[PATCH 1/6] perf tests: Add AMX instructions to x86 instruction decoder test

[Adrian Hunter <adrian.hunter@intel.com>]

x86 instruction decoder is used for both kernel instructions and user space
instructions (e.g. uprobes, perf tools Intel PT), so it is good to update
it with new instructions.

Add AMX instructions to x86 instruction decoder test.

A subsequent patch adds the instructions to the instruction decoder.

Reference:
Intel Architecture Instruction Set Extensions and Future Features
Programming Reference
May 2021
Document Number: 319433-044

Example:

  $ INSN='ldtilecfg\|sttilecfg\|tdpbf16ps\|tdpbssd\|'
  $ INSN+='tdpbsud\|tdpbusd\|'tdpbuud\|tileloadd\|'
  $ INSN+='tileloaddt1\|tilerelease\|tilestored\|tilezero'
  $ perf test -v "x86 instruction decoder" |& grep -i $INSN
  Failed to decode: c4 e2 78 49 04 c8    	ldtilecfg (%rax,%rcx,8)
  Failed to decode: c4 c2 78 49 04 c8    	ldtilecfg (%r8,%rcx,8)
  Failed to decode: c4 e2 79 49 04 c8    	sttilecfg (%rax,%rcx,8)
  Failed to decode: c4 c2 79 49 04 c8    	sttilecfg (%r8,%rcx,8)
  Failed to decode: c4 e2 7a 5c d1       	tdpbf16ps %tmm0,%tmm1,%tmm2
  Failed to decode: c4 e2 7b 5e d1       	tdpbssd %tmm0,%tmm1,%tmm2
  Failed to decode: c4 e2 7a 5e d1       	tdpbsud %tmm0,%tmm1,%tmm2
  Failed to decode: c4 e2 79 5e d1       	tdpbusd %tmm0,%tmm1,%tmm2
  Failed to decode: c4 e2 78 5e d1       	tdpbuud %tmm0,%tmm1,%tmm2
  Failed to decode: c4 e2 7b 4b 0c c8    	tileloadd (%rax,%rcx,8),%tmm1
  Failed to decode: c4 c2 7b 4b 14 c8    	tileloadd (%r8,%rcx,8),%tmm2
  Failed to decode: c4 e2 79 4b 0c c8    	tileloaddt1 (%rax,%rcx,8),%tmm1
  Failed to decode: c4 c2 79 4b 14 c8    	tileloaddt1 (%r8,%rcx,8),%tmm2
  Failed to decode: c4 e2 78 49 c0       	tilerelease
  Failed to decode: c4 e2 7a 4b 0c c8    	tilestored %tmm1,(%rax,%rcx,8)
  Failed to decode: c4 c2 7a 4b 14 c8    	tilestored %tmm2,(%r8,%rcx,8)
  Failed to decode: c4 e2 7b 49 c0       	tilezero %tmm0
  Failed to decode: c4 e2 7b 49 f8       	tilezero %tmm7

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/arch/x86/tests/insn-x86-dat-64.c  | 36 ++++++++++++++++++++
 tools/perf/arch/x86/tests/insn-x86-dat-src.c | 21 ++++++++++++
 2 files changed, 57 insertions(+)

diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-64.c b/tools/perf/arch/x86/tests/insn-x86-dat-64.c
index 5da17d41d302..3548565a1cc5 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-64.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-64.c
@@ -2459,6 +2459,42 @@
 "3e f2 ff a4 c8 78 56 34 12 \tnotrack bnd jmpq *0x12345678(%rax,%rcx,8)",},
 {{0x3e, 0xf2, 0x41, 0xff, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "jmp", "indirect",
 "3e f2 41 ff a4 c8 78 56 34 12 \tnotrack bnd jmpq *0x12345678(%r8,%rcx,8)",},
+{{0xc4, 0xe2, 0x78, 0x49, 0x04, 0xc8, }, 6, 0, "", "",
+"c4 e2 78 49 04 c8    \tldtilecfg (%rax,%rcx,8)",},
+{{0xc4, 0xc2, 0x78, 0x49, 0x04, 0xc8, }, 6, 0, "", "",
+"c4 c2 78 49 04 c8    \tldtilecfg (%r8,%rcx,8)",},
+{{0xc4, 0xe2, 0x79, 0x49, 0x04, 0xc8, }, 6, 0, "", "",
+"c4 e2 79 49 04 c8    \tsttilecfg (%rax,%rcx,8)",},
+{{0xc4, 0xc2, 0x79, 0x49, 0x04, 0xc8, }, 6, 0, "", "",
+"c4 c2 79 49 04 c8    \tsttilecfg (%r8,%rcx,8)",},
+{{0xc4, 0xe2, 0x7a, 0x5c, 0xd1, }, 5, 0, "", "",
+"c4 e2 7a 5c d1       \ttdpbf16ps %tmm0,%tmm1,%tmm2",},
+{{0xc4, 0xe2, 0x7b, 0x5e, 0xd1, }, 5, 0, "", "",
+"c4 e2 7b 5e d1       \ttdpbssd %tmm0,%tmm1,%tmm2",},
+{{0xc4, 0xe2, 0x7a, 0x5e, 0xd1, }, 5, 0, "", "",
+"c4 e2 7a 5e d1       \ttdpbsud %tmm0,%tmm1,%tmm2",},
+{{0xc4, 0xe2, 0x79, 0x5e, 0xd1, }, 5, 0, "", "",
+"c4 e2 79 5e d1       \ttdpbusd %tmm0,%tmm1,%tmm2",},
+{{0xc4, 0xe2, 0x78, 0x5e, 0xd1, }, 5, 0, "", "",
+"c4 e2 78 5e d1       \ttdpbuud %tmm0,%tmm1,%tmm2",},
+{{0xc4, 0xe2, 0x7b, 0x4b, 0x0c, 0xc8, }, 6, 0, "", "",
+"c4 e2 7b 4b 0c c8    \ttileloadd (%rax,%rcx,8),%tmm1",},
+{{0xc4, 0xc2, 0x7b, 0x4b, 0x14, 0xc8, }, 6, 0, "", "",
+"c4 c2 7b 4b 14 c8    \ttileloadd (%r8,%rcx,8),%tmm2",},
+{{0xc4, 0xe2, 0x79, 0x4b, 0x0c, 0xc8, }, 6, 0, "", "",
+"c4 e2 79 4b 0c c8    \ttileloaddt1 (%rax,%rcx,8),%tmm1",},
+{{0xc4, 0xc2, 0x79, 0x4b, 0x14, 0xc8, }, 6, 0, "", "",
+"c4 c2 79 4b 14 c8    \ttileloaddt1 (%r8,%rcx,8),%tmm2",},
+{{0xc4, 0xe2, 0x78, 0x49, 0xc0, }, 5, 0, "", "",
+"c4 e2 78 49 c0       \ttilerelease ",},
+{{0xc4, 0xe2, 0x7a, 0x4b, 0x0c, 0xc8, }, 6, 0, "", "",
+"c4 e2 7a 4b 0c c8    \ttilestored %tmm1,(%rax,%rcx,8)",},
+{{0xc4, 0xc2, 0x7a, 0x4b, 0x14, 0xc8, }, 6, 0, "", "",
+"c4 c2 7a 4b 14 c8    \ttilestored %tmm2,(%r8,%rcx,8)",},
+{{0xc4, 0xe2, 0x7b, 0x49, 0xc0, }, 5, 0, "", "",
+"c4 e2 7b 49 c0       \ttilezero %tmm0",},
+{{0xc4, 0xe2, 0x7b, 0x49, 0xf8, }, 5, 0, "", "",
+"c4 e2 7b 49 f8       \ttilezero %tmm7",},
 {{0x0f, 0x01, 0xcf, }, 3, 0, "", "",
 "0f 01 cf             \tencls  ",},
 {{0x0f, 0x01, 0xd7, }, 3, 0, "", "",
diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-src.c b/tools/perf/arch/x86/tests/insn-x86-dat-src.c
index c3808e94c46e..7906f7b2ffeb 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-src.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-src.c
@@ -1910,6 +1910,27 @@ int main(void)
 	asm volatile("notrack bnd jmpq *0x12345678(%rax,%rcx,8)");	/* Expecting: jmp indirect 0 */
 	asm volatile("notrack bnd jmpq *0x12345678(%r8,%rcx,8)");	/* Expecting: jmp indirect 0 */
 
+	/* AMX */
+
+	asm volatile("ldtilecfg (%rax,%rcx,8)");
+	asm volatile("ldtilecfg (%r8,%rcx,8)");
+	asm volatile("sttilecfg (%rax,%rcx,8)");
+	asm volatile("sttilecfg (%r8,%rcx,8)");
+	asm volatile("tdpbf16ps %tmm0, %tmm1, %tmm2");
+	asm volatile("tdpbssd %tmm0, %tmm1, %tmm2");
+	asm volatile("tdpbsud %tmm0, %tmm1, %tmm2");
+	asm volatile("tdpbusd %tmm0, %tmm1, %tmm2");
+	asm volatile("tdpbuud %tmm0, %tmm1, %tmm2");
+	asm volatile("tileloadd (%rax,%rcx,8), %tmm1");
+	asm volatile("tileloadd (%r8,%rcx,8), %tmm2");
+	asm volatile("tileloaddt1 (%rax,%rcx,8), %tmm1");
+	asm volatile("tileloaddt1 (%r8,%rcx,8), %tmm2");
+	asm volatile("tilerelease");
+	asm volatile("tilestored %tmm1, (%rax,%rcx,8)");
+	asm volatile("tilestored %tmm2, (%r8,%rcx,8)");
+	asm volatile("tilezero %tmm0");
+	asm volatile("tilezero %tmm7");
+
 #else  /* #ifdef __x86_64__ */
 
 	/* bound r32, mem (same op code as EVEX prefix) */
-- 
2.25.1