diff --git a/tools/arch/s390/include/uapi/asm/ptrace.h b/tools/arch/s390/include/uapi/asm/ptrace.h
index 543dd70e12c8..ad64d673b5e6 100644
--- a/tools/arch/s390/include/uapi/asm/ptrace.h
+++ b/tools/arch/s390/include/uapi/asm/ptrace.h
@@ -179,8 +179,9 @@
 #define ACR_SIZE	4
 
 
-#define PTRACE_OLDSETOPTIONS	     21
-
+#define PTRACE_OLDSETOPTIONS		21
+#define PTRACE_SYSEMU			31
+#define PTRACE_SYSEMU_SINGLESTEP	32
 #ifndef __ASSEMBLY__
 #include <linux/stddef.h>
 #include <linux/types.h>
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 84b887825f12..cc96e26d69f7 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -13,7 +13,7 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS			19	   /* N 32-bit words worth of info */
+#define NCAPINTS			20	   /* N 32-bit words worth of info */
 #define NBUGINTS			1	   /* N 32-bit bug flags */
 
 /*
@@ -96,7 +96,7 @@
 #define X86_FEATURE_SYSCALL32		( 3*32+14) /* "" syscall in IA32 userspace */
 #define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in IA32 userspace */
 #define X86_FEATURE_REP_GOOD		( 3*32+16) /* REP microcode works well */
-#define X86_FEATURE_SME_COHERENT	( 3*32+17) /* "" AMD hardware-enforced cache coherency */
+/* FREE!                                ( 3*32+17) */
 #define X86_FEATURE_LFENCE_RDTSC	( 3*32+18) /* "" LFENCE synchronizes RDTSC */
 #define X86_FEATURE_ACC_POWER		( 3*32+19) /* AMD Accumulated Power Mechanism */
 #define X86_FEATURE_NOPL		( 3*32+20) /* The NOPL (0F 1F) instructions */
@@ -201,7 +201,7 @@
 #define X86_FEATURE_INVPCID_SINGLE	( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
-#define X86_FEATURE_SME			( 7*32+10) /* AMD Secure Memory Encryption */
+/* FREE!                                ( 7*32+10) */
 #define X86_FEATURE_PTI			( 7*32+11) /* Kernel Page Table Isolation enabled */
 #define X86_FEATURE_RETPOLINE		( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
 #define X86_FEATURE_RETPOLINE_AMD	( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
@@ -211,7 +211,7 @@
 #define X86_FEATURE_SSBD		( 7*32+17) /* Speculative Store Bypass Disable */
 #define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
 #define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* "" Fill RSB on context switches */
-#define X86_FEATURE_SEV			( 7*32+20) /* AMD Secure Encrypted Virtualization */
+/* FREE!                                ( 7*32+20) */
 #define X86_FEATURE_USE_IBPB		( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
 #define X86_FEATURE_USE_IBRS_FW		( 7*32+22) /* "" Use IBRS during runtime firmware calls */
 #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE	( 7*32+23) /* "" Disable Speculative Store Bypass. */
@@ -236,8 +236,6 @@
 #define X86_FEATURE_EPT_AD		( 8*32+17) /* Intel Extended Page Table access-dirty bit */
 #define X86_FEATURE_VMCALL		( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
 #define X86_FEATURE_VMW_VMMCALL		( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
-#define X86_FEATURE_SEV_ES		( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */
-#define X86_FEATURE_VM_PAGE_FLUSH	( 8*32+21) /* "" VM Page Flush MSR is supported */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
@@ -294,6 +292,7 @@
 #define X86_FEATURE_PER_THREAD_MBA	(11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
+#define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
@@ -337,6 +336,7 @@
 #define X86_FEATURE_AVIC		(15*32+13) /* Virtual Interrupt Controller */
 #define X86_FEATURE_V_VMSAVE_VMLOAD	(15*32+15) /* Virtual VMSAVE VMLOAD */
 #define X86_FEATURE_VGIF		(15*32+16) /* Virtual GIF */
+#define X86_FEATURE_SVME_ADDR_CHK	(15*32+28) /* "" SVME addr check */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
 #define X86_FEATURE_AVX512VBMI		(16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
@@ -385,6 +385,13 @@
 #define X86_FEATURE_CORE_CAPABILITIES	(18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */
 #define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 
+/* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */
+#define X86_FEATURE_SME			(19*32+ 0) /* AMD Secure Memory Encryption */
+#define X86_FEATURE_SEV			(19*32+ 1) /* AMD Secure Encrypted Virtualization */
+#define X86_FEATURE_VM_PAGE_FLUSH	(19*32+ 2) /* "" VM Page Flush MSR is supported */
+#define X86_FEATURE_SEV_ES		(19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */
+#define X86_FEATURE_SME_COHERENT	(19*32+10) /* "" AMD hardware-enforced cache coherency */
+
 /*
  * BUG word(s)
  */
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 8e76d3701db3..5a3022c8af82 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -112,6 +112,7 @@ struct kvm_ioapic_state {
 #define KVM_NR_IRQCHIPS          3
 
 #define KVM_RUN_X86_SMM		 (1 << 0)
+#define KVM_RUN_X86_BUS_LOCK     (1 << 1)
 
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index ada955c5ebb6..b8e650a985e3 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -89,6 +89,7 @@
 #define EXIT_REASON_XRSTORS             64
 #define EXIT_REASON_UMWAIT              67
 #define EXIT_REASON_TPAUSE              68
+#define EXIT_REASON_BUS_LOCK            74
 
 #define VMX_EXIT_REASONS \
 	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
@@ -150,7 +151,8 @@
 	{ EXIT_REASON_XSAVES,                "XSAVES" }, \
 	{ EXIT_REASON_XRSTORS,               "XRSTORS" }, \
 	{ EXIT_REASON_UMWAIT,                "UMWAIT" }, \
-	{ EXIT_REASON_TPAUSE,                "TPAUSE" }
+	{ EXIT_REASON_TPAUSE,                "TPAUSE" }, \
+	{ EXIT_REASON_BUS_LOCK,              "BUS_LOCK" }
 
 #define VMX_EXIT_REASON_FLAGS \
 	{ VMX_EXIT_REASONS_FAILED_VMENTRY,	"FAILED_VMENTRY" }
diff --git a/tools/build/Makefile b/tools/build/Makefile
index bae48e6fa995..5ed41b96fcde 100644
--- a/tools/build/Makefile
+++ b/tools/build/Makefile
@@ -30,12 +30,18 @@ build     := -f $(srctree)/tools/build/Makefile.build dir=. obj
 
 all: $(OUTPUT)fixdep
 
+# Make sure there's anything to clean,
+# feature contains check for existing OUTPUT
+TMP_O := $(if $(OUTPUT),$(OUTPUT)/feature,./)
+
 clean:
 	$(call QUIET_CLEAN, fixdep)
 	$(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
 	$(Q)rm -f $(OUTPUT)fixdep
 	$(call QUIET_CLEAN, feature-detect)
-	$(Q)$(MAKE) -C feature/ clean >/dev/null
+ifneq ($(wildcard $(TMP_O)),)
+	$(Q)$(MAKE) -C feature OUTPUT=$(TMP_O) clean >/dev/null
+endif
 
 $(OUTPUT)fixdep-in.o: FORCE
 	$(Q)$(MAKE) $(build)=fixdep
diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h
index b0e35eec6499..4ac5c081af93 100644
--- a/tools/include/linux/coresight-pmu.h
+++ b/tools/include/linux/coresight-pmu.h
@@ -10,17 +10,27 @@
 #define CORESIGHT_ETM_PMU_NAME "cs_etm"
 #define CORESIGHT_ETM_PMU_SEED  0x10
 
-/* ETMv3.5/PTM's ETMCR config bit */
-#define ETM_OPT_CYCACC  12
-#define ETM_OPT_CTXTID	14
-#define ETM_OPT_TS      28
-#define ETM_OPT_RETSTK	29
+/*
+ * Below are the definition of bit offsets for perf option, and works as
+ * arbitrary values for all ETM versions.
+ *
+ * Most of them are orignally from ETMv3.5/PTM's ETMCR config, therefore,
+ * ETMv3.5/PTM doesn't define ETMCR config bits with prefix "ETM3_" and
+ * directly use below macros as config bits.
+ */
+#define ETM_OPT_CYCACC		12
+#define ETM_OPT_CTXTID		14
+#define ETM_OPT_CTXTID2		15
+#define ETM_OPT_TS		28
+#define ETM_OPT_RETSTK		29
 
 /* ETMv4 CONFIGR programming bits for the ETM OPTs */
 #define ETM4_CFG_BIT_CYCACC	4
 #define ETM4_CFG_BIT_CTXTID	6
+#define ETM4_CFG_BIT_VMID	7
 #define ETM4_CFG_BIT_TS		11
 #define ETM4_CFG_BIT_RETSTK	12
+#define ETM4_CFG_BIT_VMID_OPT	15
 
 static inline int coresight_get_trace_id(int cpu)
 {
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 808b48a93330..0827037c5484 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -1,11 +1,10 @@
-/**
- * \file drm.h
+/*
  * Header for the Direct Rendering Manager
  *
- * \author Rickard E. (Rik) Faith <faith@valinux.com>
+ * Author: Rickard E. (Rik) Faith <faith@valinux.com>
  *
- * \par Acknowledgments:
- * Dec 1999, Richard Henderson <rth@twiddle.net>, move to generic \c cmpxchg.
+ * Acknowledgments:
+ * Dec 1999, Richard Henderson <rth@twiddle.net>, move to generic cmpxchg.
  */
 
 /*
@@ -85,7 +84,7 @@ typedef unsigned int drm_context_t;
 typedef unsigned int drm_drawable_t;
 typedef unsigned int drm_magic_t;
 
-/**
+/*
  * Cliprect.
  *
  * \warning: If you change this structure, make sure you change
@@ -101,7 +100,7 @@ struct drm_clip_rect {
 	unsigned short y2;
 };
 
-/**
+/*
  * Drawable information.
  */
 struct drm_drawable_info {
@@ -109,7 +108,7 @@ struct drm_drawable_info {
 	struct drm_clip_rect *rects;
 };
 
-/**
+/*
  * Texture region,
  */
 struct drm_tex_region {
@@ -120,7 +119,7 @@ struct drm_tex_region {
 	unsigned int age;
 };
 
-/**
+/*
  * Hardware lock.
  *
  * The lock structure is a simple cache-line aligned integer.  To avoid
@@ -132,7 +131,7 @@ struct drm_hw_lock {
 	char padding[60];			/**< Pad to cache line */
 };
 
-/**
+/*
  * DRM_IOCTL_VERSION ioctl argument type.
  *
  * \sa drmGetVersion().
@@ -149,7 +148,7 @@ struct drm_version {
 	char __user *desc;	  /**< User-space buffer to hold desc */
 };
 
-/**
+/*
  * DRM_IOCTL_GET_UNIQUE ioctl argument type.
  *
  * \sa drmGetBusid() and drmSetBusId().
@@ -168,7 +167,7 @@ struct drm_block {
 	int unused;
 };
 
-/**
+/*
  * DRM_IOCTL_CONTROL ioctl argument type.
  *
  * \sa drmCtlInstHandler() and drmCtlUninstHandler().
@@ -183,7 +182,7 @@ struct drm_control {
 	int irq;
 };
 
-/**
+/*
  * Type of memory to map.
  */
 enum drm_map_type {
@@ -195,7 +194,7 @@ enum drm_map_type {
 	_DRM_CONSISTENT = 5	  /**< Consistent memory for PCI DMA */
 };
 
-/**
+/*
  * Memory mapping flags.
  */
 enum drm_map_flags {
@@ -214,7 +213,7 @@ struct drm_ctx_priv_map {
 	void *handle;		 /**< Handle of map */
 };
 
-/**
+/*
  * DRM_IOCTL_GET_MAP, DRM_IOCTL_ADD_MAP and DRM_IOCTL_RM_MAP ioctls
  * argument type.
  *
@@ -231,7 +230,7 @@ struct drm_map {
 	/*   Private data */
 };
 
-/**
+/*
  * DRM_IOCTL_GET_CLIENT ioctl argument type.
  */
 struct drm_client {
@@ -263,7 +262,7 @@ enum drm_stat_type {
 	    /* Add to the *END* of the list */
 };
 
-/**
+/*
  * DRM_IOCTL_GET_STATS ioctl argument type.
  */
 struct drm_stats {
@@ -274,7 +273,7 @@ struct drm_stats {
 	} data[15];
 };
 
-/**
+/*
  * Hardware locking flags.
  */
 enum drm_lock_flags {
@@ -289,7 +288,7 @@ enum drm_lock_flags {
 	_DRM_HALT_CUR_QUEUES = 0x20  /**< Halt all current queues */
 };
 
-/**
+/*
  * DRM_IOCTL_LOCK, DRM_IOCTL_UNLOCK and DRM_IOCTL_FINISH ioctl argument type.
  *
  * \sa drmGetLock() and drmUnlock().
@@ -299,7 +298,7 @@ struct drm_lock {
 	enum drm_lock_flags flags;
 };
 
-/**
+/*
  * DMA flags
  *
  * \warning
@@ -328,7 +327,7 @@ enum drm_dma_flags {
 	_DRM_DMA_LARGER_OK = 0x40     /**< Larger-than-requested buffers OK */
 };
 
-/**
+/*
  * DRM_IOCTL_ADD_BUFS and DRM_IOCTL_MARK_BUFS ioctl argument type.
  *
  * \sa drmAddBufs().
@@ -351,7 +350,7 @@ struct drm_buf_desc {
 				  */
 };
 
-/**
+/*
  * DRM_IOCTL_INFO_BUFS ioctl argument type.
  */
 struct drm_buf_info {
@@ -359,7 +358,7 @@ struct drm_buf_info {
 	struct drm_buf_desc __user *list;
 };
 
-/**
+/*
  * DRM_IOCTL_FREE_BUFS ioctl argument type.
  */
 struct drm_buf_free {
@@ -367,7 +366,7 @@ struct drm_buf_free {
 	int __user *list;
 };
 
-/**
+/*
  * Buffer information
  *
  * \sa drm_buf_map.
@@ -379,7 +378,7 @@ struct drm_buf_pub {
 	void __user *address;	       /**< Address of buffer */
 };
 
-/**
+/*
  * DRM_IOCTL_MAP_BUFS ioctl argument type.
  */
 struct drm_buf_map {
@@ -392,7 +391,7 @@ struct drm_buf_map {
 	struct drm_buf_pub __user *list;	/**< Buffer information */
 };
 
-/**
+/*
  * DRM_IOCTL_DMA ioctl argument type.
  *
  * Indices here refer to the offset into the buffer list in drm_buf_get.
@@ -417,7 +416,7 @@ enum drm_ctx_flags {
 	_DRM_CONTEXT_2DONLY = 0x02
 };
 
-/**
+/*
  * DRM_IOCTL_ADD_CTX ioctl argument type.
  *
  * \sa drmCreateContext() and drmDestroyContext().
@@ -427,7 +426,7 @@ struct drm_ctx {
 	enum drm_ctx_flags flags;
 };
 
-/**
+/*
  * DRM_IOCTL_RES_CTX ioctl argument type.
  */
 struct drm_ctx_res {
@@ -435,14 +434,14 @@ struct drm_ctx_res {
 	struct drm_ctx __user *contexts;
 };
 
-/**
+/*
  * DRM_IOCTL_ADD_DRAW and DRM_IOCTL_RM_DRAW ioctl argument type.
  */
 struct drm_draw {
 	drm_drawable_t handle;
 };
 
-/**
+/*
  * DRM_IOCTL_UPDATE_DRAW ioctl argument type.
  */
 typedef enum {
@@ -456,14 +455,14 @@ struct drm_update_draw {
 	unsigned long long data;
 };
 
-/**
+/*
  * DRM_IOCTL_GET_MAGIC and DRM_IOCTL_AUTH_MAGIC ioctl argument type.
  */
 struct drm_auth {
 	drm_magic_t magic;
 };
 
-/**
+/*
  * DRM_IOCTL_IRQ_BUSID ioctl argument type.
  *
  * \sa drmGetInterruptFromBusID().
@@ -505,7 +504,7 @@ struct drm_wait_vblank_reply {
 	long tval_usec;
 };
 
-/**
+/*
  * DRM_IOCTL_WAIT_VBLANK ioctl argument type.
  *
  * \sa drmWaitVBlank().
@@ -518,7 +517,7 @@ union drm_wait_vblank {
 #define _DRM_PRE_MODESET 1
 #define _DRM_POST_MODESET 2
 
-/**
+/*
  * DRM_IOCTL_MODESET_CTL ioctl argument type
  *
  * \sa drmModesetCtl().
@@ -528,7 +527,7 @@ struct drm_modeset_ctl {
 	__u32 cmd;
 };
 
-/**
+/*
  * DRM_IOCTL_AGP_ENABLE ioctl argument type.
  *
  * \sa drmAgpEnable().
@@ -537,7 +536,7 @@ struct drm_agp_mode {
 	unsigned long mode;	/**< AGP mode */
 };
 
-/**
+/*
  * DRM_IOCTL_AGP_ALLOC and DRM_IOCTL_AGP_FREE ioctls argument type.
  *
  * \sa drmAgpAlloc() and drmAgpFree().
@@ -549,7 +548,7 @@ struct drm_agp_buffer {
 	unsigned long physical;	/**< Physical used by i810 */
 };
 
-/**
+/*
  * DRM_IOCTL_AGP_BIND and DRM_IOCTL_AGP_UNBIND ioctls argument type.
  *
  * \sa drmAgpBind() and drmAgpUnbind().
@@ -559,7 +558,7 @@ struct drm_agp_binding {
 	unsigned long offset;	/**< In bytes -- will round to page boundary */
 };
 
-/**
+/*
  * DRM_IOCTL_AGP_INFO ioctl argument type.
  *
  * \sa drmAgpVersionMajor(), drmAgpVersionMinor(), drmAgpGetMode(),
@@ -580,7 +579,7 @@ struct drm_agp_info {
 	unsigned short id_device;
 };
 
-/**
+/*
  * DRM_IOCTL_SG_ALLOC ioctl argument type.
  */
 struct drm_scatter_gather {
@@ -588,7 +587,7 @@ struct drm_scatter_gather {
 	unsigned long handle;	/**< Used for mapping / unmapping */
 };
 
-/**
+/*
  * DRM_IOCTL_SET_VERSION ioctl argument type.
  */
 struct drm_set_version {
@@ -598,14 +597,14 @@ struct drm_set_version {
 	int drm_dd_minor;
 };
 
-/** DRM_IOCTL_GEM_CLOSE ioctl argument type */
+/* DRM_IOCTL_GEM_CLOSE ioctl argument type */
 struct drm_gem_close {
 	/** Handle of the object to be closed. */
 	__u32 handle;
 	__u32 pad;
 };
 
-/** DRM_IOCTL_GEM_FLINK ioctl argument type */
+/* DRM_IOCTL_GEM_FLINK ioctl argument type */
 struct drm_gem_flink {
 	/** Handle for the object being named */
 	__u32 handle;
@@ -614,7 +613,7 @@ struct drm_gem_flink {
 	__u32 name;
 };
 
-/** DRM_IOCTL_GEM_OPEN ioctl argument type */
+/* DRM_IOCTL_GEM_OPEN ioctl argument type */
 struct drm_gem_open {
 	/** Name of object being opened */
 	__u32 name;
@@ -652,7 +651,7 @@ struct drm_gem_open {
 #define DRM_CAP_SYNCOBJ		0x13
 #define DRM_CAP_SYNCOBJ_TIMELINE	0x14
 
-/** DRM_IOCTL_GET_CAP ioctl argument type */
+/* DRM_IOCTL_GET_CAP ioctl argument type */
 struct drm_get_cap {
 	__u64 capability;
 	__u64 value;
@@ -678,7 +677,9 @@ struct drm_get_cap {
 /**
  * DRM_CLIENT_CAP_ATOMIC
  *
- * If set to 1, the DRM core will expose atomic properties to userspace
+ * If set to 1, the DRM core will expose atomic properties to userspace. This
+ * implicitly enables &DRM_CLIENT_CAP_UNIVERSAL_PLANES and
+ * &DRM_CLIENT_CAP_ASPECT_RATIO.
  */
 #define DRM_CLIENT_CAP_ATOMIC	3
 
@@ -698,7 +699,7 @@ struct drm_get_cap {
  */
 #define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS	5
 
-/** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
+/* DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;
 	__u64 value;
@@ -950,7 +951,7 @@ extern "C" {
 
 #define DRM_IOCTL_MODE_GETFB2		DRM_IOWR(0xCE, struct drm_mode_fb_cmd2)
 
-/**
+/*
  * Device specific ioctls should only be in their respective headers
  * The device specific ioctl range is from 0x40 to 0x9f.
  * Generic IOCTLS restart at 0xA0.
@@ -961,7 +962,7 @@ extern "C" {
 #define DRM_COMMAND_BASE                0x40
 #define DRM_COMMAND_END			0xA0
 
-/**
+/*
  * Header for events written back to userspace on the drm fd.  The
  * type defines the type of event, the length specifies the total
  * length of the event (including the header), and user_data is
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index fa1f3d62f9a6..1987e2ea79a3 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -177,8 +177,9 @@ enum drm_i915_pmu_engine_sample {
 #define I915_PMU_REQUESTED_FREQUENCY	__I915_PMU_OTHER(1)
 #define I915_PMU_INTERRUPTS		__I915_PMU_OTHER(2)
 #define I915_PMU_RC6_RESIDENCY		__I915_PMU_OTHER(3)
+#define I915_PMU_SOFTWARE_GT_AWAKE_TIME	__I915_PMU_OTHER(4)
 
-#define I915_PMU_LAST I915_PMU_RC6_RESIDENCY
+#define I915_PMU_LAST /* Deprecated - do not use */ I915_PMU_RC6_RESIDENCY
 
 /* Each region is a minimum of 16k, and there are at most 255 of them.
  */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index abb89bbe5635..8b281f722e5b 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -216,6 +216,20 @@ struct kvm_hyperv_exit {
 	} u;
 };
 
+struct kvm_xen_exit {
+#define KVM_EXIT_XEN_HCALL          1
+	__u32 type;
+	union {
+		struct {
+			__u32 longmode;
+			__u32 cpl;
+			__u64 input;
+			__u64 result;
+			__u64 params[6];
+		} hcall;
+	} u;
+};
+
 #define KVM_S390_GET_SKEYS_NONE   1
 #define KVM_S390_SKEYS_MAX        1048576
 
@@ -252,6 +266,8 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_X86_WRMSR        30
 #define KVM_EXIT_DIRTY_RING_FULL  31
 #define KVM_EXIT_AP_RESET_HOLD    32
+#define KVM_EXIT_X86_BUS_LOCK     33
+#define KVM_EXIT_XEN              34
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -428,6 +444,8 @@ struct kvm_run {
 			__u32 index; /* kernel -> user */
 			__u64 data; /* kernel <-> user */
 		} msr;
+		/* KVM_EXIT_XEN */
+		struct kvm_xen_exit xen;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1058,6 +1076,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
 #define KVM_CAP_SYS_HYPERV_CPUID 191
 #define KVM_CAP_DIRTY_LOG_RING 192
+#define KVM_CAP_X86_BUS_LOCK_EXIT 193
 #define KVM_CAP_PPC_DAWR1 194
 
 #ifdef KVM_CAP_IRQ_ROUTING
@@ -1132,6 +1151,10 @@ struct kvm_x86_mce {
 #endif
 
 #ifdef KVM_CAP_XEN_HVM
+#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR	(1 << 0)
+#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL	(1 << 1)
+#define KVM_XEN_HVM_CONFIG_SHARED_INFO		(1 << 2)
+
 struct kvm_xen_hvm_config {
 	__u32 flags;
 	__u32 msr;
@@ -1566,6 +1589,45 @@ struct kvm_pv_cmd {
 /* Available with KVM_CAP_DIRTY_LOG_RING */
 #define KVM_RESET_DIRTY_RINGS		_IO(KVMIO, 0xc7)
 
+/* Per-VM Xen attributes */
+#define KVM_XEN_HVM_GET_ATTR	_IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr)
+#define KVM_XEN_HVM_SET_ATTR	_IOW(KVMIO,  0xc9, struct kvm_xen_hvm_attr)
+
+struct kvm_xen_hvm_attr {
+	__u16 type;
+	__u16 pad[3];
+	union {
+		__u8 long_mode;
+		__u8 vector;
+		struct {
+			__u64 gfn;
+		} shared_info;
+		__u64 pad[8];
+	} u;
+};
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
+#define KVM_XEN_ATTR_TYPE_LONG_MODE		0x0
+#define KVM_XEN_ATTR_TYPE_SHARED_INFO		0x1
+#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR		0x2
+
+/* Per-vCPU Xen attributes */
+#define KVM_XEN_VCPU_GET_ATTR	_IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr)
+#define KVM_XEN_VCPU_SET_ATTR	_IOW(KVMIO,  0xcb, struct kvm_xen_vcpu_attr)
+
+struct kvm_xen_vcpu_attr {
+	__u16 type;
+	__u16 pad[3];
+	union {
+		__u64 gpa;
+		__u64 pad[8];
+	} u;
+};
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO	0x0
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO	0x1
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
@@ -1594,6 +1656,8 @@ enum sev_cmd_id {
 	KVM_SEV_DBG_ENCRYPT,
 	/* Guest certificates commands */
 	KVM_SEV_CERT_EXPORT,
+	/* Attestation report */
+	KVM_SEV_GET_ATTESTATION_REPORT,
 
 	KVM_SEV_NR_MAX,
 };
@@ -1646,6 +1710,12 @@ struct kvm_sev_dbg {
 	__u32 len;
 };
 
+struct kvm_sev_attestation_report {
+	__u8 mnonce[16];
+	__u64 uaddr;
+	__u32 len;
+};
+
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 #define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)
 #define KVM_DEV_ASSIGN_MASK_INTX	(1 << 2)
@@ -1767,4 +1837,7 @@ struct kvm_dirty_gfn {
 	__u64 offset;
 };
 
+#define KVM_BUS_LOCK_DETECTION_OFF             (1 << 0)
+#define KVM_BUS_LOCK_DETECTION_EXIT            (1 << 1)
+
 #endif /* __LINUX_KVM_H */
diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
index dd8306ea336c..e6524ead2b7b 100644
--- a/tools/include/uapi/linux/mount.h
+++ b/tools/include/uapi/linux/mount.h
@@ -1,6 +1,8 @@
 #ifndef _UAPI_LINUX_MOUNT_H
 #define _UAPI_LINUX_MOUNT_H
 
+#include <linux/types.h>
+
 /*
  * These are the fs-independent mount-flags: up to 32 flags are supported
  *
@@ -117,5 +119,19 @@ enum fsconfig_command {
 #define MOUNT_ATTR_NOATIME	0x00000010 /* - Do not update access times. */
 #define MOUNT_ATTR_STRICTATIME	0x00000020 /* - Always perform atime updates */
 #define MOUNT_ATTR_NODIRATIME	0x00000080 /* Do not update directory access times */
+#define MOUNT_ATTR_IDMAP	0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */
+
+/*
+ * mount_setattr()
+ */
+struct mount_attr {
+	__u64 attr_set;
+	__u64 attr_clr;
+	__u64 propagation;
+	__u64 userns_fd;
+};
+
+/* List of all mount_attr versions. */
+#define MOUNT_ATTR_SIZE_VER0	32 /* sizeof first published struct */
 
 #endif /* _UAPI_LINUX_MOUNT_H */
diff --git a/tools/include/uapi/linux/openat2.h b/tools/include/uapi/linux/openat2.h
index 58b1eb711360..a5feb7604948 100644
--- a/tools/include/uapi/linux/openat2.h
+++ b/tools/include/uapi/linux/openat2.h
@@ -35,5 +35,9 @@ struct open_how {
 #define RESOLVE_IN_ROOT		0x10 /* Make all jumps to "/" and ".."
 					be scoped inside the dirfd
 					(similar to chroot(2)). */
+#define RESOLVE_CACHED		0x20 /* Only complete if resolution can be
+					completed through cached lookup. May
+					return -EAGAIN if that's not
+					possible. */
 
 #endif /* _UAPI_LINUX_OPENAT2_H */
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 17465d454a0e..a0aaf385cbb5 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -26,13 +26,10 @@
 
 void perf_evlist__init(struct perf_evlist *evlist)
 {
-	int i;
-
-	for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i)
-		INIT_HLIST_HEAD(&evlist->heads[i]);
 	INIT_LIST_HEAD(&evlist->entries);
 	evlist->nr_entries = 0;
 	fdarray__init(&evlist->pollfd, 64);
+	perf_evlist__reset_id_hash(evlist);
 }
 
 static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
@@ -237,6 +234,14 @@ static void perf_evlist__id_hash(struct perf_evlist *evlist,
 	hlist_add_head(&sid->node, &evlist->heads[hash]);
 }
 
+void perf_evlist__reset_id_hash(struct perf_evlist *evlist)
+{
+	int i;
+
+	for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i)
+		INIT_HLIST_HEAD(&evlist->heads[i]);
+}
+
 void perf_evlist__id_add(struct perf_evlist *evlist,
 			 struct perf_evsel *evsel,
 			 int cpu, int thread, u64 id)
diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h
index 2d0fa02b036f..212c29063ad4 100644
--- a/tools/lib/perf/include/internal/evlist.h
+++ b/tools/lib/perf/include/internal/evlist.h
@@ -124,4 +124,6 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist,
 			   struct perf_evsel *evsel,
 			   int cpu, int thread, int fd);
 
+void perf_evlist__reset_id_hash(struct perf_evlist *evlist);
+
 #endif /* __LIBPERF_INTERNAL_EVLIST_H */
diff --git a/tools/perf/Documentation/perf-evlist.txt b/tools/perf/Documentation/perf-evlist.txt
index c0a66400a960..9af8b8dfb7b6 100644
--- a/tools/perf/Documentation/perf-evlist.txt
+++ b/tools/perf/Documentation/perf-evlist.txt
@@ -29,7 +29,7 @@ OPTIONS
 	Show just the sample frequency used for each event.
 
 -v::
---verbose=::
+--verbose::
 	Show all fields.
 
 -g::
diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt
index 1e91121bac0f..6e82b7cc0bf0 100644
--- a/tools/perf/Documentation/perf-ftrace.txt
+++ b/tools/perf/Documentation/perf-ftrace.txt
@@ -28,8 +28,8 @@ OPTIONS
 	specified: function_graph or function.
 
 -v::
---verbose=::
-        Verbosity level.
+--verbose::
+        Increase the verbosity level.
 
 -F::
 --funcs::
diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt
index f3c620951f6e..c97527df8ecd 100644
--- a/tools/perf/Documentation/perf-kallsyms.txt
+++ b/tools/perf/Documentation/perf-kallsyms.txt
@@ -20,5 +20,5 @@ modules).
 OPTIONS
 -------
 -v::
---verbose=::
+--verbose::
 	Increase verbosity level, showing details about symbol table loading, etc.
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index abc9b5d83312..f0da8cf63e9a 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -97,8 +97,8 @@ filter out the startup phase of the program, which is often very different.
 	Filter out events for these pids and for 'trace' itself (comma separated list).
 
 -v::
---verbose=::
-        Verbosity level.
+--verbose::
+        Increase the verbosity level.
 
 --no-inherit::
 	Child tasks do not inherit counters.
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 5345ac70cd83..f6e609673de2 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -607,7 +607,7 @@ arch_errno_hdr_dir := $(srctree)/tools
 arch_errno_tbl := $(srctree)/tools/perf/trace/beauty/arch_errno_names.sh
 
 $(arch_errno_name_array): $(arch_errno_tbl)
-	$(Q)$(SHELL) '$(arch_errno_tbl)' $(firstword $(CC)) $(arch_errno_hdr_dir) > $@
+	$(Q)$(SHELL) '$(arch_errno_tbl)' '$(patsubst -%,,$(CC))' $(arch_errno_hdr_dir) > $@
 
 sync_file_range_arrays := $(beauty_outdir)/sync_file_range_arrays.c
 sync_file_range_tbls := $(srctree)/tools/perf/trace/beauty/sync_file_range.sh
@@ -1001,14 +1001,6 @@ $(INSTALL_DOC_TARGETS):
 
 ### Cleaning rules
 
-#
-# This is here, not in Makefile.config, because Makefile.config does
-# not get included for the clean target:
-#
-config-clean:
-	$(call QUIET_CLEAN, config)
-	$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null
-
 python-clean:
 	$(python-clean)
 
@@ -1048,7 +1040,7 @@ endif # BUILD_BPF_SKEL
 bpf-skel-clean:
 	$(call QUIET_CLEAN, bpf-skel) $(RM) -r $(SKEL_TMP_OUT) $(SKELETONS)
 
-clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBPERF)-clean config-clean fixdep-clean python-clean bpf-skel-clean
+clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBPERF)-clean fixdep-clean python-clean bpf-skel-clean
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIBPERF_A) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
 	$(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
 	$(Q)$(RM) $(OUTPUT).config-detected
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index bd446aba64f7..c25c878fd06c 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -156,6 +156,10 @@ static int cs_etm_set_timestamp(struct auxtrace_record *itr,
 	return err;
 }
 
+#define ETM_SET_OPT_CTXTID	(1 << 0)
+#define ETM_SET_OPT_TS		(1 << 1)
+#define ETM_SET_OPT_MASK	(ETM_SET_OPT_CTXTID | ETM_SET_OPT_TS)
+
 static int cs_etm_set_option(struct auxtrace_record *itr,
 			     struct evsel *evsel, u32 option)
 {
@@ -169,17 +173,17 @@ static int cs_etm_set_option(struct auxtrace_record *itr,
 		    !cpu_map__has(online_cpus, i))
 			continue;
 
-		if (option & ETM_OPT_CTXTID) {
+		if (option & ETM_SET_OPT_CTXTID) {
 			err = cs_etm_set_context_id(itr, evsel, i);
 			if (err)
 				goto out;
 		}
-		if (option & ETM_OPT_TS) {
+		if (option & ETM_SET_OPT_TS) {
 			err = cs_etm_set_timestamp(itr, evsel, i);
 			if (err)
 				goto out;
 		}
-		if (option & ~(ETM_OPT_CTXTID | ETM_OPT_TS))
+		if (option & ~(ETM_SET_OPT_MASK))
 			/* Nothing else is currently supported */
 			goto out;
 	}
@@ -406,7 +410,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 		evsel__set_sample_bit(cs_etm_evsel, CPU);
 
 		err = cs_etm_set_option(itr, cs_etm_evsel,
-					ETM_OPT_CTXTID | ETM_OPT_TS);
+					ETM_SET_OPT_CTXTID | ETM_SET_OPT_TS);
 		if (err)
 			goto out;
 	}
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index f744eb5cba88..0b2480cf3e47 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -9,9 +9,7 @@
 #
 0	nospu	restart_syscall			sys_restart_syscall
 1	nospu	exit				sys_exit
-2	32	fork				ppc_fork			sys_fork
-2	64	fork				sys_fork
-2	spu	fork				sys_ni_syscall
+2	nospu	fork				sys_fork
 3	common	read				sys_read
 4	common	write				sys_write
 5	common	open				sys_open			compat_sys_open
@@ -160,9 +158,7 @@
 119	32	sigreturn			sys_sigreturn			compat_sys_sigreturn
 119	64	sigreturn			sys_ni_syscall
 119	spu	sigreturn			sys_ni_syscall
-120	32	clone				ppc_clone			sys_clone
-120	64	clone				sys_clone
-120	spu	clone				sys_ni_syscall
+120	nospu	clone				sys_clone
 121	common	setdomainname			sys_setdomainname
 122	common	uname				sys_newuname
 123	common	modify_ldt			sys_ni_syscall
@@ -244,9 +240,7 @@
 186	spu	sendfile			sys_sendfile64
 187	common	getpmsg				sys_ni_syscall
 188	common 	putpmsg				sys_ni_syscall
-189	32	vfork				ppc_vfork			sys_vfork
-189	64	vfork				sys_vfork
-189	spu	vfork				sys_ni_syscall
+189	nospu	vfork				sys_vfork
 190	common	ugetrlimit			sys_getrlimit			compat_sys_getrlimit
 191	common	readahead			sys_readahead			compat_sys_readahead
 192	32	mmap2				sys_mmap2			compat_sys_mmap2
@@ -322,9 +316,7 @@
 248	32	clock_nanosleep			sys_clock_nanosleep_time32
 248	64	clock_nanosleep			sys_clock_nanosleep
 248	spu	clock_nanosleep			sys_clock_nanosleep
-249	32	swapcontext			ppc_swapcontext			compat_sys_swapcontext
-249	64	swapcontext			sys_swapcontext
-249	spu	swapcontext			sys_ni_syscall
+249	nospu	swapcontext			sys_swapcontext			compat_sys_swapcontext
 250	common	tgkill				sys_tgkill
 251	32	utimes				sys_utimes_time32
 251	64	utimes				sys_utimes
@@ -522,12 +514,11 @@
 432	common	fsmount				sys_fsmount
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
-435	32	clone3				ppc_clone3			sys_clone3
-435	64	clone3				sys_clone3
-435	spu	clone3				sys_ni_syscall
+435	nospu	clone3				sys_clone3
 436	common	close_range			sys_close_range
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
 440	common	process_madvise			sys_process_madvise
 441	common	epoll_pwait2			sys_epoll_pwait2		compat_sys_epoll_pwait2
+442	common	mount_setattr			sys_mount_setattr
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index d443423495e5..3abef2144dac 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -444,3 +444,4 @@
 439  common	faccessat2		sys_faccessat2			sys_faccessat2
 440  common	process_madvise		sys_process_madvise		sys_process_madvise
 441  common	epoll_pwait2		sys_epoll_pwait2		compat_sys_epoll_pwait2
+442  common	mount_setattr		sys_mount_setattr		sys_mount_setattr
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 8cc6642fce7a..5a9f9a7bf07d 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -10,10 +10,11 @@ PERF_HAVE_JITDUMP := 1
 # Syscall table generation
 #
 
-out    := $(OUTPUT)arch/x86/include/generated/asm
-header := $(out)/syscalls_64.c
-sys    := $(srctree)/tools/perf/arch/x86/entry/syscalls
-systbl := $(sys)/syscalltbl.sh
+generated := $(OUTPUT)arch/x86/include/generated
+out       := $(generated)/asm
+header    := $(out)/syscalls_64.c
+sys       := $(srctree)/tools/perf/arch/x86/entry/syscalls
+systbl    := $(sys)/syscalltbl.sh
 
 # Create output directory if not already present
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
@@ -22,6 +23,6 @@ $(header): $(sys)/syscall_64.tbl $(systbl)
 	$(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@
 
 clean::
-	$(call QUIET_CLEAN, x86) $(RM) $(header)
+	$(call QUIET_CLEAN, x86) $(RM) -r $(header) $(generated)
 
 archheaders: $(header)
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 78672124d28b..7bf01cbe582f 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -363,6 +363,7 @@
 439	common	faccessat2		sys_faccessat2
 440	common	process_madvise		sys_process_madvise
 441	common	epoll_pwait2		sys_epoll_pwait2
+442	common	mount_setattr		sys_mount_setattr
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h
index 6a54b94f1c25..0e20f3dc69f3 100644
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
@@ -10,6 +10,7 @@ int test__rdpmc(struct test *test __maybe_unused, int subtest);
 int test__insn_x86(struct test *test __maybe_unused, int subtest);
 int test__intel_pt_pkt_decoder(struct test *test, int subtest);
 int test__bp_modify(struct test *test, int subtest);
+int test__x86_sample_parsing(struct test *test, int subtest);
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build
index 36d4f248b51d..28d793390198 100644
--- a/tools/perf/arch/x86/tests/Build
+++ b/tools/perf/arch/x86/tests/Build
@@ -3,5 +3,6 @@ perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 
 perf-y += arch-tests.o
 perf-y += rdpmc.o
+perf-y += sample-parsing.o
 perf-$(CONFIG_AUXTRACE) += insn-x86.o intel-pt-pkt-decoder-test.o
 perf-$(CONFIG_X86_64) += bp-modify.o
diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c
index bc25d727b4e9..71aa67367ad6 100644
--- a/tools/perf/arch/x86/tests/arch-tests.c
+++ b/tools/perf/arch/x86/tests/arch-tests.c
@@ -30,6 +30,10 @@ struct test arch_tests[] = {
 		.func = test__bp_modify,
 	},
 #endif
+	{
+		.desc = "x86 Sample parsing",
+		.func = test__x86_sample_parsing,
+	},
 	{
 		.func = NULL,
 	},
diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c
index f782ef8c5982..4f75ae990140 100644
--- a/tools/perf/arch/x86/tests/insn-x86.c
+++ b/tools/perf/arch/x86/tests/insn-x86.c
@@ -1,11 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
-#include "../../../../arch/x86/include/asm/insn.h"
 #include <string.h>
 
 #include "debug.h"
 #include "tests/tests.h"
 #include "arch-tests.h"
+#include "../../../../arch/x86/include/asm/insn.h"
 
 #include "intel-pt-decoder/intel-pt-insn-decoder.h"
 
diff --git a/tools/perf/arch/x86/tests/sample-parsing.c b/tools/perf/arch/x86/tests/sample-parsing.c
new file mode 100644
index 000000000000..c92db87e4479
--- /dev/null
+++ b/tools/perf/arch/x86/tests/sample-parsing.c
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <stdbool.h>
+#include <inttypes.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+#include "event.h"
+#include "evsel.h"
+#include "debug.h"
+#include "util/synthetic-events.h"
+
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+#define COMP(m) do {					\
+	if (s1->m != s2->m) {				\
+		pr_debug("Samples differ at '"#m"'\n");	\
+		return false;				\
+	}						\
+} while (0)
+
+static bool samples_same(const struct perf_sample *s1,
+			 const struct perf_sample *s2,
+			 u64 type)
+{
+	if (type & PERF_SAMPLE_WEIGHT_STRUCT)
+		COMP(ins_lat);
+
+	return true;
+}
+
+static int do_test(u64 sample_type)
+{
+	struct evsel evsel = {
+		.needs_swap = false,
+		.core = {
+			. attr = {
+				.sample_type = sample_type,
+				.read_format = 0,
+			},
+		},
+	};
+	union perf_event *event;
+	struct perf_sample sample = {
+		.weight		= 101,
+		.ins_lat        = 102,
+	};
+	struct perf_sample sample_out;
+	size_t i, sz, bufsz;
+	int err, ret = -1;
+
+	sz = perf_event__sample_event_size(&sample, sample_type, 0);
+	bufsz = sz + 4096; /* Add a bit for overrun checking */
+	event = malloc(bufsz);
+	if (!event) {
+		pr_debug("malloc failed\n");
+		return -1;
+	}
+
+	memset(event, 0xff, bufsz);
+	event->header.type = PERF_RECORD_SAMPLE;
+	event->header.misc = 0;
+	event->header.size = sz;
+
+	err = perf_event__synthesize_sample(event, sample_type, 0, &sample);
+	if (err) {
+		pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
+			 "perf_event__synthesize_sample", sample_type, err);
+		goto out_free;
+	}
+
+	/* The data does not contain 0xff so we use that to check the size */
+	for (i = bufsz; i > 0; i--) {
+		if (*(i - 1 + (u8 *)event) != 0xff)
+			break;
+	}
+	if (i != sz) {
+		pr_debug("Event size mismatch: actual %zu vs expected %zu\n",
+			 i, sz);
+		goto out_free;
+	}
+
+	evsel.sample_size = __evsel__sample_size(sample_type);
+
+	err = evsel__parse_sample(&evsel, event, &sample_out);
+	if (err) {
+		pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
+			 "evsel__parse_sample", sample_type, err);
+		goto out_free;
+	}
+
+	if (!samples_same(&sample, &sample_out, sample_type)) {
+		pr_debug("parsing failed for sample_type %#"PRIx64"\n",
+			 sample_type);
+		goto out_free;
+	}
+
+	ret = 0;
+out_free:
+	free(event);
+
+	return ret;
+}
+
+/**
+ * test__x86_sample_parsing - test X86 specific sample parsing
+ *
+ * This function implements a test that synthesizes a sample event, parses it
+ * and then checks that the parsed sample matches the original sample. If the
+ * test passes %0 is returned, otherwise %-1 is returned.
+ *
+ * For now, the PERF_SAMPLE_WEIGHT_STRUCT is the only X86 specific sample type.
+ * The test only checks the PERF_SAMPLE_WEIGHT_STRUCT type.
+ */
+int test__x86_sample_parsing(struct test *test __maybe_unused, int subtest __maybe_unused)
+{
+	return do_test(PERF_SAMPLE_WEIGHT_STRUCT);
+}
diff --git a/tools/perf/arch/x86/util/archinsn.c b/tools/perf/arch/x86/util/archinsn.c
index 3e6791531ca5..34d600c51044 100644
--- a/tools/perf/arch/x86/util/archinsn.c
+++ b/tools/perf/arch/x86/util/archinsn.c
@@ -1,10 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../../../../arch/x86/include/asm/insn.h"
 #include "archinsn.h"
 #include "event.h"
 #include "machine.h"
 #include "thread.h"
 #include "symbol.h"
+#include "../../../../arch/x86/include/asm/insn.h"
 
 void arch_fetch_insn(struct perf_sample *sample,
 		     struct thread *thread,
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 11726ec6285f..20b87e29c96f 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -344,18 +344,22 @@ static void mempol_restore(void)
 
 static void bind_to_memnode(int node)
 {
-	unsigned long nodemask;
+	struct bitmask *node_mask;
 	int ret;
 
 	if (node == NUMA_NO_NODE)
 		return;
 
-	BUG_ON(g->p.nr_nodes > (int)sizeof(nodemask)*8);
-	nodemask = 1L << node;
+	node_mask = numa_allocate_nodemask();
+	BUG_ON(!node_mask);
 
-	ret = set_mempolicy(MPOL_BIND, &nodemask, sizeof(nodemask)*8);
-	dprintf("binding to node %d, mask: %016lx => %d\n", node, nodemask, ret);
+	numa_bitmask_clearall(node_mask);
+	numa_bitmask_setbit(node_mask, node);
 
+	ret = set_mempolicy(MPOL_BIND, node_mask->maskp, node_mask->size + 1);
+	dprintf("binding to node %d, mask: %016lx => %d\n", node, *node_mask->maskp, ret);
+
+	numa_bitmask_free(node_mask);
 	BUG_ON(ret);
 }
 
@@ -876,8 +880,6 @@ static void update_curr_cpu(int task_nr, unsigned long bytes_worked)
 	prctl(0, bytes_worked);
 }
 
-#define MAX_NR_NODES	64
-
 /*
  * Count the number of nodes a process's threads
  * are spread out on.
@@ -888,10 +890,15 @@ static void update_curr_cpu(int task_nr, unsigned long bytes_worked)
  */
 static int count_process_nodes(int process_nr)
 {
-	char node_present[MAX_NR_NODES] = { 0, };
+	char *node_present;
 	int nodes;
 	int n, t;
 
+	node_present = (char *)malloc(g->p.nr_nodes * sizeof(char));
+	BUG_ON(!node_present);
+	for (nodes = 0; nodes < g->p.nr_nodes; nodes++)
+		node_present[nodes] = 0;
+
 	for (t = 0; t < g->p.nr_threads; t++) {
 		struct thread_data *td;
 		int task_nr;
@@ -901,17 +908,20 @@ static int count_process_nodes(int process_nr)
 		td = g->threads + task_nr;
 
 		node = numa_node_of_cpu(td->curr_cpu);
-		if (node < 0) /* curr_cpu was likely still -1 */
+		if (node < 0) /* curr_cpu was likely still -1 */ {
+			free(node_present);
 			return 0;
+		}
 
 		node_present[node] = 1;
 	}
 
 	nodes = 0;
 
-	for (n = 0; n < MAX_NR_NODES; n++)
+	for (n = 0; n < g->p.nr_nodes; n++)
 		nodes += node_present[n];
 
+	free(node_present);
 	return nodes;
 }
 
@@ -980,7 +990,7 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
 {
 	unsigned int loops_done_min, loops_done_max;
 	int process_groups;
-	int nodes[MAX_NR_NODES];
+	int *nodes;
 	int distance;
 	int nr_min;
 	int nr_max;
@@ -994,6 +1004,8 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
 	if (!g->p.show_convergence && !g->p.measure_convergence)
 		return;
 
+	nodes = (int *)malloc(g->p.nr_nodes * sizeof(int));
+	BUG_ON(!nodes);
 	for (node = 0; node < g->p.nr_nodes; node++)
 		nodes[node] = 0;
 
@@ -1035,8 +1047,10 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
 
 	BUG_ON(sum > g->p.nr_tasks);
 
-	if (0 && (sum < g->p.nr_tasks))
+	if (0 && (sum < g->p.nr_tasks)) {
+		free(nodes);
 		return;
+	}
 
 	/*
 	 * Count the number of distinct process groups present
@@ -1088,6 +1102,8 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
 		}
 		tprintf("\n");
 	}
+
+	free(nodes);
 }
 
 static void show_summary(double runtime_ns_max, int l, double *convergence)
@@ -1413,7 +1429,7 @@ static int init(void)
 	g->p.nr_nodes = numa_max_node() + 1;
 
 	/* char array in count_process_nodes(): */
-	BUG_ON(g->p.nr_nodes > MAX_NR_NODES || g->p.nr_nodes < 0);
+	BUG_ON(g->p.nr_nodes < 0);
 
 	if (g->p.show_quiet && !g->p.show_details)
 		g->p.show_details = -1;
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index cecce93ccc63..488f6e6ba1a5 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -309,11 +309,11 @@ int bench_sched_messaging(int argc, const char **argv)
 		       num_groups, num_groups * 2 * num_fds,
 		       thread_mode ? "threads" : "processes");
 		printf(" %14s: %lu.%03lu [sec]\n", "Total time",
-		       diff.tv_sec,
+		       (unsigned long) diff.tv_sec,
 		       (unsigned long) (diff.tv_usec / USEC_PER_MSEC));
 		break;
 	case BENCH_FORMAT_SIMPLE:
-		printf("%lu.%03lu\n", diff.tv_sec,
+		printf("%lu.%03lu\n", (unsigned long) diff.tv_sec,
 		       (unsigned long) (diff.tv_usec / USEC_PER_MSEC));
 		break;
 	default:
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 3c88d1f201f1..a960e7a93aec 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -156,7 +156,7 @@ int bench_sched_pipe(int argc, const char **argv)
 		result_usec += diff.tv_usec;
 
 		printf(" %14s: %lu.%03lu [sec]\n\n", "Total time",
-		       diff.tv_sec,
+		       (unsigned long) diff.tv_sec,
 		       (unsigned long) (diff.tv_usec / USEC_PER_MSEC));
 
 		printf(" %14lf usecs/op\n",
@@ -168,7 +168,7 @@ int bench_sched_pipe(int argc, const char **argv)
 
 	case BENCH_FORMAT_SIMPLE:
 		printf("%lu.%03lu\n",
-		       diff.tv_sec,
+		       (unsigned long) diff.tv_sec,
 		       (unsigned long) (diff.tv_usec / USEC_PER_MSEC));
 		break;
 
diff --git a/tools/perf/bench/syscall.c b/tools/perf/bench/syscall.c
index 5fe621cff8e9..9b751016f4b6 100644
--- a/tools/perf/bench/syscall.c
+++ b/tools/perf/bench/syscall.c
@@ -54,7 +54,7 @@ int bench_syscall_basic(int argc, const char **argv)
 		result_usec += diff.tv_usec;
 
 		printf(" %14s: %lu.%03lu [sec]\n\n", "Total time",
-		       diff.tv_sec,
+		       (unsigned long) diff.tv_sec,
 		       (unsigned long) (diff.tv_usec/1000));
 
 		printf(" %14lf usecs/op\n",
@@ -66,7 +66,7 @@ int bench_syscall_basic(int argc, const char **argv)
 
 	case BENCH_FORMAT_SIMPLE:
 		printf("%lu.%03lu\n",
-		       diff.tv_sec,
+		       (unsigned long) diff.tv_sec,
 		       (unsigned long) (diff.tv_usec / 1000));
 		break;
 
diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c
index 617feaf020f6..ace8772a4f03 100644
--- a/tools/perf/builtin-daemon.c
+++ b/tools/perf/builtin-daemon.c
@@ -161,7 +161,7 @@ static int session_config(struct daemon *daemon, const char *var, const char *va
 	struct daemon_session *session;
 	char name[100];
 
-	if (get_session_name(var, name, sizeof(name)))
+	if (get_session_name(var, name, sizeof(name) - 1))
 		return -EINVAL;
 
 	var = strchr(var, '.');
@@ -373,12 +373,12 @@ static int daemon_session__run(struct daemon_session *session,
 	dup2(fd, 2);
 	close(fd);
 
-	if (mkfifo(SESSION_CONTROL, O_RDWR) && errno != EEXIST) {
+	if (mkfifo(SESSION_CONTROL, 0600) && errno != EEXIST) {
 		perror("failed: create control fifo");
 		return -1;
 	}
 
-	if (mkfifo(SESSION_ACK, O_RDWR) && errno != EEXIST) {
+	if (mkfifo(SESSION_ACK, 0600) && errno != EEXIST) {
 		perror("failed: create ack fifo");
 		return -1;
 	}
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 8f6c784ce629..878e04b1fab7 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -1236,7 +1236,8 @@ static int __cmd_diff(void)
 
  out_delete:
 	data__for_each_file(i, d) {
-		perf_session__delete(d->session);
+		if (!IS_ERR(d->session))
+			perf_session__delete(d->session);
 		data__free(d);
 	}
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 85b6a46e85b6..7ec18ff57fc4 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -3964,9 +3964,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 
 	evlist__config(evlist, &trace->opts, &callchain_param);
 
-	signal(SIGCHLD, sig_handler);
-	signal(SIGINT, sig_handler);
-
 	if (forks) {
 		err = evlist__prepare_workload(evlist, &trace->opts.target, argv, false, NULL);
 		if (err < 0) {
@@ -4827,6 +4824,8 @@ int cmd_trace(int argc, const char **argv)
 
 	signal(SIGSEGV, sighandler_dump_stack);
 	signal(SIGFPE, sighandler_dump_stack);
+	signal(SIGCHLD, sig_handler);
+	signal(SIGINT, sig_handler);
 
 	trace.evlist = evlist__new();
 	trace.sctbl = syscalltbl__new();
diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh
index 0cfb3e2cefef..133f0eddbcc4 100644
--- a/tools/perf/perf-archive.sh
+++ b/tools/perf/perf-archive.sh
@@ -20,9 +20,8 @@ else
 fi
 
 BUILDIDS=$(mktemp /tmp/perf-archive-buildids.XXXXXX)
-NOBUILDID=0000000000000000000000000000000000000000
 
-perf buildid-list -i $PERF_DATA --with-hits | grep -v "^$NOBUILDID " > $BUILDIDS
+perf buildid-list -i $PERF_DATA --with-hits | grep -v "^ " > $BUILDIDS
 if [ ! -s $BUILDIDS ] ; then
 	echo "perf archive: no build-ids found"
 	rm $BUILDIDS || true
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index ec972e0892ab..dd39ce9b0277 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -182,14 +182,20 @@ int test__attr(struct test *test __maybe_unused, int subtest __maybe_unused)
 	struct stat st;
 	char path_perf[PATH_MAX];
 	char path_dir[PATH_MAX];
+	char *exec_path;
 
 	/* First try development tree tests. */
 	if (!lstat("./tests", &st))
 		return run_dir("./tests", "./perf");
 
+	exec_path = get_argv_exec_path();
+	if (exec_path == NULL)
+		return -1;
+
 	/* Then installed path. */
-	snprintf(path_dir,  PATH_MAX, "%s/tests", get_argv_exec_path());
+	snprintf(path_dir,  PATH_MAX, "%s/tests", exec_path);
 	snprintf(path_perf, PATH_MAX, "%s/perf", BINDIR);
+	free(exec_path);
 
 	if (!lstat(path_dir, &st) &&
 	    !lstat(path_perf, &st))
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 280f0348a09c..2fdc7b2f996e 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -706,13 +706,9 @@ static int do_test_code_reading(bool try_kcore)
 out_put:
 	thread__put(thread);
 out_err:
-
-	if (evlist) {
-		evlist__delete(evlist);
-	} else {
-		perf_cpu_map__put(cpus);
-		perf_thread_map__put(threads);
-	}
+	evlist__delete(evlist);
+	perf_cpu_map__put(cpus);
+	perf_thread_map__put(threads);
 	machine__delete_threads(machine);
 	machine__delete(machine);
 
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index 29c793ac7d10..0472b110fe65 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -106,6 +106,8 @@ static int cpu_map_print(const char *str)
 		return -1;
 
 	cpu_map__snprint(map, buf, sizeof(buf));
+	perf_cpu_map__put(map);
+
 	return !strcmp(buf, str);
 }
 
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index e6f1b2a38e03..a0438b0f0805 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -154,10 +154,9 @@ int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_un
 	if (evlist) {
 		evlist__disable(evlist);
 		evlist__delete(evlist);
-	} else {
-		perf_cpu_map__put(cpus);
-		perf_thread_map__put(threads);
 	}
+	perf_cpu_map__put(cpus);
+	perf_thread_map__put(threads);
 
 	return err;
 }
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 57093aeacc6f..73ae8f7aa066 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -158,8 +158,6 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 
 out_delete_evlist:
 	evlist__delete(evlist);
-	cpus	= NULL;
-	threads = NULL;
 out_free_cpus:
 	perf_cpu_map__put(cpus);
 out_free_threads:
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 7cff02664d0e..680c3cffb128 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -167,6 +167,8 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 
 out_err:
 	evlist__delete(evlist);
+	perf_cpu_map__put(cpus);
+	perf_thread_map__put(threads);
 	return err;
 }
 
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 0dbe3aa99853..8fd8a4ef97da 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -129,9 +129,6 @@ static bool samples_same(const struct perf_sample *s1,
 	if (type & PERF_SAMPLE_WEIGHT)
 		COMP(weight);
 
-	if (type & PERF_SAMPLE_WEIGHT_STRUCT)
-		COMP(ins_lat);
-
 	if (type & PERF_SAMPLE_DATA_SRC)
 		COMP(data_src);
 
@@ -245,7 +242,6 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 		.cgroup		= 114,
 		.data_page_size = 115,
 		.code_page_size = 116,
-		.ins_lat        = 117,
 		.aux_sample	= {
 			.size	= sizeof(aux_data),
 			.data	= (void *)aux_data,
diff --git a/tools/perf/tests/shell/daemon.sh b/tools/perf/tests/shell/daemon.sh
index e5b824dd08d9..5ad3ca8d681b 100755
--- a/tools/perf/tests/shell/daemon.sh
+++ b/tools/perf/tests/shell/daemon.sh
@@ -140,10 +140,10 @@ test_list()
 base=BASE
 
 [session-size]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
 
 [session-time]
-run = -e task-clock
+run = -e task-clock -m 1 sleep 10
 EOF
 
 	sed -i -e "s|BASE|${base}|" ${config}
@@ -159,14 +159,14 @@ EOF
 	# check 1st session
 	# pid:size:-e cpu-clock:base/size:base/size/output:base/size/control:base/size/ack:0
 	local line=`perf daemon --config ${config} -x: | head -2 | tail -1`
-	check_line_other "${line}" size "-e cpu-clock" ${base}/session-size \
+	check_line_other "${line}" size "-e cpu-clock -m 1 sleep 10" ${base}/session-size \
 			 ${base}/session-size/output ${base}/session-size/control \
 			 ${base}/session-size/ack "0"
 
 	# check 2nd session
 	# pid:time:-e task-clock:base/time:base/time/output:base/time/control:base/time/ack:0
 	local line=`perf daemon --config ${config} -x: | head -3 | tail -1`
-	check_line_other "${line}" time "-e task-clock" ${base}/session-time \
+	check_line_other "${line}" time "-e task-clock -m 1 sleep 10" ${base}/session-time \
 			 ${base}/session-time/output ${base}/session-time/control \
 			 ${base}/session-time/ack "0"
 
@@ -190,10 +190,10 @@ test_reconfig()
 base=BASE
 
 [session-size]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
 
 [session-time]
-run = -e task-clock
+run = -e task-clock -m 1 sleep 10
 EOF
 
 	sed -i -e "s|BASE|${base}|" ${config}
@@ -204,7 +204,7 @@ EOF
 	# check 2nd session
 	# pid:time:-e task-clock:base/time:base/time/output:base/time/control:base/time/ack:0
 	local line=`perf daemon --config ${config} -x: | head -3 | tail -1`
-	check_line_other "${line}" time "-e task-clock" ${base}/session-time \
+	check_line_other "${line}" time "-e task-clock -m 1 sleep 10" ${base}/session-time \
 			 ${base}/session-time/output ${base}/session-time/control ${base}/session-time/ack "0"
 	local pid=`echo "${line}" | awk 'BEGIN { FS = ":" } ; { print $1 }'`
 
@@ -215,10 +215,10 @@ EOF
 base=BASE
 
 [session-size]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
 
 [session-time]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
 EOF
 
 	# TEST 1 - change config
@@ -238,7 +238,7 @@ EOF
 	# check reconfigured 2nd session
 	# pid:time:-e task-clock:base/time:base/time/output:base/time/control:base/time/ack:0
 	local line=`perf daemon --config ${config} -x: | head -3 | tail -1`
-	check_line_other "${line}" time "-e cpu-clock" ${base}/session-time \
+	check_line_other "${line}" time "-e cpu-clock -m 1 sleep 10" ${base}/session-time \
 			 ${base}/session-time/output ${base}/session-time/control ${base}/session-time/ack "0"
 
 	# TEST 2 - empty config
@@ -309,10 +309,10 @@ test_stop()
 base=BASE
 
 [session-size]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
 
 [session-time]
-run = -e task-clock
+run = -e task-clock -m 1 sleep 10
 EOF
 
 	sed -i -e "s|BASE|${base}|" ${config}
@@ -361,7 +361,7 @@ test_signal()
 base=BASE
 
 [session-test]
-run = -e cpu-clock --switch-output
+run = -e cpu-clock --switch-output -m 1 sleep 10
 EOF
 
 	sed -i -e "s|BASE|${base}|" ${config}
@@ -400,10 +400,10 @@ test_ping()
 base=BASE
 
 [session-size]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
 
 [session-time]
-run = -e task-clock
+run = -e task-clock -m 1 sleep 10
 EOF
 
 	sed -i -e "s|BASE|${base}|" ${config}
@@ -439,7 +439,7 @@ test_lock()
 base=BASE
 
 [session-size]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
 EOF
 
 	sed -i -e "s|BASE|${base}|" ${config}
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index a49c9e23053b..74988846be1d 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -42,8 +42,8 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		.disabled = 1,
 		.freq = 1,
 	};
-	struct perf_cpu_map *cpus;
-	struct perf_thread_map *threads;
+	struct perf_cpu_map *cpus = NULL;
+	struct perf_thread_map *threads = NULL;
 	struct mmap *md;
 
 	attr.sample_freq = 500;
@@ -66,14 +66,11 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	if (!cpus || !threads) {
 		err = -ENOMEM;
 		pr_debug("Not enough memory to create thread/cpu maps\n");
-		goto out_free_maps;
+		goto out_delete_evlist;
 	}
 
 	perf_evlist__set_maps(&evlist->core, cpus, threads);
 
-	cpus	= NULL;
-	threads = NULL;
-
 	if (evlist__open(evlist)) {
 		const char *knob = "/proc/sys/kernel/perf_event_max_sample_rate";
 
@@ -129,10 +126,9 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		err = -1;
 	}
 
-out_free_maps:
+out_delete_evlist:
 	perf_cpu_map__put(cpus);
 	perf_thread_map__put(threads);
-out_delete_evlist:
 	evlist__delete(evlist);
 	return err;
 }
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 15a2ab765d89..3ebaa758df77 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -574,10 +574,9 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_
 	if (evlist) {
 		evlist__disable(evlist);
 		evlist__delete(evlist);
-	} else {
-		perf_cpu_map__put(cpus);
-		perf_thread_map__put(threads);
 	}
+	perf_cpu_map__put(cpus);
+	perf_thread_map__put(threads);
 
 	return err;
 
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index bbf94e4aa145..4c2969db59b0 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -75,14 +75,11 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 	if (!cpus || !threads) {
 		err = -ENOMEM;
 		pr_debug("Not enough memory to create thread/cpu maps\n");
-		goto out_free_maps;
+		goto out_delete_evlist;
 	}
 
 	perf_evlist__set_maps(&evlist->core, cpus, threads);
 
-	cpus	= NULL;
-	threads = NULL;
-
 	err = evlist__prepare_workload(evlist, &target, argv, false, workload_exec_failed_signal);
 	if (err < 0) {
 		pr_debug("Couldn't run the workload!\n");
@@ -137,7 +134,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 		if (retry_count++ > 1000) {
 			pr_debug("Failed after retrying 1000 times\n");
 			err = -1;
-			goto out_free_maps;
+			goto out_delete_evlist;
 		}
 
 		goto retry;
@@ -148,10 +145,9 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 		err = -1;
 	}
 
-out_free_maps:
+out_delete_evlist:
 	perf_cpu_map__put(cpus);
 	perf_thread_map__put(threads);
-out_delete_evlist:
 	evlist__delete(evlist);
 	return err;
 }
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index 28f51c4bd373..d1e208b4a571 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -102,6 +102,7 @@ int test__thread_map_synthesize(struct test *test __maybe_unused, int subtest __
 	TEST_ASSERT_VAL("failed to synthesize map",
 		!perf_event__synthesize_thread_map2(NULL, threads, process_event, NULL));
 
+	perf_thread_map__put(threads);
 	return 0;
 }
 
@@ -109,12 +110,12 @@ int test__thread_map_remove(struct test *test __maybe_unused, int subtest __mayb
 {
 	struct perf_thread_map *threads;
 	char *str;
-	int i;
 
 	TEST_ASSERT_VAL("failed to allocate map string",
 			asprintf(&str, "%d,%d", getpid(), getppid()) >= 0);
 
 	threads = thread_map__new_str(str, NULL, 0, false);
+	free(str);
 
 	TEST_ASSERT_VAL("failed to allocate thread_map",
 			threads);
@@ -141,9 +142,6 @@ int test__thread_map_remove(struct test *test __maybe_unused, int subtest __mayb
 	TEST_ASSERT_VAL("failed to not remove thread",
 			thread_map__remove(threads, 0));
 
-	for (i = 0; i < threads->nr; i++)
-		zfree(&threads->map[i].comm);
-
-	free(threads);
+	perf_thread_map__put(threads);
 	return 0;
 }
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 5121b4db66fe..882cd1f721d9 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1306,6 +1306,7 @@ void evlist__close(struct evlist *evlist)
 		perf_evsel__free_fd(&evsel->core);
 		perf_evsel__free_id(&evsel->core);
 	}
+	perf_evlist__reset_id_hash(&evlist->core);
 }
 
 static int evlist__create_syswide_maps(struct evlist *evlist)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1bf76864c4f2..7ecbc8e2fbfa 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -46,6 +46,7 @@
 #include "string2.h"
 #include "memswap.h"
 #include "util.h"
+#include "hashmap.h"
 #include "../perf-sys.h"
 #include "util/parse-branch-options.h"
 #include <internal/xyarray.h>
@@ -1390,7 +1391,9 @@ void evsel__exit(struct evsel *evsel)
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
 	zfree(&evsel->pmu_name);
-	zfree(&evsel->per_pkg_mask);
+	evsel__zero_per_pkg(evsel);
+	hashmap__free(evsel->per_pkg_mask);
+	evsel->per_pkg_mask = NULL;
 	zfree(&evsel->metric_events);
 	perf_evsel__object.fini(evsel);
 }
@@ -2781,3 +2784,16 @@ int evsel__store_ids(struct evsel *evsel, struct evlist *evlist)
 
 	return store_evsel_ids(evsel, evlist);
 }
+
+void evsel__zero_per_pkg(struct evsel *evsel)
+{
+	struct hashmap_entry *cur;
+	size_t bkt;
+
+	if (evsel->per_pkg_mask) {
+		hashmap__for_each_entry(evsel->per_pkg_mask, cur, bkt)
+			free((char *)cur->key);
+
+		hashmap__clear(evsel->per_pkg_mask);
+	}
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4e8e49fb7e9d..6026487353dd 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -19,6 +19,7 @@ struct perf_stat_evsel;
 union perf_event;
 struct bpf_counter_ops;
 struct target;
+struct hashmap;
 
 typedef int (evsel__sb_cb_t)(union perf_event *event, void *data);
 
@@ -112,7 +113,7 @@ struct evsel {
 	bool			merged_stat;
 	bool			reset_group;
 	bool			errored;
-	unsigned long		*per_pkg_mask;
+	struct hashmap		*per_pkg_mask;
 	struct evsel		*leader;
 	struct list_head	config_terms;
 	int			err;
@@ -433,4 +434,5 @@ struct perf_env *evsel__env(struct evsel *evsel);
 
 int evsel__store_ids(struct evsel *evsel, struct evlist *evlist);
 
+void evsel__zero_per_pkg(struct evsel *evsel);
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 4fe9e2a54346..20effdff76ce 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1618,8 +1618,8 @@ static void print_clock_data(struct feat_fd *ff, FILE *fp)
 
 	fprintf(fp, "# clockid: %s (%u)\n", clockid_name(clockid), clockid);
 	fprintf(fp, "# reference time: %s = %ld.%06d (TOD) = %ld.%09ld (%s)\n",
-		    tstr, tod_ns.tv_sec, (int) tod_ns.tv_usec,
-		    clockid_ns.tv_sec, clockid_ns.tv_nsec,
+		    tstr, (long) tod_ns.tv_sec, (int) tod_ns.tv_usec,
+		    (long) clockid_ns.tv_sec, clockid_ns.tv_nsec,
 		    clockid_name(clockid));
 }
 
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 692e56dc832e..fbc40a2c17d4 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -77,8 +77,7 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
 	if (strstarts(filename, "/system/lib/")) {
 		char *ndk, *app;
 		const char *arch;
-		size_t ndk_length;
-		size_t app_length;
+		int ndk_length, app_length;
 
 		ndk = getenv("NDK_ROOT");
 		app = getenv("APP_PLATFORM");
@@ -106,8 +105,8 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
 		if (new_length > PATH_MAX)
 			return false;
 		snprintf(newfilename, new_length,
-			"%s/platforms/%s/arch-%s/usr/lib/%s",
-			ndk, app, arch, libname);
+			"%.*s/platforms/%.*s/arch-%s/usr/lib/%s",
+			ndk_length, ndk, app_length, app, arch, libname);
 
 		return true;
 	}
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index d5b6aff82f21..d57ac86ce7ca 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -89,6 +89,7 @@ static void inc_group_count(struct list_head *list,
 %type <str> PE_EVENT_NAME
 %type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE
 %type <str> PE_DRV_CFG_TERM
+%type <str> event_pmu_name
 %destructor { free ($$); } <str>
 %type <term> event_term
 %destructor { parse_events_term__delete ($$); } <term>
@@ -272,8 +273,11 @@ event_def: event_pmu |
 	   event_legacy_raw sep_dc |
 	   event_bpf_file
 
+event_pmu_name:
+PE_NAME | PE_PMU_EVENT_PRE
+
 event_pmu:
-PE_NAME opt_pmu_config
+event_pmu_name opt_pmu_config
 {
 	struct parse_events_state *parse_state = _parse_state;
 	struct parse_events_error *error = parse_state->error;
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 71b753523fac..845dd46e3c61 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -36,3 +36,4 @@ util/symbol_fprintf.c
 util/units.c
 util/affinity.c
 util/rwsem.c
+util/hashmap.c
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 0d5ad42812b9..552b590485bf 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -3140,7 +3140,7 @@ int output_field_add(struct perf_hpp_list *list, char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		if (sort__mode != SORT_MODE__MEMORY)
+		if (sort__mode != SORT_MODE__BRANCH)
 			return -EINVAL;
 
 		return __sort_dimension__add_output(list, sd);
@@ -3152,7 +3152,7 @@ int output_field_add(struct perf_hpp_list *list, char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		if (sort__mode != SORT_MODE__BRANCH)
+		if (sort__mode != SORT_MODE__MEMORY)
 			return -EINVAL;
 
 		return __sort_dimension__add_output(list, sd);
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index cce7a76d6473..7f09cdaf5b60 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -983,7 +983,7 @@ static void print_interval(struct perf_stat_config *config,
 	if (config->interval_clear)
 		puts(CONSOLE_CLEAR);
 
-	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, config->csv_sep);
+	sprintf(prefix, "%6lu.%09lu%s", (unsigned long) ts->tv_sec, ts->tv_nsec, config->csv_sep);
 
 	if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) {
 		switch (config->aggr_mode) {
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 5d8af29447f4..c400f8dde017 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -13,6 +13,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "thread_map.h"
+#include "hashmap.h"
 #include <linux/zalloc.h>
 
 void update_stats(struct stats *stats, u64 val)
@@ -277,18 +278,29 @@ void evlist__save_aggr_prev_raw_counts(struct evlist *evlist)
 	}
 }
 
-static void zero_per_pkg(struct evsel *counter)
+static size_t pkg_id_hash(const void *__key, void *ctx __maybe_unused)
 {
-	if (counter->per_pkg_mask)
-		memset(counter->per_pkg_mask, 0, cpu__max_cpu());
+	uint64_t *key = (uint64_t *) __key;
+
+	return *key & 0xffffffff;
+}
+
+static bool pkg_id_equal(const void *__key1, const void *__key2,
+			 void *ctx __maybe_unused)
+{
+	uint64_t *key1 = (uint64_t *) __key1;
+	uint64_t *key2 = (uint64_t *) __key2;
+
+	return *key1 == *key2;
 }
 
 static int check_per_pkg(struct evsel *counter,
 			 struct perf_counts_values *vals, int cpu, bool *skip)
 {
-	unsigned long *mask = counter->per_pkg_mask;
+	struct hashmap *mask = counter->per_pkg_mask;
 	struct perf_cpu_map *cpus = evsel__cpus(counter);
-	int s;
+	int s, d, ret = 0;
+	uint64_t *key;
 
 	*skip = false;
 
@@ -299,7 +311,7 @@ static int check_per_pkg(struct evsel *counter,
 		return 0;
 
 	if (!mask) {
-		mask = zalloc(cpu__max_cpu());
+		mask = hashmap__new(pkg_id_hash, pkg_id_equal, NULL);
 		if (!mask)
 			return -ENOMEM;
 
@@ -321,8 +333,25 @@ static int check_per_pkg(struct evsel *counter,
 	if (s < 0)
 		return -1;
 
-	*skip = test_and_set_bit(s, mask) == 1;
-	return 0;
+	/*
+	 * On multi-die system, die_id > 0. On no-die system, die_id = 0.
+	 * We use hashmap(socket, die) to check the used socket+die pair.
+	 */
+	d = cpu_map__get_die(cpus, cpu, NULL).die;
+	if (d < 0)
+		return -1;
+
+	key = malloc(sizeof(*key));
+	if (!key)
+		return -ENOMEM;
+
+	*key = (uint64_t)d << 32 | s;
+	if (hashmap__find(mask, (void *)key, NULL))
+		*skip = true;
+	else
+		ret = hashmap__add(mask, (void *)key, (void *)1);
+
+	return ret;
 }
 
 static int
@@ -422,7 +451,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	}
 
 	if (counter->per_pkg)
-		zero_per_pkg(counter);
+		evsel__zero_per_pkg(counter);
 
 	ret = process_counter_maps(config, counter);
 	if (ret)
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index f507dff713c9..8a01af783310 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -361,6 +361,7 @@ static int read_saved_cmdline(struct tep_handle *pevent)
 		pr_debug("error reading saved cmdlines\n");
 		goto out;
 	}
+	buf[ret] = '\0';
 
 	parse_saved_cmdline(pevent, buf, size);
 	ret = 0;