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

Pull networking updates from David Miller:

 1) Add WireGuard

 2) Add HE and TWT support to ath11k driver, from John Crispin.

 3) Add ESP in TCP encapsulation support, from Sabrina Dubroca.

 4) Add variable window congestion control to TIPC, from Jon Maloy.

 5) Add BCM84881 PHY driver, from Russell King.

 6) Start adding netlink support for ethtool operations, from Michal
    Kubecek.

 7) Add XDP drop and TX action support to ena driver, from Sameeh
    Jubran.

 8) Add new ipv4 route notifications so that mlxsw driver does not have
    to handle identical routes itself. From Ido Schimmel.

 9) Add BPF dynamic program extensions, from Alexei Starovoitov.

10) Support RX and TX timestamping in igc, from Vinicius Costa Gomes.

11) Add support for macsec HW offloading, from Antoine Tenart.

12) Add initial support for MPTCP protocol, from Christoph Paasch,
    Matthieu Baerts, Florian Westphal, Peter Krystad, and many others.

13) Add Octeontx2 PF support, from Sunil Goutham, Geetha sowjanya, Linu
    Cherian, and others.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1469 commits)
  net: phy: add default ARCH_BCM_IPROC for MDIO_BCM_IPROC
  udp: segment looped gso packets correctly
  netem: change mailing list
  qed: FW 8.42.2.0 debug features
  qed: rt init valid initialization changed
  qed: Debug feature: ilt and mdump
  qed: FW 8.42.2.0 Add fw overlay feature
  qed: FW 8.42.2.0 HSI changes
  qed: FW 8.42.2.0 iscsi/fcoe changes
  qed: Add abstraction for different hsi values per chip
  qed: FW 8.42.2.0 Additional ll2 type
  qed: Use dmae to write to widebus registers in fw_funcs
  qed: FW 8.42.2.0 Parser offsets modified
  qed: FW 8.42.2.0 Queue Manager changes
  qed: FW 8.42.2.0 Expose new registers and change windows
  qed: FW 8.42.2.0 Internal ram offsets modifications
  MAINTAINERS: Add entry for Marvell OcteonTX2 Physical Function driver
  Documentation: net: octeontx2: Add RVU HW and drivers overview
  octeontx2-pf: ethtool RSS config support
  octeontx2-pf: Add basic ethtool support
  ...

4 files changed, 310 insertions, 238 deletions

diff --git a/arch/riscv/include/asm/perf_event.h b/arch/riscv/include/asm/perf_event.h
index aefbfaa6a781..0234048b12bc 100644
--- a/arch/riscv/include/asm/perf_event.h
+++ b/arch/riscv/include/asm/perf_event.h
@@ -82,4 +82,8 @@ struct riscv_pmu {
 	int		irq;
 };
 
+#ifdef CONFIG_PERF_EVENTS
+#define perf_arch_bpf_user_pt_regs(regs) (struct user_regs_struct *)regs
+#endif
+
 #endif /* _ASM_RISCV_PERF_EVENT_H */
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 36ae01761352..f66b87314fa2 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -94,6 +94,10 @@ extern pgd_t swapper_pg_dir[];
 #define VMALLOC_END      (PAGE_OFFSET - 1)
 #define VMALLOC_START    (PAGE_OFFSET - VMALLOC_SIZE)
 
+#define BPF_JIT_REGION_SIZE	(SZ_128M)
+#define BPF_JIT_REGION_START	(PAGE_OFFSET - BPF_JIT_REGION_SIZE)
+#define BPF_JIT_REGION_END	(VMALLOC_END)
+
 /*
  * Roughly size the vmemmap space to be large enough to fit enough
  * struct pages to map half the virtual address space. Then
diff --git a/arch/riscv/include/uapi/asm/bpf_perf_event.h b/arch/riscv/include/uapi/asm/bpf_perf_event.h
new file mode 100644
index 000000000000..6cb1c2823288
--- /dev/null
+++ b/arch/riscv/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 <asm/ptrace.h>
+
+typedef struct user_regs_struct bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */
diff --git a/arch/riscv/net/bpf_jit_comp.c b/arch/riscv/net/bpf_jit_comp.c
index 7fbf56aab661..483f4ad7f4dc 100644
--- a/arch/riscv/net/bpf_jit_comp.c
+++ b/arch/riscv/net/bpf_jit_comp.c
@@ -120,6 +120,11 @@ static bool seen_reg(int reg, struct rv_jit_context *ctx)
 	return false;
 }
 
+static void mark_fp(struct rv_jit_context *ctx)
+{
+	__set_bit(RV_CTX_F_SEEN_S5, &ctx->flags);
+}
+
 static void mark_call(struct rv_jit_context *ctx)
 {
 	__set_bit(RV_CTX_F_SEEN_CALL, &ctx->flags);
@@ -456,6 +461,11 @@ static 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);
 }
 
+static u32 rv_auipc(u8 rd, u32 imm31_12)
+{
+	return rv_u_insn(imm31_12, rd, 0x17);
+}
+
 static bool is_12b_int(s64 val)
 {
 	return -(1 << 11) <= val && val < (1 << 11);
@@ -479,27 +489,7 @@ static bool is_32b_int(s64 val)
 static int is_12b_check(int off, int insn)
 {
 	if (!is_12b_int(off)) {
-		pr_err("bpf-jit: insn=%d offset=%d not supported yet!\n",
-		       insn, (int)off);
-		return -1;
-	}
-	return 0;
-}
-
-static int is_13b_check(int off, int insn)
-{
-	if (!is_13b_int(off)) {
-		pr_err("bpf-jit: insn=%d offset=%d not supported yet!\n",
-		       insn, (int)off);
-		return -1;
-	}
-	return 0;
-}
-
-static int is_21b_check(int off, int insn)
-{
-	if (!is_21b_int(off)) {
-		pr_err("bpf-jit: insn=%d offset=%d not supported yet!\n",
+		pr_err("bpf-jit: insn=%d 12b < offset=%d not supported yet!\n",
 		       insn, (int)off);
 		return -1;
 	}
@@ -545,10 +535,13 @@ static void emit_imm(u8 rd, s64 val, struct rv_jit_context *ctx)
 		emit(rv_addi(rd, rd, lower), ctx);
 }
 
-static int rv_offset(int bpf_to, int bpf_from, struct rv_jit_context *ctx)
+static int rv_offset(int insn, int off, struct rv_jit_context *ctx)
 {
-	int from = ctx->offset[bpf_from] - 1, to = ctx->offset[bpf_to];
+	int from, to;
 
+	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;
 }
 
@@ -559,7 +552,7 @@ static int epilogue_offset(struct rv_jit_context *ctx)
 	return (to - from) << 2;
 }
 
-static void __build_epilogue(u8 reg, struct rv_jit_context *ctx)
+static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx)
 {
 	int stack_adjust = ctx->stack_size, store_offset = stack_adjust - 8;
 
@@ -596,8 +589,114 @@ static void __build_epilogue(u8 reg, struct rv_jit_context *ctx)
 
 	emit(rv_addi(RV_REG_SP, RV_REG_SP, stack_adjust), ctx);
 	/* Set return value. */
-	emit(rv_addi(RV_REG_A0, RV_REG_A5, 0), ctx);
-	emit(rv_jalr(RV_REG_ZERO, reg, 0), ctx);
+	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);
+}
+
+/* return -1 or inverted cond */
+static int invert_bpf_cond(u8 cond)
+{
+	switch (cond) {
+	case BPF_JEQ:
+		return BPF_JNE;
+	case BPF_JGT:
+		return BPF_JLE;
+	case BPF_JLT:
+		return BPF_JGE;
+	case BPF_JGE:
+		return BPF_JLT;
+	case BPF_JLE:
+		return BPF_JGT;
+	case BPF_JNE:
+		return BPF_JEQ;
+	case BPF_JSGT:
+		return BPF_JSLE;
+	case BPF_JSLT:
+		return BPF_JSGE;
+	case BPF_JSGE:
+		return BPF_JSLT;
+	case BPF_JSLE:
+		return BPF_JSGT;
+	}
+	return -1;
+}
+
+static void emit_bcc(u8 cond, u8 rd, u8 rs, int rvoff,
+		     struct rv_jit_context *ctx)
+{
+	switch (cond) {
+	case BPF_JEQ:
+		emit(rv_beq(rd, rs, rvoff >> 1), ctx);
+		return;
+	case BPF_JGT:
+		emit(rv_bltu(rs, rd, rvoff >> 1), ctx);
+		return;
+	case BPF_JLT:
+		emit(rv_bltu(rd, rs, rvoff >> 1), ctx);
+		return;
+	case BPF_JGE:
+		emit(rv_bgeu(rd, rs, rvoff >> 1), ctx);
+		return;
+	case BPF_JLE:
+		emit(rv_bgeu(rs, rd, rvoff >> 1), ctx);
+		return;
+	case BPF_JNE:
+		emit(rv_bne(rd, rs, rvoff >> 1), ctx);
+		return;
+	case BPF_JSGT:
+		emit(rv_blt(rs, rd, rvoff >> 1), ctx);
+		return;
+	case BPF_JSLT:
+		emit(rv_blt(rd, rs, rvoff >> 1), ctx);
+		return;
+	case BPF_JSGE:
+		emit(rv_bge(rd, rs, rvoff >> 1), ctx);
+		return;
+	case BPF_JSLE:
+		emit(rv_bge(rs, rd, rvoff >> 1), ctx);
+	}
+}
+
+static void emit_branch(u8 cond, u8 rd, u8 rs, int rvoff,
+			struct rv_jit_context *ctx)
+{
+	s64 upper, lower;
+
+	if (is_13b_int(rvoff)) {
+		emit_bcc(cond, rd, rs, rvoff, ctx);
+		return;
+	}
+
+	/* Adjust for jal */
+	rvoff -= 4;
+
+	/* Transform, e.g.:
+	 *   bne rd,rs,foo
+	 * to
+	 *   beq rd,rs,<.L1>
+	 *   (auipc foo)
+	 *   jal(r) foo
+	 * .L1
+	 */
+	cond = invert_bpf_cond(cond);
+	if (is_21b_int(rvoff)) {
+		emit_bcc(cond, rd, rs, 8, ctx);
+		emit(rv_jal(RV_REG_ZERO, rvoff >> 1), ctx);
+		return;
+	}
+
+	/* 32b No need for an additional rvoff adjustment, since we
+	 * get that from the auipc at PC', where PC = PC' + 4.
+	 */
+	upper = (rvoff + (1 << 11)) >> 12;
+	lower = rvoff & 0xfff;
+
+	emit_bcc(cond, rd, rs, 12, ctx);
+	emit(rv_auipc(RV_REG_T1, upper), ctx);
+	emit(rv_jalr(RV_REG_ZERO, RV_REG_T1, lower), ctx);
 }
 
 static void emit_zext_32(u8 reg, struct rv_jit_context *ctx)
@@ -627,18 +726,14 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
 		return -1;
 	emit(rv_lwu(RV_REG_T1, off, RV_REG_A1), ctx);
 	off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2;
-	if (is_13b_check(off, insn))
-		return -1;
-	emit(rv_bgeu(RV_REG_A2, RV_REG_T1, off >> 1), ctx);
+	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;
-	if (is_13b_check(off, insn))
-		return -1;
-	emit(rv_blt(tcc, RV_REG_ZERO, off >> 1), ctx);
+	emit_branch(BPF_JSLT, tcc, RV_REG_ZERO, off, ctx);
 
 	/* prog = array->ptrs[index];
 	 * if (!prog)
@@ -651,18 +746,15 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
 		return -1;
 	emit(rv_ld(RV_REG_T2, off, RV_REG_T2), ctx);
 	off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2;
-	if (is_13b_check(off, insn))
-		return -1;
-	emit(rv_beq(RV_REG_T2, RV_REG_ZERO, off >> 1), ctx);
+	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_T3, RV_REG_T3, 4), ctx);
 	emit(rv_addi(RV_REG_TCC, RV_REG_T1, 0), ctx);
-	__build_epilogue(RV_REG_T3, ctx);
+	__build_epilogue(true, ctx);
 	return 0;
 }
 
@@ -687,13 +779,6 @@ static void init_regs(u8 *rd, u8 *rs, const struct bpf_insn *insn,
 		*rs = bpf_to_rv_reg(insn->src_reg, ctx);
 }
 
-static int rv_offset_check(int *rvoff, s16 off, int insn,
-			   struct rv_jit_context *ctx)
-{
-	*rvoff = rv_offset(insn + off, insn, ctx);
-	return is_13b_check(*rvoff, 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);
@@ -726,13 +811,57 @@ static void emit_sext_32_rd(u8 *rd, struct rv_jit_context *ctx)
 	*rd = RV_REG_T2;
 }
 
+static void emit_jump_and_link(u8 rd, s64 rvoff, bool force_jalr,
+			       struct rv_jit_context *ctx)
+{
+	s64 upper, lower;
+
+	if (rvoff && is_21b_int(rvoff) && !force_jalr) {
+		emit(rv_jal(rd, rvoff >> 1), ctx);
+		return;
+	}
+
+	upper = (rvoff + (1 << 11)) >> 12;
+	lower = rvoff & 0xfff;
+	emit(rv_auipc(RV_REG_T1, upper), ctx);
+	emit(rv_jalr(rd, RV_REG_T1, lower), ctx);
+}
+
+static bool is_signed_bpf_cond(u8 cond)
+{
+	return cond == BPF_JSGT || cond == BPF_JSLT ||
+		cond == BPF_JSGE || cond == BPF_JSLE;
+}
+
+static int emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx)
+{
+	s64 off = 0;
+	u64 ip;
+	u8 rd;
+
+	if (addr && ctx->insns) {
+		ip = (u64)(long)(ctx->insns + ctx->ninsns);
+		off = addr - ip;
+		if (!is_32b_int(off)) {
+			pr_err("bpf-jit: target call addr %pK is out of range\n",
+			       (void *)addr);
+			return -ERANGE;
+		}
+	}
+
+	emit_jump_and_link(RV_REG_RA, off, !fixed, ctx);
+	rd = bpf_to_rv_reg(BPF_REG_0, ctx);
+	emit(rv_addi(rd, RV_REG_A0, 0), ctx);
+	return 0;
+}
+
 static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		     bool extra_pass)
 {
 	bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 ||
 		    BPF_CLASS(insn->code) == BPF_JMP;
+	int s, e, rvoff, i = insn - ctx->prog->insnsi;
 	struct bpf_prog_aux *aux = ctx->prog->aux;
-	int rvoff, i = insn - ctx->prog->insnsi;
 	u8 rd = -1, rs = -1, code = insn->code;
 	s16 off = insn->off;
 	s32 imm = insn->imm;
@@ -1000,214 +1129,110 @@ out_be:
 
 	/* JUMP off */
 	case BPF_JMP | BPF_JA:
-		rvoff = rv_offset(i + off, i, ctx);
-		if (!is_21b_int(rvoff)) {
-			pr_err("bpf-jit: insn=%d offset=%d not supported yet!\n",
-			       i, rvoff);
-			return -1;
-		}
-
-		emit(rv_jal(RV_REG_ZERO, rvoff >> 1), ctx);
+		rvoff = rv_offset(i, off, ctx);
+		emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx);
 		break;
 
 	/* IF (dst COND src) JUMP off */
 	case BPF_JMP | BPF_JEQ | BPF_X:
 	case BPF_JMP32 | BPF_JEQ | BPF_X:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		if (!is64)
-			emit_zext_32_rd_rs(&rd, &rs, ctx);
-		emit(rv_beq(rd, rs, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JGT | BPF_X:
 	case BPF_JMP32 | BPF_JGT | BPF_X:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		if (!is64)
-			emit_zext_32_rd_rs(&rd, &rs, ctx);
-		emit(rv_bltu(rs, rd, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JLT | BPF_X:
 	case BPF_JMP32 | BPF_JLT | BPF_X:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		if (!is64)
-			emit_zext_32_rd_rs(&rd, &rs, ctx);
-		emit(rv_bltu(rd, rs, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JGE | BPF_X:
 	case BPF_JMP32 | BPF_JGE | BPF_X:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		if (!is64)
-			emit_zext_32_rd_rs(&rd, &rs, ctx);
-		emit(rv_bgeu(rd, rs, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JLE | BPF_X:
 	case BPF_JMP32 | BPF_JLE | BPF_X:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		if (!is64)
-			emit_zext_32_rd_rs(&rd, &rs, ctx);
-		emit(rv_bgeu(rs, rd, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JNE | BPF_X:
 	case BPF_JMP32 | BPF_JNE | BPF_X:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		if (!is64)
-			emit_zext_32_rd_rs(&rd, &rs, ctx);
-		emit(rv_bne(rd, rs, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JSGT | BPF_X:
 	case BPF_JMP32 | BPF_JSGT | BPF_X:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		if (!is64)
-			emit_sext_32_rd_rs(&rd, &rs, ctx);
-		emit(rv_blt(rs, rd, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JSLT | BPF_X:
 	case BPF_JMP32 | BPF_JSLT | BPF_X:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		if (!is64)
-			emit_sext_32_rd_rs(&rd, &rs, ctx);
-		emit(rv_blt(rd, rs, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JSGE | BPF_X:
 	case BPF_JMP32 | BPF_JSGE | BPF_X:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		if (!is64)
-			emit_sext_32_rd_rs(&rd, &rs, ctx);
-		emit(rv_bge(rd, rs, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JSLE | BPF_X:
 	case BPF_JMP32 | BPF_JSLE | BPF_X:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		if (!is64)
-			emit_sext_32_rd_rs(&rd, &rs, ctx);
-		emit(rv_bge(rs, rd, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JSET | BPF_X:
 	case BPF_JMP32 | BPF_JSET | BPF_X:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		if (!is64)
-			emit_zext_32_rd_rs(&rd, &rs, ctx);
-		emit(rv_and(RV_REG_T1, rd, rs), ctx);
-		emit(rv_bne(RV_REG_T1, RV_REG_ZERO, rvoff >> 1), ctx);
+		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);
+			e = ctx->ninsns;
+
+			/* Adjust for extra insns */
+			rvoff -= (e - s) << 2;
+		}
+
+		if (BPF_OP(code) == BPF_JSET) {
+			/* Adjust for and */
+			rvoff -= 4;
+			emit(rv_and(RV_REG_T1, rd, rs), ctx);
+			emit_branch(BPF_JNE, RV_REG_T1, RV_REG_ZERO, rvoff,
+				    ctx);
+		} else {
+			emit_branch(BPF_OP(code), rd, rs, rvoff, ctx);
+		}
 		break;
 
 	/* IF (dst COND imm) JUMP off */
 	case BPF_JMP | BPF_JEQ | BPF_K:
 	case BPF_JMP32 | BPF_JEQ | BPF_K:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		emit_imm(RV_REG_T1, imm, ctx);
-		if (!is64)
-			emit_zext_32_rd_t1(&rd, ctx);
-		emit(rv_beq(rd, RV_REG_T1, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JGT | BPF_K:
 	case BPF_JMP32 | BPF_JGT | BPF_K:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		emit_imm(RV_REG_T1, imm, ctx);
-		if (!is64)
-			emit_zext_32_rd_t1(&rd, ctx);
-		emit(rv_bltu(RV_REG_T1, rd, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JLT | BPF_K:
 	case BPF_JMP32 | BPF_JLT | BPF_K:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		emit_imm(RV_REG_T1, imm, ctx);
-		if (!is64)
-			emit_zext_32_rd_t1(&rd, ctx);
-		emit(rv_bltu(rd, RV_REG_T1, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JGE | BPF_K:
 	case BPF_JMP32 | BPF_JGE | BPF_K:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		emit_imm(RV_REG_T1, imm, ctx);
-		if (!is64)
-			emit_zext_32_rd_t1(&rd, ctx);
-		emit(rv_bgeu(rd, RV_REG_T1, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JLE | BPF_K:
 	case BPF_JMP32 | BPF_JLE | BPF_K:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		emit_imm(RV_REG_T1, imm, ctx);
-		if (!is64)
-			emit_zext_32_rd_t1(&rd, ctx);
-		emit(rv_bgeu(RV_REG_T1, rd, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JNE | BPF_K:
 	case BPF_JMP32 | BPF_JNE | BPF_K:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		emit_imm(RV_REG_T1, imm, ctx);
-		if (!is64)
-			emit_zext_32_rd_t1(&rd, ctx);
-		emit(rv_bne(rd, RV_REG_T1, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JSGT | BPF_K:
 	case BPF_JMP32 | BPF_JSGT | BPF_K:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		emit_imm(RV_REG_T1, imm, ctx);
-		if (!is64)
-			emit_sext_32_rd(&rd, ctx);
-		emit(rv_blt(RV_REG_T1, rd, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JSLT | BPF_K:
 	case BPF_JMP32 | BPF_JSLT | BPF_K:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		emit_imm(RV_REG_T1, imm, ctx);
-		if (!is64)
-			emit_sext_32_rd(&rd, ctx);
-		emit(rv_blt(rd, RV_REG_T1, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JSGE | BPF_K:
 	case BPF_JMP32 | BPF_JSGE | BPF_K:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		emit_imm(RV_REG_T1, imm, ctx);
-		if (!is64)
-			emit_sext_32_rd(&rd, ctx);
-		emit(rv_bge(rd, RV_REG_T1, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JSLE | BPF_K:
 	case BPF_JMP32 | BPF_JSLE | BPF_K:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
-		emit_imm(RV_REG_T1, imm, ctx);
-		if (!is64)
-			emit_sext_32_rd(&rd, ctx);
-		emit(rv_bge(RV_REG_T1, rd, rvoff >> 1), ctx);
-		break;
 	case BPF_JMP | BPF_JSET | BPF_K:
 	case BPF_JMP32 | BPF_JSET | BPF_K:
-		if (rv_offset_check(&rvoff, off, i, ctx))
-			return -1;
+		rvoff = rv_offset(i, off, ctx);
+		s = ctx->ninsns;
 		emit_imm(RV_REG_T1, imm, ctx);
-		if (!is64)
-			emit_zext_32_rd_t1(&rd, ctx);
-		emit(rv_and(RV_REG_T1, rd, RV_REG_T1), ctx);
-		emit(rv_bne(RV_REG_T1, RV_REG_ZERO, rvoff >> 1), ctx);
+		if (!is64) {
+			if (is_signed_bpf_cond(BPF_OP(code)))
+				emit_sext_32_rd(&rd, ctx);
+			else
+				emit_zext_32_rd_t1(&rd, ctx);
+		}
+		e = ctx->ninsns;
+
+		/* Adjust for extra insns */
+		rvoff -= (e - s) << 2;
+
+		if (BPF_OP(code) == BPF_JSET) {
+			/* Adjust for and */
+			rvoff -= 4;
+			emit(rv_and(RV_REG_T1, rd, RV_REG_T1), ctx);
+			emit_branch(BPF_JNE, RV_REG_T1, RV_REG_ZERO, rvoff,
+				    ctx);
+		} else {
+			emit_branch(BPF_OP(code), rd, RV_REG_T1, rvoff, ctx);
+		}
 		break;
 
 	/* function call */
 	case BPF_JMP | BPF_CALL:
 	{
 		bool fixed;
-		int i, ret;
+		int ret;
 		u64 addr;
 
 		mark_call(ctx);
@@ -1215,20 +1240,9 @@ out_be:
 					    &fixed);
 		if (ret < 0)
 			return ret;
-		if (fixed) {
-			emit_imm(RV_REG_T1, addr, ctx);
-		} else {
-			i = ctx->ninsns;
-			emit_imm(RV_REG_T1, addr, ctx);
-			for (i = ctx->ninsns - i; i < 8; i++) {
-				/* nop */
-				emit(rv_addi(RV_REG_ZERO, RV_REG_ZERO, 0),
-				     ctx);
-			}
-		}
-		emit(rv_jalr(RV_REG_RA, RV_REG_T1, 0), ctx);
-		rd = bpf_to_rv_reg(BPF_REG_0, ctx);
-		emit(rv_addi(rd, RV_REG_A0, 0), ctx);
+		ret = emit_call(fixed, addr, ctx);
+		if (ret)
+			return ret;
 		break;
 	}
 	/* tail call */
@@ -1243,9 +1257,7 @@ out_be:
 			break;
 
 		rvoff = epilogue_offset(ctx);
-		if (is_21b_check(rvoff, i))
-			return -1;
-		emit(rv_jal(RV_REG_ZERO, rvoff >> 1), ctx);
+		emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx);
 		break;
 
 	/* dst = imm64 */
@@ -1426,6 +1438,10 @@ static void build_prologue(struct rv_jit_context *ctx)
 {
 	int stack_adjust = 0, store_offset, bpf_stack_adjust;
 
+	bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16);
+	if (bpf_stack_adjust)
+		mark_fp(ctx);
+
 	if (seen_reg(RV_REG_RA, ctx))
 		stack_adjust += 8;
 	stack_adjust += 8; /* RV_REG_FP */
@@ -1443,7 +1459,6 @@ static void build_prologue(struct rv_jit_context *ctx)
 		stack_adjust += 8;
 
 	stack_adjust = round_up(stack_adjust, 16);
-	bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16);
 	stack_adjust += bpf_stack_adjust;
 
 	store_offset = stack_adjust - 8;
@@ -1502,10 +1517,10 @@ static void build_prologue(struct rv_jit_context *ctx)
 
 static void build_epilogue(struct rv_jit_context *ctx)
 {
-	__build_epilogue(RV_REG_RA, ctx);
+	__build_epilogue(false, ctx);
 }
 
-static int build_body(struct rv_jit_context *ctx, bool extra_pass)
+static int build_body(struct rv_jit_context *ctx, bool extra_pass, int *offset)
 {
 	const struct bpf_prog *prog = ctx->prog;
 	int i;
@@ -1517,12 +1532,12 @@ static int build_body(struct rv_jit_context *ctx, bool extra_pass)
 		ret = emit_insn(insn, ctx, extra_pass);
 		if (ret > 0) {
 			i++;
-			if (ctx->insns == NULL)
-				ctx->offset[i] = ctx->ninsns;
+			if (offset)
+				offset[i] = ctx->ninsns;
 			continue;
 		}
-		if (ctx->insns == NULL)
-			ctx->offset[i] = ctx->ninsns;
+		if (offset)
+			offset[i] = ctx->ninsns;
 		if (ret)
 			return ret;
 	}
@@ -1548,9 +1563,10 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	bool tmp_blinded = false, extra_pass = false;
 	struct bpf_prog *tmp, *orig_prog = prog;
+	int pass = 0, prev_ninsns = 0, i;
 	struct rv_jit_data *jit_data;
+	unsigned int image_size = 0;
 	struct rv_jit_context *ctx;
-	unsigned int image_size;
 
 	if (!prog->jit_requested)
 		return orig_prog;
@@ -1587,33 +1603,59 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		prog = orig_prog;
 		goto out_offset;
 	}
+	for (i = 0; i < prog->len; i++) {
+		prev_ninsns += 32;
+		ctx->offset[i] = prev_ninsns;
+	}
 
-	/* First pass generates the ctx->offset, but does not emit an image. */
-	if (build_body(ctx, extra_pass)) {
-		prog = orig_prog;
-		goto out_offset;
+	for (i = 0; i < 16; i++) {
+		pass++;
+		ctx->ninsns = 0;
+		if (build_body(ctx, extra_pass, ctx->offset)) {
+			prog = orig_prog;
+			goto out_offset;
+		}
+		build_prologue(ctx);
+		ctx->epilogue_offset = ctx->ninsns;
+		build_epilogue(ctx);
+
+		if (ctx->ninsns == prev_ninsns) {
+			if (jit_data->header)
+				break;
+
+			image_size = sizeof(u32) * ctx->ninsns;
+			jit_data->header =
+				bpf_jit_binary_alloc(image_size,
+						     &jit_data->image,
+						     sizeof(u32),
+						     bpf_fill_ill_insns);
+			if (!jit_data->header) {
+				prog = orig_prog;
+				goto out_offset;
+			}
+
+			ctx->insns = (u32 *)jit_data->image;
+			/* Now, when the image is allocated, the image
+			 * can potentially shrink more (auipc/jalr ->
+			 * jal).
+			 */
+		}
+		prev_ninsns = ctx->ninsns;
 	}
-	build_prologue(ctx);
-	ctx->epilogue_offset = ctx->ninsns;
-	build_epilogue(ctx);
 
-	/* Allocate image, now that we know the size. */
-	image_size = sizeof(u32) * ctx->ninsns;
-	jit_data->header = bpf_jit_binary_alloc(image_size, &jit_data->image,
-						sizeof(u32),
-						bpf_fill_ill_insns);
-	if (!jit_data->header) {
+	if (i == 16) {
+		pr_err("bpf-jit: image did not converge in <%d passes!\n", i);
+		bpf_jit_binary_free(jit_data->header);
 		prog = orig_prog;
 		goto out_offset;
 	}
 
-	/* Second, real pass, that acutally emits the image. */
-	ctx->insns = (u32 *)jit_data->image;
 skip_init_ctx:
+	pass++;
 	ctx->ninsns = 0;
 
 	build_prologue(ctx);
-	if (build_body(ctx, extra_pass)) {
+	if (build_body(ctx, extra_pass, NULL)) {
 		bpf_jit_binary_free(jit_data->header);
 		prog = orig_prog;
 		goto out_offset;
@@ -1621,7 +1663,7 @@ skip_init_ctx:
 	build_epilogue(ctx);
 
 	if (bpf_jit_enable > 1)
-		bpf_jit_dump(prog->len, image_size, 2, ctx->insns);
+		bpf_jit_dump(prog->len, image_size, pass, ctx->insns);
 
 	prog->bpf_func = (void *)ctx->insns;
 	prog->jited = 1;
@@ -1641,3 +1683,16 @@ out:
 					   tmp : orig_prog);
 	return prog;
 }
+
+void *bpf_jit_alloc_exec(unsigned long size)
+{
+	return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,
+				    BPF_JIT_REGION_END, GFP_KERNEL,
+				    PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+				    __builtin_return_address(0));
+}
+
+void bpf_jit_free_exec(void *addr)
+{
+	return vfree(addr);
+}