Merge tag 'perf-urgent-2024-05-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf event updates from Ingo Molnar:

 - Extend the x86 instruction decoder with APX and
   other new instructions

 - Misc cleanups

* tag 'perf-urgent-2024-05-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/cstate: Remove unused 'struct perf_cstate_msr'
  perf/x86/rapl: Rename 'maxdie' to nr_rapl_pmu and 'dieid' to rapl_pmu_idx
  x86/insn: Add support for APX EVEX instructions to the opcode map
  x86/insn: Add support for APX EVEX to the instruction decoder logic
  x86/insn: x86/insn: Add support for REX2 prefix to the instruction decoder opcode map
  x86/insn: Add support for REX2 prefix to the instruction decoder logic
  x86/insn: Add misc new Intel instructions
  x86/insn: Add VEX versions of VPDPBUSD, VPDPBUSDS, VPDPWSSD and VPDPWSSDS
  x86/insn: Fix PUSH instruction in x86 instruction decoder opcode map
  x86/insn: Add Key Locker instructions to the opcode map

5 files changed, 311 insertions, 97 deletions

diff --git a/tools/arch/x86/include/asm/inat.h b/tools/arch/x86/include/asm/inat.h
index a61051400311..253690eb3c26 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 +79,9 @@
 #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))
+#define INAT_EVEX_SCALABLE	(1 << (INAT_FLAG_OFFS + 10))
 /* 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 +133,11 @@ 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)
@@ -227,4 +237,9 @@ static inline int inat_must_evex(insn_attr_t attr)
 {
 	return attr & INAT_EVEXONLY;
 }
+
+static inline int inat_evex_scalable(insn_attr_t attr)
+{
+	return attr & INAT_EVEX_SCALABLE;
+}
 #endif
diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h
index 65c0d9ce1e29..0e5abd896ad4 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)
@@ -198,6 +215,13 @@ static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
 		return X86_VEX_P(insn->vex_prefix.bytes[2]);
 }
 
+static inline insn_byte_t insn_vex_w_bit(struct insn *insn)
+{
+	if (insn->vex_prefix.nbytes < 3)
+		return 0;
+	return X86_VEX_W(insn->vex_prefix.bytes[2]);
+}
+
 /* Get the last prefix id from last prefix or VEX prefix */
 static inline int insn_last_prefix_id(struct insn *insn)
 {
diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c
index ada4b4a79dd4..a43b37346a22 100644
--- a/tools/arch/x86/lib/insn.c
+++ b/tools/arch/x86/lib/insn.c
@@ -185,6 +185,17 @@ found:
 			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;
@@ -283,6 +294,10 @@ int insn_get_opcode(struct insn *insn)
 		m = insn_vex_m_bits(insn);
 		p = insn_vex_p_bits(insn);
 		insn->attr = inat_get_avx_attribute(op, m, p);
+		/* SCALABLE EVEX uses p bits to encode operand size */
+		if (inat_evex_scalable(insn->attr) && !insn_vex_w_bit(insn) &&
+		    p == INAT_PFX_OPNDSZ)
+			insn->opnd_bytes = 2;
 		if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) ||
 		    (!inat_accept_vex(insn->attr) &&
 		     !inat_is_group(insn->attr))) {
@@ -294,6 +309,20 @@ 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/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt
index 12af572201a2..caedb3ef6688 100644
--- a/tools/arch/x86/lib/x86-opcode-map.txt
+++ b/tools/arch/x86/lib/x86-opcode-map.txt
@@ -23,6 +23,7 @@
 #
 # AVX Superscripts
 #  (ev): this opcode requires EVEX prefix.
+#  (es): this opcode requires EVEX prefix and is SCALABALE.
 #  (evo): this opcode is changed by EVEX prefix (EVEX opcode)
 #  (v): this opcode requires VEX prefix.
 #  (v1): this opcode only supports 128bit VEX.
@@ -33,6 +34,10 @@
 #  - (F2): the last prefix is 0xF2
 #  - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
 #  - (66&F2): Both 0x66 and 0xF2 prefixes are specified.
+#
+# REX2 Prefix
+#  - (!REX2): REX2 is not allowed
+#  - (REX2): REX2 variant e.g. JMPABS
 
 Table: one byte opcode
 Referrer:
@@ -148,7 +153,7 @@ AVXcode:
 65: SEG=GS (Prefix)
 66: Operand-Size (Prefix)
 67: Address-Size (Prefix)
-68: PUSH Iz (d64)
+68: PUSH Iz
 69: IMUL Gv,Ev,Iz
 6a: PUSH Ib (d64)
 6b: IMUL Gv,Ev,Ib
@@ -157,22 +162,22 @@ AVXcode:
 6e: OUTS/OUTSB DX,Xb
 6f: OUTS/OUTSW/OUTSD DX,Xz
 # 0x70 - 0x7f
-70: JO Jb
-71: JNO Jb
-72: JB/JNAE/JC Jb
-73: JNB/JAE/JNC Jb
-74: JZ/JE Jb
-75: JNZ/JNE Jb
-76: JBE/JNA Jb
-77: JNBE/JA Jb
-78: JS Jb
-79: JNS Jb
-7a: JP/JPE Jb
-7b: JNP/JPO Jb
-7c: JL/JNGE Jb
-7d: JNL/JGE Jb
-7e: JLE/JNG Jb
-7f: JNLE/JG Jb
+70: JO Jb (!REX2)
+71: JNO Jb (!REX2)
+72: JB/JNAE/JC Jb (!REX2)
+73: JNB/JAE/JNC Jb (!REX2)
+74: JZ/JE Jb (!REX2)
+75: JNZ/JNE Jb (!REX2)
+76: JBE/JNA Jb (!REX2)
+77: JNBE/JA Jb (!REX2)
+78: JS Jb (!REX2)
+79: JNS Jb (!REX2)
+7a: JP/JPE Jb (!REX2)
+7b: JNP/JPO Jb (!REX2)
+7c: JL/JNGE Jb (!REX2)
+7d: JNL/JGE Jb (!REX2)
+7e: JLE/JNG Jb (!REX2)
+7f: JNLE/JG Jb (!REX2)
 # 0x80 - 0x8f
 80: Grp1 Eb,Ib (1A)
 81: Grp1 Ev,Iz (1A)
@@ -208,24 +213,24 @@ AVXcode:
 9e: SAHF
 9f: LAHF
 # 0xa0 - 0xaf
-a0: MOV AL,Ob
-a1: MOV rAX,Ov
-a2: MOV Ob,AL
-a3: MOV Ov,rAX
-a4: MOVS/B Yb,Xb
-a5: MOVS/W/D/Q Yv,Xv
-a6: CMPS/B Xb,Yb
-a7: CMPS/W/D Xv,Yv
-a8: TEST AL,Ib
-a9: TEST rAX,Iz
-aa: STOS/B Yb,AL
-ab: STOS/W/D/Q Yv,rAX
-ac: LODS/B AL,Xb
-ad: LODS/W/D/Q rAX,Xv
-ae: SCAS/B AL,Yb
+a0: MOV AL,Ob (!REX2)
+a1: MOV rAX,Ov (!REX2) | JMPABS O (REX2),(o64)
+a2: MOV Ob,AL (!REX2)
+a3: MOV Ov,rAX (!REX2)
+a4: MOVS/B Yb,Xb (!REX2)
+a5: MOVS/W/D/Q Yv,Xv (!REX2)
+a6: CMPS/B Xb,Yb (!REX2)
+a7: CMPS/W/D Xv,Yv (!REX2)
+a8: TEST AL,Ib (!REX2)
+a9: TEST rAX,Iz (!REX2)
+aa: STOS/B Yb,AL (!REX2)
+ab: STOS/W/D/Q Yv,rAX (!REX2)
+ac: LODS/B AL,Xb (!REX2)
+ad: LODS/W/D/Q rAX,Xv (!REX2)
+ae: SCAS/B AL,Yb (!REX2)
 # Note: The May 2011 Intel manual shows Xv for the second parameter of the
 # next instruction but Yv is correct
-af: SCAS/W/D/Q rAX,Yv
+af: SCAS/W/D/Q rAX,Yv (!REX2)
 # 0xb0 - 0xbf
 b0: MOV AL/R8L,Ib
 b1: MOV CL/R9L,Ib
@@ -266,7 +271,7 @@ d1: Grp2 Ev,1 (1A)
 d2: Grp2 Eb,CL (1A)
 d3: Grp2 Ev,CL (1A)
 d4: AAM Ib (i64)
-d5: AAD Ib (i64)
+d5: AAD Ib (i64) | REX2 (Prefix),(o64)
 d6:
 d7: XLAT/XLATB
 d8: ESC
@@ -281,26 +286,26 @@ df: ESC
 # Note: "forced64" is Intel CPU behavior: they ignore 0x66 prefix
 # in 64-bit mode. AMD CPUs accept 0x66 prefix, it causes RIP truncation
 # to 16 bits. In 32-bit mode, 0x66 is accepted by both Intel and AMD.
-e0: LOOPNE/LOOPNZ Jb (f64)
-e1: LOOPE/LOOPZ Jb (f64)
-e2: LOOP Jb (f64)
-e3: JrCXZ Jb (f64)
-e4: IN AL,Ib
-e5: IN eAX,Ib
-e6: OUT Ib,AL
-e7: OUT Ib,eAX
+e0: LOOPNE/LOOPNZ Jb (f64) (!REX2)
+e1: LOOPE/LOOPZ Jb (f64) (!REX2)
+e2: LOOP Jb (f64) (!REX2)
+e3: JrCXZ Jb (f64) (!REX2)
+e4: IN AL,Ib (!REX2)
+e5: IN eAX,Ib (!REX2)
+e6: OUT Ib,AL (!REX2)
+e7: OUT Ib,eAX (!REX2)
 # With 0x66 prefix in 64-bit mode, for AMD CPUs immediate offset
 # in "near" jumps and calls is 16-bit. For CALL,
 # push of return address is 16-bit wide, RSP is decremented by 2
 # but is not truncated to 16 bits, unlike RIP.
-e8: CALL Jz (f64)
-e9: JMP-near Jz (f64)
-ea: JMP-far Ap (i64)
-eb: JMP-short Jb (f64)
-ec: IN AL,DX
-ed: IN eAX,DX
-ee: OUT DX,AL
-ef: OUT DX,eAX
+e8: CALL Jz (f64) (!REX2)
+e9: JMP-near Jz (f64) (!REX2)
+ea: JMP-far Ap (i64) (!REX2)
+eb: JMP-short Jb (f64) (!REX2)
+ec: IN AL,DX (!REX2)
+ed: IN eAX,DX (!REX2)
+ee: OUT DX,AL (!REX2)
+ef: OUT DX,eAX (!REX2)
 # 0xf0 - 0xff
 f0: LOCK (Prefix)
 f1:
@@ -386,14 +391,14 @@ AVXcode: 1
 2e: vucomiss Vss,Wss (v1) | vucomisd  Vsd,Wsd (66),(v1)
 2f: vcomiss Vss,Wss (v1) | vcomisd  Vsd,Wsd (66),(v1)
 # 0x0f 0x30-0x3f
-30: WRMSR
-31: RDTSC
-32: RDMSR
-33: RDPMC
-34: SYSENTER
-35: SYSEXIT
+30: WRMSR (!REX2)
+31: RDTSC (!REX2)
+32: RDMSR (!REX2)
+33: RDPMC (!REX2)
+34: SYSENTER (!REX2)
+35: SYSEXIT (!REX2)
 36:
-37: GETSEC
+37: GETSEC (!REX2)
 38: escape # 3-byte escape 1
 39:
 3a: escape # 3-byte escape 2
@@ -473,22 +478,22 @@ AVXcode: 1
 7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
 # 0x0f 0x80-0x8f
 # Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
-80: JO Jz (f64)
-81: JNO Jz (f64)
-82: JB/JC/JNAE Jz (f64)
-83: JAE/JNB/JNC Jz (f64)
-84: JE/JZ Jz (f64)
-85: JNE/JNZ Jz (f64)
-86: JBE/JNA Jz (f64)
-87: JA/JNBE Jz (f64)
-88: JS Jz (f64)
-89: JNS Jz (f64)
-8a: JP/JPE Jz (f64)
-8b: JNP/JPO Jz (f64)
-8c: JL/JNGE Jz (f64)
-8d: JNL/JGE Jz (f64)
-8e: JLE/JNG Jz (f64)
-8f: JNLE/JG Jz (f64)
+80: JO Jz (f64) (!REX2)
+81: JNO Jz (f64) (!REX2)
+82: JB/JC/JNAE Jz (f64) (!REX2)
+83: JAE/JNB/JNC Jz (f64) (!REX2)
+84: JE/JZ Jz (f64) (!REX2)
+85: JNE/JNZ Jz (f64) (!REX2)
+86: JBE/JNA Jz (f64) (!REX2)
+87: JA/JNBE Jz (f64) (!REX2)
+88: JS Jz (f64) (!REX2)
+89: JNS Jz (f64) (!REX2)
+8a: JP/JPE Jz (f64) (!REX2)
+8b: JNP/JPO Jz (f64) (!REX2)
+8c: JL/JNGE Jz (f64) (!REX2)
+8d: JNL/JGE Jz (f64) (!REX2)
+8e: JLE/JNG Jz (f64) (!REX2)
+8f: JNLE/JG Jz (f64) (!REX2)
 # 0x0f 0x90-0x9f
 90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
 91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
@@ -698,17 +703,17 @@ AVXcode: 2
 4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
 4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
 4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)
-50: vpdpbusd Vx,Hx,Wx (66),(ev)
-51: vpdpbusds Vx,Hx,Wx (66),(ev)
-52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66),(ev) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev)
-53: vpdpwssds Vx,Hx,Wx (66),(ev) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev)
+50: vpdpbusd Vx,Hx,Wx (66) | vpdpbssd Vx,Hx,Wx (F2),(v) | vpdpbsud Vx,Hx,Wx (F3),(v) | vpdpbuud Vx,Hx,Wx (v)
+51: vpdpbusds Vx,Hx,Wx (66) | vpdpbssds Vx,Hx,Wx (F2),(v) | vpdpbsuds Vx,Hx,Wx (F3),(v) | vpdpbuuds Vx,Hx,Wx (v)
+52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev)
+53: vpdpwssds Vx,Hx,Wx (66) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev)
 54: vpopcntb/w Vx,Wx (66),(ev)
 55: vpopcntd/q Vx,Wx (66),(ev)
 58: vpbroadcastd Vx,Wx (66),(v)
 59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)
 5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)
 5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)
-5c: TDPBF16PS Vt,Wt,Ht (F3),(v1)
+5c: TDPBF16PS Vt,Wt,Ht (F3),(v1) | TDPFP16PS Vt,Wt,Ht (F2),(v1),(o64)
 # Skip 0x5d
 5e: TDPBSSD Vt,Wt,Ht (F2),(v1) | TDPBSUD Vt,Wt,Ht (F3),(v1) | TDPBUSD Vt,Wt,Ht (66),(v1) | TDPBUUD Vt,Wt,Ht (v1)
 # Skip 0x5f-0x61
@@ -718,10 +723,12 @@ AVXcode: 2
 65: vblendmps/d Vx,Hx,Wx (66),(ev)
 66: vpblendmb/w Vx,Hx,Wx (66),(ev)
 68: vp2intersectd/q Kx,Hx,Wx (F2),(ev)
-# Skip 0x69-0x6f
+# Skip 0x69-0x6b
+6c: TCMMIMFP16PS Vt,Wt,Ht (66),(v1),(o64) | TCMMRLFP16PS Vt,Wt,Ht (v1),(o64)
+# Skip 0x6d-0x6f
 70: vpshldvw Vx,Hx,Wx (66),(ev)
 71: vpshldvd/q Vx,Hx,Wx (66),(ev)
-72: vcvtne2ps2bf16 Vx,Hx,Wx (F2),(ev) | vcvtneps2bf16 Vx,Wx (F3),(ev) | vpshrdvw Vx,Hx,Wx (66),(ev)
+72: vcvtne2ps2bf16 Vx,Hx,Wx (F2),(ev) | vcvtneps2bf16 Vx,Wx (F3) | vpshrdvw Vx,Hx,Wx (66),(ev)
 73: vpshrdvd/q Vx,Hx,Wx (66),(ev)
 75: vpermi2b/w Vx,Hx,Wx (66),(ev)
 76: vpermi2d/q Vx,Hx,Wx (66),(ev)
@@ -777,8 +784,10 @@ ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
 ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
 ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
 af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
-b4: vpmadd52luq Vx,Hx,Wx (66),(ev)
-b5: vpmadd52huq Vx,Hx,Wx (66),(ev)
+b0: vcvtneebf162ps Vx,Mx (F3),(!11B),(v) | vcvtneeph2ps Vx,Mx (66),(!11B),(v) | vcvtneobf162ps Vx,Mx (F2),(!11B),(v) | vcvtneoph2ps Vx,Mx (!11B),(v)
+b1: vbcstnebf162ps Vx,Mw (F3),(!11B),(v) | vbcstnesh2ps Vx,Mw (66),(!11B),(v)
+b4: vpmadd52luq Vx,Hx,Wx (66)
+b5: vpmadd52huq Vx,Hx,Wx (66)
 b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
 b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
 b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
@@ -796,15 +805,35 @@ c7: Grp19 (1A)
 c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev)
 c9: sha1msg1 Vdq,Wdq
 ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev)
-cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev)
-cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev)
-cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev)
+cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev) | vsha512rnds2 Vqq,Hqq,Udq (F2),(11B),(v)
+cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev) | vsha512msg1 Vqq,Udq (F2),(11B),(v)
+cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev) | vsha512msg2 Vqq,Uqq (F2),(11B),(v)
 cf: vgf2p8mulb Vx,Wx (66)
+d2: vpdpwsud Vx,Hx,Wx (F3),(v) | vpdpwusd Vx,Hx,Wx (66),(v) | vpdpwuud Vx,Hx,Wx (v)
+d3: vpdpwsuds Vx,Hx,Wx (F3),(v) | vpdpwusds Vx,Hx,Wx (66),(v) | vpdpwuuds Vx,Hx,Wx (v)
+d8: AESENCWIDE128KL Qpi (F3),(000),(00B) | AESENCWIDE256KL Qpi (F3),(000),(10B) | AESDECWIDE128KL Qpi (F3),(000),(01B) | AESDECWIDE256KL Qpi (F3),(000),(11B)
+da: vsm3msg1 Vdq,Hdq,Udq (v1) | vsm3msg2 Vdq,Hdq,Udq (66),(v1) | vsm4key4 Vx,Hx,Wx (F3),(v) | vsm4rnds4 Vx,Hx,Wx (F2),(v)
 db: VAESIMC Vdq,Wdq (66),(v1)
-dc: vaesenc Vx,Hx,Wx (66)
-dd: vaesenclast Vx,Hx,Wx (66)
-de: vaesdec Vx,Hx,Wx (66)
-df: vaesdeclast Vx,Hx,Wx (66)
+dc: vaesenc Vx,Hx,Wx (66) | LOADIWKEY Vx,Hx (F3) | AESENC128KL Vpd,Qpi (F3)
+dd: vaesenclast Vx,Hx,Wx (66) | AESDEC128KL Vpd,Qpi (F3)
+de: vaesdec Vx,Hx,Wx (66) | AESENC256KL Vpd,Qpi (F3)
+df: vaesdeclast Vx,Hx,Wx (66) | AESDEC256KL Vpd,Qpi (F3)
+e0: CMPOXADD   My,Gy,By (66),(v1),(o64)
+e1: CMPNOXADD  My,Gy,By (66),(v1),(o64)
+e2: CMPBXADD   My,Gy,By (66),(v1),(o64)
+e3: CMPNBXADD  My,Gy,By (66),(v1),(o64)
+e4: CMPZXADD   My,Gy,By (66),(v1),(o64)
+e5: CMPNZXADD  My,Gy,By (66),(v1),(o64)
+e6: CMPBEXADD  My,Gy,By (66),(v1),(o64)
+e7: CMPNBEXADD My,Gy,By (66),(v1),(o64)
+e8: CMPSXADD   My,Gy,By (66),(v1),(o64)
+e9: CMPNSXADD  My,Gy,By (66),(v1),(o64)
+ea: CMPPXADD   My,Gy,By (66),(v1),(o64)
+eb: CMPNPXADD  My,Gy,By (66),(v1),(o64)
+ec: CMPLXADD   My,Gy,By (66),(v1),(o64)
+ed: CMPNLXADD  My,Gy,By (66),(v1),(o64)
+ee: CMPLEXADD  My,Gy,By (66),(v1),(o64)
+ef: CMPNLEXADD My,Gy,By (66),(v1),(o64)
 f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2)
 f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2)
 f2: ANDN Gy,By,Ey (v)
@@ -812,8 +841,11 @@ f3: Grp17 (1A)
 f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v) | WRUSSD/Q My,Gy (66)
 f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v) | WRSSD/Q My,Gy
 f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
-f8: MOVDIR64B Gv,Mdqq (66) | ENQCMD Gv,Mdqq (F2) | ENQCMDS Gv,Mdqq (F3)
+f8: MOVDIR64B Gv,Mdqq (66) | ENQCMD Gv,Mdqq (F2) | ENQCMDS Gv,Mdqq (F3) | URDMSR Rq,Gq (F2),(11B) | UWRMSR Gq,Rq (F3),(11B)
 f9: MOVDIRI My,Gy
+fa: ENCODEKEY128 Ew,Ew (F3)
+fb: ENCODEKEY256 Ew,Ew (F3)
+fc: AADD My,Gy | AAND My,Gy (66) | AOR My,Gy (F2) | AXOR My,Gy (F3)
 EndTable
 
 Table: 3-byte opcode 2 (0x0f 0x3a)
@@ -893,10 +925,103 @@ c2: vcmpph Vx,Hx,Wx,Ib (ev) | vcmpsh Vx,Hx,Wx,Ib (F3),(ev)
 cc: sha1rnds4 Vdq,Wdq,Ib
 ce: vgf2p8affineqb Vx,Wx,Ib (66)
 cf: vgf2p8affineinvqb Vx,Wx,Ib (66)
+de: vsm3rnds2 Vdq,Hdq,Wdq,Ib (66),(v1)
 df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
 f0: RORX Gy,Ey,Ib (F2),(v) | HRESET Gv,Ib (F3),(000),(11B)
 EndTable
 
+Table: EVEX map 4
+Referrer:
+AVXcode: 4
+00: ADD Eb,Gb (ev)
+01: ADD Ev,Gv (es) | ADD Ev,Gv (66),(es)
+02: ADD Gb,Eb (ev)
+03: ADD Gv,Ev (es) | ADD Gv,Ev (66),(es)
+08: OR Eb,Gb (ev)
+09: OR Ev,Gv (es) | OR Ev,Gv (66),(es)
+0a: OR Gb,Eb (ev)
+0b: OR Gv,Ev (es) | OR Gv,Ev (66),(es)
+10: ADC Eb,Gb (ev)
+11: ADC Ev,Gv (es) | ADC Ev,Gv (66),(es)
+12: ADC Gb,Eb (ev)
+13: ADC Gv,Ev (es) | ADC Gv,Ev (66),(es)
+18: SBB Eb,Gb (ev)
+19: SBB Ev,Gv (es) | SBB Ev,Gv (66),(es)
+1a: SBB Gb,Eb (ev)
+1b: SBB Gv,Ev (es) | SBB Gv,Ev (66),(es)
+20: AND Eb,Gb (ev)
+21: AND Ev,Gv (es) | AND Ev,Gv (66),(es)
+22: AND Gb,Eb (ev)
+23: AND Gv,Ev (es) | AND Gv,Ev (66),(es)
+24: SHLD Ev,Gv,Ib (es) | SHLD Ev,Gv,Ib (66),(es)
+28: SUB Eb,Gb (ev)
+29: SUB Ev,Gv (es) | SUB Ev,Gv (66),(es)
+2a: SUB Gb,Eb (ev)
+2b: SUB Gv,Ev (es) | SUB Gv,Ev (66),(es)
+2c: SHRD Ev,Gv,Ib (es) | SHRD Ev,Gv,Ib (66),(es)
+30: XOR Eb,Gb (ev)
+31: XOR Ev,Gv (es) | XOR Ev,Gv (66),(es)
+32: XOR Gb,Eb (ev)
+33: XOR Gv,Ev (es) | XOR Gv,Ev (66),(es)
+# CCMPSCC instructions are: CCOMB, CCOMBE, CCOMF, CCOML, CCOMLE, CCOMNB, CCOMNBE, CCOMNL, CCOMNLE,
+#			    CCOMNO, CCOMNS, CCOMNZ, CCOMO, CCOMS, CCOMT, CCOMZ
+38: CCMPSCC Eb,Gb (ev)
+39: CCMPSCC Ev,Gv (es) | CCMPSCC Ev,Gv (66),(es)
+3a: CCMPSCC Gv,Ev (ev)
+3b: CCMPSCC Gv,Ev (es) | CCMPSCC Gv,Ev (66),(es)
+40: CMOVO   Gv,Ev (es) | CMOVO   Gv,Ev (66),(es) | CFCMOVO   Ev,Ev (es) | CFCMOVO   Ev,Ev (66),(es) | SETO   Eb (F2),(ev)
+41: CMOVNO  Gv,Ev (es) | CMOVNO  Gv,Ev (66),(es) | CFCMOVNO  Ev,Ev (es) | CFCMOVNO  Ev,Ev (66),(es) | SETNO  Eb (F2),(ev)
+42: CMOVB   Gv,Ev (es) | CMOVB   Gv,Ev (66),(es) | CFCMOVB   Ev,Ev (es) | CFCMOVB   Ev,Ev (66),(es) | SETB   Eb (F2),(ev)
+43: CMOVNB  Gv,Ev (es) | CMOVNB  Gv,Ev (66),(es) | CFCMOVNB  Ev,Ev (es) | CFCMOVNB  Ev,Ev (66),(es) | SETNB  Eb (F2),(ev)
+44: CMOVZ   Gv,Ev (es) | CMOVZ   Gv,Ev (66),(es) | CFCMOVZ   Ev,Ev (es) | CFCMOVZ   Ev,Ev (66),(es) | SETZ   Eb (F2),(ev)
+45: CMOVNZ  Gv,Ev (es) | CMOVNZ  Gv,Ev (66),(es) | CFCMOVNZ  Ev,Ev (es) | CFCMOVNZ  Ev,Ev (66),(es) | SETNZ  Eb (F2),(ev)
+46: CMOVBE  Gv,Ev (es) | CMOVBE  Gv,Ev (66),(es) | CFCMOVBE  Ev,Ev (es) | CFCMOVBE  Ev,Ev (66),(es) | SETBE  Eb (F2),(ev)
+47: CMOVNBE Gv,Ev (es) | CMOVNBE Gv,Ev (66),(es) | CFCMOVNBE Ev,Ev (es) | CFCMOVNBE Ev,Ev (66),(es) | SETNBE Eb (F2),(ev)
+48: CMOVS   Gv,Ev (es) | CMOVS   Gv,Ev (66),(es) | CFCMOVS   Ev,Ev (es) | CFCMOVS   Ev,Ev (66),(es) | SETS   Eb (F2),(ev)
+49: CMOVNS  Gv,Ev (es) | CMOVNS  Gv,Ev (66),(es) | CFCMOVNS  Ev,Ev (es) | CFCMOVNS  Ev,Ev (66),(es) | SETNS  Eb (F2),(ev)
+4a: CMOVP   Gv,Ev (es) | CMOVP   Gv,Ev (66),(es) | CFCMOVP   Ev,Ev (es) | CFCMOVP   Ev,Ev (66),(es) | SETP   Eb (F2),(ev)
+4b: CMOVNP  Gv,Ev (es) | CMOVNP  Gv,Ev (66),(es) | CFCMOVNP  Ev,Ev (es) | CFCMOVNP  Ev,Ev (66),(es) | SETNP  Eb (F2),(ev)
+4c: CMOVL   Gv,Ev (es) | CMOVL   Gv,Ev (66),(es) | CFCMOVL   Ev,Ev (es) | CFCMOVL   Ev,Ev (66),(es) | SETL   Eb (F2),(ev)
+4d: CMOVNL  Gv,Ev (es) | CMOVNL  Gv,Ev (66),(es) | CFCMOVNL  Ev,Ev (es) | CFCMOVNL  Ev,Ev (66),(es) | SETNL  Eb (F2),(ev)
+4e: CMOVLE  Gv,Ev (es) | CMOVLE  Gv,Ev (66),(es) | CFCMOVLE  Ev,Ev (es) | CFCMOVLE  Ev,Ev (66),(es) | SETLE  Eb (F2),(ev)
+4f: CMOVNLE Gv,Ev (es) | CMOVNLE Gv,Ev (66),(es) | CFCMOVNLE Ev,Ev (es) | CFCMOVNLE Ev,Ev (66),(es) | SETNLE Eb (F2),(ev)
+60: MOVBE Gv,Ev (es) | MOVBE Gv,Ev (66),(es)
+61: MOVBE Ev,Gv (es) | MOVBE Ev,Gv (66),(es)
+65: WRUSSD Md,Gd (66),(ev) | WRUSSQ Mq,Gq (66),(ev)
+66: ADCX Gy,Ey (66),(ev) | ADOX Gy,Ey (F3),(ev) | WRSSD Md,Gd (ev) | WRSSQ Mq,Gq (66),(ev)
+69: IMUL Gv,Ev,Iz (es) | IMUL Gv,Ev,Iz (66),(es)
+6b: IMUL Gv,Ev,Ib (es) | IMUL Gv,Ev,Ib (66),(es)
+80: Grp1 Eb,Ib (1A),(ev)
+81: Grp1 Ev,Iz (1A),(es)
+83: Grp1 Ev,Ib (1A),(es)
+# CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL,
+#			     CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ
+84: CTESTSCC (ev)
+85: CTESTSCC (es) | CTESTSCC (66),(es)
+88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es)
+8f: POP2 Bq,Rq (000),(11B),(ev)
+a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es)
+ad: SHRD Ev,Gv,CL (es) | SHRD Ev,Gv,CL (66),(es)
+af: IMUL Gv,Ev (es) | IMUL Gv,Ev (66),(es)
+c0: Grp2 Eb,Ib (1A),(ev)
+c1: Grp2 Ev,Ib (1A),(es)
+d0: Grp2 Eb,1 (1A),(ev)
+d1: Grp2 Ev,1 (1A),(es)
+d2: Grp2 Eb,CL (1A),(ev)
+d3: Grp2 Ev,CL (1A),(es)
+f0: CRC32 Gy,Eb (es) | INVEPT Gq,Mdq (F3),(ev)
+f1: CRC32 Gy,Ey (es) | CRC32 Gy,Ey (66),(es) | INVVPID Gy,Mdq (F3),(ev)
+f2: INVPCID Gy,Mdq (F3),(ev)
+f4: TZCNT Gv,Ev (es) | TZCNT Gv,Ev (66),(es)
+f5: LZCNT Gv,Ev (es) | LZCNT Gv,Ev (66),(es)
+f6: Grp3_1 Eb (1A),(ev)
+f7: Grp3_2 Ev (1A),(es)
+f8: MOVDIR64B Gv,Mdqq (66),(ev) | ENQCMD Gv,Mdqq (F2),(ev) | ENQCMDS Gv,Mdqq (F3),(ev) | URDMSR Rq,Gq (F2),(11B),(ev) | UWRMSR Gq,Rq (F3),(11B),(ev)
+f9: MOVDIRI My,Gy (ev)
+fe: Grp4 (1A),(ev)
+ff: Grp5 (1A),(es) | PUSH2 Bq,Rq (110),(11B),(ev)
+EndTable
+
 Table: EVEX map 5
 Referrer:
 AVXcode: 5
@@ -975,6 +1100,12 @@ d6: vfcmulcph Vx,Hx,Wx (F2),(ev) | vfmulcph Vx,Hx,Wx (F3),(ev)
 d7: vfcmulcsh Vx,Hx,Wx (F2),(ev) | vfmulcsh Vx,Hx,Wx (F3),(ev)
 EndTable
 
+Table: VEX map 7
+Referrer:
+AVXcode: 7
+f8: URDMSR Rq,Id (F2),(v1),(11B) | UWRMSR Id,Rq (F3),(v1),(11B)
+EndTable
+
 GrpTable: Grp1
 0: ADD
 1: OR
@@ -1051,7 +1182,7 @@ GrpTable: Grp6
 EndTable
 
 GrpTable: Grp7
-0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) | WRMSRNS (110),(11B)
+0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) | WRMSRNS (110),(11B) | RDMSRLIST (F2),(110),(11B) | WRMSRLIST (F3),(110),(11B) | PBNDKB (111),(11B)
 1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) | ERETU (F3),(010),(11B) | ERETS (F2),(010),(11B)
 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B)
 3: LIDT Ms
@@ -1137,6 +1268,8 @@ GrpTable: Grp16
 1: prefetch T0
 2: prefetch T1
 3: prefetch T2
+6: prefetch IT1
+7: prefetch IT0
 EndTable
 
 GrpTable: Grp17
diff --git a/tools/arch/x86/tools/gen-insn-attr-x86.awk b/tools/arch/x86/tools/gen-insn-attr-x86.awk
index af38469afd14..5770c8097f32 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)\\)"
@@ -81,6 +83,8 @@ BEGIN {
 	vexonly_expr = "\\(v\\)"
 	# All opcodes with (ev) superscript supports *only* EVEX prefix
 	evexonly_expr = "\\(ev\\)"
+	# (es) is the same as (ev) but also "SCALABLE" i.e. W and pp determine operand size
+	evex_scalable_expr = "\\(es\\)"
 
 	prefix_expr = "\\(Prefix\\)"
 	prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
@@ -99,6 +103,7 @@ 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 +319,10 @@ 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)")
@@ -325,6 +334,8 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 		# check VEX codes
 		if (match(ext, evexonly_expr))
 			flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY")
+		else if (match(ext, evex_scalable_expr))
+			flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY | INAT_EVEX_SCALABLE")
 		else if (match(ext, vexonly_expr))
 			flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
 		else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
@@ -351,6 +362,8 @@ 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)
 		}