Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Minor comment merge conflict in mlx5.

Staging driver has a fixup due to the skb->xmit_more changes
in 'net-next', but was removed in 'net'.

Signed-off-by: David S. Miller <davem@davemloft.net>

40 files changed, 757 insertions, 198 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/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 5bf8e52c41fc..8e7c56e9590f 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -177,7 +177,7 @@ $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
 
 $(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN)
 	$(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(VERSION) \
-				    -Wl,--version-script=$(VERSION_SCRIPT) $^ -o $@
+				    -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@
 	@ln -sf $(@F) $(OUTPUT)libbpf.so
 	@ln -sf $(@F) $(OUTPUT)libbpf.so.$(VERSION)
 
@@ -220,8 +220,9 @@ install_lib: all_cmd
 install_headers:
 	$(call QUIET_INSTALL, headers) \
 		$(call do_install,bpf.h,$(prefix)/include/bpf,644); \
-		$(call do_install,libbpf.h,$(prefix)/include/bpf,644);
-		$(call do_install,btf.h,$(prefix)/include/bpf,644);
+		$(call do_install,libbpf.h,$(prefix)/include/bpf,644); \
+		$(call do_install,btf.h,$(prefix)/include/bpf,644); \
+		$(call do_install,xsk.h,$(prefix)/include/bpf,644);
 
 install: install_lib
 
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 87e3020ac1bc..cf119c9b6f27 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -2107,6 +2107,9 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 		return fwd_kind == real_kind;
 	}
 
+	if (cand_kind != canon_kind)
+		return 0;
+
 	switch (cand_kind) {
 	case BTF_KIND_INT:
 		return btf_equal_int(cand_type, canon_type);
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index c9d038f91af6..53f8be0f4a1f 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -25,14 +25,17 @@ LIBSUBCMD		= $(LIBSUBCMD_OUTPUT)libsubcmd.a
 OBJTOOL    := $(OUTPUT)objtool
 OBJTOOL_IN := $(OBJTOOL)-in.o
 
+LIBELF_FLAGS := $(shell pkg-config libelf --cflags 2>/dev/null)
+LIBELF_LIBS  := $(shell pkg-config libelf --libs 2>/dev/null || echo -lelf)
+
 all: $(OBJTOOL)
 
 INCLUDES := -I$(srctree)/tools/include \
 	    -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
 	    -I$(srctree)/tools/objtool/arch/$(ARCH)/include
 WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
-CFLAGS   += -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES)
-LDFLAGS  += -lelf $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS)
+CFLAGS   += -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES) $(LIBELF_FLAGS)
+LDFLAGS  += $(LIBELF_LIBS) $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS)
 
 # Allow old libelf to be used:
 elfshdr := $(shell echo '$(pound)include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | grep elf_getshdr)
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,
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index c3fad065c89c..c7727be9719f 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -44,6 +44,7 @@
 #include <cpuid.h>
 #include <linux/capability.h>
 #include <errno.h>
+#include <math.h>
 
 char *proc_stat = "/proc/stat";
 FILE *outf;
@@ -63,7 +64,6 @@ unsigned int dump_only;
 unsigned int do_snb_cstates;
 unsigned int do_knl_cstates;
 unsigned int do_slm_cstates;
-unsigned int do_cnl_cstates;
 unsigned int use_c1_residency_msr;
 unsigned int has_aperf;
 unsigned int has_epb;
@@ -141,9 +141,21 @@ unsigned int first_counter_read = 1;
 
 #define RAPL_CORES_ENERGY_STATUS	(1 << 9)
 					/* 0x639 MSR_PP0_ENERGY_STATUS */
+#define RAPL_PER_CORE_ENERGY	(1 << 10)
+					/* Indicates cores energy collection is per-core,
+					 * not per-package. */
+#define RAPL_AMD_F17H		(1 << 11)
+					/* 0xc0010299 MSR_RAPL_PWR_UNIT */
+					/* 0xc001029a MSR_CORE_ENERGY_STAT */
+					/* 0xc001029b MSR_PKG_ENERGY_STAT */
 #define RAPL_CORES (RAPL_CORES_ENERGY_STATUS | RAPL_CORES_POWER_LIMIT)
 #define	TJMAX_DEFAULT	100
 
+/* MSRs that are not yet in the kernel-provided header. */
+#define MSR_RAPL_PWR_UNIT	0xc0010299
+#define MSR_CORE_ENERGY_STAT	0xc001029a
+#define MSR_PKG_ENERGY_STAT	0xc001029b
+
 #define MAX(a, b) ((a) > (b) ? (a) : (b))
 
 /*
@@ -187,6 +199,7 @@ struct core_data {
 	unsigned long long c7;
 	unsigned long long mc6_us;	/* duplicate as per-core for now, even though per module */
 	unsigned int core_temp_c;
+	unsigned int core_energy;	/* MSR_CORE_ENERGY_STAT */
 	unsigned int core_id;
 	unsigned long long counter[MAX_ADDED_COUNTERS];
 } *core_even, *core_odd;
@@ -273,6 +286,7 @@ struct system_summary {
 
 struct cpu_topology {
 	int physical_package_id;
+	int die_id;
 	int logical_cpu_id;
 	int physical_node_id;
 	int logical_node_id;	/* 0-based count within the package */
@@ -283,6 +297,7 @@ struct cpu_topology {
 
 struct topo_params {
 	int num_packages;
+	int num_die;
 	int num_cpus;
 	int num_cores;
 	int max_cpu_num;
@@ -314,9 +329,8 @@ int for_all_cpus(int (func)(struct thread_data *, struct core_data *, struct pkg
 	int retval, pkg_no, core_no, thread_no, node_no;
 
 	for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) {
-		for (core_no = 0; core_no < topo.cores_per_node; ++core_no) {
-			for (node_no = 0; node_no < topo.nodes_per_pkg;
-			     node_no++) {
+		for (node_no = 0; node_no < topo.nodes_per_pkg; node_no++) {
+			for (core_no = 0; core_no < topo.cores_per_node; ++core_no) {
 				for (thread_no = 0; thread_no <
 					topo.threads_per_core; ++thread_no) {
 					struct thread_data *t;
@@ -442,6 +456,7 @@ struct msr_counter bic[] = {
 	{ 0x0, "CPU" },
 	{ 0x0, "APIC" },
 	{ 0x0, "X2APIC" },
+	{ 0x0, "Die" },
 };
 
 #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
@@ -495,6 +510,7 @@ struct msr_counter bic[] = {
 #define	BIC_CPU		(1ULL << 47)
 #define	BIC_APIC	(1ULL << 48)
 #define	BIC_X2APIC	(1ULL << 49)
+#define	BIC_Die		(1ULL << 50)
 
 #define BIC_DISABLED_BY_DEFAULT	(BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
 
@@ -621,6 +637,8 @@ void print_header(char *delim)
 		outp += sprintf(outp, "%sTime_Of_Day_Seconds", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Package))
 		outp += sprintf(outp, "%sPackage", (printed++ ? delim : ""));
+	if (DO_BIC(BIC_Die))
+		outp += sprintf(outp, "%sDie", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Node))
 		outp += sprintf(outp, "%sNode", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Core))
@@ -667,7 +685,7 @@ void print_header(char *delim)
 
 	if (DO_BIC(BIC_CPU_c1))
 		outp += sprintf(outp, "%sCPU%%c1", (printed++ ? delim : ""));
-	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates)
+	if (DO_BIC(BIC_CPU_c3))
 		outp += sprintf(outp, "%sCPU%%c3", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_CPU_c6))
 		outp += sprintf(outp, "%sCPU%%c6", (printed++ ? delim : ""));
@@ -680,6 +698,14 @@ void print_header(char *delim)
 	if (DO_BIC(BIC_CoreTmp))
 		outp += sprintf(outp, "%sCoreTmp", (printed++ ? delim : ""));
 
+	if (do_rapl && !rapl_joules) {
+		if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
+			outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : ""));
+	} else if (do_rapl && rapl_joules) {
+		if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY))
+			outp += sprintf(outp, "%sCor_J", (printed++ ? delim : ""));
+	}
+
 	for (mp = sys.cp; mp; mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
 			if (mp->width == 64)
@@ -734,7 +760,7 @@ void print_header(char *delim)
 	if (do_rapl && !rapl_joules) {
 		if (DO_BIC(BIC_PkgWatt))
 			outp += sprintf(outp, "%sPkgWatt", (printed++ ? delim : ""));
-		if (DO_BIC(BIC_CorWatt))
+		if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY))
 			outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_GFXWatt))
 			outp += sprintf(outp, "%sGFXWatt", (printed++ ? delim : ""));
@@ -747,7 +773,7 @@ void print_header(char *delim)
 	} else if (do_rapl && rapl_joules) {
 		if (DO_BIC(BIC_Pkg_J))
 			outp += sprintf(outp, "%sPkg_J", (printed++ ? delim : ""));
-		if (DO_BIC(BIC_Cor_J))
+		if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY))
 			outp += sprintf(outp, "%sCor_J", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_GFX_J))
 			outp += sprintf(outp, "%sGFX_J", (printed++ ? delim : ""));
@@ -808,6 +834,7 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "c6: %016llX\n", c->c6);
 		outp += sprintf(outp, "c7: %016llX\n", c->c7);
 		outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c);
+		outp += sprintf(outp, "Joules: %0X\n", c->core_energy);
 
 		for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 			outp += sprintf(outp, "cADDED [%d] msr0x%x: %08llX\n",
@@ -904,6 +931,8 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (t == &average.threads) {
 		if (DO_BIC(BIC_Package))
 			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+		if (DO_BIC(BIC_Die))
+			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_Node))
 			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_Core))
@@ -921,6 +950,12 @@ int format_counters(struct thread_data *t, struct core_data *c,
 			else
 				outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		}
+		if (DO_BIC(BIC_Die)) {
+			if (c)
+				outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), cpus[t->cpu_id].die_id);
+			else
+				outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+		}
 		if (DO_BIC(BIC_Node)) {
 			if (t)
 				outp += sprintf(outp, "%s%d",
@@ -1003,7 +1038,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		goto done;
 
-	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates)
+	if (DO_BIC(BIC_CPU_c3))
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c3/tsc);
 	if (DO_BIC(BIC_CPU_c6))
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c6/tsc);
@@ -1033,6 +1068,20 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		}
 	}
 
+	/*
+	 * If measurement interval exceeds minimum RAPL Joule Counter range,
+	 * indicate that results are suspect by printing "**" in fraction place.
+	 */
+	if (interval_float < rapl_joule_counter_range)
+		fmt8 = "%s%.2f";
+	else
+		fmt8 = "%6.0f**";
+
+	if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
+		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float);
+	if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY))
+		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units);
+
 	/* print per-package data only for 1st core in package */
 	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
 		goto done;
@@ -1085,18 +1134,9 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (DO_BIC(BIC_SYS_LPI))
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->sys_lpi / 1000000.0 / interval_float);
 
-	/*
- 	 * If measurement interval exceeds minimum RAPL Joule Counter range,
- 	 * indicate that results are suspect by printing "**" in fraction place.
- 	 */
-	if (interval_float < rapl_joule_counter_range)
-		fmt8 = "%s%.2f";
-	else
-		fmt8 = "%6.0f**";
-
 	if (DO_BIC(BIC_PkgWatt))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float);
-	if (DO_BIC(BIC_CorWatt))
+	if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float);
 	if (DO_BIC(BIC_GFXWatt))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units / interval_float);
@@ -1104,7 +1144,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units / interval_float);
 	if (DO_BIC(BIC_Pkg_J))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units);
-	if (DO_BIC(BIC_Cor_J))
+	if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units);
 	if (DO_BIC(BIC_GFX_J))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units);
@@ -1249,6 +1289,8 @@ delta_core(struct core_data *new, struct core_data *old)
 	old->core_temp_c = new->core_temp_c;
 	old->mc6_us = new->mc6_us - old->mc6_us;
 
+	DELTA_WRAP32(new->core_energy, old->core_energy);
+
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
 			old->counter[i] = new->counter[i];
@@ -1391,6 +1433,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	c->c7 = 0;
 	c->mc6_us = 0;
 	c->core_temp_c = 0;
+	c->core_energy = 0;
 
 	p->pkg_wtd_core_c0 = 0;
 	p->pkg_any_core_c0 = 0;
@@ -1473,6 +1516,8 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 
 	average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c);
 
+	average.cores.core_energy += c->core_energy;
+
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
 			continue;
@@ -1818,7 +1863,7 @@ retry:
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		goto done;
 
-	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates) {
+	if (DO_BIC(BIC_CPU_c3)) {
 		if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
 			return -6;
 	}
@@ -1845,6 +1890,12 @@ retry:
 		c->core_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F);
 	}
 
+	if (do_rapl & RAPL_AMD_F17H) {
+		if (get_msr(cpu, MSR_CORE_ENERGY_STAT, &msr))
+			return -14;
+		c->core_energy = msr & 0xFFFFFFFF;
+	}
+
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 		if (get_mp(cpu, mp, &c->counter[i]))
 			return -10;
@@ -1934,6 +1985,11 @@ retry:
 			return -16;
 		p->rapl_dram_perf_status = msr & 0xFFFFFFFF;
 	}
+	if (do_rapl & RAPL_AMD_F17H) {
+		if (get_msr(cpu, MSR_PKG_ENERGY_STAT, &msr))
+			return -13;
+		p->energy_pkg = msr & 0xFFFFFFFF;
+	}
 	if (DO_BIC(BIC_PkgTmp)) {
 		if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
 			return -17;
@@ -2456,6 +2512,8 @@ void free_all_buffers(void)
 
 /*
  * Parse a file containing a single int.
+ * Return 0 if file can not be opened
+ * Exit if file can be opened, but can not be parsed
  */
 int parse_int_file(const char *fmt, ...)
 {
@@ -2467,7 +2525,9 @@ int parse_int_file(const char *fmt, ...)
 	va_start(args, fmt);
 	vsnprintf(path, sizeof(path), fmt, args);
 	va_end(args);
-	filep = fopen_or_die(path, "r");
+	filep = fopen(path, "r");
+	if (!filep)
+		return 0;
 	if (fscanf(filep, "%d", &value) != 1)
 		err(1, "%s: failed to parse number from file", path);
 	fclose(filep);
@@ -2488,6 +2548,11 @@ int get_physical_package_id(int cpu)
 	return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/physical_package_id", cpu);
 }
 
+int get_die_id(int cpu)
+{
+	return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/die_id", cpu);
+}
+
 int get_core_id(int cpu)
 {
 	return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/core_id", cpu);
@@ -2578,7 +2643,8 @@ int get_thread_siblings(struct cpu_topology *thiscpu)
 	filep = fopen_or_die(path, "r");
 	do {
 		offset -= BITMASK_SIZE;
-		fscanf(filep, "%lx%c", &map, &character);
+		if (fscanf(filep, "%lx%c", &map, &character) != 2)
+			err(1, "%s: failed to parse file", path);
 		for (shift = 0; shift < BITMASK_SIZE; shift++) {
 			if ((map >> shift) & 0x1) {
 				so = shift + offset;
@@ -2855,8 +2921,11 @@ int snapshot_cpu_lpi_us(void)
 	fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", "r");
 
 	retval = fscanf(fp, "%lld", &cpuidle_cur_cpu_lpi_us);
-	if (retval != 1)
-		err(1, "CPU LPI");
+	if (retval != 1) {
+		fprintf(stderr, "Disabling Low Power Idle CPU output\n");
+		BIC_NOT_PRESENT(BIC_CPU_LPI);
+		return -1;
+	}
 
 	fclose(fp);
 
@@ -2878,9 +2947,11 @@ int snapshot_sys_lpi_us(void)
 	fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", "r");
 
 	retval = fscanf(fp, "%lld", &cpuidle_cur_sys_lpi_us);
-	if (retval != 1)
-		err(1, "SYS LPI");
-
+	if (retval != 1) {
+		fprintf(stderr, "Disabling Low Power Idle System output\n");
+		BIC_NOT_PRESENT(BIC_SYS_LPI);
+		return -1;
+	}
 	fclose(fp);
 
 	return 0;
@@ -3410,14 +3481,14 @@ dump_sysfs_cstate_config(void)
 		input = fopen(path, "r");
 		if (input == NULL)
 			continue;
-		fgets(name_buf, sizeof(name_buf), input);
+		if (!fgets(name_buf, sizeof(name_buf), input))
+			err(1, "%s: failed to read file", path);
 
 		 /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
 		sp = strchr(name_buf, '-');
 		if (!sp)
 			sp = strchrnul(name_buf, '\n');
 		*sp = '\0';
-
 		fclose(input);
 
 		sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc",
@@ -3425,7 +3496,8 @@ dump_sysfs_cstate_config(void)
 		input = fopen(path, "r");
 		if (input == NULL)
 			continue;
-		fgets(desc, sizeof(desc), input);
+		if (!fgets(desc, sizeof(desc), input))
+			err(1, "%s: failed to read file", path);
 
 		fprintf(outf, "cpu%d: %s: %s", base_cpu, name_buf, desc);
 		fclose(input);
@@ -3444,20 +3516,22 @@ dump_sysfs_pstate_config(void)
 			base_cpu);
 	input = fopen(path, "r");
 	if (input == NULL) {
-		fprintf(stderr, "NSFOD %s\n", path);
+		fprintf(outf, "NSFOD %s\n", path);
 		return;
 	}
-	fgets(driver_buf, sizeof(driver_buf), input);
+	if (!fgets(driver_buf, sizeof(driver_buf), input))
+		err(1, "%s: failed to read file", path);
 	fclose(input);
 
 	sprintf(path, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_governor",
 			base_cpu);
 	input = fopen(path, "r");
 	if (input == NULL) {
-		fprintf(stderr, "NSFOD %s\n", path);
+		fprintf(outf, "NSFOD %s\n", path);
 		return;
 	}
-	fgets(governor_buf, sizeof(governor_buf), input);
+	if (!fgets(governor_buf, sizeof(governor_buf), input))
+		err(1, "%s: failed to read file", path);
 	fclose(input);
 
 	fprintf(outf, "cpu%d: cpufreq driver: %s", base_cpu, driver_buf);
@@ -3466,7 +3540,8 @@ dump_sysfs_pstate_config(void)
 	sprintf(path, "/sys/devices/system/cpu/cpufreq/boost");
 	input = fopen(path, "r");
 	if (input != NULL) {
-		fscanf(input, "%d", &turbo);
+		if (fscanf(input, "%d", &turbo) != 1)
+			err(1, "%s: failed to parse number from file", path);
 		fprintf(outf, "cpufreq boost: %d\n", turbo);
 		fclose(input);
 	}
@@ -3474,7 +3549,8 @@ dump_sysfs_pstate_config(void)
 	sprintf(path, "/sys/devices/system/cpu/intel_pstate/no_turbo");
 	input = fopen(path, "r");
 	if (input != NULL) {
-		fscanf(input, "%d", &turbo);
+		if (fscanf(input, "%d", &turbo) != 1)
+			err(1, "%s: failed to parse number from file", path);
 		fprintf(outf, "cpufreq intel_pstate no_turbo: %d\n", turbo);
 		fclose(input);
 	}
@@ -3718,7 +3794,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 #define	RAPL_POWER_GRANULARITY	0x7FFF	/* 15 bit power granularity */
 #define	RAPL_TIME_GRANULARITY	0x3F /* 6 bit time granularity */
 
-double get_tdp(unsigned int model)
+double get_tdp_intel(unsigned int model)
 {
 	unsigned long long msr;
 
@@ -3735,6 +3811,16 @@ double get_tdp(unsigned int model)
 	}
 }
 
+double get_tdp_amd(unsigned int family)
+{
+	switch (family) {
+	case 0x17:
+	default:
+		/* This is the max stock TDP of HEDT/Server Fam17h chips */
+		return 250.0;
+	}
+}
+
 /*
  * rapl_dram_energy_units_probe()
  * Energy units are either hard-coded, or come from RAPL Energy Unit MSR.
@@ -3754,21 +3840,12 @@ rapl_dram_energy_units_probe(int  model, double rapl_energy_units)
 	}
 }
 
-
-/*
- * rapl_probe()
- *
- * sets do_rapl, rapl_power_units, rapl_energy_units, rapl_time_units
- */
-void rapl_probe(unsigned int family, unsigned int model)
+void rapl_probe_intel(unsigned int family, unsigned int model)
 {
 	unsigned long long msr;
 	unsigned int time_unit;
 	double tdp;
 
-	if (!genuine_intel)
-		return;
-
 	if (family != 6)
 		return;
 
@@ -3892,13 +3969,69 @@ void rapl_probe(unsigned int family, unsigned int model)
 
 	rapl_time_units = 1.0 / (1 << (time_unit));
 
-	tdp = get_tdp(model);
+	tdp = get_tdp_intel(model);
 
 	rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
 	if (!quiet)
 		fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
+}
 
-	return;
+void rapl_probe_amd(unsigned int family, unsigned int model)
+{
+	unsigned long long msr;
+	unsigned int eax, ebx, ecx, edx;
+	unsigned int has_rapl = 0;
+	double tdp;
+
+	if (max_extended_level >= 0x80000007) {
+		__cpuid(0x80000007, eax, ebx, ecx, edx);
+		/* RAPL (Fam 17h) */
+		has_rapl = edx & (1 << 14);
+	}
+
+	if (!has_rapl)
+		return;
+
+	switch (family) {
+	case 0x17: /* Zen, Zen+ */
+		do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY;
+		if (rapl_joules) {
+			BIC_PRESENT(BIC_Pkg_J);
+			BIC_PRESENT(BIC_Cor_J);
+		} else {
+			BIC_PRESENT(BIC_PkgWatt);
+			BIC_PRESENT(BIC_CorWatt);
+		}
+		break;
+	default:
+		return;
+	}
+
+	if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr))
+		return;
+
+	rapl_time_units = ldexp(1.0, -(msr >> 16 & 0xf));
+	rapl_energy_units = ldexp(1.0, -(msr >> 8 & 0x1f));
+	rapl_power_units = ldexp(1.0, -(msr & 0xf));
+
+	tdp = get_tdp_amd(model);
+
+	rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
+	if (!quiet)
+		fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
+}
+
+/*
+ * rapl_probe()
+ *
+ * sets do_rapl, rapl_power_units, rapl_energy_units, rapl_time_units
+ */
+void rapl_probe(unsigned int family, unsigned int model)
+{
+	if (genuine_intel)
+		rapl_probe_intel(family, model);
+	if (authentic_amd)
+		rapl_probe_amd(family, model);
 }
 
 void perf_limit_reasons_probe(unsigned int family, unsigned int model)
@@ -4003,6 +4136,7 @@ void print_power_limit_msr(int cpu, unsigned long long msr, char *label)
 int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 {
 	unsigned long long msr;
+	const char *msr_name;
 	int cpu;
 
 	if (!do_rapl)
@@ -4018,10 +4152,17 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		return -1;
 	}
 
-	if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr))
-		return -1;
+	if (do_rapl & RAPL_AMD_F17H) {
+		msr_name = "MSR_RAPL_PWR_UNIT";
+		if (get_msr(cpu, MSR_RAPL_PWR_UNIT, &msr))
+			return -1;
+	} else {
+		msr_name = "MSR_RAPL_POWER_UNIT";
+		if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr))
+			return -1;
+	}
 
-	fprintf(outf, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr,
+	fprintf(outf, "cpu%d: %s: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr_name, msr,
 		rapl_power_units, rapl_energy_units, rapl_time_units);
 
 	if (do_rapl & RAPL_PKG_POWER_INFO) {
@@ -4451,6 +4592,9 @@ unsigned int intel_model_duplicates(unsigned int model)
 	case INTEL_FAM6_KABYLAKE_MOBILE:
 	case INTEL_FAM6_KABYLAKE_DESKTOP:
 		return INTEL_FAM6_SKYLAKE_MOBILE;
+
+	case INTEL_FAM6_ICELAKE_MOBILE:
+		return INTEL_FAM6_CANNONLAKE_MOBILE;
 	}
 	return model;
 }
@@ -4702,7 +4846,9 @@ void process_cpuid()
 	}
 	do_slm_cstates = is_slm(family, model);
 	do_knl_cstates  = is_knl(family, model);
-	do_cnl_cstates = is_cnl(family, model);
+
+	if (do_slm_cstates || do_knl_cstates || is_cnl(family, model))
+		BIC_NOT_PRESENT(BIC_CPU_c3);
 
 	if (!quiet)
 		decode_misc_pwr_mgmt_msr();
@@ -4769,6 +4915,7 @@ void topology_probe()
 	int i;
 	int max_core_id = 0;
 	int max_package_id = 0;
+	int max_die_id = 0;
 	int max_siblings = 0;
 
 	/* Initialize num_cpus, max_cpu_num */
@@ -4835,6 +4982,11 @@ void topology_probe()
 		if (cpus[i].physical_package_id > max_package_id)
 			max_package_id = cpus[i].physical_package_id;
 
+		/* get die information */
+		cpus[i].die_id = get_die_id(i);
+		if (cpus[i].die_id > max_die_id)
+			max_die_id = cpus[i].die_id;
+
 		/* get numa node information */
 		cpus[i].physical_node_id = get_physical_node_id(&cpus[i]);
 		if (cpus[i].physical_node_id > topo.max_node_num)
@@ -4860,6 +5012,13 @@ void topology_probe()
 	if (!summary_only && topo.cores_per_node > 1)
 		BIC_PRESENT(BIC_Core);
 
+	topo.num_die = max_die_id + 1;
+	if (debug > 1)
+		fprintf(outf, "max_die_id %d, sizing for %d die\n",
+				max_die_id, topo.num_die);
+	if (!summary_only && topo.num_die > 1)
+		BIC_PRESENT(BIC_Die);
+
 	topo.num_packages = max_package_id + 1;
 	if (debug > 1)
 		fprintf(outf, "max_package_id %d, sizing for %d packages\n",
@@ -4884,8 +5043,8 @@ void topology_probe()
 		if (cpu_is_not_present(i))
 			continue;
 		fprintf(outf,
-			"cpu %d pkg %d node %d lnode %d core %d thread %d\n",
-			i, cpus[i].physical_package_id,
+			"cpu %d pkg %d die %d node %d lnode %d core %d thread %d\n",
+			i, cpus[i].physical_package_id, cpus[i].die_id,
 			cpus[i].physical_node_id,
 			cpus[i].logical_node_id,
 			cpus[i].physical_core_id,
@@ -5122,7 +5281,7 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-	fprintf(outf, "turbostat version 18.07.27"
+	fprintf(outf, "turbostat version 19.03.20"
 		" - Len Brown <lenb@kernel.org>\n");
 }
 
@@ -5319,7 +5478,8 @@ void probe_sysfs(void)
 		input = fopen(path, "r");
 		if (input == NULL)
 			continue;
-		fgets(name_buf, sizeof(name_buf), input);
+		if (!fgets(name_buf, sizeof(name_buf), input))
+			err(1, "%s: failed to read file", path);
 
 		 /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
 		sp = strchr(name_buf, '-');
@@ -5346,7 +5506,8 @@ void probe_sysfs(void)
 		input = fopen(path, "r");
 		if (input == NULL)
 			continue;
-		fgets(name_buf, sizeof(name_buf), input);
+		if (!fgets(name_buf, sizeof(name_buf), input))
+			err(1, "%s: failed to read file", path);
 		 /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
 		sp = strchr(name_buf, '-');
 		if (!sp)
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index bcbd928c96ab..fc818bc1d729 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -39,6 +39,58 @@ static struct bpf_flow_keys pkt_v6_flow_keys = {
 	.n_proto = __bpf_constant_htons(ETH_P_IPV6),
 };
 
+#define VLAN_HLEN	4
+
+static struct {
+	struct ethhdr eth;
+	__u16 vlan_tci;
+	__u16 vlan_proto;
+	struct iphdr iph;
+	struct tcphdr tcp;
+} __packed pkt_vlan_v4 = {
+	.eth.h_proto = __bpf_constant_htons(ETH_P_8021Q),
+	.vlan_proto = __bpf_constant_htons(ETH_P_IP),
+	.iph.ihl = 5,
+	.iph.protocol = IPPROTO_TCP,
+	.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+	.tcp.urg_ptr = 123,
+	.tcp.doff = 5,
+};
+
+static struct bpf_flow_keys pkt_vlan_v4_flow_keys = {
+	.nhoff = VLAN_HLEN,
+	.thoff = VLAN_HLEN + sizeof(struct iphdr),
+	.addr_proto = ETH_P_IP,
+	.ip_proto = IPPROTO_TCP,
+	.n_proto = __bpf_constant_htons(ETH_P_IP),
+};
+
+static struct {
+	struct ethhdr eth;
+	__u16 vlan_tci;
+	__u16 vlan_proto;
+	__u16 vlan_tci2;
+	__u16 vlan_proto2;
+	struct ipv6hdr iph;
+	struct tcphdr tcp;
+} __packed pkt_vlan_v6 = {
+	.eth.h_proto = __bpf_constant_htons(ETH_P_8021AD),
+	.vlan_proto = __bpf_constant_htons(ETH_P_8021Q),
+	.vlan_proto2 = __bpf_constant_htons(ETH_P_IPV6),
+	.iph.nexthdr = IPPROTO_TCP,
+	.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+	.tcp.urg_ptr = 123,
+	.tcp.doff = 5,
+};
+
+static struct bpf_flow_keys pkt_vlan_v6_flow_keys = {
+	.nhoff = VLAN_HLEN * 2,
+	.thoff = VLAN_HLEN * 2 + sizeof(struct ipv6hdr),
+	.addr_proto = ETH_P_IPV6,
+	.ip_proto = IPPROTO_TCP,
+	.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+};
+
 void test_flow_dissector(void)
 {
 	struct bpf_flow_keys flow_keys;
@@ -68,5 +120,21 @@ void test_flow_dissector(void)
 	      err, errno, retval, duration, size, sizeof(flow_keys));
 	CHECK_FLOW_KEYS("ipv6_flow_keys", flow_keys, pkt_v6_flow_keys);
 
+	err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v4, sizeof(pkt_vlan_v4),
+				&flow_keys, &size, &retval, &duration);
+	CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv4",
+	      "err %d errno %d retval %d duration %d size %u/%lu\n",
+	      err, errno, retval, duration, size, sizeof(flow_keys));
+	CHECK_FLOW_KEYS("vlan_ipv4_flow_keys", flow_keys,
+			pkt_vlan_v4_flow_keys);
+
+	err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v6, sizeof(pkt_vlan_v6),
+				&flow_keys, &size, &retval, &duration);
+	CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv6",
+	      "err %d errno %d retval %d duration %d size %u/%lu\n",
+	      err, errno, retval, duration, size, sizeof(flow_keys));
+	CHECK_FLOW_KEYS("vlan_ipv6_flow_keys", flow_keys,
+			pkt_vlan_v6_flow_keys);
+
 	bpf_object__close(obj);
 }
diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c
index 284660f5aa95..75b17cada539 100644
--- a/tools/testing/selftests/bpf/progs/bpf_flow.c
+++ b/tools/testing/selftests/bpf/progs/bpf_flow.c
@@ -92,7 +92,6 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
 {
 	struct bpf_flow_keys *keys = skb->flow_keys;
 
-	keys->n_proto = proto;
 	switch (proto) {
 	case bpf_htons(ETH_P_IP):
 		bpf_tail_call(skb, &jmp_table, IP);
@@ -119,10 +118,9 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
 SEC("flow_dissector")
 int _dissect(struct __sk_buff *skb)
 {
-	if (!skb->vlan_present)
-		return parse_eth_proto(skb, skb->protocol);
-	else
-		return parse_eth_proto(skb, skb->vlan_proto);
+	struct bpf_flow_keys *keys = skb->flow_keys;
+
+	return parse_eth_proto(skb, keys->n_proto);
 }
 
 /* Parses on IPPROTO_* */
@@ -336,15 +334,9 @@ PROG(VLAN)(struct __sk_buff *skb)
 {
 	struct bpf_flow_keys *keys = skb->flow_keys;
 	struct vlan_hdr *vlan, _vlan;
-	__be16 proto;
-
-	/* Peek back to see if single or double-tagging */
-	if (bpf_skb_load_bytes(skb, keys->thoff - sizeof(proto), &proto,
-			       sizeof(proto)))
-		return BPF_DROP;
 
 	/* Account for double-tagging */
-	if (proto == bpf_htons(ETH_P_8021AD)) {
+	if (keys->n_proto == bpf_htons(ETH_P_8021AD)) {
 		vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan);
 		if (!vlan)
 			return BPF_DROP;
@@ -352,6 +344,7 @@ PROG(VLAN)(struct __sk_buff *skb)
 		if (vlan->h_vlan_encapsulated_proto != bpf_htons(ETH_P_8021Q))
 			return BPF_DROP;
 
+		keys->nhoff += sizeof(*vlan);
 		keys->thoff += sizeof(*vlan);
 	}
 
@@ -359,12 +352,14 @@ PROG(VLAN)(struct __sk_buff *skb)
 	if (!vlan)
 		return BPF_DROP;
 
+	keys->nhoff += sizeof(*vlan);
 	keys->thoff += sizeof(*vlan);
 	/* Only allow 8021AD + 8021Q double tagging and no triple tagging.*/
 	if (vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021AD) ||
 	    vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021Q))
 		return BPF_DROP;
 
+	keys->n_proto = vlan->h_vlan_encapsulated_proto;
 	return parse_eth_proto(skb, vlan->h_vlan_encapsulated_proto);
 }
 
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 23e3b314ca60..ec5794e4205b 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -5777,6 +5777,53 @@ const struct btf_dedup_test dedup_tests[] = {
 	},
 },
 {
+	.descr = "dedup: void equiv check",
+	/*
+	 * // CU 1:
+	 * struct s {
+	 *	struct {} *x;
+	 * };
+	 * // CU 2:
+	 * struct s {
+	 *	int *x;
+	 * };
+	 */
+	.input = {
+		.raw_types = {
+			/* CU 1 */
+			BTF_STRUCT_ENC(0, 0, 1),				/* [1] struct {}  */
+			BTF_PTR_ENC(1),						/* [2] ptr -> [1] */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 8),			/* [3] struct s   */
+				BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+			/* CU 2 */
+			BTF_PTR_ENC(0),						/* [4] ptr -> void */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 8),			/* [5] struct s   */
+				BTF_MEMBER_ENC(NAME_NTH(2), 4, 0),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0s\0x"),
+	},
+	.expect = {
+		.raw_types = {
+			/* CU 1 */
+			BTF_STRUCT_ENC(0, 0, 1),				/* [1] struct {}  */
+			BTF_PTR_ENC(1),						/* [2] ptr -> [1] */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 8),			/* [3] struct s   */
+				BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+			/* CU 2 */
+			BTF_PTR_ENC(0),						/* [4] ptr -> void */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 8),			/* [5] struct s   */
+				BTF_MEMBER_ENC(NAME_NTH(2), 4, 0),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0s\0x"),
+	},
+	.opts = {
+		.dont_resolve_fwds = false,
+		.dedup_table_size = 1, /* force hash collisions */
+	},
+},
+{
 	.descr = "dedup: all possible kinds (no duplicates)",
 	.input = {
 		.raw_types = {
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index f2ccae39ee66..fb11240b758b 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -908,6 +908,44 @@
 	.result = REJECT,
 },
 {
+	"calls: stack depth check in dead code",
+	.insns = {
+	/* main */
+	BPF_MOV64_IMM(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call A */
+	BPF_EXIT_INSN(),
+	/* A */
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 2), /* call B */
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	/* B */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call C */
+	BPF_EXIT_INSN(),
+	/* C */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call D */
+	BPF_EXIT_INSN(),
+	/* D */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call E */
+	BPF_EXIT_INSN(),
+	/* E */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call F */
+	BPF_EXIT_INSN(),
+	/* F */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call G */
+	BPF_EXIT_INSN(),
+	/* G */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call H */
+	BPF_EXIT_INSN(),
+	/* H */
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.errstr = "call stack",
+	.result = REJECT,
+},
+{
 	"calls: spill into caller stack frame",
 	.insns = {
 	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 3c1f4bdf9000..7514fcea91a7 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -29,8 +29,8 @@ LIBKVM += $(LIBKVM_$(UNAME_M))
 INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
 LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include
-CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
-LDFLAGS += -pthread
+CFLAGS += -O2 -g -std=gnu99 -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
+LDFLAGS += -pthread -no-pie
 
 # After inclusion, $(OUTPUT) is defined and
 # $(TEST_GEN_PROGS) starts with $(OUTPUT)/
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index a84785b02557..07b71ad9734a 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -102,6 +102,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva);
 struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
 int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
 		       struct kvm_mp_state *mp_state);
 void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index b52cfdefecbf..efa0aad8b3c6 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1121,6 +1121,22 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
 	return rc;
 }
 
+void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	int ret;
+
+	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+	vcpu->state->immediate_exit = 1;
+	ret = ioctl(vcpu->fd, KVM_RUN, NULL);
+	vcpu->state->immediate_exit = 0;
+
+	TEST_ASSERT(ret == -1 && errno == EINTR,
+		    "KVM_RUN IOCTL didn't exit immediately, rc: %i, errno: %i",
+		    ret, errno);
+}
+
 /*
  * VM VCPU Set MP State
  *
diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
index d503a51fad30..7c2c4d4055a8 100644
--- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
+++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
@@ -87,22 +87,25 @@ int main(int argc, char *argv[])
 	while (1) {
 		rc = _vcpu_run(vm, VCPU_ID);
 
-		if (run->exit_reason == KVM_EXIT_IO) {
-			switch (get_ucall(vm, VCPU_ID, &uc)) {
-			case UCALL_SYNC:
-				/* emulate hypervisor clearing CR4.OSXSAVE */
-				vcpu_sregs_get(vm, VCPU_ID, &sregs);
-				sregs.cr4 &= ~X86_CR4_OSXSAVE;
-				vcpu_sregs_set(vm, VCPU_ID, &sregs);
-				break;
-			case UCALL_ABORT:
-				TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
-				break;
-			case UCALL_DONE:
-				goto done;
-			default:
-				TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
-			}
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Unexpected exit reason: %u (%s),\n",
+			    run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_SYNC:
+			/* emulate hypervisor clearing CR4.OSXSAVE */
+			vcpu_sregs_get(vm, VCPU_ID, &sregs);
+			sregs.cr4 &= ~X86_CR4_OSXSAVE;
+			vcpu_sregs_set(vm, VCPU_ID, &sregs);
+			break;
+		case UCALL_ABORT:
+			TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
+			break;
+		case UCALL_DONE:
+			goto done;
+		default:
+			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
 		}
 	}
 
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
index 4b3f556265f1..30f75856cf39 100644
--- a/tools/testing/selftests/kvm/x86_64/state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/state_test.c
@@ -134,6 +134,11 @@ int main(int argc, char *argv[])
 
 	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
 
+	if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) {
+		fprintf(stderr, "immediate_exit not available, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+
 	/* Create VM */
 	vm = vm_create_default(VCPU_ID, 0, guest_code);
 	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
@@ -156,8 +161,6 @@ int main(int argc, char *argv[])
 			    stage, run->exit_reason,
 			    exit_reason_str(run->exit_reason));
 
-		memset(&regs1, 0, sizeof(regs1));
-		vcpu_regs_get(vm, VCPU_ID, &regs1);
 		switch (get_ucall(vm, VCPU_ID, &uc)) {
 		case UCALL_ABORT:
 			TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
@@ -176,6 +179,17 @@ int main(int argc, char *argv[])
 			    uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
 			    stage, (ulong)uc.args[1]);
 
+		/*
+		 * When KVM exits to userspace with KVM_EXIT_IO, KVM guarantees
+		 * guest state is consistent only after userspace re-enters the
+		 * kernel with KVM_RUN.  Complete IO prior to migrating state
+		 * to a new VM.
+		 */
+		vcpu_run_complete_io(vm, VCPU_ID);
+
+		memset(&regs1, 0, sizeof(regs1));
+		vcpu_regs_get(vm, VCPU_ID, &regs1);
+
 		state = vcpu_save_state(vm, VCPU_ID);
 		kvm_vm_release(vm);
 
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
index 27f0acaed880..ddabb160a11b 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
@@ -144,6 +144,30 @@
         ]
     },
     {
+        "id": "7571",
+        "name": "Add sample action with invalid rate",
+        "category": [
+            "actions",
+            "sample"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action sample",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action sample rate 0 group 1 index 2",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action sample index 2",
+        "matchPattern": "action order [0-9]+: sample rate 1/0 group 1.*index 2 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action sample"
+        ]
+    },
+    {
         "id": "b6d4",
         "name": "Add sample action with mandatory arguments and invalid control action",
         "category": [