bpf: JIT helpers for fmod_ret progs

* Split the invoke_bpf program to prepare for special handling of
  fmod_ret programs introduced in a subsequent patch.
* Move the definition of emit_cond_near_jump and emit_nops as they are
  needed for fmod_ret.
* Refactor branch target alignment into its own generic helper function
  i.e. emit_align.
Signed-off-by: KP Singh <kpsingh@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200304191853.1529-3-kpsingh@chromium.org

arch/x86/net/bpf_jit_comp.c

@@ -1361,13 +1361,12 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args,
 			 -(stack_size - i * 8));
 }
 
-static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
-		      struct bpf_tramp_progs *tp, int stack_size)
+static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
+			   struct bpf_prog *p, int stack_size)
 {
 	u8 *prog = *pprog;
-	int cnt = 0, i;
+	int cnt = 0;
 
-	for (i = 0; i < tp->nr_progs; i++) {
 	if (emit_call(&prog, __bpf_prog_enter, prog))
 		return -EINVAL;
 	/* remember prog start time returned by __bpf_prog_enter */
@@ -1376,21 +1375,82 @@ static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
 	/* arg1: lea rdi, [rbp - stack_size] */
 	EMIT4(0x48, 0x8D, 0x7D, -stack_size);
 	/* arg2: progs[i]->insnsi for interpreter */
-		if (!tp->progs[i]->jited)
+	if (!p->jited)
 		emit_mov_imm64(&prog, BPF_REG_2,
-				       (long) tp->progs[i]->insnsi >> 32,
-				       (u32) (long) tp->progs[i]->insnsi);
+			       (long) p->insnsi >> 32,
+			       (u32) (long) p->insnsi);
 	/* call JITed bpf program or interpreter */
-		if (emit_call(&prog, tp->progs[i]->bpf_func, prog))
+	if (emit_call(&prog, p->bpf_func, prog))
 		return -EINVAL;
 
 	/* arg1: mov rdi, progs[i] */
-		emit_mov_imm64(&prog, BPF_REG_1, (long) tp->progs[i] >> 32,
-			       (u32) (long) tp->progs[i]);
+	emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32,
+		       (u32) (long) p);
 	/* arg2: mov rsi, rbx <- start time in nsec */
 	emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
 	if (emit_call(&prog, __bpf_prog_exit, prog))
 		return -EINVAL;
+
+	*pprog = prog;
+	return 0;
+}
+
+static void emit_nops(u8 **pprog, unsigned int len)
+{
+	unsigned int i, noplen;
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	while (len > 0) {
+		noplen = len;
+
+		if (noplen > ASM_NOP_MAX)
+			noplen = ASM_NOP_MAX;
+
+		for (i = 0; i < noplen; i++)
+			EMIT1(ideal_nops[noplen][i]);
+		len -= noplen;
+	}
+
+	*pprog = prog;
+}
+
+static void emit_align(u8 **pprog, u32 align)
+{
+	u8 *target, *prog = *pprog;
+
+	target = PTR_ALIGN(prog, align);
+	if (target != prog)
+		emit_nops(&prog, target - prog);
+
+	*pprog = prog;
+}
+
+static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	s64 offset;
+
+	offset = func - (ip + 2 + 4);
+	if (!is_simm32(offset)) {
+		pr_err("Target %p is out of range\n", func);
+		return -EINVAL;
+	}
+	EMIT2_off32(0x0F, jmp_cond + 0x10, offset);
+	*pprog = prog;
+	return 0;
+}
+
+static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
+		      struct bpf_tramp_progs *tp, int stack_size)
+{
+	int i;
+	u8 *prog = *pprog;
+
+	for (i = 0; i < tp->nr_progs; i++) {
+		if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size))
+			return -EINVAL;
 	}
 	*pprog = prog;
 	return 0;
@@ -1531,42 +1591,6 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
 	return prog - (u8 *)image;
 }
 
-static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond)
-{
-	u8 *prog = *pprog;
-	int cnt = 0;
-	s64 offset;
-
-	offset = func - (ip + 2 + 4);
-	if (!is_simm32(offset)) {
-		pr_err("Target %p is out of range\n", func);
-		return -EINVAL;
-	}
-	EMIT2_off32(0x0F, jmp_cond + 0x10, offset);
-	*pprog = prog;
-	return 0;
-}
-
-static void emit_nops(u8 **pprog, unsigned int len)
-{
-	unsigned int i, noplen;
-	u8 *prog = *pprog;
-	int cnt = 0;
-
-	while (len > 0) {
-		noplen = len;
-
-		if (noplen > ASM_NOP_MAX)
-			noplen = ASM_NOP_MAX;
-
-		for (i = 0; i < noplen; i++)
-			EMIT1(ideal_nops[noplen][i]);
-		len -= noplen;
-	}
-
-	*pprog = prog;
-}
-
 static int emit_fallback_jump(u8 **pprog)
 {
 	u8 *prog = *pprog;
@@ -1589,7 +1613,7 @@ static int emit_fallback_jump(u8 **pprog)
 
 static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs)
 {
-	u8 *jg_reloc, *jg_target, *prog = *pprog;
+	u8 *jg_reloc, *prog = *pprog;
 	int pivot, err, jg_bytes = 1, cnt = 0;
 	s64 jg_offset;
 
@@ -1644,9 +1668,7 @@ static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs)
 	 * Coding Rule 11: All branch targets should be 16-byte
 	 * aligned.
 	 */
-	jg_target = PTR_ALIGN(prog, 16);
-	if (jg_target != prog)
-		emit_nops(&prog, jg_target - prog);
+	emit_align(&prog, 16);
 	jg_offset = prog - jg_reloc;
 	emit_code(jg_reloc - jg_bytes, jg_offset, jg_bytes);