Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:

 1) Support 6Ghz band in ath11k driver, from Rajkumar Manoharan.

 2) Support UDP segmentation in code TSO code, from Eric Dumazet.

 3) Allow flashing different flash images in cxgb4 driver, from Vishal
    Kulkarni.

 4) Add drop frames counter and flow status to tc flower offloading,
    from Po Liu.

 5) Support n-tuple filters in cxgb4, from Vishal Kulkarni.

 6) Various new indirect call avoidance, from Eric Dumazet and Brian
    Vazquez.

 7) Fix BPF verifier failures on 32-bit pointer arithmetic, from
    Yonghong Song.

 8) Support querying and setting hardware address of a port function via
    devlink, use this in mlx5, from Parav Pandit.

 9) Support hw ipsec offload on bonding slaves, from Jarod Wilson.

10) Switch qca8k driver over to phylink, from Jonathan McDowell.

11) In bpftool, show list of processes holding BPF FD references to
    maps, programs, links, and btf objects. From Andrii Nakryiko.

12) Several conversions over to generic power management, from Vaibhav
    Gupta.

13) Add support for SO_KEEPALIVE et al. to bpf_setsockopt(), from Dmitry
    Yakunin.

14) Various https url conversions, from Alexander A. Klimov.

15) Timestamping and PHC support for mscc PHY driver, from Antoine
    Tenart.

16) Support bpf iterating over tcp and udp sockets, from Yonghong Song.

17) Support 5GBASE-T i40e NICs, from Aleksandr Loktionov.

18) Add kTLS RX HW offload support to mlx5e, from Tariq Toukan.

19) Fix the ->ndo_start_xmit() return type to be netdev_tx_t in several
    drivers. From Luc Van Oostenryck.

20) XDP support for xen-netfront, from Denis Kirjanov.

21) Support receive buffer autotuning in MPTCP, from Florian Westphal.

22) Support EF100 chip in sfc driver, from Edward Cree.

23) Add XDP support to mvpp2 driver, from Matteo Croce.

24) Support MPTCP in sock_diag, from Paolo Abeni.

25) Commonize UDP tunnel offloading code by creating udp_tunnel_nic
    infrastructure, from Jakub Kicinski.

26) Several pci_ --> dma_ API conversions, from Christophe JAILLET.

27) Add FLOW_ACTION_POLICE support to mlxsw, from Ido Schimmel.

28) Add SK_LOOKUP bpf program type, from Jakub Sitnicki.

29) Refactor a lot of networking socket option handling code in order to
    avoid set_fs() calls, from Christoph Hellwig.

30) Add rfc4884 support to icmp code, from Willem de Bruijn.

31) Support TBF offload in dpaa2-eth driver, from Ioana Ciornei.

32) Support XDP_REDIRECT in qede driver, from Alexander Lobakin.

33) Support PCI relaxed ordering in mlx5 driver, from Aya Levin.

34) Support TCP syncookies in MPTCP, from Flowian Westphal.

35) Fix several tricky cases of PMTU handling wrt. briding, from Stefano
    Brivio.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2056 commits)
  net: thunderx: initialize VF's mailbox mutex before first usage
  usb: hso: remove bogus check for EINPROGRESS
  usb: hso: no complaint about kmalloc failure
  hso: fix bailout in error case of probe
  ip_tunnel_core: Fix build for archs without _HAVE_ARCH_IPV6_CSUM
  selftests/net: relax cpu affinity requirement in msg_zerocopy test
  mptcp: be careful on subflow creation
  selftests: rtnetlink: make kci_test_encap() return sub-test result
  selftests: rtnetlink: correct the final return value for the test
  net: dsa: sja1105: use detected device id instead of DT one on mismatch
  tipc: set ub->ifindex for local ipv6 address
  ipv6: add ipv6_dev_find()
  net: openvswitch: silence suspicious RCU usage warning
  Revert "vxlan: fix tos value before xmit"
  ptp: only allow phase values lower than 1 period
  farsync: switch from 'pci_' to 'dma_' API
  wan: wanxl: switch from 'pci_' to 'dma_' API
  hv_netvsc: do not use VF device if link is down
  dpaa2-eth: Fix passing zero to 'PTR_ERR' warning
  net: macb: Properly handle phylink on at91sam9x
  ...

4 files changed, 643 insertions, 153 deletions

diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index 20e235d06f66..75c1e9996867 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -13,6 +13,11 @@
 #include <linux/filter.h>
 #include <asm/cacheflush.h>
 
+static inline bool rvc_enabled(void)
+{
+	return IS_ENABLED(CONFIG_RISCV_ISA_C);
+}
+
 enum {
 	RV_REG_ZERO =	0,	/* The constant value 0 */
 	RV_REG_RA =	1,	/* Return address */
@@ -48,9 +53,21 @@ enum {
 	RV_REG_T6 =	31,
 };
 
+static inline bool is_creg(u8 reg)
+{
+	return (1 << reg) & (BIT(RV_REG_FP) |
+			     BIT(RV_REG_S1) |
+			     BIT(RV_REG_A0) |
+			     BIT(RV_REG_A1) |
+			     BIT(RV_REG_A2) |
+			     BIT(RV_REG_A3) |
+			     BIT(RV_REG_A4) |
+			     BIT(RV_REG_A5));
+}
+
 struct rv_jit_context {
 	struct bpf_prog *prog;
-	u32 *insns;		/* RV insns */
+	u16 *insns;		/* RV insns */
 	int ninsns;
 	int epilogue_offset;
 	int *offset;		/* BPF to RV */
@@ -58,6 +75,12 @@ struct rv_jit_context {
 	int stack_size;
 };
 
+/* Convert from ninsns to bytes. */
+static inline int ninsns_rvoff(int ninsns)
+{
+	return ninsns << 1;
+}
+
 struct rv_jit_data {
 	struct bpf_binary_header *header;
 	u8 *image;
@@ -74,8 +97,22 @@ static inline void bpf_flush_icache(void *start, void *end)
 	flush_icache_range((unsigned long)start, (unsigned long)end);
 }
 
+/* Emit a 4-byte riscv instruction. */
 static inline void emit(const u32 insn, struct rv_jit_context *ctx)
 {
+	if (ctx->insns) {
+		ctx->insns[ctx->ninsns] = insn;
+		ctx->insns[ctx->ninsns + 1] = (insn >> 16);
+	}
+
+	ctx->ninsns += 2;
+}
+
+/* Emit a 2-byte riscv compressed instruction. */
+static inline void emitc(const u16 insn, struct rv_jit_context *ctx)
+{
+	BUILD_BUG_ON(!rvc_enabled());
+
 	if (ctx->insns)
 		ctx->insns[ctx->ninsns] = insn;
 
@@ -86,7 +123,7 @@ static inline int epilogue_offset(struct rv_jit_context *ctx)
 {
 	int to = ctx->epilogue_offset, from = ctx->ninsns;
 
-	return (to - from) << 2;
+	return ninsns_rvoff(to - from);
 }
 
 /* Return -1 or inverted cond. */
@@ -117,6 +154,36 @@ static inline int invert_bpf_cond(u8 cond)
 	return -1;
 }
 
+static inline bool is_6b_int(long val)
+{
+	return -(1L << 5) <= val && val < (1L << 5);
+}
+
+static inline bool is_7b_uint(unsigned long val)
+{
+	return val < (1UL << 7);
+}
+
+static inline bool is_8b_uint(unsigned long val)
+{
+	return val < (1UL << 8);
+}
+
+static inline bool is_9b_uint(unsigned long val)
+{
+	return val < (1UL << 9);
+}
+
+static inline bool is_10b_int(long val)
+{
+	return -(1L << 9) <= val && val < (1L << 9);
+}
+
+static inline bool is_10b_uint(unsigned long val)
+{
+	return val < (1UL << 10);
+}
+
 static inline bool is_12b_int(long val)
 {
 	return -(1L << 11) <= val && val < (1L << 11);
@@ -149,7 +216,7 @@ static inline int rv_offset(int insn, int off, struct rv_jit_context *ctx)
 	off++; /* BPF branch is from PC+1, RV is from PC */
 	from = (insn > 0) ? ctx->offset[insn - 1] : 0;
 	to = (insn + off > 0) ? ctx->offset[insn + off - 1] : 0;
-	return (to - from) << 2;
+	return ninsns_rvoff(to - from);
 }
 
 /* Instruction formats. */
@@ -207,6 +274,59 @@ static inline u32 rv_amo_insn(u8 funct5, u8 aq, u8 rl, u8 rs2, u8 rs1,
 	return rv_r_insn(funct7, rs2, rs1, funct3, rd, opcode);
 }
 
+/* RISC-V compressed instruction formats. */
+
+static inline u16 rv_cr_insn(u8 funct4, u8 rd, u8 rs2, u8 op)
+{
+	return (funct4 << 12) | (rd << 7) | (rs2 << 2) | op;
+}
+
+static inline u16 rv_ci_insn(u8 funct3, u32 imm6, u8 rd, u8 op)
+{
+	u32 imm;
+
+	imm = ((imm6 & 0x20) << 7) | ((imm6 & 0x1f) << 2);
+	return (funct3 << 13) | (rd << 7) | op | imm;
+}
+
+static inline u16 rv_css_insn(u8 funct3, u32 uimm, u8 rs2, u8 op)
+{
+	return (funct3 << 13) | (uimm << 7) | (rs2 << 2) | op;
+}
+
+static inline u16 rv_ciw_insn(u8 funct3, u32 uimm, u8 rd, u8 op)
+{
+	return (funct3 << 13) | (uimm << 5) | ((rd & 0x7) << 2) | op;
+}
+
+static inline u16 rv_cl_insn(u8 funct3, u32 imm_hi, u8 rs1, u32 imm_lo, u8 rd,
+			     u8 op)
+{
+	return (funct3 << 13) | (imm_hi << 10) | ((rs1 & 0x7) << 7) |
+		(imm_lo << 5) | ((rd & 0x7) << 2) | op;
+}
+
+static inline u16 rv_cs_insn(u8 funct3, u32 imm_hi, u8 rs1, u32 imm_lo, u8 rs2,
+			     u8 op)
+{
+	return (funct3 << 13) | (imm_hi << 10) | ((rs1 & 0x7) << 7) |
+		(imm_lo << 5) | ((rs2 & 0x7) << 2) | op;
+}
+
+static inline u16 rv_ca_insn(u8 funct6, u8 rd, u8 funct2, u8 rs2, u8 op)
+{
+	return (funct6 << 10) | ((rd & 0x7) << 7) | (funct2 << 5) |
+		((rs2 & 0x7) << 2) | op;
+}
+
+static inline u16 rv_cb_insn(u8 funct3, u32 imm6, u8 funct2, u8 rd, u8 op)
+{
+	u32 imm;
+
+	imm = ((imm6 & 0x20) << 7) | ((imm6 & 0x1f) << 2);
+	return (funct3 << 13) | (funct2 << 10) | ((rd & 0x7) << 7) | op | imm;
+}
+
 /* Instructions shared by both RV32 and RV64. */
 
 static inline u32 rv_addi(u8 rd, u8 rs1, u16 imm11_0)
@@ -414,6 +534,135 @@ static inline u32 rv_amoadd_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
 	return rv_amo_insn(0, aq, rl, rs2, rs1, 2, rd, 0x2f);
 }
 
+/* RVC instrutions. */
+
+static inline u16 rvc_addi4spn(u8 rd, u32 imm10)
+{
+	u32 imm;
+
+	imm = ((imm10 & 0x30) << 2) | ((imm10 & 0x3c0) >> 4) |
+		((imm10 & 0x4) >> 1) | ((imm10 & 0x8) >> 3);
+	return rv_ciw_insn(0x0, imm, rd, 0x0);
+}
+
+static inline u16 rvc_lw(u8 rd, u32 imm7, u8 rs1)
+{
+	u32 imm_hi, imm_lo;
+
+	imm_hi = (imm7 & 0x38) >> 3;
+	imm_lo = ((imm7 & 0x4) >> 1) | ((imm7 & 0x40) >> 6);
+	return rv_cl_insn(0x2, imm_hi, rs1, imm_lo, rd, 0x0);
+}
+
+static inline u16 rvc_sw(u8 rs1, u32 imm7, u8 rs2)
+{
+	u32 imm_hi, imm_lo;
+
+	imm_hi = (imm7 & 0x38) >> 3;
+	imm_lo = ((imm7 & 0x4) >> 1) | ((imm7 & 0x40) >> 6);
+	return rv_cs_insn(0x6, imm_hi, rs1, imm_lo, rs2, 0x0);
+}
+
+static inline u16 rvc_addi(u8 rd, u32 imm6)
+{
+	return rv_ci_insn(0, imm6, rd, 0x1);
+}
+
+static inline u16 rvc_li(u8 rd, u32 imm6)
+{
+	return rv_ci_insn(0x2, imm6, rd, 0x1);
+}
+
+static inline u16 rvc_addi16sp(u32 imm10)
+{
+	u32 imm;
+
+	imm = ((imm10 & 0x200) >> 4) | (imm10 & 0x10) | ((imm10 & 0x40) >> 3) |
+		((imm10 & 0x180) >> 6) | ((imm10 & 0x20) >> 5);
+	return rv_ci_insn(0x3, imm, RV_REG_SP, 0x1);
+}
+
+static inline u16 rvc_lui(u8 rd, u32 imm6)
+{
+	return rv_ci_insn(0x3, imm6, rd, 0x1);
+}
+
+static inline u16 rvc_srli(u8 rd, u32 imm6)
+{
+	return rv_cb_insn(0x4, imm6, 0, rd, 0x1);
+}
+
+static inline u16 rvc_srai(u8 rd, u32 imm6)
+{
+	return rv_cb_insn(0x4, imm6, 0x1, rd, 0x1);
+}
+
+static inline u16 rvc_andi(u8 rd, u32 imm6)
+{
+	return rv_cb_insn(0x4, imm6, 0x2, rd, 0x1);
+}
+
+static inline u16 rvc_sub(u8 rd, u8 rs)
+{
+	return rv_ca_insn(0x23, rd, 0, rs, 0x1);
+}
+
+static inline u16 rvc_xor(u8 rd, u8 rs)
+{
+	return rv_ca_insn(0x23, rd, 0x1, rs, 0x1);
+}
+
+static inline u16 rvc_or(u8 rd, u8 rs)
+{
+	return rv_ca_insn(0x23, rd, 0x2, rs, 0x1);
+}
+
+static inline u16 rvc_and(u8 rd, u8 rs)
+{
+	return rv_ca_insn(0x23, rd, 0x3, rs, 0x1);
+}
+
+static inline u16 rvc_slli(u8 rd, u32 imm6)
+{
+	return rv_ci_insn(0, imm6, rd, 0x2);
+}
+
+static inline u16 rvc_lwsp(u8 rd, u32 imm8)
+{
+	u32 imm;
+
+	imm = ((imm8 & 0xc0) >> 6) | (imm8 & 0x3c);
+	return rv_ci_insn(0x2, imm, rd, 0x2);
+}
+
+static inline u16 rvc_jr(u8 rs1)
+{
+	return rv_cr_insn(0x8, rs1, RV_REG_ZERO, 0x2);
+}
+
+static inline u16 rvc_mv(u8 rd, u8 rs)
+{
+	return rv_cr_insn(0x8, rd, rs, 0x2);
+}
+
+static inline u16 rvc_jalr(u8 rs1)
+{
+	return rv_cr_insn(0x9, rs1, RV_REG_ZERO, 0x2);
+}
+
+static inline u16 rvc_add(u8 rd, u8 rs)
+{
+	return rv_cr_insn(0x9, rd, rs, 0x2);
+}
+
+static inline u16 rvc_swsp(u32 imm8, u8 rs2)
+{
+	u32 imm;
+
+	imm = (imm8 & 0x3c) | ((imm8 & 0xc0) >> 6);
+	return rv_css_insn(0x6, imm, rs2, 0x2);
+}
+
 /*
  * RV64-only instructions.
  *
@@ -503,6 +752,234 @@ static inline u32 rv_amoadd_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
 	return rv_amo_insn(0, aq, rl, rs2, rs1, 3, rd, 0x2f);
 }
 
+/* RV64-only RVC instructions. */
+
+static inline u16 rvc_ld(u8 rd, u32 imm8, u8 rs1)
+{
+	u32 imm_hi, imm_lo;
+
+	imm_hi = (imm8 & 0x38) >> 3;
+	imm_lo = (imm8 & 0xc0) >> 6;
+	return rv_cl_insn(0x3, imm_hi, rs1, imm_lo, rd, 0x0);
+}
+
+static inline u16 rvc_sd(u8 rs1, u32 imm8, u8 rs2)
+{
+	u32 imm_hi, imm_lo;
+
+	imm_hi = (imm8 & 0x38) >> 3;
+	imm_lo = (imm8 & 0xc0) >> 6;
+	return rv_cs_insn(0x7, imm_hi, rs1, imm_lo, rs2, 0x0);
+}
+
+static inline u16 rvc_subw(u8 rd, u8 rs)
+{
+	return rv_ca_insn(0x27, rd, 0, rs, 0x1);
+}
+
+static inline u16 rvc_addiw(u8 rd, u32 imm6)
+{
+	return rv_ci_insn(0x1, imm6, rd, 0x1);
+}
+
+static inline u16 rvc_ldsp(u8 rd, u32 imm9)
+{
+	u32 imm;
+
+	imm = ((imm9 & 0x1c0) >> 6) | (imm9 & 0x38);
+	return rv_ci_insn(0x3, imm, rd, 0x2);
+}
+
+static inline u16 rvc_sdsp(u32 imm9, u8 rs2)
+{
+	u32 imm;
+
+	imm = (imm9 & 0x38) | ((imm9 & 0x1c0) >> 6);
+	return rv_css_insn(0x7, imm, rs2, 0x2);
+}
+
+#endif /* __riscv_xlen == 64 */
+
+/* Helper functions that emit RVC instructions when possible. */
+
+static inline void emit_jalr(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rd == RV_REG_RA && rs && !imm)
+		emitc(rvc_jalr(rs), ctx);
+	else if (rvc_enabled() && !rd && rs && !imm)
+		emitc(rvc_jr(rs), ctx);
+	else
+		emit(rv_jalr(rd, rs, imm), ctx);
+}
+
+static inline void emit_mv(u8 rd, u8 rs, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rd && rs)
+		emitc(rvc_mv(rd, rs), ctx);
+	else
+		emit(rv_addi(rd, rs, 0), ctx);
+}
+
+static inline void emit_add(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rd && rd == rs1 && rs2)
+		emitc(rvc_add(rd, rs2), ctx);
+	else
+		emit(rv_add(rd, rs1, rs2), ctx);
+}
+
+static inline void emit_addi(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rd == RV_REG_SP && rd == rs && is_10b_int(imm) && imm && !(imm & 0xf))
+		emitc(rvc_addi16sp(imm), ctx);
+	else if (rvc_enabled() && is_creg(rd) && rs == RV_REG_SP && is_10b_uint(imm) &&
+		 !(imm & 0x3) && imm)
+		emitc(rvc_addi4spn(rd, imm), ctx);
+	else if (rvc_enabled() && rd && rd == rs && imm && is_6b_int(imm))
+		emitc(rvc_addi(rd, imm), ctx);
+	else
+		emit(rv_addi(rd, rs, imm), ctx);
+}
+
+static inline void emit_li(u8 rd, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rd && is_6b_int(imm))
+		emitc(rvc_li(rd, imm), ctx);
+	else
+		emit(rv_addi(rd, RV_REG_ZERO, imm), ctx);
+}
+
+static inline void emit_lui(u8 rd, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rd && rd != RV_REG_SP && is_6b_int(imm) && imm)
+		emitc(rvc_lui(rd, imm), ctx);
+	else
+		emit(rv_lui(rd, imm), ctx);
+}
+
+static inline void emit_slli(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rd && rd == rs && imm && (u32)imm < __riscv_xlen)
+		emitc(rvc_slli(rd, imm), ctx);
+	else
+		emit(rv_slli(rd, rs, imm), ctx);
+}
+
+static inline void emit_andi(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && is_creg(rd) && rd == rs && is_6b_int(imm))
+		emitc(rvc_andi(rd, imm), ctx);
+	else
+		emit(rv_andi(rd, rs, imm), ctx);
+}
+
+static inline void emit_srli(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && is_creg(rd) && rd == rs && imm && (u32)imm < __riscv_xlen)
+		emitc(rvc_srli(rd, imm), ctx);
+	else
+		emit(rv_srli(rd, rs, imm), ctx);
+}
+
+static inline void emit_srai(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && is_creg(rd) && rd == rs && imm && (u32)imm < __riscv_xlen)
+		emitc(rvc_srai(rd, imm), ctx);
+	else
+		emit(rv_srai(rd, rs, imm), ctx);
+}
+
+static inline void emit_sub(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && is_creg(rd) && rd == rs1 && is_creg(rs2))
+		emitc(rvc_sub(rd, rs2), ctx);
+	else
+		emit(rv_sub(rd, rs1, rs2), ctx);
+}
+
+static inline void emit_or(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && is_creg(rd) && rd == rs1 && is_creg(rs2))
+		emitc(rvc_or(rd, rs2), ctx);
+	else
+		emit(rv_or(rd, rs1, rs2), ctx);
+}
+
+static inline void emit_and(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && is_creg(rd) && rd == rs1 && is_creg(rs2))
+		emitc(rvc_and(rd, rs2), ctx);
+	else
+		emit(rv_and(rd, rs1, rs2), ctx);
+}
+
+static inline void emit_xor(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && is_creg(rd) && rd == rs1 && is_creg(rs2))
+		emitc(rvc_xor(rd, rs2), ctx);
+	else
+		emit(rv_xor(rd, rs1, rs2), ctx);
+}
+
+static inline void emit_lw(u8 rd, s32 off, u8 rs1, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rs1 == RV_REG_SP && rd && is_8b_uint(off) && !(off & 0x3))
+		emitc(rvc_lwsp(rd, off), ctx);
+	else if (rvc_enabled() && is_creg(rd) && is_creg(rs1) && is_7b_uint(off) && !(off & 0x3))
+		emitc(rvc_lw(rd, off, rs1), ctx);
+	else
+		emit(rv_lw(rd, off, rs1), ctx);
+}
+
+static inline void emit_sw(u8 rs1, s32 off, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rs1 == RV_REG_SP && is_8b_uint(off) && !(off & 0x3))
+		emitc(rvc_swsp(off, rs2), ctx);
+	else if (rvc_enabled() && is_creg(rs1) && is_creg(rs2) && is_7b_uint(off) && !(off & 0x3))
+		emitc(rvc_sw(rs1, off, rs2), ctx);
+	else
+		emit(rv_sw(rs1, off, rs2), ctx);
+}
+
+/* RV64-only helper functions. */
+#if __riscv_xlen == 64
+
+static inline void emit_addiw(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rd && rd == rs && is_6b_int(imm))
+		emitc(rvc_addiw(rd, imm), ctx);
+	else
+		emit(rv_addiw(rd, rs, imm), ctx);
+}
+
+static inline void emit_ld(u8 rd, s32 off, u8 rs1, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rs1 == RV_REG_SP && rd && is_9b_uint(off) && !(off & 0x7))
+		emitc(rvc_ldsp(rd, off), ctx);
+	else if (rvc_enabled() && is_creg(rd) && is_creg(rs1) && is_8b_uint(off) && !(off & 0x7))
+		emitc(rvc_ld(rd, off, rs1), ctx);
+	else
+		emit(rv_ld(rd, off, rs1), ctx);
+}
+
+static inline void emit_sd(u8 rs1, s32 off, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && rs1 == RV_REG_SP && is_9b_uint(off) && !(off & 0x7))
+		emitc(rvc_sdsp(off, rs2), ctx);
+	else if (rvc_enabled() && is_creg(rs1) && is_creg(rs2) && is_8b_uint(off) && !(off & 0x7))
+		emitc(rvc_sd(rs1, off, rs2), ctx);
+	else
+		emit(rv_sd(rs1, off, rs2), ctx);
+}
+
+static inline void emit_subw(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvc_enabled() && is_creg(rd) && rd == rs1 && is_creg(rs2))
+		emitc(rvc_subw(rd, rs2), ctx);
+	else
+		emit(rv_subw(rd, rs1, rs2), ctx);
+}
+
 #endif /* __riscv_xlen == 64 */
 
 void bpf_jit_build_prologue(struct rv_jit_context *ctx);
diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c
index b198eaa74456..bc5f2204693f 100644
--- a/arch/riscv/net/bpf_jit_comp32.c
+++ b/arch/riscv/net/bpf_jit_comp32.c
@@ -644,7 +644,7 @@ static int emit_branch_r64(const s8 *src1, const s8 *src2, s32 rvoff,
 
 	e = ctx->ninsns;
 	/* Adjust for extra insns. */
-	rvoff -= (e - s) << 2;
+	rvoff -= ninsns_rvoff(e - s);
 	emit_jump_and_link(RV_REG_ZERO, rvoff, true, ctx);
 	return 0;
 }
@@ -713,7 +713,7 @@ static int emit_bcc(u8 op, u8 rd, u8 rs, int rvoff, struct rv_jit_context *ctx)
 	if (far) {
 		e = ctx->ninsns;
 		/* Adjust for extra insns. */
-		rvoff -= (e - s) << 2;
+		rvoff -= ninsns_rvoff(e - s);
 		emit_jump_and_link(RV_REG_ZERO, rvoff, true, ctx);
 	}
 	return 0;
@@ -731,7 +731,7 @@ static int emit_branch_r32(const s8 *src1, const s8 *src2, s32 rvoff,
 
 	e = ctx->ninsns;
 	/* Adjust for extra insns. */
-	rvoff -= (e - s) << 2;
+	rvoff -= ninsns_rvoff(e - s);
 
 	if (emit_bcc(op, lo(rs1), lo(rs2), rvoff, ctx))
 		return -1;
@@ -795,7 +795,7 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
 	 * if (index >= max_entries)
 	 *   goto out;
 	 */
-	off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2;
+	off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn));
 	emit_bcc(BPF_JGE, lo(idx_reg), RV_REG_T1, off, ctx);
 
 	/*
@@ -804,7 +804,7 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
 	 *   goto out;
 	 */
 	emit(rv_addi(RV_REG_T1, RV_REG_TCC, -1), ctx);
-	off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2;
+	off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn));
 	emit_bcc(BPF_JSLT, RV_REG_TCC, RV_REG_ZERO, off, ctx);
 
 	/*
@@ -818,7 +818,7 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
 	if (is_12b_check(off, insn))
 		return -1;
 	emit(rv_lw(RV_REG_T0, off, RV_REG_T0), ctx);
-	off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2;
+	off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn));
 	emit_bcc(BPF_JEQ, RV_REG_T0, RV_REG_ZERO, off, ctx);
 
 	/*
@@ -1214,7 +1214,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			emit_imm32(tmp2, imm, ctx);
 			src = tmp2;
 			e = ctx->ninsns;
-			rvoff -= (e - s) << 2;
+			rvoff -= ninsns_rvoff(e - s);
 		}
 
 		if (is64)
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 6cfd164cbe88..8a56b5293117 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -132,19 +132,23 @@ static void emit_imm(u8 rd, s64 val, struct rv_jit_context *ctx)
 	 *
 	 * This also means that we need to process LSB to MSB.
 	 */
-	s64 upper = (val + (1 << 11)) >> 12, lower = val & 0xfff;
+	s64 upper = (val + (1 << 11)) >> 12;
+	/* Sign-extend lower 12 bits to 64 bits since immediates for li, addiw,
+	 * and addi are signed and RVC checks will perform signed comparisons.
+	 */
+	s64 lower = ((val & 0xfff) << 52) >> 52;
 	int shift;
 
 	if (is_32b_int(val)) {
 		if (upper)
-			emit(rv_lui(rd, upper), ctx);
+			emit_lui(rd, upper, ctx);
 
 		if (!upper) {
-			emit(rv_addi(rd, RV_REG_ZERO, lower), ctx);
+			emit_li(rd, lower, ctx);
 			return;
 		}
 
-		emit(rv_addiw(rd, rd, lower), ctx);
+		emit_addiw(rd, rd, lower, ctx);
 		return;
 	}
 
@@ -154,9 +158,9 @@ static void emit_imm(u8 rd, s64 val, struct rv_jit_context *ctx)
 
 	emit_imm(rd, upper, ctx);
 
-	emit(rv_slli(rd, rd, shift), ctx);
+	emit_slli(rd, rd, shift, ctx);
 	if (lower)
-		emit(rv_addi(rd, rd, lower), ctx);
+		emit_addi(rd, rd, lower, ctx);
 }
 
 static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx)
@@ -164,43 +168,43 @@ static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx)
 	int stack_adjust = ctx->stack_size, store_offset = stack_adjust - 8;
 
 	if (seen_reg(RV_REG_RA, ctx)) {
-		emit(rv_ld(RV_REG_RA, store_offset, RV_REG_SP), ctx);
+		emit_ld(RV_REG_RA, store_offset, RV_REG_SP, ctx);
 		store_offset -= 8;
 	}
-	emit(rv_ld(RV_REG_FP, store_offset, RV_REG_SP), ctx);
+	emit_ld(RV_REG_FP, store_offset, RV_REG_SP, ctx);
 	store_offset -= 8;
 	if (seen_reg(RV_REG_S1, ctx)) {
-		emit(rv_ld(RV_REG_S1, store_offset, RV_REG_SP), ctx);
+		emit_ld(RV_REG_S1, store_offset, RV_REG_SP, ctx);
 		store_offset -= 8;
 	}
 	if (seen_reg(RV_REG_S2, ctx)) {
-		emit(rv_ld(RV_REG_S2, store_offset, RV_REG_SP), ctx);
+		emit_ld(RV_REG_S2, store_offset, RV_REG_SP, ctx);
 		store_offset -= 8;
 	}
 	if (seen_reg(RV_REG_S3, ctx)) {
-		emit(rv_ld(RV_REG_S3, store_offset, RV_REG_SP), ctx);
+		emit_ld(RV_REG_S3, store_offset, RV_REG_SP, ctx);
 		store_offset -= 8;
 	}
 	if (seen_reg(RV_REG_S4, ctx)) {
-		emit(rv_ld(RV_REG_S4, store_offset, RV_REG_SP), ctx);
+		emit_ld(RV_REG_S4, store_offset, RV_REG_SP, ctx);
 		store_offset -= 8;
 	}
 	if (seen_reg(RV_REG_S5, ctx)) {
-		emit(rv_ld(RV_REG_S5, store_offset, RV_REG_SP), ctx);
+		emit_ld(RV_REG_S5, store_offset, RV_REG_SP, ctx);
 		store_offset -= 8;
 	}
 	if (seen_reg(RV_REG_S6, ctx)) {
-		emit(rv_ld(RV_REG_S6, store_offset, RV_REG_SP), ctx);
+		emit_ld(RV_REG_S6, store_offset, RV_REG_SP, ctx);
 		store_offset -= 8;
 	}
 
-	emit(rv_addi(RV_REG_SP, RV_REG_SP, stack_adjust), ctx);
+	emit_addi(RV_REG_SP, RV_REG_SP, stack_adjust, ctx);
 	/* Set return value. */
 	if (!is_tail_call)
-		emit(rv_addi(RV_REG_A0, RV_REG_A5, 0), ctx);
-	emit(rv_jalr(RV_REG_ZERO, is_tail_call ? RV_REG_T3 : RV_REG_RA,
-		     is_tail_call ? 4 : 0), /* skip TCC init */
-	     ctx);
+		emit_mv(RV_REG_A0, RV_REG_A5, ctx);
+	emit_jalr(RV_REG_ZERO, is_tail_call ? RV_REG_T3 : RV_REG_RA,
+		  is_tail_call ? 4 : 0, /* skip TCC init */
+		  ctx);
 }
 
 static void emit_bcc(u8 cond, u8 rd, u8 rs, int rvoff,
@@ -280,8 +284,8 @@ static void emit_branch(u8 cond, u8 rd, u8 rs, int rvoff,
 
 static void emit_zext_32(u8 reg, struct rv_jit_context *ctx)
 {
-	emit(rv_slli(reg, reg, 32), ctx);
-	emit(rv_srli(reg, reg, 32), 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)
@@ -304,35 +308,35 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
 	if (is_12b_check(off, insn))
 		return -1;
 	emit(rv_lwu(RV_REG_T1, off, RV_REG_A1), ctx);
-	off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2;
+	off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn));
 	emit_branch(BPF_JGE, RV_REG_A2, RV_REG_T1, off, ctx);
 
 	/* if (TCC-- < 0)
 	 *     goto out;
 	 */
-	emit(rv_addi(RV_REG_T1, tcc, -1), ctx);
-	off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2;
+	emit_addi(RV_REG_T1, tcc, -1, ctx);
+	off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn));
 	emit_branch(BPF_JSLT, tcc, RV_REG_ZERO, off, ctx);
 
 	/* prog = array->ptrs[index];
 	 * if (!prog)
 	 *     goto out;
 	 */
-	emit(rv_slli(RV_REG_T2, RV_REG_A2, 3), ctx);
-	emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_A1), ctx);
+	emit_slli(RV_REG_T2, RV_REG_A2, 3, ctx);
+	emit_add(RV_REG_T2, RV_REG_T2, RV_REG_A1, ctx);
 	off = offsetof(struct bpf_array, ptrs);
 	if (is_12b_check(off, insn))
 		return -1;
-	emit(rv_ld(RV_REG_T2, off, RV_REG_T2), ctx);
-	off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2;
+	emit_ld(RV_REG_T2, off, RV_REG_T2, ctx);
+	off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn));
 	emit_branch(BPF_JEQ, RV_REG_T2, RV_REG_ZERO, off, ctx);
 
 	/* goto *(prog->bpf_func + 4); */
 	off = offsetof(struct bpf_prog, bpf_func);
 	if (is_12b_check(off, insn))
 		return -1;
-	emit(rv_ld(RV_REG_T3, off, RV_REG_T2), ctx);
-	emit(rv_addi(RV_REG_TCC, RV_REG_T1, 0), ctx);
+	emit_ld(RV_REG_T3, off, RV_REG_T2, ctx);
+	emit_mv(RV_REG_TCC, RV_REG_T1, ctx);
 	__build_epilogue(true, ctx);
 	return 0;
 }
@@ -360,9 +364,9 @@ static void init_regs(u8 *rd, u8 *rs, const struct bpf_insn *insn,
 
 static void emit_zext_32_rd_rs(u8 *rd, u8 *rs, struct rv_jit_context *ctx)
 {
-	emit(rv_addi(RV_REG_T2, *rd, 0), ctx);
+	emit_mv(RV_REG_T2, *rd, ctx);
 	emit_zext_32(RV_REG_T2, ctx);
-	emit(rv_addi(RV_REG_T1, *rs, 0), ctx);
+	emit_mv(RV_REG_T1, *rs, ctx);
 	emit_zext_32(RV_REG_T1, ctx);
 	*rd = RV_REG_T2;
 	*rs = RV_REG_T1;
@@ -370,15 +374,15 @@ static void emit_zext_32_rd_rs(u8 *rd, u8 *rs, struct rv_jit_context *ctx)
 
 static void emit_sext_32_rd_rs(u8 *rd, u8 *rs, struct rv_jit_context *ctx)
 {
-	emit(rv_addiw(RV_REG_T2, *rd, 0), ctx);
-	emit(rv_addiw(RV_REG_T1, *rs, 0), 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(rv_addi(RV_REG_T2, *rd, 0), 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;
@@ -386,7 +390,7 @@ static void emit_zext_32_rd_t1(u8 *rd, struct rv_jit_context *ctx)
 
 static void emit_sext_32_rd(u8 *rd, struct rv_jit_context *ctx)
 {
-	emit(rv_addiw(RV_REG_T2, *rd, 0), ctx);
+	emit_addiw(RV_REG_T2, *rd, 0, ctx);
 	*rd = RV_REG_T2;
 }
 
@@ -432,7 +436,7 @@ static int emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx)
 	if (ret)
 		return ret;
 	rd = bpf_to_rv_reg(BPF_REG_0, ctx);
-	emit(rv_addi(rd, RV_REG_A0, 0), ctx);
+	emit_mv(rd, RV_REG_A0, ctx);
 	return 0;
 }
 
@@ -458,7 +462,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			emit_zext_32(rd, ctx);
 			break;
 		}
-		emit(is64 ? rv_addi(rd, rs, 0) : rv_addiw(rd, rs, 0), ctx);
+		emit_mv(rd, rs, ctx);
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
@@ -466,31 +470,35 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	/* dst = dst OP src */
 	case BPF_ALU | BPF_ADD | BPF_X:
 	case BPF_ALU64 | BPF_ADD | BPF_X:
-		emit(is64 ? rv_add(rd, rd, rs) : rv_addw(rd, rd, rs), ctx);
+		emit_add(rd, rd, rs, ctx);
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_SUB | BPF_X:
 	case BPF_ALU64 | BPF_SUB | BPF_X:
-		emit(is64 ? rv_sub(rd, rd, rs) : rv_subw(rd, rd, rs), ctx);
+		if (is64)
+			emit_sub(rd, rd, rs, ctx);
+		else
+			emit_subw(rd, rd, rs, ctx);
+
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_AND | BPF_X:
 	case BPF_ALU64 | BPF_AND | BPF_X:
-		emit(rv_and(rd, rd, rs), ctx);
+		emit_and(rd, rd, rs, ctx);
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_OR | BPF_X:
 	case BPF_ALU64 | BPF_OR | BPF_X:
-		emit(rv_or(rd, rd, rs), ctx);
+		emit_or(rd, rd, rs, ctx);
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_XOR | BPF_X:
 	case BPF_ALU64 | BPF_XOR | BPF_X:
-		emit(rv_xor(rd, rd, rs), ctx);
+		emit_xor(rd, rd, rs, ctx);
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
@@ -534,8 +542,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	/* dst = -dst */
 	case BPF_ALU | BPF_NEG:
 	case BPF_ALU64 | BPF_NEG:
-		emit(is64 ? rv_sub(rd, RV_REG_ZERO, rd) :
-		     rv_subw(rd, RV_REG_ZERO, rd), ctx);
+		emit_sub(rd, RV_REG_ZERO, rd, ctx);
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
@@ -544,8 +551,8 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU | BPF_END | BPF_FROM_LE:
 		switch (imm) {
 		case 16:
-			emit(rv_slli(rd, rd, 48), ctx);
-			emit(rv_srli(rd, rd, 48), ctx);
+			emit_slli(rd, rd, 48, ctx);
+			emit_srli(rd, rd, 48, ctx);
 			break;
 		case 32:
 			if (!aux->verifier_zext)
@@ -558,51 +565,51 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		break;
 
 	case BPF_ALU | BPF_END | BPF_FROM_BE:
-		emit(rv_addi(RV_REG_T2, RV_REG_ZERO, 0), ctx);
+		emit_li(RV_REG_T2, 0, ctx);
 
-		emit(rv_andi(RV_REG_T1, rd, 0xff), ctx);
-		emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx);
-		emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx);
-		emit(rv_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 == 16)
 			goto out_be;
 
-		emit(rv_andi(RV_REG_T1, rd, 0xff), ctx);
-		emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx);
-		emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx);
-		emit(rv_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(rv_andi(RV_REG_T1, rd, 0xff), ctx);
-		emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx);
-		emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx);
-		emit(rv_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(rv_andi(RV_REG_T1, rd, 0xff), ctx);
-		emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx);
-		emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx);
-		emit(rv_srli(rd, rd, 8), ctx);
-
-		emit(rv_andi(RV_REG_T1, rd, 0xff), ctx);
-		emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx);
-		emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx);
-		emit(rv_srli(rd, rd, 8), ctx);
-
-		emit(rv_andi(RV_REG_T1, rd, 0xff), ctx);
-		emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx);
-		emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx);
-		emit(rv_srli(rd, rd, 8), ctx);
-
-		emit(rv_andi(RV_REG_T1, rd, 0xff), ctx);
-		emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx);
-		emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx);
-		emit(rv_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);
+
+		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(rv_andi(RV_REG_T1, rd, 0xff), ctx);
-		emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx);
+		emit_andi(RV_REG_T1, rd, 0xff, ctx);
+		emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
 
-		emit(rv_addi(rd, RV_REG_T2, 0), ctx);
+		emit_mv(rd, RV_REG_T2, ctx);
 		break;
 
 	/* dst = imm */
@@ -617,12 +624,10 @@ out_be:
 	case BPF_ALU | BPF_ADD | BPF_K:
 	case BPF_ALU64 | BPF_ADD | BPF_K:
 		if (is_12b_int(imm)) {
-			emit(is64 ? rv_addi(rd, rd, imm) :
-			     rv_addiw(rd, rd, imm), ctx);
+			emit_addi(rd, rd, imm, ctx);
 		} else {
 			emit_imm(RV_REG_T1, imm, ctx);
-			emit(is64 ? rv_add(rd, rd, RV_REG_T1) :
-			     rv_addw(rd, rd, RV_REG_T1), ctx);
+			emit_add(rd, rd, RV_REG_T1, ctx);
 		}
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
@@ -630,12 +635,10 @@ out_be:
 	case BPF_ALU | BPF_SUB | BPF_K:
 	case BPF_ALU64 | BPF_SUB | BPF_K:
 		if (is_12b_int(-imm)) {
-			emit(is64 ? rv_addi(rd, rd, -imm) :
-			     rv_addiw(rd, rd, -imm), ctx);
+			emit_addi(rd, rd, -imm, ctx);
 		} else {
 			emit_imm(RV_REG_T1, imm, ctx);
-			emit(is64 ? rv_sub(rd, rd, RV_REG_T1) :
-			     rv_subw(rd, rd, RV_REG_T1), ctx);
+			emit_sub(rd, rd, RV_REG_T1, ctx);
 		}
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
@@ -643,10 +646,10 @@ out_be:
 	case BPF_ALU | BPF_AND | BPF_K:
 	case BPF_ALU64 | BPF_AND | BPF_K:
 		if (is_12b_int(imm)) {
-			emit(rv_andi(rd, rd, imm), ctx);
+			emit_andi(rd, rd, imm, ctx);
 		} else {
 			emit_imm(RV_REG_T1, imm, ctx);
-			emit(rv_and(rd, rd, RV_REG_T1), ctx);
+			emit_and(rd, rd, RV_REG_T1, ctx);
 		}
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
@@ -657,7 +660,7 @@ out_be:
 			emit(rv_ori(rd, rd, imm), ctx);
 		} else {
 			emit_imm(RV_REG_T1, imm, ctx);
-			emit(rv_or(rd, rd, RV_REG_T1), ctx);
+			emit_or(rd, rd, RV_REG_T1, ctx);
 		}
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
@@ -668,7 +671,7 @@ out_be:
 			emit(rv_xori(rd, rd, imm), ctx);
 		} else {
 			emit_imm(RV_REG_T1, imm, ctx);
-			emit(rv_xor(rd, rd, RV_REG_T1), ctx);
+			emit_xor(rd, rd, RV_REG_T1, ctx);
 		}
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
@@ -699,19 +702,28 @@ out_be:
 		break;
 	case BPF_ALU | BPF_LSH | BPF_K:
 	case BPF_ALU64 | BPF_LSH | BPF_K:
-		emit(is64 ? rv_slli(rd, rd, imm) : rv_slliw(rd, rd, imm), ctx);
+		emit_slli(rd, rd, imm, ctx);
+
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_RSH | BPF_K:
 	case BPF_ALU64 | BPF_RSH | BPF_K:
-		emit(is64 ? rv_srli(rd, rd, imm) : rv_srliw(rd, rd, imm), ctx);
+		if (is64)
+			emit_srli(rd, rd, imm, ctx);
+		else
+			emit(rv_srliw(rd, rd, imm), ctx);
+
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_ARSH | BPF_K:
 	case BPF_ALU64 | BPF_ARSH | BPF_K:
-		emit(is64 ? rv_srai(rd, rd, imm) : rv_sraiw(rd, rd, imm), ctx);
+		if (is64)
+			emit_srai(rd, rd, imm, ctx);
+		else
+			emit(rv_sraiw(rd, rd, imm), ctx);
+
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
@@ -757,13 +769,13 @@ out_be:
 			e = ctx->ninsns;
 
 			/* Adjust for extra insns */
-			rvoff -= (e - s) << 2;
+			rvoff -= ninsns_rvoff(e - s);
 		}
 
 		if (BPF_OP(code) == BPF_JSET) {
 			/* Adjust for and */
 			rvoff -= 4;
-			emit(rv_and(RV_REG_T1, rd, rs), ctx);
+			emit_and(RV_REG_T1, rd, rs, ctx);
 			emit_branch(BPF_JNE, RV_REG_T1, RV_REG_ZERO, rvoff,
 				    ctx);
 		} else {
@@ -810,7 +822,7 @@ out_be:
 		e = ctx->ninsns;
 
 		/* Adjust for extra insns */
-		rvoff -= (e - s) << 2;
+		rvoff -= ninsns_rvoff(e - s);
 		emit_branch(BPF_OP(code), rd, rs, rvoff, ctx);
 		break;
 
@@ -819,19 +831,19 @@ out_be:
 		rvoff = rv_offset(i, off, ctx);
 		s = ctx->ninsns;
 		if (is_12b_int(imm)) {
-			emit(rv_andi(RV_REG_T1, rd, imm), ctx);
+			emit_andi(RV_REG_T1, rd, imm, ctx);
 		} else {
 			emit_imm(RV_REG_T1, imm, ctx);
-			emit(rv_and(RV_REG_T1, rd, RV_REG_T1), ctx);
+			emit_and(RV_REG_T1, rd, RV_REG_T1, ctx);
 		}
 		/* For jset32, we should clear the upper 32 bits of t1, but
 		 * sign-extension is sufficient here and saves one instruction,
 		 * as t1 is used only in comparison against zero.
 		 */
 		if (!is64 && imm < 0)
-			emit(rv_addiw(RV_REG_T1, RV_REG_T1, 0), ctx);
+			emit_addiw(RV_REG_T1, RV_REG_T1, 0, ctx);
 		e = ctx->ninsns;
-		rvoff -= (e - s) << 2;
+		rvoff -= ninsns_rvoff(e - s);
 		emit_branch(BPF_JNE, RV_REG_T1, RV_REG_ZERO, rvoff, ctx);
 		break;
 
@@ -887,7 +899,7 @@ out_be:
 		}
 
 		emit_imm(RV_REG_T1, off, ctx);
-		emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx);
+		emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
 		emit(rv_lbu(rd, 0, RV_REG_T1), ctx);
 		if (insn_is_zext(&insn[1]))
 			return 1;
@@ -899,7 +911,7 @@ out_be:
 		}
 
 		emit_imm(RV_REG_T1, off, ctx);
-		emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx);
+		emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
 		emit(rv_lhu(rd, 0, RV_REG_T1), ctx);
 		if (insn_is_zext(&insn[1]))
 			return 1;
@@ -911,20 +923,20 @@ out_be:
 		}
 
 		emit_imm(RV_REG_T1, off, ctx);
-		emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx);
+		emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
 		emit(rv_lwu(rd, 0, RV_REG_T1), ctx);
 		if (insn_is_zext(&insn[1]))
 			return 1;
 		break;
 	case BPF_LDX | BPF_MEM | BPF_DW:
 		if (is_12b_int(off)) {
-			emit(rv_ld(rd, off, rs), ctx);
+			emit_ld(rd, off, rs, ctx);
 			break;
 		}
 
 		emit_imm(RV_REG_T1, off, ctx);
-		emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx);
-		emit(rv_ld(rd, 0, RV_REG_T1), ctx);
+		emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
+		emit_ld(rd, 0, RV_REG_T1, ctx);
 		break;
 
 	/* ST: *(size *)(dst + off) = imm */
@@ -936,7 +948,7 @@ out_be:
 		}
 
 		emit_imm(RV_REG_T2, off, ctx);
-		emit(rv_add(RV_REG_T2, RV_REG_T2, rd), ctx);
+		emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
 		emit(rv_sb(RV_REG_T2, 0, RV_REG_T1), ctx);
 		break;
 
@@ -948,30 +960,30 @@ out_be:
 		}
 
 		emit_imm(RV_REG_T2, off, ctx);
-		emit(rv_add(RV_REG_T2, RV_REG_T2, rd), ctx);
+		emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
 		emit(rv_sh(RV_REG_T2, 0, RV_REG_T1), ctx);
 		break;
 	case BPF_ST | BPF_MEM | BPF_W:
 		emit_imm(RV_REG_T1, imm, ctx);
 		if (is_12b_int(off)) {
-			emit(rv_sw(rd, off, RV_REG_T1), ctx);
+			emit_sw(rd, off, RV_REG_T1, ctx);
 			break;
 		}
 
 		emit_imm(RV_REG_T2, off, ctx);
-		emit(rv_add(RV_REG_T2, RV_REG_T2, rd), ctx);
-		emit(rv_sw(RV_REG_T2, 0, RV_REG_T1), ctx);
+		emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
+		emit_sw(RV_REG_T2, 0, RV_REG_T1, ctx);
 		break;
 	case BPF_ST | BPF_MEM | BPF_DW:
 		emit_imm(RV_REG_T1, imm, ctx);
 		if (is_12b_int(off)) {
-			emit(rv_sd(rd, off, RV_REG_T1), ctx);
+			emit_sd(rd, off, RV_REG_T1, ctx);
 			break;
 		}
 
 		emit_imm(RV_REG_T2, off, ctx);
-		emit(rv_add(RV_REG_T2, RV_REG_T2, rd), ctx);
-		emit(rv_sd(RV_REG_T2, 0, RV_REG_T1), ctx);
+		emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
+		emit_sd(RV_REG_T2, 0, RV_REG_T1, ctx);
 		break;
 
 	/* STX: *(size *)(dst + off) = src */
@@ -982,7 +994,7 @@ out_be:
 		}
 
 		emit_imm(RV_REG_T1, off, ctx);
-		emit(rv_add(RV_REG_T1, RV_REG_T1, rd), ctx);
+		emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
 		emit(rv_sb(RV_REG_T1, 0, rs), ctx);
 		break;
 	case BPF_STX | BPF_MEM | BPF_H:
@@ -992,28 +1004,28 @@ out_be:
 		}
 
 		emit_imm(RV_REG_T1, off, ctx);
-		emit(rv_add(RV_REG_T1, RV_REG_T1, rd), ctx);
+		emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
 		emit(rv_sh(RV_REG_T1, 0, rs), ctx);
 		break;
 	case BPF_STX | BPF_MEM | BPF_W:
 		if (is_12b_int(off)) {
-			emit(rv_sw(rd, off, rs), ctx);
+			emit_sw(rd, off, rs, ctx);
 			break;
 		}
 
 		emit_imm(RV_REG_T1, off, ctx);
-		emit(rv_add(RV_REG_T1, RV_REG_T1, rd), ctx);
-		emit(rv_sw(RV_REG_T1, 0, rs), ctx);
+		emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+		emit_sw(RV_REG_T1, 0, rs, ctx);
 		break;
 	case BPF_STX | BPF_MEM | BPF_DW:
 		if (is_12b_int(off)) {
-			emit(rv_sd(rd, off, rs), ctx);
+			emit_sd(rd, off, rs, ctx);
 			break;
 		}
 
 		emit_imm(RV_REG_T1, off, ctx);
-		emit(rv_add(RV_REG_T1, RV_REG_T1, rd), ctx);
-		emit(rv_sd(RV_REG_T1, 0, rs), ctx);
+		emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+		emit_sd(RV_REG_T1, 0, rs, ctx);
 		break;
 	/* STX XADD: lock *(u32 *)(dst + off) += src */
 	case BPF_STX | BPF_XADD | BPF_W:
@@ -1021,10 +1033,10 @@ out_be:
 	case BPF_STX | BPF_XADD | BPF_DW:
 		if (off) {
 			if (is_12b_int(off)) {
-				emit(rv_addi(RV_REG_T1, rd, off), ctx);
+				emit_addi(RV_REG_T1, rd, off, ctx);
 			} else {
 				emit_imm(RV_REG_T1, off, ctx);
-				emit(rv_add(RV_REG_T1, RV_REG_T1, rd), ctx);
+				emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
 			}
 
 			rd = RV_REG_T1;
@@ -1073,52 +1085,53 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx)
 
 	/* First instruction is always setting the tail-call-counter
 	 * (TCC) register. This instruction is skipped for tail calls.
+	 * Force using a 4-byte (non-compressed) instruction.
 	 */
 	emit(rv_addi(RV_REG_TCC, RV_REG_ZERO, MAX_TAIL_CALL_CNT), ctx);
 
-	emit(rv_addi(RV_REG_SP, RV_REG_SP, -stack_adjust), ctx);
+	emit_addi(RV_REG_SP, RV_REG_SP, -stack_adjust, ctx);
 
 	if (seen_reg(RV_REG_RA, ctx)) {
-		emit(rv_sd(RV_REG_SP, store_offset, RV_REG_RA), ctx);
+		emit_sd(RV_REG_SP, store_offset, RV_REG_RA, ctx);
 		store_offset -= 8;
 	}
-	emit(rv_sd(RV_REG_SP, store_offset, RV_REG_FP), ctx);
+	emit_sd(RV_REG_SP, store_offset, RV_REG_FP, ctx);
 	store_offset -= 8;
 	if (seen_reg(RV_REG_S1, ctx)) {
-		emit(rv_sd(RV_REG_SP, store_offset, RV_REG_S1), ctx);
+		emit_sd(RV_REG_SP, store_offset, RV_REG_S1, ctx);
 		store_offset -= 8;
 	}
 	if (seen_reg(RV_REG_S2, ctx)) {
-		emit(rv_sd(RV_REG_SP, store_offset, RV_REG_S2), ctx);
+		emit_sd(RV_REG_SP, store_offset, RV_REG_S2, ctx);
 		store_offset -= 8;
 	}
 	if (seen_reg(RV_REG_S3, ctx)) {
-		emit(rv_sd(RV_REG_SP, store_offset, RV_REG_S3), ctx);
+		emit_sd(RV_REG_SP, store_offset, RV_REG_S3, ctx);
 		store_offset -= 8;
 	}
 	if (seen_reg(RV_REG_S4, ctx)) {
-		emit(rv_sd(RV_REG_SP, store_offset, RV_REG_S4), ctx);
+		emit_sd(RV_REG_SP, store_offset, RV_REG_S4, ctx);
 		store_offset -= 8;
 	}
 	if (seen_reg(RV_REG_S5, ctx)) {
-		emit(rv_sd(RV_REG_SP, store_offset, RV_REG_S5), ctx);
+		emit_sd(RV_REG_SP, store_offset, RV_REG_S5, ctx);
 		store_offset -= 8;
 	}
 	if (seen_reg(RV_REG_S6, ctx)) {
-		emit(rv_sd(RV_REG_SP, store_offset, RV_REG_S6), ctx);
+		emit_sd(RV_REG_SP, store_offset, RV_REG_S6, ctx);
 		store_offset -= 8;
 	}
 
-	emit(rv_addi(RV_REG_FP, RV_REG_SP, stack_adjust), ctx);
+	emit_addi(RV_REG_FP, RV_REG_SP, stack_adjust, ctx);
 
 	if (bpf_stack_adjust)
-		emit(rv_addi(RV_REG_S5, RV_REG_SP, bpf_stack_adjust), ctx);
+		emit_addi(RV_REG_S5, RV_REG_SP, bpf_stack_adjust, ctx);
 
 	/* Program contains calls and tail calls, so RV_REG_TCC need
 	 * to be saved across calls.
 	 */
 	if (seen_tail_call(ctx) && seen_call(ctx))
-		emit(rv_addi(RV_REG_TCC_SAVED, RV_REG_TCC, 0), ctx);
+		emit_mv(RV_REG_TCC_SAVED, RV_REG_TCC, ctx);
 
 	ctx->stack_size = stack_adjust;
 }
diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c
index 709b94ece3ed..3630d447352c 100644
--- a/arch/riscv/net/bpf_jit_core.c
+++ b/arch/riscv/net/bpf_jit_core.c
@@ -73,7 +73,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	if (ctx->offset) {
 		extra_pass = true;
-		image_size = sizeof(u32) * ctx->ninsns;
+		image_size = sizeof(*ctx->insns) * ctx->ninsns;
 		goto skip_init_ctx;
 	}
 
@@ -103,7 +103,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 			if (jit_data->header)
 				break;
 
-			image_size = sizeof(u32) * ctx->ninsns;
+			image_size = sizeof(*ctx->insns) * ctx->ninsns;
 			jit_data->header =
 				bpf_jit_binary_alloc(image_size,
 						     &jit_data->image,
@@ -114,7 +114,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 				goto out_offset;
 			}
 
-			ctx->insns = (u32 *)jit_data->image;
+			ctx->insns = (u16 *)jit_data->image;
 			/*
 			 * Now, when the image is allocated, the image can
 			 * potentially shrink more (auipc/jalr -> jal).