Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2024-02-29

We've added 119 non-merge commits during the last 32 day(s) which contain
a total of 150 files changed, 3589 insertions(+), 995 deletions(-).

The main changes are:

1) Extend the BPF verifier to enable static subprog calls in spin lock
   critical sections, from Kumar Kartikeya Dwivedi.

2) Fix confusing and incorrect inference of PTR_TO_CTX argument type
   in BPF global subprogs, from Andrii Nakryiko.

3) Larger batch of riscv BPF JIT improvements and enabling inlining
   of the bpf_kptr_xchg() for RV64, from Pu Lehui.

4) Allow skeleton users to change the values of the fields in struct_ops
   maps at runtime, from Kui-Feng Lee.

5) Extend the verifier's capabilities of tracking scalars when they
   are spilled to stack, especially when the spill or fill is narrowing,
   from Maxim Mikityanskiy & Eduard Zingerman.

6) Various BPF selftest improvements to fix errors under gcc BPF backend,
   from Jose E. Marchesi.

7) Avoid module loading failure when the module trying to register
   a struct_ops has its BTF section stripped, from Geliang Tang.

8) Annotate all kfuncs in .BTF_ids section which eventually allows
   for automatic kfunc prototype generation from bpftool, from Daniel Xu.

9) Several updates to the instruction-set.rst IETF standardization
   document, from Dave Thaler.

10) Shrink the size of struct bpf_map resp. bpf_array,
    from Alexei Starovoitov.

11) Initial small subset of BPF verifier prepwork for sleepable bpf_timer,
    from Benjamin Tissoires.

12) Fix bpftool to be more portable to musl libc by using POSIX's
    basename(), from Arnaldo Carvalho de Melo.

13) Add libbpf support to gcc in CORE macro definitions,
    from Cupertino Miranda.

14) Remove a duplicate type check in perf_event_bpf_event,
    from Florian Lehner.

15) Fix bpf_spin_{un,}lock BPF helpers to actually annotate them
    with notrace correctly, from Yonghong Song.

16) Replace the deprecated bpf_lpm_trie_key 0-length array with flexible
    array to fix build warnings, from Kees Cook.

17) Fix resolve_btfids cross-compilation to non host-native endianness,
    from Viktor Malik.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (119 commits)
  selftests/bpf: Test if shadow types work correctly.
  bpftool: Add an example for struct_ops map and shadow type.
  bpftool: Generated shadow variables for struct_ops maps.
  libbpf: Convert st_ops->data to shadow type.
  libbpf: Set btf_value_type_id of struct bpf_map for struct_ops.
  bpf: Replace bpf_lpm_trie_key 0-length array with flexible array
  bpf, arm64: use bpf_prog_pack for memory management
  arm64: patching: implement text_poke API
  bpf, arm64: support exceptions
  arm64: stacktrace: Implement arch_bpf_stack_walk() for the BPF JIT
  bpf: add is_async_callback_calling_insn() helper
  bpf: introduce in_sleepable() helper
  bpf: allow more maps in sleepable bpf programs
  selftests/bpf: Test case for lacking CFI stub functions.
  bpf: Check cfi_stubs before registering a struct_ops type.
  bpf: Clarify batch lookup/lookup_and_delete semantics
  bpf, docs: specify which BPF_ABS and BPF_IND fields were zero
  bpf, docs: Fix typos in instruction-set.rst
  selftests/bpf: update tcp_custom_syncookie to use scalar packet offset
  bpf: Shrink size of struct bpf_map/bpf_array.
  ...
====================

Link: https://lore.kernel.org/r/20240301001625.8800-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 210 insertions, 139 deletions

diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index a5ce1ab76ece..8b35f12a4452 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -18,6 +18,11 @@ static inline bool rvc_enabled(void)
 	return IS_ENABLED(CONFIG_RISCV_ISA_C);
 }
 
+static inline bool rvzbb_enabled(void)
+{
+	return IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && riscv_has_extension_likely(RISCV_ISA_EXT_ZBB);
+}
+
 enum {
 	RV_REG_ZERO =	0,	/* The constant value 0 */
 	RV_REG_RA =	1,	/* Return address */
@@ -730,6 +735,33 @@ static inline u16 rvc_swsp(u32 imm8, u8 rs2)
 	return rv_css_insn(0x6, imm, rs2, 0x2);
 }
 
+/* RVZBB instrutions. */
+static inline u32 rvzbb_sextb(u8 rd, u8 rs1)
+{
+	return rv_i_insn(0x604, rs1, 1, rd, 0x13);
+}
+
+static inline u32 rvzbb_sexth(u8 rd, u8 rs1)
+{
+	return rv_i_insn(0x605, rs1, 1, rd, 0x13);
+}
+
+static inline u32 rvzbb_zexth(u8 rd, u8 rs)
+{
+	if (IS_ENABLED(CONFIG_64BIT))
+		return rv_i_insn(0x80, rs, 4, rd, 0x3b);
+
+	return rv_i_insn(0x80, rs, 4, rd, 0x33);
+}
+
+static inline u32 rvzbb_rev8(u8 rd, u8 rs)
+{
+	if (IS_ENABLED(CONFIG_64BIT))
+		return rv_i_insn(0x6b8, rs, 5, rd, 0x13);
+
+	return rv_i_insn(0x698, rs, 5, rd, 0x13);
+}
+
 /*
  * RV64-only instructions.
  *
@@ -1087,6 +1119,108 @@ static inline void emit_subw(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
 		emit(rv_subw(rd, rs1, rs2), ctx);
 }
 
+static inline void emit_sextb(u8 rd, u8 rs, struct rv_jit_context *ctx)
+{
+	if (rvzbb_enabled()) {
+		emit(rvzbb_sextb(rd, rs), ctx);
+		return;
+	}
+
+	emit_slli(rd, rs, 56, ctx);
+	emit_srai(rd, rd, 56, ctx);
+}
+
+static inline void emit_sexth(u8 rd, u8 rs, struct rv_jit_context *ctx)
+{
+	if (rvzbb_enabled()) {
+		emit(rvzbb_sexth(rd, rs), ctx);
+		return;
+	}
+
+	emit_slli(rd, rs, 48, ctx);
+	emit_srai(rd, rd, 48, ctx);
+}
+
+static inline void emit_sextw(u8 rd, u8 rs, struct rv_jit_context *ctx)
+{
+	emit_addiw(rd, rs, 0, ctx);
+}
+
+static inline void emit_zexth(u8 rd, u8 rs, struct rv_jit_context *ctx)
+{
+	if (rvzbb_enabled()) {
+		emit(rvzbb_zexth(rd, rs), ctx);
+		return;
+	}
+
+	emit_slli(rd, rs, 48, ctx);
+	emit_srli(rd, rd, 48, ctx);
+}
+
+static inline void emit_zextw(u8 rd, u8 rs, struct rv_jit_context *ctx)
+{
+	emit_slli(rd, rs, 32, ctx);
+	emit_srli(rd, rd, 32, ctx);
+}
+
+static inline void emit_bswap(u8 rd, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvzbb_enabled()) {
+		int bits = 64 - imm;
+
+		emit(rvzbb_rev8(rd, rd), ctx);
+		if (bits)
+			emit_srli(rd, rd, bits, ctx);
+		return;
+	}
+
+	emit_li(RV_REG_T2, 0, ctx);
+
+	emit_andi(RV_REG_T1, rd, 0xff, ctx);
+	emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
+	emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
+	emit_srli(rd, rd, 8, ctx);
+	if (imm == 16)
+		goto out_be;
+
+	emit_andi(RV_REG_T1, rd, 0xff, ctx);
+	emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
+	emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
+	emit_srli(rd, rd, 8, ctx);
+
+	emit_andi(RV_REG_T1, rd, 0xff, ctx);
+	emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
+	emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
+	emit_srli(rd, rd, 8, ctx);
+	if (imm == 32)
+		goto out_be;
+
+	emit_andi(RV_REG_T1, rd, 0xff, ctx);
+	emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
+	emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
+	emit_srli(rd, rd, 8, ctx);
+
+	emit_andi(RV_REG_T1, rd, 0xff, ctx);
+	emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
+	emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
+	emit_srli(rd, rd, 8, ctx);
+
+	emit_andi(RV_REG_T1, rd, 0xff, ctx);
+	emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
+	emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
+	emit_srli(rd, rd, 8, ctx);
+
+	emit_andi(RV_REG_T1, rd, 0xff, ctx);
+	emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
+	emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
+	emit_srli(rd, rd, 8, ctx);
+out_be:
+	emit_andi(RV_REG_T1, rd, 0xff, ctx);
+	emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
+
+	emit_mv(rd, RV_REG_T2, ctx);
+}
+
 #endif /* __riscv_xlen == 64 */
 
 void bpf_jit_build_prologue(struct rv_jit_context *ctx);
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 719a97e7edb2..869e4282a2c4 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -141,6 +141,19 @@ static bool in_auipc_jalr_range(s64 val)
 		val < ((1L << 31) - (1L << 11));
 }
 
+/* Modify rd pointer to alternate reg to avoid corrupting original reg */
+static void emit_sextw_alt(u8 *rd, u8 ra, struct rv_jit_context *ctx)
+{
+	emit_sextw(ra, *rd, ctx);
+	*rd = ra;
+}
+
+static void emit_zextw_alt(u8 *rd, u8 ra, struct rv_jit_context *ctx)
+{
+	emit_zextw(ra, *rd, ctx);
+	*rd = ra;
+}
+
 /* Emit fixed-length instructions for address */
 static int emit_addr(u8 rd, u64 addr, bool extra_pass, struct rv_jit_context *ctx)
 {
@@ -326,12 +339,6 @@ static void emit_branch(u8 cond, u8 rd, u8 rs, int rvoff,
 	emit(rv_jalr(RV_REG_ZERO, RV_REG_T1, lower), ctx);
 }
 
-static void emit_zext_32(u8 reg, struct rv_jit_context *ctx)
-{
-	emit_slli(reg, reg, 32, ctx);
-	emit_srli(reg, reg, 32, ctx);
-}
-
 static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
 {
 	int tc_ninsn, off, start_insn = ctx->ninsns;
@@ -346,7 +353,7 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
 	 */
 	tc_ninsn = insn ? ctx->offset[insn] - ctx->offset[insn - 1] :
 		   ctx->offset[0];
-	emit_zext_32(RV_REG_A2, ctx);
+	emit_zextw(RV_REG_A2, RV_REG_A2, ctx);
 
 	off = offsetof(struct bpf_array, map.max_entries);
 	if (is_12b_check(off, insn))
@@ -405,38 +412,6 @@ static void init_regs(u8 *rd, u8 *rs, const struct bpf_insn *insn,
 		*rs = bpf_to_rv_reg(insn->src_reg, ctx);
 }
 
-static void emit_zext_32_rd_rs(u8 *rd, u8 *rs, struct rv_jit_context *ctx)
-{
-	emit_mv(RV_REG_T2, *rd, ctx);
-	emit_zext_32(RV_REG_T2, ctx);
-	emit_mv(RV_REG_T1, *rs, ctx);
-	emit_zext_32(RV_REG_T1, ctx);
-	*rd = RV_REG_T2;
-	*rs = RV_REG_T1;
-}
-
-static void emit_sext_32_rd_rs(u8 *rd, u8 *rs, struct rv_jit_context *ctx)
-{
-	emit_addiw(RV_REG_T2, *rd, 0, ctx);
-	emit_addiw(RV_REG_T1, *rs, 0, ctx);
-	*rd = RV_REG_T2;
-	*rs = RV_REG_T1;
-}
-
-static void emit_zext_32_rd_t1(u8 *rd, struct rv_jit_context *ctx)
-{
-	emit_mv(RV_REG_T2, *rd, ctx);
-	emit_zext_32(RV_REG_T2, ctx);
-	emit_zext_32(RV_REG_T1, ctx);
-	*rd = RV_REG_T2;
-}
-
-static void emit_sext_32_rd(u8 *rd, struct rv_jit_context *ctx)
-{
-	emit_addiw(RV_REG_T2, *rd, 0, ctx);
-	*rd = RV_REG_T2;
-}
-
 static int emit_jump_and_link(u8 rd, s64 rvoff, bool fixed_addr,
 			      struct rv_jit_context *ctx)
 {
@@ -519,32 +494,32 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64,
 		emit(is64 ? rv_amoadd_d(rs, rs, rd, 0, 0) :
 		     rv_amoadd_w(rs, rs, rd, 0, 0), ctx);
 		if (!is64)
-			emit_zext_32(rs, ctx);
+			emit_zextw(rs, rs, ctx);
 		break;
 	case BPF_AND | BPF_FETCH:
 		emit(is64 ? rv_amoand_d(rs, rs, rd, 0, 0) :
 		     rv_amoand_w(rs, rs, rd, 0, 0), ctx);
 		if (!is64)
-			emit_zext_32(rs, ctx);
+			emit_zextw(rs, rs, ctx);
 		break;
 	case BPF_OR | BPF_FETCH:
 		emit(is64 ? rv_amoor_d(rs, rs, rd, 0, 0) :
 		     rv_amoor_w(rs, rs, rd, 0, 0), ctx);
 		if (!is64)
-			emit_zext_32(rs, ctx);
+			emit_zextw(rs, rs, ctx);
 		break;
 	case BPF_XOR | BPF_FETCH:
 		emit(is64 ? rv_amoxor_d(rs, rs, rd, 0, 0) :
 		     rv_amoxor_w(rs, rs, rd, 0, 0), ctx);
 		if (!is64)
-			emit_zext_32(rs, ctx);
+			emit_zextw(rs, rs, ctx);
 		break;
 	/* src_reg = atomic_xchg(dst_reg + off16, src_reg); */
 	case BPF_XCHG:
 		emit(is64 ? rv_amoswap_d(rs, rs, rd, 0, 0) :
 		     rv_amoswap_w(rs, rs, rd, 0, 0), ctx);
 		if (!is64)
-			emit_zext_32(rs, ctx);
+			emit_zextw(rs, rs, ctx);
 		break;
 	/* r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg); */
 	case BPF_CMPXCHG:
@@ -1091,7 +1066,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU64 | BPF_MOV | BPF_X:
 		if (imm == 1) {
 			/* Special mov32 for zext */
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 			break;
 		}
 		switch (insn->off) {
@@ -1099,16 +1074,17 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			emit_mv(rd, rs, ctx);
 			break;
 		case 8:
+			emit_sextb(rd, rs, ctx);
+			break;
 		case 16:
-			emit_slli(RV_REG_T1, rs, 64 - insn->off, ctx);
-			emit_srai(rd, RV_REG_T1, 64 - insn->off, ctx);
+			emit_sexth(rd, rs, ctx);
 			break;
 		case 32:
-			emit_addiw(rd, rs, 0, ctx);
+			emit_sextw(rd, rs, ctx);
 			break;
 		}
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 
 	/* dst = dst OP src */
@@ -1116,7 +1092,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU64 | BPF_ADD | BPF_X:
 		emit_add(rd, rd, rs, ctx);
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_SUB | BPF_X:
 	case BPF_ALU64 | BPF_SUB | BPF_X:
@@ -1126,31 +1102,31 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			emit_subw(rd, rd, rs, ctx);
 
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_AND | BPF_X:
 	case BPF_ALU64 | BPF_AND | BPF_X:
 		emit_and(rd, rd, rs, ctx);
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_OR | BPF_X:
 	case BPF_ALU64 | BPF_OR | BPF_X:
 		emit_or(rd, rd, rs, ctx);
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_XOR | BPF_X:
 	case BPF_ALU64 | BPF_XOR | BPF_X:
 		emit_xor(rd, rd, rs, ctx);
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_MUL | BPF_X:
 	case BPF_ALU64 | BPF_MUL | BPF_X:
 		emit(is64 ? rv_mul(rd, rd, rs) : rv_mulw(rd, rd, rs), ctx);
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_DIV | BPF_X:
 	case BPF_ALU64 | BPF_DIV | BPF_X:
@@ -1159,7 +1135,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		else
 			emit(is64 ? rv_divu(rd, rd, rs) : rv_divuw(rd, rd, rs), ctx);
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_MOD | BPF_X:
 	case BPF_ALU64 | BPF_MOD | BPF_X:
@@ -1168,25 +1144,25 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		else
 			emit(is64 ? rv_remu(rd, rd, rs) : rv_remuw(rd, rd, rs), ctx);
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_LSH | BPF_X:
 	case BPF_ALU64 | BPF_LSH | BPF_X:
 		emit(is64 ? rv_sll(rd, rd, rs) : rv_sllw(rd, rd, rs), ctx);
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_RSH | BPF_X:
 	case BPF_ALU64 | BPF_RSH | BPF_X:
 		emit(is64 ? rv_srl(rd, rd, rs) : rv_srlw(rd, rd, rs), ctx);
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_ARSH | BPF_X:
 	case BPF_ALU64 | BPF_ARSH | BPF_X:
 		emit(is64 ? rv_sra(rd, rd, rs) : rv_sraw(rd, rd, rs), ctx);
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 
 	/* dst = -dst */
@@ -1194,73 +1170,27 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU64 | BPF_NEG:
 		emit_sub(rd, RV_REG_ZERO, rd, ctx);
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 
 	/* dst = BSWAP##imm(dst) */
 	case BPF_ALU | BPF_END | BPF_FROM_LE:
 		switch (imm) {
 		case 16:
-			emit_slli(rd, rd, 48, ctx);
-			emit_srli(rd, rd, 48, ctx);
+			emit_zexth(rd, rd, ctx);
 			break;
 		case 32:
 			if (!aux->verifier_zext)
-				emit_zext_32(rd, ctx);
+				emit_zextw(rd, rd, ctx);
 			break;
 		case 64:
 			/* Do nothing */
 			break;
 		}
 		break;
-
 	case BPF_ALU | BPF_END | BPF_FROM_BE:
 	case BPF_ALU64 | BPF_END | BPF_FROM_LE:
-		emit_li(RV_REG_T2, 0, ctx);
-
-		emit_andi(RV_REG_T1, rd, 0xff, ctx);
-		emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
-		emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
-		emit_srli(rd, rd, 8, ctx);
-		if (imm == 16)
-			goto out_be;
-
-		emit_andi(RV_REG_T1, rd, 0xff, ctx);
-		emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
-		emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
-		emit_srli(rd, rd, 8, ctx);
-
-		emit_andi(RV_REG_T1, rd, 0xff, ctx);
-		emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
-		emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
-		emit_srli(rd, rd, 8, ctx);
-		if (imm == 32)
-			goto out_be;
-
-		emit_andi(RV_REG_T1, rd, 0xff, ctx);
-		emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
-		emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
-		emit_srli(rd, rd, 8, ctx);
-
-		emit_andi(RV_REG_T1, rd, 0xff, ctx);
-		emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
-		emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
-		emit_srli(rd, rd, 8, ctx);
-
-		emit_andi(RV_REG_T1, rd, 0xff, ctx);
-		emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
-		emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
-		emit_srli(rd, rd, 8, ctx);
-
-		emit_andi(RV_REG_T1, rd, 0xff, ctx);
-		emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
-		emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
-		emit_srli(rd, rd, 8, ctx);
-out_be:
-		emit_andi(RV_REG_T1, rd, 0xff, ctx);
-		emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
-
-		emit_mv(rd, RV_REG_T2, ctx);
+		emit_bswap(rd, imm, ctx);
 		break;
 
 	/* dst = imm */
@@ -1268,7 +1198,7 @@ out_be:
 	case BPF_ALU64 | BPF_MOV | BPF_K:
 		emit_imm(rd, imm, ctx);
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 
 	/* dst = dst OP imm */
@@ -1281,7 +1211,7 @@ out_be:
 			emit_add(rd, rd, RV_REG_T1, ctx);
 		}
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_SUB | BPF_K:
 	case BPF_ALU64 | BPF_SUB | BPF_K:
@@ -1292,7 +1222,7 @@ out_be:
 			emit_sub(rd, rd, RV_REG_T1, ctx);
 		}
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_AND | BPF_K:
 	case BPF_ALU64 | BPF_AND | BPF_K:
@@ -1303,7 +1233,7 @@ out_be:
 			emit_and(rd, rd, RV_REG_T1, ctx);
 		}
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_OR | BPF_K:
 	case BPF_ALU64 | BPF_OR | BPF_K:
@@ -1314,7 +1244,7 @@ out_be:
 			emit_or(rd, rd, RV_REG_T1, ctx);
 		}
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_XOR | BPF_K:
 	case BPF_ALU64 | BPF_XOR | BPF_K:
@@ -1325,7 +1255,7 @@ out_be:
 			emit_xor(rd, rd, RV_REG_T1, ctx);
 		}
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_MUL | BPF_K:
 	case BPF_ALU64 | BPF_MUL | BPF_K:
@@ -1333,7 +1263,7 @@ out_be:
 		emit(is64 ? rv_mul(rd, rd, RV_REG_T1) :
 		     rv_mulw(rd, rd, RV_REG_T1), ctx);
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_DIV | BPF_K:
 	case BPF_ALU64 | BPF_DIV | BPF_K:
@@ -1345,7 +1275,7 @@ out_be:
 			emit(is64 ? rv_divu(rd, rd, RV_REG_T1) :
 			     rv_divuw(rd, rd, RV_REG_T1), ctx);
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_MOD | BPF_K:
 	case BPF_ALU64 | BPF_MOD | BPF_K:
@@ -1357,14 +1287,14 @@ out_be:
 			emit(is64 ? rv_remu(rd, rd, RV_REG_T1) :
 			     rv_remuw(rd, rd, RV_REG_T1), ctx);
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_LSH | BPF_K:
 	case BPF_ALU64 | BPF_LSH | BPF_K:
 		emit_slli(rd, rd, imm, ctx);
 
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_RSH | BPF_K:
 	case BPF_ALU64 | BPF_RSH | BPF_K:
@@ -1374,7 +1304,7 @@ out_be:
 			emit(rv_srliw(rd, rd, imm), ctx);
 
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 	case BPF_ALU | BPF_ARSH | BPF_K:
 	case BPF_ALU64 | BPF_ARSH | BPF_K:
@@ -1384,7 +1314,7 @@ out_be:
 			emit(rv_sraiw(rd, rd, imm), ctx);
 
 		if (!is64 && !aux->verifier_zext)
-			emit_zext_32(rd, ctx);
+			emit_zextw(rd, rd, ctx);
 		break;
 
 	/* JUMP off */
@@ -1425,10 +1355,13 @@ out_be:
 		rvoff = rv_offset(i, off, ctx);
 		if (!is64) {
 			s = ctx->ninsns;
-			if (is_signed_bpf_cond(BPF_OP(code)))
-				emit_sext_32_rd_rs(&rd, &rs, ctx);
-			else
-				emit_zext_32_rd_rs(&rd, &rs, ctx);
+			if (is_signed_bpf_cond(BPF_OP(code))) {
+				emit_sextw_alt(&rs, RV_REG_T1, ctx);
+				emit_sextw_alt(&rd, RV_REG_T2, ctx);
+			} else {
+				emit_zextw_alt(&rs, RV_REG_T1, ctx);
+				emit_zextw_alt(&rd, RV_REG_T2, ctx);
+			}
 			e = ctx->ninsns;
 
 			/* Adjust for extra insns */
@@ -1439,8 +1372,7 @@ out_be:
 			/* Adjust for and */
 			rvoff -= 4;
 			emit_and(RV_REG_T1, rd, rs, ctx);
-			emit_branch(BPF_JNE, RV_REG_T1, RV_REG_ZERO, rvoff,
-				    ctx);
+			emit_branch(BPF_JNE, RV_REG_T1, RV_REG_ZERO, rvoff, ctx);
 		} else {
 			emit_branch(BPF_OP(code), rd, rs, rvoff, ctx);
 		}
@@ -1469,18 +1401,18 @@ out_be:
 	case BPF_JMP32 | BPF_JSLE | BPF_K:
 		rvoff = rv_offset(i, off, ctx);
 		s = ctx->ninsns;
-		if (imm) {
+		if (imm)
 			emit_imm(RV_REG_T1, imm, ctx);
-			rs = RV_REG_T1;
-		} else {
-			/* If imm is 0, simply use zero register. */
-			rs = RV_REG_ZERO;
-		}
+		rs = imm ? RV_REG_T1 : RV_REG_ZERO;
 		if (!is64) {
-			if (is_signed_bpf_cond(BPF_OP(code)))
-				emit_sext_32_rd(&rd, ctx);
-			else
-				emit_zext_32_rd_t1(&rd, ctx);
+			if (is_signed_bpf_cond(BPF_OP(code))) {
+				emit_sextw_alt(&rd, RV_REG_T2, ctx);
+				/* rs has been sign extended */
+			} else {
+				emit_zextw_alt(&rd, RV_REG_T2, ctx);
+				if (imm)
+					emit_zextw(rs, rs, ctx);
+			}
 		}
 		e = ctx->ninsns;
 
@@ -1504,7 +1436,7 @@ out_be:
 		 * as t1 is used only in comparison against zero.
 		 */
 		if (!is64 && imm < 0)
-			emit_addiw(RV_REG_T1, RV_REG_T1, 0, ctx);
+			emit_sextw(RV_REG_T1, RV_REG_T1, ctx);
 		e = ctx->ninsns;
 		rvoff -= ninsns_rvoff(e - s);
 		emit_branch(BPF_JNE, RV_REG_T1, RV_REG_ZERO, rvoff, ctx);
@@ -1874,3 +1806,8 @@ bool bpf_jit_supports_kfunc_call(void)
 {
 	return true;
 }
+
+bool bpf_jit_supports_ptr_xchg(void)
+{
+	return true;
+}