Received-SPF: pass (google.com: domain of linux-kernel+bounces-197710-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
To: acme@kernel.org, jolsa@kernel.org, adrian.hunter@intel.com,
        irogers@google.com, namhyung@kernel.org, segher@kernel.crashing.org,
        christophe.leroy@csgroup.eu
Cc: linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
        linuxppc-dev@lists.ozlabs.org, akanksha@linux.ibm.com,
        maddy@linux.ibm.com, atrajeev@linux.vnet.ibm.com, kjain@linux.ibm.com,
        disgoel@linux.vnet.ibm.com
Subject: [PATCH V3 08/14] tools/perf: Add some of the arithmetic instructions to support instruction tracking in powerpc
Date: Sat,  1 Jun 2024 11:39:35 +0530
Message-Id: <20240601060941.13692-9-atrajeev@linux.vnet.ibm.com>
In-Reply-To: <20240601060941.13692-1-atrajeev@linux.vnet.ibm.com>
References: <20240601060941.13692-1-atrajeev@linux.vnet.ibm.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

Data type profiling has concept of instruction tracking.
Example sequence in powerpc:

	ld      r10,264(r3)
	mr      r31,r3
	<<after some sequence>
	ld      r9,312(r31)

or differently

	lwz	r10,264(r3)
	add	r31, r3, RB
	lwz	r9, 0(r31)

If a sample is hit at "lwz r9, 0(r31)", data type of r31 depends
on previous instruction sequence here. So to track the previous
instructions, patch adds changes to identify some of the arithmetic
instructions which are having opcode as 31. Since memory instructions
also has cases with opcode 31, use the bits 22:30 to filter the
arithmetic instructions here. Also there are instructions with just
two operands like addme, addze. Patch adds new instructions ops
"arithmetic_ops" to handle this

Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
---
 .../perf/arch/powerpc/annotate/instructions.c | 49 +++++++++++++++
 tools/perf/util/disasm.c                      | 61 +++++++++++++++++++
 2 files changed, 110 insertions(+)

diff --git a/tools/perf/arch/powerpc/annotate/instructions.c b/tools/perf/arch/powerpc/annotate/instructions.c
index 4ee959a24738..bec8ab0ee18d 100644
--- a/tools/perf/arch/powerpc/annotate/instructions.c
+++ b/tools/perf/arch/powerpc/annotate/instructions.c
@@ -51,6 +51,7 @@ static struct ins_ops *powerpc__associate_instruction_ops(struct arch *arch, con
 
 #define PPC_OP(op)	(((op) >> 26) & 0x3F)
 #define PPC_21_30(R)	(((R) >> 1) & 0x3ff)
+#define PPC_22_30(R)	(((R) >> 1) & 0x1ff)
 
 struct insn_offset {
 	const char	*name;
@@ -134,6 +135,44 @@ static struct insn_offset ins_array[] = {
 	{ .name = "OP_31_XOP_STFIWX",	.value = 983, },
 };
 
+/*
+ * Arithmetic instructions which are having opcode as 31.
+ * These instructions are tracked to save the register state
+ * changes. Example:
+ *
+ * lwz	r10,264(r3)
+ * add	r31, r3, r3
+ * lwz	r9, 0(r31)
+ *
+ * Here instruction tracking needs to identify the "add"
+ * instruction and save data type of r3 to r31. If a sample
+ * is hit at next "lwz r9, 0(r31)", by this instruction tracking,
+ * data type of r31 can be resolved.
+ */
+static struct insn_offset arithmetic_ins_op_31[] = {
+	{ .name = "SUB_CARRY_XO_FORM",  .value = 8, },
+	{ .name = "MUL_HDW_XO_FORM1",   .value = 9, },
+	{ .name = "ADD_CARRY_XO_FORM",  .value = 10, },
+	{ .name = "MUL_HW_XO_FORM1",    .value = 11, },
+	{ .name = "SUB_XO_FORM",        .value = 40, },
+	{ .name = "MUL_HDW_XO_FORM",    .value = 73, },
+	{ .name = "MUL_HW_XO_FORM",     .value = 75, },
+	{ .name = "SUB_EXT_XO_FORM",    .value = 136, },
+	{ .name = "ADD_EXT_XO_FORM",    .value = 138, },
+	{ .name = "SUB_ZERO_EXT_XO_FORM",       .value = 200, },
+	{ .name = "ADD_ZERO_EXT_XO_FORM",       .value = 202, },
+	{ .name = "SUB_EXT_XO_FORM2",   .value = 232, },
+	{ .name = "MUL_DW_XO_FORM",     .value = 233, },
+	{ .name = "ADD_EXT_XO_FORM2",   .value = 234, },
+	{ .name = "MUL_W_XO_FORM",      .value = 235, },
+	{ .name = "ADD_XO_FORM",	.value = 266, },
+	{ .name = "DIV_DW_XO_FORM1",    .value = 457, },
+	{ .name = "DIV_W_XO_FORM1",     .value = 459, },
+	{ .name = "DIV_DW_XO_FORM",	.value = 489, },
+	{ .name = "DIV_W_XO_FORM",	.value = 491, },
+};
+
+
 static int cmp_offset(const void *a, const void *b)
 {
 	const struct insn_offset *val1 = a;
@@ -163,6 +202,16 @@ static struct ins_ops *check_ppc_insn(int raw_insn)
 		ret = bsearch(&mem_insns_31_opcode, ins_array, ARRAY_SIZE(ins_array), sizeof(ins_array[0]), cmp_offset);
 		if (ret != NULL)
 			return &load_store_ops;
+		else {
+			mem_insns_31_opcode.value = PPC_22_30(raw_insn);
+			ret = bsearch(&mem_insns_31_opcode, arithmetic_ins_op_31, ARRAY_SIZE(arithmetic_ins_op_31),
+					sizeof(arithmetic_ins_op_31[0]), cmp_offset);
+			if (ret != NULL)
+				return &arithmetic_ops;
+			/* Bits 21 to 30 has value 444 for "mr" insn ie, OR X form */
+			if (PPC_21_30(raw_insn) == 444)
+				return &arithmetic_ops;
+		}
 	}
 
 	return NULL;
diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index 16d1e3eaaeb3..57af4dc42a58 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -38,6 +38,7 @@ static struct ins_ops nop_ops;
 static struct ins_ops lock_ops;
 static struct ins_ops ret_ops;
 static struct ins_ops load_store_ops;
+static struct ins_ops arithmetic_ops;
 
 static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops, int max_ins_name);
@@ -673,6 +674,66 @@ static struct ins_ops mov_ops = {
 	.scnprintf = mov__scnprintf,
 };
 
+#define PPC_22_30(R)    (((R) >> 1) & 0x1ff)
+#define MINUS_EXT_XO_FORM	234
+#define SUB_EXT_XO_FORM		232
+#define	ADD_ZERO_EXT_XO_FORM	202
+#define	SUB_ZERO_EXT_XO_FORM	200
+
+static int arithmetic__scnprintf(struct ins *ins, char *bf, size_t size,
+		struct ins_operands *ops, int max_ins_name)
+{
+	return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name,
+			ops->raw);
+}
+
+/*
+ * Sets the fields: "raw_insn", opcode, multi_regs and "mem_ref".
+ * "mem_ref" is set for ops->source which is later used to
+ * fill the objdump->memory_ref-char field. This ops is currently
+ * used by powerpc and since binary instruction code is used to
+ * extract opcode, regs and offset, no other parsing is needed here.
+ *
+ * Dont set multi regs for 4 cases since it has only one operand
+ * for source:
+ * - Add to Minus One Extended XO-form ( Ex: addme, addmeo )
+ * - Subtract From Minus One Extended XO-form ( Ex: subfme )
+ * - Add to Zero Extended XO-form ( Ex: addze, addzeo )
+ * - Subtract From Zero Extended XO-form ( Ex: subfze )
+ */
+static int arithmetic__parse(struct arch *arch __maybe_unused, struct ins_operands *ops,
+		struct map_symbol *ms __maybe_unused)
+{
+	ops->source.raw_insn = ops->raw_insn;
+	ops->source.mem_ref = false;
+	ops->source.opcode = ops->opcode;
+	if (ops->source.opcode == 31) {
+		int opcode = ops->source.opcode;
+
+		if ((opcode != MINUS_EXT_XO_FORM) && (opcode != SUB_EXT_XO_FORM) \
+				&& (opcode != ADD_ZERO_EXT_XO_FORM) && (opcode != SUB_ZERO_EXT_XO_FORM))
+			ops->source.multi_regs = true;
+	}
+
+	if (!ops->source.raw_insn)
+		return -1;
+
+	ops->target.raw_insn = ops->raw_insn;
+	ops->target.mem_ref = false;
+	ops->target.opcode = ops->opcode;
+	ops->target.multi_regs = false;
+
+	if (!ops->target.raw_insn)
+		return -1;
+
+	return 0;
+}
+
+static struct ins_ops arithmetic_ops = {
+	.parse     = arithmetic__parse,
+	.scnprintf = arithmetic__scnprintf,
+};
+
 static int load_store__scnprintf(struct ins *ins, char *bf, size_t size,
 		struct ins_operands *ops, int max_ins_name)
 {
-- 
2.43.0