powerpc/bpf: Emit a single branch instruction for known short branch ranges

PPC_BCC() emits two instructions to accommodate scenarios where we need
to branch outside the range of a conditional branch. PPC_BCC_SHORT()
emits a single branch instruction and can be used when the branch is
known to be within a conditional branch range.

Convert some of the uses of PPC_BCC() in the powerpc BPF JIT over to
PPC_BCC_SHORT() where we know the branch range.
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/edbca01377d1d5f472868bf6d8962b0a0d85b96f.1644834730.git.naveen.n.rao@linux.vnet.ibm.com

arch/powerpc/net/bpf_jit_comp32.c

@@ -229,7 +229,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	EMIT(PPC_RAW_LWZ(_R0, b2p_bpf_array, offsetof(struct bpf_array, map.max_entries)));
 	EMIT(PPC_RAW_CMPLW(b2p_index, _R0));
 	EMIT(PPC_RAW_LWZ(_R0, _R1, bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));
-	PPC_BCC(COND_GE, out);
+	PPC_BCC_SHORT(COND_GE, out);
 
 	/*
 	 * if (tail_call_cnt >= MAX_TAIL_CALL_CNT)
@@ -238,7 +238,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	EMIT(PPC_RAW_CMPLWI(_R0, MAX_TAIL_CALL_CNT));
 	/* tail_call_cnt++; */
 	EMIT(PPC_RAW_ADDIC(_R0, _R0, 1));
-	PPC_BCC(COND_GE, out);
+	PPC_BCC_SHORT(COND_GE, out);
 
 	/* prog = array->ptrs[index]; */
 	EMIT(PPC_RAW_RLWINM(_R3, b2p_index, 2, 0, 29));
@@ -251,7 +251,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	 *   goto out;
 	 */
 	EMIT(PPC_RAW_CMPLWI(_R3, 0));
-	PPC_BCC(COND_EQ, out);
+	PPC_BCC_SHORT(COND_EQ, out);
 
 	/* goto *(prog->bpf_func + prologue_size); */
 	EMIT(PPC_RAW_LWZ(_R3, _R3, offsetof(struct bpf_prog, bpf_func)));
@@ -842,7 +842,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 			if (BPF_MODE(code) == BPF_PROBE_MEM) {
 				PPC_LI32(_R0, TASK_SIZE - off);
 				EMIT(PPC_RAW_CMPLW(src_reg, _R0));
-				PPC_BCC(COND_GT, (ctx->idx + 5) * 4);
+				PPC_BCC_SHORT(COND_GT, (ctx->idx + 4) * 4);
 				EMIT(PPC_RAW_LI(dst_reg, 0));
 				/*
 				 * For BPF_DW case, "li reg_h,0" would be needed when

arch/powerpc/net/bpf_jit_comp64.c

@@ -225,7 +225,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	EMIT(PPC_RAW_LWZ(b2p[TMP_REG_1], b2p_bpf_array, offsetof(struct bpf_array, map.max_entries)));
 	EMIT(PPC_RAW_RLWINM(b2p_index, b2p_index, 0, 0, 31));
 	EMIT(PPC_RAW_CMPLW(b2p_index, b2p[TMP_REG_1]));
-	PPC_BCC(COND_GE, out);
+	PPC_BCC_SHORT(COND_GE, out);
 
 	/*
 	 * if (tail_call_cnt >= MAX_TAIL_CALL_CNT)
@@ -233,7 +233,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	 */
 	PPC_BPF_LL(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx));
 	EMIT(PPC_RAW_CMPLWI(b2p[TMP_REG_1], MAX_TAIL_CALL_CNT));
-	PPC_BCC(COND_GE, out);
+	PPC_BCC_SHORT(COND_GE, out);
 
 	/*
 	 * tail_call_cnt++;
@@ -251,7 +251,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	 *   goto out;
 	 */
 	EMIT(PPC_RAW_CMPLDI(b2p[TMP_REG_1], 0));
-	PPC_BCC(COND_EQ, out);
+	PPC_BCC_SHORT(COND_EQ, out);
 
 	/* goto *(prog->bpf_func + prologue_size); */
 	PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_prog, bpf_func));
@@ -807,7 +807,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 				else /* BOOK3S_64 */
 					PPC_LI64(b2p[TMP_REG_2], PAGE_OFFSET);
 				EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1], b2p[TMP_REG_2]));
-				PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
+				PPC_BCC_SHORT(COND_GT, (ctx->idx + 3) * 4);
 				EMIT(PPC_RAW_LI(dst_reg, 0));
 				/*
 				 * Check if 'off' is word aligned because PPC_BPF_LL()