ppc: bpf: implement jitting of JMP32

This patch implements code-gen for new JMP32 instructions on ppc.

For JMP32 | JSET, instruction encoding for PPC_RLWINM_DOT is added to check
the result of ANDing low 32-bit of operands.

Cc: Naveen N. Rao <naveen.n.rao@linux.ibm.com>
Cc: Sandipan Das <sandipan@linux.ibm.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

arch/powerpc/include/asm/ppc-opcode.h

@@ -337,6 +337,7 @@
 #define PPC_INST_DIVWU			0x7c000396
 #define PPC_INST_DIVD			0x7c0003d2
 #define PPC_INST_RLWINM			0x54000000
+#define PPC_INST_RLWINM_DOT		0x54000001
 #define PPC_INST_RLWIMI			0x50000000
 #define PPC_INST_RLDICL			0x78000000
 #define PPC_INST_RLDICR			0x78000004

arch/powerpc/net/bpf_jit.h

@@ -165,6 +165,10 @@
 #define PPC_RLWINM(d, a, i, mb, me)	EMIT(PPC_INST_RLWINM | ___PPC_RA(d) | \
 					___PPC_RS(a) | __PPC_SH(i) |	      \
 					__PPC_MB(mb) | __PPC_ME(me))
+#define PPC_RLWINM_DOT(d, a, i, mb, me)	EMIT(PPC_INST_RLWINM_DOT |	      \
+					___PPC_RA(d) | ___PPC_RS(a) |	      \
+					__PPC_SH(i) | __PPC_MB(mb) |	      \
+					__PPC_ME(me))
 #define PPC_RLWIMI(d, a, i, mb, me)	EMIT(PPC_INST_RLWIMI | ___PPC_RA(d) | \
 					___PPC_RS(a) | __PPC_SH(i) |	      \
 					__PPC_MB(mb) | __PPC_ME(me))

arch/powerpc/net/bpf_jit_comp64.c

@@ -768,36 +768,58 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		case BPF_JMP | BPF_JGT | BPF_X:
 		case BPF_JMP | BPF_JSGT | BPF_K:
 		case BPF_JMP | BPF_JSGT | BPF_X:
+		case BPF_JMP32 | BPF_JGT | BPF_K:
+		case BPF_JMP32 | BPF_JGT | BPF_X:
+		case BPF_JMP32 | BPF_JSGT | BPF_K:
+		case BPF_JMP32 | BPF_JSGT | BPF_X:
 			true_cond = COND_GT;
 			goto cond_branch;
 		case BPF_JMP | BPF_JLT | BPF_K:
 		case BPF_JMP | BPF_JLT | BPF_X:
 		case BPF_JMP | BPF_JSLT | BPF_K:
 		case BPF_JMP | BPF_JSLT | BPF_X:
+		case BPF_JMP32 | BPF_JLT | BPF_K:
+		case BPF_JMP32 | BPF_JLT | BPF_X:
+		case BPF_JMP32 | BPF_JSLT | BPF_K:
+		case BPF_JMP32 | BPF_JSLT | BPF_X:
 			true_cond = COND_LT;
 			goto cond_branch;
 		case BPF_JMP | BPF_JGE | BPF_K:
 		case BPF_JMP | BPF_JGE | BPF_X:
 		case BPF_JMP | BPF_JSGE | BPF_K:
 		case BPF_JMP | BPF_JSGE | BPF_X:
+		case BPF_JMP32 | BPF_JGE | BPF_K:
+		case BPF_JMP32 | BPF_JGE | BPF_X:
+		case BPF_JMP32 | BPF_JSGE | BPF_K:
+		case BPF_JMP32 | BPF_JSGE | BPF_X:
 			true_cond = COND_GE;
 			goto cond_branch;
 		case BPF_JMP | BPF_JLE | BPF_K:
 		case BPF_JMP | BPF_JLE | BPF_X:
 		case BPF_JMP | BPF_JSLE | BPF_K:
 		case BPF_JMP | BPF_JSLE | BPF_X:
+		case BPF_JMP32 | BPF_JLE | BPF_K:
+		case BPF_JMP32 | BPF_JLE | BPF_X:
+		case BPF_JMP32 | BPF_JSLE | BPF_K:
+		case BPF_JMP32 | BPF_JSLE | BPF_X:
 			true_cond = COND_LE;
 			goto cond_branch;
 		case BPF_JMP | BPF_JEQ | BPF_K:
 		case BPF_JMP | BPF_JEQ | BPF_X:
+		case BPF_JMP32 | BPF_JEQ | BPF_K:
+		case BPF_JMP32 | BPF_JEQ | BPF_X:
 			true_cond = COND_EQ;
 			goto cond_branch;
 		case BPF_JMP | BPF_JNE | BPF_K:
 		case BPF_JMP | BPF_JNE | BPF_X:
+		case BPF_JMP32 | BPF_JNE | BPF_K:
+		case BPF_JMP32 | BPF_JNE | BPF_X:
 			true_cond = COND_NE;
 			goto cond_branch;
 		case BPF_JMP | BPF_JSET | BPF_K:
 		case BPF_JMP | BPF_JSET | BPF_X:
+		case BPF_JMP32 | BPF_JSET | BPF_K:
+		case BPF_JMP32 | BPF_JSET | BPF_X:
 			true_cond = COND_NE;
 			/* Fall through */
 
@@ -809,18 +831,44 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			case BPF_JMP | BPF_JLE | BPF_X:
 			case BPF_JMP | BPF_JEQ | BPF_X:
 			case BPF_JMP | BPF_JNE | BPF_X:
+			case BPF_JMP32 | BPF_JGT | BPF_X:
+			case BPF_JMP32 | BPF_JLT | BPF_X:
+			case BPF_JMP32 | BPF_JGE | BPF_X:
+			case BPF_JMP32 | BPF_JLE | BPF_X:
+			case BPF_JMP32 | BPF_JEQ | BPF_X:
+			case BPF_JMP32 | BPF_JNE | BPF_X:
 				/* unsigned comparison */
-				PPC_CMPLD(dst_reg, src_reg);
+				if (BPF_CLASS(code) == BPF_JMP32)
+					PPC_CMPLW(dst_reg, src_reg);
+				else
+					PPC_CMPLD(dst_reg, src_reg);
 				break;
 			case BPF_JMP | BPF_JSGT | BPF_X:
 			case BPF_JMP | BPF_JSLT | BPF_X:
 			case BPF_JMP | BPF_JSGE | BPF_X:
 			case BPF_JMP | BPF_JSLE | BPF_X:
+			case BPF_JMP32 | BPF_JSGT | BPF_X:
+			case BPF_JMP32 | BPF_JSLT | BPF_X:
+			case BPF_JMP32 | BPF_JSGE | BPF_X:
+			case BPF_JMP32 | BPF_JSLE | BPF_X:
 				/* signed comparison */
-				PPC_CMPD(dst_reg, src_reg);
+				if (BPF_CLASS(code) == BPF_JMP32)
+					PPC_CMPW(dst_reg, src_reg);
+				else
+					PPC_CMPD(dst_reg, src_reg);
 				break;
 			case BPF_JMP | BPF_JSET | BPF_X:
-				PPC_AND_DOT(b2p[TMP_REG_1], dst_reg, src_reg);
+			case BPF_JMP32 | BPF_JSET | BPF_X:
+				if (BPF_CLASS(code) == BPF_JMP) {
+					PPC_AND_DOT(b2p[TMP_REG_1], dst_reg,
+						    src_reg);
+				} else {
+					int tmp_reg = b2p[TMP_REG_1];
+
+					PPC_AND(tmp_reg, dst_reg, src_reg);
+					PPC_RLWINM_DOT(tmp_reg, tmp_reg, 0, 0,
+						       31);
+				}
 				break;
 			case BPF_JMP | BPF_JNE | BPF_K:
 			case BPF_JMP | BPF_JEQ | BPF_K:
@@ -828,43 +876,87 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			case BPF_JMP | BPF_JLT | BPF_K:
 			case BPF_JMP | BPF_JGE | BPF_K:
 			case BPF_JMP | BPF_JLE | BPF_K:
+			case BPF_JMP32 | BPF_JNE | BPF_K:
+			case BPF_JMP32 | BPF_JEQ | BPF_K:
+			case BPF_JMP32 | BPF_JGT | BPF_K:
+			case BPF_JMP32 | BPF_JLT | BPF_K:
+			case BPF_JMP32 | BPF_JGE | BPF_K:
+			case BPF_JMP32 | BPF_JLE | BPF_K:
+			{
+				bool is_jmp32 = BPF_CLASS(code) == BPF_JMP32;
+
 				/*
 				 * Need sign-extended load, so only positive
 				 * values can be used as imm in cmpldi
 				 */
-				if (imm >= 0 && imm < 32768)
-					PPC_CMPLDI(dst_reg, imm);
-				else {
+				if (imm >= 0 && imm < 32768) {
+					if (is_jmp32)
+						PPC_CMPLWI(dst_reg, imm);
+					else
+						PPC_CMPLDI(dst_reg, imm);
+				} else {
 					/* sign-extending load */
 					PPC_LI32(b2p[TMP_REG_1], imm);
 					/* ... but unsigned comparison */
-					PPC_CMPLD(dst_reg, b2p[TMP_REG_1]);
+					if (is_jmp32)
+						PPC_CMPLW(dst_reg,
+							  b2p[TMP_REG_1]);
+					else
+						PPC_CMPLD(dst_reg,
+							  b2p[TMP_REG_1]);
 				}
 				break;
+			}
 			case BPF_JMP | BPF_JSGT | BPF_K:
 			case BPF_JMP | BPF_JSLT | BPF_K:
 			case BPF_JMP | BPF_JSGE | BPF_K:
 			case BPF_JMP | BPF_JSLE | BPF_K:
+			case BPF_JMP32 | BPF_JSGT | BPF_K:
+			case BPF_JMP32 | BPF_JSLT | BPF_K:
+			case BPF_JMP32 | BPF_JSGE | BPF_K:
+			case BPF_JMP32 | BPF_JSLE | BPF_K:
+			{
+				bool is_jmp32 = BPF_CLASS(code) == BPF_JMP32;
+
 				/*
 				 * signed comparison, so any 16-bit value
 				 * can be used in cmpdi
 				 */
-				if (imm >= -32768 && imm < 32768)
-					PPC_CMPDI(dst_reg, imm);
-				else {
+				if (imm >= -32768 && imm < 32768) {
+					if (is_jmp32)
+						PPC_CMPWI(dst_reg, imm);
+					else
+						PPC_CMPDI(dst_reg, imm);
+				} else {
 					PPC_LI32(b2p[TMP_REG_1], imm);
-					PPC_CMPD(dst_reg, b2p[TMP_REG_1]);
+					if (is_jmp32)
+						PPC_CMPW(dst_reg,
+							 b2p[TMP_REG_1]);
+					else
+						PPC_CMPD(dst_reg,
+							 b2p[TMP_REG_1]);
 				}
 				break;
+			}
 			case BPF_JMP | BPF_JSET | BPF_K:
+			case BPF_JMP32 | BPF_JSET | BPF_K:
 				/* andi does not sign-extend the immediate */
 				if (imm >= 0 && imm < 32768)
 					/* PPC_ANDI is _only/always_ dot-form */
 					PPC_ANDI(b2p[TMP_REG_1], dst_reg, imm);
 				else {
-					PPC_LI32(b2p[TMP_REG_1], imm);
-					PPC_AND_DOT(b2p[TMP_REG_1], dst_reg,
-						    b2p[TMP_REG_1]);
+					int tmp_reg = b2p[TMP_REG_1];
+
+					PPC_LI32(tmp_reg, imm);
+					if (BPF_CLASS(code) == BPF_JMP) {
+						PPC_AND_DOT(tmp_reg, dst_reg,
+							    tmp_reg);
+					} else {
+						PPC_AND(tmp_reg, dst_reg,
+							tmp_reg);
+						PPC_RLWINM_DOT(tmp_reg, tmp_reg,
+							       0, 0, 31);
+					}
 				}
 				break;
 			}