Merge branch 'for-next/bti' into for-next/core

Support for Branch Target Identification (BTI) in user and kernel
(Mark Brown and others)
* for-next/bti: (39 commits)
  arm64: vdso: Fix CFI directives in sigreturn trampoline
  arm64: vdso: Don't prefix sigreturn trampoline with a BTI C instruction
  arm64: bti: Fix support for userspace only BTI
  arm64: kconfig: Update and comment GCC version check for kernel BTI
  arm64: vdso: Map the vDSO text with guarded pages when built for BTI
  arm64: vdso: Force the vDSO to be linked as BTI when built for BTI
  arm64: vdso: Annotate for BTI
  arm64: asm: Provide a mechanism for generating ELF note for BTI
  arm64: bti: Provide Kconfig for kernel mode BTI
  arm64: mm: Mark executable text as guarded pages
  arm64: bpf: Annotate JITed code for BTI
  arm64: Set GP bit in kernel page tables to enable BTI for the kernel
  arm64: asm: Override SYM_FUNC_START when building the kernel with BTI
  arm64: bti: Support building kernel C code using BTI
  arm64: Document why we enable PAC support for leaf functions
  arm64: insn: Report PAC and BTI instructions as skippable
  arm64: insn: Don't assume unrecognized HINTs are skippable
  arm64: insn: Provide a better name for aarch64_insn_is_nop()
  arm64: insn: Add constants for new HINT instruction decode
  arm64: Disable old style assembly annotations
  ...

53 files changed, 735 insertions, 182 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 8d33d7fed6d8..697e6d80963b 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -9,6 +9,7 @@ config ARM64
 	select ACPI_MCFG if (ACPI && PCI)
 	select ACPI_SPCR_TABLE if ACPI
 	select ACPI_PPTT if ACPI
+	select ARCH_BINFMT_ELF_STATE
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_DMA_PREP_COHERENT
@@ -32,6 +33,7 @@ config ARM64
 	select ARCH_HAS_SYSCALL_WRAPPER
 	select ARCH_HAS_TEARDOWN_DMA_OPS if IOMMU_SUPPORT
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_HAVE_ELF_PROT
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_INLINE_READ_LOCK if !PREEMPTION
 	select ARCH_INLINE_READ_LOCK_BH if !PREEMPTION
@@ -61,8 +63,10 @@ config ARM64
 	select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPTION
 	select ARCH_KEEP_MEMBLOCK
 	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_USE_GNU_PROPERTY
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
+	select ARCH_USE_SYM_ANNOTATIONS
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && (GCC_VERSION >= 50000 || CC_IS_CLANG)
@@ -1584,6 +1588,48 @@ endmenu
 
 menu "ARMv8.5 architectural features"
 
+config ARM64_BTI
+	bool "Branch Target Identification support"
+	default y
+	help
+	  Branch Target Identification (part of the ARMv8.5 Extensions)
+	  provides a mechanism to limit the set of locations to which computed
+	  branch instructions such as BR or BLR can jump.
+
+	  To make use of BTI on CPUs that support it, say Y.
+
+	  BTI is intended to provide complementary protection to other control
+	  flow integrity protection mechanisms, such as the Pointer
+	  authentication mechanism provided as part of the ARMv8.3 Extensions.
+	  For this reason, it does not make sense to enable this option without
+	  also enabling support for pointer authentication.  Thus, when
+	  enabling this option you should also select ARM64_PTR_AUTH=y.
+
+	  Userspace binaries must also be specifically compiled to make use of
+	  this mechanism.  If you say N here or the hardware does not support
+	  BTI, such binaries can still run, but you get no additional
+	  enforcement of branch destinations.
+
+config ARM64_BTI_KERNEL
+	bool "Use Branch Target Identification for kernel"
+	default y
+	depends on ARM64_BTI
+	depends on ARM64_PTR_AUTH
+	depends on CC_HAS_BRANCH_PROT_PAC_RET_BTI
+	# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94697
+	depends on !CC_IS_GCC || GCC_VERSION >= 100100
+	depends on !(CC_IS_CLANG && GCOV_KERNEL)
+	depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS)
+	help
+	  Build the kernel with Branch Target Identification annotations
+	  and enable enforcement of this for kernel code. When this option
+	  is enabled and the system supports BTI all kernel code including
+	  modular code must have BTI enabled.
+
+config CC_HAS_BRANCH_PROT_PAC_RET_BTI
+	# GCC 9 or later, clang 8 or later
+	def_bool $(cc-option,-mbranch-protection=pac-ret+leaf+bti)
+
 config ARM64_E0PD
 	bool "Enable support for E0PD"
 	default y
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index e48867c335d2..7dcd38be7dd0 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -70,7 +70,14 @@ branch-prot-flags-y += $(call cc-option,-mbranch-protection=none)
 
 ifeq ($(CONFIG_ARM64_PTR_AUTH),y)
 branch-prot-flags-$(CONFIG_CC_HAS_SIGN_RETURN_ADDRESS) := -msign-return-address=all
+# We enable additional protection for leaf functions as there is some
+# narrow potential for ROP protection benefits and no substantial
+# performance impact has been observed.
+ifeq ($(CONFIG_ARM64_BTI_KERNEL),y)
+branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET_BTI) := -mbranch-protection=pac-ret+leaf+bti
+else
 branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET) := -mbranch-protection=pac-ret+leaf
+endif
 # -march=armv8.3-a enables the non-nops instructions for PAC, to avoid the
 # compiler to generate them and consequently to break the single image contract
 # we pass it only to the assembler. This option is utilized only in case of non
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 0bff325117b4..54d181177656 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -736,4 +736,54 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
 .Lyield_out_\@ :
 	.endm
 
+/*
+ * This macro emits a program property note section identifying
+ * architecture features which require special handling, mainly for
+ * use in assembly files included in the VDSO.
+ */
+
+#define NT_GNU_PROPERTY_TYPE_0  5
+#define GNU_PROPERTY_AARCH64_FEATURE_1_AND      0xc0000000
+
+#define GNU_PROPERTY_AARCH64_FEATURE_1_BTI      (1U << 0)
+#define GNU_PROPERTY_AARCH64_FEATURE_1_PAC      (1U << 1)
+
+#ifdef CONFIG_ARM64_BTI_KERNEL
+#define GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT		\
+		((GNU_PROPERTY_AARCH64_FEATURE_1_BTI |	\
+		  GNU_PROPERTY_AARCH64_FEATURE_1_PAC))
+#endif
+
+#ifdef GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT
+.macro emit_aarch64_feature_1_and, feat=GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT
+	.pushsection .note.gnu.property, "a"
+	.align  3
+	.long   2f - 1f
+	.long   6f - 3f
+	.long   NT_GNU_PROPERTY_TYPE_0
+1:      .string "GNU"
+2:
+	.align  3
+3:      .long   GNU_PROPERTY_AARCH64_FEATURE_1_AND
+	.long   5f - 4f
+4:
+	/*
+	 * This is described with an array of char in the Linux API
+	 * spec but the text and all other usage (including binutils,
+	 * clang and GCC) treat this as a 32 bit value so no swizzling
+	 * is required for big endian.
+	 */
+	.long   \feat
+5:
+	.align  3
+6:
+	.popsection
+.endm
+
+#else
+.macro emit_aarch64_feature_1_and, feat=0
+.endm
+
+#endif /* GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT */
+
 #endif	/* __ASM_ASSEMBLER_H */
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index c54c674e6c21..eacd0c74dfc7 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -62,7 +62,8 @@
 #define ARM64_HAS_ADDRESS_AUTH			52
 #define ARM64_HAS_GENERIC_AUTH			53
 #define ARM64_HAS_32BIT_EL1			54
+#define ARM64_BTI				55
 
-#define ARM64_NCAPS				55
+#define ARM64_NCAPS				56
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 928814d35669..5d1f4ae42799 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -687,6 +687,11 @@ static inline bool system_has_prio_mask_debugging(void)
 	       system_uses_irq_prio_masking();
 }
 
+static inline bool system_supports_bti(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_BTI) && cpus_have_const_cap(ARM64_BTI);
+}
+
 #define ARM64_BP_HARDEN_UNKNOWN		-1
 #define ARM64_BP_HARDEN_WA_NEEDED	0
 #define ARM64_BP_HARDEN_NOT_REQUIRED	1
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index b618017205a3..4f00d50585a4 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -114,7 +114,11 @@
 
 #ifndef __ASSEMBLY__
 
+#include <uapi/linux/elf.h>
 #include <linux/bug.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/types.h>
 #include <asm/processor.h> /* for signal_minsigstksz, used by ARCH_DLINFO */
 
 typedef unsigned long elf_greg_t;
@@ -224,6 +228,52 @@ extern int aarch32_setup_additional_pages(struct linux_binprm *bprm,
 
 #endif /* CONFIG_COMPAT */
 
+struct arch_elf_state {
+	int flags;
+};
+
+#define ARM64_ELF_BTI		(1 << 0)
+
+#define INIT_ARCH_ELF_STATE {			\
+	.flags = 0,				\
+}
+
+static inline int arch_parse_elf_property(u32 type, const void *data,
+					  size_t datasz, bool compat,
+					  struct arch_elf_state *arch)
+{
+	/* No known properties for AArch32 yet */
+	if (IS_ENABLED(CONFIG_COMPAT) && compat)
+		return 0;
+
+	if (type == GNU_PROPERTY_AARCH64_FEATURE_1_AND) {
+		const u32 *p = data;
+
+		if (datasz != sizeof(*p))
+			return -ENOEXEC;
+
+		if (system_supports_bti() &&
+		    (*p & GNU_PROPERTY_AARCH64_FEATURE_1_BTI))
+			arch->flags |= ARM64_ELF_BTI;
+	}
+
+	return 0;
+}
+
+static inline int arch_elf_pt_proc(void *ehdr, void *phdr,
+				   struct file *f, bool is_interp,
+				   struct arch_elf_state *state)
+{
+	return 0;
+}
+
+static inline int arch_check_elf(void *ehdr, bool has_interp,
+				 void *interp_ehdr,
+				 struct arch_elf_state *state)
+{
+	return 0;
+}
+
 #endif /* !__ASSEMBLY__ */
 
 #endif
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 6a395a7e6707..035003acfa87 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -22,7 +22,7 @@
 #define ESR_ELx_EC_PAC		(0x09)	/* EL2 and above */
 /* Unallocated EC: 0x0A - 0x0B */
 #define ESR_ELx_EC_CP14_64	(0x0C)
-/* Unallocated EC: 0x0d */
+#define ESR_ELx_EC_BTI		(0x0D)
 #define ESR_ELx_EC_ILL		(0x0E)
 /* Unallocated EC: 0x0F - 0x10 */
 #define ESR_ELx_EC_SVC32	(0x11)
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index 7a6e81ca23a8..7577a754d443 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -34,6 +34,7 @@ static inline u32 disr_to_esr(u64 disr)
 asmlinkage void enter_from_user_mode(void);
 void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
 void do_undefinstr(struct pt_regs *regs);
+void do_bti(struct pt_regs *regs);
 asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr);
 void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr,
 			struct pt_regs *regs);
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 0f00265248b5..d683bcbf1e7c 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -94,6 +94,7 @@
 #define KERNEL_HWCAP_BF16		__khwcap2_feature(BF16)
 #define KERNEL_HWCAP_DGH		__khwcap2_feature(DGH)
 #define KERNEL_HWCAP_RNG		__khwcap2_feature(RNG)
+#define KERNEL_HWCAP_BTI		__khwcap2_feature(BTI)
 
 /*
  * 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 bb313dde58a4..0bc46149e491 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -39,13 +39,37 @@ enum aarch64_insn_encoding_class {
 					 * system instructions */
 };
 
-enum aarch64_insn_hint_op {
+enum aarch64_insn_hint_cr_op {
 	AARCH64_INSN_HINT_NOP	= 0x0 << 5,
 	AARCH64_INSN_HINT_YIELD	= 0x1 << 5,
 	AARCH64_INSN_HINT_WFE	= 0x2 << 5,
 	AARCH64_INSN_HINT_WFI	= 0x3 << 5,
 	AARCH64_INSN_HINT_SEV	= 0x4 << 5,
 	AARCH64_INSN_HINT_SEVL	= 0x5 << 5,
+
+	AARCH64_INSN_HINT_XPACLRI    = 0x07 << 5,
+	AARCH64_INSN_HINT_PACIA_1716 = 0x08 << 5,
+	AARCH64_INSN_HINT_PACIB_1716 = 0x0A << 5,
+	AARCH64_INSN_HINT_AUTIA_1716 = 0x0C << 5,
+	AARCH64_INSN_HINT_AUTIB_1716 = 0x0E << 5,
+	AARCH64_INSN_HINT_PACIAZ     = 0x18 << 5,
+	AARCH64_INSN_HINT_PACIASP    = 0x19 << 5,
+	AARCH64_INSN_HINT_PACIBZ     = 0x1A << 5,
+	AARCH64_INSN_HINT_PACIBSP    = 0x1B << 5,
+	AARCH64_INSN_HINT_AUTIAZ     = 0x1C << 5,
+	AARCH64_INSN_HINT_AUTIASP    = 0x1D << 5,
+	AARCH64_INSN_HINT_AUTIBZ     = 0x1E << 5,
+	AARCH64_INSN_HINT_AUTIBSP    = 0x1F << 5,
+
+	AARCH64_INSN_HINT_ESB  = 0x10 << 5,
+	AARCH64_INSN_HINT_PSB  = 0x11 << 5,
+	AARCH64_INSN_HINT_TSB  = 0x12 << 5,
+	AARCH64_INSN_HINT_CSDB = 0x14 << 5,
+
+	AARCH64_INSN_HINT_BTI   = 0x20 << 5,
+	AARCH64_INSN_HINT_BTIC  = 0x22 << 5,
+	AARCH64_INSN_HINT_BTIJ  = 0x24 << 5,
+	AARCH64_INSN_HINT_BTIJC = 0x26 << 5,
 };
 
 enum aarch64_insn_imm_type {
@@ -344,7 +368,7 @@ __AARCH64_INSN_FUNCS(msr_reg,	0xFFF00000, 0xD5100000)
 
 #undef	__AARCH64_INSN_FUNCS
 
-bool aarch64_insn_is_nop(u32 insn);
+bool aarch64_insn_is_steppable_hint(u32 insn);
 bool aarch64_insn_is_branch_imm(u32 insn);
 
 static inline bool aarch64_insn_is_adr_adrp(u32 insn)
@@ -370,7 +394,7 @@ 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_op op);
+u32 aarch64_insn_gen_hint(enum aarch64_insn_hint_cr_op op);
 u32 aarch64_insn_gen_nop(void);
 u32 aarch64_insn_gen_branch_reg(enum aarch64_insn_register reg,
 				enum aarch64_insn_branch_type type);
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index a30b4eec7cb4..6ea53e6e8b26 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -507,10 +507,12 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
 
 static __always_inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
 {
-	if (vcpu_mode_is_32bit(vcpu))
+	if (vcpu_mode_is_32bit(vcpu)) {
 		kvm_skip_instr32(vcpu, is_wide_instr);
-	else
+	} else {
 		*vcpu_pc(vcpu) += 4;
+		*vcpu_cpsr(vcpu) &= ~PSR_BTYPE_MASK;
+	}
 
 	/* advance the singlestep state machine */
 	*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h
index ebee3113a62f..81fefd2a1d02 100644
--- a/arch/arm64/include/asm/linkage.h
+++ b/arch/arm64/include/asm/linkage.h
@@ -4,6 +4,52 @@
 #define __ALIGN		.align 2
 #define __ALIGN_STR	".align 2"
 
+#if defined(CONFIG_ARM64_BTI_KERNEL) && defined(__aarch64__)
+
+/*
+ * Since current versions of gas reject the BTI instruction unless we
+ * set the architecture version to v8.5 we use the hint instruction
+ * instead.
+ */
+#define BTI_C hint 34 ;
+#define BTI_J hint 36 ;
+
+/*
+ * When using in-kernel BTI we need to ensure that PCS-conformant assembly
+ * functions have suitable annotations.  Override SYM_FUNC_START to insert
+ * a BTI landing pad at the start of everything.
+ */
+#define SYM_FUNC_START(name)				\
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)	\
+	BTI_C
+
+#define SYM_FUNC_START_NOALIGN(name)			\
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE)	\
+	BTI_C
+
+#define SYM_FUNC_START_LOCAL(name)			\
+	SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN)	\
+	BTI_C
+
+#define SYM_FUNC_START_LOCAL_NOALIGN(name)		\
+	SYM_START(name, SYM_L_LOCAL, SYM_A_NONE)	\
+	BTI_C
+
+#define SYM_FUNC_START_WEAK(name)			\
+	SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN)	\
+	BTI_C
+
+#define SYM_FUNC_START_WEAK_NOALIGN(name)		\
+	SYM_START(name, SYM_L_WEAK, SYM_A_NONE)		\
+	BTI_C
+
+#define SYM_INNER_LABEL(name, linkage)			\
+	.type name SYM_T_NONE ASM_NL			\
+	SYM_ENTRY(name, linkage, SYM_A_NONE)		\
+	BTI_J
+
+#endif
+
 /*
  * Annotate a function as position independent, i.e., safe to be called before
  * the kernel virtual mapping is activated.
diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h
new file mode 100644
index 000000000000..081ec8de9ea6
--- /dev/null
+++ b/arch/arm64/include/asm/mman.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_MMAN_H__
+#define __ASM_MMAN_H__
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <uapi/asm/mman.h>
+
+static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
+	unsigned long pkey __always_unused)
+{
+	if (system_supports_bti() && (prot & PROT_BTI))
+		return VM_ARM64_BTI;
+
+	return 0;
+}
+#define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
+
+static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags)
+{
+	return (vm_flags & VM_ARM64_BTI) ? __pgprot(PTE_GP) : __pgprot(0);
+}
+#define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags)
+
+static inline bool arch_validate_prot(unsigned long prot,
+	unsigned long addr __always_unused)
+{
+	unsigned long supported = PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM;
+
+	if (system_supports_bti())
+		supported |= PROT_BTI;
+
+	return (prot & ~supported) == 0;
+}
+#define arch_validate_prot(prot, addr) arch_validate_prot(prot, addr)
+
+#endif /* ! __ASM_MMAN_H__ */
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 99315bdca0e6..9c91a8f93a0e 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -151,6 +151,7 @@
 #define PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
 #define PTE_AF			(_AT(pteval_t, 1) << 10)	/* Access Flag */
 #define PTE_NG			(_AT(pteval_t, 1) << 11)	/* nG */
+#define PTE_GP			(_AT(pteval_t, 1) << 50)	/* BTI guarded */
 #define PTE_DBM			(_AT(pteval_t, 1) << 51)	/* Dirty Bit Management */
 #define PTE_CONT		(_AT(pteval_t, 1) << 52)	/* Contiguous range */
 #define PTE_PXN			(_AT(pteval_t, 1) << 53)	/* Privileged XN */
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 1305e28225fc..2e7e0f452301 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -21,6 +21,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/cpufeature.h>
 #include <asm/pgtable-types.h>
 
 extern bool arm64_use_ng_mappings;
@@ -31,6 +32,16 @@ extern bool arm64_use_ng_mappings;
 #define PTE_MAYBE_NG		(arm64_use_ng_mappings ? PTE_NG : 0)
 #define PMD_MAYBE_NG		(arm64_use_ng_mappings ? PMD_SECT_NG : 0)
 
+/*
+ * If we have userspace only BTI we don't want to mark kernel pages
+ * guarded even if the system does support BTI.
+ */
+#ifdef CONFIG_ARM64_BTI_KERNEL
+#define PTE_MAYBE_GP		(system_supports_bti() ? PTE_GP : 0)
+#else
+#define PTE_MAYBE_GP		0
+#endif
+
 #define PROT_DEFAULT		(_PROT_DEFAULT | PTE_MAYBE_NG)
 #define PROT_SECT_DEFAULT	(_PROT_SECT_DEFAULT | PMD_MAYBE_NG)
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 5caff09c6a3a..e50e4dda90c2 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -661,7 +661,7 @@ static inline phys_addr_t pgd_page_paddr(pgd_t pgd)
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY |
-			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE;
+			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE | PTE_GP;
 	/* preserve the hardware dirty information */
 	if (pte_hw_dirty(pte))
 		pte = pte_mkdirty(pte);
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index bf57308fcd63..2172ec7594ba 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -35,6 +35,7 @@
 #define GIC_PRIO_PSR_I_SET		(1 << 4)
 
 /* Additional SPSR bits not exposed in the UABI */
+
 #define PSR_IL_BIT		(1 << 20)
 
 /* AArch32-specific ptrace requests */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index efe368ee4996..463175f80341 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -559,6 +559,8 @@
 #endif
 
 /* SCTLR_EL1 specific flags. */
+#define SCTLR_EL1_BT1		(BIT(36))
+#define SCTLR_EL1_BT0		(BIT(35))
 #define SCTLR_EL1_UCI		(BIT(26))
 #define SCTLR_EL1_E0E		(BIT(24))
 #define SCTLR_EL1_SPAN		(BIT(23))
@@ -679,6 +681,7 @@
 #define ID_AA64PFR1_SSBS_PSTATE_NI	0
 #define ID_AA64PFR1_SSBS_PSTATE_ONLY	1
 #define ID_AA64PFR1_SSBS_PSTATE_INSNS	2
+#define ID_AA64PFR1_BT_BTI		0x1
 
 /* id_aa64zfr0 */
 #define ID_AA64ZFR0_F64MM_SHIFT		56
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 7752d93bb50f..2d6ba1c2592e 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -73,5 +73,6 @@
 #define HWCAP2_BF16		(1 << 14)
 #define HWCAP2_DGH		(1 << 15)
 #define HWCAP2_RNG		(1 << 16)
+#define HWCAP2_BTI		(1 << 17)
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/mman.h b/arch/arm64/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..6fdd71eb644f
--- /dev/null
+++ b/arch/arm64/include/uapi/asm/mman.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI__ASM_MMAN_H
+#define _UAPI__ASM_MMAN_H
+
+#include <asm-generic/mman.h>
+
+#define PROT_BTI	0x10		/* BTI guarded page */
+
+#endif /* ! _UAPI__ASM_MMAN_H */
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index d1bb5b69f1ce..42cbe34d95ce 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -46,6 +46,7 @@
 #define PSR_I_BIT	0x00000080
 #define PSR_A_BIT	0x00000100
 #define PSR_D_BIT	0x00000200
+#define PSR_BTYPE_MASK	0x00000c00
 #define PSR_SSBS_BIT	0x00001000
 #define PSR_PAN_BIT	0x00400000
 #define PSR_UAO_BIT	0x00800000
@@ -55,6 +56,8 @@
 #define PSR_Z_BIT	0x40000000
 #define PSR_N_BIT	0x80000000
 
+#define PSR_BTYPE_SHIFT		10
+
 /*
  * Groups of PSR bits
  */
@@ -63,6 +66,12 @@
 #define PSR_x		0x0000ff00	/* Extension		*/
 #define PSR_c		0x000000ff	/* Control		*/
 
+/* Convenience names for the values of PSTATE.BTYPE */
+#define PSR_BTYPE_NONE		(0b00 << PSR_BTYPE_SHIFT)
+#define PSR_BTYPE_JC		(0b01 << PSR_BTYPE_SHIFT)
+#define PSR_BTYPE_C		(0b10 << PSR_BTYPE_SHIFT)
+#define PSR_BTYPE_J		(0b11 << PSR_BTYPE_SHIFT)
+
 /* syscall emulation path in ptrace */
 #define PTRACE_SYSEMU		  31
 #define PTRACE_SYSEMU_SINGLESTEP  32
diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S
index 38087b4c0432..4a18055b2ff9 100644
--- a/arch/arm64/kernel/cpu-reset.S
+++ b/arch/arm64/kernel/cpu-reset.S
@@ -29,7 +29,7 @@
  * branch to what would be the reset vector. It must be executed with the
  * flat identity mapping.
  */
-ENTRY(__cpu_soft_restart)
+SYM_CODE_START(__cpu_soft_restart)
 	/* Clear sctlr_el1 flags. */
 	mrs	x12, sctlr_el1
 	mov_q	x13, SCTLR_ELx_FLAGS
@@ -47,6 +47,6 @@ ENTRY(__cpu_soft_restart)
 	mov	x1, x3				// arg1
 	mov	x2, x4				// arg2
 	br	x8
-ENDPROC(__cpu_soft_restart)
+SYM_CODE_END(__cpu_soft_restart)
 
 .popsection
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index b3202a99e559..4ae41670c2e6 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -241,6 +241,8 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_MPAMFRAC_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_RASFRAC_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SSBS_SHIFT, 4, ID_AA64PFR1_SSBS_PSTATE_NI),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_BTI),
+				    FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_BT_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -1638,6 +1640,21 @@ static bool can_use_gic_priorities(const struct arm64_cpu_capabilities *entry,
 }
 #endif
 
+#ifdef CONFIG_ARM64_BTI
+static void bti_enable(const struct arm64_cpu_capabilities *__unused)
+{
+	/*
+	 * Use of X16/X17 for tail-calls and trampolines that jump to
+	 * function entry points using BR is a requirement for
+	 * marking binaries with GNU_PROPERTY_AARCH64_FEATURE_1_BTI.
+	 * So, be strict and forbid other BRs using other registers to
+	 * jump onto a PACIxSP instruction:
+	 */
+	sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_BT0 | SCTLR_EL1_BT1);
+	isb();
+}
+#endif /* CONFIG_ARM64_BTI */
+
 /* Internal helper functions to match cpu capability type */
 static bool
 cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap)
@@ -2020,6 +2037,23 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.min_field_value = 1,
 	},
 #endif
+#ifdef CONFIG_ARM64_BTI
+	{
+		.desc = "Branch Target Identification",
+		.capability = ARM64_BTI,
+#ifdef CONFIG_ARM64_BTI_KERNEL
+		.type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE,
+#else
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+#endif
+		.matches = has_cpuid_feature,
+		.cpu_enable = bti_enable,
+		.sys_reg = SYS_ID_AA64PFR1_EL1,
+		.field_pos = ID_AA64PFR1_BT_SHIFT,
+		.min_field_value = ID_AA64PFR1_BT_BTI,
+		.sign = FTR_UNSIGNED,
+	},
+#endif
 	{},
 };
 
@@ -2129,6 +2163,9 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_F64MM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_F64MM, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM),
 #endif
 	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, KERNEL_HWCAP_SSBS),
+#ifdef CONFIG_ARM64_BTI
+	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_BT_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_BT_BTI, CAP_HWCAP, KERNEL_HWCAP_BTI),
+#endif
 #ifdef CONFIG_ARM64_PTR_AUTH
 	HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, KERNEL_HWCAP_PACA),
 	HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, KERNEL_HWCAP_PACG),
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index c1a257d93e90..86637466daa8 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -92,6 +92,7 @@ static const char *const hwcap_str[] = {
 	"bf16",
 	"dgh",
 	"rng",
+	"bti",
 	NULL
 };
 
diff --git a/arch/arm64/kernel/efi-rt-wrapper.S b/arch/arm64/kernel/efi-rt-wrapper.S
index 3fc71106cb2b..1192c4bb48df 100644
--- a/arch/arm64/kernel/efi-rt-wrapper.S
+++ b/arch/arm64/kernel/efi-rt-wrapper.S
@@ -5,7 +5,7 @@
 
 #include <linux/linkage.h>
 
-ENTRY(__efi_rt_asm_wrapper)
+SYM_FUNC_START(__efi_rt_asm_wrapper)
 	stp	x29, x30, [sp, #-32]!
 	mov	x29, sp
 
@@ -35,4 +35,4 @@ ENTRY(__efi_rt_asm_wrapper)
 	b.ne	0f
 	ret
 0:	b	efi_handle_corrupted_x18	// tail call
-ENDPROC(__efi_rt_asm_wrapper)
+SYM_FUNC_END(__efi_rt_asm_wrapper)
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index bed09a866c2f..3dbdf9752b11 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -188,6 +188,14 @@ static void notrace el0_undef(struct pt_regs *regs)
 }
 NOKPROBE_SYMBOL(el0_undef);
 
+static void notrace el0_bti(struct pt_regs *regs)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_bti(regs);
+}
+NOKPROBE_SYMBOL(el0_bti);
+
 static void notrace el0_inv(struct pt_regs *regs, unsigned long esr)
 {
 	user_exit_irqoff();
@@ -255,6 +263,9 @@ asmlinkage void notrace el0_sync_handler(struct pt_regs *regs)
 	case ESR_ELx_EC_UNKNOWN:
 		el0_undef(regs);
 		break;
+	case ESR_ELx_EC_BTI:
+		el0_bti(regs);
+		break;
 	case ESR_ELx_EC_BREAKPT_LOW:
 	case ESR_ELx_EC_SOFTSTP_LOW:
 	case ESR_ELx_EC_WATCHPT_LOW:
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index 0f24eae8f3cc..f880dd63ddc3 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -16,34 +16,34 @@
  *
  * x0 - pointer to struct fpsimd_state
  */
-ENTRY(fpsimd_save_state)
+SYM_FUNC_START(fpsimd_save_state)
 	fpsimd_save x0, 8
 	ret
-ENDPROC(fpsimd_save_state)
+SYM_FUNC_END(fpsimd_save_state)
 
 /*
  * Load the FP registers.
  *
  * x0 - pointer to struct fpsimd_state
  */
-ENTRY(fpsimd_load_state)
+SYM_FUNC_START(fpsimd_load_state)
 	fpsimd_restore x0, 8
 	ret
-ENDPROC(fpsimd_load_state)
+SYM_FUNC_END(fpsimd_load_state)
 
 #ifdef CONFIG_ARM64_SVE
-ENTRY(sve_save_state)
+SYM_FUNC_START(sve_save_state)
 	sve_save 0, x1, 2
 	ret
-ENDPROC(sve_save_state)
+SYM_FUNC_END(sve_save_state)
 
-ENTRY(sve_load_state)
+SYM_FUNC_START(sve_load_state)
 	sve_load 0, x1, x2, 3, x4
 	ret
-ENDPROC(sve_load_state)
+SYM_FUNC_END(sve_load_state)
 
-ENTRY(sve_get_vl)
+SYM_FUNC_START(sve_get_vl)
 	_sve_rdvl	0, 1
 	ret
-ENDPROC(sve_get_vl)
+SYM_FUNC_END(sve_get_vl)
 #endif /* CONFIG_ARM64_SVE */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index a9265fef914f..84cbc513c1e8 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -728,20 +728,9 @@ el0_error_naked:
 SYM_CODE_END(el0_error)
 
 /*
- * Ok, we need to do extra processing, enter the slow path.
- */
-work_pending:
-	mov	x0, sp				// 'regs'
-	bl	do_notify_resume
-#ifdef CONFIG_TRACE_IRQFLAGS
-	bl	trace_hardirqs_on		// enabled while in userspace
-#endif
-	ldr	x1, [tsk, #TSK_TI_FLAGS]	// re-check for single-step
-	b	finish_ret_to_user
-/*
  * "slow" syscall return path.
  */
-ret_to_user:
+SYM_CODE_START_LOCAL(ret_to_user)
 	disable_daif
 	gic_prio_kentry_setup tmp=x3
 	ldr	x1, [tsk, #TSK_TI_FLAGS]
@@ -753,7 +742,19 @@ finish_ret_to_user:
 	bl	stackleak_erase
 #endif
 	kernel_exit 0
-ENDPROC(ret_to_user)
+
+/*
+ * Ok, we need to do extra processing, enter the slow path.
+ */
+work_pending:
+	mov	x0, sp				// 'regs'
+	bl	do_notify_resume
+#ifdef CONFIG_TRACE_IRQFLAGS
+	bl	trace_hardirqs_on		// enabled while in userspace
+#endif
+	ldr	x1, [tsk, #TSK_TI_FLAGS]	// re-check for single-step
+	b	finish_ret_to_user
+SYM_CODE_END(ret_to_user)
 
 	.popsection				// .entry.text
 
diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S
index 6532105b3e32..8ccca660034e 100644
--- a/arch/arm64/kernel/hibernate-asm.S
+++ b/arch/arm64/kernel/hibernate-asm.S
@@ -65,7 +65,7 @@
  * x5: physical address of a  zero page that remains zero after resume
  */
 .pushsection    ".hibernate_exit.text", "ax"
-ENTRY(swsusp_arch_suspend_exit)
+SYM_CODE_START(swsusp_arch_suspend_exit)
 	/*
 	 * We execute from ttbr0, change ttbr1 to our copied linear map tables
 	 * with a break-before-make via the zero page
@@ -110,7 +110,7 @@ ENTRY(swsusp_arch_suspend_exit)
 	cbz	x24, 3f		/* Do we need to re-initialise EL2? */
 	hvc	#0
 3:	ret
-ENDPROC(swsusp_arch_suspend_exit)
+SYM_CODE_END(swsusp_arch_suspend_exit)
 
 /*
  * Restore the hyp stub.
@@ -119,15 +119,15 @@ ENDPROC(swsusp_arch_suspend_exit)
  *
  * x24: The physical address of __hyp_stub_vectors
  */
-el1_sync:
+SYM_CODE_START_LOCAL(el1_sync)
 	msr	vbar_el2, x24
 	eret
-ENDPROC(el1_sync)
+SYM_CODE_END(el1_sync)
 
 .macro invalid_vector	label
-\label:
+SYM_CODE_START_LOCAL(\label)
 	b \label
-ENDPROC(\label)
+SYM_CODE_END(\label)
 .endm
 
 	invalid_vector	el2_sync_invalid
@@ -141,7 +141,7 @@ ENDPROC(\label)
 
 /* el2 vectors - switch el2 here while we restore the memory image. */
 	.align 11
-ENTRY(hibernate_el2_vectors)
+SYM_CODE_START(hibernate_el2_vectors)
 	ventry	el2_sync_invalid		// Synchronous EL2t
 	ventry	el2_irq_invalid			// IRQ EL2t
 	ventry	el2_fiq_invalid			// FIQ EL2t
@@ -161,6 +161,6 @@ ENTRY(hibernate_el2_vectors)
 	ventry	el1_irq_invalid			// IRQ 32-bit EL1
 	ventry	el1_fiq_invalid			// FIQ 32-bit EL1
 	ventry	el1_error_invalid		// Error 32-bit EL1
-END(hibernate_el2_vectors)
+SYM_CODE_END(hibernate_el2_vectors)
 
 .popsection
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index e473ead806ed..160f5881a0b7 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -21,7 +21,7 @@
 
 	.align 11
 
-ENTRY(__hyp_stub_vectors)
+SYM_CODE_START(__hyp_stub_vectors)
 	ventry	el2_sync_invalid		// Synchronous EL2t
 	ventry	el2_irq_invalid			// IRQ EL2t
 	ventry	el2_fiq_invalid			// FIQ EL2t
@@ -41,11 +41,11 @@ ENTRY(__hyp_stub_vectors)
 	ventry	el1_irq_invalid			// IRQ 32-bit EL1
 	ventry	el1_fiq_invalid			// FIQ 32-bit EL1
 	ventry	el1_error_invalid		// Error 32-bit EL1
-ENDPROC(__hyp_stub_vectors)
+SYM_CODE_END(__hyp_stub_vectors)
 
 	.align 11
 
-el1_sync:
+SYM_CODE_START_LOCAL(el1_sync)
 	cmp	x0, #HVC_SET_VECTORS
 	b.ne	2f
 	msr	vbar_el2, x1
@@ -68,12 +68,12 @@ el1_sync:
 
 9:	mov	x0, xzr
 	eret
-ENDPROC(el1_sync)
+SYM_CODE_END(el1_sync)
 
 .macro invalid_vector	label
-\label:
+SYM_CODE_START_LOCAL(\label)
 	b \label
-ENDPROC(\label)
+SYM_CODE_END(\label)
 .endm
 
 	invalid_vector	el2_sync_invalid
@@ -106,15 +106,15 @@ ENDPROC(\label)
  * initialisation entry point.
  */
 
-ENTRY(__hyp_set_vectors)
+SYM_FUNC_START(__hyp_set_vectors)
 	mov	x1, x0
 	mov	x0, #HVC_SET_VECTORS
 	hvc	#0
 	ret
-ENDPROC(__hyp_set_vectors)
+SYM_FUNC_END(__hyp_set_vectors)
 
-ENTRY(__hyp_reset_vectors)
+SYM_FUNC_START(__hyp_reset_vectors)
 	mov	x0, #HVC_RESET_VECTORS
 	hvc	#0
 	ret
-ENDPROC(__hyp_reset_vectors)
+SYM_FUNC_END(__hyp_reset_vectors)
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index cc2f3d901c91..684d871ae38d 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -51,21 +51,33 @@ enum aarch64_insn_encoding_class __kprobes aarch64_get_insn_class(u32 insn)
 	return aarch64_insn_encoding_class[(insn >> 25) & 0xf];
 }
 
-/* NOP is an alias of HINT */
-bool __kprobes aarch64_insn_is_nop(u32 insn)
+bool __kprobes aarch64_insn_is_steppable_hint(u32 insn)
 {
 	if (!aarch64_insn_is_hint(insn))
 		return false;
 
 	switch (insn & 0xFE0) {
-	case AARCH64_INSN_HINT_YIELD:
-	case AARCH64_INSN_HINT_WFE:
-	case AARCH64_INSN_HINT_WFI:
-	case AARCH64_INSN_HINT_SEV:
-	case AARCH64_INSN_HINT_SEVL:
-		return false;
-	default:
+	case AARCH64_INSN_HINT_XPACLRI:
+	case AARCH64_INSN_HINT_PACIA_1716:
+	case AARCH64_INSN_HINT_PACIB_1716:
+	case AARCH64_INSN_HINT_AUTIA_1716:
+	case AARCH64_INSN_HINT_AUTIB_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_AUTIAZ:
+	case AARCH64_INSN_HINT_AUTIASP:
+	case AARCH64_INSN_HINT_AUTIBZ:
+	case AARCH64_INSN_HINT_AUTIBSP:
+	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;
 	}
 }
 
@@ -574,7 +586,7 @@ u32 aarch64_insn_gen_cond_branch_imm(unsigned long pc, unsigned long addr,
 					     offset >> 2);
 }
 
-u32 __kprobes aarch64_insn_gen_hint(enum aarch64_insn_hint_op op)
+u32 __kprobes aarch64_insn_gen_hint(enum aarch64_insn_hint_cr_op op)
 {
 	return aarch64_insn_get_hint_value() | op;
 }
diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c
index b78fac9e546c..263d5fba4c8a 100644
--- a/arch/arm64/kernel/probes/decode-insn.c
+++ b/arch/arm64/kernel/probes/decode-insn.c
@@ -46,7 +46,7 @@ static bool __kprobes aarch64_insn_is_steppable(u32 insn)
 		 * except for the NOP case.
 		 */
 		if (aarch64_insn_is_hint(insn))
-			return aarch64_insn_is_nop(insn);
+			return aarch64_insn_is_steppable_hint(insn);
 
 		return true;
 	}
diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S
index 45dce03aaeaf..890ca72c5a51 100644
--- a/arch/arm64/kernel/probes/kprobes_trampoline.S
+++ b/arch/arm64/kernel/probes/kprobes_trampoline.S
@@ -61,7 +61,7 @@
 	ldp x28, x29, [sp, #S_X28]
 	.endm
 
-ENTRY(kretprobe_trampoline)
+SYM_CODE_START(kretprobe_trampoline)
 	sub sp, sp, #S_FRAME_SIZE
 
 	save_all_base_regs
@@ -79,4 +79,4 @@ ENTRY(kretprobe_trampoline)
 	add sp, sp, #S_FRAME_SIZE
 	ret
 
-ENDPROC(kretprobe_trampoline)
+SYM_CODE_END(kretprobe_trampoline)
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 56be4cbf771f..eade7807e819 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -11,6 +11,7 @@
 
 #include <linux/compat.h>
 #include <linux/efi.h>
+#include <linux/elf.h>
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
@@ -18,6 +19,7 @@
 #include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/lockdep.h>
+#include <linux/mman.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
 #include <linux/sysctl.h>
@@ -209,6 +211,15 @@ void machine_restart(char *cmd)
 	while (1);
 }
 
+#define bstr(suffix, str) [PSR_BTYPE_ ## suffix >> PSR_BTYPE_SHIFT] = str
+static const char *const btypes[] = {
+	bstr(NONE, "--"),
+	bstr(  JC, "jc"),
+	bstr(   C, "-c"),
+	bstr(  J , "j-")
+};
+#undef bstr
+
 static void print_pstate(struct pt_regs *regs)
 {
 	u64 pstate = regs->pstate;
@@ -227,7 +238,10 @@ static void print_pstate(struct pt_regs *regs)
 			pstate & PSR_AA32_I_BIT ? 'I' : 'i',
 			pstate & PSR_AA32_F_BIT ? 'F' : 'f');
 	} else {
-		printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO)\n",
+		const char *btype_str = btypes[(pstate & PSR_BTYPE_MASK) >>
+					       PSR_BTYPE_SHIFT];
+
+		printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO BTYPE=%s)\n",
 			pstate,
 			pstate & PSR_N_BIT ? 'N' : 'n',
 			pstate & PSR_Z_BIT ? 'Z' : 'z',
@@ -238,7 +252,8 @@ static void print_pstate(struct pt_regs *regs)
 			pstate & PSR_I_BIT ? 'I' : 'i',
 			pstate & PSR_F_BIT ? 'F' : 'f',
 			pstate & PSR_PAN_BIT ? '+' : '-',
-			pstate & PSR_UAO_BIT ? '+' : '-');
+			pstate & PSR_UAO_BIT ? '+' : '-',
+			btype_str);
 	}
 }
 
@@ -655,3 +670,25 @@ asmlinkage void __sched arm64_preempt_schedule_irq(void)
 	if (system_capabilities_finalized())
 		preempt_schedule_irq();
 }
+
+#ifdef CONFIG_BINFMT_ELF
+int arch_elf_adjust_prot(int prot, const struct arch_elf_state *state,
+			 bool has_interp, bool is_interp)
+{
+	/*
+	 * For dynamically linked executables the interpreter is
+	 * responsible for setting PROT_BTI on everything except
+	 * itself.
+	 */
+	if (is_interp != has_interp)
+		return prot;
+
+	if (!(state->flags & ARM64_ELF_BTI))
+		return prot;
+
+	if (prot & PROT_EXEC)
+		prot |= PROT_BTI;
+
+	return prot;
+}
+#endif
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index b3d3005d9515..585dd7f5c826 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1874,7 +1874,7 @@ void syscall_trace_exit(struct pt_regs *regs)
  */
 #define SPSR_EL1_AARCH64_RES0_BITS \
 	(GENMASK_ULL(63, 32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \
-	 GENMASK_ULL(20, 13) | GENMASK_ULL(11, 10) | GENMASK_ULL(5, 5))
+	 GENMASK_ULL(20, 13) | GENMASK_ULL(5, 5))
 #define SPSR_EL1_AARCH32_RES0_BITS \
 	(GENMASK_ULL(63, 32) | GENMASK_ULL(22, 22) | GENMASK_ULL(20, 20))
 
diff --git a/arch/arm64/kernel/reloc_test_syms.S b/arch/arm64/kernel/reloc_test_syms.S
index 16a34f188f26..c50f45fa29fa 100644
--- a/arch/arm64/kernel/reloc_test_syms.S
+++ b/arch/arm64/kernel/reloc_test_syms.S
@@ -5,81 +5,81 @@
 
 #include <linux/linkage.h>
 
-ENTRY(absolute_data64)
+SYM_FUNC_START(absolute_data64)
 	ldr	x0, 0f
 	ret
 0:	.quad	sym64_abs
-ENDPROC(absolute_data64)
+SYM_FUNC_END(absolute_data64)
 
-ENTRY(absolute_data32)
+SYM_FUNC_START(absolute_data32)
 	ldr	w0, 0f
 	ret
 0:	.long	sym32_abs
-ENDPROC(absolute_data32)
+SYM_FUNC_END(absolute_data32)
 
-ENTRY(absolute_data16)
+SYM_FUNC_START(absolute_data16)
 	adr	x0, 0f
 	ldrh	w0, [x0]
 	ret
 0:	.short	sym16_abs, 0
-ENDPROC(absolute_data16)
+SYM_FUNC_END(absolute_data16)
 
-ENTRY(signed_movw)
+SYM_FUNC_START(signed_movw)
 	movz	x0, #:abs_g2_s:sym64_abs
 	movk	x0, #:abs_g1_nc:sym64_abs
 	movk	x0, #:abs_g0_nc:sym64_abs
 	ret
-ENDPROC(signed_movw)
+SYM_FUNC_END(signed_movw)
 
-ENTRY(unsigned_movw)
+SYM_FUNC_START(unsigned_movw)
 	movz	x0, #:abs_g3:sym64_abs
 	movk	x0, #:abs_g2_nc:sym64_abs
 	movk	x0, #:abs_g1_nc:sym64_abs
 	movk	x0, #:abs_g0_nc:sym64_abs
 	ret
-ENDPROC(unsigned_movw)
+SYM_FUNC_END(unsigned_movw)
 
 	.align	12
 	.space	0xff8
-ENTRY(relative_adrp)
+SYM_FUNC_START(relative_adrp)
 	adrp	x0, sym64_rel
 	add	x0, x0, #:lo12:sym64_rel
 	ret
-ENDPROC(relative_adrp)
+SYM_FUNC_END(relative_adrp)
 
 	.align	12
 	.space	0xffc
-ENTRY(relative_adrp_far)
+SYM_FUNC_START(relative_adrp_far)
 	adrp	x0, memstart_addr
 	add	x0, x0, #:lo12:memstart_addr
 	ret
-ENDPROC(relative_adrp_far)
+SYM_FUNC_END(relative_adrp_far)
 
-ENTRY(relative_adr)
+SYM_FUNC_START(relative_adr)
 	adr	x0, sym64_rel
 	ret
-ENDPROC(relative_adr)
+SYM_FUNC_END(relative_adr)
 
-ENTRY(relative_data64)
+SYM_FUNC_START(relative_data64)
 	adr	x1, 0f
 	ldr	x0, [x1]
 	add	x0, x0, x1
 	ret
 0:	.quad	sym64_rel - .
-ENDPROC(relative_data64)
+SYM_FUNC_END(relative_data64)
 
-ENTRY(relative_data32)
+SYM_FUNC_START(relative_data32)
 	adr	x1, 0f
 	ldr	w0, [x1]
 	add	x0, x0, x1
 	ret
 0:	.long	sym64_rel - .
-ENDPROC(relative_data32)
+SYM_FUNC_END(relative_data32)
 
-ENTRY(relative_data16)
+SYM_FUNC_START(relative_data16)
 	adr	x1, 0f
 	ldrsh	w0, [x1]
 	add	x0, x0, x1
 	ret
 0:	.short	sym64_rel - ., 0
-ENDPROC(relative_data16)
+SYM_FUNC_END(relative_data16)
diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S
index c40ce496c78b..542d6edc6806 100644
--- a/arch/arm64/kernel/relocate_kernel.S
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -26,7 +26,7 @@
  * control_code_page, a special page which has been set up to be preserved
  * during the copy operation.
  */
-ENTRY(arm64_relocate_new_kernel)
+SYM_CODE_START(arm64_relocate_new_kernel)
 
 	/* Setup the list loop variables. */
 	mov	x18, x2				/* x18 = dtb address */
@@ -111,7 +111,7 @@ ENTRY(arm64_relocate_new_kernel)
 	mov	x3, xzr
 	br	x17
 
-ENDPROC(arm64_relocate_new_kernel)
+SYM_CODE_END(arm64_relocate_new_kernel)
 
 .align 3	/* To keep the 64-bit values below naturally aligned. */
 
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 339882db5a91..801d56cdf701 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -732,6 +732,22 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 	regs->regs[29] = (unsigned long)&user->next_frame->fp;
 	regs->pc = (unsigned long)ka->sa.sa_handler;
 
+	/*
+	 * Signal delivery is a (wacky) indirect function call in
+	 * userspace, so simulate the same setting of BTYPE as a BLR
+	 * <register containing the signal handler entry point>.
+	 * Signal delivery to a location in a PROT_BTI guarded page
+	 * that is not a function entry point will now trigger a
+	 * SIGILL in userspace.
+	 *
+	 * If the signal handler entry point is not in a PROT_BTI
+	 * guarded page, this is harmless.
+	 */
+	if (system_supports_bti()) {
+		regs->pstate &= ~PSR_BTYPE_MASK;
+		regs->pstate |= PSR_BTYPE_C;
+	}
+
 	if (ka->sa.sa_flags & SA_RESTORER)
 		sigtramp = ka->sa.sa_restorer;
 	else
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index 56b1fe9bfaa0..ba40d57757d6 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -62,7 +62,7 @@
  *
  *  x0 = struct sleep_stack_data area
  */
-ENTRY(__cpu_suspend_enter)
+SYM_FUNC_START(__cpu_suspend_enter)
 	stp	x29, lr, [x0, #SLEEP_STACK_DATA_CALLEE_REGS]
 	stp	x19, x20, [x0,#SLEEP_STACK_DATA_CALLEE_REGS+16]
 	stp	x21, x22, [x0,#SLEEP_STACK_DATA_CALLEE_REGS+32]
@@ -95,10 +95,10 @@ ENTRY(__cpu_suspend_enter)
 	ldp	x29, lr, [sp], #16
 	mov	x0, #1
 	ret
-ENDPROC(__cpu_suspend_enter)
+SYM_FUNC_END(__cpu_suspend_enter)
 
 	.pushsection ".idmap.text", "awx"
-ENTRY(cpu_resume)
+SYM_CODE_START(cpu_resume)
 	bl	el2_setup		// if in EL2 drop to EL1 cleanly
 	bl	__cpu_setup
 	/* enable the MMU early - so we can access sleep_save_stash by va */
@@ -106,11 +106,11 @@ ENTRY(cpu_resume)
 	bl	__enable_mmu
 	ldr	x8, =_cpu_resume
 	br	x8
-ENDPROC(cpu_resume)
+SYM_CODE_END(cpu_resume)
 	.ltorg
 	.popsection
 
-ENTRY(_cpu_resume)
+SYM_FUNC_START(_cpu_resume)
 	mrs	x1, mpidr_el1
 	adr_l	x8, mpidr_hash		// x8 = struct mpidr_hash virt address
 
@@ -146,4 +146,4 @@ ENTRY(_cpu_resume)
 	ldp	x29, lr, [x29]
 	mov	x0, #0
 	ret
-ENDPROC(_cpu_resume)
+SYM_FUNC_END(_cpu_resume)
diff --git a/arch/arm64/kernel/smccc-call.S b/arch/arm64/kernel/smccc-call.S
index 54655273d1e0..1f93809528a4 100644
--- a/arch/arm64/kernel/smccc-call.S
+++ b/arch/arm64/kernel/smccc-call.S
@@ -30,9 +30,9 @@
  *		  unsigned long a6, unsigned long a7, struct arm_smccc_res *res,
  *		  struct arm_smccc_quirk *quirk)
  */
-ENTRY(__arm_smccc_smc)
+SYM_FUNC_START(__arm_smccc_smc)
 	SMCCC	smc
-ENDPROC(__arm_smccc_smc)
+SYM_FUNC_END(__arm_smccc_smc)
 EXPORT_SYMBOL(__arm_smccc_smc)
 
 /*
@@ -41,7 +41,7 @@ EXPORT_SYMBOL(__arm_smccc_smc)
  *		  unsigned long a6, unsigned long a7, struct arm_smccc_res *res,
  *		  struct arm_smccc_quirk *quirk)
  */
-ENTRY(__arm_smccc_hvc)
+SYM_FUNC_START(__arm_smccc_hvc)
 	SMCCC	hvc
-ENDPROC(__arm_smccc_hvc)
+SYM_FUNC_END(__arm_smccc_hvc)
 EXPORT_SYMBOL(__arm_smccc_hvc)
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index a12c0c88d345..5f5b868292f5 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -98,6 +98,24 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	regs->orig_x0 = regs->regs[0];
 	regs->syscallno = scno;
 
+	/*
+	 * BTI note:
+	 * The architecture does not guarantee that SPSR.BTYPE is zero
+	 * on taking an SVC, so we could return to userspace with a
+	 * non-zero BTYPE after the syscall.
+	 *
+	 * This shouldn't matter except when userspace is explicitly
+	 * doing something stupid, such as setting PROT_BTI on a page
+	 * that lacks conforming BTI/PACIxSP instructions, falling
+	 * through from one executable page to another with differing
+	 * PROT_BTI, or messing with BTYPE via ptrace: in such cases,
+	 * userspace should not be surprised if a SIGILL occurs on
+	 * syscall return.
+	 *
+	 * So, don't touch regs->pstate & PSR_BTYPE_MASK here.
+	 * (Similarly for HVC and SMC elsewhere.)
+	 */
+
 	cortex_a76_erratum_1463225_svc_handler();
 	local_daif_restore(DAIF_PROCCTX);
 	user_exit();
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 8408e8670f2e..f8663308ac03 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -272,6 +272,61 @@ void arm64_notify_die(const char *str, struct pt_regs *regs,
 	}
 }
 
+#ifdef CONFIG_COMPAT
+#define PSTATE_IT_1_0_SHIFT	25
+#define PSTATE_IT_1_0_MASK	(0x3 << PSTATE_IT_1_0_SHIFT)
+#define PSTATE_IT_7_2_SHIFT	10
+#define PSTATE_IT_7_2_MASK	(0x3f << PSTATE_IT_7_2_SHIFT)
+
+static u32 compat_get_it_state(struct pt_regs *regs)
+{
+	u32 it, pstate = regs->pstate;
+
+	it  = (pstate & PSTATE_IT_1_0_MASK) >> PSTATE_IT_1_0_SHIFT;
+	it |= ((pstate & PSTATE_IT_7_2_MASK) >> PSTATE_IT_7_2_SHIFT) << 2;
+
+	return it;
+}
+
+static void compat_set_it_state(struct pt_regs *regs, u32 it)
+{
+	u32 pstate_it;
+
+	pstate_it  = (it << PSTATE_IT_1_0_SHIFT) & PSTATE_IT_1_0_MASK;
+	pstate_it |= ((it >> 2) << PSTATE_IT_7_2_SHIFT) & PSTATE_IT_7_2_MASK;
+
+	regs->pstate &= ~PSR_AA32_IT_MASK;
+	regs->pstate |= pstate_it;
+}
+
+static void advance_itstate(struct pt_regs *regs)
+{
+	u32 it;
+
+	/* ARM mode */
+	if (!(regs->pstate & PSR_AA32_T_BIT) ||
+	    !(regs->pstate & PSR_AA32_IT_MASK))
+		return;
+
+	it  = compat_get_it_state(regs);
+
+	/*
+	 * If this is the last instruction of the block, wipe the IT
+	 * state. Otherwise advance it.
+	 */
+	if (!(it & 7))
+		it = 0;
+	else
+		it = (it & 0xe0) | ((it << 1) & 0x1f);
+
+	compat_set_it_state(regs, it);
+}
+#else
+static void advance_itstate(struct pt_regs *regs)
+{
+}
+#endif
+
 void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size)
 {
 	regs->pc += size;
@@ -282,6 +337,11 @@ void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size)
 	 */
 	if (user_mode(regs))
 		user_fastforward_single_step(current);
+
+	if (compat_user_mode(regs))
+		advance_itstate(regs);
+	else
+		regs->pstate &= ~PSR_BTYPE_MASK;
 }
 
 static LIST_HEAD(undef_hook);
@@ -411,6 +471,13 @@ void do_undefinstr(struct pt_regs *regs)
 }
 NOKPROBE_SYMBOL(do_undefinstr);
 
+void do_bti(struct pt_regs *regs)
+{
+	BUG_ON(!user_mode(regs));
+	force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc);
+}
+NOKPROBE_SYMBOL(do_bti);
+
 #define __user_cache_maint(insn, address, res)			\
 	if (address >= user_addr_max()) {			\
 		res = -EFAULT;					\
@@ -566,34 +633,7 @@ static const struct sys64_hook sys64_hooks[] = {
 	{},
 };
 
-
 #ifdef CONFIG_COMPAT
-#define PSTATE_IT_1_0_SHIFT	25
-#define PSTATE_IT_1_0_MASK	(0x3 << PSTATE_IT_1_0_SHIFT)
-#define PSTATE_IT_7_2_SHIFT	10
-#define PSTATE_IT_7_2_MASK	(0x3f << PSTATE_IT_7_2_SHIFT)
-
-static u32 compat_get_it_state(struct pt_regs *regs)
-{
-	u32 it, pstate = regs->pstate;
-
-	it  = (pstate & PSTATE_IT_1_0_MASK) >> PSTATE_IT_1_0_SHIFT;
-	it |= ((pstate & PSTATE_IT_7_2_MASK) >> PSTATE_IT_7_2_SHIFT) << 2;
-
-	return it;
-}
-
-static void compat_set_it_state(struct pt_regs *regs, u32 it)
-{
-	u32 pstate_it;
-
-	pstate_it  = (it << PSTATE_IT_1_0_SHIFT) & PSTATE_IT_1_0_MASK;
-	pstate_it |= ((it >> 2) << PSTATE_IT_7_2_SHIFT) & PSTATE_IT_7_2_MASK;
-
-	regs->pstate &= ~PSR_AA32_IT_MASK;
-	regs->pstate |= pstate_it;
-}
-
 static bool cp15_cond_valid(unsigned int esr, struct pt_regs *regs)
 {
 	int cond;
@@ -614,42 +654,12 @@ static bool cp15_cond_valid(unsigned int esr, struct pt_regs *regs)
 	return aarch32_opcode_cond_checks[cond](regs->pstate);
 }
 
-static void advance_itstate(struct pt_regs *regs)
-{
-	u32 it;
-
-	/* ARM mode */
-	if (!(regs->pstate & PSR_AA32_T_BIT) ||
-	    !(regs->pstate & PSR_AA32_IT_MASK))
-		return;
-
-	it  = compat_get_it_state(regs);
-
-	/*
-	 * If this is the last instruction of the block, wipe the IT
-	 * state. Otherwise advance it.
-	 */
-	if (!(it & 7))
-		it = 0;
-	else
-		it = (it & 0xe0) | ((it << 1) & 0x1f);
-
-	compat_set_it_state(regs, it);
-}
-
-static void arm64_compat_skip_faulting_instruction(struct pt_regs *regs,
-						   unsigned int sz)
-{
-	advance_itstate(regs);
-	arm64_skip_faulting_instruction(regs, sz);
-}
-
 static void compat_cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
 {
 	int reg = (esr & ESR_ELx_CP15_32_ISS_RT_MASK) >> ESR_ELx_CP15_32_ISS_RT_SHIFT;
 
 	pt_regs_write_reg(regs, reg, arch_timer_get_rate());
-	arm64_compat_skip_faulting_instruction(regs, 4);
+	arm64_skip_faulting_instruction(regs, 4);
 }
 
 static const struct sys64_hook cp15_32_hooks[] = {
@@ -669,7 +679,7 @@ static void compat_cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
 
 	pt_regs_write_reg(regs, rt, lower_32_bits(val));
 	pt_regs_write_reg(regs, rt2, upper_32_bits(val));
-	arm64_compat_skip_faulting_instruction(regs, 4);
+	arm64_skip_faulting_instruction(regs, 4);
 }
 
 static const struct sys64_hook cp15_64_hooks[] = {
@@ -690,7 +700,7 @@ void do_cp15instr(unsigned int esr, struct pt_regs *regs)
 		 * There is no T16 variant of a CP access, so we
 		 * always advance PC by 4 bytes.
 		 */
-		arm64_compat_skip_faulting_instruction(regs, 4);
+		arm64_skip_faulting_instruction(regs, 4);
 		return;
 	}
 
@@ -753,6 +763,7 @@ static const char *esr_class_str[] = {
 	[ESR_ELx_EC_CP10_ID]		= "CP10 MRC/VMRS",
 	[ESR_ELx_EC_PAC]		= "PAC",
 	[ESR_ELx_EC_CP14_64]		= "CP14 MCRR/MRRC",
+	[ESR_ELx_EC_BTI]		= "BTI",
 	[ESR_ELx_EC_ILL]		= "PSTATE.IL",
 	[ESR_ELx_EC_SVC32]		= "SVC (AArch32)",
 	[ESR_ELx_EC_HVC32]		= "HVC (AArch32)",
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index f3eea5e20a41..d51a898fd60f 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -136,6 +136,7 @@ static int __setup_additional_pages(enum vdso_abi abi,
 				    int uses_interp)
 {
 	unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
+	unsigned long gp_flags = 0;
 	void *ret;
 
 	vdso_text_len = vdso_info[abi].vdso_pages << PAGE_SHIFT;
@@ -154,10 +155,13 @@ static int __setup_additional_pages(enum vdso_abi abi,
 	if (IS_ERR(ret))
 		goto up_fail;
 
+	if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && system_supports_bti())
+		gp_flags = VM_ARM64_BTI;
+
 	vdso_base += PAGE_SIZE;
 	mm->context.vdso = (void *)vdso_base;
 	ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
-				       VM_READ|VM_EXEC|
+				       VM_READ|VM_EXEC|gp_flags|
 				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
 				       vdso_info[abi].cm);
 	if (IS_ERR(ret))
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index 95e9e444ca93..fccd67d07c8c 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -17,12 +17,14 @@ obj-vdso := vgettimeofday.o note.o sigreturn.o
 targets := $(obj-vdso) vdso.so vdso.so.dbg
 obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
 
+btildflags-$(CONFIG_ARM64_BTI_KERNEL) += -z force-bti
+
 # -Bsymbolic has been added for consistency with arm, the compat vDSO and
 # potential future proofing if we end up with internal calls to the exported
 # routines, as x86 does (see 6f121e548f83 ("x86, vdso: Reimplement vdso.so
 # preparation in build-time C")).
 ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \
-		-Bsymbolic --eh-frame-hdr --build-id -n -T
+		-Bsymbolic --eh-frame-hdr --build-id -n $(btildflags-y) -T
 
 ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
 ccflags-y += -DDISABLE_BRANCH_PROFILING
diff --git a/arch/arm64/kernel/vdso/note.S b/arch/arm64/kernel/vdso/note.S
index 0ce6ec75a525..3d4e82290c80 100644
--- a/arch/arm64/kernel/vdso/note.S
+++ b/arch/arm64/kernel/vdso/note.S
@@ -12,9 +12,12 @@
 #include <linux/version.h>
 #include <linux/elfnote.h>
 #include <linux/build-salt.h>
+#include <asm/assembler.h>
 
 ELFNOTE_START(Linux, 0, "a")
 	.long LINUX_VERSION_CODE
 ELFNOTE_END
 
 BUILD_SALT
+
+emit_aarch64_feature_1_and
diff --git a/arch/arm64/kernel/vdso/sigreturn.S b/arch/arm64/kernel/vdso/sigreturn.S
index 12324863d5c2..620a3ef837b7 100644
--- a/arch/arm64/kernel/vdso/sigreturn.S
+++ b/arch/arm64/kernel/vdso/sigreturn.S
@@ -1,7 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Sigreturn trampoline for returning from a signal when the SA_RESTORER
- * flag is not set.
+ * flag is not set. It serves primarily as a hall of shame for crappy
+ * unwinders and features an exciting but mysterious NOP instruction.
+ *
+ * It's also fragile as hell, so please think twice before changing anything
+ * in here.
  *
  * Copyright (C) 2012 ARM Limited
  *
@@ -9,18 +13,54 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/unistd.h>
 
 	.text
 
-	nop
-SYM_FUNC_START(__kernel_rt_sigreturn)
+/* Ensure that the mysterious NOP can be associated with a function. */
 	.cfi_startproc
+
+/*
+ * .cfi_signal_frame causes the corresponding Frame Description Entry in the
+ * .eh_frame section to be annotated as a signal frame. This allows DWARF
+ * unwinders (e.g. libstdc++) to implement _Unwind_GetIPInfo(), which permits
+ * unwinding out of the signal trampoline without the need for the mysterious
+ * NOP.
+ */
 	.cfi_signal_frame
-	.cfi_def_cfa	x29, 0
-	.cfi_offset	x29, 0 * 8
-	.cfi_offset	x30, 1 * 8
+
+/*
+ * Tell the unwinder where to locate the frame record linking back to the
+ * interrupted context. We don't provide unwind info for registers other
+ * than the frame pointer and the link register here; in practice, this
+ * is sufficient for unwinding in C/C++ based runtimes and the values in
+ * the sigcontext may have been modified by this point anyway. Debuggers
+ * already have baked-in strategies for attempting to unwind out of signals.
+ */
+	.cfi_def_cfa    x29, 0
+	.cfi_offset     x29, 0 * 8
+	.cfi_offset     x30, 1 * 8
+
+/*
+ * This mysterious NOP is required for some unwinders (e.g. libc++) that
+ * unconditionally subtract one from the result of _Unwind_GetIP() in order to
+ * identify the calling function.
+ * Hack borrowed from arch/powerpc/kernel/vdso64/sigtramp.S.
+ */
+	nop	// Mysterious NOP
+
+/*
+ * GDB relies on being able to identify the sigreturn instruction sequence to
+ * unwind from signal handlers. We cannot, therefore, use SYM_FUNC_START()
+ * here, as it will emit a BTI C instruction and break the unwinder. Thankfully,
+ * this function is only ever called from a RET and so omitting the landing pad
+ * is perfectly fine.
+ */
+SYM_CODE_START(__kernel_rt_sigreturn)
 	mov	x8, #__NR_rt_sigreturn
 	svc	#0
 	.cfi_endproc
-SYM_FUNC_END(__kernel_rt_sigreturn)
+SYM_CODE_END(__kernel_rt_sigreturn)
+
+emit_aarch64_feature_1_and
diff --git a/arch/arm64/kernel/vdso/vdso.S b/arch/arm64/kernel/vdso/vdso.S
index d1414fee5274..c4b1990bf2be 100644
--- a/arch/arm64/kernel/vdso/vdso.S
+++ b/arch/arm64/kernel/vdso/vdso.S
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/linkage.h>
 #include <linux/const.h>
+#include <asm/assembler.h>
 #include <asm/page.h>
 
 	.globl vdso_start, vdso_end
@@ -19,3 +20,5 @@ vdso_start:
 vdso_end:
 
 	.previous
+
+emit_aarch64_feature_1_and
diff --git a/arch/arm64/kernel/vdso32/sigreturn.S b/arch/arm64/kernel/vdso32/sigreturn.S
index 620524969696..b0091064c3d6 100644
--- a/arch/arm64/kernel/vdso32/sigreturn.S
+++ b/arch/arm64/kernel/vdso32/sigreturn.S
@@ -3,6 +3,9 @@
  * This file provides both A32 and T32 versions, in accordance with the
  * arm sigreturn code.
  *
+ * Please read the comments in arch/arm64/kernel/vdso/sigreturn.S to
+ * understand some of the craziness in here.
+ *
  * Copyright (C) 2018 ARM Limited
  */
 
@@ -17,39 +20,39 @@
 	.save {r0-r15}
 	.pad #COMPAT_SIGFRAME_REGS_OFFSET
 	nop
-SYM_FUNC_START(__kernel_sigreturn_arm)
+SYM_CODE_START(__kernel_sigreturn_arm)
 	mov r7, #__NR_compat_sigreturn
 	svc #0
 	.fnend
-SYM_FUNC_END(__kernel_sigreturn_arm)
+SYM_CODE_END(__kernel_sigreturn_arm)
 
 	.fnstart
 	.save {r0-r15}
 	.pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
 	nop
-SYM_FUNC_START(__kernel_rt_sigreturn_arm)
+SYM_CODE_START(__kernel_rt_sigreturn_arm)
 	mov r7, #__NR_compat_rt_sigreturn
 	svc #0
 	.fnend
-SYM_FUNC_END(__kernel_rt_sigreturn_arm)
+SYM_CODE_END(__kernel_rt_sigreturn_arm)
 
 	.thumb
 	.fnstart
 	.save {r0-r15}
 	.pad #COMPAT_SIGFRAME_REGS_OFFSET
 	nop
-SYM_FUNC_START(__kernel_sigreturn_thumb)
+SYM_CODE_START(__kernel_sigreturn_thumb)
 	mov r7, #__NR_compat_sigreturn
 	svc #0
 	.fnend
-SYM_FUNC_END(__kernel_sigreturn_thumb)
+SYM_CODE_END(__kernel_sigreturn_thumb)
 
 	.fnstart
 	.save {r0-r15}
 	.pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
 	nop
-SYM_FUNC_START(__kernel_rt_sigreturn_thumb)
+SYM_CODE_START(__kernel_rt_sigreturn_thumb)
 	mov r7, #__NR_compat_rt_sigreturn
 	svc #0
 	.fnend
-SYM_FUNC_END(__kernel_rt_sigreturn_thumb)
+SYM_CODE_END(__kernel_rt_sigreturn_thumb)
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index 860c00ec8bd3..78163b7a7dde 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -146,6 +146,11 @@ static const struct prot_bits pte_bits[] = {
 		.set	= "UXN",
 		.clear	= "   ",
 	}, {
+		.mask	= PTE_GP,
+		.val	= PTE_GP,
+		.set	= "GP",
+		.clear	= "  ",
+	}, {
 		.mask	= PTE_ATTRINDX_MASK,
 		.val	= PTE_ATTRINDX(MT_DEVICE_nGnRnE),
 		.set	= "DEVICE/nGnRnE",
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index a374e4f51a62..c299b73dd5e4 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -610,6 +610,22 @@ core_initcall(map_entry_trampoline);
 #endif
 
 /*
+ * Open coded check for BTI, only for use to determine configuration
+ * for early mappings for before the cpufeature code has run.
+ */
+static bool arm64_early_this_cpu_has_bti(void)
+{
+	u64 pfr1;
+
+	if (!IS_ENABLED(CONFIG_ARM64_BTI_KERNEL))
+		return false;
+
+	pfr1 = read_sysreg_s(SYS_ID_AA64PFR1_EL1);
+	return cpuid_feature_extract_unsigned_field(pfr1,
+						    ID_AA64PFR1_BT_SHIFT);
+}
+
+/*
  * Create fine-grained mappings for the kernel.
  */
 static void __init map_kernel(pgd_t *pgdp)
@@ -625,6 +641,14 @@ static void __init map_kernel(pgd_t *pgdp)
 	pgprot_t text_prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
 
 	/*
+	 * If we have a CPU that supports BTI and a kernel built for
+	 * BTI then mark the kernel executable text as guarded pages
+	 * now so we don't have to rewrite the page tables later.
+	 */
+	if (arm64_early_this_cpu_has_bti())
+		text_prot = __pgprot_modify(text_prot, PTE_GP, PTE_GP);
+
+	/*
 	 * Only rodata will be remapped with different permissions later on,
 	 * all other segments are allowed to use contiguous mappings.
 	 */
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 250c49008d73..bde08090b838 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -126,13 +126,13 @@ int set_memory_nx(unsigned long addr, int numpages)
 {
 	return change_memory_common(addr, numpages,
 					__pgprot(PTE_PXN),
-					__pgprot(0));
+					__pgprot(PTE_MAYBE_GP));
 }
 
 int set_memory_x(unsigned long addr, int numpages)
 {
 	return change_memory_common(addr, numpages,
-					__pgprot(0),
+					__pgprot(PTE_MAYBE_GP),
 					__pgprot(PTE_PXN));
 }
 
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index 923ae7ff68c8..cc0cf0f5c7c3 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -211,4 +211,12 @@
 /* Rn & imm; set condition flags */
 #define A64_TST_I(sf, Rn, imm) A64_ANDS_I(sf, A64_ZR, Rn, imm)
 
+/* HINTs */
+#define A64_HINT(x) aarch64_insn_gen_hint(x)
+
+/* BTI */
+#define A64_BTI_C  A64_HINT(AARCH64_INSN_HINT_BTIC)
+#define A64_BTI_J  A64_HINT(AARCH64_INSN_HINT_BTIJ)
+#define A64_BTI_JC A64_HINT(AARCH64_INSN_HINT_BTIJC)
+
 #endif /* _BPF_JIT_H */
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 561a2fea9cdd..3cb25b43b368 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -177,7 +177,11 @@ static bool is_addsub_imm(u32 imm)
 #define STACK_ALIGN(sz) (((sz) + 15) & ~15)
 
 /* Tail call offset to jump into */
+#if IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)
+#define PROLOGUE_OFFSET 8
+#else
 #define PROLOGUE_OFFSET 7
+#endif
 
 static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 {
@@ -214,6 +218,10 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 	 *
 	 */
 
+	/* BTI landing pad */
+	if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL))
+		emit(A64_BTI_C, ctx);
+
 	/* Save FP and LR registers to stay align with ARM64 AAPCS */
 	emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
 	emit(A64_MOV(1, A64_FP, A64_SP), ctx);
@@ -236,6 +244,10 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 				    cur_offset, PROLOGUE_OFFSET);
 			return -1;
 		}
+
+		/* BTI landing pad for the tail call, done with a BR */
+		if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL))
+			emit(A64_BTI_J, ctx);
 	}
 
 	ctx->stack_size = STACK_ALIGN(prog->aux->stack_depth);