Merge branch 'bpf-rv64-jit'

Luke Nelson says:

====================
This patch series introduces a set of optimizations to the BPF JIT
on RV64. The optimizations are related to the verifier zero-extension
optimization and BPF_JMP BPF_K.

We tested the optimizations on a QEMU riscv64 virt machine, using
lib/test_bpf and test_verifier, and formally verified their correctness
using Serval.
====================
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

arch/riscv/net/bpf_jit_comp64.c

@@ -515,7 +515,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	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)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_RSH | BPF_X:
@@ -542,13 +542,21 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 
 	/* dst = BSWAP##imm(dst) */
 	case BPF_ALU | BPF_END | BPF_FROM_LE:
-	{
-		int shift = 64 - imm;
-
-		emit(rv_slli(rd, rd, shift), ctx);
-		emit(rv_srli(rd, rd, shift), ctx);
+		switch (imm) {
+		case 16:
+			emit(rv_slli(rd, rd, 48), ctx);
+			emit(rv_srli(rd, rd, 48), ctx);
+			break;
+		case 32:
+			if (!aux->verifier_zext)
+				emit_zext_32(rd, ctx);
+			break;
+		case 64:
+			/* Do nothing */
+			break;
+		}
 		break;
-	}
+
 	case BPF_ALU | BPF_END | BPF_FROM_BE:
 		emit(rv_addi(RV_REG_T2, RV_REG_ZERO, 0), ctx);
 
@@ -692,19 +700,19 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	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);
-		if (!is64)
+		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)
+		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)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 
@@ -784,11 +792,15 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_JMP32 | BPF_JSGE | BPF_K:
 	case BPF_JMP | BPF_JSLE | BPF_K:
 	case BPF_JMP32 | BPF_JSLE | BPF_K:
-	case BPF_JMP | BPF_JSET | BPF_K:
-	case BPF_JMP32 | BPF_JSET | BPF_K:
 		rvoff = rv_offset(i, off, ctx);
 		s = ctx->ninsns;
-		emit_imm(RV_REG_T1, imm, ctx);
+		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;
+		}
 		if (!is64) {
 			if (is_signed_bpf_cond(BPF_OP(code)))
 				emit_sext_32_rd(&rd, ctx);
@@ -799,16 +811,28 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 
 		/* Adjust for extra insns */
 		rvoff -= (e - s) << 2;
+		emit_branch(BPF_OP(code), rd, rs, rvoff, ctx);
+		break;
 
-		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);
+	case BPF_JMP | BPF_JSET | BPF_K:
+	case BPF_JMP32 | BPF_JSET | BPF_K:
+		rvoff = rv_offset(i, off, ctx);
+		s = ctx->ninsns;
+		if (is_12b_int(imm)) {
+			emit(rv_andi(RV_REG_T1, rd, imm), ctx);
 		} else {
-			emit_branch(BPF_OP(code), rd, RV_REG_T1, rvoff, ctx);
+			emit_imm(RV_REG_T1, imm, ctx);
+			emit(rv_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);
+		e = ctx->ninsns;
+		rvoff -= (e - s) << 2;
+		emit_branch(BPF_JNE, RV_REG_T1, RV_REG_ZERO, rvoff, ctx);
 		break;
 
 	/* function call */