26 files changed, 288 insertions, 103 deletions

diff --git a/tools/arch/alpha/include/uapi/asm/mman.h b/tools/arch/alpha/include/uapi/asm/mman.h
index c317d3e6867a..ea6a255ae61f 100644
--- a/tools/arch/alpha/include/uapi/asm/mman.h
+++ b/tools/arch/alpha/include/uapi/asm/mman.h
@@ -27,8 +27,6 @@
 #define MAP_NONBLOCK    0x40000
 #define MAP_NORESERVE   0x10000
 #define MAP_POPULATE    0x20000
-#define MAP_PRIVATE     0x02
-#define MAP_SHARED      0x01
 #define MAP_STACK       0x80000
 #define PROT_EXEC       0x4
 #define PROT_GROWSDOWN  0x01000000
diff --git a/tools/arch/mips/include/uapi/asm/mman.h b/tools/arch/mips/include/uapi/asm/mman.h
index de2206883abc..c8acaa138d46 100644
--- a/tools/arch/mips/include/uapi/asm/mman.h
+++ b/tools/arch/mips/include/uapi/asm/mman.h
@@ -28,8 +28,6 @@
 #define MAP_NONBLOCK    0x20000
 #define MAP_NORESERVE   0x0400
 #define MAP_POPULATE    0x10000
-#define MAP_PRIVATE     0x002
-#define MAP_SHARED      0x001
 #define MAP_STACK       0x40000
 #define PROT_EXEC       0x04
 #define PROT_GROWSDOWN  0x01000000
diff --git a/tools/arch/parisc/include/uapi/asm/mman.h b/tools/arch/parisc/include/uapi/asm/mman.h
index 1bd78758bde9..f9fd1325f5bd 100644
--- a/tools/arch/parisc/include/uapi/asm/mman.h
+++ b/tools/arch/parisc/include/uapi/asm/mman.h
@@ -27,8 +27,6 @@
 #define MAP_NONBLOCK    0x20000
 #define MAP_NORESERVE   0x4000
 #define MAP_POPULATE    0x10000
-#define MAP_PRIVATE     0x02
-#define MAP_SHARED      0x01
 #define MAP_STACK       0x40000
 #define PROT_EXEC       0x4
 #define PROT_GROWSDOWN  0x01000000
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 8c876c166ef2..26ca425f4c2c 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -463,10 +463,12 @@ struct kvm_ppc_cpu_char {
 #define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED       (1ULL << 58)
 #define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF      (1ULL << 57)
 #define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS        (1ULL << 56)
+#define KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST     (1ull << 54)
 
 #define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY       (1ULL << 63)
 #define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR          (1ULL << 62)
 #define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR     (1ULL << 61)
+#define KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE     (1ull << 58)
 
 /* Per-vcpu XICS interrupt controller state */
 #define KVM_REG_PPC_ICP_STATE   (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 6d6122524711..981ff9479648 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -344,6 +344,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW       (18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS       (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_TSX_FORCE_ABORT     (18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_PCONFIG             (18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL           (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP         (18*32+27) /* "" Single Thread Indirect Branch Predictors */
diff --git a/tools/arch/xtensa/include/uapi/asm/mman.h b/tools/arch/xtensa/include/uapi/asm/mman.h
index 34dde6f44dae..f2b08c990afc 100644
--- a/tools/arch/xtensa/include/uapi/asm/mman.h
+++ b/tools/arch/xtensa/include/uapi/asm/mman.h
@@ -27,8 +27,6 @@
 #define MAP_NONBLOCK    0x20000
 #define MAP_NORESERVE   0x0400
 #define MAP_POPULATE    0x10000
-#define MAP_PRIVATE     0x002
-#define MAP_SHARED      0x001
 #define MAP_STACK       0x40000
 #define PROT_EXEC       0x4
 #define PROT_GROWSDOWN  0x01000000
diff --git a/tools/build/feature/test-libopencsd.c b/tools/build/feature/test-libopencsd.c
index d68eb4fb40cc..2b0e02c38870 100644
--- a/tools/build/feature/test-libopencsd.c
+++ b/tools/build/feature/test-libopencsd.c
@@ -4,9 +4,9 @@
 /*
  * Check OpenCSD library version is sufficient to provide required features
  */
-#define OCSD_MIN_VER ((0 << 16) | (10 << 8) | (0))
+#define OCSD_MIN_VER ((0 << 16) | (11 << 8) | (0))
 #if !defined(OCSD_VER_NUM) || (OCSD_VER_NUM < OCSD_MIN_VER)
-#error "OpenCSD >= 0.10.0 is required"
+#error "OpenCSD >= 0.11.0 is required"
 #endif
 
 int main(void)
diff --git a/tools/include/uapi/asm-generic/mman-common-tools.h b/tools/include/uapi/asm-generic/mman-common-tools.h
new file mode 100644
index 000000000000..af7d0d3a3182
--- /dev/null
+++ b/tools/include/uapi/asm-generic/mman-common-tools.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
+#define __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
+
+#include <asm-generic/mman-common.h>
+
+/* We need this because we need to have tools/include/uapi/ included in the tools
+ * header search path to get access to stuff that is not yet in the system's
+ * copy of the files in that directory, but since this cset:
+ *
+ *     746c9398f5ac ("arch: move common mmap flags to linux/mman.h")
+ *
+ * We end up making sys/mman.h, that is in the system headers, to not find the
+ * MAP_SHARED and MAP_PRIVATE defines because they are not anymore in our copy
+ * of asm-generic/mman-common.h. So we define them here and include this header
+ * from each of the per arch mman.h headers.
+ */
+#ifndef MAP_SHARED
+#define MAP_SHARED      0x01            /* Share changes */
+#define MAP_PRIVATE     0x02            /* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03        /* share + validate extension flags */
+#endif
+#endif // __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index e7ee32861d51..abd238d0f7a4 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -15,9 +15,7 @@
 #define PROT_GROWSDOWN  0x01000000      /* mprotect flag: extend change to start of growsdown vma */
 #define PROT_GROWSUP    0x02000000      /* mprotect flag: extend change to end of growsup vma */
 
-#define MAP_SHARED      0x01            /* Share changes */
-#define MAP_PRIVATE     0x02            /* Changes are private */
-#define MAP_SHARED_VALIDATE 0x03        /* share + validate extension flags */
+/* 0x01 - 0x03 are defined in linux/mman.h */
 #define MAP_TYPE        0x0f            /* Mask for type of mapping */
 #define MAP_FIXED       0x10            /* Interpret addr exactly */
 #define MAP_ANONYMOUS   0x20            /* don't use a file */
diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h
index 653687d9771b..36c197fc44a0 100644
--- a/tools/include/uapi/asm-generic/mman.h
+++ b/tools/include/uapi/asm-generic/mman.h
@@ -2,7 +2,7 @@
 #ifndef __ASM_GENERIC_MMAN_H
 #define __ASM_GENERIC_MMAN_H
 
-#include <asm-generic/mman-common.h>
+#include <asm-generic/mman-common-tools.h>
 
 #define MAP_GROWSDOWN   0x0100          /* stack-like segment */
 #define MAP_DENYWRITE   0x0800          /* ETXTBSY */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 12cdf611d217..dee7292e1df6 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -824,8 +824,17 @@ __SYSCALL(__NR_futex_time64, sys_futex)
 __SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval)
 #endif
 
+#define __NR_pidfd_send_signal 424
+__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal)
+#define __NR_io_uring_setup 425
+__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
+#define __NR_io_uring_enter 426
+__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
+#define __NR_io_uring_register 427
+__SYSCALL(__NR_io_uring_register, sys_io_uring_register)
+
 #undef __NR_syscalls
-#define __NR_syscalls 424
+#define __NR_syscalls 428
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 298b2e197744..397810fa2d33 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -1486,9 +1486,73 @@ struct drm_i915_gem_context_param {
 #define   I915_CONTEXT_MAX_USER_PRIORITY        1023 /* inclusive */
 #define   I915_CONTEXT_DEFAULT_PRIORITY         0
 #define   I915_CONTEXT_MIN_USER_PRIORITY        -1023 /* inclusive */
+        /*
+         * When using the following param, value should be a pointer to
+         * drm_i915_gem_context_param_sseu.
+         */
+#define I915_CONTEXT_PARAM_SSEU         0x7
         __u64 value;
 };
 
+/**
+ * Context SSEU programming
+ *
+ * It may be necessary for either functional or performance reason to configure
+ * a context to run with a reduced number of SSEU (where SSEU stands for Slice/
+ * Sub-slice/EU).
+ *
+ * This is done by configuring SSEU configuration using the below
+ * @struct drm_i915_gem_context_param_sseu for every supported engine which
+ * userspace intends to use.
+ *
+ * Not all GPUs or engines support this functionality in which case an error
+ * code -ENODEV will be returned.
+ *
+ * Also, flexibility of possible SSEU configuration permutations varies between
+ * GPU generations and software imposed limitations. Requesting such a
+ * combination will return an error code of -EINVAL.
+ *
+ * NOTE: When perf/OA is active the context's SSEU configuration is ignored in
+ * favour of a single global setting.
+ */
+struct drm_i915_gem_context_param_sseu {
+        /*
+         * Engine class & instance to be configured or queried.
+         */
+        __u16 engine_class;
+        __u16 engine_instance;
+
+        /*
+         * Unused for now. Must be cleared to zero.
+         */
+        __u32 flags;
+
+        /*
+         * Mask of slices to enable for the context. Valid values are a subset
+         * of the bitmask value returned for I915_PARAM_SLICE_MASK.
+         */
+        __u64 slice_mask;
+
+        /*
+         * Mask of subslices to enable for the context. Valid values are a
+         * subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK.
+         */
+        __u64 subslice_mask;
+
+        /*
+         * Minimum/Maximum number of EUs to enable per subslice for the
+         * context. min_eus_per_subslice must be inferior or equal to
+         * max_eus_per_subslice.
+         */
+        __u16 min_eus_per_subslice;
+        __u16 max_eus_per_subslice;
+
+        /*
+         * Unused for now. Must be cleared to zero.
+         */
+        __u32 rsvd;
+};
+
 enum drm_i915_oa_format {
         I915_OA_FORMAT_A13 = 1,     /* HSW only */
         I915_OA_FORMAT_A29,         /* HSW only */
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index 6448cdd9a350..a2f8658f1c55 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -41,6 +41,7 @@
 #define F_SEAL_SHRINK   0x0002  /* prevent file from shrinking */
 #define F_SEAL_GROW     0x0004  /* prevent file from growing */
 #define F_SEAL_WRITE    0x0008  /* prevent writes */
+#define F_SEAL_FUTURE_WRITE     0x0010  /* prevent future writes while mapped */
 /* (1U << 31) is reserved for signed error codes */
 
 /*
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index d0f515d53299..fc1a64c3447b 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -12,6 +12,10 @@
 #define OVERCOMMIT_ALWAYS               1
 #define OVERCOMMIT_NEVER                2
 
+#define MAP_SHARED      0x01            /* Share changes */
+#define MAP_PRIVATE     0x02            /* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03        /* share + validate extension flags */
+
 /*
  * Huge page size encoding when MAP_HUGETLB is specified, and a huge page
  * size other than the default is desired.  See hugetlb_encode.h.
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 01f7555fd933..e8c9f77e9010 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -481,8 +481,8 @@ $(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_t
 mmap_flags_array := $(beauty_outdir)/mmap_flags_array.c
 mmap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mmap_flags.sh
 
-$(mmap_flags_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl)
-        $(Q)$(SHELL) '$(mmap_flags_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
+$(mmap_flags_array): $(linux_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl)
+        $(Q)$(SHELL) '$(mmap_flags_tbl)' $(linux_uapi_dir) $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
 
 mount_flags_array := $(beauty_outdir)/mount_flags_array.c
 mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 2ae92fddb6d5..92ee0b4378d4 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -345,6 +345,10 @@
 334     common  rseq                    __x64_sys_rseq
 # don't use numbers 387 through 423, add new calls after the last
 # 'common' entry
+424     common  pidfd_send_signal       __x64_sys_pidfd_send_signal
+425     common  io_uring_setup          __x64_sys_io_uring_setup
+426     common  io_uring_enter          __x64_sys_io_uring_enter
+427     common  io_uring_register       __x64_sys_io_uring_register
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 7b55613924de..c68ee06cae63 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -103,7 +103,7 @@ done
 # diff with extra ignore lines
 check arch/x86/lib/memcpy_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
 check arch/x86/lib/memset_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
-check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common.h>"'
+check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
 check include/uapi/linux/mman.h       '-I "^#include <\(uapi/\)*asm/mman.h>"'
 
 # diff non-symmetric files
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index e38518cdcbc3..74ef92f1d19a 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -107,6 +107,7 @@ import os
 from PySide.QtCore import *
 from PySide.QtGui import *
 from PySide.QtSql import *
+pyside_version_1 = True
 from decimal import *
 from ctypes import *
 from multiprocessing import Process, Array, Value, Event
@@ -1526,6 +1527,19 @@ def BranchDataPrep(query):
                         " (" + dsoname(query.value(15)) + ")")
         return data
 
+def BranchDataPrepWA(query):
+        data = []
+        data.append(query.value(0))
+        # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
+        data.append("{:>19}".format(query.value(1)))
+        for i in xrange(2, 8):
+                data.append(query.value(i))
+        data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) +
+                        " (" + dsoname(query.value(11)) + ")" + " -> " +
+                        tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) +
+                        " (" + dsoname(query.value(15)) + ")")
+        return data
+
 # Branch data model
 
 class BranchModel(TreeModel):
@@ -1553,7 +1567,11 @@ class BranchModel(TreeModel):
                         " AND evsel_id = " + str(self.event_id) +
                         " ORDER BY samples.id"
                         " LIMIT " + str(glb_chunk_sz))
-                self.fetcher = SQLFetcher(glb, sql, BranchDataPrep, self.AddSample)
+                if pyside_version_1 and sys.version_info[0] == 3:
+                        prep = BranchDataPrepWA
+                else:
+                        prep = BranchDataPrep
+                self.fetcher = SQLFetcher(glb, sql, prep, self.AddSample)
                 self.fetcher.done.connect(self.Update)
                 self.fetcher.Fetch(glb_chunk_sz)
 
@@ -2079,14 +2097,6 @@ def IsSelectable(db, table, sql = ""):
                 return False
         return True
 
-# SQL data preparation
-
-def SQLTableDataPrep(query, count):
-        data = []
-        for i in xrange(count):
-                data.append(query.value(i))
-        return data
-
 # SQL table data model item
 
 class SQLTableItem():
@@ -2110,7 +2120,7 @@ class SQLTableModel(TableModel):
                 self.more = True
                 self.populated = 0
                 self.column_headers = column_headers
-                self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): SQLTableDataPrep(x, y), self.AddSample)
+                self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): self.SQLTableDataPrep(x, y), self.AddSample)
                 self.fetcher.done.connect(self.Update)
                 self.fetcher.Fetch(glb_chunk_sz)
 
@@ -2154,6 +2164,12 @@ class SQLTableModel(TableModel):
         def columnHeader(self, column):
                 return self.column_headers[column]
 
+        def SQLTableDataPrep(self, query, count):
+                data = []
+                for i in xrange(count):
+                        data.append(query.value(i))
+                return data
+
 # SQL automatic table data model
 
 class SQLAutoTableModel(SQLTableModel):
@@ -2182,8 +2198,32 @@ class SQLAutoTableModel(SQLTableModel):
                         QueryExec(query, "SELECT column_name FROM information_schema.columns WHERE table_schema = '" + schema + "' and table_name = '" + select_table_name + "'")
                         while query.next():
                                 column_headers.append(query.value(0))
+                if pyside_version_1 and sys.version_info[0] == 3:
+                        if table_name == "samples_view":
+                                self.SQLTableDataPrep = self.samples_view_DataPrep
+                        if table_name == "samples":
+                                self.SQLTableDataPrep = self.samples_DataPrep
                 super(SQLAutoTableModel, self).__init__(glb, sql, column_headers, parent)
 
+        def samples_view_DataPrep(self, query, count):
+                data = []
+                data.append(query.value(0))
+                # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
+                data.append("{:>19}".format(query.value(1)))
+                for i in xrange(2, count):
+                        data.append(query.value(i))
+                return data
+
+        def samples_DataPrep(self, query, count):
+                data = []
+                for i in xrange(9):
+                        data.append(query.value(i))
+                # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
+                data.append("{:>19}".format(query.value(9)))
+                for i in xrange(10, count):
+                        data.append(query.value(i))
+                return data
+
 # Base class for custom ResizeColumnsToContents
 
 class ResizeColumnsToContentsBase(QObject):
@@ -2868,9 +2908,13 @@ class LibXED():
                 ok = self.xed_format_context(2, inst.xedp, inst.bufferp, sizeof(inst.buffer), ip, 0, 0)
                 if not ok:
                         return 0, ""
+                if sys.version_info[0] == 2:
+                        result = inst.buffer.value
+                else:
+                        result = inst.buffer.value.decode()
                 # Return instruction length and the disassembled instruction text
                 # For now, assume the length is in byte 166
-                return inst.xedd[166], inst.buffer.value
+                return inst.xedd[166], result
 
 def TryOpen(file_name):
         try:
@@ -2886,9 +2930,14 @@ def Is64Bit(f):
         header = f.read(7)
         f.seek(pos)
         magic = header[0:4]
-        eclass = ord(header[4])
-        encoding = ord(header[5])
-        version = ord(header[6])
+        if sys.version_info[0] == 2:
+                eclass = ord(header[4])
+                encoding = ord(header[5])
+                version = ord(header[6])
+        else:
+                eclass = header[4]
+                encoding = header[5]
+                version = header[6]
         if magic == chr(127) + "ELF" and eclass > 0 and eclass < 3 and encoding > 0 and encoding < 3 and version == 1:
                 result = True if eclass == 2 else False
         return result
diff --git a/tools/perf/trace/beauty/mmap_flags.sh b/tools/perf/trace/beauty/mmap_flags.sh
index 32bac9c0d694..5f5eefcb3c74 100755
--- a/tools/perf/trace/beauty/mmap_flags.sh
+++ b/tools/perf/trace/beauty/mmap_flags.sh
@@ -1,15 +1,18 @@
 #!/bin/sh
 # SPDX-License-Identifier: LGPL-2.1
 
-if [ $# -ne 2 ] ; then
+if [ $# -ne 3 ] ; then
         [ $# -eq 1 ] && hostarch=$1 || hostarch=`uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/`
+        linux_header_dir=tools/include/uapi/linux
         header_dir=tools/include/uapi/asm-generic
         arch_header_dir=tools/arch/${hostarch}/include/uapi/asm
 else
-        header_dir=$1
-        arch_header_dir=$2
+        linux_header_dir=$1
+        header_dir=$2
+        arch_header_dir=$3
 fi
 
+linux_mman=${linux_header_dir}/mman.h
 arch_mman=${arch_header_dir}/mman.h
 
 # those in egrep -vw are flags, we want just the bits
@@ -20,6 +23,11 @@ egrep -q $regex ${arch_mman} && \
 (egrep $regex ${arch_mman} | \
         sed -r "s/$regex/\2 \1/g"       | \
         xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
+egrep -q $regex ${linux_mman} && \
+(egrep $regex ${linux_mman} | \
+        egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
 ([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.*' ${arch_mman}) &&
 (egrep $regex ${header_dir}/mman-common.h | \
         egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index ba4c623cd8de..39fe21e1cf93 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -387,6 +387,7 @@ cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder,
                 break;
         case OCSD_INSTR_ISB:
         case OCSD_INSTR_DSB_DMB:
+        case OCSD_INSTR_WFI_WFE:
         case OCSD_INSTR_OTHER:
         default:
                 packet->last_instr_taken_branch = false;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index ec78e93085de..6689378ee577 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -231,35 +231,6 @@ void perf_evlist__set_leader(struct perf_evlist *evlist)
         }
 }
 
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *pattr)
-{
-        struct perf_event_attr attr = {
-                .type           = PERF_TYPE_HARDWARE,
-                .config         = PERF_COUNT_HW_CPU_CYCLES,
-                .exclude_kernel = 1,
-                .precise_ip     = 3,
-        };
-
-        event_attr_init(&attr);
-
-        /*
-         * Unnamed union member, not supported as struct member named
-         * initializer in older compilers such as gcc 4.4.7
-         */
-        attr.sample_period = 1;
-
-        while (attr.precise_ip != 0) {
-                int fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
-                if (fd != -1) {
-                        close(fd);
-                        break;
-                }
-                --attr.precise_ip;
-        }
-
-        pattr->precise_ip = attr.precise_ip;
-}
-
 int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise)
 {
         struct perf_evsel *evsel = perf_evsel__new_cycles(precise);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index dcb68f34d2cd..6a94785b9100 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -315,8 +315,6 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
                                      struct perf_evsel *tracking_evsel);
 
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
-
 struct perf_evsel *
 perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 7835e05f0c0a..66d066f18b5b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -295,7 +295,6 @@ struct perf_evsel *perf_evsel__new_cycles(bool precise)
         if (!precise)
                 goto new_event;
 
-        perf_event_attr__set_max_precise_ip(&attr);
         /*
          * Now let the usual logic to set up the perf_event_attr defaults
          * to kick in when we return and before perf_evsel__open() is called.
@@ -305,6 +304,8 @@ new_event:
         if (evsel == NULL)
                 goto out;
 
+        evsel->precise_max = true;
+
         /* use asprintf() because free(evsel) assumes name is allocated */
         if (asprintf(&evsel->name, "cycles%s%s%.*s",
                      (attr.precise_ip || attr.exclude_kernel) ? ":" : "",
@@ -1083,7 +1084,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
         }
 
         if (evsel->precise_max)
-                perf_event_attr__set_max_precise_ip(attr);
+                attr->precise_ip = 3;
 
         if (opts->all_user) {
                 attr->exclude_kernel = 1;
@@ -1749,6 +1750,59 @@ static bool ignore_missing_thread(struct perf_evsel *evsel,
         return true;
 }
 
+static void display_attr(struct perf_event_attr *attr)
+{
+        if (verbose >= 2) {
+                fprintf(stderr, "%.60s\n", graph_dotted_line);
+                fprintf(stderr, "perf_event_attr:\n");
+                perf_event_attr__fprintf(stderr, attr, __open_attr__fprintf, NULL);
+                fprintf(stderr, "%.60s\n", graph_dotted_line);
+        }
+}
+
+static int perf_event_open(struct perf_evsel *evsel,
+                           pid_t pid, int cpu, int group_fd,
+                           unsigned long flags)
+{
+        int precise_ip = evsel->attr.precise_ip;
+        int fd;
+
+        while (1) {
+                pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
+                          pid, cpu, group_fd, flags);
+
+                fd = sys_perf_event_open(&evsel->attr, pid, cpu, group_fd, flags);
+                if (fd >= 0)
+                        break;
+
+                /*
+                 * Do quick precise_ip fallback if:
+                 *  - there is precise_ip set in perf_event_attr
+                 *  - maximum precise is requested
+                 *  - sys_perf_event_open failed with ENOTSUP error,
+                 *    which is associated with wrong precise_ip
+                 */
+                if (!precise_ip || !evsel->precise_max || (errno != ENOTSUP))
+                        break;
+
+                /*
+                 * We tried all the precise_ip values, and it's
+                 * still failing, so leave it to standard fallback.
+                 */
+                if (!evsel->attr.precise_ip) {
+                        evsel->attr.precise_ip = precise_ip;
+                        break;
+                }
+
+                pr_debug2("\nsys_perf_event_open failed, error %d\n", -ENOTSUP);
+                evsel->attr.precise_ip--;
+                pr_debug2("decreasing precise_ip by one (%d)\n", evsel->attr.precise_ip);
+                display_attr(&evsel->attr);
+        }
+
+        return fd;
+}
+
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
                      struct thread_map *threads)
 {
@@ -1824,12 +1878,7 @@ retry_sample_id:
         if (perf_missing_features.sample_id_all)
                 evsel->attr.sample_id_all = 0;
 
-        if (verbose >= 2) {
-                fprintf(stderr, "%.60s\n", graph_dotted_line);
-                fprintf(stderr, "perf_event_attr:\n");
-                perf_event_attr__fprintf(stderr, &evsel->attr, __open_attr__fprintf, NULL);
-                fprintf(stderr, "%.60s\n", graph_dotted_line);
-        }
+        display_attr(&evsel->attr);
 
         for (cpu = 0; cpu < cpus->nr; cpu++) {
 
@@ -1841,13 +1890,10 @@ retry_sample_id:
 
                         group_fd = get_group_fd(evsel, cpu, thread);
 retry_open:
-                        pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
-                                  pid, cpus->map[cpu], group_fd, flags);
-
                         test_attr__ready();
 
-                        fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu],
-                                                 group_fd, flags);
+                        fd = perf_event_open(evsel, pid, cpus->map[cpu],
+                                             group_fd, flags);
 
                         FD(evsel, cpu, thread) = fd;
 
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 6e03db142091..872fab163585 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -251,19 +251,15 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
                 if (!(decoder->tsc_ctc_ratio_n % decoder->tsc_ctc_ratio_d))
                         decoder->tsc_ctc_mult = decoder->tsc_ctc_ratio_n /
                                                 decoder->tsc_ctc_ratio_d;
-
-                /*
-                 * Allow for timestamps appearing to backwards because a TSC
-                 * packet has slipped past a MTC packet, so allow 2 MTC ticks
-                 * or ...
-                 */
-                decoder->tsc_slip = multdiv(2 << decoder->mtc_shift,
-                                        decoder->tsc_ctc_ratio_n,
-                                        decoder->tsc_ctc_ratio_d);
         }
-        /* ... or 0x100 paranoia */
-        if (decoder->tsc_slip < 0x100)
-                decoder->tsc_slip = 0x100;
+
+        /*
+         * A TSC packet can slip past MTC packets so that the timestamp appears
+         * to go backwards. One estimate is that can be up to about 40 CPU
+         * cycles, which is certainly less than 0x1000 TSC ticks, but accept
+         * slippage an order of magnitude more to be on the safe side.
+         */
+        decoder->tsc_slip = 0x10000;
 
         intel_pt_log("timestamp: mtc_shift %u\n", decoder->mtc_shift);
         intel_pt_log("timestamp: tsc_ctc_ratio_n %u\n", decoder->tsc_ctc_ratio_n);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 61959aba7e27..3c520baa198c 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1421,6 +1421,20 @@ static void machine__set_kernel_mmap(struct machine *machine,
                 machine->vmlinux_map->end = ~0ULL;
 }
 
+static void machine__update_kernel_mmap(struct machine *machine,
+                                     u64 start, u64 end)
+{
+        struct map *map = machine__kernel_map(machine);
+
+        map__get(map);
+        map_groups__remove(&machine->kmaps, map);
+
+        machine__set_kernel_mmap(machine, start, end);
+
+        map_groups__insert(&machine->kmaps, map);
+        map__put(map);
+}
+
 int machine__create_kernel_maps(struct machine *machine)
 {
         struct dso *kernel = machine__get_kernel(machine);
@@ -1453,17 +1467,11 @@ int machine__create_kernel_maps(struct machine *machine)
                         goto out_put;
                 }
 
-                /* we have a real start address now, so re-order the kmaps */
-                map = machine__kernel_map(machine);
-
-                map__get(map);
-                map_groups__remove(&machine->kmaps, map);
-
-                /* assume it's the last in the kmaps */
-                machine__set_kernel_mmap(machine, addr, ~0ULL);
-
-                map_groups__insert(&machine->kmaps, map);
-                map__put(map);
+                /*
+                 * we have a real start address now, so re-order the kmaps
+                 * assume it's the last in the kmaps
+                 */
+                machine__update_kernel_mmap(machine, addr, ~0ULL);
         }
 
         if (machine__create_extra_kernel_maps(machine, kernel))
@@ -1599,7 +1607,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
                 if (strstr(kernel->long_name, "vmlinux"))
                         dso__set_short_name(kernel, "[kernel.vmlinux]", false);
 
-                machine__set_kernel_mmap(machine, event->mmap.start,
+                machine__update_kernel_mmap(machine, event->mmap.start,
                                          event->mmap.start + event->mmap.len);
 
                 /*
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 6199a3174ab9..e0429f4ef335 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -732,10 +732,20 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
 
                 if (!is_arm_pmu_core(name)) {
                         pname = pe->pmu ? pe->pmu : "cpu";
+
+                        /*
+                         * uncore alias may be from different PMU
+                         * with common prefix
+                         */
+                        if (pmu_is_uncore(name) &&
+                            !strncmp(pname, name, strlen(pname)))
+                                goto new_alias;
+
                         if (strcmp(pname, name))
                                 continue;
                 }
 
+new_alias:
                 /* need type casts to override 'const' */
                 __perf_pmu__new_alias(head, NULL, (char *)pe->name,
                                 (char *)pe->desc, (char *)pe->event,