Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "The main kernel side changes in this cycle were:

   - Various Intel-PT updates and optimizations (Alexander Shishkin)

   - Prohibit kprobes on Xen/KVM emulate prefixes (Masami Hiramatsu)

   - Add support for LSM and SELinux checks to control access to the
     perf syscall (Joel Fernandes)

   - Misc other changes, optimizations, fixes and cleanups - see the
     shortlog for details.

  There were numerous tooling changes as well - 254 non-merge commits.
  Here are the main changes - too many to list in detail:

   - Enhancements to core tooling infrastructure, perf.data, libperf,
     libtraceevent, event parsing, vendor events, Intel PT, callchains,
     BPF support and instruction decoding.

   - There were updates to the following tools:

        perf annotate
        perf diff
        perf inject
        perf kvm
        perf list
        perf maps
        perf parse
        perf probe
        perf record
        perf report
        perf script
        perf stat
        perf test
        perf trace

   - And a lot of other changes: please see the shortlog and Git log for
     more details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (279 commits)
  perf parse: Fix potential memory leak when handling tracepoint errors
  perf probe: Fix spelling mistake "addrees" -> "address"
  libtraceevent: Fix memory leakage in copy_filter_type
  libtraceevent: Fix header installation
  perf intel-bts: Does not support AUX area sampling
  perf intel-pt: Add support for decoding AUX area samples
  perf intel-pt: Add support for recording AUX area samples
  perf pmu: When using default config, record which bits of config were changed by the user
  perf auxtrace: Add support for queuing AUX area samples
  perf session: Add facility to peek at all events
  perf auxtrace: Add support for dumping AUX area samples
  perf inject: Cut AUX area samples
  perf record: Add aux-sample-size config term
  perf record: Add support for AUX area sampling
  perf auxtrace: Add support for AUX area sample recording
  perf auxtrace: Move perf_evsel__find_pmu()
  perf record: Add a function to test for kernel support for AUX area sampling
  perf tools: Add kernel AUX area sampling definitions
  perf/core: Make the mlock accounting simple again
  perf report: Jump to symbol source view from total cycles view
  ...

21 files changed, 364 insertions, 13 deletions

diff --git a/tools/perf/arch/arm/util/Build b/tools/perf/arch/arm/util/Build
index 296f0eac5e18..37fc63708966 100644
--- a/tools/perf/arch/arm/util/Build
+++ b/tools/perf/arch/arm/util/Build
@@ -1,3 +1,5 @@
+perf-y += perf_regs.o
+
 perf-$(CONFIG_DWARF) += dwarf-regs.o
 
 perf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind.o
diff --git a/tools/perf/arch/arm/util/perf_regs.c b/tools/perf/arch/arm/util/perf_regs.c
new file mode 100644
index 000000000000..2864e2e3776d
--- /dev/null
+++ b/tools/perf/arch/arm/util/perf_regs.c
@@ -0,0 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../../util/perf_regs.h"
+
+const struct sample_reg sample_reg_masks[] = {
+	SMPL_REG_END
+};
diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build
index 3cde540d2fcf..0a7782c61209 100644
--- a/tools/perf/arch/arm64/util/Build
+++ b/tools/perf/arch/arm64/util/Build
@@ -1,4 +1,5 @@
 perf-y += header.o
+perf-y += perf_regs.o
 perf-y += sym-handling.o
 perf-$(CONFIG_DWARF)     += dwarf-regs.o
 perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
diff --git a/tools/perf/arch/arm64/util/perf_regs.c b/tools/perf/arch/arm64/util/perf_regs.c
new file mode 100644
index 000000000000..2864e2e3776d
--- /dev/null
+++ b/tools/perf/arch/arm64/util/perf_regs.c
@@ -0,0 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../../util/perf_regs.h"
+
+const struct sample_reg sample_reg_masks[] = {
+	SMPL_REG_END
+};
diff --git a/tools/perf/arch/arm64/util/sym-handling.c b/tools/perf/arch/arm64/util/sym-handling.c
index 5df788985130..8dfa3e5229f1 100644
--- a/tools/perf/arch/arm64/util/sym-handling.c
+++ b/tools/perf/arch/arm64/util/sym-handling.c
@@ -6,9 +6,10 @@
 
 #include "symbol.h" // for the elf__needs_adjust_symbols() prototype
 #include <stdbool.h>
-#include <gelf.h>
 
 #ifdef HAVE_LIBELF_SUPPORT
+#include <gelf.h>
+
 bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
 {
 	return ehdr.e_type == ET_EXEC ||
diff --git a/tools/perf/arch/csky/util/Build b/tools/perf/arch/csky/util/Build
index 1160bb2332ba..7d3050134ae0 100644
--- a/tools/perf/arch/csky/util/Build
+++ b/tools/perf/arch/csky/util/Build
@@ -1,2 +1,4 @@
+perf-y += perf_regs.o
+
 perf-$(CONFIG_DWARF) += dwarf-regs.o
 perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
diff --git a/tools/perf/arch/csky/util/perf_regs.c b/tools/perf/arch/csky/util/perf_regs.c
new file mode 100644
index 000000000000..2864e2e3776d
--- /dev/null
+++ b/tools/perf/arch/csky/util/perf_regs.c
@@ -0,0 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../../util/perf_regs.h"
+
+const struct sample_reg sample_reg_masks[] = {
+	SMPL_REG_END
+};
diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c
index 9cc1c4a9dec4..16807269317c 100644
--- a/tools/perf/arch/powerpc/util/kvm-stat.c
+++ b/tools/perf/arch/powerpc/util/kvm-stat.c
@@ -113,10 +113,10 @@ static int is_tracepoint_available(const char *str, struct evlist *evlist)
 	struct parse_events_error err;
 	int ret;
 
-	err.str = NULL;
+	bzero(&err, sizeof(err));
 	ret = parse_events(evlist, str, &err);
 	if (err.str)
-		pr_err("%s : %s\n", str, err.str);
+		parse_events_print_error(&err, "tracepoint");
 	return ret;
 }
 
diff --git a/tools/perf/arch/riscv/util/Build b/tools/perf/arch/riscv/util/Build
index 1160bb2332ba..7d3050134ae0 100644
--- a/tools/perf/arch/riscv/util/Build
+++ b/tools/perf/arch/riscv/util/Build
@@ -1,2 +1,4 @@
+perf-y += perf_regs.o
+
 perf-$(CONFIG_DWARF) += dwarf-regs.o
 perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
diff --git a/tools/perf/arch/riscv/util/perf_regs.c b/tools/perf/arch/riscv/util/perf_regs.c
new file mode 100644
index 000000000000..2864e2e3776d
--- /dev/null
+++ b/tools/perf/arch/riscv/util/perf_regs.c
@@ -0,0 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../../util/perf_regs.h"
+
+const struct sample_reg sample_reg_masks[] = {
+	SMPL_REG_END
+};
diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c
index a50e70baf918..2a6662e42f89 100644
--- a/tools/perf/arch/s390/annotate/instructions.c
+++ b/tools/perf/arch/s390/annotate/instructions.c
@@ -7,7 +7,7 @@ static int s390_call__parse(struct arch *arch, struct ins_operands *ops,
 	char *endptr, *tok, *name;
 	struct map *map = ms->map;
 	struct addr_map_symbol target = {
-		.map = map,
+		.ms = { .map = map, },
 	};
 
 	tok = strchr(ops->raw, ',');
@@ -38,9 +38,9 @@ static int s390_call__parse(struct arch *arch, struct ins_operands *ops,
 		return -1;
 	target.addr = map__objdump_2mem(map, ops->target.addr);
 
-	if (map_groups__find_ams(&target) == 0 &&
-	    map__rip_2objdump(target.map, map->map_ip(target.map, target.addr)) == ops->target.addr)
-		ops->target.sym = target.sym;
+	if (map_groups__find_ams(ms->mg, &target) == 0 &&
+	    map__rip_2objdump(target.ms.map, map->map_ip(target.ms.map, target.addr)) == ops->target.addr)
+		ops->target.sym = target.ms.sym;
 
 	return 0;
 }
diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build
index 22797f043b84..3d9d0f4f72ca 100644
--- a/tools/perf/arch/s390/util/Build
+++ b/tools/perf/arch/s390/util/Build
@@ -1,5 +1,6 @@
 perf-y += header.o
 perf-y += kvm-stat.o
+perf-y += perf_regs.o
 
 perf-$(CONFIG_DWARF) += dwarf-regs.o
 perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
diff --git a/tools/perf/arch/s390/util/perf_regs.c b/tools/perf/arch/s390/util/perf_regs.c
new file mode 100644
index 000000000000..2864e2e3776d
--- /dev/null
+++ b/tools/perf/arch/s390/util/perf_regs.c
@@ -0,0 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../../util/perf_regs.h"
+
+const struct sample_reg sample_reg_masks[] = {
+	SMPL_REG_END
+};
diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-32.c b/tools/perf/arch/x86/tests/insn-x86-dat-32.c
index fab3c6de73fa..58f8f2a095c4 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-32.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-32.c
@@ -1647,6 +1647,12 @@
 "0f ae 30             \txsaveopt (%eax)",},
 {{0x0f, 0xae, 0xf0, }, 3, 0, "", "",
 "0f ae f0             \tmfence ",},
+{{0x0f, 0x1c, 0x00, }, 3, 0, "", "",
+"0f 1c 00             \tcldemote (%eax)",},
+{{0x0f, 0x1c, 0x05, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 1c 05 78 56 34 12 \tcldemote 0x12345678",},
+{{0x0f, 0x1c, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"0f 1c 84 c8 78 56 34 12 \tcldemote 0x12345678(%eax,%ecx,8)",},
 {{0x0f, 0xc7, 0x20, }, 3, 0, "", "",
 "0f c7 20             \txsavec (%eax)",},
 {{0x0f, 0xc7, 0x25, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
@@ -1677,3 +1683,49 @@
 "f3 0f ae 25 78 56 34 12 \tptwritel 0x12345678",},
 {{0xf3, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
 "f3 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%eax,%ecx,8)",},
+{{0x66, 0x0f, 0xae, 0xf3, }, 4, 0, "", "",
+"66 0f ae f3          \ttpause %ebx",},
+{{0x67, 0xf3, 0x0f, 0xae, 0xf0, }, 5, 0, "", "",
+"67 f3 0f ae f0       \tumonitor %ax",},
+{{0xf3, 0x0f, 0xae, 0xf0, }, 4, 0, "", "",
+"f3 0f ae f0          \tumonitor %eax",},
+{{0xf2, 0x0f, 0xae, 0xf0, }, 4, 0, "", "",
+"f2 0f ae f0          \tumwait %eax",},
+{{0x0f, 0x38, 0xf9, 0x03, }, 4, 0, "", "",
+"0f 38 f9 03          \tmovdiri %eax,(%ebx)",},
+{{0x0f, 0x38, 0xf9, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"0f 38 f9 88 78 56 34 12 \tmovdiri %ecx,0x12345678(%eax)",},
+{{0x66, 0x0f, 0x38, 0xf8, 0x18, }, 5, 0, "", "",
+"66 0f 38 f8 18       \tmovdir64b (%eax),%ebx",},
+{{0x66, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"66 0f 38 f8 88 78 56 34 12 \tmovdir64b 0x12345678(%eax),%ecx",},
+{{0x67, 0x66, 0x0f, 0x38, 0xf8, 0x1c, }, 6, 0, "", "",
+"67 66 0f 38 f8 1c    \tmovdir64b (%si),%bx",},
+{{0x67, 0x66, 0x0f, 0x38, 0xf8, 0x8c, 0x34, 0x12, }, 8, 0, "", "",
+"67 66 0f 38 f8 8c 34 12 \tmovdir64b 0x1234(%si),%cx",},
+{{0xf2, 0x0f, 0x38, 0xf8, 0x18, }, 5, 0, "", "",
+"f2 0f 38 f8 18       \tenqcmd (%eax),%ebx",},
+{{0xf2, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"f2 0f 38 f8 88 78 56 34 12 \tenqcmd 0x12345678(%eax),%ecx",},
+{{0x67, 0xf2, 0x0f, 0x38, 0xf8, 0x1c, }, 6, 0, "", "",
+"67 f2 0f 38 f8 1c    \tenqcmd (%si),%bx",},
+{{0x67, 0xf2, 0x0f, 0x38, 0xf8, 0x8c, 0x34, 0x12, }, 8, 0, "", "",
+"67 f2 0f 38 f8 8c 34 12 \tenqcmd 0x1234(%si),%cx",},
+{{0xf3, 0x0f, 0x38, 0xf8, 0x18, }, 5, 0, "", "",
+"f3 0f 38 f8 18       \tenqcmds (%eax),%ebx",},
+{{0xf3, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"f3 0f 38 f8 88 78 56 34 12 \tenqcmds 0x12345678(%eax),%ecx",},
+{{0x67, 0xf3, 0x0f, 0x38, 0xf8, 0x1c, }, 6, 0, "", "",
+"67 f3 0f 38 f8 1c    \tenqcmds (%si),%bx",},
+{{0x67, 0xf3, 0x0f, 0x38, 0xf8, 0x8c, 0x34, 0x12, }, 8, 0, "", "",
+"67 f3 0f 38 f8 8c 34 12 \tenqcmds 0x1234(%si),%cx",},
+{{0x0f, 0x01, 0xcf, }, 3, 0, "", "",
+"0f 01 cf             \tencls  ",},
+{{0x0f, 0x01, 0xd7, }, 3, 0, "", "",
+"0f 01 d7             \tenclu  ",},
+{{0x0f, 0x01, 0xc0, }, 3, 0, "", "",
+"0f 01 c0             \tenclv  ",},
+{{0x0f, 0x01, 0xc5, }, 3, 0, "", "",
+"0f 01 c5             \tpconfig ",},
+{{0xf3, 0x0f, 0x09, }, 3, 0, "", "",
+"f3 0f 09             \twbnoinvd ",},
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 c57f34603b9b..656f8aed31de 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-64.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-64.c
@@ -1667,6 +1667,16 @@
 "41 0f ae 30          \txsaveopt (%r8)",},
 {{0x0f, 0xae, 0xf0, }, 3, 0, "", "",
 "0f ae f0             \tmfence ",},
+{{0x0f, 0x1c, 0x00, }, 3, 0, "", "",
+"0f 1c 00             \tcldemote (%rax)",},
+{{0x41, 0x0f, 0x1c, 0x00, }, 4, 0, "", "",
+"41 0f 1c 00          \tcldemote (%r8)",},
+{{0x0f, 0x1c, 0x04, 0x25, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"0f 1c 04 25 78 56 34 12 \tcldemote 0x12345678",},
+{{0x0f, 0x1c, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"0f 1c 84 c8 78 56 34 12 \tcldemote 0x12345678(%rax,%rcx,8)",},
+{{0x41, 0x0f, 0x1c, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"41 0f 1c 84 c8 78 56 34 12 \tcldemote 0x12345678(%r8,%rcx,8)",},
 {{0x0f, 0xc7, 0x20, }, 3, 0, "", "",
 "0f c7 20             \txsavec (%rax)",},
 {{0x41, 0x0f, 0xc7, 0x20, }, 4, 0, "", "",
@@ -1727,3 +1737,55 @@
 "f3 48 0f ae a4 c8 78 56 34 12 \tptwriteq 0x12345678(%rax,%rcx,8)",},
 {{0xf3, 0x49, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
 "f3 49 0f ae a4 c8 78 56 34 12 \tptwriteq 0x12345678(%r8,%rcx,8)",},
+{{0x66, 0x0f, 0xae, 0xf3, }, 4, 0, "", "",
+"66 0f ae f3          \ttpause %ebx",},
+{{0x66, 0x41, 0x0f, 0xae, 0xf0, }, 5, 0, "", "",
+"66 41 0f ae f0       \ttpause %r8d",},
+{{0x67, 0xf3, 0x0f, 0xae, 0xf0, }, 5, 0, "", "",
+"67 f3 0f ae f0       \tumonitor %eax",},
+{{0xf3, 0x0f, 0xae, 0xf0, }, 4, 0, "", "",
+"f3 0f ae f0          \tumonitor %rax",},
+{{0x67, 0xf3, 0x41, 0x0f, 0xae, 0xf0, }, 6, 0, "", "",
+"67 f3 41 0f ae f0    \tumonitor %r8d",},
+{{0xf2, 0x0f, 0xae, 0xf0, }, 4, 0, "", "",
+"f2 0f ae f0          \tumwait %eax",},
+{{0xf2, 0x41, 0x0f, 0xae, 0xf0, }, 5, 0, "", "",
+"f2 41 0f ae f0       \tumwait %r8d",},
+{{0x48, 0x0f, 0x38, 0xf9, 0x03, }, 5, 0, "", "",
+"48 0f 38 f9 03       \tmovdiri %rax,(%rbx)",},
+{{0x48, 0x0f, 0x38, 0xf9, 0x88, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"48 0f 38 f9 88 78 56 34 12 \tmovdiri %rcx,0x12345678(%rax)",},
+{{0x66, 0x0f, 0x38, 0xf8, 0x18, }, 5, 0, "", "",
+"66 0f 38 f8 18       \tmovdir64b (%rax),%rbx",},
+{{0x66, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"66 0f 38 f8 88 78 56 34 12 \tmovdir64b 0x12345678(%rax),%rcx",},
+{{0x67, 0x66, 0x0f, 0x38, 0xf8, 0x18, }, 6, 0, "", "",
+"67 66 0f 38 f8 18    \tmovdir64b (%eax),%ebx",},
+{{0x67, 0x66, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"67 66 0f 38 f8 88 78 56 34 12 \tmovdir64b 0x12345678(%eax),%ecx",},
+{{0xf2, 0x0f, 0x38, 0xf8, 0x18, }, 5, 0, "", "",
+"f2 0f 38 f8 18       \tenqcmd (%rax),%rbx",},
+{{0xf2, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"f2 0f 38 f8 88 78 56 34 12 \tenqcmd 0x12345678(%rax),%rcx",},
+{{0x67, 0xf2, 0x0f, 0x38, 0xf8, 0x18, }, 6, 0, "", "",
+"67 f2 0f 38 f8 18    \tenqcmd (%eax),%ebx",},
+{{0x67, 0xf2, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"67 f2 0f 38 f8 88 78 56 34 12 \tenqcmd 0x12345678(%eax),%ecx",},
+{{0xf3, 0x0f, 0x38, 0xf8, 0x18, }, 5, 0, "", "",
+"f3 0f 38 f8 18       \tenqcmds (%rax),%rbx",},
+{{0xf3, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"f3 0f 38 f8 88 78 56 34 12 \tenqcmds 0x12345678(%rax),%rcx",},
+{{0x67, 0xf3, 0x0f, 0x38, 0xf8, 0x18, }, 6, 0, "", "",
+"67 f3 0f 38 f8 18    \tenqcmds (%eax),%ebx",},
+{{0x67, 0xf3, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"67 f3 0f 38 f8 88 78 56 34 12 \tenqcmds 0x12345678(%eax),%ecx",},
+{{0x0f, 0x01, 0xcf, }, 3, 0, "", "",
+"0f 01 cf             \tencls  ",},
+{{0x0f, 0x01, 0xd7, }, 3, 0, "", "",
+"0f 01 d7             \tenclu  ",},
+{{0x0f, 0x01, 0xc0, }, 3, 0, "", "",
+"0f 01 c0             \tenclv  ",},
+{{0x0f, 0x01, 0xc5, }, 3, 0, "", "",
+"0f 01 c5             \tpconfig ",},
+{{0xf3, 0x0f, 0x09, }, 3, 0, "", "",
+"f3 0f 09             \twbnoinvd ",},
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 891415b10984..dd85a3afd9ce 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-src.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-src.c
@@ -1320,6 +1320,14 @@ int main(void)
 	asm volatile("xsaveopt (%r8)");
 	asm volatile("mfence");
 
+	/* cldemote m8 */
+
+	asm volatile("cldemote (%rax)");
+	asm volatile("cldemote (%r8)");
+	asm volatile("cldemote (0x12345678)");
+	asm volatile("cldemote 0x12345678(%rax,%rcx,8)");
+	asm volatile("cldemote 0x12345678(%r8,%rcx,8)");
+
 	/* xsavec mem */
 
 	asm volatile("xsavec (%rax)");
@@ -1364,6 +1372,48 @@ int main(void)
 	asm volatile("ptwriteq 0x12345678(%rax,%rcx,8)");
 	asm volatile("ptwriteq 0x12345678(%r8,%rcx,8)");
 
+	/* tpause */
+
+	asm volatile("tpause %ebx");
+	asm volatile("tpause %r8d");
+
+	/* umonitor */
+
+	asm volatile("umonitor %eax");
+	asm volatile("umonitor %rax");
+	asm volatile("umonitor %r8d");
+
+	/* umwait */
+
+	asm volatile("umwait %eax");
+	asm volatile("umwait %r8d");
+
+	/* movdiri */
+
+	asm volatile("movdiri %rax,(%rbx)");
+	asm volatile("movdiri %rcx,0x12345678(%rax)");
+
+	/* movdir64b */
+
+	asm volatile("movdir64b (%rax),%rbx");
+	asm volatile("movdir64b 0x12345678(%rax),%rcx");
+	asm volatile("movdir64b (%eax),%ebx");
+	asm volatile("movdir64b 0x12345678(%eax),%ecx");
+
+	/* enqcmd */
+
+	asm volatile("enqcmd (%rax),%rbx");
+	asm volatile("enqcmd 0x12345678(%rax),%rcx");
+	asm volatile("enqcmd (%eax),%ebx");
+	asm volatile("enqcmd 0x12345678(%eax),%ecx");
+
+	/* enqcmds */
+
+	asm volatile("enqcmds (%rax),%rbx");
+	asm volatile("enqcmds 0x12345678(%rax),%rcx");
+	asm volatile("enqcmds (%eax),%ebx");
+	asm volatile("enqcmds 0x12345678(%eax),%ecx");
+
 #else  /* #ifdef __x86_64__ */
 
 	/* bound r32, mem (same op code as EVEX prefix) */
@@ -2656,6 +2706,12 @@ int main(void)
 	asm volatile("xsaveopt (%eax)");
 	asm volatile("mfence");
 
+	/* cldemote m8 */
+
+	asm volatile("cldemote (%eax)");
+	asm volatile("cldemote (0x12345678)");
+	asm volatile("cldemote 0x12345678(%eax,%ecx,8)");
+
 	/* xsavec mem */
 
 	asm volatile("xsavec (%eax)");
@@ -2684,8 +2740,61 @@ int main(void)
 	asm volatile("ptwritel (0x12345678)");
 	asm volatile("ptwritel 0x12345678(%eax,%ecx,8)");
 
+	/* tpause */
+
+	asm volatile("tpause %ebx");
+
+	/* umonitor */
+
+	asm volatile("umonitor %ax");
+	asm volatile("umonitor %eax");
+
+	/* umwait */
+
+	asm volatile("umwait %eax");
+
+	/* movdiri */
+
+	asm volatile("movdiri %eax,(%ebx)");
+	asm volatile("movdiri %ecx,0x12345678(%eax)");
+
+	/* movdir64b */
+
+	asm volatile("movdir64b (%eax),%ebx");
+	asm volatile("movdir64b 0x12345678(%eax),%ecx");
+	asm volatile("movdir64b (%si),%bx");
+	asm volatile("movdir64b 0x1234(%si),%cx");
+
+	/* enqcmd */
+
+	asm volatile("enqcmd (%eax),%ebx");
+	asm volatile("enqcmd 0x12345678(%eax),%ecx");
+	asm volatile("enqcmd (%si),%bx");
+	asm volatile("enqcmd 0x1234(%si),%cx");
+
+	/* enqcmds */
+
+	asm volatile("enqcmds (%eax),%ebx");
+	asm volatile("enqcmds 0x12345678(%eax),%ecx");
+	asm volatile("enqcmds (%si),%bx");
+	asm volatile("enqcmds 0x1234(%si),%cx");
+
 #endif /* #ifndef __x86_64__ */
 
+	/* SGX */
+
+	asm volatile("encls");
+	asm volatile("enclu");
+	asm volatile("enclv");
+
+	/* pconfig */
+
+	asm volatile("pconfig");
+
+	/* wbnoinvd */
+
+	asm volatile("wbnoinvd");
+
 	/* Following line is a marker for the awk script - do not change */
 	asm volatile("rdtsc"); /* Stop here */
 
diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index fa947952c16a..909ead08a6f6 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -9,6 +9,7 @@
 #include <sys/prctl.h>
 #include <perf/cpumap.h>
 #include <perf/evlist.h>
+#include <perf/mmap.h>
 
 #include "debug.h"
 #include "parse-events.h"
@@ -117,10 +118,10 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 
 	for (i = 0; i < evlist->core.nr_mmaps; i++) {
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md) < 0)
+		if (perf_mmap__read_init(&md->core) < 0)
 			continue;
 
-		while ((event = perf_mmap__read_event(md)) != NULL) {
+		while ((event = perf_mmap__read_event(&md->core)) != NULL) {
 			struct perf_sample sample;
 
 			if (event->header.type != PERF_RECORD_COMM ||
@@ -139,9 +140,9 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 				comm2_time = sample.time;
 			}
 next_event:
-			perf_mmap__consume(md);
+			perf_mmap__consume(&md->core);
 		}
-		perf_mmap__read_done(md);
+		perf_mmap__read_done(&md->core);
 	}
 
 	if (!comm1_time || !comm2_time)
diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c
index 96f4a2c11893..7abc9fd4cbec 100644
--- a/tools/perf/arch/x86/util/auxtrace.c
+++ b/tools/perf/arch/x86/util/auxtrace.c
@@ -26,7 +26,11 @@ struct auxtrace_record *auxtrace_record__init_intel(struct evlist *evlist,
 	bool found_bts = false;
 
 	intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME);
+	if (intel_pt_pmu)
+		intel_pt_pmu->auxtrace = true;
 	intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
+	if (intel_bts_pmu)
+		intel_bts_pmu->auxtrace = true;
 
 	evlist__for_each_entry(evlist, evsel) {
 		if (intel_pt_pmu && evsel->core.attr.type == intel_pt_pmu->type)
diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c
index d357c625c09f..d1044df7c0d7 100644
--- a/tools/perf/arch/x86/util/event.c
+++ b/tools/perf/arch/x86/util/event.c
@@ -29,7 +29,7 @@ int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
 		return -1;
 	}
 
-	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
+	maps__for_each_entry(maps, pos) {
 		struct kmap *kmap;
 		size_t size;
 
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index f7f68a50a5cd..27d9e214d068 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -113,6 +113,11 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
 	const struct perf_cpu_map *cpus = evlist->core.cpus;
 	bool privileged = perf_event_paranoid_check(-1);
 
+	if (opts->auxtrace_sample_mode) {
+		pr_err("Intel BTS does not support AUX area sampling\n");
+		return -EINVAL;
+	}
+
 	btsr->evlist = evlist;
 	btsr->snapshot_mode = opts->auxtrace_snapshot_mode;
 
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index d6d26256915f..20df442fdf36 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -17,6 +17,7 @@
 #include "../../util/event.h"
 #include "../../util/evlist.h"
 #include "../../util/evsel.h"
+#include "../../util/evsel_config.h"
 #include "../../util/cpumap.h"
 #include "../../util/mmap.h"
 #include <subcmd/parse-options.h>
@@ -551,6 +552,43 @@ static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu,
 					evsel->core.attr.config);
 }
 
+static void intel_pt_config_sample_mode(struct perf_pmu *intel_pt_pmu,
+					struct evsel *evsel)
+{
+	struct perf_evsel_config_term *term;
+	u64 user_bits = 0, bits;
+
+	term = perf_evsel__get_config_term(evsel, CFG_CHG);
+	if (term)
+		user_bits = term->val.cfg_chg;
+
+	bits = perf_pmu__format_bits(&intel_pt_pmu->format, "psb_period");
+
+	/* Did user change psb_period */
+	if (bits & user_bits)
+		return;
+
+	/* Set psb_period to 0 */
+	evsel->core.attr.config &= ~bits;
+}
+
+static void intel_pt_min_max_sample_sz(struct evlist *evlist,
+				       size_t *min_sz, size_t *max_sz)
+{
+	struct evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel) {
+		size_t sz = evsel->core.attr.aux_sample_size;
+
+		if (!sz)
+			continue;
+		if (min_sz && (sz < *min_sz || !*min_sz))
+			*min_sz = sz;
+		if (max_sz && sz > *max_sz)
+			*max_sz = sz;
+	}
+}
+
 /*
  * Currently, there is not enough information to disambiguate different PEBS
  * events, so only allow one.
@@ -606,6 +644,11 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 		return -EINVAL;
 	}
 
+	if (opts->auxtrace_snapshot_mode && opts->auxtrace_sample_mode) {
+		pr_err("Snapshot mode (" INTEL_PT_PMU_NAME " PMU) and sample trace cannot be used together\n");
+		return -EINVAL;
+	}
+
 	if (opts->use_clockid) {
 		pr_err("Cannot use clockid (-k option) with " INTEL_PT_PMU_NAME "\n");
 		return -EINVAL;
@@ -617,6 +660,9 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 	if (!opts->full_auxtrace)
 		return 0;
 
+	if (opts->auxtrace_sample_mode)
+		intel_pt_config_sample_mode(intel_pt_pmu, intel_pt_evsel);
+
 	err = intel_pt_validate_config(intel_pt_pmu, intel_pt_evsel);
 	if (err)
 		return err;
@@ -666,6 +712,34 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 				    opts->auxtrace_snapshot_size, psb_period);
 	}
 
+	/* Set default sizes for sample mode */
+	if (opts->auxtrace_sample_mode) {
+		size_t psb_period = intel_pt_psb_period(intel_pt_pmu, evlist);
+		size_t min_sz = 0, max_sz = 0;
+
+		intel_pt_min_max_sample_sz(evlist, &min_sz, &max_sz);
+		if (!opts->auxtrace_mmap_pages && !privileged &&
+		    opts->mmap_pages == UINT_MAX)
+			opts->mmap_pages = KiB(256) / page_size;
+		if (!opts->auxtrace_mmap_pages) {
+			size_t sz = round_up(max_sz, page_size) / page_size;
+
+			opts->auxtrace_mmap_pages = roundup_pow_of_two(sz);
+		}
+		if (max_sz > opts->auxtrace_mmap_pages * (size_t)page_size) {
+			pr_err("Sample size %zu must not be greater than AUX area tracing mmap size %zu\n",
+			       max_sz,
+			       opts->auxtrace_mmap_pages * (size_t)page_size);
+			return -EINVAL;
+		}
+		pr_debug2("Intel PT min. sample size: %zu max. sample size: %zu\n",
+			  min_sz, max_sz);
+		if (psb_period &&
+		    min_sz <= psb_period + INTEL_PT_PSB_PERIOD_NEAR)
+			ui__warning("Intel PT sample size (%zu) may be too small for PSB period (%zu)\n",
+				    min_sz, psb_period);
+	}
+
 	/* Set default sizes for full trace mode */
 	if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) {
 		if (privileged) {
@@ -682,7 +756,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 		size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size;
 		size_t min_sz;
 
-		if (opts->auxtrace_snapshot_mode)
+		if (opts->auxtrace_snapshot_mode || opts->auxtrace_sample_mode)
 			min_sz = KiB(4);
 		else
 			min_sz = KiB(8);
@@ -1136,5 +1210,10 @@ struct auxtrace_record *intel_pt_recording_init(int *err)
 	ptr->itr.parse_snapshot_options = intel_pt_parse_snapshot_options;
 	ptr->itr.reference = intel_pt_reference;
 	ptr->itr.read_finish = intel_pt_read_finish;
+	/*
+	 * Decoding starts at a PSB packet. Minimum PSB period is 2K so 4K
+	 * should give at least 1 PSB per sample.
+	 */
+	ptr->itr.default_aux_sample_size = 4096;
 	return &ptr->itr;
 }