diff --git a/arch/arm64/include/asm/extable.h b/arch/arm64/include/asm/extable.h
index 56a4f68b262e..840a35ed92ec 100644
--- a/arch/arm64/include/asm/extable.h
+++ b/arch/arm64/include/asm/extable.h
@@ -22,5 +22,17 @@ struct exception_table_entry
 
 #define ARCH_HAS_RELATIVE_EXTABLE
 
+#ifdef CONFIG_BPF_JIT
+int arm64_bpf_fixup_exception(const struct exception_table_entry *ex,
+			      struct pt_regs *regs);
+#else /* !CONFIG_BPF_JIT */
+static inline
+int arm64_bpf_fixup_exception(const struct exception_table_entry *ex,
+			      struct pt_regs *regs)
+{
+	return 0;
+}
+#endif /* !CONFIG_BPF_JIT */
+
 extern int fixup_exception(struct pt_regs *regs);
 #endif
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 310e47d54d81..74225fb3adea 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -49,13 +49,37 @@ 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 {
@@ -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/kernel/insn.c b/arch/arm64/kernel/insn.c
index 09a0463279f7..d8b39131b010 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -571,7 +571,7 @@ 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/mm/extable.c b/arch/arm64/mm/extable.c
index 81e694af5f8c..eee1732ab6cd 100644
--- a/arch/arm64/mm/extable.c
+++ b/arch/arm64/mm/extable.c
@@ -11,8 +11,14 @@ int fixup_exception(struct pt_regs *regs)
 	const struct exception_table_entry *fixup;
 
 	fixup = search_exception_tables(instruction_pointer(regs));
-	if (fixup)
-		regs->pc = (unsigned long)&fixup->fixup + fixup->fixup;
+	if (!fixup)
+		return 0;
 
-	return fixup != NULL;
+	if (IS_ENABLED(CONFIG_BPF_JIT) &&
+	    regs->pc >= BPF_JIT_REGION_START &&
+	    regs->pc < BPF_JIT_REGION_END)
+		return arm64_bpf_fixup_exception(fixup, regs);
+
+	regs->pc = (unsigned long)&fixup->fixup + fixup->fixup;
+	return 1;
 }
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index 76606e87233f..b028e6d7e9d3 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -111,6 +111,14 @@
 /* Rd = Rn OP imm12 */
 #define A64_ADD_I(sf, Rd, Rn, imm12) A64_ADDSUB_IMM(sf, Rd, Rn, imm12, ADD)
 #define A64_SUB_I(sf, Rd, Rn, imm12) A64_ADDSUB_IMM(sf, Rd, Rn, imm12, SUB)
+#define A64_ADDS_I(sf, Rd, Rn, imm12) \
+	A64_ADDSUB_IMM(sf, Rd, Rn, imm12, ADD_SETFLAGS)
+#define A64_SUBS_I(sf, Rd, Rn, imm12) \
+	A64_ADDSUB_IMM(sf, Rd, Rn, imm12, SUB_SETFLAGS)
+/* Rn + imm12; set condition flags */
+#define A64_CMN_I(sf, Rn, imm12) A64_ADDS_I(sf, A64_ZR, Rn, imm12)
+/* Rn - imm12; set condition flags */
+#define A64_CMP_I(sf, Rn, imm12) A64_SUBS_I(sf, A64_ZR, Rn, imm12)
 /* Rd = Rn */
 #define A64_MOV(sf, Rd, Rn) A64_ADD_I(sf, Rd, Rn, 0)
 
@@ -182,6 +190,9 @@
 /* Rd = Ra + Rn * Rm */
 #define A64_MADD(sf, Rd, Ra, Rn, Rm) aarch64_insn_gen_data3(Rd, Ra, Rn, Rm, \
 	A64_VARIANT(sf), AARCH64_INSN_DATA3_MADD)
+/* Rd = Ra - Rn * Rm */
+#define A64_MSUB(sf, Rd, Ra, Rn, Rm) aarch64_insn_gen_data3(Rd, Ra, Rn, Rm, \
+	A64_VARIANT(sf), AARCH64_INSN_DATA3_MSUB)
 /* Rd = Rn * Rm */
 #define A64_MUL(sf, Rd, Rn, Rm) A64_MADD(sf, Rd, A64_ZR, Rn, Rm)
 
@@ -197,4 +208,26 @@
 /* Rn & Rm; set condition flags */
 #define A64_TST(sf, Rn, Rm) A64_ANDS(sf, A64_ZR, Rn, Rm)
 
+/* Logical (immediate) */
+#define A64_LOGIC_IMM(sf, Rd, Rn, imm, type) ({ \
+	u64 imm64 = (sf) ? (u64)imm : (u64)(u32)imm; \
+	aarch64_insn_gen_logical_immediate(AARCH64_INSN_LOGIC_##type, \
+		A64_VARIANT(sf), Rn, Rd, imm64); \
+})
+/* Rd = Rn OP imm */
+#define A64_AND_I(sf, Rd, Rn, imm) A64_LOGIC_IMM(sf, Rd, Rn, imm, AND)
+#define A64_ORR_I(sf, Rd, Rn, imm) A64_LOGIC_IMM(sf, Rd, Rn, imm, ORR)
+#define A64_EOR_I(sf, Rd, Rn, imm) A64_LOGIC_IMM(sf, Rd, Rn, imm, EOR)
+#define A64_ANDS_I(sf, Rd, Rn, imm) A64_LOGIC_IMM(sf, Rd, Rn, imm, AND_SETFLAGS)
+/* 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 5ebd0c4c5e59..3b10d951dc80 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -18,6 +18,7 @@
 
 #define pr_fmt(fmt) "bpf_jit: " fmt
 
+#include <linux/bitfield.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
 #include <linux/printk.h>
@@ -68,6 +69,7 @@ struct jit_ctx {
 	int idx;
 	int epilogue_offset;
 	int *offset;
+	int exentry_idx;
 	__le32 *image;
 	u32 stack_size;
 };
@@ -135,10 +137,9 @@ static inline void emit_a64_mov_i64(const int reg, const u64 val,
 }
 
 /*
- * This is an unoptimized 64 immediate emission used for BPF to BPF call
- * addresses. It will always do a full 64 bit decomposition as otherwise
- * more complexity in the last extra pass is required since we previously
- * reserved 4 instructions for the address.
+ * Kernel addresses in the vmalloc space use at most 48 bits, and the
+ * remaining bits are guaranteed to be 0x1. So we can compose the address
+ * with a fixed length movn/movk/movk sequence.
  */
 static inline void emit_addr_mov_i64(const int reg, const u64 val,
 				     struct jit_ctx *ctx)
@@ -146,22 +147,25 @@ static inline void emit_addr_mov_i64(const int reg, const u64 val,
 	u64 tmp = val;
 	int shift = 0;
 
-	emit(A64_MOVZ(1, reg, tmp & 0xffff, shift), ctx);
-	for (;shift < 48;) {
+	emit(A64_MOVN(1, reg, ~tmp & 0xffff, shift), ctx);
+	while (shift < 32) {
 		tmp >>= 16;
 		shift += 16;
 		emit(A64_MOVK(1, reg, tmp & 0xffff, shift), ctx);
 	}
 }
 
-static inline int bpf2a64_offset(int bpf_to, int bpf_from,
+static inline int bpf2a64_offset(int bpf_insn, int off,
 				 const struct jit_ctx *ctx)
 {
-	int to = ctx->offset[bpf_to];
-	/* -1 to account for the Branch instruction */
-	int from = ctx->offset[bpf_from] - 1;
-
-	return to - from;
+	/* BPF JMP offset is relative to the next instruction */
+	bpf_insn++;
+	/*
+	 * Whereas arm64 branch instructions encode the offset
+	 * from the branch itself, so we must subtract 1 from the
+	 * instruction offset.
+	 */
+	return ctx->offset[bpf_insn + off] - (ctx->offset[bpf_insn] - 1);
 }
 
 static void jit_fill_hole(void *area, unsigned int size)
@@ -180,11 +184,21 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 	return to - from;
 }
 
+static bool is_addsub_imm(u32 imm)
+{
+	/* Either imm12 or shifted imm12. */
+	return !(imm & ~0xfff) || !(imm & ~0xfff000);
+}
+
 /* Stack must be multiples of 16B */
 #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)
 {
@@ -221,6 +235,10 @@ 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);
@@ -243,6 +261,10 @@ 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);
@@ -346,13 +368,75 @@ static void build_epilogue(struct jit_ctx *ctx)
 	emit(A64_RET(A64_LR), ctx);
 }
 
+#define BPF_FIXUP_OFFSET_MASK	GENMASK(26, 0)
+#define BPF_FIXUP_REG_MASK	GENMASK(31, 27)
+
+int arm64_bpf_fixup_exception(const struct exception_table_entry *ex,
+			      struct pt_regs *regs)
+{
+	off_t offset = FIELD_GET(BPF_FIXUP_OFFSET_MASK, ex->fixup);
+	int dst_reg = FIELD_GET(BPF_FIXUP_REG_MASK, ex->fixup);
+
+	regs->regs[dst_reg] = 0;
+	regs->pc = (unsigned long)&ex->fixup - offset;
+	return 1;
+}
+
+/* For accesses to BTF pointers, add an entry to the exception table */
+static int add_exception_handler(const struct bpf_insn *insn,
+				 struct jit_ctx *ctx,
+				 int dst_reg)
+{
+	off_t offset;
+	unsigned long pc;
+	struct exception_table_entry *ex;
+
+	if (!ctx->image)
+		/* First pass */
+		return 0;
+
+	if (BPF_MODE(insn->code) != BPF_PROBE_MEM)
+		return 0;
+
+	if (!ctx->prog->aux->extable ||
+	    WARN_ON_ONCE(ctx->exentry_idx >= ctx->prog->aux->num_exentries))
+		return -EINVAL;
+
+	ex = &ctx->prog->aux->extable[ctx->exentry_idx];
+	pc = (unsigned long)&ctx->image[ctx->idx - 1];
+
+	offset = pc - (long)&ex->insn;
+	if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN))
+		return -ERANGE;
+	ex->insn = offset;
+
+	/*
+	 * Since the extable follows the program, the fixup offset is always
+	 * negative and limited to BPF_JIT_REGION_SIZE. Store a positive value
+	 * to keep things simple, and put the destination register in the upper
+	 * bits. We don't need to worry about buildtime or runtime sort
+	 * modifying the upper bits because the table is already sorted, and
+	 * isn't part of the main exception table.
+	 */
+	offset = (long)&ex->fixup - (pc + AARCH64_INSN_SIZE);
+	if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, offset))
+		return -ERANGE;
+
+	ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, offset) |
+		    FIELD_PREP(BPF_FIXUP_REG_MASK, dst_reg);
+
+	ctx->exentry_idx++;
+	return 0;
+}
+
 /* JITs an eBPF instruction.
  * Returns:
  * 0  - successfully JITed an 8-byte eBPF instruction.
  * >0 - successfully JITed a 16-byte eBPF instruction.
  * <0 - failed to JIT.
  */
-static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
+static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
+		      bool extra_pass)
 {
 	const u8 code = insn->code;
 	const u8 dst = bpf2a64[insn->dst_reg];
@@ -363,10 +447,13 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	const s16 off = insn->off;
 	const s32 imm = insn->imm;
 	const int i = insn - ctx->prog->insnsi;
-	const bool is64 = BPF_CLASS(code) == BPF_ALU64;
+	const bool is64 = BPF_CLASS(code) == BPF_ALU64 ||
+			  BPF_CLASS(code) == BPF_JMP;
 	const bool isdw = BPF_SIZE(code) == BPF_DW;
 	u8 jmp_cond, reg;
 	s32 jmp_offset;
+	u32 a64_insn;
+	int ret;
 
 #define check_imm(bits, imm) do {				\
 	if ((((imm) > 0) && ((imm) >> (bits))) ||		\
@@ -420,8 +507,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			break;
 		case BPF_MOD:
 			emit(A64_UDIV(is64, tmp, dst, src), ctx);
-			emit(A64_MUL(is64, tmp, tmp, src), ctx);
-			emit(A64_SUB(is64, dst, dst, tmp), ctx);
+			emit(A64_MSUB(is64, dst, dst, tmp, src), ctx);
 			break;
 		}
 		break;
@@ -490,28 +576,55 @@ emit_bswap_uxt:
 	/* dst = dst OP imm */
 	case BPF_ALU | BPF_ADD | BPF_K:
 	case BPF_ALU64 | BPF_ADD | BPF_K:
-		emit_a64_mov_i(is64, tmp, imm, ctx);
-		emit(A64_ADD(is64, dst, dst, tmp), ctx);
+		if (is_addsub_imm(imm)) {
+			emit(A64_ADD_I(is64, dst, dst, imm), ctx);
+		} else if (is_addsub_imm(-imm)) {
+			emit(A64_SUB_I(is64, dst, dst, -imm), ctx);
+		} else {
+			emit_a64_mov_i(is64, tmp, imm, ctx);
+			emit(A64_ADD(is64, dst, dst, tmp), ctx);
+		}
 		break;
 	case BPF_ALU | BPF_SUB | BPF_K:
 	case BPF_ALU64 | BPF_SUB | BPF_K:
-		emit_a64_mov_i(is64, tmp, imm, ctx);
-		emit(A64_SUB(is64, dst, dst, tmp), ctx);
+		if (is_addsub_imm(imm)) {
+			emit(A64_SUB_I(is64, dst, dst, imm), ctx);
+		} else if (is_addsub_imm(-imm)) {
+			emit(A64_ADD_I(is64, dst, dst, -imm), ctx);
+		} else {
+			emit_a64_mov_i(is64, tmp, imm, ctx);
+			emit(A64_SUB(is64, dst, dst, tmp), ctx);
+		}
 		break;
 	case BPF_ALU | BPF_AND | BPF_K:
 	case BPF_ALU64 | BPF_AND | BPF_K:
-		emit_a64_mov_i(is64, tmp, imm, ctx);
-		emit(A64_AND(is64, dst, dst, tmp), ctx);
+		a64_insn = A64_AND_I(is64, dst, dst, imm);
+		if (a64_insn != AARCH64_BREAK_FAULT) {
+			emit(a64_insn, ctx);
+		} else {
+			emit_a64_mov_i(is64, tmp, imm, ctx);
+			emit(A64_AND(is64, dst, dst, tmp), ctx);
+		}
 		break;
 	case BPF_ALU | BPF_OR | BPF_K:
 	case BPF_ALU64 | BPF_OR | BPF_K:
-		emit_a64_mov_i(is64, tmp, imm, ctx);
-		emit(A64_ORR(is64, dst, dst, tmp), ctx);
+		a64_insn = A64_ORR_I(is64, dst, dst, imm);
+		if (a64_insn != AARCH64_BREAK_FAULT) {
+			emit(a64_insn, ctx);
+		} else {
+			emit_a64_mov_i(is64, tmp, imm, ctx);
+			emit(A64_ORR(is64, dst, dst, tmp), ctx);
+		}
 		break;
 	case BPF_ALU | BPF_XOR | BPF_K:
 	case BPF_ALU64 | BPF_XOR | BPF_K:
-		emit_a64_mov_i(is64, tmp, imm, ctx);
-		emit(A64_EOR(is64, dst, dst, tmp), ctx);
+		a64_insn = A64_EOR_I(is64, dst, dst, imm);
+		if (a64_insn != AARCH64_BREAK_FAULT) {
+			emit(a64_insn, ctx);
+		} else {
+			emit_a64_mov_i(is64, tmp, imm, ctx);
+			emit(A64_EOR(is64, dst, dst, tmp), ctx);
+		}
 		break;
 	case BPF_ALU | BPF_MUL | BPF_K:
 	case BPF_ALU64 | BPF_MUL | BPF_K:
@@ -527,8 +640,7 @@ emit_bswap_uxt:
 	case BPF_ALU64 | BPF_MOD | BPF_K:
 		emit_a64_mov_i(is64, tmp2, imm, ctx);
 		emit(A64_UDIV(is64, tmp, dst, tmp2), ctx);
-		emit(A64_MUL(is64, tmp, tmp, tmp2), ctx);
-		emit(A64_SUB(is64, dst, dst, tmp), ctx);
+		emit(A64_MSUB(is64, dst, dst, tmp, tmp2), ctx);
 		break;
 	case BPF_ALU | BPF_LSH | BPF_K:
 	case BPF_ALU64 | BPF_LSH | BPF_K:
@@ -545,7 +657,7 @@ emit_bswap_uxt:
 
 	/* JUMP off */
 	case BPF_JMP | BPF_JA:
-		jmp_offset = bpf2a64_offset(i + off, i, ctx);
+		jmp_offset = bpf2a64_offset(i, off, ctx);
 		check_imm26(jmp_offset);
 		emit(A64_B(jmp_offset), ctx);
 		break;
@@ -560,9 +672,19 @@ emit_bswap_uxt:
 	case BPF_JMP | BPF_JSLT | BPF_X:
 	case BPF_JMP | BPF_JSGE | BPF_X:
 	case BPF_JMP | BPF_JSLE | BPF_X:
-		emit(A64_CMP(1, dst, src), ctx);
+	case BPF_JMP32 | BPF_JEQ | BPF_X:
+	case BPF_JMP32 | BPF_JGT | BPF_X:
+	case BPF_JMP32 | BPF_JLT | BPF_X:
+	case BPF_JMP32 | BPF_JGE | BPF_X:
+	case BPF_JMP32 | BPF_JLE | BPF_X:
+	case BPF_JMP32 | BPF_JNE | BPF_X:
+	case BPF_JMP32 | BPF_JSGT | BPF_X:
+	case BPF_JMP32 | BPF_JSLT | BPF_X:
+	case BPF_JMP32 | BPF_JSGE | BPF_X:
+	case BPF_JMP32 | BPF_JSLE | BPF_X:
+		emit(A64_CMP(is64, dst, src), ctx);
 emit_cond_jmp:
-		jmp_offset = bpf2a64_offset(i + off, i, ctx);
+		jmp_offset = bpf2a64_offset(i, off, ctx);
 		check_imm19(jmp_offset);
 		switch (BPF_OP(code)) {
 		case BPF_JEQ:
@@ -602,7 +724,8 @@ emit_cond_jmp:
 		emit(A64_B_(jmp_cond, jmp_offset), ctx);
 		break;
 	case BPF_JMP | BPF_JSET | BPF_X:
-		emit(A64_TST(1, dst, src), ctx);
+	case BPF_JMP32 | BPF_JSET | BPF_X:
+		emit(A64_TST(is64, dst, src), ctx);
 		goto emit_cond_jmp;
 	/* IF (dst COND imm) JUMP off */
 	case BPF_JMP | BPF_JEQ | BPF_K:
@@ -615,23 +738,47 @@ emit_cond_jmp:
 	case BPF_JMP | BPF_JSLT | BPF_K:
 	case BPF_JMP | BPF_JSGE | BPF_K:
 	case BPF_JMP | BPF_JSLE | BPF_K:
-		emit_a64_mov_i(1, tmp, imm, ctx);
-		emit(A64_CMP(1, dst, tmp), ctx);
+	case BPF_JMP32 | BPF_JEQ | BPF_K:
+	case BPF_JMP32 | BPF_JGT | BPF_K:
+	case BPF_JMP32 | BPF_JLT | BPF_K:
+	case BPF_JMP32 | BPF_JGE | BPF_K:
+	case BPF_JMP32 | BPF_JLE | BPF_K:
+	case BPF_JMP32 | BPF_JNE | BPF_K:
+	case BPF_JMP32 | BPF_JSGT | BPF_K:
+	case BPF_JMP32 | BPF_JSLT | BPF_K:
+	case BPF_JMP32 | BPF_JSGE | BPF_K:
+	case BPF_JMP32 | BPF_JSLE | BPF_K:
+		if (is_addsub_imm(imm)) {
+			emit(A64_CMP_I(is64, dst, imm), ctx);
+		} else if (is_addsub_imm(-imm)) {
+			emit(A64_CMN_I(is64, dst, -imm), ctx);
+		} else {
+			emit_a64_mov_i(is64, tmp, imm, ctx);
+			emit(A64_CMP(is64, dst, tmp), ctx);
+		}
 		goto emit_cond_jmp;
 	case BPF_JMP | BPF_JSET | BPF_K:
-		emit_a64_mov_i(1, tmp, imm, ctx);
-		emit(A64_TST(1, dst, tmp), ctx);
+	case BPF_JMP32 | BPF_JSET | BPF_K:
+		a64_insn = A64_TST_I(is64, dst, imm);
+		if (a64_insn != AARCH64_BREAK_FAULT) {
+			emit(a64_insn, ctx);
+		} else {
+			emit_a64_mov_i(is64, tmp, imm, ctx);
+			emit(A64_TST(is64, dst, tmp), ctx);
+		}
 		goto emit_cond_jmp;
 	/* function call */
 	case BPF_JMP | BPF_CALL:
 	{
 		const u8 r0 = bpf2a64[BPF_REG_0];
-		const u64 func = (u64)__bpf_call_base + imm;
+		bool func_addr_fixed;
+		u64 func_addr;
 
-		if (ctx->prog->is_func)
-			emit_addr_mov_i64(tmp, func, ctx);
-		else
-			emit_a64_mov_i64(tmp, func, ctx);
+		ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
+					    &func_addr, &func_addr_fixed);
+		if (ret < 0)
+			return ret;
+		emit_addr_mov_i64(tmp, func_addr, ctx);
 		emit(A64_BLR(tmp), ctx);
 		emit(A64_MOV(1, r0, A64_R(0)), ctx);
 		break;
@@ -669,6 +816,10 @@ emit_cond_jmp:
 	case BPF_LDX | BPF_MEM | BPF_H:
 	case BPF_LDX | BPF_MEM | BPF_B:
 	case BPF_LDX | BPF_MEM | BPF_DW:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_W:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_H:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_B:
 		emit_a64_mov_i(1, tmp, off, ctx);
 		switch (BPF_SIZE(code)) {
 		case BPF_W:
@@ -684,6 +835,10 @@ emit_cond_jmp:
 			emit(A64_LDR64(dst, src, tmp), ctx);
 			break;
 		}
+
+		ret = add_exception_handler(insn, ctx, dst);
+		if (ret)
+			return ret;
 		break;
 
 	/* speculation barrier */
@@ -784,27 +939,43 @@ emit_cond_jmp:
 	return 0;
 }
 
-static int build_body(struct jit_ctx *ctx)
+static int build_body(struct jit_ctx *ctx, bool extra_pass)
 {
 	const struct bpf_prog *prog = ctx->prog;
 	int i;
 
+	/*
+	 * - offset[0] offset of the end of prologue,
+	 *   start of the 1st instruction.
+	 * - offset[1] - offset of the end of 1st instruction,
+	 *   start of the 2nd instruction
+	 * [....]
+	 * - offset[3] - offset of the end of 3rd instruction,
+	 *   start of 4th instruction
+	 */
 	for (i = 0; i < prog->len; i++) {
 		const struct bpf_insn *insn = &prog->insnsi[i];
 		int ret;
 
-		ret = build_insn(insn, ctx);
+		if (ctx->image == NULL)
+			ctx->offset[i] = ctx->idx;
+		ret = build_insn(insn, ctx, extra_pass);
 		if (ret > 0) {
 			i++;
 			if (ctx->image == NULL)
 				ctx->offset[i] = ctx->idx;
 			continue;
 		}
-		if (ctx->image == NULL)
-			ctx->offset[i] = ctx->idx;
 		if (ret)
 			return ret;
 	}
+	/*
+	 * offset is allocated with prog->len + 1 so fill in
+	 * the last element with the offset after the last
+	 * instruction (end of program)
+	 */
+	if (ctx->image == NULL)
+		ctx->offset[i] = ctx->idx;
 
 	return 0;
 }
@@ -820,6 +991,9 @@ static int validate_code(struct jit_ctx *ctx)
 			return -1;
 	}
 
+	if (WARN_ON_ONCE(ctx->exentry_idx != ctx->prog->aux->num_exentries))
+		return -1;
+
 	return 0;
 }
 
@@ -836,6 +1010,7 @@ struct arm64_jit_data {
 
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
+	int image_size, prog_size, extable_size;
 	struct bpf_prog *tmp, *orig_prog = prog;
 	struct bpf_binary_header *header;
 	struct arm64_jit_data *jit_data;
@@ -843,7 +1018,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	bool tmp_blinded = false;
 	bool extra_pass = false;
 	struct jit_ctx ctx;
-	int image_size;
 	u8 *image_ptr;
 
 	if (!prog->jit_requested)
@@ -874,13 +1048,13 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		image_ptr = jit_data->image;
 		header = jit_data->header;
 		extra_pass = true;
-		image_size = sizeof(u32) * ctx.idx;
+		prog_size = sizeof(u32) * ctx.idx;
 		goto skip_init_ctx;
 	}
 	memset(&ctx, 0, sizeof(ctx));
 	ctx.prog = prog;
 
-	ctx.offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL);
+	ctx.offset = kcalloc(prog->len + 1, sizeof(int), GFP_KERNEL);
 	if (ctx.offset == NULL) {
 		prog = orig_prog;
 		goto out_off;
@@ -889,7 +1063,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	/* 1. Initial fake pass to compute ctx->idx. */
 
 	/* Fake pass to fill in ctx->offset. */
-	if (build_body(&ctx)) {
+	if (build_body(&ctx, extra_pass)) {
 		prog = orig_prog;
 		goto out_off;
 	}
@@ -902,8 +1076,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	ctx.epilogue_offset = ctx.idx;
 	build_epilogue(&ctx);
 
+	extable_size = prog->aux->num_exentries *
+		sizeof(struct exception_table_entry);
+
 	/* Now we know the actual image size. */
-	image_size = sizeof(u32) * ctx.idx;
+	prog_size = sizeof(u32) * ctx.idx;
+	image_size = prog_size + extable_size;
 	header = bpf_jit_binary_alloc(image_size, &image_ptr,
 				      sizeof(u32), jit_fill_hole);
 	if (header == NULL) {
@@ -914,12 +1092,15 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	/* 2. Now, the actual pass. */
 
 	ctx.image = (__le32 *)image_ptr;
+	if (extable_size)
+		prog->aux->extable = (void *)image_ptr + prog_size;
 skip_init_ctx:
 	ctx.idx = 0;
+	ctx.exentry_idx = 0;
 
 	build_prologue(&ctx, was_classic);
 
-	if (build_body(&ctx)) {
+	if (build_body(&ctx, extra_pass)) {
 		bpf_jit_binary_free(header);
 		prog = orig_prog;
 		goto out_off;
@@ -936,7 +1117,7 @@ skip_init_ctx:
 
 	/* And we're done. */
 	if (bpf_jit_enable > 1)
-		bpf_jit_dump(prog->len, image_size, 2, ctx.image);
+		bpf_jit_dump(prog->len, prog_size, 2, ctx.image);
 
 	bpf_flush_icache(header, ctx.image + ctx.idx);
 
@@ -960,9 +1141,10 @@ skip_init_ctx:
 	}
 	prog->bpf_func = (void *)ctx.image;
 	prog->jited = 1;
-	prog->jited_len = image_size;
+	prog->jited_len = prog_size;
 
 	if (!prog->is_func || extra_pass) {
+		bpf_prog_fill_jited_linfo(prog, ctx.offset + 1);
 out_off:
 		kfree(ctx.offset);
 		kfree(jit_data);
@@ -979,7 +1161,7 @@ void *bpf_jit_alloc_exec(unsigned long size)
 {
 	return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,
 				    BPF_JIT_REGION_END, GFP_KERNEL,
-				    PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+				    PAGE_KERNEL, 0, NUMA_NO_NODE,
 				    __builtin_return_address(0));
 }
 
diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index 87e05e436baf..f704a3e18253 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -111,7 +111,7 @@ configfiles=$(wildcard $(srctree)/kernel/configs/$@ $(srctree)/arch/$(SRCARCH)/c
 %.config: $(obj)/conf
 	$(if $(call configfiles),, $(error No configuration exists for this target on this architecture))
 	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m .config $(configfiles)
-	+$(Q)yes "" | $(MAKE) -f $(srctree)/Makefile oldconfig
+	$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
 
 PHONY += kvmconfig
 kvmconfig: kvm_guest.config
diff --git a/techpack/audio/asoc/codecs/wcd_cpe_services.c b/techpack/audio/asoc/codecs/wcd_cpe_services.c
index 0a8e73dc7ff3..88df0d6f2144 100644
--- a/techpack/audio/asoc/codecs/wcd_cpe_services.c
+++ b/techpack/audio/asoc/codecs/wcd_cpe_services.c
@@ -988,7 +988,7 @@ static enum cpe_svc_result broadcast_boot_event(
 static enum cpe_process_result cpe_boot_initialize(struct cpe_info *t_info,
 	enum cpe_svc_result *cpe_rc)
 {
-	enum cpe_process_result rc = CPE_SVC_FAILED;
+	enum cpe_process_result rc = CPE_PROC_FAILED;
 	struct cpe_svc_notification payload;
 	struct cmi_core_svc_event_system_boot *p = NULL;
 
@@ -1992,7 +1992,7 @@ enum cmi_api_result cmi_send_msg(void *message)
 		      GFP_ATOMIC);
 	if (!msg) {
 		CPE_SVC_REL_LOCK(&cpe_d.cpe_api_mutex, "cpe_api");
-		return CPE_SVC_NO_MEMORY;
+		return CMI_API_NO_MEMORY;
 	}
 
 	if (CMI_HDR_GET_OBM_FLAG(hdr) == CMI_OBM_FLAG_OUT_BAND)
@@ -2007,7 +2007,7 @@ enum cmi_api_result cmi_send_msg(void *message)
 	if (!msg->payload) {
 		kfree(msg);
 		CPE_SVC_REL_LOCK(&cpe_d.cpe_api_mutex, "cpe_api");
-		return CPE_SVC_NO_MEMORY;
+		return CMI_API_NO_MEMORY;
 	}
 
 	msg->address = 0;
diff --git a/techpack/data/drivers/rmnet/perf/rmnet_perf_config.c b/techpack/data/drivers/rmnet/perf/rmnet_perf_config.c
index 1b3d4b058f9e..1c0765874c2c 100644
--- a/techpack/data/drivers/rmnet/perf/rmnet_perf_config.c
+++ b/techpack/data/drivers/rmnet/perf/rmnet_perf_config.c
@@ -455,13 +455,13 @@ static struct notifier_block rmnet_perf_dev_notifier __read_mostly = {
 	.priority = 1,
 };
 
-int __init rmnet_perf_init(void)
+static int __init rmnet_perf_init(void)
 {
 	pr_info("%s(): initializing rmnet_perf\n", __func__);
 	return register_netdevice_notifier(&rmnet_perf_dev_notifier);
 }
 
-void __exit rmnet_perf_exit(void)
+static void __exit rmnet_perf_exit(void)
 {
 	pr_info("%s(): exiting rmnet_perf\n", __func__);
 	unregister_netdevice_notifier(&rmnet_perf_dev_notifier);
diff --git a/techpack/data/drivers/rmnet/shs/rmnet_shs_config.c b/techpack/data/drivers/rmnet/shs/rmnet_shs_config.c
index eeec5c876d50..91d448e7f9fc 100644
--- a/techpack/data/drivers/rmnet/shs/rmnet_shs_config.c
+++ b/techpack/data/drivers/rmnet/shs/rmnet_shs_config.c
@@ -47,7 +47,7 @@ static struct notifier_block rmnet_shs_dev_notifier __read_mostly = {
 
 static int rmnet_vnd_total;
 /* Enable smart hashing capability upon call to initialize module*/
-int __init rmnet_shs_module_init(void)
+static int __init rmnet_shs_module_init(void)
 {
 	pr_info("%s(): Starting rmnet SHS module\n", __func__);
 	trace_rmnet_shs_high(RMNET_SHS_MODULE, RMNET_SHS_MODULE_INIT,
@@ -61,7 +61,7 @@ int __init rmnet_shs_module_init(void)
 }
 
 /* Remove smart hashing capability upon call to initialize module */
-void __exit rmnet_shs_module_exit(void)
+static void __exit rmnet_shs_module_exit(void)
 {
 	trace_rmnet_shs_high(RMNET_SHS_MODULE, RMNET_SHS_MODULE_EXIT,
 			    0xDEF, 0xDEF, 0xDEF, 0xDEF, NULL, NULL);
diff --git a/techpack/data/drivers/rmnet/shs/rmnet_shs_config.h b/techpack/data/drivers/rmnet/shs/rmnet_shs_config.h
index 8d318c173bed..3ab6729cc28a 100644
--- a/techpack/data/drivers/rmnet/shs/rmnet_shs_config.h
+++ b/techpack/data/drivers/rmnet/shs/rmnet_shs_config.h
@@ -58,8 +58,4 @@ extern unsigned long rmnet_shs_crit_err[RMNET_SHS_CRIT_ERR_MAX];
 extern struct rmnet_shs_cfg_s rmnet_shs_cfg;
 extern int rmnet_is_real_dev_registered(const struct net_device *real_dev);
 
-int __init rmnet_shs_module_init(void);
-void __exit rmnet_shs_module_exit(void);
-
-
 #endif /* _RMNET_SMHS_CONFIG_H_ */