_LOCAL_CPU))
@@ -1028,7 +1050,7 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry)
 		this_cpu_set_vectors(EL1_VECTOR_BHB_CLEAR_INSN);
 		state = SPECTRE_MITIGATED;
 		set_bit(BHB_INSN, &system_bhb_mitigations);
-	} else if (spectre_bhb_loop_affected(SCOPE_LOCAL_CPU)) {
+	} else if (spectre_bhb_loop_affected()) {
 		/*
 		 * Ensure KVM uses the indirect vector which will have the
 		 * branchy-loop added. A57/A72-r0 will already have selected
@@ -1041,32 +1063,29 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry)
 		this_cpu_set_vectors(EL1_VECTOR_BHB_LOOP);
 		state = SPECTRE_MITIGATED;
 		set_bit(BHB_LOOP, &system_bhb_mitigations);
-	} else if (is_spectre_bhb_fw_affected(SCOPE_LOCAL_CPU)) {
-		fw_state = spectre_bhb_get_cpu_fw_mitigation_state();
-		if (fw_state == SPECTRE_MITIGATED) {
-			/*
-			 * Ensure KVM uses one of the spectre bp_hardening
-			 * vectors. The indirect vector doesn't include the EL3
-			 * call, so needs upgrading to
-			 * HYP_VECTOR_SPECTRE_INDIRECT.
-			 */
-			if (!data->slot || data->slot == HYP_VECTOR_INDIRECT)
-				data->slot += 1;
-
-			this_cpu_set_vectors(EL1_VECTOR_BHB_FW);
-
-			/*
-			 * The WA3 call in the vectors supersedes the WA1 call
-			 * made during context-switch. Uninstall any firmware
-			 * bp_hardening callback.
-			 */
-			cpu_cb = spectre_v2_get_sw_mitigation_cb();
-			if (__this_cpu_read(bp_hardening_data.fn) != cpu_cb)
-				__this_cpu_write(bp_hardening_data.fn, NULL);
-
-			state = SPECTRE_MITIGATED;
-			set_bit(BHB_FW, &system_bhb_mitigations);
-		}
+	} else if (has_spectre_bhb_fw_mitigation()) {
+		/*
+		 * Ensure KVM uses one of the spectre bp_hardening
+		 * vectors. The indirect vector doesn't include the EL3
+		 * call, so needs upgrading to
+		 * HYP_VECTOR_SPECTRE_INDIRECT.
+		 */
+		if (!data->slot || data->slot == HYP_VECTOR_INDIRECT)
+			data->slot += 1;
+
+		this_cpu_set_vectors(EL1_VECTOR_BHB_FW);
+
+		/*
+		 * The WA3 call in the vectors supersedes the WA1 call
+		 * made during context-switch. Uninstall any firmware
+		 * bp_hardening callback.
+		 */
+		cpu_cb = spectre_v2_get_sw_mitigation_cb();
+		if (__this_cpu_read(bp_hardening_data.fn) != cpu_cb)
+			__this_cpu_write(bp_hardening_data.fn, NULL);
+
+		state = SPECTRE_MITIGATED;
+		set_bit(BHB_FW, &system_bhb_mitigations);
 	}
 
 	update_mitigation_state(&spectre_bhb_state, state);
@@ -1100,7 +1119,6 @@ void noinstr spectre_bhb_patch_loop_iter(struct alt_instr *alt,
 {
 	u8 rd;
 	u32 insn;
-	u16 loop_count = spectre_bhb_loop_affected(SCOPE_SYSTEM);
 
 	BUG_ON(nr_inst != 1); /* MOV -> MOV */
 
@@ -1109,7 +1127,7 @@ void noinstr spectre_bhb_patch_loop_iter(struct alt_instr *alt,
 
 	insn = le32_to_cpu(*origptr);
 	rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, insn);
-	insn = aarch64_insn_gen_movewide(rd, loop_count, 0,
+	insn = aarch64_insn_gen_movewide(rd, max_bhb_k, 0,
 					 AARCH64_INSN_VARIANT_64BIT,
 					 AARCH64_INSN_MOVEWIDE_ZERO);
 	*updptr++ = cpu_to_le32(insn);
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 99ea26d400ff..a7c37afb4ebe 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -91,7 +91,7 @@ static void save_reset_user_access_state(struct user_access_state *ua_state)
 		u64 por_enable_all = 0;
 
 		for (int pkey = 0; pkey < arch_max_pkey(); pkey++)
-			por_enable_all |= POE_RXW << (pkey * POR_BITS_PER_PKEY);
+			por_enable_all |= POR_ELx_PERM_PREP(pkey, POE_RWX);
 
 		ua_state->por_el0 = read_sysreg_s(SYS_POR_EL0);
 		write_sysreg_s(por_enable_all, SYS_POR_EL0);
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index cb180684d10d..5d07ee85bdae 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -15,8 +15,11 @@
 #include <linux/arch_topology.h>
 #include <linux/cacheinfo.h>
 #include <linux/cpufreq.h>
+#include <linux/cpu_smt.h>
 #include <linux/init.h>
 #include <linux/percpu.h>
+#include <linux/sched/isolation.h>
+#include <linux/xarray.h>
 
 #include <asm/cpu.h>
 #include <asm/cputype.h>
@@ -37,17 +40,28 @@ static bool __init acpi_cpu_is_threaded(int cpu)
 	return !!is_threaded;
 }
 
+struct cpu_smt_info {
+	unsigned int thread_num;
+	int core_id;
+};
+
 /*
  * Propagate the topology information of the processor_topology_node tree to the
  * cpu_topology array.
  */
 int __init parse_acpi_topology(void)
 {
+	unsigned int max_smt_thread_num = 1;
+	struct cpu_smt_info *entry;
+	struct xarray hetero_cpu;
+	unsigned long hetero_id;
 	int cpu, topology_id;
 
 	if (acpi_disabled)
 		return 0;
 
+	xa_init(&hetero_cpu);
+
 	for_each_possible_cpu(cpu) {
 		topology_id = find_acpi_cpu_topology(cpu, 0);
 		if (topology_id < 0)
@@ -57,6 +71,34 @@ int __init parse_acpi_topology(void)
 			cpu_topology[cpu].thread_id = topology_id;
 			topology_id = find_acpi_cpu_topology(cpu, 1);
 			cpu_topology[cpu].core_id   = topology_id;
+
+			/*
+			 * In the PPTT, CPUs below a node with the 'identical
+			 * implementation' flag have the same number of threads.
+			 * Count the number of threads for only one CPU (i.e.
+			 * one core_id) among those with the same hetero_id.
+			 * See the comment of find_acpi_cpu_topology_hetero_id()
+			 * for more details.
+			 *
+			 * One entry is created for each node having:
+			 * - the 'identical implementation' flag
+			 * - its parent not having the flag
+			 */
+			hetero_id = find_acpi_cpu_topology_hetero_id(cpu);
+			entry = xa_load(&hetero_cpu, hetero_id);
+			if (!entry) {
+				entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+				WARN_ON_ONCE(!entry);
+
+				if (entry) {
+					entry->core_id = topology_id;
+					entry->thread_num = 1;
+					xa_store(&hetero_cpu, hetero_id,
+						 entry, GFP_KERNEL);
+				}
+			} else if (entry->core_id == topology_id) {
+				entry->thread_num++;
+			}
 		} else {
 			cpu_topology[cpu].thread_id  = -1;
 			cpu_topology[cpu].core_id    = topology_id;
@@ -67,6 +109,19 @@ int __init parse_acpi_topology(void)
 		cpu_topology[cpu].package_id = topology_id;
 	}
 
+	/*
+	 * This is a short loop since the number of XArray elements is the
+	 * number of heterogeneous CPU clusters. On a homogeneous system
+	 * there's only one entry in the XArray.
+	 */
+	xa_for_each(&hetero_cpu, hetero_id, entry) {
+		max_smt_thread_num = max(max_smt_thread_num, entry->thread_num);
+		xa_erase(&hetero_cpu, hetero_id);
+		kfree(entry);
+	}
+
+	cpu_smt_set_num_threads(max_smt_thread_num, max_smt_thread_num);
+	xa_destroy(&hetero_cpu);
 	return 0;
 }
 #endif
@@ -88,18 +143,28 @@ int __init parse_acpi_topology(void)
  * initialized.
  */
 static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale) =  1UL << (2 * SCHED_CAPACITY_SHIFT);
-static DEFINE_PER_CPU(u64, arch_const_cycles_prev);
-static DEFINE_PER_CPU(u64, arch_core_cycles_prev);
 static cpumask_var_t amu_fie_cpus;
 
+struct amu_cntr_sample {
+	u64		arch_const_cycles_prev;
+	u64		arch_core_cycles_prev;
+	unsigned long	last_scale_update;
+};
+
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct amu_cntr_sample, cpu_amu_samples);
+
 void update_freq_counters_refs(void)
 {
-	this_cpu_write(arch_core_cycles_prev, read_corecnt());
-	this_cpu_write(arch_const_cycles_prev, read_constcnt());
+	struct amu_cntr_sample *amu_sample = this_cpu_ptr(&cpu_amu_samples);
+
+	amu_sample->arch_core_cycles_prev = read_corecnt();
+	amu_sample->arch_const_cycles_prev = read_constcnt();
 }
 
 static inline bool freq_counters_valid(int cpu)
 {
+	struct amu_cntr_sample *amu_sample = per_cpu_ptr(&cpu_amu_samples, cpu);
+
 	if ((cpu >= nr_cpu_ids) || !cpumask_test_cpu(cpu, cpu_present_mask))
 		return false;
 
@@ -108,8 +173,8 @@ static inline bool freq_counters_valid(int cpu)
 		return false;
 	}
 
-	if (unlikely(!per_cpu(arch_const_cycles_prev, cpu) ||
-		     !per_cpu(arch_core_cycles_prev, cpu))) {
+	if (unlikely(!amu_sample->arch_const_cycles_prev ||
+		     !amu_sample->arch_core_cycles_prev)) {
 		pr_debug("CPU%d: cycle counters are not enabled.\n", cpu);
 		return false;
 	}
@@ -152,17 +217,22 @@ void freq_inv_set_max_ratio(int cpu, u64 max_rate)
 
 static void amu_scale_freq_tick(void)
 {
+	struct amu_cntr_sample *amu_sample = this_cpu_ptr(&cpu_amu_samples);
 	u64 prev_core_cnt, prev_const_cnt;
 	u64 core_cnt, const_cnt, scale;
 
-	prev_const_cnt = this_cpu_read(arch_const_cycles_prev);
-	prev_core_cnt = this_cpu_read(arch_core_cycles_prev);
+	prev_const_cnt = amu_sample->arch_const_cycles_prev;
+	prev_core_cnt = amu_sample->arch_core_cycles_prev;
 
 	update_freq_counters_refs();
 
-	const_cnt = this_cpu_read(arch_const_cycles_prev);
-	core_cnt = this_cpu_read(arch_core_cycles_prev);
+	const_cnt = amu_sample->arch_const_cycles_prev;
+	core_cnt = amu_sample->arch_core_cycles_prev;
 
+	/*
+	 * This should not happen unless the AMUs have been reset and the
+	 * counter values have not been restored - unlikely
+	 */
 	if (unlikely(core_cnt <= prev_core_cnt ||
 		     const_cnt <= prev_const_cnt))
 		return;
@@ -182,6 +252,8 @@ static void amu_scale_freq_tick(void)
 
 	scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE);
 	this_cpu_write(arch_freq_scale, (unsigned long)scale);
+
+	amu_sample->last_scale_update = jiffies;
 }
 
 static struct scale_freq_data amu_sfd = {
@@ -189,6 +261,96 @@ static struct scale_freq_data amu_sfd = {
 	.set_freq_scale = amu_scale_freq_tick,
 };
 
+static __always_inline bool amu_fie_cpu_supported(unsigned int cpu)
+{
+	return cpumask_available(amu_fie_cpus) &&
+		cpumask_test_cpu(cpu, amu_fie_cpus);
+}
+
+void arch_cpu_idle_enter(void)
+{
+	unsigned int cpu = smp_processor_id();
+
+	if (!amu_fie_cpu_supported(cpu))
+		return;
+
+	/* Kick in AMU update but only if one has not happened already */
+	if (housekeeping_cpu(cpu, HK_TYPE_TICK) &&
+	    time_is_before_jiffies(per_cpu(cpu_amu_samples.last_scale_update, cpu)))
+		amu_scale_freq_tick();
+}
+
+#define AMU_SAMPLE_EXP_MS	20
+
+int arch_freq_get_on_cpu(int cpu)
+{
+	struct amu_cntr_sample *amu_sample;
+	unsigned int start_cpu = cpu;
+	unsigned long last_update;
+	unsigned int freq = 0;
+	u64 scale;
+
+	if (!amu_fie_cpu_supported(cpu) || !arch_scale_freq_ref(cpu))
+		return -EOPNOTSUPP;
+
+	while (1) {
+
+		amu_sample = per_cpu_ptr(&cpu_amu_samples, cpu);
+
+		last_update = amu_sample->last_scale_update;
+
+		/*
+		 * For those CPUs that are in full dynticks mode, or those that have
+		 * not seen tick for a while, try an alternative source for the counters
+		 * (and thus freq scale), if available, for given policy: this boils
+		 * down to identifying an active cpu within the same freq domain, if any.
+		 */
+		if (!housekeeping_cpu(cpu, HK_TYPE_TICK) ||
+		    time_is_before_jiffies(last_update + msecs_to_jiffies(AMU_SAMPLE_EXP_MS))) {
+			struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+			int ref_cpu;
+
+			if (!policy)
+				return -EINVAL;
+
+			if (!cpumask_intersects(policy->related_cpus,
+						housekeeping_cpumask(HK_TYPE_TICK))) {
+				cpufreq_cpu_put(policy);
+				return -EOPNOTSUPP;
+			}
+
+			for_each_cpu_wrap(ref_cpu, policy->cpus, cpu + 1) {
+				if (ref_cpu == start_cpu) {
+					/* Prevent verifying same CPU twice */
+					ref_cpu = nr_cpu_ids;
+					break;
+				}
+				if (!idle_cpu(ref_cpu))
+					break;
+			}
+
+			cpufreq_cpu_put(policy);
+
+			if (ref_cpu >= nr_cpu_ids)
+				/* No alternative to pull info from */
+				return -EAGAIN;
+
+			cpu = ref_cpu;
+		} else {
+			break;
+		}
+	}
+	/*
+	 * Reversed computation to the one used to determine
+	 * the arch_freq_scale value
+	 * (see amu_scale_freq_tick for details)
+	 */
+	scale = arch_scale_freq_capacity(cpu);
+	freq = scale * arch_scale_freq_ref(cpu);
+	freq >>= SCHED_CAPACITY_SHIFT;
+	return freq;
+}
+
 static void amu_fie_setup(const struct cpumask *cpus)
 {
 	int cpu;
diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c
index 3a96c96816e9..f74a66ce3064 100644
--- a/arch/arm64/kvm/at.c
+++ b/arch/arm64/kvm/at.c
@@ -1090,22 +1090,22 @@ static void compute_s1_overlay_permissions(struct kvm_vcpu *vcpu,
 		break;
 	}
 
-	if (pov_perms & ~POE_RXW)
+	if (pov_perms & ~POE_RWX)
 		pov_perms = POE_NONE;
 
 	if (wi->poe && wr->pov) {
 		wr->pr &= pov_perms & POE_R;
-		wr->px &= pov_perms & POE_X;
 		wr->pw &= pov_perms & POE_W;
+		wr->px &= pov_perms & POE_X;
 	}
 
-	if (uov_perms & ~POE_RXW)
+	if (uov_perms & ~POE_RWX)
 		uov_perms = POE_NONE;
 
 	if (wi->e0poe && wr->uov) {
 		wr->ur &= uov_perms & POE_R;
-		wr->ux &= uov_perms & POE_X;
 		wr->uw &= uov_perms & POE_W;
+		wr->ux &= uov_perms & POE_X;
 	}
 }
 
diff --git a/arch/arm64/kvm/ptdump.c b/arch/arm64/kvm/ptdump.c
index e4a342e903e2..098416d7e5c2 100644
--- a/arch/arm64/kvm/ptdump.c
+++ b/arch/arm64/kvm/ptdump.c
@@ -52,8 +52,8 @@ static const struct ptdump_prot_bits stage2_pte_bits[] = {
 		.set	= "AF",
 		.clear	= "  ",
 	}, {
-		.mask	= PTE_TABLE_BIT | PTE_VALID,
-		.val	= PTE_VALID,
+		.mask	= PMD_TYPE_MASK,
+		.val	= PMD_TYPE_SECT,
 		.set	= "BLK",
 		.clear	= "   ",
 	},
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index a5a5f5b97b17..de9a303b6ad0 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -17,14 +17,27 @@
  * Alignment fixed up by hardware.
  */
 
-	.p2align 4
-	// Alignment is for the loop, but since the prologue (including BTI)
-	// is also 16 bytes we can keep any padding outside the function
 SYM_FUNC_START(__arch_clear_user)
 	add	x2, x0, x1
+
+#ifdef CONFIG_AS_HAS_MOPS
+	.arch_extension mops
+alternative_if_not ARM64_HAS_MOPS
+	b	.Lno_mops
+alternative_else_nop_endif
+
+USER(9f, setpt	[x0]!, x1!, xzr)
+USER(6f, setmt	[x0]!, x1!, xzr)
+USER(6f, setet	[x0]!, x1!, xzr)
+	mov	x0, #0
+	ret
+.Lno_mops:
+#endif
+
 	subs	x1, x1, #8
 	b.mi	2f
-1:
+
+1:	.p2align 4
 USER(9f, sttr	xzr, [x0])
 	add	x0, x0, #8
 	subs	x1, x1, #8
@@ -47,6 +60,10 @@ USER(7f, sttrb	wzr, [x2, #-1])
 	ret
 
 	// Exception fixups
+6:	b.cs	9f
+	// Registers are in Option A format
+	add	x0, x0, x1
+	b	9f
 7:	sub	x0, x2, #5	// Adjust for faulting on the final byte...
 8:	add	x0, x0, #4	// ...or the second word of the 4-7 byte case
 9:	sub	x0, x2, x0
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index 34e317907524..400057d607ec 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -52,6 +52,13 @@
 	stp \reg1, \reg2, [\ptr], \val
 	.endm
 
+	.macro cpy1 dst, src, count
+	.arch_extension mops
+	USER_CPY(9997f, 0, cpyfprt [\dst]!, [\src]!, \count!)
+	USER_CPY(9996f, 0, cpyfmrt [\dst]!, [\src]!, \count!)
+	USER_CPY(9996f, 0, cpyfert [\dst]!, [\src]!, \count!)
+	.endm
+
 end	.req	x5
 srcin	.req	x15
 SYM_FUNC_START(__arch_copy_from_user)
@@ -62,6 +69,9 @@ SYM_FUNC_START(__arch_copy_from_user)
 	ret
 
 	// Exception fixups
+9996:	b.cs	9997f
+	// Registers are in Option A format
+	add	dst, dst, count
 9997:	cmp	dst, dstin
 	b.ne	9998f
 	// Before being absolutely sure we couldn't copy anything, try harder
diff --git a/arch/arm64/lib/copy_template.S b/arch/arm64/lib/copy_template.S
index 488df234c49a..7f2f5a0e2fb9 100644
--- a/arch/arm64/lib/copy_template.S
+++ b/arch/arm64/lib/copy_template.S
@@ -40,6 +40,16 @@ D_l	.req	x13
 D_h	.req	x14
 
 	mov	dst, dstin
+
+#ifdef CONFIG_AS_HAS_MOPS
+alternative_if_not ARM64_HAS_MOPS
+	b	.Lno_mops
+alternative_else_nop_endif
+	cpy1	dst, src, count
+	b	.Lexitfunc
+.Lno_mops:
+#endif
+
 	cmp	count, #16
 	/*When memory length is less than 16, the accessed are not aligned.*/
 	b.lo	.Ltiny15
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
index 802231772608..819f2e3fc7a9 100644
--- a/arch/arm64/lib/copy_to_user.S
+++ b/arch/arm64/lib/copy_to_user.S
@@ -51,6 +51,13 @@
 	user_stp 9997f, \reg1, \reg2, \ptr, \val
 	.endm
 
+	.macro cpy1 dst, src, count
+	.arch_extension mops
+	USER_CPY(9997f, 1, cpyfpwt [\dst]!, [\src]!, \count!)
+	USER_CPY(9996f, 1, cpyfmwt [\dst]!, [\src]!, \count!)
+	USER_CPY(9996f, 1, cpyfewt [\dst]!, [\src]!, \count!)
+	.endm
+
 end	.req	x5
 srcin	.req	x15
 SYM_FUNC_START(__arch_copy_to_user)
@@ -61,6 +68,9 @@ SYM_FUNC_START(__arch_copy_to_user)
 	ret
 
 	// Exception fixups
+9996:	b.cs	9997f
+	// Registers are in Option A format
+	add	dst, dst, count
 9997:	cmp	dst, dstin
 	b.ne	9998f
 	// Before being absolutely sure we couldn't copy anything, try harder
diff --git a/arch/arm64/mm/extable.c b/arch/arm64/mm/extable.c
index 228d681a8715..6e0528831cd3 100644
--- a/arch/arm64/mm/extable.c
+++ b/arch/arm64/mm/extable.c
@@ -8,8 +8,33 @@
 #include <linux/uaccess.h>
 
 #include <asm/asm-extable.h>
+#include <asm/esr.h>
 #include <asm/ptrace.h>
 
+static bool cpy_faulted_on_uaccess(const struct exception_table_entry *ex,
+				   unsigned long esr)
+{
+	bool uaccess_is_write = FIELD_GET(EX_DATA_UACCESS_WRITE, ex->data);
+	bool fault_on_write = esr & ESR_ELx_WNR;
+
+	return uaccess_is_write == fault_on_write;
+}
+
+bool insn_may_access_user(unsigned long addr, unsigned long esr)
+{
+	const struct exception_table_entry *ex = search_exception_tables(addr);
+
+	if (!ex)
+		return false;
+
+	switch (ex->type) {
+	case EX_TYPE_UACCESS_CPY:
+		return cpy_faulted_on_uaccess(ex, esr);
+	default:
+		return true;
+	}
+}
+
 static inline unsigned long
 get_ex_fixup(const struct exception_table_entry *ex)
 {
@@ -29,6 +54,17 @@ static bool ex_handler_uaccess_err_zero(const struct exception_table_entry *ex,
 	return true;
 }
 
+static bool ex_handler_uaccess_cpy(const struct exception_table_entry *ex,
+				   struct pt_regs *regs, unsigned long esr)
+{
+	/* Do not fix up faults on kernel memory accesses */
+	if (!cpy_faulted_on_uaccess(ex, esr))
+		return false;
+
+	regs->pc = get_ex_fixup(ex);
+	return true;
+}
+
 static bool
 ex_handler_load_unaligned_zeropad(const struct exception_table_entry *ex,
 				  struct pt_regs *regs)
@@ -56,7 +92,7 @@ ex_handler_load_unaligned_zeropad(const struct exception_table_entry *ex,
 	return true;
 }
 
-bool fixup_exception(struct pt_regs *regs)
+bool fixup_exception(struct pt_regs *regs, unsigned long esr)
 {
 	const struct exception_table_entry *ex;
 
@@ -70,6 +106,8 @@ bool fixup_exception(struct pt_regs *regs)
 	case EX_TYPE_UACCESS_ERR_ZERO:
 	case EX_TYPE_KACCESS_ERR_ZERO:
 		return ex_handler_uaccess_err_zero(ex, regs);
+	case EX_TYPE_UACCESS_CPY:
+		return ex_handler_uaccess_cpy(ex, regs, esr);
 	case EX_TYPE_LOAD_UNALIGNED_ZEROPAD:
 		return ex_handler_load_unaligned_zeropad(ex, regs);
 	}
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index ef63651099a9..ec0a337891dd 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -375,7 +375,7 @@ static void __do_kernel_fault(unsigned long addr, unsigned long esr,
 	 * Are we prepared to handle this kernel fault?
 	 * We are almost certainly not prepared to handle instruction faults.
 	 */
-	if (!is_el1_instruction_abort(esr) && fixup_exception(regs))
+	if (!is_el1_instruction_abort(esr) && fixup_exception(regs, esr))
 		return;
 
 	if (WARN_RATELIMIT(is_spurious_el1_translation_fault(addr, esr, regs),
@@ -606,7 +606,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
 			die_kernel_fault("execution of user memory",
 					 addr, esr, regs);
 
-		if (!search_exception_tables(regs->pc))
+		if (!insn_may_access_user(regs->pc, esr))
 			die_kernel_fault("access to user memory outside uaccess routines",
 					 addr, esr, regs);
 	}
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index b3a7fafe8892..cfe8cb8ba1cc 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -334,7 +334,9 @@ unsigned long hugetlb_mask_last_page(struct hstate *h)
 	switch (hp_size) {
 #ifndef __PAGETABLE_PMD_FOLDED
 	case PUD_SIZE:
-		return PGDIR_SIZE - PUD_SIZE;
+		if (pud_sect_supported())
+			return PGDIR_SIZE - PUD_SIZE;
+		break;
 #endif
 	case CONT_PMD_SIZE:
 		return PUD_SIZE - CONT_PMD_SIZE;
@@ -356,23 +358,21 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
 	switch (pagesize) {
 #ifndef __PAGETABLE_PMD_FOLDED
 	case PUD_SIZE:
-		entry = pud_pte(pud_mkhuge(pte_pud(entry)));
+		if (pud_sect_supported())
+			return pud_pte(pud_mkhuge(pte_pud(entry)));
 		break;
 #endif
 	case CONT_PMD_SIZE:
-		entry = pmd_pte(pmd_mkcont(pte_pmd(entry)));
-		fallthrough;
+		return pmd_pte(pmd_mkhuge(pmd_mkcont(pte_pmd(entry))));
 	case PMD_SIZE:
-		entry = pmd_pte(pmd_mkhuge(pte_pmd(entry)));
-		break;
+		return pmd_pte(pmd_mkhuge(pte_pmd(entry)));
 	case CONT_PTE_SIZE:
-		entry = pte_mkcont(entry);
-		break;
+		return pte_mkcont(entry);
 	default:
-		pr_warn("%s: unrecognized huge page size 0x%lx\n",
-			__func__, pagesize);
 		break;
 	}
+	pr_warn("%s: unrecognized huge page size 0x%lx\n",
+		__func__, pagesize);
 	return entry;
 }
 
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index b65a29440a0c..d541ce45daeb 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -190,7 +190,7 @@ static void __init kasan_pgd_populate(unsigned long addr, unsigned long end,
  */
 static bool __init root_level_aligned(u64 addr)
 {
-	int shift = (ARM64_HW_PGTABLE_LEVELS(vabits_actual) - 1) * (PAGE_SHIFT - 3);
+	int shift = (ARM64_HW_PGTABLE_LEVELS(vabits_actual) - 1) * PTDESC_TABLE_SHIFT;
 
 	return (addr % (PAGE_SIZE << shift)) == 0;
 }
@@ -245,7 +245,7 @@ static int __init root_level_idx(u64 addr)
 	 */
 	u64 vabits = IS_ENABLED(CONFIG_ARM64_64K_PAGES) ? VA_BITS
 							: vabits_actual;
-	int shift = (ARM64_HW_PGTABLE_LEVELS(vabits) - 1) * (PAGE_SHIFT - 3);
+	int shift = (ARM64_HW_PGTABLE_LEVELS(vabits) - 1) * PTDESC_TABLE_SHIFT;
 
 	return (addr & ~_PAGE_OFFSET(vabits)) >> (shift + PAGE_SHIFT);
 }
@@ -269,7 +269,7 @@ static void __init clone_next_level(u64 addr, pgd_t *tmp_pg_dir, pud_t *pud)
  */
 static int __init next_level_idx(u64 addr)
 {
-	int shift = (ARM64_HW_PGTABLE_LEVELS(vabits_actual) - 2) * (PAGE_SHIFT - 3);
+	int shift = (ARM64_HW_PGTABLE_LEVELS(vabits_actual) - 2) * PTDESC_TABLE_SHIFT;
 
 	return (addr >> (shift + PAGE_SHIFT)) % PTRS_PER_PTE;
 }
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 1dfe1a8efdbe..b98f89420713 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1558,9 +1558,8 @@ void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp)
 #ifdef CONFIG_ARCH_HAS_PKEYS
 int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val)
 {
-	u64 new_por = POE_RXW;
+	u64 new_por;
 	u64 old_por;
-	u64 pkey_shift;
 
 	if (!system_supports_poe())
 		return -ENOSPC;
@@ -1574,7 +1573,7 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long i
 		return -EINVAL;
 
 	/* Set the bits we need in POR:  */
-	new_por = POE_RXW;
+	new_por = POE_RWX;
 	if (init_val & PKEY_DISABLE_WRITE)
 		new_por &= ~POE_W;
 	if (init_val & PKEY_DISABLE_ACCESS)
@@ -1585,12 +1584,11 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long i
 		new_por &= ~POE_X;
 
 	/* Shift the bits in to the correct place in POR for pkey: */
-	pkey_shift = pkey * POR_BITS_PER_PKEY;
-	new_por <<= pkey_shift;
+	new_por = POR_ELx_PERM_PREP(pkey, new_por);
 
 	/* Get old POR and mask off any old bits in place: */
 	old_por = read_sysreg_s(SYS_POR_EL0);
-	old_por &= ~(POE_MASK << pkey_shift);
+	old_por &= ~(POE_MASK << POR_ELx_PERM_SHIFT(pkey));
 
 	/* Write old part along with new part: */
 	write_sysreg_s(old_por | new_por, SYS_POR_EL0);
diff --git a/arch/arm64/mm/physaddr.c b/arch/arm64/mm/physaddr.c
index cde44c13dda1..7d94e09b01b3 100644
--- a/arch/arm64/mm/physaddr.c
+++ b/arch/arm64/mm/physaddr.c
@@ -10,7 +10,7 @@
 phys_addr_t __virt_to_phys(unsigned long x)
 {
 	WARN(!__is_lm_address(__tag_reset(x)),
-	     "virt_to_phys used for non-linear address: %pK (%pS)\n",
+	     "virt_to_phys used for non-linear address: %p (%pS)\n",
 	      (void *)x,
 	      (void *)x);
 
diff --git a/arch/arm64/mm/ptdump.c b/arch/arm64/mm/ptdump.c
index 688fbe0271ca..8cec0da4cff2 100644
--- a/arch/arm64/mm/ptdump.c
+++ b/arch/arm64/mm/ptdump.c
@@ -80,8 +80,8 @@ static const struct ptdump_prot_bits pte_bits[] = {
 		.set	= "CON",
 		.clear	= "   ",
 	}, {
-		.mask	= PTE_TABLE_BIT | PTE_VALID,
-		.val	= PTE_VALID,
+		.mask	= PMD_TYPE_MASK,
+		.val	= PMD_TYPE_SECT,
 		.set	= "BLK",
 		.clear	= "   ",
 	}, {
diff --git a/arch/arm64/tools/gen-sysreg.awk b/arch/arm64/tools/gen-sysreg.awk
index 1a2afc9fdd42..f2a1732cb1f6 100755
--- a/arch/arm64/tools/gen-sysreg.awk
+++ b/arch/arm64/tools/gen-sysreg.awk
@@ -111,7 +111,7 @@ END {
 /^$/ { next }
 /^[\t ]*#/ { next }
 
-/^SysregFields/ && block_current() == "Root" {
+$1 == "SysregFields" && block_current() == "Root" {
 	block_push("SysregFields")
 
 	expect_fields(2)
@@ -127,7 +127,8 @@ END {
 	next
 }
 
-/^EndSysregFields/ && block_current() == "SysregFields" {
+$1 == "EndSysregFields" && block_current() == "SysregFields" {
+	expect_fields(1)
 	if (next_bit > 0)
 		fatal("Unspecified bits in " reg)
 
@@ -145,7 +146,7 @@ END {
 	next
 }
 
-/^Sysreg/ && block_current() == "Root" {
+$1 == "Sysreg" && block_current() == "Root" {
 	block_push("Sysreg")
 
 	expect_fields(7)
@@ -177,7 +178,8 @@ END {
 	next
 }
 
-/^EndSysreg/ && block_current() == "Sysreg" {
+$1 == "EndSysreg" && block_current() == "Sysreg" {
+	expect_fields(1)
 	if (next_bit > 0)
 		fatal("Unspecified bits in " reg)
 
@@ -206,7 +208,7 @@ END {
 
 # Currently this is effectivey a comment, in future we may want to emit
 # defines for the fields.
-(/^Fields/ || /^Mapping/) && block_current() == "Sysreg" {
+($1 == "Fields" || $1 == "Mapping") && block_current() == "Sysreg" {
 	expect_fields(2)
 
 	if (next_bit != 63)
@@ -224,7 +226,7 @@ END {
 }
 
 
-/^Res0/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+$1 == "Res0" && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	expect_fields(2)
 	parse_bitdef(reg, "RES0", $2)
 	field = "RES0_" msb "_" lsb
@@ -234,7 +236,7 @@ END {
 	next
 }
 
-/^Res1/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+$1 == "Res1" && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	expect_fields(2)
 	parse_bitdef(reg, "RES1", $2)
 	field = "RES1_" msb "_" lsb
@@ -244,7 +246,7 @@ END {
 	next
 }
 
-/^Unkn/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+$1 == "Unkn" && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	expect_fields(2)
 	parse_bitdef(reg, "UNKN", $2)
 	field = "UNKN_" msb "_" lsb
@@ -254,7 +256,7 @@ END {
 	next
 }
 
-/^Field/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+$1 == "Field" && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	expect_fields(3)
 	field = $3
 	parse_bitdef(reg, field, $2)
@@ -265,14 +267,14 @@ END {
 	next
 }
 
-/^Raz/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+$1 == "Raz" && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	expect_fields(2)
 	parse_bitdef(reg, field, $2)
 
 	next
 }
 
-/^SignedEnum/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+$1 == "SignedEnum" && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	block_push("Enum")
 
 	expect_fields(3)
@@ -285,7 +287,7 @@ END {
 	next
 }
 
-/^UnsignedEnum/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+$1 == "UnsignedEnum" && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	block_push("Enum")
 
 	expect_fields(3)
@@ -298,7 +300,7 @@ END {
 	next
 }
 
-/^Enum/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+$1 == "Enum" && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	block_push("Enum")
 
 	expect_fields(3)
@@ -310,7 +312,8 @@ END {
 	next
 }
 
-/^EndEnum/ && block_current() == "Enum" {
+$1 == "EndEnum" && block_current() == "Enum" {
+	expect_fields(1)
 
 	field = null
 	msb = null
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index 762ee084b37c..10809047fc87 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -1664,6 +1664,7 @@ EndEnum
 UnsignedEnum	59:56	FGT
 	0b0000	NI
 	0b0001	IMP
+	0b0010	FGT2
 EndEnum
 Res0	55:48
 UnsignedEnum	47:44	EXS
@@ -1725,6 +1726,7 @@ Enum	3:0	PARANGE
 	0b0100	44
 	0b0101	48
 	0b0110	52
+	0b0111	56
 EndEnum
 EndSysreg
 
@@ -2074,7 +2076,7 @@ EndEnum
 Res0	4:2
 Field	1	ExTRE
 Field	0	E0TRE
-EndSysregFields
+EndSysreg
 
 Sysreg	SMPRI_EL1	3	0	1	2	4
 Res0	63:4
@@ -2641,6 +2643,101 @@ Field	0	E0HTRE
 EndSysreg
 
 
+Sysreg HDFGRTR2_EL2	3	4	3	1	0
+Res0	63:25
+Field	24	nPMBMAR_EL1
+Field	23	nMDSTEPOP_EL1
+Field	22	nTRBMPAM_EL1
+Res0	21
+Field	20	nTRCITECR_EL1
+Field	19	nPMSDSFR_EL1
+Field	18	nSPMDEVAFF_EL1
+Field	17	nSPMID
+Field	16	nSPMSCR_EL1
+Field	15	nSPMACCESSR_EL1
+Field	14	nSPMCR_EL0
+Field	13	nSPMOVS
+Field	12	nSPMINTEN
+Field	11	nSPMCNTEN
+Field	10	nSPMSELR_EL0
+Field	9	nSPMEVTYPERn_EL0
+Field	8	nSPMEVCNTRn_EL0
+Field	7	nPMSSCR_EL1
+Field	6	nPMSSDATA
+Field	5	nMDSELR_EL1
+Field	4	nPMUACR_EL1
+Field	3	nPMICFILTR_EL0
+Field	2	nPMICNTR_EL0
+Field	1	nPMIAR_EL1
+Field	0	nPMECR_EL1
+EndSysreg
+
+Sysreg HDFGWTR2_EL2	3	4	3	1	1
+Res0	63:25
+Field	24	nPMBMAR_EL1
+Field	23	nMDSTEPOP_EL1
+Field	22	nTRBMPAM_EL1
+Field	21	nPMZR_EL0
+Field	20	nTRCITECR_EL1
+Field	19	nPMSDSFR_EL1
+Res0	18:17
+Field	16	nSPMSCR_EL1
+Field	15	nSPMACCESSR_EL1
+Field	14	nSPMCR_EL0
+Field	13	nSPMOVS
+Field	12	nSPMINTEN
+Field	11	nSPMCNTEN
+Field	10	nSPMSELR_EL0
+Field	9	nSPMEVTYPERn_EL0
+Field	8	nSPMEVCNTRn_EL0
+Field	7	nPMSSCR_EL1
+Res0	6
+Field	5	nMDSELR_EL1
+Field	4	nPMUACR_EL1
+Field	3	nPMICFILTR_EL0
+Field	2	nPMICNTR_EL0
+Field	1	nPMIAR_EL1
+Field	0	nPMECR_EL1
+EndSysreg
+
+Sysreg	HFGRTR2_EL2	3	4	3	1	2
+Res0	63:15
+Field	14	nACTLRALIAS_EL1
+Field	13	nACTLRMASK_EL1
+Field	12	nTCR2ALIAS_EL1
+Field	11	nTCRALIAS_EL1
+Field	10	nSCTLRALIAS2_EL1
+Field	9	nSCTLRALIAS_EL1
+Field	8	nCPACRALIAS_EL1
+Field	7	nTCR2MASK_EL1
+Field	6	nTCRMASK_EL1
+Field	5	nSCTLR2MASK_EL1
+Field	4	nSCTLRMASK_EL1
+Field	3	nCPACRMASK_EL1
+Field	2	nRCWSMASK_EL1
+Field	1	nERXGSR_EL1
+Field	0	nPFAR_EL1
+EndSysreg
+
+Sysreg	HFGWTR2_EL2	3	4	3	1	3
+Res0	63:15
+Field	14	nACTLRALIAS_EL1
+Field	13	nACTLRMASK_EL1
+Field	12	nTCR2ALIAS_EL1
+Field	11	nTCRALIAS_EL1
+Field	10	nSCTLRALIAS2_EL1
+Field	9	nSCTLRALIAS_EL1
+Field	8	nCPACRALIAS_EL1
+Field	7	nTCR2MASK_EL1
+Field	6	nTCRMASK_EL1
+Field	5	nSCTLR2MASK_EL1
+Field	4	nSCTLRMASK_EL1
+Field	3	nCPACRMASK_EL1
+Field	2	nRCWSMASK_EL1
+Res0	1
+Field	0	nPFAR_EL1
+EndSysreg
+
 Sysreg HDFGRTR_EL2	3	4	3	1	4
 Field	63	PMBIDR_EL1
 Field	62	nPMSNEVFR_EL1
@@ -2813,6 +2910,12 @@ Field	1	AMEVCNTR00_EL0
 Field	0	AMCNTEN0
 EndSysreg
 
+Sysreg	HFGITR2_EL2	3	4	3	1	7
+Res0	63:2
+Field	1	nDCCIVAPS
+Field	0	TSBCSYNC
+EndSysreg
+
 Sysreg	ZCR_EL2	3	4	1	2	0
 Fields	ZCR_ELx
 EndSysreg
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 16bacfe8c7a2..da15b5efe807 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -152,6 +152,7 @@ static inline bool topology_is_primary_thread(unsigned int cpu)
 {
 	return cpu == cpu_first_thread_sibling(cpu);
 }
+#define topology_is_primary_thread topology_is_primary_thread
 
 static inline bool topology_smt_thread_allowed(unsigned int cpu)
 {
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index ec134b719144..6c79ee7c0957 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -229,11 +229,11 @@ static inline bool topology_is_primary_thread(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_primary_thread_mask);
 }
+#define topology_is_primary_thread topology_is_primary_thread
 
 #else /* CONFIG_SMP */
 static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
 static inline int topology_max_smt_threads(void) { return 1; }
-static inline bool topology_is_primary_thread(unsigned int cpu) { return true; }
 static inline unsigned int topology_amd_nodes_per_pkg(void) { return 1; }
 #endif /* !CONFIG_SMP */
 
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index f642de2ebdac..6cf31a1649c4 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -498,7 +498,7 @@ void arch_scale_freq_tick(void)
  */
 #define MAX_SAMPLE_AGE	((unsigned long)HZ / 50)
 
-unsigned int arch_freq_get_on_cpu(int cpu)
+int arch_freq_get_on_cpu(int cpu)
 {
 	struct aperfmperf *s = per_cpu_ptr(&cpu_samples, cpu);
 	unsigned int seq, freq;
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 41ed01f46bd9..6571d432cbe3 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -86,9 +86,12 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		seq_printf(m, "microcode\t: 0x%x\n", c->microcode);
 
 	if (cpu_has(c, X86_FEATURE_TSC)) {
-		unsigned int freq = arch_freq_get_on_cpu(cpu);
+		int freq = arch_freq_get_on_cpu(cpu);
 
-		seq_printf(m, "cpu MHz\t\t: %u.%03u\n", freq / 1000, (freq % 1000));
+		if (freq < 0)
+			seq_puts(m, "cpu MHz\t\t: Unknown\n");
+		else
+			seq_printf(m, "cpu MHz\t\t: %u.%03u\n", freq / 1000, (freq % 1000));
 	}
 
 	/* Cache size */