Received-SPF: pass (google.com: domain of linux-kernel+bounces-166361-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
From: Adrian Hunter <adrian.hunter@intel.com>
To: linux-kernel@vger.kernel.org
Cc: "Chang S. Bae" <chang.seok.bae@intel.com>,
	Masami Hiramatsu <mhiramat@kernel.org>,
	Nikolay Borisov <nik.borisov@suse.com>,
	Borislav Petkov <bp@alien8.de>,
	Ingo Molnar <mingo@redhat.com>,
	"H. Peter Anvin" <hpa@zytor.com>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	x86@kernel.org,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Jiri Olsa <jolsa@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	Ian Rogers <irogers@google.com>,
	linux-perf-users@vger.kernel.org
Subject: [PATCH 05/10] x86/insn: Add support for REX2 prefix to the instruction decoder logic
Date: Thu,  2 May 2024 13:58:48 +0300
Message-Id: <20240502105853.5338-6-adrian.hunter@intel.com>
In-Reply-To: <20240502105853.5338-1-adrian.hunter@intel.com>
References: <20240502105853.5338-1-adrian.hunter@intel.com>
Precedence: bulk
MIME-Version: 1.0
Organization: Intel Finland Oy, Registered Address: PL 281, 00181 Helsinki, Business Identity Code: 0357606 - 4, Domiciled in Helsinki
Content-Transfer-Encoding: 8bit

Intel Advanced Performance Extensions (APX) uses a new 2-byte prefix named
REX2 to select extended general purpose registers (EGPRs) i.e. r16 to r31.

The REX2 prefix is effectively an extended version of the REX prefix.

REX2 and EVEX are also used with PUSH/POP instructions to provide a
Push-Pop Acceleration (PPX) hint. With PPX hints, a CPU will attempt to
fast-forward register data between matching PUSH and POP instructions.

REX2 is valid only with opcodes in maps 0 and 1. Similar extension for
other maps is provided by the EVEX prefix, covered in a separate patch.

Some opcodes in maps 0 and 1 are reserved under REX2. One of these is used
for a new 64-bit absolute direct jump instruction JMPABS.

Refer to the Intel Advanced Performance Extensions (Intel APX) Architecture
Specification for details.

Define a code value for the REX2 prefix (INAT_PFX_REX2), and add attribute
flags for opcodes reserved under REX2 (INAT_NO_REX2) and to identify
opcodes (only JMPABS) that require a mandatory REX2 prefix
(INAT_REX2_VARIANT).

Amend logic to read the REX2 prefix and get the opcode attribute for the
map number (0 or 1) encoded in the REX2 prefix.

Amend the awk script that generates the attribute tables from the opcode
map, to recognise "REX2" as attribute INAT_PFX_REX2, and "(!REX2)"
as attribute INAT_NO_REX2, and "(REX2)" as attribute INAT_REX2_VARIANT.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 arch/x86/include/asm/inat.h                | 11 +++++++++-
 arch/x86/include/asm/insn.h                | 25 ++++++++++++++++++----
 arch/x86/lib/insn.c                        | 25 ++++++++++++++++++++++
 arch/x86/tools/gen-insn-attr-x86.awk       | 11 +++++++++-
 tools/arch/x86/include/asm/inat.h          | 11 +++++++++-
 tools/arch/x86/include/asm/insn.h          | 25 ++++++++++++++++++----
 tools/arch/x86/lib/insn.c                  | 25 ++++++++++++++++++++++
 tools/arch/x86/tools/gen-insn-attr-x86.awk | 11 +++++++++-
 8 files changed, 132 insertions(+), 12 deletions(-)

diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h
index b56c5741581a..1331bdd39a23 100644
--- a/arch/x86/include/asm/inat.h
+++ b/arch/x86/include/asm/inat.h
@@ -35,6 +35,8 @@
 #define INAT_PFX_VEX2	13	/* 2-bytes VEX prefix */
 #define INAT_PFX_VEX3	14	/* 3-bytes VEX prefix */
 #define INAT_PFX_EVEX	15	/* EVEX prefix */
+/* x86-64 REX2 prefix */
+#define INAT_PFX_REX2	16	/* 0xD5 */
 
 #define INAT_LSTPFX_MAX	3
 #define INAT_LGCPFX_MAX	11
@@ -50,7 +52,7 @@
 
 /* Legacy prefix */
 #define INAT_PFX_OFFS	0
-#define INAT_PFX_BITS	4
+#define INAT_PFX_BITS	5
 #define INAT_PFX_MAX    ((1 << INAT_PFX_BITS) - 1)
 #define INAT_PFX_MASK	(INAT_PFX_MAX << INAT_PFX_OFFS)
 /* Escape opcodes */
@@ -77,6 +79,8 @@
 #define INAT_VEXOK	(1 << (INAT_FLAG_OFFS + 5))
 #define INAT_VEXONLY	(1 << (INAT_FLAG_OFFS + 6))
 #define INAT_EVEXONLY	(1 << (INAT_FLAG_OFFS + 7))
+#define INAT_NO_REX2	(1 << (INAT_FLAG_OFFS + 8))
+#define INAT_REX2_VARIANT	(1 << (INAT_FLAG_OFFS + 9))
 /* Attribute making macros for attribute tables */
 #define INAT_MAKE_PREFIX(pfx)	(pfx << INAT_PFX_OFFS)
 #define INAT_MAKE_ESCAPE(esc)	(esc << INAT_ESC_OFFS)
@@ -128,6 +132,11 @@ static inline int inat_is_rex_prefix(insn_attr_t attr)
 	return (attr & INAT_PFX_MASK) == INAT_PFX_REX;
 }
 
+static inline int inat_is_rex2_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_REX2;
+}
+
 static inline int inat_last_prefix_id(insn_attr_t attr)
 {
 	if ((attr & INAT_PFX_MASK) > INAT_LSTPFX_MAX)
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 1b29f58f730f..95249ec1f24e 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -112,10 +112,15 @@ struct insn {
 #define X86_SIB_INDEX(sib) (((sib) & 0x38) >> 3)
 #define X86_SIB_BASE(sib) ((sib) & 0x07)
 
-#define X86_REX_W(rex) ((rex) & 8)
-#define X86_REX_R(rex) ((rex) & 4)
-#define X86_REX_X(rex) ((rex) & 2)
-#define X86_REX_B(rex) ((rex) & 1)
+#define X86_REX2_M(rex) ((rex) & 0x80)	/* REX2 M0 */
+#define X86_REX2_R(rex) ((rex) & 0x40)	/* REX2 R4 */
+#define X86_REX2_X(rex) ((rex) & 0x20)	/* REX2 X4 */
+#define X86_REX2_B(rex) ((rex) & 0x10)	/* REX2 B4 */
+
+#define X86_REX_W(rex) ((rex) & 8)	/* REX or REX2 W */
+#define X86_REX_R(rex) ((rex) & 4)	/* REX or REX2 R3 */
+#define X86_REX_X(rex) ((rex) & 2)	/* REX or REX2 X3 */
+#define X86_REX_B(rex) ((rex) & 1)	/* REX or REX2 B3 */
 
 /* VEX bit flags  */
 #define X86_VEX_W(vex)	((vex) & 0x80)	/* VEX3 Byte2 */
@@ -161,6 +166,18 @@ static inline void insn_get_attribute(struct insn *insn)
 /* Instruction uses RIP-relative addressing */
 extern int insn_rip_relative(struct insn *insn);
 
+static inline int insn_is_rex2(struct insn *insn)
+{
+	if (!insn->prefixes.got)
+		insn_get_prefixes(insn);
+	return insn->rex_prefix.nbytes == 2;
+}
+
+static inline insn_byte_t insn_rex2_m_bit(struct insn *insn)
+{
+	return X86_REX2_M(insn->rex_prefix.bytes[1]);
+}
+
 static inline int insn_is_avx(struct insn *insn)
 {
 	if (!insn->prefixes.got)
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 1bb155a0955b..6126ddc6e5f5 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -185,6 +185,17 @@ int insn_get_prefixes(struct insn *insn)
 			if (X86_REX_W(b))
 				/* REX.W overrides opnd_size */
 				insn->opnd_bytes = 8;
+		} else if (inat_is_rex2_prefix(attr)) {
+			insn_set_byte(&insn->rex_prefix, 0, b);
+			b = peek_nbyte_next(insn_byte_t, insn, 1);
+			insn_set_byte(&insn->rex_prefix, 1, b);
+			insn->rex_prefix.nbytes = 2;
+			insn->next_byte += 2;
+			if (X86_REX_W(b))
+				/* REX.W overrides opnd_size */
+				insn->opnd_bytes = 8;
+			insn->rex_prefix.got = 1;
+			goto vex_end;
 		}
 	}
 	insn->rex_prefix.got = 1;
@@ -294,6 +305,20 @@ int insn_get_opcode(struct insn *insn)
 		goto end;
 	}
 
+	/* Check if there is REX2 prefix or not */
+	if (insn_is_rex2(insn)) {
+		if (insn_rex2_m_bit(insn)) {
+			/* map 1 is escape 0x0f */
+			insn_attr_t esc_attr = inat_get_opcode_attribute(0x0f);
+
+			pfx_id = insn_last_prefix_id(insn);
+			insn->attr = inat_get_escape_attribute(op, pfx_id, esc_attr);
+		} else {
+			insn->attr = inat_get_opcode_attribute(op);
+		}
+		goto end;
+	}
+
 	insn->attr = inat_get_opcode_attribute(op);
 	while (inat_is_escape(insn->attr)) {
 		/* Get escaped opcode */
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index af38469afd14..3f43aa7d8fef 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -64,7 +64,9 @@ BEGIN {
 
 	modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])"
 	force64_expr = "\\([df]64\\)"
-	rex_expr = "^REX(\\.[XRWB]+)*"
+	rex_expr = "^((REX(\\.[XRWB]+)+)|(REX$))"
+	rex2_expr = "\\(REX2\\)"
+	no_rex2_expr = "\\(!REX2\\)"
 	fpu_expr = "^ESC" # TODO
 
 	lprefix1_expr = "\\((66|!F3)\\)"
@@ -99,6 +101,7 @@ BEGIN {
 	prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
 	prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
 	prefix_num["EVEX"] = "INAT_PFX_EVEX"
+	prefix_num["REX2"] = "INAT_PFX_REX2"
 
 	clear_vars()
 }
@@ -314,6 +317,10 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 		if (match(ext, force64_expr))
 			flags = add_flags(flags, "INAT_FORCE64")
 
+		# check REX2 not allowed
+		if (match(ext, no_rex2_expr))
+			flags = add_flags(flags, "INAT_NO_REX2")
+
 		# check REX prefix
 		if (match(opcode, rex_expr))
 			flags = add_flags(flags, "INAT_MAKE_PREFIX(INAT_PFX_REX)")
@@ -351,6 +358,8 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 			lptable3[idx] = add_flags(lptable3[idx],flags)
 			variant = "INAT_VARIANT"
 		}
+		if (match(ext, rex2_expr))
+			table[idx] = add_flags(table[idx], "INAT_REX2_VARIANT")
 		if (!match(ext, lprefix_expr)){
 			table[idx] = add_flags(table[idx],flags)
 		}
diff --git a/tools/arch/x86/include/asm/inat.h b/tools/arch/x86/include/asm/inat.h
index a61051400311..2e65312cae52 100644
--- a/tools/arch/x86/include/asm/inat.h
+++ b/tools/arch/x86/include/asm/inat.h
@@ -35,6 +35,8 @@
 #define INAT_PFX_VEX2	13	/* 2-bytes VEX prefix */
 #define INAT_PFX_VEX3	14	/* 3-bytes VEX prefix */
 #define INAT_PFX_EVEX	15	/* EVEX prefix */
+/* x86-64 REX2 prefix */
+#define INAT_PFX_REX2	16	/* 0xD5 */
 
 #define INAT_LSTPFX_MAX	3
 #define INAT_LGCPFX_MAX	11
@@ -50,7 +52,7 @@
 
 /* Legacy prefix */
 #define INAT_PFX_OFFS	0
-#define INAT_PFX_BITS	4
+#define INAT_PFX_BITS	5
 #define INAT_PFX_MAX    ((1 << INAT_PFX_BITS) - 1)
 #define INAT_PFX_MASK	(INAT_PFX_MAX << INAT_PFX_OFFS)
 /* Escape opcodes */
@@ -77,6 +79,8 @@
 #define INAT_VEXOK	(1 << (INAT_FLAG_OFFS + 5))
 #define INAT_VEXONLY	(1 << (INAT_FLAG_OFFS + 6))
 #define INAT_EVEXONLY	(1 << (INAT_FLAG_OFFS + 7))
+#define INAT_NO_REX2	(1 << (INAT_FLAG_OFFS + 8))
+#define INAT_REX2_VARIANT	(1 << (INAT_FLAG_OFFS + 9))
 /* Attribute making macros for attribute tables */
 #define INAT_MAKE_PREFIX(pfx)	(pfx << INAT_PFX_OFFS)
 #define INAT_MAKE_ESCAPE(esc)	(esc << INAT_ESC_OFFS)
@@ -128,6 +132,11 @@ static inline int inat_is_rex_prefix(insn_attr_t attr)
 	return (attr & INAT_PFX_MASK) == INAT_PFX_REX;
 }
 
+static inline int inat_is_rex2_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_REX2;
+}
+
 static inline int inat_last_prefix_id(insn_attr_t attr)
 {
 	if ((attr & INAT_PFX_MASK) > INAT_LSTPFX_MAX)
diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h
index 65c0d9ce1e29..1a7e8fc4d75a 100644
--- a/tools/arch/x86/include/asm/insn.h
+++ b/tools/arch/x86/include/asm/insn.h
@@ -112,10 +112,15 @@ struct insn {
 #define X86_SIB_INDEX(sib) (((sib) & 0x38) >> 3)
 #define X86_SIB_BASE(sib) ((sib) & 0x07)
 
-#define X86_REX_W(rex) ((rex) & 8)
-#define X86_REX_R(rex) ((rex) & 4)
-#define X86_REX_X(rex) ((rex) & 2)
-#define X86_REX_B(rex) ((rex) & 1)
+#define X86_REX2_M(rex) ((rex) & 0x80)	/* REX2 M0 */
+#define X86_REX2_R(rex) ((rex) & 0x40)	/* REX2 R4 */
+#define X86_REX2_X(rex) ((rex) & 0x20)	/* REX2 X4 */
+#define X86_REX2_B(rex) ((rex) & 0x10)	/* REX2 B4 */
+
+#define X86_REX_W(rex) ((rex) & 8)	/* REX or REX2 W */
+#define X86_REX_R(rex) ((rex) & 4)	/* REX or REX2 R3 */
+#define X86_REX_X(rex) ((rex) & 2)	/* REX or REX2 X3 */
+#define X86_REX_B(rex) ((rex) & 1)	/* REX or REX2 B3 */
 
 /* VEX bit flags  */
 #define X86_VEX_W(vex)	((vex) & 0x80)	/* VEX3 Byte2 */
@@ -161,6 +166,18 @@ static inline void insn_get_attribute(struct insn *insn)
 /* Instruction uses RIP-relative addressing */
 extern int insn_rip_relative(struct insn *insn);
 
+static inline int insn_is_rex2(struct insn *insn)
+{
+	if (!insn->prefixes.got)
+		insn_get_prefixes(insn);
+	return insn->rex_prefix.nbytes == 2;
+}
+
+static inline insn_byte_t insn_rex2_m_bit(struct insn *insn)
+{
+	return X86_REX2_M(insn->rex_prefix.bytes[1]);
+}
+
 static inline int insn_is_avx(struct insn *insn)
 {
 	if (!insn->prefixes.got)
diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c
index ada4b4a79dd4..f761adeb8e8c 100644
--- a/tools/arch/x86/lib/insn.c
+++ b/tools/arch/x86/lib/insn.c
@@ -185,6 +185,17 @@ int insn_get_prefixes(struct insn *insn)
 			if (X86_REX_W(b))
 				/* REX.W overrides opnd_size */
 				insn->opnd_bytes = 8;
+		} else if (inat_is_rex2_prefix(attr)) {
+			insn_set_byte(&insn->rex_prefix, 0, b);
+			b = peek_nbyte_next(insn_byte_t, insn, 1);
+			insn_set_byte(&insn->rex_prefix, 1, b);
+			insn->rex_prefix.nbytes = 2;
+			insn->next_byte += 2;
+			if (X86_REX_W(b))
+				/* REX.W overrides opnd_size */
+				insn->opnd_bytes = 8;
+			insn->rex_prefix.got = 1;
+			goto vex_end;
 		}
 	}
 	insn->rex_prefix.got = 1;
@@ -294,6 +305,20 @@ int insn_get_opcode(struct insn *insn)
 		goto end;
 	}
 
+	/* Check if there is REX2 prefix or not */
+	if (insn_is_rex2(insn)) {
+		if (insn_rex2_m_bit(insn)) {
+			/* map 1 is escape 0x0f */
+			insn_attr_t esc_attr = inat_get_opcode_attribute(0x0f);
+
+			pfx_id = insn_last_prefix_id(insn);
+			insn->attr = inat_get_escape_attribute(op, pfx_id, esc_attr);
+		} else {
+			insn->attr = inat_get_opcode_attribute(op);
+		}
+		goto end;
+	}
+
 	insn->attr = inat_get_opcode_attribute(op);
 	while (inat_is_escape(insn->attr)) {
 		/* Get escaped opcode */
diff --git a/tools/arch/x86/tools/gen-insn-attr-x86.awk b/tools/arch/x86/tools/gen-insn-attr-x86.awk
index af38469afd14..3f43aa7d8fef 100644
--- a/tools/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/tools/arch/x86/tools/gen-insn-attr-x86.awk
@@ -64,7 +64,9 @@ BEGIN {
 
 	modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])"
 	force64_expr = "\\([df]64\\)"
-	rex_expr = "^REX(\\.[XRWB]+)*"
+	rex_expr = "^((REX(\\.[XRWB]+)+)|(REX$))"
+	rex2_expr = "\\(REX2\\)"
+	no_rex2_expr = "\\(!REX2\\)"
 	fpu_expr = "^ESC" # TODO
 
 	lprefix1_expr = "\\((66|!F3)\\)"
@@ -99,6 +101,7 @@ BEGIN {
 	prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
 	prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
 	prefix_num["EVEX"] = "INAT_PFX_EVEX"
+	prefix_num["REX2"] = "INAT_PFX_REX2"
 
 	clear_vars()
 }
@@ -314,6 +317,10 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 		if (match(ext, force64_expr))
 			flags = add_flags(flags, "INAT_FORCE64")
 
+		# check REX2 not allowed
+		if (match(ext, no_rex2_expr))
+			flags = add_flags(flags, "INAT_NO_REX2")
+
 		# check REX prefix
 		if (match(opcode, rex_expr))
 			flags = add_flags(flags, "INAT_MAKE_PREFIX(INAT_PFX_REX)")
@@ -351,6 +358,8 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 			lptable3[idx] = add_flags(lptable3[idx],flags)
 			variant = "INAT_VARIANT"
 		}
+		if (match(ext, rex2_expr))
+			table[idx] = add_flags(table[idx], "INAT_REX2_VARIANT")
 		if (!match(ext, lprefix_expr)){
 			table[idx] = add_flags(table[idx],flags)
 		}
-- 
2.34.1