LoongArch: Add BPF JIT support

BPF programs are normally handled by a BPF interpreter, add BPF JIT
support for LoongArch to allow the kernel to generate native code when
a program is loaded into the kernel. This will significantly speed-up
processing of BPF programs.

Co-developed-by: Youling Tang <tangyouling@loongson.cn>
Signed-off-by: Youling Tang <tangyouling@loongson.cn>
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

7 files changed, 1700 insertions, 0 deletions

diff --git a/arch/loongarch/Kbuild b/arch/loongarch/Kbuild
index ab5373d0a24f..b01f5cdb27e0 100644
--- a/arch/loongarch/Kbuild
+++ b/arch/loongarch/Kbuild
@@ -1,5 +1,6 @@
 obj-y += kernel/
 obj-y += mm/
+obj-y += net/
 obj-y += vdso/
 
 # for cleaning
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 2837ac5413c0..5c7c2a7762b7 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -87,6 +87,7 @@ config LOONGARCH
 	select HAVE_CONTEXT_TRACKING_USER
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_DMA_CONTIGUOUS
+	select HAVE_EBPF_JIT
 	select HAVE_EXIT_THREAD
 	select HAVE_FAST_GUP
 	select HAVE_GENERIC_VDSO
diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h
index 63df7efff276..fce1843ceebb 100644
--- a/arch/loongarch/include/asm/inst.h
+++ b/arch/loongarch/include/asm/inst.h
@@ -345,4 +345,225 @@ static inline bool unsigned_imm_check(unsigned long val, unsigned int bit)
 	return val < (1UL << bit);
 }
 
+#define DEF_EMIT_REG0I26_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       int offset)				\
+{									\
+	unsigned int immediate_l, immediate_h;				\
+									\
+	immediate_l = offset & 0xffff;					\
+	offset >>= 16;							\
+	immediate_h = offset & 0x3ff;					\
+									\
+	insn->reg0i26_format.opcode = OP;				\
+	insn->reg0i26_format.immediate_l = immediate_l;			\
+	insn->reg0i26_format.immediate_h = immediate_h;			\
+}
+
+DEF_EMIT_REG0I26_FORMAT(b, b_op)
+
+#define DEF_EMIT_REG1I20_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rd, int imm)		\
+{									\
+	insn->reg1i20_format.opcode = OP;				\
+	insn->reg1i20_format.immediate = imm;				\
+	insn->reg1i20_format.rd = rd;					\
+}
+
+DEF_EMIT_REG1I20_FORMAT(lu12iw, lu12iw_op)
+DEF_EMIT_REG1I20_FORMAT(lu32id, lu32id_op)
+DEF_EMIT_REG1I20_FORMAT(pcaddu18i, pcaddu18i_op)
+
+#define DEF_EMIT_REG2_FORMAT(NAME, OP)					\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rd,			\
+			       enum loongarch_gpr rj)			\
+{									\
+	insn->reg2_format.opcode = OP;					\
+	insn->reg2_format.rd = rd;					\
+	insn->reg2_format.rj = rj;					\
+}
+
+DEF_EMIT_REG2_FORMAT(revb2h, revb2h_op)
+DEF_EMIT_REG2_FORMAT(revb2w, revb2w_op)
+DEF_EMIT_REG2_FORMAT(revbd, revbd_op)
+
+#define DEF_EMIT_REG2I5_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rd,			\
+			       enum loongarch_gpr rj,			\
+			       int imm)					\
+{									\
+	insn->reg2i5_format.opcode = OP;				\
+	insn->reg2i5_format.immediate = imm;				\
+	insn->reg2i5_format.rd = rd;					\
+	insn->reg2i5_format.rj = rj;					\
+}
+
+DEF_EMIT_REG2I5_FORMAT(slliw, slliw_op)
+DEF_EMIT_REG2I5_FORMAT(srliw, srliw_op)
+DEF_EMIT_REG2I5_FORMAT(sraiw, sraiw_op)
+
+#define DEF_EMIT_REG2I6_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rd,			\
+			       enum loongarch_gpr rj,			\
+			       int imm)					\
+{									\
+	insn->reg2i6_format.opcode = OP;				\
+	insn->reg2i6_format.immediate = imm;				\
+	insn->reg2i6_format.rd = rd;					\
+	insn->reg2i6_format.rj = rj;					\
+}
+
+DEF_EMIT_REG2I6_FORMAT(sllid, sllid_op)
+DEF_EMIT_REG2I6_FORMAT(srlid, srlid_op)
+DEF_EMIT_REG2I6_FORMAT(sraid, sraid_op)
+
+#define DEF_EMIT_REG2I12_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rd,			\
+			       enum loongarch_gpr rj,			\
+			       int imm)					\
+{									\
+	insn->reg2i12_format.opcode = OP;				\
+	insn->reg2i12_format.immediate = imm;				\
+	insn->reg2i12_format.rd = rd;					\
+	insn->reg2i12_format.rj = rj;					\
+}
+
+DEF_EMIT_REG2I12_FORMAT(addiw, addiw_op)
+DEF_EMIT_REG2I12_FORMAT(addid, addid_op)
+DEF_EMIT_REG2I12_FORMAT(lu52id, lu52id_op)
+DEF_EMIT_REG2I12_FORMAT(andi, andi_op)
+DEF_EMIT_REG2I12_FORMAT(ori, ori_op)
+DEF_EMIT_REG2I12_FORMAT(xori, xori_op)
+DEF_EMIT_REG2I12_FORMAT(ldbu, ldbu_op)
+DEF_EMIT_REG2I12_FORMAT(ldhu, ldhu_op)
+DEF_EMIT_REG2I12_FORMAT(ldwu, ldwu_op)
+DEF_EMIT_REG2I12_FORMAT(ldd, ldd_op)
+DEF_EMIT_REG2I12_FORMAT(stb, stb_op)
+DEF_EMIT_REG2I12_FORMAT(sth, sth_op)
+DEF_EMIT_REG2I12_FORMAT(stw, stw_op)
+DEF_EMIT_REG2I12_FORMAT(std, std_op)
+
+#define DEF_EMIT_REG2I14_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rd,			\
+			       enum loongarch_gpr rj,			\
+			       int imm)					\
+{									\
+	insn->reg2i14_format.opcode = OP;				\
+	insn->reg2i14_format.immediate = imm;				\
+	insn->reg2i14_format.rd = rd;					\
+	insn->reg2i14_format.rj = rj;					\
+}
+
+DEF_EMIT_REG2I14_FORMAT(llw, llw_op)
+DEF_EMIT_REG2I14_FORMAT(scw, scw_op)
+DEF_EMIT_REG2I14_FORMAT(lld, lld_op)
+DEF_EMIT_REG2I14_FORMAT(scd, scd_op)
+DEF_EMIT_REG2I14_FORMAT(ldptrw, ldptrw_op)
+DEF_EMIT_REG2I14_FORMAT(stptrw, stptrw_op)
+DEF_EMIT_REG2I14_FORMAT(ldptrd, ldptrd_op)
+DEF_EMIT_REG2I14_FORMAT(stptrd, stptrd_op)
+
+#define DEF_EMIT_REG2I16_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rj,			\
+			       enum loongarch_gpr rd,			\
+			       int offset)				\
+{									\
+	insn->reg2i16_format.opcode = OP;				\
+	insn->reg2i16_format.immediate = offset;			\
+	insn->reg2i16_format.rj = rj;					\
+	insn->reg2i16_format.rd = rd;					\
+}
+
+DEF_EMIT_REG2I16_FORMAT(beq, beq_op)
+DEF_EMIT_REG2I16_FORMAT(bne, bne_op)
+DEF_EMIT_REG2I16_FORMAT(blt, blt_op)
+DEF_EMIT_REG2I16_FORMAT(bge, bge_op)
+DEF_EMIT_REG2I16_FORMAT(bltu, bltu_op)
+DEF_EMIT_REG2I16_FORMAT(bgeu, bgeu_op)
+DEF_EMIT_REG2I16_FORMAT(jirl, jirl_op)
+
+#define DEF_EMIT_REG2BSTRD_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rd,			\
+			       enum loongarch_gpr rj,			\
+			       int msbd,				\
+			       int lsbd)				\
+{									\
+	insn->reg2bstrd_format.opcode = OP;				\
+	insn->reg2bstrd_format.msbd = msbd;				\
+	insn->reg2bstrd_format.lsbd = lsbd;				\
+	insn->reg2bstrd_format.rj = rj;					\
+	insn->reg2bstrd_format.rd = rd;					\
+}
+
+DEF_EMIT_REG2BSTRD_FORMAT(bstrpickd, bstrpickd_op)
+
+#define DEF_EMIT_REG3_FORMAT(NAME, OP)					\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rd,			\
+			       enum loongarch_gpr rj,			\
+			       enum loongarch_gpr rk)			\
+{									\
+	insn->reg3_format.opcode = OP;					\
+	insn->reg3_format.rd = rd;					\
+	insn->reg3_format.rj = rj;					\
+	insn->reg3_format.rk = rk;					\
+}
+
+DEF_EMIT_REG3_FORMAT(addd, addd_op)
+DEF_EMIT_REG3_FORMAT(subd, subd_op)
+DEF_EMIT_REG3_FORMAT(muld, muld_op)
+DEF_EMIT_REG3_FORMAT(divdu, divdu_op)
+DEF_EMIT_REG3_FORMAT(moddu, moddu_op)
+DEF_EMIT_REG3_FORMAT(and, and_op)
+DEF_EMIT_REG3_FORMAT(or, or_op)
+DEF_EMIT_REG3_FORMAT(xor, xor_op)
+DEF_EMIT_REG3_FORMAT(sllw, sllw_op)
+DEF_EMIT_REG3_FORMAT(slld, slld_op)
+DEF_EMIT_REG3_FORMAT(srlw, srlw_op)
+DEF_EMIT_REG3_FORMAT(srld, srld_op)
+DEF_EMIT_REG3_FORMAT(sraw, sraw_op)
+DEF_EMIT_REG3_FORMAT(srad, srad_op)
+DEF_EMIT_REG3_FORMAT(ldxbu, ldxbu_op)
+DEF_EMIT_REG3_FORMAT(ldxhu, ldxhu_op)
+DEF_EMIT_REG3_FORMAT(ldxwu, ldxwu_op)
+DEF_EMIT_REG3_FORMAT(ldxd, ldxd_op)
+DEF_EMIT_REG3_FORMAT(stxb, stxb_op)
+DEF_EMIT_REG3_FORMAT(stxh, stxh_op)
+DEF_EMIT_REG3_FORMAT(stxw, stxw_op)
+DEF_EMIT_REG3_FORMAT(stxd, stxd_op)
+DEF_EMIT_REG3_FORMAT(amaddw, amaddw_op)
+DEF_EMIT_REG3_FORMAT(amaddd, amaddd_op)
+DEF_EMIT_REG3_FORMAT(amandw, amandw_op)
+DEF_EMIT_REG3_FORMAT(amandd, amandd_op)
+DEF_EMIT_REG3_FORMAT(amorw, amorw_op)
+DEF_EMIT_REG3_FORMAT(amord, amord_op)
+DEF_EMIT_REG3_FORMAT(amxorw, amxorw_op)
+DEF_EMIT_REG3_FORMAT(amxord, amxord_op)
+DEF_EMIT_REG3_FORMAT(amswapw, amswapw_op)
+DEF_EMIT_REG3_FORMAT(amswapd, amswapd_op)
+
+#define DEF_EMIT_REG3SA2_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rd,			\
+			       enum loongarch_gpr rj,			\
+			       enum loongarch_gpr rk,			\
+			       int imm)					\
+{									\
+	insn->reg3sa2_format.opcode = OP;				\
+	insn->reg3sa2_format.immediate = imm;				\
+	insn->reg3sa2_format.rd = rd;					\
+	insn->reg3sa2_format.rj = rj;					\
+	insn->reg3sa2_format.rk = rk;					\
+}
+
+DEF_EMIT_REG3SA2_FORMAT(alsld, alsld_op)
+
 #endif /* _ASM_INST_H */
diff --git a/arch/loongarch/include/uapi/asm/bpf_perf_event.h b/arch/loongarch/include/uapi/asm/bpf_perf_event.h
new file mode 100644
index 000000000000..eb6e2fd2a1f0
--- /dev/null
+++ b/arch/loongarch/include/uapi/asm/bpf_perf_event.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_BPF_PERF_EVENT_H__
+
+#include <linux/ptrace.h>
+
+typedef struct user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */
diff --git a/arch/loongarch/net/Makefile b/arch/loongarch/net/Makefile
new file mode 100644
index 000000000000..1ec12a0c324a
--- /dev/null
+++ b/arch/loongarch/net/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for arch/loongarch/net
+#
+# Copyright (C) 2022 Loongson Technology Corporation Limited
+#
+obj-$(CONFIG_BPF_JIT) += bpf_jit.o
diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
new file mode 100644
index 000000000000..43f0a98efe38
--- /dev/null
+++ b/arch/loongarch/net/bpf_jit.c
@@ -0,0 +1,1179 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * BPF JIT compiler for LoongArch
+ *
+ * Copyright (C) 2022 Loongson Technology Corporation Limited
+ */
+#include "bpf_jit.h"
+
+#define REG_TCC		LOONGARCH_GPR_A6
+#define TCC_SAVED	LOONGARCH_GPR_S5
+
+#define SAVE_RA		BIT(0)
+#define SAVE_TCC	BIT(1)
+
+static const int regmap[] = {
+	/* return value from in-kernel function, and exit value for eBPF program */
+	[BPF_REG_0] = LOONGARCH_GPR_A5,
+	/* arguments from eBPF program to in-kernel function */
+	[BPF_REG_1] = LOONGARCH_GPR_A0,
+	[BPF_REG_2] = LOONGARCH_GPR_A1,
+	[BPF_REG_3] = LOONGARCH_GPR_A2,
+	[BPF_REG_4] = LOONGARCH_GPR_A3,
+	[BPF_REG_5] = LOONGARCH_GPR_A4,
+	/* callee saved registers that in-kernel function will preserve */
+	[BPF_REG_6] = LOONGARCH_GPR_S0,
+	[BPF_REG_7] = LOONGARCH_GPR_S1,
+	[BPF_REG_8] = LOONGARCH_GPR_S2,
+	[BPF_REG_9] = LOONGARCH_GPR_S3,
+	/* read-only frame pointer to access stack */
+	[BPF_REG_FP] = LOONGARCH_GPR_S4,
+	/* temporary register for blinding constants */
+	[BPF_REG_AX] = LOONGARCH_GPR_T0,
+};
+
+static void mark_call(struct jit_ctx *ctx)
+{
+	ctx->flags |= SAVE_RA;
+}
+
+static void mark_tail_call(struct jit_ctx *ctx)
+{
+	ctx->flags |= SAVE_TCC;
+}
+
+static bool seen_call(struct jit_ctx *ctx)
+{
+	return (ctx->flags & SAVE_RA);
+}
+
+static bool seen_tail_call(struct jit_ctx *ctx)
+{
+	return (ctx->flags & SAVE_TCC);
+}
+
+static u8 tail_call_reg(struct jit_ctx *ctx)
+{
+	if (seen_call(ctx))
+		return TCC_SAVED;
+
+	return REG_TCC;
+}
+
+/*
+ * eBPF prog stack layout:
+ *
+ *                                        high
+ * original $sp ------------> +-------------------------+ <--LOONGARCH_GPR_FP
+ *                            |           $ra           |
+ *                            +-------------------------+
+ *                            |           $fp           |
+ *                            +-------------------------+
+ *                            |           $s0           |
+ *                            +-------------------------+
+ *                            |           $s1           |
+ *                            +-------------------------+
+ *                            |           $s2           |
+ *                            +-------------------------+
+ *                            |           $s3           |
+ *                            +-------------------------+
+ *                            |           $s4           |
+ *                            +-------------------------+
+ *                            |           $s5           |
+ *                            +-------------------------+ <--BPF_REG_FP
+ *                            |  prog->aux->stack_depth |
+ *                            |        (optional)       |
+ * current $sp -------------> +-------------------------+
+ *                                        low
+ */
+static void build_prologue(struct jit_ctx *ctx)
+{
+	int stack_adjust = 0, store_offset, bpf_stack_adjust;
+
+	bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16);
+
+	/* To store ra, fp, s0, s1, s2, s3, s4 and s5. */
+	stack_adjust += sizeof(long) * 8;
+
+	stack_adjust = round_up(stack_adjust, 16);
+	stack_adjust += bpf_stack_adjust;
+
+	/*
+	 * First instruction initializes the tail call count (TCC).
+	 * On tail call we skip this instruction, and the TCC is
+	 * passed in REG_TCC from the caller.
+	 */
+	emit_insn(ctx, addid, REG_TCC, LOONGARCH_GPR_ZERO, MAX_TAIL_CALL_CNT);
+
+	emit_insn(ctx, addid, LOONGARCH_GPR_SP, LOONGARCH_GPR_SP, -stack_adjust);
+
+	store_offset = stack_adjust - sizeof(long);
+	emit_insn(ctx, std, LOONGARCH_GPR_RA, LOONGARCH_GPR_SP, store_offset);
+
+	store_offset -= sizeof(long);
+	emit_insn(ctx, std, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, store_offset);
+
+	store_offset -= sizeof(long);
+	emit_insn(ctx, std, LOONGARCH_GPR_S0, LOONGARCH_GPR_SP, store_offset);
+
+	store_offset -= sizeof(long);
+	emit_insn(ctx, std, LOONGARCH_GPR_S1, LOONGARCH_GPR_SP, store_offset);
+
+	store_offset -= sizeof(long);
+	emit_insn(ctx, std, LOONGARCH_GPR_S2, LOONGARCH_GPR_SP, store_offset);
+
+	store_offset -= sizeof(long);
+	emit_insn(ctx, std, LOONGARCH_GPR_S3, LOONGARCH_GPR_SP, store_offset);
+
+	store_offset -= sizeof(long);
+	emit_insn(ctx, std, LOONGARCH_GPR_S4, LOONGARCH_GPR_SP, store_offset);
+
+	store_offset -= sizeof(long);
+	emit_insn(ctx, std, LOONGARCH_GPR_S5, LOONGARCH_GPR_SP, store_offset);
+
+	emit_insn(ctx, addid, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, stack_adjust);
+
+	if (bpf_stack_adjust)
+		emit_insn(ctx, addid, regmap[BPF_REG_FP], LOONGARCH_GPR_SP, bpf_stack_adjust);
+
+	/*
+	 * Program contains calls and tail calls, so REG_TCC need
+	 * to be saved across calls.
+	 */
+	if (seen_tail_call(ctx) && seen_call(ctx))
+		move_reg(ctx, TCC_SAVED, REG_TCC);
+
+	ctx->stack_size = stack_adjust;
+}
+
+static void __build_epilogue(struct jit_ctx *ctx, bool is_tail_call)
+{
+	int stack_adjust = ctx->stack_size;
+	int load_offset;
+
+	load_offset = stack_adjust - sizeof(long);
+	emit_insn(ctx, ldd, LOONGARCH_GPR_RA, LOONGARCH_GPR_SP, load_offset);
+
+	load_offset -= sizeof(long);
+	emit_insn(ctx, ldd, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, load_offset);
+
+	load_offset -= sizeof(long);
+	emit_insn(ctx, ldd, LOONGARCH_GPR_S0, LOONGARCH_GPR_SP, load_offset);
+
+	load_offset -= sizeof(long);
+	emit_insn(ctx, ldd, LOONGARCH_GPR_S1, LOONGARCH_GPR_SP, load_offset);
+
+	load_offset -= sizeof(long);
+	emit_insn(ctx, ldd, LOONGARCH_GPR_S2, LOONGARCH_GPR_SP, load_offset);
+
+	load_offset -= sizeof(long);
+	emit_insn(ctx, ldd, LOONGARCH_GPR_S3, LOONGARCH_GPR_SP, load_offset);
+
+	load_offset -= sizeof(long);
+	emit_insn(ctx, ldd, LOONGARCH_GPR_S4, LOONGARCH_GPR_SP, load_offset);
+
+	load_offset -= sizeof(long);
+	emit_insn(ctx, ldd, LOONGARCH_GPR_S5, LOONGARCH_GPR_SP, load_offset);
+
+	emit_insn(ctx, addid, LOONGARCH_GPR_SP, LOONGARCH_GPR_SP, stack_adjust);
+
+	if (!is_tail_call) {
+		/* Set return value */
+		move_reg(ctx, LOONGARCH_GPR_A0, regmap[BPF_REG_0]);
+		/* Return to the caller */
+		emit_insn(ctx, jirl, LOONGARCH_GPR_RA, LOONGARCH_GPR_ZERO, 0);
+	} else {
+		/*
+		 * Call the next bpf prog and skip the first instruction
+		 * of TCC initialization.
+		 */
+		emit_insn(ctx, jirl, LOONGARCH_GPR_T3, LOONGARCH_GPR_ZERO, 1);
+	}
+}
+
+static void build_epilogue(struct jit_ctx *ctx)
+{
+	__build_epilogue(ctx, false);
+}
+
+bool bpf_jit_supports_kfunc_call(void)
+{
+	return true;
+}
+
+/* initialized on the first pass of build_body() */
+static int out_offset = -1;
+static int emit_bpf_tail_call(struct jit_ctx *ctx)
+{
+	int off;
+	u8 tcc = tail_call_reg(ctx);
+	u8 a1 = LOONGARCH_GPR_A1;
+	u8 a2 = LOONGARCH_GPR_A2;
+	u8 t1 = LOONGARCH_GPR_T1;
+	u8 t2 = LOONGARCH_GPR_T2;
+	u8 t3 = LOONGARCH_GPR_T3;
+	const int idx0 = ctx->idx;
+
+#define cur_offset (ctx->idx - idx0)
+#define jmp_offset (out_offset - (cur_offset))
+
+	/*
+	 * a0: &ctx
+	 * a1: &array
+	 * a2: index
+	 *
+	 * if (index >= array->map.max_entries)
+	 *	 goto out;
+	 */
+	off = offsetof(struct bpf_array, map.max_entries);
+	emit_insn(ctx, ldwu, t1, a1, off);
+	/* bgeu $a2, $t1, jmp_offset */
+	if (emit_tailcall_jmp(ctx, BPF_JGE, a2, t1, jmp_offset) < 0)
+		goto toofar;
+
+	/*
+	 * if (--TCC < 0)
+	 *	 goto out;
+	 */
+	emit_insn(ctx, addid, REG_TCC, tcc, -1);
+	if (emit_tailcall_jmp(ctx, BPF_JSLT, REG_TCC, LOONGARCH_GPR_ZERO, jmp_offset) < 0)
+		goto toofar;
+
+	/*
+	 * prog = array->ptrs[index];
+	 * if (!prog)
+	 *	 goto out;
+	 */
+	emit_insn(ctx, alsld, t2, a2, a1, 2);
+	off = offsetof(struct bpf_array, ptrs);
+	emit_insn(ctx, ldd, t2, t2, off);
+	/* beq $t2, $zero, jmp_offset */
+	if (emit_tailcall_jmp(ctx, BPF_JEQ, t2, LOONGARCH_GPR_ZERO, jmp_offset) < 0)
+		goto toofar;
+
+	/* goto *(prog->bpf_func + 4); */
+	off = offsetof(struct bpf_prog, bpf_func);
+	emit_insn(ctx, ldd, t3, t2, off);
+	__build_epilogue(ctx, true);
+
+	/* out: */
+	if (out_offset == -1)
+		out_offset = cur_offset;
+	if (cur_offset != out_offset) {
+		pr_err_once("tail_call out_offset = %d, expected %d!\n",
+			    cur_offset, out_offset);
+		return -1;
+	}
+
+	return 0;
+
+toofar:
+	pr_info_once("tail_call: jump too far\n");
+	return -1;
+#undef cur_offset
+#undef jmp_offset
+}
+
+static void emit_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
+{
+	const u8 t1 = LOONGARCH_GPR_T1;
+	const u8 t2 = LOONGARCH_GPR_T2;
+	const u8 t3 = LOONGARCH_GPR_T3;
+	const u8 src = regmap[insn->src_reg];
+	const u8 dst = regmap[insn->dst_reg];
+	const s16 off = insn->off;
+	const s32 imm = insn->imm;
+	const bool isdw = BPF_SIZE(insn->code) == BPF_DW;
+
+	move_imm(ctx, t1, off, false);
+	emit_insn(ctx, addd, t1, dst, t1);
+	move_reg(ctx, t3, src);
+
+	switch (imm) {
+	/* lock *(size *)(dst + off) <op>= src */
+	case BPF_ADD:
+		if (isdw)
+			emit_insn(ctx, amaddd, t2, t1, src);
+		else
+			emit_insn(ctx, amaddw, t2, t1, src);
+		break;
+	case BPF_AND:
+		if (isdw)
+			emit_insn(ctx, amandd, t2, t1, src);
+		else
+			emit_insn(ctx, amandw, t2, t1, src);
+		break;
+	case BPF_OR:
+		if (isdw)
+			emit_insn(ctx, amord, t2, t1, src);
+		else
+			emit_insn(ctx, amorw, t2, t1, src);
+		break;
+	case BPF_XOR:
+		if (isdw)
+			emit_insn(ctx, amxord, t2, t1, src);
+		else
+			emit_insn(ctx, amxorw, t2, t1, src);
+		break;
+	/* src = atomic_fetch_<op>(dst + off, src) */
+	case BPF_ADD | BPF_FETCH:
+		if (isdw) {
+			emit_insn(ctx, amaddd, src, t1, t3);
+		} else {
+			emit_insn(ctx, amaddw, src, t1, t3);
+			emit_zext_32(ctx, src, true);
+		}
+		break;
+	case BPF_AND | BPF_FETCH:
+		if (isdw) {
+			emit_insn(ctx, amandd, src, t1, t3);
+		} else {
+			emit_insn(ctx, amandw, src, t1, t3);
+			emit_zext_32(ctx, src, true);
+		}
+		break;
+	case BPF_OR | BPF_FETCH:
+		if (isdw) {
+			emit_insn(ctx, amord, src, t1, t3);
+		} else {
+			emit_insn(ctx, amorw, src, t1, t3);
+			emit_zext_32(ctx, src, true);
+		}
+		break;
+	case BPF_XOR | BPF_FETCH:
+		if (isdw) {
+			emit_insn(ctx, amxord, src, t1, t3);
+		} else {
+			emit_insn(ctx, amxorw, src, t1, t3);
+			emit_zext_32(ctx, src, true);
+		}
+		break;
+	/* src = atomic_xchg(dst + off, src); */
+	case BPF_XCHG:
+		if (isdw) {
+			emit_insn(ctx, amswapd, src, t1, t3);
+		} else {
+			emit_insn(ctx, amswapw, src, t1, t3);
+			emit_zext_32(ctx, src, true);
+		}
+		break;
+	/* r0 = atomic_cmpxchg(dst + off, r0, src); */
+	case BPF_CMPXCHG:
+		u8 r0 = regmap[BPF_REG_0];
+
+		move_reg(ctx, t2, r0);
+		if (isdw) {
+			emit_insn(ctx, lld, r0, t1, 0);
+			emit_insn(ctx, bne, t2, r0, 4);
+			move_reg(ctx, t3, src);
+			emit_insn(ctx, scd, t3, t1, 0);
+			emit_insn(ctx, beq, t3, LOONGARCH_GPR_ZERO, -4);
+		} else {
+			emit_insn(ctx, llw, r0, t1, 0);
+			emit_zext_32(ctx, t2, true);
+			emit_zext_32(ctx, r0, true);
+			emit_insn(ctx, bne, t2, r0, 4);
+			move_reg(ctx, t3, src);
+			emit_insn(ctx, scw, t3, t1, 0);
+			emit_insn(ctx, beq, t3, LOONGARCH_GPR_ZERO, -6);
+			emit_zext_32(ctx, r0, true);
+		}
+		break;
+	}
+}
+
+static bool is_signed_bpf_cond(u8 cond)
+{
+	return cond == BPF_JSGT || cond == BPF_JSLT ||
+	       cond == BPF_JSGE || cond == BPF_JSLE;
+}
+
+static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool extra_pass)
+{
+	const bool is32 = BPF_CLASS(insn->code) == BPF_ALU ||
+			  BPF_CLASS(insn->code) == BPF_JMP32;
+	const u8 code = insn->code;
+	const u8 cond = BPF_OP(code);
+	const u8 t1 = LOONGARCH_GPR_T1;
+	const u8 t2 = LOONGARCH_GPR_T2;
+	const u8 src = regmap[insn->src_reg];
+	const u8 dst = regmap[insn->dst_reg];
+	const s16 off = insn->off;
+	const s32 imm = insn->imm;
+	int jmp_offset;
+	int i = insn - ctx->prog->insnsi;
+
+	switch (code) {
+	/* dst = src */
+	case BPF_ALU | BPF_MOV | BPF_X:
+	case BPF_ALU64 | BPF_MOV | BPF_X:
+		move_reg(ctx, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = imm */
+	case BPF_ALU | BPF_MOV | BPF_K:
+	case BPF_ALU64 | BPF_MOV | BPF_K:
+		move_imm(ctx, dst, imm, is32);
+		break;
+
+	/* dst = dst + src */
+	case BPF_ALU | BPF_ADD | BPF_X:
+	case BPF_ALU64 | BPF_ADD | BPF_X:
+		emit_insn(ctx, addd, dst, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst + imm */
+	case BPF_ALU | BPF_ADD | BPF_K:
+	case BPF_ALU64 | BPF_ADD | BPF_K:
+		if (is_signed_imm12(imm)) {
+			emit_insn(ctx, addid, dst, dst, imm);
+		} else {
+			move_imm(ctx, t1, imm, is32);
+			emit_insn(ctx, addd, dst, dst, t1);
+		}
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst - src */
+	case BPF_ALU | BPF_SUB | BPF_X:
+	case BPF_ALU64 | BPF_SUB | BPF_X:
+		emit_insn(ctx, subd, dst, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst - imm */
+	case BPF_ALU | BPF_SUB | BPF_K:
+	case BPF_ALU64 | BPF_SUB | BPF_K:
+		if (is_signed_imm12(-imm)) {
+			emit_insn(ctx, addid, dst, dst, -imm);
+		} else {
+			move_imm(ctx, t1, imm, is32);
+			emit_insn(ctx, subd, dst, dst, t1);
+		}
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst * src */
+	case BPF_ALU | BPF_MUL | BPF_X:
+	case BPF_ALU64 | BPF_MUL | BPF_X:
+		emit_insn(ctx, muld, dst, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst * imm */
+	case BPF_ALU | BPF_MUL | BPF_K:
+	case BPF_ALU64 | BPF_MUL | BPF_K:
+		move_imm(ctx, t1, imm, is32);
+		emit_insn(ctx, muld, dst, dst, t1);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst / src */
+	case BPF_ALU | BPF_DIV | BPF_X:
+	case BPF_ALU64 | BPF_DIV | BPF_X:
+		emit_zext_32(ctx, dst, is32);
+		move_reg(ctx, t1, src);
+		emit_zext_32(ctx, t1, is32);
+		emit_insn(ctx, divdu, dst, dst, t1);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst / imm */
+	case BPF_ALU | BPF_DIV | BPF_K:
+	case BPF_ALU64 | BPF_DIV | BPF_K:
+		move_imm(ctx, t1, imm, is32);
+		emit_zext_32(ctx, dst, is32);
+		emit_insn(ctx, divdu, dst, dst, t1);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst % src */
+	case BPF_ALU | BPF_MOD | BPF_X:
+	case BPF_ALU64 | BPF_MOD | BPF_X:
+		emit_zext_32(ctx, dst, is32);
+		move_reg(ctx, t1, src);
+		emit_zext_32(ctx, t1, is32);
+		emit_insn(ctx, moddu, dst, dst, t1);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst % imm */
+	case BPF_ALU | BPF_MOD | BPF_K:
+	case BPF_ALU64 | BPF_MOD | BPF_K:
+		move_imm(ctx, t1, imm, is32);
+		emit_zext_32(ctx, dst, is32);
+		emit_insn(ctx, moddu, dst, dst, t1);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = -dst */
+	case BPF_ALU | BPF_NEG:
+	case BPF_ALU64 | BPF_NEG:
+		move_imm(ctx, t1, imm, is32);
+		emit_insn(ctx, subd, dst, LOONGARCH_GPR_ZERO, dst);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst & src */
+	case BPF_ALU | BPF_AND | BPF_X:
+	case BPF_ALU64 | BPF_AND | BPF_X:
+		emit_insn(ctx, and, dst, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst & imm */
+	case BPF_ALU | BPF_AND | BPF_K:
+	case BPF_ALU64 | BPF_AND | BPF_K:
+		if (is_unsigned_imm12(imm)) {
+			emit_insn(ctx, andi, dst, dst, imm);
+		} else {
+			move_imm(ctx, t1, imm, is32);
+			emit_insn(ctx, and, dst, dst, t1);
+		}
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst | src */
+	case BPF_ALU | BPF_OR | BPF_X:
+	case BPF_ALU64 | BPF_OR | BPF_X:
+		emit_insn(ctx, or, dst, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst | imm */
+	case BPF_ALU | BPF_OR | BPF_K:
+	case BPF_ALU64 | BPF_OR | BPF_K:
+		if (is_unsigned_imm12(imm)) {
+			emit_insn(ctx, ori, dst, dst, imm);
+		} else {
+			move_imm(ctx, t1, imm, is32);
+			emit_insn(ctx, or, dst, dst, t1);
+		}
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst ^ src */
+	case BPF_ALU | BPF_XOR | BPF_X:
+	case BPF_ALU64 | BPF_XOR | BPF_X:
+		emit_insn(ctx, xor, dst, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst ^ imm */
+	case BPF_ALU | BPF_XOR | BPF_K:
+	case BPF_ALU64 | BPF_XOR | BPF_K:
+		if (is_unsigned_imm12(imm)) {
+			emit_insn(ctx, xori, dst, dst, imm);
+		} else {
+			move_imm(ctx, t1, imm, is32);
+			emit_insn(ctx, xor, dst, dst, t1);
+		}
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst << src (logical) */
+	case BPF_ALU | BPF_LSH | BPF_X:
+		emit_insn(ctx, sllw, dst, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	case BPF_ALU64 | BPF_LSH | BPF_X:
+		emit_insn(ctx, slld, dst, dst, src);
+		break;
+
+	/* dst = dst << imm (logical) */
+	case BPF_ALU | BPF_LSH | BPF_K:
+		emit_insn(ctx, slliw, dst, dst, imm);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	case BPF_ALU64 | BPF_LSH | BPF_K:
+		emit_insn(ctx, sllid, dst, dst, imm);
+		break;
+
+	/* dst = dst >> src (logical) */
+	case BPF_ALU | BPF_RSH | BPF_X:
+		emit_insn(ctx, srlw, dst, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	case BPF_ALU64 | BPF_RSH | BPF_X:
+		emit_insn(ctx, srld, dst, dst, src);
+		break;
+
+	/* dst = dst >> imm (logical) */
+	case BPF_ALU | BPF_RSH | BPF_K:
+		emit_insn(ctx, srliw, dst, dst, imm);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	case BPF_ALU64 | BPF_RSH | BPF_K:
+		emit_insn(ctx, srlid, dst, dst, imm);
+		break;
+
+	/* dst = dst >> src (arithmetic) */
+	case BPF_ALU | BPF_ARSH | BPF_X:
+		emit_insn(ctx, sraw, dst, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	case BPF_ALU64 | BPF_ARSH | BPF_X:
+		emit_insn(ctx, srad, dst, dst, src);
+		break;
+
+	/* dst = dst >> imm (arithmetic) */
+	case BPF_ALU | BPF_ARSH | BPF_K:
+		emit_insn(ctx, sraiw, dst, dst, imm);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	case BPF_ALU64 | BPF_ARSH | BPF_K:
+		emit_insn(ctx, sraid, dst, dst, imm);
+		break;
+
+	/* dst = BSWAP##imm(dst) */
+	case BPF_ALU | BPF_END | BPF_FROM_LE:
+		switch (imm) {
+		case 16:
+			/* zero-extend 16 bits into 64 bits */
+			emit_insn(ctx, bstrpickd, dst, dst, 15, 0);
+			break;
+		case 32:
+			/* zero-extend 32 bits into 64 bits */
+			emit_zext_32(ctx, dst, is32);
+			break;
+		case 64:
+			/* do nothing */
+			break;
+		}
+		break;
+
+	case BPF_ALU | BPF_END | BPF_FROM_BE:
+		switch (imm) {
+		case 16:
+			emit_insn(ctx, revb2h, dst, dst);
+			/* zero-extend 16 bits into 64 bits */
+			emit_insn(ctx, bstrpickd, dst, dst, 15, 0);
+			break;
+		case 32:
+			emit_insn(ctx, revb2w, dst, dst);
+			/* zero-extend 32 bits into 64 bits */
+			emit_zext_32(ctx, dst, is32);
+			break;
+		case 64:
+			emit_insn(ctx, revbd, dst, dst);
+			break;
+		}
+		break;
+
+	/* PC += off if dst cond src */
+	case BPF_JMP | BPF_JEQ | BPF_X:
+	case BPF_JMP | BPF_JNE | BPF_X:
+	case BPF_JMP | BPF_JGT | BPF_X:
+	case BPF_JMP | BPF_JGE | BPF_X:
+	case BPF_JMP | BPF_JLT | BPF_X:
+	case BPF_JMP | BPF_JLE | BPF_X:
+	case BPF_JMP | BPF_JSGT | BPF_X:
+	case BPF_JMP | BPF_JSGE | BPF_X:
+	case BPF_JMP | BPF_JSLT | BPF_X:
+	case BPF_JMP | BPF_JSLE | BPF_X:
+	case BPF_JMP32 | BPF_JEQ | BPF_X:
+	case BPF_JMP32 | BPF_JNE | BPF_X:
+	case BPF_JMP32 | BPF_JGT | BPF_X:
+	case BPF_JMP32 | BPF_JGE | BPF_X:
+	case BPF_JMP32 | BPF_JLT | BPF_X:
+	case BPF_JMP32 | BPF_JLE | BPF_X:
+	case BPF_JMP32 | BPF_JSGT | BPF_X:
+	case BPF_JMP32 | BPF_JSGE | BPF_X:
+	case BPF_JMP32 | BPF_JSLT | BPF_X:
+	case BPF_JMP32 | BPF_JSLE | BPF_X:
+		jmp_offset = bpf2la_offset(i, off, ctx);
+		move_reg(ctx, t1, dst);
+		move_reg(ctx, t2, src);
+		if (is_signed_bpf_cond(BPF_OP(code))) {
+			emit_sext_32(ctx, t1, is32);
+			emit_sext_32(ctx, t2, is32);
+		} else {
+			emit_zext_32(ctx, t1, is32);
+			emit_zext_32(ctx, t2, is32);
+		}
+		if (emit_cond_jmp(ctx, cond, t1, t2, jmp_offset) < 0)
+			goto toofar;
+		break;
+
+	/* PC += off if dst cond imm */
+	case BPF_JMP | BPF_JEQ | BPF_K:
+	case BPF_JMP | BPF_JNE | BPF_K:
+	case BPF_JMP | BPF_JGT | BPF_K:
+	case BPF_JMP | BPF_JGE | BPF_K:
+	case BPF_JMP | BPF_JLT | BPF_K:
+	case BPF_JMP | BPF_JLE | BPF_K:
+	case BPF_JMP | BPF_JSGT | BPF_K:
+	case BPF_JMP | BPF_JSGE | BPF_K:
+	case BPF_JMP | BPF_JSLT | BPF_K:
+	case BPF_JMP | BPF_JSLE | BPF_K:
+	case BPF_JMP32 | BPF_JEQ | BPF_K:
+	case BPF_JMP32 | BPF_JNE | BPF_K:
+	case BPF_JMP32 | BPF_JGT | BPF_K:
+	case BPF_JMP32 | BPF_JGE | BPF_K:
+	case BPF_JMP32 | BPF_JLT | BPF_K:
+	case BPF_JMP32 | BPF_JLE | BPF_K:
+	case BPF_JMP32 | BPF_JSGT | BPF_K:
+	case BPF_JMP32 | BPF_JSGE | BPF_K:
+	case BPF_JMP32 | BPF_JSLT | BPF_K:
+	case BPF_JMP32 | BPF_JSLE | BPF_K:
+		u8 t7 = -1;
+		jmp_offset = bpf2la_offset(i, off, ctx);
+		if (imm) {
+			move_imm(ctx, t1, imm, false);
+			t7 = t1;
+		} else {
+			/* If imm is 0, simply use zero register. */
+			t7 = LOONGARCH_GPR_ZERO;
+		}
+		move_reg(ctx, t2, dst);
+		if (is_signed_bpf_cond(BPF_OP(code))) {
+			emit_sext_32(ctx, t7, is32);
+			emit_sext_32(ctx, t2, is32);
+		} else {
+			emit_zext_32(ctx, t7, is32);
+			emit_zext_32(ctx, t2, is32);
+		}
+		if (emit_cond_jmp(ctx, cond, t2, t7, jmp_offset) < 0)
+			goto toofar;
+		break;
+
+	/* PC += off if dst & src */
+	case BPF_JMP | BPF_JSET | BPF_X:
+	case BPF_JMP32 | BPF_JSET | BPF_X:
+		jmp_offset = bpf2la_offset(i, off, ctx);
+		emit_insn(ctx, and, t1, dst, src);
+		emit_zext_32(ctx, t1, is32);
+		if (emit_cond_jmp(ctx, cond, t1, LOONGARCH_GPR_ZERO, jmp_offset) < 0)
+			goto toofar;
+		break;
+
+	/* PC += off if dst & imm */
+	case BPF_JMP | BPF_JSET | BPF_K:
+	case BPF_JMP32 | BPF_JSET | BPF_K:
+		jmp_offset = bpf2la_offset(i, off, ctx);
+		move_imm(ctx, t1, imm, is32);
+		emit_insn(ctx, and, t1, dst, t1);
+		emit_zext_32(ctx, t1, is32);
+		if (emit_cond_jmp(ctx, cond, t1, LOONGARCH_GPR_ZERO, jmp_offset) < 0)
+			goto toofar;
+		break;
+
+	/* PC += off */
+	case BPF_JMP | BPF_JA:
+		jmp_offset = bpf2la_offset(i, off, ctx);
+		if (emit_uncond_jmp(ctx, jmp_offset) < 0)
+			goto toofar;
+		break;
+
+	/* function c