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

Pull arm64 updates from Will Deacon:
 "The highlights this time are support for dynamically enabling and
  disabling Clang's Shadow Call Stack at boot and a long-awaited
  optimisation to the way in which we handle the SVE register state on
  system call entry to avoid taking unnecessary traps from userspace.

  Summary:

  ACPI:
   - Enable FPDT support for boot-time profiling
   - Fix CPU PMU probing to work better with PREEMPT_RT
   - Update SMMUv3 MSI DeviceID parsing to latest IORT spec
   - APMT support for probing Arm CoreSight PMU devices

  CPU features:
   - Advertise new SVE instructions (v2.1)
   - Advertise range prefetch instruction
   - Advertise CSSC ("Common Short Sequence Compression") scalar
     instructions, adding things like min, max, abs, popcount
   - Enable DIT (Data Independent Timing) when running in the kernel
   - More conversion of system register fields over to the generated
     header

  CPU misfeatures:
   - Workaround for Cortex-A715 erratum #2645198

  Dynamic SCS:
   - Support for dynamic shadow call stacks to allow switching at
     runtime between Clang's SCS implementation and the CPU's pointer
     authentication feature when it is supported (complete with scary
     DWARF parser!)

  Tracing and debug:
   - Remove static ftrace in favour of, err, dynamic ftrace!
   - Seperate 'struct ftrace_regs' from 'struct pt_regs' in core ftrace
     and existing arch code
   - Introduce and implement FTRACE_WITH_ARGS on arm64 to replace the
     old FTRACE_WITH_REGS
   - Extend 'crashkernel=' parameter with default value and fallback to
     placement above 4G physical if initial (low) allocation fails

  SVE:
   - Optimisation to avoid disabling SVE unconditionally on syscall
     entry and just zeroing the non-shared state on return instead

  Exceptions:
   - Rework of undefined instruction handling to avoid serialisation on
     global lock (this includes emulation of user accesses to the ID
     registers)

  Perf and PMU:
   - Support for TLP filters in Hisilicon's PCIe PMU device
   - Support for the DDR PMU present in Amlogic Meson G12 SoCs
   - Support for the terribly-named "CoreSight PMU" architecture from
     Arm (and Nvidia's implementation of said architecture)

  Misc:
   - Tighten up our boot protocol for systems with memory above 52 bits
     physical
   - Const-ify static keys to satisty jump label asm constraints
   - Trivial FFA driver cleanups in preparation for v1.1 support
   - Export the kernel_neon_* APIs as GPL symbols
   - Harden our instruction generation routines against instrumentation
   - A bunch of robustness improvements to our arch-specific selftests
   - Minor cleanups and fixes all over (kbuild, kprobes, kfence, PMU, ...)"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (151 commits)
  arm64: kprobes: Return DBG_HOOK_ERROR if kprobes can not handle a BRK
  arm64: kprobes: Let arch do_page_fault() fix up page fault in user handler
  arm64: Prohibit instrumentation on arch_stack_walk()
  arm64:uprobe fix the uprobe SWBP_INSN in big-endian
  arm64: alternatives: add __init/__initconst to some functions/variables
  arm_pmu: Drop redundant armpmu->map_event() in armpmu_event_init()
  kselftest/arm64: Allow epoll_wait() to return more than one result
  kselftest/arm64: Don't drain output while spawning children
  kselftest/arm64: Hold fp-stress children until they're all spawned
  arm64/sysreg: Remove duplicate definitions from asm/sysreg.h
  arm64/sysreg: Convert ID_DFR1_EL1 to automatic generation
  arm64/sysreg: Convert ID_DFR0_EL1 to automatic generation
  arm64/sysreg: Convert ID_AFR0_EL1 to automatic generation
  arm64/sysreg: Convert ID_MMFR5_EL1 to automatic generation
  arm64/sysreg: Convert MVFR2_EL1 to automatic generation
  arm64/sysreg: Convert MVFR1_EL1 to automatic generation
  arm64/sysreg: Convert MVFR0_EL1 to automatic generation
  arm64/sysreg: Convert ID_PFR2_EL1 to automatic generation
  arm64/sysreg: Convert ID_PFR1_EL1 to automatic generation
  arm64/sysreg: Convert ID_PFR0_EL1 to automatic generation
  ...

27 files changed, 348 insertions, 278 deletions

diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h
index 3622e9f4fb44..bdf1f6bcd010 100644
--- a/arch/arm64/include/asm/alternative-macros.h
+++ b/arch/arm64/include/asm/alternative-macros.h
@@ -224,7 +224,7 @@ alternative_endif
 #include <linux/types.h>
 
 static __always_inline bool
-alternative_has_feature_likely(unsigned long feature)
+alternative_has_feature_likely(const unsigned long feature)
 {
 	compiletime_assert(feature < ARM64_NCAPS,
 			   "feature must be < ARM64_NCAPS");
@@ -242,7 +242,7 @@ l_no:
 }
 
 static __always_inline bool
-alternative_has_feature_unlikely(unsigned long feature)
+alternative_has_feature_unlikely(const unsigned long feature)
 {
 	compiletime_assert(feature < ARM64_NCAPS,
 			   "feature must be < ARM64_NCAPS");
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index e5957a53be39..376a980f2bad 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -34,11 +34,6 @@
 	wx\n	.req	w\n
 	.endr
 
-	.macro save_and_disable_daif, flags
-	mrs	\flags, daif
-	msr	daifset, #0xf
-	.endm
-
 	.macro disable_daif
 	msr	daifset, #0xf
 	.endm
@@ -47,15 +42,6 @@
 	msr	daifclr, #0xf
 	.endm
 
-	.macro	restore_daif, flags:req
-	msr	daif, \flags
-	.endm
-
-	/* IRQ/FIQ are the lowest priority flags, unconditionally unmask the rest. */
-	.macro enable_da
-	msr	daifclr, #(8 | 4)
-	.endm
-
 /*
  * Save/restore interrupts.
  */
@@ -620,17 +606,6 @@ alternative_endif
 	.endm
 
 /*
- * Perform the reverse of offset_ttbr1.
- * bic is used as it can cover the immediate value and, in future, won't need
- * to be nop'ed out when dealing with 52-bit kernel VAs.
- */
-	.macro	restore_ttbr1, ttbr
-#ifdef CONFIG_ARM64_VA_BITS_52
-	bic	\ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET
-#endif
-	.endm
-
-/*
  * Arrange a physical address in a TTBR register, taking care of 52-bit
  * addresses.
  *
@@ -660,12 +635,10 @@ alternative_endif
 	.endm
 
 	.macro	pte_to_phys, phys, pte
-#ifdef CONFIG_ARM64_PA_BITS_52
-	ubfiz	\phys, \pte, #(48 - 16 - 12), #16
-	bfxil	\phys, \pte, #16, #32
-	lsl	\phys, \phys, #16
-#else
 	and	\phys, \pte, #PTE_ADDR_MASK
+#ifdef CONFIG_ARM64_PA_BITS_52
+	orr	\phys, \phys, \phys, lsl #PTE_ADDR_HIGH_SHIFT
+	and	\phys, \phys, GENMASK_ULL(PHYS_MASK_SHIFT - 1, PAGE_SHIFT)
 #endif
 	.endm
 
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index f73f11b55042..03d1c9d7af82 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -832,7 +832,8 @@ static inline bool system_supports_tlb_range(void)
 		cpus_have_const_cap(ARM64_HAS_TLB_RANGE);
 }
 
-extern int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
+int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
+bool try_emulate_mrs(struct pt_regs *regs, u32 isn);
 
 static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange)
 {
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 65e53ef5a396..4e8b66c74ea2 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -80,6 +80,7 @@
 #define ARM_CPU_PART_CORTEX_X1		0xD44
 #define ARM_CPU_PART_CORTEX_A510	0xD46
 #define ARM_CPU_PART_CORTEX_A710	0xD47
+#define ARM_CPU_PART_CORTEX_A715	0xD4D
 #define ARM_CPU_PART_CORTEX_X2		0xD48
 #define ARM_CPU_PART_NEOVERSE_N2	0xD49
 #define ARM_CPU_PART_CORTEX_A78C	0xD4B
@@ -142,6 +143,7 @@
 #define MIDR_CORTEX_X1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
 #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
 #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
+#define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715)
 #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2)
 #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2)
 #define MIDR_CORTEX_A78C	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C)
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index 19713d0f013b..92963f98afec 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -58,7 +58,8 @@ asmlinkage void call_on_irq_stack(struct pt_regs *regs,
 asmlinkage void asm_exit_to_user_mode(struct pt_regs *regs);
 
 void do_mem_abort(unsigned long far, unsigned long esr, struct pt_regs *regs);
-void do_undefinstr(struct pt_regs *regs, unsigned long esr);
+void do_el0_undef(struct pt_regs *regs, unsigned long esr);
+void do_el1_undef(struct pt_regs *regs, unsigned long esr);
 void do_el0_bti(struct pt_regs *regs);
 void do_el1_bti(struct pt_regs *regs, unsigned long esr);
 void do_debug_exception(unsigned long addr_if_watchpoint, unsigned long esr,
@@ -67,10 +68,10 @@ void do_fpsimd_acc(unsigned long esr, struct pt_regs *regs);
 void do_sve_acc(unsigned long esr, struct pt_regs *regs);
 void do_sme_acc(unsigned long esr, struct pt_regs *regs);
 void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs);
-void do_sysinstr(unsigned long esr, struct pt_regs *regs);
+void do_el0_sys(unsigned long esr, struct pt_regs *regs);
 void do_sp_pc_abort(unsigned long addr, unsigned long esr, struct pt_regs *regs);
 void bad_el0_sync(struct pt_regs *regs, int reason, unsigned long esr);
-void do_cp15instr(unsigned long esr, struct pt_regs *regs);
+void do_el0_cp15(unsigned long esr, struct pt_regs *regs);
 int do_compat_alignment_fixup(unsigned long addr, struct pt_regs *regs);
 void do_el0_svc(struct pt_regs *regs);
 void do_el0_svc_compat(struct pt_regs *regs);
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 6f86b7ab6c28..e6fa1e2982c8 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -56,11 +56,20 @@ 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;
+	void *sve_state;
+	void *za_state;
+	u64 *svcr;
+	unsigned int sve_vl;
+	unsigned int sme_vl;
+	enum fp_type *fp_type;
+	enum fp_type to_save;
+};
 
-extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
-				     void *sve_state, unsigned int sve_vl,
-				     void *za_state, unsigned int sme_vl,
-				     u64 *svcr);
+extern void fpsimd_bind_state_to_cpu(struct cpu_fp_state *fp_state);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
 extern void fpsimd_save_and_flush_cpu_state(void);
diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h
index 329dbbd4d50b..5664729800ae 100644
--- a/arch/arm64/include/asm/ftrace.h
+++ b/arch/arm64/include/asm/ftrace.h
@@ -23,7 +23,7 @@
  */
 #define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
 
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
 #define ARCH_SUPPORTS_FTRACE_OPS 1
 #else
 #define MCOUNT_ADDR		((unsigned long)_mcount)
@@ -33,8 +33,7 @@
 #define MCOUNT_INSN_SIZE	AARCH64_INSN_SIZE
 
 #define FTRACE_PLT_IDX		0
-#define FTRACE_REGS_PLT_IDX	1
-#define NR_FTRACE_PLTS		2
+#define NR_FTRACE_PLTS		1
 
 /*
  * Currently, gcc tends to save the link register after the local variables
@@ -69,7 +68,7 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 	 * Adjust addr to point at the BL in the callsite.
 	 * See ftrace_init_nop() for the callsite sequence.
 	 */
-	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS))
 		return addr + AARCH64_INSN_SIZE;
 	/*
 	 * addr is the address of the mcount call instruction.
@@ -78,10 +77,71 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 	return addr;
 }
 
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
 struct dyn_ftrace;
 struct ftrace_ops;
-struct ftrace_regs;
+
+#define arch_ftrace_get_regs(regs) NULL
+
+struct ftrace_regs {
+	/* x0 - x8 */
+	unsigned long regs[9];
+	unsigned long __unused;
+
+	unsigned long fp;
+	unsigned long lr;
+
+	unsigned long sp;
+	unsigned long pc;
+};
+
+static __always_inline unsigned long
+ftrace_regs_get_instruction_pointer(const struct ftrace_regs *fregs)
+{
+	return fregs->pc;
+}
+
+static __always_inline void
+ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
+				    unsigned long pc)
+{
+	fregs->pc = pc;
+}
+
+static __always_inline unsigned long
+ftrace_regs_get_stack_pointer(const struct ftrace_regs *fregs)
+{
+	return fregs->sp;
+}
+
+static __always_inline unsigned long
+ftrace_regs_get_argument(struct ftrace_regs *fregs, unsigned int n)
+{
+	if (n < 8)
+		return fregs->regs[n];
+	return 0;
+}
+
+static __always_inline unsigned long
+ftrace_regs_get_return_value(const struct ftrace_regs *fregs)
+{
+	return fregs->regs[0];
+}
+
+static __always_inline void
+ftrace_regs_set_return_value(struct ftrace_regs *fregs,
+			     unsigned long ret)
+{
+	fregs->regs[0] = ret;
+}
+
+static __always_inline void
+ftrace_override_function_with_return(struct ftrace_regs *fregs)
+{
+	fregs->pc = fregs->lr;
+}
+
+int ftrace_regs_query_register_offset(const char *name);
 
 int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
 #define ftrace_init_nop ftrace_init_nop
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index d20f5da2d76f..6a4a1ab8eb23 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -49,6 +49,15 @@ extern pte_t huge_ptep_get(pte_t *ptep);
 
 void __init arm64_hugetlb_cma_reserve(void);
 
+#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
+extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep);
+
+#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
+extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep,
+					 pte_t old_pte, pte_t new_pte);
+
 #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 298b386d3ebe..06dd12c514e6 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -120,6 +120,9 @@
 #define KERNEL_HWCAP_WFXT		__khwcap2_feature(WFXT)
 #define KERNEL_HWCAP_EBF16		__khwcap2_feature(EBF16)
 #define KERNEL_HWCAP_SVE_EBF16		__khwcap2_feature(SVE_EBF16)
+#define KERNEL_HWCAP_CSSC		__khwcap2_feature(CSSC)
+#define KERNEL_HWCAP_RPRFM		__khwcap2_feature(RPRFM)
+#define KERNEL_HWCAP_SVE2P1		__khwcap2_feature(SVE2P1)
 
 /*
  * This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 834bff720582..aaf1f52fbf3e 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -13,31 +13,6 @@
 #include <asm/insn-def.h>
 
 #ifndef __ASSEMBLY__
-/*
- * ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a
- * Section C3.1 "A64 instruction index by encoding":
- * AArch64 main encoding table
- *  Bit position
- *   28 27 26 25	Encoding Group
- *   0  0  -  -		Unallocated
- *   1  0  0  -		Data processing, immediate
- *   1  0  1  -		Branch, exception generation and system instructions
- *   -  1  -  0		Loads and stores
- *   -  1  0  1		Data processing - register
- *   0  1  1  1		Data processing - SIMD and floating point
- *   1  1  1  1		Data processing - SIMD and floating point
- * "-" means "don't care"
- */
-enum aarch64_insn_encoding_class {
-	AARCH64_INSN_CLS_UNKNOWN,	/* UNALLOCATED */
-	AARCH64_INSN_CLS_SVE,		/* SVE instructions */
-	AARCH64_INSN_CLS_DP_IMM,	/* Data processing - immediate */
-	AARCH64_INSN_CLS_DP_REG,	/* Data processing - register */
-	AARCH64_INSN_CLS_DP_FPSIMD,	/* Data processing - SIMD and FP */
-	AARCH64_INSN_CLS_LDST,		/* Loads and stores */
-	AARCH64_INSN_CLS_BR_SYS,	/* Branch, exception generation and
-					 * system instructions */
-};
 
 enum aarch64_insn_hint_cr_op {
 	AARCH64_INSN_HINT_NOP	= 0x0 << 5,
@@ -326,6 +301,23 @@ static __always_inline u32 aarch64_insn_get_##abbr##_value(void)	\
 	return (val);							\
 }
 
+/*
+ * ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a
+ * Section C3.1 "A64 instruction index by encoding":
+ * AArch64 main encoding table
+ *  Bit position
+ *   28 27 26 25	Encoding Group
+ *   0  0  -  -		Unallocated
+ *   1  0  0  -		Data processing, immediate
+ *   1  0  1  -		Branch, exception generation and system instructions
+ *   -  1  -  0		Loads and stores
+ *   -  1  0  1		Data processing - register
+ *   0  1  1  1		Data processing - SIMD and floating point
+ *   1  1  1  1		Data processing - SIMD and floating point
+ * "-" means "don't care"
+ */
+__AARCH64_INSN_FUNCS(class_branch_sys,	0x1c000000, 0x14000000)
+
 __AARCH64_INSN_FUNCS(adr,	0x9F000000, 0x10000000)
 __AARCH64_INSN_FUNCS(adrp,	0x9F000000, 0x90000000)
 __AARCH64_INSN_FUNCS(prfm,	0x3FC00000, 0x39800000)
@@ -431,58 +423,122 @@ __AARCH64_INSN_FUNCS(pssbb,	0xFFFFFFFF, 0xD503349F)
 
 #undef	__AARCH64_INSN_FUNCS
 
-bool aarch64_insn_is_steppable_hint(u32 insn);
-bool aarch64_insn_is_branch_imm(u32 insn);
+static __always_inline bool aarch64_insn_is_steppable_hint(u32 insn)
+{
+	if (!aarch64_insn_is_hint(insn))
+		return false;
+
+	switch (insn & 0xFE0) {
+	case AARCH64_INSN_HINT_XPACLRI:
+	case AARCH64_INSN_HINT_PACIA_1716:
+	case AARCH64_INSN_HINT_PACIB_1716:
+	case AARCH64_INSN_HINT_PACIAZ:
+	case AARCH64_INSN_HINT_PACIASP:
+	case AARCH64_INSN_HINT_PACIBZ:
+	case AARCH64_INSN_HINT_PACIBSP:
+	case AARCH64_INSN_HINT_BTI:
+	case AARCH64_INSN_HINT_BTIC:
+	case AARCH64_INSN_HINT_BTIJ:
+	case AARCH64_INSN_HINT_BTIJC:
+	case AARCH64_INSN_HINT_NOP:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static __always_inline bool aarch64_insn_is_branch(u32 insn)
+{
+	/* b, bl, cb*, tb*, ret*, b.cond, br*, blr* */
+
+	return aarch64_insn_is_b(insn) ||
+	       aarch64_insn_is_bl(insn) ||
+	       aarch64_insn_is_cbz(insn) ||
+	       aarch64_insn_is_cbnz(insn) ||
+	       aarch64_insn_is_tbz(insn) ||
+	       aarch64_insn_is_tbnz(insn) ||
+	       aarch64_insn_is_ret(insn) ||
+	       aarch64_insn_is_ret_auth(insn) ||
+	       aarch64_insn_is_br(insn) ||
+	       aarch64_insn_is_br_auth(insn) ||
+	       aarch64_insn_is_blr(insn) ||
+	       aarch64_insn_is_blr_auth(insn) ||
+	       aarch64_insn_is_bcond(insn);
+}
 
-static inline bool aarch64_insn_is_adr_adrp(u32 insn)
+static __always_inline bool aarch64_insn_is_branch_imm(u32 insn)
 {
-	return aarch64_insn_is_adr(insn) || aarch64_insn_is_adrp(insn);
+	return aarch64_insn_is_b(insn) ||
+	       aarch64_insn_is_bl(insn) ||
+	       aarch64_insn_is_tbz(insn) ||
+	       aarch64_insn_is_tbnz(insn) ||
+	       aarch64_insn_is_cbz(insn) ||
+	       aarch64_insn_is_cbnz(insn) ||
+	       aarch64_insn_is_bcond(insn);
 }
 
-static inline bool aarch64_insn_is_dsb(u32 insn)
+static __always_inline bool aarch64_insn_is_adr_adrp(u32 insn)
 {
-	return aarch64_insn_is_dsb_base(insn) || aarch64_insn_is_dsb_nxs(insn);
+	return aarch64_insn_is_adr(insn) ||
+	       aarch64_insn_is_adrp(insn);
 }
 
-static inline bool aarch64_insn_is_barrier(u32 insn)
+static __always_inline bool aarch64_insn_is_dsb(u32 insn)
 {
-	return aarch64_insn_is_dmb(insn) || aarch64_insn_is_dsb(insn) ||
-	       aarch64_insn_is_isb(insn) || aarch64_insn_is_sb(insn) ||
-	       aarch64_insn_is_clrex(insn) || aarch64_insn_is_ssbb(insn) ||
+	return aarch64_insn_is_dsb_base(insn) ||
+	       aarch64_insn_is_dsb_nxs(insn);
+}
+
+static __always_inline bool aarch64_insn_is_barrier(u32 insn)
+{
+	return aarch64_insn_is_dmb(insn) ||
+	       aarch64_insn_is_dsb(insn) ||
+	       aarch64_insn_is_isb(insn) ||
+	       aarch64_insn_is_sb(insn) ||
+	       aarch64_insn_is_clrex(insn) ||
+	       aarch64_insn_is_ssbb(insn) ||
 	       aarch64_insn_is_pssbb(insn);
 }
 
-static inline bool aarch64_insn_is_store_single(u32 insn)
+static __always_inline bool aarch64_insn_is_store_single(u32 insn)
 {
 	return aarch64_insn_is_store_imm(insn) ||
 	       aarch64_insn_is_store_pre(insn) ||
 	       aarch64_insn_is_store_post(insn);
 }
 
-static inline bool aarch64_insn_is_store_pair(u32 insn)
+static __always_inline bool aarch64_insn_is_store_pair(u32 insn)
 {
 	return aarch64_insn_is_stp(insn) ||
 	       aarch64_insn_is_stp_pre(insn) ||
 	       aarch64_insn_is_stp_post(insn);
 }
 
-static inline bool aarch64_insn_is_load_single(u32 insn)
+static __always_inline bool aarch64_insn_is_load_single(u32 insn)
 {
 	return aarch64_insn_is_load_imm(insn) ||
 	       aarch64_insn_is_load_pre(insn) ||
 	       aarch64_insn_is_load_post(insn);
 }
 
-static inline bool aarch64_insn_is_load_pair(u32 insn)
+static __always_inline bool aarch64_insn_is_load_pair(u32 insn)
 {
 	return aarch64_insn_is_ldp(insn) ||
 	       aarch64_insn_is_ldp_pre(insn) ||
 	       aarch64_insn_is_ldp_post(insn);
 }
 
+static __always_inline bool aarch64_insn_uses_literal(u32 insn)
+{
+	/* ldr/ldrsw (literal), prfm */
+
+	return aarch64_insn_is_ldr_lit(insn) ||
+	       aarch64_insn_is_ldrsw_lit(insn) ||
+	       aarch64_insn_is_adr_adrp(insn) ||
+	       aarch64_insn_is_prfm_lit(insn);
+}
+
 enum aarch64_insn_encoding_class aarch64_get_insn_class(u32 insn);
-bool aarch64_insn_uses_literal(u32 insn);
-bool aarch64_insn_is_branch(u32 insn);
 u64 aarch64_insn_decode_immediate(enum aarch64_insn_imm_type type, u32 insn);
 u32 aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type,
 				  u32 insn, u64 imm);
@@ -496,8 +552,18 @@ u32 aarch64_insn_gen_comp_branch_imm(unsigned long pc, unsigned long addr,
 				     enum aarch64_insn_branch_type type);
 u32 aarch64_insn_gen_cond_branch_imm(unsigned long pc, unsigned long addr,
 				     enum aarch64_insn_condition cond);
-u32 aarch64_insn_gen_hint(enum aarch64_insn_hint_cr_op op);
-u32 aarch64_insn_gen_nop(void);
+
+static __always_inline u32
+aarch64_insn_gen_hint(enum aarch64_insn_hint_cr_op op)
+{
+	return aarch64_insn_get_hint_value() | op;
+}
+
+static __always_inline u32 aarch64_insn_gen_nop(void)
+{
+	return aarch64_insn_gen_hint(AARCH64_INSN_HINT_NOP);
+}
+
 u32 aarch64_insn_gen_branch_reg(enum aarch64_insn_register reg,
 				enum aarch64_insn_branch_type type);
 u32 aarch64_insn_gen_load_store_reg(enum aarch64_insn_register reg,
@@ -580,10 +646,6 @@ u32 aarch64_insn_gen_extr(enum aarch64_insn_variant variant,
 			  enum aarch64_insn_register Rn,
 			  enum aarch64_insn_register Rd,
 			  u8 lsb);
-u32 aarch64_insn_gen_prefetch(enum aarch64_insn_register base,
-			      enum aarch64_insn_prfm_type type,
-			      enum aarch64_insn_prfm_target target,
-			      enum aarch64_insn_prfm_policy policy);
 #ifdef CONFIG_ARM64_LSE_ATOMICS
 u32 aarch64_insn_gen_atomic_ld_op(enum aarch64_insn_register result,
 				  enum aarch64_insn_register address,
diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
index cea441b6aa5d..48ddc0f45d22 100644
--- a/arch/arm64/include/asm/jump_label.h
+++ b/arch/arm64/include/asm/jump_label.h
@@ -15,8 +15,8 @@
 
 #define JUMP_LABEL_NOP_SIZE		AARCH64_INSN_SIZE
 
-static __always_inline bool arch_static_branch(struct static_key *key,
-					       bool branch)
+static __always_inline bool arch_static_branch(struct static_key * const key,
+					       const bool branch)
 {
 	asm_volatile_goto(
 		"1:	nop					\n\t"
@@ -32,8 +32,8 @@ l_yes:
 	return true;
 }
 
-static __always_inline bool arch_static_branch_jump(struct static_key *key,
-						    bool branch)
+static __always_inline bool arch_static_branch_jump(struct static_key * const key,
+						    const bool branch)
 {
 	asm_volatile_goto(
 		"1:	b		%l[l_yes]		\n\t"
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index 32d14f481f0c..fcd14197756f 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -18,11 +18,6 @@
  * with 4K (section size = 2M) but not with 16K (section size = 32M) or
  * 64K (section size = 512M).
  */
-#ifdef CONFIG_ARM64_4K_PAGES
-#define ARM64_KERNEL_USES_PMD_MAPS 1
-#else
-#define ARM64_KERNEL_USES_PMD_MAPS 0
-#endif
 
 /*
  * The idmap and swapper page tables need some space reserved in the kernel
@@ -34,7 +29,7 @@
  * VA range, so pages required to map highest possible PA are reserved in all
  * cases.
  */
-#if ARM64_KERNEL_USES_PMD_MAPS
+#ifdef CONFIG_ARM64_4K_PAGES
 #define SWAPPER_PGTABLE_LEVELS	(CONFIG_PGTABLE_LEVELS - 1)
 #else
 #define SWAPPER_PGTABLE_LEVELS	(CONFIG_PGTABLE_LEVELS)
@@ -96,7 +91,7 @@
 #define INIT_IDMAP_DIR_PAGES	EARLY_PAGES(KIMAGE_VADDR, _end + MAX_FDT_SIZE + SWAPPER_BLOCK_SIZE, 1)
 
 /* Initial memory map size */
-#if ARM64_KERNEL_USES_PMD_MAPS
+#ifdef CONFIG_ARM64_4K_PAGES
 #define SWAPPER_BLOCK_SHIFT	PMD_SHIFT
 #define SWAPPER_BLOCK_SIZE	PMD_SIZE
 #define SWAPPER_TABLE_SHIFT	PUD_SHIFT
@@ -112,7 +107,7 @@
 #define SWAPPER_PTE_FLAGS	(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
 #define SWAPPER_PMD_FLAGS	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
 
-#if ARM64_KERNEL_USES_PMD_MAPS
+#ifdef CONFIG_ARM64_4K_PAGES
 #define SWAPPER_RW_MMUFLAGS	(PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS)
 #define SWAPPER_RX_MMUFLAGS	(SWAPPER_RW_MMUFLAGS | PMD_SECT_RDONLY)
 #else
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 45e2136322ba..fd34ab155d0b 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -306,8 +306,18 @@ struct vcpu_reset_state {
 struct kvm_vcpu_arch {
 	struct kvm_cpu_context ctxt;
 
-	/* Guest floating point state */
+	/*
+	 * Guest floating point state
+	 *
+	 * The architecture has two main floating point extensions,
+	 * the original FPSIMD and SVE.  These have overlapping
+	 * register views, with the FPSIMD V registers occupying the
+	 * low 128 bits of the SVE Z registers.  When the core
+	 * floating point code saves the register state of a task it
+	 * records which view it saved in fp_type.
+	 */
 	void *sve_state;
+	enum fp_type fp_type;
 	unsigned int sve_max_vl;
 	u64 svcr;
 
diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h
index c503db8e73b0..f99d74826a7e 100644
--- a/arch/arm64/include/asm/lse.h
+++ b/arch/arm64/include/asm/lse.h
@@ -10,7 +10,6 @@
 
 #include <linux/compiler_types.h>
 #include <linux/export.h>
-#include <linux/jump_label.h>
 #include <linux/stringify.h>
 #include <asm/alternative.h>
 #include <asm/alternative-macros.h>
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index d3f8b5df0c1f..72dbd6400549 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -18,6 +18,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
+#include <asm/daifflags.h>
 #include <asm/proc-fns.h>
 #include <asm-generic/mm_hooks.h>
 #include <asm/cputype.h>
@@ -152,6 +153,7 @@ static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
 	typedef void (ttbr_replace_func)(phys_addr_t);
 	extern ttbr_replace_func idmap_cpu_replace_ttbr1;
 	ttbr_replace_func *replace_phys;
+	unsigned long daif;
 
 	/* phys_to_ttbr() zeros lower 2 bits of ttbr with 52-bit PA */
 	phys_addr_t ttbr1 = phys_to_ttbr(virt_to_phys(pgdp));
@@ -171,7 +173,15 @@ static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
 	replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
 
 	__cpu_install_idmap(idmap);
+
+	/*
+	 * We really don't want to take *any* exceptions while TTBR1 is
+	 * in the process of being replaced so mask everything.
+	 */
+	daif = local_daif_save();
 	replace_phys(ttbr1);
+	local_daif_restore(daif);
+
 	cpu_uninstall_idmap();
 }
 
diff --git a/arch/arm64/include/asm/module.lds.h b/arch/arm64/include/asm/module.lds.h
index 094701ec5500..dbba4b7559aa 100644
--- a/arch/arm64/include/asm/module.lds.h
+++ b/arch/arm64/include/asm/module.lds.h
@@ -17,4 +17,12 @@ SECTIONS {
 	 */
 	.text.hot : { *(.text.hot) }
 #endif
+
+#ifdef CONFIG_UNWIND_TABLES
+	/*
+	 * Currently, we only use unwind info at module load time, so we can
+	 * put it into the .init allocation.
+	 */
+	.init.eh_frame : { *(.eh_frame) }
+#endif
 }
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 5ab8d163198f..f658aafc47df 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -159,6 +159,7 @@
 #ifdef CONFIG_ARM64_PA_BITS_52
 #define PTE_ADDR_HIGH		(_AT(pteval_t, 0xf) << 12)
 #define PTE_ADDR_MASK		(PTE_ADDR_LOW | PTE_ADDR_HIGH)
+#define PTE_ADDR_HIGH_SHIFT	36
 #else
 #define PTE_ADDR_MASK		PTE_ADDR_LOW
 #endif
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index edf6625ce965..c36d56dbf940 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -77,11 +77,11 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 static inline phys_addr_t __pte_to_phys(pte_t pte)
 {
 	return (pte_val(pte) & PTE_ADDR_LOW) |
-		((pte_val(pte) & PTE_ADDR_HIGH) << 36);
+		((pte_val(pte) & PTE_ADDR_HIGH) << PTE_ADDR_HIGH_SHIFT);
 }
 static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
 {
-	return (phys | (phys >> 36)) & PTE_ADDR_MASK;
+	return (phys | (phys >> PTE_ADDR_HIGH_SHIFT)) & PTE_ADDR_MASK;
 }
 #else
 #define __pte_to_phys(pte)	(pte_val(pte) & PTE_ADDR_MASK)
@@ -609,7 +609,6 @@ extern pgd_t init_pg_dir[PTRS_PER_PGD];
 extern pgd_t init_pg_end[];
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
-extern pgd_t idmap_pg_end[];
 extern pgd_t tramp_pg_dir[PTRS_PER_PGD];
 extern pgd_t reserved_pg_dir[PTRS_PER_PGD];
 
@@ -1096,6 +1095,15 @@ static inline bool pud_sect_supported(void)
 }
 
 
+#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
+#define ptep_modify_prot_start ptep_modify_prot_start
+extern pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep);
+
+#define ptep_modify_prot_commit ptep_modify_prot_commit
+extern void ptep_modify_prot_commit(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep,
+				    pte_t old_pte, pte_t new_pte);
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_PGTABLE_H */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 445aa3af3b76..d51b32a69309 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -122,6 +122,12 @@ enum vec_type {
 	ARM64_VEC_MAX,
 };
 
+enum fp_type {
+	FP_STATE_CURRENT,	/* Save based on current task state. */
+	FP_STATE_FPSIMD,
+	FP_STATE_SVE,
+};
+
 struct cpu_context {
 	unsigned long x19;
 	unsigned long x20;
@@ -152,6 +158,7 @@ struct thread_struct {
 		struct user_fpsimd_state fpsimd_state;
 	} uw;
 
+	enum fp_type		fp_type;	/* registers FPSIMD or SVE? */
 	unsigned int		fpsimd_cpu;
 	void			*sve_state;	/* SVE registers, if any */
 	void			*za_state;	/* ZA register, if any */
@@ -308,13 +315,13 @@ static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc,
 }
 #endif
 
-static inline bool is_ttbr0_addr(unsigned long addr)
+static __always_inline bool is_ttbr0_addr(unsigned long addr)
 {
 	/* entry assembly clears tags for TTBR0 addrs */
 	return addr < TASK_SIZE;
 }
 
-static inline bool is_ttbr1_addr(unsigned long addr)
+static __always_inline bool is_ttbr1_addr(unsigned long addr)
 {
 	/* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */
 	return arch_kasan_reset_tag(addr) >= PAGE_OFFSET;
@@ -396,18 +403,5 @@ long get_tagged_addr_ctrl(struct task_struct *task);
 #define GET_TAGGED_ADDR_CTRL()		get_tagged_addr_ctrl(current)
 #endif
 
-/*
- * For CONFIG_GCC_PLUGIN_STACKLEAK
- *
- * These need to be macros because otherwise we get stuck in a nightmare
- * of header definitions for the use of task_stack_page.
- */
-
-/*
- * The top of the current task's task stack
- */
-#define current_top_of_stack()	((unsigned long)current->stack + THREAD_SIZE)
-#define on_thread_stack()	(on_task_stack(current, current_stack_pointer, 1))
-
 #endif /* __ASSEMBLY__ */
 #endif /* __ASM_PROCESSOR_H */
diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h
index 8297bccf0784..ff7da1268a52 100644
--- a/arch/arm64/include/asm/scs.h
+++ b/arch/arm64/include/asm/scs.h
@@ -5,6 +5,7 @@
 #ifdef __ASSEMBLY__
 
 #include <asm/asm-offsets.h>
+#include <asm/sysreg.h>
 
 #ifdef CONFIG_SHADOW_CALL_STACK
 	scs_sp	.req	x18
@@ -24,6 +25,54 @@
 	.endm
 #endif /* CONFIG_SHADOW_CALL_STACK */
 
+
+#else
+
+#include <linux/scs.h>
+#include <asm/cpufeature.h>
+
+#ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS
+static inline bool should_patch_pac_into_scs(void)
+{
+	u64 reg;
+
+	/*
+	 * We only enable the shadow call stack dynamically if we are running
+	 * on a system that does not implement PAC or BTI. PAC and SCS provide
+	 * roughly the same level of protection, and BTI relies on the PACIASP
+	 * instructions serving as landing pads, preventing us from patching
+	 * those instructions into something else.
+	 */
+	reg = read_sysreg_s(SYS_ID_AA64ISAR1_EL1);
+	if (SYS_FIELD_GET(ID_AA64ISAR1_EL1, APA, reg) |
+	    SYS_FIELD_GET(ID_AA64ISAR1_EL1, API, reg))
+		return false;
+
+	reg = read_sysreg_s(SYS_ID_AA64ISAR2_EL1);
+	if (SYS_FIELD_GET(ID_AA64ISAR2_EL1, APA3, reg))
+		return false;
+
+	if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) {
+		reg = read_sysreg_s(SYS_ID_AA64PFR1_EL1);
+		if (reg & (0xf << ID_AA64PFR1_EL1_BT_SHIFT))
+			return false;
+	}
+	return true;
+}
+
+static inline void dynamic_scs_init(void)
+{
+	if (should_patch_pac_into_scs()) {
+		pr_info("Enabling dynamic shadow call stack\n");
+		static_branch_enable(&dynamic_scs_enabled);
+	}
+}
+#else
+static inline void dynamic_scs_init(void) {}
+#endif
+
+int scs_patch(const u8 eh_frame[], int size);
+
 #endif /* __ASSEMBLY __ */
 
 #endif /* _ASM_SCS_H */
diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h
index aa3d3607d5c8..db7b371b367c 100644
--- a/arch/arm64/include/asm/spectre.h
+++ b/arch/arm64/include/asm/spectre.h
@@ -26,6 +26,7 @@ enum mitigation_state {
 	SPECTRE_VULNERABLE,
 };
 
+struct pt_regs;
 struct task_struct;
 
 /*
@@ -98,5 +99,6 @@ 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);
 #endif	/* __ASSEMBLY__ */
 #endif	/* __ASM_SPECTRE_H */
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 5a0edb064ea4..4e5354beafb0 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -57,6 +57,8 @@ static inline bool on_task_stack(const struct task_struct *tsk,
 	return stackinfo_on_stack(&info, sp, size);
 }
 
+#define on_thread_stack()	(on_task_stack(current, current_stack_pointer, 1))
+
 #ifdef CONFIG_VMAP_STACK
 DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack);
 
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 7d301700d1a9..1312fb48f18b 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -90,20 +90,24 @@
  */
 #define pstate_field(op1, op2)		((op1) << Op1_shift | (op2) << Op2_shift)
 #define PSTATE_Imm_shift		CRm_shift
+#define SET_PSTATE(x, r)		__emit_inst(0xd500401f | PSTATE_ ## r | ((!!x) << PSTATE_Imm_shift))
 
 #define PSTATE_PAN			pstate_field(0, 4)
 #define PSTATE_UAO			pstate_field(0, 3)
 #define PSTATE_SSBS			pstate_field(3, 1)
+#define PSTATE_DIT			pstate_field(3, 2)
 #define PSTATE_TCO			pstate_field(3, 4)
 
-#define SET_PSTATE_PAN(x)		__emit_inst(0xd500401f | PSTATE_PAN | ((!!x) << PSTATE_Imm_shift))
-#define SET_PSTATE_UAO(x)		__emit_inst(0xd500401f | PSTATE_UAO | ((!!x) << PSTATE_Imm_shift))
-#define SET_PSTATE_SSBS(x)		__emit_inst(0xd500401f | PSTATE_SSBS | ((!!x) << PSTATE_Imm_shift))
-#define SET_PSTATE_TCO(x)		__emit_inst(0xd500401f | PSTATE_TCO | ((!!x) << PSTATE_Imm_shift))
+#define SET_PSTATE_PAN(x)		SET_PSTATE((x), PAN)
+#define SET_PSTATE_UAO(x)		SET_PSTATE((x), UAO)
+#define SET_PSTATE_SSBS(x)		SET_PSTATE((x), SSBS)
+#define SET_PSTATE_DIT(x)		SET_PSTATE((x), DIT)
+#define SET_PSTATE_TCO(x)		SET_PSTATE((x), TCO)
 
 #define set_pstate_pan(x)		asm volatile(SET_PSTATE_PAN(x))
 #define set_pstate_uao(x)		asm volatile(SET_PSTATE_UAO(x))
 #define set_pstate_ssbs(x)		asm volatile(SET_PSTATE_SSBS(x))
+#define set_pstate_dit(x)		asm volatile(SET_PSTATE_DIT(x))
 
 #define __SYS_BARRIER_INSN(CRm, op2, Rt) \
 	__emit_inst(0xd5000000 | sys_insn(0, 3, 3, (CRm), (op2)) | ((Rt) & 0x1f))
@@ -165,31 +169,6 @@
 #define SYS_MPIDR_EL1			sys_reg(3, 0, 0, 0, 5)
 #define SYS_REVIDR_EL1			sys_reg(3, 0, 0, 0, 6)
 
-#define SYS_ID_PFR0_EL1			sys_reg(3, 0, 0, 1, 0)
-#define SYS_ID_PFR1_EL1			sys_reg(3, 0, 0, 1, 1)
-#define SYS_ID_PFR2_EL1			sys_reg(3, 0, 0, 3, 4)
-#define SYS_ID_DFR0_EL1			sys_reg(3, 0, 0, 1, 2)
-#define SYS_ID_DFR1_EL1			sys_reg(3, 0, 0, 3, 5)
-#define SYS_ID_AFR0_EL1			sys_reg(3, 0, 0, 1, 3)
-#define SYS_ID_MMFR0_EL1		sys_reg(3, 0, 0, 1, 4)
-#define SYS_ID_MMFR1_EL1		sys_reg(3, 0, 0, 1, 5)
-#define SYS_ID_MMFR2_EL1		sys_reg(3, 0, 0, 1, 6)
-#define SYS_ID_MMFR3_EL1		sys_reg(3, 0, 0, 1, 7)
-#define SYS_ID_MMFR4_EL1		sys_reg(3, 0, 0, 2, 6)
-#define SYS_ID_MMFR5_EL1		sys_reg(3, 0, 0, 3, 6)
-
-#define SYS_ID_ISAR0_EL1		sys_reg(3, 0, 0, 2, 0)
-#define SYS_ID_ISAR1_EL1		sys_reg(3, 0, 0, 2, 1)
-#define SYS_ID_ISAR2_EL1		sys_reg(3, 0, 0, 2, 2)
-#define SYS_ID_ISAR3_EL1		sys_reg(3, 0, 0, 2, 3)
-#define SYS_ID_ISAR4_EL1		sys_reg(3, 0, 0, 2, 4)
-#define SYS_ID_ISAR5_EL1		sys_reg(3, 0, 0, 2, 5)
-#define SYS_ID_ISAR6_EL1		sys_reg(3, 0, 0, 2, 7)
-
-#define SYS_MVFR0_EL1			sys_reg(3, 0, 0, 3, 0)
-#define SYS_MVFR1_EL1			sys_reg(3, 0, 0, 3, 1)
-#define SYS_MVFR2_EL1			sys_reg(3, 0, 0, 3, 2)
-
 #define SYS_ACTLR_EL1			sys_reg(3, 0, 1, 0, 1)
 #define SYS_RGSR_EL1			sys_reg(3, 0, 1, 0, 5)
 #define SYS_GCR_EL1			sys_reg(3, 0, 1, 0, 6)
@@ -692,112 +671,6 @@
 #define ID_AA64MMFR0_EL1_PARANGE_MAX	ID_AA64MMFR0_EL1_PARANGE_48
 #endif
 
-#define ID_DFR0_PERFMON_SHIFT		24
-
-#define ID_DFR0_PERFMON_8_0		0x3
-#define ID_DFR0_PERFMON_8_1		0x4
-#define ID_DFR0_PERFMON_8_4		0x5
-#define ID_DFR0_PERFMON_8_5		0x6
-
-#define ID_ISAR4_SWP_FRAC_SHIFT		28
-#define ID_ISAR4_PSR_M_SHIFT		24
-#define ID_ISAR4_SYNCH_PRIM_FRAC_SHIFT	20
-#define ID_ISAR4_BARRIER_SHIFT		16
-#define ID_ISAR4_SMC_SHIFT		12
-#define ID_ISAR4_WRITEBACK_SHIFT	8
-#define ID_ISAR4_WITHSHIFTS_SHIFT	4
-#define ID_ISAR4_UNPRIV_SHIFT		0
-
-#define ID_DFR1_MTPMU_SHIFT		0
-
-#define ID_ISAR0_DIVIDE_SHIFT		24
-#define ID_ISAR0_DEBUG_SHIFT		20
-#define ID_ISAR0_COPROC_SHIFT		16
-#define ID_ISAR0_CMPBRANCH_SHIFT	12
-#define ID_ISAR0_BITFIELD_SHIFT		8
-#define ID_ISAR0_BITCOUNT_SHIFT		4
-#define ID_ISAR0_SWAP_SHIFT		0
-
-#define ID_ISAR5_RDM_SHIFT		24
-#define ID_ISAR5_CRC32_SHIFT		16
-#define ID_ISAR5_SHA2_SHIFT		12
-#define ID_ISAR5_SHA1_SHIFT		8
-#define ID_ISAR5_AES_SHIFT		4
-#define ID_ISAR5_SEVL_SHIFT		0
-
-#define ID_ISAR6_I8MM_SHIFT		24
-#define ID_ISAR6_BF16_SHIFT		20
-#define ID_ISAR6_SPECRES_SHIFT		16
-#define ID_ISAR6_SB_SHIFT		12
-#define ID_ISAR6_FHM_SHIFT		8
-#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
-
-#define MVFR0_FPROUND_SHIFT		28
-#define MVFR0_FPSHVEC_SHIFT		24
-#define MVFR0_FPSQRT_SHIFT		20
-#define MVFR0_FPDIVIDE_SHIFT		16
-#define MVFR0_FPTRAP_SHIFT		12
-#define MVFR0_FPDP_SHIFT		8
-#define MVFR0_FPSP_SHIFT		4
-#define MVFR0_SIMD_SHIFT		0
-
-#define MVFR1_SIMDFMAC_SHIFT		28
-#define MVFR1_FPHP_SHIFT		24
-#define MVFR1_SIMDHP_SHIFT		20
-#define MVFR1_SIMDSP_SHIFT		16
-#define MVFR1_SIMDINT_SHIFT		12
-#define MVFR1_SIMDLS_SHIFT		8
-#define MVFR1_FPDNAN_SHIFT		4
-#define MVFR1_FPFTZ_SHIFT		0
-
-#define ID_PFR1_GIC_SHIFT		28
-#define ID_PFR1_VIRT_FRAC_SHIFT		24
-#define ID_PFR1_SEC_FRAC_SHIFT		20
-#define ID_PFR1_GENTIMER_SHIFT		16
-#define ID_PFR1_VIRTUALIZATION_SHIFT	12
-#define ID_PFR1_MPROGMOD_SHIFT		8
-#define ID_PFR1_SECURITY_SHIFT		4
-#define ID_PFR1_PROGMOD_SHIFT		0
-
 #if defined(CONFIG_ARM64_4K_PAGES)
 #define ID_AA64MMFR0_EL1_TGRAN_SHIFT		ID_AA64MMFR0_EL1_TGRAN4_SHIFT
 #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN	ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN
@@ -815,9 +688,6 @@
 #define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT		ID_AA64MMFR0_EL1_TGRAN64_2_SHIFT
 #endif
 
-#define MVFR2_FPMISC_SHIFT		4
-#define MVFR2_SIMDMISC_SHIFT		0
-
 #define CPACR_EL1_FPEN_EL1EN	(BIT(20)) /* enable EL1 access */
 #define CPACR_EL1_FPEN_EL0EN	(BIT(21)) /* enable EL0 access, if EL1EN set */
 
@@ -851,10 +721,6 @@
 #define SYS_RGSR_EL1_SEED_SHIFT	8
 #define SYS_RGSR_EL1_SEED_MASK	0xffffUL
 
-/* GMID_EL1 field definitions */
-#define GMID_EL1_BS_SHIFT	0
-#define GMID_EL1_BS_SIZE	4
-
 /* TFSR{,E0}_EL1 bit definitions */
 #define SYS_TFSR_EL1_TF0_SHIFT	0
 #define SYS_TFSR_EL1_TF1_SHIFT	1
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index 6e5826470bea..1f361e2da516 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -13,17 +13,16 @@
 
 struct pt_regs;
 
-struct undef_hook {
-	struct list_head node;
-	u32 instr_mask;
-	u32 instr_val;
-	u64 pstate_mask;
-	u64 pstate_val;
-	int (*fn)(struct pt_regs *regs, u32 instr);
-};
+#ifdef CONFIG_ARMV8_DEPRECATED
+bool try_emulate_armv8_deprecated(struct pt_regs *regs, u32 insn);
+#else
+static inline bool
+try_emulate_armv8_deprecated(struct pt_regs *regs, u32 insn)
+{
+	return false;
+}
+#endif /* CONFIG_ARMV8_DEPRECATED */
 
-void register_undef_hook(struct undef_hook *hook);
-void unregister_undef_hook(struct undef_hook *hook);
 void force_signal_inject(int signal, int code, unsigned long address, unsigned long err);
 void arm64_notify_segfault(unsigned long addr);
 void arm64_force_sig_fault(int signo, int code, unsigned long far, const char *str);
diff --git a/arch/arm64/include/asm/uprobes.h b/arch/arm64/include/asm/uprobes.h
index 315eef654e39..ba4bff5ca674 100644
--- a/arch/arm64/include/asm/uprobes.h
+++ b/arch/arm64/include/asm/uprobes.h
@@ -12,7 +12,7 @@
 
 #define MAX_UINSN_BYTES		AARCH64_INSN_SIZE
 
-#define UPROBE_SWBP_INSN	BRK64_OPCODE_UPROBES
+#define UPROBE_SWBP_INSN	cpu_to_le32(BRK64_OPCODE_UPROBES)
 #define UPROBE_SWBP_INSN_SIZE	AARCH64_INSN_SIZE
 #define UPROBE_XOL_SLOT_BYTES	MAX_UINSN_BYTES
 
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 9b245da6f507..b713d30544f1 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -93,5 +93,8 @@
 #define HWCAP2_WFXT		(1UL << 31)
 #define HWCAP2_EBF16		(1UL << 32)
 #define HWCAP2_SVE_EBF16	(1UL << 33)
+#define HWCAP2_CSSC		(1UL << 34)
+#define HWCAP2_RPRFM		(1UL << 35)
+#define HWCAP2_SVE2P1		(1UL << 36)
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h
index 4aaf31e3bf16..9525041e4a14 100644
--- a/arch/arm64/include/uapi/asm/sigcontext.h
+++ b/arch/arm64/include/uapi/asm/sigcontext.h
@@ -62,6 +62,10 @@ struct sigcontext {
  * context. Such structures must be placed after the rt_sigframe on the stack
  * and be 16-byte aligned. The last structure must be a dummy one with the
  * magic and size set to 0.
+ *
+ * Note that the values allocated for use as magic should be chosen to
+ * be meaningful in ASCII to aid manual parsing, ZA doesn't follow this
+ * convention due to oversight but it should be observed for future additions.
  */
 struct _aarch64_ctx {
 	__u32 magic;